diff --git a/Documentation/ABI/testing/sysfs-ata b/Documentation/ABI/testing/sysfs-ata
new file mode 100644
index 0000000..0a93215
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-ata
@@ -0,0 +1,99 @@
+What:		/sys/class/ata_...
+Date:		August 2008
+Contact:	Gwendal Grignou<gwendal@google.com>
+Description:
+
+Provide a place in sysfs for storing the ATA topology of the system.  This allows
+retrieving various information about ATA objects.
+
+Files under /sys/class/ata_port
+-------------------------------
+
+	For each port, a directory ataX is created where X is the ata_port_id of
+	the port. The device parent is the ata host device.
+
+idle_irq (read)
+
+	Number of IRQ received by the port while idle [some ata HBA only].
+
+nr_pmp_links (read)
+
+	If a SATA Port Multiplier (PM) is connected, number of link behind it.
+
+Files under /sys/class/ata_link
+-------------------------------
+
+	Behind each port, there is a ata_link. If there is a SATA PM in the
+	topology, 15 ata_link objects are created.
+
+	If a link is behind a port, the directory name is linkX, where X is
+	ata_port_id of the port.
+	If a link is behind a PM, its name is linkX.Y where X is ata_port_id
+	of the parent port and Y the PM port.
+
+hw_sata_spd_limit
+
+	Maximum speed supported by the connected SATA device.
+
+sata_spd_limit
+
+	Maximum speed imposed by libata.
+
+sata_spd
+
+	Current speed of the link [1.5, 3Gps,...].
+
+Files under /sys/class/ata_device
+---------------------------------
+
+	Behind each link, up to two ata device are created.
+	The name of the directory is devX[.Y].Z where:
+	- X is ata_port_id of the port where the device is connected,
+	- Y the port of the PM if any, and
+	- Z the device id: for PATA, there is usually 2 devices [0,1],
+	only 1 for SATA.
+
+class
+	Device class. Can be "ata" for disk, "atapi" for packet device,
+	"pmp" for PM, or "none" if no device was found behind the link.
+
+dma_mode
+
+	Transfer modes supported by the device when in DMA mode.
+	Mostly used by PATA device.
+
+pio_mode
+
+	Transfer modes supported by the device when in PIO mode.
+	Mostly used by PATA device.
+
+xfer_mode
+
+	Current transfer mode.
+
+id
+
+	Cached result of IDENTIFY command, as described in ATA8 7.16 and 7.17.
+	Only valid if the device is not a PM.
+
+gscr
+
+	Cached result of the dump of PM GSCR register.
+	Valid registers are:
+	0: 	SATA_PMP_GSCR_PROD_ID,
+	1: 	SATA_PMP_GSCR_REV,
+	2: 	SATA_PMP_GSCR_PORT_INFO,
+	32:	SATA_PMP_GSCR_ERROR,
+	33:	SATA_PMP_GSCR_ERROR_EN,
+	64:	SATA_PMP_GSCR_FEAT,
+	96:	SATA_PMP_GSCR_FEAT_EN,
+	130:	SATA_PMP_GSCR_SII_GPIO
+	Only valid if the device is a PM.
+
+spdn_cnt
+
+	Number of time libata decided to lower the speed of link due to errors.
+
+ering
+
+	Formatted output of the error ring of the device.
diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index 6123c52..7628cd1 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -77,3 +77,91 @@
 		devices this attribute is set to "enabled" by bus type code or
 		device drivers and in that cases it should be safe to leave the
 		default value.
+
+What:		/sys/devices/.../power/wakeup_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_count attribute contains the number
+		of signaled wakeup events associated with the device.  This
+		attribute is read-only.  If the device is not enabled to wake up
+		the system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_active_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_active_count attribute contains the
+		number of times the processing of wakeup events associated with
+		the device was completed (at the kernel level).  This attribute
+		is read-only.  If the device is not enabled to wake up the
+		system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_hit_count
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_hit_count attribute contains the
+		number of times the processing of a wakeup event associated with
+		the device might prevent the system from entering a sleep state.
+		This attribute is read-only.  If the device is not enabled to
+		wake up the system from sleep states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_active
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_active attribute contains either 1,
+		or 0, depending on whether or not a wakeup event associated with
+		the device is being processed (1).  This attribute is read-only.
+		If the device is not enabled to wake up the system from sleep
+		states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_total_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_total_time_ms attribute contains
+		the total time of processing wakeup events associated with the
+		device, in milliseconds.  This attribute is read-only.  If the
+		device is not enabled to wake up the system from sleep states,
+		this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_max_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_max_time_ms attribute contains
+		the maximum time of processing a single wakeup event associated
+		with the device, in milliseconds.  This attribute is read-only.
+		If the device is not enabled to wake up the system from sleep
+		states, this attribute is empty.
+
+What:		/sys/devices/.../power/wakeup_last_time_ms
+Date:		September 2010
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_last_time_ms attribute contains
+		the value of the monotonic clock corresponding to the time of
+		signaling the last wakeup event associated with the device, in
+		milliseconds.  This attribute is read-only.  If the device is
+		not enabled to wake up the system from sleep states, this
+		attribute is empty.
+
+What:		/sys/devices/.../power/autosuspend_delay_ms
+Date:		September 2010
+Contact:	Alan Stern <stern@rowland.harvard.edu>
+Description:
+		The /sys/devices/.../power/autosuspend_delay_ms attribute
+		contains the autosuspend delay value (in milliseconds).  Some
+		drivers do not want their device to suspend as soon as it
+		becomes idle at run time; they want the device to remain
+		inactive for a certain minimum period of time first.  That
+		period is called the autosuspend delay.  Negative values will
+		prevent the device from being suspended at run time (similar
+		to writing "on" to the power/control attribute).  Values >=
+		1000 will cause the autosuspend timer expiration to be rounded
+		up to the nearest second.
+
+		Not all drivers support this attribute.  If it isn't supported,
+		attempts to read or write it will yield I/O errors.
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 2875f1f..194ca44 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -99,9 +99,38 @@
 
 		dmesg -s 1000000 | grep 'hash matches'
 
+		If you do not get any matches (or they appear to be false
+		positives), it is possible that the last PM event point
+		referred to a device created by a loadable kernel module.  In
+		this case cat /sys/power/pm_trace_dev_match (see below) after
+		your system is started up and the kernel modules are loaded.
+
 		CAUTION: Using it will cause your machine's real-time (CMOS)
 		clock to be set to a random invalid time after a resume.
 
+What;		/sys/power/pm_trace_dev_match
+Date:		October 2010
+Contact:	James Hogan <james@albanarts.com>
+Description:
+		The /sys/power/pm_trace_dev_match file contains the name of the
+		device associated with the last PM event point saved in the RTC
+		across reboots when pm_trace has been used.  More precisely it
+		contains the list of current devices (including those
+		registered by loadable kernel modules since boot) which match
+		the device hash in the RTC at boot, with a newline after each
+		one.
+
+		The advantage of this file over the hash matches printed to the
+		kernel log (see /sys/power/pm_trace), is that it includes
+		devices created after boot by loadable kernel modules.
+
+		Due to the small hash size necessary to fit in the RTC, it is
+		possible that more than one device matches the hash, in which
+		case further investigation is required to determine which
+		device is causing the problem.  Note that genuine RTC clock
+		values (such as when pm_trace has not been used), can still
+		match a device and output it's name here.
+
 What:		/sys/power/pm_async
 Date:		January 2009
 Contact:	Rafael J. Wysocki <rjw@sisk.pl>
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 910c923..2861055 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -136,6 +136,7 @@
 #ifdef CONFIG_COMPAT
 		.compat_ioctl = i915_compat_ioctl,
 #endif
+		.llseek = noop_llseek,
 		},
 	.pci_driver = {
 		.name = DRIVER_NAME,
diff --git a/Documentation/DocBook/genericirq.tmpl b/Documentation/DocBook/genericirq.tmpl
index 1448b33..fb10fd0 100644
--- a/Documentation/DocBook/genericirq.tmpl
+++ b/Documentation/DocBook/genericirq.tmpl
@@ -28,7 +28,7 @@
   </authorgroup>
 
   <copyright>
-   <year>2005-2006</year>
+   <year>2005-2010</year>
    <holder>Thomas Gleixner</holder>
   </copyright>
   <copyright>
@@ -100,6 +100,10 @@
 	  <listitem><para>Edge type</para></listitem>
 	  <listitem><para>Simple type</para></listitem>
 	</itemizedlist>
+	During the implementation we identified another type:
+	<itemizedlist>
+	  <listitem><para>Fast EOI type</para></listitem>
+	</itemizedlist>
 	In the SMP world of the __do_IRQ() super-handler another type
 	was identified:
 	<itemizedlist>
@@ -153,6 +157,7 @@
 	is still available. This leads to a kind of duality for the time
 	being. Over time the new model should be used in more and more
 	architectures, as it enables smaller and cleaner IRQ subsystems.
+	It's deprecated for three years now and about to be removed.
 	</para>
   </chapter>
   <chapter id="bugs">
@@ -217,6 +222,7 @@
 	  <itemizedlist>
 	  <listitem><para>handle_level_irq</para></listitem>
 	  <listitem><para>handle_edge_irq</para></listitem>
+	  <listitem><para>handle_fasteoi_irq</para></listitem>
 	  <listitem><para>handle_simple_irq</para></listitem>
 	  <listitem><para>handle_percpu_irq</para></listitem>
 	  </itemizedlist>
@@ -233,33 +239,33 @@
 		are used by the default flow implementations.
 		The following helper functions are implemented (simplified excerpt):
 		<programlisting>
-default_enable(irq)
+default_enable(struct irq_data *data)
 {
-	desc->chip->unmask(irq);
+	desc->chip->irq_unmask(data);
 }
 
-default_disable(irq)
+default_disable(struct irq_data *data)
 {
-	if (!delay_disable(irq))
-		desc->chip->mask(irq);
+	if (!delay_disable(data))
+		desc->chip->irq_mask(data);
 }
 
-default_ack(irq)
+default_ack(struct irq_data *data)
 {
-	chip->ack(irq);
+	chip->irq_ack(data);
 }
 
-default_mask_ack(irq)
+default_mask_ack(struct irq_data *data)
 {
-	if (chip->mask_ack) {
-		chip->mask_ack(irq);
+	if (chip->irq_mask_ack) {
+		chip->irq_mask_ack(data);
 	} else {
-		chip->mask(irq);
-		chip->ack(irq);
+		chip->irq_mask(data);
+		chip->irq_ack(data);
 	}
 }
 
-noop(irq)
+noop(struct irq_data *data))
 {
 }
 
@@ -278,12 +284,27 @@
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-desc->chip->start();
+desc->chip->irq_mask();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+desc->chip->irq_unmask();
 		</programlisting>
 		</para>
-   	    </sect3>
+	    </sect3>
+	    <sect3 id="Default_FASTEOI_IRQ_flow_handler">
+		<title>Default Fast EOI IRQ flow handler</title>
+		<para>
+		handle_fasteoi_irq provides a generic implementation
+		for interrupts, which only need an EOI at the end of
+		the handler
+		</para>
+		<para>
+		The following control flow is implemented (simplified excerpt):
+		<programlisting>
+handle_IRQ_event(desc->action);
+desc->chip->irq_eoi();
+		</programlisting>
+		</para>
+	    </sect3>
 	    <sect3 id="Default_Edge_IRQ_flow_handler">
 	 	<title>Default Edge IRQ flow handler</title>
 		<para>
@@ -294,20 +315,19 @@
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
 if (desc->status &amp; running) {
-	desc->chip->hold();
+	desc->chip->irq_mask();
 	desc->status |= pending | masked;
 	return;
 }
-desc->chip->start();
+desc->chip->irq_ack();
 desc->status |= running;
 do {
 	if (desc->status &amp; masked)
-		desc->chip->enable();
+		desc->chip->irq_unmask();
 	desc->status &amp;= ~pending;
 	handle_IRQ_event(desc->action);
 } while (status &amp; pending);
 desc->status &amp;= ~running;
-desc->chip->end();
 		</programlisting>
 		</para>
    	    </sect3>
@@ -342,9 +362,9 @@
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-desc->chip->start();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+if (desc->chip->irq_eoi)
+        desc->chip->irq_eoi();
 		</programlisting>
 		</para>
    	    </sect3>
@@ -375,8 +395,7 @@
 	mechanism. (It's necessary to enable CONFIG_HARDIRQS_SW_RESEND when
 	you want to use the delayed interrupt disable feature and your
 	hardware is not capable of retriggering	an interrupt.)
-	The delayed interrupt disable can be runtime enabled, per interrupt,
-	by setting the IRQ_DELAYED_DISABLE flag in the irq_desc status field.
+	The delayed interrupt disable is not configurable.
 	</para>
 	</sect2>
     </sect1>
@@ -387,13 +406,13 @@
 	contains all the direct chip relevant functions, which
 	can be utilized by the irq flow implementations.
 	  <itemizedlist>
-	  <listitem><para>ack()</para></listitem>
-	  <listitem><para>mask_ack() - Optional, recommended for performance</para></listitem>
-	  <listitem><para>mask()</para></listitem>
-	  <listitem><para>unmask()</para></listitem>
-	  <listitem><para>retrigger() - Optional</para></listitem>
-	  <listitem><para>set_type() - Optional</para></listitem>
-	  <listitem><para>set_wake() - Optional</para></listitem>
+	  <listitem><para>irq_ack()</para></listitem>
+	  <listitem><para>irq_mask_ack() - Optional, recommended for performance</para></listitem>
+	  <listitem><para>irq_mask()</para></listitem>
+	  <listitem><para>irq_unmask()</para></listitem>
+	  <listitem><para>irq_retrigger() - Optional</para></listitem>
+	  <listitem><para>irq_set_type() - Optional</para></listitem>
+	  <listitem><para>irq_set_wake() - Optional</para></listitem>
 	  </itemizedlist>
 	These primitives are strictly intended to mean what they say: ack means
 	ACK, masking means masking of an IRQ line, etc. It is up to the flow
@@ -458,6 +477,7 @@
      <para>
      This chapter contains the autogenerated documentation of the internal functions.
      </para>
+!Ikernel/irq/irqdesc.c
 !Ikernel/irq/handle.c
 !Ikernel/irq/chip.c
   </chapter>
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index 6899f47..6b4e07f 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -257,7 +257,8 @@
 !Iblock/blk-sysfs.c
 !Eblock/blk-settings.c
 !Eblock/blk-exec.c
-!Eblock/blk-barrier.c
+!Eblock/blk-flush.c
+!Eblock/blk-lib.c
 !Eblock/blk-tag.c
 !Iblock/blk-tag.c
 !Eblock/blk-integrity.c
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index a0d479d..f66f4df 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1645,7 +1645,9 @@
       all the readers who were traversing the list when we deleted the
       element are finished.  We use <function>call_rcu()</function> to
       register a callback which will actually destroy the object once
-      the readers are finished.
+      all pre-existing readers are finished.  Alternatively,
+      <function>synchronize_rcu()</function> may be used to block until
+      all pre-existing are finished.
     </para>
     <para>
       But how does Read Copy Update know when the readers are
@@ -1714,7 +1716,7 @@
 -        object_put(obj);
 +        list_del_rcu(&amp;obj-&gt;list);
          cache_num--;
-+        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu, obj);
++        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu);
  }
 
  /* Must be holding cache_lock */
@@ -1725,14 +1727,6 @@
          if (++cache_num > MAX_CACHE_SIZE) {
                  struct object *i, *outcast = NULL;
                  list_for_each_entry(i, &amp;cache, list) {
-@@ -85,6 +94,7 @@
-         obj-&gt;popularity = 0;
-         atomic_set(&amp;obj-&gt;refcnt, 1); /* The cache holds a reference */
-         spin_lock_init(&amp;obj-&gt;lock);
-+        INIT_RCU_HEAD(&amp;obj-&gt;rcu);
-
-         spin_lock_irqsave(&amp;cache_lock, flags);
-         __cache_add(obj);
 @@ -104,12 +114,11 @@
  struct object *cache_find(int id)
  {
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 790d1a8..0c134f8 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -218,13 +218,22 @@
 	include:
 
 	a.	Keeping a count of the number of data-structure elements
-		used by the RCU-protected data structure, including those
-		waiting for a grace period to elapse.  Enforce a limit
-		on this number, stalling updates as needed to allow
-		previously deferred frees to complete.
+		used by the RCU-protected data structure, including
+		those waiting for a grace period to elapse.  Enforce a
+		limit on this number, stalling updates as needed to allow
+		previously deferred frees to complete.	Alternatively,
+		limit only the number awaiting deferred free rather than
+		the total number of elements.
 
-		Alternatively, limit only the number awaiting deferred
-		free rather than the total number of elements.
+		One way to stall the updates is to acquire the update-side
+		mutex.	(Don't try this with a spinlock -- other CPUs
+		spinning on the lock could prevent the grace period
+		from ever ending.)  Another way to stall the updates
+		is for the updates to use a wrapper function around
+		the memory allocator, so that this wrapper function
+		simulates OOM when there is too much memory awaiting an
+		RCU grace period.  There are of course many other
+		variations on this theme.
 
 	b.	Limiting update rate.  For example, if updates occur only
 		once per hour, then no explicit rate limiting is required,
@@ -365,3 +374,26 @@
 	and the compiler to freely reorder code into and out of RCU
 	read-side critical sections.  It is the responsibility of the
 	RCU update-side primitives to deal with this.
+
+17.	Use CONFIG_PROVE_RCU, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and
+	the __rcu sparse checks to validate your RCU code.  These
+	can help find problems as follows:
+
+	CONFIG_PROVE_RCU: check that accesses to RCU-protected data
+		structures are carried out under the proper RCU
+		read-side critical section, while holding the right
+		combination of locks, or whatever other conditions
+		are appropriate.
+
+	CONFIG_DEBUG_OBJECTS_RCU_HEAD: check that you don't pass the
+		same object to call_rcu() (or friends) before an RCU
+		grace period has elapsed since the last time that you
+		passed that same object to call_rcu() (or friends).
+
+	__rcu sparse checks: tag the pointer to the RCU-protected data
+		structure with __rcu, and sparse will warn you if you
+		access that pointer without the services of one of the
+		variants of rcu_dereference().
+
+	These debugging aids can help you find problems that are
+	otherwise extremely difficult to spot.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 44c6dcc9..862c08e 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -80,6 +80,24 @@
 o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
 	without invoking schedule().
 
+o	A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
+	happen to preempt a low-priority task in the middle of an RCU
+	read-side critical section.   This is especially damaging if
+	that low-priority task is not permitted to run on any other CPU,
+	in which case the next RCU grace period can never complete, which
+	will eventually cause the system to run out of memory and hang.
+	While the system is in the process of running itself out of
+	memory, you might see stall-warning messages.
+
+o	A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
+	is running at a higher priority than the RCU softirq threads.
+	This will prevent RCU callbacks from ever being invoked,
+	and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent
+	RCU grace periods from ever completing.  Either way, the
+	system will eventually run out of memory and hang.  In the
+	CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning
+	messages.
+
 o	A bug in the RCU implementation.
 
 o	A hardware failure.  This is quite unlikely, but has occurred
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index efd8cc9..a851118 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -125,6 +125,17 @@
 	of RCU callbacks is ready to invoke, then the remainder will
 	be deferred.
 
+o	"ci" is the number of RCU callbacks that have been invoked for
+	this CPU.  Note that ci+ql is the number of callbacks that have
+	been registered in absence of CPU-hotplug activity.
+
+o	"co" is the number of RCU callbacks that have been orphaned due to
+	this CPU going offline.
+
+o	"ca" is the number of RCU callbacks that have been adopted due to
+	other CPUs going offline.  Note that ci+co-ca+ql is the number of
+	RCU callbacks registered on this CPU.
+
 There is also an rcu/rcudata.csv file with the same information in
 comma-separated-variable spreadsheet format.
 
@@ -180,7 +191,7 @@
 
 o	"jfq" is the number of jiffies remaining for this grace period
 	before force_quiescent_state() is invoked to help push things
-	along.  Note that CPUs in dyntick-idle mode thoughout the grace
+	along.  Note that CPUs in dyntick-idle mode throughout the grace
 	period will not report on their own, but rather must be check by
 	some other CPU via force_quiescent_state().
 
diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index 7f5fc3b..ecf7d04 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -6,6 +6,8 @@
 	- ARM Interrupt subsystem documentation
 IXP2000
 	- Release Notes for Linux on Intel's IXP2000 Network Processor
+msm
+	- MSM specific documentation
 Netwinder
 	- Netwinder specific documentation
 Porting
diff --git a/Documentation/arm/msm/gpiomux.txt b/Documentation/arm/msm/gpiomux.txt
new file mode 100644
index 0000000..67a8162
--- /dev/null
+++ b/Documentation/arm/msm/gpiomux.txt
@@ -0,0 +1,176 @@
+This document provides an overview of the msm_gpiomux interface, which
+is used to provide gpio pin multiplexing and configuration on mach-msm
+targets.
+
+History
+=======
+
+The first-generation API for gpio configuration & multiplexing on msm
+is the function gpio_tlmm_config().  This function has a few notable
+shortcomings, which led to its deprecation and replacement by gpiomux:
+
+The 'disable' parameter:  Setting the second parameter to
+gpio_tlmm_config to GPIO_CFG_DISABLE tells the peripheral
+processor in charge of the subsystem to perform a look-up into a
+low-power table and apply the low-power/sleep setting for the pin.
+As the msm family evolved this became problematic. Not all pins
+have sleep settings, not all peripheral processors will accept requests
+to apply said sleep settings, and not all msm targets have their gpio
+subsystems managed by a peripheral processor. In order to get consistent
+behavior on all targets, drivers are forced to ignore this parameter,
+rendering it useless.
+
+The 'direction' flag: for all mux-settings other than raw-gpio (0),
+the output-enable bit of a gpio is hard-wired to a known
+input (usually VDD or ground).  For those settings, the direction flag
+is meaningless at best, and deceptive at worst.  In addition, using the
+direction flag to change output-enable (OE) directly can cause trouble in
+gpiolib, which has no visibility into gpio direction changes made
+in this way.  Direction control in gpio mode should be made through gpiolib.
+
+Key Features of gpiomux
+=======================
+
+- A consistent interface across all generations of msm.  Drivers can expect
+the same results on every target.
+- gpiomux plays nicely with gpiolib.  Functions that should belong to gpiolib
+are left to gpiolib and not duplicated here.  gpiomux is written with the
+intent that gpio_chips will call gpiomux reference-counting methods
+from their request() and free() hooks, providing full integration.
+- Tabular configuration.  Instead of having to call gpio_tlmm_config
+hundreds of times, gpio configuration is placed in a single table.
+- Per-gpio sleep.  Each gpio is individually reference counted, allowing only
+those lines which are in use to be put in high-power states.
+- 0 means 'do nothing': all flags are designed so that the default memset-zero
+equates to a sensible default of 'no configuration', preventing users
+from having to provide hundreds of 'no-op' configs for unused or
+unwanted lines.
+
+Usage
+=====
+
+To use gpiomux, provide configuration information for relevant gpio lines
+in the msm_gpiomux_configs table.  Since a 0 equates to "unconfigured",
+only those lines to be managed by gpiomux need to be specified.  Here
+is a completely fictional example:
+
+struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS] = {
+	[12] = {
+		.active = GPIOMUX_VALID | GPIOMUX_DRV_8MA | GPIOMUX_FUNC_1,
+		.suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+	},
+	[34] = {
+		.suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+	},
+};
+
+To indicate that a gpio is in use, call msm_gpiomux_get() to increase
+its reference count.  To decrease the reference count, call msm_gpiomux_put().
+
+The effect of this configuration is as follows:
+
+When the system boots, gpios 12 and 34 will be initialized with their
+'suspended' configurations.  All other gpios, which were left unconfigured,
+will not be touched.
+
+When msm_gpiomux_get() is called on gpio 12 to raise its reference count
+above 0, its active configuration will be applied.  Since no other gpio
+line has a valid active configuration, msm_gpiomux_get() will have no
+effect on any other line.
+
+When msm_gpiomux_put() is called on gpio 12 or 34 to drop their reference
+count to 0, their suspended configurations will be applied.
+Since no other gpio line has a valid suspended configuration, no other
+gpio line will be effected by msm_gpiomux_put().  Since gpio 34 has no valid
+active configuration, this is effectively a no-op for gpio 34 as well,
+with one small caveat, see the section "About Output-Enable Settings".
+
+All of the GPIOMUX_VALID flags may seem like unnecessary overhead, but
+they address some important issues.  As unused entries (all those
+except 12 and 34) are zero-filled, gpiomux needs a way to distinguish
+the used fields from the unused.  In addition, the all-zero pattern
+is a valid configuration!  Therefore, gpiomux defines an additional bit
+which is used to indicate when a field is used.  This has the pleasant
+side-effect of allowing calls to msm_gpiomux_write to use '0' to indicate
+that a value should not be changed:
+
+  msm_gpiomux_write(0, GPIOMUX_VALID, 0);
+
+replaces the active configuration of gpio 0 with an all-zero configuration,
+but leaves the suspended configuration as it was.
+
+Static Configurations
+=====================
+
+To install a static configuration, which is applied at boot and does
+not change after that, install a configuration with a suspended component
+but no active component, as in the previous example:
+
+	[34] = {
+		.suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+	},
+
+The suspended setting is applied during boot, and the lack of any valid
+active setting prevents any other setting from being applied at runtime.
+If other subsystems attempting to access the line is a concern, one could
+*really* anchor the configuration down by calling msm_gpiomux_get on the
+line at initialization to move the line into active mode.  With the line
+held, it will never be re-suspended, and with no valid active configuration,
+no new configurations will be applied.
+
+But then, if having other subsystems grabbing for the line is truly a concern,
+it should be reserved with gpio_request instead, which carries an implicit
+msm_gpiomux_get.
+
+gpiomux and gpiolib
+===================
+
+It is expected that msm gpio_chips will call msm_gpiomux_get() and
+msm_gpiomux_put() from their request and free hooks, like this fictional
+example:
+
+static int request(struct gpio_chip *chip, unsigned offset)
+{
+        return msm_gpiomux_get(chip->base + offset);
+}
+
+static void free(struct gpio_chip *chip, unsigned offset)
+{
+        msm_gpiomux_put(chip->base + offset);
+}
+
+	...somewhere in a gpio_chip declaration...
+	.request = request,
+	.free    = free,
+
+This provides important functionality:
+- It guarantees that a gpio line will have its 'active' config applied
+  when the line is requested, and will not be suspended while the line
+  remains requested; and
+- It guarantees that gpio-direction settings from gpiolib behave sensibly.
+  See "About Output-Enable Settings."
+
+This mechanism allows for "auto-request" of gpiomux lines via gpiolib
+when it is suitable.  Drivers wishing more exact control are, of course,
+free to also use msm_gpiomux_set and msm_gpiomux_get.
+
+About Output-Enable Settings
+============================
+
+Some msm targets do not have the ability to query the current gpio
+configuration setting.  This means that changes made to the output-enable
+(OE) bit by gpiolib cannot be consistently detected and preserved by gpiomux.
+Therefore, when gpiomux applies a configuration setting, any direction
+settings which may have been applied by gpiolib are lost and the default
+input settings are re-applied.
+
+For this reason, drivers should not assume that gpio direction settings
+continue to hold if they free and then re-request a gpio.  This seems like
+common sense - after all, anybody could have obtained the line in the
+meantime - but it needs saying.
+
+This also means that calls to msm_gpiomux_write will reset the OE bit,
+which means that if the gpio line is held by a client of gpiolib and
+msm_gpiomux_write is called, the direction setting has been lost and
+gpiolib's internal state has been broken.
+Release gpio lines before reconfiguring them.
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index a406286f..d111e3b 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -1,7 +1,5 @@
 00-INDEX
 	- This file
-barrier.txt
-	- I/O Barriers
 biodoc.txt
 	- Notes on the Generic Block Layer Rewrite in Linux 2.5
 capability.txt
@@ -16,3 +14,5 @@
 	- Block layer statistics in /sys/block/<dev>/stat
 switching-sched.txt
 	- Switching I/O schedulers at runtime
+writeback_cache_control.txt
+	- Control of volatile write back caches
diff --git a/Documentation/block/barrier.txt b/Documentation/block/barrier.txt
deleted file mode 100644
index 2c2f24f6..0000000
--- a/Documentation/block/barrier.txt
+++ /dev/null
@@ -1,261 +0,0 @@
-I/O Barriers
-============
-Tejun Heo <htejun@gmail.com>, July 22 2005
-
-I/O barrier requests are used to guarantee ordering around the barrier
-requests.  Unless you're crazy enough to use disk drives for
-implementing synchronization constructs (wow, sounds interesting...),
-the ordering is meaningful only for write requests for things like
-journal checkpoints.  All requests queued before a barrier request
-must be finished (made it to the physical medium) before the barrier
-request is started, and all requests queued after the barrier request
-must be started only after the barrier request is finished (again,
-made it to the physical medium).
-
-In other words, I/O barrier requests have the following two properties.
-
-1. Request ordering
-
-Requests cannot pass the barrier request.  Preceding requests are
-processed before the barrier and following requests after.
-
-Depending on what features a drive supports, this can be done in one
-of the following three ways.
-
-i. For devices which have queue depth greater than 1 (TCQ devices) and
-support ordered tags, block layer can just issue the barrier as an
-ordered request and the lower level driver, controller and drive
-itself are responsible for making sure that the ordering constraint is
-met.  Most modern SCSI controllers/drives should support this.
-
-NOTE: SCSI ordered tag isn't currently used due to limitation in the
-      SCSI midlayer, see the following random notes section.
-
-ii. For devices which have queue depth greater than 1 but don't
-support ordered tags, block layer ensures that the requests preceding
-a barrier request finishes before issuing the barrier request.  Also,
-it defers requests following the barrier until the barrier request is
-finished.  Older SCSI controllers/drives and SATA drives fall in this
-category.
-
-iii. Devices which have queue depth of 1.  This is a degenerate case
-of ii.  Just keeping issue order suffices.  Ancient SCSI
-controllers/drives and IDE drives are in this category.
-
-2. Forced flushing to physical medium
-
-Again, if you're not gonna do synchronization with disk drives (dang,
-it sounds even more appealing now!), the reason you use I/O barriers
-is mainly to protect filesystem integrity when power failure or some
-other events abruptly stop the drive from operating and possibly make
-the drive lose data in its cache.  So, I/O barriers need to guarantee
-that requests actually get written to non-volatile medium in order.
-
-There are four cases,
-
-i. No write-back cache.  Keeping requests ordered is enough.
-
-ii. Write-back cache but no flush operation.  There's no way to
-guarantee physical-medium commit order.  This kind of devices can't to
-I/O barriers.
-
-iii. Write-back cache and flush operation but no FUA (forced unit
-access).  We need two cache flushes - before and after the barrier
-request.
-
-iv. Write-back cache, flush operation and FUA.  We still need one
-flush to make sure requests preceding a barrier are written to medium,
-but post-barrier flush can be avoided by using FUA write on the
-barrier itself.
-
-
-How to support barrier requests in drivers
-------------------------------------------
-
-All barrier handling is done inside block layer proper.  All low level
-drivers have to are implementing its prepare_flush_fn and using one
-the following two functions to indicate what barrier type it supports
-and how to prepare flush requests.  Note that the term 'ordered' is
-used to indicate the whole sequence of performing barrier requests
-including draining and flushing.
-
-typedef void (prepare_flush_fn)(struct request_queue *q, struct request *rq);
-
-int blk_queue_ordered(struct request_queue *q, unsigned ordered,
-		      prepare_flush_fn *prepare_flush_fn);
-
-@q			: the queue in question
-@ordered		: the ordered mode the driver/device supports
-@prepare_flush_fn	: this function should prepare @rq such that it
-			  flushes cache to physical medium when executed
-
-For example, SCSI disk driver's prepare_flush_fn looks like the
-following.
-
-static void sd_prepare_flush(struct request_queue *q, struct request *rq)
-{
-	memset(rq->cmd, 0, sizeof(rq->cmd));
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->timeout = SD_TIMEOUT;
-	rq->cmd[0] = SYNCHRONIZE_CACHE;
-	rq->cmd_len = 10;
-}
-
-The following seven ordered modes are supported.  The following table
-shows which mode should be used depending on what features a
-device/driver supports.  In the leftmost column of table,
-QUEUE_ORDERED_ prefix is omitted from the mode names to save space.
-
-The table is followed by description of each mode.  Note that in the
-descriptions of QUEUE_ORDERED_DRAIN*, '=>' is used whereas '->' is
-used for QUEUE_ORDERED_TAG* descriptions.  '=>' indicates that the
-preceding step must be complete before proceeding to the next step.
-'->' indicates that the next step can start as soon as the previous
-step is issued.
-
-	    write-back cache	ordered tag	flush		FUA
------------------------------------------------------------------------
-NONE		yes/no		N/A		no		N/A
-DRAIN		no		no		N/A		N/A
-DRAIN_FLUSH	yes		no		yes		no
-DRAIN_FUA	yes		no		yes		yes
-TAG		no		yes		N/A		N/A
-TAG_FLUSH	yes		yes		yes		no
-TAG_FUA		yes		yes		yes		yes
-
-
-QUEUE_ORDERED_NONE
-	I/O barriers are not needed and/or supported.
-
-	Sequence: N/A
-
-QUEUE_ORDERED_DRAIN
-	Requests are ordered by draining the request queue and cache
-	flushing isn't needed.
-
-	Sequence: drain => barrier
-
-QUEUE_ORDERED_DRAIN_FLUSH
-	Requests are ordered by draining the request queue and both
-	pre-barrier and post-barrier cache flushings are needed.
-
-	Sequence: drain => preflush => barrier => postflush
-
-QUEUE_ORDERED_DRAIN_FUA
-	Requests are ordered by draining the request queue and
-	pre-barrier cache flushing is needed.  By using FUA on barrier
-	request, post-barrier flushing can be skipped.
-
-	Sequence: drain => preflush => barrier
-
-QUEUE_ORDERED_TAG
-	Requests are ordered by ordered tag and cache flushing isn't
-	needed.
-
-	Sequence: barrier
-
-QUEUE_ORDERED_TAG_FLUSH
-	Requests are ordered by ordered tag and both pre-barrier and
-	post-barrier cache flushings are needed.
-
-	Sequence: preflush -> barrier -> postflush
-
-QUEUE_ORDERED_TAG_FUA
-	Requests are ordered by ordered tag and pre-barrier cache
-	flushing is needed.  By using FUA on barrier request,
-	post-barrier flushing can be skipped.
-
-	Sequence: preflush -> barrier
-
-
-Random notes/caveats
---------------------
-
-* SCSI layer currently can't use TAG ordering even if the drive,
-controller and driver support it.  The problem is that SCSI midlayer
-request dispatch function is not atomic.  It releases queue lock and
-switch to SCSI host lock during issue and it's possible and likely to
-happen in time that requests change their relative positions.  Once
-this problem is solved, TAG ordering can be enabled.
-
-* Currently, no matter which ordered mode is used, there can be only
-one barrier request in progress.  All I/O barriers are held off by
-block layer until the previous I/O barrier is complete.  This doesn't
-make any difference for DRAIN ordered devices, but, for TAG ordered
-devices with very high command latency, passing multiple I/O barriers
-to low level *might* be helpful if they are very frequent.  Well, this
-certainly is a non-issue.  I'm writing this just to make clear that no
-two I/O barrier is ever passed to low-level driver.
-
-* Completion order.  Requests in ordered sequence are issued in order
-but not required to finish in order.  Barrier implementation can
-handle out-of-order completion of ordered sequence.  IOW, the requests
-MUST be processed in order but the hardware/software completion paths
-are allowed to reorder completion notifications - eg. current SCSI
-midlayer doesn't preserve completion order during error handling.
-
-* Requeueing order.  Low-level drivers are free to requeue any request
-after they removed it from the request queue with
-blkdev_dequeue_request().  As barrier sequence should be kept in order
-when requeued, generic elevator code takes care of putting requests in
-order around barrier.  See blk_ordered_req_seq() and
-ELEVATOR_INSERT_REQUEUE handling in __elv_add_request() for details.
-
-Note that block drivers must not requeue preceding requests while
-completing latter requests in an ordered sequence.  Currently, no
-error checking is done against this.
-
-* Error handling.  Currently, block layer will report error to upper
-layer if any of requests in an ordered sequence fails.  Unfortunately,
-this doesn't seem to be enough.  Look at the following request flow.
-QUEUE_ORDERED_TAG_FLUSH is in use.
-
- [0] [1] [2] [3] [pre] [barrier] [post] < [4] [5] [6] ... >
-					  still in elevator
-
-Let's say request [2], [3] are write requests to update file system
-metadata (journal or whatever) and [barrier] is used to mark that
-those updates are valid.  Consider the following sequence.
-
- i.	Requests [0] ~ [post] leaves the request queue and enters
-	low-level driver.
- ii.	After a while, unfortunately, something goes wrong and the
-	drive fails [2].  Note that any of [0], [1] and [3] could have
-	completed by this time, but [pre] couldn't have been finished
-	as the drive must process it in order and it failed before
-	processing that command.
- iii.	Error handling kicks in and determines that the error is
-	unrecoverable and fails [2], and resumes operation.
- iv.	[pre] [barrier] [post] gets processed.
- v.	*BOOM* power fails
-
-The problem here is that the barrier request is *supposed* to indicate
-that filesystem update requests [2] and [3] made it safely to the
-physical medium and, if the machine crashes after the barrier is
-written, filesystem recovery code can depend on that.  Sadly, that
-isn't true in this case anymore.  IOW, the success of a I/O barrier
-should also be dependent on success of some of the preceding requests,
-where only upper layer (filesystem) knows what 'some' is.
-
-This can be solved by implementing a way to tell the block layer which
-requests affect the success of the following barrier request and
-making lower lever drivers to resume operation on error only after
-block layer tells it to do so.
-
-As the probability of this happening is very low and the drive should
-be faulty, implementing the fix is probably an overkill.  But, still,
-it's there.
-
-* In previous drafts of barrier implementation, there was fallback
-mechanism such that, if FUA or ordered TAG fails, less fancy ordered
-mode can be selected and the failed barrier request is retried
-automatically.  The rationale for this feature was that as FUA is
-pretty new in ATA world and ordered tag was never used widely, there
-could be devices which report to support those features but choke when
-actually given such requests.
-
- This was removed for two reasons 1. it's an overkill 2. it's
-impossible to implement properly when TAG ordering is used as low
-level drivers resume after an error automatically.  If it's ever
-needed adding it back and modifying low level drivers accordingly
-shouldn't be difficult.
diff --git a/Documentation/block/writeback_cache_control.txt b/Documentation/block/writeback_cache_control.txt
new file mode 100644
index 0000000..83407d3
--- /dev/null
+++ b/Documentation/block/writeback_cache_control.txt
@@ -0,0 +1,86 @@
+
+Explicit volatile write back cache control
+=====================================
+
+Introduction
+------------
+
+Many storage devices, especially in the consumer market, come with volatile
+write back caches.  That means the devices signal I/O completion to the
+operating system before data actually has hit the non-volatile storage.  This
+behavior obviously speeds up various workloads, but it means the operating
+system needs to force data out to the non-volatile storage when it performs
+a data integrity operation like fsync, sync or an unmount.
+
+The Linux block layer provides two simple mechanisms that let filesystems
+control the caching behavior of the storage device.  These mechanisms are
+a forced cache flush, and the Force Unit Access (FUA) flag for requests.
+
+
+Explicit cache flushes
+----------------------
+
+The REQ_FLUSH flag can be OR ed into the r/w flags of a bio submitted from
+the filesystem and will make sure the volatile cache of the storage device
+has been flushed before the actual I/O operation is started.  This explicitly
+guarantees that previously completed write requests are on non-volatile
+storage before the flagged bio starts. In addition the REQ_FLUSH flag can be
+set on an otherwise empty bio structure, which causes only an explicit cache
+flush without any dependent I/O.  It is recommend to use
+the blkdev_issue_flush() helper for a pure cache flush.
+
+
+Forced Unit Access
+-----------------
+
+The REQ_FUA flag can be OR ed into the r/w flags of a bio submitted from the
+filesystem and will make sure that I/O completion for this request is only
+signaled after the data has been committed to non-volatile storage.
+
+
+Implementation details for filesystems
+--------------------------------------
+
+Filesystems can simply set the REQ_FLUSH and REQ_FUA bits and do not have to
+worry if the underlying devices need any explicit cache flushing and how
+the Forced Unit Access is implemented.  The REQ_FLUSH and REQ_FUA flags
+may both be set on a single bio.
+
+
+Implementation details for make_request_fn based block drivers
+--------------------------------------------------------------
+
+These drivers will always see the REQ_FLUSH and REQ_FUA bits as they sit
+directly below the submit_bio interface.  For remapping drivers the REQ_FUA
+bits need to be propagated to underlying devices, and a global flush needs
+to be implemented for bios with the REQ_FLUSH bit set.  For real device
+drivers that do not have a volatile cache the REQ_FLUSH and REQ_FUA bits
+on non-empty bios can simply be ignored, and REQ_FLUSH requests without
+data can be completed successfully without doing any work.  Drivers for
+devices with volatile caches need to implement the support for these
+flags themselves without any help from the block layer.
+
+
+Implementation details for request_fn based block drivers
+--------------------------------------------------------------
+
+For devices that do not support volatile write caches there is no driver
+support required, the block layer completes empty REQ_FLUSH requests before
+entering the driver and strips off the REQ_FLUSH and REQ_FUA bits from
+requests that have a payload.  For devices with volatile write caches the
+driver needs to tell the block layer that it supports flushing caches by
+doing:
+
+	blk_queue_flush(sdkp->disk->queue, REQ_FLUSH);
+
+and handle empty REQ_FLUSH requests in its prep_fn/request_fn.  Note that
+REQ_FLUSH requests with a payload are automatically turned into a sequence
+of an empty REQ_FLUSH request followed by the actual write by the block
+layer.  For devices that also support the FUA bit the block layer needs
+to be told to pass through the REQ_FUA bit using:
+
+	blk_queue_flush(sdkp->disk->queue, REQ_FLUSH | REQ_FUA);
+
+and the driver must handle write requests that have the REQ_FUA bit set
+in prep_fn/request_fn.  If the FUA bit is not natively supported the block
+layer turns it into an empty REQ_FLUSH request after the actual write.
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index 6919d62..d6da611 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -8,12 +8,17 @@
 Plan is to use the same cgroup based management interface for blkio controller
 and based on user options switch IO policies in the background.
 
-In the first phase, this patchset implements proportional weight time based
-division of disk policy. It is implemented in CFQ. Hence this policy takes
-effect only on leaf nodes when CFQ is being used.
+Currently two IO control policies are implemented. First one is proportional
+weight time based division of disk policy. It is implemented in CFQ. Hence
+this policy takes effect only on leaf nodes when CFQ is being used. The second
+one is throttling policy which can be used to specify upper IO rate limits
+on devices. This policy is implemented in generic block layer and can be
+used on leaf nodes as well as higher level logical devices like device mapper.
 
 HOWTO
 =====
+Proportional Weight division of bandwidth
+-----------------------------------------
 You can do a very simple testing of running two dd threads in two different
 cgroups. Here is what you can do.
 
@@ -55,6 +60,35 @@
   group dispatched to the disk. We provide fairness in terms of disk time, so
   ideally io.disk_time of cgroups should be in proportion to the weight.
 
+Throttling/Upper Limit policy
+-----------------------------
+- Enable Block IO controller
+	CONFIG_BLK_CGROUP=y
+
+- Enable throttling in block layer
+	CONFIG_BLK_DEV_THROTTLING=y
+
+- Mount blkio controller
+        mount -t cgroup -o blkio none /cgroup/blkio
+
+- Specify a bandwidth rate on particular device for root group. The format
+  for policy is "<major>:<minor>  <byes_per_second>".
+
+        echo "8:16  1048576" > /cgroup/blkio/blkio.read_bps_device
+
+  Above will put a limit of 1MB/second on reads happening for root group
+  on device having major/minor number 8:16.
+
+- Run dd to read a file and see if rate is throttled to 1MB/s or not.
+
+		# dd if=/mnt/common/zerofile of=/dev/null bs=4K count=1024
+		# iflag=direct
+        1024+0 records in
+        1024+0 records out
+        4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s
+
+ Limits for writes can be put using blkio.write_bps_device file.
+
 Various user visible config options
 ===================================
 CONFIG_BLK_CGROUP
@@ -68,8 +102,13 @@
 	- Enables group scheduling in CFQ. Currently only 1 level of group
 	  creation is allowed.
 
+CONFIG_BLK_DEV_THROTTLING
+	- Enable block device throttling support in block layer.
+
 Details of cgroup files
 =======================
+Proportional weight policy files
+--------------------------------
 - blkio.weight
 	- Specifies per cgroup weight. This is default weight of the group
 	  on all the devices until and unless overridden by per device rule.
@@ -210,6 +249,67 @@
 	  and minor number of the device and third field specifies the number
 	  of times a group was dequeued from a particular device.
 
+Throttling/Upper limit policy files
+-----------------------------------
+- blkio.throttle.read_bps_device
+	- Specifies upper limit on READ rate from the device. IO rate is
+	  specified in bytes per second. Rules are per deivce. Following is
+	  the format.
+
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.read_bps_device
+
+- blkio.throttle.write_bps_device
+	- Specifies upper limit on WRITE rate to the device. IO rate is
+	  specified in bytes per second. Rules are per deivce. Following is
+	  the format.
+
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.write_bps_device
+
+- blkio.throttle.read_iops_device
+	- Specifies upper limit on READ rate from the device. IO rate is
+	  specified in IO per second. Rules are per deivce. Following is
+	  the format.
+
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.read_iops_device
+
+- blkio.throttle.write_iops_device
+	- Specifies upper limit on WRITE rate to the device. IO rate is
+	  specified in io per second. Rules are per deivce. Following is
+	  the format.
+
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.write_iops_device
+
+Note: If both BW and IOPS rules are specified for a device, then IO is
+      subjectd to both the constraints.
+
+- blkio.throttle.io_serviced
+	- Number of IOs (bio) completed to/from the disk by the group (as
+	  seen by throttling policy). These are further divided by the type
+	  of operation - read or write, sync or async. First two fields specify
+	  the major and minor number of the device, third field specifies the
+	  operation type and the fourth field specifies the number of IOs.
+
+	  blkio.io_serviced does accounting as seen by CFQ and counts are in
+	  number of requests (struct request). On the other hand,
+	  blkio.throttle.io_serviced counts number of IO in terms of number
+	  of bios as seen by throttling policy.  These bios can later be
+	  merged by elevator and total number of requests completed can be
+	  lesser.
+
+- blkio.throttle.io_service_bytes
+	- Number of bytes transferred to/from the disk by the group. These
+	  are further divided by the type of operation - read or write, sync
+	  or async. First two fields specify the major and minor number of the
+	  device, third field specifies the operation type and the fourth field
+	  specifies the number of bytes.
+
+	  These numbers should roughly be same as blkio.io_service_bytes as
+	  updated by CFQ. The difference between two is that
+	  blkio.io_service_bytes will not be updated if CFQ is not operating
+	  on request queue.
+
+Common files among various policies
+-----------------------------------
 - blkio.reset_stats
 	- Writing an int to this file will result in resetting all the stats
 	  for that cgroup.
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index f1c5c4b..902d315 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -14,25 +14,39 @@
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+3) /sys/devices/system/cpu/cpuX/topology/book_id:
+
+	the book ID of cpuX. Typically it is the hardware platform's
+	identifier (rather than the kernel's).	The actual value is
+	architecture and platform dependent.
+
+4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internel kernel map of cpuX's hardware threads within the same
 	core as cpuX
 
-4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
+6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 attributes.
+drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
+#define topology_book_id(cpu)
 #define topology_thread_cpumask(cpu)
 #define topology_core_cpumask(cpu)
+#define topology_book_cpumask(cpu)
 
 The type of **_id is int.
 The type of siblings is (const) struct cpumask *.
@@ -45,6 +59,9 @@
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
+For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
+default definitions for topology_book_id() and topology_book_cpumask().
+
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 842aa9d..5e2bc4a 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -386,34 +386,6 @@
 
 ----------------------------
 
-What:	Support for VMware's guest paravirtuliazation technique [VMI] will be
-	dropped.
-When:	2.6.37 or earlier.
-Why:	With the recent innovations in CPU hardware acceleration technologies
-	from Intel and AMD, VMware ran a few experiments to compare these
-	techniques to guest paravirtualization technique on VMware's platform.
-	These hardware assisted virtualization techniques have outperformed the
-	performance benefits provided by VMI in most of the workloads. VMware
-	expects that these hardware features will be ubiquitous in a couple of
-	years, as a result, VMware has started a phased retirement of this
-	feature from the hypervisor. We will be removing this feature from the
-	Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
-	technical reasons (read opportunity to remove major chunk of pvops)
-	arise.
-
-	Please note that VMI has always been an optimization and non-VMI kernels
-	still work fine on VMware's platform.
-	Latest versions of VMware's product which support VMI are,
-	Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
-	releases for these products will continue supporting VMI.
-
-	For more details about VMI retirement take a look at this,
-	http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
-
-Who:	Alok N Kataria <akataria@vmware.com>
-
-----------------------------
-
 What:	Support for lcd_switch and display_get in asus-laptop driver
 When:	March 2010
 Why:	These two features use non-standard interfaces. There are the
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index 1f7ae14..5393e66 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -87,3 +87,10 @@
 			reservations - users should rarely need to change this
 			value. If allocation reservations are turned off, this
 			option will have no effect.
+coherency=full  (*)	Disallow concurrent O_DIRECT writes, cluster inode
+			lock will be taken to force other nodes drop cache,
+			therefore full cluster coherency is guaranteed even
+			for O_DIRECT writes.
+coherency=buffered	Allow concurrent O_DIRECT writes without EX lock among
+			nodes, which gains high performance at risk of getting
+			stale data on other nodes.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 8dd7248..02f21d9 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -455,7 +455,7 @@
 			[ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
 				pxa_timer,timer3,32k_counter,timer0_1
 			[AVR32] avr32
-			[X86-32] pit,hpet,tsc,vmi-timer;
+			[X86-32] pit,hpet,tsc;
 				scx200_hrt on Geode; cyclone on IBM x440
 			[MIPS] MIPS
 			[PARISC] cr16
@@ -2153,6 +2153,11 @@
 			Reserves a hole at the top of the kernel virtual
 			address space.
 
+	reservelow=	[X86]
+			Format: nn[K]
+			Set the amount of memory to reserve for BIOS at
+			the bottom of the address space.
+
 	reset_devices	[KNL] Force drivers to reset the underlying device
 			during initialization.
 
@@ -2165,6 +2170,11 @@
 			in <PAGE_SIZE> units (needed only for swap files).
 			See  Documentation/power/swsusp-and-swap-files.txt
 
+	hibernate=	[HIBERNATION]
+		noresume	Don't check if there's a hibernation image
+				present during boot.
+		nocompress	Don't compress/decompress hibernation images.
+
 	retain_initrd	[RAM] Keep initrd memory after extraction
 
 	rhash_entries=	[KNL,NET]
@@ -2435,6 +2445,10 @@
 			disables clocksource verification at runtime.
 			Used to enable high-resolution timer mode on older
 			hardware, and in virtualized environment.
+			[x86] noirqtime: Do not use TSC to do irq accounting.
+			Used to run time disable IRQ_TIME_ACCOUNTING on any
+			platforms where RDTSC is slow and this accounting
+			can add overhead.
 
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 1762b81..741fe66 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -542,9 +542,11 @@
 registration and unregistration.
 
 Probe handlers are run with preemption disabled.  Depending on the
-architecture, handlers may also run with interrupts disabled.  In any
-case, your handler should not yield the CPU (e.g., by attempting to
-acquire a semaphore).
+architecture and optimization state, handlers may also run with
+interrupts disabled (e.g., kretprobe handlers and optimized kprobe
+handlers run without interrupt disabled on x86/x86-64).  In any case,
+your handler should not yield the CPU (e.g., by attempting to acquire
+a semaphore).
 
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 8a6a8c6..dc73bc54 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -1640,15 +1640,6 @@
 	off = out->sector * 512;
 
 	/*
-	 * The block device implements "barriers", where the Guest indicates
-	 * that it wants all previous writes to occur before this write.  We
-	 * don't have a way of asking our kernel to do a barrier, so we just
-	 * synchronize all the data in the file.  Pretty poor, no?
-	 */
-	if (out->type & VIRTIO_BLK_T_BARRIER)
-		fdatasync(vblk->fd);
-
-	/*
 	 * In general the virtio block driver is allowed to try SCSI commands.
 	 * It'd be nice if we supported eject, for example, but we don't.
 	 */
@@ -1680,6 +1671,13 @@
 			/* Die, bad Guest, die. */
 			errx(1, "Write past end %llu+%u", off, ret);
 		}
+
+		wlen = sizeof(*in);
+		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
+	} else if (out->type & VIRTIO_BLK_T_FLUSH) {
+		/* Flush */
+		ret = fdatasync(vblk->fd);
+		verbose("FLUSH fdatasync: %i\n", ret);
 		wlen = sizeof(*in);
 		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
 	} else {
@@ -1703,15 +1701,6 @@
 		}
 	}
 
-	/*
-	 * OK, so we noted that it was pretty poor to use an fdatasync as a
-	 * barrier.  But Christoph Hellwig points out that we need a sync
-	 * *afterwards* as well: "Barriers specify no reordering to the front
-	 * or the back."  And Jens Axboe confirmed it, so here we are:
-	 */
-	if (out->type & VIRTIO_BLK_T_BARRIER)
-		fdatasync(vblk->fd);
-
 	/* Finished that request. */
 	add_used(vq, head, wlen);
 }
@@ -1736,8 +1725,8 @@
 	vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
 	vblk->len = lseek64(vblk->fd, 0, SEEK_END);
 
-	/* We support barriers. */
-	add_feature(dev, VIRTIO_BLK_F_BARRIER);
+	/* We support FLUSH. */
+	add_feature(dev, VIRTIO_BLK_F_FLUSH);
 
 	/* Tell Guest how many sectors this device has. */
 	conf.capacity = cpu_to_le64(vblk->len / 512);
diff --git a/Documentation/pcmcia/driver-changes.txt b/Documentation/pcmcia/driver-changes.txt
index 26c0f9c..dd04361 100644
--- a/Documentation/pcmcia/driver-changes.txt
+++ b/Documentation/pcmcia/driver-changes.txt
@@ -1,4 +1,29 @@
 This file details changes in 2.6 which affect PCMCIA card driver authors:
+* pcmcia_loop_config() and autoconfiguration (as of 2.6.36)
+   If struct pcmcia_device *p_dev->config_flags is set accordingly,
+   pcmcia_loop_config() now sets up certain configuration values
+   automatically, though the driver may still override the settings
+   in the callback function. The following autoconfiguration options
+   are provided at the moment:
+	CONF_AUTO_CHECK_VCC : check for matching Vcc
+	CONF_AUTO_SET_VPP   : set Vpp
+	CONF_AUTO_AUDIO     : auto-enable audio line, if required
+	CONF_AUTO_SET_IO    : set ioport resources (->resource[0,1])
+	CONF_AUTO_SET_IOMEM : set first iomem resource (->resource[2])
+
+* pcmcia_request_configuration -> pcmcia_enable_device (as of 2.6.36)
+   pcmcia_request_configuration() got renamed to pcmcia_enable_device(),
+   as it mirrors pcmcia_disable_device(). Configuration settings are now
+   stored in struct pcmcia_device, e.g. in the fields config_flags,
+   config_index, config_base, vpp.
+
+* pcmcia_request_window changes (as of 2.6.36)
+   Instead of win_req_t, drivers are now requested to fill out
+   struct pcmcia_device *p_dev->resource[2,3,4,5] for up to four ioport
+   ranges. After a call to pcmcia_request_window(), the regions found there
+   are reserved and may be used immediately -- until pcmcia_release_window()
+   is called.
+
 * pcmcia_request_io changes (as of 2.6.36)
    Instead of io_req_t, drivers are now requested to fill out
    struct pcmcia_device *p_dev->resource[0,1] for up to two ioport
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index fb742c2..45e9d4a 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -14,6 +14,8 @@
 	- Power management user interface in /sys/power
 notifiers.txt
 	- Registering suspend notifiers in device drivers
+opp.txt
+	- Operating Performance Point library
 pci.txt
 	- How the PCI Subsystem Does Power Management
 pm_qos_interface.txt
diff --git a/Documentation/power/interface.txt b/Documentation/power/interface.txt
index e67211f..c537834 100644
--- a/Documentation/power/interface.txt
+++ b/Documentation/power/interface.txt
@@ -57,7 +57,7 @@
 suspend image will be as small as possible.
 
 Reading from this file will display the current image size limit, which
-is set to 500 MB by default.
+is set to 2/5 of available RAM by default.
 
 /sys/power/pm_trace controls the code which saves the last PM event point in
 the RTC across reboots, so that you can debug a machine that just hangs
diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
new file mode 100644
index 0000000..44d87ad
--- /dev/null
+++ b/Documentation/power/opp.txt
@@ -0,0 +1,375 @@
+*=============*
+* OPP Library *
+*=============*
+
+(C) 2009-2010 Nishanth Menon <nm@ti.com>, Texas Instruments Incorporated
+
+Contents
+--------
+1. Introduction
+2. Initial OPP List Registration
+3. OPP Search Functions
+4. OPP Availability Control Functions
+5. OPP Data Retrieval Functions
+6. Cpufreq Table Generation
+7. Data Structures
+
+1. Introduction
+===============
+Complex SoCs of today consists of a multiple sub-modules working in conjunction.
+In an operational system executing varied use cases, not all modules in the SoC
+need to function at their highest performing frequency all the time. To
+facilitate this, sub-modules in a SoC are grouped into domains, allowing some
+domains to run at lower voltage and frequency while other domains are loaded
+more. The set of discrete tuples consisting of frequency and voltage pairs that
+the device will support per domain are called Operating Performance Points or
+OPPs.
+
+OPP library provides a set of helper functions to organize and query the OPP
+information. The library is located in drivers/base/power/opp.c and the header
+is located in include/linux/opp.h. OPP library can be enabled by enabling
+CONFIG_PM_OPP from power management menuconfig menu. OPP library depends on
+CONFIG_PM as certain SoCs such as Texas Instrument's OMAP framework allows to
+optionally boot at a certain OPP without needing cpufreq.
+
+Typical usage of the OPP library is as follows:
+(users)		-> registers a set of default OPPs		-> (library)
+SoC framework	-> modifies on required cases certain OPPs	-> OPP layer
+		-> queries to search/retrieve information	->
+
+OPP layer expects each domain to be represented by a unique device pointer. SoC
+framework registers a set of initial OPPs per device with the OPP layer. This
+list is expected to be an optimally small number typically around 5 per device.
+This initial list contains a set of OPPs that the framework expects to be safely
+enabled by default in the system.
+
+Note on OPP Availability:
+------------------------
+As the system proceeds to operate, SoC framework may choose to make certain
+OPPs available or not available on each device based on various external
+factors. Example usage: Thermal management or other exceptional situations where
+SoC framework might choose to disable a higher frequency OPP to safely continue
+operations until that OPP could be re-enabled if possible.
+
+OPP library facilitates this concept in it's implementation. The following
+operational functions operate only on available opps:
+opp_find_freq_{ceil, floor}, opp_get_voltage, opp_get_freq, opp_get_opp_count
+and opp_init_cpufreq_table
+
+opp_find_freq_exact is meant to be used to find the opp pointer which can then
+be used for opp_enable/disable functions to make an opp available as required.
+
+WARNING: Users of OPP library should refresh their availability count using
+get_opp_count if opp_enable/disable functions are invoked for a device, the
+exact mechanism to trigger these or the notification mechanism to other
+dependent subsystems such as cpufreq are left to the discretion of the SoC
+specific framework which uses the OPP library. Similar care needs to be taken
+care to refresh the cpufreq table in cases of these operations.
+
+WARNING on OPP List locking mechanism:
+-------------------------------------------------
+OPP library uses RCU for exclusivity. RCU allows the query functions to operate
+in multiple contexts and this synchronization mechanism is optimal for a read
+intensive operations on data structure as the OPP library caters to.
+
+To ensure that the data retrieved are sane, the users such as SoC framework
+should ensure that the section of code operating on OPP queries are locked
+using RCU read locks. The opp_find_freq_{exact,ceil,floor},
+opp_get_{voltage, freq, opp_count} fall into this category.
+
+opp_{add,enable,disable} are updaters which use mutex and implement it's own
+RCU locking mechanisms. opp_init_cpufreq_table acts as an updater and uses
+mutex to implment RCU updater strategy. These functions should *NOT* be called
+under RCU locks and other contexts that prevent blocking functions in RCU or
+mutex operations from working.
+
+2. Initial OPP List Registration
+================================
+The SoC implementation calls opp_add function iteratively to add OPPs per
+device. It is expected that the SoC framework will register the OPP entries
+optimally- typical numbers range to be less than 5. The list generated by
+registering the OPPs is maintained by OPP library throughout the device
+operation. The SoC framework can subsequently control the availability of the
+OPPs dynamically using the opp_enable / disable functions.
+
+opp_add - Add a new OPP for a specific domain represented by the device pointer.
+	The OPP is defined using the frequency and voltage. Once added, the OPP
+	is assumed to be available and control of it's availability can be done
+	with the opp_enable/disable functions. OPP library internally stores
+	and manages this information in the opp struct. This function may be
+	used by SoC framework to define a optimal list as per the demands of
+	SoC usage environment.
+
+	WARNING: Do not use this function in interrupt context.
+
+	Example:
+	 soc_pm_init()
+	 {
+		/* Do things */
+		r = opp_add(mpu_dev, 1000000, 900000);
+		if (!r) {
+			pr_err("%s: unable to register mpu opp(%d)\n", r);
+			goto no_cpufreq;
+		}
+		/* Do cpufreq things */
+	 no_cpufreq:
+		/* Do remaining things */
+	 }
+
+3. OPP Search Functions
+=======================
+High level framework such as cpufreq operates on frequencies. To map the
+frequency back to the corresponding OPP, OPP library provides handy functions
+to search the OPP list that OPP library internally manages. These search
+functions return the matching pointer representing the opp if a match is
+found, else returns error. These errors are expected to be handled by standard
+error checks such as IS_ERR() and appropriate actions taken by the caller.
+
+opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
+	availability. This function is especially useful to enable an OPP which
+	is not available by default.
+	Example: In a case when SoC framework detects a situation where a
+	higher frequency could be made available, it can use this function to
+	find the OPP prior to call the opp_enable to actually make it available.
+	 rcu_read_lock();
+	 opp = opp_find_freq_exact(dev, 1000000000, false);
+	 rcu_read_unlock();
+	 /* dont operate on the pointer.. just do a sanity check.. */
+	 if (IS_ERR(opp)) {
+		pr_err("frequency not disabled!\n");
+		/* trigger appropriate actions.. */
+	 } else {
+		opp_enable(dev,1000000000);
+	 }
+
+	NOTE: This is the only search function that operates on OPPs which are
+	not available.
+
+opp_find_freq_floor - Search for an available OPP which is *at most* the
+	provided frequency. This function is useful while searching for a lesser
+	match OR operating on OPP information in the order of decreasing
+	frequency.
+	Example: To find the highest opp for a device:
+	 freq = ULONG_MAX;
+	 rcu_read_lock();
+	 opp_find_freq_floor(dev, &freq);
+	 rcu_read_unlock();
+
+opp_find_freq_ceil - Search for an available OPP which is *at least* the
+	provided frequency. This function is useful while searching for a
+	higher match OR operating on OPP information in the order of increasing
+	frequency.
+	Example 1: To find the lowest opp for a device:
+	 freq = 0;
+	 rcu_read_lock();
+	 opp_find_freq_ceil(dev, &freq);
+	 rcu_read_unlock();
+	Example 2: A simplified implementation of a SoC cpufreq_driver->target:
+	 soc_cpufreq_target(..)
+	 {
+		/* Do stuff like policy checks etc. */
+		/* Find the best frequency match for the req */
+		rcu_read_lock();
+		opp = opp_find_freq_ceil(dev, &freq);
+		rcu_read_unlock();
+		if (!IS_ERR(opp))
+			soc_switch_to_freq_voltage(freq);
+		else
+			/* do something when we cant satisfy the req */
+		/* do other stuff */
+	 }
+
+4. OPP Availability Control Functions
+=====================================
+A default OPP list registered with the OPP library may not cater to all possible
+situation. The OPP library provides a set of functions to modify the
+availability of a OPP within the OPP list. This allows SoC frameworks to have
+fine grained dynamic control of which sets of OPPs are operationally available.
+These functions are intended to *temporarily* remove an OPP in conditions such
+as thermal considerations (e.g. don't use OPPx until the temperature drops).
+
+WARNING: Do not use these functions in interrupt context.
+
+opp_enable - Make a OPP available for operation.
+	Example: Lets say that 1GHz OPP is to be made available only if the
+	SoC temperature is lower than a certain threshold. The SoC framework
+	implementation might choose to do something as follows:
+	 if (cur_temp < temp_low_thresh) {
+		/* Enable 1GHz if it was disabled */
+		rcu_read_lock();
+		opp = opp_find_freq_exact(dev, 1000000000, false);
+		rcu_read_unlock();
+		/* just error check */
+		if (!IS_ERR(opp))
+			ret = opp_enable(dev, 1000000000);
+		else
+			goto try_something_else;
+	 }
+
+opp_disable - Make an OPP to be not available for operation
+	Example: Lets say that 1GHz OPP is to be disabled if the temperature
+	exceeds a threshold value. The SoC framework implementation might
+	choose to do something as follows:
+	 if (cur_temp > temp_high_thresh) {
+		/* Disable 1GHz if it was enabled */
+		rcu_read_lock();
+		opp = opp_find_freq_exact(dev, 1000000000, true);
+		rcu_read_unlock();
+		/* just error check */
+		if (!IS_ERR(opp))
+			ret = opp_disable(dev, 1000000000);
+		else
+			goto try_something_else;
+	 }
+
+5. OPP Data Retrieval Functions
+===============================
+Since OPP library abstracts away the OPP information, a set of functions to pull
+information from the OPP structure is necessary. Once an OPP pointer is
+retrieved using the search functions, the following functions can be used by SoC
+framework to retrieve the information represented inside the OPP layer.
+
+opp_get_voltage - Retrieve the voltage represented by the opp pointer.
+	Example: At a cpufreq transition to a different frequency, SoC
+	framework requires to set the voltage represented by the OPP using
+	the regulator framework to the Power Management chip providing the
+	voltage.
+	 soc_switch_to_freq_voltage(freq)
+	 {
+		/* do things */
+		rcu_read_lock();
+		opp = opp_find_freq_ceil(dev, &freq);
+		v = opp_get_voltage(opp);
+		rcu_read_unlock();
+		if (v)
+			regulator_set_voltage(.., v);
+		/* do other things */
+	 }
+
+opp_get_freq - Retrieve the freq represented by the opp pointer.
+	Example: Lets say the SoC framework uses a couple of helper functions
+	we could pass opp pointers instead of doing additional parameters to
+	handle quiet a bit of data parameters.
+	 soc_cpufreq_target(..)
+	 {
+		/* do things.. */
+		 max_freq = ULONG_MAX;
+		 rcu_read_lock();
+		 max_opp = opp_find_freq_floor(dev,&max_freq);
+		 requested_opp = opp_find_freq_ceil(dev,&freq);
+		 if (!IS_ERR(max_opp) && !IS_ERR(requested_opp))
+			r = soc_test_validity(max_opp, requested_opp);
+		 rcu_read_unlock();
+		/* do other things */
+	 }
+	 soc_test_validity(..)
+	 {
+		 if(opp_get_voltage(max_opp) < opp_get_voltage(requested_opp))
+			 return -EINVAL;
+		 if(opp_get_freq(max_opp) < opp_get_freq(requested_opp))
+			 return -EINVAL;
+		/* do things.. */
+	 }
+
+opp_get_opp_count - Retrieve the number of available opps for a device
+	Example: Lets say a co-processor in the SoC needs to know the available
+	frequencies in a table, the main processor can notify as following:
+	 soc_notify_coproc_available_frequencies()
+	 {
+		/* Do things */
+		rcu_read_lock();
+		num_available = opp_get_opp_count(dev);
+		speeds = kzalloc(sizeof(u32) * num_available, GFP_KERNEL);
+		/* populate the table in increasing order */
+		freq = 0;
+		while (!IS_ERR(opp = opp_find_freq_ceil(dev, &freq))) {
+			speeds[i] = freq;
+			freq++;
+			i++;
+		}
+		rcu_read_unlock();
+
+		soc_notify_coproc(AVAILABLE_FREQs, speeds, num_available);
+		/* Do other things */
+	 }
+
+6. Cpufreq Table Generation
+===========================
+opp_init_cpufreq_table - cpufreq framework typically is initialized with
+	cpufreq_frequency_table_cpuinfo which is provided with the list of
+	frequencies that are available for operation. This function provides
+	a ready to use conversion routine to translate the OPP layer's internal
+	information about the available frequencies into a format readily
+	providable to cpufreq.
+
+	WARNING: Do not use this function in interrupt context.
+
+	Example:
+	 soc_pm_init()
+	 {
+		/* Do things */
+		r = opp_init_cpufreq_table(dev, &freq_table);
+		if (!r)
+			cpufreq_frequency_table_cpuinfo(policy, freq_table);
+		/* Do other things */
+	 }
+
+	NOTE: This function is available only if CONFIG_CPU_FREQ is enabled in
+	addition to CONFIG_PM as power management feature is required to
+	dynamically scale voltage and frequency in a system.
+
+7. Data Structures
+==================
+Typically an SoC contains multiple voltage domains which are variable. Each
+domain is represented by a device pointer. The relationship to OPP can be
+represented as follows:
+SoC
+ |- device 1
+ |	|- opp 1 (availability, freq, voltage)
+ |	|- opp 2 ..
+ ...	...
+ |	`- opp n ..
+ |- device 2
+ ...
+ `- device m
+
+OPP library maintains a internal list that the SoC framework populates and
+accessed by various functions as described above. However, the structures
+representing the actual OPPs and domains are internal to the OPP library itself
+to allow for suitable abstraction reusable across systems.
+
+struct opp - The internal data structure of OPP library which is used to
+	represent an OPP. In addition to the freq, voltage, availability
+	information, it also contains internal book keeping information required
+	for the OPP library to operate on.  Pointer to this structure is
+	provided back to the users such as SoC framework to be used as a
+	identifier for OPP in the interactions with OPP layer.
+
+	WARNING: The struct opp pointer should not be parsed or modified by the
+	users. The defaults of for an instance is populated by opp_add, but the
+	availability of the OPP can be modified by opp_enable/disable functions.
+
+struct device - This is used to identify a domain to the OPP layer. The
+	nature of the device and it's implementation is left to the user of
+	OPP library such as the SoC framework.
+
+Overall, in a simplistic view, the data structure operations is represented as
+following:
+
+Initialization / modification:
+            +-----+        /- opp_enable
+opp_add --> | opp | <-------
+  |         +-----+        \- opp_disable
+  \-------> domain_info(device)
+
+Search functions:
+             /-- opp_find_freq_ceil  ---\   +-----+
+domain_info<---- opp_find_freq_exact -----> | opp |
+             \-- opp_find_freq_floor ---/   +-----+
+
+Retrieval functions:
++-----+     /- opp_get_voltage
+| opp | <---
++-----+     \- opp_get_freq
+
+domain_info <- opp_get_opp_count
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 55b859b..489e9ba 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -1,6 +1,7 @@
 Run-time Power Management Framework for I/O Devices
 
 (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+(C) 2010 Alan Stern <stern@rowland.harvard.edu>
 
 1. Introduction
 
@@ -157,7 +158,8 @@
     to execute it, the other callbacks will not be executed for the same device.
 
   * A request to execute ->runtime_resume() will cancel any pending or
-    scheduled requests to execute the other callbacks for the same device.
+    scheduled requests to execute the other callbacks for the same device,
+    except for scheduled autosuspends.
 
 3. Run-time PM Device Fields
 
@@ -165,7 +167,7 @@
 defined in include/linux/pm.h:
 
   struct timer_list suspend_timer;
-    - timer used for scheduling (delayed) suspend request
+    - timer used for scheduling (delayed) suspend and autosuspend requests
 
   unsigned long timer_expires;
     - timer expiration time, in jiffies (if this is different from zero, the
@@ -230,6 +232,28 @@
       interface; it may only be modified with the help of the pm_runtime_allow()
       and pm_runtime_forbid() helper functions
 
+  unsigned int no_callbacks;
+    - indicates that the device does not use the run-time PM callbacks (see
+      Section 8); it may be modified only by the pm_runtime_no_callbacks()
+      helper function
+
+  unsigned int use_autosuspend;
+    - indicates that the device's driver supports delayed autosuspend (see
+      Section 9); it may be modified only by the
+      pm_runtime{_dont}_use_autosuspend() helper functions
+
+  unsigned int timer_autosuspends;
+    - indicates that the PM core should attempt to carry out an autosuspend
+      when the timer expires rather than a normal suspend
+
+  int autosuspend_delay;
+    - the delay time (in milliseconds) to be used for autosuspend
+
+  unsigned long last_busy;
+    - the time (in jiffies) when the pm_runtime_mark_last_busy() helper
+      function was last called for this device; used in calculating inactivity
+      periods for autosuspend
+
 All of the above fields are members of the 'power' member of 'struct device'.
 
 4. Run-time PM Device Helper Functions
@@ -255,6 +279,12 @@
       error code on failure, where -EAGAIN or -EBUSY means it is safe to attempt
       to suspend the device again in future
 
+  int pm_runtime_autosuspend(struct device *dev);
+    - same as pm_runtime_suspend() except that the autosuspend delay is taken
+      into account; if pm_runtime_autosuspend_expiration() says the delay has
+      not yet expired then an autosuspend is scheduled for the appropriate time
+      and 0 is returned
+
   int pm_runtime_resume(struct device *dev);
     - execute the subsystem-level resume callback for the device; returns 0 on
       success, 1 if the device's run-time PM status was already 'active' or
@@ -267,6 +297,11 @@
       device (the request is represented by a work item in pm_wq); returns 0 on
       success or error code if the request has not been queued up
 
+  int pm_request_autosuspend(struct device *dev);
+    - schedule the execution of the subsystem-level suspend callback for the
+      device when the autosuspend delay has expired; if the delay has already
+      expired then the work item is queued up immediately
+
   int pm_schedule_suspend(struct device *dev, unsigned int delay);
     - schedule the execution of the subsystem-level suspend callback for the
       device in future, where 'delay' is the time to wait before queuing up a
@@ -298,12 +333,20 @@
     - decrement the device's usage counter
 
   int pm_runtime_put(struct device *dev);
-    - decrement the device's usage counter, run pm_request_idle(dev) and return
-      its result
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_idle(dev) and return its result
+
+  int pm_runtime_put_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_autosuspend(dev) and return its result
 
   int pm_runtime_put_sync(struct device *dev);
-    - decrement the device's usage counter, run pm_runtime_idle(dev) and return
-      its result
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_idle(dev) and return its result
+
+  int pm_runtime_put_sync_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_autosuspend(dev) and return its result
 
   void pm_runtime_enable(struct device *dev);
     - enable the run-time PM helper functions to run the device bus type's
@@ -349,19 +392,51 @@
       counter (used by the /sys/devices/.../power/control interface to
       effectively prevent the device from being power managed at run time)
 
+  void pm_runtime_no_callbacks(struct device *dev);
+    - set the power.no_callbacks flag for the device and remove the run-time
+      PM attributes from /sys/devices/.../power (or prevent them from being
+      added when the device is registered)
+
+  void pm_runtime_mark_last_busy(struct device *dev);
+    - set the power.last_busy field to the current time
+
+  void pm_runtime_use_autosuspend(struct device *dev);
+    - set the power.use_autosuspend flag, enabling autosuspend delays
+
+  void pm_runtime_dont_use_autosuspend(struct device *dev);
+    - clear the power.use_autosuspend flag, disabling autosuspend delays
+
+  void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
+    - set the power.autosuspend_delay value to 'delay' (expressed in
+      milliseconds); if 'delay' is negative then run-time suspends are
+      prevented
+
+  unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
+    - calculate the time when the current autosuspend delay period will expire,
+      based on power.last_busy and power.autosuspend_delay; if the delay time
+      is 1000 ms or larger then the expiration time is rounded up to the
+      nearest second; returns 0 if the delay period has already expired or
+      power.use_autosuspend isn't set, otherwise returns the expiration time
+      in jiffies
+
 It is safe to execute the following helper functions from interrupt context:
 
 pm_request_idle()
+pm_request_autosuspend()
 pm_schedule_suspend()
 pm_request_resume()
 pm_runtime_get_noresume()
 pm_runtime_get()
 pm_runtime_put_noidle()
 pm_runtime_put()
+pm_runtime_put_autosuspend()
+pm_runtime_enable()
 pm_suspend_ignore_children()
 pm_runtime_set_active()
 pm_runtime_set_suspended()
-pm_runtime_enable()
+pm_runtime_suspended()
+pm_runtime_mark_last_busy()
+pm_runtime_autosuspend_expiration()
 
 5. Run-time PM Initialization, Device Probing and Removal
 
@@ -524,3 +599,141 @@
 restore, and run-time resume, can achieve this with the help of the
 UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
 last argument to NULL).
+
+8. "No-Callback" Devices
+
+Some "devices" are only logical sub-devices of their parent and cannot be
+power-managed on their own.  (The prototype example is a USB interface.  Entire
+USB devices can go into low-power mode or send wake-up requests, but neither is
+possible for individual interfaces.)  The drivers for these devices have no
+need of run-time PM callbacks; if the callbacks did exist, ->runtime_suspend()
+and ->runtime_resume() would always return 0 without doing anything else and
+->runtime_idle() would always call pm_runtime_suspend().
+
+Subsystems can tell the PM core about these devices by calling
+pm_runtime_no_callbacks().  This should be done after the device structure is
+initialized and before it is registered (although after device registration is
+also okay).  The routine will set the device's power.no_callbacks flag and
+prevent the non-debugging run-time PM sysfs attributes from being created.
+
+When power.no_callbacks is set, the PM core will not invoke the
+->runtime_idle(), ->runtime_suspend(), or ->runtime_resume() callbacks.
+Instead it will assume that suspends and resumes always succeed and that idle
+devices should be suspended.
+
+As a consequence, the PM core will never directly inform the device's subsystem
+or driver about run-time power changes.  Instead, the driver for the device's
+parent must take responsibility for telling the device's driver when the
+parent's power state changes.
+
+9. Autosuspend, or automatically-delayed suspends
+
+Changing a device's power state isn't free; it requires both time and energy.
+A device should be put in a low-power state only when there's some reason to
+think it will remain in that state for a substantial time.  A common heuristic
+says that a device which hasn't been used for a while is liable to remain
+unused; following this advice, drivers should not allow devices to be suspended
+at run-time until they have been inactive for some minimum period.  Even when
+the heuristic ends up being non-optimal, it will still prevent devices from
+"bouncing" too rapidly between low-power and full-power states.
+
+The term "autosuspend" is an historical remnant.  It doesn't mean that the
+device is automatically suspended (the subsystem or driver still has to call
+the appropriate PM routines); rather it means that run-time suspends will
+automatically be delayed until the desired period of inactivity has elapsed.
+
+Inactivity is determined based on the power.last_busy field.  Drivers should
+call pm_runtime_mark_last_busy() to update this field after carrying out I/O,
+typically just before calling pm_runtime_put_autosuspend().  The desired length
+of the inactivity period is a matter of policy.  Subsystems can set this length
+initially by calling pm_runtime_set_autosuspend_delay(), but after device
+registration the length should be controlled by user space, using the
+/sys/devices/.../power/autosuspend_delay_ms attribute.
+
+In order to use autosuspend, subsystems or drivers must call
+pm_runtime_use_autosuspend() (preferably before registering the device), and
+thereafter they should use the various *_autosuspend() helper functions instead
+of the non-autosuspend counterparts:
+
+	Instead of: pm_runtime_suspend    use: pm_runtime_autosuspend;
+	Instead of: pm_schedule_suspend   use: pm_request_autosuspend;
+	Instead of: pm_runtime_put        use: pm_runtime_put_autosuspend;
+	Instead of: pm_runtime_put_sync   use: pm_runtime_put_sync_autosuspend.
+
+Drivers may also continue to use the non-autosuspend helper functions; they
+will behave normally, not taking the autosuspend delay into account.
+Similarly, if the power.use_autosuspend field isn't set then the autosuspend
+helper functions will behave just like the non-autosuspend counterparts.
+
+The implementation is well suited for asynchronous use in interrupt contexts.
+However such use inevitably involves races, because the PM core can't
+synchronize ->runtime_suspend() callbacks with the arrival of I/O requests.
+This synchronization must be handled by the driver, using its private lock.
+Here is a schematic pseudo-code example:
+
+	foo_read_or_write(struct foo_priv *foo, void *data)
+	{
+		lock(&foo->private_lock);
+		add_request_to_io_queue(foo, data);
+		if (foo->num_pending_requests++ == 0)
+			pm_runtime_get(&foo->dev);
+		if (!foo->is_suspended)
+			foo_process_next_request(foo);
+		unlock(&foo->private_lock);
+	}
+
+	foo_io_completion(struct foo_priv *foo, void *req)
+	{
+		lock(&foo->private_lock);
+		if (--foo->num_pending_requests == 0) {
+			pm_runtime_mark_last_busy(&foo->dev);
+			pm_runtime_put_autosuspend(&foo->dev);
+		} else {
+			foo_process_next_request(foo);
+		}
+		unlock(&foo->private_lock);
+		/* Send req result back to the user ... */
+	}
+
+	int foo_runtime_suspend(struct device *dev)
+	{
+		struct foo_priv foo = container_of(dev, ...);
+		int ret = 0;
+
+		lock(&foo->private_lock);
+		if (foo->num_pending_requests > 0) {
+			ret = -EBUSY;
+		} else {
+			/* ... suspend the device ... */
+			foo->is_suspended = 1;
+		}
+		unlock(&foo->private_lock);
+		return ret;
+	}
+
+	int foo_runtime_resume(struct device *dev)
+	{
+		struct foo_priv foo = container_of(dev, ...);
+
+		lock(&foo->private_lock);
+		/* ... resume the device ... */
+		foo->is_suspended = 0;
+		pm_runtime_mark_last_busy(&foo->dev);
+		if (foo->num_pending_requests > 0)
+			foo_process_requests(foo);
+		unlock(&foo->private_lock);
+		return 0;
+	}
+
+The important point is that after foo_io_completion() asks for an autosuspend,
+the foo_runtime_suspend() callback may race with foo_read_or_write().
+Therefore foo_runtime_suspend() has to check whether there are any pending I/O
+requests (while holding the private lock) before allowing the suspend to
+proceed.
+
+In addition, the power.autosuspend_delay field can be changed by user space at
+any time.  If a driver cares about this, it can call
+pm_runtime_autosuspend_expiration() from within the ->runtime_suspend()
+callback while holding its private lock.  If the function returns a nonzero
+value then the delay has not yet expired and the callback should return
+-EAGAIN.
diff --git a/Documentation/power/s2ram.txt b/Documentation/power/s2ram.txt
index 514b94f..1bdfa04 100644
--- a/Documentation/power/s2ram.txt
+++ b/Documentation/power/s2ram.txt
@@ -49,6 +49,13 @@
    device (lspci and /sys/devices/pci* is your friend), and see if you can
    fix it, disable it, or trace into its resume function.
 
+   If no device matches the hash (or any matches appear to be false positives),
+   the culprit may be a device from a loadable kernel module that is not loaded
+   until after the hash is checked. You can check the hash against the current
+   devices again after more modules are loaded using sysfs:
+
+	cat /sys/power/pm_trace_dev_match
+
 For example, the above happens to be the VGA device on my EVO, which I
 used to run with "radeonfb" (it's an ATI Radeon mobility). It turns out
 that "radeonfb" simply cannot resume that device - it tries to set the
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index 9d60ab7..ea71889 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -66,7 +66,8 @@
 powerdowns.  You must explicitly specify the swap partition to resume from with
 ``resume='' kernel option. If signature is found it loads and restores saved
 state. If the option ``noresume'' is specified as a boot parameter, it skips
-the resuming.
+the resuming.  If the option ``hibernate=nocompress'' is specified as a boot
+parameter, it saves hibernation image without compression.
 
 In the meantime while the system is suspended you should not add/remove any
 of the hardware, write to the filesystems, etc.
diff --git a/Documentation/powerpc/dts-bindings/fsl/spi.txt b/Documentation/powerpc/dts-bindings/fsl/spi.txt
index 80510c0..777abd7 100644
--- a/Documentation/powerpc/dts-bindings/fsl/spi.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/spi.txt
@@ -1,7 +1,9 @@
 * SPI (Serial Peripheral Interface)
 
 Required properties:
-- cell-index : SPI controller index.
+- cell-index : QE SPI subblock index.
+		0: QE subblock SPI1
+		1: QE subblock SPI2
 - compatible : should be "fsl,spi".
 - mode : the SPI operation mode, it can be "cpu" or "cpu-qe".
 - reg : Offset and length of the register set for the device
@@ -29,3 +31,23 @@
 		gpios = <&gpio 18 1	// device reg=<0>
 			 &gpio 19 1>;	// device reg=<1>
 	};
+
+
+* eSPI (Enhanced Serial Peripheral Interface)
+
+Required properties:
+- compatible : should be "fsl,mpc8536-espi".
+- reg : Offset and length of the register set for the device.
+- interrupts : should contain eSPI interrupt, the device has one interrupt.
+- fsl,espi-num-chipselects : the number of the chipselect signals.
+
+Example:
+	spi@110000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "fsl,mpc8536-espi";
+		reg = <0x110000 0x1000>;
+		interrupts = <53 0x2>;
+		interrupt-parent = <&mpic>;
+		fsl,espi-num-chipselects = <4>;
+	};
diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt
index e4498a2..996a27d 100644
--- a/Documentation/workqueue.txt
+++ b/Documentation/workqueue.txt
@@ -196,11 +196,11 @@
 	suspend operations.  Work items on the wq are drained and no
 	new work item starts execution until thawed.
 
-  WQ_RESCUER
+  WQ_MEM_RECLAIM
 
 	All wq which might be used in the memory reclaim paths _MUST_
-	have this flag set.  This reserves one worker exclusively for
-	the execution of this wq under memory pressure.
+	have this flag set.  The wq is guaranteed to have at least one
+	execution context regardless of memory pressure.
 
   WQ_HIGHPRI
 
@@ -356,11 +356,11 @@
 
 6. Guidelines
 
-* Do not forget to use WQ_RESCUER if a wq may process work items which
-  are used during memory reclaim.  Each wq with WQ_RESCUER set has one
-  rescuer thread reserved for it.  If there is dependency among
-  multiple work items used during memory reclaim, they should be
-  queued to separate wq each with WQ_RESCUER.
+* Do not forget to use WQ_MEM_RECLAIM if a wq may process work items
+  which are used during memory reclaim.  Each wq with WQ_MEM_RECLAIM
+  set has an execution context reserved for it.  If there is
+  dependency among multiple work items used during memory reclaim,
+  they should be queued to separate wq each with WQ_MEM_RECLAIM.
 
 * Unless strict ordering is required, there is no need to use ST wq.
 
@@ -368,12 +368,13 @@
   recommended.  In most use cases, concurrency level usually stays
   well under the default limit.
 
-* A wq serves as a domain for forward progress guarantee (WQ_RESCUER),
-  flush and work item attributes.  Work items which are not involved
-  in memory reclaim and don't need to be flushed as a part of a group
-  of work items, and don't require any special attribute, can use one
-  of the system wq.  There is no difference in execution
-  characteristics between using a dedicated wq and a system wq.
+* A wq serves as a domain for forward progress guarantee
+  (WQ_MEM_RECLAIM, flush and work item attributes.  Work items which
+  are not involved in memory reclaim and don't need to be flushed as a
+  part of a group of work items, and don't require any special
+  attribute, can use one of the system wq.  There is no difference in
+  execution characteristics between using a dedicated wq and a system
+  wq.
 
 * Unless work items are expected to consume a huge amount of CPU
   cycles, using a bound wq is usually beneficial due to the increased
diff --git a/Documentation/x86/x86_64/kernel-stacks b/Documentation/x86/x86_64/kernel-stacks
index 5ad65d5..a01eec5 100644
--- a/Documentation/x86/x86_64/kernel-stacks
+++ b/Documentation/x86/x86_64/kernel-stacks
@@ -18,9 +18,9 @@
   Used for external hardware interrupts.  If this is the first external
   hardware interrupt (i.e. not a nested hardware interrupt) then the
   kernel switches from the current task to the interrupt stack.  Like
-  the split thread and interrupt stacks on i386 (with CONFIG_4KSTACKS),
-  this gives more room for kernel interrupt processing without having
-  to increase the size of every per thread stack.
+  the split thread and interrupt stacks on i386, this gives more room
+  for kernel interrupt processing without having to increase the size
+  of every per thread stack.
 
   The interrupt stack is also used when processing a softirq.
 
diff --git a/MAINTAINERS b/MAINTAINERS
index f2a2b8e..b618b1e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -990,11 +990,23 @@
 F:	arch/arm/mach-shmobile/
 F:	drivers/sh/
 
+ARM/TELECHIPS ARM ARCHITECTURE
+M:	"Hans J. Koch" <hjk@linutronix.de>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/plat-tcc/
+F:	arch/arm/mach-tcc8k/
+
 ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 
+ARM/TETON BGA MACHINE SUPPORT
+M:	Mark F. Brown <mark.brown314@gmail.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+
 ARM/THECUS N2100 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1527,6 +1539,8 @@
 S:	Supported
 F:	Documentation/filesystems/ceph.txt
 F:	fs/ceph
+F:	net/ceph
+F:	include/linux/ceph
 
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 M:	David Vrabel <david.vrabel@csr.com>
@@ -3239,6 +3253,12 @@
 F:	include/net/irda/
 F:	net/irda/
 
+IRQ SUBSYSTEM
+M:	Thomas Gleixner <tglx@linutronix.de>
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git irq/core
+F:	kernel/irq/
+
 ISAPNP
 M:	Jaroslav Kysela <perex@perex.cz>
 S:	Maintained
@@ -4805,6 +4825,15 @@
 F:	include/linux/qnx4_fs.h
 F:	include/linux/qnxtypes.h
 
+RADOS BLOCK DEVICE (RBD)
+F:	include/linux/qnxtypes.h
+M:	Yehuda Sadeh <yehuda@hq.newdream.net>
+M:	Sage Weil <sage@newdream.net>
+M:	ceph-devel@vger.kernel.org
+S:	Supported
+F:	drivers/block/rbd.c
+F:	drivers/block/rbd_types.h
+
 RADEON FRAMEBUFFER DISPLAY DRIVER
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 L:	linux-fbdev@vger.kernel.org
diff --git a/Makefile b/Makefile
index 860c26a..3e43805 100644
--- a/Makefile
+++ b/Makefile
@@ -554,8 +554,15 @@
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 else
+# Some targets (ARM with Thumb2, for example), can't be built with frame
+# pointers.  For those, we don't have FUNCTION_TRACER automatically
+# select FRAME_POINTER.  However, FUNCTION_TRACER adds -pg, and this is
+# incompatible with -fomit-frame-pointer with current GCC, so we don't use
+# -fomit-frame-pointer with FUNCTION_TRACER.
+ifndef CONFIG_FUNCTION_TRACER
 KBUILD_CFLAGS	+= -fomit-frame-pointer
 endif
+endif
 
 ifdef CONFIG_DEBUG_INFO
 KBUILD_CFLAGS	+= -g
@@ -568,6 +575,12 @@
 
 ifdef CONFIG_FUNCTION_TRACER
 KBUILD_CFLAGS	+= -pg
+ifdef CONFIG_DYNAMIC_FTRACE
+	ifdef CONFIG_HAVE_C_RECORDMCOUNT
+		BUILD_C_RECORDMCOUNT := y
+		export BUILD_C_RECORDMCOUNT
+	endif
+endif
 endif
 
 # We trigger additional mismatches with less inlining
@@ -591,6 +604,11 @@
 # conserve stack if available
 KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
 
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
 # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
 # But warn user when we do so
 warn-assign = \
diff --git a/arch/Kconfig b/arch/Kconfig
index fe48fc7..53d7f61 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -158,4 +158,7 @@
 	  subsystem.  Also has support for calculating CPU cycle events
 	  to determine how many clock cycles in a given period.
 
+config HAVE_ARCH_JUMP_LABEL
+	bool
+
 source "kernel/gcov/Kconfig"
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index b9647bb..d04ccd7 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -9,6 +9,7 @@
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_DMA_ATTRS
 	help
diff --git a/arch/alpha/include/asm/irqflags.h b/arch/alpha/include/asm/irqflags.h
new file mode 100644
index 0000000..299bbc7
--- /dev/null
+++ b/arch/alpha/include/asm/irqflags.h
@@ -0,0 +1,67 @@
+#ifndef __ALPHA_IRQFLAGS_H
+#define __ALPHA_IRQFLAGS_H
+
+#include <asm/system.h>
+
+#define IPL_MIN		0
+#define IPL_SW0		1
+#define IPL_SW1		2
+#define IPL_DEV0	3
+#define IPL_DEV1	4
+#define IPL_TIMER	5
+#define IPL_PERF	6
+#define IPL_POWERFAIL	6
+#define IPL_MCHECK	7
+#define IPL_MAX		7
+
+#ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK
+#undef IPL_MIN
+#define IPL_MIN		__min_ipl
+extern int __min_ipl;
+#endif
+
+#define getipl()		(rdps() & 7)
+#define setipl(ipl)		((void) swpipl(ipl))
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	return rdps();
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	setipl(IPL_MAX);
+	barrier();
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = swpipl(IPL_MAX);
+	barrier();
+	return flags;
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	barrier();
+	setipl(IPL_MIN);
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	barrier();
+	setipl(flags);
+	barrier();
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags == IPL_MAX;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(getipl());
+}
+
+#endif /* __ALPHA_IRQFLAGS_H */
diff --git a/arch/alpha/include/asm/perf_event.h b/arch/alpha/include/asm/perf_event.h
index 4157cd3..fe792ca 100644
--- a/arch/alpha/include/asm/perf_event.h
+++ b/arch/alpha/include/asm/perf_event.h
@@ -1,11 +1,6 @@
 #ifndef __ASM_ALPHA_PERF_EVENT_H
 #define __ASM_ALPHA_PERF_EVENT_H
 
-/* Alpha only supports software events through this interface. */
-extern void set_perf_event_pending(void);
-
-#define PERF_EVENT_INDEX_OFFSET 0
-
 #ifdef CONFIG_PERF_EVENTS
 extern void init_hw_perf_events(void);
 #else
diff --git a/arch/alpha/include/asm/system.h b/arch/alpha/include/asm/system.h
index 5aa40cc..9f78e69 100644
--- a/arch/alpha/include/asm/system.h
+++ b/arch/alpha/include/asm/system.h
@@ -259,34 +259,6 @@
 __CALL_PAL_W1(wrusp, unsigned long);
 __CALL_PAL_W1(wrvptptr, unsigned long);
 
-#define IPL_MIN		0
-#define IPL_SW0		1
-#define IPL_SW1		2
-#define IPL_DEV0	3
-#define IPL_DEV1	4
-#define IPL_TIMER	5
-#define IPL_PERF	6
-#define IPL_POWERFAIL	6
-#define IPL_MCHECK	7
-#define IPL_MAX		7
-
-#ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK
-#undef IPL_MIN
-#define IPL_MIN		__min_ipl
-extern int __min_ipl;
-#endif
-
-#define getipl()		(rdps() & 7)
-#define setipl(ipl)		((void) swpipl(ipl))
-
-#define local_irq_disable()			do { setipl(IPL_MAX); barrier(); } while(0)
-#define local_irq_enable()			do { barrier(); setipl(IPL_MIN); } while(0)
-#define local_save_flags(flags)	((flags) = rdps())
-#define local_irq_save(flags)	do { (flags) = swpipl(IPL_MAX); barrier(); } while(0)
-#define local_irq_restore(flags)	do { barrier(); setipl(flags); barrier(); } while(0)
-
-#define irqs_disabled()	(getipl() == IPL_MAX)
-
 /*
  * TB routines..
  */
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 85d8e4f..1cc4968 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -307,7 +307,7 @@
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count  - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
+	delta = (new_raw_count - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
 
 	/* It is possible on very rare occasions that the PMC has overflowed
 	 * but the interrupt is yet to come.  Detect and fix this situation.
@@ -402,14 +402,13 @@
 		struct hw_perf_event *hwc = &pe->hw;
 		int idx = hwc->idx;
 
-		if (cpuc->current_idx[j] != PMC_NO_INDEX) {
-			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
-			continue;
+		if (cpuc->current_idx[j] == PMC_NO_INDEX) {
+			alpha_perf_event_set_period(pe, hwc, idx);
+			cpuc->current_idx[j] = idx;
 		}
 
-		alpha_perf_event_set_period(pe, hwc, idx);
-		cpuc->current_idx[j] = idx;
-		cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
+		if (!(hwc->state & PERF_HES_STOPPED))
+			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
 	}
 	cpuc->config = cpuc->event[0]->hw.config_base;
 }
@@ -420,12 +419,13 @@
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static int alpha_pmu_enable(struct perf_event *event)
+static int alpha_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	int n0;
 	int ret;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	/*
 	 * The Sparc code has the IRQ disable first followed by the perf
@@ -435,8 +435,8 @@
 	 * nevertheless we disable the PMCs first to enable a potential
 	 * final PMI to occur before we disable interrupts.
 	 */
-	perf_disable();
-	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+	local_irq_save(irq_flags);
 
 	/* Default to error to be returned */
 	ret = -EAGAIN;
@@ -455,8 +455,12 @@
 		}
 	}
 
-	local_irq_restore(flags);
-	perf_enable();
+	hwc->state = PERF_HES_UPTODATE;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_STOPPED;
+
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 
 	return ret;
 }
@@ -467,15 +471,15 @@
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static void alpha_pmu_disable(struct perf_event *event)
+static void alpha_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	unsigned long flags;
+	unsigned long irq_flags;
 	int j;
 
-	perf_disable();
-	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+	local_irq_save(irq_flags);
 
 	for (j = 0; j < cpuc->n_events; j++) {
 		if (event == cpuc->event[j]) {
@@ -501,8 +505,8 @@
 		}
 	}
 
-	local_irq_restore(flags);
-	perf_enable();
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 }
 
 
@@ -514,13 +518,44 @@
 }
 
 
-static void alpha_pmu_unthrottle(struct perf_event *event)
+static void alpha_pmu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		cpuc->idx_mask &= ~(1UL<<hwc->idx);
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		alpha_perf_event_update(event, hwc, hwc->idx, 0);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_DISABLE, (1UL<<hwc->idx));
+}
+
+
+static void alpha_pmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+		alpha_perf_event_set_period(event, hwc, hwc->idx);
+	}
+
+	hwc->state = 0;
+
 	cpuc->idx_mask |= 1UL<<hwc->idx;
-	wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
 }
 
 
@@ -642,39 +677,36 @@
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= alpha_pmu_enable,
-	.disable	= alpha_pmu_disable,
-	.read		= alpha_pmu_read,
-	.unthrottle	= alpha_pmu_unthrottle,
-};
-
-
 /*
  * Main entry point to initialise a HW performance event.
  */
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int alpha_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!alpha_pmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	/* Do the real initialisation work. */
 	err = __hw_perf_event_init(event);
 
-	if (err)
-		return ERR_PTR(err);
-
-	return &pmu;
+	return err;
 }
 
-
-
 /*
  * Main entry point - enable HW performance counters.
  */
-void hw_perf_enable(void)
+static void alpha_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -700,7 +732,7 @@
  * Main entry point - disable HW performance counters.
  */
 
-void hw_perf_disable(void)
+static void alpha_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -713,6 +745,17 @@
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= alpha_pmu_enable,
+	.pmu_disable	= alpha_pmu_disable,
+	.event_init	= alpha_pmu_event_init,
+	.add		= alpha_pmu_add,
+	.del		= alpha_pmu_del,
+	.start		= alpha_pmu_start,
+	.stop		= alpha_pmu_stop,
+	.read		= alpha_pmu_read,
+};
+
 
 /*
  * Main entry point - don't know when this is called but it
@@ -766,7 +809,7 @@
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 
 	/* la_ptr is the counter that overflowed. */
-	if (unlikely(la_ptr >= perf_max_events)) {
+	if (unlikely(la_ptr >= alpha_pmu->num_pmcs)) {
 		/* This should never occur! */
 		irq_err_count++;
 		pr_warning("PMI: silly index %ld\n", la_ptr);
@@ -807,7 +850,7 @@
 			/* Interrupts coming too quickly; "throttle" the
 			 * counter, i.e., disable it for a little while.
 			 */
-			cpuc->idx_mask &= ~(1UL<<idx);
+			alpha_pmu_stop(event, 0);
 		}
 	}
 	wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
@@ -837,6 +880,7 @@
 
 	/* And set up PMU specification */
 	alpha_pmu = &ev67_pmu;
-	perf_max_events = alpha_pmu->num_pmcs;
+
+	perf_pmu_register(&pmu);
 }
 
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index 396af17..0f1d849 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -41,7 +41,7 @@
 #include <linux/init.h>
 #include <linux/bcd.h>
 #include <linux/profile.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -83,25 +83,25 @@
 
 unsigned long est_cycle_freq;
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
 
-DEFINE_PER_CPU(u8, perf_event_pending);
+DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_perf_event_pending_flag()  __get_cpu_var(perf_event_pending) = 1
-#define test_perf_event_pending()      __get_cpu_var(perf_event_pending)
-#define clear_perf_event_pending()     __get_cpu_var(perf_event_pending) = 0
+#define set_irq_work_pending_flag()  __get_cpu_var(irq_work_pending) = 1
+#define test_irq_work_pending()      __get_cpu_var(irq_work_pending)
+#define clear_irq_work_pending()     __get_cpu_var(irq_work_pending) = 0
 
-void set_perf_event_pending(void)
+void set_irq_work_pending(void)
 {
-	set_perf_event_pending_flag();
+	set_irq_work_pending_flag();
 }
 
-#else  /* CONFIG_PERF_EVENTS */
+#else  /* CONFIG_IRQ_WORK */
 
-#define test_perf_event_pending()      0
-#define clear_perf_event_pending()
+#define test_irq_work_pending()      0
+#define clear_irq_work_pending()
 
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_IRQ_WORK */
 
 
 static inline __u32 rpcc(void)
@@ -191,9 +191,9 @@
 
 	write_sequnlock(&xtime_lock);
 
-	if (test_perf_event_pending()) {
-		clear_perf_event_pending();
-		perf_event_do_pending();
+	if (test_irq_work_pending()) {
+		clear_irq_work_pending();
+		irq_work_run();
 	}
 
 #ifndef CONFIG_SMP
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9c26ba7..3849887 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -19,13 +19,17 @@
 	select HAVE_KPROBES if (!XIP_KERNEL)
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
 	select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
+	select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
+	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL)
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V7))
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -145,6 +149,9 @@
 	  and that the relevant menu configurations are displayed for
 	  it.
 
+config ARCH_HAS_CPU_IDLE_WAIT
+       def_bool y
+
 config GENERIC_HWEIGHT
 	bool
 	default y
@@ -510,6 +517,7 @@
 	select GENERIC_CLOCKEVENTS
 	select TICK_ONESHOT
 	select PLAT_PXA
+	select SPARSE_IRQ
 	help
 	  Support for Marvell's PXA168/PXA910(MMP) and MMP2 processor line.
 
@@ -587,6 +595,7 @@
 	select GENERIC_CLOCKEVENTS
 	select TICK_ONESHOT
 	select PLAT_PXA
+	select SPARSE_IRQ
 	help
 	  Support for Intel/Marvell's PXA2xx/PXA3xx processor line.
 
@@ -678,8 +687,8 @@
 	help
 	  Samsung S3C64XX series based systems
 
-config ARCH_S5P6440
-	bool "Samsung S5P6440"
+config ARCH_S5P64X0
+	bool "Samsung S5P6440 S5P6450"
 	select CPU_V6
 	select GENERIC_GPIO
 	select HAVE_CLK
@@ -688,7 +697,8 @@
 	select HAVE_S3C2410_I2C
 	select HAVE_S3C_RTC
 	help
-	  Samsung S5P6440 CPU based systems
+	  Samsung S5P64X0 CPU based systems, such as the Samsung SMDK6440,
+	  SMDK6450.
 
 config ARCH_S5P6442
 	bool "Samsung S5P6442"
@@ -747,6 +757,15 @@
 	  Support for the StrongARM based Digital DNARD machine, also known
 	  as "Shark" (<http://www.shark-linux.de/shark.html>).
 
+config ARCH_TCC_926
+	bool "Telechips TCC ARM926-based systems"
+	select CPU_ARM926T
+	select HAVE_CLK
+	select COMMON_CLKDEV
+	select GENERIC_CLOCKEVENTS
+	help
+	  Support for Telechips TCC ARM926-based systems.
+
 config ARCH_LH7A40X
 	bool "Sharp LH7A40X"
 	select CPU_ARM922T
@@ -915,6 +934,8 @@
 
 source "arch/arm/plat-spear/Kconfig"
 
+source "arch/arm/plat-tcc/Kconfig"
+
 if ARCH_S3C2410
 source "arch/arm/mach-s3c2400/Kconfig"
 source "arch/arm/mach-s3c2410/Kconfig"
@@ -928,7 +949,7 @@
 source "arch/arm/mach-s3c64xx/Kconfig"
 endif
 
-source "arch/arm/mach-s5p6440/Kconfig"
+source "arch/arm/mach-s5p64x0/Kconfig"
 
 source "arch/arm/mach-s5p6442/Kconfig"
 
@@ -1002,7 +1023,7 @@
 
 config ARM_ERRATA_411920
 	bool "ARM errata: Invalidation of the Instruction Cache operation can fail"
-	depends on CPU_V6 && !SMP
+	depends on CPU_V6
 	help
 	  Invalidation of the Instruction Cache operation can
 	  fail. This erratum is present in 1136 (before r1p4), 1156 and 1176.
@@ -1181,13 +1202,13 @@
 
 config SMP
 	bool "Symmetric Multi-Processing (EXPERIMENTAL)"
-	depends on EXPERIMENTAL && (REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP ||\
-		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 ||\
-		 ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4)
+	depends on EXPERIMENTAL
 	depends on GENERIC_CLOCKEVENTS
+	depends on REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP || \
+		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 ||\
+		 ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4
 	select USE_GENERIC_SMP_HELPERS
-	select HAVE_ARM_SCU if ARCH_REALVIEW || ARCH_OMAP4 || ARCH_S5PV310 ||\
-		 ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4
+	select HAVE_ARM_SCU
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
@@ -1205,6 +1226,19 @@
 
 	  If you don't know what to do here, say N.
 
+config SMP_ON_UP
+	bool "Allow booting SMP kernel on uniprocessor systems (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on SMP && !XIP && !THUMB2_KERNEL
+	default y
+	help
+	  SMP kernels contain instructions which fail on non-SMP processors.
+	  Enabling this option allows the kernel to modify itself to make
+	  these instructions safe.  Disabling it allows about 1K of space
+	  savings.
+
+	  If you don't know what to do here, say Y.
+
 config HAVE_ARM_SCU
 	bool
 	depends on SMP
@@ -1255,12 +1289,9 @@
 
 config LOCAL_TIMERS
 	bool "Use local timer interrupts"
-	depends on SMP && (REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || \
-		REALVIEW_EB_A9MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
-		ARCH_S5PV310 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4)
+	depends on SMP
 	default y
-	select HAVE_ARM_TWD if ARCH_REALVIEW || ARCH_OMAP4 || ARCH_S5PV310 || \
-		ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS
+	select HAVE_ARM_TWD
 	help
 	  Enable support for local timers on SMP platforms, rather then the
 	  legacy IPI broadcast method.  Local timers allows the system
@@ -1271,7 +1302,7 @@
 
 config HZ
 	int
-	default 200 if ARCH_EBSA110 || ARCH_S3C2410 || ARCH_S5P6440 || \
+	default 200 if ARCH_EBSA110 || ARCH_S3C2410 || ARCH_S5P64X0 || \
 		ARCH_S5P6442 || ARCH_S5PV210 || ARCH_S5PV310
 	default OMAP_32K_TIMER_HZ if ARCH_OMAP && OMAP_32K_TIMER
 	default AT91_TIMER_HZ if ARCH_AT91
@@ -1477,6 +1508,20 @@
 	  However, if the CPU data cache is using a write-allocate mode,
 	  this option is unlikely to provide any performance gain.
 
+config SECCOMP
+	bool
+	prompt "Enable seccomp to safely compute untrusted bytecode"
+	---help---
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+	  and the task is only allowed to execute a few safe syscalls
+	  defined by each seccomp mode.
+
 config CC_STACKPROTECTOR
 	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
 	help
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 91344af..2fd0b99 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -2,6 +2,20 @@
 
 source "lib/Kconfig.debug"
 
+config STRICT_DEVMEM
+	bool "Filter access to /dev/mem"
+	depends on MMU
+	---help---
+	  If this option is disabled, you allow userspace (root) access to all
+	  of memory, including kernel and userspace memory. Accidental
+	  access to this is obviously disastrous, but specific access can
+	  be used by people debugging the kernel.
+
+	  If this option is switched on, the /dev/mem file only allows
+	  userspace access to memory mapped peripherals.
+
+          If in doubt, say Y.
+
 # RMK wants arm kernels compiled with frame pointers or stack unwinding.
 # If you know what you are doing and are willing to live without stack
 # traces, you can get a slightly smaller kernel by setting this option to
@@ -27,6 +41,11 @@
 	  the performance is not affected. Currently, this feature
 	  only works with EABI compilers. If unsure say Y.
 
+config OLD_MCOUNT
+	bool
+	depends on FUNCTION_TRACER && FRAME_POINTER
+	default y
+
 config DEBUG_USER
 	bool "Verbose user fault messages"
 	help
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 59c1ce8..b87aed0 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -173,7 +173,7 @@
 machine-$(CONFIG_ARCH_S3C2410)		:= s3c2410 s3c2400 s3c2412 s3c2416 s3c2440 s3c2443
 machine-$(CONFIG_ARCH_S3C24A0)		:= s3c24a0
 machine-$(CONFIG_ARCH_S3C64XX)		:= s3c64xx
-machine-$(CONFIG_ARCH_S5P6440)		:= s5p6440
+machine-$(CONFIG_ARCH_S5P64X0)		:= s5p64x0
 machine-$(CONFIG_ARCH_S5P6442)		:= s5p6442
 machine-$(CONFIG_ARCH_S5PC100)		:= s5pc100
 machine-$(CONFIG_ARCH_S5PV210)		:= s5pv210
@@ -183,6 +183,7 @@
 machine-$(CONFIG_ARCH_SHMOBILE) 	:= shmobile
 machine-$(CONFIG_ARCH_STMP378X)		:= stmp378x
 machine-$(CONFIG_ARCH_STMP37XX)		:= stmp37xx
+machine-$(CONFIG_ARCH_TCC8K)		:= tcc8k
 machine-$(CONFIG_ARCH_TEGRA)		:= tegra
 machine-$(CONFIG_ARCH_U300)		:= u300
 machine-$(CONFIG_ARCH_U8500)		:= ux500
@@ -202,6 +203,7 @@
 plat-$(CONFIG_ARCH_OMAP)	:= omap
 plat-$(CONFIG_ARCH_S3C64XX)	:= samsung
 plat-$(CONFIG_ARCH_STMP3XXX)	:= stmp3xxx
+plat-$(CONFIG_ARCH_TCC_926)	:= tcc
 plat-$(CONFIG_PLAT_IOP)		:= iop
 plat-$(CONFIG_PLAT_NOMADIK)	:= nomadik
 plat-$(CONFIG_PLAT_ORION)	:= orion
@@ -245,13 +247,14 @@
 FASTFPE_OBJ	:=$(FASTFPE)/
 endif
 
-# If we have a machine-specific directory, then include it in the build.
-core-y				+= arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
-core-y				+= $(machdirs) $(platdirs)
 core-$(CONFIG_FPE_NWFPE)	+= arch/arm/nwfpe/
 core-$(CONFIG_FPE_FASTFPE)	+= $(FASTFPE_OBJ)
 core-$(CONFIG_VFP)		+= arch/arm/vfp/
 
+# If we have a machine-specific directory, then include it in the build.
+core-y				+= arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
+core-y				+= $(machdirs) $(platdirs)
+
 drivers-$(CONFIG_OPROFILE)      += arch/arm/oprofile/
 
 libs-y				:= arch/arm/lib/ $(libs-y)
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 7dfa9a8..ada6359 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -67,25 +67,11 @@
 
 /*
  * Routines to acknowledge, disable and enable interrupts
- *
- * Linux assumes that when we're done with an interrupt we need to
- * unmask it, in the same way we need to unmask an interrupt when
- * we first enable it.
- *
- * The GIC has a separate notion of "end of interrupt" to re-enable
- * an interrupt after handling, in order to support hardware
- * prioritisation.
- *
- * We can make the GIC behave in the way that Linux expects by making
- * our "acknowledge" routine disable the interrupt, then mark it as
- * complete.
  */
 static void gic_ack_irq(unsigned int irq)
 {
-	u32 mask = 1 << (irq % 32);
 
 	spin_lock(&irq_controller_lock);
-	writel(mask, gic_dist_base(irq) + GIC_DIST_ENABLE_CLEAR + (gic_irq(irq) / 32) * 4);
 	writel(gic_irq(irq), gic_cpu_base(irq) + GIC_CPU_EOI);
 	spin_unlock(&irq_controller_lock);
 }
diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c
index 5ebbab6..8f0f86d 100644
--- a/arch/arm/common/pl330.c
+++ b/arch/arm/common/pl330.c
@@ -146,8 +146,7 @@
 #define DESIGNER	0x41
 #define REVISION	0x0
 #define INTEG_CFG	0x0
-#define PERIPH_ID_VAL	((PART << 0) | (DESIGNER << 12) \
-			  | (REVISION << 20) | (INTEG_CFG << 24))
+#define PERIPH_ID_VAL	((PART << 0) | (DESIGNER << 12))
 
 #define PCELL_ID_VAL	0xb105f00d
 
@@ -1859,10 +1858,10 @@
 	regs = pi->base;
 
 	/* Check if we can handle this DMAC */
-	if (get_id(pi, PERIPH_ID) != PERIPH_ID_VAL
+	if ((get_id(pi, PERIPH_ID) & 0xfffff) != PERIPH_ID_VAL
 	   || get_id(pi, PCELL_ID) != PCELL_ID_VAL) {
 		dev_err(pi->dev, "PERIPH_ID 0x%x, PCELL_ID 0x%x !\n",
-			readl(regs + PERIPH_ID), readl(regs + PCELL_ID));
+			get_id(pi, PERIPH_ID), get_id(pi, PCELL_ID));
 		return -EINVAL;
 	}
 
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 517d50d..c0258a8 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -678,7 +678,7 @@
  *	%-EBUSY		physical address already marked in-use.
  *	%0		successful.
  */
-static int
+static int __devinit
 __sa1111_probe(struct device *me, struct resource *mem, int irq)
 {
 	struct sa1111 *sachip;
diff --git a/arch/arm/configs/at91sam9g20ek_defconfig b/arch/arm/configs/at91sam9g20ek_defconfig
index f1bac70..9e90e6d 100644
--- a/arch/arm/configs/at91sam9g20ek_defconfig
+++ b/arch/arm/configs/at91sam9g20ek_defconfig
@@ -13,6 +13,7 @@
 CONFIG_ARCH_AT91=y
 CONFIG_ARCH_AT91SAM9G20=y
 CONFIG_MACH_AT91SAM9G20EK=y
+CONFIG_MACH_AT91SAM9G20EK_2MMC=y
 CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
 # CONFIG_ARM_THUMB is not set
 CONFIG_AEABI=y
diff --git a/arch/arm/configs/kirkwood_defconfig b/arch/arm/configs/kirkwood_defconfig
index ccc9c99..2f70428 100644
--- a/arch/arm/configs/kirkwood_defconfig
+++ b/arch/arm/configs/kirkwood_defconfig
@@ -15,6 +15,7 @@
 CONFIG_MACH_SHEEVAPLUG=y
 CONFIG_MACH_ESATA_SHEEVAPLUG=y
 CONFIG_MACH_GURUPLUG=y
+CONFIG_MACH_DOCKSTAR=y
 CONFIG_MACH_TS219=y
 CONFIG_MACH_TS41X=y
 CONFIG_MACH_OPENRD_BASE=y
diff --git a/arch/arm/configs/mx27_defconfig b/arch/arm/configs/mx27_defconfig
index b2038b0..813cfb3 100644
--- a/arch/arm/configs/mx27_defconfig
+++ b/arch/arm/configs/mx27_defconfig
@@ -21,8 +21,14 @@
 CONFIG_MACH_MX27=y
 CONFIG_MACH_MX27ADS=y
 CONFIG_MACH_PCM038=y
+CONFIG_MACH_CPUIMX27=y
+CONFIG_MACH_EUKREA_CPUIMX27_USESDHC2=y
+CONFIG_MACH_EUKREA_CPUIMX27_USEUART4=y
 CONFIG_MACH_MX27_3DS=y
+CONFIG_MACH_IMX27_VISSTRIM_M10=y
 CONFIG_MACH_IMX27LITE=y
+CONFIG_MACH_PCA100=y
+CONFIG_MACH_MXT_TD60=y
 CONFIG_MXC_IRQ_PRIOR=y
 CONFIG_MXC_PWM=y
 CONFIG_NO_HZ=y
@@ -76,7 +82,9 @@
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=m
 # CONFIG_SERIO is not set
+CONFIG_SERIAL_8250=m
 CONFIG_SERIAL_IMX=y
 CONFIG_SERIAL_IMX_CONSOLE=y
 # CONFIG_LEGACY_PTYS is not set
@@ -85,19 +93,20 @@
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_IMX=y
 CONFIG_SPI=y
-CONFIG_SPI_BITBANG=y
+CONFIG_SPI_IMX=y
 CONFIG_W1=y
 CONFIG_W1_MASTER_MXC=y
 CONFIG_W1_SLAVE_THERM=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_IMX=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
 # CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
+CONFIG_USB=m
+# CONFIG_USB_DEVICE_CLASS is not set
+CONFIG_USB_ULPI=y
 CONFIG_MMC=y
 CONFIG_MMC_MXC=y
 CONFIG_RTC_CLASS=y
diff --git a/arch/arm/configs/mx31pdk_defconfig b/arch/arm/configs/mx31pdk_defconfig
deleted file mode 100644
index 2d29329..0000000
--- a/arch/arm/configs/mx31pdk_defconfig
+++ /dev/null
@@ -1,44 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-# CONFIG_SWAP is not set
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_COMPAT_BRK is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_ARCH_MXC=y
-# CONFIG_MACH_MX31ADS is not set
-CONFIG_MACH_MX31_3DS=y
-CONFIG_AEABI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_INET_LRO is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FIRMWARE_IN_KERNEL is not set
-# CONFIG_BLK_DEV is not set
-# CONFIG_MISC_DEVICES is not set
-CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_IMX=y
-CONFIG_SERIAL_IMX_CONSOLE=y
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
-# CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
-# CONFIG_DNOTIFY is not set
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
-# CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRC32 is not set
diff --git a/arch/arm/configs/mx3_defconfig b/arch/arm/configs/mx3_defconfig
index 161f907..f0c339f 100644
--- a/arch/arm/configs/mx3_defconfig
+++ b/arch/arm/configs/mx3_defconfig
@@ -24,6 +24,7 @@
 CONFIG_MACH_ARMADILLO5X0=y
 CONFIG_MACH_MX35_3DS=y
 CONFIG_MACH_KZM_ARM11_01=y
+CONFIG_MACH_EUKREA_CPUIMX35=y
 CONFIG_MXC_IRQ_PRIOR=y
 CONFIG_MXC_PWM=y
 CONFIG_NO_HZ=y
@@ -108,7 +109,6 @@
 CONFIG_MMC_MXC=y
 CONFIG_DMADEVICES=y
 # CONFIG_DNOTIFY is not set
-CONFIG_INOTIFY=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
 CONFIG_UBIFS_FS=y
diff --git a/arch/arm/configs/mx51_defconfig b/arch/arm/configs/mx51_defconfig
index a665ecb..163cfee 100644
--- a/arch/arm/configs/mx51_defconfig
+++ b/arch/arm/configs/mx51_defconfig
@@ -15,6 +15,8 @@
 CONFIG_ARCH_MXC=y
 CONFIG_ARCH_MX5=y
 CONFIG_MACH_MX51_BABBAGE=y
+CONFIG_MACH_MX51_3DS=y
+CONFIG_MACH_EUKREA_CPUIMX51=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT_VOLUNTARY=y
@@ -69,7 +71,6 @@
 CONFIG_NATIONAL_PHY=y
 CONFIG_STE10XP=y
 CONFIG_LSI_ET1011C_PHY=y
-CONFIG_FIXED_PHY=y
 CONFIG_MDIO_BITBANG=y
 CONFIG_MDIO_GPIO=y
 CONFIG_NET_ETHERNET=y
@@ -100,7 +101,6 @@
 CONFIG_I2C_ALGOPCA=m
 CONFIG_GPIO_SYSFS=y
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID_SUPPORT is not set
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
@@ -117,13 +117,11 @@
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
 CONFIG_EXT3_FS=y
-CONFIG_EXT3_DEFAULTS_TO_ORDERED=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
-CONFIG_INOTIFY=y
 CONFIG_QUOTA=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -136,6 +134,7 @@
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
 CONFIG_CONFIGFS_FS=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
@@ -151,7 +150,6 @@
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
-# CONFIG_DETECT_SOFTLOCKUP is not set
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_BUGVERBOSE is not set
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
@@ -159,7 +157,6 @@
 # CONFIG_ARM_UNWIND is not set
 CONFIG_DEBUG_LL=y
 CONFIG_EARLY_PRINTK=y
-CONFIG_KEYS=y
 CONFIG_SECURITYFS=y
 CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
diff --git a/arch/arm/configs/realview-smp_defconfig b/arch/arm/configs/realview-smp_defconfig
index 9312ef9..5ca7a61 100644
--- a/arch/arm/configs/realview-smp_defconfig
+++ b/arch/arm/configs/realview-smp_defconfig
@@ -39,6 +39,7 @@
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_ARM_INTEGRATOR=y
+CONFIG_ARM_CHARLCD=y
 CONFIG_NETDEVICES=y
 CONFIG_SMSC_PHY=y
 CONFIG_NET_ETHERNET=y
@@ -52,10 +53,13 @@
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_VERSATILE=y
+CONFIG_SPI=y
+CONFIG_GPIOLIB=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_ARMCLCD=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
@@ -70,7 +74,13 @@
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
 CONFIG_MMC_ARMMMCI=y
-CONFIG_INOTIFY=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_DS1307=y
+CONFIG_RTC_DRV_PL031=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
@@ -80,6 +90,7 @@
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig
index fb75192..fcaa603 100644
--- a/arch/arm/configs/realview_defconfig
+++ b/arch/arm/configs/realview_defconfig
@@ -38,6 +38,7 @@
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_ARM_INTEGRATOR=y
+CONFIG_ARM_CHARLCD=y
 CONFIG_NETDEVICES=y
 CONFIG_SMSC_PHY=y
 CONFIG_NET_ETHERNET=y
@@ -51,10 +52,13 @@
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_VERSATILE=y
+CONFIG_SPI=y
+CONFIG_GPIOLIB=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
 CONFIG_FB_ARMCLCD=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
@@ -69,7 +73,13 @@
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
 CONFIG_MMC_ARMMMCI=y
-CONFIG_INOTIFY=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_DS1307=y
+CONFIG_RTC_DRV_PL031=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
@@ -79,6 +89,7 @@
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
diff --git a/arch/arm/configs/s5p6440_defconfig b/arch/arm/configs/s5p64x0_defconfig
similarity index 97%
rename from arch/arm/configs/s5p6440_defconfig
rename to arch/arm/configs/s5p64x0_defconfig
index 0b0266c..2993ecd 100644
--- a/arch/arm/configs/s5p6440_defconfig
+++ b/arch/arm/configs/s5p64x0_defconfig
@@ -5,10 +5,11 @@
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-CONFIG_ARCH_S5P6440=y
+CONFIG_ARCH_S5P64X0=y
 CONFIG_S3C_BOOT_ERROR_RESET=y
 CONFIG_S3C_LOWLEVEL_UART_PORT=1
 CONFIG_MACH_SMDK6440=y
+CONFIG_MACH_SMDK6450=y
 CONFIG_CPU_32v6K=y
 CONFIG_AEABI=y
 CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x20800000,8M console=ttySAC1,115200 init=/linuxrc"
diff --git a/arch/arm/configs/u300_defconfig b/arch/arm/configs/u300_defconfig
index 46e5e07..c1c252c 100644
--- a/arch/arm/configs/u300_defconfig
+++ b/arch/arm/configs/u300_defconfig
@@ -28,26 +28,9 @@
 CONFIG_FPE_NWFPE=y
 CONFIG_PM=y
 # CONFIG_SUSPEND is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-# CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ECC_SMC=y
+# CONFIG_MISC_DEVICES is not set
 # CONFIG_INPUT_MOUSEDEV is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
@@ -58,7 +41,6 @@
 CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
-CONFIG_POWER_SUPPLY=y
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
 CONFIG_REGULATOR=y
@@ -66,24 +48,10 @@
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_SOUND=y
-CONFIG_SND=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-# CONFIG_SND_DRIVERS is not set
-# CONFIG_SND_ARM is not set
-# CONFIG_SND_SPI is not set
-CONFIG_SND_SOC=y
 # CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
-CONFIG_MMC_DEBUG=y
 CONFIG_MMC_ARMMMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_BACKLIGHT=y
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
 CONFIG_RTC_DRV_COH901331=y
@@ -93,12 +61,11 @@
 CONFIG_FUSE_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
-# CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
-# CONFIG_DETECT_SOFTLOCKUP is not set
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_TIMER_STATS=y
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 6e8f05c..062b58c 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -154,16 +154,39 @@
 	.long	9999b,9001f;			\
 	.popsection
 
+#ifdef CONFIG_SMP
+#define ALT_SMP(instr...)					\
+9998:	instr
+#define ALT_UP(instr...)					\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	instr							;\
+	.popsection
+#define ALT_UP_B(label)					\
+	.equ	up_b_offset, label - 9998b			;\
+	.pushsection ".alt.smp.init", "a"			;\
+	.long	9998b						;\
+	b	. + up_b_offset					;\
+	.popsection
+#else
+#define ALT_SMP(instr...)
+#define ALT_UP(instr...) instr
+#define ALT_UP_B(label) b label
+#endif
+
 /*
  * SMP data memory barrier
  */
 	.macro	smp_dmb
 #ifdef CONFIG_SMP
 #if __LINUX_ARM_ARCH__ >= 7
-	dmb
+	ALT_SMP(dmb)
 #elif __LINUX_ARM_ARCH__ == 6
-	mcr	p15, 0, r0, c7, c10, 5	@ dmb
+	ALT_SMP(mcr	p15, 0, r0, c7, c10, 5)	@ dmb
+#else
+#error Incompatible SMP platform
 #endif
+	ALT_UP(nop)
 #endif
 	.endm
 
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 4656a24..3acd8fa 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -137,10 +137,10 @@
 #endif
 
 /*
- * This flag is used to indicate that the page pointed to by a pte
- * is dirty and requires cleaning before returning it to the user.
+ * This flag is used to indicate that the page pointed to by a pte is clean
+ * and does not require cleaning before returning it to the user.
  */
-#define PG_dcache_dirty PG_arch_1
+#define PG_dcache_clean PG_arch_1
 
 /*
  *	MM Cache Management
@@ -156,6 +156,12 @@
  *	Please note that the implementation of these, and the required
  *	effects are cache-type (VIVT/VIPT/PIPT) specific.
  *
+ *	flush_icache_all()
+ *
+ *		Unconditionally clean and invalidate the entire icache.
+ *		Currently only needed for cache-v6.S and cache-v7.S, see
+ *		__flush_icache_all for the generic implementation.
+ *
  *	flush_kern_all()
  *
  *		Unconditionally clean and invalidate the entire cache.
@@ -206,6 +212,7 @@
  */
 
 struct cpu_cache_fns {
+	void (*flush_icache_all)(void);
 	void (*flush_kern_all)(void);
 	void (*flush_user_all)(void);
 	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
@@ -227,6 +234,7 @@
 
 extern struct cpu_cache_fns cpu_cache;
 
+#define __cpuc_flush_icache_all		cpu_cache.flush_icache_all
 #define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
 #define __cpuc_flush_user_all		cpu_cache.flush_user_all
 #define __cpuc_flush_user_range		cpu_cache.flush_user_range
@@ -246,6 +254,7 @@
 
 #else
 
+#define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
 #define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
 #define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
 #define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
@@ -253,6 +262,7 @@
 #define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
 #define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
 
+extern void __cpuc_flush_icache_all(void);
 extern void __cpuc_flush_kern_all(void);
 extern void __cpuc_flush_user_all(void);
 extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
@@ -291,6 +301,37 @@
 /*
  * Convert calls to our calling convention.
  */
+
+/* Invalidate I-cache */
+#define __flush_icache_all_generic()					\
+	asm("mcr	p15, 0, %0, c7, c5, 0"				\
+	    : : "r" (0));
+
+/* Invalidate I-cache inner shareable */
+#define __flush_icache_all_v7_smp()					\
+	asm("mcr	p15, 0, %0, c7, c1, 0"				\
+	    : : "r" (0));
+
+/*
+ * Optimized __flush_icache_all for the common cases. Note that UP ARMv7
+ * will fall through to use __flush_icache_all_generic.
+ */
+#if (defined(CONFIG_CPU_V7) && defined(CONFIG_CPU_V6)) ||		\
+	defined(CONFIG_SMP_ON_UP)
+#define __flush_icache_preferred	__cpuc_flush_icache_all
+#elif __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+#define __flush_icache_preferred	__flush_icache_all_v7_smp
+#elif __LINUX_ARM_ARCH__ == 6 && defined(CONFIG_ARM_ERRATA_411920)
+#define __flush_icache_preferred	__cpuc_flush_icache_all
+#else
+#define __flush_icache_preferred	__flush_icache_all_generic
+#endif
+
+static inline void __flush_icache_all(void)
+{
+	__flush_icache_preferred();
+}
+
 #define flush_cache_all()		__cpuc_flush_kern_all()
 
 static inline void vivt_flush_cache_mm(struct mm_struct *mm)
@@ -366,21 +407,6 @@
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
-static inline void __flush_icache_all(void)
-{
-#ifdef CONFIG_ARM_ERRATA_411920
-	extern void v6_icache_inval_all(void);
-	v6_icache_inval_all();
-#elif defined(CONFIG_SMP) && __LINUX_ARM_ARCH__ >= 7
-	asm("mcr	p15, 0, %0, c7, c1, 0	@ invalidate I-cache inner shareable\n"
-	    :
-	    : "r" (0));
-#else
-	asm("mcr	p15, 0, %0, c7, c5, 0	@ invalidate I-cache\n"
-	    :
-	    : "r" (0));
-#endif
-}
 static inline void flush_kernel_vmap_range(void *addr, int size)
 {
 	if ((cache_is_vivt() || cache_is_vipt_aliasing()))
@@ -405,9 +431,6 @@
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 static inline void flush_kernel_dcache_page(struct page *page)
 {
-	/* highmem pages are always flushed upon kunmap already */
-	if ((cache_is_vivt() || cache_is_vipt_aliasing()) && !PageHighMem(page))
-		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 }
 
 #define flush_dcache_mmap_lock(mapping) \
diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h
index d3a4c2c..c023db0 100644
--- a/arch/arm/include/asm/cachetype.h
+++ b/arch/arm/include/asm/cachetype.h
@@ -6,6 +6,7 @@
 #define CACHEID_VIPT_ALIASING		(1 << 2)
 #define CACHEID_VIPT			(CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING)
 #define CACHEID_ASID_TAGGED		(1 << 3)
+#define CACHEID_VIPT_I_ALIASING		(1 << 4)
 
 extern unsigned int cacheid;
 
@@ -14,15 +15,18 @@
 #define cache_is_vipt_nonaliasing()	cacheid_is(CACHEID_VIPT_NONALIASING)
 #define cache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_ALIASING)
 #define icache_is_vivt_asid_tagged()	cacheid_is(CACHEID_ASID_TAGGED)
+#define icache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_I_ALIASING)
 
 /*
  * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture
  * Mask out support which will never be present on newer CPUs.
  * - v6+ is never VIVT
- * - v7+ VIPT never aliases
+ * - v7+ VIPT never aliases on D-side
  */
 #if __LINUX_ARM_ARCH__ >= 7
-#define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING | CACHEID_ASID_TAGGED)
+#define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING |\
+				 CACHEID_ASID_TAGGED |\
+				 CACHEID_VIPT_I_ALIASING)
 #elif __LINUX_ARM_ARCH__ >= 6
 #define	__CACHEID_ARCH_MIN	(~CACHEID_VIVT)
 #else
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 5747a8b..8bb66bc 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -127,4 +127,8 @@
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
+extern int vectors_user_mapping(void);
+#define arch_setup_additional_pages(bprm, uses_interp) vectors_user_mapping()
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+
 #endif
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index 103f7ee..f89515a 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -2,12 +2,30 @@
 #define _ASM_ARM_FTRACE
 
 #ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR		((long)(mcount))
+#define MCOUNT_ADDR		((unsigned long)(__gnu_mcount_nc))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
 extern void mcount(void);
 extern void __gnu_mcount_nc(void);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+struct dyn_arch_ftrace {
+#ifdef CONFIG_OLD_MCOUNT
+	bool	old_mcount;
+#endif
+};
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* With Thumb-2, the recorded addresses have the lsb set */
+	return addr & ~1;
+}
+
+extern void ftrace_caller_old(void);
+extern void ftrace_call_old(void);
+#endif
+
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h
index 212e478..7ecd793 100644
--- a/arch/arm/include/asm/hardware/coresight.h
+++ b/arch/arm/include/asm/hardware/coresight.h
@@ -21,18 +21,6 @@
 #define TRACER_RUNNING		BIT(TRACER_RUNNING_BIT)
 #define TRACER_CYCLE_ACC	BIT(TRACER_CYCLE_ACC_BIT)
 
-struct tracectx {
-	unsigned int	etb_bufsz;
-	void __iomem	*etb_regs;
-	void __iomem	*etm_regs;
-	unsigned long	flags;
-	int		ncmppairs;
-	int		etm_portsz;
-	struct device	*dev;
-	struct clk	*emu_clk;
-	struct mutex	mutex;
-};
-
 #define TRACER_TIMEOUT 10000
 
 #define etm_writel(t, v, x) \
@@ -112,10 +100,10 @@
 
 /* ETM status register, "ETM Architecture", 3.3.2 */
 #define ETMR_STATUS		(0x10)
-#define ETMST_OVERFLOW		(1 << 0)
-#define ETMST_PROGBIT		(1 << 1)
-#define ETMST_STARTSTOP		(1 << 2)
-#define ETMST_TRIGGER		(1 << 3)
+#define ETMST_OVERFLOW		BIT(0)
+#define ETMST_PROGBIT		BIT(1)
+#define ETMST_STARTSTOP		BIT(2)
+#define ETMST_TRIGGER		BIT(3)
 
 #define etm_progbit(t)		(etm_readl((t), ETMR_STATUS) & ETMST_PROGBIT)
 #define etm_started(t)		(etm_readl((t), ETMR_STATUS) & ETMST_STARTSTOP)
@@ -123,7 +111,7 @@
 
 #define ETMR_TRACEENCTRL2	0x1c
 #define ETMR_TRACEENCTRL	0x24
-#define ETMTE_INCLEXCL		(1 << 24)
+#define ETMTE_INCLEXCL		BIT(24)
 #define ETMR_TRACEENEVT		0x20
 #define ETMCTRL_OPTS		(ETMCTRL_DO_CPRT | \
 				ETMCTRL_DATA_DO_ADDR | \
@@ -146,12 +134,12 @@
 #define ETBR_CTRL		0x20
 #define ETBR_FORMATTERCTRL	0x304
 #define ETBFF_ENFTC		1
-#define ETBFF_ENFCONT		(1 << 1)
-#define ETBFF_FONFLIN		(1 << 4)
-#define ETBFF_MANUAL_FLUSH	(1 << 6)
-#define ETBFF_TRIGIN		(1 << 8)
-#define ETBFF_TRIGEVT		(1 << 9)
-#define ETBFF_TRIGFL		(1 << 10)
+#define ETBFF_ENFCONT		BIT(1)
+#define ETBFF_FONFLIN		BIT(4)
+#define ETBFF_MANUAL_FLUSH	BIT(6)
+#define ETBFF_TRIGIN		BIT(8)
+#define ETBFF_TRIGEVT		BIT(9)
+#define ETBFF_TRIGFL		BIT(10)
 
 #define etb_writel(t, v, x) \
 	(__raw_writel((v), (t)->etb_regs + (x)))
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
new file mode 100644
index 0000000..4d8ae9d
--- /dev/null
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -0,0 +1,133 @@
+#ifndef _ARM_HW_BREAKPOINT_H
+#define _ARM_HW_BREAKPOINT_H
+
+#ifdef __KERNEL__
+
+struct task_struct;
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+
+struct arch_hw_breakpoint_ctrl {
+		u32 __reserved	: 9,
+		mismatch	: 1,
+				: 9,
+		len		: 8,
+		type		: 2,
+		privilege	: 2,
+		enabled		: 1;
+};
+
+struct arch_hw_breakpoint {
+	u32	address;
+	u32	trigger;
+	struct perf_event *suspended_wp;
+	struct arch_hw_breakpoint_ctrl ctrl;
+};
+
+static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
+{
+	return (ctrl.mismatch << 22) | (ctrl.len << 5) | (ctrl.type << 3) |
+		(ctrl.privilege << 1) | ctrl.enabled;
+}
+
+static inline void decode_ctrl_reg(u32 reg,
+				   struct arch_hw_breakpoint_ctrl *ctrl)
+{
+	ctrl->enabled	= reg & 0x1;
+	reg >>= 1;
+	ctrl->privilege	= reg & 0x3;
+	reg >>= 2;
+	ctrl->type	= reg & 0x3;
+	reg >>= 2;
+	ctrl->len	= reg & 0xff;
+	reg >>= 17;
+	ctrl->mismatch	= reg & 0x1;
+}
+
+/* Debug architecture numbers. */
+#define ARM_DEBUG_ARCH_RESERVED	0	/* In case of ptrace ABI updates. */
+#define ARM_DEBUG_ARCH_V6	1
+#define ARM_DEBUG_ARCH_V6_1	2
+#define ARM_DEBUG_ARCH_V7_ECP14	3
+#define ARM_DEBUG_ARCH_V7_MM	4
+
+/* Breakpoint */
+#define ARM_BREAKPOINT_EXECUTE	0
+
+/* Watchpoints */
+#define ARM_BREAKPOINT_LOAD	1
+#define ARM_BREAKPOINT_STORE	2
+
+/* Privilege Levels */
+#define ARM_BREAKPOINT_PRIV	1
+#define ARM_BREAKPOINT_USER	2
+
+/* Lengths */
+#define ARM_BREAKPOINT_LEN_1	0x1
+#define ARM_BREAKPOINT_LEN_2	0x3
+#define ARM_BREAKPOINT_LEN_4	0xf
+#define ARM_BREAKPOINT_LEN_8	0xff
+
+/* Limits */
+#define ARM_MAX_BRP		16
+#define ARM_MAX_WRP		16
+#define ARM_MAX_HBP_SLOTS	(ARM_MAX_BRP + ARM_MAX_WRP)
+
+/* DSCR method of entry bits. */
+#define ARM_DSCR_MOE(x)			((x >> 2) & 0xf)
+#define ARM_ENTRY_BREAKPOINT		0x1
+#define ARM_ENTRY_ASYNC_WATCHPOINT	0x2
+#define ARM_ENTRY_SYNC_WATCHPOINT	0xa
+
+/* DSCR monitor/halting bits. */
+#define ARM_DSCR_HDBGEN		(1 << 14)
+#define ARM_DSCR_MDBGEN		(1 << 15)
+
+/* opcode2 numbers for the co-processor instructions. */
+#define ARM_OP2_BVR		4
+#define ARM_OP2_BCR		5
+#define ARM_OP2_WVR		6
+#define ARM_OP2_WCR		7
+
+/* Base register numbers for the debug registers. */
+#define ARM_BASE_BVR		64
+#define ARM_BASE_BCR		80
+#define ARM_BASE_WVR		96
+#define ARM_BASE_WCR		112
+
+/* Accessor macros for the debug registers. */
+#define ARM_DBG_READ(M, OP2, VAL) do {\
+	asm volatile("mrc p14, 0, %0, c0," #M ", " #OP2 : "=r" (VAL));\
+} while (0)
+
+#define ARM_DBG_WRITE(M, OP2, VAL) do {\
+	asm volatile("mcr p14, 0, %0, c0," #M ", " #OP2 : : "r" (VAL));\
+} while (0)
+
+struct notifier_block;
+struct perf_event;
+struct pmu;
+
+extern struct pmu perf_ops_bp;
+extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
+				  int *gen_len, int *gen_type);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+					   unsigned long val, void *data);
+
+extern u8 arch_get_debug_arch(void);
+extern u8 arch_get_max_wp_len(void);
+extern void clear_ptrace_hw_breakpoint(struct task_struct *tsk);
+
+int arch_install_hw_breakpoint(struct perf_event *bp);
+void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+void hw_breakpoint_pmu_read(struct perf_event *bp);
+int hw_breakpoint_slots(int type);
+
+#else
+static inline void clear_ptrace_hw_breakpoint(struct task_struct *tsk) {}
+
+#endif	/* CONFIG_HAVE_HW_BREAKPOINT */
+#endif	/* __KERNEL__ */
+#endif	/* _ARM_HW_BREAKPOINT_H */
diff --git a/arch/arm/include/asm/hw_irq.h b/arch/arm/include/asm/hw_irq.h
index 90831f6..5586b7c 100644
--- a/arch/arm/include/asm/hw_irq.h
+++ b/arch/arm/include/asm/hw_irq.h
@@ -24,4 +24,6 @@
 #define IRQF_PROBE	(1 << 1)
 #define IRQF_NOAUTOEN	(1 << 2)
 
+#define ARCH_IRQ_INIT_FLAGS	(IRQ_NOREQUEST | IRQ_NOPROBE)
+
 #endif
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 1261b1f9..815efa2 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -294,6 +294,7 @@
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
 extern int valid_phys_addr_range(unsigned long addr, size_t size);
 extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+extern int devmem_is_allowed(unsigned long pfn);
 #endif
 
 /*
diff --git a/arch/arm/include/asm/irqflags.h b/arch/arm/include/asm/irqflags.h
index 6d09974..1e6cca5 100644
--- a/arch/arm/include/asm/irqflags.h
+++ b/arch/arm/include/asm/irqflags.h
@@ -10,66 +10,85 @@
  */
 #if __LINUX_ARM_ARCH__ >= 6
 
-#define raw_local_irq_save(x)					\
-	({							\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_save\n"	\
-	"cpsid	i"						\
-	: "=r" (x) : : "memory", "cc");				\
-	})
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
 
-#define raw_local_irq_enable()  __asm__("cpsie i	@ __sti" : : : "memory", "cc")
-#define raw_local_irq_disable() __asm__("cpsid i	@ __cli" : : : "memory", "cc")
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_save\n"
+		"	cpsid	i"
+		: "=r" (flags) : : "memory", "cc");
+	return flags;
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile(
+		"	cpsie i			@ arch_local_irq_enable"
+		:
+		:
+		: "memory", "cc");
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile(
+		"	cpsid i			@ arch_local_irq_disable"
+		:
+		:
+		: "memory", "cc");
+}
+
 #define local_fiq_enable()  __asm__("cpsie f	@ __stf" : : : "memory", "cc")
 #define local_fiq_disable() __asm__("cpsid f	@ __clf" : : : "memory", "cc")
-
 #else
 
 /*
  * Save the current interrupt enable state & disable IRQs
  */
-#define raw_local_irq_save(x)					\
-	({							\
-		unsigned long temp;				\
-		(void) (&temp == &x);				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_save\n"	\
-"	orr	%1, %0, #128\n"					\
-"	msr	cpsr_c, %1"					\
-	: "=r" (x), "=r" (temp)					\
-	:							\
-	: "memory", "cc");					\
-	})
-	
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags, temp;
+
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_save\n"
+		"	orr	%1, %0, #128\n"
+		"	msr	cpsr_c, %1"
+		: "=r" (flags), "=r" (temp)
+		:
+		: "memory", "cc");
+	return flags;
+}
+
 /*
  * Enable IRQs
  */
-#define raw_local_irq_enable()					\
-	({							\
-		unsigned long temp;				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_enable\n"	\
-"	bic	%0, %0, #128\n"					\
-"	msr	cpsr_c, %0"					\
-	: "=r" (temp)						\
-	:							\
-	: "memory", "cc");					\
-	})
+static inline void arch_local_irq_enable(void)
+{
+	unsigned long temp;
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_enable\n"
+		"	bic	%0, %0, #128\n"
+		"	msr	cpsr_c, %0"
+		: "=r" (temp)
+		:
+		: "memory", "cc");
+}
 
 /*
  * Disable IRQs
  */
-#define raw_local_irq_disable()					\
-	({							\
-		unsigned long temp;				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_disable\n"	\
-"	orr	%0, %0, #128\n"					\
-"	msr	cpsr_c, %0"					\
-	: "=r" (temp)						\
-	:							\
-	: "memory", "cc");					\
-	})
+static inline void arch_local_irq_disable(void)
+{
+	unsigned long temp;
+	asm volatile(
+		"	mrs	%0, cpsr	@ arch_local_irq_disable\n"
+		"	orr	%0, %0, #128\n"
+		"	msr	cpsr_c, %0"
+		: "=r" (temp)
+		:
+		: "memory", "cc");
+}
 
 /*
  * Enable FIQs
@@ -106,27 +125,31 @@
 /*
  * Save the current interrupt enable state.
  */
-#define raw_local_save_flags(x)					\
-	({							\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_save_flags"	\
-	: "=r" (x) : : "memory", "cc");				\
-	})
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile(
+		"	mrs	%0, cpsr	@ local_save_flags"
+		: "=r" (flags) : : "memory", "cc");
+	return flags;
+}
 
 /*
  * restore saved IRQ & FIQ state
  */
-#define raw_local_irq_restore(x)				\
-	__asm__ __volatile__(					\
-	"msr	cpsr_c, %0		@ local_irq_restore\n"	\
-	:							\
-	: "r" (x)						\
-	: "memory", "cc")
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile(
+		"	msr	cpsr_c, %0	@ local_irq_restore"
+		:
+		: "r" (flags)
+		: "memory", "cc");
+}
 
-#define raw_irqs_disabled_flags(flags)	\
-({					\
-	(int)((flags) & PSR_I_BIT);	\
-})
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags & PSR_I_BIT;
+}
 
 #endif
 #endif
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 8a0dd18..d97a964 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -16,18 +16,15 @@
 
 struct machine_desc {
 	/*
-	 * Note! The first four elements are used
+	 * Note! The first two elements are used
 	 * by assembler code in head.S, head-common.S
 	 */
 	unsigned int		nr;		/* architecture number	*/
-	unsigned int		nr_irqs;	/* number of IRQs */
-	unsigned int		phys_io;	/* start of physical io	*/
-	unsigned int		io_pg_offst;	/* byte offset for io 
-						 * page tabe entry	*/
-
 	const char		*name;		/* architecture name	*/
 	unsigned long		boot_params;	/* tagged list		*/
 
+	unsigned int		nr_irqs;	/* number of IRQs */
+
 	unsigned int		video_start;	/* start of video RAM	*/
 	unsigned int		video_end;	/* end of video RAM	*/
 
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index a0b3cac..71605d9 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -18,7 +18,6 @@
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
-#include <asm-generic/mm_hooks.h>
 
 void __check_kvm_seq(struct mm_struct *mm);
 
@@ -134,4 +133,32 @@
 #define deactivate_mm(tsk,mm)	do { } while (0)
 #define activate_mm(prev,next)	switch_mm(prev, next, NULL)
 
+/*
+ * We are inserting a "fake" vma for the user-accessible vector page so
+ * gdb and friends can get to it through ptrace and /proc/<pid>/mem.
+ * But we also want to remove it before the generic code gets to see it
+ * during process exit or the unmapping of it would  cause total havoc.
+ * (the macro is used as remove_vma() is static to mm/mmap.c)
+ */
+#define arch_exit_mmap(mm) \
+do { \
+	struct vm_area_struct *high_vma = find_vma(mm, 0xffff0000); \
+	if (high_vma) { \
+		BUG_ON(high_vma->vm_next);  /* it should be last */ \
+		if (high_vma->vm_prev) \
+			high_vma->vm_prev->vm_next = NULL; \
+		else \
+			mm->mmap = NULL; \
+		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
+		mm->mmap_cache = NULL; \
+		mm->map_count--; \
+		remove_vma(high_vma); \
+	} \
+} while (0)
+
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+}
+
 #endif
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index e4dfa69..cbb0bc2 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -7,20 +7,27 @@
 
 struct unwind_table;
 
-struct mod_arch_specific
-{
 #ifdef CONFIG_ARM_UNWIND
-	Elf_Shdr *unw_sec_init;
-	Elf_Shdr *unw_sec_devinit;
-	Elf_Shdr *unw_sec_core;
-	Elf_Shdr *sec_init_text;
-	Elf_Shdr *sec_devinit_text;
-	Elf_Shdr *sec_core_text;
-	struct unwind_table *unwind_init;
-	struct unwind_table *unwind_devinit;
-	struct unwind_table *unwind_core;
-#endif
+struct arm_unwind_mapping {
+	Elf_Shdr *unw_sec;
+	Elf_Shdr *sec_text;
+	struct unwind_table *unwind;
 };
+enum {
+	ARM_SEC_INIT,
+	ARM_SEC_DEVINIT,
+	ARM_SEC_CORE,
+	ARM_SEC_EXIT,
+	ARM_SEC_DEVEXIT,
+	ARM_SEC_MAX,
+};
+struct mod_arch_specific {
+	struct arm_unwind_mapping map[ARM_SEC_MAX];
+};
+#else
+struct mod_arch_specific {
+};
+#endif
 
 /*
  * Include the ARM architecture version.
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index b5799a3..c4aa4e8 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -12,18 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/*
- * NOP: on *most* (read: all supported) ARM platforms, the performance
- * counter interrupts are regular interrupts and not an NMI. This
- * means that when we receive the interrupt we can call
- * perf_event_do_pending() that handles all of the work with
- * interrupts disabled.
- */
-static inline void
-set_perf_event_pending(void)
-{
-}
-
 /* ARM performance counters start from 1 (in the cp15 accesses) so use the
  * same indexes here for consistency. */
 #define PERF_EVENT_INDEX_OFFSET 1
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index e90b167..a9672e8 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -278,9 +278,24 @@
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 
-#define set_pte_at(mm,addr,ptep,pteval) do { \
-	set_pte_ext(ptep, pteval, (addr) >= TASK_SIZE ? 0 : PTE_EXT_NG); \
- } while (0)
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	if (addr >= TASK_SIZE)
+		set_pte_ext(ptep, pteval, 0);
+	else {
+		__sync_icache_dcache(pteval);
+		set_pte_ext(ptep, pteval, PTE_EXT_NG);
+	}
+}
 
 /*
  * The following only work if pte_present() is true.
@@ -290,8 +305,13 @@
 #define pte_write(pte)		(pte_val(pte) & L_PTE_WRITE)
 #define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
 #define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
+#define pte_exec(pte)		(pte_val(pte) & L_PTE_EXEC)
 #define pte_special(pte)	(0)
 
+#define pte_present_user(pte) \
+	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
+	 (L_PTE_PRESENT | L_PTE_USER))
+
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 7bed3da..67357ba 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -19,6 +19,7 @@
 
 #ifdef __KERNEL__
 
+#include <asm/hw_breakpoint.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
@@ -41,6 +42,9 @@
 struct debug_info {
 	int			nsaved;
 	struct debug_entry	bp[2];
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	struct perf_event	*hbp[ARM_MAX_HBP_SLOTS];
+#endif
 };
 
 struct thread_struct {
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 7ce15eb..783d50f 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -29,6 +29,8 @@
 #define PTRACE_SETCRUNCHREGS	26
 #define PTRACE_GETVFPREGS	27
 #define PTRACE_SETVFPREGS	28
+#define PTRACE_GETHBPREGS	29
+#define PTRACE_SETHBPREGS	30
 
 /*
  * PSR bits
diff --git a/arch/arm/include/asm/seccomp.h b/arch/arm/include/asm/seccomp.h
new file mode 100644
index 0000000..52b156b
--- /dev/null
+++ b/arch/arm/include/asm/seccomp.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_ARM_SECCOMP_H
+#define _ASM_ARM_SECCOMP_H
+
+#include <linux/unistd.h>
+
+#define __NR_seccomp_read __NR_read
+#define __NR_seccomp_write __NR_write
+#define __NR_seccomp_exit __NR_exit
+#define __NR_seccomp_sigreturn __NR_rt_sigreturn
+
+#endif /* _ASM_ARM_SECCOMP_H */
diff --git a/arch/arm/include/asm/smp_mpidr.h b/arch/arm/include/asm/smp_mpidr.h
new file mode 100644
index 0000000..6a9307d
--- /dev/null
+++ b/arch/arm/include/asm/smp_mpidr.h
@@ -0,0 +1,17 @@
+#ifndef ASMARM_SMP_MIDR_H
+#define ASMARM_SMP_MIDR_H
+
+#define hard_smp_processor_id()						\
+	({								\
+		unsigned int cpunum;					\
+		__asm__("\n"						\
+			"1:	mrc p15, 0, %0, c0, c0, 5\n"		\
+			"	.pushsection \".alt.smp.init\", \"a\"\n"\
+			"	.long	1b\n"				\
+			"	mov	%0, #0\n"			\
+			"	.popsection"				\
+			: "=r" (cpunum));				\
+		cpunum &= 0x0F;						\
+	})
+
+#endif
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index e621530..f24c1b9 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -7,15 +7,40 @@
 
 #include <asm/cputype.h>
 
+/*
+ * Return true if we are running on a SMP platform
+ */
+static inline bool is_smp(void)
+{
+#ifndef CONFIG_SMP
+	return false;
+#elif defined(CONFIG_SMP_ON_UP)
+	extern unsigned int smp_on_up;
+	return !!smp_on_up;
+#else
+	return true;
+#endif
+}
+
 /* all SMP configurations have the extended CPUID registers */
 static inline int tlb_ops_need_broadcast(void)
 {
+	if (!is_smp())
+		return 0;
+
 	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
 }
 
+#if !defined(CONFIG_SMP) || __LINUX_ARM_ARCH__ >= 7
+#define cache_ops_need_broadcast()	0
+#else
 static inline int cache_ops_need_broadcast(void)
 {
+	if (!is_smp())
+		return 0;
+
 	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 1;
 }
+#endif
 
 #endif
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 8ba1ccf..1120f18 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -85,6 +85,10 @@
 				       struct pt_regs *),
 		     int sig, int code, const char *name);
 
+void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int,
+				       struct pt_regs *),
+		     int sig, int code, const char *name);
+
 #define xchg(ptr,x) \
 	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
@@ -325,6 +329,8 @@
 extern void disable_hlt(void);
 extern void enable_hlt(void);
 
+void cpu_idle_wait(void);
+
 #include <asm-generic/cmpxchg-local.h>
 
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 763e29f..7b5cc8d 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -144,6 +144,7 @@
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
+#define TIF_SECCOMP		21
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
@@ -153,6 +154,7 @@
 #define _TIF_USING_IWMMXT	(1 << TIF_USING_IWMMXT)
 #define _TIF_FREEZE		(1 << TIF_FREEZE)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 
 /*
  * Change these and you break ASM code in entry-common.S
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 33b546a..ce7378ea 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -70,6 +70,10 @@
 #undef _TLB
 #undef MULTI_TLB
 
+#ifdef CONFIG_SMP_ON_UP
+#define MULTI_TLB 1
+#endif
+
 #define v3_tlb_flags	(TLB_V3_FULL | TLB_V3_PAGE)
 
 #ifdef CONFIG_CPU_TLB_V3
@@ -185,17 +189,23 @@
 # define v6wbi_always_flags	(-1UL)
 #endif
 
-#ifdef CONFIG_SMP
-#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \
+#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_V7_IS_BTB | \
 			 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID)
-#else
-#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \
+#define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BTB | \
 			 TLB_V6_U_FULL | TLB_V6_U_PAGE | TLB_V6_U_ASID)
-#endif
 
 #ifdef CONFIG_CPU_TLB_V7
-# define v7wbi_possible_flags	v7wbi_tlb_flags
-# define v7wbi_always_flags	v7wbi_tlb_flags
+
+# ifdef CONFIG_SMP_ON_UP
+#  define v7wbi_possible_flags	(v7wbi_tlb_flags_smp | v7wbi_tlb_flags_up)
+#  define v7wbi_always_flags	(v7wbi_tlb_flags_smp & v7wbi_tlb_flags_up)
+# elif defined(CONFIG_SMP)
+#  define v7wbi_possible_flags	v7wbi_tlb_flags_smp
+#  define v7wbi_always_flags	v7wbi_tlb_flags_smp
+# else
+#  define v7wbi_possible_flags	v7wbi_tlb_flags_up
+#  define v7wbi_always_flags	v7wbi_tlb_flags_up
+# endif
 # ifdef _TLB
 #  define MULTI_TLB 1
 # else
@@ -560,12 +570,20 @@
 #endif
 
 /*
- * if PG_dcache_dirty is set for the page, we need to ensure that any
+ * If PG_dcache_clean is not set for the page, we need to ensure that any
  * cache entries for the kernels virtual memory range are written
- * back to the page.
+ * back to the page. On ARMv6 and later, the cache coherency is handled via
+ * the set_pte_at() function.
  */
+#if __LINUX_ARM_ARCH__ < 6
 extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 	pte_t *ptep);
+#else
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep)
+{
+}
+#endif
 
 #endif
 
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 980b78e..5b9b268 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -42,6 +42,7 @@
 obj-$(CONFIG_ARM_UNWIND)	+= unwind.o
 obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 
 obj-$(CONFIG_CRUNCH)		+= crunch.o crunch-bits.o
 AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 8214bfe..e5e1e53 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -165,6 +165,8 @@
 #endif
 
 #ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_OLD_MCOUNT
 EXPORT_SYMBOL(mcount);
+#endif
 EXPORT_SYMBOL(__gnu_mcount_nc);
 #endif
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 85f2a01..82da661 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -102,8 +102,6 @@
   DEFINE(SIZEOF_MACHINE_DESC,	sizeof(struct machine_desc));
   DEFINE(MACHINFO_TYPE,		offsetof(struct machine_desc, nr));
   DEFINE(MACHINFO_NAME,		offsetof(struct machine_desc, name));
-  DEFINE(MACHINFO_PHYSIO,	offsetof(struct machine_desc, phys_io));
-  DEFINE(MACHINFO_PGOFFIO,	offsetof(struct machine_desc, io_pg_offst));
   BLANK();
   DEFINE(PROC_INFO_SZ,		sizeof(struct proc_info_list));
   DEFINE(PROCINFO_INITFUNC,	offsetof(struct proc_info_list, __cpu_flush));
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index a38b487..a0f0752 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -22,11 +22,11 @@
 #if defined(CONFIG_DEBUG_ICEDCC)
 		@@ debug using ARM EmbeddedICE DCC channel
 
-#if defined(CONFIG_CPU_V6)
-
-		.macro	addruart, rx, tmp
+		.macro	addruart, rp, rv
 		.endm
 
+#if defined(CONFIG_CPU_V6)
+
 		.macro	senduart, rd, rx
 		mcr	p14, 0, \rd, c0, c5, 0
 		.endm
@@ -51,9 +51,6 @@
 
 #elif defined(CONFIG_CPU_V7)
 
-		.macro	addruart, rx, tmp
-		.endm
-
 		.macro	senduart, rd, rx
 		mcr	p14, 0, \rd, c0, c5, 0
 		.endm
@@ -71,9 +68,6 @@
 
 #elif defined(CONFIG_CPU_XSCALE)
 
-		.macro	addruart, rx, tmp
-		.endm
-
 		.macro	senduart, rd, rx
 		mcr	p14, 0, \rd, c8, c0, 0
 		.endm
@@ -98,9 +92,6 @@
 
 #else
 
-		.macro	addruart, rx, tmp
-		.endm
-
 		.macro	senduart, rd, rx
 		mcr	p14, 0, \rd, c1, c0, 0
 		.endm
@@ -130,6 +121,22 @@
 #include <mach/debug-macro.S>
 #endif	/* CONFIG_DEBUG_ICEDCC */
 
+#ifdef CONFIG_MMU
+		.macro	addruart_current, rx, tmp1, tmp2
+		addruart	\tmp1, \tmp2
+		mrc		p15, 0, \rx, c1, c0
+		tst		\rx, #1
+		moveq		\rx, \tmp1
+		movne		\rx, \tmp2
+		.endm
+
+#else /* !CONFIG_MMU */
+		.macro	addruart_current, rx, tmp1, tmp2
+		addruart	\rx, \tmp1
+		.endm
+
+#endif /* CONFIG_MMU */
+
 /*
  * Useful debugging routines
  */
@@ -164,7 +171,7 @@
 		.ltorg
 
 ENTRY(printascii)
-		addruart r3, r1
+		addruart_current r3, r1, r2
 		b	2f
 1:		waituart r2, r3
 		senduart r1, r3
@@ -180,7 +187,7 @@
 ENDPROC(printascii)
 
 ENTRY(printch)
-		addruart r3, r1
+		addruart_current r3, r1, r2
 		mov	r1, r0
 		mov	r0, #0
 		b	1b
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index bb8e93a..c09e357 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -46,7 +46,8 @@
 	 * this macro assumes that irqstat (r6) and base (r5) are
 	 * preserved from get_irqnr_and_base above
 	 */
-	test_for_ipi r0, r6, r5, lr
+	ALT_SMP(test_for_ipi r0, r6, r5, lr)
+	ALT_UP_B(9997f)
 	movne	r0, sp
 	adrne	lr, BSYM(1b)
 	bne	do_IPI
@@ -57,6 +58,7 @@
 	adrne	lr, BSYM(1b)
 	bne	do_local_timer
 #endif
+9997:
 #endif
 
 	.endm
@@ -965,11 +967,8 @@
 	beq	1b
 	rsbs	r0, r3, #0
 	/* beware -- each __kuser slot must be 8 instructions max */
-#ifdef CONFIG_SMP
-	b	__kuser_memory_barrier
-#else
-	usr_ret	lr
-#endif
+	ALT_SMP(b	__kuser_memory_barrier)
+	ALT_UP(usr_ret	lr)
 
 #endif
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 7885722b..8bfa987 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -129,30 +129,58 @@
  * clobber the ip register.  This is OK because the ARM calling convention
  * allows it to be clobbered in subroutines and doesn't use it to hold
  * parameters.)
+ *
+ * When using dynamic ftrace, we patch out the mcount call by a "mov r0, r0"
+ * for the mcount case, and a "pop {lr}" for the __gnu_mcount_nc case (see
+ * arch/arm/kernel/ftrace.c).
  */
+
+#ifndef CONFIG_OLD_MCOUNT
+#if (__GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 4))
+#error Ftrace requires CONFIG_FRAME_POINTER=y with GCC older than 4.4.0.
+#endif
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(mcount)
+ENTRY(__gnu_mcount_nc)
+	mov	ip, lr
+	ldmia	sp!, {lr}
+	mov	pc, ip
+ENDPROC(__gnu_mcount_nc)
+
+ENTRY(ftrace_caller)
 	stmdb	sp!, {r0-r3, lr}
 	mov	r0, lr
 	sub	r0, r0, #MCOUNT_INSN_SIZE
+	ldr	r1, [sp, #20]
 
-	.globl mcount_call
-mcount_call:
+	.global	ftrace_call
+ftrace_call:
 	bl	ftrace_stub
-	ldr	lr, [fp, #-4]			@ restore lr
-	ldmia	sp!, {r0-r3, pc}
+	ldmia	sp!, {r0-r3, ip, lr}
+	mov	pc, ip
+ENDPROC(ftrace_caller)
 
-ENTRY(ftrace_caller)
+#ifdef CONFIG_OLD_MCOUNT
+ENTRY(mcount)
+	stmdb	sp!, {lr}
+	ldr	lr, [fp, #-4]
+	ldmia	sp!, {pc}
+ENDPROC(mcount)
+
+ENTRY(ftrace_caller_old)
 	stmdb	sp!, {r0-r3, lr}
 	ldr	r1, [fp, #-4]
 	mov	r0, lr
 	sub	r0, r0, #MCOUNT_INSN_SIZE
 
-	.globl ftrace_call
-ftrace_call:
+	.globl ftrace_call_old
+ftrace_call_old:
 	bl	ftrace_stub
 	ldr	lr, [fp, #-4]			@ restore lr
 	ldmia	sp!, {r0-r3, pc}
+ENDPROC(ftrace_caller_old)
+#endif
 
 #else
 
@@ -160,7 +188,7 @@
 	stmdb	sp!, {r0-r3, lr}
 	ldr	r0, =ftrace_trace_function
 	ldr	r2, [r0]
-	adr	r0, ftrace_stub
+	adr	r0, .Lftrace_stub
 	cmp	r0, r2
 	bne	gnu_trace
 	ldmia	sp!, {r0-r3, ip, lr}
@@ -170,11 +198,19 @@
 	ldr	r1, [sp, #20]			@ lr of instrumented routine
 	mov	r0, lr
 	sub	r0, r0, #MCOUNT_INSN_SIZE
-	mov	lr, pc
+	adr	lr, BSYM(1f)
 	mov	pc, r2
+1:
 	ldmia	sp!, {r0-r3, ip, lr}
 	mov	pc, ip
+ENDPROC(__gnu_mcount_nc)
 
+#ifdef CONFIG_OLD_MCOUNT
+/*
+ * This is under an ifdef in order to force link-time errors for people trying
+ * to build with !FRAME_POINTER with a GCC which doesn't use the new-style
+ * mcount.
+ */
 ENTRY(mcount)
 	stmdb	sp!, {r0-r3, lr}
 	ldr	r0, =ftrace_trace_function
@@ -193,12 +229,15 @@
 	mov	pc, r2
 	ldr	lr, [fp, #-4]			@ restore lr
 	ldmia	sp!, {r0-r3, pc}
+ENDPROC(mcount)
+#endif
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
-	.globl ftrace_stub
-ftrace_stub:
+ENTRY(ftrace_stub)
+.Lftrace_stub:
 	mov	pc, lr
+ENDPROC(ftrace_stub)
 
 #endif /* CONFIG_FUNCTION_TRACER */
 
@@ -295,7 +334,6 @@
 
 	get_thread_info tsk
 	adr	tbl, sys_call_table		@ load syscall table pointer
-	ldr	ip, [tsk, #TI_FLAGS]		@ check for syscall tracing
 
 #if defined(CONFIG_OABI_COMPAT)
 	/*
@@ -312,8 +350,20 @@
 	eor	scno, scno, #__NR_SYSCALL_BASE	@ check OS number
 #endif
 
+	ldr	r10, [tsk, #TI_FLAGS]		@ check for syscall tracing
 	stmdb	sp!, {r4, r5}			@ push fifth and sixth args
-	tst	ip, #_TIF_SYSCALL_TRACE		@ are we tracing syscalls?
+
+#ifdef CONFIG_SECCOMP
+	tst	r10, #_TIF_SECCOMP
+	beq	1f
+	mov	r0, scno
+	bl	__secure_computing	
+	add	r0, sp, #S_R0 + S_OFF		@ pointer to regs
+	ldmia	r0, {r0 - r3}			@ have to reload r0 - r3
+1:
+#endif
+
+	tst	r10, #_TIF_SYSCALL_TRACE		@ are we tracing syscalls?
 	bne	__sys_trace
 
 	cmp	scno, #NR_syscalls		@ check upper syscall limit
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
index 33c7077..11db628 100644
--- a/arch/arm/kernel/etm.c
+++ b/arch/arm/kernel/etm.c
@@ -30,6 +30,21 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Alexander Shishkin");
 
+/*
+ * ETM tracer state
+ */
+struct tracectx {
+	unsigned int	etb_bufsz;
+	void __iomem	*etb_regs;
+	void __iomem	*etm_regs;
+	unsigned long	flags;
+	int		ncmppairs;
+	int		etm_portsz;
+	struct device	*dev;
+	struct clk	*emu_clk;
+	struct mutex	mutex;
+};
+
 static struct tracectx tracer;
 
 static inline bool trace_isrunning(struct tracectx *t)
@@ -314,6 +329,7 @@
 	.read = etb_read,
 	.open = etb_open,
 	.release = etb_release,
+	.llseek = no_llseek,
 };
 
 static struct miscdevice etb_miscdev = {
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 0298286..971ac8c 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -2,102 +2,194 @@
  * Dynamic function tracing support.
  *
  * Copyright (C) 2008 Abhishek Sagar <sagar.abhishek@gmail.com>
+ * Copyright (C) 2010 Rabin Vincent <rabin@rab.in>
  *
  * For licencing details, see COPYING.
  *
  * Defines low-level handling of mcount calls when the kernel
  * is compiled with the -pg flag. When using dynamic ftrace, the
- * mcount call-sites get patched lazily with NOP till they are
- * enabled. All code mutation routines here take effect atomically.
+ * mcount call-sites get patched with NOP till they are enabled.
+ * All code mutation routines here are called under stop_machine().
  */
 
 #include <linux/ftrace.h>
+#include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
 #include <asm/ftrace.h>
 
-#define PC_OFFSET      8
-#define BL_OPCODE      0xeb000000
-#define BL_OFFSET_MASK 0x00ffffff
+#ifdef CONFIG_THUMB2_KERNEL
+#define	NOP		0xeb04f85d	/* pop.w {lr} */
+#else
+#define	NOP		0xe8bd4000	/* pop {lr} */
+#endif
 
-static unsigned long bl_insn;
-static const unsigned long NOP = 0xe1a00000; /* mov r0, r0 */
+#ifdef CONFIG_OLD_MCOUNT
+#define OLD_MCOUNT_ADDR	((unsigned long) mcount)
+#define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
 
-unsigned char *ftrace_nop_replace(void)
+#define	OLD_NOP		0xe1a00000	/* mov r0, r0 */
+
+static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
 {
-	return (char *)&NOP;
+	return rec->arch.old_mcount ? OLD_NOP : NOP;
 }
 
+static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
+{
+	if (!rec->arch.old_mcount)
+		return addr;
+
+	if (addr == MCOUNT_ADDR)
+		addr = OLD_MCOUNT_ADDR;
+	else if (addr == FTRACE_ADDR)
+		addr = OLD_FTRACE_ADDR;
+
+	return addr;
+}
+#else
+static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
+{
+	return NOP;
+}
+
+static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
+{
+	return addr;
+}
+#endif
+
 /* construct a branch (BL) instruction to addr */
-unsigned char *ftrace_call_replace(unsigned long pc, unsigned long addr)
+#ifdef CONFIG_THUMB2_KERNEL
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+{
+	unsigned long s, j1, j2, i1, i2, imm10, imm11;
+	unsigned long first, second;
+	long offset;
+
+	offset = (long)addr - (long)(pc + 4);
+	if (offset < -16777216 || offset > 16777214) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	s	= (offset >> 24) & 0x1;
+	i1	= (offset >> 23) & 0x1;
+	i2	= (offset >> 22) & 0x1;
+	imm10	= (offset >> 12) & 0x3ff;
+	imm11	= (offset >>  1) & 0x7ff;
+
+	j1 = (!i1) ^ s;
+	j2 = (!i2) ^ s;
+
+	first = 0xf000 | (s << 10) | imm10;
+	second = 0xd000 | (j1 << 13) | (j2 << 11) | imm11;
+
+	return (second << 16) | first;
+}
+#else
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 {
 	long offset;
 
-	offset = (long)addr - (long)(pc + PC_OFFSET);
+	offset = (long)addr - (long)(pc + 8);
 	if (unlikely(offset < -33554432 || offset > 33554428)) {
 		/* Can't generate branches that far (from ARM ARM). Ftrace
 		 * doesn't generate branches outside of kernel text.
 		 */
 		WARN_ON_ONCE(1);
-		return NULL;
+		return 0;
 	}
-	offset = (offset >> 2) & BL_OFFSET_MASK;
-	bl_insn = BL_OPCODE | offset;
-	return (unsigned char *)&bl_insn;
+
+	offset = (offset >> 2) & 0x00ffffff;
+
+	return 0xeb000000 | offset;
 }
+#endif
 
-int ftrace_modify_code(unsigned long pc, unsigned char *old_code,
-		       unsigned char *new_code)
+static int ftrace_modify_code(unsigned long pc, unsigned long old,
+			      unsigned long new)
 {
-	unsigned long err = 0, replaced = 0, old, new;
+	unsigned long replaced;
 
-	old = *(unsigned long *)old_code;
-	new = *(unsigned long *)new_code;
+	if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+		return -EFAULT;
 
-	__asm__ __volatile__ (
-		"1:  ldr    %1, [%2]  \n"
-		"    cmp    %1, %4    \n"
-		"2:  streq  %3, [%2]  \n"
-		"    cmpne  %1, %3    \n"
-		"    movne  %0, #2    \n"
-		"3:\n"
+	if (replaced != old)
+		return -EINVAL;
 
-		".pushsection .fixup, \"ax\"\n"
-		"4:  mov  %0, #1  \n"
-		"    b    3b      \n"
-		".popsection\n"
+	if (probe_kernel_write((void *)pc, &new, MCOUNT_INSN_SIZE))
+		return -EPERM;
 
-		".pushsection __ex_table, \"a\"\n"
-		"    .long 1b, 4b \n"
-		"    .long 2b, 4b \n"
-		".popsection\n"
+	flush_icache_range(pc, pc + MCOUNT_INSN_SIZE);
 
-		: "=r"(err), "=r"(replaced)
-		: "r"(pc), "r"(new), "r"(old), "0"(err), "1"(replaced)
-		: "memory");
-
-	if (!err && (replaced == old))
-		flush_icache_range(pc, pc + MCOUNT_INSN_SIZE);
-
-	return err;
+	return 0;
 }
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
-	int ret;
 	unsigned long pc, old;
-	unsigned char *new;
+	unsigned long new;
+	int ret;
 
 	pc = (unsigned long)&ftrace_call;
 	memcpy(&old, &ftrace_call, MCOUNT_INSN_SIZE);
 	new = ftrace_call_replace(pc, (unsigned long)func);
-	ret = ftrace_modify_code(pc, (unsigned char *)&old, new);
+
+	ret = ftrace_modify_code(pc, old, new);
+
+#ifdef CONFIG_OLD_MCOUNT
+	if (!ret) {
+		pc = (unsigned long)&ftrace_call_old;
+		memcpy(&old, &ftrace_call_old, MCOUNT_INSN_SIZE);
+		new = ftrace_call_replace(pc, (unsigned long)func);
+
+		ret = ftrace_modify_code(pc, old, new);
+	}
+#endif
+
 	return ret;
 }
 
-/* run from ftrace_init with irqs disabled */
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long new, old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_nop_replace(rec);
+	new = ftrace_call_replace(ip, adjust_address(rec, addr));
+
+	return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned long old;
+	unsigned long new;
+	int ret;
+
+	old = ftrace_call_replace(ip, adjust_address(rec, addr));
+	new = ftrace_nop_replace(rec);
+	ret = ftrace_modify_code(ip, old, new);
+
+#ifdef CONFIG_OLD_MCOUNT
+	if (ret == -EINVAL && addr == MCOUNT_ADDR) {
+		rec->arch.old_mcount = true;
+
+		old = ftrace_call_replace(ip, adjust_address(rec, addr));
+		new = ftrace_nop_replace(rec);
+		ret = ftrace_modify_code(ip, old, new);
+	}
+#endif
+
+	return ret;
+}
+
 int __init ftrace_dyn_arch_init(void *data)
 {
-	ftrace_mcount_set(data);
+	*(unsigned long *)data = 0;
+
 	return 0;
 }
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index b9505aa..bbecaac 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -15,55 +15,6 @@
 #define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
 #define ATAG_CORE_SIZE_EMPTY ((2*4) >> 2)
 
-	.align	2
-	.type	__switch_data, %object
-__switch_data:
-	.long	__mmap_switched
-	.long	__data_loc			@ r4
-	.long	_data				@ r5
-	.long	__bss_start			@ r6
-	.long	_end				@ r7
-	.long	processor_id			@ r4
-	.long	__machine_arch_type		@ r5
-	.long	__atags_pointer			@ r6
-	.long	cr_alignment			@ r7
-	.long	init_thread_union + THREAD_START_SP @ sp
-
-/*
- * The following fragment of code is executed with the MMU on in MMU mode,
- * and uses absolute addresses; this is not position independent.
- *
- *  r0  = cp#15 control register
- *  r1  = machine ID
- *  r2  = atags pointer
- *  r9  = processor ID
- */
-__mmap_switched:
-	adr	r3, __switch_data + 4
-
-	ldmia	r3!, {r4, r5, r6, r7}
-	cmp	r4, r5				@ Copy data segment if needed
-1:	cmpne	r5, r6
-	ldrne	fp, [r4], #4
-	strne	fp, [r5], #4
-	bne	1b
-
-	mov	fp, #0				@ Clear BSS (and zero fp)
-1:	cmp	r6, r7
-	strcc	fp, [r6],#4
-	bcc	1b
-
- ARM(	ldmia	r3, {r4, r5, r6, r7, sp})
- THUMB(	ldmia	r3, {r4, r5, r6, r7}	)
- THUMB(	ldr	sp, [r3, #16]		)
-	str	r9, [r4]			@ Save processor ID
-	str	r1, [r5]			@ Save machine type
-	str	r2, [r6]			@ Save atags pointer
-	bic	r4, r0, #CR_A			@ Clear 'A' bit
-	stmia	r7, {r0, r4}			@ Save control register values
-	b	start_kernel
-ENDPROC(__mmap_switched)
-
 /*
  * Exception handling.  Something went wrong and we can't proceed.  We
  * ought to tell the user, but since we don't have any guarantee that
@@ -73,21 +24,7 @@
  * and hope for the best (useful if bootloader fails to pass a proper
  * machine ID for example).
  */
-__error_p:
-#ifdef CONFIG_DEBUG_LL
-	adr	r0, str_p1
-	bl	printascii
-	mov	r0, r9
-	bl	printhex8
-	adr	r0, str_p2
-	bl	printascii
-	b	__error
-str_p1:	.asciz	"\nError: unrecognized/unsupported processor variant (0x"
-str_p2:	.asciz	").\n"
-	.align
-#endif
-ENDPROC(__error_p)
-
+	__HEAD
 __error_a:
 #ifdef CONFIG_DEBUG_LL
 	mov	r4, r1				@ preserve machine ID
@@ -97,7 +34,7 @@
 	bl	printhex8
 	adr	r0, str_a2
 	bl	printascii
-	adr	r3, 4f
+	adr	r3, __lookup_machine_type_data
 	ldmia	r3, {r4, r5, r6}		@ get machine desc list
 	sub	r4, r3, r4			@ get offset between virt&phys
 	add	r5, r5, r4			@ convert virt addresses to
@@ -125,78 +62,6 @@
 	.align
 #endif
 
-__error:
-#ifdef CONFIG_ARCH_RPC
-/*
- * Turn the screen red on a error - RiscPC only.
- */
-	mov	r0, #0x02000000
-	mov	r3, #0x11
-	orr	r3, r3, r3, lsl #8
-	orr	r3, r3, r3, lsl #16
-	str	r3, [r0], #4
-	str	r3, [r0], #4
-	str	r3, [r0], #4
-	str	r3, [r0], #4
-#endif
-1:	mov	r0, r0
-	b	1b
-ENDPROC(__error)
-
-
-/*
- * Read processor ID register (CP#15, CR0), and look up in the linker-built
- * supported processor list.  Note that we can't use the absolute addresses
- * for the __proc_info lists since we aren't running with the MMU on
- * (and therefore, we are not in the correct address space).  We have to
- * calculate the offset.
- *
- *	r9 = cpuid
- * Returns:
- *	r3, r4, r6 corrupted
- *	r5 = proc_info pointer in physical address space
- *	r9 = cpuid (preserved)
- */
-__lookup_processor_type:
-	adr	r3, 3f
-	ldmia	r3, {r5 - r7}
-	add	r3, r3, #8
-	sub	r3, r3, r7			@ get offset between virt&phys
-	add	r5, r5, r3			@ convert virt addresses to
-	add	r6, r6, r3			@ physical address space
-1:	ldmia	r5, {r3, r4}			@ value, mask
-	and	r4, r4, r9			@ mask wanted bits
-	teq	r3, r4
-	beq	2f
-	add	r5, r5, #PROC_INFO_SZ		@ sizeof(proc_info_list)
-	cmp	r5, r6
-	blo	1b
-	mov	r5, #0				@ unknown processor
-2:	mov	pc, lr
-ENDPROC(__lookup_processor_type)
-
-/*
- * This provides a C-API version of the above function.
- */
-ENTRY(lookup_processor_type)
-	stmfd	sp!, {r4 - r7, r9, lr}
-	mov	r9, r0
-	bl	__lookup_processor_type
-	mov	r0, r5
-	ldmfd	sp!, {r4 - r7, r9, pc}
-ENDPROC(lookup_processor_type)
-
-/*
- * Look in <asm/procinfo.h> and arch/arm/kernel/arch.[ch] for
- * more information about the __proc_info and __arch_info structures.
- */
-	.align	2
-3:	.long	__proc_info_begin
-	.long	__proc_info_end
-4:	.long	.
-	.long	__arch_info_begin
-	.long	__arch_info_end
-
 /*
  * Lookup machine architecture in the linker-build list of architectures.
  * Note that we can't use the absolute addresses for the __arch_info
@@ -209,7 +74,7 @@
  *  r5 = mach_info pointer in physical address space
  */
 __lookup_machine_type:
-	adr	r3, 4b
+	adr	r3, __lookup_machine_type_data
 	ldmia	r3, {r4, r5, r6}
 	sub	r3, r3, r4			@ get offset between virt&phys
 	add	r5, r5, r3			@ convert virt addresses to
@@ -225,15 +90,16 @@
 ENDPROC(__lookup_machine_type)
 
 /*
- * This provides a C-API version of the above function.
+ * Look in arch/arm/kernel/arch.[ch] for information about the
+ * __arch_info structures.
  */
-ENTRY(lookup_machine_type)
-	stmfd	sp!, {r4 - r6, lr}
-	mov	r1, r0
-	bl	__lookup_machine_type
-	mov	r0, r5
-	ldmfd	sp!, {r4 - r6, pc}
-ENDPROC(lookup_machine_type)
+	.align	2
+	.type	__lookup_machine_type_data, %object
+__lookup_machine_type_data:
+	.long	.
+	.long	__arch_info_begin
+	.long	__arch_info_end
+	.size	__lookup_machine_type_data, . - __lookup_machine_type_data
 
 /* Determine validity of the r2 atags pointer.  The heuristic requires
  * that the pointer be aligned, in the first 16k of physical RAM and
@@ -265,3 +131,150 @@
 1:	mov	r2, #0
 	mov	pc, lr
 ENDPROC(__vet_atags)
+
+/*
+ * The following fragment of code is executed with the MMU on in MMU mode,
+ * and uses absolute addresses; this is not position independent.
+ *
+ *  r0  = cp#15 control register
+ *  r1  = machine ID
+ *  r2  = atags pointer
+ *  r9  = processor ID
+ */
+	__INIT
+__mmap_switched:
+	adr	r3, __mmap_switched_data
+
+	ldmia	r3!, {r4, r5, r6, r7}
+	cmp	r4, r5				@ Copy data segment if needed
+1:	cmpne	r5, r6
+	ldrne	fp, [r4], #4
+	strne	fp, [r5], #4
+	bne	1b
+
+	mov	fp, #0				@ Clear BSS (and zero fp)
+1:	cmp	r6, r7
+	strcc	fp, [r6],#4
+	bcc	1b
+
+ ARM(	ldmia	r3, {r4, r5, r6, r7, sp})
+ THUMB(	ldmia	r3, {r4, r5, r6, r7}	)
+ THUMB(	ldr	sp, [r3, #16]		)
+	str	r9, [r4]			@ Save processor ID
+	str	r1, [r5]			@ Save machine type
+	str	r2, [r6]			@ Save atags pointer
+	bic	r4, r0, #CR_A			@ Clear 'A' bit
+	stmia	r7, {r0, r4}			@ Save control register values
+	b	start_kernel
+ENDPROC(__mmap_switched)
+
+	.align	2
+	.type	__mmap_switched_data, %object
+__mmap_switched_data:
+	.long	__data_loc			@ r4
+	.long	_sdata				@ r5
+	.long	__bss_start			@ r6
+	.long	_end				@ r7
+	.long	processor_id			@ r4
+	.long	__machine_arch_type		@ r5
+	.long	__atags_pointer			@ r6
+	.long	cr_alignment			@ r7
+	.long	init_thread_union + THREAD_START_SP @ sp
+	.size	__mmap_switched_data, . - __mmap_switched_data
+
+/*
+ * This provides a C-API version of __lookup_machine_type
+ */
+ENTRY(lookup_machine_type)
+	stmfd	sp!, {r4 - r6, lr}
+	mov	r1, r0
+	bl	__lookup_machine_type
+	mov	r0, r5
+	ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(lookup_machine_type)
+
+/*
+ * This provides a C-API version of __lookup_processor_type
+ */
+ENTRY(lookup_processor_type)
+	stmfd	sp!, {r4 - r6, r9, lr}
+	mov	r9, r0
+	bl	__lookup_processor_type
+	mov	r0, r5
+	ldmfd	sp!, {r4 - r6, r9, pc}
+ENDPROC(lookup_processor_type)
+
+/*
+ * Read processor ID register (CP#15, CR0), and look up in the linker-built
+ * supported processor list.  Note that we can't use the absolute addresses
+ * for the __proc_info lists since we aren't running with the MMU on
+ * (and therefore, we are not in the correct address space).  We have to
+ * calculate the offset.
+ *
+ *	r9 = cpuid
+ * Returns:
+ *	r3, r4, r6 corrupted
+ *	r5 = proc_info pointer in physical address space
+ *	r9 = cpuid (preserved)
+ */
+	__CPUINIT
+__lookup_processor_type:
+	adr	r3, __lookup_processor_type_data
+	ldmia	r3, {r4 - r6}
+	sub	r3, r3, r4			@ get offset between virt&phys
+	add	r5, r5, r3			@ convert virt addresses to
+	add	r6, r6, r3			@ physical address space
+1:	ldmia	r5, {r3, r4}			@ value, mask
+	and	r4, r4, r9			@ mask wanted bits
+	teq	r3, r4
+	beq	2f
+	add	r5, r5, #PROC_INFO_SZ		@ sizeof(proc_info_list)
+	cmp	r5, r6
+	blo	1b
+	mov	r5, #0				@ unknown processor
+2:	mov	pc, lr
+ENDPROC(__lookup_processor_type)
+
+/*
+ * Look in <asm/procinfo.h> for information about the __proc_info structure.
+ */
+	.align	2
+	.type	__lookup_processor_type_data, %object
+__lookup_processor_type_data:
+	.long	.
+	.long	__proc_info_begin
+	.long	__proc_info_end
+	.size	__lookup_processor_type_data, . - __lookup_processor_type_data
+
+__error_p:
+#ifdef CONFIG_DEBUG_LL
+	adr	r0, str_p1
+	bl	printascii
+	mov	r0, r9
+	bl	printhex8
+	adr	r0, str_p2
+	bl	printascii
+	b	__error
+str_p1:	.asciz	"\nError: unrecognized/unsupported processor variant (0x"
+str_p2:	.asciz	").\n"
+	.align
+#endif
+ENDPROC(__error_p)
+
+__error:
+#ifdef CONFIG_ARCH_RPC
+/*
+ * Turn the screen red on a error - RiscPC only.
+ */
+	mov	r0, #0x02000000
+	mov	r3, #0x11
+	orr	r3, r3, r3, lsl #8
+	orr	r3, r3, r3, lsl #16
+	str	r3, [r0], #4
+	str	r3, [r0], #4
+	str	r3, [r0], #4
+	str	r3, [r0], #4
+#endif
+1:	mov	r0, r0
+	b	1b
+ENDPROC(__error)
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 573b803..814ce1a 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -48,8 +48,6 @@
 	movs	r8, r5				@ invalid machine (r5=0)?
 	beq	__error_a			@ yes, error 'a'
 
-	ldr	r13, __switch_data		@ address to jump to after
-						@ the initialization is done
 	adr	lr, BSYM(__after_proc_init)	@ return (PIC) address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
@@ -87,8 +85,7 @@
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 #endif /* CONFIG_CPU_CP15 */
 
-	mov	r3, r13
-	mov	pc, r3				@ clear the BSS and jump
+	b	__mmap_switched			@ clear the BSS and jump
 						@ to start_kernel
 ENDPROC(__after_proc_init)
 	.ltorg
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index eb62bf9..dd6b369 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -22,6 +22,10 @@
 #include <asm/thread_info.h>
 #include <asm/system.h>
 
+#ifdef CONFIG_DEBUG_LL
+#include <mach/debug-macro.S>
+#endif
+
 #if (PHYS_OFFSET & 0x001fffff)
 #error "PHYS_OFFSET must be at an even 2MiB boundary!"
 #endif
@@ -86,6 +90,9 @@
 	movs	r8, r5				@ invalid machine (r5=0)?
 	beq	__error_a			@ yes, error 'a'
 	bl	__vet_atags
+#ifdef CONFIG_SMP_ON_UP
+	bl	__fixup_smp
+#endif
 	bl	__create_page_tables
 
 	/*
@@ -95,113 +102,15 @@
 	 * above.  On return, the CPU will be ready for the MMU to be
 	 * turned on, and r0 will hold the CPU control register value.
 	 */
-	ldr	r13, __switch_data		@ address to jump to after
+	ldr	r13, =__mmap_switched		@ address to jump to after
 						@ mmu has been enabled
-	adr	lr, BSYM(__enable_mmu)		@ return (PIC) address
+	adr	lr, BSYM(1f)			@ return (PIC) address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
  THUMB(	mov	pc, r12				)
+1:	b	__enable_mmu
 ENDPROC(stext)
-
-#if defined(CONFIG_SMP)
-ENTRY(secondary_startup)
-	/*
-	 * Common entry point for secondary CPUs.
-	 *
-	 * Ensure that we're in SVC mode, and IRQs are disabled.  Lookup
-	 * the processor type - there is no need to check the machine type
-	 * as it has already been validated by the primary processor.
-	 */
-	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
-	mrc	p15, 0, r9, c0, c0		@ get processor id
-	bl	__lookup_processor_type
-	movs	r10, r5				@ invalid processor?
-	moveq	r0, #'p'			@ yes, error 'p'
-	beq	__error
-
-	/*
-	 * Use the page tables supplied from  __cpu_up.
-	 */
-	adr	r4, __secondary_data
-	ldmia	r4, {r5, r7, r12}		@ address to jump to after
-	sub	r4, r4, r5			@ mmu has been enabled
-	ldr	r4, [r7, r4]			@ get secondary_data.pgdir
-	adr	lr, BSYM(__enable_mmu)		@ return address
-	mov	r13, r12			@ __secondary_switched address
- ARM(	add	pc, r10, #PROCINFO_INITFUNC	) @ initialise processor
-						  @ (return control reg)
- THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	mov	pc, r12				)
-ENDPROC(secondary_startup)
-
-	/*
-	 * r6  = &secondary_data
-	 */
-ENTRY(__secondary_switched)
-	ldr	sp, [r7, #4]			@ get secondary_data.stack
-	mov	fp, #0
-	b	secondary_start_kernel
-ENDPROC(__secondary_switched)
-
-	.type	__secondary_data, %object
-__secondary_data:
-	.long	.
-	.long	secondary_data
-	.long	__secondary_switched
-#endif /* defined(CONFIG_SMP) */
-
-
-
-/*
- * Setup common bits before finally enabling the MMU.  Essentially
- * this is just loading the page table pointer and domain access
- * registers.
- */
-__enable_mmu:
-#ifdef CONFIG_ALIGNMENT_TRAP
-	orr	r0, r0, #CR_A
-#else
-	bic	r0, r0, #CR_A
-#endif
-#ifdef CONFIG_CPU_DCACHE_DISABLE
-	bic	r0, r0, #CR_C
-#endif
-#ifdef CONFIG_CPU_BPREDICT_DISABLE
-	bic	r0, r0, #CR_Z
-#endif
-#ifdef CONFIG_CPU_ICACHE_DISABLE
-	bic	r0, r0, #CR_I
-#endif
-	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
-	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
-	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
-	b	__turn_mmu_on
-ENDPROC(__enable_mmu)
-
-/*
- * Enable the MMU.  This completely changes the structure of the visible
- * memory space.  You will not be able to trace execution through this.
- * If you have an enquiry about this, *please* check the linux-arm-kernel
- * mailing list archives BEFORE sending another post to the list.
- *
- *  r0  = cp#15 control register
- *  r13 = *virtual* address to jump to upon completion
- *
- * other registers depend on the function called upon completion
- */
-	.align	5
-__turn_mmu_on:
-	mov	r0, r0
-	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
-	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
-	mov	r3, r3
-	mov	r3, r13
-	mov	pc, r3
-ENDPROC(__turn_mmu_on)
-
+	.ltorg
 
 /*
  * Setup the initial page tables.  We only setup the barest
@@ -213,7 +122,7 @@
  * r10 = procinfo
  *
  * Returns:
- *  r0, r3, r6, r7 corrupted
+ *  r0, r3, r5-r7 corrupted
  *  r4 = physical page table address
  */
 __create_page_tables:
@@ -235,20 +144,30 @@
 	ldr	r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags
 
 	/*
-	 * Create identity mapping for first MB of kernel to
-	 * cater for the MMU enable.  This identity mapping
-	 * will be removed by paging_init().  We use our current program
-	 * counter to determine corresponding section base address.
+	 * Create identity mapping to cater for __enable_mmu.
+	 * This identity mapping will be removed by paging_init().
 	 */
-	mov	r6, pc
-	mov	r6, r6, lsr #20			@ start of kernel section
-	orr	r3, r7, r6, lsl #20		@ flags + kernel base
-	str	r3, [r4, r6, lsl #2]		@ identity mapping
+	adr	r0, __enable_mmu_loc
+	ldmia	r0, {r3, r5, r6}
+	sub	r0, r0, r3			@ virt->phys offset
+	add	r5, r5, r0			@ phys __enable_mmu
+	add	r6, r6, r0			@ phys __enable_mmu_end
+	mov	r5, r5, lsr #20
+	mov	r6, r6, lsr #20
+
+1:	orr	r3, r7, r5, lsl #20		@ flags + kernel base
+	str	r3, [r4, r5, lsl #2]		@ identity mapping
+	teq	r5, r6
+	addne	r5, r5, #1			@ next section
+	bne	1b
 
 	/*
 	 * Now setup the pagetables for our kernel direct
 	 * mapped region.
 	 */
+	mov	r3, pc
+	mov	r3, r3, lsr #20
+	orr	r3, r7, r3, lsl #20
 	add	r0, r4,  #(KERNEL_START & 0xff000000) >> 18
 	str	r3, [r0, #(KERNEL_START & 0x00f00000) >> 18]!
 	ldr	r6, =(KERNEL_END - 1)
@@ -289,24 +208,35 @@
 	str	r6, [r0]
 
 #ifdef CONFIG_DEBUG_LL
-	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
+#ifndef CONFIG_DEBUG_ICEDCC
 	/*
 	 * Map in IO space for serial debugging.
 	 * This allows debug messages to be output
 	 * via a serial console before paging_init.
 	 */
-	ldr	r3, [r8, #MACHINFO_PGOFFIO]
+	addruart r7, r3
+
+	mov	r3, r3, lsr #20
+	mov	r3, r3, lsl #2
+
 	add	r0, r4, r3
 	rsb	r3, r3, #0x4000			@ PTRS_PER_PGD*sizeof(long)
 	cmp	r3, #0x0800			@ limit to 512MB
 	movhi	r3, #0x0800
 	add	r6, r0, r3
-	ldr	r3, [r8, #MACHINFO_PHYSIO]
-	orr	r3, r3, r7
+	mov	r3, r7, lsr #20
+	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
+	orr	r3, r7, r3, lsl #20
 1:	str	r3, [r0], #4
 	add	r3, r3, #1 << 20
 	teq	r0, r6
 	bne	1b
+
+#else /* CONFIG_DEBUG_ICEDCC */
+	/* we don't need any serial debugging mappings for ICEDCC */
+	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
+#endif /* !CONFIG_DEBUG_ICEDCC */
+
 #if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)
 	/*
 	 * If we're using the NetWinder or CATS, we also need to map
@@ -332,5 +262,168 @@
 	mov	pc, lr
 ENDPROC(__create_page_tables)
 	.ltorg
+__enable_mmu_loc:
+	.long	.
+	.long	__enable_mmu
+	.long	__enable_mmu_end
+
+#if defined(CONFIG_SMP)
+	__CPUINIT
+ENTRY(secondary_startup)
+	/*
+	 * Common entry point for secondary CPUs.
+	 *
+	 * Ensure that we're in SVC mode, and IRQs are disabled.  Lookup
+	 * the processor type - there is no need to check the machine type
+	 * as it has already been validated by the primary processor.
+	 */
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
+	mrc	p15, 0, r9, c0, c0		@ get processor id
+	bl	__lookup_processor_type
+	movs	r10, r5				@ invalid processor?
+	moveq	r0, #'p'			@ yes, error 'p'
+	beq	__error_p
+
+	/*
+	 * Use the page tables supplied from  __cpu_up.
+	 */
+	adr	r4, __secondary_data
+	ldmia	r4, {r5, r7, r12}		@ address to jump to after
+	sub	r4, r4, r5			@ mmu has been enabled
+	ldr	r4, [r7, r4]			@ get secondary_data.pgdir
+	adr	lr, BSYM(__enable_mmu)		@ return address
+	mov	r13, r12			@ __secondary_switched address
+ ARM(	add	pc, r10, #PROCINFO_INITFUNC	) @ initialise processor
+						  @ (return control reg)
+ THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
+ THUMB(	mov	pc, r12				)
+ENDPROC(secondary_startup)
+
+	/*
+	 * r6  = &secondary_data
+	 */
+ENTRY(__secondary_switched)
+	ldr	sp, [r7, #4]			@ get secondary_data.stack
+	mov	fp, #0
+	b	secondary_start_kernel
+ENDPROC(__secondary_switched)
+
+	.type	__secondary_data, %object
+__secondary_data:
+	.long	.
+	.long	secondary_data
+	.long	__secondary_switched
+#endif /* defined(CONFIG_SMP) */
+
+
+
+/*
+ * Setup common bits before finally enabling the MMU.  Essentially
+ * this is just loading the page table pointer and domain access
+ * registers.
+ *
+ *  r0  = cp#15 control register
+ *  r1  = machine ID
+ *  r2  = atags pointer
+ *  r4  = page table pointer
+ *  r9  = processor ID
+ *  r13 = *virtual* address to jump to upon completion
+ */
+__enable_mmu:
+#ifdef CONFIG_ALIGNMENT_TRAP
+	orr	r0, r0, #CR_A
+#else
+	bic	r0, r0, #CR_A
+#endif
+#ifdef CONFIG_CPU_DCACHE_DISABLE
+	bic	r0, r0, #CR_C
+#endif
+#ifdef CONFIG_CPU_BPREDICT_DISABLE
+	bic	r0, r0, #CR_Z
+#endif
+#ifdef CONFIG_CPU_ICACHE_DISABLE
+	bic	r0, r0, #CR_I
+#endif
+	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
+		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
+		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
+	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
+	b	__turn_mmu_on
+ENDPROC(__enable_mmu)
+
+/*
+ * Enable the MMU.  This completely changes the structure of the visible
+ * memory space.  You will not be able to trace execution through this.
+ * If you have an enquiry about this, *please* check the linux-arm-kernel
+ * mailing list archives BEFORE sending another post to the list.
+ *
+ *  r0  = cp#15 control register
+ *  r1  = machine ID
+ *  r2  = atags pointer
+ *  r9  = processor ID
+ *  r13 = *virtual* address to jump to upon completion
+ *
+ * other registers depend on the function called upon completion
+ */
+	.align	5
+__turn_mmu_on:
+	mov	r0, r0
+	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
+	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
+	mov	r3, r3
+	mov	r3, r13
+	mov	pc, r3
+__enable_mmu_end:
+ENDPROC(__turn_mmu_on)
+
+
+#ifdef CONFIG_SMP_ON_UP
+__fixup_smp:
+	mov	r7, #0x00070000
+	orr	r6, r7, #0xff000000	@ mask 0xff070000
+	orr	r7, r7, #0x41000000	@ val 0x41070000
+	and	r0, r9, r6
+	teq	r0, r7			@ ARM CPU and ARMv6/v7?
+	bne	__fixup_smp_on_up	@ no, assume UP
+
+	orr	r6, r6, #0x0000ff00
+	orr	r6, r6, #0x000000f0	@ mask 0xff07fff0
+	orr	r7, r7, #0x0000b000
+	orr	r7, r7, #0x00000020	@ val 0x4107b020
+	and	r0, r9, r6
+	teq	r0, r7			@ ARM 11MPCore?
+	moveq	pc, lr			@ yes, assume SMP
+
+	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
+	tst	r0, #1 << 31
+	movne	pc, lr			@ bit 31 => SMP
+
+__fixup_smp_on_up:
+	adr	r0, 1f
+	ldmia	r0, {r3, r6, r7}
+	sub	r3, r0, r3
+	add	r6, r6, r3
+	add	r7, r7, r3
+2:	cmp	r6, r7
+	ldmia	r6!, {r0, r4}
+	strlo	r4, [r0, r3]
+	blo	2b
+	mov	pc, lr
+ENDPROC(__fixup_smp)
+
+1:	.word	.
+	.word	__smpalt_begin
+	.word	__smpalt_end
+
+	.pushsection .data
+	.globl	smp_on_up
+smp_on_up:
+	ALT_SMP(.long	1)
+	ALT_UP(.long	0)
+	.popsection
+
+#endif
 
 #include "head-common.S"
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
new file mode 100644
index 0000000..54593b0
--- /dev/null
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -0,0 +1,849 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2009, 2010 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers.
+ */
+#define pr_fmt(fmt) "hw-breakpoint: " fmt
+
+#include <linux/errno.h>
+#include <linux/perf_event.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/smp.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/current.h>
+#include <asm/hw_breakpoint.h>
+#include <asm/kdebug.h>
+#include <asm/system.h>
+#include <asm/traps.h>
+
+/* Breakpoint currently in use for each BRP. */
+static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
+
+/* Watchpoint currently in use for each WRP. */
+static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]);
+
+/* Number of BRP/WRP registers on this CPU. */
+static int core_num_brps;
+static int core_num_wrps;
+
+/* Debug architecture version. */
+static u8 debug_arch;
+
+/* Maximum supported watchpoint length. */
+static u8 max_watchpoint_len;
+
+/* Determine number of BRP registers available. */
+static int get_num_brps(void)
+{
+	u32 didr;
+	ARM_DBG_READ(c0, 0, didr);
+	return ((didr >> 24) & 0xf) + 1;
+}
+
+/* Determine number of WRP registers available. */
+static int get_num_wrps(void)
+{
+	/*
+	 * FIXME: When a watchpoint fires, the only way to work out which
+	 * watchpoint it was is by disassembling the faulting instruction
+	 * and working out the address of the memory access.
+	 *
+	 * Furthermore, we can only do this if the watchpoint was precise
+	 * since imprecise watchpoints prevent us from calculating register
+	 * based addresses.
+	 *
+	 * For the time being, we only report 1 watchpoint register so we
+	 * always know which watchpoint fired. In the future we can either
+	 * add a disassembler and address generation emulator, or we can
+	 * insert a check to see if the DFAR is set on watchpoint exception
+	 * entry [the ARM ARM states that the DFAR is UNKNOWN, but
+	 * experience shows that it is set on some implementations].
+	 */
+
+#if 0
+	u32 didr, wrps;
+	ARM_DBG_READ(c0, 0, didr);
+	return ((didr >> 28) & 0xf) + 1;
+#endif
+
+	return 1;
+}
+
+int hw_breakpoint_slots(int type)
+{
+	/*
+	 * We can be called early, so don't rely on
+	 * our static variables being initialised.
+	 */
+	switch (type) {
+	case TYPE_INST:
+		return get_num_brps();
+	case TYPE_DATA:
+		return get_num_wrps();
+	default:
+		pr_warning("unknown slot type: %d\n", type);
+		return 0;
+	}
+}
+
+/* Determine debug architecture. */
+static u8 get_debug_arch(void)
+{
+	u32 didr;
+
+	/* Do we implement the extended CPUID interface? */
+	if (((read_cpuid_id() >> 16) & 0xf) != 0xf) {
+		pr_warning("CPUID feature registers not supported. "
+				"Assuming v6 debug is present.\n");
+		return ARM_DEBUG_ARCH_V6;
+	}
+
+	ARM_DBG_READ(c0, 0, didr);
+	return (didr >> 16) & 0xf;
+}
+
+/* Does this core support mismatch breakpoints? */
+static int core_has_mismatch_bps(void)
+{
+	return debug_arch >= ARM_DEBUG_ARCH_V7_ECP14 && core_num_brps > 1;
+}
+
+u8 arch_get_debug_arch(void)
+{
+	return debug_arch;
+}
+
+#define READ_WB_REG_CASE(OP2, M, VAL)		\
+	case ((OP2 << 4) + M):			\
+		ARM_DBG_READ(c ## M, OP2, VAL); \
+		break
+
+#define WRITE_WB_REG_CASE(OP2, M, VAL)		\
+	case ((OP2 << 4) + M):			\
+		ARM_DBG_WRITE(c ## M, OP2, VAL);\
+		break
+
+#define GEN_READ_WB_REG_CASES(OP2, VAL)		\
+	READ_WB_REG_CASE(OP2, 0, VAL);		\
+	READ_WB_REG_CASE(OP2, 1, VAL);		\
+	READ_WB_REG_CASE(OP2, 2, VAL);		\
+	READ_WB_REG_CASE(OP2, 3, VAL);		\
+	READ_WB_REG_CASE(OP2, 4, VAL);		\
+	READ_WB_REG_CASE(OP2, 5, VAL);		\
+	READ_WB_REG_CASE(OP2, 6, VAL);		\
+	READ_WB_REG_CASE(OP2, 7, VAL);		\
+	READ_WB_REG_CASE(OP2, 8, VAL);		\
+	READ_WB_REG_CASE(OP2, 9, VAL);		\
+	READ_WB_REG_CASE(OP2, 10, VAL);		\
+	READ_WB_REG_CASE(OP2, 11, VAL);		\
+	READ_WB_REG_CASE(OP2, 12, VAL);		\
+	READ_WB_REG_CASE(OP2, 13, VAL);		\
+	READ_WB_REG_CASE(OP2, 14, VAL);		\
+	READ_WB_REG_CASE(OP2, 15, VAL)
+
+#define GEN_WRITE_WB_REG_CASES(OP2, VAL)	\
+	WRITE_WB_REG_CASE(OP2, 0, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 1, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 2, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 3, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 4, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 5, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 6, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 7, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 8, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 9, VAL);		\
+	WRITE_WB_REG_CASE(OP2, 10, VAL);	\
+	WRITE_WB_REG_CASE(OP2, 11, VAL);	\
+	WRITE_WB_REG_CASE(OP2, 12, VAL);	\
+	WRITE_WB_REG_CASE(OP2, 13, VAL);	\
+	WRITE_WB_REG_CASE(OP2, 14, VAL);	\
+	WRITE_WB_REG_CASE(OP2, 15, VAL)
+
+static u32 read_wb_reg(int n)
+{
+	u32 val = 0;
+
+	switch (n) {
+	GEN_READ_WB_REG_CASES(ARM_OP2_BVR, val);
+	GEN_READ_WB_REG_CASES(ARM_OP2_BCR, val);
+	GEN_READ_WB_REG_CASES(ARM_OP2_WVR, val);
+	GEN_READ_WB_REG_CASES(ARM_OP2_WCR, val);
+	default:
+		pr_warning("attempt to read from unknown breakpoint "
+				"register %d\n", n);
+	}
+
+	return val;
+}
+
+static void write_wb_reg(int n, u32 val)
+{
+	switch (n) {
+	GEN_WRITE_WB_REG_CASES(ARM_OP2_BVR, val);
+	GEN_WRITE_WB_REG_CASES(ARM_OP2_BCR, val);
+	GEN_WRITE_WB_REG_CASES(ARM_OP2_WVR, val);
+	GEN_WRITE_WB_REG_CASES(ARM_OP2_WCR, val);
+	default:
+		pr_warning("attempt to write to unknown breakpoint "
+				"register %d\n", n);
+	}
+	isb();
+}
+
+/*
+ * In order to access the breakpoint/watchpoint control registers,
+ * we must be running in debug monitor mode. Unfortunately, we can
+ * be put into halting debug mode at any time by an external debugger
+ * but there is nothing we can do to prevent that.
+ */
+static int enable_monitor_mode(void)
+{
+	u32 dscr;
+	int ret = 0;
+
+	ARM_DBG_READ(c1, 0, dscr);
+
+	/* Ensure that halting mode is disabled. */
+	if (WARN_ONCE(dscr & ARM_DSCR_HDBGEN, "halting debug mode enabled."
+				"Unable to access hardware resources.")) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	/* Write to the corresponding DSCR. */
+	switch (debug_arch) {
+	case ARM_DEBUG_ARCH_V6:
+	case ARM_DEBUG_ARCH_V6_1:
+		ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN));
+		break;
+	case ARM_DEBUG_ARCH_V7_ECP14:
+		ARM_DBG_WRITE(c2, 2, (dscr | ARM_DSCR_MDBGEN));
+		break;
+	default:
+		ret = -ENODEV;
+		goto out;
+	}
+
+	/* Check that the write made it through. */
+	ARM_DBG_READ(c1, 0, dscr);
+	if (WARN_ONCE(!(dscr & ARM_DSCR_MDBGEN),
+				"failed to enable monitor mode.")) {
+		ret = -EPERM;
+	}
+
+out:
+	return ret;
+}
+
+/*
+ * Check if 8-bit byte-address select is available.
+ * This clobbers WRP 0.
+ */
+static u8 get_max_wp_len(void)
+{
+	u32 ctrl_reg;
+	struct arch_hw_breakpoint_ctrl ctrl;
+	u8 size = 4;
+
+	if (debug_arch < ARM_DEBUG_ARCH_V7_ECP14)
+		goto out;
+
+	if (enable_monitor_mode())
+		goto out;
+
+	memset(&ctrl, 0, sizeof(ctrl));
+	ctrl.len = ARM_BREAKPOINT_LEN_8;
+	ctrl_reg = encode_ctrl_reg(ctrl);
+
+	write_wb_reg(ARM_BASE_WVR, 0);
+	write_wb_reg(ARM_BASE_WCR, ctrl_reg);
+	if ((read_wb_reg(ARM_BASE_WCR) & ctrl_reg) == ctrl_reg)
+		size = 8;
+
+out:
+	return size;
+}
+
+u8 arch_get_max_wp_len(void)
+{
+	return max_watchpoint_len;
+}
+
+/*
+ * Handler for reactivating a suspended watchpoint when the single
+ * step `mismatch' breakpoint is triggered.
+ */
+static void wp_single_step_handler(struct perf_event *bp, int unused,
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
+{
+	perf_event_enable(counter_arch_bp(bp)->suspended_wp);
+	unregister_hw_breakpoint(bp);
+}
+
+static int bp_is_single_step(struct perf_event *bp)
+{
+	return bp->overflow_handler == wp_single_step_handler;
+}
+
+/*
+ * Install a perf counter breakpoint.
+ */
+int arch_install_hw_breakpoint(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	struct perf_event **slot, **slots;
+	int i, max_slots, ctrl_base, val_base, ret = 0;
+
+	/* Ensure that we are in monitor mode and halting mode is disabled. */
+	ret = enable_monitor_mode();
+	if (ret)
+		goto out;
+
+	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
+		/* Breakpoint */
+		ctrl_base = ARM_BASE_BCR;
+		val_base = ARM_BASE_BVR;
+		slots = __get_cpu_var(bp_on_reg);
+		max_slots = core_num_brps - 1;
+
+		if (bp_is_single_step(bp)) {
+			info->ctrl.mismatch = 1;
+			i = max_slots;
+			slots[i] = bp;
+			goto setup;
+		}
+	} else {
+		/* Watchpoint */
+		ctrl_base = ARM_BASE_WCR;
+		val_base = ARM_BASE_WVR;
+		slots = __get_cpu_var(wp_on_reg);
+		max_slots = core_num_wrps;
+	}
+
+	for (i = 0; i < max_slots; ++i) {
+		slot = &slots[i];
+
+		if (!*slot) {
+			*slot = bp;
+			break;
+		}
+	}
+
+	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot")) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+setup:
+	/* Setup the address register. */
+	write_wb_reg(val_base + i, info->address);
+
+	/* Setup the control register. */
+	write_wb_reg(ctrl_base + i, encode_ctrl_reg(info->ctrl) | 0x1);
+
+out:
+	return ret;
+}
+
+void arch_uninstall_hw_breakpoint(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	struct perf_event **slot, **slots;
+	int i, max_slots, base;
+
+	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
+		/* Breakpoint */
+		base = ARM_BASE_BCR;
+		slots = __get_cpu_var(bp_on_reg);
+		max_slots = core_num_brps - 1;
+
+		if (bp_is_single_step(bp)) {
+			i = max_slots;
+			slots[i] = NULL;
+			goto reset;
+		}
+	} else {
+		/* Watchpoint */
+		base = ARM_BASE_WCR;
+		slots = __get_cpu_var(wp_on_reg);
+		max_slots = core_num_wrps;
+	}
+
+	/* Remove the breakpoint. */
+	for (i = 0; i < max_slots; ++i) {
+		slot = &slots[i];
+
+		if (*slot == bp) {
+			*slot = NULL;
+			break;
+		}
+	}
+
+	if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
+		return;
+
+reset:
+	/* Reset the control register. */
+	write_wb_reg(base + i, 0);
+}
+
+static int get_hbp_len(u8 hbp_len)
+{
+	unsigned int len_in_bytes = 0;
+
+	switch (hbp_len) {
+	case ARM_BREAKPOINT_LEN_1:
+		len_in_bytes = 1;
+		break;
+	case ARM_BREAKPOINT_LEN_2:
+		len_in_bytes = 2;
+		break;
+	case ARM_BREAKPOINT_LEN_4:
+		len_in_bytes = 4;
+		break;
+	case ARM_BREAKPOINT_LEN_8:
+		len_in_bytes = 8;
+		break;
+	}
+
+	return len_in_bytes;
+}
+
+/*
+ * Check whether bp virtual address is in kernel space.
+ */
+int arch_check_bp_in_kernelspace(struct perf_event *bp)
+{
+	unsigned int len;
+	unsigned long va;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+
+	va = info->address;
+	len = get_hbp_len(info->ctrl.len);
+
+	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
+}
+
+/*
+ * Extract generic type and length encodings from an arch_hw_breakpoint_ctrl.
+ * Hopefully this will disappear when ptrace can bypass the conversion
+ * to generic breakpoint descriptions.
+ */
+int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
+			   int *gen_len, int *gen_type)
+{
+	/* Type */
+	switch (ctrl.type) {
+	case ARM_BREAKPOINT_EXECUTE:
+		*gen_type = HW_BREAKPOINT_X;
+		break;
+	case ARM_BREAKPOINT_LOAD:
+		*gen_type = HW_BREAKPOINT_R;
+		break;
+	case ARM_BREAKPOINT_STORE:
+		*gen_type = HW_BREAKPOINT_W;
+		break;
+	case ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE:
+		*gen_type = HW_BREAKPOINT_RW;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Len */
+	switch (ctrl.len) {
+	case ARM_BREAKPOINT_LEN_1:
+		*gen_len = HW_BREAKPOINT_LEN_1;
+		break;
+	case ARM_BREAKPOINT_LEN_2:
+		*gen_len = HW_BREAKPOINT_LEN_2;
+		break;
+	case ARM_BREAKPOINT_LEN_4:
+		*gen_len = HW_BREAKPOINT_LEN_4;
+		break;
+	case ARM_BREAKPOINT_LEN_8:
+		*gen_len = HW_BREAKPOINT_LEN_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Construct an arch_hw_breakpoint from a perf_event.
+ */
+static int arch_build_bp_info(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+
+	/* Type */
+	switch (bp->attr.bp_type) {
+	case HW_BREAKPOINT_X:
+		info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+		break;
+	case HW_BREAKPOINT_R:
+		info->ctrl.type = ARM_BREAKPOINT_LOAD;
+		break;
+	case HW_BREAKPOINT_W:
+		info->ctrl.type = ARM_BREAKPOINT_STORE;
+		break;
+	case HW_BREAKPOINT_RW:
+		info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Len */
+	switch (bp->attr.bp_len) {
+	case HW_BREAKPOINT_LEN_1:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+		break;
+	case HW_BREAKPOINT_LEN_2:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+		break;
+	case HW_BREAKPOINT_LEN_4:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+		break;
+	case HW_BREAKPOINT_LEN_8:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE)
+			&& max_watchpoint_len >= 8)
+			break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Address */
+	info->address = bp->attr.bp_addr;
+
+	/* Privilege */
+	info->ctrl.privilege = ARM_BREAKPOINT_USER;
+	if (arch_check_bp_in_kernelspace(bp) && !bp_is_single_step(bp))
+		info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
+
+	/* Enabled? */
+	info->ctrl.enabled = !bp->attr.disabled;
+
+	/* Mismatch */
+	info->ctrl.mismatch = 0;
+
+	return 0;
+}
+
+/*
+ * Validate the arch-specific HW Breakpoint register settings.
+ */
+int arch_validate_hwbkpt_settings(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	int ret = 0;
+	u32 bytelen, max_len, offset, alignment_mask = 0x3;
+
+	/* Build the arch_hw_breakpoint. */
+	ret = arch_build_bp_info(bp);
+	if (ret)
+		goto out;
+
+	/* Check address alignment. */
+	if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+		alignment_mask = 0x7;
+	if (info->address & alignment_mask) {
+		/*
+		 * Try to fix the alignment. This may result in a length
+		 * that is too large, so we must check for that.
+		 */
+		bytelen = get_hbp_len(info->ctrl.len);
+		max_len = info->ctrl.type == ARM_BREAKPOINT_EXECUTE ? 4 :
+				max_watchpoint_len;
+
+		if (max_len >= 8)
+			offset = info->address & 0x7;
+		else
+			offset = info->address & 0x3;
+
+		if (bytelen > (1 << ((max_len - (offset + 1)) >> 1))) {
+			ret = -EFBIG;
+			goto out;
+		}
+
+		info->ctrl.len <<= offset;
+		info->address &= ~offset;
+
+		pr_debug("breakpoint alignment fixup: length = 0x%x, "
+			"address = 0x%x\n", info->ctrl.len, info->address);
+	}
+
+	/*
+	 * Currently we rely on an overflow handler to take
+	 * care of single-stepping the breakpoint when it fires.
+	 * In the case of userspace breakpoints on a core with V7 debug,
+	 * we can use the mismatch feature as a poor-man's hardware single-step.
+	 */
+	if (WARN_ONCE(!bp->overflow_handler &&
+		(arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_bps()),
+			"overflow handler required but none found")) {
+		ret = -EINVAL;
+		goto out;
+	}
+out:
+	return ret;
+}
+
+static void update_mismatch_flag(int idx, int flag)
+{
+	struct perf_event *bp = __get_cpu_var(bp_on_reg[idx]);
+	struct arch_hw_breakpoint *info;
+
+	if (bp == NULL)
+		return;
+
+	info = counter_arch_bp(bp);
+
+	/* Update the mismatch field to enter/exit `single-step' mode */
+	if (!bp->overflow_handler && info->ctrl.mismatch != flag) {
+		info->ctrl.mismatch = flag;
+		write_wb_reg(ARM_BASE_BCR + idx, encode_ctrl_reg(info->ctrl) | 0x1);
+	}
+}
+
+static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs)
+{
+	int i;
+	struct perf_event *bp, **slots = __get_cpu_var(wp_on_reg);
+	struct arch_hw_breakpoint *info;
+	struct perf_event_attr attr;
+
+	/* Without a disassembler, we can only handle 1 watchpoint. */
+	BUG_ON(core_num_wrps > 1);
+
+	hw_breakpoint_init(&attr);
+	attr.bp_addr	= regs->ARM_pc & ~0x3;
+	attr.bp_len	= HW_BREAKPOINT_LEN_4;
+	attr.bp_type	= HW_BREAKPOINT_X;
+
+	for (i = 0; i < core_num_wrps; ++i) {
+		rcu_read_lock();
+
+		if (slots[i] == NULL) {
+			rcu_read_unlock();
+			continue;
+		}
+
+		/*
+		 * The DFAR is an unknown value. Since we only allow a
+		 * single watchpoint, we can set the trigger to the lowest
+		 * possible faulting address.
+		 */
+		info = counter_arch_bp(slots[i]);
+		info->trigger = slots[i]->attr.bp_addr;
+		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
+		perf_bp_event(slots[i], regs);
+
+		/*
+		 * If no overflow handler is present, insert a temporary
+		 * mismatch breakpoint so we can single-step over the
+		 * watchpoint trigger.
+		 */
+		if (!slots[i]->overflow_handler) {
+			bp = register_user_hw_breakpoint(&attr,
+							 wp_single_step_handler,
+							 current);
+			counter_arch_bp(bp)->suspended_wp = slots[i];
+			perf_event_disable(slots[i]);
+		}
+
+		rcu_read_unlock();
+	}
+}
+
+static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs)
+{
+	int i;
+	int mismatch;
+	u32 ctrl_reg, val, addr;
+	struct perf_event *bp, **slots = __get_cpu_var(bp_on_reg);
+	struct arch_hw_breakpoint *info;
+	struct arch_hw_breakpoint_ctrl ctrl;
+
+	/* The exception entry code places the amended lr in the PC. */
+	addr = regs->ARM_pc;
+
+	for (i = 0; i < core_num_brps; ++i) {
+		rcu_read_lock();
+
+		bp = slots[i];
+
+		if (bp == NULL) {
+			rcu_read_unlock();
+			continue;
+		}
+
+		mismatch = 0;
+
+		/* Check if the breakpoint value matches. */
+		val = read_wb_reg(ARM_BASE_BVR + i);
+		if (val != (addr & ~0x3))
+			goto unlock;
+
+		/* Possible match, check the byte address select to confirm. */
+		ctrl_reg = read_wb_reg(ARM_BASE_BCR + i);
+		decode_ctrl_reg(ctrl_reg, &ctrl);
+		if ((1 << (addr & 0x3)) & ctrl.len) {
+			mismatch = 1;
+			info = counter_arch_bp(bp);
+			info->trigger = addr;
+		}
+
+unlock:
+		if ((mismatch && !info->ctrl.mismatch) || bp_is_single_step(bp)) {
+			pr_debug("breakpoint fired: address = 0x%x\n", addr);
+			perf_bp_event(bp, regs);
+		}
+
+		update_mismatch_flag(i, mismatch);
+		rcu_read_unlock();
+	}
+}
+
+/*
+ * Called from either the Data Abort Handler [watchpoint] or the
+ * Prefetch Abort Handler [breakpoint].
+ */
+static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
+				 struct pt_regs *regs)
+{
+	int ret = 1; /* Unhandled fault. */
+	u32 dscr;
+
+	/* We only handle watchpoints and hardware breakpoints. */
+	ARM_DBG_READ(c1, 0, dscr);
+
+	/* Perform perf callbacks. */
+	switch (ARM_DSCR_MOE(dscr)) {
+	case ARM_ENTRY_BREAKPOINT:
+		breakpoint_handler(addr, regs);
+		break;
+	case ARM_ENTRY_ASYNC_WATCHPOINT:
+		WARN_ON("Asynchronous watchpoint exception taken. "
+			"Debugging results may be unreliable");
+	case ARM_ENTRY_SYNC_WATCHPOINT:
+		watchpoint_handler(addr, regs);
+		break;
+	default:
+		goto out;
+	}
+
+	ret = 0;
+out:
+	return ret;
+}
+
+/*
+ * One-time initialisation.
+ */
+static void __init reset_ctrl_regs(void *unused)
+{
+	int i;
+
+	if (enable_monitor_mode())
+		return;
+
+	for (i = 0; i < core_num_brps; ++i) {
+		write_wb_reg(ARM_BASE_BCR + i, 0UL);
+		write_wb_reg(ARM_BASE_BVR + i, 0UL);
+	}
+
+	for (i = 0; i < core_num_wrps; ++i) {
+		write_wb_reg(ARM_BASE_WCR + i, 0UL);
+		write_wb_reg(ARM_BASE_WVR + i, 0UL);
+	}
+}
+
+static int __init arch_hw_breakpoint_init(void)
+{
+	int ret = 0;
+	u32 dscr;
+
+	debug_arch = get_debug_arch();
+
+	if (debug_arch > ARM_DEBUG_ARCH_V7_ECP14) {
+		pr_info("debug architecture 0x%x unsupported.\n", debug_arch);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	/* Determine how many BRPs/WRPs are available. */
+	core_num_brps = get_num_brps();
+	core_num_wrps = get_num_wrps();
+
+	pr_info("found %d breakpoint and %d watchpoint registers.\n",
+			core_num_brps, core_num_wrps);
+
+	if (core_has_mismatch_bps())
+		pr_info("1 breakpoint reserved for watchpoint single-step.\n");
+
+	ARM_DBG_READ(c1, 0, dscr);
+	if (dscr & ARM_DSCR_HDBGEN) {
+		pr_warning("halting debug mode enabled. Assuming maximum "
+				"watchpoint size of 4 bytes.");
+	} else {
+		/* Work out the maximum supported watchpoint length. */
+		max_watchpoint_len = get_max_wp_len();
+		pr_info("maximum watchpoint size is %u bytes.\n",
+				max_watchpoint_len);
+
+		/*
+		 * Reset the breakpoint resources. We assume that a halting
+		 * debugger will leave the world in a nice state for us.
+		 */
+		smp_call_function(reset_ctrl_regs, NULL, 1);
+		reset_ctrl_regs(NULL);
+	}
+
+	/* Register debug fault handler. */
+	hook_fault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
+			"watchpoint debug exception");
+	hook_ifault_code(2, hw_breakpoint_pending, SIGTRAP, TRAP_HWBKPT,
+			"breakpoint debug exception");
+
+out:
+	return ret;
+}
+arch_initcall(arch_hw_breakpoint_init);
+
+void hw_breakpoint_pmu_read(struct perf_event *bp)
+{
+}
+
+/*
+ * Dummy function to register with die_notifier.
+ */
+int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+					unsigned long val, void *data)
+{
+	return NOTIFY_DONE;
+}
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index c0d5c3b..36ad3be 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -154,14 +154,6 @@
 
 void __init init_IRQ(void)
 {
-	struct irq_desc *desc;
-	int irq;
-
-	for (irq = 0; irq < nr_irqs; irq++) {
-		desc = irq_to_desc_alloc_node(irq, 0);
-		desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
-	}
-
 	init_arch_irq();
 }
 
@@ -169,7 +161,7 @@
 int __init arch_probe_nr_irqs(void)
 {
 	nr_irqs = arch_nr_irqs ? arch_nr_irqs : NR_IRQS;
-	return 0;
+	return nr_irqs;
 }
 #endif
 
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 6b46058..d9bd786 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -69,20 +69,31 @@
 {
 #ifdef CONFIG_ARM_UNWIND
 	Elf_Shdr *s, *sechdrs_end = sechdrs + hdr->e_shnum;
+	struct arm_unwind_mapping *maps = mod->arch.map;
 
 	for (s = sechdrs; s < sechdrs_end; s++) {
-		if (strcmp(".ARM.exidx.init.text", secstrings + s->sh_name) == 0)
-			mod->arch.unw_sec_init = s;
-		else if (strcmp(".ARM.exidx.devinit.text", secstrings + s->sh_name) == 0)
-			mod->arch.unw_sec_devinit = s;
-		else if (strcmp(".ARM.exidx", secstrings + s->sh_name) == 0)
-			mod->arch.unw_sec_core = s;
-		else if (strcmp(".init.text", secstrings + s->sh_name) == 0)
-			mod->arch.sec_init_text = s;
-		else if (strcmp(".devinit.text", secstrings + s->sh_name) == 0)
-			mod->arch.sec_devinit_text = s;
-		else if (strcmp(".text", secstrings + s->sh_name) == 0)
-			mod->arch.sec_core_text = s;
+		char const *secname = secstrings + s->sh_name;
+
+		if (strcmp(".ARM.exidx.init.text", secname) == 0)
+			maps[ARM_SEC_INIT].unw_sec = s;
+		else if (strcmp(".ARM.exidx.devinit.text", secname) == 0)
+			maps[ARM_SEC_DEVINIT].unw_sec = s;
+		else if (strcmp(".ARM.exidx", secname) == 0)
+			maps[ARM_SEC_CORE].unw_sec = s;
+		else if (strcmp(".ARM.exidx.exit.text", secname) == 0)
+			maps[ARM_SEC_EXIT].unw_sec = s;
+		else if (strcmp(".ARM.exidx.devexit.text", secname) == 0)
+			maps[ARM_SEC_DEVEXIT].unw_sec = s;
+		else if (strcmp(".init.text", secname) == 0)
+			maps[ARM_SEC_INIT].sec_text = s;
+		else if (strcmp(".devinit.text", secname) == 0)
+			maps[ARM_SEC_DEVINIT].sec_text = s;
+		else if (strcmp(".text", secname) == 0)
+			maps[ARM_SEC_CORE].sec_text = s;
+		else if (strcmp(".exit.text", secname) == 0)
+			maps[ARM_SEC_EXIT].sec_text = s;
+		else if (strcmp(".devexit.text", secname) == 0)
+			maps[ARM_SEC_DEVEXIT].sec_text = s;
 	}
 #endif
 	return 0;
@@ -292,31 +303,22 @@
 #ifdef CONFIG_ARM_UNWIND
 static void register_unwind_tables(struct module *mod)
 {
-	if (mod->arch.unw_sec_init && mod->arch.sec_init_text)
-		mod->arch.unwind_init =
-			unwind_table_add(mod->arch.unw_sec_init->sh_addr,
-					 mod->arch.unw_sec_init->sh_size,
-					 mod->arch.sec_init_text->sh_addr,
-					 mod->arch.sec_init_text->sh_size);
-	if (mod->arch.unw_sec_devinit && mod->arch.sec_devinit_text)
-		mod->arch.unwind_devinit =
-			unwind_table_add(mod->arch.unw_sec_devinit->sh_addr,
-					 mod->arch.unw_sec_devinit->sh_size,
-					 mod->arch.sec_devinit_text->sh_addr,
-					 mod->arch.sec_devinit_text->sh_size);
-	if (mod->arch.unw_sec_core && mod->arch.sec_core_text)
-		mod->arch.unwind_core =
-			unwind_table_add(mod->arch.unw_sec_core->sh_addr,
-					 mod->arch.unw_sec_core->sh_size,
-					 mod->arch.sec_core_text->sh_addr,
-					 mod->arch.sec_core_text->sh_size);
+	int i;
+	for (i = 0; i < ARM_SEC_MAX; ++i) {
+		struct arm_unwind_mapping *map = &mod->arch.map[i];
+		if (map->unw_sec && map->sec_text)
+			map->unwind = unwind_table_add(map->unw_sec->sh_addr,
+						       map->unw_sec->sh_size,
+						       map->sec_text->sh_addr,
+						       map->sec_text->sh_size);
+	}
 }
 
 static void unregister_unwind_tables(struct module *mod)
 {
-	unwind_table_del(mod->arch.unwind_init);
-	unwind_table_del(mod->arch.unwind_devinit);
-	unwind_table_del(mod->arch.unwind_core);
+	int i = ARM_SEC_MAX;
+	while (--i >= 0)
+		unwind_table_del(mod->arch.map[i].unwind);
 }
 #else
 static inline void register_unwind_tables(struct module *mod) { }
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index ecbb028..49643b1 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -123,6 +123,12 @@
 }
 EXPORT_SYMBOL_GPL(armpmu_get_max_events);
 
+int perf_num_counters(void)
+{
+	return armpmu_get_max_events();
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
 #define HW_OP_UNSUPPORTED		0xFFFF
 
 #define C(_x) \
@@ -221,27 +227,6 @@
 }
 
 static void
-armpmu_disable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-
-	WARN_ON(idx < 0);
-
-	clear_bit(idx, cpuc->active_mask);
-	armpmu->disable(hwc, idx);
-
-	barrier();
-
-	armpmu_event_update(event, hwc, idx);
-	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
-
-	perf_event_update_userpage(event);
-}
-
-static void
 armpmu_read(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -254,13 +239,44 @@
 }
 
 static void
-armpmu_unthrottle(struct perf_event *event)
+armpmu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!armpmu)
+		return;
+
+	/*
+	 * ARM pmu always has to update the counter, so ignore
+	 * PERF_EF_UPDATE, see comments in armpmu_start().
+	 */
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		armpmu->disable(hwc, hwc->idx);
+		barrier(); /* why? */
+		armpmu_event_update(event, hwc, hwc->idx);
+		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	}
+}
+
+static void
+armpmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!armpmu)
+		return;
+
+	/*
+	 * ARM pmu always has to reprogram the period, so ignore
+	 * PERF_EF_RELOAD, see the comment below.
+	 */
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
 	/*
 	 * Set the period again. Some counters can't be stopped, so when we
-	 * were throttled we simply disabled the IRQ source and the counter
+	 * were stopped we simply disabled the IRQ source and the counter
 	 * may have been left counting. If we don't do this step then we may
 	 * get an interrupt too soon or *way* too late if the overflow has
 	 * happened since disabling.
@@ -269,14 +285,33 @@
 	armpmu->enable(hwc, hwc->idx);
 }
 
+static void
+armpmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	WARN_ON(idx < 0);
+
+	clear_bit(idx, cpuc->active_mask);
+	armpmu_stop(event, PERF_EF_UPDATE);
+	cpuc->events[idx] = NULL;
+	clear_bit(idx, cpuc->used_mask);
+
+	perf_event_update_userpage(event);
+}
+
 static int
-armpmu_enable(struct perf_event *event)
+armpmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
 
+	perf_pmu_disable(event->pmu);
+
 	/* If we don't have a space for the counter then finish early. */
 	idx = armpmu->get_event_idx(cpuc, hwc);
 	if (idx < 0) {
@@ -293,25 +328,19 @@
 	cpuc->events[idx] = event;
 	set_bit(idx, cpuc->active_mask);
 
-	/* Set the period for the event. */
-	armpmu_event_set_period(event, hwc, idx);
-
-	/* Enable the event. */
-	armpmu->enable(hwc, idx);
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	if (flags & PERF_EF_START)
+		armpmu_start(event, PERF_EF_RELOAD);
 
 	/* Propagate our changes to the userspace mapping. */
 	perf_event_update_userpage(event);
 
 out:
+	perf_pmu_enable(event->pmu);
 	return err;
 }
 
-static struct pmu pmu = {
-	.enable	    = armpmu_enable,
-	.disable    = armpmu_disable,
-	.unthrottle = armpmu_unthrottle,
-	.read	    = armpmu_read,
-};
+static struct pmu pmu;
 
 static int
 validate_event(struct cpu_hw_events *cpuc,
@@ -491,20 +520,29 @@
 	return err;
 }
 
-const struct pmu *
-hw_perf_event_init(struct perf_event *event)
+static int armpmu_event_init(struct perf_event *event)
 {
 	int err = 0;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!armpmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	event->destroy = hw_perf_event_destroy;
 
 	if (!atomic_inc_not_zero(&active_events)) {
-		if (atomic_read(&active_events) > perf_max_events) {
+		if (atomic_read(&active_events) > armpmu->num_events) {
 			atomic_dec(&active_events);
-			return ERR_PTR(-ENOSPC);
+			return -ENOSPC;
 		}
 
 		mutex_lock(&pmu_reserve_mutex);
@@ -518,17 +556,16 @@
 	}
 
 	if (err)
-		return ERR_PTR(err);
+		return err;
 
 	err = __hw_perf_event_init(event);
 	if (err)
 		hw_perf_event_destroy(event);
 
-	return err ? ERR_PTR(err) : &pmu;
+	return err;
 }
 
-void
-hw_perf_enable(void)
+static void armpmu_enable(struct pmu *pmu)
 {
 	/* Enable all of the perf events on hardware. */
 	int idx;
@@ -549,13 +586,23 @@
 	armpmu->start();
 }
 
-void
-hw_perf_disable(void)
+static void armpmu_disable(struct pmu *pmu)
 {
 	if (armpmu)
 		armpmu->stop();
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= armpmu_enable,
+	.pmu_disable	= armpmu_disable,
+	.event_init	= armpmu_event_init,
+	.add		= armpmu_add,
+	.del		= armpmu_del,
+	.start		= armpmu_start,
+	.stop		= armpmu_stop,
+	.read		= armpmu_read,
+};
+
 /*
  * ARMv6 Performance counter handling code.
  *
@@ -1045,7 +1092,7 @@
 	 * platforms that can have the PMU interrupts raised as an NMI, this
 	 * will not work.
 	 */
-	perf_event_do_pending();
+	irq_work_run();
 
 	return IRQ_HANDLED;
 }
@@ -2021,7 +2068,7 @@
 	 * platforms that can have the PMU interrupts raised as an NMI, this
 	 * will not work.
 	 */
-	perf_event_do_pending();
+	irq_work_run();
 
 	return IRQ_HANDLED;
 }
@@ -2389,7 +2436,7 @@
 			armpmu->disable(hwc, idx);
 	}
 
-	perf_event_do_pending();
+	irq_work_run();
 
 	/*
 	 * Re-enable the PMU.
@@ -2716,7 +2763,7 @@
 			armpmu->disable(hwc, idx);
 	}
 
-	perf_event_do_pending();
+	irq_work_run();
 
 	/*
 	 * Re-enable the PMU.
@@ -2933,14 +2980,12 @@
 			armpmu = &armv6pmu;
 			memcpy(armpmu_perf_cache_map, armv6_perf_cache_map,
 					sizeof(armv6_perf_cache_map));
-			perf_max_events	= armv6pmu.num_events;
 			break;
 		case 0xB020:	/* ARM11mpcore */
 			armpmu = &armv6mpcore_pmu;
 			memcpy(armpmu_perf_cache_map,
 			       armv6mpcore_perf_cache_map,
 			       sizeof(armv6mpcore_perf_cache_map));
-			perf_max_events = armv6mpcore_pmu.num_events;
 			break;
 		case 0xC080:	/* Cortex-A8 */
 			armv7pmu.id = ARM_PERF_PMU_ID_CA8;
@@ -2952,7 +2997,6 @@
 			/* Reset PMNC and read the nb of CNTx counters
 			    supported */
 			armv7pmu.num_events = armv7_reset_read_pmnc();
-			perf_max_events = armv7pmu.num_events;
 			break;
 		case 0xC090:	/* Cortex-A9 */
 			armv7pmu.id = ARM_PERF_PMU_ID_CA9;
@@ -2964,7 +3008,6 @@
 			/* Reset PMNC and read the nb of CNTx counters
 			    supported */
 			armv7pmu.num_events = armv7_reset_read_pmnc();
-			perf_max_events = armv7pmu.num_events;
 			break;
 		}
 	/* Intel CPUs [xscale]. */
@@ -2975,13 +3018,11 @@
 			armpmu = &xscale1pmu;
 			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
 					sizeof(xscale_perf_cache_map));
-			perf_max_events	= xscale1pmu.num_events;
 			break;
 		case 2:
 			armpmu = &xscale2pmu;
 			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
 					sizeof(xscale_perf_cache_map));
-			perf_max_events	= xscale2pmu.num_events;
 			break;
 		}
 	}
@@ -2991,9 +3032,10 @@
 				arm_pmu_names[armpmu->id], armpmu->num_events);
 	} else {
 		pr_info("no hardware support available\n");
-		perf_max_events = -1;
 	}
 
+	perf_pmu_register(&pmu);
+
 	return 0;
 }
 arch_initcall(init_hw_perf_events);
@@ -3001,13 +3043,6 @@
 /*
  * Callchain handling code.
  */
-static inline void
-callchain_store(struct perf_callchain_entry *entry,
-		u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 /*
  * The registers we're interested in are at the end of the variable
@@ -3039,7 +3074,7 @@
 	if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail)))
 		return NULL;
 
-	callchain_store(entry, buftail.lr);
+	perf_callchain_store(entry, buftail.lr);
 
 	/*
 	 * Frame pointers should strictly progress back up the stack
@@ -3051,16 +3086,11 @@
 	return buftail.fp - 1;
 }
 
-static void
-perf_callchain_user(struct pt_regs *regs,
-		    struct perf_callchain_entry *entry)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct frame_tail *tail;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-
-	if (!user_mode(regs))
-		regs = task_pt_regs(current);
 
 	tail = (struct frame_tail *)regs->ARM_fp - 1;
 
@@ -3078,56 +3108,18 @@
 		void *data)
 {
 	struct perf_callchain_entry *entry = data;
-	callchain_store(entry, fr->pc);
+	perf_callchain_store(entry, fr->pc);
 	return 0;
 }
 
-static void
-perf_callchain_kernel(struct pt_regs *regs,
-		      struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct stackframe fr;
 
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
 	fr.fp = regs->ARM_fp;
 	fr.sp = regs->ARM_sp;
 	fr.lr = regs->ARM_lr;
 	fr.pc = regs->ARM_pc;
 	walk_stackframe(&fr, callchain_trace, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs,
-		  struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (!current || !current->pid)
-		return;
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-
-	if (current->mm)
-		perf_callchain_user(regs, entry);
-}
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-
-struct perf_callchain_entry *
-perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry);
-
-	entry->nr = 0;
-	perf_do_callchain(regs, entry);
-	return entry;
-}
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 401e38b..e76fcaa 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -29,6 +29,7 @@
 #include <linux/utsname.h>
 #include <linux/uaccess.h>
 #include <linux/random.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/cacheflush.h>
 #include <asm/leds.h>
@@ -135,6 +136,25 @@
 void (*arm_pm_restart)(char str, const char *cmd) = arm_machine_restart;
 EXPORT_SYMBOL_GPL(arm_pm_restart);
 
+static void do_nothing(void *unused)
+{
+}
+
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
+ * pm_idle and update to new pm_idle value. Required while changing pm_idle
+ * handler on SMP systems.
+ *
+ * Caller must have changed pm_idle to the new value before the call. Old
+ * pm_idle value will not be used by any CPU after the return of this function.
+ */
+void cpu_idle_wait(void)
+{
+	smp_mb();
+	/* kick all the CPUs so that they exit out of pm_idle */
+	smp_call_function(do_nothing, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
 /*
  * This is our default idle handler.  We need to disable
@@ -317,6 +337,8 @@
 	struct thread_info *thread = current_thread_info();
 	struct task_struct *tsk = current;
 
+	flush_ptrace_hw_breakpoint(tsk);
+
 	memset(thread->used_cp, 0, sizeof(thread->used_cp));
 	memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
 	memset(&thread->fpstate, 0, sizeof(union fp_state));
@@ -345,6 +367,8 @@
 	thread->cpu_context.sp = (unsigned long)childregs;
 	thread->cpu_context.pc = (unsigned long)ret_from_fork;
 
+	clear_ptrace_hw_breakpoint(p);
+
 	if (clone_flags & CLONE_SETTLS)
 		thread->tp_value = regs->ARM_r3;
 
@@ -458,3 +482,24 @@
 	unsigned long range_end = mm->brk + 0x02000000;
 	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
 }
+
+/*
+ * The vectors page is always readable from user space for the
+ * atomic helpers and the signal restart code.  Let's declare a mapping
+ * for it so it is visible through ptrace and /proc/<pid>/mem.
+ */
+
+int vectors_user_mapping(void)
+{
+	struct mm_struct *mm = current->mm;
+	return install_special_mapping(mm, 0xffff0000, PAGE_SIZE,
+				       VM_READ | VM_EXEC |
+				       VM_MAYREAD | VM_MAYEXEC |
+				       VM_ALWAYSDUMP | VM_RESERVED,
+				       NULL);
+}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	return (vma->vm_start == 0xffff0000) ? "[vectors]" : NULL;
+}
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index f99d489..e0cb637 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -19,6 +19,8 @@
 #include <linux/init.h>
 #include <linux/signal.h>
 #include <linux/uaccess.h>
+#include <linux/perf_event.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -847,6 +849,232 @@
 }
 #endif
 
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+/*
+ * Convert a virtual register number into an index for a thread_info
+ * breakpoint array. Breakpoints are identified using positive numbers
+ * whilst watchpoints are negative. The registers are laid out as pairs
+ * of (address, control), each pair mapping to a unique hw_breakpoint struct.
+ * Register 0 is reserved for describing resource information.
+ */
+static int ptrace_hbp_num_to_idx(long num)
+{
+	if (num < 0)
+		num = (ARM_MAX_BRP << 1) - num;
+	return (num - 1) >> 1;
+}
+
+/*
+ * Returns the virtual register number for the address of the
+ * breakpoint at index idx.
+ */
+static long ptrace_hbp_idx_to_num(int idx)
+{
+	long mid = ARM_MAX_BRP << 1;
+	long num = (idx << 1) + 1;
+	return num > mid ? mid - num : num;
+}
+
+/*
+ * Handle hitting a HW-breakpoint.
+ */
+static void ptrace_hbptriggered(struct perf_event *bp, int unused,
+				     struct perf_sample_data *data,
+				     struct pt_regs *regs)
+{
+	struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
+	long num;
+	int i;
+	siginfo_t info;
+
+	for (i = 0; i < ARM_MAX_HBP_SLOTS; ++i)
+		if (current->thread.debug.hbp[i] == bp)
+			break;
+
+	num = (i == ARM_MAX_HBP_SLOTS) ? 0 : ptrace_hbp_idx_to_num(i);
+
+	info.si_signo	= SIGTRAP;
+	info.si_errno	= (int)num;
+	info.si_code	= TRAP_HWBKPT;
+	info.si_addr	= (void __user *)(bkpt->trigger);
+
+	force_sig_info(SIGTRAP, &info, current);
+}
+
+/*
+ * Set ptrace breakpoint pointers to zero for this task.
+ * This is required in order to prevent child processes from unregistering
+ * breakpoints held by their parent.
+ */
+void clear_ptrace_hw_breakpoint(struct task_struct *tsk)
+{
+	memset(tsk->thread.debug.hbp, 0, sizeof(tsk->thread.debug.hbp));
+}
+
+/*
+ * Unregister breakpoints from this task and reset the pointers in
+ * the thread_struct.
+ */
+void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
+{
+	int i;
+	struct thread_struct *t = &tsk->thread;
+
+	for (i = 0; i < ARM_MAX_HBP_SLOTS; i++) {
+		if (t->debug.hbp[i]) {
+			unregister_hw_breakpoint(t->debug.hbp[i]);
+			t->debug.hbp[i] = NULL;
+		}
+	}
+}
+
+static u32 ptrace_get_hbp_resource_info(void)
+{
+	u8 num_brps, num_wrps, debug_arch, wp_len;
+	u32 reg = 0;
+
+	num_brps	= hw_breakpoint_slots(TYPE_INST);
+	num_wrps	= hw_breakpoint_slots(TYPE_DATA);
+	debug_arch	= arch_get_debug_arch();
+	wp_len		= arch_get_max_wp_len();
+
+	reg		|= debug_arch;
+	reg		<<= 8;
+	reg		|= wp_len;
+	reg		<<= 8;
+	reg		|= num_wrps;
+	reg		<<= 8;
+	reg		|= num_brps;
+
+	return reg;
+}
+
+static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type)
+{
+	struct perf_event_attr attr;
+
+	ptrace_breakpoint_init(&attr);
+
+	/* Initialise fields to sane defaults. */
+	attr.bp_addr	= 0;
+	attr.bp_len	= HW_BREAKPOINT_LEN_4;
+	attr.bp_type	= type;
+	attr.disabled	= 1;
+
+	return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, tsk);
+}
+
+static int ptrace_gethbpregs(struct task_struct *tsk, long num,
+			     unsigned long  __user *data)
+{
+	u32 reg;
+	int idx, ret = 0;
+	struct perf_event *bp;
+	struct arch_hw_breakpoint_ctrl arch_ctrl;
+
+	if (num == 0) {
+		reg = ptrace_get_hbp_resource_info();
+	} else {
+		idx = ptrace_hbp_num_to_idx(num);
+		if (idx < 0 || idx >= ARM_MAX_HBP_SLOTS) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		bp = tsk->thread.debug.hbp[idx];
+		if (!bp) {
+			reg = 0;
+			goto put;
+		}
+
+		arch_ctrl = counter_arch_bp(bp)->ctrl;
+
+		/*
+		 * Fix up the len because we may have adjusted it
+		 * to compensate for an unaligned address.
+		 */
+		while (!(arch_ctrl.len & 0x1))
+			arch_ctrl.len >>= 1;
+
+		if (idx & 0x1)
+			reg = encode_ctrl_reg(arch_ctrl);
+		else
+			reg = bp->attr.bp_addr;
+	}
+
+put:
+	if (put_user(reg, data))
+		ret = -EFAULT;
+
+out:
+	return ret;
+}
+
+static int ptrace_sethbpregs(struct task_struct *tsk, long num,
+			     unsigned long __user *data)
+{
+	int idx, gen_len, gen_type, implied_type, ret = 0;
+	u32 user_val;
+	struct perf_event *bp;
+	struct arch_hw_breakpoint_ctrl ctrl;
+	struct perf_event_attr attr;
+
+	if (num == 0)
+		goto out;
+	else if (num < 0)
+		implied_type = HW_BREAKPOINT_RW;
+	else
+		implied_type = HW_BREAKPOINT_X;
+
+	idx = ptrace_hbp_num_to_idx(num);
+	if (idx < 0 || idx >= ARM_MAX_HBP_SLOTS) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (get_user(user_val, data)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	bp = tsk->thread.debug.hbp[idx];
+	if (!bp) {
+		bp = ptrace_hbp_create(tsk, implied_type);
+		if (IS_ERR(bp)) {
+			ret = PTR_ERR(bp);
+			goto out;
+		}
+		tsk->thread.debug.hbp[idx] = bp;
+	}
+
+	attr = bp->attr;
+
+	if (num & 0x1) {
+		/* Address */
+		attr.bp_addr	= user_val;
+	} else {
+		/* Control */
+		decode_ctrl_reg(user_val, &ctrl);
+		ret = arch_bp_generic_fields(ctrl, &gen_len, &gen_type);
+		if (ret)
+			goto out;
+
+		if ((gen_type & implied_type) != gen_type) {
+				ret = -EINVAL;
+				goto out;
+		}
+
+		attr.bp_len	= gen_len;
+		attr.bp_type	= gen_type;
+		attr.disabled	= !ctrl.enabled;
+	}
+
+	ret = modify_user_hw_breakpoint(bp, &attr);
+out:
+	return ret;
+}
+#endif
+
 long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 {
 	int ret;
@@ -916,6 +1144,17 @@
 			break;
 #endif
 
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+		case PTRACE_GETHBPREGS:
+			ret = ptrace_gethbpregs(child, addr,
+						(unsigned long __user *)data);
+			break;
+		case PTRACE_SETHBPREGS:
+			ret = ptrace_sethbpregs(child, addr,
+						(unsigned long __user *)data);
+			break;
+#endif
+
 		default:
 			ret = ptrace_request(child, request, addr, data);
 			break;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index d5231ae..336f14e 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -36,6 +36,7 @@
 #include <asm/procinfo.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/smp_plat.h>
 #include <asm/mach-types.h>
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
@@ -238,6 +239,35 @@
 	return cpu_arch;
 }
 
+static int cpu_has_aliasing_icache(unsigned int arch)
+{
+	int aliasing_icache;
+	unsigned int id_reg, num_sets, line_size;
+
+	/* arch specifies the register format */
+	switch (arch) {
+	case CPU_ARCH_ARMv7:
+		asm("mcr	p15, 2, %0, c0, c0, 0 @ set CSSELR"
+		    : /* No output operands */
+		    : "r" (1));
+		isb();
+		asm("mrc	p15, 1, %0, c0, c0, 0 @ read CCSIDR"
+		    : "=r" (id_reg));
+		line_size = 4 << ((id_reg & 0x7) + 2);
+		num_sets = ((id_reg >> 13) & 0x7fff) + 1;
+		aliasing_icache = (line_size * num_sets) > PAGE_SIZE;
+		break;
+	case CPU_ARCH_ARMv6:
+		aliasing_icache = read_cpuid_cachetype() & (1 << 11);
+		break;
+	default:
+		/* I-cache aliases will be handled by D-cache aliasing code */
+		aliasing_icache = 0;
+	}
+
+	return aliasing_icache;
+}
+
 static void __init cacheid_init(void)
 {
 	unsigned int cachetype = read_cpuid_cachetype();
@@ -249,10 +279,15 @@
 			cacheid = CACHEID_VIPT_NONALIASING;
 			if ((cachetype & (3 << 14)) == 1 << 14)
 				cacheid |= CACHEID_ASID_TAGGED;
-		} else if (cachetype & (1 << 23))
+			else if (cpu_has_aliasing_icache(CPU_ARCH_ARMv7))
+				cacheid |= CACHEID_VIPT_I_ALIASING;
+		} else if (cachetype & (1 << 23)) {
 			cacheid = CACHEID_VIPT_ALIASING;
-		else
+		} else {
 			cacheid = CACHEID_VIPT_NONALIASING;
+			if (cpu_has_aliasing_icache(CPU_ARCH_ARMv6))
+				cacheid |= CACHEID_VIPT_I_ALIASING;
+		}
 	} else {
 		cacheid = CACHEID_VIVT;
 	}
@@ -263,7 +298,7 @@
 		cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown",
 		cache_is_vivt() ? "VIVT" :
 		icache_is_vivt_asid_tagged() ? "VIVT ASID tagged" :
-		cache_is_vipt_aliasing() ? "VIPT aliasing" :
+		icache_is_vipt_aliasing() ? "VIPT aliasing" :
 		cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown");
 }
 
@@ -490,7 +525,7 @@
 
 	kernel_code.start   = virt_to_phys(_text);
 	kernel_code.end     = virt_to_phys(_etext - 1);
-	kernel_data.start   = virt_to_phys(_data);
+	kernel_data.start   = virt_to_phys(_sdata);
 	kernel_data.end     = virt_to_phys(_end - 1);
 
 	for (i = 0; i < mi->nr_banks; i++) {
@@ -825,7 +860,8 @@
 	request_standard_resources(&meminfo, mdesc);
 
 #ifdef CONFIG_SMP
-	smp_init_cpus();
+	if (is_smp())
+		smp_init_cpus();
 #endif
 	reserve_crashkernel();
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 40dc74f..8c19595 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
+#include <asm/sections.h>
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
@@ -67,12 +68,47 @@
 	IPI_CPU_STOP,
 };
 
+static inline void identity_mapping_add(pgd_t *pgd, unsigned long start,
+	unsigned long end)
+{
+	unsigned long addr, prot;
+	pmd_t *pmd;
+
+	prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE;
+	if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale())
+		prot |= PMD_BIT4;
+
+	for (addr = start & PGDIR_MASK; addr < end;) {
+		pmd = pmd_offset(pgd + pgd_index(addr), addr);
+		pmd[0] = __pmd(addr | prot);
+		addr += SECTION_SIZE;
+		pmd[1] = __pmd(addr | prot);
+		addr += SECTION_SIZE;
+		flush_pmd_entry(pmd);
+		outer_clean_range(__pa(pmd), __pa(pmd + 1));
+	}
+}
+
+static inline void identity_mapping_del(pgd_t *pgd, unsigned long start,
+	unsigned long end)
+{
+	unsigned long addr;
+	pmd_t *pmd;
+
+	for (addr = start & PGDIR_MASK; addr < end; addr += PGDIR_SIZE) {
+		pmd = pmd_offset(pgd + pgd_index(addr), addr);
+		pmd[0] = __pmd(0);
+		pmd[1] = __pmd(0);
+		clean_pmd_entry(pmd);
+		outer_clean_range(__pa(pmd), __pa(pmd + 1));
+	}
+}
+
 int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
 	struct task_struct *idle = ci->idle;
 	pgd_t *pgd;
-	pmd_t *pmd;
 	int ret;
 
 	/*
@@ -101,11 +137,16 @@
 	 * a 1:1 mapping for the physical address of the kernel.
 	 */
 	pgd = pgd_alloc(&init_mm);
-	pmd = pmd_offset(pgd + pgd_index(PHYS_OFFSET), PHYS_OFFSET);
-	*pmd = __pmd((PHYS_OFFSET & PGDIR_MASK) |
-		     PMD_TYPE_SECT | PMD_SECT_AP_WRITE);
-	flush_pmd_entry(pmd);
-	outer_clean_range(__pa(pmd), __pa(pmd + 1));
+	if (!pgd)
+		return -ENOMEM;
+
+	if (PHYS_OFFSET != PAGE_OFFSET) {
+#ifndef CONFIG_HOTPLUG_CPU
+		identity_mapping_add(pgd, __pa(__init_begin), __pa(__init_end));
+#endif
+		identity_mapping_add(pgd, __pa(_stext), __pa(_etext));
+		identity_mapping_add(pgd, __pa(_sdata), __pa(_edata));
+	}
 
 	/*
 	 * We need to tell the secondary core where to find
@@ -143,8 +184,14 @@
 	secondary_data.stack = NULL;
 	secondary_data.pgdir = 0;
 
-	*pmd = __pmd(0);
-	clean_pmd_entry(pmd);
+	if (PHYS_OFFSET != PAGE_OFFSET) {
+#ifndef CONFIG_HOTPLUG_CPU
+		identity_mapping_del(pgd, __pa(__init_begin), __pa(__init_end));
+#endif
+		identity_mapping_del(pgd, __pa(_stext), __pa(_etext));
+		identity_mapping_del(pgd, __pa(_sdata), __pa(_edata));
+	}
+
 	pgd_free(&init_mm, pgd);
 
 	if (ret) {
@@ -567,7 +614,8 @@
 {
 	cpumask_t mask = cpu_online_map;
 	cpu_clear(smp_processor_id(), mask);
-	send_ipi_message(&mask, IPI_CPU_STOP);
+	if (!cpus_empty(mask))
+		send_ipi_message(&mask, IPI_CPU_STOP);
 }
 
 /*
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index dd81a91..2a16176 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -146,6 +146,8 @@
 			    addr < table->end_addr) {
 				idx = search_index(addr, table->start,
 						   table->stop - 1);
+				/* Move-to-front to exploit common traces */
+				list_move(&table->list, &unwind_tables);
 				break;
 			}
 		}
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index b16c079..1953e3d 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -8,6 +8,19 @@
 #include <asm/memory.h>
 #include <asm/page.h>
 	
+#define PROC_INFO							\
+	VMLINUX_SYMBOL(__proc_info_begin) = .;				\
+	*(.proc.info.init)						\
+	VMLINUX_SYMBOL(__proc_info_end) = .;
+
+#ifdef CONFIG_HOTPLUG_CPU
+#define ARM_CPU_DISCARD(x)
+#define ARM_CPU_KEEP(x)		x
+#else
+#define ARM_CPU_DISCARD(x)	x
+#define ARM_CPU_KEEP(x)
+#endif
+
 OUTPUT_ARCH(arm)
 ENTRY(stext)
 
@@ -31,15 +44,18 @@
 			HEAD_TEXT
 			INIT_TEXT
 		_einittext = .;
-		__proc_info_begin = .;
-			*(.proc.info.init)
-		__proc_info_end = .;
+		ARM_CPU_DISCARD(PROC_INFO)
 		__arch_info_begin = .;
 			*(.arch.info.init)
 		__arch_info_end = .;
 		__tagtable_begin = .;
 			*(.taglist.init)
 		__tagtable_end = .;
+#ifdef CONFIG_SMP_ON_UP
+		__smpalt_begin = .;
+			*(.alt.smp.init)
+		__smpalt_end = .;
+#endif
 
 		INIT_SETUP(16)
 
@@ -68,10 +84,8 @@
 	/DISCARD/ : {
 		*(.ARM.exidx.exit.text)
 		*(.ARM.extab.exit.text)
-#ifndef CONFIG_HOTPLUG_CPU
-		*(.ARM.exidx.cpuexit.text)
-		*(.ARM.extab.cpuexit.text)
-#endif
+		ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text))
+		ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text))
 #ifndef CONFIG_HOTPLUG
 		*(.ARM.exidx.devexit.text)
 		*(.ARM.extab.devexit.text)
@@ -100,12 +114,11 @@
 			*(.glue_7)
 			*(.glue_7t)
 		*(.got)			/* Global offset table		*/
+			ARM_CPU_KEEP(PROC_INFO)
 	}
 
 	RO_DATA(PAGE_SIZE)
 
-	_etext = .;			/* End of text and rodata section */
-
 #ifdef CONFIG_ARM_UNWIND
 	/*
 	 * Stack unwinding tables
@@ -123,6 +136,8 @@
 	}
 #endif
 
+	_etext = .;			/* End of text and rodata section */
+
 #ifdef CONFIG_XIP_KERNEL
 	__data_loc = ALIGN(4);		/* location in binary */
 	. = PAGE_OFFSET + TEXT_OFFSET;
@@ -237,6 +252,12 @@
 
 	/* Default discards */
 	DISCARDS
+
+#ifndef CONFIG_SMP_ON_UP
+	/DISCARD/ : {
+		*(.alt.smp.init)
+	}
+#endif
 }
 
 /*
diff --git a/arch/arm/mach-aaec2000/aaed2000.c b/arch/arm/mach-aaec2000/aaed2000.c
index 81a3ecc..0eb3e3e 100644
--- a/arch/arm/mach-aaec2000/aaed2000.c
+++ b/arch/arm/mach-aaec2000/aaed2000.c
@@ -95,8 +95,6 @@
 
 MACHINE_START(AAED2000, "Agilent AAED-2000 Development Platform")
 	/* Maintainer: Nicolas Bellido Y Ortega */
-	.phys_io	= PIO_BASE,
-	.io_pg_offst	= ((VIO_BASE) >> 18) & 0xfffc,
 	.map_io		= aaed2000_map_io,
 	.init_irq	= aaed2000_init_irq,
 	.timer		= &aaec2000_timer,
diff --git a/arch/arm/mach-aaec2000/include/mach/debug-macro.S b/arch/arm/mach-aaec2000/include/mach/debug-macro.S
index a9cac36..bc7ad55 100644
--- a/arch/arm/mach-aaec2000/include/mach/debug-macro.S
+++ b/arch/arm/mach-aaec2000/include/mach/debug-macro.S
@@ -10,12 +10,10 @@
  */
 
 #include "hardware.h"
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x80000000		@ physical
-		movne	\rx, #io_p2v(0x80000000)	@ virtual
-		orr	\rx, \rx, #0x00000800
+		.macro	addruart, rp, rv
+		mov	\rp, 0x00000800
+		orr	\rv, \rp, #io_p2v(0x80000000)	@ virtual
+		orr	\rp, \rp, #0x80000000		@ physical
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/mach-aaec2000/include/mach/vmalloc.h b/arch/arm/mach-aaec2000/include/mach/vmalloc.h
index 551f68f..cff4e0a 100644
--- a/arch/arm/mach-aaec2000/include/mach/vmalloc.h
+++ b/arch/arm/mach-aaec2000/include/mach/vmalloc.h
@@ -11,6 +11,6 @@
 #ifndef __ASM_ARCH_VMALLOC_H
 #define __ASM_ARCH_VMALLOC_H
 
-#define VMALLOC_END		(PAGE_OFFSET + 0x10000000)
+#define VMALLOC_END		0xd0000000
 
 #endif /* __ASM_ARCH_VMALLOC_H */
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 939bccd..851e813 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -33,6 +33,7 @@
 	select HAVE_AT91_USART3
 	select HAVE_AT91_USART4
 	select HAVE_AT91_USART5
+	select HAVE_NET_MACB
 
 config ARCH_AT91SAM9261
 	bool "AT91SAM9261"
@@ -51,6 +52,7 @@
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
 	select HAVE_FB_ATMEL
+	select HAVE_NET_MACB
 
 config ARCH_AT91SAM9RL
 	bool "AT91SAM9RL"
@@ -66,6 +68,7 @@
 	select HAVE_AT91_USART3
 	select HAVE_AT91_USART4
 	select HAVE_AT91_USART5
+	select HAVE_NET_MACB
 
 config ARCH_AT91SAM9G45
 	bool "AT91SAM9G45"
@@ -73,6 +76,7 @@
 	select GENERIC_CLOCKEVENTS
 	select HAVE_AT91_USART3
 	select HAVE_FB_ATMEL
+	select HAVE_NET_MACB
 
 config ARCH_AT91CAP9
 	bool "AT91CAP9"
@@ -248,6 +252,12 @@
 	  Select this if you are using a Eukrea Electromatique's
 	  CPU9260 Board <http://www.eukrea.com/>
 
+config MACH_FLEXIBITY
+	bool "Flexibity Connect board"
+	help
+	  Select this if you are using Flexibity Connect board
+	  <http://www.flexibity.com>
+
 endif
 
 # ----------------------------------------------------------
@@ -338,6 +348,7 @@
 	  that embeds only one SD/MMC slot.
 
 config MACH_AT91SAM9G20EK_2MMC
+	depends on MACH_AT91SAM9G20EK
 	bool "Atmel AT91SAM9G20-EK Evaluation Kit with 2 SD/MMC Slots"
 	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
@@ -383,8 +394,8 @@
 
 comment "AT91SAM9G45 Board Type"
 
-config MACH_AT91SAM9G45EKES
-	bool "Atmel AT91SAM9G45-EKES Evaluation Kit"
+config MACH_AT91SAM9M10G45EK
+	bool "Atmel AT91SAM9M10G45-EK Evaluation Kits"
 	select HAVE_NAND_ATMEL_BUSWIDTH_16
 	help
 	  Select this if you are using Atmel's AT91SAM9G45-EKES Evaluation Kit.
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index ca2ac00..412b3a4 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -46,6 +46,7 @@
 obj-$(CONFIG_MACH_QIL_A9260)	+= board-qil-a9260.o
 obj-$(CONFIG_MACH_AFEB9260)	+= board-afeb-9260v1.o
 obj-$(CONFIG_MACH_CPU9260)	+= board-cpu9krea.o
+obj-$(CONFIG_MACH_FLEXIBITY)	+= board-flexibity.o
 
 # AT91SAM9261 board-specific support
 obj-$(CONFIG_MACH_AT91SAM9261EK) += board-sam9261ek.o
@@ -61,7 +62,6 @@
 
 # AT91SAM9G20 board-specific support
 obj-$(CONFIG_MACH_AT91SAM9G20EK) += board-sam9g20ek.o
-obj-$(CONFIG_MACH_AT91SAM9G20EK_2MMC) += board-sam9g20ek-2slot-mmc.o
 obj-$(CONFIG_MACH_CPU9G20)	+= board-cpu9krea.o
 obj-$(CONFIG_MACH_STAMP9G20)	+= board-stamp9g20.o
 obj-$(CONFIG_MACH_PORTUXG20)	+= board-stamp9g20.o
@@ -70,7 +70,7 @@
 obj-$(CONFIG_MACH_SNAPPER_9260)	+= board-snapper9260.o
 
 # AT91SAM9G45 board-specific support
-obj-$(CONFIG_MACH_AT91SAM9G45EKES) += board-sam9m10g45ek.o
+obj-$(CONFIG_MACH_AT91SAM9M10G45EK) += board-sam9m10g45ek.o
 
 # AT91CAP9 board-specific support
 obj-$(CONFIG_MACH_AT91CAP9ADK)	+= board-cap9adk.o
diff --git a/arch/arm/mach-at91/board-1arm.c b/arch/arm/mach-at91/board-1arm.c
index 9b27d16..46bdc82 100644
--- a/arch/arm/mach-at91/board-1arm.c
+++ b/arch/arm/mach-at91/board-1arm.c
@@ -92,8 +92,6 @@
 
 MACHINE_START(ONEARM, "Ajeco 1ARM single board computer")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= onearm_map_io,
diff --git a/arch/arm/mach-at91/board-afeb-9260v1.c b/arch/arm/mach-at91/board-afeb-9260v1.c
index 50667be..cba7f77 100644
--- a/arch/arm/mach-at91/board-afeb-9260v1.c
+++ b/arch/arm/mach-at91/board-afeb-9260v1.c
@@ -218,8 +218,6 @@
 
 MACHINE_START(AFEB9260, "Custom afeb9260 board")
 	/* Maintainer: Sergey Lapin <slapin@ossfans.org> */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= afeb9260_map_io,
diff --git a/arch/arm/mach-at91/board-at572d940hf_ek.c b/arch/arm/mach-at91/board-at572d940hf_ek.c
index 5daff27..3929f1c 100644
--- a/arch/arm/mach-at91/board-at572d940hf_ek.c
+++ b/arch/arm/mach-at91/board-at572d940hf_ek.c
@@ -216,7 +216,7 @@
 /*	.rdy_pin	= AT91_PIN_PC16, */
 	.enable_pin	= AT91_PIN_PA15,
 	.partition_info	= nand_partitions,
-#if defined(CONFIG_MTD_NAND_AT91_BUSWIDTH_16)
+#if defined(CONFIG_MTD_NAND_ATMEL_BUSWIDTH_16)
 	.bus_width_16	= 1,
 #else
 	.bus_width_16	= 0,
@@ -318,8 +318,6 @@
 
 MACHINE_START(AT572D940HFEB, "Atmel AT91D940HF-EB")
 	/* Maintainer: Atmel <costa.antonior@gmail.com> */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= eb_map_io,
diff --git a/arch/arm/mach-at91/board-cam60.c b/arch/arm/mach-at91/board-cam60.c
index 44eb9f7..b54e3e6 100644
--- a/arch/arm/mach-at91/board-cam60.c
+++ b/arch/arm/mach-at91/board-cam60.c
@@ -198,8 +198,6 @@
 
 MACHINE_START(CAM60, "KwikByte CAM60")
 	/* Maintainer: KwikByte */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= cam60_map_io,
diff --git a/arch/arm/mach-at91/board-cap9adk.c b/arch/arm/mach-at91/board-cap9adk.c
index d694087..e727444 100644
--- a/arch/arm/mach-at91/board-cap9adk.c
+++ b/arch/arm/mach-at91/board-cap9adk.c
@@ -399,8 +399,6 @@
 
 MACHINE_START(AT91CAP9ADK, "Atmel AT91CAP9A-DK")
 	/* Maintainer: Stelian Pop <stelian.pop@leadtechdesign.com> */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= cap9adk_map_io,
diff --git a/arch/arm/mach-at91/board-carmeva.c b/arch/arm/mach-at91/board-carmeva.c
index db1f954..2e74a19 100644
--- a/arch/arm/mach-at91/board-carmeva.c
+++ b/arch/arm/mach-at91/board-carmeva.c
@@ -162,8 +162,6 @@
 
 MACHINE_START(CARMEVA, "Carmeva")
 	/* Maintainer: Conitec Datasystems */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= carmeva_map_io,
diff --git a/arch/arm/mach-at91/board-cpu9krea.c b/arch/arm/mach-at91/board-cpu9krea.c
index 4bc2e9f..3838594 100644
--- a/arch/arm/mach-at91/board-cpu9krea.c
+++ b/arch/arm/mach-at91/board-cpu9krea.c
@@ -375,8 +375,6 @@
 MACHINE_START(CPUAT9G20, "Eukrea CPU9G20")
 #endif
 	/* Maintainer: Eric Benard - EUKREA Electromatique */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= cpu9krea_map_io,
diff --git a/arch/arm/mach-at91/board-cpuat91.c b/arch/arm/mach-at91/board-cpuat91.c
index a28d996..2f4dd8c 100644
--- a/arch/arm/mach-at91/board-cpuat91.c
+++ b/arch/arm/mach-at91/board-cpuat91.c
@@ -175,8 +175,6 @@
 
 MACHINE_START(CPUAT91, "Eukrea")
 	/* Maintainer: Eric Benard - EUKREA Electromatique */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= cpuat91_map_io,
diff --git a/arch/arm/mach-at91/board-csb337.c b/arch/arm/mach-at91/board-csb337.c
index fea2529..464839d 100644
--- a/arch/arm/mach-at91/board-csb337.c
+++ b/arch/arm/mach-at91/board-csb337.c
@@ -257,8 +257,6 @@
 
 MACHINE_START(CSB337, "Cogent CSB337")
 	/* Maintainer: Bill Gatliff */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= csb337_map_io,
diff --git a/arch/arm/mach-at91/board-csb637.c b/arch/arm/mach-at91/board-csb637.c
index cfa3f04..431688c 100644
--- a/arch/arm/mach-at91/board-csb637.c
+++ b/arch/arm/mach-at91/board-csb637.c
@@ -138,8 +138,6 @@
 
 MACHINE_START(CSB637, "Cogent CSB637")
 	/* Maintainer: Bill Gatliff */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= csb637_map_io,
diff --git a/arch/arm/mach-at91/board-dk.c b/arch/arm/mach-at91/board-dk.c
index 0fd0f5b..e14f0e1 100644
--- a/arch/arm/mach-at91/board-dk.c
+++ b/arch/arm/mach-at91/board-dk.c
@@ -225,8 +225,6 @@
 
 MACHINE_START(AT91RM9200DK, "Atmel AT91RM9200-DK")
 	/* Maintainer: SAN People/Atmel */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= dk_map_io,
diff --git a/arch/arm/mach-at91/board-eb9200.c b/arch/arm/mach-at91/board-eb9200.c
index 52865676..6cf6566 100644
--- a/arch/arm/mach-at91/board-eb9200.c
+++ b/arch/arm/mach-at91/board-eb9200.c
@@ -120,8 +120,6 @@
 }
 
 MACHINE_START(ATEB9200, "Embest ATEB9200")
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= eb9200_map_io,
diff --git a/arch/arm/mach-at91/board-ecbat91.c b/arch/arm/mach-at91/board-ecbat91.c
index 1d69908..7b58c94 100644
--- a/arch/arm/mach-at91/board-ecbat91.c
+++ b/arch/arm/mach-at91/board-ecbat91.c
@@ -168,8 +168,6 @@
 
 MACHINE_START(ECBAT91, "emQbit's ECB_AT91")
 	/* Maintainer: emQbit.com */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= ecb_at91map_io,
diff --git a/arch/arm/mach-at91/board-eco920.c b/arch/arm/mach-at91/board-eco920.c
index 295a966..a158a0c 100644
--- a/arch/arm/mach-at91/board-eco920.c
+++ b/arch/arm/mach-at91/board-eco920.c
@@ -148,8 +148,6 @@
 
 MACHINE_START(ECO920, "eco920")
 	/* Maintainer: Sascha Hauer */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= eco920_map_io,
diff --git a/arch/arm/mach-at91/board-ek.c b/arch/arm/mach-at91/board-ek.c
index 4cdfaac..56e92c4 100644
--- a/arch/arm/mach-at91/board-ek.c
+++ b/arch/arm/mach-at91/board-ek.c
@@ -191,8 +191,6 @@
 
 MACHINE_START(AT91RM9200EK, "Atmel AT91RM9200-EK")
 	/* Maintainer: SAN People/Atmel */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-flexibity.c b/arch/arm/mach-at91/board-flexibity.c
new file mode 100644
index 0000000..c8a62dc
--- /dev/null
+++ b/arch/arm/mach-at91/board-flexibity.c
@@ -0,0 +1,162 @@
+/*
+ * linux/arch/arm/mach-at91/board-flexibity.c
+ *
+ *  Copyright (C) 2010 Flexibity
+ *  Copyright (C) 2005 SAN People
+ *  Copyright (C) 2006 Atmel
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/input.h>
+#include <linux/gpio.h>
+
+#include <asm/mach-types.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/mach/irq.h>
+
+#include <mach/hardware.h>
+#include <mach/board.h>
+
+#include "generic.h"
+
+static void __init flexibity_map_io(void)
+{
+	/* Initialize processor: 18.432 MHz crystal */
+	at91sam9260_initialize(18432000);
+
+	/* DBGU on ttyS0. (Rx & Tx only) */
+	at91_register_uart(0, 0, 0);
+
+	/* set serial console to ttyS0 (ie, DBGU) */
+	at91_set_serial_console(0);
+}
+
+static void __init flexibity_init_irq(void)
+{
+	at91sam9260_init_interrupts(NULL);
+}
+
+/* USB Host port */
+static struct at91_usbh_data __initdata flexibity_usbh_data = {
+	.ports		= 2,
+};
+
+/* USB Device port */
+static struct at91_udc_data __initdata flexibity_udc_data = {
+	.vbus_pin	= AT91_PIN_PC5,
+	.pullup_pin	= 0,		/* pull-up driven by UDC */
+};
+
+/* SPI devices */
+static struct spi_board_info flexibity_spi_devices[] = {
+	{	/* DataFlash chip */
+		.modalias	= "mtd_dataflash",
+		.chip_select	= 1,
+		.max_speed_hz	= 15 * 1000 * 1000,
+		.bus_num	= 0,
+	},
+};
+
+/* MCI (SD/MMC) */
+static struct at91_mmc_data __initdata flexibity_mmc_data = {
+	.slot_b		= 0,
+	.wire4		= 1,
+	.det_pin	= AT91_PIN_PC9,
+	.wp_pin		= AT91_PIN_PC4,
+};
+
+/* LEDs */
+static struct gpio_led flexibity_leds[] = {
+	{
+		.name			= "usb1:green",
+		.gpio			= AT91_PIN_PA12,
+		.active_low		= 1,
+		.default_trigger	= "default-on",
+	},
+	{
+		.name			= "usb1:red",
+		.gpio			= AT91_PIN_PA13,
+		.active_low		= 1,
+		.default_trigger	= "default-on",
+	},
+	{
+		.name			= "usb2:green",
+		.gpio			= AT91_PIN_PB26,
+		.active_low		= 1,
+		.default_trigger	= "default-on",
+	},
+	{
+		.name			= "usb2:red",
+		.gpio			= AT91_PIN_PB27,
+		.active_low		= 1,
+		.default_trigger	= "default-on",
+	},
+	{
+		.name			= "usb3:green",
+		.gpio			= AT91_PIN_PC8,
+		.active_low		= 1,
+		.default_trigger	= "default-on",
+	},
+	{
+		.name			= "usb3:red",
+		.gpio			= AT91_PIN_PC6,
+		.active_low		= 1,
+		.default_trigger	= "default-on",
+	},
+	{
+		.name			= "usb4:green",
+		.gpio			= AT91_PIN_PB4,
+		.active_low		= 1,
+		.default_trigger	= "default-on",
+	},
+	{
+		.name			= "usb4:red",
+		.gpio			= AT91_PIN_PB5,
+		.active_low		= 1,
+		.default_trigger	= "default-on",
+	}
+};
+
+static void __init flexibity_board_init(void)
+{
+	/* Serial */
+	at91_add_device_serial();
+	/* USB Host */
+	at91_add_device_usbh(&flexibity_usbh_data);
+	/* USB Device */
+	at91_add_device_udc(&flexibity_udc_data);
+	/* SPI */
+	at91_add_device_spi(flexibity_spi_devices,
+		ARRAY_SIZE(flexibity_spi_devices));
+	/* MMC */
+	at91_add_device_mmc(0, &flexibity_mmc_data);
+	/* LEDs */
+	at91_gpio_leds(flexibity_leds, ARRAY_SIZE(flexibity_leds));
+}
+
+MACHINE_START(FLEXIBITY, "Flexibity Connect")
+	/* Maintainer: Maxim Osipov */
+	.boot_params	= AT91_SDRAM_BASE + 0x100,
+	.timer		= &at91sam926x_timer,
+	.map_io		= flexibity_map_io,
+	.init_irq	= flexibity_init_irq,
+	.init_machine	= flexibity_board_init,
+MACHINE_END
diff --git a/arch/arm/mach-at91/board-kafa.c b/arch/arm/mach-at91/board-kafa.c
index a87956c..c0ce79d 100644
--- a/arch/arm/mach-at91/board-kafa.c
+++ b/arch/arm/mach-at91/board-kafa.c
@@ -99,8 +99,6 @@
 
 MACHINE_START(KAFA, "Sperry-Sun KAFA")
 	/* Maintainer: Sergei Sharonov */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= kafa_map_io,
diff --git a/arch/arm/mach-at91/board-kb9202.c b/arch/arm/mach-at91/board-kb9202.c
index fe9b991..a13d206 100644
--- a/arch/arm/mach-at91/board-kb9202.c
+++ b/arch/arm/mach-at91/board-kb9202.c
@@ -136,8 +136,6 @@
 
 MACHINE_START(KB9200, "KB920x")
 	/* Maintainer: KwikByte, Inc. */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= kb9202_map_io,
diff --git a/arch/arm/mach-at91/board-neocore926.c b/arch/arm/mach-at91/board-neocore926.c
index 7c1e382..fe5f1d4 100644
--- a/arch/arm/mach-at91/board-neocore926.c
+++ b/arch/arm/mach-at91/board-neocore926.c
@@ -387,8 +387,6 @@
 
 MACHINE_START(NEOCORE926, "ADENEO NEOCORE 926")
 	/* Maintainer: ADENEO */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= neocore926_map_io,
diff --git a/arch/arm/mach-at91/board-picotux200.c b/arch/arm/mach-at91/board-picotux200.c
index 859727e..9d833bbc 100644
--- a/arch/arm/mach-at91/board-picotux200.c
+++ b/arch/arm/mach-at91/board-picotux200.c
@@ -156,8 +156,6 @@
 
 MACHINE_START(PICOTUX2XX, "picotux 200")
 	/* Maintainer: Kleinhenz Elektronik GmbH */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= picotux200_map_io,
diff --git a/arch/arm/mach-at91/board-qil-a9260.c b/arch/arm/mach-at91/board-qil-a9260.c
index 664938e..69d15a8 100644
--- a/arch/arm/mach-at91/board-qil-a9260.c
+++ b/arch/arm/mach-at91/board-qil-a9260.c
@@ -268,8 +268,6 @@
 
 MACHINE_START(QIL_A9260, "CALAO QIL_A9260")
 	/* Maintainer: calao-systems */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-sam9-l9260.c b/arch/arm/mach-at91/board-sam9-l9260.c
index b483469..25a26be 100644
--- a/arch/arm/mach-at91/board-sam9-l9260.c
+++ b/arch/arm/mach-at91/board-sam9-l9260.c
@@ -212,8 +212,6 @@
 
 MACHINE_START(SAM9_L9260, "Olimex SAM9-L9260")
 	/* Maintainer: Olimex */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-sam9260ek.c b/arch/arm/mach-at91/board-sam9260ek.c
index ba9d501..de1816e 100644
--- a/arch/arm/mach-at91/board-sam9260ek.c
+++ b/arch/arm/mach-at91/board-sam9260ek.c
@@ -356,8 +356,6 @@
 
 MACHINE_START(AT91SAM9260EK, "Atmel AT91SAM9260-EK")
 	/* Maintainer: Atmel */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c
index 65eb094..14acc90 100644
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@@ -623,8 +623,6 @@
 MACHINE_START(AT91SAM9G10EK, "Atmel AT91SAM9G10-EK")
 #endif
 	/* Maintainer: Atmel */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index 2d867fb..bfe490d 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -454,8 +454,6 @@
 
 MACHINE_START(AT91SAM9263EK, "Atmel AT91SAM9263-EK")
 	/* Maintainer: Atmel */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-sam9g20ek-2slot-mmc.c b/arch/arm/mach-at91/board-sam9g20ek-2slot-mmc.c
deleted file mode 100644
index c49f5c0..0000000
--- a/arch/arm/mach-at91/board-sam9g20ek-2slot-mmc.c
+++ /dev/null
@@ -1,329 +0,0 @@
-/*
- *  Copyright (C) 2005 SAN People
- *  Copyright (C) 2008 Atmel
- *  Copyright (C) 2009 Rob Emanuele
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/at73c213.h>
-#include <linux/clk.h>
-#include <linux/regulator/machine.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/consumer.h>
-
-#include <mach/hardware.h>
-#include <asm/setup.h>
-#include <asm/mach-types.h>
-#include <asm/irq.h>
-
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-#include <asm/mach/irq.h>
-
-#include <mach/board.h>
-#include <mach/gpio.h>
-#include <mach/at91sam9_smc.h>
-
-#include "sam9_smc.h"
-#include "generic.h"
-
-
-static void __init ek_map_io(void)
-{
-	/* Initialize processor: 18.432 MHz crystal */
-	at91sam9260_initialize(18432000);
-
-	/* DGBU on ttyS0. (Rx & Tx only) */
-	at91_register_uart(0, 0, 0);
-
-	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
-	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
-			   | ATMEL_UART_DTR | ATMEL_UART_DSR | ATMEL_UART_DCD
-			   | ATMEL_UART_RI);
-
-	/* USART1 on ttyS2. (Rx, Tx, RTS, CTS) */
-	at91_register_uart(AT91SAM9260_ID_US1, 2, ATMEL_UART_CTS | ATMEL_UART_RTS);
-
-	/* set serial console to ttyS0 (ie, DBGU) */
-	at91_set_serial_console(0);
-}
-
-static void __init ek_init_irq(void)
-{
-	at91sam9260_init_interrupts(NULL);
-}
-
-
-/*
- * USB Host port
- */
-static struct at91_usbh_data __initdata ek_usbh_data = {
-	.ports		= 2,
-};
-
-/*
- * USB Device port
- */
-static struct at91_udc_data __initdata ek_udc_data = {
-	.vbus_pin	= AT91_PIN_PC5,
-	.pullup_pin	= 0,		/* pull-up driven by UDC */
-};
-
-
-/*
- * SPI devices.
- */
-static struct spi_board_info ek_spi_devices[] = {
-#if !(defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_AT91))
-	{	/* DataFlash chip */
-		.modalias	= "mtd_dataflash",
-		.chip_select	= 1,
-		.max_speed_hz	= 15 * 1000 * 1000,
-		.bus_num	= 0,
-	},
-#if defined(CONFIG_MTD_AT91_DATAFLASH_CARD)
-	{	/* DataFlash card */
-		.modalias	= "mtd_dataflash",
-		.chip_select	= 0,
-		.max_speed_hz	= 15 * 1000 * 1000,
-		.bus_num	= 0,
-	},
-#endif
-#endif
-};
-
-
-/*
- * MACB Ethernet device
- */
-static struct at91_eth_data __initdata ek_macb_data = {
-	.phy_irq_pin	= AT91_PIN_PB0,
-	.is_rmii	= 1,
-};
-
-
-/*
- * NAND flash
- */
-static struct mtd_partition __initdata ek_nand_partition[] = {
-	{
-		.name   = "Bootstrap",
-		.offset = 0,
-		.size   = 4 * SZ_1M,
-	},
-	{
-		.name	= "Partition 1",
-		.offset	= MTDPART_OFS_NXTBLK,
-		.size	= 60 * SZ_1M,
-	},
-	{
-		.name	= "Partition 2",
-		.offset	= MTDPART_OFS_NXTBLK,
-		.size	= MTDPART_SIZ_FULL,
-	},
-};
-
-static struct mtd_partition * __init nand_partitions(int size, int *num_partitions)
-{
-	*num_partitions = ARRAY_SIZE(ek_nand_partition);
-	return ek_nand_partition;
-}
-
-/* det_pin is not connected */
-static struct atmel_nand_data __initdata ek_nand_data = {
-	.ale		= 21,
-	.cle		= 22,
-	.rdy_pin	= AT91_PIN_PC13,
-	.enable_pin	= AT91_PIN_PC14,
-	.partition_info	= nand_partitions,
-#if defined(CONFIG_MTD_NAND_ATMEL_BUSWIDTH_16)
-	.bus_width_16	= 1,
-#else
-	.bus_width_16	= 0,
-#endif
-};
-
-static struct sam9_smc_config __initdata ek_nand_smc_config = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 2,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 2,
-
-	.ncs_read_pulse		= 4,
-	.nrd_pulse		= 4,
-	.ncs_write_pulse	= 4,
-	.nwe_pulse		= 4,
-
-	.read_cycle		= 7,
-	.write_cycle		= 7,
-
-	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE,
-	.tdf_cycles		= 3,
-};
-
-static void __init ek_add_device_nand(void)
-{
-	/* setup bus-width (8 or 16) */
-	if (ek_nand_data.bus_width_16)
-		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
-	else
-		ek_nand_smc_config.mode |= AT91_SMC_DBW_8;
-
-	/* configure chip-select 3 (NAND) */
-	sam9_smc_configure(3, &ek_nand_smc_config);
-
-	at91_add_device_nand(&ek_nand_data);
-}
-
-
-/*
- * MCI (SD/MMC)
- * wp_pin is not connected
- */
-#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
-static struct mci_platform_data __initdata ek_mmc_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-		.detect_pin	= AT91_PIN_PC2,
-		.wp_pin		= -ENODEV,
-	},
-	.slot[1] = {
-		.bus_width	= 4,
-		.detect_pin	= AT91_PIN_PC9,
-		.wp_pin		= -ENODEV,
-	},
-
-};
-#else
-static struct at91_mmc_data __initdata ek_mmc_data = {
-	.slot_b		= 1,	/* Only one slot so use slot B */
-	.wire4		= 1,
-	.det_pin	= AT91_PIN_PC9,
-};
-#endif
-
-/*
- * LEDs
- */
-static struct gpio_led ek_leds[] = {
-	{	/* "bottom" led, green, userled1 to be defined */
-		.name			= "ds5",
-		.gpio			= AT91_PIN_PB8,
-		.active_low		= 1,
-		.default_trigger	= "none",
-	},
-	{	/* "power" led, yellow */
-		.name			= "ds1",
-		.gpio			= AT91_PIN_PB9,
-		.default_trigger	= "heartbeat",
-	}
-};
-
-#if defined(CONFIG_REGULATOR_FIXED_VOLTAGE) || defined(CONFIG_REGULATOR_FIXED_VOLTAGE_MODULE)
-static struct regulator_consumer_supply ek_audio_consumer_supplies[] = {
-	REGULATOR_SUPPLY("AVDD", "0-001b"),
-	REGULATOR_SUPPLY("HPVDD", "0-001b"),
-	REGULATOR_SUPPLY("DBVDD", "0-001b"),
-	REGULATOR_SUPPLY("DCVDD", "0-001b"),
-};
-
-static struct regulator_init_data ek_avdd_reg_init_data = {
-	.constraints	= {
-		.name	= "3V3",
-		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
-	},
-	.consumer_supplies = ek_audio_consumer_supplies,
-	.num_consumer_supplies = ARRAY_SIZE(ek_audio_consumer_supplies),
-};
-
-static struct fixed_voltage_config ek_vdd_pdata = {
-	.supply_name	= "board-3V3",
-	.microvolts	= 3300000,
-	.gpio		= -EINVAL,
-	.enabled_at_boot = 0,
-	.init_data	= &ek_avdd_reg_init_data,
-};
-static struct platform_device ek_voltage_regulator = {
-	.name		= "reg-fixed-voltage",
-	.id		= -1,
-	.num_resources	= 0,
-	.dev		= {
-		.platform_data	= &ek_vdd_pdata,
-	},
-};
-static void __init ek_add_regulators(void)
-{
-	platform_device_register(&ek_voltage_regulator);
-}
-#else
-static void __init ek_add_regulators(void) {}
-#endif
-
-static struct i2c_board_info __initdata ek_i2c_devices[] = {
-	{
-		I2C_BOARD_INFO("24c512", 0x50),
-	},
-};
-
-
-static void __init ek_board_init(void)
-{
-	/* Serial */
-	at91_add_device_serial();
-	/* USB Host */
-	at91_add_device_usbh(&ek_usbh_data);
-	/* USB Device */
-	at91_add_device_udc(&ek_udc_data);
-	/* SPI */
-	at91_add_device_spi(ek_spi_devices, ARRAY_SIZE(ek_spi_devices));
-	/* NAND */
-	ek_add_device_nand();
-	/* Ethernet */
-	at91_add_device_eth(&ek_macb_data);
-	/* Regulators */
-	ek_add_regulators();
-	/* MMC */
-#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
-	at91_add_device_mci(0, &ek_mmc_data);
-#else
-	at91_add_device_mmc(0, &ek_mmc_data);
-#endif
-	/* I2C */
-	at91_add_device_i2c(ek_i2c_devices, ARRAY_SIZE(ek_i2c_devices));
-	/* LEDs */
-	at91_gpio_leds(ek_leds, ARRAY_SIZE(ek_leds));
-	/* PCK0 provides MCLK to the WM8731 */
-	at91_set_B_periph(AT91_PIN_PC1, 0);
-	/* SSC (for WM8731) */
-	at91_add_device_ssc(AT91SAM9260_ID_SSC, ATMEL_SSC_TX);
-}
-
-MACHINE_START(AT91SAM9G20EK_2MMC, "Atmel AT91SAM9G20-EK 2 MMC Slot Mod")
-	/* Maintainer: Rob Emanuele */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
-	.boot_params	= AT91_SDRAM_BASE + 0x100,
-	.timer		= &at91sam926x_timer,
-	.map_io		= ek_map_io,
-	.init_irq	= ek_init_irq,
-	.init_machine	= ek_board_init,
-MACHINE_END
diff --git a/arch/arm/mach-at91/board-sam9g20ek.c b/arch/arm/mach-at91/board-sam9g20ek.c
index 6ea9808..ca8198b 100644
--- a/arch/arm/mach-at91/board-sam9g20ek.c
+++ b/arch/arm/mach-at91/board-sam9g20ek.c
@@ -47,6 +47,18 @@
 #include "sam9_smc.h"
 #include "generic.h"
 
+/*
+ * board revision encoding
+ * bit 0:
+ * 	0 => 1 sd/mmc slot
+ * 	1 => 2 sd/mmc slots connectors (board from revision C)
+ */
+#define HAVE_2MMC	(1 << 0)
+static int inline ek_have_2mmc(void)
+{
+	return machine_is_at91sam9g20ek_2mmc() || (system_rev & HAVE_2MMC);
+}
+
 
 static void __init ek_map_io(void)
 {
@@ -94,7 +106,7 @@
  * SPI devices.
  */
 static struct spi_board_info ek_spi_devices[] = {
-#if !defined(CONFIG_MMC_AT91)
+#if !(defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_AT91))
 	{	/* DataFlash chip */
 		.modalias	= "mtd_dataflash",
 		.chip_select	= 1,
@@ -121,6 +133,13 @@
 	.is_rmii	= 1,
 };
 
+static void __init ek_add_device_macb(void)
+{
+	if (ek_have_2mmc())
+		ek_macb_data.phy_irq_pin = AT91_PIN_PB0;
+
+	at91_add_device_eth(&ek_macb_data);
+}
 
 /*
  * NAND flash
@@ -198,13 +217,36 @@
 
 /*
  * MCI (SD/MMC)
- * det_pin, wp_pin and vcc_pin are not connected
+ * wp_pin and vcc_pin are not connected
  */
-static struct at91_mmc_data __initdata ek_mmc_data = {
-	.slot_b		= 1,
-	.wire4		= 1,
-};
+#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
+static struct mci_platform_data __initdata ek_mmc_data = {
+	.slot[1] = {
+		.bus_width	= 4,
+		.detect_pin	= AT91_PIN_PC9,
+	},
 
+};
+#else
+static struct at91_mmc_data __initdata ek_mmc_data = {
+	.slot_b		= 1,	/* Only one slot so use slot B */
+	.wire4		= 1,
+	.det_pin	= AT91_PIN_PC9,
+};
+#endif
+
+static void __init ek_add_device_mmc(void)
+{
+#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
+	if (ek_have_2mmc()) {
+		ek_mmc_data.slot[0].bus_width = 4;
+		ek_mmc_data.slot[0].detect_pin = AT91_PIN_PC2;
+	}
+	at91_add_device_mci(0, &ek_mmc_data);
+#else
+	at91_add_device_mmc(0, &ek_mmc_data);
+#endif
+}
 
 /*
  * LEDs
@@ -223,6 +265,15 @@
 	}
 };
 
+static void __init ek_add_device_gpio_leds(void)
+{
+	if (ek_have_2mmc()) {
+		ek_leds[0].gpio = AT91_PIN_PB8;
+		ek_leds[1].gpio = AT91_PIN_PB9;
+	}
+
+	at91_gpio_leds(ek_leds, ARRAY_SIZE(ek_leds));
+}
 
 /*
  * GPIO Buttons
@@ -336,15 +387,15 @@
 	/* NAND */
 	ek_add_device_nand();
 	/* Ethernet */
-	at91_add_device_eth(&ek_macb_data);
+	ek_add_device_macb();
 	/* Regulators */
 	ek_add_regulators();
 	/* MMC */
-	at91_add_device_mmc(0, &ek_mmc_data);
+	ek_add_device_mmc();
 	/* I2C */
 	at91_add_device_i2c(ek_i2c_devices, ARRAY_SIZE(ek_i2c_devices));
 	/* LEDs */
-	at91_gpio_leds(ek_leds, ARRAY_SIZE(ek_leds));
+	ek_add_device_gpio_leds();
 	/* Push Buttons */
 	ek_add_device_buttons();
 	/* PCK0 provides MCLK to the WM8731 */
@@ -355,8 +406,15 @@
 
 MACHINE_START(AT91SAM9G20EK, "Atmel AT91SAM9G20-EK")
 	/* Maintainer: Atmel */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
+	.boot_params	= AT91_SDRAM_BASE + 0x100,
+	.timer		= &at91sam926x_timer,
+	.map_io		= ek_map_io,
+	.init_irq	= ek_init_irq,
+	.init_machine	= ek_board_init,
+MACHINE_END
+
+MACHINE_START(AT91SAM9G20EK_2MMC, "Atmel AT91SAM9G20-EK 2 MMC Slot Mod")
+	/* Maintainer: Atmel */
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-sam9m10g45ek.c b/arch/arm/mach-at91/board-sam9m10g45ek.c
index ee80059..7913984 100644
--- a/arch/arm/mach-at91/board-sam9m10g45ek.c
+++ b/arch/arm/mach-at91/board-sam9m10g45ek.c
@@ -135,7 +135,7 @@
 	.rdy_pin	= AT91_PIN_PC8,
 	.enable_pin	= AT91_PIN_PC14,
 	.partition_info	= nand_partitions,
-#if defined(CONFIG_MTD_NAND_AT91_BUSWIDTH_16)
+#if defined(CONFIG_MTD_NAND_ATMEL_BUSWIDTH_16)
 	.bus_width_16	= 1,
 #else
 	.bus_width_16	= 0,
@@ -399,10 +399,8 @@
 	at91_pwm_leds(ek_pwm_led, ARRAY_SIZE(ek_pwm_led));
 }
 
-MACHINE_START(AT91SAM9G45EKES, "Atmel AT91SAM9G45-EKES")
+MACHINE_START(AT91SAM9M10G45EK, "Atmel AT91SAM9M10G45-EK")
 	/* Maintainer: Atmel */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-sam9rlek.c b/arch/arm/mach-at91/board-sam9rlek.c
index 7ac20f3..3bf3408 100644
--- a/arch/arm/mach-at91/board-sam9rlek.c
+++ b/arch/arm/mach-at91/board-sam9rlek.c
@@ -329,8 +329,6 @@
 
 MACHINE_START(AT91SAM9RLEK, "Atmel AT91SAM9RL-EK")
 	/* Maintainer: Atmel */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-snapper9260.c b/arch/arm/mach-at91/board-snapper9260.c
index 2c08ae4..0a99b3c 100644
--- a/arch/arm/mach-at91/board-snapper9260.c
+++ b/arch/arm/mach-at91/board-snapper9260.c
@@ -177,8 +177,6 @@
 }
 
 MACHINE_START(SNAPPER_9260, "Bluewater Systems Snapper 9260/9G20 module")
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= snapper9260_map_io,
diff --git a/arch/arm/mach-at91/board-stamp9g20.c b/arch/arm/mach-at91/board-stamp9g20.c
index 8795827..5206eef 100644
--- a/arch/arm/mach-at91/board-stamp9g20.c
+++ b/arch/arm/mach-at91/board-stamp9g20.c
@@ -294,8 +294,6 @@
 
 MACHINE_START(PORTUXG20, "taskit PortuxG20")
 	/* Maintainer: taskit GmbH */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= portuxg20_map_io,
@@ -305,8 +303,6 @@
 
 MACHINE_START(STAMP9G20, "taskit Stamp9G20")
 	/* Maintainer: taskit GmbH */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= stamp9g20_map_io,
diff --git a/arch/arm/mach-at91/board-usb-a9260.c b/arch/arm/mach-at91/board-usb-a9260.c
index 905d6ef..07784ba 100644
--- a/arch/arm/mach-at91/board-usb-a9260.c
+++ b/arch/arm/mach-at91/board-usb-a9260.c
@@ -228,8 +228,6 @@
 
 MACHINE_START(USB_A9260, "CALAO USB_A9260")
 	/* Maintainer: calao-systems */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-usb-a9263.c b/arch/arm/mach-at91/board-usb-a9263.c
index b6a3480..b6145089 100644
--- a/arch/arm/mach-at91/board-usb-a9263.c
+++ b/arch/arm/mach-at91/board-usb-a9263.c
@@ -244,8 +244,6 @@
 
 MACHINE_START(USB_A9263, "CALAO USB_A9263")
 	/* Maintainer: calao-systems */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
 	.map_io		= ek_map_io,
diff --git a/arch/arm/mach-at91/board-yl-9200.c b/arch/arm/mach-at91/board-yl-9200.c
index e22bf05..89df00a 100644
--- a/arch/arm/mach-at91/board-yl-9200.c
+++ b/arch/arm/mach-at91/board-yl-9200.c
@@ -594,8 +594,6 @@
 
 MACHINE_START(YL9200, "uCdragon YL-9200")
 	/* Maintainer: S.Birtles */
-	.phys_io	= AT91_BASE_SYS,
-	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91rm9200_timer,
 	.map_io		= yl9200_map_io,
diff --git a/arch/arm/mach-at91/include/mach/at91x40.h b/arch/arm/mach-at91/include/mach/at91x40.h
index d34cdb8..063ac44 100644
--- a/arch/arm/mach-at91/include/mach/at91x40.h
+++ b/arch/arm/mach-at91/include/mach/at91x40.h
@@ -52,4 +52,10 @@
 #define AT91_DBGU_CIDR	(AT91_SF + 0)	/* CIDR in PS segment */
 #define AT91_DBGU_EXID	(AT91_SF + 4)	/* EXID in PS segment */
 
+/*
+ * Support defines for the simple Power Controller module.
+ */
+#define	AT91_PS_CR	(AT91_PS + 0)	/* PS Control register */
+#define	AT91_PS_CR_CPU	(1 << 0)	/* CPU clock disable bit */
+
 #endif /* AT91X40_H */
diff --git a/arch/arm/mach-at91/include/mach/debug-macro.S b/arch/arm/mach-at91/include/mach/debug-macro.S
index 9e750a1..0f959fa 100644
--- a/arch/arm/mach-at91/include/mach/debug-macro.S
+++ b/arch/arm/mach-at91/include/mach/debug-macro.S
@@ -14,11 +14,9 @@
 #include <mach/hardware.h>
 #include <mach/at91_dbgu.h>
 
-	.macro	addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1						@ MMU enabled?
-	ldreq	\rx, =(AT91_BASE_SYS + AT91_DBGU)		@ System peripherals (phys address)
-	ldrne	\rx, =(AT91_VA_BASE_SYS	+ AT91_DBGU)		@ System peripherals (virt address)
+	.macro	addruart, rp, rv
+	ldr	\rp, =(AT91_BASE_SYS + AT91_DBGU)		@ System peripherals (phys address)
+	ldr	\rv, =(AT91_VA_BASE_SYS	+ AT91_DBGU)		@ System peripherals (virt address)
 	.endm
 
 	.macro	senduart,rd,rx
diff --git a/arch/arm/mach-at91/include/mach/system.h b/arch/arm/mach-at91/include/mach/system.h
index ee8db15..36af14b 100644
--- a/arch/arm/mach-at91/include/mach/system.h
+++ b/arch/arm/mach-at91/include/mach/system.h
@@ -32,7 +32,11 @@
 	 * Disable the processor clock.  The processor will be automatically
 	 * re-enabled by an interrupt or by a reset.
 	 */
+#ifdef AT91_PS
+	at91_sys_write(AT91_PS_CR, AT91_PS_CR_CPU);
+#else
 	at91_sys_write(AT91_PMC_SCDR, AT91_PMC_PCK);
+#endif
 #ifndef CONFIG_CPU_ARM920T
 	/*
 	 * Set the processor (CP15) into 'Wait for Interrupt' mode.
diff --git a/arch/arm/mach-bcmring/arch.c b/arch/arm/mach-bcmring/arch.c
index 2f13919..73eb066 100644
--- a/arch/arm/mach-bcmring/arch.c
+++ b/arch/arm/mach-bcmring/arch.c
@@ -167,8 +167,6 @@
 
 MACHINE_START(BCMRING, "BCMRING")
 	/* Maintainer: Broadcom Corporation */
-	.phys_io = MM_IO_START,
-	.io_pg_offst = (MM_IO_BASE >> 18) & 0xfffc,
 	.fixup = bcmring_fixup,
 	.map_io = bcmring_map_io,
 	.init_irq = bcmring_init_irq,
diff --git a/arch/arm/mach-bcmring/dma.c b/arch/arm/mach-bcmring/dma.c
index 29c0a91..77eb35c 100644
--- a/arch/arm/mach-bcmring/dma.c
+++ b/arch/arm/mach-bcmring/dma.c
@@ -691,7 +691,7 @@
 
 	memset(&gDMA, 0, sizeof(gDMA));
 
-	init_MUTEX_LOCKED(&gDMA.lock);
+	sema_init(&gDMA.lock, 0);
 	init_waitqueue_head(&gDMA.freeChannelQ);
 
 	/* Initialize the Hardware */
@@ -1574,7 +1574,7 @@
 {
 	memset(memMap, 0, sizeof(*memMap));
 
-	init_MUTEX(&memMap->lock);
+	sema_init(&memMap->lock, 1);
 
 	return 0;
 }
diff --git a/arch/arm/mach-bcmring/include/mach/vmalloc.h b/arch/arm/mach-bcmring/include/mach/vmalloc.h
index 35e2ead..3db3a09 100644
--- a/arch/arm/mach-bcmring/include/mach/vmalloc.h
+++ b/arch/arm/mach-bcmring/include/mach/vmalloc.h
@@ -22,4 +22,4 @@
  * 0xe0000000 to 0xefffffff. This gives us 256 MB of vm space and handles
  * larger physical memory designs better.
  */
-#define VMALLOC_END       (PAGE_OFFSET + 0x30000000)
+#define VMALLOC_END       0xf0000000
diff --git a/arch/arm/mach-bcmring/irq.c b/arch/arm/mach-bcmring/irq.c
index dc1c493..e315263 100644
--- a/arch/arm/mach-bcmring/irq.c
+++ b/arch/arm/mach-bcmring/irq.c
@@ -67,21 +67,21 @@
 }
 
 static struct irq_chip bcmring_irq0_chip = {
-	.typename = "ARM-INTC0",
+	.name = "ARM-INTC0",
 	.ack = bcmring_mask_irq0,
 	.mask = bcmring_mask_irq0,	/* mask a specific interrupt, blocking its delivery. */
 	.unmask = bcmring_unmask_irq0,	/* unmaks an interrupt */
 };
 
 static struct irq_chip bcmring_irq1_chip = {
-	.typename = "ARM-INTC1",
+	.name = "ARM-INTC1",
 	.ack = bcmring_mask_irq1,
 	.mask = bcmring_mask_irq1,
 	.unmask = bcmring_unmask_irq1,
 };
 
 static struct irq_chip bcmring_irq2_chip = {
-	.typename = "ARM-SINTC",
+	.name = "ARM-SINTC",
 	.ack = bcmring_mask_irq2,
 	.mask = bcmring_mask_irq2,
 	.unmask = bcmring_unmask_irq2,
diff --git a/arch/arm/mach-clps711x/autcpu12.c b/arch/arm/mach-clps711x/autcpu12.c
index 5f18ecc..4a74b2c9 100644
--- a/arch/arm/mach-clps711x/autcpu12.c
+++ b/arch/arm/mach-clps711x/autcpu12.c
@@ -64,8 +64,6 @@
 
 MACHINE_START(AUTCPU12, "autronix autcpu12")
 	/* Maintainer: Thomas Gleixner */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xff000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0020000,
 	.map_io		= autcpu12_map_io,
 	.init_irq	= clps711x_init_irq,
diff --git a/arch/arm/mach-clps711x/cdb89712.c b/arch/arm/mach-clps711x/cdb89712.c
index 71a80b5..5a1689d 100644
--- a/arch/arm/mach-clps711x/cdb89712.c
+++ b/arch/arm/mach-clps711x/cdb89712.c
@@ -55,8 +55,6 @@
 
 MACHINE_START(CDB89712, "Cirrus-CDB89712")
 	/* Maintainer: Ray Lehtiniemi */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xff000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= cdb89712_map_io,
 	.init_irq	= clps711x_init_irq,
diff --git a/arch/arm/mach-clps711x/ceiva.c b/arch/arm/mach-clps711x/ceiva.c
index 8ada201..16481cf 100644
--- a/arch/arm/mach-clps711x/ceiva.c
+++ b/arch/arm/mach-clps711x/ceiva.c
@@ -56,8 +56,6 @@
 
 MACHINE_START(CEIVA, "CEIVA/Polaroid Photo MAX Digital Picture Frame")
 	/* Maintainer: Rob Scott */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xff000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= ceiva_map_io,
 	.init_irq	= clps711x_init_irq,
diff --git a/arch/arm/mach-clps711x/clep7312.c b/arch/arm/mach-clps711x/clep7312.c
index 3c3bf45..67b5abb4 100644
--- a/arch/arm/mach-clps711x/clep7312.c
+++ b/arch/arm/mach-clps711x/clep7312.c
@@ -37,8 +37,6 @@
 
 MACHINE_START(CLEP7212, "Cirrus Logic 7212/7312")
 	/* Maintainer: Nobody */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xff000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.fixup		= fixup_clep7312,
 	.map_io		= clps711x_map_io,
diff --git a/arch/arm/mach-clps711x/edb7211-arch.c b/arch/arm/mach-clps711x/edb7211-arch.c
index 4a7a232..98ca5b2 100644
--- a/arch/arm/mach-clps711x/edb7211-arch.c
+++ b/arch/arm/mach-clps711x/edb7211-arch.c
@@ -57,8 +57,6 @@
 
 MACHINE_START(EDB7211, "CL-EDB7211 (EP7211 eval board)")
 	/* Maintainer: Jon McClintock */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xff000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0020100,	/* 0xc0000000 - 0xc001ffff can be video RAM */
 	.fixup		= fixup_edb7211,
 	.map_io		= edb7211_map_io,
diff --git a/arch/arm/mach-clps711x/fortunet.c b/arch/arm/mach-clps711x/fortunet.c
index a696099..b1cb479 100644
--- a/arch/arm/mach-clps711x/fortunet.c
+++ b/arch/arm/mach-clps711x/fortunet.c
@@ -75,8 +75,6 @@
 
 MACHINE_START(FORTUNET, "ARM-FortuNet")
 	/* Maintainer: FortuNet Inc. */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf0000000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000000,
 	.fixup		= fortunet_fixup,
 	.map_io		= clps711x_map_io,
diff --git a/arch/arm/mach-clps711x/include/mach/debug-macro.S b/arch/arm/mach-clps711x/include/mach/debug-macro.S
index 072cc6b..507c687 100644
--- a/arch/arm/mach-clps711x/include/mach/debug-macro.S
+++ b/arch/arm/mach-clps711x/include/mach/debug-macro.S
@@ -14,16 +14,14 @@
 #include <mach/hardware.h>
 #include <asm/hardware/clps7111.h>
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #CLPS7111_PHYS_BASE
-		movne	\rx, #CLPS7111_VIRT_BASE
+		.macro	addruart, rp, rv
 #ifndef CONFIG_DEBUG_CLPS711X_UART2
-		add	\rx, \rx, #0x0000	@ UART1
+		mov	\rp, #0x0000	@ UART1
 #else
-		add	\rx, \rx, #0x1000	@ UART2
+		mov	\rp, #0x1000	@ UART2
 #endif
+		orr	\rv, \rp, #CLPS7111_VIRT_BASE
+		orr	\rp, \rp, #CLPS7111_PHYS_BASE
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/mach-clps711x/include/mach/vmalloc.h b/arch/arm/mach-clps711x/include/mach/vmalloc.h
index ea6cc7b..30b3a287 100644
--- a/arch/arm/mach-clps711x/include/mach/vmalloc.h
+++ b/arch/arm/mach-clps711x/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#define VMALLOC_END       (PAGE_OFFSET + 0x10000000)
+#define VMALLOC_END       0xd0000000
diff --git a/arch/arm/mach-clps711x/p720t.c b/arch/arm/mach-clps711x/p720t.c
index 0d94a30..cefbce0 100644
--- a/arch/arm/mach-clps711x/p720t.c
+++ b/arch/arm/mach-clps711x/p720t.c
@@ -89,8 +89,6 @@
 
 MACHINE_START(P720T, "ARM-Prospector720T")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xff000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.fixup		= fixup_p720t,
 	.map_io		= p720t_map_io,
diff --git a/arch/arm/mach-cns3xxx/cns3420vb.c b/arch/arm/mach-cns3xxx/cns3420vb.c
index 9df8391..90fe9ab 100644
--- a/arch/arm/mach-cns3xxx/cns3420vb.c
+++ b/arch/arm/mach-cns3xxx/cns3420vb.c
@@ -142,8 +142,6 @@
 }
 
 MACHINE_START(CNS3420VB, "Cavium Networks CNS3420 Validation Board")
-	.phys_io	= CNS3XXX_UART0_BASE,
-	.io_pg_offst	= (CNS3XXX_UART0_BASE_VIRT >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= cns3420_map_io,
 	.init_irq	= cns3xxx_init_irq,
diff --git a/arch/arm/mach-cns3xxx/include/mach/debug-macro.S b/arch/arm/mach-cns3xxx/include/mach/debug-macro.S
index d16ce7e..56d8286 100644
--- a/arch/arm/mach-cns3xxx/include/mach/debug-macro.S
+++ b/arch/arm/mach-cns3xxx/include/mach/debug-macro.S
@@ -10,12 +10,10 @@
  * published by the Free Software Foundation.
  */
 
-		.macro	addruart,rx
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx,      #0x10000000
-		movne	\rx,      #0xf0000000	@ virtual base
-		orr	\rx, \rx, #0x00009000
+		.macro	addruart,rp,rv
+		mov	\rp, #0x00009000
+		orr	\rv, \rp, #0xf0000000	@ virtual base
+		orr	\rp, \rp, #0x10000000
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index c3994f3..7f3cdbf 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -597,8 +597,6 @@
 }
 
 MACHINE_START(DAVINCI_DA830_EVM, "DaVinci DA830/OMAP-L137 EVM")
-	.phys_io	= IO_PHYS,
-	.io_pg_offst	= (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params	= (DA8XX_DDR_BASE + 0x100),
 	.map_io		= da830_evm_map_io,
 	.init_irq	= cp_intc_init,
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index fdc2cc5..b26f5cb 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -817,8 +817,6 @@
 }
 
 MACHINE_START(DAVINCI_DA850_EVM, "DaVinci DA850/OMAP-L138 EVM")
-	.phys_io	= IO_PHYS,
-	.io_pg_offst	= (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params	= (DA8XX_DDR_BASE + 0x100),
 	.map_io		= da850_evm_map_io,
 	.init_irq	= cp_intc_init,
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index a319101..6e7cad13 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -351,8 +351,6 @@
 }
 
 MACHINE_START(DAVINCI_DM355_EVM, "DaVinci DM355 EVM")
-	.phys_io      = IO_PHYS,
-	.io_pg_offst  = (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params  = (0x80000100),
 	.map_io	      = dm355_evm_map_io,
 	.init_irq     = davinci_irq_init,
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index f1d8132..543f991 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -270,8 +270,6 @@
 }
 
 MACHINE_START(DM355_LEOPARD, "DaVinci DM355 leopard")
-	.phys_io      = IO_PHYS,
-	.io_pg_offst  = (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params  = (0x80000100),
 	.map_io	      = dm355_leopard_map_io,
 	.init_irq     = davinci_irq_init,
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index 84acef1..944a0cb 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -613,8 +613,6 @@
 }
 
 MACHINE_START(DAVINCI_DM365_EVM, "DaVinci DM365 EVM")
-	.phys_io	= IO_PHYS,
-	.io_pg_offst	= (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params	= (0x80000100),
 	.map_io		= dm365_evm_map_io,
 	.init_irq	= davinci_irq_init,
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 34c8b41..d59fba1 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -706,8 +706,6 @@
 
 MACHINE_START(DAVINCI_EVM, "DaVinci DM644x EVM")
 	/* Maintainer: MontaVista Software <source@mvista.com> */
-	.phys_io      = IO_PHYS,
-	.io_pg_offst  = (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params  = (DAVINCI_DDR_BASE + 0x100),
 	.map_io	      = davinci_evm_map_io,
 	.init_irq     = davinci_irq_init,
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index 4502f34..6890488 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -786,8 +786,6 @@
 }
 
 MACHINE_START(DAVINCI_DM6467_EVM, "DaVinci DM646x EVM")
-	.phys_io      = IO_PHYS,
-	.io_pg_offst  = (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params  = (0x80000100),
 	.map_io       = davinci_map_io,
 	.init_irq     = davinci_irq_init,
@@ -796,8 +794,6 @@
 MACHINE_END
 
 MACHINE_START(DAVINCI_DM6467TEVM, "DaVinci DM6467T EVM")
-	.phys_io      = IO_PHYS,
-	.io_pg_offst  = (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params  = (0x80000100),
 	.map_io       = davinci_map_io,
 	.init_irq     = davinci_irq_init,
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 4c30e92..a4def88 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -275,8 +275,6 @@
 
 MACHINE_START(NEUROS_OSD2, "Neuros OSD2")
 	/* Maintainer: Neuros Technologies <neuros@groups.google.com> */
-	.phys_io	= IO_PHYS,
-	.io_pg_offst	= (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params	= (DAVINCI_DDR_BASE + 0x100),
 	.map_io		 = davinci_ntosd2_map_io,
 	.init_irq	= davinci_irq_init,
diff --git a/arch/arm/mach-davinci/board-sffsdr.c b/arch/arm/mach-davinci/board-sffsdr.c
index 23e664a..9bdf8aa 100644
--- a/arch/arm/mach-davinci/board-sffsdr.c
+++ b/arch/arm/mach-davinci/board-sffsdr.c
@@ -154,8 +154,6 @@
 
 MACHINE_START(SFFSDR, "Lyrtech SFFSDR")
 	/* Maintainer: Hugo Villeneuve hugo.villeneuve@lyrtech.com */
-	.phys_io      = IO_PHYS,
-	.io_pg_offst  = (__IO_ADDRESS(IO_PHYS) >> 18) & 0xfffc,
 	.boot_params  = (DAVINCI_DDR_BASE + 0x100),
 	.map_io	      = davinci_sffsdr_map_io,
 	.init_irq     = davinci_irq_init,
diff --git a/arch/arm/mach-davinci/board-tnetv107x-evm.c b/arch/arm/mach-davinci/board-tnetv107x-evm.c
index fe2a9d9..b4de35b 100644
--- a/arch/arm/mach-davinci/board-tnetv107x-evm.c
+++ b/arch/arm/mach-davinci/board-tnetv107x-evm.c
@@ -164,8 +164,6 @@
 #endif
 
 MACHINE_START(TNETV107X, "TNETV107X EVM")
-	.phys_io	= TNETV107X_IO_BASE,
-	.io_pg_offst	= (TNETV107X_IO_VIRT >> 18) & 0xfffc,
 	.boot_params	= (TNETV107X_DDR_BASE + 0x100),
 	.map_io		= tnetv107x_init,
 	.init_irq	= cp_intc_init,
diff --git a/arch/arm/mach-davinci/include/mach/debug-macro.S b/arch/arm/mach-davinci/include/mach/debug-macro.S
index f761dfd..9f1befc 100644
--- a/arch/arm/mach-davinci/include/mach/debug-macro.S
+++ b/arch/arm/mach-davinci/include/mach/debug-macro.S
@@ -29,35 +29,39 @@
 davinci_uart_virt:	.word	0
 		.popsection
 
-		.macro addruart, rx, tmp
+		.macro addruart, rp, rv
 
 		/* Use davinci_uart_phys/virt if already configured */
-10:		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		ldreq	\rx, =__virt_to_phys(davinci_uart_phys)
-		ldrne	\rx, =davinci_uart_virt
-		ldr	\rx, [\rx]
-		cmp	\rx, #0			@ is port configured?
+10:		mrc	p15, 0, \rp, c1, c0
+		tst	\rp, #1			@ MMU enabled?
+		ldreq	\rp, =__virt_to_phys(davinci_uart_phys)
+		ldrne	\rp, =davinci_uart_phys
+		add	\rv, \rp, #4		@ davinci_uart_virt
+		ldr	\rp, [\rp, #0]
+		ldr	\rv, [\rv, #0]
+		cmp	\rp, #0			@ is port configured?
+		cmpne	\rv, #0
 		bne	99f			@ already configured
 
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
+		/* Check the debug UART address set in uncompress.h */
+		mrc	p15, 0, \rp, c1, c0
+		tst	\rp, #1			@ MMU enabled?
 
 		/* Copy uart phys address from decompressor uart info */
-		ldreq	\tmp, =__virt_to_phys(davinci_uart_phys)
-		ldrne	\tmp, =davinci_uart_phys
-		ldreq	\rx, =DAVINCI_UART_INFO
-		ldrne	\rx, =__phys_to_virt(DAVINCI_UART_INFO)
-		ldr	\rx, [\rx, #0]
-		str	\rx, [\tmp]
+		ldreq	\rv, =__virt_to_phys(davinci_uart_phys)
+		ldrne	\rv, =davinci_uart_phys
+		ldreq	\rp, =DAVINCI_UART_INFO
+		ldrne	\rp, =__phys_to_virt(DAVINCI_UART_INFO)
+		ldr	\rp, [\rp, #0]
+		str	\rp, [\rv]
 
 		/* Copy uart virt address from decompressor uart info */
-		ldreq	\tmp, =__virt_to_phys(davinci_uart_virt)
-		ldrne	\tmp, =davinci_uart_virt
-		ldreq	\rx, =DAVINCI_UART_INFO
-		ldrne	\rx, =__phys_to_virt(DAVINCI_UART_INFO)
-		ldr	\rx, [\rx, #4]
-		str	\rx, [\tmp]
+		ldreq	\rv, =__virt_to_phys(davinci_uart_virt)
+		ldrne	\rv, =davinci_uart_virt
+		ldreq	\rp, =DAVINCI_UART_INFO
+		ldrne	\rp, =__phys_to_virt(DAVINCI_UART_INFO)
+		ldr	\rp, [\rp, #4]
+		str	\rp, [\rv]
 
 		b	10b
 99:
diff --git a/arch/arm/mach-dove/dove-db-setup.c b/arch/arm/mach-dove/dove-db-setup.c
index bef7046..95925aa 100644
--- a/arch/arm/mach-dove/dove-db-setup.c
+++ b/arch/arm/mach-dove/dove-db-setup.c
@@ -94,8 +94,6 @@
 }
 
 MACHINE_START(DOVE_DB, "Marvell DB-MV88AP510-BP Development Board")
-	.phys_io	= DOVE_SB_REGS_PHYS_BASE,
-	.io_pg_offst	= ((DOVE_SB_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= dove_db_init,
 	.map_io		= dove_map_io,
diff --git a/arch/arm/mach-dove/include/mach/debug-macro.S b/arch/arm/mach-dove/include/mach/debug-macro.S
index 1521d13..da8bf2b 100644
--- a/arch/arm/mach-dove/include/mach/debug-macro.S
+++ b/arch/arm/mach-dove/include/mach/debug-macro.S
@@ -8,12 +8,11 @@
 
 #include <mach/bridge-regs.h>
 
-	.macro	addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1					@ MMU enabled?
-	ldreq	\rx, =DOVE_SB_REGS_PHYS_BASE
-	ldrne	\rx, =DOVE_SB_REGS_VIRT_BASE
-	orr	\rx, \rx, #0x00012000
+	.macro	addruart, rp, rv
+	ldr	\rp, =DOVE_SB_REGS_PHYS_BASE
+	ldr	\rv, =DOVE_SB_REGS_VIRT_BASE
+	orr	\rp, \rp, #0x00012000
+	orr	\rv, \rv, #0x00012000
 	.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index c7bc7fb..5df4099 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -280,8 +280,6 @@
 
 MACHINE_START(EBSA110, "EBSA110")
 	/* Maintainer: Russell King */
-	.phys_io	= 0xe0000000,
-	.io_pg_offst	= ((0xe0000000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000400,
 	.reserve_lp0	= 1,
 	.reserve_lp2	= 1,
diff --git a/arch/arm/mach-ebsa110/include/mach/debug-macro.S b/arch/arm/mach-ebsa110/include/mach/debug-macro.S
index ebbd89f..7ef5690 100644
--- a/arch/arm/mach-ebsa110/include/mach/debug-macro.S
+++ b/arch/arm/mach-ebsa110/include/mach/debug-macro.S
@@ -11,9 +11,10 @@
  *
 **/
 
-		.macro	addruart, rx, tmp
-		mov	\rx, #0xf0000000
-		orr	\rx, \rx, #0x00000be0
+		.macro	addruart, rp, rv
+		mov	\rp, #0xf0000000
+		orr	\rp, \rp, #0x00000be0
+		mov	\rp, \rv
 		.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-ebsa110/include/mach/vmalloc.h b/arch/arm/mach-ebsa110/include/mach/vmalloc.h
index 9b44c19..60bde56 100644
--- a/arch/arm/mach-ebsa110/include/mach/vmalloc.h
+++ b/arch/arm/mach-ebsa110/include/mach/vmalloc.h
@@ -7,4 +7,4 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#define VMALLOC_END       (PAGE_OFFSET + 0x1f000000)
+#define VMALLOC_END       0xdf000000
diff --git a/arch/arm/mach-ep93xx/adssphere.c b/arch/arm/mach-ep93xx/adssphere.c
index f744f67..61b98ce 100644
--- a/arch/arm/mach-ep93xx/adssphere.c
+++ b/arch/arm/mach-ep93xx/adssphere.c
@@ -33,8 +33,6 @@
 
 MACHINE_START(ADSSPHERE, "ADS Sphere board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c
index c2ce903..4b04316 100644
--- a/arch/arm/mach-ep93xx/edb93xx.c
+++ b/arch/arm/mach-ep93xx/edb93xx.c
@@ -124,8 +124,6 @@
 #ifdef CONFIG_MACH_EDB9301
 MACHINE_START(EDB9301, "Cirrus Logic EDB9301 Evaluation Board")
 	/* Maintainer: H Hartley Sweeten <hsweeten@visionengravers.com> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -137,8 +135,6 @@
 #ifdef CONFIG_MACH_EDB9302
 MACHINE_START(EDB9302, "Cirrus Logic EDB9302 Evaluation Board")
 	/* Maintainer: George Kashperko <george@chas.com.ua> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -150,8 +146,6 @@
 #ifdef CONFIG_MACH_EDB9302A
 MACHINE_START(EDB9302A, "Cirrus Logic EDB9302A Evaluation Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -163,8 +157,6 @@
 #ifdef CONFIG_MACH_EDB9307
 MACHINE_START(EDB9307, "Cirrus Logic EDB9307 Evaluation Board")
 	/* Maintainer: Herbert Valerio Riedel <hvr@gnu.org> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -176,8 +168,6 @@
 #ifdef CONFIG_MACH_EDB9307A
 MACHINE_START(EDB9307A, "Cirrus Logic EDB9307A Evaluation Board")
 	/* Maintainer: H Hartley Sweeten <hsweeten@visionengravers.com> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -189,8 +179,6 @@
 #ifdef CONFIG_MACH_EDB9312
 MACHINE_START(EDB9312, "Cirrus Logic EDB9312 Evaluation Board")
 	/* Maintainer: Toufeeq Hussain <toufeeq_hussain@infosys.com> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -202,8 +190,6 @@
 #ifdef CONFIG_MACH_EDB9315
 MACHINE_START(EDB9315, "Cirrus Logic EDB9315 Evaluation Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -215,8 +201,6 @@
 #ifdef CONFIG_MACH_EDB9315A
 MACHINE_START(EDB9315A, "Cirrus Logic EDB9315A Evaluation Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
diff --git a/arch/arm/mach-ep93xx/gesbc9312.c b/arch/arm/mach-ep93xx/gesbc9312.c
index d97168c..9bd3152 100644
--- a/arch/arm/mach-ep93xx/gesbc9312.c
+++ b/arch/arm/mach-ep93xx/gesbc9312.c
@@ -33,8 +33,6 @@
 
 MACHINE_START(GESBC9312, "Glomation GESBC-9312-sx")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
diff --git a/arch/arm/mach-ep93xx/include/mach/debug-macro.S b/arch/arm/mach-ep93xx/include/mach/debug-macro.S
index 5cd2244..b25bc907 100644
--- a/arch/arm/mach-ep93xx/include/mach/debug-macro.S
+++ b/arch/arm/mach-ep93xx/include/mach/debug-macro.S
@@ -11,12 +11,11 @@
  */
 #include <mach/ep93xx-regs.h>
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1				@ MMU enabled?
-		ldreq	\rx, =EP93XX_APB_PHYS_BASE	@ Physical base
-		ldrne	\rx, =EP93XX_APB_VIRT_BASE	@ virtual base
-		orr	\rx, \rx, #0x000c0000
+		.macro	addruart, rp, rv
+		ldr	\rp, =EP93XX_APB_PHYS_BASE	@ Physical base
+		ldr	\rv, =EP93XX_APB_VIRT_BASE	@ virtual base
+		orr	\rp, \rp, #0x000c0000
+		orr	\rv, \rv, #0x000c0000
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-ep93xx/micro9.c b/arch/arm/mach-ep93xx/micro9.c
index 2ba7763..7adea62 100644
--- a/arch/arm/mach-ep93xx/micro9.c
+++ b/arch/arm/mach-ep93xx/micro9.c
@@ -77,8 +77,6 @@
 #ifdef CONFIG_MACH_MICRO9H
 MACHINE_START(MICRO9, "Contec Micro9-High")
 	/* Maintainer: Hubert Feurstein <hubert.feurstein@contec.at> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -90,8 +88,6 @@
 #ifdef CONFIG_MACH_MICRO9M
 MACHINE_START(MICRO9M, "Contec Micro9-Mid")
 	/* Maintainer: Hubert Feurstein <hubert.feurstein@contec.at> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_ASYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -103,8 +99,6 @@
 #ifdef CONFIG_MACH_MICRO9L
 MACHINE_START(MICRO9L, "Contec Micro9-Lite")
 	/* Maintainer: Hubert Feurstein <hubert.feurstein@contec.at> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
@@ -116,8 +110,6 @@
 #ifdef CONFIG_MACH_MICRO9S
 MACHINE_START(MICRO9S, "Contec Micro9-Slim")
 	/* Maintainer: Hubert Feurstein <hubert.feurstein@contec.at> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_ASYNC + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
diff --git a/arch/arm/mach-ep93xx/simone.c b/arch/arm/mach-ep93xx/simone.c
index 5dded58..f22ce8d 100644
--- a/arch/arm/mach-ep93xx/simone.c
+++ b/arch/arm/mach-ep93xx/simone.c
@@ -65,8 +65,6 @@
 
 MACHINE_START(SIM_ONE, "Simplemachines Sim.One Board")
 /* Maintainer: Ryan Mallon <ryan@bluewatersys.com> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
diff --git a/arch/arm/mach-ep93xx/snappercl15.c b/arch/arm/mach-ep93xx/snappercl15.c
index a12c893..ac601fe 100644
--- a/arch/arm/mach-ep93xx/snappercl15.c
+++ b/arch/arm/mach-ep93xx/snappercl15.c
@@ -163,8 +163,6 @@
 
 MACHINE_START(SNAPPER_CL15, "Bluewater Systems Snapper CL15")
 	/* Maintainer: Ryan Mallon <ryan@bluewatersys.com> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
 	.map_io		= ep93xx_map_io,
 	.init_irq	= ep93xx_init_irq,
diff --git a/arch/arm/mach-ep93xx/ts72xx.c b/arch/arm/mach-ep93xx/ts72xx.c
index 93aeab8..c2d2cf4 100644
--- a/arch/arm/mach-ep93xx/ts72xx.c
+++ b/arch/arm/mach-ep93xx/ts72xx.c
@@ -257,8 +257,6 @@
 
 MACHINE_START(TS72XX, "Technologic Systems TS-72xx SBC")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= EP93XX_APB_PHYS_BASE,
-	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= EP93XX_SDCE3_PHYS_BASE_SYNC + 0x100,
 	.map_io		= ts72xx_map_io,
 	.init_irq	= ep93xx_init_irq,
diff --git a/arch/arm/mach-footbridge/cats-hw.c b/arch/arm/mach-footbridge/cats-hw.c
index 1b996b2..5b1a8db 100644
--- a/arch/arm/mach-footbridge/cats-hw.c
+++ b/arch/arm/mach-footbridge/cats-hw.c
@@ -86,8 +86,6 @@
 
 MACHINE_START(CATS, "Chalice-CATS")
 	/* Maintainer: Philip Blundell */
-	.phys_io	= DC21285_ARMCSR_BASE,
-	.io_pg_offst	= ((0xfe000000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.soft_reboot	= 1,
 	.fixup		= fixup_cats,
diff --git a/arch/arm/mach-footbridge/ebsa285.c b/arch/arm/mach-footbridge/ebsa285.c
index 30040fd..2ef69ff 100644
--- a/arch/arm/mach-footbridge/ebsa285.c
+++ b/arch/arm/mach-footbridge/ebsa285.c
@@ -15,8 +15,6 @@
 
 MACHINE_START(EBSA285, "EBSA285")
 	/* Maintainer: Russell King */
-	.phys_io	= DC21285_ARMCSR_BASE,
-	.io_pg_offst	= ((0xfe000000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.video_start	= 0x000a0000,
 	.video_end	= 0x000bffff,
diff --git a/arch/arm/mach-footbridge/include/mach/debug-macro.S b/arch/arm/mach-footbridge/include/mach/debug-macro.S
index 60dda13..3c9e0c4 100644
--- a/arch/arm/mach-footbridge/include/mach/debug-macro.S
+++ b/arch/arm/mach-footbridge/include/mach/debug-macro.S
@@ -15,12 +15,10 @@
 
 #ifndef CONFIG_DEBUG_DC21285_PORT
 	/* For NetWinder debugging */
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x7c000000	@ physical
-		movne	\rx, #0xff000000	@ virtual
-		orr	\rx, \rx, #0x000003f8
+		.macro	addruart, rp, rv
+		mov	\rp, #0x000003f8
+		orr	\rv, \rp, #0x7c000000	@ physical
+		orr	\rp, \rp, #0xff000000	@ virtual
 		.endm
 
 #define UART_SHIFT	0
@@ -32,14 +30,14 @@
 		.equ	dc21285_high, ARMCSR_BASE & 0xff000000
 		.equ	dc21285_low,  ARMCSR_BASE & 0x00ffffff
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x42000000
-		movne	\rx, #dc21285_high
+		.macro	addruart, rp, rv
 		.if	dc21285_low
-		orrne	\rx, \rx, #dc21285_low
+		mov	\rp, #dc21285_low
+		.else
+		mov	\rp, #0
 		.endif
+		orr	\rv, \rp, #0x42000000
+		orr	\rp, \rp, #dc21285_high
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/mach-footbridge/include/mach/vmalloc.h b/arch/arm/mach-footbridge/include/mach/vmalloc.h
index d0958d8..0ffbb7c 100644
--- a/arch/arm/mach-footbridge/include/mach/vmalloc.h
+++ b/arch/arm/mach-footbridge/include/mach/vmalloc.h
@@ -7,4 +7,4 @@
  */
 
 
-#define VMALLOC_END       (PAGE_OFFSET + 0x30000000)
+#define VMALLOC_END       0xf0000000
diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c
index ac7ffa6..06e514f 100644
--- a/arch/arm/mach-footbridge/netwinder-hw.c
+++ b/arch/arm/mach-footbridge/netwinder-hw.c
@@ -648,8 +648,6 @@
 
 MACHINE_START(NETWINDER, "Rebel-NetWinder")
 	/* Maintainer: Russell King/Rebel.com */
-	.phys_io	= DC21285_ARMCSR_BASE,
-	.io_pg_offst	= ((0xfe000000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.video_start	= 0x000a0000,
 	.video_end	= 0x000bffff,
diff --git a/arch/arm/mach-footbridge/personal.c b/arch/arm/mach-footbridge/personal.c
index e2c9f06..3285e91 100644
--- a/arch/arm/mach-footbridge/personal.c
+++ b/arch/arm/mach-footbridge/personal.c
@@ -15,8 +15,6 @@
 
 MACHINE_START(PERSONAL_SERVER, "Compaq-PersonalServer")
 	/* Maintainer: Jamey Hicks / George France */
-	.phys_io	= DC21285_ARMCSR_BASE,
-	.io_pg_offst	= ((0xfe000000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= footbridge_map_io,
 	.init_irq	= footbridge_init_irq,
diff --git a/arch/arm/mach-gemini/board-nas4220b.c b/arch/arm/mach-gemini/board-nas4220b.c
index 01f1d6d..2ba096d 100644
--- a/arch/arm/mach-gemini/board-nas4220b.c
+++ b/arch/arm/mach-gemini/board-nas4220b.c
@@ -101,8 +101,6 @@
 }
 
 MACHINE_START(NAS4220B, "Raidsonic NAS IB-4220-B")
-	.phys_io	= 0x7fffc000,
-	.io_pg_offst	= ((0xffffc000) >> 18) & 0xfffc,
 	.boot_params	= 0x100,
 	.map_io		= gemini_map_io,
 	.init_irq	= gemini_init_irq,
diff --git a/arch/arm/mach-gemini/board-rut1xx.c b/arch/arm/mach-gemini/board-rut1xx.c
index e0de968..a9a0d8b 100644
--- a/arch/arm/mach-gemini/board-rut1xx.c
+++ b/arch/arm/mach-gemini/board-rut1xx.c
@@ -85,8 +85,6 @@
 }
 
 MACHINE_START(RUT100, "Teltonika RUT100")
-	.phys_io	= 0x7fffc000,
-	.io_pg_offst	= ((0xffffc000) >> 18) & 0xfffc,
 	.boot_params	= 0x100,
 	.map_io		= gemini_map_io,
 	.init_irq	= gemini_init_irq,
diff --git a/arch/arm/mach-gemini/board-wbd111.c b/arch/arm/mach-gemini/board-wbd111.c
index 36538c1..8b88d50 100644
--- a/arch/arm/mach-gemini/board-wbd111.c
+++ b/arch/arm/mach-gemini/board-wbd111.c
@@ -133,8 +133,6 @@
 }
 
 MACHINE_START(WBD111, "Wiliboard WBD-111")
-	.phys_io	= 0x7fffc000,
-	.io_pg_offst	= ((0xffffc000) >> 18) & 0xfffc,
 	.boot_params	= 0x100,
 	.map_io		= gemini_map_io,
 	.init_irq	= gemini_init_irq,
diff --git a/arch/arm/mach-gemini/board-wbd222.c b/arch/arm/mach-gemini/board-wbd222.c
index ece8b4c..1eebcec 100644
--- a/arch/arm/mach-gemini/board-wbd222.c
+++ b/arch/arm/mach-gemini/board-wbd222.c
@@ -133,8 +133,6 @@
 }
 
 MACHINE_START(WBD222, "Wiliboard WBD-222")
-	.phys_io	= 0x7fffc000,
-	.io_pg_offst	= ((0xffffc000) >> 18) & 0xfffc,
 	.boot_params	= 0x100,
 	.map_io		= gemini_map_io,
 	.init_irq	= gemini_init_irq,
diff --git a/arch/arm/mach-gemini/include/mach/debug-macro.S b/arch/arm/mach-gemini/include/mach/debug-macro.S
index ad47704..f40e006 100644
--- a/arch/arm/mach-gemini/include/mach/debug-macro.S
+++ b/arch/arm/mach-gemini/include/mach/debug-macro.S
@@ -11,11 +11,9 @@
  */
 #include <mach/hardware.h>
 
-	.macro	addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1					@ MMU enabled?
-	ldreq	\rx, =GEMINI_UART_BASE			@ physical
-	ldrne	\rx, =IO_ADDRESS(GEMINI_UART_BASE)	@ virtual
+	.macro	addruart, rp, rv
+	ldr	\rp, =GEMINI_UART_BASE			@ physical
+	ldr	\rv, =IO_ADDRESS(GEMINI_UART_BASE)	@ virtual
 	.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-h720x/h7201-eval.c b/arch/arm/mach-h720x/h7201-eval.c
index 78be457..79f0b89 100644
--- a/arch/arm/mach-h720x/h7201-eval.c
+++ b/arch/arm/mach-h720x/h7201-eval.c
@@ -30,8 +30,6 @@
 
 MACHINE_START(H7201, "Hynix GMS30C7201")
 	/* Maintainer: Robert Schwebel, Pengutronix */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf0000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0001000,
 	.map_io		= h720x_map_io,
 	.init_irq	= h720x_init_irq,
diff --git a/arch/arm/mach-h720x/h7202-eval.c b/arch/arm/mach-h720x/h7202-eval.c
index 8c0ba99..cc28b1e 100644
--- a/arch/arm/mach-h720x/h7202-eval.c
+++ b/arch/arm/mach-h720x/h7202-eval.c
@@ -72,8 +72,6 @@
 
 MACHINE_START(H7202, "Hynix HMS30C7202")
 	/* Maintainer: Robert Schwebel, Pengutronix */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf0000000) >> 18) & 0xfffc,
 	.boot_params	= 0x40000100,
 	.map_io		= h720x_map_io,
 	.init_irq	= h7202_init_irq,
diff --git a/arch/arm/mach-h720x/include/mach/debug-macro.S b/arch/arm/mach-h720x/include/mach/debug-macro.S
index 27cafd1..c2093e8 100644
--- a/arch/arm/mach-h720x/include/mach/debug-macro.S
+++ b/arch/arm/mach-h720x/include/mach/debug-macro.S
@@ -16,12 +16,10 @@
 		.equ    io_virt, IO_VIRT
 		.equ    io_phys, IO_PHYS
 
-		.macro  addruart, rx, tmp
-		mrc     p15, 0, \rx, c1, c0
-		tst     \rx, #1  	       @ MMU enabled?
-		moveq   \rx, #io_phys	       @ physical base address
-		movne   \rx, #io_virt	       @ virtual address
-		add     \rx, \rx, #0x00020000   @ UART1
+		.macro  addruart, rp, rv
+		mov     \rp, #0x00020000	@ UART1
+		add     \rv, \rp, #io_virt	@ virtual address
+		add     \rp, \rp, #io_phys	@ physical base address
 		.endm
 
 		.macro  senduart,rd,rx
diff --git a/arch/arm/mach-h720x/include/mach/vmalloc.h b/arch/arm/mach-h720x/include/mach/vmalloc.h
index ff1460d..a45915b 100644
--- a/arch/arm/mach-h720x/include/mach/vmalloc.h
+++ b/arch/arm/mach-h720x/include/mach/vmalloc.h
@@ -5,6 +5,6 @@
 #ifndef __ARCH_ARM_VMALLOC_H
 #define __ARCH_ARM_VMALLOC_H
 
-#define VMALLOC_END       (PAGE_OFFSET + 0x10000000)
+#define VMALLOC_END       0xd0000000
 
 #endif
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 2f7e272..197f9e2 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -147,8 +147,8 @@
 	default MACH_EUKREA_MBIMX27_BASEBOARD
 
 config MACH_EUKREA_MBIMX27_BASEBOARD
-	prompt "Eukrea MBIMX27 development board"
-	bool
+	bool "Eukrea MBIMX27 development board"
+	select IMX_HAVE_PLATFORM_IMX_SSI
 	select IMX_HAVE_PLATFORM_IMX_UART
 	select IMX_HAVE_PLATFORM_SPI_IMX
 	help
@@ -164,6 +164,15 @@
 	  Include support for MX27PDK platform. This includes specific
 	  configurations for the board and its peripherals.
 
+config MACH_IMX27_VISSTRIM_M10
+	bool "Vista Silicon i.MX27 Visstrim_m10"
+	select IMX_HAVE_PLATFORM_IMX_I2C
+	select IMX_HAVE_PLATFORM_IMX_UART
+	help
+	  Include support for Visstrim_m10 platform and its different variants.
+	  This includes specific configurations for the board and its
+	  peripherals.
+
 config MACH_IMX27LITE
 	bool "LogicPD MX27 LITEKIT platform"
 	select IMX_HAVE_PLATFORM_IMX_UART
@@ -174,6 +183,7 @@
 config MACH_PCA100
 	bool "Phytec phyCARD-s (pca100)"
 	select IMX_HAVE_PLATFORM_IMX_I2C
+	select IMX_HAVE_PLATFORM_IMX_SSI
 	select IMX_HAVE_PLATFORM_IMX_UART
 	select IMX_HAVE_PLATFORM_MXC_NAND
 	select IMX_HAVE_PLATFORM_SPI_IMX
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 46a9fdf..5582692 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -27,6 +27,7 @@
 obj-$(CONFIG_MACH_PCM970_BASEBOARD) += pcm970-baseboard.o
 obj-$(CONFIG_MACH_MX27_3DS) += mach-mx27_3ds.o
 obj-$(CONFIG_MACH_IMX27LITE) += mach-imx27lite.o
+obj-$(CONFIG_MACH_IMX27_VISSTRIM_M10) += mach-imx27_visstrim_m10.o
 obj-$(CONFIG_MACH_CPUIMX27) += mach-cpuimx27.o
 obj-$(CONFIG_MACH_EUKREA_MBIMX27_BASEBOARD) += eukrea_mbimx27-baseboard.o
 obj-$(CONFIG_MACH_PCA100) += mach-pca100.o
diff --git a/arch/arm/mach-imx/clock-imx1.c b/arch/arm/mach-imx/clock-imx1.c
index c05096c..daca30b 100644
--- a/arch/arm/mach-imx/clock-imx1.c
+++ b/arch/arm/mach-imx/clock-imx1.c
@@ -592,7 +592,7 @@
 	_REGISTER_CLOCK("imx-uart.1", NULL, uart_clk)
 	_REGISTER_CLOCK("imx-uart.2", NULL, uart_clk)
 	_REGISTER_CLOCK("imx-i2c.0", NULL, i2c_clk)
-	_REGISTER_CLOCK("spi_imx.0", NULL, spi_clk)
+	_REGISTER_CLOCK("imx1-cspi.0", NULL, spi_clk)
 	_REGISTER_CLOCK("imx-mmc.0", NULL, sdhc_clk)
 	_REGISTER_CLOCK("imx-fb.0", NULL, lcdc_clk)
 	_REGISTER_CLOCK(NULL, "mshc", mshc_clk)
diff --git a/arch/arm/mach-imx/clock-imx21.c b/arch/arm/mach-imx/clock-imx21.c
index bb419ef..cf15ea5 100644
--- a/arch/arm/mach-imx/clock-imx21.c
+++ b/arch/arm/mach-imx/clock-imx21.c
@@ -1172,9 +1172,9 @@
 	_REGISTER_CLOCK(NULL, "pwm", pwm_clk[0])
 	_REGISTER_CLOCK(NULL, "sdhc1", sdhc_clk[0])
 	_REGISTER_CLOCK(NULL, "sdhc2", sdhc_clk[1])
-	_REGISTER_CLOCK(NULL, "cspi1", cspi_clk[0])
-	_REGISTER_CLOCK(NULL, "cspi2", cspi_clk[1])
-	_REGISTER_CLOCK(NULL, "cspi3", cspi_clk[2])
+	_REGISTER_CLOCK("imx21-cspi.0", NULL, cspi_clk[0])
+	_REGISTER_CLOCK("imx21-cspi.1", NULL, cspi_clk[1])
+	_REGISTER_CLOCK("imx21-cspi.2", NULL, cspi_clk[2])
 	_REGISTER_CLOCK("imx-fb.0", NULL, lcdc_clk[0])
 	_REGISTER_CLOCK(NULL, "csi", csi_clk[0])
 	_REGISTER_CLOCK("imx21-hcd.0", NULL, usb_clk[0])
diff --git a/arch/arm/mach-imx/clock-imx27.c b/arch/arm/mach-imx/clock-imx27.c
index 5a1aa15..98a25ba 100644
--- a/arch/arm/mach-imx/clock-imx27.c
+++ b/arch/arm/mach-imx/clock-imx27.c
@@ -594,27 +594,27 @@
 DEFINE_CLOCK(uart1_clk1,   0, PCCR1, 31, NULL, NULL, &ipg_clk);
 
 /* Clocks we cannot directly gate, but drivers need their rates */
-DEFINE_CLOCK(cspi1_clk,    0, 0,      0, NULL, &cspi1_clk1, &per2_clk);
-DEFINE_CLOCK(cspi2_clk,    1, 0,      0, NULL, &cspi2_clk1, &per2_clk);
-DEFINE_CLOCK(cspi3_clk,    2, 0,      0, NULL, &cspi13_clk1, &per2_clk);
-DEFINE_CLOCK(sdhc1_clk,    0, 0,      0, NULL, &sdhc1_clk1, &per2_clk);
-DEFINE_CLOCK(sdhc2_clk,    1, 0,      0, NULL, &sdhc2_clk1, &per2_clk);
-DEFINE_CLOCK(sdhc3_clk,    2, 0,      0, NULL, &sdhc3_clk1, &per2_clk);
-DEFINE_CLOCK(pwm_clk,      0, 0,      0, NULL, &pwm_clk1, &per1_clk);
-DEFINE_CLOCK(gpt1_clk,     0, 0,      0, NULL, &gpt1_clk1, &per1_clk);
-DEFINE_CLOCK(gpt2_clk,     1, 0,      0, NULL, &gpt2_clk1, &per1_clk);
-DEFINE_CLOCK(gpt3_clk,     2, 0,      0, NULL, &gpt3_clk1, &per1_clk);
-DEFINE_CLOCK(gpt4_clk,     3, 0,      0, NULL, &gpt4_clk1, &per1_clk);
-DEFINE_CLOCK(gpt5_clk,     4, 0,      0, NULL, &gpt5_clk1, &per1_clk);
-DEFINE_CLOCK(gpt6_clk,     5, 0,      0, NULL, &gpt6_clk1, &per1_clk);
-DEFINE_CLOCK(uart1_clk,    0, 0,      0, NULL, &uart1_clk1, &per1_clk);
-DEFINE_CLOCK(uart2_clk,    1, 0,      0, NULL, &uart2_clk1, &per1_clk);
-DEFINE_CLOCK(uart3_clk,    2, 0,      0, NULL, &uart3_clk1, &per1_clk);
-DEFINE_CLOCK(uart4_clk,    3, 0,      0, NULL, &uart4_clk1, &per1_clk);
-DEFINE_CLOCK(uart5_clk,    4, 0,      0, NULL, &uart5_clk1, &per1_clk);
-DEFINE_CLOCK(uart6_clk,    5, 0,      0, NULL, &uart6_clk1, &per1_clk);
-DEFINE_CLOCK1(lcdc_clk,    0, 0,      0, parent, &lcdc_clk1, &per3_clk);
-DEFINE_CLOCK1(csi_clk,     0, 0,      0, parent, &csi_clk1, &per4_clk);
+DEFINE_CLOCK(cspi1_clk,    0, NULL,   0, NULL, &cspi1_clk1, &per2_clk);
+DEFINE_CLOCK(cspi2_clk,    1, NULL,   0, NULL, &cspi2_clk1, &per2_clk);
+DEFINE_CLOCK(cspi3_clk,    2, NULL,   0, NULL, &cspi13_clk1, &per2_clk);
+DEFINE_CLOCK(sdhc1_clk,    0, NULL,   0, NULL, &sdhc1_clk1, &per2_clk);
+DEFINE_CLOCK(sdhc2_clk,    1, NULL,   0, NULL, &sdhc2_clk1, &per2_clk);
+DEFINE_CLOCK(sdhc3_clk,    2, NULL,   0, NULL, &sdhc3_clk1, &per2_clk);
+DEFINE_CLOCK(pwm_clk,      0, NULL,   0, NULL, &pwm_clk1, &per1_clk);
+DEFINE_CLOCK(gpt1_clk,     0, NULL,   0, NULL, &gpt1_clk1, &per1_clk);
+DEFINE_CLOCK(gpt2_clk,     1, NULL,   0, NULL, &gpt2_clk1, &per1_clk);
+DEFINE_CLOCK(gpt3_clk,     2, NULL,   0, NULL, &gpt3_clk1, &per1_clk);
+DEFINE_CLOCK(gpt4_clk,     3, NULL,   0, NULL, &gpt4_clk1, &per1_clk);
+DEFINE_CLOCK(gpt5_clk,     4, NULL,   0, NULL, &gpt5_clk1, &per1_clk);
+DEFINE_CLOCK(gpt6_clk,     5, NULL,   0, NULL, &gpt6_clk1, &per1_clk);
+DEFINE_CLOCK(uart1_clk,    0, NULL,   0, NULL, &uart1_clk1, &per1_clk);
+DEFINE_CLOCK(uart2_clk,    1, NULL,   0, NULL, &uart2_clk1, &per1_clk);
+DEFINE_CLOCK(uart3_clk,    2, NULL,   0, NULL, &uart3_clk1, &per1_clk);
+DEFINE_CLOCK(uart4_clk,    3, NULL,   0, NULL, &uart4_clk1, &per1_clk);
+DEFINE_CLOCK(uart5_clk,    4, NULL,   0, NULL, &uart5_clk1, &per1_clk);
+DEFINE_CLOCK(uart6_clk,    5, NULL,   0, NULL, &uart6_clk1, &per1_clk);
+DEFINE_CLOCK1(lcdc_clk,    0, NULL,   0, parent, &lcdc_clk1, &per3_clk);
+DEFINE_CLOCK1(csi_clk,     0, NULL,   0, parent, &csi_clk1, &per4_clk);
 
 #define _REGISTER_CLOCK(d, n, c) \
 	{ \
@@ -640,9 +640,9 @@
 	_REGISTER_CLOCK("mxc-mmc.0", NULL, sdhc1_clk)
 	_REGISTER_CLOCK("mxc-mmc.1", NULL, sdhc2_clk)
 	_REGISTER_CLOCK("mxc-mmc.2", NULL, sdhc3_clk)
-	_REGISTER_CLOCK("spi_imx.0", NULL, cspi1_clk)
-	_REGISTER_CLOCK("spi_imx.1", NULL, cspi2_clk)
-	_REGISTER_CLOCK("spi_imx.2", NULL, cspi3_clk)
+	_REGISTER_CLOCK("imx27-cspi.0", NULL, cspi1_clk)
+	_REGISTER_CLOCK("imx27-cspi.1", NULL, cspi2_clk)
+	_REGISTER_CLOCK("imx27-cspi.2", NULL, cspi3_clk)
 	_REGISTER_CLOCK("imx-fb.0", NULL, lcdc_clk)
 	_REGISTER_CLOCK("mx2-camera.0", NULL, csi_clk)
 	_REGISTER_CLOCK("fsl-usb2-udc", "usb", usb_clk)
diff --git a/arch/arm/mach-imx/devices-imx1.h b/arch/arm/mach-imx/devices-imx1.h
index a8d94f0..8197948 100644
--- a/arch/arm/mach-imx/devices-imx1.h
+++ b/arch/arm/mach-imx/devices-imx1.h
@@ -9,10 +9,12 @@
 #include <mach/mx1.h>
 #include <mach/devices-common.h>
 
-#define imx1_add_i2c_imx(pdata)		\
-	imx_add_imx_i2c(0, MX1_I2C_BASE_ADDR, SZ_4K, MX1_INT_I2C, pdata)
+extern const struct imx_imx_i2c_data imx1_imx_i2c_data __initconst;
+#define imx1_add_imx_i2c(pdata)		\
+	imx_add_imx_i2c(&imx1_imx_i2c_data, pdata)
 
-#define imx1_add_imx_uart0(pdata)	\
-	imx_add_imx_uart_3irq(0, MX1_UART1_BASE_ADDR, 0xd0, MX1_INT_UART1RX, MX1_INT_UART1TX, MX1_INT_UART1RTS, pdata)
-#define imx1_add_imx_uart1(pdata)	\
-	imx_add_imx_uart_3irq(0, MX1_UART2_BASE_ADDR, 0xd0, MX1_INT_UART2RX, MX1_INT_UART2TX, MX1_INT_UART2RTS, pdata)
+extern const struct imx_imx_uart_3irq_data imx1_imx_uart_data[] __initconst;
+#define imx1_add_imx_uart(id, pdata)	\
+	imx_add_imx_uart_3irq(&imx1_imx_uart_data[id], pdata)
+#define imx1_add_imx_uart0(pdata)	imx1_add_imx_uart(0, pdata)
+#define imx1_add_imx_uart1(pdata)	imx1_add_imx_uart(1, pdata)
diff --git a/arch/arm/mach-imx/devices-imx21.h b/arch/arm/mach-imx/devices-imx21.h
index 42788e9..d189039 100644
--- a/arch/arm/mach-imx/devices-imx21.h
+++ b/arch/arm/mach-imx/devices-imx21.h
@@ -9,22 +9,28 @@
 #include <mach/mx21.h>
 #include <mach/devices-common.h>
 
-#define imx21_add_i2c_imx(pdata)	\
-	imx_add_imx_i2c(0, MX2x_I2C_BASE_ADDR, SZ_4K, MX2x_INT_I2C, pdata)
+extern const struct imx_imx_i2c_data imx21_imx_i2c_data __initconst;
+#define imx21_add_imx_i2c(pdata)	\
+	imx_add_imx_i2c(&imx21_imx_i2c_data, pdata)
 
-#define imx21_add_imx_uart0(pdata)	\
-	imx_add_imx_uart_1irq(0, MX21_UART1_BASE_ADDR, SZ_4K, MX21_INT_UART1, pdata)
-#define imx21_add_imx_uart1(pdata)	\
-	imx_add_imx_uart_1irq(1, MX21_UART2_BASE_ADDR, SZ_4K, MX21_INT_UART2, pdata)
-#define imx21_add_imx_uart2(pdata)	\
-	imx_add_imx_uart_1irq(2, MX21_UART3_BASE_ADDR, SZ_4K, MX21_INT_UART3, pdata)
-#define imx21_add_imx_uart3(pdata)	\
-	imx_add_imx_uart_1irq(3, MX21_UART4_BASE_ADDR, SZ_4K, MX21_INT_UART4, pdata)
+extern const struct imx_imx_ssi_data imx21_imx_ssi_data[] __initconst;
+#define imx21_add_imx_ssi(id, pdata)	\
+	imx_add_imx_ssi(&imx21_imx_ssi_data[id], pdata)
 
+extern const struct imx_imx_uart_1irq_data imx21_imx_uart_data[] __initconst;
+#define imx21_add_imx_uart(id, pdata)	\
+	imx_add_imx_uart_1irq(&imx21_imx_uart_data[id], pdata)
+#define imx21_add_imx_uart0(pdata)	imx21_add_imx_uart(0, pdata)
+#define imx21_add_imx_uart1(pdata)	imx21_add_imx_uart(1, pdata)
+#define imx21_add_imx_uart2(pdata)	imx21_add_imx_uart(2, pdata)
+#define imx21_add_imx_uart3(pdata)	imx21_add_imx_uart(3, pdata)
+
+extern const struct imx_mxc_nand_data imx21_mxc_nand_data __initconst;
 #define imx21_add_mxc_nand(pdata)	\
-	imx_add_mxc_nand_v1(MX21_NFC_BASE_ADDR, MX21_INT_NANDFC, pdata)
+	imx_add_mxc_nand(&imx21_mxc_nand_data, pdata)
 
-#define imx21_add_spi_imx0(pdata)	\
-	imx_add_spi_imx(0, MX21_CSPI1_BASE_ADDR, SZ_4K, MX21_INT_CSPI1, pdata)
-#define imx21_add_spi_imx1(pdata)	\
-	imx_add_spi_imx(1, MX21_CSPI2_BASE_ADDR, SZ_4K, MX21_INT_CSPI2, pdata)
+extern const struct imx_spi_imx_data imx21_cspi_data[] __initconst;
+#define imx21_add_cspi(id, pdata)	\
+	imx_add_spi_imx(&imx21_cspi_data[id], pdata)
+#define imx21_add_spi_imx0(pdata)	imx21_add_cspi(0, pdata)
+#define imx21_add_spi_imx1(pdata)	imx21_add_cspi(1, pdata)
diff --git a/arch/arm/mach-imx/devices-imx27.h b/arch/arm/mach-imx/devices-imx27.h
index 65e7bb7..7011690 100644
--- a/arch/arm/mach-imx/devices-imx27.h
+++ b/arch/arm/mach-imx/devices-imx27.h
@@ -9,30 +9,35 @@
 #include <mach/mx27.h>
 #include <mach/devices-common.h>
 
-#define imx27_add_i2c_imx0(pdata)	\
-	imx_add_imx_i2c(0, MX27_I2C1_BASE_ADDR, SZ_4K, MX27_INT_I2C1, pdata)
-#define imx27_add_i2c_imx1(pdata)	\
-	imx_add_imx_i2c(1, MX27_I2C2_BASE_ADDR, SZ_4K, MX27_INT_I2C2, pdata)
+extern const struct imx_fec_data imx27_fec_data __initconst;
+#define imx27_add_fec(pdata)	\
+	imx_add_fec(&imx27_fec_data, pdata)
 
-#define imx27_add_imx_uart0(pdata)	\
-	imx_add_imx_uart_1irq(0, MX27_UART1_BASE_ADDR, SZ_4K, MX27_INT_UART1, pdata)
-#define imx27_add_imx_uart1(pdata)	\
-	imx_add_imx_uart_1irq(1, MX27_UART2_BASE_ADDR, SZ_4K, MX27_INT_UART2, pdata)
-#define imx27_add_imx_uart2(pdata)	\
-	imx_add_imx_uart_1irq(2, MX27_UART3_BASE_ADDR, SZ_4K, MX27_INT_UART3, pdata)
-#define imx27_add_imx_uart3(pdata)	\
-	imx_add_imx_uart_1irq(3, MX27_UART4_BASE_ADDR, SZ_4K, MX27_INT_UART4, pdata)
-#define imx27_add_imx_uart4(pdata)	\
-	imx_add_imx_uart_1irq(4, MX27_UART5_BASE_ADDR, SZ_4K, MX27_INT_UART5, pdata)
-#define imx27_add_imx_uart5(pdata)	\
-	imx_add_imx_uart_1irq(5, MX27_UART6_BASE_ADDR, SZ_4K, MX27_INT_UART6, pdata)
+extern const struct imx_imx_i2c_data imx27_imx_i2c_data[] __initconst;
+#define imx27_add_imx_i2c(id, pdata)	\
+	imx_add_imx_i2c(&imx27_imx_i2c_data[id], pdata)
 
+extern const struct imx_imx_ssi_data imx27_imx_ssi_data[] __initconst;
+#define imx27_add_imx_ssi(id, pdata)    \
+	imx_add_imx_ssi(&imx27_imx_ssi_data[id], pdata)
+
+extern const struct imx_imx_uart_1irq_data imx27_imx_uart_data[] __initconst;
+#define imx27_add_imx_uart(id, pdata)	\
+	imx_add_imx_uart_1irq(&imx27_imx_uart_data[id], pdata)
+#define imx27_add_imx_uart0(pdata)	imx27_add_imx_uart(0, pdata)
+#define imx27_add_imx_uart1(pdata)	imx27_add_imx_uart(1, pdata)
+#define imx27_add_imx_uart2(pdata)	imx27_add_imx_uart(2, pdata)
+#define imx27_add_imx_uart3(pdata)	imx27_add_imx_uart(3, pdata)
+#define imx27_add_imx_uart4(pdata)	imx27_add_imx_uart(4, pdata)
+#define imx27_add_imx_uart5(pdata)	imx27_add_imx_uart(5, pdata)
+
+extern const struct imx_mxc_nand_data imx27_mxc_nand_data __initconst;
 #define imx27_add_mxc_nand(pdata)	\
-	imx_add_mxc_nand_v1(MX27_NFC_BASE_ADDR, MX27_INT_NANDFC, pdata)
+	imx_add_mxc_nand(&imx27_mxc_nand_data, pdata)
 
-#define imx27_add_spi_imx0(pdata)	\
-	imx_add_spi_imx(0, MX27_CSPI1_BASE_ADDR, SZ_4K, MX27_INT_CSPI1, pdata)
-#define imx27_add_spi_imx1(pdata)	\
-	imx_add_spi_imx(1, MX27_CSPI2_BASE_ADDR, SZ_4K, MX27_INT_CSPI2, pdata)
-#define imx27_add_spi_imx2(pdata)	\
-	imx_add_spi_imx(2, MX27_CSPI3_BASE_ADDR, SZ_4K, MX27_INT_CSPI3, pdata)
+extern const struct imx_spi_imx_data imx27_cspi_data[] __initconst;
+#define imx27_add_cspi(id, pdata)	\
+	imx_add_spi_imx(&imx27_cspi_data[id], pdata)
+#define imx27_add_spi_imx0(pdata)	imx27_add_cspi(0, pdata)
+#define imx27_add_spi_imx1(pdata)	imx27_add_cspi(1, pdata)
+#define imx27_add_spi_imx2(pdata)	imx27_add_cspi(2, pdata)
diff --git a/arch/arm/mach-imx/devices.c b/arch/arm/mach-imx/devices.c
index 9c271a7..fba5047 100644
--- a/arch/arm/mach-imx/devices.c
+++ b/arch/arm/mach-imx/devices.c
@@ -314,27 +314,6 @@
 	},
 };
 
-#ifdef CONFIG_MACH_MX27
-static struct resource mxc_fec_resources[] = {
-	{
-		.start = MX27_FEC_BASE_ADDR,
-		.end = MX27_FEC_BASE_ADDR + SZ_4K - 1,
-		.flags = IORESOURCE_MEM,
-	}, {
-		.start = MX27_INT_FEC,
-		.end = MX27_INT_FEC,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mxc_fec_device = {
-	.name = "fec",
-	.id = 0,
-	.num_resources = ARRAY_SIZE(mxc_fec_resources),
-	.resource = mxc_fec_resources,
-};
-#endif
-
 static struct resource mxc_pwm_resources[] = {
 	{
 		.start = MX2x_PWM_BASE_ADDR,
@@ -480,41 +459,6 @@
 };
 #endif
 
-#define DEFINE_IMX_SSI_DMARES(_name, ssin, suffix)			\
-	{								\
-		.name = _name,						\
-		.start = MX2x_DMA_REQ_SSI ## ssin ## _ ## suffix,	\
-		.end = MX2x_DMA_REQ_SSI ## ssin ## _ ## suffix,		\
-		.flags = IORESOURCE_DMA,				\
-	}
-
-#define DEFINE_IMX_SSI_DEVICE(n, ssin, baseaddr, irq)			\
-	static struct resource imx_ssi_resources ## n[] = {		\
-		{							\
-			.start = MX2x_SSI ## ssin ## _BASE_ADDR,	\
-			.end = MX2x_SSI ## ssin ## _BASE_ADDR + 0x6f,	\
-			.flags = IORESOURCE_MEM,			\
-		}, {							\
-			.start = MX2x_INT_SSI1,				\
-			.end = MX2x_INT_SSI1,				\
-			.flags = IORESOURCE_IRQ,			\
-		},							\
-		DEFINE_IMX_SSI_DMARES("tx0", ssin, TX0),		\
-		DEFINE_IMX_SSI_DMARES("rx0", ssin, RX0),		\
-		DEFINE_IMX_SSI_DMARES("tx1", ssin, TX1),		\
-		DEFINE_IMX_SSI_DMARES("rx1", ssin, RX1),		\
-	};								\
-									\
-	struct platform_device imx_ssi_device ## n = {			\
-		.name = "imx-ssi",					\
-		.id = n,						\
-		.num_resources = ARRAY_SIZE(imx_ssi_resources ## n),	\
-		.resource = imx_ssi_resources ## n,			\
-	}
-
-DEFINE_IMX_SSI_DEVICE(0, 1, MX2x_SSI1_BASE_ADDR, MX2x_INT_SSI1);
-DEFINE_IMX_SSI_DEVICE(1, 2, MX2x_SSI1_BASE_ADDR, MX2x_INT_SSI1);
-
 /* GPIO port description */
 #define DEFINE_MXC_GPIO_PORT_IRQ(SOC, n, _irq)				\
 	{								\
diff --git a/arch/arm/mach-imx/devices.h b/arch/arm/mach-imx/devices.h
index efd4527..807f02a 100644
--- a/arch/arm/mach-imx/devices.h
+++ b/arch/arm/mach-imx/devices.h
@@ -16,7 +16,6 @@
 extern struct platform_device mxc_wdt;
 extern struct platform_device mxc_w1_master_device;
 extern struct platform_device mxc_fb_device;
-extern struct platform_device mxc_fec_device;
 extern struct platform_device mxc_pwm_device;
 extern struct platform_device mxc_sdhc_device0;
 extern struct platform_device mxc_sdhc_device1;
@@ -26,7 +25,5 @@
 extern struct platform_device mxc_usbh1;
 extern struct platform_device mxc_usbh2;
 extern struct platform_device mx21_usbhc_device;
-extern struct platform_device imx_ssi_device0;
-extern struct platform_device imx_ssi_device1;
 extern struct platform_device imx_kpp_device;
 #endif
diff --git a/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c b/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c
index 4edc5f4..026263c 100644
--- a/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c
+++ b/arch/arm/mach-imx/eukrea_mbimx27-baseboard.c
@@ -36,13 +36,12 @@
 #include <mach/hardware.h>
 #include <mach/mmc.h>
 #include <mach/spi.h>
-#include <mach/ssi.h>
 #include <mach/audmux.h>
 
 #include "devices-imx27.h"
 #include "devices.h"
 
-static int eukrea_mbimx27_pins[] = {
+static const int eukrea_mbimx27_pins[] __initconst = {
 	/* UART2 */
 	PE3_PF_UART2_CTS,
 	PE4_PF_UART2_RTS,
@@ -311,7 +310,8 @@
 	.dat3_card_detect = 1,
 };
 
-struct imx_ssi_platform_data eukrea_mbimx27_ssi_pdata = {
+static const
+struct imx_ssi_platform_data eukrea_mbimx27_ssi_pdata __initconst = {
 	.flags = IMX_SSI_DMA | IMX_SSI_USE_I2S_SLAVE,
 };
 
@@ -357,7 +357,7 @@
 	i2c_register_board_info(0, eukrea_mbimx27_i2c_devices,
 				ARRAY_SIZE(eukrea_mbimx27_i2c_devices));
 
-	mxc_register_device(&imx_ssi_device0, &eukrea_mbimx27_ssi_pdata);
+	imx27_add_imx_ssi(0, &eukrea_mbimx27_ssi_pdata);
 
 #if defined(CONFIG_TOUCHSCREEN_ADS7846) \
 	|| defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE)
diff --git a/arch/arm/mach-imx/mach-cpuimx27.c b/arch/arm/mach-imx/mach-cpuimx27.c
index 6830afd..745ee60 100644
--- a/arch/arm/mach-imx/mach-cpuimx27.c
+++ b/arch/arm/mach-imx/mach-cpuimx27.c
@@ -46,7 +46,7 @@
 #include "devices-imx27.h"
 #include "devices.h"
 
-static int eukrea_cpuimx27_pins[] = {
+static const int eukrea_cpuimx27_pins[] __initconst = {
 	/* UART1 */
 	PE12_PF_UART1_TXD,
 	PE13_PF_UART1_RXD,
@@ -157,7 +157,6 @@
 
 static struct platform_device *platform_devices[] __initdata = {
 	&eukrea_cpuimx27_nor_mtd_device,
-	&mxc_fec_device,
 	&mxc_wdt,
 	&mxc_w1_master_device,
 };
@@ -259,8 +258,9 @@
 	i2c_register_board_info(0, eukrea_cpuimx27_i2c_devices,
 				ARRAY_SIZE(eukrea_cpuimx27_i2c_devices));
 
-	imx27_add_i2c_imx0(&cpuimx27_i2c1_data);
+	imx27_add_imx_i2c(0, &cpuimx27_i2c1_data);
 
+	imx27_add_fec(NULL);
 	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
 
 #if defined(CONFIG_MACH_EUKREA_CPUIMX27_USESDHC2)
@@ -307,8 +307,6 @@
 };
 
 MACHINE_START(CPUIMX27, "EUKREA CPUIMX27")
-	.phys_io        = MX27_AIPI_BASE_ADDR,
-	.io_pg_offst    = ((MX27_AIPI_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX27_PHYS_OFFSET + 0x100,
 	.map_io         = mx27_map_io,
 	.init_irq       = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
new file mode 100644
index 0000000..59716fa
--- /dev/null
+++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
@@ -0,0 +1,261 @@
+/*
+ * mach-imx27_visstrim_m10.c
+ *
+ * Copyright 2010  Javier Martin <javier.martin@vista-silicon.com>
+ *
+ * Based on mach-pcm038.c, mach-pca100.c, mach-mx27ads.c and others.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/platform_device.h>
+#include <linux/mtd/physmap.h>
+#include <linux/i2c.h>
+#include <linux/i2c/pca953x.h>
+#include <linux/gpio_keys.h>
+#include <linux/input.h>
+#include <linux/gpio.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/time.h>
+#include <mach/common.h>
+#include <mach/mmc.h>
+#include <mach/iomux.h>
+#include <mach/mxc_ehci.h>
+
+#include "devices-imx27.h"
+#include "devices.h"
+
+#define OTG_PHY_CS_GPIO (GPIO_PORTF + 17)
+#define SDHC1_IRQ IRQ_GPIOB(25)
+
+static const int visstrim_m10_pins[] __initconst = {
+	/* UART1 (console) */
+	PE12_PF_UART1_TXD,
+	PE13_PF_UART1_RXD,
+	PE14_PF_UART1_CTS,
+	PE15_PF_UART1_RTS,
+	/* FEC */
+	PD0_AIN_FEC_TXD0,
+	PD1_AIN_FEC_TXD1,
+	PD2_AIN_FEC_TXD2,
+	PD3_AIN_FEC_TXD3,
+	PD4_AOUT_FEC_RX_ER,
+	PD5_AOUT_FEC_RXD1,
+	PD6_AOUT_FEC_RXD2,
+	PD7_AOUT_FEC_RXD3,
+	PD8_AF_FEC_MDIO,
+	PD9_AIN_FEC_MDC,
+	PD10_AOUT_FEC_CRS,
+	PD11_AOUT_FEC_TX_CLK,
+	PD12_AOUT_FEC_RXD0,
+	PD13_AOUT_FEC_RX_DV,
+	PD14_AOUT_FEC_RX_CLK,
+	PD15_AOUT_FEC_COL,
+	PD16_AIN_FEC_TX_ER,
+	PF23_AIN_FEC_TX_EN,
+	/* SDHC1 */
+	PE18_PF_SD1_D0,
+	PE19_PF_SD1_D1,
+	PE20_PF_SD1_D2,
+	PE21_PF_SD1_D3,
+	PE22_PF_SD1_CMD,
+	PE23_PF_SD1_CLK,
+	/* Both I2Cs */
+	PD17_PF_I2C_DATA,
+	PD18_PF_I2C_CLK,
+	PC5_PF_I2C2_SDA,
+	PC6_PF_I2C2_SCL,
+	/* USB OTG */
+	OTG_PHY_CS_GPIO | GPIO_GPIO | GPIO_OUT,
+	PC9_PF_USBOTG_DATA0,
+	PC11_PF_USBOTG_DATA1,
+	PC10_PF_USBOTG_DATA2,
+	PC13_PF_USBOTG_DATA3,
+	PC12_PF_USBOTG_DATA4,
+	PC7_PF_USBOTG_DATA5,
+	PC8_PF_USBOTG_DATA6,
+	PE25_PF_USBOTG_DATA7,
+	PE24_PF_USBOTG_CLK,
+	PE2_PF_USBOTG_DIR,
+	PE0_PF_USBOTG_NXT,
+	PE1_PF_USBOTG_STP,
+	PB23_PF_USB_PWR,
+	PB24_PF_USB_OC,
+};
+
+/* GPIOs used as events for applications */
+static struct gpio_keys_button visstrim_gpio_keys[] = {
+	{
+		.type	= EV_KEY,
+		.code	= KEY_RESTART,
+		.gpio	= (GPIO_PORTC + 15),
+		.desc	= "Default config",
+		.active_low = 0,
+		.wakeup = 1,
+	},
+	{
+		.type	= EV_KEY,
+		.code	= KEY_RECORD,
+		.gpio	= (GPIO_PORTF + 14),
+		.desc	= "Record",
+		.active_low = 0,
+		.wakeup = 1,
+	},
+	{
+		.type   = EV_KEY,
+		.code   = KEY_STOP,
+		.gpio   = (GPIO_PORTF + 13),
+		.desc   = "Stop",
+		.active_low = 0,
+		.wakeup = 1,
+	}
+};
+
+static struct gpio_keys_platform_data visstrim_gpio_keys_platform_data = {
+	.buttons	= visstrim_gpio_keys,
+	.nbuttons	= ARRAY_SIZE(visstrim_gpio_keys),
+};
+
+static struct platform_device visstrim_gpio_keys_device = {
+	.name	= "gpio-keys",
+	.id	= -1,
+	.dev	= {
+		.platform_data	= &visstrim_gpio_keys_platform_data,
+	},
+};
+
+/* Visstrim_SM10 has a microSD slot connected to sdhc1 */
+static int visstrim_m10_sdhc1_init(struct device *dev,
+		irq_handler_t detect_irq, void *data)
+{
+	int ret;
+
+	ret = request_irq(SDHC1_IRQ, detect_irq, IRQF_TRIGGER_FALLING,
+				"mmc-detect", data);
+	return ret;
+}
+
+static void visstrim_m10_sdhc1_exit(struct device *dev, void *data)
+{
+	free_irq(SDHC1_IRQ, data);
+}
+
+static struct imxmmc_platform_data visstrim_m10_sdhc_pdata = {
+	.init = visstrim_m10_sdhc1_init,
+	.exit = visstrim_m10_sdhc1_exit,
+};
+
+/* Visstrim_SM10 NOR flash */
+static struct physmap_flash_data visstrim_m10_flash_data = {
+	.width = 2,
+};
+
+static struct resource visstrim_m10_flash_resource = {
+	.start = 0xc0000000,
+	.end = 0xc0000000 + SZ_64M - 1,
+	.flags = IORESOURCE_MEM,
+};
+
+static struct platform_device visstrim_m10_nor_mtd_device = {
+	.name = "physmap-flash",
+	.id = 0,
+	.dev = {
+		.platform_data = &visstrim_m10_flash_data,
+	},
+	.num_resources = 1,
+	.resource = &visstrim_m10_flash_resource,
+};
+
+static struct platform_device *platform_devices[] __initdata = {
+	&visstrim_gpio_keys_device,
+	&visstrim_m10_nor_mtd_device,
+};
+
+/* Visstrim_M10 uses UART0 as console */
+static const struct imxuart_platform_data uart_pdata __initconst = {
+	.flags = IMXUART_HAVE_RTSCTS,
+};
+
+/* I2C */
+static const struct imxi2c_platform_data visstrim_m10_i2c_data __initconst = {
+	.bitrate = 100000,
+};
+
+static struct pca953x_platform_data visstrim_m10_pca9555_pdata = {
+	.gpio_base = 240, /* After MX27 internal GPIOs */
+	.invert = 0,
+};
+
+static struct i2c_board_info visstrim_m10_i2c_devices[] = {
+	{
+		I2C_BOARD_INFO("pca9555", 0x20),
+		.platform_data = &visstrim_m10_pca9555_pdata,
+	},
+};
+
+/* USB OTG */
+static int otg_phy_init(struct platform_device *pdev)
+{
+	gpio_set_value(OTG_PHY_CS_GPIO, 0);
+	return 0;
+}
+
+static struct mxc_usbh_platform_data visstrim_m10_usbotg_pdata = {
+	.init = otg_phy_init,
+	.portsc	= MXC_EHCI_MODE_ULPI | MXC_EHCI_UTMI_8BIT,
+	.flags	= MXC_EHCI_POWER_PINS_ENABLED,
+};
+
+static void __init visstrim_m10_board_init(void)
+{
+	int ret;
+
+	ret = mxc_gpio_setup_multiple_pins(visstrim_m10_pins,
+			ARRAY_SIZE(visstrim_m10_pins), "VISSTRIM_M10");
+	if (ret)
+		pr_err("Failed to setup pins (%d)\n", ret);
+
+	imx27_add_imx_uart0(&uart_pdata);
+
+	i2c_register_board_info(0, visstrim_m10_i2c_devices,
+				ARRAY_SIZE(visstrim_m10_i2c_devices));
+	imx27_add_imx_i2c(0, &visstrim_m10_i2c_data);
+	imx27_add_imx_i2c(1, &visstrim_m10_i2c_data);
+	mxc_register_device(&mxc_sdhc_device0, &visstrim_m10_sdhc_pdata);
+	mxc_register_device(&mxc_otg_host, &visstrim_m10_usbotg_pdata);
+	imx27_add_fec(NULL);
+	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
+}
+
+static void __init visstrim_m10_timer_init(void)
+{
+	mx27_clocks_init((unsigned long)25000000);
+}
+
+static struct sys_timer visstrim_m10_timer = {
+	.init	= visstrim_m10_timer_init,
+};
+
+MACHINE_START(IMX27_VISSTRIM_M10, "Vista Silicon Visstrim_M10")
+	.boot_params    = MX27_PHYS_OFFSET + 0x100,
+	.map_io         = mx27_map_io,
+	.init_irq       = mx27_init_irq,
+	.init_machine   = visstrim_m10_board_init,
+	.timer          = &visstrim_m10_timer,
+MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx27lite.c b/arch/arm/mach-imx/mach-imx27lite.c
index 22a2b5d..bbdbc75 100644
--- a/arch/arm/mach-imx/mach-imx27lite.c
+++ b/arch/arm/mach-imx/mach-imx27lite.c
@@ -27,7 +27,7 @@
 #include "devices-imx27.h"
 #include "devices.h"
 
-static unsigned int mx27lite_pins[] = {
+static const int mx27lite_pins[] __initconst = {
 	/* UART1 */
 	PE12_PF_UART1_TXD,
 	PE13_PF_UART1_RXD,
@@ -58,16 +58,12 @@
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
-static struct platform_device *platform_devices[] __initdata = {
-	&mxc_fec_device,
-};
-
 static void __init mx27lite_init(void)
 {
 	mxc_gpio_setup_multiple_pins(mx27lite_pins, ARRAY_SIZE(mx27lite_pins),
 		"imx27lite");
 	imx27_add_imx_uart0(&uart_pdata);
-	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
+	imx27_add_fec(NULL);
 }
 
 static void __init mx27lite_timer_init(void)
@@ -80,8 +76,6 @@
 };
 
 MACHINE_START(IMX27LITE, "LogicPD i.MX27LITE")
-	.phys_io        = MX27_AIPI_BASE_ADDR,
-	.io_pg_offst    = ((MX27_AIPI_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX27_PHYS_OFFSET + 0x100,
 	.map_io         = mx27_map_io,
 	.init_irq       = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx1ads.c b/arch/arm/mach-imx/mach-mx1ads.c
index 77a760c..6187ce9 100644
--- a/arch/arm/mach-imx/mach-mx1ads.c
+++ b/arch/arm/mach-imx/mach-mx1ads.c
@@ -32,7 +32,7 @@
 #include "devices-imx1.h"
 #include "devices.h"
 
-static int mx1ads_pins[] = {
+static const int mx1ads_pins[] __initconst = {
 	/* UART1 */
 	PC9_PF_UART1_CTS,
 	PC10_PF_UART1_RTS,
@@ -131,7 +131,7 @@
 	i2c_register_board_info(0, mx1ads_i2c_devices,
 				ARRAY_SIZE(mx1ads_i2c_devices));
 
-	imx1_add_i2c_imx(&mx1ads_i2c_data);
+	imx1_add_imx_i2c(&mx1ads_i2c_data);
 }
 
 static void __init mx1ads_timer_init(void)
@@ -145,8 +145,6 @@
 
 MACHINE_START(MX1ADS, "Freescale MX1ADS")
 	/* Maintainer: Sascha Hauer, Pengutronix */
-	.phys_io	= MX1_IO_BASE_ADDR,
-	.io_pg_offst	= (MX1_IO_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params	= MX1_PHYS_OFFSET + 0x100,
 	.map_io		= mx1_map_io,
 	.init_irq	= mx1_init_irq,
@@ -155,8 +153,6 @@
 MACHINE_END
 
 MACHINE_START(MXLADS, "Freescale MXLADS")
-	.phys_io	= MX1_IO_BASE_ADDR,
-	.io_pg_offst	= (MX1_IO_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params	= MX1_PHYS_OFFSET + 0x100,
 	.map_io		= mx1_map_io,
 	.init_irq	= mx1_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx21ads.c b/arch/arm/mach-imx/mach-mx21ads.c
index 96d7f81..e1282e9 100644
--- a/arch/arm/mach-imx/mach-mx21ads.c
+++ b/arch/arm/mach-imx/mach-mx21ads.c
@@ -67,7 +67,7 @@
 #define MX21ADS_IO_LED4_ON      0x4000
 #define MX21ADS_IO_LED3_ON      0x8000
 
-static unsigned int mx21ads_pins[] = {
+static const int mx21ads_pins[] __initconst = {
 
 	/* CS8900A */
 	(GPIO_PORTE | GPIO_GPIO | GPIO_IN | 11),
@@ -314,8 +314,6 @@
 
 MACHINE_START(MX21ADS, "Freescale i.MX21ADS")
 	/* maintainer: Freescale Semiconductor, Inc. */
-	.phys_io        = MX21_AIPI_BASE_ADDR,
-	.io_pg_offst    = ((MX21_AIPI_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX21_PHYS_OFFSET + 0x100,
 	.map_io         = mx21ads_map_io,
 	.init_irq       = mx21_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx27_3ds.c b/arch/arm/mach-imx/mach-mx27_3ds.c
index e66ffaa..b8bbd31 100644
--- a/arch/arm/mach-imx/mach-mx27_3ds.c
+++ b/arch/arm/mach-imx/mach-mx27_3ds.c
@@ -33,7 +33,7 @@
 #include "devices-imx27.h"
 #include "devices.h"
 
-static unsigned int mx27pdk_pins[] = {
+static const int mx27pdk_pins[] __initconst = {
 	/* UART1 */
 	PE12_PF_UART1_TXD,
 	PE13_PF_UART1_RXD,
@@ -64,10 +64,6 @@
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
-static struct platform_device *platform_devices[] __initdata = {
-	&mxc_fec_device,
-};
-
 /*
  * Matrix keyboard
  */
@@ -94,7 +90,7 @@
 	mxc_gpio_setup_multiple_pins(mx27pdk_pins, ARRAY_SIZE(mx27pdk_pins),
 		"mx27pdk");
 	imx27_add_imx_uart0(&uart_pdata);
-	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
+	imx27_add_fec(NULL);
 	mxc_register_device(&imx_kpp_device, &mx27_3ds_keymap_data);
 }
 
@@ -109,8 +105,6 @@
 
 MACHINE_START(MX27_3DS, "Freescale MX27PDK")
 	/* maintainer: Freescale Semiconductor, Inc. */
-	.phys_io        = MX27_AIPI_BASE_ADDR,
-	.io_pg_offst    = ((MX27_AIPI_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX27_PHYS_OFFSET + 0x100,
 	.map_io         = mx27_map_io,
 	.init_irq       = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-mx27ads.c b/arch/arm/mach-imx/mach-mx27ads.c
index 9c77da9..a1e4bc5 100644
--- a/arch/arm/mach-imx/mach-mx27ads.c
+++ b/arch/arm/mach-imx/mach-mx27ads.c
@@ -66,7 +66,7 @@
 /* to determine the correct external crystal reference */
 #define CKIH_27MHZ_BIT_SET      (1 << 3)
 
-static unsigned int mx27ads_pins[] = {
+static const int mx27ads_pins[] __initconst = {
 	/* UART0 */
 	PE12_PF_UART1_TXD,
 	PE13_PF_UART1_RXD,
@@ -284,7 +284,6 @@
 
 static struct platform_device *platform_devices[] __initdata = {
 	&mx27ads_nor_mtd_device,
-	&mxc_fec_device,
 	&mxc_w1_master_device,
 };
 
@@ -308,11 +307,12 @@
 	/* only the i2c master 1 is used on this CPU card */
 	i2c_register_board_info(1, mx27ads_i2c_devices,
 				ARRAY_SIZE(mx27ads_i2c_devices));
-	imx27_add_i2c_imx1(&mx27ads_i2c1_data);
+	imx27_add_imx_i2c(1, &mx27ads_i2c1_data);
 	mxc_register_device(&mxc_fb_device, &mx27ads_fb_data);
 	mxc_register_device(&mxc_sdhc_device0, &sdhc1_pdata);
 	mxc_register_device(&mxc_sdhc_device1, &sdhc2_pdata);
 
+	imx27_add_fec(NULL);
 	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
 }
 
@@ -347,8 +347,6 @@
 
 MACHINE_START(MX27ADS, "Freescale i.MX27ADS")
 	/* maintainer: Freescale Semiconductor, Inc. */
-	.phys_io        = MX27_AIPI_BASE_ADDR,
-	.io_pg_offst    = ((MX27_AIPI_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX27_PHYS_OFFSET + 0x100,
 	.map_io         = mx27ads_map_io,
 	.init_irq       = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-mxt_td60.c b/arch/arm/mach-imx/mach-mxt_td60.c
index a3a1e45..38d3a4a 100644
--- a/arch/arm/mach-imx/mach-mxt_td60.c
+++ b/arch/arm/mach-imx/mach-mxt_td60.c
@@ -37,7 +37,7 @@
 #include "devices-imx27.h"
 #include "devices.h"
 
-static unsigned int mxt_td60_pins[] __initdata = {
+static const int mxt_td60_pins[] __initconst = {
 	/* UART0 */
 	PE12_PF_UART1_TXD,
 	PE13_PF_UART1_RXD,
@@ -231,10 +231,6 @@
 	.exit = mxt_td60_sdhc1_exit,
 };
 
-static struct platform_device *platform_devices[] __initdata = {
-	&mxc_fec_device,
-};
-
 static const struct imxuart_platform_data uart_pdata __initconst = {
 	.flags = IMXUART_HAVE_RTSCTS,
 };
@@ -255,12 +251,11 @@
 	i2c_register_board_info(1, mxt_td60_i2c2_devices,
 				ARRAY_SIZE(mxt_td60_i2c2_devices));
 
-	imx27_add_i2c_imx0(&mxt_td60_i2c0_data);
-	imx27_add_i2c_imx1(&mxt_td60_i2c1_data);
+	imx27_add_imx_i2c(0, &mxt_td60_i2c0_data);
+	imx27_add_imx_i2c(1, &mxt_td60_i2c1_data);
 	mxc_register_device(&mxc_fb_device, &mxt_td60_fb_data);
 	mxc_register_device(&mxc_sdhc_device0, &sdhc1_pdata);
-
-	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
+	imx27_add_fec(NULL);
 }
 
 static void __init mxt_td60_timer_init(void)
@@ -274,8 +269,6 @@
 
 MACHINE_START(MXT_TD60, "Maxtrack i-MXT TD60")
 	/* maintainer: Maxtrack Industrial */
-	.phys_io	= MX27_AIPI_BASE_ADDR,
-	.io_pg_offst	= ((MX27_AIPI_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params	= MX27_PHYS_OFFSET + 0x100,
 	.map_io		= mx27_map_io,
 	.init_irq	= mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-pca100.c b/arch/arm/mach-imx/mach-pca100.c
index 23c9e1f..8c720d4 100644
--- a/arch/arm/mach-imx/mach-pca100.c
+++ b/arch/arm/mach-imx/mach-pca100.c
@@ -38,7 +38,6 @@
 #include <mach/iomux-mx27.h>
 #include <asm/mach/time.h>
 #include <mach/audmux.h>
-#include <mach/ssi.h>
 #include <mach/mxc_nand.h>
 #include <mach/irqs.h>
 #include <mach/mmc.h>
@@ -55,7 +54,7 @@
 #define SPI1_SS1 (GPIO_PORTD + 27)
 #define SD2_CD (GPIO_PORTC + 29)
 
-static int pca100_pins[] = {
+static const int pca100_pins[] __initconst = {
 	/* UART1 */
 	PE12_PF_UART1_TXD,
 	PE13_PF_UART1_RXD,
@@ -174,7 +173,6 @@
 
 static struct platform_device *platform_devices[] __initdata = {
 	&mxc_w1_master_device,
-	&mxc_fec_device,
 	&mxc_wdt,
 };
 
@@ -193,11 +191,9 @@
 		I2C_BOARD_INFO("at24", 0x52), /* E0=0, E1=1, E2=0 */
 		.platform_data = &board_eeprom,
 	}, {
-		I2C_BOARD_INFO("rtc-pcf8563", 0x51),
-		.type = "pcf8563"
+		I2C_BOARD_INFO("pcf8563", 0x51),
 	}, {
 		I2C_BOARD_INFO("lm75", 0x4a),
-		.type = "lm75"
 	}
 };
 
@@ -252,7 +248,7 @@
 	msleep(2);
 }
 
-static struct imx_ssi_platform_data pca100_ssi_pdata = {
+static const struct imx_ssi_platform_data pca100_ssi_pdata __initconst = {
 	.ac97_reset		= pca100_ac97_cold_reset,
 	.ac97_warm_reset	= pca100_ac97_warm_reset,
 	.flags			= IMX_SSI_USE_AC97,
@@ -389,7 +385,7 @@
 	if (ret)
 		printk(KERN_ERR "pca100: Failed to setup pins (%d)\n", ret);
 
-	mxc_register_device(&imx_ssi_device0, &pca100_ssi_pdata);
+	imx27_add_imx_ssi(0, &pca100_ssi_pdata);
 
 	imx27_add_imx_uart0(&uart_pdata);
 
@@ -401,7 +397,7 @@
 	i2c_register_board_info(1, pca100_i2c_devices,
 				ARRAY_SIZE(pca100_i2c_devices));
 
-	imx27_add_i2c_imx1(&pca100_i2c1_data);
+	imx27_add_imx_i2c(1, &pca100_i2c1_data);
 
 #if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE)
 	mxc_gpio_mode(GPIO_PORTD | 28 | GPIO_GPIO | GPIO_IN);
@@ -436,6 +432,7 @@
 
 	mxc_register_device(&mxc_fb_device, &pca100_fb_data);
 
+	imx27_add_fec(NULL);
 	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
 }
 
@@ -449,8 +446,6 @@
 };
 
 MACHINE_START(PCA100, "phyCARD-i.MX27")
-	.phys_io        = MX27_AIPI_BASE_ADDR,
-	.io_pg_offst    = ((MX27_AIPI_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX27_PHYS_OFFSET + 0x100,
 	.map_io         = mx27_map_io,
 	.init_irq       = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-pcm038.c b/arch/arm/mach-imx/mach-pcm038.c
index 9212e8f..49a97ce 100644
--- a/arch/arm/mach-imx/mach-pcm038.c
+++ b/arch/arm/mach-imx/mach-pcm038.c
@@ -43,7 +43,7 @@
 #include "devices-imx27.h"
 #include "devices.h"
 
-static int pcm038_pins[] = {
+static const int pcm038_pins[] __initconst = {
 	/* UART1 */
 	PE12_PF_UART1_TXD,
 	PE13_PF_UART1_RXD,
@@ -173,7 +173,6 @@
 static struct platform_device *platform_devices[] __initdata = {
 	&pcm038_nor_mtd_device,
 	&mxc_w1_master_device,
-	&mxc_fec_device,
 	&pcm038_sram_mtd_device,
 	&mxc_wdt,
 };
@@ -257,7 +256,7 @@
 	.consumer_supplies = cam_consumers,
 };
 
-struct mc13783_regulator_init_data pcm038_regulators[] = {
+static struct mc13783_regulator_init_data pcm038_regulators[] = {
 	{
 		.id = MC13783_REGU_VCAM,
 		.init_data = &cam_data,
@@ -309,7 +308,7 @@
 	i2c_register_board_info(1, pcm038_i2c_devices,
 				ARRAY_SIZE(pcm038_i2c_devices));
 
-	imx27_add_i2c_imx1(&pcm038_i2c1_data);
+	imx27_add_imx_i2c(1, &pcm038_i2c1_data);
 
 	/* PE18 for user-LED D40 */
 	mxc_gpio_mode(GPIO_PORTE | 18 | GPIO_GPIO | GPIO_OUT);
@@ -325,6 +324,7 @@
 
 	mxc_register_device(&mxc_usbh2, &usbh2_pdata);
 
+	imx27_add_fec(NULL);
 	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
 
 #ifdef CONFIG_MACH_PCM970_BASEBOARD
@@ -342,8 +342,6 @@
 };
 
 MACHINE_START(PCM038, "phyCORE-i.MX27")
-	.phys_io        = MX27_AIPI_BASE_ADDR,
-	.io_pg_offst    = ((MX27_AIPI_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX27_PHYS_OFFSET + 0x100,
 	.map_io         = mx27_map_io,
 	.init_irq       = mx27_init_irq,
diff --git a/arch/arm/mach-imx/mach-scb9328.c b/arch/arm/mach-imx/mach-scb9328.c
index 88bf0d1..1fbdd3f 100644
--- a/arch/arm/mach-imx/mach-scb9328.c
+++ b/arch/arm/mach-imx/mach-scb9328.c
@@ -95,7 +95,7 @@
 	}
 };
 
-static int mxc_uart1_pins[] = {
+static const int mxc_uart1_pins[] = {
 	PC9_PF_UART1_CTS,
 	PC10_PF_UART1_RTS,
 	PC11_PF_UART1_TXD,
@@ -147,8 +147,6 @@
 
 MACHINE_START(SCB9328, "Synertronixx scb9328")
     /* Sascha Hauer */
-	.phys_io	= 0x00200000,
-	.io_pg_offst	= ((0xe0200000) >> 18) & 0xfffc,
 	.boot_params	= 0x08000100,
 	.map_io		= mx1_map_io,
 	.init_irq	= mx1_init_irq,
diff --git a/arch/arm/mach-imx/pcm970-baseboard.c b/arch/arm/mach-imx/pcm970-baseboard.c
index f490a40..9110d9c 100644
--- a/arch/arm/mach-imx/pcm970-baseboard.c
+++ b/arch/arm/mach-imx/pcm970-baseboard.c
@@ -31,7 +31,7 @@
 
 #include "devices.h"
 
-static int pcm970_pins[] = {
+static const int pcm970_pins[] __initconst = {
 	/* SDHC */
 	PB4_PF_SD2_D0,
 	PB5_PF_SD2_D1,
@@ -200,7 +200,7 @@
 	},
 };
 
-struct sja1000_platform_data pcm970_sja1000_platform_data = {
+static struct sja1000_platform_data pcm970_sja1000_platform_data = {
 	.osc_freq	= 16000000,
 	.ocr		= OCR_TX1_PULLDOWN | OCR_TX0_PUSHPULL,
 	.cdr		= CDR_CBP,
diff --git a/arch/arm/mach-integrator/include/mach/debug-macro.S b/arch/arm/mach-integrator/include/mach/debug-macro.S
index 87a6888..a1f598f 100644
--- a/arch/arm/mach-integrator/include/mach/debug-macro.S
+++ b/arch/arm/mach-integrator/include/mach/debug-macro.S
@@ -11,12 +11,10 @@
  *
 */
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x16000000	@ physical base address
-		movne	\rx, #0xf0000000	@ virtual base
-		addne	\rx, \rx, #0x16000000 >> 4
+		.macro	addruart, rp, rv
+		mov	\rp, #0x16000000	@ physical base address
+		mov	\rv, #0xf0000000	@ virtual base
+		add	\rv, \rv, #0x16000000 >> 4
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-integrator/include/mach/vmalloc.h b/arch/arm/mach-integrator/include/mach/vmalloc.h
index e87ab0b..e056e7c 100644
--- a/arch/arm/mach-integrator/include/mach/vmalloc.h
+++ b/arch/arm/mach-integrator/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#define VMALLOC_END       (PAGE_OFFSET + 0x10000000)
+#define VMALLOC_END       0xd0000000
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 6ab5a03..548208f 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -500,8 +500,6 @@
 
 MACHINE_START(INTEGRATOR, "ARM-Integrator")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= 0x16000000,
-	.io_pg_offst	= ((0xf1600000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= ap_map_io,
 	.reserve	= integrator_reserve,
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 05db40e..6258c90 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -599,8 +599,6 @@
 
 MACHINE_START(CINTEGRATOR, "ARM-IntegratorCP")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= 0x16000000,
-	.io_pg_offst	= ((0xf1600000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= intcp_map_io,
 	.reserve	= integrator_reserve,
diff --git a/arch/arm/mach-iop13xx/include/mach/debug-macro.S b/arch/arm/mach-iop13xx/include/mach/debug-macro.S
index c9d6ba4..e664466 100644
--- a/arch/arm/mach-iop13xx/include/mach/debug-macro.S
+++ b/arch/arm/mach-iop13xx/include/mach/debug-macro.S
@@ -11,15 +11,13 @@
  * published by the Free Software Foundation.
  */
 
-	.macro	addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1			@ mmu enabled?
-	moveq	\rx, #0xff000000	@ physical
-	orreq	\rx, \rx, #0x00d80000
-	movne	\rx, #0xfe000000	@ virtual
-	orrne	\rx, \rx, #0x00e80000
-	orr	\rx, \rx, #0x00002300
-	orr	\rx, \rx, #0x00000040
+	.macro	addruart, rp, rv
+	mov	\rp, #0x00002300
+	orr	\rp, \rp, #0x00000040
+	orr	\rv, \rp, #0xfe000000	@ virtual
+	orr	\rv, \rv, #0x00e80000
+	orr	\rp, \rp, #0xff000000	@ physical
+	orr	\rp, \rp, #0x00d80000
 	.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-iop13xx/iq81340mc.c b/arch/arm/mach-iop13xx/iq81340mc.c
index f91f315..9b5a63f 100644
--- a/arch/arm/mach-iop13xx/iq81340mc.c
+++ b/arch/arm/mach-iop13xx/iq81340mc.c
@@ -91,8 +91,6 @@
 
 MACHINE_START(IQ81340MC, "Intel IQ81340MC")
 	/* Maintainer: Dan Williams <dan.j.williams@intel.com> */
-	.phys_io        = IOP13XX_PMMR_PHYS_MEM_BASE,
-	.io_pg_offst    = (IOP13XX_PMMR_VIRT_MEM_BASE >> 18) & 0xfffc,
 	.boot_params    = 0x00000100,
 	.map_io         = iop13xx_map_io,
 	.init_irq       = iop13xx_init_irq,
diff --git a/arch/arm/mach-iop13xx/iq81340sc.c b/arch/arm/mach-iop13xx/iq81340sc.c
index ddb7a34..df3492a 100644
--- a/arch/arm/mach-iop13xx/iq81340sc.c
+++ b/arch/arm/mach-iop13xx/iq81340sc.c
@@ -93,8 +93,6 @@
 
 MACHINE_START(IQ81340SC, "Intel IQ81340SC")
 	/* Maintainer: Dan Williams <dan.j.williams@intel.com> */
-	.phys_io	= IOP13XX_PMMR_PHYS_MEM_BASE,
-	.io_pg_offst	= (IOP13XX_PMMR_VIRT_MEM_BASE >> 18) & 0xfffc,
 	.boot_params    = 0x00000100,
 	.map_io         = iop13xx_map_io,
 	.init_irq       = iop13xx_init_irq,
diff --git a/arch/arm/mach-iop13xx/msi.c b/arch/arm/mach-iop13xx/msi.c
index f34b0ed..7149fcc 100644
--- a/arch/arm/mach-iop13xx/msi.c
+++ b/arch/arm/mach-iop13xx/msi.c
@@ -164,10 +164,10 @@
 static struct irq_chip iop13xx_msi_chip = {
 	.name = "PCI-MSI",
 	.ack = iop13xx_msi_nop,
-	.enable = unmask_msi_irq,
-	.disable = mask_msi_irq,
-	.mask = mask_msi_irq,
-	.unmask = unmask_msi_irq,
+	.irq_enable = unmask_msi_irq,
+	.irq_disable = mask_msi_irq,
+	.irq_mask = mask_msi_irq,
+	.irq_unmask = unmask_msi_irq,
 };
 
 int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
diff --git a/arch/arm/mach-iop32x/em7210.c b/arch/arm/mach-iop32x/em7210.c
index 2bef9b6..779f924 100644
--- a/arch/arm/mach-iop32x/em7210.c
+++ b/arch/arm/mach-iop32x/em7210.c
@@ -203,8 +203,6 @@
 }
 
 MACHINE_START(EM7210, "Lanner EM7210")
-	.phys_io	= IQ31244_UART,
-	.io_pg_offst	= ((IQ31244_UART) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= em7210_map_io,
 	.init_irq	= iop32x_init_irq,
diff --git a/arch/arm/mach-iop32x/glantank.c b/arch/arm/mach-iop32x/glantank.c
index 10384fc..c6b6f9c 100644
--- a/arch/arm/mach-iop32x/glantank.c
+++ b/arch/arm/mach-iop32x/glantank.c
@@ -207,8 +207,6 @@
 
 MACHINE_START(GLANTANK, "GLAN Tank")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= GLANTANK_UART,
-	.io_pg_offst	= ((GLANTANK_UART) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= glantank_map_io,
 	.init_irq	= iop32x_init_irq,
diff --git a/arch/arm/mach-iop32x/include/mach/debug-macro.S b/arch/arm/mach-iop32x/include/mach/debug-macro.S
index 736afe1..ff9e76c 100644
--- a/arch/arm/mach-iop32x/include/mach/debug-macro.S
+++ b/arch/arm/mach-iop32x/include/mach/debug-macro.S
@@ -11,9 +11,10 @@
  * published by the Free Software Foundation.
  */
 
-		.macro	addruart, rx, tmp
-		mov	\rx, #0xfe000000	@ physical as well as virtual
-		orr	\rx, \rx, #0x00800000	@ location of the UART
+		.macro	addruart, rp, rv
+		mov	\rp, #0xfe000000	@ physical as well as virtual
+		orr	\rp, \rp, #0x00800000	@ location of the UART
+		mov	\rv, \rp
 		.endm
 
 #define UART_SHIFT	0
diff --git a/arch/arm/mach-iop32x/iq31244.c b/arch/arm/mach-iop32x/iq31244.c
index d6ac85f..fde962c 100644
--- a/arch/arm/mach-iop32x/iq31244.c
+++ b/arch/arm/mach-iop32x/iq31244.c
@@ -313,8 +313,6 @@
 
 MACHINE_START(IQ31244, "Intel IQ31244")
 	/* Maintainer: Intel Corp. */
-	.phys_io	= IQ31244_UART,
-	.io_pg_offst	= ((IQ31244_UART) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= iq31244_map_io,
 	.init_irq	= iop32x_init_irq,
@@ -329,8 +327,6 @@
  */
 MACHINE_START(EP80219, "Intel EP80219")
 	/* Maintainer: Intel Corp. */
-	.phys_io	= IQ31244_UART,
-	.io_pg_offst	= ((IQ31244_UART) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= iq31244_map_io,
 	.init_irq	= iop32x_init_irq,
diff --git a/arch/arm/mach-iop32x/iq80321.c b/arch/arm/mach-iop32x/iq80321.c
index c6a0e4e..3a95950 100644
--- a/arch/arm/mach-iop32x/iq80321.c
+++ b/arch/arm/mach-iop32x/iq80321.c
@@ -186,8 +186,6 @@
 
 MACHINE_START(IQ80321, "Intel IQ80321")
 	/* Maintainer: Intel Corp. */
-	.phys_io	= IQ80321_UART,
-	.io_pg_offst	= ((IQ80321_UART) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= iq80321_map_io,
 	.init_irq	= iop32x_init_irq,
diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c
index f108a31..626aa37 100644
--- a/arch/arm/mach-iop32x/n2100.c
+++ b/arch/arm/mach-iop32x/n2100.c
@@ -327,8 +327,6 @@
 
 MACHINE_START(N2100, "Thecus N2100")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= N2100_UART,
-	.io_pg_offst	= ((N2100_UART) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= n2100_map_io,
 	.init_irq	= iop32x_init_irq,
diff --git a/arch/arm/mach-iop33x/include/mach/debug-macro.S b/arch/arm/mach-iop33x/include/mach/debug-macro.S
index addb2da..40c500d 100644
--- a/arch/arm/mach-iop33x/include/mach/debug-macro.S
+++ b/arch/arm/mach-iop33x/include/mach/debug-macro.S
@@ -11,13 +11,11 @@
  * published by the Free Software Foundation.
  */
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ mmu enabled?
-		moveq	\rx, #0xff000000	@ physical
-		movne	\rx, #0xfe000000	@ virtual
-		orr	\rx, \rx, #0x00ff0000
-		orr	\rx, \rx, #0x0000f700
+		.macro	addruart, rp, rv
+		mov	\rp, #0x00ff0000
+		orr	\rp, \rp, #0x0000f700
+		orr	\rv, #0xfe000000	@ virtual
+		orr	\rp, #0xff000000	@ physical
 		.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-iop33x/iq80331.c b/arch/arm/mach-iop33x/iq80331.c
index c6ff552..c565f8d 100644
--- a/arch/arm/mach-iop33x/iq80331.c
+++ b/arch/arm/mach-iop33x/iq80331.c
@@ -141,8 +141,6 @@
 
 MACHINE_START(IQ80331, "Intel IQ80331")
 	/* Maintainer: Intel Corp. */
-	.phys_io	= 0xfefff000,
-	.io_pg_offst	= ((0xfffff000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= iop3xx_map_io,
 	.init_irq	= iop33x_init_irq,
diff --git a/arch/arm/mach-iop33x/iq80332.c b/arch/arm/mach-iop33x/iq80332.c
index fbf55140..36a9efb 100644
--- a/arch/arm/mach-iop33x/iq80332.c
+++ b/arch/arm/mach-iop33x/iq80332.c
@@ -141,8 +141,6 @@
 
 MACHINE_START(IQ80332, "Intel IQ80332")
 	/* Maintainer: Intel Corp. */
-	.phys_io	= 0xfefff000,
-	.io_pg_offst	= ((0xfffff000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= iop3xx_map_io,
 	.init_irq	= iop33x_init_irq,
diff --git a/arch/arm/mach-ixp2000/enp2611.c b/arch/arm/mach-ixp2000/enp2611.c
index 1a557e0..88663ab 100644
--- a/arch/arm/mach-ixp2000/enp2611.c
+++ b/arch/arm/mach-ixp2000/enp2611.c
@@ -253,8 +253,6 @@
 
 MACHINE_START(ENP2611, "Radisys ENP-2611 PCI network processor board")
 	/* Maintainer: Lennert Buytenhek <buytenh@wantstofly.org> */
-	.phys_io	= IXP2000_UART_PHYS_BASE,
-	.io_pg_offst	= ((IXP2000_UART_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= enp2611_map_io,
 	.init_irq	= ixp2000_init_irq,
diff --git a/arch/arm/mach-ixp2000/include/mach/debug-macro.S b/arch/arm/mach-ixp2000/include/mach/debug-macro.S
index 6a82768..0ef533b 100644
--- a/arch/arm/mach-ixp2000/include/mach/debug-macro.S
+++ b/arch/arm/mach-ixp2000/include/mach/debug-macro.S
@@ -11,16 +11,14 @@
  *
 */
 
-		.macro  addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0xc0000000	@ Physical base
-		movne	\rx, #0xfe000000	@ virtual base
-		orrne	\rx, \rx, #0x00f00000
-		orr	\rx, \rx, #0x00030000
+		.macro  addruart, rp, rv
+		mov	\rp, #0x00030000
 #ifdef	__ARMEB__
-		orr	\rx, \rx, #0x00000003
+		orr	\rp, \rp, #0x00000003
 #endif
+		orr	\rv, \rp, #0xfe000000	@ virtual base
+		orr	\rv, \rv, #0x00f00000
+		orr	\rp, \rp, #0xc0000000	@ Physical base
 		.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-ixp2000/ixdp2400.c b/arch/arm/mach-ixp2000/ixdp2400.c
index 55e5c69..dfffc1e 100644
--- a/arch/arm/mach-ixp2000/ixdp2400.c
+++ b/arch/arm/mach-ixp2000/ixdp2400.c
@@ -170,8 +170,6 @@
 
 MACHINE_START(IXDP2400, "Intel IXDP2400 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP2000_UART_PHYS_BASE,
-	.io_pg_offst	= ((IXP2000_UART_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= ixdp2x00_map_io,
 	.init_irq	= ixdp2400_init_irq,
diff --git a/arch/arm/mach-ixp2000/ixdp2800.c b/arch/arm/mach-ixp2000/ixdp2800.c
index 237b61a..cd4c9bc 100644
--- a/arch/arm/mach-ixp2000/ixdp2800.c
+++ b/arch/arm/mach-ixp2000/ixdp2800.c
@@ -285,8 +285,6 @@
 
 MACHINE_START(IXDP2800, "Intel IXDP2800 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP2000_UART_PHYS_BASE,
-	.io_pg_offst	= ((IXP2000_UART_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= ixdp2x00_map_io,
 	.init_irq	= ixdp2800_init_irq,
diff --git a/arch/arm/mach-ixp2000/ixdp2x01.c b/arch/arm/mach-ixp2000/ixdp2x01.c
index 0369ec4..6c121bd 100644
--- a/arch/arm/mach-ixp2000/ixdp2x01.c
+++ b/arch/arm/mach-ixp2000/ixdp2x01.c
@@ -416,8 +416,6 @@
 #ifdef CONFIG_ARCH_IXDP2401
 MACHINE_START(IXDP2401, "Intel IXDP2401 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP2000_UART_PHYS_BASE,
-	.io_pg_offst	= ((IXP2000_UART_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= ixdp2x01_map_io,
 	.init_irq	= ixdp2x01_init_irq,
@@ -429,8 +427,6 @@
 #ifdef CONFIG_ARCH_IXDP2801
 MACHINE_START(IXDP2801, "Intel IXDP2801 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP2000_UART_PHYS_BASE,
-	.io_pg_offst	= ((IXP2000_UART_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= ixdp2x01_map_io,
 	.init_irq	= ixdp2x01_init_irq,
@@ -444,8 +440,6 @@
  */
 MACHINE_START(IXDP28X5, "Intel IXDP2805/2855 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP2000_UART_PHYS_BASE,
-	.io_pg_offst	= ((IXP2000_UART_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= ixdp2x01_map_io,
 	.init_irq	= ixdp2x01_init_irq,
diff --git a/arch/arm/mach-ixp23xx/espresso.c b/arch/arm/mach-ixp23xx/espresso.c
index 1c06bfc..e25e5fe 100644
--- a/arch/arm/mach-ixp23xx/espresso.c
+++ b/arch/arm/mach-ixp23xx/espresso.c
@@ -85,8 +85,6 @@
 
 MACHINE_START(ESPRESSO, "IP Fabrics Double Espresso")
 	/* Maintainer: Lennert Buytenhek */
-	.phys_io	= IXP23XX_PERIPHERAL_PHYS,
-	.io_pg_offst	= ((IXP23XX_PERIPHERAL_VIRT >> 18)) & 0xfffc,
 	.map_io		= ixp23xx_map_io,
 	.init_irq	= ixp23xx_init_irq,
 	.timer		= &ixp23xx_timer,
diff --git a/arch/arm/mach-ixp23xx/include/mach/debug-macro.S b/arch/arm/mach-ixp23xx/include/mach/debug-macro.S
index a82e3754..f7c6eef 100644
--- a/arch/arm/mach-ixp23xx/include/mach/debug-macro.S
+++ b/arch/arm/mach-ixp23xx/include/mach/debug-macro.S
@@ -12,13 +12,12 @@
  */
 #include <mach/ixp23xx.h>
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1				@ mmu enabled?
-		ldreq	\rx, =IXP23XX_PERIPHERAL_PHYS 	@ physical
-		ldrne	\rx, =IXP23XX_PERIPHERAL_VIRT	@ virtual
+		.macro	addruart, rp, rv
+		ldr	\rp, =IXP23XX_PERIPHERAL_PHYS 	@ physical
+		ldr	\rv, =IXP23XX_PERIPHERAL_VIRT	@ virtual
 #ifdef __ARMEB__
-		orr	\rx, \rx, #0x00000003
+		orr	\rp, \rp, #0x00000003
+		orr	\rv, \rv, #0x00000003
 #endif
 		.endm
 
diff --git a/arch/arm/mach-ixp23xx/ixdp2351.c b/arch/arm/mach-ixp23xx/ixdp2351.c
index f1b124a..664e39c 100644
--- a/arch/arm/mach-ixp23xx/ixdp2351.c
+++ b/arch/arm/mach-ixp23xx/ixdp2351.c
@@ -328,8 +328,6 @@
 
 MACHINE_START(IXDP2351, "Intel IXDP2351 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP23XX_PERIPHERAL_PHYS,
-	.io_pg_offst	= ((IXP23XX_PERIPHERAL_VIRT >> 18)) & 0xfffc,
 	.map_io		= ixdp2351_map_io,
 	.init_irq	= ixdp2351_init_irq,
 	.timer		= &ixp23xx_timer,
diff --git a/arch/arm/mach-ixp23xx/roadrunner.c b/arch/arm/mach-ixp23xx/roadrunner.c
index 6d38d76..76c61ba 100644
--- a/arch/arm/mach-ixp23xx/roadrunner.c
+++ b/arch/arm/mach-ixp23xx/roadrunner.c
@@ -171,8 +171,6 @@
 
 MACHINE_START(ROADRUNNER, "ADI Engineering RoadRunner Development Platform")
 	/* Maintainer: Deepak Saxena */
-	.phys_io	= IXP23XX_PERIPHERAL_PHYS,
-	.io_pg_offst	= ((IXP23XX_PERIPHERAL_VIRT >> 18)) & 0xfffc,
 	.map_io		= ixp23xx_map_io,
 	.init_irq	= ixp23xx_init_irq,
 	.timer		= &ixp23xx_timer,
diff --git a/arch/arm/mach-ixp4xx/avila-setup.c b/arch/arm/mach-ixp4xx/avila-setup.c
index d8bc86d..73745ff 100644
--- a/arch/arm/mach-ixp4xx/avila-setup.c
+++ b/arch/arm/mach-ixp4xx/avila-setup.c
@@ -164,8 +164,6 @@
 
 MACHINE_START(AVILA, "Gateworks Avila Network Platform")
 	/* Maintainer: Deepak Saxena <dsaxena@plexity.net> */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
@@ -181,8 +179,6 @@
 #ifdef CONFIG_MACH_LOFT
 MACHINE_START(LOFT, "Giant Shoulder Inc Loft board")
 	/* Maintainer: Tom Billman <kernel@giantshoulderinc.com> */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/coyote-setup.c b/arch/arm/mach-ixp4xx/coyote-setup.c
index 31a47f6..355e3de 100644
--- a/arch/arm/mach-ixp4xx/coyote-setup.c
+++ b/arch/arm/mach-ixp4xx/coyote-setup.c
@@ -109,8 +109,6 @@
 #ifdef CONFIG_ARCH_ADI_COYOTE
 MACHINE_START(ADI_COYOTE, "ADI Engineering Coyote")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
@@ -126,8 +124,6 @@
 #ifdef CONFIG_MACH_IXDPG425
 MACHINE_START(IXDPG425, "Intel IXDPG425")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c
index 7c1fa54..d398229 100644
--- a/arch/arm/mach-ixp4xx/dsmg600-setup.c
+++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c
@@ -279,8 +279,6 @@
 
 MACHINE_START(DSMG600, "D-Link DSM-G600 RevA")
 	/* Maintainer: www.nslu2-linux.org */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
diff --git a/arch/arm/mach-ixp4xx/fsg-setup.c b/arch/arm/mach-ixp4xx/fsg-setup.c
index e7f4bef..727ee39 100644
--- a/arch/arm/mach-ixp4xx/fsg-setup.c
+++ b/arch/arm/mach-ixp4xx/fsg-setup.c
@@ -270,8 +270,6 @@
 
 MACHINE_START(FSG, "Freecom FSG-3")
 	/* Maintainer: www.nslu2-linux.org */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/gateway7001-setup.c b/arch/arm/mach-ixp4xx/gateway7001-setup.c
index 2583b2a..9dc0b4e 100644
--- a/arch/arm/mach-ixp4xx/gateway7001-setup.c
+++ b/arch/arm/mach-ixp4xx/gateway7001-setup.c
@@ -96,8 +96,6 @@
 #ifdef CONFIG_MACH_GATEWAY7001
 MACHINE_START(GATEWAY7001, "Gateway 7001 AP")
 	/* Maintainer: Imre Kaloz <kaloz@openwrt.org> */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/goramo_mlr.c b/arch/arm/mach-ixp4xx/goramo_mlr.c
index 1c28048..d0e4861 100644
--- a/arch/arm/mach-ixp4xx/goramo_mlr.c
+++ b/arch/arm/mach-ixp4xx/goramo_mlr.c
@@ -496,8 +496,6 @@
 
 MACHINE_START(GORAMO_MLR, "MultiLink")
 	/* Maintainer: Krzysztof Halasa */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xFFFC,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/gtwx5715-setup.c b/arch/arm/mach-ixp4xx/gtwx5715-setup.c
index c67586b..77abead 100644
--- a/arch/arm/mach-ixp4xx/gtwx5715-setup.c
+++ b/arch/arm/mach-ixp4xx/gtwx5715-setup.c
@@ -164,8 +164,6 @@
 
 MACHINE_START(GTWX5715, "Gemtek GTWX5715 (Linksys WRV54G)")
 	/* Maintainer: George Joseph */
-	.phys_io	= IXP4XX_UART2_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_UART2_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/include/mach/debug-macro.S b/arch/arm/mach-ixp4xx/include/mach/debug-macro.S
index 3fc66d6..b974a49 100644
--- a/arch/arm/mach-ixp4xx/include/mach/debug-macro.S
+++ b/arch/arm/mach-ixp4xx/include/mach/debug-macro.S
@@ -10,16 +10,16 @@
  * published by the Free Software Foundation.
 */
 
-                .macro  addruart, rx, tmp
-                mrc     p15, 0, \rx, c1, c0
-                tst     \rx, #1                 @ MMU enabled?
-                moveq   \rx, #0xc8000000
-                movne   \rx, #0xff000000
-		orrne	\rx, \rx, #0x00b00000
+                .macro  addruart, rp, rv
 #ifdef __ARMEB__
-                add     \rx,\rx,#3              @ Uart regs are at off set of 3 if
-						@ byte writes used - Big Endian.
+                mov     \rp, #3         @ Uart regs are at off set of 3 if
+					@ byte writes used - Big Endian.
+#else
+		mov	\rp, #0
 #endif
+                orr     \rv, \rp, #0xff000000	@ virtual
+		orr	\rv, \rv, #0x00b00000
+                orr     \rp, \rp, #0xc8000000	@ physical
                 .endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-ixp4xx/ixdp425-setup.c b/arch/arm/mach-ixp4xx/ixdp425-setup.c
index ea9ee4e..1407833 100644
--- a/arch/arm/mach-ixp4xx/ixdp425-setup.c
+++ b/arch/arm/mach-ixp4xx/ixdp425-setup.c
@@ -257,8 +257,6 @@
 #ifdef CONFIG_ARCH_IXDP425
 MACHINE_START(IXDP425, "Intel IXDP425 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
@@ -270,8 +268,6 @@
 #ifdef CONFIG_MACH_IXDP465
 MACHINE_START(IXDP465, "Intel IXDP465 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
@@ -283,8 +279,6 @@
 #ifdef CONFIG_ARCH_PRPMC1100
 MACHINE_START(IXCDP1100, "Intel IXCDP1100 Development Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
@@ -296,8 +290,6 @@
 #ifdef CONFIG_MACH_KIXRP435
 MACHINE_START(KIXRP435, "Intel KIXRP435 Reference Platform")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
index e3ee880..f18fee7 100644
--- a/arch/arm/mach-ixp4xx/nas100d-setup.c
+++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
@@ -314,8 +314,6 @@
 
 MACHINE_START(NAS100D, "Iomega NAS 100d")
 	/* Maintainer: www.nslu2-linux.org */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
diff --git a/arch/arm/mach-ixp4xx/nslu2-setup.c b/arch/arm/mach-ixp4xx/nslu2-setup.c
index c14e003..f79b62e 100644
--- a/arch/arm/mach-ixp4xx/nslu2-setup.c
+++ b/arch/arm/mach-ixp4xx/nslu2-setup.c
@@ -300,8 +300,6 @@
 
 MACHINE_START(NSLU2, "Linksys NSLU2")
 	/* Maintainer: www.nslu2-linux.org */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
diff --git a/arch/arm/mach-ixp4xx/vulcan-setup.c b/arch/arm/mach-ixp4xx/vulcan-setup.c
index 465cc5c..4e72cfd 100644
--- a/arch/arm/mach-ixp4xx/vulcan-setup.c
+++ b/arch/arm/mach-ixp4xx/vulcan-setup.c
@@ -236,8 +236,6 @@
 
 MACHINE_START(ARCOM_VULCAN, "Arcom/Eurotech Vulcan")
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-ixp4xx/wg302v2-setup.c b/arch/arm/mach-ixp4xx/wg302v2-setup.c
index 4dd7486..5d148c7 100644
--- a/arch/arm/mach-ixp4xx/wg302v2-setup.c
+++ b/arch/arm/mach-ixp4xx/wg302v2-setup.c
@@ -97,8 +97,6 @@
 #ifdef CONFIG_MACH_WG302V2
 MACHINE_START(WG302V2, "Netgear WG302 v2 / WAG302 v2")
 	/* Maintainer: Imre Kaloz <kaloz@openwrt.org> */
-	.phys_io	= IXP4XX_PERIPHERAL_BASE_PHYS,
-	.io_pg_offst	= ((IXP4XX_PERIPHERAL_BASE_VIRT) >> 18) & 0xfffc,
 	.map_io		= ixp4xx_map_io,
 	.init_irq	= ixp4xx_init_irq,
 	.timer		= &ixp4xx_timer,
diff --git a/arch/arm/mach-kirkwood/Kconfig b/arch/arm/mach-kirkwood/Kconfig
index cc25501..3410633 100644
--- a/arch/arm/mach-kirkwood/Kconfig
+++ b/arch/arm/mach-kirkwood/Kconfig
@@ -58,6 +58,12 @@
 	  QNAP TS-410, TS-410U, TS-419P and TS-419U Turbo NAS
 	  devices.
 
+config MACH_DOCKSTAR
+	bool "Seagate FreeAgent DockStar"
+	help
+	  Say 'Y' here if you want your kernel to support the
+	  Seagate FreeAgent DockStar.
+
 config MACH_OPENRD
         bool
 
@@ -100,6 +106,12 @@
 	  Say 'Y' here if you want your kernel to support the
 	  LaCie Network Space Max v2 NAS.
 
+config MACH_D2NET_V2
+	bool "LaCie d2 Network v2 NAS Board"
+	help
+	  Say 'Y' here if you want your kernel to support the
+	  LaCie d2 Network v2 NAS.
+
 config MACH_NET2BIG_V2
 	bool "LaCie 2Big Network v2 NAS Board"
 	help
diff --git a/arch/arm/mach-kirkwood/Makefile b/arch/arm/mach-kirkwood/Makefile
index 295d7ba..5dcaa81 100644
--- a/arch/arm/mach-kirkwood/Makefile
+++ b/arch/arm/mach-kirkwood/Makefile
@@ -7,14 +7,16 @@
 obj-$(CONFIG_MACH_SHEEVAPLUG)		+= sheevaplug-setup.o
 obj-$(CONFIG_MACH_ESATA_SHEEVAPLUG)	+= sheevaplug-setup.o
 obj-$(CONFIG_MACH_GURUPLUG)		+= guruplug-setup.o
+obj-$(CONFIG_MACH_DOCKSTAR)		+= dockstar-setup.o
 obj-$(CONFIG_MACH_TS219)		+= ts219-setup.o tsx1x-common.o
 obj-$(CONFIG_MACH_TS41X)		+= ts41x-setup.o tsx1x-common.o
 obj-$(CONFIG_MACH_OPENRD)		+= openrd-setup.o
-obj-$(CONFIG_MACH_NETSPACE_V2)		+= netspace_v2-setup.o
-obj-$(CONFIG_MACH_INETSPACE_V2)		+= netspace_v2-setup.o
-obj-$(CONFIG_MACH_NETSPACE_MAX_V2)	+= netspace_v2-setup.o
-obj-$(CONFIG_MACH_NET2BIG_V2)		+= netxbig_v2-setup.o
-obj-$(CONFIG_MACH_NET5BIG_V2)		+= netxbig_v2-setup.o
+obj-$(CONFIG_MACH_NETSPACE_V2)		+= netspace_v2-setup.o lacie_v2-common.o
+obj-$(CONFIG_MACH_INETSPACE_V2)		+= netspace_v2-setup.o lacie_v2-common.o
+obj-$(CONFIG_MACH_NETSPACE_MAX_V2)	+= netspace_v2-setup.o lacie_v2-common.o
+obj-$(CONFIG_MACH_D2NET_V2)		+= d2net_v2-setup.o lacie_v2-common.o
+obj-$(CONFIG_MACH_NET2BIG_V2)		+= netxbig_v2-setup.o lacie_v2-common.o
+obj-$(CONFIG_MACH_NET5BIG_V2)		+= netxbig_v2-setup.o lacie_v2-common.o
 obj-$(CONFIG_MACH_T5325)		+= t5325-setup.o
 
 obj-$(CONFIG_CPU_IDLE)			+= cpuidle.o
diff --git a/arch/arm/mach-kirkwood/d2net_v2-setup.c b/arch/arm/mach-kirkwood/d2net_v2-setup.c
new file mode 100644
index 0000000..4aa86e4
--- /dev/null
+++ b/arch/arm/mach-kirkwood/d2net_v2-setup.c
@@ -0,0 +1,229 @@
+/*
+ * arch/arm/mach-kirkwood/d2net_v2-setup.c
+ *
+ * LaCie d2 Network Space v2 Board Setup
+ *
+ * Copyright (C) 2010 Simon Guinot <sguinot@lacie.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/ata_platform.h>
+#include <linux/mv643xx_eth.h>
+#include <linux/input.h>
+#include <linux/gpio.h>
+#include <linux/gpio_keys.h>
+#include <linux/leds.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <mach/kirkwood.h>
+#include <mach/leds-ns2.h>
+#include "common.h"
+#include "mpp.h"
+#include "lacie_v2-common.h"
+
+/*****************************************************************************
+ * Ethernet
+ ****************************************************************************/
+
+static struct mv643xx_eth_platform_data d2net_v2_ge00_data = {
+	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
+};
+
+/*****************************************************************************
+ * SATA
+ ****************************************************************************/
+
+static struct mv_sata_platform_data d2net_v2_sata_data = {
+	.n_ports	= 2,
+};
+
+/*****************************************************************************
+ * GPIO keys
+ ****************************************************************************/
+
+#define D2NET_V2_GPIO_PUSH_BUTTON          34
+#define D2NET_V2_GPIO_POWER_SWITCH_ON      13
+#define D2NET_V2_GPIO_POWER_SWITCH_OFF     15
+
+#define D2NET_V2_SWITCH_POWER_ON           0x1
+#define D2NET_V2_SWITCH_POWER_OFF          0x2
+
+static struct gpio_keys_button d2net_v2_buttons[] = {
+	[0] = {
+		.type           = EV_SW,
+		.code           = D2NET_V2_SWITCH_POWER_ON,
+		.gpio           = D2NET_V2_GPIO_POWER_SWITCH_ON,
+		.desc           = "Back power switch (on|auto)",
+		.active_low     = 0,
+	},
+	[1] = {
+		.type           = EV_SW,
+		.code           = D2NET_V2_SWITCH_POWER_OFF,
+		.gpio           = D2NET_V2_GPIO_POWER_SWITCH_OFF,
+		.desc           = "Back power switch (auto|off)",
+		.active_low     = 0,
+	},
+	[2] = {
+		.code           = KEY_POWER,
+		.gpio           = D2NET_V2_GPIO_PUSH_BUTTON,
+		.desc           = "Front Push Button",
+		.active_low     = 1,
+	},
+};
+
+static struct gpio_keys_platform_data d2net_v2_button_data = {
+	.buttons	= d2net_v2_buttons,
+	.nbuttons	= ARRAY_SIZE(d2net_v2_buttons),
+};
+
+static struct platform_device d2net_v2_gpio_buttons = {
+	.name		= "gpio-keys",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= &d2net_v2_button_data,
+	},
+};
+
+/*****************************************************************************
+ * GPIO LEDs
+ ****************************************************************************/
+
+#define D2NET_V2_GPIO_RED_LED		12
+
+static struct gpio_led d2net_v2_gpio_led_pins[] = {
+	{
+		.name	= "d2net_v2:red:fail",
+		.gpio	= D2NET_V2_GPIO_RED_LED,
+	},
+};
+
+static struct gpio_led_platform_data d2net_v2_gpio_leds_data = {
+	.num_leds	= ARRAY_SIZE(d2net_v2_gpio_led_pins),
+	.leds		= d2net_v2_gpio_led_pins,
+};
+
+static struct platform_device d2net_v2_gpio_leds = {
+	.name		= "leds-gpio",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= &d2net_v2_gpio_leds_data,
+	},
+};
+
+/*****************************************************************************
+ * Dual-GPIO CPLD LEDs
+ ****************************************************************************/
+
+#define D2NET_V2_GPIO_BLUE_LED_SLOW	29
+#define D2NET_V2_GPIO_BLUE_LED_CMD	30
+
+static struct ns2_led d2net_v2_led_pins[] = {
+	{
+		.name	= "d2net_v2:blue:sata",
+		.cmd	= D2NET_V2_GPIO_BLUE_LED_CMD,
+		.slow	= D2NET_V2_GPIO_BLUE_LED_SLOW,
+	},
+};
+
+static struct ns2_led_platform_data d2net_v2_leds_data = {
+	.num_leds	= ARRAY_SIZE(d2net_v2_led_pins),
+	.leds		= d2net_v2_led_pins,
+};
+
+static struct platform_device d2net_v2_leds = {
+	.name		= "leds-ns2",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= &d2net_v2_leds_data,
+	},
+};
+
+/*****************************************************************************
+ * General Setup
+ ****************************************************************************/
+
+static unsigned int d2net_v2_mpp_config[] __initdata = {
+	MPP0_SPI_SCn,
+	MPP1_SPI_MOSI,
+	MPP2_SPI_SCK,
+	MPP3_SPI_MISO,
+	MPP6_SYSRST_OUTn,
+	MPP7_GPO,		/* Request power-off */
+	MPP8_TW0_SDA,
+	MPP9_TW0_SCK,
+	MPP10_UART0_TXD,
+	MPP11_UART0_RXD,
+	MPP12_GPO,		/* Red led */
+	MPP13_GPIO,		/* Rear power switch (on|auto) */
+	MPP14_GPIO,		/* USB fuse */
+	MPP15_GPIO,		/* Rear power switch (auto|off) */
+	MPP16_GPIO,		/* SATA 0 power */
+	MPP21_SATA0_ACTn,
+	MPP24_GPIO,		/* USB mode select */
+	MPP26_GPIO,		/* USB device vbus */
+	MPP28_GPIO,		/* USB enable host vbus */
+	MPP29_GPIO,		/* Blue led (slow register) */
+	MPP30_GPIO,		/* Blue led (command register) */
+	MPP34_GPIO,		/* Power button (1 = Released, 0 = Pushed) */
+	MPP35_GPIO,		/* Inhibit power-off */
+	0
+};
+
+#define D2NET_V2_GPIO_POWER_OFF		7
+
+static void d2net_v2_power_off(void)
+{
+	gpio_set_value(D2NET_V2_GPIO_POWER_OFF, 1);
+}
+
+static void __init d2net_v2_init(void)
+{
+	/*
+	 * Basic setup. Needs to be called early.
+	 */
+	kirkwood_init();
+	kirkwood_mpp_conf(d2net_v2_mpp_config);
+
+	lacie_v2_hdd_power_init(1);
+
+	kirkwood_ehci_init();
+	kirkwood_ge00_init(&d2net_v2_ge00_data);
+	kirkwood_sata_init(&d2net_v2_sata_data);
+	kirkwood_uart0_init();
+	lacie_v2_register_flash();
+	lacie_v2_register_i2c_devices();
+
+	platform_device_register(&d2net_v2_leds);
+	platform_device_register(&d2net_v2_gpio_leds);
+	platform_device_register(&d2net_v2_gpio_buttons);
+
+	if (gpio_request(D2NET_V2_GPIO_POWER_OFF, "power-off") == 0 &&
+	    gpio_direction_output(D2NET_V2_GPIO_POWER_OFF, 0) == 0)
+		pm_power_off = d2net_v2_power_off;
+	else
+		pr_err("d2net_v2: failed to configure power-off GPIO\n");
+}
+
+MACHINE_START(D2NET_V2, "LaCie d2 Network v2")
+	.boot_params	= 0x00000100,
+	.init_machine	= d2net_v2_init,
+	.map_io		= kirkwood_map_io,
+	.init_irq	= kirkwood_init_irq,
+	.timer		= &lacie_v2_timer,
+MACHINE_END
diff --git a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
index 16f6691..9ea7118 100644
--- a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
+++ b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
@@ -97,8 +97,6 @@
 
 MACHINE_START(DB88F6281_BP, "Marvell DB-88F6281-BP Development Board")
 	/* Maintainer: Saeed Bishara <saeed@marvell.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= db88f6281_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/dockstar-setup.c b/arch/arm/mach-kirkwood/dockstar-setup.c
new file mode 100644
index 0000000..433ea36
--- /dev/null
+++ b/arch/arm/mach-kirkwood/dockstar-setup.c
@@ -0,0 +1,110 @@
+/*
+ * arch/arm/mach-kirkwood/dockstar-setup.c
+ *
+ * Seagate FreeAgent DockStar Setup
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/ata_platform.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mv643xx_eth.h>
+#include <linux/gpio.h>
+#include <linux/leds.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <mach/kirkwood.h>
+#include <plat/mvsdio.h>
+#include "common.h"
+#include "mpp.h"
+
+static struct mtd_partition dockstar_nand_parts[] = {
+	{
+		.name = "u-boot",
+		.offset = 0,
+		.size = SZ_1M
+	}, {
+		.name = "uImage",
+		.offset = MTDPART_OFS_NXTBLK,
+		.size = SZ_4M
+	}, {
+		.name = "root",
+		.offset = MTDPART_OFS_NXTBLK,
+		.size = MTDPART_SIZ_FULL
+	},
+};
+
+static struct mv643xx_eth_platform_data dockstar_ge00_data = {
+	.phy_addr	= MV643XX_ETH_PHY_ADDR(0),
+};
+
+static struct gpio_led dockstar_led_pins[] = {
+	{
+		.name			= "dockstar:green:health",
+		.default_trigger	= "default-on",
+		.gpio			= 46,
+		.active_low		= 1,
+	},
+	{
+		.name			= "dockstar:orange:misc",
+		.default_trigger	= "none",
+		.gpio			= 47,
+		.active_low		= 1,
+	},
+};
+
+static struct gpio_led_platform_data dockstar_led_data = {
+	.leds		= dockstar_led_pins,
+	.num_leds	= ARRAY_SIZE(dockstar_led_pins),
+};
+
+static struct platform_device dockstar_leds = {
+	.name	= "leds-gpio",
+	.id	= -1,
+	.dev	= {
+		.platform_data	= &dockstar_led_data,
+	}
+};
+
+static unsigned int dockstar_mpp_config[] __initdata = {
+	MPP29_GPIO,	/* USB Power Enable */
+	MPP46_GPIO,	/* LED green */
+	MPP47_GPIO,	/* LED orange */
+	0
+};
+
+static void __init dockstar_init(void)
+{
+	/*
+	 * Basic setup. Needs to be called early.
+	 */
+	kirkwood_init();
+
+	/* setup gpio pin select */
+	kirkwood_mpp_conf(dockstar_mpp_config);
+
+	kirkwood_uart0_init();
+	kirkwood_nand_init(ARRAY_AND_SIZE(dockstar_nand_parts), 25);
+
+	if (gpio_request(29, "USB Power Enable") != 0 ||
+	    gpio_direction_output(29, 1) != 0)
+		printk(KERN_ERR "can't set up GPIO 29 (USB Power Enable)\n");
+	kirkwood_ehci_init();
+
+	kirkwood_ge00_init(&dockstar_ge00_data);
+
+	platform_device_register(&dockstar_leds);
+}
+
+MACHINE_START(DOCKSTAR, "Seagate FreeAgent DockStar")
+	.boot_params	= 0x00000100,
+	.init_machine	= dockstar_init,
+	.map_io		= kirkwood_map_io,
+	.init_irq	= kirkwood_init_irq,
+	.timer		= &kirkwood_timer,
+MACHINE_END
diff --git a/arch/arm/mach-kirkwood/guruplug-setup.c b/arch/arm/mach-kirkwood/guruplug-setup.c
index 54d07c8..8f47dc0 100644
--- a/arch/arm/mach-kirkwood/guruplug-setup.c
+++ b/arch/arm/mach-kirkwood/guruplug-setup.c
@@ -121,8 +121,6 @@
 
 MACHINE_START(GURUPLUG, "Marvell GuruPlug Reference Board")
 	/* Maintainer: Siddarth Gore <gores@marvell.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= guruplug_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/include/mach/debug-macro.S b/arch/arm/mach-kirkwood/include/mach/debug-macro.S
index d060677..db06ae43 100644
--- a/arch/arm/mach-kirkwood/include/mach/debug-macro.S
+++ b/arch/arm/mach-kirkwood/include/mach/debug-macro.S
@@ -8,12 +8,11 @@
 
 #include <mach/bridge-regs.h>
 
-	.macro	addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1					@ MMU enabled?
-	ldreq	\rx, =KIRKWOOD_REGS_PHYS_BASE
-	ldrne	\rx, =KIRKWOOD_REGS_VIRT_BASE
-	orr	\rx, \rx, #0x00012000
+	.macro	addruart, rp, rv
+	ldr	\rp, =KIRKWOOD_REGS_PHYS_BASE
+	ldr	\rv, =KIRKWOOD_REGS_VIRT_BASE
+	orr	\rp, \rp, #0x00012000
+	orr	\rv, \rv, #0x00012000
 	.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-kirkwood/include/mach/leds-netxbig.h b/arch/arm/mach-kirkwood/include/mach/leds-netxbig.h
new file mode 100644
index 0000000..24b536e
--- /dev/null
+++ b/arch/arm/mach-kirkwood/include/mach/leds-netxbig.h
@@ -0,0 +1,55 @@
+/*
+ * arch/arm/mach-kirkwood/include/mach/leds-netxbig.h
+ *
+ * Platform data structure for netxbig LED driver
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __MACH_LEDS_NETXBIG_H
+#define __MACH_LEDS_NETXBIG_H
+
+struct netxbig_gpio_ext {
+	unsigned	*addr;
+	int		num_addr;
+	unsigned	*data;
+	int		num_data;
+	unsigned	enable;
+};
+
+enum netxbig_led_mode {
+	NETXBIG_LED_OFF,
+	NETXBIG_LED_ON,
+	NETXBIG_LED_SATA,
+	NETXBIG_LED_TIMER1,
+	NETXBIG_LED_TIMER2,
+	NETXBIG_LED_MODE_NUM,
+};
+
+#define NETXBIG_LED_INVALID_MODE NETXBIG_LED_MODE_NUM
+
+struct netxbig_led_timer {
+	unsigned long		delay_on;
+	unsigned long		delay_off;
+	enum netxbig_led_mode	mode;
+};
+
+struct netxbig_led {
+	const char	*name;
+	const char	*default_trigger;
+	int		mode_addr;
+	int		*mode_val;
+	int		bright_addr;
+};
+
+struct netxbig_led_platform_data {
+	struct netxbig_gpio_ext	*gpio_ext;
+	struct netxbig_led_timer *timer;
+	int			num_timer;
+	struct netxbig_led	*leds;
+	int			num_leds;
+};
+
+#endif /* __MACH_LEDS_NETXBIG_H */
diff --git a/arch/arm/mach-kirkwood/lacie_v2-common.c b/arch/arm/mach-kirkwood/lacie_v2-common.c
new file mode 100644
index 0000000..d3ea1b6
--- /dev/null
+++ b/arch/arm/mach-kirkwood/lacie_v2-common.c
@@ -0,0 +1,127 @@
+/*
+ * arch/arm/mach-kirkwood/lacie_v2-common.c
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mtd/physmap.h>
+#include <linux/spi/flash.h>
+#include <linux/spi/spi.h>
+#include <linux/i2c.h>
+#include <linux/i2c/at24.h>
+#include <linux/gpio.h>
+#include <asm/mach/time.h>
+#include <mach/kirkwood.h>
+#include <mach/irqs.h>
+#include <plat/time.h>
+#include "common.h"
+
+/*****************************************************************************
+ * 512KB SPI Flash on Boot Device (MACRONIX MX25L4005)
+ ****************************************************************************/
+
+static struct mtd_partition lacie_v2_flash_parts[] = {
+	{
+		.name = "u-boot",
+		.size = MTDPART_SIZ_FULL,
+		.offset = 0,
+		.mask_flags = MTD_WRITEABLE, /* force read-only */
+	},
+};
+
+static const struct flash_platform_data lacie_v2_flash = {
+	.type		= "mx25l4005a",
+	.name		= "spi_flash",
+	.parts		= lacie_v2_flash_parts,
+	.nr_parts	= ARRAY_SIZE(lacie_v2_flash_parts),
+};
+
+static struct spi_board_info __initdata lacie_v2_spi_slave_info[] = {
+	{
+		.modalias	= "m25p80",
+		.platform_data	= &lacie_v2_flash,
+		.irq		= -1,
+		.max_speed_hz	= 20000000,
+		.bus_num	= 0,
+		.chip_select	= 0,
+	},
+};
+
+void __init lacie_v2_register_flash(void)
+{
+	spi_register_board_info(lacie_v2_spi_slave_info,
+				ARRAY_SIZE(lacie_v2_spi_slave_info));
+	kirkwood_spi_init();
+}
+
+/*****************************************************************************
+ * I2C devices
+ ****************************************************************************/
+
+static struct at24_platform_data at24c04 = {
+	.byte_len	= SZ_4K / 8,
+	.page_size	= 16,
+};
+
+/*
+ * i2c addr | chip         | description
+ * 0x50     | HT24LC04     | eeprom (512B)
+ */
+
+static struct i2c_board_info __initdata lacie_v2_i2c_info[] = {
+	{
+		I2C_BOARD_INFO("24c04", 0x50),
+		.platform_data  = &at24c04,
+	}
+};
+
+void __init lacie_v2_register_i2c_devices(void)
+{
+	kirkwood_i2c_init();
+	i2c_register_board_info(0, lacie_v2_i2c_info,
+				ARRAY_SIZE(lacie_v2_i2c_info));
+}
+
+/*****************************************************************************
+ * Hard Disk power
+ ****************************************************************************/
+
+static int __initdata lacie_v2_gpio_hdd_power[] = { 16, 17, 41, 42, 43 };
+
+void __init lacie_v2_hdd_power_init(int hdd_num)
+{
+	int i;
+	int err;
+
+	/* Power up all hard disks. */
+	for (i = 0; i < hdd_num; i++) {
+		err = gpio_request(lacie_v2_gpio_hdd_power[i], NULL);
+		if (err == 0) {
+			err = gpio_direction_output(
+					lacie_v2_gpio_hdd_power[i], 1);
+			/* Free the HDD power GPIOs. This allow user-space to
+			 * configure them via the gpiolib sysfs interface. */
+			gpio_free(lacie_v2_gpio_hdd_power[i]);
+		}
+		if (err)
+			pr_err("Failed to power up HDD%d\n", i + 1);
+	}
+}
+
+/*****************************************************************************
+ * Timer
+ ****************************************************************************/
+
+static void lacie_v2_timer_init(void)
+{
+	kirkwood_tclk = 166666667;
+	orion_time_init(IRQ_KIRKWOOD_BRIDGE, kirkwood_tclk);
+}
+
+struct sys_timer lacie_v2_timer = {
+	.init = lacie_v2_timer_init,
+};
diff --git a/arch/arm/mach-kirkwood/lacie_v2-common.h b/arch/arm/mach-kirkwood/lacie_v2-common.h
new file mode 100644
index 0000000..af52131
--- /dev/null
+++ b/arch/arm/mach-kirkwood/lacie_v2-common.h
@@ -0,0 +1,18 @@
+/*
+ * arch/arm/mach-kirkwood/lacie_v2-common.h
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __ARCH_KIRKWOOD_LACIE_V2_COMMON_H
+#define __ARCH_KIRKWOOD_LACIE_V2_COMMON_H
+
+void lacie_v2_register_flash(void);
+void lacie_v2_register_i2c_devices(void);
+void lacie_v2_hdd_power_init(int hdd_num);
+
+extern struct sys_timer lacie_v2_timer;
+
+#endif
diff --git a/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c b/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
index c6b92b4..1e5266f 100644
--- a/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
+++ b/arch/arm/mach-kirkwood/mv88f6281gtw_ge-setup.c
@@ -163,8 +163,6 @@
 
 MACHINE_START(MV88F6281GTW_GE, "Marvell 88F6281 GTW GE Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= mv88f6281gtw_ge_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/netspace_v2-setup.c b/arch/arm/mach-kirkwood/netspace_v2-setup.c
index d26bf32..5e28644 100644
--- a/arch/arm/mach-kirkwood/netspace_v2-setup.c
+++ b/arch/arm/mach-kirkwood/netspace_v2-setup.c
@@ -24,56 +24,19 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/mtd/physmap.h>
-#include <linux/spi/flash.h>
-#include <linux/spi/spi.h>
 #include <linux/ata_platform.h>
 #include <linux/mv643xx_eth.h>
-#include <linux/i2c.h>
-#include <linux/i2c/at24.h>
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/gpio_keys.h>
 #include <linux/leds.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <asm/mach/time.h>
 #include <mach/kirkwood.h>
 #include <mach/leds-ns2.h>
-#include <plat/time.h>
 #include "common.h"
 #include "mpp.h"
-
-/*****************************************************************************
- * 512KB SPI Flash on Boot Device (MACRONIX MX25L4005)
- ****************************************************************************/
-
-static struct mtd_partition netspace_v2_flash_parts[] = {
-	{
-		.name = "u-boot",
-		.size = MTDPART_SIZ_FULL,
-		.offset = 0,
-		.mask_flags = MTD_WRITEABLE, /* force read-only */
-	},
-};
-
-static const struct flash_platform_data netspace_v2_flash = {
-	.type		= "mx25l4005a",
-	.name		= "spi_flash",
-	.parts		= netspace_v2_flash_parts,
-	.nr_parts	= ARRAY_SIZE(netspace_v2_flash_parts),
-};
-
-static struct spi_board_info __initdata netspace_v2_spi_slave_info[] = {
-	{
-		.modalias	= "m25p80",
-		.platform_data	= &netspace_v2_flash,
-		.irq		= -1,
-		.max_speed_hz	= 20000000,
-		.bus_num	= 0,
-		.chip_select	= 0,
-	},
-};
+#include "lacie_v2-common.h"
 
 /*****************************************************************************
  * Ethernet
@@ -84,27 +47,6 @@
 };
 
 /*****************************************************************************
- * I2C devices
- ****************************************************************************/
-
-static struct at24_platform_data at24c04 = {
-	.byte_len	= SZ_4K / 8,
-	.page_size	= 16,
-};
-
-/*
- * i2c addr | chip         | description
- * 0x50     | HT24LC04     | eeprom (512B)
- */
-
-static struct i2c_board_info __initdata netspace_v2_i2c_info[] = {
-	{
-		I2C_BOARD_INFO("24c04", 0x50),
-		.platform_data  = &at24c04,
-	}
-};
-
-/*****************************************************************************
  * SATA
  ****************************************************************************/
 
@@ -112,35 +54,6 @@
 	.n_ports	= 2,
 };
 
-#define NETSPACE_V2_GPIO_SATA0_POWER	16
-#define NETSPACE_V2_GPIO_SATA1_POWER	17
-
-static void __init netspace_v2_sata_power_init(void)
-{
-	int err;
-
-	err = gpio_request(NETSPACE_V2_GPIO_SATA0_POWER, "SATA0 power");
-	if (err == 0) {
-		err = gpio_direction_output(NETSPACE_V2_GPIO_SATA0_POWER, 1);
-		if (err)
-			gpio_free(NETSPACE_V2_GPIO_SATA0_POWER);
-	}
-	if (err)
-		pr_err("netspace_v2: failed to setup SATA0 power\n");
-
-	if (machine_is_netspace_max_v2()) {
-		err = gpio_request(NETSPACE_V2_GPIO_SATA1_POWER, "SATA1 power");
-		if (err == 0) {
-			err = gpio_direction_output(
-					NETSPACE_V2_GPIO_SATA1_POWER, 1);
-			if (err)
-				gpio_free(NETSPACE_V2_GPIO_SATA1_POWER);
-		}
-		if (err)
-			pr_err("netspace_v2: failed to setup SATA1 power\n");
-	}
-}
-
 /*****************************************************************************
  * GPIO keys
  ****************************************************************************/
@@ -224,20 +137,6 @@
 };
 
 /*****************************************************************************
- * Timer
- ****************************************************************************/
-
-static void netspace_v2_timer_init(void)
-{
-	kirkwood_tclk = 166666667;
-	orion_time_init(IRQ_KIRKWOOD_BRIDGE, kirkwood_tclk);
-}
-
-struct sys_timer netspace_v2_timer = {
-	.init = netspace_v2_timer_init,
-};
-
-/*****************************************************************************
  * General Setup
  ****************************************************************************/
 
@@ -291,18 +190,17 @@
 	kirkwood_init();
 	kirkwood_mpp_conf(netspace_v2_mpp_config);
 
-	netspace_v2_sata_power_init();
+	if (machine_is_netspace_max_v2())
+		lacie_v2_hdd_power_init(2);
+	else
+		lacie_v2_hdd_power_init(1);
 
 	kirkwood_ehci_init();
 	kirkwood_ge00_init(&netspace_v2_ge00_data);
 	kirkwood_sata_init(&netspace_v2_sata_data);
 	kirkwood_uart0_init();
-	spi_register_board_info(netspace_v2_spi_slave_info,
-				ARRAY_SIZE(netspace_v2_spi_slave_info));
-	kirkwood_spi_init();
-	kirkwood_i2c_init();
-	i2c_register_board_info(0, netspace_v2_i2c_info,
-				ARRAY_SIZE(netspace_v2_i2c_info));
+	lacie_v2_register_flash();
+	lacie_v2_register_i2c_devices();
 
 	platform_device_register(&netspace_v2_leds);
 	platform_device_register(&netspace_v2_gpio_leds);
@@ -317,36 +215,30 @@
 
 #ifdef CONFIG_MACH_NETSPACE_V2
 MACHINE_START(NETSPACE_V2, "LaCie Network Space v2")
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &netspace_v2_timer,
+	.timer		= &lacie_v2_timer,
 MACHINE_END
 #endif
 
 #ifdef CONFIG_MACH_INETSPACE_V2
 MACHINE_START(INETSPACE_V2, "LaCie Internet Space v2")
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &netspace_v2_timer,
+	.timer		= &lacie_v2_timer,
 MACHINE_END
 #endif
 
 #ifdef CONFIG_MACH_NETSPACE_MAX_V2
 MACHINE_START(NETSPACE_MAX_V2, "LaCie Network Space Max v2")
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &netspace_v2_timer,
+	.timer		= &lacie_v2_timer,
 MACHINE_END
 #endif
diff --git a/arch/arm/mach-kirkwood/netxbig_v2-setup.c b/arch/arm/mach-kirkwood/netxbig_v2-setup.c
index 2bd14c5..a1b45d5 100644
--- a/arch/arm/mach-kirkwood/netxbig_v2-setup.c
+++ b/arch/arm/mach-kirkwood/netxbig_v2-setup.c
@@ -23,55 +23,19 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/mtd/physmap.h>
-#include <linux/spi/flash.h>
-#include <linux/spi/spi.h>
 #include <linux/ata_platform.h>
 #include <linux/mv643xx_eth.h>
-#include <linux/i2c.h>
-#include <linux/i2c/at24.h>
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/gpio_keys.h>
 #include <linux/leds.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <asm/mach/time.h>
 #include <mach/kirkwood.h>
-#include <plat/time.h>
+#include <mach/leds-netxbig.h>
 #include "common.h"
 #include "mpp.h"
-
-/*****************************************************************************
- * 512KB SPI Flash on Boot Device (MACRONIX MX25L4005)
- ****************************************************************************/
-
-static struct mtd_partition netxbig_v2_flash_parts[] = {
-	{
-		.name = "u-boot",
-		.size = MTDPART_SIZ_FULL,
-		.offset = 0,
-		.mask_flags = MTD_WRITEABLE, /* force read-only */
-	},
-};
-
-static const struct flash_platform_data netxbig_v2_flash = {
-	.type		= "mx25l4005a",
-	.name		= "spi_flash",
-	.parts		= netxbig_v2_flash_parts,
-	.nr_parts	= ARRAY_SIZE(netxbig_v2_flash_parts),
-};
-
-static struct spi_board_info __initdata netxbig_v2_spi_slave_info[] = {
-	{
-		.modalias	= "m25p80",
-		.platform_data	= &netxbig_v2_flash,
-		.irq		= -1,
-		.max_speed_hz	= 20000000,
-		.bus_num	= 0,
-		.chip_select	= 0,
-	},
-};
+#include "lacie_v2-common.h"
 
 /*****************************************************************************
  * Ethernet
@@ -86,27 +50,6 @@
 };
 
 /*****************************************************************************
- * I2C devices
- ****************************************************************************/
-
-static struct at24_platform_data at24c04 = {
-	.byte_len	= SZ_4K / 8,
-	.page_size	= 16,
-};
-
-/*
- * i2c addr | chip         | description
- * 0x50     | HT24LC04     | eeprom (512B)
- */
-
-static struct i2c_board_info __initdata netxbig_v2_i2c_info[] = {
-	{
-		I2C_BOARD_INFO("24c04", 0x50),
-		.platform_data  = &at24c04,
-	}
-};
-
-/*****************************************************************************
  * SATA
  ****************************************************************************/
 
@@ -114,34 +57,6 @@
 	.n_ports	= 2,
 };
 
-static int __initdata netxbig_v2_gpio_hdd_power[] = { 16, 17, 41, 42, 43 };
-
-static void __init netxbig_v2_sata_power_init(void)
-{
-	int i;
-	int err;
-	int hdd_nb;
-
-	if (machine_is_net2big_v2())
-		hdd_nb = 2;
-	else
-		hdd_nb = 5;
-
-	/* Power up all hard disks. */
-	for (i = 0; i < hdd_nb; i++) {
-		err = gpio_request(netxbig_v2_gpio_hdd_power[i], NULL);
-		if (err == 0) {
-			err = gpio_direction_output(
-					netxbig_v2_gpio_hdd_power[i], 1);
-			/* Free the HDD power GPIOs. This allow user-space to
-			 * configure them via the gpiolib sysfs interface. */
-			gpio_free(netxbig_v2_gpio_hdd_power[i]);
-		}
-		if (err)
-			pr_err("netxbig_v2: failed to power up HDD%d\n", i + 1);
-	}
-}
-
 /*****************************************************************************
  * GPIO keys
  ****************************************************************************/
@@ -190,7 +105,7 @@
 };
 
 /*****************************************************************************
- * GPIO LEDs
+ * GPIO extension LEDs
  ****************************************************************************/
 
 /*
@@ -200,19 +115,32 @@
  * - address register : bit [0-2] -> GPIO [47-49]
  * - data register    : bit [0-2] -> GPIO [44-46]
  * - enable register  : GPIO 29
- *
+ */
+
+static int netxbig_v2_gpio_ext_addr[] = { 47, 48, 49 };
+static int netxbig_v2_gpio_ext_data[] = { 44, 45, 46 };
+
+static struct netxbig_gpio_ext netxbig_v2_gpio_ext = {
+	.addr		= netxbig_v2_gpio_ext_addr,
+	.num_addr	= ARRAY_SIZE(netxbig_v2_gpio_ext_addr),
+	.data		= netxbig_v2_gpio_ext_data,
+	.num_data	= ARRAY_SIZE(netxbig_v2_gpio_ext_data),
+	.enable		= 29,
+};
+
+/*
  * Address register selection:
  *
  * addr | register
  * ----------------------------
  *   0  | front LED
  *   1  | front LED brightness
- *   2  | HDD LED brightness
- *   3  | HDD1 LED
- *   4  | HDD2 LED
- *   5  | HDD3 LED
- *   6  | HDD4 LED
- *   7  | HDD5 LED
+ *   2  | SATA LED brightness
+ *   3  | SATA0 LED
+ *   4  | SATA1 LED
+ *   5  | SATA2 LED
+ *   6  | SATA3 LED
+ *   7  | SATA4 LED
  *
  * Data register configuration:
  *
@@ -233,30 +161,107 @@
  *   6  | blink blue on=1 sec and red on=1 sec
  *   7  | blink blue on=0.5 sec and blue off=2.5 sec
  *
- * data | HDD LED mode
+ * data | SATA LED mode
  * -------------------------------------------------
- *   0  | fix blue on
+ *   0  | fix off
  *   1  | SATA activity blink
  *   2  | fix red on
  *   3  | blink blue on=1 sec and blue off=1 sec
  *   4  | blink red on=1 sec and red off=1 sec
  *   5  | blink blue on=2.5 sec and red on=0.5 sec
  *   6  | blink blue on=1 sec and red on=1 sec
- *   7  | blink blue on=0.5 sec and blue off=2.5 sec
+ *   7  | fix blue on
  */
 
-/*****************************************************************************
- * Timer
- ****************************************************************************/
+static int netxbig_v2_red_mled[NETXBIG_LED_MODE_NUM] = {
+	[NETXBIG_LED_OFF]	= 0,
+	[NETXBIG_LED_ON]	= 2,
+	[NETXBIG_LED_SATA]	= NETXBIG_LED_INVALID_MODE,
+	[NETXBIG_LED_TIMER1]	= 4,
+	[NETXBIG_LED_TIMER2]	= NETXBIG_LED_INVALID_MODE,
+};
 
-static void netxbig_v2_timer_init(void)
-{
-	kirkwood_tclk = 166666667;
-	orion_time_init(IRQ_KIRKWOOD_BRIDGE, kirkwood_tclk);
-}
+static int netxbig_v2_blue_pwr_mled[NETXBIG_LED_MODE_NUM] = {
+	[NETXBIG_LED_OFF]	= 0,
+	[NETXBIG_LED_ON]	= 1,
+	[NETXBIG_LED_SATA]	= NETXBIG_LED_INVALID_MODE,
+	[NETXBIG_LED_TIMER1]	= 3,
+	[NETXBIG_LED_TIMER2]	= 7,
+};
 
-struct sys_timer netxbig_v2_timer = {
-	.init = netxbig_v2_timer_init,
+static int netxbig_v2_blue_sata_mled[NETXBIG_LED_MODE_NUM] = {
+	[NETXBIG_LED_OFF]	= 0,
+	[NETXBIG_LED_ON]	= 7,
+	[NETXBIG_LED_SATA]	= 1,
+	[NETXBIG_LED_TIMER1]	= 3,
+	[NETXBIG_LED_TIMER2]	= NETXBIG_LED_INVALID_MODE,
+};
+
+static struct netxbig_led_timer netxbig_v2_led_timer[] = {
+	[0] = {
+		.delay_on	= 500,
+		.delay_off	= 500,
+		.mode		= NETXBIG_LED_TIMER1,
+	},
+	[1] = {
+		.delay_on	= 500,
+		.delay_off	= 1000,
+		.mode		= NETXBIG_LED_TIMER2,
+	},
+};
+
+#define NETXBIG_LED(_name, maddr, mval, baddr)			\
+	{ .name		= _name,				\
+	  .mode_addr	= maddr,				\
+	  .mode_val	= mval,					\
+	  .bright_addr	= baddr }
+
+static struct netxbig_led net2big_v2_leds_ctrl[] = {
+	NETXBIG_LED("net2big-v2:blue:power", 0, netxbig_v2_blue_pwr_mled,  1),
+	NETXBIG_LED("net2big-v2:red:power",  0, netxbig_v2_red_mled,       1),
+	NETXBIG_LED("net2big-v2:blue:sata0", 3, netxbig_v2_blue_sata_mled, 2),
+	NETXBIG_LED("net2big-v2:red:sata0",  3, netxbig_v2_red_mled,       2),
+	NETXBIG_LED("net2big-v2:blue:sata1", 4, netxbig_v2_blue_sata_mled, 2),
+	NETXBIG_LED("net2big-v2:red:sata1",  4, netxbig_v2_red_mled,       2),
+};
+
+static struct netxbig_led_platform_data net2big_v2_leds_data = {
+	.gpio_ext	= &netxbig_v2_gpio_ext,
+	.timer		= netxbig_v2_led_timer,
+	.num_timer	= ARRAY_SIZE(netxbig_v2_led_timer),
+	.leds		= net2big_v2_leds_ctrl,
+	.num_leds	= ARRAY_SIZE(net2big_v2_leds_ctrl),
+};
+
+static struct netxbig_led net5big_v2_leds_ctrl[] = {
+	NETXBIG_LED("net5big-v2:blue:power", 0, netxbig_v2_blue_pwr_mled,  1),
+	NETXBIG_LED("net5big-v2:red:power",  0, netxbig_v2_red_mled,       1),
+	NETXBIG_LED("net5big-v2:blue:sata0", 3, netxbig_v2_blue_sata_mled, 2),
+	NETXBIG_LED("net5big-v2:red:sata0",  3, netxbig_v2_red_mled,       2),
+	NETXBIG_LED("net5big-v2:blue:sata1", 4, netxbig_v2_blue_sata_mled, 2),
+	NETXBIG_LED("net5big-v2:red:sata1",  4, netxbig_v2_red_mled,       2),
+	NETXBIG_LED("net5big-v2:blue:sata2", 5, netxbig_v2_blue_sata_mled, 2),
+	NETXBIG_LED("net5big-v2:red:sata2",  5, netxbig_v2_red_mled,       2),
+	NETXBIG_LED("net5big-v2:blue:sata3", 6, netxbig_v2_blue_sata_mled, 2),
+	NETXBIG_LED("net5big-v2:red:sata3",  6, netxbig_v2_red_mled,       2),
+	NETXBIG_LED("net5big-v2:blue:sata4", 7, netxbig_v2_blue_sata_mled, 2),
+	NETXBIG_LED("net5big-v2:red:sata5",  7, netxbig_v2_red_mled,       2),
+};
+
+static struct netxbig_led_platform_data net5big_v2_leds_data = {
+	.gpio_ext	= &netxbig_v2_gpio_ext,
+	.timer		= netxbig_v2_led_timer,
+	.num_timer	= ARRAY_SIZE(netxbig_v2_led_timer),
+	.leds		= net5big_v2_leds_ctrl,
+	.num_leds	= ARRAY_SIZE(net5big_v2_leds_ctrl),
+};
+
+static struct platform_device netxbig_v2_leds = {
+	.name		= "leds-netxbig",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= &net2big_v2_leds_data,
+	},
 };
 
 /*****************************************************************************
@@ -284,18 +289,18 @@
 	MPP24_GPIO,		/* USB mode select */
 	MPP26_GPIO,		/* USB device vbus */
 	MPP28_GPIO,		/* USB enable host vbus */
-	MPP29_GPIO,		/* CPLD extension ALE */
+	MPP29_GPIO,		/* GPIO extension ALE */
 	MPP34_GPIO,		/* Rear Push button */
 	MPP35_GPIO,		/* Inhibit switch power-off */
 	MPP36_GPIO,		/* SATA HDD1 presence */
 	MPP37_GPIO,		/* SATA HDD2 presence */
 	MPP40_GPIO,		/* eSATA presence */
-	MPP44_GPIO,		/* CPLD extension (data 0) */
-	MPP45_GPIO,		/* CPLD extension (data 1) */
-	MPP46_GPIO,		/* CPLD extension (data 2) */
-	MPP47_GPIO,		/* CPLD extension (addr 0) */
-	MPP48_GPIO,		/* CPLD extension (addr 1) */
-	MPP49_GPIO,		/* CPLD extension (addr 2) */
+	MPP44_GPIO,		/* GPIO extension (data 0) */
+	MPP45_GPIO,		/* GPIO extension (data 1) */
+	MPP46_GPIO,		/* GPIO extension (data 2) */
+	MPP47_GPIO,		/* GPIO extension (addr 0) */
+	MPP48_GPIO,		/* GPIO extension (addr 1) */
+	MPP49_GPIO,		/* GPIO extension (addr 2) */
 	0
 };
 
@@ -324,7 +329,7 @@
 	MPP26_GE1_RXD2,
 	MPP27_GE1_RXD3,
 	MPP28_GPIO,		/* USB enable host vbus */
-	MPP29_GPIO,		/* CPLD extension ALE */
+	MPP29_GPIO,		/* GPIO extension ALE */
 	MPP30_GE1_RXCTL,
 	MPP31_GE1_RXCLK,
 	MPP32_GE1_TCLKOUT,
@@ -339,12 +344,12 @@
 	MPP41_GPIO,		/* SATA HDD3 power */
 	MPP42_GPIO,		/* SATA HDD4 power */
 	MPP43_GPIO,		/* SATA HDD5 power */
-	MPP44_GPIO,		/* CPLD extension (data 0) */
-	MPP45_GPIO,		/* CPLD extension (data 1) */
-	MPP46_GPIO,		/* CPLD extension (data 2) */
-	MPP47_GPIO,		/* CPLD extension (addr 0) */
-	MPP48_GPIO,		/* CPLD extension (addr 1) */
-	MPP49_GPIO,		/* CPLD extension (addr 2) */
+	MPP44_GPIO,		/* GPIO extension (data 0) */
+	MPP45_GPIO,		/* GPIO extension (data 1) */
+	MPP46_GPIO,		/* GPIO extension (data 2) */
+	MPP47_GPIO,		/* GPIO extension (addr 0) */
+	MPP48_GPIO,		/* GPIO extension (addr 1) */
+	MPP49_GPIO,		/* GPIO extension (addr 2) */
 	0
 };
 
@@ -366,7 +371,10 @@
 	else
 		kirkwood_mpp_conf(net5big_v2_mpp_config);
 
-	netxbig_v2_sata_power_init();
+	if (machine_is_net2big_v2())
+		lacie_v2_hdd_power_init(2);
+	else
+		lacie_v2_hdd_power_init(5);
 
 	kirkwood_ehci_init();
 	kirkwood_ge00_init(&netxbig_v2_ge00_data);
@@ -374,13 +382,12 @@
 		kirkwood_ge01_init(&netxbig_v2_ge01_data);
 	kirkwood_sata_init(&netxbig_v2_sata_data);
 	kirkwood_uart0_init();
-	spi_register_board_info(netxbig_v2_spi_slave_info,
-				ARRAY_SIZE(netxbig_v2_spi_slave_info));
-	kirkwood_spi_init();
-	kirkwood_i2c_init();
-	i2c_register_board_info(0, netxbig_v2_i2c_info,
-				ARRAY_SIZE(netxbig_v2_i2c_info));
+	lacie_v2_register_flash();
+	lacie_v2_register_i2c_devices();
 
+	if (machine_is_net5big_v2())
+		netxbig_v2_leds.dev.platform_data = &net5big_v2_leds_data;
+	platform_device_register(&netxbig_v2_leds);
 	platform_device_register(&netxbig_v2_gpio_buttons);
 
 	if (gpio_request(NETXBIG_V2_GPIO_POWER_OFF, "power-off") == 0 &&
@@ -392,24 +399,20 @@
 
 #ifdef CONFIG_MACH_NET2BIG_V2
 MACHINE_START(NET2BIG_V2, "LaCie 2Big Network v2")
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= netxbig_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &netxbig_v2_timer,
+	.timer		= &lacie_v2_timer,
 MACHINE_END
 #endif
 
 #ifdef CONFIG_MACH_NET5BIG_V2
 MACHINE_START(NET5BIG_V2, "LaCie 5Big Network v2")
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= netxbig_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &netxbig_v2_timer,
+	.timer		= &lacie_v2_timer,
 MACHINE_END
 #endif
diff --git a/arch/arm/mach-kirkwood/openrd-setup.c b/arch/arm/mach-kirkwood/openrd-setup.c
index fd06be6..c9d77fa 100644
--- a/arch/arm/mach-kirkwood/openrd-setup.c
+++ b/arch/arm/mach-kirkwood/openrd-setup.c
@@ -16,6 +16,7 @@
 #include <linux/ata_platform.h>
 #include <linux/mv643xx_eth.h>
 #include <linux/i2c.h>
+#include <linux/gpio.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <mach/kirkwood.h>
@@ -57,7 +58,22 @@
 };
 
 static unsigned int openrd_mpp_config[] __initdata = {
+	MPP12_SD_CLK,
+	MPP13_SD_CMD,
+	MPP14_SD_D0,
+	MPP15_SD_D1,
+	MPP16_SD_D2,
+	MPP17_SD_D3,
+	MPP28_GPIO,
 	MPP29_GPIO,
+	MPP34_GPIO,
+	0
+};
+
+/* Configure MPP for UART1 */
+static unsigned int openrd_uart1_mpp_config[] __initdata = {
+	MPP13_UART1_TXD,
+	MPP14_UART1_RXD,
 	0
 };
 
@@ -67,6 +83,68 @@
 	},
 };
 
+static int __initdata uart1;
+
+static int __init sd_uart_selection(char *str)
+{
+	uart1 = -EINVAL;
+
+	/* Default is SD. Change if required, for UART */
+	if (!str)
+		return 0;
+
+	if (!strncmp(str, "232", 3)) {
+		uart1 = 232;
+	} else if (!strncmp(str, "485", 3)) {
+		/* OpenRD-Base doesn't have RS485. Treat is as an
+		 * unknown argument & just have default setting -
+		 * which is SD */
+		if (machine_is_openrd_base()) {
+			uart1 = -ENODEV;
+			return 1;
+		}
+
+		uart1 = 485;
+	}
+	return 1;
+}
+/* Parse boot_command_line string kw_openrd_init_uart1=232/485 */
+__setup("kw_openrd_init_uart1=", sd_uart_selection);
+
+static int __init uart1_mpp_config(void)
+{
+	kirkwood_mpp_conf(openrd_uart1_mpp_config);
+
+	if (gpio_request(34, "SD_UART1_SEL")) {
+		printk(KERN_ERR "GPIO request failed for SD/UART1 selection"
+				", gpio: 34\n");
+		return -EIO;
+	}
+
+	if (gpio_request(28, "RS232_RS485_SEL")) {
+		printk(KERN_ERR "GPIO request failed for RS232/RS485 selection"
+				", gpio# 28\n");
+		gpio_free(34);
+		return -EIO;
+	}
+
+	/* Select UART1
+	 * Pin # 34: 0 => UART1, 1 => SD */
+	gpio_direction_output(34, 0);
+
+	/* Select RS232 OR RS485
+	 * Pin # 28: 0 => RS232, 1 => RS485 */
+	if (uart1 == 232)
+		gpio_direction_output(28, 0);
+	else
+		gpio_direction_output(28, 1);
+
+	gpio_free(34);
+	gpio_free(28);
+
+	return 0;
+}
+
 static void __init openrd_init(void)
 {
 	/*
@@ -90,7 +168,6 @@
 		kirkwood_ge01_init(&openrd_ge01_data);
 
 	kirkwood_sata_init(&openrd_sata_data);
-	kirkwood_sdio_init(&openrd_mvsdio_data);
 
 	kirkwood_i2c_init();
 
@@ -99,6 +176,28 @@
 			ARRAY_SIZE(i2c_board_info));
 		kirkwood_audio_init();
 	}
+
+	if (uart1 <= 0) {
+		if (uart1 < 0)
+			printk(KERN_ERR "Invalid kernel parameter to select "
+				"UART1. Defaulting to SD. ERROR CODE: %d\n",
+				uart1);
+
+		/* Select SD
+		 * Pin # 34: 0 => UART1, 1 => SD */
+		if (gpio_request(34, "SD_UART1_SEL")) {
+			printk(KERN_ERR "GPIO request failed for SD/UART1 "
+					"selection, gpio: 34\n");
+		} else {
+
+			gpio_direction_output(34, 1);
+			gpio_free(34);
+			kirkwood_sdio_init(&openrd_mvsdio_data);
+		}
+	} else {
+		if (!uart1_mpp_config())
+			kirkwood_uart1_init();
+	}
 }
 
 static int __init openrd_pci_init(void)
@@ -115,8 +214,6 @@
 #ifdef CONFIG_MACH_OPENRD_BASE
 MACHINE_START(OPENRD_BASE, "Marvell OpenRD Base Board")
 	/* Maintainer: Dhaval Vasa <dhaval.vasa@einfochips.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= openrd_init,
 	.map_io		= kirkwood_map_io,
@@ -128,8 +225,6 @@
 #ifdef CONFIG_MACH_OPENRD_CLIENT
 MACHINE_START(OPENRD_CLIENT, "Marvell OpenRD Client Board")
 	/* Maintainer: Dhaval Vasa <dhaval.vasa@einfochips.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= openrd_init,
 	.map_io		= kirkwood_map_io,
@@ -141,8 +236,6 @@
 #ifdef CONFIG_MACH_OPENRD_ULTIMATE
 MACHINE_START(OPENRD_ULTIMATE, "Marvell OpenRD Ultimate Board")
 	/* Maintainer: Dhaval Vasa <dhaval.vasa@einfochips.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= openrd_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/rd88f6192-nas-setup.c b/arch/arm/mach-kirkwood/rd88f6192-nas-setup.c
index c34718c..0049614 100644
--- a/arch/arm/mach-kirkwood/rd88f6192-nas-setup.c
+++ b/arch/arm/mach-kirkwood/rd88f6192-nas-setup.c
@@ -79,8 +79,6 @@
 
 MACHINE_START(RD88F6192_NAS, "Marvell RD-88F6192-NAS Development Board")
 	/* Maintainer: Saeed Bishara <saeed@marvell.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= rd88f6192_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/rd88f6281-setup.c b/arch/arm/mach-kirkwood/rd88f6281-setup.c
index 3d14771..0998a08 100644
--- a/arch/arm/mach-kirkwood/rd88f6281-setup.c
+++ b/arch/arm/mach-kirkwood/rd88f6281-setup.c
@@ -115,8 +115,6 @@
 
 MACHINE_START(RD88F6281, "Marvell RD-88F6281 Reference Board")
 	/* Maintainer: Saeed Bishara <saeed@marvell.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= rd88f6281_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/sheevaplug-setup.c b/arch/arm/mach-kirkwood/sheevaplug-setup.c
index a00879d..d2eec35 100644
--- a/arch/arm/mach-kirkwood/sheevaplug-setup.c
+++ b/arch/arm/mach-kirkwood/sheevaplug-setup.c
@@ -131,8 +131,6 @@
 #ifdef CONFIG_MACH_SHEEVAPLUG
 MACHINE_START(SHEEVAPLUG, "Marvell SheevaPlug Reference Board")
 	/* Maintainer: shadi Ammouri <shadi@marvell.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= sheevaplug_init,
 	.map_io		= kirkwood_map_io,
@@ -143,8 +141,6 @@
 
 #ifdef CONFIG_MACH_ESATA_SHEEVAPLUG
 MACHINE_START(ESATA_SHEEVAPLUG, "Marvell eSATA SheevaPlug Reference Board")
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= sheevaplug_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/t5325-setup.c b/arch/arm/mach-kirkwood/t5325-setup.c
index d01bf89..ce50e61a 100644
--- a/arch/arm/mach-kirkwood/t5325-setup.c
+++ b/arch/arm/mach-kirkwood/t5325-setup.c
@@ -184,8 +184,6 @@
 
 MACHINE_START(T5325, "HP t5325 Thin Client")
 	/* Maintainer: Martin Michlmayr <tbm@cyrius.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= hp_t5325_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/ts219-setup.c b/arch/arm/mach-kirkwood/ts219-setup.c
index a5bd7fd..6710bd7 100644
--- a/arch/arm/mach-kirkwood/ts219-setup.c
+++ b/arch/arm/mach-kirkwood/ts219-setup.c
@@ -120,8 +120,6 @@
 
 MACHINE_START(TS219, "QNAP TS-119/TS-219")
 	/* Maintainer: Martin Michlmayr <tbm@cyrius.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= qnap_ts219_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-kirkwood/ts41x-setup.c b/arch/arm/mach-kirkwood/ts41x-setup.c
index 2e14afe..8be09a0 100644
--- a/arch/arm/mach-kirkwood/ts41x-setup.c
+++ b/arch/arm/mach-kirkwood/ts41x-setup.c
@@ -149,8 +149,6 @@
 
 MACHINE_START(TS41X, "QNAP TS-41x")
 	/* Maintainer: Martin Michlmayr <tbm@cyrius.com> */
-	.phys_io	= KIRKWOOD_REGS_PHYS_BASE,
-	.io_pg_offst	= ((KIRKWOOD_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= qnap_ts41x_init,
 	.map_io		= kirkwood_map_io,
diff --git a/arch/arm/mach-ks8695/board-acs5k.c b/arch/arm/mach-ks8695/board-acs5k.c
index 9e3e5a6..3ca4f8e 100644
--- a/arch/arm/mach-ks8695/board-acs5k.c
+++ b/arch/arm/mach-ks8695/board-acs5k.c
@@ -223,8 +223,6 @@
 
 MACHINE_START(ACS5K, "Brivo Systems LLC ACS-5000 Master board")
 	/* Maintainer: Simtec Electronics. */
-	.phys_io	= KS8695_IO_PA,
-	.io_pg_offst	= (KS8695_IO_VA >> 18) & 0xfffc,
 	.boot_params	= KS8695_SDRAM_PA + 0x100,
 	.map_io		= ks8695_map_io,
 	.init_irq	= ks8695_init_irq,
diff --git a/arch/arm/mach-ks8695/board-dsm320.c b/arch/arm/mach-ks8695/board-dsm320.c
index 521ff07..ada92b6 100644
--- a/arch/arm/mach-ks8695/board-dsm320.c
+++ b/arch/arm/mach-ks8695/board-dsm320.c
@@ -121,8 +121,6 @@
 
 MACHINE_START(DSM320, "D-Link DSM-320 Wireless Media Player")
 	/* Maintainer: Simtec Electronics. */
-	.phys_io	= KS8695_IO_PA,
-	.io_pg_offst	= (KS8695_IO_VA >> 18) & 0xfffc,
 	.boot_params	= KS8695_SDRAM_PA + 0x100,
 	.map_io		= ks8695_map_io,
 	.init_irq	= ks8695_init_irq,
diff --git a/arch/arm/mach-ks8695/board-micrel.c b/arch/arm/mach-ks8695/board-micrel.c
index 8ceaf5a..c7ad09b 100644
--- a/arch/arm/mach-ks8695/board-micrel.c
+++ b/arch/arm/mach-ks8695/board-micrel.c
@@ -53,8 +53,6 @@
 
 MACHINE_START(KS8695, "KS8695 Centaur Development Board")
 	/* Maintainer: Micrel Semiconductor Inc. */
-	.phys_io	= KS8695_IO_PA,
-	.io_pg_offst	= (KS8695_IO_VA >> 18) & 0xfffc,
 	.boot_params	= KS8695_SDRAM_PA + 0x100,
 	.map_io		= ks8695_map_io,
 	.init_irq	= ks8695_init_irq,
diff --git a/arch/arm/mach-ks8695/include/mach/debug-macro.S b/arch/arm/mach-ks8695/include/mach/debug-macro.S
index cf2095d..bf516ad 100644
--- a/arch/arm/mach-ks8695/include/mach/debug-macro.S
+++ b/arch/arm/mach-ks8695/include/mach/debug-macro.S
@@ -14,11 +14,9 @@
 #include <mach/hardware.h>
 #include <mach/regs-uart.h>
 
-	.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1				@ MMU enabled?
-		ldreq	\rx, =KS8695_UART_PA		@ physical base address
-		ldrne	\rx, =KS8695_UART_VA		@ virtual base address
+	.macro	addruart, rp, rv
+		ldr	\rp, =KS8695_UART_PA		@ physical base address
+		ldr	\rv, =KS8695_UART_VA		@ virtual base address
 	.endm
 
 	.macro	senduart, rd, rx
diff --git a/arch/arm/mach-l7200/include/mach/debug-macro.S b/arch/arm/mach-l7200/include/mach/debug-macro.S
new file mode 100644
index 0000000..b0a2db7
--- /dev/null
+++ b/arch/arm/mach-l7200/include/mach/debug-macro.S
@@ -0,0 +1,38 @@
+/* arch/arm/mach-l7200/include/mach/debug-macro.S
+ *
+ * Debugging macro include header
+ *
+ *  Copyright (C) 1994-1999 Russell King
+ *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+*/
+
+		.equ	io_virt, IO_BASE
+		.equ	io_phys, IO_START
+
+		.macro	addruart, rp, rv
+		mov	\rp, #0x00044000	@ UART1
+@		mov	\rp, #0x00045000	@ UART2
+		add	\rv, \rp, #io_virt	@ virtual address
+		add	\rp, \rp, #io_phys	@ physical base address
+		.endm
+
+		.macro	senduart,rd,rx
+		str	\rd, [\rx, #0x0]	@ UARTDR
+		.endm
+
+		.macro	waituart,rd,rx
+1001:		ldr	\rd, [\rx, #0x18]	@ UARTFLG
+		tst	\rd, #1 << 5		@ UARTFLGUTXFF - 1 when full
+		bne	1001b
+		.endm
+
+		.macro	busyuart,rd,rx
+1001:		ldr	\rd, [\rx, #0x18]	@ UARTFLG
+		tst	\rd, #1 << 3		@ UARTFLGUBUSY - 1 when busy
+		bne	1001b
+		.endm
diff --git a/arch/arm/mach-lh7a40x/arch-kev7a400.c b/arch/arm/mach-lh7a40x/arch-kev7a400.c
index 3d7bd50..9088c166 100644
--- a/arch/arm/mach-lh7a40x/arch-kev7a400.c
+++ b/arch/arm/mach-lh7a40x/arch-kev7a400.c
@@ -111,8 +111,6 @@
 
 MACHINE_START (KEV7A400, "Sharp KEV7a400")
 	/* Maintainer: Marc Singer */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((io_p2v (0x80000000))>>18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= kev7a400_map_io,
 	.init_irq	= lh7a400_init_irq,
diff --git a/arch/arm/mach-lh7a40x/arch-lpd7a40x.c b/arch/arm/mach-lh7a40x/arch-lpd7a40x.c
index cb15e5d..7315a56 100644
--- a/arch/arm/mach-lh7a40x/arch-lpd7a40x.c
+++ b/arch/arm/mach-lh7a40x/arch-lpd7a40x.c
@@ -398,8 +398,6 @@
 
 MACHINE_START (LPD7A400, "Logic Product Development LPD7A400-10")
 	/* Maintainer: Marc Singer */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((io_p2v (0x80000000))>>18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= lpd7a40x_map_io,
 	.init_irq	= lh7a400_init_irq,
@@ -413,8 +411,6 @@
 
 MACHINE_START (LPD7A404, "Logic Product Development LPD7A404-10")
 	/* Maintainer: Marc Singer */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((io_p2v (0x80000000))>>18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= lpd7a40x_map_io,
 	.init_irq	= lh7a404_init_irq,
diff --git a/arch/arm/mach-lh7a40x/include/mach/debug-macro.S b/arch/arm/mach-lh7a40x/include/mach/debug-macro.S
index c0dcbbb..cff3362 100644
--- a/arch/arm/mach-lh7a40x/include/mach/debug-macro.S
+++ b/arch/arm/mach-lh7a40x/include/mach/debug-macro.S
@@ -14,12 +14,10 @@
 	@ It is not known if this will be appropriate for every 40x
 	@ board.
 
-		.macro  addruart, rx, tmp
-		mrc     p15, 0, \rx, c1, c0
-		tst     \rx, #1                 @ MMU enabled?
-		mov     \rx, #0x00000700        @ offset from base
-		orreq   \rx, \rx, #0x80000000   @ physical base
-		orrne   \rx, \rx, #0xf8000000   @ virtual base
+		.macro  addruart, rp, rv
+		mov     \rp, #0x00000700        @ offset from base
+		orr     \rv, \rp, #0xf8000000   @ virtual base
+		orr     \rp, \rp, #0x80000000   @ physical base
 		.endm
 
 		.macro  senduart,rd,rx
diff --git a/arch/arm/mach-loki/include/mach/debug-macro.S b/arch/arm/mach-loki/include/mach/debug-macro.S
index 3136c91..cc90d99 100644
--- a/arch/arm/mach-loki/include/mach/debug-macro.S
+++ b/arch/arm/mach-loki/include/mach/debug-macro.S
@@ -8,12 +8,11 @@
 
 #include <mach/loki.h>
 
-	.macro	addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1					@ MMU enabled?
-	ldreq	\rx, =LOKI_REGS_PHYS_BASE
-	ldrne	\rx, =LOKI_REGS_VIRT_BASE
-	orr	\rx, \rx, #0x00012000
+	.macro	addruart, rp, rv
+	ldr	\rp, =LOKI_REGS_PHYS_BASE
+	ldr	\rv, =LOKI_REGS_VIRT_BASE
+	orr	\rp, \rp, #0x00012000
+	orr	\rv, \rv, #0x00012000
 	.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-loki/lb88rc8480-setup.c b/arch/arm/mach-loki/lb88rc8480-setup.c
index 85f9c12..a1e75e7 100644
--- a/arch/arm/mach-loki/lb88rc8480-setup.c
+++ b/arch/arm/mach-loki/lb88rc8480-setup.c
@@ -90,8 +90,6 @@
 
 MACHINE_START(LB88RC8480, "Marvell LB88RC8480 Development Board")
 	/* Maintainer: Ke Wei <kewei@marvell.com> */
-	.phys_io	= LOKI_REGS_PHYS_BASE,
-	.io_pg_offst	= ((LOKI_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= lb88rc8480_init,
 	.map_io		= loki_map_io,
diff --git a/arch/arm/mach-lpc32xx/include/mach/debug-macro.S b/arch/arm/mach-lpc32xx/include/mach/debug-macro.S
index 621744d..629e744 100644
--- a/arch/arm/mach-lpc32xx/include/mach/debug-macro.S
+++ b/arch/arm/mach-lpc32xx/include/mach/debug-macro.S
@@ -20,11 +20,9 @@
  * Debug output is hardcoded to standard UART 5
 */
 
-	.macro	addruart,rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1				@ MMU enabled?
-	ldreq	\rx, =0x40090000
-	ldrne	\rx, =0xF4090000
+	.macro	addruart, rp, rv
+	ldreq	\rp, =0x40090000
+	ldrne	\rv, =0xF4090000
 	.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c
index bc9a42d..7993b09 100644
--- a/arch/arm/mach-lpc32xx/phy3250.c
+++ b/arch/arm/mach-lpc32xx/phy3250.c
@@ -172,18 +172,12 @@
 }
 
 static struct pl022_config_chip spi0_chip_info = {
-	.lbm			= LOOPBACK_DISABLED,
 	.com_mode		= INTERRUPT_TRANSFER,
 	.iface			= SSP_INTERFACE_MOTOROLA_SPI,
 	.hierarchy		= SSP_MASTER,
 	.slave_tx_disable	= 0,
-	.endian_tx		= SSP_TX_LSB,
-	.endian_rx		= SSP_RX_LSB,
-	.data_size		= SSP_DATA_BITS_8,
 	.rx_lev_trig		= SSP_RX_4_OR_MORE_ELEM,
 	.tx_lev_trig		= SSP_TX_4_OR_MORE_EMPTY_LOC,
-	.clk_phase		= SSP_CLK_FIRST_EDGE,
-	.clk_pol		= SSP_CLK_POL_IDLE_LOW,
 	.ctrl_len		= SSP_BITS_8,
 	.wait_state		= SSP_MWIRE_WAIT_ZERO,
 	.duplex			= SSP_MICROWIRE_CHANNEL_FULL_DUPLEX,
@@ -239,6 +233,7 @@
 			.max_speed_hz = 5000000,
 			.bus_num = 0,
 			.chip_select = 0,
+			.mode = SPI_MODE_0,
 			.platform_data = &eeprom,
 			.controller_data = &spi0_chip_info,
 		},
@@ -387,8 +382,6 @@
 
 MACHINE_START(PHY3250, "Phytec 3250 board with the LPC3250 Microcontroller")
 	/* Maintainer: Kevin Wells, NXP Semiconductors */
-	.phys_io	= LPC32XX_UART5_BASE,
-	.io_pg_offst	= ((IO_ADDRESS(LPC32XX_UART5_BASE))>>18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= lpc32xx_map_io,
 	.init_irq	= lpc32xx_init_irq,
diff --git a/arch/arm/mach-mmp/Kconfig b/arch/arm/mach-mmp/Kconfig
index 6ab843e..0711d3b 100644
--- a/arch/arm/mach-mmp/Kconfig
+++ b/arch/arm/mach-mmp/Kconfig
@@ -57,6 +57,13 @@
 	  PXA910-based development board. Since MMP2 is compatible to
 	  ARMv6 architecture.
 
+config MACH_TETON_BGA
+	bool "Marvell's PXA168 Teton BGA Development Board"
+	select CPU_PXA168
+	help
+	  Say 'Y' here if you want to support the Marvell PXA168-based
+	  Teton BGA Development Board.
+
 endmenu
 
 config CPU_PXA168
diff --git a/arch/arm/mach-mmp/Makefile b/arch/arm/mach-mmp/Makefile
index 8b66d06..751cdbf 100644
--- a/arch/arm/mach-mmp/Makefile
+++ b/arch/arm/mach-mmp/Makefile
@@ -17,3 +17,4 @@
 obj-$(CONFIG_MACH_TTC_DKB)	+= ttc_dkb.o
 obj-$(CONFIG_MACH_FLINT)	+= flint.o
 obj-$(CONFIG_MACH_MARVELL_JASPER) += jasper.o
+obj-$(CONFIG_MACH_TETON_BGA)	+= teton_bga.o
diff --git a/arch/arm/mach-mmp/aspenite.c b/arch/arm/mach-mmp/aspenite.c
index 0629394..06b5fa8 100644
--- a/arch/arm/mach-mmp/aspenite.c
+++ b/arch/arm/mach-mmp/aspenite.c
@@ -16,6 +16,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/nand.h>
+#include <linux/interrupt.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -23,6 +24,9 @@
 #include <mach/mfp-pxa168.h>
 #include <mach/pxa168.h>
 #include <mach/gpio.h>
+#include <video/pxa168fb.h>
+#include <linux/input.h>
+#include <plat/pxa27x_keypad.h>
 
 #include "common.h"
 
@@ -66,6 +70,43 @@
 	GPIO115_I2S_BCLK,
 	GPIO116_I2S_RXD,
 	GPIO117_I2S_TXD,
+
+	/* LCD */
+	GPIO56_LCD_FCLK_RD,
+	GPIO57_LCD_LCLK_A0,
+	GPIO58_LCD_PCLK_WR,
+	GPIO59_LCD_DENA_BIAS,
+	GPIO60_LCD_DD0,
+	GPIO61_LCD_DD1,
+	GPIO62_LCD_DD2,
+	GPIO63_LCD_DD3,
+	GPIO64_LCD_DD4,
+	GPIO65_LCD_DD5,
+	GPIO66_LCD_DD6,
+	GPIO67_LCD_DD7,
+	GPIO68_LCD_DD8,
+	GPIO69_LCD_DD9,
+	GPIO70_LCD_DD10,
+	GPIO71_LCD_DD11,
+	GPIO72_LCD_DD12,
+	GPIO73_LCD_DD13,
+	GPIO74_LCD_DD14,
+	GPIO75_LCD_DD15,
+	GPIO76_LCD_DD16,
+	GPIO77_LCD_DD17,
+	GPIO78_LCD_DD18,
+	GPIO79_LCD_DD19,
+	GPIO80_LCD_DD20,
+	GPIO81_LCD_DD21,
+	GPIO82_LCD_DD22,
+	GPIO83_LCD_DD23,
+
+	/* Keypad */
+	GPIO109_KP_MKIN1,
+	GPIO110_KP_MKIN0,
+	GPIO111_KP_MKOUT7,
+	GPIO112_KP_MKOUT6,
+	GPIO121_KP_MKIN4,
 };
 
 static struct smc91x_platdata smc91x_info = {
@@ -134,6 +175,51 @@
 	{ I2C_BOARD_INFO("wm8753", 0x1b), },
 };
 
+static struct fb_videomode video_modes[] = {
+	[0] = {
+		.pixclock	= 30120,
+		.refresh	= 60,
+		.xres		= 800,
+		.yres		= 480,
+		.hsync_len	= 1,
+		.left_margin	= 215,
+		.right_margin	= 40,
+		.vsync_len	= 1,
+		.upper_margin	= 34,
+		.lower_margin	= 10,
+		.sync		= FB_SYNC_VERT_HIGH_ACT | FB_SYNC_HOR_HIGH_ACT,
+	},
+};
+
+struct pxa168fb_mach_info aspenite_lcd_info = {
+	.id			= "Graphic Frame",
+	.modes			= video_modes,
+	.num_modes		= ARRAY_SIZE(video_modes),
+	.pix_fmt		= PIX_FMT_RGB565,
+	.io_pin_allocation_mode = PIN_MODE_DUMB_24,
+	.dumb_mode		= DUMB_MODE_RGB888,
+	.active			= 1,
+	.panel_rbswap		= 0,
+	.invert_pixclock	= 0,
+};
+
+static unsigned int aspenite_matrix_key_map[] = {
+	KEY(0, 6, KEY_UP),	/* SW 4 */
+	KEY(0, 7, KEY_DOWN),	/* SW 5 */
+	KEY(1, 6, KEY_LEFT),	/* SW 6 */
+	KEY(1, 7, KEY_RIGHT),	/* SW 7 */
+	KEY(4, 6, KEY_ENTER),	/* SW 8 */
+	KEY(4, 7, KEY_ESC),	/* SW 9 */
+};
+
+static struct pxa27x_keypad_platform_data aspenite_keypad_info __initdata = {
+	.matrix_key_rows	= 5,
+	.matrix_key_cols	= 8,
+	.matrix_key_map		= aspenite_matrix_key_map,
+	.matrix_key_map_size	= ARRAY_SIZE(aspenite_matrix_key_map),
+	.debounce_interval	= 30,
+};
+
 static void __init common_init(void)
 {
 	mfp_config(ARRAY_AND_SIZE(common_pin_config));
@@ -143,24 +229,24 @@
 	pxa168_add_twsi(1, NULL, ARRAY_AND_SIZE(aspenite_i2c_info));
 	pxa168_add_ssp(1);
 	pxa168_add_nand(&aspenite_nand_info);
+	pxa168_add_fb(&aspenite_lcd_info);
+	pxa168_add_keypad(&aspenite_keypad_info);
 
 	/* off-chip devices */
 	platform_device_register(&smc91x_device);
 }
 
 MACHINE_START(ASPENITE, "PXA168-based Aspenite Development Platform")
-	.phys_io        = APB_PHYS_BASE,
-	.io_pg_offst    = (APB_VIRT_BASE >> 18) & 0xfffc,
 	.map_io		= mmp_map_io,
+	.nr_irqs	= IRQ_BOARD_START,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = common_init,
 MACHINE_END
 
 MACHINE_START(ZYLONITE2, "PXA168-based Zylonite2 Development Platform")
-	.phys_io        = APB_PHYS_BASE,
-	.io_pg_offst    = (APB_VIRT_BASE >> 18) & 0xfffc,
 	.map_io		= mmp_map_io,
+	.nr_irqs	= IRQ_BOARD_START,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
 	.init_machine   = common_init,
diff --git a/arch/arm/mach-mmp/avengers_lite.c b/arch/arm/mach-mmp/avengers_lite.c
index 69bcba1..39f0878 100644
--- a/arch/arm/mach-mmp/avengers_lite.c
+++ b/arch/arm/mach-mmp/avengers_lite.c
@@ -41,8 +41,6 @@
 }
 
 MACHINE_START(AVENGERS_LITE, "PXA168 Avengers lite Development Platform")
-	.phys_io        = APB_PHYS_BASE,
-	.io_pg_offst    = (APB_VIRT_BASE >> 18) & 0xfffc,
 	.map_io		= mmp_map_io,
 	.init_irq       = pxa168_init_irq,
 	.timer          = &pxa168_timer,
diff --git a/arch/arm/mach-mmp/common.c b/arch/arm/mach-mmp/common.c
index 3b29fa7..0ec0ca8 100644
--- a/arch/arm/mach-mmp/common.c
+++ b/arch/arm/mach-mmp/common.c
@@ -10,13 +10,20 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 
 #include <asm/page.h>
 #include <asm/mach/map.h>
 #include <mach/addr-map.h>
+#include <mach/cputype.h>
 
 #include "common.h"
 
+#define MMP_CHIPID	(AXI_VIRT_BASE + 0x82c00)
+
+unsigned int mmp_chip_id;
+EXPORT_SYMBOL(mmp_chip_id);
+
 static struct map_desc standard_io_desc[] __initdata = {
 	{
 		.pfn		= __phys_to_pfn(APB_PHYS_BASE),
@@ -34,4 +41,7 @@
 void __init mmp_map_io(void)
 {
 	iotable_init(standard_io_desc, ARRAY_SIZE(standard_io_desc));
+
+	/* this is early, initialize mmp_chip_id here */
+	mmp_chip_id = __raw_readl(MMP_CHIPID);
 }
diff --git a/arch/arm/mach-mmp/flint.c b/arch/arm/mach-mmp/flint.c
index e4312d2..bdeb6db 100644
--- a/arch/arm/mach-mmp/flint.c
+++ b/arch/arm/mach-mmp/flint.c
@@ -16,6 +16,7 @@
 #include <linux/smc91x.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
+#include <linux/interrupt.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -25,6 +26,8 @@
 
 #include "common.h"
 
+#define FLINT_NR_IRQS	(IRQ_BOARD_START + 48)
+
 static unsigned long flint_pin_config[] __initdata = {
 	/* UART1 */
 	GPIO45_UART1_RXD,
@@ -113,9 +116,8 @@
 }
 
 MACHINE_START(FLINT, "Flint Development Platform")
-	.phys_io        = APB_PHYS_BASE,
-	.io_pg_offst    = (APB_VIRT_BASE >> 18) & 0xfffc,
 	.map_io		= mmp_map_io,
+	.nr_irqs	= FLINT_NR_IRQS,
 	.init_irq       = mmp2_init_irq,
 	.timer          = &mmp2_timer,
 	.init_machine   = flint_init,
diff --git a/arch/arm/mach-mmp/include/mach/cputype.h b/arch/arm/mach-mmp/include/mach/cputype.h
index 83b1872..f43a68b 100644
--- a/arch/arm/mach-mmp/include/mach/cputype.h
+++ b/arch/arm/mach-mmp/include/mach/cputype.h
@@ -4,36 +4,51 @@
 #include <asm/cputype.h>
 
 /*
- *  CPU   Stepping   OLD_ID       CPU_ID      CHIP_ID
+ *  CPU   Stepping   CPU_ID      CHIP_ID
  *
- * PXA168    A0    0x41159263   0x56158400   0x00A0A333
- * PXA910    Y0    0x41159262   0x56158000   0x00F0C910
- * MMP2	     Z0			0x560f5811
+ * PXA168    S0    0x56158400   0x0000C910
+ * PXA168    A0    0x56158400   0x00A0A168
+ * PXA910    Y1    0x56158400   0x00F2C920
+ * PXA910    A0    0x56158400   0x00F2C910
+ * PXA910    A1    0x56158400   0x00A0C910
+ * PXA920    Y0    0x56158400   0x00F2C920
+ * PXA920    A0    0x56158400   0x00A0C920
+ * PXA920    A1    0x56158400   0x00A1C920
+ * MMP2	     Z0	   0x560f5811   0x00F00410
+ * MMP2      Z1    0x560f5811   0x00E00410
+ * MMP2      A0    0x560f5811   0x00A0A610
  */
 
+extern unsigned int mmp_chip_id;
+
 #ifdef CONFIG_CPU_PXA168
-#  define __cpu_is_pxa168(id)	\
-	({ unsigned int _id = ((id) >> 8) & 0xff; _id == 0x84; })
+static inline int cpu_is_pxa168(void)
+{
+	return (((read_cpuid_id() >> 8) & 0xff) == 0x84) &&
+		((mmp_chip_id & 0xfff) == 0x168);
+}
 #else
-#  define __cpu_is_pxa168(id)	(0)
+#define cpu_is_pxa168()	(0)
 #endif
 
+/* cpu_is_pxa910() is shared on both pxa910 and pxa920 */
 #ifdef CONFIG_CPU_PXA910
-#  define __cpu_is_pxa910(id)	\
-	({ unsigned int _id = ((id) >> 8) & 0xff; _id == 0x80; })
+static inline int cpu_is_pxa910(void)
+{
+	return (((read_cpuid_id() >> 8) & 0xff) == 0x84) &&
+		(((mmp_chip_id & 0xfff) == 0x910) ||
+		 ((mmp_chip_id & 0xfff) == 0x920));
+}
 #else
-#  define __cpu_is_pxa910(id)	(0)
+#define cpu_is_pxa910()	(0)
 #endif
 
 #ifdef CONFIG_CPU_MMP2
-#  define __cpu_is_mmp2(id)	\
-	({ unsigned int _id = ((id) >> 8) & 0xff; _id == 0x58; })
+static inline int cpu_is_mmp2(void)
+{
+	return (((cpu_readid_id() >> 8) & 0xff) == 0x58);
 #else
-#  define __cpu_is_mmp2(id)	(0)
+#define cpu_is_mmp2()	(0)
 #endif
 
-#define cpu_is_pxa168()		({ __cpu_is_pxa168(read_cpuid_id()); })
-#define cpu_is_pxa910()		({ __cpu_is_pxa910(read_cpuid_id()); })
-#define cpu_is_mmp2()		({ __cpu_is_mmp2(read_cpuid_id()); })
-
 #endif /* __ASM_MACH_CPUTYPE_H */
diff --git a/arch/arm/mach-mmp/include/mach/debug-macro.S b/arch/arm/mach-mmp/include/mach/debug-macro.S
index 76deff2..7e2ebd3 100644
--- a/arch/arm/mach-mmp/include/mach/debug-macro.S
+++ b/arch/arm/mach-mmp/include/mach/debug-macro.S
@@ -11,12 +11,11 @@
 
 #include <mach/addr-map.h>
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1				@ MMU enabled?
-		ldreq	\rx, =APB_PHYS_BASE		@ physical
-		ldrne	\rx, =APB_VIRT_BASE		@ virtual
-		orr	\rx, \rx, #0x00017000
+		.macro	addruart, rp, rv
+		ldr	\rp, =APB_PHYS_BASE		@ physical
+		ldr	\rv, =APB_VIRT_BASE		@ virtual
+		orr	\rp, \rp, #0x00017000
+		orr	\rv, \rv, #0x00017000
 		.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-mmp/include/mach/irqs.h b/arch/arm/mach-mmp/include/mach/irqs.h
index b379cde..a09d328 100644
--- a/arch/arm/mach-mmp/include/mach/irqs.h
+++ b/arch/arm/mach-mmp/include/mach/irqs.h
@@ -222,10 +222,8 @@
 #define IRQ_GPIO_NUM			192
 #define IRQ_GPIO(x)			(IRQ_GPIO_START + (x))
 
-/* Board IRQ - 64 by default, increase if not enough */
 #define IRQ_BOARD_START			(IRQ_GPIO_START + IRQ_GPIO_NUM)
-#define IRQ_BOARD_END			(IRQ_BOARD_START + 64)
 
-#define NR_IRQS				(IRQ_BOARD_END)
+#define NR_IRQS				(IRQ_BOARD_START)
 
 #endif /* __ASM_MACH_IRQS_H */
diff --git a/arch/arm/mach-mmp/include/mach/mfp-pxa168.h b/arch/arm/mach-mmp/include/mach/mfp-pxa168.h
index ded43c4..4621067 100644
--- a/arch/arm/mach-mmp/include/mach/mfp-pxa168.h
+++ b/arch/arm/mach-mmp/include/mach/mfp-pxa168.h
@@ -289,4 +289,11 @@
 #define GPIO86_PWM1_OUT		MFP_CFG(GPIO86, AF2)
 #define GPIO86_PWM2_OUT		MFP_CFG(GPIO86, AF3)
 
+/* Keypad */
+#define GPIO109_KP_MKIN1        MFP_CFG(GPIO109, AF7)
+#define GPIO110_KP_MKIN0        MFP_CFG(GPIO110, AF7)
+#define GPIO111_KP_MKOUT7       MFP_CFG(GPIO111, AF7)
+#define GPIO112_KP_MKOUT6       MFP_CFG(GPIO112, AF7)
+#define GPIO121_KP_MKIN4        MFP_CFG(GPIO121, AF7)
+
 #endif /* __ASM_MACH_MFP_PXA168_H */
diff --git a/arch/arm/mach-mmp/include/mach/pxa168.h b/arch/arm/mach-mmp/include/mach/pxa168.h
index 27e1bc7..1801e42 100644
--- a/arch/arm/mach-mmp/include/mach/pxa168.h
+++ b/arch/arm/mach-mmp/include/mach/pxa168.h
@@ -5,11 +5,15 @@
 
 extern struct sys_timer pxa168_timer;
 extern void __init pxa168_init_irq(void);
+extern void pxa168_clear_keypad_wakeup(void);
 
 #include <linux/i2c.h>
 #include <mach/devices.h>
 #include <plat/i2c.h>
 #include <plat/pxa3xx_nand.h>
+#include <video/pxa168fb.h>
+#include <plat/pxa27x_keypad.h>
+#include <mach/cputype.h>
 
 extern struct pxa_device_desc pxa168_device_uart1;
 extern struct pxa_device_desc pxa168_device_uart2;
@@ -25,6 +29,8 @@
 extern struct pxa_device_desc pxa168_device_ssp4;
 extern struct pxa_device_desc pxa168_device_ssp5;
 extern struct pxa_device_desc pxa168_device_nand;
+extern struct pxa_device_desc pxa168_device_fb;
+extern struct pxa_device_desc pxa168_device_keypad;
 
 static inline int pxa168_add_uart(int id)
 {
@@ -97,4 +103,18 @@
 {
 	return pxa_register_device(&pxa168_device_nand, info, sizeof(*info));
 }
+
+static inline int pxa168_add_fb(struct pxa168fb_mach_info *mi)
+{
+	return pxa_register_device(&pxa168_device_fb, mi, sizeof(*mi));
+}
+
+static inline int pxa168_add_keypad(struct pxa27x_keypad_platform_data *data)
+{
+	if (cpu_is_pxa168())
+		data->clear_wakeup_event = pxa168_clear_keypad_wakeup;
+
+	return pxa_register_device(&pxa168_device_keypad, data, sizeof(*data));
+}
+
 #endif /* __ASM_MACH_PXA168_H */
diff --git a/arch/arm/mach-mmp/include/mach/regs-apmu.h b/arch/arm/mach-mmp/include/mach/regs-apmu.h
index 9190305..ac47023 100644
--- a/arch/arm/mach-mmp/include/mach/regs-apmu.h
+++ b/arch/arm/mach-mmp/include/mach/regs-apmu.h
@@ -33,4 +33,16 @@
 #define APMU_FNRST_DIS	(1 << 1)
 #define APMU_AXIRST_DIS	(1 << 0)
 
+/* Wake Clear Register */
+#define APMU_WAKE_CLR	APMU_REG(0x07c)
+
+#define APMU_PXA168_KP_WAKE_CLR		(1 << 7)
+#define APMU_PXA168_CFI_WAKE_CLR	(1 << 6)
+#define APMU_PXA168_XD_WAKE_CLR		(1 << 5)
+#define APMU_PXA168_MSP_WAKE_CLR	(1 << 4)
+#define APMU_PXA168_SD4_WAKE_CLR	(1 << 3)
+#define APMU_PXA168_SD3_WAKE_CLR	(1 << 2)
+#define APMU_PXA168_SD2_WAKE_CLR	(1 << 1)
+#define APMU_PXA168_SD1_WAKE_CLR	(1 << 0)
+
 #endif /* __ASM_MACH_REGS_APMU_H */
diff --git a/arch/arm/mach-mmp/include/mach/teton_bga.h b/arch/arm/mach-mmp/include/mach/teton_bga.h
new file mode 100644
index 0000000..61a539b
--- /dev/null
+++ b/arch/arm/mach-mmp/include/mach/teton_bga.h
@@ -0,0 +1,27 @@
+/*
+ *  linux/arch/arm/mach-mmp/include/mach/teton_bga.h
+ *
+ *  Support for the Marvell PXA168 Teton BGA Development Platform.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  publishhed by the Free Software Foundation.
+ */
+#ifndef __ASM_MACH_TETON_BGA_H
+#define __ASM_MACH_TETON_BGA_H
+
+/* GPIOs */
+#define MMC_PWENA_GPIO		27
+#define USBHPENB_GPIO		55
+#define RTC_INT_GPIO		78
+#define LCD_VBLK_EN_GPIO	79
+#define LCD_DVDD_EN_GPIO	80
+#define RST_WIFI_GPIO		81
+#define CF_PWEN_GPIO		82
+#define USB_OC_GPIO		83
+#define PWM_GPIO		84
+#define USBHPENA_GPIO		85
+#define TS_INT_GPIO		86
+#define CIR_GPIO		108
+
+#endif /* __ASM_MACH_TETON_BGA_H */
diff --git a/arch/arm/mach-mmp/jasper.c b/arch/arm/mach-mmp/jasper.c
index 80c3e7a..2a684fa 100644
--- a/arch/arm/mach-mmp/jasper.c
+++ b/arch/arm/mach-mmp/jasper.c
@@ -18,16 +18,18 @@
 #include <linux/regulator/machine.h>
 #include <linux/regulator/max8649.h>
 #include <linux/mfd/max8925.h>
+#include <linux/interrupt.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <mach/addr-map.h>
 #include <mach/mfp-mmp2.h>
 #include <mach/mmp2.h>
-#include <mach/irqs.h>
 
 #include "common.h"
 
+#define JASPER_NR_IRQS		(IRQ_BOARD_START + 48)
+
 static unsigned long jasper_pin_config[] __initdata = {
 	/* UART1 */
 	GPIO29_UART1_RXD,
@@ -134,9 +136,8 @@
 }
 
 MACHINE_START(MARVELL_JASPER, "Jasper Development Platform")
-	.phys_io        = APB_PHYS_BASE,
-	.io_pg_offst    = (APB_VIRT_BASE >> 18) & 0xfffc,
 	.map_io		= mmp_map_io,
+	.nr_irqs	= JASPER_NR_IRQS,
 	.init_irq       = mmp2_init_irq,
 	.timer          = &mmp2_timer,
 	.init_machine   = jasper_init,
diff --git a/arch/arm/mach-mmp/pxa168.c b/arch/arm/mach-mmp/pxa168.c
index 652ae66..72b4e76 100644
--- a/arch/arm/mach-mmp/pxa168.c
+++ b/arch/arm/mach-mmp/pxa168.c
@@ -77,8 +77,10 @@
 static APBC_CLK(ssp3, PXA168_SSP3, 4, 0);
 static APBC_CLK(ssp4, PXA168_SSP4, 4, 0);
 static APBC_CLK(ssp5, PXA168_SSP5, 4, 0);
+static APBC_CLK(keypad, PXA168_KPC, 0, 32000);
 
 static APMU_CLK(nand, NAND, 0x01db, 208000000);
+static APMU_CLK(lcd, LCD, 0x7f, 312000000);
 
 /* device and clock bindings */
 static struct clk_lookup pxa168_clkregs[] = {
@@ -96,6 +98,8 @@
 	INIT_CLKREG(&clk_ssp4, "pxa168-ssp.3", NULL),
 	INIT_CLKREG(&clk_ssp5, "pxa168-ssp.4", NULL),
 	INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL),
+	INIT_CLKREG(&clk_lcd, "pxa168-fb", NULL),
+	INIT_CLKREG(&clk_keypad, "pxa27x-keypad", NULL),
 };
 
 static int __init pxa168_init(void)
@@ -132,6 +136,16 @@
 	.init	= pxa168_timer_init,
 };
 
+void pxa168_clear_keypad_wakeup(void)
+{
+	uint32_t val;
+	uint32_t mask = APMU_PXA168_KP_WAKE_CLR;
+
+	/* wake event clear is needed in order to clear keypad interrupt */
+	val = __raw_readl(APMU_WAKE_CLR);
+	__raw_writel(val |  mask, APMU_WAKE_CLR);
+}
+
 /* on-chip devices */
 PXA168_DEVICE(uart1, "pxa2xx-uart", 0, UART1, 0xd4017000, 0x30, 21, 22);
 PXA168_DEVICE(uart2, "pxa2xx-uart", 1, UART2, 0xd4018000, 0x30, 23, 24);
@@ -147,3 +161,5 @@
 PXA168_DEVICE(ssp3, "pxa168-ssp", 2, SSP3, 0xd401f000, 0x40, 56, 57);
 PXA168_DEVICE(ssp4, "pxa168-ssp", 3, SSP4, 0xd4020000, 0x40, 58, 59);
 PXA168_DEVICE(ssp5, "pxa168-ssp", 4, SSP5, 0xd4021000, 0x40, 60, 61);
+PXA168_DEVICE(fb, "pxa168-fb", -1, LCD, 0xd420b000, 0x1c8);
+PXA168_DEVICE(keypad, "pxa27x-keypad", -1, KEYPAD, 0xd4012000, 0x4c);
diff --git a/arch/arm/mach-mmp/tavorevb.c b/arch/arm/mach-mmp/tavorevb.c
index e81db74..c296b75 100644
--- a/arch/arm/mach-mmp/tavorevb.c
+++ b/arch/arm/mach-mmp/tavorevb.c
@@ -99,8 +99,6 @@
 }
 
 MACHINE_START(TAVOREVB, "PXA910 Evaluation Board (aka TavorEVB)")
-	.phys_io        = APB_PHYS_BASE,
-	.io_pg_offst    = (APB_VIRT_BASE >> 18) & 0xfffc,
 	.map_io		= mmp_map_io,
 	.init_irq       = pxa910_init_irq,
 	.timer          = &pxa910_timer,
diff --git a/arch/arm/mach-mmp/teton_bga.c b/arch/arm/mach-mmp/teton_bga.c
new file mode 100644
index 0000000..bbe4727
--- /dev/null
+++ b/arch/arm/mach-mmp/teton_bga.c
@@ -0,0 +1,89 @@
+/*
+ *  linux/arch/arm/mach-mmp/teton_bga.c
+ *
+ *  Support for the Marvell PXA168 Teton BGA Development Platform.
+ *
+ *  Author: Mark F. Brown <mark.brown314@gmail.com>
+ *
+ *  This code is based on aspenite.c
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  publishhed by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+#include <linux/input.h>
+#include <plat/pxa27x_keypad.h>
+#include <linux/i2c.h>
+
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <mach/addr-map.h>
+#include <mach/mfp-pxa168.h>
+#include <mach/pxa168.h>
+#include <mach/teton_bga.h>
+
+#include "common.h"
+
+static unsigned long teton_bga_pin_config[] __initdata = {
+	/* UART1 */
+	GPIO107_UART1_TXD,
+	GPIO108_UART1_RXD,
+
+	/* Keypad */
+	GPIO109_KP_MKIN1,
+	GPIO110_KP_MKIN0,
+	GPIO111_KP_MKOUT7,
+	GPIO112_KP_MKOUT6,
+
+	/* I2C Bus */
+	GPIO105_CI2C_SDA,
+	GPIO106_CI2C_SCL,
+
+	/* RTC */
+	GPIO78_GPIO,
+};
+
+static unsigned int teton_bga_matrix_key_map[] = {
+	KEY(0, 6, KEY_ESC),
+	KEY(0, 7, KEY_ENTER),
+	KEY(1, 6, KEY_LEFT),
+	KEY(1, 7, KEY_RIGHT),
+};
+
+static struct pxa27x_keypad_platform_data teton_bga_keypad_info __initdata = {
+	.matrix_key_rows        = 2,
+	.matrix_key_cols        = 8,
+	.matrix_key_map         = teton_bga_matrix_key_map,
+	.matrix_key_map_size    = ARRAY_SIZE(teton_bga_matrix_key_map),
+	.debounce_interval      = 30,
+};
+
+static struct i2c_board_info teton_bga_i2c_info[] __initdata = {
+	{
+		I2C_BOARD_INFO("ds1337", 0x68),
+		.irq = gpio_to_irq(RTC_INT_GPIO)
+	},
+};
+
+static void __init teton_bga_init(void)
+{
+	mfp_config(ARRAY_AND_SIZE(teton_bga_pin_config));
+
+	/* on-chip devices */
+	pxa168_add_uart(1);
+	pxa168_add_keypad(&teton_bga_keypad_info);
+	pxa168_add_twsi(0, NULL, ARRAY_AND_SIZE(teton_bga_i2c_info));
+}
+
+MACHINE_START(TETON_BGA, "PXA168-based Teton BGA Development Platform")
+	.map_io		= mmp_map_io,
+	.nr_irqs	= IRQ_BOARD_START,
+	.init_irq       = pxa168_init_irq,
+	.timer          = &pxa168_timer,
+	.init_machine   = teton_bga_init,
+MACHINE_END
diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c
index ee65e05..e411039 100644
--- a/arch/arm/mach-mmp/ttc_dkb.c
+++ b/arch/arm/mach-mmp/ttc_dkb.c
@@ -14,6 +14,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/onenand.h>
+#include <linux/interrupt.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -24,6 +25,8 @@
 
 #include "common.h"
 
+#define TTCDKB_NR_IRQS		(IRQ_BOARD_START + 24)
+
 static unsigned long ttc_dkb_pin_config[] __initdata = {
 	/* UART2 */
 	GPIO47_UART2_RXD,
@@ -122,9 +125,8 @@
 }
 
 MACHINE_START(TTC_DKB, "PXA910-based TTC_DKB Development Platform")
-	.phys_io        = APB_PHYS_BASE,
-	.io_pg_offst    = (APB_VIRT_BASE >> 18) & 0xfffc,
 	.map_io		= mmp_map_io,
+	.nr_irqs	= TTCDKB_NR_IRQS,
 	.init_irq       = pxa910_init_irq,
 	.timer          = &pxa910_timer,
 	.init_machine   = ttc_dkb_init,
diff --git a/arch/arm/mach-msm/Kconfig b/arch/arm/mach-msm/Kconfig
index 47264a7..3115a29 100644
--- a/arch/arm/mach-msm/Kconfig
+++ b/arch/arm/mach-msm/Kconfig
@@ -10,6 +10,8 @@
 	select MSM_SMD
 	select MSM_SMD_PKG3
 	select CPU_V6
+	select MSM_PROC_COMM
+	select HAS_MSM_DEBUG_UART_PHYS
 
 config ARCH_MSM7X30
 	bool "MSM7x30"
@@ -18,6 +20,9 @@
 	select MSM_VIC
 	select CPU_V7
 	select MSM_REMOTE_SPINLOCK_DEKKERS
+	select MSM_GPIOMUX
+	select MSM_PROC_COMM
+	select HAS_MSM_DEBUG_UART_PHYS
 
 config ARCH_QSD8X50
 	bool "QSD8X50"
@@ -26,6 +31,19 @@
 	select MSM_VIC
 	select CPU_V7
 	select MSM_REMOTE_SPINLOCK_LDREX
+	select MSM_GPIOMUX
+	select MSM_PROC_COMM
+	select HAS_MSM_DEBUG_UART_PHYS
+
+config ARCH_MSM8X60
+	bool "MSM8X60"
+	select ARM_GIC
+	select CPU_V7
+	select MSM_V2_TLMM
+	select MSM_GPIOMUX
+	select MACH_MSM8X60_SURF if (!MACH_MSM8X60_RUMI3 && !MACH_MSM8X60_SIM \
+				  && !MACH_MSM8X60_FFA)
+
 endchoice
 
 config MSM_SOC_REV_A
@@ -36,6 +54,9 @@
 config  ARCH_MSM_SCORPION
 	bool
 
+config HAS_MSM_DEBUG_UART_PHYS
+	bool
+
 config  MSM_VIC
 	bool
 
@@ -74,6 +95,30 @@
 	help
 	  Support for the Qualcomm ST1.5.
 
+config MACH_MSM8X60_RUMI3
+	depends on ARCH_MSM8X60
+	bool "MSM8x60 RUMI3"
+	help
+	  Support for the Qualcomm MSM8x60 RUMI3 emulator.
+
+config MACH_MSM8X60_SURF
+	depends on ARCH_MSM8X60
+	bool "MSM8x60 SURF"
+	help
+	  Support for the Qualcomm MSM8x60 SURF eval board.
+
+config MACH_MSM8X60_SIM
+	depends on ARCH_MSM8X60
+	bool "MSM8x60 Simulator"
+	help
+	  Support for the Qualcomm MSM8x60 simulator.
+
+config MACH_MSM8X60_FFA
+	depends on ARCH_MSM8X60
+	bool "MSM8x60 FFA"
+	help
+	  Support for the Qualcomm MSM8x60 FFA eval board.
+
 endmenu
 
 config MSM_DEBUG_UART
@@ -82,6 +127,7 @@
 	default 2 if MSM_DEBUG_UART2
 	default 3 if MSM_DEBUG_UART3
 
+if HAS_MSM_DEBUG_UART_PHYS
 choice
 	prompt "Debug UART"
 
@@ -99,11 +145,20 @@
 	config MSM_DEBUG_UART3
 		bool "UART3"
 endchoice
+endif
 
 config MSM_SMD_PKG3
 	bool
 
+config MSM_PROC_COMM
+	bool
+
 config MSM_SMD
 	bool
 
+config MSM_GPIOMUX
+	bool
+
+config MSM_V2_TLMM
+	bool
 endif
diff --git a/arch/arm/mach-msm/Makefile b/arch/arm/mach-msm/Makefile
index 7046106..b5a7b07 100644
--- a/arch/arm/mach-msm/Makefile
+++ b/arch/arm/mach-msm/Makefile
@@ -1,16 +1,20 @@
-obj-y += proc_comm.o
-obj-y += io.o idle.o timer.o dma.o
-obj-y += vreg.o
+obj-y += io.o idle.o timer.o
+ifndef CONFIG_ARCH_MSM8X60
 obj-y += acpuclock-arm11.o
-obj-y += clock.o clock-pcom.o
-obj-y += gpio.o
+obj-y += dma.o
+endif
 
 ifdef CONFIG_MSM_VIC
 obj-y += irq-vic.o
 else
+ifndef CONFIG_ARCH_MSM8X60
 obj-y += irq.o
 endif
+endif
 
+obj-$(CONFIG_ARCH_MSM8X60) += clock-dummy.o iommu.o iommu_dev.o devices-msm8x60-iommu.o
+obj-$(CONFIG_MSM_PROC_COMM) += proc_comm.o clock-pcom.o vreg.o
+obj-$(CONFIG_MSM_PROC_COMM) += clock.o
 obj-$(CONFIG_ARCH_QSD8X50) += sirc.o
 obj-$(CONFIG_MSM_SMD) += smd.o smd_debug.o
 obj-$(CONFIG_MSM_SMD) += last_radio_log.o
@@ -19,4 +23,11 @@
 obj-$(CONFIG_MACH_HALIBUT) += board-halibut.o devices-msm7x00.o
 obj-$(CONFIG_ARCH_MSM7X30) += board-msm7x30.o devices-msm7x30.o
 obj-$(CONFIG_ARCH_QSD8X50) += board-qsd8x50.o devices-qsd8x50.o
+obj-$(CONFIG_ARCH_MSM8X60) += board-msm8x60.o
 
+obj-$(CONFIG_ARCH_MSM7X30) += gpiomux-7x30.o gpiomux-v1.o gpiomux.o
+obj-$(CONFIG_ARCH_QSD8X50) += gpiomux-8x50.o gpiomux-v1.o gpiomux.o
+obj-$(CONFIG_ARCH_MSM8X60) += gpiomux-8x60.o gpiomux-v2.o gpiomux.o
+ifndef CONFIG_MSM_V2_TLMM
+obj-y	+= gpio.o
+endif
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index 7bd72e8..59edecb 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -95,8 +95,6 @@
 
 MACHINE_START(HALIBUT, "Halibut Board (QCT SURF7200A)")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io        = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst    = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params	= 0x10000100,
 	.fixup		= halibut_fixup,
diff --git a/arch/arm/mach-msm/board-mahimahi.c b/arch/arm/mach-msm/board-mahimahi.c
index bcbefdf..ef3ebf2 100644
--- a/arch/arm/mach-msm/board-mahimahi.c
+++ b/arch/arm/mach-msm/board-mahimahi.c
@@ -75,8 +75,6 @@
 
 MACHINE_START(MAHIMAHI, "mahimahi")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io        = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst    = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params	= 0x20000100,
 	.fixup		= mahimahi_fixup,
diff --git a/arch/arm/mach-msm/board-msm7x27.c b/arch/arm/mach-msm/board-msm7x27.c
index db9381b..e7a76ef 100644
--- a/arch/arm/mach-msm/board-msm7x27.c
+++ b/arch/arm/mach-msm/board-msm7x27.c
@@ -131,8 +131,6 @@
 
 MACHINE_START(MSM7X27_SURF, "QCT MSM7x27 SURF")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io        = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst    = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params	= PHYS_OFFSET + 0x100,
 	.map_io		= msm7x2x_map_io,
@@ -143,8 +141,6 @@
 
 MACHINE_START(MSM7X27_FFA, "QCT MSM7x27 FFA")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io        = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst    = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params	= PHYS_OFFSET + 0x100,
 	.map_io		= msm7x2x_map_io,
@@ -155,8 +151,6 @@
 
 MACHINE_START(MSM7X25_SURF, "QCT MSM7x25 SURF")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io        = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst    = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params	= PHYS_OFFSET + 0x100,
 	.map_io		= msm7x2x_map_io,
@@ -167,8 +161,6 @@
 
 MACHINE_START(MSM7X25_FFA, "QCT MSM7x25 FFA")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io        = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst    = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params	= PHYS_OFFSET + 0x100,
 	.map_io		= msm7x2x_map_io,
diff --git a/arch/arm/mach-msm/board-msm7x30.c b/arch/arm/mach-msm/board-msm7x30.c
index e329819..05241df 100644
--- a/arch/arm/mach-msm/board-msm7x30.c
+++ b/arch/arm/mach-msm/board-msm7x30.c
@@ -39,27 +39,11 @@
 
 extern struct sys_timer msm_timer;
 
-#ifdef CONFIG_SERIAL_MSM_CONSOLE
-static struct msm_gpio uart2_config_data[] = {
-	{ GPIO_CFG(49, 2, GPIO_OUTPUT,  GPIO_PULL_DOWN, GPIO_2MA), "UART2_RFR"},
-	{ GPIO_CFG(50, 2, GPIO_INPUT,   GPIO_PULL_DOWN, GPIO_2MA), "UART2_CTS"},
-	{ GPIO_CFG(51, 2, GPIO_INPUT,   GPIO_PULL_DOWN, GPIO_2MA), "UART2_Rx"},
-	{ GPIO_CFG(52, 2, GPIO_OUTPUT,  GPIO_PULL_DOWN, GPIO_2MA), "UART2_Tx"},
-};
-
-static void msm7x30_init_uart2(void)
-{
-	msm_gpios_request_enable(uart2_config_data,
-			ARRAY_SIZE(uart2_config_data));
-
-}
-#endif
-
 static struct platform_device *devices[] __initdata = {
 #if defined(CONFIG_SERIAL_MSM) || defined(CONFIG_MSM_SERIAL_DEBUGGER)
         &msm_device_uart2,
 #endif
-
+	&msm_device_smd,
 };
 
 static void __init msm7x30_init_irq(void)
@@ -70,10 +54,6 @@
 static void __init msm7x30_init(void)
 {
 	platform_add_devices(devices, ARRAY_SIZE(devices));
-#ifdef CONFIG_SERIAL_MSM_CONSOLE
-	msm7x30_init_uart2();
-#endif
-
 }
 
 static void __init msm7x30_map_io(void)
@@ -84,8 +64,6 @@
 
 MACHINE_START(MSM7X30_SURF, "QCT MSM7X30 SURF")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io  = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params = PHYS_OFFSET + 0x100,
 	.map_io = msm7x30_map_io,
@@ -96,8 +74,6 @@
 
 MACHINE_START(MSM7X30_FFA, "QCT MSM7X30 FFA")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io  = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params = PHYS_OFFSET + 0x100,
 	.map_io = msm7x30_map_io,
@@ -108,8 +84,6 @@
 
 MACHINE_START(MSM7X30_FLUID, "QCT MSM7X30 FLUID")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io  = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params = PHYS_OFFSET + 0x100,
 	.map_io = msm7x30_map_io,
diff --git a/arch/arm/mach-msm/board-msm8x60.c b/arch/arm/mach-msm/board-msm8x60.c
new file mode 100644
index 0000000..7486a68
--- /dev/null
+++ b/arch/arm/mach-msm/board-msm8x60.c
@@ -0,0 +1,100 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/hardware/gic.h>
+
+#include <mach/board.h>
+#include <mach/msm_iomap.h>
+
+void __iomem *gic_cpu_base_addr;
+
+unsigned long clk_get_max_axi_khz(void)
+{
+	return 0;
+}
+
+static void __init msm8x60_map_io(void)
+{
+	msm_map_msm8x60_io();
+}
+
+static void __init msm8x60_init_irq(void)
+{
+	unsigned int i;
+
+	gic_dist_init(0, MSM_QGIC_DIST_BASE, GIC_PPI_START);
+	gic_cpu_base_addr = (void *)MSM_QGIC_CPU_BASE;
+	gic_cpu_init(0, MSM_QGIC_CPU_BASE);
+
+	/* Edge trigger PPIs except AVS_SVICINT and AVS_SVICINTSWDONE */
+	writel(0xFFFFD7FF, MSM_QGIC_DIST_BASE + GIC_DIST_CONFIG + 4);
+
+	/* RUMI does not adhere to GIC spec by enabling STIs by default.
+	 * Enable/clear is supposed to be RO for STIs, but is RW on RUMI.
+	 */
+	if (!machine_is_msm8x60_sim())
+		writel(0x0000FFFF, MSM_QGIC_DIST_BASE + GIC_DIST_ENABLE_SET);
+
+	/* FIXME: Not installing AVS_SVICINT and AVS_SVICINTSWDONE yet
+	 * as they are configured as level, which does not play nice with
+	 * handle_percpu_irq.
+	 */
+	for (i = GIC_PPI_START; i < GIC_SPI_START; i++) {
+		if (i != AVS_SVICINT && i != AVS_SVICINTSWDONE)
+			set_irq_handler(i, handle_percpu_irq);
+	}
+}
+
+static void __init msm8x60_init(void)
+{
+}
+
+MACHINE_START(MSM8X60_RUMI3, "QCT MSM8X60 RUMI3")
+	.map_io = msm8x60_map_io,
+	.init_irq = msm8x60_init_irq,
+	.init_machine = msm8x60_init,
+	.timer = &msm_timer,
+MACHINE_END
+
+MACHINE_START(MSM8X60_SURF, "QCT MSM8X60 SURF")
+	.map_io = msm8x60_map_io,
+	.init_irq = msm8x60_init_irq,
+	.init_machine = msm8x60_init,
+	.timer = &msm_timer,
+MACHINE_END
+
+MACHINE_START(MSM8X60_SIM, "QCT MSM8X60 SIMULATOR")
+	.map_io = msm8x60_map_io,
+	.init_irq = msm8x60_init_irq,
+	.init_machine = msm8x60_init,
+	.timer = &msm_timer,
+MACHINE_END
+
+MACHINE_START(MSM8X60_FFA, "QCT MSM8X60 FFA")
+	.map_io = msm8x60_map_io,
+	.init_irq = msm8x60_init_irq,
+	.init_machine = msm8x60_init,
+	.timer = &msm_timer,
+MACHINE_END
diff --git a/arch/arm/mach-msm/board-qsd8x50.c b/arch/arm/mach-msm/board-qsd8x50.c
index e3cc807..ed2af4a 100644
--- a/arch/arm/mach-msm/board-qsd8x50.c
+++ b/arch/arm/mach-msm/board-qsd8x50.c
@@ -35,21 +35,50 @@
 
 extern struct sys_timer msm_timer;
 
-static struct msm_gpio uart3_config_data[] = {
-	{ GPIO_CFG(86, 1, GPIO_INPUT,   GPIO_PULL_DOWN, GPIO_2MA), "UART2_Rx"},
-	{ GPIO_CFG(87, 1, GPIO_OUTPUT,  GPIO_PULL_DOWN, GPIO_2MA), "UART2_Tx"},
+static const resource_size_t qsd8x50_surf_smc91x_base __initdata = 0x70000300;
+static const unsigned        qsd8x50_surf_smc91x_gpio __initdata = 156;
+
+/* Leave smc91x resources empty here, as we'll fill them in
+ * at run-time: they vary from board to board, and the true
+ * configuration won't be known until boot.
+ */
+static struct resource smc91x_resources[] __initdata = {
+	[0] = {
+		.flags = IORESOURCE_MEM,
+	},
+	[1] = {
+		.flags = IORESOURCE_IRQ,
+	},
 };
 
+static struct platform_device smc91x_device __initdata = {
+	.name           = "smc91x",
+	.id             = 0,
+	.num_resources  = ARRAY_SIZE(smc91x_resources),
+	.resource       = smc91x_resources,
+};
+
+static int __init msm_init_smc91x(void)
+{
+	if (machine_is_qsd8x50_surf()) {
+		smc91x_resources[0].start = qsd8x50_surf_smc91x_base;
+		smc91x_resources[0].end   = qsd8x50_surf_smc91x_base + 0xff;
+		smc91x_resources[1].start =
+			gpio_to_irq(qsd8x50_surf_smc91x_gpio);
+		smc91x_resources[1].end   =
+			gpio_to_irq(qsd8x50_surf_smc91x_gpio);
+		platform_device_register(&smc91x_device);
+	}
+
+	return 0;
+}
+module_init(msm_init_smc91x);
+
 static struct platform_device *devices[] __initdata = {
 	&msm_device_uart3,
+	&msm_device_smd,
 };
 
-static void msm8x50_init_uart3(void)
-{
-	msm_gpios_request_enable(uart3_config_data,
-				ARRAY_SIZE(uart3_config_data));
-}
-
 static void __init qsd8x50_map_io(void)
 {
 	msm_map_qsd8x50_io();
@@ -64,14 +93,11 @@
 
 static void __init qsd8x50_init(void)
 {
-	msm8x50_init_uart3();
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 }
 
 MACHINE_START(QSD8X50_SURF, "QCT QSD8X50 SURF")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io  = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params = PHYS_OFFSET + 0x100,
 	.map_io = qsd8x50_map_io,
@@ -82,8 +108,6 @@
 
 MACHINE_START(QSD8X50A_ST1_5, "QCT QSD8X50A ST1.5")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io  = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params = PHYS_OFFSET + 0x100,
 	.map_io = qsd8x50_map_io,
diff --git a/arch/arm/mach-msm/board-sapphire.c b/arch/arm/mach-msm/board-sapphire.c
index 2bc1b9d..8919ffb1 100644
--- a/arch/arm/mach-msm/board-sapphire.c
+++ b/arch/arm/mach-msm/board-sapphire.c
@@ -106,8 +106,6 @@
 MACHINE_START(SAPPHIRE, "sapphire")
 /* Maintainer: Brian Swetland <swetland@google.com> */
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io        = MSM_DEBUG_UART_PHYS,
-	.io_pg_offst    = ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params    = PHYS_OFFSET + 0x100,
 	.fixup          = sapphire_fixup,
diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c
index 469e0be..73f1460 100644
--- a/arch/arm/mach-msm/board-trout.c
+++ b/arch/arm/mach-msm/board-trout.c
@@ -93,8 +93,6 @@
 
 MACHINE_START(TROUT, "HTC Dream")
 #ifdef CONFIG_MSM_DEBUG_UART
-	.phys_io	= MSM_DEBUG_UART_PHYS,
-	.io_pg_offst	= ((MSM_DEBUG_UART_BASE) >> 18) & 0xfffc,
 #endif
 	.boot_params	= 0x10000100,
 	.fixup		= trout_fixup,
diff --git a/arch/arm/mach-msm/clock-dummy.c b/arch/arm/mach-msm/clock-dummy.c
new file mode 100644
index 0000000..1250d22
--- /dev/null
+++ b/arch/arm/mach-msm/clock-dummy.c
@@ -0,0 +1,54 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ */
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/module.h>
+
+struct clk *clk_get(struct device *dev, const char *id)
+{
+	return ERR_PTR(-ENOENT);
+}
+EXPORT_SYMBOL(clk_get);
+
+int clk_enable(struct clk *clk)
+{
+	return -ENOENT;
+}
+EXPORT_SYMBOL(clk_enable);
+
+void clk_disable(struct clk *clk)
+{
+}
+EXPORT_SYMBOL(clk_disable);
+
+unsigned long clk_get_rate(struct clk *clk)
+{
+	return 0;
+}
+EXPORT_SYMBOL(clk_get_rate);
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	return -ENOENT;
+}
+EXPORT_SYMBOL(clk_set_rate);
+
+void clk_put(struct clk *clk)
+{
+}
+EXPORT_SYMBOL(clk_put);
diff --git a/arch/arm/mach-msm/devices-msm7x30.c b/arch/arm/mach-msm/devices-msm7x30.c
index b449e8a..7fcf2e3 100644
--- a/arch/arm/mach-msm/devices-msm7x30.c
+++ b/arch/arm/mach-msm/devices-msm7x30.c
@@ -51,6 +51,11 @@
 	.resource	= resources_uart2,
 };
 
+struct platform_device msm_device_smd = {
+	.name   = "msm_smd",
+	.id     = -1,
+};
+
 struct clk msm_clocks_7x30[] = {
 	CLK_PCOM("adm_clk",	ADM_CLK,	NULL, 0),
 	CLK_PCOM("adsp_clk",	ADSP_CLK,	NULL, 0),
diff --git a/arch/arm/mach-msm/devices-msm8x60-iommu.c b/arch/arm/mach-msm/devices-msm8x60-iommu.c
new file mode 100644
index 0000000..89b9d44
--- /dev/null
+++ b/arch/arm/mach-msm/devices-msm8x60-iommu.c
@@ -0,0 +1,883 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/bootmem.h>
+
+#include <mach/msm_iomap-8x60.h>
+#include <mach/irqs-8x60.h>
+#include <mach/iommu.h>
+
+static struct resource msm_iommu_jpegd_resources[] = {
+	{
+		.start = MSM_IOMMU_JPEGD_PHYS,
+		.end   = MSM_IOMMU_JPEGD_PHYS + MSM_IOMMU_JPEGD_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_JPEGD_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_JPEGD_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_JPEGD_CB_SC_SECURE_IRQ,
+		.end   = SMMU_JPEGD_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_vpe_resources[] = {
+	{
+		.start = MSM_IOMMU_VPE_PHYS,
+		.end   = MSM_IOMMU_VPE_PHYS + MSM_IOMMU_VPE_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_VPE_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_VPE_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_VPE_CB_SC_SECURE_IRQ,
+		.end   = SMMU_VPE_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_mdp0_resources[] = {
+	{
+		.start = MSM_IOMMU_MDP0_PHYS,
+		.end   = MSM_IOMMU_MDP0_PHYS + MSM_IOMMU_MDP0_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_MDP0_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_MDP0_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_MDP0_CB_SC_SECURE_IRQ,
+		.end   = SMMU_MDP0_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_mdp1_resources[] = {
+	{
+		.start = MSM_IOMMU_MDP1_PHYS,
+		.end   = MSM_IOMMU_MDP1_PHYS + MSM_IOMMU_MDP1_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_MDP1_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_MDP1_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_MDP1_CB_SC_SECURE_IRQ,
+		.end   = SMMU_MDP1_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_rot_resources[] = {
+	{
+		.start = MSM_IOMMU_ROT_PHYS,
+		.end   = MSM_IOMMU_ROT_PHYS + MSM_IOMMU_ROT_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_ROT_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_ROT_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_ROT_CB_SC_SECURE_IRQ,
+		.end   = SMMU_ROT_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_ijpeg_resources[] = {
+	{
+		.start = MSM_IOMMU_IJPEG_PHYS,
+		.end   = MSM_IOMMU_IJPEG_PHYS + MSM_IOMMU_IJPEG_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_IJPEG_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_IJPEG_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_IJPEG_CB_SC_SECURE_IRQ,
+		.end   = SMMU_IJPEG_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_vfe_resources[] = {
+	{
+		.start = MSM_IOMMU_VFE_PHYS,
+		.end   = MSM_IOMMU_VFE_PHYS + MSM_IOMMU_VFE_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_VFE_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_VFE_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_VFE_CB_SC_SECURE_IRQ,
+		.end   = SMMU_VFE_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_vcodec_a_resources[] = {
+	{
+		.start = MSM_IOMMU_VCODEC_A_PHYS,
+		.end   = MSM_IOMMU_VCODEC_A_PHYS + MSM_IOMMU_VCODEC_A_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_VCODEC_A_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_VCODEC_A_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_VCODEC_A_CB_SC_SECURE_IRQ,
+		.end   = SMMU_VCODEC_A_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_vcodec_b_resources[] = {
+	{
+		.start = MSM_IOMMU_VCODEC_B_PHYS,
+		.end   = MSM_IOMMU_VCODEC_B_PHYS + MSM_IOMMU_VCODEC_B_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_VCODEC_B_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_VCODEC_B_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_VCODEC_B_CB_SC_SECURE_IRQ,
+		.end   = SMMU_VCODEC_B_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_gfx3d_resources[] = {
+	{
+		.start = MSM_IOMMU_GFX3D_PHYS,
+		.end   = MSM_IOMMU_GFX3D_PHYS + MSM_IOMMU_GFX3D_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_GFX3D_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_GFX3D_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_GFX3D_CB_SC_SECURE_IRQ,
+		.end   = SMMU_GFX3D_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource msm_iommu_gfx2d0_resources[] = {
+	{
+		.start = MSM_IOMMU_GFX2D0_PHYS,
+		.end   = MSM_IOMMU_GFX2D0_PHYS + MSM_IOMMU_GFX2D0_SIZE - 1,
+		.name  = "physbase",
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "nonsecure_irq",
+		.start = SMMU_GFX2D0_CB_SC_NON_SECURE_IRQ,
+		.end   = SMMU_GFX2D0_CB_SC_NON_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name = "secure_irq",
+		.start = SMMU_GFX2D0_CB_SC_SECURE_IRQ,
+		.end   = SMMU_GFX2D0_CB_SC_SECURE_IRQ,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device msm_root_iommu_dev = {
+	.name = "msm_iommu",
+	.id = -1,
+};
+
+static struct msm_iommu_dev jpegd_smmu = {
+	.name = "jpegd",
+	.clk_rate = -1
+};
+
+static struct msm_iommu_dev vpe_smmu = {
+	.name = "vpe"
+};
+
+static struct msm_iommu_dev mdp0_smmu = {
+	.name = "mdp0"
+};
+
+static struct msm_iommu_dev mdp1_smmu = {
+	.name = "mdp1"
+};
+
+static struct msm_iommu_dev rot_smmu = {
+	.name = "rot"
+};
+
+static struct msm_iommu_dev ijpeg_smmu = {
+	.name = "ijpeg"
+};
+
+static struct msm_iommu_dev vfe_smmu = {
+	.name = "vfe",
+	.clk_rate = -1
+};
+
+static struct msm_iommu_dev vcodec_a_smmu = {
+	.name = "vcodec_a"
+};
+
+static struct msm_iommu_dev vcodec_b_smmu = {
+	.name = "vcodec_b"
+};
+
+static struct msm_iommu_dev gfx3d_smmu = {
+	.name = "gfx3d",
+	.clk_rate = 27000000
+};
+
+static struct msm_iommu_dev gfx2d0_smmu = {
+	.name = "gfx2d0",
+	.clk_rate = 27000000
+};
+
+static struct platform_device msm_device_smmu_jpegd = {
+	.name = "msm_iommu",
+	.id = 0,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_jpegd_resources),
+	.resource = msm_iommu_jpegd_resources,
+};
+
+static struct platform_device msm_device_smmu_vpe = {
+	.name = "msm_iommu",
+	.id = 1,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_vpe_resources),
+	.resource = msm_iommu_vpe_resources,
+};
+
+static struct platform_device msm_device_smmu_mdp0 = {
+	.name = "msm_iommu",
+	.id = 2,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_mdp0_resources),
+	.resource = msm_iommu_mdp0_resources,
+};
+
+static struct platform_device msm_device_smmu_mdp1 = {
+	.name = "msm_iommu",
+	.id = 3,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_mdp1_resources),
+	.resource = msm_iommu_mdp1_resources,
+};
+
+static struct platform_device msm_device_smmu_rot = {
+	.name = "msm_iommu",
+	.id = 4,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_rot_resources),
+	.resource = msm_iommu_rot_resources,
+};
+
+static struct platform_device msm_device_smmu_ijpeg = {
+	.name = "msm_iommu",
+	.id = 5,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_ijpeg_resources),
+	.resource = msm_iommu_ijpeg_resources,
+};
+
+static struct platform_device msm_device_smmu_vfe = {
+	.name = "msm_iommu",
+	.id = 6,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_vfe_resources),
+	.resource = msm_iommu_vfe_resources,
+};
+
+static struct platform_device msm_device_smmu_vcodec_a = {
+	.name = "msm_iommu",
+	.id = 7,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_vcodec_a_resources),
+	.resource = msm_iommu_vcodec_a_resources,
+};
+
+static struct platform_device msm_device_smmu_vcodec_b = {
+	.name = "msm_iommu",
+	.id = 8,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_vcodec_b_resources),
+	.resource = msm_iommu_vcodec_b_resources,
+};
+
+static struct platform_device msm_device_smmu_gfx3d = {
+	.name = "msm_iommu",
+	.id = 9,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_gfx3d_resources),
+	.resource = msm_iommu_gfx3d_resources,
+};
+
+static struct platform_device msm_device_smmu_gfx2d0 = {
+	.name = "msm_iommu",
+	.id = 10,
+	.dev = {
+		.parent = &msm_root_iommu_dev.dev,
+	},
+	.num_resources = ARRAY_SIZE(msm_iommu_gfx2d0_resources),
+	.resource = msm_iommu_gfx2d0_resources,
+};
+
+static struct msm_iommu_ctx_dev jpegd_src_ctx = {
+	.name = "jpegd_src",
+	.num = 0,
+	.mids = {0, -1}
+};
+
+static struct msm_iommu_ctx_dev jpegd_dst_ctx = {
+	.name = "jpegd_dst",
+	.num = 1,
+	.mids = {1, -1}
+};
+
+static struct msm_iommu_ctx_dev vpe_src_ctx = {
+	.name = "vpe_src",
+	.num = 0,
+	.mids = {0, -1}
+};
+
+static struct msm_iommu_ctx_dev vpe_dst_ctx = {
+	.name = "vpe_dst",
+	.num = 1,
+	.mids = {1, -1}
+};
+
+static struct msm_iommu_ctx_dev mdp_vg1_ctx = {
+	.name = "mdp_vg1",
+	.num = 0,
+	.mids = {0, 2, -1}
+};
+
+static struct msm_iommu_ctx_dev mdp_rgb1_ctx = {
+	.name = "mdp_rgb1",
+	.num = 1,
+	.mids = {1, 3, 4, 5, 6, 7, 8, 9, 10, -1}
+};
+
+static struct msm_iommu_ctx_dev mdp_vg2_ctx = {
+	.name = "mdp_vg2",
+	.num = 0,
+	.mids = {0, 2, -1}
+};
+
+static struct msm_iommu_ctx_dev mdp_rgb2_ctx = {
+	.name = "mdp_rgb2",
+	.num = 1,
+	.mids = {1, 3, 4, 5, 6, 7, 8, 9, 10, -1}
+};
+
+static struct msm_iommu_ctx_dev rot_src_ctx = {
+	.name = "rot_src",
+	.num = 0,
+	.mids = {0, -1}
+};
+
+static struct msm_iommu_ctx_dev rot_dst_ctx = {
+	.name = "rot_dst",
+	.num = 1,
+	.mids = {1, -1}
+};
+
+static struct msm_iommu_ctx_dev ijpeg_src_ctx = {
+	.name = "ijpeg_src",
+	.num = 0,
+	.mids = {0, -1}
+};
+
+static struct msm_iommu_ctx_dev ijpeg_dst_ctx = {
+	.name = "ijpeg_dst",
+	.num = 1,
+	.mids = {1, -1}
+};
+
+static struct msm_iommu_ctx_dev vfe_imgwr_ctx = {
+	.name = "vfe_imgwr",
+	.num = 0,
+	.mids = {2, 3, 4, 5, 6, 7, 8, -1}
+};
+
+static struct msm_iommu_ctx_dev vfe_misc_ctx = {
+	.name = "vfe_misc",
+	.num = 1,
+	.mids = {0, 1, 9, -1}
+};
+
+static struct msm_iommu_ctx_dev vcodec_a_stream_ctx = {
+	.name = "vcodec_a_stream",
+	.num = 0,
+	.mids = {2, 5, -1}
+};
+
+static struct msm_iommu_ctx_dev vcodec_a_mm1_ctx = {
+	.name = "vcodec_a_mm1",
+	.num = 1,
+	.mids = {0, 1, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, -1}
+};
+
+static struct msm_iommu_ctx_dev vcodec_b_mm2_ctx = {
+	.name = "vcodec_b_mm2",
+	.num = 0,
+	.mids = {0, 1, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, -1}
+};
+
+static struct msm_iommu_ctx_dev gfx3d_rbpa_ctx = {
+	.name = "gfx3d_rbpa",
+	.num = 0,
+	.mids = {-1}
+};
+
+static struct msm_iommu_ctx_dev gfx3d_cpvgttc_ctx = {
+	.name = "gfx3d_cpvgttc",
+	.num = 1,
+	.mids = {0, 1, 2, 3, 4, 5, 6, 7, -1}
+};
+
+static struct msm_iommu_ctx_dev gfx3d_smmu_ctx = {
+	.name = "gfx3d_smmu",
+	.num = 2,
+	.mids = {8, 9, 10, 11, 12, -1}
+};
+
+static struct msm_iommu_ctx_dev gfx2d0_pixv1_ctx = {
+	.name = "gfx2d0_pixv1_smmu",
+	.num = 0,
+	.mids = {0, 3, 4, -1}
+};
+
+static struct msm_iommu_ctx_dev gfx2d0_texv3_ctx = {
+	.name = "gfx2d0_texv3_smmu",
+	.num = 1,
+	.mids = {1, 6, 7, -1}
+};
+
+static struct platform_device msm_device_jpegd_src_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 0,
+	.dev = {
+		.parent = &msm_device_smmu_jpegd.dev,
+	},
+};
+
+static struct platform_device msm_device_jpegd_dst_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 1,
+	.dev = {
+		.parent = &msm_device_smmu_jpegd.dev,
+	},
+};
+
+static struct platform_device msm_device_vpe_src_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 2,
+	.dev = {
+		.parent = &msm_device_smmu_vpe.dev,
+	},
+};
+
+static struct platform_device msm_device_vpe_dst_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 3,
+	.dev = {
+		.parent = &msm_device_smmu_vpe.dev,
+	},
+};
+
+static struct platform_device msm_device_mdp_vg1_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 4,
+	.dev = {
+		.parent = &msm_device_smmu_mdp0.dev,
+	},
+};
+
+static struct platform_device msm_device_mdp_rgb1_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 5,
+	.dev = {
+		.parent = &msm_device_smmu_mdp0.dev,
+	},
+};
+
+static struct platform_device msm_device_mdp_vg2_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 6,
+	.dev = {
+		.parent = &msm_device_smmu_mdp1.dev,
+	},
+};
+
+static struct platform_device msm_device_mdp_rgb2_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 7,
+	.dev = {
+		.parent = &msm_device_smmu_mdp1.dev,
+	},
+};
+
+static struct platform_device msm_device_rot_src_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 8,
+	.dev = {
+		.parent = &msm_device_smmu_rot.dev,
+	},
+};
+
+static struct platform_device msm_device_rot_dst_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 9,
+	.dev = {
+		.parent = &msm_device_smmu_rot.dev,
+	},
+};
+
+static struct platform_device msm_device_ijpeg_src_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 10,
+	.dev = {
+		.parent = &msm_device_smmu_ijpeg.dev,
+	},
+};
+
+static struct platform_device msm_device_ijpeg_dst_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 11,
+	.dev = {
+		.parent = &msm_device_smmu_ijpeg.dev,
+	},
+};
+
+static struct platform_device msm_device_vfe_imgwr_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 12,
+	.dev = {
+		.parent = &msm_device_smmu_vfe.dev,
+	},
+};
+
+static struct platform_device msm_device_vfe_misc_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 13,
+	.dev = {
+		.parent = &msm_device_smmu_vfe.dev,
+	},
+};
+
+static struct platform_device msm_device_vcodec_a_stream_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 14,
+	.dev = {
+		.parent = &msm_device_smmu_vcodec_a.dev,
+	},
+};
+
+static struct platform_device msm_device_vcodec_a_mm1_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 15,
+	.dev = {
+		.parent = &msm_device_smmu_vcodec_a.dev,
+	},
+};
+
+static struct platform_device msm_device_vcodec_b_mm2_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 16,
+	.dev = {
+		.parent = &msm_device_smmu_vcodec_b.dev,
+	},
+};
+
+static struct platform_device msm_device_gfx3d_rbpa_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 17,
+	.dev = {
+		.parent = &msm_device_smmu_gfx3d.dev,
+	},
+};
+
+static struct platform_device msm_device_gfx3d_cpvgttc_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 18,
+	.dev = {
+		.parent = &msm_device_smmu_gfx3d.dev,
+	},
+};
+
+static struct platform_device msm_device_gfx3d_smmu_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 19,
+	.dev = {
+		.parent = &msm_device_smmu_gfx3d.dev,
+	},
+};
+
+static struct platform_device msm_device_gfx2d0_pixv1_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 20,
+	.dev = {
+		.parent = &msm_device_smmu_gfx2d0.dev,
+	},
+};
+
+static struct platform_device msm_device_gfx2d0_texv3_ctx = {
+	.name = "msm_iommu_ctx",
+	.id = 21,
+	.dev = {
+		.parent = &msm_device_smmu_gfx2d0.dev,
+	},
+};
+
+static struct platform_device *msm_iommu_devs[] = {
+	&msm_device_smmu_jpegd,
+	&msm_device_smmu_vpe,
+	&msm_device_smmu_mdp0,
+	&msm_device_smmu_mdp1,
+	&msm_device_smmu_rot,
+	&msm_device_smmu_ijpeg,
+	&msm_device_smmu_vfe,
+	&msm_device_smmu_vcodec_a,
+	&msm_device_smmu_vcodec_b,
+	&msm_device_smmu_gfx3d,
+	&msm_device_smmu_gfx2d0,
+};
+
+static struct msm_iommu_dev *msm_iommu_data[] = {
+	&jpegd_smmu,
+	&vpe_smmu,
+	&mdp0_smmu,
+	&mdp1_smmu,
+	&rot_smmu,
+	&ijpeg_smmu,
+	&vfe_smmu,
+	&vcodec_a_smmu,
+	&vcodec_b_smmu,
+	&gfx3d_smmu,
+	&gfx2d0_smmu,
+};
+
+static struct platform_device *msm_iommu_ctx_devs[] = {
+	&msm_device_jpegd_src_ctx,
+	&msm_device_jpegd_dst_ctx,
+	&msm_device_vpe_src_ctx,
+	&msm_device_vpe_dst_ctx,
+	&msm_device_mdp_vg1_ctx,
+	&msm_device_mdp_rgb1_ctx,
+	&msm_device_mdp_vg2_ctx,
+	&msm_device_mdp_rgb2_ctx,
+	&msm_device_rot_src_ctx,
+	&msm_device_rot_dst_ctx,
+	&msm_device_ijpeg_src_ctx,
+	&msm_device_ijpeg_dst_ctx,
+	&msm_device_vfe_imgwr_ctx,
+	&msm_device_vfe_misc_ctx,
+	&msm_device_vcodec_a_stream_ctx,
+	&msm_device_vcodec_a_mm1_ctx,
+	&msm_device_vcodec_b_mm2_ctx,
+	&msm_device_gfx3d_rbpa_ctx,
+	&msm_device_gfx3d_cpvgttc_ctx,
+	&msm_device_gfx3d_smmu_ctx,
+	&msm_device_gfx2d0_pixv1_ctx,
+	&msm_device_gfx2d0_texv3_ctx,
+};
+
+static struct msm_iommu_ctx_dev *msm_iommu_ctx_data[] = {
+	&jpegd_src_ctx,
+	&jpegd_dst_ctx,
+	&vpe_src_ctx,
+	&vpe_dst_ctx,
+	&mdp_vg1_ctx,
+	&mdp_rgb1_ctx,
+	&mdp_vg2_ctx,
+	&mdp_rgb2_ctx,
+	&rot_src_ctx,
+	&rot_dst_ctx,
+	&ijpeg_src_ctx,
+	&ijpeg_dst_ctx,
+	&vfe_imgwr_ctx,
+	&vfe_misc_ctx,
+	&vcodec_a_stream_ctx,
+	&vcodec_a_mm1_ctx,
+	&vcodec_b_mm2_ctx,
+	&gfx3d_rbpa_ctx,
+	&gfx3d_cpvgttc_ctx,
+	&gfx3d_smmu_ctx,
+	&gfx2d0_pixv1_ctx,
+	&gfx2d0_texv3_ctx,
+};
+
+static int msm8x60_iommu_init(void)
+{
+	int ret, i;
+
+	ret = platform_device_register(&msm_root_iommu_dev);
+	if (ret != 0) {
+		pr_err("Failed to register root IOMMU device!\n");
+		goto failure;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(msm_iommu_devs); i++) {
+		ret = platform_device_add_data(msm_iommu_devs[i],
+					       msm_iommu_data[i],
+					       sizeof(struct msm_iommu_dev));
+		if (ret != 0) {
+			pr_err("platform_device_add_data failed, "
+			       "i = %d\n", i);
+			goto failure_unwind;
+		}
+
+		ret = platform_device_register(msm_iommu_devs[i]);
+
+		if (ret != 0) {
+			pr_err("platform_device_register smmu failed, "
+			       "i = %d\n", i);
+			goto failure_unwind;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(msm_iommu_ctx_devs); i++) {
+		ret = platform_device_add_data(msm_iommu_ctx_devs[i],
+					       msm_iommu_ctx_data[i],
+					       sizeof(*msm_iommu_ctx_devs[i]));
+		if (ret != 0) {
+			pr_err("platform_device_add_data smmu failed, "
+			       "i = %d\n", i);
+			goto failure_unwind2;
+		}
+
+		ret = platform_device_register(msm_iommu_ctx_devs[i]);
+		if (ret != 0) {
+			pr_err("platform_device_register ctx failed, "
+			       "i = %d\n", i);
+			goto failure_unwind2;
+		}
+	}
+	return 0;
+
+failure_unwind2:
+	while (--i >= 0)
+		platform_device_unregister(msm_iommu_ctx_devs[i]);
+failure_unwind:
+	while (--i >= 0)
+		platform_device_unregister(msm_iommu_devs[i]);
+
+	platform_device_unregister(&msm_root_iommu_dev);
+failure:
+	return ret;
+}
+
+static void msm8x60_iommu_exit(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(msm_iommu_ctx_devs); i++)
+		platform_device_unregister(msm_iommu_ctx_devs[i]);
+
+	for (i = 0; i < ARRAY_SIZE(msm_iommu_devs); ++i)
+		platform_device_unregister(msm_iommu_devs[i]);
+
+	platform_device_unregister(&msm_root_iommu_dev);
+}
+
+subsys_initcall(msm8x60_iommu_init);
+module_exit(msm8x60_iommu_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
diff --git a/arch/arm/mach-msm/devices-qsd8x50.c b/arch/arm/mach-msm/devices-qsd8x50.c
index 4d4a507..6fe67c5 100644
--- a/arch/arm/mach-msm/devices-qsd8x50.c
+++ b/arch/arm/mach-msm/devices-qsd8x50.c
@@ -48,6 +48,11 @@
 	.resource	= resources_uart3,
 };
 
+struct platform_device msm_device_smd = {
+	.name   = "msm_smd",
+	.id     = -1,
+};
+
 struct clk msm_clocks_8x50[] = {
 	CLK_PCOM("adm_clk",	ADM_CLK,	NULL, 0),
 	CLK_PCOM("ebi1_clk",	EBI1_CLK,	NULL, CLK_MIN),
diff --git a/arch/arm/mach-msm/gpio.c b/arch/arm/mach-msm/gpio.c
index bc32c84..33051b5 100644
--- a/arch/arm/mach-msm/gpio.c
+++ b/arch/arm/mach-msm/gpio.c
@@ -1,7 +1,7 @@
 /* linux/arch/arm/mach-msm/gpio.c
  *
  * Copyright (C) 2007 Google, Inc.
- * Copyright (c) 2009, Code Aurora Forum. All rights reserved.
+ * Copyright (c) 2009-2010, Code Aurora Forum. All rights reserved.
  *
  * This software is licensed under the terms of the GNU General Public
  * License version 2, as published by the Free Software Foundation, and
@@ -14,72 +14,363 @@
  *
  */
 
+#include <linux/bitops.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/module.h>
-#include <mach/gpio.h>
-#include "proc_comm.h"
+#include "gpio_hw.h"
+#include "gpiomux.h"
 
-int gpio_tlmm_config(unsigned config, unsigned disable)
-{
-	return msm_proc_comm(PCOM_RPC_GPIO_TLMM_CONFIG_EX, &config, &disable);
-}
-EXPORT_SYMBOL(gpio_tlmm_config);
+#define FIRST_GPIO_IRQ MSM_GPIO_TO_INT(0)
 
-int msm_gpios_enable(const struct msm_gpio *table, int size)
-{
-	int rc;
-	int i;
-	const struct msm_gpio *g;
-	for (i = 0; i < size; i++) {
-		g = table + i;
-		rc = gpio_tlmm_config(g->gpio_cfg, GPIO_ENABLE);
-		if (rc) {
-			pr_err("gpio_tlmm_config(0x%08x, GPIO_ENABLE)"
-			       " <%s> failed: %d\n",
-			       g->gpio_cfg, g->label ?: "?", rc);
-			pr_err("pin %d func %d dir %d pull %d drvstr %d\n",
-			       GPIO_PIN(g->gpio_cfg), GPIO_FUNC(g->gpio_cfg),
-			       GPIO_DIR(g->gpio_cfg), GPIO_PULL(g->gpio_cfg),
-			       GPIO_DRVSTR(g->gpio_cfg));
-			goto err;
-		}
+#define MSM_GPIO_BANK(bank, first, last)				\
+	{								\
+		.regs = {						\
+			.out =         MSM_GPIO_OUT_##bank,		\
+			.in =          MSM_GPIO_IN_##bank,		\
+			.int_status =  MSM_GPIO_INT_STATUS_##bank,	\
+			.int_clear =   MSM_GPIO_INT_CLEAR_##bank,	\
+			.int_en =      MSM_GPIO_INT_EN_##bank,		\
+			.int_edge =    MSM_GPIO_INT_EDGE_##bank,	\
+			.int_pos =     MSM_GPIO_INT_POS_##bank,		\
+			.oe =          MSM_GPIO_OE_##bank,		\
+		},							\
+		.chip = {						\
+			.base = (first),				\
+			.ngpio = (last) - (first) + 1,			\
+			.get = msm_gpio_get,				\
+			.set = msm_gpio_set,				\
+			.direction_input = msm_gpio_direction_input,	\
+			.direction_output = msm_gpio_direction_output,	\
+			.to_irq = msm_gpio_to_irq,			\
+			.request = msm_gpio_request,			\
+			.free = msm_gpio_free,				\
+		}							\
 	}
+
+#define MSM_GPIO_BROKEN_INT_CLEAR 1
+
+struct msm_gpio_regs {
+	void __iomem *out;
+	void __iomem *in;
+	void __iomem *int_status;
+	void __iomem *int_clear;
+	void __iomem *int_en;
+	void __iomem *int_edge;
+	void __iomem *int_pos;
+	void __iomem *oe;
+};
+
+struct msm_gpio_chip {
+	spinlock_t		lock;
+	struct gpio_chip	chip;
+	struct msm_gpio_regs	regs;
+#if MSM_GPIO_BROKEN_INT_CLEAR
+	unsigned                int_status_copy;
+#endif
+	unsigned int            both_edge_detect;
+	unsigned int            int_enable[2]; /* 0: awake, 1: sleep */
+};
+
+static int msm_gpio_write(struct msm_gpio_chip *msm_chip,
+			  unsigned offset, unsigned on)
+{
+	unsigned mask = BIT(offset);
+	unsigned val;
+
+	val = readl(msm_chip->regs.out);
+	if (on)
+		writel(val | mask, msm_chip->regs.out);
+	else
+		writel(val & ~mask, msm_chip->regs.out);
 	return 0;
-err:
-	msm_gpios_disable(table, i);
-	return rc;
 }
-EXPORT_SYMBOL(msm_gpios_enable);
 
-void msm_gpios_disable(const struct msm_gpio *table, int size)
+static void msm_gpio_update_both_edge_detect(struct msm_gpio_chip *msm_chip)
 {
-	int rc;
-	int i;
-	const struct msm_gpio *g;
-	for (i = size-1; i >= 0; i--) {
-		g = table + i;
-		rc = gpio_tlmm_config(g->gpio_cfg, GPIO_DISABLE);
-		if (rc) {
-			pr_err("gpio_tlmm_config(0x%08x, GPIO_DISABLE)"
-			       " <%s> failed: %d\n",
-			       g->gpio_cfg, g->label ?: "?", rc);
-			pr_err("pin %d func %d dir %d pull %d drvstr %d\n",
-			       GPIO_PIN(g->gpio_cfg), GPIO_FUNC(g->gpio_cfg),
-			       GPIO_DIR(g->gpio_cfg), GPIO_PULL(g->gpio_cfg),
-			       GPIO_DRVSTR(g->gpio_cfg));
+	int loop_limit = 100;
+	unsigned pol, val, val2, intstat;
+	do {
+		val = readl(msm_chip->regs.in);
+		pol = readl(msm_chip->regs.int_pos);
+		pol = (pol & ~msm_chip->both_edge_detect) |
+		      (~val & msm_chip->both_edge_detect);
+		writel(pol, msm_chip->regs.int_pos);
+		intstat = readl(msm_chip->regs.int_status);
+		val2 = readl(msm_chip->regs.in);
+		if (((val ^ val2) & msm_chip->both_edge_detect & ~intstat) == 0)
+			return;
+	} while (loop_limit-- > 0);
+	printk(KERN_ERR "msm_gpio_update_both_edge_detect, "
+	       "failed to reach stable state %x != %x\n", val, val2);
+}
+
+static int msm_gpio_clear_detect_status(struct msm_gpio_chip *msm_chip,
+					unsigned offset)
+{
+	unsigned bit = BIT(offset);
+
+#if MSM_GPIO_BROKEN_INT_CLEAR
+	/* Save interrupts that already triggered before we loose them. */
+	/* Any interrupt that triggers between the read of int_status */
+	/* and the write to int_clear will still be lost though. */
+	msm_chip->int_status_copy |= readl(msm_chip->regs.int_status);
+	msm_chip->int_status_copy &= ~bit;
+#endif
+	writel(bit, msm_chip->regs.int_clear);
+	msm_gpio_update_both_edge_detect(msm_chip);
+	return 0;
+}
+
+static int msm_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
+{
+	struct msm_gpio_chip *msm_chip;
+	unsigned long irq_flags;
+
+	msm_chip = container_of(chip, struct msm_gpio_chip, chip);
+	spin_lock_irqsave(&msm_chip->lock, irq_flags);
+	writel(readl(msm_chip->regs.oe) & ~BIT(offset), msm_chip->regs.oe);
+	spin_unlock_irqrestore(&msm_chip->lock, irq_flags);
+	return 0;
+}
+
+static int
+msm_gpio_direction_output(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct msm_gpio_chip *msm_chip;
+	unsigned long irq_flags;
+
+	msm_chip = container_of(chip, struct msm_gpio_chip, chip);
+	spin_lock_irqsave(&msm_chip->lock, irq_flags);
+	msm_gpio_write(msm_chip, offset, value);
+	writel(readl(msm_chip->regs.oe) | BIT(offset), msm_chip->regs.oe);
+	spin_unlock_irqrestore(&msm_chip->lock, irq_flags);
+	return 0;
+}
+
+static int msm_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct msm_gpio_chip *msm_chip;
+
+	msm_chip = container_of(chip, struct msm_gpio_chip, chip);
+	return (readl(msm_chip->regs.in) & (1U << offset)) ? 1 : 0;
+}
+
+static void msm_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct msm_gpio_chip *msm_chip;
+	unsigned long irq_flags;
+
+	msm_chip = container_of(chip, struct msm_gpio_chip, chip);
+	spin_lock_irqsave(&msm_chip->lock, irq_flags);
+	msm_gpio_write(msm_chip, offset, value);
+	spin_unlock_irqrestore(&msm_chip->lock, irq_flags);
+}
+
+static int msm_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+	return MSM_GPIO_TO_INT(chip->base + offset);
+}
+
+#ifdef CONFIG_MSM_GPIOMUX
+static int msm_gpio_request(struct gpio_chip *chip, unsigned offset)
+{
+	return msm_gpiomux_get(chip->base + offset);
+}
+
+static void msm_gpio_free(struct gpio_chip *chip, unsigned offset)
+{
+	msm_gpiomux_put(chip->base + offset);
+}
+#else
+#define msm_gpio_request NULL
+#define msm_gpio_free NULL
+#endif
+
+struct msm_gpio_chip msm_gpio_chips[] = {
+#if defined(CONFIG_ARCH_MSM7X00A)
+	MSM_GPIO_BANK(0,   0,  15),
+	MSM_GPIO_BANK(1,  16,  42),
+	MSM_GPIO_BANK(2,  43,  67),
+	MSM_GPIO_BANK(3,  68,  94),
+	MSM_GPIO_BANK(4,  95, 106),
+	MSM_GPIO_BANK(5, 107, 121),
+#elif defined(CONFIG_ARCH_MSM7X25) || defined(CONFIG_ARCH_MSM7X27)
+	MSM_GPIO_BANK(0,   0,  15),
+	MSM_GPIO_BANK(1,  16,  42),
+	MSM_GPIO_BANK(2,  43,  67),
+	MSM_GPIO_BANK(3,  68,  94),
+	MSM_GPIO_BANK(4,  95, 106),
+	MSM_GPIO_BANK(5, 107, 132),
+#elif defined(CONFIG_ARCH_MSM7X30)
+	MSM_GPIO_BANK(0,   0,  15),
+	MSM_GPIO_BANK(1,  16,  43),
+	MSM_GPIO_BANK(2,  44,  67),
+	MSM_GPIO_BANK(3,  68,  94),
+	MSM_GPIO_BANK(4,  95, 106),
+	MSM_GPIO_BANK(5, 107, 133),
+	MSM_GPIO_BANK(6, 134, 150),
+	MSM_GPIO_BANK(7, 151, 181),
+#elif defined(CONFIG_ARCH_QSD8X50)
+	MSM_GPIO_BANK(0,   0,  15),
+	MSM_GPIO_BANK(1,  16,  42),
+	MSM_GPIO_BANK(2,  43,  67),
+	MSM_GPIO_BANK(3,  68,  94),
+	MSM_GPIO_BANK(4,  95, 103),
+	MSM_GPIO_BANK(5, 104, 121),
+	MSM_GPIO_BANK(6, 122, 152),
+	MSM_GPIO_BANK(7, 153, 164),
+#endif
+};
+
+static void msm_gpio_irq_ack(unsigned int irq)
+{
+	unsigned long irq_flags;
+	struct msm_gpio_chip *msm_chip = get_irq_chip_data(irq);
+	spin_lock_irqsave(&msm_chip->lock, irq_flags);
+	msm_gpio_clear_detect_status(msm_chip,
+				     irq - gpio_to_irq(msm_chip->chip.base));
+	spin_unlock_irqrestore(&msm_chip->lock, irq_flags);
+}
+
+static void msm_gpio_irq_mask(unsigned int irq)
+{
+	unsigned long irq_flags;
+	struct msm_gpio_chip *msm_chip = get_irq_chip_data(irq);
+	unsigned offset = irq - gpio_to_irq(msm_chip->chip.base);
+
+	spin_lock_irqsave(&msm_chip->lock, irq_flags);
+	/* level triggered interrupts are also latched */
+	if (!(readl(msm_chip->regs.int_edge) & BIT(offset)))
+		msm_gpio_clear_detect_status(msm_chip, offset);
+	msm_chip->int_enable[0] &= ~BIT(offset);
+	writel(msm_chip->int_enable[0], msm_chip->regs.int_en);
+	spin_unlock_irqrestore(&msm_chip->lock, irq_flags);
+}
+
+static void msm_gpio_irq_unmask(unsigned int irq)
+{
+	unsigned long irq_flags;
+	struct msm_gpio_chip *msm_chip = get_irq_chip_data(irq);
+	unsigned offset = irq - gpio_to_irq(msm_chip->chip.base);
+
+	spin_lock_irqsave(&msm_chip->lock, irq_flags);
+	/* level triggered interrupts are also latched */
+	if (!(readl(msm_chip->regs.int_edge) & BIT(offset)))
+		msm_gpio_clear_detect_status(msm_chip, offset);
+	msm_chip->int_enable[0] |= BIT(offset);
+	writel(msm_chip->int_enable[0], msm_chip->regs.int_en);
+	spin_unlock_irqrestore(&msm_chip->lock, irq_flags);
+}
+
+static int msm_gpio_irq_set_wake(unsigned int irq, unsigned int on)
+{
+	unsigned long irq_flags;
+	struct msm_gpio_chip *msm_chip = get_irq_chip_data(irq);
+	unsigned offset = irq - gpio_to_irq(msm_chip->chip.base);
+
+	spin_lock_irqsave(&msm_chip->lock, irq_flags);
+
+	if (on)
+		msm_chip->int_enable[1] |= BIT(offset);
+	else
+		msm_chip->int_enable[1] &= ~BIT(offset);
+
+	spin_unlock_irqrestore(&msm_chip->lock, irq_flags);
+	return 0;
+}
+
+static int msm_gpio_irq_set_type(unsigned int irq, unsigned int flow_type)
+{
+	unsigned long irq_flags;
+	struct msm_gpio_chip *msm_chip = get_irq_chip_data(irq);
+	unsigned offset = irq - gpio_to_irq(msm_chip->chip.base);
+	unsigned val, mask = BIT(offset);
+
+	spin_lock_irqsave(&msm_chip->lock, irq_flags);
+	val = readl(msm_chip->regs.int_edge);
+	if (flow_type & IRQ_TYPE_EDGE_BOTH) {
+		writel(val | mask, msm_chip->regs.int_edge);
+		irq_desc[irq].handle_irq = handle_edge_irq;
+	} else {
+		writel(val & ~mask, msm_chip->regs.int_edge);
+		irq_desc[irq].handle_irq = handle_level_irq;
+	}
+	if ((flow_type & IRQ_TYPE_EDGE_BOTH) == IRQ_TYPE_EDGE_BOTH) {
+		msm_chip->both_edge_detect |= mask;
+		msm_gpio_update_both_edge_detect(msm_chip);
+	} else {
+		msm_chip->both_edge_detect &= ~mask;
+		val = readl(msm_chip->regs.int_pos);
+		if (flow_type & (IRQF_TRIGGER_RISING | IRQF_TRIGGER_HIGH))
+			writel(val | mask, msm_chip->regs.int_pos);
+		else
+			writel(val & ~mask, msm_chip->regs.int_pos);
+	}
+	spin_unlock_irqrestore(&msm_chip->lock, irq_flags);
+	return 0;
+}
+
+static void msm_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+{
+	int i, j, mask;
+	unsigned val;
+
+	for (i = 0; i < ARRAY_SIZE(msm_gpio_chips); i++) {
+		struct msm_gpio_chip *msm_chip = &msm_gpio_chips[i];
+		val = readl(msm_chip->regs.int_status);
+		val &= msm_chip->int_enable[0];
+		while (val) {
+			mask = val & -val;
+			j = fls(mask) - 1;
+			/* printk("%s %08x %08x bit %d gpio %d irq %d\n",
+				__func__, v, m, j, msm_chip->chip.start + j,
+				FIRST_GPIO_IRQ + msm_chip->chip.start + j); */
+			val &= ~mask;
+			generic_handle_irq(FIRST_GPIO_IRQ +
+					   msm_chip->chip.base + j);
 		}
 	}
+	desc->chip->ack(irq);
 }
-EXPORT_SYMBOL(msm_gpios_disable);
 
-int msm_gpios_request_enable(const struct msm_gpio *table, int size)
-{
-	int rc = msm_gpios_enable(table, size);
-	return rc;
-}
-EXPORT_SYMBOL(msm_gpios_request_enable);
+static struct irq_chip msm_gpio_irq_chip = {
+	.name      = "msmgpio",
+	.ack       = msm_gpio_irq_ack,
+	.mask      = msm_gpio_irq_mask,
+	.unmask    = msm_gpio_irq_unmask,
+	.set_wake  = msm_gpio_irq_set_wake,
+	.set_type  = msm_gpio_irq_set_type,
+};
 
-void msm_gpios_disable_free(const struct msm_gpio *table, int size)
+static int __init msm_init_gpio(void)
 {
-	msm_gpios_disable(table, size);
+	int i, j = 0;
+
+	for (i = FIRST_GPIO_IRQ; i < FIRST_GPIO_IRQ + NR_GPIO_IRQS; i++) {
+		if (i - FIRST_GPIO_IRQ >=
+			msm_gpio_chips[j].chip.base +
+			msm_gpio_chips[j].chip.ngpio)
+			j++;
+		set_irq_chip_data(i, &msm_gpio_chips[j]);
+		set_irq_chip(i, &msm_gpio_irq_chip);
+		set_irq_handler(i, handle_edge_irq);
+		set_irq_flags(i, IRQF_VALID);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(msm_gpio_chips); i++) {
+		spin_lock_init(&msm_gpio_chips[i].lock);
+		writel(0, msm_gpio_chips[i].regs.int_en);
+		gpiochip_add(&msm_gpio_chips[i].chip);
+	}
+
+	set_irq_chained_handler(INT_GPIO_GROUP1, msm_gpio_irq_handler);
+	set_irq_chained_handler(INT_GPIO_GROUP2, msm_gpio_irq_handler);
+	set_irq_wake(INT_GPIO_GROUP1, 1);
+	set_irq_wake(INT_GPIO_GROUP2, 2);
+	return 0;
 }
-EXPORT_SYMBOL(msm_gpios_disable_free);
+
+postcore_initcall(msm_init_gpio);
diff --git a/arch/arm/mach-msm/gpio_hw.h b/arch/arm/mach-msm/gpio_hw.h
new file mode 100644
index 0000000..6b50660
--- /dev/null
+++ b/arch/arm/mach-msm/gpio_hw.h
@@ -0,0 +1,278 @@
+/* arch/arm/mach-msm/gpio_hw.h
+ *
+ * Copyright (C) 2007 Google, Inc.
+ * Author: Brian Swetland <swetland@google.com>
+ * Copyright (c) 2008-2010, Code Aurora Forum. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __ARCH_ARM_MACH_MSM_GPIO_HW_H
+#define __ARCH_ARM_MACH_MSM_GPIO_HW_H
+
+#include <mach/msm_iomap.h>
+
+/* see 80-VA736-2 Rev C pp 695-751
+**
+** These are actually the *shadow* gpio registers, since the
+** real ones (which allow full access) are only available to the
+** ARM9 side of the world.
+**
+** Since the _BASE need to be page-aligned when we're mapping them
+** to virtual addresses, adjust for the additional offset in these
+** macros.
+*/
+
+#if defined(CONFIG_ARCH_MSM7X30)
+#define MSM_GPIO1_REG(off) (MSM_GPIO1_BASE + (off))
+#define MSM_GPIO2_REG(off) (MSM_GPIO2_BASE + 0x400 + (off))
+#else
+#define MSM_GPIO1_REG(off) (MSM_GPIO1_BASE + 0x800 + (off))
+#define MSM_GPIO2_REG(off) (MSM_GPIO2_BASE + 0xC00 + (off))
+#endif
+
+#if defined(CONFIG_ARCH_MSM7X00A) || defined(CONFIG_ARCH_MSM7X25) ||\
+    defined(CONFIG_ARCH_MSM7X27)
+
+/* output value */
+#define MSM_GPIO_OUT_0         MSM_GPIO1_REG(0x00)  /* gpio  15-0  */
+#define MSM_GPIO_OUT_1         MSM_GPIO2_REG(0x00)  /* gpio  42-16 */
+#define MSM_GPIO_OUT_2         MSM_GPIO1_REG(0x04)  /* gpio  67-43 */
+#define MSM_GPIO_OUT_3         MSM_GPIO1_REG(0x08)  /* gpio  94-68 */
+#define MSM_GPIO_OUT_4         MSM_GPIO1_REG(0x0C)  /* gpio 106-95 */
+#define MSM_GPIO_OUT_5         MSM_GPIO1_REG(0x50)  /* gpio 107-121 */
+
+/* same pin map as above, output enable */
+#define MSM_GPIO_OE_0          MSM_GPIO1_REG(0x10)
+#define MSM_GPIO_OE_1          MSM_GPIO2_REG(0x08)
+#define MSM_GPIO_OE_2          MSM_GPIO1_REG(0x14)
+#define MSM_GPIO_OE_3          MSM_GPIO1_REG(0x18)
+#define MSM_GPIO_OE_4          MSM_GPIO1_REG(0x1C)
+#define MSM_GPIO_OE_5          MSM_GPIO1_REG(0x54)
+
+/* same pin map as above, input read */
+#define MSM_GPIO_IN_0          MSM_GPIO1_REG(0x34)
+#define MSM_GPIO_IN_1          MSM_GPIO2_REG(0x20)
+#define MSM_GPIO_IN_2          MSM_GPIO1_REG(0x38)
+#define MSM_GPIO_IN_3          MSM_GPIO1_REG(0x3C)
+#define MSM_GPIO_IN_4          MSM_GPIO1_REG(0x40)
+#define MSM_GPIO_IN_5          MSM_GPIO1_REG(0x44)
+
+/* same pin map as above, 1=edge 0=level interrup */
+#define MSM_GPIO_INT_EDGE_0    MSM_GPIO1_REG(0x60)
+#define MSM_GPIO_INT_EDGE_1    MSM_GPIO2_REG(0x50)
+#define MSM_GPIO_INT_EDGE_2    MSM_GPIO1_REG(0x64)
+#define MSM_GPIO_INT_EDGE_3    MSM_GPIO1_REG(0x68)
+#define MSM_GPIO_INT_EDGE_4    MSM_GPIO1_REG(0x6C)
+#define MSM_GPIO_INT_EDGE_5    MSM_GPIO1_REG(0xC0)
+
+/* same pin map as above, 1=positive 0=negative */
+#define MSM_GPIO_INT_POS_0     MSM_GPIO1_REG(0x70)
+#define MSM_GPIO_INT_POS_1     MSM_GPIO2_REG(0x58)
+#define MSM_GPIO_INT_POS_2     MSM_GPIO1_REG(0x74)
+#define MSM_GPIO_INT_POS_3     MSM_GPIO1_REG(0x78)
+#define MSM_GPIO_INT_POS_4     MSM_GPIO1_REG(0x7C)
+#define MSM_GPIO_INT_POS_5     MSM_GPIO1_REG(0xBC)
+
+/* same pin map as above, interrupt enable */
+#define MSM_GPIO_INT_EN_0      MSM_GPIO1_REG(0x80)
+#define MSM_GPIO_INT_EN_1      MSM_GPIO2_REG(0x60)
+#define MSM_GPIO_INT_EN_2      MSM_GPIO1_REG(0x84)
+#define MSM_GPIO_INT_EN_3      MSM_GPIO1_REG(0x88)
+#define MSM_GPIO_INT_EN_4      MSM_GPIO1_REG(0x8C)
+#define MSM_GPIO_INT_EN_5      MSM_GPIO1_REG(0xB8)
+
+/* same pin map as above, write 1 to clear interrupt */
+#define MSM_GPIO_INT_CLEAR_0   MSM_GPIO1_REG(0x90)
+#define MSM_GPIO_INT_CLEAR_1   MSM_GPIO2_REG(0x68)
+#define MSM_GPIO_INT_CLEAR_2   MSM_GPIO1_REG(0x94)
+#define MSM_GPIO_INT_CLEAR_3   MSM_GPIO1_REG(0x98)
+#define MSM_GPIO_INT_CLEAR_4   MSM_GPIO1_REG(0x9C)
+#define MSM_GPIO_INT_CLEAR_5   MSM_GPIO1_REG(0xB4)
+
+/* same pin map as above, 1=interrupt pending */
+#define MSM_GPIO_INT_STATUS_0  MSM_GPIO1_REG(0xA0)
+#define MSM_GPIO_INT_STATUS_1  MSM_GPIO2_REG(0x70)
+#define MSM_GPIO_INT_STATUS_2  MSM_GPIO1_REG(0xA4)
+#define MSM_GPIO_INT_STATUS_3  MSM_GPIO1_REG(0xA8)
+#define MSM_GPIO_INT_STATUS_4  MSM_GPIO1_REG(0xAC)
+#define MSM_GPIO_INT_STATUS_5  MSM_GPIO1_REG(0xB0)
+
+#endif
+
+#if defined(CONFIG_ARCH_QSD8X50)
+/* output value */
+#define MSM_GPIO_OUT_0         MSM_GPIO1_REG(0x00)  /* gpio  15-0   */
+#define MSM_GPIO_OUT_1         MSM_GPIO2_REG(0x00)  /* gpio  42-16  */
+#define MSM_GPIO_OUT_2         MSM_GPIO1_REG(0x04)  /* gpio  67-43  */
+#define MSM_GPIO_OUT_3         MSM_GPIO1_REG(0x08)  /* gpio  94-68  */
+#define MSM_GPIO_OUT_4         MSM_GPIO1_REG(0x0C)  /* gpio 103-95  */
+#define MSM_GPIO_OUT_5         MSM_GPIO1_REG(0x10)  /* gpio 121-104 */
+#define MSM_GPIO_OUT_6         MSM_GPIO1_REG(0x14)  /* gpio 152-122 */
+#define MSM_GPIO_OUT_7         MSM_GPIO1_REG(0x18)  /* gpio 164-153 */
+
+/* same pin map as above, output enable */
+#define MSM_GPIO_OE_0          MSM_GPIO1_REG(0x20)
+#define MSM_GPIO_OE_1          MSM_GPIO2_REG(0x08)
+#define MSM_GPIO_OE_2          MSM_GPIO1_REG(0x24)
+#define MSM_GPIO_OE_3          MSM_GPIO1_REG(0x28)
+#define MSM_GPIO_OE_4          MSM_GPIO1_REG(0x2C)
+#define MSM_GPIO_OE_5          MSM_GPIO1_REG(0x30)
+#define MSM_GPIO_OE_6          MSM_GPIO1_REG(0x34)
+#define MSM_GPIO_OE_7          MSM_GPIO1_REG(0x38)
+
+/* same pin map as above, input read */
+#define MSM_GPIO_IN_0          MSM_GPIO1_REG(0x50)
+#define MSM_GPIO_IN_1          MSM_GPIO2_REG(0x20)
+#define MSM_GPIO_IN_2          MSM_GPIO1_REG(0x54)
+#define MSM_GPIO_IN_3          MSM_GPIO1_REG(0x58)
+#define MSM_GPIO_IN_4          MSM_GPIO1_REG(0x5C)
+#define MSM_GPIO_IN_5          MSM_GPIO1_REG(0x60)
+#define MSM_GPIO_IN_6          MSM_GPIO1_REG(0x64)
+#define MSM_GPIO_IN_7          MSM_GPIO1_REG(0x68)
+
+/* same pin map as above, 1=edge 0=level interrup */
+#define MSM_GPIO_INT_EDGE_0    MSM_GPIO1_REG(0x70)
+#define MSM_GPIO_INT_EDGE_1    MSM_GPIO2_REG(0x50)
+#define MSM_GPIO_INT_EDGE_2    MSM_GPIO1_REG(0x74)
+#define MSM_GPIO_INT_EDGE_3    MSM_GPIO1_REG(0x78)
+#define MSM_GPIO_INT_EDGE_4    MSM_GPIO1_REG(0x7C)
+#define MSM_GPIO_INT_EDGE_5    MSM_GPIO1_REG(0x80)
+#define MSM_GPIO_INT_EDGE_6    MSM_GPIO1_REG(0x84)
+#define MSM_GPIO_INT_EDGE_7    MSM_GPIO1_REG(0x88)
+
+/* same pin map as above, 1=positive 0=negative */
+#define MSM_GPIO_INT_POS_0     MSM_GPIO1_REG(0x90)
+#define MSM_GPIO_INT_POS_1     MSM_GPIO2_REG(0x58)
+#define MSM_GPIO_INT_POS_2     MSM_GPIO1_REG(0x94)
+#define MSM_GPIO_INT_POS_3     MSM_GPIO1_REG(0x98)
+#define MSM_GPIO_INT_POS_4     MSM_GPIO1_REG(0x9C)
+#define MSM_GPIO_INT_POS_5     MSM_GPIO1_REG(0xA0)
+#define MSM_GPIO_INT_POS_6     MSM_GPIO1_REG(0xA4)
+#define MSM_GPIO_INT_POS_7     MSM_GPIO1_REG(0xA8)
+
+/* same pin map as above, interrupt enable */
+#define MSM_GPIO_INT_EN_0      MSM_GPIO1_REG(0xB0)
+#define MSM_GPIO_INT_EN_1      MSM_GPIO2_REG(0x60)
+#define MSM_GPIO_INT_EN_2      MSM_GPIO1_REG(0xB4)
+#define MSM_GPIO_INT_EN_3      MSM_GPIO1_REG(0xB8)
+#define MSM_GPIO_INT_EN_4      MSM_GPIO1_REG(0xBC)
+#define MSM_GPIO_INT_EN_5      MSM_GPIO1_REG(0xC0)
+#define MSM_GPIO_INT_EN_6      MSM_GPIO1_REG(0xC4)
+#define MSM_GPIO_INT_EN_7      MSM_GPIO1_REG(0xC8)
+
+/* same pin map as above, write 1 to clear interrupt */
+#define MSM_GPIO_INT_CLEAR_0   MSM_GPIO1_REG(0xD0)
+#define MSM_GPIO_INT_CLEAR_1   MSM_GPIO2_REG(0x68)
+#define MSM_GPIO_INT_CLEAR_2   MSM_GPIO1_REG(0xD4)
+#define MSM_GPIO_INT_CLEAR_3   MSM_GPIO1_REG(0xD8)
+#define MSM_GPIO_INT_CLEAR_4   MSM_GPIO1_REG(0xDC)
+#define MSM_GPIO_INT_CLEAR_5   MSM_GPIO1_REG(0xE0)
+#define MSM_GPIO_INT_CLEAR_6   MSM_GPIO1_REG(0xE4)
+#define MSM_GPIO_INT_CLEAR_7   MSM_GPIO1_REG(0xE8)
+
+/* same pin map as above, 1=interrupt pending */
+#define MSM_GPIO_INT_STATUS_0  MSM_GPIO1_REG(0xF0)
+#define MSM_GPIO_INT_STATUS_1  MSM_GPIO2_REG(0x70)
+#define MSM_GPIO_INT_STATUS_2  MSM_GPIO1_REG(0xF4)
+#define MSM_GPIO_INT_STATUS_3  MSM_GPIO1_REG(0xF8)
+#define MSM_GPIO_INT_STATUS_4  MSM_GPIO1_REG(0xFC)
+#define MSM_GPIO_INT_STATUS_5  MSM_GPIO1_REG(0x100)
+#define MSM_GPIO_INT_STATUS_6  MSM_GPIO1_REG(0x104)
+#define MSM_GPIO_INT_STATUS_7  MSM_GPIO1_REG(0x108)
+
+#endif
+
+#if defined(CONFIG_ARCH_MSM7X30)
+
+/* output value */
+#define MSM_GPIO_OUT_0         MSM_GPIO1_REG(0x00)   /* gpio  15-0   */
+#define MSM_GPIO_OUT_1         MSM_GPIO2_REG(0x00)   /* gpio  43-16  */
+#define MSM_GPIO_OUT_2         MSM_GPIO1_REG(0x04)   /* gpio  67-44  */
+#define MSM_GPIO_OUT_3         MSM_GPIO1_REG(0x08)   /* gpio  94-68  */
+#define MSM_GPIO_OUT_4         MSM_GPIO1_REG(0x0C)   /* gpio 106-95  */
+#define MSM_GPIO_OUT_5         MSM_GPIO1_REG(0x50)   /* gpio 133-107 */
+#define MSM_GPIO_OUT_6         MSM_GPIO1_REG(0xC4)   /* gpio 150-134 */
+#define MSM_GPIO_OUT_7         MSM_GPIO1_REG(0x214)  /* gpio 181-151 */
+
+/* same pin map as above, output enable */
+#define MSM_GPIO_OE_0          MSM_GPIO1_REG(0x10)
+#define MSM_GPIO_OE_1          MSM_GPIO2_REG(0x08)
+#define MSM_GPIO_OE_2          MSM_GPIO1_REG(0x14)
+#define MSM_GPIO_OE_3          MSM_GPIO1_REG(0x18)
+#define MSM_GPIO_OE_4          MSM_GPIO1_REG(0x1C)
+#define MSM_GPIO_OE_5          MSM_GPIO1_REG(0x54)
+#define MSM_GPIO_OE_6          MSM_GPIO1_REG(0xC8)
+#define MSM_GPIO_OE_7          MSM_GPIO1_REG(0x218)
+
+/* same pin map as above, input read */
+#define MSM_GPIO_IN_0          MSM_GPIO1_REG(0x34)
+#define MSM_GPIO_IN_1          MSM_GPIO2_REG(0x20)
+#define MSM_GPIO_IN_2          MSM_GPIO1_REG(0x38)
+#define MSM_GPIO_IN_3          MSM_GPIO1_REG(0x3C)
+#define MSM_GPIO_IN_4          MSM_GPIO1_REG(0x40)
+#define MSM_GPIO_IN_5          MSM_GPIO1_REG(0x44)
+#define MSM_GPIO_IN_6          MSM_GPIO1_REG(0xCC)
+#define MSM_GPIO_IN_7          MSM_GPIO1_REG(0x21C)
+
+/* same pin map as above, 1=edge 0=level interrup */
+#define MSM_GPIO_INT_EDGE_0    MSM_GPIO1_REG(0x60)
+#define MSM_GPIO_INT_EDGE_1    MSM_GPIO2_REG(0x50)
+#define MSM_GPIO_INT_EDGE_2    MSM_GPIO1_REG(0x64)
+#define MSM_GPIO_INT_EDGE_3    MSM_GPIO1_REG(0x68)
+#define MSM_GPIO_INT_EDGE_4    MSM_GPIO1_REG(0x6C)
+#define MSM_GPIO_INT_EDGE_5    MSM_GPIO1_REG(0xC0)
+#define MSM_GPIO_INT_EDGE_6    MSM_GPIO1_REG(0xD0)
+#define MSM_GPIO_INT_EDGE_7    MSM_GPIO1_REG(0x240)
+
+/* same pin map as above, 1=positive 0=negative */
+#define MSM_GPIO_INT_POS_0     MSM_GPIO1_REG(0x70)
+#define MSM_GPIO_INT_POS_1     MSM_GPIO2_REG(0x58)
+#define MSM_GPIO_INT_POS_2     MSM_GPIO1_REG(0x74)
+#define MSM_GPIO_INT_POS_3     MSM_GPIO1_REG(0x78)
+#define MSM_GPIO_INT_POS_4     MSM_GPIO1_REG(0x7C)
+#define MSM_GPIO_INT_POS_5     MSM_GPIO1_REG(0xBC)
+#define MSM_GPIO_INT_POS_6     MSM_GPIO1_REG(0xD4)
+#define MSM_GPIO_INT_POS_7     MSM_GPIO1_REG(0x228)
+
+/* same pin map as above, interrupt enable */
+#define MSM_GPIO_INT_EN_0      MSM_GPIO1_REG(0x80)
+#define MSM_GPIO_INT_EN_1      MSM_GPIO2_REG(0x60)
+#define MSM_GPIO_INT_EN_2      MSM_GPIO1_REG(0x84)
+#define MSM_GPIO_INT_EN_3      MSM_GPIO1_REG(0x88)
+#define MSM_GPIO_INT_EN_4      MSM_GPIO1_REG(0x8C)
+#define MSM_GPIO_INT_EN_5      MSM_GPIO1_REG(0xB8)
+#define MSM_GPIO_INT_EN_6      MSM_GPIO1_REG(0xD8)
+#define MSM_GPIO_INT_EN_7      MSM_GPIO1_REG(0x22C)
+
+/* same pin map as above, write 1 to clear interrupt */
+#define MSM_GPIO_INT_CLEAR_0   MSM_GPIO1_REG(0x90)
+#define MSM_GPIO_INT_CLEAR_1   MSM_GPIO2_REG(0x68)
+#define MSM_GPIO_INT_CLEAR_2   MSM_GPIO1_REG(0x94)
+#define MSM_GPIO_INT_CLEAR_3   MSM_GPIO1_REG(0x98)
+#define MSM_GPIO_INT_CLEAR_4   MSM_GPIO1_REG(0x9C)
+#define MSM_GPIO_INT_CLEAR_5   MSM_GPIO1_REG(0xB4)
+#define MSM_GPIO_INT_CLEAR_6   MSM_GPIO1_REG(0xDC)
+#define MSM_GPIO_INT_CLEAR_7   MSM_GPIO1_REG(0x230)
+
+/* same pin map as above, 1=interrupt pending */
+#define MSM_GPIO_INT_STATUS_0  MSM_GPIO1_REG(0xA0)
+#define MSM_GPIO_INT_STATUS_1  MSM_GPIO2_REG(0x70)
+#define MSM_GPIO_INT_STATUS_2  MSM_GPIO1_REG(0xA4)
+#define MSM_GPIO_INT_STATUS_3  MSM_GPIO1_REG(0xA8)
+#define MSM_GPIO_INT_STATUS_4  MSM_GPIO1_REG(0xAC)
+#define MSM_GPIO_INT_STATUS_5  MSM_GPIO1_REG(0xB0)
+#define MSM_GPIO_INT_STATUS_6  MSM_GPIO1_REG(0xE0)
+#define MSM_GPIO_INT_STATUS_7  MSM_GPIO1_REG(0x234)
+
+#endif
+
+#endif
diff --git a/arch/arm/mach-msm/gpiomux-7x30.c b/arch/arm/mach-msm/gpiomux-7x30.c
new file mode 100644
index 0000000..6ce41c5
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux-7x30.c
@@ -0,0 +1,38 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#include "gpiomux.h"
+
+struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS] = {
+#ifdef CONFIG_SERIAL_MSM_CONSOLE
+	[49] = { /* UART2 RFR */
+		.suspended = GPIOMUX_DRV_2MA | GPIOMUX_PULL_DOWN |
+			     GPIOMUX_FUNC_2 | GPIOMUX_VALID,
+	},
+	[50] = { /* UART2 CTS */
+		.suspended = GPIOMUX_DRV_2MA | GPIOMUX_PULL_DOWN |
+			     GPIOMUX_FUNC_2 | GPIOMUX_VALID,
+	},
+	[51] = { /* UART2 RX */
+		.suspended = GPIOMUX_DRV_2MA | GPIOMUX_PULL_DOWN |
+			     GPIOMUX_FUNC_2 | GPIOMUX_VALID,
+	},
+	[52] = { /* UART2 TX */
+		.suspended = GPIOMUX_DRV_2MA | GPIOMUX_PULL_DOWN |
+			     GPIOMUX_FUNC_2 | GPIOMUX_VALID,
+	},
+#endif
+};
diff --git a/arch/arm/mach-msm/gpiomux-8x50.c b/arch/arm/mach-msm/gpiomux-8x50.c
new file mode 100644
index 0000000..4406e0f
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux-8x50.c
@@ -0,0 +1,28 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#include "gpiomux.h"
+
+struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS] = {
+	[86] = { /* UART3 RX */
+		.suspended = GPIOMUX_DRV_2MA | GPIOMUX_PULL_DOWN |
+			     GPIOMUX_FUNC_1 | GPIOMUX_VALID,
+	},
+	[87] = { /* UART3 TX */
+		.suspended = GPIOMUX_DRV_2MA | GPIOMUX_PULL_DOWN |
+			     GPIOMUX_FUNC_1 | GPIOMUX_VALID,
+	},
+};
diff --git a/arch/arm/mach-msm/gpiomux-8x60.c b/arch/arm/mach-msm/gpiomux-8x60.c
new file mode 100644
index 0000000..7b380b3
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux-8x60.c
@@ -0,0 +1,19 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#include "gpiomux.h"
+
+struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS] = {};
diff --git a/arch/arm/mach-msm/gpiomux-v1.c b/arch/arm/mach-msm/gpiomux-v1.c
new file mode 100644
index 0000000..27de2ab
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux-v1.c
@@ -0,0 +1,33 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#include <linux/kernel.h>
+#include "gpiomux.h"
+#include "proc_comm.h"
+
+void __msm_gpiomux_write(unsigned gpio, gpiomux_config_t val)
+{
+	unsigned tlmm_config  = (val & ~GPIOMUX_CTL_MASK) |
+				((gpio & 0x3ff) << 4);
+	unsigned tlmm_disable = 0;
+	int rc;
+
+	rc = msm_proc_comm(PCOM_RPC_GPIO_TLMM_CONFIG_EX,
+			   &tlmm_config, &tlmm_disable);
+	if (rc)
+		pr_err("%s: unexpected proc_comm failure %d: %08x %08x\n",
+		       __func__, rc, tlmm_config, tlmm_disable);
+}
diff --git a/arch/arm/mach-msm/gpiomux-v1.h b/arch/arm/mach-msm/gpiomux-v1.h
new file mode 100644
index 0000000..71d86fe
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux-v1.h
@@ -0,0 +1,67 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#ifndef __ARCH_ARM_MACH_MSM_GPIOMUX_V1_H
+#define __ARCH_ARM_MACH_MSM_GPIOMUX_V1_H
+
+#if defined(CONFIG_ARCH_MSM7X30)
+#define GPIOMUX_NGPIOS 182
+#elif defined(CONFIG_ARCH_QSD8X50)
+#define GPIOMUX_NGPIOS 165
+#else
+#define GPIOMUX_NGPIOS 133
+#endif
+
+typedef u32 gpiomux_config_t;
+
+enum {
+	GPIOMUX_DRV_2MA  = 0UL << 17,
+	GPIOMUX_DRV_4MA  = 1UL << 17,
+	GPIOMUX_DRV_6MA  = 2UL << 17,
+	GPIOMUX_DRV_8MA  = 3UL << 17,
+	GPIOMUX_DRV_10MA = 4UL << 17,
+	GPIOMUX_DRV_12MA = 5UL << 17,
+	GPIOMUX_DRV_14MA = 6UL << 17,
+	GPIOMUX_DRV_16MA = 7UL << 17,
+};
+
+enum {
+	GPIOMUX_FUNC_GPIO = 0UL,
+	GPIOMUX_FUNC_1    = 1UL,
+	GPIOMUX_FUNC_2    = 2UL,
+	GPIOMUX_FUNC_3    = 3UL,
+	GPIOMUX_FUNC_4    = 4UL,
+	GPIOMUX_FUNC_5    = 5UL,
+	GPIOMUX_FUNC_6    = 6UL,
+	GPIOMUX_FUNC_7    = 7UL,
+	GPIOMUX_FUNC_8    = 8UL,
+	GPIOMUX_FUNC_9    = 9UL,
+	GPIOMUX_FUNC_A    = 10UL,
+	GPIOMUX_FUNC_B    = 11UL,
+	GPIOMUX_FUNC_C    = 12UL,
+	GPIOMUX_FUNC_D    = 13UL,
+	GPIOMUX_FUNC_E    = 14UL,
+	GPIOMUX_FUNC_F    = 15UL,
+};
+
+enum {
+	GPIOMUX_PULL_NONE   = 0UL << 15,
+	GPIOMUX_PULL_DOWN   = 1UL << 15,
+	GPIOMUX_PULL_KEEPER = 2UL << 15,
+	GPIOMUX_PULL_UP     = 3UL << 15,
+};
+
+#endif
diff --git a/arch/arm/mach-msm/gpiomux-v2.c b/arch/arm/mach-msm/gpiomux-v2.c
new file mode 100644
index 0000000..273396d
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux-v2.c
@@ -0,0 +1,25 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#include <linux/io.h>
+#include <mach/msm_iomap.h>
+#include "gpiomux.h"
+
+void __msm_gpiomux_write(unsigned gpio, gpiomux_config_t val)
+{
+	writel(val & ~GPIOMUX_CTL_MASK,
+	       MSM_TLMM_BASE + 0x1000 + (0x10 * gpio));
+}
diff --git a/arch/arm/mach-msm/gpiomux-v2.h b/arch/arm/mach-msm/gpiomux-v2.h
new file mode 100644
index 0000000..3bf10e7
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux-v2.h
@@ -0,0 +1,61 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#ifndef __ARCH_ARM_MACH_MSM_GPIOMUX_V2_H
+#define __ARCH_ARM_MACH_MSM_GPIOMUX_V2_H
+
+#define GPIOMUX_NGPIOS 173
+
+typedef u16 gpiomux_config_t;
+
+enum {
+	GPIOMUX_DRV_2MA  = 0UL << 6,
+	GPIOMUX_DRV_4MA  = 1UL << 6,
+	GPIOMUX_DRV_6MA  = 2UL << 6,
+	GPIOMUX_DRV_8MA  = 3UL << 6,
+	GPIOMUX_DRV_10MA = 4UL << 6,
+	GPIOMUX_DRV_12MA = 5UL << 6,
+	GPIOMUX_DRV_14MA = 6UL << 6,
+	GPIOMUX_DRV_16MA = 7UL << 6,
+};
+
+enum {
+	GPIOMUX_FUNC_GPIO = 0UL  << 2,
+	GPIOMUX_FUNC_1    = 1UL  << 2,
+	GPIOMUX_FUNC_2    = 2UL  << 2,
+	GPIOMUX_FUNC_3    = 3UL  << 2,
+	GPIOMUX_FUNC_4    = 4UL  << 2,
+	GPIOMUX_FUNC_5    = 5UL  << 2,
+	GPIOMUX_FUNC_6    = 6UL  << 2,
+	GPIOMUX_FUNC_7    = 7UL  << 2,
+	GPIOMUX_FUNC_8    = 8UL  << 2,
+	GPIOMUX_FUNC_9    = 9UL  << 2,
+	GPIOMUX_FUNC_A    = 10UL << 2,
+	GPIOMUX_FUNC_B    = 11UL << 2,
+	GPIOMUX_FUNC_C    = 12UL << 2,
+	GPIOMUX_FUNC_D    = 13UL << 2,
+	GPIOMUX_FUNC_E    = 14UL << 2,
+	GPIOMUX_FUNC_F    = 15UL << 2,
+};
+
+enum {
+	GPIOMUX_PULL_NONE   = 0UL,
+	GPIOMUX_PULL_DOWN   = 1UL,
+	GPIOMUX_PULL_KEEPER = 2UL,
+	GPIOMUX_PULL_UP     = 3UL,
+};
+
+#endif
diff --git a/arch/arm/mach-msm/gpiomux.c b/arch/arm/mach-msm/gpiomux.c
new file mode 100644
index 0000000..53af21a
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux.c
@@ -0,0 +1,96 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include "gpiomux.h"
+
+static DEFINE_SPINLOCK(gpiomux_lock);
+
+int msm_gpiomux_write(unsigned gpio,
+		      gpiomux_config_t active,
+		      gpiomux_config_t suspended)
+{
+	struct msm_gpiomux_config *cfg = msm_gpiomux_configs + gpio;
+	unsigned long irq_flags;
+	gpiomux_config_t setting;
+
+	if (gpio >= GPIOMUX_NGPIOS)
+		return -EINVAL;
+
+	spin_lock_irqsave(&gpiomux_lock, irq_flags);
+
+	if (active & GPIOMUX_VALID)
+		cfg->active = active;
+
+	if (suspended & GPIOMUX_VALID)
+		cfg->suspended = suspended;
+
+	setting = cfg->ref ? active : suspended;
+	if (setting & GPIOMUX_VALID)
+		__msm_gpiomux_write(gpio, setting);
+
+	spin_unlock_irqrestore(&gpiomux_lock, irq_flags);
+	return 0;
+}
+EXPORT_SYMBOL(msm_gpiomux_write);
+
+int msm_gpiomux_get(unsigned gpio)
+{
+	struct msm_gpiomux_config *cfg = msm_gpiomux_configs + gpio;
+	unsigned long irq_flags;
+
+	if (gpio >= GPIOMUX_NGPIOS)
+		return -EINVAL;
+
+	spin_lock_irqsave(&gpiomux_lock, irq_flags);
+	if (cfg->ref++ == 0 && cfg->active & GPIOMUX_VALID)
+		__msm_gpiomux_write(gpio, cfg->active);
+	spin_unlock_irqrestore(&gpiomux_lock, irq_flags);
+	return 0;
+}
+EXPORT_SYMBOL(msm_gpiomux_get);
+
+int msm_gpiomux_put(unsigned gpio)
+{
+	struct msm_gpiomux_config *cfg = msm_gpiomux_configs + gpio;
+	unsigned long irq_flags;
+
+	if (gpio >= GPIOMUX_NGPIOS)
+		return -EINVAL;
+
+	spin_lock_irqsave(&gpiomux_lock, irq_flags);
+	BUG_ON(cfg->ref == 0);
+	if (--cfg->ref == 0 && cfg->suspended & GPIOMUX_VALID)
+		__msm_gpiomux_write(gpio, cfg->suspended);
+	spin_unlock_irqrestore(&gpiomux_lock, irq_flags);
+	return 0;
+}
+EXPORT_SYMBOL(msm_gpiomux_put);
+
+static int __init gpiomux_init(void)
+{
+	unsigned n;
+
+	for (n = 0; n < GPIOMUX_NGPIOS; ++n) {
+		msm_gpiomux_configs[n].ref = 0;
+		if (!(msm_gpiomux_configs[n].suspended & GPIOMUX_VALID))
+			continue;
+		__msm_gpiomux_write(n, msm_gpiomux_configs[n].suspended);
+	}
+	return 0;
+}
+postcore_initcall(gpiomux_init);
diff --git a/arch/arm/mach-msm/gpiomux.h b/arch/arm/mach-msm/gpiomux.h
new file mode 100644
index 0000000..b178d9c
--- /dev/null
+++ b/arch/arm/mach-msm/gpiomux.h
@@ -0,0 +1,114 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+#ifndef __ARCH_ARM_MACH_MSM_GPIOMUX_H
+#define __ARCH_ARM_MACH_MSM_GPIOMUX_H
+
+#include <linux/bitops.h>
+#include <linux/errno.h>
+
+#if defined(CONFIG_MSM_V2_TLMM)
+#include "gpiomux-v2.h"
+#else
+#include "gpiomux-v1.h"
+#endif
+
+/**
+ * struct msm_gpiomux_config: gpiomux settings for one gpio line.
+ *
+ * A complete gpiomux config is the bitwise-or of a drive-strength,
+ * function, and pull.  For functions other than GPIO, the OE
+ * is hard-wired according to the function.  For GPIO mode,
+ * OE is controlled by gpiolib.
+ *
+ * Available settings differ by target; see the gpiomux header
+ * specific to your target arch for available configurations.
+ *
+ * @active: The configuration to be installed when the line is
+ * active, or its reference count is > 0.
+ * @suspended: The configuration to be installed when the line
+ * is suspended, or its reference count is 0.
+ * @ref: The reference count of the line.  For internal use of
+ * the gpiomux framework only.
+ */
+struct msm_gpiomux_config {
+	gpiomux_config_t active;
+	gpiomux_config_t suspended;
+	unsigned         ref;
+};
+
+/**
+ * @GPIOMUX_VALID:	If set, the config field contains 'good data'.
+ *                      The absence of this bit will prevent the gpiomux
+ *			system from applying the configuration under all
+ *			circumstances.
+ */
+enum {
+	GPIOMUX_VALID	 = BIT(sizeof(gpiomux_config_t) * BITS_PER_BYTE - 1),
+	GPIOMUX_CTL_MASK = GPIOMUX_VALID,
+};
+
+#ifdef CONFIG_MSM_GPIOMUX
+
+/* Each architecture must provide its own instance of this table.
+ * To avoid having gpiomux manage any given gpio, one or both of
+ * the entries can avoid setting GPIOMUX_VALID - the absence
+ * of that flag will prevent the configuration from being applied
+ * during state transitions.
+ */
+extern struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS];
+
+/* Increment a gpio's reference count, possibly activating the line. */
+int __must_check msm_gpiomux_get(unsigned gpio);
+
+/* Decrement a gpio's reference count, possibly suspending the line. */
+int msm_gpiomux_put(unsigned gpio);
+
+/* Install a new configuration to the gpio line.  To avoid overwriting
+ * a configuration, leave the VALID bit out.
+ */
+int msm_gpiomux_write(unsigned gpio,
+		      gpiomux_config_t active,
+		      gpiomux_config_t suspended);
+
+/* Architecture-internal function for use by the framework only.
+ * This function can assume the following:
+ * - the gpio value has passed a bounds-check
+ * - the gpiomux spinlock has been obtained
+ *
+ * This function is not for public consumption.  External users
+ * should use msm_gpiomux_write.
+ */
+void __msm_gpiomux_write(unsigned gpio, gpiomux_config_t val);
+#else
+static inline int __must_check msm_gpiomux_get(unsigned gpio)
+{
+	return -ENOSYS;
+}
+
+static inline int msm_gpiomux_put(unsigned gpio)
+{
+	return -ENOSYS;
+}
+
+static inline int msm_gpiomux_write(unsigned gpio,
+				    gpiomux_config_t active,
+				    gpiomux_config_t suspended)
+{
+	return -ENOSYS;
+}
+#endif
+#endif
diff --git a/arch/arm/mach-msm/include/mach/board.h b/arch/arm/mach-msm/include/mach/board.h
index 5a79bcf..6abf4a6 100644
--- a/arch/arm/mach-msm/include/mach/board.h
+++ b/arch/arm/mach-msm/include/mach/board.h
@@ -33,6 +33,8 @@
 
 struct clk;
 
+extern struct sys_timer msm_timer;
+
 /* common init routines for use by arch/arm/mach-msm/board-*.c */
 
 void __init msm_add_devices(void);
diff --git a/arch/arm/mach-msm/include/mach/debug-macro.S b/arch/arm/mach-msm/include/mach/debug-macro.S
index 528750f..fbd5d90 100644
--- a/arch/arm/mach-msm/include/mach/debug-macro.S
+++ b/arch/arm/mach-msm/include/mach/debug-macro.S
@@ -19,13 +19,10 @@
 #include <mach/hardware.h>
 #include <mach/msm_iomap.h>
 
-#ifdef CONFIG_MSM_DEBUG_UART
-	.macro	addruart, rx, tmp
-	@ see if the MMU is enabled and select appropriate base address
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1
-	ldreq	\rx, =MSM_DEBUG_UART_PHYS
-	ldrne	\rx, =MSM_DEBUG_UART_BASE
+#ifdef CONFIG_HAS_MSM_DEBUG_UART_PHYS
+	.macro	addruart, rp, rv
+	ldr	\rp, =MSM_DEBUG_UART_PHYS
+	ldr	\rv, =MSM_DEBUG_UART_BASE
 	.endm
 
 	.macro	senduart,rd,rx
@@ -39,16 +36,7 @@
 	tst	\rd, #0x04
 	beq	1001b
 	.endm
-#else
-	.macro	addruart, rx, tmp
-	.endm
-
-	.macro	senduart,rd,rx
-	.endm
-
-	.macro	waituart,rd,rx
-	.endm
-#endif
 
 	.macro	busyuart,rd,rx
 	.endm
+#endif
diff --git a/arch/arm/mach-msm/include/mach/dma.h b/arch/arm/mach-msm/include/mach/dma.h
index 00f9bbf..05583f5 100644
--- a/arch/arm/mach-msm/include/mach/dma.h
+++ b/arch/arm/mach-msm/include/mach/dma.h
@@ -32,10 +32,18 @@
 	void *data;
 };
 
+#ifndef CONFIG_ARCH_MSM8X60
 void msm_dmov_enqueue_cmd(unsigned id, struct msm_dmov_cmd *cmd);
 void msm_dmov_stop_cmd(unsigned id, struct msm_dmov_cmd *cmd, int graceful);
 int msm_dmov_exec_cmd(unsigned id, unsigned int cmdptr);
-
+#else
+static inline
+void msm_dmov_enqueue_cmd(unsigned id, struct msm_dmov_cmd *cmd) { }
+static inline
+void msm_dmov_stop_cmd(unsigned id, struct msm_dmov_cmd *cmd, int graceful) { }
+static inline
+int msm_dmov_exec_cmd(unsigned id, unsigned int cmdptr) { return -EIO; }
+#endif
 
 
 #define DMOV_SD0(off, ch) (MSM_DMOV_BASE + 0x0000 + (off) + ((ch) << 2))
diff --git a/arch/arm/mach-msm/include/mach/entry-macro-qgic.S b/arch/arm/mach-msm/include/mach/entry-macro-qgic.S
new file mode 100644
index 0000000..4dc99aa
--- /dev/null
+++ b/arch/arm/mach-msm/include/mach/entry-macro-qgic.S
@@ -0,0 +1,88 @@
+/*
+ * Low-level IRQ helper macros
+ *
+ * Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This file is licensed under  the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <mach/hardware.h>
+#include <asm/hardware/gic.h>
+
+	.macro	disable_fiq
+	.endm
+
+	.macro  get_irqnr_preamble, base, tmp
+	ldr	\base, =gic_cpu_base_addr
+	ldr	\base, [\base]
+	.endm
+
+	.macro  arch_ret_to_user, tmp1, tmp2
+	.endm
+
+	/*
+	 * The interrupt numbering scheme is defined in the
+	 * interrupt controller spec.  To wit:
+	 *
+	 * Migrated the code from ARM MP port to be more consistant
+	 * with interrupt processing , the following still holds true
+	 * however, all interrupts are treated the same regardless of
+	 * if they are local IPI or PPI
+	 *
+	 * Interrupts 0-15 are IPI
+	 * 16-31 are PPI
+	 *   (16-18 are the timers)
+	 * 32-1020 are global
+	 * 1021-1022 are reserved
+	 * 1023 is "spurious" (no interrupt)
+	 *
+	 * A simple read from the controller will tell us the number of the
+	 * highest priority enabled interrupt.  We then just need to check
+	 * whether it is in the valid range for an IRQ (0-1020 inclusive).
+	 *
+	 * Base ARM code assumes that the local (private) peripheral interrupts
+	 * are not valid, we treat them differently, in that the privates are
+	 * handled like normal shared interrupts with the exception that only
+	 * one processor can register the interrupt and the handler must be
+	 * the same for all processors.
+	 */
+
+	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
+
+	ldr  \irqstat, [\base, #GIC_CPU_INTACK] /* bits 12-10 =srcCPU,
+						   9-0 =int # */
+
+	bic     \irqnr, \irqstat, #0x1c00	@mask src
+	cmp     \irqnr, #15
+	ldr		\tmp, =1021
+	cmpcc	\irqnr, \irqnr
+	cmpne	\irqnr, \tmp
+	cmpcs	\irqnr, \irqnr
+
+	.endm
+
+	/* We assume that irqstat (the raw value of the IRQ acknowledge
+	 * register) is preserved from the macro above.
+	 * If there is an IPI, we immediately signal end of interrupt on the
+	 * controller, since this requires the original irqstat value which
+	 * we won't easily be able to recreate later.
+	 */
+	.macro test_for_ipi, irqnr, irqstat, base, tmp
+    bic \irqnr, \irqstat, #0x1c00
+    cmp \irqnr, #16
+    strcc   \irqstat, [\base, #GIC_CPU_EOI]
+    cmpcs   \irqnr, \irqnr
+	.endm
+
+	/* As above, this assumes that irqstat and base are preserved.. */
+
+	.macro test_for_ltirq, irqnr, irqstat, base, tmp
+    bic \irqnr, \irqstat, #0x1c00
+    mov     \tmp, #0
+    cmp \irqnr, #16
+    moveq   \tmp, #1
+    streq   \irqstat, [\base, #GIC_CPU_EOI]
+    cmp \tmp, #0
+	.endm
diff --git a/arch/arm/mach-msm/include/mach/entry-macro-vic.S b/arch/arm/mach-msm/include/mach/entry-macro-vic.S
new file mode 100644
index 0000000..70563ed
--- /dev/null
+++ b/arch/arm/mach-msm/include/mach/entry-macro-vic.S
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2007 Google, Inc.
+ * Author: Brian Swetland <swetland@google.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <mach/msm_iomap.h>
+
+	.macro	disable_fiq
+	.endm
+
+	.macro	get_irqnr_preamble, base, tmp
+	@ enable imprecise aborts
+	cpsie	a
+	mov	\base, #MSM_VIC_BASE
+	.endm
+
+	.macro	arch_ret_to_user, tmp1, tmp2
+	.endm
+
+	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
+	@ 0xD0 has irq# or old irq# if the irq has been handled
+	@ 0xD4 has irq# or -1 if none pending *but* if you just
+	@ read 0xD4 you never get the first irq for some reason
+	ldr	\irqnr, [\base, #0xD0]
+	ldr	\irqnr, [\base, #0xD4]
+	cmp	\irqnr, #0xffffffff
+	.endm
diff --git a/arch/arm/mach-msm/include/mach/entry-macro.S b/arch/arm/mach-msm/include/mach/entry-macro.S
index d225948..b16f082 100644
--- a/arch/arm/mach-msm/include/mach/entry-macro.S
+++ b/arch/arm/mach-msm/include/mach/entry-macro.S
@@ -1,38 +1,23 @@
-/* arch/arm/mach-msm7200/include/mach/entry-macro.S
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
  *
- * Copyright (C) 2007 Google, Inc.
- * Author: Brian Swetland <swetland@google.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
  */
 
-#include <mach/msm_iomap.h>
-
- 	.macro	disable_fiq
-	.endm
-
-	.macro	get_irqnr_preamble, base, tmp
-	@ enable imprecise aborts
-	cpsie	a
-	mov	\base, #MSM_VIC_BASE
-	.endm
-
-	.macro	arch_ret_to_user, tmp1, tmp2
-	.endm
-
-	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
-	@ 0xD0 has irq# or old irq# if the irq has been handled
-	@ 0xD4 has irq# or -1 if none pending *but* if you just
-	@ read 0xD4 you never get the first irq for some reason
-	ldr	\irqnr, [\base, #0xD0]
-	ldr	\irqnr, [\base, #0xD4]
-	cmp	\irqnr, #0xffffffff
-	.endm
+#if defined(CONFIG_ARM_GIC)
+#include <mach/entry-macro-qgic.S>
+#else
+#include <mach/entry-macro-vic.S>
+#endif
diff --git a/arch/arm/mach-msm/include/mach/gpio.h b/arch/arm/mach-msm/include/mach/gpio.h
index 83e47c0..36ad50d 100644
--- a/arch/arm/mach-msm/include/mach/gpio.h
+++ b/arch/arm/mach-msm/include/mach/gpio.h
@@ -23,127 +23,4 @@
 #define gpio_cansleep   __gpio_cansleep
 #define gpio_to_irq     __gpio_to_irq
 
-/**
- * struct msm_gpio - GPIO pin description
- * @gpio_cfg - configuration bitmap, as per gpio_tlmm_config()
- * @label - textual label
- *
- * Usually, GPIO's are operated by sets.
- * This struct accumulate all GPIO information in single source
- * and facilitete group operations provided by msm_gpios_xxx()
- */
-struct msm_gpio {
-	u32 gpio_cfg;
-	const char *label;
-};
-
-/**
- * msm_gpios_request_enable() - request and enable set of GPIOs
- *
- * Request and configure set of GPIO's
- * In case of error, all operations rolled back.
- * Return error code.
- *
- * @table: GPIO table
- * @size:  number of entries in @table
- */
-int msm_gpios_request_enable(const struct msm_gpio *table, int size);
-
-/**
- * msm_gpios_disable_free() - disable and free set of GPIOs
- *
- * @table: GPIO table
- * @size:  number of entries in @table
- */
-void msm_gpios_disable_free(const struct msm_gpio *table, int size);
-
-/**
- * msm_gpios_request() - request set of GPIOs
- * In case of error, all operations rolled back.
- * Return error code.
- *
- * @table: GPIO table
- * @size:  number of entries in @table
- */
-int msm_gpios_request(const struct msm_gpio *table, int size);
-
-/**
- * msm_gpios_free() - free set of GPIOs
- *
- * @table: GPIO table
- * @size:  number of entries in @table
- */
-void msm_gpios_free(const struct msm_gpio *table, int size);
-
-/**
- * msm_gpios_enable() - enable set of GPIOs
- * In case of error, all operations rolled back.
- * Return error code.
- *
- * @table: GPIO table
- * @size:  number of entries in @table
- */
-int msm_gpios_enable(const struct msm_gpio *table, int size);
-
-/**
- * msm_gpios_disable() - disable set of GPIOs
- *
- * @table: GPIO table
- * @size:  number of entries in @table
- */
-void msm_gpios_disable(const struct msm_gpio *table, int size);
-
-/* GPIO TLMM (Top Level Multiplexing) Definitions */
-
-/* GPIO TLMM: Function -- GPIO specific */
-
-/* GPIO TLMM: Direction */
-enum {
-	GPIO_INPUT,
-	GPIO_OUTPUT,
-};
-
-/* GPIO TLMM: Pullup/Pulldown */
-enum {
-	GPIO_NO_PULL,
-	GPIO_PULL_DOWN,
-	GPIO_KEEPER,
-	GPIO_PULL_UP,
-};
-
-/* GPIO TLMM: Drive Strength */
-enum {
-	GPIO_2MA,
-	GPIO_4MA,
-	GPIO_6MA,
-	GPIO_8MA,
-	GPIO_10MA,
-	GPIO_12MA,
-	GPIO_14MA,
-	GPIO_16MA,
-};
-
-enum {
-	GPIO_ENABLE,
-	GPIO_DISABLE,
-};
-
-#define GPIO_CFG(gpio, func, dir, pull, drvstr) \
-	((((gpio) & 0x3FF) << 4)        |	  \
-	 ((func) & 0xf)                  |	  \
-	 (((dir) & 0x1) << 14)           |	  \
-	 (((pull) & 0x3) << 15)          |	  \
-	 (((drvstr) & 0xF) << 17))
-
-/**
- * extract GPIO pin from bit-field used for gpio_tlmm_config
- */
-#define GPIO_PIN(gpio_cfg)    (((gpio_cfg) >>  4) & 0x3ff)
-#define GPIO_FUNC(gpio_cfg)   (((gpio_cfg) >>  0) & 0xf)
-#define GPIO_DIR(gpio_cfg)    (((gpio_cfg) >> 14) & 0x1)
-#define GPIO_PULL(gpio_cfg)   (((gpio_cfg) >> 15) & 0x3)
-#define GPIO_DRVSTR(gpio_cfg) (((gpio_cfg) >> 17) & 0xf)
-
-int gpio_tlmm_config(unsigned config, unsigned disable);
-
 #endif /* __ASM_ARCH_MSM_GPIO_H */
diff --git a/arch/arm/mach-msm/include/mach/io.h b/arch/arm/mach-msm/include/mach/io.h
index c35b29f..7386e73 100644
--- a/arch/arm/mach-msm/include/mach/io.h
+++ b/arch/arm/mach-msm/include/mach/io.h
@@ -28,6 +28,7 @@
 
 void msm_map_qsd8x50_io(void);
 void msm_map_msm7x30_io(void);
+void msm_map_msm8x60_io(void);
 
 extern unsigned int msm_shared_ram_phys;
 
diff --git a/arch/arm/mach-msm/include/mach/iommu.h b/arch/arm/mach-msm/include/mach/iommu.h
new file mode 100644
index 0000000..218ef57
--- /dev/null
+++ b/arch/arm/mach-msm/include/mach/iommu.h
@@ -0,0 +1,103 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef MSM_IOMMU_H
+#define MSM_IOMMU_H
+
+#include <linux/interrupt.h>
+
+/* Maximum number of Machine IDs that we are allowing to be mapped to the same
+ * context bank. The number of MIDs mapped to the same CB does not affect
+ * performance, but there is a practical limit on how many distinct MIDs may
+ * be present. These mappings are typically determined at design time and are
+ * not expected to change at run time.
+ */
+#define MAX_NUM_MIDS	16
+
+/**
+ * struct msm_iommu_dev - a single IOMMU hardware instance
+ * name		Human-readable name given to this IOMMU HW instance
+ * clk_rate	Rate to set for this IOMMU's clock, if applicable to this
+ *		particular IOMMU. 0 means don't set a rate.
+ *		-1 means it is an AXI clock with no valid rate
+ *
+ */
+struct msm_iommu_dev {
+	const char *name;
+	int clk_rate;
+};
+
+/**
+ * struct msm_iommu_ctx_dev - an IOMMU context bank instance
+ * name		Human-readable name given to this context bank
+ * num		Index of this context bank within the hardware
+ * mids		List of Machine IDs that are to be mapped into this context
+ *		bank, terminated by -1. The MID is a set of signals on the
+ *		AXI bus that identifies the function associated with a specific
+ *		memory request. (See ARM spec).
+ */
+struct msm_iommu_ctx_dev {
+	const char *name;
+	int num;
+	int mids[MAX_NUM_MIDS];
+};
+
+
+/**
+ * struct msm_iommu_drvdata - A single IOMMU hardware instance
+ * @base:	IOMMU config port base address (VA)
+ * @irq:	Interrupt number
+  *
+ * A msm_iommu_drvdata holds the global driver data about a single piece
+ * of an IOMMU hardware instance.
+ */
+struct msm_iommu_drvdata {
+	void __iomem *base;
+	int irq;
+};
+
+/**
+ * struct msm_iommu_ctx_drvdata - an IOMMU context bank instance
+ * @num:		Hardware context number of this context
+ * @pdev:		Platform device associated wit this HW instance
+ * @attached_elm:	List element for domains to track which devices are
+ *			attached to them
+ *
+ * A msm_iommu_ctx_drvdata holds the driver data for a single context bank
+ * within each IOMMU hardware instance
+ */
+struct msm_iommu_ctx_drvdata {
+	int num;
+	struct platform_device *pdev;
+	struct list_head attached_elm;
+};
+
+/*
+ * Look up an IOMMU context device by its context name. NULL if none found.
+ * Useful for testing and drivers that do not yet fully have IOMMU stuff in
+ * their platform devices.
+ */
+struct device *msm_iommu_get_ctx(const char *ctx_name);
+
+/*
+ * Interrupt handler for the IOMMU context fault interrupt. Hooking the
+ * interrupt is not supported in the API yet, but this will print an error
+ * message and dump useful IOMMU registers.
+ */
+irqreturn_t msm_iommu_fault_handler(int irq, void *dev_id);
+
+#endif
diff --git a/arch/arm/mach-msm/include/mach/iommu_hw-8xxx.h b/arch/arm/mach-msm/include/mach/iommu_hw-8xxx.h
new file mode 100644
index 0000000..f9386d3
--- /dev/null
+++ b/arch/arm/mach-msm/include/mach/iommu_hw-8xxx.h
@@ -0,0 +1,1871 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef __ARCH_ARM_MACH_MSM_IOMMU_HW_8XXX_H
+#define __ARCH_ARM_MACH_MSM_IOMMU_HW_8XXX_H
+
+#define CTX_SHIFT 12
+
+#define GET_GLOBAL_REG(reg, base) (readl((base) + (reg)))
+#define GET_CTX_REG(reg, base, ctx) \
+				(readl((base) + (reg) + ((ctx) << CTX_SHIFT)))
+
+#define SET_GLOBAL_REG(reg, base, val)	writel((val), ((base) + (reg)))
+
+#define SET_CTX_REG(reg, base, ctx, val) \
+			writel((val), ((base) + (reg) + ((ctx) << CTX_SHIFT)))
+
+/* Wrappers for numbered registers */
+#define SET_GLOBAL_REG_N(b, n, r, v) SET_GLOBAL_REG(b, ((r) + (n << 2)), (v))
+#define GET_GLOBAL_REG_N(b, n, r)    GET_GLOBAL_REG(b, ((r) + (n << 2)))
+
+/* Field wrappers */
+#define GET_GLOBAL_FIELD(b, r, F)    GET_FIELD(((b) + (r)), F##_MASK, F##_SHIFT)
+#define GET_CONTEXT_FIELD(b, c, r, F)	\
+	GET_FIELD(((b) + (r) + ((c) << CTX_SHIFT)), F##_MASK, F##_SHIFT)
+
+#define SET_GLOBAL_FIELD(b, r, F, v) \
+	SET_FIELD(((b) + (r)), F##_MASK, F##_SHIFT, (v))
+#define SET_CONTEXT_FIELD(b, c, r, F, v)	\
+	SET_FIELD(((b) + (r) + ((c) << CTX_SHIFT)), F##_MASK, F##_SHIFT, (v))
+
+#define GET_FIELD(addr, mask, shift)  ((readl(addr) >> (shift)) & (mask))
+
+#define SET_FIELD(addr, mask, shift, v) \
+do { \
+	int t = readl(addr); \
+	writel((t & ~((mask) << (shift))) + (((v) & (mask)) << (shift)), addr);\
+} while (0)
+
+
+#define NUM_FL_PTE	4096
+#define NUM_SL_PTE	256
+
+/* First-level page table bits */
+#define FL_BASE_MASK		0xFFFFFC00
+#define FL_TYPE_TABLE		(1 << 0)
+#define FL_TYPE_SECT		(2 << 0)
+#define FL_SUPERSECTION		(1 << 18)
+#define FL_AP_WRITE		(1 << 10)
+#define FL_AP_READ		(1 << 11)
+#define FL_SHARED		(1 << 16)
+#define FL_OFFSET(va)		(((va) & 0xFFF00000) >> 20)
+
+/* Second-level page table bits */
+#define SL_BASE_MASK_LARGE	0xFFFF0000
+#define SL_BASE_MASK_SMALL	0xFFFFF000
+#define SL_TYPE_LARGE		(1 << 0)
+#define SL_TYPE_SMALL		(2 << 0)
+#define SL_AP0			(1 << 4)
+#define SL_AP1			(2 << 4)
+#define SL_SHARED		(1 << 10)
+#define SL_OFFSET(va)		(((va) & 0xFF000) >> 12)
+
+/* Global register setters / getters */
+#define SET_M2VCBR_N(b, N, v)	 SET_GLOBAL_REG_N(M2VCBR_N, N, (b), (v))
+#define SET_CBACR_N(b, N, v)	 SET_GLOBAL_REG_N(CBACR_N, N, (b), (v))
+#define SET_TLBRSW(b, v)	 SET_GLOBAL_REG(TLBRSW, (b), (v))
+#define SET_TLBTR0(b, v)	 SET_GLOBAL_REG(TLBTR0, (b), (v))
+#define SET_TLBTR1(b, v)	 SET_GLOBAL_REG(TLBTR1, (b), (v))
+#define SET_TLBTR2(b, v)	 SET_GLOBAL_REG(TLBTR2, (b), (v))
+#define SET_TESTBUSCR(b, v)	 SET_GLOBAL_REG(TESTBUSCR, (b), (v))
+#define SET_GLOBAL_TLBIALL(b, v) SET_GLOBAL_REG(GLOBAL_TLBIALL, (b), (v))
+#define SET_TLBIVMID(b, v)	 SET_GLOBAL_REG(TLBIVMID, (b), (v))
+#define SET_CR(b, v)		 SET_GLOBAL_REG(CR, (b), (v))
+#define SET_EAR(b, v)		 SET_GLOBAL_REG(EAR, (b), (v))
+#define SET_ESR(b, v)		 SET_GLOBAL_REG(ESR, (b), (v))
+#define SET_ESRRESTORE(b, v)	 SET_GLOBAL_REG(ESRRESTORE, (b), (v))
+#define SET_ESYNR0(b, v)	 SET_GLOBAL_REG(ESYNR0, (b), (v))
+#define SET_ESYNR1(b, v)	 SET_GLOBAL_REG(ESYNR1, (b), (v))
+#define SET_RPU_ACR(b, v)	 SET_GLOBAL_REG(RPU_ACR, (b), (v))
+
+#define GET_M2VCBR_N(b, N)	 GET_GLOBAL_REG_N(M2VCBR_N, N, (b))
+#define GET_CBACR_N(b, N)	 GET_GLOBAL_REG_N(CBACR_N, N, (b))
+#define GET_TLBTR0(b)		 GET_GLOBAL_REG(TLBTR0, (b))
+#define GET_TLBTR1(b)		 GET_GLOBAL_REG(TLBTR1, (b))
+#define GET_TLBTR2(b)		 GET_GLOBAL_REG(TLBTR2, (b))
+#define GET_TESTBUSCR(b)	 GET_GLOBAL_REG(TESTBUSCR, (b))
+#define GET_GLOBAL_TLBIALL(b)	 GET_GLOBAL_REG(GLOBAL_TLBIALL, (b))
+#define GET_TLBIVMID(b)		 GET_GLOBAL_REG(TLBIVMID, (b))
+#define GET_CR(b)		 GET_GLOBAL_REG(CR, (b))
+#define GET_EAR(b)		 GET_GLOBAL_REG(EAR, (b))
+#define GET_ESR(b)		 GET_GLOBAL_REG(ESR, (b))
+#define GET_ESRRESTORE(b)	 GET_GLOBAL_REG(ESRRESTORE, (b))
+#define GET_ESYNR0(b)		 GET_GLOBAL_REG(ESYNR0, (b))
+#define GET_ESYNR1(b)		 GET_GLOBAL_REG(ESYNR1, (b))
+#define GET_REV(b)		 GET_GLOBAL_REG(REV, (b))
+#define GET_IDR(b)		 GET_GLOBAL_REG(IDR, (b))
+#define GET_RPU_ACR(b)		 GET_GLOBAL_REG(RPU_ACR, (b))
+
+
+/* Context register setters/getters */
+#define SET_SCTLR(b, c, v)	 SET_CTX_REG(SCTLR, (b), (c), (v))
+#define SET_ACTLR(b, c, v)	 SET_CTX_REG(ACTLR, (b), (c), (v))
+#define SET_CONTEXTIDR(b, c, v)	 SET_CTX_REG(CONTEXTIDR, (b), (c), (v))
+#define SET_TTBR0(b, c, v)	 SET_CTX_REG(TTBR0, (b), (c), (v))
+#define SET_TTBR1(b, c, v)	 SET_CTX_REG(TTBR1, (b), (c), (v))
+#define SET_TTBCR(b, c, v)	 SET_CTX_REG(TTBCR, (b), (c), (v))
+#define SET_PAR(b, c, v)	 SET_CTX_REG(PAR, (b), (c), (v))
+#define SET_FSR(b, c, v)	 SET_CTX_REG(FSR, (b), (c), (v))
+#define SET_FSRRESTORE(b, c, v)	 SET_CTX_REG(FSRRESTORE, (b), (c), (v))
+#define SET_FAR(b, c, v)	 SET_CTX_REG(FAR, (b), (c), (v))
+#define SET_FSYNR0(b, c, v)	 SET_CTX_REG(FSYNR0, (b), (c), (v))
+#define SET_FSYNR1(b, c, v)	 SET_CTX_REG(FSYNR1, (b), (c), (v))
+#define SET_PRRR(b, c, v)	 SET_CTX_REG(PRRR, (b), (c), (v))
+#define SET_NMRR(b, c, v)	 SET_CTX_REG(NMRR, (b), (c), (v))
+#define SET_TLBLKCR(b, c, v)	 SET_CTX_REG(TLBLCKR, (b), (c), (v))
+#define SET_V2PSR(b, c, v)	 SET_CTX_REG(V2PSR, (b), (c), (v))
+#define SET_TLBFLPTER(b, c, v)	 SET_CTX_REG(TLBFLPTER, (b), (c), (v))
+#define SET_TLBSLPTER(b, c, v)	 SET_CTX_REG(TLBSLPTER, (b), (c), (v))
+#define SET_BFBCR(b, c, v)	 SET_CTX_REG(BFBCR, (b), (c), (v))
+#define SET_CTX_TLBIALL(b, c, v) SET_CTX_REG(CTX_TLBIALL, (b), (c), (v))
+#define SET_TLBIASID(b, c, v)	 SET_CTX_REG(TLBIASID, (b), (c), (v))
+#define SET_TLBIVA(b, c, v)	 SET_CTX_REG(TLBIVA, (b), (c), (v))
+#define SET_TLBIVAA(b, c, v)	 SET_CTX_REG(TLBIVAA, (b), (c), (v))
+#define SET_V2PPR(b, c, v)	 SET_CTX_REG(V2PPR, (b), (c), (v))
+#define SET_V2PPW(b, c, v)	 SET_CTX_REG(V2PPW, (b), (c), (v))
+#define SET_V2PUR(b, c, v)	 SET_CTX_REG(V2PUR, (b), (c), (v))
+#define SET_V2PUW(b, c, v)	 SET_CTX_REG(V2PUW, (b), (c), (v))
+#define SET_RESUME(b, c, v)	 SET_CTX_REG(RESUME, (b), (c), (v))
+
+#define GET_SCTLR(b, c)		 GET_CTX_REG(SCTLR, (b), (c))
+#define GET_ACTLR(b, c)		 GET_CTX_REG(ACTLR, (b), (c))
+#define GET_CONTEXTIDR(b, c)	 GET_CTX_REG(CONTEXTIDR, (b), (c))
+#define GET_TTBR0(b, c)		 GET_CTX_REG(TTBR0, (b), (c))
+#define GET_TTBR1(b, c)		 GET_CTX_REG(TTBR1, (b), (c))
+#define GET_TTBCR(b, c)		 GET_CTX_REG(TTBCR, (b), (c))
+#define GET_PAR(b, c)		 GET_CTX_REG(PAR, (b), (c))
+#define GET_FSR(b, c)		 GET_CTX_REG(FSR, (b), (c))
+#define GET_FSRRESTORE(b, c)	 GET_CTX_REG(FSRRESTORE, (b), (c))
+#define GET_FAR(b, c)		 GET_CTX_REG(FAR, (b), (c))
+#define GET_FSYNR0(b, c)	 GET_CTX_REG(FSYNR0, (b), (c))
+#define GET_FSYNR1(b, c)	 GET_CTX_REG(FSYNR1, (b), (c))
+#define GET_PRRR(b, c)		 GET_CTX_REG(PRRR, (b), (c))
+#define GET_NMRR(b, c)		 GET_CTX_REG(NMRR, (b), (c))
+#define GET_TLBLCKR(b, c)	 GET_CTX_REG(TLBLCKR, (b), (c))
+#define GET_V2PSR(b, c)		 GET_CTX_REG(V2PSR, (b), (c))
+#define GET_TLBFLPTER(b, c)	 GET_CTX_REG(TLBFLPTER, (b), (c))
+#define GET_TLBSLPTER(b, c)	 GET_CTX_REG(TLBSLPTER, (b), (c))
+#define GET_BFBCR(b, c)		 GET_CTX_REG(BFBCR, (b), (c))
+#define GET_CTX_TLBIALL(b, c)	 GET_CTX_REG(CTX_TLBIALL, (b), (c))
+#define GET_TLBIASID(b, c)	 GET_CTX_REG(TLBIASID, (b), (c))
+#define GET_TLBIVA(b, c)	 GET_CTX_REG(TLBIVA, (b), (c))
+#define GET_TLBIVAA(b, c)	 GET_CTX_REG(TLBIVAA, (b), (c))
+#define GET_V2PPR(b, c)		 GET_CTX_REG(V2PPR, (b), (c))
+#define GET_V2PPW(b, c)		 GET_CTX_REG(V2PPW, (b), (c))
+#define GET_V2PUR(b, c)		 GET_CTX_REG(V2PUR, (b), (c))
+#define GET_V2PUW(b, c)		 GET_CTX_REG(V2PUW, (b), (c))
+#define GET_RESUME(b, c)	 GET_CTX_REG(RESUME, (b), (c))
+
+
+/* Global field setters / getters */
+/* Global Field Setters: */
+/* CBACR_N */
+#define SET_RWVMID(b, n, v)   SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWVMID, v)
+#define SET_RWE(b, n, v)      SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWE, v)
+#define SET_RWGE(b, n, v)     SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWGE, v)
+#define SET_CBVMID(b, n, v)   SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), CBVMID, v)
+#define SET_IRPTNDX(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), IRPTNDX, v)
+
+
+/* M2VCBR_N */
+#define SET_VMID(b, n, v)     SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), VMID, v)
+#define SET_CBNDX(b, n, v)    SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), CBNDX, v)
+#define SET_BYPASSD(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BYPASSD, v)
+#define SET_BPRCOSH(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCOSH, v)
+#define SET_BPRCISH(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCISH, v)
+#define SET_BPRCNSH(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCNSH, v)
+#define SET_BPSHCFG(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPSHCFG, v)
+#define SET_NSCFG(b, n, v)    SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), NSCFG, v)
+#define SET_BPMTCFG(b, n, v)  SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPMTCFG, v)
+#define SET_BPMEMTYPE(b, n, v) \
+	SET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPMEMTYPE, v)
+
+
+/* CR */
+#define SET_RPUE(b, v)		 SET_GLOBAL_FIELD(b, CR, RPUE, v)
+#define SET_RPUERE(b, v)	 SET_GLOBAL_FIELD(b, CR, RPUERE, v)
+#define SET_RPUEIE(b, v)	 SET_GLOBAL_FIELD(b, CR, RPUEIE, v)
+#define SET_DCDEE(b, v)		 SET_GLOBAL_FIELD(b, CR, DCDEE, v)
+#define SET_CLIENTPD(b, v)       SET_GLOBAL_FIELD(b, CR, CLIENTPD, v)
+#define SET_STALLD(b, v)	 SET_GLOBAL_FIELD(b, CR, STALLD, v)
+#define SET_TLBLKCRWE(b, v)      SET_GLOBAL_FIELD(b, CR, TLBLKCRWE, v)
+#define SET_CR_TLBIALLCFG(b, v)  SET_GLOBAL_FIELD(b, CR, CR_TLBIALLCFG, v)
+#define SET_TLBIVMIDCFG(b, v)    SET_GLOBAL_FIELD(b, CR, TLBIVMIDCFG, v)
+#define SET_CR_HUME(b, v)        SET_GLOBAL_FIELD(b, CR, CR_HUME, v)
+
+
+/* ESR */
+#define SET_CFG(b, v)		 SET_GLOBAL_FIELD(b, ESR, CFG, v)
+#define SET_BYPASS(b, v)	 SET_GLOBAL_FIELD(b, ESR, BYPASS, v)
+#define SET_ESR_MULTI(b, v)      SET_GLOBAL_FIELD(b, ESR, ESR_MULTI, v)
+
+
+/* ESYNR0 */
+#define SET_ESYNR0_AMID(b, v)    SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_AMID, v)
+#define SET_ESYNR0_APID(b, v)    SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_APID, v)
+#define SET_ESYNR0_ABID(b, v)    SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_ABID, v)
+#define SET_ESYNR0_AVMID(b, v)   SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_AVMID, v)
+#define SET_ESYNR0_ATID(b, v)    SET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_ATID, v)
+
+
+/* ESYNR1 */
+#define SET_ESYNR1_AMEMTYPE(b, v) \
+			SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AMEMTYPE, v)
+#define SET_ESYNR1_ASHARED(b, v)  SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ASHARED, v)
+#define SET_ESYNR1_AINNERSHARED(b, v) \
+			SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AINNERSHARED, v)
+#define SET_ESYNR1_APRIV(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_APRIV, v)
+#define SET_ESYNR1_APROTNS(b, v) SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_APROTNS, v)
+#define SET_ESYNR1_AINST(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AINST, v)
+#define SET_ESYNR1_AWRITE(b, v)  SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AWRITE, v)
+#define SET_ESYNR1_ABURST(b, v)  SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ABURST, v)
+#define SET_ESYNR1_ALEN(b, v)    SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ALEN, v)
+#define SET_ESYNR1_ASIZE(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ASIZE, v)
+#define SET_ESYNR1_ALOCK(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ALOCK, v)
+#define SET_ESYNR1_AOOO(b, v)    SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AOOO, v)
+#define SET_ESYNR1_AFULL(b, v)   SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AFULL, v)
+#define SET_ESYNR1_AC(b, v)      SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AC, v)
+#define SET_ESYNR1_DCD(b, v)     SET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_DCD, v)
+
+
+/* TESTBUSCR */
+#define SET_TBE(b, v)		 SET_GLOBAL_FIELD(b, TESTBUSCR, TBE, v)
+#define SET_SPDMBE(b, v)	 SET_GLOBAL_FIELD(b, TESTBUSCR, SPDMBE, v)
+#define SET_WGSEL(b, v)		 SET_GLOBAL_FIELD(b, TESTBUSCR, WGSEL, v)
+#define SET_TBLSEL(b, v)	 SET_GLOBAL_FIELD(b, TESTBUSCR, TBLSEL, v)
+#define SET_TBHSEL(b, v)	 SET_GLOBAL_FIELD(b, TESTBUSCR, TBHSEL, v)
+#define SET_SPDM0SEL(b, v)       SET_GLOBAL_FIELD(b, TESTBUSCR, SPDM0SEL, v)
+#define SET_SPDM1SEL(b, v)       SET_GLOBAL_FIELD(b, TESTBUSCR, SPDM1SEL, v)
+#define SET_SPDM2SEL(b, v)       SET_GLOBAL_FIELD(b, TESTBUSCR, SPDM2SEL, v)
+#define SET_SPDM3SEL(b, v)       SET_GLOBAL_FIELD(b, TESTBUSCR, SPDM3SEL, v)
+
+
+/* TLBIVMID */
+#define SET_TLBIVMID_VMID(b, v)  SET_GLOBAL_FIELD(b, TLBIVMID, TLBIVMID_VMID, v)
+
+
+/* TLBRSW */
+#define SET_TLBRSW_INDEX(b, v)   SET_GLOBAL_FIELD(b, TLBRSW, TLBRSW_INDEX, v)
+#define SET_TLBBFBS(b, v)	 SET_GLOBAL_FIELD(b, TLBRSW, TLBBFBS, v)
+
+
+/* TLBTR0 */
+#define SET_PR(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, PR, v)
+#define SET_PW(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, PW, v)
+#define SET_UR(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, UR, v)
+#define SET_UW(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, UW, v)
+#define SET_XN(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, XN, v)
+#define SET_NSDESC(b, v)	 SET_GLOBAL_FIELD(b, TLBTR0, NSDESC, v)
+#define SET_ISH(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, ISH, v)
+#define SET_SH(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, SH, v)
+#define SET_MT(b, v)		 SET_GLOBAL_FIELD(b, TLBTR0, MT, v)
+#define SET_DPSIZR(b, v)	 SET_GLOBAL_FIELD(b, TLBTR0, DPSIZR, v)
+#define SET_DPSIZC(b, v)	 SET_GLOBAL_FIELD(b, TLBTR0, DPSIZC, v)
+
+
+/* TLBTR1 */
+#define SET_TLBTR1_VMID(b, v)    SET_GLOBAL_FIELD(b, TLBTR1, TLBTR1_VMID, v)
+#define SET_TLBTR1_PA(b, v)      SET_GLOBAL_FIELD(b, TLBTR1, TLBTR1_PA, v)
+
+
+/* TLBTR2 */
+#define SET_TLBTR2_ASID(b, v)    SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_ASID, v)
+#define SET_TLBTR2_V(b, v)       SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_V, v)
+#define SET_TLBTR2_NSTID(b, v)   SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_NSTID, v)
+#define SET_TLBTR2_NV(b, v)      SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_NV, v)
+#define SET_TLBTR2_VA(b, v)      SET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_VA, v)
+
+
+/* Global Field Getters */
+/* CBACR_N */
+#define GET_RWVMID(b, n)	 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWVMID)
+#define GET_RWE(b, n)		 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWE)
+#define GET_RWGE(b, n)		 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), RWGE)
+#define GET_CBVMID(b, n)	 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), CBVMID)
+#define GET_IRPTNDX(b, n)	 GET_GLOBAL_FIELD(b, (n<<2)|(CBACR_N), IRPTNDX)
+
+
+/* M2VCBR_N */
+#define GET_VMID(b, n)       GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), VMID)
+#define GET_CBNDX(b, n)      GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), CBNDX)
+#define GET_BYPASSD(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BYPASSD)
+#define GET_BPRCOSH(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCOSH)
+#define GET_BPRCISH(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCISH)
+#define GET_BPRCNSH(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPRCNSH)
+#define GET_BPSHCFG(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPSHCFG)
+#define GET_NSCFG(b, n)      GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), NSCFG)
+#define GET_BPMTCFG(b, n)    GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPMTCFG)
+#define GET_BPMEMTYPE(b, n)  GET_GLOBAL_FIELD(b, (n<<2)|(M2VCBR_N), BPMEMTYPE)
+
+
+/* CR */
+#define GET_RPUE(b)		 GET_GLOBAL_FIELD(b, CR, RPUE)
+#define GET_RPUERE(b)		 GET_GLOBAL_FIELD(b, CR, RPUERE)
+#define GET_RPUEIE(b)		 GET_GLOBAL_FIELD(b, CR, RPUEIE)
+#define GET_DCDEE(b)		 GET_GLOBAL_FIELD(b, CR, DCDEE)
+#define GET_CLIENTPD(b)		 GET_GLOBAL_FIELD(b, CR, CLIENTPD)
+#define GET_STALLD(b)		 GET_GLOBAL_FIELD(b, CR, STALLD)
+#define GET_TLBLKCRWE(b)	 GET_GLOBAL_FIELD(b, CR, TLBLKCRWE)
+#define GET_CR_TLBIALLCFG(b)	 GET_GLOBAL_FIELD(b, CR, CR_TLBIALLCFG)
+#define GET_TLBIVMIDCFG(b)	 GET_GLOBAL_FIELD(b, CR, TLBIVMIDCFG)
+#define GET_CR_HUME(b)		 GET_GLOBAL_FIELD(b, CR, CR_HUME)
+
+
+/* ESR */
+#define GET_CFG(b)		 GET_GLOBAL_FIELD(b, ESR, CFG)
+#define GET_BYPASS(b)		 GET_GLOBAL_FIELD(b, ESR, BYPASS)
+#define GET_ESR_MULTI(b)	 GET_GLOBAL_FIELD(b, ESR, ESR_MULTI)
+
+
+/* ESYNR0 */
+#define GET_ESYNR0_AMID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_AMID)
+#define GET_ESYNR0_APID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_APID)
+#define GET_ESYNR0_ABID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_ABID)
+#define GET_ESYNR0_AVMID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_AVMID)
+#define GET_ESYNR0_ATID(b)	 GET_GLOBAL_FIELD(b, ESYNR0, ESYNR0_ATID)
+
+
+/* ESYNR1 */
+#define GET_ESYNR1_AMEMTYPE(b)   GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AMEMTYPE)
+#define GET_ESYNR1_ASHARED(b)    GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ASHARED)
+#define GET_ESYNR1_AINNERSHARED(b) \
+			GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AINNERSHARED)
+#define GET_ESYNR1_APRIV(b)      GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_APRIV)
+#define GET_ESYNR1_APROTNS(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_APROTNS)
+#define GET_ESYNR1_AINST(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AINST)
+#define GET_ESYNR1_AWRITE(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AWRITE)
+#define GET_ESYNR1_ABURST(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ABURST)
+#define GET_ESYNR1_ALEN(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ALEN)
+#define GET_ESYNR1_ASIZE(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ASIZE)
+#define GET_ESYNR1_ALOCK(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_ALOCK)
+#define GET_ESYNR1_AOOO(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AOOO)
+#define GET_ESYNR1_AFULL(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AFULL)
+#define GET_ESYNR1_AC(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_AC)
+#define GET_ESYNR1_DCD(b)	 GET_GLOBAL_FIELD(b, ESYNR1, ESYNR1_DCD)
+
+
+/* IDR */
+#define GET_NM2VCBMT(b)		 GET_GLOBAL_FIELD(b, IDR, NM2VCBMT)
+#define GET_HTW(b)		 GET_GLOBAL_FIELD(b, IDR, HTW)
+#define GET_HUM(b)		 GET_GLOBAL_FIELD(b, IDR, HUM)
+#define GET_TLBSIZE(b)		 GET_GLOBAL_FIELD(b, IDR, TLBSIZE)
+#define GET_NCB(b)		 GET_GLOBAL_FIELD(b, IDR, NCB)
+#define GET_NIRPT(b)		 GET_GLOBAL_FIELD(b, IDR, NIRPT)
+
+
+/* REV */
+#define GET_MAJOR(b)		 GET_GLOBAL_FIELD(b, REV, MAJOR)
+#define GET_MINOR(b)		 GET_GLOBAL_FIELD(b, REV, MINOR)
+
+
+/* TESTBUSCR */
+#define GET_TBE(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, TBE)
+#define GET_SPDMBE(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDMBE)
+#define GET_WGSEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, WGSEL)
+#define GET_TBLSEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, TBLSEL)
+#define GET_TBHSEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, TBHSEL)
+#define GET_SPDM0SEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDM0SEL)
+#define GET_SPDM1SEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDM1SEL)
+#define GET_SPDM2SEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDM2SEL)
+#define GET_SPDM3SEL(b)		 GET_GLOBAL_FIELD(b, TESTBUSCR, SPDM3SEL)
+
+
+/* TLBIVMID */
+#define GET_TLBIVMID_VMID(b)	 GET_GLOBAL_FIELD(b, TLBIVMID, TLBIVMID_VMID)
+
+
+/* TLBTR0 */
+#define GET_PR(b)		 GET_GLOBAL_FIELD(b, TLBTR0, PR)
+#define GET_PW(b)		 GET_GLOBAL_FIELD(b, TLBTR0, PW)
+#define GET_UR(b)		 GET_GLOBAL_FIELD(b, TLBTR0, UR)
+#define GET_UW(b)		 GET_GLOBAL_FIELD(b, TLBTR0, UW)
+#define GET_XN(b)		 GET_GLOBAL_FIELD(b, TLBTR0, XN)
+#define GET_NSDESC(b)		 GET_GLOBAL_FIELD(b, TLBTR0, NSDESC)
+#define GET_ISH(b)		 GET_GLOBAL_FIELD(b, TLBTR0, ISH)
+#define GET_SH(b)		 GET_GLOBAL_FIELD(b, TLBTR0, SH)
+#define GET_MT(b)		 GET_GLOBAL_FIELD(b, TLBTR0, MT)
+#define GET_DPSIZR(b)		 GET_GLOBAL_FIELD(b, TLBTR0, DPSIZR)
+#define GET_DPSIZC(b)		 GET_GLOBAL_FIELD(b, TLBTR0, DPSIZC)
+
+
+/* TLBTR1 */
+#define GET_TLBTR1_VMID(b)	 GET_GLOBAL_FIELD(b, TLBTR1, TLBTR1_VMID)
+#define GET_TLBTR1_PA(b)	 GET_GLOBAL_FIELD(b, TLBTR1, TLBTR1_PA)
+
+
+/* TLBTR2 */
+#define GET_TLBTR2_ASID(b)	 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_ASID)
+#define GET_TLBTR2_V(b)		 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_V)
+#define GET_TLBTR2_NSTID(b)	 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_NSTID)
+#define GET_TLBTR2_NV(b)	 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_NV)
+#define GET_TLBTR2_VA(b)	 GET_GLOBAL_FIELD(b, TLBTR2, TLBTR2_VA)
+
+
+/* Context Register setters / getters */
+/* Context Register setters */
+/* ACTLR */
+#define SET_CFERE(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, CFERE, v)
+#define SET_CFEIE(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, CFEIE, v)
+#define SET_PTSHCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, PTSHCFG, v)
+#define SET_RCOSH(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, RCOSH, v)
+#define SET_RCISH(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, RCISH, v)
+#define SET_RCNSH(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, RCNSH, v)
+#define SET_PRIVCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, PRIVCFG, v)
+#define SET_DNA(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, DNA, v)
+#define SET_DNLV2PA(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, DNLV2PA, v)
+#define SET_TLBMCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, TLBMCFG, v)
+#define SET_CFCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, CFCFG, v)
+#define SET_TIPCF(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, TIPCF, v)
+#define SET_V2PCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, V2PCFG, v)
+#define SET_HUME(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, HUME, v)
+#define SET_PTMTCFG(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, PTMTCFG, v)
+#define SET_PTMEMTYPE(b, c, v)	 SET_CONTEXT_FIELD(b, c, ACTLR, PTMEMTYPE, v)
+
+
+/* BFBCR */
+#define SET_BFBDFE(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, BFBDFE, v)
+#define SET_BFBSFE(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, BFBSFE, v)
+#define SET_SFVS(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, SFVS, v)
+#define SET_FLVIC(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, FLVIC, v)
+#define SET_SLVIC(b, c, v)	 SET_CONTEXT_FIELD(b, c, BFBCR, SLVIC, v)
+
+
+/* CONTEXTIDR */
+#define SET_CONTEXTIDR_ASID(b, c, v)   \
+		SET_CONTEXT_FIELD(b, c, CONTEXTIDR, CONTEXTIDR_ASID, v)
+#define SET_CONTEXTIDR_PROCID(b, c, v) \
+		SET_CONTEXT_FIELD(b, c, CONTEXTIDR, PROCID, v)
+
+
+/* FSR */
+#define SET_TF(b, c, v)		 SET_CONTEXT_FIELD(b, c, FSR, TF, v)
+#define SET_AFF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, AFF, v)
+#define SET_APF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, APF, v)
+#define SET_TLBMF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, TLBMF, v)
+#define SET_HTWDEEF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, HTWDEEF, v)
+#define SET_HTWSEEF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, HTWSEEF, v)
+#define SET_MHF(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, MHF, v)
+#define SET_SL(b, c, v)		 SET_CONTEXT_FIELD(b, c, FSR, SL, v)
+#define SET_SS(b, c, v)		 SET_CONTEXT_FIELD(b, c, FSR, SS, v)
+#define SET_MULTI(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSR, MULTI, v)
+
+
+/* FSYNR0 */
+#define SET_AMID(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR0, AMID, v)
+#define SET_APID(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR0, APID, v)
+#define SET_ABID(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR0, ABID, v)
+#define SET_ATID(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR0, ATID, v)
+
+
+/* FSYNR1 */
+#define SET_AMEMTYPE(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, AMEMTYPE, v)
+#define SET_ASHARED(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, ASHARED, v)
+#define SET_AINNERSHARED(b, c, v)  \
+				SET_CONTEXT_FIELD(b, c, FSYNR1, AINNERSHARED, v)
+#define SET_APRIV(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, APRIV, v)
+#define SET_APROTNS(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, APROTNS, v)
+#define SET_AINST(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, AINST, v)
+#define SET_AWRITE(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, AWRITE, v)
+#define SET_ABURST(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, ABURST, v)
+#define SET_ALEN(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, ALEN, v)
+#define SET_FSYNR1_ASIZE(b, c, v) \
+				SET_CONTEXT_FIELD(b, c, FSYNR1, FSYNR1_ASIZE, v)
+#define SET_ALOCK(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, ALOCK, v)
+#define SET_AFULL(b, c, v)	 SET_CONTEXT_FIELD(b, c, FSYNR1, AFULL, v)
+
+
+/* NMRR */
+#define SET_ICPC0(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC0, v)
+#define SET_ICPC1(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC1, v)
+#define SET_ICPC2(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC2, v)
+#define SET_ICPC3(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC3, v)
+#define SET_ICPC4(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC4, v)
+#define SET_ICPC5(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC5, v)
+#define SET_ICPC6(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC6, v)
+#define SET_ICPC7(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, ICPC7, v)
+#define SET_OCPC0(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC0, v)
+#define SET_OCPC1(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC1, v)
+#define SET_OCPC2(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC2, v)
+#define SET_OCPC3(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC3, v)
+#define SET_OCPC4(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC4, v)
+#define SET_OCPC5(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC5, v)
+#define SET_OCPC6(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC6, v)
+#define SET_OCPC7(b, c, v)	 SET_CONTEXT_FIELD(b, c, NMRR, OCPC7, v)
+
+
+/* PAR */
+#define SET_FAULT(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT, v)
+
+#define SET_FAULT_TF(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_TF, v)
+#define SET_FAULT_AFF(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_AFF, v)
+#define SET_FAULT_APF(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_APF, v)
+#define SET_FAULT_TLBMF(b, c, v) SET_CONTEXT_FIELD(b, c, PAR, FAULT_TLBMF, v)
+#define SET_FAULT_HTWDEEF(b, c, v) \
+				SET_CONTEXT_FIELD(b, c, PAR, FAULT_HTWDEEF, v)
+#define SET_FAULT_HTWSEEF(b, c, v) \
+				SET_CONTEXT_FIELD(b, c, PAR, FAULT_HTWSEEF, v)
+#define SET_FAULT_MHF(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_MHF, v)
+#define SET_FAULT_SL(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_SL, v)
+#define SET_FAULT_SS(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, FAULT_SS, v)
+
+#define SET_NOFAULT_SS(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_SS, v)
+#define SET_NOFAULT_MT(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_MT, v)
+#define SET_NOFAULT_SH(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_SH, v)
+#define SET_NOFAULT_NS(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_NS, v)
+#define SET_NOFAULT_NOS(b, c, v) SET_CONTEXT_FIELD(b, c, PAR, NOFAULT_NOS, v)
+#define SET_NPFAULT_PA(b, c, v)	 SET_CONTEXT_FIELD(b, c, PAR, NPFAULT_PA, v)
+
+
+/* PRRR */
+#define SET_MTC0(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC0, v)
+#define SET_MTC1(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC1, v)
+#define SET_MTC2(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC2, v)
+#define SET_MTC3(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC3, v)
+#define SET_MTC4(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC4, v)
+#define SET_MTC5(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC5, v)
+#define SET_MTC6(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC6, v)
+#define SET_MTC7(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, MTC7, v)
+#define SET_SHDSH0(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, SHDSH0, v)
+#define SET_SHDSH1(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, SHDSH1, v)
+#define SET_SHNMSH0(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, SHNMSH0, v)
+#define SET_SHNMSH1(b, c, v)     SET_CONTEXT_FIELD(b, c, PRRR, SHNMSH1, v)
+#define SET_NOS0(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS0, v)
+#define SET_NOS1(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS1, v)
+#define SET_NOS2(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS2, v)
+#define SET_NOS3(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS3, v)
+#define SET_NOS4(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS4, v)
+#define SET_NOS5(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS5, v)
+#define SET_NOS6(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS6, v)
+#define SET_NOS7(b, c, v)	 SET_CONTEXT_FIELD(b, c, PRRR, NOS7, v)
+
+
+/* RESUME */
+#define SET_TNR(b, c, v)	 SET_CONTEXT_FIELD(b, c, RESUME, TNR, v)
+
+
+/* SCTLR */
+#define SET_M(b, c, v)		 SET_CONTEXT_FIELD(b, c, SCTLR, M, v)
+#define SET_TRE(b, c, v)	 SET_CONTEXT_FIELD(b, c, SCTLR, TRE, v)
+#define SET_AFE(b, c, v)	 SET_CONTEXT_FIELD(b, c, SCTLR, AFE, v)
+#define SET_HAF(b, c, v)	 SET_CONTEXT_FIELD(b, c, SCTLR, HAF, v)
+#define SET_BE(b, c, v)		 SET_CONTEXT_FIELD(b, c, SCTLR, BE, v)
+#define SET_AFFD(b, c, v)	 SET_CONTEXT_FIELD(b, c, SCTLR, AFFD, v)
+
+
+/* TLBLKCR */
+#define SET_LKE(b, c, v)	   SET_CONTEXT_FIELD(b, c, TLBLKCR, LKE, v)
+#define SET_TLBLKCR_TLBIALLCFG(b, c, v) \
+			SET_CONTEXT_FIELD(b, c, TLBLKCR, TLBLCKR_TLBIALLCFG, v)
+#define SET_TLBIASIDCFG(b, c, v) \
+			SET_CONTEXT_FIELD(b, c, TLBLKCR, TLBIASIDCFG, v)
+#define SET_TLBIVAACFG(b, c, v)	SET_CONTEXT_FIELD(b, c, TLBLKCR, TLBIVAACFG, v)
+#define SET_FLOOR(b, c, v)	SET_CONTEXT_FIELD(b, c, TLBLKCR, FLOOR, v)
+#define SET_VICTIM(b, c, v)	SET_CONTEXT_FIELD(b, c, TLBLKCR, VICTIM, v)
+
+
+/* TTBCR */
+#define SET_N(b, c, v)	         SET_CONTEXT_FIELD(b, c, TTBCR, N, v)
+#define SET_PD0(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBCR, PD0, v)
+#define SET_PD1(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBCR, PD1, v)
+
+
+/* TTBR0 */
+#define SET_TTBR0_IRGNH(b, c, v) SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_IRGNH, v)
+#define SET_TTBR0_SH(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_SH, v)
+#define SET_TTBR0_ORGN(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_ORGN, v)
+#define SET_TTBR0_NOS(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_NOS, v)
+#define SET_TTBR0_IRGNL(b, c, v) SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_IRGNL, v)
+#define SET_TTBR0_PA(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_PA, v)
+
+
+/* TTBR1 */
+#define SET_TTBR1_IRGNH(b, c, v) SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_IRGNH, v)
+#define SET_TTBR1_SH(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_SH, v)
+#define SET_TTBR1_ORGN(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_ORGN, v)
+#define SET_TTBR1_NOS(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_NOS, v)
+#define SET_TTBR1_IRGNL(b, c, v) SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_IRGNL, v)
+#define SET_TTBR1_PA(b, c, v)	 SET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_PA, v)
+
+
+/* V2PSR */
+#define SET_HIT(b, c, v)	 SET_CONTEXT_FIELD(b, c, V2PSR, HIT, v)
+#define SET_INDEX(b, c, v)	 SET_CONTEXT_FIELD(b, c, V2PSR, INDEX, v)
+
+
+/* V2Pxx UW UR PW PR */
+#define SET_V2PUW_INDEX(b, c, v) SET_CONTEXT_FIELD(b, c, V2PUW, V2Pxx_INDEX, v)
+#define SET_V2PUW_VA(b, c, v)	 SET_CONTEXT_FIELD(b, c, V2PUW, V2Pxx_VA, v)
+
+#define SET_V2PUR_INDEX(b, c, v) SET_CONTEXT_FIELD(b, c, V2PUR, V2Pxx_INDEX, v)
+#define SET_V2PUR_VA(b, c, v)	 SET_CONTEXT_FIELD(b, c, V2PUR, V2Pxx_VA, v)
+
+#define SET_V2PPW_INDEX(b, c, v) SET_CONTEXT_FIELD(b, c, V2PPW, V2Pxx_INDEX, v)
+#define SET_V2PPW_VA(b, c, v)	 SET_CONTEXT_FIELD(b, c, V2PPW, V2Pxx_VA, v)
+
+#define SET_V2PPR_INDEX(b, c, v) SET_CONTEXT_FIELD(b, c, V2PPR, V2Pxx_INDEX, v)
+#define SET_V2PPR_VA(b, c, v)	 SET_CONTEXT_FIELD(b, c, V2PPR, V2Pxx_VA, v)
+
+
+/* Context Register getters */
+/* ACTLR */
+#define GET_CFERE(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, CFERE)
+#define GET_CFEIE(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, CFEIE)
+#define GET_PTSHCFG(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, PTSHCFG)
+#define GET_RCOSH(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, RCOSH)
+#define GET_RCISH(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, RCISH)
+#define GET_RCNSH(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, RCNSH)
+#define GET_PRIVCFG(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, PRIVCFG)
+#define GET_DNA(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, DNA)
+#define GET_DNLV2PA(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, DNLV2PA)
+#define GET_TLBMCFG(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, TLBMCFG)
+#define GET_CFCFG(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, CFCFG)
+#define GET_TIPCF(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, TIPCF)
+#define GET_V2PCFG(b, c)        GET_CONTEXT_FIELD(b, c, ACTLR, V2PCFG)
+#define GET_HUME(b, c)	        GET_CONTEXT_FIELD(b, c, ACTLR, HUME)
+#define GET_PTMTCFG(b, c)       GET_CONTEXT_FIELD(b, c, ACTLR, PTMTCFG)
+#define GET_PTMEMTYPE(b, c)     GET_CONTEXT_FIELD(b, c, ACTLR, PTMEMTYPE)
+
+/* BFBCR */
+#define GET_BFBDFE(b, c)	GET_CONTEXT_FIELD(b, c, BFBCR, BFBDFE)
+#define GET_BFBSFE(b, c)	GET_CONTEXT_FIELD(b, c, BFBCR, BFBSFE)
+#define GET_SFVS(b, c)		GET_CONTEXT_FIELD(b, c, BFBCR, SFVS)
+#define GET_FLVIC(b, c)		GET_CONTEXT_FIELD(b, c, BFBCR, FLVIC)
+#define GET_SLVIC(b, c)		GET_CONTEXT_FIELD(b, c, BFBCR, SLVIC)
+
+
+/* CONTEXTIDR */
+#define GET_CONTEXTIDR_ASID(b, c) \
+			GET_CONTEXT_FIELD(b, c, CONTEXTIDR, CONTEXTIDR_ASID)
+#define GET_CONTEXTIDR_PROCID(b, c) GET_CONTEXT_FIELD(b, c, CONTEXTIDR, PROCID)
+
+
+/* FSR */
+#define GET_TF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, TF)
+#define GET_AFF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, AFF)
+#define GET_APF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, APF)
+#define GET_TLBMF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, TLBMF)
+#define GET_HTWDEEF(b, c)	GET_CONTEXT_FIELD(b, c, FSR, HTWDEEF)
+#define GET_HTWSEEF(b, c)	GET_CONTEXT_FIELD(b, c, FSR, HTWSEEF)
+#define GET_MHF(b, c)		GET_CONTEXT_FIELD(b, c, FSR, MHF)
+#define GET_SL(b, c)		GET_CONTEXT_FIELD(b, c, FSR, SL)
+#define GET_SS(b, c)		GET_CONTEXT_FIELD(b, c, FSR, SS)
+#define GET_MULTI(b, c)		GET_CONTEXT_FIELD(b, c, FSR, MULTI)
+
+
+/* FSYNR0 */
+#define GET_AMID(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR0, AMID)
+#define GET_APID(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR0, APID)
+#define GET_ABID(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR0, ABID)
+#define GET_ATID(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR0, ATID)
+
+
+/* FSYNR1 */
+#define GET_AMEMTYPE(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, AMEMTYPE)
+#define GET_ASHARED(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, ASHARED)
+#define GET_AINNERSHARED(b, c)  GET_CONTEXT_FIELD(b, c, FSYNR1, AINNERSHARED)
+#define GET_APRIV(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, APRIV)
+#define GET_APROTNS(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, APROTNS)
+#define GET_AINST(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, AINST)
+#define GET_AWRITE(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, AWRITE)
+#define GET_ABURST(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, ABURST)
+#define GET_ALEN(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, ALEN)
+#define GET_FSYNR1_ASIZE(b, c)	GET_CONTEXT_FIELD(b, c, FSYNR1, FSYNR1_ASIZE)
+#define GET_ALOCK(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, ALOCK)
+#define GET_AFULL(b, c)		GET_CONTEXT_FIELD(b, c, FSYNR1, AFULL)
+
+
+/* NMRR */
+#define GET_ICPC0(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC0)
+#define GET_ICPC1(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC1)
+#define GET_ICPC2(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC2)
+#define GET_ICPC3(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC3)
+#define GET_ICPC4(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC4)
+#define GET_ICPC5(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC5)
+#define GET_ICPC6(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC6)
+#define GET_ICPC7(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, ICPC7)
+#define GET_OCPC0(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC0)
+#define GET_OCPC1(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC1)
+#define GET_OCPC2(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC2)
+#define GET_OCPC3(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC3)
+#define GET_OCPC4(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC4)
+#define GET_OCPC5(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC5)
+#define GET_OCPC6(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC6)
+#define GET_OCPC7(b, c)		GET_CONTEXT_FIELD(b, c, NMRR, OCPC7)
+
+
+/* PAR */
+#define GET_FAULT(b, c)		GET_CONTEXT_FIELD(b, c, PAR, FAULT)
+
+#define GET_FAULT_TF(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_TF)
+#define GET_FAULT_AFF(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_AFF)
+#define GET_FAULT_APF(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_APF)
+#define GET_FAULT_TLBMF(b, c)   GET_CONTEXT_FIELD(b, c, PAR, FAULT_TLBMF)
+#define GET_FAULT_HTWDEEF(b, c) GET_CONTEXT_FIELD(b, c, PAR, FAULT_HTWDEEF)
+#define GET_FAULT_HTWSEEF(b, c) GET_CONTEXT_FIELD(b, c, PAR, FAULT_HTWSEEF)
+#define GET_FAULT_MHF(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_MHF)
+#define GET_FAULT_SL(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_SL)
+#define GET_FAULT_SS(b, c)	GET_CONTEXT_FIELD(b, c, PAR, FAULT_SS)
+
+#define GET_NOFAULT_SS(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_SS)
+#define GET_NOFAULT_MT(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_MT)
+#define GET_NOFAULT_SH(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_SH)
+#define GET_NOFAULT_NS(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_NS)
+#define GET_NOFAULT_NOS(b, c)   GET_CONTEXT_FIELD(b, c, PAR, PAR_NOFAULT_NOS)
+#define GET_NPFAULT_PA(b, c)	GET_CONTEXT_FIELD(b, c, PAR, PAR_NPFAULT_PA)
+
+
+/* PRRR */
+#define GET_MTC0(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC0)
+#define GET_MTC1(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC1)
+#define GET_MTC2(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC2)
+#define GET_MTC3(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC3)
+#define GET_MTC4(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC4)
+#define GET_MTC5(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC5)
+#define GET_MTC6(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC6)
+#define GET_MTC7(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, MTC7)
+#define GET_SHDSH0(b, c)	GET_CONTEXT_FIELD(b, c, PRRR, SHDSH0)
+#define GET_SHDSH1(b, c)	GET_CONTEXT_FIELD(b, c, PRRR, SHDSH1)
+#define GET_SHNMSH0(b, c)	GET_CONTEXT_FIELD(b, c, PRRR, SHNMSH0)
+#define GET_SHNMSH1(b, c)	GET_CONTEXT_FIELD(b, c, PRRR, SHNMSH1)
+#define GET_NOS0(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS0)
+#define GET_NOS1(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS1)
+#define GET_NOS2(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS2)
+#define GET_NOS3(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS3)
+#define GET_NOS4(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS4)
+#define GET_NOS5(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS5)
+#define GET_NOS6(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS6)
+#define GET_NOS7(b, c)		GET_CONTEXT_FIELD(b, c, PRRR, NOS7)
+
+
+/* RESUME */
+#define GET_TNR(b, c)		GET_CONTEXT_FIELD(b, c, RESUME, TNR)
+
+
+/* SCTLR */
+#define GET_M(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, M)
+#define GET_TRE(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, TRE)
+#define GET_AFE(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, AFE)
+#define GET_HAF(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, HAF)
+#define GET_BE(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, BE)
+#define GET_AFFD(b, c)		GET_CONTEXT_FIELD(b, c, SCTLR, AFFD)
+
+
+/* TLBLKCR */
+#define GET_LKE(b, c)		GET_CONTEXT_FIELD(b, c, TLBLKCR, LKE)
+#define GET_TLBLCKR_TLBIALLCFG(b, c) \
+			GET_CONTEXT_FIELD(b, c, TLBLKCR, TLBLCKR_TLBIALLCFG)
+#define GET_TLBIASIDCFG(b, c)   GET_CONTEXT_FIELD(b, c, TLBLKCR, TLBIASIDCFG)
+#define GET_TLBIVAACFG(b, c)	GET_CONTEXT_FIELD(b, c, TLBLKCR, TLBIVAACFG)
+#define GET_FLOOR(b, c)		GET_CONTEXT_FIELD(b, c, TLBLKCR, FLOOR)
+#define GET_VICTIM(b, c)	GET_CONTEXT_FIELD(b, c, TLBLKCR, VICTIM)
+
+
+/* TTBCR */
+#define GET_N(b, c)		GET_CONTEXT_FIELD(b, c, TTBCR, N)
+#define GET_PD0(b, c)		GET_CONTEXT_FIELD(b, c, TTBCR, PD0)
+#define GET_PD1(b, c)		GET_CONTEXT_FIELD(b, c, TTBCR, PD1)
+
+
+/* TTBR0 */
+#define GET_TTBR0_IRGNH(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_IRGNH)
+#define GET_TTBR0_SH(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_SH)
+#define GET_TTBR0_ORGN(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_ORGN)
+#define GET_TTBR0_NOS(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_NOS)
+#define GET_TTBR0_IRGNL(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_IRGNL)
+#define GET_TTBR0_PA(b, c)	GET_CONTEXT_FIELD(b, c, TTBR0, TTBR0_PA)
+
+
+/* TTBR1 */
+#define GET_TTBR1_IRGNH(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_IRGNH)
+#define GET_TTBR1_SH(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_SH)
+#define GET_TTBR1_ORGN(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_ORGN)
+#define GET_TTBR1_NOS(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_NOS)
+#define GET_TTBR1_IRGNL(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_IRGNL)
+#define GET_TTBR1_PA(b, c)	GET_CONTEXT_FIELD(b, c, TTBR1, TTBR1_PA)
+
+
+/* V2PSR */
+#define GET_HIT(b, c)		GET_CONTEXT_FIELD(b, c, V2PSR, HIT)
+#define GET_INDEX(b, c)		GET_CONTEXT_FIELD(b, c, V2PSR, INDEX)
+
+
+/* V2Pxx UW UR PW PR */
+#define GET_V2PUW_INDEX(b, c)	GET_CONTEXT_FIELD(b, c, V2PUW, V2Pxx_INDEX)
+#define GET_V2PUW_VA(b, c)	GET_CONTEXT_FIELD(b, c, V2PUW, V2Pxx_VA)
+
+#define GET_V2PUR_INDEX(b, c)	GET_CONTEXT_FIELD(b, c, V2PUR, V2Pxx_INDEX)
+#define GET_V2PUR_VA(b, c)	GET_CONTEXT_FIELD(b, c, V2PUR, V2Pxx_VA)
+
+#define GET_V2PPW_INDEX(b, c)	GET_CONTEXT_FIELD(b, c, V2PPW, V2Pxx_INDEX)
+#define GET_V2PPW_VA(b, c)	GET_CONTEXT_FIELD(b, c, V2PPW, V2Pxx_VA)
+
+#define GET_V2PPR_INDEX(b, c)	GET_CONTEXT_FIELD(b, c, V2PPR, V2Pxx_INDEX)
+#define GET_V2PPR_VA(b, c)	GET_CONTEXT_FIELD(b, c, V2PPR, V2Pxx_VA)
+
+
+/* Global Registers */
+#define M2VCBR_N	(0xFF000)
+#define CBACR_N		(0xFF800)
+#define TLBRSW		(0xFFE00)
+#define TLBTR0		(0xFFE80)
+#define TLBTR1		(0xFFE84)
+#define TLBTR2		(0xFFE88)
+#define TESTBUSCR	(0xFFE8C)
+#define GLOBAL_TLBIALL	(0xFFF00)
+#define TLBIVMID	(0xFFF04)
+#define CR		(0xFFF80)
+#define EAR		(0xFFF84)
+#define ESR		(0xFFF88)
+#define ESRRESTORE	(0xFFF8C)
+#define ESYNR0		(0xFFF90)
+#define ESYNR1		(0xFFF94)
+#define REV		(0xFFFF4)
+#define IDR		(0xFFFF8)
+#define RPU_ACR		(0xFFFFC)
+
+
+/* Context Bank Registers */
+#define SCTLR		(0x000)
+#define ACTLR		(0x004)
+#define CONTEXTIDR	(0x008)
+#define TTBR0		(0x010)
+#define TTBR1		(0x014)
+#define TTBCR		(0x018)
+#define PAR		(0x01C)
+#define FSR		(0x020)
+#define FSRRESTORE	(0x024)
+#define FAR		(0x028)
+#define FSYNR0		(0x02C)
+#define FSYNR1		(0x030)
+#define PRRR		(0x034)
+#define NMRR		(0x038)
+#define TLBLCKR		(0x03C)
+#define V2PSR		(0x040)
+#define TLBFLPTER	(0x044)
+#define TLBSLPTER	(0x048)
+#define BFBCR		(0x04C)
+#define CTX_TLBIALL	(0x800)
+#define TLBIASID	(0x804)
+#define TLBIVA		(0x808)
+#define TLBIVAA		(0x80C)
+#define V2PPR		(0x810)
+#define V2PPW		(0x814)
+#define V2PUR		(0x818)
+#define V2PUW		(0x81C)
+#define RESUME		(0x820)
+
+
+/* Global Register Fields */
+/* CBACRn */
+#define RWVMID        (RWVMID_MASK       << RWVMID_SHIFT)
+#define RWE           (RWE_MASK          << RWE_SHIFT)
+#define RWGE          (RWGE_MASK         << RWGE_SHIFT)
+#define CBVMID        (CBVMID_MASK       << CBVMID_SHIFT)
+#define IRPTNDX       (IRPTNDX_MASK      << IRPTNDX_SHIFT)
+
+
+/* CR */
+#define RPUE          (RPUE_MASK          << RPUE_SHIFT)
+#define RPUERE        (RPUERE_MASK        << RPUERE_SHIFT)
+#define RPUEIE        (RPUEIE_MASK        << RPUEIE_SHIFT)
+#define DCDEE         (DCDEE_MASK         << DCDEE_SHIFT)
+#define CLIENTPD      (CLIENTPD_MASK      << CLIENTPD_SHIFT)
+#define STALLD        (STALLD_MASK        << STALLD_SHIFT)
+#define TLBLKCRWE     (TLBLKCRWE_MASK     << TLBLKCRWE_SHIFT)
+#define CR_TLBIALLCFG (CR_TLBIALLCFG_MASK << CR_TLBIALLCFG_SHIFT)
+#define TLBIVMIDCFG   (TLBIVMIDCFG_MASK   << TLBIVMIDCFG_SHIFT)
+#define CR_HUME       (CR_HUME_MASK       << CR_HUME_SHIFT)
+
+
+/* ESR */
+#define CFG           (CFG_MASK          << CFG_SHIFT)
+#define BYPASS        (BYPASS_MASK       << BYPASS_SHIFT)
+#define ESR_MULTI     (ESR_MULTI_MASK    << ESR_MULTI_SHIFT)
+
+
+/* ESYNR0 */
+#define ESYNR0_AMID   (ESYNR0_AMID_MASK  << ESYNR0_AMID_SHIFT)
+#define ESYNR0_APID   (ESYNR0_APID_MASK  << ESYNR0_APID_SHIFT)
+#define ESYNR0_ABID   (ESYNR0_ABID_MASK  << ESYNR0_ABID_SHIFT)
+#define ESYNR0_AVMID  (ESYNR0_AVMID_MASK << ESYNR0_AVMID_SHIFT)
+#define ESYNR0_ATID   (ESYNR0_ATID_MASK  << ESYNR0_ATID_SHIFT)
+
+
+/* ESYNR1 */
+#define ESYNR1_AMEMTYPE      (ESYNR1_AMEMTYPE_MASK    << ESYNR1_AMEMTYPE_SHIFT)
+#define ESYNR1_ASHARED       (ESYNR1_ASHARED_MASK     << ESYNR1_ASHARED_SHIFT)
+#define ESYNR1_AINNERSHARED  (ESYNR1_AINNERSHARED_MASK<< \
+						ESYNR1_AINNERSHARED_SHIFT)
+#define ESYNR1_APRIV         (ESYNR1_APRIV_MASK       << ESYNR1_APRIV_SHIFT)
+#define ESYNR1_APROTNS       (ESYNR1_APROTNS_MASK     << ESYNR1_APROTNS_SHIFT)
+#define ESYNR1_AINST         (ESYNR1_AINST_MASK       << ESYNR1_AINST_SHIFT)
+#define ESYNR1_AWRITE        (ESYNR1_AWRITE_MASK      << ESYNR1_AWRITE_SHIFT)
+#define ESYNR1_ABURST        (ESYNR1_ABURST_MASK      << ESYNR1_ABURST_SHIFT)
+#define ESYNR1_ALEN          (ESYNR1_ALEN_MASK        << ESYNR1_ALEN_SHIFT)
+#define ESYNR1_ASIZE         (ESYNR1_ASIZE_MASK       << ESYNR1_ASIZE_SHIFT)
+#define ESYNR1_ALOCK         (ESYNR1_ALOCK_MASK       << ESYNR1_ALOCK_SHIFT)
+#define ESYNR1_AOOO          (ESYNR1_AOOO_MASK        << ESYNR1_AOOO_SHIFT)
+#define ESYNR1_AFULL         (ESYNR1_AFULL_MASK       << ESYNR1_AFULL_SHIFT)
+#define ESYNR1_AC            (ESYNR1_AC_MASK          << ESYNR1_AC_SHIFT)
+#define ESYNR1_DCD           (ESYNR1_DCD_MASK         << ESYNR1_DCD_SHIFT)
+
+
+/* IDR */
+#define NM2VCBMT      (NM2VCBMT_MASK     << NM2VCBMT_SHIFT)
+#define HTW           (HTW_MASK          << HTW_SHIFT)
+#define HUM           (HUM_MASK          << HUM_SHIFT)
+#define TLBSIZE       (TLBSIZE_MASK      << TLBSIZE_SHIFT)
+#define NCB           (NCB_MASK          << NCB_SHIFT)
+#define NIRPT         (NIRPT_MASK        << NIRPT_SHIFT)
+
+
+/* M2VCBRn */
+#define VMID          (VMID_MASK         << VMID_SHIFT)
+#define CBNDX         (CBNDX_MASK        << CBNDX_SHIFT)
+#define BYPASSD       (BYPASSD_MASK      << BYPASSD_SHIFT)
+#define BPRCOSH       (BPRCOSH_MASK      << BPRCOSH_SHIFT)
+#define BPRCISH       (BPRCISH_MASK      << BPRCISH_SHIFT)
+#define BPRCNSH       (BPRCNSH_MASK      << BPRCNSH_SHIFT)
+#define BPSHCFG       (BPSHCFG_MASK      << BPSHCFG_SHIFT)
+#define NSCFG         (NSCFG_MASK        << NSCFG_SHIFT)
+#define BPMTCFG       (BPMTCFG_MASK      << BPMTCFG_SHIFT)
+#define BPMEMTYPE     (BPMEMTYPE_MASK    << BPMEMTYPE_SHIFT)
+
+
+/* REV */
+#define IDR_MINOR     (MINOR_MASK        << MINOR_SHIFT)
+#define IDR_MAJOR     (MAJOR_MASK        << MAJOR_SHIFT)
+
+
+/* TESTBUSCR */
+#define TBE           (TBE_MASK          << TBE_SHIFT)
+#define SPDMBE        (SPDMBE_MASK       << SPDMBE_SHIFT)
+#define WGSEL         (WGSEL_MASK        << WGSEL_SHIFT)
+#define TBLSEL        (TBLSEL_MASK       << TBLSEL_SHIFT)
+#define TBHSEL        (TBHSEL_MASK       << TBHSEL_SHIFT)
+#define SPDM0SEL      (SPDM0SEL_MASK     << SPDM0SEL_SHIFT)
+#define SPDM1SEL      (SPDM1SEL_MASK     << SPDM1SEL_SHIFT)
+#define SPDM2SEL      (SPDM2SEL_MASK     << SPDM2SEL_SHIFT)
+#define SPDM3SEL      (SPDM3SEL_MASK     << SPDM3SEL_SHIFT)
+
+
+/* TLBIVMID */
+#define TLBIVMID_VMID (TLBIVMID_VMID_MASK << TLBIVMID_VMID_SHIFT)
+
+
+/* TLBRSW */
+#define TLBRSW_INDEX  (TLBRSW_INDEX_MASK << TLBRSW_INDEX_SHIFT)
+#define TLBBFBS       (TLBBFBS_MASK      << TLBBFBS_SHIFT)
+
+
+/* TLBTR0 */
+#define PR            (PR_MASK           << PR_SHIFT)
+#define PW            (PW_MASK           << PW_SHIFT)
+#define UR            (UR_MASK           << UR_SHIFT)
+#define UW            (UW_MASK           << UW_SHIFT)
+#define XN            (XN_MASK           << XN_SHIFT)
+#define NSDESC        (NSDESC_MASK       << NSDESC_SHIFT)
+#define ISH           (ISH_MASK          << ISH_SHIFT)
+#define SH            (SH_MASK           << SH_SHIFT)
+#define MT            (MT_MASK           << MT_SHIFT)
+#define DPSIZR        (DPSIZR_MASK       << DPSIZR_SHIFT)
+#define DPSIZC        (DPSIZC_MASK       << DPSIZC_SHIFT)
+
+
+/* TLBTR1 */
+#define TLBTR1_VMID   (TLBTR1_VMID_MASK  << TLBTR1_VMID_SHIFT)
+#define TLBTR1_PA     (TLBTR1_PA_MASK    << TLBTR1_PA_SHIFT)
+
+
+/* TLBTR2 */
+#define TLBTR2_ASID   (TLBTR2_ASID_MASK  << TLBTR2_ASID_SHIFT)
+#define TLBTR2_V      (TLBTR2_V_MASK     << TLBTR2_V_SHIFT)
+#define TLBTR2_NSTID  (TLBTR2_NSTID_MASK << TLBTR2_NSTID_SHIFT)
+#define TLBTR2_NV     (TLBTR2_NV_MASK    << TLBTR2_NV_SHIFT)
+#define TLBTR2_VA     (TLBTR2_VA_MASK    << TLBTR2_VA_SHIFT)
+
+
+/* Context Register Fields */
+/* ACTLR */
+#define CFERE              (CFERE_MASK              << CFERE_SHIFT)
+#define CFEIE              (CFEIE_MASK              << CFEIE_SHIFT)
+#define PTSHCFG            (PTSHCFG_MASK            << PTSHCFG_SHIFT)
+#define RCOSH              (RCOSH_MASK              << RCOSH_SHIFT)
+#define RCISH              (RCISH_MASK              << RCISH_SHIFT)
+#define RCNSH              (RCNSH_MASK              << RCNSH_SHIFT)
+#define PRIVCFG            (PRIVCFG_MASK            << PRIVCFG_SHIFT)
+#define DNA                (DNA_MASK                << DNA_SHIFT)
+#define DNLV2PA            (DNLV2PA_MASK            << DNLV2PA_SHIFT)
+#define TLBMCFG            (TLBMCFG_MASK            << TLBMCFG_SHIFT)
+#define CFCFG              (CFCFG_MASK              << CFCFG_SHIFT)
+#define TIPCF              (TIPCF_MASK              << TIPCF_SHIFT)
+#define V2PCFG             (V2PCFG_MASK             << V2PCFG_SHIFT)
+#define HUME               (HUME_MASK               << HUME_SHIFT)
+#define PTMTCFG            (PTMTCFG_MASK            << PTMTCFG_SHIFT)
+#define PTMEMTYPE          (PTMEMTYPE_MASK          << PTMEMTYPE_SHIFT)
+
+
+/* BFBCR */
+#define BFBDFE             (BFBDFE_MASK             << BFBDFE_SHIFT)
+#define BFBSFE             (BFBSFE_MASK             << BFBSFE_SHIFT)
+#define SFVS               (SFVS_MASK               << SFVS_SHIFT)
+#define FLVIC              (FLVIC_MASK              << FLVIC_SHIFT)
+#define SLVIC              (SLVIC_MASK              << SLVIC_SHIFT)
+
+
+/* CONTEXTIDR */
+#define CONTEXTIDR_ASID    (CONTEXTIDR_ASID_MASK    << CONTEXTIDR_ASID_SHIFT)
+#define PROCID             (PROCID_MASK             << PROCID_SHIFT)
+
+
+/* FSR */
+#define TF                 (TF_MASK                 << TF_SHIFT)
+#define AFF                (AFF_MASK                << AFF_SHIFT)
+#define APF                (APF_MASK                << APF_SHIFT)
+#define TLBMF              (TLBMF_MASK              << TLBMF_SHIFT)
+#define HTWDEEF            (HTWDEEF_MASK            << HTWDEEF_SHIFT)
+#define HTWSEEF            (HTWSEEF_MASK            << HTWSEEF_SHIFT)
+#define MHF                (MHF_MASK                << MHF_SHIFT)
+#define SL                 (SL_MASK                 << SL_SHIFT)
+#define SS                 (SS_MASK                 << SS_SHIFT)
+#define MULTI              (MULTI_MASK              << MULTI_SHIFT)
+
+
+/* FSYNR0 */
+#define AMID               (AMID_MASK               << AMID_SHIFT)
+#define APID               (APID_MASK               << APID_SHIFT)
+#define ABID               (ABID_MASK               << ABID_SHIFT)
+#define ATID               (ATID_MASK               << ATID_SHIFT)
+
+
+/* FSYNR1 */
+#define AMEMTYPE           (AMEMTYPE_MASK           << AMEMTYPE_SHIFT)
+#define ASHARED            (ASHARED_MASK            << ASHARED_SHIFT)
+#define AINNERSHARED       (AINNERSHARED_MASK       << AINNERSHARED_SHIFT)
+#define APRIV              (APRIV_MASK              << APRIV_SHIFT)
+#define APROTNS            (APROTNS_MASK            << APROTNS_SHIFT)
+#define AINST              (AINST_MASK              << AINST_SHIFT)
+#define AWRITE             (AWRITE_MASK             << AWRITE_SHIFT)
+#define ABURST             (ABURST_MASK             << ABURST_SHIFT)
+#define ALEN               (ALEN_MASK               << ALEN_SHIFT)
+#define FSYNR1_ASIZE       (FSYNR1_ASIZE_MASK       << FSYNR1_ASIZE_SHIFT)
+#define ALOCK              (ALOCK_MASK              << ALOCK_SHIFT)
+#define AFULL              (AFULL_MASK              << AFULL_SHIFT)
+
+
+/* NMRR */
+#define ICPC0              (ICPC0_MASK              << ICPC0_SHIFT)
+#define ICPC1              (ICPC1_MASK              << ICPC1_SHIFT)
+#define ICPC2              (ICPC2_MASK              << ICPC2_SHIFT)
+#define ICPC3              (ICPC3_MASK              << ICPC3_SHIFT)
+#define ICPC4              (ICPC4_MASK              << ICPC4_SHIFT)
+#define ICPC5              (ICPC5_MASK              << ICPC5_SHIFT)
+#define ICPC6              (ICPC6_MASK              << ICPC6_SHIFT)
+#define ICPC7              (ICPC7_MASK              << ICPC7_SHIFT)
+#define OCPC0              (OCPC0_MASK              << OCPC0_SHIFT)
+#define OCPC1              (OCPC1_MASK              << OCPC1_SHIFT)
+#define OCPC2              (OCPC2_MASK              << OCPC2_SHIFT)
+#define OCPC3              (OCPC3_MASK              << OCPC3_SHIFT)
+#define OCPC4              (OCPC4_MASK              << OCPC4_SHIFT)
+#define OCPC5              (OCPC5_MASK              << OCPC5_SHIFT)
+#define OCPC6              (OCPC6_MASK              << OCPC6_SHIFT)
+#define OCPC7              (OCPC7_MASK              << OCPC7_SHIFT)
+
+
+/* PAR */
+#define FAULT              (FAULT_MASK              << FAULT_SHIFT)
+/* If a fault is present, these are the
+same as the fault fields in the FAR */
+#define FAULT_TF           (FAULT_TF_MASK           << FAULT_TF_SHIFT)
+#define FAULT_AFF          (FAULT_AFF_MASK          << FAULT_AFF_SHIFT)
+#define FAULT_APF          (FAULT_APF_MASK          << FAULT_APF_SHIFT)
+#define FAULT_TLBMF        (FAULT_TLBMF_MASK        << FAULT_TLBMF_SHIFT)
+#define FAULT_HTWDEEF      (FAULT_HTWDEEF_MASK      << FAULT_HTWDEEF_SHIFT)
+#define FAULT_HTWSEEF      (FAULT_HTWSEEF_MASK      << FAULT_HTWSEEF_SHIFT)
+#define FAULT_MHF          (FAULT_MHF_MASK          << FAULT_MHF_SHIFT)
+#define FAULT_SL           (FAULT_SL_MASK           << FAULT_SL_SHIFT)
+#define FAULT_SS           (FAULT_SS_MASK           << FAULT_SS_SHIFT)
+
+/* If NO fault is present, the following fields are in effect */
+/* (FAULT remains as before) */
+#define PAR_NOFAULT_SS     (PAR_NOFAULT_SS_MASK     << PAR_NOFAULT_SS_SHIFT)
+#define PAR_NOFAULT_MT     (PAR_NOFAULT_MT_MASK     << PAR_NOFAULT_MT_SHIFT)
+#define PAR_NOFAULT_SH     (PAR_NOFAULT_SH_MASK     << PAR_NOFAULT_SH_SHIFT)
+#define PAR_NOFAULT_NS     (PAR_NOFAULT_NS_MASK     << PAR_NOFAULT_NS_SHIFT)
+#define PAR_NOFAULT_NOS    (PAR_NOFAULT_NOS_MASK    << PAR_NOFAULT_NOS_SHIFT)
+#define PAR_NPFAULT_PA     (PAR_NPFAULT_PA_MASK     << PAR_NPFAULT_PA_SHIFT)
+
+
+/* PRRR */
+#define MTC0               (MTC0_MASK               << MTC0_SHIFT)
+#define MTC1               (MTC1_MASK               << MTC1_SHIFT)
+#define MTC2               (MTC2_MASK               << MTC2_SHIFT)
+#define MTC3               (MTC3_MASK               << MTC3_SHIFT)
+#define MTC4               (MTC4_MASK               << MTC4_SHIFT)
+#define MTC5               (MTC5_MASK               << MTC5_SHIFT)
+#define MTC6               (MTC6_MASK               << MTC6_SHIFT)
+#define MTC7               (MTC7_MASK               << MTC7_SHIFT)
+#define SHDSH0             (SHDSH0_MASK             << SHDSH0_SHIFT)
+#define SHDSH1             (SHDSH1_MASK             << SHDSH1_SHIFT)
+#define SHNMSH0            (SHNMSH0_MASK            << SHNMSH0_SHIFT)
+#define SHNMSH1            (SHNMSH1_MASK            << SHNMSH1_SHIFT)
+#define NOS0               (NOS0_MASK               << NOS0_SHIFT)
+#define NOS1               (NOS1_MASK               << NOS1_SHIFT)
+#define NOS2               (NOS2_MASK               << NOS2_SHIFT)
+#define NOS3               (NOS3_MASK               << NOS3_SHIFT)
+#define NOS4               (NOS4_MASK               << NOS4_SHIFT)
+#define NOS5               (NOS5_MASK               << NOS5_SHIFT)
+#define NOS6               (NOS6_MASK               << NOS6_SHIFT)
+#define NOS7               (NOS7_MASK               << NOS7_SHIFT)
+
+
+/* RESUME */
+#define TNR                (TNR_MASK                << TNR_SHIFT)
+
+
+/* SCTLR */
+#define M                  (M_MASK                  << M_SHIFT)
+#define TRE                (TRE_MASK                << TRE_SHIFT)
+#define AFE                (AFE_MASK                << AFE_SHIFT)
+#define HAF                (HAF_MASK                << HAF_SHIFT)
+#define BE                 (BE_MASK                 << BE_SHIFT)
+#define AFFD               (AFFD_MASK               << AFFD_SHIFT)
+
+
+/* TLBIASID */
+#define TLBIASID_ASID      (TLBIASID_ASID_MASK      << TLBIASID_ASID_SHIFT)
+
+
+/* TLBIVA */
+#define TLBIVA_ASID        (TLBIVA_ASID_MASK        << TLBIVA_ASID_SHIFT)
+#define TLBIVA_VA          (TLBIVA_VA_MASK          << TLBIVA_VA_SHIFT)
+
+
+/* TLBIVAA */
+#define TLBIVAA_VA         (TLBIVAA_VA_MASK         << TLBIVAA_VA_SHIFT)
+
+
+/* TLBLCKR */
+#define LKE                (LKE_MASK                << LKE_SHIFT)
+#define TLBLCKR_TLBIALLCFG (TLBLCKR_TLBIALLCFG_MASK<<TLBLCKR_TLBIALLCFG_SHIFT)
+#define TLBIASIDCFG        (TLBIASIDCFG_MASK        << TLBIASIDCFG_SHIFT)
+#define TLBIVAACFG         (TLBIVAACFG_MASK         << TLBIVAACFG_SHIFT)
+#define FLOOR              (FLOOR_MASK              << FLOOR_SHIFT)
+#define VICTIM             (VICTIM_MASK             << VICTIM_SHIFT)
+
+
+/* TTBCR */
+#define N                  (N_MASK                  << N_SHIFT)
+#define PD0                (PD0_MASK                << PD0_SHIFT)
+#define PD1                (PD1_MASK                << PD1_SHIFT)
+
+
+/* TTBR0 */
+#define TTBR0_IRGNH        (TTBR0_IRGNH_MASK        << TTBR0_IRGNH_SHIFT)
+#define TTBR0_SH           (TTBR0_SH_MASK           << TTBR0_SH_SHIFT)
+#define TTBR0_ORGN         (TTBR0_ORGN_MASK         << TTBR0_ORGN_SHIFT)
+#define TTBR0_NOS          (TTBR0_NOS_MASK          << TTBR0_NOS_SHIFT)
+#define TTBR0_IRGNL        (TTBR0_IRGNL_MASK        << TTBR0_IRGNL_SHIFT)
+#define TTBR0_PA           (TTBR0_PA_MASK           << TTBR0_PA_SHIFT)
+
+
+/* TTBR1 */
+#define TTBR1_IRGNH        (TTBR1_IRGNH_MASK        << TTBR1_IRGNH_SHIFT)
+#define TTBR1_SH           (TTBR1_SH_MASK           << TTBR1_SH_SHIFT)
+#define TTBR1_ORGN         (TTBR1_ORGN_MASK         << TTBR1_ORGN_SHIFT)
+#define TTBR1_NOS          (TTBR1_NOS_MASK          << TTBR1_NOS_SHIFT)
+#define TTBR1_IRGNL        (TTBR1_IRGNL_MASK        << TTBR1_IRGNL_SHIFT)
+#define TTBR1_PA           (TTBR1_PA_MASK           << TTBR1_PA_SHIFT)
+
+
+/* V2PSR */
+#define HIT                (HIT_MASK                << HIT_SHIFT)
+#define INDEX              (INDEX_MASK              << INDEX_SHIFT)
+
+
+/* V2Pxx */
+#define V2Pxx_INDEX        (V2Pxx_INDEX_MASK        << V2Pxx_INDEX_SHIFT)
+#define V2Pxx_VA           (V2Pxx_VA_MASK           << V2Pxx_VA_SHIFT)
+
+
+/* Global Register Masks */
+/* CBACRn */
+#define RWVMID_MASK               0x1F
+#define RWE_MASK                  0x01
+#define RWGE_MASK                 0x01
+#define CBVMID_MASK               0x1F
+#define IRPTNDX_MASK              0xFF
+
+
+/* CR */
+#define RPUE_MASK                 0x01
+#define RPUERE_MASK               0x01
+#define RPUEIE_MASK               0x01
+#define DCDEE_MASK                0x01
+#define CLIENTPD_MASK             0x01
+#define STALLD_MASK               0x01
+#define TLBLKCRWE_MASK            0x01
+#define CR_TLBIALLCFG_MASK        0x01
+#define TLBIVMIDCFG_MASK          0x01
+#define CR_HUME_MASK              0x01
+
+
+/* ESR */
+#define CFG_MASK                  0x01
+#define BYPASS_MASK               0x01
+#define ESR_MULTI_MASK            0x01
+
+
+/* ESYNR0 */
+#define ESYNR0_AMID_MASK          0xFF
+#define ESYNR0_APID_MASK          0x1F
+#define ESYNR0_ABID_MASK          0x07
+#define ESYNR0_AVMID_MASK         0x1F
+#define ESYNR0_ATID_MASK          0xFF
+
+
+/* ESYNR1 */
+#define ESYNR1_AMEMTYPE_MASK             0x07
+#define ESYNR1_ASHARED_MASK              0x01
+#define ESYNR1_AINNERSHARED_MASK         0x01
+#define ESYNR1_APRIV_MASK                0x01
+#define ESYNR1_APROTNS_MASK              0x01
+#define ESYNR1_AINST_MASK                0x01
+#define ESYNR1_AWRITE_MASK               0x01
+#define ESYNR1_ABURST_MASK               0x01
+#define ESYNR1_ALEN_MASK                 0x0F
+#define ESYNR1_ASIZE_MASK                0x01
+#define ESYNR1_ALOCK_MASK                0x03
+#define ESYNR1_AOOO_MASK                 0x01
+#define ESYNR1_AFULL_MASK                0x01
+#define ESYNR1_AC_MASK                   0x01
+#define ESYNR1_DCD_MASK                  0x01
+
+
+/* IDR */
+#define NM2VCBMT_MASK             0x1FF
+#define HTW_MASK                  0x01
+#define HUM_MASK                  0x01
+#define TLBSIZE_MASK              0x0F
+#define NCB_MASK                  0xFF
+#define NIRPT_MASK                0xFF
+
+
+/* M2VCBRn */
+#define VMID_MASK                 0x1F
+#define CBNDX_MASK                0xFF
+#define BYPASSD_MASK              0x01
+#define BPRCOSH_MASK              0x01
+#define BPRCISH_MASK              0x01
+#define BPRCNSH_MASK              0x01
+#define BPSHCFG_MASK              0x03
+#define NSCFG_MASK                0x03
+#define BPMTCFG_MASK              0x01
+#define BPMEMTYPE_MASK            0x07
+
+
+/* REV */
+#define MINOR_MASK                0x0F
+#define MAJOR_MASK                0x0F
+
+
+/* TESTBUSCR */
+#define TBE_MASK                  0x01
+#define SPDMBE_MASK               0x01
+#define WGSEL_MASK                0x03
+#define TBLSEL_MASK               0x03
+#define TBHSEL_MASK               0x03
+#define SPDM0SEL_MASK             0x0F
+#define SPDM1SEL_MASK             0x0F
+#define SPDM2SEL_MASK             0x0F
+#define SPDM3SEL_MASK             0x0F
+
+
+/* TLBIMID */
+#define TLBIVMID_VMID_MASK        0x1F
+
+
+/* TLBRSW */
+#define TLBRSW_INDEX_MASK         0xFF
+#define TLBBFBS_MASK              0x03
+
+
+/* TLBTR0 */
+#define PR_MASK                   0x01
+#define PW_MASK                   0x01
+#define UR_MASK                   0x01
+#define UW_MASK                   0x01
+#define XN_MASK                   0x01
+#define NSDESC_MASK               0x01
+#define ISH_MASK                  0x01
+#define SH_MASK                   0x01
+#define MT_MASK                   0x07
+#define DPSIZR_MASK               0x07
+#define DPSIZC_MASK               0x07
+
+
+/* TLBTR1 */
+#define TLBTR1_VMID_MASK          0x1F
+#define TLBTR1_PA_MASK            0x000FFFFF
+
+
+/* TLBTR2 */
+#define TLBTR2_ASID_MASK          0xFF
+#define TLBTR2_V_MASK             0x01
+#define TLBTR2_NSTID_MASK         0x01
+#define TLBTR2_NV_MASK            0x01
+#define TLBTR2_VA_MASK            0x000FFFFF
+
+
+/* Global Register Shifts */
+/* CBACRn */
+#define RWVMID_SHIFT             0
+#define RWE_SHIFT                8
+#define RWGE_SHIFT               9
+#define CBVMID_SHIFT             16
+#define IRPTNDX_SHIFT            24
+
+
+/* CR */
+#define RPUE_SHIFT               0
+#define RPUERE_SHIFT             1
+#define RPUEIE_SHIFT             2
+#define DCDEE_SHIFT              3
+#define CLIENTPD_SHIFT           4
+#define STALLD_SHIFT             5
+#define TLBLKCRWE_SHIFT          6
+#define CR_TLBIALLCFG_SHIFT      7
+#define TLBIVMIDCFG_SHIFT        8
+#define CR_HUME_SHIFT            9
+
+
+/* ESR */
+#define CFG_SHIFT                0
+#define BYPASS_SHIFT             1
+#define ESR_MULTI_SHIFT          31
+
+
+/* ESYNR0 */
+#define ESYNR0_AMID_SHIFT        0
+#define ESYNR0_APID_SHIFT        8
+#define ESYNR0_ABID_SHIFT        13
+#define ESYNR0_AVMID_SHIFT       16
+#define ESYNR0_ATID_SHIFT        24
+
+
+/* ESYNR1 */
+#define ESYNR1_AMEMTYPE_SHIFT           0
+#define ESYNR1_ASHARED_SHIFT            3
+#define ESYNR1_AINNERSHARED_SHIFT       4
+#define ESYNR1_APRIV_SHIFT              5
+#define ESYNR1_APROTNS_SHIFT            6
+#define ESYNR1_AINST_SHIFT              7
+#define ESYNR1_AWRITE_SHIFT             8
+#define ESYNR1_ABURST_SHIFT             10
+#define ESYNR1_ALEN_SHIFT               12
+#define ESYNR1_ASIZE_SHIFT              16
+#define ESYNR1_ALOCK_SHIFT              20
+#define ESYNR1_AOOO_SHIFT               22
+#define ESYNR1_AFULL_SHIFT              24
+#define ESYNR1_AC_SHIFT                 30
+#define ESYNR1_DCD_SHIFT                31
+
+
+/* IDR */
+#define NM2VCBMT_SHIFT           0
+#define HTW_SHIFT                9
+#define HUM_SHIFT                10
+#define TLBSIZE_SHIFT            12
+#define NCB_SHIFT                16
+#define NIRPT_SHIFT              24
+
+
+/* M2VCBRn */
+#define VMID_SHIFT               0
+#define CBNDX_SHIFT              8
+#define BYPASSD_SHIFT            16
+#define BPRCOSH_SHIFT            17
+#define BPRCISH_SHIFT            18
+#define BPRCNSH_SHIFT            19
+#define BPSHCFG_SHIFT            20
+#define NSCFG_SHIFT              22
+#define BPMTCFG_SHIFT            24
+#define BPMEMTYPE_SHIFT          25
+
+
+/* REV */
+#define MINOR_SHIFT              0
+#define MAJOR_SHIFT              4
+
+
+/* TESTBUSCR */
+#define TBE_SHIFT                0
+#define SPDMBE_SHIFT             1
+#define WGSEL_SHIFT              8
+#define TBLSEL_SHIFT             12
+#define TBHSEL_SHIFT             14
+#define SPDM0SEL_SHIFT           16
+#define SPDM1SEL_SHIFT           20
+#define SPDM2SEL_SHIFT           24
+#define SPDM3SEL_SHIFT           28
+
+
+/* TLBIMID */
+#define TLBIVMID_VMID_SHIFT      0
+
+
+/* TLBRSW */
+#define TLBRSW_INDEX_SHIFT       0
+#define TLBBFBS_SHIFT            8
+
+
+/* TLBTR0 */
+#define PR_SHIFT                 0
+#define PW_SHIFT                 1
+#define UR_SHIFT                 2
+#define UW_SHIFT                 3
+#define XN_SHIFT                 4
+#define NSDESC_SHIFT             6
+#define ISH_SHIFT                7
+#define SH_SHIFT                 8
+#define MT_SHIFT                 9
+#define DPSIZR_SHIFT             16
+#define DPSIZC_SHIFT             20
+
+
+/* TLBTR1 */
+#define TLBTR1_VMID_SHIFT        0
+#define TLBTR1_PA_SHIFT          12
+
+
+/* TLBTR2 */
+#define TLBTR2_ASID_SHIFT        0
+#define TLBTR2_V_SHIFT           8
+#define TLBTR2_NSTID_SHIFT       9
+#define TLBTR2_NV_SHIFT          10
+#define TLBTR2_VA_SHIFT          12
+
+
+/* Context Register Masks */
+/* ACTLR */
+#define CFERE_MASK                       0x01
+#define CFEIE_MASK                       0x01
+#define PTSHCFG_MASK                     0x03
+#define RCOSH_MASK                       0x01
+#define RCISH_MASK                       0x01
+#define RCNSH_MASK                       0x01
+#define PRIVCFG_MASK                     0x03
+#define DNA_MASK                         0x01
+#define DNLV2PA_MASK                     0x01
+#define TLBMCFG_MASK                     0x03
+#define CFCFG_MASK                       0x01
+#define TIPCF_MASK                       0x01
+#define V2PCFG_MASK                      0x03
+#define HUME_MASK                        0x01
+#define PTMTCFG_MASK                     0x01
+#define PTMEMTYPE_MASK                   0x07
+
+
+/* BFBCR */
+#define BFBDFE_MASK                      0x01
+#define BFBSFE_MASK                      0x01
+#define SFVS_MASK                        0x01
+#define FLVIC_MASK                       0x0F
+#define SLVIC_MASK                       0x0F
+
+
+/* CONTEXTIDR */
+#define CONTEXTIDR_ASID_MASK             0xFF
+#define PROCID_MASK                      0x00FFFFFF
+
+
+/* FSR */
+#define TF_MASK                          0x01
+#define AFF_MASK                         0x01
+#define APF_MASK                         0x01
+#define TLBMF_MASK                       0x01
+#define HTWDEEF_MASK                     0x01
+#define HTWSEEF_MASK                     0x01
+#define MHF_MASK                         0x01
+#define SL_MASK                          0x01
+#define SS_MASK                          0x01
+#define MULTI_MASK                       0x01
+
+
+/* FSYNR0 */
+#define AMID_MASK                        0xFF
+#define APID_MASK                        0x1F
+#define ABID_MASK                        0x07
+#define ATID_MASK                        0xFF
+
+
+/* FSYNR1 */
+#define AMEMTYPE_MASK                    0x07
+#define ASHARED_MASK                     0x01
+#define AINNERSHARED_MASK                0x01
+#define APRIV_MASK                       0x01
+#define APROTNS_MASK                     0x01
+#define AINST_MASK                       0x01
+#define AWRITE_MASK                      0x01
+#define ABURST_MASK                      0x01
+#define ALEN_MASK                        0x0F
+#define FSYNR1_ASIZE_MASK                0x07
+#define ALOCK_MASK                       0x03
+#define AFULL_MASK                       0x01
+
+
+/* NMRR */
+#define ICPC0_MASK                       0x03
+#define ICPC1_MASK                       0x03
+#define ICPC2_MASK                       0x03
+#define ICPC3_MASK                       0x03
+#define ICPC4_MASK                       0x03
+#define ICPC5_MASK                       0x03
+#define ICPC6_MASK                       0x03
+#define ICPC7_MASK                       0x03
+#define OCPC0_MASK                       0x03
+#define OCPC1_MASK                       0x03
+#define OCPC2_MASK                       0x03
+#define OCPC3_MASK                       0x03
+#define OCPC4_MASK                       0x03
+#define OCPC5_MASK                       0x03
+#define OCPC6_MASK                       0x03
+#define OCPC7_MASK                       0x03
+
+
+/* PAR */
+#define FAULT_MASK                       0x01
+/* If a fault is present, these are the
+same as the fault fields in the FAR */
+#define FAULT_TF_MASK                    0x01
+#define FAULT_AFF_MASK                   0x01
+#define FAULT_APF_MASK                   0x01
+#define FAULT_TLBMF_MASK                 0x01
+#define FAULT_HTWDEEF_MASK               0x01
+#define FAULT_HTWSEEF_MASK               0x01
+#define FAULT_MHF_MASK                   0x01
+#define FAULT_SL_MASK                    0x01
+#define FAULT_SS_MASK                    0x01
+
+/* If NO fault is present, the following
+ * fields are in effect
+ * (FAULT remains as before) */
+#define PAR_NOFAULT_SS_MASK              0x01
+#define PAR_NOFAULT_MT_MASK              0x07
+#define PAR_NOFAULT_SH_MASK              0x01
+#define PAR_NOFAULT_NS_MASK              0x01
+#define PAR_NOFAULT_NOS_MASK             0x01
+#define PAR_NPFAULT_PA_MASK              0x000FFFFF
+
+
+/* PRRR */
+#define MTC0_MASK                        0x03
+#define MTC1_MASK                        0x03
+#define MTC2_MASK                        0x03
+#define MTC3_MASK                        0x03
+#define MTC4_MASK                        0x03
+#define MTC5_MASK                        0x03
+#define MTC6_MASK                        0x03
+#define MTC7_MASK                        0x03
+#define SHDSH0_MASK                      0x01
+#define SHDSH1_MASK                      0x01
+#define SHNMSH0_MASK                     0x01
+#define SHNMSH1_MASK                     0x01
+#define NOS0_MASK                        0x01
+#define NOS1_MASK                        0x01
+#define NOS2_MASK                        0x01
+#define NOS3_MASK                        0x01
+#define NOS4_MASK                        0x01
+#define NOS5_MASK                        0x01
+#define NOS6_MASK                        0x01
+#define NOS7_MASK                        0x01
+
+
+/* RESUME */
+#define TNR_MASK                         0x01
+
+
+/* SCTLR */
+#define M_MASK                           0x01
+#define TRE_MASK                         0x01
+#define AFE_MASK                         0x01
+#define HAF_MASK                         0x01
+#define BE_MASK                          0x01
+#define AFFD_MASK                        0x01
+
+
+/* TLBIASID */
+#define TLBIASID_ASID_MASK               0xFF
+
+
+/* TLBIVA */
+#define TLBIVA_ASID_MASK                 0xFF
+#define TLBIVA_VA_MASK                   0x000FFFFF
+
+
+/* TLBIVAA */
+#define TLBIVAA_VA_MASK                  0x000FFFFF
+
+
+/* TLBLCKR */
+#define LKE_MASK                         0x01
+#define TLBLCKR_TLBIALLCFG_MASK          0x01
+#define TLBIASIDCFG_MASK                 0x01
+#define TLBIVAACFG_MASK                  0x01
+#define FLOOR_MASK                       0xFF
+#define VICTIM_MASK                      0xFF
+
+
+/* TTBCR */
+#define N_MASK                           0x07
+#define PD0_MASK                         0x01
+#define PD1_MASK                         0x01
+
+
+/* TTBR0 */
+#define TTBR0_IRGNH_MASK                 0x01
+#define TTBR0_SH_MASK                    0x01
+#define TTBR0_ORGN_MASK                  0x03
+#define TTBR0_NOS_MASK                   0x01
+#define TTBR0_IRGNL_MASK                 0x01
+#define TTBR0_PA_MASK                    0x0003FFFF
+
+
+/* TTBR1 */
+#define TTBR1_IRGNH_MASK                 0x01
+#define TTBR1_SH_MASK                    0x01
+#define TTBR1_ORGN_MASK                  0x03
+#define TTBR1_NOS_MASK                   0x01
+#define TTBR1_IRGNL_MASK                 0x01
+#define TTBR1_PA_MASK                    0x0003FFFF
+
+
+/* V2PSR */
+#define HIT_MASK                         0x01
+#define INDEX_MASK                       0xFF
+
+
+/* V2Pxx */
+#define V2Pxx_INDEX_MASK                 0xFF
+#define V2Pxx_VA_MASK                    0x000FFFFF
+
+
+/* Context Register Shifts */
+/* ACTLR */
+#define CFERE_SHIFT                    0
+#define CFEIE_SHIFT                    1
+#define PTSHCFG_SHIFT                  2
+#define RCOSH_SHIFT                    4
+#define RCISH_SHIFT                    5
+#define RCNSH_SHIFT                    6
+#define PRIVCFG_SHIFT                  8
+#define DNA_SHIFT                      10
+#define DNLV2PA_SHIFT                  11
+#define TLBMCFG_SHIFT                  12
+#define CFCFG_SHIFT                    14
+#define TIPCF_SHIFT                    15
+#define V2PCFG_SHIFT                   16
+#define HUME_SHIFT                     18
+#define PTMTCFG_SHIFT                  20
+#define PTMEMTYPE_SHIFT                21
+
+
+/* BFBCR */
+#define BFBDFE_SHIFT                   0
+#define BFBSFE_SHIFT                   1
+#define SFVS_SHIFT                     2
+#define FLVIC_SHIFT                    4
+#define SLVIC_SHIFT                    8
+
+
+/* CONTEXTIDR */
+#define CONTEXTIDR_ASID_SHIFT          0
+#define PROCID_SHIFT                   8
+
+
+/* FSR */
+#define TF_SHIFT                       1
+#define AFF_SHIFT                      2
+#define APF_SHIFT                      3
+#define TLBMF_SHIFT                    4
+#define HTWDEEF_SHIFT                  5
+#define HTWSEEF_SHIFT                  6
+#define MHF_SHIFT                      7
+#define SL_SHIFT                       16
+#define SS_SHIFT                       30
+#define MULTI_SHIFT                    31
+
+
+/* FSYNR0 */
+#define AMID_SHIFT                     0
+#define APID_SHIFT                     8
+#define ABID_SHIFT                     13
+#define ATID_SHIFT                     24
+
+
+/* FSYNR1 */
+#define AMEMTYPE_SHIFT                 0
+#define ASHARED_SHIFT                  3
+#define AINNERSHARED_SHIFT             4
+#define APRIV_SHIFT                    5
+#define APROTNS_SHIFT                  6
+#define AINST_SHIFT                    7
+#define AWRITE_SHIFT                   8
+#define ABURST_SHIFT                   10
+#define ALEN_SHIFT                     12
+#define FSYNR1_ASIZE_SHIFT             16
+#define ALOCK_SHIFT                    20
+#define AFULL_SHIFT                    24
+
+
+/* NMRR */
+#define ICPC0_SHIFT                    0
+#define ICPC1_SHIFT                    2
+#define ICPC2_SHIFT                    4
+#define ICPC3_SHIFT                    6
+#define ICPC4_SHIFT                    8
+#define ICPC5_SHIFT                    10
+#define ICPC6_SHIFT                    12
+#define ICPC7_SHIFT                    14
+#define OCPC0_SHIFT                    16
+#define OCPC1_SHIFT                    18
+#define OCPC2_SHIFT                    20
+#define OCPC3_SHIFT                    22
+#define OCPC4_SHIFT                    24
+#define OCPC5_SHIFT                    26
+#define OCPC6_SHIFT                    28
+#define OCPC7_SHIFT                    30
+
+
+/* PAR */
+#define FAULT_SHIFT                    0
+/* If a fault is present, these are the
+same as the fault fields in the FAR */
+#define FAULT_TF_SHIFT                 1
+#define FAULT_AFF_SHIFT                2
+#define FAULT_APF_SHIFT                3
+#define FAULT_TLBMF_SHIFT              4
+#define FAULT_HTWDEEF_SHIFT            5
+#define FAULT_HTWSEEF_SHIFT            6
+#define FAULT_MHF_SHIFT                7
+#define FAULT_SL_SHIFT                 16
+#define FAULT_SS_SHIFT                 30
+
+/* If NO fault is present, the following
+ * fields are in effect
+ * (FAULT remains as before) */
+#define PAR_NOFAULT_SS_SHIFT           1
+#define PAR_NOFAULT_MT_SHIFT           4
+#define PAR_NOFAULT_SH_SHIFT           7
+#define PAR_NOFAULT_NS_SHIFT           9
+#define PAR_NOFAULT_NOS_SHIFT          10
+#define PAR_NPFAULT_PA_SHIFT           12
+
+
+/* PRRR */
+#define MTC0_SHIFT                     0
+#define MTC1_SHIFT                     2
+#define MTC2_SHIFT                     4
+#define MTC3_SHIFT                     6
+#define MTC4_SHIFT                     8
+#define MTC5_SHIFT                     10
+#define MTC6_SHIFT                     12
+#define MTC7_SHIFT                     14
+#define SHDSH0_SHIFT                   16
+#define SHDSH1_SHIFT                   17
+#define SHNMSH0_SHIFT                  18
+#define SHNMSH1_SHIFT                  19
+#define NOS0_SHIFT                     24
+#define NOS1_SHIFT                     25
+#define NOS2_SHIFT                     26
+#define NOS3_SHIFT                     27
+#define NOS4_SHIFT                     28
+#define NOS5_SHIFT                     29
+#define NOS6_SHIFT                     30
+#define NOS7_SHIFT                     31
+
+
+/* RESUME */
+#define TNR_SHIFT                      0
+
+
+/* SCTLR */
+#define M_SHIFT                        0
+#define TRE_SHIFT                      1
+#define AFE_SHIFT                      2
+#define HAF_SHIFT                      3
+#define BE_SHIFT                       4
+#define AFFD_SHIFT                     5
+
+
+/* TLBIASID */
+#define TLBIASID_ASID_SHIFT            0
+
+
+/* TLBIVA */
+#define TLBIVA_ASID_SHIFT              0
+#define TLBIVA_VA_SHIFT                12
+
+
+/* TLBIVAA */
+#define TLBIVAA_VA_SHIFT               12
+
+
+/* TLBLCKR */
+#define LKE_SHIFT                      0
+#define TLBLCKR_TLBIALLCFG_SHIFT       1
+#define TLBIASIDCFG_SHIFT              2
+#define TLBIVAACFG_SHIFT               3
+#define FLOOR_SHIFT                    8
+#define VICTIM_SHIFT                   8
+
+
+/* TTBCR */
+#define N_SHIFT                        3
+#define PD0_SHIFT                      4
+#define PD1_SHIFT                      5
+
+
+/* TTBR0 */
+#define TTBR0_IRGNH_SHIFT              0
+#define TTBR0_SH_SHIFT                 1
+#define TTBR0_ORGN_SHIFT               3
+#define TTBR0_NOS_SHIFT                5
+#define TTBR0_IRGNL_SHIFT              6
+#define TTBR0_PA_SHIFT                 14
+
+
+/* TTBR1 */
+#define TTBR1_IRGNH_SHIFT              0
+#define TTBR1_SH_SHIFT                 1
+#define TTBR1_ORGN_SHIFT               3
+#define TTBR1_NOS_SHIFT                5
+#define TTBR1_IRGNL_SHIFT              6
+#define TTBR1_PA_SHIFT                 14
+
+
+/* V2PSR */
+#define HIT_SHIFT                      0
+#define INDEX_SHIFT                    8
+
+
+/* V2Pxx */
+#define V2Pxx_INDEX_SHIFT              0
+#define V2Pxx_VA_SHIFT                 12
+
+#endif
diff --git a/arch/arm/mach-msm/include/mach/irqs-8x60.h b/arch/arm/mach-msm/include/mach/irqs-8x60.h
new file mode 100644
index 0000000..36074cf
--- /dev/null
+++ b/arch/arm/mach-msm/include/mach/irqs-8x60.h
@@ -0,0 +1,253 @@
+/* Copyright (c) 2010 Code Aurora Forum. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __ASM_ARCH_MSM_IRQS_8X60_H
+#define __ASM_ARCH_MSM_IRQS_8X60_H
+
+/* MSM ACPU Interrupt Numbers */
+
+/* 0-15:  STI/SGI (software triggered/generated interrupts)
+ * 16-31: PPI (private peripheral interrupts)
+ * 32+:   SPI (shared peripheral interrupts)
+ */
+
+#define GIC_PPI_START 16
+#define GIC_SPI_START 32
+
+#define INT_DEBUG_TIMER_EXP			(GIC_PPI_START + 0)
+#define INT_GP_TIMER_EXP			(GIC_PPI_START + 1)
+#define INT_GP_TIMER2_EXP			(GIC_PPI_START + 2)
+#define WDT0_ACCSCSSNBARK_INT			(GIC_PPI_START + 3)
+#define WDT1_ACCSCSSNBARK_INT			(GIC_PPI_START + 4)
+#define AVS_SVICINT				(GIC_PPI_START + 5)
+#define AVS_SVICINTSWDONE			(GIC_PPI_START + 6)
+#define CPU_DBGCPUXCOMMRXFULL			(GIC_PPI_START + 7)
+#define CPU_DBGCPUXCOMMTXEMPTY			(GIC_PPI_START + 8)
+#define CPU_SICCPUXPERFMONIRPTREQ		(GIC_PPI_START + 9)
+#define SC_AVSCPUXDOWN				(GIC_PPI_START + 10)
+#define SC_AVSCPUXUP				(GIC_PPI_START + 11)
+#define SC_SICCPUXACGIRPTREQ			(GIC_PPI_START + 12)
+/* PPI 13 to 15 are unused */
+
+
+#define SC_SICMPUIRPTREQ			(GIC_SPI_START + 0)
+#define SC_SICL2IRPTREQ				(GIC_SPI_START + 1)
+#define SC_SICL2ACGIRPTREQ			(GIC_SPI_START + 2)
+#define NC					(GIC_SPI_START + 3)
+#define TLMM_SCSS_DIR_CONN_IRQ_0		(GIC_SPI_START + 4)
+#define TLMM_SCSS_DIR_CONN_IRQ_1		(GIC_SPI_START + 5)
+#define TLMM_SCSS_DIR_CONN_IRQ_2		(GIC_SPI_START + 6)
+#define TLMM_SCSS_DIR_CONN_IRQ_3		(GIC_SPI_START + 7)
+#define TLMM_SCSS_DIR_CONN_IRQ_4		(GIC_SPI_START + 8)
+#define TLMM_SCSS_DIR_CONN_IRQ_5		(GIC_SPI_START + 9)
+#define TLMM_SCSS_DIR_CONN_IRQ_6		(GIC_SPI_START + 10)
+#define TLMM_SCSS_DIR_CONN_IRQ_7		(GIC_SPI_START + 11)
+#define TLMM_SCSS_DIR_CONN_IRQ_8		(GIC_SPI_START + 12)
+#define TLMM_SCSS_DIR_CONN_IRQ_9		(GIC_SPI_START + 13)
+#define PM8058_SEC_IRQ_N			(GIC_SPI_START + 14)
+#define PM8901_SEC_IRQ_N			(GIC_SPI_START + 15)
+#define TLMM_SCSS_SUMMARY_IRQ			(GIC_SPI_START + 16)
+#define SPDM_RT_1_IRQ				(GIC_SPI_START + 17)
+#define SPDM_DIAG_IRQ				(GIC_SPI_START + 18)
+#define RPM_SCSS_CPU0_GP_HIGH_IRQ		(GIC_SPI_START + 19)
+#define RPM_SCSS_CPU0_GP_MEDIUM_IRQ		(GIC_SPI_START + 20)
+#define RPM_SCSS_CPU0_GP_LOW_IRQ		(GIC_SPI_START + 21)
+#define RPM_SCSS_CPU0_WAKE_UP_IRQ		(GIC_SPI_START + 22)
+#define RPM_SCSS_CPU1_GP_HIGH_IRQ		(GIC_SPI_START + 23)
+#define RPM_SCSS_CPU1_GP_MEDIUM_IRQ		(GIC_SPI_START + 24)
+#define RPM_SCSS_CPU1_GP_LOW_IRQ		(GIC_SPI_START + 25)
+#define RPM_SCSS_CPU1_WAKE_UP_IRQ		(GIC_SPI_START + 26)
+#define SSBI2_2_SC_CPU0_SECURE_INT		(GIC_SPI_START + 27)
+#define SSBI2_2_SC_CPU0_NON_SECURE_INT		(GIC_SPI_START + 28)
+#define SSBI2_1_SC_CPU0_SECURE_INT		(GIC_SPI_START + 29)
+#define SSBI2_1_SC_CPU0_NON_SECURE_INT		(GIC_SPI_START + 30)
+#define MSMC_SC_SEC_CE_IRQ			(GIC_SPI_START + 31)
+#define MSMC_SC_PRI_CE_IRQ			(GIC_SPI_START + 32)
+#define MARM_FIQ				(GIC_SPI_START + 33)
+#define MARM_IRQ				(GIC_SPI_START + 34)
+#define MARM_L2CC_IRQ				(GIC_SPI_START + 35)
+#define MARM_WDOG_EXPIRED			(GIC_SPI_START + 36)
+#define MARM_SCSS_GP_IRQ_0			(GIC_SPI_START + 37)
+#define MARM_SCSS_GP_IRQ_1			(GIC_SPI_START + 38)
+#define MARM_SCSS_GP_IRQ_2			(GIC_SPI_START + 39)
+#define MARM_SCSS_GP_IRQ_3			(GIC_SPI_START + 40)
+#define MARM_SCSS_GP_IRQ_4			(GIC_SPI_START + 41)
+#define MARM_SCSS_GP_IRQ_5			(GIC_SPI_START + 42)
+#define MARM_SCSS_GP_IRQ_6			(GIC_SPI_START + 43)
+#define MARM_SCSS_GP_IRQ_7			(GIC_SPI_START + 44)
+#define MARM_SCSS_GP_IRQ_8			(GIC_SPI_START + 45)
+#define MARM_SCSS_GP_IRQ_9			(GIC_SPI_START + 46)
+#define VPE_IRQ					(GIC_SPI_START + 47)
+#define VFE_IRQ					(GIC_SPI_START + 48)
+#define VCODEC_IRQ				(GIC_SPI_START + 49)
+#define TV_ENC_IRQ				(GIC_SPI_START + 50)
+#define SMMU_VPE_CB_SC_SECURE_IRQ		(GIC_SPI_START + 51)
+#define SMMU_VPE_CB_SC_NON_SECURE_IRQ		(GIC_SPI_START + 52)
+#define SMMU_VFE_CB_SC_SECURE_IRQ		(GIC_SPI_START + 53)
+#define SMMU_VFE_CB_SC_NON_SECURE_IRQ		(GIC_SPI_START + 54)
+#define SMMU_VCODEC_B_CB_SC_SECURE_IRQ		(GIC_SPI_START + 55)
+#define SMMU_VCODEC_B_CB_SC_NON_SECURE_IRQ	(GIC_SPI_START + 56)
+#define SMMU_VCODEC_A_CB_SC_SECURE_IRQ		(GIC_SPI_START + 57)
+#define SMMU_VCODEC_A_CB_SC_NON_SECURE_IRQ	(GIC_SPI_START + 58)
+#define SMMU_ROT_CB_SC_SECURE_IRQ		(GIC_SPI_START + 59)
+#define SMMU_ROT_CB_SC_NON_SECURE_IRQ		(GIC_SPI_START + 60)
+#define SMMU_MDP1_CB_SC_SECURE_IRQ		(GIC_SPI_START + 61)
+#define SMMU_MDP1_CB_SC_NON_SECURE_IRQ		(GIC_SPI_START + 62)
+#define SMMU_MDP0_CB_SC_SECURE_IRQ		(GIC_SPI_START + 63)
+#define SMMU_MDP0_CB_SC_NON_SECURE_IRQ		(GIC_SPI_START + 64)
+#define SMMU_JPEGD_CB_SC_SECURE_IRQ		(GIC_SPI_START + 65)
+#define SMMU_JPEGD_CB_SC_NON_SECURE_IRQ		(GIC_SPI_START + 66)
+#define SMMU_IJPEG_CB_SC_SECURE_IRQ		(GIC_SPI_START + 67)
+#define SMMU_IJPEG_CB_SC_NON_SECURE_IRQ		(GIC_SPI_START + 68)
+#define SMMU_GFX3D_CB_SC_SECURE_IRQ		(GIC_SPI_START + 69)
+#define SMMU_GFX3D_CB_SC_NON_SECURE_IRQ		(GIC_SPI_START + 70)
+#define SMMU_GFX2D0_CB_SC_SECURE_IRQ		(GIC_SPI_START + 71)
+#define SMMU_GFX2D0_CB_SC_NON_SECURE_IRQ	(GIC_SPI_START + 72)
+#define ROT_IRQ					(GIC_SPI_START + 73)
+#define MMSS_FABRIC_IRQ				(GIC_SPI_START + 74)
+#define MDP_IRQ					(GIC_SPI_START + 75)
+#define JPEGD_IRQ				(GIC_SPI_START + 76)
+#define JPEG_IRQ				(GIC_SPI_START + 77)
+#define MMSS_IMEM_IRQ				(GIC_SPI_START + 78)
+#define HDMI_IRQ				(GIC_SPI_START + 79)
+#define GFX3D_IRQ				(GIC_SPI_START + 80)
+#define GFX2D0_IRQ				(GIC_SPI_START + 81)
+#define DSI_IRQ					(GIC_SPI_START + 82)
+#define CSI_1_IRQ				(GIC_SPI_START + 83)
+#define CSI_0_IRQ				(GIC_SPI_START + 84)
+#define LPASS_SCSS_AUDIO_IF_OUT0_IRQ		(GIC_SPI_START + 85)
+#define LPASS_SCSS_MIDI_IRQ			(GIC_SPI_START + 86)
+#define LPASS_Q6SS_WDOG_EXPIRED			(GIC_SPI_START + 87)
+#define LPASS_SCSS_GP_LOW_IRQ			(GIC_SPI_START + 88)
+#define LPASS_SCSS_GP_MEDIUM_IRQ		(GIC_SPI_START + 89)
+#define LPASS_SCSS_GP_HIGH_IRQ			(GIC_SPI_START + 90)
+#define TOP_IMEM_IRQ				(GIC_SPI_START + 91)
+#define FABRIC_SYS_IRQ				(GIC_SPI_START + 92)
+#define FABRIC_APPS_IRQ				(GIC_SPI_START + 93)
+#define USB1_HS_BAM_IRQ				(GIC_SPI_START + 94)
+#define SDC4_BAM_IRQ				(GIC_SPI_START + 95)
+#define SDC3_BAM_IRQ				(GIC_SPI_START + 96)
+#define SDC2_BAM_IRQ				(GIC_SPI_START + 97)
+#define SDC1_BAM_IRQ				(GIC_SPI_START + 98)
+#define FABRIC_SPS_IRQ				(GIC_SPI_START + 99)
+#define USB1_HS_IRQ				(GIC_SPI_START + 100)
+#define SDC4_IRQ_0				(GIC_SPI_START + 101)
+#define SDC3_IRQ_0				(GIC_SPI_START + 102)
+#define SDC2_IRQ_0				(GIC_SPI_START + 103)
+#define SDC1_IRQ_0				(GIC_SPI_START + 104)
+#define SPS_BAM_DMA_IRQ				(GIC_SPI_START + 105)
+#define SPS_SEC_VIOL_IRQ			(GIC_SPI_START + 106)
+#define SPS_MTI_0				(GIC_SPI_START + 107)
+#define SPS_MTI_1				(GIC_SPI_START + 108)
+#define SPS_MTI_2				(GIC_SPI_START + 109)
+#define SPS_MTI_3				(GIC_SPI_START + 110)
+#define SPS_MTI_4				(GIC_SPI_START + 111)
+#define SPS_MTI_5				(GIC_SPI_START + 112)
+#define SPS_MTI_6				(GIC_SPI_START + 113)
+#define SPS_MTI_7				(GIC_SPI_START + 114)
+#define SPS_MTI_8				(GIC_SPI_START + 115)
+#define SPS_MTI_9				(GIC_SPI_START + 116)
+#define SPS_MTI_10				(GIC_SPI_START + 117)
+#define SPS_MTI_11				(GIC_SPI_START + 118)
+#define SPS_MTI_12				(GIC_SPI_START + 119)
+#define SPS_MTI_13				(GIC_SPI_START + 120)
+#define SPS_MTI_14				(GIC_SPI_START + 121)
+#define SPS_MTI_15				(GIC_SPI_START + 122)
+#define SPS_MTI_16				(GIC_SPI_START + 123)
+#define SPS_MTI_17				(GIC_SPI_START + 124)
+#define SPS_MTI_18				(GIC_SPI_START + 125)
+#define SPS_MTI_19				(GIC_SPI_START + 126)
+#define SPS_MTI_20				(GIC_SPI_START + 127)
+#define SPS_MTI_21				(GIC_SPI_START + 128)
+#define SPS_MTI_22				(GIC_SPI_START + 129)
+#define SPS_MTI_23				(GIC_SPI_START + 130)
+#define SPS_MTI_24				(GIC_SPI_START + 131)
+#define SPS_MTI_25				(GIC_SPI_START + 132)
+#define SPS_MTI_26				(GIC_SPI_START + 133)
+#define SPS_MTI_27				(GIC_SPI_START + 134)
+#define SPS_MTI_28				(GIC_SPI_START + 135)
+#define SPS_MTI_29				(GIC_SPI_START + 136)
+#define SPS_MTI_30				(GIC_SPI_START + 137)
+#define SPS_MTI_31				(GIC_SPI_START + 138)
+#define UXMC_EBI2_WR_ER_DONE_IRQ		(GIC_SPI_START + 139)
+#define UXMC_EBI2_OP_DONE_IRQ			(GIC_SPI_START + 140)
+#define USB2_IRQ				(GIC_SPI_START + 141)
+#define USB1_IRQ				(GIC_SPI_START + 142)
+#define TSSC_SSBI_IRQ				(GIC_SPI_START + 143)
+#define TSSC_SAMPLE_IRQ				(GIC_SPI_START + 144)
+#define TSSC_PENUP_IRQ				(GIC_SPI_START + 145)
+#define INT_UART1DM_IRQ				(GIC_SPI_START + 146)
+#define GSBI1_QUP_IRQ				(GIC_SPI_START + 147)
+#define INT_UART2DM_IRQ				(GIC_SPI_START + 148)
+#define GSBI2_QUP_IRQ				(GIC_SPI_START + 149)
+#define INT_UART3DM_IRQ				(GIC_SPI_START + 150)
+#define GSBI3_QUP_IRQ				(GIC_SPI_START + 151)
+#define INT_UART4DM_IRQ				(GIC_SPI_START + 152)
+#define GSBI4_QUP_IRQ				(GIC_SPI_START + 153)
+#define INT_UART5DM_IRQ				(GIC_SPI_START + 154)
+#define GSBI5_QUP_IRQ				(GIC_SPI_START + 155)
+#define INT_UART6DM_IRQ				(GIC_SPI_START + 156)
+#define GSBI6_QUP_IRQ				(GIC_SPI_START + 157)
+#define INT_UART7DM_IRQ				(GIC_SPI_START + 158)
+#define GSBI7_QUP_IRQ				(GIC_SPI_START + 159)
+#define INT_UART8DM_IRQ				(GIC_SPI_START + 160)
+#define GSBI8_QUP_IRQ				(GIC_SPI_START + 161)
+#define TSIF_TSPP_IRQ				(GIC_SPI_START + 162)
+#define TSIF_BAM_IRQ				(GIC_SPI_START + 163)
+#define TSIF2_IRQ				(GIC_SPI_START + 164)
+#define TSIF1_IRQ				(GIC_SPI_START + 165)
+#define INT_ADM1_MASTER				(GIC_SPI_START + 166)
+#define INT_ADM1_AARM				(GIC_SPI_START + 167)
+#define INT_ADM1_SD2				(GIC_SPI_START + 168)
+#define INT_ADM1_SD3				(GIC_SPI_START + 169)
+#define INT_ADM0_MASTER				(GIC_SPI_START + 170)
+#define INT_ADM0_AARM				(GIC_SPI_START + 171)
+#define INT_ADM0_SD2				(GIC_SPI_START + 172)
+#define INT_ADM0_SD3				(GIC_SPI_START + 173)
+#define CC_SCSS_WDT1CPU1BITEEXPIRED		(GIC_SPI_START + 174)
+#define CC_SCSS_WDT1CPU0BITEEXPIRED		(GIC_SPI_START + 175)
+#define CC_SCSS_WDT0CPU1BITEEXPIRED		(GIC_SPI_START + 176)
+#define CC_SCSS_WDT0CPU0BITEEXPIRED		(GIC_SPI_START + 177)
+#define TSENS_UPPER_LOWER_INT			(GIC_SPI_START + 178)
+#define SSBI2_2_SC_CPU1_SECURE_INT		(GIC_SPI_START + 179)
+#define SSBI2_2_SC_CPU1_NON_SECURE_INT		(GIC_SPI_START + 180)
+#define SSBI2_1_SC_CPU1_SECURE_INT		(GIC_SPI_START + 181)
+#define SSBI2_1_SC_CPU1_NON_SECURE_INT		(GIC_SPI_START + 182)
+#define XPU_SUMMARY_IRQ				(GIC_SPI_START + 183)
+#define BUS_EXCEPTION_SUMMARY_IRQ		(GIC_SPI_START + 184)
+#define HSDDRX_SMICH0_IRQ			(GIC_SPI_START + 185)
+#define HSDDRX_EBI1_IRQ				(GIC_SPI_START + 186)
+#define SDC5_BAM_IRQ				(GIC_SPI_START + 187)
+#define SDC5_IRQ_0				(GIC_SPI_START + 188)
+#define INT_UART9DM_IRQ				(GIC_SPI_START + 189)
+#define GSBI9_QUP_IRQ				(GIC_SPI_START + 190)
+#define INT_UART10DM_IRQ			(GIC_SPI_START + 191)
+#define GSBI10_QUP_IRQ				(GIC_SPI_START + 192)
+#define INT_UART11DM_IRQ			(GIC_SPI_START + 193)
+#define GSBI11_QUP_IRQ				(GIC_SPI_START + 194)
+#define INT_UART12DM_IRQ			(GIC_SPI_START + 195)
+#define GSBI12_QUP_IRQ				(GIC_SPI_START + 196)
+/*SPI 197 to 216 arent used in 8x60*/
+#define SMPSS_SPARE_1				(GIC_SPI_START + 217)
+#define SMPSS_SPARE_2				(GIC_SPI_START + 218)
+#define SMPSS_SPARE_3				(GIC_SPI_START + 219)
+#define SMPSS_SPARE_4				(GIC_SPI_START + 220)
+#define SMPSS_SPARE_5				(GIC_SPI_START + 221)
+#define SMPSS_SPARE_6				(GIC_SPI_START + 222)
+#define SMPSS_SPARE_7				(GIC_SPI_START + 223)
+
+#define NR_GPIO_IRQS 173
+#define NR_MSM_IRQS 256
+#define NR_BOARD_IRQS 0
+
+#endif
diff --git a/arch/arm/mach-msm/include/mach/irqs.h b/arch/arm/mach-msm/include/mach/irqs.h
index 164d355..8679a45 100644
--- a/arch/arm/mach-msm/include/mach/irqs.h
+++ b/arch/arm/mach-msm/include/mach/irqs.h
@@ -24,6 +24,8 @@
 #elif defined(CONFIG_ARCH_QSD8X50)
 #include "irqs-8x50.h"
 #include "sirc.h"
+#elif defined(CONFIG_ARCH_MSM8X60)
+#include "irqs-8x60.h"
 #elif defined(CONFIG_ARCH_MSM_ARM11)
 #include "irqs-7x00.h"
 #else
diff --git a/arch/arm/mach-msm/include/mach/memory.h b/arch/arm/mach-msm/include/mach/memory.h
index 50c7847..070e17d 100644
--- a/arch/arm/mach-msm/include/mach/memory.h
+++ b/arch/arm/mach-msm/include/mach/memory.h
@@ -23,6 +23,8 @@
 #define PHYS_OFFSET		UL(0x20000000)
 #elif defined(CONFIG_ARCH_MSM7X30)
 #define PHYS_OFFSET		UL(0x00200000)
+#elif defined(CONFIG_ARCH_MSM8X60)
+#define PHYS_OFFSET		UL(0x40200000)
 #else
 #define PHYS_OFFSET		UL(0x10000000)
 #endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h b/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
new file mode 100644
index 0000000..45bab50
--- /dev/null
+++ b/arch/arm/mach-msm/include/mach/msm_iomap-8x60.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2007 Google, Inc.
+ * Copyright (c) 2008-2010, Code Aurora Forum. All rights reserved.
+ * Author: Brian Swetland <swetland@google.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ *
+ * The MSM peripherals are spread all over across 768MB of physical
+ * space, which makes just having a simple IO_ADDRESS macro to slide
+ * them into the right virtual location rough.  Instead, we will
+ * provide a master phys->virt mapping for peripherals here.
+ *
+ */
+
+#ifndef __ASM_ARCH_MSM_IOMAP_8X60_H
+#define __ASM_ARCH_MSM_IOMAP_8X60_H
+
+/* Physical base address and size of peripherals.
+ * Ordered by the virtual base addresses they will be mapped at.
+ *
+ * MSM_VIC_BASE must be an value that can be loaded via a "mov"
+ * instruction, otherwise entry-macro.S will not compile.
+ *
+ * If you add or remove entries here, you'll want to edit the
+ * msm_io_desc array in arch/arm/mach-msm/io.c to reflect your
+ * changes.
+ *
+ */
+
+#define MSM_QGIC_DIST_BASE	IOMEM(0xF0000000)
+#define MSM_QGIC_DIST_PHYS	0x02080000
+#define MSM_QGIC_DIST_SIZE	SZ_4K
+
+#define MSM_QGIC_CPU_BASE	IOMEM(0xF0001000)
+#define MSM_QGIC_CPU_PHYS	0x02081000
+#define MSM_QGIC_CPU_SIZE	SZ_4K
+
+#define MSM_ACC_BASE		IOMEM(0xF0002000)
+#define MSM_ACC_PHYS		0x02001000
+#define MSM_ACC_SIZE		SZ_4K
+
+#define MSM_GCC_BASE		IOMEM(0xF0003000)
+#define MSM_GCC_PHYS		0x02082000
+#define MSM_GCC_SIZE		SZ_4K
+
+#define MSM_TLMM_BASE		IOMEM(0xF0004000)
+#define MSM_TLMM_PHYS		0x00800000
+#define MSM_TLMM_SIZE		SZ_16K
+
+#define MSM_SHARED_RAM_BASE	IOMEM(0xF0100000)
+#define MSM_SHARED_RAM_SIZE	SZ_1M
+
+#define MSM_TMR_BASE		IOMEM(0xF0200000)
+#define MSM_TMR_PHYS		0x02000000
+#define MSM_TMR_SIZE		(SZ_1M)
+
+#define MSM_GPT_BASE		(MSM_TMR_BASE + 0x4)
+#define MSM_DGT_BASE		(MSM_TMR_BASE + 0x24)
+
+#define MSM_IOMMU_JPEGD_PHYS	0x07300000
+#define MSM_IOMMU_JPEGD_SIZE	SZ_1M
+
+#define MSM_IOMMU_VPE_PHYS	0x07400000
+#define MSM_IOMMU_VPE_SIZE	SZ_1M
+
+#define MSM_IOMMU_MDP0_PHYS	0x07500000
+#define MSM_IOMMU_MDP0_SIZE	SZ_1M
+
+#define MSM_IOMMU_MDP1_PHYS	0x07600000
+#define MSM_IOMMU_MDP1_SIZE	SZ_1M
+
+#define MSM_IOMMU_ROT_PHYS	0x07700000
+#define MSM_IOMMU_ROT_SIZE	SZ_1M
+
+#define MSM_IOMMU_IJPEG_PHYS	0x07800000
+#define MSM_IOMMU_IJPEG_SIZE	SZ_1M
+
+#define MSM_IOMMU_VFE_PHYS	0x07900000
+#define MSM_IOMMU_VFE_SIZE	SZ_1M
+
+#define MSM_IOMMU_VCODEC_A_PHYS	0x07A00000
+#define MSM_IOMMU_VCODEC_A_SIZE	SZ_1M
+
+#define MSM_IOMMU_VCODEC_B_PHYS	0x07B00000
+#define MSM_IOMMU_VCODEC_B_SIZE	SZ_1M
+
+#define MSM_IOMMU_GFX3D_PHYS	0x07C00000
+#define MSM_IOMMU_GFX3D_SIZE	SZ_1M
+
+#define MSM_IOMMU_GFX2D0_PHYS	0x07D00000
+#define MSM_IOMMU_GFX2D0_SIZE	SZ_1M
+
+#endif
diff --git a/arch/arm/mach-msm/include/mach/msm_iomap.h b/arch/arm/mach-msm/include/mach/msm_iomap.h
index e6b1821..8e24dd8 100644
--- a/arch/arm/mach-msm/include/mach/msm_iomap.h
+++ b/arch/arm/mach-msm/include/mach/msm_iomap.h
@@ -47,8 +47,12 @@
 #include "msm_iomap-7x30.h"
 #elif defined(CONFIG_ARCH_QSD8X50)
 #include "msm_iomap-8x50.h"
+#elif defined(CONFIG_ARCH_MSM8X60)
+#include "msm_iomap-8x60.h"
 #else
 #include "msm_iomap-7x00.h"
 #endif
 
+
+
 #endif
diff --git a/arch/arm/mach-msm/include/mach/smp.h b/arch/arm/mach-msm/include/mach/smp.h
new file mode 100644
index 0000000..3ff7bf5
--- /dev/null
+++ b/arch/arm/mach-msm/include/mach/smp.h
@@ -0,0 +1,39 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Code Aurora nor
+ *       the names of its contributors may be used to endorse or promote
+ *       products derived from this software without specific prior written
+ *       permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NON-INFRINGEMENT ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef __ASM_ARCH_MSM_SMP_H
+#define __ASM_ARCH_MSM_SMP_H
+
+#include <asm/hardware/gic.h>
+
+static inline void smp_cross_call(const struct cpumask *mask)
+{
+	gic_raise_softirq(mask, 1);
+}
+
+#endif
diff --git a/arch/arm/mach-msm/include/mach/vmalloc.h b/arch/arm/mach-msm/include/mach/vmalloc.h
index 05f81fd..31a32ad 100644
--- a/arch/arm/mach-msm/include/mach/vmalloc.h
+++ b/arch/arm/mach-msm/include/mach/vmalloc.h
@@ -16,7 +16,7 @@
 #ifndef __ASM_ARCH_MSM_VMALLOC_H
 #define __ASM_ARCH_MSM_VMALLOC_H
 
-#define VMALLOC_END	  (PAGE_OFFSET + 0x10000000)
+#define VMALLOC_END	  0xd0000000
 
 #endif
 
diff --git a/arch/arm/mach-msm/io.c b/arch/arm/mach-msm/io.c
index 1c05060..d36b610 100644
--- a/arch/arm/mach-msm/io.c
+++ b/arch/arm/mach-msm/io.c
@@ -100,6 +100,21 @@
 }
 #endif /* CONFIG_ARCH_QSD8X50 */
 
+#ifdef CONFIG_ARCH_MSM8X60
+static struct map_desc msm8x60_io_desc[] __initdata = {
+	MSM_DEVICE(QGIC_DIST),
+	MSM_DEVICE(QGIC_CPU),
+	MSM_DEVICE(TMR),
+	MSM_DEVICE(ACC),
+	MSM_DEVICE(GCC),
+};
+
+void __init msm_map_msm8x60_io(void)
+{
+	iotable_init(msm8x60_io_desc, ARRAY_SIZE(msm8x60_io_desc));
+}
+#endif /* CONFIG_ARCH_MSM8X60 */
+
 #ifdef CONFIG_ARCH_MSM7X30
 static struct map_desc msm7x30_io_desc[] __initdata = {
 	MSM_DEVICE(VIC),
diff --git a/arch/arm/mach-msm/iommu.c b/arch/arm/mach-msm/iommu.c
new file mode 100644
index 0000000..f71747d
--- /dev/null
+++ b/arch/arm/mach-msm/iommu.c
@@ -0,0 +1,597 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/iommu.h>
+
+#include <asm/cacheflush.h>
+#include <asm/sizes.h>
+
+#include <mach/iommu_hw-8xxx.h>
+#include <mach/iommu.h>
+
+DEFINE_SPINLOCK(msm_iommu_lock);
+
+struct msm_priv {
+	unsigned long *pgtable;
+	struct list_head list_attached;
+};
+
+static void __flush_iotlb(struct iommu_domain *domain)
+{
+	struct msm_priv *priv = domain->priv;
+	struct msm_iommu_drvdata *iommu_drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+
+#ifndef CONFIG_IOMMU_PGTABLES_L2
+	unsigned long *fl_table = priv->pgtable;
+	int i;
+
+	dmac_flush_range(fl_table, fl_table + SZ_16K);
+
+	for (i = 0; i < NUM_FL_PTE; i++)
+		if ((fl_table[i] & 0x03) == FL_TYPE_TABLE) {
+			void *sl_table = __va(fl_table[i] & FL_BASE_MASK);
+			dmac_flush_range(sl_table, sl_table + SZ_4K);
+		}
+#endif
+
+	list_for_each_entry(ctx_drvdata, &priv->list_attached, attached_elm) {
+		if (!ctx_drvdata->pdev || !ctx_drvdata->pdev->dev.parent)
+			BUG();
+
+		iommu_drvdata = dev_get_drvdata(ctx_drvdata->pdev->dev.parent);
+		SET_CTX_TLBIALL(iommu_drvdata->base, ctx_drvdata->num, 0);
+	}
+}
+
+static void __reset_context(void __iomem *base, int ctx)
+{
+	SET_BPRCOSH(base, ctx, 0);
+	SET_BPRCISH(base, ctx, 0);
+	SET_BPRCNSH(base, ctx, 0);
+	SET_BPSHCFG(base, ctx, 0);
+	SET_BPMTCFG(base, ctx, 0);
+	SET_ACTLR(base, ctx, 0);
+	SET_SCTLR(base, ctx, 0);
+	SET_FSRRESTORE(base, ctx, 0);
+	SET_TTBR0(base, ctx, 0);
+	SET_TTBR1(base, ctx, 0);
+	SET_TTBCR(base, ctx, 0);
+	SET_BFBCR(base, ctx, 0);
+	SET_PAR(base, ctx, 0);
+	SET_FAR(base, ctx, 0);
+	SET_CTX_TLBIALL(base, ctx, 0);
+	SET_TLBFLPTER(base, ctx, 0);
+	SET_TLBSLPTER(base, ctx, 0);
+	SET_TLBLKCR(base, ctx, 0);
+	SET_PRRR(base, ctx, 0);
+	SET_NMRR(base, ctx, 0);
+	SET_CONTEXTIDR(base, ctx, 0);
+}
+
+static void __program_context(void __iomem *base, int ctx, phys_addr_t pgtable)
+{
+	__reset_context(base, ctx);
+
+	/* Set up HTW mode */
+	/* TLB miss configuration: perform HTW on miss */
+	SET_TLBMCFG(base, ctx, 0x3);
+
+	/* V2P configuration: HTW for access */
+	SET_V2PCFG(base, ctx, 0x3);
+
+	SET_TTBCR(base, ctx, 0);
+	SET_TTBR0_PA(base, ctx, (pgtable >> 14));
+
+	/* Invalidate the TLB for this context */
+	SET_CTX_TLBIALL(base, ctx, 0);
+
+	/* Set interrupt number to "secure" interrupt */
+	SET_IRPTNDX(base, ctx, 0);
+
+	/* Enable context fault interrupt */
+	SET_CFEIE(base, ctx, 1);
+
+	/* Stall access on a context fault and let the handler deal with it */
+	SET_CFCFG(base, ctx, 1);
+
+	/* Redirect all cacheable requests to L2 slave port. */
+	SET_RCISH(base, ctx, 1);
+	SET_RCOSH(base, ctx, 1);
+	SET_RCNSH(base, ctx, 1);
+
+	/* Turn on TEX Remap */
+	SET_TRE(base, ctx, 1);
+
+	/* Do not configure PRRR / NMRR on the IOMMU for now. We will assume
+	 * TEX class 0 for everything until attributes are properly worked out
+	 */
+	SET_PRRR(base, ctx, 0);
+	SET_NMRR(base, ctx, 0);
+
+	/* Turn on BFB prefetch */
+	SET_BFBDFE(base, ctx, 1);
+
+#ifdef CONFIG_IOMMU_PGTABLES_L2
+	/* Configure page tables as inner-cacheable and shareable to reduce
+	 * the TLB miss penalty.
+	 */
+	SET_TTBR0_SH(base, ctx, 1);
+	SET_TTBR1_SH(base, ctx, 1);
+
+	SET_TTBR0_NOS(base, ctx, 1);
+	SET_TTBR1_NOS(base, ctx, 1);
+
+	SET_TTBR0_IRGNH(base, ctx, 0); /* WB, WA */
+	SET_TTBR0_IRGNL(base, ctx, 1);
+
+	SET_TTBR1_IRGNH(base, ctx, 0); /* WB, WA */
+	SET_TTBR1_IRGNL(base, ctx, 1);
+
+	SET_TTBR0_ORGN(base, ctx, 1); /* WB, WA */
+	SET_TTBR1_ORGN(base, ctx, 1); /* WB, WA */
+#endif
+
+	/* Enable the MMU */
+	SET_M(base, ctx, 1);
+}
+
+static int msm_iommu_domain_init(struct iommu_domain *domain)
+{
+	struct msm_priv *priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+
+	if (!priv)
+		goto fail_nomem;
+
+	INIT_LIST_HEAD(&priv->list_attached);
+	priv->pgtable = (unsigned long *)__get_free_pages(GFP_KERNEL,
+							  get_order(SZ_16K));
+
+	if (!priv->pgtable)
+		goto fail_nomem;
+
+	memset(priv->pgtable, 0, SZ_16K);
+	domain->priv = priv;
+	return 0;
+
+fail_nomem:
+	kfree(priv);
+	return -ENOMEM;
+}
+
+static void msm_iommu_domain_destroy(struct iommu_domain *domain)
+{
+	struct msm_priv *priv;
+	unsigned long flags;
+	unsigned long *fl_table;
+	int i;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	priv = domain->priv;
+	domain->priv = NULL;
+
+	if (priv) {
+		fl_table = priv->pgtable;
+
+		for (i = 0; i < NUM_FL_PTE; i++)
+			if ((fl_table[i] & 0x03) == FL_TYPE_TABLE)
+				free_page((unsigned long) __va(((fl_table[i]) &
+								FL_BASE_MASK)));
+
+		free_pages((unsigned long)priv->pgtable, get_order(SZ_16K));
+		priv->pgtable = NULL;
+	}
+
+	kfree(priv);
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
+
+static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct msm_priv *priv;
+	struct msm_iommu_ctx_dev *ctx_dev;
+	struct msm_iommu_drvdata *iommu_drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	struct msm_iommu_ctx_drvdata *tmp_drvdata;
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	priv = domain->priv;
+
+	if (!priv || !dev) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	iommu_drvdata = dev_get_drvdata(dev->parent);
+	ctx_drvdata = dev_get_drvdata(dev);
+	ctx_dev = dev->platform_data;
+
+	if (!iommu_drvdata || !ctx_drvdata || !ctx_dev) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	list_for_each_entry(tmp_drvdata, &priv->list_attached, attached_elm)
+		if (tmp_drvdata == ctx_drvdata) {
+			ret = -EBUSY;
+			goto fail;
+		}
+
+	__program_context(iommu_drvdata->base, ctx_dev->num,
+			  __pa(priv->pgtable));
+
+	list_add(&(ctx_drvdata->attached_elm), &priv->list_attached);
+	__flush_iotlb(domain);
+
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return ret;
+}
+
+static void msm_iommu_detach_dev(struct iommu_domain *domain,
+				 struct device *dev)
+{
+	struct msm_priv *priv;
+	struct msm_iommu_ctx_dev *ctx_dev;
+	struct msm_iommu_drvdata *iommu_drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	unsigned long flags;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	priv = domain->priv;
+
+	if (!priv || !dev)
+		goto fail;
+
+	iommu_drvdata = dev_get_drvdata(dev->parent);
+	ctx_drvdata = dev_get_drvdata(dev);
+	ctx_dev = dev->platform_data;
+
+	if (!iommu_drvdata || !ctx_drvdata || !ctx_dev)
+		goto fail;
+
+	__flush_iotlb(domain);
+	__reset_context(iommu_drvdata->base, ctx_dev->num);
+	list_del_init(&ctx_drvdata->attached_elm);
+
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
+
+static int msm_iommu_map(struct iommu_domain *domain, unsigned long va,
+			 phys_addr_t pa, int order, int prot)
+{
+	struct msm_priv *priv;
+	unsigned long flags;
+	unsigned long *fl_table;
+	unsigned long *fl_pte;
+	unsigned long fl_offset;
+	unsigned long *sl_table;
+	unsigned long *sl_pte;
+	unsigned long sl_offset;
+	size_t len = 0x1000UL << order;
+	int ret = 0;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+	priv = domain->priv;
+
+	if (!priv) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	fl_table = priv->pgtable;
+
+	if (len != SZ_16M && len != SZ_1M &&
+	    len != SZ_64K && len != SZ_4K) {
+		pr_debug("Bad size: %d\n", len);
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (!fl_table) {
+		pr_debug("Null page table\n");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	fl_offset = FL_OFFSET(va);	/* Upper 12 bits */
+	fl_pte = fl_table + fl_offset;	/* int pointers, 4 bytes */
+
+	if (len == SZ_16M) {
+		int i = 0;
+		for (i = 0; i < 16; i++)
+			*(fl_pte+i) = (pa & 0xFF000000) | FL_SUPERSECTION |
+				  FL_AP_READ | FL_AP_WRITE | FL_TYPE_SECT |
+				  FL_SHARED;
+	}
+
+	if (len == SZ_1M)
+		*fl_pte = (pa & 0xFFF00000) | FL_AP_READ | FL_AP_WRITE |
+						FL_TYPE_SECT | FL_SHARED;
+
+	/* Need a 2nd level table */
+	if ((len == SZ_4K || len == SZ_64K) && (*fl_pte) == 0) {
+		unsigned long *sl;
+		sl = (unsigned long *) __get_free_pages(GFP_KERNEL,
+							get_order(SZ_4K));
+
+		if (!sl) {
+			pr_debug("Could not allocate second level table\n");
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		memset(sl, 0, SZ_4K);
+		*fl_pte = ((((int)__pa(sl)) & FL_BASE_MASK) | FL_TYPE_TABLE);
+	}
+
+	sl_table = (unsigned long *) __va(((*fl_pte) & FL_BASE_MASK));
+	sl_offset = SL_OFFSET(va);
+	sl_pte = sl_table + sl_offset;
+
+
+	if (len == SZ_4K)
+		*sl_pte = (pa & SL_BASE_MASK_SMALL) | SL_AP0 | SL_AP1 |
+					  SL_SHARED | SL_TYPE_SMALL;
+
+	if (len == SZ_64K) {
+		int i;
+
+		for (i = 0; i < 16; i++)
+			*(sl_pte+i) = (pa & SL_BASE_MASK_LARGE) | SL_AP0 |
+					    SL_AP1 | SL_SHARED | SL_TYPE_LARGE;
+	}
+
+	__flush_iotlb(domain);
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return ret;
+}
+
+static int msm_iommu_unmap(struct iommu_domain *domain, unsigned long va,
+			    int order)
+{
+	struct msm_priv *priv;
+	unsigned long flags;
+	unsigned long *fl_table;
+	unsigned long *fl_pte;
+	unsigned long fl_offset;
+	unsigned long *sl_table;
+	unsigned long *sl_pte;
+	unsigned long sl_offset;
+	size_t len = 0x1000UL << order;
+	int i, ret = 0;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	priv = domain->priv;
+
+	if (!priv) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	fl_table = priv->pgtable;
+
+	if (len != SZ_16M && len != SZ_1M &&
+	    len != SZ_64K && len != SZ_4K) {
+		pr_debug("Bad length: %d\n", len);
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	if (!fl_table) {
+		pr_debug("Null page table\n");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	fl_offset = FL_OFFSET(va);	/* Upper 12 bits */
+	fl_pte = fl_table + fl_offset;	/* int pointers, 4 bytes */
+
+	if (*fl_pte == 0) {
+		pr_debug("First level PTE is 0\n");
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	/* Unmap supersection */
+	if (len == SZ_16M)
+		for (i = 0; i < 16; i++)
+			*(fl_pte+i) = 0;
+
+	if (len == SZ_1M)
+		*fl_pte = 0;
+
+	sl_table = (unsigned long *) __va(((*fl_pte) & FL_BASE_MASK));
+	sl_offset = SL_OFFSET(va);
+	sl_pte = sl_table + sl_offset;
+
+	if (len == SZ_64K) {
+		for (i = 0; i < 16; i++)
+			*(sl_pte+i) = 0;
+	}
+
+	if (len == SZ_4K)
+		*sl_pte = 0;
+
+	if (len == SZ_4K || len == SZ_64K) {
+		int used = 0;
+
+		for (i = 0; i < NUM_SL_PTE; i++)
+			if (sl_table[i])
+				used = 1;
+		if (!used) {
+			free_page((unsigned long)sl_table);
+			*fl_pte = 0;
+		}
+	}
+
+	__flush_iotlb(domain);
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return ret;
+}
+
+static phys_addr_t msm_iommu_iova_to_phys(struct iommu_domain *domain,
+					  unsigned long va)
+{
+	struct msm_priv *priv;
+	struct msm_iommu_drvdata *iommu_drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata;
+	unsigned int par;
+	unsigned long flags;
+	void __iomem *base;
+	phys_addr_t ret = 0;
+	int ctx;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	priv = domain->priv;
+	if (list_empty(&priv->list_attached))
+		goto fail;
+
+	ctx_drvdata = list_entry(priv->list_attached.next,
+				 struct msm_iommu_ctx_drvdata, attached_elm);
+	iommu_drvdata = dev_get_drvdata(ctx_drvdata->pdev->dev.parent);
+
+	base = iommu_drvdata->base;
+	ctx = ctx_drvdata->num;
+
+	/* Invalidate context TLB */
+	SET_CTX_TLBIALL(base, ctx, 0);
+	SET_V2PPR_VA(base, ctx, va >> V2Pxx_VA_SHIFT);
+
+	if (GET_FAULT(base, ctx))
+		goto fail;
+
+	par = GET_PAR(base, ctx);
+
+	/* We are dealing with a supersection */
+	if (GET_NOFAULT_SS(base, ctx))
+		ret = (par & 0xFF000000) | (va & 0x00FFFFFF);
+	else	/* Upper 20 bits from PAR, lower 12 from VA */
+		ret = (par & 0xFFFFF000) | (va & 0x00000FFF);
+
+fail:
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+	return ret;
+}
+
+static int msm_iommu_domain_has_cap(struct iommu_domain *domain,
+				    unsigned long cap)
+{
+	return 0;
+}
+
+static void print_ctx_regs(void __iomem *base, int ctx)
+{
+	unsigned int fsr = GET_FSR(base, ctx);
+	pr_err("FAR    = %08x    PAR    = %08x\n",
+	       GET_FAR(base, ctx), GET_PAR(base, ctx));
+	pr_err("FSR    = %08x [%s%s%s%s%s%s%s%s%s%s]\n", fsr,
+			(fsr & 0x02) ? "TF " : "",
+			(fsr & 0x04) ? "AFF " : "",
+			(fsr & 0x08) ? "APF " : "",
+			(fsr & 0x10) ? "TLBMF " : "",
+			(fsr & 0x20) ? "HTWDEEF " : "",
+			(fsr & 0x40) ? "HTWSEEF " : "",
+			(fsr & 0x80) ? "MHF " : "",
+			(fsr & 0x10000) ? "SL " : "",
+			(fsr & 0x40000000) ? "SS " : "",
+			(fsr & 0x80000000) ? "MULTI " : "");
+
+	pr_err("FSYNR0 = %08x    FSYNR1 = %08x\n",
+	       GET_FSYNR0(base, ctx), GET_FSYNR1(base, ctx));
+	pr_err("TTBR0  = %08x    TTBR1  = %08x\n",
+	       GET_TTBR0(base, ctx), GET_TTBR1(base, ctx));
+	pr_err("SCTLR  = %08x    ACTLR  = %08x\n",
+	       GET_SCTLR(base, ctx), GET_ACTLR(base, ctx));
+	pr_err("PRRR   = %08x    NMRR   = %08x\n",
+	       GET_PRRR(base, ctx), GET_NMRR(base, ctx));
+}
+
+irqreturn_t msm_iommu_fault_handler(int irq, void *dev_id)
+{
+	struct msm_iommu_drvdata *drvdata = dev_id;
+	void __iomem *base;
+	unsigned int fsr = 0;
+	int ncb = 0, i = 0;
+
+	spin_lock(&msm_iommu_lock);
+
+	if (!drvdata) {
+		pr_err("Invalid device ID in context interrupt handler\n");
+		goto fail;
+	}
+
+	base = drvdata->base;
+
+	pr_err("===== WOAH! =====\n");
+	pr_err("Unexpected IOMMU page fault!\n");
+	pr_err("base = %08x\n", (unsigned int) base);
+
+	ncb = GET_NCB(base)+1;
+	for (i = 0; i < ncb; i++) {
+		fsr = GET_FSR(base, i);
+		if (fsr) {
+			pr_err("Fault occurred in context %d.\n", i);
+			pr_err("Interesting registers:\n");
+			print_ctx_regs(base, i);
+			SET_FSR(base, i, 0x4000000F);
+		}
+	}
+fail:
+	spin_unlock(&msm_iommu_lock);
+	return 0;
+}
+
+static struct iommu_ops msm_iommu_ops = {
+	.domain_init = msm_iommu_domain_init,
+	.domain_destroy = msm_iommu_domain_destroy,
+	.attach_dev = msm_iommu_attach_dev,
+	.detach_dev = msm_iommu_detach_dev,
+	.map = msm_iommu_map,
+	.unmap = msm_iommu_unmap,
+	.iova_to_phys = msm_iommu_iova_to_phys,
+	.domain_has_cap = msm_iommu_domain_has_cap
+};
+
+static int msm_iommu_init(void)
+{
+	register_iommu(&msm_iommu_ops);
+	return 0;
+}
+
+subsys_initcall(msm_iommu_init);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
diff --git a/arch/arm/mach-msm/iommu_dev.c b/arch/arm/mach-msm/iommu_dev.c
new file mode 100644
index 0000000..c33ae78
--- /dev/null
+++ b/arch/arm/mach-msm/iommu_dev.c
@@ -0,0 +1,374 @@
+/* Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/iommu.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+#include <mach/iommu_hw-8xxx.h>
+#include <mach/iommu.h>
+
+struct iommu_ctx_iter_data {
+	/* input */
+	const char *name;
+
+	/* output */
+	struct device *dev;
+};
+
+static struct platform_device *msm_iommu_root_dev;
+
+static int each_iommu_ctx(struct device *dev, void *data)
+{
+	struct iommu_ctx_iter_data *res = data;
+	struct msm_iommu_ctx_dev *c = dev->platform_data;
+
+	if (!res || !c || !c->name || !res->name)
+		return -EINVAL;
+
+	if (!strcmp(res->name, c->name)) {
+		res->dev = dev;
+		return 1;
+	}
+	return 0;
+}
+
+static int each_iommu(struct device *dev, void *data)
+{
+	return device_for_each_child(dev, data, each_iommu_ctx);
+}
+
+struct device *msm_iommu_get_ctx(const char *ctx_name)
+{
+	struct iommu_ctx_iter_data r;
+	int found;
+
+	if (!msm_iommu_root_dev) {
+		pr_err("No root IOMMU device.\n");
+		goto fail;
+	}
+
+	r.name = ctx_name;
+	found = device_for_each_child(&msm_iommu_root_dev->dev, &r, each_iommu);
+
+	if (!found) {
+		pr_err("Could not find context <%s>\n", ctx_name);
+		goto fail;
+	}
+
+	return r.dev;
+fail:
+	return NULL;
+}
+EXPORT_SYMBOL(msm_iommu_get_ctx);
+
+static void msm_iommu_reset(void __iomem *base)
+{
+	int ctx, ncb;
+
+	SET_RPUE(base, 0);
+	SET_RPUEIE(base, 0);
+	SET_ESRRESTORE(base, 0);
+	SET_TBE(base, 0);
+	SET_CR(base, 0);
+	SET_SPDMBE(base, 0);
+	SET_TESTBUSCR(base, 0);
+	SET_TLBRSW(base, 0);
+	SET_GLOBAL_TLBIALL(base, 0);
+	SET_RPU_ACR(base, 0);
+	SET_TLBLKCRWE(base, 1);
+	ncb = GET_NCB(base)+1;
+
+	for (ctx = 0; ctx < ncb; ctx++) {
+		SET_BPRCOSH(base, ctx, 0);
+		SET_BPRCISH(base, ctx, 0);
+		SET_BPRCNSH(base, ctx, 0);
+		SET_BPSHCFG(base, ctx, 0);
+		SET_BPMTCFG(base, ctx, 0);
+		SET_ACTLR(base, ctx, 0);
+		SET_SCTLR(base, ctx, 0);
+		SET_FSRRESTORE(base, ctx, 0);
+		SET_TTBR0(base, ctx, 0);
+		SET_TTBR1(base, ctx, 0);
+		SET_TTBCR(base, ctx, 0);
+		SET_BFBCR(base, ctx, 0);
+		SET_PAR(base, ctx, 0);
+		SET_FAR(base, ctx, 0);
+		SET_CTX_TLBIALL(base, ctx, 0);
+		SET_TLBFLPTER(base, ctx, 0);
+		SET_TLBSLPTER(base, ctx, 0);
+		SET_TLBLKCR(base, ctx, 0);
+		SET_PRRR(base, ctx, 0);
+		SET_NMRR(base, ctx, 0);
+		SET_CONTEXTIDR(base, ctx, 0);
+	}
+}
+
+static int msm_iommu_probe(struct platform_device *pdev)
+{
+	struct resource *r;
+	struct clk *iommu_clk;
+	struct msm_iommu_drvdata *drvdata;
+	struct msm_iommu_dev *iommu_dev = pdev->dev.platform_data;
+	void __iomem *regs_base;
+	resource_size_t	len;
+	int ret = 0, ncb, nm2v, irq;
+
+	if (pdev->id != -1) {
+		drvdata = kzalloc(sizeof(*drvdata), GFP_KERNEL);
+
+		if (!drvdata) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		if (!iommu_dev) {
+			ret = -ENODEV;
+			goto fail;
+		}
+
+		if (iommu_dev->clk_rate != 0) {
+			iommu_clk = clk_get(&pdev->dev, "iommu_clk");
+
+			if (IS_ERR(iommu_clk)) {
+				ret = -ENODEV;
+				goto fail;
+			}
+
+			if (iommu_dev->clk_rate > 0) {
+				ret = clk_set_rate(iommu_clk,
+							iommu_dev->clk_rate);
+				if (ret) {
+					clk_put(iommu_clk);
+					goto fail;
+				}
+			}
+
+			ret = clk_enable(iommu_clk);
+			if (ret) {
+				clk_put(iommu_clk);
+				goto fail;
+			}
+			clk_put(iommu_clk);
+		}
+
+		r = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						 "physbase");
+		if (!r) {
+			ret = -ENODEV;
+			goto fail;
+		}
+
+		len = r->end - r->start + 1;
+
+		r = request_mem_region(r->start, len, r->name);
+		if (!r) {
+			pr_err("Could not request memory region: "
+			"start=%p, len=%d\n", (void *) r->start, len);
+			ret = -EBUSY;
+			goto fail;
+		}
+
+		regs_base = ioremap(r->start, len);
+
+		if (!regs_base) {
+			pr_err("Could not ioremap: start=%p, len=%d\n",
+				 (void *) r->start, len);
+			ret = -EBUSY;
+			goto fail;
+		}
+
+		irq = platform_get_irq_byname(pdev, "secure_irq");
+		if (irq < 0) {
+			ret = -ENODEV;
+			goto fail;
+		}
+
+		mb();
+
+		if (GET_IDR(regs_base) == 0) {
+			pr_err("Invalid IDR value detected\n");
+			ret = -ENODEV;
+			goto fail;
+		}
+
+		ret = request_irq(irq, msm_iommu_fault_handler, 0,
+				"msm_iommu_secure_irpt_handler", drvdata);
+		if (ret) {
+			pr_err("Request IRQ %d failed with ret=%d\n", irq, ret);
+			goto fail;
+		}
+
+		msm_iommu_reset(regs_base);
+		drvdata->base = regs_base;
+		drvdata->irq = irq;
+
+		nm2v = GET_NM2VCBMT((unsigned long) regs_base);
+		ncb = GET_NCB((unsigned long) regs_base);
+
+		pr_info("device %s mapped at %p, irq %d with %d ctx banks\n",
+			iommu_dev->name, regs_base, irq, ncb+1);
+
+		platform_set_drvdata(pdev, drvdata);
+	} else
+		msm_iommu_root_dev = pdev;
+
+	return 0;
+
+fail:
+	kfree(drvdata);
+	return ret;
+}
+
+static int msm_iommu_remove(struct platform_device *pdev)
+{
+	struct msm_iommu_drvdata *drv = NULL;
+
+	drv = platform_get_drvdata(pdev);
+	if (drv) {
+		memset(drv, 0, sizeof(struct msm_iommu_drvdata));
+		kfree(drv);
+		platform_set_drvdata(pdev, NULL);
+	}
+	return 0;
+}
+
+static int msm_iommu_ctx_probe(struct platform_device *pdev)
+{
+	struct msm_iommu_ctx_dev *c = pdev->dev.platform_data;
+	struct msm_iommu_drvdata *drvdata;
+	struct msm_iommu_ctx_drvdata *ctx_drvdata = NULL;
+	int i, ret = 0;
+	if (!c || !pdev->dev.parent) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	drvdata = dev_get_drvdata(pdev->dev.parent);
+
+	if (!drvdata) {
+		ret = -ENODEV;
+		goto fail;
+	}
+
+	ctx_drvdata = kzalloc(sizeof(*ctx_drvdata), GFP_KERNEL);
+	if (!ctx_drvdata) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+	ctx_drvdata->num = c->num;
+	ctx_drvdata->pdev = pdev;
+
+	INIT_LIST_HEAD(&ctx_drvdata->attached_elm);
+	platform_set_drvdata(pdev, ctx_drvdata);
+
+	/* Program the M2V tables for this context */
+	for (i = 0; i < MAX_NUM_MIDS; i++) {
+		int mid = c->mids[i];
+		if (mid == -1)
+			break;
+
+		SET_M2VCBR_N(drvdata->base, mid, 0);
+		SET_CBACR_N(drvdata->base, c->num, 0);
+
+		/* Set VMID = MID */
+		SET_VMID(drvdata->base, mid, mid);
+
+		/* Set the context number for that MID to this context */
+		SET_CBNDX(drvdata->base, mid, c->num);
+
+		/* Set MID associated with this context bank */
+		SET_CBVMID(drvdata->base, c->num, mid);
+
+		/* Set security bit override to be Non-secure */
+		SET_NSCFG(drvdata->base, mid, 3);
+	}
+
+	pr_info("context device %s with bank index %d\n", c->name, c->num);
+
+	return 0;
+fail:
+	kfree(ctx_drvdata);
+	return ret;
+}
+
+static int msm_iommu_ctx_remove(struct platform_device *pdev)
+{
+	struct msm_iommu_ctx_drvdata *drv = NULL;
+	drv = platform_get_drvdata(pdev);
+	if (drv) {
+		memset(drv, 0, sizeof(struct msm_iommu_ctx_drvdata));
+		kfree(drv);
+		platform_set_drvdata(pdev, NULL);
+	}
+	return 0;
+}
+
+static struct platform_driver msm_iommu_driver = {
+	.driver = {
+		.name	= "msm_iommu",
+	},
+	.probe		= msm_iommu_probe,
+	.remove		= msm_iommu_remove,
+};
+
+static struct platform_driver msm_iommu_ctx_driver = {
+	.driver = {
+		.name	= "msm_iommu_ctx",
+	},
+	.probe		= msm_iommu_ctx_probe,
+	.remove		= msm_iommu_ctx_remove,
+};
+
+static int msm_iommu_driver_init(void)
+{
+	int ret;
+	ret = platform_driver_register(&msm_iommu_driver);
+	if (ret != 0) {
+		pr_err("Failed to register IOMMU driver\n");
+		goto error;
+	}
+
+	ret = platform_driver_register(&msm_iommu_ctx_driver);
+	if (ret != 0) {
+		pr_err("Failed to register IOMMU context driver\n");
+		goto error;
+	}
+
+error:
+	return ret;
+}
+
+static void msm_iommu_driver_exit(void)
+{
+	platform_driver_unregister(&msm_iommu_ctx_driver);
+	platform_driver_unregister(&msm_iommu_driver);
+}
+
+subsys_initcall(msm_iommu_driver_init);
+module_exit(msm_iommu_driver_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
diff --git a/arch/arm/mach-msm/last_radio_log.c b/arch/arm/mach-msm/last_radio_log.c
index b64ba5a..1e243f4 100644
--- a/arch/arm/mach-msm/last_radio_log.c
+++ b/arch/arm/mach-msm/last_radio_log.c
@@ -48,7 +48,8 @@
 }
 
 static struct file_operations last_radio_log_fops = {
-	.read = last_radio_log_read
+	.read = last_radio_log_read,
+	.llseek = default_llseek,
 };
 
 void msm_init_last_radio_log(struct module *owner)
diff --git a/arch/arm/mach-msm/smd_debug.c b/arch/arm/mach-msm/smd_debug.c
index 3b2dd71..f91c3b7 100644
--- a/arch/arm/mach-msm/smd_debug.c
+++ b/arch/arm/mach-msm/smd_debug.c
@@ -212,6 +212,7 @@
 static const struct file_operations debug_ops = {
 	.read = debug_read,
 	.open = debug_open,
+	.llseek = default_llseek,
 };
 
 static void debug_create(const char *name, mode_t mode,
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index dec5ca6..7689848 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -28,7 +28,6 @@
 #ifndef MSM_DGT_BASE
 #define MSM_DGT_BASE (MSM_GPT_BASE + 0x10)
 #endif
-#define MSM_DGT_SHIFT (5)
 
 #define TIMER_MATCH_VAL         0x0000
 #define TIMER_COUNT_VAL         0x0004
@@ -36,12 +35,28 @@
 #define TIMER_ENABLE_CLR_ON_MATCH_EN    2
 #define TIMER_ENABLE_EN                 1
 #define TIMER_CLEAR             0x000C
-
+#define DGT_CLK_CTL             0x0034
+enum {
+	DGT_CLK_CTL_DIV_1 = 0,
+	DGT_CLK_CTL_DIV_2 = 1,
+	DGT_CLK_CTL_DIV_3 = 2,
+	DGT_CLK_CTL_DIV_4 = 3,
+};
 #define CSR_PROTECTION          0x0020
 #define CSR_PROTECTION_EN               1
 
 #define GPT_HZ 32768
+
+#if defined(CONFIG_ARCH_QSD8X50)
+#define DGT_HZ (19200000 / 4) /* 19.2 MHz / 4 by default */
+#define MSM_DGT_SHIFT (0)
+#elif defined(CONFIG_ARCH_MSM7X30) || defined(CONFIG_ARCH_MSM8X60)
+#define DGT_HZ (24576000 / 4) /* 24.576 MHz (LPXO) / 4 by default */
+#define MSM_DGT_SHIFT (0)
+#else
 #define DGT_HZ 19200000 /* 19.2 MHz or 600 KHz after shift */
+#define MSM_DGT_SHIFT (5)
+#endif
 
 struct msm_clock {
 	struct clock_event_device   clockevent;
@@ -170,6 +185,10 @@
 	int i;
 	int res;
 
+#ifdef CONFIG_ARCH_MSM8X60
+	writel(DGT_CLK_CTL_DIV_4, MSM_TMR_BASE + DGT_CLK_CTL);
+#endif
+
 	for (i = 0; i < ARRAY_SIZE(msm_clocks); i++) {
 		struct msm_clock *clock = &msm_clocks[i];
 		struct clock_event_device *ce = &clock->clockevent;
diff --git a/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c b/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
index 61e5e58..29e390e 100644
--- a/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
+++ b/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
@@ -145,8 +145,6 @@
 
 MACHINE_START(TERASTATION_WXL, "Buffalo Nas WXL")
 	/* Maintainer: Sebastien Requiem <sebastien@requiem.fr> */
-	.phys_io	= MV78XX0_REGS_PHYS_BASE,
-	.io_pg_offst	= ((MV78XX0_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= wxl_init,
 	.map_io		= mv78xx0_map_io,
diff --git a/arch/arm/mach-mv78xx0/db78x00-bp-setup.c b/arch/arm/mach-mv78xx0/db78x00-bp-setup.c
index efdabe0..207c95e 100644
--- a/arch/arm/mach-mv78xx0/db78x00-bp-setup.c
+++ b/arch/arm/mach-mv78xx0/db78x00-bp-setup.c
@@ -93,8 +93,6 @@
 
 MACHINE_START(DB78X00_BP, "Marvell DB-78x00-BP Development Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.phys_io	= MV78XX0_REGS_PHYS_BASE,
-	.io_pg_offst	= ((MV78XX0_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= db78x00_init,
 	.map_io		= mv78xx0_map_io,
diff --git a/arch/arm/mach-mv78xx0/include/mach/debug-macro.S b/arch/arm/mach-mv78xx0/include/mach/debug-macro.S
index cd81689..04891428 100644
--- a/arch/arm/mach-mv78xx0/include/mach/debug-macro.S
+++ b/arch/arm/mach-mv78xx0/include/mach/debug-macro.S
@@ -8,12 +8,11 @@
 
 #include <mach/mv78xx0.h>
 
-	.macro	addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1					@ MMU enabled?
-	ldreq	\rx, =MV78XX0_REGS_PHYS_BASE
-	ldrne	\rx, =MV78XX0_REGS_VIRT_BASE
-	orr	\rx, \rx, #0x00012000
+	.macro	addruart, rp, rv
+	ldr	\rp, =MV78XX0_REGS_PHYS_BASE
+	ldr	\rv, =MV78XX0_REGS_VIRT_BASE
+	orr	\rp, \rp, #0x00012000
+	orr	\rv, \rv, #0x00012000
 	.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-mv78xx0/rd78x00-masa-setup.c b/arch/arm/mach-mv78xx0/rd78x00-masa-setup.c
index e136b7a..3511ad4 100644
--- a/arch/arm/mach-mv78xx0/rd78x00-masa-setup.c
+++ b/arch/arm/mach-mv78xx0/rd78x00-masa-setup.c
@@ -78,8 +78,6 @@
 
 MACHINE_START(RD78X00_MASA, "Marvell RD-78x00-MASA Development Board")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.phys_io	= MV78XX0_REGS_PHYS_BASE,
-	.io_pg_offst	= ((MV78XX0_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= rd78x00_masa_init,
 	.map_io		= mv78xx0_map_io,
diff --git a/arch/arm/mach-mx25/Kconfig b/arch/arm/mach-mx25/Kconfig
index c71a7bc..aa57e35 100644
--- a/arch/arm/mach-mx25/Kconfig
+++ b/arch/arm/mach-mx25/Kconfig
@@ -12,6 +12,8 @@
 	select IMX_HAVE_PLATFORM_IMX_I2C
 	select IMX_HAVE_PLATFORM_IMX_UART
 	select IMX_HAVE_PLATFORM_MXC_NAND
+	select IMX_HAVE_PLATFORM_FLEXCAN
+	select IMX_HAVE_PLATFORM_ESDHC
 	select MXC_ULPI if USB_ULPI
 
 choice
@@ -20,8 +22,8 @@
 	default MACH_EUKREA_MBIMXSD25_BASEBOARD
 
 config MACH_EUKREA_MBIMXSD25_BASEBOARD
-	prompt "Eukrea MBIMXSD development board"
-	bool
+	bool "Eukrea MBIMXSD development board"
+	select IMX_HAVE_PLATFORM_IMX_SSI
 	help
 	  This adds board specific devices that can be found on Eukrea's
 	  MBIMXSD evaluation board.
diff --git a/arch/arm/mach-mx25/clock.c b/arch/arm/mach-mx25/clock.c
index 40c7cc4..9e4a557 100644
--- a/arch/arm/mach-mx25/clock.c
+++ b/arch/arm/mach-mx25/clock.c
@@ -72,7 +72,7 @@
 	unsigned long rate = get_rate_mpll();
 
 	if (cctl & (1 << 14))
-		rate = (rate * 3) >> 1;
+		rate = (rate * 3) >> 2;
 
 	return rate / ((cctl >> 30) + 1);
 }
@@ -99,7 +99,7 @@
 	if (readl(CRM_BASE + 0x64) & (1 << per))
 		fref = get_rate_upll();
 	else
-		fref = get_rate_ipg(NULL);
+		fref = get_rate_ahb(NULL);
 
 	return fref / (val + 1);
 }
@@ -139,6 +139,16 @@
 	return get_rate_per(7);
 }
 
+static unsigned long get_rate_esdhc1(struct clk *clk)
+{
+	return get_rate_per(3);
+}
+
+static unsigned long get_rate_esdhc2(struct clk *clk)
+{
+	return get_rate_per(4);
+}
+
 static unsigned long get_rate_csi(struct clk *clk)
 {
 	return get_rate_per(0);
@@ -213,6 +223,12 @@
 DEFINE_CLOCK(cspi1_clk,  0, CCM_CGCR1,  5, get_rate_ipg, NULL, NULL);
 DEFINE_CLOCK(cspi2_clk,  0, CCM_CGCR1,  6, get_rate_ipg, NULL, NULL);
 DEFINE_CLOCK(cspi3_clk,  0, CCM_CGCR1,  7, get_rate_ipg, NULL, NULL);
+DEFINE_CLOCK(esdhc1_ahb_clk, 0, CCM_CGCR0, 21, get_rate_esdhc1,	 NULL, NULL);
+DEFINE_CLOCK(esdhc1_per_clk, 0, CCM_CGCR0,  3, get_rate_esdhc1,	 NULL,
+		&esdhc1_ahb_clk);
+DEFINE_CLOCK(esdhc2_ahb_clk, 0, CCM_CGCR0, 22, get_rate_esdhc2,	 NULL, NULL);
+DEFINE_CLOCK(esdhc2_per_clk, 0, CCM_CGCR0,  4, get_rate_esdhc2,	 NULL,
+		&esdhc2_ahb_clk);
 DEFINE_CLOCK(fec_ahb_clk, 0, CCM_CGCR0, 23, NULL,	 NULL, NULL);
 DEFINE_CLOCK(lcdc_ahb_clk, 0, CCM_CGCR0, 24, NULL,	 NULL, NULL);
 DEFINE_CLOCK(lcdc_per_clk, 0, CCM_CGCR0,  7, NULL,	 NULL, &lcdc_ahb_clk);
@@ -238,10 +254,14 @@
 DEFINE_CLOCK(wdt_clk,    0, CCM_CGCR2, 19, get_rate_ipg, NULL,  NULL);
 DEFINE_CLOCK(ssi1_clk,  0, CCM_CGCR2, 11, get_rate_ssi1, NULL, &ssi1_per_clk);
 DEFINE_CLOCK(ssi2_clk,  1, CCM_CGCR2, 12, get_rate_ssi2, NULL, &ssi2_per_clk);
+DEFINE_CLOCK(esdhc1_clk,  0, CCM_CGCR1, 13, get_rate_esdhc1, NULL,
+		&esdhc1_per_clk);
+DEFINE_CLOCK(esdhc2_clk,  1, CCM_CGCR1, 14, get_rate_esdhc2, NULL,
+		&esdhc2_per_clk);
 DEFINE_CLOCK(audmux_clk, 0, CCM_CGCR1, 0, NULL, NULL, NULL);
 DEFINE_CLOCK(csi_clk,    0, CCM_CGCR1,  4, get_rate_csi, NULL,  &csi_per_clk);
 DEFINE_CLOCK(can1_clk,	 0, CCM_CGCR1,  2, get_rate_ipg, NULL, NULL);
-DEFINE_CLOCK(can2_clk,	 0, CCM_CGCR1,  3, get_rate_ipg, NULL, NULL);
+DEFINE_CLOCK(can2_clk,	 1, CCM_CGCR1,  3, get_rate_ipg, NULL, NULL);
 
 #define _REGISTER_CLOCK(d, n, c)	\
 	{				\
@@ -261,9 +281,9 @@
 	_REGISTER_CLOCK("mxc-ehci.2", "usb", usbotg_clk)
 	_REGISTER_CLOCK("fsl-usb2-udc", "usb", usbotg_clk)
 	_REGISTER_CLOCK("mxc_nand.0", NULL, nfc_clk)
-	_REGISTER_CLOCK("spi_imx.0", NULL, cspi1_clk)
-	_REGISTER_CLOCK("spi_imx.1", NULL, cspi2_clk)
-	_REGISTER_CLOCK("spi_imx.2", NULL, cspi3_clk)
+	_REGISTER_CLOCK("imx25-cspi.0", NULL, cspi1_clk)
+	_REGISTER_CLOCK("imx25-cspi.1", NULL, cspi2_clk)
+	_REGISTER_CLOCK("imx25-cspi.2", NULL, cspi3_clk)
 	_REGISTER_CLOCK("mxc_pwm.0", NULL, pwm1_clk)
 	_REGISTER_CLOCK("mxc_pwm.1", NULL, pwm2_clk)
 	_REGISTER_CLOCK("mxc_pwm.2", NULL, pwm3_clk)
@@ -279,6 +299,8 @@
 	_REGISTER_CLOCK("imx-wdt.0", NULL, wdt_clk)
 	_REGISTER_CLOCK("imx-ssi.0", NULL, ssi1_clk)
 	_REGISTER_CLOCK("imx-ssi.1", NULL, ssi2_clk)
+	_REGISTER_CLOCK("sdhci-esdhc-imx.0", NULL, esdhc1_clk)
+	_REGISTER_CLOCK("sdhci-esdhc-imx.1", NULL, esdhc2_clk)
 	_REGISTER_CLOCK("mx2-camera.0", NULL, csi_clk)
 	_REGISTER_CLOCK(NULL, "audmux", audmux_clk)
 	_REGISTER_CLOCK("flexcan.0", NULL, can1_clk)
diff --git a/arch/arm/mach-mx25/devices-imx25.h b/arch/arm/mach-mx25/devices-imx25.h
index d86a7c3..93afa10 100644
--- a/arch/arm/mach-mx25/devices-imx25.h
+++ b/arch/arm/mach-mx25/devices-imx25.h
@@ -9,35 +9,46 @@
 #include <mach/mx25.h>
 #include <mach/devices-common.h>
 
+extern const struct imx_fec_data imx25_fec_data __initconst;
+#define imx25_add_fec(pdata)	\
+	imx_add_fec(&imx25_fec_data, pdata)
+
 #define imx25_add_flexcan0(pdata)	\
 	imx_add_flexcan(0, MX25_CAN1_BASE_ADDR, SZ_16K, MX25_INT_CAN1, pdata)
 #define imx25_add_flexcan1(pdata)	\
 	imx_add_flexcan(1, MX25_CAN2_BASE_ADDR, SZ_16K, MX25_INT_CAN2, pdata)
 
-#define imx25_add_imx_i2c0(pdata)	\
-	imx_add_imx_i2c(0, MX25_I2C1_BASE_ADDR, SZ_16K, MX25_INT_I2C1, pdata)
-#define imx25_add_imx_i2c1(pdata)	\
-	imx_add_imx_i2c(1, MX25_I2C2_BASE_ADDR, SZ_16K, MX25_INT_I2C2, pdata)
-#define imx25_add_imx_i2c2(pdata)	\
-	imx_add_imx_i2c(2, MX25_I2C3_BASE_ADDR, SZ_16K, MX25_INT_I2C3, pdata)
+extern const struct imx_imx_i2c_data imx25_imx_i2c_data[] __initconst;
+#define imx25_add_imx_i2c(id, pdata)	\
+	imx_add_imx_i2c(&imx25_imx_i2c_data[id], pdata)
+#define imx25_add_imx_i2c0(pdata)	imx25_add_imx_i2c(0, pdata)
+#define imx25_add_imx_i2c1(pdata)	imx25_add_imx_i2c(1, pdata)
+#define imx25_add_imx_i2c2(pdata)	imx25_add_imx_i2c(2, pdata)
 
-#define imx25_add_imx_uart0(pdata)	\
-	imx_add_imx_uart_1irq(0, MX25_UART1_BASE_ADDR, SZ_16K, MX25_INT_UART1, pdata)
-#define imx25_add_imx_uart1(pdata)	\
-	imx_add_imx_uart_1irq(1, MX25_UART2_BASE_ADDR, SZ_16K, MX25_INT_UART2, pdata)
-#define imx25_add_imx_uart2(pdata)	\
-	imx_add_imx_uart_1irq(2, MX25_UART3_BASE_ADDR, SZ_16K, MX25_INT_UART3, pdata)
-#define imx25_add_imx_uart3(pdata)	\
-	imx_add_imx_uart_1irq(3, MX25_UART4_BASE_ADDR, SZ_16K, MX25_INT_UART4, pdata)
-#define imx25_add_imx_uart4(pdata)	\
-	imx_add_imx_uart_1irq(4, MX25_UART5_BASE_ADDR, SZ_16K, MX25_INT_UART5, pdata)
+extern const struct imx_imx_ssi_data imx25_imx_ssi_data[] __initconst;
+#define imx25_add_imx_ssi(id, pdata)	\
+	imx_add_imx_ssi(&imx25_imx_ssi_data[id], pdata)
 
+extern const struct imx_imx_uart_1irq_data imx25_imx_uart_data[] __initconst;
+#define imx25_add_imx_uart(id, pdata)	\
+	imx_add_imx_uart_1irq(&imx25_imx_uart_data[id], pdata)
+#define imx25_add_imx_uart0(pdata)	imx25_add_imx_uart(0, pdata)
+#define imx25_add_imx_uart1(pdata)	imx25_add_imx_uart(1, pdata)
+#define imx25_add_imx_uart2(pdata)	imx25_add_imx_uart(2, pdata)
+#define imx25_add_imx_uart3(pdata)	imx25_add_imx_uart(3, pdata)
+#define imx25_add_imx_uart4(pdata)	imx25_add_imx_uart(4, pdata)
+
+extern const struct imx_mxc_nand_data imx25_mxc_nand_data __initconst;
 #define imx25_add_mxc_nand(pdata)	\
-	imx_add_mxc_nand_v21(MX25_NFC_BASE_ADDR, MX25_INT_NANDFC, pdata)
+	imx_add_mxc_nand(&imx25_mxc_nand_data, pdata)
 
-#define imx25_add_spi_imx0(pdata)	\
-	imx_add_spi_imx(0, MX25_CSPI1_BASE_ADDR, SZ_16K, MX25_INT_CSPI1, pdata)
-#define imx25_add_spi_imx1(pdata)	\
-	imx_add_spi_imx(1, MX25_CSPI2_BASE_ADDR, SZ_16K, MX25_INT_CSPI2, pdata)
-#define imx25_add_spi_imx2(pdata)	\
-	imx_add_spi_imx(2, MX25_CSPI3_BASE_ADDR, SZ_16K, MX25_INT_CSPI3, pdata)
+extern const struct imx_spi_imx_data imx25_spi_imx_data[] __initconst;
+#define imx25_add_spi_imx(id, pdata)	\
+	imx_add_spi_imx(&imx25_spi_imx_data[id], pdata)
+#define imx25_add_spi_imx0(pdata)	imx25_add_spi_imx(0, pdata)
+#define imx25_add_spi_imx1(pdata)	imx25_add_spi_imx(1, pdata)
+#define imx25_add_spi_imx2(pdata)	imx25_add_spi_imx(2, pdata)
+
+extern const struct imx_esdhc_imx_data imx25_esdhc_data[] __initconst;
+#define imx25_add_esdhc(id, pdata)	\
+	imx_add_esdhc(&imx25_esdhc_data[id], pdata)
diff --git a/arch/arm/mach-mx25/devices.c b/arch/arm/mach-mx25/devices.c
index 3468eb1..1d0eb3e 100644
--- a/arch/arm/mach-mx25/devices.c
+++ b/arch/arm/mach-mx25/devices.c
@@ -208,26 +208,6 @@
 	return mxc_gpio_init(imx_gpio_ports, ARRAY_SIZE(imx_gpio_ports));
 }
 
-static struct resource mx25_fec_resources[] = {
-	{
-		.start	= MX25_FEC_BASE_ADDR,
-		.end	= MX25_FEC_BASE_ADDR + 0xfff,
-		.flags	= IORESOURCE_MEM,
-	},
-	{
-		.start	= MX25_INT_FEC,
-		.end	= MX25_INT_FEC,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mx25_fec_device = {
-	.name	= "fec",
-	.id	= 0,
-	.num_resources	= ARRAY_SIZE(mx25_fec_resources),
-	.resource	= mx25_fec_resources,
-};
-
 static struct resource mx25_rtc_resources[] = {
 	{
 		.start	= MX25_DRYICE_BASE_ADDR,
@@ -305,44 +285,6 @@
 	.resource	= mx25_kpp_resources,
 };
 
-static struct resource imx_ssi_resources0[] = {
-	{
-		.start	= MX25_SSI1_BASE_ADDR,
-		.end	= MX25_SSI1_BASE_ADDR + 0x3fff,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= MX25_INT_SSI1,
-		.end	= MX25_INT_SSI1,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource imx_ssi_resources1[] = {
-	{
-		.start	= MX25_SSI2_BASE_ADDR,
-		.end	= MX25_SSI2_BASE_ADDR + 0x3fff,
-		.flags	= IORESOURCE_MEM
-	}, {
-		.start	= MX25_INT_SSI2,
-		.end	= MX25_INT_SSI2,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device imx_ssi_device0 = {
-	.name = "imx-ssi",
-	.id = 0,
-	.num_resources = ARRAY_SIZE(imx_ssi_resources0),
-	.resource = imx_ssi_resources0,
-};
-
-struct platform_device imx_ssi_device1 = {
-	.name = "imx-ssi",
-	.id = 1,
-	.num_resources = ARRAY_SIZE(imx_ssi_resources1),
-	.resource = imx_ssi_resources1,
-};
-
 static struct resource mx25_csi_resources[] = {
 	{
 		.start	= MX25_CSI_BASE_ADDR,
diff --git a/arch/arm/mach-mx25/devices.h b/arch/arm/mach-mx25/devices.h
index 4aceb68..7b70a43 100644
--- a/arch/arm/mach-mx25/devices.h
+++ b/arch/arm/mach-mx25/devices.h
@@ -6,11 +6,8 @@
 extern struct platform_device mxc_pwm_device2;
 extern struct platform_device mxc_pwm_device3;
 extern struct platform_device mxc_keypad_device;
-extern struct platform_device mx25_fec_device;
 extern struct platform_device mx25_rtc_device;
 extern struct platform_device mx25_fb_device;
 extern struct platform_device mxc_wdt;
 extern struct platform_device mx25_kpp_device;
-extern struct platform_device imx_ssi_device0;
-extern struct platform_device imx_ssi_device1;
 extern struct platform_device mx25_csi_device;
diff --git a/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c b/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c
index 4aaadc7..e765ac5 100644
--- a/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c
+++ b/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c
@@ -34,7 +34,6 @@
 #include <mach/mx25.h>
 #include <mach/imx-uart.h>
 #include <mach/imxfb.h>
-#include <mach/ssi.h>
 #include <mach/audmux.h>
 
 #include "devices-imx25.h"
@@ -90,6 +89,9 @@
 	MX25_PAD_KPP_COL2__AUD5_TXC,
 	MX25_PAD_KPP_COL1__AUD5_RXD,
 	MX25_PAD_KPP_COL0__AUD5_TXD,
+	/* CAN */
+	MX25_PAD_GPIO_D__CAN2_RX,
+	MX25_PAD_GPIO_C__CAN2_TX,
 };
 
 #define GPIO_LED1	83
@@ -114,6 +116,38 @@
 		},
 		.bpp	= 16,
 		.pcr	= 0xCAD08B80,
+	}, {
+		.mode = {
+			.name		= "DVI-VGA",
+			.refresh	= 60,
+			.xres		= 640,
+			.yres		= 480,
+			.pixclock	= 32000,
+			.hsync_len	= 7,
+			.left_margin	= 100,
+			.right_margin	= 100,
+			.vsync_len	= 7,
+			.upper_margin	= 7,
+			.lower_margin	= 100,
+		},
+		.pcr		= 0xFA208B80,
+		.bpp		= 16,
+	}, {
+		.mode = {
+			.name		= "DVI-SVGA",
+			.refresh	= 60,
+			.xres		= 800,
+			.yres		= 600,
+			.pixclock	= 25000,
+			.hsync_len	= 7,
+			.left_margin	= 75,
+			.right_margin	= 75,
+			.vsync_len	= 7,
+			.upper_margin	= 7,
+			.lower_margin	= 75,
+		},
+		.pcr		= 0xFA208B80,
+		.bpp		= 16,
 	},
 };
 
@@ -205,7 +239,8 @@
 	},
 };
 
-struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata = {
+static const
+struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata __initconst = {
 	.flags = IMX_SSI_SYN | IMX_SSI_NET | IMX_SSI_USE_I2S_SLAVE,
 };
 
@@ -239,7 +274,10 @@
 
 	imx25_add_imx_uart1(&uart_pdata);
 	mxc_register_device(&mx25_fb_device, &eukrea_mximxsd_fb_pdata);
-	mxc_register_device(&imx_ssi_device0, &eukrea_mbimxsd_ssi_pdata);
+	imx25_add_imx_ssi(0, &eukrea_mbimxsd_ssi_pdata);
+
+	imx25_add_flexcan1(NULL);
+	imx25_add_esdhc(0, NULL);
 
 	gpio_request(GPIO_LED1, "LED1");
 	gpio_direction_output(GPIO_LED1, 1);
diff --git a/arch/arm/mach-mx25/mach-cpuimx25.c b/arch/arm/mach-mx25/mach-cpuimx25.c
index e064bb3..f6f9ad6 100644
--- a/arch/arm/mach-mx25/mach-cpuimx25.c
+++ b/arch/arm/mach-mx25/mach-cpuimx25.c
@@ -23,7 +23,6 @@
 #include <linux/clk.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
-#include <linux/fec.h>
 #include <linux/platform_device.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
@@ -41,7 +40,6 @@
 #include <mach/mxc_nand.h>
 #include <mach/imxfb.h>
 #include <mach/mxc_ehci.h>
-#include <mach/ulpi.h>
 #include <mach/iomux-mx25.h>
 
 #include "devices-imx25.h"
@@ -67,7 +65,7 @@
 	MX25_PAD_I2C1_DAT__I2C1_DAT,
 };
 
-static struct fec_platform_data mx25_fec_pdata = {
+static const struct fec_platform_data mx25_fec_pdata __initconst = {
 	.phy	= PHY_INTERFACE_MODE_RMII,
 };
 
@@ -129,24 +127,19 @@
 	imx25_add_imx_uart0(&uart_pdata);
 	imx25_add_mxc_nand(&eukrea_cpuimx25_nand_board_info);
 	mxc_register_device(&mx25_rtc_device, NULL);
-	mxc_register_device(&mx25_fec_device, &mx25_fec_pdata);
+	imx25_add_fec(&mx25_fec_pdata);
 
 	i2c_register_board_info(0, eukrea_cpuimx25_i2c_devices,
 				ARRAY_SIZE(eukrea_cpuimx25_i2c_devices));
 	imx25_add_imx_i2c0(&eukrea_cpuimx25_i2c0_data);
 
-#if defined(CONFIG_USB_ULPI)
-	if (otg_mode_host) {
-		otg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops,
-				ULPI_OTG_DRVVBUS | ULPI_OTG_DRVVBUS_EXT);
-
+	if (otg_mode_host)
 		mxc_register_device(&mxc_otg, &otg_pdata);
-	}
-	mxc_register_device(&mxc_usbh2, &usbh2_pdata);
-#endif
-	if (!otg_mode_host)
+	else
 		mxc_register_device(&otg_udc_device, &otg_device_pdata);
 
+	mxc_register_device(&mxc_usbh2, &usbh2_pdata);
+
 #ifdef CONFIG_MACH_EUKREA_MBIMXSD25_BASEBOARD
 	eukrea_mbimxsd25_baseboard_init();
 #endif
@@ -163,8 +156,6 @@
 
 MACHINE_START(EUKREA_CPUIMX25, "Eukrea CPUIMX25")
 	/* Maintainer: Eukrea Electromatique */
-	.phys_io	= MX25_AIPS1_BASE_ADDR,
-	.io_pg_offst	= ((MX25_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX25_PHYS_OFFSET + 0x100,
 	.map_io         = mx25_map_io,
 	.init_irq       = mx25_init_irq,
diff --git a/arch/arm/mach-mx25/mach-mx25_3ds.c b/arch/arm/mach-mx25/mach-mx25_3ds.c
index 62bc21f..8080510 100644
--- a/arch/arm/mach-mx25/mach-mx25_3ds.c
+++ b/arch/arm/mach-mx25/mach-mx25_3ds.c
@@ -28,7 +28,6 @@
 #include <linux/clk.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
-#include <linux/fec.h>
 #include <linux/platform_device.h>
 #include <linux/input/matrix_keypad.h>
 
@@ -99,7 +98,7 @@
 	MX25_PAD_KPP_COL3__KPP_COL3,
 };
 
-static struct fec_platform_data mx25_fec_pdata = {
+static const struct fec_platform_data mx25_fec_pdata __initconst = {
         .phy    = PHY_INTERFACE_MODE_RMII,
 };
 
@@ -192,7 +191,7 @@
 	mxc_register_device(&mxc_wdt, NULL);
 
 	mx25pdk_fec_reset();
-	mxc_register_device(&mx25_fec_device, &mx25_fec_pdata);
+	imx25_add_fec(&mx25_fec_pdata);
 	mxc_register_device(&mx25_kpp_device, &mx25pdk_keymap_data);
 }
 
@@ -207,8 +206,6 @@
 
 MACHINE_START(MX25_3DS, "Freescale MX25PDK (3DS)")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.phys_io	= MX25_AIPS1_BASE_ADDR,
-	.io_pg_offst	= ((MX25_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX25_PHYS_OFFSET + 0x100,
 	.map_io         = mx25_map_io,
 	.init_irq       = mx25_init_irq,
diff --git a/arch/arm/mach-mx3/Kconfig b/arch/arm/mach-mx3/Kconfig
index 85beece..096fd33 100644
--- a/arch/arm/mach-mx3/Kconfig
+++ b/arch/arm/mach-mx3/Kconfig
@@ -9,6 +9,7 @@
 	bool
 	select ARCH_MXC_IOMUX_V3
 	select ARCH_MXC_AUDMUX_V2
+	select HAVE_EPIT
 
 comment "MX3 platforms:"
 
@@ -16,6 +17,7 @@
 	bool "Support MX31ADS platforms"
 	select ARCH_MX31
 	select IMX_HAVE_PLATFORM_IMX_I2C
+	select IMX_HAVE_PLATFORM_IMX_SSI
 	select IMX_HAVE_PLATFORM_IMX_UART
 	default y
 	help
@@ -117,9 +119,11 @@
 	bool "Support Phytec pcm043 (i.MX35) platforms"
 	select ARCH_MX35
 	select IMX_HAVE_PLATFORM_IMX_I2C
+	select IMX_HAVE_PLATFORM_IMX_SSI
 	select IMX_HAVE_PLATFORM_IMX_UART
 	select IMX_HAVE_PLATFORM_MXC_NAND
 	select IMX_HAVE_PLATFORM_FLEXCAN
+	select IMX_HAVE_PLATFORM_ESDHC
 	select MXC_ULPI if USB_ULPI
 	help
 	  Include support for Phytec pcm043 platform. This includes
@@ -140,6 +144,7 @@
 	bool "Support MX35PDK platform"
 	select ARCH_MX35
 	select IMX_HAVE_PLATFORM_IMX_UART
+	select IMX_HAVE_PLATFORM_MXC_NAND
 	default n
 	help
 	  Include support for MX35PDK platform. This includes specific
@@ -159,6 +164,8 @@
 	select IMX_HAVE_PLATFORM_IMX_UART
 	select IMX_HAVE_PLATFORM_IMX_I2C
 	select IMX_HAVE_PLATFORM_MXC_NAND
+	select IMX_HAVE_PLATFORM_FLEXCAN
+	select IMX_HAVE_PLATFORM_ESDHC
 	select MXC_ULPI if USB_ULPI
 	help
 	  Include support for Eukrea CPUIMX35 platform. This includes
@@ -170,8 +177,8 @@
 	default MACH_EUKREA_MBIMXSD35_BASEBOARD
 
 config MACH_EUKREA_MBIMXSD35_BASEBOARD
-	prompt "Eukrea MBIMXSD development board"
-	bool
+	bool "Eukrea MBIMXSD development board"
+	select IMX_HAVE_PLATFORM_IMX_SSI
 	help
 	  This adds board specific devices that can be found on Eukrea's
 	  MBIMXSD evaluation board.
diff --git a/arch/arm/mach-mx3/Makefile b/arch/arm/mach-mx3/Makefile
index 2bd7bec..8a182d0a 100644
--- a/arch/arm/mach-mx3/Makefile
+++ b/arch/arm/mach-mx3/Makefile
@@ -7,7 +7,6 @@
 obj-y				:= mm.o devices.o cpu.o
 CFLAGS_mm.o = -DIMX_NEEDS_DEPRECATED_SYMBOLS
 CFLAGS_devices.o = -DIMX_NEEDS_DEPRECATED_SYMBOLS
-CFLAGS_cpu.o = -DIMX_NEEDS_DEPRECATED_SYMBOLS
 obj-$(CONFIG_ARCH_MX31)		+= clock-imx31.o iomux-imx31.o
 obj-$(CONFIG_ARCH_MX35)		+= clock-imx35.o
 obj-$(CONFIG_MACH_MX31ADS)	+= mach-mx31ads.o
diff --git a/arch/arm/mach-mx3/clock-imx31.c b/arch/arm/mach-mx3/clock-imx31.c
index 9a9eb6d..109e98f 100644
--- a/arch/arm/mach-mx3/clock-imx31.c
+++ b/arch/arm/mach-mx3/clock-imx31.c
@@ -477,7 +477,7 @@
 DEFINE_CLOCK(epit2_clk,   1, MXC_CCM_CGR0,  8, NULL, NULL, &perclk_clk);
 DEFINE_CLOCK(iim_clk,     0, MXC_CCM_CGR0, 10, NULL, NULL, &ipg_clk);
 DEFINE_CLOCK(ata_clk,     0, MXC_CCM_CGR0, 12, NULL, NULL, &ipg_clk);
-DEFINE_CLOCK(sdma_clk1,   0, MXC_CCM_CGR0, 14, NULL, &sdma_clk1, &ahb_clk);
+DEFINE_CLOCK(sdma_clk1,   0, MXC_CCM_CGR0, 14, NULL, NULL, &ahb_clk);
 DEFINE_CLOCK(cspi3_clk,   2, MXC_CCM_CGR0, 16, NULL, NULL, &ipg_clk);
 DEFINE_CLOCK(rng_clk,     0, MXC_CCM_CGR0, 18, NULL, NULL, &ipg_clk);
 DEFINE_CLOCK(uart1_clk,   0, MXC_CCM_CGR0, 20, NULL, NULL, &perclk_clk);
@@ -525,9 +525,9 @@
 
 static struct clk_lookup lookups[] = {
 	_REGISTER_CLOCK(NULL, "emi", emi_clk)
-	_REGISTER_CLOCK("spi_imx.0", NULL, cspi1_clk)
-	_REGISTER_CLOCK("spi_imx.1", NULL, cspi2_clk)
-	_REGISTER_CLOCK("spi_imx.2", NULL, cspi3_clk)
+	_REGISTER_CLOCK("imx31-cspi.0", NULL, cspi1_clk)
+	_REGISTER_CLOCK("imx31-cspi.1", NULL, cspi2_clk)
+	_REGISTER_CLOCK("imx31-cspi.2", NULL, cspi3_clk)
 	_REGISTER_CLOCK(NULL, "gpt", gpt_clk)
 	_REGISTER_CLOCK(NULL, "pwm", pwm_clk)
 	_REGISTER_CLOCK("imx-wdt.0", NULL, wdog_clk)
@@ -564,7 +564,7 @@
 	_REGISTER_CLOCK(NULL, "ata", ata_clk)
 	_REGISTER_CLOCK(NULL, "rtic", rtic_clk)
 	_REGISTER_CLOCK(NULL, "rng", rng_clk)
-	_REGISTER_CLOCK(NULL, "sdma_ahb", sdma_clk1)
+	_REGISTER_CLOCK("imx-sdma", NULL, sdma_clk1)
 	_REGISTER_CLOCK(NULL, "sdma_ipg", sdma_clk2)
 	_REGISTER_CLOCK(NULL, "mstick", mstick1_clk)
 	_REGISTER_CLOCK(NULL, "mstick", mstick2_clk)
diff --git a/arch/arm/mach-mx3/clock-imx35.c b/arch/arm/mach-mx3/clock-imx35.c
index 7a62e74..61e4a31 100644
--- a/arch/arm/mach-mx3/clock-imx35.c
+++ b/arch/arm/mach-mx3/clock-imx35.c
@@ -364,8 +364,8 @@
 DEFINE_CLOCK(ect_clk,    0, CCM_CGR0, 14, get_rate_ipg, NULL);
 DEFINE_CLOCK(edio_clk,   0, CCM_CGR0, 16, NULL, NULL);
 DEFINE_CLOCK(emi_clk,    0, CCM_CGR0, 18, get_rate_ipg, NULL);
-DEFINE_CLOCK(epit1_clk,  0, CCM_CGR0, 20, get_rate_ipg_per, NULL);
-DEFINE_CLOCK(epit2_clk,  1, CCM_CGR0, 22, get_rate_ipg_per, NULL);
+DEFINE_CLOCK(epit1_clk,  0, CCM_CGR0, 20, get_rate_ipg, NULL);
+DEFINE_CLOCK(epit2_clk,  1, CCM_CGR0, 22, get_rate_ipg, NULL);
 DEFINE_CLOCK(esai_clk,   0, CCM_CGR0, 24, NULL, NULL);
 DEFINE_CLOCK(esdhc1_clk, 0, CCM_CGR0, 26, get_rate_sdhc, NULL);
 DEFINE_CLOCK(esdhc2_clk, 1, CCM_CGR0, 28, get_rate_sdhc, NULL);
@@ -451,17 +451,17 @@
 	_REGISTER_CLOCK(NULL, "ata", ata_clk)
 	_REGISTER_CLOCK("flexcan.0", NULL, can1_clk)
 	_REGISTER_CLOCK("flexcan.1", NULL, can2_clk)
-	_REGISTER_CLOCK("spi_imx.0", NULL, cspi1_clk)
-	_REGISTER_CLOCK("spi_imx.1", NULL, cspi2_clk)
+	_REGISTER_CLOCK("imx35-cspi.0", NULL, cspi1_clk)
+	_REGISTER_CLOCK("imx35-cspi.1", NULL, cspi2_clk)
 	_REGISTER_CLOCK(NULL, "ect", ect_clk)
 	_REGISTER_CLOCK(NULL, "edio", edio_clk)
 	_REGISTER_CLOCK(NULL, "emi", emi_clk)
-	_REGISTER_CLOCK(NULL, "epit", epit1_clk)
-	_REGISTER_CLOCK(NULL, "epit", epit2_clk)
+	_REGISTER_CLOCK("imx-epit.0", NULL, epit1_clk)
+	_REGISTER_CLOCK("imx-epit.1", NULL, epit2_clk)
 	_REGISTER_CLOCK(NULL, "esai", esai_clk)
-	_REGISTER_CLOCK(NULL, "sdhc", esdhc1_clk)
-	_REGISTER_CLOCK(NULL, "sdhc", esdhc2_clk)
-	_REGISTER_CLOCK(NULL, "sdhc", esdhc3_clk)
+	_REGISTER_CLOCK("sdhci-esdhc-imx.0", NULL, esdhc1_clk)
+	_REGISTER_CLOCK("sdhci-esdhc-imx.1", NULL, esdhc2_clk)
+	_REGISTER_CLOCK("sdhci-esdhc-imx.2", NULL, esdhc3_clk)
 	_REGISTER_CLOCK("fec.0", NULL, fec_clk)
 	_REGISTER_CLOCK(NULL, "gpio", gpio1_clk)
 	_REGISTER_CLOCK(NULL, "gpio", gpio2_clk)
@@ -482,7 +482,7 @@
 	_REGISTER_CLOCK(NULL, "rtc", rtc_clk)
 	_REGISTER_CLOCK(NULL, "rtic", rtic_clk)
 	_REGISTER_CLOCK(NULL, "scc", scc_clk)
-	_REGISTER_CLOCK(NULL, "sdma", sdma_clk)
+	_REGISTER_CLOCK("imx-sdma", NULL, sdma_clk)
 	_REGISTER_CLOCK(NULL, "spba", spba_clk)
 	_REGISTER_CLOCK(NULL, "spdif", spdif_clk)
 	_REGISTER_CLOCK("imx-ssi.0", NULL, ssi1_clk)
@@ -535,8 +535,16 @@
 	__raw_writel(cgr2, CCM_BASE + CCM_CGR2);
 	__raw_writel(cgr3, CCM_BASE + CCM_CGR3);
 
+	clk_enable(&iim_clk);
+	mx35_read_cpu_rev();
+
+#ifdef CONFIG_MXC_USE_EPIT
+	epit_timer_init(&epit1_clk,
+			MX35_IO_ADDRESS(MX35_EPIT1_BASE_ADDR), MX35_INT_EPIT1);
+#else
 	mxc_timer_init(&gpt_clk,
 			MX35_IO_ADDRESS(MX35_GPT1_BASE_ADDR), MX35_INT_GPT);
+#endif
 
 	return 0;
 }
diff --git a/arch/arm/mach-mx3/cpu.c b/arch/arm/mach-mx3/cpu.c
index 861afe0..d00a754 100644
--- a/arch/arm/mach-mx3/cpu.c
+++ b/arch/arm/mach-mx3/cpu.c
@@ -25,15 +25,15 @@
 };
 
 static struct mx3_cpu_type mx31_cpu_type[] __initdata = {
-	{ .srev = 0x00, .name = "i.MX31(L)", .v = "1.0",  .rev = CHIP_REV_1_0	},
-	{ .srev = 0x10, .name = "i.MX31",    .v = "1.1",  .rev = CHIP_REV_1_1	},
-	{ .srev = 0x11, .name = "i.MX31L",   .v = "1.1",  .rev = CHIP_REV_1_1	},
-	{ .srev = 0x12, .name = "i.MX31",    .v = "1.15", .rev = CHIP_REV_1_1	},
-	{ .srev = 0x13, .name = "i.MX31L",   .v = "1.15", .rev = CHIP_REV_1_1	},
-	{ .srev = 0x14, .name = "i.MX31",    .v = "1.2",  .rev = CHIP_REV_1_2	},
-	{ .srev = 0x15, .name = "i.MX31L",   .v = "1.2",  .rev = CHIP_REV_1_2	},
-	{ .srev = 0x28, .name = "i.MX31",    .v = "2.0",  .rev = CHIP_REV_2_0	},
-	{ .srev = 0x29, .name = "i.MX31L",   .v = "2.0",  .rev = CHIP_REV_2_0	},
+	{ .srev = 0x00, .name = "i.MX31(L)", .v = "1.0",  .rev = MX3x_CHIP_REV_1_0 },
+	{ .srev = 0x10, .name = "i.MX31",    .v = "1.1",  .rev = MX3x_CHIP_REV_1_1 },
+	{ .srev = 0x11, .name = "i.MX31L",   .v = "1.1",  .rev = MX3x_CHIP_REV_1_1 },
+	{ .srev = 0x12, .name = "i.MX31",    .v = "1.15", .rev = MX3x_CHIP_REV_1_1 },
+	{ .srev = 0x13, .name = "i.MX31L",   .v = "1.15", .rev = MX3x_CHIP_REV_1_1 },
+	{ .srev = 0x14, .name = "i.MX31",    .v = "1.2",  .rev = MX3x_CHIP_REV_1_2 },
+	{ .srev = 0x15, .name = "i.MX31L",   .v = "1.2",  .rev = MX3x_CHIP_REV_1_2 },
+	{ .srev = 0x28, .name = "i.MX31",    .v = "2.0",  .rev = MX3x_CHIP_REV_2_0 },
+	{ .srev = 0x29, .name = "i.MX31L",   .v = "2.0",  .rev = MX3x_CHIP_REV_2_0 },
 };
 
 void __init mx31_read_cpu_rev(void)
@@ -41,7 +41,7 @@
 	u32 i, srev;
 
 	/* read SREV register from IIM module */
-	srev = __raw_readl(IO_ADDRESS(IIM_BASE_ADDR + MXC_IIMSREV));
+	srev = __raw_readl(MX31_IO_ADDRESS(MX31_IIM_BASE_ADDR + MXC_IIMSREV));
 
 	for (i = 0; i < ARRAY_SIZE(mx31_cpu_type); i++)
 		if (srev == mx31_cpu_type[i].srev) {
@@ -55,3 +55,30 @@
 
 	printk(KERN_WARNING "Unknown CPU identifier. srev = %02x\n", srev);
 }
+
+unsigned int mx35_cpu_rev;
+EXPORT_SYMBOL(mx35_cpu_rev);
+
+void __init mx35_read_cpu_rev(void)
+{
+	u32 rev;
+	char *srev = "unknown";
+
+	rev = __raw_readl(MX35_IO_ADDRESS(MX35_IIM_BASE_ADDR + MXC_IIMSREV));
+	switch (rev) {
+	case 0x00:
+		mx35_cpu_rev = MX3x_CHIP_REV_1_0;
+		srev = "1.0";
+		break;
+	case 0x10:
+		mx35_cpu_rev = MX3x_CHIP_REV_2_0;
+		srev = "2.0";
+		break;
+	case 0x11:
+		mx35_cpu_rev = MX3x_CHIP_REV_2_1;
+		srev = "2.1";
+		break;
+	}
+
+	printk(KERN_INFO "CPU identified as i.MX35, silicon rev %s\n", srev);
+}
diff --git a/arch/arm/mach-mx3/devices-imx31.h b/arch/arm/mach-mx3/devices-imx31.h
index 3b1a44a..de95985 100644
--- a/arch/arm/mach-mx3/devices-imx31.h
+++ b/arch/arm/mach-mx3/devices-imx31.h
@@ -9,30 +9,33 @@
 #include <mach/mx31.h>
 #include <mach/devices-common.h>
 
-#define imx31_add_imx_i2c0(pdata)	\
-	imx_add_imx_i2c(0, MX31_I2C1_BASE_ADDR, SZ_4K, MX31_INT_I2C1, pdata)
-#define imx31_add_imx_i2c1(pdata)	\
-	imx_add_imx_i2c(1, MX31_I2C2_BASE_ADDR, SZ_4K, MX31_INT_I2C2, pdata)
-#define imx31_add_imx_i2c2(pdata)	\
-	imx_add_imx_i2c(2, MX31_I2C3_BASE_ADDR, SZ_4K, MX31_INT_I2C3, pdata)
+extern const struct imx_imx_i2c_data imx31_imx_i2c_data[] __initconst;
+#define imx31_add_imx_i2c(id, pdata)	\
+	imx_add_imx_i2c(&imx31_imx_i2c_data[id], pdata)
+#define imx31_add_imx_i2c0(pdata)	imx31_add_imx_i2c(0, pdata)
+#define imx31_add_imx_i2c1(pdata)	imx31_add_imx_i2c(1, pdata)
+#define imx31_add_imx_i2c2(pdata)	imx31_add_imx_i2c(2, pdata)
 
-#define imx31_add_imx_uart0(pdata)	\
-	imx_add_imx_uart_1irq(0, MX31_UART1_BASE_ADDR, SZ_16K, MX31_INT_UART1, pdata)
-#define imx31_add_imx_uart1(pdata)	\
-	imx_add_imx_uart_1irq(1, MX31_UART2_BASE_ADDR, SZ_16K, MX31_INT_UART2, pdata)
-#define imx31_add_imx_uart2(pdata)	\
-	imx_add_imx_uart_1irq(2, MX31_UART3_BASE_ADDR, SZ_16K, MX31_INT_UART3, pdata)
-#define imx31_add_imx_uart3(pdata)	\
-	imx_add_imx_uart_1irq(3, MX31_UART4_BASE_ADDR, SZ_16K, MX31_INT_UART4, pdata)
-#define imx31_add_imx_uart4(pdata)	\
-	imx_add_imx_uart_1irq(4, MX31_UART5_BASE_ADDR, SZ_16K, MX31_INT_UART5, pdata)
+extern const struct imx_imx_ssi_data imx31_imx_ssi_data[] __initconst;
+#define imx31_add_imx_ssi(id, pdata)    \
+	imx_add_imx_ssi(&imx31_imx_ssi_data[id], pdata)
 
+extern const struct imx_imx_uart_1irq_data imx31_imx_uart_data[] __initconst;
+#define imx31_add_imx_uart(id, pdata)	\
+	imx_add_imx_uart_1irq(&imx31_imx_uart_data[id], pdata)
+#define imx31_add_imx_uart0(pdata)	imx31_add_imx_uart(0, pdata)
+#define imx31_add_imx_uart1(pdata)	imx31_add_imx_uart(1, pdata)
+#define imx31_add_imx_uart2(pdata)	imx31_add_imx_uart(2, pdata)
+#define imx31_add_imx_uart3(pdata)	imx31_add_imx_uart(3, pdata)
+#define imx31_add_imx_uart4(pdata)	imx31_add_imx_uart(4, pdata)
+
+extern const struct imx_mxc_nand_data imx31_mxc_nand_data __initconst;
 #define imx31_add_mxc_nand(pdata)	\
-	imx_add_mxc_nand_v1(MX31_NFC_BASE_ADDR, MX31_INT_NANDFC, pdata)
+	imx_add_mxc_nand(&imx31_mxc_nand_data, pdata)
 
-#define imx31_add_spi_imx0(pdata)	\
-	imx_add_spi_imx(0, MX31_CSPI1_BASE_ADDR, SZ_4K, MX31_INT_CSPI1, pdata)
-#define imx31_add_spi_imx1(pdata)	\
-	imx_add_spi_imx(1, MX31_CSPI2_BASE_ADDR, SZ_4K, MX31_INT_CSPI2, pdata)
-#define imx31_add_spi_imx2(pdata)	\
-	imx_add_spi_imx(2, MX31_CSPI3_BASE_ADDR, SZ_4K, MX31_INT_CSPI3, pdata)
+extern const struct imx_spi_imx_data imx31_cspi_data[] __initconst;
+#define imx31_add_cspi(id, pdata)	\
+	imx_add_spi_imx(&imx31_cspi_data[id], pdata)
+#define imx31_add_spi_imx0(pdata)	imx31_add_cspi(0, pdata)
+#define imx31_add_spi_imx1(pdata)	imx31_add_cspi(1, pdata)
+#define imx31_add_spi_imx2(pdata)	imx31_add_cspi(2, pdata)
diff --git a/arch/arm/mach-mx3/devices-imx35.h b/arch/arm/mach-mx3/devices-imx35.h
index f6a431a..5eb917b 100644
--- a/arch/arm/mach-mx3/devices-imx35.h
+++ b/arch/arm/mach-mx3/devices-imx35.h
@@ -9,29 +9,43 @@
 #include <mach/mx35.h>
 #include <mach/devices-common.h>
 
+extern const struct imx_fec_data imx35_fec_data __initconst;
+#define imx35_add_fec(pdata)	\
+	imx_add_fec(&imx35_fec_data, pdata)
+
 #define imx35_add_flexcan0(pdata)	\
 	imx_add_flexcan(0, MX35_CAN1_BASE_ADDR, SZ_16K, MX35_INT_CAN1, pdata)
 #define imx35_add_flexcan1(pdata)	\
 	imx_add_flexcan(1, MX35_CAN2_BASE_ADDR, SZ_16K, MX35_INT_CAN2, pdata)
 
-#define imx35_add_imx_i2c0(pdata)	\
-	imx_add_imx_i2c(0, MX35_I2C1_BASE_ADDR, SZ_4K, MX35_INT_I2C1, pdata)
-#define imx35_add_imx_i2c1(pdata)	\
-	imx_add_imx_i2c(1, MX35_I2C2_BASE_ADDR, SZ_4K, MX35_INT_I2C2, pdata)
-#define imx35_add_imx_i2c2(pdata)	\
-	imx_add_imx_i2c(2, MX35_I2C3_BASE_ADDR, SZ_4K, MX35_INT_I2C3, pdata)
+extern const struct imx_imx_i2c_data imx35_imx_i2c_data[] __initconst;
+#define imx35_add_imx_i2c(id, pdata)	\
+	imx_add_imx_i2c(&imx35_imx_i2c_data[id], pdata)
+#define imx35_add_imx_i2c0(pdata)	imx35_add_imx_i2c(0, pdata)
+#define imx35_add_imx_i2c1(pdata)	imx35_add_imx_i2c(1, pdata)
+#define imx35_add_imx_i2c2(pdata)	imx35_add_imx_i2c(2, pdata)
 
-#define imx35_add_imx_uart0(pdata)	\
-	imx_add_imx_uart_1irq(0, MX35_UART1_BASE_ADDR, SZ_16K, MX35_INT_UART1, pdata)
-#define imx35_add_imx_uart1(pdata)	\
-	imx_add_imx_uart_1irq(1, MX35_UART2_BASE_ADDR, SZ_16K, MX35_INT_UART2, pdata)
-#define imx35_add_imx_uart2(pdata)	\
-	imx_add_imx_uart_1irq(2, MX35_UART3_BASE_ADDR, SZ_16K, MX35_INT_UART3, pdata)
+extern const struct imx_imx_ssi_data imx35_imx_ssi_data[] __initconst;
+#define imx35_add_imx_ssi(id, pdata)    \
+	imx_add_imx_ssi(&imx35_imx_ssi_data[id], pdata)
 
+extern const struct imx_imx_uart_1irq_data imx35_imx_uart_data[] __initconst;
+#define imx35_add_imx_uart(id, pdata)	\
+	imx_add_imx_uart_1irq(&imx35_imx_uart_data[id], pdata)
+#define imx35_add_imx_uart0(pdata)	imx35_add_imx_uart(0, pdata)
+#define imx35_add_imx_uart1(pdata)	imx35_add_imx_uart(1, pdata)
+#define imx35_add_imx_uart2(pdata)	imx35_add_imx_uart(2, pdata)
+
+extern const struct imx_mxc_nand_data imx35_mxc_nand_data __initconst;
 #define imx35_add_mxc_nand(pdata)	\
-	imx_add_mxc_nand_v21(MX35_NFC_BASE_ADDR, MX35_INT_NANDFC, pdata)
+	imx_add_mxc_nand(&imx35_mxc_nand_data, pdata)
 
-#define imx35_add_spi_imx0(pdata)	\
-	imx_add_spi_imx(0, MX35_CSPI1_BASE_ADDR, SZ_4K, MX35_INT_CSPI1, pdata)
-#define imx35_add_spi_imx1(pdata)	\
-	imx_add_spi_imx(1, MX35_CSPI2_BASE_ADDR, SZ_4K, MX35_INT_CSPI2, pdata)
+extern const struct imx_spi_imx_data imx35_cspi_data[] __initconst;
+#define imx35_add_cspi(id, pdata)	\
+	imx_add_spi_imx(&imx35_cspi_data[id], pdata)
+#define imx35_add_spi_imx0(pdata)	imx35_add_cspi(0, pdata)
+#define imx35_add_spi_imx1(pdata)	imx35_add_cspi(1, pdata)
+
+extern const struct imx_esdhc_imx_data imx35_esdhc_data[] __initconst;
+#define imx35_add_esdhc(id, pdata)	\
+	imx_add_esdhc(&imx35_esdhc_data[id], pdata)
diff --git a/arch/arm/mach-mx3/devices.c b/arch/arm/mach-mx3/devices.c
index a4fd1a2..f4dff11 100644
--- a/arch/arm/mach-mx3/devices.c
+++ b/arch/arm/mach-mx3/devices.c
@@ -281,65 +281,6 @@
 	.num_resources = ARRAY_SIZE(mxc_usbh2_resources),
 };
 
-#if defined(CONFIG_ARCH_MX35)
-static struct resource mxc_fec_resources[] = {
-	{
-		.start	= MXC_FEC_BASE_ADDR,
-		.end	= MXC_FEC_BASE_ADDR + 0xfff,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= MXC_INT_FEC,
-		.end	= MXC_INT_FEC,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mxc_fec_device = {
-	.name = "fec",
-	.id = 0,
-	.num_resources = ARRAY_SIZE(mxc_fec_resources),
-	.resource = mxc_fec_resources,
-};
-#endif
-
-static struct resource imx_ssi_resources0[] = {
-	{
-		.start	= SSI1_BASE_ADDR,
-		.end	= SSI1_BASE_ADDR + 0xfff,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= MX31_INT_SSI1,
-		.end	= MX31_INT_SSI1,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource imx_ssi_resources1[] = {
-	{
-		.start	= SSI2_BASE_ADDR,
-		.end	= SSI2_BASE_ADDR + 0xfff,
-		.flags	= IORESOURCE_MEM
-	}, {
-		.start	= MX31_INT_SSI2,
-		.end	= MX31_INT_SSI2,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device imx_ssi_device0 = {
-	.name = "imx-ssi",
-	.id = 0,
-	.num_resources = ARRAY_SIZE(imx_ssi_resources0),
-	.resource = imx_ssi_resources0,
-};
-
-struct platform_device imx_ssi_device1 = {
-	.name = "imx-ssi",
-	.id = 1,
-	.num_resources = ARRAY_SIZE(imx_ssi_resources1),
-	.resource = imx_ssi_resources1,
-};
-
 static struct resource imx_wdt_resources[] = {
 	{
 		.flags = IORESOURCE_MEM,
@@ -410,10 +351,6 @@
 		mxc_usbh1_resources[0].end = MX35_OTG_BASE_ADDR + 0x5ff;
 		mxc_usbh1_resources[1].start = MXC_INT_USBHS;
 		mxc_usbh1_resources[1].end = MXC_INT_USBHS;
-		imx_ssi_resources0[1].start = MX35_INT_SSI1;
-		imx_ssi_resources0[1].end = MX35_INT_SSI1;
-		imx_ssi_resources1[1].start = MX35_INT_SSI2;
-		imx_ssi_resources1[1].end = MX35_INT_SSI2;
 		imx_wdt_resources[0].start = MX35_WDOG_BASE_ADDR;
 		imx_wdt_resources[0].end = MX35_WDOG_BASE_ADDR + 0x3fff;
 	}
diff --git a/arch/arm/mach-mx3/devices.h b/arch/arm/mach-mx3/devices.h
index e553523..585f814 100644
--- a/arch/arm/mach-mx3/devices.h
+++ b/arch/arm/mach-mx3/devices.h
@@ -2,7 +2,6 @@
 extern struct platform_device mx3_ipu;
 extern struct platform_device mx3_fb;
 extern struct platform_device mx3_camera;
-extern struct platform_device mxc_fec_device;
 extern struct platform_device mxcsdhc_device0;
 extern struct platform_device mxcsdhc_device1;
 extern struct platform_device mxc_otg_udc_device;
@@ -10,9 +9,6 @@
 extern struct platform_device mxc_usbh1;
 extern struct platform_device mxc_usbh2;
 extern struct platform_device mxc_rnga_device;
-extern struct platform_device imx_ssi_device0;
-extern struct platform_device imx_ssi_device1;
-extern struct platform_device imx_ssi_device1;
 extern struct platform_device imx_wdt_device0;
 extern struct platform_device imx_rtc_device0;
 extern struct platform_device imx_kpp_device;
diff --git a/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c b/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c
index f8f15e3..1abc10d 100644
--- a/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c
+++ b/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c
@@ -43,14 +43,13 @@
 #include <mach/ipu.h>
 #include <mach/mx3fb.h>
 #include <mach/audmux.h>
-#include <mach/ssi.h>
 
 #include "devices-imx35.h"
 #include "devices.h"
 
 static const struct fb_videomode fb_modedb[] = {
 	{
-		.name		= "CMO_QVGA",
+		.name		= "CMO-QVGA",
 		.refresh	= 60,
 		.xres		= 320,
 		.yres		= 240,
@@ -65,6 +64,40 @@
 		.vmode		= FB_VMODE_NONINTERLACED,
 		.flag		= 0,
 	},
+	{
+		.name		= "DVI-VGA",
+		.refresh	= 60,
+		.xres		= 640,
+		.yres		= 480,
+		.pixclock	= 32000,
+		.left_margin	= 100,
+		.right_margin	= 100,
+		.upper_margin	= 7,
+		.lower_margin	= 100,
+		.hsync_len	= 7,
+		.vsync_len	= 7,
+		.sync		= FB_SYNC_VERT_HIGH_ACT | FB_SYNC_HOR_HIGH_ACT |
+				  FB_SYNC_OE_ACT_HIGH | FB_SYNC_CLK_INVERT,
+		.vmode		= FB_VMODE_NONINTERLACED,
+		.flag		= 0,
+	},
+	{
+		.name		= "DVI-SVGA",
+		.refresh	= 60,
+		.xres		= 800,
+		.yres		= 600,
+		.pixclock	= 25000,
+		.left_margin	= 75,
+		.right_margin	= 75,
+		.upper_margin	= 7,
+		.lower_margin	= 75,
+		.hsync_len	= 7,
+		.vsync_len	= 7,
+		.sync		= FB_SYNC_VERT_HIGH_ACT | FB_SYNC_HOR_HIGH_ACT |
+				  FB_SYNC_OE_ACT_HIGH | FB_SYNC_CLK_INVERT,
+		.vmode		= FB_VMODE_NONINTERLACED,
+		.flag		= 0,
+	},
 };
 
 static struct ipu_platform_data mx3_ipu_data = {
@@ -73,7 +106,7 @@
 
 static struct mx3fb_platform_data mx3fb_pdata = {
 	.dma_dev	= &mx3_ipu.dev,
-	.name		= "CMO_QVGA",
+	.name		= "CMO-QVGA",
 	.mode		= fb_modedb,
 	.num_modes	= ARRAY_SIZE(fb_modedb),
 };
@@ -120,6 +153,16 @@
 	MX35_PAD_STXD4__AUDMUX_AUD4_TXD,
 	MX35_PAD_SRXD4__AUDMUX_AUD4_RXD,
 	MX35_PAD_SCK4__AUDMUX_AUD4_TXC,
+	/* CAN2 */
+	MX35_PAD_TX5_RX0__CAN2_TXCAN,
+	MX35_PAD_TX4_RX1__CAN2_RXCAN,
+	/* SDCARD */
+	MX35_PAD_SD1_CMD__ESDHC1_CMD,
+	MX35_PAD_SD1_CLK__ESDHC1_CLK,
+	MX35_PAD_SD1_DATA0__ESDHC1_DAT0,
+	MX35_PAD_SD1_DATA1__ESDHC1_DAT1,
+	MX35_PAD_SD1_DATA2__ESDHC1_DAT2,
+	MX35_PAD_SD1_DATA3__ESDHC1_DAT3,
 };
 
 #define GPIO_LED1	(2 * 32 + 29)
@@ -206,7 +249,8 @@
 	},
 };
 
-struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata = {
+static const
+struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata __initconst = {
 	.flags = IMX_SSI_SYN | IMX_SSI_NET | IMX_SSI_USE_I2S_SLAVE,
 };
 
@@ -242,7 +286,10 @@
 	mxc_register_device(&mx3_ipu, &mx3_ipu_data);
 	mxc_register_device(&mx3_fb, &mx3fb_pdata);
 
-	mxc_register_device(&imx_ssi_device0, &eukrea_mbimxsd_ssi_pdata);
+	imx35_add_imx_ssi(0, &eukrea_mbimxsd_ssi_pdata);
+
+	imx35_add_flexcan1(NULL);
+	imx35_add_esdhc(0, NULL);
 
 	gpio_request(GPIO_LED1, "LED1");
 	gpio_direction_output(GPIO_LED1, 1);
@@ -254,7 +301,7 @@
 
 	gpio_request(GPIO_LCDPWR, "LCDPWR");
 	gpio_direction_output(GPIO_LCDPWR, 1);
-	gpio_free(GPIO_SWITCH1);
+	gpio_free(GPIO_LCDPWR);
 
 	i2c_register_board_info(0, eukrea_mbimxsd_i2c_devices,
 				ARRAY_SIZE(eukrea_mbimxsd_i2c_devices));
diff --git a/arch/arm/mach-mx3/mach-armadillo5x0.c b/arch/arm/mach-mx3/mach-armadillo5x0.c
index 68879c9..aaa30fe 100644
--- a/arch/arm/mach-mx3/mach-armadillo5x0.c
+++ b/arch/arm/mach-mx3/mach-armadillo5x0.c
@@ -571,8 +571,6 @@
 
 MACHINE_START(ARMADILLO5X0, "Armadillo-500")
 	/* Maintainer: Alberto Panizzo  */
-	.phys_io	= MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst	= (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params	= MX3x_PHYS_OFFSET + 0x100,
 	.map_io		= mx31_map_io,
 	.init_irq	= mx31_init_irq,
diff --git a/arch/arm/mach-mx3/mach-cpuimx35.c b/arch/arm/mach-mx3/mach-cpuimx35.c
index 2a4f8b7..8533bf0 100644
--- a/arch/arm/mach-mx3/mach-cpuimx35.c
+++ b/arch/arm/mach-mx3/mach-cpuimx35.c
@@ -31,6 +31,7 @@
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
 #include <linux/fsl_devices.h>
+#include <linux/i2c-gpio.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -43,7 +44,6 @@
 #include <mach/iomux-mx35.h>
 #include <mach/mxc_nand.h>
 #include <mach/mxc_ehci.h>
-#include <mach/ulpi.h>
 
 #include "devices-imx35.h"
 #include "devices.h"
@@ -53,39 +53,16 @@
 };
 
 static const struct imxi2c_platform_data
-eukrea_cpuimx35_i2c0_data __initconst = {
-	.bitrate = 50000,
+		eukrea_cpuimx35_i2c0_data __initconst = {
+	.bitrate =		100000,
 };
 
-#define TSC2007_IRQGPIO		(2 * 32 + 2)
-static int ts_get_pendown_state(void)
-{
-	int val = 0;
-	gpio_free(TSC2007_IRQGPIO);
-	gpio_request(TSC2007_IRQGPIO, NULL);
-	gpio_direction_input(TSC2007_IRQGPIO);
-
-	val = gpio_get_value(TSC2007_IRQGPIO);
-
-	gpio_free(TSC2007_IRQGPIO);
-	gpio_request(TSC2007_IRQGPIO, NULL);
-
-	return val ? 0 : 1;
-}
-
-static int ts_init(void)
-{
-	gpio_request(TSC2007_IRQGPIO, NULL);
-	return 0;
-}
-
 static struct tsc2007_platform_data tsc2007_info = {
 	.model			= 2007,
 	.x_plate_ohms		= 180,
-	.get_pendown_state	= ts_get_pendown_state,
-	.init_platform_hw	= ts_init,
 };
 
+#define TSC2007_IRQGPIO		(2 * 32 + 2)
 static struct i2c_board_info eukrea_cpuimx35_i2c_devices[] = {
 	{
 		I2C_BOARD_INFO("pcf8563", 0x51),
@@ -98,7 +75,6 @@
 };
 
 static struct platform_device *devices[] __initdata = {
-	&mxc_fec_device,
 	&imx_wdt_device0,
 };
 
@@ -135,18 +111,18 @@
 };
 
 static const struct mxc_nand_platform_data
-eukrea_cpuimx35_nand_board_info __initconst = {
+		eukrea_cpuimx35_nand_board_info __initconst = {
 	.width		= 1,
 	.hw_ecc		= 1,
 	.flash_bbt	= 1,
 };
 
-static struct mxc_usbh_platform_data otg_pdata = {
+static struct mxc_usbh_platform_data __maybe_unused otg_pdata = {
 	.portsc	= MXC_EHCI_MODE_UTMI,
 	.flags	= MXC_EHCI_INTERFACE_DIFF_UNI,
 };
 
-static struct mxc_usbh_platform_data usbh1_pdata = {
+static struct mxc_usbh_platform_data __maybe_unused usbh1_pdata = {
 	.portsc	= MXC_EHCI_MODE_SERIAL,
 	.flags	= MXC_EHCI_INTERFACE_SINGLE_UNI | MXC_EHCI_INTERNAL_PHY |
 		  MXC_EHCI_IPPUE_DOWN,
@@ -180,6 +156,7 @@
 	mxc_iomux_v3_setup_multiple_pads(eukrea_cpuimx35_pads,
 			ARRAY_SIZE(eukrea_cpuimx35_pads));
 
+	imx35_add_fec(NULL);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	imx35_add_imx_uart0(&uart_pdata);
@@ -189,18 +166,13 @@
 			ARRAY_SIZE(eukrea_cpuimx35_i2c_devices));
 	imx35_add_imx_i2c0(&eukrea_cpuimx35_i2c0_data);
 
-#if defined(CONFIG_USB_ULPI)
-	if (otg_mode_host) {
-		otg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops,
-				ULPI_OTG_DRVVBUS | ULPI_OTG_DRVVBUS_EXT);
-
+	if (otg_mode_host)
 		mxc_register_device(&mxc_otg_host, &otg_pdata);
-	}
-	mxc_register_device(&mxc_usbh1, &usbh1_pdata);
-#endif
-	if (!otg_mode_host)
+	else
 		mxc_register_device(&mxc_otg_udc_device, &otg_device_pdata);
 
+	mxc_register_device(&mxc_usbh1, &usbh1_pdata);
+
 #ifdef CONFIG_MACH_EUKREA_MBIMXSD35_BASEBOARD
 	eukrea_mbimxsd35_baseboard_init();
 #endif
@@ -217,8 +189,6 @@
 
 MACHINE_START(EUKREA_CPUIMX35, "Eukrea CPUIMX35")
 	/* Maintainer: Eukrea Electromatique */
-	.phys_io	= MX35_AIPS1_BASE_ADDR,
-	.io_pg_offst	= ((MX35_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx35_map_io,
 	.init_irq       = mx35_init_irq,
diff --git a/arch/arm/mach-mx3/mach-kzm_arm11_01.c b/arch/arm/mach-mx3/mach-kzm_arm11_01.c
index 5b23e41..042cd56 100644
--- a/arch/arm/mach-mx3/mach-kzm_arm11_01.c
+++ b/arch/arm/mach-mx3/mach-kzm_arm11_01.c
@@ -274,8 +274,6 @@
  * initialize __mach_desc_KZM_ARM11_01 data structure.
  */
 MACHINE_START(KZM_ARM11_01, "Kyoto Microcomputer Co., Ltd. KZM-ARM11-01")
-	.phys_io        = MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst    = (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = kzm_map_io,
 	.init_irq       = mx31_init_irq,
diff --git a/arch/arm/mach-mx3/mach-mx31_3ds.c b/arch/arm/mach-mx3/mach-mx31_3ds.c
index 6fe69e1..5c1d0e8 100644
--- a/arch/arm/mach-mx3/mach-mx31_3ds.c
+++ b/arch/arm/mach-mx3/mach-mx31_3ds.c
@@ -301,8 +301,6 @@
  */
 MACHINE_START(MX31_3DS, "Freescale MX31PDK (3DS)")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.phys_io	= MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst	= (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx31_3ds_map_io,
 	.init_irq       = mx31_init_irq,
diff --git a/arch/arm/mach-mx3/mach-mx31ads.c b/arch/arm/mach-mx3/mach-mx31ads.c
index 94b3e7c..b993b9b 100644
--- a/arch/arm/mach-mx3/mach-mx31ads.c
+++ b/arch/arm/mach-mx3/mach-mx31ads.c
@@ -22,13 +22,13 @@
 #include <linux/i2c.h>
 #include <linux/irq.h>
 
-#include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 #include <asm/memory.h>
 #include <asm/mach/map.h>
 #include <mach/common.h>
+#include <mach/board-mx31ads.h>
 #include <mach/iomux-mx3.h>
 
 #ifdef CONFIG_MACH_MX31ADS_WM1133_EV1
@@ -40,10 +40,6 @@
 #include "devices-imx31.h"
 #include "devices.h"
 
-/* Base address of PBC controller */
-#define PBC_BASE_ADDRESS        MX31_CS4_BASE_ADDR_VIRT
-/* Offsets for the PBC Controller register */
-
 /* PBC Board interrupt status register */
 #define PBC_INTSTATUS           0x000016
 
@@ -67,7 +63,6 @@
 #define PBC_INTMASK_CLEAR_REG	(PBC_INTMASK_CLEAR + PBC_BASE_ADDRESS)
 #define EXPIO_PARENT_INT	IOMUX_TO_IRQ(MX31_PIN_GPIO1_4)
 
-#define MXC_EXP_IO_BASE		(MXC_BOARD_IRQ_START)
 #define MXC_IRQ_TO_EXPIO(irq)	((irq) - MXC_EXP_IO_BASE)
 
 #define EXPIO_INT_XUART_INTA	(MXC_EXP_IO_BASE + 10)
@@ -517,7 +512,7 @@
 
 static void mxc_init_audio(void)
 {
-	mxc_register_device(&imx_ssi_device0, NULL);
+	imx31_add_imx_ssi(0, NULL);
 	mxc_iomux_setup_multiple_pins(ssi_pins, ARRAY_SIZE(ssi_pins), "ssi");
 }
 
@@ -574,8 +569,6 @@
  */
 MACHINE_START(MX31ADS, "Freescale MX31ADS")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.phys_io	= MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst	= (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx31ads_map_io,
 	.init_irq       = mx31ads_init_irq,
diff --git a/arch/arm/mach-mx3/mach-mx31lilly.c b/arch/arm/mach-mx3/mach-mx31lilly.c
index 7c37daa..42f47fa 100644
--- a/arch/arm/mach-mx3/mach-mx31lilly.c
+++ b/arch/arm/mach-mx3/mach-mx31lilly.c
@@ -348,8 +348,6 @@
 };
 
 MACHINE_START(LILLY1131, "INCO startec LILLY-1131")
-	.phys_io	= MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst	= (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params	= MX3x_PHYS_OFFSET + 0x100,
 	.map_io		= mx31_map_io,
 	.init_irq	= mx31_init_irq,
diff --git a/arch/arm/mach-mx3/mach-mx31lite.c b/arch/arm/mach-mx3/mach-mx31lite.c
index f66a957..b938958 100644
--- a/arch/arm/mach-mx3/mach-mx31lite.c
+++ b/arch/arm/mach-mx3/mach-mx31lite.c
@@ -282,8 +282,6 @@
 
 MACHINE_START(MX31LITE, "LogicPD i.MX31 SOM")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.phys_io        = MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst    = (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx31lite_map_io,
 	.init_irq       = mx31_init_irq,
diff --git a/arch/arm/mach-mx3/mach-mx31moboard.c b/arch/arm/mach-mx3/mach-mx31moboard.c
index 7a075e8..eb5f426 100644
--- a/arch/arm/mach-mx3/mach-mx31moboard.c
+++ b/arch/arm/mach-mx3/mach-mx31moboard.c
@@ -560,8 +560,6 @@
 
 MACHINE_START(MX31MOBOARD, "EPFL Mobots mx31moboard")
 	/* Maintainer: Valentin Longchamp, EPFL Mobots group */
-	.phys_io	= MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst	= (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx31_map_io,
 	.init_irq       = mx31_init_irq,
diff --git a/arch/arm/mach-mx3/mach-mx35_3ds.c b/arch/arm/mach-mx3/mach-mx35_3ds.c
index 1c30d72..05f628d 100644
--- a/arch/arm/mach-mx3/mach-mx35_3ds.c
+++ b/arch/arm/mach-mx3/mach-mx35_3ds.c
@@ -1,5 +1,6 @@
 /*
  * Copyright 2009 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright (C) 2009 Marc Kleine-Budde, Pengutronix
  *
  * Author: Fabio Estevam <fabio.estevam@freescale.com>
  *
@@ -27,6 +28,8 @@
 #include <linux/gpio.h>
 #include <linux/fsl_devices.h>
 
+#include <linux/mtd/physmap.h>
+
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
@@ -35,6 +38,7 @@
 #include <mach/hardware.h>
 #include <mach/common.h>
 #include <mach/iomux-mx35.h>
+#include <mach/mxc_ehci.h>
 
 #include "devices-imx35.h"
 #include "devices.h"
@@ -43,8 +47,34 @@
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
+static struct physmap_flash_data mx35pdk_flash_data = {
+	.width  = 2,
+};
+
+static struct resource mx35pdk_flash_resource = {
+	.start	= MX35_CS0_BASE_ADDR,
+	.end	= MX35_CS0_BASE_ADDR + SZ_64M - 1,
+	.flags	= IORESOURCE_MEM,
+};
+
+static struct platform_device mx35pdk_flash = {
+	.name	= "physmap-flash",
+	.id	= 0,
+	.dev	= {
+		.platform_data  = &mx35pdk_flash_data,
+	},
+	.resource = &mx35pdk_flash_resource,
+	.num_resources = 1,
+};
+
+static const struct mxc_nand_platform_data mx35pdk_nand_board_info __initconst = {
+	.width = 1,
+	.hw_ecc = 1,
+	.flash_bbt = 1,
+};
+
 static struct platform_device *devices[] __initdata = {
-	&mxc_fec_device,
+	&mx35pdk_flash,
 };
 
 static struct pad_desc mx35pdk_pads[] = {
@@ -75,14 +105,24 @@
 	/* USBOTG */
 	MX35_PAD_USBOTG_PWR__USB_TOP_USBOTG_PWR,
 	MX35_PAD_USBOTG_OC__USB_TOP_USBOTG_OC,
+	/* USBH1 */
+	MX35_PAD_I2C2_CLK__USB_TOP_USBH2_PWR,
+	MX35_PAD_I2C2_DAT__USB_TOP_USBH2_OC,
 };
 
 /* OTG config */
-static struct fsl_usb2_platform_data usb_pdata = {
+static struct fsl_usb2_platform_data usb_otg_pdata = {
 	.operating_mode	= FSL_USB2_DR_DEVICE,
 	.phy_mode	= FSL_USB2_PHY_UTMI_WIDE,
 };
 
+/* USB HOST config */
+static struct mxc_usbh_platform_data usb_host_pdata = {
+	.portsc		= MXC_EHCI_MODE_SERIAL,
+	.flags		= MXC_EHCI_INTERFACE_SINGLE_UNI |
+			  MXC_EHCI_INTERNAL_PHY,
+};
+
 /*
  * Board specific initialization.
  */
@@ -90,11 +130,16 @@
 {
 	mxc_iomux_v3_setup_multiple_pads(mx35pdk_pads, ARRAY_SIZE(mx35pdk_pads));
 
+	imx35_add_fec(NULL);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	imx35_add_imx_uart0(&uart_pdata);
 
-	mxc_register_device(&mxc_otg_udc_device, &usb_pdata);
+	mxc_register_device(&mxc_otg_udc_device, &usb_otg_pdata);
+
+	mxc_register_device(&mxc_usbh1, &usb_host_pdata);
+
+	imx35_add_mxc_nand(&mx35pdk_nand_board_info);
 }
 
 static void __init mx35pdk_timer_init(void)
@@ -108,8 +153,6 @@
 
 MACHINE_START(MX35_3DS, "Freescale MX35PDK")
 	/* Maintainer: Freescale Semiconductor, Inc */
-	.phys_io	= MX35_AIPS1_BASE_ADDR,
-	.io_pg_offst	= ((MX35_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx35_map_io,
 	.init_irq       = mx35_init_irq,
diff --git a/arch/arm/mach-mx3/mach-pcm037.c b/arch/arm/mach-mx3/mach-pcm037.c
index 214de11..86e86c1 100644
--- a/arch/arm/mach-mx3/mach-pcm037.c
+++ b/arch/arm/mach-mx3/mach-pcm037.c
@@ -680,8 +680,6 @@
 
 MACHINE_START(PCM037, "Phytec Phycore pcm037")
 	/* Maintainer: Pengutronix */
-	.phys_io	= MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst	= (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx31_map_io,
 	.init_irq       = mx31_init_irq,
diff --git a/arch/arm/mach-mx3/mach-pcm037_eet.c b/arch/arm/mach-mx3/mach-pcm037_eet.c
index c8b9821..99e0894 100644
--- a/arch/arm/mach-mx3/mach-pcm037_eet.c
+++ b/arch/arm/mach-mx3/mach-pcm037_eet.c
@@ -19,6 +19,7 @@
 
 #include "pcm037.h"
 #include "devices.h"
+#include "devices-imx31.h"
 
 static unsigned int pcm037_eet_pins[] = {
 	/* Reserve and hardwire GPIO 57 high - S6E63D6 chipselect */
@@ -181,7 +182,7 @@
 	/* SPI */
 	spi_register_board_info(pcm037_spi_dev, ARRAY_SIZE(pcm037_spi_dev));
 #if defined(CONFIG_SPI_IMX) || defined(CONFIG_SPI_IMX_MODULE)
-	imx35_add_spi_imx0(&pcm037_spi1_pdata);
+	imx31_add_spi_imx0(&pcm037_spi1_pdata);
 #endif
 
 	platform_device_register(&pcm037_gpio_keys_device);
diff --git a/arch/arm/mach-mx3/mach-pcm043.c b/arch/arm/mach-mx3/mach-pcm043.c
index 28886f0..4e1de87 100644
--- a/arch/arm/mach-mx3/mach-pcm043.c
+++ b/arch/arm/mach-mx3/mach-pcm043.c
@@ -42,7 +42,6 @@
 #include <mach/mxc_ehci.h>
 #include <mach/ulpi.h>
 #include <mach/audmux.h>
-#include <mach/ssi.h>
 
 #include "devices-imx35.h"
 #include "devices.h"
@@ -141,7 +140,6 @@
 
 static struct platform_device *devices[] __initdata = {
 	&pcm043_flash,
-	&mxc_fec_device,
 	&imx_wdt_device0,
 };
 
@@ -217,6 +215,13 @@
 	/* CAN2 */
 	MX35_PAD_TX5_RX0__CAN2_TXCAN,
 	MX35_PAD_TX4_RX1__CAN2_RXCAN,
+	/* esdhc */
+	MX35_PAD_SD1_CMD__ESDHC1_CMD,
+	MX35_PAD_SD1_CLK__ESDHC1_CLK,
+	MX35_PAD_SD1_DATA0__ESDHC1_DAT0,
+	MX35_PAD_SD1_DATA1__ESDHC1_DAT1,
+	MX35_PAD_SD1_DATA2__ESDHC1_DAT2,
+	MX35_PAD_SD1_DATA3__ESDHC1_DAT3,
 };
 
 #define AC97_GPIO_TXFS	(1 * 32 + 31)
@@ -293,7 +298,7 @@
 	mdelay(1);
 }
 
-static struct imx_ssi_platform_data pcm043_ssi_pdata = {
+static const struct imx_ssi_platform_data pcm043_ssi_pdata __initconst = {
 	.ac97_reset = pcm043_ac97_cold_reset,
 	.ac97_warm_reset = pcm043_ac97_warm_reset,
 	.flags = IMX_SSI_USE_AC97,
@@ -357,11 +362,12 @@
 			MXC_AUDMUX_V2_PTCR_TCLKDIR, /* clock is output */
 			MXC_AUDMUX_V2_PDCR_RXDSEL(3));
 
+	imx35_add_fec(NULL);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	imx35_add_imx_uart0(&uart_pdata);
 	imx35_add_mxc_nand(&pcm037_nand_board_info);
-	mxc_register_device(&imx_ssi_device0, &pcm043_ssi_pdata);
+	imx35_add_imx_ssi(0, &pcm043_ssi_pdata);
 
 	imx35_add_imx_uart1(&uart_pdata);
 
@@ -389,6 +395,7 @@
 		mxc_register_device(&mxc_otg_udc_device, &otg_device_pdata);
 
 	imx35_add_flexcan1(NULL);
+	imx35_add_esdhc(0, NULL);
 }
 
 static void __init pcm043_timer_init(void)
@@ -402,8 +409,6 @@
 
 MACHINE_START(PCM043, "Phytec Phycore pcm043")
 	/* Maintainer: Pengutronix */
-	.phys_io	= MX35_AIPS1_BASE_ADDR,
-	.io_pg_offst	= ((MX35_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx35_map_io,
 	.init_irq       = mx35_init_irq,
diff --git a/arch/arm/mach-mx3/mach-qong.c b/arch/arm/mach-mx3/mach-qong.c
index c8c380e..fd1050c 100644
--- a/arch/arm/mach-mx3/mach-qong.c
+++ b/arch/arm/mach-mx3/mach-qong.c
@@ -270,8 +270,6 @@
 
 MACHINE_START(QONG, "Dave/DENX QongEVB-LITE")
 	/* Maintainer: DENX Software Engineering GmbH */
-	.phys_io        = MX31_AIPS1_BASE_ADDR,
-	.io_pg_offst    = (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
 	.map_io         = mx31_map_io,
 	.init_irq       = mx31_init_irq,
diff --git a/arch/arm/mach-mx3/mm.c b/arch/arm/mach-mx3/mm.c
index 20e48c0..b4ffc53 100644
--- a/arch/arm/mach-mx3/mm.c
+++ b/arch/arm/mach-mx3/mm.c
@@ -110,6 +110,24 @@
 static int mxc_init_l2x0(void)
 {
 	void __iomem *l2x0_base;
+	void __iomem *clkctl_base;
+/*
+ * First of all, we must repair broken chip settings. There are some
+ * i.MX35 CPUs in the wild, comming with bogus L2 cache settings. These
+ * misconfigured CPUs will run amok immediately when the L2 cache gets enabled.
+ * Workaraound is to setup the correct register setting prior enabling the
+ * L2 cache. This should not hurt already working CPUs, as they are using the
+ * same value
+ */
+#define L2_MEM_VAL 0x10
+
+	clkctl_base = ioremap(MX35_CLKCTL_BASE_ADDR, 4096);
+	if (clkctl_base != NULL) {
+		writel(0x00000515, clkctl_base + L2_MEM_VAL);
+		iounmap(clkctl_base);
+	} else {
+		pr_err("L2 cache: Cannot fix timing. Trying to continue without\n");
+	}
 
 	l2x0_base = ioremap(L2CC_BASE_ADDR, 4096);
 	if (IS_ERR(l2x0_base)) {
diff --git a/arch/arm/mach-mx5/Kconfig b/arch/arm/mach-mx5/Kconfig
index 0848db5..a2df9ac 100644
--- a/arch/arm/mach-mx5/Kconfig
+++ b/arch/arm/mach-mx5/Kconfig
@@ -5,11 +5,14 @@
 	default y
 	select MXC_TZIC
 	select ARCH_MXC_IOMUX_V3
+	select ARCH_MXC_AUDMUX_V2
 
 comment "MX5 platforms:"
 
 config MACH_MX51_BABBAGE
 	bool "Support MX51 BABBAGE platforms"
+	select IMX_HAVE_PLATFORM_IMX_I2C
+	select IMX_HAVE_PLATFORM_IMX_UART
 	help
 	  Include support for MX51 Babbage platform, also known as MX51EVK in
 	  u-boot. This includes specific configurations for the board and its
@@ -17,6 +20,8 @@
 
 config MACH_MX51_3DS
 	bool "Support MX51PDK (3DS)"
+	select IMX_HAVE_PLATFORM_IMX_UART
+	select IMX_HAVE_PLATFORM_SPI_IMX
 	select MXC_DEBUG_BOARD
 	help
 	  Include support for MX51PDK (3DS) platform. This includes specific
@@ -24,6 +29,10 @@
 
 config MACH_EUKREA_CPUIMX51
 	bool "Support Eukrea CPUIMX51 module"
+	select IMX_HAVE_PLATFORM_IMX_I2C
+	select IMX_HAVE_PLATFORM_IMX_UART
+	select IMX_HAVE_PLATFORM_MXC_NAND
+	select IMX_HAVE_PLATFORM_SPI_IMX
 	help
 	  Include support for Eukrea CPUIMX51 platform. This includes
 	  specific configurations for the module and its peripherals.
@@ -36,10 +45,43 @@
 config MACH_EUKREA_MBIMX51_BASEBOARD
 	prompt "Eukrea MBIMX51 development board"
 	bool
+	select IMX_HAVE_PLATFORM_ESDHC
 	help
 	  This adds board specific devices that can be found on Eukrea's
 	  MBIMX51 evaluation board.
 
 endchoice
 
+config MACH_EUKREA_CPUIMX51SD
+	bool "Support Eukrea CPUIMX51SD module"
+	select IMX_HAVE_PLATFORM_IMX_I2C
+	select IMX_HAVE_PLATFORM_SPI_IMX
+	select IMX_HAVE_PLATFORM_IMX_UART
+	select IMX_HAVE_PLATFORM_MXC_NAND
+	help
+	  Include support for Eukrea CPUIMX51SD platform. This includes
+	  specific configurations for the module and its peripherals.
+
+choice
+	prompt "Baseboard"
+	depends on MACH_EUKREA_CPUIMX51SD
+	default MACH_EUKREA_MBIMXSD51_BASEBOARD
+
+config MACH_EUKREA_MBIMXSD51_BASEBOARD
+	prompt "Eukrea MBIMXSD development board"
+	bool
+	select IMX_HAVE_PLATFORM_ESDHC
+	help
+	  This adds board specific devices that can be found on Eukrea's
+	  MBIMXSD evaluation board.
+
+endchoice
+
+config MACH_MX51_EFIKAMX
+	bool "Support MX51 Genesi Efika MX nettop"
+	select IMX_HAVE_PLATFORM_IMX_UART
+	help
+	  Include support for Genesi Efika MX nettop. This includes specific
+	  configurations for the board and its peripherals.
+
 endif
diff --git a/arch/arm/mach-mx5/Makefile b/arch/arm/mach-mx5/Makefile
index 86c66e7..1769c16 100644
--- a/arch/arm/mach-mx5/Makefile
+++ b/arch/arm/mach-mx5/Makefile
@@ -9,3 +9,6 @@
 obj-$(CONFIG_MACH_MX51_3DS) += board-mx51_3ds.o
 obj-$(CONFIG_MACH_EUKREA_CPUIMX51) += board-cpuimx51.o
 obj-$(CONFIG_MACH_EUKREA_MBIMX51_BASEBOARD) += eukrea_mbimx51-baseboard.o
+obj-$(CONFIG_MACH_EUKREA_CPUIMX51SD) += board-cpuimx51sd.o
+obj-$(CONFIG_MACH_EUKREA_MBIMXSD51_BASEBOARD) += eukrea_mbimxsd-baseboard.o
+obj-$(CONFIG_MACH_MX51_EFIKAMX) += board-mx51_efikamx.o
diff --git a/arch/arm/mach-mx5/board-cpuimx51.c b/arch/arm/mach-mx5/board-cpuimx51.c
index 623607a..6a9792f 100644
--- a/arch/arm/mach-mx5/board-cpuimx51.c
+++ b/arch/arm/mach-mx5/board-cpuimx51.c
@@ -28,9 +28,7 @@
 #include <mach/eukrea-baseboards.h>
 #include <mach/common.h>
 #include <mach/hardware.h>
-#include <mach/imx-uart.h>
 #include <mach/iomux-mx51.h>
-#include <mach/i2c.h>
 #include <mach/mxc_ehci.h>
 
 #include <asm/irq.h>
@@ -39,6 +37,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 
+#include "devices-imx51.h"
 #include "devices.h"
 
 #define CPUIMX51_USBH1_STP	(0*32 + 27)
@@ -109,7 +108,6 @@
 #endif
 
 static struct platform_device *devices[] __initdata = {
-	&mxc_fec_device,
 #if defined(CONFIG_SERIAL_8250) || defined(CONFIG_SERIAL_8250_MODULE)
 	&serial_device,
 #endif
@@ -148,11 +146,19 @@
 	MX51_PAD_USBH1_STP__USBH1_STP,
 };
 
-static struct imxuart_platform_data uart_pdata = {
+static const struct mxc_nand_platform_data
+		eukrea_cpuimx51_nand_board_info __initconst = {
+	.width		= 1,
+	.hw_ecc		= 1,
+	.flash_bbt	= 1,
+};
+
+static const struct imxuart_platform_data uart_pdata __initconst = {
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
-static struct imxi2c_platform_data eukrea_cpuimx51_i2c_data = {
+static const
+struct imxi2c_platform_data eukrea_cpuimx51_i2c_data __initconst = {
 	.bitrate = 100000,
 };
 
@@ -239,7 +245,9 @@
 	mxc_iomux_v3_setup_multiple_pads(eukrea_cpuimx51_pads,
 					ARRAY_SIZE(eukrea_cpuimx51_pads));
 
-	mxc_register_device(&mxc_uart_device0, &uart_pdata);
+	imx51_add_imx_uart(0, &uart_pdata);
+	imx51_add_mxc_nand(&eukrea_cpuimx51_nand_board_info);
+
 	gpio_request(CPUIMX51_QUARTA_GPIO, "quarta_irq");
 	gpio_direction_input(CPUIMX51_QUARTA_GPIO);
 	gpio_free(CPUIMX51_QUARTA_GPIO);
@@ -253,9 +261,10 @@
 	gpio_direction_input(CPUIMX51_QUARTD_GPIO);
 	gpio_free(CPUIMX51_QUARTD_GPIO);
 
+	imx51_add_fec(NULL);
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
-	mxc_register_device(&mxc_i2c_device1, &eukrea_cpuimx51_i2c_data);
+	imx51_add_imx_i2c(1, &eukrea_cpuimx51_i2c_data);
 	i2c_register_board_info(1, eukrea_cpuimx51_i2c_devices,
 				ARRAY_SIZE(eukrea_cpuimx51_i2c_devices));
 
@@ -283,8 +292,6 @@
 
 MACHINE_START(EUKREA_CPUIMX51, "Eukrea CPUIMX51 Module")
 	/* Maintainer: Eric Bénard <eric@eukrea.com> */
-	.phys_io = MX51_AIPS1_BASE_ADDR,
-	.io_pg_offst = ((MX51_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params = PHYS_OFFSET + 0x100,
 	.map_io = mx51_map_io,
 	.init_irq = mx51_init_irq,
diff --git a/arch/arm/mach-mx5/board-cpuimx51sd.c b/arch/arm/mach-mx5/board-cpuimx51sd.c
new file mode 100644
index 0000000..4b3a611
--- /dev/null
+++ b/arch/arm/mach-mx5/board-cpuimx51sd.c
@@ -0,0 +1,331 @@
+/*
+ *
+ * Copyright (C) 2010 Eric Bénard <eric@eukrea.com>
+ *
+ * based on board-mx51_babbage.c which is
+ * Copyright 2009 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright (C) 2009-2010 Amit Kucheria <amit.kucheria@canonical.com>
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/i2c.h>
+#include <linux/i2c/tsc2007.h>
+#include <linux/gpio.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/fsl_devices.h>
+#include <linux/i2c-gpio.h>
+#include <linux/spi/spi.h>
+#include <linux/can/platform/mcp251x.h>
+
+#include <mach/eukrea-baseboards.h>
+#include <mach/common.h>
+#include <mach/hardware.h>
+#include <mach/iomux-mx51.h>
+#include <mach/mxc_ehci.h>
+
+#include <asm/irq.h>
+#include <asm/setup.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/time.h>
+
+#include "devices-imx51.h"
+#include "devices.h"
+
+#define USBH1_RST		(1*32 + 28)
+#define ETH_RST			(1*32 + 31)
+#define TSC2007_IRQGPIO		(2*32 + 12)
+#define CAN_IRQGPIO		(0*32 + 1)
+#define CAN_RST			(3*32 + 15)
+#define CAN_NCS			(3*32 + 24)
+#define CAN_RXOBF		(0*32 + 4)
+#define CAN_RX1BF		(0*32 + 6)
+#define CAN_TXORTS		(0*32 + 7)
+#define CAN_TX1RTS		(0*32 + 8)
+#define CAN_TX2RTS		(0*32 + 9)
+#define I2C_SCL			(3*32 + 16)
+#define I2C_SDA			(3*32 + 17)
+
+/* USB_CTRL_1 */
+#define MX51_USB_CTRL_1_OFFSET		0x10
+#define MX51_USB_CTRL_UH1_EXT_CLK_EN	(1 << 25)
+
+#define	MX51_USB_PLLDIV_12_MHZ		0x00
+#define	MX51_USB_PLL_DIV_19_2_MHZ	0x01
+#define	MX51_USB_PLL_DIV_24_MHZ		0x02
+
+#define CPUIMX51SD_GPIO_3_12 IOMUX_PAD(0x57C, 0x194, 3, 0x0, 0, \
+				MX51_PAD_CTRL_1 | PAD_CTL_PUS_22K_UP)
+
+static struct pad_desc eukrea_cpuimx51sd_pads[] = {
+	/* UART1 */
+	MX51_PAD_UART1_RXD__UART1_RXD,
+	MX51_PAD_UART1_TXD__UART1_TXD,
+	MX51_PAD_UART1_RTS__UART1_RTS,
+	MX51_PAD_UART1_CTS__UART1_CTS,
+
+	/* USB HOST1 */
+	MX51_PAD_USBH1_CLK__USBH1_CLK,
+	MX51_PAD_USBH1_DIR__USBH1_DIR,
+	MX51_PAD_USBH1_NXT__USBH1_NXT,
+	MX51_PAD_USBH1_DATA0__USBH1_DATA0,
+	MX51_PAD_USBH1_DATA1__USBH1_DATA1,
+	MX51_PAD_USBH1_DATA2__USBH1_DATA2,
+	MX51_PAD_USBH1_DATA3__USBH1_DATA3,
+	MX51_PAD_USBH1_DATA4__USBH1_DATA4,
+	MX51_PAD_USBH1_DATA5__USBH1_DATA5,
+	MX51_PAD_USBH1_DATA6__USBH1_DATA6,
+	MX51_PAD_USBH1_DATA7__USBH1_DATA7,
+	MX51_PAD_USBH1_STP__USBH1_STP,
+	MX51_PAD_EIM_CS3__GPIO_2_28,		/* PHY nRESET */
+
+	/* FEC */
+	MX51_PAD_EIM_DTACK__GPIO_2_31,		/* PHY nRESET */
+
+	/* HSI2C */
+	MX51_PAD_I2C1_CLK__GPIO_4_16,
+	MX51_PAD_I2C1_DAT__GPIO_4_17,
+
+	/* CAN */
+	MX51_PAD_CSPI1_MOSI__ECSPI1_MOSI,
+	MX51_PAD_CSPI1_MISO__ECSPI1_MISO,
+	MX51_PAD_CSPI1_SCLK__ECSPI1_SCLK,
+	MX51_PAD_CSPI1_SS0__GPIO_4_24,		/* nCS */
+	MX51_PAD_CSI2_PIXCLK__GPIO_4_15,	/* nReset */
+	MX51_PAD_GPIO_1_1__GPIO_1_1,		/* IRQ */
+	MX51_PAD_GPIO_1_4__GPIO_1_4,		/* Control signals */
+	MX51_PAD_GPIO_1_6__GPIO_1_6,
+	MX51_PAD_GPIO_1_7__GPIO_1_7,
+	MX51_PAD_GPIO_1_8__GPIO_1_8,
+	MX51_PAD_GPIO_1_9__GPIO_1_9,
+
+	/* Touchscreen */
+	CPUIMX51SD_GPIO_3_12,			/* IRQ */
+};
+
+static const struct imxuart_platform_data uart_pdata __initconst = {
+	.flags = IMXUART_HAVE_RTSCTS,
+};
+
+static int ts_get_pendown_state(void)
+{
+	return gpio_get_value(TSC2007_IRQGPIO) ? 0 : 1;
+}
+
+static struct tsc2007_platform_data tsc2007_info = {
+	.model			= 2007,
+	.x_plate_ohms		= 180,
+	.get_pendown_state	= ts_get_pendown_state,
+};
+
+static struct i2c_board_info eukrea_cpuimx51sd_i2c_devices[] = {
+	{
+		I2C_BOARD_INFO("pcf8563", 0x51),
+	}, {
+		I2C_BOARD_INFO("tsc2007", 0x49),
+		.type		= "tsc2007",
+		.platform_data	= &tsc2007_info,
+		.irq		= gpio_to_irq(TSC2007_IRQGPIO),
+	},
+};
+
+static const struct mxc_nand_platform_data
+		eukrea_cpuimx51sd_nand_board_info __initconst = {
+	.width		= 1,
+	.hw_ecc		= 1,
+	.flash_bbt	= 1,
+};
+
+/* This function is board specific as the bit mask for the plldiv will also
+be different for other Freescale SoCs, thus a common bitmask is not
+possible and cannot get place in /plat-mxc/ehci.c.*/
+static int initialize_otg_port(struct platform_device *pdev)
+{
+	u32 v;
+	void __iomem *usb_base;
+	void __iomem *usbother_base;
+
+	usb_base = ioremap(MX51_OTG_BASE_ADDR, SZ_4K);
+	usbother_base = usb_base + MX5_USBOTHER_REGS_OFFSET;
+
+	/* Set the PHY clock to 19.2MHz */
+	v = __raw_readl(usbother_base + MXC_USB_PHY_CTR_FUNC2_OFFSET);
+	v &= ~MX5_USB_UTMI_PHYCTRL1_PLLDIV_MASK;
+	v |= MX51_USB_PLL_DIV_19_2_MHZ;
+	__raw_writel(v, usbother_base + MXC_USB_PHY_CTR_FUNC2_OFFSET);
+	iounmap(usb_base);
+	return 0;
+}
+
+static int initialize_usbh1_port(struct platform_device *pdev)
+{
+	u32 v;
+	void __iomem *usb_base;
+	void __iomem *usbother_base;
+
+	usb_base = ioremap(MX51_OTG_BASE_ADDR, SZ_4K);
+	usbother_base = usb_base + MX5_USBOTHER_REGS_OFFSET;
+
+	/* The clock for the USBH1 ULPI port will come from the PHY. */
+	v = __raw_readl(usbother_base + MX51_USB_CTRL_1_OFFSET);
+	__raw_writel(v | MX51_USB_CTRL_UH1_EXT_CLK_EN,
+			usbother_base + MX51_USB_CTRL_1_OFFSET);
+	iounmap(usb_base);
+	return 0;
+}
+
+static struct mxc_usbh_platform_data dr_utmi_config = {
+	.init		= initialize_otg_port,
+	.portsc	= MXC_EHCI_UTMI_16BIT,
+	.flags	= MXC_EHCI_INTERNAL_PHY,
+};
+
+static struct fsl_usb2_platform_data usb_pdata = {
+	.operating_mode	= FSL_USB2_DR_DEVICE,
+	.phy_mode	= FSL_USB2_PHY_UTMI_WIDE,
+};
+
+static struct mxc_usbh_platform_data usbh1_config = {
+	.init		= initialize_usbh1_port,
+	.portsc	= MXC_EHCI_MODE_ULPI,
+	.flags	= (MXC_EHCI_POWER_PINS_ENABLED | MXC_EHCI_ITC_NO_THRESHOLD),
+};
+
+static int otg_mode_host;
+
+static int __init eukrea_cpuimx51sd_otg_mode(char *options)
+{
+	if (!strcmp(options, "host"))
+		otg_mode_host = 1;
+	else if (!strcmp(options, "device"))
+		otg_mode_host = 0;
+	else
+		pr_info("otg_mode neither \"host\" nor \"device\". "
+			"Defaulting to device\n");
+	return 0;
+}
+__setup("otg_mode=", eukrea_cpuimx51sd_otg_mode);
+
+static struct i2c_gpio_platform_data pdata = {
+	.sda_pin		= I2C_SDA,
+	.sda_is_open_drain	= 0,
+	.scl_pin		= I2C_SCL,
+	.scl_is_open_drain	= 0,
+	.udelay			= 2,
+};
+
+static struct platform_device hsi2c_gpio_device = {
+	.name			= "i2c-gpio",
+	.id			= 0,
+	.dev.platform_data	= &pdata,
+};
+
+static struct mcp251x_platform_data mcp251x_info = {
+	.oscillator_frequency = 24E6,
+};
+
+static struct spi_board_info cpuimx51sd_spi_device[] = {
+	{
+		.modalias        = "mcp2515",
+		.max_speed_hz    = 6500000,
+		.bus_num         = 0,
+		.mode		= SPI_MODE_0,
+		.chip_select     = 0,
+		.platform_data   = &mcp251x_info,
+		.irq             = gpio_to_irq(0 * 32 + 1)
+	},
+};
+
+static int cpuimx51sd_spi1_cs[] = {
+	CAN_NCS,
+};
+
+static const struct spi_imx_master cpuimx51sd_ecspi1_pdata __initconst = {
+	.chipselect	= cpuimx51sd_spi1_cs,
+	.num_chipselect	= ARRAY_SIZE(cpuimx51sd_spi1_cs),
+};
+
+static struct platform_device *platform_devices[] __initdata = {
+	&hsi2c_gpio_device,
+};
+
+static void __init eukrea_cpuimx51sd_init(void)
+{
+	mxc_iomux_v3_setup_multiple_pads(eukrea_cpuimx51sd_pads,
+					ARRAY_SIZE(eukrea_cpuimx51sd_pads));
+
+	imx51_add_imx_uart(0, &uart_pdata);
+	imx51_add_mxc_nand(&eukrea_cpuimx51sd_nand_board_info);
+
+	gpio_request(ETH_RST, "eth_rst");
+	gpio_set_value(ETH_RST, 1);
+	imx51_add_fec(NULL);
+
+	gpio_request(CAN_IRQGPIO, "can_irq");
+	gpio_direction_input(CAN_IRQGPIO);
+	gpio_free(CAN_IRQGPIO);
+	gpio_request(CAN_NCS, "can_ncs");
+	gpio_direction_output(CAN_NCS, 1);
+	gpio_free(CAN_NCS);
+	gpio_request(CAN_RST, "can_rst");
+	gpio_direction_output(CAN_RST, 0);
+	msleep(20);
+	gpio_set_value(CAN_RST, 1);
+	imx51_add_ecspi(0, &cpuimx51sd_ecspi1_pdata);
+	spi_register_board_info(cpuimx51sd_spi_device,
+				ARRAY_SIZE(cpuimx51sd_spi_device));
+
+	gpio_request(TSC2007_IRQGPIO, "tsc2007_irq");
+	gpio_direction_input(TSC2007_IRQGPIO);
+	gpio_free(TSC2007_IRQGPIO);
+
+	i2c_register_board_info(0, eukrea_cpuimx51sd_i2c_devices,
+			ARRAY_SIZE(eukrea_cpuimx51sd_i2c_devices));
+	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
+
+	if (otg_mode_host)
+		mxc_register_device(&mxc_usbdr_host_device, &dr_utmi_config);
+	else {
+		initialize_otg_port(NULL);
+		mxc_register_device(&mxc_usbdr_udc_device, &usb_pdata);
+	}
+
+	gpio_request(USBH1_RST, "usb_rst");
+	gpio_direction_output(USBH1_RST, 0);
+	msleep(20);
+	gpio_set_value(USBH1_RST, 1);
+	mxc_register_device(&mxc_usbh1_device, &usbh1_config);
+
+#ifdef CONFIG_MACH_EUKREA_MBIMXSD51_BASEBOARD
+	eukrea_mbimxsd51_baseboard_init();
+#endif
+}
+
+static void __init eukrea_cpuimx51sd_timer_init(void)
+{
+	mx51_clocks_init(32768, 24000000, 22579200, 0);
+}
+
+static struct sys_timer mxc_timer = {
+	.init	= eukrea_cpuimx51sd_timer_init,
+};
+
+MACHINE_START(EUKREA_CPUIMX51SD, "Eukrea CPUIMX51SD")
+	/* Maintainer: Eric Bénard <eric@eukrea.com> */
+	.boot_params = PHYS_OFFSET + 0x100,
+	.map_io = mx51_map_io,
+	.init_irq = mx51_init_irq,
+	.init_machine = eukrea_cpuimx51sd_init,
+	.timer = &mxc_timer,
+MACHINE_END
diff --git a/arch/arm/mach-mx5/board-mx51_3ds.c b/arch/arm/mach-mx5/board-mx51_3ds.c
index f95c2fd..79ce8dc 100644
--- a/arch/arm/mach-mx5/board-mx51_3ds.c
+++ b/arch/arm/mach-mx5/board-mx51_3ds.c
@@ -13,6 +13,7 @@
 #include <linux/irq.h>
 #include <linux/platform_device.h>
 #include <linux/input/matrix_keypad.h>
+#include <linux/spi/spi.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -21,12 +22,13 @@
 #include <mach/hardware.h>
 #include <mach/common.h>
 #include <mach/iomux-mx51.h>
-#include <mach/imx-uart.h>
 #include <mach/3ds_debugboard.h>
 
+#include "devices-imx51.h"
 #include "devices.h"
 
 #define EXPIO_PARENT_INT	(MXC_INTERNAL_IRQS + GPIO_PORTA + 6)
+#define MX51_3DS_ECSPI2_CS	(GPIO_PORTC + 28)
 
 static struct pad_desc mx51_3ds_pads[] = {
 	/* UART1 */
@@ -61,19 +63,25 @@
 	MX51_PAD_KEY_COL3__KEY_COL3,
 	MX51_PAD_KEY_COL4__KEY_COL4,
 	MX51_PAD_KEY_COL5__KEY_COL5,
+
+	/* eCSPI2 */
+	MX51_PAD_NANDF_RB2__ECSPI2_SCLK,
+	MX51_PAD_NANDF_RB3__ECSPI2_MISO,
+	MX51_PAD_NANDF_D15__ECSPI2_MOSI,
+	MX51_PAD_NANDF_D12__GPIO_3_28,
 };
 
 /* Serial ports */
 #if defined(CONFIG_SERIAL_IMX) || defined(CONFIG_SERIAL_IMX_MODULE)
-static struct imxuart_platform_data uart_pdata = {
+static const struct imxuart_platform_data uart_pdata __initconst = {
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
 static inline void mxc_init_imx_uart(void)
 {
-	mxc_register_device(&mxc_uart_device0, &uart_pdata);
-	mxc_register_device(&mxc_uart_device1, &uart_pdata);
-	mxc_register_device(&mxc_uart_device2, &uart_pdata);
+	imx51_add_imx_uart(0, &uart_pdata);
+	imx51_add_imx_uart(1, &uart_pdata);
+	imx51_add_imx_uart(2, &uart_pdata);
 }
 #else /* !SERIAL_IMX */
 static inline void mxc_init_imx_uart(void)
@@ -127,6 +135,26 @@
 }
 #endif
 
+static int mx51_3ds_spi2_cs[] = {
+	MXC_SPI_CS(0),
+	MX51_3DS_ECSPI2_CS,
+};
+
+static const struct spi_imx_master mx51_3ds_ecspi2_pdata __initconst = {
+	.chipselect	= mx51_3ds_spi2_cs,
+	.num_chipselect	= ARRAY_SIZE(mx51_3ds_spi2_cs),
+};
+
+static struct spi_board_info mx51_3ds_spi_nor_device[] = {
+	{
+	 .modalias = "m25p80",
+	 .max_speed_hz = 25000000,	/* max spi clock (SCK) speed in HZ */
+	 .bus_num = 1,
+	 .chip_select = 1,
+	 .mode = SPI_MODE_0,
+	 .platform_data = NULL,},
+};
+
 /*
  * Board specific initialization.
  */
@@ -136,6 +164,10 @@
 					ARRAY_SIZE(mx51_3ds_pads));
 	mxc_init_imx_uart();
 
+	imx51_add_ecspi(1, &mx51_3ds_ecspi2_pdata);
+	spi_register_board_info(mx51_3ds_spi_nor_device,
+				ARRAY_SIZE(mx51_3ds_spi_nor_device));
+
 	if (mxc_expio_init(MX51_CS5_BASE_ADDR, EXPIO_PARENT_INT))
 		printk(KERN_WARNING "Init of the debugboard failed, all "
 				    "devices on the board are unusable.\n");
@@ -154,8 +186,6 @@
 
 MACHINE_START(MX51_3DS, "Freescale MX51 3-Stack Board")
 	/* Maintainer: Freescale Semiconductor, Inc. */
-	.phys_io = MX51_AIPS1_BASE_ADDR,
-	.io_pg_offst = ((MX51_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params = PHYS_OFFSET + 0x100,
 	.map_io = mx51_map_io,
 	.init_irq = mx51_init_irq,
diff --git a/arch/arm/mach-mx5/board-mx51_babbage.c b/arch/arm/mach-mx5/board-mx51_babbage.c
index 6e384d9..0821fe9 100644
--- a/arch/arm/mach-mx5/board-mx51_babbage.c
+++ b/arch/arm/mach-mx5/board-mx51_babbage.c
@@ -17,12 +17,11 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/fsl_devices.h>
+#include <linux/fec.h>
 
 #include <mach/common.h>
 #include <mach/hardware.h>
-#include <mach/imx-uart.h>
 #include <mach/iomux-mx51.h>
-#include <mach/i2c.h>
 #include <mach/mxc_ehci.h>
 
 #include <asm/irq.h>
@@ -31,11 +30,13 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 
+#include "devices-imx51.h"
 #include "devices.h"
 
 #define BABBAGE_USB_HUB_RESET	(0*32 + 7)	/* GPIO_1_7 */
 #define BABBAGE_USBH1_STP	(0*32 + 27)	/* GPIO_1_27 */
-#define BABBAGE_PHY_RESET (1*32 +5)	/* GPIO_2_5 */
+#define BABBAGE_PHY_RESET	(1*32 + 5)	/* GPIO_2_5 */
+#define BABBAGE_FEC_PHY_RESET	(1*32 + 14)	/* GPIO_2_14 */
 
 /* USB_CTRL_1 */
 #define MX51_USB_CTRL_1_OFFSET			0x10
@@ -45,10 +46,6 @@
 #define	MX51_USB_PLL_DIV_19_2_MHZ	0x01
 #define	MX51_USB_PLL_DIV_24_MHZ	0x02
 
-static struct platform_device *devices[] __initdata = {
-	&mxc_fec_device,
-};
-
 static struct pad_desc mx51babbage_pads[] = {
 	/* UART1 */
 	MX51_PAD_UART1_RXD__UART1_RXD,
@@ -93,19 +90,41 @@
 
 	/* USB HUB reset line*/
 	MX51_PAD_GPIO_1_7__GPIO_1_7,
+
+	/* FEC */
+	MX51_PAD_EIM_EB2__FEC_MDIO,
+	MX51_PAD_EIM_EB3__FEC_RDAT1,
+	MX51_PAD_EIM_CS2__FEC_RDAT2,
+	MX51_PAD_EIM_CS3__FEC_RDAT3,
+	MX51_PAD_EIM_CS4__FEC_RX_ER,
+	MX51_PAD_EIM_CS5__FEC_CRS,
+	MX51_PAD_NANDF_RB2__FEC_COL,
+	MX51_PAD_NANDF_RB3__FEC_RXCLK,
+	MX51_PAD_NANDF_RB6__FEC_RDAT0,
+	MX51_PAD_NANDF_RB7__FEC_TDAT0,
+	MX51_PAD_NANDF_CS2__FEC_TX_ER,
+	MX51_PAD_NANDF_CS3__FEC_MDC,
+	MX51_PAD_NANDF_CS4__FEC_TDAT1,
+	MX51_PAD_NANDF_CS5__FEC_TDAT2,
+	MX51_PAD_NANDF_CS6__FEC_TDAT3,
+	MX51_PAD_NANDF_CS7__FEC_TX_EN,
+	MX51_PAD_NANDF_RDY_INT__FEC_TX_CLK,
+
+	/* FEC PHY reset line */
+	MX51_PAD_EIM_A20__GPIO_2_14,
 };
 
 /* Serial ports */
 #if defined(CONFIG_SERIAL_IMX) || defined(CONFIG_SERIAL_IMX_MODULE)
-static struct imxuart_platform_data uart_pdata = {
+static const struct imxuart_platform_data uart_pdata __initconst = {
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
 static inline void mxc_init_imx_uart(void)
 {
-	mxc_register_device(&mxc_uart_device0, &uart_pdata);
-	mxc_register_device(&mxc_uart_device1, &uart_pdata);
-	mxc_register_device(&mxc_uart_device2, &uart_pdata);
+	imx51_add_imx_uart(0, &uart_pdata);
+	imx51_add_imx_uart(1, &uart_pdata);
+	imx51_add_imx_uart(2, &uart_pdata);
 }
 #else /* !SERIAL_IMX */
 static inline void mxc_init_imx_uart(void)
@@ -113,7 +132,7 @@
 }
 #endif /* SERIAL_IMX */
 
-static struct imxi2c_platform_data babbage_i2c_data = {
+static const struct imxi2c_platform_data babbage_i2c_data __initconst = {
 	.bitrate = 100000,
 };
 
@@ -171,6 +190,22 @@
 	gpio_set_value(BABBAGE_USB_HUB_RESET, 1);
 }
 
+static inline void babbage_fec_reset(void)
+{
+	int ret;
+
+	/* reset FEC PHY */
+	ret = gpio_request(BABBAGE_FEC_PHY_RESET, "fec-phy-reset");
+	if (ret) {
+		printk(KERN_ERR"failed to get GPIO_FEC_PHY_RESET: %d\n", ret);
+		return;
+	}
+	gpio_direction_output(BABBAGE_FEC_PHY_RESET, 0);
+	gpio_set_value(BABBAGE_FEC_PHY_RESET, 0);
+	msleep(1);
+	gpio_set_value(BABBAGE_FEC_PHY_RESET, 1);
+}
+
 /* This function is board specific as the bit mask for the plldiv will also
 be different for other Freescale SoCs, thus a common bitmask is not
 possible and cannot get place in /plat-mxc/ehci.c.*/
@@ -178,7 +213,7 @@
 {
 	u32 v;
 	void __iomem *usb_base;
-	u32 usbother_base;
+	void __iomem *usbother_base;
 
 	usb_base = ioremap(MX51_OTG_BASE_ADDR, SZ_4K);
 	usbother_base = usb_base + MX5_USBOTHER_REGS_OFFSET;
@@ -196,7 +231,7 @@
 {
 	u32 v;
 	void __iomem *usb_base;
-	u32 usbother_base;
+	void __iomem *usbother_base;
 
 	usb_base = ioremap(MX51_OTG_BASE_ADDR, SZ_4K);
 	usbother_base = usb_base + MX5_USBOTHER_REGS_OFFSET;
@@ -250,10 +285,11 @@
 	mxc_iomux_v3_setup_multiple_pads(mx51babbage_pads,
 					ARRAY_SIZE(mx51babbage_pads));
 	mxc_init_imx_uart();
-	platform_add_devices(devices, ARRAY_SIZE(devices));
+	babbage_fec_reset();
+	imx51_add_fec(NULL);
 
-	mxc_register_device(&mxc_i2c_device0, &babbage_i2c_data);
-	mxc_register_device(&mxc_i2c_device1, &babbage_i2c_data);
+	imx51_add_imx_i2c(0, &babbage_i2c_data);
+	imx51_add_imx_i2c(1, &babbage_i2c_data);
 	mxc_register_device(&mxc_hsi2c_device, &babbage_hsi2c_data);
 
 	if (otg_mode_host)
@@ -281,9 +317,7 @@
 
 MACHINE_START(MX51_BABBAGE, "Freescale MX51 Babbage Board")
 	/* Maintainer: Amit Kucheria <amit.kucheria@canonical.com> */
-	.phys_io = MX51_AIPS1_BASE_ADDR,
-	.io_pg_offst = ((MX51_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
-	.boot_params = PHYS_OFFSET + 0x100,
+	.boot_params = MX51_PHYS_OFFSET + 0x100,
 	.map_io = mx51_map_io,
 	.init_irq = mx51_init_irq,
 	.init_machine = mxc_board_init,
diff --git a/arch/arm/mach-mx5/board-mx51_efikamx.c b/arch/arm/mach-mx5/board-mx51_efikamx.c
new file mode 100644
index 0000000..6e623bd
--- /dev/null
+++ b/arch/arm/mach-mx5/board-mx51_efikamx.c
@@ -0,0 +1,119 @@
+/*
+ * Copyright (C) 2010 Linaro Limited
+ *
+ * based on code from the following
+ * Copyright 2009-2010 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright 2009-2010 Pegatron Corporation. All Rights Reserved.
+ * Copyright 2009-2010 Genesi USA, Inc. All Rights Reserved.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/fsl_devices.h>
+
+#include <mach/common.h>
+#include <mach/hardware.h>
+#include <mach/iomux-mx51.h>
+#include <mach/i2c.h>
+#include <mach/mxc_ehci.h>
+
+#include <asm/irq.h>
+#include <asm/setup.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/time.h>
+
+#include "devices-imx51.h"
+#include "devices.h"
+
+#define	MX51_USB_PLL_DIV_24_MHZ	0x01
+
+static struct pad_desc mx51efikamx_pads[] = {
+	/* UART1 */
+	MX51_PAD_UART1_RXD__UART1_RXD,
+	MX51_PAD_UART1_TXD__UART1_TXD,
+	MX51_PAD_UART1_RTS__UART1_RTS,
+	MX51_PAD_UART1_CTS__UART1_CTS,
+};
+
+/* Serial ports */
+#if defined(CONFIG_SERIAL_IMX) || defined(CONFIG_SERIAL_IMX_MODULE)
+static const struct imxuart_platform_data uart_pdata = {
+	.flags = IMXUART_HAVE_RTSCTS,
+};
+
+static inline void mxc_init_imx_uart(void)
+{
+	imx51_add_imx_uart(0, &uart_pdata);
+	imx51_add_imx_uart(1, &uart_pdata);
+	imx51_add_imx_uart(2, &uart_pdata);
+}
+#else /* !SERIAL_IMX */
+static inline void mxc_init_imx_uart(void)
+{
+}
+#endif /* SERIAL_IMX */
+
+/* This function is board specific as the bit mask for the plldiv will also
+ * be different for other Freescale SoCs, thus a common bitmask is not
+ * possible and cannot get place in /plat-mxc/ehci.c.
+ */
+static int initialize_otg_port(struct platform_device *pdev)
+{
+	u32 v;
+	void __iomem *usb_base;
+	void __iomem *usbother_base;
+	usb_base = ioremap(MX51_OTG_BASE_ADDR, SZ_4K);
+	usbother_base = (void __iomem *)(usb_base + MX5_USBOTHER_REGS_OFFSET);
+
+	/* Set the PHY clock to 19.2MHz */
+	v = __raw_readl(usbother_base + MXC_USB_PHY_CTR_FUNC2_OFFSET);
+	v &= ~MX5_USB_UTMI_PHYCTRL1_PLLDIV_MASK;
+	v |= MX51_USB_PLL_DIV_24_MHZ;
+	__raw_writel(v, usbother_base + MXC_USB_PHY_CTR_FUNC2_OFFSET);
+	iounmap(usb_base);
+	return 0;
+}
+
+static struct mxc_usbh_platform_data dr_utmi_config = {
+	.init   = initialize_otg_port,
+	.portsc = MXC_EHCI_UTMI_16BIT,
+	.flags  = MXC_EHCI_INTERNAL_PHY,
+};
+
+static void __init mxc_board_init(void)
+{
+	mxc_iomux_v3_setup_multiple_pads(mx51efikamx_pads,
+					ARRAY_SIZE(mx51efikamx_pads));
+	mxc_register_device(&mxc_usbdr_host_device, &dr_utmi_config);
+	mxc_init_imx_uart();
+}
+
+static void __init mx51_efikamx_timer_init(void)
+{
+	mx51_clocks_init(32768, 24000000, 22579200, 24576000);
+}
+
+static struct sys_timer mxc_timer = {
+	.init	= mx51_efikamx_timer_init,
+};
+
+MACHINE_START(MX51_EFIKAMX, "Genesi EfikaMX nettop")
+	/* Maintainer: Amit Kucheria <amit.kucheria@linaro.org> */
+	.boot_params = MX51_PHYS_OFFSET + 0x100,
+	.map_io = mx51_map_io,
+	.init_irq = mx51_init_irq,
+	.init_machine =  mxc_board_init,
+	.timer = &mxc_timer,
+MACHINE_END
diff --git a/arch/arm/mach-mx5/clock-mx51.c b/arch/arm/mach-mx5/clock-mx51.c
index 57c10a9..f2aae92 100644
--- a/arch/arm/mach-mx5/clock-mx51.c
+++ b/arch/arm/mach-mx5/clock-mx51.c
@@ -41,34 +41,66 @@
 
 #define MAX_DPLL_WAIT_TRIES	1000 /* 1000 * udelay(1) = 1ms */
 
+/* calculate best pre and post dividers to get the required divider */
+static void __calc_pre_post_dividers(u32 div, u32 *pre, u32 *post,
+	u32 max_pre, u32 max_post)
+{
+	if (div >= max_pre * max_post) {
+		*pre = max_pre;
+		*post = max_post;
+	} else if (div >= max_pre) {
+		u32 min_pre, temp_pre, old_err, err;
+		min_pre = DIV_ROUND_UP(div, max_post);
+		old_err = max_pre;
+		for (temp_pre = max_pre; temp_pre >= min_pre; temp_pre--) {
+			err = div % temp_pre;
+			if (err == 0) {
+				*pre = temp_pre;
+				break;
+			}
+			err = temp_pre - err;
+			if (err < old_err) {
+				old_err = err;
+				*pre = temp_pre;
+			}
+		}
+		*post = DIV_ROUND_UP(div, *pre);
+	} else {
+		*pre = div;
+		*post = 1;
+	}
+}
+
+static void _clk_ccgr_setclk(struct clk *clk, unsigned mode)
+{
+	u32 reg = __raw_readl(clk->enable_reg);
+
+	reg &= ~(MXC_CCM_CCGRx_CG_MASK << clk->enable_shift);
+	reg |= mode << clk->enable_shift;
+
+	__raw_writel(reg, clk->enable_reg);
+}
+
 static int _clk_ccgr_enable(struct clk *clk)
 {
-	u32 reg;
-
-	reg = __raw_readl(clk->enable_reg);
-	reg |= MXC_CCM_CCGRx_MOD_ON << clk->enable_shift;
-	__raw_writel(reg, clk->enable_reg);
-
+	_clk_ccgr_setclk(clk, MXC_CCM_CCGRx_MOD_ON);
 	return 0;
 }
 
 static void _clk_ccgr_disable(struct clk *clk)
 {
-	u32 reg;
-	reg = __raw_readl(clk->enable_reg);
-	reg &= ~(MXC_CCM_CCGRx_CG_MASK << clk->enable_shift);
-	__raw_writel(reg, clk->enable_reg);
+	_clk_ccgr_setclk(clk, MXC_CCM_CCGRx_MOD_OFF);
+}
 
+static int _clk_ccgr_enable_inrun(struct clk *clk)
+{
+	_clk_ccgr_setclk(clk, MXC_CCM_CCGRx_MOD_IDLE);
+	return 0;
 }
 
 static void _clk_ccgr_disable_inwait(struct clk *clk)
 {
-	u32 reg;
-
-	reg = __raw_readl(clk->enable_reg);
-	reg &= ~(MXC_CCM_CCGRx_CG_MASK << clk->enable_shift);
-	reg |= MXC_CCM_CCGRx_MOD_IDLE << clk->enable_shift;
-	__raw_writel(reg, clk->enable_reg);
+	_clk_ccgr_setclk(clk, MXC_CCM_CCGRx_MOD_IDLE);
 }
 
 /*
@@ -542,60 +574,60 @@
 	return 0;
 }
 
-static unsigned long clk_uart_get_rate(struct clk *clk)
+#define clk_nfc_set_parent	NULL
+
+static unsigned long clk_nfc_get_rate(struct clk *clk)
 {
-	u32 reg, prediv, podf;
-	unsigned long parent_rate;
+	unsigned long rate;
+	u32 reg, div;
 
-	parent_rate = clk_get_rate(clk->parent);
-
-	reg = __raw_readl(MXC_CCM_CSCDR1);
-	prediv = ((reg & MXC_CCM_CSCDR1_UART_CLK_PRED_MASK) >>
-		  MXC_CCM_CSCDR1_UART_CLK_PRED_OFFSET) + 1;
-	podf = ((reg & MXC_CCM_CSCDR1_UART_CLK_PODF_MASK) >>
-		MXC_CCM_CSCDR1_UART_CLK_PODF_OFFSET) + 1;
-
-	return parent_rate / (prediv * podf);
+	reg = __raw_readl(MXC_CCM_CBCDR);
+	div = ((reg & MXC_CCM_CBCDR_NFC_PODF_MASK) >>
+	       MXC_CCM_CBCDR_NFC_PODF_OFFSET) + 1;
+	rate = clk_get_rate(clk->parent) / div;
+	WARN_ON(rate == 0);
+	return rate;
 }
 
-static int _clk_uart_set_parent(struct clk *clk, struct clk *parent)
+static unsigned long clk_nfc_round_rate(struct clk *clk,
+						unsigned long rate)
 {
-	u32 reg, mux;
+	u32 div;
+	unsigned long parent_rate = clk_get_rate(clk->parent);
 
-	mux = _get_mux(parent, &pll1_sw_clk, &pll2_sw_clk, &pll3_sw_clk,
-		       &lp_apm_clk);
-	reg = __raw_readl(MXC_CCM_CSCMR1) & ~MXC_CCM_CSCMR1_UART_CLK_SEL_MASK;
-	reg |= mux << MXC_CCM_CSCMR1_UART_CLK_SEL_OFFSET;
-	__raw_writel(reg, MXC_CCM_CSCMR1);
+	if (!rate)
+		return -EINVAL;
 
-	return 0;
+	div = parent_rate / rate;
+
+	if (parent_rate % rate)
+		div++;
+
+	if (div > 8)
+		return -EINVAL;
+
+	return parent_rate / div;
+
 }
 
-static unsigned long clk_usboh3_get_rate(struct clk *clk)
+static int clk_nfc_set_rate(struct clk *clk, unsigned long rate)
 {
-	u32 reg, prediv, podf;
-	unsigned long parent_rate;
+	u32 reg, div;
 
-	parent_rate = clk_get_rate(clk->parent);
+	div = clk_get_rate(clk->parent) / rate;
+	if (div == 0)
+		div++;
+	if (((clk_get_rate(clk->parent) / div) != rate) || (div > 8))
+		return -EINVAL;
 
-	reg = __raw_readl(MXC_CCM_CSCDR1);
-	prediv = ((reg & MXC_CCM_CSCDR1_USBOH3_CLK_PRED_MASK) >>
-		  MXC_CCM_CSCDR1_USBOH3_CLK_PRED_OFFSET) + 1;
-	podf = ((reg & MXC_CCM_CSCDR1_USBOH3_CLK_PODF_MASK) >>
-		MXC_CCM_CSCDR1_USBOH3_CLK_PODF_OFFSET) + 1;
+	reg = __raw_readl(MXC_CCM_CBCDR);
+	reg &= ~MXC_CCM_CBCDR_NFC_PODF_MASK;
+	reg |= (div - 1) << MXC_CCM_CBCDR_NFC_PODF_OFFSET;
+	__raw_writel(reg, MXC_CCM_CBCDR);
 
-	return parent_rate / (prediv * podf);
-}
-
-static int _clk_usboh3_set_parent(struct clk *clk, struct clk *parent)
-{
-	u32 reg, mux;
-
-	mux = _get_mux(parent, &pll1_sw_clk, &pll2_sw_clk, &pll3_sw_clk,
-		       &lp_apm_clk);
-	reg = __raw_readl(MXC_CCM_CSCMR1) & ~MXC_CCM_CSCMR1_USBOH3_CLK_SEL_MASK;
-	reg |= mux << MXC_CCM_CSCMR1_USBOH3_CLK_SEL_OFFSET;
-	__raw_writel(reg, MXC_CCM_CSCMR1);
+	while (__raw_readl(MXC_CCM_CDHIPR) &
+			MXC_CCM_CDHIPR_NFC_IPG_INT_MEM_PODF_BUSY){
+	}
 
 	return 0;
 }
@@ -620,6 +652,17 @@
 	return ckih2_reference;
 }
 
+static unsigned long clk_emi_slow_get_rate(struct clk *clk)
+{
+	u32 reg, div;
+
+	reg = __raw_readl(MXC_CCM_CBCDR);
+	div = ((reg & MXC_CCM_CBCDR_EMI_PODF_MASK) >>
+	       MXC_CCM_CBCDR_EMI_PODF_OFFSET) + 1;
+
+	return clk_get_rate(clk->parent) / div;
+}
+
 /* External high frequency clock */
 static struct clk ckih_clk = {
 	.get_rate = get_high_reference_clock_rate,
@@ -715,18 +758,6 @@
 	.set_parent = _clk_ipg_per_set_parent,
 };
 
-static struct clk uart_root_clk = {
-	.parent = &pll2_sw_clk,
-	.get_rate = clk_uart_get_rate,
-	.set_parent = _clk_uart_set_parent,
-};
-
-static struct clk usboh3_clk = {
-	.parent = &pll2_sw_clk,
-	.get_rate = clk_usboh3_get_rate,
-	.set_parent = _clk_usboh3_set_parent,
-};
-
 static struct clk ahb_max_clk = {
 	.parent = &ahb_clk,
 	.enable_reg = MXC_CCM_CCGR0,
@@ -762,45 +793,183 @@
 	.id = 0,
 };
 
-#define DEFINE_CLOCK(name, i, er, es, gr, sr, p, s)	\
+static struct clk emi_slow_clk = {
+	.parent = &pll2_sw_clk,
+	.enable_reg = MXC_CCM_CCGR5,
+	.enable_shift = MXC_CCM_CCGRx_CG8_OFFSET,
+	.enable = _clk_ccgr_enable,
+	.disable = _clk_ccgr_disable_inwait,
+	.get_rate = clk_emi_slow_get_rate,
+};
+
+#define DEFINE_CLOCK_CCGR(name, i, er, es, pfx, p, s)	\
 	static struct clk name = {			\
 		.id		= i,			\
 		.enable_reg	= er,			\
 		.enable_shift	= es,			\
-		.get_rate	= gr,			\
-		.set_rate	= sr,			\
+		.get_rate	= pfx##_get_rate,	\
+		.set_rate	= pfx##_set_rate,	\
+		.round_rate	= pfx##_round_rate,	\
+		.set_parent	= pfx##_set_parent,	\
 		.enable		= _clk_ccgr_enable,	\
 		.disable	= _clk_ccgr_disable,	\
 		.parent		= p,			\
 		.secondary	= s,			\
 	}
 
-/* DEFINE_CLOCK(name, id, enable_reg, enable_shift,
-   get_rate, set_rate, parent, secondary); */
+#define DEFINE_CLOCK_MAX(name, i, er, es, pfx, p, s)	\
+	static struct clk name = {			\
+		.id		= i,			\
+		.enable_reg	= er,			\
+		.enable_shift	= es,			\
+		.get_rate	= pfx##_get_rate,	\
+		.set_rate	= pfx##_set_rate,	\
+		.set_parent	= pfx##_set_parent,	\
+		.enable		= _clk_max_enable,	\
+		.disable	= _clk_max_disable,	\
+		.parent		= p,			\
+		.secondary	= s,			\
+	}
+
+#define CLK_GET_RATE(name, nr, bitsname)				\
+static unsigned long clk_##name##_get_rate(struct clk *clk)		\
+{									\
+	u32 reg, pred, podf;						\
+									\
+	reg = __raw_readl(MXC_CCM_CSCDR##nr);				\
+	pred = (reg & MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PRED_MASK)	\
+		>> MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PRED_OFFSET;	\
+	podf = (reg & MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PODF_MASK)	\
+		>> MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PODF_OFFSET;	\
+									\
+	return DIV_ROUND_CLOSEST(clk_get_rate(clk->parent),		\
+			(pred + 1) * (podf + 1));			\
+}
+
+#define CLK_SET_PARENT(name, nr, bitsname)				\
+static int clk_##name##_set_parent(struct clk *clk, struct clk *parent)	\
+{									\
+	u32 reg, mux;							\
+									\
+	mux = _get_mux(parent, &pll1_sw_clk, &pll2_sw_clk,		\
+			&pll3_sw_clk, &lp_apm_clk);			\
+	reg = __raw_readl(MXC_CCM_CSCMR##nr) &				\
+		~MXC_CCM_CSCMR##nr##_##bitsname##_CLK_SEL_MASK;		\
+	reg |= mux << MXC_CCM_CSCMR##nr##_##bitsname##_CLK_SEL_OFFSET;	\
+	__raw_writel(reg, MXC_CCM_CSCMR##nr);				\
+									\
+	return 0;							\
+}
+
+#define CLK_SET_RATE(name, nr, bitsname)				\
+static int clk_##name##_set_rate(struct clk *clk, unsigned long rate)	\
+{									\
+	u32 reg, div, parent_rate;					\
+	u32 pre = 0, post = 0;						\
+									\
+	parent_rate = clk_get_rate(clk->parent);			\
+	div = parent_rate / rate;					\
+									\
+	if ((parent_rate / div) != rate)				\
+		return -EINVAL;						\
+									\
+	__calc_pre_post_dividers(div, &pre, &post,			\
+		(MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PRED_MASK >>	\
+		MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PRED_OFFSET) + 1,	\
+		(MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PODF_MASK >>	\
+		MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PODF_OFFSET) + 1);\
+									\
+	/* Set sdhc1 clock divider */					\
+	reg = __raw_readl(MXC_CCM_CSCDR##nr) &				\
+		~(MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PRED_MASK	\
+		| MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PODF_MASK);	\
+	reg |= (post - 1) <<						\
+		MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PODF_OFFSET;	\
+	reg |= (pre - 1) <<						\
+		MXC_CCM_CSCDR##nr##_##bitsname##_CLK_PRED_OFFSET;	\
+	__raw_writel(reg, MXC_CCM_CSCDR##nr);				\
+									\
+	return 0;							\
+}
+
+/* UART */
+CLK_GET_RATE(uart, 1, UART)
+CLK_SET_PARENT(uart, 1, UART)
+
+static struct clk uart_root_clk = {
+	.parent = &pll2_sw_clk,
+	.get_rate = clk_uart_get_rate,
+	.set_parent = clk_uart_set_parent,
+};
+
+/* USBOH3 */
+CLK_GET_RATE(usboh3, 1, USBOH3)
+CLK_SET_PARENT(usboh3, 1, USBOH3)
+
+static struct clk usboh3_clk = {
+	.parent = &pll2_sw_clk,
+	.get_rate = clk_usboh3_get_rate,
+	.set_parent = clk_usboh3_set_parent,
+};
+
+/* eCSPI */
+CLK_GET_RATE(ecspi, 2, CSPI)
+CLK_SET_PARENT(ecspi, 1, CSPI)
+
+static struct clk ecspi_main_clk = {
+	.parent = &pll3_sw_clk,
+	.get_rate = clk_ecspi_get_rate,
+	.set_parent = clk_ecspi_set_parent,
+};
+
+/* eSDHC */
+CLK_GET_RATE(esdhc1, 1, ESDHC1_MSHC1)
+CLK_SET_PARENT(esdhc1, 1, ESDHC1_MSHC1)
+CLK_SET_RATE(esdhc1, 1, ESDHC1_MSHC1)
+
+CLK_GET_RATE(esdhc2, 1, ESDHC2_MSHC2)
+CLK_SET_PARENT(esdhc2, 1, ESDHC2_MSHC2)
+CLK_SET_RATE(esdhc2, 1, ESDHC2_MSHC2)
+
+#define DEFINE_CLOCK_FULL(name, i, er, es, gr, sr, e, d, p, s)		\
+	static struct clk name = {					\
+		.id		= i,					\
+		.enable_reg	= er,					\
+		.enable_shift	= es,					\
+		.get_rate	= gr,					\
+		.set_rate	= sr,					\
+		.enable		= e,					\
+		.disable	= d,					\
+		.parent		= p,					\
+		.secondary	= s,					\
+	}
+
+#define DEFINE_CLOCK(name, i, er, es, gr, sr, p, s)			\
+	DEFINE_CLOCK_FULL(name, i, er, es, gr, sr, _clk_ccgr_enable, _clk_ccgr_disable, p, s)
 
 /* Shared peripheral bus arbiter */
 DEFINE_CLOCK(spba_clk, 0, MXC_CCM_CCGR5, MXC_CCM_CCGRx_CG0_OFFSET,
 	NULL,  NULL, &ipg_clk, NULL);
 
 /* UART */
-DEFINE_CLOCK(uart1_clk, 0, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG4_OFFSET,
-	NULL,  NULL, &uart_root_clk, NULL);
-DEFINE_CLOCK(uart2_clk, 1, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG6_OFFSET,
-	NULL,  NULL, &uart_root_clk, NULL);
-DEFINE_CLOCK(uart3_clk, 2, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG8_OFFSET,
-	NULL,  NULL, &uart_root_clk, NULL);
 DEFINE_CLOCK(uart1_ipg_clk, 0, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG3_OFFSET,
 	NULL,  NULL, &ipg_clk, &aips_tz1_clk);
 DEFINE_CLOCK(uart2_ipg_clk, 1, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG5_OFFSET,
 	NULL,  NULL, &ipg_clk, &aips_tz1_clk);
 DEFINE_CLOCK(uart3_ipg_clk, 2, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG7_OFFSET,
 	NULL,  NULL, &ipg_clk, &spba_clk);
+DEFINE_CLOCK(uart1_clk, 0, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG4_OFFSET,
+	NULL,  NULL, &uart_root_clk, &uart1_ipg_clk);
+DEFINE_CLOCK(uart2_clk, 1, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG6_OFFSET,
+	NULL,  NULL, &uart_root_clk, &uart2_ipg_clk);
+DEFINE_CLOCK(uart3_clk, 2, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG8_OFFSET,
+	NULL,  NULL, &uart_root_clk, &uart3_ipg_clk);
 
 /* GPT */
-DEFINE_CLOCK(gpt_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG9_OFFSET,
-	NULL,  NULL, &ipg_clk, NULL);
 DEFINE_CLOCK(gpt_ipg_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG10_OFFSET,
 	NULL,  NULL, &ipg_clk, NULL);
+DEFINE_CLOCK(gpt_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG9_OFFSET,
+	NULL,  NULL, &ipg_clk, &gpt_ipg_clk);
 
 /* I2C */
 DEFINE_CLOCK(i2c1_clk, 0, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG9_OFFSET,
@@ -814,6 +983,52 @@
 DEFINE_CLOCK(fec_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG12_OFFSET,
 	NULL,  NULL, &ipg_clk, NULL);
 
+/* NFC */
+DEFINE_CLOCK_CCGR(nfc_clk, 0, MXC_CCM_CCGR5, MXC_CCM_CCGRx_CG10_OFFSET,
+	clk_nfc, &emi_slow_clk, NULL);
+
+/* SSI */
+DEFINE_CLOCK(ssi1_ipg_clk, 0, MXC_CCM_CCGR3, MXC_CCM_CCGRx_CG8_OFFSET,
+	NULL, NULL, &ipg_clk, NULL);
+DEFINE_CLOCK(ssi1_clk, 0, MXC_CCM_CCGR3, MXC_CCM_CCGRx_CG9_OFFSET,
+	NULL, NULL, &pll3_sw_clk, &ssi1_ipg_clk);
+DEFINE_CLOCK(ssi2_ipg_clk, 1, MXC_CCM_CCGR3, MXC_CCM_CCGRx_CG10_OFFSET,
+	NULL, NULL, &ipg_clk, NULL);
+DEFINE_CLOCK(ssi2_clk, 1, MXC_CCM_CCGR3, MXC_CCM_CCGRx_CG11_OFFSET,
+	NULL, NULL, &pll3_sw_clk, &ssi2_ipg_clk);
+
+/* eCSPI */
+DEFINE_CLOCK_FULL(ecspi1_ipg_clk, 0, MXC_CCM_CCGR4, MXC_CCM_CCGRx_CG9_OFFSET,
+		NULL, NULL, _clk_ccgr_enable_inrun, _clk_ccgr_disable,
+		&ipg_clk, &spba_clk);
+DEFINE_CLOCK(ecspi1_clk, 0, MXC_CCM_CCGR4, MXC_CCM_CCGRx_CG10_OFFSET,
+		NULL, NULL, &ecspi_main_clk, &ecspi1_ipg_clk);
+DEFINE_CLOCK_FULL(ecspi2_ipg_clk, 0, MXC_CCM_CCGR4, MXC_CCM_CCGRx_CG11_OFFSET,
+		NULL, NULL, _clk_ccgr_enable_inrun, _clk_ccgr_disable,
+		&ipg_clk, &aips_tz2_clk);
+DEFINE_CLOCK(ecspi2_clk, 0, MXC_CCM_CCGR4, MXC_CCM_CCGRx_CG12_OFFSET,
+		NULL, NULL, &ecspi_main_clk, &ecspi2_ipg_clk);
+
+/* CSPI */
+DEFINE_CLOCK(cspi_ipg_clk, 0, MXC_CCM_CCGR4, MXC_CCM_CCGRx_CG9_OFFSET,
+		NULL, NULL, &ipg_clk, &aips_tz2_clk);
+DEFINE_CLOCK(cspi_clk, 0, MXC_CCM_CCGR4, MXC_CCM_CCGRx_CG13_OFFSET,
+		NULL, NULL, &ipg_clk, &cspi_ipg_clk);
+
+/* SDMA */
+DEFINE_CLOCK(sdma_clk, 1, MXC_CCM_CCGR4, MXC_CCM_CCGRx_CG15_OFFSET,
+		NULL, NULL, &ahb_clk, NULL);
+
+/* eSDHC */
+DEFINE_CLOCK_FULL(esdhc1_ipg_clk, 0, MXC_CCM_CCGR3, MXC_CCM_CCGRx_CG0_OFFSET,
+	NULL,  NULL, _clk_max_enable, _clk_max_disable, &ipg_clk, NULL);
+DEFINE_CLOCK_MAX(esdhc1_clk, 0, MXC_CCM_CCGR3, MXC_CCM_CCGRx_CG1_OFFSET,
+	clk_esdhc1, &pll2_sw_clk, &esdhc1_ipg_clk);
+DEFINE_CLOCK_FULL(esdhc2_ipg_clk, 1, MXC_CCM_CCGR3, MXC_CCM_CCGRx_CG2_OFFSET,
+	NULL,  NULL, _clk_max_enable, _clk_max_disable, &ipg_clk, NULL);
+DEFINE_CLOCK_MAX(esdhc2_clk, 1, MXC_CCM_CCGR3, MXC_CCM_CCGRx_CG3_OFFSET,
+	clk_esdhc2, &pll2_sw_clk, &esdhc2_ipg_clk);
+
 #define _REGISTER_CLOCK(d, n, c) \
        { \
 		.dev_id = d, \
@@ -837,6 +1052,18 @@
 	_REGISTER_CLOCK("fsl-usb2-udc", "usb", usboh3_clk)
 	_REGISTER_CLOCK("fsl-usb2-udc", "usb_ahb", ahb_clk)
 	_REGISTER_CLOCK("imx-keypad.0", NULL, kpp_clk)
+	_REGISTER_CLOCK("mxc_nand", NULL, nfc_clk)
+	_REGISTER_CLOCK("imx-ssi.0", NULL, ssi1_clk)
+	_REGISTER_CLOCK("imx-ssi.1", NULL, ssi2_clk)
+	_REGISTER_CLOCK("imx-sdma", NULL, sdma_clk)
+	_REGISTER_CLOCK(NULL, "ckih", ckih_clk)
+	_REGISTER_CLOCK(NULL, "ckih2", ckih2_clk)
+	_REGISTER_CLOCK(NULL, "gpt_32k", gpt_32k_clk)
+	_REGISTER_CLOCK("imx51-ecspi.0", NULL, ecspi1_clk)
+	_REGISTER_CLOCK("imx51-ecspi.1", NULL, ecspi2_clk)
+	_REGISTER_CLOCK("imx51-cspi.0", NULL, cspi_clk)
+	_REGISTER_CLOCK("sdhci-esdhc-imx.0", NULL, esdhc1_clk)
+	_REGISTER_CLOCK("sdhci-esdhc-imx.1", NULL, esdhc2_clk)
 };
 
 static void clk_tree_init(void)
@@ -880,6 +1107,14 @@
 	/* set the usboh3_clk parent to pll2_sw_clk */
 	clk_set_parent(&usboh3_clk, &pll2_sw_clk);
 
+	/* Set SDHC parents to be PLL2 */
+	clk_set_parent(&esdhc1_clk, &pll2_sw_clk);
+	clk_set_parent(&esdhc2_clk, &pll2_sw_clk);
+
+	/* set SDHC root clock as 166.25MHZ*/
+	clk_set_rate(&esdhc1_clk, 166250000);
+	clk_set_rate(&esdhc2_clk, 166250000);
+
 	/* System timer */
 	mxc_timer_init(&gpt_clk, MX51_IO_ADDRESS(MX51_GPT1_BASE_ADDR),
 		MX51_MXC_INT_GPT);
diff --git a/arch/arm/mach-mx5/cpu.c b/arch/arm/mach-mx5/cpu.c
index 2d37785..eaacb6e 100644
--- a/arch/arm/mach-mx5/cpu.c
+++ b/arch/arm/mach-mx5/cpu.c
@@ -70,6 +70,25 @@
 }
 EXPORT_SYMBOL(mx51_revision);
 
+#ifdef CONFIG_NEON
+
+/*
+ * All versions of the silicon before Rev. 3 have broken NEON implementations.
+ * Dependent on link order - so the assumption is that vfp_init is called
+ * before us.
+ */
+static int __init mx51_neon_fixup(void)
+{
+	if (mx51_revision() < MX51_CHIP_REV_3_0 && (elf_hwcap & HWCAP_NEON)) {
+		elf_hwcap &= ~HWCAP_NEON;
+		pr_info("Turning off NEON support, detected broken NEON implementation\n");
+	}
+	return 0;
+}
+
+late_initcall(mx51_neon_fixup);
+#endif
+
 static int __init post_cpu_init(void)
 {
 	unsigned int reg;
diff --git a/arch/arm/mach-mx5/devices-imx51.h b/arch/arm/mach-mx5/devices-imx51.h
new file mode 100644
index 0000000..5cc910e
--- /dev/null
+++ b/arch/arm/mach-mx5/devices-imx51.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) 2010 Pengutronix
+ * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+#include <mach/mx51.h>
+#include <mach/devices-common.h>
+
+extern const struct imx_fec_data imx51_fec_data __initconst;
+#define imx51_add_fec(pdata)	\
+	imx_add_fec(&imx51_fec_data, pdata)
+
+extern const struct imx_imx_i2c_data imx51_imx_i2c_data[] __initconst;
+#define imx51_add_imx_i2c(id, pdata)	\
+	imx_add_imx_i2c(&imx51_imx_i2c_data[id], pdata)
+
+extern const struct imx_imx_ssi_data imx51_imx_ssi_data[] __initconst;
+#define imx51_add_imx_ssi(id, pdata)	\
+	imx_add_imx_ssi(&imx51_imx_ssi_data[id], pdata)
+
+extern const struct imx_imx_uart_1irq_data imx51_imx_uart_data[] __initconst;
+#define imx51_add_imx_uart(id, pdata)	\
+	imx_add_imx_uart_1irq(&imx51_imx_uart_data[id], pdata)
+
+extern const struct imx_mxc_nand_data imx51_mxc_nand_data __initconst;
+#define imx51_add_mxc_nand(pdata)	\
+	imx_add_mxc_nand(&imx51_mxc_nand_data, pdata)
+
+extern const struct imx_spi_imx_data imx51_cspi_data __initconst;
+#define imx51_add_cspi(pdata)	\
+	imx_add_spi_imx(&imx51_cspi_data, pdata)
+
+extern const struct imx_spi_imx_data imx51_ecspi_data[] __initconst;
+#define imx51_add_ecspi(id, pdata)	\
+	imx_add_spi_imx(&imx51_ecspi_data[id], pdata)
+
+extern const struct imx_esdhc_imx_data imx51_esdhc_data[] __initconst;
+#define imx51_add_esdhc(id, pdata)	\
+	imx_add_esdhc(&imx51_esdhc_data[id], pdata)
diff --git a/arch/arm/mach-mx5/devices.c b/arch/arm/mach-mx5/devices.c
index 1920ff4..4c7be87 100644
--- a/arch/arm/mach-mx5/devices.c
+++ b/arch/arm/mach-mx5/devices.c
@@ -17,120 +17,6 @@
 #include <mach/imx-uart.h>
 #include <mach/irqs.h>
 
-static struct resource uart0[] = {
-	{
-		.start = MX51_UART1_BASE_ADDR,
-		.end = MX51_UART1_BASE_ADDR + 0xfff,
-		.flags = IORESOURCE_MEM,
-	}, {
-		.start = MX51_MXC_INT_UART1,
-		.end = MX51_MXC_INT_UART1,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mxc_uart_device0 = {
-	.name = "imx-uart",
-	.id = 0,
-	.resource = uart0,
-	.num_resources = ARRAY_SIZE(uart0),
-};
-
-static struct resource uart1[] = {
-	{
-		.start = MX51_UART2_BASE_ADDR,
-		.end = MX51_UART2_BASE_ADDR + 0xfff,
-		.flags = IORESOURCE_MEM,
-	}, {
-		.start = MX51_MXC_INT_UART2,
-		.end = MX51_MXC_INT_UART2,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mxc_uart_device1 = {
-	.name = "imx-uart",
-	.id = 1,
-	.resource = uart1,
-	.num_resources = ARRAY_SIZE(uart1),
-};
-
-static struct resource uart2[] = {
-	{
-		.start = MX51_UART3_BASE_ADDR,
-		.end = MX51_UART3_BASE_ADDR + 0xfff,
-		.flags = IORESOURCE_MEM,
-	}, {
-		.start = MX51_MXC_INT_UART3,
-		.end = MX51_MXC_INT_UART3,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mxc_uart_device2 = {
-	.name = "imx-uart",
-	.id = 2,
-	.resource = uart2,
-	.num_resources = ARRAY_SIZE(uart2),
-};
-
-static struct resource mxc_fec_resources[] = {
-	{
-		.start	= MX51_MXC_FEC_BASE_ADDR,
-		.end	= MX51_MXC_FEC_BASE_ADDR + 0xfff,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= MX51_MXC_INT_FEC,
-		.end	= MX51_MXC_INT_FEC,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mxc_fec_device = {
-	.name = "fec",
-	.id = 0,
-	.num_resources = ARRAY_SIZE(mxc_fec_resources),
-	.resource = mxc_fec_resources,
-};
-
-static struct resource mxc_i2c0_resources[] = {
-	{
-		.start = MX51_I2C1_BASE_ADDR,
-		.end = MX51_I2C1_BASE_ADDR + SZ_4K - 1,
-		.flags = IORESOURCE_MEM,
-	}, {
-		.start = MX51_MXC_INT_I2C1,
-		.end = MX51_MXC_INT_I2C1,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mxc_i2c_device0 = {
-	.name = "imx-i2c",
-	.id = 0,
-	.num_resources = ARRAY_SIZE(mxc_i2c0_resources),
-	.resource = mxc_i2c0_resources,
-};
-
-static struct resource mxc_i2c1_resources[] = {
-	{
-		.start = MX51_I2C2_BASE_ADDR,
-		.end = MX51_I2C2_BASE_ADDR + SZ_4K - 1,
-		.flags = IORESOURCE_MEM,
-	}, {
-		.start = MX51_MXC_INT_I2C2,
-		.end = MX51_MXC_INT_I2C2,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device mxc_i2c_device1 = {
-	.name = "imx-i2c",
-	.id = 1,
-	.num_resources = ARRAY_SIZE(mxc_i2c1_resources),
-	.resource = mxc_i2c1_resources,
-};
-
 static struct resource mxc_hsi2c_resources[] = {
 	{
 		.start = MX51_HSI2C_DMA_BASE_ADDR,
diff --git a/arch/arm/mach-mx5/devices.h b/arch/arm/mach-mx5/devices.h
index e509cfa..af1d07c 100644
--- a/arch/arm/mach-mx5/devices.h
+++ b/arch/arm/mach-mx5/devices.h
@@ -1,12 +1,6 @@
-extern struct platform_device mxc_uart_device0;
-extern struct platform_device mxc_uart_device1;
-extern struct platform_device mxc_uart_device2;
-extern struct platform_device mxc_fec_device;
 extern struct platform_device mxc_usbdr_host_device;
 extern struct platform_device mxc_usbh1_device;
 extern struct platform_device mxc_usbdr_udc_device;
 extern struct platform_device mxc_wdt;
-extern struct platform_device mxc_i2c_device0;
-extern struct platform_device mxc_i2c_device1;
 extern struct platform_device mxc_hsi2c_device;
 extern struct platform_device mxc_keypad_device;
diff --git a/arch/arm/mach-mx5/eukrea_mbimx51-baseboard.c b/arch/arm/mach-mx5/eukrea_mbimx51-baseboard.c
index ffa93d1..a2e6e8c 100644
--- a/arch/arm/mach-mx5/eukrea_mbimx51-baseboard.c
+++ b/arch/arm/mach-mx5/eukrea_mbimx51-baseboard.c
@@ -30,6 +30,7 @@
 
 #include <asm/mach/arch.h>
 
+#include "devices-imx51.h"
 #include "devices.h"
 
 #define MBIMX51_TSC2007_GPIO	(2*32 + 30)
@@ -112,9 +113,25 @@
 	MX51_PAD_KEY_COL1__KEY_COL1,
 	MX51_PAD_KEY_COL2__KEY_COL2,
 	MX51_PAD_KEY_COL3__KEY_COL3,
+
+	/* SD 1 */
+	MX51_PAD_SD1_CMD__SD1_CMD,
+	MX51_PAD_SD1_CLK__SD1_CLK,
+	MX51_PAD_SD1_DATA0__SD1_DATA0,
+	MX51_PAD_SD1_DATA1__SD1_DATA1,
+	MX51_PAD_SD1_DATA2__SD1_DATA2,
+	MX51_PAD_SD1_DATA3__SD1_DATA3,
+
+	/* SD 2 */
+	MX51_PAD_SD2_CMD__SD2_CMD,
+	MX51_PAD_SD2_CLK__SD2_CLK,
+	MX51_PAD_SD2_DATA0__SD2_DATA0,
+	MX51_PAD_SD2_DATA1__SD2_DATA1,
+	MX51_PAD_SD2_DATA2__SD2_DATA2,
+	MX51_PAD_SD2_DATA3__SD2_DATA3,
 };
 
-static struct imxuart_platform_data uart_pdata = {
+static const struct imxuart_platform_data uart_pdata __initconst = {
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
@@ -158,9 +175,11 @@
 
 static struct i2c_board_info mbimx51_i2c_devices[] = {
 	{
-		I2C_BOARD_INFO("tsc2007", 0x48),
+		I2C_BOARD_INFO("tsc2007", 0x49),
 		.irq  = MBIMX51_TSC2007_IRQ,
 		.platform_data = &tsc2007_data,
+	}, {
+		I2C_BOARD_INFO("tlv320aic23", 0x1a),
 	},
 };
 
@@ -172,8 +191,8 @@
 	mxc_iomux_v3_setup_multiple_pads(mbimx51_pads,
 					ARRAY_SIZE(mbimx51_pads));
 
-	mxc_register_device(&mxc_uart_device1, NULL);
-	mxc_register_device(&mxc_uart_device2, &uart_pdata);
+	imx51_add_imx_uart(1, NULL);
+	imx51_add_imx_uart(2, &uart_pdata);
 
 	gpio_request(MBIMX51_LED0, "LED0");
 	gpio_direction_output(MBIMX51_LED0, 1);
@@ -197,4 +216,7 @@
 	set_irq_type(MBIMX51_TSC2007_IRQ, IRQF_TRIGGER_FALLING);
 	i2c_register_board_info(1, mbimx51_i2c_devices,
 				ARRAY_SIZE(mbimx51_i2c_devices));
+
+	imx51_add_esdhc(0, NULL);
+	imx51_add_esdhc(1, NULL);
 }
diff --git a/arch/arm/mach-mx5/eukrea_mbimxsd-baseboard.c b/arch/arm/mach-mx5/eukrea_mbimxsd-baseboard.c
new file mode 100644
index 0000000..2b48f51
--- /dev/null
+++ b/arch/arm/mach-mx5/eukrea_mbimxsd-baseboard.c
@@ -0,0 +1,166 @@
+/*
+ * Copyright (C) 2010 Eric Benard - eric@eukrea.com
+ *
+ * Based on pcm970-baseboard.c which is :
+ * Copyright (C) 2008 Juergen Beisert (kernel@pengutronix.de)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include <linux/types.h>
+#include <linux/init.h>
+
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/leds.h>
+#include <linux/platform_device.h>
+#include <linux/gpio_keys.h>
+#include <linux/input.h>
+#include <linux/i2c.h>
+
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/time.h>
+#include <asm/mach/map.h>
+
+#include <mach/hardware.h>
+#include <mach/common.h>
+#include <mach/imx-uart.h>
+#include <mach/iomux-mx51.h>
+#include <mach/audmux.h>
+
+#include "devices-imx51.h"
+#include "devices.h"
+
+#define MBIMXSD_GPIO_3_31 IOMUX_PAD(0x554, 0x16C, 3, 0x0, 0, \
+				MX51_PAD_CTRL_1 | PAD_CTL_PUS_22K_UP)
+
+static struct pad_desc eukrea_mbimxsd_pads[] = {
+	/* LED */
+	MX51_PAD_NANDF_D10__GPIO_3_30,
+	/* SWITCH */
+	MBIMXSD_GPIO_3_31,
+	/* UART2 */
+	MX51_PAD_UART2_RXD__UART2_RXD,
+	MX51_PAD_UART2_TXD__UART2_TXD,
+	/* UART 3 */
+	MX51_PAD_UART3_RXD__UART3_RXD,
+	MX51_PAD_UART3_TXD__UART3_TXD,
+	MX51_PAD_KEY_COL4__UART3_RTS,
+	MX51_PAD_KEY_COL5__UART3_CTS,
+	/* SD */
+	MX51_PAD_SD1_CMD__SD1_CMD,
+	MX51_PAD_SD1_CLK__SD1_CLK,
+	MX51_PAD_SD1_DATA0__SD1_DATA0,
+	MX51_PAD_SD1_DATA1__SD1_DATA1,
+	MX51_PAD_SD1_DATA2__SD1_DATA2,
+	MX51_PAD_SD1_DATA3__SD1_DATA3,
+};
+
+#define GPIO_LED1	(2 * 32 + 30)
+#define GPIO_SWITCH1	(2 * 32 + 31)
+
+static struct gpio_led eukrea_mbimxsd_leds[] = {
+	{
+		.name			= "led1",
+		.default_trigger	= "heartbeat",
+		.active_low		= 1,
+		.gpio			= GPIO_LED1,
+	},
+};
+
+static struct gpio_led_platform_data eukrea_mbimxsd_led_info = {
+	.leds		= eukrea_mbimxsd_leds,
+	.num_leds	= ARRAY_SIZE(eukrea_mbimxsd_leds),
+};
+
+static struct platform_device eukrea_mbimxsd_leds_gpio = {
+	.name	= "leds-gpio",
+	.id	= -1,
+	.dev	= {
+		.platform_data	= &eukrea_mbimxsd_led_info,
+	},
+};
+
+static struct gpio_keys_button eukrea_mbimxsd_gpio_buttons[] = {
+	{
+		.gpio		= GPIO_SWITCH1,
+		.code		= BTN_0,
+		.desc		= "BP1",
+		.active_low	= 1,
+		.wakeup		= 1,
+	},
+};
+
+static struct gpio_keys_platform_data eukrea_mbimxsd_button_data = {
+	.buttons	= eukrea_mbimxsd_gpio_buttons,
+	.nbuttons	= ARRAY_SIZE(eukrea_mbimxsd_gpio_buttons),
+};
+
+static struct platform_device eukrea_mbimxsd_button_device = {
+	.name		= "gpio-keys",
+	.id		= -1,
+	.num_resources	= 0,
+	.dev		= {
+		.platform_data	= &eukrea_mbimxsd_button_data,
+	}
+};
+
+static struct platform_device *platform_devices[] __initdata = {
+	&eukrea_mbimxsd_leds_gpio,
+	&eukrea_mbimxsd_button_device,
+};
+
+static const struct imxuart_platform_data uart_pdata __initconst = {
+	.flags = IMXUART_HAVE_RTSCTS,
+};
+
+static struct i2c_board_info eukrea_mbimxsd_i2c_devices[] = {
+	{
+		I2C_BOARD_INFO("tlv320aic23", 0x1a),
+	},
+};
+
+/*
+ * system init for baseboard usage. Will be called by cpuimx51sd init.
+ *
+ * Add platform devices present on this baseboard and init
+ * them from CPU side as far as required to use them later on
+ */
+void __init eukrea_mbimxsd51_baseboard_init(void)
+{
+	if (mxc_iomux_v3_setup_multiple_pads(eukrea_mbimxsd_pads,
+			ARRAY_SIZE(eukrea_mbimxsd_pads)))
+		printk(KERN_ERR "error setting mbimxsd pads !\n");
+
+	imx51_add_imx_uart(1, NULL);
+	imx51_add_imx_uart(2, &uart_pdata);
+
+	imx51_add_esdhc(0, NULL);
+
+	gpio_request(GPIO_LED1, "LED1");
+	gpio_direction_output(GPIO_LED1, 1);
+	gpio_free(GPIO_LED1);
+
+	gpio_request(GPIO_SWITCH1, "SWITCH1");
+	gpio_direction_input(GPIO_SWITCH1);
+	gpio_free(GPIO_SWITCH1);
+
+	i2c_register_board_info(0, eukrea_mbimxsd_i2c_devices,
+				ARRAY_SIZE(eukrea_mbimxsd_i2c_devices));
+
+	platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices));
+}
diff --git a/arch/arm/mach-mxc91231/magx-zn5.c b/arch/arm/mach-mxc91231/magx-zn5.c
index 69816ba..395d83b 100644
--- a/arch/arm/mach-mxc91231/magx-zn5.c
+++ b/arch/arm/mach-mxc91231/magx-zn5.c
@@ -53,8 +53,6 @@
 };
 
 MACHINE_START(MAGX_ZN5, "Motorola Zn5")
-	.phys_io	= MXC91231_AIPS1_BASE_ADDR,
-	.io_pg_offst	= ((MXC91231_AIPS1_BASE_ADDR_VIRT) >> 18) & 0xfffc,
 	.boot_params	= MXC91231_PHYS_OFFSET + 0x100,
 	.map_io		= mxc91231_map_io,
 	.init_irq	= mxc91231_init_irq,
diff --git a/arch/arm/mach-netx/include/mach/debug-macro.S b/arch/arm/mach-netx/include/mach/debug-macro.S
index e96339e..56a9152 100644
--- a/arch/arm/mach-netx/include/mach/debug-macro.S
+++ b/arch/arm/mach-netx/include/mach/debug-macro.S
@@ -13,12 +13,10 @@
 
 #include "hardware.h"
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x00100000		@ physical
-		movne	\rx, #io_p2v(0x00100000)	@ virtual
-		orr	\rx, \rx, #0x00000a00
+		.macro	addruart, rp, rv
+		mov	\rp, #0x00000a00
+		orr	\rv, \rp, #io_p2v(0x00100000)	@ virtual
+		orr	\rp, \rp, #0x00100000		@ physical
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/mach-netx/include/mach/vmalloc.h b/arch/arm/mach-netx/include/mach/vmalloc.h
index 25d5cc6..7cca357 100644
--- a/arch/arm/mach-netx/include/mach/vmalloc.h
+++ b/arch/arm/mach-netx/include/mach/vmalloc.h
@@ -16,4 +16,4 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#define VMALLOC_END       (PAGE_OFFSET + 0x10000000)
+#define VMALLOC_END       0xd0000000
diff --git a/arch/arm/mach-netx/nxdb500.c b/arch/arm/mach-netx/nxdb500.c
index c9b174b..ca8b203 100644
--- a/arch/arm/mach-netx/nxdb500.c
+++ b/arch/arm/mach-netx/nxdb500.c
@@ -200,8 +200,6 @@
 }
 
 MACHINE_START(NXDB500, "Hilscher nxdb500")
-	.phys_io	= 0x00100000,
-	.io_pg_offst	= (io_p2v(0x00100000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= netx_map_io,
 	.init_irq	= netx_init_irq,
diff --git a/arch/arm/mach-netx/nxdkn.c b/arch/arm/mach-netx/nxdkn.c
index 15b54c6..d775cbe 100644
--- a/arch/arm/mach-netx/nxdkn.c
+++ b/arch/arm/mach-netx/nxdkn.c
@@ -93,8 +93,6 @@
 }
 
 MACHINE_START(NXDKN, "Hilscher nxdkn")
-	.phys_io	= 0x00100000,
-	.io_pg_offst	= (io_p2v(0x00100000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= netx_map_io,
 	.init_irq	= netx_init_irq,
diff --git a/arch/arm/mach-netx/nxeb500hmi.c b/arch/arm/mach-netx/nxeb500hmi.c
index 1061c01..de369cd 100644
--- a/arch/arm/mach-netx/nxeb500hmi.c
+++ b/arch/arm/mach-netx/nxeb500hmi.c
@@ -177,8 +177,6 @@
 }
 
 MACHINE_START(NXEB500HMI, "Hilscher nxeb500hmi")
-	.phys_io	= 0x00100000,
-	.io_pg_offst	= (io_p2v(0x00100000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= netx_map_io,
 	.init_irq	= netx_init_irq,
diff --git a/arch/arm/mach-nomadik/board-nhk8815.c b/arch/arm/mach-nomadik/board-nhk8815.c
index 841d459..1399303 100644
--- a/arch/arm/mach-nomadik/board-nhk8815.c
+++ b/arch/arm/mach-nomadik/board-nhk8815.c
@@ -276,8 +276,6 @@
 
 MACHINE_START(NOMADIK, "NHK8815")
 	/* Maintainer: ST MicroElectronics */
-	.phys_io	= NOMADIK_UART0_BASE,
-	.io_pg_offst	= (IO_ADDRESS(NOMADIK_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x100,
 	.map_io		= cpu8815_map_io,
 	.init_irq	= cpu8815_init_irq,
diff --git a/arch/arm/mach-nomadik/include/mach/debug-macro.S b/arch/arm/mach-nomadik/include/mach/debug-macro.S
index 4f92acf..e7151b4 100644
--- a/arch/arm/mach-nomadik/include/mach/debug-macro.S
+++ b/arch/arm/mach-nomadik/include/mach/debug-macro.S
@@ -10,13 +10,11 @@
  *
 */
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x10000000	@ physical base address
-		movne	\rx, #0xf0000000	@ virtual base
-		add	\rx, \rx, #0x00100000
-		add	\rx, \rx, #0x000fb000
+		.macro	addruart, rp, rv
+		mov	\rp, #0x00100000
+		add	\rp, \rp, #0x000fb000
+		add	\rv, \rp, #0xf0000000	@ virtual base
+		add	\rp, \rp, #0x10000000	@ physical base address
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-ns9xxx/include/mach/debug-macro.S b/arch/arm/mach-ns9xxx/include/mach/debug-macro.S
index 5c934bd..5a2acbd 100644
--- a/arch/arm/mach-ns9xxx/include/mach/debug-macro.S
+++ b/arch/arm/mach-ns9xxx/include/mach/debug-macro.S
@@ -12,11 +12,9 @@
 
 #include <mach/regs-board-a9m9750dev.h>
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, =NS9XXX_CSxSTAT_PHYS(0)
-		ldrne	\rx, =io_p2v(NS9XXX_CSxSTAT_PHYS(0))
+		.macro	addruart, rp, rv
+		ldr	\rp, =NS9XXX_CSxSTAT_PHYS(0)
+		ldr	\rv, =io_p2v(NS9XXX_CSxSTAT_PHYS(0))
 		.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-nuc93x/mach-nuc932evb.c b/arch/arm/mach-nuc93x/mach-nuc932evb.c
index 9f79266..d702570 100644
--- a/arch/arm/mach-nuc93x/mach-nuc932evb.c
+++ b/arch/arm/mach-nuc93x/mach-nuc932evb.c
@@ -35,8 +35,6 @@
 
 MACHINE_START(NUC932EVB, "NUC932EVB")
 	/* Maintainer: Wan ZongShun */
-	.phys_io	= NUC93X_PA_UART,
-	.io_pg_offst	= (((u32)NUC93X_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= 0,
 	.map_io		= nuc932evb_map_io,
 	.init_irq	= nuc93x_init_irq,
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index 41992ab..73c8639 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -297,8 +297,6 @@
 
 MACHINE_START(AMS_DELTA, "Amstrad E3 (Delta)")
 	/* Maintainer: Jonathan McDowell <noodles@earth.li> */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= ams_delta_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-fsample.c b/arch/arm/mach-omap1/board-fsample.c
index 180ce79..149fdd3 100644
--- a/arch/arm/mach-omap1/board-fsample.c
+++ b/arch/arm/mach-omap1/board-fsample.c
@@ -386,8 +386,6 @@
 
 MACHINE_START(OMAP_FSAMPLE, "OMAP730 F-Sample")
 /* Maintainer: Brian Swetland <swetland@google.com> */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= omap_fsample_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-generic.c b/arch/arm/mach-omap1/board-generic.c
index 93b9ab8..23f4ab9 100644
--- a/arch/arm/mach-omap1/board-generic.c
+++ b/arch/arm/mach-omap1/board-generic.c
@@ -94,8 +94,6 @@
 
 MACHINE_START(OMAP_GENERIC, "Generic OMAP1510/1610/1710")
 	/* Maintainer: Tony Lindgren <tony@atomide.com> */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= omap_generic_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index d2cda58..197adb4 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -458,8 +458,6 @@
 
 MACHINE_START(OMAP_H2, "TI-H2")
 	/* Maintainer: Imre Deak <imre.deak@nokia.com> */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= h2_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index c2ef4ff..9126e3e 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -446,8 +446,6 @@
 
 MACHINE_START(OMAP_H3, "TI OMAP1710 H3 board")
 	/* Maintainer: Texas Instruments, Inc. */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= h3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-htcherald.c b/arch/arm/mach-omap1/board-htcherald.c
index 311899f..86afb29 100644
--- a/arch/arm/mach-omap1/board-htcherald.c
+++ b/arch/arm/mach-omap1/board-htcherald.c
@@ -300,8 +300,6 @@
 MACHINE_START(HERALD, "HTC Herald")
 	/* Maintainer: Cory Maccarrone <darkstar6262@gmail.com> */
 	/* Maintainer: wing-linux.sourceforge.net */
-	.phys_io        = 0xfff00000,
-	.io_pg_offst    = ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params    = 0x10000100,
 	.map_io         = htcherald_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index 3daf87a..dc2b86f 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -459,8 +459,6 @@
 
 MACHINE_START(OMAP_INNOVATOR, "TI-Innovator")
 	/* Maintainer: MontaVista Software, Inc. */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= innovator_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 51a4539..aa8375b 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -262,8 +262,6 @@
 }
 
 MACHINE_START(NOKIA770, "Nokia 770")
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= omap_nokia770_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index 679740c..e9dd791 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -580,8 +580,6 @@
 
 MACHINE_START(OMAP_OSK, "TI-OSK")
 	/* Maintainer: Dirk Behme <dirk.behme@de.bosch.com> */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= osk_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-palmte.c b/arch/arm/mach-omap1/board-palmte.c
index 782bb25..f32738b 100644
--- a/arch/arm/mach-omap1/board-palmte.c
+++ b/arch/arm/mach-omap1/board-palmte.c
@@ -285,8 +285,6 @@
 }
 
 MACHINE_START(OMAP_PALMTE, "OMAP310 based Palm Tungsten E")
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= omap_palmte_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-palmtt.c b/arch/arm/mach-omap1/board-palmtt.c
index 0b35ef5..ed1400a 100644
--- a/arch/arm/mach-omap1/board-palmtt.c
+++ b/arch/arm/mach-omap1/board-palmtt.c
@@ -317,8 +317,6 @@
 }
 
 MACHINE_START(OMAP_PALMTT, "OMAP1510 based Palm Tungsten|T")
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= omap_palmtt_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-palmz71.c b/arch/arm/mach-omap1/board-palmz71.c
index 6636290..d7a245c 100644
--- a/arch/arm/mach-omap1/board-palmz71.c
+++ b/arch/arm/mach-omap1/board-palmz71.c
@@ -338,8 +338,6 @@
 }
 
 MACHINE_START(OMAP_PALMZ71, "OMAP310 based Palm Zire71")
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= omap_palmz71_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-perseus2.c b/arch/arm/mach-omap1/board-perseus2.c
index 34ab354..a8d16a2 100644
--- a/arch/arm/mach-omap1/board-perseus2.c
+++ b/arch/arm/mach-omap1/board-perseus2.c
@@ -347,8 +347,6 @@
 
 MACHINE_START(OMAP_PERSEUS2, "OMAP730 Perseus2")
 	/* Maintainer: Kevin Hilman <kjh@hilman.org> */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= omap_perseus2_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-sx1.c b/arch/arm/mach-omap1/board-sx1.c
index 2eb148b..d25f59e 100644
--- a/arch/arm/mach-omap1/board-sx1.c
+++ b/arch/arm/mach-omap1/board-sx1.c
@@ -419,8 +419,6 @@
 }
 
 MACHINE_START(SX1, "OMAP310 based Siemens SX1")
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= omap_sx1_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/board-voiceblue.c b/arch/arm/mach-omap1/board-voiceblue.c
index 6b3cf14..f5992c2 100644
--- a/arch/arm/mach-omap1/board-voiceblue.c
+++ b/arch/arm/mach-omap1/board-voiceblue.c
@@ -283,8 +283,6 @@
 
 MACHINE_START(VOICEBLUE, "VoiceBlue OMAP5910")
 	/* Maintainer: Ladislav Michl <michl@2n.cz> */
-	.phys_io	= 0xfff00000,
-	.io_pg_offst	= ((0xfef00000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.map_io		= voiceblue_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap1/include/mach/debug-macro.S b/arch/arm/mach-omap1/include/mach/debug-macro.S
index 671408e..6a0fa04 100644
--- a/arch/arm/mach-omap1/include/mach/debug-macro.S
+++ b/arch/arm/mach-omap1/include/mach/debug-macro.S
@@ -28,56 +28,58 @@
 		 * the desired UART phys and virt addresses temporarily into
 		 * the omap_uart_phys and omap_uart_virt above.
 		 */
-		.macro	addruart, rx, tmp
+		.macro	addruart, rp, rv
 
 		/* Use omap_uart_phys/virt if already configured */
-9:		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		ldreq	\rx, =__virt_to_phys(omap_uart_phys)	@ physical base address
-		ldrne	\rx, =omap_uart_virt	@ virtual base
-		ldr	\rx, [\rx, #0]
-		cmp	\rx, #0			@ is port configured?
+9:		mrc	p15, 0, \rp, c1, c0
+		tst	\rp, #1			@ MMU enabled?
+		ldreq	\rp, =__virt_to_phys(omap_uart_phys)	@ MMU not enabled
+		ldrne	\rp, =omap_uart_phys	@ MMU enabled
+		add	\rv, \rp, #4		@ omap_uart_virt
+		ldr	\rp, [\rp, #0]
+		ldr	\rv, [\rv, #0]
+		cmp	\rp, #0			@ is port configured?
+		cmpne	\rv, #0
 		bne	99f			@ already configured
 
 		/* Check the debug UART configuration set in uncompress.h */
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		ldreq	\rx, =OMAP_UART_INFO
-		ldrne	\rx, =__phys_to_virt(OMAP_UART_INFO)
-		ldr	\rx, [\rx, #0]
+		mrc	p15, 0, \rp, c1, c0
+		tst	\rp, #1			@ MMU enabled?
+		ldreq	\rp, =OMAP_UART_INFO	@ MMU not enabled
+		ldrne	\rp, =__phys_to_virt(OMAP_UART_INFO)	@ MMU enabled
+		ldr	\rp, [\rp, #0]
 
 		/* Select the UART to use based on the UART1 scratchpad value */
-10:		cmp	\rx, #0			@ no port configured?
+10:		cmp	\rp, #0			@ no port configured?
 		beq	11f			@ if none, try to use UART1
-		cmp	\rx, #OMAP1UART1
+		cmp	\rp, #OMAP1UART1
 		beq	11f			@ configure OMAP1UART1
-		cmp	\rx, #OMAP1UART2
+		cmp	\rp, #OMAP1UART2
 		beq	12f			@ configure OMAP1UART2
-		cmp	\rx, #OMAP1UART3
+		cmp	\rp, #OMAP1UART3
 		beq	13f			@ configure OMAP2UART3
 
 		/* Configure the UART offset from the phys/virt base */
-11:		mov	\rx, #0x00fb0000	@ OMAP1UART1
+11:		mov	\rp, #0x00fb0000	@ OMAP1UART1
 		b	98f
-12:		mov	\rx, #0x00fb0000	@ OMAP1UART1
-		orr	\rx, \rx, #0x00000800	@ OMAP1UART2
+12:		mov	\rp, #0x00fb0000	@ OMAP1UART1
+		orr	\rp, \rp, #0x00000800	@ OMAP1UART2
 		b	98f
-13:		mov	\rx, #0x00fb0000	@ OMAP1UART1
-		orr	\rx, \rx, #0x00000800	@ OMAP1UART2
-		orr	\rx, \rx, #0x00009000	@ OMAP1UART3
+13:		mov	\rp, #0x00fb0000	@ OMAP1UART1
+		orr	\rp, \rp, #0x00000800	@ OMAP1UART2
+		orr	\rp, \rp, #0x00009000	@ OMAP1UART3
 
 		/* Store both phys and virt address for the uart */
-98:		add	\rx, \rx, #0xff000000	@ phys base
-		mrc	p15, 0, \tmp, c1, c0
-		tst	\tmp, #1		@ MMU enabled?
-		ldreq	\tmp, =__virt_to_phys(omap_uart_phys)
-		ldrne	\tmp, =omap_uart_phys
-		str	\rx, [\tmp, #0]
-		sub	\rx, \rx, #0xff000000	@ phys base
-		add	\rx, \rx, #0xfe000000	@ virt base
-		ldreq	\tmp, =__virt_to_phys(omap_uart_virt)
-		ldrne	\tmp, =omap_uart_virt
-		str	\rx, [\tmp, #0]
+98:		add	\rp, \rp, #0xff000000	@ phys base
+		mrc	p15, 0, \rv, c1, c0
+		tst	\rv, #1			@ MMU enabled?
+		ldreq	\rv, =__virt_to_phys(omap_uart_phys)	@ MMU not enabled
+		ldrne	\rv, =omap_uart_phys	@ MMU enabled
+		str	\rp, [\rv, #0]
+		sub	\rp, \rp, #0xff000000	@ phys base
+		add	\rp, \rp, #0xfe000000	@ virt base
+		add	\rv, \rv, #4		@ omap_uart_lsr
+		str	\rp, [\rv, #0]
 		b	9b
 99:
 		.endm
diff --git a/arch/arm/mach-omap1/include/mach/vmalloc.h b/arch/arm/mach-omap1/include/mach/vmalloc.h
index 1b2af14..b001f67 100644
--- a/arch/arm/mach-omap1/include/mach/vmalloc.h
+++ b/arch/arm/mach-omap1/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
-#define VMALLOC_END	(PAGE_OFFSET + 0x18000000)
+#define VMALLOC_END	0xd8000000
diff --git a/arch/arm/mach-omap2/board-2430sdp.c b/arch/arm/mach-omap2/board-2430sdp.c
index 8538e41..b857ce4 100644
--- a/arch/arm/mach-omap2/board-2430sdp.c
+++ b/arch/arm/mach-omap2/board-2430sdp.c
@@ -253,8 +253,6 @@
 
 MACHINE_START(OMAP_2430SDP, "OMAP2430 sdp2430 board")
 	/* Maintainer: Syed Khasim - Texas Instruments Inc */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap_2430sdp_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c
index 67b95b5f..a5b095c 100644
--- a/arch/arm/mach-omap2/board-3430sdp.c
+++ b/arch/arm/mach-omap2/board-3430sdp.c
@@ -817,8 +817,6 @@
 
 MACHINE_START(OMAP_3430SDP, "OMAP3430 3430SDP board")
 	/* Maintainer: Syed Khasim - Texas Instruments Inc */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-3630sdp.c b/arch/arm/mach-omap2/board-3630sdp.c
index b359c3f..fd27ac0 100644
--- a/arch/arm/mach-omap2/board-3630sdp.c
+++ b/arch/arm/mach-omap2/board-3630sdp.c
@@ -217,8 +217,6 @@
 }
 
 MACHINE_START(OMAP_3630SDP, "OMAP 3630SDP board")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index 9447644..0b6a65f 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -458,8 +458,6 @@
 
 MACHINE_START(OMAP_4430SDP, "OMAP4430 4430SDP board")
 	/* Maintainer: Santosh Shilimkar - Texas Instruments Inc */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap_4430sdp_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-am3517evm.c b/arch/arm/mach-omap2/board-am3517evm.c
index 4d0f585..f85c8da 100644
--- a/arch/arm/mach-omap2/board-am3517evm.c
+++ b/arch/arm/mach-omap2/board-am3517evm.c
@@ -462,8 +462,6 @@
 }
 
 MACHINE_START(OMAP3517EVM, "OMAP3517/AM3517 EVM")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xd8000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c
index c6421a7..68f07f5 100644
--- a/arch/arm/mach-omap2/board-apollon.c
+++ b/arch/arm/mach-omap2/board-apollon.c
@@ -356,8 +356,6 @@
 
 MACHINE_START(OMAP_APOLLON, "OMAP24xx Apollon")
 	/* Maintainer: Kyungmin Park <kyungmin.park@samsung.com> */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap_apollon_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index e10bc10..934d938 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -809,8 +809,6 @@
 }
 
 MACHINE_START(CM_T35, "Compulab CM-T35")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xd8000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index a07086d..2205c20 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -800,8 +800,6 @@
 }
 
 MACHINE_START(DEVKIT8000, "OMAP3 Devkit8000")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xd8000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 3482b99..69064b1 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -54,8 +54,6 @@
 
 MACHINE_START(OMAP_GENERIC, "Generic OMAP24xx")
 	/* Maintainer: Paul Mundt <paul.mundt@nokia.com> */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap_generic_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c
index e09bd68..cc39fc8 100644
--- a/arch/arm/mach-omap2/board-h4.c
+++ b/arch/arm/mach-omap2/board-h4.c
@@ -376,8 +376,6 @@
 
 MACHINE_START(OMAP_H4, "OMAP2420 H4 board")
 	/* Maintainer: Paul Mundt <paul.mundt@nokia.com> */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap_h4_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c
index 175f043..b62a68b 100644
--- a/arch/arm/mach-omap2/board-igep0020.c
+++ b/arch/arm/mach-omap2/board-igep0020.c
@@ -533,8 +533,6 @@
 }
 
 MACHINE_START(IGEP0020, "IGEP v2 board")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index 00d9b13..f28fd77 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -442,8 +442,6 @@
 }
 
 MACHINE_START(OMAP_LDP, "OMAP LDP board")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index a3e2b49..3f79668 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -674,8 +674,6 @@
 }
 
 MACHINE_START(NOKIA_N800, "Nokia N800")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= n8x0_map_io,
 	.reserve	= omap_reserve,
@@ -685,8 +683,6 @@
 MACHINE_END
 
 MACHINE_START(NOKIA_N810, "Nokia N810")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= n8x0_map_io,
 	.reserve	= omap_reserve,
@@ -696,8 +692,6 @@
 MACHINE_END
 
 MACHINE_START(NOKIA_N810_WIMAX, "Nokia N810 WiMAX")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= n8x0_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 87969c7..9d9f5b8 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -487,8 +487,6 @@
 
 MACHINE_START(OMAP3_BEAGLE, "OMAP3 Beagle Board")
 	/* Maintainer: Syed Mohammed Khasim - http://beagleboard.org */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c
index f76d9c0..8936e4f 100644
--- a/arch/arm/mach-omap2/board-omap3evm.c
+++ b/arch/arm/mach-omap2/board-omap3evm.c
@@ -714,8 +714,6 @@
 
 MACHINE_START(OMAP3EVM, "OMAP3 EVM")
 	/* Maintainer: Syed Mohammed Khasim - Texas Instruments */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index dd3af2b..b7d6df4 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -717,8 +717,6 @@
 }
 
 MACHINE_START(OMAP3_PANDORA, "Pandora Handheld Console")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index bcd01d2..bc5ac83 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -654,8 +654,6 @@
 
 MACHINE_START(SBC3530, "OMAP3 STALKER")
 	/* Maintainer: Jason Lam -lzg@ema-tech.com */
-	.phys_io		= 0x48000000,
-	.io_pg_offst		= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params		= 0x80000100,
 	.map_io			= omap3_map_io,
 	.init_irq		= omap3_stalker_init_irq,
diff --git a/arch/arm/mach-omap2/board-omap3touchbook.c b/arch/arm/mach-omap2/board-omap3touchbook.c
index 663c62d..0e99ce5 100644
--- a/arch/arm/mach-omap2/board-omap3touchbook.c
+++ b/arch/arm/mach-omap2/board-omap3touchbook.c
@@ -538,8 +538,6 @@
 
 MACHINE_START(TOUCHBOOK, "OMAP3 touchbook Board")
 	/* Maintainer: Gregoire Gentil - http://www.alwaysinnovating.com */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xd8000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index c03d1d5..db69bca 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -294,8 +294,6 @@
 
 MACHINE_START(OMAP4_PANDA, "OMAP4 Panda board")
 	/* Maintainer: David Anders - Texas Instruments Inc */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap4_panda_map_io,
 	.init_irq	= omap4_panda_init_irq,
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index 4c48436..5e528ca 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -501,8 +501,6 @@
 }
 
 MACHINE_START(OVERO, "Gumstix Overo")
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c
index a58e8cb..36f2cf4 100644
--- a/arch/arm/mach-omap2/board-rx51.c
+++ b/arch/arm/mach-omap2/board-rx51.c
@@ -150,8 +150,6 @@
 
 MACHINE_START(NOKIA_RX51, "Nokia RX-51 board")
 	/* Maintainer: Lauri Leukkunen <lauri.leukkunen@nokia.com> */
-	.phys_io	= 0x48000000,
-	.io_pg_offst	= ((0xfa000000) >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= rx51_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-zoom2.c b/arch/arm/mach-omap2/board-zoom2.c
index 3ad9ecf..24bbd0d 100644
--- a/arch/arm/mach-omap2/board-zoom2.c
+++ b/arch/arm/mach-omap2/board-zoom2.c
@@ -141,8 +141,6 @@
 }
 
 MACHINE_START(OMAP_ZOOM2, "OMAP Zoom2 board")
-	.phys_io	= ZOOM_UART_BASE,
-	.io_pg_offst	= (ZOOM_UART_VIRT >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/board-zoom3.c b/arch/arm/mach-omap2/board-zoom3.c
index 6ca0b83..b2bb3ff 100644
--- a/arch/arm/mach-omap2/board-zoom3.c
+++ b/arch/arm/mach-omap2/board-zoom3.c
@@ -123,8 +123,6 @@
 }
 
 MACHINE_START(OMAP_ZOOM3, "OMAP Zoom3 board")
-	.phys_io	= ZOOM_UART_BASE,
-	.io_pg_offst	= (ZOOM_UART_VIRT >> 18) & 0xfffc,
 	.boot_params	= 0x80000100,
 	.map_io		= omap3_map_io,
 	.reserve	= omap_reserve,
diff --git a/arch/arm/mach-omap2/include/mach/debug-macro.S b/arch/arm/mach-omap2/include/mach/debug-macro.S
index 09331bb..6a4d413 100644
--- a/arch/arm/mach-omap2/include/mach/debug-macro.S
+++ b/arch/arm/mach-omap2/include/mach/debug-macro.S
@@ -31,95 +31,94 @@
 		 * the desired UART phys and virt addresses temporarily into
 		 * the omap_uart_phys and omap_uart_virt above.
 		 */
-		.macro	addruart, rx, tmp
+		.macro	addruart, rp, rv
 
 		/* Use omap_uart_phys/virt if already configured */
-10:		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		ldreq	\rx, =__virt_to_phys(omap_uart_phys)	@ physical base address
-		ldrne	\rx, =omap_uart_virt	@ virtual base address
-		ldr	\rx, [\rx, #0]
-		cmp	\rx, #0			@ is port configured?
+10:		mrc	p15, 0, \rp, c1, c0
+		tst	\rp, #1			@ MMU enabled?
+		ldreq	\rp, =__virt_to_phys(omap_uart_phys)	@ MMU not enabled
+		ldrne	\rp, =omap_uart_phys	@ MMU enabled
+		add	\rv, \rp, #4		@ omap_uart_virt
+		ldr	\rp, [\rp, #0]
+		ldr	\rv, [\rv, #0]
+		cmp	\rp, #0			@ is port configured?
+		cmpne	\rv, #0
 		bne	99f			@ already configured
 
 		/* Check the debug UART configuration set in uncompress.h */
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		ldreq	\rx, =OMAP_UART_INFO
-		ldrne	\rx, =__phys_to_virt(OMAP_UART_INFO)
-		ldr	\rx, [\rx, #0]
+		mrc	p15, 0, \rp, c1, c0
+		tst	\rp, #1			@ MMU enabled?
+		ldreq	\rp, =OMAP_UART_INFO	@ MMU not enabled
+		ldrne	\rp, =__phys_to_virt(OMAP_UART_INFO)	@ MMU enabled
+		ldr	\rp, [\rp, #0]
 
 		/* Select the UART to use based on the UART1 scratchpad value */
-		cmp	\rx, #0			@ no port configured?
+		cmp	\rp, #0			@ no port configured?
 		beq	21f			@ if none, try to use UART1
-		cmp	\rx, #OMAP2UART1	@ OMAP2/3/4UART1
+		cmp	\rp, #OMAP2UART1	@ OMAP2/3/4UART1
 		beq	21f			@ configure OMAP2/3/4UART1
-		cmp	\rx, #OMAP2UART2	@ OMAP2/3/4UART2
+		cmp	\rp, #OMAP2UART2	@ OMAP2/3/4UART2
 		beq	22f			@ configure OMAP2/3/4UART2
-		cmp	\rx, #OMAP2UART3	@ only on 24xx
+		cmp	\rp, #OMAP2UART3	@ only on 24xx
 		beq	23f			@ configure OMAP2UART3
-		cmp	\rx, #OMAP3UART3	@ only on 34xx
+		cmp	\rp, #OMAP3UART3	@ only on 34xx
 		beq	33f			@ configure OMAP3UART3
-		cmp	\rx, #OMAP4UART3	@ only on 44xx
+		cmp	\rp, #OMAP4UART3	@ only on 44xx
 		beq	43f			@ configure OMAP4UART3
-		cmp	\rx, #OMAP3UART4	@ only on 36xx
+		cmp	\rp, #OMAP3UART4	@ only on 36xx
 		beq	34f			@ configure OMAP3UART4
-		cmp	\rx, #OMAP4UART4	@ only on 44xx
+		cmp	\rp, #OMAP4UART4	@ only on 44xx
 		beq	44f			@ configure OMAP4UART4
-		cmp	\rx, #ZOOM_UART		@ only on zoom2/3
+		cmp	\rp, #ZOOM_UART		@ only on zoom2/3
 		beq	95f			@ configure ZOOM_UART
 
 		/* Configure the UART offset from the phys/virt base */
-21:		mov	\rx, #UART_OFFSET(OMAP2_UART1_BASE)	@ omap2/3/4
+21:		mov	\rp, #UART_OFFSET(OMAP2_UART1_BASE)	@ omap2/3/4
 		b	98f
-22:		mov	\rx, #UART_OFFSET(OMAP2_UART2_BASE)	@ omap2/3/4
+22:		mov	\rp, #UART_OFFSET(OMAP2_UART2_BASE)	@ omap2/3/4
 		b	98f
-23:		mov	\rx, #UART_OFFSET(OMAP2_UART3_BASE)
+23:		mov	\rp, #UART_OFFSET(OMAP2_UART3_BASE)
 		b	98f
-33:		mov	\rx, #UART_OFFSET(OMAP3_UART1_BASE)
-		add	\rx, \rx, #0x00fb0000
-		add	\rx, \rx, #0x00006000		@ OMAP3_UART3_BASE
+33:		mov	\rp, #UART_OFFSET(OMAP3_UART1_BASE)
+		add	\rp, \rp, #0x00fb0000
+		add	\rp, \rp, #0x00006000		@ OMAP3_UART3_BASE
 		b	98f
-34:		mov	\rx, #UART_OFFSET(OMAP3_UART1_BASE)
-		add	\rx, \rx, #0x00fb0000
-		add	\rx, \rx, #0x00028000		@ OMAP3_UART4_BASE
+34:		mov	\rp, #UART_OFFSET(OMAP3_UART1_BASE)
+		add	\rp, \rp, #0x00fb0000
+		add	\rp, \rp, #0x00028000		@ OMAP3_UART4_BASE
 		b	98f
-43:		mov	\rx, #UART_OFFSET(OMAP4_UART3_BASE)
+43:		mov	\rp, #UART_OFFSET(OMAP4_UART3_BASE)
 		b	98f
-44:		mov	\rx, #UART_OFFSET(OMAP4_UART4_BASE)
+44:		mov	\rp, #UART_OFFSET(OMAP4_UART4_BASE)
 		b	98f
-95:		ldr	\rx, =ZOOM_UART_BASE
-		mrc	p15, 0, \tmp, c1, c0
-		tst	\tmp, #1		@ MMU enabled?
-		ldreq	\tmp, =__virt_to_phys(omap_uart_phys)
-		ldrne	\tmp, =omap_uart_phys
-		str	\rx, [\tmp, #0]
-		ldr	\rx, =ZOOM_UART_VIRT
-		ldreq	\tmp, =__virt_to_phys(omap_uart_virt)
-		ldrne	\tmp, =omap_uart_virt
-		str	\rx, [\tmp, #0]
-		mov	\rx, #(UART_LSR << ZOOM_PORT_SHIFT)
-		ldreq	\tmp, =__virt_to_phys(omap_uart_lsr)
-		ldrne	\tmp, =omap_uart_lsr
-		str	\rx, [\tmp, #0]
+95:		ldr	\rp, =ZOOM_UART_BASE
+		mrc	p15, 0, \rv, c1, c0
+		tst	\rv, #1			@ MMU enabled?
+		ldreq	\rv, =__virt_to_phys(omap_uart_phys)	@ MMU not enabled
+		ldrne	\rv, =omap_uart_phys	@ MMU enabled
+		str	\rp, [\rv, #0]
+		ldr	\rp, =ZOOM_UART_VIRT
+		add	\rv, \rv, #4		@ omap_uart_virt
+		str	\rp, [\rv, #0]
+		mov	\rp, #(UART_LSR << ZOOM_PORT_SHIFT)
+		add	\rv, \rv, #4		@ omap_uart_lsr
+		str	\rp, [\rv, #0]
 		b	10b
 
 		/* Store both phys and virt address for the uart */
-98:		add	\rx, \rx, #0x48000000	@ phys base
-		mrc	p15, 0, \tmp, c1, c0
-		tst	\tmp, #1		@ MMU enabled?
-		ldreq	\tmp, =__virt_to_phys(omap_uart_phys)
-		ldrne	\tmp, =omap_uart_phys
-		str	\rx, [\tmp, #0]
-		sub	\rx, \rx, #0x48000000	@ phys base
-		add	\rx, \rx, #0xfa000000	@ virt base
-		ldreq	\tmp, =__virt_to_phys(omap_uart_virt)
-		ldrne	\tmp, =omap_uart_virt
-		str	\rx, [\tmp, #0]
-		mov	\rx, #(UART_LSR << OMAP_PORT_SHIFT)
-		ldreq	\tmp, =__virt_to_phys(omap_uart_lsr)
-		ldrne	\tmp, =omap_uart_lsr
-		str	\rx, [\tmp, #0]
+98:		add	\rp, \rp, #0x48000000	@ phys base
+		mrc	p15, 0, \rv, c1, c0
+		tst	\rv, #1			@ MMU enabled?
+		ldreq	\rv, =__virt_to_phys(omap_uart_phys)	@ MMU not enabled
+		ldrne	\rv, =omap_uart_phys	@ MMU enabled
+		str	\rp, [\rv, #0]
+		sub	\rp, \rp, #0x48000000	@ phys base
+		add	\rp, \rp, #0xfa000000	@ virt base
+		add	\rv, \rv, #4		@ omap_uart_virt
+		str	\rp, [\rv, #0]
+		mov	\rp, #(UART_LSR << OMAP_PORT_SHIFT)
+		add	\rv, \rv, #4		@ omap_uart_lsr
+		str	\rp, [\rv, #0]
 
 		b	10b
 99:
@@ -131,9 +130,9 @@
 
 		.macro	busyuart,rd,rx
 1001:		mrc	p15, 0, \rd, c1, c0
-		tst	\rd, #1		@ MMU enabled?
-		ldreq	\rd, =__virt_to_phys(omap_uart_lsr)
-		ldrne	\rd, =omap_uart_lsr
+		tst	\rd, #1			@ MMU enabled?
+		ldreq	\rd, =__virt_to_phys(omap_uart_lsr)	@ MMU not enabled
+		ldrne	\rd, =omap_uart_lsr	@ MMU enabled
 		ldr	\rd, [\rd, #0]
 		ldrb	\rd, [\rx, \rd]
 		and	\rd, \rd, #(UART_LSR_TEMT | UART_LSR_THRE)
diff --git a/arch/arm/mach-omap2/include/mach/vmalloc.h b/arch/arm/mach-omap2/include/mach/vmalloc.h
index 9ce9b6e..4da31e9 100644
--- a/arch/arm/mach-omap2/include/mach/vmalloc.h
+++ b/arch/arm/mach-omap2/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
-#define VMALLOC_END	  (PAGE_OFFSET + 0x38000000)
+#define VMALLOC_END	  0xf8000000
diff --git a/arch/arm/mach-orion5x/d2net-setup.c b/arch/arm/mach-orion5x/d2net-setup.c
index 7130904..b1c451f 100644
--- a/arch/arm/mach-orion5x/d2net-setup.c
+++ b/arch/arm/mach-orion5x/d2net-setup.c
@@ -336,8 +336,6 @@
 
 #ifdef CONFIG_MACH_D2NET
 MACHINE_START(D2NET, "LaCie d2 Network")
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= d2net_init,
 	.map_io		= orion5x_map_io,
@@ -349,8 +347,6 @@
 
 #ifdef CONFIG_MACH_BIGDISK
 MACHINE_START(BIGDISK, "LaCie Big Disk Network")
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= d2net_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/db88f5281-setup.c b/arch/arm/mach-orion5x/db88f5281-setup.c
index d318bea..df1083f 100644
--- a/arch/arm/mach-orion5x/db88f5281-setup.c
+++ b/arch/arm/mach-orion5x/db88f5281-setup.c
@@ -358,8 +358,6 @@
 
 MACHINE_START(DB88F5281, "Marvell Orion-2 Development Board")
 	/* Maintainer: Tzachi Perelstein <tzachi@marvell.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.init_machine	= db88f5281_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index a47100d..3a7bc0e 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -730,8 +730,6 @@
 /* Warning: D-Link uses a wrong mach-type (=526) in their bootloader */
 MACHINE_START(DNS323, "D-Link DNS-323")
 	/* Maintainer: Herbert Valerio Riedel <hvr@gnu.org> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= dns323_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/edmini_v2-setup.c b/arch/arm/mach-orion5x/edmini_v2-setup.c
index b24ee0c..ba98459 100644
--- a/arch/arm/mach-orion5x/edmini_v2-setup.c
+++ b/arch/arm/mach-orion5x/edmini_v2-setup.c
@@ -251,8 +251,6 @@
 /* Warning: LaCie use a wrong mach-type (0x20e=526) in their bootloader. */
 MACHINE_START(EDMINI_V2, "LaCie Ethernet Disk mini V2")
 	/* Maintainer: Christopher Moore <moore@free.fr> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= edmini_v2_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/include/mach/debug-macro.S b/arch/arm/mach-orion5x/include/mach/debug-macro.S
index 91e0e39..5e3bf5b 100644
--- a/arch/arm/mach-orion5x/include/mach/debug-macro.S
+++ b/arch/arm/mach-orion5x/include/mach/debug-macro.S
@@ -10,12 +10,11 @@
 
 #include <mach/orion5x.h>
 
-	.macro  addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1					@ MMU enabled?
-	ldreq	\rx, =ORION5X_REGS_PHYS_BASE
-	ldrne	\rx, =ORION5X_REGS_VIRT_BASE
-	orr	\rx, \rx, #0x00012000
+	.macro  addruart, rp, rv
+	ldr	\rp, =ORION5X_REGS_PHYS_BASE
+	ldr	\rv, =ORION5X_REGS_VIRT_BASE
+	orr	\rp, \rp, #0x00012000
+	orr	\rv, \rv, #0x00012000
 	.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-orion5x/kurobox_pro-setup.c b/arch/arm/mach-orion5x/kurobox_pro-setup.c
index dfbb68d..4be9aa0 100644
--- a/arch/arm/mach-orion5x/kurobox_pro-setup.c
+++ b/arch/arm/mach-orion5x/kurobox_pro-setup.c
@@ -379,8 +379,6 @@
 #ifdef CONFIG_MACH_KUROBOX_PRO
 MACHINE_START(KUROBOX_PRO, "Buffalo/Revogear Kurobox Pro")
 	/* Maintainer: Ronen Shitrit <rshitrit@marvell.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= kurobox_pro_init,
 	.map_io		= orion5x_map_io,
@@ -393,8 +391,6 @@
 #ifdef CONFIG_MACH_LINKSTATION_PRO
 MACHINE_START(LINKSTATION_PRO, "Buffalo Linkstation Pro/Live")
 	/* Maintainer: Byron Bradley <byron.bbradley@gmail.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= kurobox_pro_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/ls_hgl-setup.c b/arch/arm/mach-orion5x/ls_hgl-setup.c
index 8e569be..437364b 100644
--- a/arch/arm/mach-orion5x/ls_hgl-setup.c
+++ b/arch/arm/mach-orion5x/ls_hgl-setup.c
@@ -265,8 +265,6 @@
 
 MACHINE_START(LINKSTATION_LS_HGL, "Buffalo Linkstation LS-HGL")
 	/* Maintainer: Zhu Qingsen <zhuqs@cn.fujistu.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= ls_hgl_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/lsmini-setup.c b/arch/arm/mach-orion5x/lsmini-setup.c
index c704f05..ab9b0cf 100644
--- a/arch/arm/mach-orion5x/lsmini-setup.c
+++ b/arch/arm/mach-orion5x/lsmini-setup.c
@@ -267,8 +267,6 @@
 #ifdef CONFIG_MACH_LINKSTATION_MINI
 MACHINE_START(LINKSTATION_MINI, "Buffalo Linkstation Mini")
 	/* Maintainer: Alexey Kopytko <alexey@kopytko.ru> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= lsmini_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/mss2-setup.c b/arch/arm/mach-orion5x/mss2-setup.c
index 61c086b..2f0e16c 100644
--- a/arch/arm/mach-orion5x/mss2-setup.c
+++ b/arch/arm/mach-orion5x/mss2-setup.c
@@ -261,8 +261,6 @@
 
 MACHINE_START(MSS2, "Maxtor Shared Storage II")
 	/* Maintainer: Sylver Bruneau <sylver.bruneau@googlemail.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= mss2_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/mv2120-setup.c b/arch/arm/mach-orion5x/mv2120-setup.c
index 97c9ccb..b3d90f2 100644
--- a/arch/arm/mach-orion5x/mv2120-setup.c
+++ b/arch/arm/mach-orion5x/mv2120-setup.c
@@ -229,8 +229,6 @@
 /* Warning: HP uses a wrong mach-type (=526) in their bootloader */
 MACHINE_START(MV2120, "HP Media Vault mv2120")
 	/* Maintainer: Martin Michlmayr <tbm@cyrius.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= mv2120_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/net2big-setup.c b/arch/arm/mach-orion5x/net2big-setup.c
index 7bd6283..d6665b3 100644
--- a/arch/arm/mach-orion5x/net2big-setup.c
+++ b/arch/arm/mach-orion5x/net2big-setup.c
@@ -419,8 +419,6 @@
 
 /* Warning: LaCie use a wrong mach-type (0x20e=526) in their bootloader. */
 MACHINE_START(NET2BIG, "LaCie 2Big Network")
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= net2big_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c b/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
index 9c1ca41..f4c26fd 100644
--- a/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
@@ -169,8 +169,6 @@
 
 MACHINE_START(RD88F5181L_FXO, "Marvell Orion-VoIP FXO Reference Design")
 	/* Maintainer: Nicolas Pitre <nico@marvell.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= rd88f5181l_fxo_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c b/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
index ee1399f..b594290 100644
--- a/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
@@ -181,8 +181,6 @@
 
 MACHINE_START(RD88F5181L_GE, "Marvell Orion-VoIP GE Reference Design")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= rd88f5181l_ge_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/rd88f5182-setup.c b/arch/arm/mach-orion5x/rd88f5182-setup.c
index a04f9e4..165ed870 100644
--- a/arch/arm/mach-orion5x/rd88f5182-setup.c
+++ b/arch/arm/mach-orion5x/rd88f5182-setup.c
@@ -305,8 +305,6 @@
 
 MACHINE_START(RD88F5182, "Marvell Orion-NAS Reference Design")
 	/* Maintainer: Ronen Shitrit <rshitrit@marvell.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= rd88f5182_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c b/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
index 7737cf9..02ff45f 100644
--- a/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
+++ b/arch/arm/mach-orion5x/rd88f6183ap-ge-setup.c
@@ -123,8 +123,6 @@
 
 MACHINE_START(RD88F6183AP_GE, "Marvell Orion-1-90 AP GE Reference Design")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= rd88f6183ap_ge_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/terastation_pro2-setup.c b/arch/arm/mach-orion5x/terastation_pro2-setup.c
index 0b101d7d..4403fae 100644
--- a/arch/arm/mach-orion5x/terastation_pro2-setup.c
+++ b/arch/arm/mach-orion5x/terastation_pro2-setup.c
@@ -358,8 +358,6 @@
 
 MACHINE_START(TERASTATION_PRO2, "Buffalo Terastation Pro II/Live")
 	/* Maintainer:  Sylver Bruneau <sylver.bruneau@googlemail.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= tsp2_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/ts209-setup.c b/arch/arm/mach-orion5x/ts209-setup.c
index 9d68905..1e19612 100644
--- a/arch/arm/mach-orion5x/ts209-setup.c
+++ b/arch/arm/mach-orion5x/ts209-setup.c
@@ -322,8 +322,6 @@
 
 MACHINE_START(TS209, "QNAP TS-109/TS-209")
 	/* Maintainer: Byron Bradley <byron.bbradley@gmail.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= qnap_ts209_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/ts409-setup.c b/arch/arm/mach-orion5x/ts409-setup.c
index d85588a..428af20 100644
--- a/arch/arm/mach-orion5x/ts409-setup.c
+++ b/arch/arm/mach-orion5x/ts409-setup.c
@@ -311,8 +311,6 @@
 
 MACHINE_START(TS409, "QNAP TS-409")
 	/* Maintainer:  Sylver Bruneau <sylver.bruneau@gmail.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= qnap_ts409_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/ts78xx-setup.c b/arch/arm/mach-orion5x/ts78xx-setup.c
index 696b1a9..16f1bd5 100644
--- a/arch/arm/mach-orion5x/ts78xx-setup.c
+++ b/arch/arm/mach-orion5x/ts78xx-setup.c
@@ -550,8 +550,6 @@
 
 MACHINE_START(TS78XX, "Technologic Systems TS-78xx SBC")
 	/* Maintainer: Alexander Clouter <alex@digriz.org.uk> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= ts78xx_init,
 	.map_io		= ts78xx_map_io,
diff --git a/arch/arm/mach-orion5x/wnr854t-setup.c b/arch/arm/mach-orion5x/wnr854t-setup.c
index 6920821..7994d6e 100644
--- a/arch/arm/mach-orion5x/wnr854t-setup.c
+++ b/arch/arm/mach-orion5x/wnr854t-setup.c
@@ -172,8 +172,6 @@
 
 MACHINE_START(WNR854T, "Netgear WNR854T")
 	/* Maintainer: Imre Kaloz <kaloz@openwrt.org> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= wnr854t_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-orion5x/wrt350n-v2-setup.c b/arch/arm/mach-orion5x/wrt350n-v2-setup.c
index f9f222e..a5989b7 100644
--- a/arch/arm/mach-orion5x/wrt350n-v2-setup.c
+++ b/arch/arm/mach-orion5x/wrt350n-v2-setup.c
@@ -260,8 +260,6 @@
 
 MACHINE_START(WRT350N_V2, "Linksys WRT350N v2")
 	/* Maintainer: Lennert Buytenhek <buytenh@marvell.com> */
-	.phys_io	= ORION5X_REGS_PHYS_BASE,
-	.io_pg_offst	= ((ORION5X_REGS_VIRT_BASE) >> 18) & 0xFFFC,
 	.boot_params	= 0x00000100,
 	.init_machine	= wrt350n_v2_init,
 	.map_io		= orion5x_map_io,
diff --git a/arch/arm/mach-pnx4008/core.c b/arch/arm/mach-pnx4008/core.c
index 45734bb..63399755 100644
--- a/arch/arm/mach-pnx4008/core.c
+++ b/arch/arm/mach-pnx4008/core.c
@@ -264,8 +264,6 @@
 
 MACHINE_START(PNX4008, "Philips PNX4008")
 	/* Maintainer: MontaVista Software Inc. */
-	.phys_io 		= 0x40090000,
-	.io_pg_offst 		= (0xf4090000 >> 18) & 0xfffc,
 	.boot_params		= 0x80000100,
 	.map_io 		= pnx4008_map_io,
 	.init_irq 		= pnx4008_init_irq,
diff --git a/arch/arm/mach-pnx4008/include/mach/debug-macro.S b/arch/arm/mach-pnx4008/include/mach/debug-macro.S
index 6ca8bd3..931afeb 100644
--- a/arch/arm/mach-pnx4008/include/mach/debug-macro.S
+++ b/arch/arm/mach-pnx4008/include/mach/debug-macro.S
@@ -11,12 +11,10 @@
  *
 */
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		mov	\rx, #0x00090000
-		addeq	\rx, \rx, #0x40000000
-		addne	\rx, \rx, #0xf4000000
+		.macro	addruart, rp, rv
+		mov	\rp, #0x00090000
+		add	\rv, \rp, #0xf4000000	@ virtual
+		add	\rp, \rp, #0x40000000	@ physical
 		.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-pnx4008/include/mach/vmalloc.h b/arch/arm/mach-pnx4008/include/mach/vmalloc.h
index 2ad3983..31b65ee 100644
--- a/arch/arm/mach-pnx4008/include/mach/vmalloc.h
+++ b/arch/arm/mach-pnx4008/include/mach/vmalloc.h
@@ -17,4 +17,4 @@
  * The vmalloc() routines leaves a hole of 4kB between each vmalloced
  * area for the same reason. ;)
  */
-#define VMALLOC_END       (PAGE_OFFSET + 0x10000000)
+#define VMALLOC_END       0xd0000000
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 7aefb90..dd235ec 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -8,19 +8,16 @@
 	bool "Intel DBPXA250 Development Platform (aka Lubbock)"
 	select PXA25x
 	select SA1111
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_MAINSTONE
 	bool "Intel HCDDBBVA0 Development Platform (aka Mainstone)"
 	select PXA27x
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_ZYLONITE
 	bool
 	select PXA3xx
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_ZYLONITE300
 	bool "PXA3xx Development Platform (aka Zylonite) PXA300/310"
@@ -44,6 +41,10 @@
 	select PXA3xx
 	select CPU_PXA930
 
+config MACH_TAVOREVB3
+	bool "PXA95x Development Platform (aka TavorEVB III)"
+	select CPU_PXA950
+
 config MACH_SAAR
 	bool "PXA930 Handheld Platform (aka SAAR)"
 	select PXA3xx
@@ -61,7 +62,6 @@
 	select ISA
 	select I2C_GPIO
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 	select PXA_HAVE_ISA_IRQS
 	select ARCOM_PCMCIA
 
@@ -69,7 +69,6 @@
 	bool "Arcom/Eurotech ZEUS SBC"
 	select PXA27x
 	select ISA
-	select PXA_HAVE_BOARD_IRQS
 	select PXA_HAVE_ISA_IRQS
 	select ARCOM_PCMCIA
 
@@ -77,7 +76,6 @@
 	bool "Balloon 3 board"
 	select PXA27x
 	select IWMMXT
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_CSB726
 	bool "Enable Cogent CSB726 System On a Module"
@@ -140,13 +138,11 @@
 	bool "Intel Mote 2 Platform"
 	select PXA27x
 	select IWMMXT
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_STARGATE2
 	bool "Intel Stargate 2 Platform"
 	select PXA27x
 	select IWMMXT
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_XCEP
 	bool "Iskratel Electronics XCEP"
@@ -206,13 +202,11 @@
 	bool "LogicPD PXA270 Card Engine Development Platform"
 	select PXA27x
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_PCM027
 	bool "Phytec phyCORE-PXA270 CPU module (PCM-027)"
 	select PXA27x
 	select IWMMXT
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_PCM990_BASEBOARD
 	bool "PHYTEC PCM-990 development board"
@@ -247,7 +241,6 @@
 	depends on MACH_COLIBRI
 	select PXA27x
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_COLIBRI300
 	bool "Toradex Colibri PXA300/310"
@@ -274,7 +267,6 @@
 	select PXA27x
 	select IWMMXT
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_H5000
 	bool "HP iPAQ h5000"
@@ -289,7 +281,6 @@
 	select PXA27x
 	select IWMMXT
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_MIOA701
 	bool "Mitac Mio A701 Support"
@@ -307,7 +298,6 @@
 	select PXA27x
 	select IWMMXT
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_EZX_A780
 	bool "Motorola EZX A780"
@@ -478,7 +468,6 @@
 	depends on PXA_SHARPSL
 	select PXA25x
 	select SHARP_LOCOMO
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_CORGI
 	bool "Enable Sharp SL-C700 (Corgi) Support"
@@ -523,7 +512,6 @@
 	bool "Enable Sharp SL-6000x (Tosa) Support"
 	depends on PXA_SHARPSL
 	select PXA25x
-	select PXA_HAVE_BOARD_IRQS
 
 config TOSA_BT
 	tristate "Control the state of built-in bluetooth chip on Sharp SL-6000"
@@ -552,7 +540,6 @@
 config ARCH_PXA_ESERIES
 	bool "PXA based Toshiba e-series PDAs"
 	select PXA25x
-	select PXA_HAVE_BOARD_IRQS
 
 config MACH_E330
 	bool "Toshiba e330"
@@ -606,7 +593,6 @@
 	bool "Zipit Z2 Handheld"
 	select PXA27x
 	select HAVE_PWM
-	select PXA_HAVE_BOARD_IRQS
 
 endmenu
 
@@ -643,6 +629,7 @@
 config CPU_PXA310
 	bool
 	select CPU_PXA300
+	select PXA310_ULPI if USB_ULPI
 	help
 	  PXA310 (codename Monahans-LV)
 
@@ -692,10 +679,10 @@
 	select HWMON
 	select SENSORS_MAX1111
 
-config PXA_HAVE_BOARD_IRQS
+config PXA_HAVE_ISA_IRQS
 	bool
 
-config PXA_HAVE_ISA_IRQS
+config PXA310_ULPI
 	bool
 
 endif
diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile
index 85c7fb3..e2f89c2 100644
--- a/arch/arm/mach-pxa/Makefile
+++ b/arch/arm/mach-pxa/Makefile
@@ -18,7 +18,7 @@
 # SoC-specific code
 obj-$(CONFIG_PXA25x)		+= mfp-pxa2xx.o pxa2xx.o pxa25x.o
 obj-$(CONFIG_PXA27x)		+= mfp-pxa2xx.o pxa2xx.o pxa27x.o
-obj-$(CONFIG_PXA3xx)		+= mfp-pxa3xx.o pxa3xx.o smemc.o
+obj-$(CONFIG_PXA3xx)		+= mfp-pxa3xx.o pxa3xx.o smemc.o pxa3xx-ulpi.o
 obj-$(CONFIG_CPU_PXA300)	+= pxa300.o
 obj-$(CONFIG_CPU_PXA320)	+= pxa320.o
 obj-$(CONFIG_CPU_PXA930)	+= pxa930.o
@@ -32,6 +32,7 @@
 obj-$(CONFIG_MACH_ZYLONITE320)	+= zylonite.o zylonite_pxa320.o
 obj-$(CONFIG_MACH_LITTLETON)	+= littleton.o
 obj-$(CONFIG_MACH_TAVOREVB)	+= tavorevb.o
+obj-$(CONFIG_MACH_TAVOREVB3)	+= tavorevb3.o
 obj-$(CONFIG_MACH_SAAR)		+= saar.o
 
 # 3rd Party Dev Platforms
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index 9041340..21e1889 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -68,42 +68,6 @@
 
 	/* Reset, configured as GPIO wakeup source */
 	GPIO1_GPIO | WAKEUP_ON_EDGE_BOTH,
-
-	/* LEDs */
-	GPIO9_GPIO,	/* NAND activity LED */
-	GPIO10_GPIO,	/* Heartbeat LED */
-
-	/* AC97 */
-	GPIO28_AC97_BITCLK,
-	GPIO29_AC97_SDATA_IN_0,
-	GPIO30_AC97_SDATA_OUT,
-	GPIO31_AC97_SYNC,
-	GPIO113_AC97_nRESET,
-	GPIO95_GPIO,
-
-	/* MMC */
-	GPIO32_MMC_CLK,
-	GPIO92_MMC_DAT_0,
-	GPIO109_MMC_DAT_1,
-	GPIO110_MMC_DAT_2,
-	GPIO111_MMC_DAT_3,
-	GPIO112_MMC_CMD,
-
-	/* USB Host */
-	GPIO88_USBH1_PWR,
-	GPIO89_USBH1_PEN,
-
-	/* PC Card */
-	GPIO48_nPOE,
-	GPIO49_nPWE,
-	GPIO50_nPIOR,
-	GPIO51_nPIOW,
-	GPIO85_nPCE_1,
-	GPIO54_nPCE_2,
-	GPIO79_PSKTSEL,
-	GPIO55_nPREG,
-	GPIO56_nPWAIT,
-	GPIO57_nIOIS16,
 };
 
 /******************************************************************************
@@ -132,6 +96,34 @@
 early_param("balloon3_features", parse_balloon3_features);
 
 /******************************************************************************
+ * Compact Flash slot
+ ******************************************************************************/
+#if	defined(CONFIG_PCMCIA_PXA2XX) || defined(CONFIG_PCMCIA_PXA2XX_MODULE)
+static unsigned long balloon3_cf_pin_config[] __initdata = {
+	GPIO48_nPOE,
+	GPIO49_nPWE,
+	GPIO50_nPIOR,
+	GPIO51_nPIOW,
+	GPIO85_nPCE_1,
+	GPIO54_nPCE_2,
+	GPIO79_PSKTSEL,
+	GPIO55_nPREG,
+	GPIO56_nPWAIT,
+	GPIO57_nIOIS16,
+};
+
+static void __init balloon3_cf_init(void)
+{
+	if (!balloon3_has(BALLOON3_FEATURE_CF))
+		return;
+
+	pxa2xx_mfp_config(ARRAY_AND_SIZE(balloon3_cf_pin_config));
+}
+#else
+static inline void balloon3_cf_init(void) {}
+#endif
+
+/******************************************************************************
  * NOR Flash
  ******************************************************************************/
 #if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE)
@@ -179,6 +171,15 @@
  ******************************************************************************/
 #if	defined(CONFIG_TOUCHSCREEN_UCB1400) || \
 	defined(CONFIG_TOUCHSCREEN_UCB1400_MODULE)
+static unsigned long balloon3_ac97_pin_config[] __initdata = {
+	GPIO28_AC97_BITCLK,
+	GPIO29_AC97_SDATA_IN_0,
+	GPIO30_AC97_SDATA_OUT,
+	GPIO31_AC97_SYNC,
+	GPIO113_AC97_nRESET,
+	GPIO95_GPIO,
+};
+
 static struct ucb1400_pdata vpac270_ucb1400_pdata = {
 	.irq		= IRQ_GPIO(BALLOON3_GPIO_CODEC_IRQ),
 };
@@ -197,6 +198,7 @@
 	if (!balloon3_has(BALLOON3_FEATURE_AUDIO))
 		return;
 
+	pxa2xx_mfp_config(ARRAY_AND_SIZE(balloon3_ac97_pin_config));
 	pxa_set_ac97_info(NULL);
 	platform_device_register(&balloon3_ucb1400_device);
 }
@@ -208,6 +210,11 @@
  * Framebuffer
  ******************************************************************************/
 #if defined(CONFIG_FB_PXA) || defined(CONFIG_FB_PXA_MODULE)
+static unsigned long balloon3_lcd_pin_config[] __initdata = {
+	GPIOxx_LCD_TFT_16BPP,
+	GPIO99_GPIO,
+};
+
 static struct pxafb_mode_info balloon3_lcd_modes[] = {
 	{
 		.pixclock		= 38000,
@@ -242,6 +249,8 @@
 	if (!balloon3_has(BALLOON3_FEATURE_TOPPOLY))
 		return;
 
+	pxa2xx_mfp_config(ARRAY_AND_SIZE(balloon3_lcd_pin_config));
+
 	ret = gpio_request(BALLOON3_GPIO_RUN_BACKLIGHT, "BKL-ON");
 	if (ret) {
 		pr_err("Requesting BKL-ON GPIO failed!\n");
@@ -271,6 +280,15 @@
  * SD/MMC card controller
  ******************************************************************************/
 #if defined(CONFIG_MMC_PXA) || defined(CONFIG_MMC_PXA_MODULE)
+static unsigned long balloon3_mmc_pin_config[] __initdata = {
+	GPIO32_MMC_CLK,
+	GPIO92_MMC_DAT_0,
+	GPIO109_MMC_DAT_1,
+	GPIO110_MMC_DAT_2,
+	GPIO111_MMC_DAT_3,
+	GPIO112_MMC_CMD,
+};
+
 static struct pxamci_platform_data balloon3_mci_platform_data = {
 	.ocr_mask		= MMC_VDD_32_33 | MMC_VDD_33_34,
 	.gpio_card_detect	= -1,
@@ -281,6 +299,7 @@
 
 static void __init balloon3_mmc_init(void)
 {
+	pxa2xx_mfp_config(ARRAY_AND_SIZE(balloon3_mmc_pin_config));
 	pxa_set_mci_info(&balloon3_mci_platform_data);
 }
 #else
@@ -339,6 +358,11 @@
  * USB Host
  ******************************************************************************/
 #if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
+static unsigned long balloon3_uhc_pin_config[] __initdata = {
+	GPIO88_USBH1_PWR,
+	GPIO89_USBH1_PEN,
+};
+
 static struct pxaohci_platform_data balloon3_ohci_info = {
 	.port_mode	= PMM_PERPORT_MODE,
 	.flags		= ENABLE_PORT_ALL | POWER_CONTROL_LOW | POWER_SENSE_LOW,
@@ -348,6 +372,7 @@
 {
 	if (!balloon3_has(BALLOON3_FEATURE_OHCI))
 		return;
+	pxa2xx_mfp_config(ARRAY_AND_SIZE(balloon3_uhc_pin_config));
 	pxa_set_ohci_info(&balloon3_ohci_info);
 }
 #else
@@ -358,6 +383,11 @@
  * LEDs
  ******************************************************************************/
 #if defined(CONFIG_LEDS_GPIO) || defined(CONFIG_LEDS_GPIO_MODULE)
+static unsigned long balloon3_led_pin_config[] __initdata = {
+	GPIO9_GPIO,	/* NAND activity LED */
+	GPIO10_GPIO,	/* Heartbeat LED */
+};
+
 struct gpio_led balloon3_gpio_leds[] = {
 	{
 		.name			= "balloon3:green:idle",
@@ -436,6 +466,7 @@
 
 static void __init balloon3_leds_init(void)
 {
+	pxa2xx_mfp_config(ARRAY_AND_SIZE(balloon3_led_pin_config));
 	platform_device_register(&balloon3_leds);
 	platform_device_register(&balloon3_pcf_leds);
 }
@@ -757,6 +788,7 @@
 	balloon3_ts_init();
 	balloon3_udc_init();
 	balloon3_uhc_init();
+	balloon3_cf_init();
 }
 
 static struct map_desc balloon3_io_desc[] __initdata = {
@@ -776,9 +808,8 @@
 
 MACHINE_START(BALLOON3, "Balloon3")
 	/* Maintainer: Nick Bane. */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= balloon3_map_io,
+	.nr_irqs	= BALLOON3_NR_IRQS,
 	.init_irq	= balloon3_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= balloon3_init,
diff --git a/arch/arm/mach-pxa/capc7117.c b/arch/arm/mach-pxa/capc7117.c
index aae5446..4bd7a3c 100644
--- a/arch/arm/mach-pxa/capc7117.c
+++ b/arch/arm/mach-pxa/capc7117.c
@@ -148,9 +148,7 @@
 
 MACHINE_START(CAPC7117,
 	      "Embedian CAPC-7117 evaluation kit based on the MXM-8x10 CoM")
-	.phys_io = 0x40000000,
 	.boot_params = 0xa0000100,
-	.io_pg_offst = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io = pxa_map_io,
 	.init_irq = pxa3xx_init_irq,
 	.timer = &pxa_timer,
diff --git a/arch/arm/mach-pxa/cm-x2xx.c b/arch/arm/mach-pxa/cm-x2xx.c
index bff6e78..ac5598c 100644
--- a/arch/arm/mach-pxa/cm-x2xx.c
+++ b/arch/arm/mach-pxa/cm-x2xx.c
@@ -33,6 +33,9 @@
 extern void cmx255_init(void);
 extern void cmx270_init(void);
 
+/* reserve IRQs for IT8152 */
+#define CMX2XX_NR_IRQS		(IRQ_BOARD_START + 40)
+
 /* virtual addresses for statically mapped regions */
 #define CMX2XX_VIRT_BASE	(0xe8000000)
 #define CMX2XX_IT8152_VIRT	(CMX2XX_VIRT_BASE)
@@ -511,9 +514,8 @@
 
 MACHINE_START(ARMCORE, "Compulab CM-X2XX")
 	.boot_params	= 0xa0000100,
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= cmx2xx_map_io,
+	.nr_irqs	= CMX2XX_NR_IRQS,
 	.init_irq	= cmx2xx_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= cmx2xx_init,
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index c70e6c2..922b107 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 
 #include <linux/gpio.h>
 #include <linux/dm9000.h>
@@ -50,6 +51,7 @@
 #include <plat/i2c.h>
 #include <plat/pxa3xx_nand.h>
 #include <mach/audio.h>
+#include <mach/pxa3xx-u2d.h>
 
 #include <asm/mach/map.h>
 
@@ -68,6 +70,8 @@
 #define GPIO97_RTC_RD		(97)
 #define GPIO98_RTC_IO		(98)
 
+#define GPIO_ULPI_PHY_RST	(127)
+
 static mfp_cfg_t cm_x3xx_mfp_cfg[] __initdata = {
 	/* LCD */
 	GPIO54_LCD_LDD_0,
@@ -472,6 +476,78 @@
 static inline void cm_x300_init_mmc(void) {}
 #endif
 
+#if defined(CONFIG_PXA310_ULPI)
+static struct clk *pout_clk;
+
+static int cm_x300_ulpi_phy_reset(void)
+{
+	int err;
+
+	/* reset the PHY */
+	err = gpio_request(GPIO_ULPI_PHY_RST, "ulpi reset");
+	if (err) {
+		pr_err("%s: failed to request ULPI reset GPIO: %d\n",
+		       __func__, err);
+		return err;
+	}
+
+	gpio_direction_output(GPIO_ULPI_PHY_RST, 0);
+	msleep(10);
+	gpio_set_value(GPIO_ULPI_PHY_RST, 1);
+	msleep(10);
+
+	gpio_free(GPIO_ULPI_PHY_RST);
+
+	return 0;
+}
+
+static inline int cm_x300_u2d_init(struct device *dev)
+{
+	int err = 0;
+
+	if (cpu_is_pxa310()) {
+		/* CLK_POUT is connected to the ULPI PHY */
+		pout_clk = clk_get(NULL, "CLK_POUT");
+		if (IS_ERR(pout_clk)) {
+			err = PTR_ERR(pout_clk);
+			pr_err("%s: failed to get CLK_POUT: %d\n",
+			       __func__, err);
+			return err;
+		}
+		clk_enable(pout_clk);
+
+		err = cm_x300_ulpi_phy_reset();
+		if (err) {
+			clk_disable(pout_clk);
+			clk_put(pout_clk);
+		}
+	}
+
+	return err;
+}
+
+static void cm_x300_u2d_exit(struct device *dev)
+{
+	if (cpu_is_pxa310()) {
+		clk_disable(pout_clk);
+		clk_put(pout_clk);
+	}
+}
+
+static struct pxa3xx_u2d_platform_data cm_x300_u2d_platform_data = {
+	.ulpi_mode	= ULPI_SER_6PIN,
+	.init		= cm_x300_u2d_init,
+	.exit		= cm_x300_u2d_exit,
+};
+
+static void cm_x300_init_u2d(void)
+{
+	pxa3xx_set_u2d_info(&cm_x300_u2d_platform_data);
+}
+#else
+static inline void cm_x300_init_u2d(void) {}
+#endif
+
 #if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 static int cm_x300_ohci_init(struct device *dev)
 {
@@ -754,6 +830,7 @@
 	cm_x300_init_da9030();
 	cm_x300_init_dm9000();
 	cm_x300_init_lcd();
+	cm_x300_init_u2d();
 	cm_x300_init_ohci();
 	cm_x300_init_mmc();
 	cm_x300_init_nand();
@@ -779,9 +856,7 @@
 }
 
 MACHINE_START(CM_X300, "CM-X300 module")
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0000100,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa3xx_init_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/colibri-pxa270.c b/arch/arm/mach-pxa/colibri-pxa270.c
index 98673ac..bc04510 100644
--- a/arch/arm/mach-pxa/colibri-pxa270.c
+++ b/arch/arm/mach-pxa/colibri-pxa270.c
@@ -207,8 +207,6 @@
 }
 
 MACHINE_START(COLIBRI, "Toradex Colibri PXA270")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= COLIBRI_SDRAM_BASE + 0x100,
 	.init_machine	= colibri_pxa270_init,
 	.map_io		= pxa_map_io,
@@ -217,8 +215,6 @@
 MACHINE_END
 
 MACHINE_START(INCOME, "Income s.r.o. SH-Dmaster PXA270 SBC")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.init_machine	= colibri_pxa270_income_init,
 	.map_io		= pxa_map_io,
diff --git a/arch/arm/mach-pxa/colibri-pxa300.c b/arch/arm/mach-pxa/colibri-pxa300.c
index 40b6ac2..a70b256 100644
--- a/arch/arm/mach-pxa/colibri-pxa300.c
+++ b/arch/arm/mach-pxa/colibri-pxa300.c
@@ -186,8 +186,6 @@
 }
 
 MACHINE_START(COLIBRI300, "Toradex Colibri PXA300")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= COLIBRI_SDRAM_BASE + 0x100,
 	.init_machine	= colibri_pxa300_init,
 	.map_io		= pxa_map_io,
diff --git a/arch/arm/mach-pxa/colibri-pxa320.c b/arch/arm/mach-pxa/colibri-pxa320.c
index 99e850d..ca5f29e 100644
--- a/arch/arm/mach-pxa/colibri-pxa320.c
+++ b/arch/arm/mach-pxa/colibri-pxa320.c
@@ -255,8 +255,6 @@
 }
 
 MACHINE_START(COLIBRI320, "Toradex Colibri PXA320")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= COLIBRI_SDRAM_BASE + 0x100,
 	.init_machine	= colibri_pxa320_init,
 	.map_io		= pxa_map_io,
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 3fb0fc0..821229ac 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -720,8 +720,6 @@
 
 #ifdef CONFIG_MACH_CORGI
 MACHINE_START(CORGI, "SHARP Corgi")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.fixup		= fixup_corgi,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa25x_init_irq,
@@ -732,8 +730,6 @@
 
 #ifdef CONFIG_MACH_SHEPHERD
 MACHINE_START(SHEPHERD, "SHARP Shepherd")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.fixup		= fixup_corgi,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa25x_init_irq,
@@ -744,8 +740,6 @@
 
 #ifdef CONFIG_MACH_HUSKY
 MACHINE_START(HUSKY, "SHARP Husky")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.fixup		= fixup_corgi,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa25x_init_irq,
diff --git a/arch/arm/mach-pxa/cpufreq-pxa3xx.c b/arch/arm/mach-pxa/cpufreq-pxa3xx.c
index 0a0d0fe..88fbec0 100644
--- a/arch/arm/mach-pxa/cpufreq-pxa3xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa3xx.c
@@ -159,7 +159,7 @@
 
 static unsigned int pxa3xx_cpufreq_get(unsigned int cpu)
 {
-	return get_clk_frequency_khz(0);
+	return pxa3xx_get_clk_frequency_khz(0);
 }
 
 static int pxa3xx_cpufreq_set(struct cpufreq_policy *policy,
@@ -212,7 +212,8 @@
 	policy->cpuinfo.min_freq = 104000;
 	policy->cpuinfo.max_freq = (cpu_is_pxa320()) ? 806000 : 624000;
 	policy->cpuinfo.transition_latency = 1000; /* FIXME: 1 ms, assumed */
-	policy->cur = policy->min = policy->max = get_clk_frequency_khz(0);
+	policy->max = pxa3xx_get_clk_frequency_khz(0);
+	policy->cur = policy->min = policy->max;
 
 	if (cpu_is_pxa300() || cpu_is_pxa310())
 		ret = setup_freqs_table(policy, ARRAY_AND_SIZE(pxa300_freqs));
diff --git a/arch/arm/mach-pxa/csb726.c b/arch/arm/mach-pxa/csb726.c
index 91fd4fe..57cacaf 100644
--- a/arch/arm/mach-pxa/csb726.c
+++ b/arch/arm/mach-pxa/csb726.c
@@ -272,9 +272,7 @@
 }
 
 MACHINE_START(CSB726, "Cogent CSB726")
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0000100,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io         = pxa_map_io,
 	.init_irq       = pxa27x_init_irq,
 	.init_machine   = csb726_init,
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 65447dc..08b4103 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -6,11 +6,12 @@
 
 #include <asm/pmu.h>
 #include <mach/udc.h>
+#include <mach/pxa3xx-u2d.h>
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
 #include <mach/irda.h>
 #include <mach/ohci.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/pxa2xx_spi.h>
 #include <mach/camera.h>
 #include <mach/audio.h>
@@ -134,6 +135,33 @@
 	}
 };
 
+#ifdef CONFIG_PXA3xx
+static struct resource pxa3xx_u2d_resources[] = {
+	[0] = {
+		.start	= 0x54100000,
+		.end	= 0x54100fff,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_USB2,
+		.end	= IRQ_USB2,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device pxa3xx_device_u2d = {
+	.name		= "pxa3xx-u2d",
+	.id		= -1,
+	.resource	= pxa3xx_u2d_resources,
+	.num_resources	= ARRAY_SIZE(pxa3xx_u2d_resources),
+};
+
+void __init pxa3xx_set_u2d_info(struct pxa3xx_u2d_platform_data *info)
+{
+	pxa_register_device(&pxa3xx_device_u2d, info);
+}
+#endif /* CONFIG_PXA3xx */
+
 static struct resource pxafb_resources[] = {
 	[0] = {
 		.start	= 0x44000000,
diff --git a/arch/arm/mach-pxa/devices.h b/arch/arm/mach-pxa/devices.h
index 50353ea..715e8bd 100644
--- a/arch/arm/mach-pxa/devices.h
+++ b/arch/arm/mach-pxa/devices.h
@@ -4,6 +4,7 @@
 extern struct platform_device pxa3xx_device_mci3;
 extern struct platform_device pxa25x_device_udc;
 extern struct platform_device pxa27x_device_udc;
+extern struct platform_device pxa3xx_device_u2d;
 extern struct platform_device pxa_device_fb;
 extern struct platform_device pxa_device_ffuart;
 extern struct platform_device pxa_device_btuart;
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 0517c17..ab48bb8 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -43,7 +43,7 @@
 #include <mach/pxafb.h>
 #include <mach/ohci.h>
 #include <mach/mmc.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <plat/i2c.h>
 #include <mach/camera.h>
 #include <mach/pxa2xx_spi.h>
@@ -1301,8 +1301,6 @@
 
 MACHINE_START(EM_X270, "Compulab EM-X270")
 	.boot_params	= 0xa0000100,
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.timer		= &pxa_timer,
@@ -1311,8 +1309,6 @@
 
 MACHINE_START(EXEDA, "Compulab eXeda")
 	.boot_params	= 0xa0000100,
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index 349212a..b25690c 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -29,6 +29,7 @@
 
 #include <mach/pxa25x.h>
 #include <mach/eseries-gpio.h>
+#include <mach/eseries-irq.h>
 #include <mach/audio.h>
 #include <mach/pxafb.h>
 #include <mach/udc.h>
@@ -179,10 +180,9 @@
 
 MACHINE_START(E330, "Toshiba e330")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.fixup		= eseries_fixup,
 	.init_machine	= e330_init,
@@ -229,10 +229,9 @@
 
 MACHINE_START(E350, "Toshiba e350")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.fixup		= eseries_fixup,
 	.init_machine	= e350_init,
@@ -352,10 +351,9 @@
 
 MACHINE_START(E400, "Toshiba e400")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.fixup		= eseries_fixup,
 	.init_machine	= e400_init,
@@ -541,10 +539,9 @@
 
 MACHINE_START(E740, "Toshiba e740")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.fixup		= eseries_fixup,
 	.init_machine	= e740_init,
@@ -733,10 +730,9 @@
 
 MACHINE_START(E750, "Toshiba e750")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.fixup		= eseries_fixup,
 	.init_machine	= e750_init,
@@ -929,10 +925,9 @@
 
 MACHINE_START(E800, "Toshiba e800")
 	/* Maintainer: Ian Molton (spyro@f2s.com) */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= ESERIES_NR_IRQS,
 	.init_irq	= pxa25x_init_irq,
 	.fixup		= eseries_fixup,
 	.init_machine	= e800_init,
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index 626c82b..80a9352 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -32,12 +32,14 @@
 #include <mach/ohci.h>
 #include <plat/i2c.h>
 #include <mach/hardware.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/camera.h>
 
 #include "devices.h"
 #include "generic.h"
 
+#define EZX_NR_IRQS			(IRQ_BOARD_START + 24)
+
 #define GPIO12_A780_FLIP_LID 		12
 #define GPIO15_A1200_FLIP_LID 		15
 #define GPIO15_A910_FLIP_LID 		15
@@ -796,10 +798,9 @@
 }
 
 MACHINE_START(EZX_A780, "Motorola EZX A780")
-	.phys_io        = 0x40000000,
-	.io_pg_offst    = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params    = 0xa0000100,
 	.map_io         = pxa_map_io,
+	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.timer          = &pxa_timer,
 	.init_machine   = a780_init,
@@ -862,10 +863,9 @@
 }
 
 MACHINE_START(EZX_E680, "Motorola EZX E680")
-	.phys_io        = 0x40000000,
-	.io_pg_offst    = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params    = 0xa0000100,
 	.map_io         = pxa_map_io,
+	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.timer          = &pxa_timer,
 	.init_machine   = e680_init,
@@ -928,10 +928,9 @@
 }
 
 MACHINE_START(EZX_A1200, "Motorola EZX A1200")
-	.phys_io        = 0x40000000,
-	.io_pg_offst    = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params    = 0xa0000100,
 	.map_io         = pxa_map_io,
+	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.timer          = &pxa_timer,
 	.init_machine   = a1200_init,
@@ -1120,10 +1119,9 @@
 }
 
 MACHINE_START(EZX_A910, "Motorola EZX A910")
-	.phys_io        = 0x40000000,
-	.io_pg_offst    = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params    = 0xa0000100,
 	.map_io         = pxa_map_io,
+	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.timer          = &pxa_timer,
 	.init_machine   = a910_init,
@@ -1186,10 +1184,9 @@
 }
 
 MACHINE_START(EZX_E6, "Motorola EZX E6")
-	.phys_io        = 0x40000000,
-	.io_pg_offst    = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params    = 0xa0000100,
 	.map_io         = pxa_map_io,
+	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.timer          = &pxa_timer,
 	.init_machine   = e6_init,
@@ -1226,10 +1223,9 @@
 }
 
 MACHINE_START(EZX_E2, "Motorola EZX E2")
-	.phys_io        = 0x40000000,
-	.io_pg_offst    = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params    = 0xa0000100,
 	.map_io         = pxa_map_io,
+	.nr_irqs	= EZX_NR_IRQS,
 	.init_irq       = pxa27x_init_irq,
 	.timer          = &pxa_timer,
 	.init_machine   = e2_init,
diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index baabb3c..6451e9c 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -66,8 +66,7 @@
 		return pxa25x_get_clk_frequency_khz(info);
 	else if (cpu_is_pxa27x())
 		return pxa27x_get_clk_frequency_khz(info);
-	else
-		return pxa3xx_get_clk_frequency_khz(info);
+	return 0;
 }
 EXPORT_SYMBOL(get_clk_frequency_khz);
 
@@ -80,8 +79,7 @@
 		return pxa25x_get_memclk_frequency_10khz();
 	else if (cpu_is_pxa27x())
 		return pxa27x_get_memclk_frequency_10khz();
-	else
-		return pxa3xx_get_memclk_frequency_10khz();
+	return 0;
 }
 EXPORT_SYMBOL(get_memclk_frequency_10khz);
 
diff --git a/arch/arm/mach-pxa/generic.h b/arch/arm/mach-pxa/generic.h
index c6305c5..4b1ad27 100644
--- a/arch/arm/mach-pxa/generic.h
+++ b/arch/arm/mach-pxa/generic.h
@@ -54,11 +54,9 @@
 
 #ifdef CONFIG_PXA3xx
 extern unsigned pxa3xx_get_clk_frequency_khz(int);
-extern unsigned pxa3xx_get_memclk_frequency_10khz(void);
 extern void pxa3xx_clear_reset_status(unsigned int);
 #else
 #define pxa3xx_get_clk_frequency_khz(x)		(0)
-#define pxa3xx_get_memclk_frequency_10khz()	(0)
 static inline void pxa3xx_clear_reset_status(unsigned int mask) {}
 #endif
 
diff --git a/arch/arm/mach-pxa/gumstix.c b/arch/arm/mach-pxa/gumstix.c
index 96c3451..1e2a9a1 100644
--- a/arch/arm/mach-pxa/gumstix.c
+++ b/arch/arm/mach-pxa/gumstix.c
@@ -224,9 +224,7 @@
 }
 
 MACHINE_START(GUMSTIX, "Gumstix")
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0000100, /* match u-boot bi_boot_params */
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa25x_init_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/h5000.c b/arch/arm/mach-pxa/h5000.c
index c1cab08..7057a1f 100644
--- a/arch/arm/mach-pxa/h5000.c
+++ b/arch/arm/mach-pxa/h5000.c
@@ -201,8 +201,6 @@
 }
 
 MACHINE_START(H5400, "HP iPAQ H5000")
-	.phys_io = 0x40000000,
-	.io_pg_offst = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params = 0xa0000100,
 	.map_io = pxa_map_io,
 	.init_irq = pxa25x_init_irq,
diff --git a/arch/arm/mach-pxa/himalaya.c b/arch/arm/mach-pxa/himalaya.c
index f9a2e4b..01b7f07 100644
--- a/arch/arm/mach-pxa/himalaya.c
+++ b/arch/arm/mach-pxa/himalaya.c
@@ -159,8 +159,6 @@
 
 
 MACHINE_START(HIMALAYA, "HTC Himalaya")
-	.phys_io = 0x40000000,
-	.io_pg_offst = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params = 0xa0000100,
 	.map_io = pxa_map_io,
 	.init_irq = pxa25x_init_irq,
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index 848c861..76d93a2 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -870,10 +870,9 @@
 }
 
 MACHINE_START(H4700, "HP iPAQ HX4700")
-	.phys_io      = 0x40000000,
-	.io_pg_offst  = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params  = 0xa0000100,
 	.map_io       = pxa_map_io,
+	.nr_irqs      = HX4700_NR_IRQS,
 	.init_irq     = pxa27x_init_irq,
 	.init_machine = hx4700_init,
 	.timer        = &pxa_timer,
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index 5ccb0ce..d51ee3d 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -191,9 +191,7 @@
 }
 
 MACHINE_START(ICONTROL, "iControl/SafeTcam boards using Embedian MXM-8x10 CoM")
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0000100,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa3xx_init_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index bc78c4d..e773dce 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -194,8 +194,6 @@
 
 MACHINE_START(PXA_IDP, "Vibren PXA255 IDP")
 	/* Maintainer: Vibren Technologies */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= idp_map_io,
 	.init_irq	= pxa25x_init_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/include/mach/balloon3.h b/arch/arm/mach-pxa/include/mach/balloon3.h
index eec92e6..561562b 100644
--- a/arch/arm/mach-pxa/include/mach/balloon3.h
+++ b/arch/arm/mach-pxa/include/mach/balloon3.h
@@ -174,6 +174,8 @@
 #define BALLOON3_CODEC_IRQ	IRQ_GPIO(BALLOON3_GPIO_CODEC_IRQ)
 #define BALLOON3_S0_CD_IRQ	IRQ_GPIO(BALLOON3_GPIO_S0_CD)
 
+#define BALLOON3_NR_IRQS	(IRQ_BOARD_START + 4)
+
 extern int balloon3_has(enum balloon3_features feature);
 
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/debug-macro.S b/arch/arm/mach-pxa/include/mach/debug-macro.S
index 01cf813..7d5c751 100644
--- a/arch/arm/mach-pxa/include/mach/debug-macro.S
+++ b/arch/arm/mach-pxa/include/mach/debug-macro.S
@@ -13,12 +13,10 @@
 
 #include "hardware.h"
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x40000000		@ physical
-		movne	\rx, #io_p2v(0x40000000)	@ virtual
-		orr	\rx, \rx, #0x00100000
+		.macro	addruart, rp, rv
+		mov	\rp, #0x00100000
+		orr	\rv, \rp, #io_p2v(0x40000000)	@ virtual
+		orr	\rp, \rp, #0x40000000		@ physical
 		.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-pxa/include/mach/eseries-irq.h b/arch/arm/mach-pxa/include/mach/eseries-irq.h
index f2a93d5..de292b2 100644
--- a/arch/arm/mach-pxa/include/mach/eseries-irq.h
+++ b/arch/arm/mach-pxa/include/mach/eseries-irq.h
@@ -25,3 +25,4 @@
 #define TMIO_SD_IRQ     IRQ_TMIO(1)
 #define TMIO_USB_IRQ    IRQ_TMIO(2)
 
+#define ESERIES_NR_IRQS	(IRQ_BOARD_START + 16)
diff --git a/arch/arm/mach-pxa/include/mach/hx4700.h b/arch/arm/mach-pxa/include/mach/hx4700.h
index 9eaeed1..3740844 100644
--- a/arch/arm/mach-pxa/include/mach/hx4700.h
+++ b/arch/arm/mach-pxa/include/mach/hx4700.h
@@ -17,6 +17,7 @@
 
 #define HX4700_ASIC3_GPIO_BASE	NR_BUILTIN_GPIO
 #define HX4700_EGPIO_BASE	(HX4700_ASIC3_GPIO_BASE + ASIC3_NUM_GPIOS)
+#define HX4700_NR_IRQS		(IRQ_BOARD_START + 70)
 
 /*
  * PXA GPIOs
diff --git a/arch/arm/mach-pxa/include/mach/irqs.h b/arch/arm/mach-pxa/include/mach/irqs.h
index ffc8314..d372caa 100644
--- a/arch/arm/mach-pxa/include/mach/irqs.h
+++ b/arch/arm/mach-pxa/include/mach/irqs.h
@@ -117,48 +117,12 @@
 /*
  * The following interrupts are for board specific purposes. Since
  * the kernel can only run on one machine at a time, we can re-use
- * these.  There will be 16 IRQs by default.  If it is not enough,
- * IRQ_BOARD_END is allowed be customized for each board, but keep
- * the numbers within sensible limits and in descending order, so
- * when multiple config options are selected, the maximum will be
- * used.
+ * these.
+ * By default, no board IRQ is reserved. It should be finished in
+ * custom board since sparse IRQ is already enabled.
  */
 #define IRQ_BOARD_START		(PXA_GPIO_IRQ_BASE + PXA_GPIO_IRQ_NUM)
 
-#if defined(CONFIG_MACH_H4700)
-#define IRQ_BOARD_END		(IRQ_BOARD_START + 70)
-#elif defined(CONFIG_MACH_ZYLONITE)
-#define IRQ_BOARD_END		(IRQ_BOARD_START + 32)
-#elif defined(CONFIG_PXA_EZX)
-#define IRQ_BOARD_END		(IRQ_BOARD_START + 23)
-#else
-#define IRQ_BOARD_END		(IRQ_BOARD_START + 16)
-#endif
-
-/*
- * Figure out the MAX IRQ number.
- *
- * If we have an SA1111, the max IRQ is S1_BVD1_STSCHG+1.
- * If we have an LoCoMo, the max IRQ is IRQ_LOCOMO_SPI_TEND+1
- * Otherwise, we have the standard IRQs only.
- */
-#ifdef CONFIG_SA1111
-#define NR_IRQS			(IRQ_BOARD_END + 55)
-#elif defined(CONFIG_PXA_HAVE_BOARD_IRQS)
-#define NR_IRQS			(IRQ_BOARD_END)
-#else
 #define NR_IRQS			(IRQ_BOARD_START)
-#endif
-
-/* add IT8152 IRQs beyond BOARD_END */
-#ifdef CONFIG_PCI_HOST_ITE8152
-#define IT8152_LAST_IRQ         (IRQ_BOARD_END + 40)
-
-#if NR_IRQS < (IT8152_LAST_IRQ+1)
-#undef NR_IRQS
-#define NR_IRQS (IT8152_LAST_IRQ+1)
-#endif
-
-#endif /* CONFIG_PCI_HOST_ITE8152 */
 
 #endif /* __ASM_MACH_IRQS_H */
diff --git a/arch/arm/mach-pxa/include/mach/littleton.h b/arch/arm/mach-pxa/include/mach/littleton.h
index 6c9b21c..2a5726c 100644
--- a/arch/arm/mach-pxa/include/mach/littleton.h
+++ b/arch/arm/mach-pxa/include/mach/littleton.h
@@ -10,4 +10,6 @@
 #define EXT0_GPIO_BASE	(NR_BUILTIN_GPIO)
 #define EXT0_GPIO(x)	(EXT0_GPIO_BASE + (x))
 
+#define LITTLETON_NR_IRQS	(IRQ_BOARD_START + 8)
+
 #endif /* __ASM_ARCH_LITTLETON_H */
diff --git a/arch/arm/mach-pxa/include/mach/lpd270.h b/arch/arm/mach-pxa/include/mach/lpd270.h
index 0e6440c..cd07009 100644
--- a/arch/arm/mach-pxa/include/mach/lpd270.h
+++ b/arch/arm/mach-pxa/include/mach/lpd270.h
@@ -38,5 +38,6 @@
 #define LPD270_USBC_IRQ		LPD270_IRQ(2)
 #define LPD270_ETHERNET_IRQ	LPD270_IRQ(3)
 #define LPD270_AC97_IRQ		LPD270_IRQ(4)
+#define LPD270_NR_IRQS		(IRQ_BOARD_START + 5)
 
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/lubbock.h b/arch/arm/mach-pxa/include/mach/lubbock.h
index a0d4247..2a086e8 100644
--- a/arch/arm/mach-pxa/include/mach/lubbock.h
+++ b/arch/arm/mach-pxa/include/mach/lubbock.h
@@ -45,6 +45,9 @@
 #define LUBBOCK_USB_DISC_IRQ	LUBBOCK_IRQ(6)  /* usb disconnect */
 #define LUBBOCK_LAST_IRQ	LUBBOCK_IRQ(6)
 
+#define LUBBOCK_SA1111_IRQ_BASE	(IRQ_BOARD_START + 16)
+#define LUBBOCK_NR_IRQS		(IRQ_BOARD_START + 16 + 55)
+
 #ifndef __ASSEMBLY__
 extern void lubbock_set_misc_wr(unsigned int mask, unsigned int set);
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/magician.h b/arch/arm/mach-pxa/include/mach/magician.h
index 20ef37d..0a2efcf 100644
--- a/arch/arm/mach-pxa/include/mach/magician.h
+++ b/arch/arm/mach-pxa/include/mach/magician.h
@@ -71,6 +71,8 @@
 #define IRQ_MAGICIAN_BT		(IRQ_BOARD_START + 2)
 #define IRQ_MAGICIAN_VBUS	(IRQ_BOARD_START + 3)
 
+#define MAGICIAN_NR_IRQS	(IRQ_BOARD_START + 8)
+
 /*
  * CPLD EGPIOs
  */
diff --git a/arch/arm/mach-pxa/include/mach/mainstone.h b/arch/arm/mach-pxa/include/mach/mainstone.h
index 86e623a..4c2d11c 100644
--- a/arch/arm/mach-pxa/include/mach/mainstone.h
+++ b/arch/arm/mach-pxa/include/mach/mainstone.h
@@ -134,4 +134,6 @@
 #define MAINSTONE_S1_STSCHG_IRQ	MAINSTONE_IRQ(14)
 #define MAINSTONE_S1_IRQ	MAINSTONE_IRQ(15)
 
+#define MAINSTONE_NR_IRQS	(IRQ_BOARD_START + 16)
+
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/mfp-pxa930.h b/arch/arm/mach-pxa/include/mach/mfp-pxa930.h
index 0d119d3..04f7c97 100644
--- a/arch/arm/mach-pxa/include/mach/mfp-pxa930.h
+++ b/arch/arm/mach-pxa/include/mach/mfp-pxa930.h
@@ -69,6 +69,7 @@
 #define nBE0_GPIO_60		MFP_CFG(nBE0, AF0)
 #define nBE1_GPIO_61		MFP_CFG(nBE1, AF0)
 #define RDY_GPIO_62		MFP_CFG(RDY, AF0)
+#define PMIC_INT_GPIO83		MFP_CFG_LPM(PMIC_INT, AF0, PULL_HIGH)
 
 /* Chip Select */
 #define DF_nCS0_nCS2		MFP_CFG_LPM(DF_nCS0, AF3, PULL_HIGH)
@@ -92,6 +93,9 @@
 #define GPIO63_CI2C_SCL		MFP_CFG_LPM(GPIO63, AF4, PULL_HIGH)
 #define GPIO64_CI2C_SDA		MFP_CFG_LPM(GPIO64, AF4, PULL_HIGH)
 
+#define GPIO73_CI2C_SCL		MFP_CFG_LPM(GPIO73, AF1, PULL_HIGH)
+#define GPIO74_CI2C_SDA		MFP_CFG_LPM(GPIO74, AF1, PULL_HIGH)
+
 #define GPIO77_CI2C_SCL		MFP_CFG_LPM(GPIO77, AF2, PULL_HIGH)
 #define GPIO78_CI2C_SDA		MFP_CFG_LPM(GPIO78, AF2, PULL_HIGH)
 
@@ -345,6 +349,9 @@
 #define GPIO69_UART1_CTS	MFP_CFG(GPIO69, AF2)
 #define GPIO70_UART1_RTS	MFP_CFG(GPIO70, AF2)
 
+#define GPIO53_UART1_TXD	MFP_CFG(GPIO53, AF2)
+#define GPIO54_UART1_RXD	MFP_CFG(GPIO54, AF2)
+
 /* UART2 - BTUART */
 #define GPIO91_UART2_RXD	MFP_CFG(GPIO91, AF1)
 #define GPIO92_UART2_TXD	MFP_CFG(GPIO92, AF1)
diff --git a/arch/arm/mach-pxa/include/mach/pcm027.h b/arch/arm/mach-pxa/include/mach/pcm027.h
index 040832631..4bac588 100644
--- a/arch/arm/mach-pxa/include/mach/pcm027.h
+++ b/arch/arm/mach-pxa/include/mach/pcm027.h
@@ -30,6 +30,8 @@
 #define PCM027_MMCDET_IRQ      PCM027_IRQ(2)
 #define PCM027_PM_5V_IRQ       PCM027_IRQ(3)
 
+#define PCM027_NR_IRQS		(IRQ_BOARD_START + 32)
+
 /* I2C RTC */
 #define PCM027_RTC_IRQ_GPIO	0
 #define PCM027_RTC_IRQ		IRQ_GPIO(PCM027_RTC_IRQ_GPIO)
diff --git a/arch/arm/mach-pxa/include/mach/poodle.h b/arch/arm/mach-pxa/include/mach/poodle.h
index 0b3e6d0..83d1cfd 100644
--- a/arch/arm/mach-pxa/include/mach/poodle.h
+++ b/arch/arm/mach-pxa/include/mach/poodle.h
@@ -85,6 +85,8 @@
 #define POODLE_LOCOMO_GPIO_232VCC_ON   LOCOMO_GPIO(12)
 #define POODLE_LOCOMO_GPIO_JK_B        LOCOMO_GPIO(13)
 
+#define POODLE_NR_IRQS		(IRQ_BOARD_START + 4)	/* 4 for LoCoMo */
+
 extern struct platform_device poodle_locomo_device;
 
 #endif /* __ASM_ARCH_POODLE_H  */
diff --git a/arch/arm/mach-pxa/include/mach/pxa3xx-u2d.h b/arch/arm/mach-pxa/include/mach/pxa3xx-u2d.h
new file mode 100644
index 0000000..9d82cb6
--- /dev/null
+++ b/arch/arm/mach-pxa/include/mach/pxa3xx-u2d.h
@@ -0,0 +1,35 @@
+/*
+ * PXA3xx U2D header
+ *
+ * Copyright (C) 2010 CompuLab Ltd.
+ *
+ * Igor Grinberg <grinberg@compulab.co.il>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __PXA310_U2D__
+#define __PXA310_U2D__
+
+#include <linux/usb/ulpi.h>
+
+struct pxa3xx_u2d_platform_data {
+
+#define ULPI_SER_6PIN	(1 << 0)
+#define ULPI_SER_3PIN	(1 << 1)
+	unsigned int ulpi_mode;
+
+	int (*init)(struct device *);
+	void (*exit)(struct device *);
+};
+
+
+/* Start PXA3xx U2D host */
+int pxa3xx_u2d_start_hc(struct usb_bus *host);
+/* Stop PXA3xx U2D host */
+void pxa3xx_u2d_stop_hc(struct usb_bus *host);
+
+extern void pxa3xx_set_u2d_info(struct pxa3xx_u2d_platform_data *info);
+
+#endif /* __PXA310_U2D__ */
diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h
index 1bbd1f2..1272c4b 100644
--- a/arch/arm/mach-pxa/include/mach/tosa.h
+++ b/arch/arm/mach-pxa/include/mach/tosa.h
@@ -20,6 +20,7 @@
 /* Jacket Scoop */
 #define TOSA_SCOOP_PHYS  	(PXA_CS5_PHYS + 0x00800000)
 
+#define TOSA_NR_IRQS		(IRQ_BOARD_START + TC6393XB_NR_IRQS)
 /*
  * SCOOP2 internal GPIOs
  */
diff --git a/arch/arm/mach-pxa/include/mach/zeus.h b/arch/arm/mach-pxa/include/mach/zeus.h
index 6e11997..faa408a 100644
--- a/arch/arm/mach-pxa/include/mach/zeus.h
+++ b/arch/arm/mach-pxa/include/mach/zeus.h
@@ -15,6 +15,8 @@
 #ifndef _MACH_ZEUS_H
 #define _MACH_ZEUS_H
 
+#define ZEUS_NR_IRQS		(IRQ_BOARD_START + 48)
+
 /* Physical addresses */
 #define ZEUS_FLASH_PHYS		PXA_CS0_PHYS
 #define ZEUS_ETH0_PHYS		PXA_CS1_PHYS
diff --git a/arch/arm/mach-pxa/include/mach/zylonite.h b/arch/arm/mach-pxa/include/mach/zylonite.h
index 9edf645..ea24998 100644
--- a/arch/arm/mach-pxa/include/mach/zylonite.h
+++ b/arch/arm/mach-pxa/include/mach/zylonite.h
@@ -5,6 +5,8 @@
 
 #define EXT_GPIO(x)		(128 + (x))
 
+#define ZYLONITE_NR_IRQS	(IRQ_BOARD_START + 32)
+
 /* the following variables are processor specific and initialized
  * by the corresponding zylonite_pxa3xx_init()
  */
diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c
index 9b90461..41aa89e 100644
--- a/arch/arm/mach-pxa/littleton.c
+++ b/arch/arm/mach-pxa/littleton.c
@@ -43,7 +43,7 @@
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
 #include <mach/pxa2xx_spi.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/littleton.h>
 #include <plat/i2c.h>
 #include <plat/pxa3xx_nand.h>
@@ -437,10 +437,9 @@
 }
 
 MACHINE_START(LITTLETON, "Marvell Form Factor Development Platform (aka Littleton)")
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0000100,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= LITTLETON_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= littleton_init,
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index d279507..623af02 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -505,10 +505,9 @@
 
 MACHINE_START(LOGICPD_PXA270, "LogicPD PXA270 Card Engine")
 	/* Maintainer: Peter Barada */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= lpd270_map_io,
+	.nr_irqs	= LPD270_NR_IRQS,
 	.init_irq	= lpd270_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= lpd270_init,
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index 330c328..1499493 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -229,7 +229,7 @@
 };
 
 static struct sa1111_platform_data sa1111_info = {
-	.irq_base	= IRQ_BOARD_END,
+	.irq_base	= LUBBOCK_SA1111_IRQ_BASE,
 };
 
 static struct platform_device sa1111_device = {
@@ -557,9 +557,8 @@
 
 MACHINE_START(LUBBOCK, "Intel DBPXA250 Development Platform (aka Lubbock)")
 	/* Maintainer: MontaVista Software Inc. */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= lubbock_map_io,
+	.nr_irqs	= LUBBOCK_NR_IRQS,
 	.init_irq	= lubbock_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= lubbock_init,
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index e81dd0c..9066376 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -764,10 +764,9 @@
 
 
 MACHINE_START(MAGICIAN, "HTC Magician")
-	.phys_io = 0x40000000,
-	.io_pg_offst = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params = 0xa0000100,
 	.map_io = pxa_map_io,
+	.nr_irqs = MAGICIAN_NR_IRQS,
 	.init_irq = pxa27x_init_irq,
 	.init_machine = magician_init,
 	.timer = &pxa_timer,
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index 5543c64..a980a5c 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -50,7 +50,7 @@
 #include <mach/mmc.h>
 #include <mach/irda.h>
 #include <mach/ohci.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 
 #include "generic.h"
 #include "devices.h"
@@ -624,10 +624,9 @@
 
 MACHINE_START(MAINSTONE, "Intel HCDDBBVA0 Development Platform (aka Mainstone)")
 	/* Maintainer: MontaVista Software Inc. */
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0000100,	/* BLOB boot parameter setting */
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= mainstone_map_io,
+	.nr_irqs	= MAINSTONE_NR_IRQS,
 	.init_irq	= mainstone_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= mainstone_init,
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index dc66942..0c31fab 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -45,7 +45,7 @@
 
 #include <mach/pxa27x.h>
 #include <mach/regs-rtc.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
 #include <mach/udc.h>
@@ -819,8 +819,6 @@
 }
 
 MACHINE_START(MIOA701, "MIO A701")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= &pxa_map_io,
 	.init_irq	= &pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/mp900.c b/arch/arm/mach-pxa/mp900.c
index 6d45039..116167aa 100644
--- a/arch/arm/mach-pxa/mp900.c
+++ b/arch/arm/mach-pxa/mp900.c
@@ -92,9 +92,7 @@
 
 /* Maintainer - Michael Petchkovsky <mkpetch@internode.on.net> */
 MACHINE_START(NEC_MP900, "MobilePro900/C")
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0220100,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.timer		= &pxa_timer,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa25x_init_irq,
diff --git a/arch/arm/mach-pxa/palmld.c b/arch/arm/mach-pxa/palmld.c
index 91038ee..ce092c5 100644
--- a/arch/arm/mach-pxa/palmld.c
+++ b/arch/arm/mach-pxa/palmld.c
@@ -39,7 +39,7 @@
 #include <mach/mmc.h>
 #include <mach/pxafb.h>
 #include <mach/irda.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/palmasoc.h>
 #include <mach/palm27x.h>
 
@@ -343,8 +343,6 @@
 }
 
 MACHINE_START(PALMLD, "Palm LifeDrive")
-	.phys_io	= PALMLD_PHYS_IO_START,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= palmld_map_io,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/palmt5.c b/arch/arm/mach-pxa/palmt5.c
index 1c28199..862da81 100644
--- a/arch/arm/mach-pxa/palmt5.c
+++ b/arch/arm/mach-pxa/palmt5.c
@@ -39,7 +39,7 @@
 #include <mach/mmc.h>
 #include <mach/pxafb.h>
 #include <mach/irda.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/udc.h>
 #include <mach/palmasoc.h>
 #include <mach/palm27x.h>
@@ -202,8 +202,6 @@
 }
 
 MACHINE_START(PALMT5, "Palm Tungsten|T5")
-	.phys_io	= PALMT5_PHYS_IO_START,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
 	.reserve	= palmt5_reserve,
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index ce1104d..2131d58 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -412,9 +412,7 @@
 };
 
 MACHINE_START(PALMTC, "Palm Tungsten|C")
-	.phys_io	= 0x40000000,
 	.boot_params 	= 0xa0000100,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa25x_init_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/palmte2.c b/arch/arm/mach-pxa/palmte2.c
index 93c11a0..a9dae7b 100644
--- a/arch/arm/mach-pxa/palmte2.c
+++ b/arch/arm/mach-pxa/palmte2.c
@@ -373,8 +373,6 @@
 }
 
 MACHINE_START(PALMTE2, "Palm Tungsten|E2")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa25x_init_irq,
diff --git a/arch/arm/mach-pxa/palmtreo.c b/arch/arm/mach-pxa/palmtreo.c
index 52defd5..00e2d7b 100644
--- a/arch/arm/mach-pxa/palmtreo.c
+++ b/arch/arm/mach-pxa/palmtreo.c
@@ -39,7 +39,7 @@
 #include <mach/mmc.h>
 #include <mach/pxafb.h>
 #include <mach/irda.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/udc.h>
 #include <mach/ohci.h>
 #include <mach/pxa2xx-regs.h>
@@ -441,8 +441,6 @@
 }
 
 MACHINE_START(TREO680, "Palm Treo 680")
-	.phys_io        = TREO_PHYS_IO_START,
-	.io_pg_offst    = io_p2v(0x40000000),
 	.boot_params    = 0xa0000100,
 	.map_io         = pxa_map_io,
 	.reserve	= treo_reserve,
@@ -452,8 +450,6 @@
 MACHINE_END
 
 MACHINE_START(CENTRO, "Palm Centro 685")
-	.phys_io        = TREO_PHYS_IO_START,
-	.io_pg_offst    = io_p2v(0x40000000),
 	.boot_params    = 0xa0000100,
 	.map_io         = pxa_map_io,
 	.reserve	= treo_reserve,
diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c
index 144dc2b..d2060a1 100644
--- a/arch/arm/mach-pxa/palmtx.c
+++ b/arch/arm/mach-pxa/palmtx.c
@@ -43,7 +43,7 @@
 #include <mach/mmc.h>
 #include <mach/pxafb.h>
 #include <mach/irda.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/udc.h>
 #include <mach/palmasoc.h>
 #include <mach/palm27x.h>
@@ -363,8 +363,6 @@
 }
 
 MACHINE_START(PALMTX, "Palm T|X")
-	.phys_io	= PALMTX_PHYS_IO_START,
-	.io_pg_offst	= io_p2v(0x40000000),
 	.boot_params	= 0xa0000100,
 	.map_io		= palmtx_map_io,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c
index 87e4b10..af6203f 100644
--- a/arch/arm/mach-pxa/palmz72.c
+++ b/arch/arm/mach-pxa/palmz72.c
@@ -41,7 +41,7 @@
 #include <mach/mmc.h>
 #include <mach/pxafb.h>
 #include <mach/irda.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/udc.h>
 #include <mach/palmasoc.h>
 #include <mach/palm27x.h>
@@ -279,8 +279,6 @@
 }
 
 MACHINE_START(PALMZ72, "Palm Zire72")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= io_p2v(0x40000000),
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/pcm027.c b/arch/arm/mach-pxa/pcm027.c
index 2190af0..c77e8f3 100644
--- a/arch/arm/mach-pxa/pcm027.c
+++ b/arch/arm/mach-pxa/pcm027.c
@@ -259,9 +259,8 @@
 MACHINE_START(PCM027, "Phytec Messtechnik GmbH phyCORE-PXA270")
 	/* Maintainer: Pengutronix */
 	.boot_params	= 0xa0000100,
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pcm027_map_io,
+	.nr_irqs	= PCM027_NR_IRQS,
 	.init_irq	= pxa27x_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= pcm027_init,
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 55e8fcd..93a191c 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -465,10 +465,9 @@
 }
 
 MACHINE_START(POODLE, "SHARP Poodle")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.fixup		= fixup_poodle,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= POODLE_NR_IRQS,	/* 4 for LoCoMo */
 	.init_irq	= pxa25x_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= poodle_init,
diff --git a/arch/arm/mach-pxa/pxa3xx-ulpi.c b/arch/arm/mach-pxa/pxa3xx-ulpi.c
new file mode 100644
index 0000000..ce7168b
--- /dev/null
+++ b/arch/arm/mach-pxa/pxa3xx-ulpi.c
@@ -0,0 +1,400 @@
+/*
+ * linux/arch/arm/mach-pxa/pxa3xx-ulpi.c
+ *
+ * code specific to pxa3xx aka Monahans
+ *
+ * Copyright (C) 2010 CompuLab Ltd.
+ *
+ * 2010-13-07: Igor Grinberg <grinberg@compulab.co.il>
+ *             initial version: pxa310 USB Host mode support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/clk.h>
+#include <linux/usb.h>
+#include <linux/usb/otg.h>
+
+#include <mach/hardware.h>
+#include <mach/regs-u2d.h>
+#include <mach/pxa3xx-u2d.h>
+
+struct pxa3xx_u2d_ulpi {
+	struct clk		*clk;
+	void __iomem		*mmio_base;
+
+	struct otg_transceiver	*otg;
+	unsigned int		ulpi_mode;
+};
+
+static struct pxa3xx_u2d_ulpi *u2d;
+
+static inline u32 u2d_readl(u32 reg)
+{
+	return __raw_readl(u2d->mmio_base + reg);
+}
+
+static inline void u2d_writel(u32 reg, u32 val)
+{
+	__raw_writel(val, u2d->mmio_base + reg);
+}
+
+#if defined(CONFIG_PXA310_ULPI)
+enum u2d_ulpi_phy_mode {
+	SYNCH		= 0,
+	CARKIT		= (1 << 0),
+	SER_3PIN	= (1 << 1),
+	SER_6PIN	= (1 << 2),
+	LOWPOWER	= (1 << 3),
+};
+
+static inline enum u2d_ulpi_phy_mode pxa310_ulpi_get_phymode(void)
+{
+	return (u2d_readl(U2DOTGUSR) >> 28) & 0xF;
+}
+
+static int pxa310_ulpi_poll(void)
+{
+	int timeout = 50000;
+
+	while (timeout--) {
+		if (!(u2d_readl(U2DOTGUCR) & U2DOTGUCR_RUN))
+			return 0;
+
+		cpu_relax();
+	}
+
+	pr_warning("%s: ULPI access timed out!\n", __func__);
+
+	return -ETIMEDOUT;
+}
+
+static int pxa310_ulpi_read(struct otg_transceiver *otg, u32 reg)
+{
+	int err;
+
+	if (pxa310_ulpi_get_phymode() != SYNCH) {
+		pr_warning("%s: PHY is not in SYNCH mode!\n", __func__);
+		return -EBUSY;
+	}
+
+	u2d_writel(U2DOTGUCR, U2DOTGUCR_RUN | U2DOTGUCR_RNW | (reg << 16));
+	msleep(5);
+
+	err = pxa310_ulpi_poll();
+	if (err)
+		return err;
+
+	return u2d_readl(U2DOTGUCR) & U2DOTGUCR_RDATA;
+}
+
+static int pxa310_ulpi_write(struct otg_transceiver *otg, u32 val, u32 reg)
+{
+	if (pxa310_ulpi_get_phymode() != SYNCH) {
+		pr_warning("%s: PHY is not in SYNCH mode!\n", __func__);
+		return -EBUSY;
+	}
+
+	u2d_writel(U2DOTGUCR, U2DOTGUCR_RUN | (reg << 16) | (val << 8));
+	msleep(5);
+
+	return pxa310_ulpi_poll();
+}
+
+struct otg_io_access_ops pxa310_ulpi_access_ops = {
+	.read	= pxa310_ulpi_read,
+	.write	= pxa310_ulpi_write,
+};
+
+static void pxa310_otg_transceiver_rtsm(void)
+{
+	u32 u2dotgcr;
+
+	/* put PHY to sync mode */
+	u2dotgcr = u2d_readl(U2DOTGCR);
+	u2dotgcr |=  U2DOTGCR_RTSM | U2DOTGCR_UTMID;
+	u2d_writel(U2DOTGCR, u2dotgcr);
+	msleep(10);
+
+	/* setup OTG sync mode */
+	u2dotgcr = u2d_readl(U2DOTGCR);
+	u2dotgcr |= U2DOTGCR_ULAF;
+	u2dotgcr &= ~(U2DOTGCR_SMAF | U2DOTGCR_CKAF);
+	u2d_writel(U2DOTGCR, u2dotgcr);
+}
+
+static int pxa310_start_otg_host_transcvr(struct usb_bus *host)
+{
+	int err;
+
+	pxa310_otg_transceiver_rtsm();
+
+	err = otg_init(u2d->otg);
+	if (err) {
+		pr_err("OTG transceiver init failed");
+		return err;
+	}
+
+	err = otg_set_vbus(u2d->otg, 1);
+	if (err) {
+		pr_err("OTG transceiver VBUS set failed");
+		return err;
+	}
+
+	err = otg_set_host(u2d->otg, host);
+	if (err)
+		pr_err("OTG transceiver Host mode set failed");
+
+	return err;
+}
+
+static int pxa310_start_otg_hc(struct usb_bus *host)
+{
+	u32 u2dotgcr;
+	int err;
+
+	/* disable USB device controller */
+	u2d_writel(U2DCR, u2d_readl(U2DCR) & ~U2DCR_UDE);
+	u2d_writel(U2DOTGCR, u2d_readl(U2DOTGCR) | U2DOTGCR_UTMID);
+	u2d_writel(U2DOTGICR, u2d_readl(U2DOTGICR) & ~0x37F7F);
+
+	err = pxa310_start_otg_host_transcvr(host);
+	if (err)
+		return err;
+
+	/* set xceiver mode */
+	if (u2d->ulpi_mode & ULPI_IC_6PIN_SERIAL)
+		u2d_writel(U2DP3CR, u2d_readl(U2DP3CR) & ~U2DP3CR_P2SS);
+	else if (u2d->ulpi_mode & ULPI_IC_3PIN_SERIAL)
+		u2d_writel(U2DP3CR, u2d_readl(U2DP3CR) | U2DP3CR_P2SS);
+
+	/* start OTG host controller */
+	u2dotgcr = u2d_readl(U2DOTGCR) | U2DOTGCR_SMAF;
+	u2d_writel(U2DOTGCR, u2dotgcr & ~(U2DOTGCR_ULAF | U2DOTGCR_CKAF));
+
+	return 0;
+}
+
+static void pxa310_stop_otg_hc(void)
+{
+	pxa310_otg_transceiver_rtsm();
+
+	otg_set_host(u2d->otg, NULL);
+	otg_set_vbus(u2d->otg, 0);
+	otg_shutdown(u2d->otg);
+}
+
+static void pxa310_u2d_setup_otg_hc(void)
+{
+	u32 u2dotgcr;
+
+	u2dotgcr = u2d_readl(U2DOTGCR);
+	u2dotgcr |= U2DOTGCR_ULAF | U2DOTGCR_UTMID;
+	u2dotgcr &= ~(U2DOTGCR_SMAF | U2DOTGCR_CKAF);
+	u2d_writel(U2DOTGCR, u2dotgcr);
+	msleep(5);
+	u2d_writel(U2DOTGCR, u2dotgcr | U2DOTGCR_ULE);
+	msleep(5);
+	u2d_writel(U2DOTGICR, u2d_readl(U2DOTGICR) & ~0x37F7F);
+}
+
+static int pxa310_otg_init(struct pxa3xx_u2d_platform_data *pdata)
+{
+	unsigned int ulpi_mode = ULPI_OTG_DRVVBUS;
+
+	if (pdata) {
+		if (pdata->ulpi_mode & ULPI_SER_6PIN)
+			ulpi_mode |= ULPI_IC_6PIN_SERIAL;
+		else if (pdata->ulpi_mode & ULPI_SER_3PIN)
+			ulpi_mode |= ULPI_IC_3PIN_SERIAL;
+	}
+
+	u2d->ulpi_mode = ulpi_mode;
+
+	u2d->otg = otg_ulpi_create(&pxa310_ulpi_access_ops, ulpi_mode);
+	if (!u2d->otg)
+		return -ENOMEM;
+
+	u2d->otg->io_priv = u2d->mmio_base;
+
+	return 0;
+}
+
+static void pxa310_otg_exit(void)
+{
+	kfree(u2d->otg);
+}
+#else
+static inline void pxa310_u2d_setup_otg_hc(void) {}
+static inline int pxa310_start_otg_hc(struct usb_bus *host)
+{
+	return 0;
+}
+static inline void pxa310_stop_otg_hc(void) {}
+static inline int pxa310_otg_init(struct pxa3xx_u2d_platform_data *pdata)
+{
+	return 0;
+}
+static inline void pxa310_otg_exit(void) {}
+#endif /* CONFIG_PXA310_ULPI */
+
+int pxa3xx_u2d_start_hc(struct usb_bus *host)
+{
+	int err = 0;
+
+	/* In case the PXA3xx ULPI isn't used, do nothing. */
+	if (!u2d)
+		return 0;
+
+	clk_enable(u2d->clk);
+
+	if (cpu_is_pxa310()) {
+		pxa310_u2d_setup_otg_hc();
+		err = pxa310_start_otg_hc(host);
+	}
+
+	return err;
+}
+
+void pxa3xx_u2d_stop_hc(struct usb_bus *host)
+{
+	/* In case the PXA3xx ULPI isn't used, do nothing. */
+	if (!u2d)
+		return;
+
+	if (cpu_is_pxa310())
+		pxa310_stop_otg_hc();
+
+	clk_disable(u2d->clk);
+}
+
+static int pxa3xx_u2d_probe(struct platform_device *pdev)
+{
+	struct pxa3xx_u2d_platform_data *pdata = pdev->dev.platform_data;
+	struct resource *r;
+	int err;
+
+	u2d = kzalloc(sizeof(struct pxa3xx_u2d_ulpi), GFP_KERNEL);
+	if (!u2d) {
+		dev_err(&pdev->dev, "failed to allocate memory\n");
+		return -ENOMEM;
+	}
+
+	u2d->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(u2d->clk)) {
+		dev_err(&pdev->dev, "failed to get u2d clock\n");
+		err = PTR_ERR(u2d->clk);
+		goto err_free_mem;
+	}
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r) {
+		dev_err(&pdev->dev, "no IO memory resource defined\n");
+		err = -ENODEV;
+		goto err_put_clk;
+	}
+
+        r = request_mem_region(r->start, resource_size(r), pdev->name);
+        if (!r) {
+                dev_err(&pdev->dev, "failed to request memory resource\n");
+                err = -EBUSY;
+                goto err_put_clk;
+        }
+
+	u2d->mmio_base = ioremap(r->start, resource_size(r));
+	if (!u2d->mmio_base) {
+		dev_err(&pdev->dev, "ioremap() failed\n");
+		err = -ENODEV;
+		goto err_free_res;
+	}
+
+	if (pdata->init) {
+		err = pdata->init(&pdev->dev);
+		if (err)
+			goto err_free_io;
+	}
+
+	/* Only PXA310 U2D has OTG functionality */
+	if (cpu_is_pxa310()) {
+		err = pxa310_otg_init(pdata);
+		if (err)
+			goto err_free_plat;
+	}
+
+	platform_set_drvdata(pdev, &u2d);
+
+	return 0;
+
+err_free_plat:
+	if (pdata->exit)
+		pdata->exit(&pdev->dev);
+err_free_io:
+	iounmap(u2d->mmio_base);
+err_free_res:
+	release_mem_region(r->start, resource_size(r));
+err_put_clk:
+	clk_put(u2d->clk);
+err_free_mem:
+	kfree(u2d);
+	return err;
+}
+
+static int pxa3xx_u2d_remove(struct platform_device *pdev)
+{
+	struct pxa3xx_u2d_platform_data *pdata = pdev->dev.platform_data;
+	struct resource *r;
+
+	if (cpu_is_pxa310()) {
+		pxa310_stop_otg_hc();
+		pxa310_otg_exit();
+	}
+
+	if (pdata->exit)
+		pdata->exit(&pdev->dev);
+
+	platform_set_drvdata(pdev, NULL);
+	iounmap(u2d->mmio_base);
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(r->start, resource_size(r));
+
+	clk_put(u2d->clk);
+
+	kfree(u2d);
+
+	return 0;
+}
+
+static struct platform_driver pxa3xx_u2d_ulpi_driver = {
+        .driver		= {
+                .name   = "pxa3xx-u2d",
+		.owner	= THIS_MODULE,
+        },
+        .probe          = pxa3xx_u2d_probe,
+        .remove         = pxa3xx_u2d_remove,
+};
+
+static int pxa3xx_u2d_ulpi_init(void)
+{
+	return platform_driver_register(&pxa3xx_u2d_ulpi_driver);
+}
+module_init(pxa3xx_u2d_ulpi_init);
+
+static void __exit pxa3xx_u2d_ulpi_exit(void)
+{
+	platform_driver_unregister(&pxa3xx_u2d_ulpi_driver);
+}
+module_exit(pxa3xx_u2d_ulpi_exit);
+
+MODULE_DESCRIPTION("PXA3xx U2D ULPI driver");
+MODULE_AUTHOR("Igor Grinberg");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index fa00148..c85c3a7 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -98,23 +98,6 @@
 	return CLK / 1000;
 }
 
-/*
- * Return the current static memory controller clock frequency
- * in units of 10kHz
- */
-unsigned int pxa3xx_get_memclk_frequency_10khz(void)
-{
-	unsigned long acsr;
-	unsigned int smcfs, clk = 0;
-
-	acsr = ACSR;
-
-	smcfs = (acsr >> 23) & 0x7;
-	clk = (acsr & ACCR_D0CS) ? RO_CLK : smcfs_mult[smcfs] * BASE_CLK;
-
-	return (clk / 10000);
-}
-
 void pxa3xx_clear_reset_status(unsigned int mask)
 {
 	/* RESET_STATUS_* has a 1:1 mapping with ARSR */
@@ -265,7 +248,7 @@
 	INIT_CLKREG(&clk_pxa3xx_i2c, "pxa2xx-i2c.0", NULL),
 	INIT_CLKREG(&clk_pxa3xx_udc, "pxa27x-udc", NULL),
 	INIT_CLKREG(&clk_pxa3xx_usbh, "pxa27x-ohci", NULL),
-	INIT_CLKREG(&clk_pxa3xx_u2d, NULL, "U2DCLK"),
+	INIT_CLKREG(&clk_pxa3xx_u2d, "pxa3xx-u2d", NULL),
 	INIT_CLKREG(&clk_pxa3xx_keypad, "pxa27x-keypad", NULL),
 	INIT_CLKREG(&clk_pxa3xx_ssp1, "pxa27x-ssp.0", NULL),
 	INIT_CLKREG(&clk_pxa3xx_ssp2, "pxa27x-ssp.1", NULL),
diff --git a/arch/arm/mach-pxa/pxa930.c b/arch/arm/mach-pxa/pxa930.c
index 0642920..7d29dd3 100644
--- a/arch/arm/mach-pxa/pxa930.c
+++ b/arch/arm/mach-pxa/pxa930.c
@@ -192,7 +192,7 @@
 
 static int __init pxa930_init(void)
 {
-	if (cpu_is_pxa930() || cpu_is_pxa935()) {
+	if (cpu_is_pxa930() || cpu_is_pxa935() || cpu_is_pxa950()) {
 		mfp_init_base(io_p2v(MFPR_BASE));
 		mfp_init_addr(pxa930_mfp_addr_map);
 	}
diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c
index 67e04f4..4121d03 100644
--- a/arch/arm/mach-pxa/raumfeld.c
+++ b/arch/arm/mach-pxa/raumfeld.c
@@ -1083,8 +1083,6 @@
 
 #ifdef CONFIG_MACH_RAUMFELD_RC
 MACHINE_START(RAUMFELD_RC, "Raumfeld Controller")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= RAUMFELD_SDRAM_BASE + 0x100,
 	.init_machine	= raumfeld_controller_init,
 	.map_io		= pxa_map_io,
@@ -1095,8 +1093,6 @@
 
 #ifdef CONFIG_MACH_RAUMFELD_CONNECTOR
 MACHINE_START(RAUMFELD_CONNECTOR, "Raumfeld Connector")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= RAUMFELD_SDRAM_BASE + 0x100,
 	.init_machine	= raumfeld_connector_init,
 	.map_io		= pxa_map_io,
@@ -1107,8 +1103,6 @@
 
 #ifdef CONFIG_MACH_RAUMFELD_SPEAKER
 MACHINE_START(RAUMFELD_SPEAKER, "Raumfeld Speaker")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= RAUMFELD_SDRAM_BASE + 0x100,
 	.init_machine	= raumfeld_speaker_init,
 	.map_io		= pxa_map_io,
diff --git a/arch/arm/mach-pxa/saar.c b/arch/arm/mach-pxa/saar.c
index 115b6f2..4b521e0 100644
--- a/arch/arm/mach-pxa/saar.c
+++ b/arch/arm/mach-pxa/saar.c
@@ -596,9 +596,7 @@
 
 MACHINE_START(SAAR, "PXA930 Handheld Platform (aka SAAR)")
 	/* Maintainer: Eric Miao <eric.miao@marvell.com> */
-	.phys_io        = 0x40000000,
 	.boot_params    = 0xa0000100,
-	.io_pg_offst    = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io         = pxa_map_io,
 	.init_irq       = pxa3xx_init_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 1cd99cb..f736119 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -979,8 +979,6 @@
 
 #ifdef CONFIG_MACH_SPITZ
 MACHINE_START(SPITZ, "SHARP Spitz")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.fixup		= spitz_fixup,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
@@ -991,8 +989,6 @@
 
 #ifdef CONFIG_MACH_BORZOI
 MACHINE_START(BORZOI, "SHARP Borzoi")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.fixup		= spitz_fixup,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
@@ -1003,8 +999,6 @@
 
 #ifdef CONFIG_MACH_AKITA
 MACHINE_START(AKITA, "SHARP Akita")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.fixup		= spitz_fixup,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c
index a654d1e..738adc1 100644
--- a/arch/arm/mach-pxa/stargate2.c
+++ b/arch/arm/mach-pxa/stargate2.c
@@ -56,6 +56,8 @@
 #include "devices.h"
 #include "generic.h"
 
+#define STARGATE_NR_IRQS	(IRQ_BOARD_START + 8)
+
 /* Bluetooth */
 #define SG2_BT_RESET		81
 
@@ -996,8 +998,6 @@
 
 #ifdef CONFIG_MACH_INTELMOTE2
 MACHINE_START(INTELMOTE2, "IMOTE 2")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.timer		= &pxa_timer,
@@ -1008,9 +1008,8 @@
 
 #ifdef CONFIG_MACH_STARGATE2
 MACHINE_START(STARGATE2, "Stargate 2")
-	.phys_io = 0x40000000,
-	.io_pg_offst = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io = pxa_map_io,
+	.nr_irqs = STARGATE_NR_IRQS,
 	.init_irq = pxa27x_init_irq,
 	.timer = &pxa_timer,
 	.init_machine = stargate2_init,
diff --git a/arch/arm/mach-pxa/tavorevb.c b/arch/arm/mach-pxa/tavorevb.c
index f02dcb5..2ea7545 100644
--- a/arch/arm/mach-pxa/tavorevb.c
+++ b/arch/arm/mach-pxa/tavorevb.c
@@ -25,7 +25,7 @@
 
 #include <mach/pxa930.h>
 #include <mach/pxafb.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 
 #include "devices.h"
 #include "generic.h"
@@ -489,9 +489,7 @@
 
 MACHINE_START(TAVOREVB, "PXA930 Evaluation Board (aka TavorEVB)")
 	/* Maintainer: Eric Miao <eric.miao@marvell.com> */
-	.phys_io        = 0x40000000,
 	.boot_params    = 0xa0000100,
-	.io_pg_offst    = (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io         = pxa_map_io,
 	.init_irq       = pxa3xx_init_irq,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/tavorevb3.c b/arch/arm/mach-pxa/tavorevb3.c
new file mode 100644
index 0000000..dc30116
--- /dev/null
+++ b/arch/arm/mach-pxa/tavorevb3.c
@@ -0,0 +1,135 @@
+/*
+ *  linux/arch/arm/mach-pxa/tavorevb3.c
+ *
+ *  Support for the Marvell EVB3 Development Platform.
+ *
+ *  Copyright:  (C) Copyright 2008-2010 Marvell International Ltd.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  publishhed by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/mfd/88pm860x.h>
+
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+
+#include <mach/pxa930.h>
+
+#include <plat/i2c.h>
+
+#include "devices.h"
+#include "generic.h"
+
+#define TAVOREVB3_NR_IRQS	(IRQ_BOARD_START + 24)
+
+static mfp_cfg_t evb3_mfp_cfg[] __initdata = {
+	/* UART */
+	GPIO53_UART1_TXD,
+	GPIO54_UART1_RXD,
+
+	/* PMIC */
+	PMIC_INT_GPIO83,
+};
+
+#if defined(CONFIG_I2C_PXA) || defined(CONFIG_I2C_PXA_MODULE)
+static struct pm860x_touch_pdata evb3_touch = {
+	.gpadc_prebias	= 1,
+	.slot_cycle	= 1,
+	.tsi_prebias	= 6,
+	.pen_prebias	= 16,
+	.pen_prechg	= 2,
+	.res_x		= 300,
+};
+
+static struct pm860x_backlight_pdata evb3_backlight[] = {
+	{
+		.id	= PM8606_ID_BACKLIGHT,
+		.iset	= PM8606_WLED_CURRENT(24),
+		.flags	= PM8606_BACKLIGHT1,
+	},
+	{},
+};
+
+static struct pm860x_led_pdata evb3_led[] = {
+	{
+		.id	= PM8606_ID_LED,
+		.iset	= PM8606_LED_CURRENT(12),
+		.flags	= PM8606_LED1_RED,
+	}, {
+		.id	= PM8606_ID_LED,
+		.iset	= PM8606_LED_CURRENT(12),
+		.flags	= PM8606_LED1_GREEN,
+	}, {
+		.id	= PM8606_ID_LED,
+		.iset	= PM8606_LED_CURRENT(12),
+		.flags	= PM8606_LED1_BLUE,
+	}, {
+		.id	= PM8606_ID_LED,
+		.iset	= PM8606_LED_CURRENT(12),
+		.flags	= PM8606_LED2_RED,
+	}, {
+		.id	= PM8606_ID_LED,
+		.iset	= PM8606_LED_CURRENT(12),
+		.flags	= PM8606_LED2_GREEN,
+	}, {
+		.id	= PM8606_ID_LED,
+		.iset	= PM8606_LED_CURRENT(12),
+		.flags	= PM8606_LED2_BLUE,
+	},
+};
+
+static struct pm860x_platform_data evb3_pm8607_info = {
+	.touch				= &evb3_touch,
+	.backlight			= &evb3_backlight[0],
+	.led				= &evb3_led[0],
+	.companion_addr			= 0x10,
+	.irq_mode			= 0,
+	.irq_base			= IRQ_BOARD_START,
+
+	.i2c_port			= GI2C_PORT,
+};
+
+static struct i2c_board_info evb3_i2c_info[] = {
+	{
+		.type		= "88PM860x",
+		.addr		= 0x34,
+		.platform_data	= &evb3_pm8607_info,
+		.irq		= gpio_to_irq(mfp_to_gpio(MFP_PIN_GPIO83)),
+	},
+};
+
+static void __init evb3_init_i2c(void)
+{
+	pxa_set_i2c_info(NULL);
+	i2c_register_board_info(0, ARRAY_AND_SIZE(evb3_i2c_info));
+}
+#else
+static inline void evb3_init_i2c(void) {}
+#endif
+
+static void __init evb3_init(void)
+{
+	/* initialize MFP configurations */
+	pxa3xx_mfp_config(ARRAY_AND_SIZE(evb3_mfp_cfg));
+
+	pxa_set_ffuart_info(NULL);
+
+	evb3_init_i2c();
+}
+
+MACHINE_START(TAVOREVB3, "PXA950 Evaluation Board (aka TavorEVB3)")
+	.boot_params	= 0xa0000100,
+	.map_io         = pxa_map_io,
+	.nr_irqs	= TAVOREVB3_NR_IRQS,
+	.init_irq       = pxa3xx_init_irq,
+	.timer          = &pxa_timer,
+	.init_machine   = evb3_init,
+MACHINE_END
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 83cc3a1..0ee1df4 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -952,10 +952,9 @@
 }
 
 MACHINE_START(TOSA, "SHARP Tosa")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.fixup          = fixup_tosa,
 	.map_io         = pxa_map_io,
+	.nr_irqs	= TOSA_NR_IRQS,
 	.init_irq       = pxa25x_init_irq,
 	.init_machine   = tosa_init,
 	.timer          = &pxa_timer,
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index 0acff17..565d062 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -555,8 +555,6 @@
 
 MACHINE_START(TRIZEPS4, "Keith und Koep Trizeps IV module")
 	/* MAINTAINER("Jürgen Schindele") */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= TRIZEPS4_SDRAM_BASE + 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
@@ -566,8 +564,6 @@
 
 MACHINE_START(TRIZEPS4WL, "Keith und Koep Trizeps IV-WL module")
 	/* MAINTAINER("Jürgen Schindele") */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= TRIZEPS4_SDRAM_BASE + 0x100,
 	.init_machine	= trizeps4_init,
 	.map_io		= trizeps4_map_io,
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index e90114a..438fc9a 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -992,8 +992,6 @@
 
 MACHINE_START(VIPER, "Arcom/Eurotech VIPER SBC")
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= viper_map_io,
 	.init_irq	= viper_init_irq,
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index 37d6173..f45ac09 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -718,8 +718,6 @@
 }
 
 MACHINE_START(VPAC270, "Voipac PXA270")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index d3b4e3f..3260ce7 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -181,8 +181,6 @@
 }
 
 MACHINE_START(XCEP, "Iskratel XCEP")
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.boot_params	= 0xa0000100,
 	.init_machine	= xcep_init,
 	.map_io		= pxa_map_io,
diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c
index f0d0228..fefde98 100644
--- a/arch/arm/mach-pxa/z2.c
+++ b/arch/arm/mach-pxa/z2.c
@@ -37,7 +37,7 @@
 #include <mach/z2.h>
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <mach/pxa2xx_spi.h>
 
 #include <plat/i2c.h>
@@ -703,9 +703,7 @@
 }
 
 MACHINE_START(ZIPIT2, "Zipit Z2")
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0000100,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
 	.init_irq	= pxa27x_init_irq,
 	.timer		= &pxa_timer,
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 03b9cb9..dea46a2 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -900,10 +900,9 @@
 
 MACHINE_START(ARCOM_ZEUS, "Arcom/Eurotech ZEUS")
 	/* Maintainer: Marc Zyngier <maz@misterjones.org> */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= ((io_p2v(0x40000000) >> 18) & 0xfffc),
 	.boot_params	= 0xa0000100,
 	.map_io		= zeus_map_io,
+	.nr_irqs	= ZEUS_NR_IRQS,
 	.init_irq	= zeus_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= zeus_init,
diff --git a/arch/arm/mach-pxa/zylonite.c b/arch/arm/mach-pxa/zylonite.c
index c479cbe..f25fb62 100644
--- a/arch/arm/mach-pxa/zylonite.c
+++ b/arch/arm/mach-pxa/zylonite.c
@@ -30,7 +30,7 @@
 #include <mach/zylonite.h>
 #include <mach/mmc.h>
 #include <mach/ohci.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 #include <plat/pxa3xx_nand.h>
 
 #include "devices.h"
@@ -411,10 +411,9 @@
 }
 
 MACHINE_START(ZYLONITE, "PXA3xx Platform Development Kit (aka Zylonite)")
-	.phys_io	= 0x40000000,
 	.boot_params	= 0xa0000100,
-	.io_pg_offst	= (io_p2v(0x40000000) >> 18) & 0xfffc,
 	.map_io		= pxa_map_io,
+	.nr_irqs	= ZYLONITE_NR_IRQS,
 	.init_irq	= pxa3xx_init_irq,
 	.timer		= &pxa_timer,
 	.init_machine	= zylonite_init,
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index 2fa38df..07c0815 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -259,6 +259,7 @@
 	.status		= realview_mmc_status,
 	.gpio_wp	= 17,
 	.gpio_cd	= 16,
+	.cd_invert	= true,
 };
 
 struct mmci_platform_data realview_mmc1_plat_data = {
@@ -266,6 +267,7 @@
 	.status		= realview_mmc_status,
 	.gpio_wp	= 19,
 	.gpio_cd	= 18,
+	.cd_invert	= true,
 };
 
 /*
diff --git a/arch/arm/mach-realview/include/mach/debug-macro.S b/arch/arm/mach-realview/include/mach/debug-macro.S
index 8662228..90b687c 100644
--- a/arch/arm/mach-realview/include/mach/debug-macro.S
+++ b/arch/arm/mach-realview/include/mach/debug-macro.S
@@ -33,12 +33,10 @@
 #error "Unknown RealView platform"
 #endif
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx,      #0x10000000
-		movne	\rx,      #0xfb000000	@ virtual base
-		orr	\rx, \rx, #DEBUG_LL_UART_OFFSET
+		.macro	addruart, rp, rv
+		mov	\rp, #DEBUG_LL_UART_OFFSET
+		orr	\rv, \rp, #0xfb000000	@ virtual base
+		orr	\rp, \rp, #0x10000000	@ physical base
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-realview/include/mach/smp.h b/arch/arm/mach-realview/include/mach/smp.h
index dd53892..d3cd265 100644
--- a/arch/arm/mach-realview/include/mach/smp.h
+++ b/arch/arm/mach-realview/include/mach/smp.h
@@ -1,16 +1,8 @@
 #ifndef ASMARM_ARCH_SMP_H
 #define ASMARM_ARCH_SMP_H
 
-
 #include <asm/hardware/gic.h>
-
-#define hard_smp_processor_id()			\
-	({						\
-		unsigned int cpunum;			\
-		__asm__("mrc p15, 0, %0, c0, c0, 5"	\
-			: "=r" (cpunum));		\
-		cpunum &= 0x0F;				\
-	})
+#include <asm/smp_mpidr.h>
 
 /*
  * We use IRQ1 as the IPI
diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c
index 991c1f8..f269710 100644
--- a/arch/arm/mach-realview/realview_eb.c
+++ b/arch/arm/mach-realview/realview_eb.c
@@ -486,8 +486,6 @@
 
 MACHINE_START(REALVIEW_EB, "ARM-RealView EB")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_EB_UART0_BASE & SECTION_MASK,
-	.io_pg_offst	= (IO_ADDRESS(REALVIEW_EB_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_fixup,
 	.map_io		= realview_eb_map_io,
diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c
index d2be12e..a412561 100644
--- a/arch/arm/mach-realview/realview_pb1176.c
+++ b/arch/arm/mach-realview/realview_pb1176.c
@@ -378,8 +378,6 @@
 
 MACHINE_START(REALVIEW_PB1176, "ARM-RealView PB1176")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_PB1176_UART0_BASE & SECTION_MASK,
-	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PB1176_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_pb1176_fixup,
 	.map_io		= realview_pb1176_map_io,
diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c
index d591bc0..117b95b 100644
--- a/arch/arm/mach-realview/realview_pb11mp.c
+++ b/arch/arm/mach-realview/realview_pb11mp.c
@@ -381,8 +381,6 @@
 
 MACHINE_START(REALVIEW_PB11MP, "ARM-RealView PB11MPCore")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_PB11MP_UART0_BASE & SECTION_MASK,
-	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PB11MP_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_fixup,
 	.map_io		= realview_pb11mp_map_io,
diff --git a/arch/arm/mach-realview/realview_pba8.c b/arch/arm/mach-realview/realview_pba8.c
index 6c37621..929b8dc 100644
--- a/arch/arm/mach-realview/realview_pba8.c
+++ b/arch/arm/mach-realview/realview_pba8.c
@@ -331,8 +331,6 @@
 
 MACHINE_START(REALVIEW_PBA8, "ARM-RealView PB-A8")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_PBA8_UART0_BASE & SECTION_MASK,
-	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PBA8_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_fixup,
 	.map_io		= realview_pba8_map_io,
diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c
index 9428eff..b9f9e20 100644
--- a/arch/arm/mach-realview/realview_pbx.c
+++ b/arch/arm/mach-realview/realview_pbx.c
@@ -417,8 +417,6 @@
 
 MACHINE_START(REALVIEW_PBX, "ARM-RealView PBX")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_PBX_UART0_BASE & SECTION_MASK,
-	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PBX_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_pbx_fixup,
 	.map_io		= realview_pbx_map_io,
diff --git a/arch/arm/mach-rpc/include/mach/debug-macro.S b/arch/arm/mach-rpc/include/mach/debug-macro.S
index 6fc8d66..85effff 100644
--- a/arch/arm/mach-rpc/include/mach/debug-macro.S
+++ b/arch/arm/mach-rpc/include/mach/debug-macro.S
@@ -11,13 +11,11 @@
  *
 */
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x03000000
-		movne	\rx, #0xe0000000
-		orr	\rx, \rx, #0x00010000
-		orr	\rx, \rx, #0x00000fe0
+		.macro	addruart, rp, rv
+		mov	\rp, #0x00010000
+		orr	\rp, \rp, #0x00000fe0
+		orr	\rv, \rp, #0xe0000000	@ virtual
+		orr	\rp, \rp, #0x03000000	@ physical
 		.endm
 
 #define UART_SHIFT	2
diff --git a/arch/arm/mach-rpc/include/mach/vmalloc.h b/arch/arm/mach-rpc/include/mach/vmalloc.h
index 9a96fd6..3bcd86f 100644
--- a/arch/arm/mach-rpc/include/mach/vmalloc.h
+++ b/arch/arm/mach-rpc/include/mach/vmalloc.h
@@ -7,4 +7,4 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#define VMALLOC_END       (PAGE_OFFSET + 0x1c000000)
+#define VMALLOC_END       0xdc000000
diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c
index c7fc01e..580b3c7 100644
--- a/arch/arm/mach-rpc/riscpc.c
+++ b/arch/arm/mach-rpc/riscpc.c
@@ -218,8 +218,6 @@
 
 MACHINE_START(RISCPC, "Acorn-RiscPC")
 	/* Maintainer: Russell King */
-	.phys_io	= 0x03000000,
-	.io_pg_offst	= ((0xe0000000) >> 18) & 0xfffc,
 	.boot_params	= 0x10000100,
 	.reserve_lp0	= 1,
 	.reserve_lp1	= 1,
diff --git a/arch/arm/mach-s3c2410/include/mach/debug-macro.S b/arch/arm/mach-s3c2410/include/mach/debug-macro.S
index 0eef78b..5882dea 100644
--- a/arch/arm/mach-s3c2410/include/mach/debug-macro.S
+++ b/arch/arm/mach-s3c2410/include/mach/debug-macro.S
@@ -19,13 +19,12 @@
 #define S3C2410_UART1_OFF (0x4000)
 #define SHIFT_2440TXF (14-9)
 
-	.macro addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, = S3C24XX_PA_UART
-		ldrne	\rx, = S3C24XX_VA_UART
+	.macro addruart, rp, rv
+		ldr	\rp, = S3C24XX_PA_UART
+		ldr	\rv, = S3C24XX_VA_UART
 #if CONFIG_DEBUG_S3C_UART != 0
-		add	\rx, \rx, #(S3C2410_UART1_OFF * CONFIG_DEBUG_S3C_UART)
+		add	\rp, \rp, #(S3C2410_UART1_OFF * CONFIG_DEBUG_S3C_UART)
+		add	\rv, \rv, #(S3C2410_UART1_OFF * CONFIG_DEBUG_S3C_UART)
 #endif
 	.endm
 
diff --git a/arch/arm/mach-s3c2410/mach-amlm5900.c b/arch/arm/mach-s3c2410/mach-amlm5900.c
index 34fc05a..44440cb 100644
--- a/arch/arm/mach-s3c2410/mach-amlm5900.c
+++ b/arch/arm/mach-s3c2410/mach-amlm5900.c
@@ -241,8 +241,6 @@
 }
 
 MACHINE_START(AML_M5900, "AML_M5900")
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= amlm5900_map_io,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2410/mach-bast.c b/arch/arm/mach-s3c2410/mach-bast.c
index c1f90f6..2970ea9 100644
--- a/arch/arm/mach-s3c2410/mach-bast.c
+++ b/arch/arm/mach-s3c2410/mach-bast.c
@@ -664,8 +664,6 @@
 
 MACHINE_START(BAST, "Simtec-BAST")
 	/* Maintainer: Ben Dooks <ben@simtec.co.uk> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= bast_map_io,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2410/mach-h1940.c b/arch/arm/mach-s3c2410/mach-h1940.c
index 3ba3bab..98c5c9e 100644
--- a/arch/arm/mach-s3c2410/mach-h1940.c
+++ b/arch/arm/mach-s3c2410/mach-h1940.c
@@ -350,8 +350,6 @@
 
 MACHINE_START(H1940, "IPAQ-H1940")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= h1940_map_io,
 	.reserve	= h1940_reserve,
diff --git a/arch/arm/mach-s3c2410/mach-n30.c b/arch/arm/mach-s3c2410/mach-n30.c
index 41f299d..271b9aa 100644
--- a/arch/arm/mach-s3c2410/mach-n30.c
+++ b/arch/arm/mach-s3c2410/mach-n30.c
@@ -605,8 +605,6 @@
 	/* Maintainer: Christer Weinigel <christer@weinigel.se>,
 				Ben Dooks <ben-linux@fluff.org>
 	*/
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.timer		= &s3c24xx_timer,
 	.init_machine	= n30_init,
@@ -617,8 +615,6 @@
 MACHINE_START(N35, "Acer-N35")
 	/* Maintainer: Christer Weinigel <christer@weinigel.se>
 	*/
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.timer		= &s3c24xx_timer,
 	.init_machine	= n30_init,
diff --git a/arch/arm/mach-s3c2410/mach-otom.c b/arch/arm/mach-s3c2410/mach-otom.c
index d8c7f2e..0aa16cd 100644
--- a/arch/arm/mach-s3c2410/mach-otom.c
+++ b/arch/arm/mach-s3c2410/mach-otom.c
@@ -116,8 +116,6 @@
 
 MACHINE_START(OTOM, "Nex Vision - Otom 1.1")
 	/* Maintainer: Guillaume GOURAT <guillaume.gourat@nexvision.tv> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= otom11_map_io,
 	.init_machine	= otom11_init,
diff --git a/arch/arm/mach-s3c2410/mach-qt2410.c b/arch/arm/mach-s3c2410/mach-qt2410.c
index d0e87b6..e8f49fe 100644
--- a/arch/arm/mach-s3c2410/mach-qt2410.c
+++ b/arch/arm/mach-s3c2410/mach-qt2410.c
@@ -362,8 +362,6 @@
 }
 
 MACHINE_START(QT2410, "QT2410")
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= qt2410_map_io,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2410/mach-smdk2410.c b/arch/arm/mach-s3c2410/mach-smdk2410.c
index 4522230..e17f033 100644
--- a/arch/arm/mach-s3c2410/mach-smdk2410.c
+++ b/arch/arm/mach-s3c2410/mach-smdk2410.c
@@ -111,8 +111,6 @@
 MACHINE_START(SMDK2410, "SMDK2410") /* @TODO: request a new identifier and switch
 				    * to SMDK2410 */
 	/* Maintainer: Jonas Dietsche */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= smdk2410_map_io,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2410/mach-tct_hammer.c b/arch/arm/mach-s3c2410/mach-tct_hammer.c
index 929164a..a15d062 100644
--- a/arch/arm/mach-s3c2410/mach-tct_hammer.c
+++ b/arch/arm/mach-s3c2410/mach-tct_hammer.c
@@ -152,8 +152,6 @@
 }
 
 MACHINE_START(TCT_HAMMER, "TCT_HAMMER")
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= tct_hammer_map_io,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2410/mach-vr1000.c b/arch/arm/mach-s3c2410/mach-vr1000.c
index d540d79..6ccce5a 100644
--- a/arch/arm/mach-s3c2410/mach-vr1000.c
+++ b/arch/arm/mach-s3c2410/mach-vr1000.c
@@ -400,8 +400,6 @@
 
 MACHINE_START(VR1000, "Thorcom-VR1000")
 	/* Maintainer: Ben Dooks <ben@simtec.co.uk> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= vr1000_map_io,
 	.init_machine	= vr1000_init,
diff --git a/arch/arm/mach-s3c2412/mach-jive.c b/arch/arm/mach-s3c2412/mach-jive.c
index 478f4b4..923e01b 100644
--- a/arch/arm/mach-s3c2412/mach-jive.c
+++ b/arch/arm/mach-s3c2412/mach-jive.c
@@ -675,8 +675,6 @@
 
 MACHINE_START(JIVE, "JIVE")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2412/mach-smdk2413.c b/arch/arm/mach-s3c2412/mach-smdk2413.c
index 054c9f9..8e5758b 100644
--- a/arch/arm/mach-s3c2412/mach-smdk2413.c
+++ b/arch/arm/mach-s3c2412/mach-smdk2413.c
@@ -150,8 +150,6 @@
 
 MACHINE_START(S3C2413, "S3C2413")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 
 	.fixup		= smdk2413_fixup,
@@ -163,8 +161,6 @@
 
 MACHINE_START(SMDK2412, "SMDK2412")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 
 	.fixup		= smdk2413_fixup,
@@ -176,8 +172,6 @@
 
 MACHINE_START(SMDK2413, "SMDK2413")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 
 	.fixup		= smdk2413_fixup,
diff --git a/arch/arm/mach-s3c2412/mach-vstms.c b/arch/arm/mach-s3c2412/mach-vstms.c
index f291ac2..83544eb 100644
--- a/arch/arm/mach-s3c2412/mach-vstms.c
+++ b/arch/arm/mach-s3c2412/mach-vstms.c
@@ -156,8 +156,6 @@
 }
 
 MACHINE_START(VSTMS, "VSTMS")
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 
 	.fixup		= vstms_fixup,
diff --git a/arch/arm/mach-s3c2416/mach-smdk2416.c b/arch/arm/mach-s3c2416/mach-smdk2416.c
index 5fc3f67..7fc3664 100644
--- a/arch/arm/mach-s3c2416/mach-smdk2416.c
+++ b/arch/arm/mach-s3c2416/mach-smdk2416.c
@@ -195,8 +195,6 @@
 
 MACHINE_START(SMDK2416, "SMDK2416")
 	/* Maintainer: Yauhen Kharuzhy <jekhor@gmail.com> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-anubis.c b/arch/arm/mach-s3c2440/mach-anubis.c
index b73f78a..d708678 100644
--- a/arch/arm/mach-s3c2440/mach-anubis.c
+++ b/arch/arm/mach-s3c2440/mach-anubis.c
@@ -498,8 +498,6 @@
 
 MACHINE_START(ANUBIS, "Simtec-Anubis")
 	/* Maintainer: Ben Dooks <ben@simtec.co.uk> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= anubis_map_io,
 	.init_machine	= anubis_init,
diff --git a/arch/arm/mach-s3c2440/mach-at2440evb.c b/arch/arm/mach-s3c2440/mach-at2440evb.c
index 8472579..e3810c8 100644
--- a/arch/arm/mach-s3c2440/mach-at2440evb.c
+++ b/arch/arm/mach-s3c2440/mach-at2440evb.c
@@ -233,8 +233,6 @@
 
 
 MACHINE_START(AT2440EVB, "AT2440EVB")
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= at2440evb_map_io,
 	.init_machine	= at2440evb_init,
diff --git a/arch/arm/mach-s3c2440/mach-gta02.c b/arch/arm/mach-s3c2440/mach-gta02.c
index deaabe8..9f2c14e 100644
--- a/arch/arm/mach-s3c2440/mach-gta02.c
+++ b/arch/arm/mach-s3c2440/mach-gta02.c
@@ -572,8 +572,6 @@
 
 MACHINE_START(NEO1973_GTA02, "GTA02")
 	/* Maintainer: Nelson Castillo <arhuaco@freaks-unidos.net> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= gta02_map_io,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-mini2440.c b/arch/arm/mach-s3c2440/mach-mini2440.c
index a76bcda..f62bb4c 100644
--- a/arch/arm/mach-s3c2440/mach-mini2440.c
+++ b/arch/arm/mach-s3c2440/mach-mini2440.c
@@ -691,8 +691,6 @@
 
 MACHINE_START(MINI2440, "MINI2440")
 	/* Maintainer: Michel Pollet <buserror@gmail.com> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= mini2440_map_io,
 	.init_machine	= mini2440_init,
diff --git a/arch/arm/mach-s3c2440/mach-nexcoder.c b/arch/arm/mach-s3c2440/mach-nexcoder.c
index 3ff62de..37dd306 100644
--- a/arch/arm/mach-s3c2440/mach-nexcoder.c
+++ b/arch/arm/mach-s3c2440/mach-nexcoder.c
@@ -151,8 +151,6 @@
 
 MACHINE_START(NEXCODER_2440, "NexVision - Nexcoder 2440")
 	/* Maintainer: Guillaume GOURAT <guillaume.gourat@nexvision.tv> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= nexcoder_map_io,
 	.init_machine	= nexcoder_init,
diff --git a/arch/arm/mach-s3c2440/mach-osiris.c b/arch/arm/mach-s3c2440/mach-osiris.c
index 319458d..14dc678 100644
--- a/arch/arm/mach-s3c2440/mach-osiris.c
+++ b/arch/arm/mach-s3c2440/mach-osiris.c
@@ -455,8 +455,6 @@
 
 MACHINE_START(OSIRIS, "Simtec-OSIRIS")
 	/* Maintainer: Ben Dooks <ben@simtec.co.uk> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= osiris_map_io,
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2440/mach-rx1950.c b/arch/arm/mach-s3c2440/mach-rx1950.c
index 142d1f9..32019bd 100644
--- a/arch/arm/mach-s3c2440/mach-rx1950.c
+++ b/arch/arm/mach-s3c2440/mach-rx1950.c
@@ -580,8 +580,6 @@
 
 MACHINE_START(RX1950, "HP iPAQ RX1950")
     /* Maintainers: Vasily Khoruzhick */
-    .phys_io = S3C2410_PA_UART,
-	.io_pg_offst = (((u32) S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params = S3C2410_SDRAM_PA + 0x100,
 	.map_io = rx1950_map_io,
 	.reserve	= rx1950_reserve,
diff --git a/arch/arm/mach-s3c2440/mach-rx3715.c b/arch/arm/mach-s3c2440/mach-rx3715.c
index 6bb44f7..1472b1a 100644
--- a/arch/arm/mach-s3c2440/mach-rx3715.c
+++ b/arch/arm/mach-s3c2440/mach-rx3715.c
@@ -218,8 +218,6 @@
 
 MACHINE_START(RX3715, "IPAQ-RX3715")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 	.map_io		= rx3715_map_io,
 	.reserve	= rx3715_reserve,
diff --git a/arch/arm/mach-s3c2440/mach-smdk2440.c b/arch/arm/mach-s3c2440/mach-smdk2440.c
index df83276..eedfe0f 100644
--- a/arch/arm/mach-s3c2440/mach-smdk2440.c
+++ b/arch/arm/mach-s3c2440/mach-smdk2440.c
@@ -175,8 +175,6 @@
 
 MACHINE_START(S3C2440, "SMDK2440")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c2443/mach-smdk2443.c b/arch/arm/mach-s3c2443/mach-smdk2443.c
index 4c863d3..4337f0a 100644
--- a/arch/arm/mach-s3c2443/mach-smdk2443.c
+++ b/arch/arm/mach-s3c2443/mach-smdk2443.c
@@ -132,8 +132,6 @@
 
 MACHINE_START(SMDK2443, "SMDK2443")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C2410_PA_UART,
-	.io_pg_offst	= (((u32)S3C24XX_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C2410_SDRAM_PA + 0x100,
 
 	.init_irq	= s3c24xx_init_irq,
diff --git a/arch/arm/mach-s3c24a0/include/mach/debug-macro.S b/arch/arm/mach-s3c24a0/include/mach/debug-macro.S
index 239476b..0c5a738 100644
--- a/arch/arm/mach-s3c24a0/include/mach/debug-macro.S
+++ b/arch/arm/mach-s3c24a0/include/mach/debug-macro.S
@@ -10,13 +10,12 @@
 #include <mach/map.h>
 #include <plat/regs-serial.h>
 
-	.macro addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, = S3C24XX_PA_UART
-		ldrne	\rx, = S3C24XX_VA_UART
+	.macro addruart, rp, rv
+		ldr	\rp, = S3C24XX_PA_UART
+		ldr	\rv, = S3C24XX_VA_UART
 #if CONFIG_DEBUG_S3C_UART != 0
-		add	\rx, \rx, #(S3C2410_UART1_OFF * CONFIG_DEBUG_S3C_UART)
+		add	\rp, \rp, #(S3C2410_UART1_OFF * CONFIG_DEBUG_S3C_UART)
+		add	\rv, \rv, #(S3C2410_UART1_OFF * CONFIG_DEBUG_S3C_UART)
 #endif
 	.endm
 
diff --git a/arch/arm/mach-s3c64xx/include/mach/debug-macro.S b/arch/arm/mach-s3c64xx/include/mach/debug-macro.S
index f9ab5d2..a29e705 100644
--- a/arch/arm/mach-s3c64xx/include/mach/debug-macro.S
+++ b/arch/arm/mach-s3c64xx/include/mach/debug-macro.S
@@ -21,13 +21,12 @@
 	 * aligned and add in the offset when we load the value here.
 	 */
 
-	.macro addruart, rx, rtmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, = S3C_PA_UART
-		ldrne	\rx, = (S3C_VA_UART + S3C_PA_UART & 0xfffff)
+	.macro addruart, rp, rv
+		ldr	\rp, = S3C_PA_UART
+		ldr	\rv, = (S3C_VA_UART + S3C_PA_UART & 0xfffff)
 #if CONFIG_DEBUG_S3C_UART != 0
-		add	\rx, \rx, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rp, \rp, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rv, \rv, #(0x400 * CONFIG_DEBUG_S3C_UART)
 #endif
 	.endm
 
diff --git a/arch/arm/mach-s3c64xx/mach-anw6410.c b/arch/arm/mach-s3c64xx/mach-anw6410.c
index 742dc87..a53cf14 100644
--- a/arch/arm/mach-s3c64xx/mach-anw6410.c
+++ b/arch/arm/mach-s3c64xx/mach-anw6410.c
@@ -233,8 +233,6 @@
 
 MACHINE_START(ANW6410, "A&W6410")
 	/* Maintainer: Kwangwoo Lee <kwangwoo.lee@gmail.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
 
 	.init_irq	= s3c6410_init_irq,
diff --git a/arch/arm/mach-s3c64xx/mach-hmt.c b/arch/arm/mach-s3c64xx/mach-hmt.c
index fba9022..b263958 100644
--- a/arch/arm/mach-s3c64xx/mach-hmt.c
+++ b/arch/arm/mach-s3c64xx/mach-hmt.c
@@ -265,8 +265,6 @@
 
 MACHINE_START(HMT, "Airgoo-HMT")
 	/* Maintainer: Peter Korsgaard <jacmet@sunsite.dk> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= hmt_map_io,
diff --git a/arch/arm/mach-s3c64xx/mach-ncp.c b/arch/arm/mach-s3c64xx/mach-ncp.c
index bf65747..c498649 100644
--- a/arch/arm/mach-s3c64xx/mach-ncp.c
+++ b/arch/arm/mach-s3c64xx/mach-ncp.c
@@ -97,8 +97,6 @@
 
 MACHINE_START(NCP, "NCP")
 	/* Maintainer: Samsung Electronics */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= ncp_map_io,
diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c
index e130379..4b4475d 100644
--- a/arch/arm/mach-s3c64xx/mach-real6410.c
+++ b/arch/arm/mach-s3c64xx/mach-real6410.c
@@ -141,8 +141,6 @@
 
 MACHINE_START(REAL6410, "REAL6410")
 	/* Maintainer: Darius Augulis <augulis.darius@gmail.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
 
 	.init_irq	= s3c6410_init_irq,
diff --git a/arch/arm/mach-s3c64xx/mach-smartq.c b/arch/arm/mach-s3c64xx/mach-smartq.c
index 3a9639b..cb1ebeb 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq.c
@@ -136,7 +136,7 @@
 	.dev.platform_data	= &smartq_usb_otg_vbus_pdata,
 };
 
-static int __init smartq_bl_init(struct device *dev)
+static int smartq_bl_init(struct device *dev)
 {
     s3c_gpio_cfgpin(S3C64XX_GPF(15), S3C_GPIO_SFN(2));
 
diff --git a/arch/arm/mach-s3c64xx/mach-smartq5.c b/arch/arm/mach-s3c64xx/mach-smartq5.c
index a4d59b0..3a3e5ac 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq5.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq5.c
@@ -32,7 +32,7 @@
 
 #include "mach-smartq.h"
 
-static struct gpio_led smartq5_leds[] __initdata = {
+static struct gpio_led smartq5_leds[] = {
 	{
 		.name			= "smartq5:green",
 		.active_low		= 1,
@@ -146,8 +146,6 @@
 
 MACHINE_START(SMARTQ5, "SmartQ 5")
 	/* Maintainer: Maurus Cuelenaere <mcuelenaere AT gmail DOT com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= smartq_map_io,
diff --git a/arch/arm/mach-s3c64xx/mach-smartq7.c b/arch/arm/mach-s3c64xx/mach-smartq7.c
index e50a7d7..e653758 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq7.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq7.c
@@ -32,7 +32,7 @@
 
 #include "mach-smartq.h"
 
-static struct gpio_led smartq7_leds[] __initdata = {
+static struct gpio_led smartq7_leds[] = {
 	{
 		.name			= "smartq7:red",
 		.active_low		= 1,
@@ -162,8 +162,6 @@
 
 MACHINE_START(SMARTQ7, "SmartQ 7")
 	/* Maintainer: Maurus Cuelenaere <mcuelenaere AT gmail DOT com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= smartq_map_io,
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6400.c b/arch/arm/mach-s3c64xx/mach-smdk6400.c
index 5991667..3cca642 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6400.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6400.c
@@ -85,8 +85,6 @@
 
 MACHINE_START(SMDK6400, "SMDK6400")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
 
 	.init_irq	= s3c6400_init_irq,
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index d498219..ec8865c 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -704,8 +704,6 @@
 
 MACHINE_START(SMDK6410, "SMDK6410")
 	/* Maintainer: Ben Dooks <ben-linux@fluff.org> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S3C64XX_PA_SDRAM + 0x100,
 
 	.init_irq	= s3c6410_init_irq,
diff --git a/arch/arm/mach-s5p6440/Kconfig b/arch/arm/mach-s5p6440/Kconfig
deleted file mode 100644
index 6a4af7f..0000000
--- a/arch/arm/mach-s5p6440/Kconfig
+++ /dev/null
@@ -1,33 +0,0 @@
-# arch/arm/mach-s5p6440/Kconfig
-#
-# Copyright (c) 2009 Samsung Electronics Co., Ltd.
-#		http://www.samsung.com/
-#
-# Licensed under GPLv2
-
-if ARCH_S5P6440
-
-config CPU_S5P6440
-	bool
-	select S3C_PL330_DMA
-	help
-	  Enable S5P6440 CPU support
-
-config S5P6440_SETUP_I2C1
-	bool
-	help
-	  Common setup code for i2c bus 1.
-
-config MACH_SMDK6440
-	bool "SMDK6440"
-	select CPU_S5P6440
-	select S3C_DEV_I2C1
-	select S3C_DEV_RTC
-	select S3C_DEV_WDT
-	select SAMSUNG_DEV_ADC
-	select SAMSUNG_DEV_TS
-	select S5P6440_SETUP_I2C1
-	help
-	  Machine support for the Samsung SMDK6440
-
-endif
diff --git a/arch/arm/mach-s5p6440/Makefile b/arch/arm/mach-s5p6440/Makefile
deleted file mode 100644
index c3fe4d3..0000000
--- a/arch/arm/mach-s5p6440/Makefile
+++ /dev/null
@@ -1,25 +0,0 @@
-# arch/arm/mach-s5p6440/Makefile
-#
-# Copyright (c) 2009 Samsung Electronics Co., Ltd.
-# 		http://www.samsung.com/
-#
-# Licensed under GPLv2
-
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
-# Core support for S5P6440 system
-
-obj-$(CONFIG_CPU_S5P6440)	+= cpu.o init.o clock.o gpio.o dma.o
-obj-$(CONFIG_CPU_S5P6440)	+= setup-i2c0.o
-
-# machine support
-
-obj-$(CONFIG_MACH_SMDK6440)	+= mach-smdk6440.o
-
-# device support
-obj-y				+= dev-audio.o
-obj-$(CONFIG_S3C64XX_DEV_SPI)	+= dev-spi.o
-obj-$(CONFIG_S5P6440_SETUP_I2C1)	+= setup-i2c1.o
diff --git a/arch/arm/mach-s5p6440/clock.c b/arch/arm/mach-s5p6440/clock.c
deleted file mode 100644
index ca6e48d..0000000
--- a/arch/arm/mach-s5p6440/clock.c
+++ /dev/null
@@ -1,846 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/clock.c
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6440 - Clock support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/sysdev.h>
-#include <linux/io.h>
-
-#include <mach/hardware.h>
-#include <mach/map.h>
-
-#include <plat/cpu-freq.h>
-#include <mach/regs-clock.h>
-#include <plat/clock.h>
-#include <plat/cpu.h>
-#include <plat/clock-clksrc.h>
-#include <plat/s5p-clock.h>
-#include <plat/pll.h>
-#include <plat/s5p6440.h>
-
-/* APLL Mux output clock */
-static struct clksrc_clk clk_mout_apll = {
-	.clk    = {
-		.name           = "mout_apll",
-		.id             = -1,
-	},
-	.sources        = &clk_src_apll,
-	.reg_src        = { .reg = S5P_CLK_SRC0, .shift = 0, .size = 1 },
-};
-
-static int s5p6440_epll_enable(struct clk *clk, int enable)
-{
-	unsigned int ctrlbit = clk->ctrlbit;
-	unsigned int epll_con = __raw_readl(S5P_EPLL_CON) & ~ctrlbit;
-
-	if (enable)
-		__raw_writel(epll_con | ctrlbit, S5P_EPLL_CON);
-	else
-		__raw_writel(epll_con, S5P_EPLL_CON);
-
-	return 0;
-}
-
-static unsigned long s5p6440_epll_get_rate(struct clk *clk)
-{
-	return clk->rate;
-}
-
-static u32 epll_div[][5] = {
-	{ 36000000,	0,	48, 1, 4 },
-	{ 48000000,	0,	32, 1, 3 },
-	{ 60000000,	0,	40, 1, 3 },
-	{ 72000000,	0,	48, 1, 3 },
-	{ 84000000,	0,	28, 1, 2 },
-	{ 96000000,	0,	32, 1, 2 },
-	{ 32768000,	45264,	43, 1, 4 },
-	{ 45158000,	6903,	30, 1, 3 },
-	{ 49152000,	50332,	32, 1, 3 },
-	{ 67738000,	10398,	45, 1, 3 },
-	{ 73728000,	9961,	49, 1, 3 }
-};
-
-static int s5p6440_epll_set_rate(struct clk *clk, unsigned long rate)
-{
-	unsigned int epll_con, epll_con_k;
-	unsigned int i;
-
-	if (clk->rate == rate)	/* Return if nothing changed */
-		return 0;
-
-	epll_con = __raw_readl(S5P_EPLL_CON);
-	epll_con_k = __raw_readl(S5P_EPLL_CON_K);
-
-	epll_con_k &= ~(PLL90XX_KDIV_MASK);
-	epll_con &= ~(PLL90XX_MDIV_MASK | PLL90XX_PDIV_MASK | PLL90XX_SDIV_MASK);
-
-	for (i = 0; i < ARRAY_SIZE(epll_div); i++) {
-		 if (epll_div[i][0] == rate) {
-			epll_con_k |= (epll_div[i][1] << PLL90XX_KDIV_SHIFT);
-			epll_con |= (epll_div[i][2] << PLL90XX_MDIV_SHIFT) |
-				    (epll_div[i][3] << PLL90XX_PDIV_SHIFT) |
-				    (epll_div[i][4] << PLL90XX_SDIV_SHIFT);
-			break;
-		}
-	}
-
-	if (i == ARRAY_SIZE(epll_div)) {
-		printk(KERN_ERR "%s: Invalid Clock EPLL Frequency\n", __func__);
-		return -EINVAL;
-	}
-
-	__raw_writel(epll_con, S5P_EPLL_CON);
-	__raw_writel(epll_con_k, S5P_EPLL_CON_K);
-
-	clk->rate = rate;
-
-	return 0;
-}
-
-static struct clk_ops s5p6440_epll_ops = {
-	.get_rate = s5p6440_epll_get_rate,
-	.set_rate = s5p6440_epll_set_rate,
-};
-
-static struct clksrc_clk clk_mout_epll = {
-	.clk    = {
-		.name           = "mout_epll",
-		.id             = -1,
-	},
-	.sources        = &clk_src_epll,
-	.reg_src        = { .reg = S5P_CLK_SRC0, .shift = 2, .size = 1 },
-};
-
-static struct clksrc_clk clk_mout_mpll = {
-	.clk = {
-		.name           = "mout_mpll",
-		.id             = -1,
-	},
-	.sources        = &clk_src_mpll,
-	.reg_src        = { .reg = S5P_CLK_SRC0, .shift = 1, .size = 1 },
-};
-
-enum perf_level {
-	L0 = 532*1000,
-	L1 = 266*1000,
-	L2 = 133*1000,
-};
-
-static const u32 clock_table[][3] = {
-	/*{ARM_CLK, DIVarm, DIVhclk}*/
-	{L0 * 1000, (0 << ARM_DIV_RATIO_SHIFT), (3 << S5P_CLKDIV0_HCLK_SHIFT)},
-	{L1 * 1000, (1 << ARM_DIV_RATIO_SHIFT), (1 << S5P_CLKDIV0_HCLK_SHIFT)},
-	{L2 * 1000, (3 << ARM_DIV_RATIO_SHIFT), (0 << S5P_CLKDIV0_HCLK_SHIFT)},
-};
-
-static unsigned long s5p6440_armclk_get_rate(struct clk *clk)
-{
-	unsigned long rate = clk_get_rate(clk->parent);
-	u32 clkdiv;
-
-	/* divisor mask starts at bit0, so no need to shift */
-	clkdiv = __raw_readl(ARM_CLK_DIV) & ARM_DIV_MASK;
-
-	return rate / (clkdiv + 1);
-}
-
-static unsigned long s5p6440_armclk_round_rate(struct clk *clk,
-						unsigned long rate)
-{
-	u32 iter;
-
-	for (iter = 1 ; iter < ARRAY_SIZE(clock_table) ; iter++) {
-		if (rate > clock_table[iter][0])
-			return clock_table[iter-1][0];
-	}
-
-	return clock_table[ARRAY_SIZE(clock_table) - 1][0];
-}
-
-static int s5p6440_armclk_set_rate(struct clk *clk, unsigned long rate)
-{
-	u32 round_tmp;
-	u32 iter;
-	u32 clk_div0_tmp;
-	u32 cur_rate = clk->ops->get_rate(clk);
-	unsigned long flags;
-
-	round_tmp = clk->ops->round_rate(clk, rate);
-	if (round_tmp == cur_rate)
-		return 0;
-
-
-	for (iter = 0 ; iter < ARRAY_SIZE(clock_table) ; iter++) {
-		if (round_tmp == clock_table[iter][0])
-			break;
-	}
-
-	if (iter >= ARRAY_SIZE(clock_table))
-		iter = ARRAY_SIZE(clock_table) - 1;
-
-	local_irq_save(flags);
-	if (cur_rate > round_tmp) {
-		/* Frequency Down */
-		clk_div0_tmp = __raw_readl(ARM_CLK_DIV) & ~(ARM_DIV_MASK);
-		clk_div0_tmp |= clock_table[iter][1];
-		__raw_writel(clk_div0_tmp, ARM_CLK_DIV);
-
-		clk_div0_tmp = __raw_readl(ARM_CLK_DIV) &
-				~(S5P_CLKDIV0_HCLK_MASK);
-		clk_div0_tmp |= clock_table[iter][2];
-		__raw_writel(clk_div0_tmp, ARM_CLK_DIV);
-
-
-	} else {
-		/* Frequency Up */
-		clk_div0_tmp = __raw_readl(ARM_CLK_DIV) &
-				~(S5P_CLKDIV0_HCLK_MASK);
-		clk_div0_tmp |= clock_table[iter][2];
-		__raw_writel(clk_div0_tmp, ARM_CLK_DIV);
-
-		clk_div0_tmp = __raw_readl(ARM_CLK_DIV) & ~(ARM_DIV_MASK);
-		clk_div0_tmp |= clock_table[iter][1];
-		__raw_writel(clk_div0_tmp, ARM_CLK_DIV);
-		}
-	local_irq_restore(flags);
-
-	clk->rate = clock_table[iter][0];
-
-	return 0;
-}
-
-static struct clk_ops s5p6440_clkarm_ops = {
-	.get_rate	= s5p6440_armclk_get_rate,
-	.set_rate	= s5p6440_armclk_set_rate,
-	.round_rate	= s5p6440_armclk_round_rate,
-};
-
-static struct clksrc_clk clk_armclk = {
-	.clk	= {
-		.name	= "armclk",
-		.id	= 1,
-		.parent	= &clk_mout_apll.clk,
-		.ops	= &s5p6440_clkarm_ops,
-	},
-	.reg_div	= { .reg = S5P_CLK_DIV0, .shift = 0, .size = 4 },
-};
-
-static struct clksrc_clk clk_dout_mpll = {
-	.clk	= {
-		.name	= "dout_mpll",
-		.id	= -1,
-		.parent	= &clk_mout_mpll.clk,
-	},
-	.reg_div	= { .reg = S5P_CLK_DIV0, .shift = 4, .size = 1 },
-};
-
-static struct clksrc_clk clk_hclk = {
-	.clk	= {
-		.name	= "clk_hclk",
-		.id	= -1,
-		.parent	= &clk_armclk.clk,
-	},
-	.reg_div	= { .reg = S5P_CLK_DIV0, .shift = 8, .size = 4 },
-};
-
-static struct clksrc_clk clk_pclk = {
-	.clk	= {
-		.name	= "clk_pclk",
-		.id	= -1,
-		.parent	= &clk_hclk.clk,
-	},
-	.reg_div = { .reg = S5P_CLK_DIV0, .shift = 12, .size = 4 },
-};
-
-static struct clk *clkset_hclklow_list[] = {
-	&clk_mout_apll.clk,
-	&clk_mout_mpll.clk,
-};
-
-static struct clksrc_sources clkset_hclklow = {
-	.sources	= clkset_hclklow_list,
-	.nr_sources	= ARRAY_SIZE(clkset_hclklow_list),
-};
-
-static struct clksrc_clk clk_hclk_low = {
-	.clk = {
-		.name	= "hclk_low",
-		.id	= -1,
-	},
-	.sources	= &clkset_hclklow,
-	.reg_src	= { .reg = S5P_SYS_OTHERS, .shift = 6, .size = 1 },
-	.reg_div	= { .reg = S5P_CLK_DIV3, .shift = 8, .size = 4 },
-};
-
-static struct clksrc_clk clk_pclk_low = {
-	.clk	= {
-		.name	= "pclk_low",
-		.id	= -1,
-		.parent	= &clk_hclk_low.clk,
-	},
-	.reg_div = { .reg = S5P_CLK_DIV3, .shift = 12, .size = 4 },
-};
-
-int s5p6440_clk48m_ctrl(struct clk *clk, int enable)
-{
-	unsigned long flags;
-	u32 val;
-
-	/* can't rely on clock lock, this register has other usages */
-	local_irq_save(flags);
-
-	val = __raw_readl(S5P_OTHERS);
-	if (enable)
-		val |= S5P_OTHERS_USB_SIG_MASK;
-	else
-		val &= ~S5P_OTHERS_USB_SIG_MASK;
-
-	__raw_writel(val, S5P_OTHERS);
-
-	local_irq_restore(flags);
-
-	return 0;
-}
-
-static int s5p6440_pclk_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLK_GATE_PCLK, clk, enable);
-}
-
-static int s5p6440_hclk0_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLK_GATE_HCLK0, clk, enable);
-}
-
-static int s5p6440_hclk1_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLK_GATE_HCLK1, clk, enable);
-}
-
-static int s5p6440_sclk_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLK_GATE_SCLK0, clk, enable);
-}
-
-static int s5p6440_sclk1_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLK_GATE_SCLK1, clk, enable);
-}
-
-static int s5p6440_mem_ctrl(struct clk *clk, int enable)
-{
-	return s5p_gatectrl(S5P_CLK_GATE_MEM0, clk, enable);
-}
-
-/*
- * The following clocks will be disabled during clock initialization. It is
- * recommended to keep the following clocks disabled until the driver requests
- * for enabling the clock.
- */
-static struct clk init_clocks_disable[] = {
-	{
-		.name		= "nand",
-		.id		= -1,
-		.parent		= &clk_hclk.clk,
-		.enable		= s5p6440_mem_ctrl,
-		.ctrlbit	= S5P_CLKCON_MEM0_HCLK_NFCON,
-	}, {
-		.name		= "adc",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_TSADC,
-	}, {
-		.name		= "i2c",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_IIC0,
-	}, {
-		.name		= "i2s_v40",
-		.id		= 0,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_IIS2,
-	}, {
-		.name		= "spi",
-		.id		= 0,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_SPI0,
-	}, {
-		.name		= "spi",
-		.id		= 1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_SPI1,
-	}, {
-		.name		= "sclk_spi_48",
-		.id		= 0,
-		.parent		= &clk_48m,
-		.enable		= s5p6440_sclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_SCLK0_SPI0_48,
-	}, {
-		.name		= "sclk_spi_48",
-		.id		= 1,
-		.parent		= &clk_48m,
-		.enable		= s5p6440_sclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_SCLK0_SPI1_48,
-	}, {
-		.name		= "mmc_48m",
-		.id		= 0,
-		.parent		= &clk_48m,
-		.enable		= s5p6440_sclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_SCLK0_MMC0_48,
-	}, {
-		.name		= "mmc_48m",
-		.id		= 1,
-		.parent		= &clk_48m,
-		.enable		= s5p6440_sclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_SCLK0_MMC1_48,
-	}, {
-		.name		= "mmc_48m",
-		.id		= 2,
-		.parent		= &clk_48m,
-		.enable		= s5p6440_sclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_SCLK0_MMC2_48,
-	}, {
-		.name    	= "otg",
-		.id	   	= -1,
-		.parent		= &clk_hclk_low.clk,
-		.enable  	= s5p6440_hclk0_ctrl,
-		.ctrlbit 	= S5P_CLKCON_HCLK0_USB
-	}, {
-		.name    	= "post",
-		.id	   	= -1,
-		.parent		= &clk_hclk_low.clk,
-		.enable  	= s5p6440_hclk0_ctrl,
-		.ctrlbit 	= S5P_CLKCON_HCLK0_POST0
-	}, {
-		.name		= "lcd",
-		.id		= -1,
-		.parent		= &clk_hclk_low.clk,
-		.enable		= s5p6440_hclk1_ctrl,
-		.ctrlbit	= S5P_CLKCON_HCLK1_DISPCON,
-	}, {
-		.name		= "hsmmc",
-		.id		= 0,
-		.parent		= &clk_hclk_low.clk,
-		.enable		= s5p6440_hclk0_ctrl,
-		.ctrlbit	= S5P_CLKCON_HCLK0_HSMMC0,
-	}, {
-		.name		= "hsmmc",
-		.id		= 1,
-		.parent		= &clk_hclk_low.clk,
-		.enable		= s5p6440_hclk0_ctrl,
-		.ctrlbit	= S5P_CLKCON_HCLK0_HSMMC1,
-	}, {
-		.name		= "hsmmc",
-		.id		= 2,
-		.parent		= &clk_hclk_low.clk,
-		.enable		= s5p6440_hclk0_ctrl,
-		.ctrlbit	= S5P_CLKCON_HCLK0_HSMMC2,
-	}, {
-		.name		= "rtc",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_RTC,
-	}, {
-		.name		= "watchdog",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_WDT,
-	}, {
-		.name		= "timers",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_PWM,
-	}, {
-		.name		= "hclk_fimgvg",
-		.id		= -1,
-		.parent		= &clk_hclk.clk,
-		.enable		= s5p6440_hclk1_ctrl,
-		.ctrlbit	= (1 << 2),
-	}, {
-		.name		= "tsi",
-		.id		= -1,
-		.parent		= &clk_hclk_low.clk,
-		.enable		= s5p6440_hclk1_ctrl,
-		.ctrlbit	= (1 << 0),
-	}, {
-		.name		= "pclk_fimgvg",
-		.id		= -1,
-		.parent		= &clk_pclk.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= (1 << 31),
-	}, {
-		.name		= "dmc0",
-		.id		= -1,
-		.parent		= &clk_pclk.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= (1 << 30),
-	}, {
-		.name		= "etm",
-		.id		= -1,
-		.parent		= &clk_pclk.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= (1 << 29),
-	}, {
-		.name		= "dsim",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= (1 << 28),
-	}, {
-		.name		= "gps",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= (1 << 25),
-	}, {
-		.name		= "pcm",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= (1 << 8),
-	}, {
-		.name		= "irom",
-		.id		= -1,
-		.parent		= &clk_hclk.clk,
-		.enable		= s5p6440_hclk0_ctrl,
-		.ctrlbit	= (1 << 25),
-	}, {
-		.name		= "dma",
-		.id		= -1,
-		.parent		= &clk_hclk_low.clk,
-		.enable		= s5p6440_hclk0_ctrl,
-		.ctrlbit	= (1 << 12),
-	}, {
-		.name		= "2d",
-		.id		= -1,
-		.parent		= &clk_hclk.clk,
-		.enable		= s5p6440_hclk0_ctrl,
-		.ctrlbit	= (1 << 8),
-	},
-};
-
-/*
- * The following clocks will be enabled during clock initialization.
- */
-static struct clk init_clocks[] = {
-	{
-		.name		= "gpio",
-		.id		= -1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_GPIO,
-	}, {
-		.name		= "uart",
-		.id		= 0,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_UART0,
-	}, {
-		.name		= "uart",
-		.id		= 1,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_UART1,
-	}, {
-		.name		= "uart",
-		.id		= 2,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_UART2,
-	}, {
-		.name		= "uart",
-		.id		= 3,
-		.parent		= &clk_pclk_low.clk,
-		.enable		= s5p6440_pclk_ctrl,
-		.ctrlbit	= S5P_CLKCON_PCLK_UART3,
-	}, {
-		.name		= "mem",
-		.id		= -1,
-		.parent		= &clk_hclk.clk,
-		.enable		= s5p6440_hclk0_ctrl,
-		.ctrlbit	= (1 << 21),
-	}, {
-		.name		= "intc",
-		.id		= -1,
-		.parent		= &clk_hclk.clk,
-		.enable		= s5p6440_hclk0_ctrl,
-		.ctrlbit	= (1 << 1),
-	},
-};
-
-static struct clk clk_iis_cd_v40 = {
-	.name		= "iis_cdclk_v40",
-	.id		= -1,
-};
-
-static struct clk clk_pcm_cd = {
-	.name		= "pcm_cdclk",
-	.id		= -1,
-};
-
-static struct clk *clkset_group1_list[] = {
-	&clk_mout_epll.clk,
-	&clk_dout_mpll.clk,
-	&clk_fin_epll,
-};
-
-static struct clksrc_sources clkset_group1 = {
-	.sources	= clkset_group1_list,
-	.nr_sources	= ARRAY_SIZE(clkset_group1_list),
-};
-
-static struct clk *clkset_uart_list[] = {
-	&clk_mout_epll.clk,
-	&clk_dout_mpll.clk,
-};
-
-static struct clksrc_sources clkset_uart = {
-	.sources	= clkset_uart_list,
-	.nr_sources	= ARRAY_SIZE(clkset_uart_list),
-};
-
-static struct clk *clkset_audio_list[] = {
-	&clk_mout_epll.clk,
-	&clk_dout_mpll.clk,
-	&clk_fin_epll,
-	&clk_iis_cd_v40,
-	&clk_pcm_cd,
-};
-
-static struct clksrc_sources clkset_audio = {
-	.sources	= clkset_audio_list,
-	.nr_sources	= ARRAY_SIZE(clkset_audio_list),
-};
-
-static struct clksrc_clk clksrcs[] = {
-	{
-		.clk	= {
-			.name		= "mmc_bus",
-			.id		= 0,
-			.ctrlbit        = S5P_CLKCON_SCLK0_MMC0,
-			.enable		= s5p6440_sclk_ctrl,
-		},
-		.sources = &clkset_group1,
-		.reg_src = { .reg = S5P_CLK_SRC0, .shift = 18, .size = 2 },
-		.reg_div = { .reg = S5P_CLK_DIV1, .shift = 0, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "mmc_bus",
-			.id		= 1,
-			.ctrlbit        = S5P_CLKCON_SCLK0_MMC1,
-			.enable		= s5p6440_sclk_ctrl,
-		},
-		.sources = &clkset_group1,
-		.reg_src = { .reg = S5P_CLK_SRC0, .shift = 20, .size = 2 },
-		.reg_div = { .reg = S5P_CLK_DIV1, .shift = 4, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "mmc_bus",
-			.id		= 2,
-			.ctrlbit        = S5P_CLKCON_SCLK0_MMC2,
-			.enable		= s5p6440_sclk_ctrl,
-		},
-		.sources = &clkset_group1,
-		.reg_src = { .reg = S5P_CLK_SRC0, .shift = 22, .size = 2 },
-		.reg_div = { .reg = S5P_CLK_DIV1, .shift = 8, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "uclk1",
-			.id		= -1,
-			.ctrlbit        = S5P_CLKCON_SCLK0_UART,
-			.enable		= s5p6440_sclk_ctrl,
-		},
-		.sources = &clkset_uart,
-		.reg_src = { .reg = S5P_CLK_SRC0, .shift = 13, .size = 1 },
-		.reg_div = { .reg = S5P_CLK_DIV2, .shift = 16, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "spi_epll",
-			.id		= 0,
-			.ctrlbit        = S5P_CLKCON_SCLK0_SPI0,
-			.enable		= s5p6440_sclk_ctrl,
-		},
-		.sources = &clkset_group1,
-		.reg_src = { .reg = S5P_CLK_SRC0, .shift = 14, .size = 2 },
-		.reg_div = { .reg = S5P_CLK_DIV2, .shift = 0, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "spi_epll",
-			.id		= 1,
-			.ctrlbit        = S5P_CLKCON_SCLK0_SPI1,
-			.enable		= s5p6440_sclk_ctrl,
-		},
-		.sources = &clkset_group1,
-		.reg_src = { .reg = S5P_CLK_SRC0, .shift = 16, .size = 2 },
-		.reg_div = { .reg = S5P_CLK_DIV2, .shift = 4, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "sclk_post",
-			.id		= -1,
-			.ctrlbit	= (1 << 10),
-			.enable		= s5p6440_sclk_ctrl,
-		},
-		.sources = &clkset_group1,
-		.reg_src = { .reg = S5P_CLK_SRC0, .shift = 26, .size = 2 },
-		.reg_div = { .reg = S5P_CLK_DIV1, .shift = 12, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "sclk_dispcon",
-			.id		= -1,
-			.ctrlbit	= (1 << 1),
-			.enable		= s5p6440_sclk1_ctrl,
-		},
-		.sources = &clkset_group1,
-		.reg_src = { .reg = S5P_CLK_SRC1, .shift = 4, .size = 2 },
-		.reg_div = { .reg = S5P_CLK_DIV3, .shift = 0, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "sclk_fimgvg",
-			.id		= -1,
-			.ctrlbit	= (1 << 2),
-			.enable		= s5p6440_sclk1_ctrl,
-		},
-		.sources = &clkset_group1,
-		.reg_src = { .reg = S5P_CLK_SRC1, .shift = 8, .size = 2 },
-		.reg_div = { .reg = S5P_CLK_DIV3, .shift = 4, .size = 4 },
-	}, {
-		.clk	= {
-			.name		= "sclk_audio2",
-			.id		= -1,
-			.ctrlbit	= (1 << 11),
-			.enable		= s5p6440_sclk_ctrl,
-		},
-		.sources = &clkset_audio,
-		.reg_src = { .reg = S5P_CLK_SRC1, .shift = 0, .size = 3 },
-		.reg_div = { .reg = S5P_CLK_DIV2, .shift = 24, .size = 4 },
-	},
-};
-
-/* Clock initialisation code */
-static struct clksrc_clk *sysclks[] = {
-	&clk_mout_apll,
-	&clk_mout_epll,
-	&clk_mout_mpll,
-	&clk_dout_mpll,
-	&clk_armclk,
-	&clk_hclk,
-	&clk_pclk,
-	&clk_hclk_low,
-	&clk_pclk_low,
-};
-
-void __init_or_cpufreq s5p6440_setup_clocks(void)
-{
-	struct clk *xtal_clk;
-	unsigned long xtal;
-	unsigned long fclk;
-	unsigned long hclk;
-	unsigned long hclk_low;
-	unsigned long pclk;
-	unsigned long pclk_low;
-	unsigned long epll;
-	unsigned long apll;
-	unsigned long mpll;
-	unsigned int ptr;
-
-	/* Set S5P6440 functions for clk_fout_epll */
-	clk_fout_epll.enable = s5p6440_epll_enable;
-	clk_fout_epll.ops = &s5p6440_epll_ops;
-
-	clk_48m.enable = s5p6440_clk48m_ctrl;
-
-	xtal_clk = clk_get(NULL, "ext_xtal");
-	BUG_ON(IS_ERR(xtal_clk));
-
-	xtal = clk_get_rate(xtal_clk);
-	clk_put(xtal_clk);
-
-	epll = s5p_get_pll90xx(xtal, __raw_readl(S5P_EPLL_CON),
-				__raw_readl(S5P_EPLL_CON_K));
-	mpll = s5p_get_pll45xx(xtal, __raw_readl(S5P_MPLL_CON), pll_4502);
-	apll = s5p_get_pll45xx(xtal, __raw_readl(S5P_APLL_CON), pll_4502);
-
-	clk_fout_mpll.rate = mpll;
-	clk_fout_epll.rate = epll;
-	clk_fout_apll.rate = apll;
-
-	printk(KERN_INFO "S5P6440: PLL settings, A=%ld.%ldMHz, M=%ld.%ldMHz," \
-			" E=%ld.%ldMHz\n",
-			print_mhz(apll), print_mhz(mpll), print_mhz(epll));
-
-	fclk = clk_get_rate(&clk_armclk.clk);
-	hclk = clk_get_rate(&clk_hclk.clk);
-	pclk = clk_get_rate(&clk_pclk.clk);
-	hclk_low = clk_get_rate(&clk_hclk_low.clk);
-	pclk_low = clk_get_rate(&clk_pclk_low.clk);
-
-	printk(KERN_INFO "S5P6440: HCLK=%ld.%ldMHz, HCLK_LOW=%ld.%ldMHz," \
-			" PCLK=%ld.%ldMHz, PCLK_LOW=%ld.%ldMHz\n",
-			print_mhz(hclk), print_mhz(hclk_low),
-			print_mhz(pclk), print_mhz(pclk_low));
-
-	clk_f.rate = fclk;
-	clk_h.rate = hclk;
-	clk_p.rate = pclk;
-
-	for (ptr = 0; ptr < ARRAY_SIZE(clksrcs); ptr++)
-		s3c_set_clksrc(&clksrcs[ptr], true);
-}
-
-static struct clk *clks[] __initdata = {
-	&clk_ext,
-	&clk_iis_cd_v40,
-	&clk_pcm_cd,
-};
-
-void __init s5p6440_register_clocks(void)
-{
-	struct clk *clkp;
-	int ret;
-	int ptr;
-
-	ret = s3c24xx_register_clocks(clks, ARRAY_SIZE(clks));
-	if (ret > 0)
-		printk(KERN_ERR "Failed to register %u clocks\n", ret);
-
-	for (ptr = 0; ptr < ARRAY_SIZE(sysclks); ptr++)
-		s3c_register_clksrc(sysclks[ptr], 1);
-
-	s3c_register_clksrc(clksrcs, ARRAY_SIZE(clksrcs));
-	s3c_register_clocks(init_clocks, ARRAY_SIZE(init_clocks));
-
-	clkp = init_clocks_disable;
-	for (ptr = 0; ptr < ARRAY_SIZE(init_clocks_disable); ptr++, clkp++) {
-
-		ret = s3c24xx_register_clock(clkp);
-		if (ret < 0) {
-			printk(KERN_ERR "Failed to register clock %s (%d)\n",
-			       clkp->name, ret);
-		}
-		(clkp->enable)(clkp, 0);
-	}
-
-	s3c_pwmclk_init();
-}
diff --git a/arch/arm/mach-s5p6440/cpu.c b/arch/arm/mach-s5p6440/cpu.c
deleted file mode 100644
index ec592e8..0000000
--- a/arch/arm/mach-s5p6440/cpu.c
+++ /dev/null
@@ -1,117 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/cpu.c
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/list.h>
-#include <linux/timer.h>
-#include <linux/init.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/sysdev.h>
-#include <linux/serial_core.h>
-#include <linux/platform_device.h>
-#include <linux/sched.h>
-
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-#include <asm/mach/irq.h>
-
-#include <asm/proc-fns.h>
-
-#include <mach/hardware.h>
-#include <mach/map.h>
-#include <asm/irq.h>
-
-#include <plat/regs-serial.h>
-#include <mach/regs-clock.h>
-
-#include <plat/cpu.h>
-#include <plat/devs.h>
-#include <plat/clock.h>
-#include <plat/s5p6440.h>
-#include <plat/adc-core.h>
-
-static void s5p6440_idle(void)
-{
-	unsigned long val;
-
-	if (!need_resched()) {
-		val = __raw_readl(S5P_PWR_CFG);
-		val &= ~(0x3<<5);
-		val |= (0x1<<5);
-		__raw_writel(val, S5P_PWR_CFG);
-
-		cpu_do_idle();
-	}
-	local_irq_enable();
-}
-
-/* s5p6440_map_io
- *
- * register the standard cpu IO areas
-*/
-
-void __init s5p6440_map_io(void)
-{
-	/* initialize any device information early */
-	s3c_adc_setname("s3c64xx-adc");
-}
-
-void __init s5p6440_init_clocks(int xtal)
-{
-	printk(KERN_DEBUG "%s: initializing clocks\n", __func__);
-
-	s3c24xx_register_baseclocks(xtal);
-	s5p_register_clocks(xtal);
-	s5p6440_register_clocks();
-	s5p6440_setup_clocks();
-}
-
-void __init s5p6440_init_irq(void)
-{
-	/* S5P6440 supports only 2 VIC */
-	u32 vic[2];
-
-	/*
-	 * VIC0 is missing IRQ_VIC0[3, 4, 8, 10, (12-22)]
-	 * VIC1 is missing IRQ VIC1[1, 3, 4, 10, 11, 12, 14, 15, 22]
-	 */
-	vic[0] = 0xff800ae7;
-	vic[1] = 0xffbf23e5;
-
-	s5p_init_irq(vic, ARRAY_SIZE(vic));
-}
-
-struct sysdev_class s5p6440_sysclass = {
-	.name	= "s5p6440-core",
-};
-
-static struct sys_device s5p6440_sysdev = {
-	.cls	= &s5p6440_sysclass,
-};
-
-static int __init s5p6440_core_init(void)
-{
-	return sysdev_class_register(&s5p6440_sysclass);
-}
-
-core_initcall(s5p6440_core_init);
-
-int __init s5p6440_init(void)
-{
-	printk(KERN_INFO "S5P6440: Initializing architecture\n");
-
-	/* set idle function */
-	pm_idle = s5p6440_idle;
-
-	return sysdev_register(&s5p6440_sysdev);
-}
diff --git a/arch/arm/mach-s5p6440/dev-audio.c b/arch/arm/mach-s5p6440/dev-audio.c
deleted file mode 100644
index 3ca0d2b..0000000
--- a/arch/arm/mach-s5p6440/dev-audio.c
+++ /dev/null
@@ -1,127 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/dev-audio.c
- *
- * Copyright (c) 2010 Samsung Electronics Co. Ltd
- *	Jaswinder Singh <jassi.brar@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/gpio.h>
-
-#include <plat/gpio-cfg.h>
-#include <plat/audio.h>
-
-#include <mach/map.h>
-#include <mach/dma.h>
-#include <mach/irqs.h>
-
-static int s5p6440_cfg_i2s(struct platform_device *pdev)
-{
-	/* configure GPIO for i2s port */
-	switch (pdev->id) {
-	case -1:
-		s3c_gpio_cfgpin(S5P6440_GPR(4), S3C_GPIO_SFN(5));
-		s3c_gpio_cfgpin(S5P6440_GPR(5), S3C_GPIO_SFN(5));
-		s3c_gpio_cfgpin(S5P6440_GPR(6), S3C_GPIO_SFN(5));
-		s3c_gpio_cfgpin(S5P6440_GPR(7), S3C_GPIO_SFN(5));
-		s3c_gpio_cfgpin(S5P6440_GPR(8), S3C_GPIO_SFN(5));
-		s3c_gpio_cfgpin(S5P6440_GPR(13), S3C_GPIO_SFN(5));
-		s3c_gpio_cfgpin(S5P6440_GPR(14), S3C_GPIO_SFN(5));
-		break;
-
-	default:
-		printk(KERN_ERR "Invalid Device %d\n", pdev->id);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static struct s3c_audio_pdata s3c_i2s_pdata = {
-	.cfg_gpio = s5p6440_cfg_i2s,
-};
-
-static struct resource s5p6440_iis0_resource[] = {
-	[0] = {
-		.start = S5P6440_PA_I2S,
-		.end   = S5P6440_PA_I2S + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_I2S0_TX,
-		.end   = DMACH_I2S0_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_I2S0_RX,
-		.end   = DMACH_I2S0_RX,
-		.flags = IORESOURCE_DMA,
-	},
-};
-
-struct platform_device s5p6440_device_iis = {
-	.name		  = "s3c64xx-iis-v4",
-	.id		  = -1,
-	.num_resources	  = ARRAY_SIZE(s5p6440_iis0_resource),
-	.resource	  = s5p6440_iis0_resource,
-	.dev = {
-		.platform_data = &s3c_i2s_pdata,
-	},
-};
-
-/* PCM Controller platform_devices */
-
-static int s5p6440_pcm_cfg_gpio(struct platform_device *pdev)
-{
-	switch (pdev->id) {
-	case 0:
-		s3c_gpio_cfgpin(S5P6440_GPR(7), S3C_GPIO_SFN(2));
-		s3c_gpio_cfgpin(S5P6440_GPR(13), S3C_GPIO_SFN(2));
-		s3c_gpio_cfgpin(S5P6440_GPR(14), S3C_GPIO_SFN(2));
-		s3c_gpio_cfgpin(S5P6440_GPR(8), S3C_GPIO_SFN(2));
-		s3c_gpio_cfgpin(S5P6440_GPR(6), S3C_GPIO_SFN(2));
-		break;
-
-	default:
-		printk(KERN_DEBUG "Invalid PCM Controller number!");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static struct s3c_audio_pdata s3c_pcm_pdata = {
-	.cfg_gpio = s5p6440_pcm_cfg_gpio,
-};
-
-static struct resource s5p6440_pcm0_resource[] = {
-	[0] = {
-		.start = S5P6440_PA_PCM,
-		.end   = S5P6440_PA_PCM + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_PCM0_TX,
-		.end   = DMACH_PCM0_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_PCM0_RX,
-		.end   = DMACH_PCM0_RX,
-		.flags = IORESOURCE_DMA,
-	},
-};
-
-struct platform_device s5p6440_device_pcm = {
-	.name		  = "samsung-pcm",
-	.id		  = 0,
-	.num_resources	  = ARRAY_SIZE(s5p6440_pcm0_resource),
-	.resource	  = s5p6440_pcm0_resource,
-	.dev = {
-		.platform_data = &s3c_pcm_pdata,
-	},
-};
diff --git a/arch/arm/mach-s5p6440/dev-spi.c b/arch/arm/mach-s5p6440/dev-spi.c
deleted file mode 100644
index 510af44..0000000
--- a/arch/arm/mach-s5p6440/dev-spi.c
+++ /dev/null
@@ -1,176 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/dev-spi.c
- *
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/gpio.h>
-
-#include <mach/dma.h>
-#include <mach/map.h>
-#include <mach/irqs.h>
-#include <mach/spi-clocks.h>
-
-#include <plat/s3c64xx-spi.h>
-#include <plat/gpio-cfg.h>
-
-static char *spi_src_clks[] = {
-	[S5P6440_SPI_SRCCLK_PCLK] = "pclk",
-	[S5P6440_SPI_SRCCLK_SCLK] = "spi_epll",
-};
-
-/* SPI Controller platform_devices */
-
-/* Since we emulate multi-cs capability, we do not touch the CS.
- * The emulated CS is toggled by board specific mechanism, as it can
- * be either some immediate GPIO or some signal out of some other
- * chip in between ... or some yet another way.
- * We simply do not assume anything about CS.
- */
-static int s5p6440_spi_cfg_gpio(struct platform_device *pdev)
-{
-	switch (pdev->id) {
-	case 0:
-		s3c_gpio_cfgpin(S5P6440_GPC(0), S3C_GPIO_SFN(2));
-		s3c_gpio_cfgpin(S5P6440_GPC(1), S3C_GPIO_SFN(2));
-		s3c_gpio_cfgpin(S5P6440_GPC(2), S3C_GPIO_SFN(2));
-		s3c_gpio_setpull(S5P6440_GPC(0), S3C_GPIO_PULL_UP);
-		s3c_gpio_setpull(S5P6440_GPC(1), S3C_GPIO_PULL_UP);
-		s3c_gpio_setpull(S5P6440_GPC(2), S3C_GPIO_PULL_UP);
-		break;
-
-	case 1:
-		s3c_gpio_cfgpin(S5P6440_GPC(4), S3C_GPIO_SFN(2));
-		s3c_gpio_cfgpin(S5P6440_GPC(5), S3C_GPIO_SFN(2));
-		s3c_gpio_cfgpin(S5P6440_GPC(6), S3C_GPIO_SFN(2));
-		s3c_gpio_setpull(S5P6440_GPC(4), S3C_GPIO_PULL_UP);
-		s3c_gpio_setpull(S5P6440_GPC(5), S3C_GPIO_PULL_UP);
-		s3c_gpio_setpull(S5P6440_GPC(6), S3C_GPIO_PULL_UP);
-		break;
-
-	default:
-		dev_err(&pdev->dev, "Invalid SPI Controller number!");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static struct resource s5p6440_spi0_resource[] = {
-	[0] = {
-		.start = S5P6440_PA_SPI0,
-		.end   = S5P6440_PA_SPI0 + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_SPI0_TX,
-		.end   = DMACH_SPI0_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_SPI0_RX,
-		.end   = DMACH_SPI0_RX,
-		.flags = IORESOURCE_DMA,
-	},
-	[3] = {
-		.start = IRQ_SPI0,
-		.end   = IRQ_SPI0,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct s3c64xx_spi_info s5p6440_spi0_pdata = {
-	.cfg_gpio = s5p6440_spi_cfg_gpio,
-	.fifo_lvl_mask = 0x1ff,
-	.rx_lvl_offset = 15,
-};
-
-static u64 spi_dmamask = DMA_BIT_MASK(32);
-
-struct platform_device s5p6440_device_spi0 = {
-	.name		  = "s3c64xx-spi",
-	.id		  = 0,
-	.num_resources	  = ARRAY_SIZE(s5p6440_spi0_resource),
-	.resource	  = s5p6440_spi0_resource,
-	.dev = {
-		.dma_mask		= &spi_dmamask,
-		.coherent_dma_mask	= DMA_BIT_MASK(32),
-		.platform_data = &s5p6440_spi0_pdata,
-	},
-};
-
-static struct resource s5p6440_spi1_resource[] = {
-	[0] = {
-		.start = S5P6440_PA_SPI1,
-		.end   = S5P6440_PA_SPI1 + 0x100 - 1,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start = DMACH_SPI1_TX,
-		.end   = DMACH_SPI1_TX,
-		.flags = IORESOURCE_DMA,
-	},
-	[2] = {
-		.start = DMACH_SPI1_RX,
-		.end   = DMACH_SPI1_RX,
-		.flags = IORESOURCE_DMA,
-	},
-	[3] = {
-		.start = IRQ_SPI1,
-		.end   = IRQ_SPI1,
-		.flags = IORESOURCE_IRQ,
-	},
-};
-
-static struct s3c64xx_spi_info s5p6440_spi1_pdata = {
-	.cfg_gpio = s5p6440_spi_cfg_gpio,
-	.fifo_lvl_mask = 0x7f,
-	.rx_lvl_offset = 15,
-};
-
-struct platform_device s5p6440_device_spi1 = {
-	.name		  = "s3c64xx-spi",
-	.id		  = 1,
-	.num_resources	  = ARRAY_SIZE(s5p6440_spi1_resource),
-	.resource	  = s5p6440_spi1_resource,
-	.dev = {
-		.dma_mask		= &spi_dmamask,
-		.coherent_dma_mask	= DMA_BIT_MASK(32),
-		.platform_data = &s5p6440_spi1_pdata,
-	},
-};
-
-void __init s5p6440_spi_set_info(int cntrlr, int src_clk_nr, int num_cs)
-{
-	struct s3c64xx_spi_info *pd;
-
-	/* Reject invalid configuration */
-	if (!num_cs || src_clk_nr < 0
-			|| src_clk_nr > S5P6440_SPI_SRCCLK_SCLK) {
-		printk(KERN_ERR "%s: Invalid SPI configuration\n", __func__);
-		return;
-	}
-
-	switch (cntrlr) {
-	case 0:
-		pd = &s5p6440_spi0_pdata;
-		break;
-	case 1:
-		pd = &s5p6440_spi1_pdata;
-		break;
-	default:
-		printk(KERN_ERR "%s: Invalid SPI controller(%d)\n",
-							__func__, cntrlr);
-		return;
-	}
-
-	pd->num_cs = num_cs;
-	pd->src_clk_nr = src_clk_nr;
-	pd->src_clk_name = spi_src_clks[src_clk_nr];
-}
diff --git a/arch/arm/mach-s5p6440/dma.c b/arch/arm/mach-s5p6440/dma.c
deleted file mode 100644
index 07606ad..0000000
--- a/arch/arm/mach-s5p6440/dma.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
-
-#include <plat/devs.h>
-#include <plat/irqs.h>
-
-#include <mach/map.h>
-#include <mach/irqs.h>
-
-#include <plat/s3c-pl330-pdata.h>
-
-static u64 dma_dmamask = DMA_BIT_MASK(32);
-
-static struct resource s5p6440_pdma_resource[] = {
-	[0] = {
-		.start  = S5P6440_PA_PDMA,
-		.end    = S5P6440_PA_PDMA + SZ_4K,
-		.flags = IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_DMA0,
-		.end	= IRQ_DMA0,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct s3c_pl330_platdata s5p6440_pdma_pdata = {
-	.peri = {
-		[0] = DMACH_UART0_RX,
-		[1] = DMACH_UART0_TX,
-		[2] = DMACH_UART1_RX,
-		[3] = DMACH_UART1_TX,
-		[4] = DMACH_UART2_RX,
-		[5] = DMACH_UART2_TX,
-		[6] = DMACH_UART3_RX,
-		[7] = DMACH_UART3_TX,
-		[8] = DMACH_MAX,
-		[9] = DMACH_MAX,
-		[10] = DMACH_PCM0_TX,
-		[11] = DMACH_PCM0_RX,
-		[12] = DMACH_I2S0_TX,
-		[13] = DMACH_I2S0_RX,
-		[14] = DMACH_SPI0_TX,
-		[15] = DMACH_SPI0_RX,
-		[16] = DMACH_MAX,
-		[17] = DMACH_MAX,
-		[18] = DMACH_MAX,
-		[19] = DMACH_MAX,
-		[20] = DMACH_SPI1_TX,
-		[21] = DMACH_SPI1_RX,
-		[22] = DMACH_MAX,
-		[23] = DMACH_MAX,
-		[24] = DMACH_MAX,
-		[25] = DMACH_MAX,
-		[26] = DMACH_MAX,
-		[27] = DMACH_MAX,
-		[28] = DMACH_MAX,
-		[29] = DMACH_PWM,
-		[30] = DMACH_MAX,
-		[31] = DMACH_MAX,
-	},
-};
-
-static struct platform_device s5p6440_device_pdma = {
-	.name		= "s3c-pl330",
-	.id		= 1,
-	.num_resources	= ARRAY_SIZE(s5p6440_pdma_resource),
-	.resource	= s5p6440_pdma_resource,
-	.dev		= {
-		.dma_mask = &dma_dmamask,
-		.coherent_dma_mask = DMA_BIT_MASK(32),
-		.platform_data = &s5p6440_pdma_pdata,
-	},
-};
-
-static struct platform_device *s5p6440_dmacs[] __initdata = {
-	&s5p6440_device_pdma,
-};
-
-static int __init s5p6440_dma_init(void)
-{
-	platform_add_devices(s5p6440_dmacs, ARRAY_SIZE(s5p6440_dmacs));
-
-	return 0;
-}
-arch_initcall(s5p6440_dma_init);
diff --git a/arch/arm/mach-s5p6440/include/mach/debug-macro.S b/arch/arm/mach-s5p6440/include/mach/debug-macro.S
deleted file mode 100644
index 1347d7f..0000000
--- a/arch/arm/mach-s5p6440/include/mach/debug-macro.S
+++ /dev/null
@@ -1,37 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/debug-macro.S
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-/* pull in the relevant register and map files. */
-
-#include <mach/map.h>
-#include <plat/regs-serial.h>
-
-	/* note, for the boot process to work we have to keep the UART
-	 * virtual address aligned to an 1MiB boundary for the L1
-	 * mapping the head code makes. We keep the UART virtual address
-	 * aligned and add in the offset when we load the value here.
-	 */
-
-	.macro addruart, rx, rtmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, = S3C_PA_UART
-		ldrne	\rx, = S3C_VA_UART
-#if CONFIG_DEBUG_S3C_UART != 0
-		add	\rx, \rx, #(0x400 * CONFIG_DEBUG_S3C_UART)
-#endif
-	.endm
-
-/* include the reset of the code which will do the work, we're only
- * compiling for a single cpu processor type so the default of s3c2440
- * will be fine with us.
- */
-
-#include <plat/debug-macro.S>
diff --git a/arch/arm/mach-s5p6440/include/mach/entry-macro.S b/arch/arm/mach-s5p6440/include/mach/entry-macro.S
deleted file mode 100644
index e65f1b9..0000000
--- a/arch/arm/mach-s5p6440/include/mach/entry-macro.S
+++ /dev/null
@@ -1,16 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/entry-macro.S
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * Low-level IRQ helper macros for the Samsung S5P6440
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <mach/map.h>
-#include <plat/irqs.h>
-
-#include <asm/entry-macro-vic2.S>
diff --git a/arch/arm/mach-s5p6440/include/mach/gpio.h b/arch/arm/mach-s5p6440/include/mach/gpio.h
deleted file mode 100644
index 2178383..0000000
--- a/arch/arm/mach-s5p6440/include/mach/gpio.h
+++ /dev/null
@@ -1,80 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/gpio.h
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6440 - GPIO lib support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_ARCH_GPIO_H
-#define __ASM_ARCH_GPIO_H __FILE__
-
-#define gpio_get_value	__gpio_get_value
-#define gpio_set_value	__gpio_set_value
-#define gpio_cansleep	__gpio_cansleep
-#define gpio_to_irq	__gpio_to_irq
-
-/* GPIO bank sizes */
-#define S5P6440_GPIO_A_NR	(6)
-#define S5P6440_GPIO_B_NR	(7)
-#define S5P6440_GPIO_C_NR	(8)
-#define S5P6440_GPIO_F_NR	(2)
-#define S5P6440_GPIO_G_NR	(7)
-#define S5P6440_GPIO_H_NR	(10)
-#define S5P6440_GPIO_I_NR	(16)
-#define S5P6440_GPIO_J_NR	(12)
-#define S5P6440_GPIO_N_NR	(16)
-#define S5P6440_GPIO_P_NR	(8)
-#define S5P6440_GPIO_R_NR	(15)
-
-/* GPIO bank numbers */
-
-/* CONFIG_S3C_GPIO_SPACE allows the user to select extra
- * space for debugging purposes so that any accidental
- * change from one gpio bank to another can be caught.
-*/
-#define S5P6440_GPIO_NEXT(__gpio) \
-	((__gpio##_START) + (__gpio##_NR) + CONFIG_S3C_GPIO_SPACE + 1)
-
-enum s5p_gpio_number {
-	S5P6440_GPIO_A_START = 0,
-	S5P6440_GPIO_B_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_A),
-	S5P6440_GPIO_C_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_B),
-	S5P6440_GPIO_F_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_C),
-	S5P6440_GPIO_G_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_F),
-	S5P6440_GPIO_H_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_G),
-	S5P6440_GPIO_I_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_H),
-	S5P6440_GPIO_J_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_I),
-	S5P6440_GPIO_N_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_J),
-	S5P6440_GPIO_P_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_N),
-	S5P6440_GPIO_R_START = S5P6440_GPIO_NEXT(S5P6440_GPIO_P),
-};
-
-/* S5P6440 GPIO number definitions. */
-#define S5P6440_GPA(_nr)	(S5P6440_GPIO_A_START + (_nr))
-#define S5P6440_GPB(_nr)	(S5P6440_GPIO_B_START + (_nr))
-#define S5P6440_GPC(_nr)	(S5P6440_GPIO_C_START + (_nr))
-#define S5P6440_GPF(_nr)	(S5P6440_GPIO_F_START + (_nr))
-#define S5P6440_GPG(_nr)	(S5P6440_GPIO_G_START + (_nr))
-#define S5P6440_GPH(_nr)	(S5P6440_GPIO_H_START + (_nr))
-#define S5P6440_GPI(_nr)	(S5P6440_GPIO_I_START + (_nr))
-#define S5P6440_GPJ(_nr)	(S5P6440_GPIO_J_START + (_nr))
-#define S5P6440_GPN(_nr)	(S5P6440_GPIO_N_START + (_nr))
-#define S5P6440_GPP(_nr)	(S5P6440_GPIO_P_START + (_nr))
-#define S5P6440_GPR(_nr)	(S5P6440_GPIO_R_START + (_nr))
-
-/* the end of the S5P6440 specific gpios */
-#define S5P6440_GPIO_END	(S5P6440_GPR(S5P6440_GPIO_R_NR) + 1)
-#define S3C_GPIO_END		S5P6440_GPIO_END
-
-/* define the number of gpios we need to the one after the GPR() range */
-#define ARCH_NR_GPIOS		(S5P6440_GPR(S5P6440_GPIO_R_NR) +	\
-				 CONFIG_SAMSUNG_GPIO_EXTRA + 1)
-
-#include <asm-generic/gpio.h>
-
-#endif /* __ASM_ARCH_GPIO_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/io.h b/arch/arm/mach-s5p6440/include/mach/io.h
deleted file mode 100644
index fa2d69c..0000000
--- a/arch/arm/mach-s5p6440/include/mach/io.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* arch/arm/mach-s5p6440/include/mach/io.h
- *
- * Copyright 2008 Simtec Electronics
- *	Ben Dooks <ben-linux@fluff.org>
- *
- * Default IO routines for S3C64XX based
- */
-
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-/* No current ISA/PCI bus support. */
-#define __io(a)		__typesafe_io(a)
-#define __mem_pci(a)	(a)
-
-#define IO_SPACE_LIMIT (0xFFFFFFFF)
-
-#endif
diff --git a/arch/arm/mach-s5p6440/include/mach/map.h b/arch/arm/mach-s5p6440/include/mach/map.h
deleted file mode 100644
index 6cc5cbc..0000000
--- a/arch/arm/mach-s5p6440/include/mach/map.h
+++ /dev/null
@@ -1,86 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/map.h
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6440 - Memory map definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_ARCH_MAP_H
-#define __ASM_ARCH_MAP_H __FILE__
-
-#include <plat/map-base.h>
-#include <plat/map-s5p.h>
-
-#define S5P6440_PA_CHIPID	(0xE0000000)
-#define S5P_PA_CHIPID		S5P6440_PA_CHIPID
-
-#define S5P6440_PA_SYSCON	(0xE0100000)
-#define S5P6440_PA_CLK		(S5P6440_PA_SYSCON + 0x0)
-#define S5P_PA_SYSCON		S5P6440_PA_SYSCON
-
-#define S5P6440_PA_GPIO		(0xE0308000)
-#define S5P_PA_GPIO		S5P6440_PA_GPIO
-
-#define S5P6440_PA_VIC0		(0xE4000000)
-#define S5P_PA_VIC0		S5P6440_PA_VIC0
-
-#define S5P6440_PA_PDMA		0xE9000000
-
-#define S5P6440_PA_VIC1		(0xE4100000)
-#define S5P_PA_VIC1		S5P6440_PA_VIC1
-
-#define S5P6440_PA_TIMER	(0xEA000000)
-#define S5P_PA_TIMER		S5P6440_PA_TIMER
-
-#define S5P6440_PA_RTC		(0xEA100000)
-
-#define S5P6440_PA_WDT		(0xEA200000)
-#define S5P_PA_WDT		S5P6440_PA_WDT
-
-#define S5P6440_PA_UART		(0xEC000000)
-
-#define S5P_PA_UART0		(S5P6440_PA_UART + 0x0)
-#define S5P_PA_UART1		(S5P6440_PA_UART + 0x400)
-#define S5P_PA_UART2		(S5P6440_PA_UART + 0x800)
-#define S5P_PA_UART3		(S5P6440_PA_UART + 0xC00)
-
-#define S5P_SZ_UART		SZ_256
-
-#define S5P6440_PA_IIC0		(0xEC104000)
-#define S5P6440_PA_IIC1		(0xEC20F000)
-
-#define S5P6440_PA_SPI0		0xEC400000
-#define S5P6440_PA_SPI1		0xEC500000
-
-#define S5P6440_PA_HSOTG	(0xED100000)
-
-#define S5P6440_PA_HSMMC0	(0xED800000)
-#define S5P6440_PA_HSMMC1	(0xED900000)
-#define S5P6440_PA_HSMMC2	(0xEDA00000)
-
-#define S5P6440_PA_SDRAM	(0x20000000)
-#define S5P_PA_SDRAM		S5P6440_PA_SDRAM
-
-/* I2S */
-#define S5P6440_PA_I2S		0xF2000000
-
-/* PCM */
-#define S5P6440_PA_PCM		0xF2100000
-
-#define S5P6440_PA_ADC		(0xF3000000)
-
-/* compatibiltiy defines. */
-#define S3C_PA_UART		S5P6440_PA_UART
-#define S3C_PA_IIC		S5P6440_PA_IIC0
-#define S3C_PA_RTC		S5P6440_PA_RTC
-#define S3C_PA_IIC1		S5P6440_PA_IIC1
-#define S3C_PA_WDT		S5P6440_PA_WDT
-
-#define SAMSUNG_PA_ADC		S5P6440_PA_ADC
-
-#endif /* __ASM_ARCH_MAP_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/memory.h b/arch/arm/mach-s5p6440/include/mach/memory.h
deleted file mode 100644
index d62910c..0000000
--- a/arch/arm/mach-s5p6440/include/mach/memory.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/memory.h
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6440 - Memory definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_ARCH_MEMORY_H
-#define __ASM_ARCH_MEMORY_H
-
-#define PHYS_OFFSET     	UL(0x20000000)
-#define CONSISTENT_DMA_SIZE	SZ_8M
-
-#endif /* __ASM_ARCH_MEMORY_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/regs-clock.h b/arch/arm/mach-s5p6440/include/mach/regs-clock.h
deleted file mode 100644
index c783ecc..0000000
--- a/arch/arm/mach-s5p6440/include/mach/regs-clock.h
+++ /dev/null
@@ -1,130 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/regs-clock.h
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6440 - Clock register definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_ARCH_REGS_CLOCK_H
-#define __ASM_ARCH_REGS_CLOCK_H __FILE__
-
-#include <mach/map.h>
-
-#define S5P_CLKREG(x)		(S3C_VA_SYS + (x))
-
-#define S5P_APLL_LOCK		S5P_CLKREG(0x00)
-#define S5P_MPLL_LOCK		S5P_CLKREG(0x04)
-#define S5P_EPLL_LOCK		S5P_CLKREG(0x08)
-#define S5P_APLL_CON		S5P_CLKREG(0x0C)
-#define S5P_MPLL_CON		S5P_CLKREG(0x10)
-#define S5P_EPLL_CON		S5P_CLKREG(0x14)
-#define S5P_EPLL_CON_K		S5P_CLKREG(0x18)
-#define S5P_CLK_SRC0		S5P_CLKREG(0x1C)
-#define S5P_CLK_DIV0		S5P_CLKREG(0x20)
-#define S5P_CLK_DIV1		S5P_CLKREG(0x24)
-#define S5P_CLK_DIV2		S5P_CLKREG(0x28)
-#define S5P_CLK_OUT		S5P_CLKREG(0x2C)
-#define S5P_CLK_GATE_HCLK0	S5P_CLKREG(0x30)
-#define S5P_CLK_GATE_PCLK	S5P_CLKREG(0x34)
-#define S5P_CLK_GATE_SCLK0	S5P_CLKREG(0x38)
-#define S5P_CLK_GATE_MEM0	S5P_CLKREG(0x3C)
-#define S5P_CLK_DIV3		S5P_CLKREG(0x40)
-#define S5P_CLK_GATE_HCLK1	S5P_CLKREG(0x44)
-#define S5P_CLK_GATE_SCLK1	S5P_CLKREG(0x48)
-#define S5P_AHB_CON0           	S5P_CLKREG(0x100)
-#define S5P_CLK_SRC1           	S5P_CLKREG(0x10C)
-#define S5P_SWRESET		S5P_CLKREG(0x114)
-#define S5P_SYS_ID		S5P_CLKREG(0x118)
-#define S5P_SYS_OTHERS		S5P_CLKREG(0x11C)
-#define S5P_MEM_CFG_STAT	S5P_CLKREG(0x12C)
-#define S5P_PWR_CFG		S5P_CLKREG(0x804)
-#define S5P_EINT_WAKEUP_MASK	S5P_CLKREG(0x808)
-#define S5P_NORMAL_CFG		S5P_CLKREG(0x810)
-#define S5P_STOP_CFG		S5P_CLKREG(0x814)
-#define S5P_SLEEP_CFG		S5P_CLKREG(0x818)
-#define S5P_OSC_FREQ		S5P_CLKREG(0x820)
-#define S5P_OSC_STABLE		S5P_CLKREG(0x824)
-#define S5P_PWR_STABLE		S5P_CLKREG(0x828)
-#define S5P_MTC_STABLE		S5P_CLKREG(0x830)
-#define S5P_OTHERS		S5P_CLKREG(0x900)
-#define S5P_RST_STAT		S5P_CLKREG(0x904)
-#define S5P_WAKEUP_STAT		S5P_CLKREG(0x908)
-#define S5P_SLPEN		S5P_CLKREG(0x930)
-#define S5P_INFORM0		S5P_CLKREG(0xA00)
-#define S5P_INFORM1		S5P_CLKREG(0xA04)
-#define S5P_INFORM2		S5P_CLKREG(0xA08)
-#define S5P_INFORM3		S5P_CLKREG(0xA0C)
-
-/* CLKDIV0 */
-#define S5P_CLKDIV0_PCLK_MASK		(0xf << 12)
-#define S5P_CLKDIV0_PCLK_SHIFT		(12)
-#define S5P_CLKDIV0_HCLK_MASK		(0xf << 8)
-#define S5P_CLKDIV0_HCLK_SHIFT		(8)
-#define S5P_CLKDIV0_MPLL_MASK		(0x1 << 4)
-#define S5P_CLKDIV0_ARM_MASK		(0xf << 0)
-#define S5P_CLKDIV0_ARM_SHIFT		(0)
-
-/* CLKDIV3 */
-#define S5P_CLKDIV3_PCLK_LOW_MASK	(0xf << 12)
-#define S5P_CLKDIV3_PCLK_LOW_SHIFT	(12)
-#define S5P_CLKDIV3_HCLK_LOW_MASK	(0xf << 8)
-#define S5P_CLKDIV3_HCLK_LOW_SHIFT	(8)
-
-/* HCLK0 GATE Registers */
-#define S5P_CLKCON_HCLK0_USB		(1<<20)
-#define S5P_CLKCON_HCLK0_HSMMC2		(1<<19)
-#define S5P_CLKCON_HCLK0_HSMMC1		(1<<18)
-#define S5P_CLKCON_HCLK0_HSMMC0		(1<<17)
-#define S5P_CLKCON_HCLK0_POST0		(1<<5)
-
-/* HCLK1 GATE Registers */
-#define S5P_CLKCON_HCLK1_DISPCON	(1<<1)
-
-/* PCLK GATE Registers */
-#define S5P_CLKCON_PCLK_IIS2		(1<<26)
-#define S5P_CLKCON_PCLK_SPI1		(1<<22)
-#define S5P_CLKCON_PCLK_SPI0		(1<<21)
-#define S5P_CLKCON_PCLK_GPIO		(1<<18)
-#define S5P_CLKCON_PCLK_IIC0		(1<<17)
-#define S5P_CLKCON_PCLK_TSADC		(1<<12)
-#define S5P_CLKCON_PCLK_PWM		(1<<7)
-#define S5P_CLKCON_PCLK_RTC		(1<<6)
-#define S5P_CLKCON_PCLK_WDT		(1<<5)
-#define S5P_CLKCON_PCLK_UART3		(1<<4)
-#define S5P_CLKCON_PCLK_UART2		(1<<3)
-#define S5P_CLKCON_PCLK_UART1		(1<<2)
-#define S5P_CLKCON_PCLK_UART0		(1<<1)
-
-/* SCLK0 GATE Registers */
-#define S5P_CLKCON_SCLK0_MMC2_48	(1<<29)
-#define S5P_CLKCON_SCLK0_MMC1_48	(1<<28)
-#define S5P_CLKCON_SCLK0_MMC0_48	(1<<27)
-#define S5P_CLKCON_SCLK0_MMC2		(1<<26)
-#define S5P_CLKCON_SCLK0_MMC1		(1<<25)
-#define S5P_CLKCON_SCLK0_MMC0		(1<<24)
-#define S5P_CLKCON_SCLK0_SPI1_48 	(1<<23)
-#define S5P_CLKCON_SCLK0_SPI0_48 	(1<<22)
-#define S5P_CLKCON_SCLK0_SPI1		(1<<21)
-#define S5P_CLKCON_SCLK0_SPI0		(1<<20)
-#define S5P_CLKCON_SCLK0_UART		(1<<5)
-
-/* SCLK1 GATE Registers */
-
-/* MEM0 GATE Registers */
-#define S5P_CLKCON_MEM0_HCLK_NFCON	(1<<2)
-
-/*OTHERS Resgister */
-#define S5P_OTHERS_USB_SIG_MASK		(1<<16)
-#define S5P_OTHERS_HCLK_LOW_SEL_MPLL	(1<<6)
-
-/* Compatibility defines */
-#define ARM_CLK_DIV			S5P_CLK_DIV0
-#define ARM_DIV_RATIO_SHIFT		0
-#define ARM_DIV_MASK			(0xf << ARM_DIV_RATIO_SHIFT)
-
-#endif /* __ASM_ARCH_REGS_CLOCK_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/spi-clocks.h b/arch/arm/mach-s5p6440/include/mach/spi-clocks.h
deleted file mode 100644
index 5fbca50..0000000
--- a/arch/arm/mach-s5p6440/include/mach/spi-clocks.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/spi-clocks.h
- *
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- *	Jaswinder Singh <jassi.brar@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __S5P6440_PLAT_SPI_CLKS_H
-#define __S5P6440_PLAT_SPI_CLKS_H __FILE__
-
-#define S5P6440_SPI_SRCCLK_PCLK		0
-#define S5P6440_SPI_SRCCLK_SCLK		1
-
-#endif /* __S5P6440_PLAT_SPI_CLKS_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/uncompress.h b/arch/arm/mach-s5p6440/include/mach/uncompress.h
deleted file mode 100644
index 7c1f600d..0000000
--- a/arch/arm/mach-s5p6440/include/mach/uncompress.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/uncompress.h
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6440 - uncompress code
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __ASM_ARCH_UNCOMPRESS_H
-#define __ASM_ARCH_UNCOMPRESS_H
-
-#include <mach/map.h>
-#include <plat/uncompress.h>
-
-static void arch_detect_cpu(void)
-{
-	/* we do not need to do any cpu detection here at the moment. */
-}
-
-#endif /* __ASM_ARCH_UNCOMPRESS_H */
diff --git a/arch/arm/mach-s5p6440/init.c b/arch/arm/mach-s5p6440/init.c
deleted file mode 100644
index a1f3727..0000000
--- a/arch/arm/mach-s5p6440/init.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/init.c
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * S5P6440 - Init support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/serial_core.h>
-
-#include <plat/cpu.h>
-#include <plat/devs.h>
-#include <plat/s5p6440.h>
-#include <plat/regs-serial.h>
-
-static struct s3c24xx_uart_clksrc s5p6440_serial_clocks[] = {
-	[0] = {
-		.name		= "pclk_low",
-		.divisor	= 1,
-		.min_baud	= 0,
-		.max_baud	= 0,
-	},
-	[1] = {
-		.name		= "uclk1",
-		.divisor	= 1,
-		.min_baud	= 0,
-		.max_baud	= 0,
-	},
-};
-
-/* uart registration process */
-void __init s5p6440_common_init_uarts(struct s3c2410_uartcfg *cfg, int no)
-{
-	struct s3c2410_uartcfg *tcfg = cfg;
-	u32 ucnt;
-
-	for (ucnt = 0; ucnt < no; ucnt++, tcfg++) {
-		if (!tcfg->clocks) {
-			tcfg->clocks = s5p6440_serial_clocks;
-			tcfg->clocks_size = ARRAY_SIZE(s5p6440_serial_clocks);
-		}
-	}
-
-	s3c24xx_init_uartdevs("s3c6400-uart", s5p_uart_resources, cfg, no);
-}
diff --git a/arch/arm/mach-s5p6440/setup-i2c0.c b/arch/arm/mach-s5p6440/setup-i2c0.c
deleted file mode 100644
index 2c99d14..0000000
--- a/arch/arm/mach-s5p6440/setup-i2c0.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/setup-i2c0.c
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * I2C0 GPIO configuration.
- *
- * Based on plat-s3c64xx/setup-i2c0.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-
-struct platform_device; /* don't need the contents */
-
-#include <linux/gpio.h>
-#include <plat/gpio-cfg.h>
-#include <plat/iic.h>
-
-void s3c_i2c0_cfg_gpio(struct platform_device *dev)
-{
-	s3c_gpio_cfgpin(S5P6440_GPB(5), S3C_GPIO_SFN(2));
-	s3c_gpio_setpull(S5P6440_GPB(5), S3C_GPIO_PULL_UP);
-	s3c_gpio_cfgpin(S5P6440_GPB(6), S3C_GPIO_SFN(2));
-	s3c_gpio_setpull(S5P6440_GPB(6), S3C_GPIO_PULL_UP);
-}
diff --git a/arch/arm/mach-s5p6440/setup-i2c1.c b/arch/arm/mach-s5p6440/setup-i2c1.c
deleted file mode 100644
index 9a1537f..0000000
--- a/arch/arm/mach-s5p6440/setup-i2c1.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/* linux/arch/arm/mach-s5p6440/setup-i2c1.c
- *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * I2C1 GPIO configuration.
- *
- * Based on plat-s3c64xx/setup-i2c0.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/gpio.h>
-
-struct platform_device; /* don't need the contents */
-
-#include <plat/gpio-cfg.h>
-#include <plat/iic.h>
-
-void s3c_i2c1_cfg_gpio(struct platform_device *dev)
-{
-	s3c_gpio_cfgpin(S5P6440_GPR(9), S3C_GPIO_SFN(6));
-	s3c_gpio_setpull(S5P6440_GPR(9), S3C_GPIO_PULL_UP);
-	s3c_gpio_cfgpin(S5P6440_GPR(10), S3C_GPIO_SFN(6));
-	s3c_gpio_setpull(S5P6440_GPR(10), S3C_GPIO_PULL_UP);
-}
diff --git a/arch/arm/mach-s5p6442/cpu.c b/arch/arm/mach-s5p6442/cpu.c
index 70ac681..842af86 100644
--- a/arch/arm/mach-s5p6442/cpu.c
+++ b/arch/arm/mach-s5p6442/cpu.c
@@ -1,7 +1,7 @@
 /* linux/arch/arm/mach-s5p6442/cpu.c
  *
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ *		http://www.samsung.com
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -48,10 +48,30 @@
 		.length		= SZ_16K,
 		.type		= MT_DEVICE,
 	}, {
+		.virtual	= (unsigned long)S5P_VA_GPIO,
+		.pfn		= __phys_to_pfn(S5P6442_PA_GPIO),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)VA_VIC0,
+		.pfn		= __phys_to_pfn(S5P6442_PA_VIC0),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)VA_VIC1,
+		.pfn		= __phys_to_pfn(S5P6442_PA_VIC1),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	}, {
 		.virtual	= (unsigned long)VA_VIC2,
 		.pfn		= __phys_to_pfn(S5P6442_PA_VIC2),
 		.length		= SZ_16K,
 		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S3C_VA_UART,
+		.pfn		= __phys_to_pfn(S3C_PA_UART),
+		.length		= SZ_512K,
+		.type		= MT_DEVICE,
 	}
 };
 
@@ -63,10 +83,11 @@
 	local_irq_enable();
 }
 
-/* s5p6442_map_io
+/*
+ * s5p6442_map_io
  *
  * register the standard cpu IO areas
-*/
+ */
 
 void __init s5p6442_map_io(void)
 {
diff --git a/arch/arm/mach-s5p6442/include/mach/debug-macro.S b/arch/arm/mach-s5p6442/include/mach/debug-macro.S
index bb65361..e2213205 100644
--- a/arch/arm/mach-s5p6442/include/mach/debug-macro.S
+++ b/arch/arm/mach-s5p6442/include/mach/debug-macro.S
@@ -15,13 +15,12 @@
 #include <mach/map.h>
 #include <plat/regs-serial.h>
 
-	.macro addruart, rx, rtmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, = S3C_PA_UART
-		ldrne	\rx, = S3C_VA_UART
+	.macro addruart, rp, rv
+		ldr	\rp, = S3C_PA_UART
+		ldr	\rv, = S3C_VA_UART
 #if CONFIG_DEBUG_S3C_UART != 0
-		add	\rx, \rx, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rp, \rp, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rv, \rv, #(0x400 * CONFIG_DEBUG_S3C_UART)
 #endif
 	.endm
 
diff --git a/arch/arm/mach-s5p6442/include/mach/map.h b/arch/arm/mach-s5p6442/include/mach/map.h
index 281d256..31fb2e68 100644
--- a/arch/arm/mach-s5p6442/include/mach/map.h
+++ b/arch/arm/mach-s5p6442/include/mach/map.h
@@ -23,16 +23,10 @@
 #define S5P_PA_SYSCON		S5P6442_PA_SYSCON
 
 #define S5P6442_PA_GPIO		(0xE0200000)
-#define S5P_PA_GPIO		S5P6442_PA_GPIO
 
 #define S5P6442_PA_VIC0		(0xE4000000)
-#define S5P_PA_VIC0		S5P6442_PA_VIC0
-
 #define S5P6442_PA_VIC1		(0xE4100000)
-#define S5P_PA_VIC1		S5P6442_PA_VIC1
-
 #define S5P6442_PA_VIC2		(0xE4200000)
-#define S5P_PA_VIC2		S5P6442_PA_VIC2
 
 #define S5P6442_PA_MDMA		0xE8000000
 #define S5P6442_PA_PDMA		0xE9000000
diff --git a/arch/arm/mach-s5p6442/mach-smdk6442.c b/arch/arm/mach-s5p6442/mach-smdk6442.c
index 8d8d042..819fd80 100644
--- a/arch/arm/mach-s5p6442/mach-smdk6442.c
+++ b/arch/arm/mach-s5p6442/mach-smdk6442.c
@@ -83,8 +83,6 @@
 
 MACHINE_START(SMDK6442, "SMDK6442")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S5P_PA_SDRAM + 0x100,
 	.init_irq	= s5p6442_init_irq,
 	.map_io		= smdk6442_map_io,
diff --git a/arch/arm/mach-s5p64x0/Kconfig b/arch/arm/mach-s5p64x0/Kconfig
new file mode 100644
index 0000000..fbcae93
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/Kconfig
@@ -0,0 +1,57 @@
+# arch/arm/mach-s5p64x0/Kconfig
+#
+# Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+#		http://www.samsung.com/
+#
+# Licensed under GPLv2
+
+if ARCH_S5P64X0
+
+config CPU_S5P6440
+	bool
+	select PLAT_S5P
+	select S3C_PL330_DMA
+	help
+	  Enable S5P6440 CPU support
+
+config CPU_S5P6450
+	bool
+	select PLAT_S5P
+	select S3C_PL330_DMA
+	help
+	  Enable S5P6450 CPU support
+
+config S5P64X0_SETUP_I2C1
+	bool
+	help
+	  Common setup code for i2c bus 1.
+
+# machine support
+
+config MACH_SMDK6440
+	bool "SMDK6440"
+	select CPU_S5P6440
+	select S3C_DEV_I2C1
+	select S3C_DEV_RTC
+	select S3C_DEV_WDT
+	select S3C64XX_DEV_SPI
+	select SAMSUNG_DEV_ADC
+	select SAMSUNG_DEV_TS
+	select S5P64X0_SETUP_I2C1
+	help
+	  Machine support for the Samsung SMDK6440
+
+config MACH_SMDK6450
+	bool "SMDK6450"
+	select CPU_S5P6450
+	select S3C_DEV_I2C1
+	select S3C_DEV_RTC
+	select S3C_DEV_WDT
+	select S3C64XX_DEV_SPI
+	select SAMSUNG_DEV_ADC
+	select SAMSUNG_DEV_TS
+	select S5P64X0_SETUP_I2C1
+	help
+	  Machine support for the Samsung SMDK6450
+
+endif
diff --git a/arch/arm/mach-s5p64x0/Makefile b/arch/arm/mach-s5p64x0/Makefile
new file mode 100644
index 0000000..2655829
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/Makefile
@@ -0,0 +1,30 @@
+# arch/arm/mach-s5p64x0/Makefile
+#
+# Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+# 		http://www.samsung.com
+#
+# Licensed under GPLv2
+
+obj-y				:=
+obj-m				:=
+obj-n				:=
+obj-				:=
+
+# Core support for S5P64X0 system
+
+obj-$(CONFIG_ARCH_S5P64X0)	+= cpu.o init.o clock.o dma.o
+obj-$(CONFIG_ARCH_S5P64X0)	+= setup-i2c0.o
+obj-$(CONFIG_CPU_S5P6440)	+= clock-s5p6440.o gpio.o
+obj-$(CONFIG_CPU_S5P6450)	+= clock-s5p6450.o
+
+# machine support
+
+obj-$(CONFIG_MACH_SMDK6440)	+= mach-smdk6440.o
+obj-$(CONFIG_MACH_SMDK6450)	+= mach-smdk6450.o
+
+# device support
+
+obj-y				+= dev-audio.o
+obj-$(CONFIG_S3C64XX_DEV_SPI)	+= dev-spi.o
+
+obj-$(CONFIG_S5P64X0_SETUP_I2C1)	+= setup-i2c1.o
diff --git a/arch/arm/mach-s5p6440/Makefile.boot b/arch/arm/mach-s5p64x0/Makefile.boot
similarity index 100%
rename from arch/arm/mach-s5p6440/Makefile.boot
rename to arch/arm/mach-s5p64x0/Makefile.boot
diff --git a/arch/arm/mach-s5p64x0/clock-s5p6440.c b/arch/arm/mach-s5p64x0/clock-s5p6440.c
new file mode 100644
index 0000000..f93dcd8
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/clock-s5p6440.c
@@ -0,0 +1,626 @@
+/* linux/arch/arm/mach-s5p64x0/clock-s5p6440.c
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P6440 - Clock support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/sysdev.h>
+#include <linux/io.h>
+
+#include <mach/hardware.h>
+#include <mach/map.h>
+#include <mach/regs-clock.h>
+#include <mach/s5p64x0-clock.h>
+
+#include <plat/cpu-freq.h>
+#include <plat/clock.h>
+#include <plat/cpu.h>
+#include <plat/pll.h>
+#include <plat/s5p-clock.h>
+#include <plat/clock-clksrc.h>
+#include <plat/s5p6440.h>
+
+static u32 epll_div[][5] = {
+	{ 36000000,	0,	48, 1, 4 },
+	{ 48000000,	0,	32, 1, 3 },
+	{ 60000000,	0,	40, 1, 3 },
+	{ 72000000,	0,	48, 1, 3 },
+	{ 84000000,	0,	28, 1, 2 },
+	{ 96000000,	0,	32, 1, 2 },
+	{ 32768000,	45264,	43, 1, 4 },
+	{ 45158000,	6903,	30, 1, 3 },
+	{ 49152000,	50332,	32, 1, 3 },
+	{ 67738000,	10398,	45, 1, 3 },
+	{ 73728000,	9961,	49, 1, 3 }
+};
+
+static int s5p6440_epll_set_rate(struct clk *clk, unsigned long rate)
+{
+	unsigned int epll_con, epll_con_k;
+	unsigned int i;
+
+	if (clk->rate == rate)	/* Return if nothing changed */
+		return 0;
+
+	epll_con = __raw_readl(S5P64X0_EPLL_CON);
+	epll_con_k = __raw_readl(S5P64X0_EPLL_CON_K);
+
+	epll_con_k &= ~(PLL90XX_KDIV_MASK);
+	epll_con &= ~(PLL90XX_MDIV_MASK | PLL90XX_PDIV_MASK | PLL90XX_SDIV_MASK);
+
+	for (i = 0; i < ARRAY_SIZE(epll_div); i++) {
+		 if (epll_div[i][0] == rate) {
+			epll_con_k |= (epll_div[i][1] << PLL90XX_KDIV_SHIFT);
+			epll_con |= (epll_div[i][2] << PLL90XX_MDIV_SHIFT) |
+				    (epll_div[i][3] << PLL90XX_PDIV_SHIFT) |
+				    (epll_div[i][4] << PLL90XX_SDIV_SHIFT);
+			break;
+		}
+	}
+
+	if (i == ARRAY_SIZE(epll_div)) {
+		printk(KERN_ERR "%s: Invalid Clock EPLL Frequency\n", __func__);
+		return -EINVAL;
+	}
+
+	__raw_writel(epll_con, S5P64X0_EPLL_CON);
+	__raw_writel(epll_con_k, S5P64X0_EPLL_CON_K);
+
+	clk->rate = rate;
+
+	return 0;
+}
+
+static struct clk_ops s5p6440_epll_ops = {
+	.get_rate = s5p64x0_epll_get_rate,
+	.set_rate = s5p6440_epll_set_rate,
+};
+
+static struct clksrc_clk clk_hclk = {
+	.clk	= {
+		.name		= "clk_hclk",
+		.id		= -1,
+		.parent		= &clk_armclk.clk,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV0, .shift = 8, .size = 4 },
+};
+
+static struct clksrc_clk clk_pclk = {
+	.clk	= {
+		.name		= "clk_pclk",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV0, .shift = 12, .size = 4 },
+};
+static struct clksrc_clk clk_hclk_low = {
+	.clk	= {
+		.name		= "clk_hclk_low",
+		.id		= -1,
+	},
+	.sources	= &clkset_hclk_low,
+	.reg_src	= { .reg = S5P64X0_SYS_OTHERS, .shift = 6, .size = 1 },
+	.reg_div	= { .reg = S5P64X0_CLK_DIV3, .shift = 8, .size = 4 },
+};
+
+static struct clksrc_clk clk_pclk_low = {
+	.clk	= {
+		.name		= "clk_pclk_low",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV3, .shift = 12, .size = 4 },
+};
+
+/*
+ * The following clocks will be disabled during clock initialization. It is
+ * recommended to keep the following clocks disabled until the driver requests
+ * for enabling the clock.
+ */
+static struct clk init_clocks_disable[] = {
+	{
+		.name		= "nand",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+		.enable		= s5p64x0_mem_ctrl,
+		.ctrlbit	= (1 << 2),
+	}, {
+		.name		= "post",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 5)
+	}, {
+		.name		= "2d",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 8),
+	}, {
+		.name		= "hsmmc",
+		.id		= 0,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 17),
+	}, {
+		.name		= "hsmmc",
+		.id		= 1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 18),
+	}, {
+		.name		= "hsmmc",
+		.id		= 2,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 19),
+	}, {
+		.name		= "otg",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 20)
+	}, {
+		.name		= "irom",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 25),
+	}, {
+		.name		= "lcd",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk1_ctrl,
+		.ctrlbit	= (1 << 1),
+	}, {
+		.name		= "hclk_fimgvg",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+		.enable		= s5p64x0_hclk1_ctrl,
+		.ctrlbit	= (1 << 2),
+	}, {
+		.name		= "tsi",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk1_ctrl,
+		.ctrlbit	= (1 << 0),
+	}, {
+		.name		= "watchdog",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 5),
+	}, {
+		.name		= "rtc",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 6),
+	}, {
+		.name		= "timers",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 7),
+	}, {
+		.name		= "pcm",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 8),
+	}, {
+		.name		= "adc",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 12),
+	}, {
+		.name		= "i2c",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 17),
+	}, {
+		.name		= "spi",
+		.id		= 0,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 21),
+	}, {
+		.name		= "spi",
+		.id		= 1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 22),
+	}, {
+		.name		= "gps",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 25),
+	}, {
+		.name		= "i2s_v40",
+		.id		= 0,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 26),
+	}, {
+		.name		= "dsim",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 28),
+	}, {
+		.name		= "etm",
+		.id		= -1,
+		.parent		= &clk_pclk.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 29),
+	}, {
+		.name		= "dmc0",
+		.id		= -1,
+		.parent		= &clk_pclk.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 30),
+	}, {
+		.name		= "pclk_fimgvg",
+		.id		= -1,
+		.parent		= &clk_pclk.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 31),
+	}, {
+		.name		= "sclk_spi_48",
+		.id		= 0,
+		.parent		= &clk_48m,
+		.enable		= s5p64x0_sclk_ctrl,
+		.ctrlbit	= (1 << 22),
+	}, {
+		.name		= "sclk_spi_48",
+		.id		= 1,
+		.parent		= &clk_48m,
+		.enable		= s5p64x0_sclk_ctrl,
+		.ctrlbit	= (1 << 23),
+	}, {
+		.name		= "mmc_48m",
+		.id		= 0,
+		.parent		= &clk_48m,
+		.enable		= s5p64x0_sclk_ctrl,
+		.ctrlbit	= (1 << 27),
+	}, {
+		.name		= "mmc_48m",
+		.id		= 1,
+		.parent		= &clk_48m,
+		.enable		= s5p64x0_sclk_ctrl,
+		.ctrlbit	= (1 << 28),
+	}, {
+		.name		= "mmc_48m",
+		.id		= 2,
+		.parent		= &clk_48m,
+		.enable		= s5p64x0_sclk_ctrl,
+		.ctrlbit	= (1 << 29),
+	},
+};
+
+/*
+ * The following clocks will be enabled during clock initialization.
+ */
+static struct clk init_clocks[] = {
+	{
+		.name		= "intc",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 1),
+	}, {
+		.name		= "mem",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 21),
+	}, {
+		.name		= "dma",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 12),
+	}, {
+		.name		= "uart",
+		.id		= 0,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 1),
+	}, {
+		.name		= "uart",
+		.id		= 1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 2),
+	}, {
+		.name		= "uart",
+		.id		= 2,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 3),
+	}, {
+		.name		= "uart",
+		.id		= 3,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 4),
+	}, {
+		.name		= "gpio",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 18),
+	},
+};
+
+static struct clk clk_iis_cd_v40 = {
+	.name		= "iis_cdclk_v40",
+	.id		= -1,
+};
+
+static struct clk clk_pcm_cd = {
+	.name		= "pcm_cdclk",
+	.id		= -1,
+};
+
+static struct clk *clkset_group1_list[] = {
+	&clk_mout_epll.clk,
+	&clk_dout_mpll.clk,
+	&clk_fin_epll,
+};
+
+static struct clksrc_sources clkset_group1 = {
+	.sources	= clkset_group1_list,
+	.nr_sources	= ARRAY_SIZE(clkset_group1_list),
+};
+
+static struct clk *clkset_uart_list[] = {
+	&clk_mout_epll.clk,
+	&clk_dout_mpll.clk,
+};
+
+static struct clksrc_sources clkset_uart = {
+	.sources	= clkset_uart_list,
+	.nr_sources	= ARRAY_SIZE(clkset_uart_list),
+};
+
+static struct clk *clkset_audio_list[] = {
+	&clk_mout_epll.clk,
+	&clk_dout_mpll.clk,
+	&clk_fin_epll,
+	&clk_iis_cd_v40,
+	&clk_pcm_cd,
+};
+
+static struct clksrc_sources clkset_audio = {
+	.sources	= clkset_audio_list,
+	.nr_sources	= ARRAY_SIZE(clkset_audio_list),
+};
+
+static struct clksrc_clk clksrcs[] = {
+	{
+		.clk	= {
+			.name		= "mmc_bus",
+			.id		= 0,
+			.ctrlbit	= (1 << 24),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group1,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 18, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 0, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "mmc_bus",
+			.id		= 1,
+			.ctrlbit	= (1 << 25),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group1,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 20, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 4, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "mmc_bus",
+			.id		= 2,
+			.ctrlbit	= (1 << 26),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group1,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 22, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 8, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "uclk1",
+			.id		= -1,
+			.ctrlbit	= (1 << 5),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_uart,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 13, .size = 1 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV2, .shift = 16, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_spi",
+			.id		= 0,
+			.ctrlbit	= (1 << 20),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group1,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 14, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV2, .shift = 0, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_spi",
+			.id		= 1,
+			.ctrlbit	= (1 << 21),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group1,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 16, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV2, .shift = 4, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_post",
+			.id		= -1,
+			.ctrlbit	= (1 << 10),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group1,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 26, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 12, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_dispcon",
+			.id		= -1,
+			.ctrlbit	= (1 << 1),
+			.enable		= s5p64x0_sclk1_ctrl,
+		},
+		.sources = &clkset_group1,
+		.reg_src = { .reg = S5P64X0_CLK_SRC1, .shift = 4, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV3, .shift = 0, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_fimgvg",
+			.id		= -1,
+			.ctrlbit	= (1 << 2),
+			.enable		= s5p64x0_sclk1_ctrl,
+		},
+		.sources = &clkset_group1,
+		.reg_src = { .reg = S5P64X0_CLK_SRC1, .shift = 8, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV3, .shift = 4, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_audio2",
+			.id		= -1,
+			.ctrlbit	= (1 << 11),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_audio,
+		.reg_src = { .reg = S5P64X0_CLK_SRC1, .shift = 0, .size = 3 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV2, .shift = 24, .size = 4 },
+	},
+};
+
+/* Clock initialization code */
+static struct clksrc_clk *sysclks[] = {
+	&clk_mout_apll,
+	&clk_mout_epll,
+	&clk_mout_mpll,
+	&clk_dout_mpll,
+	&clk_armclk,
+	&clk_hclk,
+	&clk_pclk,
+	&clk_hclk_low,
+	&clk_pclk_low,
+};
+
+void __init_or_cpufreq s5p6440_setup_clocks(void)
+{
+	struct clk *xtal_clk;
+
+	unsigned long xtal;
+	unsigned long fclk;
+	unsigned long hclk;
+	unsigned long hclk_low;
+	unsigned long pclk;
+	unsigned long pclk_low;
+
+	unsigned long apll;
+	unsigned long mpll;
+	unsigned long epll;
+	unsigned int ptr;
+
+	/* Set S5P6440 functions for clk_fout_epll */
+
+	clk_fout_epll.enable = s5p64x0_epll_enable;
+	clk_fout_epll.ops = &s5p6440_epll_ops;
+
+	clk_48m.enable = s5p64x0_clk48m_ctrl;
+
+	xtal_clk = clk_get(NULL, "ext_xtal");
+	BUG_ON(IS_ERR(xtal_clk));
+
+	xtal = clk_get_rate(xtal_clk);
+	clk_put(xtal_clk);
+
+	apll = s5p_get_pll45xx(xtal, __raw_readl(S5P64X0_APLL_CON), pll_4502);
+	mpll = s5p_get_pll45xx(xtal, __raw_readl(S5P64X0_MPLL_CON), pll_4502);
+	epll = s5p_get_pll90xx(xtal, __raw_readl(S5P64X0_EPLL_CON),
+				__raw_readl(S5P64X0_EPLL_CON_K));
+
+	clk_fout_apll.rate = apll;
+	clk_fout_mpll.rate = mpll;
+	clk_fout_epll.rate = epll;
+
+	printk(KERN_INFO "S5P6440: PLL settings, A=%ld.%ldMHz, M=%ld.%ldMHz," \
+			" E=%ld.%ldMHz\n",
+			print_mhz(apll), print_mhz(mpll), print_mhz(epll));
+
+	fclk = clk_get_rate(&clk_armclk.clk);
+	hclk = clk_get_rate(&clk_hclk.clk);
+	pclk = clk_get_rate(&clk_pclk.clk);
+	hclk_low = clk_get_rate(&clk_hclk_low.clk);
+	pclk_low = clk_get_rate(&clk_pclk_low.clk);
+
+	printk(KERN_INFO "S5P6440: HCLK=%ld.%ldMHz, HCLK_LOW=%ld.%ldMHz," \
+			" PCLK=%ld.%ldMHz, PCLK_LOW=%ld.%ldMHz\n",
+			print_mhz(hclk), print_mhz(hclk_low),
+			print_mhz(pclk), print_mhz(pclk_low));
+
+	clk_f.rate = fclk;
+	clk_h.rate = hclk;
+	clk_p.rate = pclk;
+
+	for (ptr = 0; ptr < ARRAY_SIZE(clksrcs); ptr++)
+		s3c_set_clksrc(&clksrcs[ptr], true);
+}
+
+static struct clk *clks[] __initdata = {
+	&clk_ext,
+	&clk_iis_cd_v40,
+	&clk_pcm_cd,
+};
+
+void __init s5p6440_register_clocks(void)
+{
+	struct clk *clkp;
+	int ret;
+	int ptr;
+
+	s3c24xx_register_clocks(clks, ARRAY_SIZE(clks));
+
+	for (ptr = 0; ptr < ARRAY_SIZE(sysclks); ptr++)
+		s3c_register_clksrc(sysclks[ptr], 1);
+
+	s3c_register_clksrc(clksrcs, ARRAY_SIZE(clksrcs));
+	s3c_register_clocks(init_clocks, ARRAY_SIZE(init_clocks));
+
+	clkp = init_clocks_disable;
+	for (ptr = 0; ptr < ARRAY_SIZE(init_clocks_disable); ptr++, clkp++) {
+
+		ret = s3c24xx_register_clock(clkp);
+		if (ret < 0) {
+			printk(KERN_ERR "Failed to register clock %s (%d)\n",
+			       clkp->name, ret);
+		}
+		(clkp->enable)(clkp, 0);
+	}
+
+	s3c_pwmclk_init();
+}
diff --git a/arch/arm/mach-s5p64x0/clock-s5p6450.c b/arch/arm/mach-s5p64x0/clock-s5p6450.c
new file mode 100644
index 0000000..f9afb05
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/clock-s5p6450.c
@@ -0,0 +1,655 @@
+/* linux/arch/arm/mach-s5p64x0/clock-s5p6450.c
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P6450 - Clock support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/sysdev.h>
+#include <linux/io.h>
+
+#include <mach/hardware.h>
+#include <mach/map.h>
+#include <mach/regs-clock.h>
+#include <mach/s5p64x0-clock.h>
+
+#include <plat/cpu-freq.h>
+#include <plat/clock.h>
+#include <plat/cpu.h>
+#include <plat/pll.h>
+#include <plat/s5p-clock.h>
+#include <plat/clock-clksrc.h>
+#include <plat/s5p6450.h>
+
+static struct clksrc_clk clk_mout_dpll = {
+	.clk	= {
+		.name		= "mout_dpll",
+		.id		= -1,
+	},
+	.sources	= &clk_src_dpll,
+	.reg_src	= { .reg = S5P64X0_CLK_SRC0, .shift = 5, .size = 1 },
+};
+
+static u32 epll_div[][5] = {
+	{ 133000000,	27307,	55, 2, 2 },
+	{ 100000000,	43691,	41, 2, 2 },
+	{ 480000000,	0,	80, 2, 0 },
+};
+
+static int s5p6450_epll_set_rate(struct clk *clk, unsigned long rate)
+{
+	unsigned int epll_con, epll_con_k;
+	unsigned int i;
+
+	if (clk->rate == rate)	/* Return if nothing changed */
+		return 0;
+
+	epll_con = __raw_readl(S5P64X0_EPLL_CON);
+	epll_con_k = __raw_readl(S5P64X0_EPLL_CON_K);
+
+	epll_con_k &= ~(PLL90XX_KDIV_MASK);
+	epll_con &= ~(PLL90XX_MDIV_MASK | PLL90XX_PDIV_MASK | PLL90XX_SDIV_MASK);
+
+	for (i = 0; i < ARRAY_SIZE(epll_div); i++) {
+		 if (epll_div[i][0] == rate) {
+			epll_con_k |= (epll_div[i][1] << PLL90XX_KDIV_SHIFT);
+			epll_con |= (epll_div[i][2] << PLL90XX_MDIV_SHIFT) |
+				    (epll_div[i][3] << PLL90XX_PDIV_SHIFT) |
+				    (epll_div[i][4] << PLL90XX_SDIV_SHIFT);
+			break;
+		}
+	}
+
+	if (i == ARRAY_SIZE(epll_div)) {
+		printk(KERN_ERR "%s: Invalid Clock EPLL Frequency\n", __func__);
+		return -EINVAL;
+	}
+
+	__raw_writel(epll_con, S5P64X0_EPLL_CON);
+	__raw_writel(epll_con_k, S5P64X0_EPLL_CON_K);
+
+	clk->rate = rate;
+
+	return 0;
+}
+
+static struct clk_ops s5p6450_epll_ops = {
+	.get_rate = s5p64x0_epll_get_rate,
+	.set_rate = s5p6450_epll_set_rate,
+};
+
+static struct clksrc_clk clk_dout_epll = {
+	.clk	= {
+		.name		= "dout_epll",
+		.id		= -1,
+		.parent		= &clk_mout_epll.clk,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV1, .shift = 24, .size = 4 },
+};
+
+static struct clksrc_clk clk_mout_hclk_sel = {
+	.clk	= {
+		.name		= "mout_hclk_sel",
+		.id		= -1,
+	},
+	.sources	= &clkset_hclk_low,
+	.reg_src	= { .reg = S5P64X0_OTHERS, .shift = 15, .size = 1 },
+};
+
+static struct clk *clkset_hclk_list[] = {
+	&clk_mout_hclk_sel.clk,
+	&clk_armclk.clk,
+};
+
+static struct clksrc_sources clkset_hclk = {
+	.sources	= clkset_hclk_list,
+	.nr_sources	= ARRAY_SIZE(clkset_hclk_list),
+};
+
+static struct clksrc_clk clk_hclk = {
+	.clk	= {
+		.name		= "clk_hclk",
+		.id		= -1,
+	},
+	.sources	= &clkset_hclk,
+	.reg_src	= { .reg = S5P64X0_OTHERS, .shift = 14, .size = 1 },
+	.reg_div	= { .reg = S5P64X0_CLK_DIV0, .shift = 8, .size = 4 },
+};
+
+static struct clksrc_clk clk_pclk = {
+	.clk	= {
+		.name		= "clk_pclk",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+	},
+	.reg_div = { .reg = S5P64X0_CLK_DIV0, .shift = 12, .size = 4 },
+};
+static struct clksrc_clk clk_dout_pwm_ratio0 = {
+	.clk	= {
+		.name		= "clk_dout_pwm_ratio0",
+		.id		= -1,
+		.parent		= &clk_mout_hclk_sel.clk,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV3, .shift = 16, .size = 4 },
+};
+
+static struct clksrc_clk clk_pclk_to_wdt_pwm = {
+	.clk	= {
+		.name		= "clk_pclk_to_wdt_pwm",
+		.id		= -1,
+		.parent		= &clk_dout_pwm_ratio0.clk,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV3, .shift = 20, .size = 4 },
+};
+
+static struct clksrc_clk clk_hclk_low = {
+	.clk	= {
+		.name		= "clk_hclk_low",
+		.id		= -1,
+	},
+	.sources	= &clkset_hclk_low,
+	.reg_src	= { .reg = S5P64X0_OTHERS, .shift = 6, .size = 1 },
+	.reg_div	= { .reg = S5P64X0_CLK_DIV3, .shift = 8, .size = 4 },
+};
+
+static struct clksrc_clk clk_pclk_low = {
+	.clk	= {
+		.name		= "clk_pclk_low",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV3, .shift = 12, .size = 4 },
+};
+
+/*
+ * The following clocks will be disabled during clock initialization. It is
+ * recommended to keep the following clocks disabled until the driver requests
+ * for enabling the clock.
+ */
+static struct clk init_clocks_disable[] = {
+	{
+		.name		= "usbhost",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 3),
+	}, {
+		.name		= "hsmmc",
+		.id		= 0,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 17),
+	}, {
+		.name		= "hsmmc",
+		.id		= 1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 18),
+	}, {
+		.name		= "hsmmc",
+		.id		= 2,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 19),
+	}, {
+		.name		= "usbotg",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 20),
+	}, {
+		.name		= "lcd",
+		.id		= -1,
+		.parent		= &clk_h,
+		.enable		= s5p64x0_hclk1_ctrl,
+		.ctrlbit	= (1 << 1),
+	}, {
+		.name		= "watchdog",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 5),
+	}, {
+		.name		= "adc",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 12),
+	}, {
+		.name		= "i2c",
+		.id		= 0,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 17),
+	}, {
+		.name		= "spi",
+		.id		= 0,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 21),
+	}, {
+		.name		= "spi",
+		.id		= 1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 22),
+	}, {
+		.name		= "iis",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 26),
+	}, {
+		.name		= "i2c",
+		.id		= 1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 27),
+	}, {
+		.name		= "dmc0",
+		.id		= -1,
+		.parent		= &clk_pclk.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 30),
+	}
+};
+
+/*
+ * The following clocks will be enabled during clock initialization.
+ */
+static struct clk init_clocks[] = {
+	{
+		.name		= "intc",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 1),
+	}, {
+		.name		= "mem",
+		.id		= -1,
+		.parent		= &clk_hclk.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 21),
+	}, {
+		.name		= "dma",
+		.id		= -1,
+		.parent		= &clk_hclk_low.clk,
+		.enable		= s5p64x0_hclk0_ctrl,
+		.ctrlbit	= (1 << 12),
+	}, {
+		.name		= "uart",
+		.id		= 0,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 1),
+	}, {
+		.name		= "uart",
+		.id		= 1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 2),
+	}, {
+		.name		= "uart",
+		.id		= 2,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 3),
+	}, {
+		.name		= "uart",
+		.id		= 3,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 4),
+	}, {
+		.name		= "timers",
+		.id		= -1,
+		.parent		= &clk_pclk_to_wdt_pwm.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 7),
+	}, {
+		.name		= "gpio",
+		.id		= -1,
+		.parent		= &clk_pclk_low.clk,
+		.enable		= s5p64x0_pclk_ctrl,
+		.ctrlbit	= (1 << 18),
+	},
+};
+
+static struct clk *clkset_uart_list[] = {
+	&clk_dout_epll.clk,
+	&clk_dout_mpll.clk,
+};
+
+static struct clksrc_sources clkset_uart = {
+	.sources	= clkset_uart_list,
+	.nr_sources	= ARRAY_SIZE(clkset_uart_list),
+};
+
+static struct clk *clkset_mali_list[] = {
+	&clk_mout_epll.clk,
+	&clk_mout_apll.clk,
+	&clk_mout_mpll.clk,
+};
+
+static struct clksrc_sources clkset_mali = {
+	.sources	= clkset_mali_list,
+	.nr_sources	= ARRAY_SIZE(clkset_mali_list),
+};
+
+static struct clk *clkset_group2_list[] = {
+	&clk_dout_epll.clk,
+	&clk_dout_mpll.clk,
+	&clk_ext_xtal_mux,
+};
+
+static struct clksrc_sources clkset_group2 = {
+	.sources	= clkset_group2_list,
+	.nr_sources	= ARRAY_SIZE(clkset_group2_list),
+};
+
+static struct clk *clkset_dispcon_list[] = {
+	&clk_dout_epll.clk,
+	&clk_dout_mpll.clk,
+	&clk_ext_xtal_mux,
+	&clk_mout_dpll.clk,
+};
+
+static struct clksrc_sources clkset_dispcon = {
+	.sources	= clkset_dispcon_list,
+	.nr_sources	= ARRAY_SIZE(clkset_dispcon_list),
+};
+
+static struct clk *clkset_hsmmc44_list[] = {
+	&clk_dout_epll.clk,
+	&clk_dout_mpll.clk,
+	&clk_ext_xtal_mux,
+	&s5p_clk_27m,
+	&clk_48m,
+};
+
+static struct clksrc_sources clkset_hsmmc44 = {
+	.sources	= clkset_hsmmc44_list,
+	.nr_sources	= ARRAY_SIZE(clkset_hsmmc44_list),
+};
+
+static struct clk *clkset_sclk_audio0_list[] = {
+	[0] = &clk_dout_epll.clk,
+	[1] = &clk_dout_mpll.clk,
+	[2] = &clk_ext_xtal_mux,
+	[3] = NULL,
+	[4] = NULL,
+};
+
+static struct clksrc_sources clkset_sclk_audio0 = {
+	.sources	= clkset_sclk_audio0_list,
+	.nr_sources	= ARRAY_SIZE(clkset_sclk_audio0_list),
+};
+
+static struct clksrc_clk clk_sclk_audio0 = {
+	.clk		= {
+		.name		= "audio-bus",
+		.id		= -1,
+		.enable		= s5p64x0_sclk_ctrl,
+		.ctrlbit	= (1 << 8),
+		.parent		= &clk_dout_epll.clk,
+	},
+	.sources	= &clkset_sclk_audio0,
+	.reg_src	= { .reg = S5P64X0_CLK_SRC1, .shift = 10, .size = 3 },
+	.reg_div	= { .reg = S5P64X0_CLK_DIV2, .shift = 8, .size = 4 },
+};
+
+static struct clksrc_clk clksrcs[] = {
+	{
+		.clk	= {
+			.name		= "sclk_mmc",
+			.id		= 0,
+			.ctrlbit	= (1 << 24),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group2,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 18, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 0, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_mmc",
+			.id		= 1,
+			.ctrlbit	= (1 << 25),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group2,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 20, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 4, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_mmc",
+			.id		= 2,
+			.ctrlbit	= (1 << 26),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group2,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 22, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 8, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "uclk1",
+			.id		= -1,
+			.ctrlbit	= (1 << 5),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_uart,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 13, .size = 1 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV2, .shift = 16, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_spi",
+			.id		= 0,
+			.ctrlbit	= (1 << 20),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group2,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 14, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV2, .shift = 0, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_spi",
+			.id		= 1,
+			.ctrlbit	= (1 << 21),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group2,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 16, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV2, .shift = 4, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_fimc",
+			.id		= -1,
+			.ctrlbit	= (1 << 10),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group2,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 26, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 12, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "aclk_mali",
+			.id		= -1,
+			.ctrlbit	= (1 << 2),
+			.enable		= s5p64x0_sclk1_ctrl,
+		},
+		.sources = &clkset_mali,
+		.reg_src = { .reg = S5P64X0_CLK_SRC1, .shift = 8, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV3, .shift = 4, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_2d",
+			.id		= -1,
+			.ctrlbit	= (1 << 12),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_mali,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 30, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV2, .shift = 20, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_usi",
+			.id		= -1,
+			.ctrlbit	= (1 << 7),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group2,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 10, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 16, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_camif",
+			.id		= -1,
+			.ctrlbit	= (1 << 6),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_group2,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 28, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 20, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_dispcon",
+			.id		= -1,
+			.ctrlbit	= (1 << 1),
+			.enable		= s5p64x0_sclk1_ctrl,
+		},
+		.sources = &clkset_dispcon,
+		.reg_src = { .reg = S5P64X0_CLK_SRC1, .shift = 4, .size = 2 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV3, .shift = 0, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_hsmmc44",
+			.id		= -1,
+			.ctrlbit	= (1 << 30),
+			.enable		= s5p64x0_sclk_ctrl,
+		},
+		.sources = &clkset_hsmmc44,
+		.reg_src = { .reg = S5P64X0_CLK_SRC0, .shift = 6, .size = 3 },
+		.reg_div = { .reg = S5P64X0_CLK_DIV1, .shift = 28, .size = 4 },
+	},
+};
+
+/* Clock initialization code */
+static struct clksrc_clk *sysclks[] = {
+	&clk_mout_apll,
+	&clk_mout_epll,
+	&clk_dout_epll,
+	&clk_mout_mpll,
+	&clk_dout_mpll,
+	&clk_armclk,
+	&clk_mout_hclk_sel,
+	&clk_dout_pwm_ratio0,
+	&clk_pclk_to_wdt_pwm,
+	&clk_hclk,
+	&clk_pclk,
+	&clk_hclk_low,
+	&clk_pclk_low,
+	&clk_sclk_audio0,
+};
+
+void __init_or_cpufreq s5p6450_setup_clocks(void)
+{
+	struct clk *xtal_clk;
+
+	unsigned long xtal;
+	unsigned long fclk;
+	unsigned long hclk;
+	unsigned long hclk_low;
+	unsigned long pclk;
+	unsigned long pclk_low;
+
+	unsigned long apll;
+	unsigned long mpll;
+	unsigned long epll;
+	unsigned long dpll;
+	unsigned int ptr;
+
+	/* Set S5P6450 functions for clk_fout_epll */
+
+	clk_fout_epll.enable = s5p64x0_epll_enable;
+	clk_fout_epll.ops = &s5p6450_epll_ops;
+
+	clk_48m.enable = s5p64x0_clk48m_ctrl;
+
+	xtal_clk = clk_get(NULL, "ext_xtal");
+	BUG_ON(IS_ERR(xtal_clk));
+
+	xtal = clk_get_rate(xtal_clk);
+	clk_put(xtal_clk);
+
+	apll = s5p_get_pll45xx(xtal, __raw_readl(S5P64X0_APLL_CON), pll_4502);
+	mpll = s5p_get_pll45xx(xtal, __raw_readl(S5P64X0_MPLL_CON), pll_4502);
+	epll = s5p_get_pll90xx(xtal, __raw_readl(S5P64X0_EPLL_CON),
+				__raw_readl(S5P64X0_EPLL_CON_K));
+	dpll = s5p_get_pll46xx(xtal, __raw_readl(S5P6450_DPLL_CON),
+				__raw_readl(S5P6450_DPLL_CON_K), pll_4650c);
+
+	clk_fout_apll.rate = apll;
+	clk_fout_mpll.rate = mpll;
+	clk_fout_epll.rate = epll;
+	clk_fout_dpll.rate = dpll;
+
+	printk(KERN_INFO "S5P6450: PLL settings, A=%ld.%ldMHz, M=%ld.%ldMHz," \
+			" E=%ld.%ldMHz, D=%ld.%ldMHz\n",
+			print_mhz(apll), print_mhz(mpll), print_mhz(epll),
+			print_mhz(dpll));
+
+	fclk = clk_get_rate(&clk_armclk.clk);
+	hclk = clk_get_rate(&clk_hclk.clk);
+	pclk = clk_get_rate(&clk_pclk.clk);
+	hclk_low = clk_get_rate(&clk_hclk_low.clk);
+	pclk_low = clk_get_rate(&clk_pclk_low.clk);
+
+	printk(KERN_INFO "S5P6450: HCLK=%ld.%ldMHz, HCLK_LOW=%ld.%ldMHz," \
+			" PCLK=%ld.%ldMHz, PCLK_LOW=%ld.%ldMHz\n",
+			print_mhz(hclk), print_mhz(hclk_low),
+			print_mhz(pclk), print_mhz(pclk_low));
+
+	clk_f.rate = fclk;
+	clk_h.rate = hclk;
+	clk_p.rate = pclk;
+
+	for (ptr = 0; ptr < ARRAY_SIZE(clksrcs); ptr++)
+		s3c_set_clksrc(&clksrcs[ptr], true);
+}
+
+void __init s5p6450_register_clocks(void)
+{
+	struct clk *clkp;
+	int ret;
+	int ptr;
+
+	for (ptr = 0; ptr < ARRAY_SIZE(sysclks); ptr++)
+		s3c_register_clksrc(sysclks[ptr], 1);
+
+	s3c_register_clksrc(clksrcs, ARRAY_SIZE(clksrcs));
+	s3c_register_clocks(init_clocks, ARRAY_SIZE(init_clocks));
+
+	clkp = init_clocks_disable;
+	for (ptr = 0; ptr < ARRAY_SIZE(init_clocks_disable); ptr++, clkp++) {
+
+		ret = s3c24xx_register_clock(clkp);
+		if (ret < 0) {
+			printk(KERN_ERR "Failed to register clock %s (%d)\n",
+			       clkp->name, ret);
+		}
+		(clkp->enable)(clkp, 0);
+	}
+
+	s3c_pwmclk_init();
+}
diff --git a/arch/arm/mach-s5p64x0/clock.c b/arch/arm/mach-s5p64x0/clock.c
new file mode 100644
index 0000000..523ba80
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/clock.c
@@ -0,0 +1,253 @@
+/* linux/arch/arm/mach-s5p64x0/clock.c
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P64X0 - Clock support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/sysdev.h>
+#include <linux/io.h>
+
+#include <mach/hardware.h>
+#include <mach/map.h>
+#include <mach/regs-clock.h>
+
+#include <plat/cpu-freq.h>
+#include <plat/clock.h>
+#include <plat/cpu.h>
+#include <plat/pll.h>
+#include <plat/s5p-clock.h>
+#include <plat/clock-clksrc.h>
+#include <plat/s5p6440.h>
+#include <plat/s5p6450.h>
+
+struct clksrc_clk clk_mout_apll = {
+	.clk	= {
+		.name		= "mout_apll",
+		.id		= -1,
+	},
+	.sources	= &clk_src_apll,
+	.reg_src	= { .reg = S5P64X0_CLK_SRC0, .shift = 0, .size = 1 },
+};
+
+struct clksrc_clk clk_mout_mpll = {
+	.clk	= {
+		.name		= "mout_mpll",
+		.id		= -1,
+	},
+	.sources	= &clk_src_mpll,
+	.reg_src	= { .reg = S5P64X0_CLK_SRC0, .shift = 1, .size = 1 },
+};
+
+struct clksrc_clk clk_mout_epll = {
+	.clk	= {
+		.name		= "mout_epll",
+		.id		= -1,
+	},
+	.sources	= &clk_src_epll,
+	.reg_src	= { .reg = S5P64X0_CLK_SRC0, .shift = 2, .size = 1 },
+};
+
+enum perf_level {
+	L0 = 532*1000,
+	L1 = 266*1000,
+	L2 = 133*1000,
+};
+
+static const u32 clock_table[][3] = {
+	/*{ARM_CLK, DIVarm, DIVhclk}*/
+	{L0 * 1000, (0 << ARM_DIV_RATIO_SHIFT), (3 << S5P64X0_CLKDIV0_HCLK_SHIFT)},
+	{L1 * 1000, (1 << ARM_DIV_RATIO_SHIFT), (1 << S5P64X0_CLKDIV0_HCLK_SHIFT)},
+	{L2 * 1000, (3 << ARM_DIV_RATIO_SHIFT), (0 << S5P64X0_CLKDIV0_HCLK_SHIFT)},
+};
+
+int s5p64x0_epll_enable(struct clk *clk, int enable)
+{
+	unsigned int ctrlbit = clk->ctrlbit;
+	unsigned int epll_con = __raw_readl(S5P64X0_EPLL_CON) & ~ctrlbit;
+
+	if (enable)
+		__raw_writel(epll_con | ctrlbit, S5P64X0_EPLL_CON);
+	else
+		__raw_writel(epll_con, S5P64X0_EPLL_CON);
+
+	return 0;
+}
+
+unsigned long s5p64x0_epll_get_rate(struct clk *clk)
+{
+	return clk->rate;
+}
+
+unsigned long s5p64x0_armclk_get_rate(struct clk *clk)
+{
+	unsigned long rate = clk_get_rate(clk->parent);
+	u32 clkdiv;
+
+	/* divisor mask starts at bit0, so no need to shift */
+	clkdiv = __raw_readl(ARM_CLK_DIV) & ARM_DIV_MASK;
+
+	return rate / (clkdiv + 1);
+}
+
+unsigned long s5p64x0_armclk_round_rate(struct clk *clk, unsigned long rate)
+{
+	u32 iter;
+
+	for (iter = 1 ; iter < ARRAY_SIZE(clock_table) ; iter++) {
+		if (rate > clock_table[iter][0])
+			return clock_table[iter-1][0];
+	}
+
+	return clock_table[ARRAY_SIZE(clock_table) - 1][0];
+}
+
+int s5p64x0_armclk_set_rate(struct clk *clk, unsigned long rate)
+{
+	u32 round_tmp;
+	u32 iter;
+	u32 clk_div0_tmp;
+	u32 cur_rate = clk->ops->get_rate(clk);
+	unsigned long flags;
+
+	round_tmp = clk->ops->round_rate(clk, rate);
+	if (round_tmp == cur_rate)
+		return 0;
+
+
+	for (iter = 0 ; iter < ARRAY_SIZE(clock_table) ; iter++) {
+		if (round_tmp == clock_table[iter][0])
+			break;
+	}
+
+	if (iter >= ARRAY_SIZE(clock_table))
+		iter = ARRAY_SIZE(clock_table) - 1;
+
+	local_irq_save(flags);
+	if (cur_rate > round_tmp) {
+		/* Frequency Down */
+		clk_div0_tmp = __raw_readl(ARM_CLK_DIV) & ~(ARM_DIV_MASK);
+		clk_div0_tmp |= clock_table[iter][1];
+		__raw_writel(clk_div0_tmp, ARM_CLK_DIV);
+
+		clk_div0_tmp = __raw_readl(ARM_CLK_DIV) &
+				~(S5P64X0_CLKDIV0_HCLK_MASK);
+		clk_div0_tmp |= clock_table[iter][2];
+		__raw_writel(clk_div0_tmp, ARM_CLK_DIV);
+
+
+	} else {
+		/* Frequency Up */
+		clk_div0_tmp = __raw_readl(ARM_CLK_DIV) &
+				~(S5P64X0_CLKDIV0_HCLK_MASK);
+		clk_div0_tmp |= clock_table[iter][2];
+		__raw_writel(clk_div0_tmp, ARM_CLK_DIV);
+
+		clk_div0_tmp = __raw_readl(ARM_CLK_DIV) & ~(ARM_DIV_MASK);
+		clk_div0_tmp |= clock_table[iter][1];
+		__raw_writel(clk_div0_tmp, ARM_CLK_DIV);
+	}
+	local_irq_restore(flags);
+
+	clk->rate = clock_table[iter][0];
+
+	return 0;
+}
+
+struct clk_ops s5p64x0_clkarm_ops = {
+	.get_rate	= s5p64x0_armclk_get_rate,
+	.set_rate	= s5p64x0_armclk_set_rate,
+	.round_rate	= s5p64x0_armclk_round_rate,
+};
+
+struct clksrc_clk clk_armclk = {
+	.clk	= {
+		.name		= "armclk",
+		.id		= 1,
+		.parent		= &clk_mout_apll.clk,
+		.ops		= &s5p64x0_clkarm_ops,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV0, .shift = 0, .size = 4 },
+};
+
+struct clksrc_clk clk_dout_mpll = {
+	.clk	= {
+		.name		= "dout_mpll",
+		.id		= -1,
+		.parent		= &clk_mout_mpll.clk,
+	},
+	.reg_div	= { .reg = S5P64X0_CLK_DIV0, .shift = 4, .size = 1 },
+};
+
+struct clk *clkset_hclk_low_list[] = {
+	&clk_mout_apll.clk,
+	&clk_mout_mpll.clk,
+};
+
+struct clksrc_sources clkset_hclk_low = {
+	.sources	= clkset_hclk_low_list,
+	.nr_sources	= ARRAY_SIZE(clkset_hclk_low_list),
+};
+
+int s5p64x0_pclk_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(S5P64X0_CLK_GATE_PCLK, clk, enable);
+}
+
+int s5p64x0_hclk0_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(S5P64X0_CLK_GATE_HCLK0, clk, enable);
+}
+
+int s5p64x0_hclk1_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(S5P64X0_CLK_GATE_HCLK1, clk, enable);
+}
+
+int s5p64x0_sclk_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(S5P64X0_CLK_GATE_SCLK0, clk, enable);
+}
+
+int s5p64x0_sclk1_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(S5P64X0_CLK_GATE_SCLK1, clk, enable);
+}
+
+int s5p64x0_mem_ctrl(struct clk *clk, int enable)
+{
+	return s5p_gatectrl(S5P64X0_CLK_GATE_MEM0, clk, enable);
+}
+
+int s5p64x0_clk48m_ctrl(struct clk *clk, int enable)
+{
+	unsigned long flags;
+	u32 val;
+
+	/* can't rely on clock lock, this register has other usages */
+	local_irq_save(flags);
+
+	val = __raw_readl(S5P64X0_OTHERS);
+	if (enable)
+		val |= S5P64X0_OTHERS_USB_SIG_MASK;
+	else
+		val &= ~S5P64X0_OTHERS_USB_SIG_MASK;
+
+	__raw_writel(val, S5P64X0_OTHERS);
+
+	local_irq_restore(flags);
+
+	return 0;
+}
diff --git a/arch/arm/mach-s5p64x0/cpu.c b/arch/arm/mach-s5p64x0/cpu.c
new file mode 100644
index 0000000..b8d02eb
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/cpu.c
@@ -0,0 +1,209 @@
+/* linux/arch/arm/mach-s5p64x0/cpu.c
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/timer.h>
+#include <linux/init.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/sysdev.h>
+#include <linux/serial_core.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/mach/irq.h>
+#include <asm/proc-fns.h>
+#include <asm/irq.h>
+
+#include <mach/hardware.h>
+#include <mach/map.h>
+#include <mach/regs-clock.h>
+
+#include <plat/regs-serial.h>
+#include <plat/cpu.h>
+#include <plat/devs.h>
+#include <plat/clock.h>
+#include <plat/s5p6440.h>
+#include <plat/s5p6450.h>
+#include <plat/adc-core.h>
+
+/* Initial IO mappings */
+
+static struct map_desc s5p64x0_iodesc[] __initdata = {
+	{
+		.virtual	= (unsigned long)S5P_VA_GPIO,
+		.pfn		= __phys_to_pfn(S5P64X0_PA_GPIO),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)VA_VIC0,
+		.pfn		= __phys_to_pfn(S5P64X0_PA_VIC0),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)VA_VIC1,
+		.pfn		= __phys_to_pfn(S5P64X0_PA_VIC1),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	},
+};
+
+static struct map_desc s5p6440_iodesc[] __initdata = {
+	{
+		.virtual	= (unsigned long)S3C_VA_UART,
+		.pfn		= __phys_to_pfn(S5P6440_PA_UART(0)),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	},
+};
+
+static struct map_desc s5p6450_iodesc[] __initdata = {
+	{
+		.virtual	= (unsigned long)S3C_VA_UART,
+		.pfn		= __phys_to_pfn(S5P6450_PA_UART(0)),
+		.length		= SZ_512K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S3C_VA_UART + SZ_512K,
+		.pfn		= __phys_to_pfn(S5P6450_PA_UART(5)),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	},
+};
+
+static void s5p64x0_idle(void)
+{
+	unsigned long val;
+
+	if (!need_resched()) {
+		val = __raw_readl(S5P64X0_PWR_CFG);
+		val &= ~(0x3 << 5);
+		val |= (0x1 << 5);
+		__raw_writel(val, S5P64X0_PWR_CFG);
+
+		cpu_do_idle();
+	}
+	local_irq_enable();
+}
+
+/*
+ * s5p64x0_map_io
+ *
+ * register the standard CPU IO areas
+ */
+
+void __init s5p6440_map_io(void)
+{
+	/* initialize any device information early */
+	s3c_adc_setname("s3c64xx-adc");
+
+	iotable_init(s5p64x0_iodesc, ARRAY_SIZE(s5p64x0_iodesc));
+	iotable_init(s5p6440_iodesc, ARRAY_SIZE(s5p6440_iodesc));
+}
+
+void __init s5p6450_map_io(void)
+{
+	/* initialize any device information early */
+	s3c_adc_setname("s3c64xx-adc");
+
+	iotable_init(s5p64x0_iodesc, ARRAY_SIZE(s5p64x0_iodesc));
+	iotable_init(s5p6450_iodesc, ARRAY_SIZE(s5p6440_iodesc));
+}
+
+/*
+ * s5p64x0_init_clocks
+ *
+ * register and setup the CPU clocks
+ */
+
+void __init s5p6440_init_clocks(int xtal)
+{
+	printk(KERN_DEBUG "%s: initializing clocks\n", __func__);
+
+	s3c24xx_register_baseclocks(xtal);
+	s5p_register_clocks(xtal);
+	s5p6440_register_clocks();
+	s5p6440_setup_clocks();
+}
+
+void __init s5p6450_init_clocks(int xtal)
+{
+	printk(KERN_DEBUG "%s: initializing clocks\n", __func__);
+
+	s3c24xx_register_baseclocks(xtal);
+	s5p_register_clocks(xtal);
+	s5p6450_register_clocks();
+	s5p6450_setup_clocks();
+}
+
+/*
+ * s5p64x0_init_irq
+ *
+ * register the CPU interrupts
+ */
+
+void __init s5p6440_init_irq(void)
+{
+	/* S5P6440 supports 2 VIC */
+	u32 vic[2];
+
+	/*
+	 * VIC0 is missing IRQ_VIC0[3, 4, 8, 10, (12-22)]
+	 * VIC1 is missing IRQ VIC1[1, 3, 4, 10, 11, 12, 14, 15, 22]
+	 */
+	vic[0] = 0xff800ae7;
+	vic[1] = 0xffbf23e5;
+
+	s5p_init_irq(vic, ARRAY_SIZE(vic));
+}
+
+void __init s5p6450_init_irq(void)
+{
+	/* S5P6450 supports only 2 VIC */
+	u32 vic[2];
+
+	/*
+	 * VIC0 is missing IRQ_VIC0[(13-15), (21-22)]
+	 * VIC1 is missing IRQ VIC1[12, 14, 23]
+	 */
+	vic[0] = 0xff9f1fff;
+	vic[1] = 0xff7fafff;
+
+	s5p_init_irq(vic, ARRAY_SIZE(vic));
+}
+
+struct sysdev_class s5p64x0_sysclass = {
+	.name	= "s5p64x0-core",
+};
+
+static struct sys_device s5p64x0_sysdev = {
+	.cls	= &s5p64x0_sysclass,
+};
+
+static int __init s5p64x0_core_init(void)
+{
+	return sysdev_class_register(&s5p64x0_sysclass);
+}
+core_initcall(s5p64x0_core_init);
+
+int __init s5p64x0_init(void)
+{
+	printk(KERN_INFO "S5P64X0(S5P6440/S5P6450): Initializing architecture\n");
+
+	/* set idle function */
+	pm_idle = s5p64x0_idle;
+
+	return sysdev_register(&s5p64x0_sysdev);
+}
diff --git a/arch/arm/mach-s5p64x0/dev-audio.c b/arch/arm/mach-s5p64x0/dev-audio.c
new file mode 100644
index 0000000..fa097bd
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/dev-audio.c
@@ -0,0 +1,164 @@
+/* linux/arch/arm/mach-s5p64x0/dev-audio.c
+ *
+ * Copyright (c) 2010 Samsung Electronics Co. Ltd
+ *	Jaswinder Singh <jassi.brar@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/gpio.h>
+
+#include <plat/gpio-cfg.h>
+#include <plat/audio.h>
+
+#include <mach/map.h>
+#include <mach/dma.h>
+#include <mach/irqs.h>
+
+static int s5p6440_cfg_i2s(struct platform_device *pdev)
+{
+	/* configure GPIO for i2s port */
+	switch (pdev->id) {
+	case -1:
+		s3c_gpio_cfgpin(S5P6440_GPR(4), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6440_GPR(5), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6440_GPR(6), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6440_GPR(7), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6440_GPR(8), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6440_GPR(13), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6440_GPR(14), S3C_GPIO_SFN(5));
+		break;
+
+	default:
+		printk(KERN_ERR "Invalid Device %d\n", pdev->id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int s5p6450_cfg_i2s(struct platform_device *pdev)
+{
+	/* configure GPIO for i2s port */
+	switch (pdev->id) {
+	case -1:
+		s3c_gpio_cfgpin(S5P6450_GPB(4), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6450_GPR(4), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6450_GPR(5), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6450_GPR(6), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6450_GPR(7), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6450_GPR(8), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6450_GPR(13), S3C_GPIO_SFN(5));
+		s3c_gpio_cfgpin(S5P6450_GPR(14), S3C_GPIO_SFN(5));
+		break;
+
+	default:
+		printk(KERN_ERR "Invalid Device %d\n", pdev->id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct s3c_audio_pdata s5p6440_i2s_pdata = {
+	.cfg_gpio = s5p6440_cfg_i2s,
+};
+
+static struct s3c_audio_pdata s5p6450_i2s_pdata = {
+	.cfg_gpio = s5p6450_cfg_i2s,
+};
+
+static struct resource s5p64x0_iis0_resource[] = {
+	[0] = {
+		.start	= S5P64X0_PA_I2S,
+		.end	= S5P64X0_PA_I2S + 0x100 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= DMACH_I2S0_TX,
+		.end	= DMACH_I2S0_TX,
+		.flags	= IORESOURCE_DMA,
+	},
+	[2] = {
+		.start	= DMACH_I2S0_RX,
+		.end	= DMACH_I2S0_RX,
+		.flags	= IORESOURCE_DMA,
+	},
+};
+
+struct platform_device s5p6440_device_iis = {
+	.name		= "s3c64xx-iis-v4",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(s5p64x0_iis0_resource),
+	.resource	= s5p64x0_iis0_resource,
+	.dev = {
+		.platform_data = &s5p6440_i2s_pdata,
+	},
+};
+
+struct platform_device s5p6450_device_iis0 = {
+	.name		= "s3c64xx-iis-v4",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(s5p64x0_iis0_resource),
+	.resource	= s5p64x0_iis0_resource,
+	.dev = {
+		.platform_data = &s5p6450_i2s_pdata,
+	},
+};
+
+/* PCM Controller platform_devices */
+
+static int s5p6440_pcm_cfg_gpio(struct platform_device *pdev)
+{
+	switch (pdev->id) {
+	case 0:
+		s3c_gpio_cfgpin(S5P6440_GPR(7), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6440_GPR(13), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6440_GPR(14), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6440_GPR(8), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6440_GPR(6), S3C_GPIO_SFN(2));
+		break;
+
+	default:
+		printk(KERN_DEBUG "Invalid PCM Controller number!");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct s3c_audio_pdata s5p6440_pcm_pdata = {
+	.cfg_gpio = s5p6440_pcm_cfg_gpio,
+};
+
+static struct resource s5p6440_pcm0_resource[] = {
+	[0] = {
+		.start	= S5P64X0_PA_PCM,
+		.end	= S5P64X0_PA_PCM + 0x100 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= DMACH_PCM0_TX,
+		.end	= DMACH_PCM0_TX,
+		.flags	= IORESOURCE_DMA,
+	},
+	[2] = {
+		.start	= DMACH_PCM0_RX,
+		.end	= DMACH_PCM0_RX,
+		.flags	= IORESOURCE_DMA,
+	},
+};
+
+struct platform_device s5p6440_device_pcm = {
+	.name		= "samsung-pcm",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s5p6440_pcm0_resource),
+	.resource	= s5p6440_pcm0_resource,
+	.dev = {
+		.platform_data = &s5p6440_pcm_pdata,
+	},
+};
diff --git a/arch/arm/mach-s5p64x0/dev-spi.c b/arch/arm/mach-s5p64x0/dev-spi.c
new file mode 100644
index 0000000..5b69ec4
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/dev-spi.c
@@ -0,0 +1,232 @@
+/* linux/arch/arm/mach-s5p64x0/dev-spi.c
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Copyright (C) 2010 Samsung Electronics Co. Ltd.
+ *	Jaswinder Singh <jassi.brar@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/gpio.h>
+
+#include <mach/dma.h>
+#include <mach/map.h>
+#include <mach/irqs.h>
+#include <mach/regs-clock.h>
+#include <mach/spi-clocks.h>
+
+#include <plat/s3c64xx-spi.h>
+#include <plat/gpio-cfg.h>
+
+static char *s5p64x0_spi_src_clks[] = {
+	[S5P64X0_SPI_SRCCLK_PCLK] = "pclk",
+	[S5P64X0_SPI_SRCCLK_SCLK] = "sclk_spi",
+};
+
+/* SPI Controller platform_devices */
+
+/* Since we emulate multi-cs capability, we do not touch the CS.
+ * The emulated CS is toggled by board specific mechanism, as it can
+ * be either some immediate GPIO or some signal out of some other
+ * chip in between ... or some yet another way.
+ * We simply do not assume anything about CS.
+ */
+static int s5p6440_spi_cfg_gpio(struct platform_device *pdev)
+{
+	switch (pdev->id) {
+	case 0:
+		s3c_gpio_cfgpin(S5P6440_GPC(0), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6440_GPC(1), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6440_GPC(2), S3C_GPIO_SFN(2));
+		s3c_gpio_setpull(S5P6440_GPC(0), S3C_GPIO_PULL_UP);
+		s3c_gpio_setpull(S5P6440_GPC(1), S3C_GPIO_PULL_UP);
+		s3c_gpio_setpull(S5P6440_GPC(2), S3C_GPIO_PULL_UP);
+		break;
+
+	case 1:
+		s3c_gpio_cfgpin(S5P6440_GPC(4), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6440_GPC(5), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6440_GPC(6), S3C_GPIO_SFN(2));
+		s3c_gpio_setpull(S5P6440_GPC(4), S3C_GPIO_PULL_UP);
+		s3c_gpio_setpull(S5P6440_GPC(5), S3C_GPIO_PULL_UP);
+		s3c_gpio_setpull(S5P6440_GPC(6), S3C_GPIO_PULL_UP);
+		break;
+
+	default:
+		dev_err(&pdev->dev, "Invalid SPI Controller number!");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int s5p6450_spi_cfg_gpio(struct platform_device *pdev)
+{
+	switch (pdev->id) {
+	case 0:
+		s3c_gpio_cfgpin(S5P6450_GPC(0), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6450_GPC(1), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6450_GPC(2), S3C_GPIO_SFN(2));
+		s3c_gpio_setpull(S5P6450_GPC(0), S3C_GPIO_PULL_UP);
+		s3c_gpio_setpull(S5P6450_GPC(1), S3C_GPIO_PULL_UP);
+		s3c_gpio_setpull(S5P6450_GPC(2), S3C_GPIO_PULL_UP);
+		break;
+
+	case 1:
+		s3c_gpio_cfgpin(S5P6450_GPC(4), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6450_GPC(5), S3C_GPIO_SFN(2));
+		s3c_gpio_cfgpin(S5P6450_GPC(6), S3C_GPIO_SFN(2));
+		s3c_gpio_setpull(S5P6450_GPC(4), S3C_GPIO_PULL_UP);
+		s3c_gpio_setpull(S5P6450_GPC(5), S3C_GPIO_PULL_UP);
+		s3c_gpio_setpull(S5P6450_GPC(6), S3C_GPIO_PULL_UP);
+		break;
+
+	default:
+		dev_err(&pdev->dev, "Invalid SPI Controller number!");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct resource s5p64x0_spi0_resource[] = {
+	[0] = {
+		.start	= S5P64X0_PA_SPI0,
+		.end	= S5P64X0_PA_SPI0 + 0x100 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= DMACH_SPI0_TX,
+		.end	= DMACH_SPI0_TX,
+		.flags	= IORESOURCE_DMA,
+	},
+	[2] = {
+		.start	= DMACH_SPI0_RX,
+		.end	= DMACH_SPI0_RX,
+		.flags	= IORESOURCE_DMA,
+	},
+	[3] = {
+		.start	= IRQ_SPI0,
+		.end	= IRQ_SPI0,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct s3c64xx_spi_info s5p6440_spi0_pdata = {
+	.cfg_gpio	= s5p6440_spi_cfg_gpio,
+	.fifo_lvl_mask	= 0x1ff,
+	.rx_lvl_offset	= 15,
+};
+
+static struct s3c64xx_spi_info s5p6450_spi0_pdata = {
+	.cfg_gpio	= s5p6450_spi_cfg_gpio,
+	.fifo_lvl_mask	= 0x1ff,
+	.rx_lvl_offset	= 15,
+};
+
+static u64 spi_dmamask = DMA_BIT_MASK(32);
+
+struct platform_device s5p64x0_device_spi0 = {
+	.name		= "s3c64xx-spi",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s5p64x0_spi0_resource),
+	.resource	= s5p64x0_spi0_resource,
+	.dev = {
+		.dma_mask		= &spi_dmamask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	},
+};
+
+static struct resource s5p64x0_spi1_resource[] = {
+	[0] = {
+		.start	= S5P64X0_PA_SPI1,
+		.end	= S5P64X0_PA_SPI1 + 0x100 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= DMACH_SPI1_TX,
+		.end	= DMACH_SPI1_TX,
+		.flags	= IORESOURCE_DMA,
+	},
+	[2] = {
+		.start	= DMACH_SPI1_RX,
+		.end	= DMACH_SPI1_RX,
+		.flags	= IORESOURCE_DMA,
+	},
+	[3] = {
+		.start	= IRQ_SPI1,
+		.end	= IRQ_SPI1,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct s3c64xx_spi_info s5p6440_spi1_pdata = {
+	.cfg_gpio	= s5p6440_spi_cfg_gpio,
+	.fifo_lvl_mask	= 0x7f,
+	.rx_lvl_offset	= 15,
+};
+
+static struct s3c64xx_spi_info s5p6450_spi1_pdata = {
+	.cfg_gpio	= s5p6450_spi_cfg_gpio,
+	.fifo_lvl_mask	= 0x7f,
+	.rx_lvl_offset	= 15,
+};
+
+struct platform_device s5p64x0_device_spi1 = {
+	.name		= "s3c64xx-spi",
+	.id		= 1,
+	.num_resources	= ARRAY_SIZE(s5p64x0_spi1_resource),
+	.resource	= s5p64x0_spi1_resource,
+	.dev = {
+		.dma_mask		= &spi_dmamask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	},
+};
+
+void __init s5p64x0_spi_set_info(int cntrlr, int src_clk_nr, int num_cs)
+{
+	unsigned int id;
+	struct s3c64xx_spi_info *pd;
+
+	id = __raw_readl(S5P64X0_SYS_ID) & 0xFF000;
+
+	/* Reject invalid configuration */
+	if (!num_cs || src_clk_nr < 0
+			|| src_clk_nr > S5P64X0_SPI_SRCCLK_SCLK) {
+		printk(KERN_ERR "%s: Invalid SPI configuration\n", __func__);
+		return;
+	}
+
+	switch (cntrlr) {
+	case 0:
+		if (id == 0x50000)
+			pd = &s5p6450_spi0_pdata;
+		else
+			pd = &s5p6440_spi0_pdata;
+
+		s5p64x0_device_spi0.dev.platform_data = pd;
+		break;
+	case 1:
+		if (id == 0x50000)
+			pd = &s5p6450_spi1_pdata;
+		else
+			pd = &s5p6440_spi1_pdata;
+
+		s5p64x0_device_spi1.dev.platform_data = pd;
+		break;
+	default:
+		printk(KERN_ERR "%s: Invalid SPI controller(%d)\n",
+							__func__, cntrlr);
+		return;
+	}
+
+	pd->num_cs = num_cs;
+	pd->src_clk_nr = src_clk_nr;
+	pd->src_clk_name = s5p64x0_spi_src_clks[src_clk_nr];
+}
diff --git a/arch/arm/mach-s5p64x0/dma.c b/arch/arm/mach-s5p64x0/dma.c
new file mode 100644
index 0000000..29a8c24
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/dma.c
@@ -0,0 +1,149 @@
+/* linux/arch/arm/mach-s5p64x0/dma.c
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Copyright (C) 2010 Samsung Electronics Co. Ltd.
+ *	Jaswinder Singh <jassi.brar@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+*/
+
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+
+#include <mach/map.h>
+#include <mach/irqs.h>
+#include <mach/regs-clock.h>
+
+#include <plat/devs.h>
+#include <plat/s3c-pl330-pdata.h>
+
+static u64 dma_dmamask = DMA_BIT_MASK(32);
+
+static struct resource s5p64x0_pdma_resource[] = {
+	[0] = {
+		.start	= S5P64X0_PA_PDMA,
+		.end	= S5P64X0_PA_PDMA + SZ_4K,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_DMA0,
+		.end	= IRQ_DMA0,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct s3c_pl330_platdata s5p6440_pdma_pdata = {
+	.peri = {
+		[0] = DMACH_UART0_RX,
+		[1] = DMACH_UART0_TX,
+		[2] = DMACH_UART1_RX,
+		[3] = DMACH_UART1_TX,
+		[4] = DMACH_UART2_RX,
+		[5] = DMACH_UART2_TX,
+		[6] = DMACH_UART3_RX,
+		[7] = DMACH_UART3_TX,
+		[8] = DMACH_MAX,
+		[9] = DMACH_MAX,
+		[10] = DMACH_PCM0_TX,
+		[11] = DMACH_PCM0_RX,
+		[12] = DMACH_I2S0_TX,
+		[13] = DMACH_I2S0_RX,
+		[14] = DMACH_SPI0_TX,
+		[15] = DMACH_SPI0_RX,
+		[16] = DMACH_MAX,
+		[17] = DMACH_MAX,
+		[18] = DMACH_MAX,
+		[19] = DMACH_MAX,
+		[20] = DMACH_SPI1_TX,
+		[21] = DMACH_SPI1_RX,
+		[22] = DMACH_MAX,
+		[23] = DMACH_MAX,
+		[24] = DMACH_MAX,
+		[25] = DMACH_MAX,
+		[26] = DMACH_MAX,
+		[27] = DMACH_MAX,
+		[28] = DMACH_MAX,
+		[29] = DMACH_PWM,
+		[30] = DMACH_MAX,
+		[31] = DMACH_MAX,
+	},
+};
+
+static struct s3c_pl330_platdata s5p6450_pdma_pdata = {
+	.peri = {
+		[0] = DMACH_UART0_RX,
+		[1] = DMACH_UART0_TX,
+		[2] = DMACH_UART1_RX,
+		[3] = DMACH_UART1_TX,
+		[4] = DMACH_UART2_RX,
+		[5] = DMACH_UART2_TX,
+		[6] = DMACH_UART3_RX,
+		[7] = DMACH_UART3_TX,
+		[8] = DMACH_UART4_RX,
+		[9] = DMACH_UART4_TX,
+		[10] = DMACH_PCM0_TX,
+		[11] = DMACH_PCM0_RX,
+		[12] = DMACH_I2S0_TX,
+		[13] = DMACH_I2S0_RX,
+		[14] = DMACH_SPI0_TX,
+		[15] = DMACH_SPI0_RX,
+		[16] = DMACH_PCM1_TX,
+		[17] = DMACH_PCM1_RX,
+		[18] = DMACH_PCM2_TX,
+		[19] = DMACH_PCM2_RX,
+		[20] = DMACH_SPI1_TX,
+		[21] = DMACH_SPI1_RX,
+		[22] = DMACH_USI_TX,
+		[23] = DMACH_USI_RX,
+		[24] = DMACH_MAX,
+		[25] = DMACH_I2S1_TX,
+		[26] = DMACH_I2S1_RX,
+		[27] = DMACH_I2S2_TX,
+		[28] = DMACH_I2S2_RX,
+		[29] = DMACH_PWM,
+		[30] = DMACH_UART5_RX,
+		[31] = DMACH_UART5_TX,
+	},
+};
+
+static struct platform_device s5p64x0_device_pdma = {
+	.name		= "s3c-pl330",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s5p64x0_pdma_resource),
+	.resource	= s5p64x0_pdma_resource,
+	.dev		= {
+		.dma_mask = &dma_dmamask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+	},
+};
+
+static int __init s5p64x0_dma_init(void)
+{
+	unsigned int id;
+
+	id = __raw_readl(S5P64X0_SYS_ID) & 0xFF000;
+
+	if (id == 0x50000)
+		s5p64x0_device_pdma.dev.platform_data = &s5p6450_pdma_pdata;
+	else
+		s5p64x0_device_pdma.dev.platform_data = &s5p6440_pdma_pdata;
+
+	platform_device_register(&s5p64x0_device_pdma);
+
+	return 0;
+}
+arch_initcall(s5p64x0_dma_init);
diff --git a/arch/arm/mach-s5p6440/gpio.c b/arch/arm/mach-s5p64x0/gpio.c
similarity index 74%
rename from arch/arm/mach-s5p6440/gpio.c
rename to arch/arm/mach-s5p64x0/gpio.c
index 8bf6e0c..39159dd 100644
--- a/arch/arm/mach-s5p6440/gpio.c
+++ b/arch/arm/mach-s5p64x0/gpio.c
@@ -1,14 +1,14 @@
-/* arch/arm/mach-s5p6440/gpio.c
+/* linux/arch/arm/mach-s5p64x0/gpio.c
  *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- * 		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
- * S5P6440 - GPIOlib support
+ * S5P64X0 - GPIOlib support
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- */
+*/
 
 #include <linux/kernel.h>
 #include <linux/irq.h>
@@ -22,26 +22,29 @@
 #include <plat/gpio-cfg.h>
 #include <plat/gpio-cfg-helpers.h>
 
-/* GPIO bank summary:
-*
-* Bank	GPIOs	Style	SlpCon	ExtInt Group
-* A	6	4Bit	Yes	1
-* B	7	4Bit	Yes	1
-* C	8	4Bit	Yes	2
-* F	2	2Bit	Yes	4 [1]
-* G	7	4Bit	Yes	5
-* H	10	4Bit[2]	Yes	6
-* I	16	2Bit	Yes	None
-* J	12	2Bit	Yes	None
-* N	16	2Bit	No	IRQ_EINT
-* P	8	2Bit	Yes	8
-* R	15	4Bit[2]	Yes	8
-*
-* [1] BANKF pins 14,15 do not form part of the external interrupt sources
-* [2] BANK has two control registers, GPxCON0 and GPxCON1
-*/
+/* To be implemented S5P6450 GPIO */
 
-static int s5p6440_gpiolib_rbank_4bit2_input(struct gpio_chip *chip,
+/*
+ * S5P6440 GPIO bank summary:
+ *
+ * Bank	GPIOs	Style	SlpCon	ExtInt Group
+ * A	6	4Bit	Yes	1
+ * B	7	4Bit	Yes	1
+ * C	8	4Bit	Yes	2
+ * F	2	2Bit	Yes	4 [1]
+ * G	7	4Bit	Yes	5
+ * H	10	4Bit[2]	Yes	6
+ * I	16	2Bit	Yes	None
+ * J	12	2Bit	Yes	None
+ * N	16	2Bit	No	IRQ_EINT
+ * P	8	2Bit	Yes	8
+ * R	15	4Bit[2]	Yes	8
+ *
+ * [1] BANKF pins 14,15 do not form part of the external interrupt sources
+ * [2] BANK has two control registers, GPxCON0 and GPxCON1
+ */
+
+static int s5p64x0_gpiolib_rbank_4bit2_input(struct gpio_chip *chip,
 					     unsigned int offset)
 {
 	struct s3c_gpio_chip *ourchip = to_s3c_gpio(chip);
@@ -77,7 +80,7 @@
 	return 0;
 }
 
-static int s5p6440_gpiolib_rbank_4bit2_output(struct gpio_chip *chip,
+static int s5p64x0_gpiolib_rbank_4bit2_output(struct gpio_chip *chip,
 					      unsigned int offset, int value)
 {
 	struct s3c_gpio_chip *ourchip = to_s3c_gpio(chip);
@@ -124,12 +127,11 @@
 	return 0;
 }
 
-int s5p6440_gpio_setcfg_4bit_rbank(struct s3c_gpio_chip *chip,
+int s5p64x0_gpio_setcfg_4bit_rbank(struct s3c_gpio_chip *chip,
 				   unsigned int off, unsigned int cfg)
 {
 	void __iomem *reg = chip->base;
 	unsigned int shift;
-	unsigned long flags;
 	u32 con;
 
 	switch (off) {
@@ -155,26 +157,22 @@
 		cfg <<= shift;
 	}
 
-	s3c_gpio_lock(chip, flags);
-
 	con = __raw_readl(reg);
 	con &= ~(0xf << shift);
 	con |= cfg;
 	__raw_writel(con, reg);
 
-	s3c_gpio_unlock(chip, flags);
-
 	return 0;
 }
 
-static struct s3c_gpio_cfg s5p6440_gpio_cfgs[] = {
+static struct s3c_gpio_cfg s5p64x0_gpio_cfgs[] = {
 	{
 		.cfg_eint	= 0,
 	}, {
 		.cfg_eint	= 7,
 	}, {
 		.cfg_eint	= 3,
-		.set_config	= s5p6440_gpio_setcfg_4bit_rbank,
+		.set_config	= s5p64x0_gpio_setcfg_4bit_rbank,
 	}, {
 		.cfg_eint	= 0,
 		.set_config	= s3c_gpio_setcfg_s3c24xx,
@@ -193,7 +191,7 @@
 static struct s3c_gpio_chip s5p6440_gpio_4bit[] = {
 	{
 		.base	= S5P6440_GPA_BASE,
-		.config	= &s5p6440_gpio_cfgs[1],
+		.config	= &s5p64x0_gpio_cfgs[1],
 		.chip	= {
 			.base	= S5P6440_GPA(0),
 			.ngpio	= S5P6440_GPIO_A_NR,
@@ -201,7 +199,7 @@
 		},
 	}, {
 		.base	= S5P6440_GPB_BASE,
-		.config	= &s5p6440_gpio_cfgs[1],
+		.config	= &s5p64x0_gpio_cfgs[1],
 		.chip	= {
 			.base	= S5P6440_GPB(0),
 			.ngpio	= S5P6440_GPIO_B_NR,
@@ -209,7 +207,7 @@
 		},
 	}, {
 		.base	= S5P6440_GPC_BASE,
-		.config	= &s5p6440_gpio_cfgs[1],
+		.config	= &s5p64x0_gpio_cfgs[1],
 		.chip	= {
 			.base	= S5P6440_GPC(0),
 			.ngpio	= S5P6440_GPIO_C_NR,
@@ -217,7 +215,7 @@
 		},
 	}, {
 		.base	= S5P6440_GPG_BASE,
-		.config	= &s5p6440_gpio_cfgs[1],
+		.config	= &s5p64x0_gpio_cfgs[1],
 		.chip	= {
 			.base	= S5P6440_GPG(0),
 			.ngpio	= S5P6440_GPIO_G_NR,
@@ -229,7 +227,7 @@
 static struct s3c_gpio_chip s5p6440_gpio_4bit2[] = {
 	{
 		.base	= S5P6440_GPH_BASE + 0x4,
-		.config	= &s5p6440_gpio_cfgs[1],
+		.config	= &s5p64x0_gpio_cfgs[1],
 		.chip	= {
 			.base	= S5P6440_GPH(0),
 			.ngpio	= S5P6440_GPIO_H_NR,
@@ -238,10 +236,10 @@
 	},
 };
 
-static struct s3c_gpio_chip gpio_rbank_4bit2[] = {
+static struct s3c_gpio_chip s5p6440_gpio_rbank_4bit2[] = {
 	{
 		.base	= S5P6440_GPR_BASE + 0x4,
-		.config	= &s5p6440_gpio_cfgs[2],
+		.config	= &s5p64x0_gpio_cfgs[2],
 		.chip	= {
 			.base	= S5P6440_GPR(0),
 			.ngpio	= S5P6440_GPIO_R_NR,
@@ -253,7 +251,7 @@
 static struct s3c_gpio_chip s5p6440_gpio_2bit[] = {
 	{
 		.base	= S5P6440_GPF_BASE,
-		.config	= &s5p6440_gpio_cfgs[5],
+		.config	= &s5p64x0_gpio_cfgs[5],
 		.chip	= {
 			.base	= S5P6440_GPF(0),
 			.ngpio	= S5P6440_GPIO_F_NR,
@@ -261,7 +259,7 @@
 		},
 	}, {
 		.base	= S5P6440_GPI_BASE,
-		.config	= &s5p6440_gpio_cfgs[3],
+		.config	= &s5p64x0_gpio_cfgs[3],
 		.chip	= {
 			.base	= S5P6440_GPI(0),
 			.ngpio	= S5P6440_GPIO_I_NR,
@@ -269,7 +267,7 @@
 		},
 	}, {
 		.base	= S5P6440_GPJ_BASE,
-		.config	= &s5p6440_gpio_cfgs[3],
+		.config	= &s5p64x0_gpio_cfgs[3],
 		.chip	= {
 			.base	= S5P6440_GPJ(0),
 			.ngpio	= S5P6440_GPIO_J_NR,
@@ -277,7 +275,7 @@
 		},
 	}, {
 		.base	= S5P6440_GPN_BASE,
-		.config	= &s5p6440_gpio_cfgs[4],
+		.config	= &s5p64x0_gpio_cfgs[4],
 		.chip	= {
 			.base	= S5P6440_GPN(0),
 			.ngpio	= S5P6440_GPIO_N_NR,
@@ -285,7 +283,7 @@
 		},
 	}, {
 		.base	= S5P6440_GPP_BASE,
-		.config	= &s5p6440_gpio_cfgs[5],
+		.config	= &s5p64x0_gpio_cfgs[5],
 		.chip	= {
 			.base	= S5P6440_GPP(0),
 			.ngpio	= S5P6440_GPIO_P_NR,
@@ -294,7 +292,7 @@
 	},
 };
 
-void __init s5p6440_gpiolib_set_cfg(struct s3c_gpio_cfg *chipcfg, int nr_chips)
+void __init s5p64x0_gpiolib_set_cfg(struct s3c_gpio_cfg *chipcfg, int nr_chips)
 {
 	for (; nr_chips > 0; nr_chips--, chipcfg++) {
 		if (!chipcfg->set_config)
@@ -308,13 +306,13 @@
 	}
 }
 
-static void __init s5p6440_gpio_add_rbank_4bit2(struct s3c_gpio_chip *chip,
+static void __init s5p64x0_gpio_add_rbank_4bit2(struct s3c_gpio_chip *chip,
 						int nr_chips)
 {
 	for (; nr_chips > 0; nr_chips--, chip++) {
-		chip->chip.direction_input = s5p6440_gpiolib_rbank_4bit2_input;
+		chip->chip.direction_input = s5p64x0_gpiolib_rbank_4bit2_input;
 		chip->chip.direction_output =
-					s5p6440_gpiolib_rbank_4bit2_output;
+					s5p64x0_gpiolib_rbank_4bit2_output;
 		s3c_gpiolib_add(chip);
 	}
 }
@@ -324,8 +322,8 @@
 	struct s3c_gpio_chip *chips = s5p6440_gpio_2bit;
 	int nr_chips = ARRAY_SIZE(s5p6440_gpio_2bit);
 
-	s5p6440_gpiolib_set_cfg(s5p6440_gpio_cfgs,
-				ARRAY_SIZE(s5p6440_gpio_cfgs));
+	s5p64x0_gpiolib_set_cfg(s5p64x0_gpio_cfgs,
+				ARRAY_SIZE(s5p64x0_gpio_cfgs));
 
 	for (; nr_chips > 0; nr_chips--, chips++)
 		s3c_gpiolib_add(chips);
@@ -336,8 +334,8 @@
 	samsung_gpiolib_add_4bit2_chips(s5p6440_gpio_4bit2,
 				ARRAY_SIZE(s5p6440_gpio_4bit2));
 
-	s5p6440_gpio_add_rbank_4bit2(gpio_rbank_4bit2,
-				ARRAY_SIZE(gpio_rbank_4bit2));
+	s5p64x0_gpio_add_rbank_4bit2(s5p6440_gpio_rbank_4bit2,
+				ARRAY_SIZE(s5p6440_gpio_rbank_4bit2));
 
 	return 0;
 }
diff --git a/arch/arm/mach-s5p64x0/include/mach/debug-macro.S b/arch/arm/mach-s5p64x0/include/mach/debug-macro.S
new file mode 100644
index 0000000..79b04e6
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/debug-macro.S
@@ -0,0 +1,33 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/debug-macro.S
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+/* pull in the relevant register and map files. */
+
+#include <plat/map-base.h>
+#include <plat/map-s5p.h>
+
+#include <plat/regs-serial.h>
+
+	.macro addruart, rp, rv
+		mov	\rp, #0xE0000000
+		orr	\rp, \rp, #0x00100000
+		ldr	\rp, [\rp, #0x118 ]
+		and	\rp, \rp, #0xff000
+		teq	\rp, #0x50000		@@ S5P6450
+		ldreq	\rp, =0xEC800000
+		movne	\rp, #0xEC000000	@@ S5P6440
+		ldrne	\rv, = S3C_VA_UART
+#if CONFIG_DEBUG_S3C_UART != 0
+		add	\rp, \rp, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rv, \rv, #(0x400 * CONFIG_DEBUG_S3C_UART)
+#endif
+	.endm
+
+#include <plat/debug-macro.S>
diff --git a/arch/arm/mach-s5p6440/include/mach/dma.h b/arch/arm/mach-s5p64x0/include/mach/dma.h
similarity index 100%
rename from arch/arm/mach-s5p6440/include/mach/dma.h
rename to arch/arm/mach-s5p64x0/include/mach/dma.h
diff --git a/arch/arm/mach-s5p64x0/include/mach/entry-macro.S b/arch/arm/mach-s5p64x0/include/mach/entry-macro.S
new file mode 100644
index 0000000..10b62b4
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/entry-macro.S
@@ -0,0 +1,16 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/entry-macro.S
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Low-level IRQ helper macros for the Samsung S5P64X0
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <mach/map.h>
+#include <plat/irqs.h>
+
+#include <asm/entry-macro-vic2.S>
diff --git a/arch/arm/mach-s5p64x0/include/mach/gpio.h b/arch/arm/mach-s5p64x0/include/mach/gpio.h
new file mode 100644
index 0000000..5486c8f
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/gpio.h
@@ -0,0 +1,139 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/gpio.h
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P64X0 - GPIO lib support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef __ASM_ARCH_GPIO_H
+#define __ASM_ARCH_GPIO_H __FILE__
+
+#define gpio_get_value	__gpio_get_value
+#define gpio_set_value	__gpio_set_value
+#define gpio_cansleep	__gpio_cansleep
+#define gpio_to_irq	__gpio_to_irq
+
+/* GPIO bank sizes */
+
+#define S5P6440_GPIO_A_NR	(6)
+#define S5P6440_GPIO_B_NR	(7)
+#define S5P6440_GPIO_C_NR	(8)
+#define S5P6440_GPIO_F_NR	(2)
+#define S5P6440_GPIO_G_NR	(7)
+#define S5P6440_GPIO_H_NR	(10)
+#define S5P6440_GPIO_I_NR	(16)
+#define S5P6440_GPIO_J_NR	(12)
+#define S5P6440_GPIO_N_NR	(16)
+#define S5P6440_GPIO_P_NR	(8)
+#define S5P6440_GPIO_R_NR	(15)
+
+#define S5P6450_GPIO_A_NR	(6)
+#define S5P6450_GPIO_B_NR	(7)
+#define S5P6450_GPIO_C_NR	(8)
+#define S5P6450_GPIO_D_NR	(8)
+#define S5P6450_GPIO_F_NR	(2)
+#define S5P6450_GPIO_G_NR	(14)
+#define S5P6450_GPIO_H_NR	(10)
+#define S5P6450_GPIO_I_NR	(16)
+#define S5P6450_GPIO_J_NR	(12)
+#define S5P6450_GPIO_K_NR	(5)
+#define S5P6450_GPIO_N_NR	(16)
+#define S5P6450_GPIO_P_NR	(11)
+#define S5P6450_GPIO_Q_NR	(14)
+#define S5P6450_GPIO_R_NR	(15)
+#define S5P6450_GPIO_S_NR	(8)
+
+/* GPIO bank numbers */
+
+/* CONFIG_S3C_GPIO_SPACE allows the user to select extra
+ * space for debugging purposes so that any accidental
+ * change from one gpio bank to another can be caught.
+*/
+
+#define S5P64X0_GPIO_NEXT(__gpio) \
+	((__gpio##_START) + (__gpio##_NR) + CONFIG_S3C_GPIO_SPACE + 1)
+
+enum s5p6440_gpio_number {
+	S5P6440_GPIO_A_START	= 0,
+	S5P6440_GPIO_B_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_A),
+	S5P6440_GPIO_C_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_B),
+	S5P6440_GPIO_F_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_C),
+	S5P6440_GPIO_G_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_F),
+	S5P6440_GPIO_H_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_G),
+	S5P6440_GPIO_I_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_H),
+	S5P6440_GPIO_J_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_I),
+	S5P6440_GPIO_N_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_J),
+	S5P6440_GPIO_P_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_N),
+	S5P6440_GPIO_R_START	= S5P64X0_GPIO_NEXT(S5P6440_GPIO_P),
+};
+
+enum s5p6450_gpio_number {
+	S5P6450_GPIO_A_START	= 0,
+	S5P6450_GPIO_B_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_A),
+	S5P6450_GPIO_C_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_B),
+	S5P6450_GPIO_D_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_C),
+	S5P6450_GPIO_F_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_D),
+	S5P6450_GPIO_G_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_F),
+	S5P6450_GPIO_H_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_G),
+	S5P6450_GPIO_I_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_H),
+	S5P6450_GPIO_J_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_I),
+	S5P6450_GPIO_K_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_J),
+	S5P6450_GPIO_N_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_K),
+	S5P6450_GPIO_P_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_N),
+	S5P6450_GPIO_Q_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_P),
+	S5P6450_GPIO_R_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_Q),
+	S5P6450_GPIO_S_START	= S5P64X0_GPIO_NEXT(S5P6450_GPIO_R),
+};
+
+/* GPIO number definitions */
+
+#define S5P6440_GPA(_nr)	(S5P6440_GPIO_A_START + (_nr))
+#define S5P6440_GPB(_nr)	(S5P6440_GPIO_B_START + (_nr))
+#define S5P6440_GPC(_nr)	(S5P6440_GPIO_C_START + (_nr))
+#define S5P6440_GPF(_nr)	(S5P6440_GPIO_F_START + (_nr))
+#define S5P6440_GPG(_nr)	(S5P6440_GPIO_G_START + (_nr))
+#define S5P6440_GPH(_nr)	(S5P6440_GPIO_H_START + (_nr))
+#define S5P6440_GPI(_nr)	(S5P6440_GPIO_I_START + (_nr))
+#define S5P6440_GPJ(_nr)	(S5P6440_GPIO_J_START + (_nr))
+#define S5P6440_GPN(_nr)	(S5P6440_GPIO_N_START + (_nr))
+#define S5P6440_GPP(_nr)	(S5P6440_GPIO_P_START + (_nr))
+#define S5P6440_GPR(_nr)	(S5P6440_GPIO_R_START + (_nr))
+
+#define S5P6450_GPA(_nr)	(S5P6450_GPIO_A_START + (_nr))
+#define S5P6450_GPB(_nr)	(S5P6450_GPIO_B_START + (_nr))
+#define S5P6450_GPC(_nr)	(S5P6450_GPIO_C_START + (_nr))
+#define S5P6450_GPD(_nr)	(S5P6450_GPIO_D_START + (_nr))
+#define S5P6450_GPF(_nr)	(S5P6450_GPIO_F_START + (_nr))
+#define S5P6450_GPG(_nr)	(S5P6450_GPIO_G_START + (_nr))
+#define S5P6450_GPH(_nr)	(S5P6450_GPIO_H_START + (_nr))
+#define S5P6450_GPI(_nr)	(S5P6450_GPIO_I_START + (_nr))
+#define S5P6450_GPJ(_nr)	(S5P6450_GPIO_J_START + (_nr))
+#define S5P6450_GPK(_nr)	(S5P6450_GPIO_K_START + (_nr))
+#define S5P6450_GPN(_nr)	(S5P6450_GPIO_N_START + (_nr))
+#define S5P6450_GPP(_nr)	(S5P6450_GPIO_P_START + (_nr))
+#define S5P6450_GPQ(_nr)	(S5P6450_GPIO_Q_START + (_nr))
+#define S5P6450_GPR(_nr)	(S5P6450_GPIO_R_START + (_nr))
+#define S5P6450_GPS(_nr)	(S5P6450_GPIO_S_START + (_nr))
+
+/* the end of the S5P64X0 specific gpios */
+
+#define S5P6440_GPIO_END	(S5P6440_GPR(S5P6440_GPIO_R_NR) + 1)
+#define S5P6450_GPIO_END	(S5P6450_GPS(S5P6450_GPIO_S_NR) + 1)
+
+#define S5P64X0_GPIO_END	(S5P6440_GPIO_END > S5P6450_GPIO_END ?	\
+				 S5P6440_GPIO_END : S5P6450_GPIO_END)
+
+#define S3C_GPIO_END		S5P64X0_GPIO_END
+
+/* define the number of gpios we need to the one after the last GPIO range */
+
+#define ARCH_NR_GPIOS		(S5P64X0_GPIO_END + CONFIG_SAMSUNG_GPIO_EXTRA)
+
+#include <asm-generic/gpio.h>
+
+#endif /* __ASM_ARCH_GPIO_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/hardware.h b/arch/arm/mach-s5p64x0/include/mach/hardware.h
similarity index 67%
rename from arch/arm/mach-s5p6440/include/mach/hardware.h
rename to arch/arm/mach-s5p64x0/include/mach/hardware.h
index be8b26e..d3e8799 100644
--- a/arch/arm/mach-s5p6440/include/mach/hardware.h
+++ b/arch/arm/mach-s5p64x0/include/mach/hardware.h
@@ -1,9 +1,9 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/hardware.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/hardware.h
  *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
- * S5P6440 - Hardware support
+ * S5P64X0 - Hardware support
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/mach-s5p64x0/include/mach/i2c.h b/arch/arm/mach-s5p64x0/include/mach/i2c.h
new file mode 100644
index 0000000..887d252
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/i2c.h
@@ -0,0 +1,17 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/i2c.h
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P64X0 I2C configuration
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+extern void s5p6440_i2c0_cfg_gpio(struct platform_device *dev);
+extern void s5p6440_i2c1_cfg_gpio(struct platform_device *dev);
+
+extern void s5p6450_i2c0_cfg_gpio(struct platform_device *dev);
+extern void s5p6450_i2c1_cfg_gpio(struct platform_device *dev);
diff --git a/arch/arm/mach-s5p64x0/include/mach/io.h b/arch/arm/mach-s5p64x0/include/mach/io.h
new file mode 100644
index 0000000..a3e095c
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/io.h
@@ -0,0 +1,25 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/io.h
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Copyright 2008 Simtec Electronics
+ *	Ben Dooks <ben-linux@fluff.org>
+ *
+ * Default IO routines for S5P64X0 based
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef __ASM_ARM_ARCH_IO_H
+#define __ASM_ARM_ARCH_IO_H
+
+/* No current ISA/PCI bus support. */
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
+
+#define IO_SPACE_LIMIT (0xFFFFFFFF)
+
+#endif
diff --git a/arch/arm/mach-s5p6440/include/mach/irqs.h b/arch/arm/mach-s5p64x0/include/mach/irqs.h
similarity index 71%
rename from arch/arm/mach-s5p6440/include/mach/irqs.h
rename to arch/arm/mach-s5p64x0/include/mach/irqs.h
index 16a7612..513abff 100644
--- a/arch/arm/mach-s5p6440/include/mach/irqs.h
+++ b/arch/arm/mach-s5p64x0/include/mach/irqs.h
@@ -1,17 +1,17 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/irqs.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/irqs.h
  *
- * Copyright 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
- * S5P6440 - IRQ definitions
+ * S5P64X0 - IRQ definitions
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
 */
 
-#ifndef __ASM_ARCH_S5P_IRQS_H
-#define __ASM_ARCH_S5P_IRQS_H __FILE__
+#ifndef __ASM_ARCH_IRQS_H
+#define __ASM_ARCH_IRQS_H __FILE__
 
 #include <plat/irqs.h>
 
@@ -20,10 +20,12 @@
 #define IRQ_EINT0_3		S5P_IRQ_VIC0(0)
 #define IRQ_EINT4_11		S5P_IRQ_VIC0(1)
 #define IRQ_RTC_TIC		S5P_IRQ_VIC0(2)
+#define IRQ_IIS1		S5P_IRQ_VIC0(3)	/* for only S5P6450 */
+#define IRQ_IIS2		S5P_IRQ_VIC0(4)	/* for only S5P6450 */
 #define IRQ_IIC1		S5P_IRQ_VIC0(5)
 #define IRQ_I2SV40		S5P_IRQ_VIC0(6)
-#define IRQ_GPS			S5P_IRQ_VIC0(7)
-#define IRQ_POST0		S5P_IRQ_VIC0(9)
+#define IRQ_GPS			S5P_IRQ_VIC0(7)	/* for only S5P6450 */
+
 #define IRQ_2D			S5P_IRQ_VIC0(11)
 #define IRQ_TIMER0_VIC		S5P_IRQ_VIC0(23)
 #define IRQ_TIMER1_VIC		S5P_IRQ_VIC0(24)
@@ -39,22 +41,26 @@
 
 #define IRQ_EINT12_15		S5P_IRQ_VIC1(0)
 #define IRQ_PCM0		S5P_IRQ_VIC1(2)
+#define IRQ_PCM1		S5P_IRQ_VIC1(3)	/* for only S5P6450 */
+#define IRQ_PCM2		S5P_IRQ_VIC1(4)	/* for only S5P6450 */
 #define IRQ_UART0		S5P_IRQ_VIC1(5)
 #define IRQ_UART1		S5P_IRQ_VIC1(6)
 #define IRQ_UART2		S5P_IRQ_VIC1(7)
 #define IRQ_UART3		S5P_IRQ_VIC1(8)
 #define IRQ_DMA0		S5P_IRQ_VIC1(9)
+#define IRQ_UART4		S5P_IRQ_VIC1(10)	/* S5P6450 */
+#define IRQ_UART5		S5P_IRQ_VIC1(11)	/* S5P6450 */
 #define IRQ_NFC			S5P_IRQ_VIC1(13)
+#define IRQ_USI			S5P_IRQ_VIC1(15)	/* S5P6450 */
 #define IRQ_SPI0		S5P_IRQ_VIC1(16)
 #define IRQ_SPI1		S5P_IRQ_VIC1(17)
+#define IRQ_HSMMC2		S5P_IRQ_VIC1(17)	/* Shared */
 #define IRQ_IIC			S5P_IRQ_VIC1(18)
 #define IRQ_DISPCON3		S5P_IRQ_VIC1(19)
-#define IRQ_FIMGVG		S5P_IRQ_VIC1(20)
 #define IRQ_EINT_GROUPS		S5P_IRQ_VIC1(21)
-#define IRQ_PMU			S5P_IRQ_VIC1(23)
+#define IRQ_PMU			S5P_IRQ_VIC1(23)	/* S5P6440 */
 #define IRQ_HSMMC0		S5P_IRQ_VIC1(24)
 #define IRQ_HSMMC1		S5P_IRQ_VIC1(25)
-#define IRQ_HSMMC2		IRQ_SPI1	/* shared with SPI1 */
 #define IRQ_OTG			S5P_IRQ_VIC1(26)
 #define IRQ_DSI			S5P_IRQ_VIC1(27)
 #define IRQ_RTC_ALARM		S5P_IRQ_VIC1(28)
@@ -63,6 +69,24 @@
 #define IRQ_TC			IRQ_PENDN
 #define IRQ_ADC			S5P_IRQ_VIC1(31)
 
+/* UART interrupts, S5P6450 has 5 UARTs */
+#define IRQ_S5P_UART_BASE4	(96)
+#define IRQ_S5P_UART_BASE5	(100)
+
+#define IRQ_S5P_UART_RX4	(IRQ_S5P_UART_BASE4 + UART_IRQ_RXD)
+#define IRQ_S5P_UART_TX4	(IRQ_S5P_UART_BASE4 + UART_IRQ_TXD)
+#define IRQ_S5P_UART_ERR4	(IRQ_S5P_UART_BASE4 + UART_IRQ_ERR)
+
+#define IRQ_S5P_UART_RX5	(IRQ_S5P_UART_BASE5 + UART_IRQ_RXD)
+#define IRQ_S5P_UART_TX5	(IRQ_S5P_UART_BASE5 + UART_IRQ_TXD)
+#define IRQ_S5P_UART_ERR5	(IRQ_S5P_UART_BASE5 + UART_IRQ_ERR)
+
+/* S3C compatibilty defines */
+#define IRQ_S3CUART_RX4		IRQ_S5P_UART_RX4
+#define IRQ_S3CUART_RX5		IRQ_S5P_UART_RX5
+
+/* S5P6450 EINT feature will be added */
+
 /*
  * Since the IRQ_EINT(x) are a linear mapping on s5p6440 we just defined
  * them as an IRQ_EINT(x) macro from S5P_IRQ_EINT_BASE which we place
@@ -115,4 +139,4 @@
 
 #define NR_IRQS			(IRQ_EINT_GROUP8_BASE + IRQ_EINT_GROUP8_NR + 1)
 
-#endif /* __ASM_ARCH_S5P_IRQS_H */
+#endif /* __ASM_ARCH_IRQS_H */
diff --git a/arch/arm/mach-s5p64x0/include/mach/map.h b/arch/arm/mach-s5p64x0/include/mach/map.h
new file mode 100644
index 0000000..31e5341
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/map.h
@@ -0,0 +1,83 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/map.h
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P64X0 - Memory map definitions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef __ASM_ARCH_MAP_H
+#define __ASM_ARCH_MAP_H __FILE__
+
+#include <plat/map-base.h>
+#include <plat/map-s5p.h>
+
+#define S5P64X0_PA_SDRAM	(0x20000000)
+
+#define S5P64X0_PA_CHIPID	(0xE0000000)
+#define S5P_PA_CHIPID		S5P64X0_PA_CHIPID
+
+#define S5P64X0_PA_SYSCON	(0xE0100000)
+#define S5P_PA_SYSCON		S5P64X0_PA_SYSCON
+
+#define S5P64X0_PA_GPIO		(0xE0308000)
+
+#define S5P64X0_PA_VIC0		(0xE4000000)
+#define S5P64X0_PA_VIC1		(0xE4100000)
+
+#define S5P64X0_PA_PDMA		(0xE9000000)
+
+#define S5P64X0_PA_TIMER	(0xEA000000)
+#define S5P_PA_TIMER		S5P64X0_PA_TIMER
+
+#define S5P64X0_PA_RTC		(0xEA100000)
+
+#define S5P64X0_PA_WDT		(0xEA200000)
+
+#define S5P6440_PA_UART(x)	(0xEC000000 + ((x) * S3C_UART_OFFSET))
+#define S5P6450_PA_UART(x)	((x < 5) ? (0xEC800000 + ((x) * S3C_UART_OFFSET)) : (0xEC000000))
+
+#define S5P_PA_UART0		S5P6450_PA_UART(0)
+#define S5P_PA_UART1		S5P6450_PA_UART(1)
+#define S5P_PA_UART2		S5P6450_PA_UART(2)
+#define S5P_PA_UART3		S5P6450_PA_UART(3)
+#define S5P_PA_UART4		S5P6450_PA_UART(4)
+#define S5P_PA_UART5		S5P6450_PA_UART(5)
+
+#define S5P_SZ_UART		SZ_256
+
+#define S5P6440_PA_IIC0		(0xEC104000)
+#define S5P6440_PA_IIC1		(0xEC20F000)
+#define S5P6450_PA_IIC0		(0xEC100000)
+#define S5P6450_PA_IIC1		(0xEC200000)
+
+#define S5P64X0_PA_SPI0		(0xEC400000)
+#define S5P64X0_PA_SPI1		(0xEC500000)
+
+#define S5P64X0_PA_HSOTG	(0xED100000)
+
+#define S5P64X0_PA_HSMMC(x)	(0xED800000 + ((x) * 0x100000))
+
+#define S5P64X0_PA_I2S		(0xF2000000)
+
+#define S5P64X0_PA_PCM		(0xF2100000)
+
+#define S5P64X0_PA_ADC		(0xF3000000)
+
+/* compatibiltiy defines. */
+
+#define S3C_PA_HSMMC0		S5P64X0_PA_HSMMC(0)
+#define S3C_PA_HSMMC1		S5P64X0_PA_HSMMC(1)
+#define S3C_PA_HSMMC2		S5P64X0_PA_HSMMC(2)
+#define S3C_PA_IIC		S5P6440_PA_IIC0
+#define S3C_PA_IIC1		S5P6440_PA_IIC1
+#define S3C_PA_RTC		S5P64X0_PA_RTC
+#define S3C_PA_WDT		S5P64X0_PA_WDT
+
+#define SAMSUNG_PA_ADC		S5P64X0_PA_ADC
+
+#endif /* __ASM_ARCH_MAP_H */
diff --git a/arch/arm/mach-s5p64x0/include/mach/memory.h b/arch/arm/mach-s5p64x0/include/mach/memory.h
new file mode 100644
index 0000000..1b036b0
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/memory.h
@@ -0,0 +1,19 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/memory.h
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P64X0 - Memory definitions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef __ASM_ARCH_MEMORY_H
+#define __ASM_ARCH_MEMORY_H __FILE__
+
+#define PHYS_OFFSET		UL(0x20000000)
+#define CONSISTENT_DMA_SIZE	SZ_8M
+
+#endif /* __ASM_ARCH_MEMORY_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/pwm-clock.h b/arch/arm/mach-s5p64x0/include/mach/pwm-clock.h
similarity index 86%
rename from arch/arm/mach-s5p6440/include/mach/pwm-clock.h
rename to arch/arm/mach-s5p64x0/include/mach/pwm-clock.h
index 6a2a02f..19fff8b7 100644
--- a/arch/arm/mach-s5p6440/include/mach/pwm-clock.h
+++ b/arch/arm/mach-s5p64x0/include/mach/pwm-clock.h
@@ -1,16 +1,14 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/pwm-clock.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/pwm-clock.h
  *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
  * Copyright 2008 Openmoko, Inc.
  * Copyright 2008 Simtec Electronics
  *      Ben Dooks <ben@simtec.co.uk>
  *      http://armlinux.simtec.co.uk/
  *
- * Based on arch/arm/mach-s3c64xx/include/mach/pwm-clock.h
- *
- * S5P6440 - pwm clock and timer support
+ * S5P64X0 - pwm clock and timer support
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/mach-s5p64x0/include/mach/regs-clock.h b/arch/arm/mach-s5p64x0/include/mach/regs-clock.h
new file mode 100644
index 0000000..58e1bc8
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/regs-clock.h
@@ -0,0 +1,63 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/regs-clock.h
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P64X0 - Clock register definitions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef __ASM_ARCH_REGS_CLOCK_H
+#define __ASM_ARCH_REGS_CLOCK_H __FILE__
+
+#include <mach/map.h>
+
+#define S5P_CLKREG(x)			(S3C_VA_SYS + (x))
+
+#define S5P64X0_APLL_CON		S5P_CLKREG(0x0C)
+#define S5P64X0_MPLL_CON		S5P_CLKREG(0x10)
+#define S5P64X0_EPLL_CON		S5P_CLKREG(0x14)
+#define S5P64X0_EPLL_CON_K		S5P_CLKREG(0x18)
+
+#define S5P64X0_CLK_SRC0		S5P_CLKREG(0x1C)
+
+#define S5P64X0_CLK_DIV0		S5P_CLKREG(0x20)
+#define S5P64X0_CLK_DIV1		S5P_CLKREG(0x24)
+#define S5P64X0_CLK_DIV2		S5P_CLKREG(0x28)
+
+#define S5P64X0_CLK_GATE_HCLK0		S5P_CLKREG(0x30)
+#define S5P64X0_CLK_GATE_PCLK		S5P_CLKREG(0x34)
+#define S5P64X0_CLK_GATE_SCLK0		S5P_CLKREG(0x38)
+#define S5P64X0_CLK_GATE_MEM0		S5P_CLKREG(0x3C)
+
+#define S5P64X0_CLK_DIV3		S5P_CLKREG(0x40)
+
+#define S5P64X0_CLK_GATE_HCLK1		S5P_CLKREG(0x44)
+#define S5P64X0_CLK_GATE_SCLK1		S5P_CLKREG(0x48)
+
+#define S5P6450_DPLL_CON		S5P_CLKREG(0x50)
+#define S5P6450_DPLL_CON_K		S5P_CLKREG(0x54)
+
+#define S5P64X0_CLK_SRC1		S5P_CLKREG(0x10C)
+
+#define S5P64X0_SYS_ID			S5P_CLKREG(0x118)
+#define S5P64X0_SYS_OTHERS		S5P_CLKREG(0x11C)
+
+#define S5P64X0_PWR_CFG			S5P_CLKREG(0x804)
+#define S5P64X0_OTHERS			S5P_CLKREG(0x900)
+
+#define S5P64X0_CLKDIV0_HCLK_SHIFT	(8)
+#define S5P64X0_CLKDIV0_HCLK_MASK	(0xF << S5P64X0_CLKDIV0_HCLK_SHIFT)
+
+#define S5P64X0_OTHERS_USB_SIG_MASK	(1 << 16)
+
+/* Compatibility defines */
+
+#define ARM_CLK_DIV			S5P64X0_CLK_DIV0
+#define ARM_DIV_RATIO_SHIFT		0
+#define ARM_DIV_MASK			(0xF << ARM_DIV_RATIO_SHIFT)
+
+#endif /* __ASM_ARCH_REGS_CLOCK_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/regs-gpio.h b/arch/arm/mach-s5p64x0/include/mach/regs-gpio.h
similarity index 79%
rename from arch/arm/mach-s5p6440/include/mach/regs-gpio.h
rename to arch/arm/mach-s5p64x0/include/mach/regs-gpio.h
index 82ff753..85f448e 100644
--- a/arch/arm/mach-s5p6440/include/mach/regs-gpio.h
+++ b/arch/arm/mach-s5p64x0/include/mach/regs-gpio.h
@@ -1,21 +1,24 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/regs-gpio.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/regs-gpio.h
  *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
- * S5P6440 - GPIO register definitions
+ * S5P64X0 - GPIO register definitions
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- */
+*/
 
 #ifndef __ASM_ARCH_REGS_GPIO_H
 #define __ASM_ARCH_REGS_GPIO_H __FILE__
 
 #include <mach/map.h>
 
+/* Will be implemented S5P6442 GPIOlib */
+
 /* Base addresses for each of the banks */
+
 #define S5P6440_GPA_BASE		(S5P_VA_GPIO + 0x0000)
 #define S5P6440_GPB_BASE		(S5P_VA_GPIO + 0x0020)
 #define S5P6440_GPC_BASE		(S5P_VA_GPIO + 0x0040)
@@ -27,6 +30,7 @@
 #define S5P6440_GPN_BASE		(S5P_VA_GPIO + 0x0830)
 #define S5P6440_GPP_BASE		(S5P_VA_GPIO + 0x0160)
 #define S5P6440_GPR_BASE		(S5P_VA_GPIO + 0x0290)
+
 #define S5P6440_EINT0CON0		(S5P_VA_GPIO + 0x900)
 #define S5P6440_EINT0FLTCON0		(S5P_VA_GPIO + 0x910)
 #define S5P6440_EINT0FLTCON1		(S5P_VA_GPIO + 0x914)
@@ -34,19 +38,23 @@
 #define S5P6440_EINT0PEND		(S5P_VA_GPIO + 0x924)
 
 /* for LCD */
+
 #define S5P6440_SPCON_LCD_SEL_RGB	(1 << 0)
 #define S5P6440_SPCON_LCD_SEL_MASK	(3 << 0)
 
-/* These set of macros are not really useful for the
- * GPF/GPI/GPJ/GPN/GPP,
- * useful for others set of GPIO's (4 bit)
+/*
+ * These set of macros are not really useful for the
+ * GPF/GPI/GPJ/GPN/GPP, useful for others set of GPIO's (4 bit)
  */
+
 #define S5P6440_GPIO_CONMASK(__gpio)	(0xf << ((__gpio) * 4))
 #define S5P6440_GPIO_INPUT(__gpio)	(0x0 << ((__gpio) * 4))
 #define S5P6440_GPIO_OUTPUT(__gpio)	(0x1 << ((__gpio) * 4))
 
-/* Use these macros for GPF/GPI/GPJ/GPN/GPP set of GPIO (2 bit)
- * */
+/*
+ * Use these macros for GPF/GPI/GPJ/GPN/GPP set of GPIO (2 bit)
+ */
+
 #define S5P6440_GPIO2_CONMASK(__gpio)	(0x3 << ((__gpio) * 2))
 #define S5P6440_GPIO2_INPUT(__gpio)	(0x0 << ((__gpio) * 2))
 #define S5P6440_GPIO2_OUTPUT(__gpio)	(0x1 << ((__gpio) * 2))
diff --git a/arch/arm/mach-s5p6440/include/mach/regs-irq.h b/arch/arm/mach-s5p64x0/include/mach/regs-irq.h
similarity index 66%
rename from arch/arm/mach-s5p6440/include/mach/regs-irq.h
rename to arch/arm/mach-s5p64x0/include/mach/regs-irq.h
index a961f4b..4aaebda 100644
--- a/arch/arm/mach-s5p6440/include/mach/regs-irq.h
+++ b/arch/arm/mach-s5p64x0/include/mach/regs-irq.h
@@ -1,9 +1,9 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/regs-irq.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/regs-irq.h
  *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
- * S5P6440 - IRQ register definitions
+ * S5P64X0 - IRQ register definitions
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/mach-s5p64x0/include/mach/s5p64x0-clock.h b/arch/arm/mach-s5p64x0/include/mach/s5p64x0-clock.h
new file mode 100644
index 0000000..ff85b4b
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/s5p64x0-clock.h
@@ -0,0 +1,46 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/s5p64x0-clock.h
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Header file for s5p64x0 clock support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef __ASM_ARCH_CLOCK_H
+#define __ASM_ARCH_CLOCK_H __FILE__
+
+#include <linux/clk.h>
+
+extern struct clksrc_clk clk_mout_apll;
+extern struct clksrc_clk clk_mout_mpll;
+extern struct clksrc_clk clk_mout_epll;
+
+extern int s5p64x0_epll_enable(struct clk *clk, int enable);
+extern unsigned long s5p64x0_epll_get_rate(struct clk *clk);
+
+extern unsigned long s5p64x0_armclk_get_rate(struct clk *clk);
+extern unsigned long s5p64x0_armclk_round_rate(struct clk *clk, unsigned long rate);
+extern int s5p64x0_armclk_set_rate(struct clk *clk, unsigned long rate);
+
+extern struct clk_ops s5p64x0_clkarm_ops;
+
+extern struct clksrc_clk clk_armclk;
+extern struct clksrc_clk clk_dout_mpll;
+
+extern struct clk *clkset_hclk_low_list[];
+extern struct clksrc_sources clkset_hclk_low;
+
+extern int s5p64x0_pclk_ctrl(struct clk *clk, int enable);
+extern int s5p64x0_hclk0_ctrl(struct clk *clk, int enable);
+extern int s5p64x0_hclk1_ctrl(struct clk *clk, int enable);
+extern int s5p64x0_sclk_ctrl(struct clk *clk, int enable);
+extern int s5p64x0_sclk1_ctrl(struct clk *clk, int enable);
+extern int s5p64x0_mem_ctrl(struct clk *clk, int enable);
+
+extern int s5p64x0_clk48m_ctrl(struct clk *clk, int enable);
+
+#endif /* __ASM_ARCH_CLOCK_H */
diff --git a/arch/arm/mach-s5p64x0/include/mach/spi-clocks.h b/arch/arm/mach-s5p64x0/include/mach/spi-clocks.h
new file mode 100644
index 0000000..170a20a
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/spi-clocks.h
@@ -0,0 +1,20 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/spi-clocks.h
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Copyright (C) 2010 Samsung Electronics Co. Ltd.
+ *	Jaswinder Singh <jassi.brar@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef __ASM_ARCH_SPI_CLKS_H
+#define __ASM_ARCH_SPI_CLKS_H __FILE__
+
+#define S5P64X0_SPI_SRCCLK_PCLK		0
+#define S5P64X0_SPI_SRCCLK_SCLK		1
+
+#endif /* __ASM_ARCH_SPI_CLKS_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/system.h b/arch/arm/mach-s5p64x0/include/mach/system.h
similarity index 69%
rename from arch/arm/mach-s5p6440/include/mach/system.h
rename to arch/arm/mach-s5p64x0/include/mach/system.h
index a359ee3..60f5753 100644
--- a/arch/arm/mach-s5p6440/include/mach/system.h
+++ b/arch/arm/mach-s5p64x0/include/mach/system.h
@@ -1,9 +1,9 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/system.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/system.h
  *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
- * S5P6440 - system support header
+ * S5P64X0 - system support header
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/mach-s5p6440/include/mach/tick.h b/arch/arm/mach-s5p64x0/include/mach/tick.h
similarity index 60%
rename from arch/arm/mach-s5p6440/include/mach/tick.h
rename to arch/arm/mach-s5p64x0/include/mach/tick.h
index 2f25c7f..00aa7f1 100644
--- a/arch/arm/mach-s5p6440/include/mach/tick.h
+++ b/arch/arm/mach-s5p64x0/include/mach/tick.h
@@ -1,9 +1,14 @@
-/* linux/arch/arm/mach-s5p6440/include/mach/tick.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/tick.h
  *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
- * S5P6440 - Timer tick support definitions
+ * Copyright 2008 Openmoko, Inc.
+ * Copyright 2008 Simtec Electronics
+ *	http://armlinux.simtec.co.uk/
+ *	Ben Dooks <ben@simtec.co.uk>
+ *
+ * S5P64X0 - Timer tick support definitions
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/mach-s5p6440/include/mach/timex.h b/arch/arm/mach-s5p64x0/include/mach/timex.h
similarity index 80%
rename from arch/arm/mach-s5p6440/include/mach/timex.h
rename to arch/arm/mach-s5p64x0/include/mach/timex.h
index fb2e8cd..4b91faa 100644
--- a/arch/arm/mach-s5p6440/include/mach/timex.h
+++ b/arch/arm/mach-s5p64x0/include/mach/timex.h
@@ -1,9 +1,12 @@
-/* arch/arm/mach-s3c64xx/include/mach/timex.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/timex.h
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
  * Copyright (c) 2003-2005 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
- * S3C6400 - time parameters
+ * S5P64X0 - time parameters
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/mach-s5p64x0/include/mach/uncompress.h b/arch/arm/mach-s5p64x0/include/mach/uncompress.h
new file mode 100644
index 0000000..c65b229
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/include/mach/uncompress.h
@@ -0,0 +1,212 @@
+/* linux/arch/arm/mach-s5p64x0/include/mach/uncompress.h
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P64X0 - uncompress code
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#ifndef __ASM_ARCH_UNCOMPRESS_H
+#define __ASM_ARCH_UNCOMPRESS_H
+
+#include <mach/map.h>
+
+/*
+ * cannot use commonly <plat/uncompress.h>
+ * because uart base of S5P6440 and S5P6450 is different
+ */
+
+typedef unsigned int upf_t;	/* cannot include linux/serial_core.h */
+
+/* uart setup */
+
+static unsigned int fifo_mask;
+static unsigned int fifo_max;
+
+/* forward declerations */
+
+static void arch_detect_cpu(void);
+
+/* defines for UART registers */
+
+#include <plat/regs-serial.h>
+#include <plat/regs-watchdog.h>
+
+/* working in physical space... */
+#undef S3C2410_WDOGREG
+#define S3C2410_WDOGREG(x) ((S3C24XX_PA_WATCHDOG + (x)))
+
+/* how many bytes we allow into the FIFO at a time in FIFO mode */
+#define FIFO_MAX	 (14)
+
+static unsigned long uart_base;
+
+static __inline__ void get_uart_base(void)
+{
+	unsigned int chipid;
+
+	chipid = *(const volatile unsigned int __force *) 0xE0100118;
+
+	uart_base = S3C_UART_OFFSET * CONFIG_S3C_LOWLEVEL_UART_PORT;
+
+	if ((chipid & 0xff000) == 0x50000)
+		uart_base += 0xEC800000;
+	else
+		uart_base += 0xEC000000;
+}
+
+static __inline__ void uart_wr(unsigned int reg, unsigned int val)
+{
+	volatile unsigned int *ptr;
+
+	get_uart_base();
+	ptr = (volatile unsigned int *)(reg + uart_base);
+	*ptr = val;
+}
+
+static __inline__ unsigned int uart_rd(unsigned int reg)
+{
+	volatile unsigned int *ptr;
+
+	get_uart_base();
+	ptr = (volatile unsigned int *)(reg + uart_base);
+	return *ptr;
+}
+
+/*
+ * we can deal with the case the UARTs are being run
+ * in FIFO mode, so that we don't hold up our execution
+ * waiting for tx to happen...
+ */
+
+static void putc(int ch)
+{
+	if (uart_rd(S3C2410_UFCON) & S3C2410_UFCON_FIFOMODE) {
+		int level;
+
+		while (1) {
+			level = uart_rd(S3C2410_UFSTAT);
+			level &= fifo_mask;
+
+			if (level < fifo_max)
+				break;
+		}
+
+	} else {
+		/* not using fifos */
+
+		while ((uart_rd(S3C2410_UTRSTAT) & S3C2410_UTRSTAT_TXE) != S3C2410_UTRSTAT_TXE)
+			barrier();
+	}
+
+	/* write byte to transmission register */
+	uart_wr(S3C2410_UTXH, ch);
+}
+
+static inline void flush(void)
+{
+}
+
+#define __raw_writel(d, ad)			\
+	do {							\
+		*((volatile unsigned int __force *)(ad)) = (d); \
+	} while (0)
+
+/*
+ * CONFIG_S3C_BOOT_WATCHDOG
+ *
+ * Simple boot-time watchdog setup, to reboot the system if there is
+ * any problem with the boot process
+ */
+
+#ifdef CONFIG_S3C_BOOT_WATCHDOG
+
+#define WDOG_COUNT (0xff00)
+
+static inline void arch_decomp_wdog(void)
+{
+	__raw_writel(WDOG_COUNT, S3C2410_WTCNT);
+}
+
+static void arch_decomp_wdog_start(void)
+{
+	__raw_writel(WDOG_COUNT, S3C2410_WTDAT);
+	__raw_writel(WDOG_COUNT, S3C2410_WTCNT);
+	__raw_writel(S3C2410_WTCON_ENABLE | S3C2410_WTCON_DIV128 | S3C2410_WTCON_RSTEN | S3C2410_WTCON_PRESCALE(0x80), S3C2410_WTCON);
+}
+
+#else
+#define arch_decomp_wdog_start()
+#define arch_decomp_wdog()
+#endif
+
+#ifdef CONFIG_S3C_BOOT_ERROR_RESET
+
+static void arch_decomp_error(const char *x)
+{
+	putstr("\n\n");
+	putstr(x);
+	putstr("\n\n -- System resetting\n");
+
+	__raw_writel(0x4000, S3C2410_WTDAT);
+	__raw_writel(0x4000, S3C2410_WTCNT);
+	__raw_writel(S3C2410_WTCON_ENABLE | S3C2410_WTCON_DIV128 | S3C2410_WTCON_RSTEN | S3C2410_WTCON_PRESCALE(0x40), S3C2410_WTCON);
+
+	while(1);
+}
+
+#define arch_error arch_decomp_error
+#endif
+
+#ifdef CONFIG_S3C_BOOT_UART_FORCE_FIFO
+static inline void arch_enable_uart_fifo(void)
+{
+	u32 fifocon = uart_rd(S3C2410_UFCON);
+
+	if (!(fifocon & S3C2410_UFCON_FIFOMODE)) {
+		fifocon |= S3C2410_UFCON_RESETBOTH;
+		uart_wr(S3C2410_UFCON, fifocon);
+
+		/* wait for fifo reset to complete */
+		while (1) {
+			fifocon = uart_rd(S3C2410_UFCON);
+			if (!(fifocon & S3C2410_UFCON_RESETBOTH))
+				break;
+		}
+	}
+}
+#else
+#define arch_enable_uart_fifo() do { } while(0)
+#endif
+
+static void arch_decomp_setup(void)
+{
+	/*
+	 * we may need to setup the uart(s) here if we are not running
+	 * on an BAST... the BAST will have left the uarts configured
+	 * after calling linux.
+	 */
+
+	arch_detect_cpu();
+	arch_decomp_wdog_start();
+
+	/*
+	 * Enable the UART FIFOs if they where not enabled and our
+	 * configuration says we should turn them on.
+	 */
+
+	arch_enable_uart_fifo();
+}
+
+
+
+static void arch_detect_cpu(void)
+{
+	/* we do not need to do any cpu detection here at the moment. */
+}
+
+#endif /* __ASM_ARCH_UNCOMPRESS_H */
diff --git a/arch/arm/mach-s5p6440/include/mach/vmalloc.h b/arch/arm/mach-s5p64x0/include/mach/vmalloc.h
similarity index 74%
rename from arch/arm/mach-s5p6440/include/mach/vmalloc.h
rename to arch/arm/mach-s5p64x0/include/mach/vmalloc.h
index e3f0eeb..97a9df3 100644
--- a/arch/arm/mach-s5p6440/include/mach/vmalloc.h
+++ b/arch/arm/mach-s5p64x0/include/mach/vmalloc.h
@@ -1,4 +1,7 @@
-/* arch/arm/mach-s5p6440/include/mach/vmalloc.h
+/* linux/arch/arm/mach-s5p64x0/include/mach/vmalloc.h
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
  * Copyright 2010 Ben Dooks <ben-linux@fluff.org>
  *
diff --git a/arch/arm/mach-s5p64x0/init.c b/arch/arm/mach-s5p64x0/init.c
new file mode 100644
index 0000000..79833ca
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/init.c
@@ -0,0 +1,73 @@
+/* linux/arch/arm/mach-s5p64x0/init.c
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * S5P64X0 - Init support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/serial_core.h>
+
+#include <mach/map.h>
+
+#include <plat/cpu.h>
+#include <plat/devs.h>
+#include <plat/s5p6440.h>
+#include <plat/s5p6450.h>
+#include <plat/regs-serial.h>
+
+static struct s3c24xx_uart_clksrc s5p64x0_serial_clocks[] = {
+	[0] = {
+		.name		= "pclk_low",
+		.divisor	= 1,
+		.min_baud	= 0,
+		.max_baud	= 0,
+	},
+	[1] = {
+		.name		= "uclk1",
+		.divisor	= 1,
+		.min_baud	= 0,
+		.max_baud	= 0,
+	},
+};
+
+/* uart registration process */
+
+void __init s5p64x0_common_init_uarts(struct s3c2410_uartcfg *cfg, int no)
+{
+	struct s3c2410_uartcfg *tcfg = cfg;
+	u32 ucnt;
+
+	for (ucnt = 0; ucnt < no; ucnt++, tcfg++) {
+		if (!tcfg->clocks) {
+			tcfg->clocks = s5p64x0_serial_clocks;
+			tcfg->clocks_size = ARRAY_SIZE(s5p64x0_serial_clocks);
+		}
+	}
+}
+
+void __init s5p6440_init_uarts(struct s3c2410_uartcfg *cfg, int no)
+{
+	int uart;
+
+	for (uart = 0; uart < no; uart++) {
+		s5p_uart_resources[uart].resources->start = S5P6440_PA_UART(uart);
+		s5p_uart_resources[uart].resources->end = S5P6440_PA_UART(uart) + S5P_SZ_UART;
+	}
+
+	s5p64x0_common_init_uarts(cfg, no);
+	s3c24xx_init_uartdevs("s3c6400-uart", s5p_uart_resources, cfg, no);
+}
+
+void __init s5p6450_init_uarts(struct s3c2410_uartcfg *cfg, int no)
+{
+	s5p64x0_common_init_uarts(cfg, no);
+	s3c24xx_init_uartdevs("s3c6400-uart", s5p_uart_resources, cfg, no);
+}
diff --git a/arch/arm/mach-s5p6440/mach-smdk6440.c b/arch/arm/mach-s5p64x0/mach-smdk6440.c
similarity index 67%
rename from arch/arm/mach-s5p6440/mach-smdk6440.c
rename to arch/arm/mach-s5p64x0/mach-smdk6440.c
index 9202aaa..87c3f03 100644
--- a/arch/arm/mach-s5p6440/mach-smdk6440.c
+++ b/arch/arm/mach-s5p64x0/mach-smdk6440.c
@@ -1,7 +1,7 @@
-/* linux/arch/arm/mach-s5p6440/mach-smdk6440.c
+/* linux/arch/arm/mach-s5p64x0/mach-smdk6440.c
  *
- * Copyright (c) 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -21,21 +21,22 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/clk.h>
+#include <linux/gpio.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
-
-#include <mach/hardware.h>
-#include <mach/map.h>
-
 #include <asm/irq.h>
 #include <asm/mach-types.h>
 
-#include <plat/regs-serial.h>
+#include <mach/hardware.h>
+#include <mach/map.h>
+#include <mach/regs-clock.h>
+#include <mach/i2c.h>
 
+#include <plat/regs-serial.h>
+#include <plat/gpio-cfg.h>
 #include <plat/s5p6440.h>
 #include <plat/clock.h>
-#include <mach/regs-clock.h>
 #include <plat/devs.h>
 #include <plat/cpu.h>
 #include <plat/iic.h>
@@ -58,43 +59,60 @@
 
 static struct s3c2410_uartcfg smdk6440_uartcfgs[] __initdata = {
 	[0] = {
-		.hwport	     = 0,
-		.flags	     = 0,
-		.ucon	     = SMDK6440_UCON_DEFAULT,
-		.ulcon	     = SMDK6440_ULCON_DEFAULT,
-		.ufcon	     = SMDK6440_UFCON_DEFAULT,
+		.hwport		= 0,
+		.flags		= 0,
+		.ucon		= SMDK6440_UCON_DEFAULT,
+		.ulcon		= SMDK6440_ULCON_DEFAULT,
+		.ufcon		= SMDK6440_UFCON_DEFAULT,
 	},
 	[1] = {
-		.hwport	     = 1,
-		.flags	     = 0,
-		.ucon	     = SMDK6440_UCON_DEFAULT,
-		.ulcon	     = SMDK6440_ULCON_DEFAULT,
-		.ufcon	     = SMDK6440_UFCON_DEFAULT,
+		.hwport		= 1,
+		.flags		= 0,
+		.ucon		= SMDK6440_UCON_DEFAULT,
+		.ulcon		= SMDK6440_ULCON_DEFAULT,
+		.ufcon		= SMDK6440_UFCON_DEFAULT,
 	},
 	[2] = {
-		.hwport	     = 2,
-		.flags	     = 0,
-		.ucon	     = SMDK6440_UCON_DEFAULT,
-		.ulcon	     = SMDK6440_ULCON_DEFAULT,
-		.ufcon	     = SMDK6440_UFCON_DEFAULT,
+		.hwport		= 2,
+		.flags		= 0,
+		.ucon		= SMDK6440_UCON_DEFAULT,
+		.ulcon		= SMDK6440_ULCON_DEFAULT,
+		.ufcon		= SMDK6440_UFCON_DEFAULT,
 	},
 	[3] = {
-		.hwport	     = 3,
-		.flags	     = 0,
-		.ucon	     = SMDK6440_UCON_DEFAULT,
-		.ulcon	     = SMDK6440_ULCON_DEFAULT,
-		.ufcon	     = SMDK6440_UFCON_DEFAULT,
+		.hwport		= 3,
+		.flags		= 0,
+		.ucon		= SMDK6440_UCON_DEFAULT,
+		.ulcon		= SMDK6440_ULCON_DEFAULT,
+		.ufcon		= SMDK6440_UFCON_DEFAULT,
 	},
 };
 
 static struct platform_device *smdk6440_devices[] __initdata = {
-	&s5p6440_device_iis,
 	&s3c_device_adc,
 	&s3c_device_rtc,
 	&s3c_device_i2c0,
 	&s3c_device_i2c1,
 	&s3c_device_ts,
 	&s3c_device_wdt,
+	&s5p6440_device_iis,
+};
+
+static struct s3c2410_platform_i2c s5p6440_i2c0_data __initdata = {
+	.flags		= 0,
+	.slave_addr	= 0x10,
+	.frequency	= 100*1000,
+	.sda_delay	= 100,
+	.cfg_gpio	= s5p6440_i2c0_cfg_gpio,
+};
+
+static struct s3c2410_platform_i2c s5p6440_i2c1_data __initdata = {
+	.flags		= 0,
+	.bus_num	= 1,
+	.slave_addr	= 0x10,
+	.frequency	= 100*1000,
+	.sda_delay	= 100,
+	.cfg_gpio	= s5p6440_i2c1_cfg_gpio,
 };
 
 static struct i2c_board_info smdk6440_i2c_devs0[] __initdata = {
@@ -113,7 +131,7 @@
 
 static void __init smdk6440_map_io(void)
 {
-	s5p_init_io(NULL, 0, S5P_SYS_ID);
+	s5p_init_io(NULL, 0, S5P64X0_SYS_ID);
 	s3c24xx_init_clocks(12000000);
 	s3c24xx_init_uarts(smdk6440_uartcfgs, ARRAY_SIZE(smdk6440_uartcfgs));
 }
@@ -122,9 +140,8 @@
 {
 	s3c24xx_ts_set_platdata(&s3c_ts_platform);
 
-	/* I2C */
-	s3c_i2c0_set_platdata(NULL);
-	s3c_i2c1_set_platdata(NULL);
+	s3c_i2c0_set_platdata(&s5p6440_i2c0_data);
+	s3c_i2c1_set_platdata(&s5p6440_i2c1_data);
 	i2c_register_board_info(0, smdk6440_i2c_devs0,
 			ARRAY_SIZE(smdk6440_i2c_devs0));
 	i2c_register_board_info(1, smdk6440_i2c_devs1,
@@ -135,9 +152,7 @@
 
 MACHINE_START(SMDK6440, "SMDK6440")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
-	.boot_params	= S5P_PA_SDRAM + 0x100,
+	.boot_params	= S5P64X0_PA_SDRAM + 0x100,
 
 	.init_irq	= s5p6440_init_irq,
 	.map_io		= smdk6440_map_io,
diff --git a/arch/arm/mach-s5p64x0/mach-smdk6450.c b/arch/arm/mach-s5p64x0/mach-smdk6450.c
new file mode 100644
index 0000000..d609f5a
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/mach-smdk6450.c
@@ -0,0 +1,180 @@
+/* linux/arch/arm/mach-s5p64x0/mach-smdk6450.c
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/timer.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/i2c.h>
+#include <linux/serial_core.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/gpio.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/irq.h>
+#include <asm/mach-types.h>
+
+#include <mach/hardware.h>
+#include <mach/map.h>
+#include <mach/regs-clock.h>
+#include <mach/i2c.h>
+
+#include <plat/regs-serial.h>
+#include <plat/gpio-cfg.h>
+#include <plat/s5p6450.h>
+#include <plat/clock.h>
+#include <plat/devs.h>
+#include <plat/cpu.h>
+#include <plat/iic.h>
+#include <plat/pll.h>
+#include <plat/adc.h>
+#include <plat/ts.h>
+
+#define SMDK6450_UCON_DEFAULT	(S3C2410_UCON_TXILEVEL |	\
+				S3C2410_UCON_RXILEVEL |		\
+				S3C2410_UCON_TXIRQMODE |	\
+				S3C2410_UCON_RXIRQMODE |	\
+				S3C2410_UCON_RXFIFO_TOI |	\
+				S3C2443_UCON_RXERR_IRQEN)
+
+#define SMDK6450_ULCON_DEFAULT	S3C2410_LCON_CS8
+
+#define SMDK6450_UFCON_DEFAULT	(S3C2410_UFCON_FIFOMODE |	\
+				S3C2440_UFCON_TXTRIG16 |	\
+				S3C2410_UFCON_RXTRIG8)
+
+static struct s3c2410_uartcfg smdk6450_uartcfgs[] __initdata = {
+	[0] = {
+		.hwport		= 0,
+		.flags		= 0,
+		.ucon		= SMDK6450_UCON_DEFAULT,
+		.ulcon		= SMDK6450_ULCON_DEFAULT,
+		.ufcon		= SMDK6450_UFCON_DEFAULT,
+	},
+	[1] = {
+		.hwport		= 1,
+		.flags		= 0,
+		.ucon		= SMDK6450_UCON_DEFAULT,
+		.ulcon		= SMDK6450_ULCON_DEFAULT,
+		.ufcon		= SMDK6450_UFCON_DEFAULT,
+	},
+	[2] = {
+		.hwport		= 2,
+		.flags		= 0,
+		.ucon		= SMDK6450_UCON_DEFAULT,
+		.ulcon		= SMDK6450_ULCON_DEFAULT,
+		.ufcon		= SMDK6450_UFCON_DEFAULT,
+	},
+	[3] = {
+		.hwport		= 3,
+		.flags		= 0,
+		.ucon		= SMDK6450_UCON_DEFAULT,
+		.ulcon		= SMDK6450_ULCON_DEFAULT,
+		.ufcon		= SMDK6450_UFCON_DEFAULT,
+	},
+#if CONFIG_SERIAL_SAMSUNG_UARTS > 4
+	[4] = {
+		.hwport		= 4,
+		.flags		= 0,
+		.ucon		= SMDK6450_UCON_DEFAULT,
+		.ulcon		= SMDK6450_ULCON_DEFAULT,
+		.ufcon		= SMDK6450_UFCON_DEFAULT,
+	},
+#endif
+#if CONFIG_SERIAL_SAMSUNG_UARTS > 5
+	[5] = {
+		.hwport		= 5,
+		.flags		= 0,
+		.ucon		= SMDK6450_UCON_DEFAULT,
+		.ulcon		= SMDK6450_ULCON_DEFAULT,
+		.ufcon		= SMDK6450_UFCON_DEFAULT,
+	},
+#endif
+};
+
+static struct platform_device *smdk6450_devices[] __initdata = {
+	&s3c_device_adc,
+	&s3c_device_rtc,
+	&s3c_device_i2c0,
+	&s3c_device_i2c1,
+	&s3c_device_ts,
+	&s3c_device_wdt,
+	&s5p6450_device_iis0,
+	/* s5p6450_device_spi0 will be added */
+};
+
+static struct s3c2410_platform_i2c s5p6450_i2c0_data __initdata = {
+	.flags		= 0,
+	.slave_addr	= 0x10,
+	.frequency	= 100*1000,
+	.sda_delay	= 100,
+	.cfg_gpio	= s5p6450_i2c0_cfg_gpio,
+};
+
+static struct s3c2410_platform_i2c s5p6450_i2c1_data __initdata = {
+	.flags		= 0,
+	.bus_num	= 1,
+	.slave_addr	= 0x10,
+	.frequency	= 100*1000,
+	.sda_delay	= 100,
+	.cfg_gpio	= s5p6450_i2c1_cfg_gpio,
+};
+
+static struct i2c_board_info smdk6450_i2c_devs0[] __initdata = {
+	{ I2C_BOARD_INFO("24c08", 0x50), },	/* Samsung KS24C080C EEPROM */
+};
+
+static struct i2c_board_info smdk6450_i2c_devs1[] __initdata = {
+	{ I2C_BOARD_INFO("24c128", 0x57), },/* Samsung S524AD0XD1 EEPROM */
+};
+
+static struct s3c2410_ts_mach_info s3c_ts_platform __initdata = {
+	.delay			= 10000,
+	.presc			= 49,
+	.oversampling_shift	= 2,
+};
+
+static void __init smdk6450_map_io(void)
+{
+	s5p_init_io(NULL, 0, S5P64X0_SYS_ID);
+	s3c24xx_init_clocks(19200000);
+	s3c24xx_init_uarts(smdk6450_uartcfgs, ARRAY_SIZE(smdk6450_uartcfgs));
+}
+
+static void __init smdk6450_machine_init(void)
+{
+	s3c24xx_ts_set_platdata(&s3c_ts_platform);
+
+	s3c_i2c0_set_platdata(&s5p6450_i2c0_data);
+	s3c_i2c1_set_platdata(&s5p6450_i2c1_data);
+	i2c_register_board_info(0, smdk6450_i2c_devs0,
+			ARRAY_SIZE(smdk6450_i2c_devs0));
+	i2c_register_board_info(1, smdk6450_i2c_devs1,
+			ARRAY_SIZE(smdk6450_i2c_devs1));
+
+	platform_add_devices(smdk6450_devices, ARRAY_SIZE(smdk6450_devices));
+}
+
+MACHINE_START(SMDK6450, "SMDK6450")
+	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
+	.boot_params	= S5P64X0_PA_SDRAM + 0x100,
+
+	.init_irq	= s5p6450_init_irq,
+	.map_io		= smdk6450_map_io,
+	.init_machine	= smdk6450_machine_init,
+	.timer		= &s3c24xx_timer,
+MACHINE_END
diff --git a/arch/arm/mach-s5p64x0/setup-i2c0.c b/arch/arm/mach-s5p64x0/setup-i2c0.c
new file mode 100644
index 0000000..dc4cc65
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/setup-i2c0.c
@@ -0,0 +1,42 @@
+/* linux/arch/arm/mach-s5p64x0/setup-i2c0.c
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * I2C0 GPIO configuration.
+ *
+ * Based on plat-s3c64x0/setup-i2c0.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/gpio.h>
+
+struct platform_device; /* don't need the contents */
+
+#include <plat/gpio-cfg.h>
+#include <plat/iic.h>
+
+#include <mach/i2c.h>
+
+void s5p6440_i2c0_cfg_gpio(struct platform_device *dev)
+{
+	s3c_gpio_cfgpin(S5P6440_GPB(5), S3C_GPIO_SFN(2));
+	s3c_gpio_setpull(S5P6440_GPB(5), S3C_GPIO_PULL_UP);
+	s3c_gpio_cfgpin(S5P6440_GPB(6), S3C_GPIO_SFN(2));
+	s3c_gpio_setpull(S5P6440_GPB(6), S3C_GPIO_PULL_UP);
+}
+
+void s5p6450_i2c0_cfg_gpio(struct platform_device *dev)
+{
+	s3c_gpio_cfgpin(S5P6450_GPB(5), S3C_GPIO_SFN(2));
+	s3c_gpio_setpull(S5P6450_GPB(5), S3C_GPIO_PULL_UP);
+	s3c_gpio_cfgpin(S5P6450_GPB(6), S3C_GPIO_SFN(2));
+	s3c_gpio_setpull(S5P6450_GPB(6), S3C_GPIO_PULL_UP);
+}
+
+void s3c_i2c0_cfg_gpio(struct platform_device *dev) { }
diff --git a/arch/arm/mach-s5p64x0/setup-i2c1.c b/arch/arm/mach-s5p64x0/setup-i2c1.c
new file mode 100644
index 0000000..2edd791
--- /dev/null
+++ b/arch/arm/mach-s5p64x0/setup-i2c1.c
@@ -0,0 +1,42 @@
+/* linux/arch/arm/mach-s5p64xx/setup-i2c1.c
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * I2C1 GPIO configuration.
+ *
+ * Based on plat-s3c64xx/setup-i2c0.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/gpio.h>
+
+struct platform_device; /* don't need the contents */
+
+#include <plat/gpio-cfg.h>
+#include <plat/iic.h>
+
+#include <mach/i2c.h>
+
+void s5p6440_i2c1_cfg_gpio(struct platform_device *dev)
+{
+	s3c_gpio_cfgpin(S5P6440_GPR(9), S3C_GPIO_SFN(6));
+	s3c_gpio_setpull(S5P6440_GPR(9), S3C_GPIO_PULL_UP);
+	s3c_gpio_cfgpin(S5P6440_GPR(10), S3C_GPIO_SFN(6));
+	s3c_gpio_setpull(S5P6440_GPR(10), S3C_GPIO_PULL_UP);
+}
+
+void s5p6450_i2c1_cfg_gpio(struct platform_device *dev)
+{
+	s3c_gpio_cfgpin(S5P6450_GPR(9), S3C_GPIO_SFN(6));
+	s3c_gpio_setpull(S5P6450_GPR(9), S3C_GPIO_PULL_UP);
+	s3c_gpio_cfgpin(S5P6450_GPR(10), S3C_GPIO_SFN(6));
+	s3c_gpio_setpull(S5P6450_GPR(10), S3C_GPIO_PULL_UP);
+}
+
+void s3c_i2c1_cfg_gpio(struct platform_device *dev) { }
diff --git a/arch/arm/mach-s5pc100/cpu.c b/arch/arm/mach-s5pc100/cpu.c
index cd1afbc..fd2708e 100644
--- a/arch/arm/mach-s5pc100/cpu.c
+++ b/arch/arm/mach-s5pc100/cpu.c
@@ -1,5 +1,8 @@
 /* linux/arch/arm/mach-s5pc100/cpu.c
  *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
  * Copyright 2009 Samsung Electronics Co.
  *	Byungho Min <bhmin@samsung.com>
  *
@@ -57,11 +60,31 @@
 		.length		= SZ_16K,
 		.type		= MT_DEVICE,
 	}, {
-		.virtual	= (unsigned long)VA_VIC2,
-		.pfn		= __phys_to_pfn(S5P_PA_VIC2),
+		.virtual	= (unsigned long)S5P_VA_GPIO,
+		.pfn		= __phys_to_pfn(S5PC100_PA_GPIO),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)VA_VIC0,
+		.pfn		= __phys_to_pfn(S5PC100_PA_VIC0),
 		.length		= SZ_16K,
 		.type		= MT_DEVICE,
 	}, {
+		.virtual	= (unsigned long)VA_VIC1,
+		.pfn		= __phys_to_pfn(S5PC100_PA_VIC1),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)VA_VIC2,
+		.pfn		= __phys_to_pfn(S5PC100_PA_VIC2),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S3C_VA_UART,
+		.pfn		= __phys_to_pfn(S3C_PA_UART),
+		.length		= SZ_512K,
+		.type		= MT_DEVICE,
+	}, {
 		.virtual	= (unsigned long)S5PC100_VA_OTHERS,
 		.pfn		= __phys_to_pfn(S5PC100_PA_OTHERS),
 		.length		= SZ_4K,
diff --git a/arch/arm/mach-s5pc100/include/mach/debug-macro.S b/arch/arm/mach-s5pc100/include/mach/debug-macro.S
index 70e02e9..b2ba95d 100644
--- a/arch/arm/mach-s5pc100/include/mach/debug-macro.S
+++ b/arch/arm/mach-s5pc100/include/mach/debug-macro.S
@@ -22,13 +22,12 @@
 	 * aligned and add in the offset when we load the value here.
 	 */
 
-	.macro addruart, rx, rtmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, = S3C_PA_UART
-		ldrne	\rx, = S3C_VA_UART
+	.macro addruart, rp, rv
+		ldr	\rp, = S3C_PA_UART
+		ldr	\rv, = S3C_VA_UART
 #if CONFIG_DEBUG_S3C_UART != 0
-		add	\rx, \rx, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rp, \rp, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rv, \rv, #(0x400 * CONFIG_DEBUG_S3C_UART)
 #endif
 	.endm
 
diff --git a/arch/arm/mach-s5pc100/include/mach/map.h b/arch/arm/mach-s5pc100/include/mach/map.h
index 01b9134..8751ef4 100644
--- a/arch/arm/mach-s5pc100/include/mach/map.h
+++ b/arch/arm/mach-s5pc100/include/mach/map.h
@@ -44,19 +44,16 @@
 #define S5PC100_PA_OTHERS	(0xE0200000)
 #define S5PC100_VA_OTHERS	(S3C_VA_SYS + 0x10000)
 
-#define S5P_PA_GPIO		(0xE0300000)
+#define S5PC100_PA_GPIO		(0xE0300000)
 #define S5PC1XX_VA_GPIO		S3C_ADDR(0x00500000)
 
 /* Interrupt */
-#define S5PC100_PA_VIC		(0xE4000000)
+#define S5PC100_PA_VIC0		(0xE4000000)
+#define S5PC100_PA_VIC1		(0xE4100000)
+#define S5PC100_PA_VIC2		(0xE4200000)
 #define S5PC100_VA_VIC		S3C_VA_IRQ
-#define S5PC100_PA_VIC_OFFSET	0x100000
 #define S5PC100_VA_VIC_OFFSET	0x10000
-#define S5PC1XX_PA_VIC(x)	(S5PC100_PA_VIC + ((x) * S5PC100_PA_VIC_OFFSET))
 #define S5PC1XX_VA_VIC(x)	(S5PC100_VA_VIC + ((x) * S5PC100_VA_VIC_OFFSET))
-#define S5P_PA_VIC0		S5PC1XX_PA_VIC(0)
-#define S5P_PA_VIC1		S5PC1XX_PA_VIC(1)
-#define S5P_PA_VIC2		S5PC1XX_PA_VIC(2)
 
 
 #define S5PC100_PA_ONENAND	(0xE7100000)
diff --git a/arch/arm/mach-s5pc100/mach-smdkc100.c b/arch/arm/mach-s5pc100/mach-smdkc100.c
index 020c3f9..880fb07 100644
--- a/arch/arm/mach-s5pc100/mach-smdkc100.c
+++ b/arch/arm/mach-s5pc100/mach-smdkc100.c
@@ -235,8 +235,6 @@
 
 MACHINE_START(SMDKC100, "SMDKC100")
 	/* Maintainer: Byungho Min <bhmin@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S5P_PA_SDRAM + 0x100,
 	.init_irq	= s5pc100_init_irq,
 	.map_io		= smdkc100_map_io,
diff --git a/arch/arm/mach-s5pv210/Kconfig b/arch/arm/mach-s5pv210/Kconfig
index d3a3895..5315fec 100644
--- a/arch/arm/mach-s5pv210/Kconfig
+++ b/arch/arm/mach-s5pv210/Kconfig
@@ -53,11 +53,6 @@
 	help
 	  Common setup code for SDHCI gpio.
 
-config S5PC110_DEV_ONENAND
-	bool
-	help
-	  Compile in platform device definition for OneNAND1 controller
-
 menu "S5PC110 Machines"
 
 config MACH_AQUILA
@@ -71,7 +66,7 @@
 	select S3C_DEV_HSMMC
 	select S3C_DEV_HSMMC1
 	select S3C_DEV_HSMMC2
-	select S5PC110_DEV_ONENAND
+	select S5P_DEV_ONENAND
 	select S5PV210_SETUP_FB_24BPP
 	select S5PV210_SETUP_SDHCI
 	help
@@ -88,7 +83,7 @@
 	select S3C_DEV_HSMMC
 	select S3C_DEV_HSMMC1
 	select S3C_DEV_HSMMC2
-	select S5PC110_DEV_ONENAND
+	select S5P_DEV_ONENAND
 	select S5PV210_SETUP_FB_24BPP
 	select S5PV210_SETUP_SDHCI
 	help
diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile
index 05048c5..7045489 100644
--- a/arch/arm/mach-s5pv210/Makefile
+++ b/arch/arm/mach-s5pv210/Makefile
@@ -26,7 +26,6 @@
 
 obj-y				+= dev-audio.o
 obj-$(CONFIG_S3C64XX_DEV_SPI)	+= dev-spi.o
-obj-$(CONFIG_S5PC110_DEV_ONENAND) += dev-onenand.o
 
 obj-$(CONFIG_S5PV210_SETUP_FB_24BPP)	+= setup-fb-24bpp.o
 obj-$(CONFIG_S5PV210_SETUP_I2C1) 	+= setup-i2c1.o
diff --git a/arch/arm/mach-s5pv210/cpu.c b/arch/arm/mach-s5pv210/cpu.c
index 245b82b..2f16bfc 100644
--- a/arch/arm/mach-s5pv210/cpu.c
+++ b/arch/arm/mach-s5pv210/cpu.c
@@ -1,7 +1,7 @@
 /* linux/arch/arm/mach-s5pv210/cpu.c
  *
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ *		http://www.samsung.com
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -51,6 +51,21 @@
 		.length		= SZ_4K,
 		.type		= MT_DEVICE,
 	}, {
+		.virtual	= (unsigned long)S5P_VA_GPIO,
+		.pfn		= __phys_to_pfn(S5PV210_PA_GPIO),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)VA_VIC0,
+		.pfn		= __phys_to_pfn(S5PV210_PA_VIC0),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)VA_VIC1,
+		.pfn		= __phys_to_pfn(S5PV210_PA_VIC1),
+		.length		= SZ_16K,
+		.type		= MT_DEVICE,
+	}, {
 		.virtual	= (unsigned long)VA_VIC2,
 		.pfn		= __phys_to_pfn(S5PV210_PA_VIC2),
 		.length		= SZ_16K,
@@ -61,6 +76,11 @@
 		.length		= SZ_16K,
 		.type		= MT_DEVICE,
 	}, {
+		.virtual	= (unsigned long)S3C_VA_UART,
+		.pfn		= __phys_to_pfn(S3C_PA_UART),
+		.length		= SZ_512K,
+		.type		= MT_DEVICE,
+	}, {
 		.virtual	= (unsigned long)S5P_VA_SROMC,
 		.pfn		= __phys_to_pfn(S5PV210_PA_SROMC),
 		.length		= SZ_4K,
diff --git a/arch/arm/mach-s5pv210/dev-onenand.c b/arch/arm/mach-s5pv210/dev-onenand.c
deleted file mode 100644
index f8ede33..0000000
--- a/arch/arm/mach-s5pv210/dev-onenand.c
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * linux/arch/arm/mach-s5pv210/dev-onenand.c
- *
- *  Copyright (c) 2008-2010 Samsung Electronics
- *  Kyungmin Park <kyungmin.park@samsung.com>
- *
- * S5PC110 series device definition for OneNAND devices
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/onenand.h>
-
-#include <mach/irqs.h>
-#include <mach/map.h>
-
-static struct resource s5pc110_onenand_resources[] = {
-	[0] = {
-		.start	= S5PC110_PA_ONENAND,
-		.end	= S5PC110_PA_ONENAND + SZ_128K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= S5PC110_PA_ONENAND_DMA,
-		.end	= S5PC110_PA_ONENAND_DMA + SZ_8K - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[2] = {
-		.start	= IRQ_ONENAND_AUDI,
-		.end	= IRQ_ONENAND_AUDI,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device s5pc110_device_onenand = {
-	.name		= "s5pc110-onenand",
-	.id		= -1,
-	.num_resources	= ARRAY_SIZE(s5pc110_onenand_resources),
-	.resource	= s5pc110_onenand_resources,
-};
-
-void s5pc110_onenand_set_platdata(struct onenand_platform_data *pdata)
-{
-	struct onenand_platform_data *pd;
-
-	pd = kmemdup(pdata, sizeof(struct onenand_platform_data), GFP_KERNEL);
-	if (!pd)
-		printk(KERN_ERR "%s: no memory for platform data\n", __func__);
-	s5pc110_device_onenand.dev.platform_data = pd;
-}
diff --git a/arch/arm/mach-s5pv210/include/mach/debug-macro.S b/arch/arm/mach-s5pv210/include/mach/debug-macro.S
index 7872f5c..169fe65 100644
--- a/arch/arm/mach-s5pv210/include/mach/debug-macro.S
+++ b/arch/arm/mach-s5pv210/include/mach/debug-macro.S
@@ -21,13 +21,12 @@
 	 * aligned and add in the offset when we load the value here.
 	 */
 
-	.macro addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, = S3C_PA_UART
-		ldrne	\rx, = S3C_VA_UART
+	.macro addruart, rp, rv
+		ldr	\rp, = S3C_PA_UART
+		ldr	\rv, = S3C_VA_UART
 #if CONFIG_DEBUG_S3C_UART != 0
-		add	\rx, \rx, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rp, \rp, #(0x400 * CONFIG_DEBUG_S3C_UART)
+		add	\rv, \rv, #(0x400 * CONFIG_DEBUG_S3C_UART)
 #endif
 	.endm
 
diff --git a/arch/arm/mach-s5pv210/include/mach/map.h b/arch/arm/mach-s5pv210/include/mach/map.h
index dd4fb6b..bd9afd5 100644
--- a/arch/arm/mach-s5pv210/include/mach/map.h
+++ b/arch/arm/mach-s5pv210/include/mach/map.h
@@ -17,7 +17,10 @@
 #include <plat/map-s5p.h>
 
 #define S5PC110_PA_ONENAND	(0xB0000000)
+#define S5P_PA_ONENAND		S5PC110_PA_ONENAND
+
 #define S5PC110_PA_ONENAND_DMA	(0xB0600000)
+#define S5P_PA_ONENAND_DMA	S5PC110_PA_ONENAND_DMA
 
 #define S5PV210_PA_CHIPID	(0xE0000000)
 #define S5P_PA_CHIPID		S5PV210_PA_CHIPID
@@ -26,7 +29,6 @@
 #define S5P_PA_SYSCON		S5PV210_PA_SYSCON
 
 #define S5PV210_PA_GPIO		(0xE0200000)
-#define S5P_PA_GPIO		S5PV210_PA_GPIO
 
 /* SPI */
 #define S5PV210_PA_SPI0		0xE1300000
@@ -72,16 +74,9 @@
 #define S5PV210_PA_HSMMC(x)	(0xEB000000 + ((x) * 0x100000))
 
 #define S5PV210_PA_VIC0		(0xF2000000)
-#define S5P_PA_VIC0		S5PV210_PA_VIC0
-
 #define S5PV210_PA_VIC1		(0xF2100000)
-#define S5P_PA_VIC1		S5PV210_PA_VIC1
-
 #define S5PV210_PA_VIC2		(0xF2200000)
-#define S5P_PA_VIC2		S5PV210_PA_VIC2
-
 #define S5PV210_PA_VIC3		(0xF2300000)
-#define S5P_PA_VIC3		S5PV210_PA_VIC3
 
 #define S5PV210_PA_SDRAM	(0x20000000)
 #define S5P_PA_SDRAM		S5PV210_PA_SDRAM
diff --git a/arch/arm/mach-s5pv210/mach-aquila.c b/arch/arm/mach-s5pv210/mach-aquila.c
index 0dda801..0088308 100644
--- a/arch/arm/mach-s5pv210/mach-aquila.c
+++ b/arch/arm/mach-s5pv210/mach-aquila.c
@@ -477,7 +477,7 @@
 	&aquila_i2c_gpio_pmic,
 	&aquila_device_gpiokeys,
 	&s3c_device_fb,
-	&s5pc110_device_onenand,
+	&s5p_device_onenand,
 	&s3c_device_hsmmc0,
 	&s3c_device_hsmmc1,
 	&s3c_device_hsmmc2,
@@ -516,8 +516,6 @@
 	/* Maintainers:
 	   Marek Szyprowski <m.szyprowski@samsung.com>
 	   Kyungmin Park <kyungmin.park@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S5P_PA_SDRAM + 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= aquila_map_io,
diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c
index 53754d7..d9ecf57 100644
--- a/arch/arm/mach-s5pv210/mach-goni.c
+++ b/arch/arm/mach-s5pv210/mach-goni.c
@@ -456,7 +456,7 @@
 
 static struct platform_device *goni_devices[] __initdata = {
 	&s3c_device_fb,
-	&s5pc110_device_onenand,
+	&s5p_device_onenand,
 	&goni_i2c_gpio_pmic,
 	&goni_device_gpiokeys,
 	&s5p_device_fimc0,
@@ -491,8 +491,6 @@
 
 MACHINE_START(GONI, "GONI")
 	/* Maintainers: Kyungmin Park <kyungmin.park@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S5P_PA_SDRAM + 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= goni_map_io,
diff --git a/arch/arm/mach-s5pv210/mach-smdkc110.c b/arch/arm/mach-s5pv210/mach-smdkc110.c
index 8211bb8..cea9bca 100644
--- a/arch/arm/mach-s5pv210/mach-smdkc110.c
+++ b/arch/arm/mach-s5pv210/mach-smdkc110.c
@@ -127,8 +127,6 @@
 
 MACHINE_START(SMDKC110, "SMDKC110")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S5P_PA_SDRAM + 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= smdkc110_map_io,
diff --git a/arch/arm/mach-s5pv210/mach-smdkv210.c b/arch/arm/mach-s5pv210/mach-smdkv210.c
index fbbc0a3..83189ae 100644
--- a/arch/arm/mach-s5pv210/mach-smdkv210.c
+++ b/arch/arm/mach-s5pv210/mach-smdkv210.c
@@ -165,8 +165,6 @@
 
 MACHINE_START(SMDKV210, "SMDKV210")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S5P_PA_SDRAM + 0x100,
 	.init_irq	= s5pv210_init_irq,
 	.map_io		= smdkv210_map_io,
diff --git a/arch/arm/mach-s5pv310/cpu.c b/arch/arm/mach-s5pv310/cpu.c
index e5b261a..4add3985 100644
--- a/arch/arm/mach-s5pv310/cpu.c
+++ b/arch/arm/mach-s5pv310/cpu.c
@@ -31,21 +31,6 @@
 /* Initial IO mappings */
 static struct map_desc s5pv310_iodesc[] __initdata = {
 	{
-		.virtual	= (unsigned long)S5P_VA_COREPERI_BASE,
-		.pfn		= __phys_to_pfn(S5PV310_PA_COREPERI),
-		.length		= SZ_8K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)S5P_VA_COMBINER_BASE,
-		.pfn		= __phys_to_pfn(S5PV310_PA_COMBINER),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)S5P_VA_L2CC,
-		.pfn		= __phys_to_pfn(S5PV310_PA_L2CC),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
 		.virtual	= (unsigned long)S5P_VA_SYSRAM,
 		.pfn		= __phys_to_pfn(S5PV310_PA_SYSRAM),
 		.length		= SZ_4K,
@@ -55,6 +40,31 @@
 		.pfn		= __phys_to_pfn(S5PV310_PA_CMU),
 		.length		= SZ_128K,
 		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_COMBINER_BASE,
+		.pfn		= __phys_to_pfn(S5PV310_PA_COMBINER),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_COREPERI_BASE,
+		.pfn		= __phys_to_pfn(S5PV310_PA_COREPERI),
+		.length		= SZ_8K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_L2CC,
+		.pfn		= __phys_to_pfn(S5PV310_PA_L2CC),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S5P_VA_GPIO,
+		.pfn		= __phys_to_pfn(S5PV310_PA_GPIO1),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)S3C_VA_UART,
+		.pfn		= __phys_to_pfn(S3C_PA_UART),
+		.length		= SZ_512K,
+		.type		= MT_DEVICE,
 	},
 };
 
diff --git a/arch/arm/mach-s5pv310/include/mach/debug-macro.S b/arch/arm/mach-s5pv310/include/mach/debug-macro.S
index 6fb3893..b0d920c 100644
--- a/arch/arm/mach-s5pv310/include/mach/debug-macro.S
+++ b/arch/arm/mach-s5pv310/include/mach/debug-macro.S
@@ -20,13 +20,12 @@
 	 * aligned and add in the offset when we load the value here.
 	 */
 
-	.macro addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1
-		ldreq	\rx, = S3C_PA_UART
-		ldrne	\rx, = S3C_VA_UART
+	.macro addruart, rp, rv
+		ldreq	\rp, = S3C_PA_UART
+		ldrne	\rv, = S3C_VA_UART
 #if CONFIG_DEBUG_S3C_UART != 0
-		add	\rx, \rx, #(0x10000 * CONFIG_DEBUG_S3C_UART)
+		add	\rp, \rp, #(0x10000 * CONFIG_DEBUG_S3C_UART)
+		add	\rv, \rv, #(0x10000 * CONFIG_DEBUG_S3C_UART)
 #endif
 	.endm
 
diff --git a/arch/arm/mach-s5pv310/include/mach/irqs.h b/arch/arm/mach-s5pv310/include/mach/irqs.h
index 4cdedda..471fc3b 100644
--- a/arch/arm/mach-s5pv310/include/mach/irqs.h
+++ b/arch/arm/mach-s5pv310/include/mach/irqs.h
@@ -68,6 +68,8 @@
 
 #define IRQ_IIC			COMBINER_IRQ(27, 0)
 
+#define IRQ_ONENAND_AUDI	COMBINER_IRQ(34, 0)
+
 /* Set the default NR_IRQS */
 
 #define NR_IRQS			COMBINER_IRQ(MAX_COMBINER_NR, 0)
diff --git a/arch/arm/mach-s5pv310/include/mach/map.h b/arch/arm/mach-s5pv310/include/mach/map.h
index 213e110..aff6d23 100644
--- a/arch/arm/mach-s5pv310/include/mach/map.h
+++ b/arch/arm/mach-s5pv310/include/mach/map.h
@@ -25,6 +25,12 @@
 
 #define S5PV310_PA_SYSRAM		(0x02025000)
 
+#define S5PC210_PA_ONENAND		(0x0C000000)
+#define S5P_PA_ONENAND			S5PC210_PA_ONENAND
+
+#define S5PC210_PA_ONENAND_DMA		(0x0C600000)
+#define S5P_PA_ONENAND_DMA		S5PC210_PA_ONENAND_DMA
+
 #define S5PV310_PA_CHIPID		(0x10000000)
 #define S5P_PA_CHIPID			S5PV310_PA_CHIPID
 
@@ -46,7 +52,6 @@
 #define S5PV310_PA_GPIO1		(0x11400000)
 #define S5PV310_PA_GPIO2		(0x11000000)
 #define S5PV310_PA_GPIO3		(0x03860000)
-#define S5P_PA_GPIO			S5PV310_PA_GPIO1
 
 #define S5PV310_PA_HSMMC(x)		(0x12510000 + ((x) * 0x10000))
 
diff --git a/arch/arm/mach-s5pv310/include/mach/smp.h b/arch/arm/mach-s5pv310/include/mach/smp.h
index 990f3ba..b7ec252 100644
--- a/arch/arm/mach-s5pv310/include/mach/smp.h
+++ b/arch/arm/mach-s5pv310/include/mach/smp.h
@@ -7,17 +7,10 @@
 #define ASM_ARCH_SMP_H __FILE__
 
 #include <asm/hardware/gic.h>
+#include <asm/smp_mpidr.h>
 
 extern void __iomem *gic_cpu_base_addr;
 
-#define hard_smp_processor_id()			\
-	({						\
-		unsigned int cpunum;			\
-		__asm__("mrc p15, 0, %0, c0, c0, 5"	\
-			: "=r" (cpunum));		\
-		cpunum &= 0x03;				\
-	})
-
 /*
  * We use IRQ1 as the IPI
  */
diff --git a/arch/arm/mach-s5pv310/mach-smdkv310.c b/arch/arm/mach-s5pv310/mach-smdkv310.c
index 0d6ab77..46215a1 100644
--- a/arch/arm/mach-s5pv310/mach-smdkv310.c
+++ b/arch/arm/mach-s5pv310/mach-smdkv310.c
@@ -82,8 +82,6 @@
 MACHINE_START(SMDKV310, "SMDKV310")
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
 	/* Maintainer: Changhwan Youn <chaos.youn@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S5P_PA_SDRAM + 0x100,
 	.init_irq	= s5pv310_init_irq,
 	.map_io		= smdkv310_map_io,
diff --git a/arch/arm/mach-s5pv310/mach-universal_c210.c b/arch/arm/mach-s5pv310/mach-universal_c210.c
index 2388cb9..d7c2ec7 100644
--- a/arch/arm/mach-s5pv310/mach-universal_c210.c
+++ b/arch/arm/mach-s5pv310/mach-universal_c210.c
@@ -76,8 +76,6 @@
 
 MACHINE_START(UNIVERSAL_C210, "UNIVERSAL_C210")
 	/* Maintainer: Kyungmin Park <kyungmin.park@samsung.com> */
-	.phys_io	= S3C_PA_UART & 0xfff00000,
-	.io_pg_offst	= (((u32)S3C_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= S5P_PA_SDRAM + 0x100,
 	.init_irq	= s5pv310_init_irq,
 	.map_io		= universal_map_io,
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index 169e5b8..5778274 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -447,8 +447,6 @@
 
 
 MACHINE_START(ASSABET, "Intel-Assabet")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.fixup		= fixup_assabet,
 	.map_io		= assabet_map_io,
diff --git a/arch/arm/mach-sa1100/badge4.c b/arch/arm/mach-sa1100/badge4.c
index 259cb2c..4f19ff8 100644
--- a/arch/arm/mach-sa1100/badge4.c
+++ b/arch/arm/mach-sa1100/badge4.c
@@ -302,8 +302,6 @@
 }
 
 MACHINE_START(BADGE4, "Hewlett-Packard Laboratories BadgePAD 4")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= badge4_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-sa1100/cerf.c b/arch/arm/mach-sa1100/cerf.c
index bc950ef..98d7806 100644
--- a/arch/arm/mach-sa1100/cerf.c
+++ b/arch/arm/mach-sa1100/cerf.c
@@ -135,8 +135,6 @@
 
 MACHINE_START(CERF, "Intrinsyc CerfBoard/CerfCube")
 	/* Maintainer: support@intrinsyc.com */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.map_io		= cerf_map_io,
 	.init_irq	= cerf_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index 16e682d..d43c5ef 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -379,8 +379,6 @@
 }
 
 MACHINE_START(COLLIE, "Sharp-Collie")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.map_io		= collie_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/h3100.c b/arch/arm/mach-sa1100/h3100.c
index 0c7cea0..03d7376 100644
--- a/arch/arm/mach-sa1100/h3100.c
+++ b/arch/arm/mach-sa1100/h3100.c
@@ -84,8 +84,6 @@
 }
 
 MACHINE_START(H3100, "Compaq iPAQ H3100")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= h3100_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-sa1100/h3600.c b/arch/arm/mach-sa1100/h3600.c
index af3b714..965f64a 100644
--- a/arch/arm/mach-sa1100/h3600.c
+++ b/arch/arm/mach-sa1100/h3600.c
@@ -125,8 +125,6 @@
 }
 
 MACHINE_START(H3600, "Compaq iPAQ H3600")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= h3600_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-sa1100/hackkit.c b/arch/arm/mach-sa1100/hackkit.c
index 51568df..db5e434 100644
--- a/arch/arm/mach-sa1100/hackkit.c
+++ b/arch/arm/mach-sa1100/hackkit.c
@@ -195,8 +195,6 @@
  */
 
 MACHINE_START(HACKKIT, "HackKit Cpu Board")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= hackkit_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-sa1100/include/mach/debug-macro.S b/arch/arm/mach-sa1100/include/mach/debug-macro.S
index 336adcc..0cd0fc9 100644
--- a/arch/arm/mach-sa1100/include/mach/debug-macro.S
+++ b/arch/arm/mach-sa1100/include/mach/debug-macro.S
@@ -12,33 +12,37 @@
 */
 #include <mach/hardware.h>
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x80000000	@ physical base address
-		movne	\rx, #0xf8000000	@ virtual address
+		.macro	addruart, rp, rv
+		mrc	p15, 0, \rp, c1, c0
+		tst	\rp, #1			@ MMU enabled?
+		moveq	\rp, #0x80000000	@ physical base address
+		movne	\rp, #0xf8000000	@ virtual address
 
 		@ We probe for the active serial port here, coherently with
 		@ the comment in arch/arm/mach-sa1100/include/mach/uncompress.h.
 		@ We assume r1 can be clobbered.
 
 		@ see if Ser3 is active
-		add	\rx, \rx, #0x00050000
-		ldr	r1, [\rx, #UTCR3]
-		tst	r1, #UTCR3_TXE
+		add	\rp, \rp, #0x00050000
+		ldr	\rv, [\rp, #UTCR3]
+		tst	\rv, #UTCR3_TXE
 
 		@ if Ser3 is inactive, then try Ser1
-		addeq	\rx, \rx, #(0x00010000 - 0x00050000)
-		ldreq	r1, [\rx, #UTCR3]
-		tsteq	r1, #UTCR3_TXE
+		addeq	\rp, \rp, #(0x00010000 - 0x00050000)
+		ldreq	\rv, [\rp, #UTCR3]
+		tsteq	\rv, #UTCR3_TXE
 
 		@ if Ser1 is inactive, then try Ser2
-		addeq	\rx, \rx, #(0x00030000 - 0x00010000)
-		ldreq	r1, [\rx, #UTCR3]
-		tsteq	r1, #UTCR3_TXE
+		addeq	\rp, \rp, #(0x00030000 - 0x00010000)
+		ldreq	\rv, [\rp, #UTCR3]
+		tsteq	\rv, #UTCR3_TXE
 
-		@ if all ports are inactive, then there is nothing we can do
-		moveq	pc, lr
+		@ clear top bits, and generate both phys and virt addresses
+		lsl	\rp, \rp, #8
+		lsr	\rp, \rp, #8
+		orr	\rv, \rp, #0xf8000000	@ virtual
+		orr	\rp, \rp, #0x80000000	@ physical
+
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/mach-sa1100/jornada720.c b/arch/arm/mach-sa1100/jornada720.c
index d3ec620..491ac9f 100644
--- a/arch/arm/mach-sa1100/jornada720.c
+++ b/arch/arm/mach-sa1100/jornada720.c
@@ -364,8 +364,6 @@
 
 MACHINE_START(JORNADA720, "HP Jornada 720")
 	/* Maintainer: Kristoffer Ericson <Kristoffer.Ericson@gmail.com> */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= jornada720_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-sa1100/lart.c b/arch/arm/mach-sa1100/lart.c
index 68069d6..7b9556b 100644
--- a/arch/arm/mach-sa1100/lart.c
+++ b/arch/arm/mach-sa1100/lart.c
@@ -61,8 +61,6 @@
 }
 
 MACHINE_START(LART, "LART")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= lart_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index 1ccd601..42b8040 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -146,8 +146,6 @@
 }
 
 MACHINE_START(PLEB, "PLEB")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.map_io		= pleb_map_io,
 	.init_irq	= sa1100_init_irq,
 	.timer		= &sa1100_timer,
diff --git a/arch/arm/mach-sa1100/shannon.c b/arch/arm/mach-sa1100/shannon.c
index 85e82bb..7917b24 100644
--- a/arch/arm/mach-sa1100/shannon.c
+++ b/arch/arm/mach-sa1100/shannon.c
@@ -82,8 +82,6 @@
 }
 
 MACHINE_START(SHANNON, "Shannon (AKA: Tuxscreen)")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= shannon_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c
index 49cfd64..27692d0 100644
--- a/arch/arm/mach-sa1100/simpad.c
+++ b/arch/arm/mach-sa1100/simpad.c
@@ -228,8 +228,6 @@
 
 MACHINE_START(SIMPAD, "Simpad")
 	/* Maintainer: Holger Freyther */
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf8000000) >> 18) & 0xfffc,
 	.boot_params	= 0xc0000100,
 	.map_io		= simpad_map_io,
 	.init_irq	= sa1100_init_irq,
diff --git a/arch/arm/mach-shark/core.c b/arch/arm/mach-shark/core.c
index 358d875..5cf7f94 100644
--- a/arch/arm/mach-shark/core.c
+++ b/arch/arm/mach-shark/core.c
@@ -152,8 +152,6 @@
 
 MACHINE_START(SHARK, "Shark")
 	/* Maintainer: Alexander Schulz */
-	.phys_io	= 0x40000000,
-	.io_pg_offst	= ((0xe0000000) >> 18) & 0xfffc,
 	.boot_params	= 0x08003000,
 	.map_io		= shark_map_io,
 	.init_irq	= shark_init_irq,
diff --git a/arch/arm/mach-shark/include/mach/debug-macro.S b/arch/arm/mach-shark/include/mach/debug-macro.S
index 5ea24d4..a473f55 100644
--- a/arch/arm/mach-shark/include/mach/debug-macro.S
+++ b/arch/arm/mach-shark/include/mach/debug-macro.S
@@ -11,9 +11,10 @@
  *
 */
 
-		.macro	addruart, rx, tmp
-		mov	\rx, #0xe0000000
-		orr	\rx, \rx, #0x000003f8
+		.macro	addruart, rp, rv
+		mov	\rp, #0xe0000000
+		orr	\rp, \rp, #0x000003f8
+		mov	\rv, \rp
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/mach-shark/include/mach/vmalloc.h b/arch/arm/mach-shark/include/mach/vmalloc.h
index f6c6837..8e845b6 100644
--- a/arch/arm/mach-shark/include/mach/vmalloc.h
+++ b/arch/arm/mach-shark/include/mach/vmalloc.h
@@ -1,4 +1,4 @@
 /*
  * arch/arm/mach-shark/include/mach/vmalloc.h
  */
-#define VMALLOC_END       (PAGE_OFFSET + 0x10000000)
+#define VMALLOC_END       0xd0000000
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 95935c8..1492398 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -1105,8 +1105,6 @@
 };
 
 MACHINE_START(AP4EVB, "ap4evb")
-	.phys_io	= 0xe6000000,
-	.io_pg_offst	= ((0xe6000000) >> 18) & 0xfffc,
 	.map_io		= ap4evb_map_io,
 	.init_irq	= sh7372_init_irq,
 	.init_machine	= ap4evb_init,
diff --git a/arch/arm/mach-shmobile/board-g3evm.c b/arch/arm/mach-shmobile/board-g3evm.c
index a552590..3b83d63 100644
--- a/arch/arm/mach-shmobile/board-g3evm.c
+++ b/arch/arm/mach-shmobile/board-g3evm.c
@@ -365,8 +365,6 @@
 };
 
 MACHINE_START(G3EVM, "g3evm")
-	.phys_io	= 0xe6000000,
-	.io_pg_offst	= ((0xe6000000) >> 18) & 0xfffc,
 	.map_io		= g3evm_map_io,
 	.init_irq	= sh7367_init_irq,
 	.init_machine	= g3evm_init,
diff --git a/arch/arm/mach-shmobile/board-g4evm.c b/arch/arm/mach-shmobile/board-g4evm.c
index 2c3ff6f..5b3b582 100644
--- a/arch/arm/mach-shmobile/board-g4evm.c
+++ b/arch/arm/mach-shmobile/board-g4evm.c
@@ -392,8 +392,6 @@
 };
 
 MACHINE_START(G4EVM, "g4evm")
-	.phys_io	= 0xe6000000,
-	.io_pg_offst	= ((0xe6000000) >> 18) & 0xfffc,
 	.map_io		= g4evm_map_io,
 	.init_irq	= sh7377_init_irq,
 	.init_machine	= g4evm_init,
diff --git a/arch/arm/mach-stmp378x/stmp378x_devb.c b/arch/arm/mach-stmp378x/stmp378x_devb.c
index 90d8fe6..0615884 100644
--- a/arch/arm/mach-stmp378x/stmp378x_devb.c
+++ b/arch/arm/mach-stmp378x/stmp378x_devb.c
@@ -324,8 +324,6 @@
 }
 
 MACHINE_START(STMP378X, "STMP378X")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf0000000) >> 18) & 0xfffc,
 	.boot_params	= 0x40000100,
 	.map_io		= stmp378x_map_io,
 	.init_irq	= stmp378x_init_irq,
diff --git a/arch/arm/mach-stmp37xx/stmp37xx_devb.c b/arch/arm/mach-stmp37xx/stmp37xx_devb.c
index 394f21a..311d855 100644
--- a/arch/arm/mach-stmp37xx/stmp37xx_devb.c
+++ b/arch/arm/mach-stmp37xx/stmp37xx_devb.c
@@ -91,8 +91,6 @@
 }
 
 MACHINE_START(STMP37XX, "STMP37XX")
-	.phys_io	= 0x80000000,
-	.io_pg_offst	= ((0xf0000000) >> 18) & 0xfffc,
 	.boot_params	= 0x40000100,
 	.map_io		= stmp37xx_map_io,
 	.init_irq	= stmp37xx_init_irq,
diff --git a/arch/arm/mach-tcc8k/Kconfig b/arch/arm/mach-tcc8k/Kconfig
new file mode 100644
index 0000000..ad86415
--- /dev/null
+++ b/arch/arm/mach-tcc8k/Kconfig
@@ -0,0 +1,11 @@
+if ARCH_TCC8K
+
+comment "TCC8000 systems:"
+
+config MACH_TCC8000_SDK
+	bool "Telechips TCC8000-SDK development kit"
+	default y
+	help
+	  Support for the Telechips TCC8000-SDK board.
+
+endif
diff --git a/arch/arm/mach-tcc8k/Makefile b/arch/arm/mach-tcc8k/Makefile
new file mode 100644
index 0000000..9bacf31
--- /dev/null
+++ b/arch/arm/mach-tcc8k/Makefile
@@ -0,0 +1,9 @@
+#
+# Makefile for TCC8K boards and common files.
+#
+
+# Common support
+obj-y += clock.o irq.o time.o io.o devices.o
+
+# Board specific support
+obj-$(CONFIG_MACH_TCC8000_SDK) += board-tcc8000-sdk.o
diff --git a/arch/arm/mach-tcc8k/Makefile.boot b/arch/arm/mach-tcc8k/Makefile.boot
new file mode 100644
index 0000000..f135c9d
--- /dev/null
+++ b/arch/arm/mach-tcc8k/Makefile.boot
@@ -0,0 +1,3 @@
+   zreladdr-y		:= 0x20008000
+params_phys-y		:= 0x20000100
+initrd_phys-y		:= 0x20800000
diff --git a/arch/arm/mach-tcc8k/board-tcc8000-sdk.c b/arch/arm/mach-tcc8k/board-tcc8000-sdk.c
new file mode 100644
index 0000000..7991415
--- /dev/null
+++ b/arch/arm/mach-tcc8k/board-tcc8000-sdk.c
@@ -0,0 +1,62 @@
+/*
+ * Copyright (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach-types.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/mach/time.h>
+
+#include <mach/clock.h>
+
+#include "common.h"
+
+#define XI_FREQUENCY	12000000
+#define XTI_FREQUENCY	32768
+
+#ifdef CONFIG_MTD_NAND_TCC
+/* NAND */
+static struct tcc_nand_platform_data tcc8k_sdk_nand_data = {
+	.width = 1,
+	.hw_ecc = 0,
+};
+#endif
+
+static void __init tcc8k_init(void)
+{
+#ifdef CONFIG_MTD_NAND_TCC
+	tcc_nand_device.dev.platform_data = &tcc8k_sdk_nand_data;
+	platform_device_register(&tcc_nand_device);
+#endif
+}
+
+static void __init tcc8k_init_timer(void)
+{
+	tcc_clocks_init(XI_FREQUENCY, XTI_FREQUENCY);
+}
+
+static struct sys_timer tcc8k_timer = {
+	.init	= tcc8k_init_timer,
+};
+
+static void __init tcc8k_map_io(void)
+{
+	tcc8k_map_common_io();
+}
+
+MACHINE_START(TCC8000_SDK, "Telechips TCC8000-SDK Demo Board")
+	.boot_params	= PHYS_OFFSET + 0x00000100,
+	.map_io		= tcc8k_map_io,
+	.init_irq	= tcc8k_init_irq,
+	.init_machine	= tcc8k_init,
+	.timer		= &tcc8k_timer,
+MACHINE_END
diff --git a/arch/arm/mach-tcc8k/clock.c b/arch/arm/mach-tcc8k/clock.c
new file mode 100644
index 0000000..ba32a15
--- /dev/null
+++ b/arch/arm/mach-tcc8k/clock.c
@@ -0,0 +1,567 @@
+/*
+ * Lowlevel clock handling for Telechips TCC8xxx SoCs
+ *
+ * Copyright (C) 2010 by Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GPL v2
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+
+#include <asm/clkdev.h>
+
+#include <mach/clock.h>
+#include <mach/irqs.h>
+#include <mach/tcc8k-regs.h>
+
+#include "common.h"
+
+#define BCLKCTR0	(CKC_BASE + BCLKCTR0_OFFS)
+#define BCLKCTR1	(CKC_BASE + BCLKCTR1_OFFS)
+
+#define ACLKREF		(CKC_BASE + ACLKREF_OFFS)
+#define ACLKUART0	(CKC_BASE + ACLKUART0_OFFS)
+#define ACLKUART1	(CKC_BASE + ACLKUART1_OFFS)
+#define ACLKUART2	(CKC_BASE + ACLKUART2_OFFS)
+#define ACLKUART3	(CKC_BASE + ACLKUART3_OFFS)
+#define ACLKUART4	(CKC_BASE + ACLKUART4_OFFS)
+#define ACLKI2C		(CKC_BASE + ACLKI2C_OFFS)
+#define ACLKADC		(CKC_BASE + ACLKADC_OFFS)
+#define ACLKUSBH	(CKC_BASE + ACLKUSBH_OFFS)
+#define ACLKLCD		(CKC_BASE + ACLKLCD_OFFS)
+#define ACLKSDH0	(CKC_BASE + ACLKSDH0_OFFS)
+#define ACLKSDH1	(CKC_BASE + ACLKSDH1_OFFS)
+#define ACLKSPI0	(CKC_BASE + ACLKSPI0_OFFS)
+#define ACLKSPI1	(CKC_BASE + ACLKSPI1_OFFS)
+#define ACLKSPDIF	(CKC_BASE + ACLKSPDIF_OFFS)
+#define ACLKC3DEC	(CKC_BASE + ACLKC3DEC_OFFS)
+#define ACLKCAN0	(CKC_BASE + ACLKCAN0_OFFS)
+#define ACLKCAN1	(CKC_BASE + ACLKCAN1_OFFS)
+#define ACLKGSB0	(CKC_BASE + ACLKGSB0_OFFS)
+#define ACLKGSB1	(CKC_BASE + ACLKGSB1_OFFS)
+#define ACLKGSB2	(CKC_BASE + ACLKGSB2_OFFS)
+#define ACLKGSB3	(CKC_BASE + ACLKGSB3_OFFS)
+#define ACLKUSBH	(CKC_BASE + ACLKUSBH_OFFS)
+#define ACLKTCT		(CKC_BASE + ACLKTCT_OFFS)
+#define ACLKTCX		(CKC_BASE + ACLKTCX_OFFS)
+#define ACLKTCZ		(CKC_BASE + ACLKTCZ_OFFS)
+
+/* Crystal frequencies */
+static unsigned long xi_rate, xti_rate;
+
+static void __iomem *pll_cfg_addr(int pll)
+{
+	switch (pll) {
+	case 0: return (CKC_BASE + PLL0CFG_OFFS);
+	case 1: return (CKC_BASE + PLL1CFG_OFFS);
+	case 2: return (CKC_BASE + PLL2CFG_OFFS);
+	default:
+		BUG();
+	}
+}
+
+static int pll_enable(int pll, int enable)
+{
+	u32 reg;
+	void __iomem *addr = pll_cfg_addr(pll);
+
+	reg = __raw_readl(addr);
+	if (enable)
+		reg &= ~PLLxCFG_PD;
+	else
+		reg |= PLLxCFG_PD;
+
+	__raw_writel(reg, addr);
+	return 0;
+}
+
+static int xi_enable(int enable)
+{
+	u32 reg;
+
+	reg = __raw_readl(CKC_BASE + CLKCTRL_OFFS);
+	if (enable)
+		reg |= CLKCTRL_XE;
+	else
+		reg &= ~CLKCTRL_XE;
+
+	__raw_writel(reg, CKC_BASE + CLKCTRL_OFFS);
+	return 0;
+}
+
+static int root_clk_enable(enum root_clks src)
+{
+	switch (src) {
+	case CLK_SRC_PLL0: return pll_enable(0, 1);
+	case CLK_SRC_PLL1: return pll_enable(1, 1);
+	case CLK_SRC_PLL2: return pll_enable(2, 1);
+	case CLK_SRC_XI: return xi_enable(1);
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+static int root_clk_disable(enum root_clks root_src)
+{
+	switch (root_src) {
+	case CLK_SRC_PLL0: return pll_enable(0, 0);
+	case CLK_SRC_PLL1: return pll_enable(1, 0);
+	case CLK_SRC_PLL2: return pll_enable(2, 0);
+	case CLK_SRC_XI: return xi_enable(0);
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+static int enable_clk(struct clk *clk)
+{
+	u32 reg;
+
+	if (clk->root_id != CLK_SRC_NOROOT)
+		return root_clk_enable(clk->root_id);
+
+	if (clk->aclkreg) {
+		reg = __raw_readl(clk->aclkreg);
+		reg |= ACLK_EN;
+		__raw_writel(reg, clk->aclkreg);
+	}
+	if (clk->bclkctr) {
+		reg = __raw_readl(clk->bclkctr);
+		reg |= 1 << clk->bclk_shift;
+		__raw_writel(reg, clk->bclkctr);
+	}
+	return 0;
+}
+
+static void disable_clk(struct clk *clk)
+{
+	u32 reg;
+
+	if (clk->root_id != CLK_SRC_NOROOT) {
+		root_clk_disable(clk->root_id);
+		return;
+	}
+
+	if (clk->bclkctr) {
+		reg = __raw_readl(clk->bclkctr);
+		reg &= ~(1 << clk->bclk_shift);
+		__raw_writel(reg, clk->bclkctr);
+	}
+	if (clk->aclkreg) {
+		reg = __raw_readl(clk->aclkreg);
+		reg &= ~ACLK_EN;
+		__raw_writel(reg, clk->aclkreg);
+	}
+}
+
+static unsigned long get_rate_pll(int pll)
+{
+	u32 reg;
+	unsigned long s, m, p;
+	void __iomem *addr = pll_cfg_addr(pll);
+
+	reg = __raw_readl(addr);
+	s = (reg >> 16) & 0x07;
+	m = (reg >> 8) & 0xff;
+	p = reg & 0x3f;
+
+	return (m * xi_rate) / (p * (1 << s));
+}
+
+static unsigned long get_rate_pll_div(int pll)
+{
+	u32 reg;
+	unsigned long div = 0;
+	void __iomem *addr;
+
+	switch (pll) {
+	case 0:
+		addr = CKC_BASE + CLKDIVC0_OFFS;
+		reg = __raw_readl(addr);
+		if (reg & CLKDIVC0_P0E)
+			div = (reg >> 24) & 0x3f;
+		break;
+	case 1:
+		addr = CKC_BASE + CLKDIVC0_OFFS;
+		reg = __raw_readl(addr);
+		if (reg & CLKDIVC0_P1E)
+			div = (reg >> 16) & 0x3f;
+		break;
+	case 2:
+		addr = CKC_BASE + CLKDIVC1_OFFS;
+		reg = __raw_readl(addr);
+		if (reg & CLKDIVC1_P2E)
+			div = __raw_readl(addr) & 0x3f;
+		break;
+	}
+	return get_rate_pll(pll) / (div + 1);
+}
+
+static unsigned long get_rate_xi_div(void)
+{
+	unsigned long div = 0;
+	u32 reg = __raw_readl(CKC_BASE + CLKDIVC0_OFFS);
+
+	if (reg & CLKDIVC0_XE)
+		div = (reg >> 8) & 0x3f;
+
+	return xi_rate / (div + 1);
+}
+
+static unsigned long get_rate_xti_div(void)
+{
+	unsigned long div = 0;
+	u32 reg = __raw_readl(CKC_BASE + CLKDIVC0_OFFS);
+
+	if (reg & CLKDIVC0_XTE)
+		div = reg & 0x3f;
+
+	return xti_rate / (div + 1);
+}
+
+static unsigned long root_clk_get_rate(enum root_clks src)
+{
+	switch (src) {
+	case CLK_SRC_PLL0: return get_rate_pll(0);
+	case CLK_SRC_PLL1: return get_rate_pll(1);
+	case CLK_SRC_PLL2: return get_rate_pll(2);
+	case CLK_SRC_PLL0DIV: return get_rate_pll_div(0);
+	case CLK_SRC_PLL1DIV: return get_rate_pll_div(1);
+	case CLK_SRC_PLL2DIV: return get_rate_pll_div(2);
+	case CLK_SRC_XI: return xi_rate;
+	case CLK_SRC_XTI: return xti_rate;
+	case CLK_SRC_XIDIV: return get_rate_xi_div();
+	case CLK_SRC_XTIDIV: return get_rate_xti_div();
+	default: return 0;
+	}
+}
+
+static unsigned long aclk_get_rate(struct clk *clk)
+{
+	u32 reg;
+	unsigned long div;
+	unsigned int src;
+
+	reg = __raw_readl(clk->aclkreg);
+	div = reg & 0x0fff;
+	src = (reg >> ACLK_SEL_SHIFT) & CLK_SRC_MASK;
+	return root_clk_get_rate(src) / (div + 1);
+}
+
+static unsigned long aclk_best_div(struct clk *clk, unsigned long rate)
+{
+	unsigned long div, src, freq, r1, r2;
+
+	src = __raw_readl(clk->aclkreg) >> ACLK_SEL_SHIFT;
+	src &= CLK_SRC_MASK;
+	freq = root_clk_get_rate(src);
+	div = freq / rate + 1;
+	r1 = freq / div;
+	r2 = freq / (div + 1);
+	if (r2 >= rate)
+		return div + 1;
+	if ((rate - r2) < (r1 - rate))
+		return div + 1;
+
+	return div;
+}
+
+static unsigned long aclk_round_rate(struct clk *clk, unsigned long rate)
+{
+	unsigned int src;
+
+	src = __raw_readl(clk->aclkreg) >> ACLK_SEL_SHIFT;
+	src &= CLK_SRC_MASK;
+
+	return root_clk_get_rate(src) / aclk_best_div(clk, rate);
+}
+
+static int aclk_set_rate(struct clk *clk, unsigned long rate)
+{
+	u32 reg;
+
+	reg = __raw_readl(clk->aclkreg) & ~ACLK_DIV_MASK;
+	reg |= aclk_best_div(clk, rate);
+	return 0;
+}
+
+static unsigned long get_rate_sys(struct clk *clk)
+{
+	unsigned int src;
+
+	src = __raw_readl(CKC_BASE + CLKCTRL_OFFS) & CLK_SRC_MASK;
+		return root_clk_get_rate(src);
+}
+
+static unsigned long get_rate_bus(struct clk *clk)
+{
+	unsigned int div;
+
+	div = (__raw_readl(CKC_BASE + CLKCTRL_OFFS) >> 4) & 0xff;
+	return get_rate_sys(clk) / (div + 1);
+}
+
+static unsigned long get_rate_cpu(struct clk *clk)
+{
+	unsigned int reg, div, fsys, fbus;
+
+	fbus = get_rate_bus(clk);
+	reg = __raw_readl(CKC_BASE + CLKCTRL_OFFS);
+	if (reg & (1 << 29))
+		return fbus;
+	fsys = get_rate_sys(clk);
+	div = (reg >> 16) & 0x0f;
+	return fbus + ((fsys - fbus) * (div + 1)) / 16;
+}
+
+static unsigned long get_rate_root(struct clk *clk)
+{
+	return root_clk_get_rate(clk->root_id);
+}
+
+static int aclk_set_parent(struct clk *clock, struct clk *parent)
+{
+	u32 reg;
+
+	if (clock->parent == parent)
+		return 0;
+
+	clock->parent = parent;
+
+	if (!parent)
+		return 0;
+
+	if (parent->root_id == CLK_SRC_NOROOT)
+		return 0;
+	reg = __raw_readl(clock->aclkreg);
+	reg &= ~ACLK_SEL_MASK;
+	reg |= (parent->root_id << ACLK_SEL_SHIFT) & ACLK_SEL_MASK;
+	__raw_writel(reg, clock->aclkreg);
+
+	return 0;
+}
+
+#define DEFINE_ROOT_CLOCK(name, ri, p)	\
+	static struct clk name = {		\
+		.root_id = ri,			\
+		.get_rate = get_rate_root,			\
+		.enable = enable_clk,		\
+		.disable = disable_clk,		\
+		.parent = p,			\
+	};
+
+#define DEFINE_SPECIAL_CLOCK(name, gr, p)	\
+	static struct clk name = {		\
+		.root_id = CLK_SRC_NOROOT,	\
+		.get_rate = gr,			\
+		.parent = p,			\
+	};
+
+#define DEFINE_ACLOCK(name, bc, bs, ar)		\
+	static struct clk name = {		\
+		.root_id = CLK_SRC_NOROOT,	\
+		.bclkctr = bc,			\
+		.bclk_shift = bs,		\
+		.aclkreg = ar,			\
+		.get_rate = aclk_get_rate,	\
+		.set_rate = aclk_set_rate,	\
+		.round_rate = aclk_round_rate,	\
+		.enable = enable_clk,		\
+		.disable = disable_clk,		\
+		.set_parent = aclk_set_parent,	\
+	};
+
+#define DEFINE_BCLOCK(name, bc, bs, gr, p)	\
+	static struct clk name = {		\
+		.root_id = CLK_SRC_NOROOT,	\
+		.bclkctr = bc,			\
+		.bclk_shift = bs,		\
+		.get_rate = gr,			\
+		.enable = enable_clk,		\
+		.disable = disable_clk,		\
+		.parent = p,			\
+	};
+
+DEFINE_ROOT_CLOCK(xi, CLK_SRC_XI, NULL)
+DEFINE_ROOT_CLOCK(xti, CLK_SRC_XTI, NULL)
+DEFINE_ROOT_CLOCK(xidiv, CLK_SRC_XIDIV, &xi)
+DEFINE_ROOT_CLOCK(xtidiv, CLK_SRC_XTIDIV, &xti)
+DEFINE_ROOT_CLOCK(pll0, CLK_SRC_PLL0, &xi)
+DEFINE_ROOT_CLOCK(pll1, CLK_SRC_PLL1, &xi)
+DEFINE_ROOT_CLOCK(pll2, CLK_SRC_PLL2, &xi)
+DEFINE_ROOT_CLOCK(pll0div, CLK_SRC_PLL0DIV, &pll0)
+DEFINE_ROOT_CLOCK(pll1div, CLK_SRC_PLL1DIV, &pll1)
+DEFINE_ROOT_CLOCK(pll2div, CLK_SRC_PLL2DIV, &pll2)
+
+/* The following 3 clocks are special and are initialized explicitly later */
+DEFINE_SPECIAL_CLOCK(sys, get_rate_sys, NULL)
+DEFINE_SPECIAL_CLOCK(bus, get_rate_bus, &sys)
+DEFINE_SPECIAL_CLOCK(cpu, get_rate_cpu, &sys)
+
+DEFINE_ACLOCK(tct, NULL, 0, ACLKTCT)
+DEFINE_ACLOCK(tcx, NULL, 0, ACLKTCX)
+DEFINE_ACLOCK(tcz, NULL, 0, ACLKTCZ)
+DEFINE_ACLOCK(ref, NULL, 0, ACLKREF)
+DEFINE_ACLOCK(uart0, BCLKCTR0, 5, ACLKUART0)
+DEFINE_ACLOCK(uart1, BCLKCTR0, 23, ACLKUART1)
+DEFINE_ACLOCK(uart2, BCLKCTR0, 6, ACLKUART2)
+DEFINE_ACLOCK(uart3, BCLKCTR0, 8, ACLKUART3)
+DEFINE_ACLOCK(uart4, BCLKCTR1, 6, ACLKUART4)
+DEFINE_ACLOCK(i2c, BCLKCTR0, 7, ACLKI2C)
+DEFINE_ACLOCK(adc, BCLKCTR0, 10, ACLKADC)
+DEFINE_ACLOCK(usbh0, BCLKCTR0, 11, ACLKUSBH)
+DEFINE_ACLOCK(lcd, BCLKCTR0, 13, ACLKLCD)
+DEFINE_ACLOCK(sd0, BCLKCTR0, 17, ACLKSDH0)
+DEFINE_ACLOCK(sd1, BCLKCTR1, 5, ACLKSDH1)
+DEFINE_ACLOCK(spi0, BCLKCTR0, 24, ACLKSPI0)
+DEFINE_ACLOCK(spi1, BCLKCTR0, 30, ACLKSPI1)
+DEFINE_ACLOCK(spdif, BCLKCTR1, 2, ACLKSPDIF)
+DEFINE_ACLOCK(c3dec, BCLKCTR1, 9, ACLKC3DEC)
+DEFINE_ACLOCK(can0, BCLKCTR1, 10, ACLKCAN0)
+DEFINE_ACLOCK(can1, BCLKCTR1, 11, ACLKCAN1)
+DEFINE_ACLOCK(gsb0, BCLKCTR1, 13, ACLKGSB0)
+DEFINE_ACLOCK(gsb1, BCLKCTR1, 14, ACLKGSB1)
+DEFINE_ACLOCK(gsb2, BCLKCTR1, 15, ACLKGSB2)
+DEFINE_ACLOCK(gsb3, BCLKCTR1, 16, ACLKGSB3)
+DEFINE_ACLOCK(usbh1, BCLKCTR1, 20, ACLKUSBH)
+
+DEFINE_BCLOCK(dai0, BCLKCTR0, 0, NULL, NULL)
+DEFINE_BCLOCK(pic, BCLKCTR0, 1, NULL, NULL)
+DEFINE_BCLOCK(tc, BCLKCTR0, 2, NULL, NULL)
+DEFINE_BCLOCK(gpio, BCLKCTR0, 3, NULL, NULL)
+DEFINE_BCLOCK(usbd, BCLKCTR0, 4, NULL, NULL)
+DEFINE_BCLOCK(ecc, BCLKCTR0, 9, NULL, NULL)
+DEFINE_BCLOCK(gdma0, BCLKCTR0, 12, NULL, NULL)
+DEFINE_BCLOCK(rtc, BCLKCTR0, 15, NULL, NULL)
+DEFINE_BCLOCK(nfc, BCLKCTR0, 16, NULL, NULL)
+DEFINE_BCLOCK(g2d, BCLKCTR0, 18, NULL, NULL)
+DEFINE_BCLOCK(gdma1, BCLKCTR0, 22, NULL, NULL)
+DEFINE_BCLOCK(mscl, BCLKCTR0, 25, NULL, NULL)
+DEFINE_BCLOCK(bdma, BCLKCTR1, 0, NULL, NULL)
+DEFINE_BCLOCK(adma0, BCLKCTR1, 1, NULL, NULL)
+DEFINE_BCLOCK(scfg, BCLKCTR1, 3, NULL, NULL)
+DEFINE_BCLOCK(cid, BCLKCTR1, 4, NULL, NULL)
+DEFINE_BCLOCK(dai1, BCLKCTR1, 7, NULL, NULL)
+DEFINE_BCLOCK(adma1, BCLKCTR1, 8, NULL, NULL)
+DEFINE_BCLOCK(gps, BCLKCTR1, 12, NULL, NULL)
+DEFINE_BCLOCK(gdma2, BCLKCTR1, 17, NULL, NULL)
+DEFINE_BCLOCK(gdma3, BCLKCTR1, 18, NULL, NULL)
+DEFINE_BCLOCK(ddrc, BCLKCTR1, 19, NULL, NULL)
+
+#define _REGISTER_CLOCK(d, n, c) \
+	{ \
+		.dev_id = d, \
+		.con_id = n, \
+		.clk = &c, \
+	},
+
+static struct clk_lookup lookups[] = {
+	_REGISTER_CLOCK(NULL, "bus", bus)
+	_REGISTER_CLOCK(NULL, "cpu", cpu)
+	_REGISTER_CLOCK(NULL, "tct", tct)
+	_REGISTER_CLOCK(NULL, "tcx", tcx)
+	_REGISTER_CLOCK(NULL, "tcz", tcz)
+	_REGISTER_CLOCK(NULL, "ref", ref)
+	_REGISTER_CLOCK(NULL, "dai0", dai0)
+	_REGISTER_CLOCK(NULL, "pic", pic)
+	_REGISTER_CLOCK(NULL, "tc", tc)
+	_REGISTER_CLOCK(NULL, "gpio", gpio)
+	_REGISTER_CLOCK(NULL, "usbd", usbd)
+	_REGISTER_CLOCK("tcc-uart.0", NULL, uart0)
+	_REGISTER_CLOCK("tcc-uart.2", NULL, uart2)
+	_REGISTER_CLOCK("tcc-i2c", NULL, i2c)
+	_REGISTER_CLOCK("tcc-uart.3", NULL, uart3)
+	_REGISTER_CLOCK(NULL, "ecc", ecc)
+	_REGISTER_CLOCK(NULL, "adc", adc)
+	_REGISTER_CLOCK("tcc-usbh.0", "usb", usbh0)
+	_REGISTER_CLOCK(NULL, "gdma0", gdma0)
+	_REGISTER_CLOCK(NULL, "lcd", lcd)
+	_REGISTER_CLOCK(NULL, "rtc", rtc)
+	_REGISTER_CLOCK(NULL, "nfc", nfc)
+	_REGISTER_CLOCK("tcc-mmc.0", NULL, sd0)
+	_REGISTER_CLOCK(NULL, "g2d", g2d)
+	_REGISTER_CLOCK(NULL, "gdma1", gdma1)
+	_REGISTER_CLOCK("tcc-uart.1", NULL, uart1)
+	_REGISTER_CLOCK("tcc-spi.0", NULL, spi0)
+	_REGISTER_CLOCK(NULL, "mscl", mscl)
+	_REGISTER_CLOCK("tcc-spi.1", NULL, spi1)
+	_REGISTER_CLOCK(NULL, "bdma", bdma)
+	_REGISTER_CLOCK(NULL, "adma0", adma0)
+	_REGISTER_CLOCK(NULL, "spdif", spdif)
+	_REGISTER_CLOCK(NULL, "scfg", scfg)
+	_REGISTER_CLOCK(NULL, "cid", cid)
+	_REGISTER_CLOCK("tcc-mmc.1", NULL, sd1)
+	_REGISTER_CLOCK("tcc-uart.4", NULL, uart4)
+	_REGISTER_CLOCK(NULL, "dai1", dai1)
+	_REGISTER_CLOCK(NULL, "adma1", adma1)
+	_REGISTER_CLOCK(NULL, "c3dec", c3dec)
+	_REGISTER_CLOCK("tcc-can.0", NULL, can0)
+	_REGISTER_CLOCK("tcc-can.1", NULL, can1)
+	_REGISTER_CLOCK(NULL, "gps", gps)
+	_REGISTER_CLOCK("tcc-gsb.0", NULL, gsb0)
+	_REGISTER_CLOCK("tcc-gsb.1", NULL, gsb1)
+	_REGISTER_CLOCK("tcc-gsb.2", NULL, gsb2)
+	_REGISTER_CLOCK("tcc-gsb.3", NULL, gsb3)
+	_REGISTER_CLOCK(NULL, "gdma2", gdma2)
+	_REGISTER_CLOCK(NULL, "gdma3", gdma3)
+	_REGISTER_CLOCK(NULL, "ddrc", ddrc)
+	_REGISTER_CLOCK("tcc-usbh.1", "usb", usbh1)
+};
+
+static struct clk *root_clk_by_index(enum root_clks src)
+{
+	switch (src) {
+	case CLK_SRC_PLL0: return &pll0;
+	case CLK_SRC_PLL1: return &pll1;
+	case CLK_SRC_PLL2: return &pll2;
+	case CLK_SRC_PLL0DIV: return &pll0div;
+	case CLK_SRC_PLL1DIV: return &pll1div;
+	case CLK_SRC_PLL2DIV: return &pll2div;
+	case CLK_SRC_XI: return &xi;
+	case CLK_SRC_XTI: return &xti;
+	case CLK_SRC_XIDIV: return &xidiv;
+	case CLK_SRC_XTIDIV: return &xtidiv;
+	default: return NULL;
+	}
+}
+
+static void find_aclk_parent(struct clk *clk)
+{
+	unsigned int src;
+	struct clk *clock;
+
+	if (!clk->aclkreg)
+		return;
+
+	src = __raw_readl(clk->aclkreg) >> ACLK_SEL_SHIFT;
+	src &= CLK_SRC_MASK;
+
+	clock = root_clk_by_index(src);
+	if (!clock)
+		return;
+
+	clk->parent = clock;
+	clk->set_parent = aclk_set_parent;
+}
+
+void __init tcc_clocks_init(unsigned long xi_freq, unsigned long xti_freq)
+{
+	int i;
+
+	xi_rate = xi_freq;
+	xti_rate = xti_freq;
+
+	/* fixup parents and add the clock */
+	for (i = 0; i < ARRAY_SIZE(lookups); i++) {
+		find_aclk_parent(lookups[i].clk);
+		clkdev_add(&lookups[i]);
+	}
+	tcc8k_timer_init(&tcz, (void __iomem *)TIMER_BASE, INT_TC32);
+}
diff --git a/arch/arm/mach-tcc8k/common.h b/arch/arm/mach-tcc8k/common.h
new file mode 100644
index 0000000..705690a
--- /dev/null
+++ b/arch/arm/mach-tcc8k/common.h
@@ -0,0 +1,15 @@
+#ifndef MACH_TCC8K_COMMON_H
+#define MACH_TCC8K_COMMON_H
+
+#include <linux/platform_device.h>
+
+extern struct platform_device tcc_nand_device;
+
+struct clk;
+
+extern void tcc_clocks_init(unsigned long xi_freq, unsigned long xti_freq);
+extern void tcc8k_timer_init(struct clk *clock, void __iomem *base, int irq);
+extern void tcc8k_init_irq(void);
+extern void tcc8k_map_common_io(void);
+
+#endif
diff --git a/arch/arm/mach-tcc8k/devices.c b/arch/arm/mach-tcc8k/devices.c
new file mode 100644
index 0000000..6722ad7
--- /dev/null
+++ b/arch/arm/mach-tcc8k/devices.c
@@ -0,0 +1,239 @@
+/*
+ * linux/arch/arm/mach-tcc8k/devices.c
+ *
+ * Copyright (C) Telechips, Inc.
+ * Copyright (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of GPL v2.
+ *
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/mach/map.h>
+
+#include <mach/tcc8k-regs.h>
+#include <mach/irqs.h>
+
+#include "common.h"
+
+static u64 tcc8k_dmamask = DMA_BIT_MASK(32);
+
+#ifdef CONFIG_MTD_NAND_TCC
+/* NAND controller */
+static struct resource tcc_nand_resources[] = {
+	{
+		.start	= (resource_size_t)NFC_BASE,
+		.end	= (resource_size_t)NFC_BASE + 0x7f,
+		.flags	= IORESOURCE_MEM,
+	}, {
+		.start	= INT_NFC,
+		.end	= INT_NFC,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device tcc_nand_device = {
+	.name = "tcc_nand",
+	.id = 0,
+	.num_resources = ARRAY_SIZE(tcc_nand_resources),
+	.resource = tcc_nand_resources,
+};
+#endif
+
+#ifdef CONFIG_MMC_TCC8K
+/* MMC controller */
+static struct resource tcc8k_mmc0_resource[] = {
+	{
+		.start = INT_SD0,
+		.end   = INT_SD0,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct resource tcc8k_mmc1_resource[] = {
+	{
+		.start = INT_SD1,
+		.end   = INT_SD1,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device tcc8k_mmc0_device = {
+	.name		= "tcc-mmc",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(tcc8k_mmc0_resource),
+	.resource	= tcc8k_mmc0_resource,
+	.dev		= {
+		.dma_mask		= &tcc8k_dmamask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	}
+};
+
+struct platform_device tcc8k_mmc1_device = {
+	.name		= "tcc-mmc",
+	.id		= 1,
+	.num_resources	= ARRAY_SIZE(tcc8k_mmc1_resource),
+	.resource	= tcc8k_mmc1_resource,
+	.dev		= {
+		.dma_mask		= &tcc8k_dmamask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	}
+};
+
+static inline void tcc8k_init_mmc(void)
+{
+	u32 reg = __raw_readl(GPIOPS_BASE + GPIOPS_FS1_OFFS);
+
+	reg |= GPIOPS_FS1_SDH0_BITS | GPIOPS_FS1_SDH1_BITS;
+	__raw_writel(reg, GPIOPS_BASE + GPIOPS_FS1_OFFS);
+
+	platform_device_register(&tcc8k_mmc0_device);
+	platform_device_register(&tcc8k_mmc1_device);
+}
+#else
+static inline void tcc8k_init_mmc(void) { }
+#endif
+
+#ifdef CONFIG_USB_OHCI_HCD
+static int tcc8k_ohci_init(struct device *dev)
+{
+	u32 reg;
+
+	/* Use GPIO PK19 as VBUS control output */
+	reg = __raw_readl(GPIOPK_BASE + GPIOPK_FS0_OFFS);
+	reg &= ~(1 << 19);
+	__raw_writel(reg, GPIOPK_BASE + GPIOPK_FS0_OFFS);
+	reg = __raw_readl(GPIOPK_BASE + GPIOPK_FS1_OFFS);
+	reg &= ~(1 << 19);
+	__raw_writel(reg, GPIOPK_BASE + GPIOPK_FS1_OFFS);
+
+	reg = __raw_readl(GPIOPK_BASE + GPIOPK_DOE_OFFS);
+	reg |= (1 << 19);
+	__raw_writel(reg, GPIOPK_BASE + GPIOPK_DOE_OFFS);
+	/* Turn on VBUS */
+	reg = __raw_readl(GPIOPK_BASE + GPIOPK_DAT_OFFS);
+	reg |= (1 << 19);
+	__raw_writel(reg, GPIOPK_BASE + GPIOPK_DAT_OFFS);
+
+	return 0;
+}
+
+static struct resource tcc8k_ohci0_resources[] = {
+	[0] = {
+		.start = (resource_size_t)USBH0_BASE,
+		.end   = (resource_size_t)USBH0_BASE + 0x5c,
+		.flags = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start = INT_USBH0,
+		.end   = INT_USBH0,
+		.flags = IORESOURCE_IRQ,
+	}
+};
+
+static struct resource tcc8k_ohci1_resources[] = {
+	[0] = {
+		.start = (resource_size_t)USBH1_BASE,
+		.end   = (resource_size_t)USBH1_BASE + 0x5c,
+		.flags = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start = INT_USBH1,
+		.end   = INT_USBH1,
+		.flags = IORESOURCE_IRQ,
+	}
+};
+
+static struct tccohci_platform_data tcc8k_ohci0_platform_data = {
+	.controller	= 0,
+	.port_mode	= PMM_PERPORT_MODE,
+	.init		= tcc8k_ohci_init,
+};
+
+static struct tccohci_platform_data tcc8k_ohci1_platform_data = {
+	.controller	= 1,
+	.port_mode	= PMM_PERPORT_MODE,
+	.init		= tcc8k_ohci_init,
+};
+
+static struct platform_device ohci0_device = {
+	.name = "tcc-ohci",
+	.id = 0,
+	.dev = {
+		.dma_mask = &tcc8k_dmamask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+		.platform_data = &tcc8k_ohci0_platform_data,
+	},
+	.num_resources  = ARRAY_SIZE(tcc8k_ohci0_resources),
+	.resource       = tcc8k_ohci0_resources,
+};
+
+static struct platform_device ohci1_device = {
+	.name = "tcc-ohci",
+	.id = 1,
+	.dev = {
+		.dma_mask = &tcc8k_dmamask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+		.platform_data = &tcc8k_ohci1_platform_data,
+	},
+	.num_resources  = ARRAY_SIZE(tcc8k_ohci1_resources),
+	.resource       = tcc8k_ohci1_resources,
+};
+
+static void __init tcc8k_init_usbhost(void)
+{
+	platform_device_register(&ohci0_device);
+	platform_device_register(&ohci1_device);
+}
+#else
+static void __init tcc8k_init_usbhost(void) { }
+#endif
+
+/* USB device controller*/
+#ifdef CONFIG_USB_GADGET_TCC8K
+static struct resource udc_resources[] = {
+	[0] = {
+		.start = INT_USBD,
+		.end   = INT_USBD,
+		.flags = IORESOURCE_IRQ,
+	},
+	[1] = {
+		.start = INT_UDMA,
+		.end   = INT_UDMA,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device tcc8k_udc_device = {
+	.name = "tcc-udc",
+	.id = 0,
+	.resource = udc_resources,
+	.num_resources = ARRAY_SIZE(udc_resources),
+	.dev = {
+		 .dma_mask = &tcc8k_dmamask,
+		 .coherent_dma_mask = DMA_BIT_MASK(32),
+	},
+};
+
+static void __init tcc8k_init_usb_gadget(void)
+{
+	platform_device_register(&tcc8k_udc_device);
+}
+#else
+static void __init tcc8k_init_usb_gadget(void) { }
+#endif	/* CONFIG_USB_GADGET_TCC83X */
+
+static int __init tcc8k_init_devices(void)
+{
+	tcc8k_init_mmc();
+	tcc8k_init_usbhost();
+	tcc8k_init_usb_gadget();
+	return 0;
+}
+
+arch_initcall(tcc8k_init_devices);
diff --git a/arch/arm/mach-tcc8k/io.c b/arch/arm/mach-tcc8k/io.c
new file mode 100644
index 0000000..9b39d7f
--- /dev/null
+++ b/arch/arm/mach-tcc8k/io.c
@@ -0,0 +1,62 @@
+/*
+ * linux/arch/arm/mach-tcc8k/io.c
+ *
+ * (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * derived from TCC83xx io.c
+ * Copyright (C) Telechips, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+
+#include <asm/mach/map.h>
+
+#include <mach/tcc8k-regs.h>
+
+/*
+ * The machine specific code may provide the extra mapping besides the
+ * default mapping provided here.
+ */
+static struct map_desc tcc8k_io_desc[] __initdata = {
+	{
+		.virtual	= (unsigned long)CS1_BASE_VIRT,
+		.pfn		= __phys_to_pfn(CS1_BASE),
+		.length		= CS1_SIZE,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)AHB_PERI_BASE_VIRT,
+		.pfn		= __phys_to_pfn(AHB_PERI_BASE),
+		.length		= AHB_PERI_SIZE,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)APB0_PERI_BASE_VIRT,
+		.pfn		= __phys_to_pfn(APB0_PERI_BASE),
+		.length		= APB0_PERI_SIZE,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)APB1_PERI_BASE_VIRT,
+		.pfn		= __phys_to_pfn(APB1_PERI_BASE),
+		.length		= APB1_PERI_SIZE,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= (unsigned long)EXT_MEM_CTRL_BASE_VIRT,
+		.pfn		= __phys_to_pfn(EXT_MEM_CTRL_BASE),
+		.length		= EXT_MEM_CTRL_SIZE,
+		.type		= MT_DEVICE,
+	},
+};
+
+/*
+ * Maps common IO regions for tcc8k.
+ *
+ */
+void __init tcc8k_map_common_io(void)
+{
+	iotable_init(tcc8k_io_desc, ARRAY_SIZE(tcc8k_io_desc));
+}
diff --git a/arch/arm/mach-tcc8k/irq.c b/arch/arm/mach-tcc8k/irq.c
new file mode 100644
index 0000000..34575c4
--- /dev/null
+++ b/arch/arm/mach-tcc8k/irq.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright (C) Telechips, Inc.
+ * Copyright (C) 2009-2010 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GNU GPL version 2.
+ */
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+
+#include <asm/irq.h>
+#include <asm/mach/irq.h>
+
+#include <mach/tcc8k-regs.h>
+#include <mach/irqs.h>
+
+#include "common.h"
+
+/* Disable IRQ */
+static void tcc8000_mask_ack_irq0(unsigned int irq)
+{
+	PIC0_IEN &= ~(1 << irq);
+	PIC0_CREQ |=  (1 << irq);
+}
+
+static void tcc8000_mask_ack_irq1(unsigned int irq)
+{
+	PIC1_IEN &= ~(1 << (irq - 32));
+	PIC1_CREQ |= (1 << (irq - 32));
+}
+
+static void tcc8000_mask_irq0(unsigned int irq)
+{
+	PIC0_IEN &= ~(1 << irq);
+}
+
+static void tcc8000_mask_irq1(unsigned int irq)
+{
+	PIC1_IEN &= ~(1 << (irq - 32));
+}
+
+static void tcc8000_ack_irq0(unsigned int irq)
+{
+	PIC0_CREQ |=  (1 << irq);
+}
+
+static void tcc8000_ack_irq1(unsigned int irq)
+{
+	PIC1_CREQ |= (1 << (irq - 32));
+}
+
+/* Enable IRQ */
+static void tcc8000_unmask_irq0(unsigned int irq)
+{
+	PIC0_IEN |= (1 << irq);
+	PIC0_INTOEN |= (1 << irq);
+}
+
+static void tcc8000_unmask_irq1(unsigned int irq)
+{
+	PIC1_IEN |= (1 << (irq - 32));
+	PIC1_INTOEN |= (1 << (irq - 32));
+}
+
+static struct irq_chip tcc8000_irq_chip0 = {
+	.name		= "tcc_irq0",
+	.mask		= tcc8000_mask_irq0,
+	.ack		= tcc8000_ack_irq0,
+	.mask_ack	= tcc8000_mask_ack_irq0,
+	.unmask		= tcc8000_unmask_irq0,
+};
+
+static struct irq_chip tcc8000_irq_chip1 = {
+	.name		= "tcc_irq1",
+	.mask		= tcc8000_mask_irq1,
+	.ack		= tcc8000_ack_irq1,
+	.mask_ack	= tcc8000_mask_ack_irq1,
+	.unmask		= tcc8000_unmask_irq1,
+};
+
+void __init tcc8k_init_irq(void)
+{
+	int irqno;
+
+	/* Mask and clear all interrupts */
+	PIC0_IEN = 0x00000000;
+	PIC0_CREQ = 0xffffffff;
+	PIC1_IEN = 0x00000000;
+	PIC1_CREQ = 0xffffffff;
+
+	PIC0_MEN0 = 0x00000003;
+	PIC1_MEN1 = 0x00000003;
+	PIC1_MEN = 0x00000003;
+
+	/* let all IRQs be level triggered */
+	PIC0_TMODE = 0xffffffff;
+	PIC1_TMODE = 0xffffffff;
+	/* all IRQs are IRQs (not FIQs) */
+	PIC0_IRQSEL = 0xffffffff;
+	PIC1_IRQSEL = 0xffffffff;
+
+	for (irqno = 0; irqno < NR_IRQS; irqno++) {
+		if (irqno < 32)
+			set_irq_chip(irqno, &tcc8000_irq_chip0);
+		else
+			set_irq_chip(irqno, &tcc8000_irq_chip1);
+		set_irq_handler(irqno, handle_level_irq);
+		set_irq_flags(irqno, IRQF_VALID);
+	}
+}
diff --git a/arch/arm/mach-tcc8k/time.c b/arch/arm/mach-tcc8k/time.c
new file mode 100644
index 0000000..78d0600
--- /dev/null
+++ b/arch/arm/mach-tcc8k/time.c
@@ -0,0 +1,149 @@
+/*
+ * TCC8000 system timer setup
+ *
+ * (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GPL version 2.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+
+#include <asm/mach/time.h>
+
+#include <mach/tcc8k-regs.h>
+#include <mach/irqs.h>
+
+#include "common.h"
+
+static void __iomem *timer_base;
+
+static cycle_t tcc_get_cycles(struct clocksource *cs)
+{
+	return __raw_readl(timer_base + TC32MCNT_OFFS);
+}
+
+static struct clocksource clocksource_tcc = {
+	.name		= "tcc_tc32",
+	.rating		= 200,
+	.read		= tcc_get_cycles,
+	.mask		= CLOCKSOURCE_MASK(32),
+	.shift		= 28,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static int tcc_set_next_event(unsigned long evt,
+			      struct clock_event_device *unused)
+{
+	unsigned long reg = __raw_readl(timer_base + TC32MCNT_OFFS);
+
+	__raw_writel(reg + evt, timer_base + TC32CMP0_OFFS);
+	return 0;
+}
+
+static void tcc_set_mode(enum clock_event_mode mode,
+				struct clock_event_device *evt)
+{
+	unsigned long tc32irq;
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_ONESHOT:
+		tc32irq = __raw_readl(timer_base + TC32IRQ_OFFS);
+		tc32irq |= TC32IRQ_IRQEN0;
+		__raw_writel(tc32irq, timer_base + TC32IRQ_OFFS);
+		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+		tc32irq = __raw_readl(timer_base + TC32IRQ_OFFS);
+		tc32irq &= ~TC32IRQ_IRQEN0;
+		__raw_writel(tc32irq, timer_base + TC32IRQ_OFFS);
+		break;
+	case CLOCK_EVT_MODE_PERIODIC:
+	case CLOCK_EVT_MODE_RESUME:
+		break;
+	}
+}
+
+static irqreturn_t tcc8k_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	/* Acknowledge TC32 interrupt by reading TC32IRQ */
+	__raw_readl(timer_base + TC32IRQ_OFFS);
+
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static struct clock_event_device clockevent_tcc = {
+	.name		= "tcc_timer1",
+	.features	= CLOCK_EVT_FEAT_ONESHOT,
+	.shift		= 32,
+	.set_mode	= tcc_set_mode,
+	.set_next_event	= tcc_set_next_event,
+	.rating		= 200,
+};
+
+static struct irqaction tcc8k_timer_irq = {
+	.name		= "TC32_timer",
+	.flags		= IRQF_DISABLED | IRQF_TIMER,
+	.handler	= tcc8k_timer_interrupt,
+	.dev_id		= &clockevent_tcc,
+};
+
+static int __init tcc_clockevent_init(struct clk *clock)
+{
+	unsigned int c = clk_get_rate(clock);
+
+	clocksource_tcc.mult = clocksource_hz2mult(c,
+					clocksource_tcc.shift);
+	clocksource_register(&clocksource_tcc);
+
+	clockevent_tcc.mult = div_sc(c, NSEC_PER_SEC,
+					clockevent_tcc.shift);
+	clockevent_tcc.max_delta_ns =
+			clockevent_delta2ns(0xfffffffe, &clockevent_tcc);
+	clockevent_tcc.min_delta_ns =
+			clockevent_delta2ns(0xff, &clockevent_tcc);
+
+	clockevent_tcc.cpumask = cpumask_of(0);
+
+	clockevents_register_device(&clockevent_tcc);
+
+	return 0;
+}
+
+void __init tcc8k_timer_init(struct clk *clock, void __iomem *base, int irq)
+{
+	u32 reg;
+
+	timer_base = base;
+	tcc8k_timer_irq.irq = irq;
+
+	/* Enable clocks */
+	clk_enable(clock);
+
+	/* Initialize 32-bit timer */
+	reg = __raw_readl(timer_base + TC32EN_OFFS);
+	reg &= ~TC32EN_ENABLE; /* Disable timer */
+	__raw_writel(reg, timer_base + TC32EN_OFFS);
+	/* Free running timer, counting from 0 to 0xffffffff */
+	__raw_writel(0, timer_base + TC32EN_OFFS);
+	__raw_writel(0, timer_base + TC32LDV_OFFS);
+	reg = __raw_readl(timer_base + TC32IRQ_OFFS);
+	reg |= TC32IRQ_IRQEN0; /* irq at match with CMP0 */
+	__raw_writel(reg, timer_base + TC32IRQ_OFFS);
+
+	__raw_writel(TC32EN_ENABLE, timer_base + TC32EN_OFFS);
+
+	tcc_clockevent_init(clock);
+	setup_irq(irq, &tcc8k_timer_irq);
+}
diff --git a/arch/arm/mach-tegra/board-harmony.c b/arch/arm/mach-tegra/board-harmony.c
index 9e305de..b9dbdb1 100644
--- a/arch/arm/mach-tegra/board-harmony.c
+++ b/arch/arm/mach-tegra/board-harmony.c
@@ -115,8 +115,6 @@
 
 MACHINE_START(HARMONY, "harmony")
 	.boot_params  = 0x00000100,
-	.phys_io        = IO_APB_PHYS,
-	.io_pg_offst    = ((IO_APB_VIRT) >> 18) & 0xfffc,
 	.fixup		= tegra_harmony_fixup,
 	.init_irq       = tegra_init_irq,
 	.init_machine   = tegra_harmony_init,
diff --git a/arch/arm/mach-tegra/include/mach/debug-macro.S b/arch/arm/mach-tegra/include/mach/debug-macro.S
index 55a3956..8ea3bff 100644
--- a/arch/arm/mach-tegra/include/mach/debug-macro.S
+++ b/arch/arm/mach-tegra/include/mach/debug-macro.S
@@ -20,24 +20,28 @@
 
 #include <mach/io.h>
 
-	.macro  addruart,rx, tmp
-        mrc     p15, 0, \rx, c1, c0
-        tst     \rx, #1                 @ MMU enabled?
-        ldreq   \rx, =IO_APB_PHYS       @ physical
-        ldrne   \rx, =IO_APB_VIRT        @ virtual
+	.macro  addruart, rp, rv
+        ldreq   \rp, =IO_APB_PHYS       @ physical
+        ldrne   \rv, =IO_APB_VIRT        @ virtual
 #if defined(CONFIG_TEGRA_DEBUG_UART_NONE)
 #error "A debug UART must be selected in the kernel config to use DEBUG_LL"
 #elif defined(CONFIG_TEGRA_DEBUG_UARTA)
-        orr     \rx, \rx, #0x6000
+        orr     \rp, \rp, #0x6000
+        orr     \rv, \rv, #0x6000
 #elif defined(CONFIG_TEGRA_DEBUG_UARTB)
-	ldr	\tmp, =0x6040
-        orr     \rx, \rx, \tmp
+        orr     \rp, \rp, #0x6000
+	orr	\rp, \rp, #0x40
+        orr     \rv, \rv, #0x6000
+	orr	\rv, \rv, #0x40
 #elif defined(CONFIG_TEGRA_DEBUG_UARTC)
-        orr     \rx, \rx, #0x6200
+        orr     \rp, \rp, #0x6200
+        orr     \rv, \rv, #0x6200
 #elif defined(CONFIG_TEGRA_DEBUG_UARTD)
-        orr     \rx, \rx, #0x6300
+        orr     \rp, \rp, #0x6300
+        orr     \rv, \rv, #0x6300
 #elif defined(CONFIG_TEGRA_DEBUG_UARTE)
-        orr     \rx, \rx, #0x6400
+        orr     \rp, \rp, #0x6400
+        orr     \rv, \rv, #0x6400
 #endif
 	.endm
 
diff --git a/arch/arm/mach-tegra/include/mach/smp.h b/arch/arm/mach-tegra/include/mach/smp.h
index 8b42dab..e4a34a3 100644
--- a/arch/arm/mach-tegra/include/mach/smp.h
+++ b/arch/arm/mach-tegra/include/mach/smp.h
@@ -1,16 +1,8 @@
 #ifndef ASMARM_ARCH_SMP_H
 #define ASMARM_ARCH_SMP_H
 
-
 #include <asm/hardware/gic.h>
-
-#define hard_smp_processor_id()			\
-	({						\
-		unsigned int cpunum;			\
-		__asm__("mrc p15, 0, %0, c0, c0, 5"	\
-			: "=r" (cpunum));		\
-		cpunum &= 0x0F;				\
-	})
+#include <asm/smp_mpidr.h>
 
 /*
  * We use IRQ1 as the IPI
diff --git a/arch/arm/mach-u300/dummyspichip.c b/arch/arm/mach-u300/dummyspichip.c
index 5f55012..03f7936 100644
--- a/arch/arm/mach-u300/dummyspichip.c
+++ b/arch/arm/mach-u300/dummyspichip.c
@@ -46,7 +46,6 @@
 	 * struct, this is just used here to alter the behaviour of the chip
 	 * in order to perform tests.
 	 */
-	struct pl022_config_chip *chip_info = spi->controller_data;
 	int status;
 	u8 txbuf[14] = {0xDE, 0xAD, 0xBE, 0xEF, 0x2B, 0xAD,
 			0xCA, 0xFE, 0xBA, 0xBE, 0xB1, 0x05,
@@ -72,7 +71,7 @@
 	 * Force chip to 8 bit mode
 	 * WARNING: NEVER DO THIS IN REAL DRIVER CODE, THIS SHOULD BE STATIC!
 	 */
-	chip_info->data_size = SSP_DATA_BITS_8;
+	spi->bits_per_word = 8;
 	/* You should NOT DO THIS EITHER */
 	spi->master->setup(spi);
 
@@ -159,7 +158,7 @@
 	 * Force chip to 16 bit mode
 	 * WARNING: NEVER DO THIS IN REAL DRIVER CODE, THIS SHOULD BE STATIC!
 	 */
-	chip_info->data_size = SSP_DATA_BITS_16;
+	spi->bits_per_word = 16;
 	/* You should NOT DO THIS EITHER */
 	spi->master->setup(spi);
 
diff --git a/arch/arm/mach-u300/include/mach/debug-macro.S b/arch/arm/mach-u300/include/mach/debug-macro.S
index 92c1242..df71570 100644
--- a/arch/arm/mach-u300/include/mach/debug-macro.S
+++ b/arch/arm/mach-u300/include/mach/debug-macro.S
@@ -10,13 +10,12 @@
  */
 #include <mach/hardware.h>
 
-	.macro	addruart, rx, tmp
+	.macro	addruart, rp, rv
 	/* If we move the address using MMU, use this. */
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1			@ MMU enabled?
-	ldreq	\rx,	  = U300_SLOW_PER_PHYS_BASE @ MMU off, physical address
-	ldrne	\rx,	  = U300_SLOW_PER_VIRT_BASE @ MMU on, virtual address
-	orr	\rx, \rx, #0x00003000
+	ldr	\rp,	  = U300_SLOW_PER_PHYS_BASE @ MMU off, physical address
+	ldr	\rv,	  = U300_SLOW_PER_VIRT_BASE @ MMU on, virtual address
+	orr	\rp, \rp, #0x00003000
+	orr	\rv, \rv, #0x00003000
 	.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-u300/spi.c b/arch/arm/mach-u300/spi.c
index f0e887b..edb2c0d 100644
--- a/arch/arm/mach-u300/spi.c
+++ b/arch/arm/mach-u300/spi.c
@@ -30,8 +30,6 @@
 }
 
 struct pl022_config_chip dummy_chip_info = {
-	/* Nominally this is LOOPBACK_DISABLED, but this is our dummy chip! */
-	.lbm = LOOPBACK_ENABLED,
 	/*
 	 * available POLLING_TRANSFER and INTERRUPT_TRANSFER,
 	 * DMA_TRANSFER does not work
@@ -42,14 +40,8 @@
 	.hierarchy = SSP_MASTER,
 	/* 0 = drive TX even as slave, 1 = do not drive TX as slave */
 	.slave_tx_disable = 0,
-	/* LSB first */
-	.endian_tx = SSP_TX_LSB,
-	.endian_rx = SSP_RX_LSB,
-	.data_size = SSP_DATA_BITS_8, /* used to be 12 in some default */
 	.rx_lev_trig = SSP_RX_1_OR_MORE_ELEM,
 	.tx_lev_trig = SSP_TX_1_OR_MORE_EMPTY_LOC,
-	.clk_phase = SSP_CLK_SECOND_EDGE,
-	.clk_pol = SSP_CLK_POL_IDLE_LOW,
 	.ctrl_len = SSP_BITS_12,
 	.wait_state = SSP_MWIRE_WAIT_ZERO,
 	.duplex = SSP_MICROWIRE_CHANNEL_FULL_DUPLEX,
@@ -75,7 +67,7 @@
 		.bus_num        = 0, /* Only one bus on this chip */
 		.chip_select    = 0,
 		/* Means SPI_CS_HIGH, change if e.g low CS */
-		.mode           = 0,
+		.mode           = SPI_MODE_1 | SPI_LSB_FIRST | SPI_LOOP,
 	},
 #endif
 };
diff --git a/arch/arm/mach-u300/u300.c b/arch/arm/mach-u300/u300.c
index bfcda98..07c35a8 100644
--- a/arch/arm/mach-u300/u300.c
+++ b/arch/arm/mach-u300/u300.c
@@ -61,8 +61,6 @@
 
 MACHINE_START(U300, MACH_U300_STRING)
 	/* Maintainer: Linus Walleij <linus.walleij@stericsson.com> */
-	.phys_io	= U300_AHB_PER_PHYS_BASE,
-	.io_pg_offst	= ((U300_AHB_PER_VIRT_BASE) >> 18) & 0xfffc,
 	.boot_params	= BOOT_PARAMS_OFFSET,
 	.map_io		= u300_map_io,
 	.reserve	= u300_reserve,
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index 6625e5b..2dd44a0 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -21,9 +21,7 @@
 	bool "U8500 Development platform"
 	select UX500_SOC_DB8500
 	help
-	  Include support for mop500 development platform
-	  based on U8500 architecture. The platform is based
-	  on early drop silicon version of 8500.
+	  Include support for the mop500 development platform.
 
 config MACH_U5500
 	bool "U5500 Development platform"
@@ -39,4 +37,18 @@
 	  Choose the UART on which kernel low-level debug messages should be
 	  output.
 
+config U5500_MODEM_IRQ
+	bool "Modem IRQ support"
+	depends on MACH_U5500
+	default y
+	help
+	  Add support for handling IRQ:s from modem side
+
+config U5500_MBOX
+	bool "Mailbox support"
+	depends on MACH_U5500 && U5500_MODEM_IRQ
+	default y
+	help
+	  Add support for U5500 mailbox communication with modem side
+
 endif
diff --git a/arch/arm/mach-ux500/Makefile b/arch/arm/mach-ux500/Makefile
index 4556aea..9e27a84 100644
--- a/arch/arm/mach-ux500/Makefile
+++ b/arch/arm/mach-ux500/Makefile
@@ -4,8 +4,12 @@
 
 obj-y				:= clock.o cpu.o devices.o
 obj-$(CONFIG_UX500_SOC_DB5500)	+= cpu-db5500.o devices-db5500.o
-obj-$(CONFIG_UX500_SOC_DB8500)	+= cpu-db8500.o devices-db8500.o
-obj-$(CONFIG_MACH_U8500_MOP)	+= board-mop500.o
+obj-$(CONFIG_UX500_SOC_DB8500)	+= cpu-db8500.o devices-db8500.o prcmu.o
+obj-$(CONFIG_MACH_U8500_MOP)	+= board-mop500.o board-mop500-sdi.o
 obj-$(CONFIG_MACH_U5500)	+= board-u5500.o
 obj-$(CONFIG_SMP)		+= platsmp.o headsmp.o
+obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug.o
 obj-$(CONFIG_LOCAL_TIMERS)	+= localtimer.o
+obj-$(CONFIG_REGULATOR_AB8500)	+= board-mop500-regulators.o
+obj-$(CONFIG_U5500_MODEM_IRQ)	+= modem_irq.o
+obj-$(CONFIG_U5500_MBOX)	+= mbox.o
diff --git a/arch/arm/mach-ux500/board-mop500-regulators.c b/arch/arm/mach-ux500/board-mop500-regulators.c
new file mode 100644
index 0000000..1187f1f
--- /dev/null
+++ b/arch/arm/mach-ux500/board-mop500-regulators.c
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ *
+ * Author: Sundar Iyer <sundar.iyer@stericsson.com>
+ *
+ * MOP500 board specific initialization for regulators
+ */
+#include <linux/kernel.h>
+#include <linux/regulator/machine.h>
+
+/* supplies to the display/camera */
+static struct regulator_init_data ab8500_vaux1_regulator = {
+	.constraints = {
+		.name = "V-DISPLAY",
+		.min_uV = 2500000,
+		.max_uV = 2900000,
+		.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE|
+					REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supplies to the on-board eMMC */
+static struct regulator_init_data ab8500_vaux2_regulator = {
+	.constraints = {
+		.name = "V-eMMC1",
+		.min_uV = 1100000,
+		.max_uV = 3300000,
+		.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE|
+					REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supply for VAUX3, supplies to SDcard slots */
+static struct regulator_init_data ab8500_vaux3_regulator = {
+	.constraints = {
+		.name = "V-MMC-SD",
+		.min_uV = 1100000,
+		.max_uV = 3300000,
+		.valid_ops_mask = REGULATOR_CHANGE_VOLTAGE|
+					REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supply for tvout, gpadc, TVOUT LDO */
+static struct regulator_init_data ab8500_vtvout_init = {
+	.constraints = {
+		.name = "V-TVOUT",
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supply for ab8500-vaudio, VAUDIO LDO */
+static struct regulator_init_data ab8500_vaudio_init = {
+	.constraints = {
+		.name = "V-AUD",
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supply for v-anamic1 VAMic1-LDO */
+static struct regulator_init_data ab8500_vamic1_init = {
+	.constraints = {
+		.name = "V-AMIC1",
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supply for v-amic2, VAMIC2 LDO, reuse constants for AMIC1 */
+static struct regulator_init_data ab8500_vamic2_init = {
+	.constraints = {
+		.name = "V-AMIC2",
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supply for v-dmic, VDMIC LDO */
+static struct regulator_init_data ab8500_vdmic_init = {
+	.constraints = {
+		.name = "V-DMIC",
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supply for v-intcore12, VINTCORE12 LDO */
+static struct regulator_init_data ab8500_vintcore_init = {
+	.constraints = {
+		.name = "V-INTCORE",
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+};
+
+/* supply for U8500 CSI/DSI, VANA LDO */
+static struct regulator_init_data ab8500_vana_init = {
+	.constraints = {
+		.name = "V-CSI/DSI",
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+};
+
diff --git a/arch/arm/mach-ux500/board-mop500-sdi.c b/arch/arm/mach-ux500/board-mop500-sdi.c
new file mode 100644
index 0000000..bac9956
--- /dev/null
+++ b/arch/arm/mach-ux500/board-mop500-sdi.c
@@ -0,0 +1,91 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * Author: Hanumath Prasad <hanumath.prasad@stericsson.com>
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/amba/bus.h>
+#include <linux/amba/mmci.h>
+#include <linux/mmc/host.h>
+#include <linux/platform_device.h>
+
+#include <plat/pincfg.h>
+#include <mach/devices.h>
+#include <mach/hardware.h>
+
+#include "pins-db8500.h"
+#include "board-mop500.h"
+
+static pin_cfg_t mop500_sdi_pins[] = {
+	/* SDI4 (on-board eMMC) */
+	GPIO197_MC4_DAT3,
+	GPIO198_MC4_DAT2,
+	GPIO199_MC4_DAT1,
+	GPIO200_MC4_DAT0,
+	GPIO201_MC4_CMD,
+	GPIO202_MC4_FBCLK,
+	GPIO203_MC4_CLK,
+	GPIO204_MC4_DAT7,
+	GPIO205_MC4_DAT6,
+	GPIO206_MC4_DAT5,
+	GPIO207_MC4_DAT4,
+};
+
+static pin_cfg_t mop500_sdi2_pins[] = {
+	/* SDI2 (POP eMMC) */
+	GPIO128_MC2_CLK,
+	GPIO129_MC2_CMD,
+	GPIO130_MC2_FBCLK,
+	GPIO131_MC2_DAT0,
+	GPIO132_MC2_DAT1,
+	GPIO133_MC2_DAT2,
+	GPIO134_MC2_DAT3,
+	GPIO135_MC2_DAT4,
+	GPIO136_MC2_DAT5,
+	GPIO137_MC2_DAT6,
+	GPIO138_MC2_DAT7,
+};
+
+/*
+ * SDI 2 (POP eMMC, not on DB8500ed)
+ */
+
+static struct mmci_platform_data mop500_sdi2_data = {
+	.ocr_mask	= MMC_VDD_165_195,
+	.f_max		= 100000000,
+	.capabilities	= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA,
+	.gpio_cd	= -1,
+	.gpio_wp	= -1,
+};
+
+/*
+ * SDI 4 (on-board eMMC)
+ */
+
+static struct mmci_platform_data mop500_sdi4_data = {
+	.ocr_mask	= MMC_VDD_29_30,
+	.f_max		= 100000000,
+	.capabilities	= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA |
+			  MMC_CAP_MMC_HIGHSPEED,
+	.gpio_cd	= -1,
+	.gpio_wp	= -1,
+};
+
+void mop500_sdi_init(void)
+{
+	nmk_config_pins(mop500_sdi_pins, ARRAY_SIZE(mop500_sdi_pins));
+
+	u8500_sdi2_device.dev.platform_data = &mop500_sdi2_data;
+	u8500_sdi4_device.dev.platform_data = &mop500_sdi4_data;
+
+	if (!cpu_is_u8500ed()) {
+		nmk_config_pins(mop500_sdi2_pins, ARRAY_SIZE(mop500_sdi2_pins));
+		amba_device_register(&u8500_sdi2_device, &iomem_resource);
+	}
+
+	/* On-board eMMC */
+	amba_device_register(&u8500_sdi4_device, &iomem_resource);
+}
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index 0e8fd13..fcb587f 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -28,8 +28,10 @@
 #include <mach/hardware.h>
 #include <mach/setup.h>
 #include <mach/devices.h>
+#include <mach/irqs.h>
 
 #include "pins-db8500.h"
+#include "board-mop500.h"
 
 static pin_cfg_t mop500_pins[] = {
 	/* SSP0 */
@@ -55,19 +57,13 @@
 }
 
 struct pl022_config_chip ab4500_chip_info = {
-	.lbm = LOOPBACK_DISABLED,
 	.com_mode = INTERRUPT_TRANSFER,
 	.iface = SSP_INTERFACE_MOTOROLA_SPI,
 	/* we can act as master only */
 	.hierarchy = SSP_MASTER,
 	.slave_tx_disable = 0,
-	.endian_rx = SSP_RX_MSB,
-	.endian_tx = SSP_TX_MSB,
-	.data_size = SSP_DATA_BITS_24,
 	.rx_lev_trig = SSP_RX_1_OR_MORE_ELEM,
 	.tx_lev_trig = SSP_TX_1_OR_MORE_EMPTY_LOC,
-	.clk_phase = SSP_CLK_SECOND_EDGE,
-	.clk_pol = SSP_CLK_POL_IDLE_HIGH,
 	.cs_control = ab4500_spi_cs_control,
 };
 
@@ -75,15 +71,33 @@
 	.irq_base	= MOP500_AB8500_IRQ_BASE,
 };
 
-static struct spi_board_info u8500_spi_devices[] = {
+static struct resource ab8500_resources[] = {
+	[0] = {
+		.start = IRQ_AB8500,
+		.end = IRQ_AB8500,
+		.flags = IORESOURCE_IRQ
+	}
+};
+
+struct platform_device ab8500_device = {
+	.name = "ab8500-i2c",
+	.id = 0,
+	.dev = {
+		.platform_data = &ab8500_platdata,
+	},
+	.num_resources = 1,
+	.resource = ab8500_resources,
+};
+
+static struct spi_board_info ab8500_spi_devices[] = {
 	{
-		.modalias = "ab8500",
+		.modalias = "ab8500-spi",
 		.controller_data = &ab4500_chip_info,
 		.platform_data = &ab8500_platdata,
 		.max_speed_hz = 12000000,
 		.bus_num = 0,
 		.chip_select = 0,
-		.mode = SPI_MODE_0,
+		.mode = SPI_MODE_3,
 		.irq = IRQ_DB8500_AB8500,
 	},
 };
@@ -163,14 +177,18 @@
 
 	platform_add_devices(platform_devs, ARRAY_SIZE(platform_devs));
 
-	spi_register_board_info(u8500_spi_devices,
-			ARRAY_SIZE(u8500_spi_devices));
+	mop500_sdi_init();
+
+	/* If HW is early drop (ED) or V1.0 then use SPI to access AB8500 */
+	if (cpu_is_u8500ed() || cpu_is_u8500v10())
+		spi_register_board_info(ab8500_spi_devices,
+			ARRAY_SIZE(ab8500_spi_devices));
+	else /* If HW is v.1.1 or later use I2C to access AB8500 */
+		platform_device_register(&ab8500_device);
 }
 
 MACHINE_START(U8500, "ST-Ericsson MOP500 platform")
 	/* Maintainer: Srinidhi Kasagar <srinidhi.kasagar@stericsson.com> */
-	.phys_io	= U8500_UART2_BASE,
-	.io_pg_offst	= (IO_ADDRESS(U8500_UART2_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x100,
 	.map_io		= u8500_map_io,
 	.init_irq	= ux500_init_irq,
diff --git a/arch/arm/mach-ux500/board-mop500.h b/arch/arm/mach-ux500/board-mop500.h
new file mode 100644
index 0000000..2d24032
--- /dev/null
+++ b/arch/arm/mach-ux500/board-mop500.h
@@ -0,0 +1,12 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#ifndef __BOARD_MOP500_H
+#define __BOARD_MOP500_H
+
+extern void mop500_sdi_init(void);
+
+#endif
diff --git a/arch/arm/mach-ux500/board-u5500.c b/arch/arm/mach-ux500/board-u5500.c
index 4430e69..1ca094a 100644
--- a/arch/arm/mach-ux500/board-u5500.c
+++ b/arch/arm/mach-ux500/board-u5500.c
@@ -31,8 +31,6 @@
 }
 
 MACHINE_START(U8500, "ST-Ericsson U5500 Platform")
-	.phys_io	= UX500_UART0_BASE,
-	.io_pg_offst	= (IO_ADDRESS(UX500_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= u5500_map_io,
 	.init_irq	= ux500_init_irq,
diff --git a/arch/arm/mach-ux500/cpu-db5500.c b/arch/arm/mach-ux500/cpu-db5500.c
index e9278f6..2f87075 100644
--- a/arch/arm/mach-ux500/cpu-db5500.c
+++ b/arch/arm/mach-ux500/cpu-db5500.c
@@ -14,6 +14,7 @@
 #include <mach/hardware.h>
 #include <mach/devices.h>
 #include <mach/setup.h>
+#include <mach/irqs.h>
 
 static struct map_desc u5500_io_desc[] __initdata = {
 	__IO_DEV_DESC(U5500_GPIO0_BASE, SZ_4K),
@@ -24,6 +25,90 @@
 	__IO_DEV_DESC(U5500_PRCMU_BASE, SZ_4K),
 };
 
+static struct resource mbox0_resources[] = {
+	{
+		.name = "mbox_peer",
+		.start = U5500_MBOX0_PEER_START,
+		.end = U5500_MBOX0_PEER_END,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "mbox_local",
+		.start = U5500_MBOX0_LOCAL_START,
+		.end = U5500_MBOX0_LOCAL_END,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "mbox_irq",
+		.start = MBOX_PAIR0_VIRT_IRQ,
+		.end = MBOX_PAIR0_VIRT_IRQ,
+		.flags = IORESOURCE_IRQ,
+	}
+};
+
+static struct resource mbox1_resources[] = {
+	{
+		.name = "mbox_peer",
+		.start = U5500_MBOX1_PEER_START,
+		.end = U5500_MBOX1_PEER_END,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "mbox_local",
+		.start = U5500_MBOX1_LOCAL_START,
+		.end = U5500_MBOX1_LOCAL_END,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "mbox_irq",
+		.start = MBOX_PAIR1_VIRT_IRQ,
+		.end = MBOX_PAIR1_VIRT_IRQ,
+		.flags = IORESOURCE_IRQ,
+	}
+};
+
+static struct resource mbox2_resources[] = {
+	{
+		.name = "mbox_peer",
+		.start = U5500_MBOX2_PEER_START,
+		.end = U5500_MBOX2_PEER_END,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "mbox_local",
+		.start = U5500_MBOX2_LOCAL_START,
+		.end = U5500_MBOX2_LOCAL_END,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name = "mbox_irq",
+		.start = MBOX_PAIR2_VIRT_IRQ,
+		.end = MBOX_PAIR2_VIRT_IRQ,
+		.flags = IORESOURCE_IRQ,
+	}
+};
+
+static struct platform_device mbox0_device = {
+	.id = 0,
+	.name = "mbox",
+	.resource = mbox0_resources,
+	.num_resources = ARRAY_SIZE(mbox0_resources),
+};
+
+static struct platform_device mbox1_device = {
+	.id = 1,
+	.name = "mbox",
+	.resource = mbox1_resources,
+	.num_resources = ARRAY_SIZE(mbox1_resources),
+};
+
+static struct platform_device mbox2_device = {
+	.id = 2,
+	.name = "mbox",
+	.resource = mbox2_resources,
+	.num_resources = ARRAY_SIZE(mbox2_resources),
+};
+
 static struct platform_device *u5500_platform_devs[] __initdata = {
 	&u5500_gpio_devs[0],
 	&u5500_gpio_devs[1],
@@ -33,6 +118,9 @@
 	&u5500_gpio_devs[5],
 	&u5500_gpio_devs[6],
 	&u5500_gpio_devs[7],
+	&mbox0_device,
+	&mbox1_device,
+	&mbox2_device,
 };
 
 void __init u5500_map_io(void)
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index f21c444..4acab75 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -38,10 +38,12 @@
 /* minimum static i/o mapping required to boot U8500 platforms */
 static struct map_desc u8500_io_desc[] __initdata = {
 	__IO_DEV_DESC(U8500_PRCMU_BASE, SZ_4K),
+	__IO_DEV_DESC(U8500_PRCMU_TCDM_BASE, SZ_4K),
 	__IO_DEV_DESC(U8500_GPIO0_BASE, SZ_4K),
 	__IO_DEV_DESC(U8500_GPIO1_BASE, SZ_4K),
 	__IO_DEV_DESC(U8500_GPIO2_BASE, SZ_4K),
 	__IO_DEV_DESC(U8500_GPIO3_BASE, SZ_4K),
+	__MEM_DEV_DESC(U8500_BOOT_ROM_BASE, SZ_1M),
 };
 
 static struct map_desc u8500ed_io_desc[] __initdata = {
@@ -53,6 +55,69 @@
 	__IO_DEV_DESC(U8500_MTU0_BASE, SZ_4K),
 };
 
+/*
+ * Functions to differentiate between later ASICs
+ * We look into the end of the ROM to locate the hardcoded ASIC ID.
+ * This is only needed to differentiate between minor revisions and
+ * process variants of an ASIC, the major revisions are encoded in
+ * the cpuid.
+ */
+#define U8500_ASIC_ID_LOC_ED_V1	(U8500_BOOT_ROM_BASE + 0x1FFF4)
+#define U8500_ASIC_ID_LOC_V2	(U8500_BOOT_ROM_BASE + 0x1DBF4)
+#define U8500_ASIC_REV_ED	0x01
+#define U8500_ASIC_REV_V10	0xA0
+#define U8500_ASIC_REV_V11	0xA1
+#define U8500_ASIC_REV_V20	0xB0
+
+/**
+ * struct db8500_asic_id - fields of the ASIC ID
+ * @process: the manufacturing process, 0x40 is 40 nm
+ *  0x00 is "standard"
+ * @partnumber: hithereto 0x8500 for DB8500
+ * @revision: version code in the series
+ * This field definion is not formally defined but makes
+ * sense.
+ */
+struct db8500_asic_id {
+	u8 process;
+	u16 partnumber;
+	u8 revision;
+};
+
+/* This isn't going to change at runtime */
+static struct db8500_asic_id db8500_id;
+
+static void __init get_db8500_asic_id(void)
+{
+	u32 asicid;
+
+	if (cpu_is_u8500v1() || cpu_is_u8500ed())
+		asicid = readl(__io_address(U8500_ASIC_ID_LOC_ED_V1));
+	else if (cpu_is_u8500v2())
+		asicid = readl(__io_address(U8500_ASIC_ID_LOC_V2));
+	else
+		BUG();
+
+	db8500_id.process = (asicid >> 24);
+	db8500_id.partnumber = (asicid >> 16) & 0xFFFFU;
+	db8500_id.revision = asicid & 0xFFU;
+}
+
+bool cpu_is_u8500v10(void)
+{
+	return (db8500_id.revision == U8500_ASIC_REV_V10);
+}
+
+bool cpu_is_u8500v11(void)
+{
+	return (db8500_id.revision == U8500_ASIC_REV_V11);
+}
+
+bool cpu_is_u8500v20(void)
+{
+	return (db8500_id.revision == U8500_ASIC_REV_V20);
+}
+
 void __init u8500_map_io(void)
 {
 	ux500_map_io();
@@ -63,6 +128,9 @@
 		iotable_init(u8500ed_io_desc, ARRAY_SIZE(u8500ed_io_desc));
 	else
 		iotable_init(u8500v1_io_desc, ARRAY_SIZE(u8500v1_io_desc));
+
+	/* Read out the ASIC ID as early as we can */
+	get_db8500_asic_id();
 }
 
 /*
@@ -70,6 +138,20 @@
  */
 void __init u8500_init_devices(void)
 {
+	/* Display some ASIC boilerplate */
+	pr_info("DB8500: process: %02x, revision ID: 0x%02x\n",
+		db8500_id.process, db8500_id.revision);
+	if (cpu_is_u8500ed())
+		pr_info("DB8500: Early Drop (ED)\n");
+	else if (cpu_is_u8500v10())
+		pr_info("DB8500: version 1.0\n");
+	else if (cpu_is_u8500v11())
+		pr_info("DB8500: version 1.1\n");
+	else if (cpu_is_u8500v20())
+		pr_info("DB8500: version 2.0\n");
+	else
+		pr_warning("ASIC: UNKNOWN SILICON VERSION!\n");
+
 	ux500_init_devices();
 
 	if (cpu_is_u8500ed())
diff --git a/arch/arm/mach-ux500/devices-db8500.c b/arch/arm/mach-ux500/devices-db8500.c
index 9280d25..40032fe 100644
--- a/arch/arm/mach-ux500/devices-db8500.c
+++ b/arch/arm/mach-ux500/devices-db8500.c
@@ -110,6 +110,82 @@
 	.num_resources	= ARRAY_SIZE(u8500_i2c4_resources),
 };
 
+/*
+ * SD/MMC
+ */
+
+struct amba_device u8500_sdi0_device = {
+	.dev		= {
+		.init_name = "sdi0",
+	},
+	.res		= {
+		.start	= U8500_SDI0_BASE,
+		.end	= U8500_SDI0_BASE + SZ_4K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	.irq		= {IRQ_DB8500_SDMMC0, NO_IRQ},
+};
+
+struct amba_device u8500_sdi1_device = {
+	.dev		= {
+		.init_name = "sdi1",
+	},
+	.res		= {
+		.start	= U8500_SDI1_BASE,
+		.end	= U8500_SDI1_BASE + SZ_4K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	.irq		= {IRQ_DB8500_SDMMC1, NO_IRQ},
+};
+
+struct amba_device u8500_sdi2_device = {
+	.dev		= {
+		.init_name = "sdi2",
+	},
+	.res		= {
+		.start	= U8500_SDI2_BASE,
+		.end	= U8500_SDI2_BASE + SZ_4K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	.irq		= {IRQ_DB8500_SDMMC2, NO_IRQ},
+};
+
+struct amba_device u8500_sdi3_device = {
+	.dev		= {
+		.init_name = "sdi3",
+	},
+	.res		= {
+		.start	= U8500_SDI3_BASE,
+		.end	= U8500_SDI3_BASE + SZ_4K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	.irq		= {IRQ_DB8500_SDMMC3, NO_IRQ},
+};
+
+struct amba_device u8500_sdi4_device = {
+	.dev		= {
+		.init_name = "sdi4",
+	},
+	.res		= {
+		.start	= U8500_SDI4_BASE,
+		.end	= U8500_SDI4_BASE + SZ_4K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	.irq		= {IRQ_DB8500_SDMMC4, NO_IRQ},
+};
+
+struct amba_device u8500_sdi5_device = {
+	.dev		= {
+		.init_name = "sdi5",
+	},
+	.res		= {
+		.start	= U8500_SDI5_BASE,
+		.end	= U8500_SDI5_BASE + SZ_4K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	.irq		= {IRQ_DB8500_SDMMC5, NO_IRQ},
+};
+
 static struct resource dma40_resources[] = {
 	[0] = {
 		.start = U8500_DMA_BASE,
@@ -170,23 +246,23 @@
  * Mapping between destination event lines and physical device address.
  * The event line is tied to a device and therefor the address is constant.
  */
-static const dma_addr_t dma40_tx_map[STEDMA40_NR_DEV];
+static const dma_addr_t dma40_tx_map[DB8500_DMA_NR_DEV];
 
 /* Mapping between source event lines and physical device address */
-static const dma_addr_t dma40_rx_map[STEDMA40_NR_DEV];
+static const dma_addr_t dma40_rx_map[DB8500_DMA_NR_DEV];
 
 /* Reserved event lines for memcpy only */
 static int dma40_memcpy_event[] = {
-	STEDMA40_MEMCPY_TX_0,
-	STEDMA40_MEMCPY_TX_1,
-	STEDMA40_MEMCPY_TX_2,
-	STEDMA40_MEMCPY_TX_3,
-	STEDMA40_MEMCPY_TX_4,
-	STEDMA40_MEMCPY_TX_5,
+	DB8500_DMA_MEMCPY_TX_0,
+	DB8500_DMA_MEMCPY_TX_1,
+	DB8500_DMA_MEMCPY_TX_2,
+	DB8500_DMA_MEMCPY_TX_3,
+	DB8500_DMA_MEMCPY_TX_4,
+	DB8500_DMA_MEMCPY_TX_5,
 };
 
 static struct stedma40_platform_data dma40_plat_data = {
-	.dev_len = STEDMA40_NR_DEV,
+	.dev_len = DB8500_DMA_NR_DEV,
 	.dev_rx = dma40_rx_map,
 	.dev_tx = dma40_tx_map,
 	.memcpy = dma40_memcpy_event,
diff --git a/arch/arm/mach-ux500/hotplug.c b/arch/arm/mach-ux500/hotplug.c
new file mode 100644
index 0000000..b782a03
--- /dev/null
+++ b/arch/arm/mach-ux500/hotplug.c
@@ -0,0 +1,75 @@
+/*
+ * Copyright (C) STMicroelectronics 2009
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ *	Based on ARM realview platform
+ *
+ * Author: Sundar Iyer <sundar.iyer@stericsson.com>
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/smp.h>
+#include <linux/completion.h>
+
+#include <asm/cacheflush.h>
+
+extern volatile int pen_release;
+
+static DECLARE_COMPLETION(cpu_killed);
+
+static inline void platform_do_lowpower(unsigned int cpu)
+{
+	flush_cache_all();
+
+	/* we put the platform to just WFI */
+	for (;;) {
+		__asm__ __volatile__("dsb\n\t" "wfi\n\t"
+				: : : "memory");
+		if (pen_release == cpu) {
+			/*
+			 * OK, proper wakeup, we're done
+			 */
+			break;
+		}
+	}
+}
+
+int platform_cpu_kill(unsigned int cpu)
+{
+	return wait_for_completion_timeout(&cpu_killed, 5000);
+}
+
+/*
+ * platform-specific code to shutdown a CPU
+ *
+ * Called with IRQs disabled
+ */
+void platform_cpu_die(unsigned int cpu)
+{
+#ifdef DEBUG
+	unsigned int this_cpu = hard_smp_processor_id();
+
+	if (cpu != this_cpu) {
+		printk(KERN_CRIT "Eek! platform_cpu_die running on %u, should be %u\n",
+			   this_cpu, cpu);
+		BUG();
+	}
+#endif
+
+	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
+	complete(&cpu_killed);
+
+	/* directly enter low power state, skipping secure registers */
+	platform_do_lowpower(cpu);
+}
+
+int platform_cpu_disable(unsigned int cpu)
+{
+	/*
+	 * we don't allow CPU 0 to be shutdown (it is still too special
+	 * e.g. clock tick interrupts)
+	 */
+	return cpu == 0 ? -EPERM : 0;
+}
diff --git a/arch/arm/mach-ux500/include/mach/db5500-regs.h b/arch/arm/mach-ux500/include/mach/db5500-regs.h
index 545c80f..3eafc0e 100644
--- a/arch/arm/mach-ux500/include/mach/db5500-regs.h
+++ b/arch/arm/mach-ux500/include/mach/db5500-regs.h
@@ -100,4 +100,18 @@
 #define U5500_GPIOBANK6_BASE	(U5500_GPIO4_BASE + 0x80)
 #define U5500_GPIOBANK7_BASE	(U5500_GPIO4_BASE + 0x100)
 
+#define U5500_MBOX_BASE		(U5500_MODEM_BASE + 0xFFD1000)
+#define U5500_MBOX0_PEER_START	(U5500_MBOX_BASE + 0x40)
+#define U5500_MBOX0_PEER_END	(U5500_MBOX_BASE + 0x5F)
+#define U5500_MBOX0_LOCAL_START	(U5500_MBOX_BASE + 0x60)
+#define U5500_MBOX0_LOCAL_END	(U5500_MBOX_BASE + 0x7F)
+#define U5500_MBOX1_PEER_START	(U5500_MBOX_BASE + 0x80)
+#define U5500_MBOX1_PEER_END	(U5500_MBOX_BASE + 0x9F)
+#define U5500_MBOX1_LOCAL_START	(U5500_MBOX_BASE + 0xA0)
+#define U5500_MBOX1_LOCAL_END	(U5500_MBOX_BASE + 0xBF)
+#define U5500_MBOX2_PEER_START	(U5500_MBOX_BASE + 0x00)
+#define U5500_MBOX2_PEER_END	(U5500_MBOX_BASE + 0x1F)
+#define U5500_MBOX2_LOCAL_START	(U5500_MBOX_BASE + 0x20)
+#define U5500_MBOX2_LOCAL_END	(U5500_MBOX_BASE + 0x3F)
+
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/db8500-regs.h b/arch/arm/mach-ux500/include/mach/db8500-regs.h
index f000218..f07d098 100644
--- a/arch/arm/mach-ux500/include/mach/db8500-regs.h
+++ b/arch/arm/mach-ux500/include/mach/db8500-regs.h
@@ -30,8 +30,6 @@
 #define U8500_ICN_BASE		0x81000000
 
 #define U8500_BOOT_ROM_BASE	0x90000000
-/* ASIC ID is at 0xff4 offset within this region */
-#define U8500_ASIC_ID_BASE	0x9001F000
 
 #define U8500_PER6_BASE		0xa03c0000
 #define U8500_PER5_BASE		0xa03e0000
diff --git a/arch/arm/mach-ux500/include/mach/debug-macro.S b/arch/arm/mach-ux500/include/mach/debug-macro.S
index c5203b7..be7c0f1 100644
--- a/arch/arm/mach-ux500/include/mach/debug-macro.S
+++ b/arch/arm/mach-ux500/include/mach/debug-macro.S
@@ -18,11 +18,9 @@
 #define UX500_UART(n)	__UX500_UART(n)
 #define UART_BASE	UX500_UART(CONFIG_UX500_DEBUG_UART)
 
-	.macro	addruart, rx, tmp
-	mrc	p15, 0, \rx, c1, c0
-	tst	\rx, #1					@ MMU enabled?
-	ldreq	\rx, =UART_BASE				@ no, physical address
-	ldrne	\rx, =IO_ADDRESS(UART_BASE)		@ yes, virtual address
+	.macro	addruart, rp, rv
+	ldr	\rp, =UART_BASE				@ no, physical address
+	ldr	\rv, =IO_ADDRESS(UART_BASE)		@ yes, virtual address
 	.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-ux500/include/mach/devices.h b/arch/arm/mach-ux500/include/mach/devices.h
index c2b2f25..33a120c 100644
--- a/arch/arm/mach-ux500/include/mach/devices.h
+++ b/arch/arm/mach-ux500/include/mach/devices.h
@@ -27,6 +27,13 @@
 extern struct platform_device u8500_i2c4_device;
 extern struct platform_device u8500_dma40_device;
 
+extern struct amba_device u8500_sdi0_device;
+extern struct amba_device u8500_sdi1_device;
+extern struct amba_device u8500_sdi2_device;
+extern struct amba_device u8500_sdi3_device;
+extern struct amba_device u8500_sdi4_device;
+extern struct amba_device u8500_sdi5_device;
+
 void dma40_u8500ed_fixup(void);
 
 #endif
diff --git a/arch/arm/mach-ux500/include/mach/hardware.h b/arch/arm/mach-ux500/include/mach/hardware.h
index 8656379..32e883a 100644
--- a/arch/arm/mach-ux500/include/mach/hardware.h
+++ b/arch/arm/mach-ux500/include/mach/hardware.h
@@ -104,16 +104,35 @@
 #endif
 }
 
+#define CPUID_DB8500ED	0x410fc090
+#define CPUID_DB8500V1	0x411fc091
+#define CPUID_DB8500V2	0x412fc091
+
 static inline bool cpu_is_u8500ed(void)
 {
-	return cpu_is_u8500() && (read_cpuid_id() & 15) == 0;
+	return cpu_is_u8500() && (read_cpuid_id() == CPUID_DB8500ED);
 }
 
 static inline bool cpu_is_u8500v1(void)
 {
-	return cpu_is_u8500() && (read_cpuid_id() & 15) == 1;
+	return cpu_is_u8500() && (read_cpuid_id() == CPUID_DB8500V1);
 }
 
+static inline bool cpu_is_u8500v2(void)
+{
+	return cpu_is_u8500() && (read_cpuid_id() == CPUID_DB8500V2);
+}
+
+#ifdef CONFIG_UX500_SOC_DB8500
+bool cpu_is_u8500v10(void);
+bool cpu_is_u8500v11(void);
+bool cpu_is_u8500v20(void);
+#else
+static inline bool cpu_is_u8500v10(void) { return false; }
+static inline bool cpu_is_u8500v11(void) { return false; }
+static inline bool cpu_is_u8500v20(void) { return false; }
+#endif
+
 static inline bool cpu_is_u5500(void)
 {
 #ifdef CONFIG_UX500_SOC_DB5500
diff --git a/arch/arm/mach-ux500/include/mach/irqs-db5500.h b/arch/arm/mach-ux500/include/mach/irqs-db5500.h
index 6fbfe5e..bfa123d 100644
--- a/arch/arm/mach-ux500/include/mach/irqs-db5500.h
+++ b/arch/arm/mach-ux500/include/mach/irqs-db5500.h
@@ -61,6 +61,7 @@
 #define IRQ_DB5500_SDMMC0		(IRQ_SHPI_START + 60)
 #define IRQ_DB5500_HSEM			(IRQ_SHPI_START + 61)
 #define IRQ_DB5500_SBAG			(IRQ_SHPI_START + 63)
+#define IRQ_DB5500_MODEM		(IRQ_SHPI_START + 65)
 #define IRQ_DB5500_SPI1			(IRQ_SHPI_START + 96)
 #define IRQ_DB5500_MSP2			(IRQ_SHPI_START + 98)
 #define IRQ_DB5500_SRPTIMER		(IRQ_SHPI_START + 101)
diff --git a/arch/arm/mach-ux500/include/mach/irqs.h b/arch/arm/mach-ux500/include/mach/irqs.h
index 10385bd..693aa57 100644
--- a/arch/arm/mach-ux500/include/mach/irqs.h
+++ b/arch/arm/mach-ux500/include/mach/irqs.h
@@ -40,7 +40,8 @@
 #define IRQ_HSIR_CH1_OVRRUN	(IRQ_SHPI_START + 33)
 #define IRQ_HSIR_CH2_OVRRUN	(IRQ_SHPI_START + 34)
 #define IRQ_HSIR_CH3_OVRRUN	(IRQ_SHPI_START + 35)
-#define IRQ_AB4500		(IRQ_SHPI_START + 40)
+#define IRQ_AB8500		(IRQ_SHPI_START + 40)
+#define IRQ_PRCMU               (IRQ_SHPI_START + 47)
 #define IRQ_DISP		(IRQ_SHPI_START + 48)
 #define IRQ_SiPI3		(IRQ_SHPI_START + 49)
 #define IRQ_I2C4		(IRQ_SHPI_START + 51)
@@ -83,6 +84,19 @@
 #include <mach/irqs-board-mop500.h>
 #endif
 
-#define NR_IRQS				IRQ_BOARD_END
+/*
+ * After the board specific IRQ:s we reserve a range of IRQ:s in which virtual
+ * IRQ:s representing modem IRQ:s can be allocated
+ */
+#define IRQ_MODEM_EVENTS_BASE (IRQ_BOARD_END + 1)
+#define IRQ_MODEM_EVENTS_NBR 72
+#define IRQ_MODEM_EVENTS_END (IRQ_MODEM_EVENTS_BASE + IRQ_MODEM_EVENTS_NBR)
+
+/* List of virtual IRQ:s that are allocated from the range above */
+#define MBOX_PAIR0_VIRT_IRQ (IRQ_MODEM_EVENTS_BASE + 43)
+#define MBOX_PAIR1_VIRT_IRQ (IRQ_MODEM_EVENTS_BASE + 45)
+#define MBOX_PAIR2_VIRT_IRQ (IRQ_MODEM_EVENTS_BASE + 41)
+
+#define NR_IRQS				IRQ_MODEM_EVENTS_END
 
 #endif /* ASM_ARCH_IRQS_H */
diff --git a/arch/arm/mach-ux500/include/mach/mbox.h b/arch/arm/mach-ux500/include/mach/mbox.h
new file mode 100644
index 0000000..7f9da4d
--- /dev/null
+++ b/arch/arm/mach-ux500/include/mach/mbox.h
@@ -0,0 +1,88 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ * Author: Stefan Nilsson <stefan.xk.nilsson@stericsson.com> for ST-Ericsson.
+ * Author: Martin Persson <martin.persson@stericsson.com> for ST-Ericsson.
+ * License terms: GNU General Public License (GPL), version 2.
+ */
+
+#ifndef __INC_STE_MBOX_H
+#define __INC_STE_MBOX_H
+
+#define MBOX_BUF_SIZE 16
+#define MBOX_NAME_SIZE 8
+
+/**
+  * mbox_recv_cb_t - Definition of the mailbox callback.
+  * @mbox_msg:	The mailbox message.
+  * @priv:	The clients private data as specified in the call to mbox_setup.
+  *
+  * This function will be called upon reception of new mailbox messages.
+  */
+typedef void mbox_recv_cb_t (u32 mbox_msg, void *priv);
+
+/**
+  * struct mbox - Mailbox instance struct
+  * @list:		Linked list head.
+  * @pdev:		Pointer to device struct.
+  * @cb:		Callback function. Will be called
+  *			when new data is received.
+  * @client_data:	Clients private data. Will be sent back
+  *			in the callback function.
+  * @virtbase_peer:	Virtual address for outgoing mailbox.
+  * @virtbase_local:	Virtual address for incoming mailbox.
+  * @buffer:		Then internal queue for outgoing messages.
+  * @name:		Name of this mailbox.
+  * @buffer_available:	Completion variable to achieve "blocking send".
+  *			This variable will be signaled when there is
+  *			internal buffer space available.
+  * @client_blocked:	To keep track if any client is currently
+  *			blocked.
+  * @lock:		Spinlock to protect this mailbox instance.
+  * @write_index:	Index in internal buffer to write to.
+  * @read_index:	Index in internal buffer to read from.
+  * @allocated:		Indicates whether this particular mailbox
+  *			id has been allocated by someone.
+  */
+struct mbox {
+	struct list_head list;
+	struct platform_device *pdev;
+	mbox_recv_cb_t *cb;
+	void *client_data;
+	void __iomem *virtbase_peer;
+	void __iomem *virtbase_local;
+	u32 buffer[MBOX_BUF_SIZE];
+	char name[MBOX_NAME_SIZE];
+	struct completion buffer_available;
+	u8 client_blocked;
+	spinlock_t lock;
+	u8 write_index;
+	u8 read_index;
+	bool allocated;
+};
+
+/**
+  * mbox_setup - Set up a mailbox and return its instance.
+  * @mbox_id:	The ID number of the mailbox. 0 or 1 for modem CPU,
+  *		2 for modem DSP.
+  * @mbox_cb:	Pointer to the callback function to be called when a new message
+  *		is received.
+  * @priv:	Client user data which will be returned in the callback.
+  *
+  * Returns a mailbox instance to be specified in subsequent calls to mbox_send.
+  */
+struct mbox *mbox_setup(u8 mbox_id, mbox_recv_cb_t *mbox_cb, void *priv);
+
+/**
+  * mbox_send - Send a mailbox message.
+  * @mbox:	Mailbox instance (returned by mbox_setup)
+  * @mbox_msg:	The mailbox message to send.
+  * @block:	Specifies whether this call will block until send is possible,
+  *		or return an error if the mailbox buffer is full.
+  *
+  * Returns 0 on success or a negative error code on error. -ENOMEM indicates
+  * that the internal buffer is full and you have to try again later (or
+  * specify "block" in order to block until send is possible).
+  */
+int mbox_send(struct mbox *mbox, u32 mbox_msg, bool block);
+
+#endif /*INC_STE_MBOX_H*/
diff --git a/arch/arm/mach-ux500/include/mach/prcmu-regs.h b/arch/arm/mach-ux500/include/mach/prcmu-regs.h
new file mode 100644
index 0000000..8885f39
--- /dev/null
+++ b/arch/arm/mach-ux500/include/mach/prcmu-regs.h
@@ -0,0 +1,91 @@
+/*
+ * Copyright (c) 2009 ST-Ericsson SA
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ */
+#ifndef __MACH_PRCMU_REGS_H
+#define __MACH_PRCMU_REGS_H
+
+#include <mach/hardware.h>
+
+#define _PRCMU_BASE		IO_ADDRESS(U8500_PRCMU_BASE)
+
+#define PRCM_ARM_PLLDIVPS	(_PRCMU_BASE + 0x118)
+#define PRCM_ARM_CHGCLKREQ	(_PRCMU_BASE + 0x114)
+#define PRCM_PLLARM_ENABLE	(_PRCMU_BASE + 0x98)
+#define PRCM_ARMCLKFIX_MGT	(_PRCMU_BASE + 0x0)
+#define PRCM_A9_RESETN_CLR	(_PRCMU_BASE + 0x1f4)
+#define PRCM_A9_RESETN_SET	(_PRCMU_BASE + 0x1f0)
+#define PRCM_ARM_LS_CLAMP	(_PRCMU_BASE + 0x30c)
+#define PRCM_SRAM_A9		(_PRCMU_BASE + 0x308)
+
+/* ARM WFI Standby signal register */
+#define PRCM_ARM_WFI_STANDBY    (_PRCMU_BASE + 0x130)
+#define PRCMU_IOCR              (_PRCMU_BASE + 0x310)
+
+/* CPU mailbox registers */
+#define PRCM_MBOX_CPU_VAL	(_PRCMU_BASE + 0x0fc)
+#define PRCM_MBOX_CPU_SET	(_PRCMU_BASE + 0x100)
+#define PRCM_MBOX_CPU_CLR	(_PRCMU_BASE + 0x104)
+
+/* Dual A9 core interrupt management unit registers */
+#define PRCM_A9_MASK_REQ	(_PRCMU_BASE + 0x328)
+#define PRCM_A9_MASK_ACK	(_PRCMU_BASE + 0x32c)
+#define PRCM_ARMITMSK31TO0	(_PRCMU_BASE + 0x11c)
+#define PRCM_ARMITMSK63TO32	(_PRCMU_BASE + 0x120)
+#define PRCM_ARMITMSK95TO64	(_PRCMU_BASE + 0x124)
+#define PRCM_ARMITMSK127TO96	(_PRCMU_BASE + 0x128)
+#define PRCM_POWER_STATE_VAL	(_PRCMU_BASE + 0x25C)
+#define PRCM_ARMITVAL31TO0	(_PRCMU_BASE + 0x260)
+#define PRCM_ARMITVAL63TO32	(_PRCMU_BASE + 0x264)
+#define PRCM_ARMITVAL95TO64	(_PRCMU_BASE + 0x268)
+#define PRCM_ARMITVAL127TO96	(_PRCMU_BASE + 0x26C)
+
+#define PRCM_HOSTACCESS_REQ	(_PRCMU_BASE + 0x334)
+#define ARM_WAKEUP_MODEM	0x1
+
+#define PRCM_ARM_IT1_CLEAR	(_PRCMU_BASE + 0x48C)
+#define PRCM_ARM_IT1_VAL	(_PRCMU_BASE + 0x494)
+#define PRCM_HOLD_EVT		(_PRCMU_BASE + 0x174)
+
+#define PRCM_ITSTATUS0		(_PRCMU_BASE + 0x148)
+#define PRCM_ITSTATUS1		(_PRCMU_BASE + 0x150)
+#define PRCM_ITSTATUS2		(_PRCMU_BASE + 0x158)
+#define PRCM_ITSTATUS3		(_PRCMU_BASE + 0x160)
+#define PRCM_ITSTATUS4		(_PRCMU_BASE + 0x168)
+#define PRCM_ITSTATUS5		(_PRCMU_BASE + 0x484)
+#define PRCM_ITCLEAR5		(_PRCMU_BASE + 0x488)
+#define PRCM_ARMIT_MASKXP70_IT	(_PRCMU_BASE + 0x1018)
+
+/* System reset register */
+#define PRCM_APE_SOFTRST	(_PRCMU_BASE + 0x228)
+
+/* Level shifter and clamp control registers */
+#define PRCM_MMIP_LS_CLAMP_SET     (_PRCMU_BASE + 0x420)
+#define PRCM_MMIP_LS_CLAMP_CLR     (_PRCMU_BASE + 0x424)
+
+/* PRCMU clock/PLL/reset registers */
+#define PRCM_PLLDSI_FREQ           (_PRCMU_BASE + 0x500)
+#define PRCM_PLLDSI_ENABLE         (_PRCMU_BASE + 0x504)
+#define PRCM_LCDCLK_MGT            (_PRCMU_BASE + 0x044)
+#define PRCM_MCDECLK_MGT           (_PRCMU_BASE + 0x064)
+#define PRCM_HDMICLK_MGT           (_PRCMU_BASE + 0x058)
+#define PRCM_TVCLK_MGT             (_PRCMU_BASE + 0x07c)
+#define PRCM_DSI_PLLOUT_SEL        (_PRCMU_BASE + 0x530)
+#define PRCM_DSITVCLK_DIV          (_PRCMU_BASE + 0x52C)
+#define PRCM_APE_RESETN_SET        (_PRCMU_BASE + 0x1E4)
+#define PRCM_APE_RESETN_CLR        (_PRCMU_BASE + 0x1E8)
+
+/* ePOD and memory power signal control registers */
+#define PRCM_EPOD_C_SET            (_PRCMU_BASE + 0x410)
+#define PRCM_SRAM_LS_SLEEP         (_PRCMU_BASE + 0x304)
+
+/* Debug power control unit registers */
+#define PRCM_POWER_STATE_SET       (_PRCMU_BASE + 0x254)
+
+/* Miscellaneous unit registers */
+#define PRCM_DSI_SW_RESET          (_PRCMU_BASE + 0x324)
+
+#endif /* __MACH_PRCMU__REGS_H */
diff --git a/arch/arm/mach-ux500/include/mach/prcmu.h b/arch/arm/mach-ux500/include/mach/prcmu.h
new file mode 100644
index 0000000..549843f
--- /dev/null
+++ b/arch/arm/mach-ux500/include/mach/prcmu.h
@@ -0,0 +1,15 @@
+/*
+ * Copyright (C) STMicroelectronics 2009
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ *
+ * PRCMU f/w APIs
+ */
+#ifndef __MACH_PRCMU_H
+#define __MACH_PRCMU_H
+
+int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
+int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size);
+
+#endif /* __MACH_PRCMU_H */
diff --git a/arch/arm/mach-ux500/include/mach/setup.h b/arch/arm/mach-ux500/include/mach/setup.h
index e978dbd..54bbe64 100644
--- a/arch/arm/mach-ux500/include/mach/setup.h
+++ b/arch/arm/mach-ux500/include/mach/setup.h
@@ -38,4 +38,11 @@
 	.type		= MT_DEVICE,		\
 }
 
+#define __MEM_DEV_DESC(x, sz)	{		\
+	.virtual	= IO_ADDRESS(x),	\
+	.pfn		= __phys_to_pfn(x),	\
+	.length		= sz,			\
+	.type		= MT_MEMORY,		\
+}
+
 #endif /*  __ASM_ARCH_SETUP_H */
diff --git a/arch/arm/mach-ux500/include/mach/smp.h b/arch/arm/mach-ux500/include/mach/smp.h
index b59f7bc..197e841 100644
--- a/arch/arm/mach-ux500/include/mach/smp.h
+++ b/arch/arm/mach-ux500/include/mach/smp.h
@@ -10,18 +10,11 @@
 #define ASMARM_ARCH_SMP_H
 
 #include <asm/hardware/gic.h>
+#include <asm/smp_mpidr.h>
 
 /* This is required to wakeup the secondary core */
 extern void u8500_secondary_startup(void);
 
-#define hard_smp_processor_id()				\
-	({						\
-		unsigned int cpunum;			\
-		__asm__("mrc p15, 0, %0, c0, c0, 5"	\
-			: "=r" (cpunum));		\
-		cpunum &= 0x0F;				\
-	})
-
 /*
  * We use IRQ1 as the IPI
  */
diff --git a/arch/arm/mach-ux500/mbox.c b/arch/arm/mach-ux500/mbox.c
new file mode 100644
index 0000000..6343538
--- /dev/null
+++ b/arch/arm/mach-ux500/mbox.c
@@ -0,0 +1,567 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ * Author: Stefan Nilsson <stefan.xk.nilsson@stericsson.com> for ST-Ericsson.
+ * Author: Martin Persson <martin.persson@stericsson.com> for ST-Ericsson.
+ * License terms: GNU General Public License (GPL), version 2.
+ */
+
+/*
+ * Mailbox nomenclature:
+ *
+ *       APE           MODEM
+ *           mbox pairX
+ *   ..........................
+ *   .                       .
+ *   .           peer        .
+ *   .     send  ----        .
+ *   .      -->  |  |        .
+ *   .           |  |        .
+ *   .           ----        .
+ *   .                       .
+ *   .           local       .
+ *   .     rec   ----        .
+ *   .           |  | <--    .
+ *   .           |  |        .
+ *   .           ----        .
+ *   .........................
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/platform_device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/completion.h>
+#include <mach/mbox.h>
+
+#define MBOX_NAME "mbox"
+
+#define MBOX_FIFO_DATA        0x000
+#define MBOX_FIFO_ADD         0x004
+#define MBOX_FIFO_REMOVE      0x008
+#define MBOX_FIFO_THRES_FREE  0x00C
+#define MBOX_FIFO_THRES_OCCUP 0x010
+#define MBOX_FIFO_STATUS      0x014
+
+#define MBOX_DISABLE_IRQ 0x4
+#define MBOX_ENABLE_IRQ  0x0
+#define MBOX_LATCH 1
+
+/* Global list of all mailboxes */
+static struct list_head mboxs = LIST_HEAD_INIT(mboxs);
+
+static struct mbox *get_mbox_with_id(u8 id)
+{
+	u8 i;
+	struct list_head *pos = &mboxs;
+	for (i = 0; i <= id; i++)
+		pos = pos->next;
+
+	return (struct mbox *) list_entry(pos, struct mbox, list);
+}
+
+int mbox_send(struct mbox *mbox, u32 mbox_msg, bool block)
+{
+	int res = 0;
+
+	spin_lock(&mbox->lock);
+
+	dev_dbg(&(mbox->pdev->dev),
+		"About to buffer 0x%X to mailbox 0x%X."
+		" ri = %d, wi = %d\n",
+		mbox_msg, (u32)mbox, mbox->read_index,
+		mbox->write_index);
+
+	/* Check if write buffer is full */
+	while (((mbox->write_index + 1) % MBOX_BUF_SIZE) == mbox->read_index) {
+		if (!block) {
+			dev_dbg(&(mbox->pdev->dev),
+			"Buffer full in non-blocking call! "
+			"Returning -ENOMEM!\n");
+			res = -ENOMEM;
+			goto exit;
+		}
+		spin_unlock(&mbox->lock);
+		dev_dbg(&(mbox->pdev->dev),
+			"Buffer full in blocking call! Sleeping...\n");
+		mbox->client_blocked = 1;
+		wait_for_completion(&mbox->buffer_available);
+		dev_dbg(&(mbox->pdev->dev),
+			"Blocking send was woken up! Trying again...\n");
+		spin_lock(&mbox->lock);
+	}
+
+	mbox->buffer[mbox->write_index] = mbox_msg;
+	mbox->write_index = (mbox->write_index + 1) % MBOX_BUF_SIZE;
+
+	/*
+	 * Indicate that we want an IRQ as soon as there is a slot
+	 * in the FIFO
+	 */
+	writel(MBOX_ENABLE_IRQ, mbox->virtbase_peer + MBOX_FIFO_THRES_FREE);
+
+exit:
+	spin_unlock(&mbox->lock);
+	return res;
+}
+EXPORT_SYMBOL(mbox_send);
+
+#if defined(CONFIG_DEBUG_FS)
+/*
+ * Expected input: <value> <nbr sends>
+ * Example: "echo 0xdeadbeef 4 > mbox-node" sends 0xdeadbeef 4 times
+ */
+static ssize_t mbox_write_fifo(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf,
+			       size_t count)
+{
+	unsigned long mbox_mess;
+	unsigned long nbr_sends;
+	unsigned long i;
+	char int_buf[16];
+	char *token;
+	char *val;
+
+	struct mbox *mbox = (struct mbox *) dev->platform_data;
+
+	strncpy((char *) &int_buf, buf, sizeof(int_buf));
+	token = (char *) &int_buf;
+
+	/* Parse message */
+	val = strsep(&token, " ");
+	if ((val == NULL) || (strict_strtoul(val, 16, &mbox_mess) != 0))
+		mbox_mess = 0xDEADBEEF;
+
+	val = strsep(&token, " ");
+	if ((val == NULL) || (strict_strtoul(val, 10, &nbr_sends) != 0))
+		nbr_sends = 1;
+
+	dev_dbg(dev, "Will write 0x%lX %ld times using data struct at 0x%X\n",
+		mbox_mess, nbr_sends, (u32) mbox);
+
+	for (i = 0; i < nbr_sends; i++)
+		mbox_send(mbox, mbox_mess, true);
+
+	return count;
+}
+
+static ssize_t mbox_read_fifo(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	int mbox_value;
+	struct mbox *mbox = (struct mbox *) dev->platform_data;
+
+	if ((readl(mbox->virtbase_local + MBOX_FIFO_STATUS) & 0x7) <= 0)
+		return sprintf(buf, "Mailbox is empty\n");
+
+	mbox_value = readl(mbox->virtbase_local + MBOX_FIFO_DATA);
+	writel(MBOX_LATCH, (mbox->virtbase_local + MBOX_FIFO_REMOVE));
+
+	return sprintf(buf, "0x%X\n", mbox_value);
+}
+
+static DEVICE_ATTR(fifo, S_IWUGO | S_IRUGO, mbox_read_fifo, mbox_write_fifo);
+
+static int mbox_show(struct seq_file *s, void *data)
+{
+	struct list_head *pos;
+	u8 mbox_index = 0;
+
+	list_for_each(pos, &mboxs) {
+		struct mbox *m =
+			(struct mbox *) list_entry(pos, struct mbox, list);
+		if (m == NULL) {
+			seq_printf(s,
+				   "Unable to retrieve mailbox %d\n",
+				   mbox_index);
+			continue;
+		}
+
+		spin_lock(&m->lock);
+		if ((m->virtbase_peer == NULL) || (m->virtbase_local == NULL)) {
+			seq_printf(s, "MAILBOX %d not setup or corrupt\n",
+				   mbox_index);
+			spin_unlock(&m->lock);
+			continue;
+		}
+
+		seq_printf(s,
+		"===========================\n"
+		" MAILBOX %d\n"
+		" PEER MAILBOX DUMP\n"
+		"---------------------------\n"
+		"FIFO:                 0x%X (%d)\n"
+		"Free     Threshold:   0x%.2X (%d)\n"
+		"Occupied Threshold:   0x%.2X (%d)\n"
+		"Status:               0x%.2X (%d)\n"
+		"   Free spaces  (ot):    %d (%d)\n"
+		"   Occup spaces (ot):    %d (%d)\n"
+		"===========================\n"
+		" LOCAL MAILBOX DUMP\n"
+		"---------------------------\n"
+		"FIFO:                 0x%.X (%d)\n"
+		"Free     Threshold:   0x%.2X (%d)\n"
+		"Occupied Threshold:   0x%.2X (%d)\n"
+		"Status:               0x%.2X (%d)\n"
+		"   Free spaces  (ot):    %d (%d)\n"
+		"   Occup spaces (ot):    %d (%d)\n"
+		"===========================\n"
+		"write_index: %d\n"
+		"read_index : %d\n"
+		"===========================\n"
+		"\n",
+		mbox_index,
+		readl(m->virtbase_peer + MBOX_FIFO_DATA),
+		readl(m->virtbase_peer + MBOX_FIFO_DATA),
+		readl(m->virtbase_peer + MBOX_FIFO_THRES_FREE),
+		readl(m->virtbase_peer + MBOX_FIFO_THRES_FREE),
+		readl(m->virtbase_peer + MBOX_FIFO_THRES_OCCUP),
+		readl(m->virtbase_peer + MBOX_FIFO_THRES_OCCUP),
+		readl(m->virtbase_peer + MBOX_FIFO_STATUS),
+		readl(m->virtbase_peer + MBOX_FIFO_STATUS),
+		(readl(m->virtbase_peer + MBOX_FIFO_STATUS) >> 4) & 0x7,
+		(readl(m->virtbase_peer + MBOX_FIFO_STATUS) >> 7) & 0x1,
+		(readl(m->virtbase_peer + MBOX_FIFO_STATUS) >> 0) & 0x7,
+		(readl(m->virtbase_peer + MBOX_FIFO_STATUS) >> 3) & 0x1,
+		readl(m->virtbase_local + MBOX_FIFO_DATA),
+		readl(m->virtbase_local + MBOX_FIFO_DATA),
+		readl(m->virtbase_local + MBOX_FIFO_THRES_FREE),
+		readl(m->virtbase_local + MBOX_FIFO_THRES_FREE),
+		readl(m->virtbase_local + MBOX_FIFO_THRES_OCCUP),
+		readl(m->virtbase_local + MBOX_FIFO_THRES_OCCUP),
+		readl(m->virtbase_local + MBOX_FIFO_STATUS),
+		readl(m->virtbase_local + MBOX_FIFO_STATUS),
+		(readl(m->virtbase_local + MBOX_FIFO_STATUS) >> 4) & 0x7,
+		(readl(m->virtbase_local + MBOX_FIFO_STATUS) >> 7) & 0x1,
+		(readl(m->virtbase_local + MBOX_FIFO_STATUS) >> 0) & 0x7,
+		(readl(m->virtbase_local + MBOX_FIFO_STATUS) >> 3) & 0x1,
+		m->write_index, m->read_index);
+		mbox_index++;
+		spin_unlock(&m->lock);
+	}
+
+	return 0;
+}
+
+static int mbox_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mbox_show, NULL);
+}
+
+static const struct file_operations mbox_operations = {
+	.owner = THIS_MODULE,
+	.open = mbox_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+#endif
+
+static irqreturn_t mbox_irq(int irq, void *arg)
+{
+	u32 mbox_value;
+	int nbr_occup;
+	int nbr_free;
+	struct mbox *mbox = (struct mbox *) arg;
+
+	spin_lock(&mbox->lock);
+
+	dev_dbg(&(mbox->pdev->dev),
+		"mbox IRQ [%d] received. ri = %d, wi = %d\n",
+		irq, mbox->read_index, mbox->write_index);
+
+	/*
+	 * Check if we have any outgoing messages, and if there is space for
+	 * them in the FIFO.
+	 */
+	if (mbox->read_index != mbox->write_index) {
+		/*
+		 * Check by reading FREE for LOCAL since that indicates
+		 * OCCUP for PEER
+		 */
+		nbr_free = (readl(mbox->virtbase_local + MBOX_FIFO_STATUS)
+			    >> 4) & 0x7;
+		dev_dbg(&(mbox->pdev->dev),
+			"Status indicates %d empty spaces in the FIFO!\n",
+			nbr_free);
+
+		while ((nbr_free > 0) &&
+		       (mbox->read_index != mbox->write_index)) {
+			/* Write the message and latch it into the FIFO */
+			writel(mbox->buffer[mbox->read_index],
+			       (mbox->virtbase_peer + MBOX_FIFO_DATA));
+			writel(MBOX_LATCH,
+			       (mbox->virtbase_peer + MBOX_FIFO_ADD));
+			dev_dbg(&(mbox->pdev->dev),
+				"Wrote message 0x%X to addr 0x%X\n",
+				mbox->buffer[mbox->read_index],
+				(u32) (mbox->virtbase_peer + MBOX_FIFO_DATA));
+
+			nbr_free--;
+			mbox->read_index =
+				(mbox->read_index + 1) % MBOX_BUF_SIZE;
+		}
+
+		/*
+		 * Check if we still want IRQ:s when there is free
+		 * space to send
+		 */
+		if (mbox->read_index != mbox->write_index) {
+			dev_dbg(&(mbox->pdev->dev),
+				"Still have messages to send, but FIFO full. "
+				"Request IRQ again!\n");
+			writel(MBOX_ENABLE_IRQ,
+			       mbox->virtbase_peer + MBOX_FIFO_THRES_FREE);
+		} else {
+			dev_dbg(&(mbox->pdev->dev),
+				"No more messages to send. "
+				"Do not request IRQ again!\n");
+			writel(MBOX_DISABLE_IRQ,
+			       mbox->virtbase_peer + MBOX_FIFO_THRES_FREE);
+		}
+
+		/*
+		 * Check if we can signal any blocked clients that it is OK to
+		 * start buffering again
+		 */
+		if (mbox->client_blocked &&
+		    (((mbox->write_index + 1) % MBOX_BUF_SIZE)
+		     != mbox->read_index)) {
+			dev_dbg(&(mbox->pdev->dev),
+				"Waking up blocked client\n");
+			complete(&mbox->buffer_available);
+			mbox->client_blocked = 0;
+		}
+	}
+
+	/* Check if we have any incoming messages */
+	nbr_occup = readl(mbox->virtbase_local + MBOX_FIFO_STATUS) & 0x7;
+	if (nbr_occup == 0)
+		goto exit;
+
+	if (mbox->cb == NULL) {
+		dev_dbg(&(mbox->pdev->dev), "No receive callback registered, "
+			"leaving %d incoming messages in fifo!\n", nbr_occup);
+		goto exit;
+	}
+
+	/* Read and acknowledge the message */
+	mbox_value = readl(mbox->virtbase_local + MBOX_FIFO_DATA);
+	writel(MBOX_LATCH, (mbox->virtbase_local + MBOX_FIFO_REMOVE));
+
+	/* Notify consumer of new mailbox message */
+	dev_dbg(&(mbox->pdev->dev), "Calling callback for message 0x%X!\n",
+		mbox_value);
+	mbox->cb(mbox_value, mbox->client_data);
+
+exit:
+	dev_dbg(&(mbox->pdev->dev), "Exit mbox IRQ. ri = %d, wi = %d\n",
+		mbox->read_index, mbox->write_index);
+	spin_unlock(&mbox->lock);
+
+	return IRQ_HANDLED;
+}
+
+/* Setup is executed once for each mbox pair */
+struct mbox *mbox_setup(u8 mbox_id, mbox_recv_cb_t *mbox_cb, void *priv)
+{
+	struct resource *resource;
+	int irq;
+	int res;
+	struct mbox *mbox;
+
+	mbox = get_mbox_with_id(mbox_id);
+	if (mbox == NULL) {
+		dev_err(&(mbox->pdev->dev), "Incorrect mailbox id: %d!\n",
+			mbox_id);
+		goto exit;
+	}
+
+	/*
+	 * Check if mailbox has been allocated to someone else,
+	 * otherwise allocate it
+	 */
+	if (mbox->allocated) {
+		dev_err(&(mbox->pdev->dev), "Mailbox number %d is busy!\n",
+			mbox_id);
+		mbox = NULL;
+		goto exit;
+	}
+	mbox->allocated = true;
+
+	dev_dbg(&(mbox->pdev->dev), "Initiating mailbox number %d: 0x%X...\n",
+		mbox_id, (u32)mbox);
+
+	mbox->client_data = priv;
+	mbox->cb = mbox_cb;
+
+	/* Get addr for peer mailbox and ioremap it */
+	resource = platform_get_resource_byname(mbox->pdev,
+						IORESOURCE_MEM,
+						"mbox_peer");
+	if (resource == NULL) {
+		dev_err(&(mbox->pdev->dev),
+			"Unable to retrieve mbox peer resource\n");
+		mbox = NULL;
+		goto exit;
+	}
+	dev_dbg(&(mbox->pdev->dev),
+		"Resource name: %s start: 0x%X, end: 0x%X\n",
+		resource->name, resource->start, resource->end);
+	mbox->virtbase_peer =
+		ioremap(resource->start, resource->end - resource->start);
+	if (!mbox->virtbase_peer) {
+		dev_err(&(mbox->pdev->dev), "Unable to ioremap peer mbox\n");
+		mbox = NULL;
+		goto exit;
+	}
+	dev_dbg(&(mbox->pdev->dev),
+		"ioremapped peer physical: (0x%X-0x%X) to virtual: 0x%X\n",
+		resource->start, resource->end, (u32) mbox->virtbase_peer);
+
+	/* Get addr for local mailbox and ioremap it */
+	resource = platform_get_resource_byname(mbox->pdev,
+						IORESOURCE_MEM,
+						"mbox_local");
+	if (resource == NULL) {
+		dev_err(&(mbox->pdev->dev),
+			"Unable to retrieve mbox local resource\n");
+		mbox = NULL;
+		goto exit;
+	}
+	dev_dbg(&(mbox->pdev->dev),
+		"Resource name: %s start: 0x%X, end: 0x%X\n",
+		resource->name, resource->start, resource->end);
+	mbox->virtbase_local =
+		ioremap(resource->start, resource->end - resource->start);
+	if (!mbox->virtbase_local) {
+		dev_err(&(mbox->pdev->dev), "Unable to ioremap local mbox\n");
+		mbox = NULL;
+		goto exit;
+	}
+	dev_dbg(&(mbox->pdev->dev),
+		"ioremapped local physical: (0x%X-0x%X) to virtual: 0x%X\n",
+		resource->start, resource->end, (u32) mbox->virtbase_peer);
+
+	init_completion(&mbox->buffer_available);
+	mbox->client_blocked = 0;
+
+	/* Get IRQ for mailbox and allocate it */
+	irq = platform_get_irq_byname(mbox->pdev, "mbox_irq");
+	if (irq < 0) {
+		dev_err(&(mbox->pdev->dev),
+			"Unable to retrieve mbox irq resource\n");
+		mbox = NULL;
+		goto exit;
+	}
+
+	dev_dbg(&(mbox->pdev->dev), "Allocating irq %d...\n", irq);
+	res = request_irq(irq, mbox_irq, 0, mbox->name, (void *) mbox);
+	if (res < 0) {
+		dev_err(&(mbox->pdev->dev),
+			"Unable to allocate mbox irq %d\n", irq);
+		mbox = NULL;
+		goto exit;
+	}
+
+	/* Set up mailbox to not launch IRQ on free space in mailbox */
+	writel(MBOX_DISABLE_IRQ, mbox->virtbase_peer + MBOX_FIFO_THRES_FREE);
+
+	/*
+	 * Set up mailbox to launch IRQ on new message if we have
+	 * a callback set. If not, do not raise IRQ, but keep message
+	 * in FIFO for manual retrieval
+	 */
+	if (mbox_cb != NULL)
+		writel(MBOX_ENABLE_IRQ,
+		       mbox->virtbase_local + MBOX_FIFO_THRES_OCCUP);
+	else
+		writel(MBOX_DISABLE_IRQ,
+		       mbox->virtbase_local + MBOX_FIFO_THRES_OCCUP);
+
+#if defined(CONFIG_DEBUG_FS)
+	res = device_create_file(&(mbox->pdev->dev), &dev_attr_fifo);
+	if (res != 0)
+		dev_warn(&(mbox->pdev->dev),
+			 "Unable to create mbox sysfs entry");
+
+	(void) debugfs_create_file("mbox", S_IFREG | S_IRUGO, NULL,
+				   NULL, &mbox_operations);
+#endif
+
+	dev_info(&(mbox->pdev->dev),
+		 "Mailbox driver with index %d initated!\n", mbox_id);
+
+exit:
+	return mbox;
+}
+EXPORT_SYMBOL(mbox_setup);
+
+
+int __init mbox_probe(struct platform_device *pdev)
+{
+	struct mbox local_mbox;
+	struct mbox *mbox;
+	int res = 0;
+	dev_dbg(&(pdev->dev), "Probing mailbox (pdev = 0x%X)...\n", (u32) pdev);
+
+	memset(&local_mbox, 0x0, sizeof(struct mbox));
+
+	/* Associate our mbox data with the platform device */
+	res = platform_device_add_data(pdev,
+				       (void *) &local_mbox,
+				       sizeof(struct mbox));
+	if (res != 0) {
+		dev_err(&(pdev->dev),
+			"Unable to allocate driver platform data!\n");
+		goto exit;
+	}
+
+	mbox = (struct mbox *) pdev->dev.platform_data;
+	mbox->pdev = pdev;
+	mbox->write_index = 0;
+	mbox->read_index = 0;
+
+	INIT_LIST_HEAD(&(mbox->list));
+	list_add_tail(&(mbox->list), &mboxs);
+
+	sprintf(mbox->name, "%s", MBOX_NAME);
+	spin_lock_init(&mbox->lock);
+
+	dev_info(&(pdev->dev), "Mailbox driver loaded\n");
+
+exit:
+	return res;
+}
+
+static struct platform_driver mbox_driver = {
+	.driver = {
+		.name = MBOX_NAME,
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init mbox_init(void)
+{
+	return platform_driver_probe(&mbox_driver, mbox_probe);
+}
+
+module_init(mbox_init);
+
+void __exit mbox_exit(void)
+{
+	platform_driver_unregister(&mbox_driver);
+}
+
+module_exit(mbox_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MBOX driver");
diff --git a/arch/arm/mach-ux500/modem_irq.c b/arch/arm/mach-ux500/modem_irq.c
new file mode 100644
index 0000000..3187f88
--- /dev/null
+++ b/arch/arm/mach-ux500/modem_irq.c
@@ -0,0 +1,139 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ * Author: Stefan Nilsson <stefan.xk.nilsson@stericsson.com> for ST-Ericsson.
+ * Author: Martin Persson <martin.persson@stericsson.com> for ST-Ericsson.
+ * License terms: GNU General Public License (GPL), version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+
+#define MODEM_INTCON_BASE_ADDR 0xBFFD3000
+#define MODEM_INTCON_SIZE 0xFFF
+
+#define DEST_IRQ41_OFFSET 0x2A4
+#define DEST_IRQ43_OFFSET 0x2AC
+#define DEST_IRQ45_OFFSET 0x2B4
+
+#define PRIO_IRQ41_OFFSET 0x6A4
+#define PRIO_IRQ43_OFFSET 0x6AC
+#define PRIO_IRQ45_OFFSET 0x6B4
+
+#define ALLOW_IRQ_OFFSET 0x104
+
+#define MODEM_INTCON_CPU_NBR 0x1
+#define MODEM_INTCON_PRIO_HIGH 0x0
+
+#define MODEM_INTCON_ALLOW_IRQ41 0x0200
+#define MODEM_INTCON_ALLOW_IRQ43 0x0800
+#define MODEM_INTCON_ALLOW_IRQ45 0x2000
+
+#define MODEM_IRQ_REG_OFFSET 0x4
+
+struct modem_irq {
+	void __iomem *modem_intcon_base;
+};
+
+
+static void setup_modem_intcon(void __iomem *modem_intcon_base)
+{
+	/* IC_DESTINATION_BASE_ARRAY - Which CPU to receive the IRQ */
+	writel(MODEM_INTCON_CPU_NBR, modem_intcon_base + DEST_IRQ41_OFFSET);
+	writel(MODEM_INTCON_CPU_NBR, modem_intcon_base + DEST_IRQ43_OFFSET);
+	writel(MODEM_INTCON_CPU_NBR, modem_intcon_base + DEST_IRQ45_OFFSET);
+
+	/* IC_PRIORITY_BASE_ARRAY - IRQ priority in modem IRQ controller */
+	writel(MODEM_INTCON_PRIO_HIGH, modem_intcon_base + PRIO_IRQ41_OFFSET);
+	writel(MODEM_INTCON_PRIO_HIGH, modem_intcon_base + PRIO_IRQ43_OFFSET);
+	writel(MODEM_INTCON_PRIO_HIGH, modem_intcon_base + PRIO_IRQ45_OFFSET);
+
+	/* IC_ALLOW_ARRAY - IRQ enable */
+	writel(MODEM_INTCON_ALLOW_IRQ41 |
+		   MODEM_INTCON_ALLOW_IRQ43 |
+		   MODEM_INTCON_ALLOW_IRQ45,
+		   modem_intcon_base + ALLOW_IRQ_OFFSET);
+}
+
+static irqreturn_t modem_cpu_irq_handler(int irq, void *data)
+{
+	int real_irq;
+	int virt_irq;
+	struct modem_irq *mi = (struct modem_irq *)data;
+
+	/* Read modem side IRQ number from modem IRQ controller */
+	real_irq = readl(mi->modem_intcon_base + MODEM_IRQ_REG_OFFSET) & 0xFF;
+	virt_irq = IRQ_MODEM_EVENTS_BASE + real_irq;
+
+	pr_debug("modem_irq: Worker read addr 0x%X and got value 0x%X "
+		 "which will be 0x%X (%d) which translates to "
+		 "virtual IRQ 0x%X (%d)!\n",
+		   (u32)mi->modem_intcon_base + MODEM_IRQ_REG_OFFSET,
+		   real_irq,
+		   real_irq & 0xFF,
+		   real_irq & 0xFF,
+		   virt_irq,
+		   virt_irq);
+
+	if (virt_irq != 0)
+		generic_handle_irq(virt_irq);
+
+	pr_debug("modem_irq: Done handling virtual IRQ %d!\n", virt_irq);
+
+	return IRQ_HANDLED;
+}
+
+static void create_virtual_irq(int irq, struct irq_chip *modem_irq_chip)
+{
+	set_irq_chip(irq, modem_irq_chip);
+	set_irq_handler(irq, handle_simple_irq);
+	set_irq_flags(irq, IRQF_VALID);
+
+	pr_debug("modem_irq: Created virtual IRQ %d\n", irq);
+}
+
+static int modem_irq_init(void)
+{
+	int err;
+	static struct irq_chip  modem_irq_chip;
+	struct modem_irq *mi;
+
+	pr_info("modem_irq: Set up IRQ handler for incoming modem IRQ %d\n",
+		   IRQ_DB5500_MODEM);
+
+	mi = kmalloc(sizeof(struct modem_irq), GFP_KERNEL);
+	if (!mi) {
+		pr_err("modem_irq: Could not allocate device\n");
+		return -ENOMEM;
+	}
+
+	mi->modem_intcon_base =
+		ioremap(MODEM_INTCON_BASE_ADDR, MODEM_INTCON_SIZE);
+	pr_debug("modem_irq: ioremapped modem_intcon_base from "
+		 "phy 0x%x to virt 0x%x\n", MODEM_INTCON_BASE_ADDR,
+		 (u32)mi->modem_intcon_base);
+
+	setup_modem_intcon(mi->modem_intcon_base);
+
+	modem_irq_chip = dummy_irq_chip;
+	modem_irq_chip.name = "modem_irq";
+
+	/* Create the virtual IRQ:s needed */
+	create_virtual_irq(MBOX_PAIR0_VIRT_IRQ, &modem_irq_chip);
+	create_virtual_irq(MBOX_PAIR1_VIRT_IRQ, &modem_irq_chip);
+	create_virtual_irq(MBOX_PAIR2_VIRT_IRQ, &modem_irq_chip);
+
+	err = request_threaded_irq(IRQ_DB5500_MODEM, NULL,
+				   modem_cpu_irq_handler, IRQF_ONESHOT,
+				   "modem_irq", mi);
+	if (err)
+		pr_err("modem_irq: Could not register IRQ %d\n",
+		       IRQ_DB5500_MODEM);
+
+	return 0;
+}
+
+arch_initcall(modem_irq_init);
diff --git a/arch/arm/mach-ux500/pins-db5500.h b/arch/arm/mach-ux500/pins-db5500.h
new file mode 100644
index 0000000..bf50c21
--- /dev/null
+++ b/arch/arm/mach-ux500/pins-db5500.h
@@ -0,0 +1,620 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * License terms: GNU General Public License, version 2
+ * Author: Rabin Vincent <rabin.vincent@stericsson.com>
+ */
+
+#ifndef __MACH_DB5500_PINS_H
+#define __MACH_DB5500_PINS_H
+
+#define GPIO0_GPIO		PIN_CFG(0, GPIO)
+#define GPIO0_SM_CS3n		PIN_CFG(0, ALT_A)
+
+#define GPIO1_GPIO		PIN_CFG(1, GPIO)
+#define GPIO1_SM_A3		PIN_CFG(1, ALT_A)
+
+#define GPIO2_GPIO		PIN_CFG(2, GPIO)
+#define GPIO2_SM_A4		PIN_CFG(2, ALT_A)
+#define GPIO2_SM_AVD		PIN_CFG(2, ALT_B)
+
+#define GPIO3_GPIO		PIN_CFG(3, GPIO)
+#define GPIO3_I2C1_SCL		PIN_CFG(3, ALT_A)
+
+#define GPIO4_GPIO		PIN_CFG(4, GPIO)
+#define GPIO4_I2C1_SDA		PIN_CFG(4, ALT_A)
+
+#define GPIO5_GPIO		PIN_CFG(5, GPIO)
+#define GPIO5_MC0_DAT0		PIN_CFG(5, ALT_A)
+#define GPIO5_SM_ADQ8		PIN_CFG(5, ALT_B)
+
+#define GPIO6_GPIO		PIN_CFG(6, GPIO)
+#define GPIO6_MC0_DAT1		PIN_CFG(6, ALT_A)
+#define GPIO6_SM_ADQ0		PIN_CFG(6, ALT_B)
+
+#define GPIO7_GPIO		PIN_CFG(7, GPIO)
+#define GPIO7_MC0_DAT2		PIN_CFG(7, ALT_A)
+#define GPIO7_SM_ADQ9		PIN_CFG(7, ALT_B)
+
+#define GPIO8_GPIO		PIN_CFG(8, GPIO)
+#define GPIO8_MC0_DAT3		PIN_CFG(8, ALT_A)
+#define GPIO8_SM_ADQ1		PIN_CFG(8, ALT_B)
+
+#define GPIO9_GPIO		PIN_CFG(9, GPIO)
+#define GPIO9_MC0_DAT4		PIN_CFG(9, ALT_A)
+#define GPIO9_SM_ADQ10		PIN_CFG(9, ALT_B)
+
+#define GPIO10_GPIO		PIN_CFG(10, GPIO)
+#define GPIO10_MC0_DAT5		PIN_CFG(10, ALT_A)
+#define GPIO10_SM_ADQ2		PIN_CFG(10, ALT_B)
+
+#define GPIO11_GPIO		PIN_CFG(11, GPIO)
+#define GPIO11_MC0_DAT6		PIN_CFG(11, ALT_A)
+#define GPIO11_SM_ADQ11		PIN_CFG(11, ALT_B)
+
+#define GPIO12_GPIO		PIN_CFG(12, GPIO)
+#define GPIO12_MC0_DAT7		PIN_CFG(12, ALT_A)
+#define GPIO12_SM_ADQ3		PIN_CFG(12, ALT_B)
+
+#define GPIO13_GPIO		PIN_CFG(13, GPIO)
+#define GPIO13_MC0_CMD		PIN_CFG(13, ALT_A)
+#define GPIO13_SM_BUSY0n	PIN_CFG(13, ALT_B)
+#define GPIO13_SM_WAIT0n	PIN_CFG(13, ALT_C)
+
+#define GPIO14_GPIO		PIN_CFG(14, GPIO)
+#define GPIO14_MC0_CLK		PIN_CFG(14, ALT_A)
+#define GPIO14_SM_CS1n		PIN_CFG(14, ALT_B)
+#define GPIO14_SM_CKO		PIN_CFG(14, ALT_C)
+
+#define GPIO15_GPIO		PIN_CFG(15, GPIO)
+#define GPIO15_SM_A5		PIN_CFG(15, ALT_A)
+#define GPIO15_SM_CLE		PIN_CFG(15, ALT_B)
+
+#define GPIO16_GPIO		PIN_CFG(16, GPIO)
+#define GPIO16_MC2_CMD		PIN_CFG(16, ALT_A)
+#define GPIO16_SM_OEn		PIN_CFG(16, ALT_B)
+
+#define GPIO17_GPIO		PIN_CFG(17, GPIO)
+#define GPIO17_MC2_CLK		PIN_CFG(17, ALT_A)
+#define GPIO17_SM_WEn		PIN_CFG(17, ALT_B)
+
+#define GPIO18_GPIO		PIN_CFG(18, GPIO)
+#define GPIO18_SM_A6		PIN_CFG(18, ALT_A)
+#define GPIO18_SM_ALE		PIN_CFG(18, ALT_B)
+#define GPIO18_SM_AVDn		PIN_CFG(18, ALT_C)
+
+#define GPIO19_GPIO		PIN_CFG(19, GPIO)
+#define GPIO19_MC2_DAT1		PIN_CFG(19, ALT_A)
+#define GPIO19_SM_ADQ4		PIN_CFG(19, ALT_B)
+
+#define GPIO20_GPIO		PIN_CFG(20, GPIO)
+#define GPIO20_MC2_DAT3		PIN_CFG(20, ALT_A)
+#define GPIO20_SM_ADQ5		PIN_CFG(20, ALT_B)
+
+#define GPIO21_GPIO		PIN_CFG(21, GPIO)
+#define GPIO21_MC2_DAT5		PIN_CFG(21, ALT_A)
+#define GPIO21_SM_ADQ6		PIN_CFG(21, ALT_B)
+
+#define GPIO22_GPIO		PIN_CFG(22, GPIO)
+#define GPIO22_MC2_DAT7		PIN_CFG(22, ALT_A)
+#define GPIO22_SM_ADQ7		PIN_CFG(22, ALT_B)
+
+#define GPIO23_GPIO		PIN_CFG(23, GPIO)
+#define GPIO23_MC2_DAT0		PIN_CFG(23, ALT_A)
+#define GPIO23_SM_ADQ12		PIN_CFG(23, ALT_B)
+#define GPIO23_MC0_DAT1		PIN_CFG(23, ALT_C)
+
+#define GPIO24_GPIO		PIN_CFG(24, GPIO)
+#define GPIO24_MC2_DAT2		PIN_CFG(24, ALT_A)
+#define GPIO24_SM_ADQ13		PIN_CFG(24, ALT_B)
+#define GPIO24_MC0_DAT3		PIN_CFG(24, ALT_C)
+
+#define GPIO25_GPIO		PIN_CFG(25, GPIO)
+#define GPIO25_MC2_DAT4		PIN_CFG(25, ALT_A)
+#define GPIO25_SM_ADQ14		PIN_CFG(25, ALT_B)
+#define GPIO25_MC0_CMD		PIN_CFG(25, ALT_C)
+
+#define GPIO26_GPIO		PIN_CFG(26, GPIO)
+#define GPIO26_MC2_DAT6		PIN_CFG(26, ALT_A)
+#define GPIO26_SM_ADQ15		PIN_CFG(26, ALT_B)
+
+#define GPIO27_GPIO		PIN_CFG(27, GPIO)
+#define GPIO27_SM_CS0n		PIN_CFG(27, ALT_A)
+#define GPIO27_SM_PS0n		PIN_CFG(27, ALT_B)
+
+#define GPIO28_GPIO		PIN_CFG(28, GPIO)
+#define GPIO28_U0_TXD		PIN_CFG(28, ALT_A)
+#define GPIO28_SM_A0		PIN_CFG(28, ALT_B)
+
+#define GPIO29_GPIO		PIN_CFG(29, GPIO)
+#define GPIO29_U0_RXD		PIN_CFG(29, ALT_A)
+#define GPIO29_SM_A1		PIN_CFG(29, ALT_B)
+#define GPIO29_PWM_0		PIN_CFG(29, ALT_C)
+
+#define GPIO30_GPIO		PIN_CFG(30, GPIO)
+#define GPIO30_MC0_DAT5		PIN_CFG(30, ALT_A)
+#define GPIO30_SM_A2		PIN_CFG(30, ALT_B)
+#define GPIO30_PWM_1		PIN_CFG(30, ALT_C)
+
+#define GPIO31_GPIO		PIN_CFG(31, GPIO)
+#define GPIO31_MC0_DAT7		PIN_CFG(31, ALT_A)
+#define GPIO31_SM_CS2n		PIN_CFG(31, ALT_B)
+#define GPIO31_PWM_2		PIN_CFG(31, ALT_C)
+
+#define GPIO32_GPIO		PIN_CFG(32, GPIO)
+#define GPIO32_MSP0_TCK		PIN_CFG(32, ALT_A)
+#define GPIO32_ACCI2S0_SCK	PIN_CFG(32, ALT_B)
+
+#define GPIO33_GPIO		PIN_CFG(33, GPIO)
+#define GPIO33_MSP0_TFS		PIN_CFG(33, ALT_A)
+#define GPIO33_ACCI2S0_WS	PIN_CFG(33, ALT_B)
+
+#define GPIO34_GPIO		PIN_CFG(34, GPIO)
+#define GPIO34_MSP0_TXD		PIN_CFG(34, ALT_A)
+#define GPIO34_ACCI2S0_DLD	PIN_CFG(34, ALT_B)
+
+#define GPIO35_GPIO		PIN_CFG(35, GPIO)
+#define GPIO35_MSP0_RXD		PIN_CFG(35, ALT_A)
+#define GPIO35_ACCI2S0_ULD	PIN_CFG(35, ALT_B)
+
+#define GPIO64_GPIO		PIN_CFG(64, GPIO)
+#define GPIO64_USB_DAT0		PIN_CFG(64, ALT_A)
+#define GPIO64_U0_TXD		PIN_CFG(64, ALT_B)
+
+#define GPIO65_GPIO		PIN_CFG(65, GPIO)
+#define GPIO65_USB_DAT1		PIN_CFG(65, ALT_A)
+#define GPIO65_U0_RXD		PIN_CFG(65, ALT_B)
+
+#define GPIO66_GPIO		PIN_CFG(66, GPIO)
+#define GPIO66_USB_DAT2		PIN_CFG(66, ALT_A)
+
+#define GPIO67_GPIO		PIN_CFG(67, GPIO)
+#define GPIO67_USB_DAT3		PIN_CFG(67, ALT_A)
+
+#define GPIO68_GPIO		PIN_CFG(68, GPIO)
+#define GPIO68_USB_DAT4		PIN_CFG(68, ALT_A)
+
+#define GPIO69_GPIO		PIN_CFG(69, GPIO)
+#define GPIO69_USB_DAT5		PIN_CFG(69, ALT_A)
+
+#define GPIO70_GPIO		PIN_CFG(70, GPIO)
+#define GPIO70_USB_DAT6		PIN_CFG(70, ALT_A)
+
+#define GPIO71_GPIO		PIN_CFG(71, GPIO)
+#define GPIO71_USB_DAT7		PIN_CFG(71, ALT_A)
+
+#define GPIO72_GPIO		PIN_CFG(72, GPIO)
+#define GPIO72_USB_STP		PIN_CFG(72, ALT_A)
+
+#define GPIO73_GPIO		PIN_CFG(73, GPIO)
+#define GPIO73_USB_DIR		PIN_CFG(73, ALT_A)
+
+#define GPIO74_GPIO		PIN_CFG(74, GPIO)
+#define GPIO74_USB_NXT		PIN_CFG(74, ALT_A)
+
+#define GPIO75_GPIO		PIN_CFG(75, GPIO)
+#define GPIO75_USB_XCLK		PIN_CFG(75, ALT_A)
+
+#define GPIO76_GPIO		PIN_CFG(76, GPIO)
+
+#define GPIO77_GPIO		PIN_CFG(77, GPIO)
+#define GPIO77_ACCTX_ON		PIN_CFG(77, ALT_A)
+
+#define GPIO78_GPIO		PIN_CFG(78, GPIO)
+#define GPIO78_IRQn		PIN_CFG(78, ALT_A)
+
+#define GPIO79_GPIO		PIN_CFG(79, GPIO)
+#define GPIO79_ACCSIM_Clk	PIN_CFG(79, ALT_A)
+
+#define GPIO80_GPIO		PIN_CFG(80, GPIO)
+#define GPIO80_ACCSIM_Da	PIN_CFG(80, ALT_A)
+
+#define GPIO81_GPIO		PIN_CFG(81, GPIO)
+#define GPIO81_ACCSIM_Reset	PIN_CFG(81, ALT_A)
+
+#define GPIO82_GPIO		PIN_CFG(82, GPIO)
+#define GPIO82_ACCSIM_DDir	PIN_CFG(82, ALT_A)
+
+#define GPIO96_GPIO		PIN_CFG(96, GPIO)
+#define GPIO96_MSP1_TCK		PIN_CFG(96, ALT_A)
+#define GPIO96_PRCMU_DEBUG3	PIN_CFG(96, ALT_B)
+#define GPIO96_PRCMU_DEBUG7	PIN_CFG(96, ALT_C)
+
+#define GPIO97_GPIO		PIN_CFG(97, GPIO)
+#define GPIO97_MSP1_TFS		PIN_CFG(97, ALT_A)
+#define GPIO97_PRCMU_DEBUG2	PIN_CFG(97, ALT_B)
+#define GPIO97_PRCMU_DEBUG6	PIN_CFG(97, ALT_C)
+
+#define GPIO98_GPIO		PIN_CFG(98, GPIO)
+#define GPIO98_MSP1_TXD		PIN_CFG(98, ALT_A)
+#define GPIO98_PRCMU_DEBUG1	PIN_CFG(98, ALT_B)
+#define GPIO98_PRCMU_DEBUG5	PIN_CFG(98, ALT_C)
+
+#define GPIO99_GPIO		PIN_CFG(99, GPIO)
+#define GPIO99_MSP1_RXD		PIN_CFG(99, ALT_A)
+#define GPIO99_PRCMU_DEBUG0	PIN_CFG(99, ALT_B)
+#define GPIO99_PRCMU_DEBUG4	PIN_CFG(99, ALT_C)
+
+#define GPIO100_GPIO		PIN_CFG(100, GPIO)
+#define GPIO100_I2C0_SCL	PIN_CFG(100, ALT_A)
+
+#define GPIO101_GPIO		PIN_CFG(101, GPIO)
+#define GPIO101_I2C0_SDA	PIN_CFG(101, ALT_A)
+
+#define GPIO128_GPIO		PIN_CFG(128, GPIO)
+#define GPIO128_KP_I0		PIN_CFG(128, ALT_A)
+#define GPIO128_BUSMON_D0	PIN_CFG(128, ALT_B)
+
+#define GPIO129_GPIO		PIN_CFG(129, GPIO)
+#define GPIO129_KP_O0		PIN_CFG(129, ALT_A)
+#define GPIO129_BUSMON_D1	PIN_CFG(129, ALT_B)
+
+#define GPIO130_GPIO		PIN_CFG(130, GPIO)
+#define GPIO130_KP_I1		PIN_CFG(130, ALT_A)
+#define GPIO130_BUSMON_D2	PIN_CFG(130, ALT_B)
+
+#define GPIO131_GPIO		PIN_CFG(131, GPIO)
+#define GPIO131_KP_O1		PIN_CFG(131, ALT_A)
+#define GPIO131_BUSMON_D3	PIN_CFG(131, ALT_B)
+
+#define GPIO132_GPIO		PIN_CFG(132, GPIO)
+#define GPIO132_KP_I2		PIN_CFG(132, ALT_A)
+#define GPIO132_ETM_D15		PIN_CFG(132, ALT_B)
+#define GPIO132_STMAPE_CLK	PIN_CFG(132, ALT_C)
+
+#define GPIO133_GPIO		PIN_CFG(133, GPIO)
+#define GPIO133_KP_O2		PIN_CFG(133, ALT_A)
+#define GPIO133_ETM_D14		PIN_CFG(133, ALT_B)
+#define GPIO133_U0_RXD		PIN_CFG(133, ALT_C)
+
+#define GPIO134_GPIO		PIN_CFG(134, GPIO)
+#define GPIO134_KP_I3		PIN_CFG(134, ALT_A)
+#define GPIO134_ETM_D13		PIN_CFG(134, ALT_B)
+#define GPIO134_STMAPE_DAT0	PIN_CFG(134, ALT_C)
+
+#define GPIO135_GPIO		PIN_CFG(135, GPIO)
+#define GPIO135_KP_O3		PIN_CFG(135, ALT_A)
+#define GPIO135_ETM_D12		PIN_CFG(135, ALT_B)
+#define GPIO135_STMAPE_DAT1	PIN_CFG(135, ALT_C)
+
+#define GPIO136_GPIO		PIN_CFG(136, GPIO)
+#define GPIO136_KP_I4		PIN_CFG(136, ALT_A)
+#define GPIO136_ETM_D11		PIN_CFG(136, ALT_B)
+#define GPIO136_STMAPE_DAT2	PIN_CFG(136, ALT_C)
+
+#define GPIO137_GPIO		PIN_CFG(137, GPIO)
+#define GPIO137_KP_O4		PIN_CFG(137, ALT_A)
+#define GPIO137_ETM_D10		PIN_CFG(137, ALT_B)
+#define GPIO137_STMAPE_DAT3	PIN_CFG(137, ALT_C)
+
+#define GPIO138_GPIO		PIN_CFG(138, GPIO)
+#define GPIO138_KP_I5		PIN_CFG(138, ALT_A)
+#define GPIO138_ETM_D9		PIN_CFG(138, ALT_B)
+#define GPIO138_U0_TXD		PIN_CFG(138, ALT_C)
+
+#define GPIO139_GPIO		PIN_CFG(139, GPIO)
+#define GPIO139_KP_O5		PIN_CFG(139, ALT_A)
+#define GPIO139_ETM_D8		PIN_CFG(139, ALT_B)
+#define GPIO139_BUSMON_D11	PIN_CFG(139, ALT_C)
+
+#define GPIO140_GPIO		PIN_CFG(140, GPIO)
+#define GPIO140_KP_I6		PIN_CFG(140, ALT_A)
+#define GPIO140_ETM_D7		PIN_CFG(140, ALT_B)
+#define GPIO140_STMAPE_CLK	PIN_CFG(140, ALT_C)
+
+#define GPIO141_GPIO		PIN_CFG(141, GPIO)
+#define GPIO141_KP_O6		PIN_CFG(141, ALT_A)
+#define GPIO141_ETM_D6		PIN_CFG(141, ALT_B)
+#define GPIO141_U0_RXD		PIN_CFG(141, ALT_C)
+
+#define GPIO142_GPIO		PIN_CFG(142, GPIO)
+#define GPIO142_KP_I7		PIN_CFG(142, ALT_A)
+#define GPIO142_ETM_D5		PIN_CFG(142, ALT_B)
+#define GPIO142_STMAPE_DAT0	PIN_CFG(142, ALT_C)
+
+#define GPIO143_GPIO		PIN_CFG(143, GPIO)
+#define GPIO143_KP_O7		PIN_CFG(143, ALT_A)
+#define GPIO143_ETM_D4		PIN_CFG(143, ALT_B)
+#define GPIO143_STMAPE_DAT1	PIN_CFG(143, ALT_C)
+
+#define GPIO144_GPIO		PIN_CFG(144, GPIO)
+#define GPIO144_I2C3_SCL	PIN_CFG(144, ALT_A)
+#define GPIO144_ETM_D3		PIN_CFG(144, ALT_B)
+#define GPIO144_STMAPE_DAT2	PIN_CFG(144, ALT_C)
+
+#define GPIO145_GPIO		PIN_CFG(145, GPIO)
+#define GPIO145_I2C3_SDA	PIN_CFG(145, ALT_A)
+#define GPIO145_ETM_D2		PIN_CFG(145, ALT_B)
+#define GPIO145_STMAPE_DAT3	PIN_CFG(145, ALT_C)
+
+#define GPIO146_GPIO		PIN_CFG(146, GPIO)
+#define GPIO146_PWM_0		PIN_CFG(146, ALT_A)
+#define GPIO146_ETM_D1		PIN_CFG(146, ALT_B)
+
+#define GPIO147_GPIO		PIN_CFG(147, GPIO)
+#define GPIO147_PWM_1		PIN_CFG(147, ALT_A)
+#define GPIO147_ETM_D0		PIN_CFG(147, ALT_B)
+
+#define GPIO148_GPIO		PIN_CFG(148, GPIO)
+#define GPIO148_PWM_2		PIN_CFG(148, ALT_A)
+#define GPIO148_ETM_CLK		PIN_CFG(148, ALT_B)
+
+#define GPIO160_GPIO		PIN_CFG(160, GPIO)
+#define GPIO160_CLKOUT_REQn	PIN_CFG(160, ALT_A)
+
+#define GPIO161_GPIO		PIN_CFG(161, GPIO)
+#define GPIO161_CLKOUT_0	PIN_CFG(161, ALT_A)
+
+#define GPIO162_GPIO		PIN_CFG(162, GPIO)
+#define GPIO162_CLKOUT_1	PIN_CFG(162, ALT_A)
+
+#define GPIO163_GPIO		PIN_CFG(163, GPIO)
+
+#define GPIO164_GPIO		PIN_CFG(164, GPIO)
+#define GPIO164_GPS_START	PIN_CFG(164, ALT_A)
+
+#define GPIO165_GPIO		PIN_CFG(165, GPIO)
+#define GPIO165_SPI1_CS2n	PIN_CFG(165, ALT_A)
+#define GPIO165_U3_RXD		PIN_CFG(165, ALT_B)
+#define GPIO165_BUSMON_D20	PIN_CFG(165, ALT_C)
+
+#define GPIO166_GPIO		PIN_CFG(166, GPIO)
+#define GPIO166_SPI1_CS1n	PIN_CFG(166, ALT_A)
+#define GPIO166_U3_TXD		PIN_CFG(166, ALT_B)
+#define GPIO166_BUSMON_D21	PIN_CFG(166, ALT_C)
+
+#define GPIO167_GPIO		PIN_CFG(167, GPIO)
+#define GPIO167_SPI1_CS0n	PIN_CFG(167, ALT_A)
+#define GPIO167_U3_RTSn		PIN_CFG(167, ALT_B)
+#define GPIO167_BUSMON_D22	PIN_CFG(167, ALT_C)
+
+#define GPIO168_GPIO		PIN_CFG(168, GPIO)
+#define GPIO168_SPI1_RXD	PIN_CFG(168, ALT_A)
+#define GPIO168_U3_CTSn		PIN_CFG(168, ALT_B)
+#define GPIO168_BUSMON_D23	PIN_CFG(168, ALT_C)
+
+#define GPIO169_GPIO		PIN_CFG(169, GPIO)
+#define GPIO169_SPI1_TXD	PIN_CFG(169, ALT_A)
+#define GPIO169_DDR_RC		PIN_CFG(169, ALT_B)
+#define GPIO169_BUSMON_D24	PIN_CFG(169, ALT_C)
+
+#define GPIO170_GPIO		PIN_CFG(170, GPIO)
+#define GPIO170_SPI1_CLK	PIN_CFG(170, ALT_A)
+
+#define GPIO171_GPIO		PIN_CFG(171, GPIO)
+#define GPIO171_MC3_DAT0	PIN_CFG(171, ALT_A)
+#define GPIO171_SPI3_RXD	PIN_CFG(171, ALT_B)
+#define GPIO171_BUSMON_D25	PIN_CFG(171, ALT_C)
+
+#define GPIO172_GPIO		PIN_CFG(172, GPIO)
+#define GPIO172_MC3_DAT1	PIN_CFG(172, ALT_A)
+#define GPIO172_SPI3_CS1n	PIN_CFG(172, ALT_B)
+#define GPIO172_BUSMON_D26	PIN_CFG(172, ALT_C)
+
+#define GPIO173_GPIO		PIN_CFG(173, GPIO)
+#define GPIO173_MC3_DAT2	PIN_CFG(173, ALT_A)
+#define GPIO173_SPI3_CS2n	PIN_CFG(173, ALT_B)
+#define GPIO173_BUSMON_D27	PIN_CFG(173, ALT_C)
+
+#define GPIO174_GPIO		PIN_CFG(174, GPIO)
+#define GPIO174_MC3_DAT3	PIN_CFG(174, ALT_A)
+#define GPIO174_SPI3_CS0n	PIN_CFG(174, ALT_B)
+#define GPIO174_BUSMON_D28	PIN_CFG(174, ALT_C)
+
+#define GPIO175_GPIO		PIN_CFG(175, GPIO)
+#define GPIO175_MC3_CMD		PIN_CFG(175, ALT_A)
+#define GPIO175_SPI3_TXD	PIN_CFG(175, ALT_B)
+#define GPIO175_BUSMON_D29	PIN_CFG(175, ALT_C)
+
+#define GPIO176_GPIO		PIN_CFG(176, GPIO)
+#define GPIO176_MC3_CLK		PIN_CFG(176, ALT_A)
+#define GPIO176_SPI3_CLK	PIN_CFG(176, ALT_B)
+
+#define GPIO177_GPIO		PIN_CFG(177, GPIO)
+#define GPIO177_U2_RXD		PIN_CFG(177, ALT_A)
+#define GPIO177_I2C3_SCL	PIN_CFG(177, ALT_B)
+#define GPIO177_BUSMON_D30	PIN_CFG(177, ALT_C)
+
+#define GPIO178_GPIO		PIN_CFG(178, GPIO)
+#define GPIO178_U2_TXD		PIN_CFG(178, ALT_A)
+#define GPIO178_I2C3_SDA	PIN_CFG(178, ALT_B)
+#define GPIO178_BUSMON_D31	PIN_CFG(178, ALT_C)
+
+#define GPIO179_GPIO		PIN_CFG(179, GPIO)
+#define GPIO179_U2_CTSn		PIN_CFG(179, ALT_A)
+#define GPIO179_U3_RXD		PIN_CFG(179, ALT_B)
+#define GPIO179_BUSMON_D32	PIN_CFG(179, ALT_C)
+
+#define GPIO180_GPIO		PIN_CFG(180, GPIO)
+#define GPIO180_U2_RTSn		PIN_CFG(180, ALT_A)
+#define GPIO180_U3_TXD		PIN_CFG(180, ALT_B)
+#define GPIO180_BUSMON_D33	PIN_CFG(180, ALT_C)
+
+#define GPIO185_GPIO		PIN_CFG(185, GPIO)
+#define GPIO185_SPI3_CS2n	PIN_CFG(185, ALT_A)
+#define GPIO185_MC4_DAT0	PIN_CFG(185, ALT_B)
+
+#define GPIO186_GPIO		PIN_CFG(186, GPIO)
+#define GPIO186_SPI3_CS1n	PIN_CFG(186, ALT_A)
+#define GPIO186_MC4_DAT1	PIN_CFG(186, ALT_B)
+
+#define GPIO187_GPIO		PIN_CFG(187, GPIO)
+#define GPIO187_SPI3_CS0n	PIN_CFG(187, ALT_A)
+#define GPIO187_MC4_DAT2	PIN_CFG(187, ALT_B)
+
+#define GPIO188_GPIO		PIN_CFG(188, GPIO)
+#define GPIO188_SPI3_RXD	PIN_CFG(188, ALT_A)
+#define GPIO188_MC4_DAT3	PIN_CFG(188, ALT_B)
+
+#define GPIO189_GPIO		PIN_CFG(189, GPIO)
+#define GPIO189_SPI3_TXD	PIN_CFG(189, ALT_A)
+#define GPIO189_MC4_CMD		PIN_CFG(189, ALT_B)
+
+#define GPIO190_GPIO		PIN_CFG(190, GPIO)
+#define GPIO190_SPI3_CLK	PIN_CFG(190, ALT_A)
+#define GPIO190_MC4_CLK		PIN_CFG(190, ALT_B)
+
+#define GPIO191_GPIO		PIN_CFG(191, GPIO)
+#define GPIO191_MC1_DAT0	PIN_CFG(191, ALT_A)
+#define GPIO191_MC4_DAT4	PIN_CFG(191, ALT_B)
+#define GPIO191_STMAPE_DAT0	PIN_CFG(191, ALT_C)
+
+#define GPIO192_GPIO		PIN_CFG(192, GPIO)
+#define GPIO192_MC1_DAT1	PIN_CFG(192, ALT_A)
+#define GPIO192_MC4_DAT5	PIN_CFG(192, ALT_B)
+#define GPIO192_STMAPE_DAT1	PIN_CFG(192, ALT_C)
+
+#define GPIO193_GPIO		PIN_CFG(193, GPIO)
+#define GPIO193_MC1_DAT2	PIN_CFG(193, ALT_A)
+#define GPIO193_MC4_DAT6	PIN_CFG(193, ALT_B)
+#define GPIO193_STMAPE_DAT2	PIN_CFG(193, ALT_C)
+
+#define GPIO194_GPIO		PIN_CFG(194, GPIO)
+#define GPIO194_MC1_DAT3	PIN_CFG(194, ALT_A)
+#define GPIO194_MC4_DAT7	PIN_CFG(194, ALT_B)
+#define GPIO194_STMAPE_DAT3	PIN_CFG(194, ALT_C)
+
+#define GPIO195_GPIO		PIN_CFG(195, GPIO)
+#define GPIO195_MC1_CLK		PIN_CFG(195, ALT_A)
+#define GPIO195_STMAPE_CLK	PIN_CFG(195, ALT_B)
+#define GPIO195_BUSMON_CLK	PIN_CFG(195, ALT_C)
+
+#define GPIO196_GPIO		PIN_CFG(196, GPIO)
+#define GPIO196_MC1_CMD		PIN_CFG(196, ALT_A)
+#define GPIO196_U0_RXD		PIN_CFG(196, ALT_B)
+#define GPIO196_BUSMON_D38	PIN_CFG(196, ALT_C)
+
+#define GPIO197_GPIO		PIN_CFG(197, GPIO)
+#define GPIO197_MC1_CMDDIR	PIN_CFG(197, ALT_A)
+#define GPIO197_BUSMON_D39	PIN_CFG(197, ALT_B)
+
+#define GPIO198_GPIO		PIN_CFG(198, GPIO)
+#define GPIO198_MC1_FBCLK	PIN_CFG(198, ALT_A)
+
+#define GPIO199_GPIO		PIN_CFG(199, GPIO)
+#define GPIO199_MC1_DAT0DIR	PIN_CFG(199, ALT_A)
+#define GPIO199_BUSMON_D40	PIN_CFG(199, ALT_B)
+
+#define GPIO200_GPIO		PIN_CFG(200, GPIO)
+#define GPIO200_U1_TXD		PIN_CFG(200, ALT_A)
+#define GPIO200_ACCU0_RTSn	PIN_CFG(200, ALT_B)
+
+#define GPIO201_GPIO		PIN_CFG(201, GPIO)
+#define GPIO201_U1_RXD		PIN_CFG(201, ALT_A)
+#define GPIO201_ACCU0_CTSn	PIN_CFG(201, ALT_B)
+
+#define GPIO202_GPIO		PIN_CFG(202, GPIO)
+#define GPIO202_U1_CTSn		PIN_CFG(202, ALT_A)
+#define GPIO202_ACCU0_RXD	PIN_CFG(202, ALT_B)
+
+#define GPIO203_GPIO		PIN_CFG(203, GPIO)
+#define GPIO203_U1_RTSn		PIN_CFG(203, ALT_A)
+#define GPIO203_ACCU0_TXD	PIN_CFG(203, ALT_B)
+
+#define GPIO204_GPIO		PIN_CFG(204, GPIO)
+#define GPIO204_SPI0_CS2n	PIN_CFG(204, ALT_A)
+#define GPIO204_ACCGPIO_000	PIN_CFG(204, ALT_B)
+#define GPIO204_LCD_VSI1	PIN_CFG(204, ALT_C)
+
+#define GPIO205_GPIO		PIN_CFG(205, GPIO)
+#define GPIO205_SPI0_CS1n	PIN_CFG(205, ALT_A)
+#define GPIO205_ACCGPIO_001	PIN_CFG(205, ALT_B)
+#define GPIO205_LCD_D3		PIN_CFG(205, ALT_C)
+
+#define GPIO206_GPIO		PIN_CFG(206, GPIO)
+#define GPIO206_SPI0_CS0n	PIN_CFG(206, ALT_A)
+#define GPIO206_ACCGPIO_002	PIN_CFG(206, ALT_B)
+#define GPIO206_LCD_D2		PIN_CFG(206, ALT_C)
+
+#define GPIO207_GPIO		PIN_CFG(207, GPIO)
+#define GPIO207_SPI0_RXD	PIN_CFG(207, ALT_A)
+#define GPIO207_ACCGPIO_003	PIN_CFG(207, ALT_B)
+#define GPIO207_LCD_D1		PIN_CFG(207, ALT_C)
+
+#define GPIO208_GPIO		PIN_CFG(208, GPIO)
+#define GPIO208_SPI0_TXD	PIN_CFG(208, ALT_A)
+#define GPIO208_ACCGPIO_004	PIN_CFG(208, ALT_B)
+#define GPIO208_LCD_D0		PIN_CFG(208, ALT_C)
+
+#define GPIO209_GPIO		PIN_CFG(209, GPIO)
+#define GPIO209_SPI0_CLK	PIN_CFG(209, ALT_A)
+#define GPIO209_ACCGPIO_005	PIN_CFG(209, ALT_B)
+#define GPIO209_LCD_CLK		PIN_CFG(209, ALT_C)
+
+#define GPIO210_GPIO		PIN_CFG(210, GPIO)
+#define GPIO210_LCD_VSO		PIN_CFG(210, ALT_A)
+#define GPIO210_PRCMU_PWRCTRL1	PIN_CFG(210, ALT_B)
+
+#define GPIO211_GPIO		PIN_CFG(211, GPIO)
+#define GPIO211_LCD_VSI0	PIN_CFG(211, ALT_A)
+#define GPIO211_PRCMU_PWRCTRL2	PIN_CFG(211, ALT_B)
+
+#define GPIO212_GPIO		PIN_CFG(212, GPIO)
+#define GPIO212_SPI2_CS2n	PIN_CFG(212, ALT_A)
+#define GPIO212_LCD_HSO		PIN_CFG(212, ALT_B)
+
+#define GPIO213_GPIO		PIN_CFG(213, GPIO)
+#define GPIO213_SPI2_CS1n	PIN_CFG(213, ALT_A)
+#define GPIO213_LCD_DE		PIN_CFG(213, ALT_B)
+#define GPIO213_BUSMON_D16	PIN_CFG(213, ALT_C)
+
+#define GPIO214_GPIO		PIN_CFG(214, GPIO)
+#define GPIO214_SPI2_CS0n	PIN_CFG(214, ALT_A)
+#define GPIO214_LCD_D7		PIN_CFG(214, ALT_B)
+#define GPIO214_BUSMON_D17	PIN_CFG(214, ALT_C)
+
+#define GPIO215_GPIO		PIN_CFG(215, GPIO)
+#define GPIO215_SPI2_RXD	PIN_CFG(215, ALT_A)
+#define GPIO215_LCD_D6		PIN_CFG(215, ALT_B)
+#define GPIO215_BUSMON_D18	PIN_CFG(215, ALT_C)
+
+#define GPIO216_GPIO		PIN_CFG(216, GPIO)
+#define GPIO216_SPI2_CLK	PIN_CFG(216, ALT_A)
+#define GPIO216_LCD_D5		PIN_CFG(216, ALT_B)
+
+#define GPIO217_GPIO		PIN_CFG(217, GPIO)
+#define GPIO217_SPI2_TXD	PIN_CFG(217, ALT_A)
+#define GPIO217_LCD_D4		PIN_CFG(217, ALT_B)
+#define GPIO217_BUSMON_D19	PIN_CFG(217, ALT_C)
+
+#define GPIO218_GPIO		PIN_CFG(218, GPIO)
+#define GPIO218_I2C2_SCL	PIN_CFG(218, ALT_A)
+#define GPIO218_LCD_VSO		PIN_CFG(218, ALT_B)
+
+#define GPIO219_GPIO		PIN_CFG(219, GPIO)
+#define GPIO219_I2C2_SDA	PIN_CFG(219, ALT_A)
+#define GPIO219_LCD_D3		PIN_CFG(219, ALT_B)
+
+#define GPIO220_GPIO		PIN_CFG(220, GPIO)
+#define GPIO220_MSP2_TCK	PIN_CFG(220, ALT_A)
+#define GPIO220_LCD_D2		PIN_CFG(220, ALT_B)
+
+#define GPIO221_GPIO		PIN_CFG(221, GPIO)
+#define GPIO221_MSP2_TFS	PIN_CFG(221, ALT_A)
+#define GPIO221_LCD_D1		PIN_CFG(221, ALT_B)
+
+#define GPIO222_GPIO		PIN_CFG(222, GPIO)
+#define GPIO222_MSP2_TXD	PIN_CFG(222, ALT_A)
+#define GPIO222_LCD_D0		PIN_CFG(222, ALT_B)
+
+#define GPIO223_GPIO		PIN_CFG(223, GPIO)
+#define GPIO223_MSP2_RXD	PIN_CFG(223, ALT_A)
+#define GPIO223_LCD_CLK		PIN_CFG(223, ALT_B)
+
+#define GPIO224_GPIO		PIN_CFG(224, GPIO)
+#define GPIO224_PRCMU_PWRCTRL0	PIN_CFG(224, ALT_A)
+#define GPIO224_LCD_VSI1	PIN_CFG(224, ALT_B)
+
+#define GPIO225_GPIO		PIN_CFG(225, GPIO)
+#define GPIO225_PRCMU_PWRCTRL1	PIN_CFG(225, ALT_A)
+#define GPIO225_IRDA_RXD	PIN_CFG(225, ALT_B)
+
+#define GPIO226_GPIO		PIN_CFG(226, GPIO)
+#define GPIO226_PRCMU_PWRCTRL2	PIN_CFG(226, ALT_A)
+#define GPIO226_IRRC_DAT	PIN_CFG(226, ALT_B)
+
+#define GPIO227_GPIO		PIN_CFG(227, GPIO)
+#define GPIO227_IRRC_DAT	PIN_CFG(227, ALT_A)
+#define GPIO227_IRDA_TXD	PIN_CFG(227, ALT_B)
+
+#endif
diff --git a/arch/arm/mach-ux500/pins-db8500.h b/arch/arm/mach-ux500/pins-db8500.h
index 9055d5d..66f8761 100644
--- a/arch/arm/mach-ux500/pins-db8500.h
+++ b/arch/arm/mach-ux500/pins-db8500.h
@@ -96,57 +96,57 @@
 #define GPIO17_SLIM0_CLK	PIN_CFG(17, ALT_C)
 
 #define GPIO18_GPIO		PIN_CFG(18, GPIO)
-#define GPIO18_MC0_CMDDIR	PIN_CFG(18, ALT_A)
+#define GPIO18_MC0_CMDDIR	PIN_CFG_PULL(18, ALT_A, UP)
 #define GPIO18_U2_RXD		PIN_CFG(18, ALT_B)
 #define GPIO18_MS_IEP		PIN_CFG(18, ALT_C)
 
 #define GPIO19_GPIO		PIN_CFG(19, GPIO)
-#define GPIO19_MC0_DAT0DIR	PIN_CFG(19, ALT_A)
+#define GPIO19_MC0_DAT0DIR	PIN_CFG_PULL(19, ALT_A, UP)
 #define GPIO19_U2_TXD		PIN_CFG(19, ALT_B)
 #define GPIO19_MS_DAT0DIR	PIN_CFG(19, ALT_C)
 
 #define GPIO20_GPIO		PIN_CFG(20, GPIO)
-#define GPIO20_MC0_DAT2DIR	PIN_CFG(20, ALT_A)
+#define GPIO20_MC0_DAT2DIR	PIN_CFG_PULL(20, ALT_A, UP)
 #define GPIO20_UARTMOD_TXD	PIN_CFG(20, ALT_B)
 #define GPIO20_IP_TRIGOUT	PIN_CFG(20, ALT_C)
 
 #define GPIO21_GPIO		PIN_CFG(21, GPIO)
-#define GPIO21_MC0_DAT31DIR	PIN_CFG(21, ALT_A)
+#define GPIO21_MC0_DAT31DIR	PIN_CFG_PULL(21, ALT_A, UP)
 #define GPIO21_MSP0_SCK		PIN_CFG(21, ALT_B)
 #define GPIO21_MS_DAT31DIR	PIN_CFG(21, ALT_C)
 
 #define GPIO22_GPIO		PIN_CFG(22, GPIO)
-#define GPIO22_MC0_FBCLK	PIN_CFG(22, ALT_A)
+#define GPIO22_MC0_FBCLK	PIN_CFG_PULL(22, ALT_A, UP)
 #define GPIO22_UARTMOD_RXD	PIN_CFG(22, ALT_B)
 #define GPIO22_MS_FBCLK		PIN_CFG(22, ALT_C)
 
 #define GPIO23_GPIO		PIN_CFG(23, GPIO)
-#define GPIO23_MC0_CLK		PIN_CFG(23, ALT_A)
+#define GPIO23_MC0_CLK		PIN_CFG_PULL(23, ALT_A, UP)
 #define GPIO23_STMMOD_CLK	PIN_CFG(23, ALT_B)
 #define GPIO23_MS_CLK		PIN_CFG(23, ALT_C)
 
 #define GPIO24_GPIO		PIN_CFG(24, GPIO)
-#define GPIO24_MC0_CMD		PIN_CFG(24, ALT_A)
+#define GPIO24_MC0_CMD		PIN_CFG_PULL(24, ALT_A, UP)
 #define GPIO24_UARTMOD_RXD	PIN_CFG(24, ALT_B)
 #define GPIO24_MS_BS		PIN_CFG(24, ALT_C)
 
 #define GPIO25_GPIO		PIN_CFG(25, GPIO)
-#define GPIO25_MC0_DAT0		PIN_CFG(25, ALT_A)
+#define GPIO25_MC0_DAT0		PIN_CFG_PULL(25, ALT_A, UP)
 #define GPIO25_STMMOD_DAT0	PIN_CFG(25, ALT_B)
 #define GPIO25_MS_DAT0		PIN_CFG(25, ALT_C)
 
 #define GPIO26_GPIO		PIN_CFG(26, GPIO)
-#define GPIO26_MC0_DAT1		PIN_CFG(26, ALT_A)
+#define GPIO26_MC0_DAT1		PIN_CFG_PULL(26, ALT_A, UP)
 #define GPIO26_STMMOD_DAT1	PIN_CFG(26, ALT_B)
 #define GPIO26_MS_DAT1		PIN_CFG(26, ALT_C)
 
 #define GPIO27_GPIO		PIN_CFG(27, GPIO)
-#define GPIO27_MC0_DAT2		PIN_CFG(27, ALT_A)
+#define GPIO27_MC0_DAT2		PIN_CFG_PULL(27, ALT_A, UP)
 #define GPIO27_STMMOD_DAT2	PIN_CFG(27, ALT_B)
 #define GPIO27_MS_DAT2		PIN_CFG(27, ALT_C)
 
 #define GPIO28_GPIO		PIN_CFG(28, GPIO)
-#define GPIO28_MC0_DAT3		PIN_CFG(28, ALT_A)
+#define GPIO28_MC0_DAT3		PIN_CFG_PULL(28, ALT_A, UP)
 #define GPIO28_STMMOD_DAT3	PIN_CFG(28, ALT_B)
 #define GPIO28_MS_DAT3		PIN_CFG(28, ALT_C)
 
@@ -357,48 +357,48 @@
 #define GPIO97_MC5_DAT7		PIN_CFG(97, ALT_C)
 
 #define GPIO128_GPIO		PIN_CFG(128, GPIO)
-#define GPIO128_MC2_CLK		PIN_CFG(128, ALT_A)
+#define GPIO128_MC2_CLK		PIN_CFG_PULL(128, ALT_A, UP)
 #define GPIO128_SM_CKO		PIN_CFG(128, ALT_B)
 
 #define GPIO129_GPIO		PIN_CFG(129, GPIO)
-#define GPIO129_MC2_CMD		PIN_CFG(129, ALT_A)
+#define GPIO129_MC2_CMD		PIN_CFG_PULL(129, ALT_A, UP)
 #define GPIO129_SM_WAIT0n	PIN_CFG(129, ALT_B)
 
 #define GPIO130_GPIO		PIN_CFG(130, GPIO)
-#define GPIO130_MC2_FBCLK	PIN_CFG(130, ALT_A)
+#define GPIO130_MC2_FBCLK	PIN_CFG_PULL(130, ALT_A, UP)
 #define GPIO130_SM_FBCLK	PIN_CFG(130, ALT_B)
 #define GPIO130_MC2_RSTN	PIN_CFG(130, ALT_C)
 
 #define GPIO131_GPIO		PIN_CFG(131, GPIO)
-#define GPIO131_MC2_DAT0	PIN_CFG(131, ALT_A)
+#define GPIO131_MC2_DAT0	PIN_CFG_PULL(131, ALT_A, UP)
 #define GPIO131_SM_ADQ8		PIN_CFG(131, ALT_B)
 
 #define GPIO132_GPIO		PIN_CFG(132, GPIO)
-#define GPIO132_MC2_DAT1	PIN_CFG(132, ALT_A)
+#define GPIO132_MC2_DAT1	PIN_CFG_PULL(132, ALT_A, UP)
 #define GPIO132_SM_ADQ9		PIN_CFG(132, ALT_B)
 
 #define GPIO133_GPIO		PIN_CFG(133, GPIO)
-#define GPIO133_MC2_DAT2	PIN_CFG(133, ALT_A)
+#define GPIO133_MC2_DAT2	PIN_CFG_PULL(133, ALT_A, UP)
 #define GPIO133_SM_ADQ10	PIN_CFG(133, ALT_B)
 
 #define GPIO134_GPIO		PIN_CFG(134, GPIO)
-#define GPIO134_MC2_DAT3	PIN_CFG(134, ALT_A)
+#define GPIO134_MC2_DAT3	PIN_CFG_PULL(134, ALT_A, UP)
 #define GPIO134_SM_ADQ11	PIN_CFG(134, ALT_B)
 
 #define GPIO135_GPIO		PIN_CFG(135, GPIO)
-#define GPIO135_MC2_DAT4	PIN_CFG(135, ALT_A)
+#define GPIO135_MC2_DAT4	PIN_CFG_PULL(135, ALT_A, UP)
 #define GPIO135_SM_ADQ12	PIN_CFG(135, ALT_B)
 
 #define GPIO136_GPIO		PIN_CFG(136, GPIO)
-#define GPIO136_MC2_DAT5	PIN_CFG(136, ALT_A)
+#define GPIO136_MC2_DAT5	PIN_CFG_PULL(136, ALT_A, UP)
 #define GPIO136_SM_ADQ13	PIN_CFG(136, ALT_B)
 
 #define GPIO137_GPIO		PIN_CFG(137, GPIO)
-#define GPIO137_MC2_DAT6	PIN_CFG(137, ALT_A)
+#define GPIO137_MC2_DAT6	PIN_CFG_PULL(137, ALT_A, UP)
 #define GPIO137_SM_ADQ14	PIN_CFG(137, ALT_B)
 
 #define GPIO138_GPIO		PIN_CFG(138, GPIO)
-#define GPIO138_MC2_DAT7	PIN_CFG(138, ALT_A)
+#define GPIO138_MC2_DAT7	PIN_CFG_PULL(138, ALT_A, UP)
 #define GPIO138_SM_ADQ15	PIN_CFG(138, ALT_B)
 
 #define GPIO139_GPIO		PIN_CFG(139, GPIO)
@@ -569,39 +569,39 @@
 #define GPIO196_MSP2_RXD	PIN_CFG(196, ALT_A)
 
 #define GPIO197_GPIO		PIN_CFG(197, GPIO)
-#define GPIO197_MC4_DAT3	PIN_CFG(197, ALT_A)
+#define GPIO197_MC4_DAT3	PIN_CFG_PULL(197, ALT_A, UP)
 
 #define GPIO198_GPIO		PIN_CFG(198, GPIO)
-#define GPIO198_MC4_DAT2	PIN_CFG(198, ALT_A)
+#define GPIO198_MC4_DAT2	PIN_CFG_PULL(198, ALT_A, UP)
 
 #define GPIO199_GPIO		PIN_CFG(199, GPIO)
-#define GPIO199_MC4_DAT1	PIN_CFG(199, ALT_A)
+#define GPIO199_MC4_DAT1	PIN_CFG_PULL(199, ALT_A, UP)
 
 #define GPIO200_GPIO		PIN_CFG(200, GPIO)
-#define GPIO200_MC4_DAT0	PIN_CFG(200, ALT_A)
+#define GPIO200_MC4_DAT0	PIN_CFG_PULL(200, ALT_A, UP)
 
 #define GPIO201_GPIO		PIN_CFG(201, GPIO)
-#define GPIO201_MC4_CMD		PIN_CFG(201, ALT_A)
+#define GPIO201_MC4_CMD		PIN_CFG_PULL(201, ALT_A, UP)
 
 #define GPIO202_GPIO		PIN_CFG(202, GPIO)
-#define GPIO202_MC4_FBCLK	PIN_CFG(202, ALT_A)
+#define GPIO202_MC4_FBCLK	PIN_CFG_PULL(202, ALT_A, UP)
 #define GPIO202_PWL		PIN_CFG(202, ALT_B)
 #define GPIO202_MC4_RSTN	PIN_CFG(202, ALT_C)
 
 #define GPIO203_GPIO		PIN_CFG(203, GPIO)
-#define GPIO203_MC4_CLK		PIN_CFG(203, ALT_A)
+#define GPIO203_MC4_CLK		PIN_CFG_PULL(203, ALT_A, UP)
 
 #define GPIO204_GPIO		PIN_CFG(204, GPIO)
-#define GPIO204_MC4_DAT7	PIN_CFG(204, ALT_A)
+#define GPIO204_MC4_DAT7	PIN_CFG_PULL(204, ALT_A, UP)
 
 #define GPIO205_GPIO		PIN_CFG(205, GPIO)
-#define GPIO205_MC4_DAT6	PIN_CFG(205, ALT_A)
+#define GPIO205_MC4_DAT6	PIN_CFG_PULL(205, ALT_A, UP)
 
 #define GPIO206_GPIO		PIN_CFG(206, GPIO)
-#define GPIO206_MC4_DAT5	PIN_CFG(206, ALT_A)
+#define GPIO206_MC4_DAT5	PIN_CFG_PULL(206, ALT_A, UP)
 
 #define GPIO207_GPIO		PIN_CFG(207, GPIO)
-#define GPIO207_MC4_DAT4	PIN_CFG(207, ALT_A)
+#define GPIO207_MC4_DAT4	PIN_CFG_PULL(207, ALT_A, UP)
 
 #define GPIO208_GPIO		PIN_CFG(208, GPIO)
 #define GPIO208_MC1_CLK		PIN_CFG(208, ALT_A)
diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index 438ef16..9e4c678 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -78,6 +78,8 @@
 	__cpuc_flush_dcache_area((void *)&pen_release, sizeof(pen_release));
 	outer_clean_range(__pa(&pen_release), __pa(&pen_release) + 1);
 
+	smp_cross_call(cpumask_of(cpu));
+
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
 		if (pen_release == -1)
diff --git a/arch/arm/mach-ux500/prcmu.c b/arch/arm/mach-ux500/prcmu.c
new file mode 100644
index 0000000..293274d
--- /dev/null
+++ b/arch/arm/mach-ux500/prcmu.c
@@ -0,0 +1,231 @@
+/*
+ * Copyright (C) ST Ericsson SA 2010
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Mattias Nilsson <mattias.i.nilsson@stericsson.com>
+ *
+ * U8500 PRCMU driver.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/mutex.h>
+#include <linux/completion.h>
+#include <linux/jiffies.h>
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+
+#include <mach/hardware.h>
+#include <mach/prcmu-regs.h>
+
+#define PRCMU_TCDM_BASE __io_address(U8500_PRCMU_TCDM_BASE)
+
+#define REQ_MB5 (PRCMU_TCDM_BASE + 0xE44)
+#define ACK_MB5 (PRCMU_TCDM_BASE + 0xDF4)
+
+#define REQ_MB5_I2C_SLAVE_OP (REQ_MB5)
+#define REQ_MB5_I2C_HW_BITS (REQ_MB5 + 1)
+#define REQ_MB5_I2C_REG (REQ_MB5 + 2)
+#define REQ_MB5_I2C_VAL (REQ_MB5 + 3)
+
+#define ACK_MB5_I2C_STATUS (ACK_MB5 + 1)
+#define ACK_MB5_I2C_VAL (ACK_MB5 + 3)
+
+#define I2C_WRITE(slave) ((slave) << 1)
+#define I2C_READ(slave) (((slave) << 1) | BIT(0))
+#define I2C_STOP_EN BIT(3)
+
+enum ack_mb5_status {
+	I2C_WR_OK = 0x01,
+	I2C_RD_OK = 0x02,
+};
+
+#define MBOX_BIT BIT
+#define NUM_MBOX 8
+
+static struct {
+	struct mutex lock;
+	struct completion work;
+	bool failed;
+	struct {
+		u8 status;
+		u8 value;
+	} ack;
+} mb5_transfer;
+
+/**
+ * prcmu_abb_read() - Read register value(s) from the ABB.
+ * @slave:	The I2C slave address.
+ * @reg:	The (start) register address.
+ * @value:	The read out value(s).
+ * @size:	The number of registers to read.
+ *
+ * Reads register value(s) from the ABB.
+ * @size has to be 1 for the current firmware version.
+ */
+int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size)
+{
+	int r;
+
+	if (size != 1)
+		return -EINVAL;
+
+	r = mutex_lock_interruptible(&mb5_transfer.lock);
+	if (r)
+		return r;
+
+	while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
+		cpu_relax();
+
+	writeb(I2C_READ(slave), REQ_MB5_I2C_SLAVE_OP);
+	writeb(I2C_STOP_EN, REQ_MB5_I2C_HW_BITS);
+	writeb(reg, REQ_MB5_I2C_REG);
+
+	writel(MBOX_BIT(5), PRCM_MBOX_CPU_SET);
+	if (!wait_for_completion_timeout(&mb5_transfer.work,
+			msecs_to_jiffies(500))) {
+		pr_err("prcmu: prcmu_abb_read timed out.\n");
+		r = -EIO;
+		goto unlock_and_return;
+	}
+	r = ((mb5_transfer.ack.status == I2C_RD_OK) ? 0 : -EIO);
+	if (!r)
+		*value = mb5_transfer.ack.value;
+
+unlock_and_return:
+	mutex_unlock(&mb5_transfer.lock);
+	return r;
+}
+EXPORT_SYMBOL(prcmu_abb_read);
+
+/**
+ * prcmu_abb_write() - Write register value(s) to the ABB.
+ * @slave:	The I2C slave address.
+ * @reg:	The (start) register address.
+ * @value:	The value(s) to write.
+ * @size:	The number of registers to write.
+ *
+ * Reads register value(s) from the ABB.
+ * @size has to be 1 for the current firmware version.
+ */
+int prcmu_abb_write(u8 slave, u8 reg, u8 *value, u8 size)
+{
+	int r;
+
+	if (size != 1)
+		return -EINVAL;
+
+	r = mutex_lock_interruptible(&mb5_transfer.lock);
+	if (r)
+		return r;
+
+
+	while (readl(PRCM_MBOX_CPU_VAL) & MBOX_BIT(5))
+		cpu_relax();
+
+	writeb(I2C_WRITE(slave), REQ_MB5_I2C_SLAVE_OP);
+	writeb(I2C_STOP_EN, REQ_MB5_I2C_HW_BITS);
+	writeb(reg, REQ_MB5_I2C_REG);
+	writeb(*value, REQ_MB5_I2C_VAL);
+
+	writel(MBOX_BIT(5), PRCM_MBOX_CPU_SET);
+	if (!wait_for_completion_timeout(&mb5_transfer.work,
+			msecs_to_jiffies(500))) {
+		pr_err("prcmu: prcmu_abb_write timed out.\n");
+		r = -EIO;
+		goto unlock_and_return;
+	}
+	r = ((mb5_transfer.ack.status == I2C_WR_OK) ? 0 : -EIO);
+
+unlock_and_return:
+	mutex_unlock(&mb5_transfer.lock);
+	return r;
+}
+EXPORT_SYMBOL(prcmu_abb_write);
+
+static void read_mailbox_0(void)
+{
+	writel(MBOX_BIT(0), PRCM_ARM_IT1_CLEAR);
+}
+
+static void read_mailbox_1(void)
+{
+	writel(MBOX_BIT(1), PRCM_ARM_IT1_CLEAR);
+}
+
+static void read_mailbox_2(void)
+{
+	writel(MBOX_BIT(2), PRCM_ARM_IT1_CLEAR);
+}
+
+static void read_mailbox_3(void)
+{
+	writel(MBOX_BIT(3), PRCM_ARM_IT1_CLEAR);
+}
+
+static void read_mailbox_4(void)
+{
+	writel(MBOX_BIT(4), PRCM_ARM_IT1_CLEAR);
+}
+
+static void read_mailbox_5(void)
+{
+	mb5_transfer.ack.status = readb(ACK_MB5_I2C_STATUS);
+	mb5_transfer.ack.value = readb(ACK_MB5_I2C_VAL);
+	complete(&mb5_transfer.work);
+	writel(MBOX_BIT(5), PRCM_ARM_IT1_CLEAR);
+}
+
+static void read_mailbox_6(void)
+{
+	writel(MBOX_BIT(6), PRCM_ARM_IT1_CLEAR);
+}
+
+static void read_mailbox_7(void)
+{
+	writel(MBOX_BIT(7), PRCM_ARM_IT1_CLEAR);
+}
+
+static void (* const read_mailbox[NUM_MBOX])(void) = {
+	read_mailbox_0,
+	read_mailbox_1,
+	read_mailbox_2,
+	read_mailbox_3,
+	read_mailbox_4,
+	read_mailbox_5,
+	read_mailbox_6,
+	read_mailbox_7
+};
+
+static irqreturn_t prcmu_irq_handler(int irq, void *data)
+{
+	u32 bits;
+	u8 n;
+
+	bits = (readl(PRCM_ARM_IT1_VAL) & (MBOX_BIT(NUM_MBOX) - 1));
+	if (unlikely(!bits))
+		return IRQ_NONE;
+
+	for (n = 0; bits; n++) {
+		if (bits & MBOX_BIT(n)) {
+			bits -= MBOX_BIT(n);
+			read_mailbox[n]();
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static int __init prcmu_init(void)
+{
+	mutex_init(&mb5_transfer.lock);
+	init_completion(&mb5_transfer.work);
+
+	/* Clean up the mailbox interrupts after pre-kernel code. */
+	writel((MBOX_BIT(NUM_MBOX) - 1), PRCM_ARM_IT1_CLEAR);
+
+	return request_irq(IRQ_PRCMU, prcmu_irq_handler, 0, "prcmu", NULL);
+}
+
+arch_initcall(prcmu_init);
diff --git a/arch/arm/mach-ux500/ste-dma40-db5500.h b/arch/arm/mach-ux500/ste-dma40-db5500.h
new file mode 100644
index 0000000..cb2110c
--- /dev/null
+++ b/arch/arm/mach-ux500/ste-dma40-db5500.h
@@ -0,0 +1,135 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2010
+ *
+ * Author: Rabin Vincent <rabin.vincent@stericsson.com> for ST-Ericsson
+ * License terms: GNU General Public License (GPL) version 2
+ *
+ * DB5500-SoC-specific configuration for DMA40
+ */
+
+#ifndef STE_DMA40_DB5500_H
+#define STE_DMA40_DB5500_H
+
+#define DB5500_DMA_NR_DEV 64
+
+enum dma_src_dev_type {
+	DB5500_DMA_DEV0_SPI0_RX = 0,
+	DB5500_DMA_DEV1_SPI1_RX = 1,
+	DB5500_DMA_DEV2_SPI2_RX = 2,
+	DB5500_DMA_DEV3_SPI3_RX = 3,
+	DB5500_DMA_DEV4_USB_OTG_IEP_1_9 = 4,
+	DB5500_DMA_DEV5_USB_OTG_IEP_2_10 = 5,
+	DB5500_DMA_DEV6_USB_OTG_IEP_3_11 = 6,
+	DB5500_DMA_DEV7_IRDA_RFS = 7,
+	DB5500_DMA_DEV8_IRDA_FIFO_RX = 8,
+	DB5500_DMA_DEV9_MSP0_RX = 9,
+	DB5500_DMA_DEV10_MSP1_RX = 10,
+	DB5500_DMA_DEV11_MSP2_RX = 11,
+	DB5500_DMA_DEV12_UART0_RX = 12,
+	DB5500_DMA_DEV13_UART1_RX = 13,
+	DB5500_DMA_DEV14_UART2_RX = 14,
+	DB5500_DMA_DEV15_UART3_RX = 15,
+	DB5500_DMA_DEV16_USB_OTG_IEP_8 = 16,
+	DB5500_DMA_DEV17_USB_OTG_IEP_1_9 = 17,
+	DB5500_DMA_DEV18_USB_OTG_IEP_2_10 = 18,
+	DB5500_DMA_DEV19_USB_OTG_IEP_3_11 = 19,
+	DB5500_DMA_DEV20_USB_OTG_IEP_4_12 = 20,
+	DB5500_DMA_DEV21_USB_OTG_IEP_5_13 = 21,
+	DB5500_DMA_DEV22_USB_OTG_IEP_6_14 = 22,
+	DB5500_DMA_DEV23_USB_OTG_IEP_7_15 = 23,
+	DB5500_DMA_DEV24_SDMMC0_RX = 24,
+	DB5500_DMA_DEV25_SDMMC1_RX = 25,
+	DB5500_DMA_DEV26_SDMMC2_RX = 26,
+	DB5500_DMA_DEV27_SDMMC3_RX = 27,
+	DB5500_DMA_DEV28_SDMMC4_RX = 28,
+	/* 29 - 32 not used */
+	DB5500_DMA_DEV33_SDMMC0_RX = 33,
+	DB5500_DMA_DEV34_SDMMC1_RX = 34,
+	DB5500_DMA_DEV35_SDMMC2_RX = 35,
+	DB5500_DMA_DEV36_SDMMC3_RX = 36,
+	DB5500_DMA_DEV37_SDMMC4_RX = 37,
+	DB5500_DMA_DEV38_USB_OTG_IEP_8 = 38,
+	DB5500_DMA_DEV39_USB_OTG_IEP_1_9 = 39,
+	DB5500_DMA_DEV40_USB_OTG_IEP_2_10 = 40,
+	DB5500_DMA_DEV41_USB_OTG_IEP_3_11 = 41,
+	DB5500_DMA_DEV42_USB_OTG_IEP_4_12 = 42,
+	DB5500_DMA_DEV43_USB_OTG_IEP_5_13 = 43,
+	DB5500_DMA_DEV44_USB_OTG_IEP_6_14 = 44,
+	DB5500_DMA_DEV45_USB_OTG_IEP_7_15 = 45,
+	/* 46 not used */
+	DB5500_DMA_DEV47_MCDE_RX = 47,
+	DB5500_DMA_DEV48_CRYPTO1_RX = 48,
+	/* 49, 50 not used */
+	DB5500_DMA_DEV49_I2C1_RX = 51,
+	DB5500_DMA_DEV50_I2C3_RX = 52,
+	DB5500_DMA_DEV51_I2C2_RX = 53,
+	/* 54 - 60 not used */
+	DB5500_DMA_DEV61_CRYPTO0_RX = 61,
+	/* 62, 63 not used */
+};
+
+enum dma_dest_dev_type {
+	DB5500_DMA_DEV0_SPI0_TX = 0,
+	DB5500_DMA_DEV1_SPI1_TX = 1,
+	DB5500_DMA_DEV2_SPI2_TX = 2,
+	DB5500_DMA_DEV3_SPI3_TX = 3,
+	DB5500_DMA_DEV4_USB_OTG_OEP_1_9 = 4,
+	DB5500_DMA_DEV5_USB_OTG_OEP_2_10 = 5,
+	DB5500_DMA_DEV6_USB_OTG_OEP_3_11 = 6,
+	DB5500_DMA_DEV7_IRRC_TX = 7,
+	DB5500_DMA_DEV8_IRDA_FIFO_TX = 8,
+	DB5500_DMA_DEV9_MSP0_TX = 9,
+	DB5500_DMA_DEV10_MSP1_TX = 10,
+	DB5500_DMA_DEV11_MSP2_TX = 11,
+	DB5500_DMA_DEV12_UART0_TX = 12,
+	DB5500_DMA_DEV13_UART1_TX = 13,
+	DB5500_DMA_DEV14_UART2_TX = 14,
+	DB5500_DMA_DEV15_UART3_TX = 15,
+	DB5500_DMA_DEV16_USB_OTG_OEP_8 = 16,
+	DB5500_DMA_DEV17_USB_OTG_OEP_1_9 = 17,
+	DB5500_DMA_DEV18_USB_OTG_OEP_2_10 = 18,
+	DB5500_DMA_DEV19_USB_OTG_OEP_3_11 = 19,
+	DB5500_DMA_DEV20_USB_OTG_OEP_4_12 = 20,
+	DB5500_DMA_DEV21_USB_OTG_OEP_5_13 = 21,
+	DB5500_DMA_DEV22_USB_OTG_OEP_6_14 = 22,
+	DB5500_DMA_DEV23_USB_OTG_OEP_7_15 = 23,
+	DB5500_DMA_DEV24_SDMMC0_TX = 24,
+	DB5500_DMA_DEV25_SDMMC1_TX = 25,
+	DB5500_DMA_DEV26_SDMMC2_TX = 26,
+	DB5500_DMA_DEV27_SDMMC3_TX = 27,
+	DB5500_DMA_DEV28_SDMMC4_TX = 28,
+	/* 29 - 31 not used */
+	DB5500_DMA_DEV32_FSMC_TX = 32,
+	DB5500_DMA_DEV33_SDMMC0_TX = 33,
+	DB5500_DMA_DEV34_SDMMC1_TX = 34,
+	DB5500_DMA_DEV35_SDMMC2_TX = 35,
+	DB5500_DMA_DEV36_SDMMC3_TX = 36,
+	DB5500_DMA_DEV37_SDMMC4_TX = 37,
+	DB5500_DMA_DEV38_USB_OTG_OEP_8 = 38,
+	DB5500_DMA_DEV39_USB_OTG_OEP_1_9 = 39,
+	DB5500_DMA_DEV40_USB_OTG_OEP_2_10 = 40,
+	DB5500_DMA_DEV41_USB_OTG_OEP_3_11 = 41,
+	DB5500_DMA_DEV42_USB_OTG_OEP_4_12 = 42,
+	DB5500_DMA_DEV43_USB_OTG_OEP_5_13 = 43,
+	DB5500_DMA_DEV44_USB_OTG_OEP_6_14 = 44,
+	DB5500_DMA_DEV45_USB_OTG_OEP_7_15 = 45,
+	/* 46 not used */
+	DB5500_DMA_DEV47_STM_TX = 47,
+	DB5500_DMA_DEV48_CRYPTO1_TX = 48,
+	DB5500_DMA_DEV49_CRYPTO1_TX_HASH1_TX = 49,
+	DB5500_DMA_DEV50_HASH1_TX = 50,
+	DB5500_DMA_DEV51_I2C1_TX = 51,
+	DB5500_DMA_DEV52_I2C3_TX = 52,
+	DB5500_DMA_DEV53_I2C2_TX = 53,
+	/* 54, 55 not used */
+	DB5500_DMA_MEMCPY_TX_1 = 56,
+	DB5500_DMA_MEMCPY_TX_2 = 57,
+	DB5500_DMA_MEMCPY_TX_3 = 58,
+	DB5500_DMA_MEMCPY_TX_4 = 59,
+	DB5500_DMA_MEMCPY_TX_5 = 60,
+	DB5500_DMA_DEV61_CRYPTO0_TX = 61,
+	DB5500_DMA_DEV62_CRYPTO0_TX_HASH0_TX = 62,
+	DB5500_DMA_DEV63_HASH0_TX = 63,
+};
+
+#endif
diff --git a/arch/arm/mach-ux500/ste-dma40-db8500.h b/arch/arm/mach-ux500/ste-dma40-db8500.h
index 9d9d3797..a616419 100644
--- a/arch/arm/mach-ux500/ste-dma40-db8500.h
+++ b/arch/arm/mach-ux500/ste-dma40-db8500.h
@@ -10,145 +10,135 @@
 #ifndef STE_DMA40_DB8500_H
 #define STE_DMA40_DB8500_H
 
-#define STEDMA40_NR_DEV 64
+#define DB8500_DMA_NR_DEV 64
 
 enum dma_src_dev_type {
-	STEDMA40_DEV_SPI0_RX = 0,
-	STEDMA40_DEV_SD_MMC0_RX = 1,
-	STEDMA40_DEV_SD_MMC1_RX = 2,
-	STEDMA40_DEV_SD_MMC2_RX = 3,
-	STEDMA40_DEV_I2C1_RX = 4,
-	STEDMA40_DEV_I2C3_RX = 5,
-	STEDMA40_DEV_I2C2_RX = 6,
-	STEDMA40_DEV_I2C4_RX = 7, /* Only on V1 */
-	STEDMA40_DEV_SSP0_RX = 8,
-	STEDMA40_DEV_SSP1_RX = 9,
-	STEDMA40_DEV_MCDE_RX = 10,
-	STEDMA40_DEV_UART2_RX = 11,
-	STEDMA40_DEV_UART1_RX = 12,
-	STEDMA40_DEV_UART0_RX = 13,
-	STEDMA40_DEV_MSP2_RX = 14,
-	STEDMA40_DEV_I2C0_RX = 15,
-	STEDMA40_DEV_USB_OTG_IEP_8 = 16,
-	STEDMA40_DEV_USB_OTG_IEP_1_9 = 17,
-	STEDMA40_DEV_USB_OTG_IEP_2_10 = 18,
-	STEDMA40_DEV_USB_OTG_IEP_3_11 = 19,
-	STEDMA40_DEV_SLIM0_CH0_RX_HSI_RX_CH0 = 20,
-	STEDMA40_DEV_SLIM0_CH1_RX_HSI_RX_CH1 = 21,
-	STEDMA40_DEV_SLIM0_CH2_RX_HSI_RX_CH2 = 22,
-	STEDMA40_DEV_SLIM0_CH3_RX_HSI_RX_CH3 = 23,
-	STEDMA40_DEV_SRC_SXA0_RX_TX = 24,
-	STEDMA40_DEV_SRC_SXA1_RX_TX = 25,
-	STEDMA40_DEV_SRC_SXA2_RX_TX = 26,
-	STEDMA40_DEV_SRC_SXA3_RX_TX = 27,
-	STEDMA40_DEV_SD_MM2_RX = 28,
-	STEDMA40_DEV_SD_MM0_RX = 29,
-	STEDMA40_DEV_MSP1_RX = 30,
-	/*
-	 * This channel is either SlimBus or MSP,
-	 * never both at the same time.
-	 */
-	STEDMA40_SLIM0_CH0_RX = 31,
-	STEDMA40_DEV_MSP0_RX = 31,
-	STEDMA40_DEV_SD_MM1_RX = 32,
-	STEDMA40_DEV_SPI2_RX = 33,
-	STEDMA40_DEV_I2C3_RX2 = 34,
-	STEDMA40_DEV_SPI1_RX = 35,
-	STEDMA40_DEV_USB_OTG_IEP_4_12 = 36,
-	STEDMA40_DEV_USB_OTG_IEP_5_13 = 37,
-	STEDMA40_DEV_USB_OTG_IEP_6_14 = 38,
-	STEDMA40_DEV_USB_OTG_IEP_7_15 = 39,
-	STEDMA40_DEV_SPI3_RX = 40,
-	STEDMA40_DEV_SD_MM3_RX = 41,
-	STEDMA40_DEV_SD_MM4_RX = 42,
-	STEDMA40_DEV_SD_MM5_RX = 43,
-	STEDMA40_DEV_SRC_SXA4_RX_TX = 44,
-	STEDMA40_DEV_SRC_SXA5_RX_TX = 45,
-	STEDMA40_DEV_SRC_SXA6_RX_TX = 46,
-	STEDMA40_DEV_SRC_SXA7_RX_TX = 47,
-	STEDMA40_DEV_CAC1_RX = 48,
-	/* RX channels 49 and 50 are unused */
-	STEDMA40_DEV_MSHC_RX = 51,
-	STEDMA40_DEV_SLIM1_CH0_RX_HSI_RX_CH4 = 52,
-	STEDMA40_DEV_SLIM1_CH1_RX_HSI_RX_CH5 = 53,
-	STEDMA40_DEV_SLIM1_CH2_RX_HSI_RX_CH6 = 54,
-	STEDMA40_DEV_SLIM1_CH3_RX_HSI_RX_CH7 = 55,
-	/* RX channels 56 thru 60 are unused */
-	STEDMA40_DEV_CAC0_RX = 61,
-	/* RX channels 62 and 63 are unused */
+	DB8500_DMA_DEV0_SPI0_RX = 0,
+	DB8500_DMA_DEV1_SD_MMC0_RX = 1,
+	DB8500_DMA_DEV2_SD_MMC1_RX = 2,
+	DB8500_DMA_DEV3_SD_MMC2_RX = 3,
+	DB8500_DMA_DEV4_I2C1_RX = 4,
+	DB8500_DMA_DEV5_I2C3_RX = 5,
+	DB8500_DMA_DEV6_I2C2_RX = 6,
+	DB8500_DMA_DEV7_I2C4_RX = 7, /* Only on V1 and later */
+	DB8500_DMA_DEV8_SSP0_RX = 8,
+	DB8500_DMA_DEV9_SSP1_RX = 9,
+	DB8500_DMA_DEV10_MCDE_RX = 10,
+	DB8500_DMA_DEV11_UART2_RX = 11,
+	DB8500_DMA_DEV12_UART1_RX = 12,
+	DB8500_DMA_DEV13_UART0_RX = 13,
+	DB8500_DMA_DEV14_MSP2_RX = 14,
+	DB8500_DMA_DEV15_I2C0_RX = 15,
+	DB8500_DMA_DEV16_USB_OTG_IEP_7_15 = 16,
+	DB8500_DMA_DEV17_USB_OTG_IEP_6_14 = 17,
+	DB8500_DMA_DEV18_USB_OTG_IEP_5_13 = 18,
+	DB8500_DMA_DEV19_USB_OTG_IEP_4_12 = 19,
+	DB8500_DMA_DEV20_SLIM0_CH0_RX_HSI_RX_CH0 = 20,
+	DB8500_DMA_DEV21_SLIM0_CH1_RX_HSI_RX_CH1 = 21,
+	DB8500_DMA_DEV22_SLIM0_CH2_RX_HSI_RX_CH2 = 22,
+	DB8500_DMA_DEV23_SLIM0_CH3_RX_HSI_RX_CH3 = 23,
+	DB8500_DMA_DEV24_SRC_SXA0_RX_TX = 24,
+	DB8500_DMA_DEV25_SRC_SXA1_RX_TX = 25,
+	DB8500_DMA_DEV26_SRC_SXA2_RX_TX = 26,
+	DB8500_DMA_DEV27_SRC_SXA3_RX_TX = 27,
+	DB8500_DMA_DEV28_SD_MM2_RX = 28,
+	DB8500_DMA_DEV29_SD_MM0_RX = 29,
+	DB8500_DMA_DEV30_MSP1_RX = 30,
+	/* On DB8500v2, MSP3 RX replaces MSP1 RX */
+	DB8500_DMA_DEV30_MSP3_RX = 30,
+	DB8500_DMA_DEV31_MSP0_RX_SLIM0_CH0_RX = 31,
+	DB8500_DMA_DEV32_SD_MM1_RX = 32,
+	DB8500_DMA_DEV33_SPI2_RX = 33,
+	DB8500_DMA_DEV34_I2C3_RX2 = 34,
+	DB8500_DMA_DEV35_SPI1_RX = 35,
+	DB8500_DMA_DEV36_USB_OTG_IEP_3_11 = 36,
+	DB8500_DMA_DEV37_USB_OTG_IEP_2_10 = 37,
+	DB8500_DMA_DEV38_USB_OTG_IEP_1_9 = 38,
+	DB8500_DMA_DEV39_USB_OTG_IEP_8 = 39,
+	DB8500_DMA_DEV40_SPI3_RX = 40,
+	DB8500_DMA_DEV41_SD_MM3_RX = 41,
+	DB8500_DMA_DEV42_SD_MM4_RX = 42,
+	DB8500_DMA_DEV43_SD_MM5_RX = 43,
+	DB8500_DMA_DEV44_SRC_SXA4_RX_TX = 44,
+	DB8500_DMA_DEV45_SRC_SXA5_RX_TX = 45,
+	DB8500_DMA_DEV46_SLIM0_CH8_RX_SRC_SXA6_RX_TX = 46,
+	DB8500_DMA_DEV47_SLIM0_CH9_RX_SRC_SXA7_RX_TX = 47,
+	DB8500_DMA_DEV48_CAC1_RX = 48,
+	/* 49, 50 and 51 are not used */
+	DB8500_DMA_DEV52_SLIM0_CH4_RX_HSI_RX_CH4 = 52,
+	DB8500_DMA_DEV53_SLIM0_CH5_RX_HSI_RX_CH5 = 53,
+	DB8500_DMA_DEV54_SLIM0_CH6_RX_HSI_RX_CH6 = 54,
+	DB8500_DMA_DEV55_SLIM0_CH7_RX_HSI_RX_CH7 = 55,
+	/* 56, 57, 58, 59 and 60 are not used */
+	DB8500_DMA_DEV61_CAC0_RX = 61,
+	/* 62 and 63 are not used */
 };
 
 enum dma_dest_dev_type {
-	STEDMA40_DEV_SPI0_TX = 0,
-	STEDMA40_DEV_SD_MMC0_TX = 1,
-	STEDMA40_DEV_SD_MMC1_TX = 2,
-	STEDMA40_DEV_SD_MMC2_TX = 3,
-	STEDMA40_DEV_I2C1_TX = 4,
-	STEDMA40_DEV_I2C3_TX = 5,
-	STEDMA40_DEV_I2C2_TX = 6,
-	STEDMA50_DEV_I2C4_TX = 7, /* Only on V1 */
-	STEDMA40_DEV_SSP0_TX = 8,
-	STEDMA40_DEV_SSP1_TX = 9,
-	/* TX channel 10 is unused */
-	STEDMA40_DEV_UART2_TX = 11,
-	STEDMA40_DEV_UART1_TX = 12,
-	STEDMA40_DEV_UART0_TX= 13,
-	STEDMA40_DEV_MSP2_TX = 14,
-	STEDMA40_DEV_I2C0_TX = 15,
-	STEDMA40_DEV_USB_OTG_OEP_8 = 16,
-	STEDMA40_DEV_USB_OTG_OEP_1_9 = 17,
-	STEDMA40_DEV_USB_OTG_OEP_2_10= 18,
-	STEDMA40_DEV_USB_OTG_OEP_3_11 = 19,
-	STEDMA40_DEV_SLIM0_CH0_TX_HSI_TX_CH0 = 20,
-	STEDMA40_DEV_SLIM0_CH1_TX_HSI_TX_CH1 = 21,
-	STEDMA40_DEV_SLIM0_CH2_TX_HSI_TX_CH2 = 22,
-	STEDMA40_DEV_SLIM0_CH3_TX_HSI_TX_CH3 = 23,
-	STEDMA40_DEV_DST_SXA0_RX_TX = 24,
-	STEDMA40_DEV_DST_SXA1_RX_TX = 25,
-	STEDMA40_DEV_DST_SXA2_RX_TX = 26,
-	STEDMA40_DEV_DST_SXA3_RX_TX = 27,
-	STEDMA40_DEV_SD_MM2_TX = 28,
-	STEDMA40_DEV_SD_MM0_TX = 29,
-	STEDMA40_DEV_MSP1_TX = 30,
-	/*
-	 * This channel is either SlimBus or MSP,
-	 * never both at the same time.
-	 */
-	STEDMA40_SLIM0_CH0_TX = 31,
-	STEDMA40_DEV_MSP0_TX = 31,
-	STEDMA40_DEV_SD_MM1_TX = 32,
-	STEDMA40_DEV_SPI2_TX = 33,
-	/* Secondary I2C3 channel */
-	STEDMA40_DEV_I2C3_TX2 = 34,
-	STEDMA40_DEV_SPI1_TX = 35,
-	STEDMA40_DEV_USB_OTG_OEP_4_12 = 36,
-	STEDMA40_DEV_USB_OTG_OEP_5_13 = 37,
-	STEDMA40_DEV_USB_OTG_OEP_6_14 = 38,
-	STEDMA40_DEV_USB_OTG_OEP_7_15 = 39,
-	STEDMA40_DEV_SPI3_TX = 40,
-	STEDMA40_DEV_SD_MM3_TX = 41,
-	STEDMA40_DEV_SD_MM4_TX = 42,
-	STEDMA40_DEV_SD_MM5_TX = 43,
-	STEDMA40_DEV_DST_SXA4_RX_TX = 44,
-	STEDMA40_DEV_DST_SXA5_RX_TX = 45,
-	STEDMA40_DEV_DST_SXA6_RX_TX = 46,
-	STEDMA40_DEV_DST_SXA7_RX_TX = 47,
-	STEDMA40_DEV_CAC1_TX = 48,
-	STEDMA40_DEV_CAC1_TX_HAC1_TX = 49,
-	STEDMA40_DEV_HAC1_TX = 50,
-	STEDMA40_MEMCPY_TX_0 = 51,
-	STEDMA40_DEV_SLIM1_CH0_TX_HSI_TX_CH4 = 52,
-	STEDMA40_DEV_SLIM1_CH1_TX_HSI_TX_CH5 = 53,
-	STEDMA40_DEV_SLIM1_CH2_TX_HSI_TX_CH6 = 54,
-	STEDMA40_DEV_SLIM1_CH3_TX_HSI_TX_CH7 = 55,
-	STEDMA40_MEMCPY_TX_1 = 56,
-	STEDMA40_MEMCPY_TX_2 = 57,
-	STEDMA40_MEMCPY_TX_3 = 58,
-	STEDMA40_MEMCPY_TX_4 = 59,
-	STEDMA40_MEMCPY_TX_5 = 60,
-	STEDMA40_DEV_CAC0_TX = 61,
-	STEDMA40_DEV_CAC0_TX_HAC0_TX = 62,
-	STEDMA40_DEV_HAC0_TX = 63,
+	DB8500_DMA_DEV0_SPI0_TX = 0,
+	DB8500_DMA_DEV1_SD_MMC0_TX = 1,
+	DB8500_DMA_DEV2_SD_MMC1_TX = 2,
+	DB8500_DMA_DEV3_SD_MMC2_TX = 3,
+	DB8500_DMA_DEV4_I2C1_TX = 4,
+	DB8500_DMA_DEV5_I2C3_TX = 5,
+	DB8500_DMA_DEV6_I2C2_TX = 6,
+	DB8500_DMA_DEV7_I2C4_TX = 7, /* Only on V1 and later */
+	DB8500_DMA_DEV8_SSP0_TX = 8,
+	DB8500_DMA_DEV9_SSP1_TX = 9,
+	/* 10 is not used*/
+	DB8500_DMA_DEV11_UART2_TX = 11,
+	DB8500_DMA_DEV12_UART1_TX = 12,
+	DB8500_DMA_DEV13_UART0_TX = 13,
+	DB8500_DMA_DEV14_MSP2_TX = 14,
+	DB8500_DMA_DEV15_I2C0_TX = 15,
+	DB8500_DMA_DEV16_USB_OTG_OEP_7_15 = 16,
+	DB8500_DMA_DEV17_USB_OTG_OEP_6_14 = 17,
+	DB8500_DMA_DEV18_USB_OTG_OEP_5_13 = 18,
+	DB8500_DMA_DEV19_USB_OTG_OEP_4_12 = 19,
+	DB8500_DMA_DEV20_SLIM0_CH0_TX_HSI_TX_CH0 = 20,
+	DB8500_DMA_DEV21_SLIM0_CH1_TX_HSI_TX_CH1 = 21,
+	DB8500_DMA_DEV22_SLIM0_CH2_TX_HSI_TX_CH2 = 22,
+	DB8500_DMA_DEV23_SLIM0_CH3_TX_HSI_TX_CH3 = 23,
+	DB8500_DMA_DEV24_DST_SXA0_RX_TX = 24,
+	DB8500_DMA_DEV25_DST_SXA1_RX_TX = 25,
+	DB8500_DMA_DEV26_DST_SXA2_RX_TX = 26,
+	DB8500_DMA_DEV27_DST_SXA3_RX_TX = 27,
+	DB8500_DMA_DEV28_SD_MM2_TX = 28,
+	DB8500_DMA_DEV29_SD_MM0_TX = 29,
+	DB8500_DMA_DEV30_MSP1_TX = 30,
+	DB8500_DMA_DEV31_MSP0_TX_SLIM0_CH0_TX = 31,
+	DB8500_DMA_DEV32_SD_MM1_TX = 32,
+	DB8500_DMA_DEV33_SPI2_TX = 33,
+	DB8500_DMA_DEV34_I2C3_TX2 = 34,
+	DB8500_DMA_DEV35_SPI1_TX = 35,
+	DB8500_DMA_DEV36_USB_OTG_OEP_3_11 = 36,
+	DB8500_DMA_DEV37_USB_OTG_OEP_2_10 = 37,
+	DB8500_DMA_DEV38_USB_OTG_OEP_1_9 = 38,
+	DB8500_DMA_DEV39_USB_OTG_OEP_8 = 39,
+	DB8500_DMA_DEV40_SPI3_TX = 40,
+	DB8500_DMA_DEV41_SD_MM3_TX = 41,
+	DB8500_DMA_DEV42_SD_MM4_TX = 42,
+	DB8500_DMA_DEV43_SD_MM5_TX = 43,
+	DB8500_DMA_DEV44_DST_SXA4_RX_TX = 44,
+	DB8500_DMA_DEV45_DST_SXA5_RX_TX = 45,
+	DB8500_DMA_DEV46_SLIM0_CH8_TX_DST_SXA6_RX_TX = 46,
+	DB8500_DMA_DEV47_SLIM0_CH9_TX_DST_SXA7_RX_TX = 47,
+	DB8500_DMA_DEV48_CAC1_TX  = 48,
+	DB8500_DMA_DEV49_CAC1_TX_HAC1_TX = 49,
+	DB8500_DMA_DEV50_HAC1_TX = 50,
+	DB8500_DMA_MEMCPY_TX_0 = 51,
+	DB8500_DMA_DEV52_SLIM1_CH4_TX_HSI_TX_CH4 = 52,
+	DB8500_DMA_DEV53_SLIM1_CH5_TX_HSI_TX_CH5 = 53,
+	DB8500_DMA_DEV54_SLIM1_CH6_TX_HSI_TX_CH6 = 54,
+	DB8500_DMA_DEV55_SLIM1_CH7_TX_HSI_TX_CH7 = 55,
+	DB8500_DMA_MEMCPY_TX_1 = 56,
+	DB8500_DMA_MEMCPY_TX_2 = 57,
+	DB8500_DMA_MEMCPY_TX_3 = 58,
+	DB8500_DMA_MEMCPY_TX_4 = 59,
+	DB8500_DMA_MEMCPY_TX_5 = 60,
+	DB8500_DMA_DEV61_CAC0_TX = 61,
+	DB8500_DMA_DEV62_CAC0_TX_HAC0_TX = 62,
+	DB8500_DMA_DEV63_HAC0_TX = 63,
 };
 
 #endif
diff --git a/arch/arm/mach-versatile/include/mach/debug-macro.S b/arch/arm/mach-versatile/include/mach/debug-macro.S
index 6fea719..eb2cf7d 100644
--- a/arch/arm/mach-versatile/include/mach/debug-macro.S
+++ b/arch/arm/mach-versatile/include/mach/debug-macro.S
@@ -11,13 +11,11 @@
  *
 */
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx,      #0x10000000
-		movne	\rx,      #0xf1000000	@ virtual base
-		orr	\rx, \rx, #0x001F0000
-		orr	\rx, \rx, #0x00001000
+		.macro	addruart, rp, rv
+		mov	\rp,      #0x001F0000
+		orr	\rp, \rp, #0x00001000
+		orr	\rv, \rp, #0xf1000000	@ virtual base
+		orr	\rp, \rp,  #0x10000000	@ physical base
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-versatile/include/mach/vmalloc.h b/arch/arm/mach-versatile/include/mach/vmalloc.h
index 427e361..ebd8a25 100644
--- a/arch/arm/mach-versatile/include/mach/vmalloc.h
+++ b/arch/arm/mach-versatile/include/mach/vmalloc.h
@@ -18,4 +18,4 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#define VMALLOC_END		(PAGE_OFFSET + 0x18000000)
+#define VMALLOC_END		0xd8000000
diff --git a/arch/arm/mach-versatile/versatile_ab.c b/arch/arm/mach-versatile/versatile_ab.c
index bb8ec77..aa9730f 100644
--- a/arch/arm/mach-versatile/versatile_ab.c
+++ b/arch/arm/mach-versatile/versatile_ab.c
@@ -35,8 +35,6 @@
 
 MACHINE_START(VERSATILE_AB, "ARM-Versatile AB")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= 0x101f1000,
-	.io_pg_offst	= ((0xf11f1000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= versatile_map_io,
 	.init_irq	= versatile_init_irq,
diff --git a/arch/arm/mach-versatile/versatile_pb.c b/arch/arm/mach-versatile/versatile_pb.c
index 239cd30..bf46964 100644
--- a/arch/arm/mach-versatile/versatile_pb.c
+++ b/arch/arm/mach-versatile/versatile_pb.c
@@ -108,8 +108,6 @@
 
 MACHINE_START(VERSATILE_PB, "ARM-Versatile PB")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= 0x101f1000,
-	.io_pg_offst	= ((0xf11f1000) >> 18) & 0xfffc,
 	.boot_params	= 0x00000100,
 	.map_io		= versatile_map_io,
 	.init_irq	= versatile_init_irq,
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 71fb173..c2e405a 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -245,8 +245,6 @@
 }
 
 MACHINE_START(VEXPRESS, "ARM-Versatile Express CA9x4")
-	.phys_io	= V2M_UART0 & SECTION_MASK,
-	.io_pg_offst	= (__MMIO_P2V(V2M_UART0) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.map_io		= ct_ca9x4_map_io,
 	.init_irq	= ct_ca9x4_init_irq,
diff --git a/arch/arm/mach-vexpress/include/mach/debug-macro.S b/arch/arm/mach-vexpress/include/mach/debug-macro.S
index 5167e2a..050d65e 100644
--- a/arch/arm/mach-vexpress/include/mach/debug-macro.S
+++ b/arch/arm/mach-vexpress/include/mach/debug-macro.S
@@ -12,12 +12,10 @@
 
 #define DEBUG_LL_UART_OFFSET	0x00009000
 
-		.macro	addruart,rx,tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx,      #0x10000000
-		movne	\rx,      #0xf8000000	@ virtual base
-		orr	\rx, \rx, #DEBUG_LL_UART_OFFSET
+		.macro	addruart,rp,rv
+		mov	\rp, #DEBUG_LL_UART_OFFSET
+		orr	\rv, \rp, #0xf8000000	@ virtual base
+		orr	\rp, \rp, #0x10000000	@ physical base
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-vexpress/include/mach/smp.h b/arch/arm/mach-vexpress/include/mach/smp.h
index 72a9621..5a6da4f 100644
--- a/arch/arm/mach-vexpress/include/mach/smp.h
+++ b/arch/arm/mach-vexpress/include/mach/smp.h
@@ -2,14 +2,7 @@
 #define __MACH_SMP_H
 
 #include <asm/hardware/gic.h>
-
-#define hard_smp_processor_id()				\
-	({						\
-		unsigned int cpunum;			\
-		__asm__("mrc p15, 0, %0, c0, c0, 5"	\
-			: "=r" (cpunum));		\
-		cpunum &= 0x0F;				\
-	})
+#include <asm/smp_mpidr.h>
 
 /*
  * We use IRQ1 as the IPI
diff --git a/arch/arm/mach-w90x900/mach-nuc910evb.c b/arch/arm/mach-w90x900/mach-nuc910evb.c
index ec05bda..30fccde 100644
--- a/arch/arm/mach-w90x900/mach-nuc910evb.c
+++ b/arch/arm/mach-w90x900/mach-nuc910evb.c
@@ -34,8 +34,6 @@
 
 MACHINE_START(W90P910EVB, "W90P910EVB")
 	/* Maintainer: Wan ZongShun */
-	.phys_io	= W90X900_PA_UART,
-	.io_pg_offst	= (((u32)W90X900_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= 0,
 	.map_io		= nuc910evb_map_io,
 	.init_irq	= nuc900_init_irq,
diff --git a/arch/arm/mach-w90x900/mach-nuc950evb.c b/arch/arm/mach-w90x900/mach-nuc950evb.c
index 04d295f..590c99b 100644
--- a/arch/arm/mach-w90x900/mach-nuc950evb.c
+++ b/arch/arm/mach-w90x900/mach-nuc950evb.c
@@ -37,8 +37,6 @@
 
 MACHINE_START(W90P950EVB, "W90P950EVB")
 	/* Maintainer: Wan ZongShun */
-	.phys_io	= W90X900_PA_UART,
-	.io_pg_offst	= (((u32)W90X900_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= 0,
 	.map_io		= nuc950evb_map_io,
 	.init_irq	= nuc900_init_irq,
diff --git a/arch/arm/mach-w90x900/mach-nuc960evb.c b/arch/arm/mach-w90x900/mach-nuc960evb.c
index e3a46f1..e09c645 100644
--- a/arch/arm/mach-w90x900/mach-nuc960evb.c
+++ b/arch/arm/mach-w90x900/mach-nuc960evb.c
@@ -34,8 +34,6 @@
 
 MACHINE_START(W90N960EVB, "W90N960EVB")
 	/* Maintainer: Wan ZongShun */
-	.phys_io	= W90X900_PA_UART,
-	.io_pg_offst	= (((u32)W90X900_VA_UART) >> 18) & 0xfffc,
 	.boot_params	= 0,
 	.map_io		= nuc960evb_map_io,
 	.init_irq	= nuc900_init_irq,
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 86aa689..99fa688 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -21,18 +21,22 @@
 #define D_CACHE_LINE_SIZE	32
 #define BTB_FLUSH_SIZE		8
 
-#ifdef CONFIG_ARM_ERRATA_411920
 /*
- * Invalidate the entire I cache (this code is a workaround for the ARM1136
- * erratum 411920 - Invalidate Instruction Cache operation can fail. This
- * erratum is present in 1136, 1156 and 1176. It does not affect the MPCore.
+ *	v6_flush_icache_all()
  *
- * Registers:
- *   r0 - set to 0
- *   r1 - corrupted
+ *	Flush the whole I-cache.
+ *
+ *	ARM1136 erratum 411920 - Invalidate Instruction Cache operation can fail.
+ *	This erratum is present in 1136, 1156 and 1176. It does not affect the
+ *	MPCore.
+ *
+ *	Registers:
+ *	r0 - set to 0
+ *	r1 - corrupted
  */
-ENTRY(v6_icache_inval_all)
+ENTRY(v6_flush_icache_all)
 	mov	r0, #0
+#ifdef CONFIG_ARM_ERRATA_411920
 	mrs	r1, cpsr
 	cpsid	ifa				@ disable interrupts
 	mcr	p15, 0, r0, c7, c5, 0		@ invalidate entire I-cache
@@ -43,8 +47,11 @@
 	.rept	11				@ ARM Ltd recommends at least
 	nop					@ 11 NOPs
 	.endr
-	mov	pc, lr
+#else
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I-cache
 #endif
+	mov	pc, lr
+ENDPROC(v6_flush_icache_all)
 
 /*
  *	v6_flush_cache_all()
@@ -60,7 +67,7 @@
 #ifndef CONFIG_ARM_ERRATA_411920
 	mcr	p15, 0, r0, c7, c5, 0		@ I+BTB cache invalidate
 #else
-	b	v6_icache_inval_all
+	b	v6_flush_icache_all
 #endif
 #else
 	mcr	p15, 0, r0, c7, c15, 0		@ Cache clean+invalidate
@@ -138,7 +145,7 @@
 #ifndef CONFIG_ARM_ERRATA_411920
 	mcr	p15, 0, r0, c7, c5, 0		@ I+BTB cache invalidate
 #else
-	b	v6_icache_inval_all
+	b	v6_flush_icache_all
 #endif
 #else
 	mcr	p15, 0, r0, c7, c5, 6		@ invalidate BTB
@@ -312,6 +319,7 @@
 
 	.type	v6_cache_fns, #object
 ENTRY(v6_cache_fns)
+	.long	v6_flush_icache_all
 	.long	v6_flush_kern_cache_all
 	.long	v6_flush_user_cache_all
 	.long	v6_flush_user_cache_range
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 37c8157..a3ebf7a 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -18,6 +18,21 @@
 #include "proc-macros.S"
 
 /*
+ *	v7_flush_icache_all()
+ *
+ *	Flush the whole I-cache.
+ *
+ *	Registers:
+ *	r0 - set to 0
+ */
+ENTRY(v7_flush_icache_all)
+	mov	r0, #0
+	ALT_SMP(mcr	p15, 0, r0, c7, c1, 0)		@ invalidate I-cache inner shareable
+	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)		@ I+BTB cache invalidate
+	mov	pc, lr
+ENDPROC(v7_flush_icache_all)
+
+/*
  *	v7_flush_dcache_all()
  *
  *	Flush the whole D-cache.
@@ -91,11 +106,8 @@
  THUMB(	stmfd	sp!, {r4-r7, r9-r11, lr}	)
 	bl	v7_flush_dcache_all
 	mov	r0, #0
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r0, c7, c1, 0		@ invalidate I-cache inner shareable
-#else
-	mcr	p15, 0, r0, c7, c5, 0		@ I+BTB cache invalidate
-#endif
+	ALT_SMP(mcr	p15, 0, r0, c7, c1, 0)	@ invalidate I-cache inner shareable
+	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)	@ I+BTB cache invalidate
  ARM(	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
  THUMB(	ldmfd	sp!, {r4-r7, r9-r11, lr}	)
 	mov	pc, lr
@@ -171,11 +183,8 @@
 	cmp	r0, r1
 	blo	1b
 	mov	r0, #0
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r0, c7, c1, 6		@ invalidate BTB Inner Shareable
-#else
-	mcr	p15, 0, r0, c7, c5, 6		@ invalidate BTB
-#endif
+	ALT_SMP(mcr	p15, 0, r0, c7, c1, 6)	@ invalidate BTB Inner Shareable
+	ALT_UP(mcr	p15, 0, r0, c7, c5, 6)	@ invalidate BTB
 	dsb
 	isb
 	mov	pc, lr
@@ -309,6 +318,7 @@
 
 	.type	v7_cache_fns, #object
 ENTRY(v7_cache_fns)
+	.long	v7_flush_icache_all
 	.long	v7_flush_kern_cache_all
 	.long	v7_flush_user_cache_all
 	.long	v7_flush_user_cache_range
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index 598c51a..b806151 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -73,7 +73,7 @@
 {
 	void *kto = kmap_atomic(to, KM_USER1);
 
-	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
 		__flush_dcache_page(page_mapping(from), from);
 
 	spin_lock(&minicache_lock);
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index f55fa10..bdba6c6 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -79,7 +79,7 @@
 	unsigned int offset = CACHE_COLOUR(vaddr);
 	unsigned long kfrom, kto;
 
-	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
 		__flush_dcache_page(page_mapping(from), from);
 
 	/* FIXME: not highmem safe */
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 9920c0a..649bbcd 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -95,7 +95,7 @@
 {
 	void *kto = kmap_atomic(to, KM_USER1);
 
-	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
 		__flush_dcache_page(page_mapping(from), from);
 
 	spin_lock(&minicache_lock);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4bc43e5..e4dd064 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -523,6 +523,12 @@
 		outer_inv_range(paddr, paddr + size);
 
 	dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+
+	/*
+	 * Mark the D-cache clean for this page to avoid extra flushing.
+	 */
+	if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
+		set_bit(PG_dcache_clean, &page->flags);
 }
 EXPORT_SYMBOL(___dma_page_dev_to_cpu);
 
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 9b906de..8440d95 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -28,6 +28,7 @@
 
 static unsigned long shared_pte_mask = L_PTE_MT_BUFFERABLE;
 
+#if __LINUX_ARM_ARCH__ < 6
 /*
  * We take the easy way out of this problem - we make the
  * PTE uncacheable.  However, we leave the write buffer on.
@@ -141,7 +142,7 @@
  * a page table, or changing an existing PTE.  Basically, there are two
  * things that we need to take care of:
  *
- *  1. If PG_dcache_dirty is set for the page, we need to ensure
+ *  1. If PG_dcache_clean is not set for the page, we need to ensure
  *     that any cache entries for the kernels virtual memory
  *     range are written back to the page.
  *  2. If we have multiple shared mappings of the same space in
@@ -168,10 +169,8 @@
 		return;
 
 	mapping = page_mapping(page);
-#ifndef CONFIG_SMP
-	if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		__flush_dcache_page(mapping, page);
-#endif
 	if (mapping) {
 		if (cache_is_vivt())
 			make_coherent(mapping, vma, addr, ptep, pfn);
@@ -179,6 +178,7 @@
 			__flush_icache_all();
 	}
 }
+#endif	/* __LINUX_ARM_ARCH__ < 6 */
 
 /*
  * Check whether the write buffer has physical address aliasing
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 23b0b03..1e21e12 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -581,6 +581,19 @@
 	{ do_bad,		SIGBUS,  0,		"unknown 31"			   },
 };
 
+void __init
+hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
+		 int sig, int code, const char *name)
+{
+	if (nr < 0 || nr >= ARRAY_SIZE(ifsr_info))
+		BUG();
+
+	ifsr_info[nr].fn   = fn;
+	ifsr_info[nr].sig  = sig;
+	ifsr_info[nr].code = code;
+	ifsr_info[nr].name = name;
+}
+
 asmlinkage void __exception
 do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 {
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index c6844cb..391ffae 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -17,6 +17,7 @@
 #include <asm/smp_plat.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
+#include <asm/smp_plat.h>
 
 #include "mm.h"
 
@@ -39,6 +40,18 @@
 	    : "cc");
 }
 
+static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned long len)
+{
+	unsigned long colour = CACHE_COLOUR(vaddr);
+	unsigned long offset = vaddr & (PAGE_SIZE - 1);
+	unsigned long to;
+
+	set_pte_ext(TOP_PTE(ALIAS_FLUSH_START) + colour, pfn_pte(pfn, PAGE_KERNEL), 0);
+	to = ALIAS_FLUSH_START + (colour << PAGE_SHIFT) + offset;
+	flush_tlb_kernel_page(to);
+	flush_icache_range(to, to + len);
+}
+
 void flush_cache_mm(struct mm_struct *mm)
 {
 	if (cache_is_vivt()) {
@@ -89,16 +102,16 @@
 	if (vma->vm_flags & VM_EXEC && icache_is_vivt_asid_tagged())
 		__flush_icache_all();
 }
+
 #else
-#define flush_pfn_alias(pfn,vaddr)	do { } while (0)
+#define flush_pfn_alias(pfn,vaddr)		do { } while (0)
+#define flush_icache_alias(pfn,vaddr,len)	do { } while (0)
 #endif
 
-#ifdef CONFIG_SMP
 static void flush_ptrace_access_other(void *args)
 {
 	__flush_icache_all();
 }
-#endif
 
 static
 void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
@@ -118,15 +131,16 @@
 		return;
 	}
 
-	/* VIPT non-aliasing cache */
+	/* VIPT non-aliasing D-cache */
 	if (vma->vm_flags & VM_EXEC) {
 		unsigned long addr = (unsigned long)kaddr;
-		__cpuc_coherent_kern_range(addr, addr + len);
-#ifdef CONFIG_SMP
+		if (icache_is_vipt_aliasing())
+			flush_icache_alias(page_to_pfn(page), uaddr, len);
+		else
+			__cpuc_coherent_kern_range(addr, addr + len);
 		if (cache_ops_need_broadcast())
 			smp_call_function(flush_ptrace_access_other,
 					  NULL, 1);
-#endif
 	}
 }
 
@@ -215,6 +229,36 @@
 	flush_dcache_mmap_unlock(mapping);
 }
 
+#if __LINUX_ARM_ARCH__ >= 6
+void __sync_icache_dcache(pte_t pteval)
+{
+	unsigned long pfn;
+	struct page *page;
+	struct address_space *mapping;
+
+	if (!pte_present_user(pteval))
+		return;
+	if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
+		/* only flush non-aliasing VIPT caches for exec mappings */
+		return;
+	pfn = pte_pfn(pteval);
+	if (!pfn_valid(pfn))
+		return;
+
+	page = pfn_to_page(pfn);
+	if (cache_is_vipt_aliasing())
+		mapping = page_mapping(page);
+	else
+		mapping = NULL;
+
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+		__flush_dcache_page(mapping, page);
+	/* pte_exec() already checked above for non-aliasing VIPT cache */
+	if (cache_is_vipt_nonaliasing() || pte_exec(pteval))
+		__flush_icache_all();
+}
+#endif
+
 /*
  * Ensure cache coherency between kernel mapping and userspace mapping
  * of this page.
@@ -246,17 +290,16 @@
 
 	mapping = page_mapping(page);
 
-#ifndef CONFIG_SMP
-	if (!PageHighMem(page) && mapping && !mapping_mapped(mapping))
-		set_bit(PG_dcache_dirty, &page->flags);
-	else
-#endif
-	{
+	if (!cache_ops_need_broadcast() &&
+	    mapping && !mapping_mapped(mapping))
+		clear_bit(PG_dcache_clean, &page->flags);
+	else {
 		__flush_dcache_page(mapping, page);
 		if (mapping && cache_is_vivt())
 			__flush_dcache_aliases(mapping, page);
 		else if (mapping)
 			__flush_icache_all();
+		set_bit(PG_dcache_clean, &page->flags);
 	}
 }
 EXPORT_SYMBOL(flush_dcache_page);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 7185b00..7fd9b5e 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -150,6 +150,7 @@
 static void __init arm_bootmem_init(struct meminfo *mi,
 	unsigned long start_pfn, unsigned long end_pfn)
 {
+	struct memblock_region *reg;
 	unsigned int boot_pages;
 	phys_addr_t bitmap;
 	pg_data_t *pgdat;
@@ -180,13 +181,13 @@
 	/*
 	 * Reserve the memblock reserved regions in bootmem.
 	 */
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		phys_addr_t start = memblock_start_pfn(&memblock.reserved, i);
-		if (start >= start_pfn &&
-		    memblock_end_pfn(&memblock.reserved, i) <= end_pfn)
+	for_each_memblock(reserved, reg) {
+		phys_addr_t start = memblock_region_reserved_base_pfn(reg);
+		phys_addr_t end = memblock_region_reserved_end_pfn(reg);
+		if (start >= start_pfn && end <= end_pfn)
 			reserve_bootmem_node(pgdat, __pfn_to_phys(start),
-				memblock_size_bytes(&memblock.reserved, i),
-				BOOTMEM_DEFAULT);
+					     (end - start) << PAGE_SHIFT,
+					     BOOTMEM_DEFAULT);
 	}
 }
 
@@ -237,20 +238,7 @@
 #ifndef CONFIG_SPARSEMEM
 int pfn_valid(unsigned long pfn)
 {
-	struct memblock_region *mem = &memblock.memory;
-	unsigned int left = 0, right = mem->cnt;
-
-	do {
-		unsigned int mid = (right + left) / 2;
-
-		if (pfn < memblock_start_pfn(mem, mid))
-			right = mid;
-		else if (pfn >= memblock_end_pfn(mem, mid))
-			left = mid + 1;
-		else
-			return 1;
-	} while (left < right);
-	return 0;
+	return memblock_is_memory(pfn << PAGE_SHIFT);
 }
 EXPORT_SYMBOL(pfn_valid);
 
@@ -260,10 +248,11 @@
 #else
 static void arm_memory_present(void)
 {
-	int i;
-	for (i = 0; i < memblock.memory.cnt; i++)
-		memory_present(0, memblock_start_pfn(&memblock.memory, i),
-				  memblock_end_pfn(&memblock.memory, i));
+	struct memblock_region *reg;
+
+	for_each_memblock(memory, reg)
+		memory_present(0, memblock_region_memory_base_pfn(reg),
+			       memblock_region_memory_end_pfn(reg));
 }
 #endif
 
@@ -277,7 +266,7 @@
 
 	/* Register the kernel text, kernel data and initrd with memblock. */
 #ifdef CONFIG_XIP_KERNEL
-	memblock_reserve(__pa(_data), _end - _data);
+	memblock_reserve(__pa(_sdata), _end - _sdata);
 #else
 	memblock_reserve(__pa(_stext), _end - _stext);
 #endif
@@ -545,7 +534,7 @@
 
 			MLK_ROUNDUP(__init_begin, __init_end),
 			MLK_ROUNDUP(_text, _etext),
-			MLK_ROUNDUP(_data, _edata));
+			MLK_ROUNDUP(_sdata, _edata));
 
 #undef MLK
 #undef MLM
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 4f5b396..b0a9830 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -144,3 +144,25 @@
 {
 	return !(pfn + (size >> PAGE_SHIFT) > 0x00100000);
 }
+
+#ifdef CONFIG_STRICT_DEVMEM
+
+#include <linux/ioport.h>
+
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain
+ * address is valid. The argument is a physical page number.
+ * We mimic x86 here by disallowing access to system RAM as well as
+ * device-exclusive MMIO regions. This effectively disable read()/write()
+ * on /dev/mem.
+ */
+int devmem_is_allowed(unsigned long pfn)
+{
+	if (iomem_is_exclusive(pfn << PAGE_SHIFT))
+		return 0;
+	if (!page_is_ram(pfn))
+		return 1;
+	return 0;
+}
+
+#endif
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e8ed9dc..c32f731 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -310,9 +310,8 @@
 			cachepolicy = CPOLICY_WRITEBACK;
 		ecc_mask = 0;
 	}
-#ifdef CONFIG_SMP
-	cachepolicy = CPOLICY_WRITEALLOC;
-#endif
+	if (is_smp())
+		cachepolicy = CPOLICY_WRITEALLOC;
 
 	/*
 	 * Strip out features not present on earlier architectures.
@@ -406,13 +405,11 @@
 	cp = &cache_policies[cachepolicy];
 	vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
 
-#ifndef CONFIG_SMP
 	/*
 	 * Only use write-through for non-SMP systems
 	 */
-	if (cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH)
+	if (!is_smp() && cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH)
 		vecs_pgprot = cache_policies[CPOLICY_WRITETHROUGH].pte;
-#endif
 
 	/*
 	 * Enable CPU-specific coherency if supported.
@@ -436,22 +433,23 @@
 		mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 
-#ifdef CONFIG_SMP
-		/*
-		 * Mark memory with the "shared" attribute for SMP systems
-		 */
-		user_pgprot |= L_PTE_SHARED;
-		kern_pgprot |= L_PTE_SHARED;
-		vecs_pgprot |= L_PTE_SHARED;
-		mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
-		mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
-		mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
-		mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
-		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
-		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
-		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
-#endif
+		if (is_smp()) {
+			/*
+			 * Mark memory with the "shared" attribute
+			 * for SMP systems
+			 */
+			user_pgprot |= L_PTE_SHARED;
+			kern_pgprot |= L_PTE_SHARED;
+			vecs_pgprot |= L_PTE_SHARED;
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
+			mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
+			mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+			mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+			mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+		}
 	}
 
 	/*
@@ -829,8 +827,7 @@
 			 * rather difficult.
 			 */
 			reason = "with VIPT aliasing cache";
-#ifdef CONFIG_SMP
-		} else if (tlb_ops_need_broadcast()) {
+		} else if (is_smp() && tlb_ops_need_broadcast()) {
 			/*
 			 * kmap_high needs to occasionally flush TLB entries,
 			 * however, if the TLB entries need to be broadcast
@@ -840,7 +837,6 @@
 			 *   (must not be called with irqs off)
 			 */
 			reason = "without hardware TLB ops broadcasting";
-#endif
 		}
 		if (reason) {
 			printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 203a4e9..a6f5f84 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -430,7 +430,7 @@
 #endif /* CONFIG_MMU */
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm1020_setup, #function
 __arm1020_setup:
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index 1a511e7..afc06b9 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -412,7 +412,7 @@
 #endif /* CONFIG_MMU */
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm1020e_setup, #function
 __arm1020e_setup:
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 1ffa4eb..8915e0b 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -394,7 +394,7 @@
 #endif /* CONFIG_MMU */
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm1022_setup, #function
 __arm1022_setup:
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index 5697c34..ff446c5 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -384,7 +384,7 @@
 	mov	pc, lr
 
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm1026_setup, #function
 __arm1026_setup:
diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S
index 64e0b32..6a7be18 100644
--- a/arch/arm/mm/proc-arm6_7.S
+++ b/arch/arm/mm/proc-arm6_7.S
@@ -238,7 +238,7 @@
 		mcr	p15, 0, r1, c1, c0, 0		@ turn off MMU etc
 		mov	pc, r0
 
-		__INIT
+		__CPUINIT
 
 		.type	__arm6_setup, #function
 __arm6_setup:	mov	r0, #0
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index 9d96824..c285395 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -113,7 +113,7 @@
 		mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 		mov	pc, r0
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm710_setup, #function
 __arm710_setup:
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index 6c1a9ab..38b27dc 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -55,7 +55,7 @@
 	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
 	mov	pc, r0
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm740_setup, #function
 __arm740_setup:
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index 6a850db..0c9786d 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -46,7 +46,7 @@
 ENTRY(cpu_arm7tdmi_reset)
 		mov	pc, r0
 
-		__INIT
+		__CPUINIT
 
 		.type	__arm7tdmi_setup, #function
 __arm7tdmi_setup:
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 86f80aa..fecf570 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -375,7 +375,7 @@
 #endif
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm920_setup, #function
 __arm920_setup:
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index f76ce9b..e3cbf87 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -379,7 +379,7 @@
 #endif /* CONFIG_MMU */
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm922_setup, #function
 __arm922_setup:
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index 657bd3f..572424c 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -428,7 +428,7 @@
 #endif /* CONFIG_MMU */
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm925_setup, #function
 __arm925_setup:
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 73f1f3c..63d168b 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -389,7 +389,7 @@
 #endif
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm926_setup, #function
 __arm926_setup:
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index fffb061..f6a6282 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -264,7 +264,7 @@
 	.long	arm940_dma_unmap_area
 	.long	arm940_dma_flush_range
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm940_setup, #function
 __arm940_setup:
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 249a605..ea2e7f2 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -317,7 +317,7 @@
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__arm946_setup, #function
 __arm946_setup:
diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S
index db47566..db67e31 100644
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -46,7 +46,7 @@
 ENTRY(cpu_arm9tdmi_reset)
 		mov	pc, r0
 
-		__INIT
+		__CPUINIT
 
 		.type	__arm9tdmi_setup, #function
 __arm9tdmi_setup:
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index 7803fdf..7c9ad62 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -134,7 +134,7 @@
 #endif
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__fa526_setup, #function
 __fa526_setup:
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index b304d01..578da69 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -494,7 +494,7 @@
 #endif
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__feroceon_setup, #function
 __feroceon_setup:
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 5f6892f..4458ee6 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -338,7 +338,7 @@
 	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__mohawk_setup, #function
 __mohawk_setup:
diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S
index a201eb0..5aa8d59 100644
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -156,7 +156,7 @@
 #endif
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__sa110_setup, #function
 __sa110_setup:
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 7ddc480..2ac4e6f 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -169,7 +169,7 @@
 #endif
 	mov	pc, lr
 
-	__INIT
+	__CPUINIT
 
 	.type	__sa1100_setup, #function
 __sa1100_setup:
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 22aac85..59a7e1f 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -30,13 +30,10 @@
 #define TTB_RGN_WT	(2 << 3)
 #define TTB_RGN_WB	(3 << 3)
 
-#ifndef CONFIG_SMP
-#define TTB_FLAGS	TTB_RGN_WBWA
-#define PMD_FLAGS	PMD_SECT_WB
-#else
-#define TTB_FLAGS	TTB_RGN_WBWA|TTB_S
-#define PMD_FLAGS	PMD_SECT_WBWA|PMD_SECT_S
-#endif
+#define TTB_FLAGS_UP	TTB_RGN_WBWA
+#define PMD_FLAGS_UP	PMD_SECT_WB
+#define TTB_FLAGS_SMP	TTB_RGN_WBWA|TTB_S
+#define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
 
 ENTRY(cpu_v6_proc_init)
 	mov	pc, lr
@@ -97,7 +94,8 @@
 #ifdef CONFIG_MMU
 	mov	r2, #0
 	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
-	orr	r0, r0, #TTB_FLAGS
+	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 	mcr	p15, 0, r2, c7, c10, 4		@ drain write buffer
 	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
@@ -137,7 +135,7 @@
 
 	.align
 
-	__INIT
+	__CPUINIT
 
 /*
  *	__v6_setup
@@ -156,9 +154,11 @@
  */
 __v6_setup:
 #ifdef CONFIG_SMP
-	mrc	p15, 0, r0, c1, c0, 1		@ Enable SMP/nAMP mode
+	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)	@ Enable SMP/nAMP mode
+	ALT_UP(nop)
 	orr	r0, r0, #0x20
-	mcr	p15, 0, r0, c1, c0, 1
+	ALT_SMP(mcr	p15, 0, r0, c1, c0, 1)
+	ALT_UP(nop)
 #endif
 
 	mov	r0, #0
@@ -169,7 +169,8 @@
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r0, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r0, c2, c0, 2		@ TTB control register
-	orr	r4, r4, #TTB_FLAGS
+	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
 #endif /* CONFIG_MMU */
 	adr	r5, v6_crval
@@ -192,6 +193,8 @@
 v6_crval:
 	crval	clear=0x01e0fb7f, mmuset=0x00c0387d, ucset=0x00c0187c
 
+	__INITDATA
+
 	.type	v6_processor_functions, #object
 ENTRY(v6_processor_functions)
 	.word	v6_early_abort
@@ -205,6 +208,8 @@
 	.word	cpu_v6_set_pte_ext
 	.size	v6_processor_functions, . - v6_processor_functions
 
+	.section ".rodata"
+
 	.type	cpu_arch_name, #object
 cpu_arch_name:
 	.asciz	"armv6"
@@ -225,10 +230,16 @@
 __v6_proc_info:
 	.long	0x0007b000
 	.long	0x0007f000
-	.long   PMD_TYPE_SECT | \
+	ALT_SMP(.long \
+		PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | \
-		PMD_FLAGS
+		PMD_FLAGS_SMP)
+	ALT_UP(.long \
+		PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS_UP)
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
@@ -249,10 +260,16 @@
 __pj4_v6_proc_info:
 	.long	0x560f5810
 	.long	0xff0ffff0
-	.long   PMD_TYPE_SECT | \
+	ALT_SMP(.long \
+		PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | \
-		PMD_FLAGS
+		PMD_FLAGS_SMP)
+	ALT_UP(.long \
+		PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS_UP)
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 197f21b..53cbe22 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -30,15 +30,13 @@
 #define TTB_IRGN_WT	((1 << 0) | (0 << 6))
 #define TTB_IRGN_WB	((1 << 0) | (1 << 6))
 
-#ifndef CONFIG_SMP
 /* PTWs cacheable, inner WB not shareable, outer WB not shareable */
-#define TTB_FLAGS	TTB_IRGN_WB|TTB_RGN_OC_WB
-#define PMD_FLAGS	PMD_SECT_WB
-#else
+#define TTB_FLAGS_UP	TTB_IRGN_WB|TTB_RGN_OC_WB
+#define PMD_FLAGS_UP	PMD_SECT_WB
+
 /* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
-#define TTB_FLAGS	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
-#define PMD_FLAGS	PMD_SECT_WBWA|PMD_SECT_S
-#endif
+#define TTB_FLAGS_SMP	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
+#define PMD_FLAGS_SMP	PMD_SECT_WBWA|PMD_SECT_S
 
 ENTRY(cpu_v7_proc_init)
 	mov	pc, lr
@@ -105,7 +103,8 @@
 #ifdef CONFIG_MMU
 	mov	r2, #0
 	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
-	orr	r0, r0, #TTB_FLAGS
+	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 #ifdef CONFIG_ARM_ERRATA_430973
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 #endif
@@ -169,7 +168,7 @@
 	.ascii	"ARMv7 Processor"
 	.align
 
-	__INIT
+	__CPUINIT
 
 /*
  *	__v7_setup
@@ -188,7 +187,8 @@
  */
 __v7_ca9mp_setup:
 #ifdef CONFIG_SMP
-	mrc	p15, 0, r0, c1, c0, 1
+	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)
+	ALT_UP(mov	r0, #(1 << 6))		@ fake it for UP
 	tst	r0, #(1 << 6)			@ SMP/nAMP mode enabled?
 	orreq	r0, r0, #(1 << 6) | (1 << 0)	@ Enable SMP/nAMP mode and
 	mcreq	p15, 0, r0, c1, c0, 1		@ TLB ops broadcasting
@@ -270,7 +270,8 @@
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r10, c2, c0, 2		@ TTB control register
-	orr	r4, r4, #TTB_FLAGS
+	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
 	mov	r10, #0x1f			@ domains 0, 1 = manager
 	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
@@ -332,6 +333,8 @@
 __v7_setup_stack:
 	.space	4 * 11				@ 11 registers
 
+	__INITDATA
+
 	.type	v7_processor_functions, #object
 ENTRY(v7_processor_functions)
 	.word	v7_early_abort
@@ -345,6 +348,8 @@
 	.word	cpu_v7_set_pte_ext
 	.size	v7_processor_functions, . - v7_processor_functions
 
+	.section ".rodata"
+
 	.type	cpu_arch_name, #object
 cpu_arch_name:
 	.asciz	"armv7"
@@ -362,10 +367,16 @@
 __v7_ca9mp_proc_info:
 	.long	0x410fc090		@ Required ID value
 	.long	0xff0ffff0		@ Mask for ID
-	.long   PMD_TYPE_SECT | \
+	ALT_SMP(.long \
+		PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | \
-		PMD_FLAGS
+		PMD_FLAGS_SMP)
+	ALT_UP(.long \
+		PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS_UP)
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
@@ -388,10 +399,16 @@
 __v7_proc_info:
 	.long	0x000f0000		@ Required ID value
 	.long	0x000f0000		@ Mask for ID
-	.long   PMD_TYPE_SECT | \
+	ALT_SMP(.long \
+		PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | \
-		PMD_FLAGS
+		PMD_FLAGS_SMP)
+	ALT_UP(.long \
+		PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS_UP)
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 361a51e..cad07e4 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -404,7 +404,7 @@
 
 	.align
 
-	__INIT
+	__CPUINIT
 
 	.type	__xsc3_setup, #function
 __xsc3_setup:
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 1407597..cb245ed 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -506,7 +506,7 @@
 
 	.align
 
-	__INIT
+	__CPUINIT
 
 	.type	__xscale_setup, #function
 __xscale_setup:
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index f3f288a..53cd5b4 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -13,6 +13,7 @@
  */
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/tlbflush.h>
@@ -41,20 +42,15 @@
 	orr	r0, r3, r0, lsl #PAGE_SHIFT	@ Create initial MVA
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r0, c8, c3, 1		@ TLB invalidate U MVA (shareable) 
-#else
-	mcr	p15, 0, r0, c8, c7, 1		@ TLB invalidate U MVA
-#endif
+	ALT_SMP(mcr	p15, 0, r0, c8, c3, 1)	@ TLB invalidate U MVA (shareable)
+	ALT_UP(mcr	p15, 0, r0, c8, c7, 1)	@ TLB invalidate U MVA
+
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
 	mov	ip, #0
-#ifdef CONFIG_SMP
-	mcr	p15, 0, ip, c7, c1, 6		@ flush BTAC/BTB Inner Shareable
-#else
-	mcr	p15, 0, ip, c7, c5, 6		@ flush BTAC/BTB
-#endif
+	ALT_SMP(mcr	p15, 0, ip, c7, c1, 6)	@ flush BTAC/BTB Inner Shareable
+	ALT_UP(mcr	p15, 0, ip, c7, c5, 6)	@ flush BTAC/BTB
 	dsb
 	mov	pc, lr
 ENDPROC(v7wbi_flush_user_tlb_range)
@@ -74,20 +70,14 @@
 	mov	r0, r0, lsl #PAGE_SHIFT
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r0, c8, c3, 1		@ TLB invalidate U MVA (shareable)
-#else
-	mcr	p15, 0, r0, c8, c7, 1		@ TLB invalidate U MVA
-#endif
+	ALT_SMP(mcr	p15, 0, r0, c8, c3, 1)	@ TLB invalidate U MVA (shareable)
+	ALT_UP(mcr	p15, 0, r0, c8, c7, 1)	@ TLB invalidate U MVA
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
 	mov	r2, #0
-#ifdef CONFIG_SMP
-	mcr	p15, 0, r2, c7, c1, 6		@ flush BTAC/BTB Inner Shareable
-#else
-	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
-#endif
+	ALT_SMP(mcr	p15, 0, r2, c7, c1, 6)	@ flush BTAC/BTB Inner Shareable
+	ALT_UP(mcr	p15, 0, r2, c7, c5, 6)	@ flush BTAC/BTB
 	dsb
 	isb
 	mov	pc, lr
@@ -99,5 +89,6 @@
 ENTRY(v7wbi_tlb_fns)
 	.long	v7wbi_flush_user_tlb_range
 	.long	v7wbi_flush_kern_tlb_range
-	.long	v7wbi_tlb_flags
+	ALT_SMP(.long	v7wbi_tlb_flags_smp)
+	ALT_UP(.long	v7wbi_tlb_flags_up)
 	.size	v7wbi_tlb_fns, . - v7wbi_tlb_fns
diff --git a/arch/arm/oprofile/Makefile b/arch/arm/oprofile/Makefile
index e666eaf..b2215c6 100644
--- a/arch/arm/oprofile/Makefile
+++ b/arch/arm/oprofile/Makefile
@@ -6,4 +6,8 @@
 		oprofilefs.o oprofile_stats.o \
 		timer_int.o )
 
+ifeq ($(CONFIG_HW_PERF_EVENTS),y)
+DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o)
+endif
+
 oprofile-y				:= $(DRIVER_OBJS) common.o
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index 72e09eb..8aa9744 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -25,139 +25,10 @@
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_HW_PERF_EVENTS
-/*
- * Per performance monitor configuration as set via oprofilefs.
- */
-struct op_counter_config {
-	unsigned long count;
-	unsigned long enabled;
-	unsigned long event;
-	unsigned long unit_mask;
-	unsigned long kernel;
-	unsigned long user;
-	struct perf_event_attr attr;
-};
-
-static int op_arm_enabled;
-static DEFINE_MUTEX(op_arm_mutex);
-
-static struct op_counter_config *counter_config;
-static struct perf_event **perf_events[nr_cpumask_bits];
-static int perf_num_counters;
-
-/*
- * Overflow callback for oprofile.
- */
-static void op_overflow_handler(struct perf_event *event, int unused,
-			struct perf_sample_data *data, struct pt_regs *regs)
+char *op_name_from_perf_id(void)
 {
-	int id;
-	u32 cpu = smp_processor_id();
+	enum arm_perf_pmu_ids id = armpmu_get_pmu_id();
 
-	for (id = 0; id < perf_num_counters; ++id)
-		if (perf_events[cpu][id] == event)
-			break;
-
-	if (id != perf_num_counters)
-		oprofile_add_sample(regs, id);
-	else
-		pr_warning("oprofile: ignoring spurious overflow "
-				"on cpu %u\n", cpu);
-}
-
-/*
- * Called by op_arm_setup to create perf attributes to mirror the oprofile
- * settings in counter_config. Attributes are created as `pinned' events and
- * so are permanently scheduled on the PMU.
- */
-static void op_perf_setup(void)
-{
-	int i;
-	u32 size = sizeof(struct perf_event_attr);
-	struct perf_event_attr *attr;
-
-	for (i = 0; i < perf_num_counters; ++i) {
-		attr = &counter_config[i].attr;
-		memset(attr, 0, size);
-		attr->type		= PERF_TYPE_RAW;
-		attr->size		= size;
-		attr->config		= counter_config[i].event;
-		attr->sample_period	= counter_config[i].count;
-		attr->pinned		= 1;
-	}
-}
-
-static int op_create_counter(int cpu, int event)
-{
-	int ret = 0;
-	struct perf_event *pevent;
-
-	if (!counter_config[event].enabled || (perf_events[cpu][event] != NULL))
-		return ret;
-
-	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
-						  cpu, -1,
-						  op_overflow_handler);
-
-	if (IS_ERR(pevent)) {
-		ret = PTR_ERR(pevent);
-	} else if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
-		perf_event_release_kernel(pevent);
-		pr_warning("oprofile: failed to enable event %d "
-				"on CPU %d\n", event, cpu);
-		ret = -EBUSY;
-	} else {
-		perf_events[cpu][event] = pevent;
-	}
-
-	return ret;
-}
-
-static void op_destroy_counter(int cpu, int event)
-{
-	struct perf_event *pevent = perf_events[cpu][event];
-
-	if (pevent) {
-		perf_event_release_kernel(pevent);
-		perf_events[cpu][event] = NULL;
-	}
-}
-
-/*
- * Called by op_arm_start to create active perf events based on the
- * perviously configured attributes.
- */
-static int op_perf_start(void)
-{
-	int cpu, event, ret = 0;
-
-	for_each_online_cpu(cpu) {
-		for (event = 0; event < perf_num_counters; ++event) {
-			ret = op_create_counter(cpu, event);
-			if (ret)
-				goto out;
-		}
-	}
-
-out:
-	return ret;
-}
-
-/*
- * Called by op_arm_stop at the end of a profiling run.
- */
-static void op_perf_stop(void)
-{
-	int cpu, event;
-
-	for_each_online_cpu(cpu)
-		for (event = 0; event < perf_num_counters; ++event)
-			op_destroy_counter(cpu, event);
-}
-
-
-static char *op_name_from_perf_id(enum arm_perf_pmu_ids id)
-{
 	switch (id) {
 	case ARM_PERF_PMU_ID_XSCALE1:
 		return "arm/xscale1";
@@ -176,116 +47,6 @@
 	}
 }
 
-static int op_arm_create_files(struct super_block *sb, struct dentry *root)
-{
-	unsigned int i;
-
-	for (i = 0; i < perf_num_counters; i++) {
-		struct dentry *dir;
-		char buf[4];
-
-		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
-		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
-		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
-	}
-
-	return 0;
-}
-
-static int op_arm_setup(void)
-{
-	spin_lock(&oprofilefs_lock);
-	op_perf_setup();
-	spin_unlock(&oprofilefs_lock);
-	return 0;
-}
-
-static int op_arm_start(void)
-{
-	int ret = -EBUSY;
-
-	mutex_lock(&op_arm_mutex);
-	if (!op_arm_enabled) {
-		ret = 0;
-		op_perf_start();
-		op_arm_enabled = 1;
-	}
-	mutex_unlock(&op_arm_mutex);
-	return ret;
-}
-
-static void op_arm_stop(void)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled)
-		op_perf_stop();
-	op_arm_enabled = 0;
-	mutex_unlock(&op_arm_mutex);
-}
-
-#ifdef CONFIG_PM
-static int op_arm_suspend(struct platform_device *dev, pm_message_t state)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled)
-		op_perf_stop();
-	mutex_unlock(&op_arm_mutex);
-	return 0;
-}
-
-static int op_arm_resume(struct platform_device *dev)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled && op_perf_start())
-		op_arm_enabled = 0;
-	mutex_unlock(&op_arm_mutex);
-	return 0;
-}
-
-static struct platform_driver oprofile_driver = {
-	.driver		= {
-		.name		= "arm-oprofile",
-	},
-	.resume		= op_arm_resume,
-	.suspend	= op_arm_suspend,
-};
-
-static struct platform_device *oprofile_pdev;
-
-static int __init init_driverfs(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&oprofile_driver);
-	if (ret)
-		goto out;
-
-	oprofile_pdev =	platform_device_register_simple(
-				oprofile_driver.driver.name, 0, NULL, 0);
-	if (IS_ERR(oprofile_pdev)) {
-		ret = PTR_ERR(oprofile_pdev);
-		platform_driver_unregister(&oprofile_driver);
-	}
-
-out:
-	return ret;
-}
-
-static void  exit_driverfs(void)
-{
-	platform_device_unregister(oprofile_pdev);
-	platform_driver_unregister(&oprofile_driver);
-}
-#else
-static int __init init_driverfs(void) { return 0; }
-#define exit_driverfs() do { } while (0)
-#endif /* CONFIG_PM */
-
 static int report_trace(struct stackframe *frame, void *d)
 {
 	unsigned int *depth = d;
@@ -350,74 +111,14 @@
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-	int cpu, ret = 0;
-
-	perf_num_counters = armpmu_get_max_events();
-
-	counter_config = kcalloc(perf_num_counters,
-			sizeof(struct op_counter_config), GFP_KERNEL);
-
-	if (!counter_config) {
-		pr_info("oprofile: failed to allocate %d "
-				"counters\n", perf_num_counters);
-		return -ENOMEM;
-	}
-
-	ret = init_driverfs();
-	if (ret) {
-		kfree(counter_config);
-		counter_config = NULL;
-		return ret;
-	}
-
-	for_each_possible_cpu(cpu) {
-		perf_events[cpu] = kcalloc(perf_num_counters,
-				sizeof(struct perf_event *), GFP_KERNEL);
-		if (!perf_events[cpu]) {
-			pr_info("oprofile: failed to allocate %d perf events "
-					"for cpu %d\n", perf_num_counters, cpu);
-			while (--cpu >= 0)
-				kfree(perf_events[cpu]);
-			return -ENOMEM;
-		}
-	}
-
 	ops->backtrace		= arm_backtrace;
-	ops->create_files	= op_arm_create_files;
-	ops->setup		= op_arm_setup;
-	ops->start		= op_arm_start;
-	ops->stop		= op_arm_stop;
-	ops->shutdown		= op_arm_stop;
-	ops->cpu_type		= op_name_from_perf_id(armpmu_get_pmu_id());
 
-	if (!ops->cpu_type)
-		ret = -ENODEV;
-	else
-		pr_info("oprofile: using %s\n", ops->cpu_type);
-
-	return ret;
+	return oprofile_perf_init(ops);
 }
 
-void oprofile_arch_exit(void)
+void __exit oprofile_arch_exit(void)
 {
-	int cpu, id;
-	struct perf_event *event;
-
-	if (*perf_events) {
-		for_each_possible_cpu(cpu) {
-			for (id = 0; id < perf_num_counters; ++id) {
-				event = perf_events[cpu][id];
-				if (event != NULL)
-					perf_event_release_kernel(event);
-			}
-			kfree(perf_events[cpu]);
-		}
-	}
-
-	if (counter_config) {
-		kfree(counter_config);
-		exit_driverfs();
-	}
+	oprofile_perf_exit();
 }
 #else
 int __init oprofile_arch_init(struct oprofile_operations *ops)
@@ -425,5 +126,5 @@
 	pr_info("oprofile: hardware counters not available\n");
 	return -ENODEV;
 }
-void oprofile_arch_exit(void) {}
+void __exit oprofile_arch_exit(void) {}
 #endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/arch/arm/plat-mxc/Kconfig b/arch/arm/plat-mxc/Kconfig
index 6785db4..64e3a64 100644
--- a/arch/arm/plat-mxc/Kconfig
+++ b/arch/arm/plat-mxc/Kconfig
@@ -92,6 +92,18 @@
 	  data/address de-multiplexing and decode, signal level shift,
 	  interrupt control and various board functions.
 
+config HAVE_EPIT
+	bool
+
+config MXC_USE_EPIT
+	bool "Use EPIT instead of GPT"
+	depends on HAVE_EPIT
+	help
+	  Use EPIT as the system timer on systems that have it. Normally you
+	  don't have a reason to do so as the EPIT has the same features and
+	  uses the same clocks as the GPT. Anyway, on some systems the GPT
+	  may be in use for other purposes.
+
 config MXC_ULPI
 	bool
 
@@ -110,4 +122,8 @@
 config ARCH_MXC_AUDMUX_V2
 	bool
 
+config IRAM_ALLOC
+	bool
+	select GENERIC_ALLOCATOR
+
 endif
diff --git a/arch/arm/plat-mxc/Makefile b/arch/arm/plat-mxc/Makefile
index 78d405e..06875b4 100644
--- a/arch/arm/plat-mxc/Makefile
+++ b/arch/arm/plat-mxc/Makefile
@@ -10,9 +10,11 @@
 
 obj-$(CONFIG_IMX_HAVE_IOMUX_V1) += iomux-v1.o
 obj-$(CONFIG_ARCH_MXC_IOMUX_V3) += iomux-v3.o
+obj-$(CONFIG_IRAM_ALLOC) += iram_alloc.o
 obj-$(CONFIG_MXC_PWM)  += pwm.o
 obj-$(CONFIG_USB_EHCI_MXC) += ehci.o
 obj-$(CONFIG_MXC_ULPI) += ulpi.o
+obj-$(CONFIG_MXC_USE_EPIT) += epit.o
 obj-$(CONFIG_ARCH_MXC_AUDMUX_V1) += audmux-v1.o
 obj-$(CONFIG_ARCH_MXC_AUDMUX_V2) += audmux-v2.o
 obj-$(CONFIG_MXC_DEBUG_BOARD) += 3ds_debugboard.o
diff --git a/arch/arm/plat-mxc/audmux-v2.c b/arch/arm/plat-mxc/audmux-v2.c
index f9e7cdb..0be1ac7 100644
--- a/arch/arm/plat-mxc/audmux-v2.c
+++ b/arch/arm/plat-mxc/audmux-v2.c
@@ -137,6 +137,7 @@
 static const struct file_operations audmux_debugfs_fops = {
 	.open = audmux_open_file,
 	.read = audmux_read_file,
+	.llseek = default_llseek,
 };
 
 static void audmux_debugfs_init(void)
@@ -186,7 +187,13 @@
 static int mxc_audmux_v2_init(void)
 {
 	int ret;
-
+#if defined(CONFIG_ARCH_MX5)
+	if (cpu_is_mx51()) {
+		audmux_base = MX51_IO_ADDRESS(MX51_AUDMUX_BASE_ADDR);
+		ret = 0;
+		return ret;
+	}
+#endif
 #if defined(CONFIG_ARCH_MX3)
 	if (cpu_is_mx31())
 		audmux_base = MX31_IO_ADDRESS(MX31_AUDMUX_BASE_ADDR);
diff --git a/arch/arm/plat-mxc/devices/Kconfig b/arch/arm/plat-mxc/devices/Kconfig
index 9ab784b..4047994 100644
--- a/arch/arm/plat-mxc/devices/Kconfig
+++ b/arch/arm/plat-mxc/devices/Kconfig
@@ -1,3 +1,10 @@
+config IMX_HAVE_PLATFORM_ESDHC
+	bool
+
+config IMX_HAVE_PLATFORM_FEC
+	bool
+	default y if ARCH_MX25 || SOC_IMX27 || ARCH_MX35 || ARCH_MX51
+
 config IMX_HAVE_PLATFORM_FLEXCAN
 	select HAVE_CAN_FLEXCAN
 	bool
@@ -5,6 +12,9 @@
 config IMX_HAVE_PLATFORM_IMX_I2C
 	bool
 
+config IMX_HAVE_PLATFORM_IMX_SSI
+	bool
+
 config IMX_HAVE_PLATFORM_IMX_UART
 	bool
 
diff --git a/arch/arm/plat-mxc/devices/Makefile b/arch/arm/plat-mxc/devices/Makefile
index 347da51..0a3c1f0 100644
--- a/arch/arm/plat-mxc/devices/Makefile
+++ b/arch/arm/plat-mxc/devices/Makefile
@@ -1,8 +1,9 @@
-ifdef CONFIG_CAN_FLEXCAN
-# the ifdef can be removed once the flexcan driver has been merged
-obj-$(CONFIG_IMX_HAVE_PLATFORM_FLEXCAN) +=  platform-flexcan.o
-endif
+obj-$(CONFIG_IMX_HAVE_PLATFORM_ESDHC) += platform-esdhc.o
+obj-$(CONFIG_IMX_HAVE_PLATFORM_FEC) += platform-fec.o
+obj-$(CONFIG_IMX_HAVE_PLATFORM_FLEXCAN) += platform-flexcan.o
+obj-y += platform-imx-dma.o
 obj-$(CONFIG_IMX_HAVE_PLATFORM_IMX_I2C) += platform-imx-i2c.o
+obj-$(CONFIG_IMX_HAVE_PLATFORM_IMX_SSI) += platform-imx-ssi.o
 obj-$(CONFIG_IMX_HAVE_PLATFORM_IMX_UART) += platform-imx-uart.o
 obj-$(CONFIG_IMX_HAVE_PLATFORM_MXC_NAND) += platform-mxc_nand.o
 obj-$(CONFIG_IMX_HAVE_PLATFORM_SPI_IMX) +=  platform-spi_imx.o
diff --git a/arch/arm/plat-mxc/devices/platform-esdhc.c b/arch/arm/plat-mxc/devices/platform-esdhc.c
new file mode 100644
index 0000000..2605bfa
--- /dev/null
+++ b/arch/arm/plat-mxc/devices/platform-esdhc.c
@@ -0,0 +1,71 @@
+/*
+ * Copyright (C) 2010 Pengutronix, Wolfram Sang <w.sang@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+
+#include <mach/hardware.h>
+#include <mach/devices-common.h>
+#include <mach/esdhc.h>
+
+#define imx_esdhc_imx_data_entry_single(soc, _id, hwid) \
+	{								\
+		.id = _id,						\
+		.iobase = soc ## _ESDHC ## hwid ## _BASE_ADDR,	\
+		.irq = soc ## _INT_ESDHC ## hwid,			\
+	}
+
+#define imx_esdhc_imx_data_entry(soc, id, hwid)	\
+	[id] = imx_esdhc_imx_data_entry_single(soc, id, hwid)
+
+#ifdef CONFIG_ARCH_MX25
+const struct imx_esdhc_imx_data imx25_esdhc_data[] __initconst = {
+#define imx25_esdhc_data_entry(_id, _hwid)				\
+	imx_esdhc_imx_data_entry(MX25, _id, _hwid)
+	imx25_esdhc_data_entry(0, 1),
+	imx25_esdhc_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_ARCH_MX25 */
+
+#ifdef CONFIG_ARCH_MX35
+const struct imx_esdhc_imx_data imx35_esdhc_data[] __initconst = {
+#define imx35_esdhc_data_entry(_id, _hwid)                           \
+	imx_esdhc_imx_data_entry(MX35, _id, _hwid)
+	imx35_esdhc_data_entry(0, 1),
+	imx35_esdhc_data_entry(1, 2),
+	imx35_esdhc_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_ARCH_MX35 */
+
+#ifdef CONFIG_ARCH_MX51
+const struct imx_esdhc_imx_data imx51_esdhc_data[] __initconst = {
+#define imx51_esdhc_data_entry(_id, _hwid)				\
+	imx_esdhc_imx_data_entry(MX51, _id, _hwid)
+	imx51_esdhc_data_entry(0, 1),
+	imx51_esdhc_data_entry(1, 2),
+	imx51_esdhc_data_entry(2, 3),
+	imx51_esdhc_data_entry(3, 4),
+};
+#endif /* ifdef CONFIG_ARCH_MX51 */
+
+struct platform_device *__init imx_add_esdhc(
+		const struct imx_esdhc_imx_data *data,
+		const struct esdhc_platform_data *pdata)
+{
+	struct resource res[] = {
+		{
+			.start = data->iobase,
+			.end = data->iobase + SZ_16K - 1,
+			.flags = IORESOURCE_MEM,
+		}, {
+			.start = data->irq,
+			.end = data->irq,
+			.flags = IORESOURCE_IRQ,
+		},
+	};
+
+	return imx_add_platform_device("sdhci-esdhc-imx", data->id, res,
+			ARRAY_SIZE(res), pdata, sizeof(*pdata));
+}
diff --git a/arch/arm/plat-mxc/devices/platform-fec.c b/arch/arm/plat-mxc/devices/platform-fec.c
new file mode 100644
index 0000000..11d087f
--- /dev/null
+++ b/arch/arm/plat-mxc/devices/platform-fec.c
@@ -0,0 +1,58 @@
+/*
+ * Copyright (C) 2010 Pengutronix
+ * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+#include <asm/sizes.h>
+#include <mach/hardware.h>
+#include <mach/devices-common.h>
+
+#define imx_fec_data_entry_single(soc)					\
+	{								\
+		.iobase = soc ## _FEC_BASE_ADDR,			\
+		.irq = soc ## _INT_FEC,					\
+	}
+
+#ifdef CONFIG_ARCH_MX25
+const struct imx_fec_data imx25_fec_data __initconst =
+	imx_fec_data_entry_single(MX25);
+#endif /* ifdef CONFIG_ARCH_MX25 */
+
+#ifdef CONFIG_SOC_IMX27
+const struct imx_fec_data imx27_fec_data __initconst =
+	imx_fec_data_entry_single(MX27);
+#endif /* ifdef CONFIG_SOC_IMX27 */
+
+#ifdef CONFIG_ARCH_MX35
+const struct imx_fec_data imx35_fec_data __initconst =
+	imx_fec_data_entry_single(MX35);
+#endif
+
+#ifdef CONFIG_ARCH_MX51
+const struct imx_fec_data imx51_fec_data __initconst =
+	imx_fec_data_entry_single(MX51);
+#endif
+
+struct platform_device *__init imx_add_fec(
+		const struct imx_fec_data *data,
+		const struct fec_platform_data *pdata)
+{
+	struct resource res[] = {
+		{
+			.start = data->iobase,
+			.end = data->iobase + SZ_4K,
+			.flags = IORESOURCE_MEM,
+		}, {
+			.start = data->irq,
+			.end = data->irq,
+			.flags = IORESOURCE_IRQ,
+		},
+	};
+
+	return imx_add_platform_device("fec", 0 /* -1? */,
+			res, ARRAY_SIZE(res),
+			pdata, sizeof(*pdata));
+}
diff --git a/arch/arm/plat-mxc/devices/platform-imx-dma.c b/arch/arm/plat-mxc/devices/platform-imx-dma.c
new file mode 100644
index 0000000..02d9890
--- /dev/null
+++ b/arch/arm/plat-mxc/devices/platform-imx-dma.c
@@ -0,0 +1,129 @@
+/*
+ * Copyright (C) 2010 Pengutronix
+ * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/init.h>
+
+#include <mach/hardware.h>
+#include <mach/devices-common.h>
+#ifdef SDMA_IS_MERGED
+#include <mach/sdma.h>
+#else
+struct sdma_platform_data {
+	int sdma_version;
+	char *cpu_name;
+	int to_version;
+};
+#endif
+
+struct imx_imx_sdma_data {
+	resource_size_t iobase;
+	resource_size_t irq;
+	struct sdma_platform_data pdata;
+};
+
+#define imx_imx_sdma_data_entry_single(soc, _sdma_version, _cpu_name, _to_version)\
+	{								\
+		.iobase = soc ## _SDMA ## _BASE_ADDR,			\
+		.irq = soc ## _INT_SDMA,				\
+		.pdata = {						\
+			.sdma_version = _sdma_version,			\
+			.cpu_name = _cpu_name,				\
+			.to_version = _to_version,			\
+		},							\
+	}
+
+#ifdef CONFIG_ARCH_MX25
+const struct imx_imx_sdma_data imx25_imx_sdma_data __initconst =
+	imx_imx_sdma_data_entry_single(MX25, 1, "imx25", 0);
+#endif /* ifdef CONFIG_ARCH_MX25 */
+
+#ifdef CONFIG_ARCH_MX31
+struct imx_imx_sdma_data imx31_imx_sdma_data __initdata =
+	imx_imx_sdma_data_entry_single(MX31, 1, "imx31", 0);
+#endif /* ifdef CONFIG_ARCH_MX31 */
+
+#ifdef CONFIG_ARCH_MX35
+struct imx_imx_sdma_data imx35_imx_sdma_data __initdata =
+	imx_imx_sdma_data_entry_single(MX35, 2, "imx35", 0);
+#endif /* ifdef CONFIG_ARCH_MX35 */
+
+#ifdef CONFIG_ARCH_MX51
+const struct imx_imx_sdma_data imx51_imx_sdma_data __initconst =
+	imx_imx_sdma_data_entry_single(MX51, 2, "imx51", 0);
+#endif /* ifdef CONFIG_ARCH_MX51 */
+
+static struct platform_device __init __maybe_unused *imx_add_imx_sdma(
+		const struct imx_imx_sdma_data *data)
+{
+	struct resource res[] = {
+		{
+			.start = data->iobase,
+			.end = data->iobase + SZ_4K - 1,
+			.flags = IORESOURCE_MEM,
+		}, {
+			.start = data->irq,
+			.end = data->irq,
+			.flags = IORESOURCE_IRQ,
+		},
+	};
+
+	return imx_add_platform_device("imx-sdma", -1,
+			res, ARRAY_SIZE(res),
+			&data->pdata, sizeof(data->pdata));
+}
+
+static struct platform_device __init __maybe_unused *imx_add_imx_dma(void)
+{
+	return imx_add_platform_device("imx-dma", -1, NULL, 0, NULL, 0);
+}
+
+static int __init imxXX_add_imx_dma(void)
+{
+	struct platform_device *ret;
+
+#if defined(CONFIG_SOC_IMX21) || defined(CONFIG_SOC_IMX27)
+	if (cpu_is_mx21() || cpu_is_mx27())
+		ret = imx_add_imx_dma();
+	else
+#endif
+
+#if defined(CONFIG_ARCH_MX25)
+	if (cpu_is_mx25())
+		ret = imx_add_imx_sdma(&imx25_imx_sdma_data);
+	else
+#endif
+
+#if defined(CONFIG_ARCH_MX31)
+	if (cpu_is_mx31()) {
+		imx31_imx_sdma_data.pdata.to_version = mx31_revision() >> 4;
+		ret = imx_add_imx_sdma(&imx31_imx_sdma_data);
+	} else
+#endif
+
+#if defined(CONFIG_ARCH_MX35)
+	if (cpu_is_mx35()) {
+		imx35_imx_sdma_data.pdata.to_version = mx35_revision() >> 4;
+		ret = imx_add_imx_sdma(&imx35_imx_sdma_data);
+	} else
+#endif
+
+#if defined(CONFIG_ARCH_MX51)
+	if (cpu_is_mx51())
+		ret = imx_add_imx_sdma(&imx51_imx_sdma_data);
+	else
+#endif
+		ret = ERR_PTR(-ENODEV);
+
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
+	return 0;
+}
+arch_initcall(imxXX_add_imx_dma);
diff --git a/arch/arm/plat-mxc/devices/platform-imx-i2c.c b/arch/arm/plat-mxc/devices/platform-imx-i2c.c
index d0af9f7..6795884 100644
--- a/arch/arm/plat-mxc/devices/platform-imx-i2c.c
+++ b/arch/arm/plat-mxc/devices/platform-imx-i2c.c
@@ -6,24 +6,95 @@
  * the terms of the GNU General Public License version 2 as published by the
  * Free Software Foundation.
  */
+#include <mach/hardware.h>
 #include <mach/devices-common.h>
 
-struct platform_device *__init imx_add_imx_i2c(int id,
-		resource_size_t iobase, resource_size_t iosize, int irq,
+#define imx_imx_i2c_data_entry_single(soc, _id, _hwid, _size)		\
+	{								\
+		.id = _id,						\
+		.iobase = soc ## _I2C ## _hwid ## _BASE_ADDR,		\
+		.iosize = _size,					\
+		.irq = soc ## _INT_I2C ## _hwid,			\
+	}
+
+#define imx_imx_i2c_data_entry(soc, _id, _hwid, _size)			\
+	[_id] = imx_imx_i2c_data_entry_single(soc, _id, _hwid, _size)
+
+#ifdef CONFIG_SOC_IMX1
+const struct imx_imx_i2c_data imx1_imx_i2c_data __initconst =
+	imx_imx_i2c_data_entry_single(MX1, 0, , SZ_4K);
+#endif /* ifdef CONFIG_SOC_IMX1 */
+
+#ifdef CONFIG_SOC_IMX21
+const struct imx_imx_i2c_data imx21_imx_i2c_data __initconst =
+	imx_imx_i2c_data_entry_single(MX21, 0, , SZ_4K);
+#endif /* ifdef CONFIG_SOC_IMX21 */
+
+#ifdef CONFIG_ARCH_MX25
+const struct imx_imx_i2c_data imx25_imx_i2c_data[] __initconst = {
+#define imx25_imx_i2c_data_entry(_id, _hwid)				\
+	imx_imx_i2c_data_entry(MX25, _id, _hwid, SZ_16K)
+	imx25_imx_i2c_data_entry(0, 1),
+	imx25_imx_i2c_data_entry(1, 2),
+	imx25_imx_i2c_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_ARCH_MX25 */
+
+#ifdef CONFIG_SOC_IMX27
+const struct imx_imx_i2c_data imx27_imx_i2c_data[] __initconst = {
+#define imx27_imx_i2c_data_entry(_id, _hwid)				\
+	imx_imx_i2c_data_entry(MX27, _id, _hwid, SZ_4K)
+	imx27_imx_i2c_data_entry(0, 1),
+	imx27_imx_i2c_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_SOC_IMX27 */
+
+#ifdef CONFIG_ARCH_MX31
+const struct imx_imx_i2c_data imx31_imx_i2c_data[] __initconst = {
+#define imx31_imx_i2c_data_entry(_id, _hwid)				\
+	imx_imx_i2c_data_entry(MX31, _id, _hwid, SZ_4K)
+	imx31_imx_i2c_data_entry(0, 1),
+	imx31_imx_i2c_data_entry(1, 2),
+	imx31_imx_i2c_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_ARCH_MX31 */
+
+#ifdef CONFIG_ARCH_MX35
+const struct imx_imx_i2c_data imx35_imx_i2c_data[] __initconst = {
+#define imx35_imx_i2c_data_entry(_id, _hwid)				\
+	imx_imx_i2c_data_entry(MX35, _id, _hwid, SZ_4K)
+	imx35_imx_i2c_data_entry(0, 1),
+	imx35_imx_i2c_data_entry(1, 2),
+	imx35_imx_i2c_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_ARCH_MX35 */
+
+#ifdef CONFIG_ARCH_MX51
+const struct imx_imx_i2c_data imx51_imx_i2c_data[] __initconst = {
+#define imx51_imx_i2c_data_entry(_id, _hwid)				\
+	imx_imx_i2c_data_entry(MX51, _id, _hwid, SZ_4K)
+	imx51_imx_i2c_data_entry(0, 1),
+	imx51_imx_i2c_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_ARCH_MX51 */
+
+struct platform_device *__init imx_add_imx_i2c(
+		const struct imx_imx_i2c_data *data,
 		const struct imxi2c_platform_data *pdata)
 {
 	struct resource res[] = {
 		{
-			.start = iobase,
-			.end = iobase + iosize - 1,
+			.start = data->iobase,
+			.end = data->iobase + data->iosize - 1,
 			.flags = IORESOURCE_MEM,
 		}, {
-			.start = irq,
-			.end = irq,
+			.start = data->irq,
+			.end = data->irq,
 			.flags = IORESOURCE_IRQ,
 		},
 	};
 
-	return imx_add_platform_device("imx-i2c", id, res, ARRAY_SIZE(res),
+	return imx_add_platform_device("imx-i2c", data->id,
+			res, ARRAY_SIZE(res),
 			pdata, sizeof(*pdata));
 }
diff --git a/arch/arm/plat-mxc/devices/platform-imx-ssi.c b/arch/arm/plat-mxc/devices/platform-imx-ssi.c
new file mode 100644
index 0000000..38a7a0b
--- /dev/null
+++ b/arch/arm/plat-mxc/devices/platform-imx-ssi.c
@@ -0,0 +1,107 @@
+/*
+ * Copyright (C) 2010 Pengutronix
+ * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+#include <mach/hardware.h>
+#include <mach/devices-common.h>
+
+#define imx_imx_ssi_data_entry(soc, _id, _hwid, _size)			\
+	[_id] = {							\
+		.id = _id,						\
+		.iobase = soc ## _SSI ## _hwid ## _BASE_ADDR,		\
+		.iosize = _size,					\
+		.irq = soc ## _INT_SSI ## _hwid,			\
+		.dmatx0 = soc ## _DMA_REQ_SSI ## _hwid ## _TX0,		\
+		.dmarx0 = soc ## _DMA_REQ_SSI ## _hwid ## _RX0,		\
+		.dmatx1 = soc ## _DMA_REQ_SSI ## _hwid ## _TX1,		\
+		.dmarx1 = soc ## _DMA_REQ_SSI ## _hwid ## _RX1,		\
+	}
+
+#ifdef CONFIG_SOC_IMX21
+const struct imx_imx_ssi_data imx21_imx_ssi_data[] __initconst = {
+#define imx21_imx_ssi_data_entry(_id, _hwid)				\
+	imx_imx_ssi_data_entry(MX21, _id, _hwid, SZ_4K)
+	imx21_imx_ssi_data_entry(0, 1),
+	imx21_imx_ssi_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_SOC_IMX21 */
+
+#ifdef CONFIG_ARCH_MX25
+const struct imx_imx_ssi_data imx25_imx_ssi_data[] __initconst = {
+#define imx25_imx_ssi_data_entry(_id, _hwid)				\
+	imx_imx_ssi_data_entry(MX25, _id, _hwid, SZ_4K)
+	imx25_imx_ssi_data_entry(0, 1),
+	imx25_imx_ssi_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_ARCH_MX25 */
+
+#ifdef CONFIG_SOC_IMX27
+const struct imx_imx_ssi_data imx27_imx_ssi_data[] __initconst = {
+#define imx27_imx_ssi_data_entry(_id, _hwid)				\
+	imx_imx_ssi_data_entry(MX27, _id, _hwid, SZ_4K)
+	imx27_imx_ssi_data_entry(0, 1),
+	imx27_imx_ssi_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_SOC_IMX27 */
+
+#ifdef CONFIG_ARCH_MX31
+const struct imx_imx_ssi_data imx31_imx_ssi_data[] __initconst = {
+#define imx31_imx_ssi_data_entry(_id, _hwid)				\
+	imx_imx_ssi_data_entry(MX31, _id, _hwid, SZ_4K)
+	imx31_imx_ssi_data_entry(0, 1),
+	imx31_imx_ssi_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_ARCH_MX31 */
+
+#ifdef CONFIG_ARCH_MX35
+const struct imx_imx_ssi_data imx35_imx_ssi_data[] __initconst = {
+#define imx35_imx_ssi_data_entry(_id, _hwid)				\
+	imx_imx_ssi_data_entry(MX35, _id, _hwid, SZ_4K)
+	imx35_imx_ssi_data_entry(0, 1),
+	imx35_imx_ssi_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_ARCH_MX35 */
+
+#ifdef CONFIG_ARCH_MX51
+const struct imx_imx_ssi_data imx51_imx_ssi_data[] __initconst = {
+#define imx51_imx_ssi_data_entry(_id, _hwid)				\
+	imx_imx_ssi_data_entry(MX51, _id, _hwid, SZ_4K)
+	imx51_imx_ssi_data_entry(0, 1),
+	imx51_imx_ssi_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_ARCH_MX51 */
+
+struct platform_device *__init imx_add_imx_ssi(
+		const struct imx_imx_ssi_data *data,
+		const struct imx_ssi_platform_data *pdata)
+{
+	struct resource res[] = {
+		{
+			.start = data->iobase,
+			.end = data->iobase + data->iosize - 1,
+			.flags = IORESOURCE_MEM,
+		}, {
+			.start = data->irq,
+			.end = data->irq,
+			.flags = IORESOURCE_IRQ,
+		},
+#define DMARES(_name) {							\
+	.name = #_name,							\
+	.start = data->dma ## _name,					\
+	.end = data->dma ## _name,					\
+	.flags = IORESOURCE_DMA,					\
+}
+		DMARES(tx0),
+		DMARES(rx0),
+		DMARES(tx1),
+		DMARES(rx1),
+	};
+
+	return imx_add_platform_device("imx-ssi", data->id,
+			res, ARRAY_SIZE(res),
+			pdata, sizeof(*pdata));
+}
diff --git a/arch/arm/plat-mxc/devices/platform-imx-uart.c b/arch/arm/plat-mxc/devices/platform-imx-uart.c
index fa3dff1..2039640 100644
--- a/arch/arm/plat-mxc/devices/platform-imx-uart.c
+++ b/arch/arm/plat-mxc/devices/platform-imx-uart.c
@@ -6,55 +6,148 @@
  * the terms of the GNU General Public License version 2 as published by the
  * Free Software Foundation.
  */
+#include <mach/hardware.h>
 #include <mach/devices-common.h>
 
-struct platform_device *__init imx_add_imx_uart_3irq(int id,
-		resource_size_t iobase, resource_size_t iosize,
-		resource_size_t irqrx, resource_size_t irqtx,
-		resource_size_t irqrts,
+#define imx_imx_uart_3irq_data_entry(soc, _id, _hwid, _size)		\
+	[_id] = {							\
+		.id = _id,						\
+		.iobase = soc ## _UART ## _hwid ## _BASE_ADDR,		\
+		.iosize = _size,					\
+		.irqrx = soc ## _INT_UART ## _hwid ## RX,		\
+		.irqtx = soc ## _INT_UART ## _hwid ## TX,		\
+		.irqrts = soc ## _INT_UART ## _hwid ## RTS,		\
+	}
+
+#define imx_imx_uart_1irq_data_entry(soc, _id, _hwid, _size)		\
+	[_id] = {							\
+		.id = _id,						\
+		.iobase = soc ## _UART ## _hwid ## _BASE_ADDR,		\
+		.iosize = _size,					\
+		.irq = soc ## _INT_UART ## _hwid,			\
+	}
+
+#ifdef CONFIG_SOC_IMX1
+const struct imx_imx_uart_3irq_data imx1_imx_uart_data[] __initconst = {
+#define imx1_imx_uart_data_entry(_id, _hwid)				\
+	imx_imx_uart_3irq_data_entry(MX1, _id, _hwid, 0xd0)
+	imx1_imx_uart_data_entry(0, 1),
+	imx1_imx_uart_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_SOC_IMX1 */
+
+#ifdef CONFIG_SOC_IMX21
+const struct imx_imx_uart_1irq_data imx21_imx_uart_data[] __initconst = {
+#define imx21_imx_uart_data_entry(_id, _hwid)				\
+	imx_imx_uart_1irq_data_entry(MX21, _id, _hwid, SZ_4K)
+	imx21_imx_uart_data_entry(0, 1),
+	imx21_imx_uart_data_entry(1, 2),
+	imx21_imx_uart_data_entry(2, 3),
+	imx21_imx_uart_data_entry(3, 4),
+};
+#endif
+
+#ifdef CONFIG_ARCH_MX25
+const struct imx_imx_uart_1irq_data imx25_imx_uart_data[] __initconst = {
+#define imx25_imx_uart_data_entry(_id, _hwid)				\
+	imx_imx_uart_1irq_data_entry(MX25, _id, _hwid, SZ_16K)
+	imx25_imx_uart_data_entry(0, 1),
+	imx25_imx_uart_data_entry(1, 2),
+	imx25_imx_uart_data_entry(2, 3),
+	imx25_imx_uart_data_entry(3, 4),
+	imx25_imx_uart_data_entry(4, 5),
+};
+#endif /* ifdef CONFIG_ARCH_MX25 */
+
+#ifdef CONFIG_SOC_IMX27
+const struct imx_imx_uart_1irq_data imx27_imx_uart_data[] __initconst = {
+#define imx27_imx_uart_data_entry(_id, _hwid)				\
+	imx_imx_uart_1irq_data_entry(MX27, _id, _hwid, SZ_4K)
+	imx27_imx_uart_data_entry(0, 1),
+	imx27_imx_uart_data_entry(1, 2),
+	imx27_imx_uart_data_entry(2, 3),
+	imx27_imx_uart_data_entry(3, 4),
+	imx27_imx_uart_data_entry(4, 5),
+	imx27_imx_uart_data_entry(5, 6),
+};
+#endif /* ifdef CONFIG_SOC_IMX27 */
+
+#ifdef CONFIG_ARCH_MX31
+const struct imx_imx_uart_1irq_data imx31_imx_uart_data[] __initconst = {
+#define imx31_imx_uart_data_entry(_id, _hwid)				\
+	imx_imx_uart_1irq_data_entry(MX31, _id, _hwid, SZ_4K)
+	imx31_imx_uart_data_entry(0, 1),
+	imx31_imx_uart_data_entry(1, 2),
+	imx31_imx_uart_data_entry(2, 3),
+	imx31_imx_uart_data_entry(3, 4),
+	imx31_imx_uart_data_entry(4, 5),
+};
+#endif /* ifdef CONFIG_ARCH_MX31 */
+
+#ifdef CONFIG_ARCH_MX35
+const struct imx_imx_uart_1irq_data imx35_imx_uart_data[] __initconst = {
+#define imx35_imx_uart_data_entry(_id, _hwid)				\
+	imx_imx_uart_1irq_data_entry(MX31, _id, _hwid, SZ_16K)
+	imx35_imx_uart_data_entry(0, 1),
+	imx35_imx_uart_data_entry(1, 2),
+	imx35_imx_uart_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_ARCH_MX35 */
+
+#ifdef CONFIG_ARCH_MX51
+const struct imx_imx_uart_1irq_data imx51_imx_uart_data[] __initconst = {
+#define imx51_imx_uart_data_entry(_id, _hwid)				\
+	imx_imx_uart_1irq_data_entry(MX51, _id, _hwid, SZ_4K)
+	imx51_imx_uart_data_entry(0, 1),
+	imx51_imx_uart_data_entry(1, 2),
+	imx51_imx_uart_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_ARCH_MX51 */
+
+struct platform_device *__init imx_add_imx_uart_3irq(
+		const struct imx_imx_uart_3irq_data *data,
 		const struct imxuart_platform_data *pdata)
 {
 	struct resource res[] = {
 		{
-			.start = iobase,
-			.end = iobase + iosize - 1,
+			.start = data->iobase,
+			.end = data->iobase + data->iosize - 1,
 			.flags = IORESOURCE_MEM,
 		}, {
-			.start = irqrx,
-			.end = irqrx,
+			.start = data->irqrx,
+			.end = data->irqrx,
 			.flags = IORESOURCE_IRQ,
 		}, {
-			.start = irqtx,
-			.end = irqtx,
+			.start = data->irqtx,
+			.end = data->irqtx,
 			.flags = IORESOURCE_IRQ,
 		}, {
-			.start = irqrts,
-			.end = irqrx,
+			.start = data->irqrts,
+			.end = data->irqrx,
 			.flags = IORESOURCE_IRQ,
 		},
 	};
 
-	return imx_add_platform_device("imx-uart", id, res, ARRAY_SIZE(res),
-			pdata, sizeof(*pdata));
+	return imx_add_platform_device("imx-uart", data->id, res,
+			ARRAY_SIZE(res), pdata, sizeof(*pdata));
 }
 
-struct platform_device *__init imx_add_imx_uart_1irq(int id,
-		resource_size_t iobase, resource_size_t iosize,
-		resource_size_t irq,
+struct platform_device *__init imx_add_imx_uart_1irq(
+		const struct imx_imx_uart_1irq_data *data,
 		const struct imxuart_platform_data *pdata)
 {
 	struct resource res[] = {
 		{
-			.start = iobase,
-			.end = iobase + iosize - 1,
+			.start = data->iobase,
+			.end = data->iobase + data->iosize - 1,
 			.flags = IORESOURCE_MEM,
 		}, {
-			.start = irq,
-			.end = irq,
+			.start = data->irq,
+			.end = data->irq,
 			.flags = IORESOURCE_IRQ,
 		},
 	};
 
-	return imx_add_platform_device("imx-uart", id, res, ARRAY_SIZE(res),
+	return imx_add_platform_device("imx-uart", data->id, res, ARRAY_SIZE(res),
 			pdata, sizeof(*pdata));
 }
diff --git a/arch/arm/plat-mxc/devices/platform-mxc_nand.c b/arch/arm/plat-mxc/devices/platform-mxc_nand.c
index 1c28641..3fdcc32 100644
--- a/arch/arm/plat-mxc/devices/platform-mxc_nand.c
+++ b/arch/arm/plat-mxc/devices/platform-mxc_nand.c
@@ -7,38 +7,77 @@
  * Free Software Foundation.
  */
 #include <asm/sizes.h>
+#include <mach/hardware.h>
 #include <mach/devices-common.h>
 
-static struct platform_device *__init imx_add_mxc_nand(resource_size_t iobase,
-		int irq, const struct mxc_nand_platform_data *pdata,
-		resource_size_t iosize)
+#define imx_mxc_nand_data_entry_single(soc, _size)			\
+	{								\
+		.iobase = soc ## _NFC_BASE_ADDR,			\
+		.iosize = _size,					\
+		.irq = soc ## _INT_NFC					\
+	}
+
+#define imx_mxc_nandv3_data_entry_single(soc, _size)			\
+	{								\
+		.id = -1,						\
+		.iobase = soc ## _NFC_BASE_ADDR,			\
+		.iosize = _size,					\
+		.axibase = soc ## _NFC_AXI_BASE_ADDR,			\
+		.irq = soc ## _INT_NFC					\
+	}
+
+#ifdef CONFIG_SOC_IMX21
+const struct imx_mxc_nand_data imx21_mxc_nand_data __initconst =
+	imx_mxc_nand_data_entry_single(MX21, SZ_4K);
+#endif /* ifdef CONFIG_SOC_IMX21 */
+
+#ifdef CONFIG_ARCH_MX25
+const struct imx_mxc_nand_data imx25_mxc_nand_data __initconst =
+	imx_mxc_nand_data_entry_single(MX25, SZ_8K);
+#endif /* ifdef CONFIG_ARCH_MX25 */
+
+#ifdef CONFIG_SOC_IMX27
+const struct imx_mxc_nand_data imx27_mxc_nand_data __initconst =
+	imx_mxc_nand_data_entry_single(MX27, SZ_4K);
+#endif /* ifdef CONFIG_SOC_IMX27 */
+
+#ifdef CONFIG_ARCH_MX31
+const struct imx_mxc_nand_data imx31_mxc_nand_data __initconst =
+	imx_mxc_nand_data_entry_single(MX31, SZ_4K);
+#endif
+
+#ifdef CONFIG_ARCH_MX35
+const struct imx_mxc_nand_data imx35_mxc_nand_data __initconst =
+	imx_mxc_nand_data_entry_single(MX35, SZ_8K);
+#endif
+
+#ifdef CONFIG_ARCH_MX51
+const struct imx_mxc_nand_data imx51_mxc_nand_data __initconst =
+	imx_mxc_nandv3_data_entry_single(MX51, SZ_16K);
+#endif
+
+struct platform_device *__init imx_add_mxc_nand(
+		const struct imx_mxc_nand_data *data,
+		const struct mxc_nand_platform_data *pdata)
 {
-	static int id = 0;
-	
+	/* AXI has to come first, that's how the mxc_nand driver expect it */
 	struct resource res[] = {
 		{
-			.start = iobase,
-			.end = iobase + iosize - 1,
+			.start = data->axibase,
+			.end = data->axibase + SZ_16K - 1,
 			.flags = IORESOURCE_MEM,
 		}, {
-			.start = irq,
-			.end = irq,
+			.start = data->iobase,
+			.end = data->iobase + data->iosize - 1,
+			.flags = IORESOURCE_MEM,
+		}, {
+			.start = data->irq,
+			.end = data->irq,
 			.flags = IORESOURCE_IRQ,
 		},
 	};
-
-	return imx_add_platform_device("mxc_nand", id++, res, ARRAY_SIZE(res),
+	return imx_add_platform_device("mxc_nand", data->id,
+			res + !data->axibase,
+			ARRAY_SIZE(res) - !data->axibase,
 			pdata, sizeof(*pdata));
 }
-
-struct platform_device *__init imx_add_mxc_nand_v1(resource_size_t iobase,
-		int irq, const struct mxc_nand_platform_data *pdata)
-{
-	return imx_add_mxc_nand(iobase, irq, pdata, SZ_4K);
-}
-
-struct platform_device *__init imx_add_mxc_nand_v21(resource_size_t iobase,
-		int irq, const struct mxc_nand_platform_data *pdata)
-{
-	return imx_add_mxc_nand(iobase, irq, pdata, SZ_8K);
-}
diff --git a/arch/arm/plat-mxc/devices/platform-spi_imx.c b/arch/arm/plat-mxc/devices/platform-spi_imx.c
index 2831a6d..e48340e 100644
--- a/arch/arm/plat-mxc/devices/platform-spi_imx.c
+++ b/arch/arm/plat-mxc/devices/platform-spi_imx.c
@@ -6,25 +6,96 @@
  * the terms of the GNU General Public License version 2 as published by the
  * Free Software Foundation.
  */
-#include <asm/sizes.h>
+#include <mach/hardware.h>
 #include <mach/devices-common.h>
 
-struct platform_device *__init imx_add_spi_imx(int id,
-		resource_size_t iobase, resource_size_t iosize, int irq,
+#define imx_spi_imx_data_entry_single(soc, type, _devid, _id, hwid, _size) \
+	{								\
+		.devid = _devid,					\
+		.id = _id,						\
+		.iobase = soc ## _ ## type ## hwid ## _BASE_ADDR,	\
+		.iosize = _size,					\
+		.irq = soc ## _INT_ ## type ## hwid,			\
+	}
+
+#define imx_spi_imx_data_entry(soc, type, devid, id, hwid, size)	\
+	[id] = imx_spi_imx_data_entry_single(soc, type, devid, id, hwid, size)
+
+#ifdef CONFIG_SOC_IMX21
+const struct imx_spi_imx_data imx21_cspi_data[] __initconst = {
+#define imx21_cspi_data_entry(_id, _hwid)                            \
+	imx_spi_imx_data_entry(MX21, CSPI, "imx21-cspi", _id, _hwid, SZ_4K)
+	imx21_cspi_data_entry(0, 1),
+	imx21_cspi_data_entry(1, 2),
+#endif
+
+#ifdef CONFIG_ARCH_MX25
+const struct imx_spi_imx_data imx25_cspi_data[] __initconst = {
+#define imx25_cspi_data_entry(_id, _hwid)				\
+	imx_spi_imx_data_entry(MX25, CSPI, "imx25-cspi", _id, _hwid, SZ_16K)
+	imx25_cspi_data_entry(0, 1),
+	imx25_cspi_data_entry(1, 2),
+	imx25_cspi_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_ARCH_MX25 */
+
+#ifdef CONFIG_SOC_IMX27
+const struct imx_spi_imx_data imx27_cspi_data[] __initconst = {
+#define imx27_cspi_data_entry(_id, _hwid)				\
+	imx_spi_imx_data_entry(MX27, CSPI, "imx27-cspi", _id, _hwid, SZ_4K)
+	imx27_cspi_data_entry(0, 1),
+	imx27_cspi_data_entry(1, 2),
+	imx27_cspi_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_SOC_IMX27 */
+
+#ifdef CONFIG_ARCH_MX31
+const struct imx_spi_imx_data imx31_cspi_data[] __initconst = {
+#define imx31_cspi_data_entry(_id, _hwid)				\
+	imx_spi_imx_data_entry(MX31, CSPI, "imx31-cspi", _id, _hwid, SZ_4K)
+	imx31_cspi_data_entry(0, 1),
+	imx31_cspi_data_entry(1, 2),
+	imx31_cspi_data_entry(2, 3),
+};
+#endif /* ifdef CONFIG_ARCH_MX31 */
+
+#ifdef CONFIG_ARCH_MX35
+const struct imx_spi_imx_data imx35_cspi_data[] __initconst = {
+#define imx35_cspi_data_entry(_id, _hwid)                           \
+	imx_spi_imx_data_entry(MX35, CSPI, "imx35-cspi", _id, _hwid, SZ_4K)
+	imx35_cspi_data_entry(0, 1),
+	imx35_cspi_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_ARCH_MX35 */
+
+#ifdef CONFIG_ARCH_MX51
+const struct imx_spi_imx_data imx51_cspi_data __initconst =
+	imx_spi_imx_data_entry_single(MX51, CSPI, "imx51-cspi", 0, , SZ_4K);
+
+const struct imx_spi_imx_data imx51_ecspi_data[] __initconst = {
+#define imx51_ecspi_data_entry(_id, _hwid)				\
+	imx_spi_imx_data_entry(MX51, ECSPI, "imx51-ecspi", _id, _hwid, SZ_4K)
+	imx51_ecspi_data_entry(0, 1),
+	imx51_ecspi_data_entry(1, 2),
+};
+#endif /* ifdef CONFIG_ARCH_MX51 */
+
+struct platform_device *__init imx_add_spi_imx(
+		const struct imx_spi_imx_data *data,
 		const struct spi_imx_master *pdata)
 {
 	struct resource res[] = {
 		{
-			.start = iobase,
-			.end = iobase + iosize - 1,
+			.start = data->iobase,
+			.end = data->iobase + data->iosize - 1,
 			.flags = IORESOURCE_MEM,
 		}, {
-			.start = irq,
-			.end = irq,
+			.start = data->irq,
+			.end = data->irq,
 			.flags = IORESOURCE_IRQ,
 		},
 	};
 
-	return imx_add_platform_device("spi_imx", id, res, ARRAY_SIZE(res),
-			pdata, sizeof(*pdata));
+	return imx_add_platform_device(data->devid, data->id,
+			res, ARRAY_SIZE(res), pdata, sizeof(*pdata));
 }
diff --git a/arch/arm/plat-mxc/ehci.c b/arch/arm/plat-mxc/ehci.c
index 35a064f..9915607 100644
--- a/arch/arm/plat-mxc/ehci.c
+++ b/arch/arm/plat-mxc/ehci.c
@@ -249,8 +249,8 @@
 #ifdef CONFIG_ARCH_MX51
 	if (cpu_is_mx51()) {
 		void __iomem *usb_base;
-		u32 usbotg_base;
-		u32 usbother_base;
+		void __iomem *usbotg_base;
+		void __iomem *usbother_base;
 		int ret = 0;
 
 		usb_base = ioremap(MX51_OTG_BASE_ADDR, SZ_4K);
diff --git a/arch/arm/plat-mxc/epit.c b/arch/arm/plat-mxc/epit.c
new file mode 100644
index 0000000..ee9582f
--- /dev/null
+++ b/arch/arm/plat-mxc/epit.c
@@ -0,0 +1,242 @@
+/*
+ *  linux/arch/arm/plat-mxc/epit.c
+ *
+ *  Copyright (C) 2010 Sascha Hauer <s.hauer@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#define EPITCR		0x00
+#define EPITSR		0x04
+#define EPITLR		0x08
+#define EPITCMPR	0x0c
+#define EPITCNR		0x10
+
+#define EPITCR_EN			(1 << 0)
+#define EPITCR_ENMOD			(1 << 1)
+#define EPITCR_OCIEN			(1 << 2)
+#define EPITCR_RLD			(1 << 3)
+#define EPITCR_PRESC(x)			(((x) & 0xfff) << 4)
+#define EPITCR_SWR			(1 << 16)
+#define EPITCR_IOVW			(1 << 17)
+#define EPITCR_DBGEN			(1 << 18)
+#define EPITCR_WAITEN			(1 << 19)
+#define EPITCR_RES			(1 << 20)
+#define EPITCR_STOPEN			(1 << 21)
+#define EPITCR_OM_DISCON		(0 << 22)
+#define EPITCR_OM_TOGGLE		(1 << 22)
+#define EPITCR_OM_CLEAR			(2 << 22)
+#define EPITCR_OM_SET			(3 << 22)
+#define EPITCR_CLKSRC_OFF		(0 << 24)
+#define EPITCR_CLKSRC_PERIPHERAL	(1 << 24)
+#define EPITCR_CLKSRC_REF_HIGH		(1 << 24)
+#define EPITCR_CLKSRC_REF_LOW		(3 << 24)
+
+#define EPITSR_OCIF			(1 << 0)
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/clockchips.h>
+#include <linux/clk.h>
+
+#include <mach/hardware.h>
+#include <asm/mach/time.h>
+#include <mach/common.h>
+
+static struct clock_event_device clockevent_epit;
+static enum clock_event_mode clockevent_mode = CLOCK_EVT_MODE_UNUSED;
+
+static void __iomem *timer_base;
+
+static inline void epit_irq_disable(void)
+{
+	u32 val;
+
+	val = __raw_readl(timer_base + EPITCR);
+	val &= ~EPITCR_OCIEN;
+	__raw_writel(val, timer_base + EPITCR);
+}
+
+static inline void epit_irq_enable(void)
+{
+	u32 val;
+
+	val = __raw_readl(timer_base + EPITCR);
+	val |= EPITCR_OCIEN;
+	__raw_writel(val, timer_base + EPITCR);
+}
+
+static void epit_irq_acknowledge(void)
+{
+	__raw_writel(EPITSR_OCIF, timer_base + EPITSR);
+}
+
+static cycle_t epit_read(struct clocksource *cs)
+{
+	return 0 - __raw_readl(timer_base + EPITCNR);
+}
+
+static struct clocksource clocksource_epit = {
+	.name		= "epit",
+	.rating		= 200,
+	.read		= epit_read,
+	.mask		= CLOCKSOURCE_MASK(32),
+	.shift		= 20,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static int __init epit_clocksource_init(struct clk *timer_clk)
+{
+	unsigned int c = clk_get_rate(timer_clk);
+
+	clocksource_epit.mult = clocksource_hz2mult(c,
+					clocksource_epit.shift);
+	clocksource_register(&clocksource_epit);
+
+	return 0;
+}
+
+/* clock event */
+
+static int epit_set_next_event(unsigned long evt,
+			      struct clock_event_device *unused)
+{
+	unsigned long tcmp;
+
+	tcmp = __raw_readl(timer_base + EPITCNR);
+
+	__raw_writel(tcmp - evt, timer_base + EPITCMPR);
+
+	return 0;
+}
+
+static void epit_set_mode(enum clock_event_mode mode,
+				struct clock_event_device *evt)
+{
+	unsigned long flags;
+
+	/*
+	 * The timer interrupt generation is disabled at least
+	 * for enough time to call epit_set_next_event()
+	 */
+	local_irq_save(flags);
+
+	/* Disable interrupt in GPT module */
+	epit_irq_disable();
+
+	if (mode != clockevent_mode) {
+		/* Set event time into far-far future */
+
+		/* Clear pending interrupt */
+		epit_irq_acknowledge();
+	}
+
+	/* Remember timer mode */
+	clockevent_mode = mode;
+	local_irq_restore(flags);
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		printk(KERN_ERR "epit_set_mode: Periodic mode is not "
+				"supported for i.MX EPIT\n");
+		break;
+	case CLOCK_EVT_MODE_ONESHOT:
+	/*
+	 * Do not put overhead of interrupt enable/disable into
+	 * epit_set_next_event(), the core has about 4 minutes
+	 * to call epit_set_next_event() or shutdown clock after
+	 * mode switching
+	 */
+		local_irq_save(flags);
+		epit_irq_enable();
+		local_irq_restore(flags);
+		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_RESUME:
+		/* Left event sources disabled, no more interrupts appear */
+		break;
+	}
+}
+
+/*
+ * IRQ handler for the timer
+ */
+static irqreturn_t epit_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = &clockevent_epit;
+
+	epit_irq_acknowledge();
+
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction epit_timer_irq = {
+	.name		= "i.MX EPIT Timer Tick",
+	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.handler	= epit_timer_interrupt,
+};
+
+static struct clock_event_device clockevent_epit = {
+	.name		= "epit",
+	.features	= CLOCK_EVT_FEAT_ONESHOT,
+	.shift		= 32,
+	.set_mode	= epit_set_mode,
+	.set_next_event	= epit_set_next_event,
+	.rating		= 200,
+};
+
+static int __init epit_clockevent_init(struct clk *timer_clk)
+{
+	unsigned int c = clk_get_rate(timer_clk);
+
+	clockevent_epit.mult = div_sc(c, NSEC_PER_SEC,
+					clockevent_epit.shift);
+	clockevent_epit.max_delta_ns =
+			clockevent_delta2ns(0xfffffffe, &clockevent_epit);
+	clockevent_epit.min_delta_ns =
+			clockevent_delta2ns(0x800, &clockevent_epit);
+
+	clockevent_epit.cpumask = cpumask_of(0);
+
+	clockevents_register_device(&clockevent_epit);
+
+	return 0;
+}
+
+void __init epit_timer_init(struct clk *timer_clk, void __iomem *base, int irq)
+{
+	clk_enable(timer_clk);
+
+	timer_base = base;
+
+	/*
+	 * Initialise to a known state (all timers off, and timing reset)
+	 */
+	__raw_writel(0x0, timer_base + EPITCR);
+
+	__raw_writel(0xffffffff, timer_base + EPITLR);
+	__raw_writel(EPITCR_EN | EPITCR_CLKSRC_REF_HIGH | EPITCR_WAITEN,
+			timer_base + EPITCR);
+
+	/* init and register the timer to the framework */
+	epit_clocksource_init(timer_clk);
+	epit_clockevent_init(timer_clk);
+
+	/* Make irqs happen */
+	setup_irq(irq, &epit_timer_irq);
+}
diff --git a/arch/arm/plat-mxc/gpio.c b/arch/arm/plat-mxc/gpio.c
index 57ec4a8..9d38da0 100644
--- a/arch/arm/plat-mxc/gpio.c
+++ b/arch/arm/plat-mxc/gpio.c
@@ -235,7 +235,7 @@
 	unsigned long flags;
 
 	spin_lock_irqsave(&port->lock, flags);
-	l = (__raw_readl(reg) & (~(1 << offset))) | (value << offset);
+	l = (__raw_readl(reg) & (~(1 << offset))) | (!!value << offset);
 	__raw_writel(l, reg);
 	spin_unlock_irqrestore(&port->lock, flags);
 }
diff --git a/arch/arm/plat-mxc/include/mach/board-mx31ads.h b/arch/arm/plat-mxc/include/mach/board-mx31ads.h
new file mode 100644
index 0000000..94b60dd4
--- /dev/null
+++ b/arch/arm/plat-mxc/include/mach/board-mx31ads.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2005-2007 Freescale Semiconductor, Inc. All Rights Reserved.
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_ARCH_MXC_BOARD_MX31ADS_H__
+#define __ASM_ARCH_MXC_BOARD_MX31ADS_H__
+
+#include <mach/hardware.h>
+
+/*
+ * These symbols are used by drivers/net/cs89x0.c.
+ * This is ugly as hell, but we have to provide them until
+ * someone fixed the driver.
+ */
+
+/* Base address of PBC controller */
+#define PBC_BASE_ADDRESS        MX31_CS4_BASE_ADDR_VIRT
+/* Offsets for the PBC Controller register */
+
+/* Ethernet Controller IO base address */
+#define PBC_CS8900A_IOBASE      0x020000
+
+#define MXC_EXP_IO_BASE		(MXC_BOARD_IRQ_START)
+
+#define EXPIO_INT_ENET_INT	(MXC_EXP_IO_BASE + 8)
+
+#endif /* __ASM_ARCH_MXC_BOARD_MX31ADS_H__ */
diff --git a/arch/arm/plat-mxc/include/mach/common.h b/arch/arm/plat-mxc/include/mach/common.h
index 2941472..7a1e1f8 100644
--- a/arch/arm/plat-mxc/include/mach/common.h
+++ b/arch/arm/plat-mxc/include/mach/common.h
@@ -32,6 +32,7 @@
 extern void mx35_init_irq(void);
 extern void mx51_init_irq(void);
 extern void mxc91231_init_irq(void);
+extern void epit_timer_init(struct clk *timer_clk, void __iomem *base, int irq);
 extern void mxc_timer_init(struct clk *timer_clk, void __iomem *, int);
 extern int mx1_clocks_init(unsigned long fref);
 extern int mx21_clocks_init(unsigned long lref, unsigned long fref);
diff --git a/arch/arm/plat-mxc/include/mach/debug-macro.S b/arch/arm/plat-mxc/include/mach/debug-macro.S
index 2560640..d56213f 100644
--- a/arch/arm/plat-mxc/include/mach/debug-macro.S
+++ b/arch/arm/plat-mxc/include/mach/debug-macro.S
@@ -62,11 +62,9 @@
 #define UART_PADDR	MXC91231_UART2_BASE_ADDR
 #define UART_VADDR	MXC91231_IO_ADDRESS(MXC91231_UART2_BASE_ADDR)
 #endif
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		ldreq	\rx, =UART_PADDR	@ physical
-		ldrne	\rx, =UART_VADDR	@ virtual
+		.macro	addruart, rp, rv
+		ldr	\rp, =UART_PADDR	@ physical
+		ldr	\rv, =UART_VADDR	@ virtual
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/plat-mxc/include/mach/devices-common.h b/arch/arm/plat-mxc/include/mach/devices-common.h
index c5f68c5..86d7575 100644
--- a/arch/arm/plat-mxc/include/mach/devices-common.h
+++ b/arch/arm/plat-mxc/include/mach/devices-common.h
@@ -14,47 +14,105 @@
 		const struct resource *res, unsigned int num_resources,
 		const void *data, size_t size_data);
 
-#if defined (CONFIG_CAN_FLEXCAN) || defined (CONFIG_CAN_FLEXCAN_MODULE)
+#include <linux/fec.h>
+struct imx_fec_data {
+	resource_size_t iobase;
+	resource_size_t irq;
+};
+struct platform_device *__init imx_add_fec(
+		const struct imx_fec_data *data,
+		const struct fec_platform_data *pdata);
+
 #include <linux/can/platform/flexcan.h>
 struct platform_device *__init imx_add_flexcan(int id,
 		resource_size_t iobase, resource_size_t iosize,
 		resource_size_t irq,
 		const struct flexcan_platform_data *pdata);
-#else
-/* the ifdef can be removed once the flexcan driver has been merged */
-struct flexcan_platform_data;
-static inline struct platform_device *__init imx_add_flexcan(int id,
-		resource_size_t iobase, resource_size_t iosize,
-		resource_size_t irq,
-		const struct flexcan_platform_data *pdata)
-{
-	return NULL;
-}
-#endif
 
 #include <mach/i2c.h>
-struct platform_device *__init imx_add_imx_i2c(int id,
-		resource_size_t iobase, resource_size_t iosize, int irq,
+struct imx_imx_i2c_data {
+	int id;
+	resource_size_t iobase;
+	resource_size_t iosize;
+	resource_size_t irq;
+};
+struct platform_device *__init imx_add_imx_i2c(
+		const struct imx_imx_i2c_data *data,
 		const struct imxi2c_platform_data *pdata);
 
+#include <mach/ssi.h>
+struct imx_imx_ssi_data {
+	int id;
+	resource_size_t iobase;
+	resource_size_t iosize;
+	resource_size_t irq;
+	resource_size_t dmatx0;
+	resource_size_t dmarx0;
+	resource_size_t dmatx1;
+	resource_size_t dmarx1;
+};
+struct platform_device *__init imx_add_imx_ssi(
+		const struct imx_imx_ssi_data *data,
+		const struct imx_ssi_platform_data *pdata);
+
 #include <mach/imx-uart.h>
-struct platform_device *__init imx_add_imx_uart_3irq(int id,
-		resource_size_t iobase, resource_size_t iosize,
-		resource_size_t irqrx, resource_size_t irqtx,
-		resource_size_t irqrts,
+struct imx_imx_uart_3irq_data {
+	int id;
+	resource_size_t iobase;
+	resource_size_t iosize;
+	resource_size_t irqrx;
+	resource_size_t irqtx;
+	resource_size_t irqrts;
+};
+struct platform_device *__init imx_add_imx_uart_3irq(
+		const struct imx_imx_uart_3irq_data *data,
 		const struct imxuart_platform_data *pdata);
-struct platform_device *__init imx_add_imx_uart_1irq(int id,
-		resource_size_t iobase, resource_size_t iosize,
-		resource_size_t irq,
+
+struct imx_imx_uart_1irq_data {
+	int id;
+	resource_size_t iobase;
+	resource_size_t iosize;
+	resource_size_t irq;
+};
+struct platform_device *__init imx_add_imx_uart_1irq(
+		const struct imx_imx_uart_1irq_data *data,
 		const struct imxuart_platform_data *pdata);
 
 #include <mach/mxc_nand.h>
-struct platform_device *__init imx_add_mxc_nand_v1(resource_size_t iobase,
-		int irq, const struct mxc_nand_platform_data *pdata);
-struct platform_device *__init imx_add_mxc_nand_v21(resource_size_t iobase,
-		int irq, const struct mxc_nand_platform_data *pdata);
+struct imx_mxc_nand_data {
+	/*
+	 * id is traditionally 0, but -1 is more appropriate.  We use -1 for new
+	 * machines but don't change existing devices as the nand device usually
+	 * appears in the kernel command line to pass its partitioning.
+	 */
+	int id;
+	resource_size_t iobase;
+	resource_size_t iosize;
+	resource_size_t axibase;
+	resource_size_t irq;
+};
+struct platform_device *__init imx_add_mxc_nand(
+		const struct imx_mxc_nand_data *data,
+		const struct mxc_nand_platform_data *pdata);
 
 #include <mach/spi.h>
-struct platform_device *__init imx_add_spi_imx(int id,
-		resource_size_t iobase, resource_size_t iosize, int irq,
+struct imx_spi_imx_data {
+	const char *devid;
+	int id;
+	resource_size_t iobase;
+	resource_size_t iosize;
+	int irq;
+};
+struct platform_device *__init imx_add_spi_imx(
+		const struct imx_spi_imx_data *data,
 		const struct spi_imx_master *pdata);
+
+#include <mach/esdhc.h>
+struct imx_esdhc_imx_data {
+	int id;
+	resource_size_t iobase;
+	resource_size_t irq;
+};
+struct platform_device *__init imx_add_esdhc(
+		const struct imx_esdhc_imx_data *data,
+		const struct esdhc_platform_data *pdata);
diff --git a/arch/arm/plat-mxc/include/mach/esdhc.h b/arch/arm/plat-mxc/include/mach/esdhc.h
new file mode 100644
index 0000000..a48a9aa
--- /dev/null
+++ b/arch/arm/plat-mxc/include/mach/esdhc.h
@@ -0,0 +1,16 @@
+/*
+ * Copyright 2010 Wolfram Sang <w.sang@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#ifndef __ASM_ARCH_IMX_ESDHC_H
+#define __ASM_ARCH_IMX_ESDHC_H
+
+struct esdhc_platform_data {
+	unsigned int wp_gpio;	/* write protect pin */
+};
+#endif /* __ASM_ARCH_IMX_ESDHC_H */
diff --git a/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h b/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h
index 656acb4..a21d331 100644
--- a/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h
+++ b/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h
@@ -28,19 +28,22 @@
  * its own devices, it calls baseboard's init function.
  * TODO: Add your own baseboard init function and call it from
  * inside eukrea_cpuimx25_init() eukrea_cpuimx27_init()
- * eukrea_cpuimx35_init() or eukrea_cpuimx51_init().
+ * eukrea_cpuimx35_init() eukrea_cpuimx51_init()
+ * or eukrea_cpuimx51sd_init().
  *
  * This example here is for the development board. Refer
  * mach-mx25/eukrea_mbimxsd-baseboard.c for cpuimx25
  * mach-imx/eukrea_mbimx27-baseboard.c for cpuimx27
  * mach-mx3/eukrea_mbimxsd-baseboard.c for cpuimx35
  * mach-mx5/eukrea_mbimx51-baseboard.c for cpuimx51
+ * mach-mx5/eukrea_mbimxsd-baseboard.c for cpuimx51sd
  */
 
 extern void eukrea_mbimxsd25_baseboard_init(void);
 extern void eukrea_mbimx27_baseboard_init(void);
 extern void eukrea_mbimxsd35_baseboard_init(void);
 extern void eukrea_mbimx51_baseboard_init(void);
+extern void eukrea_mbimxsd51_baseboard_init(void);
 
 #endif
 
diff --git a/arch/arm/plat-mxc/include/mach/iomux-mx51.h b/arch/arm/plat-mxc/include/mach/iomux-mx51.h
index 21bfa46..e46b1c2 100644
--- a/arch/arm/plat-mxc/include/mach/iomux-mx51.h
+++ b/arch/arm/plat-mxc/include/mach/iomux-mx51.h
@@ -45,6 +45,18 @@
 				PAD_CTL_PKE | PAD_CTL_HYS)
 #define MX51_GPIO_PAD_CTRL		(PAD_CTL_DSE_HIGH | PAD_CTL_PKE | \
 				PAD_CTL_SRE_FAST)
+#define MX51_ECSPI_PAD_CTRL	(PAD_CTL_HYS | PAD_CTL_PKE | PAD_CTL_DSE_HIGH | \
+				PAD_CTL_SRE_FAST)
+#define MX51_SDHCI_PAD_CTRL	(PAD_CTL_DSE_HIGH | PAD_CTL_PUS_47K_UP | \
+				PAD_CTL_PKE | PAD_CTL_PUE | PAD_CTL_SRE_FAST | \
+				PAD_CTL_DVS)
+
+#define MX51_PAD_CTRL_1	(PAD_CTL_SRE_FAST | PAD_CTL_DSE_HIGH | \
+					PAD_CTL_PUE | PAD_CTL_PKE | PAD_CTL_HYS)
+#define MX51_PAD_CTRL_2	(PAD_CTL_HYS | PAD_CTL_PKE)
+#define MX51_PAD_CTRL_3	(PAD_CTL_PKE | PAD_CTL_PUS_100K_UP)
+#define MX51_PAD_CTRL_4	(PAD_CTL_DVS | PAD_CTL_HYS | PAD_CTL_PKE)
+#define MX51_PAD_CTRL_5	(PAD_CTL_DVS | PAD_CTL_DSE_HIGH)
 
 /*
  * The naming convention for the pad modes is MX51_PAD_<padname>__<padmode>
@@ -106,14 +118,20 @@
 #define MX51_PAD_EIM_EB0__EIM_EB0               IOMUX_PAD(0x460, 0x0cc, 0, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_EIM_EB1__EIM_EB1               IOMUX_PAD(0x464, 0x0d0, 0, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_EIM_EB2__GPIO_2_22             IOMUX_PAD(0x468, 0x0d4, 1, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_EIM_EB2__FEC_MDIO		IOMUX_PAD(0x468, 0x0d4, 3, 0x0,   0, MX51_PAD_CTRL_1 | PAD_CTL_PUS_22K_UP)
 #define MX51_PAD_EIM_EB3__GPIO_2_23             IOMUX_PAD(0x46c, 0x0d8, 1, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_EIM_EB3__FEC_RDAT1		IOMUX_PAD(0x46c, 0x0d8, 3, 0x0,   0, MX51_PAD_CTRL_2)
 #define MX51_PAD_EIM_OE__GPIO_2_24              IOMUX_PAD(0x470, 0x0dc, 1, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_EIM_CS0__GPIO_2_25             IOMUX_PAD(0x474, 0x0e0, 1, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_EIM_CS1__GPIO_2_26             IOMUX_PAD(0x478, 0x0e4, 1, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_EIM_CS2__GPIO_2_27             IOMUX_PAD(0x47c, 0x0e8, 1, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_EIM_CS2__FEC_RDAT2		IOMUX_PAD(0x47c, 0x0e8, 3, 0x0,   0, MX51_PAD_CTRL_2)
 #define MX51_PAD_EIM_CS3__GPIO_2_28             IOMUX_PAD(0x480, 0x0ec, 1, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_EIM_CS3__FEC_RDAT3		IOMUX_PAD(0x480, 0x0ec, 3, 0x0,   0, MX51_PAD_CTRL_2)
 #define MX51_PAD_EIM_CS4__GPIO_2_29             IOMUX_PAD(0x484, 0x0f0, 1, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_EIM_CS4__FEC_RX_ER		IOMUX_PAD(0x484, 0x0f0, 3, 0x0,   0, MX51_PAD_CTRL_2)
 #define MX51_PAD_EIM_CS5__GPIO_2_30             IOMUX_PAD(0x488, 0x0f4, 1, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_EIM_CS5__FEC_CRS		IOMUX_PAD(0x488, 0x0f4, 3, 0x0,   0, MX51_PAD_CTRL_2)
 #define MX51_PAD_EIM_DTACK__GPIO_2_31           IOMUX_PAD(0x48c, 0x0f8, 1, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_EIM_LBA__GPIO_3_1              IOMUX_PAD(0x494, 0x0FC, 1, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_EIM_CRE__GPIO_3_2              IOMUX_PAD(0x4A0, 0x100, 1, 0x0,   0, NO_PAD_CTRL)
@@ -126,18 +144,32 @@
 #define MX51_PAD_NANDF_RB0__GPIO_3_8            IOMUX_PAD(0x4F8, 0x11C, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_NANDF_RB1__GPIO_3_9            IOMUX_PAD(0x4FC, 0x120, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_NANDF_RB2__GPIO_3_10           IOMUX_PAD(0x500, 0x124, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_RB2__ECSPI2_SCLK         IOMUX_PAD(0x500, 0x124, 2, 0x0,   0, MX51_ECSPI_PAD_CTRL)
+#define MX51_PAD_NANDF_RB2__FEC_COL		IOMUX_PAD(0x500, 0x124, 1, 0x0,   0, MX51_PAD_CTRL_2)
 #define MX51_PAD_NANDF_RB3__GPIO_3_11           IOMUX_PAD(0x504, 0x128, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_RB3__ECSPI2_MISO         IOMUX_PAD(0x504, 0x128, 2, 0x0,   0, MX51_ECSPI_PAD_CTRL)
+#define MX51_PAD_NANDF_RB3__FEC_RXCLK		IOMUX_PAD(0x504, 0x128, 1, 0x0,   0, MX51_PAD_CTRL_2)
+#define MX51_PAD_NANDF_RB6__FEC_RDAT0		IOMUX_PAD(0x5DC, 0x134, 1, 0x0,   0, MX51_PAD_CTRL_4)
+#define MX51_PAD_NANDF_RB7__FEC_TDAT0		IOMUX_PAD(0x5E0, 0x138, 1, 0x0,   0, MX51_PAD_CTRL_5)
 #define MX51_PAD_GPIO_NAND__GPIO_3_12           IOMUX_PAD(0x514, 0x12C, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_NANDF_CS0__GPIO_3_16           IOMUX_PAD(0x518, 0x130, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_NANDF_CS1__GPIO_3_17           IOMUX_PAD(0x51C, 0x134, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_NANDF_CS2__GPIO_3_18           IOMUX_PAD(0x520, 0x138, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_CS2__FEC_TX_ER		IOMUX_PAD(0x520, 0x138, 2, 0x0,   0, MX51_PAD_CTRL_5)
 #define MX51_PAD_NANDF_CS3__GPIO_3_19           IOMUX_PAD(0x524, 0x13C, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_CS3__FEC_MDC		IOMUX_PAD(0x524, 0x13C, 2, 0x0,   0, MX51_PAD_CTRL_5)
 #define MX51_PAD_NANDF_CS4__GPIO_3_20           IOMUX_PAD(0x528, 0x140, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_CS4__FEC_TDAT1		IOMUX_PAD(0x528, 0x140, 2, 0x0,   0, MX51_PAD_CTRL_5)
 #define MX51_PAD_NANDF_CS5__GPIO_3_21           IOMUX_PAD(0x52C, 0x144, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_CS5__FEC_TDAT2		IOMUX_PAD(0x52C, 0x144, 2, 0x0,   0, MX51_PAD_CTRL_5)
 #define MX51_PAD_NANDF_CS6__GPIO_3_22           IOMUX_PAD(0x530, 0x148, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_CS6__FEC_TDAT3		IOMUX_PAD(0x530, 0x148, 2, 0x0,   0, MX51_PAD_CTRL_5)
 #define MX51_PAD_NANDF_CS7__GPIO_3_23           IOMUX_PAD(0x534, 0x14C, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_CS7__FEC_TX_EN		IOMUX_PAD(0x534, 0x14C, 1, 0x0,   0, MX51_PAD_CTRL_5)
 #define MX51_PAD_NANDF_RDY_INT__GPIO_3_24       IOMUX_PAD(0x538, 0x150, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_RDY_INT__FEC_TX_CLK	IOMUX_PAD(0x538, 0x150, 1, 0x0,   0, MX51_PAD_CTRL_4)
 #define MX51_PAD_NANDF_D15__GPIO_3_25           IOMUX_PAD(0x53C, 0x154, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_NANDF_D15__ECSPI2_MOSI         IOMUX_PAD(0x53C, 0x154, 2, 0x0,   0, MX51_ECSPI_PAD_CTRL)
 #define MX51_PAD_NANDF_D14__GPIO_3_26           IOMUX_PAD(0x540, 0x158, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_NANDF_D13__GPIO_3_27           IOMUX_PAD(0x544, 0x15C, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_NANDF_D12__GPIO_3_28           IOMUX_PAD(0x548, 0x160, 3, 0x0,   0, NO_PAD_CTRL)
@@ -185,15 +217,25 @@
 #define MX51_PAD_I2C1_CLK__HSI2C_CLK		IOMUX_PAD(0x5E8, 0x1F8, 0, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_I2C1_DAT__GPIO_4_17            IOMUX_PAD(0x5EC, 0x1FC, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_I2C1_DAT__HSI2C_DAT		IOMUX_PAD(0x5EC, 0x1FC, 0, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_AUD3_BB_TXD__AUD3_BB_TXD       IOMUX_PAD(0x5F0, 0x200, IOMUX_CONFIG_SION, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_AUD3_BB_TXD__GPIO_4_18         IOMUX_PAD(0x5F0, 0x200, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_AUD3_BB_RXD__AUD3_BB_RXD       IOMUX_PAD(0x5F4, 0x204, IOMUX_CONFIG_SION, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_AUD3_BB_RXD__GPIO_4_19         IOMUX_PAD(0x5F4, 0x204, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_AUD3_BB_CK__AUD3_BB_CK         IOMUX_PAD(0x5F8, 0x208, IOMUX_CONFIG_SION, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_AUD3_BB_CK__GPIO_4_20          IOMUX_PAD(0x5F8, 0x208, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_AUD3_BB_FS__AUD3_BB_FS         IOMUX_PAD(0x5FC, 0x20C, IOMUX_CONFIG_SION, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_AUD3_BB_FS__GPIO_4_21          IOMUX_PAD(0x5FC, 0x20C, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_CSPI1_MOSI__ECSPI1_MOSI        IOMUX_PAD(0x600, 0x210, 0, 0x0,   0, MX51_ECSPI_PAD_CTRL)
 #define MX51_PAD_CSPI1_MOSI__GPIO_4_22          IOMUX_PAD(0x600, 0x210, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_CSPI1_MISO__ECSPI1_MISO        IOMUX_PAD(0x604, 0x214, 0, 0x0,   0, MX51_ECSPI_PAD_CTRL)
 #define MX51_PAD_CSPI1_MISO__GPIO_4_23          IOMUX_PAD(0x604, 0x214, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_CSPI1_SS0__ECSPI1_SS0          IOMUX_PAD(0x608, 0x218, 0, 0x0,   0, MX51_ECSPI_PAD_CTRL)
 #define MX51_PAD_CSPI1_SS0__GPIO_4_24           IOMUX_PAD(0x608, 0x218, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_CSPI1_SS1__ECSPI1_SS1          IOMUX_PAD(0x60C, 0x21C, 0, 0x0,   0, MX51_ECSPI_PAD_CTRL)
 #define MX51_PAD_CSPI1_SS1__GPIO_4_25           IOMUX_PAD(0x60C, 0x21C, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_CSPI1_RDY__ECSPI1_RDY          IOMUX_PAD(0x610, 0x220, 0, 0x0,   0, MX51_ECSPI_PAD_CTRL)
 #define MX51_PAD_CSPI1_RDY__GPIO_4_26           IOMUX_PAD(0x610, 0x220, 3, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_CSPI1_SCLK__ECSPI1_SCLK        IOMUX_PAD(0x614, 0x224, 0, 0x0,   0, MX51_ECSPI_PAD_CTRL)
 #define MX51_PAD_CSPI1_SCLK__GPIO_4_27          IOMUX_PAD(0x614, 0x224, 3, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_UART1_RXD__UART1_RXD           IOMUX_PAD(0x618, 0x228, 0, 0x9e4, 0, MX51_UART1_PAD_CTRL | PAD_CTL_SRE_FAST)
 #define MX51_PAD_UART1_TXD__UART1_TXD           IOMUX_PAD(0x61C, 0x22C, 0, 0x0,   0, MX51_UART1_PAD_CTRL | PAD_CTL_SRE_FAST)
@@ -236,14 +278,14 @@
 #define MX51_PAD_USBH1_DATA6__USBH1_DATA6       IOMUX_PAD(0x6A0, 0x2A0, 0, 0x0,   0, MX51_USBH1_PAD_CTRL)
 #define MX51_PAD_USBH1_DATA7__USBH1_DATA7       IOMUX_PAD(0x6A4, 0x2A4, 0, 0x0,   0, MX51_USBH1_PAD_CTRL)
 #define MX51_PAD_DI1_PIN11__GPIO_3_0            IOMUX_PAD(0x6A8, 0x2A8, 4, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_DI1_PIN12__GPIO_3_1            IOMUX_PAD(0x6AC, 0x2AC, 4, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_DI1_PIN13__GPIO_3_2            IOMUX_PAD(0x6B0, 0x2B0, 4, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_DI1_D0_CS__GPIO_3_3            IOMUX_PAD(0x6B4, 0x2B4, 4, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_DI1_D1_CS__GPIO_3_4            IOMUX_PAD(0x6B8, 0x2B8, 4, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_DISPB2_SER_DIN__GPIO_3_5       IOMUX_PAD(0x6BC, 0x2BC, 4, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_DISPB2_SER_DIO__GPIO_3_6       IOMUX_PAD(0x6C0, 0x2C0, 4, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_DISPB2_SER_CLK__GPIO_3_7       IOMUX_PAD(0x6C4, 0x2C4, 4, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_DISPB2_SER_RS__GPIO_3_8        IOMUX_PAD(0x6C8, 0x2C8, 4, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_DI1_PIN12__GPIO_3_1            IOMUX_PAD(0x6AC, 0x2AC, 4, 0x978, 1, NO_PAD_CTRL)
+#define MX51_PAD_DI1_PIN13__GPIO_3_2            IOMUX_PAD(0x6B0, 0x2B0, 4, 0x97c, 1, NO_PAD_CTRL)
+#define MX51_PAD_DI1_D0_CS__GPIO_3_3            IOMUX_PAD(0x6B4, 0x2B4, 4, 0x980, 1, NO_PAD_CTRL)
+#define MX51_PAD_DI1_D1_CS__GPIO_3_4            IOMUX_PAD(0x6B8, 0x2B8, 4, 0x984, 1, NO_PAD_CTRL)
+#define MX51_PAD_DISPB2_SER_DIN__GPIO_3_5       IOMUX_PAD(0x6BC, 0x2BC, 4, 0x988, 1, NO_PAD_CTRL)
+#define MX51_PAD_DISPB2_SER_DIO__GPIO_3_6       IOMUX_PAD(0x6C0, 0x2C0, 4, 0x98c, 1, NO_PAD_CTRL)
+#define MX51_PAD_DISPB2_SER_CLK__GPIO_3_7       IOMUX_PAD(0x6C4, 0x2C4, 4, 0x990, 1, NO_PAD_CTRL)
+#define MX51_PAD_DISPB2_SER_RS__GPIO_3_8        IOMUX_PAD(0x6C8, 0x2C8, 4, 0x994, 1, NO_PAD_CTRL)
 #define MX51_PAD_DISP1_DAT0__DISP1_DAT0         IOMUX_PAD(0x6CC, 0x2CC, 0, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_DISP1_DAT1__DISP1_DAT1         IOMUX_PAD(0x6D0, 0x2D0, 0, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_DISP1_DAT2__DISP1_DAT2         IOMUX_PAD(0x6D4, 0x2D4, 0, 0x0,   0, NO_PAD_CTRL)
@@ -294,32 +336,50 @@
 #define MX51_PAD_DISP2_DAT13__DISP2_DAT13       IOMUX_PAD(0x790, 0x388, 0, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_DISP2_DAT14__DISP2_DAT14       IOMUX_PAD(0x794, 0x38C, 0, 0x0,   0, NO_PAD_CTRL)
 #define MX51_PAD_DISP2_DAT15__DISP2_DAT15       IOMUX_PAD(0x798, 0x390, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD1_CMD__SD1_CMD               IOMUX_PAD(0x79C, 0x394, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD1_CLK__SD1_CLK               IOMUX_PAD(0x7A0, 0x398, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD1_DATA0__SD1_DATA0           IOMUX_PAD(0x7A4, 0x39C, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD1_DATA1__SD1_DATA1           IOMUX_PAD(0x7A8, 0x3A0, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD1_DATA2__SD1_DATA2           IOMUX_PAD(0x7AC, 0x3A4, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD1_DATA3__SD1_DATA3           IOMUX_PAD(0x7B0, 0x3A8, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_0__GPIO_1_0		IOMUX_PAD(0x7B4, 0x3AC, 1, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_1__GPIO_1_1		IOMUX_PAD(0x7B8, 0x3B0, 1, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD2_CMD__SD2_CMD               IOMUX_PAD(0x7BC, 0x3B4, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD2_CLK__SD2_CLK               IOMUX_PAD(0x7C0, 0x3B8, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD2_DATA0__SD2_DATA0           IOMUX_PAD(0x7C4, 0x3BC, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD2_DATA1__SD2_DATA1           IOMUX_PAD(0x7C8, 0x3C0, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD2_DATA2__SD2_DATA2           IOMUX_PAD(0x7CC, 0x3C4, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_SD2_DATA3__SD2_DATA3           IOMUX_PAD(0x7D0, 0x3C8, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_2__GPIO_1_2		IOMUX_PAD(0x7D4, 0x3CC, 0, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_SD1_CMD__SD1_CMD		IOMUX_PAD(0x79C, 0x394, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD1_CMD__AUD5_RXFS             IOMUX_PAD(0x79C, 0x394, 1, 0x8e0, 1, NO_PAD_CTRL)
+#define MX51_PAD_SD1_CLK__SD1_CLK		IOMUX_PAD(0x7A0, 0x398, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL | PAD_CTL_HYS)
+#define MX51_PAD_SD1_CLK__AUD5_RXC              IOMUX_PAD(0x7A0, 0x398, 1, 0x8dc, 1, NO_PAD_CTRL)
+#define MX51_PAD_SD1_DATA0__SD1_DATA0		IOMUX_PAD(0x7A4, 0x39C, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD1_DATA0__AUD5_TXD            IOMUX_PAD(0x7A4, 0x39C, 1, 0x8d8, 2, NO_PAD_CTRL)
+#define MX51_PAD_SD1_DATA1__SD1_DATA1		IOMUX_PAD(0x7A8, 0x3A0, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD1_DATA1__AUD5_RXD            IOMUX_PAD(0x7A8, 0x3A0, 1, 0x8d4, 2, NO_PAD_CTRL)
+#define MX51_PAD_SD1_DATA2__SD1_DATA2		IOMUX_PAD(0x7AC, 0x3A4, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD1_DATA2__AUD5_TXC            IOMUX_PAD(0x7AC, 0x3A4, 1, 0x8e4, 2, NO_PAD_CTRL)
+#define MX51_PAD_SD1_DATA3__SD1_DATA3		IOMUX_PAD(0x7B0, 0x3A8, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD1_DATA3__AUD5_TXFS           IOMUX_PAD(0x7B0, 0x3A8, 1, 0x8e8, 2, NO_PAD_CTRL)
+#define MX51_PAD_SD2_CMD__SD2_CMD		IOMUX_PAD(0x7BC, 0x3B4, IOMUX_CONFIG_SION, 0x0, 1, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD2_CLK__SD2_CLK		IOMUX_PAD(0x7C0, 0x3B8, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL | PAD_CTL_HYS)
+#define MX51_PAD_SD2_DATA0__SD2_DATA0		IOMUX_PAD(0x7C4, 0x3BC, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD2_DATA1__SD2_DATA1		IOMUX_PAD(0x7C8, 0x3C0, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD2_DATA2__SD2_DATA2		IOMUX_PAD(0x7CC, 0x3C4, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_SD2_DATA3__SD2_DATA3		IOMUX_PAD(0x7D0, 0x3C8, IOMUX_CONFIG_SION, 0x0, 0, \
+							MX51_SDHCI_PAD_CTRL)
+#define MX51_PAD_GPIO_1_0__GPIO_1_0		IOMUX_PAD(0x7B4, 0x3AC, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_1__GPIO_1_1		IOMUX_PAD(0x7B8, 0x3B0, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_2__GPIO_1_2		IOMUX_PAD(0x7D4, 0x3CC, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
 #define MX51_PAD_GPIO_1_2__I2C2_SCL		IOMUX_PAD(0x7D4, 0x3CC, (2 | IOMUX_CONFIG_SION), \
 							0x9b8,   3, MX51_I2C_PAD_CTRL)
-#define MX51_PAD_GPIO_1_3__GPIO_1_3		IOMUX_PAD(0x7D8, 0x3D0, 0, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_3__GPIO_1_3		IOMUX_PAD(0x7D8, 0x3D0, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
 #define MX51_PAD_GPIO_1_3__I2C2_SDA		IOMUX_PAD(0x7D8, 0x3D0, (2 | IOMUX_CONFIG_SION), \
 							0x9bc,   3, MX51_I2C_PAD_CTRL)
 #define MX51_PAD_PMIC_INT_REQ__PMIC_INT_REQ	IOMUX_PAD(0x7FC, 0x3D4, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_4__GPIO_1_4		IOMUX_PAD(0x804, 0x3D8, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_5__GPIO_1_5		IOMUX_PAD(0x808, 0x3DC, 0, 0x0,   0, NO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_6__GPIO_1_6		IOMUX_PAD(0x80C, 0x3E0, 0, 0x0,   0, MX51_GPIO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_7__GPIO_1_7		IOMUX_PAD(0x810, 0x3E4, 0, 0x0,   0, MX51_GPIO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_8__GPIO_1_8		IOMUX_PAD(0x814, 0x3E8, 0, 0x0,   1, MX51_GPIO_PAD_CTRL)
-#define MX51_PAD_GPIO_1_9__GPIO_1_9		IOMUX_PAD(0x818, 0x3EC, 0, 0x0,   0, NO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_4__GPIO_1_4		IOMUX_PAD(0x804, 0x3D8, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_5__GPIO_1_5		IOMUX_PAD(0x808, 0x3DC, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_6__GPIO_1_6		IOMUX_PAD(0x80C, 0x3E0, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_7__GPIO_1_7		IOMUX_PAD(0x810, 0x3E4, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_8__GPIO_1_8		IOMUX_PAD(0x814, 0x3E8, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
+#define MX51_PAD_GPIO_1_9__GPIO_1_9		IOMUX_PAD(0x818, 0x3EC, 1, 0x0,   0, MX51_GPIO_PAD_CTRL)
 
 #endif /* __MACH_IOMUX_MX51_H__ */
diff --git a/arch/arm/plat-mxc/include/mach/iram.h b/arch/arm/plat-mxc/include/mach/iram.h
new file mode 100644
index 0000000..022690c
--- /dev/null
+++ b/arch/arm/plat-mxc/include/mach/iram.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+#include <linux/errno.h>
+
+#ifdef CONFIG_IRAM_ALLOC
+
+int __init iram_init(unsigned long base, unsigned long size);
+void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr);
+void iram_free(unsigned long dma_addr, unsigned int size);
+
+#else
+
+static inline int __init iram_init(unsigned long base, unsigned long size)
+{
+	return -ENOMEM;
+}
+
+static inline void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr)
+{
+	return NULL;
+}
+
+static inline void iram_free(unsigned long base, unsigned long size) {}
+
+#endif
diff --git a/arch/arm/plat-mxc/include/mach/mx21.h b/arch/arm/plat-mxc/include/mach/mx21.h
index ed98b9c..8bc5972 100644
--- a/arch/arm/plat-mxc/include/mach/mx21.h
+++ b/arch/arm/plat-mxc/include/mach/mx21.h
@@ -120,7 +120,7 @@
 #define MX21_INT_GPT1		26
 #define MX21_INT_WDOG		27
 #define MX21_INT_PCMCIA		28
-#define MX21_INT_NANDFC		29
+#define MX21_INT_NFC		29
 #define MX21_INT_BMI		30
 #define MX21_INT_CSI		31
 #define MX21_INT_DMACH0		32
diff --git a/arch/arm/plat-mxc/include/mach/mx25.h b/arch/arm/plat-mxc/include/mach/mx25.h
index 4a6f800..cf46a45 100644
--- a/arch/arm/plat-mxc/include/mach/mx25.h
+++ b/arch/arm/plat-mxc/include/mach/mx25.h
@@ -50,8 +50,11 @@
 #define MX25_SSI1_BASE_ADDR		0x50034000
 #define MX25_NFC_BASE_ADDR		0xbb000000
 #define MX25_DRYICE_BASE_ADDR		0x53ffc000
+#define MX25_ESDHC1_BASE_ADDR		0x53fb4000
+#define MX25_ESDHC2_BASE_ADDR		0x53fb8000
 #define MX25_LCDC_BASE_ADDR		0x53fbc000
 #define MX25_KPP_BASE_ADDR		0x43fa8000
+#define MX25_SDMA_BASE_ADDR		0x53fd4000
 #define MX25_OTG_BASE_ADDR		0x53ff4000
 #define MX25_CSI_BASE_ADDR		0x53ff8000
 
@@ -59,6 +62,8 @@
 #define MX25_INT_I2C1		3
 #define MX25_INT_I2C2		4
 #define MX25_INT_UART4		5
+#define MX25_INT_ESDHC2		8
+#define MX25_INT_ESDHC1		9
 #define MX25_INT_I2C3		10
 #define MX25_INT_SSI2		11
 #define MX25_INT_SSI1		12
@@ -69,7 +74,8 @@
 #define MX25_INT_KPP		24
 #define MX25_INT_DRYICE		25
 #define MX25_INT_UART2		32
-#define MX25_INT_NANDFC		33
+#define MX25_INT_NFC		33
+#define MX25_INT_SDMA		34
 #define MX25_INT_LCDC		39
 #define MX25_INT_UART5		40
 #define MX25_INT_CAN1		43
@@ -77,4 +83,13 @@
 #define MX25_INT_UART1		45
 #define MX25_INT_FEC		57
 
+#define MX25_DMA_REQ_SSI2_RX1	22
+#define MX25_DMA_REQ_SSI2_TX1	23
+#define MX25_DMA_REQ_SSI2_RX0	24
+#define MX25_DMA_REQ_SSI2_TX0	25
+#define MX25_DMA_REQ_SSI1_RX1	26
+#define MX25_DMA_REQ_SSI1_TX1	27
+#define MX25_DMA_REQ_SSI1_RX0	28
+#define MX25_DMA_REQ_SSI1_TX0	29
+
 #endif /* ifndef __MACH_MX25_H__ */
diff --git a/arch/arm/plat-mxc/include/mach/mx27.h b/arch/arm/plat-mxc/include/mach/mx27.h
index a8ab2e0..2237ba2 100644
--- a/arch/arm/plat-mxc/include/mach/mx27.h
+++ b/arch/arm/plat-mxc/include/mach/mx27.h
@@ -167,7 +167,7 @@
 #define MX27_INT_GPT1		26
 #define MX27_INT_WDOG		27
 #define MX27_INT_PCMCIA		28
-#define MX27_INT_NANDFC		29
+#define MX27_INT_NFC		29
 #define MX27_INT_ATA		30
 #define MX27_INT_CSI		31
 #define MX27_INT_DMACH0		32
diff --git a/arch/arm/plat-mxc/include/mach/mx31.h b/arch/arm/plat-mxc/include/mach/mx31.h
index afee3ab..03e2afa 100644
--- a/arch/arm/plat-mxc/include/mach/mx31.h
+++ b/arch/arm/plat-mxc/include/mach/mx31.h
@@ -168,7 +168,7 @@
 #define MX31_INT_POWER_FAIL	30
 #define MX31_INT_CCM_DVFS	31
 #define MX31_INT_UART2		32
-#define MX31_INT_NANDFC		33
+#define MX31_INT_NFC		33
 #define MX31_INT_SDMA		34
 #define MX31_INT_USB1		35
 #define MX31_INT_USB2		36
@@ -197,6 +197,15 @@
 #define MX31_INT_EXT_WDOG	62
 #define MX31_INT_EXT_TV		63
 
+#define MX31_DMA_REQ_SSI2_RX1	22
+#define MX31_DMA_REQ_SSI2_TX1	23
+#define MX31_DMA_REQ_SSI2_RX0	24
+#define MX31_DMA_REQ_SSI2_TX0	25
+#define MX31_DMA_REQ_SSI1_RX1	26
+#define MX31_DMA_REQ_SSI1_TX1	27
+#define MX31_DMA_REQ_SSI1_RX0	28
+#define MX31_DMA_REQ_SSI1_TX0	29
+
 #define MX31_PROD_SIGNATURE		0x1	/* For MX31 */
 
 /* silicon revisions specific to i.MX31 */
diff --git a/arch/arm/plat-mxc/include/mach/mx35.h b/arch/arm/plat-mxc/include/mach/mx35.h
index af3038c..ff905cb 100644
--- a/arch/arm/plat-mxc/include/mach/mx35.h
+++ b/arch/arm/plat-mxc/include/mach/mx35.h
@@ -1,5 +1,6 @@
 #ifndef __MACH_MX35_H__
 #define __MACH_MX35_H__
+
 /*
  * IRAM
  */
@@ -52,6 +53,9 @@
 #define MX35_GPIO3_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xa4000)
 #define MX35_SCC_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xac000)
 #define MX35_RNGA_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xb0000)
+#define MX35_ESDHC1_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xb4000)
+#define MX35_ESDHC2_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xb8000)
+#define MX35_ESDHC3_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xbc000)
 #define MX35_IPU_CTRL_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xc0000)
 #define MX35_AUDMUX_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xc4000)
 #define MX35_GPIO1_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xcc000)
@@ -63,6 +67,8 @@
 #define MX35_CAN1_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xe4000)
 #define MX35_CAN2_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xe8000)
 #define MX35_RTIC_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xec000)
+#define MX35_IIM_BASE_ADDR			(MX35_AIPS2_BASE_ADDR + 0xf0000)
+
 #define MX35_OTG_BASE_ADDR		0x53ff4000
 
 #define MX35_ROMP_BASE_ADDR		0x60000000
@@ -122,9 +128,9 @@
 #define MX35_INT_I2C3		3
 #define MX35_INT_I2C2		4
 #define MX35_INT_RTIC		6
-#define MX35_INT_MMC_SDHC1	7
-#define MX35_INT_MMC_SDHC2	8
-#define MX35_INT_MMC_SDHC3	9
+#define MX35_INT_ESDHC1		7
+#define MX35_INT_ESDHC2		8
+#define MX35_INT_ESDHC3		9
 #define MX35_INT_I2C1		10
 #define MX35_INT_SSI1		11
 #define MX35_INT_SSI2		12
@@ -145,7 +151,7 @@
 #define MX35_INT_GPT		29
 #define MX35_INT_POWER_FAIL	30
 #define MX35_INT_UART2		32
-#define MX35_INT_NANDFC		33
+#define MX35_INT_NFC		33
 #define MX35_INT_SDMA		34
 #define MX35_INT_USBHS		35
 #define MX35_INT_USBOTG		37
@@ -173,22 +179,18 @@
 #define MX35_INT_EXT_WDOG	62
 #define MX35_INT_EXT_TV		63
 
+#define MX35_DMA_REQ_SSI2_RX1   22
+#define MX35_DMA_REQ_SSI2_TX1   23
+#define MX35_DMA_REQ_SSI2_RX0   24
+#define MX35_DMA_REQ_SSI2_TX0   25
+#define MX35_DMA_REQ_SSI1_RX1   26
+#define MX35_DMA_REQ_SSI1_TX1   27
+#define MX35_DMA_REQ_SSI1_RX0   28
+#define MX35_DMA_REQ_SSI1_TX0   29
+
 #define MX35_PROD_SIGNATURE		0x1	/* For MX31 */
 
-/* silicon revisions specific to i.MX31 */
-#define MX35_CHIP_REV_1_0		0x10
-#define MX35_CHIP_REV_1_1		0x11
-#define MX35_CHIP_REV_1_2		0x12
-#define MX35_CHIP_REV_1_3		0x13
-#define MX35_CHIP_REV_2_0		0x20
-#define MX35_CHIP_REV_2_1		0x21
-#define MX35_CHIP_REV_2_2		0x22
-#define MX35_CHIP_REV_2_3		0x23
-#define MX35_CHIP_REV_3_0		0x30
-#define MX35_CHIP_REV_3_1		0x31
-#define MX35_CHIP_REV_3_2		0x32
-
-#define MX35_SYSTEM_REV_MIN		MX35_CHIP_REV_1_0
+#define MX35_SYSTEM_REV_MIN		MX3x_CHIP_REV_1_0
 #define MX35_SYSTEM_REV_NUM		3
 
 #ifdef IMX_NEEDS_DEPRECATED_SYMBOLS
diff --git a/arch/arm/plat-mxc/include/mach/mx3x.h b/arch/arm/plat-mxc/include/mach/mx3x.h
index 7a356de3..d1bd26d 100644
--- a/arch/arm/plat-mxc/include/mach/mx3x.h
+++ b/arch/arm/plat-mxc/include/mach/mx3x.h
@@ -240,7 +240,7 @@
 
 #define MX3x_PROD_SIGNATURE		0x1	/* For MX31 */
 
-/* silicon revisions specific to i.MX31 */
+/* silicon revisions specific to i.MX31 and i.MX35 */
 #define MX3x_CHIP_REV_1_0		0x10
 #define MX3x_CHIP_REV_1_1		0x11
 #define MX3x_CHIP_REV_1_2		0x12
@@ -267,6 +267,14 @@
 {
 	return mx31_cpu_rev;
 }
+
+extern unsigned int mx35_cpu_rev;
+extern void mx35_read_cpu_rev(void);
+
+static inline int mx35_revision(void)
+{
+	return mx35_cpu_rev;
+}
 #endif
 
 #ifdef IMX_NEEDS_DEPRECATED_SYMBOLS
@@ -389,19 +397,6 @@
 #define MXC_INT_EXT_WDOG MX3x_INT_EXT_WDOG
 #define MXC_INT_EXT_TV MX3x_INT_EXT_TV
 #define PROD_SIGNATURE MX3x_PROD_SIGNATURE
-#define CHIP_REV_1_0 MX3x_CHIP_REV_1_0
-#define CHIP_REV_1_1 MX3x_CHIP_REV_1_1
-#define CHIP_REV_1_2 MX3x_CHIP_REV_1_2
-#define CHIP_REV_1_3 MX3x_CHIP_REV_1_3
-#define CHIP_REV_2_0 MX3x_CHIP_REV_2_0
-#define CHIP_REV_2_1 MX3x_CHIP_REV_2_1
-#define CHIP_REV_2_2 MX3x_CHIP_REV_2_2
-#define CHIP_REV_2_3 MX3x_CHIP_REV_2_3
-#define CHIP_REV_3_0 MX3x_CHIP_REV_3_0
-#define CHIP_REV_3_1 MX3x_CHIP_REV_3_1
-#define CHIP_REV_3_2 MX3x_CHIP_REV_3_2
-#define SYSTEM_REV_MIN MX3x_SYSTEM_REV_MIN
-#define SYSTEM_REV_NUM MX3x_SYSTEM_REV_NUM
 #endif
 
 #endif /* ifndef __MACH_MX3x_H__ */
diff --git a/arch/arm/plat-mxc/include/mach/mx51.h b/arch/arm/plat-mxc/include/mach/mx51.h
index 5aad344..2af7a10 100644
--- a/arch/arm/plat-mxc/include/mach/mx51.h
+++ b/arch/arm/plat-mxc/include/mach/mx51.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_ARCH_MXC_MX51_H__
-#define __ASM_ARCH_MXC_MX51_H__
+#ifndef __MACH_MX51_H__
+#define __MACH_MX51_H__
 
 /*
  * MX51 memory map:
@@ -7,24 +7,23 @@
  *
  * Virt		Phys		Size	What
  * ---------------------------------------------------------------------------
- * FA3E0000	1FFE0000	128K	IRAM (SCCv2 RAM)
+ * fa3e0000	1ffe0000	128K	IRAM (SCCv2 RAM)
  *         	30000000	256M	GPU
  *         	40000000	512M	IPU
- * FA200000	60000000	1M	DEBUG
- * FB100000	70000000	1M	SPBA 0
- * FB000000	73F00000	1M	AIPS 1
- * FB200000	83F00000	1M	AIPS 2
- *		8FFFC000	16K	TZIC (interrupt controller)
+ * fa200000	60000000	1M	DEBUG
+ * fb100000	70000000	1M	SPBA 0
+ * fb000000	73f00000	1M	AIPS 1
+ * fb200000	83f00000	1M	AIPS 2
+ *		8fffc000	16K	TZIC (interrupt controller)
  *         	90000000	256M	CSD0 SDRAM/DDR
- *         	A0000000	256M	CSD1 SDRAM/DDR
- *         	B0000000	128M	CS0 Flash
- *         	B8000000	128M	CS1 Flash
- *         	C0000000	128M	CS2 Flash
- *         	C8000000	64M	CS3 Flash
- *         	CC000000	32M	CS4 SRAM
- *         	CE000000	32M	CS5 SRAM
- *		CFFF0000	64K	NFC (NAND Flash AXI)
- *
+ *         	a0000000	256M	CSD1 SDRAM/DDR
+ *         	b0000000	128M	CS0 Flash
+ *         	b8000000	128M	CS1 Flash
+ *         	c0000000	128M	CS2 Flash
+ *         	c8000000	64M	CS3 Flash
+ *         	cc000000	32M	CS4 SRAM
+ *         	ce000000	32M	CS5 SRAM
+ *		cfff0000	64K	NFC (NAND Flash AXI)
  */
 
 /*
@@ -36,65 +35,151 @@
 /*
  * IRAM
  */
-#define MX51_IRAM_BASE_ADDR		0x1FFE0000	/* internal ram */
-#define MX51_IRAM_BASE_ADDR_VIRT	0xFA3E0000
+#define MX51_IRAM_BASE_ADDR		0x1ffe0000	/* internal ram */
+#define MX51_IRAM_BASE_ADDR_VIRT	0xfa3e0000
 #define MX51_IRAM_PARTITIONS		16
-#define MX51_IRAM_PARTITIONS_TO1	12
 #define MX51_IRAM_SIZE		(MX51_IRAM_PARTITIONS * SZ_8K)	/* 128KB */
 
-/*
- * NFC
- */
-#define MX51_NFC_AXI_BASE_ADDR		0xCFFF0000	/* NAND flash AXI */
-#define MX51_NFC_AXI_SIZE		SZ_64K
-
-/*
- * Graphics Memory of GPU
- */
 #define MX51_GPU_BASE_ADDR		0x20000000
-#define MX51_GPU2D_BASE_ADDR		0xD0000000
-
-#define MX51_TZIC_BASE_ADDR_TO1		0x8FFFC000
-#define MX51_TZIC_BASE_ADDR		0xE0000000
+#define MX51_GPU_CTRL_BASE_ADDR		0x30000000
+#define MX51_IPU_CTRL_BASE_ADDR		0x40000000
 
 #define MX51_DEBUG_BASE_ADDR		0x60000000
-#define MX51_DEBUG_BASE_ADDR_VIRT	0xFA200000
+#define MX51_DEBUG_BASE_ADDR_VIRT	0xfa200000
 #define MX51_DEBUG_SIZE			SZ_1M
-#define MX51_ETB_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x00001000)
-#define MX51_ETM_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x00002000)
-#define MX51_TPIU_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x00003000)
-#define MX51_CTI0_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x00004000)
-#define MX51_CTI1_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x00005000)
-#define MX51_CTI2_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x00006000)
-#define MX51_CTI3_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x00007000)
-#define MX51_CORTEX_DBG_BASE_ADDR	(MX51_DEBUG_BASE_ADDR + 0x00008000)
+
+#define MX51_ETB_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x01000)
+#define MX51_ETM_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x02000)
+#define MX51_TPIU_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x03000)
+#define MX51_CTI0_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x04000)
+#define MX51_CTI1_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x05000)
+#define MX51_CTI2_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x06000)
+#define MX51_CTI3_BASE_ADDR		(MX51_DEBUG_BASE_ADDR + 0x07000)
+#define MX51_CORTEX_DBG_BASE_ADDR	(MX51_DEBUG_BASE_ADDR + 0x08000)
 
 /*
  * SPBA global module enabled #0
  */
-#define MX51_SPBA0_BASE_ADDR 		0x70000000
-#define MX51_SPBA0_BASE_ADDR_VIRT	0xFB100000
+#define MX51_SPBA0_BASE_ADDR		0x70000000
+#define MX51_SPBA0_BASE_ADDR_VIRT	0xfb100000
 #define MX51_SPBA0_SIZE			SZ_1M
 
-#define MX51_MMC_SDHC1_BASE_ADDR	(MX51_SPBA0_BASE_ADDR + 0x00004000)
-#define MX51_MMC_SDHC2_BASE_ADDR	(MX51_SPBA0_BASE_ADDR + 0x00008000)
-#define MX51_UART3_BASE_ADDR 		(MX51_SPBA0_BASE_ADDR + 0x0000C000)
-#define MX51_CSPI1_BASE_ADDR 		(MX51_SPBA0_BASE_ADDR + 0x00010000)
-#define MX51_SSI2_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x00014000)
-#define MX51_MMC_SDHC3_BASE_ADDR	(MX51_SPBA0_BASE_ADDR + 0x00020000)
-#define MX51_MMC_SDHC4_BASE_ADDR	(MX51_SPBA0_BASE_ADDR + 0x00024000)
-#define MX51_SPDIF_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x00028000)
-#define MX51_ATA_DMA_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x00030000)
-#define MX51_SLIM_DMA_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x00034000)
-#define MX51_HSI2C_DMA_BASE_ADDR	(MX51_SPBA0_BASE_ADDR + 0x00038000)
-#define MX51_SPBA_CTRL_BASE_ADDR	(MX51_SPBA0_BASE_ADDR + 0x0003C000)
+#define MX51_ESDHC1_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x04000)
+#define MX51_ESDHC2_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x08000)
+#define MX51_UART3_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x0c000)
+#define MX51_ECSPI1_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x10000)
+#define MX51_SSI2_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x14000)
+#define MX51_ESDHC3_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x20000)
+#define MX51_ESDHC4_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x24000)
+#define MX51_SPDIF_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x28000)
+#define MX51_ATA_DMA_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x30000)
+#define MX51_SLIM_DMA_BASE_ADDR		(MX51_SPBA0_BASE_ADDR + 0x34000)
+#define MX51_HSI2C_DMA_BASE_ADDR	(MX51_SPBA0_BASE_ADDR + 0x38000)
+#define MX51_SPBA_CTRL_BASE_ADDR	(MX51_SPBA0_BASE_ADDR + 0x3c000)
+
+/*
+ * AIPS 1
+ */
+#define MX51_AIPS1_BASE_ADDR		0x73f00000
+#define MX51_AIPS1_BASE_ADDR_VIRT	0xfb000000
+#define MX51_AIPS1_SIZE			SZ_1M
+
+#define MX51_OTG_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0x80000)
+#define MX51_GPIO1_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0x84000)
+#define MX51_GPIO2_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0x88000)
+#define MX51_GPIO3_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0x8c000)
+#define MX51_GPIO4_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0x90000)
+#define MX51_KPP_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0x94000)
+#define MX51_WDOG_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0x98000)
+#define MX51_WDOG2_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0x9c000)
+#define MX51_GPT1_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xa0000)
+#define MX51_SRTC_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xa4000)
+#define MX51_IOMUXC_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xa8000)
+#define MX51_EPIT1_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xac000)
+#define MX51_EPIT2_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xb0000)
+#define MX51_PWM1_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xb4000)
+#define MX51_PWM2_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xb8000)
+#define MX51_UART1_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xbc000)
+#define MX51_UART2_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xc0000)
+#define MX51_SRC_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xd0000)
+#define MX51_CCM_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xd4000)
+#define MX51_GPC_BASE_ADDR		(MX51_AIPS1_BASE_ADDR + 0xd8000)
+
+/*
+ * AIPS 2
+ */
+#define MX51_AIPS2_BASE_ADDR		0x83f00000
+#define MX51_AIPS2_BASE_ADDR_VIRT	0xfb200000
+#define MX51_AIPS2_SIZE			SZ_1M
+
+#define MX51_PLL1_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0x80000)
+#define MX51_PLL2_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0x84000)
+#define MX51_PLL3_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0x88000)
+#define MX51_AHBMAX_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0x94000)
+#define MX51_IIM_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0x98000)
+#define MX51_CSU_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0x9c000)
+#define MX51_ARM_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xa0000)
+#define MX51_OWIRE_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xa4000)
+#define MX51_FIRI_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xa8000)
+#define MX51_ECSPI2_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xac000)
+#define MX51_SDMA_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xb0000)
+#define MX51_SCC_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xb4000)
+#define MX51_ROMCP_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xb8000)
+#define MX51_RTIC_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xbc000)
+#define MX51_CSPI_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xc0000)
+#define MX51_I2C2_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xc4000)
+#define MX51_I2C1_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xc8000)
+#define MX51_SSI1_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xcc000)
+#define MX51_AUDMUX_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xd0000)
+#define MX51_M4IF_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xd8000)
+#define MX51_ESDCTL_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xd9000)
+#define MX51_WEIM_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xda000)
+#define MX51_NFC_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xdb000)
+#define MX51_EMI_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xdbf00)
+#define MX51_MIPI_HSC_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xdc000)
+#define MX51_ATA_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xe0000)
+#define MX51_SIM_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xe4000)
+#define MX51_SSI3BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xe8000)
+#define MX51_FEC_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xec000)
+#define MX51_TVE_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xf0000)
+#define MX51_VPU_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xf4000)
+#define MX51_SAHARA_BASE_ADDR		(MX51_AIPS2_BASE_ADDR + 0xf8000)
+
+#define MX51_CSD0_BASE_ADDR		0x90000000
+#define MX51_CSD1_BASE_ADDR		0xa0000000
+#define MX51_CS0_BASE_ADDR		0xb0000000
+#define MX51_CS1_BASE_ADDR		0xb8000000
+#define MX51_CS2_BASE_ADDR		0xc0000000
+#define MX51_CS3_BASE_ADDR		0xc8000000
+#define MX51_CS4_BASE_ADDR		0xcc000000
+#define MX51_CS5_BASE_ADDR		0xce000000
+
+/*
+ * NFC
+ */
+#define MX51_NFC_AXI_BASE_ADDR		0xcfff0000	/* NAND flash AXI */
+#define MX51_NFC_AXI_SIZE		SZ_64K
+
+#define MX51_GPU2D_BASE_ADDR		0xd0000000
+#define MX51_TZIC_BASE_ADDR		0xe0000000
+
+#define MX51_IO_ADDRESS(x) (						\
+	IMX_IO_ADDRESS(x, MX51_IRAM) ?:					\
+	IMX_IO_ADDRESS(x, MX51_DEBUG) ?:				\
+	IMX_IO_ADDRESS(x, MX51_SPBA0) ?:				\
+	IMX_IO_ADDRESS(x, MX51_AIPS1) ?:				\
+	IMX_IO_ADDRESS(x, MX51_AIPS2))
+
+/* This is currently used in <mach/debug-macro.S>, but should go away */
+#define MX51_AIPS1_IO_ADDRESS(x)  \
+	(((x) - MX51_AIPS1_BASE_ADDR) + MX51_AIPS1_BASE_ADDR_VIRT)
 
 /*
  * defines for SPBA modules
  */
 #define MX51_SPBA_SDHC1	0x04
 #define MX51_SPBA_SDHC2	0x08
-#define MX51_SPBA_UART3	0x0C
+#define MX51_SPBA_UART3	0x0c
 #define MX51_SPBA_CSPI1	0x10
 #define MX51_SPBA_SSI2	0x14
 #define MX51_SPBA_SDHC3	0x20
@@ -103,35 +188,7 @@
 #define MX51_SPBA_ATA	0x30
 #define MX51_SPBA_SLIM	0x34
 #define MX51_SPBA_HSI2C	0x38
-#define MX51_SPBA_CTRL	0x3C
-
-/*
- * AIPS 1
- */
-#define MX51_AIPS1_BASE_ADDR 	0x73F00000
-#define MX51_AIPS1_BASE_ADDR_VIRT	0xFB000000
-#define MX51_AIPS1_SIZE		SZ_1M
-
-#define MX51_OTG_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x00080000)
-#define MX51_GPIO1_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x00084000)
-#define MX51_GPIO2_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x00088000)
-#define MX51_GPIO3_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x0008C000)
-#define MX51_GPIO4_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x00090000)
-#define MX51_KPP_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x00094000)
-#define MX51_WDOG_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x00098000)
-#define MX51_WDOG2_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x0009C000)
-#define MX51_GPT1_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000A0000)
-#define MX51_SRTC_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000A4000)
-#define MX51_IOMUXC_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000A8000)
-#define MX51_EPIT1_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000AC000)
-#define MX51_EPIT2_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000B0000)
-#define MX51_PWM1_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000B4000)
-#define MX51_PWM2_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000B8000)
-#define MX51_UART1_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000BC000)
-#define MX51_UART2_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000C0000)
-#define MX51_SRC_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000D0000)
-#define MX51_CCM_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000D4000)
-#define MX51_GPC_BASE_ADDR	(MX51_AIPS1_BASE_ADDR + 0x000D8000)
+#define MX51_SPBA_CTRL	0x3c
 
 /*
  * Defines for modules using static and dynamic DMA channels
@@ -164,282 +221,186 @@
 #define MX51_MXC_DMA_CHANNEL_ATA_TX	MXC_DMA_DYNAMIC_CHANNEL
 #define MX51_MXC_DMA_CHANNEL_MEMORY	MXC_DMA_DYNAMIC_CHANNEL
 
-/*
- * AIPS 2
- */
-#define MX51_AIPS2_BASE_ADDR		0x83F00000
-#define MX51_AIPS2_BASE_ADDR_VIRT	0xFB200000
-#define MX51_AIPS2_SIZE			SZ_1M
-
-#define MX51_PLL1_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x00080000)
-#define MX51_PLL2_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x00084000)
-#define MX51_PLL3_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x00088000)
-#define MX51_AHBMAX_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x00094000)
-#define MX51_IIM_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x00098000)
-#define MX51_CSU_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x0009C000)
-#define MX51_ARM_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000A0000)
-#define MX51_OWIRE_BASE_ADDR 	(MX51_AIPS2_BASE_ADDR + 0x000A4000)
-#define MX51_FIRI_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000A8000)
-#define MX51_CSPI2_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000AC000)
-#define MX51_SDMA_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000B0000)
-#define MX51_SCC_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000B4000)
-#define MX51_ROMCP_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000B8000)
-#define MX51_RTIC_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000BC000)
-#define MX51_CSPI3_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000C0000)
-#define MX51_I2C2_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000C4000)
-#define MX51_I2C1_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000C8000)
-#define MX51_SSI1_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000CC000)
-#define MX51_AUDMUX_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000D0000)
-#define MX51_M4IF_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000D8000)
-#define MX51_ESDCTL_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000D9000)
-#define MX51_WEIM_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000DA000)
-#define MX51_NFC_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000DB000)
-#define MX51_EMI_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000DBF00)
-#define MX51_MIPI_HSC_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000DC000)
-#define MX51_ATA_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000E0000)
-#define MX51_SIM_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000E4000)
-#define MX51_SSI3BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000E8000)
-#define MX51_MXC_FEC_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000EC000)
-#define MX51_TVE_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000F0000)
-#define MX51_VPU_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000F4000)
-#define MX51_SAHARA_BASE_ADDR	(MX51_AIPS2_BASE_ADDR + 0x000F8000)
-
-/*
- * Memory regions and CS
- */
-#define MX51_GPU_CTRL_BASE_ADDR		0x30000000
-#define MX51_IPU_CTRL_BASE_ADDR		0x40000000
-#define MX51_CSD0_BASE_ADDR		0x90000000
-#define MX51_CSD1_BASE_ADDR		0xA0000000
-#define MX51_CS0_BASE_ADDR		0xB0000000
-#define MX51_CS1_BASE_ADDR		0xB8000000
-#define MX51_CS2_BASE_ADDR		0xC0000000
-#define MX51_CS3_BASE_ADDR		0xC8000000
-#define MX51_CS4_BASE_ADDR		0xCC000000
-#define MX51_CS5_BASE_ADDR		0xCE000000
-
-/* Does given address belongs to the specified memory region? */
-#define ADDRESS_IN_REGION(addr, start, size)			\
-	(((addr) >= (start)) && ((addr) < (start)+(size)))
-
-/* Does given address belongs to the specified named `module'? */
-#define MX51_IS_MODULE(addr, module)			       \
-	ADDRESS_IN_REGION(addr, MX51_ ## module ## _BASE_ADDR, \
-				MX51_ ## module ## _SIZE)
-/*
- * This macro defines the physical to virtual address mapping for all the
- * peripheral modules. It is used by passing in the physical address as x
- * and returning the virtual address. If the physical address is not mapped,
- * it returns 0xDEADBEEF
- */
-
-#define MX51_IO_ADDRESS(x)					\
-	(void __iomem *)					\
-	(MX51_IS_MODULE(x, IRAM) ? MX51_IRAM_IO_ADDRESS(x) :	\
-	MX51_IS_MODULE(x, DEBUG) ? MX51_DEBUG_IO_ADDRESS(x) :	\
-	MX51_IS_MODULE(x, SPBA0) ? MX51_SPBA0_IO_ADDRESS(x) :	\
-	MX51_IS_MODULE(x, AIPS1) ? MX51_AIPS1_IO_ADDRESS(x) :	\
-	MX51_IS_MODULE(x, AIPS2) ? MX51_AIPS2_IO_ADDRESS(x) : \
-	0xDEADBEEF)
-
-/*
- * define the address mapping macros: in physical address order
- */
-#define MX51_IRAM_IO_ADDRESS(x)  \
-	(((x) - MX51_IRAM_BASE_ADDR) + MX51_IRAM_BASE_ADDR_VIRT)
-
-#define MX51_DEBUG_IO_ADDRESS(x)  \
-	(((x) - MX51_DEBUG_BASE_ADDR) + MX51_DEBUG_BASE_ADDR_VIRT)
-
-#define MX51_SPBA0_IO_ADDRESS(x)  \
-	(((x) - MX51_SPBA0_BASE_ADDR) + MX51_SPBA0_BASE_ADDR_VIRT)
-
-#define MX51_AIPS1_IO_ADDRESS(x)  \
-	(((x) - MX51_AIPS1_BASE_ADDR) + MX51_AIPS1_BASE_ADDR_VIRT)
-
-#define MX51_AIPS2_IO_ADDRESS(x)  \
-	(((x) - MX51_AIPS2_BASE_ADDR) + MX51_AIPS2_BASE_ADDR_VIRT)
-
 #define MX51_IS_MEM_DEVICE_NONSHARED(x)		0
 
 /*
  * DMA request assignments
  */
-#define MX51_DMA_REQ_SSI3_TX1	47
-#define MX51_DMA_REQ_SSI3_RX1	46
-#define MX51_DMA_REQ_SPDIF	45
-#define MX51_DMA_REQ_UART3_TX	44
-#define MX51_DMA_REQ_UART3_RX	43
-#define MX51_DMA_REQ_SLIM_B_TX	42
-#define MX51_DMA_REQ_SDHC4	41
-#define MX51_DMA_REQ_SDHC3	40
-#define MX51_DMA_REQ_CSPI_TX	39
-#define MX51_DMA_REQ_CSPI_RX	38
-#define MX51_DMA_REQ_SSI3_TX2	37
-#define MX51_DMA_REQ_IPU	36
-#define MX51_DMA_REQ_SSI3_RX2	35
-#define MX51_DMA_REQ_EPIT2	34
-#define MX51_DMA_REQ_CTI2_1	33
-#define MX51_DMA_REQ_EMI_WR	32
-#define MX51_DMA_REQ_CTI2_0	31
-#define MX51_DMA_REQ_EMI_RD	30
-#define MX51_DMA_REQ_SSI1_TX1	29
-#define MX51_DMA_REQ_SSI1_RX1	28
-#define MX51_DMA_REQ_SSI1_TX2	27
-#define MX51_DMA_REQ_SSI1_RX2	26
-#define MX51_DMA_REQ_SSI2_TX1	25
-#define MX51_DMA_REQ_SSI2_RX1	24
-#define MX51_DMA_REQ_SSI2_TX2	23
-#define MX51_DMA_REQ_SSI2_RX2	22
-#define MX51_DMA_REQ_SDHC2	21
-#define MX51_DMA_REQ_SDHC1	20
-#define MX51_DMA_REQ_UART1_TX	19
-#define MX51_DMA_REQ_UART1_RX	18
-#define MX51_DMA_REQ_UART2_TX	17
-#define MX51_DMA_REQ_UART2_RX	16
-#define MX51_DMA_REQ_GPU	15
-#define MX51_DMA_REQ_EXTREQ1	14
-#define MX51_DMA_REQ_FIRI_TX	13
-#define MX51_DMA_REQ_FIRI_RX	12
-#define MX51_DMA_REQ_HS_I2C_RX	11
-#define MX51_DMA_REQ_HS_I2C_TX	10
-#define MX51_DMA_REQ_CSPI2_TX	9
-#define MX51_DMA_REQ_CSPI2_RX	8
-#define MX51_DMA_REQ_CSPI1_TX	7
-#define MX51_DMA_REQ_CSPI1_RX	6
-#define MX51_DMA_REQ_SLIM_B	5
-#define MX51_DMA_REQ_ATA_TX_END	4
-#define MX51_DMA_REQ_ATA_TX	3
-#define MX51_DMA_REQ_ATA_RX	2
-#define MX51_DMA_REQ_GPC	1
-#define MX51_DMA_REQ_VPU	0
+#define MX51_DMA_REQ_VPU		0
+#define MX51_DMA_REQ_GPC		1
+#define MX51_DMA_REQ_ATA_RX		2
+#define MX51_DMA_REQ_ATA_TX		3
+#define MX51_DMA_REQ_ATA_TX_END		4
+#define MX51_DMA_REQ_SLIM_B		5
+#define MX51_DMA_REQ_CSPI1_RX		6
+#define MX51_DMA_REQ_CSPI1_TX		7
+#define MX51_DMA_REQ_CSPI2_RX		8
+#define MX51_DMA_REQ_CSPI2_TX		9
+#define MX51_DMA_REQ_HS_I2C_TX		10
+#define MX51_DMA_REQ_HS_I2C_RX		11
+#define MX51_DMA_REQ_FIRI_RX		12
+#define MX51_DMA_REQ_FIRI_TX		13
+#define MX51_DMA_REQ_EXTREQ1		14
+#define MX51_DMA_REQ_GPU		15
+#define MX51_DMA_REQ_UART2_RX		16
+#define MX51_DMA_REQ_UART2_TX		17
+#define MX51_DMA_REQ_UART1_RX		18
+#define MX51_DMA_REQ_UART1_TX		19
+#define MX51_DMA_REQ_SDHC1		20
+#define MX51_DMA_REQ_SDHC2		21
+#define MX51_DMA_REQ_SSI2_RX1		22
+#define MX51_DMA_REQ_SSI2_TX1		23
+#define MX51_DMA_REQ_SSI2_RX0		24
+#define MX51_DMA_REQ_SSI2_TX0		25
+#define MX51_DMA_REQ_SSI1_RX1		26
+#define MX51_DMA_REQ_SSI1_TX1		27
+#define MX51_DMA_REQ_SSI1_RX0		28
+#define MX51_DMA_REQ_SSI1_TX0		29
+#define MX51_DMA_REQ_EMI_RD		30
+#define MX51_DMA_REQ_CTI2_0		31
+#define MX51_DMA_REQ_EMI_WR		32
+#define MX51_DMA_REQ_CTI2_1		33
+#define MX51_DMA_REQ_EPIT2		34
+#define MX51_DMA_REQ_SSI3_RX2		35
+#define MX51_DMA_REQ_IPU		36
+#define MX51_DMA_REQ_SSI3_TX2		37
+#define MX51_DMA_REQ_CSPI_RX		38
+#define MX51_DMA_REQ_CSPI_TX		39
+#define MX51_DMA_REQ_SDHC3		40
+#define MX51_DMA_REQ_SDHC4		41
+#define MX51_DMA_REQ_SLIM_B_TX		42
+#define MX51_DMA_REQ_UART3_RX		43
+#define MX51_DMA_REQ_UART3_TX		44
+#define MX51_DMA_REQ_SPDIF		45
+#define MX51_DMA_REQ_SSI3_RX1		46
+#define MX51_DMA_REQ_SSI3_TX1		47
 
 /*
  * Interrupt numbers
  */
-#define MX51_MXC_INT_BASE	0
-#define MX51_MXC_INT_RESV0	0
-#define MX51_MXC_INT_MMC_SDHC1	1
-#define MX51_MXC_INT_MMC_SDHC2	2
-#define MX51_MXC_INT_MMC_SDHC3	3
-#define MX51_MXC_INT_MMC_SDHC4	4
-#define MX51_MXC_INT_RESV5	5
-#define MX51_MXC_INT_SDMA	6
-#define MX51_MXC_INT_IOMUX	7
-#define MX51_MXC_INT_NFC	8
-#define MX51_MXC_INT_VPU	9
-#define MX51_MXC_INT_IPU_ERR	10
-#define MX51_MXC_INT_IPU_SYN	11
-#define MX51_MXC_INT_GPU	12
-#define MX51_MXC_INT_RESV13	13
-#define MX51_MXC_INT_USB_H1	14
-#define MX51_MXC_INT_EMI	15
-#define MX51_MXC_INT_USB_H2	16
-#define MX51_MXC_INT_USB_H3	17
-#define MX51_MXC_INT_USB_OTG	18
-#define MX51_MXC_INT_SAHARA_H0	19
-#define MX51_MXC_INT_SAHARA_H1	20
-#define MX51_MXC_INT_SCC_SMN	21
-#define MX51_MXC_INT_SCC_STZ	22
-#define MX51_MXC_INT_SCC_SCM	23
-#define MX51_MXC_INT_SRTC_NTZ	24
-#define MX51_MXC_INT_SRTC_TZ	25
-#define MX51_MXC_INT_RTIC	26
-#define MX51_MXC_INT_CSU	27
-#define MX51_MXC_INT_SLIM_B	28
-#define MX51_MXC_INT_SSI1	29
-#define MX51_MXC_INT_SSI2	30
-#define MX51_MXC_INT_UART1	31
-#define MX51_MXC_INT_UART2	32
-#define MX51_MXC_INT_UART3	33
-#define MX51_MXC_INT_RESV34	34
-#define MX51_MXC_INT_RESV35	35
-#define MX51_MXC_INT_CSPI1	36
-#define MX51_MXC_INT_CSPI2	37
-#define MX51_MXC_INT_CSPI	38
-#define MX51_MXC_INT_GPT	39
-#define MX51_MXC_INT_EPIT1	40
-#define MX51_MXC_INT_EPIT2	41
-#define MX51_MXC_INT_GPIO1_INT7	42
-#define MX51_MXC_INT_GPIO1_INT6	43
-#define MX51_MXC_INT_GPIO1_INT5	44
-#define MX51_MXC_INT_GPIO1_INT4	45
-#define MX51_MXC_INT_GPIO1_INT3	46
-#define MX51_MXC_INT_GPIO1_INT2	47
-#define MX51_MXC_INT_GPIO1_INT1	48
-#define MX51_MXC_INT_GPIO1_INT0	49
-#define MX51_MXC_INT_GPIO1_LOW	50
-#define MX51_MXC_INT_GPIO1_HIGH	51
-#define MX51_MXC_INT_GPIO2_LOW	52
-#define MX51_MXC_INT_GPIO2_HIGH	53
-#define MX51_MXC_INT_GPIO3_LOW	54
-#define MX51_MXC_INT_GPIO3_HIGH	55
-#define MX51_MXC_INT_GPIO4_LOW	56
-#define MX51_MXC_INT_GPIO4_HIGH	57
-#define MX51_MXC_INT_WDOG1	58
-#define MX51_MXC_INT_WDOG2	59
-#define MX51_MXC_INT_KPP	60
-#define MX51_MXC_INT_PWM1	61
-#define MX51_MXC_INT_I2C1	62
-#define MX51_MXC_INT_I2C2	63
-#define MX51_MXC_INT_HS_I2C	64
-#define MX51_MXC_INT_RESV65	65
-#define MX51_MXC_INT_RESV66	66
-#define MX51_MXC_INT_SIM_IPB	67
-#define MX51_MXC_INT_SIM_DAT	68
-#define MX51_MXC_INT_IIM	69
-#define MX51_MXC_INT_ATA	70
-#define MX51_MXC_INT_CCM1	71
-#define MX51_MXC_INT_CCM2	72
-#define MX51_MXC_INT_GPC1	73
-#define MX51_MXC_INT_GPC2	74
-#define MX51_MXC_INT_SRC	75
-#define MX51_MXC_INT_NM		76
-#define MX51_MXC_INT_PMU	77
-#define MX51_MXC_INT_CTI_IRQ	78
-#define MX51_MXC_INT_CTI1_TG0	79
-#define MX51_MXC_INT_CTI1_TG1	80
-#define MX51_MXC_INT_MCG_ERR	81
-#define MX51_MXC_INT_MCG_TMR	82
-#define MX51_MXC_INT_MCG_FUNC	83
-#define MX51_MXC_INT_GPU2_IRQ	84
-#define MX51_MXC_INT_GPU2_BUSY	85
-#define MX51_MXC_INT_RESV86	86
-#define MX51_MXC_INT_FEC	87
-#define MX51_MXC_INT_OWIRE	88
-#define MX51_MXC_INT_CTI1_TG2	89
-#define MX51_MXC_INT_SJC	90
-#define MX51_MXC_INT_SPDIF	91
-#define MX51_MXC_INT_TVE	92
-#define MX51_MXC_INT_FIRI	93
-#define MX51_MXC_INT_PWM2	94
-#define MX51_MXC_INT_SLIM_EXP	95
-#define MX51_MXC_INT_SSI3	96
-#define MX51_MXC_INT_EMI_BOOT	97
-#define MX51_MXC_INT_CTI1_TG3	98
-#define MX51_MXC_INT_SMC_RX	99
-#define MX51_MXC_INT_VPU_IDLE	100
-#define MX51_MXC_INT_EMI_NFC	101
-#define MX51_MXC_INT_GPU_IDLE	102
+#define MX51_MXC_INT_BASE		0
+#define MX51_MXC_INT_RESV0		0
+#define MX51_INT_ESDHC1			1
+#define MX51_INT_ESDHC2			2
+#define MX51_INT_ESDHC3			3
+#define MX51_INT_ESDHC4			4
+#define MX51_MXC_INT_RESV5		5
+#define MX51_INT_SDMA			6
+#define MX51_MXC_INT_IOMUX		7
+#define MX51_INT_NFC			8
+#define MX51_MXC_INT_VPU		9
+#define MX51_MXC_INT_IPU_ERR		10
+#define MX51_MXC_INT_IPU_SYN		11
+#define MX51_MXC_INT_GPU		12
+#define MX51_MXC_INT_RESV13		13
+#define MX51_MXC_INT_USB_H1		14
+#define MX51_MXC_INT_EMI		15
+#define MX51_MXC_INT_USB_H2		16
+#define MX51_MXC_INT_USB_H3		17
+#define MX51_MXC_INT_USB_OTG		18
+#define MX51_MXC_INT_SAHARA_H0		19
+#define MX51_MXC_INT_SAHARA_H1		20
+#define MX51_MXC_INT_SCC_SMN		21
+#define MX51_MXC_INT_SCC_STZ		22
+#define MX51_MXC_INT_SCC_SCM		23
+#define MX51_MXC_INT_SRTC_NTZ		24
+#define MX51_MXC_INT_SRTC_TZ		25
+#define MX51_MXC_INT_RTIC		26
+#define MX51_MXC_INT_CSU		27
+#define MX51_MXC_INT_SLIM_B		28
+#define MX51_INT_SSI1			29
+#define MX51_INT_SSI2			30
+#define MX51_INT_UART1			31
+#define MX51_INT_UART2			32
+#define MX51_INT_UART3			33
+#define MX51_MXC_INT_RESV34		34
+#define MX51_MXC_INT_RESV35		35
+#define MX51_INT_ECSPI1			36
+#define MX51_INT_ECSPI2			37
+#define MX51_INT_CSPI			38
+#define MX51_MXC_INT_GPT		39
+#define MX51_MXC_INT_EPIT1		40
+#define MX51_MXC_INT_EPIT2		41
+#define MX51_MXC_INT_GPIO1_INT7		42
+#define MX51_MXC_INT_GPIO1_INT6		43
+#define MX51_MXC_INT_GPIO1_INT5		44
+#define MX51_MXC_INT_GPIO1_INT4		45
+#define MX51_MXC_INT_GPIO1_INT3		46
+#define MX51_MXC_INT_GPIO1_INT2		47
+#define MX51_MXC_INT_GPIO1_INT1		48
+#define MX51_MXC_INT_GPIO1_INT0		49
+#define MX51_MXC_INT_GPIO1_LOW		50
+#define MX51_MXC_INT_GPIO1_HIGH		51
+#define MX51_MXC_INT_GPIO2_LOW		52
+#define MX51_MXC_INT_GPIO2_HIGH		53
+#define MX51_MXC_INT_GPIO3_LOW		54
+#define MX51_MXC_INT_GPIO3_HIGH		55
+#define MX51_MXC_INT_GPIO4_LOW		56
+#define MX51_MXC_INT_GPIO4_HIGH		57
+#define MX51_MXC_INT_WDOG1		58
+#define MX51_MXC_INT_WDOG2		59
+#define MX51_MXC_INT_KPP		60
+#define MX51_MXC_INT_PWM1		61
+#define MX51_INT_I2C1			62
+#define MX51_INT_I2C2			63
+#define MX51_MXC_INT_HS_I2C		64
+#define MX51_MXC_INT_RESV65		65
+#define MX51_MXC_INT_RESV66		66
+#define MX51_MXC_INT_SIM_IPB		67
+#define MX51_MXC_INT_SIM_DAT		68
+#define MX51_MXC_INT_IIM		69
+#define MX51_MXC_INT_ATA		70
+#define MX51_MXC_INT_CCM1		71
+#define MX51_MXC_INT_CCM2		72
+#define MX51_MXC_INT_GPC1		73
+#define MX51_MXC_INT_GPC2		74
+#define MX51_MXC_INT_SRC		75
+#define MX51_MXC_INT_NM			76
+#define MX51_MXC_INT_PMU		77
+#define MX51_MXC_INT_CTI_IRQ		78
+#define MX51_MXC_INT_CTI1_TG0		79
+#define MX51_MXC_INT_CTI1_TG1		80
+#define MX51_MXC_INT_MCG_ERR		81
+#define MX51_MXC_INT_MCG_TMR		82
+#define MX51_MXC_INT_MCG_FUNC		83
+#define MX51_MXC_INT_GPU2_IRQ		84
+#define MX51_MXC_INT_GPU2_BUSY		85
+#define MX51_MXC_INT_RESV86		86
+#define MX51_INT_FEC			87
+#define MX51_MXC_INT_OWIRE		88
+#define MX51_MXC_INT_CTI1_TG2		89
+#define MX51_MXC_INT_SJC		90
+#define MX51_MXC_INT_SPDIF		91
+#define MX51_MXC_INT_TVE		92
+#define MX51_MXC_INT_FIRI		93
+#define MX51_MXC_INT_PWM2		94
+#define MX51_MXC_INT_SLIM_EXP		95
+#define MX51_MXC_INT_SSI3		96
+#define MX51_MXC_INT_EMI_BOOT		97
+#define MX51_MXC_INT_CTI1_TG3		98
+#define MX51_MXC_INT_SMC_RX		99
+#define MX51_MXC_INT_VPU_IDLE		100
+#define MX51_MXC_INT_EMI_NFC		101
+#define MX51_MXC_INT_GPU_IDLE		102
 
 /* silicon revisions specific to i.MX51 */
-#define MX51_CHIP_REV_1_0	0x10
-#define MX51_CHIP_REV_1_1	0x11
-#define MX51_CHIP_REV_1_2	0x12
-#define MX51_CHIP_REV_1_3	0x13
-#define MX51_CHIP_REV_2_0	0x20
-#define MX51_CHIP_REV_2_1	0x21
-#define MX51_CHIP_REV_2_2	0x22
-#define MX51_CHIP_REV_2_3	0x23
-#define MX51_CHIP_REV_3_0	0x30
-#define MX51_CHIP_REV_3_1	0x31
-#define MX51_CHIP_REV_3_2	0x32
-
-/* Mandatory defines used globally */
+#define MX51_CHIP_REV_1_0		0x10
+#define MX51_CHIP_REV_1_1		0x11
+#define MX51_CHIP_REV_1_2		0x12
+#define MX51_CHIP_REV_1_3		0x13
+#define MX51_CHIP_REV_2_0		0x20
+#define MX51_CHIP_REV_2_1		0x21
+#define MX51_CHIP_REV_2_2		0x22
+#define MX51_CHIP_REV_2_3		0x23
+#define MX51_CHIP_REV_3_0		0x30
+#define MX51_CHIP_REV_3_1		0x31
+#define MX51_CHIP_REV_3_2		0x32
 
 #if !defined(__ASSEMBLY__) && !defined(__MXC_BOOT_UNCOMPRESS)
-
 extern int mx51_revision(void);
 #endif
 
-#endif	/*  __ASM_ARCH_MXC_MX51_H__ */
+/* tape-out 1 defines */
+#define MX51_TZIC_BASE_ADDR_TO1		0x8fffc000
+
+#endif	/* ifndef __MACH_MX51_H__ */
diff --git a/arch/arm/plat-mxc/include/mach/system.h b/arch/arm/plat-mxc/include/mach/system.h
index 4acd114..95be51b 100644
--- a/arch/arm/plat-mxc/include/mach/system.h
+++ b/arch/arm/plat-mxc/include/mach/system.h
@@ -1,7 +1,7 @@
 /*
  *  Copyright (C) 1999 ARM Limited
  *  Copyright (C) 2000 Deep Blue Solutions Ltd
- *  Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
+ *  Copyright 2004-2008 Freescale Semiconductor, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -28,8 +28,34 @@
 		mxc91231_prepare_idle();
 	}
 #endif
-
-	cpu_do_idle();
+	/* fix i.MX31 errata TLSbo65953 and i.MX35 errata ENGcm09472 */
+	if (cpu_is_mx31() || cpu_is_mx35()) {
+		unsigned long reg = 0;
+		__asm__ __volatile__(
+			/* disable I and D cache */
+			"mrc p15, 0, %0, c1, c0, 0\n"
+			"bic %0, %0, #0x00001000\n"
+			"bic %0, %0, #0x00000004\n"
+			"mcr p15, 0, %0, c1, c0, 0\n"
+			/* invalidate I cache */
+			"mov %0, #0\n"
+			"mcr p15, 0, %0, c7, c5, 0\n"
+			/* clear and invalidate D cache */
+			"mov %0, #0\n"
+			"mcr p15, 0, %0, c7, c14, 0\n"
+			/* WFI */
+			"mov %0, #0\n"
+			"mcr p15, 0, %0, c7, c0, 4\n"
+			"nop\n" "nop\n" "nop\n" "nop\n"
+			"nop\n" "nop\n" "nop\n"
+			/* enable I and D cache */
+			"mrc p15, 0, %0, c1, c0, 0\n"
+			"orr %0, %0, #0x00001000\n"
+			"orr %0, %0, #0x00000004\n"
+			"mcr p15, 0, %0, c1, c0, 0\n"
+			: "=r" (reg));
+	} else
+		cpu_do_idle();
 }
 
 void arch_reset(char mode, const char *cmd);
diff --git a/arch/arm/plat-mxc/include/mach/uncompress.h b/arch/arm/plat-mxc/include/mach/uncompress.h
index d9bd37e..9dd9c20 100644
--- a/arch/arm/plat-mxc/include/mach/uncompress.h
+++ b/arch/arm/plat-mxc/include/mach/uncompress.h
@@ -99,6 +99,7 @@
 		uart_base = MX3X_UART2_BASE_ADDR;
 		break;
 	case MACH_TYPE_MX51_BABBAGE:
+	case MACH_TYPE_EUKREA_CPUIMX51SD:
 		uart_base = MX51_UART1_BASE_ADDR;
 		break;
 	default:
diff --git a/arch/arm/plat-mxc/iram_alloc.c b/arch/arm/plat-mxc/iram_alloc.c
new file mode 100644
index 0000000..074c386
--- /dev/null
+++ b/arch/arm/plat-mxc/iram_alloc.c
@@ -0,0 +1,73 @@
+/*
+ * Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/genalloc.h>
+#include <mach/iram.h>
+
+static unsigned long iram_phys_base;
+static void __iomem *iram_virt_base;
+static struct gen_pool *iram_pool;
+
+static inline void __iomem *iram_phys_to_virt(unsigned long p)
+{
+	return iram_virt_base + (p - iram_phys_base);
+}
+
+void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr)
+{
+	if (!iram_pool)
+		return NULL;
+
+	*dma_addr = gen_pool_alloc(iram_pool, size);
+	pr_debug("iram alloc - %dB@0x%lX\n", size, *dma_addr);
+	if (!*dma_addr)
+		return NULL;
+	return iram_phys_to_virt(*dma_addr);
+}
+EXPORT_SYMBOL(iram_alloc);
+
+void iram_free(unsigned long addr, unsigned int size)
+{
+	if (!iram_pool)
+		return;
+
+	gen_pool_free(iram_pool, addr, size);
+}
+EXPORT_SYMBOL(iram_free);
+
+int __init iram_init(unsigned long base, unsigned long size)
+{
+	iram_phys_base = base;
+
+	iram_pool = gen_pool_create(PAGE_SHIFT, -1);
+	if (!iram_pool)
+		return -ENOMEM;
+
+	gen_pool_add(iram_pool, base, size, -1);
+	iram_virt_base = ioremap(iram_phys_base, size);
+	if (!iram_virt_base)
+		return -EIO;
+
+	pr_debug("i.MX IRAM pool: %ld KB@0x%p\n", size / 1024, iram_virt_base);
+	return 0;
+}
diff --git a/arch/arm/plat-nomadik/gpio.c b/arch/arm/plat-nomadik/gpio.c
index 977c8f9..85e6fd21 100644
--- a/arch/arm/plat-nomadik/gpio.c
+++ b/arch/arm/plat-nomadik/gpio.c
@@ -102,6 +102,22 @@
 	writel(1 << offset, nmk_chip->addr + NMK_GPIO_DIRC);
 }
 
+static void __nmk_gpio_set_output(struct nmk_gpio_chip *nmk_chip,
+				  unsigned offset, int val)
+{
+	if (val)
+		writel(1 << offset, nmk_chip->addr + NMK_GPIO_DATS);
+	else
+		writel(1 << offset, nmk_chip->addr + NMK_GPIO_DATC);
+}
+
+static void __nmk_gpio_make_output(struct nmk_gpio_chip *nmk_chip,
+				  unsigned offset, int val)
+{
+	writel(1 << offset, nmk_chip->addr + NMK_GPIO_DIRS);
+	__nmk_gpio_set_output(nmk_chip, offset, val);
+}
+
 static void __nmk_config_pin(struct nmk_gpio_chip *nmk_chip, unsigned offset,
 			     pin_cfg_t cfg)
 {
@@ -118,20 +134,29 @@
 		[3] /* illegal */	= "??"
 	};
 	static const char *slpmnames[] = {
-		[NMK_GPIO_SLPM_INPUT]		= "input",
-		[NMK_GPIO_SLPM_NOCHANGE]	= "no-change",
+		[NMK_GPIO_SLPM_INPUT]		= "input/wakeup",
+		[NMK_GPIO_SLPM_NOCHANGE]	= "no-change/no-wakeup",
 	};
 
 	int pin = PIN_NUM(cfg);
 	int pull = PIN_PULL(cfg);
 	int af = PIN_ALT(cfg);
 	int slpm = PIN_SLPM(cfg);
+	int output = PIN_DIR(cfg);
+	int val = PIN_VAL(cfg);
 
-	dev_dbg(nmk_chip->chip.dev, "pin %d: af %s, pull %s, slpm %s\n",
-		pin, afnames[af], pullnames[pull], slpmnames[slpm]);
+	dev_dbg(nmk_chip->chip.dev, "pin %d: af %s, pull %s, slpm %s (%s%s)\n",
+		pin, afnames[af], pullnames[pull], slpmnames[slpm],
+		output ? "output " : "input",
+		output ? (val ? "high" : "low") : "");
 
-	__nmk_gpio_make_input(nmk_chip, offset);
-	__nmk_gpio_set_pull(nmk_chip, offset, pull);
+	if (output)
+		__nmk_gpio_make_output(nmk_chip, offset, val);
+	else {
+		__nmk_gpio_make_input(nmk_chip, offset);
+		__nmk_gpio_set_pull(nmk_chip, offset, pull);
+	}
+
 	__nmk_gpio_set_slpm(nmk_chip, offset, slpm);
 	__nmk_gpio_set_mode(nmk_chip, offset, af);
 }
@@ -200,6 +225,10 @@
  * changed to an input (with pullup/down enabled) in sleep and deep sleep.  If
  * @mode is NMK_GPIO_SLPM_NOCHANGE, the pin remains in the state it was
  * configured even when in sleep and deep sleep.
+ *
+ * On DB8500v2 onwards, this setting loses the previous meaning and instead
+ * indicates if wakeup detection is enabled on the pin.  Note that
+ * enable_irq_wake() will automatically enable wakeup detection.
  */
 int nmk_gpio_set_slpm(int gpio, enum nmk_gpio_slpm mode)
 {
@@ -367,7 +396,27 @@
 
 static int nmk_gpio_irq_set_wake(unsigned int irq, unsigned int on)
 {
-	return nmk_gpio_irq_modify(irq, WAKE, on);
+	struct nmk_gpio_chip *nmk_chip;
+	unsigned long flags;
+	int gpio;
+
+	gpio = NOMADIK_IRQ_TO_GPIO(irq);
+	nmk_chip = get_irq_chip_data(irq);
+	if (!nmk_chip)
+		return -EINVAL;
+
+	spin_lock_irqsave(&nmk_chip->lock, flags);
+#ifdef CONFIG_ARCH_U8500
+	if (cpu_is_u8500v2()) {
+		__nmk_gpio_set_slpm(nmk_chip, gpio,
+				    on ? NMK_GPIO_SLPM_WAKEUP_ENABLE
+				       : NMK_GPIO_SLPM_WAKEUP_DISABLE);
+	}
+#endif
+	__nmk_gpio_irq_modify(nmk_chip, gpio, WAKE, on);
+	spin_unlock_irqrestore(&nmk_chip->lock, flags);
+
+	return 0;
 }
 
 static int nmk_gpio_irq_set_type(unsigned int irq, unsigned int type)
@@ -495,12 +544,8 @@
 {
 	struct nmk_gpio_chip *nmk_chip =
 		container_of(chip, struct nmk_gpio_chip, chip);
-	u32 bit = 1 << offset;
 
-	if (val)
-		writel(bit, nmk_chip->addr + NMK_GPIO_DATS);
-	else
-		writel(bit, nmk_chip->addr + NMK_GPIO_DATC);
+	__nmk_gpio_set_output(nmk_chip, offset, val);
 }
 
 static int nmk_gpio_make_output(struct gpio_chip *chip, unsigned offset,
@@ -509,8 +554,7 @@
 	struct nmk_gpio_chip *nmk_chip =
 		container_of(chip, struct nmk_gpio_chip, chip);
 
-	writel(1 << offset, nmk_chip->addr + NMK_GPIO_DIRS);
-	nmk_gpio_set_output(chip, offset, val);
+	__nmk_gpio_make_output(nmk_chip, offset, val);
 
 	return 0;
 }
@@ -534,7 +578,7 @@
 	.can_sleep		= 0,
 };
 
-static int __init nmk_gpio_probe(struct platform_device *dev)
+static int __devinit nmk_gpio_probe(struct platform_device *dev)
 {
 	struct nmk_gpio_platform_data *pdata = dev->dev.platform_data;
 	struct nmk_gpio_chip *nmk_chip;
diff --git a/arch/arm/plat-nomadik/include/plat/gpio.h b/arch/arm/plat-nomadik/include/plat/gpio.h
index aba3551..67b113d 100644
--- a/arch/arm/plat-nomadik/include/plat/gpio.h
+++ b/arch/arm/plat-nomadik/include/plat/gpio.h
@@ -65,7 +65,9 @@
 /* Sleep mode */
 enum nmk_gpio_slpm {
 	NMK_GPIO_SLPM_INPUT,
+	NMK_GPIO_SLPM_WAKEUP_ENABLE = NMK_GPIO_SLPM_INPUT,
 	NMK_GPIO_SLPM_NOCHANGE,
+	NMK_GPIO_SLPM_WAKEUP_DISABLE = NMK_GPIO_SLPM_NOCHANGE,
 };
 
 extern int nmk_gpio_set_slpm(int gpio, enum nmk_gpio_slpm mode);
diff --git a/arch/arm/plat-nomadik/include/plat/pincfg.h b/arch/arm/plat-nomadik/include/plat/pincfg.h
index 7eed11c..8c5ae3f 100644
--- a/arch/arm/plat-nomadik/include/plat/pincfg.h
+++ b/arch/arm/plat-nomadik/include/plat/pincfg.h
@@ -19,12 +19,16 @@
  *	bit  9..10 - Alternate Function Selection
  *	bit 11..12 - Pull up/down state
  *	bit     13 - Sleep mode behaviour
+ *	bit     14 - (sleep mode) Direction
+ *	bit     15 - (sleep mode) Value (if output)
  *
  * to facilitate the definition, the following macros are provided
  *
  * PIN_CFG_DEFAULT - default config (0):
  *		     pull up/down = disabled
- *		     sleep mode = input
+ *		     sleep mode = input/wakeup
+ *		     (sleep mode) direction = input
+ *		     (sleep mode) value = low
  *
  * PIN_CFG	   - default config with alternate function
  * PIN_CFG_PULL	   - default config with alternate function and pull up/down
@@ -53,8 +57,36 @@
 #define PIN_SLPM_SHIFT		13
 #define PIN_SLPM_MASK		(0x1 << PIN_SLPM_SHIFT)
 #define PIN_SLPM(x)		(((x) & PIN_SLPM_MASK) >> PIN_SLPM_SHIFT)
-#define PIN_SLPM_INPUT		(NMK_GPIO_SLPM_INPUT << PIN_SLPM_SHIFT)
+#define PIN_SLPM_MAKE_INPUT	(NMK_GPIO_SLPM_INPUT << PIN_SLPM_SHIFT)
 #define PIN_SLPM_NOCHANGE	(NMK_GPIO_SLPM_NOCHANGE << PIN_SLPM_SHIFT)
+/* These two replace the above in DB8500v2+ */
+#define PIN_SLPM_WAKEUP_ENABLE	(NMK_GPIO_SLPM_WAKEUP_ENABLE << PIN_SLPM_SHIFT)
+#define PIN_SLPM_WAKEUP_DISABLE	(NMK_GPIO_SLPM_WAKEUP_DISABLE << PIN_SLPM_SHIFT)
+
+#define PIN_DIR_SHIFT		14
+#define PIN_DIR_MASK		(0x1 << PIN_DIR_SHIFT)
+#define PIN_DIR(x)		(((x) & PIN_DIR_MASK) >> PIN_DIR_SHIFT)
+#define PIN_DIR_INPUT		(0 << PIN_DIR_SHIFT)
+#define PIN_DIR_OUTPUT		(1 << PIN_DIR_SHIFT)
+
+#define PIN_VAL_SHIFT		15
+#define PIN_VAL_MASK		(0x1 << PIN_VAL_SHIFT)
+#define PIN_VAL(x)		(((x) & PIN_VAL_MASK) >> PIN_VAL_SHIFT)
+#define PIN_VAL_LOW		(0 << PIN_VAL_SHIFT)
+#define PIN_VAL_HIGH		(1 << PIN_VAL_SHIFT)
+
+/* Shortcuts.  Use these instead of separate DIR and VAL.  */
+#define PIN_INPUT		PIN_DIR_INPUT
+#define PIN_OUTPUT_LOW		(PIN_DIR_OUTPUT | PIN_VAL_LOW)
+#define PIN_OUTPUT_HIGH		(PIN_DIR_OUTPUT | PIN_VAL_HIGH)
+
+/*
+ * These are the same as the ones above, but should make more sense to the
+ * reader when seen along with a setting a pin to AF mode.
+ */
+#define PIN_SLPM_INPUT		PIN_INPUT
+#define PIN_SLPM_OUTPUT_LOW	PIN_OUTPUT_LOW
+#define PIN_SLPM_OUTPUT_HIGH	PIN_OUTPUT_HIGH
 
 #define PIN_CFG_DEFAULT		(PIN_PULL_NONE | PIN_SLPM_INPUT)
 
diff --git a/arch/arm/plat-omap/fb.c b/arch/arm/plat-omap/fb.c
index 0054b95..7193481 100644
--- a/arch/arm/plat-omap/fb.c
+++ b/arch/arm/plat-omap/fb.c
@@ -173,11 +173,7 @@
 
 static int valid_sdram(unsigned long addr, unsigned long size)
 {
-	struct memblock_property res;
-
-	res.base = addr;
-	res.size = size;
-	return !memblock_find(&res) && res.base == addr && res.size == size;
+	return memblock_is_region_memory(addr, size);
 }
 
 static int reserve_sdram(unsigned long addr, unsigned long size)
diff --git a/arch/arm/plat-omap/include/plat/smp.h b/arch/arm/plat-omap/include/plat/smp.h
index 5177a9c..ecd6a48 100644
--- a/arch/arm/plat-omap/include/plat/smp.h
+++ b/arch/arm/plat-omap/include/plat/smp.h
@@ -18,6 +18,7 @@
 #define OMAP_ARCH_SMP_H
 
 #include <asm/hardware/gic.h>
+#include <asm/smp_mpidr.h>
 
 /* Needed for secondary core boot */
 extern void omap_secondary_startup(void);
@@ -33,15 +34,4 @@
 	gic_raise_softirq(mask, 1);
 }
 
-/*
- * Read MPIDR: Multiprocessor affinity register
- */
-#define hard_smp_processor_id()			\
-	({						\
-		unsigned int cpunum;			\
-		__asm__("mrc p15, 0, %0, c0, c0, 5"	\
-			: "=r" (cpunum));		\
-		cpunum &= 0x0F;				\
-	})
-
 #endif
diff --git a/arch/arm/plat-omap/iommu-debug.c b/arch/arm/plat-omap/iommu-debug.c
index e6c0d53..f07cf2f 100644
--- a/arch/arm/plat-omap/iommu-debug.c
+++ b/arch/arm/plat-omap/iommu-debug.c
@@ -328,12 +328,14 @@
 		.open = debug_open_generic,				\
 		.read = debug_read_##name,				\
 		.write = debug_write_##name,				\
+		.llseek = generic_file_llseek,				\
 	};
 
 #define DEBUG_FOPS_RO(name)						\
 	static const struct file_operations debug_##name##_fops = {	\
 		.open = debug_open_generic,				\
 		.read = debug_read_##name,				\
+		.llseek = generic_file_llseek,				\
 	};
 
 DEBUG_FOPS_RO(ver);
diff --git a/arch/arm/mach-pxa/include/mach/pxa27x_keypad.h b/arch/arm/plat-pxa/include/plat/pxa27x_keypad.h
similarity index 83%
rename from arch/arm/mach-pxa/include/mach/pxa27x_keypad.h
rename to arch/arm/plat-pxa/include/plat/pxa27x_keypad.h
index 7b4eadc..abcc36e 100644
--- a/arch/arm/mach-pxa/include/mach/pxa27x_keypad.h
+++ b/arch/arm/plat-pxa/include/plat/pxa27x_keypad.h
@@ -25,6 +25,13 @@
  *
  * 4. matrix key and direct key will use the same debounce_interval by
  *    default, which should be sufficient in most cases
+ *
+ * pxa168 keypad platform specific parameter
+ *
+ * NOTE:
+ * clear_wakeup_event callback is a workaround required to clear the
+ * keypad interrupt. The keypad wake must be cleared in addition to
+ * reading the MI/DI bits in the KPC register.
  */
 struct pxa27x_keypad_platform_data {
 
@@ -52,6 +59,9 @@
 
 	/* key debounce interval */
 	unsigned int	debounce_interval;
+
+	/* clear wakeup event requirement for pxa168 */
+	void		(*clear_wakeup_event)(void);
 };
 
 extern void pxa_set_keypad_info(struct pxa27x_keypad_platform_data *info);
diff --git a/arch/arm/plat-s5p/Kconfig b/arch/arm/plat-s5p/Kconfig
index c6a855d..2596096 100644
--- a/arch/arm/plat-s5p/Kconfig
+++ b/arch/arm/plat-s5p/Kconfig
@@ -7,7 +7,7 @@
 
 config PLAT_S5P
 	bool
-	depends on (ARCH_S5P6440 || ARCH_S5P6442 || ARCH_S5PC100 || ARCH_S5PV210 || ARCH_S5PV310)
+	depends on (ARCH_S5P64X0 || ARCH_S5P6442 || ARCH_S5PC100 || ARCH_S5PV210 || ARCH_S5PV310)
 	default y
 	select ARM_VIC if !ARCH_S5PV310
 	select ARM_GIC if ARCH_S5PV310
@@ -30,7 +30,7 @@
 	bool
 	help
 	  Use the external interrupts (other than GPIO interrupts.)
-	  Note: Do not choose this for S5P6440.
+	  Note: Do not choose this for S5P6440 and S5P6450.
 
 config S5P_DEV_FIMC0
 	bool
@@ -46,3 +46,8 @@
 	bool
 	help
 	  Compile in platform device definitions for FIMC controller 2
+
+config S5P_DEV_ONENAND
+	bool
+	help
+	  Compile in platform device definition for OneNAND controller
diff --git a/arch/arm/plat-s5p/Makefile b/arch/arm/plat-s5p/Makefile
index b2e0296..f3e917e 100644
--- a/arch/arm/plat-s5p/Makefile
+++ b/arch/arm/plat-s5p/Makefile
@@ -24,3 +24,4 @@
 obj-$(CONFIG_S5P_DEV_FIMC0)	+= dev-fimc0.o
 obj-$(CONFIG_S5P_DEV_FIMC1)	+= dev-fimc1.o
 obj-$(CONFIG_S5P_DEV_FIMC2)	+= dev-fimc2.o
+obj-$(CONFIG_S5P_DEV_ONENAND)	+= dev-onenand.o
diff --git a/arch/arm/plat-s5p/clock.c b/arch/arm/plat-s5p/clock.c
index b5e2552..8aaf4e6 100644
--- a/arch/arm/plat-s5p/clock.c
+++ b/arch/arm/plat-s5p/clock.c
@@ -74,6 +74,13 @@
 	.ctrlbit	= (1 << 31),
 };
 
+/* DPLL clock output */
+struct clk clk_fout_dpll = {
+	.name		= "fout_dpll",
+	.id		= -1,
+	.ctrlbit	= (1 << 31),
+};
+
 /* VPLL clock output */
 struct clk clk_fout_vpll = {
 	.name		= "fout_vpll",
@@ -122,6 +129,17 @@
 	.nr_sources	= ARRAY_SIZE(clk_src_epll_list),
 };
 
+/* Possible clock sources for DPLL Mux */
+static struct clk *clk_src_dpll_list[] = {
+	[0] = &clk_fin_dpll,
+	[1] = &clk_fout_dpll,
+};
+
+struct clksrc_sources clk_src_dpll = {
+	.sources	= clk_src_dpll_list,
+	.nr_sources	= ARRAY_SIZE(clk_src_dpll_list),
+};
+
 struct clk clk_vpll = {
 	.name		= "vpll",
 	.id		= -1,
@@ -145,6 +163,7 @@
 	&clk_fout_apll,
 	&clk_fout_mpll,
 	&clk_fout_epll,
+	&clk_fout_dpll,
 	&clk_fout_vpll,
 	&clk_arm,
 	&clk_vpll,
diff --git a/arch/arm/plat-s5p/cpu.c b/arch/arm/plat-s5p/cpu.c
index b07a078..74f7f5a 100644
--- a/arch/arm/plat-s5p/cpu.c
+++ b/arch/arm/plat-s5p/cpu.c
@@ -19,6 +19,7 @@
 #include <plat/cpu.h>
 #include <plat/s5p6440.h>
 #include <plat/s5p6442.h>
+#include <plat/s5p6450.h>
 #include <plat/s5pc100.h>
 #include <plat/s5pv210.h>
 #include <plat/s5pv310.h>
@@ -27,6 +28,7 @@
 
 static const char name_s5p6440[] = "S5P6440";
 static const char name_s5p6442[] = "S5P6442";
+static const char name_s5p6450[] = "S5P6450";
 static const char name_s5pc100[] = "S5PC100";
 static const char name_s5pv210[] = "S5PV210/S5PC110";
 static const char name_s5pv310[] = "S5PV310";
@@ -38,7 +40,7 @@
 		.map_io		= s5p6440_map_io,
 		.init_clocks	= s5p6440_init_clocks,
 		.init_uarts	= s5p6440_init_uarts,
-		.init		= s5p6440_init,
+		.init		= s5p64x0_init,
 		.name		= name_s5p6440,
 	}, {
 		.idcode		= 0x36442000,
@@ -49,6 +51,14 @@
 		.init		= s5p6442_init,
 		.name		= name_s5p6442,
 	}, {
+		.idcode		= 0x36450000,
+		.idmask		= 0xffffff00,
+		.map_io		= s5p6450_map_io,
+		.init_clocks	= s5p6450_init_clocks,
+		.init_uarts	= s5p6450_init_uarts,
+		.init		= s5p64x0_init,
+		.name		= name_s5p6450,
+	}, {
 		.idcode		= 0x43100000,
 		.idmask		= 0xfffff000,
 		.map_io		= s5pc100_map_io,
@@ -89,33 +99,11 @@
 		.length		= SZ_64K,
 		.type		= MT_DEVICE,
 	}, {
-		.virtual	= (unsigned long)S3C_VA_UART,
-		.pfn		= __phys_to_pfn(S3C_PA_UART),
-		.length		= SZ_512K,
-		.type		= MT_DEVICE,
-#ifdef CONFIG_ARM_VIC
-	}, {
-		.virtual	= (unsigned long)VA_VIC0,
-		.pfn		= __phys_to_pfn(S5P_PA_VIC0),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-	}, {
-		.virtual	= (unsigned long)VA_VIC1,
-		.pfn		= __phys_to_pfn(S5P_PA_VIC1),
-		.length		= SZ_16K,
-		.type		= MT_DEVICE,
-#endif
-	}, {
 		.virtual	= (unsigned long)S3C_VA_TIMER,
 		.pfn		= __phys_to_pfn(S5P_PA_TIMER),
 		.length		= SZ_16K,
 		.type		= MT_DEVICE,
 	}, {
-		.virtual	= (unsigned long)S5P_VA_GPIO,
-		.pfn		= __phys_to_pfn(S5P_PA_GPIO),
-		.length		= SZ_4K,
-		.type		= MT_DEVICE,
-	}, {
 		.virtual	= (unsigned long)S3C_VA_WATCHDOG,
 		.pfn		= __phys_to_pfn(S3C_PA_WDT),
 		.length		= SZ_4K,
diff --git a/arch/arm/plat-s5p/dev-onenand.c b/arch/arm/plat-s5p/dev-onenand.c
new file mode 100644
index 0000000..6db9262
--- /dev/null
+++ b/arch/arm/plat-s5p/dev-onenand.c
@@ -0,0 +1,57 @@
+/* linux/arch/arm/plat-s5p/dev-onenand.c
+ *
+ * Copyright 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ *  Copyright (c) 2008-2010 Samsung Electronics
+ *  Kyungmin Park <kyungmin.park@samsung.com>
+ *
+ * S5P series device definition for OneNAND devices
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/onenand.h>
+
+#include <mach/irqs.h>
+#include <mach/map.h>
+
+static struct resource s5p_onenand_resources[] = {
+	[0] = {
+		.start	= S5P_PA_ONENAND,
+		.end	= S5P_PA_ONENAND + SZ_128K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= S5P_PA_ONENAND_DMA,
+		.end	= S5P_PA_ONENAND_DMA + SZ_8K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[2] = {
+		.start	= IRQ_ONENAND_AUDI,
+		.end	= IRQ_ONENAND_AUDI,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device s5p_device_onenand = {
+	.name		= "s5pc110-onenand",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(s5p_onenand_resources),
+	.resource	= s5p_onenand_resources,
+};
+
+void s5p_onenand_set_platdata(struct onenand_platform_data *pdata)
+{
+	struct onenand_platform_data *pd;
+
+	pd = kmemdup(pdata, sizeof(struct onenand_platform_data), GFP_KERNEL);
+	if (!pd)
+		printk(KERN_ERR "%s: no memory for platform data\n", __func__);
+	s5p_device_onenand.dev.platform_data = pd;
+}
diff --git a/arch/arm/plat-s5p/dev-uart.c b/arch/arm/plat-s5p/dev-uart.c
index a89331e..6a73428 100644
--- a/arch/arm/plat-s5p/dev-uart.c
+++ b/arch/arm/plat-s5p/dev-uart.c
@@ -119,6 +119,56 @@
 #endif
 };
 
+static struct resource s5p_uart4_resource[] = {
+#if CONFIG_SERIAL_SAMSUNG_UARTS > 4
+	[0] = {
+		.start	= S5P_PA_UART4,
+		.end	= S5P_PA_UART4 + S5P_SZ_UART,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_S5P_UART_RX4,
+		.end	= IRQ_S5P_UART_RX4,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[2] = {
+		.start	= IRQ_S5P_UART_TX4,
+		.end	= IRQ_S5P_UART_TX4,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[3] = {
+		.start	= IRQ_S5P_UART_ERR4,
+		.end	= IRQ_S5P_UART_ERR4,
+		.flags	= IORESOURCE_IRQ,
+	},
+#endif
+};
+
+static struct resource s5p_uart5_resource[] = {
+#if CONFIG_SERIAL_SAMSUNG_UARTS > 5
+	[0] = {
+		.start	= S5P_PA_UART5,
+		.end	= S5P_PA_UART5 + S5P_SZ_UART,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= IRQ_S5P_UART_RX5,
+		.end	= IRQ_S5P_UART_RX5,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[2] = {
+		.start	= IRQ_S5P_UART_TX5,
+		.end	= IRQ_S5P_UART_TX5,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[3] = {
+		.start	= IRQ_S5P_UART_ERR5,
+		.end	= IRQ_S5P_UART_ERR5,
+		.flags	= IORESOURCE_IRQ,
+	},
+#endif
+};
+
 struct s3c24xx_uart_resources s5p_uart_resources[] __initdata = {
 	[0] = {
 		.resources	= s5p_uart0_resource,
@@ -136,4 +186,12 @@
 		.resources	= s5p_uart3_resource,
 		.nr_resources	= ARRAY_SIZE(s5p_uart3_resource),
 	},
+	[4] = {
+		.resources	= s5p_uart4_resource,
+		.nr_resources	= ARRAY_SIZE(s5p_uart4_resource),
+	},
+	[5] = {
+		.resources	= s5p_uart5_resource,
+		.nr_resources	= ARRAY_SIZE(s5p_uart5_resource),
+	},
 };
diff --git a/arch/arm/plat-s5p/include/plat/pll.h b/arch/arm/plat-s5p/include/plat/pll.h
index 4e8fe08..bf28fad 100644
--- a/arch/arm/plat-s5p/include/plat/pll.h
+++ b/arch/arm/plat-s5p/include/plat/pll.h
@@ -47,6 +47,7 @@
 }
 
 #define PLL46XX_KDIV_MASK	(0xFFFF)
+#define PLL4650C_KDIV_MASK	(0xFFF)
 #define PLL46XX_MDIV_MASK	(0x1FF)
 #define PLL46XX_PDIV_MASK	(0x3F)
 #define PLL46XX_SDIV_MASK	(0x7)
@@ -57,6 +58,7 @@
 enum pll46xx_type_t {
 	pll_4600,
 	pll_4650,
+	pll_4650c,
 };
 
 static inline unsigned long s5p_get_pll46xx(unsigned long baseclk,
@@ -72,6 +74,11 @@
 	sdiv = (pll_con0 >> PLL46XX_SDIV_SHIFT) & PLL46XX_SDIV_MASK;
 	kdiv = pll_con1 & PLL46XX_KDIV_MASK;
 
+	if (pll_type == pll_4650c)
+		kdiv = pll_con1 & PLL4650C_KDIV_MASK;
+	else
+		kdiv = pll_con1 & PLL46XX_KDIV_MASK;
+
 	tmp = baseclk;
 
 	if (pll_type == pll_4600) {
diff --git a/arch/arm/plat-s5p/include/plat/s5p-clock.h b/arch/arm/plat-s5p/include/plat/s5p-clock.h
index 09418b1..17036c8 100644
--- a/arch/arm/plat-s5p/include/plat/s5p-clock.h
+++ b/arch/arm/plat-s5p/include/plat/s5p-clock.h
@@ -1,7 +1,7 @@
 /* linux/arch/arm/plat-s5p/include/plat/s5p-clock.h
  *
- * Copyright 2009 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
  *
  * Header file for s5p clock support
  *
@@ -20,6 +20,7 @@
 #define clk_fin_apll clk_ext_xtal_mux
 #define clk_fin_mpll clk_ext_xtal_mux
 #define clk_fin_epll clk_ext_xtal_mux
+#define clk_fin_dpll clk_ext_xtal_mux
 #define clk_fin_vpll clk_ext_xtal_mux
 #define clk_fin_hpll clk_ext_xtal_mux
 
@@ -30,6 +31,7 @@
 extern struct clk clk_fout_apll;
 extern struct clk clk_fout_mpll;
 extern struct clk clk_fout_epll;
+extern struct clk clk_fout_dpll;
 extern struct clk clk_fout_vpll;
 extern struct clk clk_arm;
 extern struct clk clk_vpll;
@@ -37,8 +39,8 @@
 extern struct clksrc_sources clk_src_apll;
 extern struct clksrc_sources clk_src_mpll;
 extern struct clksrc_sources clk_src_epll;
+extern struct clksrc_sources clk_src_dpll;
 
-extern int s5p6440_clk48m_ctrl(struct clk *clk, int enable);
 extern int s5p_gatectrl(void __iomem *reg, struct clk *clk, int enable);
 
 #endif /* __ASM_PLAT_S5P_CLOCK_H */
diff --git a/arch/arm/plat-s5p/include/plat/s5p6440.h b/arch/arm/plat-s5p/include/plat/s5p6440.h
index a4cd75a..528585d 100644
--- a/arch/arm/plat-s5p/include/plat/s5p6440.h
+++ b/arch/arm/plat-s5p/include/plat/s5p6440.h
@@ -12,24 +12,23 @@
 
  /* Common init code for S5P6440 related SoCs */
 
-extern void s5p6440_common_init_uarts(struct s3c2410_uartcfg *cfg, int no);
 extern void s5p6440_register_clocks(void);
 extern void s5p6440_setup_clocks(void);
 
 #ifdef CONFIG_CPU_S5P6440
 
-extern  int s5p6440_init(void);
+extern  int s5p64x0_init(void);
 extern void s5p6440_init_irq(void);
 extern void s5p6440_map_io(void);
 extern void s5p6440_init_clocks(int xtal);
 
-#define s5p6440_init_uarts s5p6440_common_init_uarts
+extern void s5p6440_init_uarts(struct s3c2410_uartcfg *cfg, int no);
 
 #else
 #define s5p6440_init_clocks NULL
 #define s5p6440_init_uarts NULL
 #define s5p6440_map_io NULL
-#define s5p6440_init NULL
+#define s5p64x0_init NULL
 #endif
 
 /* S5P6440 timer */
diff --git a/arch/arm/plat-s5p/include/plat/s5p6450.h b/arch/arm/plat-s5p/include/plat/s5p6450.h
new file mode 100644
index 0000000..640a41c
--- /dev/null
+++ b/arch/arm/plat-s5p/include/plat/s5p6450.h
@@ -0,0 +1,36 @@
+/* arch/arm/plat-s5p/include/plat/s5p6450.h
+ *
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Header file for s5p6450 cpu support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+/* Common init code for S5P6450 related SoCs */
+
+extern void s5p6450_register_clocks(void);
+extern void s5p6450_setup_clocks(void);
+
+#ifdef CONFIG_CPU_S5P6450
+
+extern  int s5p64x0_init(void);
+extern void s5p6450_init_irq(void);
+extern void s5p6450_map_io(void);
+extern void s5p6450_init_clocks(int xtal);
+
+extern void s5p6450_init_uarts(struct s3c2410_uartcfg *cfg, int no);
+
+#else
+#define s5p6450_init_clocks NULL
+#define s5p6450_init_uarts NULL
+#define s5p6450_map_io NULL
+#define s5p64x0_init NULL
+#endif
+
+/* S5P6450 timer */
+
+extern struct sys_timer s5p6450_timer;
diff --git a/arch/arm/plat-samsung/include/plat/cpu.h b/arch/arm/plat-samsung/include/plat/cpu.h
index 6412933..9addb3d 100644
--- a/arch/arm/plat-samsung/include/plat/cpu.h
+++ b/arch/arm/plat-samsung/include/plat/cpu.h
@@ -79,7 +79,7 @@
 extern struct sysdev_class s3c2443_sysclass;
 extern struct sysdev_class s3c6410_sysclass;
 extern struct sysdev_class s3c64xx_sysclass;
-extern struct sysdev_class s5p6440_sysclass;
+extern struct sysdev_class s5p64x0_sysclass;
 extern struct sysdev_class s5p6442_sysclass;
 extern struct sysdev_class s5pv210_sysclass;
 
diff --git a/arch/arm/plat-samsung/include/plat/devs.h b/arch/arm/plat-samsung/include/plat/devs.h
index 85f6f23..7d448e1 100644
--- a/arch/arm/plat-samsung/include/plat/devs.h
+++ b/arch/arm/plat-samsung/include/plat/devs.h
@@ -67,13 +67,15 @@
 extern struct platform_device s5pv210_device_spi1;
 extern struct platform_device s5p6440_device_spi0;
 extern struct platform_device s5p6440_device_spi1;
+extern struct platform_device s5p6450_device_spi0;
+extern struct platform_device s5p6450_device_spi1;
 
 extern struct platform_device s3c_device_hwmon;
 
 extern struct platform_device s3c_device_nand;
 extern struct platform_device s3c_device_onenand;
 extern struct platform_device s3c64xx_device_onenand1;
-extern struct platform_device s5pc110_device_onenand;
+extern struct platform_device s5p_device_onenand;
 
 extern struct platform_device s3c_device_usbgadget;
 extern struct platform_device s3c_device_usb_hsotg;
@@ -95,6 +97,9 @@
 extern struct platform_device s5p6440_device_pcm;
 extern struct platform_device s5p6440_device_iis;
 
+extern struct platform_device s5p6450_device_iis0;
+extern struct platform_device s5p6450_device_pcm0;
+
 extern struct platform_device s5pc100_device_ac97;
 extern struct platform_device s5pc100_device_pcm0;
 extern struct platform_device s5pc100_device_pcm1;
diff --git a/arch/arm/plat-samsung/include/plat/s3c-dma-pl330.h b/arch/arm/plat-samsung/include/plat/s3c-dma-pl330.h
index 5fe6721..8107442 100644
--- a/arch/arm/plat-samsung/include/plat/s3c-dma-pl330.h
+++ b/arch/arm/plat-samsung/include/plat/s3c-dma-pl330.h
@@ -32,6 +32,12 @@
 	DMACH_UART2_TX,
 	DMACH_UART3_RX,
 	DMACH_UART3_TX,
+	DMACH_UART4_RX,
+	DMACH_UART4_TX,
+	DMACH_UART5_RX,
+	DMACH_UART5_TX,
+	DMACH_USI_RX,
+	DMACH_USI_TX,
 	DMACH_IRDA,
 	DMACH_I2S0_RX,
 	DMACH_I2S0_TX,
@@ -64,6 +70,20 @@
 	DMACH_MSM_REQ2,
 	DMACH_MSM_REQ1,
 	DMACH_MSM_REQ0,
+	DMACH_SLIMBUS0_RX,
+	DMACH_SLIMBUS0_TX,
+	DMACH_SLIMBUS0AUX_RX,
+	DMACH_SLIMBUS0AUX_TX,
+	DMACH_SLIMBUS1_RX,
+	DMACH_SLIMBUS1_TX,
+	DMACH_SLIMBUS2_RX,
+	DMACH_SLIMBUS2_TX,
+	DMACH_SLIMBUS3_RX,
+	DMACH_SLIMBUS3_TX,
+	DMACH_SLIMBUS4_RX,
+	DMACH_SLIMBUS4_TX,
+	DMACH_SLIMBUS5_RX,
+	DMACH_SLIMBUS5_TX,
 	/* END Marker, also used to denote a reserved channel */
 	DMACH_MAX,
 };
diff --git a/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h b/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
index e5aba8f..ff1a561 100644
--- a/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
+++ b/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
@@ -32,6 +32,8 @@
  * struct s3c64xx_spi_info - SPI Controller defining structure
  * @src_clk_nr: Clock source index for the CLK_CFG[SPI_CLKSEL] field.
  * @src_clk_name: Platform name of the corresponding clock.
+ * @clk_from_cmu: If the SPI clock/prescalar control block is present
+ *     by the platform's clock-management-unit and not in SPI controller.
  * @num_cs: Number of CS this controller emulates.
  * @cfg_gpio: Configure pins for this SPI controller.
  * @fifo_lvl_mask: All tx fifo_lvl fields start at offset-6
@@ -41,6 +43,7 @@
 struct s3c64xx_spi_info {
 	int src_clk_nr;
 	char *src_clk_name;
+	bool clk_from_cmu;
 
 	int num_cs;
 
@@ -65,7 +68,7 @@
 extern void s3c64xx_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
 extern void s5pc100_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
 extern void s5pv210_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
-extern void s5p6440_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
+extern void s5p64x0_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
 extern void s5p6442_spi_set_info(int cntrlr, int src_clk_nr, int num_cs);
 
 #endif /* __S3C64XX_PLAT_SPI_H */
diff --git a/arch/arm/plat-spear/include/plat/debug-macro.S b/arch/arm/plat-spear/include/plat/debug-macro.S
index 37fa593..e91270e 100644
--- a/arch/arm/plat-spear/include/plat/debug-macro.S
+++ b/arch/arm/plat-spear/include/plat/debug-macro.S
@@ -14,11 +14,9 @@
 #include <linux/amba/serial.h>
 #include <mach/spear.h>
 
-		.macro	addruart, rx
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1					@ MMU enabled?
-		moveq	\rx, #SPEAR_DBG_UART_BASE		@ Physical base
-		movne	\rx, #VA_SPEAR_DBG_UART_BASE		@ Virtual base
+		.macro	addruart, rp, rv
+		mov	\rp, #SPEAR_DBG_UART_BASE		@ Physical base
+		mov	\rv, #VA_SPEAR_DBG_UART_BASE		@ Virtual base
 		.endm
 
 		.macro	senduart, rd, rx
diff --git a/arch/arm/plat-stmp3xxx/include/mach/debug-macro.S b/arch/arm/plat-stmp3xxx/include/mach/debug-macro.S
index 1b9348b..d3a0985 100644
--- a/arch/arm/plat-stmp3xxx/include/mach/debug-macro.S
+++ b/arch/arm/plat-stmp3xxx/include/mach/debug-macro.S
@@ -16,13 +16,10 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-		.macro	addruart, rx, tmp
-		mrc	p15, 0, \rx, c1, c0
-		tst	\rx, #1			@ MMU enabled?
-		moveq	\rx, #0x80000000	@ physical base address
-		addeq	\rx, \rx, #0x00070000
-		movne	\rx, #0xf0000000	@ virtual base
-		addne	\rx, \rx, #0x00070000
+		.macro	addruart, rp, rv
+		mov	\rp,      #0x00070000
+		add	\rv, \rp, #0xf0000000	@ virtual base
+		add	\rp, \rp, #0x80000000	@ physical base
 		.endm
 
 		.macro	senduart,rd,rx
diff --git a/arch/arm/plat-tcc/Kconfig b/arch/arm/plat-tcc/Kconfig
new file mode 100644
index 0000000..1bf4995
--- /dev/null
+++ b/arch/arm/plat-tcc/Kconfig
@@ -0,0 +1,20 @@
+if ARCH_TCC_926
+
+menu "Telechips ARM926-based CPUs"
+
+choice
+	prompt "Telechips CPU type:"
+	default ARCH_TCC8K
+
+config ARCH_TCC8K
+	bool TCC8000
+	select USB_ARCH_HAS_OHCI
+	help
+	  Support for Telechips TCC8000 systems
+
+endchoice
+
+source "arch/arm/mach-tcc8k/Kconfig"
+
+endmenu
+endif
diff --git a/arch/arm/plat-tcc/Makefile b/arch/arm/plat-tcc/Makefile
new file mode 100644
index 0000000..eceabc8
--- /dev/null
+++ b/arch/arm/plat-tcc/Makefile
@@ -0,0 +1,3 @@
+# "Telechips Platform Common Modules"
+
+obj-y := clock.o system.o
diff --git a/arch/arm/plat-tcc/clock.c b/arch/arm/plat-tcc/clock.c
new file mode 100644
index 0000000..f3ced10
--- /dev/null
+++ b/arch/arm/plat-tcc/clock.c
@@ -0,0 +1,179 @@
+/*
+ * Clock framework for Telechips SoCs
+ * Based on arch/arm/plat-mxc/clock.c
+ *
+ * Copyright (C) 2004 - 2005 Nokia corporation
+ * Written by Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>
+ * Modified for omap shared clock framework by Tony Lindgren <tony@atomide.com>
+ * Copyright 2007 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright 2008 Juergen Beisert, kernel@pengutronix.de
+ * Copyright 2010 Hans J. Koch, hjk@linutronix.de
+ *
+ * Licensed under the terms of the GPL v2.
+ */
+
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/string.h>
+
+#include <mach/clock.h>
+#include <mach/hardware.h>
+
+static DEFINE_MUTEX(clocks_mutex);
+
+/*-------------------------------------------------------------------------
+ * Standard clock functions defined in include/linux/clk.h
+ *-------------------------------------------------------------------------*/
+
+static void __clk_disable(struct clk *clk)
+{
+	BUG_ON(clk->refcount == 0);
+
+	if (!(--clk->refcount) && clk->disable) {
+		/* Unconditionally disable the clock in hardware */
+		clk->disable(clk);
+		/* recursively disable parents */
+		if (clk->parent)
+			__clk_disable(clk->parent);
+	}
+}
+
+static int __clk_enable(struct clk *clk)
+{
+	int ret = 0;
+
+	if (clk->refcount++ == 0 && clk->enable) {
+		if (clk->parent)
+			ret = __clk_enable(clk->parent);
+		if (ret)
+			return ret;
+		else
+			return clk->enable(clk);
+	}
+
+	return 0;
+}
+
+/* This function increments the reference count on the clock and enables the
+ * clock if not already enabled. The parent clock tree is recursively enabled
+ */
+int clk_enable(struct clk *clk)
+{
+	int ret = 0;
+
+	if (!clk)
+		return -EINVAL;
+
+	mutex_lock(&clocks_mutex);
+	ret = __clk_enable(clk);
+	mutex_unlock(&clocks_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_enable);
+
+/* This function decrements the reference count on the clock and disables
+ * the clock when reference count is 0. The parent clock tree is
+ * recursively disabled
+ */
+void clk_disable(struct clk *clk)
+{
+	if (!clk)
+		return;
+
+	mutex_lock(&clocks_mutex);
+	__clk_disable(clk);
+	mutex_unlock(&clocks_mutex);
+}
+EXPORT_SYMBOL_GPL(clk_disable);
+
+/* Retrieve the *current* clock rate. If the clock itself
+ * does not provide a special calculation routine, ask
+ * its parent and so on, until one is able to return
+ * a valid clock rate
+ */
+unsigned long clk_get_rate(struct clk *clk)
+{
+	if (!clk)
+		return 0UL;
+
+	if (clk->get_rate)
+		return clk->get_rate(clk);
+
+	return clk_get_rate(clk->parent);
+}
+EXPORT_SYMBOL_GPL(clk_get_rate);
+
+/* Round the requested clock rate to the nearest supported
+ * rate that is less than or equal to the requested rate.
+ * This is dependent on the clock's current parent.
+ */
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	if (!clk)
+		return 0;
+	if (!clk->round_rate)
+		return 0;
+
+	return clk->round_rate(clk, rate);
+}
+EXPORT_SYMBOL_GPL(clk_round_rate);
+
+/* Set the clock to the requested clock rate. The rate must
+ * match a supported rate exactly based on what clk_round_rate returns
+ */
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	int ret = -EINVAL;
+
+	if (!clk)
+		return ret;
+	if (!clk->set_rate || !rate)
+		return ret;
+
+	mutex_lock(&clocks_mutex);
+	ret = clk->set_rate(clk, rate);
+	mutex_unlock(&clocks_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_rate);
+
+/* Set the clock's parent to another clock source */
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	struct clk *old;
+	int ret = -EINVAL;
+
+	if (!clk)
+		return ret;
+	if (!clk->set_parent || !parent)
+		return ret;
+
+	mutex_lock(&clocks_mutex);
+	old = clk->parent;
+	if (clk->refcount)
+		__clk_enable(parent);
+	ret = clk->set_parent(clk, parent);
+	if (ret)
+		old = parent;
+	if (clk->refcount)
+		__clk_disable(old);
+	mutex_unlock(&clocks_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_parent);
+
+/* Retrieve the clock's parent clock source */
+struct clk *clk_get_parent(struct clk *clk)
+{
+	if (!clk)
+		return NULL;
+
+	return clk->parent;
+}
+EXPORT_SYMBOL_GPL(clk_get_parent);
diff --git a/arch/arm/plat-tcc/include/mach/clkdev.h b/arch/arm/plat-tcc/include/mach/clkdev.h
new file mode 100644
index 0000000..04b37a8
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/clkdev.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_MACH_CLKDEV_H
+#define __ASM_MACH_CLKDEV_H
+
+#define __clk_get(clk) ({ 1; })
+#define __clk_put(clk) do { } while (0)
+
+#endif
diff --git a/arch/arm/plat-tcc/include/mach/clock.h b/arch/arm/plat-tcc/include/mach/clock.h
new file mode 100644
index 0000000..a12f58a
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/clock.h
@@ -0,0 +1,48 @@
+/*
+ * Low level clock header file for Telechips TCC architecture
+ * (C) 2010 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the GPL v2.
+ */
+
+#ifndef __ASM_ARCH_TCC_CLOCK_H__
+#define __ASM_ARCH_TCC_CLOCK_H__
+
+#ifndef __ASSEMBLY__
+
+struct clk {
+	struct clk *parent;
+	/* id number of a root clock, 0 for normal clocks */
+	int root_id;
+	/* Reference count of clock enable/disable */
+	int refcount;
+	/* Address of associated BCLKCTRx register. Must be set. */
+	void __iomem *bclkctr;
+	/* Bit position for BCLKCTRx. Must be set. */
+	int bclk_shift;
+	/* Address of ACLKxxx register, if any. */
+	void __iomem *aclkreg;
+	/* get the current clock rate (always a fresh value) */
+	unsigned long (*get_rate) (struct clk *);
+	/* Function ptr to set the clock to a new rate. The rate must match a
+	   supported rate returned from round_rate. Leave blank if clock is not
+	   programmable */
+	int (*set_rate) (struct clk *, unsigned long);
+	/* Function ptr to round the requested clock rate to the nearest
+	   supported rate that is less than or equal to the requested rate. */
+	unsigned long (*round_rate) (struct clk *, unsigned long);
+	/* Function ptr to enable the clock. Leave blank if clock can not
+	   be gated. */
+	int (*enable) (struct clk *);
+	/* Function ptr to disable the clock. Leave blank if clock can not
+	   be gated. */
+	void (*disable) (struct clk *);
+	/* Function ptr to set the parent clock of the clock. */
+	int (*set_parent) (struct clk *, struct clk *);
+};
+
+int clk_register(struct clk *clk);
+void clk_unregister(struct clk *clk);
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_ARCH_MXC_CLOCK_H__ */
diff --git a/arch/arm/plat-tcc/include/mach/debug-macro.S b/arch/arm/plat-tcc/include/mach/debug-macro.S
new file mode 100644
index 0000000..7662f73
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/debug-macro.S
@@ -0,0 +1,32 @@
+/*
+ * Copyright (C) 1994-1999 Russell King
+ * Copyright (C) 2008-2009 Telechips
+ * Copyright (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+		.macro	addruart, rp, rv
+		moveq	\rp, #0x90000000	@ physical base address
+		movne	\rv, #0xF1000000	@ virtual base
+		orr	\rp, \rp, #0x00007000	@ UART0
+		orr	\rv, \rv, #0x00007000	@ UART0
+		.endm
+
+		.macro	senduart,rd,rx
+		strb	\rd, [\rx, #0x44]
+		.endm
+
+		.macro	waituart,rd,rx
+		.endm
+
+		.macro	busyuart,rd,rx
+1001:
+		ldr \rd, [\rx, #0x14]
+		tst \rd, #0x20
+
+		beq 1001b
+		.endm
diff --git a/arch/arm/plat-tcc/include/mach/entry-macro.S b/arch/arm/plat-tcc/include/mach/entry-macro.S
new file mode 100644
index 0000000..748f401
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/entry-macro.S
@@ -0,0 +1,68 @@
+/*
+ * include/asm-arm/arch-tcc83x/entry-macro.S
+ *
+ * Author : <linux@telechips.com>
+ * Created: June 10, 2008
+ * Description: Low-level IRQ helper macros for Telechips-based platforms
+ *
+ * Copyright (C) 2008-2009 Telechips
+ *
+ * This file is licensed under  the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <mach/hardware.h>
+#include <mach/irqs.h>
+
+	.macro	disable_fiq
+	.endm
+
+	.macro  get_irqnr_preamble, base, tmp
+	.endm
+
+	.macro  arch_ret_to_user, tmp1, tmp2
+	.endm
+
+	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
+
+		ldr	\base, =0xF2003000 @ base address of PIC registers
+
+		@@ read MREQ register of PIC0
+
+		mov	\irqnr, #0
+		ldr	\irqstat, [\base, #0x00000014 ]	@ lower 32 interrupts
+		cmp	\irqstat, #0
+		bne	1001f
+
+		@@ read MREQ register of PIC1
+
+		ldr	\irqstat, [\base, #0x00000094]	@ upper 32 interrupts
+		cmp	\irqstat, #0
+		beq	1002f
+		mov	\irqnr, #0x20
+
+1001:
+		movs	\tmp, \irqstat, lsl #16
+		movne	\irqstat, \tmp
+		addeq	\irqnr, \irqnr, #16
+
+		movs	\tmp, \irqstat, lsl #8
+		movne	\irqstat, \tmp
+		addeq	\irqnr, \irqnr, #8
+
+		movs	\tmp, \irqstat, lsl #4
+		movne	\irqstat, \tmp
+		addeq	\irqnr, \irqnr, #4
+
+		movs	\tmp, \irqstat, lsl #2
+		movne	\irqstat, \tmp
+		addeq	\irqnr, \irqnr, #2
+
+		movs	\tmp, \irqstat, lsl #1
+		addeq	\irqnr, \irqnr, #1
+		orrs	\base, \base, #1
+1002:
+		@@ exit here, Z flag unset if IRQ
+
+	.endm
diff --git a/arch/arm/plat-tcc/include/mach/hardware.h b/arch/arm/plat-tcc/include/mach/hardware.h
new file mode 100644
index 0000000..e70d126
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/hardware.h
@@ -0,0 +1,43 @@
+/*
+ * Author: RidgeRun, Inc. Greg Lonnon <glonnon@ridgerun.com>
+ * Reorganized for Linux-2.6 by Tony Lindgren <tony@atomide.com>
+ *                          and Dirk Behme <dirk.behme@de.bosch.com>
+ * Rewritten by:    <linux@telechips.com>
+ * Description: Hardware definitions for TCC8300 processors and boards
+ *
+ * Copyright (C) 2001 RidgeRun, Inc.
+ * Copyright (C) 2008-2009 Telechips
+ *
+ * Modifications for mainline (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GNU Pulic License version 2.
+ */
+
+#ifndef __ASM_ARCH_TCC_HARDWARE_H
+#define __ASM_ARCH_TCC_HARDWARE_H
+
+#include <asm/sizes.h>
+#ifndef __ASSEMBLER__
+#include <asm/types.h>
+#endif
+#include <mach/io.h>
+
+/*
+ * ----------------------------------------------------------------------------
+ * Clocks
+ * ----------------------------------------------------------------------------
+ */
+#define CLKGEN_REG_BASE		0xfffece00
+#define ARM_CKCTL		(CLKGEN_REG_BASE + 0x0)
+#define ARM_IDLECT1		(CLKGEN_REG_BASE + 0x4)
+#define ARM_IDLECT2		(CLKGEN_REG_BASE + 0x8)
+#define ARM_EWUPCT		(CLKGEN_REG_BASE + 0xC)
+#define ARM_RSTCT1		(CLKGEN_REG_BASE + 0x10)
+#define ARM_RSTCT2		(CLKGEN_REG_BASE + 0x14)
+#define ARM_SYSST		(CLKGEN_REG_BASE + 0x18)
+#define ARM_IDLECT3		(CLKGEN_REG_BASE + 0x24)
+
+/* DPLL control registers */
+#define DPLL_CTL		0xfffecf00
+
+#endif	/* __ASM_ARCH_TCC_HARDWARE_H */
diff --git a/arch/arm/plat-tcc/include/mach/io.h b/arch/arm/plat-tcc/include/mach/io.h
new file mode 100644
index 0000000..3e911d3
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/io.h
@@ -0,0 +1,23 @@
+/*
+ * IO definitions for TCC8000 processors and boards
+ *
+ * Copyright (C) 1997-1999 Russell King
+ * Copyright (C) 2008-2009 Telechips
+ * Copyright (C) 2010 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GNU Public License version 2.
+ */
+
+#ifndef __ASM_ARM_ARCH_IO_H
+#define __ASM_ARM_ARCH_IO_H
+
+#define IO_SPACE_LIMIT 0xffffffff
+
+/*
+ * We don't actually have real ISA nor PCI buses, but there is so many
+ * drivers out there that might just work if we fake them...
+ */
+#define __io(a)			__typesafe_io(a)
+#define __mem_pci(a)		(a)
+
+#endif
diff --git a/arch/arm/plat-tcc/include/mach/irqs.h b/arch/arm/plat-tcc/include/mach/irqs.h
new file mode 100644
index 0000000..da86389
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/irqs.h
@@ -0,0 +1,83 @@
+/*
+ * IRQ definitions for TCC8xxx
+ *
+ * Copyright (C) 2008-2009 Telechips
+ * Copyright (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GPL v2.
+ *
+ */
+
+#ifndef __ASM_ARCH_TCC_IRQS_H
+#define __ASM_ARCH_TCC_IRQS_H
+
+#define NR_IRQS 64
+
+/* PIC0 interrupts */
+#define INT_ADMA1	0
+#define INT_BDMA	1
+#define INT_ADMA0	2
+#define INT_GDMA1	3
+#define INT_I2S0RX	4
+#define INT_I2S0TX	5
+#define INT_TC		6
+#define INT_UART0	7
+#define INT_USBD	8
+#define INT_SPI0TX	9
+#define INT_UDMA	10
+#define INT_LIRQ	11
+#define INT_GDMA2	12
+#define INT_GDMA0	13
+#define INT_TC32	14
+#define INT_LCD		15
+#define INT_ADC		16
+#define INT_I2C		17
+#define INT_RTCP	18
+#define INT_RTCA	19
+#define INT_NFC		20
+#define INT_SD0		21
+#define INT_GSB0	22
+#define INT_PK		23
+#define INT_USBH0	24
+#define INT_USBH1	25
+#define INT_G2D		26
+#define INT_ECC		27
+#define INT_SPI0RX	28
+#define INT_UART1	29
+#define INT_MSCL	30
+#define INT_GSB1	31
+/* PIC1 interrupts */
+#define INT_E0		32
+#define INT_E1		33
+#define INT_E2		34
+#define INT_E3		35
+#define INT_E4		36
+#define INT_E5		37
+#define INT_E6		38
+#define INT_E7		39
+#define INT_UART2	40
+#define INT_UART3	41
+#define INT_SPI1TX	42
+#define INT_SPI1RX	43
+#define INT_GSB2	44
+#define INT_SPDIF	45
+#define INT_CDIF	46
+#define INT_VBON	47
+#define INT_VBOFF	48
+#define INT_SD1		49
+#define INT_UART4	50
+#define INT_GDMA3	51
+#define INT_I2S1RX	52
+#define INT_I2S1TX	53
+#define INT_CAN0	54
+#define INT_CAN1	55
+#define INT_GSB3	56
+#define INT_KRST	57
+#define INT_UNUSED	58
+#define INT_SD0D3	59
+#define INT_SD1D3	60
+#define INT_GPS0	61
+#define INT_GPS1	62
+#define INT_GPS2	63
+
+#endif  /* ASM_ARCH_TCC_IRQS_H */
diff --git a/arch/arm/plat-tcc/include/mach/memory.h b/arch/arm/plat-tcc/include/mach/memory.h
new file mode 100644
index 0000000..cd91ba8
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/memory.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 1999 ARM Limited
+ * Copyright (C) 2000 RidgeRun, Inc.
+ * Copyright (C) 2008-2009 Telechips
+ * Copyright (C) 2010 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GPL v2.
+ */
+
+#ifndef __ASM_ARCH_MEMORY_H
+#define __ASM_ARCH_MEMORY_H
+
+/*
+ * Physical DRAM offset.
+ */
+#define PHYS_OFFSET		UL(0x20000000)
+
+#endif
diff --git a/arch/arm/plat-tcc/include/mach/system.h b/arch/arm/plat-tcc/include/mach/system.h
new file mode 100644
index 0000000..909e603
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/system.h
@@ -0,0 +1,31 @@
+/*
+ * Author: <linux@telechips.com>
+ * Created: June 10, 2008
+ * Description: LINUX SYSTEM FUNCTIONS for TCC83x
+ *
+ * Copyright (C) 2008-2009 Telechips
+ *
+ * Licensed under the terms of the GPL v2.
+ *
+ */
+
+#ifndef __ASM_ARCH_SYSTEM_H
+#define __ASM_ARCH_SYSTEM_H
+#include <linux/clk.h>
+
+#include <asm/mach-types.h>
+#include <mach/hardware.h>
+
+extern void plat_tcc_reboot(void);
+
+static inline void arch_idle(void)
+{
+	cpu_do_idle();
+}
+
+static inline void arch_reset(char mode, const char *cmd)
+{
+	plat_tcc_reboot();
+}
+
+#endif
diff --git a/arch/arm/plat-tcc/include/mach/tcc8k-regs.h b/arch/arm/plat-tcc/include/mach/tcc8k-regs.h
new file mode 100644
index 0000000..1d94282
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/tcc8k-regs.h
@@ -0,0 +1,807 @@
+/*
+ * Telechips TCC8000 register definitions
+ *
+ * (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GPLv2.
+ */
+
+#ifndef TCC8K_REGS_H
+#define TCC8K_REGS_H
+
+#include <linux/types.h>
+
+#define EXT_SDRAM_BASE		0x20000000
+#define INT_SRAM_BASE		0x30000000
+#define INT_SRAM_SIZE		SZ_32K
+#define CS0_BASE		0x40000000
+#define CS1_BASE		0x50000000
+#define CS1_SIZE		SZ_64K
+#define CS2_BASE		0x60000000
+#define CS3_BASE		0x70000000
+#define AHB_PERI_BASE		0x80000000
+#define AHB_PERI_SIZE		SZ_64K
+#define APB0_PERI_BASE		0x90000000
+#define APB0_PERI_SIZE		SZ_128K
+#define APB1_PERI_BASE		0x98000000
+#define APB1_PERI_SIZE		SZ_128K
+#define DATA_TCM_BASE		0xa0000000
+#define DATA_TCM_SIZE		SZ_8K
+#define EXT_MEM_CTRL_BASE	0xf0000000
+#define EXT_MEM_CTRL_SIZE	SZ_4K
+
+#define CS1_BASE_VIRT		(void __iomem *)0xf7000000
+#define AHB_PERI_BASE_VIRT	(void __iomem *)0xf4000000
+#define APB0_PERI_BASE_VIRT	(void __iomem *)0xf1000000
+#define APB1_PERI_BASE_VIRT	(void __iomem *)0xf2000000
+#define EXT_MEM_CTRL_BASE_VIRT	(void __iomem *)0xf3000000
+#define INT_SRAM_BASE_VIRT	(void __iomem *)0xf5000000
+#define DATA_TCM_BASE_VIRT	(void __iomem *)0xf6000000
+
+#define __REG(x)     (*((volatile u32 *)(x)))
+
+/* USB Device Controller Registers */
+#define UDC_BASE	(AHB_PERI_BASE_VIRT + 0x8000)
+#define UDC_BASE_PHYS	(AHB_PERI_BASE + 0x8000)
+
+#define UDC_IR_OFFS		0x00
+#define UDC_EIR_OFFS		0x04
+#define UDC_EIER_OFFS		0x08
+#define UDC_FAR_OFFS		0x0c
+#define UDC_FNR_OFFS		0x10
+#define UDC_EDR_OFFS		0x14
+#define UDC_RT_OFFS		0x18
+#define UDC_SSR_OFFS		0x1c
+#define UDC_SCR_OFFS		0x20
+#define UDC_EP0SR_OFFS		0x24
+#define UDC_EP0CR_OFFS		0x28
+
+#define UDC_ESR_OFFS		0x2c
+#define UDC_ECR_OFFS		0x30
+#define UDC_BRCR_OFFS		0x34
+#define UDC_BWCR_OFFS		0x38
+#define UDC_MPR_OFFS		0x3c
+#define UDC_DCR_OFFS		0x40
+#define UDC_DTCR_OFFS		0x44
+#define UDC_DFCR_OFFS		0x48
+#define UDC_DTTCR1_OFFS		0x4c
+#define UDC_DTTCR2_OFFS		0x50
+#define UDC_ESR2_OFFS		0x54
+
+#define UDC_SCR2_OFFS		0x58
+#define UDC_EP0BUF_OFFS		0x60
+#define UDC_EP1BUF_OFFS		0x64
+#define UDC_EP2BUF_OFFS		0x68
+#define UDC_EP3BUF_OFFS		0x6c
+#define UDC_PLICR_OFFS		0xa0
+#define UDC_PCR_OFFS		0xa4
+
+#define UDC_UPCR0_OFFS		0xc8
+#define UDC_UPCR1_OFFS		0xcc
+#define UDC_UPCR2_OFFS		0xd0
+#define UDC_UPCR3_OFFS		0xd4
+
+/* Bits in UDC_EIR */
+#define UDC_EIR_EP0I		(1 << 0)
+#define UDC_EIR_EP1I		(1 << 1)
+#define UDC_EIR_EP2I		(1 << 2)
+#define UDC_EIR_EP3I		(1 << 3)
+#define UDC_EIR_EPI_MASK	0x0f
+
+/* Bits in UDC_EIER */
+#define UDC_EIER_EP0IE		(1 << 0)
+#define UDC_EIER_EP1IE		(1 << 1)
+#define UDC_EIER_EP2IE		(1 << 2)
+#define UDC_EIER_EP3IE		(1 << 3)
+
+/* Bits in UDC_FNR */
+#define UDC_FNR_FN_MASK		0x7ff
+#define UDC_FNR_SM		(1 << 13)
+#define UDC_FNR_FTL		(1 << 14)
+
+/* Bits in UDC_SSR */
+#define UDC_SSR_HFRES		(1 << 0)
+#define UDC_SSR_HFSUSP		(1 << 1)
+#define UDC_SSR_HFRM		(1 << 2)
+#define UDC_SSR_SDE		(1 << 3)
+#define UDC_SSR_HSP		(1 << 4)
+#define UDC_SSR_DM		(1 << 5)
+#define UDC_SSR_DP		(1 << 6)
+#define UDC_SSR_TBM		(1 << 7)
+#define UDC_SSR_VBON		(1 << 8)
+#define UDC_SSR_VBOFF		(1 << 9)
+#define UDC_SSR_EOERR		(1 << 10)
+#define UDC_SSR_DCERR		(1 << 11)
+#define UDC_SSR_TCERR		(1 << 12)
+#define UDC_SSR_BSERR		(1 << 13)
+#define UDC_SSR_TMERR		(1 << 14)
+#define UDC_SSR_BAERR		(1 << 15)
+
+/* Bits in UDC_SCR */
+#define UDC_SCR_HRESE		(1 << 0)
+#define UDC_SCR_HSSPE		(1 << 1)
+#define UDC_SCR_RRDE		(1 << 5)
+#define UDC_SCR_SPDEN		(1 << 6)
+#define UDC_SCR_DIEN		(1 << 12)
+
+/* Bits in UDC_EP0SR */
+#define UDC_EP0SR_RSR		(1 << 0)
+#define UDC_EP0SR_TST		(1 << 1)
+#define UDC_EP0SR_SHT		(1 << 4)
+#define UDC_EP0SR_LWO		(1 << 6)
+
+/* Bits in UDC_EP0CR */
+#define UDC_EP0CR_ESS		(1 << 1)
+
+/* Bits in UDC_ESR */
+#define UDC_ESR_RPS		(1 << 0)
+#define UDC_ESR_TPS		(1 << 1)
+#define UDC_ESR_LWO		(1 << 4)
+#define UDC_ESR_FFS		(1 << 6)
+
+/* Bits in UDC_ECR */
+#define UDC_ECR_ESS		(1 << 1)
+#define UDC_ECR_CDP		(1 << 2)
+
+#define UDC_ECR_FLUSH		(1 << 6)
+#define UDC_ECR_DUEN		(1 << 7)
+
+/* Bits in UDC_UPCR0 */
+#define UDC_UPCR0_VBD		(1 << 1)
+#define UDC_UPCR0_VBDS		(1 << 6)
+#define UDC_UPCR0_RCD_12	(0x0 << 9)
+#define UDC_UPCR0_RCD_24	(0x1 << 9)
+#define UDC_UPCR0_RCD_48	(0x2 << 9)
+#define UDC_UPCR0_RCS_EXT	(0x1 << 11)
+#define UDC_UPCR0_RCS_XTAL	(0x0 << 11)
+
+/* Bits in UDC_UPCR1 */
+#define UDC_UPCR1_CDT(x)	((x) << 0)
+#define UDC_UPCR1_OTGT(x)	((x) << 3)
+#define UDC_UPCR1_SQRXT(x)	((x) << 8)
+#define UDC_UPCR1_TXFSLST(x)	((x) << 12)
+
+/* Bits in UDC_UPCR2 */
+#define UDC_UPCR2_TP		(1 << 0)
+#define UDC_UPCR2_TXRT(x)	((x) << 2)
+#define UDC_UPCR2_TXVRT(x)	((x) << 5)
+#define UDC_UPCR2_OPMODE(x)	((x) << 9)
+#define UDC_UPCR2_XCVRSEL(x)	((x) << 12)
+#define UDC_UPCR2_TM		(1 << 14)
+
+/* USB Host Controller registers */
+#define USBH0_BASE	(AHB_PERI_BASE_VIRT + 0xb000)
+#define USBH1_BASE	(AHB_PERI_BASE_VIRT + 0xb800)
+
+#define OHCI_INT_ENABLE_OFFS	0x10
+
+#define RH_DESCRIPTOR_A_OFFS	0x48
+#define RH_DESCRIPTOR_B_OFFS	0x4c
+
+#define USBHTCFG0_OFFS		0x100
+#define USBHHCFG0_OFFS		0x104
+#define USBHHCFG1_OFFS		0x104
+
+/* DMA controller registers */
+#define DMAC0_BASE	(AHB_PERI_BASE + 0x4000)
+#define DMAC1_BASE	(AHB_PERI_BASE + 0xa000)
+#define DMAC2_BASE	(AHB_PERI_BASE + 0x4800)
+#define DMAC3_BASE	(AHB_PERI_BASE + 0xa800)
+
+#define DMAC_CH_OFFSET(ch)	(ch * 0x30)
+
+#define ST_SADR_OFFS		0x00
+#define SPARAM_OFFS		0x04
+#define C_SADR_OFFS		0x0c
+#define ST_DADR_OFFS		0x10
+#define DPARAM_OFFS		0x14
+#define C_DADR_OFFS		0x1c
+#define HCOUNT_OFFS		0x20
+#define CHCTRL_OFFS		0x24
+#define RPTCTRL_OFFS		0x28
+#define EXTREQ_A_OFFS		0x2c
+
+/* Bits in CHCTRL register */
+#define CHCTRL_EN		(1 << 0)
+
+#define CHCTRL_IEN		(1 << 2)
+#define CHCTRL_FLAG		(1 << 3)
+#define CHCTRL_WSIZE8		(0 << 4)
+#define CHCTRL_WSIZE16		(1 << 4)
+#define CHCTRL_WSIZE32		(2 << 4)
+
+#define CHCTRL_BSIZE1		(0 << 6)
+#define CHCTRL_BSIZE2		(1 << 6)
+#define CHCTRL_BSIZE4		(2 << 6)
+#define CHCTRL_BSIZE8		(3 << 6)
+
+#define CHCTRL_TYPE_SINGLE_E	(0 << 8)
+#define CHCTRL_TYPE_HW		(1 << 8)
+#define CHCTRL_TYPE_SW		(2 << 8)
+#define CHCTRL_TYPE_SINGLE_L	(3 << 8)
+
+#define CHCTRL_BST		(1 << 10)
+
+/* Use DMA controller 0, channel 2 for USB */
+#define USB_DMA_BASE		(DMAC0_BASE + DMAC_CH_OFFSET(2))
+
+/* NAND flash controller registers */
+#define NFC_BASE	(AHB_PERI_BASE_VIRT + 0xd000)
+#define NFC_BASE_PHYS	(AHB_PERI_BASE + 0xd000)
+
+#define NFC_CMD_OFFS		0x00
+#define NFC_LADDR_OFFS		0x04
+#define NFC_BADDR_OFFS		0x08
+#define NFC_SADDR_OFFS		0x0c
+#define NFC_WDATA_OFFS		0x10
+#define NFC_LDATA_OFFS		0x20
+#define NFC_SDATA_OFFS		0x40
+#define NFC_CTRL_OFFS		0x50
+#define NFC_PSTART_OFFS		0x54
+#define NFC_RSTART_OFFS		0x58
+#define NFC_DSIZE_OFFS		0x5c
+#define NFC_IREQ_OFFS		0x60
+#define NFC_RST_OFFS		0x64
+#define NFC_CTRL1_OFFS		0x68
+#define NFC_MDATA_OFFS		0x70
+
+#define NFC_WDATA_PHYS_ADDR	(NFC_BASE_PHYS + NFC_WDATA_OFFS)
+
+/* Bits in NFC_CTRL */
+#define NFC_CTRL_BHLD_MASK	(0xf << 0)
+#define NFC_CTRL_BPW_MASK	(0xf << 4)
+#define NFC_CTRL_BSTP_MASK	(0xf << 8)
+#define NFC_CTRL_CADDR_MASK	(0x7 << 12)
+#define NFC_CTRL_CADDR_1	(0x0 << 12)
+#define NFC_CTRL_CADDR_2	(0x1 << 12)
+#define NFC_CTRL_CADDR_3	(0x2 << 12)
+#define NFC_CTRL_CADDR_4	(0x3 << 12)
+#define NFC_CTRL_CADDR_5	(0x4 << 12)
+#define NFC_CTRL_MSK		(1 << 15)
+#define NFC_CTRL_PSIZE256	(0 << 16)
+#define NFC_CTRL_PSIZE512	(1 << 16)
+#define NFC_CTRL_PSIZE1024	(2 << 16)
+#define NFC_CTRL_PSIZE2048	(3 << 16)
+#define NFC_CTRL_PSIZE4096	(4 << 16)
+#define NFC_CTRL_PSIZE_MASK	(7 << 16)
+#define NFC_CTRL_BSIZE1		(0 << 19)
+#define NFC_CTRL_BSIZE2		(1 << 19)
+#define NFC_CTRL_BSIZE4		(2 << 19)
+#define NFC_CTRL_BSIZE8		(3 << 19)
+#define NFC_CTRL_BSIZE_MASK	(3 << 19)
+#define NFC_CTRL_RDY		(1 << 21)
+#define NFC_CTRL_CS0SEL		(1 << 22)
+#define NFC_CTRL_CS1SEL		(1 << 23)
+#define NFC_CTRL_CS2SEL		(1 << 24)
+#define NFC_CTRL_CS3SEL		(1 << 25)
+#define NFC_CTRL_CSMASK		(0xf << 22)
+#define NFC_CTRL_BW		(1 << 26)
+#define NFC_CTRL_FS		(1 << 27)
+#define NFC_CTRL_DEN		(1 << 28)
+#define NFC_CTRL_READ_IEN	(1 << 29)
+#define NFC_CTRL_PROG_IEN	(1 << 30)
+#define NFC_CTRL_RDY_IEN	(1 << 31)
+
+/* Bits in NFC_IREQ */
+#define NFC_IREQ_IRQ0		(1 << 0)
+#define NFC_IREQ_IRQ1		(1 << 1)
+#define NFC_IREQ_IRQ2		(1 << 2)
+
+#define NFC_IREQ_FLAG0		(1 << 4)
+#define NFC_IREQ_FLAG1		(1 << 5)
+#define NFC_IREQ_FLAG2		(1 << 6)
+
+/* MMC controller registers */
+#define MMC0_BASE	(AHB_PERI_BASE_VIRT + 0xe000)
+#define MMC1_BASE	(AHB_PERI_BASE_VIRT + 0xe800)
+
+/* UART base addresses */
+
+#define UART0_BASE	(APB0_PERI_BASE_VIRT + 0x07000)
+#define UART0_BASE_PHYS	(APB0_PERI_BASE + 0x07000)
+#define UART1_BASE	(APB0_PERI_BASE_VIRT + 0x08000)
+#define UART1_BASE_PHYS	(APB0_PERI_BASE + 0x08000)
+#define UART2_BASE	(APB0_PERI_BASE_VIRT + 0x09000)
+#define UART2_BASE_PHYS	(APB0_PERI_BASE + 0x09000)
+#define UART3_BASE	(APB0_PERI_BASE_VIRT + 0x0a000)
+#define UART3_BASE_PHYS	(APB0_PERI_BASE + 0x0a000)
+#define UART4_BASE	(APB0_PERI_BASE_VIRT + 0x15000)
+#define UART4_BASE_PHYS	(APB0_PERI_BASE + 0x15000)
+
+#define UART_BASE	UART0_BASE
+#define UART_BASE_PHYS	UART0_BASE_PHYS
+
+/* ECC controller */
+#define ECC_CTR_BASE	(APB0_PERI_BASE_VIRT + 0xd000)
+
+#define ECC_CTRL_OFFS		0x00
+#define ECC_BASE_OFFS		0x04
+#define ECC_MASK_OFFS		0x08
+#define ECC_CLEAR_OFFS		0x0c
+#define ECC4_0_OFFS		0x10
+#define ECC4_1_OFFS		0x14
+
+#define ECC_EADDR0_OFFS		0x50
+
+#define ECC_ERRNUM_OFFS		0x90
+#define ECC_IREQ_OFFS		0x94
+
+/* Bits in ECC_CTRL */
+#define ECC_CTRL_ECC4_DIEN	(1 << 28)
+#define ECC_CTRL_ECC8_DIEN	(1 << 29)
+#define ECC_CTRL_ECC12_DIEN	(1 << 30)
+#define ECC_CTRL_ECC_DISABLE	0x0
+#define ECC_CTRL_ECC_SLC_ENC	0x8
+#define ECC_CTRL_ECC_SLC_DEC	0x9
+#define ECC_CTRL_ECC4_ENC	0xa
+#define ECC_CTRL_ECC4_DEC	0xb
+#define ECC_CTRL_ECC8_ENC	0xc
+#define ECC_CTRL_ECC8_DEC	0xd
+#define ECC_CTRL_ECC12_ENC	0xe
+#define ECC_CTRL_ECC12_DEC	0xf
+
+/* Bits in ECC_IREQ */
+#define ECC_IREQ_E4DI		(1 << 4)
+
+#define ECC_IREQ_E4DF		(1 << 20)
+#define ECC_IREQ_E4EF		(1 << 21)
+
+/* Interrupt controller */
+
+#define PIC0_BASE	(APB1_PERI_BASE_VIRT + 0x3000)
+#define PIC0_BASE_PHYS	(APB1_PERI_BASE + 0x3000)
+
+#define PIC0_IEN_OFFS		0x00
+#define PIC0_CREQ_OFFS		0x04
+#define PIC0_IREQ_OFFS		0x08
+#define PIC0_IRQSEL_OFFS	0x0c
+#define PIC0_SRC_OFFS		0x10
+#define PIC0_MREQ_OFFS		0x14
+#define PIC0_TSTREQ_OFFS	0x18
+#define PIC0_POL_OFFS		0x1c
+#define PIC0_IRQ_OFFS		0x20
+#define PIC0_FIQ_OFFS		0x24
+#define PIC0_MIRQ_OFFS		0x28
+#define PIC0_MFIQ_OFFS		0x2c
+#define PIC0_TMODE_OFFS		0x30
+#define PIC0_SYNC_OFFS		0x34
+#define PIC0_WKUP_OFFS		0x38
+#define PIC0_TMODEA_OFFS	0x3c
+#define PIC0_INTOEN_OFFS	0x40
+#define PIC0_MEN0_OFFS		0x44
+#define PIC0_MEN_OFFS		0x48
+
+#define PIC0_IEN		__REG(PIC0_BASE + PIC0_IEN_OFFS)
+#define PIC0_IEN_PHYS		__REG(PIC0_BASE_PHYS + PIC0_IEN_OFFS)
+#define PIC0_CREQ		__REG(PIC0_BASE + PIC0_CREQ_OFFS)
+#define PIC0_CREQ_PHYS		__REG(PIC0_BASE_PHYS + PIC0_CREQ_OFFS)
+#define PIC0_IREQ		__REG(PIC0_BASE + PIC0_IREQ_OFFS)
+#define PIC0_IRQSEL		__REG(PIC0_BASE + PIC0_IRQSEL_OFFS)
+#define PIC0_IRQSEL_PHYS	__REG(PIC0_BASE_PHYS + PIC0_IRQSEL_OFFS)
+#define PIC0_SRC		__REG(PIC0_BASE + PIC0_SRC_OFFS)
+#define PIC0_MREQ		__REG(PIC0_BASE + PIC0_MREQ_OFFS)
+#define PIC0_TSTREQ		__REG(PIC0_BASE + PIC0_TSTREQ_OFFS)
+#define PIC0_POL		__REG(PIC0_BASE + PIC0_POL_OFFS)
+#define PIC0_IRQ		__REG(PIC0_BASE + PIC0_IRQ_OFFS)
+#define PIC0_FIQ		__REG(PIC0_BASE + PIC0_FIQ_OFFS)
+#define PIC0_MIRQ		__REG(PIC0_BASE + PIC0_MIRQ_OFFS)
+#define PIC0_MFIQ		__REG(PIC0_BASE + PIC0_MFIQ_OFFS)
+#define PIC0_TMODE		__REG(PIC0_BASE + PIC0_TMODE_OFFS)
+#define PIC0_TMODE_PHYS		__REG(PIC0_BASE_PHYS + PIC0_TMODE_OFFS)
+#define PIC0_SYNC		__REG(PIC0_BASE + PIC0_SYNC_OFFS)
+#define PIC0_WKUP		__REG(PIC0_BASE + PIC0_WKUP_OFFS)
+#define PIC0_TMODEA		__REG(PIC0_BASE + PIC0_TMODEA_OFFS)
+#define PIC0_INTOEN		__REG(PIC0_BASE + PIC0_INTOEN_OFFS)
+#define PIC0_MEN0		__REG(PIC0_BASE + PIC0_MEN0_OFFS)
+#define PIC0_MEN		__REG(PIC0_BASE + PIC0_MEN_OFFS)
+
+#define PIC1_BASE	(APB1_PERI_BASE_VIRT + 0x3080)
+
+#define PIC1_IEN_OFFS		0x00
+#define PIC1_CREQ_OFFS		0x04
+#define PIC1_IREQ_OFFS		0x08
+#define PIC1_IRQSEL_OFFS	0x0c
+#define PIC1_SRC_OFFS		0x10
+#define PIC1_MREQ_OFFS		0x14
+#define PIC1_TSTREQ_OFFS	0x18
+#define PIC1_POL_OFFS		0x1c
+#define PIC1_IRQ_OFFS		0x20
+#define PIC1_FIQ_OFFS		0x24
+#define PIC1_MIRQ_OFFS		0x28
+#define PIC1_MFIQ_OFFS		0x2c
+#define PIC1_TMODE_OFFS		0x30
+#define PIC1_SYNC_OFFS		0x34
+#define PIC1_WKUP_OFFS		0x38
+#define PIC1_TMODEA_OFFS	0x3c
+#define PIC1_INTOEN_OFFS	0x40
+#define PIC1_MEN1_OFFS		0x44
+#define PIC1_MEN_OFFS		0x48
+
+#define PIC1_IEN	__REG(PIC1_BASE + PIC1_IEN_OFFS)
+#define PIC1_CREQ	__REG(PIC1_BASE + PIC1_CREQ_OFFS)
+#define PIC1_IREQ	__REG(PIC1_BASE + PIC1_IREQ_OFFS)
+#define PIC1_IRQSEL	__REG(PIC1_BASE + PIC1_IRQSEL_OFFS)
+#define PIC1_SRC	__REG(PIC1_BASE + PIC1_SRC_OFFS)
+#define PIC1_MREQ	__REG(PIC1_BASE + PIC1_MREQ_OFFS)
+#define PIC1_TSTREQ	__REG(PIC1_BASE + PIC1_TSTREQ_OFFS)
+#define PIC1_POL	__REG(PIC1_BASE + PIC1_POL_OFFS)
+#define PIC1_IRQ	__REG(PIC1_BASE + PIC1_IRQ_OFFS)
+#define PIC1_FIQ	__REG(PIC1_BASE + PIC1_FIQ_OFFS)
+#define PIC1_MIRQ	__REG(PIC1_BASE + PIC1_MIRQ_OFFS)
+#define PIC1_MFIQ	__REG(PIC1_BASE + PIC1_MFIQ_OFFS)
+#define PIC1_TMODE	__REG(PIC1_BASE + PIC1_TMODE_OFFS)
+#define PIC1_SYNC	__REG(PIC1_BASE + PIC1_SYNC_OFFS)
+#define PIC1_WKUP	__REG(PIC1_BASE + PIC1_WKUP_OFFS)
+#define PIC1_TMODEA	__REG(PIC1_BASE + PIC1_TMODEA_OFFS)
+#define PIC1_INTOEN	__REG(PIC1_BASE + PIC1_INTOEN_OFFS)
+#define PIC1_MEN1	__REG(PIC1_BASE + PIC1_MEN1_OFFS)
+#define PIC1_MEN	__REG(PIC1_BASE + PIC1_MEN_OFFS)
+
+/* Timer registers */
+#define TIMER_BASE		(APB1_PERI_BASE_VIRT + 0x4000)
+#define TIMER_BASE_PHYS		(APB1_PERI_BASE + 0x4000)
+
+#define TWDCFG_OFFS		0x70
+
+#define TC32EN_OFFS		0x80
+#define TC32LDV_OFFS		0x84
+#define TC32CMP0_OFFS		0x88
+#define TC32CMP1_OFFS		0x8c
+#define TC32PCNT_OFFS		0x90
+#define TC32MCNT_OFFS		0x94
+#define TC32IRQ_OFFS		0x98
+
+/* Bits in TC32EN */
+#define TC32EN_PRESCALE_MASK	0x00ffffff
+#define TC32EN_ENABLE		(1 << 24)
+#define TC32EN_LOADZERO		(1 << 25)
+#define TC32EN_STOPMODE		(1 << 26)
+#define TC32EN_LDM0		(1 << 28)
+#define TC32EN_LDM1		(1 << 29)
+
+/* Bits in TC32IRQ */
+#define TC32IRQ_MSTAT_MASK	0x0000001f
+#define TC32IRQ_RSTAT_MASK	(0x1f << 8)
+#define TC32IRQ_IRQEN0		(1 << 16)
+#define TC32IRQ_IRQEN1		(1 << 17)
+#define TC32IRQ_IRQEN2		(1 << 18)
+#define TC32IRQ_IRQEN3		(1 << 19)
+#define TC32IRQ_IRQEN4		(1 << 20)
+#define TC32IRQ_RSYNC		(1 << 30)
+#define TC32IRQ_IRQCLR		(1 << 31)
+
+/* GPIO registers */
+#define GPIOPD_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOPD_DAT_OFFS		0x00
+#define GPIOPD_DOE_OFFS		0x04
+#define GPIOPD_FS0_OFFS		0x08
+#define GPIOPD_FS1_OFFS		0x0c
+#define GPIOPD_FS2_OFFS		0x10
+#define GPIOPD_RPU_OFFS		0x30
+#define GPIOPD_RPD_OFFS		0x34
+#define GPIOPD_DV0_OFFS		0x38
+#define GPIOPD_DV1_OFFS		0x3c
+
+#define GPIOPS_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOPS_DAT_OFFS		0x40
+#define GPIOPS_DOE_OFFS		0x44
+#define GPIOPS_FS0_OFFS		0x48
+#define GPIOPS_FS1_OFFS		0x4c
+#define GPIOPS_FS2_OFFS		0x50
+#define GPIOPS_FS3_OFFS		0x54
+#define GPIOPS_RPU_OFFS		0x70
+#define GPIOPS_RPD_OFFS		0x74
+#define GPIOPS_DV0_OFFS		0x78
+#define GPIOPS_DV1_OFFS		0x7c
+
+#define GPIOPS_FS1_SDH0_BITS	0x000000ff
+#define GPIOPS_FS1_SDH1_BITS	0x0000ff00
+
+#define GPIOPU_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOPU_DAT_OFFS		0x80
+#define GPIOPU_DOE_OFFS		0x84
+#define GPIOPU_FS0_OFFS		0x88
+#define GPIOPU_FS1_OFFS		0x8c
+#define GPIOPU_FS2_OFFS		0x90
+#define GPIOPU_RPU_OFFS		0xb0
+#define GPIOPU_RPD_OFFS		0xb4
+#define GPIOPU_DV0_OFFS		0xb8
+#define GPIOPU_DV1_OFFS		0xbc
+
+#define GPIOPU_FS0_TXD0		(1 << 0)
+#define GPIOPU_FS0_RXD0		(1 << 1)
+#define GPIOPU_FS0_CTS0		(1 << 2)
+#define GPIOPU_FS0_RTS0		(1 << 3)
+#define GPIOPU_FS0_TXD1		(1 << 4)
+#define GPIOPU_FS0_RXD1		(1 << 5)
+#define GPIOPU_FS0_CTS1		(1 << 6)
+#define GPIOPU_FS0_RTS1		(1 << 7)
+#define GPIOPU_FS0_TXD2		(1 << 8)
+#define GPIOPU_FS0_RXD2		(1 << 9)
+#define GPIOPU_FS0_CTS2		(1 << 10)
+#define GPIOPU_FS0_RTS2		(1 << 11)
+#define GPIOPU_FS0_TXD3		(1 << 12)
+#define GPIOPU_FS0_RXD3		(1 << 13)
+#define GPIOPU_FS0_CTS3		(1 << 14)
+#define GPIOPU_FS0_RTS3		(1 << 15)
+#define GPIOPU_FS0_TXD4		(1 << 16)
+#define GPIOPU_FS0_RXD4		(1 << 17)
+#define GPIOPU_FS0_CTS4		(1 << 18)
+#define GPIOPU_FS0_RTS4		(1 << 19)
+
+#define GPIOFC_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOFC_DAT_OFFS		0xc0
+#define GPIOFC_DOE_OFFS		0xc4
+#define GPIOFC_FS0_OFFS		0xc8
+#define GPIOFC_FS1_OFFS		0xcc
+#define GPIOFC_FS2_OFFS		0xd0
+#define GPIOFC_FS3_OFFS		0xd4
+#define GPIOFC_RPU_OFFS		0xf0
+#define GPIOFC_RPD_OFFS		0xf4
+#define GPIOFC_DV0_OFFS		0xf8
+#define GPIOFC_DV1_OFFS		0xfc
+
+#define GPIOFD_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOFD_DAT_OFFS		0x100
+#define GPIOFD_DOE_OFFS		0x104
+#define GPIOFD_FS0_OFFS		0x108
+#define GPIOFD_FS1_OFFS		0x10c
+#define GPIOFD_FS2_OFFS		0x110
+#define GPIOFD_RPU_OFFS		0x130
+#define GPIOFD_RPD_OFFS		0x134
+#define GPIOFD_DV0_OFFS		0x138
+#define GPIOFD_DV1_OFFS		0x13c
+
+#define GPIOLC_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOLC_DAT_OFFS		0x140
+#define GPIOLC_DOE_OFFS		0x144
+#define GPIOLC_FS0_OFFS		0x148
+#define GPIOLC_FS1_OFFS		0x14c
+#define GPIOLC_RPU_OFFS		0x170
+#define GPIOLC_RPD_OFFS		0x174
+#define GPIOLC_DV0_OFFS		0x178
+#define GPIOLC_DV1_OFFS		0x17c
+
+#define GPIOLD_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOLD_DAT_OFFS		0x180
+#define GPIOLD_DOE_OFFS		0x184
+#define GPIOLD_FS0_OFFS		0x188
+#define GPIOLD_FS1_OFFS		0x18c
+#define GPIOLD_FS2_OFFS		0x190
+#define GPIOLD_RPU_OFFS		0x1b0
+#define GPIOLD_RPD_OFFS		0x1b4
+#define GPIOLD_DV0_OFFS		0x1b8
+#define GPIOLD_DV1_OFFS		0x1bc
+
+#define GPIOAD_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOAD_DAT_OFFS		0x1c0
+#define GPIOAD_DOE_OFFS		0x1c4
+#define GPIOAD_FS0_OFFS		0x1c8
+#define GPIOAD_RPU_OFFS		0x1f0
+#define GPIOAD_RPD_OFFS		0x1f4
+#define GPIOAD_DV0_OFFS		0x1f8
+#define GPIOAD_DV1_OFFS		0x1fc
+
+#define GPIOXC_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOXC_DAT_OFFS		0x200
+#define GPIOXC_DOE_OFFS		0x204
+#define GPIOXC_FS0_OFFS		0x208
+#define GPIOXC_RPU_OFFS		0x230
+#define GPIOXC_RPD_OFFS		0x234
+#define GPIOXC_DV0_OFFS		0x238
+#define GPIOXC_DV1_OFFS		0x23c
+
+#define GPIOXC_FS0		__REG(GPIOXC_BASE + GPIOXC_FS0_OFFS)
+
+#define GPIOXC_FS0_CS0		(1 << 26)
+#define GPIOXC_FS0_CS1		(1 << 27)
+
+#define GPIOXD_BASE		(APB1_PERI_BASE_VIRT + 0x5000)
+
+#define GPIOXD_DAT_OFFS		0x240
+#define GPIOXD_FS0_OFFS		0x248
+#define GPIOXD_RPU_OFFS		0x270
+#define GPIOXD_RPD_OFFS		0x274
+#define GPIOXD_DV0_OFFS		0x278
+#define GPIOXD_DV1_OFFS		0x27c
+
+#define GPIOPK_BASE		(APB1_PERI_BASE_VIRT + 0x1c000)
+
+#define GPIOPK_RST_OFFS		0x008
+#define GPIOPK_DAT_OFFS		0x100
+#define GPIOPK_DOE_OFFS		0x104
+#define GPIOPK_FS0_OFFS		0x108
+#define GPIOPK_FS1_OFFS		0x10c
+#define GPIOPK_FS2_OFFS		0x110
+#define GPIOPK_IRQST_OFFS	0x210
+#define GPIOPK_IRQEN_OFFS	0x214
+#define GPIOPK_IRQPOL_OFFS	0x218
+#define GPIOPK_IRQTM0_OFFS	0x21c
+#define GPIOPK_IRQTM1_OFFS	0x220
+#define GPIOPK_CTL_OFFS		0x22c
+
+#define PMGPIO_BASE		(APB1_PERI_BASE_VIRT + 0x10000)
+#define BACKUP_RAM_BASE		PMGPIO_BASE
+
+#define PMGPIO_DAT_OFFS		0x800
+#define PMGPIO_DOE_OFFS		0x804
+#define PMGPIO_FS0_OFFS		0x808
+#define PMGPIO_RPU_OFFS		0x810
+#define PMGPIO_RPD_OFFS		0x814
+#define PMGPIO_DV0_OFFS		0x818
+#define PMGPIO_DV1_OFFS		0x81c
+#define PMGPIO_EE0_OFFS		0x820
+#define PMGPIO_EE1_OFFS		0x824
+#define PMGPIO_CTL_OFFS		0x828
+#define PMGPIO_DI_OFFS		0x82c
+#define PMGPIO_STR_OFFS		0x830
+#define PMGPIO_STF_OFFS		0x834
+#define PMGPIO_POL_OFFS		0x838
+#define PMGPIO_APB_OFFS		0x800
+
+/* Clock controller registers */
+#define CKC_BASE	((void __iomem *)(APB1_PERI_BASE_VIRT + 0x6000))
+
+#define CLKCTRL_OFFS		0x00
+#define PLL0CFG_OFFS		0x04
+#define PLL1CFG_OFFS		0x08
+#define CLKDIVC0_OFFS		0x0c
+
+#define BCLKCTR0_OFFS		0x14
+#define SWRESET0_OFFS		0x18
+
+#define BCLKCTR1_OFFS		0x60
+#define SWRESET1_OFFS		0x64
+#define PWDCTL_OFFS		0x68
+#define PLL2CFG_OFFS		0x6c
+#define CLKDIVC1_OFFS		0x70
+
+#define ACLKREF_OFFS		0x80
+#define ACLKI2C_OFFS		0x84
+#define ACLKSPI0_OFFS		0x88
+#define ACLKSPI1_OFFS		0x8c
+#define ACLKUART0_OFFS		0x90
+#define ACLKUART1_OFFS		0x94
+#define ACLKUART2_OFFS		0x98
+#define ACLKUART3_OFFS		0x9c
+#define ACLKUART4_OFFS		0xa0
+#define ACLKTCT_OFFS		0xa4
+#define ACLKTCX_OFFS		0xa8
+#define ACLKTCZ_OFFS		0xac
+#define ACLKADC_OFFS		0xb0
+#define ACLKDAI0_OFFS		0xb4
+#define ACLKDAI1_OFFS		0xb8
+#define ACLKLCD_OFFS		0xbc
+#define ACLKSPDIF_OFFS		0xc0
+#define ACLKUSBH_OFFS		0xc4
+#define ACLKSDH0_OFFS		0xc8
+#define ACLKSDH1_OFFS		0xcc
+#define ACLKC3DEC_OFFS		0xd0
+#define ACLKEXT_OFFS		0xd4
+#define ACLKCAN0_OFFS		0xd8
+#define ACLKCAN1_OFFS		0xdc
+#define ACLKGSB0_OFFS		0xe0
+#define ACLKGSB1_OFFS		0xe4
+#define ACLKGSB2_OFFS		0xe8
+#define ACLKGSB3_OFFS		0xec
+
+#define PLLxCFG_PD		(1 << 31)
+
+/* CLKCTRL bits */
+#define CLKCTRL_XE		(1 << 31)
+
+/* CLKDIVCx bits */
+#define CLKDIVC0_XTE		(1 << 7)
+#define CLKDIVC0_XE		(1 << 15)
+#define CLKDIVC0_P1E		(1 << 23)
+#define CLKDIVC0_P0E		(1 << 31)
+
+#define CLKDIVC1_P2E		(1 << 7)
+
+/* BCLKCTR0 clock bits */
+#define BCLKCTR0_USBD		(1 << 4)
+#define BCLKCTR0_ECC		(1 << 9)
+#define BCLKCTR0_USBH0		(1 << 11)
+#define BCLKCTR0_NFC		(1 << 16)
+
+/* BCLKCTR1 clock bits */
+#define BCLKCTR1_USBH1		(1 << 20)
+
+/* SWRESET0 bits */
+#define SWRESET0_USBD		(1 << 4)
+#define SWRESET0_USBH0		(1 << 11)
+
+/* SWRESET1 bits */
+#define SWRESET1_USBH1		(1 << 20)
+
+/* System clock sources.
+ * Note: These are the clock sources that serve as parents for
+ * all other clocks. They have no parents themselves.
+ *
+ * These values are used for struct clk->root_id. All clocks
+ * that are not system clock sources have this value set to
+ * CLK_SRC_NOROOT.
+ * The values for system clocks start with CLK_SRC_PLL0 == 0
+ * because this gives us exactly the values needed for the lower
+ * 4 bits of ACLK_* registers. Therefore, CLK_SRC_NOROOT is
+ * defined as -1 to not disturb the order.
+ */
+enum root_clks {
+	CLK_SRC_NOROOT = -1,
+	CLK_SRC_PLL0 = 0,
+	CLK_SRC_PLL1,
+	CLK_SRC_PLL0DIV,
+	CLK_SRC_PLL1DIV,
+	CLK_SRC_XI,
+	CLK_SRC_XIDIV,
+	CLK_SRC_XTI,
+	CLK_SRC_XTIDIV,
+	CLK_SRC_PLL2,
+	CLK_SRC_PLL2DIV,
+	CLK_SRC_PK0,
+	CLK_SRC_PK1,
+	CLK_SRC_PK2,
+	CLK_SRC_PK3,
+	CLK_SRC_PK4,
+	CLK_SRC_48MHZ
+};
+
+#define CLK_SRC_MASK		0xf
+
+/* Bits in ACLK* registers */
+#define ACLK_EN		(1 << 28)
+#define ACLK_SEL_SHIFT		24
+#define ACLK_SEL_MASK		0x0f000000
+#define ACLK_DIV_MASK		0x00000fff
+
+/* System configuration registers */
+
+#define SCFG_BASE		(APB1_PERI_BASE_VIRT + 0x13000)
+
+#define	BMI_OFFS		0x00
+#define AHBCON0_OFFS		0x04
+#define APBPWE_OFFS		0x08
+#define DTCMWAIT_OFFS		0x0c
+#define ECCSEL_OFFS		0x10
+#define AHBCON1_OFFS		0x14
+#define SDHCFG_OFFS		0x18
+#define REMAP_OFFS		0x20
+#define LCDSIAE_OFFS		0x24
+#define XMCCFG_OFFS		0xe0
+#define IMCCFG_OFFS		0xe4
+
+/* Values for ECCSEL */
+#define ECCSEL_EXTMEM		0x0
+#define ECCSEL_DTCM		0x1
+#define ECCSEL_INT_SRAM		0x2
+#define ECCSEL_AHB		0x3
+
+/* Bits in XMCCFG */
+#define XMCCFG_NFCE		(1 << 1)
+#define XMCCFG_FDXD		(1 << 2)
+
+/* External memory controller registers */
+
+#define EMC_BASE		EXT_MEM_CTRL_BASE
+
+#define SDCFG_OFFS		0x00
+#define SDFSM_OFFS		0x04
+#define MCFG_OFFS		0x08
+
+#define CSCFG0_OFFS		0x10
+#define CSCFG1_OFFS		0x14
+#define CSCFG2_OFFS		0x18
+#define CSCFG3_OFFS		0x1c
+
+#define MCFG_SDEN		(1 << 4)
+
+#endif /* TCC8K_REGS_H */
diff --git a/arch/arm/plat-tcc/include/mach/timex.h b/arch/arm/plat-tcc/include/mach/timex.h
new file mode 100644
index 0000000..057acbe
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/timex.h
@@ -0,0 +1,5 @@
+/*
+ * A definition needed by arch core code.
+ *
+ */
+#define CLOCK_TICK_RATE		(HZ * 100000UL)
diff --git a/arch/arm/plat-tcc/include/mach/uncompress.h b/arch/arm/plat-tcc/include/mach/uncompress.h
new file mode 100644
index 0000000..7a3e33a
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/uncompress.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2009 Hans J. Koch <hjk@linutronix.de>
+ *
+ * This file is licensed under the terms of the GPL version 2.
+ */
+
+#include <linux/serial_reg.h>
+#include <linux/types.h>
+
+#include <mach/tcc8k-regs.h>
+
+unsigned int system_rev;
+
+#define ID_MASK			0x7fff
+
+static void putc(int c)
+{
+	u32 *uart_lsr = (u32 *)(UART_BASE_PHYS + (UART_LSR << 2));
+	u32 *uart_tx = (u32 *)(UART_BASE_PHYS + (UART_TX << 2));
+
+	while (!(*uart_lsr & UART_LSR_THRE))
+		barrier();
+	*uart_tx = c;
+}
+
+static inline void flush(void)
+{
+}
+
+/*
+ * nothing to do
+ */
+#define arch_decomp_setup()
+#define arch_decomp_wdog()
diff --git a/arch/arm/plat-tcc/include/mach/vmalloc.h b/arch/arm/plat-tcc/include/mach/vmalloc.h
new file mode 100644
index 0000000..99414d9
--- /dev/null
+++ b/arch/arm/plat-tcc/include/mach/vmalloc.h
@@ -0,0 +1,10 @@
+/*
+ * Author: <linux@telechips.com>
+ * Created: June 10, 2008
+ *
+ * Copyright (C) 2000 Russell King.
+ * Copyright (C) 2008-2009 Telechips
+ *
+ * Licensed under the terms of the GPL v2.
+ */
+#define VMALLOC_END	0xf0000000UL
diff --git a/arch/arm/plat-tcc/system.c b/arch/arm/plat-tcc/system.c
new file mode 100644
index 0000000..cc208fa
--- /dev/null
+++ b/arch/arm/plat-tcc/system.c
@@ -0,0 +1,25 @@
+/*
+ * System functions for Telechips TCCxxxx SoCs
+ *
+ * Copyright (C) Hans J. Koch <hjk@linutronix.de>
+ *
+ * Licensed under the terms of the GPL v2.
+ *
+ */
+
+#include <linux/io.h>
+
+#include <mach/tcc8k-regs.h>
+
+/* System reboot */
+void plat_tcc_reboot(void)
+{
+	/* Make sure clocks are on */
+	__raw_writel(0xffffffff, CKC_BASE + BCLKCTR0_OFFS);
+
+	/* Enable watchdog reset */
+	__raw_writel(0x49, TIMER_BASE + TWDCFG_OFFS);
+	/* Wait for reset */
+	while(1)
+		;
+}
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index f515727..9ac8725 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -90,6 +90,7 @@
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_ALLOCATOR
 	select HAVE_FB_ATMEL
+	select HAVE_NET_MACB
 
 #
 # CPU types
diff --git a/arch/avr32/boards/mimc200/fram.c b/arch/avr32/boards/mimc200/fram.c
index 54fbd95..9764a1a 100644
--- a/arch/avr32/boards/mimc200/fram.c
+++ b/arch/avr32/boards/mimc200/fram.c
@@ -41,6 +41,7 @@
 static const struct file_operations fram_fops = {
 	.owner			= THIS_MODULE,
 	.mmap			= fram_mmap,
+	.llseek			= noop_llseek,
 };
 
 #define FRAM_MINOR	0
diff --git a/arch/avr32/include/asm/irqflags.h b/arch/avr32/include/asm/irqflags.h
index 93570da..006e948 100644
--- a/arch/avr32/include/asm/irqflags.h
+++ b/arch/avr32/include/asm/irqflags.h
@@ -8,16 +8,14 @@
 #ifndef __ASM_AVR32_IRQFLAGS_H
 #define __ASM_AVR32_IRQFLAGS_H
 
+#include <linux/types.h>
 #include <asm/sysreg.h>
 
-static inline unsigned long __raw_local_save_flags(void)
+static inline unsigned long arch_local_save_flags(void)
 {
 	return sysreg_read(SR);
 }
 
-#define raw_local_save_flags(x)					\
-	do { (x) = __raw_local_save_flags(); } while (0)
-
 /*
  * This will restore ALL status register flags, not only the interrupt
  * mask flag.
@@ -25,44 +23,39 @@
  * The empty asm statement informs the compiler of this fact while
  * also serving as a barrier.
  */
-static inline void raw_local_irq_restore(unsigned long flags)
+static inline void arch_local_irq_restore(unsigned long flags)
 {
 	sysreg_write(SR, flags);
 	asm volatile("" : : : "memory", "cc");
 }
 
-static inline void raw_local_irq_disable(void)
+static inline void arch_local_irq_disable(void)
 {
 	asm volatile("ssrf %0" : : "n"(SYSREG_GM_OFFSET) : "memory");
 }
 
-static inline void raw_local_irq_enable(void)
+static inline void arch_local_irq_enable(void)
 {
 	asm volatile("csrf %0" : : "n"(SYSREG_GM_OFFSET) : "memory");
 }
 
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
 	return (flags & SYSREG_BIT(GM)) != 0;
 }
 
-static inline int raw_irqs_disabled(void)
+static inline bool arch_irqs_disabled(void)
 {
-	unsigned long flags = __raw_local_save_flags();
-
-	return raw_irqs_disabled_flags(flags);
+	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
-static inline unsigned long __raw_local_irq_save(void)
+static inline unsigned long arch_local_irq_save(void)
 {
-	unsigned long flags = __raw_local_save_flags();
+	unsigned long flags = arch_local_save_flags();
 
-	raw_local_irq_disable();
+	arch_local_irq_disable();
 
 	return flags;
 }
 
-#define raw_local_irq_save(flags)				\
-	do { (flags) = __raw_local_irq_save(); } while (0)
-
 #endif /* __ASM_AVR32_IRQFLAGS_H */
diff --git a/arch/blackfin/include/asm/bfin5xx_spi.h b/arch/blackfin/include/asm/bfin5xx_spi.h
index ed4f8c6..4223cf0 100644
--- a/arch/blackfin/include/asm/bfin5xx_spi.h
+++ b/arch/blackfin/include/asm/bfin5xx_spi.h
@@ -11,26 +11,17 @@
 
 #define MIN_SPI_BAUD_VAL	2
 
-#define SPI_READ              0
-#define SPI_WRITE             1
-
-#define SPI_CTRL_OFF            0x0
-#define SPI_FLAG_OFF            0x4
-#define SPI_STAT_OFF            0x8
-#define SPI_TXBUFF_OFF          0xc
-#define SPI_RXBUFF_OFF          0x10
-#define SPI_BAUD_OFF            0x14
-#define SPI_SHAW_OFF            0x18
-
-
 #define BIT_CTL_ENABLE      0x4000
 #define BIT_CTL_OPENDRAIN   0x2000
 #define BIT_CTL_MASTER      0x1000
-#define BIT_CTL_POLAR       0x0800
-#define BIT_CTL_PHASE       0x0400
-#define BIT_CTL_BITORDER    0x0200
+#define BIT_CTL_CPOL        0x0800
+#define BIT_CTL_CPHA        0x0400
+#define BIT_CTL_LSBF        0x0200
 #define BIT_CTL_WORDSIZE    0x0100
-#define BIT_CTL_MISOENABLE  0x0020
+#define BIT_CTL_EMISO       0x0020
+#define BIT_CTL_PSSE        0x0010
+#define BIT_CTL_GM          0x0008
+#define BIT_CTL_SZ          0x0004
 #define BIT_CTL_RXMOD       0x0000
 #define BIT_CTL_TXMOD       0x0001
 #define BIT_CTL_TIMOD_DMA_TX 0x0003
@@ -50,61 +41,7 @@
 #define BIT_STU_SENDOVER    0x0001
 #define BIT_STU_RECVFULL    0x0020
 
-#define CFG_SPI_ENABLE      1
-#define CFG_SPI_DISABLE     0
-
-#define CFG_SPI_OUTENABLE   1
-#define CFG_SPI_OUTDISABLE  0
-
-#define CFG_SPI_ACTLOW      1
-#define CFG_SPI_ACTHIGH     0
-
-#define CFG_SPI_PHASESTART  1
-#define CFG_SPI_PHASEMID    0
-
-#define CFG_SPI_MASTER      1
-#define CFG_SPI_SLAVE       0
-
-#define CFG_SPI_SENELAST    0
-#define CFG_SPI_SENDZERO    1
-
-#define CFG_SPI_RCVFLUSH    1
-#define CFG_SPI_RCVDISCARD  0
-
-#define CFG_SPI_LSBFIRST    1
-#define CFG_SPI_MSBFIRST    0
-
-#define CFG_SPI_WORDSIZE16  1
-#define CFG_SPI_WORDSIZE8   0
-
-#define CFG_SPI_MISOENABLE   1
-#define CFG_SPI_MISODISABLE  0
-
-#define CFG_SPI_READ      0x00
-#define CFG_SPI_WRITE     0x01
-#define CFG_SPI_DMAREAD   0x02
-#define CFG_SPI_DMAWRITE  0x03
-
-#define CFG_SPI_CSCLEARALL  0
-#define CFG_SPI_CHIPSEL1    1
-#define CFG_SPI_CHIPSEL2    2
-#define CFG_SPI_CHIPSEL3    3
-#define CFG_SPI_CHIPSEL4    4
-#define CFG_SPI_CHIPSEL5    5
-#define CFG_SPI_CHIPSEL6    6
-#define CFG_SPI_CHIPSEL7    7
-
-#define CFG_SPI_CS1VALUE    1
-#define CFG_SPI_CS2VALUE    2
-#define CFG_SPI_CS3VALUE    3
-#define CFG_SPI_CS4VALUE    4
-#define CFG_SPI_CS5VALUE    5
-#define CFG_SPI_CS6VALUE    6
-#define CFG_SPI_CS7VALUE    7
-
-#define CMD_SPI_SET_BAUDRATE  2
-#define CMD_SPI_GET_SYSTEMCLOCK   25
-#define CMD_SPI_SET_WRITECONTINUOUS     26
+#define MAX_CTRL_CS          8  /* cs in spi controller */
 
 /* device.platform_data for SSP controller devices */
 struct bfin5xx_spi_master {
@@ -120,9 +57,7 @@
 	u16 ctl_reg;
 	u8 enable_dma;
 	u8 bits_per_word;
-	u8 cs_change_per_word;
 	u16 cs_chg_udelay; /* Some devices require 16-bit delays */
-	u32 cs_gpio;
 	/* Value to send if no TX value is supplied, usually 0x0 or 0xFFFF */
 	u16 idle_tx_val;
 	u8 pio_interrupt; /* Enable spi data irq */
diff --git a/arch/blackfin/include/asm/ipipe.h b/arch/blackfin/include/asm/ipipe.h
index d3b40449..40f94a7 100644
--- a/arch/blackfin/include/asm/ipipe.h
+++ b/arch/blackfin/include/asm/ipipe.h
@@ -49,7 +49,7 @@
 #define prepare_arch_switch(next)		\
 do {						\
 	ipipe_schedule_notify(current, next);	\
-	local_irq_disable_hw();			\
+	hard_local_irq_disable();			\
 } while (0)
 
 #define task_hijacked(p)						\
@@ -57,7 +57,7 @@
 		int __x__ = __ipipe_root_domain_p;			\
 		__clear_bit(IPIPE_SYNC_FLAG, &ipipe_root_cpudom_var(status)); \
 		if (__x__)						\
-			local_irq_enable_hw();				\
+			hard_local_irq_enable();				\
 		!__x__;							\
 	})
 
@@ -167,7 +167,7 @@
 #define __ipipe_run_isr(ipd, irq)					\
 	do {								\
 		if (!__ipipe_pipeline_head_p(ipd))			\
-			local_irq_enable_hw();				\
+			hard_local_irq_enable();				\
 		if (ipd == ipipe_root_domain) {				\
 			if (unlikely(ipipe_virtual_irq_p(irq))) {	\
 				irq_enter();				\
@@ -183,7 +183,7 @@
 			__ipipe_run_irqtail();				\
 			__set_bit(IPIPE_SYNC_FLAG, &ipipe_cpudom_var(ipd, status)); \
 		}							\
-		local_irq_disable_hw();					\
+		hard_local_irq_disable();					\
 	} while (0)
 
 #define __ipipe_syscall_watched_p(p, sc)	\
diff --git a/arch/blackfin/include/asm/irqflags.h b/arch/blackfin/include/asm/irqflags.h
index 813a1af..41c4d70 100644
--- a/arch/blackfin/include/asm/irqflags.h
+++ b/arch/blackfin/include/asm/irqflags.h
@@ -8,6 +8,8 @@
 #ifndef __ASM_BFIN_IRQFLAGS_H__
 #define __ASM_BFIN_IRQFLAGS_H__
 
+#include <mach/blackfin.h>
+
 #ifdef CONFIG_SMP
 # include <asm/pda.h>
 # include <asm/processor.h>
@@ -31,54 +33,108 @@
 	return flags;
 }
 
-#ifdef CONFIG_IPIPE
-
-#include <linux/compiler.h>
-#include <linux/ipipe_base.h>
-#include <linux/ipipe_trace.h>
-
 #ifdef CONFIG_DEBUG_HWERR
 # define bfin_no_irqs 0x3f
 #else
 # define bfin_no_irqs 0x1f
 #endif
 
-#define raw_local_irq_disable()				\
-	do {						\
-		ipipe_check_context(ipipe_root_domain);	\
-		__ipipe_stall_root();			\
-		barrier();				\
-	} while (0)
+/*****************************************************************************/
+/*
+ * Hard, untraced CPU interrupt flag manipulation and access.
+ */
+static inline void __hard_local_irq_disable(void)
+{
+	bfin_cli();
+}
 
-#define raw_local_irq_enable()				\
-	do {						\
-		barrier();				\
-		ipipe_check_context(ipipe_root_domain);	\
-		__ipipe_unstall_root();			\
-	} while (0)
+static inline void __hard_local_irq_enable(void)
+{
+	bfin_sti(bfin_irq_flags);
+}
 
-#define raw_local_save_flags_ptr(x)					\
-	do {								\
-		*(x) = __ipipe_test_root() ? bfin_no_irqs : bfin_irq_flags; \
-	} while (0)
+static inline unsigned long hard_local_save_flags(void)
+{
+	return bfin_read_IMASK();
+}
 
-#define raw_local_save_flags(x)		raw_local_save_flags_ptr(&(x))
+static inline unsigned long __hard_local_irq_save(void)
+{
+	unsigned long flags;
+	flags = bfin_cli();
+#ifdef CONFIG_DEBUG_HWERR
+	bfin_sti(0x3f);
+#endif
+	return flags;
+}
 
-#define raw_irqs_disabled_flags(x)	((x) == bfin_no_irqs)
+static inline int hard_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & ~0x3f) == 0;
+}
 
-#define raw_local_irq_save_ptr(x)					\
-	do {								\
-		*(x) = __ipipe_test_and_stall_root() ? bfin_no_irqs : bfin_irq_flags; \
-		barrier();						\
-	} while (0)
+static inline int hard_irqs_disabled(void)
+{
+	unsigned long flags = hard_local_save_flags();
+	return hard_irqs_disabled_flags(flags);
+}
 
-#define raw_local_irq_save(x)				\
-	do {						\
-		ipipe_check_context(ipipe_root_domain);	\
-		raw_local_irq_save_ptr(&(x));		\
-	} while (0)
+static inline void __hard_local_irq_restore(unsigned long flags)
+{
+	if (!hard_irqs_disabled_flags(flags))
+		__hard_local_irq_enable();
+}
 
-static inline unsigned long raw_mangle_irq_bits(int virt, unsigned long real)
+/*****************************************************************************/
+/*
+ * Interrupt pipe handling.
+ */
+#ifdef CONFIG_IPIPE
+
+#include <linux/compiler.h>
+#include <linux/ipipe_base.h>
+#include <linux/ipipe_trace.h>
+
+/*
+ * Interrupt pipe interface to linux/irqflags.h.
+ */
+static inline void arch_local_irq_disable(void)
+{
+	ipipe_check_context(ipipe_root_domain);
+	__ipipe_stall_root();
+	barrier();
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	barrier();
+	ipipe_check_context(ipipe_root_domain);
+	__ipipe_unstall_root();
+}
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	return __ipipe_test_root() ? bfin_no_irqs : bfin_irq_flags;
+}
+
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags == bfin_no_irqs;
+}
+
+static inline void arch_local_irq_save_ptr(unsigned long *_flags)
+{
+	x = __ipipe_test_and_stall_root() ? bfin_no_irqs : bfin_irq_flags;
+	barrier();
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	ipipe_check_context(ipipe_root_domain);
+	return __hard_local_irq_save();
+}
+
+static inline unsigned long arch_mangle_irq_bits(int virt, unsigned long real)
 {
 	/*
 	 * Merge virtual and real interrupt mask bits into a single
@@ -87,130 +143,79 @@
 	return (real & ~(1 << 31)) | ((virt != 0) << 31);
 }
 
-static inline int raw_demangle_irq_bits(unsigned long *x)
+static inline int arch_demangle_irq_bits(unsigned long *x)
 {
 	int virt = (*x & (1 << 31)) != 0;
 	*x &= ~(1L << 31);
 	return virt;
 }
 
-static inline void local_irq_disable_hw_notrace(void)
-{
-	bfin_cli();
-}
-
-static inline void local_irq_enable_hw_notrace(void)
-{
-	bfin_sti(bfin_irq_flags);
-}
-
-#define local_save_flags_hw(flags)			\
-	do {						\
-		(flags) = bfin_read_IMASK();		\
-	} while (0)
-
-#define irqs_disabled_flags_hw(flags) (((flags) & ~0x3f) == 0)
-
-#define irqs_disabled_hw()			\
-	({					\
-	unsigned long flags;			\
-	local_save_flags_hw(flags);		\
-	irqs_disabled_flags_hw(flags);		\
-	})
-
-static inline void local_irq_save_ptr_hw(unsigned long *flags)
-{
-	*flags = bfin_cli();
-#ifdef CONFIG_DEBUG_HWERR
-	bfin_sti(0x3f);
-#endif
-}
-
-#define local_irq_save_hw_notrace(flags)		\
-	do {						\
-		local_irq_save_ptr_hw(&(flags));	\
-	} while (0)
-
-static inline void local_irq_restore_hw_notrace(unsigned long flags)
-{
-	if (!irqs_disabled_flags_hw(flags))
-		local_irq_enable_hw_notrace();
-}
-
+/*
+ * Interface to various arch routines that may be traced.
+ */
 #ifdef CONFIG_IPIPE_TRACE_IRQSOFF
-# define local_irq_disable_hw()				\
-	do {						\
-		if (!irqs_disabled_hw()) {		\
-			local_irq_disable_hw_notrace();	\
-			ipipe_trace_begin(0x80000000);	\
-		}					\
-	} while (0)
-# define local_irq_enable_hw()				\
-	do {						\
-		if (irqs_disabled_hw()) {		\
-			ipipe_trace_end(0x80000000);	\
-			local_irq_enable_hw_notrace();	\
-		}					\
-	} while (0)
-# define local_irq_save_hw(flags)			\
-	do {						\
-		local_save_flags_hw(flags);		\
-		if (!irqs_disabled_flags_hw(flags)) {	\
-			local_irq_disable_hw_notrace();	\
-			ipipe_trace_begin(0x80000001);	\
-		}					\
-	} while (0)
-# define local_irq_restore_hw(flags)			\
-	do {						\
-		if (!irqs_disabled_flags_hw(flags)) {	\
-			ipipe_trace_end(0x80000001);	\
-			local_irq_enable_hw_notrace();	\
-		}					\
-	} while (0)
+static inline void hard_local_irq_disable(void)
+{
+	if (!hard_irqs_disabled()) {
+		__hard_local_irq_disable();
+		ipipe_trace_begin(0x80000000);
+	}
+}
+
+static inline void hard_local_irq_enable(void)
+{
+	if (hard_irqs_disabled()) {
+		ipipe_trace_end(0x80000000);
+		__hard_local_irq_enable();
+	}
+}
+
+static inline unsigned long hard_local_irq_save(void)
+{
+	unsigned long flags = hard_local_save_flags();
+	if (!hard_irqs_disabled_flags(flags)) {
+		__hard_local_irq_disable();
+		ipipe_trace_begin(0x80000001);
+	}
+	return flags;
+}
+
+static inline void hard_local_irq_restore(unsigned long flags)
+{
+	if (!hard_irqs_disabled_flags(flags)) {
+		ipipe_trace_end(0x80000001);
+		__hard_local_irq_enable();
+	}
+}
+
 #else /* !CONFIG_IPIPE_TRACE_IRQSOFF */
-# define local_irq_disable_hw()		local_irq_disable_hw_notrace()
-# define local_irq_enable_hw()		local_irq_enable_hw_notrace()
-# define local_irq_save_hw(flags)	local_irq_save_hw_notrace(flags)
-# define local_irq_restore_hw(flags)	local_irq_restore_hw_notrace(flags)
+# define hard_local_irq_disable()	__hard_local_irq_disable()
+# define hard_local_irq_enable()	__hard_local_irq_enable()
+# define hard_local_irq_save()		__hard_local_irq_save()
+# define hard_local_irq_restore(flags)	__hard_local_irq_restore(flags)
 #endif /* !CONFIG_IPIPE_TRACE_IRQSOFF */
 
 #else /* CONFIG_IPIPE */
 
-static inline void raw_local_irq_disable(void)
-{
-	bfin_cli();
-}
-static inline void raw_local_irq_enable(void)
-{
-	bfin_sti(bfin_irq_flags);
-}
+/*
+ * Direct interface to linux/irqflags.h.
+ */
+#define arch_local_save_flags()		hard_local_save_flags()
+#define arch_local_irq_save(flags)	__hard_local_irq_save()
+#define arch_local_irq_restore(flags)	__hard_local_irq_restore(flags)
+#define arch_local_irq_enable()		__hard_local_irq_enable()
+#define arch_local_irq_disable()	__hard_local_irq_disable()
+#define arch_irqs_disabled_flags(flags)	hard_irqs_disabled_flags(flags)
+#define arch_irqs_disabled()		hard_irqs_disabled()
 
-#define raw_local_save_flags(flags) do { (flags) = bfin_read_IMASK(); } while (0)
+/*
+ * Interface to various arch routines that may be traced.
+ */
+#define hard_local_irq_save()		__hard_local_irq_save()
+#define hard_local_irq_restore(flags)	__hard_local_irq_restore(flags)
+#define hard_local_irq_enable()		__hard_local_irq_enable()
+#define hard_local_irq_disable()	__hard_local_irq_disable()
 
-#define raw_irqs_disabled_flags(flags) (((flags) & ~0x3f) == 0)
-
-static inline unsigned long __raw_local_irq_save(void)
-{
-	unsigned long flags = bfin_cli();
-#ifdef CONFIG_DEBUG_HWERR
-	bfin_sti(0x3f);
-#endif
-	return flags;
-}
-#define raw_local_irq_save(flags) do { (flags) = __raw_local_irq_save(); } while (0)
-
-#define local_irq_save_hw(flags)	raw_local_irq_save(flags)
-#define local_irq_restore_hw(flags)	raw_local_irq_restore(flags)
-#define local_irq_enable_hw()		raw_local_irq_enable()
-#define local_irq_disable_hw()		raw_local_irq_disable()
-#define irqs_disabled_hw()		irqs_disabled()
 
 #endif /* !CONFIG_IPIPE */
-
-static inline void raw_local_irq_restore(unsigned long flags)
-{
-	if (!raw_irqs_disabled_flags(flags))
-		raw_local_irq_enable();
-}
-
 #endif
diff --git a/arch/blackfin/include/asm/mmu_context.h b/arch/blackfin/include/asm/mmu_context.h
index e1a9b46..3828c70 100644
--- a/arch/blackfin/include/asm/mmu_context.h
+++ b/arch/blackfin/include/asm/mmu_context.h
@@ -97,8 +97,8 @@
 }
 
 #ifdef CONFIG_IPIPE
-#define lock_mm_switch(flags)	local_irq_save_hw_cond(flags)
-#define unlock_mm_switch(flags)	local_irq_restore_hw_cond(flags)
+#define lock_mm_switch(flags)	flags = hard_local_irq_save_cond()
+#define unlock_mm_switch(flags)	hard_local_irq_restore_cond(flags)
 #else
 #define lock_mm_switch(flags)	do { (void)(flags); } while (0)
 #define unlock_mm_switch(flags)	do { (void)(flags); } while (0)
@@ -205,9 +205,9 @@
 }
 
 #define ipipe_mm_switch_protect(flags)		\
-	local_irq_save_hw_cond(flags)
+	flags = hard_local_irq_save_cond()
 
 #define ipipe_mm_switch_unprotect(flags)	\
-	local_irq_restore_hw_cond(flags)
+	hard_local_irq_restore_cond(flags)
 
 #endif
diff --git a/arch/blackfin/include/asm/system.h b/arch/blackfin/include/asm/system.h
index dde19b1..19e2c7c 100644
--- a/arch/blackfin/include/asm/system.h
+++ b/arch/blackfin/include/asm/system.h
@@ -117,7 +117,7 @@
 	unsigned long tmp = 0;
 	unsigned long flags;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	switch (size) {
 	case 1:
@@ -139,7 +139,7 @@
 			 : "=&d" (tmp) : "d" (x), "m" (*__xg(ptr)) : "memory");
 		break;
 	}
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 	return tmp;
 }
 
diff --git a/arch/blackfin/kernel/bfin_gpio.c b/arch/blackfin/kernel/bfin_gpio.c
index dc07ed0..ca1c1f9 100644
--- a/arch/blackfin/kernel/bfin_gpio.c
+++ b/arch/blackfin/kernel/bfin_gpio.c
@@ -349,13 +349,13 @@
 void set_gpio_ ## name(unsigned gpio, unsigned short arg) \
 { \
 	unsigned long flags; \
-	local_irq_save_hw(flags); \
+	flags = hard_local_irq_save(); \
 	if (arg) \
 		gpio_array[gpio_bank(gpio)]->name |= gpio_bit(gpio); \
 	else \
 		gpio_array[gpio_bank(gpio)]->name &= ~gpio_bit(gpio); \
 	AWA_DUMMY_READ(name); \
-	local_irq_restore_hw(flags); \
+	hard_local_irq_restore(flags); \
 } \
 EXPORT_SYMBOL(set_gpio_ ## name);
 
@@ -371,14 +371,14 @@
 { \
 	unsigned long flags; \
 	if (ANOMALY_05000311 || ANOMALY_05000323) \
-		local_irq_save_hw(flags); \
+		flags = hard_local_irq_save(); \
 	if (arg) \
 		gpio_array[gpio_bank(gpio)]->name ## _set = gpio_bit(gpio); \
 	else \
 		gpio_array[gpio_bank(gpio)]->name ## _clear = gpio_bit(gpio); \
 	if (ANOMALY_05000311 || ANOMALY_05000323) { \
 		AWA_DUMMY_READ(name); \
-		local_irq_restore_hw(flags); \
+		hard_local_irq_restore(flags); \
 	} \
 } \
 EXPORT_SYMBOL(set_gpio_ ## name);
@@ -391,11 +391,11 @@
 {
 	unsigned long flags;
 	if (ANOMALY_05000311 || ANOMALY_05000323)
-		local_irq_save_hw(flags);
+		flags = hard_local_irq_save();
 	gpio_array[gpio_bank(gpio)]->toggle = gpio_bit(gpio);
 	if (ANOMALY_05000311 || ANOMALY_05000323) {
 		AWA_DUMMY_READ(toggle);
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 	}
 }
 EXPORT_SYMBOL(set_gpio_toggle);
@@ -408,11 +408,11 @@
 { \
 	unsigned long flags; \
 	if (ANOMALY_05000311 || ANOMALY_05000323) \
-		local_irq_save_hw(flags); \
+		flags = hard_local_irq_save(); \
 	gpio_array[gpio_bank(gpio)]->name = arg; \
 	if (ANOMALY_05000311 || ANOMALY_05000323) { \
 		AWA_DUMMY_READ(name); \
-		local_irq_restore_hw(flags); \
+		hard_local_irq_restore(flags); \
 	} \
 } \
 EXPORT_SYMBOL(set_gpiop_ ## name);
@@ -433,11 +433,11 @@
 	unsigned long flags; \
 	unsigned short ret; \
 	if (ANOMALY_05000311 || ANOMALY_05000323) \
-		local_irq_save_hw(flags); \
+		flags = hard_local_irq_save(); \
 	ret = 0x01 & (gpio_array[gpio_bank(gpio)]->name >> gpio_sub_n(gpio)); \
 	if (ANOMALY_05000311 || ANOMALY_05000323) { \
 		AWA_DUMMY_READ(name); \
-		local_irq_restore_hw(flags); \
+		hard_local_irq_restore(flags); \
 	} \
 	return ret; \
 } \
@@ -460,11 +460,11 @@
 	unsigned long flags; \
 	unsigned short ret; \
 	if (ANOMALY_05000311 || ANOMALY_05000323) \
-		local_irq_save_hw(flags); \
+		flags = hard_local_irq_save(); \
 	ret = (gpio_array[gpio_bank(gpio)]->name); \
 	if (ANOMALY_05000311 || ANOMALY_05000323) { \
 		AWA_DUMMY_READ(name); \
-		local_irq_restore_hw(flags); \
+		hard_local_irq_restore(flags); \
 	} \
 	return ret; \
 } \
@@ -525,14 +525,14 @@
 	if (check_gpio(gpio) < 0)
 		return -EINVAL;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	if (ctrl)
 		reserve(wakeup, gpio);
 	else
 		unreserve(wakeup, gpio);
 
 	set_gpio_maskb(gpio, ctrl);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	return 0;
 }
@@ -690,7 +690,7 @@
 
 	BUG_ON(ident >= MAX_RESOURCES);
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	/* If a pin can be muxed as either GPIO or peripheral, make
 	 * sure it is not already a GPIO pin when we request it.
@@ -701,7 +701,7 @@
 		printk(KERN_ERR
 		       "%s: Peripheral %d is already reserved as GPIO by %s !\n",
 		       __func__, ident, get_label(ident));
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return -EBUSY;
 	}
 
@@ -730,7 +730,7 @@
 			printk(KERN_ERR
 			       "%s: Peripheral %d function %d is already reserved by %s !\n",
 			       __func__, ident, P_FUNCT2MUX(per), get_label(ident));
-			local_irq_restore_hw(flags);
+			hard_local_irq_restore(flags);
 			return -EBUSY;
 		}
 	}
@@ -741,7 +741,7 @@
 	portmux_setup(per);
 	port_setup(ident, PERIPHERAL_USAGE);
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 	set_label(ident, label);
 
 	return 0;
@@ -780,10 +780,10 @@
 	if (!(per & P_DEFINED))
 		return;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	if (unlikely(!is_reserved(peri, ident, 0))) {
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return;
 	}
 
@@ -794,7 +794,7 @@
 
 	set_label(ident, "free");
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 EXPORT_SYMBOL(peripheral_free);
 
@@ -828,7 +828,7 @@
 	if (check_gpio(gpio) < 0)
 		return -EINVAL;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	/*
 	 * Allow that the identical GPIO can
@@ -837,7 +837,7 @@
 	 */
 
 	if (cmp_label(gpio, label) == 0) {
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return 0;
 	}
 
@@ -846,7 +846,7 @@
 			dump_stack();
 		printk(KERN_ERR "bfin-gpio: GPIO %d is already reserved by %s !\n",
 		       gpio, get_label(gpio));
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return -EBUSY;
 	}
 	if (unlikely(is_reserved(peri, gpio, 1))) {
@@ -855,7 +855,7 @@
 		printk(KERN_ERR
 		       "bfin-gpio: GPIO %d is already reserved as Peripheral by %s !\n",
 		       gpio, get_label(gpio));
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return -EBUSY;
 	}
 	if (unlikely(is_reserved(gpio_irq, gpio, 1))) {
@@ -871,7 +871,7 @@
 	reserve(gpio, gpio);
 	set_label(gpio, label);
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	port_setup(gpio, GPIO_USAGE);
 
@@ -888,13 +888,13 @@
 
 	might_sleep();
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	if (unlikely(!is_reserved(gpio, gpio, 0))) {
 		if (system_state == SYSTEM_BOOTING)
 			dump_stack();
 		gpio_error(gpio);
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return;
 	}
 
@@ -902,7 +902,7 @@
 
 	set_label(gpio, "free");
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 EXPORT_SYMBOL(bfin_gpio_free);
 
@@ -913,7 +913,7 @@
 {
 	unsigned long flags;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	/*
 	 * Allow that the identical GPIO can
@@ -922,19 +922,19 @@
 	 */
 
 	if (cmp_label(gpio, label) == 0) {
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return 0;
 	}
 
 	if (unlikely(is_reserved(special_gpio, gpio, 1))) {
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		printk(KERN_ERR "bfin-gpio: GPIO %d is already reserved by %s !\n",
 		       gpio, get_label(gpio));
 
 		return -EBUSY;
 	}
 	if (unlikely(is_reserved(peri, gpio, 1))) {
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		printk(KERN_ERR
 		       "bfin-gpio: GPIO %d is already reserved as Peripheral by %s !\n",
 		       gpio, get_label(gpio));
@@ -946,7 +946,7 @@
 	reserve(peri, gpio);
 
 	set_label(gpio, label);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 	port_setup(gpio, GPIO_USAGE);
 
 	return 0;
@@ -959,18 +959,18 @@
 
 	might_sleep();
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	if (unlikely(!is_reserved(special_gpio, gpio, 0))) {
 		gpio_error(gpio);
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return;
 	}
 
 	unreserve(special_gpio, gpio);
 	unreserve(peri, gpio);
 	set_label(gpio, "free");
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 EXPORT_SYMBOL(bfin_special_gpio_free);
 #endif
@@ -983,7 +983,7 @@
 	if (check_gpio(gpio) < 0)
 		return -EINVAL;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	if (unlikely(is_reserved(peri, gpio, 1))) {
 		if (system_state == SYSTEM_BOOTING)
@@ -991,7 +991,7 @@
 		printk(KERN_ERR
 		       "bfin-gpio: GPIO %d is already reserved as Peripheral by %s !\n",
 		       gpio, get_label(gpio));
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return -EBUSY;
 	}
 	if (unlikely(is_reserved(gpio, gpio, 1)))
@@ -1002,7 +1002,7 @@
 	reserve(gpio_irq, gpio);
 	set_label(gpio, label);
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	port_setup(gpio, GPIO_USAGE);
 
@@ -1016,13 +1016,13 @@
 	if (check_gpio(gpio) < 0)
 		return;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	if (unlikely(!is_reserved(gpio_irq, gpio, 0))) {
 		if (system_state == SYSTEM_BOOTING)
 			dump_stack();
 		gpio_error(gpio);
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return;
 	}
 
@@ -1030,7 +1030,7 @@
 
 	set_label(gpio, "free");
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 
 static inline void __bfin_gpio_direction_input(unsigned gpio)
@@ -1052,10 +1052,10 @@
 		return -EINVAL;
 	}
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	__bfin_gpio_direction_input(gpio);
 	AWA_DUMMY_READ(inen);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	return 0;
 }
@@ -1070,9 +1070,9 @@
 	port_setup(gpio, GPIO_USAGE);
 
 #ifdef CONFIG_BF54x
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	__bfin_gpio_direction_input(gpio);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 #endif
 }
 
@@ -1094,7 +1094,7 @@
 		return -EINVAL;
 	}
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	gpio_array[gpio_bank(gpio)]->inen &= ~gpio_bit(gpio);
 	gpio_set_value(gpio, value);
@@ -1105,7 +1105,7 @@
 #endif
 
 	AWA_DUMMY_READ(dir);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	return 0;
 }
@@ -1120,11 +1120,11 @@
 
 	if (unlikely(get_gpio_edge(gpio))) {
 		int ret;
-		local_irq_save_hw(flags);
+		flags = hard_local_irq_save();
 		set_gpio_edge(gpio, 0);
 		ret = get_gpio_data(gpio);
 		set_gpio_edge(gpio, 1);
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return ret;
 	} else
 		return get_gpio_data(gpio);
diff --git a/arch/blackfin/kernel/cplb-mpu/cplbmgr.c b/arch/blackfin/kernel/cplb-mpu/cplbmgr.c
index 87b25b1..8de9229 100644
--- a/arch/blackfin/kernel/cplb-mpu/cplbmgr.c
+++ b/arch/blackfin/kernel/cplb-mpu/cplbmgr.c
@@ -318,7 +318,7 @@
 
 	nr_cplb_flush[cpu]++;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	_disable_icplb();
 	for (i = first_switched_icplb; i < MAX_CPLBS; i++) {
 		icplb_tbl[cpu][i].data = 0;
@@ -332,7 +332,7 @@
 		bfin_write32(DCPLB_DATA0 + i * 4, 0);
 	}
 	_enable_dcplb();
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 }
 
@@ -348,7 +348,7 @@
 		return;
 	}
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	current_rwx_mask[cpu] = masks;
 
 	if (L2_LENGTH && addr >= L2_START && addr < L2_START + L2_LENGTH) {
@@ -373,5 +373,5 @@
 		addr += PAGE_SIZE;
 	}
 	_enable_dcplb();
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
diff --git a/arch/blackfin/kernel/ipipe.c b/arch/blackfin/kernel/ipipe.c
index 1a496cd..3b1da4a 100644
--- a/arch/blackfin/kernel/ipipe.c
+++ b/arch/blackfin/kernel/ipipe.c
@@ -219,10 +219,10 @@
 
 	ret = __ipipe_dispatch_event(IPIPE_EVENT_SYSCALL, regs);
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	if (!__ipipe_root_domain_p) {
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		return 1;
 	}
 
@@ -230,7 +230,7 @@
 	if ((p->irqpend_himask & IPIPE_IRQMASK_VIRT) != 0)
 		__ipipe_sync_pipeline(IPIPE_IRQMASK_VIRT);
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	return -ret;
 }
@@ -239,14 +239,14 @@
 {
 	unsigned long flags;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	return flags;
 }
 
 void ipipe_critical_exit(unsigned long flags)
 {
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 
 static void __ipipe_no_irqtail(void)
@@ -279,9 +279,9 @@
 		return -EINVAL;
 #endif
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	__ipipe_handle_irq(irq, NULL);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	return 1;
 }
@@ -293,7 +293,7 @@
 
 	BUG_ON(irqs_disabled());
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	if (irq_tail_hook)
 		irq_tail_hook();
@@ -303,7 +303,7 @@
 	if (ipipe_root_cpudom_var(irqpend_himask) != 0)
 		__ipipe_sync_pipeline(IPIPE_IRQMASK_ANY);
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 
 void ___ipipe_sync_pipeline(unsigned long syncmask)
@@ -344,10 +344,10 @@
 {
 	unsigned long *p, flags;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	p = &__ipipe_root_status;
 	__set_bit(IPIPE_STALL_FLAG, p);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__ipipe_stall_root);
 
@@ -356,10 +356,10 @@
 	unsigned long *p, flags;
 	int x;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	p = &__ipipe_root_status;
 	x = __test_and_set_bit(IPIPE_STALL_FLAG, p);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	return x;
 }
@@ -371,10 +371,10 @@
 	unsigned long flags;
 	int x;
 
-	local_irq_save_hw_smp(flags);
+	flags = hard_local_irq_save_smp();
 	p = &__ipipe_root_status;
 	x = test_bit(IPIPE_STALL_FLAG, p);
-	local_irq_restore_hw_smp(flags);
+	hard_local_irq_restore_smp(flags);
 
 	return x;
 }
@@ -384,10 +384,10 @@
 {
 	unsigned long *p, flags;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	p = &__ipipe_root_status;
 	__set_bit(IPIPE_SYNCDEFER_FLAG, p);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__ipipe_lock_root);
 
@@ -395,9 +395,9 @@
 {
 	unsigned long *p, flags;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	p = &__ipipe_root_status;
 	__clear_bit(IPIPE_SYNCDEFER_FLAG, p);
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__ipipe_unlock_root);
diff --git a/arch/blackfin/kernel/kgdb_test.c b/arch/blackfin/kernel/kgdb_test.c
index 9a4b075..08c0236 100644
--- a/arch/blackfin/kernel/kgdb_test.c
+++ b/arch/blackfin/kernel/kgdb_test.c
@@ -88,6 +88,7 @@
 	.owner = THIS_MODULE,
 	.read  = kgdb_test_proc_read,
 	.write = kgdb_test_proc_write,
+	.llseek = noop_llseek,
 };
 
 static int __init kgdbtest_init(void)
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 01f98cb..c86a3ed 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -65,11 +65,11 @@
 #ifdef CONFIG_IPIPE
 	ipipe_suspend_domain();
 #endif
-	local_irq_disable_hw();
+	hard_local_irq_disable();
 	if (!need_resched())
 		idle_with_irq_disabled();
 
-	local_irq_enable_hw();
+	hard_local_irq_enable();
 }
 
 /*
diff --git a/arch/blackfin/kernel/trace.c b/arch/blackfin/kernel/trace.c
index 59fcdf6..05b5508 100644
--- a/arch/blackfin/kernel/trace.c
+++ b/arch/blackfin/kernel/trace.c
@@ -15,6 +15,7 @@
 #include <linux/kallsyms.h>
 #include <linux/err.h>
 #include <linux/fs.h>
+#include <linux/irq.h>
 #include <asm/dma.h>
 #include <asm/trace.h>
 #include <asm/fixed_code.h>
diff --git a/arch/blackfin/mach-bf518/include/mach/cdefBF51x_base.h b/arch/blackfin/mach-bf518/include/mach/cdefBF51x_base.h
index e548e9d..29498e5 100644
--- a/arch/blackfin/mach-bf518/include/mach/cdefBF51x_base.h
+++ b/arch/blackfin/mach-bf518/include/mach/cdefBF51x_base.h
@@ -1058,54 +1058,4 @@
 /* These need to be last due to the cdef/linux inter-dependencies */
 #include <asm/irq.h>
 
-/* Writing to PLL_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_PLL_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1;
-
-	if (val == bfin_read_PLL_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SIC_IWR0);
-	iwr1 = bfin_read32(SIC_IWR1);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
-	bfin_write32(SIC_IWR1, 0);
-
-	bfin_write16(PLL_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR0, iwr0);
-	bfin_write32(SIC_IWR1, iwr1);
-	local_irq_restore_hw(flags);
-}
-
-/* Writing to VR_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_VR_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1;
-
-	if (val == bfin_read_VR_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SIC_IWR0);
-	iwr1 = bfin_read32(SIC_IWR1);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
-	bfin_write32(SIC_IWR1, 0);
-
-	bfin_write16(VR_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR0, iwr0);
-	bfin_write32(SIC_IWR1, iwr1);
-	local_irq_restore_hw(flags);
-}
-
 #endif /* _CDEF_BF52X_H */
diff --git a/arch/blackfin/mach-bf518/include/mach/pll.h b/arch/blackfin/mach-bf518/include/mach/pll.h
new file mode 100644
index 0000000..d550298
--- /dev/null
+++ b/arch/blackfin/mach-bf518/include/mach/pll.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright 2008 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later
+ */
+
+#ifndef _MACH_PLL_H
+#define _MACH_PLL_H
+
+#include <asm/blackfin.h>
+#include <asm/irqflags.h>
+
+/* Writing to PLL_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_PLL_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1;
+
+	if (val == bfin_read_PLL_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SIC_IWR0);
+	iwr1 = bfin_read32(SIC_IWR1);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
+	bfin_write32(SIC_IWR1, 0);
+
+	bfin_write16(PLL_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR0, iwr0);
+	bfin_write32(SIC_IWR1, iwr1);
+	hard_local_irq_restore(flags);
+}
+
+/* Writing to VR_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_VR_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1;
+
+	if (val == bfin_read_VR_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SIC_IWR0);
+	iwr1 = bfin_read32(SIC_IWR1);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
+	bfin_write32(SIC_IWR1, 0);
+
+	bfin_write16(VR_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR0, iwr0);
+	bfin_write32(SIC_IWR1, iwr1);
+	hard_local_irq_restore(flags);
+}
+
+#endif /* _MACH_PLL_H */
diff --git a/arch/blackfin/mach-bf527/include/mach/cdefBF52x_base.h b/arch/blackfin/mach-bf527/include/mach/cdefBF52x_base.h
index 12f2ad4..11fb27b 100644
--- a/arch/blackfin/mach-bf527/include/mach/cdefBF52x_base.h
+++ b/arch/blackfin/mach-bf527/include/mach/cdefBF52x_base.h
@@ -1110,54 +1110,4 @@
 /* These need to be last due to the cdef/linux inter-dependencies */
 #include <asm/irq.h>
 
-/* Writing to PLL_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_PLL_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1;
-
-	if (val == bfin_read_PLL_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SIC_IWR0);
-	iwr1 = bfin_read32(SIC_IWR1);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
-	bfin_write32(SIC_IWR1, 0);
-
-	bfin_write16(PLL_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR0, iwr0);
-	bfin_write32(SIC_IWR1, iwr1);
-	local_irq_restore_hw(flags);
-}
-
-/* Writing to VR_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_VR_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1;
-
-	if (val == bfin_read_VR_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SIC_IWR0);
-	iwr1 = bfin_read32(SIC_IWR1);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
-	bfin_write32(SIC_IWR1, 0);
-
-	bfin_write16(VR_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR0, iwr0);
-	bfin_write32(SIC_IWR1, iwr1);
-	local_irq_restore_hw(flags);
-}
-
 #endif /* _CDEF_BF52X_H */
diff --git a/arch/blackfin/mach-bf527/include/mach/pll.h b/arch/blackfin/mach-bf527/include/mach/pll.h
new file mode 100644
index 0000000..24f1d7c
--- /dev/null
+++ b/arch/blackfin/mach-bf527/include/mach/pll.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright 2007-2008 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later
+ */
+
+#ifndef _MACH_PLL_H
+#define _MACH_PLL_H
+
+#include <asm/blackfin.h>
+#include <asm/irqflags.h>
+
+/* Writing to PLL_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_PLL_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1;
+
+	if (val == bfin_read_PLL_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SIC_IWR0);
+	iwr1 = bfin_read32(SIC_IWR1);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
+	bfin_write32(SIC_IWR1, 0);
+
+	bfin_write16(PLL_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR0, iwr0);
+	bfin_write32(SIC_IWR1, iwr1);
+	hard_local_irq_restore(flags);
+}
+
+/* Writing to VR_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_VR_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1;
+
+	if (val == bfin_read_VR_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SIC_IWR0);
+	iwr1 = bfin_read32(SIC_IWR1);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
+	bfin_write32(SIC_IWR1, 0);
+
+	bfin_write16(VR_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR0, iwr0);
+	bfin_write32(SIC_IWR1, iwr1);
+	hard_local_irq_restore(flags);
+}
+
+#endif /* _MACH_PLL_H */
diff --git a/arch/blackfin/mach-bf533/boards/blackstamp.c b/arch/blackfin/mach-bf533/boards/blackstamp.c
index 842b4fa..84a06f6 100644
--- a/arch/blackfin/mach-bf533/boards/blackstamp.c
+++ b/arch/blackfin/mach-bf533/boards/blackstamp.c
@@ -25,6 +25,7 @@
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
 #include <asm/dpmc.h>
+#include <mach/fio_flag.h>
 
 /*
  * Name the Board for the /proc/cpuinfo
diff --git a/arch/blackfin/mach-bf533/boards/ip0x.c b/arch/blackfin/mach-bf533/boards/ip0x.c
index 7349970..b8474ca 100644
--- a/arch/blackfin/mach-bf533/boards/ip0x.c
+++ b/arch/blackfin/mach-bf533/boards/ip0x.c
@@ -22,6 +22,7 @@
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
+#include <mach/fio_flag.h>
 
 /*
  * Name the Board for the /proc/cpuinfo
diff --git a/arch/blackfin/mach-bf533/boards/stamp.c b/arch/blackfin/mach-bf533/boards/stamp.c
index c457eaa..29c219e 100644
--- a/arch/blackfin/mach-bf533/boards/stamp.c
+++ b/arch/blackfin/mach-bf533/boards/stamp.c
@@ -24,6 +24,7 @@
 #include <asm/reboot.h>
 #include <asm/portmux.h>
 #include <asm/dpmc.h>
+#include <mach/fio_flag.h>
 
 /*
  * Name the Board for the /proc/cpuinfo
diff --git a/arch/blackfin/mach-bf533/include/mach/cdefBF532.h b/arch/blackfin/mach-bf533/include/mach/cdefBF532.h
index feb2392..401e524 100644
--- a/arch/blackfin/mach-bf533/include/mach/cdefBF532.h
+++ b/arch/blackfin/mach-bf533/include/mach/cdefBF532.h
@@ -7,11 +7,6 @@
 #ifndef _CDEF_BF532_H
 #define _CDEF_BF532_H
 
-#include <asm/blackfin.h>
-
-/*include all Core registers and bit definitions*/
-#include "defBF532.h"
-
 /*include core specific register pointer definitions*/
 #include <asm/cdef_LPBlackfin.h>
 
@@ -655,90 +650,4 @@
 /* These need to be last due to the cdef/linux inter-dependencies */
 #include <asm/irq.h>
 
-#if ANOMALY_05000311
-#define BFIN_WRITE_FIO_FLAG(name) \
-static inline void bfin_write_FIO_FLAG_##name(unsigned short val) \
-{ \
-	unsigned long flags; \
-	local_irq_save_hw(flags); \
-	bfin_write16(FIO_FLAG_##name, val); \
-	bfin_read_CHIPID(); \
-	local_irq_restore_hw(flags); \
-}
-BFIN_WRITE_FIO_FLAG(D)
-BFIN_WRITE_FIO_FLAG(C)
-BFIN_WRITE_FIO_FLAG(S)
-BFIN_WRITE_FIO_FLAG(T)
-
-#define BFIN_READ_FIO_FLAG(name) \
-static inline u16 bfin_read_FIO_FLAG_##name(void) \
-{ \
-	unsigned long flags; \
-	u16 ret; \
-	local_irq_save_hw(flags); \
-	ret = bfin_read16(FIO_FLAG_##name); \
-	bfin_read_CHIPID(); \
-	local_irq_restore_hw(flags); \
-	return ret; \
-}
-BFIN_READ_FIO_FLAG(D)
-BFIN_READ_FIO_FLAG(C)
-BFIN_READ_FIO_FLAG(S)
-BFIN_READ_FIO_FLAG(T)
-
-#else
-#define bfin_write_FIO_FLAG_D(val)           bfin_write16(FIO_FLAG_D, val)
-#define bfin_write_FIO_FLAG_C(val)           bfin_write16(FIO_FLAG_C, val)
-#define bfin_write_FIO_FLAG_S(val)           bfin_write16(FIO_FLAG_S, val)
-#define bfin_write_FIO_FLAG_T(val)           bfin_write16(FIO_FLAG_T, val)
-#define bfin_read_FIO_FLAG_T()               bfin_read16(FIO_FLAG_T)
-#define bfin_read_FIO_FLAG_C()               bfin_read16(FIO_FLAG_C)
-#define bfin_read_FIO_FLAG_S()               bfin_read16(FIO_FLAG_S)
-#define bfin_read_FIO_FLAG_D()               bfin_read16(FIO_FLAG_D)
-#endif
-
-/* Writing to PLL_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_PLL_CTL(unsigned int val)
-{
-	unsigned long flags, iwr;
-
-	if (val == bfin_read_PLL_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr = bfin_read32(SIC_IWR);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR, IWR_ENABLE(0));
-
-	bfin_write16(PLL_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR, iwr);
-	local_irq_restore_hw(flags);
-}
-
-/* Writing to VR_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_VR_CTL(unsigned int val)
-{
-	unsigned long flags, iwr;
-
-	if (val == bfin_read_VR_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr = bfin_read32(SIC_IWR);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR, IWR_ENABLE(0));
-
-	bfin_write16(VR_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR, iwr);
-	local_irq_restore_hw(flags);
-}
-
 #endif				/* _CDEF_BF532_H */
diff --git a/arch/blackfin/mach-bf533/include/mach/fio_flag.h b/arch/blackfin/mach-bf533/include/mach/fio_flag.h
new file mode 100644
index 0000000..d0bfba0
--- /dev/null
+++ b/arch/blackfin/mach-bf533/include/mach/fio_flag.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2005-2008 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later
+ */
+
+#ifndef _MACH_FIO_FLAG_H
+#define _MACH_FIO_FLAG_H
+
+#include <asm/blackfin.h>
+#include <asm/irqflags.h>
+
+#if ANOMALY_05000311
+#define BFIN_WRITE_FIO_FLAG(name) \
+static inline void bfin_write_FIO_FLAG_##name(unsigned short val) \
+{ \
+	unsigned long flags; \
+	flags = hard_local_irq_save(); \
+	bfin_write16(FIO_FLAG_##name, val); \
+	bfin_read_CHIPID(); \
+	hard_local_irq_restore(flags); \
+}
+BFIN_WRITE_FIO_FLAG(D)
+BFIN_WRITE_FIO_FLAG(C)
+BFIN_WRITE_FIO_FLAG(S)
+BFIN_WRITE_FIO_FLAG(T)
+
+#define BFIN_READ_FIO_FLAG(name) \
+static inline u16 bfin_read_FIO_FLAG_##name(void) \
+{ \
+	unsigned long flags; \
+	u16 ret; \
+	flags = hard_local_irq_save(); \
+	ret = bfin_read16(FIO_FLAG_##name); \
+	bfin_read_CHIPID(); \
+	hard_local_irq_restore(flags); \
+	return ret; \
+}
+BFIN_READ_FIO_FLAG(D)
+BFIN_READ_FIO_FLAG(C)
+BFIN_READ_FIO_FLAG(S)
+BFIN_READ_FIO_FLAG(T)
+
+#else
+#define bfin_write_FIO_FLAG_D(val)           bfin_write16(FIO_FLAG_D, val)
+#define bfin_write_FIO_FLAG_C(val)           bfin_write16(FIO_FLAG_C, val)
+#define bfin_write_FIO_FLAG_S(val)           bfin_write16(FIO_FLAG_S, val)
+#define bfin_write_FIO_FLAG_T(val)           bfin_write16(FIO_FLAG_T, val)
+#define bfin_read_FIO_FLAG_T()               bfin_read16(FIO_FLAG_T)
+#define bfin_read_FIO_FLAG_C()               bfin_read16(FIO_FLAG_C)
+#define bfin_read_FIO_FLAG_S()               bfin_read16(FIO_FLAG_S)
+#define bfin_read_FIO_FLAG_D()               bfin_read16(FIO_FLAG_D)
+#endif
+
+#endif /* _MACH_FIO_FLAG_H */
diff --git a/arch/blackfin/mach-bf533/include/mach/pll.h b/arch/blackfin/mach-bf533/include/mach/pll.h
new file mode 100644
index 0000000..169c106
--- /dev/null
+++ b/arch/blackfin/mach-bf533/include/mach/pll.h
@@ -0,0 +1,57 @@
+/*
+ * Copyright 2005-2008 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later
+ */
+
+#ifndef _MACH_PLL_H
+#define _MACH_PLL_H
+
+#include <asm/blackfin.h>
+#include <asm/irqflags.h>
+
+/* Writing to PLL_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_PLL_CTL(unsigned int val)
+{
+	unsigned long flags, iwr;
+
+	if (val == bfin_read_PLL_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr = bfin_read32(SIC_IWR);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR, IWR_ENABLE(0));
+
+	bfin_write16(PLL_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR, iwr);
+	hard_local_irq_restore(flags);
+}
+
+/* Writing to VR_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_VR_CTL(unsigned int val)
+{
+	unsigned long flags, iwr;
+
+	if (val == bfin_read_VR_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr = bfin_read32(SIC_IWR);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR, IWR_ENABLE(0));
+
+	bfin_write16(VR_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR, iwr);
+	hard_local_irq_restore(flags);
+}
+
+#endif /* _MACH_PLL_H */
diff --git a/arch/blackfin/mach-bf537/include/mach/cdefBF534.h b/arch/blackfin/mach-bf537/include/mach/cdefBF534.h
index 91825c9..fbeb35e 100644
--- a/arch/blackfin/mach-bf537/include/mach/cdefBF534.h
+++ b/arch/blackfin/mach-bf537/include/mach/cdefBF534.h
@@ -1750,48 +1750,4 @@
 /* These need to be last due to the cdef/linux inter-dependencies */
 #include <asm/irq.h>
 
-/* Writing to PLL_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_PLL_CTL(unsigned int val)
-{
-	unsigned long flags, iwr;
-
-	if (val == bfin_read_PLL_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr = bfin_read32(SIC_IWR);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR, IWR_ENABLE(0));
-
-	bfin_write16(PLL_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR, iwr);
-	local_irq_restore_hw(flags);
-}
-
-/* Writing to VR_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_VR_CTL(unsigned int val)
-{
-	unsigned long flags, iwr;
-
-	if (val == bfin_read_VR_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr = bfin_read32(SIC_IWR);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR, IWR_ENABLE(0));
-
-	bfin_write16(VR_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR, iwr);
-	local_irq_restore_hw(flags);
-}
-
 #endif				/* _CDEF_BF534_H */
diff --git a/arch/blackfin/mach-bf537/include/mach/pll.h b/arch/blackfin/mach-bf537/include/mach/pll.h
new file mode 100644
index 0000000..169c106
--- /dev/null
+++ b/arch/blackfin/mach-bf537/include/mach/pll.h
@@ -0,0 +1,57 @@
+/*
+ * Copyright 2005-2008 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later
+ */
+
+#ifndef _MACH_PLL_H
+#define _MACH_PLL_H
+
+#include <asm/blackfin.h>
+#include <asm/irqflags.h>
+
+/* Writing to PLL_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_PLL_CTL(unsigned int val)
+{
+	unsigned long flags, iwr;
+
+	if (val == bfin_read_PLL_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr = bfin_read32(SIC_IWR);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR, IWR_ENABLE(0));
+
+	bfin_write16(PLL_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR, iwr);
+	hard_local_irq_restore(flags);
+}
+
+/* Writing to VR_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_VR_CTL(unsigned int val)
+{
+	unsigned long flags, iwr;
+
+	if (val == bfin_read_VR_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr = bfin_read32(SIC_IWR);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR, IWR_ENABLE(0));
+
+	bfin_write16(VR_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR, iwr);
+	hard_local_irq_restore(flags);
+}
+
+#endif /* _MACH_PLL_H */
diff --git a/arch/blackfin/mach-bf538/include/mach/cdefBF538.h b/arch/blackfin/mach-bf538/include/mach/cdefBF538.h
index 66aa722..085b06b 100644
--- a/arch/blackfin/mach-bf538/include/mach/cdefBF538.h
+++ b/arch/blackfin/mach-bf538/include/mach/cdefBF538.h
@@ -2027,54 +2027,4 @@
 /* These need to be last due to the cdef/linux inter-dependencies */
 #include <asm/irq.h>
 
-/* Writing to PLL_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_PLL_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1;
-
-	if (val == bfin_read_PLL_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SIC_IWR0);
-	iwr1 = bfin_read32(SIC_IWR1);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
-	bfin_write32(SIC_IWR1, 0);
-
-	bfin_write16(PLL_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR0, iwr0);
-	bfin_write32(SIC_IWR1, iwr1);
-	local_irq_restore_hw(flags);
-}
-
-/* Writing to VR_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_VR_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1;
-
-	if (val == bfin_read_VR_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SIC_IWR0);
-	iwr1 = bfin_read32(SIC_IWR1);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
-	bfin_write32(SIC_IWR1, 0);
-
-	bfin_write16(VR_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR0, iwr0);
-	bfin_write32(SIC_IWR1, iwr1);
-	local_irq_restore_hw(flags);
-}
-
 #endif
diff --git a/arch/blackfin/mach-bf538/include/mach/pll.h b/arch/blackfin/mach-bf538/include/mach/pll.h
new file mode 100644
index 0000000..b30bbcd
--- /dev/null
+++ b/arch/blackfin/mach-bf538/include/mach/pll.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright 2008-2009 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef _MACH_PLL_H
+#define _MACH_PLL_H
+
+#include <asm/blackfin.h>
+#include <asm/irqflags.h>
+
+/* Writing to PLL_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_PLL_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1;
+
+	if (val == bfin_read_PLL_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SIC_IWR0);
+	iwr1 = bfin_read32(SIC_IWR1);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
+	bfin_write32(SIC_IWR1, 0);
+
+	bfin_write16(PLL_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR0, iwr0);
+	bfin_write32(SIC_IWR1, iwr1);
+	hard_local_irq_restore(flags);
+}
+
+/* Writing to VR_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_VR_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1;
+
+	if (val == bfin_read_VR_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SIC_IWR0);
+	iwr1 = bfin_read32(SIC_IWR1);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
+	bfin_write32(SIC_IWR1, 0);
+
+	bfin_write16(VR_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR0, iwr0);
+	bfin_write32(SIC_IWR1, iwr1);
+	hard_local_irq_restore(flags);
+}
+
+#endif /* _MACH_PLL_H */
diff --git a/arch/blackfin/mach-bf548/include/mach/cdefBF54x_base.h b/arch/blackfin/mach-bf548/include/mach/cdefBF54x_base.h
index ea3ec4e..0c16067d 100644
--- a/arch/blackfin/mach-bf548/include/mach/cdefBF54x_base.h
+++ b/arch/blackfin/mach-bf548/include/mach/cdefBF54x_base.h
@@ -2648,61 +2648,5 @@
 /* These need to be last due to the cdef/linux inter-dependencies */
 #include <asm/irq.h>
 
-/* Writing to PLL_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_PLL_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1, iwr2;
-
-	if (val == bfin_read_PLL_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SIC_IWR0);
-	iwr1 = bfin_read32(SIC_IWR1);
-	iwr2 = bfin_read32(SIC_IWR2);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
-	bfin_write32(SIC_IWR1, 0);
-	bfin_write32(SIC_IWR2, 0);
-
-	bfin_write16(PLL_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR0, iwr0);
-	bfin_write32(SIC_IWR1, iwr1);
-	bfin_write32(SIC_IWR2, iwr2);
-	local_irq_restore_hw(flags);
-}
-
-/* Writing to VR_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_VR_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1, iwr2;
-
-	if (val == bfin_read_VR_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SIC_IWR0);
-	iwr1 = bfin_read32(SIC_IWR1);
-	iwr2 = bfin_read32(SIC_IWR2);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
-	bfin_write32(SIC_IWR1, 0);
-	bfin_write32(SIC_IWR2, 0);
-
-	bfin_write16(VR_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SIC_IWR0, iwr0);
-	bfin_write32(SIC_IWR1, iwr1);
-	bfin_write32(SIC_IWR2, iwr2);
-	local_irq_restore_hw(flags);
-}
-
 #endif /* _CDEF_BF54X_H */
 
diff --git a/arch/blackfin/mach-bf548/include/mach/pll.h b/arch/blackfin/mach-bf548/include/mach/pll.h
new file mode 100644
index 0000000..7865a09
--- /dev/null
+++ b/arch/blackfin/mach-bf548/include/mach/pll.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright 2007-2008 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef _MACH_PLL_H
+#define _MACH_PLL_H
+
+#include <asm/blackfin.h>
+#include <asm/irqflags.h>
+
+/* Writing to PLL_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_PLL_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1, iwr2;
+
+	if (val == bfin_read_PLL_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SIC_IWR0);
+	iwr1 = bfin_read32(SIC_IWR1);
+	iwr2 = bfin_read32(SIC_IWR2);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
+	bfin_write32(SIC_IWR1, 0);
+	bfin_write32(SIC_IWR2, 0);
+
+	bfin_write16(PLL_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR0, iwr0);
+	bfin_write32(SIC_IWR1, iwr1);
+	bfin_write32(SIC_IWR2, iwr2);
+	hard_local_irq_restore(flags);
+}
+
+/* Writing to VR_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_VR_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1, iwr2;
+
+	if (val == bfin_read_VR_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SIC_IWR0);
+	iwr1 = bfin_read32(SIC_IWR1);
+	iwr2 = bfin_read32(SIC_IWR2);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SIC_IWR0, IWR_ENABLE(0));
+	bfin_write32(SIC_IWR1, 0);
+	bfin_write32(SIC_IWR2, 0);
+
+	bfin_write16(VR_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SIC_IWR0, iwr0);
+	bfin_write32(SIC_IWR1, iwr1);
+	bfin_write32(SIC_IWR2, iwr2);
+	hard_local_irq_restore(flags);
+}
+
+#endif /* _MACH_PLL_H */
diff --git a/arch/blackfin/mach-bf561/coreb.c b/arch/blackfin/mach-bf561/coreb.c
index deb2271..c6a4c8f 100644
--- a/arch/blackfin/mach-bf561/coreb.c
+++ b/arch/blackfin/mach-bf561/coreb.c
@@ -51,6 +51,7 @@
 static const struct file_operations coreb_fops = {
 	.owner          = THIS_MODULE,
 	.unlocked_ioctl = coreb_ioctl,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice coreb_dev = {
diff --git a/arch/blackfin/mach-bf561/include/mach/cdefBF561.h b/arch/blackfin/mach-bf561/include/mach/cdefBF561.h
index 81ecdb7..cc0416a 100644
--- a/arch/blackfin/mach-bf561/include/mach/cdefBF561.h
+++ b/arch/blackfin/mach-bf561/include/mach/cdefBF561.h
@@ -1534,54 +1534,4 @@
 /* These need to be last due to the cdef/linux inter-dependencies */
 #include <asm/irq.h>
 
-/* Writing to PLL_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_PLL_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1;
-
-	if (val == bfin_read_PLL_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SICA_IWR0);
-	iwr1 = bfin_read32(SICA_IWR1);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SICA_IWR0, IWR_ENABLE(0));
-	bfin_write32(SICA_IWR1, 0);
-
-	bfin_write16(PLL_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SICA_IWR0, iwr0);
-	bfin_write32(SICA_IWR1, iwr1);
-	local_irq_restore_hw(flags);
-}
-
-/* Writing to VR_CTL initiates a PLL relock sequence. */
-static __inline__ void bfin_write_VR_CTL(unsigned int val)
-{
-	unsigned long flags, iwr0, iwr1;
-
-	if (val == bfin_read_VR_CTL())
-		return;
-
-	local_irq_save_hw(flags);
-	/* Enable the PLL Wakeup bit in SIC IWR */
-	iwr0 = bfin_read32(SICA_IWR0);
-	iwr1 = bfin_read32(SICA_IWR1);
-	/* Only allow PPL Wakeup) */
-	bfin_write32(SICA_IWR0, IWR_ENABLE(0));
-	bfin_write32(SICA_IWR1, 0);
-
-	bfin_write16(VR_CTL, val);
-	SSYNC();
-	asm("IDLE;");
-
-	bfin_write32(SICA_IWR0, iwr0);
-	bfin_write32(SICA_IWR1, iwr1);
-	local_irq_restore_hw(flags);
-}
-
 #endif				/* _CDEF_BF561_H */
diff --git a/arch/blackfin/mach-bf561/include/mach/pll.h b/arch/blackfin/mach-bf561/include/mach/pll.h
new file mode 100644
index 0000000..f2b1fbd
--- /dev/null
+++ b/arch/blackfin/mach-bf561/include/mach/pll.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright 2005-2009 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef _MACH_PLL_H
+#define _MACH_PLL_H
+
+#include <asm/blackfin.h>
+#include <asm/irqflags.h>
+
+/* Writing to PLL_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_PLL_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1;
+
+	if (val == bfin_read_PLL_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SICA_IWR0);
+	iwr1 = bfin_read32(SICA_IWR1);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SICA_IWR0, IWR_ENABLE(0));
+	bfin_write32(SICA_IWR1, 0);
+
+	bfin_write16(PLL_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SICA_IWR0, iwr0);
+	bfin_write32(SICA_IWR1, iwr1);
+	hard_local_irq_restore(flags);
+}
+
+/* Writing to VR_CTL initiates a PLL relock sequence. */
+static __inline__ void bfin_write_VR_CTL(unsigned int val)
+{
+	unsigned long flags, iwr0, iwr1;
+
+	if (val == bfin_read_VR_CTL())
+		return;
+
+	flags = hard_local_irq_save();
+	/* Enable the PLL Wakeup bit in SIC IWR */
+	iwr0 = bfin_read32(SICA_IWR0);
+	iwr1 = bfin_read32(SICA_IWR1);
+	/* Only allow PPL Wakeup) */
+	bfin_write32(SICA_IWR0, IWR_ENABLE(0));
+	bfin_write32(SICA_IWR1, 0);
+
+	bfin_write16(VR_CTL, val);
+	SSYNC();
+	asm("IDLE;");
+
+	bfin_write32(SICA_IWR0, iwr0);
+	bfin_write32(SICA_IWR1, iwr1);
+	hard_local_irq_restore(flags);
+}
+
+#endif /* _MACH_PLL_H */
diff --git a/arch/blackfin/mach-common/cpufreq.c b/arch/blackfin/mach-common/cpufreq.c
index 4391d03..f4cf11d 100644
--- a/arch/blackfin/mach-common/cpufreq.c
+++ b/arch/blackfin/mach-common/cpufreq.c
@@ -134,7 +134,7 @@
 
 		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 		if (cpu == CPUFREQ_CPU) {
-			local_irq_save_hw(flags);
+			flags = hard_local_irq_save();
 			plldiv = (bfin_read_PLL_DIV() & SSEL) |
 						dpm_state_table[index].csel;
 			bfin_write_PLL_DIV(plldiv);
@@ -155,7 +155,7 @@
 				loops_per_jiffy = cpufreq_scale(lpj_ref,
 						lpj_ref_freq, freqs.new);
 			}
-			local_irq_restore_hw(flags);
+			hard_local_irq_restore(flags);
 		}
 		/* TODO: just test case for cycles clock source, remove later */
 		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 1c8c4c7..eaece5f 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -132,8 +132,8 @@
 static void bfin_core_mask_irq(unsigned int irq)
 {
 	bfin_irq_flags &= ~(1 << irq);
-	if (!irqs_disabled_hw())
-		local_irq_enable_hw();
+	if (!hard_irqs_disabled())
+		hard_local_irq_enable();
 }
 
 static void bfin_core_unmask_irq(unsigned int irq)
@@ -148,8 +148,8 @@
 	 * local_irq_enable just does "STI bfin_irq_flags", so it's exactly
 	 * what we need.
 	 */
-	if (!irqs_disabled_hw())
-		local_irq_enable_hw();
+	if (!hard_irqs_disabled())
+		hard_local_irq_enable();
 	return;
 }
 
@@ -158,12 +158,12 @@
 	unsigned long flags;
 
 #ifdef CONFIG_BF53x
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() &
 			     ~(1 << SIC_SYSIRQ(irq)));
 #else
 	unsigned mask_bank, mask_bit;
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	mask_bank = SIC_SYSIRQ(irq) / 32;
 	mask_bit = SIC_SYSIRQ(irq) % 32;
 	bfin_write_SIC_IMASK(mask_bank, bfin_read_SIC_IMASK(mask_bank) &
@@ -173,7 +173,7 @@
 			     ~(1 << mask_bit));
 #endif
 #endif
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 
 #ifdef CONFIG_SMP
@@ -186,12 +186,12 @@
 	unsigned long flags;
 
 #ifdef CONFIG_BF53x
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	bfin_write_SIC_IMASK(bfin_read_SIC_IMASK() |
 			     (1 << SIC_SYSIRQ(irq)));
 #else
 	unsigned mask_bank, mask_bit;
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	mask_bank = SIC_SYSIRQ(irq) / 32;
 	mask_bit = SIC_SYSIRQ(irq) % 32;
 #ifdef CONFIG_SMP
@@ -207,7 +207,7 @@
 			(1 << mask_bit));
 #endif
 #endif
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 
 #ifdef CONFIG_SMP
@@ -264,7 +264,7 @@
 	break;
 	}
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	if (state) {
 		bfin_sic_iwr[bank] |= (1 << bit);
@@ -275,7 +275,7 @@
 		vr_wakeup  &= ~wakeup;
 	}
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 
 	return 0;
 }
diff --git a/arch/blackfin/mach-common/pm.c b/arch/blackfin/mach-common/pm.c
index 09c1fb4..80884b1 100644
--- a/arch/blackfin/mach-common/pm.c
+++ b/arch/blackfin/mach-common/pm.c
@@ -25,7 +25,7 @@
 {
 	unsigned long flags;
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 	bfin_pm_standby_setup();
 
 #ifdef CONFIG_PM_BFIN_SLEEP_DEEPER
@@ -56,7 +56,7 @@
 	bfin_write_SIC_IWR(IWR_DISABLE_ALL);
 #endif
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 }
 
 int bf53x_suspend_l1_mem(unsigned char *memptr)
@@ -149,12 +149,12 @@
 	wakeup |= GPWE;
 #endif
 
-	local_irq_save_hw(flags);
+	flags = hard_local_irq_save();
 
 	ret = blackfin_dma_suspend();
 
 	if (ret) {
-		local_irq_restore_hw(flags);
+		hard_local_irq_restore(flags);
 		kfree(memptr);
 		return ret;
 	}
@@ -178,7 +178,7 @@
 	bfin_gpio_pm_hibernate_restore();
 	blackfin_dma_resume();
 
-	local_irq_restore_hw(flags);
+	hard_local_irq_restore(flags);
 	kfree(memptr);
 
 	return 0;
diff --git a/arch/cris/arch-v10/drivers/ds1302.c b/arch/cris/arch-v10/drivers/ds1302.c
index 8842756..3d655dc 100644
--- a/arch/cris/arch-v10/drivers/ds1302.c
+++ b/arch/cris/arch-v10/drivers/ds1302.c
@@ -19,7 +19,7 @@
 #include <linux/module.h>
 #include <linux/miscdevice.h>
 #include <linux/delay.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/bcd.h>
 #include <linux/capability.h>
 
@@ -34,6 +34,7 @@
 
 #define RTC_MAJOR_NR 121 /* local major, change later */
 
+static DEFINE_MUTEX(ds1302_mutex);
 static const char ds1302_name[] = "ds1302";
 
 /* The DS1302 might be connected to different bits on different products. 
@@ -357,9 +358,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ds1302_mutex);
 	ret = rtc_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ds1302_mutex);
 
 	return ret;
 }
@@ -387,6 +388,7 @@
 static const struct file_operations rtc_fops = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl = rtc_unlocked_ioctl,
+	.llseek		= noop_llseek,
 }; 
 
 /* Probe for the chip by writing something to its RAM and try reading it back. */
diff --git a/arch/cris/arch-v10/drivers/gpio.c b/arch/cris/arch-v10/drivers/gpio.c
index a07b6d2..a276f08 100644
--- a/arch/cris/arch-v10/drivers/gpio.c
+++ b/arch/cris/arch-v10/drivers/gpio.c
@@ -745,6 +745,7 @@
 	.write          = gpio_write,
 	.open           = gpio_open,
 	.release        = gpio_release,
+	.llseek		= noop_llseek,
 };
 
 static void ioif_watcher(const unsigned int gpio_in_available,
diff --git a/arch/cris/arch-v10/drivers/i2c.c b/arch/cris/arch-v10/drivers/i2c.c
index 77a9418..c413539 100644
--- a/arch/cris/arch-v10/drivers/i2c.c
+++ b/arch/cris/arch-v10/drivers/i2c.c
@@ -617,6 +617,7 @@
 	.unlocked_ioctl	= i2c_ioctl,
 	.open		= i2c_open,
 	.release	= i2c_release,
+	.llseek		= noop_llseek,
 };
 
 int __init
diff --git a/arch/cris/arch-v10/drivers/pcf8563.c b/arch/cris/arch-v10/drivers/pcf8563.c
index 7dcb1f8..ea69fab 100644
--- a/arch/cris/arch-v10/drivers/pcf8563.c
+++ b/arch/cris/arch-v10/drivers/pcf8563.c
@@ -27,7 +27,6 @@
 #include <linux/delay.h>
 #include <linux/bcd.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -49,6 +48,7 @@
 #define rtc_read(x) i2c_readreg(RTC_I2C_READ, x)
 #define rtc_write(x,y) i2c_writereg(RTC_I2C_WRITE, x, y)
 
+static DEFINE_MUTEX(pcf8563_mutex);
 static DEFINE_MUTEX(rtc_lock); /* Protect state etc */
 
 static const unsigned char days_in_month[] =
@@ -64,6 +64,7 @@
 static const struct file_operations pcf8563_fops = {
 	.owner = THIS_MODULE,
 	.unlocked_ioctl = pcf8563_unlocked_ioctl,
+	.llseek		= noop_llseek,
 };
 
 unsigned char
@@ -343,9 +344,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&pcf8563_mutex);
 	return pcf8563_ioctl(filp, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&pcf8563_mutex);
 
 	return ret;
 }
diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c
index ee2dd43..399dc1ec 100644
--- a/arch/cris/arch-v10/drivers/sync_serial.c
+++ b/arch/cris/arch-v10/drivers/sync_serial.c
@@ -20,7 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/poll.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/timer.h>
 #include <asm/irq.h>
 #include <asm/dma.h>
@@ -149,6 +149,7 @@
 };
 
 
+static DEFINE_MUTEX(sync_serial_mutex);
 static int etrax_sync_serial_init(void);
 static void initialize_port(int portnbr);
 static inline int sync_data_avail(struct sync_port *port);
@@ -250,7 +251,8 @@
 	.poll		= sync_serial_poll,
 	.unlocked_ioctl	= sync_serial_ioctl,
 	.open		= sync_serial_open,
-	.release	= sync_serial_release
+	.release	= sync_serial_release,
+	.llseek		= noop_llseek,
 };
 
 static int __init etrax_sync_serial_init(void)
@@ -445,7 +447,7 @@
 	int mode;
 	int err = -EBUSY;
 
-	lock_kernel();
+	mutex_lock(&sync_serial_mutex);
 	DEBUG(printk(KERN_DEBUG "Open sync serial port %d\n", dev));
 
 	if (dev < 0 || dev >= NUMBER_OF_PORTS || !ports[dev].enabled) {
@@ -626,7 +628,7 @@
 	ret = 0;
 	
 out:
-	unlock_kernel();
+	mutex_unlock(&sync_serial_mutex);
 	return ret;
 }
 
@@ -961,9 +963,9 @@
 {
 	long ret;
 
-	lock_kernel();
+	mutex_lock(&sync_serial_mutex);
 	ret = sync_serial_ioctl_unlocked(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&sync_serial_mutex);
 
 	return ret;
 }
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index b07646a..c03bc3b 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -281,7 +281,8 @@
 	.owner		= THIS_MODULE,
 	.open		= cryptocop_open,
 	.release	= cryptocop_release,
-	.unlocked_ioctl = cryptocop_ioctl
+	.unlocked_ioctl = cryptocop_ioctl,
+	.llseek		= noop_llseek,
 };
 
 
@@ -3139,9 +3140,9 @@
        struct inode *inode = file->f_path.dentry->d_inode;
        long ret;
 
-       lock_kernel();
+       mutex_lock(&cryptocop_mutex);
        ret = cryptocop_ioctl_unlocked(inode, filp, cmd, arg);
-       unlock_kernel();
+       mutex_unlock(&cryptocop_mutex);
 
        return ret;
 }
diff --git a/arch/cris/arch-v32/drivers/i2c.c b/arch/cris/arch-v32/drivers/i2c.c
index 5a3e900..ddb2399 100644
--- a/arch/cris/arch-v32/drivers/i2c.c
+++ b/arch/cris/arch-v32/drivers/i2c.c
@@ -698,6 +698,7 @@
 	.unlocked_ioctl = i2c_ioctl,
 	.open		= i2c_open,
 	.release	= i2c_release,
+	.llseek		= noop_llseek,
 };
 
 static int __init i2c_init(void)
diff --git a/arch/cris/arch-v32/drivers/mach-a3/gpio.c b/arch/cris/arch-v32/drivers/mach-a3/gpio.c
index 2dcd27a..c845831 100644
--- a/arch/cris/arch-v32/drivers/mach-a3/gpio.c
+++ b/arch/cris/arch-v32/drivers/mach-a3/gpio.c
@@ -23,7 +23,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <asm/etraxgpio.h>
 #include <hwregs/reg_map.h>
@@ -66,6 +66,7 @@
 #define DP(x)
 #endif
 
+static DEFINE_MUTEX(gpio_mutex);
 static char gpio_name[] = "etrax gpio";
 
 #ifdef CONFIG_ETRAX_VIRTUAL_GPIO
@@ -391,7 +392,7 @@
 	if (!priv)
 		return -ENOMEM;
 
-	lock_kernel();
+	mutex_lock(&gpio_mutex);
 	memset(priv, 0, sizeof(*priv));
 
 	priv->minor = p;
@@ -414,7 +415,7 @@
 		spin_unlock_irq(&gpio_lock);
 	}
 
-	unlock_kernel();
+	mutex_unlock(&gpio_mutex);
 	return 0;
 }
 
@@ -667,9 +668,9 @@
 {
        long ret;
 
-       lock_kernel();
+       mutex_lock(&gpio_mutex);
        ret = gpio_ioctl_unlocked(file, cmd, arg);
-       unlock_kernel();
+       mutex_unlock(&gpio_mutex);
 
        return ret;
 }
@@ -893,6 +894,7 @@
 	.write		= gpio_write,
 	.open		= gpio_open,
 	.release	= gpio_release,
+	.llseek		= noop_llseek,
 };
 
 #ifdef CONFIG_ETRAX_VIRTUAL_GPIO
diff --git a/arch/cris/arch-v32/drivers/mach-fs/gpio.c b/arch/cris/arch-v32/drivers/mach-fs/gpio.c
index 5ec8a7d..ee90d26 100644
--- a/arch/cris/arch-v32/drivers/mach-fs/gpio.c
+++ b/arch/cris/arch-v32/drivers/mach-fs/gpio.c
@@ -22,7 +22,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <asm/etraxgpio.h>
 #include <hwregs/reg_map.h>
@@ -64,6 +64,7 @@
 #define DP(x)
 #endif
 
+static DEFINE_MUTEX(gpio_mutex);
 static char gpio_name[] = "etrax gpio";
 
 #if 0
@@ -429,7 +430,7 @@
 	if (!priv)
 		return -ENOMEM;
 
-	lock_kernel();
+	mutex_lock(&gpio_mutex);
 	memset(priv, 0, sizeof(*priv));
 
 	priv->minor = p;
@@ -450,7 +451,7 @@
 	alarmlist = priv;
 	spin_unlock_irq(&alarm_lock);
 
-	unlock_kernel();
+	mutex_unlock(&gpio_mutex);
 	return 0;
 }
 
@@ -708,9 +709,9 @@
 {
        long ret;
 
-       lock_kernel();
+       mutex_lock(&gpio_mutex);
        ret = gpio_ioctl_unlocked(file, cmd, arg);
-       unlock_kernel();
+       mutex_unlock(&gpio_mutex);
 
        return ret;
 }
@@ -870,6 +871,7 @@
 	.write		= gpio_write,
 	.open		= gpio_open,
 	.release	= gpio_release,
+	.llseek		= noop_llseek,
 };
 
 #ifdef CONFIG_ETRAX_VIRTUAL_GPIO
diff --git a/arch/cris/arch-v32/drivers/pcf8563.c b/arch/cris/arch-v32/drivers/pcf8563.c
index bef6eb5..b6e4fc0 100644
--- a/arch/cris/arch-v32/drivers/pcf8563.c
+++ b/arch/cris/arch-v32/drivers/pcf8563.c
@@ -24,7 +24,6 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/ioctl.h>
-#include <linux/smp_lock.h>
 #include <linux/delay.h>
 #include <linux/bcd.h>
 #include <linux/mutex.h>
@@ -45,6 +44,7 @@
 #define rtc_read(x) i2c_readreg(RTC_I2C_READ, x)
 #define rtc_write(x,y) i2c_writereg(RTC_I2C_WRITE, x, y)
 
+static DEFINE_MUTEX(pcf8563_mutex);
 static DEFINE_MUTEX(rtc_lock); /* Protect state etc */
 
 static const unsigned char days_in_month[] =
@@ -60,6 +60,7 @@
 static const struct file_operations pcf8563_fops = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl = pcf8563_unlocked_ioctl,
+	.llseek		= noop_llseek,
 };
 
 unsigned char
@@ -339,9 +340,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&pcf8563_mutex);
 	return pcf8563_ioctl(filp, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&pcf8563_mutex);
 
 	return ret;
 }
diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index ca248f3..c8637a9 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -13,7 +13,7 @@
 #include <linux/errno.h>
 #include <linux/major.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/interrupt.h>
 #include <linux/poll.h>
 #include <linux/init.h>
@@ -145,6 +145,7 @@
 	spinlock_t lock;
 } sync_port;
 
+static DEFINE_MUTEX(sync_serial_mutex);
 static int etrax_sync_serial_init(void);
 static void initialize_port(int portnbr);
 static inline int sync_data_avail(struct sync_port *port);
@@ -247,7 +248,8 @@
 	.poll		= sync_serial_poll,
 	.unlocked_ioctl	= sync_serial_ioctl,
 	.open		= sync_serial_open,
-	.release	= sync_serial_release
+	.release	= sync_serial_release,
+	.llseek		= noop_llseek,
 };
 
 static int __init etrax_sync_serial_init(void)
@@ -434,7 +436,7 @@
 	reg_dma_rw_cfg cfg = {.en = regk_dma_yes};
 	reg_dma_rw_intr_mask intr_mask = {.data = regk_dma_yes};
 
-	lock_kernel();
+	mutex_lock(&sync_serial_mutex);
 	DEBUG(printk(KERN_DEBUG "Open sync serial port %d\n", dev));
 
 	if (dev < 0 || dev >= NBR_PORTS || !ports[dev].enabled)
@@ -583,7 +585,7 @@
 	port->busy++;
 	ret = 0;
 out:
-	unlock_kernel();
+	mutex_unlock(&sync_serial_mutex);
 	return ret;
 }
 
@@ -966,9 +968,9 @@
 {
        long ret;
 
-       lock_kernel();
+       mutex_lock(&sync_serial_mutex);
        ret = sync_serial_ioctl_unlocked(file, cmd, arg);
-       unlock_kernel();
+       mutex_unlock(&sync_serial_mutex);
 
        return ret;
 }
diff --git a/arch/cris/include/arch-v10/arch/irqflags.h b/arch/cris/include/arch-v10/arch/irqflags.h
new file mode 100644
index 0000000..75ef189
--- /dev/null
+++ b/arch/cris/include/arch-v10/arch/irqflags.h
@@ -0,0 +1,45 @@
+#ifndef __ASM_CRIS_ARCH_IRQFLAGS_H
+#define __ASM_CRIS_ARCH_IRQFLAGS_H
+
+#include <linux/types.h>
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile("move $ccr,%0" : "=rm" (flags) : : "memory");
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile("di" : : : "memory");
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile("ei" : : : "memory");
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = arch_local_save_flags();
+	arch_local_irq_disable();
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile("move %0,$ccr" : : "rm" (flags) : "memory");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & (1 << 5));
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* __ASM_CRIS_ARCH_IRQFLAGS_H */
diff --git a/arch/cris/include/arch-v10/arch/system.h b/arch/cris/include/arch-v10/arch/system.h
index 4a9cd36..935fde3 100644
--- a/arch/cris/include/arch-v10/arch/system.h
+++ b/arch/cris/include/arch-v10/arch/system.h
@@ -44,20 +44,4 @@
 struct __xchg_dummy { unsigned long a[100]; };
 #define __xg(x) ((struct __xchg_dummy *)(x))
 
-/* interrupt control.. */
-#define local_save_flags(x)	__asm__ __volatile__ ("move $ccr,%0" : "=rm" (x) : : "memory");
-#define local_irq_restore(x) 	__asm__ __volatile__ ("move %0,$ccr" : : "rm" (x) : "memory");
-#define local_irq_disable() 	__asm__ __volatile__ ( "di" : : :"memory");
-#define local_irq_enable()	__asm__ __volatile__ ( "ei" : : :"memory");
-
-#define irqs_disabled()			\
-({					\
-	unsigned long flags;		\
-	local_save_flags(flags);	\
-	!(flags & (1<<5));		\
-})
-
-/* For spinlocks etc */
-#define local_irq_save(x) __asm__ __volatile__ ("move $ccr,%0\n\tdi" : "=rm" (x) : : "memory");
-
 #endif
diff --git a/arch/cris/include/arch-v32/arch/irqflags.h b/arch/cris/include/arch-v32/arch/irqflags.h
new file mode 100644
index 0000000..041851f
--- /dev/null
+++ b/arch/cris/include/arch-v32/arch/irqflags.h
@@ -0,0 +1,46 @@
+#ifndef __ASM_CRIS_ARCH_IRQFLAGS_H
+#define __ASM_CRIS_ARCH_IRQFLAGS_H
+
+#include <linux/types.h>
+#include <arch/ptrace.h>
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile("move $ccs,%0" : "=rm" (flags) : : "memory");
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile("di" : : : "memory");
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile("ei" : : : "memory");
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = arch_local_save_flags();
+	arch_local_irq_disable();
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile("move %0,$ccs" : : "rm" (flags) : "memory");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & (1 << I_CCS_BITNR));
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* __ASM_CRIS_ARCH_IRQFLAGS_H */
diff --git a/arch/cris/include/arch-v32/arch/system.h b/arch/cris/include/arch-v32/arch/system.h
index 6ca90f1..76cea99 100644
--- a/arch/cris/include/arch-v32/arch/system.h
+++ b/arch/cris/include/arch-v32/arch/system.h
@@ -44,26 +44,4 @@
 struct __xchg_dummy { unsigned long a[100]; };
 #define __xg(x) ((struct __xchg_dummy *)(x))
 
-/* Used for interrupt control. */
-#define local_save_flags(x) \
-	__asm__ __volatile__ ("move $ccs, %0" : "=rm" (x) : : "memory");
-
-#define local_irq_restore(x) \
-	__asm__ __volatile__ ("move %0, $ccs" : : "rm" (x) : "memory");
-
-#define local_irq_disable()  __asm__ __volatile__ ("di" : : : "memory");
-#define local_irq_enable()   __asm__ __volatile__ ("ei" : : : "memory");
-
-#define irqs_disabled()		\
-({				\
-	unsigned long flags;	\
-				\
-	local_save_flags(flags);\
-	!(flags & (1 << I_CCS_BITNR));	\
-})
-
-/* Used for spinlocks, etc. */
-#define local_irq_save(x) \
-	__asm__ __volatile__ ("move $ccs, %0\n\tdi" : "=rm" (x) : : "memory");
-
 #endif /* _ASM_CRIS_ARCH_SYSTEM_H */
diff --git a/arch/cris/include/asm/irqflags.h b/arch/cris/include/asm/irqflags.h
new file mode 100644
index 0000000..943ba5c
--- /dev/null
+++ b/arch/cris/include/asm/irqflags.h
@@ -0,0 +1 @@
+#include <arch/irqflags.h>
diff --git a/arch/cris/include/asm/system.h b/arch/cris/include/asm/system.h
index 8657b08..ea10592 100644
--- a/arch/cris/include/asm/system.h
+++ b/arch/cris/include/asm/system.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_CRIS_SYSTEM_H
 #define __ASM_CRIS_SYSTEM_H
 
+#include <linux/irqflags.h>
 #include <arch/system.h>
 
 /* the switch_to macro calls resume, an asm function in entry.S which does the actual
diff --git a/arch/cris/kernel/profile.c b/arch/cris/kernel/profile.c
index 195ec5f..b82e086 100644
--- a/arch/cris/kernel/profile.c
+++ b/arch/cris/kernel/profile.c
@@ -59,6 +59,7 @@
 static const struct file_operations cris_proc_profile_operations = {
 	.read		= read_cris_profile,
 	.write		= write_cris_profile,
+	.llseek		= default_llseek,
 };
 
 static int __init init_cris_profile(void)
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index 16399bd..0f2417d 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -7,6 +7,7 @@
 	default y
 	select HAVE_IDE
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 
 config ZONE_DMA
diff --git a/arch/frv/include/asm/irqflags.h b/arch/frv/include/asm/irqflags.h
new file mode 100644
index 0000000..82f0b53
--- /dev/null
+++ b/arch/frv/include/asm/irqflags.h
@@ -0,0 +1,158 @@
+/* FR-V interrupt handling
+ *
+ * Copyright (C) 2010 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _ASM_IRQFLAGS_H
+#define _ASM_IRQFLAGS_H
+
+/*
+ * interrupt flag manipulation
+ * - use virtual interrupt management since touching the PSR is slow
+ *   - ICC2.Z: T if interrupts virtually disabled
+ *   - ICC2.C: F if interrupts really disabled
+ * - if Z==1 upon interrupt:
+ *   - C is set to 0
+ *   - interrupts are really disabled
+ *   - entry.S returns immediately
+ * - uses TIHI (TRAP if Z==0 && C==0) #2 to really reenable interrupts
+ *   - if taken, the trap:
+ *     - sets ICC2.C
+ *     - enables interrupts
+ */
+static inline void arch_local_irq_disable(void)
+{
+	/* set Z flag, but don't change the C flag */
+	asm volatile("	andcc	gr0,gr0,gr0,icc2	\n"
+		     :
+		     :
+		     : "memory", "icc2"
+		     );
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	/* clear Z flag and then test the C flag */
+	asm volatile("  oricc	gr0,#1,gr0,icc2		\n"
+		     "	tihi	icc2,gr0,#2		\n"
+		     :
+		     :
+		     : "memory", "icc2"
+		     );
+}
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+
+	asm volatile("movsg ccr,%0"
+		     : "=r"(flags)
+		     :
+		     : "memory");
+
+	/* shift ICC2.Z to bit 0 */
+	flags >>= 26;
+
+	/* make flags 1 if interrupts disabled, 0 otherwise */
+	return flags & 1UL;
+
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = arch_local_save_flags();
+	arch_local_irq_disable();
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	/* load the Z flag by turning 1 if disabled into 0 if disabled
+	 * and thus setting the Z flag but not the C flag */
+	asm volatile("  xoricc	%0,#1,gr0,icc2		\n"
+		     /* then trap if Z=0 and C=0 */
+		     "	tihi	icc2,gr0,#2		\n"
+		     :
+		     : "r"(flags)
+		     : "memory", "icc2"
+		     );
+
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+/*
+ * real interrupt flag manipulation
+ */
+#define __arch_local_irq_disable()			\
+do {							\
+	unsigned long psr;				\
+	asm volatile("	movsg	psr,%0		\n"	\
+		     "	andi	%0,%2,%0	\n"	\
+		     "	ori	%0,%1,%0	\n"	\
+		     "	movgs	%0,psr		\n"	\
+		     : "=r"(psr)			\
+		     : "i" (PSR_PIL_14), "i" (~PSR_PIL)	\
+		     : "memory");			\
+} while (0)
+
+#define __arch_local_irq_enable()			\
+do {							\
+	unsigned long psr;				\
+	asm volatile("	movsg	psr,%0		\n"	\
+		     "	andi	%0,%1,%0	\n"	\
+		     "	movgs	%0,psr		\n"	\
+		     : "=r"(psr)			\
+		     : "i" (~PSR_PIL)			\
+		     : "memory");			\
+} while (0)
+
+#define __arch_local_save_flags(flags)		\
+do {						\
+	typecheck(unsigned long, flags);	\
+	asm("movsg psr,%0"			\
+	    : "=r"(flags)			\
+	    :					\
+	    : "memory");			\
+} while (0)
+
+#define	__arch_local_irq_save(flags)			\
+do {							\
+	unsigned long npsr;				\
+	typecheck(unsigned long, flags);		\
+	asm volatile("	movsg	psr,%0		\n"	\
+		     "	andi	%0,%3,%1	\n"	\
+		     "	ori	%1,%2,%1	\n"	\
+		     "	movgs	%1,psr		\n"	\
+		     : "=r"(flags), "=r"(npsr)		\
+		     : "i" (PSR_PIL_14), "i" (~PSR_PIL)	\
+		     : "memory");			\
+} while (0)
+
+#define	__arch_local_irq_restore(flags)			\
+do {							\
+	typecheck(unsigned long, flags);		\
+	asm volatile("	movgs	%0,psr		\n"	\
+		     :					\
+		     : "r" (flags)			\
+		     : "memory");			\
+} while (0)
+
+#define __arch_irqs_disabled()			\
+	((__get_PSR() & PSR_PIL) >= PSR_PIL_14)
+
+#endif /* _ASM_IRQFLAGS_H */
diff --git a/arch/frv/include/asm/system.h b/arch/frv/include/asm/system.h
index efd22d9..0a6d8d9 100644
--- a/arch/frv/include/asm/system.h
+++ b/arch/frv/include/asm/system.h
@@ -37,142 +37,6 @@
 } while(0)
 
 /*
- * interrupt flag manipulation
- * - use virtual interrupt management since touching the PSR is slow
- *   - ICC2.Z: T if interrupts virtually disabled
- *   - ICC2.C: F if interrupts really disabled
- * - if Z==1 upon interrupt:
- *   - C is set to 0
- *   - interrupts are really disabled
- *   - entry.S returns immediately
- * - uses TIHI (TRAP if Z==0 && C==0) #2 to really reenable interrupts
- *   - if taken, the trap:
- *     - sets ICC2.C
- *     - enables interrupts
- */
-#define local_irq_disable()					\
-do {								\
-	/* set Z flag, but don't change the C flag */		\
-	asm volatile("	andcc	gr0,gr0,gr0,icc2	\n"	\
-		     :						\
-		     :						\
-		     : "memory", "icc2"				\
-		     );						\
-} while(0)
-
-#define local_irq_enable()					\
-do {								\
-	/* clear Z flag and then test the C flag */		\
-	asm volatile("  oricc	gr0,#1,gr0,icc2		\n"	\
-		     "	tihi	icc2,gr0,#2		\n"	\
-		     :						\
-		     :						\
-		     : "memory", "icc2"				\
-		     );						\
-} while(0)
-
-#define local_save_flags(flags)					\
-do {								\
-	typecheck(unsigned long, flags);			\
-	asm volatile("movsg ccr,%0"				\
-		     : "=r"(flags)				\
-		     :						\
-		     : "memory");				\
-								\
-	/* shift ICC2.Z to bit 0 */				\
-	flags >>= 26;						\
-								\
-	/* make flags 1 if interrupts disabled, 0 otherwise */	\
-	flags &= 1UL;						\
-} while(0)
-
-#define irqs_disabled() \
-	({unsigned long flags; local_save_flags(flags); !!flags; })
-
-#define	local_irq_save(flags)			\
-do {						\
-	typecheck(unsigned long, flags);	\
-	local_save_flags(flags);		\
-	local_irq_disable();			\
-} while(0)
-
-#define	local_irq_restore(flags)					\
-do {									\
-	typecheck(unsigned long, flags);				\
-									\
-	/* load the Z flag by turning 1 if disabled into 0 if disabled	\
-	 * and thus setting the Z flag but not the C flag */		\
-	asm volatile("  xoricc	%0,#1,gr0,icc2		\n"		\
-		     /* then test Z=0 and C=0 */			\
-		     "	tihi	icc2,gr0,#2		\n"		\
-		     :							\
-		     : "r"(flags)					\
-		     : "memory", "icc2"					\
-		     );							\
-									\
-} while(0)
-
-/*
- * real interrupt flag manipulation
- */
-#define __local_irq_disable()				\
-do {							\
-	unsigned long psr;				\
-	asm volatile("	movsg	psr,%0		\n"	\
-		     "	andi	%0,%2,%0	\n"	\
-		     "	ori	%0,%1,%0	\n"	\
-		     "	movgs	%0,psr		\n"	\
-		     : "=r"(psr)			\
-		     : "i" (PSR_PIL_14), "i" (~PSR_PIL)	\
-		     : "memory");			\
-} while(0)
-
-#define __local_irq_enable()				\
-do {							\
-	unsigned long psr;				\
-	asm volatile("	movsg	psr,%0		\n"	\
-		     "	andi	%0,%1,%0	\n"	\
-		     "	movgs	%0,psr		\n"	\
-		     : "=r"(psr)			\
-		     : "i" (~PSR_PIL)			\
-		     : "memory");			\
-} while(0)
-
-#define __local_save_flags(flags)		\
-do {						\
-	typecheck(unsigned long, flags);	\
-	asm("movsg psr,%0"			\
-	    : "=r"(flags)			\
-	    :					\
-	    : "memory");			\
-} while(0)
-
-#define	__local_irq_save(flags)				\
-do {							\
-	unsigned long npsr;				\
-	typecheck(unsigned long, flags);		\
-	asm volatile("	movsg	psr,%0		\n"	\
-		     "	andi	%0,%3,%1	\n"	\
-		     "	ori	%1,%2,%1	\n"	\
-		     "	movgs	%1,psr		\n"	\
-		     : "=r"(flags), "=r"(npsr)		\
-		     : "i" (PSR_PIL_14), "i" (~PSR_PIL)	\
-		     : "memory");			\
-} while(0)
-
-#define	__local_irq_restore(flags)			\
-do {							\
-	typecheck(unsigned long, flags);		\
-	asm volatile("	movgs	%0,psr		\n"	\
-		     :					\
-		     : "r" (flags)			\
-		     : "memory");			\
-} while(0)
-
-#define __irqs_disabled() \
-	((__get_PSR() & PSR_PIL) >= PSR_PIL_14)
-
-/*
  * Force strict CPU ordering.
  */
 #define nop()			asm volatile ("nop"::)
diff --git a/arch/frv/lib/Makefile b/arch/frv/lib/Makefile
index f470975..4ff2fb1 100644
--- a/arch/frv/lib/Makefile
+++ b/arch/frv/lib/Makefile
@@ -5,4 +5,4 @@
 lib-y := \
 	__ashldi3.o __lshrdi3.o __muldi3.o __ashrdi3.o __negdi2.o __ucmpdi2.o \
 	checksum.o memcpy.o memset.o atomic-ops.o atomic64-ops.o \
-	outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o perf_event.o
+	outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o
diff --git a/arch/frv/lib/perf_event.c b/arch/frv/lib/perf_event.c
deleted file mode 100644
index 9ac5acf..0000000
--- a/arch/frv/lib/perf_event.c
+++ /dev/null
@@ -1,19 +0,0 @@
-/* Performance event handling
- *
- * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#include <linux/perf_event.h>
-
-/*
- * mark the performance event as pending
- */
-void set_perf_event_pending(void)
-{
-}
diff --git a/arch/h8300/include/asm/irqflags.h b/arch/h8300/include/asm/irqflags.h
new file mode 100644
index 0000000..9617cd5
--- /dev/null
+++ b/arch/h8300/include/asm/irqflags.h
@@ -0,0 +1,43 @@
+#ifndef _H8300_IRQFLAGS_H
+#define _H8300_IRQFLAGS_H
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile ("stc ccr,%w0" : "=r" (flags));
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile ("orc  #0x80,ccr" : : : "memory");
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile ("andc #0x7f,ccr" : : : "memory");
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = arch_local_save_flags();
+	arch_local_irq_disable();
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile ("ldc %w0,ccr" : : "r" (flags) : "memory");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & 0x80) == 0x80;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* _H8300_IRQFLAGS_H */
diff --git a/arch/h8300/include/asm/system.h b/arch/h8300/include/asm/system.h
index 16bf156..2c2382e 100644
--- a/arch/h8300/include/asm/system.h
+++ b/arch/h8300/include/asm/system.h
@@ -2,6 +2,7 @@
 #define _H8300_SYSTEM_H
 
 #include <linux/linkage.h>
+#include <linux/irqflags.h>
 
 struct pt_regs;
 
@@ -51,31 +52,8 @@
   (last) = _last; 					    \
 }
 
-#define __sti() asm volatile ("andc #0x7f,ccr")
-#define __cli() asm volatile ("orc  #0x80,ccr")
-
-#define __save_flags(x) \
-       asm volatile ("stc ccr,%w0":"=r" (x))
-
-#define __restore_flags(x) \
-       asm volatile ("ldc %w0,ccr": :"r" (x))
-
-#define	irqs_disabled()			\
-({					\
-	unsigned char flags;		\
-	__save_flags(flags);	        \
-	((flags & 0x80) == 0x80);	\
-})
-
 #define iret() __asm__ __volatile__ ("rte": : :"memory", "sp", "cc")
 
-/* For spinlocks etc */
-#define local_irq_disable()	__cli()
-#define local_irq_enable()      __sti()
-#define local_irq_save(x)	({ __save_flags(x); local_irq_disable(); })
-#define local_irq_restore(x)	__restore_flags(x)
-#define local_save_flags(x)     __save_flags(x)
-
 /*
  * Force strict CPU ordering.
  * Not really required on H8...
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index ba22849..7c82fa1 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -53,6 +53,9 @@
 	bool
 	default y
 
+config ARCH_DMA_ADDR_T_64BIT
+	def_bool y
+
 config NEED_DMA_MAP_STATE
 	def_bool y
 
@@ -62,6 +65,9 @@
 config SWIOTLB
        bool
 
+config STACKTRACE_SUPPORT
+	def_bool y
+
 config GENERIC_LOCKBREAK
 	def_bool n
 
@@ -683,8 +689,10 @@
 # Use the generic interrupt handling code in kernel/irq/:
 #
 config GENERIC_HARDIRQS
-	bool
-	default y
+	def_bool y
+
+config GENERIC_HARDIRQS_NO__DO_IRQ
+	def_bool y
 
 config GENERIC_IRQ_PROBE
 	bool
diff --git a/arch/ia64/include/asm/compat.h b/arch/ia64/include/asm/compat.h
deleted file mode 100644
index 9301a28..0000000
--- a/arch/ia64/include/asm/compat.h
+++ /dev/null
@@ -1,208 +0,0 @@
-#ifndef _ASM_IA64_COMPAT_H
-#define _ASM_IA64_COMPAT_H
-/*
- * Architecture specific compatibility types
- */
-#include <linux/types.h>
-
-#define COMPAT_USER_HZ		100
-#define COMPAT_UTS_MACHINE	"i686\0\0\0"
-
-typedef u32		compat_size_t;
-typedef s32		compat_ssize_t;
-typedef s32		compat_time_t;
-typedef s32		compat_clock_t;
-typedef s32		compat_key_t;
-typedef s32		compat_pid_t;
-typedef u16		__compat_uid_t;
-typedef u16		__compat_gid_t;
-typedef u32		__compat_uid32_t;
-typedef u32		__compat_gid32_t;
-typedef u16		compat_mode_t;
-typedef u32		compat_ino_t;
-typedef u16		compat_dev_t;
-typedef s32		compat_off_t;
-typedef s64		compat_loff_t;
-typedef u16		compat_nlink_t;
-typedef u16		compat_ipc_pid_t;
-typedef s32		compat_daddr_t;
-typedef u32		compat_caddr_t;
-typedef __kernel_fsid_t	compat_fsid_t;
-typedef s32		compat_timer_t;
-
-typedef s32		compat_int_t;
-typedef s32		compat_long_t;
-typedef s64 __attribute__((aligned(4))) compat_s64;
-typedef u32		compat_uint_t;
-typedef u32		compat_ulong_t;
-typedef u64 __attribute__((aligned(4))) compat_u64;
-
-struct compat_timespec {
-	compat_time_t	tv_sec;
-	s32		tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t	tv_sec;
-	s32		tv_usec;
-};
-
-struct compat_stat {
-	compat_dev_t	st_dev;
-	u16		__pad1;
-	compat_ino_t	st_ino;
-	compat_mode_t	st_mode;
-	compat_nlink_t	st_nlink;
-	__compat_uid_t	st_uid;
-	__compat_gid_t	st_gid;
-	compat_dev_t	st_rdev;
-	u16		__pad2;
-	u32		st_size;
-	u32		st_blksize;
-	u32		st_blocks;
-	u32		st_atime;
-	u32		st_atime_nsec;
-	u32		st_mtime;
-	u32		st_mtime_nsec;
-	u32		st_ctime;
-	u32		st_ctime_nsec;
-	u32		__unused4;
-	u32		__unused5;
-};
-
-struct compat_flock {
-	short		l_type;
-	short		l_whence;
-	compat_off_t	l_start;
-	compat_off_t	l_len;
-	compat_pid_t	l_pid;
-};
-
-#define F_GETLK64	12
-#define F_SETLK64	13
-#define F_SETLKW64	14
-
-/*
- * IA32 uses 4 byte alignment for 64 bit quantities,
- * so we need to pack this structure.
- */
-struct compat_flock64 {
-	short		l_type;
-	short		l_whence;
-	compat_loff_t	l_start;
-	compat_loff_t	l_len;
-	compat_pid_t	l_pid;
-} __attribute__((packed));
-
-struct compat_statfs {
-	int		f_type;
-	int		f_bsize;
-	int		f_blocks;
-	int		f_bfree;
-	int		f_bavail;
-	int		f_files;
-	int		f_ffree;
-	compat_fsid_t	f_fsid;
-	int		f_namelen;	/* SunOS ignores this field. */
-	int		f_frsize;
-	int		f_spare[5];
-};
-
-#define COMPAT_RLIM_OLD_INFINITY       0x7fffffff
-#define COMPAT_RLIM_INFINITY           0xffffffff
-
-typedef u32		compat_old_sigset_t;	/* at least 32 bits */
-
-#define _COMPAT_NSIG		64
-#define _COMPAT_NSIG_BPW	32
-
-typedef u32		compat_sigset_word;
-
-#define COMPAT_OFF_T_MAX	0x7fffffff
-#define COMPAT_LOFF_T_MAX	0x7fffffffffffffffL
-
-struct compat_ipc64_perm {
-	compat_key_t key;
-	__compat_uid32_t uid;
-	__compat_gid32_t gid;
-	__compat_uid32_t cuid;
-	__compat_gid32_t cgid;
-	unsigned short mode;
-	unsigned short __pad1;
-	unsigned short seq;
-	unsigned short __pad2;
-	compat_ulong_t unused1;
-	compat_ulong_t unused2;
-};
-
-struct compat_semid64_ds {
-	struct compat_ipc64_perm sem_perm;
-	compat_time_t  sem_otime;
-	compat_ulong_t __unused1;
-	compat_time_t  sem_ctime;
-	compat_ulong_t __unused2;
-	compat_ulong_t sem_nsems;
-	compat_ulong_t __unused3;
-	compat_ulong_t __unused4;
-};
-
-struct compat_msqid64_ds {
-	struct compat_ipc64_perm msg_perm;
-	compat_time_t  msg_stime;
-	compat_ulong_t __unused1;
-	compat_time_t  msg_rtime;
-	compat_ulong_t __unused2;
-	compat_time_t  msg_ctime;
-	compat_ulong_t __unused3;
-	compat_ulong_t msg_cbytes;
-	compat_ulong_t msg_qnum;
-	compat_ulong_t msg_qbytes;
-	compat_pid_t   msg_lspid;
-	compat_pid_t   msg_lrpid;
-	compat_ulong_t __unused4;
-	compat_ulong_t __unused5;
-};
-
-struct compat_shmid64_ds {
-	struct compat_ipc64_perm shm_perm;
-	compat_size_t  shm_segsz;
-	compat_time_t  shm_atime;
-	compat_ulong_t __unused1;
-	compat_time_t  shm_dtime;
-	compat_ulong_t __unused2;
-	compat_time_t  shm_ctime;
-	compat_ulong_t __unused3;
-	compat_pid_t   shm_cpid;
-	compat_pid_t   shm_lpid;
-	compat_ulong_t shm_nattch;
-	compat_ulong_t __unused4;
-	compat_ulong_t __unused5;
-};
-
-/*
- * A pointer passed in from user mode. This should not be used for syscall parameters,
- * just declare them as pointers because the syscall entry code will have appropriately
- * converted them already.
- */
-typedef	u32		compat_uptr_t;
-
-static inline void __user *
-compat_ptr (compat_uptr_t uptr)
-{
-	return (void __user *) (unsigned long) uptr;
-}
-
-static inline compat_uptr_t
-ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
-static __inline__ void __user *
-arch_compat_alloc_user_space (long len)
-{
-	struct pt_regs *regs = task_pt_regs(current);
-	return (void __user *) (((regs->r12 & 0xffffffff) & -16) - len);
-}
-
-#endif /* _ASM_IA64_COMPAT_H */
diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h
index d514cd9..8fb7d33 100644
--- a/arch/ia64/include/asm/hardirq.h
+++ b/arch/ia64/include/asm/hardirq.h
@@ -6,12 +6,6 @@
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-#include <asm/processor.h>
-
 /*
  * No irq_cpustat_t for IA-64.  The data is held in the per-CPU data structure.
  */
@@ -20,6 +14,11 @@
 
 #define local_softirq_pending()		(local_cpu_data->softirq_pending)
 
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+#include <asm/processor.h>
+
 extern void __iomem *ipi_base_addr;
 
 void ack_bad_irq(unsigned int irq);
diff --git a/arch/ia64/include/asm/iommu_table.h b/arch/ia64/include/asm/iommu_table.h
new file mode 100644
index 0000000..92c8d36
--- /dev/null
+++ b/arch/ia64/include/asm/iommu_table.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_IA64_IOMMU_TABLE_H
+#define _ASM_IA64_IOMMU_TABLE_H
+
+#define IOMMU_INIT_POST(_detect)
+
+#endif /* _ASM_IA64_IOMMU_TABLE_H */
diff --git a/arch/ia64/include/asm/irqflags.h b/arch/ia64/include/asm/irqflags.h
new file mode 100644
index 0000000..f82d6be
--- /dev/null
+++ b/arch/ia64/include/asm/irqflags.h
@@ -0,0 +1,94 @@
+/*
+ * IRQ flags defines.
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ */
+
+#ifndef _ASM_IA64_IRQFLAGS_H
+#define _ASM_IA64_IRQFLAGS_H
+
+#ifdef CONFIG_IA64_DEBUG_IRQ
+extern unsigned long last_cli_ip;
+static inline void arch_maybe_save_ip(unsigned long flags)
+{
+	if (flags & IA64_PSR_I)
+		last_cli_ip = ia64_getreg(_IA64_REG_IP);
+}
+#else
+#define arch_maybe_save_ip(flags) do {} while (0)
+#endif
+
+/*
+ * - clearing psr.i is implicitly serialized (visible by next insn)
+ * - setting psr.i requires data serialization
+ * - we need a stop-bit before reading PSR because we sometimes
+ *   write a floating-point register right before reading the PSR
+ *   and that writes to PSR.mfl
+ */
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	ia64_stop();
+#ifdef CONFIG_PARAVIRT
+	return ia64_get_psr_i();
+#else
+	return ia64_getreg(_IA64_REG_PSR);
+#endif
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = arch_local_save_flags();
+
+	ia64_stop();
+	ia64_rsm(IA64_PSR_I);
+	arch_maybe_save_ip(flags);
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+#ifdef CONFIG_IA64_DEBUG_IRQ
+	arch_local_irq_save();
+#else
+	ia64_stop();
+	ia64_rsm(IA64_PSR_I);
+#endif
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	ia64_stop();
+	ia64_ssm(IA64_PSR_I);
+	ia64_srlz_d();
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+#ifdef CONFIG_IA64_DEBUG_IRQ
+	unsigned long old_psr = arch_local_save_flags();
+#endif
+	ia64_intrin_local_irq_restore(flags & IA64_PSR_I);
+	arch_maybe_save_ip(old_psr & ~flags);
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & IA64_PSR_I) == 0;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+static inline void arch_safe_halt(void)
+{
+	ia64_pal_halt_light();	/* PAL_HALT_LIGHT */
+}
+
+
+#endif /* _ASM_IA64_IRQFLAGS_H */
diff --git a/arch/ia64/include/asm/system.h b/arch/ia64/include/asm/system.h
index 9f342a5..6cca307 100644
--- a/arch/ia64/include/asm/system.h
+++ b/arch/ia64/include/asm/system.h
@@ -107,87 +107,11 @@
  */
 #define set_mb(var, value)	do { (var) = (value); mb(); } while (0)
 
-#define safe_halt()         ia64_pal_halt_light()    /* PAL_HALT_LIGHT */
-
 /*
  * The group barrier in front of the rsm & ssm are necessary to ensure
  * that none of the previous instructions in the same group are
  * affected by the rsm/ssm.
  */
-/* For spinlocks etc */
-
-/*
- * - clearing psr.i is implicitly serialized (visible by next insn)
- * - setting psr.i requires data serialization
- * - we need a stop-bit before reading PSR because we sometimes
- *   write a floating-point register right before reading the PSR
- *   and that writes to PSR.mfl
- */
-#ifdef CONFIG_PARAVIRT
-#define __local_save_flags()	ia64_get_psr_i()
-#else
-#define __local_save_flags()	ia64_getreg(_IA64_REG_PSR)
-#endif
-
-#define __local_irq_save(x)			\
-do {						\
-	ia64_stop();				\
-	(x) = __local_save_flags();		\
-	ia64_stop();				\
-	ia64_rsm(IA64_PSR_I);			\
-} while (0)
-
-#define __local_irq_disable()			\
-do {						\
-	ia64_stop();				\
-	ia64_rsm(IA64_PSR_I);			\
-} while (0)
-
-#define __local_irq_restore(x)	ia64_intrin_local_irq_restore((x) & IA64_PSR_I)
-
-#ifdef CONFIG_IA64_DEBUG_IRQ
-
-  extern unsigned long last_cli_ip;
-
-# define __save_ip()		last_cli_ip = ia64_getreg(_IA64_REG_IP)
-
-# define local_irq_save(x)					\
-do {								\
-	unsigned long __psr;					\
-								\
-	__local_irq_save(__psr);				\
-	if (__psr & IA64_PSR_I)					\
-		__save_ip();					\
-	(x) = __psr;						\
-} while (0)
-
-# define local_irq_disable()	do { unsigned long __x; local_irq_save(__x); } while (0)
-
-# define local_irq_restore(x)					\
-do {								\
-	unsigned long __old_psr, __psr = (x);			\
-								\
-	local_save_flags(__old_psr);				\
-	__local_irq_restore(__psr);				\
-	if ((__old_psr & IA64_PSR_I) && !(__psr & IA64_PSR_I))	\
-		__save_ip();					\
-} while (0)
-
-#else /* !CONFIG_IA64_DEBUG_IRQ */
-# define local_irq_save(x)	__local_irq_save(x)
-# define local_irq_disable()	__local_irq_disable()
-# define local_irq_restore(x)	__local_irq_restore(x)
-#endif /* !CONFIG_IA64_DEBUG_IRQ */
-
-#define local_irq_enable()	({ ia64_stop(); ia64_ssm(IA64_PSR_I); ia64_srlz_d(); })
-#define local_save_flags(flags)	({ ia64_stop(); (flags) = __local_save_flags(); })
-
-#define irqs_disabled()				\
-({						\
-	unsigned long __ia64_id_flags;		\
-	local_save_flags(__ia64_id_flags);	\
-	(__ia64_id_flags & IA64_PSR_I) == 0;	\
-})
 
 #ifdef __KERNEL__
 
@@ -272,10 +196,6 @@
 
 void default_idle(void);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void account_system_vtime(struct task_struct *);
-#endif
-
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index db10b1e..395c2f2 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -34,6 +34,7 @@
 obj-$(CONFIG_PCI_MSI)		+= msi_ia64.o
 mca_recovery-y			+= mca_drv.o mca_drv_asm.o
 obj-$(CONFIG_IA64_MC_ERR_INJECT)+= err_inject.o
+obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirtentry.o \
 				   paravirt_patch.o
diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c
index 71e3586..d52f1f7 100644
--- a/arch/ia64/kernel/cyclone.c
+++ b/arch/ia64/kernel/cyclone.c
@@ -59,13 +59,13 @@
 		return -ENODEV;
 	}
 	base = readq(reg);
+	iounmap(reg);
 	if(!base){
 		printk(KERN_ERR "Summit chipset: Could not find valid CBAR"
 				" value.\n");
 		use_cyclone = 0;
 		return -ENODEV;
 	}
-	iounmap(reg);
 
 	/* setup PMCC */
 	offset = (base + CYCLONE_PMCC_OFFSET);
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 7ded766..22c3840 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -108,10 +108,6 @@
 #define DBG(fmt...)
 #endif
 
-#define NR_PREALLOCATE_RTE_ENTRIES \
-	(PAGE_SIZE / sizeof(struct iosapic_rte_info))
-#define RTE_PREALLOCATED	(1)
-
 static DEFINE_SPINLOCK(iosapic_lock);
 
 /*
@@ -136,7 +132,6 @@
 	struct list_head rte_list;	/* RTEs sharing the same vector */
 	char		rte_index;	/* IOSAPIC RTE index */
 	int		refcnt;		/* reference counter */
-	unsigned int	flags;		/* flags */
 	struct iosapic	*iosapic;
 } ____cacheline_aligned;
 
@@ -155,9 +150,6 @@
 
 static unsigned char pcat_compat __devinitdata;	/* 8259 compatibility flag */
 
-static int iosapic_kmalloc_ok;
-static LIST_HEAD(free_rte_list);
-
 static inline void
 iosapic_write(struct iosapic *iosapic, unsigned int reg, u32 val)
 {
@@ -394,7 +386,7 @@
 }
 
 static void
-iosapic_end_level_irq (unsigned int irq)
+iosapic_unmask_level_irq (unsigned int irq)
 {
 	ia64_vector vec = irq_to_vector(irq);
 	struct iosapic_rte_info *rte;
@@ -404,7 +396,8 @@
 	if (unlikely(irq_desc[irq].status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
 		mask_irq(irq);
-	}
+	} else
+		unmask_irq(irq);
 
 	list_for_each_entry(rte, &iosapic_intr_info[irq].rtes, rte_list)
 		iosapic_eoi(rte->iosapic->addr, vec);
@@ -427,9 +420,8 @@
 	.enable =	iosapic_enable_level_irq,
 	.disable =	iosapic_disable_level_irq,
 	.ack =		iosapic_ack_level_irq,
-	.end =		iosapic_end_level_irq,
 	.mask =		mask_irq,
-	.unmask =	unmask_irq,
+	.unmask =	iosapic_unmask_level_irq,
 	.set_affinity =	iosapic_set_affinity
 };
 
@@ -552,37 +544,6 @@
 	}
 }
 
-static struct iosapic_rte_info * __init_refok iosapic_alloc_rte (void)
-{
-	int i;
-	struct iosapic_rte_info *rte;
-	int preallocated = 0;
-
-	if (!iosapic_kmalloc_ok && list_empty(&free_rte_list)) {
-		rte = alloc_bootmem(sizeof(struct iosapic_rte_info) *
-				    NR_PREALLOCATE_RTE_ENTRIES);
-		for (i = 0; i < NR_PREALLOCATE_RTE_ENTRIES; i++, rte++)
-			list_add(&rte->rte_list, &free_rte_list);
-	}
-
-	if (!list_empty(&free_rte_list)) {
-		rte = list_entry(free_rte_list.next, struct iosapic_rte_info,
-				 rte_list);
-		list_del(&rte->rte_list);
-		preallocated++;
-	} else {
-		rte = kmalloc(sizeof(struct iosapic_rte_info), GFP_ATOMIC);
-		if (!rte)
-			return NULL;
-	}
-
-	memset(rte, 0, sizeof(struct iosapic_rte_info));
-	if (preallocated)
-		rte->flags |= RTE_PREALLOCATED;
-
-	return rte;
-}
-
 static inline int irq_is_shared (int irq)
 {
 	return (iosapic_intr_info[irq].count > 1);
@@ -615,7 +576,7 @@
 
 	rte = find_rte(irq, gsi);
 	if (!rte) {
-		rte = iosapic_alloc_rte();
+		rte = kzalloc(sizeof (*rte), GFP_ATOMIC);
 		if (!rte) {
 			printk(KERN_WARNING "%s: cannot allocate memory\n",
 			       __func__);
@@ -658,6 +619,10 @@
 			       idesc->chip->name, irq_type->name);
 		idesc->chip = irq_type;
 	}
+	if (trigger == IOSAPIC_EDGE)
+		__set_irq_handler_unlocked(irq, handle_edge_irq);
+	else
+		__set_irq_handler_unlocked(irq, handle_level_irq);
 	return 0;
 }
 
@@ -1161,10 +1126,3 @@
 	return;
 }
 #endif
-
-static int __init iosapic_enable_kmalloc (void)
-{
-	iosapic_kmalloc_ok = 1;
-	return 0;
-}
-core_initcall (iosapic_enable_kmalloc);
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index f14c35f..9a26015 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -30,6 +30,7 @@
 #include <linux/bitops.h>
 #include <linux/irq.h>
 #include <linux/ratelimit.h>
+#include <linux/acpi.h>
 
 #include <asm/delay.h>
 #include <asm/intrinsics.h>
@@ -635,6 +636,7 @@
 	desc->chip = &irq_type_ia64_lsapic;
 	if (action)
 		setup_irq(irq, action);
+	set_irq_handler(irq, handle_percpu_irq);
 }
 
 void __init
@@ -650,6 +652,9 @@
 void __init
 init_IRQ (void)
 {
+#ifdef CONFIG_ACPI
+	acpi_boot_init();
+#endif
 	ia64_register_ipi();
 	register_percpu_irq(IA64_SPURIOUS_INT_VECTOR, NULL);
 #ifdef CONFIG_SMP
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index a0220dc..1753f6a 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -2055,25 +2055,6 @@
 
 	IA64_MCA_DEBUG("%s: registered OS INIT handler with SAL\n", __func__);
 
-	/*
-	 *  Configure the CMCI/P vector and handler. Interrupts for CMC are
-	 *  per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c).
-	 */
-	register_percpu_irq(IA64_CMC_VECTOR, &cmci_irqaction);
-	register_percpu_irq(IA64_CMCP_VECTOR, &cmcp_irqaction);
-	ia64_mca_cmc_vector_setup();       /* Setup vector on BSP */
-
-	/* Setup the MCA rendezvous interrupt vector */
-	register_percpu_irq(IA64_MCA_RENDEZ_VECTOR, &mca_rdzv_irqaction);
-
-	/* Setup the MCA wakeup interrupt vector */
-	register_percpu_irq(IA64_MCA_WAKEUP_VECTOR, &mca_wkup_irqaction);
-
-#ifdef CONFIG_ACPI
-	/* Setup the CPEI/P handler */
-	register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction);
-#endif
-
 	/* Initialize the areas set aside by the OS to buffer the
 	 * platform/processor error states for MCA/INIT/CMC
 	 * handling.
@@ -2103,6 +2084,25 @@
 	if (!mca_init)
 		return 0;
 
+	/*
+	 *  Configure the CMCI/P vector and handler. Interrupts for CMC are
+	 *  per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c).
+	 */
+	register_percpu_irq(IA64_CMC_VECTOR, &cmci_irqaction);
+	register_percpu_irq(IA64_CMCP_VECTOR, &cmcp_irqaction);
+	ia64_mca_cmc_vector_setup();       /* Setup vector on BSP */
+
+	/* Setup the MCA rendezvous interrupt vector */
+	register_percpu_irq(IA64_MCA_RENDEZ_VECTOR, &mca_rdzv_irqaction);
+
+	/* Setup the MCA wakeup interrupt vector */
+	register_percpu_irq(IA64_MCA_WAKEUP_VECTOR, &mca_wkup_irqaction);
+
+#ifdef CONFIG_ACPI
+	/* Setup the CPEI/P handler */
+	register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction);
+#endif
+
 	register_hotcpu_notifier(&mca_cpu_notifier);
 
 	/* Setup the CMCI/P vector and handler */
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 4a746ea..00b19a4 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -104,8 +104,8 @@
  */
 static struct irq_chip ia64_msi_chip = {
 	.name		= "PCI-MSI",
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
 	.ack		= ia64_ack_msi_irq,
 #ifdef CONFIG_SMP
 	.set_affinity	= ia64_set_msi_irq_affinity,
@@ -160,8 +160,8 @@
 
 static struct irq_chip dmar_msi_type = {
 	.name = "DMAR_MSI",
-	.unmask = dmar_msi_unmask,
-	.mask = dmar_msi_mask,
+	.irq_unmask = dmar_msi_unmask,
+	.irq_mask = dmar_msi_mask,
 	.ack = ia64_ack_msi_irq,
 #ifdef CONFIG_SMP
 	.set_affinity = dmar_msi_set_affinity,
diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c
index fdf6f9d..77597e5 100644
--- a/arch/ia64/kernel/palinfo.c
+++ b/arch/ia64/kernel/palinfo.c
@@ -434,7 +434,7 @@
 	unsigned long phys_stacked;
 	pal_hints_u_t hints;
 	unsigned long iregs, dregs;
-	char *info_type[]={
+	static const char * const info_type[] = {
 		"Implemented AR(s)",
 		"AR(s) with read side-effects",
 		"Implemented CR(s)",
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index cce050e..6b1852f 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -1573,7 +1573,7 @@
 		return -EINVAL;
 	}
 
-	ctx = (pfm_context_t *)filp->private_data;
+	ctx = filp->private_data;
 	if (ctx == NULL) {
 		printk(KERN_ERR "perfmon: pfm_read: NULL ctx [%d]\n", task_pid_nr(current));
 		return -EINVAL;
@@ -1673,7 +1673,7 @@
 		return 0;
 	}
 
-	ctx = (pfm_context_t *)filp->private_data;
+	ctx = filp->private_data;
 	if (ctx == NULL) {
 		printk(KERN_ERR "perfmon: pfm_poll: NULL ctx [%d]\n", task_pid_nr(current));
 		return 0;
@@ -1733,7 +1733,7 @@
 		return -EBADF;
 	}
 
-	ctx = (pfm_context_t *)filp->private_data;
+	ctx = filp->private_data;
 	if (ctx == NULL) {
 		printk(KERN_ERR "perfmon: pfm_fasync NULL ctx [%d]\n", task_pid_nr(current));
 		return -EBADF;
@@ -1841,7 +1841,7 @@
 		return -EBADF;
 	}
 
-	ctx = (pfm_context_t *)filp->private_data;
+	ctx = filp->private_data;
 	if (ctx == NULL) {
 		printk(KERN_ERR "perfmon: pfm_flush: NULL ctx [%d]\n", task_pid_nr(current));
 		return -EBADF;
@@ -1984,7 +1984,7 @@
 		return -EBADF;
 	}
 	
-	ctx = (pfm_context_t *)filp->private_data;
+	ctx = filp->private_data;
 	if (ctx == NULL) {
 		printk(KERN_ERR "perfmon: pfm_close: NULL ctx [%d]\n", task_pid_nr(current));
 		return -EBADF;
@@ -4907,7 +4907,7 @@
 		goto error_args;
 	}
 
-	ctx = (pfm_context_t *)file->private_data;
+	ctx = file->private_data;
 	if (unlikely(ctx == NULL)) {
 		DPRINT(("no context for fd %d\n", fd));
 		goto error_args;
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index aa8b5fa..79802e5 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -354,6 +354,7 @@
 static const struct file_operations salinfo_event_fops = {
 	.open  = salinfo_event_open,
 	.read  = salinfo_event_read,
+	.llseek = noop_llseek,
 };
 
 static int
@@ -571,6 +572,7 @@
 	.release = salinfo_log_release,
 	.read    = salinfo_log_read,
 	.write   = salinfo_log_write,
+	.llseek  = default_llseek,
 };
 
 static int __cpuinit
@@ -642,7 +644,7 @@
 	for (i = 0; i < ARRAY_SIZE(salinfo_log_name); i++) {
 		data = salinfo_data + i;
 		data->type = i;
-		init_MUTEX(&data->mutex);
+		sema_init(&data->mutex, 1);
 		dir = proc_mkdir(salinfo_log_name[i], salinfo_dir);
 		if (!dir)
 			continue;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 8fb958a..911cf97 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -594,10 +594,6 @@
 	cpu_init();	/* initialize the bootstrap CPU */
 	mmu_context_init();	/* initialize context_id bitmap */
 
-#ifdef CONFIG_ACPI
-	acpi_boot_init();
-#endif
-
 	paravirt_banner();
 	paravirt_arch_setup_console(cmdline_p);
 
diff --git a/arch/ia64/kernel/stacktrace.c b/arch/ia64/kernel/stacktrace.c
new file mode 100644
index 0000000..5af2783
--- /dev/null
+++ b/arch/ia64/kernel/stacktrace.c
@@ -0,0 +1,39 @@
+/*
+ * arch/ia64/kernel/stacktrace.c
+ *
+ * Stack trace management functions
+ *
+ */
+#include <linux/sched.h>
+#include <linux/stacktrace.h>
+#include <linux/module.h>
+
+static void
+ia64_do_save_stack(struct unw_frame_info *info, void *arg)
+{
+	struct stack_trace *trace = arg;
+	unsigned long ip;
+	int skip = trace->skip;
+
+	trace->nr_entries = 0;
+	do {
+		unw_get_ip(info, &ip);
+		if (ip == 0)
+			break;
+		if (skip == 0) {
+			trace->entries[trace->nr_entries++] = ip;
+			if (trace->nr_entries == trace->max_entries)
+				break;
+		} else
+			skip--;
+	} while (unw_unwind(info) >= 0);
+}
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+void save_stack_trace(struct stack_trace *trace)
+{
+	unw_init_running(ia64_do_save_stack, trace);
+}
+EXPORT_SYMBOL(save_stack_trace);
diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c
index b6c0e63..fed6afa 100644
--- a/arch/ia64/kernel/unwind.c
+++ b/arch/ia64/kernel/unwind.c
@@ -1204,10 +1204,10 @@
 static inline unw_hash_index_t
 hash (unsigned long ip)
 {
-#	define hashmagic	0x9e3779b97f4a7c16UL	/* based on (sqrt(5)/2-1)*2^64 */
+	/* magic number = ((sqrt(5)-1)/2)*2^64 */
+	static const unsigned long hashmagic = 0x9e3779b97f4a7c16UL;
 
-	return (ip >> 4)*hashmagic >> (64 - UNW_LOG_HASH_SIZE);
-#undef hashmagic
+	return (ip >> 4) * hashmagic >> (64 - UNW_LOG_HASH_SIZE);
 }
 
 static inline long
@@ -1531,7 +1531,7 @@
 	struct unw_labeled_state *ls, *next;
 	unsigned long ip = info->ip;
 	struct unw_state_record sr;
-	struct unw_table *table;
+	struct unw_table *table, *prev;
 	struct unw_reg_info *r;
 	struct unw_insn insn;
 	u8 *dp, *desc_end;
@@ -1560,11 +1560,26 @@
 
 	STAT(parse_start = ia64_get_itc());
 
+	prev = NULL;
 	for (table = unw.tables; table; table = table->next) {
 		if (ip >= table->start && ip < table->end) {
+			/*
+			 * Leave the kernel unwind table at the very front,
+			 * lest moving it breaks some assumption elsewhere.
+			 * Otherwise, move the matching table to the second
+			 * position in the list so that traversals can benefit
+			 * from commonality in backtrace paths.
+			 */
+			if (prev && prev != unw.tables) {
+				/* unw is safe - we're already spinlocked */
+				prev->next = table->next;
+				table->next = unw.tables->next;
+				unw.tables->next = table;
+			}
 			e = lookup(table, ip - table->segment_base);
 			break;
 		}
+		prev = table;
 	}
 	if (!e) {
 		/* no info, return default unwinder (leaf proc, no mem stack, no saved regs)  */
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index 0c72dd4..a5e500f 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -228,8 +228,8 @@
 
 static struct irq_chip sn_msi_chip = {
 	.name		= "PCI-MSI",
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
 	.ack		= sn_ack_msi_irq,
 #ifdef CONFIG_SMP
 	.set_affinity	= sn_set_msi_irq_affinity,
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index fa1ecee..30862c0 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -860,6 +860,7 @@
 
 static const struct file_operations sn_hwperf_fops = {
 	.unlocked_ioctl = sn_hwperf_ioctl,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice sn_hwperf_dev = {
diff --git a/arch/ia64/xen/xen_pv_ops.c b/arch/ia64/xen/xen_pv_ops.c
index 8adc6a1..3e8d350 100644
--- a/arch/ia64/xen/xen_pv_ops.c
+++ b/arch/ia64/xen/xen_pv_ops.c
@@ -1136,7 +1136,6 @@
 static void __init
 xen_patch_branch(unsigned long tag, unsigned long type)
 {
-	const unsigned long nelem =
-		sizeof(xen_branch_target) / sizeof(xen_branch_target[0]);
-	__paravirt_patch_apply_branch(tag, type, xen_branch_target, nelem);
+	__paravirt_patch_apply_branch(tag, type, xen_branch_target,
+					ARRAY_SIZE(xen_branch_target));
 }
diff --git a/arch/m32r/include/asm/irqflags.h b/arch/m32r/include/asm/irqflags.h
new file mode 100644
index 0000000..1f92d29
--- /dev/null
+++ b/arch/m32r/include/asm/irqflags.h
@@ -0,0 +1,104 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001  Hiroyuki Kondo, Hirokazu Takata, and Hitoshi Yamamoto
+ * Copyright (C) 2004, 2006  Hirokazu Takata <takata at linux-m32r.org>
+ */
+
+#ifndef _ASM_M32R_IRQFLAGS_H
+#define _ASM_M32R_IRQFLAGS_H
+
+#include <linux/types.h>
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile("mvfc %0,psw" : "=r"(flags));
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+#if !defined(CONFIG_CHIP_M32102) && !defined(CONFIG_CHIP_M32104)
+	asm volatile (
+		"clrpsw #0x40 -> nop"
+		: : : "memory");
+#else
+	unsigned long tmpreg0, tmpreg1;
+	asm volatile (
+		"ld24	%0, #0	; Use 32-bit insn.			\n\t"
+		"mvfc	%1, psw	; No interrupt can be accepted here.	\n\t"
+		"mvtc	%0, psw						\n\t"
+		"and3	%0, %1, #0xffbf					\n\t"
+		"mvtc	%0, psw						\n\t"
+		: "=&r" (tmpreg0), "=&r" (tmpreg1)
+		:
+		: "cbit", "memory");
+#endif
+}
+
+static inline void arch_local_irq_enable(void)
+{
+#if !defined(CONFIG_CHIP_M32102) && !defined(CONFIG_CHIP_M32104)
+	asm volatile (
+		"setpsw #0x40 -> nop"
+		: : : "memory");
+#else
+	unsigned long tmpreg;
+	asm volatile (
+		"mvfc	%0, psw;		\n\t"
+		"or3	%0, %0, #0x0040;	\n\t"
+		"mvtc	%0, psw;		\n\t"
+		: "=&r" (tmpreg)
+		:
+		: "cbit", "memory");
+#endif
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+#if !(defined(CONFIG_CHIP_M32102) || defined(CONFIG_CHIP_M32104))
+	asm volatile (
+		"mvfc	%0, psw;	\n\t"
+		"clrpsw	#0x40 -> nop;	\n\t"
+		: "=r" (flags)
+		:
+		: "memory");
+#else
+	unsigned long tmpreg;
+	asm volatile (
+		"ld24	%1, #0		\n\t"
+		"mvfc	%0, psw		\n\t"
+		"mvtc	%1, psw		\n\t"
+		"and3	%1, %0, #0xffbf	\n\t"
+		"mvtc	%1, psw		\n\t"
+		: "=r" (flags), "=&r" (tmpreg)
+		:
+		: "cbit", "memory");
+#endif
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile("mvtc %0,psw"
+		     :
+		     : "r" (flags)
+		     : "cbit", "memory");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & 0x40);
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* _ASM_M32R_IRQFLAGS_H */
diff --git a/arch/m32r/include/asm/system.h b/arch/m32r/include/asm/system.h
index c980f5b..13c4679 100644
--- a/arch/m32r/include/asm/system.h
+++ b/arch/m32r/include/asm/system.h
@@ -11,6 +11,7 @@
  */
 
 #include <linux/compiler.h>
+#include <linux/irqflags.h>
 #include <asm/assembler.h>
 
 #ifdef __KERNEL__
@@ -54,71 +55,6 @@
 	); \
 } while(0)
 
-/* Interrupt Control */
-#if !defined(CONFIG_CHIP_M32102) && !defined(CONFIG_CHIP_M32104)
-#define local_irq_enable() \
-	__asm__ __volatile__ ("setpsw #0x40 -> nop": : :"memory")
-#define local_irq_disable() \
-	__asm__ __volatile__ ("clrpsw #0x40 -> nop": : :"memory")
-#else	/* CONFIG_CHIP_M32102 || CONFIG_CHIP_M32104 */
-static inline void local_irq_enable(void)
-{
-	unsigned long tmpreg;
-	__asm__ __volatile__(
-		"mvfc	%0, psw;		\n\t"
-		"or3	%0, %0, #0x0040;	\n\t"
-		"mvtc	%0, psw;		\n\t"
-	: "=&r" (tmpreg) : : "cbit", "memory");
-}
-
-static inline void local_irq_disable(void)
-{
-	unsigned long tmpreg0, tmpreg1;
-	__asm__ __volatile__(
-		"ld24	%0, #0	; Use 32-bit insn. \n\t"
-		"mvfc	%1, psw	; No interrupt can be accepted here. \n\t"
-		"mvtc	%0, psw	\n\t"
-		"and3	%0, %1, #0xffbf	\n\t"
-		"mvtc	%0, psw	\n\t"
-	: "=&r" (tmpreg0), "=&r" (tmpreg1) : : "cbit", "memory");
-}
-#endif	/* CONFIG_CHIP_M32102 || CONFIG_CHIP_M32104 */
-
-#define local_save_flags(x) \
-	__asm__ __volatile__("mvfc %0,psw" : "=r"(x) : /* no input */)
-
-#define local_irq_restore(x) \
-	__asm__ __volatile__("mvtc %0,psw" : /* no outputs */ \
-		: "r" (x) : "cbit", "memory")
-
-#if !(defined(CONFIG_CHIP_M32102) || defined(CONFIG_CHIP_M32104))
-#define local_irq_save(x)				\
-	__asm__ __volatile__(				\
-  		"mvfc	%0, psw;		\n\t"	\
-	  	"clrpsw	#0x40 -> nop;		\n\t"	\
-  		: "=r" (x) : /* no input */ : "memory")
-#else	/* CONFIG_CHIP_M32102 || CONFIG_CHIP_M32104 */
-#define local_irq_save(x) 				\
-	({						\
-		unsigned long tmpreg;			\
-		__asm__ __volatile__( 			\
-			"ld24	%1, #0 \n\t" 		\
-			"mvfc	%0, psw \n\t"		\
-			"mvtc	%1, psw \n\t"		\
-			"and3	%1, %0, #0xffbf \n\t"	\
-			"mvtc	%1, psw \n\t" 		\
-			: "=r" (x), "=&r" (tmpreg)	\
-			: : "cbit", "memory");		\
-	})
-#endif	/* CONFIG_CHIP_M32102 || CONFIG_CHIP_M32104 */
-
-#define irqs_disabled()					\
-	({						\
-		unsigned long flags;			\
-		local_save_flags(flags);		\
-		!(flags & 0x40);			\
-	})
-
 #define nop()	__asm__ __volatile__ ("nop" : : )
 
 #define xchg(ptr, x)							\
diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c
index 3c71f77..7db26f1 100644
--- a/arch/m32r/kernel/irq.c
+++ b/arch/m32r/kernel/irq.c
@@ -51,7 +51,7 @@
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)
diff --git a/arch/m32r/platforms/m32104ut/setup.c b/arch/m32r/platforms/m32104ut/setup.c
index 922fdfd..402a59d 100644
--- a/arch/m32r/platforms/m32104ut/setup.c
+++ b/arch/m32r/platforms/m32104ut/setup.c
@@ -65,7 +65,7 @@
 
 static struct irq_chip m32104ut_irq_type =
 {
-	.typename = "M32104UT-IRQ",
+	.name = "M32104UT-IRQ",
 	.startup = startup_m32104ut_irq,
 	.shutdown = shutdown_m32104ut_irq,
 	.enable = enable_m32104ut_irq,
diff --git a/arch/m32r/platforms/m32700ut/setup.c b/arch/m32r/platforms/m32700ut/setup.c
index 9c1bc74..80b1a02 100644
--- a/arch/m32r/platforms/m32700ut/setup.c
+++ b/arch/m32r/platforms/m32700ut/setup.c
@@ -71,7 +71,7 @@
 
 static struct irq_chip m32700ut_irq_type =
 {
-	.typename = "M32700UT-IRQ",
+	.name = "M32700UT-IRQ",
 	.startup = startup_m32700ut_irq,
 	.shutdown = shutdown_m32700ut_irq,
 	.enable = enable_m32700ut_irq,
@@ -148,7 +148,7 @@
 
 static struct irq_chip m32700ut_pld_irq_type =
 {
-	.typename = "M32700UT-PLD-IRQ",
+	.name = "M32700UT-PLD-IRQ",
 	.startup = startup_m32700ut_pld_irq,
 	.shutdown = shutdown_m32700ut_pld_irq,
 	.enable = enable_m32700ut_pld_irq,
@@ -217,7 +217,7 @@
 
 static struct irq_chip m32700ut_lanpld_irq_type =
 {
-	.typename = "M32700UT-PLD-LAN-IRQ",
+	.name = "M32700UT-PLD-LAN-IRQ",
 	.startup = startup_m32700ut_lanpld_irq,
 	.shutdown = shutdown_m32700ut_lanpld_irq,
 	.enable = enable_m32700ut_lanpld_irq,
@@ -286,7 +286,7 @@
 
 static struct irq_chip m32700ut_lcdpld_irq_type =
 {
-	.typename = "M32700UT-PLD-LCD-IRQ",
+	.name = "M32700UT-PLD-LCD-IRQ",
 	.startup = startup_m32700ut_lcdpld_irq,
 	.shutdown = shutdown_m32700ut_lcdpld_irq,
 	.enable = enable_m32700ut_lcdpld_irq,
diff --git a/arch/m32r/platforms/mappi/setup.c b/arch/m32r/platforms/mappi/setup.c
index fb4b177..ea00c84 100644
--- a/arch/m32r/platforms/mappi/setup.c
+++ b/arch/m32r/platforms/mappi/setup.c
@@ -65,7 +65,7 @@
 
 static struct irq_chip mappi_irq_type =
 {
-	.typename = "MAPPI-IRQ",
+	.name = "MAPPI-IRQ",
 	.startup = startup_mappi_irq,
 	.shutdown = shutdown_mappi_irq,
 	.enable = enable_mappi_irq,
diff --git a/arch/m32r/platforms/mappi2/setup.c b/arch/m32r/platforms/mappi2/setup.c
index 6a65eda..c049376 100644
--- a/arch/m32r/platforms/mappi2/setup.c
+++ b/arch/m32r/platforms/mappi2/setup.c
@@ -72,7 +72,7 @@
 
 static struct irq_chip mappi2_irq_type =
 {
-	.typename = "MAPPI2-IRQ",
+	.name = "MAPPI2-IRQ",
 	.startup = startup_mappi2_irq,
 	.shutdown = shutdown_mappi2_irq,
 	.enable = enable_mappi2_irq,
diff --git a/arch/m32r/platforms/mappi3/setup.c b/arch/m32r/platforms/mappi3/setup.c
index 9c337ae..882de25 100644
--- a/arch/m32r/platforms/mappi3/setup.c
+++ b/arch/m32r/platforms/mappi3/setup.c
@@ -72,7 +72,7 @@
 
 static struct irq_chip mappi3_irq_type =
 {
-	.typename = "MAPPI3-IRQ",
+	.name = "MAPPI3-IRQ",
 	.startup = startup_mappi3_irq,
 	.shutdown = shutdown_mappi3_irq,
 	.enable = enable_mappi3_irq,
diff --git a/arch/m32r/platforms/oaks32r/setup.c b/arch/m32r/platforms/oaks32r/setup.c
index ed86574..d11d93b 100644
--- a/arch/m32r/platforms/oaks32r/setup.c
+++ b/arch/m32r/platforms/oaks32r/setup.c
@@ -63,7 +63,7 @@
 
 static struct irq_chip oaks32r_irq_type =
 {
-	.typename = "OAKS32R-IRQ",
+	.name = "OAKS32R-IRQ",
 	.startup = startup_oaks32r_irq,
 	.shutdown = shutdown_oaks32r_irq,
 	.enable = enable_oaks32r_irq,
diff --git a/arch/m32r/platforms/opsput/setup.c b/arch/m32r/platforms/opsput/setup.c
index 80d6806..5f3402a 100644
--- a/arch/m32r/platforms/opsput/setup.c
+++ b/arch/m32r/platforms/opsput/setup.c
@@ -72,7 +72,7 @@
 
 static struct irq_chip opsput_irq_type =
 {
-	.typename = "OPSPUT-IRQ",
+	.name = "OPSPUT-IRQ",
 	.startup = startup_opsput_irq,
 	.shutdown = shutdown_opsput_irq,
 	.enable = enable_opsput_irq,
@@ -149,7 +149,7 @@
 
 static struct irq_chip opsput_pld_irq_type =
 {
-	.typename = "OPSPUT-PLD-IRQ",
+	.name = "OPSPUT-PLD-IRQ",
 	.startup = startup_opsput_pld_irq,
 	.shutdown = shutdown_opsput_pld_irq,
 	.enable = enable_opsput_pld_irq,
@@ -218,7 +218,7 @@
 
 static struct irq_chip opsput_lanpld_irq_type =
 {
-	.typename = "OPSPUT-PLD-LAN-IRQ",
+	.name = "OPSPUT-PLD-LAN-IRQ",
 	.startup = startup_opsput_lanpld_irq,
 	.shutdown = shutdown_opsput_lanpld_irq,
 	.enable = enable_opsput_lanpld_irq,
diff --git a/arch/m32r/platforms/usrv/setup.c b/arch/m32r/platforms/usrv/setup.c
index 7573026..1beac7a 100644
--- a/arch/m32r/platforms/usrv/setup.c
+++ b/arch/m32r/platforms/usrv/setup.c
@@ -63,7 +63,7 @@
 
 static struct irq_chip mappi_irq_type =
 {
-	.typename = "M32700-IRQ",
+	.name = "M32700-IRQ",
 	.startup = startup_mappi_irq,
 	.shutdown = shutdown_mappi_irq,
 	.enable = enable_mappi_irq,
@@ -136,7 +136,7 @@
 
 static struct irq_chip m32700ut_pld_irq_type =
 {
-	.typename = "USRV-PLD-IRQ",
+	.name = "USRV-PLD-IRQ",
 	.startup = startup_m32700ut_pld_irq,
 	.shutdown = shutdown_m32700ut_pld_irq,
 	.enable = enable_m32700ut_pld_irq,
diff --git a/arch/m68k/bvme6000/rtc.c b/arch/m68k/bvme6000/rtc.c
index cb8617b..1c4d4c7 100644
--- a/arch/m68k/bvme6000/rtc.c
+++ b/arch/m68k/bvme6000/rtc.c
@@ -155,6 +155,7 @@
 	.unlocked_ioctl	= rtc_ioctl,
 	.open		= rtc_open,
 	.release	= rtc_release,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice rtc_dev = {
diff --git a/arch/m68k/include/asm/entry_no.h b/arch/m68k/include/asm/entry_no.h
index 907ed03..80e4149 100644
--- a/arch/m68k/include/asm/entry_no.h
+++ b/arch/m68k/include/asm/entry_no.h
@@ -28,7 +28,7 @@
  *			M68K		  COLDFIRE
  */
 
-#define ALLOWINT 0xf8ff
+#define ALLOWINT (~0x700)
 
 #ifdef __ASSEMBLY__
 
diff --git a/arch/m68k/include/asm/irqflags.h b/arch/m68k/include/asm/irqflags.h
new file mode 100644
index 0000000..4a5b284
--- /dev/null
+++ b/arch/m68k/include/asm/irqflags.h
@@ -0,0 +1,76 @@
+#ifndef _M68K_IRQFLAGS_H
+#define _M68K_IRQFLAGS_H
+
+#include <linux/types.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <asm/thread_info.h>
+#include <asm/entry.h>
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile ("movew %%sr,%0" : "=d" (flags) : : "memory");
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+#ifdef CONFIG_COLDFIRE
+	asm volatile (
+		"move	%/sr,%%d0	\n\t"
+		"ori.l	#0x0700,%%d0	\n\t"
+		"move	%%d0,%/sr	\n"
+		: /* no outputs */
+		:
+		: "cc", "%d0", "memory");
+#else
+	asm volatile ("oriw  #0x0700,%%sr" : : : "memory");
+#endif
+}
+
+static inline void arch_local_irq_enable(void)
+{
+#if defined(CONFIG_COLDFIRE)
+	asm volatile (
+		"move	%/sr,%%d0	\n\t"
+		"andi.l	#0xf8ff,%%d0	\n\t"
+		"move	%%d0,%/sr	\n"
+		: /* no outputs */
+		:
+		: "cc", "%d0", "memory");
+#else
+# if defined(CONFIG_MMU)
+	if (MACH_IS_Q40 || !hardirq_count())
+# endif
+		asm volatile (
+			"andiw %0,%%sr"
+			:
+			: "i" (ALLOWINT)
+			: "memory");
+#endif
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = arch_local_save_flags();
+	arch_local_irq_disable();
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile ("movew %0,%%sr" : : "d" (flags) : "memory");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & ~ALLOWINT) != 0;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* _M68K_IRQFLAGS_H */
diff --git a/arch/m68k/include/asm/system_mm.h b/arch/m68k/include/asm/system_mm.h
index 485daec..47b01f47 100644
--- a/arch/m68k/include/asm/system_mm.h
+++ b/arch/m68k/include/asm/system_mm.h
@@ -3,6 +3,7 @@
 
 #include <linux/linkage.h>
 #include <linux/kernel.h>
+#include <linux/irqflags.h>
 #include <asm/segment.h>
 #include <asm/entry.h>
 
@@ -62,30 +63,6 @@
 #define smp_wmb()	barrier()
 #define smp_read_barrier_depends()	((void)0)
 
-/* interrupt control.. */
-#if 0
-#define local_irq_enable() asm volatile ("andiw %0,%%sr": : "i" (ALLOWINT) : "memory")
-#else
-#include <linux/hardirq.h>
-#define local_irq_enable() ({							\
-	if (MACH_IS_Q40 || !hardirq_count())					\
-		asm volatile ("andiw %0,%%sr": : "i" (ALLOWINT) : "memory");	\
-})
-#endif
-#define local_irq_disable() asm volatile ("oriw  #0x0700,%%sr": : : "memory")
-#define local_save_flags(x) asm volatile ("movew %%sr,%0":"=d" (x) : : "memory")
-#define local_irq_restore(x) asm volatile ("movew %0,%%sr": :"d" (x) : "memory")
-
-static inline int irqs_disabled(void)
-{
-	unsigned long flags;
-	local_save_flags(flags);
-	return flags & ~ALLOWINT;
-}
-
-/* For spinlocks etc */
-#define local_irq_save(x)	({ local_save_flags(x); local_irq_disable(); })
-
 #define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
 struct __xchg_dummy { unsigned long a[100]; };
diff --git a/arch/m68k/include/asm/system_no.h b/arch/m68k/include/asm/system_no.h
index 08f31bd..6fe9f93 100644
--- a/arch/m68k/include/asm/system_no.h
+++ b/arch/m68k/include/asm/system_no.h
@@ -2,6 +2,7 @@
 #define _M68KNOMMU_SYSTEM_H
 
 #include <linux/linkage.h>
+#include <linux/irqflags.h>
 #include <asm/segment.h>
 #include <asm/entry.h>
 
@@ -46,54 +47,6 @@
   (last) = _last;						\
 }
 
-#ifdef CONFIG_COLDFIRE
-#define local_irq_enable() __asm__ __volatile__ (		\
-	"move %/sr,%%d0\n\t"					\
-	"andi.l #0xf8ff,%%d0\n\t"				\
-	"move %%d0,%/sr\n"					\
-	: /* no outputs */					\
-	:							\
-        : "cc", "%d0", "memory")
-#define local_irq_disable() __asm__ __volatile__ (		\
-	"move %/sr,%%d0\n\t"					\
-	"ori.l #0x0700,%%d0\n\t"				\
-	"move %%d0,%/sr\n"					\
-	: /* no outputs */					\
-	:							\
-	: "cc", "%d0", "memory")
-/* For spinlocks etc */
-#define local_irq_save(x) __asm__ __volatile__ (		\
-	"movew %%sr,%0\n\t"					\
-	"movew #0x0700,%%d0\n\t"				\
-	"or.l  %0,%%d0\n\t"					\
-	"movew %%d0,%/sr"					\
-	: "=d" (x)						\
-	:							\
-	: "cc", "%d0", "memory")
-#else
-
-/* portable version */ /* FIXME - see entry.h*/
-#define ALLOWINT 0xf8ff
-
-#define local_irq_enable() asm volatile ("andiw %0,%%sr": : "i" (ALLOWINT) : "memory")
-#define local_irq_disable() asm volatile ("oriw  #0x0700,%%sr": : : "memory")
-#endif
-
-#define local_save_flags(x) asm volatile ("movew %%sr,%0":"=d" (x) : : "memory")
-#define local_irq_restore(x) asm volatile ("movew %0,%%sr": :"d" (x) : "memory")
-
-/* For spinlocks etc */
-#ifndef local_irq_save
-#define local_irq_save(x) do { local_save_flags(x); local_irq_disable(); } while (0)
-#endif
-
-#define	irqs_disabled()			\
-({					\
-	unsigned long flags;		\
-	local_save_flags(flags);	\
-	((flags & 0x0700) == 0x0700);	\
-})
-
 #define iret() __asm__ __volatile__ ("rte": : :"memory", "sp", "cc")
 
 /*
@@ -197,12 +150,4 @@
 #define arch_align_stack(x) (x)
 
 
-static inline int irqs_disabled_flags(unsigned long flags)
-{
-	if (flags & 0x0700)
-		return 0;
-	else
-		return 1;
-}
-
 #endif /* _M68KNOMMU_SYSTEM_H */
diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c
index 11ac6f6..39c79eb 100644
--- a/arch/m68k/mvme16x/rtc.c
+++ b/arch/m68k/mvme16x/rtc.c
@@ -144,6 +144,7 @@
 	.unlocked_ioctl	= rtc_ioctl,
 	.open		= rtc_open,
 	.release	= rtc_release,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice rtc_dev=
diff --git a/arch/m68knommu/kernel/asm-offsets.c b/arch/m68knommu/kernel/asm-offsets.c
index 9a8876f..2433502 100644
--- a/arch/m68knommu/kernel/asm-offsets.c
+++ b/arch/m68knommu/kernel/asm-offsets.c
@@ -74,8 +74,6 @@
 
 	DEFINE(PT_PTRACED, PT_PTRACED);
 
-	DEFINE(THREAD_SIZE, THREAD_SIZE);
-
 	/* Offsets in thread_info structure */
 	DEFINE(TI_TASK, offsetof(struct thread_info, task));
 	DEFINE(TI_EXECDOMAIN, offsetof(struct thread_info, exec_domain));
diff --git a/arch/m68knommu/platform/coldfire/head.S b/arch/m68knommu/platform/coldfire/head.S
index 4b91aa2..0b2d7c7 100644
--- a/arch/m68knommu/platform/coldfire/head.S
+++ b/arch/m68knommu/platform/coldfire/head.S
@@ -15,6 +15,7 @@
 #include <asm/coldfire.h>
 #include <asm/mcfcache.h>
 #include <asm/mcfsim.h>
+#include <asm/thread_info.h>
 
 /*****************************************************************************/
 
diff --git a/arch/microblaze/include/asm/irqflags.h b/arch/microblaze/include/asm/irqflags.h
index 2c38c6d..5fd3190 100644
--- a/arch/microblaze/include/asm/irqflags.h
+++ b/arch/microblaze/include/asm/irqflags.h
@@ -9,103 +9,114 @@
 #ifndef _ASM_MICROBLAZE_IRQFLAGS_H
 #define _ASM_MICROBLAZE_IRQFLAGS_H
 
-#include <linux/irqflags.h>
+#include <linux/types.h>
 #include <asm/registers.h>
 
-# if CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR
+#ifdef CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR
 
-# define raw_local_irq_save(flags)			\
-	do {						\
-		asm volatile ("	msrclr %0, %1;		\
-				nop;"			\
-				: "=r"(flags)		\
-				: "i"(MSR_IE)		\
-				: "memory");		\
-	} while (0)
-
-# define raw_local_irq_disable()			\
-	do {						\
-		asm volatile ("	msrclr r0, %0;		\
-				nop;"			\
-				:			\
-				: "i"(MSR_IE)		\
-				: "memory");		\
-	} while (0)
-
-# define raw_local_irq_enable()				\
-	do {						\
-		asm volatile ("	msrset	r0, %0;		\
-				nop;"			\
-				:			\
-				: "i"(MSR_IE)		\
-				: "memory");		\
-	} while (0)
-
-# else /* CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR == 0 */
-
-# define raw_local_irq_save(flags)				\
-	do {							\
-		register unsigned tmp;				\
-		asm volatile ("	mfs	%0, rmsr;		\
-				nop;				\
-				andi	%1, %0, %2;		\
-				mts	rmsr, %1;		\
-				nop;"				\
-				: "=r"(flags), "=r" (tmp)	\
-				: "i"(~MSR_IE)			\
-				: "memory");			\
-	} while (0)
-
-# define raw_local_irq_disable()				\
-	do {							\
-		register unsigned tmp;				\
-		asm volatile ("	mfs	%0, rmsr;		\
-				nop;				\
-				andi	%0, %0, %1;		\
-				mts	rmsr, %0;		\
-				nop;"			\
-				: "=r"(tmp)			\
-				: "i"(~MSR_IE)			\
-				: "memory");			\
-	} while (0)
-
-# define raw_local_irq_enable()					\
-	do {							\
-		register unsigned tmp;				\
-		asm volatile ("	mfs	%0, rmsr;		\
-				nop;				\
-				ori	%0, %0, %1;		\
-				mts	rmsr, %0;		\
-				nop;"				\
-				: "=r"(tmp)			\
-				: "i"(MSR_IE)			\
-				: "memory");			\
-	} while (0)
-
-# endif /* CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR */
-
-#define raw_local_irq_restore(flags)				\
-	do {							\
-		asm volatile ("	mts	rmsr, %0;		\
-				nop;"				\
-				:				\
-				: "r"(flags)			\
-				: "memory");			\
-	} while (0)
-
-static inline unsigned long get_msr(void)
+static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
-	asm volatile ("	mfs	%0, rmsr;	\
-			nop;"			\
-			: "=r"(flags)		\
-			:			\
-			: "memory");		\
+	asm volatile("	msrclr %0, %1	\n"
+		     "	nop		\n"
+		     : "=r"(flags)
+		     : "i"(MSR_IE)
+		     : "memory");
 	return flags;
 }
 
-#define raw_local_save_flags(flags)	((flags) = get_msr())
-#define raw_irqs_disabled()		((get_msr() & MSR_IE) == 0)
-#define raw_irqs_disabled_flags(flags)	((flags & MSR_IE) == 0)
+static inline void arch_local_irq_disable(void)
+{
+	/* this uses r0 without declaring it - is that correct? */
+	asm volatile("	msrclr r0, %0	\n"
+		     "	nop		\n"
+		     :
+		     : "i"(MSR_IE)
+		     : "memory");
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	/* this uses r0 without declaring it - is that correct? */
+	asm volatile("	msrset	r0, %0	\n"
+		     "	nop		\n"
+		     :
+		     : "i"(MSR_IE)
+		     : "memory");
+}
+
+#else /* !CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR */
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags, tmp;
+	asm volatile ("	mfs	%0, rmsr	\n"
+		      "	nop			\n"
+		      "	andi	%1, %0, %2	\n"
+		      "	mts	rmsr, %1	\n"
+		      "	nop			\n"
+		      : "=r"(flags), "=r"(tmp)
+		      : "i"(~MSR_IE)
+		      : "memory");
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	unsigned long tmp;
+	asm volatile("	mfs	%0, rmsr	\n"
+		     "	nop			\n"
+		     "	andi	%0, %0, %1	\n"
+		     "	mts	rmsr, %0	\n"
+		     "	nop			\n"
+		     : "=r"(tmp)
+		     : "i"(~MSR_IE)
+		     : "memory");
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	unsigned long tmp;
+	asm volatile("	mfs	%0, rmsr	\n"
+		     "	nop			\n"
+		     "	ori	%0, %0, %1	\n"
+		     "	mts	rmsr, %0	\n"
+		     "	nop			\n"
+		     : "=r"(tmp)
+		     : "i"(MSR_IE)
+		     : "memory");
+}
+
+#endif /* CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR */
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile("	mfs	%0, rmsr	\n"
+		     "	nop			\n"
+		     : "=r"(flags)
+		     :
+		     : "memory");
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile("	mts	rmsr, %0	\n"
+		     "	nop			\n"
+		     :
+		     : "r"(flags)
+		     : "memory");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & MSR_IE) == 0;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
 
 #endif /* _ASM_MICROBLAZE_IRQFLAGS_H */
diff --git a/arch/microblaze/include/asm/memblock.h b/arch/microblaze/include/asm/memblock.h
index f9c2fa3..20a8e25 100644
--- a/arch/microblaze/include/asm/memblock.h
+++ b/arch/microblaze/include/asm/memblock.h
@@ -9,9 +9,6 @@
 #ifndef _ASM_MICROBLAZE_MEMBLOCK_H
 #define _ASM_MICROBLAZE_MEMBLOCK_H
 
-/* MEMBLOCK limit is OFF */
-#define MEMBLOCK_REAL_LIMIT	0xFFFFFFFF
-
 #endif /* _ASM_MICROBLAZE_MEMBLOCK_H */
 
 
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 65eb004..c843786 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -70,16 +70,16 @@
 
 void __init setup_memory(void)
 {
-	int i;
 	unsigned long map_size;
+	struct memblock_region *reg;
+
 #ifndef CONFIG_MMU
 	u32 kernel_align_start, kernel_align_size;
 
 	/* Find main memory where is the kernel */
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		memory_start = (u32) memblock.memory.region[i].base;
-		memory_end = (u32) memblock.memory.region[i].base
-				+ (u32) memblock.memory.region[i].size;
+	for_each_memblock(memory, reg) {
+		memory_start = (u32)reg->base;
+		memory_end = (u32) reg->base + reg->size;
 		if ((memory_start <= (u32)_text) &&
 					((u32)_text <= memory_end)) {
 			memory_size = memory_end - memory_start;
@@ -142,12 +142,10 @@
 	free_bootmem(memory_start, memory_size);
 
 	/* reserve allocate blocks */
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		pr_debug("reserved %d - 0x%08x-0x%08x\n", i,
-			(u32) memblock.reserved.region[i].base,
-			(u32) memblock_size_bytes(&memblock.reserved, i));
-		reserve_bootmem(memblock.reserved.region[i].base,
-			memblock_size_bytes(&memblock.reserved, i) - 1, BOOTMEM_DEFAULT);
+	for_each_memblock(reserved, reg) {
+		pr_debug("reserved - 0x%08x-0x%08x\n",
+			 (u32) reg->base, (u32) reg->size);
+		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
 	}
 #ifdef CONFIG_MMU
 	init_bootmem_done = 1;
@@ -230,7 +228,7 @@
 		if (maxmem && memory_size > maxmem) {
 			memory_size = maxmem;
 			memory_end = memory_start + memory_size;
-			memblock.memory.region[0].size = memory_size;
+			memblock.memory.regions[0].size = memory_size;
 		}
 	}
 }
@@ -273,14 +271,14 @@
 		machine_restart(NULL);
 	}
 
-	if ((u32) memblock.memory.region[0].size < 0x1000000) {
+	if ((u32) memblock.memory.regions[0].size < 0x1000000) {
 		printk(KERN_EMERG "Memory must be greater than 16MB\n");
 		machine_restart(NULL);
 	}
 	/* Find main memory where the kernel is */
-	memory_start = (u32) memblock.memory.region[0].base;
-	memory_end = (u32) memblock.memory.region[0].base +
-				(u32) memblock.memory.region[0].size;
+	memory_start = (u32) memblock.memory.regions[0].base;
+	memory_end = (u32) memblock.memory.regions[0].base +
+				(u32) memblock.memory.regions[0].size;
 	memory_size = memory_end - memory_start;
 
 	mm_cmdline_setup(); /* FIXME parse args from command line - not used */
diff --git a/arch/mips/alchemy/devboards/bcsr.c b/arch/mips/alchemy/devboards/bcsr.c
index 3bc4fd2..c52af88 100644
--- a/arch/mips/alchemy/devboards/bcsr.c
+++ b/arch/mips/alchemy/devboards/bcsr.c
@@ -10,6 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
+#include <linux/irq.h>
 #include <asm/addrspace.h>
 #include <asm/io.h>
 #include <asm/mach-db1x00/bcsr.h>
diff --git a/arch/mips/ar7/irq.c b/arch/mips/ar7/irq.c
index c781556..4ec2642 100644
--- a/arch/mips/ar7/irq.c
+++ b/arch/mips/ar7/irq.c
@@ -19,6 +19,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c
index a0c5cd1..3be87f2 100644
--- a/arch/mips/bcm63xx/irq.c
+++ b/arch/mips/bcm63xx/irq.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/irq.h>
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
 #include <bcm63xx_cpu.h>
diff --git a/arch/mips/cavium-octeon/serial.c b/arch/mips/cavium-octeon/serial.c
index 638adab..12dbf53 100644
--- a/arch/mips/cavium-octeon/serial.c
+++ b/arch/mips/cavium-octeon/serial.c
@@ -13,6 +13,7 @@
 #include <linux/serial_8250.h>
 #include <linux/serial_reg.h>
 #include <linux/tty.h>
+#include <linux/irq.h>
 
 #include <asm/time.h>
 
diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c
index bd5431e..fa45e92 100644
--- a/arch/mips/dec/setup.c
+++ b/arch/mips/dec/setup.c
@@ -18,6 +18,7 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/pm.h>
+#include <linux/irq.h>
 
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index 701ec0b..9ef3b0d 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -17,7 +17,7 @@
 #include <asm/hazards.h>
 
 __asm__(
-	"	.macro	raw_local_irq_enable				\n"
+	"	.macro	arch_local_irq_enable				\n"
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
@@ -40,7 +40,7 @@
 
 extern void smtc_ipi_replay(void);
 
-static inline void raw_local_irq_enable(void)
+static inline void arch_local_irq_enable(void)
 {
 #ifdef CONFIG_MIPS_MT_SMTC
 	/*
@@ -50,7 +50,7 @@
 	smtc_ipi_replay();
 #endif
 	__asm__ __volatile__(
-		"raw_local_irq_enable"
+		"arch_local_irq_enable"
 		: /* no outputs */
 		: /* no inputs */
 		: "memory");
@@ -76,7 +76,7 @@
  * Workaround: mask EXL bit of the result or place a nop before mfc0.
  */
 __asm__(
-	"	.macro	raw_local_irq_disable\n"
+	"	.macro	arch_local_irq_disable\n"
 	"	.set	push						\n"
 	"	.set	noat						\n"
 #ifdef CONFIG_MIPS_MT_SMTC
@@ -97,17 +97,17 @@
 	"	.set	pop						\n"
 	"	.endm							\n");
 
-static inline void raw_local_irq_disable(void)
+static inline void arch_local_irq_disable(void)
 {
 	__asm__ __volatile__(
-		"raw_local_irq_disable"
+		"arch_local_irq_disable"
 		: /* no outputs */
 		: /* no inputs */
 		: "memory");
 }
 
 __asm__(
-	"	.macro	raw_local_save_flags flags			\n"
+	"	.macro	arch_local_save_flags flags			\n"
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 #ifdef CONFIG_MIPS_MT_SMTC
@@ -118,13 +118,15 @@
 	"	.set	pop						\n"
 	"	.endm							\n");
 
-#define raw_local_save_flags(x)						\
-__asm__ __volatile__(							\
-	"raw_local_save_flags %0"					\
-	: "=r" (x))
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile("arch_local_save_flags %0" : "=r" (flags));
+	return flags;
+}
 
 __asm__(
-	"	.macro	raw_local_irq_save result			\n"
+	"	.macro	arch_local_irq_save result			\n"
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
@@ -148,15 +150,18 @@
 	"	.set	pop						\n"
 	"	.endm							\n");
 
-#define raw_local_irq_save(x)						\
-__asm__ __volatile__(							\
-	"raw_local_irq_save\t%0"					\
-	: "=r" (x)							\
-	: /* no inputs */						\
-	: "memory")
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+	asm volatile("arch_local_irq_save\t%0"
+		     : "=r" (flags)
+		     : /* no inputs */
+		     : "memory");
+	return flags;
+}
 
 __asm__(
-	"	.macro	raw_local_irq_restore flags			\n"
+	"	.macro	arch_local_irq_restore flags			\n"
 	"	.set	push						\n"
 	"	.set	noreorder					\n"
 	"	.set	noat						\n"
@@ -196,7 +201,7 @@
 	"	.endm							\n");
 
 
-static inline void raw_local_irq_restore(unsigned long flags)
+static inline void arch_local_irq_restore(unsigned long flags)
 {
 	unsigned long __tmp1;
 
@@ -211,24 +216,24 @@
 #endif
 
 	__asm__ __volatile__(
-		"raw_local_irq_restore\t%0"
+		"arch_local_irq_restore\t%0"
 		: "=r" (__tmp1)
 		: "0" (flags)
 		: "memory");
 }
 
-static inline void __raw_local_irq_restore(unsigned long flags)
+static inline void __arch_local_irq_restore(unsigned long flags)
 {
 	unsigned long __tmp1;
 
 	__asm__ __volatile__(
-		"raw_local_irq_restore\t%0"
+		"arch_local_irq_restore\t%0"
 		: "=r" (__tmp1)
 		: "0" (flags)
 		: "memory");
 }
 
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 #ifdef CONFIG_MIPS_MT_SMTC
 	/*
diff --git a/arch/mips/include/asm/mach-loongson/loongson.h b/arch/mips/include/asm/mach-loongson/loongson.h
index cb6985f..1e29b9d 100644
--- a/arch/mips/include/asm/mach-loongson/loongson.h
+++ b/arch/mips/include/asm/mach-loongson/loongson.h
@@ -13,6 +13,7 @@
 
 #include <linux/io.h>
 #include <linux/init.h>
+#include <linux/irq.h>
 
 /* loongson internal northbridge initialization */
 extern void bonito_irq_init(void);
diff --git a/arch/mips/jazz/irq.c b/arch/mips/jazz/irq.c
index ee18028..35b3e2f 100644
--- a/arch/mips/jazz/irq.c
+++ b/arch/mips/jazz/irq.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/smp.h>
 #include <linux/spinlock.h>
+#include <linux/irq.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/i8253.h>
diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c
index bfea327..36c3898 100644
--- a/arch/mips/kernel/cevt-bcm1480.c
+++ b/arch/mips/kernel/cevt-bcm1480.c
@@ -19,6 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
 #include <linux/smp.h>
+#include <linux/irq.h>
 
 #include <asm/addrspace.h>
 #include <asm/io.h>
diff --git a/arch/mips/kernel/cevt-ds1287.c b/arch/mips/kernel/cevt-ds1287.c
index 00a4da2..939157e 100644
--- a/arch/mips/kernel/cevt-ds1287.c
+++ b/arch/mips/kernel/cevt-ds1287.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/mc146818rtc.h>
+#include <linux/irq.h>
 
 #include <asm/time.h>
 
diff --git a/arch/mips/kernel/cevt-gt641xx.c b/arch/mips/kernel/cevt-gt641xx.c
index 392ef37..339f363 100644
--- a/arch/mips/kernel/cevt-gt641xx.c
+++ b/arch/mips/kernel/cevt-gt641xx.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
+#include <linux/irq.h>
 
 #include <asm/gt64120.h>
 #include <asm/time.h>
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 2a4d50f..2f4d7a9 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -10,6 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
 #include <linux/smp.h>
+#include <linux/irq.h>
 
 #include <asm/smtc_ipi.h>
 #include <asm/time.h>
diff --git a/arch/mips/kernel/cevt-sb1250.c b/arch/mips/kernel/cevt-sb1250.c
index da78eea..590c54f 100644
--- a/arch/mips/kernel/cevt-sb1250.c
+++ b/arch/mips/kernel/cevt-sb1250.c
@@ -17,6 +17,7 @@
  */
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/percpu.h>
 #include <linux/smp.h>
 
diff --git a/arch/mips/kernel/cevt-smtc.c b/arch/mips/kernel/cevt-smtc.c
index b102e4f..2e72d30 100644
--- a/arch/mips/kernel/cevt-smtc.c
+++ b/arch/mips/kernel/cevt-smtc.c
@@ -11,6 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
 #include <linux/smp.h>
+#include <linux/irq.h>
 
 #include <asm/smtc_ipi.h>
 #include <asm/time.h>
diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c
index 218ee6b..0b73773 100644
--- a/arch/mips/kernel/cevt-txx9.c
+++ b/arch/mips/kernel/cevt-txx9.c
@@ -13,6 +13,7 @@
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/time.h>
 #include <asm/txx9tmr.h>
 
diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c
index 9479406..2392a7a2 100644
--- a/arch/mips/kernel/i8253.c
+++ b/arch/mips/kernel/i8253.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/smp.h>
 #include <linux/spinlock.h>
+#include <linux/irq.h>
 
 #include <asm/delay.h>
 #include <asm/i8253.h>
diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c
index 2779911..c58176c 100644
--- a/arch/mips/kernel/i8259.c
+++ b/arch/mips/kernel/i8259.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
 #include <linux/sysdev.h>
+#include <linux/irq.h>
 
 #include <asm/i8259.h>
 #include <asm/io.h>
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 82ba9f6..1774271 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -3,11 +3,11 @@
 #include <linux/bitmap.h>
 #include <linux/init.h>
 #include <linux/smp.h>
+#include <linux/irq.h>
 
 #include <asm/io.h>
 #include <asm/gic.h>
 #include <asm/gcmpregs.h>
-#include <asm/irq.h>
 #include <linux/hardirq.h>
 #include <asm-generic/bitops/find.h>
 
diff --git a/arch/mips/kernel/irq-rm7000.c b/arch/mips/kernel/irq-rm7000.c
index fb50cc7..9731e8b4 100644
--- a/arch/mips/kernel/irq-rm7000.c
+++ b/arch/mips/kernel/irq-rm7000.c
@@ -11,6 +11,7 @@
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel.h>
 
 #include <asm/irq_cpu.h>
diff --git a/arch/mips/kernel/irq-rm9000.c b/arch/mips/kernel/irq-rm9000.c
index b47e461..b7e4025 100644
--- a/arch/mips/kernel/irq-rm9000.c
+++ b/arch/mips/kernel/irq-rm9000.c
@@ -11,6 +11,7 @@
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 
diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c
index 55c8a3c..0262abe 100644
--- a/arch/mips/kernel/irq_cpu.c
+++ b/arch/mips/kernel/irq_cpu.c
@@ -30,6 +30,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/irq.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
diff --git a/arch/mips/kernel/irq_txx9.c b/arch/mips/kernel/irq_txx9.c
index 9b78029..95a96f6 100644
--- a/arch/mips/kernel/irq_txx9.c
+++ b/arch/mips/kernel/irq_txx9.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/types.h>
+#include <linux/irq.h>
 #include <asm/txx9irq.h>
 
 struct txx9_irc_reg {
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 2340f11..9a526ba 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -103,7 +103,7 @@
 	if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
 		goto out_unlock;
 
-	retval = security_task_setscheduler(p, 0, NULL);
+	retval = security_task_setscheduler(p)
 	if (retval)
 		goto out_unlock;
 
diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index 26f9b9a..557ef72 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -468,7 +468,8 @@
 	.release = file_release,
 	.write =   file_write,
 	.read =    file_read,
-	.poll =    file_poll
+	.poll =    file_poll,
+	.llseek =  noop_llseek,
 };
 
 static struct irqaction rtlx_irq = {
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index cfeb2c1..39c0825 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -1038,7 +1038,7 @@
 		 * but it's more efficient, given that we're already
 		 * running down the IPI queue.
 		 */
-		__raw_local_irq_restore(flags);
+		__arch_local_irq_restore(flags);
 	}
 }
 
@@ -1190,7 +1190,7 @@
 		/*
 		 ** But use a raw restore here to avoid recursion.
 		 */
-		__raw_local_irq_restore(flags);
+		__arch_local_irq_restore(flags);
 
 		if (pipi) {
 			self_ipi(pipi);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 03ec001..d053bf4 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -28,6 +28,7 @@
 #include <linux/kprobes.h>
 #include <linux/notifier.h>
 #include <linux/kdb.h>
+#include <linux/irq.h>
 
 #include <asm/bootinfo.h>
 #include <asm/branch.h>
@@ -51,7 +52,6 @@
 #include <asm/mmu_context.h>
 #include <asm/types.h>
 #include <asm/stacktrace.h>
-#include <asm/irq.h>
 #include <asm/uasm.h>
 
 extern void check_wait(void);
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index 2bd2151..3eb3cde 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -1192,7 +1192,8 @@
 	.owner = THIS_MODULE,
 	.open = vpe_open,
 	.release = vpe_release,
-	.write = vpe_write
+	.write = vpe_write,
+	.llseek = noop_llseek,
 };
 
 /* module wrapper entry points */
diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c
index 72e32a7..4c35301 100644
--- a/arch/mips/mti-malta/malta-platform.c
+++ b/arch/mips/mti-malta/malta-platform.c
@@ -25,6 +25,7 @@
 #include <linux/serial_8250.h>
 #include <linux/mc146818rtc.h>
 #include <linux/module.h>
+#include <linux/irq.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
diff --git a/arch/mips/pci/ops-tx3927.c b/arch/mips/pci/ops-tx3927.c
index 31c1501..6a3bdb5 100644
--- a/arch/mips/pci/ops-tx3927.c
+++ b/arch/mips/pci/ops-tx3927.c
@@ -38,6 +38,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 
 #include <asm/addrspace.h>
 #include <asm/txx9irq.h>
diff --git a/arch/mips/pci/ops-tx4927.c b/arch/mips/pci/ops-tx4927.c
index 5989e74..a1e7e6d 100644
--- a/arch/mips/pci/ops-tx4927.c
+++ b/arch/mips/pci/ops-tx4927.c
@@ -17,6 +17,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/txx9/pci.h>
 #include <asm/txx9/tx4927pcic.h>
 
diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c b/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c
index 94c9c2c..07e71ff 100644
--- a/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c
+++ b/arch/mips/pmc-sierra/msp71xx/msp_irq_cic.c
@@ -14,6 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
+#include <linux/irq.h>
 
 #include <asm/system.h>
 
diff --git a/arch/mips/powertv/asic/irq_asic.c b/arch/mips/powertv/asic/irq_asic.c
index b54d244..e553824 100644
--- a/arch/mips/powertv/asic/irq_asic.c
+++ b/arch/mips/powertv/asic/irq_asic.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/irq.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
diff --git a/arch/mips/rb532/serial.c b/arch/mips/rb532/serial.c
index 00ed19f..7048254 100644
--- a/arch/mips/rb532/serial.c
+++ b/arch/mips/rb532/serial.c
@@ -29,6 +29,7 @@
 #include <linux/tty.h>
 #include <linux/serial_core.h>
 #include <linux/serial_8250.h>
+#include <linux/irq.h>
 
 #include <asm/serial.h>
 #include <asm/mach-rc32434/rb.h>
diff --git a/arch/mips/sibyte/common/sb_tbprof.c b/arch/mips/sibyte/common/sb_tbprof.c
index d4ed7a9..ca35b73 100644
--- a/arch/mips/sibyte/common/sb_tbprof.c
+++ b/arch/mips/sibyte/common/sb_tbprof.c
@@ -545,6 +545,7 @@
 	.unlocked_ioctl	= sbprof_tb_ioctl,
 	.compat_ioctl	= sbprof_tb_ioctl,
 	.mmap		= NULL,
+	.llseek		= default_llseek,
 };
 
 static struct class *tb_class;
diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c
index e698089..bbe7187 100644
--- a/arch/mips/sni/a20r.c
+++ b/arch/mips/sni/a20r.c
@@ -10,6 +10,7 @@
 
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/platform_device.h>
 #include <linux/serial_8250.h>
 
diff --git a/arch/mips/sni/pcimt.c b/arch/mips/sni/pcimt.c
index 51e62bb..8c92c73 100644
--- a/arch/mips/sni/pcimt.c
+++ b/arch/mips/sni/pcimt.c
@@ -11,6 +11,7 @@
 
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/serial_8250.h>
 
diff --git a/arch/mips/sni/pcit.c b/arch/mips/sni/pcit.c
index f4699d3..dc98745 100644
--- a/arch/mips/sni/pcit.c
+++ b/arch/mips/sni/pcit.c
@@ -10,6 +10,7 @@
 
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/serial_8250.h>
 
diff --git a/arch/mips/sni/rm200.c b/arch/mips/sni/rm200.c
index 90c558f..0e6f42c 100644
--- a/arch/mips/sni/rm200.c
+++ b/arch/mips/sni/rm200.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/platform_device.h>
 #include <linux/serial_8250.h>
 #include <linux/io.h>
diff --git a/arch/mips/sni/time.c b/arch/mips/sni/time.c
index f3b60e6..c76151b 100644
--- a/arch/mips/sni/time.c
+++ b/arch/mips/sni/time.c
@@ -1,5 +1,6 @@
 #include <linux/types.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/smp.h>
 #include <linux/time.h>
 #include <linux/clockchips.h>
diff --git a/arch/mips/txx9/generic/irq_tx4927.c b/arch/mips/txx9/generic/irq_tx4927.c
index ad2870d..e1828e8 100644
--- a/arch/mips/txx9/generic/irq_tx4927.c
+++ b/arch/mips/txx9/generic/irq_tx4927.c
@@ -25,6 +25,7 @@
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/irq_cpu.h>
 #include <asm/txx9/tx4927.h>
 
diff --git a/arch/mips/txx9/generic/irq_tx4938.c b/arch/mips/txx9/generic/irq_tx4938.c
index 025ae11..a6e6e80 100644
--- a/arch/mips/txx9/generic/irq_tx4938.c
+++ b/arch/mips/txx9/generic/irq_tx4938.c
@@ -13,6 +13,7 @@
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/irq_cpu.h>
 #include <asm/txx9/tx4938.h>
 
diff --git a/arch/mips/txx9/generic/irq_tx4939.c b/arch/mips/txx9/generic/irq_tx4939.c
index 013213a8..3886ad7 100644
--- a/arch/mips/txx9/generic/irq_tx4939.c
+++ b/arch/mips/txx9/generic/irq_tx4939.c
@@ -19,6 +19,7 @@
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/types.h>
 #include <asm/irq_cpu.h>
 #include <asm/txx9irq.h>
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 575d219b..812816c 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -24,6 +24,7 @@
 #include <linux/leds.h>
 #include <linux/sysdev.h>
 #include <linux/slab.h>
+#include <linux/irq.h>
 #include <asm/bootinfo.h>
 #include <asm/time.h>
 #include <asm/reboot.h>
diff --git a/arch/mips/txx9/jmr3927/irq.c b/arch/mips/txx9/jmr3927/irq.c
index 6ec626c..0a7f8e3 100644
--- a/arch/mips/txx9/jmr3927/irq.c
+++ b/arch/mips/txx9/jmr3927/irq.c
@@ -32,6 +32,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 
 #include <asm/io.h>
 #include <asm/mipsregs.h>
diff --git a/arch/mips/txx9/rbtx4927/irq.c b/arch/mips/txx9/rbtx4927/irq.c
index 9c14ebb..c4b54d2 100644
--- a/arch/mips/txx9/rbtx4927/irq.c
+++ b/arch/mips/txx9/rbtx4927/irq.c
@@ -111,6 +111,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/io.h>
 #include <asm/mipsregs.h>
 #include <asm/txx9/generic.h>
diff --git a/arch/mips/txx9/rbtx4938/irq.c b/arch/mips/txx9/rbtx4938/irq.c
index 7d21bef..67a73a8 100644
--- a/arch/mips/txx9/rbtx4938/irq.c
+++ b/arch/mips/txx9/rbtx4938/irq.c
@@ -64,6 +64,7 @@
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/mipsregs.h>
 #include <asm/txx9/generic.h>
 #include <asm/txx9/rbtx4938.h>
diff --git a/arch/mips/txx9/rbtx4939/irq.c b/arch/mips/txx9/rbtx4939/irq.c
index 500cc0a..57fa740 100644
--- a/arch/mips/txx9/rbtx4939/irq.c
+++ b/arch/mips/txx9/rbtx4939/irq.c
@@ -11,6 +11,7 @@
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/mipsregs.h>
 #include <asm/txx9/rbtx4939.h>
 
diff --git a/arch/mips/vr41xx/common/irq.c b/arch/mips/vr41xx/common/irq.c
index bef0687..0975eb7 100644
--- a/arch/mips/vr41xx/common/irq.c
+++ b/arch/mips/vr41xx/common/irq.c
@@ -19,6 +19,7 @@
  */
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/irq.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/system.h>
diff --git a/arch/mips/vr41xx/common/siu.c b/arch/mips/vr41xx/common/siu.c
index 54eae56..bbd45d2 100644
--- a/arch/mips/vr41xx/common/siu.c
+++ b/arch/mips/vr41xx/common/siu.c
@@ -22,6 +22,7 @@
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
 #include <linux/serial_core.h>
+#include <linux/irq.h>
 
 #include <asm/cpu.h>
 #include <asm/vr41xx/siu.h>
diff --git a/arch/mn10300/include/asm/irqflags.h b/arch/mn10300/include/asm/irqflags.h
new file mode 100644
index 0000000..5e529a1
--- /dev/null
+++ b/arch/mn10300/include/asm/irqflags.h
@@ -0,0 +1,123 @@
+/* MN10300 IRQ flag handling
+ *
+ * Copyright (C) 2010 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _ASM_IRQFLAGS_H
+#define _ASM_IRQFLAGS_H
+
+#include <asm/cpu-regs.h>
+
+/*
+ * interrupt control
+ * - "disabled": run in IM1/2
+ *   - level 0 - GDB stub
+ *   - level 1 - virtual serial DMA (if present)
+ *   - level 5 - normal interrupt priority
+ *   - level 6 - timer interrupt
+ * - "enabled":  run in IM7
+ */
+#ifdef CONFIG_MN10300_TTYSM
+#define MN10300_CLI_LEVEL	EPSW_IM_2
+#else
+#define MN10300_CLI_LEVEL	EPSW_IM_1
+#endif
+
+#ifndef __ASSEMBLY__
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+
+	asm volatile("mov epsw,%0" : "=d"(flags));
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile(
+		"	and %0,epsw	\n"
+		"	or %1,epsw	\n"
+		"	nop		\n"
+		"	nop		\n"
+		"	nop		\n"
+		:
+		: "i"(~EPSW_IM), "i"(EPSW_IE | MN10300_CLI_LEVEL)
+		: "memory");
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+	flags = arch_local_save_flags();
+	arch_local_irq_disable();
+	return flags;
+}
+
+/*
+ * we make sure arch_irq_enable() doesn't cause priority inversion
+ */
+extern unsigned long __mn10300_irq_enabled_epsw;
+
+static inline void arch_local_irq_enable(void)
+{
+	unsigned long tmp;
+
+	asm volatile(
+		"	mov	epsw,%0		\n"
+		"	and	%1,%0		\n"
+		"	or	%2,%0		\n"
+		"	mov	%0,epsw		\n"
+		: "=&d"(tmp)
+		: "i"(~EPSW_IM), "r"(__mn10300_irq_enabled_epsw)
+		: "memory");
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile(
+		"	mov %0,epsw	\n"
+		"	nop		\n"
+		"	nop		\n"
+		"	nop		\n"
+		:
+		: "d"(flags)
+		: "memory", "cc");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & EPSW_IM) <= MN10300_CLI_LEVEL;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+/*
+ * Hook to save power by halting the CPU
+ * - called from the idle loop
+ * - must reenable interrupts (which takes three instruction cycles to complete)
+ */
+static inline void arch_safe_halt(void)
+{
+	asm volatile(
+		"	or	%0,epsw	\n"
+		"	nop		\n"
+		"	nop		\n"
+		"	bset	%2,(%1)	\n"
+		:
+		: "i"(EPSW_IE|EPSW_IM), "n"(&CPUM), "i"(CPUM_SLEEP)
+		: "cc");
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_IRQFLAGS_H */
diff --git a/arch/mn10300/include/asm/system.h b/arch/mn10300/include/asm/system.h
index 3636c05..9f7c7e1 100644
--- a/arch/mn10300/include/asm/system.h
+++ b/arch/mn10300/include/asm/system.h
@@ -17,6 +17,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/kernel.h>
+#include <linux/irqflags.h>
 
 struct task_struct;
 struct thread_struct;
@@ -81,114 +82,6 @@
 
 /*****************************************************************************/
 /*
- * interrupt control
- * - "disabled": run in IM1/2
- *   - level 0 - GDB stub
- *   - level 1 - virtual serial DMA (if present)
- *   - level 5 - normal interrupt priority
- *   - level 6 - timer interrupt
- * - "enabled":  run in IM7
- */
-#ifdef CONFIG_MN10300_TTYSM
-#define MN10300_CLI_LEVEL	EPSW_IM_2
-#else
-#define MN10300_CLI_LEVEL	EPSW_IM_1
-#endif
-
-#define local_save_flags(x)			\
-do {						\
-	typecheck(unsigned long, x);		\
-	asm volatile(				\
-		"	mov epsw,%0	\n"	\
-		: "=d"(x)			\
-		);				\
-} while (0)
-
-#define local_irq_disable()						\
-do {									\
-	asm volatile(							\
-		"	and %0,epsw	\n"				\
-		"	or %1,epsw	\n"				\
-		"	nop		\n"				\
-		"	nop		\n"				\
-		"	nop		\n"				\
-		:							\
-		: "i"(~EPSW_IM), "i"(EPSW_IE | MN10300_CLI_LEVEL)	\
-		);							\
-} while (0)
-
-#define local_irq_save(x)			\
-do {						\
-	local_save_flags(x);			\
-	local_irq_disable();			\
-} while (0)
-
-/*
- * we make sure local_irq_enable() doesn't cause priority inversion
- */
-#ifndef __ASSEMBLY__
-
-extern unsigned long __mn10300_irq_enabled_epsw;
-
-#endif
-
-#define local_irq_enable()						\
-do {									\
-	unsigned long tmp;						\
-									\
-	asm volatile(							\
-		"	mov	epsw,%0		\n"			\
-		"	and	%1,%0		\n"			\
-		"	or	%2,%0		\n"			\
-		"	mov	%0,epsw		\n"			\
-		: "=&d"(tmp)						\
-		: "i"(~EPSW_IM), "r"(__mn10300_irq_enabled_epsw)	\
-		: "cc"							\
-		);							\
-} while (0)
-
-#define local_irq_restore(x)			\
-do {						\
-	typecheck(unsigned long, x);		\
-	asm volatile(				\
-		"	mov %0,epsw	\n"	\
-		"	nop		\n"	\
-		"	nop		\n"	\
-		"	nop		\n"	\
-		:				\
-		: "d"(x)			\
-		: "memory", "cc"		\
-		);				\
-} while (0)
-
-#define irqs_disabled()				\
-({						\
-	unsigned long flags;			\
-	local_save_flags(flags);		\
-	(flags & EPSW_IM) <= MN10300_CLI_LEVEL;	\
-})
-
-/* hook to save power by halting the CPU
- * - called from the idle loop
- * - must reenable interrupts (which takes three instruction cycles to complete)
- */
-#define safe_halt()							\
-do {									\
-	asm volatile("	or	%0,epsw	\n"				\
-		     "	nop		\n"				\
-		     "	nop		\n"				\
-		     "	bset	%2,(%1)	\n"				\
-		     :							\
-		     : "i"(EPSW_IE|EPSW_IM), "n"(&CPUM), "i"(CPUM_SLEEP)\
-		     : "cc"						\
-		     );							\
-} while (0)
-
-#define STI	or EPSW_IE|EPSW_IM,epsw
-#define CLI	and ~EPSW_IM,epsw; or EPSW_IE|MN10300_CLI_LEVEL,epsw; nop; nop; nop
-
-/*****************************************************************************/
-/*
  * MN10300 doesn't actually have an exchange instruction
  */
 #ifndef __ASSEMBLY__
diff --git a/arch/mn10300/kernel/entry.S b/arch/mn10300/kernel/entry.S
index d9ed5a1..3d394b4 100644
--- a/arch/mn10300/kernel/entry.S
+++ b/arch/mn10300/kernel/entry.S
@@ -16,6 +16,7 @@
 #include <linux/linkage.h>
 #include <asm/smp.h>
 #include <asm/system.h>
+#include <asm/irqflags.h>
 #include <asm/thread_info.h>
 #include <asm/intctl-regs.h>
 #include <asm/busctl-regs.h>
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 907417d..79a04a9 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -16,6 +16,7 @@
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
 	select BUG
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select GENERIC_ATOMIC64 if !64BIT
 	help
diff --git a/arch/parisc/include/asm/irqflags.h b/arch/parisc/include/asm/irqflags.h
new file mode 100644
index 0000000..34f9cb9
--- /dev/null
+++ b/arch/parisc/include/asm/irqflags.h
@@ -0,0 +1,46 @@
+#ifndef __PARISC_IRQFLAGS_H
+#define __PARISC_IRQFLAGS_H
+
+#include <linux/types.h>
+#include <asm/psw.h>
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile("ssm 0, %0" : "=r" (flags) : : "memory");
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile("rsm %0,%%r0\n" : : "i" (PSW_I) : "memory");
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile("ssm %0,%%r0\n" : : "i" (PSW_I) : "memory");
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+	asm volatile("rsm %1,%0" : "=r" (flags) : "i" (PSW_I) : "memory");
+	return flags;
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile("mtsm %0" : : "r" (flags) : "memory");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & PSW_I) == 0;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* __PARISC_IRQFLAGS_H */
diff --git a/arch/parisc/include/asm/perf_event.h b/arch/parisc/include/asm/perf_event.h
index cc146427..1e0fd8b 100644
--- a/arch/parisc/include/asm/perf_event.h
+++ b/arch/parisc/include/asm/perf_event.h
@@ -1,7 +1,6 @@
 #ifndef __ASM_PARISC_PERF_EVENT_H
 #define __ASM_PARISC_PERF_EVENT_H
 
-/* parisc only supports software events through this interface. */
-static inline void set_perf_event_pending(void) { }
+/* Empty, just to avoid compiling error */
 
 #endif /* __ASM_PARISC_PERF_EVENT_H */
diff --git a/arch/parisc/include/asm/system.h b/arch/parisc/include/asm/system.h
index 2ab4af5..b19e63a 100644
--- a/arch/parisc/include/asm/system.h
+++ b/arch/parisc/include/asm/system.h
@@ -1,7 +1,7 @@
 #ifndef __PARISC_SYSTEM_H
 #define __PARISC_SYSTEM_H
 
-#include <asm/psw.h>
+#include <linux/irqflags.h>
 
 /* The program status word as bitfields.  */
 struct pa_psw {
@@ -48,23 +48,6 @@
 	(last) = _switch_to(prev, next);			\
 } while(0)
 
-/* interrupt control */
-#define local_save_flags(x)	__asm__ __volatile__("ssm 0, %0" : "=r" (x) : : "memory")
-#define local_irq_disable()	__asm__ __volatile__("rsm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
-#define local_irq_enable()	__asm__ __volatile__("ssm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
-
-#define local_irq_save(x) \
-	__asm__ __volatile__("rsm %1,%0" : "=r" (x) :"i" (PSW_I) : "memory" )
-#define local_irq_restore(x) \
-	__asm__ __volatile__("mtsm %0" : : "r" (x) : "memory" )
-
-#define irqs_disabled()			\
-({					\
-	unsigned long flags;		\
-	local_save_flags(flags);	\
-	(flags & PSW_I) == 0;		\
-})
-
 #define mfctl(reg)	({		\
 	unsigned long cr;		\
 	__asm__ __volatile__(		\
diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index f9f6783..ba0c053 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -46,7 +46,6 @@
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/miscdevice.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 
 #include <asm/uaccess.h>
@@ -261,16 +260,13 @@
  */
 static int perf_open(struct inode *inode, struct file *file)
 {
-	lock_kernel();
 	spin_lock(&perf_lock);
 	if (perf_enabled) {
 		spin_unlock(&perf_lock);
-		unlock_kernel();
 		return -EBUSY;
 	}
 	perf_enabled = 1;
  	spin_unlock(&perf_lock);
-	unlock_kernel();
 
 	return 0;
 }
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 631e5a0..4b1e521 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -138,6 +138,7 @@
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS if PPC64
 	select GENERIC_ATOMIC64 if PPC32
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
diff --git a/arch/powerpc/boot/addnote.c b/arch/powerpc/boot/addnote.c
index b1e5611..349b553 100644
--- a/arch/powerpc/boot/addnote.c
+++ b/arch/powerpc/boot/addnote.c
@@ -20,7 +20,7 @@
 #include <string.h>
 
 /* CHRP note section */
-char arch[] = "PowerPC";
+static const char arch[] = "PowerPC";
 
 #define N_DESCR	6
 unsigned int descr[N_DESCR] = {
@@ -33,7 +33,7 @@
 };
 
 /* RPA note section */
-char rpaname[] = "IBM,RPA-Client-Config";
+static const char rpaname[] = "IBM,RPA-Client-Config";
 
 /*
  * Note: setting ignore_my_client_config *should* mean that OF ignores
diff --git a/arch/powerpc/boot/dts/bluestone.dts b/arch/powerpc/boot/dts/bluestone.dts
new file mode 100644
index 0000000..9bb3d72
--- /dev/null
+++ b/arch/powerpc/boot/dts/bluestone.dts
@@ -0,0 +1,254 @@
+/*
+ * Device Tree for Bluestone (APM821xx) board.
+ *
+ * Copyright (c) 2010, Applied Micro Circuits Corporation
+ * Author: Tirumala R Marri <tmarri@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ *
+ */
+
+/dts-v1/;
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	model = "apm,bluestone";
+	compatible = "apm,bluestone";
+	dcr-parent = <&{/cpus/cpu@0}>;
+
+	aliases {
+		ethernet0 = &EMAC0;
+		serial0 = &UART0;
+		serial1 = &UART1;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			model = "PowerPC,apm821xx";
+			reg = <0x00000000>;
+			clock-frequency = <0>; /* Filled in by U-Boot */
+			timebase-frequency = <0>; /* Filled in by U-Boot */
+			i-cache-line-size = <32>;
+			d-cache-line-size = <32>;
+			i-cache-size = <32768>;
+			d-cache-size = <32768>;
+			dcr-controller;
+			dcr-access-method = "native";
+			next-level-cache = <&L2C0>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x00000000 0x00000000>; /* Filled in by U-Boot */
+	};
+
+	UIC0: interrupt-controller0 {
+		compatible = "ibm,uic";
+		interrupt-controller;
+		cell-index = <0>;
+		dcr-reg = <0x0c0 0x009>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		#interrupt-cells = <2>;
+	};
+
+	UIC1: interrupt-controller1 {
+		compatible = "ibm,uic";
+		interrupt-controller;
+		cell-index = <1>;
+		dcr-reg = <0x0d0 0x009>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		#interrupt-cells = <2>;
+		interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
+		interrupt-parent = <&UIC0>;
+	};
+
+	UIC2: interrupt-controller2 {
+		compatible = "ibm,uic";
+		interrupt-controller;
+		cell-index = <2>;
+		dcr-reg = <0x0e0 0x009>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		#interrupt-cells = <2>;
+		interrupts = <0xa 0x4 0xb 0x4>; /* cascade */
+		interrupt-parent = <&UIC0>;
+	};
+
+	UIC3: interrupt-controller3 {
+		compatible = "ibm,uic";
+		interrupt-controller;
+		cell-index = <3>;
+		dcr-reg = <0x0f0 0x009>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		#interrupt-cells = <2>;
+		interrupts = <0x10 0x4 0x11 0x4>; /* cascade */
+		interrupt-parent = <&UIC0>;
+	};
+
+	SDR0: sdr {
+		compatible = "ibm,sdr-apm821xx";
+		dcr-reg = <0x00e 0x002>;
+	};
+
+	CPR0: cpr {
+		compatible = "ibm,cpr-apm821xx";
+		dcr-reg = <0x00c 0x002>;
+	};
+
+	plb {
+		compatible = "ibm,plb4";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+		clock-frequency = <0>; /* Filled in by U-Boot */
+
+		SDRAM0: sdram {
+			compatible = "ibm,sdram-apm821xx";
+			dcr-reg = <0x010 0x002>;
+		};
+
+		MAL0: mcmal {
+			compatible = "ibm,mcmal2";
+			descriptor-memory = "ocm";
+			dcr-reg = <0x180 0x062>;
+			num-tx-chans = <1>;
+			num-rx-chans = <1>;
+			#address-cells = <0>;
+			#size-cells = <0>;
+			interrupt-parent = <&UIC2>;
+			interrupts = <	/*TXEOB*/ 0x6 0x4
+					/*RXEOB*/ 0x7 0x4
+					/*SERR*/  0x3 0x4
+					/*TXDE*/  0x4 0x4
+					/*RXDE*/  0x5 0x4
+		};
+
+		POB0: opb {
+			compatible = "ibm,opb";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0xb0000000 0x00000004 0xb0000000 0x50000000>;
+			clock-frequency = <0>; /* Filled in by U-Boot */
+
+			EBC0: ebc {
+				compatible = "ibm,ebc";
+				dcr-reg = <0x012 0x002>;
+				#address-cells = <2>;
+				#size-cells = <1>;
+				clock-frequency = <0>; /* Filled in by U-Boot */
+				/* ranges property is supplied by U-Boot */
+				ranges = < 0x00000003 0x00000000 0xe0000000 0x8000000>;
+				interrupts = <0x6 0x4>;
+				interrupt-parent = <&UIC1>;
+
+				nor_flash@0,0 {
+					compatible = "amd,s29gl512n", "cfi-flash";
+					bank-width = <2>;
+					reg = <0x00000000 0x00000000 0x00400000>;
+					#address-cells = <1>;
+					#size-cells = <1>;
+					partition@0 {
+						label = "kernel";
+						reg = <0x00000000 0x00180000>;
+					};
+					partition@180000 {
+						label = "env";
+						reg = <0x00180000 0x00020000>;
+					};
+					partition@1a0000 {
+						label = "u-boot";
+						reg = <0x001a0000 0x00060000>;
+					};
+				};
+			}
+
+			UART0: serial@ef600300 {
+				device_type = "serial";
+				compatible = "ns16550";
+				reg = <0xef600300 0x00000008>;
+				virtual-reg = <0xef600300>;
+				clock-frequency = <0>; /* Filled in by U-Boot */
+				current-speed = <0>; /* Filled in by U-Boot */
+				interrupt-parent = <&UIC1>;
+				interrupts = <0x1 0x4>;
+			};
+
+			IIC0: i2c@ef600700 {
+				compatible = "ibm,iic";
+				reg = <0xef600700 0x00000014>;
+				interrupt-parent = <&UIC0>;
+				interrupts = <0x2 0x4>;
+			};
+
+			IIC1: i2c@ef600800 {
+				compatible = "ibm,iic";
+				reg = <0xef600800 0x00000014>;
+				interrupt-parent = <&UIC0>;
+				interrupts = <0x3 0x4>;
+			};
+
+			RGMII0: emac-rgmii@ef601500 {
+				compatible = "ibm,rgmii";
+				reg = <0xef601500 0x00000008>;
+				has-mdio;
+			};
+
+			TAH0: emac-tah@ef601350 {
+				compatible = "ibm,tah";
+				reg = <0xef601350 0x00000030>;
+			};
+
+			EMAC0: ethernet@ef600c00 {
+				device_type = "network";
+				compatible = "ibm,emac4sync";
+				interrupt-parent = <&EMAC0>;
+				interrupts = <0x0 0x1>;
+				#interrupt-cells = <1>;
+				#address-cells = <0>;
+				#size-cells = <0>;
+				interrupt-map = </*Status*/ 0x0 &UIC2 0x10 0x4
+						 /*Wake*/   0x1 &UIC2 0x14 0x4>;
+				reg = <0xef600c00 0x000000c4>;
+				local-mac-address = [000000000000]; /* Filled in by U-Boot */
+				mal-device = <&MAL0>;
+				mal-tx-channel = <0>;
+				mal-rx-channel = <0>;
+				cell-index = <0>;
+				max-frame-size = <9000>;
+				rx-fifo-size = <16384>;
+				tx-fifo-size = <2048>;
+				phy-mode = "rgmii";
+				phy-map = <0x00000000>;
+				rgmii-device = <&RGMII0>;
+				rgmii-channel = <0>;
+				tah-device = <&TAH0>;
+				tah-channel = <0>;
+				has-inverted-stacr-oc;
+				has-new-stacr-staopc;
+			};
+		};
+
+	};
+};
diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts
new file mode 100644
index 0000000..05a76cc
--- /dev/null
+++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts
@@ -0,0 +1,332 @@
+/*
+ * mpc8308_p1m Device Tree Source
+ *
+ * Copyright 2010 Ilya Yanok, Emcraft Systems, yanok@emcraft.com
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/dts-v1/;
+
+/ {
+	compatible = "denx,mpc8308_p1m";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	aliases {
+		ethernet0 = &enet0;
+		ethernet1 = &enet1;
+		serial0 = &serial0;
+		serial1 = &serial1;
+		pci0 = &pci0;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,8308@0 {
+			device_type = "cpu";
+			reg = <0x0>;
+			d-cache-line-size = <32>;
+			i-cache-line-size = <32>;
+			d-cache-size = <16384>;
+			i-cache-size = <16384>;
+			timebase-frequency = <0>;	// from bootloader
+			bus-frequency = <0>;		// from bootloader
+			clock-frequency = <0>;		// from bootloader
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x08000000>;	// 128MB at 0
+	};
+
+	localbus@e0005000 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		compatible = "fsl,mpc8315-elbc", "fsl,elbc", "simple-bus";
+		reg = <0xe0005000 0x1000>;
+		interrupts = <77 0x8>;
+		interrupt-parent = <&ipic>;
+
+		ranges = <0x0 0x0 0xfc000000 0x04000000
+		          0x1 0x0 0xfbff0000 0x00008000
+		          0x2 0x0 0xfbff8000 0x00008000>;
+
+		flash@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x4000000>;
+			bank-width = <2>;
+			device-width = <1>;
+
+			u-boot@0 {
+				reg = <0x0 0x60000>;
+				read-only;
+			};
+			env@60000 {
+				reg = <0x60000 0x20000>;
+			};
+			env1@80000 {
+				reg = <0x80000 0x20000>;
+			};
+			kernel@a0000 {
+				reg = <0xa0000 0x200000>;
+			};
+			dtb@2a0000 {
+				reg = <0x2a0000 0x20000>;
+			};
+			ramdisk@2c0000 {
+				reg = <0x2c0000 0x640000>;
+			};
+			user@700000 {
+				reg = <0x700000 0x3900000>;
+			};
+		};
+
+		can@1,0 {
+			compatible = "nxp,sja1000";
+			reg = <0x1 0x0 0x80>;
+			interrupts = <18 0x8>;
+			interrups-parent = <&ipic>;
+		};
+
+		cpld@2,0 {
+			compatible = "denx,mpc8308_p1m-cpld";
+			reg = <0x2 0x0 0x8>;
+			interrupts = <48 0x8>;
+			interrups-parent = <&ipic>;
+		};
+	};
+
+	immr@e0000000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		device_type = "soc";
+		compatible = "fsl,mpc8308-immr", "simple-bus";
+		ranges = <0 0xe0000000 0x00100000>;
+		reg = <0xe0000000 0x00000200>;
+		bus-frequency = <0>;
+
+		i2c@3000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl-i2c";
+			reg = <0x3000 0x100>;
+			interrupts = <14 0x8>;
+			interrupt-parent = <&ipic>;
+			dfsrr;
+			fram@50 {
+				compatible = "ramtron,24c64";
+				reg = <0x50>;
+			};
+		};
+
+		i2c@3100 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl-i2c";
+			reg = <0x3100 0x100>;
+			interrupts = <15 0x8>;
+			interrupt-parent = <&ipic>;
+			dfsrr;
+			pwm@28 {
+				compatible = "maxim,ds1050";
+				reg = <0x28>;
+			};
+			sensor@48 {
+				compatible = "maxim,max6625";
+				reg = <0x48>;
+			};
+			sensor@49 {
+				compatible = "maxim,max6625";
+				reg = <0x49>;
+			};
+			sensor@4b {
+				compatible = "maxim,max6625";
+				reg = <0x4b>;
+			};
+		};
+
+		usb@23000 {
+			compatible = "fsl-usb2-dr";
+			reg = <0x23000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupt-parent = <&ipic>;
+			interrupts = <38 0x8>;
+			dr_mode = "peripheral";
+			phy_type = "ulpi";
+		};
+
+		enet0: ethernet@24000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0x0 0x24000 0x1000>;
+
+			cell-index = <0>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x24000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <32 0x8 33 0x8 34 0x8>;
+			interrupt-parent = <&ipic>;
+			phy-handle = < &phy1 >;
+
+			mdio@520 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,gianfar-mdio";
+				reg = <0x520 0x20>;
+				phy1: ethernet-phy@1 {
+					interrupt-parent = <&ipic>;
+					interrupts = <17 0x8>;
+					reg = <0x1>;
+					device_type = "ethernet-phy";
+				};
+				phy2: ethernet-phy@2 {
+					interrupt-parent = <&ipic>;
+					interrupts = <19 0x8>;
+					reg = <0x2>;
+					device_type = "ethernet-phy";
+				};
+				tbi0: tbi-phy@11 {
+					reg = <0x11>;
+					device_type = "tbi-phy";
+				};
+			};
+		};
+
+		enet1: ethernet@25000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			cell-index = <1>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x25000 0x1000>;
+			ranges = <0x0 0x25000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <35 0x8 36 0x8 37 0x8>;
+			interrupt-parent = <&ipic>;
+			phy-handle = < &phy2 >;
+
+			mdio@520 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				compatible = "fsl,gianfar-tbi";
+				reg = <0x520 0x20>;
+				tbi1: tbi-phy@11 {
+					reg = <0x11>;
+					device_type = "tbi-phy";
+				};
+			};
+		};
+
+		serial0: serial@4500 {
+			cell-index = <0>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x4500 0x100>;
+			clock-frequency = <133333333>;
+			interrupts = <9 0x8>;
+			interrupt-parent = <&ipic>;
+		};
+
+		serial1: serial@4600 {
+			cell-index = <1>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x4600 0x100>;
+			clock-frequency = <133333333>;
+			interrupts = <10 0x8>;
+			interrupt-parent = <&ipic>;
+		};
+
+		gpio@c00 {
+			#gpio-cells = <2>;
+			compatible = "fsl,mpc8308-gpio", "fsl,mpc8349-gpio";
+			reg = <0xc00 0x18>;
+			interrupts = <74 0x8>;
+			interrupt-parent = <&ipic>;
+			gpio-controller;
+		};
+
+		timer@500 {
+			compatible = "fsl,mpc8308-gtm", "fsl,gtm";
+			reg = <0x500 0x100>;
+			interrupts = <90 8 78 8 84 8 72 8>;
+			interrupt-parent = <&ipic>;
+			clock-frequency = <133333333>;
+		};
+
+		/* IPIC
+		 * interrupts cell = <intr #, sense>
+		 * sense values match linux IORESOURCE_IRQ_* defines:
+		 * sense == 8: Level, low assertion
+		 * sense == 2: Edge, high-to-low change
+		 */
+		ipic: interrupt-controller@700 {
+			compatible = "fsl,ipic";
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			reg = <0x700 0x100>;
+			device_type = "ipic";
+		};
+
+		ipic-msi@7c0 {
+			compatible = "fsl,ipic-msi";
+			reg = <0x7c0 0x40>;
+			msi-available-ranges = <0x0 0x100>;
+			interrupts = < 0x43 0x8
+					0x4  0x8
+					0x51 0x8
+					0x52 0x8
+					0x56 0x8
+					0x57 0x8
+					0x58 0x8
+					0x59 0x8 >;
+			interrupt-parent = < &ipic >;
+		};
+
+	};
+
+	pci0: pcie@e0009000 {
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+		device_type = "pci";
+		compatible = "fsl,mpc8308-pcie", "fsl,mpc8314-pcie";
+		reg = <0xe0009000 0x00001000
+			0xb0000000 0x01000000>;
+		ranges = <0x02000000 0 0xa0000000 0xa0000000 0 0x10000000
+		          0x01000000 0 0x00000000 0xb1000000 0 0x00800000>;
+		bus-range = <0 0>;
+		interrupt-map-mask = <0 0 0 0>;
+		interrupt-map = <0 0 0 0 &ipic 1 8>;
+		interrupts = <0x1 0x8>;
+		interrupt-parent = <&ipic>;
+		clock-frequency = <0>;
+
+		pcie@0 {
+			#address-cells = <3>;
+			#size-cells = <2>;
+			device_type = "pci";
+			reg = <0 0 0 0 0>;
+			ranges = <0x02000000 0 0xa0000000
+				  0x02000000 0 0xa0000000
+				  0 0x10000000
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00800000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/mpc8536ds.dts b/arch/powerpc/boot/dts/mpc8536ds.dts
index 815cebb..a75c10e 100644
--- a/arch/powerpc/boot/dts/mpc8536ds.dts
+++ b/arch/powerpc/boot/dts/mpc8536ds.dts
@@ -108,6 +108,58 @@
 			};
 		};
 
+		spi@7000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,mpc8536-espi";
+			reg = <0x7000 0x1000>;
+			interrupts = <59 0x2>;
+			interrupt-parent = <&mpic>;
+			fsl,espi-num-chipselects = <4>;
+
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "spansion,s25sl12801";
+				reg = <0>;
+				spi-max-frequency = <40000000>;
+				partition@u-boot {
+					label = "u-boot";
+					reg = <0x00000000 0x00100000>;
+					read-only;
+				};
+				partition@kernel {
+					label = "kernel";
+					reg = <0x00100000 0x00500000>;
+					read-only;
+				};
+				partition@dtb {
+					label = "dtb";
+					reg = <0x00600000 0x00100000>;
+					read-only;
+				};
+				partition@fs {
+					label = "file system";
+					reg = <0x00700000 0x00900000>;
+				};
+			};
+			flash@1 {
+				compatible = "spansion,s25sl12801";
+				reg = <1>;
+				spi-max-frequency = <40000000>;
+			};
+			flash@2 {
+				compatible = "spansion,s25sl12801";
+				reg = <2>;
+				spi-max-frequency = <40000000>;
+			};
+			flash@3 {
+				compatible = "spansion,s25sl12801";
+				reg = <3>;
+				spi-max-frequency = <40000000>;
+			};
+		};
+
 		dma@21300 {
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/p1022ds.dts b/arch/powerpc/boot/dts/p1022ds.dts
index 8bcb10b..2bbecbb 100644
--- a/arch/powerpc/boot/dts/p1022ds.dts
+++ b/arch/powerpc/boot/dts/p1022ds.dts
@@ -148,6 +148,17 @@
 				label = "reserved-nand";
 			};
 		};
+
+		board-control@3,0 {
+			compatible = "fsl,p1022ds-pixis";
+			reg = <3 0 0x30>;
+			interrupt-parent = <&mpic>;
+			/*
+			 * IRQ8 is generated if the "EVENT" switch is pressed
+			 * and PX_CTL[EVESEL] is set to 00.
+			 */
+			interrupts = <8 8>;
+		};
 	};
 
 	soc@fffe00000 {
diff --git a/arch/powerpc/boot/dts/p4080ds.dts b/arch/powerpc/boot/dts/p4080ds.dts
index 2f0de24..5b7fc29 100644
--- a/arch/powerpc/boot/dts/p4080ds.dts
+++ b/arch/powerpc/boot/dts/p4080ds.dts
@@ -236,22 +236,19 @@
 		};
 
 		spi@110000 {
-			cell-index = <0>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			compatible = "fsl,espi";
+			compatible = "fsl,p4080-espi", "fsl,mpc8536-espi";
 			reg = <0x110000 0x1000>;
 			interrupts = <53 0x2>;
 			interrupt-parent = <&mpic>;
-			espi,num-ss-bits = <4>;
-			mode = "cpu";
+			fsl,espi-num-chipselects = <4>;
 
-			fsl_m25p80@0 {
+			flash@0 {
 				#address-cells = <1>;
 				#size-cells = <1>;
-				compatible = "fsl,espi-flash";
+				compatible = "spansion,s25sl12801";
 				reg = <0>;
-				linux,modalias = "fsl_m25p80";
 				spi-max-frequency = <40000000>; /* input clock */
 				partition@u-boot {
 					label = "u-boot";
diff --git a/arch/powerpc/configs/44x/bluestone_defconfig b/arch/powerpc/configs/44x/bluestone_defconfig
new file mode 100644
index 0000000..ac65b48
--- /dev/null
+++ b/arch/powerpc/configs/44x/bluestone_defconfig
@@ -0,0 +1,68 @@
+CONFIG_44x=y
+CONFIG_EXPERIMENTAL=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_PCI_QUIRKS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_BLUESTONE=y
+# CONFIG_EBONY is not set
+# CONFIG_KVM_GUEST is not set
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_SPARSE_IRQ=y
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE=""
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_CONNECTOR=y
+CONFIG_MTD=y
+CONFIG_MTD_PARTITIONS=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_OF_PARTS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=35000
+CONFIG_NETDEVICES=y
+CONFIG_NET_ETHERNET=y
+CONFIG_IBM_NEW_EMAC=y
+CONFIG_IBM_NEW_EMAC_RXB=256
+CONFIG_IBM_NEW_EMAC_TXB=256
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=2
+CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_IBM_IIC=y
+CONFIG_SENSORS_AD7414=y
+# CONFIG_HID_SUPPORT is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_M41T80=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_CRAMFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS=y
diff --git a/arch/powerpc/configs/e55xx_smp_defconfig b/arch/powerpc/configs/e55xx_smp_defconfig
new file mode 100644
index 0000000..94d120e
--- /dev/null
+++ b/arch/powerpc/configs/e55xx_smp_defconfig
@@ -0,0 +1,84 @@
+CONFIG_PPC64=y
+CONFIG_PPC_BOOK3E_64=y
+# CONFIG_VIRT_CPU_ACCOUNTING is not set
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_EXPERIMENTAL=y
+CONFIG_SYSVIPC=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_EMBEDDED=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KALLSYMS_EXTRA_PASS=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_P5020_DS=y
+# CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BINFMT_MISC=m
+CONFIG_SPARSE_IRQ=y
+# CONFIG_PCI is not set
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_PROC_DEVICETREE=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=131072
+CONFIG_EEPROM_LEGACY=y
+CONFIG_INPUT_FF_MEMLESS=m
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_SERIO_LIBPS2=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_I2C=y
+# CONFIG_HWMON is not set
+CONFIG_VIDEO_OUTPUT_CONTROL=y
+# CONFIG_HID_SUPPORT is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_DMADEVICES=y
+CONFIG_FSL_DMA=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
+CONFIG_NLS=y
+CONFIG_NLS_UTF8=m
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=m
+CONFIG_LIBCRC32C=m
+CONFIG_FRAME_WARN=1024
+CONFIG_DEBUG_FS=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_VIRQ_DEBUG=y
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_CBC=y
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_SHA1=m
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRYPTO_DEV_TALITOS=y
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index cd446fb..2fa05f7 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -12,6 +12,7 @@
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_BAMBOO=y
+CONFIG_BLUESTONE=y
 CONFIG_SAM440EP=y
 CONFIG_SEQUOIA=y
 CONFIG_TAISHAN=y
@@ -97,14 +98,17 @@
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=m
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_INOTIFY=y
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
 CONFIG_UBIFS_FS=m
 CONFIG_UBIFS_FS_XATTR=y
+CONFIG_LOGFS=m
 CONFIG_CRAMFS=y
+CONFIG_SQUASHFS=m
+CONFIG_SQUASHFS_XATTR=y
+CONFIG_SQUASHFS_LZO=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
 CONFIG_ROOT_NFS=y
@@ -116,11 +120,8 @@
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_CRYPTO_CBC=y
 CONFIG_CRYPTO_ECB=y
 CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
 CONFIG_VIRTUALIZATION=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 04ae074..7bd1763 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -18,6 +18,7 @@
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_P5020_DS=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
@@ -256,7 +257,6 @@
 CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
 CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_TT_NEWSCHED=y
 # CONFIG_USB_EHCI_HCD_PPC_OF is not set
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_STORAGE=m
@@ -290,7 +290,6 @@
 CONFIG_JFS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_POSIX_ACL=y
-CONFIG_INOTIFY=y
 CONFIG_AUTOFS4_FS=m
 CONFIG_ISO9660_FS=y
 CONFIG_UDF_FS=m
@@ -384,7 +383,6 @@
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES=m
 CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_ARC4=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST6=m
 CONFIG_CRYPTO_KHAZAD=m
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 7cdf358..ce0c284 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -52,12 +52,22 @@
 extern __wsum csum_partial_copy_generic(const void *src, void *dst,
 					      int len, __wsum sum,
 					      int *src_err, int *dst_err);
+
+#ifdef __powerpc64__
+#define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
+				      int len, __wsum sum, int *err_ptr);
+#define HAVE_CSUM_COPY_USER
+extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
+				    int len, __wsum sum, int *err_ptr);
+#else
 /*
  * the same as csum_partial, but copies from src to dst while it
  * checksums.
  */
 #define csum_partial_copy_from_user(src, dst, len, sum, errp)   \
         csum_partial_copy_generic((__force const void *)(src), (dst), (len), (sum), (errp), NULL)
+#endif
 
 #define csum_partial_copy_nocheck(src, dst, len, sum)   \
         csum_partial_copy_generic((src), (dst), (len), (sum), NULL, NULL)
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index a11d4ea..2296112 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -143,7 +143,7 @@
 	 * We cant access below the stack pointer in the 32bit ABI and
 	 * can access 288 bytes in the 64bit ABI
 	 */
-	if (!(test_thread_flag(TIF_32BIT)))
+	if (!is_32bit_task())
 		usp -= 288;
 
 	return (void __user *) (usp - len);
@@ -213,7 +213,7 @@
 
 static inline int is_compat_task(void)
 {
-	return test_thread_flag(TIF_32BIT);
+	return is_32bit_task();
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 3a40a99..f3a1fdd 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -198,6 +198,7 @@
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0040000000000000)
 #define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0080000000000000)
 #define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0100000000000000)
+#define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0200000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -392,28 +393,31 @@
 	    CPU_FTR_MMCRA | CPU_FTR_CTRL)
 #define CPU_FTRS_POWER4	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
-	    CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ)
+	    CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS)
 #define CPU_FTRS_PPC970	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
-	    CPU_FTR_CP_USE_DCBTZ)
+	    CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS)
 #define CPU_FTRS_POWER5	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
-	    CPU_FTR_PURR)
+	    CPU_FTR_PURR | CPU_FTR_STCX_CHECKS_ADDRESS)
 #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD)
+	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT)
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 8c9c6ad..6d2416a 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -127,19 +127,7 @@
 	return dma_ops->dma_supported(dev, mask);
 }
 
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	if (unlikely(dma_ops == NULL))
-		return -EIO;
-	if (dma_ops->set_dma_mask != NULL)
-		return dma_ops->set_dma_mask(dev, dma_mask);
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
+extern int dma_set_mask(struct device *dev, u64 dma_mask);
 
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 				       dma_addr_t *dma_handle, gfp_t flag)
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index c376eda..2b917c6 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -250,7 +250,7 @@
  * the 64bit ABI has never had these issues dont enable the workaround
  * even if we have an executable stack.
  */
-# define elf_read_implies_exec(ex, exec_stk) (test_thread_flag(TIF_32BIT) ? \
+# define elf_read_implies_exec(ex, exec_stk) (is_32bit_task() ? \
 		(exec_stk == EXSTACK_DEFAULT) : 0)
 #else 
 # define SET_PERSONALITY(ex) \
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 57c4000..7778d6f 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -137,7 +137,8 @@
 	li	r10,0;							   \
 	ld	r11,exception_marker@toc(r2);				   \
 	std	r10,RESULT(r1);		/* clear regs->result		*/ \
-	std	r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame	*/
+	std	r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame	*/ \
+	ACCOUNT_STOLEN_TIME
 
 /*
  * Exception vectors.
diff --git a/arch/powerpc/include/asm/fsl_85xx_cache_sram.h b/arch/powerpc/include/asm/fsl_85xx_cache_sram.h
new file mode 100644
index 0000000..2af2bdc
--- /dev/null
+++ b/arch/powerpc/include/asm/fsl_85xx_cache_sram.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2009 Freescale Semiconductor, Inc.
+ *
+ * Cache SRAM handling for QorIQ platform
+ *
+ * Author: Vivek Mahajan <vivek.mahajan@freescale.com>
+
+ * This file is derived from the original work done
+ * by Sylvain Munaut for the Bestcomm SRAM allocator.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef __ASM_POWERPC_FSL_85XX_CACHE_SRAM_H__
+#define __ASM_POWERPC_FSL_85XX_CACHE_SRAM_H__
+
+#include <asm/rheap.h>
+#include <linux/spinlock.h>
+
+/*
+ * Cache-SRAM
+ */
+
+struct mpc85xx_cache_sram {
+	phys_addr_t base_phys;
+	void *base_virt;
+	unsigned int size;
+	rh_info_t *rh;
+	spinlock_t lock;
+};
+
+extern void mpc85xx_cache_sram_free(void *ptr);
+extern void *mpc85xx_cache_sram_alloc(unsigned int size,
+				  phys_addr_t *phys, unsigned int align);
+
+#endif /* __AMS_POWERPC_FSL_85XX_CACHE_SRAM_H__ */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index bd100fc..ff08b70 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -16,42 +16,57 @@
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 
-static inline unsigned long local_get_flags(void)
+static inline unsigned long arch_local_save_flags(void)
 {
 	unsigned long flags;
 
-	__asm__ __volatile__("lbz %0,%1(13)"
-	: "=r" (flags)
-	: "i" (offsetof(struct paca_struct, soft_enabled)));
+	asm volatile(
+		"lbz %0,%1(13)"
+		: "=r" (flags)
+		: "i" (offsetof(struct paca_struct, soft_enabled)));
 
 	return flags;
 }
 
-static inline unsigned long raw_local_irq_disable(void)
+static inline unsigned long arch_local_irq_disable(void)
 {
 	unsigned long flags, zero;
 
-	__asm__ __volatile__("li %1,0; lbz %0,%2(13); stb %1,%2(13)"
-	: "=r" (flags), "=&r" (zero)
-	: "i" (offsetof(struct paca_struct, soft_enabled))
-	: "memory");
+	asm volatile(
+		"li %1,0; lbz %0,%2(13); stb %1,%2(13)"
+		: "=r" (flags), "=&r" (zero)
+		: "i" (offsetof(struct paca_struct, soft_enabled))
+		: "memory");
 
 	return flags;
 }
 
-extern void raw_local_irq_restore(unsigned long);
+extern void arch_local_irq_restore(unsigned long);
 extern void iseries_handle_interrupts(void);
 
-#define raw_local_irq_enable()		raw_local_irq_restore(1)
-#define raw_local_save_flags(flags)	((flags) = local_get_flags())
-#define raw_local_irq_save(flags)	((flags) = raw_local_irq_disable())
+static inline void arch_local_irq_enable(void)
+{
+	arch_local_irq_restore(1);
+}
 
-#define raw_irqs_disabled()		(local_get_flags() == 0)
-#define raw_irqs_disabled_flags(flags)	((flags) == 0)
+static inline unsigned long arch_local_irq_save(void)
+{
+	return arch_local_irq_disable();
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return flags == 0;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
 
 #ifdef CONFIG_PPC_BOOK3E
-#define __hard_irq_enable()	__asm__ __volatile__("wrteei 1": : :"memory");
-#define __hard_irq_disable()	__asm__ __volatile__("wrteei 0": : :"memory");
+#define __hard_irq_enable()	asm volatile("wrteei 1" : : : "memory");
+#define __hard_irq_disable()	asm volatile("wrteei 0" : : : "memory");
 #else
 #define __hard_irq_enable()	__mtmsrd(mfmsr() | MSR_EE, 1)
 #define __hard_irq_disable()	__mtmsrd(mfmsr() & ~MSR_EE, 1)
@@ -64,64 +79,66 @@
 		get_paca()->hard_enabled = 0;	\
 	} while(0)
 
-#else
+#else /* CONFIG_PPC64 */
 
-#if defined(CONFIG_BOOKE)
 #define SET_MSR_EE(x)	mtmsr(x)
-#define raw_local_irq_restore(flags)	__asm__ __volatile__("wrtee %0" : : "r" (flags) : "memory")
-#else
-#define SET_MSR_EE(x)	mtmsr(x)
-#define raw_local_irq_restore(flags)	mtmsr(flags)
-#endif
 
-static inline void raw_local_irq_disable(void)
+static inline unsigned long arch_local_save_flags(void)
 {
-#ifdef CONFIG_BOOKE
-	__asm__ __volatile__("wrteei 0": : :"memory");
-#else
-	unsigned long msr;
+	return mfmsr();
+}
 
-	msr = mfmsr();
-	SET_MSR_EE(msr & ~MSR_EE);
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+#if defined(CONFIG_BOOKE)
+	asm volatile("wrtee %0" : : "r" (flags) : "memory");
+#else
+	mtmsr(flags);
 #endif
 }
 
-static inline void raw_local_irq_enable(void)
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags = arch_local_save_flags();
+#ifdef CONFIG_BOOKE
+	asm volatile("wrteei 0" : : : "memory");
+#else
+	SET_MSR_EE(flags & ~MSR_EE);
+#endif
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
 {
 #ifdef CONFIG_BOOKE
-	__asm__ __volatile__("wrteei 1": : :"memory");
+	asm volatile("wrteei 0" : : : "memory");
 #else
-	unsigned long msr;
+	arch_local_irq_save();
+#endif
+}
 
-	msr = mfmsr();
+static inline void arch_local_irq_enable(void)
+{
+#ifdef CONFIG_BOOKE
+	asm volatile("wrteei 1" : : : "memory");
+#else
+	unsigned long msr = mfmsr();
 	SET_MSR_EE(msr | MSR_EE);
 #endif
 }
 
-static inline void raw_local_irq_save_ptr(unsigned long *flags)
-{
-	unsigned long msr;
-	msr = mfmsr();
-	*flags = msr;
-#ifdef CONFIG_BOOKE
-	__asm__ __volatile__("wrteei 0": : :"memory");
-#else
-	SET_MSR_EE(msr & ~MSR_EE);
-#endif
-}
-
-#define raw_local_save_flags(flags)	((flags) = mfmsr())
-#define raw_local_irq_save(flags)	raw_local_irq_save_ptr(&flags)
-#define raw_irqs_disabled()		((mfmsr() & MSR_EE) == 0)
-#define raw_irqs_disabled_flags(flags)	(((flags) & MSR_EE) == 0)
-
-#define hard_irq_disable()		raw_local_irq_disable()
-
-static inline int irqs_disabled_flags(unsigned long flags)
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
 	return (flags & MSR_EE) == 0;
 }
 
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#define hard_irq_disable()		arch_local_irq_disable()
+
 #endif /* CONFIG_PPC64 */
 
 /*
diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h
index 5f68ecf..b85d8dd 100644
--- a/arch/powerpc/include/asm/irqflags.h
+++ b/arch/powerpc/include/asm/irqflags.h
@@ -6,7 +6,7 @@
 
 #ifndef __ASSEMBLY__
 /*
- * Get definitions for raw_local_save_flags(x), etc.
+ * Get definitions for arch_local_save_flags(x), etc.
  */
 #include <asm/hw_irq.h>
 
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 076327f..f54408d 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -91,6 +91,7 @@
 extern void crash_kexec_secondary(struct pt_regs *regs);
 extern int overlaps_crashkernel(unsigned long start, unsigned long size);
 extern void reserve_crashkernel(void);
+extern void machine_kexec_mask_interrupts(void);
 
 #else /* !CONFIG_KEXEC */
 static inline int kexec_sr_activated(int cpu) { return 0; }
diff --git a/arch/powerpc/include/asm/kvm_fpu.h b/arch/powerpc/include/asm/kvm_fpu.h
index c3d4f05..92daae1 100644
--- a/arch/powerpc/include/asm/kvm_fpu.h
+++ b/arch/powerpc/include/asm/kvm_fpu.h
@@ -82,7 +82,7 @@
 FPD_THREE_IN(fnmsub)
 FPD_THREE_IN(fnmadd)
 
-extern void kvm_cvt_fd(u32 *from, u64 *to, u64 *fpscr);
-extern void kvm_cvt_df(u64 *from, u32 *to, u64 *fpscr);
+extern void kvm_cvt_fd(u32 *from, u64 *to);
+extern void kvm_cvt_df(u64 *from, u32 *to);
 
 #endif
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 14b592d..7f5e0fe 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -153,6 +153,8 @@
 
 extern struct lppaca lppaca[];
 
+#define lppaca_of(cpu)	(*paca[cpu].lppaca_ptr)
+
 /*
  * SLB shadow buffer structure as defined in the PAPR.  The save_area
  * contains adjacent ESID and VSID pairs for each shadowed SLB.  The
@@ -170,6 +172,33 @@
 
 extern struct slb_shadow slb_shadow[];
 
+/*
+ * Layout of entries in the hypervisor's dispatch trace log buffer.
+ */
+struct dtl_entry {
+	u8	dispatch_reason;
+	u8	preempt_reason;
+	u16	processor_id;
+	u32	enqueue_to_dispatch_time;
+	u32	ready_to_enqueue_time;
+	u32	waiting_to_ready_time;
+	u64	timebase;
+	u64	fault_addr;
+	u64	srr0;
+	u64	srr1;
+};
+
+#define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
+#define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
+
+/*
+ * When CONFIG_VIRT_CPU_ACCOUNTING = y, the cpu accounting code controls
+ * reading from the dispatch trace log.  If other code wants to consume
+ * DTL entries, it can set this pointer to a function that will get
+ * called once for each DTL entry that gets processed.
+ */
+extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index);
+
 #endif /* CONFIG_PPC_BOOK3S */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_LPPACA_H */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index adc8e6c..d045b01 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -102,6 +102,9 @@
 	void		(*pci_dma_dev_setup)(struct pci_dev *dev);
 	void		(*pci_dma_bus_setup)(struct pci_bus *bus);
 
+	/* Platform set_dma_mask override */
+	int		(*dma_set_mask)(struct device *dev, u64 dma_mask);
+
 	int		(*probe)(void);
 	void		(*setup_arch)(void); /* Optional, may be NULL */
 	void		(*init_early)(void);
diff --git a/arch/powerpc/include/asm/memblock.h b/arch/powerpc/include/asm/memblock.h
index 3c29728..43efc34 100644
--- a/arch/powerpc/include/asm/memblock.h
+++ b/arch/powerpc/include/asm/memblock.h
@@ -5,11 +5,4 @@
 
 #define MEMBLOCK_DBG(fmt...) udbg_printf(fmt)
 
-#ifdef CONFIG_PPC32
-extern phys_addr_t lowmem_end_addr;
-#define MEMBLOCK_REAL_LIMIT	lowmem_end_addr
-#else
-#define MEMBLOCK_REAL_LIMIT	0
-#endif
-
 #endif /* _ASM_POWERPC_MEMBLOCK_H */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 87a1d78..8eaed81 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -114,6 +114,17 @@
 
 #define MAS7_RPN		0xFFFFFFFF
 
+/* Bit definitions for MMUCFG */
+#define MMUCFG_MAVN	0x00000003	/* MMU Architecture Version Number */
+#define MMUCFG_MAVN_V1	0x00000000	/* v1.0 */
+#define MMUCFG_MAVN_V2	0x00000001	/* v2.0 */
+#define MMUCFG_NTLBS	0x0000000c	/* Number of TLBs */
+#define MMUCFG_PIDSIZE	0x000007c0	/* PID Reg Size */
+#define MMUCFG_TWC	0x00008000	/* TLB Write Conditional (v2.0) */
+#define MMUCFG_LRAT	0x00010000	/* LRAT Supported (v2.0) */
+#define MMUCFG_RASIZE	0x00fe0000	/* Real Addr Size */
+#define MMUCFG_LPIDSIZE	0x0f000000	/* LPID Reg Size */
+
 /* Bit definitions for MMUCSR0 */
 #define MMUCSR0_TLB1FI	0x00000002	/* TLB1 Flash invalidate */
 #define MMUCSR0_TLB0FI	0x00000004	/* TLB0 Flash invalidate */
@@ -133,6 +144,10 @@
 #define TLBnCFG_GTWE		0x00010000	/* Guest can write */
 #define TLBnCFG_IND		0x00020000	/* IND entries supported */
 #define TLBnCFG_PT		0x00040000	/* Can load from page table */
+#define TLBnCFG_MINSIZE		0x00f00000	/* Minimum Page Size (v1.0) */
+#define TLBnCFG_MINSIZE_SHIFT	20
+#define TLBnCFG_MAXSIZE		0x000f0000	/* Maximum Page Size (v1.0) */
+#define TLBnCFG_MAXSIZE_SHIFT	16
 #define TLBnCFG_ASSOC		0xff000000	/* Associativity */
 
 /* TLBnPS encoding */
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 7ebf42e..bb40a06 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -2,6 +2,8 @@
 #define _ASM_POWERPC_MMU_H_
 #ifdef __KERNEL__
 
+#include <linux/types.h>
+
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 
@@ -82,6 +84,16 @@
 extern void early_init_mmu(void);
 extern void early_init_mmu_secondary(void);
 
+extern void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				       phys_addr_t first_memblock_size);
+
+#ifdef CONFIG_PPC64
+/* This is our real memory area size on ppc64 server, on embedded, we
+ * make it match the size our of bolted TLB area
+ */
+extern u64 ppc64_rma_size;
+#endif /* CONFIG_PPC64 */
+
 #endif /* !__ASSEMBLY__ */
 
 /* The kernel use the constants below to index in the page sizes array.
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 1ff6662..ec57540 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -85,6 +85,8 @@
 	u8 kexec_state;		/* set when kexec down has irqs off */
 #ifdef CONFIG_PPC_STD_MMU_64
 	struct slb_shadow *slb_shadow_ptr;
+	struct dtl_entry *dispatch_log;
+	struct dtl_entry *dispatch_log_end;
 
 	/*
 	 * Now, starting in cacheline 2, the exception save areas
@@ -129,13 +131,19 @@
 	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 hard_enabled;		/* set if irqs are enabled in MSR */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
-	u8 perf_event_pending;		/* PM interrupt while soft-disabled */
+	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
 
 	/* Stuff for accurate time accounting */
 	u64 user_time;			/* accumulated usermode TB ticks */
 	u64 system_time;		/* accumulated system TB ticks */
-	u64 startpurr;			/* PURR/TB value snapshot */
+	u64 user_time_scaled;		/* accumulated usermode SPURR ticks */
+	u64 starttime;			/* TB value snapshot */
+	u64 starttime_user;		/* TB value on exit to usermode */
 	u64 startspurr;			/* SPURR value snapshot */
+	u64 utime_sspurr;		/* ->user_time when ->startspurr set */
+	u64 stolen_time;		/* TB ticks taken by hypervisor */
+	u64 dtl_ridx;			/* read index in dispatch log */
+	struct dtl_entry *dtl_curr;	/* pointer corresponding to dtl_ridx */
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
 	/* We use this to store guest state in */
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 358ff14..932f88d 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -163,7 +163,7 @@
 #endif /* !CONFIG_HUGETLB_PAGE */
 
 #define VM_DATA_DEFAULT_FLAGS \
-	(test_thread_flag(TIF_32BIT) ? \
+	(is_32bit_task() ? \
 	 VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64)
 
 /*
@@ -179,7 +179,7 @@
 					 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
 #define VM_STACK_DEFAULT_FLAGS \
-	(test_thread_flag(TIF_32BIT) ? \
+	(is_32bit_task() ? \
 	 VM_STACK_DEFAULT_FLAGS32 : VM_STACK_DEFAULT_FLAGS64)
 
 #include <asm-generic/getorder.h>
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index 42fdff0..43268f1 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -28,8 +28,8 @@
 extern struct pci_dev *isa_bridge_pcidev;	/* may be NULL if no ISA bus */
 
 /** Bus Unit ID macros; get low and hi 32-bits of the 64-bit BUID */
-#define BUID_HI(buid) ((buid) >> 32)
-#define BUID_LO(buid) ((buid) & 0xffffffff)
+#define BUID_HI(buid) upper_32_bits(buid)
+#define BUID_LO(buid) lower_32_bits(buid)
 
 /* PCI device_node operations */
 struct device_node;
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 498fe09..9821006 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -9,6 +9,7 @@
 #include <asm/asm-compat.h>
 #include <asm/processor.h>
 #include <asm/ppc-opcode.h>
+#include <asm/firmware.h>
 
 #ifndef __ASSEMBLY__
 #error __FILE__ should only be used in assembler files
@@ -26,17 +27,13 @@
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 #define ACCOUNT_CPU_USER_ENTRY(ra, rb)
 #define ACCOUNT_CPU_USER_EXIT(ra, rb)
+#define ACCOUNT_STOLEN_TIME
 #else
 #define ACCOUNT_CPU_USER_ENTRY(ra, rb)					\
 	beq	2f;			/* if from kernel mode */	\
-BEGIN_FTR_SECTION;							\
-	mfspr	ra,SPRN_PURR;		/* get processor util. reg */	\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);					\
-BEGIN_FTR_SECTION;							\
-	MFTB(ra);			/* or get TB if no PURR */	\
-END_FTR_SECTION_IFCLR(CPU_FTR_PURR);					\
-	ld	rb,PACA_STARTPURR(r13);					\
-	std	ra,PACA_STARTPURR(r13);					\
+	MFTB(ra);			/* get timebase */		\
+	ld	rb,PACA_STARTTIME_USER(r13);				\
+	std	ra,PACA_STARTTIME(r13);					\
 	subf	rb,rb,ra;		/* subtract start value */	\
 	ld	ra,PACA_USER_TIME(r13);					\
 	add	ra,ra,rb;		/* add on to user time */	\
@@ -44,19 +41,34 @@
 2:
 
 #define ACCOUNT_CPU_USER_EXIT(ra, rb)					\
-BEGIN_FTR_SECTION;							\
-	mfspr	ra,SPRN_PURR;		/* get processor util. reg */	\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);					\
-BEGIN_FTR_SECTION;							\
-	MFTB(ra);			/* or get TB if no PURR */	\
-END_FTR_SECTION_IFCLR(CPU_FTR_PURR);					\
-	ld	rb,PACA_STARTPURR(r13);					\
-	std	ra,PACA_STARTPURR(r13);					\
+	MFTB(ra);			/* get timebase */		\
+	ld	rb,PACA_STARTTIME(r13);					\
+	std	ra,PACA_STARTTIME_USER(r13);				\
 	subf	rb,rb,ra;		/* subtract start value */	\
 	ld	ra,PACA_SYSTEM_TIME(r13);				\
-	add	ra,ra,rb;		/* add on to user time */	\
-	std	ra,PACA_SYSTEM_TIME(r13);
-#endif
+	add	ra,ra,rb;		/* add on to system time */	\
+	std	ra,PACA_SYSTEM_TIME(r13)
+
+#ifdef CONFIG_PPC_SPLPAR
+#define ACCOUNT_STOLEN_TIME						\
+BEGIN_FW_FTR_SECTION;							\
+	beq	33f;							\
+	/* from user - see if there are any DTL entries to process */	\
+	ld	r10,PACALPPACAPTR(r13);	/* get ptr to VPA */		\
+	ld	r11,PACA_DTL_RIDX(r13);	/* get log read index */	\
+	ld	r10,LPPACA_DTLIDX(r10);	/* get log write index */	\
+	cmpd	cr1,r11,r10;						\
+	beq+	cr1,33f;						\
+	bl	.accumulate_stolen_time;				\
+33:									\
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
+
+#else  /* CONFIG_PPC_SPLPAR */
+#define ACCOUNT_STOLEN_TIME
+
+#endif /* CONFIG_PPC_SPLPAR */
+
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
 /*
  * Macros for storing registers into and loading registers from
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 19c05b0..4c14187 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -118,7 +118,7 @@
 #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
 #define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_USER64 / 4))
 
-#define TASK_UNMAPPED_BASE ((test_thread_flag(TIF_32BIT)) ? \
+#define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
 		TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
 #endif
 
@@ -128,7 +128,7 @@
 #define STACK_TOP_USER64 TASK_SIZE_USER64
 #define STACK_TOP_USER32 TASK_SIZE_USER32
 
-#define STACK_TOP (test_thread_flag(TIF_32BIT) ? \
+#define STACK_TOP (is_32bit_task() ? \
 		   STACK_TOP_USER32 : STACK_TOP_USER64)
 
 #define STACK_TOP_MAX STACK_TOP_USER64
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index f2b3701..76bb195 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -171,6 +171,13 @@
 /* Make modules code happy. We don't set RO yet */
 #define PAGE_KERNEL_EXEC	PAGE_KERNEL_X
 
+/*
+ * Don't just check for any non zero bits in __PAGE_USER, since for book3e
+ * and PTE_64BIT, PAGE_KERNEL_X contains _PAGE_BAP_SR which is also in
+ * _PAGE_USER.  Need to explictly match _PAGE_BAP_UR bit in that case too.
+ */
+#define pte_user(val)		((val & _PAGE_USER) == _PAGE_USER)
+
 /* Advertise special mapping type for AGP */
 #define PAGE_AGP		(PAGE_KERNEL_NC)
 #define HAVE_PAGE_AGP
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 3d35f8a..9a1193e 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -187,6 +187,7 @@
 extern void rtas_initialize(void);
 extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
+extern int rtas_ibm_suspend_me(struct rtas_args *);
 
 struct rtc_time;
 extern unsigned long rtas_get_boot_time(void);
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 3d21266..aa0f1eb 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -329,3 +329,22 @@
 SYSCALL(fanotify_init)
 COMPAT_SYS(fanotify_mark)
 SYSCALL_SPU(prlimit64)
+SYSCALL_SPU(socket)
+SYSCALL_SPU(bind)
+SYSCALL_SPU(connect)
+SYSCALL_SPU(listen)
+SYSCALL_SPU(accept)
+SYSCALL_SPU(getsockname)
+SYSCALL_SPU(getpeername)
+SYSCALL_SPU(socketpair)
+SYSCALL_SPU(send)
+SYSCALL_SPU(sendto)
+COMPAT_SYS_SPU(recv)
+COMPAT_SYS_SPU(recvfrom)
+SYSCALL_SPU(shutdown)
+COMPAT_SYS_SPU(setsockopt)
+COMPAT_SYS_SPU(getsockopt)
+COMPAT_SYS_SPU(sendmsg)
+COMPAT_SYS_SPU(recvmsg)
+COMPAT_SYS_SPU(recvmmsg)
+SYSCALL_SPU(accept4)
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index 6c294ac..5e474dd 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -154,8 +154,8 @@
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
 extern int fix_alignment(struct pt_regs *);
-extern void cvt_fd(float *from, double *to, struct thread_struct *thread);
-extern void cvt_df(double *from, float *to, struct thread_struct *thread);
+extern void cvt_fd(float *from, double *to);
+extern void cvt_df(double *from, float *to);
 
 #ifndef CONFIG_SMP
 extern void discard_lazy_cpu_state(void);
@@ -542,10 +542,6 @@
 
 #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void account_system_vtime(struct task_struct *);
-#endif
-
 extern struct dentry *powerpc_debugfs_root;
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index dc779df..fe6f7c2 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -34,7 +34,6 @@
 extern void GregorianDay(struct rtc_time *tm);
 
 extern void generic_calibrate_decr(void);
-extern void snapshot_timebase(void);
 
 extern void set_dec_cpu6(unsigned int val);
 
@@ -212,12 +211,8 @@
 DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array);
 
 #if defined(CONFIG_VIRT_CPU_ACCOUNTING)
-extern void calculate_steal_time(void);
-extern void snapshot_timebases(void);
 #define account_process_vtime(tsk)		account_process_tick(tsk, 0)
 #else
-#define calculate_steal_time()			do { } while (0)
-#define snapshot_timebases()			do { } while (0)
 #define account_process_vtime(tsk)		do { } while (0)
 #endif
 
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 597e6f9..6151937 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -348,10 +348,29 @@
 #define __NR_fanotify_init	323
 #define __NR_fanotify_mark	324
 #define __NR_prlimit64		325
+#define __NR_socket		326
+#define __NR_bind		327
+#define __NR_connect		328
+#define __NR_listen		329
+#define __NR_accept		330
+#define __NR_getsockname	331
+#define __NR_getpeername	332
+#define __NR_socketpair		333
+#define __NR_send		334
+#define __NR_sendto		335
+#define __NR_recv		336
+#define __NR_recvfrom		337
+#define __NR_shutdown		338
+#define __NR_setsockopt		339
+#define __NR_getsockopt		340
+#define __NR_sendmsg		341
+#define __NR_recvmsg		342
+#define __NR_recvmmsg		343
+#define __NR_accept4		344
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		326
+#define __NR_syscalls		345
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 1dda701..4ed076a 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -55,7 +55,9 @@
 obj-$(CONFIG_IBMEBUS)           += ibmebus.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+ifeq ($(CONFIG_PPC32),y)
 obj-$(CONFIG_E500)		+= idle_e500.o
+endif
 obj-$(CONFIG_6xx)		+= idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
 obj-$(CONFIG_TAU)		+= tau_6xx.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o suspend.o
@@ -67,7 +69,7 @@
 obj64-$(CONFIG_HIBERNATION)	+= swsusp_asm64.o
 obj-$(CONFIG_MODULES)		+= module.o module_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_44x)		+= cpu_setup_44x.o
-obj-$(CONFIG_FSL_BOOKE)		+= cpu_setup_fsl_booke.o dbell.o
+obj-$(CONFIG_PPC_FSL_BOOK3E)	+= cpu_setup_fsl_booke.o dbell.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= dbell.o
 
 extra-y				:= head_$(CONFIG_WORD_SIZE).o
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index b876e989..8184ee9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -889,7 +889,7 @@
 #ifdef CONFIG_PPC_FPU
 			preempt_disable();
 			enable_kernel_fp();
-			cvt_df(&data.dd, (float *)&data.v[4], &current->thread);
+			cvt_df(&data.dd, (float *)&data.v[4]);
 			preempt_enable();
 #else
 			return 0;
@@ -933,7 +933,7 @@
 #ifdef CONFIG_PPC_FPU
 		preempt_disable();
 		enable_kernel_fp();
-		cvt_fd((float *)&data.v[4], &data.dd, &current->thread);
+		cvt_fd((float *)&data.v[4], &data.dd);
 		preempt_enable();
 #else
 		return 0;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1c0607d..c3e0194 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -61,7 +61,7 @@
 #endif
 #endif
 
-#if defined(CONFIG_FSL_BOOKE)
+#if defined(CONFIG_PPC_FSL_BOOK3E)
 #include "../mm/mmu_decl.h"
 #endif
 
@@ -181,17 +181,19 @@
 	       offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid));
 	DEFINE(SLBSHADOW_STACKESID,
 	       offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid));
+	DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area));
 	DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0));
 	DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1));
 	DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int));
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
-	DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area));
+	DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
+	DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
 #endif /* CONFIG_PPC_STD_MMU_64 */
 	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
 	DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
-	DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
-	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
+	DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
+	DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
@@ -468,7 +470,7 @@
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);
 	DEFINE(PTE_T_LOG2, PTE_T_LOG2);
 #endif
-#ifdef CONFIG_FSL_BOOKE
+#ifdef CONFIG_PPC_FSL_BOOK3E
 	DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
 	DEFINE(TLBCAM_MAS0, offsetof(struct tlbcam, MAS0));
 	DEFINE(TLBCAM_MAS1, offsetof(struct tlbcam, MAS1));
diff --git a/arch/powerpc/kernel/cpu_setup_44x.S b/arch/powerpc/kernel/cpu_setup_44x.S
index 7d606f8..e32b4a9 100644
--- a/arch/powerpc/kernel/cpu_setup_44x.S
+++ b/arch/powerpc/kernel/cpu_setup_44x.S
@@ -35,6 +35,7 @@
 _GLOBAL(__setup_cpu_460ex)
 _GLOBAL(__setup_cpu_460gt)
 _GLOBAL(__setup_cpu_460sx)
+_GLOBAL(__setup_cpu_apm821xx)
 	mflr	r4
 	bl	__init_fpu_44x
 	bl	__fixup_440A_mcheck
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 0adb50a..894e64f 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -51,6 +51,7 @@
 	isync
 	blr
 
+#ifdef CONFIG_PPC32
 _GLOBAL(__setup_cpu_e200)
 	/* enable dedicated debug exception handling resources (Debug APU) */
 	mfspr	r3,SPRN_HID0
@@ -72,3 +73,17 @@
 	bl	__setup_e500mc_ivors
 	mtlr	r4
 	blr
+#endif
+/* Right now, restore and setup are the same thing */
+_GLOBAL(__restore_cpu_e5500)
+_GLOBAL(__setup_cpu_e5500)
+	mflr	r4
+	bl	__e500_icache_setup
+	bl	__e500_dcache_setup
+#ifdef CONFIG_PPC_BOOK3E_64
+	bl	.__setup_base_ivors
+#else
+	bl	__setup_e500mc_ivors
+#endif
+	mtlr	r4
+	blr
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 1f9123f..96a908f 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -48,6 +48,7 @@
 extern void __setup_cpu_460ex(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_460gt(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_460sx(unsigned long offset, struct cpu_spec *spec);
+extern void __setup_cpu_apm821xx(unsigned long offset, struct cpu_spec *spec);
 extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec);
@@ -66,6 +67,10 @@
 extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power7(void);
 #endif /* CONFIG_PPC64 */
+#if defined(CONFIG_E500)
+extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
+extern void __restore_cpu_e5500(void);
+#endif /* CONFIG_E500 */
 
 /* This table only contains "desktop" CPUs, it need to be filled with embedded
  * ones as well...
@@ -1805,6 +1810,20 @@
 		.machine_check		= machine_check_440A,
 		.platform		= "ppc440",
 	},
+	{ /* 464 in APM821xx */
+		.pvr_mask		= 0xffffff00,
+		.pvr_value		= 0x12C41C80,
+		.cpu_name		= "APM821XX",
+		.cpu_features		= CPU_FTRS_44X,
+		.cpu_user_features	= COMMON_USER_BOOKE |
+			PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_44x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.cpu_setup		= __setup_cpu_apm821xx,
+		.machine_check		= machine_check_440A,
+		.platform		= "ppc440",
+	},
 	{ /* 476 core */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x11a50000,
@@ -1891,7 +1910,9 @@
 		.platform		= "ppc5554",
 	}
 #endif /* CONFIG_E200 */
+#endif /* CONFIG_PPC32 */
 #ifdef CONFIG_E500
+#ifdef CONFIG_PPC32
 	{	/* e500 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x80200000,
@@ -1946,6 +1967,26 @@
 		.machine_check		= machine_check_e500mc,
 		.platform		= "ppce500mc",
 	},
+#endif /* CONFIG_PPC32 */
+	{	/* e5500 */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x80240000,
+		.cpu_name		= "e5500",
+		.cpu_features		= CPU_FTRS_E500MC,
+		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
+			MMU_FTR_USE_TLBILX,
+		.icache_bsize		= 64,
+		.dcache_bsize		= 64,
+		.num_pmcs		= 4,
+		.oprofile_cpu_type	= "ppc/e500mc",
+		.oprofile_type		= PPC_OPROFILE_FSL_EMB,
+		.cpu_setup		= __setup_cpu_e5500,
+		.cpu_restore		= __restore_cpu_e5500,
+		.machine_check		= machine_check_e500mc,
+		.platform		= "ppce5500",
+	},
+#ifdef CONFIG_PPC32
 	{	/* default match */
 		.pvr_mask		= 0x00000000,
 		.pvr_value		= 0x00000000,
@@ -1960,8 +2001,8 @@
 		.machine_check		= machine_check_e500,
 		.platform		= "powerpc",
 	}
-#endif /* CONFIG_E500 */
 #endif /* CONFIG_PPC32 */
+#endif /* CONFIG_E500 */
 
 #ifdef CONFIG_PPC_BOOK3E_64
 	{	/* This is a default entry to get going, to be replaced by
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 4457382..832c8c4 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -414,18 +414,7 @@
 	crash_kexec_wait_realmode(crashing_cpu);
 #endif
 
-	for_each_irq(i) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		if (!desc || !desc->chip || !desc->chip->eoi)
-			continue;
-
-		if (desc->status & IRQ_INPROGRESS)
-			desc->chip->eoi(i);
-
-		if (!(desc->status & IRQ_DISABLED))
-			desc->chip->shutdown(i);
-	}
+	machine_kexec_mask_interrupts();
 
 	/*
 	 * Call registered shutdown routines savely.  Swap out
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 37771a5..6e54a0f 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -74,16 +74,17 @@
 {
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
-	if (!tbl || tbl->it_offset > mask) {
-		printk(KERN_INFO
-		       "Warning: IOMMU offset too big for device mask\n");
-		if (tbl)
-			printk(KERN_INFO
-			       "mask: 0x%08llx, table offset: 0x%08lx\n",
-				mask, tbl->it_offset);
-		else
-			printk(KERN_INFO "mask: 0x%08llx, table unavailable\n",
-				mask);
+	if (!tbl) {
+		dev_info(dev, "Warning: IOMMU dma not supported: mask 0x%08llx"
+			", table unavailable\n", mask);
+		return 0;
+	}
+
+	if ((tbl->it_offset + tbl->it_size) > (mask >> IOMMU_PAGE_SHIFT)) {
+		dev_info(dev, "Warning: IOMMU window too big for device mask\n");
+		dev_info(dev, "mask: 0x%08llx, table end: 0x%08lx\n",
+				mask, (tbl->it_offset + tbl->it_size) <<
+				IOMMU_PAGE_SHIFT);
 		return 0;
 	} else
 		return 1;
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 84d6367..cf02cad 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -12,6 +12,7 @@
 #include <linux/memblock.h>
 #include <asm/bug.h>
 #include <asm/abs_addr.h>
+#include <asm/machdep.h>
 
 /*
  * Generic direct DMA implementation
@@ -89,7 +90,7 @@
 	/* Could be improved so platforms can set the limit in case
 	 * they have limited DMA windows
 	 */
-	return mask >= (memblock_end_of_DRAM() - 1);
+	return mask >= get_dma_offset(dev) + (memblock_end_of_DRAM() - 1);
 #else
 	return 1;
 #endif
@@ -154,6 +155,23 @@
 
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
 
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+	if (ppc_md.dma_set_mask)
+		return ppc_md.dma_set_mask(dev, dma_mask);
+	if (unlikely(dma_ops == NULL))
+		return -EIO;
+	if (dma_ops->set_dma_mask != NULL)
+		return dma_ops->set_dma_mask(dev, dma_mask);
+	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
+		return -EIO;
+	*dev->dma_mask = dma_mask;
+	return 0;
+}
+EXPORT_SYMBOL(dma_set_mask);
+
 static int __init dma_init(void)
 {
        dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 42e9d90..d82878c 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -97,6 +97,24 @@
 	addi	r9,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r9)		/* "regshere" marker */
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR)
+BEGIN_FW_FTR_SECTION
+	beq	33f
+	/* if from user, see if there are any DTL entries to process */
+	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
+	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
+	ld	r10,LPPACA_DTLIDX(r10)	/* get log write index */
+	cmpd	cr1,r11,r10
+	beq+	cr1,33f
+	bl	.accumulate_stolen_time
+	REST_GPR(0,r1)
+	REST_4GPRS(3,r1)
+	REST_2GPRS(7,r1)
+	addi	r9,r1,STACK_FRAME_OVERHEAD
+33:
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING && CONFIG_PPC_SPLPAR */
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	.trace_hardirqs_on
 	REST_GPR(0,r1)
@@ -202,7 +220,9 @@
 	bge-	syscall_error
 syscall_error_cont:
 	ld	r7,_NIP(r1)
+BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1			/* to clear the reservation */
+END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	andi.	r6,r8,MSR_PR
 	ld	r4,_LINK(r1)
 	/*
@@ -419,6 +439,17 @@
 	sync
 #endif /* CONFIG_SMP */
 
+	/*
+	 * If we optimise away the clear of the reservation in system
+	 * calls because we know the CPU tracks the address of the
+	 * reservation, then we need to clear it here to cover the
+	 * case that the kernel context switch path has no larx
+	 * instructions.
+	 */
+BEGIN_FTR_SECTION
+	ldarx	r6,0,r1
+END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS)
+
 	addi	r6,r4,-THREAD	/* Convert THREAD to 'current' */
 	std	r6,PACACURRENT(r13)	/* Set new 'current' */
 
@@ -576,7 +607,16 @@
 	andi.	r0,r3,MSR_RI
 	beq-	unrecov_restore
 
+	/*
+	 * Clear the reservation. If we know the CPU tracks the address of
+	 * the reservation then we can potentially save some cycles and use
+	 * a larx. On POWER6 and POWER7 this is significantly faster.
+	 */
+BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1		/* to clear the reservation */
+FTR_SECTION_ELSE
+	ldarx	r4,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	/*
 	 * Clear RI before restoring r13.  If we are returning to
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f53029a..39b0c48 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -818,12 +818,12 @@
 
 	/*
 	 * hash_page couldn't handle it, set soft interrupt enable back
-	 * to what it was before the trap.  Note that .raw_local_irq_restore
+	 * to what it was before the trap.  Note that .arch_local_irq_restore
 	 * handles any interrupts pending at this point.
 	 */
 	ld	r3,SOFTE(r1)
 	TRACE_AND_RESTORE_IRQ_PARTIAL(r3, 11f)
-	bl	.raw_local_irq_restore
+	bl	.arch_local_irq_restore
 	b	11f
 
 /* We have a data breakpoint exception - handle it */
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index fc8f5b1..e86c040 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -163,24 +163,14 @@
 /*
  * These are used in the alignment trap handler when emulating
  * single-precision loads and stores.
- * We restore and save the fpscr so the task gets the same result
- * and exceptions as if the cpu had performed the load or store.
  */
 
 _GLOBAL(cvt_fd)
-	lfd	0,THREAD_FPSCR(r5)	/* load up fpscr value */
-	MTFSF_L(0)
 	lfs	0,0(r3)
 	stfd	0,0(r4)
-	mffs	0
-	stfd	0,THREAD_FPSCR(r5)	/* save new fpscr value */
 	blr
 
 _GLOBAL(cvt_df)
-	lfd	0,THREAD_FPSCR(r5)	/* load up fpscr value */
-	MTFSF_L(0)
 	lfd	0,0(r3)
 	stfs	0,0(r4)
-	mffs	0
-	stfd	0,THREAD_FPSCR(r5)	/* save new fpscr value */
 	blr
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index a90625f..8278e8b 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -923,11 +923,7 @@
 	mtspr	SPRN_PID,r0
 	sync
 
-	/* Configure and load two entries into TLB slots 62 and 63.
-	 * In case we are pinning TLBs, these are reserved in by the
-	 * other TLB functions.  If not reserving, then it doesn't
-	 * matter where they are loaded.
-	 */
+	/* Configure and load one entry into TLB slots 63 */
 	clrrwi	r4,r4,10		/* Mask off the real page number */
 	ori	r4,r4,(TLB_WR | TLB_EX)	/* Set the write and execute bits */
 
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 4faeba2..529b817 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -152,8 +152,11 @@
 	/* Check to see if we're the second processor, and jump
 	 * to the secondary_start code if so
 	 */
-	mfspr	r24,SPRN_PIR
-	cmpwi	r24,0
+	lis	r24, boot_cpuid@h
+	ori	r24, r24, boot_cpuid@l
+	lwz	r24, 0(r24)
+	cmpwi	r24, -1
+	mfspr   r24,SPRN_PIR
 	bne	__secondary_start
 #endif
 
@@ -175,6 +178,9 @@
 	li	r0,0
 	stwu	r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
 
+	rlwinm  r22,r1,0,0,31-THREAD_SHIFT      /* current thread_info */
+	stw	r24, TI_CPU(r22)
+
 	bl	early_init
 
 #ifdef CONFIG_RELOCATABLE
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 4a65386..ce557f6 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -116,7 +116,7 @@
 	: : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
 }
 
-notrace void raw_local_irq_restore(unsigned long en)
+notrace void arch_local_irq_restore(unsigned long en)
 {
 	/*
 	 * get_paca()->soft_enabled = en;
@@ -192,7 +192,7 @@
 
 	__hard_irq_enable();
 }
-EXPORT_SYMBOL(raw_local_irq_restore);
+EXPORT_SYMBOL(arch_local_irq_restore);
 #endif /* CONFIG_PPC64 */
 
 static int show_other_interrupts(struct seq_file *p, int prec)
@@ -587,8 +587,10 @@
 			 * this will be fixed once slab is made available early
 			 * instead of the current cruft
 			 */
-			if (mem_init_done)
+			if (mem_init_done) {
+				of_node_put(host->of_node);
 				kfree(host);
+			}
 			return NULL;
 		}
 		irq_map[0].host = host;
@@ -1143,7 +1145,7 @@
 	unsigned long flags;
 	struct irq_desc *desc;
 	const char *p;
-	char none[] = "none";
+	static const char none[] = "none";
 	int i;
 
 	seq_printf(m, "%-5s  %-7s  %-15s  %s\n", "virq", "hwirq",
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index 50362b6..1646836 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -56,7 +56,7 @@
 
 	for_each_possible_cpu(cpu) {
 		if (firmware_has_feature(FW_FEATURE_ISERIES))
-			sum_purr += lppaca[cpu].emulated_time_base;
+			sum_purr += lppaca_of(cpu).emulated_time_base;
 		else {
 			struct cpu_usage *cu;
 
@@ -263,7 +263,7 @@
 	           ppp_data.active_system_procs);
 
 	/* pool related entries are apropriate for shared configs */
-	if (lppaca[0].shared_proc) {
+	if (lppaca_of(0).shared_proc) {
 		unsigned long pool_idle_time, pool_procs;
 
 		seq_printf(m, "pool=%d\n", ppp_data.pool_num);
@@ -460,8 +460,8 @@
 		return;
 
 	for_each_possible_cpu(cpu) {
-		cmo_faults += lppaca[cpu].cmo_faults;
-		cmo_fault_time += lppaca[cpu].cmo_fault_time;
+		cmo_faults += lppaca_of(cpu).cmo_faults;
+		cmo_fault_time += lppaca_of(cpu).cmo_fault_time;
 	}
 
 	seq_printf(m, "cmo_faults=%lu\n", cmo_faults);
@@ -479,8 +479,8 @@
 	unsigned long dispatch_dispersions = 0;
 
 	for_each_possible_cpu(cpu) {
-		dispatches += lppaca[cpu].yield_count;
-		dispatch_dispersions += lppaca[cpu].dispersion_count;
+		dispatches += lppaca_of(cpu).yield_count;
+		dispatch_dispersions += lppaca_of(cpu).dispersion_count;
 	}
 
 	seq_printf(m, "dispatches=%lu\n", dispatches);
@@ -545,7 +545,7 @@
 	seq_printf(m, "partition_potential_processors=%d\n",
 		   partition_potential_processors);
 
-	seq_printf(m, "shared_processor_mode=%d\n", lppaca[0].shared_proc);
+	seq_printf(m, "shared_processor_mode=%d\n", lppaca_of(0).shared_proc);
 
 	seq_printf(m, "slb_size=%d\n", mmu_slb_size);
 
@@ -780,6 +780,7 @@
 	.write		= lparcfg_write,
 	.open		= lparcfg_open,
 	.release	= single_release,
+	.llseek		= seq_lseek,
 };
 
 static int __init lparcfg_init(void)
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index dd6c141..df7e20c 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -14,10 +14,34 @@
 #include <linux/threads.h>
 #include <linux/memblock.h>
 #include <linux/of.h>
+#include <linux/irq.h>
+
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/sections.h>
 
+void machine_kexec_mask_interrupts(void) {
+	unsigned int i;
+
+	for_each_irq(i) {
+		struct irq_desc *desc = irq_to_desc(i);
+
+		if (!desc || !desc->chip)
+			continue;
+
+		if (desc->chip->eoi &&
+		    desc->status & IRQ_INPROGRESS)
+			desc->chip->eoi(i);
+
+		if (desc->chip->mask)
+			desc->chip->mask(i);
+
+		if (desc->chip->disable &&
+		    !(desc->status & IRQ_DISABLED))
+			desc->chip->disable(i);
+	}
+}
+
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	if (ppc_md.machine_crash_shutdown)
diff --git a/arch/powerpc/kernel/machine_kexec_32.c b/arch/powerpc/kernel/machine_kexec_32.c
index ae63a96..e63f2e7 100644
--- a/arch/powerpc/kernel/machine_kexec_32.c
+++ b/arch/powerpc/kernel/machine_kexec_32.c
@@ -39,6 +39,10 @@
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
 
+	/* mask each interrupt so we are in a more sane state for the
+	 * kexec kernel */
+	machine_kexec_mask_interrupts();
+
 	page_list = image->head;
 
 	/* we need both effective and real address here */
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index d0a26f1..ebf9846 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -27,6 +27,20 @@
 #ifdef CONFIG_PPC_BOOK3S
 
 /*
+ * We only have to have statically allocated lppaca structs on
+ * legacy iSeries, which supports at most 64 cpus.
+ */
+#ifdef CONFIG_PPC_ISERIES
+#if NR_CPUS < 64
+#define NR_LPPACAS	NR_CPUS
+#else
+#define NR_LPPACAS	64
+#endif
+#else /* not iSeries */
+#define NR_LPPACAS	1
+#endif
+
+/*
  * The structure which the hypervisor knows about - this structure
  * should not cross a page boundary.  The vpa_init/register_vpa call
  * is now known to fail if the lppaca structure crosses a page
@@ -36,7 +50,7 @@
  * will suffice to ensure that it doesn't cross a page boundary.
  */
 struct lppaca lppaca[] = {
-	[0 ... (NR_CPUS-1)] = {
+	[0 ... (NR_LPPACAS-1)] = {
 		.desc = 0xd397d781,	/* "LpPa" */
 		.size = sizeof(struct lppaca),
 		.dyn_proc_status = 2,
@@ -49,6 +63,54 @@
 	},
 };
 
+static struct lppaca *extra_lppacas;
+static long __initdata lppaca_size;
+
+static void allocate_lppacas(int nr_cpus, unsigned long limit)
+{
+	if (nr_cpus <= NR_LPPACAS)
+		return;
+
+	lppaca_size = PAGE_ALIGN(sizeof(struct lppaca) *
+				 (nr_cpus - NR_LPPACAS));
+	extra_lppacas = __va(memblock_alloc_base(lppaca_size,
+						 PAGE_SIZE, limit));
+}
+
+static struct lppaca *new_lppaca(int cpu)
+{
+	struct lppaca *lp;
+
+	if (cpu < NR_LPPACAS)
+		return &lppaca[cpu];
+
+	lp = extra_lppacas + (cpu - NR_LPPACAS);
+	*lp = lppaca[0];
+
+	return lp;
+}
+
+static void free_lppacas(void)
+{
+	long new_size = 0, nr;
+
+	if (!lppaca_size)
+		return;
+	nr = num_possible_cpus() - NR_LPPACAS;
+	if (nr > 0)
+		new_size = PAGE_ALIGN(nr * sizeof(struct lppaca));
+	if (new_size >= lppaca_size)
+		return;
+
+	memblock_free(__pa(extra_lppacas) + new_size, lppaca_size - new_size);
+	lppaca_size = new_size;
+}
+
+#else
+
+static inline void allocate_lppacas(int nr_cpus, unsigned long limit) { }
+static inline void free_lppacas(void) { }
+
 #endif /* CONFIG_PPC_BOOK3S */
 
 #ifdef CONFIG_PPC_STD_MMU_64
@@ -88,7 +150,7 @@
 	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
 
 #ifdef CONFIG_PPC_BOOK3S
-	new_paca->lppaca_ptr = &lppaca[cpu];
+	new_paca->lppaca_ptr = new_lppaca(cpu);
 #else
 	new_paca->kernel_pgd = swapper_pg_dir;
 #endif
@@ -127,7 +189,7 @@
 	 * the first segment. On iSeries they must be within the area mapped
 	 * by the HV, which is HvPagesToMap * HVPAGESIZE bytes.
 	 */
-	limit = min(0x10000000ULL, memblock.rmo_size);
+	limit = min(0x10000000ULL, ppc64_rma_size);
 	if (firmware_has_feature(FW_FEATURE_ISERIES))
 		limit = min(limit, HvPagesToMap * HVPAGESIZE);
 
@@ -144,6 +206,8 @@
 	printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n",
 		paca_size, nr_cpus, paca);
 
+	allocate_lppacas(nr_cpus, limit);
+
 	/* Can't use for_each_*_cpu, as they aren't functional yet */
 	for (cpu = 0; cpu < nr_cpus; cpu++)
 		initialise_paca(&paca[cpu], cpu);
@@ -164,4 +228,6 @@
 		paca_size - new_size);
 
 	paca_size = new_size;
+
+	free_lppacas();
 }
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 9021c4a..10a44e6 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1090,8 +1090,6 @@
 		 bus->number, bus->self ? pci_name(bus->self) : "PHB");
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		struct dev_archdata *sd = &dev->dev.archdata;
-
 		/* Cardbus can call us to add new devices to a bus, so ignore
 		 * those who are already fully discovered
 		 */
@@ -1107,7 +1105,7 @@
 		set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
 
 		/* Hook up default DMA ops */
-		sd->dma_ops = pci_dma_ops;
+		set_dma_ops(&dev->dev, pci_dma_ops);
 		set_dma_offset(&dev->dev, PCI_DRAM_OFFSET);
 
 		/* Additional platform DMA/iommu setup */
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index 95ad9da..d05ae42 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -23,18 +23,6 @@
 #include "ppc32.h"
 #endif
 
-/*
- * Store another value in a callchain_entry.
- */
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	unsigned int nr = entry->nr;
-
-	if (nr < PERF_MAX_STACK_DEPTH) {
-		entry->ip[nr] = ip;
-		entry->nr = nr + 1;
-	}
-}
 
 /*
  * Is sp valid as the address of the next kernel stack frame after prev_sp?
@@ -58,8 +46,8 @@
 	return 0;
 }
 
-static void perf_callchain_kernel(struct pt_regs *regs,
-				  struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -69,8 +57,7 @@
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->nip);
+	perf_callchain_store(entry, regs->nip);
 
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return;
@@ -89,7 +76,7 @@
 			next_ip = regs->nip;
 			lr = regs->link;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_KERNEL);
+			perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 
 		} else {
 			if (level == 0)
@@ -111,7 +98,7 @@
 			++level;
 		}
 
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		if (!valid_next_sp(next_sp, sp))
 			return;
 		sp = next_sp;
@@ -233,8 +220,8 @@
 		puc == (unsigned long) &sf->uc;
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -246,8 +233,7 @@
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, next_ip);
+	perf_callchain_store(entry, next_ip);
 
 	for (;;) {
 		fp = (unsigned long __user *) sp;
@@ -276,14 +262,14 @@
 			    read_user_stack_64(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
@@ -315,8 +301,8 @@
 	return __get_user_inatomic(*ret, ptr);
 }
 
-static inline void perf_callchain_user_64(struct pt_regs *regs,
-					  struct perf_callchain_entry *entry)
+static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
+					  struct pt_regs *regs)
 {
 }
 
@@ -435,8 +421,8 @@
 	return mctx->mc_gregs;
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned int sp, next_sp;
 	unsigned int next_ip;
@@ -447,8 +433,7 @@
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, next_ip);
+	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		fp = (unsigned int __user *) (unsigned long) sp;
@@ -470,45 +455,24 @@
 			    read_user_stack_32(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
 }
 
-/*
- * Since we can't get PMU interrupts inside a PMU interrupt handler,
- * we don't need separate irq and nmi entries here.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain);
-
-	entry->nr = 0;
-
-	if (!user_mode(regs)) {
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		if (current_is_64bit())
-			perf_callchain_user_64(regs, entry);
-		else
-			perf_callchain_user_32(regs, entry);
-	}
-
-	return entry;
+	if (current_is_64bit())
+		perf_callchain_user_64(entry, regs);
+	else
+		perf_callchain_user_32(entry, regs);
 }
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index d301a30..3129c85 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -402,6 +402,9 @@
 {
 	s64 val, delta, prev;
 
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	if (!event->hw.idx)
 		return;
 	/*
@@ -517,7 +520,7 @@
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void power_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -565,7 +568,7 @@
  * If we were previously disabled and events were added, then
  * put the new config on the PMU.
  */
-void hw_perf_enable(void)
+static void power_pmu_enable(struct pmu *pmu)
 {
 	struct perf_event *event;
 	struct cpu_hw_events *cpuhw;
@@ -672,6 +675,8 @@
 		}
 		local64_set(&event->hw.prev_count, val);
 		event->hw.idx = idx;
+		if (event->hw.state & PERF_HES_STOPPED)
+			val = 0;
 		write_pmc(idx, val);
 		perf_event_update_userpage(event);
 	}
@@ -727,7 +732,7 @@
  * re-enable the PMU in order to get hw_perf_enable to do the
  * actual work of reconfiguring the PMU.
  */
-static int power_pmu_enable(struct perf_event *event)
+static int power_pmu_add(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -735,7 +740,7 @@
 	int ret = -EAGAIN;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	/*
 	 * Add the event to the list (if there is room)
@@ -749,6 +754,9 @@
 	cpuhw->events[n0] = event->hw.config;
 	cpuhw->flags[n0] = event->hw.event_base;
 
+	if (!(ef_flags & PERF_EF_START))
+		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
@@ -769,7 +777,7 @@
 
 	ret = 0;
  out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
@@ -777,14 +785,14 @@
 /*
  * Remove a event from the PMU.
  */
-static void power_pmu_disable(struct perf_event *event)
+static void power_pmu_del(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuhw;
 	long i;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	power_pmu_read(event);
 
@@ -821,34 +829,60 @@
 		cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE);
 	}
 
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
 /*
- * Re-enable interrupts on a event after they were throttled
- * because they were coming too fast.
+ * POWER-PMU does not support disabling individual counters, hence
+ * program their cycle counter to their max value and ignore the interrupts.
  */
-static void power_pmu_unthrottle(struct perf_event *event)
+
+static void power_pmu_start(struct perf_event *event, int ef_flags)
 {
-	s64 val, left;
+	unsigned long flags;
+	s64 left;
+
+	if (!event->hw.idx || !event->hw.sample_period)
+		return;
+
+	if (!(event->hw.state & PERF_HES_STOPPED))
+		return;
+
+	if (ef_flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = 0;
+	left = local64_read(&event->hw.period_left);
+	write_pmc(event->hw.idx, left);
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
+
+static void power_pmu_stop(struct perf_event *event, int ef_flags)
+{
 	unsigned long flags;
 
 	if (!event->hw.idx || !event->hw.sample_period)
 		return;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
+
 	power_pmu_read(event);
-	left = event->hw.sample_period;
-	event->hw.last_period = left;
-	val = 0;
-	if (left < 0x80000000L)
-		val = 0x80000000L - left;
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	write_pmc(event->hw.idx, 0);
+
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -857,10 +891,11 @@
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-void power_pmu_start_txn(const struct pmu *pmu)
+void power_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 	cpuhw->n_txn_start = cpuhw->n_events;
 }
@@ -870,11 +905,12 @@
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-void power_pmu_cancel_txn(const struct pmu *pmu)
+void power_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -882,7 +918,7 @@
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-int power_pmu_commit_txn(const struct pmu *pmu)
+int power_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	long i, n;
@@ -901,19 +937,10 @@
 		cpuhw->event[i]->hw.config = cpuhw->events[i];
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-struct pmu power_pmu = {
-	.enable		= power_pmu_enable,
-	.disable	= power_pmu_disable,
-	.read		= power_pmu_read,
-	.unthrottle	= power_pmu_unthrottle,
-	.start_txn	= power_pmu_start_txn,
-	.cancel_txn	= power_pmu_cancel_txn,
-	.commit_txn	= power_pmu_commit_txn,
-};
-
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
@@ -1014,7 +1041,7 @@
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int power_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
 	unsigned long flags;
@@ -1026,25 +1053,27 @@
 	struct cpu_hw_events *cpuhw;
 
 	if (!ppmu)
-		return ERR_PTR(-ENXIO);
+		return -ENOENT;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
-			return ERR_PTR(-EOPNOTSUPP);
+			return -EOPNOTSUPP;
 		ev = ppmu->generic_events[ev];
 		break;
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
-			return ERR_PTR(err);
+			return err;
 		break;
 	case PERF_TYPE_RAW:
 		ev = event->attr.config;
 		break;
 	default:
-		return ERR_PTR(-EINVAL);
+		return -ENOENT;
 	}
+
 	event->hw.config_base = ev;
 	event->hw.idx = 0;
 
@@ -1063,7 +1092,7 @@
 	 * XXX we should check if the task is an idle task.
 	 */
 	flags = 0;
-	if (event->ctx->task)
+	if (event->attach_state & PERF_ATTACH_TASK)
 		flags |= PPMU_ONLY_COUNT_RUN;
 
 	/*
@@ -1081,7 +1110,7 @@
 			 */
 			ev = normal_pmc_alternative(ev, flags);
 			if (!ev)
-				return ERR_PTR(-EINVAL);
+				return -EINVAL;
 		}
 	}
 
@@ -1095,19 +1124,19 @@
 		n = collect_events(event->group_leader, ppmu->n_counter - 1,
 				   ctrs, events, cflags);
 		if (n < 0)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 	events[n] = ev;
 	ctrs[n] = event;
 	cflags[n] = flags;
 	if (check_excludes(ctrs, cflags, n, 1))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	cpuhw = &get_cpu_var(cpu_hw_events);
 	err = power_check_constraints(cpuhw, events, cflags, n + 1);
 	put_cpu_var(cpu_hw_events);
 	if (err)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	event->hw.config = events[n];
 	event->hw.event_base = cflags[n];
@@ -1132,11 +1161,23 @@
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
-		return ERR_PTR(err);
-	return &power_pmu;
+	return err;
 }
 
+struct pmu power_pmu = {
+	.pmu_enable	= power_pmu_enable,
+	.pmu_disable	= power_pmu_disable,
+	.event_init	= power_pmu_event_init,
+	.add		= power_pmu_add,
+	.del		= power_pmu_del,
+	.start		= power_pmu_start,
+	.stop		= power_pmu_stop,
+	.read		= power_pmu_read,
+	.start_txn	= power_pmu_start_txn,
+	.cancel_txn	= power_pmu_cancel_txn,
+	.commit_txn	= power_pmu_commit_txn,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -1149,6 +1190,11 @@
 	s64 prev, delta, left;
 	int record = 0;
 
+	if (event->hw.state & PERF_HES_STOPPED) {
+		write_pmc(event->hw.idx, 0);
+		return;
+	}
+
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
@@ -1171,6 +1217,11 @@
 			val = 0x80000000LL - left;
 	}
 
+	write_pmc(event->hw.idx, val);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+
 	/*
 	 * Finally record data if requested.
 	 */
@@ -1183,23 +1234,9 @@
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
 			perf_get_data_addr(regs, &data.addr);
 
-		if (perf_event_overflow(event, nmi, &data, regs)) {
-			/*
-			 * Interrupts are coming too fast - throttle them
-			 * by setting the event to 0, so it will be
-			 * at least 2^30 cycles until the next interrupt
-			 * (assuming each event counts at most 2 counts
-			 * per cycle).
-			 */
-			val = 0;
-			left = ~0ULL >> 1;
-		}
+		if (perf_event_overflow(event, nmi, &data, regs))
+			power_pmu_stop(event, 0);
 	}
-
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
-	perf_event_update_userpage(event);
 }
 
 /*
@@ -1342,6 +1379,7 @@
 		freeze_events_kernel = MMCR0_FCHV;
 #endif /* CONFIG_PPC64 */
 
+	perf_pmu_register(&power_pmu);
 	perf_cpu_notifier(power_pmu_notifier);
 
 	return 0;
diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c
index 1ba4547..7ecca59 100644
--- a/arch/powerpc/kernel/perf_event_fsl_emb.c
+++ b/arch/powerpc/kernel/perf_event_fsl_emb.c
@@ -156,6 +156,9 @@
 {
 	s64 val, delta, prev;
 
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	/*
 	 * Performance monitor interrupts come even when interrupts
 	 * are soft-disabled, as long as interrupts are hard-enabled.
@@ -177,7 +180,7 @@
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void fsl_emb_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -216,7 +219,7 @@
  * If we were previously disabled and events were added, then
  * put the new config on the PMU.
  */
-void hw_perf_enable(void)
+static void fsl_emb_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -262,8 +265,8 @@
 	return n;
 }
 
-/* perf must be disabled, context locked on entry */
-static int fsl_emb_pmu_enable(struct perf_event *event)
+/* context locked on entry */
+static int fsl_emb_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuhw;
 	int ret = -EAGAIN;
@@ -271,6 +274,7 @@
 	u64 val;
 	int i;
 
+	perf_pmu_disable(event->pmu);
 	cpuhw = &get_cpu_var(cpu_hw_events);
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)
@@ -301,6 +305,12 @@
 			val = 0x80000000L - left;
 	}
 	local64_set(&event->hw.prev_count, val);
+
+	if (!(flags & PERF_EF_START)) {
+		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+		val = 0;
+	}
+
 	write_pmc(i, val);
 	perf_event_update_userpage(event);
 
@@ -310,15 +320,17 @@
 	ret = 0;
  out:
 	put_cpu_var(cpu_hw_events);
+	perf_pmu_enable(event->pmu);
 	return ret;
 }
 
-/* perf must be disabled, context locked on entry */
-static void fsl_emb_pmu_disable(struct perf_event *event)
+/* context locked on entry */
+static void fsl_emb_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuhw;
 	int i = event->hw.idx;
 
+	perf_pmu_disable(event->pmu);
 	if (i < 0)
 		goto out;
 
@@ -346,45 +358,58 @@
 	cpuhw->n_events--;
 
  out:
+	perf_pmu_enable(event->pmu);
 	put_cpu_var(cpu_hw_events);
 }
 
-/*
- * Re-enable interrupts on a event after they were throttled
- * because they were coming too fast.
- *
- * Context is locked on entry, but perf is not disabled.
- */
-static void fsl_emb_pmu_unthrottle(struct perf_event *event)
+static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags)
 {
-	s64 val, left;
+	unsigned long flags;
+	s64 left;
+
+	if (event->hw.idx < 0 || !event->hw.sample_period)
+		return;
+
+	if (!(event->hw.state & PERF_HES_STOPPED))
+		return;
+
+	if (ef_flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = 0;
+	left = local64_read(&event->hw.period_left);
+	write_pmc(event->hw.idx, left);
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
+
+static void fsl_emb_pmu_stop(struct perf_event *event, int ef_flags)
+{
 	unsigned long flags;
 
 	if (event->hw.idx < 0 || !event->hw.sample_period)
 		return;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
+
 	fsl_emb_pmu_read(event);
-	left = event->hw.sample_period;
-	event->hw.last_period = left;
-	val = 0;
-	if (left < 0x80000000L)
-		val = 0x80000000L - left;
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	write_pmc(event->hw.idx, 0);
+
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
-static struct pmu fsl_emb_pmu = {
-	.enable		= fsl_emb_pmu_enable,
-	.disable	= fsl_emb_pmu_disable,
-	.read		= fsl_emb_pmu_read,
-	.unthrottle	= fsl_emb_pmu_unthrottle,
-};
-
 /*
  * Release the PMU if this is the last perf_event.
  */
@@ -428,7 +453,7 @@
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int fsl_emb_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
 	struct perf_event *events[MAX_HWEVENTS];
@@ -441,14 +466,14 @@
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
-			return ERR_PTR(-EOPNOTSUPP);
+			return -EOPNOTSUPP;
 		ev = ppmu->generic_events[ev];
 		break;
 
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
-			return ERR_PTR(err);
+			return err;
 		break;
 
 	case PERF_TYPE_RAW:
@@ -456,12 +481,12 @@
 		break;
 
 	default:
-		return ERR_PTR(-EINVAL);
+		return -ENOENT;
 	}
 
 	event->hw.config = ppmu->xlate_event(ev);
 	if (!(event->hw.config & FSL_EMB_EVENT_VALID))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	/*
 	 * If this is in a group, check if it can go on with all the
@@ -473,7 +498,7 @@
 		n = collect_events(event->group_leader,
 		                   ppmu->n_counter - 1, events);
 		if (n < 0)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) {
@@ -484,7 +509,7 @@
 		}
 
 		if (num_restricted >= ppmu->n_restricted)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	event->hw.idx = -1;
@@ -497,7 +522,7 @@
 	if (event->attr.exclude_kernel)
 		event->hw.config_base |= PMLCA_FCS;
 	if (event->attr.exclude_idle)
-		return ERR_PTR(-ENOTSUPP);
+		return -ENOTSUPP;
 
 	event->hw.last_period = event->hw.sample_period;
 	local64_set(&event->hw.period_left, event->hw.last_period);
@@ -523,11 +548,20 @@
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
-		return ERR_PTR(err);
-	return &fsl_emb_pmu;
+	return err;
 }
 
+static struct pmu fsl_emb_pmu = {
+	.pmu_enable	= fsl_emb_pmu_enable,
+	.pmu_disable	= fsl_emb_pmu_disable,
+	.event_init	= fsl_emb_pmu_event_init,
+	.add		= fsl_emb_pmu_add,
+	.del		= fsl_emb_pmu_del,
+	.start		= fsl_emb_pmu_start,
+	.stop		= fsl_emb_pmu_stop,
+	.read		= fsl_emb_pmu_read,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -540,6 +574,11 @@
 	s64 prev, delta, left;
 	int record = 0;
 
+	if (event->hw.state & PERF_HES_STOPPED) {
+		write_pmc(event->hw.idx, 0);
+		return;
+	}
+
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
@@ -562,6 +601,11 @@
 			val = 0x80000000LL - left;
 	}
 
+	write_pmc(event->hw.idx, val);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+
 	/*
 	 * Finally record data if requested.
 	 */
@@ -571,23 +615,9 @@
 		perf_sample_data_init(&data, 0);
 		data.period = event->hw.last_period;
 
-		if (perf_event_overflow(event, nmi, &data, regs)) {
-			/*
-			 * Interrupts are coming too fast - throttle them
-			 * by setting the event to 0, so it will be
-			 * at least 2^30 cycles until the next interrupt
-			 * (assuming each event counts at most 2 counts
-			 * per cycle).
-			 */
-			val = 0;
-			left = ~0ULL >> 1;
-		}
+		if (perf_event_overflow(event, nmi, &data, regs))
+			fsl_emb_pmu_stop(event, 0);
 	}
-
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
-	perf_event_update_userpage(event);
 }
 
 static void perf_event_interrupt(struct pt_regs *regs)
@@ -651,5 +681,7 @@
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
+	perf_pmu_register(&fsl_emb_pmu);
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
index 8eff48e..3fee685 100644
--- a/arch/powerpc/kernel/ppc970-pmu.c
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -169,9 +169,11 @@
 	switch (unit) {
 	case PM_VPU:
 		mask = 0x4c;		/* byte 0 bits 2,3,6 */
+		break;
 	case PM_LSU0:
 		/* byte 2 bits 0,2,3,4,6; all of byte 1 */
 		mask = 0x085dff00;
+		break;
 	case PM_LSU1L:
 		mask = 0x50 << 24;	/* byte 3 bits 4,6 */
 		break;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b1c648a..84906d3 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -517,7 +517,6 @@
 
 	account_system_vtime(current);
 	account_process_vtime(current);
-	calculate_steal_time();
 
 	/*
 	 * We can't take a PMU exception inside _switch() since there is a
@@ -1298,14 +1297,3 @@
 
 	return ret;
 }
-
-#ifdef CONFIG_SMP
-int arch_sd_sibling_asym_packing(void)
-{
-	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
-		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
-		return SD_ASYM_PACKING;
-	}
-	return 0;
-}
-#endif
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index fed9bf6..c3c6a88 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -66,6 +66,7 @@
 int __initdata iommu_is_off;
 int __initdata iommu_force_on;
 unsigned long tce_alloc_start, tce_alloc_end;
+u64 ppc64_rma_size;
 #endif
 
 static int __init early_parse_mem(char *p)
@@ -98,7 +99,7 @@
 
 	if ((memory_limit && (start + size) > memory_limit) ||
 			overlaps_crashkernel(start, size)) {
-		p = __va(memblock_alloc_base(size, PAGE_SIZE, memblock.rmo_size));
+		p = __va(memblock_alloc(size, PAGE_SIZE));
 		memcpy(p, initial_boot_params, size);
 		initial_boot_params = (struct boot_param_header *)p;
 		DBG("Moved device tree to 0x%p\n", p);
@@ -492,7 +493,7 @@
 
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
-#if defined(CONFIG_PPC64)
+#ifdef CONFIG_PPC64
 	if (iommu_is_off) {
 		if (base >= 0x80000000ul)
 			return;
@@ -501,9 +502,13 @@
 	}
 #endif
 
-	memblock_add(base, size);
-
+	/* First MEMBLOCK added, do some special initializations */
+	if (memstart_addr == ~(phys_addr_t)0)
+		setup_initial_memory_limit(base, size);
 	memstart_addr = min((u64)memstart_addr, base);
+
+	/* Add the chunk to the MEMBLOCK list */
+	memblock_add(base, size);
 }
 
 u64 __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
@@ -655,7 +660,6 @@
 static inline void __init phyp_dump_reserve_mem(void) {}
 #endif /* CONFIG_PHYP_DUMP  && CONFIG_PPC_RTAS */
 
-
 void __init early_init_devtree(void *params)
 {
 	phys_addr_t limit;
@@ -683,6 +687,7 @@
 
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	memblock_init();
+
 	of_scan_flat_dt(early_init_dt_scan_root, NULL);
 	of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
 
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 11f3cd9..286d978 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1681,7 +1681,7 @@
 
 	if (unlikely(current->audit_context)) {
 #ifdef CONFIG_PPC64
-		if (!test_thread_flag(TIF_32BIT))
+		if (!is_32bit_task())
 			audit_syscall_entry(AUDIT_ARCH_PPC64,
 					    regs->gpr[0],
 					    regs->gpr[3], regs->gpr[4],
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 41048de..8fe8bc6 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -805,7 +805,7 @@
 	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
 }
 
-static int rtas_ibm_suspend_me(struct rtas_args *args)
+int rtas_ibm_suspend_me(struct rtas_args *args)
 {
 	long state;
 	long rc;
@@ -855,7 +855,7 @@
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
-static int rtas_ibm_suspend_me(struct rtas_args *args)
+int rtas_ibm_suspend_me(struct rtas_args *args)
 {
 	return -ENOSYS;
 }
@@ -969,7 +969,7 @@
 	 */
 #ifdef CONFIG_PPC64
 	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) {
-		rtas_region = min(memblock.rmo_size, RTAS_INSTANTIATE_MAX);
+		rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX);
 		ibm_suspend_me_token = rtas_token("ibm,suspend-me");
 	}
 #endif
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 67a84d8..2b442e6 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -716,6 +716,7 @@
 	.write		= rtas_flash_write,
 	.open		= rtas_excl_open,
 	.release	= rtas_flash_release,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations manage_flash_operations = {
@@ -724,6 +725,7 @@
 	.write		= manage_flash_write,
 	.open		= rtas_excl_open,
 	.release	= rtas_excl_release,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations validate_flash_operations = {
@@ -732,6 +734,7 @@
 	.write		= validate_flash_write,
 	.open		= rtas_excl_open,
 	.release	= validate_flash_release,
+	.llseek		= default_llseek,
 };
 
 static int __init rtas_flash_init(void)
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 638883e..0438f81 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -354,6 +354,7 @@
 	.poll =		rtas_log_poll,
 	.open =		rtas_log_open,
 	.release =	rtas_log_release,
+	.llseek =	noop_llseek,
 };
 
 static int enable_surveillance(int timeout)
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 93666f9..1d2fbc9 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -46,7 +46,7 @@
 
 extern void bootx_init(unsigned long r4, unsigned long phys);
 
-int boot_cpuid;
+int boot_cpuid = -1;
 EXPORT_SYMBOL_GPL(boot_cpuid);
 int boot_cpuid_phys;
 
@@ -246,7 +246,7 @@
 	unsigned int i;
 
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
-	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
+	 * as the memblock is limited to lowmem by default */
 	for_each_possible_cpu(i) {
 		softirq_ctx[i] = (struct thread_info *)
 			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index e72690e..2a178b0 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -486,7 +486,7 @@
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
 	 */
-	limit = min(slb0_limit(), memblock.rmo_size);
+	limit = min(slb0_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		unsigned long sp;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0008bc5..68034bb 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -508,9 +508,6 @@
 	if (smp_ops->take_timebase)
 		smp_ops->take_timebase();
 
-	if (system_state > SYSTEM_BOOTING)
-		snapshot_timebase();
-
 	secondary_cpu_time_init();
 
 	ipi_call_lock();
@@ -575,11 +572,18 @@
 
 	free_cpumask_var(old_mask);
 
-	snapshot_timebases();
-
 	dump_numa_cpu_topology();
 }
 
+int arch_sd_sibling_asym_packing(void)
+{
+	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+		return SD_ASYM_PACKING;
+	}
+	return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 int __cpu_disable(void)
 {
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 8533b3b..0104069 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -53,7 +53,7 @@
 #include <linux/posix-timers.h>
 #include <linux/irq.h>
 #include <linux/delay.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 #include <asm/trace.h>
 
 #include <asm/io.h>
@@ -161,10 +161,9 @@
 static long timezone_offset;
 
 unsigned long ppc_proc_freq;
-EXPORT_SYMBOL(ppc_proc_freq);
+EXPORT_SYMBOL_GPL(ppc_proc_freq);
 unsigned long ppc_tb_freq;
-
-static DEFINE_PER_CPU(u64, last_jiffy);
+EXPORT_SYMBOL_GPL(ppc_tb_freq);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 /*
@@ -185,6 +184,8 @@
 
 cputime_t cputime_one_jiffy;
 
+void (*dtl_consumer)(struct dtl_entry *, u64);
+
 static void calc_cputime_factors(void)
 {
 	struct div_result res;
@@ -200,62 +201,153 @@
 }
 
 /*
- * Read the PURR on systems that have it, otherwise the timebase.
+ * Read the SPURR on systems that have it, otherwise the PURR,
+ * or if that doesn't exist return the timebase value passed in.
  */
-static u64 read_purr(void)
+static u64 read_spurr(u64 tb)
 {
+	if (cpu_has_feature(CPU_FTR_SPURR))
+		return mfspr(SPRN_SPURR);
 	if (cpu_has_feature(CPU_FTR_PURR))
 		return mfspr(SPRN_PURR);
-	return mftb();
+	return tb;
+}
+
+#ifdef CONFIG_PPC_SPLPAR
+
+/*
+ * Scan the dispatch trace log and count up the stolen time.
+ * Should be called with interrupts disabled.
+ */
+static u64 scan_dispatch_log(u64 stop_tb)
+{
+	u64 i = local_paca->dtl_ridx;
+	struct dtl_entry *dtl = local_paca->dtl_curr;
+	struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
+	struct lppaca *vpa = local_paca->lppaca_ptr;
+	u64 tb_delta;
+	u64 stolen = 0;
+	u64 dtb;
+
+	if (i == vpa->dtl_idx)
+		return 0;
+	while (i < vpa->dtl_idx) {
+		if (dtl_consumer)
+			dtl_consumer(dtl, i);
+		dtb = dtl->timebase;
+		tb_delta = dtl->enqueue_to_dispatch_time +
+			dtl->ready_to_enqueue_time;
+		barrier();
+		if (i + N_DISPATCH_LOG < vpa->dtl_idx) {
+			/* buffer has overflowed */
+			i = vpa->dtl_idx - N_DISPATCH_LOG;
+			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+			continue;
+		}
+		if (dtb > stop_tb)
+			break;
+		stolen += tb_delta;
+		++i;
+		++dtl;
+		if (dtl == dtl_end)
+			dtl = local_paca->dispatch_log;
+	}
+	local_paca->dtl_ridx = i;
+	local_paca->dtl_curr = dtl;
+	return stolen;
 }
 
 /*
- * Read the SPURR on systems that have it, otherwise the purr
+ * Accumulate stolen time by scanning the dispatch trace log.
+ * Called on entry from user mode.
  */
-static u64 read_spurr(u64 purr)
+void accumulate_stolen_time(void)
 {
-	/*
-	 * cpus without PURR won't have a SPURR
-	 * We already know the former when we use this, so tell gcc
-	 */
-	if (cpu_has_feature(CPU_FTR_PURR) && cpu_has_feature(CPU_FTR_SPURR))
-		return mfspr(SPRN_SPURR);
-	return purr;
+	u64 sst, ust;
+
+	sst = scan_dispatch_log(get_paca()->starttime_user);
+	ust = scan_dispatch_log(get_paca()->starttime);
+	get_paca()->system_time -= sst;
+	get_paca()->user_time -= ust;
+	get_paca()->stolen_time += ust + sst;
 }
 
+static inline u64 calculate_stolen_time(u64 stop_tb)
+{
+	u64 stolen = 0;
+
+	if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) {
+		stolen = scan_dispatch_log(stop_tb);
+		get_paca()->system_time -= stolen;
+	}
+
+	stolen += get_paca()->stolen_time;
+	get_paca()->stolen_time = 0;
+	return stolen;
+}
+
+#else /* CONFIG_PPC_SPLPAR */
+static inline u64 calculate_stolen_time(u64 stop_tb)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PPC_SPLPAR */
+
 /*
  * Account time for a transition between system, hard irq
  * or soft irq state.
  */
 void account_system_vtime(struct task_struct *tsk)
 {
-	u64 now, nowscaled, delta, deltascaled, sys_time;
+	u64 now, nowscaled, delta, deltascaled;
 	unsigned long flags;
+	u64 stolen, udelta, sys_scaled, user_scaled;
 
 	local_irq_save(flags);
-	now = read_purr();
+	now = mftb();
 	nowscaled = read_spurr(now);
-	delta = now - get_paca()->startpurr;
+	get_paca()->system_time += now - get_paca()->starttime;
+	get_paca()->starttime = now;
 	deltascaled = nowscaled - get_paca()->startspurr;
-	get_paca()->startpurr = now;
 	get_paca()->startspurr = nowscaled;
-	if (!in_interrupt()) {
-		/* deltascaled includes both user and system time.
-		 * Hence scale it based on the purr ratio to estimate
-		 * the system time */
-		sys_time = get_paca()->system_time;
-		if (get_paca()->user_time)
-			deltascaled = deltascaled * sys_time /
-			     (sys_time + get_paca()->user_time);
-		delta += sys_time;
-		get_paca()->system_time = 0;
+
+	stolen = calculate_stolen_time(now);
+
+	delta = get_paca()->system_time;
+	get_paca()->system_time = 0;
+	udelta = get_paca()->user_time - get_paca()->utime_sspurr;
+	get_paca()->utime_sspurr = get_paca()->user_time;
+
+	/*
+	 * Because we don't read the SPURR on every kernel entry/exit,
+	 * deltascaled includes both user and system SPURR ticks.
+	 * Apportion these ticks to system SPURR ticks and user
+	 * SPURR ticks in the same ratio as the system time (delta)
+	 * and user time (udelta) values obtained from the timebase
+	 * over the same interval.  The system ticks get accounted here;
+	 * the user ticks get saved up in paca->user_time_scaled to be
+	 * used by account_process_tick.
+	 */
+	sys_scaled = delta;
+	user_scaled = udelta;
+	if (deltascaled != delta + udelta) {
+		if (udelta) {
+			sys_scaled = deltascaled * delta / (delta + udelta);
+			user_scaled = deltascaled - sys_scaled;
+		} else {
+			sys_scaled = deltascaled;
+		}
 	}
-	if (in_irq() || idle_task(smp_processor_id()) != tsk)
-		account_system_time(tsk, 0, delta, deltascaled);
-	else
-		account_idle_time(delta);
-	__get_cpu_var(cputime_last_delta) = delta;
-	__get_cpu_var(cputime_scaled_last_delta) = deltascaled;
+	get_paca()->user_time_scaled += user_scaled;
+
+	if (in_irq() || idle_task(smp_processor_id()) != tsk) {
+		account_system_time(tsk, 0, delta, sys_scaled);
+		if (stolen)
+			account_steal_time(stolen);
+	} else {
+		account_idle_time(delta + stolen);
+	}
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
@@ -265,125 +357,26 @@
  * by the exception entry and exit code to the generic process
  * user and system time records.
  * Must be called with interrupts disabled.
+ * Assumes that account_system_vtime() has been called recently
+ * (i.e. since the last entry from usermode) so that
+ * get_paca()->user_time_scaled is up to date.
  */
 void account_process_tick(struct task_struct *tsk, int user_tick)
 {
 	cputime_t utime, utimescaled;
 
 	utime = get_paca()->user_time;
+	utimescaled = get_paca()->user_time_scaled;
 	get_paca()->user_time = 0;
-	utimescaled = cputime_to_scaled(utime);
+	get_paca()->user_time_scaled = 0;
+	get_paca()->utime_sspurr = 0;
 	account_user_time(tsk, utime, utimescaled);
 }
 
-/*
- * Stuff for accounting stolen time.
- */
-struct cpu_purr_data {
-	int	initialized;			/* thread is running */
-	u64	tb;			/* last TB value read */
-	u64	purr;			/* last PURR value read */
-	u64	spurr;			/* last SPURR value read */
-};
-
-/*
- * Each entry in the cpu_purr_data array is manipulated only by its
- * "owner" cpu -- usually in the timer interrupt but also occasionally
- * in process context for cpu online.  As long as cpus do not touch
- * each others' cpu_purr_data, disabling local interrupts is
- * sufficient to serialize accesses.
- */
-static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);
-
-static void snapshot_tb_and_purr(void *data)
-{
-	unsigned long flags;
-	struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);
-
-	local_irq_save(flags);
-	p->tb = get_tb_or_rtc();
-	p->purr = mfspr(SPRN_PURR);
-	wmb();
-	p->initialized = 1;
-	local_irq_restore(flags);
-}
-
-/*
- * Called during boot when all cpus have come up.
- */
-void snapshot_timebases(void)
-{
-	if (!cpu_has_feature(CPU_FTR_PURR))
-		return;
-	on_each_cpu(snapshot_tb_and_purr, NULL, 1);
-}
-
-/*
- * Must be called with interrupts disabled.
- */
-void calculate_steal_time(void)
-{
-	u64 tb, purr;
-	s64 stolen;
-	struct cpu_purr_data *pme;
-
-	pme = &__get_cpu_var(cpu_purr_data);
-	if (!pme->initialized)
-		return;		/* !CPU_FTR_PURR or early in early boot */
-	tb = mftb();
-	purr = mfspr(SPRN_PURR);
-	stolen = (tb - pme->tb) - (purr - pme->purr);
-	if (stolen > 0) {
-		if (idle_task(smp_processor_id()) != current)
-			account_steal_time(stolen);
-		else
-			account_idle_time(stolen);
-	}
-	pme->tb = tb;
-	pme->purr = purr;
-}
-
-#ifdef CONFIG_PPC_SPLPAR
-/*
- * Must be called before the cpu is added to the online map when
- * a cpu is being brought up at runtime.
- */
-static void snapshot_purr(void)
-{
-	struct cpu_purr_data *pme;
-	unsigned long flags;
-
-	if (!cpu_has_feature(CPU_FTR_PURR))
-		return;
-	local_irq_save(flags);
-	pme = &__get_cpu_var(cpu_purr_data);
-	pme->tb = mftb();
-	pme->purr = mfspr(SPRN_PURR);
-	pme->initialized = 1;
-	local_irq_restore(flags);
-}
-
-#endif /* CONFIG_PPC_SPLPAR */
-
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
 #define calc_cputime_factors()
-#define calculate_steal_time()		do { } while (0)
 #endif
 
-#if !(defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR))
-#define snapshot_purr()			do { } while (0)
-#endif
-
-/*
- * Called when a cpu comes up after the system has finished booting,
- * i.e. as a result of a hotplug cpu action.
- */
-void snapshot_timebase(void)
-{
-	__get_cpu_var(last_jiffy) = get_tb_or_rtc();
-	snapshot_purr();
-}
-
 void __delay(unsigned long loops)
 {
 	unsigned long start;
@@ -493,60 +486,60 @@
 }
 #endif /* CONFIG_PPC_ISERIES */
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
 
 /*
  * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
  */
 #ifdef CONFIG_PPC64
-static inline unsigned long test_perf_event_pending(void)
+static inline unsigned long test_irq_work_pending(void)
 {
 	unsigned long x;
 
 	asm volatile("lbz %0,%1(13)"
 		: "=r" (x)
-		: "i" (offsetof(struct paca_struct, perf_event_pending)));
+		: "i" (offsetof(struct paca_struct, irq_work_pending)));
 	return x;
 }
 
-static inline void set_perf_event_pending_flag(void)
+static inline void set_irq_work_pending_flag(void)
 {
 	asm volatile("stb %0,%1(13)" : :
 		"r" (1),
-		"i" (offsetof(struct paca_struct, perf_event_pending)));
+		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
-static inline void clear_perf_event_pending(void)
+static inline void clear_irq_work_pending(void)
 {
 	asm volatile("stb %0,%1(13)" : :
 		"r" (0),
-		"i" (offsetof(struct paca_struct, perf_event_pending)));
+		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
 #else /* 32-bit */
 
-DEFINE_PER_CPU(u8, perf_event_pending);
+DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_perf_event_pending_flag()	__get_cpu_var(perf_event_pending) = 1
-#define test_perf_event_pending()	__get_cpu_var(perf_event_pending)
-#define clear_perf_event_pending()	__get_cpu_var(perf_event_pending) = 0
+#define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1
+#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)
+#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0
 
 #endif /* 32 vs 64 bit */
 
-void set_perf_event_pending(void)
+void set_irq_work_pending(void)
 {
 	preempt_disable();
-	set_perf_event_pending_flag();
+	set_irq_work_pending_flag();
 	set_dec(1);
 	preempt_enable();
 }
 
-#else  /* CONFIG_PERF_EVENTS */
+#else  /* CONFIG_IRQ_WORK */
 
-#define test_perf_event_pending()	0
-#define clear_perf_event_pending()
+#define test_irq_work_pending()	0
+#define clear_irq_work_pending()
 
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_IRQ_WORK */
 
 /*
  * For iSeries shared processors, we have to let the hypervisor
@@ -585,11 +578,9 @@
 	old_regs = set_irq_regs(regs);
 	irq_enter();
 
-	calculate_steal_time();
-
-	if (test_perf_event_pending()) {
-		clear_perf_event_pending();
-		perf_event_do_pending();
+	if (test_irq_work_pending()) {
+		clear_irq_work_pending();
+		irq_work_run();
 	}
 
 #ifdef CONFIG_PPC_ISERIES
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index a45a63c..1b2cdc8 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -538,6 +538,11 @@
 
 	return 0;
 }
+
+int machine_check_generic(struct pt_regs *regs)
+{
+	return 0;
+}
 #elif defined(CONFIG_E200)
 int machine_check_e200(struct pt_regs *regs)
 {
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 13002fe..fd87287 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -159,7 +159,7 @@
 {
 	int i;
 
-	if (!vma || test_thread_flag(TIF_32BIT)) {
+	if (!vma || is_32bit_task()) {
 		printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase);
 		for (i=0; i<vdso32_pages; i++) {
 			struct page *pg = virt_to_page(vdso32_kbase +
@@ -170,7 +170,7 @@
 			dump_one_vdso_page(pg, upg);
 		}
 	}
-	if (!vma || !test_thread_flag(TIF_32BIT)) {
+	if (!vma || !is_32bit_task()) {
 		printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase);
 		for (i=0; i<vdso64_pages; i++) {
 			struct page *pg = virt_to_page(vdso64_kbase +
@@ -200,7 +200,7 @@
 		return 0;
 
 #ifdef CONFIG_PPC64
-	if (test_thread_flag(TIF_32BIT)) {
+	if (is_32bit_task()) {
 		vdso_pagelist = vdso32_pagelist;
 		vdso_pages = vdso32_pages;
 		vdso_base = VDSO32_MBASE;
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 51ead52..9a7946c 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -14,10 +14,10 @@
 
 GCOV_PROFILE := n
 
-EXTRA_CFLAGS := -shared -fno-common -fno-builtin
-EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
+ccflags-y := -shared -fno-common -fno-builtin
+ccflags-y += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
 		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
-EXTRA_AFLAGS := -D__VDSO32__ -s
+asflags-y := -D__VDSO32__ -s
 
 obj-y += vdso32_wrapper.o
 extra-y += vdso32.lds
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 79da65d..8c500d8 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -9,10 +9,10 @@
 
 GCOV_PROFILE := n
 
-EXTRA_CFLAGS := -shared -fno-common -fno-builtin
-EXTRA_CFLAGS += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
+ccflags-y := -shared -fno-common -fno-builtin
+ccflags-y += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
 		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
-EXTRA_AFLAGS := -D__VDSO64__ -s
+asflags-y := -D__VDSO64__ -s
 
 obj-y += vdso64_wrapper.o
 extra-y += vdso64.lds
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index fa3469d..d692989 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1184,7 +1184,12 @@
 /* vio_dev refcount hit 0 */
 static void __devinit vio_dev_release(struct device *dev)
 {
-	/* XXX should free TCE table */
+	struct iommu_table *tbl = get_iommu_table_base(dev);
+
+	/* iSeries uses a common table for all vio devices */
+	if (!firmware_has_feature(FW_FEATURE_ISERIES) && tbl)
+		iommu_free_table(tbl, dev->of_node ?
+			dev->of_node->full_name : dev_name(dev));
 	of_node_put(dev->of_node);
 	kfree(to_vio_dev(dev));
 }
@@ -1254,8 +1259,7 @@
 	if (device_register(&viodev->dev)) {
 		printk(KERN_ERR "%s: failed to register device %s\n",
 				__func__, dev_name(&viodev->dev));
-		/* XXX free TCE table */
-		kfree(viodev);
+		put_device(&viodev->dev);
 		return NULL;
 	}
 
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index d45c818..4d68638 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -4,7 +4,7 @@
 
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
-EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm
+ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm
 
 common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index 474f2e2..35a701f 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -159,7 +159,7 @@
 
 static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt)
 {
-	kvm_cvt_df(&vcpu->arch.fpr[rt], &vcpu->arch.qpr[rt], &vcpu->arch.fpscr);
+	kvm_cvt_df(&vcpu->arch.fpr[rt], &vcpu->arch.qpr[rt]);
 }
 
 static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
@@ -204,7 +204,7 @@
 	/* put in registers */
 	switch (ls_type) {
 	case FPU_LS_SINGLE:
-		kvm_cvt_fd((u32*)tmp, &vcpu->arch.fpr[rs], &vcpu->arch.fpscr);
+		kvm_cvt_fd((u32*)tmp, &vcpu->arch.fpr[rs]);
 		vcpu->arch.qpr[rs] = *((u32*)tmp);
 		break;
 	case FPU_LS_DOUBLE:
@@ -230,7 +230,7 @@
 
 	switch (ls_type) {
 	case FPU_LS_SINGLE:
-		kvm_cvt_df(&vcpu->arch.fpr[rs], (u32*)tmp, &vcpu->arch.fpscr);
+		kvm_cvt_df(&vcpu->arch.fpr[rs], (u32*)tmp);
 		val = *((u32*)tmp);
 		len = sizeof(u32);
 		break;
@@ -296,7 +296,7 @@
 	emulated = EMULATE_DONE;
 
 	/* put in registers */
-	kvm_cvt_fd(&tmp[0], &vcpu->arch.fpr[rs], &vcpu->arch.fpscr);
+	kvm_cvt_fd(&tmp[0], &vcpu->arch.fpr[rs]);
 	vcpu->arch.qpr[rs] = tmp[1];
 
 	dprintk(KERN_INFO "KVM: PSQ_LD [0x%x, 0x%x] at 0x%lx (%d)\n", tmp[0],
@@ -314,7 +314,7 @@
 	u32 tmp[2];
 	int len = w ? sizeof(u32) : sizeof(u64);
 
-	kvm_cvt_df(&vcpu->arch.fpr[rs], &tmp[0], &vcpu->arch.fpscr);
+	kvm_cvt_df(&vcpu->arch.fpr[rs], &tmp[0]);
 	tmp[1] = vcpu->arch.qpr[rs];
 
 	r = kvmppc_st(vcpu, &addr, len, tmp, true);
@@ -516,9 +516,9 @@
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in1], &ps0_in1, &vcpu->arch.fpscr);
-	kvm_cvt_df(&fpr[reg_in2], &ps0_in2, &vcpu->arch.fpscr);
-	kvm_cvt_df(&fpr[reg_in3], &ps0_in3, &vcpu->arch.fpscr);
+	kvm_cvt_df(&fpr[reg_in1], &ps0_in1);
+	kvm_cvt_df(&fpr[reg_in2], &ps0_in2);
+	kvm_cvt_df(&fpr[reg_in3], &ps0_in3);
 
 	if (scalar & SCALAR_LOW)
 		ps0_in2 = qpr[reg_in2];
@@ -529,7 +529,7 @@
 			  ps0_in1, ps0_in2, ps0_in3, ps0_out);
 
 	if (!(scalar & SCALAR_NO_PS0))
-		kvm_cvt_fd(&ps0_out, &fpr[reg_out], &vcpu->arch.fpscr);
+		kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
 
 	/* PS1 */
 	ps1_in1 = qpr[reg_in1];
@@ -566,12 +566,12 @@
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in1], &ps0_in1, &vcpu->arch.fpscr);
+	kvm_cvt_df(&fpr[reg_in1], &ps0_in1);
 
 	if (scalar & SCALAR_LOW)
 		ps0_in2 = qpr[reg_in2];
 	else
-		kvm_cvt_df(&fpr[reg_in2], &ps0_in2, &vcpu->arch.fpscr);
+		kvm_cvt_df(&fpr[reg_in2], &ps0_in2);
 
 	func(&vcpu->arch.fpscr, &ps0_out, &ps0_in1, &ps0_in2);
 
@@ -579,7 +579,7 @@
 		dprintk(KERN_INFO "PS2 ps0 -> f(0x%x, 0x%x) = 0x%x\n",
 				  ps0_in1, ps0_in2, ps0_out);
 
-		kvm_cvt_fd(&ps0_out, &fpr[reg_out], &vcpu->arch.fpscr);
+		kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
 	}
 
 	/* PS1 */
@@ -615,13 +615,13 @@
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in], &ps0_in, &vcpu->arch.fpscr);
+	kvm_cvt_df(&fpr[reg_in], &ps0_in);
 	func(&vcpu->arch.fpscr, &ps0_out, &ps0_in);
 
 	dprintk(KERN_INFO "PS1 ps0 -> f(0x%x) = 0x%x\n",
 			  ps0_in, ps0_out);
 
-	kvm_cvt_fd(&ps0_out, &fpr[reg_out], &vcpu->arch.fpscr);
+	kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
 
 	/* PS1 */
 	ps1_in = qpr[reg_in];
@@ -671,7 +671,7 @@
 #ifdef DEBUG
 	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) {
 		u32 f;
-		kvm_cvt_df(&vcpu->arch.fpr[i], &f, &vcpu->arch.fpscr);
+		kvm_cvt_df(&vcpu->arch.fpr[i], &f);
 		dprintk(KERN_INFO "FPR[%d] = 0x%x / 0x%llx    QPR[%d] = 0x%x\n",
 			i, f, vcpu->arch.fpr[i], i, vcpu->arch.qpr[i]);
 	}
@@ -796,8 +796,7 @@
 			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra];
 			/* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */
 			kvm_cvt_df(&vcpu->arch.fpr[ax_rb],
-				   &vcpu->arch.qpr[ax_rd],
-				   &vcpu->arch.fpscr);
+				   &vcpu->arch.qpr[ax_rd]);
 			break;
 		case OP_4X_PS_MERGE01:
 			WARN_ON(rcomp);
@@ -808,19 +807,16 @@
 			WARN_ON(rcomp);
 			/* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */
 			kvm_cvt_fd(&vcpu->arch.qpr[ax_ra],
-				   &vcpu->arch.fpr[ax_rd],
-				   &vcpu->arch.fpscr);
+				   &vcpu->arch.fpr[ax_rd]);
 			/* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */
 			kvm_cvt_df(&vcpu->arch.fpr[ax_rb],
-				   &vcpu->arch.qpr[ax_rd],
-				   &vcpu->arch.fpscr);
+				   &vcpu->arch.qpr[ax_rd]);
 			break;
 		case OP_4X_PS_MERGE11:
 			WARN_ON(rcomp);
 			/* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */
 			kvm_cvt_fd(&vcpu->arch.qpr[ax_ra],
-				   &vcpu->arch.fpr[ax_rd],
-				   &vcpu->arch.fpscr);
+				   &vcpu->arch.fpr[ax_rd]);
 			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
 			break;
 		}
@@ -1255,7 +1251,7 @@
 #ifdef DEBUG
 	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) {
 		u32 f;
-		kvm_cvt_df(&vcpu->arch.fpr[i], &f, &vcpu->arch.fpscr);
+		kvm_cvt_df(&vcpu->arch.fpr[i], &f);
 		dprintk(KERN_INFO "FPR[%d] = 0x%x\n", i, f);
 	}
 #endif
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 4568ec3..b83ba58 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -145,7 +145,7 @@
 	/* this default type might be overwritten by subcategories */
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
 
-	pr_debug(KERN_INFO "Emulating opcode %d / %d\n", get_op(inst), get_xop(inst));
+	pr_debug("Emulating opcode %d / %d\n", get_op(inst), get_xop(inst));
 
 	switch (get_op(inst)) {
 	case OP_TRAP:
@@ -275,7 +275,7 @@
 			{
 				u64 jd = get_tb() - vcpu->arch.dec_jiffies;
 				kvmppc_set_gpr(vcpu, rt, vcpu->arch.dec - jd);
-				pr_debug(KERN_INFO "mfDEC: %x - %llx = %lx\n",
+				pr_debug("mfDEC: %x - %llx = %lx\n",
 					 vcpu->arch.dec, jd,
 					 kvmppc_get_gpr(vcpu, rt));
 				break;
diff --git a/arch/powerpc/kvm/fpu.S b/arch/powerpc/kvm/fpu.S
index cb34bbe..bf68d59 100644
--- a/arch/powerpc/kvm/fpu.S
+++ b/arch/powerpc/kvm/fpu.S
@@ -273,19 +273,11 @@
 FPD_THREE_IN(fnmadd)
 
 _GLOBAL(kvm_cvt_fd)
-	lfd	0,0(r5)			/* load up fpscr value */
-	MTFSF_L(0)
 	lfs	0,0(r3)
 	stfd	0,0(r4)
-	mffs	0
-	stfd	0,0(r5)			/* save new fpscr value */
 	blr
 
 _GLOBAL(kvm_cvt_df)
-	lfd	0,0(r5)			/* load up fpscr value */
-	MTFSF_L(0)
 	lfd	0,0(r3)
 	stfs	0,0(r4)
-	mffs	0
-	stfd	0,0(r5)			/* save new fpscr value */
 	blr
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 5bb89c82..889f2bc 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -4,9 +4,7 @@
 
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
-ifeq ($(CONFIG_PPC64),y)
-EXTRA_CFLAGS		+= -mno-minimal-toc
-endif
+ccflags-$(CONFIG_PPC64)	:= -mno-minimal-toc
 
 CFLAGS_REMOVE_code-patching.o = -pg
 CFLAGS_REMOVE_feature-fixups.o = -pg
@@ -17,7 +15,8 @@
 obj-$(CONFIG_HAS_IOMEM)	+= devres.o
 
 obj-$(CONFIG_PPC64)	+= copypage_64.o copyuser_64.o \
-			   memcpy_64.o usercopy_64.o mem_64.o string.o
+			   memcpy_64.o usercopy_64.o mem_64.o string.o \
+			   checksum_wrappers_64.o
 obj-$(CONFIG_XMON)	+= sstep.o ldstfp.o
 obj-$(CONFIG_KPROBES)	+= sstep.o ldstfp.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= sstep.o ldstfp.o
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index ef96c6c..18245af 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -65,165 +65,393 @@
 	srwi	r3,r3,16
 	blr
 
+#define STACKFRAMESIZE 256
+#define STK_REG(i)	(112 + ((i)-14)*8)
+
 /*
  * Computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit).
  *
- * This code assumes at least halfword alignment, though the length
- * can be any number of bytes.  The sum is accumulated in r5.
- *
  * csum_partial(r3=buff, r4=len, r5=sum)
  */
 _GLOBAL(csum_partial)
-        subi	r3,r3,8		/* we'll offset by 8 for the loads */
-        srdi.	r6,r4,3         /* divide by 8 for doubleword count */
-        addic   r5,r5,0         /* clear carry */
-        beq	3f              /* if we're doing < 8 bytes */
-        andi.	r0,r3,2         /* aligned on a word boundary already? */
-        beq+	1f
-        lhz     r6,8(r3)        /* do 2 bytes to get aligned */
-        addi    r3,r3,2
-        subi    r4,r4,2
-        addc    r5,r5,r6
-        srdi.   r6,r4,3         /* recompute number of doublewords */
-        beq     3f              /* any left? */
-1:      mtctr   r6
-2:      ldu     r6,8(r3)        /* main sum loop */
-        adde    r5,r5,r6
-        bdnz    2b
-        andi.	r4,r4,7         /* compute bytes left to sum after doublewords */
-3:	cmpwi	0,r4,4		/* is at least a full word left? */
-	blt	4f
-	lwz	r6,8(r3)	/* sum this word */
+	addic	r0,r5,0			/* clear carry */
+
+	srdi.	r6,r4,3			/* less than 8 bytes? */
+	beq	.Lcsum_tail_word
+
+	/*
+	 * If only halfword aligned, align to a double word. Since odd
+	 * aligned addresses should be rare and they would require more
+	 * work to calculate the correct checksum, we ignore that case
+	 * and take the potential slowdown of unaligned loads.
+	 */
+	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 & 0x3) >> 1 */
+	beq	.Lcsum_aligned
+
+	li	r7,4
+	sub	r6,r7,r6
+	mtctr	r6
+
+1:
+	lhz	r6,0(r3)		/* align to doubleword */
+	subi	r4,r4,2
+	addi	r3,r3,2
+	adde	r0,r0,r6
+	bdnz	1b
+
+.Lcsum_aligned:
+	/*
+	 * We unroll the loop such that each iteration is 64 bytes with an
+	 * entry and exit limb of 64 bytes, meaning a minimum size of
+	 * 128 bytes.
+	 */
+	srdi.	r6,r4,7
+	beq	.Lcsum_tail_doublewords		/* len < 128 */
+
+	srdi	r6,r4,6
+	subi	r6,r6,1
+	mtctr	r6
+
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(r14)(r1)
+	std	r15,STK_REG(r15)(r1)
+	std	r16,STK_REG(r16)(r1)
+
+	ld	r6,0(r3)
+	ld	r9,8(r3)
+
+	ld	r10,16(r3)
+	ld	r11,24(r3)
+
+	/*
+	 * On POWER6 and POWER7 back to back addes take 2 cycles because of
+	 * the XER dependency. This means the fastest this loop can go is
+	 * 16 cycles per iteration. The scheduling of the loop below has
+	 * been shown to hit this on both POWER6 and POWER7.
+	 */
+	.align 5
+2:
+	adde	r0,r0,r6
+	ld	r12,32(r3)
+	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+	ld	r15,48(r3)
+	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+
+	adde	r0,r0,r11
+
+	adde	r0,r0,r12
+
+	adde	r0,r0,r14
+
+	adde	r0,r0,r15
+	ld	r6,0(r3)
+	ld	r9,8(r3)
+
+	adde	r0,r0,r16
+	ld	r10,16(r3)
+	ld	r11,24(r3)
+	bdnz	2b
+
+
+	adde	r0,r0,r6
+	ld	r12,32(r3)
+	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+	ld	r15,48(r3)
+	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+	adde	r0,r0,r11
+	adde	r0,r0,r12
+	adde	r0,r0,r14
+	adde	r0,r0,r15
+	adde	r0,r0,r16
+
+	ld	r14,STK_REG(r14)(r1)
+	ld	r15,STK_REG(r15)(r1)
+	ld	r16,STK_REG(r16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	andi.	r4,r4,63
+
+.Lcsum_tail_doublewords:		/* Up to 127 bytes to go */
+	srdi.	r6,r4,3
+	beq	.Lcsum_tail_word
+
+	mtctr	r6
+3:
+	ld	r6,0(r3)
+	addi	r3,r3,8
+	adde	r0,r0,r6
+	bdnz	3b
+
+	andi.	r4,r4,7
+
+.Lcsum_tail_word:			/* Up to 7 bytes to go */
+	srdi.	r6,r4,2
+	beq	.Lcsum_tail_halfword
+
+	lwz	r6,0(r3)
 	addi	r3,r3,4
+	adde	r0,r0,r6
 	subi	r4,r4,4
-	adde	r5,r5,r6
-4:	cmpwi	0,r4,2		/* is at least a halfword left? */
-        blt+	5f
-        lhz     r6,8(r3)        /* sum this halfword */
-        addi    r3,r3,2
-        subi    r4,r4,2
-        adde    r5,r5,r6
-5:	cmpwi	0,r4,1		/* is at least a byte left? */
-        bne+    6f
-        lbz     r6,8(r3)        /* sum this byte */
-        slwi    r6,r6,8         /* this byte is assumed to be the upper byte of a halfword */
-        adde    r5,r5,r6
-6:      addze	r5,r5		/* add in final carry */
-	rldicl  r4,r5,32,0      /* fold two 32-bit halves together */
-        add     r3,r4,r5
-        srdi    r3,r3,32
-        blr
+
+.Lcsum_tail_halfword:			/* Up to 3 bytes to go */
+	srdi.	r6,r4,1
+	beq	.Lcsum_tail_byte
+
+	lhz	r6,0(r3)
+	addi	r3,r3,2
+	adde	r0,r0,r6
+	subi	r4,r4,2
+
+.Lcsum_tail_byte:			/* Up to 1 byte to go */
+	andi.	r6,r4,1
+	beq	.Lcsum_finish
+
+	lbz	r6,0(r3)
+	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
+	adde	r0,r0,r9
+
+.Lcsum_finish:
+	addze	r0,r0			/* add in final carry */
+	rldicl	r4,r0,32,0		/* fold two 32 bit halves together */
+	add	r3,r4,r0
+	srdi	r3,r3,32
+	blr
+
+
+	.macro source
+100:
+	.section __ex_table,"a"
+	.align 3
+	.llong 100b,.Lsrc_error
+	.previous
+	.endm
+
+	.macro dest
+200:
+	.section __ex_table,"a"
+	.align 3
+	.llong 200b,.Ldest_error
+	.previous
+	.endm
 
 /*
  * Computes the checksum of a memory block at src, length len,
  * and adds in "sum" (32-bit), while copying the block to dst.
  * If an access exception occurs on src or dst, it stores -EFAULT
- * to *src_err or *dst_err respectively, and (for an error on
- * src) zeroes the rest of dst.
- *
- * This code needs to be reworked to take advantage of 64 bit sum+copy.
- * However, due to tokenring halfword alignment problems this will be very
- * tricky.  For now we'll leave it until we instrument it somehow.
+ * to *src_err or *dst_err respectively. The caller must take any action
+ * required in this case (zeroing memory, recalculating partial checksum etc).
  *
  * csum_partial_copy_generic(r3=src, r4=dst, r5=len, r6=sum, r7=src_err, r8=dst_err)
  */
 _GLOBAL(csum_partial_copy_generic)
-	addic	r0,r6,0
-	subi	r3,r3,4
-	subi	r4,r4,4
-	srwi.	r6,r5,2
-	beq	3f		/* if we're doing < 4 bytes */
-	andi.	r9,r4,2		/* Align dst to longword boundary */
-	beq+	1f
-81:	lhz	r6,4(r3)	/* do 2 bytes to get aligned */
-	addi	r3,r3,2
+	addic	r0,r6,0			/* clear carry */
+
+	srdi.	r6,r5,3			/* less than 8 bytes? */
+	beq	.Lcopy_tail_word
+
+	/*
+	 * If only halfword aligned, align to a double word. Since odd
+	 * aligned addresses should be rare and they would require more
+	 * work to calculate the correct checksum, we ignore that case
+	 * and take the potential slowdown of unaligned loads.
+	 *
+	 * If the source and destination are relatively unaligned we only
+	 * align the source. This keeps things simple.
+	 */
+	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 & 0x3) >> 1 */
+	beq	.Lcopy_aligned
+
+	li	r7,4
+	sub	r6,r7,r6
+	mtctr	r6
+
+1:
+source;	lhz	r6,0(r3)		/* align to doubleword */
 	subi	r5,r5,2
-91:	sth	r6,4(r4)
-	addi	r4,r4,2
-	addc	r0,r0,r6
-	srwi.	r6,r5,2		/* # words to do */
-	beq	3f
-1:	mtctr	r6
-82:	lwzu	r6,4(r3)	/* the bdnz has zero overhead, so it should */
-92:	stwu	r6,4(r4)	/* be unnecessary to unroll this loop */
-	adde	r0,r0,r6
-	bdnz	82b
-	andi.	r5,r5,3
-3:	cmpwi	0,r5,2
-	blt+	4f
-83:	lhz	r6,4(r3)
 	addi	r3,r3,2
-	subi	r5,r5,2
-93:	sth	r6,4(r4)
+	adde	r0,r0,r6
+dest;	sth	r6,0(r4)
 	addi	r4,r4,2
+	bdnz	1b
+
+.Lcopy_aligned:
+	/*
+	 * We unroll the loop such that each iteration is 64 bytes with an
+	 * entry and exit limb of 64 bytes, meaning a minimum size of
+	 * 128 bytes.
+	 */
+	srdi.	r6,r5,7
+	beq	.Lcopy_tail_doublewords		/* len < 128 */
+
+	srdi	r6,r5,6
+	subi	r6,r6,1
+	mtctr	r6
+
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(r14)(r1)
+	std	r15,STK_REG(r15)(r1)
+	std	r16,STK_REG(r16)(r1)
+
+source;	ld	r6,0(r3)
+source;	ld	r9,8(r3)
+
+source;	ld	r10,16(r3)
+source;	ld	r11,24(r3)
+
+	/*
+	 * On POWER6 and POWER7 back to back addes take 2 cycles because of
+	 * the XER dependency. This means the fastest this loop can go is
+	 * 16 cycles per iteration. The scheduling of the loop below has
+	 * been shown to hit this on both POWER6 and POWER7.
+	 */
+	.align 5
+2:
 	adde	r0,r0,r6
-4:	cmpwi	0,r5,1
-	bne+	5f
-84:	lbz	r6,4(r3)
-94:	stb	r6,4(r4)
-	slwi	r6,r6,8		/* Upper byte of word */
+source;	ld	r12,32(r3)
+source;	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+source;	ld	r15,48(r3)
+source;	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+dest;	std	r6,0(r4)
+dest;	std	r9,8(r4)
+
+	adde	r0,r0,r11
+dest;	std	r10,16(r4)
+dest;	std	r11,24(r4)
+
+	adde	r0,r0,r12
+dest;	std	r12,32(r4)
+dest;	std	r14,40(r4)
+
+	adde	r0,r0,r14
+dest;	std	r15,48(r4)
+dest;	std	r16,56(r4)
+	addi	r4,r4,64
+
+	adde	r0,r0,r15
+source;	ld	r6,0(r3)
+source;	ld	r9,8(r3)
+
+	adde	r0,r0,r16
+source;	ld	r10,16(r3)
+source;	ld	r11,24(r3)
+	bdnz	2b
+
+
 	adde	r0,r0,r6
-5:	addze	r3,r0		/* add in final carry (unlikely with 64-bit regs) */
-        rldicl  r4,r3,32,0      /* fold 64 bit value */
-        add     r3,r4,r3
-        srdi    r3,r3,32
+source;	ld	r12,32(r3)
+source;	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+source;	ld	r15,48(r3)
+source;	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+dest;	std	r6,0(r4)
+dest;	std	r9,8(r4)
+
+	adde	r0,r0,r11
+dest;	std	r10,16(r4)
+dest;	std	r11,24(r4)
+
+	adde	r0,r0,r12
+dest;	std	r12,32(r4)
+dest;	std	r14,40(r4)
+
+	adde	r0,r0,r14
+dest;	std	r15,48(r4)
+dest;	std	r16,56(r4)
+	addi	r4,r4,64
+
+	adde	r0,r0,r15
+	adde	r0,r0,r16
+
+	ld	r14,STK_REG(r14)(r1)
+	ld	r15,STK_REG(r15)(r1)
+	ld	r16,STK_REG(r16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	andi.	r5,r5,63
+
+.Lcopy_tail_doublewords:		/* Up to 127 bytes to go */
+	srdi.	r6,r5,3
+	beq	.Lcopy_tail_word
+
+	mtctr	r6
+3:
+source;	ld	r6,0(r3)
+	addi	r3,r3,8
+	adde	r0,r0,r6
+dest;	std	r6,0(r4)
+	addi	r4,r4,8
+	bdnz	3b
+
+	andi.	r5,r5,7
+
+.Lcopy_tail_word:			/* Up to 7 bytes to go */
+	srdi.	r6,r5,2
+	beq	.Lcopy_tail_halfword
+
+source;	lwz	r6,0(r3)
+	addi	r3,r3,4
+	adde	r0,r0,r6
+dest;	stw	r6,0(r4)
+	addi	r4,r4,4
+	subi	r5,r5,4
+
+.Lcopy_tail_halfword:			/* Up to 3 bytes to go */
+	srdi.	r6,r5,1
+	beq	.Lcopy_tail_byte
+
+source;	lhz	r6,0(r3)
+	addi	r3,r3,2
+	adde	r0,r0,r6
+dest;	sth	r6,0(r4)
+	addi	r4,r4,2
+	subi	r5,r5,2
+
+.Lcopy_tail_byte:			/* Up to 1 byte to go */
+	andi.	r6,r5,1
+	beq	.Lcopy_finish
+
+source;	lbz	r6,0(r3)
+	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
+	adde	r0,r0,r9
+dest;	stb	r6,0(r4)
+
+.Lcopy_finish:
+	addze	r0,r0			/* add in final carry */
+	rldicl	r4,r0,32,0		/* fold two 32 bit halves together */
+	add	r3,r4,r0
+	srdi	r3,r3,32
 	blr
 
-/* These shouldn't go in the fixup section, since that would
-   cause the ex_table addresses to get out of order. */
-
-	.globl src_error_1
-src_error_1:
-	li	r6,0
-	subi	r5,r5,2
-95:	sth	r6,4(r4)
-	addi	r4,r4,2
-	srwi.	r6,r5,2
-	beq	3f
-	mtctr	r6
-	.globl src_error_2
-src_error_2:
-	li	r6,0
-96:	stwu	r6,4(r4)
-	bdnz	96b
-3:	andi.	r5,r5,3
-	beq	src_error
-	.globl src_error_3
-src_error_3:
-	li	r6,0
-	mtctr	r5
-	addi	r4,r4,3
-97:	stbu	r6,1(r4)
-	bdnz	97b
-	.globl src_error
-src_error:
+.Lsrc_error:
 	cmpdi	0,r7,0
-	beq	1f
+	beqlr
 	li	r6,-EFAULT
 	stw	r6,0(r7)
-1:	addze	r3,r0
 	blr
 
-	.globl dst_error
-dst_error:
+.Ldest_error:
 	cmpdi	0,r8,0
-	beq	1f
+	beqlr
 	li	r6,-EFAULT
 	stw	r6,0(r8)
-1:	addze	r3,r0
 	blr
-
-.section __ex_table,"a"
-	.align  3
-	.llong	81b,src_error_1
-	.llong	91b,dst_error
-	.llong	82b,src_error_2
-	.llong	92b,dst_error
-	.llong	83b,src_error_3
-	.llong	93b,dst_error
-	.llong	84b,src_error_3
-	.llong	94b,dst_error
-	.llong	95b,dst_error
-	.llong	96b,dst_error
-	.llong	97b,dst_error
diff --git a/arch/powerpc/lib/checksum_wrappers_64.c b/arch/powerpc/lib/checksum_wrappers_64.c
new file mode 100644
index 0000000..769b817
--- /dev/null
+++ b/arch/powerpc/lib/checksum_wrappers_64.c
@@ -0,0 +1,102 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2010
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/checksum.h>
+#include <asm/uaccess.h>
+
+__wsum csum_and_copy_from_user(const void __user *src, void *dst,
+			       int len, __wsum sum, int *err_ptr)
+{
+	unsigned int csum;
+
+	might_sleep();
+
+	*err_ptr = 0;
+
+	if (!len) {
+		csum = 0;
+		goto out;
+	}
+
+	if (unlikely((len < 0) || !access_ok(VERIFY_READ, src, len))) {
+		*err_ptr = -EFAULT;
+		csum = (__force unsigned int)sum;
+		goto out;
+	}
+
+	csum = csum_partial_copy_generic((void __force *)src, dst,
+					 len, sum, err_ptr, NULL);
+
+	if (unlikely(*err_ptr)) {
+		int missing = __copy_from_user(dst, src, len);
+
+		if (missing) {
+			memset(dst + len - missing, 0, missing);
+			*err_ptr = -EFAULT;
+		} else {
+			*err_ptr = 0;
+		}
+
+		csum = csum_partial(dst, len, sum);
+	}
+
+out:
+	return (__force __wsum)csum;
+}
+EXPORT_SYMBOL(csum_and_copy_from_user);
+
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
+			     __wsum sum, int *err_ptr)
+{
+	unsigned int csum;
+
+	might_sleep();
+
+	*err_ptr = 0;
+
+	if (!len) {
+		csum = 0;
+		goto out;
+	}
+
+	if (unlikely((len < 0) || !access_ok(VERIFY_WRITE, dst, len))) {
+		*err_ptr = -EFAULT;
+		csum = -1; /* invalid checksum */
+		goto out;
+	}
+
+	csum = csum_partial_copy_generic(src, (void __force *)dst,
+					 len, sum, NULL, err_ptr);
+
+	if (unlikely(*err_ptr)) {
+		csum = csum_partial(src, len, sum);
+
+		if (copy_to_user(dst, src, len)) {
+			*err_ptr = -EFAULT;
+			csum = -1; /* invalid checksum */
+		}
+	}
+
+out:
+	return (__force __wsum)csum;
+}
+EXPORT_SYMBOL(csum_and_copy_to_user);
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 74a7f41..55f19f9 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -62,7 +62,7 @@
 
 	.text
 	.stabs	"arch/powerpc/lib/",N_SO,0,0,0f
-	.stabs	"copy32.S",N_SO,0,0,0f
+	.stabs	"copy_32.S",N_SO,0,0,0f
 0:
 
 CACHELINE_BYTES = L1_CACHE_BYTES
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
index f644863..6a85380 100644
--- a/arch/powerpc/lib/ldstfp.S
+++ b/arch/powerpc/lib/ldstfp.S
@@ -17,6 +17,8 @@
 #include <asm/asm-offsets.h>
 #include <linux/errno.h>
 
+#ifdef CONFIG_PPC_FPU
+
 #define STKFRM	(PPC_MIN_STKFRM + 16)
 
 	.macro	extab	instr,handler
@@ -81,7 +83,7 @@
 	mfmsr	r6
 	ori	r7,r6,MSR_FP
 	cmpwi	cr7,r3,0
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stfd	fr0,STKFRM-16(r1)
@@ -93,7 +95,7 @@
 	lfd	fr0,STKFRM-16(r1)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -108,7 +110,7 @@
 	mfmsr	r6
 	ori	r7,r6,MSR_FP
 	cmpwi	cr7,r3,0
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stfd	fr0,STKFRM-16(r1)
@@ -120,7 +122,7 @@
 	lfd	fr0,STKFRM-16(r1)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -135,7 +137,7 @@
 	mfmsr	r6
 	ori	r7,r6,MSR_FP
 	cmpwi	cr7,r3,0
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stfd	fr0,STKFRM-16(r1)
@@ -147,7 +149,7 @@
 	lfd	fr0,STKFRM-16(r1)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -162,7 +164,7 @@
 	mfmsr	r6
 	ori	r7,r6,MSR_FP
 	cmpwi	cr7,r3,0
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stfd	fr0,STKFRM-16(r1)
@@ -174,7 +176,7 @@
 	lfd	fr0,STKFRM-16(r1)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -229,7 +231,7 @@
 	oris	r7,r6,MSR_VEC@h
 	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stvx	vr0,r1,r8
@@ -241,7 +243,7 @@
 	lvx	vr0,r1,r8
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -257,7 +259,7 @@
 	oris	r7,r6,MSR_VEC@h
 	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stvx	vr0,r1,r8
@@ -269,7 +271,7 @@
 	lvx	vr0,r1,r8
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -325,7 +327,7 @@
 	oris	r7,r6,MSR_VSX@h
 	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	STXVD2X(0,r1,r8)
@@ -337,7 +339,7 @@
 	LXVD2X(0,r1,r8)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -353,7 +355,7 @@
 	oris	r7,r6,MSR_VSX@h
 	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	STXVD2X(0,r1,r8)
@@ -365,7 +367,7 @@
 	LXVD2X(0,r1,r8)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -373,3 +375,5 @@
 	extab	2b,3b
 
 #endif /* CONFIG_VSX */
+
+#endif	/* CONFIG_PPC_FPU */
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 58e14fb..9b8182e 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -34,7 +34,7 @@
 		return;
 	holder_cpu = lock_value & 0xffff;
 	BUG_ON(holder_cpu >= NR_CPUS);
-	yield_count = lppaca[holder_cpu].yield_count;
+	yield_count = lppaca_of(holder_cpu).yield_count;
 	if ((yield_count & 1) == 0)
 		return;		/* virtual cpu is currently running */
 	rmb();
@@ -65,7 +65,7 @@
 		return;		/* no write lock at present */
 	holder_cpu = lock_value & 0xffff;
 	BUG_ON(holder_cpu >= NR_CPUS);
-	yield_count = lppaca[holder_cpu].yield_count;
+	yield_count = lppaca_of(holder_cpu).yield_count;
 	if ((yield_count & 1) == 0)
 		return;		/* virtual cpu is currently running */
 	rmb();
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index e0a9858..ae5189a 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -30,6 +30,7 @@
 #define XER_OV		0x40000000U
 #define XER_CA		0x20000000U
 
+#ifdef CONFIG_PPC_FPU
 /*
  * Functions in ldstfp.S
  */
@@ -41,6 +42,7 @@
 extern int do_stvx(int rn, unsigned long ea);
 extern int do_lxvd2x(int rn, unsigned long ea);
 extern int do_stxvd2x(int rn, unsigned long ea);
+#endif
 
 /*
  * Determine whether a conditional branch instruction would branch.
@@ -290,6 +292,7 @@
 	return write_mem_unaligned(val, ea, nb, regs);
 }
 
+#ifdef CONFIG_PPC_FPU
 /*
  * Check the address and alignment, and call func to do the actual
  * load or store.
@@ -351,6 +354,7 @@
 	}
 	return err;
 }
+#endif
 
 #ifdef CONFIG_ALTIVEC
 /* For Altivec/VMX, no need to worry about alignment */
@@ -1393,6 +1397,7 @@
 				regs->gpr[rd] = byterev_4(val);
 			goto ldst_done;
 
+#ifdef CONFIG_PPC_CPU
 		case 535:	/* lfsx */
 		case 567:	/* lfsux */
 			if (!(regs->msr & MSR_FP))
@@ -1424,6 +1429,7 @@
 			ea = xform_ea(instr, regs, u);
 			err = do_fp_store(rd, do_stfd, ea, 8, regs);
 			goto ldst_done;
+#endif
 
 #ifdef __powerpc64__
 		case 660:	/* stdbrx */
@@ -1534,6 +1540,7 @@
 		} while (++rd < 32);
 		goto instr_done;
 
+#ifdef CONFIG_PPC_FPU
 	case 48:	/* lfs */
 	case 49:	/* lfsu */
 		if (!(regs->msr & MSR_FP))
@@ -1565,6 +1572,7 @@
 		ea = dform_ea(instr, regs);
 		err = do_fp_store(rd, do_stfd, ea, 8, regs);
 		goto ldst_done;
+#endif
 
 #ifdef __powerpc64__
 	case 58:	/* ld[u], lwa */
diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile
index 0c16ab9..7d1dba0 100644
--- a/arch/powerpc/math-emu/Makefile
+++ b/arch/powerpc/math-emu/Makefile
@@ -15,4 +15,4 @@
 CFLAGS_fabs.o = -fno-builtin-fabs
 CFLAGS_math.o = -fno-builtin-fabs
 
-EXTRA_CFLAGS = -I. -Iinclude/math-emu -w
+ccflags-y = -I. -Iinclude/math-emu -w
diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c
index 1dc2fa5..5810967 100644
--- a/arch/powerpc/mm/40x_mmu.c
+++ b/arch/powerpc/mm/40x_mmu.c
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -47,6 +48,7 @@
 #include <asm/bootx.h>
 #include <asm/machdep.h>
 #include <asm/setup.h>
+
 #include "mmu_decl.h"
 
 extern int __map_without_ltlbs;
@@ -139,8 +141,19 @@
 	 * coverage with normal-sized pages (or other reasons) do not
 	 * attempt to allocate outside the allowed range.
 	 */
-
-	__initial_memory_limit_addr = memstart_addr + mapped;
+	memblock_set_current_limit(mapped);
 
 	return mapped;
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 40x can only access 16MB at the moment (see head_40x.S) */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+}
diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
index d8c6efb..024acab 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/44x_mmu.c
@@ -24,6 +24,8 @@
  */
 
 #include <linux/init.h>
+#include <linux/memblock.h>
+
 #include <asm/mmu.h>
 #include <asm/system.h>
 #include <asm/page.h>
@@ -213,6 +215,18 @@
 	return total_lowmem;
 }
 
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 44x has a 256M TLB entry pinned at boot */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, PPC_PIN_SIZE));
+}
+
 #ifdef CONFIG_SMP
 void __cpuinit mmu_init_secondary(int cpu)
 {
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index ce68708..bdca46e 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -4,9 +4,7 @@
 
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
-ifeq ($(CONFIG_PPC64),y)
-EXTRA_CFLAGS	+= -mno-minimal-toc
-endif
+ccflags-$(CONFIG_PPC64)	:= -mno-minimal-toc
 
 obj-y				:= fault.o mem.o pgtable.o gup.o \
 				   init_$(CONFIG_WORD_SIZE).o \
@@ -25,7 +23,7 @@
 				   mmu_context_hash$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_40x)		+= 40x_mmu.o
 obj-$(CONFIG_44x)		+= 44x_mmu.o
-obj-$(CONFIG_FSL_BOOKE)		+= fsl_booke_mmu.o
+obj-$(CONFIG_PPC_FSL_BOOK3E)	+= fsl_booke_mmu.o
 obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 ifeq ($(CONFIG_HUGETLB_PAGE),y)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 1bd712c..54f4fb9 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -30,6 +30,7 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>
+#include <linux/magic.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -385,6 +386,7 @@
 void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 {
 	const struct exception_table_entry *entry;
+	unsigned long *stackend;
 
 	/* Are we prepared to handle this fault?  */
 	if ((entry = search_exception_tables(regs->nip)) != NULL) {
@@ -413,5 +415,9 @@
 	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
 		regs->nip);
 
+	stackend = end_of_stack(current);
+	if (current != &init_task && *stackend != STACK_END_MAGIC)
+		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+
 	die("Kernel access of bad area", regs, sig);
 }
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 4b66a1e..f7802c8 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -40,6 +40,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/highmem.h>
+#include <linux/memblock.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -56,11 +57,6 @@
 
 unsigned int tlbcam_index;
 
-
-#if defined(CONFIG_LOWMEM_CAM_NUM_BOOL) && (CONFIG_LOWMEM_CAM_NUM >= NUM_TLBCAMS)
-#error "LOWMEM_CAM_NUM must be less than NUM_TLBCAMS"
-#endif
-
 #define NUM_TLBCAMS	(64)
 struct tlbcam TLBCAM[NUM_TLBCAMS];
 
@@ -137,7 +133,8 @@
 	if (mmu_has_feature(MMU_FTR_BIG_PHYS))
 		TLBCAM[index].MAS7 = (u64)phys >> 32;
 
-	if (flags & _PAGE_USER) {
+	/* Below is unlikely -- only for large user pages or similar */
+	if (pte_user(flags)) {
 	   TLBCAM[index].MAS3 |= MAS3_UX | MAS3_UR;
 	   TLBCAM[index].MAS3 |= ((flags & _PAGE_RW) ? MAS3_UW : 0);
 	}
@@ -184,6 +181,12 @@
 	return amount_mapped;
 }
 
+#ifdef CONFIG_PPC32
+
+#if defined(CONFIG_LOWMEM_CAM_NUM_BOOL) && (CONFIG_LOWMEM_CAM_NUM >= NUM_TLBCAMS)
+#error "LOWMEM_CAM_NUM must be less than NUM_TLBCAMS"
+#endif
+
 unsigned long __init mmu_mapin_ram(unsigned long top)
 {
 	return tlbcam_addrs[tlbcam_index - 1].limit - PAGE_OFFSET + 1;
@@ -213,5 +216,15 @@
 	pr_cont("%lu Mb, residual: %dMb\n", tlbcam_sz(tlbcam_index - 1) >> 20,
 	        (unsigned int)((total_lowmem - __max_low_memory) >> 20));
 
-	__initial_memory_limit_addr = memstart_addr + __max_low_memory;
+	memblock_set_current_limit(memstart_addr + __max_low_memory);
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	phys_addr_t limit = first_memblock_base + first_memblock_size;
+
+	/* 64M mapped initially according to head_fsl_booke.S */
+	memblock_set_current_limit(min_t(u64, limit, 0x04000000));
+}
+#endif
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 09dffe6..83f534d 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -588,7 +588,7 @@
 	unsigned long pteg_count;
 	unsigned long prot;
 	unsigned long base = 0, size = 0, limit;
-	int i;
+	struct memblock_region *reg;
 
 	DBG(" -> htab_initialize()\n");
 
@@ -625,7 +625,7 @@
 		if (machine_is(cell))
 			limit = 0x80000000;
 		else
-			limit = 0;
+			limit = MEMBLOCK_ALLOC_ANYWHERE;
 
 		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes, limit);
 
@@ -649,7 +649,7 @@
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	linear_map_hash_slots = __va(memblock_alloc_base(linear_map_hash_count,
-						    1, memblock.rmo_size));
+						    1, ppc64_rma_size));
 	memset(linear_map_hash_slots, 0, linear_map_hash_count);
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
@@ -659,9 +659,9 @@
 	 */
 
 	/* create bolted the linear mapping in the hash table */
-	for (i=0; i < memblock.memory.cnt; i++) {
-		base = (unsigned long)__va(memblock.memory.region[i].base);
-		size = memblock.memory.region[i].size;
+	for_each_memblock(memory, reg) {
+		base = (unsigned long)__va(reg->base);
+		size = reg->size;
 
 		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
 		    base, size, prot);
@@ -696,7 +696,8 @@
 #endif /* CONFIG_U3_DART */
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
 				prot, mmu_linear_psize, mmu_kernel_ssize));
-       }
+	}
+	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 
 	/*
 	 * If we have a memory_limit and we've allocated TCEs then we need to
@@ -1247,3 +1248,23 @@
 	local_irq_restore(flags);
 }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* On LPAR systems, the first entry is our RMA region,
+	 * non-LPAR 64-bit hash MMU systems don't have a limitation
+	 * on real mode access, but using the first entry works well
+	 * enough. We also clamp it to 1G to avoid some funky things
+	 * such as RTAS bugs etc...
+	 */
+	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+	/* Finally limit subsequent allocations */
+	memblock_set_current_limit(ppc64_rma_size);
+}
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 6a6975d..742da43 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -92,12 +92,6 @@
 unsigned long __max_low_memory = MAX_LOW_MEM;
 
 /*
- * address of the limit of what is accessible with initial MMU setup -
- * 256MB usually, but only 16MB on 601.
- */
-phys_addr_t __initial_memory_limit_addr = (phys_addr_t)0x10000000;
-
-/*
  * Check for command-line options that affect what MMU_init will do.
  */
 void MMU_setup(void)
@@ -126,13 +120,6 @@
 	if (ppc_md.progress)
 		ppc_md.progress("MMU:enter", 0x111);
 
-	/* 601 can only access 16MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
-		__initial_memory_limit_addr = 0x01000000;
-	/* 8xx can only access 8MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 0x50)
-		__initial_memory_limit_addr = 0x00800000;
-
 	/* parse args from command line */
 	MMU_setup();
 
@@ -190,20 +177,18 @@
 #ifdef CONFIG_BOOTX_TEXT
 	btext_unmap();
 #endif
+
+	/* Shortly after that, the entire linear mapping will be available */
+	memblock_set_current_limit(lowmem_end_addr);
 }
 
 /* This is only called until mem_init is done. */
 void __init *early_get_page(void)
 {
-	void *p;
-
-	if (init_bootmem_done) {
-		p = alloc_bootmem_pages(PAGE_SIZE);
-	} else {
-		p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
-					__initial_memory_limit_addr));
-	}
-	return p;
+	if (init_bootmem_done)
+		return alloc_bootmem_pages(PAGE_SIZE);
+	else
+		return __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE));
 }
 
 /* Free up now-unused memory */
@@ -252,3 +237,17 @@
 }
 #endif
 
+
+#ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 8xx can only access 8MB at the moment */
+	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
+}
+#endif /* CONFIG_8xx */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index ace85fa..6374b21 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -330,3 +330,4 @@
 	return 0;
 }
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1a84a8d..a664996 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -82,18 +82,11 @@
 	return pfn < max_pfn;
 #else
 	unsigned long paddr = (pfn << PAGE_SHIFT);
-	int i;
-	for (i=0; i < memblock.memory.cnt; i++) {
-		unsigned long base;
+	struct memblock_region *reg;
 
-		base = memblock.memory.region[i].base;
-
-		if ((paddr >= base) &&
-			(paddr < (base + memblock.memory.region[i].size))) {
+	for_each_memblock(memory, reg)
+		if (paddr >= reg->base && paddr < (reg->base + reg->size))
 			return 1;
-		}
-	}
-
 	return 0;
 #endif
 }
@@ -149,23 +142,19 @@
 walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 		void *arg, int (*func)(unsigned long, unsigned long, void *))
 {
-	struct memblock_property res;
-	unsigned long pfn, len;
-	u64 end;
+	struct memblock_region *reg;
+	unsigned long end_pfn = start_pfn + nr_pages;
+	unsigned long tstart, tend;
 	int ret = -1;
 
-	res.base = (u64) start_pfn << PAGE_SHIFT;
-	res.size = (u64) nr_pages << PAGE_SHIFT;
-
-	end = res.base + res.size - 1;
-	while ((res.base < end) && (memblock_find(&res) >= 0)) {
-		pfn = (unsigned long)(res.base >> PAGE_SHIFT);
-		len = (unsigned long)(res.size >> PAGE_SHIFT);
-		ret = (*func)(pfn, len, arg);
+	for_each_memblock(memory, reg) {
+		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
+		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
+		if (tstart >= tend)
+			continue;
+		ret = (*func)(tstart, tend - tstart, arg);
 		if (ret)
 			break;
-		res.base += (res.size + 1);
-		res.size = (end - res.base + 1);
 	}
 	return ret;
 }
@@ -179,9 +168,9 @@
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 void __init do_init_bootmem(void)
 {
-	unsigned long i;
 	unsigned long start, bootmap_pages;
 	unsigned long total_pages;
+	struct memblock_region *reg;
 	int boot_mapsize;
 
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
@@ -204,10 +193,10 @@
 	boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn);
 
 	/* Add active regions with valid PFNs */
-	for (i = 0; i < memblock.memory.cnt; i++) {
+	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+		start_pfn = memblock_region_memory_base_pfn(reg);
+		end_pfn = memblock_region_memory_end_pfn(reg);
 		add_active_range(0, start_pfn, end_pfn);
 	}
 
@@ -218,29 +207,21 @@
 	free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT);
 
 	/* reserve the sections we're already using */
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long addr = memblock.reserved.region[i].base +
-				     memblock_size_bytes(&memblock.reserved, i) - 1;
-		if (addr < lowmem_end_addr)
-			reserve_bootmem(memblock.reserved.region[i].base,
-					memblock_size_bytes(&memblock.reserved, i),
-					BOOTMEM_DEFAULT);
-		else if (memblock.reserved.region[i].base < lowmem_end_addr) {
-			unsigned long adjusted_size = lowmem_end_addr -
-				      memblock.reserved.region[i].base;
-			reserve_bootmem(memblock.reserved.region[i].base,
-					adjusted_size, BOOTMEM_DEFAULT);
+	for_each_memblock(reserved, reg) {
+		unsigned long top = reg->base + reg->size - 1;
+		if (top < lowmem_end_addr)
+			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+		else if (reg->base < lowmem_end_addr) {
+			unsigned long trunc_size = lowmem_end_addr - reg->base;
+			reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
 		}
 	}
 #else
 	free_bootmem_with_active_regions(0, max_pfn);
 
 	/* reserve the sections we're already using */
-	for (i = 0; i < memblock.reserved.cnt; i++)
-		reserve_bootmem(memblock.reserved.region[i].base,
-				memblock_size_bytes(&memblock.reserved, i),
-				BOOTMEM_DEFAULT);
-
+	for_each_memblock(reserved, reg)
+		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
 #endif
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
@@ -251,22 +232,15 @@
 /* mark pages that don't exist as nosave */
 static int __init mark_nonram_nosave(void)
 {
-	unsigned long memblock_next_region_start_pfn,
-		      memblock_region_max_pfn;
-	int i;
+	struct memblock_region *reg, *prev = NULL;
 
-	for (i = 0; i < memblock.memory.cnt - 1; i++) {
-		memblock_region_max_pfn =
-			(memblock.memory.region[i].base >> PAGE_SHIFT) +
-			(memblock.memory.region[i].size >> PAGE_SHIFT);
-		memblock_next_region_start_pfn =
-			memblock.memory.region[i+1].base >> PAGE_SHIFT;
-
-		if (memblock_region_max_pfn < memblock_next_region_start_pfn)
-			register_nosave_region(memblock_region_max_pfn,
-					       memblock_next_region_start_pfn);
+	for_each_memblock(memory, reg) {
+		if (prev &&
+		    memblock_region_memory_end_pfn(prev) < memblock_region_memory_base_pfn(reg))
+			register_nosave_region(memblock_region_memory_end_pfn(prev),
+					       memblock_region_memory_base_pfn(reg));
+		prev = reg;
 	}
-
 	return 0;
 }
 
@@ -327,7 +301,7 @@
 		swiotlb_init(1);
 #endif
 
-	num_physpages = memblock.memory.size >> PAGE_SHIFT;
+	num_physpages = memblock_phys_mem_size() >> PAGE_SHIFT;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index ddfd7ad..5ce9984 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -334,7 +334,7 @@
 	/* We don't touch CPU 0 map, it's allocated at aboot and kept
 	 * around forever
 	 */
-	if (cpu == 0)
+	if (cpu == boot_cpuid)
 		return NOTIFY_OK;
 
 	switch (action) {
@@ -420,9 +420,11 @@
 	 */
 	context_map = alloc_bootmem(CTX_MAP_SIZE);
 	context_mm = alloc_bootmem(sizeof(void *) * (last_context + 1));
+#ifndef CONFIG_SMP
 	stale_map[0] = alloc_bootmem(CTX_MAP_SIZE);
+#else
+	stale_map[boot_cpuid] = alloc_bootmem(CTX_MAP_SIZE);
 
-#ifdef CONFIG_SMP
 	register_cpu_notifier(&mmu_context_cpu_nb);
 #endif
 
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 63b84a0..dd0a258 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -140,10 +140,13 @@
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(unsigned long top);
 
-#elif defined(CONFIG_FSL_BOOKE)
+#elif defined(CONFIG_PPC_FSL_BOOK3E)
+extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx);
+#ifdef CONFIG_PPC32
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(unsigned long top);
 extern void adjust_total_lowmem(void);
+#endif
 extern void loadcam_entry(unsigned int index);
 
 struct tlbcam {
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 002878c..74505b2 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -802,16 +802,17 @@
 	unsigned long top_of_ram = memblock_end_of_DRAM();
 	unsigned long total_ram = memblock_phys_mem_size();
 	unsigned long start_pfn, end_pfn;
-	unsigned int i, nid = 0;
+	unsigned int nid = 0;
+	struct memblock_region *reg;
 
 	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
 	       top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (top_of_ram - total_ram) >> 20);
 
-	for (i = 0; i < memblock.memory.cnt; ++i) {
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
+		start_pfn = memblock_region_memory_base_pfn(reg);
+		end_pfn = memblock_region_memory_end_pfn(reg);
 
 		fake_numa_create_new_node(end_pfn, &nid);
 		add_active_range(nid, start_pfn, end_pfn);
@@ -947,11 +948,11 @@
 static void mark_reserved_regions_for_nid(int nid)
 {
 	struct pglist_data *node = NODE_DATA(nid);
-	int i;
+	struct memblock_region *reg;
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long physbase = memblock.reserved.region[i].base;
-		unsigned long size = memblock.reserved.region[i].size;
+	for_each_memblock(reserved, reg) {
+		unsigned long physbase = reg->base;
+		unsigned long size = reg->size;
 		unsigned long start_pfn = physbase >> PAGE_SHIFT;
 		unsigned long end_pfn = PFN_UP(physbase + size);
 		struct node_active_region node_ar;
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index f8a0182..11571e1 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -223,8 +223,7 @@
 	 * Find some memory for the hash table.
 	 */
 	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
-	Hash = __va(memblock_alloc_base(Hash_size, Hash_size,
-				   __initial_memory_limit_addr));
+	Hash = __va(memblock_alloc(Hash_size, Hash_size));
 	cacheable_memzero(Hash, Hash_size);
 	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
 
@@ -272,3 +271,18 @@
 
 	if ( ppc_md.progress ) ppc_md.progress("hash:done", 0x205);
 }
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* We don't currently support the first MEMBLOCK not mapping 0
+	 * physical on those processors
+	 */
+	BUG_ON(first_memblock_base != 0);
+
+	/* 601 can only access 16MB at the moment */
+	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
+	else /* Anything else has 256M mapped */
+		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
+}
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index fe391e9..36c0c44 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -349,11 +349,47 @@
 
 static void setup_page_sizes(void)
 {
-	unsigned int tlb0cfg = mfspr(SPRN_TLB0CFG);
-	unsigned int tlb0ps = mfspr(SPRN_TLB0PS);
-	unsigned int eptcfg = mfspr(SPRN_EPTCFG);
+	unsigned int tlb0cfg;
+	unsigned int tlb0ps;
+	unsigned int eptcfg;
 	int i, psize;
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	unsigned int mmucfg = mfspr(SPRN_MMUCFG);
+
+	if (((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) &&
+		(mmu_has_feature(MMU_FTR_TYPE_FSL_E))) {
+		unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
+		unsigned int min_pg, max_pg;
+
+		min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
+		max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+			struct mmu_psize_def *def;
+			unsigned int shift;
+
+			def = &mmu_psize_defs[psize];
+			shift = def->shift;
+
+			if (shift == 0)
+				continue;
+
+			/* adjust to be in terms of 4^shift Kb */
+			shift = (shift - 10) >> 1;
+
+			if ((shift >= min_pg) && (shift <= max_pg))
+				def->flags |= MMU_PAGE_SIZE_DIRECT;
+		}
+
+		goto no_indirect;
+	}
+#endif
+
+	tlb0cfg = mfspr(SPRN_TLB0CFG);
+	tlb0ps = mfspr(SPRN_TLB0PS);
+	eptcfg = mfspr(SPRN_EPTCFG);
+
 	/* Look for supported direct sizes */
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		struct mmu_psize_def *def = &mmu_psize_defs[psize];
@@ -505,10 +541,26 @@
 	 */
 	linear_map_top = memblock_end_of_DRAM();
 
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+		unsigned int num_cams;
+
+		/* use a quarter of the TLBCAM for bolted linear map */
+		num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+		linear_map_top = map_mem_in_cams(linear_map_top, num_cams);
+
+		/* limit memory so we dont have linear faults */
+		memblock_enforce_memory_limit(linear_map_top);
+		memblock_analyze();
+	}
+#endif
+
 	/* A sync won't hurt us after mucking around with
 	 * the MMU configuration
 	 */
 	mb();
+
+	memblock_set_current_limit(linear_map_top);
 }
 
 void __init early_init_mmu(void)
@@ -521,4 +573,18 @@
 	__early_init_mmu(0);
 }
 
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/* On Embedded 64-bit, we adjust the RMA size to match
+	 * the bolted TLB entry. We know for now that only 1G
+	 * entries are supported though that may eventually
+	 * change. We crop it to the size of the first MEMBLOCK to
+	 * avoid going over total available memory just in case...
+	 */
+	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+
+	/* Finally limit subsequent allocations */
+	memblock_set_current_limit(ppc64_memblock_base + ppc64_rma_size);
+}
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S
index b9d9fed..af405ee 100644
--- a/arch/powerpc/mm/tlb_nohash_low.S
+++ b/arch/powerpc/mm/tlb_nohash_low.S
@@ -367,7 +367,7 @@
 #error Unsupported processor type !
 #endif
 
-#if defined(CONFIG_FSL_BOOKE)
+#if defined(CONFIG_PPC_FSL_BOOK3E)
 /*
  * extern void loadcam_entry(unsigned int index)
  *
diff --git a/arch/powerpc/oprofile/Makefile b/arch/powerpc/oprofile/Makefile
index e219ca4..73456c4 100644
--- a/arch/powerpc/oprofile/Makefile
+++ b/arch/powerpc/oprofile/Makefile
@@ -1,8 +1,6 @@
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
-ifeq ($(CONFIG_PPC64),y)
-EXTRA_CFLAGS	+= -mno-minimal-toc
-endif
+ccflags-$(CONFIG_PPC64)	:= -mno-minimal-toc
 
 obj-$(CONFIG_OPROFILE) += oprofile.o
 
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index b4278cf..f75301f 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -105,7 +105,7 @@
 		}
 	} else {
 #ifdef CONFIG_PPC64
-		if (!test_thread_flag(TIF_32BIT)) {
+		if (!is_32bit_task()) {
 			while (depth--) {
 				sp = user_getsp64(sp, first_frame);
 				if (!sp)
diff --git a/arch/powerpc/oprofile/op_model_fsl_emb.c b/arch/powerpc/oprofile/op_model_fsl_emb.c
index 62312ab..d4e6507 100644
--- a/arch/powerpc/oprofile/op_model_fsl_emb.c
+++ b/arch/powerpc/oprofile/op_model_fsl_emb.c
@@ -2,7 +2,7 @@
  * Freescale Embedded oprofile support, based on ppc64 oprofile support
  * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
  *
- * Copyright (c) 2004 Freescale Semiconductor, Inc
+ * Copyright (c) 2004, 2010 Freescale Semiconductor, Inc
  *
  * Author: Andy Fleming
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
@@ -321,9 +321,6 @@
 	int val;
 	int i;
 
-	/* set the PMM bit (see comment below) */
-	mtmsr(mfmsr() | MSR_PMM);
-
 	pc = regs->nip;
 	is_kernel = is_kernel_addr(pc);
 
@@ -340,9 +337,13 @@
 	}
 
 	/* The freeze bit was set by the interrupt. */
-	/* Clear the freeze bit, and reenable the interrupt.
-	 * The counters won't actually start until the rfi clears
-	 * the PMM bit */
+	/* Clear the freeze bit, and reenable the interrupt.  The
+	 * counters won't actually start until the rfi clears the PMM
+	 * bit.  The PMM bit should not be set until after the interrupt
+	 * is cleared to avoid it getting lost in some hypervisor
+	 * environments.
+	 */
+	mtmsr(mfmsr() | MSR_PMM);
 	pmc_start_ctrs(1);
 }
 
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 69d668c..0f979c5 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -17,6 +17,16 @@
 	help
 	  This option enables support for the IBM PPC440EP evaluation board.
 
+config BLUESTONE
+	bool "Bluestone"
+	depends on 44x
+	default n
+	select PPC44x_SIMPLE
+	select APM821xx
+	select IBM_NEW_EMAC_RGMII
+	help
+	  This option enables support for the APM APM821xx Evaluation board.
+
 config EBONY
 	bool "Ebony"
 	depends on 44x
@@ -293,6 +303,12 @@
 	select IBM_NEW_EMAC_ZMII
 	select IBM_NEW_EMAC_TAH
 
+config APM821xx
+	bool
+	select PPC_FPU
+	select IBM_NEW_EMAC_EMAC4
+	select IBM_NEW_EMAC_TAH
+
 # 44x errata/workaround config symbols, selected by the CPU models above
 config IBM440EP_ERR42
 	bool
diff --git a/arch/powerpc/platforms/44x/ppc44x_simple.c b/arch/powerpc/platforms/44x/ppc44x_simple.c
index 5f7a29d..7ddcba3 100644
--- a/arch/powerpc/platforms/44x/ppc44x_simple.c
+++ b/arch/powerpc/platforms/44x/ppc44x_simple.c
@@ -52,6 +52,7 @@
 static char *board[] __initdata = {
 	"amcc,arches",
 	"amcc,bamboo",
+	"amcc,bluestone",
 	"amcc,canyonlands",
 	"amcc,glacier",
 	"ibm,ebony",
diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig
index 021763a..73f4135 100644
--- a/arch/powerpc/platforms/83xx/Kconfig
+++ b/arch/powerpc/platforms/83xx/Kconfig
@@ -10,12 +10,12 @@
 if PPC_83xx
 
 config MPC830x_RDB
-	bool "Freescale MPC830x RDB"
+	bool "Freescale MPC830x RDB and derivatives"
 	select DEFAULT_UIMAGE
 	select PPC_MPC831x
 	select FSL_GTM
 	help
-	  This option enables support for the MPC8308 RDB board.
+	  This option enables support for the MPC8308 RDB and MPC8308 P1M boards.
 
 config MPC831x_RDB
 	bool "Freescale MPC831x RDB"
diff --git a/arch/powerpc/platforms/83xx/mpc830x_rdb.c b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
index ac102ee..846831d 100644
--- a/arch/powerpc/platforms/83xx/mpc830x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
@@ -65,7 +65,8 @@
 	unsigned long root = of_get_flat_dt_root();
 
 	return of_flat_dt_is_compatible(root, "MPC8308RDB") ||
-	       of_flat_dt_is_compatible(root, "fsl,mpc8308rdb");
+	       of_flat_dt_is_compatible(root, "fsl,mpc8308rdb") ||
+	       of_flat_dt_is_compatible(root, "denx,mpc8308_p1m");
 }
 
 static struct of_device_id __initdata of_bus_ids[] = {
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index bea1f59..b6976e1 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -11,6 +11,8 @@
 
 if FSL_SOC_BOOKE
 
+if PPC32
+
 config MPC8540_ADS
 	bool "Freescale MPC8540 ADS"
 	select DEFAULT_UIMAGE
@@ -153,10 +155,20 @@
 	help
 	  This option enables support for the Wind River SBC8560 board
 
+config P3041_DS
+	bool "Freescale P3041 DS"
+	select DEFAULT_UIMAGE
+	select PPC_E500MC
+	select PHYS_64BIT
+	select SWIOTLB
+	select MPC8xxx_GPIO
+	select HAS_RAPIDIO
+	help
+	  This option enables support for the P3041 DS board
+
 config P4080_DS
 	bool "Freescale P4080 DS"
 	select DEFAULT_UIMAGE
-	select PPC_FSL_BOOK3E
 	select PPC_E500MC
 	select PHYS_64BIT
 	select SWIOTLB
@@ -165,6 +177,20 @@
 	help
 	  This option enables support for the P4080 DS board
 
+endif # PPC32
+
+config P5020_DS
+	bool "Freescale P5020 DS"
+	select DEFAULT_UIMAGE
+	select E500
+	select PPC_E500MC
+	select PHYS_64BIT
+	select SWIOTLB
+	select MPC8xxx_GPIO
+	select HAS_RAPIDIO
+	help
+	  This option enables support for the P5020 DS board
+
 endif # FSL_SOC_BOOKE
 
 config TQM85xx
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index a2ec3f8..dd70db7 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -11,7 +11,9 @@
 obj-$(CONFIG_MPC85xx_MDS) += mpc85xx_mds.o
 obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o
 obj-$(CONFIG_P1022_DS)    += p1022_ds.o
+obj-$(CONFIG_P3041_DS)    += p3041_ds.o corenet_ds.o
 obj-$(CONFIG_P4080_DS)    += p4080_ds.o corenet_ds.o
+obj-$(CONFIG_P5020_DS)    += p5020_ds.o corenet_ds.o
 obj-$(CONFIG_STX_GP3)	  += stx_gp3.o
 obj-$(CONFIG_TQM85xx)	  += tqm85xx.o
 obj-$(CONFIG_SBC8560)     += sbc8560.o
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 34e0090..2b390d1 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -112,6 +112,8 @@
 	{ .compatible = "soc", },
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
+	/* So that the DMA channel nodes can be probed individually: */
+	{ .compatible = "fsl,eloplus-dma", },
 	{},
 };
 
diff --git a/arch/powerpc/platforms/85xx/p3041_ds.c b/arch/powerpc/platforms/85xx/p3041_ds.c
new file mode 100644
index 0000000..0ed52e1
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/p3041_ds.c
@@ -0,0 +1,64 @@
+/*
+ * P3041 DS Setup
+ *
+ * Maintained by Kumar Gala (see MAINTAINERS for contact information)
+ *
+ * Copyright 2009-2010 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/kdev_t.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/phy.h>
+
+#include <asm/system.h>
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <mm/mmu_decl.h>
+#include <asm/prom.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+
+#include <linux/of_platform.h>
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+
+#include "corenet_ds.h"
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init p3041_ds_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "fsl,P3041DS");
+}
+
+define_machine(p3041_ds) {
+	.name			= "P3041 DS",
+	.probe			= p3041_ds_probe,
+	.setup_arch		= corenet_ds_setup_arch,
+	.init_IRQ		= corenet_ds_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_coreint_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
+
+machine_device_initcall(p3041_ds, corenet_ds_publish_devices);
+
+#ifdef CONFIG_SWIOTLB
+machine_arch_initcall(p3041_ds, swiotlb_setup_bus_notifier);
+#endif
diff --git a/arch/powerpc/platforms/85xx/p5020_ds.c b/arch/powerpc/platforms/85xx/p5020_ds.c
new file mode 100644
index 0000000..7467b71
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/p5020_ds.c
@@ -0,0 +1,69 @@
+/*
+ * P5020 DS Setup
+ *
+ * Maintained by Kumar Gala (see MAINTAINERS for contact information)
+ *
+ * Copyright 2009-2010 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/kdev_t.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/phy.h>
+
+#include <asm/system.h>
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <mm/mmu_decl.h>
+#include <asm/prom.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+
+#include <linux/of_platform.h>
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+
+#include "corenet_ds.h"
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init p5020_ds_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "fsl,P5020DS");
+}
+
+define_machine(p5020_ds) {
+	.name			= "P5020 DS",
+	.probe			= p5020_ds_probe,
+	.setup_arch		= corenet_ds_setup_arch,
+	.init_IRQ		= corenet_ds_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
+#ifdef CONFIG_PPC64
+	.get_irq		= mpic_get_irq,
+#else
+	.get_irq		= mpic_get_coreint_irq,
+#endif
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
+
+machine_device_initcall(p5020_ds, corenet_ds_publish_devices);
+
+#ifdef CONFIG_SWIOTLB
+machine_arch_initcall(p5020_ds, swiotlb_setup_bus_notifier);
+#endif
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index a6b1065..5c91a99 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/kexec.h>
+#include <linux/highmem.h>
 
 #include <asm/machdep.h>
 #include <asm/pgtable.h>
@@ -79,6 +80,7 @@
 	local_irq_save(flags);
 
 	out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr);
+#ifdef CONFIG_PPC32
 	out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
 
 	if (!ioremappable)
@@ -88,6 +90,12 @@
 	/* Wait a bit for the CPU to ack. */
 	while ((__secondary_hold_acknowledge != nr) && (++n < 1000))
 		mdelay(1);
+#else
+	out_be64((u64 *)(bptr_vaddr + BOOT_ENTRY_ADDR_UPPER),
+		__pa((u64)*((unsigned long long *) generic_secondary_smp_init)));
+
+	smp_generic_kick_cpu(nr);
+#endif
 
 	local_irq_restore(flags);
 
@@ -114,19 +122,15 @@
 };
 
 #ifdef CONFIG_KEXEC
-static int kexec_down_cpus = 0;
+atomic_t kexec_down_cpus = ATOMIC_INIT(0);
 
 void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
 {
-	mpic_teardown_this_cpu(1);
+	local_irq_disable();
 
-	/* When crashing, this gets called on all CPU's we only
-	 * take down the non-boot cpus */
-	if (smp_processor_id() != boot_cpuid)
-	{
-		local_irq_disable();
-		kexec_down_cpus++;
-
+	if (secondary) {
+		atomic_inc(&kexec_down_cpus);
+		/* loop forever */
 		while (1);
 	}
 }
@@ -137,16 +141,65 @@
 		ppc_md.kexec_cpu_down(0,1);
 }
 
-static void mpc85xx_smp_machine_kexec(struct kimage *image)
+static void map_and_flush(unsigned long paddr)
 {
-	int timeout = 2000;
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned long kaddr  = (unsigned long)kmap(page);
+
+	flush_dcache_range(kaddr, kaddr + PAGE_SIZE);
+	kunmap(page);
+}
+
+/**
+ * Before we reset the other cores, we need to flush relevant cache
+ * out to memory so we don't get anything corrupted, some of these flushes
+ * are performed out of an overabundance of caution as interrupts are not
+ * disabled yet and we can switch cores
+ */
+static void mpc85xx_smp_flush_dcache_kexec(struct kimage *image)
+{
+	kimage_entry_t *ptr, entry;
+	unsigned long paddr;
 	int i;
 
-	set_cpus_allowed(current, cpumask_of_cpu(boot_cpuid));
+	if (image->type == KEXEC_TYPE_DEFAULT) {
+		/* normal kexec images are stored in temporary pages */
+		for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE);
+		     ptr = (entry & IND_INDIRECTION) ?
+				phys_to_virt(entry & PAGE_MASK) : ptr + 1) {
+			if (!(entry & IND_DESTINATION)) {
+				map_and_flush(entry);
+			}
+		}
+		/* flush out last IND_DONE page */
+		map_and_flush(entry);
+	} else {
+		/* crash type kexec images are copied to the crash region */
+		for (i = 0; i < image->nr_segments; i++) {
+			struct kexec_segment *seg = &image->segment[i];
+			for (paddr = seg->mem; paddr < seg->mem + seg->memsz;
+			     paddr += PAGE_SIZE) {
+				map_and_flush(paddr);
+			}
+		}
+	}
 
-	smp_call_function(mpc85xx_smp_kexec_down, NULL, 0);
+	/* also flush the kimage struct to be passed in as well */
+	flush_dcache_range((unsigned long)image,
+			   (unsigned long)image + sizeof(*image));
+}
 
-	while ( (kexec_down_cpus != (num_online_cpus() - 1)) &&
+static void mpc85xx_smp_machine_kexec(struct kimage *image)
+{
+	int timeout = INT_MAX;
+	int i, num_cpus = num_present_cpus();
+
+	mpc85xx_smp_flush_dcache_kexec(image);
+
+	if (image->type == KEXEC_TYPE_DEFAULT)
+		smp_call_function(mpc85xx_smp_kexec_down, NULL, 0);
+
+	while ( (atomic_read(&kexec_down_cpus) != (num_cpus - 1)) &&
 		( timeout > 0 ) )
 	{
 		timeout--;
@@ -155,7 +208,7 @@
 	if ( !timeout )
 		printk(KERN_ERR "Unable to bring down secondary cpu(s)");
 
-	for (i = 0; i < num_present_cpus(); i++)
+	for (i = 0; i < num_cpus; i++)
 	{
 		if ( i == smp_processor_id() ) continue;
 		mpic_reset_core(i);
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index d361f81..111138c 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -125,6 +125,7 @@
 
 config E500
 	select FSL_EMB_PERFMON
+	select PPC_FSL_BOOK3E
 	bool
 
 config PPC_E500MC
@@ -166,9 +167,14 @@
 
 config FSL_BOOKE
 	bool
-	depends on E200 || E500
+	depends on (E200 || E500) && PPC32
 	default y
 
+# this is for common code between PPC32 & PPC64 FSL BOOKE
+config PPC_FSL_BOOK3E
+	bool
+	select FSL_EMB_PERFMON
+	default y if FSL_BOOKE
 
 config PTE_64BIT
 	bool
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 9708553..e3e379c 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -310,9 +310,9 @@
 }
 
 static struct irq_chip msic_irq_chip = {
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
-	.shutdown	= unmask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
+	.irq_shutdown	= mask_msi_irq,
 	.name		= "AXON-MSI",
 };
 
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 1d3c4ef..5ec1e47 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -173,8 +173,10 @@
 		return -ENODEV;
 
 	size = of_get_property(np, "ibm,cbe-ptcal-size", NULL);
-	if (!size)
+	if (!size) {
+		of_node_put(np);
 		return -ENODEV;
+	}
 
 	pr_debug("%s: enabling PTCAL, size = 0x%x\n", __func__, *size);
 	order = get_order(*size);
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 5876e88..3f2e557 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -258,8 +258,10 @@
 		return NO_IRQ;
 	imap += intsize + 1;
 	tmp = of_get_property(iic, "#interrupt-cells", NULL);
-	if (tmp == NULL)
+	if (tmp == NULL) {
+		of_node_put(iic);
 		return NO_IRQ;
+	}
 	intsize = *tmp;
 	/* Assume unit is last entry of interrupt specifier */
 	unit = imap[intsize - 1];
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 1a40da9..02f7b11 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -154,6 +154,7 @@
 	.release = spufs_attr_release,					\
 	.read	 = spufs_attr_read,					\
 	.write	 = spufs_attr_write,					\
+	.llseek  = generic_file_llseek,					\
 };
 
 
@@ -521,6 +522,7 @@
 	.release = spufs_cntl_release,
 	.read = simple_attr_read,
 	.write = simple_attr_write,
+	.llseek	= generic_file_llseek,
 	.mmap = spufs_cntl_mmap,
 };
 
@@ -714,6 +716,7 @@
 static const struct file_operations spufs_mbox_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_mbox_read,
+	.llseek	= no_llseek,
 };
 
 static ssize_t spufs_mbox_stat_read(struct file *file, char __user *buf,
@@ -743,6 +746,7 @@
 static const struct file_operations spufs_mbox_stat_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_mbox_stat_read,
+	.llseek = no_llseek,
 };
 
 /* low-level ibox access function */
@@ -863,6 +867,7 @@
 	.read	= spufs_ibox_read,
 	.poll	= spufs_ibox_poll,
 	.fasync	= spufs_ibox_fasync,
+	.llseek = no_llseek,
 };
 
 static ssize_t spufs_ibox_stat_read(struct file *file, char __user *buf,
@@ -890,6 +895,7 @@
 static const struct file_operations spufs_ibox_stat_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_ibox_stat_read,
+	.llseek = no_llseek,
 };
 
 /* low-level mailbox write */
@@ -1011,6 +1017,7 @@
 	.write	= spufs_wbox_write,
 	.poll	= spufs_wbox_poll,
 	.fasync	= spufs_wbox_fasync,
+	.llseek = no_llseek,
 };
 
 static ssize_t spufs_wbox_stat_read(struct file *file, char __user *buf,
@@ -1038,6 +1045,7 @@
 static const struct file_operations spufs_wbox_stat_fops = {
 	.open	= spufs_pipe_open,
 	.read	= spufs_wbox_stat_read,
+	.llseek = no_llseek,
 };
 
 static int spufs_signal1_open(struct inode *inode, struct file *file)
@@ -1166,6 +1174,7 @@
 	.read = spufs_signal1_read,
 	.write = spufs_signal1_write,
 	.mmap = spufs_signal1_mmap,
+	.llseek = no_llseek,
 };
 
 static const struct file_operations spufs_signal1_nosched_fops = {
@@ -1173,6 +1182,7 @@
 	.release = spufs_signal1_release,
 	.write = spufs_signal1_write,
 	.mmap = spufs_signal1_mmap,
+	.llseek = no_llseek,
 };
 
 static int spufs_signal2_open(struct inode *inode, struct file *file)
@@ -1305,6 +1315,7 @@
 	.read = spufs_signal2_read,
 	.write = spufs_signal2_write,
 	.mmap = spufs_signal2_mmap,
+	.llseek = no_llseek,
 };
 
 static const struct file_operations spufs_signal2_nosched_fops = {
@@ -1312,6 +1323,7 @@
 	.release = spufs_signal2_release,
 	.write = spufs_signal2_write,
 	.mmap = spufs_signal2_mmap,
+	.llseek = no_llseek,
 };
 
 /*
@@ -1451,6 +1463,7 @@
 	.open	 = spufs_mss_open,
 	.release = spufs_mss_release,
 	.mmap	 = spufs_mss_mmap,
+	.llseek  = no_llseek,
 };
 
 static int
@@ -1508,6 +1521,7 @@
 	.open	 = spufs_psmap_open,
 	.release = spufs_psmap_release,
 	.mmap	 = spufs_psmap_mmap,
+	.llseek  = no_llseek,
 };
 
 
@@ -1871,6 +1885,7 @@
 	.fsync	 = spufs_mfc_fsync,
 	.fasync	 = spufs_mfc_fasync,
 	.mmap	 = spufs_mfc_mmap,
+	.llseek  = no_llseek,
 };
 
 static int spufs_npc_set(void *data, u64 val)
@@ -2246,6 +2261,7 @@
 static const struct file_operations spufs_dma_info_fops = {
 	.open = spufs_info_open,
 	.read = spufs_dma_info_read,
+	.llseek = no_llseek,
 };
 
 static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx,
@@ -2299,6 +2315,7 @@
 static const struct file_operations spufs_proxydma_info_fops = {
 	.open = spufs_info_open,
 	.read = spufs_proxydma_info_read,
+	.llseek = no_llseek,
 };
 
 static int spufs_show_tid(struct seq_file *s, void *private)
@@ -2585,6 +2602,7 @@
 	.read		= spufs_switch_log_read,
 	.poll		= spufs_switch_log_poll,
 	.release	= spufs_switch_log_release,
+	.llseek		= no_llseek,
 };
 
 /**
diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c
index ba3588f..d3ceff0 100644
--- a/arch/powerpc/platforms/chrp/nvram.c
+++ b/arch/powerpc/platforms/chrp/nvram.c
@@ -74,8 +74,10 @@
 		return;
 
 	nbytes_p = of_get_property(nvram, "#bytes", &proplen);
-	if (nbytes_p == NULL || proplen != sizeof(unsigned int))
+	if (nbytes_p == NULL || proplen != sizeof(unsigned int)) {
+		of_node_put(nvram);
 		return;
+	}
 
 	nvram_size = *nbytes_p;
 
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 5cdcc7c..649473a 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -65,7 +65,7 @@
 
 void __init wii_memory_fixups(void)
 {
-	struct memblock_property *p = memblock.memory.region;
+	struct memblock_region *p = memblock.memory.regions;
 
 	/*
 	 * This is part of a workaround to allow the use of two
diff --git a/arch/powerpc/platforms/iseries/Makefile b/arch/powerpc/platforms/iseries/Makefile
index ce01492..a7602b1 100644
--- a/arch/powerpc/platforms/iseries/Makefile
+++ b/arch/powerpc/platforms/iseries/Makefile
@@ -1,4 +1,4 @@
-EXTRA_CFLAGS	+= -mno-minimal-toc
+ccflags-y	:= -mno-minimal-toc
 
 obj-y += exception.o
 obj-y += hvlog.o hvlpconfig.o lpardata.o setup.o dt.o mf.o lpevents.o \
diff --git a/arch/powerpc/platforms/iseries/dt.c b/arch/powerpc/platforms/iseries/dt.c
index 7f45a51..fdb7384 100644
--- a/arch/powerpc/platforms/iseries/dt.c
+++ b/arch/powerpc/platforms/iseries/dt.c
@@ -243,7 +243,7 @@
 	pft_size[1] = __ilog2(HvCallHpt_getHptPages() * HW_PAGE_SIZE);
 
 	for (i = 0; i < NR_CPUS; i++) {
-		if (lppaca[i].dyn_proc_status >= 2)
+		if (lppaca_of(i).dyn_proc_status >= 2)
 			continue;
 
 		snprintf(p, 32 - (p - buf), "@%d", i);
@@ -251,7 +251,7 @@
 
 		dt_prop_str(dt, "device_type", device_type_cpu);
 
-		index = lppaca[i].dyn_hv_phys_proc_index;
+		index = lppaca_of(i).dyn_hv_phys_proc_index;
 		d = &xIoHriProcessorVpd[index];
 
 		dt_prop_u32(dt, "i-cache-size", d->xInstCacheSize * 1024);
diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c
index 33e5fc7..42d0a88 100644
--- a/arch/powerpc/platforms/iseries/mf.c
+++ b/arch/powerpc/platforms/iseries/mf.c
@@ -1249,6 +1249,7 @@
 
 static const struct file_operations proc_vmlinux_operations = {
 	.write		= proc_mf_change_vmlinux,
+	.llseek		= default_llseek,
 };
 
 static int __init mf_proc_init(void)
diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c
index 6590850..6c60299 100644
--- a/arch/powerpc/platforms/iseries/smp.c
+++ b/arch/powerpc/platforms/iseries/smp.c
@@ -91,7 +91,7 @@
 	BUG_ON((nr < 0) || (nr >= NR_CPUS));
 
 	/* Verify that our partition has a processor nr */
-	if (lppaca[nr].dyn_proc_status >= 2)
+	if (lppaca_of(nr).dyn_proc_status >= 2)
 		return;
 
 	/* The processor is currently spinning, waiting
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 3fff8d9..fe34c3d 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -358,6 +358,7 @@
 	model = (const unsigned char *)of_get_property(np, "model", NULL);
 	if (!model) {
 		printk(KERN_ERR "%s: Unabel to get model info\n", __func__);
+		of_node_put(np);
 		return -ENODEV;
 	}
 
diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c
index cec6359..b0c3777 100644
--- a/arch/powerpc/platforms/powermac/pfunc_core.c
+++ b/arch/powerpc/platforms/powermac/pfunc_core.c
@@ -837,8 +837,10 @@
 		return NULL;
  find_it:
 	dev = pmf_find_device(actor);
-	if (dev == NULL)
-		return NULL;
+	if (dev == NULL) {
+		result = NULL;
+		goto out;
+	}
 
 	list_for_each_entry(func, &dev->functions, link) {
 		if (name && strcmp(name, func->name))
@@ -850,8 +852,9 @@
 		result = func;
 		break;
 	}
-	of_node_put(actor);
 	pmf_put_device(dev);
+out:
+	of_node_put(actor);
 	return result;
 }
 
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 046ace9..59eb8bd 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -1,14 +1,9 @@
-ifeq ($(CONFIG_PPC64),y)
-EXTRA_CFLAGS		+= -mno-minimal-toc
-endif
-
-ifeq ($(CONFIG_PPC_PSERIES_DEBUG),y)
-EXTRA_CFLAGS		+= -DDEBUG
-endif
+ccflags-$(CONFIG_PPC64)			:= -mno-minimal-toc
+ccflags-$(CONFIG_PPC_PSERIES_DEBUG)	+= -DDEBUG
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   setup.o iommu.o event_sources.o ras.o \
-			   firmware.o power.o dlpar.o
+			   firmware.o power.o dlpar.o mobility.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_XICS)	+= xics.o
 obj-$(CONFIG_SCANLOG)	+= scanlog.o
@@ -23,7 +18,7 @@
 obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
 obj-$(CONFIG_HCALL_STATS)	+= hvCall_inst.o
-obj-$(CONFIG_PHYP_DUMP)	+= phyp_dump.o
+obj-$(CONFIG_PHYP_DUMP)		+= phyp_dump.o
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_DTL)		+= dtl.o
 
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 72d8054..b74a923 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -33,7 +33,7 @@
 	u32	prop_offset;
 };
 
-static void dlpar_free_cc_property(struct property *prop)
+void dlpar_free_cc_property(struct property *prop)
 {
 	kfree(prop->name);
 	kfree(prop->value);
@@ -55,13 +55,12 @@
 
 	prop->length = ccwa->prop_length;
 	value = (char *)ccwa + ccwa->prop_offset;
-	prop->value = kzalloc(prop->length, GFP_KERNEL);
+	prop->value = kmemdup(value, prop->length, GFP_KERNEL);
 	if (!prop->value) {
 		dlpar_free_cc_property(prop);
 		return NULL;
 	}
 
-	memcpy(prop->value, value, prop->length);
 	return prop;
 }
 
@@ -102,7 +101,7 @@
 	kfree(dn);
 }
 
-static void dlpar_free_cc_nodes(struct device_node *dn)
+void dlpar_free_cc_nodes(struct device_node *dn)
 {
 	if (dn->child)
 		dlpar_free_cc_nodes(dn->child);
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index a00addb5..c371bc0 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -23,37 +23,22 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/debugfs.h>
+#include <linux/spinlock.h>
 #include <asm/smp.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/firmware.h>
+#include <asm/lppaca.h>
 
 #include "plpar_wrappers.h"
 
-/*
- * Layout of entries in the hypervisor's DTL buffer. Although we don't
- * actually access the internals of an entry (we only need to know the size),
- * we might as well define it here for reference.
- */
-struct dtl_entry {
-	u8	dispatch_reason;
-	u8	preempt_reason;
-	u16	processor_id;
-	u32	enqueue_to_dispatch_time;
-	u32	ready_to_enqueue_time;
-	u32	waiting_to_ready_time;
-	u64	timebase;
-	u64	fault_addr;
-	u64	srr0;
-	u64	srr1;
-};
-
 struct dtl {
 	struct dtl_entry	*buf;
 	struct dentry		*file;
 	int			cpu;
 	int			buf_entries;
 	u64			last_idx;
+	spinlock_t		lock;
 };
 static DEFINE_PER_CPU(struct dtl, cpu_dtl);
 
@@ -72,26 +57,98 @@
 static int dtl_buf_entries = (16 * 85);
 
 
-static int dtl_enable(struct dtl *dtl)
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+struct dtl_ring {
+	u64	write_index;
+	struct dtl_entry *write_ptr;
+	struct dtl_entry *buf;
+	struct dtl_entry *buf_end;
+	u8	saved_dtl_mask;
+};
+
+static DEFINE_PER_CPU(struct dtl_ring, dtl_rings);
+
+static atomic_t dtl_count;
+
+/*
+ * The cpu accounting code controls the DTL ring buffer, and we get
+ * given entries as they are processed.
+ */
+static void consume_dtle(struct dtl_entry *dtle, u64 index)
+{
+	struct dtl_ring *dtlr = &__get_cpu_var(dtl_rings);
+	struct dtl_entry *wp = dtlr->write_ptr;
+	struct lppaca *vpa = local_paca->lppaca_ptr;
+
+	if (!wp)
+		return;
+
+	*wp = *dtle;
+	barrier();
+
+	/* check for hypervisor ring buffer overflow, ignore this entry if so */
+	if (index + N_DISPATCH_LOG < vpa->dtl_idx)
+		return;
+
+	++wp;
+	if (wp == dtlr->buf_end)
+		wp = dtlr->buf;
+	dtlr->write_ptr = wp;
+
+	/* incrementing write_index makes the new entry visible */
+	smp_wmb();
+	++dtlr->write_index;
+}
+
+static int dtl_start(struct dtl *dtl)
+{
+	struct dtl_ring *dtlr = &per_cpu(dtl_rings, dtl->cpu);
+
+	dtlr->buf = dtl->buf;
+	dtlr->buf_end = dtl->buf + dtl->buf_entries;
+	dtlr->write_index = 0;
+
+	/* setting write_ptr enables logging into our buffer */
+	smp_wmb();
+	dtlr->write_ptr = dtl->buf;
+
+	/* enable event logging */
+	dtlr->saved_dtl_mask = lppaca_of(dtl->cpu).dtl_enable_mask;
+	lppaca_of(dtl->cpu).dtl_enable_mask |= dtl_event_mask;
+
+	dtl_consumer = consume_dtle;
+	atomic_inc(&dtl_count);
+	return 0;
+}
+
+static void dtl_stop(struct dtl *dtl)
+{
+	struct dtl_ring *dtlr = &per_cpu(dtl_rings, dtl->cpu);
+
+	dtlr->write_ptr = NULL;
+	smp_wmb();
+
+	dtlr->buf = NULL;
+
+	/* restore dtl_enable_mask */
+	lppaca_of(dtl->cpu).dtl_enable_mask = dtlr->saved_dtl_mask;
+
+	if (atomic_dec_and_test(&dtl_count))
+		dtl_consumer = NULL;
+}
+
+static u64 dtl_current_index(struct dtl *dtl)
+{
+	return per_cpu(dtl_rings, dtl->cpu).write_index;
+}
+
+#else /* CONFIG_VIRT_CPU_ACCOUNTING */
+
+static int dtl_start(struct dtl *dtl)
 {
 	unsigned long addr;
 	int ret, hwcpu;
 
-	/* only allow one reader */
-	if (dtl->buf)
-		return -EBUSY;
-
-	/* we need to store the original allocation size for use during read */
-	dtl->buf_entries = dtl_buf_entries;
-
-	dtl->buf = kmalloc_node(dtl->buf_entries * sizeof(struct dtl_entry),
-			GFP_KERNEL, cpu_to_node(dtl->cpu));
-	if (!dtl->buf) {
-		printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
-				__func__, dtl->cpu);
-		return -ENOMEM;
-	}
-
 	/* Register our dtl buffer with the hypervisor. The HV expects the
 	 * buffer size to be passed in the second word of the buffer */
 	((u32 *)dtl->buf)[1] = dtl->buf_entries * sizeof(struct dtl_entry);
@@ -102,34 +159,82 @@
 	if (ret) {
 		printk(KERN_WARNING "%s: DTL registration for cpu %d (hw %d) "
 		       "failed with %d\n", __func__, dtl->cpu, hwcpu, ret);
-		kfree(dtl->buf);
 		return -EIO;
 	}
 
 	/* set our initial buffer indices */
-	dtl->last_idx = lppaca[dtl->cpu].dtl_idx = 0;
+	lppaca_of(dtl->cpu).dtl_idx = 0;
 
 	/* ensure that our updates to the lppaca fields have occurred before
 	 * we actually enable the logging */
 	smp_wmb();
 
 	/* enable event logging */
-	lppaca[dtl->cpu].dtl_enable_mask = dtl_event_mask;
+	lppaca_of(dtl->cpu).dtl_enable_mask = dtl_event_mask;
 
 	return 0;
 }
 
-static void dtl_disable(struct dtl *dtl)
+static void dtl_stop(struct dtl *dtl)
 {
 	int hwcpu = get_hard_smp_processor_id(dtl->cpu);
 
-	lppaca[dtl->cpu].dtl_enable_mask = 0x0;
+	lppaca_of(dtl->cpu).dtl_enable_mask = 0x0;
 
 	unregister_dtl(hwcpu, __pa(dtl->buf));
+}
 
+static u64 dtl_current_index(struct dtl *dtl)
+{
+	return lppaca_of(dtl->cpu).dtl_idx;
+}
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+
+static int dtl_enable(struct dtl *dtl)
+{
+	long int n_entries;
+	long int rc;
+	struct dtl_entry *buf = NULL;
+
+	/* only allow one reader */
+	if (dtl->buf)
+		return -EBUSY;
+
+	n_entries = dtl_buf_entries;
+	buf = kmalloc_node(n_entries * sizeof(struct dtl_entry),
+			GFP_KERNEL, cpu_to_node(dtl->cpu));
+	if (!buf) {
+		printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
+				__func__, dtl->cpu);
+		return -ENOMEM;
+	}
+
+	spin_lock(&dtl->lock);
+	rc = -EBUSY;
+	if (!dtl->buf) {
+		/* store the original allocation size for use during read */
+		dtl->buf_entries = n_entries;
+		dtl->buf = buf;
+		dtl->last_idx = 0;
+		rc = dtl_start(dtl);
+		if (rc)
+			dtl->buf = NULL;
+	}
+	spin_unlock(&dtl->lock);
+
+	if (rc)
+		kfree(buf);
+	return rc;
+}
+
+static void dtl_disable(struct dtl *dtl)
+{
+	spin_lock(&dtl->lock);
+	dtl_stop(dtl);
 	kfree(dtl->buf);
 	dtl->buf = NULL;
 	dtl->buf_entries = 0;
+	spin_unlock(&dtl->lock);
 }
 
 /* file interface */
@@ -157,8 +262,9 @@
 static ssize_t dtl_file_read(struct file *filp, char __user *buf, size_t len,
 		loff_t *pos)
 {
-	int rc, cur_idx, last_idx, n_read, n_req, read_size;
+	long int rc, n_read, n_req, read_size;
 	struct dtl *dtl;
+	u64 cur_idx, last_idx, i;
 
 	if ((len % sizeof(struct dtl_entry)) != 0)
 		return -EINVAL;
@@ -171,41 +277,48 @@
 	/* actual number of entries read */
 	n_read = 0;
 
-	cur_idx = lppaca[dtl->cpu].dtl_idx;
+	spin_lock(&dtl->lock);
+
+	cur_idx = dtl_current_index(dtl);
 	last_idx = dtl->last_idx;
 
-	if (cur_idx - last_idx > dtl->buf_entries) {
-		pr_debug("%s: hv buffer overflow for cpu %d, samples lost\n",
-				__func__, dtl->cpu);
-	}
+	if (last_idx + dtl->buf_entries <= cur_idx)
+		last_idx = cur_idx - dtl->buf_entries + 1;
 
-	cur_idx  %= dtl->buf_entries;
-	last_idx %= dtl->buf_entries;
+	if (last_idx + n_req > cur_idx)
+		n_req = cur_idx - last_idx;
+
+	if (n_req > 0)
+		dtl->last_idx = last_idx + n_req;
+
+	spin_unlock(&dtl->lock);
+
+	if (n_req <= 0)
+		return 0;
+
+	i = last_idx % dtl->buf_entries;
 
 	/* read the tail of the buffer if we've wrapped */
-	if (last_idx > cur_idx) {
-		read_size = min(n_req, dtl->buf_entries - last_idx);
+	if (i + n_req > dtl->buf_entries) {
+		read_size = dtl->buf_entries - i;
 
-		rc = copy_to_user(buf, &dtl->buf[last_idx],
+		rc = copy_to_user(buf, &dtl->buf[i],
 				read_size * sizeof(struct dtl_entry));
 		if (rc)
 			return -EFAULT;
 
-		last_idx = 0;
+		i = 0;
 		n_req -= read_size;
 		n_read += read_size;
 		buf += read_size * sizeof(struct dtl_entry);
 	}
 
 	/* .. and now the head */
-	read_size = min(n_req, cur_idx - last_idx);
-	rc = copy_to_user(buf, &dtl->buf[last_idx],
-			read_size * sizeof(struct dtl_entry));
+	rc = copy_to_user(buf, &dtl->buf[i], n_req * sizeof(struct dtl_entry));
 	if (rc)
 		return -EFAULT;
 
-	n_read += read_size;
-	dtl->last_idx += n_read;
+	n_read += n_req;
 
 	return n_read * sizeof(struct dtl_entry);
 }
@@ -263,6 +376,7 @@
 	/* set up the per-cpu log structures */
 	for_each_possible_cpu(i) {
 		struct dtl *dtl = &per_cpu(cpu_dtl, i);
+		spin_lock_init(&dtl->lock);
 		dtl->cpu = i;
 
 		rc = dtl_setup_file(dtl);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index cf79b46..f129040 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -248,11 +248,13 @@
 	int hwcpu = get_hard_smp_processor_id(cpu);
 	unsigned long addr;
 	long ret;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
 
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
-		lppaca[cpu].vmxregs_in_use = 1;
+		lppaca_of(cpu).vmxregs_in_use = 1;
 
-	addr = __pa(&lppaca[cpu]);
+	addr = __pa(&lppaca_of(cpu));
 	ret = register_vpa(hwcpu, addr);
 
 	if (ret) {
@@ -274,6 +276,25 @@
 			       "registration for cpu %d (hw %d) of area %lx "
 			       "returns %ld\n", cpu, hwcpu, addr, ret);
 	}
+
+	/*
+	 * Register dispatch trace log, if one has been allocated.
+	 */
+	pp = &paca[cpu];
+	dtl = pp->dispatch_log;
+	if (dtl) {
+		pp->dtl_ridx = 0;
+		pp->dtl_curr = dtl;
+		lppaca_of(cpu).dtl_idx = 0;
+
+		/* hypervisor reads buffer length from this field */
+		dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+		ret = register_dtl(hwcpu, __pa(dtl));
+		if (ret)
+			pr_warn("DTL registration failed for cpu %d (%ld)\n",
+				cpu, ret);
+		lppaca_of(cpu).dtl_enable_mask = 2;
+	}
 }
 
 static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
new file mode 100644
index 0000000..3e7f651
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -0,0 +1,362 @@
+/*
+ * Support for Partition Mobility/Migration
+ *
+ * Copyright (C) 2010 Nathan Fontenot
+ * Copyright (C) 2010 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/smp.h>
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+
+#include <asm/rtas.h>
+#include "pseries.h"
+
+static struct kobject *mobility_kobj;
+
+struct update_props_workarea {
+	u32 phandle;
+	u32 state;
+	u64 reserved;
+	u32 nprops;
+};
+
+#define NODE_ACTION_MASK	0xff000000
+#define NODE_COUNT_MASK		0x00ffffff
+
+#define DELETE_DT_NODE	0x01000000
+#define UPDATE_DT_NODE	0x02000000
+#define ADD_DT_NODE	0x03000000
+
+static int mobility_rtas_call(int token, char *buf)
+{
+	int rc;
+
+	spin_lock(&rtas_data_buf_lock);
+
+	memcpy(rtas_data_buf, buf, RTAS_DATA_BUF_SIZE);
+	rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, 1);
+	memcpy(buf, rtas_data_buf, RTAS_DATA_BUF_SIZE);
+
+	spin_unlock(&rtas_data_buf_lock);
+	return rc;
+}
+
+static int delete_dt_node(u32 phandle)
+{
+	struct device_node *dn;
+
+	dn = of_find_node_by_phandle(phandle);
+	if (!dn)
+		return -ENOENT;
+
+	dlpar_detach_node(dn);
+	return 0;
+}
+
+static int update_dt_property(struct device_node *dn, struct property **prop,
+			      const char *name, u32 vd, char *value)
+{
+	struct property *new_prop = *prop;
+	struct property *old_prop;
+	int more = 0;
+
+	/* A negative 'vd' value indicates that only part of the new property
+	 * value is contained in the buffer and we need to call
+	 * ibm,update-properties again to get the rest of the value.
+	 *
+	 * A negative value is also the two's compliment of the actual value.
+	 */
+	if (vd & 0x80000000) {
+		vd = ~vd + 1;
+		more = 1;
+	}
+
+	if (new_prop) {
+		/* partial property fixup */
+		char *new_data = kzalloc(new_prop->length + vd, GFP_KERNEL);
+		if (!new_data)
+			return -ENOMEM;
+
+		memcpy(new_data, new_prop->value, new_prop->length);
+		memcpy(new_data + new_prop->length, value, vd);
+
+		kfree(new_prop->value);
+		new_prop->value = new_data;
+		new_prop->length += vd;
+	} else {
+		new_prop = kzalloc(sizeof(*new_prop), GFP_KERNEL);
+		if (!new_prop)
+			return -ENOMEM;
+
+		new_prop->name = kstrdup(name, GFP_KERNEL);
+		if (!new_prop->name) {
+			kfree(new_prop);
+			return -ENOMEM;
+		}
+
+		new_prop->length = vd;
+		new_prop->value = kzalloc(new_prop->length, GFP_KERNEL);
+		if (!new_prop->value) {
+			kfree(new_prop->name);
+			kfree(new_prop);
+			return -ENOMEM;
+		}
+
+		memcpy(new_prop->value, value, vd);
+		*prop = new_prop;
+	}
+
+	if (!more) {
+		old_prop = of_find_property(dn, new_prop->name, NULL);
+		if (old_prop)
+			prom_update_property(dn, new_prop, old_prop);
+		else
+			prom_add_property(dn, new_prop);
+
+		new_prop = NULL;
+	}
+
+	return 0;
+}
+
+static int update_dt_node(u32 phandle)
+{
+	struct update_props_workarea *upwa;
+	struct device_node *dn;
+	struct property *prop = NULL;
+	int i, rc;
+	char *prop_data;
+	char *rtas_buf;
+	int update_properties_token;
+
+	update_properties_token = rtas_token("ibm,update-properties");
+	if (update_properties_token == RTAS_UNKNOWN_SERVICE)
+		return -EINVAL;
+
+	rtas_buf = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
+	if (!rtas_buf)
+		return -ENOMEM;
+
+	dn = of_find_node_by_phandle(phandle);
+	if (!dn) {
+		kfree(rtas_buf);
+		return -ENOENT;
+	}
+
+	upwa = (struct update_props_workarea *)&rtas_buf[0];
+	upwa->phandle = phandle;
+
+	do {
+		rc = mobility_rtas_call(update_properties_token, rtas_buf);
+		if (rc < 0)
+			break;
+
+		prop_data = rtas_buf + sizeof(*upwa);
+
+		for (i = 0; i < upwa->nprops; i++) {
+			char *prop_name;
+			u32 vd;
+
+			prop_name = prop_data + 1;
+			prop_data += strlen(prop_name) + 1;
+			vd = *prop_data++;
+
+			switch (vd) {
+			case 0x00000000:
+				/* name only property, nothing to do */
+				break;
+
+			case 0x80000000:
+				prop = of_find_property(dn, prop_name, NULL);
+				prom_remove_property(dn, prop);
+				prop = NULL;
+				break;
+
+			default:
+				rc = update_dt_property(dn, &prop, prop_name,
+							vd, prop_data);
+				if (rc) {
+					printk(KERN_ERR "Could not update %s"
+					       " property\n", prop_name);
+				}
+
+				prop_data += vd;
+			}
+		}
+	} while (rc == 1);
+
+	of_node_put(dn);
+	kfree(rtas_buf);
+	return 0;
+}
+
+static int add_dt_node(u32 parent_phandle, u32 drc_index)
+{
+	struct device_node *dn;
+	struct device_node *parent_dn;
+	int rc;
+
+	dn = dlpar_configure_connector(drc_index);
+	if (!dn)
+		return -ENOENT;
+
+	parent_dn = of_find_node_by_phandle(parent_phandle);
+	if (!parent_dn) {
+		dlpar_free_cc_nodes(dn);
+		return -ENOENT;
+	}
+
+	dn->parent = parent_dn;
+	rc = dlpar_attach_node(dn);
+	if (rc)
+		dlpar_free_cc_nodes(dn);
+
+	of_node_put(parent_dn);
+	return rc;
+}
+
+static int pseries_devicetree_update(void)
+{
+	char *rtas_buf;
+	u32 *data;
+	int update_nodes_token;
+	int rc;
+
+	update_nodes_token = rtas_token("ibm,update-nodes");
+	if (update_nodes_token == RTAS_UNKNOWN_SERVICE)
+		return -EINVAL;
+
+	rtas_buf = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
+	if (!rtas_buf)
+		return -ENOMEM;
+
+	do {
+		rc = mobility_rtas_call(update_nodes_token, rtas_buf);
+		if (rc && rc != 1)
+			break;
+
+		data = (u32 *)rtas_buf + 4;
+		while (*data & NODE_ACTION_MASK) {
+			int i;
+			u32 action = *data & NODE_ACTION_MASK;
+			int node_count = *data & NODE_COUNT_MASK;
+
+			data++;
+
+			for (i = 0; i < node_count; i++) {
+				u32 phandle = *data++;
+				u32 drc_index;
+
+				switch (action) {
+				case DELETE_DT_NODE:
+					delete_dt_node(phandle);
+					break;
+				case UPDATE_DT_NODE:
+					update_dt_node(phandle);
+					break;
+				case ADD_DT_NODE:
+					drc_index = *data++;
+					add_dt_node(phandle, drc_index);
+					break;
+				}
+			}
+		}
+	} while (rc == 1);
+
+	kfree(rtas_buf);
+	return rc;
+}
+
+void post_mobility_fixup(void)
+{
+	int rc;
+	int activate_fw_token;
+
+	rc = pseries_devicetree_update();
+	if (rc) {
+		printk(KERN_ERR "Initial post-mobility device tree update "
+		       "failed: %d\n", rc);
+		return;
+	}
+
+	activate_fw_token = rtas_token("ibm,activate-firmware");
+	if (activate_fw_token == RTAS_UNKNOWN_SERVICE) {
+		printk(KERN_ERR "Could not make post-mobility "
+		       "activate-fw call.\n");
+		return;
+	}
+
+	rc = rtas_call(activate_fw_token, 0, 1, NULL);
+	if (!rc) {
+		rc = pseries_devicetree_update();
+		if (rc)
+			printk(KERN_ERR "Secondary post-mobility device tree "
+			       "update failed: %d\n", rc);
+	} else {
+		printk(KERN_ERR "Post-mobility activate-fw failed: %d\n", rc);
+		return;
+	}
+
+	return;
+}
+
+static ssize_t migrate_store(struct class *class, struct class_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct rtas_args args;
+	u64 streamid;
+	int rc;
+
+	rc = strict_strtoull(buf, 0, &streamid);
+	if (rc)
+		return rc;
+
+	memset(&args, 0, sizeof(args));
+	args.token = rtas_token("ibm,suspend-me");
+	args.nargs = 2;
+	args.nret = 1;
+
+	args.args[0] = streamid >> 32 ;
+	args.args[1] = streamid & 0xffffffff;
+	args.rets = &args.args[args.nargs];
+
+	do {
+		args.rets[0] = 0;
+		rc = rtas_ibm_suspend_me(&args);
+		if (!rc && args.rets[0] == RTAS_NOT_SUSPENDABLE)
+			ssleep(1);
+	} while (!rc && args.rets[0] == RTAS_NOT_SUSPENDABLE);
+
+	if (rc)
+		return rc;
+	else if (args.rets[0])
+		return args.rets[0];
+
+	post_mobility_fixup();
+	return count;
+}
+
+static CLASS_ATTR(migration, S_IWUSR, NULL, migrate_store);
+
+static int __init mobility_sysfs_init(void)
+{
+	int rc;
+
+	mobility_kobj = kobject_create_and_add("mobility", kernel_kobj);
+	if (!mobility_kobj)
+		return -ENOMEM;
+
+	rc = sysfs_create_file(mobility_kobj, &class_attr_migration.attr);
+
+	return rc;
+}
+device_initcall(mobility_sysfs_init);
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 40c93ca..e9f6d28 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -17,6 +17,8 @@
 extern void request_event_sources_irqs(struct device_node *np,
 				       irq_handler_t handler, const char *name);
 
+#include <linux/of.h>
+
 extern void __init fw_feature_init(const char *hypertas, unsigned long len);
 
 struct pt_regs;
@@ -47,4 +49,11 @@
 
 extern void find_udbg_vterm(void);
 
+/* Dynamic logical Partitioning/Mobility */
+extern void dlpar_free_cc_nodes(struct device_node *);
+extern void dlpar_free_cc_property(struct property *);
+extern struct device_node *dlpar_configure_connector(u32);
+extern int dlpar_attach_node(struct device_node *);
+extern int dlpar_detach_node(struct device_node *);
+
 #endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 57ddbb4..1de2cbb 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -539,7 +539,8 @@
 }
 
 static const struct file_operations ofdt_fops = {
-	.write = ofdt_write
+	.write = ofdt_write,
+	.llseek = noop_llseek,
 };
 
 /* create /proc/powerpc/ofdt write-only by root */
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index 80e9e76..5544572 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -170,6 +170,7 @@
 	.write		= scanlog_write,
 	.open		= scanlog_open,
 	.release	= scanlog_release,
+	.llseek		= noop_llseek,
 };
 
 static int __init scanlog_init(void)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index a6d19e3..d345bfd 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -273,6 +273,58 @@
 	.notifier_call = pci_dn_reconfig_notifier,
 };
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+/*
+ * Allocate space for the dispatch trace log for all possible cpus
+ * and register the buffers with the hypervisor.  This is used for
+ * computing time stolen by the hypervisor.
+ */
+static int alloc_dispatch_logs(void)
+{
+	int cpu, ret;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return 0;
+
+	for_each_possible_cpu(cpu) {
+		pp = &paca[cpu];
+		dtl = kmalloc_node(DISPATCH_LOG_BYTES, GFP_KERNEL,
+				   cpu_to_node(cpu));
+		if (!dtl) {
+			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
+				cpu);
+			pr_warn("Stolen time statistics will be unreliable\n");
+			break;
+		}
+
+		pp->dtl_ridx = 0;
+		pp->dispatch_log = dtl;
+		pp->dispatch_log_end = dtl + N_DISPATCH_LOG;
+		pp->dtl_curr = dtl;
+	}
+
+	/* Register the DTL for the current (boot) cpu */
+	dtl = get_paca()->dispatch_log;
+	get_paca()->dtl_ridx = 0;
+	get_paca()->dtl_curr = dtl;
+	get_paca()->lppaca_ptr->dtl_idx = 0;
+
+	/* hypervisor reads buffer length from this field */
+	dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
+	if (ret)
+		pr_warn("DTL registration failed for boot cpu %d (%d)\n",
+			smp_processor_id(), ret);
+	get_paca()->lppaca_ptr->dtl_enable_mask = 2;
+
+	return 0;
+}
+
+early_initcall(alloc_dispatch_logs);
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+
 static void __init pSeries_setup_arch(void)
 {
 	/* Discover PIC type and setup ppc_md accordingly */
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 93834b0..7b96e5a 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -178,7 +178,7 @@
 	if (!distribute_irqs)
 		return default_server;
 
-	if (!cpumask_equal(cpumask, cpu_all_mask)) {
+	if (!cpumask_subset(cpu_possible_mask, cpumask)) {
 		int server = cpumask_first_and(cpu_online_mask, cpumask);
 
 		if (server < nr_cpu_ids)
@@ -243,7 +243,7 @@
 	 * at that level, so we do it here by hand.
 	 */
 	if (irq_to_desc(virq)->msi_desc)
-		unmask_msi_irq(virq);
+		unmask_msi_irq(irq_get_irq_data(virq));
 
 	/* unmask it */
 	xics_unmask_irq(virq);
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 5642924..0bef9da 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -1,8 +1,6 @@
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
-ifeq ($(CONFIG_PPC64),y)
-EXTRA_CFLAGS			+= -mno-minimal-toc
-endif
+ccflags-$(CONFIG_PPC64)		:= -mno-minimal-toc
 
 mpic-msi-obj-$(CONFIG_PCI_MSI)	+= mpic_msi.o mpic_u3msi.o mpic_pasemi_msi.o
 obj-$(CONFIG_MPIC)		+= mpic.o $(mpic-msi-obj-y)
@@ -20,6 +18,7 @@
 obj-$(CONFIG_FSL_LBC)		+= fsl_lbc.o
 obj-$(CONFIG_FSL_GTM)		+= fsl_gtm.o
 obj-$(CONFIG_MPC8xxx_GPIO)	+= mpc8xxx_gpio.o
+obj-$(CONFIG_FSL_85XX_CACHE_SRAM)	+= fsl_85xx_l2ctlr.o fsl_85xx_cache_sram.o
 obj-$(CONFIG_SIMPLE_GPIO)	+= simple_gpio.o
 obj-$(CONFIG_RAPIDIO)		+= fsl_rio.o
 obj-$(CONFIG_TSI108_BRIDGE)	+= tsi108_pci.o tsi108_dev.o
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 559db2b..17cf15e 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -70,6 +70,8 @@
 static int dart_dirty;
 static int dart_is_u4;
 
+#define DART_U4_BYPASS_BASE	0x8000000000ull
+
 #define DBG(...)
 
 static inline void dart_tlb_invalidate_all(void)
@@ -292,12 +294,20 @@
 	set_bit(iommu_table_dart.it_size - 1, iommu_table_dart.it_map);
 }
 
-static void pci_dma_dev_setup_dart(struct pci_dev *dev)
+static void dma_dev_setup_dart(struct device *dev)
 {
 	/* We only have one iommu table on the mac for now, which makes
 	 * things simple. Setup all PCI devices to point to this table
 	 */
-	set_iommu_table_base(&dev->dev, &iommu_table_dart);
+	if (get_dma_ops(dev) == &dma_direct_ops)
+		set_dma_offset(dev, DART_U4_BYPASS_BASE);
+	else
+		set_iommu_table_base(dev, &iommu_table_dart);
+}
+
+static void pci_dma_dev_setup_dart(struct pci_dev *dev)
+{
+	dma_dev_setup_dart(&dev->dev);
 }
 
 static void pci_dma_bus_setup_dart(struct pci_bus *bus)
@@ -315,6 +325,45 @@
 		PCI_DN(dn)->iommu_table = &iommu_table_dart;
 }
 
+static bool dart_device_on_pcie(struct device *dev)
+{
+	struct device_node *np = of_node_get(dev->of_node);
+
+	while(np) {
+		if (of_device_is_compatible(np, "U4-pcie") ||
+		    of_device_is_compatible(np, "u4-pcie")) {
+			of_node_put(np);
+			return true;
+		}
+		np = of_get_next_parent(np);
+	}
+	return false;
+}
+
+static int dart_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
+		return -EIO;
+
+	/* U4 supports a DART bypass, we use it for 64-bit capable
+	 * devices to improve performances. However, that only works
+	 * for devices connected to U4 own PCIe interface, not bridged
+	 * through hypertransport. We need the device to support at
+	 * least 40 bits of addresses.
+	 */
+	if (dart_device_on_pcie(dev) && dma_mask >= DMA_BIT_MASK(40)) {
+		dev_info(dev, "Using 64-bit DMA iommu bypass\n");
+		set_dma_ops(dev, &dma_direct_ops);
+	} else {
+		dev_info(dev, "Using 32-bit DMA via iommu\n");
+		set_dma_ops(dev, &dma_iommu_ops);
+	}
+	dma_dev_setup_dart(dev);
+
+	*dev->dma_mask = dma_mask;
+	return 0;
+}
+
 void __init iommu_init_early_dart(void)
 {
 	struct device_node *dn;
@@ -328,20 +377,25 @@
 		dart_is_u4 = 1;
 	}
 
+	/* Initialize the DART HW */
+	if (dart_init(dn) != 0)
+		goto bail;
+
 	/* Setup low level TCE operations for the core IOMMU code */
 	ppc_md.tce_build = dart_build;
 	ppc_md.tce_free  = dart_free;
 	ppc_md.tce_flush = dart_flush;
 
-	/* Initialize the DART HW */
-	if (dart_init(dn) == 0) {
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_dart;
-		ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_dart;
+	/* Setup bypass if supported */
+	if (dart_is_u4)
+		ppc_md.dma_set_mask = dart_dma_set_mask;
 
-		/* Setup pci_dma ops */
-		set_pci_dma_ops(&dma_iommu_ops);
-		return;
-	}
+	ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_dart;
+	ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_dart;
+
+	/* Setup pci_dma ops */
+	set_pci_dma_ops(&dma_iommu_ops);
+	return;
 
  bail:
 	/* If init failed, use direct iommu and null setup functions */
diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h b/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h
new file mode 100644
index 0000000..60c9c0b
--- /dev/null
+++ b/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright 2009-2010 Freescale Semiconductor, Inc
+ *
+ * QorIQ based Cache Controller Memory Mapped Registers
+ *
+ * Author: Vivek Mahajan <vivek.mahajan@freescale.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef __FSL_85XX_CACHE_CTLR_H__
+#define __FSL_85XX_CACHE_CTLR_H__
+
+#define L2CR_L2FI		0x40000000	/* L2 flash invalidate */
+#define L2CR_L2IO		0x00200000	/* L2 instruction only */
+#define L2CR_SRAM_ZERO		0x00000000	/* L2SRAM zero size */
+#define L2CR_SRAM_FULL		0x00010000	/* L2SRAM full size */
+#define L2CR_SRAM_HALF		0x00020000	/* L2SRAM half size */
+#define L2CR_SRAM_TWO_HALFS	0x00030000	/* L2SRAM two half sizes */
+#define L2CR_SRAM_QUART		0x00040000	/* L2SRAM one quarter size */
+#define L2CR_SRAM_TWO_QUARTS	0x00050000	/* L2SRAM two quarter size */
+#define L2CR_SRAM_EIGHTH	0x00060000	/* L2SRAM one eighth size */
+#define L2CR_SRAM_TWO_EIGHTH	0x00070000	/* L2SRAM two eighth size */
+
+#define L2SRAM_OPTIMAL_SZ_SHIFT	0x00000003	/* Optimum size for L2SRAM */
+
+#define L2SRAM_BAR_MSK_LO18	0xFFFFC000	/* Lower 18 bits */
+#define L2SRAM_BARE_MSK_HI4	0x0000000F	/* Upper 4 bits */
+
+enum cache_sram_lock_ways {
+	LOCK_WAYS_ZERO,
+	LOCK_WAYS_EIGHTH,
+	LOCK_WAYS_TWO_EIGHTH,
+	LOCK_WAYS_HALF = 4,
+	LOCK_WAYS_FULL = 8,
+};
+
+struct mpc85xx_l2ctlr {
+	u32	ctl;		/* 0x000 - L2 control */
+	u8	res1[0xC];
+	u32	ewar0;		/* 0x010 - External write address 0 */
+	u32	ewarea0;	/* 0x014 - External write address extended 0 */
+	u32	ewcr0;		/* 0x018 - External write ctrl */
+	u8	res2[4];
+	u32	ewar1;		/* 0x020 - External write address 1 */
+	u32	ewarea1;	/* 0x024 - External write address extended 1 */
+	u32	ewcr1;		/* 0x028 - External write ctrl 1 */
+	u8	res3[4];
+	u32	ewar2;		/* 0x030 - External write address 2 */
+	u32	ewarea2;	/* 0x034 - External write address extended 2 */
+	u32	ewcr2;		/* 0x038 - External write ctrl 2 */
+	u8	res4[4];
+	u32	ewar3;		/* 0x040 - External write address 3 */
+	u32	ewarea3;	/* 0x044 - External write address extended 3 */
+	u32	ewcr3;		/* 0x048 - External write ctrl 3 */
+	u8	res5[0xB4];
+	u32	srbar0;		/* 0x100 - SRAM base address 0 */
+	u32	srbarea0;	/* 0x104 - SRAM base addr reg ext address 0 */
+	u32	srbar1;		/* 0x108 - SRAM base address 1 */
+	u32	srbarea1;	/* 0x10C - SRAM base addr reg ext address 1 */
+	u8	res6[0xCF0];
+	u32	errinjhi;	/* 0xE00 - Error injection mask high */
+	u32	errinjlo;	/* 0xE04 - Error injection mask low */
+	u32	errinjctl;	/* 0xE08 - Error injection tag/ecc control */
+	u8	res7[0x14];
+	u32	captdatahi;	/* 0xE20 - Error data high capture */
+	u32	captdatalo;	/* 0xE24 - Error data low capture */
+	u32	captecc;	/* 0xE28 - Error syndrome */
+	u8	res8[0x14];
+	u32	errdet;		/* 0xE40 - Error detect */
+	u32	errdis;		/* 0xE44 - Error disable */
+	u32	errinten;	/* 0xE48 - Error interrupt enable */
+	u32	errattr;	/* 0xE4c - Error attribute capture */
+	u32	erradrrl;	/* 0xE50 - Error address capture low */
+	u32	erradrrh;	/* 0xE54 - Error address capture high */
+	u32	errctl;		/* 0xE58 - Error control */
+	u8	res9[0x1A4];
+};
+
+struct sram_parameters {
+	unsigned int sram_size;
+	uint64_t sram_offset;
+};
+
+extern int instantiate_cache_sram(struct platform_device *dev,
+		struct sram_parameters sram_params);
+extern void remove_cache_sram(struct platform_device *dev);
+
+#endif /* __FSL_85XX_CACHE_CTLR_H__ */
diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
new file mode 100644
index 0000000..54fb192
--- /dev/null
+++ b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
@@ -0,0 +1,159 @@
+/*
+ * Copyright 2009-2010 Freescale Semiconductor, Inc.
+ *
+ * Simple memory allocator abstraction for QorIQ (P1/P2) based Cache-SRAM
+ *
+ * Author: Vivek Mahajan <vivek.mahajan@freescale.com>
+ *
+ * This file is derived from the original work done
+ * by Sylvain Munaut for the Bestcomm SRAM allocator.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/of_platform.h>
+#include <asm/pgtable.h>
+#include <asm/fsl_85xx_cache_sram.h>
+
+#include "fsl_85xx_cache_ctlr.h"
+
+struct mpc85xx_cache_sram *cache_sram;
+
+void *mpc85xx_cache_sram_alloc(unsigned int size,
+				phys_addr_t *phys, unsigned int align)
+{
+	unsigned long offset;
+	unsigned long flags;
+
+	if (unlikely(cache_sram == NULL))
+		return NULL;
+
+	if (!size || (size > cache_sram->size) || (align > cache_sram->size)) {
+		pr_err("%s(): size(=%x) or align(=%x) zero or too big\n",
+			__func__, size, align);
+		return NULL;
+	}
+
+	if ((align & (align - 1)) || align <= 1) {
+		pr_err("%s(): align(=%x) must be power of two and >1\n",
+			__func__, align);
+		return NULL;
+	}
+
+	spin_lock_irqsave(&cache_sram->lock, flags);
+	offset = rh_alloc_align(cache_sram->rh, size, align, NULL);
+	spin_unlock_irqrestore(&cache_sram->lock, flags);
+
+	if (IS_ERR_VALUE(offset))
+		return NULL;
+
+	*phys = cache_sram->base_phys + offset;
+
+	return (unsigned char *)cache_sram->base_virt + offset;
+}
+EXPORT_SYMBOL(mpc85xx_cache_sram_alloc);
+
+void mpc85xx_cache_sram_free(void *ptr)
+{
+	unsigned long flags;
+	BUG_ON(!ptr);
+
+	spin_lock_irqsave(&cache_sram->lock, flags);
+	rh_free(cache_sram->rh, ptr - cache_sram->base_virt);
+	spin_unlock_irqrestore(&cache_sram->lock, flags);
+}
+EXPORT_SYMBOL(mpc85xx_cache_sram_free);
+
+int __init instantiate_cache_sram(struct platform_device *dev,
+		struct sram_parameters sram_params)
+{
+	int ret = 0;
+
+	if (cache_sram) {
+		dev_err(&dev->dev, "Already initialized cache-sram\n");
+		return -EBUSY;
+	}
+
+	cache_sram = kzalloc(sizeof(struct mpc85xx_cache_sram), GFP_KERNEL);
+	if (!cache_sram) {
+		dev_err(&dev->dev, "Out of memory for cache_sram structure\n");
+		return -ENOMEM;
+	}
+
+	cache_sram->base_phys = sram_params.sram_offset;
+	cache_sram->size = sram_params.sram_size;
+
+	if (!request_mem_region(cache_sram->base_phys, cache_sram->size,
+						"fsl_85xx_cache_sram")) {
+		dev_err(&dev->dev, "%s: request memory failed\n",
+				dev->dev.of_node->full_name);
+		ret = -ENXIO;
+		goto out_free;
+	}
+
+	cache_sram->base_virt = ioremap_flags(cache_sram->base_phys,
+				cache_sram->size, _PAGE_COHERENT | PAGE_KERNEL);
+	if (!cache_sram->base_virt) {
+		dev_err(&dev->dev, "%s: ioremap_flags failed\n",
+				dev->dev.of_node->full_name);
+		ret = -ENOMEM;
+		goto out_release;
+	}
+
+	cache_sram->rh = rh_create(sizeof(unsigned int));
+	if (IS_ERR(cache_sram->rh)) {
+		dev_err(&dev->dev, "%s: Unable to create remote heap\n",
+				dev->dev.of_node->full_name);
+		ret = PTR_ERR(cache_sram->rh);
+		goto out_unmap;
+	}
+
+	rh_attach_region(cache_sram->rh, 0, cache_sram->size);
+	spin_lock_init(&cache_sram->lock);
+
+	dev_info(&dev->dev, "[base:0x%llx, size:0x%x] configured and loaded\n",
+		(unsigned long long)cache_sram->base_phys, cache_sram->size);
+
+	return 0;
+
+out_unmap:
+	iounmap(cache_sram->base_virt);
+
+out_release:
+	release_mem_region(cache_sram->base_phys, cache_sram->size);
+
+out_free:
+	kfree(cache_sram);
+	return ret;
+}
+
+void remove_cache_sram(struct platform_device *dev)
+{
+	BUG_ON(!cache_sram);
+
+	rh_detach_region(cache_sram->rh, 0, cache_sram->size);
+	rh_destroy(cache_sram->rh);
+
+	iounmap(cache_sram->base_virt);
+	release_mem_region(cache_sram->base_phys, cache_sram->size);
+
+	kfree(cache_sram);
+	cache_sram = NULL;
+
+	dev_info(&dev->dev, "MPC85xx Cache-SRAM driver unloaded\n");
+}
diff --git a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
new file mode 100644
index 0000000..cc8d655
--- /dev/null
+++ b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
@@ -0,0 +1,231 @@
+/*
+ * Copyright 2009-2010 Freescale Semiconductor, Inc.
+ *
+ * QorIQ (P1/P2) L2 controller init for Cache-SRAM instantiation
+ *
+ * Author: Vivek Mahajan <vivek.mahajan@freescale.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/of_platform.h>
+#include <asm/io.h>
+
+#include "fsl_85xx_cache_ctlr.h"
+
+static char *sram_size;
+static char *sram_offset;
+struct mpc85xx_l2ctlr __iomem *l2ctlr;
+
+static long get_cache_sram_size(void)
+{
+	unsigned long val;
+
+	if (!sram_size || (strict_strtoul(sram_size, 0, &val) < 0))
+		return -EINVAL;
+
+	return val;
+}
+
+static long get_cache_sram_offset(void)
+{
+	unsigned long val;
+
+	if (!sram_offset || (strict_strtoul(sram_offset, 0, &val) < 0))
+		return -EINVAL;
+
+	return val;
+}
+
+static int __init get_size_from_cmdline(char *str)
+{
+	if (!str)
+		return 0;
+
+	sram_size = str;
+	return 1;
+}
+
+static int __init get_offset_from_cmdline(char *str)
+{
+	if (!str)
+		return 0;
+
+	sram_offset = str;
+	return 1;
+}
+
+__setup("cache-sram-size=", get_size_from_cmdline);
+__setup("cache-sram-offset=", get_offset_from_cmdline);
+
+static int __devinit mpc85xx_l2ctlr_of_probe(struct platform_device *dev,
+					  const struct of_device_id *match)
+{
+	long rval;
+	unsigned int rem;
+	unsigned char ways;
+	const unsigned int *prop;
+	unsigned int l2cache_size;
+	struct sram_parameters sram_params;
+
+	if (!dev->dev.of_node) {
+		dev_err(&dev->dev, "Device's OF-node is NULL\n");
+		return -EINVAL;
+	}
+
+	prop = of_get_property(dev->dev.of_node, "cache-size", NULL);
+	if (!prop) {
+		dev_err(&dev->dev, "Missing L2 cache-size\n");
+		return -EINVAL;
+	}
+	l2cache_size = *prop;
+
+	sram_params.sram_size  = get_cache_sram_size();
+	if (sram_params.sram_size <= 0) {
+		dev_err(&dev->dev,
+			"Entire L2 as cache, Aborting Cache-SRAM stuff\n");
+		return -EINVAL;
+	}
+
+	sram_params.sram_offset  = get_cache_sram_offset();
+	if (sram_params.sram_offset <= 0) {
+		dev_err(&dev->dev,
+			"Entire L2 as cache, provide a valid sram offset\n");
+		return -EINVAL;
+	}
+
+
+	rem = l2cache_size % sram_params.sram_size;
+	ways = LOCK_WAYS_FULL * sram_params.sram_size / l2cache_size;
+	if (rem || (ways & (ways - 1))) {
+		dev_err(&dev->dev, "Illegal cache-sram-size in command line\n");
+		return -EINVAL;
+	}
+
+	l2ctlr = of_iomap(dev->dev.of_node, 0);
+	if (!l2ctlr) {
+		dev_err(&dev->dev, "Can't map L2 controller\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Write bits[0-17] to srbar0
+	 */
+	out_be32(&l2ctlr->srbar0,
+		sram_params.sram_offset & L2SRAM_BAR_MSK_LO18);
+
+	/*
+	 * Write bits[18-21] to srbare0
+	 */
+#ifdef CONFIG_PHYS_64BIT
+	out_be32(&l2ctlr->srbarea0,
+		(sram_params.sram_offset >> 32) & L2SRAM_BARE_MSK_HI4);
+#endif
+
+	clrsetbits_be32(&l2ctlr->ctl, L2CR_L2E, L2CR_L2FI);
+
+	switch (ways) {
+	case LOCK_WAYS_EIGHTH:
+		setbits32(&l2ctlr->ctl,
+			L2CR_L2E | L2CR_L2FI | L2CR_SRAM_EIGHTH);
+		break;
+
+	case LOCK_WAYS_TWO_EIGHTH:
+		setbits32(&l2ctlr->ctl,
+			L2CR_L2E | L2CR_L2FI | L2CR_SRAM_QUART);
+		break;
+
+	case LOCK_WAYS_HALF:
+		setbits32(&l2ctlr->ctl,
+			L2CR_L2E | L2CR_L2FI | L2CR_SRAM_HALF);
+		break;
+
+	case LOCK_WAYS_FULL:
+	default:
+		setbits32(&l2ctlr->ctl,
+			L2CR_L2E | L2CR_L2FI | L2CR_SRAM_FULL);
+		break;
+	}
+	eieio();
+
+	rval = instantiate_cache_sram(dev, sram_params);
+	if (rval < 0) {
+		dev_err(&dev->dev, "Can't instantiate Cache-SRAM\n");
+		iounmap(l2ctlr);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __devexit mpc85xx_l2ctlr_of_remove(struct platform_device *dev)
+{
+	BUG_ON(!l2ctlr);
+
+	iounmap(l2ctlr);
+	remove_cache_sram(dev);
+	dev_info(&dev->dev, "MPC85xx L2 controller unloaded\n");
+
+	return 0;
+}
+
+static struct of_device_id mpc85xx_l2ctlr_of_match[] = {
+	{
+		.compatible = "fsl,p2020-l2-cache-controller",
+	},
+	{
+		.compatible = "fsl,p2010-l2-cache-controller",
+	},
+	{
+		.compatible = "fsl,p1020-l2-cache-controller",
+	},
+	{
+		.compatible = "fsl,p1011-l2-cache-controller",
+	},
+	{
+		.compatible = "fsl,p1013-l2-cache-controller",
+	},
+	{
+		.compatible = "fsl,p1022-l2-cache-controller",
+	},
+	{},
+};
+
+static struct of_platform_driver mpc85xx_l2ctlr_of_platform_driver = {
+	.driver	= {
+		.name		= "fsl-l2ctlr",
+		.owner		= THIS_MODULE,
+		.of_match_table	= mpc85xx_l2ctlr_of_match,
+	},
+	.probe		= mpc85xx_l2ctlr_of_probe,
+	.remove		= __devexit_p(mpc85xx_l2ctlr_of_remove),
+};
+
+static __init int mpc85xx_l2ctlr_of_init(void)
+{
+	return of_register_platform_driver(&mpc85xx_l2ctlr_of_platform_driver);
+}
+
+static void __exit mpc85xx_l2ctlr_of_exit(void)
+{
+	of_unregister_platform_driver(&mpc85xx_l2ctlr_of_platform_driver);
+}
+
+subsys_initcall(mpc85xx_l2ctlr_of_init);
+module_exit(mpc85xx_l2ctlr_of_exit);
+
+MODULE_DESCRIPTION("Freescale MPC85xx L2 controller init");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 87991d3..108d76f 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -24,6 +24,7 @@
 #include <asm/ppc-pci.h>
 #include <asm/mpic.h>
 #include "fsl_msi.h"
+#include "fsl_pci.h"
 
 LIST_HEAD(msi_head);
 
@@ -51,8 +52,8 @@
 }
 
 static struct irq_chip fsl_msi_chip = {
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
 	.ack		= fsl_msi_end_irq,
 	.name		= "FSL-MSI",
 };
@@ -125,13 +126,11 @@
 {
 	struct fsl_msi *msi_data = fsl_msi_data;
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	u32 base = 0;
+	u64 base = fsl_pci_immrbar_base(hose);
 
-	pci_bus_read_config_dword(hose->bus,
-		PCI_DEVFN(0, 0), PCI_BASE_ADDRESS_0, &base);
+	msg->address_lo = msi_data->msi_addr_lo + lower_32_bits(base);
+	msg->address_hi = msi_data->msi_addr_hi + upper_32_bits(base);
 
-	msg->address_lo = msi_data->msi_addr_lo + base;
-	msg->address_hi = msi_data->msi_addr_hi;
 	msg->data = hwirq;
 
 	pr_debug("%s: allocated srs: %d, ibs: %d\n",
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 4ae9332..818f7c6 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1,7 +1,7 @@
 /*
  * MPC83xx/85xx/86xx PCI/PCIE support routing.
  *
- * Copyright 2007-2009 Freescale Semiconductor, Inc.
+ * Copyright 2007-2010 Freescale Semiconductor, Inc.
  * Copyright 2008-2009 MontaVista Software, Inc.
  *
  * Initial author: Xianghua Xiao <x.xiao@freescale.com>
@@ -34,7 +34,7 @@
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
 
-static int fsl_pcie_bus_fixup;
+static int fsl_pcie_bus_fixup, is_mpc83xx_pci;
 
 static void __init quirk_fsl_pcie_header(struct pci_dev *dev)
 {
@@ -407,10 +407,18 @@
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2010, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2020E, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2020, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2040E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2040, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P3041E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P3041, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P4040E, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P4040, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P4080E, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P4080, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P5010E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P5010, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P5020E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P5020, quirk_fsl_pcie_header);
 #endif /* CONFIG_FSL_SOC_BOOKE || CONFIG_PPC_86xx */
 
 #if defined(CONFIG_PPC_83xx) || defined(CONFIG_PPC_MPC512x)
@@ -430,6 +438,13 @@
 	u32 dev_base;
 };
 
+struct pex_inbound_window {
+	u32 ar;
+	u32 tar;
+	u32 barl;
+	u32 barh;
+};
+
 /*
  * With the convention of u-boot, the PCIE outbound window 0 serves
  * as configuration transactions outbound.
@@ -437,6 +452,8 @@
 #define PEX_OUTWIN0_BAR		0xCA4
 #define PEX_OUTWIN0_TAL		0xCA8
 #define PEX_OUTWIN0_TAH		0xCAC
+#define PEX_RC_INWIN_BASE	0xE60
+#define PEX_RCIWARn_EN		0x1
 
 static int mpc83xx_pcie_exclude_device(struct pci_bus *bus, unsigned int devfn)
 {
@@ -604,6 +621,8 @@
 	const int *bus_range;
 	int primary;
 
+	is_mpc83xx_pci = 1;
+
 	if (!of_device_is_available(dev)) {
 		pr_warning("%s: disabled by the firmware.\n",
 			   dev->full_name);
@@ -683,3 +702,40 @@
 	return ret;
 }
 #endif /* CONFIG_PPC_83xx */
+
+u64 fsl_pci_immrbar_base(struct pci_controller *hose)
+{
+#ifdef CONFIG_PPC_83xx
+	if (is_mpc83xx_pci) {
+		struct mpc83xx_pcie_priv *pcie = hose->dn->data;
+		struct pex_inbound_window *in;
+		int i;
+
+		/* Walk the Root Complex Inbound windows to match IMMR base */
+		in = pcie->cfg_type0 + PEX_RC_INWIN_BASE;
+		for (i = 0; i < 4; i++) {
+			/* not enabled, skip */
+			if (!in_le32(&in[i].ar) & PEX_RCIWARn_EN)
+				 continue;
+
+			if (get_immrbase() == in_le32(&in[i].tar))
+				return (u64)in_le32(&in[i].barh) << 32 |
+					    in_le32(&in[i].barl);
+		}
+
+		printk(KERN_WARNING "could not find PCI BAR matching IMMR\n");
+	}
+#endif
+
+#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
+	if (!is_mpc83xx_pci) {
+		u32 base;
+
+		pci_bus_read_config_dword(hose->bus,
+			PCI_DEVFN(0, 0), PCI_BASE_ADDRESS_0, &base);
+		return base;
+	}
+#endif
+
+	return 0;
+}
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index a9d8bbe..8ad72a1 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -88,6 +88,7 @@
 extern int fsl_add_bridge(struct device_node *dev, int is_primary);
 extern void fsl_pcibios_fixup_bus(struct pci_bus *bus);
 extern int mpc83xx_add_bridge(struct device_node *dev);
+u64 fsl_pci_immrbar_base(struct pci_controller *hose);
 
 #endif /* __POWERPC_FSL_PCI_H */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 3017532..4127636 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -117,44 +117,59 @@
 };
 
 struct rio_msg_regs {
-	u32 omr;
-	u32 osr;
+	u32 omr;	/* 0xD_3000 - Outbound message 0 mode register */
+	u32 osr;	/* 0xD_3004 - Outbound message 0 status register */
 	u32 pad1;
-	u32 odqdpar;
+	u32 odqdpar;	/* 0xD_300C - Outbound message 0 descriptor queue
+			   dequeue pointer address register */
 	u32 pad2;
-	u32 osar;
-	u32 odpr;
-	u32 odatr;
-	u32 odcr;
+	u32 osar;	/* 0xD_3014 - Outbound message 0 source address
+			   register */
+	u32 odpr;	/* 0xD_3018 - Outbound message 0 destination port
+			   register */
+	u32 odatr;	/* 0xD_301C - Outbound message 0 destination attributes
+			   Register*/
+	u32 odcr;	/* 0xD_3020 - Outbound message 0 double-word count
+			   register */
 	u32 pad3;
-	u32 odqepar;
+	u32 odqepar;	/* 0xD_3028 - Outbound message 0 descriptor queue
+			   enqueue pointer address register */
 	u32 pad4[13];
-	u32 imr;
-	u32 isr;
+	u32 imr;	/* 0xD_3060 - Inbound message 0 mode register */
+	u32 isr;	/* 0xD_3064 - Inbound message 0 status register */
 	u32 pad5;
-	u32 ifqdpar;
+	u32 ifqdpar;	/* 0xD_306C - Inbound message 0 frame queue dequeue
+			   pointer address register*/
 	u32 pad6;
-	u32 ifqepar;
+	u32 ifqepar;	/* 0xD_3074 - Inbound message 0 frame queue enqueue
+			   pointer address register */
 	u32 pad7[226];
-	u32 odmr;
-	u32 odsr;
+	u32 odmr;	/* 0xD_3400 - Outbound doorbell mode register */
+	u32 odsr;	/* 0xD_3404 - Outbound doorbell status register */
 	u32 res0[4];
-	u32 oddpr;
-	u32 oddatr;
+	u32 oddpr;	/* 0xD_3418 - Outbound doorbell destination port
+			   register */
+	u32 oddatr;	/* 0xD_341c - Outbound doorbell destination attributes
+			   register */
 	u32 res1[3];
-	u32 odretcr;
+	u32 odretcr;	/* 0xD_342C - Outbound doorbell retry error threshold
+			   configuration register */
 	u32 res2[12];
-	u32 dmr;
-	u32 dsr;
+	u32 dmr;	/* 0xD_3460 - Inbound doorbell mode register */
+	u32 dsr;	/* 0xD_3464 - Inbound doorbell status register */
 	u32 pad8;
-	u32 dqdpar;
+	u32 dqdpar;	/* 0xD_346C - Inbound doorbell queue dequeue Pointer
+			   address register */
 	u32 pad9;
-	u32 dqepar;
+	u32 dqepar;	/* 0xD_3474 - Inbound doorbell Queue enqueue pointer
+			   address register */
 	u32 pad10[26];
-	u32 pwmr;
-	u32 pwsr;
-	u32 epwqbar;
-	u32 pwqbar;
+	u32 pwmr;	/* 0xD_34E0 - Inbound port-write mode register */
+	u32 pwsr;	/* 0xD_34E4 - Inbound port-write status register */
+	u32 epwqbar;	/* 0xD_34E8 - Extended Port-Write Queue Base Address
+			   register */
+	u32 pwqbar;	/* 0xD_34EC - Inbound port-write queue base address
+			   register */
 };
 
 struct rio_tx_desc {
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index b91f7ac..6c67d9e 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -378,17 +378,23 @@
 static int __init setup_rstcr(void)
 {
 	struct device_node *np;
-	np = of_find_node_by_name(NULL, "global-utilities");
-	if ((np && of_get_property(np, "fsl,has-rstcr", NULL))) {
-		rstcr = of_iomap(np, 0) + 0xb0;
-		if (!rstcr)
-			printk (KERN_EMERG "Error: reset control register "
-					"not mapped!\n");
-	} else if (ppc_md.restart == fsl_rstcr_restart)
+
+	for_each_node_by_name(np, "global-utilities") {
+		if ((of_get_property(np, "fsl,has-rstcr", NULL))) {
+			rstcr = of_iomap(np, 0) + 0xb0;
+			if (!rstcr)
+				printk (KERN_ERR "Error: reset control "
+						"register not mapped!\n");
+			break;
+		}
+	}
+
+	if (!rstcr && ppc_md.restart == fsl_rstcr_restart)
 		printk(KERN_ERR "No RSTCR register, warm reboot won't work\n");
 
 	if (np)
 		of_node_put(np);
+
 	return 0;
 }
 
diff --git a/arch/powerpc/sysdev/mpc8xxx_gpio.c b/arch/powerpc/sysdev/mpc8xxx_gpio.c
index 2b69084..c0ea05e 100644
--- a/arch/powerpc/sysdev/mpc8xxx_gpio.c
+++ b/arch/powerpc/sysdev/mpc8xxx_gpio.c
@@ -330,6 +330,9 @@
 	for_each_compatible_node(np, NULL, "fsl,mpc8610-gpio")
 		mpc8xxx_add_controller(np);
 
+	for_each_compatible_node(np, NULL, "fsl,qoriq-gpio")
+		mpc8xxx_add_controller(np);
+
 	return 0;
 }
 arch_initcall(mpc8xxx_add_gpiochips);
diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/sysdev/mpic_pasemi_msi.c
index 3b6a9a4..320ad5a 100644
--- a/arch/powerpc/sysdev/mpic_pasemi_msi.c
+++ b/arch/powerpc/sysdev/mpic_pasemi_msi.c
@@ -39,24 +39,24 @@
 static struct mpic *msi_mpic;
 
 
-static void mpic_pasemi_msi_mask_irq(unsigned int irq)
+static void mpic_pasemi_msi_mask_irq(struct irq_data *data)
 {
-	pr_debug("mpic_pasemi_msi_mask_irq %d\n", irq);
-	mask_msi_irq(irq);
-	mpic_mask_irq(irq);
+	pr_debug("mpic_pasemi_msi_mask_irq %d\n", data->irq);
+	mask_msi_irq(data);
+	mpic_mask_irq(data->irq);
 }
 
-static void mpic_pasemi_msi_unmask_irq(unsigned int irq)
+static void mpic_pasemi_msi_unmask_irq(struct irq_data *data)
 {
-	pr_debug("mpic_pasemi_msi_unmask_irq %d\n", irq);
-	mpic_unmask_irq(irq);
-	unmask_msi_irq(irq);
+	pr_debug("mpic_pasemi_msi_unmask_irq %d\n", data->irq);
+	mpic_unmask_irq(data->irq);
+	unmask_msi_irq(data);
 }
 
 static struct irq_chip mpic_pasemi_msi_chip = {
-	.shutdown	= mpic_pasemi_msi_mask_irq,
-	.mask		= mpic_pasemi_msi_mask_irq,
-	.unmask		= mpic_pasemi_msi_unmask_irq,
+	.irq_shutdown	= mpic_pasemi_msi_mask_irq,
+	.irq_mask	= mpic_pasemi_msi_mask_irq,
+	.irq_unmask	= mpic_pasemi_msi_unmask_irq,
 	.eoi		= mpic_end_irq,
 	.set_type	= mpic_set_irq_type,
 	.set_affinity	= mpic_set_affinity,
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index bcbfe79..a2b028b 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -23,22 +23,22 @@
 /* A bit ugly, can we get this from the pci_dev somehow? */
 static struct mpic *msi_mpic;
 
-static void mpic_u3msi_mask_irq(unsigned int irq)
+static void mpic_u3msi_mask_irq(struct irq_data *data)
 {
-	mask_msi_irq(irq);
-	mpic_mask_irq(irq);
+	mask_msi_irq(data);
+	mpic_mask_irq(data->irq);
 }
 
-static void mpic_u3msi_unmask_irq(unsigned int irq)
+static void mpic_u3msi_unmask_irq(struct irq_data *data)
 {
-	mpic_unmask_irq(irq);
-	unmask_msi_irq(irq);
+	mpic_unmask_irq(data->irq);
+	unmask_msi_irq(data);
 }
 
 static struct irq_chip mpic_u3msi_chip = {
-	.shutdown	= mpic_u3msi_mask_irq,
-	.mask		= mpic_u3msi_mask_irq,
-	.unmask		= mpic_u3msi_unmask_irq,
+	.irq_shutdown	= mpic_u3msi_mask_irq,
+	.irq_mask	= mpic_u3msi_mask_irq,
+	.irq_unmask	= mpic_u3msi_unmask_irq,
 	.eoi		= mpic_end_irq,
 	.set_type	= mpic_set_irq_type,
 	.set_affinity	= mpic_set_affinity,
diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c
index 24a0bb9..4260f36 100644
--- a/arch/powerpc/sysdev/pmi.c
+++ b/arch/powerpc/sysdev/pmi.c
@@ -114,7 +114,7 @@
 
 	spin_lock(&data->handler_spinlock);
 	list_for_each_entry(handler, &data->handler, node) {
-		pr_debug(KERN_INFO "pmi: notifying handler %p\n", handler);
+		pr_debug("pmi: notifying handler %p\n", handler);
 		if (handler->type == data->msg.type)
 			handler->handle_pmi_message(data->msg);
 	}
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index faa81b6..c168c54e 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -4,9 +4,7 @@
 
 GCOV_PROFILE := n
 
-ifdef CONFIG_PPC64
-EXTRA_CFLAGS += -mno-minimal-toc
-endif
+ccflags-$(CONFIG_PPC64) := -mno-minimal-toc
 
 obj-y			+= xmon.o start.o nonstdio.o
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f0777a4..75976a1 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -95,6 +95,7 @@
 	select HAVE_KVM if 64BIT
 	select HAVE_ARCH_TRACEHOOK
 	select INIT_ALL_POSSIBLE
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
@@ -198,6 +199,13 @@
 	  can be controlled through /sys/devices/system/cpu/cpu#.
 	  Say N if you want to disable CPU hotplug.
 
+config SCHED_BOOK
+	bool "Book scheduler support"
+	depends on SMP
+	help
+	  Book scheduler support improves the CPU scheduler's decision making
+	  when dealing with machines that have several books.
+
 config MATHEMU
 	bool "IEEE FPU emulation"
 	depends on MARCH_G5
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index aa819da..975e3ab 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -152,6 +152,7 @@
 	.open		= &prng_open,
 	.release	= NULL,
 	.read		= &prng_read,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice prng_dev = {
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 1211bb1..020e51c 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -618,6 +618,7 @@
 	.open		= dbfs_d204_open,
 	.read		= dbfs_d204_read,
 	.release	= dbfs_d204_release,
+	.llseek		= no_llseek,
 };
 
 static int hypfs_dbfs_init(void)
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index ee5ab1a..26cf177 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -275,6 +275,7 @@
 	.open		= dbfs_d2fc_open,
 	.read		= dbfs_d2fc_read,
 	.release	= dbfs_d2fc_release,
+	.llseek		= no_llseek,
 };
 
 int hypfs_vm_init(void)
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 98a4a4c..74d9867 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -449,6 +449,7 @@
 	.write		= do_sync_write,
 	.aio_read	= hypfs_aio_read,
 	.aio_write	= hypfs_aio_write,
+	.llseek		= no_llseek,
 };
 
 static struct file_system_type hypfs_type = {
diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h
index 498bc38..881d945 100644
--- a/arch/s390/include/asm/hardirq.h
+++ b/arch/s390/include/asm/hardirq.h
@@ -12,10 +12,6 @@
 #ifndef __ASM_HARDIRQ_H
 #define __ASM_HARDIRQ_H
 
-#include <linux/threads.h>
-#include <linux/sched.h>
-#include <linux/cache.h>
-#include <linux/interrupt.h>
 #include <asm/lowcore.h>
 
 #define local_softirq_pending() (S390_lowcore.softirq_pending)
diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h
index 15b3ac2..865d6d8 100644
--- a/arch/s390/include/asm/irqflags.h
+++ b/arch/s390/include/asm/irqflags.h
@@ -8,8 +8,8 @@
 
 #include <linux/types.h>
 
-/* store then or system mask. */
-#define __raw_local_irq_stosm(__or)					\
+/* store then OR system mask. */
+#define __arch_local_irq_stosm(__or)					\
 ({									\
 	unsigned long __mask;						\
 	asm volatile(							\
@@ -18,8 +18,8 @@
 	__mask;								\
 })
 
-/* store then and system mask. */
-#define __raw_local_irq_stnsm(__and)					\
+/* store then AND system mask. */
+#define __arch_local_irq_stnsm(__and)					\
 ({									\
 	unsigned long __mask;						\
 	asm volatile(							\
@@ -29,39 +29,44 @@
 })
 
 /* set system mask. */
-#define __raw_local_irq_ssm(__mask)					\
-({									\
-	asm volatile("ssm   %0" : : "Q" (__mask) : "memory");		\
-})
-
-/* interrupt control.. */
-static inline unsigned long raw_local_irq_enable(void)
+static inline void __arch_local_irq_ssm(unsigned long flags)
 {
-	return __raw_local_irq_stosm(0x03);
+	asm volatile("ssm   %0" : : "Q" (flags) : "memory");
 }
 
-static inline unsigned long raw_local_irq_disable(void)
+static inline unsigned long arch_local_save_flags(void)
 {
-	return __raw_local_irq_stnsm(0xfc);
+	return __arch_local_irq_stosm(0x00);
 }
 
-#define raw_local_save_flags(x)						\
-do {									\
-	typecheck(unsigned long, x);					\
-	(x) = __raw_local_irq_stosm(0x00);				\
-} while (0)
-
-static inline void raw_local_irq_restore(unsigned long flags)
+static inline unsigned long arch_local_irq_save(void)
 {
-	__raw_local_irq_ssm(flags);
+	return __arch_local_irq_stnsm(0xfc);
 }
 
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+static inline void arch_local_irq_disable(void)
+{
+	arch_local_irq_save();
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	__arch_local_irq_stosm(0x03);
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	__arch_local_irq_ssm(flags);
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !(flags & (3UL << (BITS_PER_LONG - 8)));
 }
 
-/* For spinlocks etc */
-#define raw_local_irq_save(x)	((x) = raw_local_irq_disable())
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
 
 #endif /* __ASM_IRQFLAGS_H */
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 3840cbe..a75f168 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -4,7 +4,6 @@
  * Copyright 2009 Martin Schwidefsky, IBM Corporation.
  */
 
-static inline void set_perf_event_pending(void) {}
-static inline void clear_perf_event_pending(void) {}
+/* Empty, just to avoid compiling error */
 
 #define PERF_EVENT_INDEX_OFFSET 0
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
index cef6621..1f2ebc4 100644
--- a/arch/s390/include/asm/system.h
+++ b/arch/s390/include/asm/system.h
@@ -97,7 +97,6 @@
 
 extern void account_vtime(struct task_struct *, struct task_struct *);
 extern void account_tick_vtime(struct task_struct *);
-extern void account_system_vtime(struct task_struct *);
 
 #ifdef CONFIG_PFAULT
 extern void pfault_irq_init(void);
@@ -399,7 +398,7 @@
 static inline void
 __set_psw_mask(unsigned long mask)
 {
-	__load_psw_mask(mask | (__raw_local_irq_stosm(0x00) & ~(-1UL >> 8)));
+	__load_psw_mask(mask | (arch_local_save_flags() & ~(-1UL >> 8)));
 }
 
 #define local_mcck_enable()  __set_psw_mask(psw_kernel_bits)
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 831bd03..051107a 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -3,15 +3,32 @@
 
 #include <linux/cpumask.h>
 
-#define mc_capable()	(1)
-
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
-
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
+static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+	return &cpu_core_map[cpu];
+}
+
 #define topology_core_id(cpu)		(cpu_core_id[cpu])
 #define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
+#define mc_capable()			(1)
+
+#ifdef CONFIG_SCHED_BOOK
+
+extern unsigned char cpu_book_id[NR_CPUS];
+extern cpumask_t cpu_book_map[NR_CPUS];
+
+static inline const struct cpumask *cpu_book_mask(unsigned int cpu)
+{
+	return &cpu_book_map[cpu];
+}
+
+#define topology_book_id(cpu)		(cpu_book_id[cpu])
+#define topology_book_cpumask(cpu)	(&cpu_book_map[cpu])
+
+#endif /* CONFIG_SCHED_BOOK */
 
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
@@ -30,6 +47,8 @@
 };
 #endif
 
+#define SD_BOOK_INIT	SD_CPU_INIT
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 9819226..5ad6bc0 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -174,6 +174,7 @@
 	.write   = debug_input,
 	.open    = debug_open,
 	.release = debug_close,
+	.llseek  = no_llseek,
 };
 
 static struct dentry *debug_debugfs_root_entry;
diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c
index 559af0d..0fbe4e3 100644
--- a/arch/s390/kernel/mem_detect.c
+++ b/arch/s390/kernel/mem_detect.c
@@ -54,11 +54,11 @@
 	 * right thing and we don't get scheduled away with low address
 	 * protection disabled.
 	 */
-	flags = __raw_local_irq_stnsm(0xf8);
+	flags = __arch_local_irq_stnsm(0xf8);
 	__ctl_store(cr0, 0, 0);
 	__ctl_clear_bit(0, 28);
 	find_memory_chunks(chunk);
 	__ctl_load(cr0, 0, 0);
-	__raw_local_irq_ssm(flags);
+	arch_local_irq_restore(flags);
 }
 EXPORT_SYMBOL(detect_memory_layout);
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index bcef007..13559c9 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -57,8 +57,8 @@
 	union tl_entry tle[0];
 };
 
-struct core_info {
-	struct core_info *next;
+struct mask_info {
+	struct mask_info *next;
 	unsigned char id;
 	cpumask_t mask;
 };
@@ -66,7 +66,6 @@
 static int topology_enabled;
 static void topology_work_fn(struct work_struct *work);
 static struct tl_info *tl_info;
-static struct core_info core_info;
 static int machine_has_topology;
 static struct timer_list topology_timer;
 static void set_topology_timer(void);
@@ -74,38 +73,37 @@
 /* topology_lock protects the core linked list */
 static DEFINE_SPINLOCK(topology_lock);
 
+static struct mask_info core_info;
 cpumask_t cpu_core_map[NR_CPUS];
 unsigned char cpu_core_id[NR_CPUS];
 
-static cpumask_t cpu_coregroup_map(unsigned int cpu)
+#ifdef CONFIG_SCHED_BOOK
+static struct mask_info book_info;
+cpumask_t cpu_book_map[NR_CPUS];
+unsigned char cpu_book_id[NR_CPUS];
+#endif
+
+static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
-	struct core_info *core = &core_info;
-	unsigned long flags;
 	cpumask_t mask;
 
 	cpus_clear(mask);
 	if (!topology_enabled || !machine_has_topology)
 		return cpu_possible_map;
-	spin_lock_irqsave(&topology_lock, flags);
-	while (core) {
-		if (cpu_isset(cpu, core->mask)) {
-			mask = core->mask;
+	while (info) {
+		if (cpu_isset(cpu, info->mask)) {
+			mask = info->mask;
 			break;
 		}
-		core = core->next;
+		info = info->next;
 	}
-	spin_unlock_irqrestore(&topology_lock, flags);
 	if (cpus_empty(mask))
 		mask = cpumask_of_cpu(cpu);
 	return mask;
 }
 
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
-{
-	return &cpu_core_map[cpu];
-}
-
-static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
+static void add_cpus_to_mask(struct tl_cpu *tl_cpu, struct mask_info *book,
+			     struct mask_info *core)
 {
 	unsigned int cpu;
 
@@ -117,23 +115,35 @@
 
 		rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin;
 		for_each_present_cpu(lcpu) {
-			if (cpu_logical_map(lcpu) == rcpu) {
-				cpu_set(lcpu, core->mask);
-				cpu_core_id[lcpu] = core->id;
-				smp_cpu_polarization[lcpu] = tl_cpu->pp;
-			}
+			if (cpu_logical_map(lcpu) != rcpu)
+				continue;
+#ifdef CONFIG_SCHED_BOOK
+			cpu_set(lcpu, book->mask);
+			cpu_book_id[lcpu] = book->id;
+#endif
+			cpu_set(lcpu, core->mask);
+			cpu_core_id[lcpu] = core->id;
+			smp_cpu_polarization[lcpu] = tl_cpu->pp;
 		}
 	}
 }
 
-static void clear_cores(void)
+static void clear_masks(void)
 {
-	struct core_info *core = &core_info;
+	struct mask_info *info;
 
-	while (core) {
-		cpus_clear(core->mask);
-		core = core->next;
+	info = &core_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
 	}
+#ifdef CONFIG_SCHED_BOOK
+	info = &book_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
+	}
+#endif
 }
 
 static union tl_entry *next_tle(union tl_entry *tle)
@@ -146,29 +156,36 @@
 
 static void tl_to_cores(struct tl_info *info)
 {
+#ifdef CONFIG_SCHED_BOOK
+	struct mask_info *book = &book_info;
+#else
+	struct mask_info *book = NULL;
+#endif
+	struct mask_info *core = &core_info;
 	union tl_entry *tle, *end;
-	struct core_info *core = &core_info;
+
 
 	spin_lock_irq(&topology_lock);
-	clear_cores();
+	clear_masks();
 	tle = info->tle;
 	end = (union tl_entry *)((unsigned long)info + info->length);
 	while (tle < end) {
 		switch (tle->nl) {
-		case 5:
-		case 4:
-		case 3:
+#ifdef CONFIG_SCHED_BOOK
 		case 2:
+			book = book->next;
+			book->id = tle->container.id;
 			break;
+#endif
 		case 1:
 			core = core->next;
 			core->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_core(&tle->cpu, core);
+			add_cpus_to_mask(&tle->cpu, book, core);
 			break;
 		default:
-			clear_cores();
+			clear_masks();
 			machine_has_topology = 0;
 			goto out;
 		}
@@ -221,10 +238,29 @@
 
 static void update_cpu_core_map(void)
 {
+	unsigned long flags;
 	int cpu;
 
-	for_each_possible_cpu(cpu)
-		cpu_core_map[cpu] = cpu_coregroup_map(cpu);
+	spin_lock_irqsave(&topology_lock, flags);
+	for_each_possible_cpu(cpu) {
+		cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
+#ifdef CONFIG_SCHED_BOOK
+		cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
+#endif
+	}
+	spin_unlock_irqrestore(&topology_lock, flags);
+}
+
+static void store_topology(struct tl_info *info)
+{
+#ifdef CONFIG_SCHED_BOOK
+	int rc;
+
+	rc = stsi(info, 15, 1, 3);
+	if (rc != -ENOSYS)
+		return;
+#endif
+	stsi(info, 15, 1, 2);
 }
 
 int arch_update_cpu_topology(void)
@@ -238,7 +274,7 @@
 		topology_update_polarization_simple();
 		return 0;
 	}
-	stsi(info, 15, 1, 2);
+	store_topology(info);
 	tl_to_cores(info);
 	update_cpu_core_map();
 	for_each_online_cpu(cpu) {
@@ -299,12 +335,24 @@
 }
 __initcall(init_topology_update);
 
+static void alloc_masks(struct tl_info *info, struct mask_info *mask, int offset)
+{
+	int i, nr_masks;
+
+	nr_masks = info->mag[NR_MAG - offset];
+	for (i = 0; i < info->mnest - offset; i++)
+		nr_masks *= info->mag[NR_MAG - offset - 1 - i];
+	nr_masks = max(nr_masks, 1);
+	for (i = 0; i < nr_masks; i++) {
+		mask->next = alloc_bootmem(sizeof(struct mask_info));
+		mask = mask->next;
+	}
+}
+
 void __init s390_init_cpu_topology(void)
 {
 	unsigned long long facility_bits;
 	struct tl_info *info;
-	struct core_info *core;
-	int nr_cores;
 	int i;
 
 	if (stfle(&facility_bits, 1) <= 0)
@@ -315,25 +363,13 @@
 
 	tl_info = alloc_bootmem_pages(PAGE_SIZE);
 	info = tl_info;
-	stsi(info, 15, 1, 2);
-
-	nr_cores = info->mag[NR_MAG - 2];
-	for (i = 0; i < info->mnest - 2; i++)
-		nr_cores *= info->mag[NR_MAG - 3 - i];
-
+	store_topology(info);
 	pr_info("The CPU configuration topology of the machine is:");
 	for (i = 0; i < NR_MAG; i++)
 		printk(" %d", info->mag[i]);
 	printk(" / %d\n", info->mnest);
-
-	core = &core_info;
-	for (i = 0; i < nr_cores; i++) {
-		core->next = alloc_bootmem(sizeof(struct core_info));
-		core = core->next;
-		if (!core)
-			goto error;
-	}
-	return;
-error:
-	machine_has_topology = 0;
+	alloc_masks(info, &core_info, 2);
+#ifdef CONFIG_SCHED_BOOK
+	alloc_masks(info, &book_info, 3);
+#endif
 }
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 30eb6d02..94b8ba2 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -50,7 +50,6 @@
  */
 void __init paging_init(void)
 {
-	static const int ssm_mask = 0x04000000L;
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 	unsigned long pgd_type;
 
@@ -72,7 +71,7 @@
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
 	__ctl_load(S390_lowcore.kernel_asce, 13, 13);
-	__raw_local_irq_ssm(ssm_mask);
+	arch_local_irq_restore(4UL << (BITS_PER_LONG - 8));
 
 	atomic_set(&init_mm.context.attach_count, 1);
 
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index a8c2af8..71a4b0d 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -71,7 +71,7 @@
 
 	if (!count)
 		return 0;
-	flags = __raw_local_irq_stnsm(0xf8UL);
+	flags = __arch_local_irq_stnsm(0xf8UL);
 	asm volatile (
 		"0:	mvcle	%1,%2,0x0\n"
 		"1:	jo	0b\n"
@@ -82,6 +82,6 @@
 		  "+d" (_len2), "=m" (*((long *) dest))
 		: "m" (*((long *) src))
 		: "cc", "memory");
-	__raw_local_irq_ssm(flags);
+	arch_local_irq_restore(flags);
 	return rc;
 }
diff --git a/arch/score/include/asm/irqflags.h b/arch/score/include/asm/irqflags.h
index 690a6ca..5c75638 100644
--- a/arch/score/include/asm/irqflags.h
+++ b/arch/score/include/asm/irqflags.h
@@ -3,107 +3,118 @@
 
 #ifndef __ASSEMBLY__
 
-#define raw_local_irq_save(x)			\
-{						\
-	__asm__ __volatile__(			\
-		"mfcr	r8, cr0;"		\
-		"li	r9, 0xfffffffe;"	\
-		"nop;"				\
-		"mv	%0, r8;"		\
-		"and	r8, r8, r9;"		\
-		"mtcr	r8, cr0;"		\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		: "=r" (x)			\
-		:				\
-		: "r8", "r9"			\
-		);				\
+#include <linux/types.h>
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+
+	asm volatile(
+		"	mfcr	r8, cr0		\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	mv	%0, r8		\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	ldi	r9, 0x1		\n"
+		"	and	%0, %0, r9	\n"
+		: "=r" (flags)
+		:
+		: "r8", "r9");
+	return flags;
 }
 
-#define raw_local_irq_restore(x)		\
-{						\
-	__asm__ __volatile__(			\
-		"mfcr	r8, cr0;"		\
-		"ldi	r9, 0x1;"		\
-		"and	%0, %0, r9;"		\
-		"or	r8, r8, %0;"		\
-		"mtcr	r8, cr0;"		\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		:				\
-		: "r"(x)			\
-		: "r8", "r9"			\
-		);				\
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags
+
+	asm volatile(
+		"	mfcr	r8, cr0		\n"
+		"	li	r9, 0xfffffffe	\n"
+		"	nop			\n"
+		"	mv	%0, r8		\n"
+		"	and	r8, r8, r9	\n"
+		"	mtcr	r8, cr0		\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		: "=r" (flags)
+		:
+		: "r8", "r9", "memory");
+
+	return flags;
 }
 
-#define raw_local_irq_enable(void)		\
-{						\
-	__asm__ __volatile__(			\
-		"mfcr\tr8,cr0;"			\
-		"nop;"				\
-		"nop;"				\
-		"ori\tr8,0x1;"			\
-		"mtcr\tr8,cr0;"			\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		:				\
-		:				\
-		: "r8");			\
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile(
+		"	mfcr	r8, cr0		\n"
+		"	ldi	r9, 0x1		\n"
+		"	and	%0, %0, r9	\n"
+		"	or	r8, r8, %0	\n"
+		"	mtcr	r8, cr0		\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		:
+		: "r"(flags)
+		: "r8", "r9", "memory");
 }
 
-#define raw_local_irq_disable(void)		\
-{						\
-	__asm__ __volatile__(			\
-		"mfcr\tr8,cr0;"			\
-		"nop;"				\
-		"nop;"				\
-		"srli\tr8,r8,1;"		\
-		"slli\tr8,r8,1;"		\
-		"mtcr\tr8,cr0;"			\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		:				\
-		:				\
-		: "r8");			\
+static inline void arch_local_irq_enable(void)
+{
+	asm volatile(
+		"	mfcr	r8,cr0		\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	ori	r8,0x1		\n"
+		"	mtcr	r8,cr0		\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		:
+		:
+		: "r8", "memory");
 }
 
-#define raw_local_save_flags(x)			\
-{						\
-	__asm__ __volatile__(			\
-		"mfcr	r8, cr0;"		\
-		"nop;"				\
-		"nop;"				\
-		"mv	%0, r8;"		\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"nop;"				\
-		"ldi	r9, 0x1;"		\
-		"and	%0, %0, r9;"		\
-		: "=r" (x)			\
-		:				\
-		: "r8", "r9"			\
-		);				\
+static inline void arch_local_irq_disable(void)
+{
+	asm volatile(
+		"	mfcr	r8,cr0		\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	srli	r8,r8,1		\n"
+		"	slli	r8,r8,1		\n"
+		"	mtcr	r8,cr0		\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		"	nop			\n"
+		:
+		:
+		: "r8", "memory");
 }
 
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !(flags & 1);
 }
 
-#endif
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_SCORE_IRQFLAGS_H */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 33990fa..35b6879 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -16,6 +16,7 @@
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_KERNEL_GZIP
@@ -249,6 +250,11 @@
 	select PM
 	select PM_RUNTIME
 
+config CPU_HAS_PMU
+       depends on CPU_SH4 || CPU_SH4A
+       default y
+       bool
+
 if SUPERH32
 
 choice
@@ -738,6 +744,14 @@
 	  LLSC, this should be more efficient than the other alternative of
 	  disabling interrupts around the atomic sequence.
 
+config HW_PERF_EVENTS
+	bool "Enable hardware performance counter support for perf events"
+	depends on PERF_EVENTS && CPU_HAS_PMU
+	default y
+	help
+	  Enable hardware performance counter support for perf events. If
+	  disabled, perf events will use software events only.
+
 source "drivers/sh/Kconfig"
 
 endmenu
diff --git a/arch/sh/boards/mach-landisk/gio.c b/arch/sh/boards/mach-landisk/gio.c
index 01e6abb..8132dff 100644
--- a/arch/sh/boards/mach-landisk/gio.c
+++ b/arch/sh/boards/mach-landisk/gio.c
@@ -128,6 +128,7 @@
 	.open = gio_open,	/* open */
 	.release = gio_close,	/* release */
 	.unlocked_ioctl = gio_ioctl,
+	.llseek = noop_llseek,
 };
 
 static int __init gio_init(void)
diff --git a/arch/sh/include/asm/irqflags.h b/arch/sh/include/asm/irqflags.h
index a741153..43b7608 100644
--- a/arch/sh/include/asm/irqflags.h
+++ b/arch/sh/include/asm/irqflags.h
@@ -1,8 +1,8 @@
 #ifndef __ASM_SH_IRQFLAGS_H
 #define __ASM_SH_IRQFLAGS_H
 
-#define RAW_IRQ_DISABLED	0xf0
-#define RAW_IRQ_ENABLED		0x00
+#define ARCH_IRQ_DISABLED	0xf0
+#define ARCH_IRQ_ENABLED	0x00
 
 #include <asm-generic/irqflags.h>
 
diff --git a/arch/sh/include/asm/memblock.h b/arch/sh/include/asm/memblock.h
index dfe683b..e87063f 100644
--- a/arch/sh/include/asm/memblock.h
+++ b/arch/sh/include/asm/memblock.h
@@ -1,6 +1,4 @@
 #ifndef __ASM_SH_MEMBLOCK_H
 #define __ASM_SH_MEMBLOCK_H
 
-#define MEMBLOCK_REAL_LIMIT	0
-
 #endif /* __ASM_SH_MEMBLOCK_H */
diff --git a/arch/sh/include/asm/perf_event.h b/arch/sh/include/asm/perf_event.h
index 3d0c9f3..14308be 100644
--- a/arch/sh/include/asm/perf_event.h
+++ b/arch/sh/include/asm/perf_event.h
@@ -26,11 +26,4 @@
 extern int reserve_pmc_hardware(void);
 extern void release_pmc_hardware(void);
 
-static inline void set_perf_event_pending(void)
-{
-	/* Nothing to see here, move along. */
-}
-
-#define PERF_EVENT_INDEX_OFFSET	0
-
 #endif /* __ASM_SH_PERF_EVENT_H */
diff --git a/arch/sh/include/asm/syscalls_32.h b/arch/sh/include/asm/syscalls_32.h
index be201fd..ae717e3 100644
--- a/arch/sh/include/asm/syscalls_32.h
+++ b/arch/sh/include/asm/syscalls_32.h
@@ -19,9 +19,10 @@
 asmlinkage int sys_vfork(unsigned long r4, unsigned long r5,
 			 unsigned long r6, unsigned long r7,
 			 struct pt_regs __regs);
-asmlinkage int sys_execve(const char __user *ufilename, char __user * __user *uargv,
-			  char __user * __user *uenvp, unsigned long r7,
-			  struct pt_regs __regs);
+asmlinkage int sys_execve(const char __user *ufilename,
+			  const char __user *const __user *uargv,
+			  const char __user *const __user *uenvp,
+			  unsigned long r7, struct pt_regs __regs);
 asmlinkage int sys_sigsuspend(old_sigset_t mask, unsigned long r5,
 			      unsigned long r6, unsigned long r7,
 			      struct pt_regs __regs);
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 257de1f..ae5bac3 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -290,7 +290,7 @@
 int __init arch_probe_nr_irqs(void)
 {
 	nr_irqs = sh_mv.mv_nr_irqs;
-	return 0;
+	return NR_IRQS_LEGACY;
 }
 #endif
 
diff --git a/arch/sh/kernel/irq_32.c b/arch/sh/kernel/irq_32.c
index e33ab15..e5a755b 100644
--- a/arch/sh/kernel/irq_32.c
+++ b/arch/sh/kernel/irq_32.c
@@ -10,11 +10,11 @@
 #include <linux/irqflags.h>
 #include <linux/module.h>
 
-void notrace raw_local_irq_restore(unsigned long flags)
+void notrace arch_local_irq_restore(unsigned long flags)
 {
 	unsigned long __dummy0, __dummy1;
 
-	if (flags == RAW_IRQ_DISABLED) {
+	if (flags == ARCH_IRQ_DISABLED) {
 		__asm__ __volatile__ (
 			"stc	sr, %0\n\t"
 			"or	#0xf0, %0\n\t"
@@ -33,14 +33,14 @@
 #endif
 			"ldc	%0, sr\n\t"
 			: "=&r" (__dummy0), "=r" (__dummy1)
-			: "1" (~RAW_IRQ_DISABLED)
+			: "1" (~ARCH_IRQ_DISABLED)
 			: "memory"
 		);
 	}
 }
-EXPORT_SYMBOL(raw_local_irq_restore);
+EXPORT_SYMBOL(arch_local_irq_restore);
 
-unsigned long notrace __raw_local_save_flags(void)
+unsigned long notrace arch_local_save_flags(void)
 {
 	unsigned long flags;
 
@@ -54,4 +54,4 @@
 
 	return flags;
 }
-EXPORT_SYMBOL(__raw_local_save_flags);
+EXPORT_SYMBOL(arch_local_save_flags);
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index a9dd3ab..d5ca1ef 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -14,11 +14,6 @@
 #include <asm/unwinder.h>
 #include <asm/ptrace.h>
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 static void callchain_warning(void *data, char *msg)
 {
@@ -39,7 +34,7 @@
 	struct perf_callchain_entry *entry = data;
 
 	if (reliable)
-		callchain_store(entry, addr);
+		perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops callchain_ops = {
@@ -49,47 +44,10 @@
 	.address	= callchain_address,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->pc);
+	perf_callchain_store(entry, regs->pc);
 
 	unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	/*
-	 * Only the kernel side is implemented for now.
-	 */
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-}
-
-/*
- * No need for separate IRQ and NMI entries.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-	entry->nr = 0;
-
-	perf_do_callchain(regs, entry);
-
-	return entry;
-}
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7a3dc35..5a4b334 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -59,6 +59,24 @@
 	return !!sh_pmu;
 }
 
+const char *perf_pmu_name(void)
+{
+	if (!sh_pmu)
+		return NULL;
+
+	return sh_pmu->name;
+}
+EXPORT_SYMBOL_GPL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	if (!sh_pmu)
+		return 0;
+
+	return sh_pmu->num_events;
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
 /*
  * Release the PMU if this is the last perf_event.
  */
@@ -206,50 +224,80 @@
 	local64_add(delta, &event->count);
 }
 
-static void sh_pmu_disable(struct perf_event *event)
+static void sh_pmu_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	clear_bit(idx, cpuc->active_mask);
-	sh_pmu->disable(hwc, idx);
+	if (!(event->hw.state & PERF_HES_STOPPED)) {
+		sh_pmu->disable(hwc, idx);
+		cpuc->events[idx] = NULL;
+		event->hw.state |= PERF_HES_STOPPED;
+	}
 
-	barrier();
+	if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+		sh_perf_event_update(event, &event->hw, idx);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
 
-	sh_perf_event_update(event, &event->hw, idx);
+static void sh_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
 
-	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	cpuc->events[idx] = event;
+	event->hw.state = 0;
+	sh_pmu->enable(hwc, idx);
+}
+
+static void sh_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	sh_pmu_stop(event, PERF_EF_UPDATE);
+	__clear_bit(event->hw.idx, cpuc->used_mask);
 
 	perf_event_update_userpage(event);
 }
 
-static int sh_pmu_enable(struct perf_event *event)
+static int sh_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	int ret = -EAGAIN;
 
-	if (test_and_set_bit(idx, cpuc->used_mask)) {
+	perf_pmu_disable(event->pmu);
+
+	if (__test_and_set_bit(idx, cpuc->used_mask)) {
 		idx = find_first_zero_bit(cpuc->used_mask, sh_pmu->num_events);
 		if (idx == sh_pmu->num_events)
-			return -EAGAIN;
+			goto out;
 
-		set_bit(idx, cpuc->used_mask);
+		__set_bit(idx, cpuc->used_mask);
 		hwc->idx = idx;
 	}
 
 	sh_pmu->disable(hwc, idx);
 
-	cpuc->events[idx] = event;
-	set_bit(idx, cpuc->active_mask);
-
-	sh_pmu->enable(hwc, idx);
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (flags & PERF_EF_START)
+		sh_pmu_start(event, PERF_EF_RELOAD);
 
 	perf_event_update_userpage(event);
-
-	return 0;
+	ret = 0;
+out:
+	perf_pmu_enable(event->pmu);
+	return ret;
 }
 
 static void sh_pmu_read(struct perf_event *event)
@@ -257,24 +305,56 @@
 	sh_perf_event_update(event, &event->hw, event->hw.idx);
 }
 
-static const struct pmu pmu = {
-	.enable		= sh_pmu_enable,
-	.disable	= sh_pmu_disable,
-	.read		= sh_pmu_read,
-};
-
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int sh_pmu_event_init(struct perf_event *event)
 {
-	int err = __hw_perf_event_init(event);
+	int err;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HW_CACHE:
+	case PERF_TYPE_HARDWARE:
+		err = __hw_perf_event_init(event);
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (unlikely(err)) {
 		if (event->destroy)
 			event->destroy(event);
-		return ERR_PTR(err);
 	}
 
-	return &pmu;
+	return err;
 }
 
+static void sh_pmu_enable(struct pmu *pmu)
+{
+	if (!sh_pmu_initialized())
+		return;
+
+	sh_pmu->enable_all();
+}
+
+static void sh_pmu_disable(struct pmu *pmu)
+{
+	if (!sh_pmu_initialized())
+		return;
+
+	sh_pmu->disable_all();
+}
+
+static struct pmu pmu = {
+	.pmu_enable	= sh_pmu_enable,
+	.pmu_disable	= sh_pmu_disable,
+	.event_init	= sh_pmu_event_init,
+	.add		= sh_pmu_add,
+	.del		= sh_pmu_del,
+	.start		= sh_pmu_start,
+	.stop		= sh_pmu_stop,
+	.read		= sh_pmu_read,
+};
+
 static void sh_pmu_setup(int cpu)
 {
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
@@ -299,32 +379,17 @@
 	return NOTIFY_OK;
 }
 
-void hw_perf_enable(void)
-{
-	if (!sh_pmu_initialized())
-		return;
-
-	sh_pmu->enable_all();
-}
-
-void hw_perf_disable(void)
-{
-	if (!sh_pmu_initialized())
-		return;
-
-	sh_pmu->disable_all();
-}
-
-int __cpuinit register_sh_pmu(struct sh_pmu *pmu)
+int __cpuinit register_sh_pmu(struct sh_pmu *_pmu)
 {
 	if (sh_pmu)
 		return -EBUSY;
-	sh_pmu = pmu;
+	sh_pmu = _pmu;
 
-	pr_info("Performance Events: %s support registered\n", pmu->name);
+	pr_info("Performance Events: %s support registered\n", _pmu->name);
 
-	WARN_ON(pmu->num_events > MAX_HWEVENTS);
+	WARN_ON(_pmu->num_events > MAX_HWEVENTS);
 
+	perf_pmu_register(&pmu);
 	perf_cpu_notifier(sh_pmu_notifier);
 	return 0;
 }
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index d0e24910..552bea5 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -200,7 +200,6 @@
 	unsigned long total_pages, paddr;
 	unsigned long end_pfn;
 	struct pglist_data *p;
-	int i;
 
 	p = NODE_DATA(nid);
 
@@ -226,11 +225,12 @@
 	 * reservations in other nodes.
 	 */
 	if (nid == 0) {
+		struct memblock_region *reg;
+
 		/* Reserve the sections we're already using. */
-		for (i = 0; i < memblock.reserved.cnt; i++)
-			reserve_bootmem(memblock.reserved.region[i].base,
-					memblock_size_bytes(&memblock.reserved, i),
-					BOOTMEM_DEFAULT);
+		for_each_memblock(reserved, reg) {
+			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+		}
 	}
 
 	sparse_memory_present_with_active_regions(nid);
@@ -238,13 +238,14 @@
 
 static void __init do_init_bootmem(void)
 {
+	struct memblock_region *reg;
 	int i;
 
 	/* Add active regions with valid PFNs. */
-	for (i = 0; i < memblock.memory.cnt; i++) {
+	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+		start_pfn = memblock_region_memory_base_pfn(reg);
+		end_pfn = memblock_region_memory_end_pfn(reg);
 		__add_active_range(0, start_pfn, end_pfn);
 	}
 
diff --git a/arch/sh/oprofile/Makefile b/arch/sh/oprofile/Makefile
index 4886c5c..e85aae7 100644
--- a/arch/sh/oprofile/Makefile
+++ b/arch/sh/oprofile/Makefile
@@ -6,4 +6,8 @@
 		oprofilefs.o oprofile_stats.o \
 		timer_int.o )
 
+ifeq ($(CONFIG_HW_PERF_EVENTS),y)
+DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o)
+endif
+
 oprofile-y	:= $(DRIVER_OBJS) common.o backtrace.o
diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c
index ac60493..e10d893 100644
--- a/arch/sh/oprofile/common.c
+++ b/arch/sh/oprofile/common.c
@@ -17,114 +17,45 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 #include <asm/processor.h>
-#include "op_impl.h"
 
-static struct op_sh_model *model;
-
-static struct op_counter_config ctr[20];
-
+#ifdef CONFIG_HW_PERF_EVENTS
 extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
 
-static int op_sh_setup(void)
+char *op_name_from_perf_id(void)
 {
-	/* Pre-compute the values to stuff in the hardware registers.  */
-	model->reg_setup(ctr);
+	const char *pmu;
+	char buf[20];
+	int size;
 
-	/* Configure the registers on all cpus.  */
-	on_each_cpu(model->cpu_setup, NULL, 1);
+	pmu = perf_pmu_name();
+	if (!pmu)
+		return NULL;
 
-        return 0;
-}
+	size = snprintf(buf, sizeof(buf), "sh/%s", pmu);
+	if (size > -1 && size < sizeof(buf))
+		return buf;
 
-static int op_sh_create_files(struct super_block *sb, struct dentry *root)
-{
-	int i, ret = 0;
-
-	for (i = 0; i < model->num_counters; i++) {
-		struct dentry *dir;
-		char buf[4];
-
-		snprintf(buf, sizeof(buf), "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
-
-		ret |= oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
-		ret |= oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
-		ret |= oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
-		ret |= oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
-
-		if (model->create_files)
-			ret |= model->create_files(sb, dir);
-		else
-			ret |= oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
-
-		/* Dummy entries */
-		ret |= oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
-	}
-
-	return ret;
-}
-
-static int op_sh_start(void)
-{
-	/* Enable performance monitoring for all counters.  */
-	on_each_cpu(model->cpu_start, NULL, 1);
-
-	return 0;
-}
-
-static void op_sh_stop(void)
-{
-	/* Disable performance monitoring for all counters.  */
-	on_each_cpu(model->cpu_stop, NULL, 1);
+	return NULL;
 }
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-	struct op_sh_model *lmodel = NULL;
-	int ret;
-
-	/*
-	 * Always assign the backtrace op. If the counter initialization
-	 * fails, we fall back to the timer which will still make use of
-	 * this.
-	 */
 	ops->backtrace = sh_backtrace;
 
-	/*
-	 * XXX
-	 *
-	 * All of the SH7750/SH-4A counters have been converted to perf,
-	 * this infrastructure hook is left for other users until they've
-	 * had a chance to convert over, at which point all of this
-	 * will be deleted.
-	 */
-
-	if (!lmodel)
-		return -ENODEV;
-	if (!(current_cpu_data.flags & CPU_HAS_PERF_COUNTER))
-		return -ENODEV;
-
-	ret = lmodel->init();
-	if (unlikely(ret != 0))
-		return ret;
-
-	model = lmodel;
-
-	ops->setup		= op_sh_setup;
-	ops->create_files	= op_sh_create_files;
-	ops->start		= op_sh_start;
-	ops->stop		= op_sh_stop;
-	ops->cpu_type		= lmodel->cpu_type;
-
-	printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
-	       lmodel->cpu_type);
-
-	return 0;
+	return oprofile_perf_init(ops);
 }
 
-void oprofile_arch_exit(void)
+void __exit oprofile_arch_exit(void)
 {
-	if (model && model->exit)
-		model->exit();
+	oprofile_perf_exit();
 }
+#else
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+	pr_info("oprofile: hardware counters not available\n");
+	return -ENODEV;
+}
+void __exit oprofile_arch_exit(void) {}
+#endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/arch/sh/oprofile/op_impl.h b/arch/sh/oprofile/op_impl.h
deleted file mode 100644
index 1244479..0000000
--- a/arch/sh/oprofile/op_impl.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef __OP_IMPL_H
-#define __OP_IMPL_H
-
-/* Per-counter configuration as set via oprofilefs.  */
-struct op_counter_config {
-	unsigned long enabled;
-	unsigned long event;
-
-	unsigned long count;
-
-	/* Dummy values for userspace tool compliance */
-	unsigned long kernel;
-	unsigned long user;
-	unsigned long unit_mask;
-};
-
-/* Per-architecture configury and hooks.  */
-struct op_sh_model {
-	void (*reg_setup)(struct op_counter_config *);
-	int (*create_files)(struct super_block *sb, struct dentry *dir);
-	void (*cpu_setup)(void *dummy);
-	int (*init)(void);
-	void (*exit)(void);
-	void (*cpu_start)(void *args);
-	void (*cpu_stop)(void *args);
-	char *cpu_type;
-	unsigned char num_counters;
-};
-
-/* arch/sh/oprofile/common.c */
-extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
-
-#endif /* __OP_IMPL_H */
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 491e9d6..3e9d314 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -26,10 +26,12 @@
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select RTC_CLASS
 	select RTC_DRV_M48T59
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
+	select HAVE_ARCH_JUMP_LABEL
 
 config SPARC32
 	def_bool !64BIT
@@ -53,6 +55,7 @@
 	select RTC_DRV_BQ4802
 	select RTC_DRV_SUN4V
 	select RTC_DRV_STARFIRE
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 
diff --git a/arch/sparc/include/asm/irqflags_32.h b/arch/sparc/include/asm/irqflags_32.h
index 0fca9d9..d4d0711 100644
--- a/arch/sparc/include/asm/irqflags_32.h
+++ b/arch/sparc/include/asm/irqflags_32.h
@@ -5,33 +5,40 @@
  *
  * This file gets included from lowlevel asm headers too, to provide
  * wrapped versions of the local_irq_*() APIs, based on the
- * raw_local_irq_*() functions from the lowlevel headers.
+ * arch_local_irq_*() functions from the lowlevel headers.
  */
 #ifndef _ASM_IRQFLAGS_H
 #define _ASM_IRQFLAGS_H
 
 #ifndef __ASSEMBLY__
 
-extern void raw_local_irq_restore(unsigned long);
-extern unsigned long __raw_local_irq_save(void);
-extern void raw_local_irq_enable(void);
+#include <linux/types.h>
 
-static inline unsigned long getipl(void)
+extern void arch_local_irq_restore(unsigned long);
+extern unsigned long arch_local_irq_save(void);
+extern void arch_local_irq_enable(void);
+
+static inline unsigned long arch_local_save_flags(void)
 {
-        unsigned long retval;
+	unsigned long flags;
 
-        __asm__ __volatile__("rd        %%psr, %0" : "=r" (retval));
-        return retval;
+	asm volatile("rd        %%psr, %0" : "=r" (flags));
+	return flags;
 }
 
-#define raw_local_save_flags(flags) ((flags) = getipl())
-#define raw_local_irq_save(flags)   ((flags) = __raw_local_irq_save())
-#define raw_local_irq_disable()     ((void) __raw_local_irq_save())
-#define raw_irqs_disabled()         ((getipl() & PSR_PIL) != 0)
-
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+static inline void arch_local_irq_disable(void)
 {
-        return ((flags & PSR_PIL) != 0);
+	arch_local_irq_save();
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & PSR_PIL) != 0;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
 #endif /* (__ASSEMBLY__) */
diff --git a/arch/sparc/include/asm/irqflags_64.h b/arch/sparc/include/asm/irqflags_64.h
index bfa1ea4..aab969c 100644
--- a/arch/sparc/include/asm/irqflags_64.h
+++ b/arch/sparc/include/asm/irqflags_64.h
@@ -5,7 +5,7 @@
  *
  * This file gets included from lowlevel asm headers too, to provide
  * wrapped versions of the local_irq_*() APIs, based on the
- * raw_local_irq_*() functions from the lowlevel headers.
+ * arch_local_irq_*() functions from the lowlevel headers.
  */
 #ifndef _ASM_IRQFLAGS_H
 #define _ASM_IRQFLAGS_H
@@ -14,7 +14,7 @@
 
 #ifndef __ASSEMBLY__
 
-static inline unsigned long __raw_local_save_flags(void)
+static inline unsigned long arch_local_save_flags(void)
 {
 	unsigned long flags;
 
@@ -26,10 +26,7 @@
 	return flags;
 }
 
-#define raw_local_save_flags(flags) \
-		do { (flags) = __raw_local_save_flags(); } while (0)
-
-static inline void raw_local_irq_restore(unsigned long flags)
+static inline void arch_local_irq_restore(unsigned long flags)
 {
 	__asm__ __volatile__(
 		"wrpr	%0, %%pil"
@@ -39,7 +36,7 @@
 	);
 }
 
-static inline void raw_local_irq_disable(void)
+static inline void arch_local_irq_disable(void)
 {
 	__asm__ __volatile__(
 		"wrpr	%0, %%pil"
@@ -49,7 +46,7 @@
 	);
 }
 
-static inline void raw_local_irq_enable(void)
+static inline void arch_local_irq_enable(void)
 {
 	__asm__ __volatile__(
 		"wrpr	0, %%pil"
@@ -59,22 +56,17 @@
 	);
 }
 
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return (flags > 0);
 }
 
-static inline int raw_irqs_disabled(void)
+static inline int arch_irqs_disabled(void)
 {
-	unsigned long flags = __raw_local_save_flags();
-
-	return raw_irqs_disabled_flags(flags);
+	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
-/*
- * For spinlocks, etc:
- */
-static inline unsigned long __raw_local_irq_save(void)
+static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags, tmp;
 
@@ -100,9 +92,6 @@
 	return flags;
 }
 
-#define raw_local_irq_save(flags) \
-		do { (flags) = __raw_local_irq_save(); } while (0)
-
 #endif /* (__ASSEMBLY__) */
 
 #endif /* !(_ASM_IRQFLAGS_H) */
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
new file mode 100644
index 0000000..62e66d7
--- /dev/null
+++ b/arch/sparc/include/asm/jump_label.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_SPARC_JUMP_LABEL_H
+#define _ASM_SPARC_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/system.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+#define JUMP_LABEL(key, label)					\
+	do {							\
+		asm goto("1:\n\t"				\
+			 "nop\n\t"				\
+			 "nop\n\t"				\
+			 ".pushsection __jump_table,  \"a\"\n\t"\
+			 ".word 1b, %l[" #label "], %c0\n\t"	\
+			 ".popsection \n\t"			\
+			 : :  "i" (key) :  : label);\
+	} while (0)
+
+#endif /* __KERNEL__ */
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif
diff --git a/arch/sparc/include/asm/memblock.h b/arch/sparc/include/asm/memblock.h
index f12af88..c67b047 100644
--- a/arch/sparc/include/asm/memblock.h
+++ b/arch/sparc/include/asm/memblock.h
@@ -5,6 +5,4 @@
 
 #define MEMBLOCK_DBG(fmt...) prom_printf(fmt)
 
-#define MEMBLOCK_REAL_LIMIT	0
-
 #endif /* !(_SPARC64_MEMBLOCK_H) */
diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h
index 727af70..6e8bfa1 100644
--- a/arch/sparc/include/asm/perf_event.h
+++ b/arch/sparc/include/asm/perf_event.h
@@ -1,10 +1,6 @@
 #ifndef __ASM_SPARC_PERF_EVENT_H
 #define __ASM_SPARC_PERF_EVENT_H
 
-extern void set_perf_event_pending(void);
-
-#define	PERF_EVENT_INDEX_OFFSET	0
-
 #ifdef CONFIG_PERF_EVENTS
 #include <asm/ptrace.h>
 
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 0c2dc1f..599398f 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -119,3 +119,5 @@
 
 pc--$(CONFIG_PERF_EVENTS) := perf_event.o
 obj-$(CONFIG_SPARC64)	+= $(pc--y)
+
+obj-$(CONFIG_SPARC64)	+= jump_label.o
diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c
index 2c0046e..52de4a9 100644
--- a/arch/sparc/kernel/apc.c
+++ b/arch/sparc/kernel/apc.c
@@ -132,6 +132,7 @@
 	.unlocked_ioctl =	apc_ioctl,
 	.open =			apc_open,
 	.release =		apc_release,
+	.llseek =		noop_llseek,
 };
 
 static struct miscdevice apc_miscdev = { APC_MINOR, APC_DEVNAME, &apc_fops };
diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c
index e1af437..0116d8d 100644
--- a/arch/sparc/kernel/irq_32.c
+++ b/arch/sparc/kernel/irq_32.c
@@ -57,7 +57,7 @@
 #define SMP_NOP2
 #define SMP_NOP3
 #endif /* SMP */
-unsigned long __raw_local_irq_save(void)
+unsigned long arch_local_irq_save(void)
 {
 	unsigned long retval;
 	unsigned long tmp;
@@ -74,8 +74,9 @@
 
 	return retval;
 }
+EXPORT_SYMBOL(arch_local_irq_save);
 
-void raw_local_irq_enable(void)
+void arch_local_irq_enable(void)
 {
 	unsigned long tmp;
 
@@ -89,8 +90,9 @@
 		: "i" (PSR_PIL)
 		: "memory");
 }
+EXPORT_SYMBOL(arch_local_irq_enable);
 
-void raw_local_irq_restore(unsigned long old_psr)
+void arch_local_irq_restore(unsigned long old_psr)
 {
 	unsigned long tmp;
 
@@ -105,10 +107,7 @@
 		: "i" (PSR_PIL), "r" (old_psr)
 		: "memory");
 }
-
-EXPORT_SYMBOL(__raw_local_irq_save);
-EXPORT_SYMBOL(raw_local_irq_enable);
-EXPORT_SYMBOL(raw_local_irq_restore);
+EXPORT_SYMBOL(arch_local_irq_restore);
 
 /*
  * Dave Redman (djhr@tadpole.co.uk)
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
new file mode 100644
index 0000000..ea2dafc
--- /dev/null
+++ b/arch/sparc/kernel/jump_label.c
@@ -0,0 +1,47 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	u32 val;
+	u32 *insn = (u32 *) (unsigned long) entry->code;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		s32 off = (s32)entry->target - (s32)entry->code;
+
+#ifdef CONFIG_SPARC64
+		/* ba,pt %xcc, . + (off << 2) */
+		val = 0x10680000 | ((u32) off >> 2);
+#else
+		/* ba . + (off << 2) */
+		val = 0x10800000 | ((u32) off >> 2);
+#endif
+	} else {
+		val = 0x01000000;
+	}
+
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+	*insn = val;
+	flushi(insn);
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+}
+
+void arch_jump_label_text_poke_early(jump_label_t addr)
+{
+	u32 *insn_p = (u32 *) (unsigned long) addr;
+
+	*insn_p = 0x01000000;
+	flushi(insn_p);
+}
+
+#endif
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 83e85c2..6addb91 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -890,6 +890,7 @@
 static const struct file_operations mdesc_fops = {
 	.read	= mdesc_read,
 	.owner	= THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice mdesc_misc = {
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index f848aad..ee3c7dd 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -18,6 +18,9 @@
 #include <asm/spitfire.h>
 
 #ifdef CONFIG_SPARC64
+
+#include <linux/jump_label.h>
+
 static void *module_map(unsigned long size)
 {
 	struct vm_struct *area;
@@ -227,6 +230,9 @@
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
+	/* make jump label nops */
+	jump_label_apply_nops(me);
+
 	/* Cheetah's I-cache is fully coherent.  */
 	if (tlb_type == spitfire) {
 		unsigned long va;
diff --git a/arch/sparc/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c
index 548b8ca..b210416 100644
--- a/arch/sparc/kernel/pci_msi.c
+++ b/arch/sparc/kernel/pci_msi.c
@@ -114,10 +114,10 @@
 
 static struct irq_chip msi_irq = {
 	.name		= "PCI-MSI",
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
-	.enable		= unmask_msi_irq,
-	.disable	= mask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
+	.irq_enable	= unmask_msi_irq,
+	.irq_disable	= mask_msi_irq,
 	/* XXX affinity XXX */
 };
 
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index c4a6a50..b87873c 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -7,7 +7,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 #include <linux/ftrace.h>
 
 #include <asm/pil.h>
@@ -43,14 +43,14 @@
 
 	old_regs = set_irq_regs(regs);
 	irq_enter();
-#ifdef CONFIG_PERF_EVENTS
-	perf_event_do_pending();
+#ifdef CONFIG_IRQ_WORK
+	irq_work_run();
 #endif
 	irq_exit();
 	set_irq_regs(old_regs);
 }
 
-void set_perf_event_pending(void)
+void arch_irq_work_raise(void)
 {
 	set_softint(1 << PIL_DEFERRED_PCR_WORK);
 }
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 6318e62..0d6deb5 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -658,13 +658,16 @@
 
 		enc = perf_event_get_enc(cpuc->events[i]);
 		pcr &= ~mask_for_index(idx);
-		pcr |= event_encoding(enc, idx);
+		if (hwc->state & PERF_HES_STOPPED)
+			pcr |= nop_for_index(idx);
+		else
+			pcr |= event_encoding(enc, idx);
 	}
 out:
 	return pcr;
 }
 
-void hw_perf_enable(void)
+static void sparc_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	u64 pcr;
@@ -691,7 +694,7 @@
 	pcr_ops->write(cpuc->pcr);
 }
 
-void hw_perf_disable(void)
+static void sparc_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	u64 val;
@@ -710,48 +713,6 @@
 	pcr_ops->write(cpuc->pcr);
 }
 
-static void sparc_pmu_disable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	unsigned long flags;
-	int i;
-
-	local_irq_save(flags);
-	perf_disable();
-
-	for (i = 0; i < cpuc->n_events; i++) {
-		if (event == cpuc->event[i]) {
-			int idx = cpuc->current_idx[i];
-
-			/* Shift remaining entries down into
-			 * the existing slot.
-			 */
-			while (++i < cpuc->n_events) {
-				cpuc->event[i - 1] = cpuc->event[i];
-				cpuc->events[i - 1] = cpuc->events[i];
-				cpuc->current_idx[i - 1] =
-					cpuc->current_idx[i];
-			}
-
-			/* Absorb the final count and turn off the
-			 * event.
-			 */
-			sparc_pmu_disable_event(cpuc, hwc, idx);
-			barrier();
-			sparc_perf_event_update(event, hwc, idx);
-
-			perf_event_update_userpage(event);
-
-			cpuc->n_events--;
-			break;
-		}
-	}
-
-	perf_enable();
-	local_irq_restore(flags);
-}
-
 static int active_event_index(struct cpu_hw_events *cpuc,
 			      struct perf_event *event)
 {
@@ -765,6 +726,74 @@
 	return cpuc->current_idx[i];
 }
 
+static void sparc_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = active_event_index(cpuc, event);
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		sparc_perf_event_set_period(event, &event->hw, idx);
+	}
+
+	event->hw.state = 0;
+
+	sparc_pmu_enable_event(cpuc, &event->hw, idx);
+}
+
+static void sparc_pmu_stop(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = active_event_index(cpuc, event);
+
+	if (!(event->hw.state & PERF_HES_STOPPED)) {
+		sparc_pmu_disable_event(cpuc, &event->hw, idx);
+		event->hw.state |= PERF_HES_STOPPED;
+	}
+
+	if (!(event->hw.state & PERF_HES_UPTODATE) && (flags & PERF_EF_UPDATE)) {
+		sparc_perf_event_update(event, &event->hw, idx);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
+
+static void sparc_pmu_del(struct perf_event *event, int _flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	unsigned long flags;
+	int i;
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		if (event == cpuc->event[i]) {
+			/* Absorb the final count and turn off the
+			 * event.
+			 */
+			sparc_pmu_stop(event, PERF_EF_UPDATE);
+
+			/* Shift remaining entries down into
+			 * the existing slot.
+			 */
+			while (++i < cpuc->n_events) {
+				cpuc->event[i - 1] = cpuc->event[i];
+				cpuc->events[i - 1] = cpuc->events[i];
+				cpuc->current_idx[i - 1] =
+					cpuc->current_idx[i];
+			}
+
+			perf_event_update_userpage(event);
+
+			cpuc->n_events--;
+			break;
+		}
+	}
+
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
+
 static void sparc_pmu_read(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -774,15 +803,6 @@
 	sparc_perf_event_update(event, hwc, idx);
 }
 
-static void sparc_pmu_unthrottle(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	int idx = active_event_index(cpuc, event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	sparc_pmu_enable_event(cpuc, hwc, idx);
-}
-
 static atomic_t active_events = ATOMIC_INIT(0);
 static DEFINE_MUTEX(pmc_grab_mutex);
 
@@ -877,7 +897,7 @@
 	if (!n_ev)
 		return 0;
 
-	if (n_ev > perf_max_events)
+	if (n_ev > MAX_HWEVENTS)
 		return -1;
 
 	msk0 = perf_event_get_msk(events[0]);
@@ -984,23 +1004,27 @@
 	return n;
 }
 
-static int sparc_pmu_enable(struct perf_event *event)
+static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int n0, ret = -EAGAIN;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	n0 = cpuc->n_events;
-	if (n0 >= perf_max_events)
+	if (n0 >= MAX_HWEVENTS)
 		goto out;
 
 	cpuc->event[n0] = event;
 	cpuc->events[n0] = event->hw.event_base;
 	cpuc->current_idx[n0] = PIC_NO_INDEX;
 
+	event->hw.state = PERF_HES_UPTODATE;
+	if (!(ef_flags & PERF_EF_START))
+		event->hw.state |= PERF_HES_STOPPED;
+
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
@@ -1020,12 +1044,12 @@
 
 	ret = 0;
 out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int sparc_pmu_event_init(struct perf_event *event)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct perf_event *evts[MAX_HWEVENTS];
@@ -1038,22 +1062,33 @@
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
-	pmap = NULL;
-	if (attr->type == PERF_TYPE_HARDWARE) {
+	switch (attr->type) {
+	case PERF_TYPE_HARDWARE:
 		if (attr->config >= sparc_pmu->max_events)
 			return -EINVAL;
 		pmap = sparc_pmu->event_map(attr->config);
-	} else if (attr->type == PERF_TYPE_HW_CACHE) {
+		break;
+
+	case PERF_TYPE_HW_CACHE:
 		pmap = sparc_map_cache_event(attr->config);
 		if (IS_ERR(pmap))
 			return PTR_ERR(pmap);
-	} else if (attr->type != PERF_TYPE_RAW)
-		return -EOPNOTSUPP;
+		break;
+
+	case PERF_TYPE_RAW:
+		pmap = NULL;
+		break;
+
+	default:
+		return -ENOENT;
+
+	}
 
 	if (pmap) {
 		hwc->event_base = perf_event_encode(pmap);
 	} else {
-		/* User gives us "(encoding << 16) | pic_mask" for
+		/*
+		 * User gives us "(encoding << 16) | pic_mask" for
 		 * PERF_TYPE_RAW events.
 		 */
 		hwc->event_base = attr->config;
@@ -1071,7 +1106,7 @@
 	n = 0;
 	if (event->group_leader != event) {
 		n = collect_events(event->group_leader,
-				   perf_max_events - 1,
+				   MAX_HWEVENTS - 1,
 				   evts, events, current_idx_dmy);
 		if (n < 0)
 			return -EINVAL;
@@ -1107,10 +1142,11 @@
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void sparc_pmu_start_txn(const struct pmu *pmu)
+static void sparc_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 }
 
@@ -1119,11 +1155,12 @@
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void sparc_pmu_cancel_txn(const struct pmu *pmu)
+static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -1131,7 +1168,7 @@
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int sparc_pmu_commit_txn(const struct pmu *pmu)
+static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int n;
@@ -1147,28 +1184,24 @@
 		return -EAGAIN;
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= sparc_pmu_enable,
-	.disable	= sparc_pmu_disable,
+static struct pmu pmu = {
+	.pmu_enable	= sparc_pmu_enable,
+	.pmu_disable	= sparc_pmu_disable,
+	.event_init	= sparc_pmu_event_init,
+	.add		= sparc_pmu_add,
+	.del		= sparc_pmu_del,
+	.start		= sparc_pmu_start,
+	.stop		= sparc_pmu_stop,
 	.read		= sparc_pmu_read,
-	.unthrottle	= sparc_pmu_unthrottle,
 	.start_txn	= sparc_pmu_start_txn,
 	.cancel_txn	= sparc_pmu_cancel_txn,
 	.commit_txn	= sparc_pmu_commit_txn,
 };
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
-{
-	int err = __hw_perf_event_init(event);
-
-	if (err)
-		return ERR_PTR(err);
-	return &pmu;
-}
-
 void perf_event_print_debug(void)
 {
 	unsigned long flags;
@@ -1244,7 +1277,7 @@
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			sparc_pmu_disable_event(cpuc, hwc, idx);
+			sparc_pmu_stop(event, 0);
 	}
 
 	return NOTIFY_STOP;
@@ -1285,28 +1318,21 @@
 
 	pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type);
 
-	/* All sparc64 PMUs currently have 2 events.  */
-	perf_max_events = 2;
-
+	perf_pmu_register(&pmu);
 	register_die_notifier(&perf_event_nmi_notifier);
 }
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
-
-static void perf_callchain_kernel(struct pt_regs *regs,
-				  struct perf_callchain_entry *entry)
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+			   struct pt_regs *regs)
 {
 	unsigned long ksp, fp;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	int graph = 0;
 #endif
 
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->tpc);
+	stack_trace_flush();
+
+	perf_callchain_store(entry, regs->tpc);
 
 	ksp = regs->u_regs[UREG_I6];
 	fp = ksp + STACK_BIAS;
@@ -1330,13 +1356,13 @@
 			pc = sf->callers_pc;
 			fp = (unsigned long)sf->fp + STACK_BIAS;
 		}
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 		if ((pc + 8UL) == (unsigned long) &return_to_handler) {
 			int index = current->curr_ret_stack;
 			if (current->ret_stack && index >= graph) {
 				pc = current->ret_stack[index - graph].ret;
-				callchain_store(entry, pc);
+				perf_callchain_store(entry, pc);
 				graph++;
 			}
 		}
@@ -1344,13 +1370,12 @@
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->tpc);
+	perf_callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
 	do {
@@ -1363,17 +1388,16 @@
 
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp + STACK_BIAS;
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->tpc);
+	perf_callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
 	do {
@@ -1386,34 +1410,16 @@
 
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp;
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-/* Like powerpc we can't get PMU interrupts within the PMU handler,
- * so no need for separate NMI and IRQ chains as on x86.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-	entry->nr = 0;
-	if (!user_mode(regs)) {
-		stack_trace_flush();
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-	if (regs) {
-		flushw_user();
-		if (test_thread_flag(TIF_32BIT))
-			perf_callchain_user_32(regs, entry);
-		else
-			perf_callchain_user_64(regs, entry);
-	}
-	return entry;
+	flushw_user();
+	if (test_thread_flag(TIF_32BIT))
+		perf_callchain_user_32(entry, regs);
+	else
+		perf_callchain_user_64(entry, regs);
 }
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index f043451..4c25727 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -785,8 +785,7 @@
 	return -1;
 }
 
-static unsigned long long nid_range(unsigned long long start,
-				    unsigned long long end, int *nid)
+u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = find_node(start);
 	start += PAGE_SIZE;
@@ -804,8 +803,7 @@
 	return start;
 }
 #else
-static unsigned long long nid_range(unsigned long long start,
-				    unsigned long long end, int *nid)
+u64 memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = 0;
 	return end;
@@ -822,8 +820,7 @@
 	struct pglist_data *p;
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-	paddr = memblock_alloc_nid(sizeof(struct pglist_data),
-			      SMP_CACHE_BYTES, nid, nid_range);
+	paddr = memblock_alloc_try_nid(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid);
 	if (!paddr) {
 		prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid);
 		prom_halt();
@@ -843,8 +840,7 @@
 	if (p->node_spanned_pages) {
 		num_pages = bootmem_bootmap_pages(p->node_spanned_pages);
 
-		paddr = memblock_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid,
-				      nid_range);
+		paddr = memblock_alloc_try_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid);
 		if (!paddr) {
 			prom_printf("Cannot allocate bootmap for nid[%d]\n",
 				  nid);
@@ -972,19 +968,19 @@
 
 static void __init add_node_ranges(void)
 {
-	int i;
+	struct memblock_region *reg;
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		unsigned long size = memblock_size_bytes(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
+		unsigned long size = reg->size;
 		unsigned long start, end;
 
-		start = memblock.memory.region[i].base;
+		start = reg->base;
 		end = start + size;
 		while (start < end) {
 			unsigned long this_end;
 			int nid;
 
-			this_end = nid_range(start, end, &nid);
+			this_end = memblock_nid_range(start, end, &nid);
 
 			numadbg("Adding active range nid[%d] "
 				"start[%lx] end[%lx]\n",
@@ -1281,7 +1277,7 @@
 {
 	unsigned long top_of_ram = memblock_end_of_DRAM();
 	unsigned long total_ram = memblock_phys_mem_size();
-	unsigned int i;
+	struct memblock_region *reg;
 
 	numadbg("bootmem_init_nonnuma()\n");
 
@@ -1292,15 +1288,14 @@
 
 	init_node_masks_nonnuma();
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		unsigned long size = memblock_size_bytes(&memblock.memory, i);
+	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
 
-		if (!size)
+		if (!reg->size)
 			continue;
 
-		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
-		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);
+		start_pfn = memblock_region_memory_base_pfn(reg);
+		end_pfn = memblock_region_memory_end_pfn(reg);
 		add_active_range(0, start_pfn, end_pfn);
 	}
 
@@ -1318,7 +1313,7 @@
 		unsigned long this_end;
 		int n;
 
-		this_end = nid_range(start, end, &n);
+		this_end = memblock_nid_range(start, end, &n);
 		if (n == nid) {
 			numadbg("      MATCH reserving range [%lx:%lx]\n",
 				start, this_end);
@@ -1334,17 +1329,12 @@
 
 static void __init trim_reserved_in_node(int nid)
 {
-	int i;
+	struct memblock_region *reg;
 
 	numadbg("  trim_reserved_in_node(%d)\n", nid);
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		unsigned long start = memblock.reserved.region[i].base;
-		unsigned long size = memblock_size_bytes(&memblock.reserved, i);
-		unsigned long end = start + size;
-
-		reserve_range_in_node(nid, start, end);
-	}
+	for_each_memblock(reserved, reg)
+		reserve_range_in_node(nid, reg->base, reg->base + reg->size);
 }
 
 static void __init bootmem_init_one_node(int nid)
diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c
index fa6e4e2..d9850c2 100644
--- a/arch/sparc/prom/p1275.c
+++ b/arch/sparc/prom/p1275.c
@@ -39,7 +39,7 @@
 	unsigned long flags;
 
 	raw_local_save_flags(flags);
-	raw_local_irq_restore(PIL_NMI);
+	raw_local_irq_restore((unsigned long)PIL_NMI);
 	raw_spin_lock(&prom_entry_lock);
 
 	prom_world(1);
diff --git a/arch/tile/include/asm/bitops.h b/arch/tile/include/asm/bitops.h
index 6832b4b..6d4f0ff 100644
--- a/arch/tile/include/asm/bitops.h
+++ b/arch/tile/include/asm/bitops.h
@@ -120,6 +120,7 @@
 
 #include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/ext2-non-atomic.h>
 #include <asm-generic/bitops/minix.h>
diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h
index 45cf67c..a11d483 100644
--- a/arch/tile/include/asm/irqflags.h
+++ b/arch/tile/include/asm/irqflags.h
@@ -103,55 +103,57 @@
 #define INITIAL_INTERRUPTS_ENABLED INT_MASK(INT_MEM_ERROR)
 
 /* Disable interrupts. */
-#define raw_local_irq_disable() \
+#define arch_local_irq_disable() \
 	interrupt_mask_set_mask(LINUX_MASKABLE_INTERRUPTS)
 
 /* Disable all interrupts, including NMIs. */
-#define raw_local_irq_disable_all() \
+#define arch_local_irq_disable_all() \
 	interrupt_mask_set_mask(-1UL)
 
 /* Re-enable all maskable interrupts. */
-#define raw_local_irq_enable() \
+#define arch_local_irq_enable() \
 	interrupt_mask_reset_mask(__get_cpu_var(interrupts_enabled_mask))
 
 /* Disable or enable interrupts based on flag argument. */
-#define raw_local_irq_restore(disabled) do { \
+#define arch_local_irq_restore(disabled) do { \
 	if (disabled) \
-		raw_local_irq_disable(); \
+		arch_local_irq_disable(); \
 	else \
-		raw_local_irq_enable(); \
+		arch_local_irq_enable(); \
 } while (0)
 
 /* Return true if "flags" argument means interrupts are disabled. */
-#define raw_irqs_disabled_flags(flags) ((flags) != 0)
+#define arch_irqs_disabled_flags(flags) ((flags) != 0)
 
 /* Return true if interrupts are currently disabled. */
-#define raw_irqs_disabled() interrupt_mask_check(INT_MEM_ERROR)
+#define arch_irqs_disabled() interrupt_mask_check(INT_MEM_ERROR)
 
 /* Save whether interrupts are currently disabled. */
-#define raw_local_save_flags(flags) ((flags) = raw_irqs_disabled())
+#define arch_local_save_flags() arch_irqs_disabled()
 
 /* Save whether interrupts are currently disabled, then disable them. */
-#define raw_local_irq_save(flags) \
-	do { raw_local_save_flags(flags); raw_local_irq_disable(); } while (0)
+#define arch_local_irq_save() ({ \
+	unsigned long __flags = arch_local_save_flags(); \
+	arch_local_irq_disable(); \
+	__flags; })
 
 /* Prevent the given interrupt from being enabled next time we enable irqs. */
-#define raw_local_irq_mask(interrupt) \
+#define arch_local_irq_mask(interrupt) \
 	(__get_cpu_var(interrupts_enabled_mask) &= ~INT_MASK(interrupt))
 
 /* Prevent the given interrupt from being enabled immediately. */
-#define raw_local_irq_mask_now(interrupt) do { \
-	raw_local_irq_mask(interrupt); \
+#define arch_local_irq_mask_now(interrupt) do { \
+	arch_local_irq_mask(interrupt); \
 	interrupt_mask_set(interrupt); \
 } while (0)
 
 /* Allow the given interrupt to be enabled next time we enable irqs. */
-#define raw_local_irq_unmask(interrupt) \
+#define arch_local_irq_unmask(interrupt) \
 	(__get_cpu_var(interrupts_enabled_mask) |= INT_MASK(interrupt))
 
 /* Allow the given interrupt to be enabled immediately, if !irqs_disabled. */
-#define raw_local_irq_unmask_now(interrupt) do { \
-	raw_local_irq_unmask(interrupt); \
+#define arch_local_irq_unmask_now(interrupt) do { \
+	arch_local_irq_unmask(interrupt); \
 	if (!irqs_disabled()) \
 		interrupt_mask_reset(interrupt); \
 } while (0)
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index 584b965..1e54a78 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -774,6 +774,7 @@
 #endif
 	.flush          = hardwall_flush,
 	.release        = hardwall_release,
+	.llseek		= noop_llseek,
 };
 
 static struct cdev hardwall_dev;
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index 596c600..9a27d56 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -208,7 +208,7 @@
 }
 
 static struct irq_chip tile_irq_chip = {
-	.typename = "tile_irq_chip",
+	.name = "tile_irq_chip",
 	.ack = tile_irq_chip_ack,
 	.eoi = tile_irq_chip_eoi,
 	.mask = tile_irq_chip_mask,
@@ -288,7 +288,7 @@
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action = action->next; action; action = action->next)
diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c
index cfcac1f..2d0266d 100644
--- a/arch/um/drivers/harddog_kern.c
+++ b/arch/um/drivers/harddog_kern.c
@@ -42,7 +42,7 @@
 #include <linux/miscdevice.h>
 #include <linux/watchdog.h>
 #include <linux/reboot.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <asm/uaccess.h>
@@ -50,6 +50,7 @@
 
 MODULE_LICENSE("GPL");
 
+static DEFINE_MUTEX(harddog_mutex);
 static DEFINE_SPINLOCK(lock);
 static int timer_alive;
 static int harddog_in_fd = -1;
@@ -66,7 +67,7 @@
 	int err = -EBUSY;
 	char *sock = NULL;
 
-	lock_kernel();
+	mutex_lock(&harddog_mutex);
 	spin_lock(&lock);
 	if(timer_alive)
 		goto err;
@@ -83,11 +84,11 @@
 
 	timer_alive = 1;
 	spin_unlock(&lock);
-	unlock_kernel();
+	mutex_unlock(&harddog_mutex);
 	return nonseekable_open(inode, file);
 err:
 	spin_unlock(&lock);
-	unlock_kernel();
+	mutex_unlock(&harddog_mutex);
 	return err;
 }
 
@@ -153,9 +154,9 @@
 {
 	long ret;
 
-	lock_kernel();
+	mutex_lock(&harddog_mutex);
 	ret = harddog_ioctl_unlocked(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&harddog_mutex);
 
 	return ret;
 }
@@ -166,6 +167,7 @@
 	.unlocked_ioctl	= harddog_ioctl,
 	.open		= harddog_open,
 	.release	= harddog_release,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice harddog_miscdev = {
diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c
index 63c740a..f9f6a4e 100644
--- a/arch/um/drivers/hostaudio_kern.c
+++ b/arch/um/drivers/hostaudio_kern.c
@@ -8,7 +8,7 @@
 #include "linux/slab.h"
 #include "linux/sound.h"
 #include "linux/soundcard.h"
-#include "linux/smp_lock.h"
+#include "linux/mutex.h"
 #include "asm/uaccess.h"
 #include "init.h"
 #include "os.h"
@@ -63,6 +63,8 @@
 __uml_setup("mixer=", set_mixer, "mixer=<mixer device>\n" MIXER_HELP);
 #endif
 
+static DEFINE_MUTEX(hostaudio_mutex);
+
 /* /dev/dsp file operations */
 
 static ssize_t hostaudio_read(struct file *file, char __user *buffer,
@@ -198,9 +200,9 @@
 		w = 1;
 
 	kparam_block_sysfs_write(dsp);
-	lock_kernel();
+	mutex_lock(&hostaudio_mutex);
 	ret = os_open_file(dsp, of_set_rw(OPENFLAGS(), r, w), 0);
-	unlock_kernel();
+	mutex_unlock(&hostaudio_mutex);
 	kparam_unblock_sysfs_write(dsp);
 
 	if (ret < 0) {
@@ -259,9 +261,9 @@
 		w = 1;
 
 	kparam_block_sysfs_write(mixer);
-	lock_kernel();
+	mutex_lock(&hostaudio_mutex);
 	ret = os_open_file(mixer, of_set_rw(OPENFLAGS(), r, w), 0);
-	unlock_kernel();
+	mutex_unlock(&hostaudio_mutex);
 	kparam_unblock_sysfs_write(mixer);
 
 	if (ret < 0) {
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index ebc6807..975613b 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -843,6 +843,7 @@
 static const struct file_operations mconsole_proc_fops = {
 	.owner		= THIS_MODULE,
 	.write		= mconsole_proc_write,
+	.llseek		= noop_llseek,
 };
 
 static int create_proc_mconsole(void)
diff --git a/arch/um/drivers/mmapper_kern.c b/arch/um/drivers/mmapper_kern.c
index 7158393..8501e7d 100644
--- a/arch/um/drivers/mmapper_kern.c
+++ b/arch/um/drivers/mmapper_kern.c
@@ -93,6 +93,7 @@
 	.mmap		= mmapper_mmap,
 	.open		= mmapper_open,
 	.release	= mmapper_release,
+	.llseek		= default_llseek,
 };
 
 /*
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index 4949044..981085a 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -100,6 +100,7 @@
 	.owner		= THIS_MODULE,
 	.open		= rng_dev_open,
 	.read		= rng_dev_read,
+	.llseek		= noop_llseek,
 };
 
 /* rng_init shouldn't be called more than once at boot time */
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 9734994..ba4a98b 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -33,7 +33,7 @@
 #include "linux/mm.h"
 #include "linux/slab.h"
 #include "linux/vmalloc.h"
-#include "linux/smp_lock.h"
+#include "linux/mutex.h"
 #include "linux/blkpg.h"
 #include "linux/genhd.h"
 #include "linux/spinlock.h"
@@ -100,6 +100,7 @@
 #define DRIVER_NAME "uml-blkdev"
 
 static DEFINE_MUTEX(ubd_lock);
+static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */
 
 static int ubd_open(struct block_device *bdev, fmode_t mode);
 static int ubd_release(struct gendisk *disk, fmode_t mode);
@@ -1101,7 +1102,7 @@
 	struct ubd *ubd_dev = disk->private_data;
 	int err = 0;
 
-	lock_kernel();
+	mutex_lock(&ubd_mutex);
 	if(ubd_dev->count == 0){
 		err = ubd_open_dev(ubd_dev);
 		if(err){
@@ -1120,7 +1121,7 @@
 	        err = -EROFS;
 	}*/
 out:
-	unlock_kernel();
+	mutex_unlock(&ubd_mutex);
 	return err;
 }
 
@@ -1128,10 +1129,10 @@
 {
 	struct ubd *ubd_dev = disk->private_data;
 
-	lock_kernel();
+	mutex_lock(&ubd_mutex);
 	if(--ubd_dev->count == 0)
 		ubd_close_dev(ubd_dev);
-	unlock_kernel();
+	mutex_unlock(&ubd_mutex);
 	return 0;
 }
 
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 49b5e1e..340268b 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -78,13 +78,11 @@
 	long error;
 	char *filename;
 
-	lock_kernel();
 	filename = getname(file);
 	error = PTR_ERR(filename);
 	if (IS_ERR(filename)) goto out;
 	error = execve1(filename, argv, env);
 	putname(filename);
  out:
-	unlock_kernel();
 	return error;
 }
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index a3f0b04..a746e30 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -46,7 +46,7 @@
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)
@@ -369,7 +369,7 @@
 
 /* This is used for everything else than the timer. */
 static struct irq_chip normal_irq_type = {
-	.typename = "SIGIO",
+	.name = "SIGIO",
 	.release = free_irq_by_irq_and_dev,
 	.disable = dummy,
 	.enable = dummy,
@@ -378,7 +378,7 @@
 };
 
 static struct irq_chip SIGVTALRM_irq_type = {
-	.typename = "SIGVTALRM",
+	.name = "SIGVTALRM",
 	.release = free_irq_by_irq_and_dev,
 	.shutdown = dummy, /* never called */
 	.disable = dummy,
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cea0cd9..dfabfef 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -25,14 +25,17 @@
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS if (!M386 && !M486)
+	select HAVE_IRQ_WORK
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
+	select HAVE_MEMBLOCK
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_DMA_ATTRS
 	select HAVE_KRETPROBES
 	select HAVE_OPTPROBES
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_C_RECORDMCOUNT
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
@@ -59,6 +62,12 @@
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
+	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_TEXT_POKE_SMP
+	select HAVE_GENERIC_HARDIRQS
+	select HAVE_SPARSE_IRQ
+	select GENERIC_IRQ_PROBE
+	select GENERIC_PENDING_IRQ if SMP
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
@@ -193,27 +202,10 @@
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
-config HAVE_EARLY_RES
-	def_bool y
-
 config HAVE_INTEL_TXT
 	def_bool y
 	depends on EXPERIMENTAL && DMAR && ACPI
 
-# Use the generic interrupt handling code in kernel/irq/:
-config GENERIC_HARDIRQS
-	def_bool y
-
-config GENERIC_HARDIRQS_NO__DO_IRQ
-       def_bool y
-
-config GENERIC_IRQ_PROBE
-	def_bool y
-
-config GENERIC_PENDING_IRQ
-	def_bool y
-	depends on GENERIC_HARDIRQS && SMP
-
 config USE_GENERIC_SMP_HELPERS
 	def_bool y
 	depends on SMP
@@ -296,23 +288,6 @@
 
 	  If you don't know what to do here, say N.
 
-config SPARSE_IRQ
-	bool "Support sparse irq numbering"
-	depends on PCI_MSI || HT_IRQ
-	---help---
-	  This enables support for sparse irqs. This is useful for distro
-	  kernels that want to define a high CONFIG_NR_CPUS value but still
-	  want to have low kernel memory footprint on smaller machines.
-
-	  ( Sparse IRQs can also be beneficial on NUMA boxes, as they spread
-	    out the irq_desc[] array in a more NUMA-friendly way. )
-
-	  If you don't know what to do here, say N.
-
-config NUMA_IRQ_DESC
-	def_bool y
-	depends on SPARSE_IRQ && NUMA
-
 config X86_MPPARSE
 	bool "Enable MPS table" if ACPI
 	default y
@@ -517,25 +492,6 @@
 
 source "arch/x86/xen/Kconfig"
 
-config VMI
-	bool "VMI Guest support (DEPRECATED)"
-	select PARAVIRT
-	depends on X86_32
-	---help---
-	  VMI provides a paravirtualized interface to the VMware ESX server
-	  (it could be used by other hypervisors in theory too, but is not
-	  at the moment), by linking the kernel to a GPL-ed ROM module
-	  provided by the hypervisor.
-
-	  As of September 2009, VMware has started a phased retirement
-	  of this feature from VMware's products. Please see
-	  feature-removal-schedule.txt for details.  If you are
-	  planning to enable this option, please note that you cannot
-	  live migrate a VMI enabled VM to a future VMware product,
-	  which doesn't support VMI. So if you expect your kernel to
-	  seamlessly migrate to newer VMware products, keep this
-	  disabled.
-
 config KVM_CLOCK
 	bool "KVM paravirtualized clock"
 	select PARAVIRT
@@ -590,16 +546,7 @@
 	  a paravirt_op is missing when it is called.
 
 config NO_BOOTMEM
-	default y
-	bool "Disable Bootmem code"
-	---help---
-	  Use early_res directly instead of bootmem before slab is ready.
-		- allocator (buddy) [generic]
-		- early allocator (bootmem) [generic]
-		- very early allocator (reserve_early*()) [x86]
-		- very very early allocator (early brk model) [x86]
-	  So reduce one layer between early allocator to final allocator
-
+	def_bool y
 
 config MEMTEST
 	bool "Memtest"
@@ -670,7 +617,7 @@
 	bool "GART IOMMU support" if EMBEDDED
 	default y
 	select SWIOTLB
-	depends on X86_64 && PCI && K8_NB
+	depends on X86_64 && PCI && AMD_NB
 	---help---
 	  Support for full DMA access of devices with 32bit memory access only
 	  on systems with more than 3GB. This is usually needed for USB,
@@ -795,6 +742,17 @@
 	  making when dealing with multi-core CPU chips at a cost of slightly
 	  increased overhead in some places. If unsure say N here.
 
+config IRQ_TIME_ACCOUNTING
+	bool "Fine granularity task level IRQ time accounting"
+	default n
+	---help---
+	  Select this option to enable fine granularity task irq time
+	  accounting. This is done by reading a timestamp on each
+	  transitions between softirq and hardirq state, so there can be a
+	  small performance impact.
+
+	  If in doubt, say N here.
+
 source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
@@ -1148,6 +1106,9 @@
 config ARCH_PHYS_ADDR_T_64BIT
 	def_bool X86_64 || X86_PAE
 
+config ARCH_DMA_ADDR_T_64BIT
+	def_bool X86_64 || HIGHMEM64G
+
 config DIRECT_GBPAGES
 	bool "Enable 1GB pages for kernel pagetables" if EMBEDDED
 	default y
@@ -1326,25 +1287,34 @@
 	  Set whether the default state of memory_corruption_check is
 	  on or off.
 
-config X86_RESERVE_LOW_64K
-	bool "Reserve low 64K of RAM on AMI/Phoenix BIOSen"
-	default y
+config X86_RESERVE_LOW
+	int "Amount of low memory, in kilobytes, to reserve for the BIOS"
+	default 64
+	range 4 640
 	---help---
-	  Reserve the first 64K of physical RAM on BIOSes that are known
-	  to potentially corrupt that memory range. A numbers of BIOSes are
-	  known to utilize this area during suspend/resume, so it must not
-	  be used by the kernel.
+	  Specify the amount of low memory to reserve for the BIOS.
 
-	  Set this to N if you are absolutely sure that you trust the BIOS
-	  to get all its memory reservations and usages right.
+	  The first page contains BIOS data structures that the kernel
+	  must not use, so that page must always be reserved.
 
-	  If you have doubts about the BIOS (e.g. suspend/resume does not
-	  work or there's kernel crashes after certain hardware hotplug
-	  events) and it's not AMI or Phoenix, then you might want to enable
-	  X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check typical
-	  corruption patterns.
+	  By default we reserve the first 64K of physical RAM, as a
+	  number of BIOSes are known to corrupt that memory range
+	  during events such as suspend/resume or monitor cable
+	  insertion, so it must not be used by the kernel.
 
-	  Say Y if unsure.
+	  You can set this to 4 if you are absolutely sure that you
+	  trust the BIOS to get all its memory reservations and usages
+	  right.  If you know your BIOS have problems beyond the
+	  default 64K area, you can set this to 640 to avoid using the
+	  entire low memory range.
+
+	  If you have doubts about the BIOS (e.g. suspend/resume does
+	  not work or there's kernel crashes after certain hardware
+	  hotplug events) then you might want to enable
+	  X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check
+	  typical corruption patterns.
+
+	  Leave this to the default value of 64 if you are unsure.
 
 config MATH_EMULATION
 	bool
@@ -1900,7 +1870,7 @@
 	bool "Direct"
 
 config PCI_GOOLPC
-	bool "OLPC"
+	bool "OLPC XO-1"
 	depends on OLPC
 
 config PCI_GOANY
@@ -2061,14 +2031,21 @@
 config OLPC
 	bool "One Laptop Per Child support"
 	select GPIOLIB
+	select OLPC_OPENFIRMWARE
 	---help---
 	  Add support for detecting the unique features of the OLPC
 	  XO hardware.
 
+config OLPC_XO1
+	tristate "OLPC XO-1 support"
+	depends on OLPC && PCI
+	---help---
+	  Add support for non-essential features of the OLPC XO-1 laptop.
+
 config OLPC_OPENFIRMWARE
 	bool "Support for OLPC's Open Firmware"
 	depends on !X86_64 && !X86_PAE
-	default y if OLPC
+	default n
 	help
 	  This option adds support for the implementation of Open Firmware
 	  that is used on the OLPC XO-1 Children's Machine.
@@ -2076,7 +2053,7 @@
 
 endif # X86_32
 
-config K8_NB
+config AMD_NB
 	def_bool y
 	depends on CPU_SUP_AMD && PCI
 
@@ -2125,6 +2102,10 @@
 	def_bool y
 	depends on X86_32
 
+config HAVE_TEXT_POKE_SMP
+	bool
+	select STOP_MACHINE if SMP
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 7508508..b59ee76 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -43,6 +43,10 @@
 	  with klogd/syslogd or the X server. You should normally N here,
 	  unless you want to debug such a crash.
 
+config EARLY_PRINTK_MRST
+	bool "Early printk for MRST platform support"
+	depends on EARLY_PRINTK && X86_MRST
+
 config EARLY_PRINTK_DBGP
 	bool "Early printk via EHCI debug port"
 	depends on EARLY_PRINTK && PCI
@@ -121,16 +125,6 @@
 	  and the software setup of this feature.
 	  If in doubt, say "N"
 
-config 4KSTACKS
-	bool "Use 4Kb for kernel stacks instead of 8Kb"
-	depends on X86_32
-	---help---
-	  If you say Y here the kernel will use a 4Kb stacksize for the
-	  kernel stack attached to each process/thread. This facilitates
-	  running more threads on a system and also reduces the pressure
-	  on the VM subsystem for higher order allocations. This option
-	  will also use IRQ stacks to compensate for the reduced stackspace.
-
 config DOUBLEFAULT
 	default y
 	bool "Enable doublefault exception handler" if EMBEDDED
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index e8c8881..b02e509 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -96,8 +96,12 @@
 # is .cfi_signal_frame supported too?
 cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
 cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections)
+
+# does binutils support specific instructions?
+asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+
+KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr)
+KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index bc6abb7..76561d2 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
+#include <linux/jump_label.h>
 #include <asm/asm.h>
 
 /*
@@ -160,6 +161,8 @@
 #define __parainstructions_end	NULL
 #endif
 
+extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
  * Allows the kernel to edit read-only pages.
@@ -180,4 +183,12 @@
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+#define IDEAL_NOP_SIZE_5 5
+extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+extern void arch_init_ideal_nop5(void);
+#else
+static inline void arch_init_ideal_nop5(void) {}
+#endif
+
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index 5af2982..a6863a2 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -24,11 +24,11 @@
 
 #ifdef CONFIG_AMD_IOMMU
 
-extern void amd_iommu_detect(void);
+extern int amd_iommu_detect(void);
 
 #else
 
-static inline void amd_iommu_detect(void) { }
+static inline int amd_iommu_detect(void) { return -ENODEV; }
 
 #endif
 
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index cb03037..916bc81 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2009-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *
  * This program is free software; you can redistribute it and/or modify it
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 0861618..e3509fc 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -416,13 +416,22 @@
 	struct dma_ops_domain *default_dom;
 
 	/*
-	 * This array is required to work around a potential BIOS bug.
-	 * The BIOS may miss to restore parts of the PCI configuration
-	 * space when the system resumes from S3. The result is that the
-	 * IOMMU does not execute commands anymore which leads to system
-	 * failure.
+	 * We can't rely on the BIOS to restore all values on reinit, so we
+	 * need to stash them
 	 */
-	u32 cache_cfg[4];
+
+	/* The iommu BAR */
+	u32 stored_addr_lo;
+	u32 stored_addr_hi;
+
+	/*
+	 * Each iommu has 6 l1s, each of which is documented as having 0x12
+	 * registers
+	 */
+	u32 stored_l1[6][0x12];
+
+	/* The l2 indirect registers */
+	u32 stored_l2[0x83];
 };
 
 /*
diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/amd_nb.h
similarity index 61%
rename from arch/x86/include/asm/k8.h
rename to arch/x86/include/asm/amd_nb.h
index af00bd1..c8517f8 100644
--- a/arch/x86/include/asm/k8.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_K8_H
-#define _ASM_X86_K8_H
+#ifndef _ASM_X86_AMD_NB_H
+#define _ASM_X86_AMD_NB_H
 
 #include <linux/pci.h>
 
@@ -7,24 +7,27 @@
 struct bootnode;
 
 extern int early_is_k8_nb(u32 value);
-extern struct pci_dev **k8_northbridges;
-extern int num_k8_northbridges;
 extern int cache_k8_northbridges(void);
 extern void k8_flush_garts(void);
 extern int k8_get_nodes(struct bootnode *nodes);
 extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn);
 extern int k8_scan_nodes(void);
 
-#ifdef CONFIG_K8_NB
-extern int num_k8_northbridges;
+struct k8_northbridge_info {
+	u16 num;
+	u8 gart_supported;
+	struct pci_dev **nb_misc;
+};
+extern struct k8_northbridge_info k8_northbridges;
+
+#ifdef CONFIG_AMD_NB
 
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
-	return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
+	return (node < k8_northbridges.num) ? k8_northbridges.nb_misc[node] : NULL;
 }
 
 #else
-#define num_k8_northbridges 0
 
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
@@ -33,4 +36,4 @@
 #endif
 
 
-#endif /* _ASM_X86_K8_H */
+#endif /* _ASM_X86_AMD_NB_H */
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index a69b1ac..2fefa50 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -54,7 +54,6 @@
 extern unsigned long apbt_quick_calibrate(void);
 extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
 extern void apbt_setup_secondary_clock(void);
-extern unsigned int boot_cpu_id;
 
 extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
 extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1fa03e0..286de34 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -252,9 +252,7 @@
 }
 #endif
 
-extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
-extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
-
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 7fe3b30..a859ca4 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -131,6 +131,7 @@
 #define APIC_EILVTn(n)	(0x500 + 0x10 * n)
 #define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
 #define		APIC_EILVT_NR_AMD_10H	4
+#define		APIC_EILVT_NR_MAX	APIC_EILVT_NR_AMD_10H
 #define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
 #define		APIC_EILVT_MSG_FIX	0x0
 #define		APIC_EILVT_MSG_SMI	0x2
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index bafd80d..903683b0 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -440,6 +440,8 @@
 
 #ifdef __KERNEL__
 
+#include <asm-generic/bitops/find.h>
+
 #include <asm-generic/bitops/sched.h>
 
 #define ARCH_HAS_FAST_MULTIPLIER 1
diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h
index 0918654..0d467b3 100644
--- a/arch/x86/include/asm/calgary.h
+++ b/arch/x86/include/asm/calgary.h
@@ -62,9 +62,9 @@
 extern int use_calgary;
 
 #ifdef CONFIG_CALGARY_IOMMU
-extern void detect_calgary(void);
+extern int detect_calgary(void);
 #else
-static inline void detect_calgary(void) { return; }
+static inline int detect_calgary(void) { return -ENODEV; }
 #endif
 
 #endif /* _ASM_X86_CALGARY_H */
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index b185091..4fab24d 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -32,6 +32,5 @@
 
 DECLARE_PER_CPU(int, cpu_state);
 
-extern unsigned int boot_cpu_id;
 
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3f76523..220e2ea 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -152,10 +152,14 @@
 #define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
 #define X86_FEATURE_OSVW	(6*32+ 9) /* OS Visible Workaround */
 #define X86_FEATURE_IBS		(6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
+#define X86_FEATURE_XOP		(6*32+11) /* extended AVX instructions */
 #define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP		(6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4	(6*32+16) /* 4 operands MAC instructions */
 #define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -180,6 +184,13 @@
 #define X86_FEATURE_LBRV	(8*32+ 6) /* AMD LBR Virtualization support */
 #define X86_FEATURE_SVML	(8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
 #define X86_FEATURE_NRIPS	(8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 733f7e9..3260991 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -89,6 +89,16 @@
 	CFI_ADJUST_CFA_OFFSET -8
 	.endm
 
+	.macro pushfq_cfi
+	pushfq
+	CFI_ADJUST_CFA_OFFSET 8
+	.endm
+
+	.macro popfq_cfi
+	popfq
+	CFI_ADJUST_CFA_OFFSET -8
+	.endm
+
 	.macro movq_cfi reg offset=0
 	movq %\reg, \offset(%rsp)
 	CFI_REL_OFFSET \reg, \offset
@@ -109,6 +119,16 @@
 	CFI_ADJUST_CFA_OFFSET -4
 	.endm
 
+	.macro pushfl_cfi
+	pushfl
+	CFI_ADJUST_CFA_OFFSET 4
+	.endm
+
+	.macro popfl_cfi
+	popfl
+	CFI_ADJUST_CFA_OFFSET -4
+	.endm
+
 	.macro movl_cfi reg offset=0
 	movl %\reg, \offset(%esp)
 	CFI_REL_OFFSET \reg, \offset
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index ec8a52d..5be1542 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -112,23 +112,13 @@
 }
 #endif
 
-extern unsigned long end_user_pfn;
-
-extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
-extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-#include <linux/early_res.h>
-
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
-extern int e820_find_active_region(const struct e820entry *ei,
-				  unsigned long start_pfn,
-				  unsigned long last_pfn,
-				  unsigned long *ei_startpfn,
-				  unsigned long *ei_endpfn);
-extern void e820_register_active_regions(int nid, unsigned long start_pfn,
-					 unsigned long end_pfn);
-extern u64 e820_hole_size(u64 start, u64 end);
+extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+
+void memblock_x86_fill(void);
+void memblock_find_dma_reserve(void);
+
 extern void finish_e820_parsing(void);
 extern void e820_reserve_resources(void);
 extern void e820_reserve_resources_late(void);
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8406ed7..8e4a165 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -90,7 +90,7 @@
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
-extern void efi_reserve_early(void);
+extern void efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 8e8ec66..b8e96a1 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -49,8 +49,8 @@
 BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
-#ifdef CONFIG_PERF_EVENTS
-BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR)
+#ifdef CONFIG_IRQ_WORK
+BUILD_INTERRUPT(irq_work_interrupt, IRQ_WORK_VECTOR)
 #endif
 
 #ifdef CONFIG_X86_THERMAL_VECTOR
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index d07b44f..4d293dc 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -214,5 +214,20 @@
 	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
 	return __virt_to_fix(vaddr);
 }
+
+/* Return an pointer with offset calculated */
+static inline unsigned long __set_fixmap_offset(enum fixed_addresses idx,
+				phys_addr_t phys, pgprot_t flags)
+{
+	__set_fixmap(idx, phys, flags);
+	return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1));
+}
+
+#define set_fixmap_offset(idx, phys)			\
+	__set_fixmap_offset(idx, phys, PAGE_KERNEL)
+
+#define set_fixmap_offset_nocache(idx, phys)			\
+	__set_fixmap_offset(idx, phys, PAGE_KERNEL_NOCACHE)
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_FIXMAP_H */
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 4ac5b0f..43085bf 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -17,6 +17,7 @@
 #define GARTEN		(1<<0)
 #define DISGARTCPU	(1<<4)
 #define DISGARTIO	(1<<5)
+#define DISTLBWALKPRB	(1<<6)
 
 /* GART cache control register bits. */
 #define INVGART		(1<<0)
@@ -27,7 +28,6 @@
 #define AMD64_GARTAPERTUREBASE	0x94
 #define AMD64_GARTTABLEBASE	0x98
 #define AMD64_GARTCACHECTL	0x9c
-#define AMD64_GARTEN		(1<<0)
 
 #ifdef CONFIG_GART_IOMMU
 extern int gart_iommu_aperture;
@@ -37,7 +37,7 @@
 extern void early_gart_iommu_check(void);
 extern int gart_iommu_init(void);
 extern void __init gart_parse_options(char *);
-extern void gart_iommu_hole_init(void);
+extern int gart_iommu_hole_init(void);
 
 #else
 #define gart_iommu_aperture            0
@@ -50,13 +50,27 @@
 static inline void gart_parse_options(char *options)
 {
 }
-static inline void gart_iommu_hole_init(void)
+static inline int gart_iommu_hole_init(void)
 {
+	return -ENODEV;
 }
 #endif
 
 extern int agp_amd64_init(void);
 
+static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order)
+{
+	u32 ctl;
+
+	/*
+	 * Don't enable translation but enable GART IO and CPU accesses.
+	 * Also, set DISTLBWALKPRB since GART tables memory is UC.
+	 */
+	ctl = DISTLBWALKPRB | order << 1;
+
+	pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+}
+
 static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
 {
 	u32 tmp, ctl;
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index aeab29a..55e4de6 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -14,7 +14,7 @@
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;
-	unsigned int apic_pending_irqs;
+	unsigned int apic_irq_work_irqs;
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 1d5c08a..2c392d6 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,10 +74,12 @@
 extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
-extern void hpet_msi_unmask(unsigned int irq);
-extern void hpet_msi_mask(unsigned int irq);
-extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
-extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
+struct irq_data;
+extern void hpet_msi_unmask(struct irq_data *data);
+extern void hpet_msi_mask(struct irq_data *data);
+struct hpet_dev;
+extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
+extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
 
 #ifdef CONFIG_PCI_MSI
 extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id);
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 46c0fe0..0274ec5 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,7 +29,7 @@
 extern void apic_timer_interrupt(void);
 extern void x86_platform_ipi(void);
 extern void error_interrupt(void);
-extern void perf_pending_interrupt(void);
+extern void irq_work_interrupt(void);
 
 extern void spurious_interrupt(void);
 extern void thermal_interrupt(void);
@@ -78,6 +78,13 @@
 	irq_attr->polarity	= polarity;
 }
 
+struct irq_2_iommu {
+	struct intel_iommu *iommu;
+	u16 irte_index;
+	u16 sub_handle;
+	u8  irte_mask;
+};
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -89,15 +96,17 @@
 	cpumask_var_t		old_domain;
 	u8			vector;
 	u8			move_in_progress : 1;
+#ifdef CONFIG_INTR_REMAP
+	struct irq_2_iommu	irq_2_iommu;
+#endif
 };
 
-extern struct irq_cfg *irq_cfg(unsigned int);
 extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
 extern void send_cleanup_vector(struct irq_cfg *);
 
-struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
-				      unsigned int *dest_id);
+struct irq_data;
+int __ioapic_set_affinity(struct irq_data *, const struct cpumask *,
+			  unsigned int *dest_id);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index a73a8d5..4aa2bb3 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -55,6 +55,12 @@
 extern int restore_i387_xstate_ia32(void __user *buf);
 #endif
 
+#ifdef CONFIG_MATH_EMULATION
+extern void finit_soft_fpu(struct i387_soft_struct *soft);
+#else
+static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
+#endif
+
 #define X87_FSW_ES (1 << 7)	/* Exception Summary */
 
 static __always_inline __pure bool use_xsaveopt(void)
@@ -67,6 +73,11 @@
 	return static_cpu_has(X86_FEATURE_XSAVE);
 }
 
+static __always_inline __pure bool use_fxsr(void)
+{
+        return static_cpu_has(X86_FEATURE_FXSR);
+}
+
 extern void __sanitize_i387_state(struct task_struct *);
 
 static inline void sanitize_i387_state(struct task_struct *tsk)
@@ -77,19 +88,11 @@
 }
 
 #ifdef CONFIG_X86_64
-
-/* Ignore delayed exceptions from user space */
-static inline void tolerant_fwait(void)
-{
-	asm volatile("1: fwait\n"
-		     "2:\n"
-		     _ASM_EXTABLE(1b, 2b));
-}
-
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
 	int err;
 
+	/* See comment in fxsave() below. */
 	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
@@ -98,44 +101,10 @@
 		     ".previous\n"
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err)
-#if 0 /* See comment in fxsave() below. */
-		     : [fx] "r" (fx), "m" (*fx), "0" (0));
-#else
-		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
-#endif
+		     : [fx] "R" (fx), "m" (*fx), "0" (0));
 	return err;
 }
 
-/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
-   is pending. Clear the x87 state here by setting it to fixed
-   values. The kernel data segment can be sometimes 0 and sometimes
-   new user value. Both should be ok.
-   Use the PDA as safe address because it should be already in L1. */
-static inline void fpu_clear(struct fpu *fpu)
-{
-	struct xsave_struct *xstate = &fpu->state->xsave;
-	struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
-	/*
-	 * xsave header may indicate the init state of the FP.
-	 */
-	if (use_xsave() &&
-	    !(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-		return;
-
-	if (unlikely(fx->swd & X87_FSW_ES))
-		asm volatile("fnclex");
-	alternative_input(ASM_NOP8 ASM_NOP2,
-			  "    emms\n"		/* clear stack tags */
-			  "    fildl %%gs:0",	/* load to clear state */
-			  X86_FEATURE_FXSAVE_LEAK);
-}
-
-static inline void clear_fpu_state(struct task_struct *tsk)
-{
-	fpu_clear(&tsk->thread.fpu);
-}
-
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
 	int err;
@@ -149,6 +118,7 @@
 	if (unlikely(err))
 		return -EFAULT;
 
+	/* See comment in fxsave() below. */
 	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
@@ -157,11 +127,7 @@
 		     ".previous\n"
 		     _ASM_EXTABLE(1b, 3b)
 		     : [err] "=r" (err), "=m" (*fx)
-#if 0 /* See comment in fxsave() below. */
-		     : [fx] "r" (fx), "0" (0));
-#else
-		     : [fx] "cdaSDb" (fx), "0" (0));
-#endif
+		     : [fx] "R" (fx), "0" (0));
 	if (unlikely(err) &&
 	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
 		err = -EFAULT;
@@ -175,56 +141,29 @@
 	   uses any extended registers for addressing, a second REX prefix
 	   will be generated (to the assembler, rex64 followed by semicolon
 	   is a separate instruction), and hence the 64-bitness is lost. */
-#if 0
+
+#ifdef CONFIG_AS_FXSAVEQ
 	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
 	   starting with gas 2.16. */
 	__asm__ __volatile__("fxsaveq %0"
 			     : "=m" (fpu->state->fxsave));
-#elif 0
+#else
 	/* Using, as a workaround, the properly prefixed form below isn't
 	   accepted by any binutils version so far released, complaining that
 	   the same type of prefix is used twice if an extended register is
-	   needed for addressing (fix submitted to mainline 2005-11-21). */
-	__asm__ __volatile__("rex64/fxsave %0"
-			     : "=m" (fpu->state->fxsave));
-#else
-	/* This, however, we can work around by forcing the compiler to select
+	   needed for addressing (fix submitted to mainline 2005-11-21).
+	asm volatile("rex64/fxsave %0"
+		     : "=m" (fpu->state->fxsave));
+	   This, however, we can work around by forcing the compiler to select
 	   an addressing mode that doesn't require extended registers. */
-	__asm__ __volatile__("rex64/fxsave (%1)"
-			     : "=m" (fpu->state->fxsave)
-			     : "cdaSDb" (&fpu->state->fxsave));
+	asm volatile("rex64/fxsave (%[fx])"
+		     : "=m" (fpu->state->fxsave)
+		     : [fx] "R" (&fpu->state->fxsave));
 #endif
 }
 
-static inline void fpu_save_init(struct fpu *fpu)
-{
-	if (use_xsave())
-		fpu_xsave(fpu);
-	else
-		fpu_fxsave(fpu);
-
-	fpu_clear(fpu);
-}
-
-static inline void __save_init_fpu(struct task_struct *tsk)
-{
-	fpu_save_init(&tsk->thread.fpu);
-	task_thread_info(tsk)->status &= ~TS_USEDFPU;
-}
-
 #else  /* CONFIG_X86_32 */
 
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-static inline void tolerant_fwait(void)
-{
-	asm volatile("fnclex ; fwait");
-}
-
 /* perform fxrstor iff the processor has extended states, otherwise frstor */
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
@@ -241,6 +180,14 @@
 	return 0;
 }
 
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+	asm volatile("fxsave %[fx]"
+		     : [fx] "=m" (fpu->state->fxsave));
+}
+
+#endif	/* CONFIG_X86_64 */
+
 /* We need a safe address that is cheap to find and that is already
    in L1 during context switch. The best choices are unfortunately
    different for UP and SMP */
@@ -256,47 +203,33 @@
 static inline void fpu_save_init(struct fpu *fpu)
 {
 	if (use_xsave()) {
-		struct xsave_struct *xstate = &fpu->state->xsave;
-		struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
 		fpu_xsave(fpu);
 
 		/*
 		 * xsave header may indicate the init state of the FP.
 		 */
-		if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-			goto end;
-
-		if (unlikely(fx->swd & X87_FSW_ES))
-			asm volatile("fnclex");
-
-		/*
-		 * we can do a simple return here or be paranoid :)
-		 */
-		goto clear_state;
+		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
+			return;
+	} else if (use_fxsr()) {
+		fpu_fxsave(fpu);
+	} else {
+		asm volatile("fsave %[fx]; fwait"
+			     : [fx] "=m" (fpu->state->fsave));
+		return;
 	}
 
-	/* Use more nops than strictly needed in case the compiler
-	   varies code */
-	alternative_input(
-		"fnsave %[fx] ;fwait;" GENERIC_NOP8 GENERIC_NOP4,
-		"fxsave %[fx]\n"
-		"bt $7,%[fsw] ; jnc 1f ; fnclex\n1:",
-		X86_FEATURE_FXSR,
-		[fx] "m" (fpu->state->fxsave),
-		[fsw] "m" (fpu->state->fxsave.swd) : "memory");
-clear_state:
+	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+		asm volatile("fnclex");
+
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. safe_address is a random variable that should be in L1 */
 	alternative_input(
-		GENERIC_NOP8 GENERIC_NOP2,
+		ASM_NOP8 ASM_NOP2,
 		"emms\n\t"	  	/* clear stack tags */
-		"fildl %[addr]", 	/* set F?P to defined value */
+		"fildl %P[addr]",	/* set F?P to defined value */
 		X86_FEATURE_FXSAVE_LEAK,
 		[addr] "m" (safe_address));
-end:
-	;
 }
 
 static inline void __save_init_fpu(struct task_struct *tsk)
@@ -305,9 +238,6 @@
 	task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
-
-#endif	/* CONFIG_X86_64 */
-
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
 {
 	return fxrstor_checking(&fpu->state->fxsave);
@@ -344,7 +274,10 @@
 static inline void __clear_fpu(struct task_struct *tsk)
 {
 	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		tolerant_fwait();
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
 		task_thread_info(tsk)->status &= ~TS_USEDFPU;
 		stts();
 	}
@@ -405,19 +338,6 @@
 		stts();
 }
 
-#ifdef CONFIG_X86_64
-
-static inline void save_init_fpu(struct task_struct *tsk)
-{
-	__save_init_fpu(tsk);
-	stts();
-}
-
-#define unlazy_fpu	__unlazy_fpu
-#define clear_fpu	__clear_fpu
-
-#else  /* CONFIG_X86_32 */
-
 /*
  * These disable preemption on their own and are safe
  */
@@ -443,8 +363,6 @@
 	preempt_enable();
 }
 
-#endif	/* CONFIG_X86_64 */
-
 /*
  * i387 state interaction
  */
@@ -508,7 +426,4 @@
 
 #endif /* __ASSEMBLY__ */
 
-#define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5
-#define PSHUFB_XMM5_XMM6 .byte 0x66, 0x0f, 0x38, 0x00, 0xf5
-
 #endif /* _ASM_X86_I387_H */
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 1655147..a203659 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -55,6 +55,8 @@
 struct legacy_pic {
 	int nr_legacy_irqs;
 	struct irq_chip *chip;
+	void (*mask)(unsigned int irq);
+	void (*unmask)(unsigned int irq);
 	void (*mask_all)(void);
 	void (*restore_mask)(void);
 	void (*init)(int auto_eoi);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 30a3e97..f0203f4 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -206,6 +206,7 @@
 
 extern void iounmap(volatile void __iomem *addr);
 
+extern void set_iounmap_nonlazy(void);
 
 #ifdef __KERNEL__
 
@@ -348,6 +349,7 @@
 				    unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
 extern void fixup_early_ioremap(void);
+extern bool is_early_ioremap_ptep(pte_t *ptep);
 
 #define IO_SPACE_LIMIT 0xffff
 
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 9cb2edb..c8be456 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -170,12 +170,6 @@
 
 extern void probe_nr_irqs_gsi(void);
 
-extern int setup_ioapic_entry(int apic, int irq,
-			      struct IO_APIC_route_entry *entry,
-			      unsigned int destination, int trigger,
-			      int polarity, int vector, int pin);
-extern void ioapic_write_entry(int apic, int pin,
-			       struct IO_APIC_route_entry e);
 extern void setup_ioapic_ids_from_mpc(void);
 
 struct mp_ioapic_gsi{
diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h
new file mode 100644
index 0000000..f229b13
--- /dev/null
+++ b/arch/x86/include/asm/iommu_table.h
@@ -0,0 +1,100 @@
+#ifndef _ASM_X86_IOMMU_TABLE_H
+#define _ASM_X86_IOMMU_TABLE_H
+
+#include <asm/swiotlb.h>
+
+/*
+ * History lesson:
+ * The execution chain of IOMMUs in 2.6.36 looks as so:
+ *
+ *            [xen-swiotlb]
+ *                 |
+ *         +----[swiotlb *]--+
+ *        /         |         \
+ *       /          |          \
+ *    [GART]     [Calgary]  [Intel VT-d]
+ *     /
+ *    /
+ * [AMD-Vi]
+ *
+ * *: if SWIOTLB detected 'iommu=soft'/'swiotlb=force' it would skip
+ * over the rest of IOMMUs and unconditionally initialize the SWIOTLB.
+ * Also it would surreptitiously initialize set the swiotlb=1 if there were
+ * more than 4GB and if the user did not pass in 'iommu=off'. The swiotlb
+ * flag would be turned off by all IOMMUs except the Calgary one.
+ *
+ * The IOMMU_INIT* macros allow a similar tree (or more complex if desired)
+ * to be built by defining who we depend on.
+ *
+ * And all that needs to be done is to use one of the macros in the IOMMU
+ * and the pci-dma.c will take care of the rest.
+ */
+
+struct iommu_table_entry {
+	initcall_t	detect;
+	initcall_t	depend;
+	void		(*early_init)(void); /* No memory allocate available. */
+	void		(*late_init)(void); /* Yes, can allocate memory. */
+#define IOMMU_FINISH_IF_DETECTED (1<<0)
+#define IOMMU_DETECTED		 (1<<1)
+	int		flags;
+};
+/*
+ * Macro fills out an entry in the .iommu_table that is equivalent
+ * to the fields that 'struct iommu_table_entry' has. The entries
+ * that are put in the .iommu_table section are not put in any order
+ * hence during boot-time we will have to resort them based on
+ * dependency. */
+
+
+#define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\
+	static const struct iommu_table_entry const			\
+		__iommu_entry_##_detect __used				\
+	__attribute__ ((unused, __section__(".iommu_table"),		\
+			aligned((sizeof(void *)))))	\
+	= {_detect, _depend, _early_init, _late_init,			\
+	   _finish ? IOMMU_FINISH_IF_DETECTED : 0}
+/*
+ * The simplest IOMMU definition. Provide the detection routine
+ * and it will be run after the SWIOTLB and the other IOMMUs
+ * that utilize this macro. If the IOMMU is detected (ie, the
+ * detect routine returns a positive value), the other IOMMUs
+ * are also checked. You can use IOMMU_INIT_POST_FINISH if you prefer
+ * to stop detecting the other IOMMUs after yours has been detected.
+ */
+#define IOMMU_INIT_POST(_detect)					\
+	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  0, 0, 0)
+
+#define IOMMU_INIT_POST_FINISH(detect)					\
+	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  0, 0, 1)
+
+/*
+ * A more sophisticated version of IOMMU_INIT. This variant requires:
+ *  a). A detection routine function.
+ *  b). The name of the detection routine we depend on to get called
+ *      before us.
+ *  c). The init routine which gets called if the detection routine
+ *      returns a positive value from the pci_iommu_alloc. This means
+ *      no presence of a memory allocator.
+ *  d). Similar to the 'init', except that this gets called from pci_iommu_init
+ *      where we do have a memory allocator.
+ *
+ * The standard vs the _FINISH differs in that the _FINISH variant will
+ * continue detecting other IOMMUs in the call list after the
+ * the detection routine returns a positive number. The _FINISH will
+ * stop the execution chain. Both will still call the 'init' and
+ * 'late_init' functions if they are set.
+ */
+#define IOMMU_INIT_FINISH(_detect, _depend, _init, _late_init)		\
+	__IOMMU_INIT(_detect, _depend, _init, _late_init, 1)
+
+#define IOMMU_INIT(_detect, _depend, _init, _late_init)			\
+	__IOMMU_INIT(_detect, _depend, _init, _late_init, 0)
+
+void sort_iommu_table(struct iommu_table_entry *start,
+		      struct iommu_table_entry *finish);
+
+void check_iommu_entries(struct iommu_table_entry *start,
+			 struct iommu_table_entry *finish);
+
+#endif /* _ASM_X86_IOMMU_TABLE_H */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 5458380..0bf5b00 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -19,18 +19,16 @@
 # define ARCH_HAS_NMI_WATCHDOG
 #endif
 
-#ifdef CONFIG_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
+#ifdef CONFIG_X86_32
+extern void irq_ctx_init(int cpu);
+extern void irq_ctx_exit(int cpu);
 #else
 # define irq_ctx_init(cpu) do { } while (0)
 # define irq_ctx_exit(cpu) do { } while (0)
-# ifdef CONFIG_X86_64
-#  define __ARCH_HAS_DO_SOFTIRQ
-# endif
 #endif
 
+#define __ARCH_HAS_DO_SOFTIRQ
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(void);
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index f275e22..1c23360 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -3,4 +3,39 @@
 
 #define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
+#ifdef CONFIG_INTR_REMAP
+static inline void prepare_irte(struct irte *irte, int vector,
+			        unsigned int dest)
+{
+	memset(irte, 0, sizeof(*irte));
+
+	irte->present = 1;
+	irte->dst_mode = apic->irq_dest_mode;
+	/*
+	 * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
+	 * actual level or edge trigger will be setup in the IO-APIC
+	 * RTE. This will help simplify level triggered irq migration.
+	 * For more details, see the comments (in io_apic.c) explainig IO-APIC
+	 * irq migration in the presence of interrupt-remapping.
+	*/
+	irte->trigger_mode = 0;
+	irte->dlvry_mode = apic->irq_delivery_mode;
+	irte->vector = vector;
+	irte->dest_id = IRTE_DEST(dest);
+	irte->redir_hint = 1;
+}
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+	return cfg->irq_2_iommu.iommu != NULL;
+}
+#else
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
+{
+}
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+	return false;
+}
+#endif
+
 #endif	/* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index e2ca300..6af0894 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -114,9 +114,9 @@
 #define X86_PLATFORM_IPI_VECTOR		0xed
 
 /*
- * Performance monitoring pending work vector:
+ * IRQ work vector:
  */
-#define LOCAL_PENDING_VECTOR		0xec
+#define IRQ_WORK_VECTOR			0xec
 
 #define UV_BAU_MESSAGE			0xea
 
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 9e2b952..5745ce8 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -61,22 +61,22 @@
 #else
 #ifndef __ASSEMBLY__
 
-static inline unsigned long __raw_local_save_flags(void)
+static inline unsigned long arch_local_save_flags(void)
 {
 	return native_save_fl();
 }
 
-static inline void raw_local_irq_restore(unsigned long flags)
+static inline void arch_local_irq_restore(unsigned long flags)
 {
 	native_restore_fl(flags);
 }
 
-static inline void raw_local_irq_disable(void)
+static inline void arch_local_irq_disable(void)
 {
 	native_irq_disable();
 }
 
-static inline void raw_local_irq_enable(void)
+static inline void arch_local_irq_enable(void)
 {
 	native_irq_enable();
 }
@@ -85,7 +85,7 @@
  * Used in the idle loop; sti takes one instruction cycle
  * to complete:
  */
-static inline void raw_safe_halt(void)
+static inline void arch_safe_halt(void)
 {
 	native_safe_halt();
 }
@@ -102,12 +102,10 @@
 /*
  * For spinlocks, etc:
  */
-static inline unsigned long __raw_local_irq_save(void)
+static inline unsigned long arch_local_irq_save(void)
 {
-	unsigned long flags = __raw_local_save_flags();
-
-	raw_local_irq_disable();
-
+	unsigned long flags = arch_local_save_flags();
+	arch_local_irq_disable();
 	return flags;
 }
 #else
@@ -153,22 +151,16 @@
 #endif /* CONFIG_PARAVIRT */
 
 #ifndef __ASSEMBLY__
-#define raw_local_save_flags(flags)				\
-	do { (flags) = __raw_local_save_flags(); } while (0)
-
-#define raw_local_irq_save(flags)				\
-	do { (flags) = __raw_local_irq_save(); } while (0)
-
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !(flags & X86_EFLAGS_IF);
 }
 
-static inline int raw_irqs_disabled(void)
+static inline int arch_irqs_disabled(void)
 {
-	unsigned long flags = __raw_local_save_flags();
+	unsigned long flags = arch_local_save_flags();
 
-	return raw_irqs_disabled_flags(flags);
+	return arch_irqs_disabled_flags(flags);
 }
 
 #else
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
new file mode 100644
index 0000000..f52d42e
--- /dev/null
+++ b/arch/x86/include/asm/jump_label.h
@@ -0,0 +1,37 @@
+#ifndef _ASM_X86_JUMP_LABEL_H
+#define _ASM_X86_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/nops.h>
+
+#define JUMP_LABEL_NOP_SIZE 5
+
+# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+
+# define JUMP_LABEL(key, label)					\
+	do {							\
+		asm goto("1:"					\
+			JUMP_LABEL_INITIAL_NOP			\
+			".pushsection __jump_table,  \"a\" \n\t"\
+			_ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
+			".popsection \n\t"			\
+			: :  "i" (key) :  : label);		\
+	} while (0)
+
+#endif /* __KERNEL__ */
+
+#ifdef CONFIG_X86_64
+typedef u64 jump_label_t;
+#else
+typedef u32 jump_label_t;
+#endif
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif
diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h
new file mode 100644
index 0000000..19ae14b
--- /dev/null
+++ b/arch/x86/include/asm/memblock.h
@@ -0,0 +1,23 @@
+#ifndef _X86_MEMBLOCK_H
+#define _X86_MEMBLOCK_H
+
+#define ARCH_DISCARD_MEMBLOCK
+
+u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
+void memblock_x86_to_bootmem(u64 start, u64 end);
+
+void memblock_x86_reserve_range(u64 start, u64 end, char *name);
+void memblock_x86_free_range(u64 start, u64 end);
+struct range;
+int __get_free_all_memory_range(struct range **range, int nodeid,
+			 unsigned long start_pfn, unsigned long end_pfn);
+int get_free_all_memory_range(struct range **rangep, int nodeid);
+
+void memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn);
+u64 memblock_x86_hole_size(u64 start, u64 end);
+u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
+u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
+u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
+
+#endif
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 3e2ce58..67763c5 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -60,12 +60,7 @@
 #endif
 
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_4KSTACKS
-#  define MODULE_STACKSIZE "4KSTACKS "
-# else
-#  define MODULE_STACKSIZE ""
-# endif
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
 #endif
 
 #endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 1635074..4a711a6 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -10,6 +10,9 @@
  */
 #ifndef _ASM_X86_MRST_H
 #define _ASM_X86_MRST_H
+
+#include <linux/sfi.h>
+
 extern int pci_mrst_init(void);
 int __init sfi_parse_mrtc(struct sfi_table_header *table);
 
@@ -26,7 +29,7 @@
 };
 
 extern enum mrst_cpu_type __mrst_cpu_chip;
-static enum mrst_cpu_type mrst_identify_cpu(void)
+static inline enum mrst_cpu_type mrst_identify_cpu(void)
 {
 	return __mrst_cpu_chip;
 }
@@ -42,4 +45,9 @@
 #define SFI_MTMR_MAX_NUM 8
 #define SFI_MRTC_MAX	8
 
+extern struct console early_mrst_console;
+extern void mrst_early_console_init(void);
+
+extern struct console early_hsu_console;
+extern void hsu_early_console_init(void);
 #endif /* _ASM_X86_MRST_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
new file mode 100644
index 0000000..bcdff99
--- /dev/null
+++ b/arch/x86/include/asm/mwait.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_X86_MWAIT_H
+#define _ASM_X86_MWAIT_H
+
+#define MWAIT_SUBSTATE_MASK		0xf
+#define MWAIT_CSTATE_MASK		0xf
+#define MWAIT_SUBSTATE_SIZE		4
+#define MWAIT_MAX_NUM_CSTATES		8
+
+#define CPUID_MWAIT_LEAF		5
+#define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1
+#define CPUID5_ECX_INTERRUPT_BREAK	0x2
+
+#define MWAIT_ECX_INTERRUPT_BREAK	0x1
+
+#endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h
index 08fde47..2a84781 100644
--- a/arch/x86/include/asm/olpc_ofw.h
+++ b/arch/x86/include/asm/olpc_ofw.h
@@ -21,10 +21,14 @@
 /* install OFW's pde permanently into the kernel's pgtable */
 extern void setup_olpc_ofw_pgd(void);
 
+/* check if OFW was detected during boot */
+extern bool olpc_ofw_present(void);
+
 #else /* !CONFIG_OLPC_OPENFIRMWARE */
 
 static inline void olpc_ofw_detect(void) { }
 static inline void setup_olpc_ofw_pgd(void) { }
+static inline bool olpc_ofw_present(void) { return false; }
 
 #endif /* !CONFIG_OLPC_OPENFIRMWARE */
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 6f1b733..ade619f 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -15,11 +15,7 @@
  */
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
-#ifdef CONFIG_4KSTACKS
-#define THREAD_ORDER	0
-#else
 #define THREAD_ORDER	1
-#endif
 #define THREAD_SIZE 	(PAGE_SIZE << THREAD_ORDER)
 
 #define STACKFAULT_STACK 0
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index a667f24..1df6621 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -8,7 +8,7 @@
 #define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 
-#define __PHYSICAL_MASK		((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __PHYSICAL_MASK		((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
 #define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
 
 /* Cast PAGE_MASK to a signed type so that it is sign-extended if
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5653f43..18e3b8a 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -105,7 +105,7 @@
 }
 #endif
 
-static inline void raw_safe_halt(void)
+static inline void arch_safe_halt(void)
 {
 	PVOP_VCALL0(pv_irq_ops.safe_halt);
 }
@@ -416,11 +416,6 @@
 	PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
 }
 
-static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
-					    unsigned long start, unsigned long count)
-{
-	PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
-}
 static inline void paravirt_release_pmd(unsigned long pfn)
 {
 	PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
@@ -829,32 +824,32 @@
 #define __PV_IS_CALLEE_SAVE(func)			\
 	((struct paravirt_callee_save) { func })
 
-static inline unsigned long __raw_local_save_flags(void)
+static inline unsigned long arch_local_save_flags(void)
 {
 	return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
 }
 
-static inline void raw_local_irq_restore(unsigned long f)
+static inline void arch_local_irq_restore(unsigned long f)
 {
 	PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
 }
 
-static inline void raw_local_irq_disable(void)
+static inline void arch_local_irq_disable(void)
 {
 	PVOP_VCALLEE0(pv_irq_ops.irq_disable);
 }
 
-static inline void raw_local_irq_enable(void)
+static inline void arch_local_irq_enable(void)
 {
 	PVOP_VCALLEE0(pv_irq_ops.irq_enable);
 }
 
-static inline unsigned long __raw_local_irq_save(void)
+static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long f;
 
-	f = __raw_local_save_flags();
-	raw_local_irq_disable();
+	f = arch_local_save_flags();
+	arch_local_irq_disable();
 	return f;
 }
 
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index db9ef55..b82bac9 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -255,7 +255,6 @@
 	 */
 	void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
 	void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
-	void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
 	void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
 	void (*release_pte)(unsigned long pfn);
 	void (*release_pmd)(unsigned long pfn);
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index cd28f9a..f899e01 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -47,6 +47,20 @@
 #ifdef CONFIG_SMP
 #define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x
 #define __my_cpu_offset		percpu_read(this_cpu_off)
+
+/*
+ * Compared to the generic __my_cpu_offset version, the following
+ * saves one instruction and avoids clobbering a temp register.
+ */
+#define __this_cpu_ptr(ptr)				\
+({							\
+	unsigned long tcp_ptr__;			\
+	__verify_pcpu_ptr(ptr);				\
+	asm volatile("add " __percpu_arg(1) ", %0"	\
+		     : "=r" (tcp_ptr__)			\
+		     : "m" (this_cpu_off), "0" (ptr));	\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
+})
 #else
 #define __percpu_arg(x)		"%P" #x
 #endif
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index def5007..a70cd21 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -36,19 +36,6 @@
 #define P4_ESCR_EMASK(v)	((v) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_TAG(v)		((v) << P4_ESCR_TAG_SHIFT)
 
-/* Non HT mask */
-#define P4_ESCR_MASK			\
-	(P4_ESCR_EVENT_MASK	|	\
-	P4_ESCR_EVENTMASK_MASK	|	\
-	P4_ESCR_TAG_MASK	|	\
-	P4_ESCR_TAG_ENABLE	|	\
-	P4_ESCR_T0_OS		|	\
-	P4_ESCR_T0_USR)
-
-/* HT mask */
-#define P4_ESCR_MASK_HT			\
-	(P4_ESCR_MASK |	P4_ESCR_T1_OS | P4_ESCR_T1_USR)
-
 #define P4_CCCR_OVF			0x80000000U
 #define P4_CCCR_CASCADE			0x40000000U
 #define P4_CCCR_OVF_PMI_T0		0x04000000U
@@ -70,23 +57,6 @@
 #define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
 #define P4_CCCR_ESEL(v)			((v) << P4_CCCR_ESCR_SELECT_SHIFT)
 
-/* Non HT mask */
-#define P4_CCCR_MASK				\
-	(P4_CCCR_OVF			|	\
-	P4_CCCR_CASCADE			|	\
-	P4_CCCR_OVF_PMI_T0		|	\
-	P4_CCCR_FORCE_OVF		|	\
-	P4_CCCR_EDGE			|	\
-	P4_CCCR_THRESHOLD_MASK		|	\
-	P4_CCCR_COMPLEMENT		|	\
-	P4_CCCR_COMPARE			|	\
-	P4_CCCR_ESCR_SELECT_MASK	|	\
-	P4_CCCR_ENABLE)
-
-/* HT mask */
-#define P4_CCCR_MASK_HT				\
-	(P4_CCCR_MASK | P4_CCCR_OVF_PMI_T1 | P4_CCCR_THREAD_ANY)
-
 #define P4_GEN_ESCR_EMASK(class, name, bit)	\
 	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_EMASK_BIT(class, name)		class##__##name
@@ -127,6 +97,28 @@
 #define P4_CONFIG_HT_SHIFT		63
 #define P4_CONFIG_HT			(1ULL << P4_CONFIG_HT_SHIFT)
 
+/*
+ * The bits we allow to pass for RAW events
+ */
+#define P4_CONFIG_MASK_ESCR		\
+	P4_ESCR_EVENT_MASK	|	\
+	P4_ESCR_EVENTMASK_MASK	|	\
+	P4_ESCR_TAG_MASK	|	\
+	P4_ESCR_TAG_ENABLE
+
+#define P4_CONFIG_MASK_CCCR		\
+	P4_CCCR_EDGE		|	\
+	P4_CCCR_THRESHOLD_MASK	|	\
+	P4_CCCR_COMPLEMENT	|	\
+	P4_CCCR_COMPARE		|	\
+	P4_CCCR_THREAD_ANY	|	\
+	P4_CCCR_RESERVED
+
+/* some dangerous bits are reserved for kernel internals */
+#define P4_CONFIG_MASK				  	  \
+	(p4_config_pack_escr(P4_CONFIG_MASK_ESCR))	| \
+	(p4_config_pack_cccr(P4_CONFIG_MASK_CCCR))
+
 static inline bool p4_is_event_cascaded(u64 config)
 {
 	u32 cccr = p4_config_unpack_cccr(config);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index a34c785..ada823a 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,6 +28,8 @@
 extern spinlock_t pgd_lock;
 extern struct list_head pgd_list;
 
+extern struct mm_struct *pgd_page_get_mm(struct page *page);
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT */
@@ -603,6 +605,8 @@
 	pte_update(mm, addr, ptep);
 }
 
+#define flush_tlb_fix_spurious_fault(vma, address)
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 076052c..f96ac9b 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -102,6 +102,8 @@
 	native_set_pgd(pgd, native_make_pgd(0));
 }
 
+extern void sync_global_pgds(unsigned long start, unsigned long end);
+
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 325b7bd..cae9c3c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -110,6 +110,8 @@
 	u16			phys_proc_id;
 	/* Core id: */
 	u16			cpu_core_id;
+	/* Compute unit id */
+	u8			compute_unit_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 #endif
@@ -602,7 +604,7 @@
 
 static inline void set_in_cr4(unsigned long mask)
 {
-	unsigned cr4;
+	unsigned long cr4;
 
 	mmu_cr4_features |= mask;
 	cr4 = read_cr4();
@@ -612,7 +614,7 @@
 
 static inline void clear_in_cr4(unsigned long mask)
 {
-	unsigned cr4;
+	unsigned long cr4;
 
 	mmu_cr4_features &= ~mask;
 	cr4 = read_cr4();
@@ -764,29 +766,6 @@
 extern unsigned long		idle_nomwait;
 extern bool			c1e_detected;
 
-/*
- * on systems with caches, caches must be flashed as the absolute
- * last instruction before going into a suspended halt.  Otherwise,
- * dirty data can linger in the cache and become stale on resume,
- * leading to strange errors.
- *
- * perform a variety of operations to guarantee that the compiler
- * will not reorder instructions.  wbinvd itself is serializing
- * so the processor will not reorder.
- *
- * Systems without cache can just go into halt.
- */
-static inline void wbinvd_halt(void)
-{
-	mb();
-	/* check for clflush to determine if wbinvd is legal */
-	if (cpu_has_clflush)
-		asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
-	else
-		while (1)
-			halt();
-}
-
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ef292c7..d6763b139a 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -93,6 +93,11 @@
 			: : "i" (sz));					\
 	}
 
+/* Helper for reserving space for arrays of things */
+#define RESERVE_BRK_ARRAY(type, name, entries)		\
+	type *name;					\
+	RESERVE_BRK(name, sizeof(type) * entries)
+
 #ifdef __i386__
 
 void __init i386_start_kernel(void);
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index 8085277..977f176 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -5,17 +5,26 @@
 
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
-extern int __init pci_swiotlb_detect(void);
+extern int __init pci_swiotlb_detect_override(void);
+extern int __init pci_swiotlb_detect_4gb(void);
 extern void __init pci_swiotlb_init(void);
+extern void __init pci_swiotlb_late_init(void);
 #else
 #define swiotlb 0
-static inline int pci_swiotlb_detect(void)
+static inline int pci_swiotlb_detect_override(void)
+{
+	return 0;
+}
+static inline int pci_swiotlb_detect_4gb(void)
 {
 	return 0;
 }
 static inline void pci_swiotlb_init(void)
 {
 }
+static inline void pci_swiotlb_late_init(void)
+{
+}
 #endif
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
diff --git a/arch/x86/include/asm/vmi.h b/arch/x86/include/asm/vmi.h
deleted file mode 100644
index 61e08c0..0000000
--- a/arch/x86/include/asm/vmi.h
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * VMI interface definition
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Maintained by: Zachary Amsden zach@vmware.com
- *
- */
-#include <linux/types.h>
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI Option ROM API
- *
- *---------------------------------------------------------------------
- */
-#define VMI_SIGNATURE 0x696d5663   /* "cVmi" */
-
-#define PCI_VENDOR_ID_VMWARE            0x15AD
-#define PCI_DEVICE_ID_VMWARE_VMI        0x0801
-
-/*
- * We use two version numbers for compatibility, with the major
- * number signifying interface breakages, and the minor number
- * interface extensions.
- */
-#define VMI_API_REV_MAJOR       3
-#define VMI_API_REV_MINOR       0
-
-#define VMI_CALL_CPUID			0
-#define VMI_CALL_WRMSR			1
-#define VMI_CALL_RDMSR			2
-#define VMI_CALL_SetGDT			3
-#define VMI_CALL_SetLDT			4
-#define VMI_CALL_SetIDT			5
-#define VMI_CALL_SetTR			6
-#define VMI_CALL_GetGDT			7
-#define VMI_CALL_GetLDT			8
-#define VMI_CALL_GetIDT			9
-#define VMI_CALL_GetTR			10
-#define VMI_CALL_WriteGDTEntry		11
-#define VMI_CALL_WriteLDTEntry		12
-#define VMI_CALL_WriteIDTEntry		13
-#define VMI_CALL_UpdateKernelStack	14
-#define VMI_CALL_SetCR0			15
-#define VMI_CALL_SetCR2			16
-#define VMI_CALL_SetCR3			17
-#define VMI_CALL_SetCR4			18
-#define VMI_CALL_GetCR0			19
-#define VMI_CALL_GetCR2			20
-#define VMI_CALL_GetCR3			21
-#define VMI_CALL_GetCR4			22
-#define VMI_CALL_WBINVD			23
-#define VMI_CALL_SetDR			24
-#define VMI_CALL_GetDR			25
-#define VMI_CALL_RDPMC			26
-#define VMI_CALL_RDTSC			27
-#define VMI_CALL_CLTS			28
-#define VMI_CALL_EnableInterrupts	29
-#define VMI_CALL_DisableInterrupts	30
-#define VMI_CALL_GetInterruptMask	31
-#define VMI_CALL_SetInterruptMask	32
-#define VMI_CALL_IRET			33
-#define VMI_CALL_SYSEXIT		34
-#define VMI_CALL_Halt			35
-#define VMI_CALL_Reboot			36
-#define VMI_CALL_Shutdown		37
-#define VMI_CALL_SetPxE			38
-#define VMI_CALL_SetPxELong		39
-#define VMI_CALL_UpdatePxE		40
-#define VMI_CALL_UpdatePxELong		41
-#define VMI_CALL_MachineToPhysical	42
-#define VMI_CALL_PhysicalToMachine	43
-#define VMI_CALL_AllocatePage		44
-#define VMI_CALL_ReleasePage		45
-#define VMI_CALL_InvalPage		46
-#define VMI_CALL_FlushTLB		47
-#define VMI_CALL_SetLinearMapping	48
-
-#define VMI_CALL_SetIOPLMask		61
-#define VMI_CALL_SetInitialAPState	62
-#define VMI_CALL_APICWrite		63
-#define VMI_CALL_APICRead		64
-#define VMI_CALL_IODelay		65
-#define VMI_CALL_SetLazyMode		73
-
-/*
- *---------------------------------------------------------------------
- *
- * MMU operation flags
- *
- *---------------------------------------------------------------------
- */
-
-/* Flags used by VMI_{Allocate|Release}Page call */
-#define VMI_PAGE_PAE             0x10  /* Allocate PAE shadow */
-#define VMI_PAGE_CLONE           0x20  /* Clone from another shadow */
-#define VMI_PAGE_ZEROED          0x40  /* Page is pre-zeroed */
-
-
-/* Flags shared by Allocate|Release Page and PTE updates */
-#define VMI_PAGE_PT              0x01
-#define VMI_PAGE_PD              0x02
-#define VMI_PAGE_PDP             0x04
-#define VMI_PAGE_PML4            0x08
-
-#define VMI_PAGE_NORMAL          0x00 /* for debugging */
-
-/* Flags used by PTE updates */
-#define VMI_PAGE_CURRENT_AS      0x10 /* implies VMI_PAGE_VA_MASK is valid */
-#define VMI_PAGE_DEFER           0x20 /* may queue update until TLB inval */
-#define VMI_PAGE_VA_MASK         0xfffff000
-
-#ifdef CONFIG_X86_PAE
-#define VMI_PAGE_L1		(VMI_PAGE_PT | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2		(VMI_PAGE_PD | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#else
-#define VMI_PAGE_L1		(VMI_PAGE_PT | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2		(VMI_PAGE_PD | VMI_PAGE_ZEROED)
-#endif
-
-/* Flags used by VMI_FlushTLB call */
-#define VMI_FLUSH_TLB            0x01
-#define VMI_FLUSH_GLOBAL         0x02
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI relocation definitions for ROM call get_reloc
- *
- *---------------------------------------------------------------------
- */
-
-/* VMI Relocation types */
-#define VMI_RELOCATION_NONE     0
-#define VMI_RELOCATION_CALL_REL 1
-#define VMI_RELOCATION_JUMP_REL 2
-#define VMI_RELOCATION_NOP	3
-
-#ifndef __ASSEMBLY__
-struct vmi_relocation_info {
-	unsigned char           *eip;
-	unsigned char           type;
-	unsigned char           reserved[3];
-};
-#endif
-
-
-/*
- *---------------------------------------------------------------------
- *
- *  Generic ROM structures and definitions
- *
- *---------------------------------------------------------------------
- */
-
-#ifndef __ASSEMBLY__
-
-struct vrom_header {
-	u16     rom_signature;  /* option ROM signature */
-	u8      rom_length;     /* ROM length in 512 byte chunks */
-	u8      rom_entry[4];   /* 16-bit code entry point */
-	u8      rom_pad0;       /* 4-byte align pad */
-	u32     vrom_signature; /* VROM identification signature */
-	u8      api_version_min;/* Minor version of API */
-	u8      api_version_maj;/* Major version of API */
-	u8      jump_slots;     /* Number of jump slots */
-	u8      reserved1;      /* Reserved for expansion */
-	u32     virtual_top;    /* Hypervisor virtual address start */
-	u16     reserved2;      /* Reserved for expansion */
-	u16	license_offs;	/* Offset to License string */
-	u16     pci_header_offs;/* Offset to PCI OPROM header */
-	u16     pnp_header_offs;/* Offset to PnP OPROM header */
-	u32     rom_pad3;       /* PnP reserverd / VMI reserved */
-	u8      reserved[96];   /* Reserved for headers */
-	char    vmi_init[8];    /* VMI_Init jump point */
-	char    get_reloc[8];   /* VMI_GetRelocationInfo jump point */
-} __attribute__((packed));
-
-struct pnp_header {
-	char sig[4];
-	char rev;
-	char size;
-	short next;
-	short res;
-	long devID;
-	unsigned short manufacturer_offset;
-	unsigned short product_offset;
-} __attribute__((packed));
-
-struct pci_header {
-	char sig[4];
-	short vendorID;
-	short deviceID;
-	short vpdData;
-	short size;
-	char rev;
-	char class;
-	char subclass;
-	char interface;
-	short chunks;
-	char rom_version_min;
-	char rom_version_maj;
-	char codetype;
-	char lastRom;
-	short reserved;
-} __attribute__((packed));
-
-/* Function prototypes for bootstrapping */
-#ifdef CONFIG_VMI
-extern void vmi_init(void);
-extern void vmi_activate(void);
-extern void vmi_bringup(void);
-#else
-static inline void vmi_init(void) {}
-static inline void vmi_activate(void) {}
-static inline void vmi_bringup(void) {}
-#endif
-
-/* State needed to start an application processor in an SMP system. */
-struct vmi_ap_state {
-	u32 cr0;
-	u32 cr2;
-	u32 cr3;
-	u32 cr4;
-
-	u64 efer;
-
-	u32 eip;
-	u32 eflags;
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-	u32 esp;
-	u32 ebp;
-	u32 esi;
-	u32 edi;
-	u16 cs;
-	u16 ss;
-	u16 ds;
-	u16 es;
-	u16 fs;
-	u16 gs;
-	u16 ldtr;
-
-	u16 gdtr_limit;
-	u32 gdtr_base;
-	u32 idtr_base;
-	u16 idtr_limit;
-};
-
-#endif
diff --git a/arch/x86/include/asm/vmi_time.h b/arch/x86/include/asm/vmi_time.h
deleted file mode 100644
index c6e0bee..0000000
--- a/arch/x86/include/asm/vmi_time.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * VMI Time wrappers
- *
- * Copyright (C) 2006, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to dhecht@vmware.com
- *
- */
-
-#ifndef _ASM_X86_VMI_TIME_H
-#define _ASM_X86_VMI_TIME_H
-
-/*
- * Raw VMI call indices for timer functions
- */
-#define VMI_CALL_GetCycleFrequency	66
-#define VMI_CALL_GetCycleCounter	67
-#define VMI_CALL_SetAlarm		68
-#define VMI_CALL_CancelAlarm		69
-#define VMI_CALL_GetWallclockTime	70
-#define VMI_CALL_WallclockUpdated	71
-
-/* Cached VMI timer operations */
-extern struct vmi_timer_ops {
-	u64 (*get_cycle_frequency)(void);
-	u64 (*get_cycle_counter)(int);
-	u64 (*get_wallclock)(void);
-	int (*wallclock_updated)(void);
-	void (*set_alarm)(u32 flags, u64 expiry, u64 period);
-	void (*cancel_alarm)(u32 flags);
-} vmi_timer_ops;
-
-/* Prototypes */
-extern void __init vmi_time_init(void);
-extern unsigned long vmi_get_wallclock(void);
-extern int vmi_set_wallclock(unsigned long now);
-extern unsigned long long vmi_sched_clock(void);
-extern unsigned long vmi_tsc_khz(void);
-
-#ifdef CONFIG_X86_LOCAL_APIC
-extern void __devinit vmi_time_bsp_init(void);
-extern void __devinit vmi_time_ap_init(void);
-#endif
-
-/*
- * When run under a hypervisor, a vcpu is always in one of three states:
- * running, halted, or ready.  The vcpu is in the 'running' state if it
- * is executing.  When the vcpu executes the halt interface, the vcpu
- * enters the 'halted' state and remains halted until there is some work
- * pending for the vcpu (e.g. an alarm expires, host I/O completes on
- * behalf of virtual I/O).  At this point, the vcpu enters the 'ready'
- * state (waiting for the hypervisor to reschedule it).  Finally, at any
- * time when the vcpu is not in the 'running' state nor the 'halted'
- * state, it is in the 'ready' state.
- *
- * Real time is advances while the vcpu is 'running', 'ready', or
- * 'halted'.  Stolen time is the time in which the vcpu is in the
- * 'ready' state.  Available time is the remaining time -- the vcpu is
- * either 'running' or 'halted'.
- *
- * All three views of time are accessible through the VMI cycle
- * counters.
- */
-
-/* The cycle counters. */
-#define VMI_CYCLES_REAL         0
-#define VMI_CYCLES_AVAILABLE    1
-#define VMI_CYCLES_STOLEN       2
-
-/* The alarm interface 'flags' bits */
-#define VMI_ALARM_COUNTERS      2
-
-#define VMI_ALARM_COUNTER_MASK  0x000000ff
-
-#define VMI_ALARM_WIRED_IRQ0    0x00000000
-#define VMI_ALARM_WIRED_LVTT    0x00010000
-
-#define VMI_ALARM_IS_ONESHOT    0x00000000
-#define VMI_ALARM_IS_PERIODIC   0x00000100
-
-#define CONFIG_VMI_ALARM_HZ	100
-
-#endif /* _ASM_X86_VMI_TIME_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index fedf32a..2c833d8 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -34,7 +34,8 @@
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o x86_init.o i8259.o irqinit.o
+obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
+obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
@@ -44,6 +45,7 @@
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
+obj-y			+= pci-iommu_table.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
@@ -85,15 +87,15 @@
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_VM86)		+= vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+obj-$(CONFIG_EARLY_PRINTK_MRST)	+= early_printk_mrst.o
 
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_APB_TIMER)		+= apb_timer.o
 
-obj-$(CONFIG_K8_NB)		+= k8.o
+obj-$(CONFIG_AMD_NB)		+= amd_nb.o
 obj-$(CONFIG_DEBUG_RODATA_TEST)	+= test_rodata.o
 obj-$(CONFIG_DEBUG_NX_TEST)	+= test_nx.o
 
-obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o
 obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
@@ -106,6 +108,7 @@
 scx200-y			+= scx200_32.o
 
 obj-$(CONFIG_OLPC)		+= olpc.o
+obj-$(CONFIG_OLPC_XO1)		+= olpc-xo1.o
 obj-$(CONFIG_OLPC_OPENFIRMWARE)	+= olpc_ofw.o
 obj-$(CONFIG_X86_MRST)		+= mrst.o
 
@@ -122,7 +125,6 @@
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
 	obj-$(CONFIG_X86_UV)		+= tlb_uv.o bios_uv.o uv_irq.o uv_sysfs.o uv_time.o
-	obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
 	obj-$(CONFIG_AUDIT)		+= audit_64.o
 
 	obj-$(CONFIG_GART_IOMMU)	+= pci-gart_64.o aperture_64.o
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index fb16f17..5812404 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -13,6 +13,7 @@
 
 #include <acpi/processor.h>
 #include <asm/acpi.h>
+#include <asm/mwait.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
@@ -65,16 +66,6 @@
 
 static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
 
-#define MWAIT_SUBSTATE_MASK	(0xf)
-#define MWAIT_CSTATE_MASK	(0xf)
-#define MWAIT_SUBSTATE_SIZE	(4)
-
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK	(0x2)
-
-#define MWAIT_ECX_INTERRUPT_BREAK	(0x1)
-
 #define NATIVE_CSTATE_BEYOND_HALT	(2)
 
 static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 33cec15..e125207 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -7,6 +7,7 @@
 
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/dmi.h>
 #include <linux/cpumask.h>
 #include <asm/segment.h>
@@ -125,7 +126,7 @@
  */
 void __init acpi_reserve_wakeup_memory(void)
 {
-	unsigned long mem;
+	phys_addr_t mem;
 
 	if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) {
 		printk(KERN_ERR
@@ -133,15 +134,15 @@
 		return;
 	}
 
-	mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
+	mem = memblock_find_in_range(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
 
-	if (mem == -1L) {
+	if (mem == MEMBLOCK_ERROR) {
 		printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
 		return;
 	}
 	acpi_realmode = (unsigned long) phys_to_virt(mem);
 	acpi_wakeup_address = mem;
-	reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
+	memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
 }
 
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index f65ab8b..a36bb90 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -195,7 +195,7 @@
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
-static void *text_poke_early(void *addr, const void *opcode, size_t len);
+void *text_poke_early(void *addr, const void *opcode, size_t len);
 
 /* Replace instructions with better alternatives for this CPU type.
    This runs before SMP is initialized to avoid SMP problems with
@@ -522,7 +522,7 @@
  * instructions. And on the local CPU you need to be protected again NMI or MCE
  * handlers seeing an inconsistent instruction while you patch.
  */
-static void *__init_or_module text_poke_early(void *addr, const void *opcode,
+void *__init_or_module text_poke_early(void *addr, const void *opcode,
 					      size_t len)
 {
 	unsigned long flags;
@@ -637,7 +637,72 @@
 	tpp.len = len;
 	atomic_set(&stop_machine_first, 1);
 	wrote_text = 0;
-	stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+	/* Use __stop_machine() because the caller already got online_cpus. */
+	__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
 	return addr;
 }
 
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+
+unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+
+void __init arch_init_ideal_nop5(void)
+{
+	extern const unsigned char ftrace_test_p6nop[];
+	extern const unsigned char ftrace_test_nop5[];
+	extern const unsigned char ftrace_test_jmp[];
+	int faulted = 0;
+
+	/*
+	 * There is no good nop for all x86 archs.
+	 * We will default to using the P6_NOP5, but first we
+	 * will test to make sure that the nop will actually
+	 * work on this CPU. If it faults, we will then
+	 * go to a lesser efficient 5 byte nop. If that fails
+	 * we then just use a jmp as our nop. This isn't the most
+	 * efficient nop, but we can not use a multi part nop
+	 * since we would then risk being preempted in the middle
+	 * of that nop, and if we enabled tracing then, it might
+	 * cause a system crash.
+	 *
+	 * TODO: check the cpuid to determine the best nop.
+	 */
+	asm volatile (
+		"ftrace_test_jmp:"
+		"jmp ftrace_test_p6nop\n"
+		"nop\n"
+		"nop\n"
+		"nop\n"  /* 2 byte jmp + 3 bytes */
+		"ftrace_test_p6nop:"
+		P6_NOP5
+		"jmp 1f\n"
+		"ftrace_test_nop5:"
+		".byte 0x66,0x66,0x66,0x66,0x90\n"
+		"1:"
+		".section .fixup, \"ax\"\n"
+		"2:	movl $1, %0\n"
+		"	jmp ftrace_test_nop5\n"
+		"3:	movl $2, %0\n"
+		"	jmp 1b\n"
+		".previous\n"
+		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
+		_ASM_EXTABLE(ftrace_test_nop5, 3b)
+		: "=r"(faulted) : "0" (faulted));
+
+	switch (faulted) {
+	case 0:
+		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
+		memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5);
+		break;
+	case 1:
+		pr_info("converting mcount calls to 66 66 66 66 90\n");
+		memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5);
+		break;
+	case 2:
+		pr_info("converting mcount calls to jmp . + 5\n");
+		memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5);
+		break;
+	}
+
+}
+#endif
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 679b645..d2fdb08 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 5a170cb..6e11c81 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -31,7 +31,7 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/x86_init.h>
-
+#include <asm/iommu_table.h>
 /*
  * definitions for the ACPI scanning code
  */
@@ -194,6 +194,39 @@
 	return 1UL << shift;
 }
 
+/* Access to l1 and l2 indexed register spaces */
+
+static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address)
+{
+	u32 val;
+
+	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16));
+	pci_read_config_dword(iommu->dev, 0xfc, &val);
+	return val;
+}
+
+static void iommu_write_l1(struct amd_iommu *iommu, u16 l1, u8 address, u32 val)
+{
+	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16 | 1 << 31));
+	pci_write_config_dword(iommu->dev, 0xfc, val);
+	pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16));
+}
+
+static u32 iommu_read_l2(struct amd_iommu *iommu, u8 address)
+{
+	u32 val;
+
+	pci_write_config_dword(iommu->dev, 0xf0, address);
+	pci_read_config_dword(iommu->dev, 0xf4, &val);
+	return val;
+}
+
+static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val)
+{
+	pci_write_config_dword(iommu->dev, 0xf0, (address | 1 << 8));
+	pci_write_config_dword(iommu->dev, 0xf4, val);
+}
+
 /****************************************************************************
  *
  * AMD IOMMU MMIO register space handling functions
@@ -619,6 +652,7 @@
 {
 	int cap_ptr = iommu->cap_ptr;
 	u32 range, misc;
+	int i, j;
 
 	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
 			      &iommu->cap);
@@ -633,12 +667,29 @@
 					MMIO_GET_LD(range));
 	iommu->evt_msi_num = MMIO_MSI_NUM(misc);
 
-	if (is_rd890_iommu(iommu->dev)) {
-		pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]);
-		pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]);
-		pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]);
-		pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]);
-	}
+	if (!is_rd890_iommu(iommu->dev))
+		return;
+
+	/*
+	 * Some rd890 systems may not be fully reconfigured by the BIOS, so
+	 * it's necessary for us to store this information so it can be
+	 * reprogrammed on resume
+	 */
+
+	pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4,
+			      &iommu->stored_addr_lo);
+	pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8,
+			      &iommu->stored_addr_hi);
+
+	/* Low bit locks writes to configuration space */
+	iommu->stored_addr_lo &= ~1;
+
+	for (i = 0; i < 6; i++)
+		for (j = 0; j < 0x12; j++)
+			iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j);
+
+	for (i = 0; i < 0x83; i++)
+		iommu->stored_l2[i] = iommu_read_l2(iommu, i);
 }
 
 /*
@@ -1127,14 +1178,53 @@
 	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
 }
 
-static void iommu_apply_quirks(struct amd_iommu *iommu)
+static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
 {
-	if (is_rd890_iommu(iommu->dev)) {
-		pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]);
-		pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]);
-		pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]);
-		pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]);
-	}
+	int i, j;
+	u32 ioc_feature_control;
+	struct pci_dev *pdev = NULL;
+
+	/* RD890 BIOSes may not have completely reconfigured the iommu */
+	if (!is_rd890_iommu(iommu->dev))
+		return;
+
+	/*
+	 * First, we need to ensure that the iommu is enabled. This is
+	 * controlled by a register in the northbridge
+	 */
+	pdev = pci_get_bus_and_slot(iommu->dev->bus->number, PCI_DEVFN(0, 0));
+
+	if (!pdev)
+		return;
+
+	/* Select Northbridge indirect register 0x75 and enable writing */
+	pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7));
+	pci_read_config_dword(pdev, 0x64, &ioc_feature_control);
+
+	/* Enable the iommu */
+	if (!(ioc_feature_control & 0x1))
+		pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1);
+
+	pci_dev_put(pdev);
+
+	/* Restore the iommu BAR */
+	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
+			       iommu->stored_addr_lo);
+	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 8,
+			       iommu->stored_addr_hi);
+
+	/* Restore the l1 indirect regs for each of the 6 l1s */
+	for (i = 0; i < 6; i++)
+		for (j = 0; j < 0x12; j++)
+			iommu_write_l1(iommu, i, j, iommu->stored_l1[i][j]);
+
+	/* Restore the l2 indirect regs */
+	for (i = 0; i < 0x83; i++)
+		iommu_write_l2(iommu, i, iommu->stored_l2[i]);
+
+	/* Lock PCI setup registers */
+	pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
+			       iommu->stored_addr_lo | 1);
 }
 
 /*
@@ -1147,7 +1237,6 @@
 
 	for_each_iommu(iommu) {
 		iommu_disable(iommu);
-		iommu_apply_quirks(iommu);
 		iommu_init_flags(iommu);
 		iommu_set_device_table(iommu);
 		iommu_enable_command_buffer(iommu);
@@ -1173,6 +1262,11 @@
 
 static int amd_iommu_resume(struct sys_device *dev)
 {
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu)
+		iommu_apply_resume_quirks(iommu);
+
 	/* re-load the hardware */
 	enable_iommus();
 
@@ -1405,13 +1499,13 @@
 	return 0;
 }
 
-void __init amd_iommu_detect(void)
+int __init amd_iommu_detect(void)
 {
 	if (no_iommu || (iommu_detected && !gart_iommu_aperture))
-		return;
+		return -ENODEV;
 
 	if (amd_iommu_disabled)
-		return;
+		return -ENODEV;
 
 	if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) {
 		iommu_detected = 1;
@@ -1420,7 +1514,9 @@
 
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
+		return 1;
 	}
+	return -ENODEV;
 }
 
 /****************************************************************************
@@ -1451,3 +1547,8 @@
 
 __setup("amd_iommu_dump", parse_amd_iommu_dump);
 __setup("amd_iommu=", parse_amd_iommu_options);
+
+IOMMU_INIT_FINISH(amd_iommu_detect,
+		  gart_iommu_hole_init,
+		  0,
+		  0);
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/amd_nb.c
similarity index 66%
rename from arch/x86/kernel/k8.c
rename to arch/x86/kernel/amd_nb.c
index 0f7bc20..8f6463d 100644
--- a/arch/x86/kernel/k8.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -8,21 +8,19 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <asm/k8.h>
-
-int num_k8_northbridges;
-EXPORT_SYMBOL(num_k8_northbridges);
+#include <asm/amd_nb.h>
 
 static u32 *flush_words;
 
 struct pci_device_id k8_nb_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) },
 	{}
 };
 EXPORT_SYMBOL(k8_nb_ids);
 
-struct pci_dev **k8_northbridges;
+struct k8_northbridge_info k8_northbridges;
 EXPORT_SYMBOL(k8_northbridges);
 
 static struct pci_dev *next_k8_northbridge(struct pci_dev *dev)
@@ -40,36 +38,45 @@
 	int i;
 	struct pci_dev *dev;
 
-	if (num_k8_northbridges)
+	if (k8_northbridges.num)
 		return 0;
 
 	dev = NULL;
 	while ((dev = next_k8_northbridge(dev)) != NULL)
-		num_k8_northbridges++;
+		k8_northbridges.num++;
 
-	k8_northbridges = kmalloc((num_k8_northbridges + 1) * sizeof(void *),
-				  GFP_KERNEL);
-	if (!k8_northbridges)
+	/* some CPU families (e.g. family 0x11) do not support GART */
+	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+	    boot_cpu_data.x86 == 0x15)
+		k8_northbridges.gart_supported = 1;
+
+	k8_northbridges.nb_misc = kmalloc((k8_northbridges.num + 1) *
+					  sizeof(void *), GFP_KERNEL);
+	if (!k8_northbridges.nb_misc)
 		return -ENOMEM;
 
-	if (!num_k8_northbridges) {
-		k8_northbridges[0] = NULL;
+	if (!k8_northbridges.num) {
+		k8_northbridges.nb_misc[0] = NULL;
 		return 0;
 	}
 
-	flush_words = kmalloc(num_k8_northbridges * sizeof(u32), GFP_KERNEL);
-	if (!flush_words) {
-		kfree(k8_northbridges);
-		return -ENOMEM;
+	if (k8_northbridges.gart_supported) {
+		flush_words = kmalloc(k8_northbridges.num * sizeof(u32),
+				      GFP_KERNEL);
+		if (!flush_words) {
+			kfree(k8_northbridges.nb_misc);
+			return -ENOMEM;
+		}
 	}
 
 	dev = NULL;
 	i = 0;
 	while ((dev = next_k8_northbridge(dev)) != NULL) {
-		k8_northbridges[i] = dev;
-		pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
+		k8_northbridges.nb_misc[i] = dev;
+		if (k8_northbridges.gart_supported)
+			pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
 	}
-	k8_northbridges[i] = NULL;
+	k8_northbridges.nb_misc[i] = NULL;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(cache_k8_northbridges);
@@ -93,22 +100,25 @@
 	unsigned long flags;
 	static DEFINE_SPINLOCK(gart_lock);
 
+	if (!k8_northbridges.gart_supported)
+		return;
+
 	/* Avoid races between AGP and IOMMU. In theory it's not needed
 	   but I'm not sure if the hardware won't lose flush requests
 	   when another is pending. This whole thing is so expensive anyways
 	   that it doesn't matter to serialize more. -AK */
 	spin_lock_irqsave(&gart_lock, flags);
 	flushed = 0;
-	for (i = 0; i < num_k8_northbridges; i++) {
-		pci_write_config_dword(k8_northbridges[i], 0x9c,
+	for (i = 0; i < k8_northbridges.num; i++) {
+		pci_write_config_dword(k8_northbridges.nb_misc[i], 0x9c,
 				       flush_words[i]|1);
 		flushed++;
 	}
-	for (i = 0; i < num_k8_northbridges; i++) {
+	for (i = 0; i < k8_northbridges.num; i++) {
 		u32 w;
 		/* Make sure the hardware actually executed the flush*/
 		for (;;) {
-			pci_read_config_dword(k8_northbridges[i],
+			pci_read_config_dword(k8_northbridges.nb_misc[i],
 					      0x9c, &w);
 			if (!(w & 1))
 				break;
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 8dd7780..92543c7 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -231,34 +231,6 @@
 	apbt_start_counter(phy_cs_timer_id);
 }
 
-/* Setup IRQ routing via IOAPIC */
-#ifdef CONFIG_SMP
-static void apbt_setup_irq(struct apbt_dev *adev)
-{
-	struct irq_chip *chip;
-	struct irq_desc *desc;
-
-	/* timer0 irq has been setup early */
-	if (adev->irq == 0)
-		return;
-	desc = irq_to_desc(adev->irq);
-	chip = get_irq_chip(adev->irq);
-	disable_irq(adev->irq);
-	desc->status |= IRQ_MOVE_PCNTXT;
-	irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
-	/* APB timer irqs are set up as mp_irqs, timer is edge triggerred */
-	set_irq_chip_and_handler_name(adev->irq, chip, handle_edge_irq, "edge");
-	enable_irq(adev->irq);
-	if (system_state == SYSTEM_BOOTING)
-		if (request_irq(adev->irq, apbt_interrupt_handler,
-				IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
-				adev->name, adev)) {
-			printk(KERN_ERR "Failed request IRQ for APBT%d\n",
-			       adev->num);
-		}
-}
-#endif
-
 static void apbt_enable_int(int n)
 {
 	unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
@@ -334,6 +306,27 @@
 }
 
 #ifdef CONFIG_SMP
+
+static void apbt_setup_irq(struct apbt_dev *adev)
+{
+	/* timer0 irq has been setup early */
+	if (adev->irq == 0)
+		return;
+
+	if (system_state == SYSTEM_BOOTING) {
+		irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
+		/* APB timer irqs are set up as mp_irqs, timer is edge type */
+		__set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
+		if (request_irq(adev->irq, apbt_interrupt_handler,
+				IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
+				adev->name, adev)) {
+			printk(KERN_ERR "Failed request IRQ for APBT%d\n",
+			       adev->num);
+		}
+	} else
+		enable_irq(adev->irq);
+}
+
 /* Should be called with per cpu */
 void apbt_setup_secondary_clock(void)
 {
@@ -343,7 +336,7 @@
 
 	/* Don't register boot CPU clockevent */
 	cpu = smp_processor_id();
-	if (cpu == boot_cpu_id)
+	if (!cpu)
 		return;
 	/*
 	 * We need to calculate the scaled math multiplication factor for
@@ -389,16 +382,17 @@
 
 	switch (action & 0xf) {
 	case CPU_DEAD:
+		disable_irq(adev->irq);
 		apbt_disable_int(cpu);
-		if (system_state == SYSTEM_RUNNING)
+		if (system_state == SYSTEM_RUNNING) {
 			pr_debug("skipping APBT CPU %lu offline\n", cpu);
-		else if (adev) {
+		} else if (adev) {
 			pr_debug("APBT clockevent for cpu %lu offline\n", cpu);
 			free_irq(adev->irq, adev);
 		}
 		break;
 	default:
-		pr_debug(KERN_INFO "APBT notified %lu, no action\n", action);
+		pr_debug("APBT notified %lu, no action\n", action);
 	}
 	return NOTIFY_OK;
 }
@@ -552,7 +546,7 @@
 		pr_debug("APB CS going back %lx:%lx:%lx ",
 			 t2, last_read, t2 - last_read);
 bad_count_x3:
-		pr_debug(KERN_INFO "tripple check enforced\n");
+		pr_debug("triple check enforced\n");
 		t0 = apbt_readl(phy_cs_timer_id,
 				APBTMR_N_CURRENT_VALUE);
 		udelay(1);
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index a2e0caf..b3a16e8 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -27,7 +27,7 @@
 #include <asm/gart.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/x86_init.h>
 
 int gart_iommu_aperture;
@@ -307,7 +307,7 @@
 				continue;
 
 			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
-			aper_enabled = ctl & AMD64_GARTEN;
+			aper_enabled = ctl & GARTEN;
 			aper_order = (ctl >> 1) & 7;
 			aper_size = (32 * 1024 * 1024) << aper_order;
 			aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
@@ -362,7 +362,7 @@
 				continue;
 
 			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
-			ctl &= ~AMD64_GARTEN;
+			ctl &= ~GARTEN;
 			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
 		}
 	}
@@ -371,7 +371,7 @@
 
 static int __initdata printed_gart_size_msg;
 
-void __init gart_iommu_hole_init(void)
+int __init gart_iommu_hole_init(void)
 {
 	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
@@ -381,7 +381,7 @@
 
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
-		return;
+		return -ENODEV;
 
 	printk(KERN_INFO  "Checking aperture...\n");
 
@@ -463,8 +463,9 @@
 			unsigned long n = (32 * 1024 * 1024) << last_aper_order;
 
 			insert_aperture_resource((u32)last_aper_base, n);
+			return 1;
 		}
-		return;
+		return 0;
 	}
 
 	if (!fallback_aper_force) {
@@ -500,13 +501,18 @@
 			panic("Not enough memory for aperture");
 		}
 	} else {
-		return;
+		return 0;
 	}
 
 	/* Fix up the north bridges */
 	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
-		int bus;
-		int dev_base, dev_limit;
+		int bus, dev_base, dev_limit;
+
+		/*
+		 * Don't enable translation yet but enable GART IO and CPU
+		 * accesses and set DISTLBWALKPRB since GART table memory is UC.
+		 */
+		u32 ctl = DISTLBWALKPRB | aper_order << 1;
 
 		bus = bus_dev_ranges[i].bus;
 		dev_base = bus_dev_ranges[i].dev_base;
@@ -515,13 +521,12 @@
 			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
-			/* Don't enable translation yet. That is done later.
-			   Assume this BIOS didn't initialise the GART so
-			   just overwrite all previous bits */
-			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1);
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
 			write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25);
 		}
 	}
 
 	set_up_gart_resume(aper_order, aper_alloc);
+
+	return 1;
 }
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e3b534c..850657d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -52,6 +52,7 @@
 #include <asm/mce.h>
 #include <asm/kvm_para.h>
 #include <asm/tsc.h>
+#include <asm/atomic.h>
 
 unsigned int num_processors;
 
@@ -370,38 +371,87 @@
 }
 
 /*
- * Setup extended LVT, AMD specific (K8, family 10h)
+ * Setup extended LVT, AMD specific
  *
- * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
- * MCE interrupts are supported. Thus MCE offset must be set to 0.
+ * Software should use the LVT offsets the BIOS provides.  The offsets
+ * are determined by the subsystems using it like those for MCE
+ * threshold or IBS.  On K8 only offset 0 (APIC500) and MCE interrupts
+ * are supported. Beginning with family 10h at least 4 offsets are
+ * available.
  *
+ * Since the offsets must be consistent for all cores, we keep track
+ * of the LVT offsets in software and reserve the offset for the same
+ * vector also to be used on other cores. An offset is freed by
+ * setting the entry to APIC_EILVT_MASKED.
+ *
+ * If the BIOS is right, there should be no conflicts. Otherwise a
+ * "[Firmware Bug]: ..." error message is generated. However, if
+ * software does not properly determines the offsets, it is not
+ * necessarily a BIOS bug.
+ */
+
+static atomic_t eilvt_offsets[APIC_EILVT_NR_MAX];
+
+static inline int eilvt_entry_is_changeable(unsigned int old, unsigned int new)
+{
+	return (old & APIC_EILVT_MASKED)
+		|| (new == APIC_EILVT_MASKED)
+		|| ((new & ~APIC_EILVT_MASKED) == old);
+}
+
+static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
+{
+	unsigned int rsvd;			/* 0: uninitialized */
+
+	if (offset >= APIC_EILVT_NR_MAX)
+		return ~0;
+
+	rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED;
+	do {
+		if (rsvd &&
+		    !eilvt_entry_is_changeable(rsvd, new))
+			/* may not change if vectors are different */
+			return rsvd;
+		rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
+	} while (rsvd != new);
+
+	return new;
+}
+
+/*
  * If mask=1, the LVT entry does not generate interrupts while mask=0
  * enables the vector. See also the BKDGs.
  */
 
-#define APIC_EILVT_LVTOFF_MCE 0
-#define APIC_EILVT_LVTOFF_IBS 1
-
-static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
+int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
 {
-	unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
-	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
+	unsigned long reg = APIC_EILVTn(offset);
+	unsigned int new, old, reserved;
 
-	apic_write(reg, v);
-}
+	new = (mask << 16) | (msg_type << 8) | vector;
+	old = apic_read(reg);
+	reserved = reserve_eilvt_offset(offset, new);
 
-u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask)
-{
-	setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask);
-	return APIC_EILVT_LVTOFF_MCE;
-}
+	if (reserved != new) {
+		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
+		       "vector 0x%x was already reserved by another core, "
+		       "APIC%lX=0x%x\n",
+		       smp_processor_id(), new, reserved, reg, old);
+		return -EINVAL;
+	}
 
-u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
-{
-	setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
-	return APIC_EILVT_LVTOFF_IBS;
+	if (!eilvt_entry_is_changeable(old, new)) {
+		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
+		       "register already in use, APIC%lX=0x%x\n",
+		       smp_processor_id(), new, reg, old);
+		return -EBUSY;
+	}
+
+	apic_write(reg, new);
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
+EXPORT_SYMBOL_GPL(setup_APIC_eilvt);
 
 /*
  * Program the next event, relative to now
@@ -1665,10 +1715,7 @@
 	}
 #endif
 
-#ifndef CONFIG_SMP
-	enable_IR_x2apic();
 	default_setup_apic_routing();
-#endif
 
 	verify_local_APIC();
 	connect_bsp_APIC();
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 5c5b8f3..8ae808d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -131,13 +131,9 @@
 	struct irq_pin_list *next;
 };
 
-static struct irq_pin_list *get_one_free_irq_2_pin(int node)
+static struct irq_pin_list *alloc_irq_pin_list(int node)
 {
-	struct irq_pin_list *pin;
-
-	pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
-
-	return pin;
+	return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
 }
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -150,10 +146,7 @@
 int __init arch_early_irq_init(void)
 {
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
-	int count;
-	int node;
-	int i;
+	int count, node, i;
 
 	if (!legacy_pic->nr_legacy_irqs) {
 		nr_irqs_gsi = 0;
@@ -162,13 +155,15 @@
 
 	cfg = irq_cfgx;
 	count = ARRAY_SIZE(irq_cfgx);
-	node= cpu_to_node(boot_cpu_id);
+	node = cpu_to_node(0);
+
+	/* Make sure the legacy interrupts are marked in the bitmap */
+	irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
 
 	for (i = 0; i < count; i++) {
-		desc = irq_to_desc(i);
-		desc->chip_data = &cfg[i];
-		zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
-		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
+		set_irq_chip_data(i, &cfg[i]);
+		zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
+		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
 		/*
 		 * For legacy IRQ's, start with assigning irq0 to irq15 to
 		 * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
@@ -183,170 +178,88 @@
 }
 
 #ifdef CONFIG_SPARSE_IRQ
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct irq_cfg *irq_cfg(unsigned int irq)
 {
-	struct irq_cfg *cfg = NULL;
-	struct irq_desc *desc;
+	return get_irq_chip_data(irq);
+}
 
-	desc = irq_to_desc(irq);
-	if (desc)
-		cfg = desc->chip_data;
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+{
+	struct irq_cfg *cfg;
 
+	cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
+	if (!cfg)
+		return NULL;
+	if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
+		goto out_cfg;
+	if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+		goto out_domain;
 	return cfg;
+out_domain:
+	free_cpumask_var(cfg->domain);
+out_cfg:
+	kfree(cfg);
+	return NULL;
 }
 
-static struct irq_cfg *get_one_free_irq_cfg(int node)
+static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
 {
-	struct irq_cfg *cfg;
-
-	cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
-	if (cfg) {
-		if (!zalloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
-			kfree(cfg);
-			cfg = NULL;
-		} else if (!zalloc_cpumask_var_node(&cfg->old_domain,
-							  GFP_ATOMIC, node)) {
-			free_cpumask_var(cfg->domain);
-			kfree(cfg);
-			cfg = NULL;
-		}
-	}
-
-	return cfg;
-}
-
-int arch_init_chip_data(struct irq_desc *desc, int node)
-{
-	struct irq_cfg *cfg;
-
-	cfg = desc->chip_data;
-	if (!cfg) {
-		desc->chip_data = get_one_free_irq_cfg(node);
-		if (!desc->chip_data) {
-			printk(KERN_ERR "can not alloc irq_cfg\n");
-			BUG_ON(1);
-		}
-	}
-
-	return 0;
-}
-
-/* for move_irq_desc */
-static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
-{
-	struct irq_pin_list *old_entry, *head, *tail, *entry;
-
-	cfg->irq_2_pin = NULL;
-	old_entry = old_cfg->irq_2_pin;
-	if (!old_entry)
-		return;
-
-	entry = get_one_free_irq_2_pin(node);
-	if (!entry)
-		return;
-
-	entry->apic	= old_entry->apic;
-	entry->pin	= old_entry->pin;
-	head		= entry;
-	tail		= entry;
-	old_entry	= old_entry->next;
-	while (old_entry) {
-		entry = get_one_free_irq_2_pin(node);
-		if (!entry) {
-			entry = head;
-			while (entry) {
-				head = entry->next;
-				kfree(entry);
-				entry = head;
-			}
-			/* still use the old one */
-			return;
-		}
-		entry->apic	= old_entry->apic;
-		entry->pin	= old_entry->pin;
-		tail->next	= entry;
-		tail		= entry;
-		old_entry	= old_entry->next;
-	}
-
-	tail->next = NULL;
-	cfg->irq_2_pin = head;
-}
-
-static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
-{
-	struct irq_pin_list *entry, *next;
-
-	if (old_cfg->irq_2_pin == cfg->irq_2_pin)
-		return;
-
-	entry = old_cfg->irq_2_pin;
-
-	while (entry) {
-		next = entry->next;
-		kfree(entry);
-		entry = next;
-	}
-	old_cfg->irq_2_pin = NULL;
-}
-
-void arch_init_copy_chip_data(struct irq_desc *old_desc,
-				 struct irq_desc *desc, int node)
-{
-	struct irq_cfg *cfg;
-	struct irq_cfg *old_cfg;
-
-	cfg = get_one_free_irq_cfg(node);
-
 	if (!cfg)
 		return;
-
-	desc->chip_data = cfg;
-
-	old_cfg = old_desc->chip_data;
-
-	cfg->vector = old_cfg->vector;
-	cfg->move_in_progress = old_cfg->move_in_progress;
-	cpumask_copy(cfg->domain, old_cfg->domain);
-	cpumask_copy(cfg->old_domain, old_cfg->old_domain);
-
-	init_copy_irq_2_pin(old_cfg, cfg, node);
-}
-
-static void free_irq_cfg(struct irq_cfg *cfg)
-{
+	set_irq_chip_data(at, NULL);
 	free_cpumask_var(cfg->domain);
 	free_cpumask_var(cfg->old_domain);
 	kfree(cfg);
 }
 
-void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
-{
-	struct irq_cfg *old_cfg, *cfg;
-
-	old_cfg = old_desc->chip_data;
-	cfg = desc->chip_data;
-
-	if (old_cfg == cfg)
-		return;
-
-	if (old_cfg) {
-		free_irq_2_pin(old_cfg, cfg);
-		free_irq_cfg(old_cfg);
-		old_desc->chip_data = NULL;
-	}
-}
-/* end for move_irq_desc */
-
 #else
+
 struct irq_cfg *irq_cfg(unsigned int irq)
 {
 	return irq < nr_irqs ? irq_cfgx + irq : NULL;
 }
 
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+{
+	return irq_cfgx + irq;
+}
+
+static inline void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) { }
+
 #endif
 
+static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
+{
+	int res = irq_alloc_desc_at(at, node);
+	struct irq_cfg *cfg;
+
+	if (res < 0) {
+		if (res != -EEXIST)
+			return NULL;
+		cfg = get_irq_chip_data(at);
+		if (cfg)
+			return cfg;
+	}
+
+	cfg = alloc_irq_cfg(at, node);
+	if (cfg)
+		set_irq_chip_data(at, cfg);
+	else
+		irq_free_desc(at);
+	return cfg;
+}
+
+static int alloc_irq_from(unsigned int from, int node)
+{
+	return irq_alloc_desc_from(from, node);
+}
+
+static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
+{
+	free_irq_cfg(at, cfg);
+	irq_free_desc(at);
+}
+
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -451,7 +364,7 @@
 	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
 }
 
-void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	unsigned long flags;
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
@@ -481,7 +394,7 @@
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
 static int
-add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
+__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list **last, *entry;
 
@@ -493,7 +406,7 @@
 		last = &entry->next;
 	}
 
-	entry = get_one_free_irq_2_pin(node);
+	entry = alloc_irq_pin_list(node);
 	if (!entry) {
 		printk(KERN_ERR "can not alloc irq_pin_list (%d,%d,%d)\n",
 				node, apic, pin);
@@ -508,7 +421,7 @@
 
 static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
-	if (add_pin_to_irq_node_nopanic(cfg, node, apic, pin))
+	if (__add_pin_to_irq_node(cfg, node, apic, pin))
 		panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
 }
 
@@ -571,11 +484,6 @@
 			     IO_APIC_REDIR_LEVEL_TRIGGER, NULL);
 }
 
-static void __unmask_IO_APIC_irq(struct irq_cfg *cfg)
-{
-	io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
 static void io_apic_sync(struct irq_pin_list *entry)
 {
 	/*
@@ -587,44 +495,37 @@
 	readl(&io_apic->data);
 }
 
-static void __mask_IO_APIC_irq(struct irq_cfg *cfg)
+static void mask_ioapic(struct irq_cfg *cfg)
 {
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
-}
-
-static void mask_IO_APIC_irq_desc(struct irq_desc *desc)
-{
-	struct irq_cfg *cfg = desc->chip_data;
-	unsigned long flags;
-
-	BUG_ON(!cfg);
-
-	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__mask_IO_APIC_irq(cfg);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
+static void mask_ioapic_irq(struct irq_data *data)
 {
-	struct irq_cfg *cfg = desc->chip_data;
+	mask_ioapic(data->chip_data);
+}
+
+static void __unmask_ioapic(struct irq_cfg *cfg)
+{
+	io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
+}
+
+static void unmask_ioapic(struct irq_cfg *cfg)
+{
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__unmask_IO_APIC_irq(cfg);
+	__unmask_ioapic(cfg);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_IO_APIC_irq(unsigned int irq)
+static void unmask_ioapic_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	mask_IO_APIC_irq_desc(desc);
-}
-static void unmask_IO_APIC_irq(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	unmask_IO_APIC_irq_desc(desc);
+	unmask_ioapic(data->chip_data);
 }
 
 static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
@@ -694,14 +595,14 @@
 	struct IO_APIC_route_entry **ioapic_entries;
 
 	ioapic_entries = kzalloc(sizeof(*ioapic_entries) * nr_ioapics,
-				GFP_ATOMIC);
+				GFP_KERNEL);
 	if (!ioapic_entries)
 		return 0;
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
 		ioapic_entries[apic] =
 			kzalloc(sizeof(struct IO_APIC_route_entry) *
-				nr_ioapic_registers[apic], GFP_ATOMIC);
+				nr_ioapic_registers[apic], GFP_KERNEL);
 		if (!ioapic_entries[apic])
 			goto nomem;
 	}
@@ -1259,7 +1160,6 @@
 	/* Initialize vector_irq on a new cpu */
 	int irq, vector;
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 
 	/*
 	 * vector_lock will make sure that we don't run into irq vector
@@ -1268,9 +1168,10 @@
 	 */
 	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
-	for_each_irq_desc(irq, desc) {
-		cfg = desc->chip_data;
-
+	for_each_active_irq(irq) {
+		cfg = get_irq_chip_data(irq);
+		if (!cfg)
+			continue;
 		/*
 		 * If it is a legacy IRQ handled by the legacy PIC, this cpu
 		 * will be part of the irq_cfg's domain.
@@ -1327,17 +1228,17 @@
 }
 #endif
 
-static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long trigger)
+static void ioapic_register_intr(unsigned int irq, unsigned long trigger)
 {
 
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 	    trigger == IOAPIC_LEVEL)
-		desc->status |= IRQ_LEVEL;
+		irq_set_status_flags(irq, IRQ_LEVEL);
 	else
-		desc->status &= ~IRQ_LEVEL;
+		irq_clear_status_flags(irq, IRQ_LEVEL);
 
-	if (irq_remapped(irq)) {
-		desc->status |= IRQ_MOVE_PCNTXT;
+	if (irq_remapped(get_irq_chip_data(irq))) {
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 		if (trigger)
 			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
 						      handle_fasteoi_irq,
@@ -1358,10 +1259,10 @@
 					      handle_edge_irq, "edge");
 }
 
-int setup_ioapic_entry(int apic_id, int irq,
-		       struct IO_APIC_route_entry *entry,
-		       unsigned int destination, int trigger,
-		       int polarity, int vector, int pin)
+static int setup_ioapic_entry(int apic_id, int irq,
+			      struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int trigger,
+			      int polarity, int vector, int pin)
 {
 	/*
 	 * add it to the IO-APIC irq-routing table:
@@ -1382,21 +1283,7 @@
 		if (index < 0)
 			panic("Failed to allocate IRTE for ioapic %d\n", apic_id);
 
-		memset(&irte, 0, sizeof(irte));
-
-		irte.present = 1;
-		irte.dst_mode = apic->irq_dest_mode;
-		/*
-		 * Trigger mode in the IRTE will always be edge, and the
-		 * actual level or edge trigger will be setup in the IO-APIC
-		 * RTE. This will help simplify level triggered irq migration.
-		 * For more details, see the comments above explainig IO-APIC
-		 * irq migration in the presence of interrupt-remapping.
-		 */
-		irte.trigger_mode = 0;
-		irte.dlvry_mode = apic->irq_delivery_mode;
-		irte.vector = vector;
-		irte.dest_id = IRTE_DEST(destination);
+		prepare_irte(&irte, vector, destination);
 
 		/* Set source-id of interrupt request */
 		set_ioapic_sid(&irte, apic_id);
@@ -1431,18 +1318,14 @@
 	return 0;
 }
 
-static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq_desc *desc,
-			      int trigger, int polarity)
+static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq,
+			     struct irq_cfg *cfg, int trigger, int polarity)
 {
-	struct irq_cfg *cfg;
 	struct IO_APIC_route_entry entry;
 	unsigned int dest;
 
 	if (!IO_APIC_IRQ(irq))
 		return;
-
-	cfg = desc->chip_data;
-
 	/*
 	 * For legacy irqs, cfg->domain starts with cpu 0 for legacy
 	 * controllers like 8259. Now that IO-APIC can handle this irq, update
@@ -1471,9 +1354,9 @@
 		return;
 	}
 
-	ioapic_register_intr(irq, desc, trigger);
+	ioapic_register_intr(irq, trigger);
 	if (irq < legacy_pic->nr_legacy_irqs)
-		legacy_pic->chip->mask(irq);
+		legacy_pic->mask(irq);
 
 	ioapic_write_entry(apic_id, pin, entry);
 }
@@ -1484,11 +1367,9 @@
 
 static void __init setup_IO_APIC_irqs(void)
 {
-	int apic_id, pin, idx, irq;
-	int notcon = 0;
-	struct irq_desc *desc;
+	int apic_id, pin, idx, irq, notcon = 0;
+	int node = cpu_to_node(0);
 	struct irq_cfg *cfg;
-	int node = cpu_to_node(boot_cpu_id);
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
@@ -1525,19 +1406,17 @@
 				apic->multi_timer_check(apic_id, irq))
 			continue;
 
-		desc = irq_to_desc_alloc_node(irq, node);
-		if (!desc) {
-			printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+		cfg = alloc_irq_and_cfg_at(irq, node);
+		if (!cfg)
 			continue;
-		}
-		cfg = desc->chip_data;
+
 		add_pin_to_irq_node(cfg, node, apic_id, pin);
 		/*
 		 * don't mark it in pin_programmed, so later acpi could
 		 * set it correctly when irq < 16
 		 */
-		setup_IO_APIC_irq(apic_id, pin, irq, desc,
-				irq_trigger(idx), irq_polarity(idx));
+		setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx),
+				  irq_polarity(idx));
 	}
 
 	if (notcon)
@@ -1552,9 +1431,7 @@
  */
 void setup_IO_APIC_irq_extra(u32 gsi)
 {
-	int apic_id = 0, pin, idx, irq;
-	int node = cpu_to_node(boot_cpu_id);
-	struct irq_desc *desc;
+	int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
 	struct irq_cfg *cfg;
 
 	/*
@@ -1570,18 +1447,15 @@
 		return;
 
 	irq = pin_2_irq(idx, apic_id, pin);
-#ifdef CONFIG_SPARSE_IRQ
-	desc = irq_to_desc(irq);
-	if (desc)
-		return;
-#endif
-	desc = irq_to_desc_alloc_node(irq, node);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc for %d\n", irq);
-		return;
-	}
 
-	cfg = desc->chip_data;
+	/* Only handle the non legacy irqs on secondary ioapics */
+	if (apic_id == 0 || irq < NR_IRQS_LEGACY)
+		return;
+
+	cfg = alloc_irq_and_cfg_at(irq, node);
+	if (!cfg)
+		return;
+
 	add_pin_to_irq_node(cfg, node, apic_id, pin);
 
 	if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
@@ -1591,7 +1465,7 @@
 	}
 	set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
 
-	setup_IO_APIC_irq(apic_id, pin, irq, desc,
+	setup_ioapic_irq(apic_id, pin, irq, cfg,
 			irq_trigger(idx), irq_polarity(idx));
 }
 
@@ -1642,7 +1516,6 @@
 	union IO_APIC_reg_03 reg_03;
 	unsigned long flags;
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 	unsigned int irq;
 
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
@@ -1729,10 +1602,10 @@
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for_each_irq_desc(irq, desc) {
+	for_each_active_irq(irq) {
 		struct irq_pin_list *entry;
 
-		cfg = desc->chip_data;
+		cfg = get_irq_chip_data(irq);
 		if (!cfg)
 			continue;
 		entry = cfg->irq_2_pin;
@@ -2239,29 +2112,26 @@
  * an edge even if it isn't on the 8259A...
  */
 
-static unsigned int startup_ioapic_irq(unsigned int irq)
+static unsigned int startup_ioapic_irq(struct irq_data *data)
 {
-	int was_pending = 0;
+	int was_pending = 0, irq = data->irq;
 	unsigned long flags;
-	struct irq_cfg *cfg;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	if (irq < legacy_pic->nr_legacy_irqs) {
-		legacy_pic->chip->mask(irq);
+		legacy_pic->mask(irq);
 		if (legacy_pic->irq_pending(irq))
 			was_pending = 1;
 	}
-	cfg = irq_cfg(irq);
-	__unmask_IO_APIC_irq(cfg);
+	__unmask_ioapic(data->chip_data);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return was_pending;
 }
 
-static int ioapic_retrigger_irq(unsigned int irq)
+static int ioapic_retrigger_irq(struct irq_data *data)
 {
-
-	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
@@ -2312,7 +2182,7 @@
 		 * With interrupt-remapping, destination information comes
 		 * from interrupt-remapping table entry.
 		 */
-		if (!irq_remapped(irq))
+		if (!irq_remapped(cfg))
 			io_apic_write(apic, 0x11 + pin*2, dest);
 		reg = io_apic_read(apic, 0x10 + pin*2);
 		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
@@ -2322,65 +2192,46 @@
 }
 
 /*
- * Either sets desc->affinity to a valid value, and returns
+ * Either sets data->affinity to a valid value, and returns
  * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves desc->affinity untouched.
+ * leaves data->affinity untouched.
  */
-unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask,
-		  unsigned int *dest_id)
+int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			  unsigned int *dest_id)
 {
-	struct irq_cfg *cfg;
-	unsigned int irq;
+	struct irq_cfg *cfg = data->chip_data;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
 		return -1;
 
-	irq = desc->irq;
-	cfg = desc->chip_data;
-	if (assign_irq_vector(irq, cfg, mask))
+	if (assign_irq_vector(data->irq, data->chip_data, mask))
 		return -1;
 
-	cpumask_copy(desc->affinity, mask);
+	cpumask_copy(data->affinity, mask);
 
-	*dest_id = apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+	*dest_id = apic->cpu_mask_to_apicid_and(mask, cfg->domain);
 	return 0;
 }
 
 static int
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_cfg *cfg;
+	unsigned int dest, irq = data->irq;
 	unsigned long flags;
-	unsigned int dest;
-	unsigned int irq;
-	int ret = -1;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
+	int ret;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	ret = set_desc_affinity(desc, mask, &dest);
+	ret = __ioapic_set_affinity(data, mask, &dest);
 	if (!ret) {
 		/* Only the high 8 bits are valid. */
 		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, cfg);
+		__target_IO_APIC_irq(irq, dest, data->chip_data);
 	}
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-
 	return ret;
 }
 
-static int
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	return set_ioapic_affinity_irq_desc(desc, mask);
-}
-
 #ifdef CONFIG_INTR_REMAP
 
 /*
@@ -2395,24 +2246,21 @@
  * the interrupt-remapping table entry.
  */
 static int
-migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		       bool force)
 {
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct irte irte;
-	unsigned int dest;
-	unsigned int irq;
-	int ret = -1;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
-		return ret;
+		return -EINVAL;
 
-	irq = desc->irq;
 	if (get_irte(irq, &irte))
-		return ret;
+		return -EBUSY;
 
-	cfg = desc->chip_data;
 	if (assign_irq_vector(irq, cfg, mask))
-		return ret;
+		return -EBUSY;
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
 
@@ -2427,29 +2275,14 @@
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
 
-	cpumask_copy(desc->affinity, mask);
-
+	cpumask_copy(data->affinity, mask);
 	return 0;
 }
 
-/*
- * Migrates the IRQ destination in the process context.
- */
-static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
-					    const struct cpumask *mask)
-{
-	return migrate_ioapic_irq_desc(desc, mask);
-}
-static int set_ir_ioapic_affinity_irq(unsigned int irq,
-				       const struct cpumask *mask)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	return set_ir_ioapic_affinity_irq_desc(desc, mask);
-}
 #else
-static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
-						   const struct cpumask *mask)
+static inline int
+ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		       bool force)
 {
 	return 0;
 }
@@ -2511,10 +2344,8 @@
 	irq_exit();
 }
 
-static void __irq_complete_move(struct irq_desc **descp, unsigned vector)
+static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
 {
-	struct irq_desc *desc = *descp;
-	struct irq_cfg *cfg = desc->chip_data;
 	unsigned me;
 
 	if (likely(!cfg->move_in_progress))
@@ -2526,31 +2357,28 @@
 		send_cleanup_vector(cfg);
 }
 
-static void irq_complete_move(struct irq_desc **descp)
+static void irq_complete_move(struct irq_cfg *cfg)
 {
-	__irq_complete_move(descp, ~get_irq_regs()->orig_ax);
+	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
 }
 
 void irq_force_complete_move(int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 
 	if (!cfg)
 		return;
 
-	__irq_complete_move(&desc, cfg->vector);
+	__irq_complete_move(cfg, cfg->vector);
 }
 #else
-static inline void irq_complete_move(struct irq_desc **descp) {}
+static inline void irq_complete_move(struct irq_cfg *cfg) { }
 #endif
 
-static void ack_apic_edge(unsigned int irq)
+static void ack_apic_edge(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	irq_complete_move(&desc);
-	move_native_irq(irq);
+	irq_complete_move(data->chip_data);
+	move_native_irq(data->irq);
 	ack_APIC_irq();
 }
 
@@ -2572,10 +2400,12 @@
  * Otherwise, we simulate the EOI message manually by changing the trigger
  * mode to edge and then back to level, with RTE being masked during this.
 */
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 {
 	struct irq_pin_list *entry;
+	unsigned long flags;
 
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	for_each_irq_pin(entry, cfg->irq_2_pin) {
 		if (mp_ioapics[entry->apic].apicver >= 0x20) {
 			/*
@@ -2584,7 +2414,7 @@
 			 * intr-remapping table entry. Hence for the io-apic
 			 * EOI we use the pin number.
 			 */
-			if (irq_remapped(irq))
+			if (irq_remapped(cfg))
 				io_apic_eoi(entry->apic, entry->pin);
 			else
 				io_apic_eoi(entry->apic, cfg->vector);
@@ -2593,36 +2423,22 @@
 			__unmask_and_level_IO_APIC_irq(entry);
 		}
 	}
-}
-
-static void eoi_ioapic_irq(struct irq_desc *desc)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__eoi_ioapic_irq(irq, cfg);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void ack_apic_level(unsigned int irq)
+static void ack_apic_level(struct irq_data *data)
 {
+	struct irq_cfg *cfg = data->chip_data;
+	int i, do_unmask_irq = 0, irq = data->irq;
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long v;
-	int i;
-	struct irq_cfg *cfg;
-	int do_unmask_irq = 0;
 
-	irq_complete_move(&desc);
+	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
 	if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
-		mask_IO_APIC_irq_desc(desc);
+		mask_ioapic(cfg);
 	}
 #endif
 
@@ -2658,7 +2474,6 @@
 	 * we use the above logic (mask+edge followed by unmask+level) from
 	 * Manfred Spraul to clear the remote IRR.
 	 */
-	cfg = desc->chip_data;
 	i = cfg->vector;
 	v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
 
@@ -2678,7 +2493,7 @@
 	if (!(v & (1 << (i & 0x1f)))) {
 		atomic_inc(&irq_mis_count);
 
-		eoi_ioapic_irq(desc);
+		eoi_ioapic_irq(irq, cfg);
 	}
 
 	/* Now we can move and renable the irq */
@@ -2709,61 +2524,57 @@
 		 * accurate and is causing problems then it is a hardware bug
 		 * and you can go talk to the chipset vendor about it.
 		 */
-		cfg = desc->chip_data;
 		if (!io_apic_level_ack_pending(cfg))
 			move_masked_irq(irq);
-		unmask_IO_APIC_irq_desc(desc);
+		unmask_ioapic(cfg);
 	}
 }
 
 #ifdef CONFIG_INTR_REMAP
-static void ir_ack_apic_edge(unsigned int irq)
+static void ir_ack_apic_edge(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
-static void ir_ack_apic_level(unsigned int irq)
+static void ir_ack_apic_level(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
 	ack_APIC_irq();
-	eoi_ioapic_irq(desc);
+	eoi_ioapic_irq(data->irq, data->chip_data);
 }
 #endif /* CONFIG_INTR_REMAP */
 
 static struct irq_chip ioapic_chip __read_mostly = {
-	.name		= "IO-APIC",
-	.startup	= startup_ioapic_irq,
-	.mask		= mask_IO_APIC_irq,
-	.unmask		= unmask_IO_APIC_irq,
-	.ack		= ack_apic_edge,
-	.eoi		= ack_apic_level,
+	.name			= "IO-APIC",
+	.irq_startup		= startup_ioapic_irq,
+	.irq_mask		= mask_ioapic_irq,
+	.irq_unmask		= unmask_ioapic_irq,
+	.irq_ack		= ack_apic_edge,
+	.irq_eoi		= ack_apic_level,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ioapic_affinity_irq,
+	.irq_set_affinity	= ioapic_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip ir_ioapic_chip __read_mostly = {
-	.name		= "IR-IO-APIC",
-	.startup	= startup_ioapic_irq,
-	.mask		= mask_IO_APIC_irq,
-	.unmask		= unmask_IO_APIC_irq,
+	.name			= "IR-IO-APIC",
+	.irq_startup		= startup_ioapic_irq,
+	.irq_mask		= mask_ioapic_irq,
+	.irq_unmask		= unmask_ioapic_irq,
 #ifdef CONFIG_INTR_REMAP
-	.ack		= ir_ack_apic_edge,
-	.eoi		= ir_ack_apic_level,
+	.irq_ack		= ir_ack_apic_edge,
+	.irq_eoi		= ir_ack_apic_level,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ir_ioapic_affinity_irq,
+	.irq_set_affinity	= ir_ioapic_set_affinity,
 #endif
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static inline void init_IO_APIC_traps(void)
 {
-	int irq;
-	struct irq_desc *desc;
 	struct irq_cfg *cfg;
+	unsigned int irq;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -2776,8 +2587,8 @@
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for_each_irq_desc(irq, desc) {
-		cfg = desc->chip_data;
+	for_each_active_irq(irq) {
+		cfg = get_irq_chip_data(irq);
 		if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
@@ -2788,7 +2599,7 @@
 				legacy_pic->make_irq(irq);
 			else
 				/* Strange. Oh, well.. */
-				desc->chip = &no_irq_chip;
+				set_irq_chip(irq, &no_irq_chip);
 		}
 	}
 }
@@ -2797,7 +2608,7 @@
  * The local APIC irq-chip implementation:
  */
 
-static void mask_lapic_irq(unsigned int irq)
+static void mask_lapic_irq(struct irq_data *data)
 {
 	unsigned long v;
 
@@ -2805,7 +2616,7 @@
 	apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
 }
 
-static void unmask_lapic_irq(unsigned int irq)
+static void unmask_lapic_irq(struct irq_data *data)
 {
 	unsigned long v;
 
@@ -2813,21 +2624,21 @@
 	apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
 }
 
-static void ack_lapic_irq(unsigned int irq)
+static void ack_lapic_irq(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
 static struct irq_chip lapic_chip __read_mostly = {
 	.name		= "local-APIC",
-	.mask		= mask_lapic_irq,
-	.unmask		= unmask_lapic_irq,
-	.ack		= ack_lapic_irq,
+	.irq_mask	= mask_lapic_irq,
+	.irq_unmask	= unmask_lapic_irq,
+	.irq_ack	= ack_lapic_irq,
 };
 
-static void lapic_register_intr(int irq, struct irq_desc *desc)
+static void lapic_register_intr(int irq)
 {
-	desc->status &= ~IRQ_LEVEL;
+	irq_clear_status_flags(irq, IRQ_LEVEL);
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 }
@@ -2930,9 +2741,8 @@
  */
 static inline void __init check_timer(void)
 {
-	struct irq_desc *desc = irq_to_desc(0);
-	struct irq_cfg *cfg = desc->chip_data;
-	int node = cpu_to_node(boot_cpu_id);
+	struct irq_cfg *cfg = get_irq_chip_data(0);
+	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
 	int no_pin1 = 0;
@@ -2942,7 +2752,7 @@
 	/*
 	 * get/set the timer IRQ vector:
 	 */
-	legacy_pic->chip->mask(0);
+	legacy_pic->mask(0);
 	assign_irq_vector(0, cfg, apic->target_cpus());
 
 	/*
@@ -3001,7 +2811,7 @@
 			add_pin_to_irq_node(cfg, node, apic1, pin1);
 			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
 		} else {
-			/* for edge trigger, setup_IO_APIC_irq already
+			/* for edge trigger, setup_ioapic_irq already
 			 * leave it unmasked.
 			 * so only need to unmask if it is level-trigger
 			 * do we really have level trigger timer?
@@ -3009,12 +2819,12 @@
 			int idx;
 			idx = find_irq_entry(apic1, pin1, mp_INT);
 			if (idx != -1 && irq_trigger(idx))
-				unmask_IO_APIC_irq_desc(desc);
+				unmask_ioapic(cfg);
 		}
 		if (timer_irq_works()) {
 			if (nmi_watchdog == NMI_IO_APIC) {
 				setup_nmi();
-				legacy_pic->chip->unmask(0);
+				legacy_pic->unmask(0);
 			}
 			if (disable_timer_pin_1 > 0)
 				clear_IO_APIC_pin(0, pin1);
@@ -3037,14 +2847,14 @@
 		 */
 		replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
-		legacy_pic->chip->unmask(0);
+		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
 			timer_through_8259 = 1;
 			if (nmi_watchdog == NMI_IO_APIC) {
-				legacy_pic->chip->mask(0);
+				legacy_pic->mask(0);
 				setup_nmi();
-				legacy_pic->chip->unmask(0);
+				legacy_pic->unmask(0);
 			}
 			goto out;
 		}
@@ -3052,7 +2862,7 @@
 		 * Cleanup, just in case ...
 		 */
 		local_irq_disable();
-		legacy_pic->chip->mask(0);
+		legacy_pic->mask(0);
 		clear_IO_APIC_pin(apic2, pin2);
 		apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
 	}
@@ -3069,16 +2879,16 @@
 	apic_printk(APIC_QUIET, KERN_INFO
 		    "...trying to set up timer as Virtual Wire IRQ...\n");
 
-	lapic_register_intr(0, desc);
+	lapic_register_intr(0);
 	apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);	/* Fixed mode */
-	legacy_pic->chip->unmask(0);
+	legacy_pic->unmask(0);
 
 	if (timer_irq_works()) {
 		apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
 		goto out;
 	}
 	local_irq_disable();
-	legacy_pic->chip->mask(0);
+	legacy_pic->mask(0);
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
 	apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
 
@@ -3244,49 +3054,42 @@
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int irq_want, int node)
+unsigned int create_irq_nr(unsigned int from, int node)
 {
-	/* Allocate an unused irq */
-	unsigned int irq;
-	unsigned int new;
+	struct irq_cfg *cfg;
 	unsigned long flags;
-	struct irq_cfg *cfg_new = NULL;
-	struct irq_desc *desc_new = NULL;
+	unsigned int ret = 0;
+	int irq;
 
-	irq = 0;
-	if (irq_want < nr_irqs_gsi)
-		irq_want = nr_irqs_gsi;
+	if (from < nr_irqs_gsi)
+		from = nr_irqs_gsi;
+
+	irq = alloc_irq_from(from, node);
+	if (irq < 0)
+		return 0;
+	cfg = alloc_irq_cfg(irq, node);
+	if (!cfg) {
+		free_irq_at(irq, NULL);
+		return 0;
+	}
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	for (new = irq_want; new < nr_irqs; new++) {
-		desc_new = irq_to_desc_alloc_node(new, node);
-		if (!desc_new) {
-			printk(KERN_INFO "can not get irq_desc for %d\n", new);
-			continue;
-		}
-		cfg_new = desc_new->chip_data;
-
-		if (cfg_new->vector != 0)
-			continue;
-
-		desc_new = move_irq_desc(desc_new, node);
-		cfg_new = desc_new->chip_data;
-
-		if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
-			irq = new;
-		break;
-	}
+	if (!__assign_irq_vector(irq, cfg, apic->target_cpus()))
+		ret = irq;
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
-	if (irq > 0)
-		dynamic_irq_init_keep_chip_data(irq);
-
-	return irq;
+	if (ret) {
+		set_irq_chip_data(irq, cfg);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST);
+	} else {
+		free_irq_at(irq, cfg);
+	}
+	return ret;
 }
 
 int create_irq(void)
 {
-	int node = cpu_to_node(boot_cpu_id);
+	int node = cpu_to_node(0);
 	unsigned int irq_want;
 	int irq;
 
@@ -3301,14 +3104,17 @@
 
 void destroy_irq(unsigned int irq)
 {
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 	unsigned long flags;
 
-	dynamic_irq_cleanup_keep_chip_data(irq);
+	irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
 
-	free_irte(irq);
+	if (intr_remapping_enabled)
+		free_irte(irq);
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	__clear_irq_vector(irq, get_irq_chip_data(irq));
+	__clear_irq_vector(irq, cfg);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
+	free_irq_at(irq, cfg);
 }
 
 /*
@@ -3332,7 +3138,7 @@
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
 
-	if (irq_remapped(irq)) {
+	if (irq_remapped(get_irq_chip_data(irq))) {
 		struct irte irte;
 		int ir_index;
 		u16 sub_handle;
@@ -3340,14 +3146,7 @@
 		ir_index = map_irq_to_irte_handle(irq, &sub_handle);
 		BUG_ON(ir_index == -1);
 
-		memset (&irte, 0, sizeof(irte));
-
-		irte.present = 1;
-		irte.dst_mode = apic->irq_dest_mode;
-		irte.trigger_mode = 0; /* edge */
-		irte.dlvry_mode = apic->irq_delivery_mode;
-		irte.vector = cfg->vector;
-		irte.dest_id = IRTE_DEST(dest);
+		prepare_irte(&irte, cfg->vector, dest);
 
 		/* Set source-id of interrupt request */
 		if (pdev)
@@ -3392,26 +3191,24 @@
 }
 
 #ifdef CONFIG_SMP
-static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	struct msi_msg msg;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	get_cached_msi_msg_desc(desc, &msg);
+	__get_cached_msi_msg(data->msi_desc, &msg);
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
 	msg.data |= MSI_DATA_VECTOR(cfg->vector);
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
-	write_msi_msg_desc(desc, &msg);
+	__write_msi_msg(data->msi_desc, &msg);
 
 	return 0;
 }
@@ -3421,17 +3218,17 @@
  * done in the process context using interrupt-remapping hardware.
  */
 static int
-ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+ir_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
-	unsigned int dest;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct irte irte;
 
 	if (get_irte(irq, &irte))
 		return -1;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
 	irte.vector = cfg->vector;
@@ -3461,27 +3258,27 @@
  * which implement the MSI or MSI-X Capability Structure.
  */
 static struct irq_chip msi_chip = {
-	.name		= "PCI-MSI",
-	.unmask		= unmask_msi_irq,
-	.mask		= mask_msi_irq,
-	.ack		= ack_apic_edge,
+	.name			= "PCI-MSI",
+	.irq_unmask		= unmask_msi_irq,
+	.irq_mask		= mask_msi_irq,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_msi_irq_affinity,
+	.irq_set_affinity	= msi_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip msi_ir_chip = {
-	.name		= "IR-PCI-MSI",
-	.unmask		= unmask_msi_irq,
-	.mask		= mask_msi_irq,
+	.name			= "IR-PCI-MSI",
+	.irq_unmask		= unmask_msi_irq,
+	.irq_mask		= mask_msi_irq,
 #ifdef CONFIG_INTR_REMAP
-	.ack		= ir_ack_apic_edge,
+	.irq_ack		= ir_ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= ir_set_msi_irq_affinity,
+	.irq_set_affinity	= ir_msi_set_affinity,
 #endif
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 /*
@@ -3513,8 +3310,8 @@
 
 static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 {
-	int ret;
 	struct msi_msg msg;
+	int ret;
 
 	ret = msi_compose_msg(dev, irq, &msg, -1);
 	if (ret < 0)
@@ -3523,12 +3320,8 @@
 	set_irq_msi(irq, msidesc);
 	write_msi_msg(irq, &msg);
 
-	if (irq_remapped(irq)) {
-		struct irq_desc *desc = irq_to_desc(irq);
-		/*
-		 * irq migration in process context
-		 */
-		desc->status |= IRQ_MOVE_PCNTXT;
+	if (irq_remapped(get_irq_chip_data(irq))) {
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 		set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
 	} else
 		set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
@@ -3540,13 +3333,10 @@
 
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	unsigned int irq;
-	int ret, sub_handle;
+	int node, ret, sub_handle, index = 0;
+	unsigned int irq, irq_want;
 	struct msi_desc *msidesc;
-	unsigned int irq_want;
 	struct intel_iommu *iommu = NULL;
-	int index = 0;
-	int node;
 
 	/* x86 doesn't support multiple MSI yet */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
@@ -3606,18 +3396,17 @@
 
 #if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
 #ifdef CONFIG_SMP
-static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct msi_msg msg;
-	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
 	dmar_msi_read(irq, &msg);
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
@@ -3633,14 +3422,14 @@
 #endif /* CONFIG_SMP */
 
 static struct irq_chip dmar_msi_type = {
-	.name = "DMAR_MSI",
-	.unmask = dmar_msi_unmask,
-	.mask = dmar_msi_mask,
-	.ack = ack_apic_edge,
+	.name			= "DMAR_MSI",
+	.irq_unmask		= dmar_msi_unmask,
+	.irq_mask		= dmar_msi_mask,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = dmar_msi_set_affinity,
+	.irq_set_affinity	= dmar_msi_set_affinity,
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 int arch_setup_dmar_msi(unsigned int irq)
@@ -3661,26 +3450,24 @@
 #ifdef CONFIG_HPET_TIMER
 
 #ifdef CONFIG_SMP
-static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(struct irq_data *data,
+				 const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	struct msi_msg msg;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	hpet_msi_read(irq, &msg);
+	hpet_msi_read(data->handler_data, &msg);
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
 	msg.data |= MSI_DATA_VECTOR(cfg->vector);
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
-	hpet_msi_write(irq, &msg);
+	hpet_msi_write(data->handler_data, &msg);
 
 	return 0;
 }
@@ -3688,34 +3475,33 @@
 #endif /* CONFIG_SMP */
 
 static struct irq_chip ir_hpet_msi_type = {
-	.name = "IR-HPET_MSI",
-	.unmask = hpet_msi_unmask,
-	.mask = hpet_msi_mask,
+	.name			= "IR-HPET_MSI",
+	.irq_unmask		= hpet_msi_unmask,
+	.irq_mask		= hpet_msi_mask,
 #ifdef CONFIG_INTR_REMAP
-	.ack = ir_ack_apic_edge,
+	.irq_ack		= ir_ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = ir_set_msi_irq_affinity,
+	.irq_set_affinity	= ir_msi_set_affinity,
 #endif
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip hpet_msi_type = {
 	.name = "HPET_MSI",
-	.unmask = hpet_msi_unmask,
-	.mask = hpet_msi_mask,
-	.ack = ack_apic_edge,
+	.irq_unmask = hpet_msi_unmask,
+	.irq_mask = hpet_msi_mask,
+	.irq_ack = ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = hpet_msi_set_affinity,
+	.irq_set_affinity = hpet_msi_set_affinity,
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger = ioapic_retrigger_irq,
 };
 
 int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
-	int ret;
 	struct msi_msg msg;
-	struct irq_desc *desc = irq_to_desc(irq);
+	int ret;
 
 	if (intr_remapping_enabled) {
 		struct intel_iommu *iommu = map_hpet_to_ir(id);
@@ -3733,9 +3519,9 @@
 	if (ret < 0)
 		return ret;
 
-	hpet_msi_write(irq, &msg);
-	desc->status |= IRQ_MOVE_PCNTXT;
-	if (irq_remapped(irq))
+	hpet_msi_write(get_irq_data(irq), &msg);
+	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+	if (irq_remapped(get_irq_chip_data(irq)))
 		set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
 					      handle_edge_irq, "edge");
 	else
@@ -3768,33 +3554,30 @@
 	write_ht_irq_msg(irq, &msg);
 }
 
-static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	target_ht_irq(irq, dest, cfg->vector);
-
+	target_ht_irq(data->irq, dest, cfg->vector);
 	return 0;
 }
 
 #endif
 
 static struct irq_chip ht_irq_chip = {
-	.name		= "PCI-HT",
-	.mask		= mask_ht_irq,
-	.unmask		= unmask_ht_irq,
-	.ack		= ack_apic_edge,
+	.name			= "PCI-HT",
+	.irq_mask		= mask_ht_irq,
+	.irq_unmask		= unmask_ht_irq,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ht_irq_affinity,
+	.irq_set_affinity	= ht_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
@@ -3885,14 +3668,13 @@
 	if (nr < nr_irqs)
 		nr_irqs = nr;
 
-	return 0;
+	return NR_IRQS_LEGACY;
 }
 #endif
 
 static int __io_apic_set_pci_routing(struct device *dev, int irq,
 				struct io_apic_irq_attr *irq_attr)
 {
-	struct irq_desc *desc;
 	struct irq_cfg *cfg;
 	int node;
 	int ioapic, pin;
@@ -3908,13 +3690,11 @@
 	if (dev)
 		node = dev_to_node(dev);
 	else
-		node = cpu_to_node(boot_cpu_id);
+		node = cpu_to_node(0);
 
-	desc = irq_to_desc_alloc_node(irq, node);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc %d\n", irq);
+	cfg = alloc_irq_and_cfg_at(irq, node);
+	if (!cfg)
 		return 0;
-	}
 
 	pin = irq_attr->ioapic_pin;
 	trigger = irq_attr->trigger;
@@ -3924,15 +3704,14 @@
 	 * IRQs < 16 are already in the irq_2_pin[] map
 	 */
 	if (irq >= legacy_pic->nr_legacy_irqs) {
-		cfg = desc->chip_data;
-		if (add_pin_to_irq_node_nopanic(cfg, node, ioapic, pin)) {
+		if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) {
 			printk(KERN_INFO "can not add pin %d for irq %d\n",
 				pin, irq);
 			return 0;
 		}
 	}
 
-	setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+	setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity);
 
 	return 0;
 }
@@ -4125,14 +3904,14 @@
 		 */
 		if (desc->status &
 		    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-			mask = desc->affinity;
+			mask = desc->irq_data.affinity;
 		else
 			mask = apic->target_cpus();
 
 		if (intr_remapping_enabled)
-			set_ir_ioapic_affinity_irq_desc(desc, mask);
+			ir_ioapic_set_affinity(&desc->irq_data, mask, false);
 		else
-			set_ioapic_affinity_irq_desc(desc, mask);
+			ioapic_set_affinity(&desc->irq_data, mask, false);
 	}
 
 }
@@ -4316,19 +4095,18 @@
 void __init pre_init_apic_IRQ0(void)
 {
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 
 	printk(KERN_INFO "Early APIC setup for system timer0\n");
 #ifndef CONFIG_SMP
 	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
 #endif
-	desc = irq_to_desc_alloc_node(0, 0);
+	/* Make sure the irq descriptor is set up */
+	cfg = alloc_irq_and_cfg_at(0, 0);
 
 	setup_local_APIC();
 
-	cfg = irq_cfg(0);
 	add_pin_to_irq_node(cfg, 0, 0, 0);
 	set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
 
-	setup_IO_APIC_irq(0, 0, 0, desc, 0, 0);
+	setup_ioapic_irq(0, 0, 0, cfg, 0, 0);
 }
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index a43f71c..c90041c 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -178,7 +178,7 @@
 error:
 	if (nmi_watchdog == NMI_IO_APIC) {
 		if (!timer_through_8259)
-			legacy_pic->chip->mask(0);
+			legacy_pic->mask(0);
 		on_each_cpu(__acpi_nmi_disable, NULL, 1);
 	}
 
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 3e28401..960f26a 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -26,6 +26,7 @@
 #include <linux/nodemask.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/kernel.h>
@@ -88,7 +89,7 @@
 	node_end_pfn[node] =
 		 MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size);
 
-	e820_register_active_regions(node, node_start_pfn[node],
+	memblock_x86_register_active_regions(node, node_start_pfn[node],
 						node_end_pfn[node]);
 
 	memory_present(node, node_start_pfn[node], node_end_pfn[node]);
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 83e9be4..f9e4e6a 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -54,6 +54,9 @@
  */
 void __init default_setup_apic_routing(void)
 {
+
+	enable_IR_x2apic();
+
 #ifdef CONFIG_X86_X2APIC
 	if (x2apic_mode
 #ifdef CONFIG_X86_UV
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 4c9c67b..fbbc4da 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1926,6 +1926,7 @@
 	.unlocked_ioctl	= do_ioctl,
 	.open		= do_open,
 	.release	= do_release,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice apm_device = {
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index fc999e6..13a3891 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -2,7 +2,8 @@
 #include <linux/sched.h>
 #include <linux/kthread.h>
 #include <linux/workqueue.h>
-#include <asm/e820.h>
+#include <linux/memblock.h>
+
 #include <asm/proto.h>
 
 /*
@@ -18,10 +19,12 @@
 static unsigned __read_mostly corruption_check_size = 64*1024;
 static unsigned __read_mostly corruption_check_period = 60; /* seconds */
 
-static struct e820entry scan_areas[MAX_SCAN_AREAS];
+static struct scan_area {
+	u64 addr;
+	u64 size;
+} scan_areas[MAX_SCAN_AREAS];
 static int num_scan_areas;
 
-
 static __init int set_corruption_check(char *arg)
 {
 	char *end;
@@ -81,9 +84,9 @@
 
 	while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) {
 		u64 size;
-		addr = find_e820_area_size(addr, &size, PAGE_SIZE);
+		addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE);
 
-		if (!(addr + 1))
+		if (addr == MEMBLOCK_ERROR)
 			break;
 
 		if (addr >= corruption_check_size)
@@ -92,7 +95,7 @@
 		if ((addr + size) > corruption_check_size)
 			size = corruption_check_size - addr;
 
-		e820_update_range(addr, size, E820_RAM, E820_RESERVED);
+		memblock_x86_reserve_range(addr, addr + size, "SCAN RAM");
 		scan_areas[num_scan_areas].addr = addr;
 		scan_areas[num_scan_areas].size = size;
 		num_scan_areas++;
@@ -105,7 +108,6 @@
 
 	printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
 	       num_scan_areas);
-	update_e820();
 }
 
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ba5f62f..9e093f8 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -148,7 +148,7 @@
 {
 #ifdef CONFIG_SMP
 	/* calling is from identify_secondary_cpu() ? */
-	if (c->cpu_index == boot_cpu_id)
+	if (!c->cpu_index)
 		return;
 
 	/*
@@ -253,37 +253,51 @@
 #endif
 
 /*
- * Fixup core topology information for AMD multi-node processors.
- * Assumption: Number of cores in each internal node is the same.
+ * Fixup core topology information for
+ * (1) AMD multi-node processors
+ *     Assumption: Number of cores in each internal node is the same.
+ * (2) AMD processors supporting compute units
  */
 #ifdef CONFIG_X86_HT
-static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
+static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
 {
-	unsigned long long value;
-	u32 nodes, cores_per_node;
+	u32 nodes;
+	u8 node_id;
 	int cpu = smp_processor_id();
 
-	if (!cpu_has(c, X86_FEATURE_NODEID_MSR))
+	/* get information required for multi-node processors */
+	if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+		nodes = ((ecx >> 8) & 7) + 1;
+		node_id = ecx & 7;
+
+		/* get compute unit information */
+		smp_num_siblings = ((ebx >> 8) & 3) + 1;
+		c->compute_unit_id = ebx & 0xff;
+	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
+		u64 value;
+
+		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		nodes = ((value >> 3) & 7) + 1;
+		node_id = value & 7;
+	} else
 		return;
 
-	/* fixup topology information only once for a core */
-	if (cpu_has(c, X86_FEATURE_AMD_DCM))
-		return;
+	/* fixup multi-node processor information */
+	if (nodes > 1) {
+		u32 cores_per_node;
 
-	rdmsrl(MSR_FAM10H_NODE_ID, value);
+		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+		cores_per_node = c->x86_max_cores / nodes;
 
-	nodes = ((value >> 3) & 7) + 1;
-	if (nodes == 1)
-		return;
+		/* store NodeID, use llc_shared_map to store sibling info */
+		per_cpu(cpu_llc_id, cpu) = node_id;
 
-	set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-	cores_per_node = c->x86_max_cores / nodes;
-
-	/* store NodeID, use llc_shared_map to store sibling info */
-	per_cpu(cpu_llc_id, cpu) = value & 7;
-
-	/* fixup core id to be in range from 0 to (cores_per_node - 1) */
-	c->cpu_core_id = c->cpu_core_id % cores_per_node;
+		/* core id to be in range from 0 to (cores_per_node - 1) */
+		c->cpu_core_id = c->cpu_core_id % cores_per_node;
+	}
 }
 #endif
 
@@ -304,9 +318,7 @@
 	c->phys_proc_id = c->initial_apicid >> bits;
 	/* use socket ID also for last level cache */
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
-	/* fixup topology information on multi-node processors */
-	if ((c->x86 == 0x10) && (c->x86_model == 9))
-		amd_fixup_dcm(c);
+	amd_get_topology(c);
 #endif
 }
 
@@ -412,6 +424,23 @@
 			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
 	}
 #endif
+
+	/* We need to do the following only once */
+	if (c != &boot_cpu_data)
+		return;
+
+	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+
+		if (c->x86 > 0x10 ||
+		    (c->x86 == 0x10 && c->x86_model >= 0x2)) {
+			u64 val;
+
+			rdmsrl(MSR_K7_HWCR, val);
+			if (!(val & BIT(24)))
+				printk(KERN_WARNING FW_BUG "TSC doesn't count "
+					"with P0 frequency!\n");
+		}
+	}
 }
 
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
@@ -523,7 +552,7 @@
 #endif
 
 	if (c->extended_cpuid_level >= 0x80000006) {
-		if ((c->x86 >= 0x0f) && (cpuid_edx(0x80000006) & 0xf000))
+		if (cpuid_edx(0x80000006) & 0xf000)
 			num_cache_leaves = 4;
 		else
 			num_cache_leaves = 3;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f2f9ac7..4b68bda 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -665,7 +665,7 @@
 		this_cpu->c_early_init(c);
 
 #ifdef CONFIG_SMP
-	c->cpu_index = boot_cpu_id;
+	c->cpu_index = 0;
 #endif
 	filter_cpuid_features(c, false);
 }
@@ -704,16 +704,21 @@
 }
 
 /*
- * The NOPL instruction is supposed to exist on all CPUs with
- * family >= 6; unfortunately, that's not true in practice because
- * of early VIA chips and (more importantly) broken virtualizers that
- * are not easy to detect.  In the latter case it doesn't even *fail*
- * reliably, so probing for it doesn't even work.  Disable it completely
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
  * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
  */
 static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
 	clear_cpu_cap(c, X86_FEATURE_NOPL);
+#else
+	set_cpu_cap(c, X86_FEATURE_NOPL);
+#endif
 }
 
 static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
@@ -1264,13 +1269,6 @@
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	/*
-	 * Force FPU initialization:
-	 */
-	current_thread_info()->status = 0;
-	clear_used_math();
-	mxcsr_feature_mask_init();
-
 	fpu_init();
 	xsave_init();
 }
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index f668bb1..e765633 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -32,6 +32,7 @@
 extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
+extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b438944..695f177 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -170,7 +170,7 @@
 {
 #ifdef CONFIG_SMP
 	/* calling is from identify_secondary_cpu() ? */
-	if (c->cpu_index == boot_cpu_id)
+	if (!c->cpu_index)
 		return;
 
 	/*
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 898c2f4..12cd823 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -17,7 +17,7 @@
 
 #include <asm/processor.h>
 #include <linux/smp.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/smp.h>
 
 #define LVL_1_INST	1
@@ -306,7 +306,7 @@
 	ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
 };
 
-#ifdef CONFIG_CPU_SUP_AMD
+#ifdef CONFIG_AMD_NB
 
 /*
  * L3 cache descriptors
@@ -369,7 +369,7 @@
 			return;
 
 	/* not in virtualized environments */
-	if (num_k8_northbridges == 0)
+	if (k8_northbridges.num == 0)
 		return;
 
 	/*
@@ -377,7 +377,7 @@
 	 * never freed but this is done only on shutdown so it doesn't matter.
 	 */
 	if (!l3_caches) {
-		int size = num_k8_northbridges * sizeof(struct amd_l3_cache *);
+		int size = k8_northbridges.num * sizeof(struct amd_l3_cache *);
 
 		l3_caches = kzalloc(size, GFP_ATOMIC);
 		if (!l3_caches)
@@ -556,12 +556,12 @@
 static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
 		show_cache_disable_1, store_cache_disable_1);
 
-#else	/* CONFIG_CPU_SUP_AMD */
+#else	/* CONFIG_AMD_NB */
 static void __cpuinit
 amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index)
 {
 };
-#endif /* CONFIG_CPU_SUP_AMD */
+#endif /* CONFIG_AMD_NB */
 
 static int
 __cpuinit cpuid4_cache_lookup_regs(int index,
@@ -1000,7 +1000,7 @@
 
 static struct attribute *default_l3_attrs[] = {
 	DEFAULT_SYSFS_CACHE_ATTRS,
-#ifdef CONFIG_CPU_SUP_AMD
+#ifdef CONFIG_AMD_NB
 	&cache_disable_0.attr,
 	&cache_disable_1.attr,
 #endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 8a85dd1..1e8d66c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -192,6 +192,7 @@
 	.release	= seq_release,
 	.read		= seq_read,
 	.write		= severities_coverage_write,
+	.llseek		= seq_lseek,
 };
 
 static int __init severities_debugfs_init(void)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ed41562..7a35b72 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1665,6 +1665,7 @@
 	.read			= mce_read,
 	.poll			= mce_poll,
 	.unlocked_ioctl		= mce_ioctl,
+	.llseek		= no_llseek,
 };
 EXPORT_SYMBOL_GPL(mce_chrdev_ops);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 39aaee5..80c4823 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -131,7 +131,8 @@
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block;
 	struct thresh_restart tr;
-	u8 lvt_off;
+	int lvt_off = -1;
+	u8 offset;
 
 	for (bank = 0; bank < NR_BANKS; ++bank) {
 		for (block = 0; block < NR_BLOCKS; ++block) {
@@ -162,8 +163,28 @@
 			if (shared_bank[bank] && c->cpu_core_id)
 				break;
 #endif
-			lvt_off = setup_APIC_eilvt_mce(THRESHOLD_APIC_VECTOR,
-						       APIC_EILVT_MSG_FIX, 0);
+			offset = (high & MASK_LVTOFF_HI) >> 20;
+			if (lvt_off < 0) {
+				if (setup_APIC_eilvt(offset,
+						     THRESHOLD_APIC_VECTOR,
+						     APIC_EILVT_MSG_FIX, 0)) {
+					pr_err(FW_BUG "cpu %d, failed to "
+					       "setup threshold interrupt "
+					       "for bank %d, block %d "
+					       "(MSR%08X=0x%x%08x)",
+					       smp_processor_id(), bank, block,
+					       address, high, low);
+					continue;
+				}
+				lvt_off = offset;
+			} else if (lvt_off != offset) {
+				pr_err(FW_BUG "cpu %d, invalid threshold "
+				       "interrupt offset %d for bank %d,"
+				       "block %d (MSR%08X=0x%x%08x)",
+				       smp_processor_id(), lvt_off, bank,
+				       block, address, high, low);
+				continue;
+			}
 
 			high &= ~MASK_LVTOFF_HI;
 			high |= lvt_off << 20;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 169d880..4b68326 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -350,7 +350,7 @@
 
 static void unexpected_thermal_interrupt(void)
 {
-	printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
+	printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
 			smp_processor_id());
 	add_taint(TAINT_MACHINE_CHECK);
 }
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index c5f59d0..ac140c7 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -827,7 +827,7 @@
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		return 0;
-	if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
+	if (boot_cpu_data.x86 < 0xf)
 		return 0;
 	/* In case some hypervisor doesn't pass SYSCFG through: */
 	if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0)
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7d28d7d..9f27228 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -64,18 +64,59 @@
 	}
 }
 
+/* Get the size of contiguous MTRR range */
+static u64 get_mtrr_size(u64 mask)
+{
+	u64 size;
+
+	mask >>= PAGE_SHIFT;
+	mask |= size_or_mask;
+	size = -mask;
+	size <<= PAGE_SHIFT;
+	return size;
+}
+
 /*
- * Returns the effective MTRR type for the region
- * Error returns:
- * - 0xFE - when the range is "not entirely covered" by _any_ var range MTRR
- * - 0xFF - when MTRR is not enabled
+ * Check and return the effective type for MTRR-MTRR type overlap.
+ * Returns 1 if the effective type is UNCACHEABLE, else returns 0
  */
-u8 mtrr_type_lookup(u64 start, u64 end)
+static int check_type_overlap(u8 *prev, u8 *curr)
+{
+	if (*prev == MTRR_TYPE_UNCACHABLE || *curr == MTRR_TYPE_UNCACHABLE) {
+		*prev = MTRR_TYPE_UNCACHABLE;
+		*curr = MTRR_TYPE_UNCACHABLE;
+		return 1;
+	}
+
+	if ((*prev == MTRR_TYPE_WRBACK && *curr == MTRR_TYPE_WRTHROUGH) ||
+	    (*prev == MTRR_TYPE_WRTHROUGH && *curr == MTRR_TYPE_WRBACK)) {
+		*prev = MTRR_TYPE_WRTHROUGH;
+		*curr = MTRR_TYPE_WRTHROUGH;
+	}
+
+	if (*prev != *curr) {
+		*prev = MTRR_TYPE_UNCACHABLE;
+		*curr = MTRR_TYPE_UNCACHABLE;
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Error/Semi-error returns:
+ * 0xFF - when MTRR is not enabled
+ * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
+ *		corresponds only to [start:*partial_end].
+ *		Caller has to lookup again for [*partial_end:end].
+ */
+static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 {
 	int i;
 	u64 base, mask;
 	u8 prev_match, curr_match;
 
+	*repeat = 0;
 	if (!mtrr_state_set)
 		return 0xFF;
 
@@ -126,8 +167,34 @@
 
 		start_state = ((start & mask) == (base & mask));
 		end_state = ((end & mask) == (base & mask));
-		if (start_state != end_state)
-			return 0xFE;
+
+		if (start_state != end_state) {
+			/*
+			 * We have start:end spanning across an MTRR.
+			 * We split the region into
+			 * either
+			 * (start:mtrr_end) (mtrr_end:end)
+			 * or
+			 * (start:mtrr_start) (mtrr_start:end)
+			 * depending on kind of overlap.
+			 * Return the type for first region and a pointer to
+			 * the start of second region so that caller will
+			 * lookup again on the second region.
+			 * Note: This way we handle multiple overlaps as well.
+			 */
+			if (start_state)
+				*partial_end = base + get_mtrr_size(mask);
+			else
+				*partial_end = base;
+
+			if (unlikely(*partial_end <= start)) {
+				WARN_ON(1);
+				*partial_end = start + PAGE_SIZE;
+			}
+
+			end = *partial_end - 1; /* end is inclusive */
+			*repeat = 1;
+		}
 
 		if ((start & mask) != (base & mask))
 			continue;
@@ -138,21 +205,8 @@
 			continue;
 		}
 
-		if (prev_match == MTRR_TYPE_UNCACHABLE ||
-		    curr_match == MTRR_TYPE_UNCACHABLE) {
-			return MTRR_TYPE_UNCACHABLE;
-		}
-
-		if ((prev_match == MTRR_TYPE_WRBACK &&
-		     curr_match == MTRR_TYPE_WRTHROUGH) ||
-		    (prev_match == MTRR_TYPE_WRTHROUGH &&
-		     curr_match == MTRR_TYPE_WRBACK)) {
-			prev_match = MTRR_TYPE_WRTHROUGH;
-			curr_match = MTRR_TYPE_WRTHROUGH;
-		}
-
-		if (prev_match != curr_match)
-			return MTRR_TYPE_UNCACHABLE;
+		if (check_type_overlap(&prev_match, &curr_match))
+			return curr_match;
 	}
 
 	if (mtrr_tom2) {
@@ -166,6 +220,36 @@
 	return mtrr_state.def_type;
 }
 
+/*
+ * Returns the effective MTRR type for the region
+ * Error return:
+ * 0xFF - when MTRR is not enabled
+ */
+u8 mtrr_type_lookup(u64 start, u64 end)
+{
+	u8 type, prev_type;
+	int repeat;
+	u64 partial_end;
+
+	type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+
+	/*
+	 * Common path is with repeat = 0.
+	 * However, we can have cases where [start:end] spans across some
+	 * MTRR range. Do repeated lookups for that case here.
+	 */
+	while (repeat) {
+		prev_type = type;
+		start = partial_end;
+		type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+
+		if (check_type_overlap(&prev_type, &type))
+			return type;
+	}
+
+	return type;
+}
+
 /* Get the MSR pair relating to a var range */
 static void
 get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 03a5b03..fe73c18 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -531,7 +531,7 @@
 /*
  * Setup the hardware configuration for a given attr_type
  */
-static int __hw_perf_event_init(struct perf_event *event)
+static int __x86_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
@@ -584,7 +584,7 @@
 	}
 }
 
-void hw_perf_disable(void)
+static void x86_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -619,7 +619,7 @@
 	}
 }
 
-static const struct pmu pmu;
+static struct pmu pmu;
 
 static inline int is_x86_event(struct perf_event *event)
 {
@@ -801,10 +801,10 @@
 		hwc->last_tag == cpuc->tags[i];
 }
 
-static int x86_pmu_start(struct perf_event *event);
-static void x86_pmu_stop(struct perf_event *event);
+static void x86_pmu_start(struct perf_event *event, int flags);
+static void x86_pmu_stop(struct perf_event *event, int flags);
 
-void hw_perf_enable(void)
+static void x86_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *event;
@@ -840,7 +840,14 @@
 			    match_prev_assignment(hwc, cpuc, i))
 				continue;
 
-			x86_pmu_stop(event);
+			/*
+			 * Ensure we don't accidentally enable a stopped
+			 * counter simply because we rescheduled.
+			 */
+			if (hwc->state & PERF_HES_STOPPED)
+				hwc->state |= PERF_HES_ARCH;
+
+			x86_pmu_stop(event, PERF_EF_UPDATE);
 		}
 
 		for (i = 0; i < cpuc->n_events; i++) {
@@ -852,7 +859,10 @@
 			else if (i < n_running)
 				continue;
 
-			x86_pmu_start(event);
+			if (hwc->state & PERF_HES_ARCH)
+				continue;
+
+			x86_pmu_start(event, PERF_EF_RELOAD);
 		}
 		cpuc->n_added = 0;
 		perf_events_lapic_init();
@@ -953,15 +963,12 @@
 }
 
 /*
- * activate a single event
+ * Add a single event to the PMU.
  *
  * The event is added to the group of enabled events
  * but only if it can be scehduled with existing events.
- *
- * Called with PMU disabled. If successful and return value 1,
- * then guaranteed to call perf_enable() and hw_perf_enable()
  */
-static int x86_pmu_enable(struct perf_event *event)
+static int x86_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc;
@@ -970,58 +977,67 @@
 
 	hwc = &event->hw;
 
+	perf_pmu_disable(event->pmu);
 	n0 = cpuc->n_events;
-	n = collect_events(cpuc, event, false);
-	if (n < 0)
-		return n;
+	ret = n = collect_events(cpuc, event, false);
+	if (ret < 0)
+		goto out;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_ARCH;
 
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
-	 * at commit time(->commit_txn) as a whole
+	 * at commit time (->commit_txn) as a whole
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
-		goto out;
+		goto done_collect;
 
 	ret = x86_pmu.schedule_events(cpuc, n, assign);
 	if (ret)
-		return ret;
+		goto out;
 	/*
 	 * copy new assignment, now we know it is possible
 	 * will be used by hw_perf_enable()
 	 */
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
-out:
+done_collect:
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
 
-	return 0;
+	ret = 0;
+out:
+	perf_pmu_enable(event->pmu);
+	return ret;
 }
 
-static int x86_pmu_start(struct perf_event *event)
+static void x86_pmu_start(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx = event->hw.idx;
 
-	if (idx == -1)
-		return -EAGAIN;
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
 
-	x86_perf_event_set_period(event);
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		x86_perf_event_set_period(event);
+	}
+
+	event->hw.state = 0;
+
 	cpuc->events[idx] = event;
 	__set_bit(idx, cpuc->active_mask);
 	__set_bit(idx, cpuc->running);
 	x86_pmu.enable(event);
 	perf_event_update_userpage(event);
-
-	return 0;
-}
-
-static void x86_pmu_unthrottle(struct perf_event *event)
-{
-	int ret = x86_pmu_start(event);
-	WARN_ON_ONCE(ret);
 }
 
 void perf_event_print_debug(void)
@@ -1078,27 +1094,29 @@
 	local_irq_restore(flags);
 }
 
-static void x86_pmu_stop(struct perf_event *event)
+static void x86_pmu_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
 
-	if (!__test_and_clear_bit(idx, cpuc->active_mask))
-		return;
+	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+		x86_pmu.disable(event);
+		cpuc->events[hwc->idx] = NULL;
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+	}
 
-	x86_pmu.disable(event);
-
-	/*
-	 * Drain the remaining delta count out of a event
-	 * that we are disabling:
-	 */
-	x86_perf_event_update(event);
-
-	cpuc->events[idx] = NULL;
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of a event
+		 * that we are disabling:
+		 */
+		x86_perf_event_update(event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
 }
 
-static void x86_pmu_disable(struct perf_event *event)
+static void x86_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int i;
@@ -1111,7 +1129,7 @@
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		return;
 
-	x86_pmu_stop(event);
+	x86_pmu_stop(event, PERF_EF_UPDATE);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event_list[i]) {
@@ -1134,7 +1152,6 @@
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc;
 	struct perf_event *event;
-	struct hw_perf_event *hwc;
 	int idx, handled = 0;
 	u64 val;
 
@@ -1155,7 +1172,6 @@
 		}
 
 		event = cpuc->events[idx];
-		hwc = &event->hw;
 
 		val = x86_perf_event_update(event);
 		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
@@ -1171,7 +1187,7 @@
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu_stop(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	if (handled)
@@ -1180,25 +1196,6 @@
 	return handled;
 }
 
-void smp_perf_pending_interrupt(struct pt_regs *regs)
-{
-	irq_enter();
-	ack_APIC_irq();
-	inc_irq_stat(apic_pending_irqs);
-	perf_event_do_pending();
-	irq_exit();
-}
-
-void set_perf_event_pending(void)
-{
-#ifdef CONFIG_X86_LOCAL_APIC
-	if (!x86_pmu.apic || !x86_pmu_initialized())
-		return;
-
-	apic->send_IPI_self(LOCAL_PENDING_VECTOR);
-#endif
-}
-
 void perf_events_lapic_init(void)
 {
 	if (!x86_pmu.apic || !x86_pmu_initialized())
@@ -1388,7 +1385,6 @@
 		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 	}
 	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
-	perf_max_events = x86_pmu.num_counters;
 
 	if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
@@ -1424,6 +1420,7 @@
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
+	perf_pmu_register(&pmu);
 	perf_cpu_notifier(x86_pmu_notifier);
 }
 
@@ -1437,10 +1434,11 @@
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void x86_pmu_start_txn(const struct pmu *pmu)
+static void x86_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuc->group_flag |= PERF_EVENT_TXN;
 	cpuc->n_txn = 0;
 }
@@ -1450,7 +1448,7 @@
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void x86_pmu_cancel_txn(const struct pmu *pmu)
+static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -1460,6 +1458,7 @@
 	 */
 	cpuc->n_added -= cpuc->n_txn;
 	cpuc->n_events -= cpuc->n_txn;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -1467,7 +1466,7 @@
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int x86_pmu_commit_txn(const struct pmu *pmu)
+static int x86_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int assign[X86_PMC_IDX_MAX];
@@ -1489,22 +1488,10 @@
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
-
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= x86_pmu_enable,
-	.disable	= x86_pmu_disable,
-	.start		= x86_pmu_start,
-	.stop		= x86_pmu_stop,
-	.read		= x86_pmu_read,
-	.unthrottle	= x86_pmu_unthrottle,
-	.start_txn	= x86_pmu_start_txn,
-	.cancel_txn	= x86_pmu_cancel_txn,
-	.commit_txn	= x86_pmu_commit_txn,
-};
-
 /*
  * validate that we can schedule this event
  */
@@ -1579,12 +1566,22 @@
 	return ret;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+int x86_pmu_event_init(struct perf_event *event)
 {
-	const struct pmu *tmp;
+	struct pmu *tmp;
 	int err;
 
-	err = __hw_perf_event_init(event);
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
+	err = __x86_pmu_event_init(event);
 	if (!err) {
 		/*
 		 * we temporarily connect event to its pmu
@@ -1604,27 +1601,32 @@
 	if (err) {
 		if (event->destroy)
 			event->destroy(event);
-		return ERR_PTR(err);
 	}
 
-	return &pmu;
+	return err;
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= x86_pmu_enable,
+	.pmu_disable	= x86_pmu_disable,
+
+	.event_init	= x86_pmu_event_init,
+
+	.add		= x86_pmu_add,
+	.del		= x86_pmu_del,
+	.start		= x86_pmu_start,
+	.stop		= x86_pmu_stop,
+	.read		= x86_pmu_read,
+
+	.start_txn	= x86_pmu_start_txn,
+	.cancel_txn	= x86_pmu_cancel_txn,
+	.commit_txn	= x86_pmu_commit_txn,
+};
+
 /*
  * callchain support
  */
 
-static inline
-void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
-
-
 static void
 backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
 {
@@ -1645,7 +1647,7 @@
 {
 	struct perf_callchain_entry *entry = data;
 
-	callchain_store(entry, addr);
+	perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops backtrace_ops = {
@@ -1656,11 +1658,15 @@
 	.walk_stack		= print_context_stack_bp,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->ip);
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return;
+	}
+
+	perf_callchain_store(entry, regs->ip);
 
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
 }
@@ -1689,7 +1695,7 @@
 		if (fp < compat_ptr(regs->sp))
 			break;
 
-		callchain_store(entry, frame.return_address);
+		perf_callchain_store(entry, frame.return_address);
 		fp = compat_ptr(frame.next_frame);
 	}
 	return 1;
@@ -1702,19 +1708,20 @@
 }
 #endif
 
-static void
-perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
 	const void __user *fp;
 
-	if (!user_mode(regs))
-		regs = task_pt_regs(current);
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+		/* TODO: We don't support guest os callchain now */
+		return;
+	}
 
 	fp = (void __user *)regs->bp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, regs->ip);
+	perf_callchain_store(entry, regs->ip);
 
 	if (perf_callchain_user32(regs, entry))
 		return;
@@ -1731,52 +1738,11 @@
 		if ((unsigned long)fp < regs->sp)
 			break;
 
-		callchain_store(entry, frame.return_address);
+		perf_callchain_store(entry, frame.return_address);
 		fp = frame.next_frame;
 	}
 }
 
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-
-	if (current->mm)
-		perf_callchain_user(regs, entry);
-}
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* TODO: We don't support guest os callchain now */
-		return NULL;
-	}
-
-	if (in_nmi())
-		entry = &__get_cpu_var(pmc_nmi_entry);
-	else
-		entry = &__get_cpu_var(pmc_irq_entry);
-
-	entry->nr = 0;
-
-	perf_do_callchain(regs, entry);
-
-	return entry;
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long ip;
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index c2897b7..46d5844 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -52,7 +52,7 @@
  [ C(DTLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-		[ C(RESULT_MISS)   ] = 0x0046, /* L1 DTLB and L2 DLTB Miss   */
+		[ C(RESULT_MISS)   ] = 0x0746, /* L1_DTLB_AND_L2_DLTB_MISS.ALL */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0,
@@ -66,7 +66,7 @@
  [ C(ITLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes        */
-		[ C(RESULT_MISS)   ] = 0x0085, /* Instr. fetch ITLB misses   */
+		[ C(RESULT_MISS)   ] = 0x0385, /* L1_ITLB_AND_L2_ITLB_MISS.ALL */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = -1,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index ee05c90..c8f5c08 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -713,18 +713,18 @@
 	struct cpu_hw_events *cpuc;
 	int bit, loops;
 	u64 status;
-	int handled = 0;
+	int handled;
 
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	intel_pmu_disable_all();
-	intel_pmu_drain_bts_buffer();
+	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
 	if (!status) {
 		intel_pmu_enable_all(0);
-		return 0;
+		return handled;
 	}
 
 	loops = 0;
@@ -763,7 +763,7 @@
 		data.period = event->hw.last_period;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu_stop(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 18018d1..4977f9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -214,7 +214,7 @@
 	update_debugctlmsr(debugctlmsr);
 }
 
-static void intel_pmu_drain_bts_buffer(void)
+static int intel_pmu_drain_bts_buffer(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
@@ -231,16 +231,16 @@
 	struct pt_regs regs;
 
 	if (!event)
-		return;
+		return 0;
 
 	if (!ds)
-		return;
+		return 0;
 
 	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
 	top = (struct bts_record *)(unsigned long)ds->bts_index;
 
 	if (top <= at)
-		return;
+		return 0;
 
 	ds->bts_index = ds->bts_buffer_base;
 
@@ -256,7 +256,7 @@
 	perf_prepare_sample(&header, &data, event, &regs);
 
 	if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1))
-		return;
+		return 1;
 
 	for (; at < top; at++) {
 		data.ip		= at->from;
@@ -270,6 +270,7 @@
 	/* There's new data available. */
 	event->hw.interrupts++;
 	event->pending_kill = POLL_IN;
+	return 1;
 }
 
 /*
@@ -491,7 +492,7 @@
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
 	if (perf_event_overflow(event, 1, &data, &regs))
-		x86_pmu_stop(event);
+		x86_pmu_stop(event, 0);
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 2490151..81400b9 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -18,6 +18,8 @@
 struct p4_event_bind {
 	unsigned int opcode;			/* Event code and ESCR selector */
 	unsigned int escr_msr[2];		/* ESCR MSR for this event */
+	unsigned int escr_emask;		/* valid ESCR EventMask bits */
+	unsigned int shared;			/* event is shared across threads */
 	char cntr[2][P4_CNTR_LIMIT];		/* counter index (offset), -1 on abscence */
 };
 
@@ -66,231 +68,435 @@
 	[P4_EVENT_TC_DELIVER_MODE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_DELIVER_MODE),
 		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DB)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DI)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BD)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BB)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BI)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, ID),
+		.shared		= 1,
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_BPU_FETCH_REQUEST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST),
 		.escr_msr	= { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BPU_FETCH_REQUEST, TCMISS),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_ITLB_REFERENCE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_ITLB_REFERENCE),
 		.escr_msr	= { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, HIT)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, MISS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, HIT_UK),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_MEMORY_CANCEL] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_CANCEL),
 		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_CANCEL, 64K_CONF),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_MEMORY_COMPLETE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_COMPLETE),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_COMPLETE, LSC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_COMPLETE, SSC),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_LOAD_PORT_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_STORE_PORT_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0 ,  MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_MOB_LOAD_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY),
 		.escr_msr	= { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, NO_STA)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, NO_STD)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_PAGE_WALK_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE),
 		.escr_msr	= { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PAGE_WALK_TYPE, DTMISS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_PAGE_WALK_TYPE, ITMISS),
+		.shared		= 1,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BSQ_CACHE_REFERENCE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE),
 		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_IOQ_ALLOCATION] = {
 		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ALLOCATION),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, DEFAULT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, ALL_READ)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_UC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WB)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, OWN)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, OTHER)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, PREFETCH),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_IOQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
 		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES),
 		.escr_msr	= { MSR_P4_FSB_ESCR1,  MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH),
 		.cntr		= { {2, -1, -1}, {3, -1, -1} },
 	},
 	[P4_EVENT_FSB_DATA_ACTIVITY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER),
+		.shared		= 1,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BSQ_ALLOCATION] = {		/* shared ESCR, broken CCCR1 */
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ALLOCATION),
 		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2),
 		.cntr		= { {0, -1, -1}, {1, -1, -1} },
 	},
 	[P4_EVENT_BSQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES),
 		.escr_msr	= { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2),
 		.cntr		= { {2, -1, -1}, {3, -1, -1} },
 	},
 	[P4_EVENT_SSE_INPUT_ASSIST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SSE_INPUT_ASSIST, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_PACKED_SP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PACKED_SP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PACKED_SP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_PACKED_DP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PACKED_DP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PACKED_DP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_SCALAR_SP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_SP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SCALAR_SP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_SCALAR_DP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_DP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SCALAR_DP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_64BIT_MMX_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_64BIT_MMX_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_64BIT_MMX_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_128BIT_MMX_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_128BIT_MMX_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_128BIT_MMX_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_X87_FP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_X87_FP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_FP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_TC_MISC] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_MISC),
 		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_MISC, FLUSH),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_GLOBAL_POWER_EVENTS] = {
 		.opcode		= P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_TC_MS_XFER] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_MS_XFER),
 		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_MS_XFER, CISC),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_UOP_QUEUE_WRITES] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES),
 		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE),
 		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RETIRED_BRANCH_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE),
 		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RESOURCE_STALL] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RESOURCE_STALL),
 		.escr_msr	= { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RESOURCE_STALL, SBFULL),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_WC_BUFFER] = {
 		.opcode		= P4_OPCODE(P4_EVENT_WC_BUFFER),
 		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_WC_BUFFER, WCB_EVICTS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_B2B_CYCLES] = {
 		.opcode		= P4_OPCODE(P4_EVENT_B2B_CYCLES),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BNR] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BNR),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_SNOOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SNOOP),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_RESPONSE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RESPONSE),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_FRONT_END_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_FRONT_END_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_FRONT_END_EVENT, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FRONT_END_EVENT, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_EXECUTION_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_EXECUTION_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_REPLAY_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_REPLAY_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_REPLAY_EVENT, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_REPLAY_EVENT, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_INSTR_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_INSTR_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSTAG),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_UOPS_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOPS_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOPS_RETIRED, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOPS_RETIRED, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_UOP_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOP_TYPE),
 		.escr_msr	= { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_TYPE, TAGLOADS)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_TYPE, TAGSTORES),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_BRANCH_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BRANCH_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMNP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMNM)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMTP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMTM),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_MISPRED_BRANCH_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+		P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_X87_ASSIST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_X87_ASSIST),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, FPSU)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, FPSO)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, POAO)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, POAU)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, PREA),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_MACHINE_CLEAR] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MACHINE_CLEAR),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, CLEAR)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, MOCLEAR)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, SMCLEAR),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_INSTR_COMPLETED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_INSTR_COMPLETED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_COMPLETED, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_COMPLETED, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 };
@@ -428,29 +634,73 @@
 	return config;
 }
 
-static int p4_validate_raw_event(struct perf_event *event)
+/* check cpu model specifics */
+static bool p4_event_match_cpu_model(unsigned int event_idx)
 {
-	unsigned int v;
-
-	/* user data may have out-of-bound event index */
-	v = p4_config_unpack_event(event->attr.config);
-	if (v >= ARRAY_SIZE(p4_event_bind_map)) {
-		pr_warning("P4 PMU: Unknown event code: %d\n", v);
-		return -EINVAL;
+	/* INSTR_COMPLETED event only exist for model 3, 4, 6 (Prescott) */
+	if (event_idx == P4_EVENT_INSTR_COMPLETED) {
+		if (boot_cpu_data.x86_model != 3 &&
+			boot_cpu_data.x86_model != 4 &&
+			boot_cpu_data.x86_model != 6)
+			return false;
 	}
 
 	/*
-	 * it may have some screwed PEBS bits
+	 * For info
+	 * - IQ_ESCR0, IQ_ESCR1 only for models 1 and 2
 	 */
-	if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE)) {
-		pr_warning("P4 PMU: PEBS are not supported yet\n");
+
+	return true;
+}
+
+static int p4_validate_raw_event(struct perf_event *event)
+{
+	unsigned int v, emask;
+
+	/* User data may have out-of-bound event index */
+	v = p4_config_unpack_event(event->attr.config);
+	if (v >= ARRAY_SIZE(p4_event_bind_map))
 		return -EINVAL;
+
+	/* It may be unsupported: */
+	if (!p4_event_match_cpu_model(v))
+		return -EINVAL;
+
+	/*
+	 * NOTE: P4_CCCR_THREAD_ANY has not the same meaning as
+	 * in Architectural Performance Monitoring, it means not
+	 * on _which_ logical cpu to count but rather _when_, ie it
+	 * depends on logical cpu state -- count event if one cpu active,
+	 * none, both or any, so we just allow user to pass any value
+	 * desired.
+	 *
+	 * In turn we always set Tx_OS/Tx_USR bits bound to logical
+	 * cpu without their propagation to another cpu
+	 */
+
+	/*
+	 * if an event is shared accross the logical threads
+	 * the user needs special permissions to be able to use it
+	 */
+	if (p4_event_bind_map[v].shared) {
+		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
 	}
+
+	/* ESCR EventMask bits may be invalid */
+	emask = p4_config_unpack_escr(event->attr.config) & P4_ESCR_EVENTMASK_MASK;
+	if (emask & ~p4_event_bind_map[v].escr_emask)
+		return -EINVAL;
+
+	/*
+	 * it may have some invalid PEBS bits
+	 */
+	if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE))
+		return -EINVAL;
+
 	v = p4_config_unpack_metric(event->attr.config);
-	if (v >= ARRAY_SIZE(p4_pebs_bind_map)) {
-		pr_warning("P4 PMU: Unknown metric code: %d\n", v);
+	if (v >= ARRAY_SIZE(p4_pebs_bind_map))
 		return -EINVAL;
-	}
 
 	return 0;
 }
@@ -478,27 +728,21 @@
 
 	if (event->attr.type == PERF_TYPE_RAW) {
 
+		/*
+		 * Clear bits we reserve to be managed by kernel itself
+		 * and never allowed from a user space
+		 */
+		 event->attr.config &= P4_CONFIG_MASK;
+
 		rc = p4_validate_raw_event(event);
 		if (rc)
 			goto out;
 
 		/*
-		 * We don't control raw events so it's up to the caller
-		 * to pass sane values (and we don't count the thread number
-		 * on HT machine but allow HT-compatible specifics to be
-		 * passed on)
-		 *
 		 * Note that for RAW events we allow user to use P4_CCCR_RESERVED
 		 * bits since we keep additional info here (for cache events and etc)
-		 *
-		 * XXX: HT wide things should check perf_paranoid_cpu() &&
-		 *      CAP_SYS_ADMIN
 		 */
-		event->hw.config |= event->attr.config &
-			(p4_config_pack_escr(P4_ESCR_MASK_HT) |
-			 p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED));
-
-		event->hw.config &= ~P4_CCCR_FORCE_OVF;
+		event->hw.config |= event->attr.config;
 	}
 
 	rc = x86_setup_perfctr(event);
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index fb329e9..d9f4ff8 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -700,11 +700,10 @@
 {
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
-		if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 &&
-		    boot_cpu_data.x86 != 16 && boot_cpu_data.x86 != 17)
-			return;
-		wd_ops = &k7_wd_ops;
-		break;
+		if (boot_cpu_data.x86 == 6 ||
+		    (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15))
+			wd_ops = &k7_wd_ops;
+		return;
 	case X86_VENDOR_INTEL:
 		/* Work around where perfctr1 doesn't have a working enable
 		 * bit as described in the following errata:
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index d490795..c7f64e6 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -44,6 +44,12 @@
 		{ X86_FEATURE_LBRV,		CR_EDX, 1, 0x8000000a, 0 },
 		{ X86_FEATURE_SVML,		CR_EDX, 2, 0x8000000a, 0 },
 		{ X86_FEATURE_NRIPS,		CR_EDX, 3, 0x8000000a, 0 },
+		{ X86_FEATURE_TSCRATEMSR,	CR_EDX, 4, 0x8000000a, 0 },
+		{ X86_FEATURE_VMCBCLEAN,	CR_EDX, 5, 0x8000000a, 0 },
+		{ X86_FEATURE_FLUSHBYASID,	CR_EDX, 6, 0x8000000a, 0 },
+		{ X86_FEATURE_DECODEASSISTS,	CR_EDX, 7, 0x8000000a, 0 },
+		{ X86_FEATURE_PAUSEFILTER,	CR_EDX,10, 0x8000000a, 0 },
+		{ X86_FEATURE_PFTHRESHOLD,	CR_EDX,12, 0x8000000a, 0 },
 		{ 0, 0, 0, 0, 0 }
 	};
 
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 045b36c..9948288 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -34,7 +34,7 @@
 	if (!csize)
 		return 0;
 
-	vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+	vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE);
 	if (!vaddr)
 		return -ENOMEM;
 
@@ -46,6 +46,7 @@
 	} else
 		memcpy(buf, vaddr + offset, csize);
 
+	set_iounmap_nonlazy();
 	iounmap(vaddr);
 	return csize;
 }
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 0d6fc71..0c2b7ef 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -15,6 +15,7 @@
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/firmware-map.h>
+#include <linux/memblock.h>
 
 #include <asm/e820.h>
 #include <asm/proto.h>
@@ -738,73 +739,7 @@
 #endif
 
 /*
- * Find a free area with specified alignment in a specific range.
- */
-u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-
-		ei_last = ei->addr + ei->size;
-		ei_start = ei->addr;
-		addr = find_early_area(ei_start, ei_last, start, end,
-					 size, align);
-
-		if (addr != -1ULL)
-			return addr;
-	}
-	return -1ULL;
-}
-
-u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
-{
-	return find_e820_area(start, end, size, align);
-}
-
-u64 __init get_max_mapped(void)
-{
-	u64 end = max_pfn_mapped;
-
-	end <<= PAGE_SHIFT;
-
-	return end;
-}
-/*
- * Find next free range after *start
- */
-u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
-{
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr;
-		u64 ei_start, ei_last;
-
-		if (ei->type != E820_RAM)
-			continue;
-
-		ei_last = ei->addr + ei->size;
-		ei_start = ei->addr;
-		addr = find_early_area_size(ei_start, ei_last, start,
-					 sizep, align);
-
-		if (addr != -1ULL)
-			return addr;
-	}
-
-	return -1ULL;
-}
-
-/*
- * pre allocated 4k and reserved it in e820
+ * pre allocated 4k and reserved it in memblock and e820_saved
  */
 u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 {
@@ -813,8 +748,8 @@
 	u64 start;
 
 	for (start = startt; ; start += size) {
-		start = find_e820_area_size(start, &size, align);
-		if (!(start + 1))
+		start = memblock_x86_find_in_range_size(start, &size, align);
+		if (start == MEMBLOCK_ERROR)
 			return 0;
 		if (size >= sizet)
 			break;
@@ -830,10 +765,9 @@
 	addr = round_down(start + size - sizet, align);
 	if (addr < start)
 		return 0;
-	e820_update_range(addr, sizet, E820_RAM, E820_RESERVED);
+	memblock_x86_reserve_range(addr, addr + sizet, "new next");
 	e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED);
-	printk(KERN_INFO "update e820 for early_reserve_e820\n");
-	update_e820();
+	printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
 	update_e820_saved();
 
 	return addr;
@@ -895,74 +829,6 @@
 {
 	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
 }
-/*
- * Finds an active region in the address range from start_pfn to last_pfn and
- * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
- */
-int __init e820_find_active_region(const struct e820entry *ei,
-				  unsigned long start_pfn,
-				  unsigned long last_pfn,
-				  unsigned long *ei_startpfn,
-				  unsigned long *ei_endpfn)
-{
-	u64 align = PAGE_SIZE;
-
-	*ei_startpfn = round_up(ei->addr, align) >> PAGE_SHIFT;
-	*ei_endpfn = round_down(ei->addr + ei->size, align) >> PAGE_SHIFT;
-
-	/* Skip map entries smaller than a page */
-	if (*ei_startpfn >= *ei_endpfn)
-		return 0;
-
-	/* Skip if map is outside the node */
-	if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
-				    *ei_startpfn >= last_pfn)
-		return 0;
-
-	/* Check for overlaps */
-	if (*ei_startpfn < start_pfn)
-		*ei_startpfn = start_pfn;
-	if (*ei_endpfn > last_pfn)
-		*ei_endpfn = last_pfn;
-
-	return 1;
-}
-
-/* Walk the e820 map and register active regions within a node */
-void __init e820_register_active_regions(int nid, unsigned long start_pfn,
-					 unsigned long last_pfn)
-{
-	unsigned long ei_startpfn;
-	unsigned long ei_endpfn;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++)
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, last_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			add_active_range(nid, ei_startpfn, ei_endpfn);
-}
-
-/*
- * Find the hole size (in bytes) in the memory range.
- * @start: starting address of the memory range to scan
- * @end: ending address of the memory range to scan
- */
-u64 __init e820_hole_size(u64 start, u64 end)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long last_pfn = end >> PAGE_SHIFT;
-	unsigned long ei_startpfn, ei_endpfn, ram = 0;
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		if (e820_find_active_region(&e820.map[i],
-					    start_pfn, last_pfn,
-					    &ei_startpfn, &ei_endpfn))
-			ram += ei_endpfn - ei_startpfn;
-	}
-	return end - start - ((u64)ram << PAGE_SHIFT);
-}
 
 static void early_panic(char *msg)
 {
@@ -1210,3 +1076,48 @@
 	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
 	e820_print_map(who);
 }
+
+void __init memblock_x86_fill(void)
+{
+	int i;
+	u64 end;
+
+	/*
+	 * EFI may have more than 128 entries
+	 * We are safe to enable resizing, beause memblock_x86_fill()
+	 * is rather later for x86
+	 */
+	memblock_can_resize = 1;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		end = ei->addr + ei->size;
+		if (end != (resource_size_t)end)
+			continue;
+
+		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+			continue;
+
+		memblock_add(ei->addr, ei->size);
+	}
+
+	memblock_analyze();
+	memblock_dump_all();
+}
+
+void __init memblock_find_dma_reserve(void)
+{
+#ifdef CONFIG_X86_64
+	u64 free_size_pfn;
+	u64 mem_size_pfn;
+	/*
+	 * need to find out used area below MAX_DMA_PFN
+	 * need to use memblock to get free size in [0, MAX_DMA_PFN]
+	 * at first, and assume boot_mem will not take below MAX_DMA_PFN
+	 */
+	mem_size_pfn = memblock_x86_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
+	free_size_pfn = memblock_x86_free_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT;
+	set_dma_reserve(mem_size_pfn - free_size_pfn);
+#endif
+}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index ebdb85c..76b8cd9 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -97,7 +97,6 @@
 }
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
-#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
 static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 {
 	u32 d;
@@ -115,7 +114,6 @@
 	d &= 0xff;
 	return d;
 }
-#endif
 
 static void __init ati_bugs(int num, int slot, int func)
 {
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index fa99bae..4572f25 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -14,6 +14,7 @@
 #include <xen/hvc-console.h>
 #include <asm/pci-direct.h>
 #include <asm/fixmap.h>
+#include <asm/mrst.h>
 #include <asm/pgtable.h>
 #include <linux/usb/ehci_def.h>
 
@@ -239,6 +240,18 @@
 		if (!strncmp(buf, "xen", 3))
 			early_console_register(&xenboot_console, keep);
 #endif
+#ifdef CONFIG_X86_MRST_EARLY_PRINTK
+		if (!strncmp(buf, "mrst", 4)) {
+			mrst_early_console_init();
+			early_console_register(&early_mrst_console, keep);
+		}
+
+		if (!strncmp(buf, "hsu", 3)) {
+			hsu_early_console_init();
+			early_console_register(&early_hsu_console, keep);
+		}
+
+#endif
 		buf++;
 	}
 	return 0;
diff --git a/arch/x86/kernel/early_printk_mrst.c b/arch/x86/kernel/early_printk_mrst.c
new file mode 100644
index 0000000..65df603
--- /dev/null
+++ b/arch/x86/kernel/early_printk_mrst.c
@@ -0,0 +1,319 @@
+/*
+ * early_printk_mrst.c - early consoles for Intel MID platforms
+ *
+ * Copyright (c) 2008-2010, Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+/*
+ * This file implements two early consoles named mrst and hsu.
+ * mrst is based on Maxim3110 spi-uart device, it exists in both
+ * Moorestown and Medfield platforms, while hsu is based on a High
+ * Speed UART device which only exists in the Medfield platform
+ */
+
+#include <linux/serial_reg.h>
+#include <linux/serial_mfd.h>
+#include <linux/kmsg_dump.h>
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+
+#include <asm/fixmap.h>
+#include <asm/pgtable.h>
+#include <asm/mrst.h>
+
+#define MRST_SPI_TIMEOUT		0x200000
+#define MRST_REGBASE_SPI0		0xff128000
+#define MRST_REGBASE_SPI1		0xff128400
+#define MRST_CLK_SPI0_REG		0xff11d86c
+
+/* Bit fields in CTRLR0 */
+#define SPI_DFS_OFFSET			0
+
+#define SPI_FRF_OFFSET			4
+#define SPI_FRF_SPI			0x0
+#define SPI_FRF_SSP			0x1
+#define SPI_FRF_MICROWIRE		0x2
+#define SPI_FRF_RESV			0x3
+
+#define SPI_MODE_OFFSET			6
+#define SPI_SCPH_OFFSET			6
+#define SPI_SCOL_OFFSET			7
+#define SPI_TMOD_OFFSET			8
+#define	SPI_TMOD_TR			0x0		/* xmit & recv */
+#define SPI_TMOD_TO			0x1		/* xmit only */
+#define SPI_TMOD_RO			0x2		/* recv only */
+#define SPI_TMOD_EPROMREAD		0x3		/* eeprom read mode */
+
+#define SPI_SLVOE_OFFSET		10
+#define SPI_SRL_OFFSET			11
+#define SPI_CFS_OFFSET			12
+
+/* Bit fields in SR, 7 bits */
+#define SR_MASK				0x7f		/* cover 7 bits */
+#define SR_BUSY				(1 << 0)
+#define SR_TF_NOT_FULL			(1 << 1)
+#define SR_TF_EMPT			(1 << 2)
+#define SR_RF_NOT_EMPT			(1 << 3)
+#define SR_RF_FULL			(1 << 4)
+#define SR_TX_ERR			(1 << 5)
+#define SR_DCOL				(1 << 6)
+
+struct dw_spi_reg {
+	u32	ctrl0;
+	u32	ctrl1;
+	u32	ssienr;
+	u32	mwcr;
+	u32	ser;
+	u32	baudr;
+	u32	txfltr;
+	u32	rxfltr;
+	u32	txflr;
+	u32	rxflr;
+	u32	sr;
+	u32	imr;
+	u32	isr;
+	u32	risr;
+	u32	txoicr;
+	u32	rxoicr;
+	u32	rxuicr;
+	u32	msticr;
+	u32	icr;
+	u32	dmacr;
+	u32	dmatdlr;
+	u32	dmardlr;
+	u32	idr;
+	u32	version;
+
+	/* Currently operates as 32 bits, though only the low 16 bits matter */
+	u32	dr;
+} __packed;
+
+#define dw_readl(dw, name)		__raw_readl(&(dw)->name)
+#define dw_writel(dw, name, val)	__raw_writel((val), &(dw)->name)
+
+/* Default use SPI0 register for mrst, we will detect Penwell and use SPI1 */
+static unsigned long mrst_spi_paddr = MRST_REGBASE_SPI0;
+
+static u32 *pclk_spi0;
+/* Always contains an accessable address, start with 0 */
+static struct dw_spi_reg *pspi;
+
+static struct kmsg_dumper dw_dumper;
+static int dumper_registered;
+
+static void dw_kmsg_dump(struct kmsg_dumper *dumper,
+			enum kmsg_dump_reason reason,
+			const char *s1, unsigned long l1,
+			const char *s2, unsigned long l2)
+{
+	int i;
+
+	/* When run to this, we'd better re-init the HW */
+	mrst_early_console_init();
+
+	for (i = 0; i < l1; i++)
+		early_mrst_console.write(&early_mrst_console, s1 + i, 1);
+	for (i = 0; i < l2; i++)
+		early_mrst_console.write(&early_mrst_console, s2 + i, 1);
+}
+
+/* Set the ratio rate to 115200, 8n1, IRQ disabled */
+static void max3110_write_config(void)
+{
+	u16 config;
+
+	config = 0xc001;
+	dw_writel(pspi, dr, config);
+}
+
+/* Translate char to a eligible word and send to max3110 */
+static void max3110_write_data(char c)
+{
+	u16 data;
+
+	data = 0x8000 | c;
+	dw_writel(pspi, dr, data);
+}
+
+void mrst_early_console_init(void)
+{
+	u32 ctrlr0 = 0;
+	u32 spi0_cdiv;
+	u32 freq; /* Freqency info only need be searched once */
+
+	/* Base clk is 100 MHz, the actual clk = 100M / (clk_divider + 1) */
+	pclk_spi0 = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
+							MRST_CLK_SPI0_REG);
+	spi0_cdiv = ((*pclk_spi0) & 0xe00) >> 9;
+	freq = 100000000 / (spi0_cdiv + 1);
+
+	if (mrst_identify_cpu() == MRST_CPU_CHIP_PENWELL)
+		mrst_spi_paddr = MRST_REGBASE_SPI1;
+
+	pspi = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
+						mrst_spi_paddr);
+
+	/* Disable SPI controller */
+	dw_writel(pspi, ssienr, 0);
+
+	/* Set control param, 8 bits, transmit only mode */
+	ctrlr0 = dw_readl(pspi, ctrl0);
+
+	ctrlr0 &= 0xfcc0;
+	ctrlr0 |= 0xf | (SPI_FRF_SPI << SPI_FRF_OFFSET)
+		      | (SPI_TMOD_TO << SPI_TMOD_OFFSET);
+	dw_writel(pspi, ctrl0, ctrlr0);
+
+	/*
+	 * Change the spi0 clk to comply with 115200 bps, use 100000 to
+	 * calculate the clk dividor to make the clock a little slower
+	 * than real baud rate.
+	 */
+	dw_writel(pspi, baudr, freq/100000);
+
+	/* Disable all INT for early phase */
+	dw_writel(pspi, imr, 0x0);
+
+	/* Set the cs to spi-uart */
+	dw_writel(pspi, ser, 0x2);
+
+	/* Enable the HW, the last step for HW init */
+	dw_writel(pspi, ssienr, 0x1);
+
+	/* Set the default configuration */
+	max3110_write_config();
+
+	/* Register the kmsg dumper */
+	if (!dumper_registered) {
+		dw_dumper.dump = dw_kmsg_dump;
+		kmsg_dump_register(&dw_dumper);
+		dumper_registered = 1;
+	}
+}
+
+/* Slave select should be called in the read/write function */
+static void early_mrst_spi_putc(char c)
+{
+	unsigned int timeout;
+	u32 sr;
+
+	timeout = MRST_SPI_TIMEOUT;
+	/* Early putc needs to make sure the TX FIFO is not full */
+	while (--timeout) {
+		sr = dw_readl(pspi, sr);
+		if (!(sr & SR_TF_NOT_FULL))
+			cpu_relax();
+		else
+			break;
+	}
+
+	if (!timeout)
+		pr_warning("MRST earlycon: timed out\n");
+	else
+		max3110_write_data(c);
+}
+
+/* Early SPI only uses polling mode */
+static void early_mrst_spi_write(struct console *con, const char *str, unsigned n)
+{
+	int i;
+
+	for (i = 0; i < n && *str; i++) {
+		if (*str == '\n')
+			early_mrst_spi_putc('\r');
+		early_mrst_spi_putc(*str);
+		str++;
+	}
+}
+
+struct console early_mrst_console = {
+	.name =		"earlymrst",
+	.write =	early_mrst_spi_write,
+	.flags =	CON_PRINTBUFFER,
+	.index =	-1,
+};
+
+/*
+ * Following is the early console based on Medfield HSU (High
+ * Speed UART) device.
+ */
+#define HSU_PORT2_PADDR		0xffa28180
+
+static void __iomem *phsu;
+
+void hsu_early_console_init(void)
+{
+	u8 lcr;
+
+	phsu = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
+							HSU_PORT2_PADDR);
+
+	/* Disable FIFO */
+	writeb(0x0, phsu + UART_FCR);
+
+	/* Set to default 115200 bps, 8n1 */
+	lcr = readb(phsu + UART_LCR);
+	writeb((0x80 | lcr), phsu + UART_LCR);
+	writeb(0x18, phsu + UART_DLL);
+	writeb(lcr,  phsu + UART_LCR);
+	writel(0x3600, phsu + UART_MUL*4);
+
+	writeb(0x8, phsu + UART_MCR);
+	writeb(0x7, phsu + UART_FCR);
+	writeb(0x3, phsu + UART_LCR);
+
+	/* Clear IRQ status */
+	readb(phsu + UART_LSR);
+	readb(phsu + UART_RX);
+	readb(phsu + UART_IIR);
+	readb(phsu + UART_MSR);
+
+	/* Enable FIFO */
+	writeb(0x7, phsu + UART_FCR);
+}
+
+#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
+
+static void early_hsu_putc(char ch)
+{
+	unsigned int timeout = 10000; /* 10ms */
+	u8 status;
+
+	while (--timeout) {
+		status = readb(phsu + UART_LSR);
+		if (status & BOTH_EMPTY)
+			break;
+		udelay(1);
+	}
+
+	/* Only write the char when there was no timeout */
+	if (timeout)
+		writeb(ch, phsu + UART_TX);
+}
+
+static void early_hsu_write(struct console *con, const char *str, unsigned n)
+{
+	int i;
+
+	for (i = 0; i < n && *str; i++) {
+		if (*str == '\n')
+			early_hsu_putc('\r');
+		early_hsu_putc(*str);
+		str++;
+	}
+}
+
+struct console early_hsu_console = {
+	.name =		"earlyhsu",
+	.write =	early_hsu_write,
+	.flags =	CON_PRINTBUFFER,
+	.index =	-1,
+};
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index c2fa9b8..0fe27d7 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -30,6 +30,7 @@
 #include <linux/init.h>
 #include <linux/efi.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 #include <linux/time.h>
@@ -275,7 +276,7 @@
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
-void __init efi_reserve_early(void)
+void __init efi_memblock_x86_reserve_range(void)
 {
 	unsigned long pmap;
 
@@ -290,7 +291,7 @@
 		boot_params.efi_info.efi_memdesc_size;
 	memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
 	memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
-	reserve_early(pmap, pmap + memmap.nr_map * memmap.desc_size,
+	memblock_x86_reserve_range(pmap, pmap + memmap.nr_map * memmap.desc_size,
 		      "EFI memmap");
 }
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 227d009..9fb188d 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -115,8 +115,7 @@
 
  /* unfortunately push/pop can't be no-op */
 .macro PUSH_GS
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
 .endm
 .macro POP_GS pop=0
 	addl $(4 + \pop), %esp
@@ -140,14 +139,12 @@
 #else	/* CONFIG_X86_32_LAZY_GS */
 
 .macro PUSH_GS
-	pushl %gs
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %gs
 	/*CFI_REL_OFFSET gs, 0*/
 .endm
 
 .macro POP_GS pop=0
-98:	popl %gs
-	CFI_ADJUST_CFA_OFFSET -4
+98:	popl_cfi %gs
 	/*CFI_RESTORE gs*/
   .if \pop <> 0
 	add $\pop, %esp
@@ -195,35 +192,25 @@
 .macro SAVE_ALL
 	cld
 	PUSH_GS
-	pushl %fs
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %fs
 	/*CFI_REL_OFFSET fs, 0;*/
-	pushl %es
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %es
 	/*CFI_REL_OFFSET es, 0;*/
-	pushl %ds
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ds
 	/*CFI_REL_OFFSET ds, 0;*/
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	CFI_REL_OFFSET eax, 0
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebp
 	CFI_REL_OFFSET ebp, 0
-	pushl %edi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edi
 	CFI_REL_OFFSET edi, 0
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %esi
 	CFI_REL_OFFSET esi, 0
-	pushl %edx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edx
 	CFI_REL_OFFSET edx, 0
-	pushl %ecx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx
 	CFI_REL_OFFSET ecx, 0
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	CFI_REL_OFFSET ebx, 0
 	movl $(__USER_DS), %edx
 	movl %edx, %ds
@@ -234,39 +221,29 @@
 .endm
 
 .macro RESTORE_INT_REGS
-	popl %ebx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebx
 	CFI_RESTORE ebx
-	popl %ecx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ecx
 	CFI_RESTORE ecx
-	popl %edx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %edx
 	CFI_RESTORE edx
-	popl %esi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %esi
 	CFI_RESTORE esi
-	popl %edi
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %edi
 	CFI_RESTORE edi
-	popl %ebp
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ebp
 	CFI_RESTORE ebp
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
 	CFI_RESTORE eax
 .endm
 
 .macro RESTORE_REGS pop=0
 	RESTORE_INT_REGS
-1:	popl %ds
-	CFI_ADJUST_CFA_OFFSET -4
+1:	popl_cfi %ds
 	/*CFI_RESTORE ds;*/
-2:	popl %es
-	CFI_ADJUST_CFA_OFFSET -4
+2:	popl_cfi %es
 	/*CFI_RESTORE es;*/
-3:	popl %fs
-	CFI_ADJUST_CFA_OFFSET -4
+3:	popl_cfi %fs
 	/*CFI_RESTORE fs;*/
 	POP_GS \pop
 .pushsection .fixup, "ax"
@@ -320,16 +297,12 @@
 
 ENTRY(ret_from_fork)
 	CFI_STARTPROC
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	call schedule_tail
 	GET_THREAD_INFO(%ebp)
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
-	pushl $0x0202			# Reset kernel eflags
-	CFI_ADJUST_CFA_OFFSET 4
-	popfl
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
+	pushl_cfi $0x0202		# Reset kernel eflags
+	popfl_cfi
 	jmp syscall_exit
 	CFI_ENDPROC
 END(ret_from_fork)
@@ -409,29 +382,23 @@
 	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
 	 * we immediately enable interrupts at that point anyway.
 	 */
-	pushl $(__USER_DS)
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $(__USER_DS)
 	/*CFI_REL_OFFSET ss, 0*/
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebp
 	CFI_REL_OFFSET esp, 0
-	pushfl
+	pushfl_cfi
 	orl $X86_EFLAGS_IF, (%esp)
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $(__USER_CS)
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $(__USER_CS)
 	/*CFI_REL_OFFSET cs, 0*/
 	/*
 	 * Push current_thread_info()->sysenter_return to the stack.
 	 * A tiny bit of offset fixup is necessary - 4*4 means the 4 words
 	 * pushed above; +8 corresponds to copy_thread's esp0 setting.
 	 */
-	pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
 	CFI_REL_OFFSET eip, 0
 
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	SAVE_ALL
 	ENABLE_INTERRUPTS(CLBR_NONE)
 
@@ -486,8 +453,7 @@
 	movl %eax,%edx			/* 2nd arg: syscall number */
 	movl $AUDIT_ARCH_I386,%eax	/* 1st arg: audit arch */
 	call audit_syscall_entry
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	movl PT_EAX(%esp),%eax		/* reload syscall number */
 	jmp sysenter_do_call
 
@@ -529,8 +495,7 @@
 	# system call handler stub
 ENTRY(system_call)
 	RING0_INT_FRAME			# can't unwind into user space anyway
-	pushl %eax			# save orig_eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax			# save orig_eax
 	SAVE_ALL
 	GET_THREAD_INFO(%ebp)
 					# system call tracing in operation / emulation
@@ -566,7 +531,6 @@
 	je ldt_ss			# returning to user-space with LDT SS
 restore_nocheck:
 	RESTORE_REGS 4			# skip orig_eax/error_code
-	CFI_ADJUST_CFA_OFFSET -4
 irq_return:
 	INTERRUPT_RETURN
 .section .fixup,"ax"
@@ -619,10 +583,8 @@
 	shr $16, %edx
 	mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
 	mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
-	pushl $__ESPFIX_SS
-	CFI_ADJUST_CFA_OFFSET 4
-	push %eax			/* new kernel esp */
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $__ESPFIX_SS
+	pushl_cfi %eax			/* new kernel esp */
 	/* Disable interrupts, but do not irqtrace this section: we
 	 * will soon execute iret and the tracer was already set to
 	 * the irqstate after the iret */
@@ -666,11 +628,9 @@
 
 	ALIGN
 work_notifysig_v86:
-	pushl %ecx			# save ti_flags for do_notify_resume
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx			# save ti_flags for do_notify_resume
 	call save_v86_state		# %eax contains pt_regs pointer
-	popl %ecx
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %ecx
 	movl %eax, %esp
 #else
 	movl %esp, %eax
@@ -750,14 +710,18 @@
 #define PTREGSCALL3(name) \
 	ALIGN; \
 ptregs_##name: \
+	CFI_STARTPROC; \
 	leal 4(%esp),%eax; \
-	pushl %eax; \
+	pushl_cfi %eax; \
 	movl PT_EDX(%eax),%ecx; \
 	movl PT_ECX(%eax),%edx; \
 	movl PT_EBX(%eax),%eax; \
 	call sys_##name; \
 	addl $4,%esp; \
-	ret
+	CFI_ADJUST_CFA_OFFSET -4; \
+	ret; \
+	CFI_ENDPROC; \
+ENDPROC(ptregs_##name)
 
 PTREGSCALL1(iopl)
 PTREGSCALL0(fork)
@@ -772,15 +736,19 @@
 /* Clone is an oddball.  The 4th arg is in %edi */
 	ALIGN;
 ptregs_clone:
+	CFI_STARTPROC
 	leal 4(%esp),%eax
-	pushl %eax
-	pushl PT_EDI(%eax)
+	pushl_cfi %eax
+	pushl_cfi PT_EDI(%eax)
 	movl PT_EDX(%eax),%ecx
 	movl PT_ECX(%eax),%edx
 	movl PT_EBX(%eax),%eax
 	call sys_clone
 	addl $8,%esp
+	CFI_ADJUST_CFA_OFFSET -8
 	ret
+	CFI_ENDPROC
+ENDPROC(ptregs_clone)
 
 .macro FIXUP_ESPFIX_STACK
 /*
@@ -795,10 +763,8 @@
 	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
 	shl $16, %eax
 	addl %esp, %eax			/* the adjusted stack pointer */
-	pushl $__KERNEL_DS
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $__KERNEL_DS
+	pushl_cfi %eax
 	lss (%esp), %esp		/* switch to the normal stack segment */
 	CFI_ADJUST_CFA_OFFSET -8
 .endm
@@ -835,8 +801,7 @@
       .if vector <> FIRST_EXTERNAL_VECTOR
 	CFI_ADJUST_CFA_OFFSET -4
       .endif
-1:	pushl $(~vector+0x80)	/* Note: always in signed byte range */
-	CFI_ADJUST_CFA_OFFSET 4
+1:	pushl_cfi $(~vector+0x80)	/* Note: always in signed byte range */
       .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
 	jmp 2f
       .endif
@@ -876,8 +841,7 @@
 #define BUILD_INTERRUPT3(name, nr, fn)	\
 ENTRY(name)				\
 	RING0_INT_FRAME;		\
-	pushl $~(nr);			\
-	CFI_ADJUST_CFA_OFFSET 4;	\
+	pushl_cfi $~(nr);		\
 	SAVE_ALL;			\
 	TRACE_IRQS_OFF			\
 	movl %esp,%eax;			\
@@ -893,21 +857,18 @@
 
 ENTRY(coprocessor_error)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_coprocessor_error
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_coprocessor_error
 	jmp error_code
 	CFI_ENDPROC
 END(coprocessor_error)
 
 ENTRY(simd_coprocessor_error)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
 #ifdef CONFIG_X86_INVD_BUG
 	/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
-661:	pushl $do_general_protection
+661:	pushl_cfi $do_general_protection
 662:
 .section .altinstructions,"a"
 	.balign 4
@@ -922,19 +883,16 @@
 664:
 .previous
 #else
-	pushl $do_simd_coprocessor_error
+	pushl_cfi $do_simd_coprocessor_error
 #endif
-	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
 END(simd_coprocessor_error)
 
 ENTRY(device_not_available)
 	RING0_INT_FRAME
-	pushl $-1			# mark this as an int
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_device_not_available
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $-1			# mark this as an int
+	pushl_cfi $do_device_not_available
 	jmp error_code
 	CFI_ENDPROC
 END(device_not_available)
@@ -956,82 +914,68 @@
 
 ENTRY(overflow)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_overflow
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_overflow
 	jmp error_code
 	CFI_ENDPROC
 END(overflow)
 
 ENTRY(bounds)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_bounds
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_bounds
 	jmp error_code
 	CFI_ENDPROC
 END(bounds)
 
 ENTRY(invalid_op)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_invalid_op
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_invalid_op
 	jmp error_code
 	CFI_ENDPROC
 END(invalid_op)
 
 ENTRY(coprocessor_segment_overrun)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_coprocessor_segment_overrun
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_coprocessor_segment_overrun
 	jmp error_code
 	CFI_ENDPROC
 END(coprocessor_segment_overrun)
 
 ENTRY(invalid_TSS)
 	RING0_EC_FRAME
-	pushl $do_invalid_TSS
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_invalid_TSS
 	jmp error_code
 	CFI_ENDPROC
 END(invalid_TSS)
 
 ENTRY(segment_not_present)
 	RING0_EC_FRAME
-	pushl $do_segment_not_present
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_segment_not_present
 	jmp error_code
 	CFI_ENDPROC
 END(segment_not_present)
 
 ENTRY(stack_segment)
 	RING0_EC_FRAME
-	pushl $do_stack_segment
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_stack_segment
 	jmp error_code
 	CFI_ENDPROC
 END(stack_segment)
 
 ENTRY(alignment_check)
 	RING0_EC_FRAME
-	pushl $do_alignment_check
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_alignment_check
 	jmp error_code
 	CFI_ENDPROC
 END(alignment_check)
 
 ENTRY(divide_error)
 	RING0_INT_FRAME
-	pushl $0			# no error code
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_divide_error
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0			# no error code
+	pushl_cfi $do_divide_error
 	jmp error_code
 	CFI_ENDPROC
 END(divide_error)
@@ -1039,10 +983,8 @@
 #ifdef CONFIG_X86_MCE
 ENTRY(machine_check)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl machine_check_vector
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi machine_check_vector
 	jmp error_code
 	CFI_ENDPROC
 END(machine_check)
@@ -1050,10 +992,8 @@
 
 ENTRY(spurious_interrupt_bug)
 	RING0_INT_FRAME
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $do_spurious_interrupt_bug
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
+	pushl_cfi $do_spurious_interrupt_bug
 	jmp error_code
 	CFI_ENDPROC
 END(spurious_interrupt_bug)
@@ -1084,8 +1024,7 @@
 
 ENTRY(xen_hypervisor_callback)
 	CFI_STARTPROC
-	pushl $0
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $0
 	SAVE_ALL
 	TRACE_IRQS_OFF
 
@@ -1121,23 +1060,20 @@
 # We distinguish between categories by maintaining a status value in EAX.
 ENTRY(xen_failsafe_callback)
 	CFI_STARTPROC
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	movl $1,%eax
 1:	mov 4(%esp),%ds
 2:	mov 8(%esp),%es
 3:	mov 12(%esp),%fs
 4:	mov 16(%esp),%gs
 	testl %eax,%eax
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
 	lea 16(%esp),%esp
 	CFI_ADJUST_CFA_OFFSET -16
 	jz 5f
 	addl $16,%esp
 	jmp iret_exc		# EAX != 0 => Category 2 (Bad IRET)
-5:	pushl $0		# EAX == 0 => Category 1 (Bad segment)
-	CFI_ADJUST_CFA_OFFSET 4
+5:	pushl_cfi $0		# EAX == 0 => Category 1 (Bad segment)
 	SAVE_ALL
 	jmp ret_from_exception
 	CFI_ENDPROC
@@ -1287,40 +1223,29 @@
 
 ENTRY(page_fault)
 	RING0_EC_FRAME
-	pushl $do_page_fault
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_page_fault
 	ALIGN
 error_code:
 	/* the function address is in %gs's slot on the stack */
-	pushl %fs
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %fs
 	/*CFI_REL_OFFSET fs, 0*/
-	pushl %es
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %es
 	/*CFI_REL_OFFSET es, 0*/
-	pushl %ds
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ds
 	/*CFI_REL_OFFSET ds, 0*/
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	CFI_REL_OFFSET eax, 0
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebp
 	CFI_REL_OFFSET ebp, 0
-	pushl %edi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edi
 	CFI_REL_OFFSET edi, 0
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %esi
 	CFI_REL_OFFSET esi, 0
-	pushl %edx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %edx
 	CFI_REL_OFFSET edx, 0
-	pushl %ecx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ecx
 	CFI_REL_OFFSET ecx, 0
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ebx
 	CFI_REL_OFFSET ebx, 0
 	cld
 	movl $(__KERNEL_PERCPU), %ecx
@@ -1362,12 +1287,9 @@
 	movl TSS_sysenter_sp0 + \offset(%esp), %esp
 	CFI_DEF_CFA esp, 0
 	CFI_UNDEFINED eip
-	pushfl
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $__KERNEL_CS
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl $sysenter_past_esp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushfl_cfi
+	pushl_cfi $__KERNEL_CS
+	pushl_cfi $sysenter_past_esp
 	CFI_REL_OFFSET eip, 0
 .endm
 
@@ -1377,8 +1299,7 @@
 	jne debug_stack_correct
 	FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
 debug_stack_correct:
-	pushl $-1			# mark this as an int
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $-1			# mark this as an int
 	SAVE_ALL
 	TRACE_IRQS_OFF
 	xorl %edx,%edx			# error code 0
@@ -1398,32 +1319,27 @@
  */
 ENTRY(nmi)
 	RING0_INT_FRAME
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	movl %ss, %eax
 	cmpw $__ESPFIX_SS, %ax
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
 	je nmi_espfix_stack
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	movl %esp,%eax
 	/* Do not access memory above the end of our stack page,
 	 * it might not exist.
 	 */
 	andl $(THREAD_SIZE-1),%eax
 	cmpl $(THREAD_SIZE-20),%eax
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
+	popl_cfi %eax
 	jae nmi_stack_correct
 	cmpl $ia32_sysenter_target,12(%esp)
 	je nmi_debug_stack_check
 nmi_stack_correct:
 	/* We have a RING0_INT_FRAME here */
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	SAVE_ALL
 	xorl %edx,%edx		# zero error code
 	movl %esp,%eax		# pt_regs pointer
@@ -1452,18 +1368,14 @@
 	 *
 	 * create the pointer to lss back
 	 */
-	pushl %ss
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl %esp
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %ss
+	pushl_cfi %esp
 	addl $4, (%esp)
 	/* copy the iret frame of 12 bytes */
 	.rept 3
-	pushl 16(%esp)
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi 16(%esp)
 	.endr
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi %eax
 	SAVE_ALL
 	FIXUP_ESPFIX_STACK		# %eax == %esp
 	xorl %edx,%edx			# zero error code
@@ -1477,8 +1389,7 @@
 
 ENTRY(int3)
 	RING0_INT_FRAME
-	pushl $-1			# mark this as an int
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $-1			# mark this as an int
 	SAVE_ALL
 	TRACE_IRQS_OFF
 	xorl %edx,%edx		# zero error code
@@ -1490,8 +1401,7 @@
 
 ENTRY(general_protection)
 	RING0_EC_FRAME
-	pushl $do_general_protection
-	CFI_ADJUST_CFA_OFFSET 4
+	pushl_cfi $do_general_protection
 	jmp error_code
 	CFI_ENDPROC
 END(general_protection)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 17be5ec..a7ae7fd 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -213,23 +213,17 @@
 	.macro FAKE_STACK_FRAME child_rip
 	/* push in order ss, rsp, eflags, cs, rip */
 	xorl %eax, %eax
-	pushq $__KERNEL_DS /* ss */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi $__KERNEL_DS /* ss */
 	/*CFI_REL_OFFSET	ss,0*/
-	pushq %rax /* rsp */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi %rax /* rsp */
 	CFI_REL_OFFSET	rsp,0
-	pushq $X86_EFLAGS_IF /* eflags - interrupts on */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi $X86_EFLAGS_IF /* eflags - interrupts on */
 	/*CFI_REL_OFFSET	rflags,0*/
-	pushq $__KERNEL_CS /* cs */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi $__KERNEL_CS /* cs */
 	/*CFI_REL_OFFSET	cs,0*/
-	pushq \child_rip /* rip */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi \child_rip /* rip */
 	CFI_REL_OFFSET	rip,0
-	pushq	%rax /* orig rax */
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi %rax /* orig rax */
 	.endm
 
 	.macro UNFAKE_STACK_FRAME
@@ -398,10 +392,8 @@
 
 	LOCK ; btr $TIF_FORK,TI_flags(%r8)
 
-	push kernel_eflags(%rip)
-	CFI_ADJUST_CFA_OFFSET 8
-	popf					# reset kernel eflags
-	CFI_ADJUST_CFA_OFFSET -8
+	pushq_cfi kernel_eflags(%rip)
+	popfq_cfi				# reset kernel eflags
 
 	call schedule_tail			# rdi: 'prev' task parameter
 
@@ -521,11 +513,9 @@
 	jnc sysret_signal
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq %rdi
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rdi
 	call schedule
-	popq  %rdi
-	CFI_ADJUST_CFA_OFFSET -8
+	popq_cfi %rdi
 	jmp sysret_check
 
 	/* Handle a signal */
@@ -634,11 +624,9 @@
 	jnc  int_very_careful
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq %rdi
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rdi
 	call schedule
-	popq %rdi
-	CFI_ADJUST_CFA_OFFSET -8
+	popq_cfi %rdi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	jmp int_with_check
@@ -652,12 +640,10 @@
 	/* Check for syscall exit trace */
 	testl $_TIF_WORK_SYSCALL_EXIT,%edx
 	jz int_signal
-	pushq %rdi
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi %rdi
 	leaq 8(%rsp),%rdi	# &ptregs -> arg1
 	call syscall_trace_leave
-	popq %rdi
-	CFI_ADJUST_CFA_OFFSET -8
+	popq_cfi %rdi
 	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
 	jmp int_restore_rest
 
@@ -714,9 +700,8 @@
 
 ENTRY(stub_execve)
 	CFI_STARTPROC
-	popq %r11
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_REGISTER rip, r11
+	addq $8, %rsp
+	PARTIAL_FRAME 0
 	SAVE_REST
 	FIXUP_TOP_OF_STACK %r11
 	movq %rsp, %rcx
@@ -735,7 +720,7 @@
 ENTRY(stub_rt_sigreturn)
 	CFI_STARTPROC
 	addq $8, %rsp
-	CFI_ADJUST_CFA_OFFSET	-8
+	PARTIAL_FRAME 0
 	SAVE_REST
 	movq %rsp,%rdi
 	FIXUP_TOP_OF_STACK %r11
@@ -766,8 +751,7 @@
       .if vector <> FIRST_EXTERNAL_VECTOR
 	CFI_ADJUST_CFA_OFFSET -8
       .endif
-1:	pushq $(~vector+0x80)	/* Note: always in signed byte range */
-	CFI_ADJUST_CFA_OFFSET 8
+1:	pushq_cfi $(~vector+0x80)	/* Note: always in signed byte range */
       .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
 	jmp 2f
       .endif
@@ -796,8 +780,8 @@
 
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
-	subq $10*8, %rsp
-	CFI_ADJUST_CFA_OFFSET 10*8
+	subq $ORIG_RAX-ARGOFFSET+8, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8
 	call save_args
 	PARTIAL_FRAME 0
 	call \func
@@ -822,6 +806,7 @@
 	TRACE_IRQS_OFF
 	decl PER_CPU_VAR(irq_count)
 	leaveq
+	CFI_RESTORE		rbp
 	CFI_DEF_CFA_REGISTER	rsp
 	CFI_ADJUST_CFA_OFFSET	-8
 exit_intr:
@@ -903,11 +888,9 @@
 	jnc   retint_signal
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq %rdi
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi %rdi
 	call  schedule
-	popq %rdi
-	CFI_ADJUST_CFA_OFFSET	-8
+	popq_cfi %rdi
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
@@ -956,8 +939,7 @@
 .macro apicinterrupt num sym do_sym
 ENTRY(\sym)
 	INTR_FRAME
-	pushq $~(\num)
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi $~(\num)
 	interrupt \do_sym
 	jmp ret_from_intr
 	CFI_ENDPROC
@@ -1023,9 +1005,9 @@
 apicinterrupt SPURIOUS_APIC_VECTOR \
 	spurious_interrupt smp_spurious_interrupt
 
-#ifdef CONFIG_PERF_EVENTS
-apicinterrupt LOCAL_PENDING_VECTOR \
-	perf_pending_interrupt smp_perf_pending_interrupt
+#ifdef CONFIG_IRQ_WORK
+apicinterrupt IRQ_WORK_VECTOR \
+	irq_work_interrupt smp_irq_work_interrupt
 #endif
 
 /*
@@ -1036,8 +1018,8 @@
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
-	subq $15*8,%rsp
-	CFI_ADJUST_CFA_OFFSET 15*8
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call error_entry
 	DEFAULT_FRAME 0
 	movq %rsp,%rdi		/* pt_regs pointer */
@@ -1052,9 +1034,9 @@
 ENTRY(\sym)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $-1		/* ORIG_RAX: no syscall to restart */
-	CFI_ADJUST_CFA_OFFSET 8
-	subq $15*8, %rsp
+	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
 	TRACE_IRQS_OFF
 	movq %rsp,%rdi		/* pt_regs pointer */
@@ -1070,9 +1052,9 @@
 ENTRY(\sym)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $-1		/* ORIG_RAX: no syscall to restart */
-	CFI_ADJUST_CFA_OFFSET 8
-	subq $15*8, %rsp
+	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
 	TRACE_IRQS_OFF
 	movq %rsp,%rdi		/* pt_regs pointer */
@@ -1089,8 +1071,8 @@
 ENTRY(\sym)
 	XCPT_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	subq $15*8,%rsp
-	CFI_ADJUST_CFA_OFFSET 15*8
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call error_entry
 	DEFAULT_FRAME 0
 	movq %rsp,%rdi			/* pt_regs pointer */
@@ -1107,8 +1089,8 @@
 ENTRY(\sym)
 	XCPT_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	subq $15*8,%rsp
-	CFI_ADJUST_CFA_OFFSET 15*8
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
 	DEFAULT_FRAME 0
 	TRACE_IRQS_OFF
@@ -1139,16 +1121,14 @@
 	/* edi:  new selector */
 ENTRY(native_load_gs_index)
 	CFI_STARTPROC
-	pushf
-	CFI_ADJUST_CFA_OFFSET 8
+	pushfq_cfi
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
 	SWAPGS
 gs_change:
 	movl %edi,%gs
 2:	mfence		/* workaround */
 	SWAPGS
-	popf
-	CFI_ADJUST_CFA_OFFSET -8
+	popfq_cfi
 	ret
 	CFI_ENDPROC
 END(native_load_gs_index)
@@ -1215,8 +1195,7 @@
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(call_softirq)
 	CFI_STARTPROC
-	push %rbp
-	CFI_ADJUST_CFA_OFFSET	8
+	pushq_cfi %rbp
 	CFI_REL_OFFSET rbp,0
 	mov  %rsp,%rbp
 	CFI_DEF_CFA_REGISTER rbp
@@ -1225,6 +1204,7 @@
 	push  %rbp			# backlink for old unwinder
 	call __do_softirq
 	leaveq
+	CFI_RESTORE		rbp
 	CFI_DEF_CFA_REGISTER	rsp
 	CFI_ADJUST_CFA_OFFSET   -8
 	decl PER_CPU_VAR(irq_count)
@@ -1368,7 +1348,7 @@
 
 	/* ebx:	no swapgs flag */
 ENTRY(paranoid_exit)
-	INTR_FRAME
+	DEFAULT_FRAME
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl %ebx,%ebx				/* swapgs needed? */
@@ -1445,7 +1425,6 @@
 error_sti:
 	TRACE_IRQS_OFF
 	ret
-	CFI_ENDPROC
 
 /*
  * There are two places in the kernel that can potentially fault with
@@ -1470,6 +1449,7 @@
 	/* Fix truncated RIP */
 	movq %rcx,RIP+8(%rsp)
 	jmp error_swapgs
+	CFI_ENDPROC
 END(error_entry)
 
 
@@ -1498,8 +1478,8 @@
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1
-	subq $15*8, %rsp
-	CFI_ADJUST_CFA_OFFSET 15*8
+	subq $ORIG_RAX-R15, %rsp
+	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
 	call save_paranoid
 	DEFAULT_FRAME 0
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index cd37469..3afb33f 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -257,14 +257,9 @@
 	return mod_code_status;
 }
 
-
-
-
-static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
-
 static unsigned char *ftrace_nop_replace(void)
 {
-	return ftrace_nop;
+	return ideal_nop5;
 }
 
 static int
@@ -338,62 +333,6 @@
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	extern const unsigned char ftrace_test_p6nop[];
-	extern const unsigned char ftrace_test_nop5[];
-	extern const unsigned char ftrace_test_jmp[];
-	int faulted = 0;
-
-	/*
-	 * There is no good nop for all x86 archs.
-	 * We will default to using the P6_NOP5, but first we
-	 * will test to make sure that the nop will actually
-	 * work on this CPU. If it faults, we will then
-	 * go to a lesser efficient 5 byte nop. If that fails
-	 * we then just use a jmp as our nop. This isn't the most
-	 * efficient nop, but we can not use a multi part nop
-	 * since we would then risk being preempted in the middle
-	 * of that nop, and if we enabled tracing then, it might
-	 * cause a system crash.
-	 *
-	 * TODO: check the cpuid to determine the best nop.
-	 */
-	asm volatile (
-		"ftrace_test_jmp:"
-		"jmp ftrace_test_p6nop\n"
-		"nop\n"
-		"nop\n"
-		"nop\n"  /* 2 byte jmp + 3 bytes */
-		"ftrace_test_p6nop:"
-		P6_NOP5
-		"jmp 1f\n"
-		"ftrace_test_nop5:"
-		".byte 0x66,0x66,0x66,0x66,0x90\n"
-		"1:"
-		".section .fixup, \"ax\"\n"
-		"2:	movl $1, %0\n"
-		"	jmp ftrace_test_nop5\n"
-		"3:	movl $2, %0\n"
-		"	jmp 1b\n"
-		".previous\n"
-		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
-		_ASM_EXTABLE(ftrace_test_nop5, 3b)
-		: "=r"(faulted) : "0" (faulted));
-
-	switch (faulted) {
-	case 0:
-		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
-		memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
-		break;
-	case 1:
-		pr_info("converting mcount calls to 66 66 66 66 90\n");
-		memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
-		break;
-	case 2:
-		pr_info("converting mcount calls to jmp . + 5\n");
-		memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
-		break;
-	}
-
 	/* The return code is retured via data */
 	*(unsigned long *)data = 0;
 
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index 3e66bd3..af0699b 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -1,5 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/bios_ebda.h>
@@ -51,5 +52,5 @@
 		lowmem = 0x9f000;
 
 	/* reserve all memory between lowmem and the 1MB mark */
-	reserve_early_overlap_ok(lowmem, 0x100000, "BIOS reserved");
+	memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved");
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 784360c..9a6ca23 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/start_kernel.h>
 #include <linux/mm.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -30,17 +31,18 @@
 
 void __init i386_start_kernel(void)
 {
+	memblock_init();
+
 #ifdef CONFIG_X86_TRAMPOLINE
 	/*
 	 * But first pinch a few for the stack/trampoline stuff
 	 * FIXME: Don't need the extra page at 4K, but need to fix
 	 * trampoline before removing it. (see the GDT stuff)
 	 */
-	reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE,
-					 "EX TRAMPOLINE");
+	memblock_x86_reserve_range(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
 #endif
 
-	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+	memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
@@ -49,7 +51,7 @@
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
 		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+		memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 7147143..2d2673c 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -12,6 +12,7 @@
 #include <linux/percpu.h>
 #include <linux/start_kernel.h>
 #include <linux/io.h>
+#include <linux/memblock.h>
 
 #include <asm/processor.h>
 #include <asm/proto.h>
@@ -79,6 +80,8 @@
 	/* Cleanup the over mapped high alias */
 	cleanup_highmap();
 
+	max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
+
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) {
 #ifdef CONFIG_EARLY_PRINTK
 		set_intr_gate(i, &early_idt_handlers[i]);
@@ -98,7 +101,9 @@
 {
 	copy_bootdata(__va(real_mode_data));
 
-	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
+	memblock_init();
+
+	memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
@@ -107,7 +112,7 @@
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
 		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
+		memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 7494999..aff0b3c 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -380,44 +380,35 @@
 			   struct clock_event_device *evt, int timer)
 {
 	u32 cnt;
+	s32 res;
 
 	cnt = hpet_readl(HPET_COUNTER);
 	cnt += (u32) delta;
 	hpet_writel(cnt, HPET_Tn_CMP(timer));
 
 	/*
-	 * We need to read back the CMP register on certain HPET
-	 * implementations (ATI chipsets) which seem to delay the
-	 * transfer of the compare register into the internal compare
-	 * logic. With small deltas this might actually be too late as
-	 * the counter could already be higher than the compare value
-	 * at that point and we would wait for the next hpet interrupt
-	 * forever. We found out that reading the CMP register back
-	 * forces the transfer so we can rely on the comparison with
-	 * the counter register below. If the read back from the
-	 * compare register does not match the value we programmed
-	 * then we might have a real hardware problem. We can not do
-	 * much about it here, but at least alert the user/admin with
-	 * a prominent warning.
-	 *
-	 * An erratum on some chipsets (ICH9,..), results in
-	 * comparator read immediately following a write returning old
-	 * value. Workaround for this is to read this value second
-	 * time, when first read returns old value.
-	 *
-	 * In fact the write to the comparator register is delayed up
-	 * to two HPET cycles so the workaround we tried to restrict
-	 * the readback to those known to be borked ATI chipsets
-	 * failed miserably. So we give up on optimizations forever
-	 * and penalize all HPET incarnations unconditionally.
+	 * HPETs are a complete disaster. The compare register is
+	 * based on a equal comparison and neither provides a less
+	 * than or equal functionality (which would require to take
+	 * the wraparound into account) nor a simple count down event
+	 * mode. Further the write to the comparator register is
+	 * delayed internally up to two HPET clock cycles in certain
+	 * chipsets (ATI, ICH9,10). We worked around that by reading
+	 * back the compare register, but that required another
+	 * workaround for ICH9,10 chips where the first readout after
+	 * write can return the old stale value. We already have a
+	 * minimum delta of 5us enforced, but a NMI or SMI hitting
+	 * between the counter readout and the comparator write can
+	 * move us behind that point easily. Now instead of reading
+	 * the compare register back several times, we make the ETIME
+	 * decision based on the following: Return ETIME if the
+	 * counter value after the write is less than 8 HPET cycles
+	 * away from the event or if the counter is already ahead of
+	 * the event.
 	 */
-	if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) {
-		if (hpet_readl(HPET_Tn_CMP(timer)) != cnt)
-			printk_once(KERN_WARNING
-				"hpet: compare register read back failed.\n");
-	}
+	res = (s32)(cnt - hpet_readl(HPET_COUNTER));
 
-	return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
+	return res < 8 ? -ETIME : 0;
 }
 
 static void hpet_legacy_set_mode(enum clock_event_mode mode,
@@ -440,9 +431,9 @@
 static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
 static struct hpet_dev	*hpet_devs;
 
-void hpet_msi_unmask(unsigned int irq)
+void hpet_msi_unmask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
+	struct hpet_dev *hdev = data->handler_data;
 	unsigned int cfg;
 
 	/* unmask it */
@@ -451,10 +442,10 @@
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
-void hpet_msi_mask(unsigned int irq)
+void hpet_msi_mask(struct irq_data *data)
 {
+	struct hpet_dev *hdev = data->handler_data;
 	unsigned int cfg;
-	struct hpet_dev *hdev = get_irq_data(irq);
 
 	/* mask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
@@ -462,18 +453,14 @@
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
-void hpet_msi_write(unsigned int irq, struct msi_msg *msg)
+void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
-
 	hpet_writel(msg->data, HPET_Tn_ROUTE(hdev->num));
 	hpet_writel(msg->address_lo, HPET_Tn_ROUTE(hdev->num) + 4);
 }
 
-void hpet_msi_read(unsigned int irq, struct msi_msg *msg)
+void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
-
 	msg->data = hpet_readl(HPET_Tn_ROUTE(hdev->num));
 	msg->address_lo = hpet_readl(HPET_Tn_ROUTE(hdev->num) + 4);
 	msg->address_hi = 0;
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index a46cb35..58bb239 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -68,19 +68,22 @@
 	 */
 
 	if (!HAVE_HWFP) {
+		/*
+		 * Disable xsave as we do not support it if i387
+		 * emulation is enabled.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 		xstate_size = sizeof(struct i387_soft_struct);
 		return;
 	}
 
 	if (cpu_has_fxsr)
 		xstate_size = sizeof(struct i387_fxsave_struct);
-#ifdef CONFIG_X86_32
 	else
 		xstate_size = sizeof(struct i387_fsave_struct);
-#endif
 }
 
-#ifdef CONFIG_X86_64
 /*
  * Called at bootup to set up the initial FPU state that is later cloned
  * into all processes.
@@ -88,12 +91,21 @@
 
 void __cpuinit fpu_init(void)
 {
-	unsigned long oldcr0 = read_cr0();
+	unsigned long cr0;
+	unsigned long cr4_mask = 0;
 
-	set_in_cr4(X86_CR4_OSFXSR);
-	set_in_cr4(X86_CR4_OSXMMEXCPT);
+	if (cpu_has_fxsr)
+		cr4_mask |= X86_CR4_OSFXSR;
+	if (cpu_has_xmm)
+		cr4_mask |= X86_CR4_OSXMMEXCPT;
+	if (cr4_mask)
+		set_in_cr4(cr4_mask);
 
-	write_cr0(oldcr0 & ~(X86_CR0_TS|X86_CR0_EM)); /* clear TS and EM */
+	cr0 = read_cr0();
+	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+	if (!HAVE_HWFP)
+		cr0 |= X86_CR0_EM;
+	write_cr0(cr0);
 
 	if (!smp_processor_id())
 		init_thread_xstate();
@@ -104,24 +116,12 @@
 	clear_used_math();
 }
 
-#else	/* CONFIG_X86_64 */
-
-void __cpuinit fpu_init(void)
-{
-	if (!smp_processor_id())
-		init_thread_xstate();
-}
-
-#endif	/* CONFIG_X86_32 */
-
 void fpu_finit(struct fpu *fpu)
 {
-#ifdef CONFIG_X86_32
 	if (!HAVE_HWFP) {
 		finit_soft_fpu(&fpu->state->soft);
 		return;
 	}
-#endif
 
 	if (cpu_has_fxsr) {
 		struct i387_fxsave_struct *fx = &fpu->state->fxsave;
@@ -386,19 +386,17 @@
 #ifdef CONFIG_X86_64
 	env->fip = fxsave->rip;
 	env->foo = fxsave->rdp;
+	/*
+	 * should be actually ds/cs at fpu exception time, but
+	 * that information is not available in 64bit mode.
+	 */
+	env->fcs = task_pt_regs(tsk)->cs;
 	if (tsk == current) {
-		/*
-		 * should be actually ds/cs at fpu exception time, but
-		 * that information is not available in 64bit mode.
-		 */
-		asm("mov %%ds, %[fos]" : [fos] "=r" (env->fos));
-		asm("mov %%cs, %[fcs]" : [fcs] "=r" (env->fcs));
+		savesegment(ds, env->fos);
 	} else {
-		struct pt_regs *regs = task_pt_regs(tsk);
-
-		env->fos = 0xffff0000 | tsk->thread.ds;
-		env->fcs = regs->cs;
+		env->fos = tsk->thread.ds;
 	}
+	env->fos |= 0xffff0000;
 #else
 	env->fip = fxsave->fip;
 	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index cafa7c8..20757cb 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -29,24 +29,10 @@
  * plus some generic x86 specific things if generic specifics makes
  * any sense at all.
  */
+static void init_8259A(int auto_eoi);
 
 static int i8259A_auto_eoi;
 DEFINE_RAW_SPINLOCK(i8259A_lock);
-static void mask_and_ack_8259A(unsigned int);
-static void mask_8259A(void);
-static void unmask_8259A(void);
-static void disable_8259A_irq(unsigned int irq);
-static void enable_8259A_irq(unsigned int irq);
-static void init_8259A(int auto_eoi);
-static int i8259A_irq_pending(unsigned int irq);
-
-struct irq_chip i8259A_chip = {
-	.name		= "XT-PIC",
-	.mask		= disable_8259A_irq,
-	.disable	= disable_8259A_irq,
-	.unmask		= enable_8259A_irq,
-	.mask_ack	= mask_and_ack_8259A,
-};
 
 /*
  * 8259A PIC functions to handle ISA devices:
@@ -68,7 +54,7 @@
  */
 unsigned long io_apic_irqs;
 
-static void disable_8259A_irq(unsigned int irq)
+static void mask_8259A_irq(unsigned int irq)
 {
 	unsigned int mask = 1 << irq;
 	unsigned long flags;
@@ -82,7 +68,12 @@
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-static void enable_8259A_irq(unsigned int irq)
+static void disable_8259A_irq(struct irq_data *data)
+{
+	mask_8259A_irq(data->irq);
+}
+
+static void unmask_8259A_irq(unsigned int irq)
 {
 	unsigned int mask = ~(1 << irq);
 	unsigned long flags;
@@ -96,6 +87,11 @@
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
+static void enable_8259A_irq(struct irq_data *data)
+{
+	unmask_8259A_irq(data->irq);
+}
+
 static int i8259A_irq_pending(unsigned int irq)
 {
 	unsigned int mask = 1<<irq;
@@ -117,7 +113,7 @@
 	disable_irq_nosync(irq);
 	io_apic_irqs &= ~(1<<irq);
 	set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
-				      "XT");
+				      i8259A_chip.name);
 	enable_irq(irq);
 }
 
@@ -150,8 +146,9 @@
  * first, _then_ send the EOI, and the order of EOI
  * to the two 8259s is important!
  */
-static void mask_and_ack_8259A(unsigned int irq)
+static void mask_and_ack_8259A(struct irq_data *data)
 {
+	unsigned int irq = data->irq;
 	unsigned int irqmask = 1 << irq;
 	unsigned long flags;
 
@@ -223,6 +220,14 @@
 	}
 }
 
+struct irq_chip i8259A_chip = {
+	.name		= "XT-PIC",
+	.irq_mask	= disable_8259A_irq,
+	.irq_disable	= disable_8259A_irq,
+	.irq_unmask	= enable_8259A_irq,
+	.irq_mask_ack	= mask_and_ack_8259A,
+};
+
 static char irq_trigger[2];
 /**
  * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
@@ -342,9 +347,9 @@
 		 * In AEOI mode we just have to mask the interrupt
 		 * when acking.
 		 */
-		i8259A_chip.mask_ack = disable_8259A_irq;
+		i8259A_chip.irq_mask_ack = disable_8259A_irq;
 	else
-		i8259A_chip.mask_ack = mask_and_ack_8259A;
+		i8259A_chip.irq_mask_ack = mask_and_ack_8259A;
 
 	udelay(100);		/* wait for 8259A to initialize */
 
@@ -363,14 +368,6 @@
 static void legacy_pic_noop(void) { };
 static void legacy_pic_uint_noop(unsigned int unused) { };
 static void legacy_pic_int_noop(int unused) { };
-
-static struct irq_chip dummy_pic_chip  = {
-	.name = "dummy pic",
-	.mask = legacy_pic_uint_noop,
-	.unmask = legacy_pic_uint_noop,
-	.disable = legacy_pic_uint_noop,
-	.mask_ack = legacy_pic_uint_noop,
-};
 static int legacy_pic_irq_pending_noop(unsigned int irq)
 {
 	return 0;
@@ -378,7 +375,9 @@
 
 struct legacy_pic null_legacy_pic = {
 	.nr_legacy_irqs = 0,
-	.chip = &dummy_pic_chip,
+	.chip = &dummy_irq_chip,
+	.mask = legacy_pic_uint_noop,
+	.unmask = legacy_pic_uint_noop,
 	.mask_all = legacy_pic_noop,
 	.restore_mask = legacy_pic_noop,
 	.init = legacy_pic_int_noop,
@@ -389,7 +388,9 @@
 struct legacy_pic default_legacy_pic = {
 	.nr_legacy_irqs = NR_IRQS_LEGACY,
 	.chip  = &i8259A_chip,
-	.mask_all  = mask_8259A,
+	.mask = mask_8259A_irq,
+	.unmask = unmask_8259A_irq,
+	.mask_all = mask_8259A,
 	.restore_mask = unmask_8259A,
 	.init = init_8259A,
 	.irq_pending = i8259A_irq_pending,
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 91fd0c7..83ec017 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -67,10 +67,10 @@
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
 	seq_printf(p, "  Performance monitoring interrupts\n");
-	seq_printf(p, "%*s: ", prec, "PND");
+	seq_printf(p, "%*s: ", prec, "IWI");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs);
-	seq_printf(p, "  Performance pending work\n");
+		seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs);
+	seq_printf(p, "  IRQ work interrupts\n");
 #endif
 	if (x86_platform_ipi_callback) {
 		seq_printf(p, "%*s: ", prec, "PLT");
@@ -159,7 +159,7 @@
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-	seq_printf(p, " %8s", desc->chip->name);
+	seq_printf(p, " %8s", desc->irq_data.chip->name);
 	seq_printf(p, "-%-8s", desc->name);
 
 	if (action) {
@@ -185,7 +185,7 @@
 	sum += irq_stats(cpu)->apic_timer_irqs;
 	sum += irq_stats(cpu)->irq_spurious_count;
 	sum += irq_stats(cpu)->apic_perf_irqs;
-	sum += irq_stats(cpu)->apic_pending_irqs;
+	sum += irq_stats(cpu)->apic_irq_work_irqs;
 #endif
 	if (x86_platform_ipi_callback)
 		sum += irq_stats(cpu)->x86_platform_ipis;
@@ -282,6 +282,7 @@
 	unsigned int irq, vector;
 	static int warned;
 	struct irq_desc *desc;
+	struct irq_data *data;
 
 	for_each_irq_desc(irq, desc) {
 		int break_affinity = 0;
@@ -296,7 +297,8 @@
 		/* interrupt's are disabled at this point */
 		raw_spin_lock(&desc->lock);
 
-		affinity = desc->affinity;
+		data = &desc->irq_data;
+		affinity = data->affinity;
 		if (!irq_has_action(irq) ||
 		    cpumask_equal(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
@@ -315,16 +317,16 @@
 			affinity = cpu_all_mask;
 		}
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->mask)
-			desc->chip->mask(irq);
+		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
+			data->chip->irq_mask(data);
 
-		if (desc->chip->set_affinity)
-			desc->chip->set_affinity(irq, affinity);
+		if (data->chip->irq_set_affinity)
+			data->chip->irq_set_affinity(data, affinity, true);
 		else if (!(warned++))
 			set_affinity = 0;
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->unmask)
-			desc->chip->unmask(irq);
+		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
+			data->chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
 
@@ -355,10 +357,10 @@
 		if (irr  & (1 << (vector % 32))) {
 			irq = __get_cpu_var(vector_irq)[vector];
 
-			desc = irq_to_desc(irq);
+			data = irq_get_irq_data(irq);
 			raw_spin_lock(&desc->lock);
-			if (desc->chip->retrigger)
-				desc->chip->retrigger(irq);
+			if (data->chip->irq_retrigger)
+				data->chip->irq_retrigger(data);
 			raw_spin_unlock(&desc->lock);
 		}
 	}
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 10709f2..50fbbe6 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -49,20 +49,19 @@
 static inline void print_stack_overflow(void) { }
 #endif
 
-#ifdef CONFIG_4KSTACKS
 /*
  * per-CPU IRQ handling contexts (thread information and stack)
  */
 union irq_ctx {
 	struct thread_info      tinfo;
 	u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __attribute__((aligned(PAGE_SIZE)));
+} __attribute__((aligned(THREAD_SIZE)));
 
 static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
 static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
 
-static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, hardirq_stack);
-static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, softirq_stack);
+static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, hardirq_stack, THREAD_SIZE);
+static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, softirq_stack, THREAD_SIZE);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -187,11 +186,6 @@
 	local_irq_restore(flags);
 }
 
-#else
-static inline int
-execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
-#endif
-
 bool handle_irq(unsigned irq, struct pt_regs *regs)
 {
 	struct irq_desc *desc;
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
new file mode 100644
index 0000000..ca8f703
--- /dev/null
+++ b/arch/x86/kernel/irq_work.c
@@ -0,0 +1,30 @@
+/*
+ * x86 specific code for irq_work
+ *
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/irq_work.h>
+#include <linux/hardirq.h>
+#include <asm/apic.h>
+
+void smp_irq_work_interrupt(struct pt_regs *regs)
+{
+	irq_enter();
+	ack_APIC_irq();
+	inc_irq_stat(apic_irq_work_irqs);
+	irq_work_run();
+	irq_exit();
+}
+
+void arch_irq_work_raise(void)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+	if (!cpu_has_apic)
+		return;
+
+	apic->send_IPI_self(IRQ_WORK_VECTOR);
+	apic_wait_icr_idle();
+#endif
+}
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 990ae7c..c752e97 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -100,6 +100,8 @@
 
 void __init init_ISA_irqs(void)
 {
+	struct irq_chip *chip = legacy_pic->chip;
+	const char *name = chip->name;
 	int i;
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
@@ -107,19 +109,8 @@
 #endif
 	legacy_pic->init(0);
 
-	/*
-	 * 16 old-style INTA-cycle interrupts:
-	 */
-	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-					      handle_level_irq, "XT");
-	}
+	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
+		set_irq_chip_and_handler_name(i, chip, handle_level_irq, name);
 }
 
 void __init init_IRQ(void)
@@ -224,9 +215,9 @@
 	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
 
-	/* Performance monitoring interrupts: */
-# ifdef CONFIG_PERF_EVENTS
-	alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt);
+	/* IRQ work interrupts: */
+# ifdef CONFIG_IRQ_WORK
+	alloc_intr_gate(IRQ_WORK_VECTOR, irq_work_interrupt);
 # endif
 
 #endif
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
new file mode 100644
index 0000000..961b6b3
--- /dev/null
+++ b/arch/x86/kernel/jump_label.c
@@ -0,0 +1,50 @@
+/*
+ * jump label x86 support
+ *
+ * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
+ *
+ */
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/cpu.h>
+#include <asm/kprobes.h>
+#include <asm/alternative.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+union jump_code_union {
+	char code[JUMP_LABEL_NOP_SIZE];
+	struct {
+		char jump;
+		int offset;
+	} __attribute__((packed));
+};
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	union jump_code_union code;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		code.jump = 0xe9;
+		code.offset = entry->target -
+				(entry->code + JUMP_LABEL_NOP_SIZE);
+	} else
+		memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+	text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+}
+
+void arch_jump_label_text_poke_early(jump_label_t addr)
+{
+	text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+}
+
+#endif
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 8afd9f3..90fcf62 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -78,6 +78,7 @@
 static const struct file_operations fops_setup_data = {
 	.read		= setup_data_read,
 	.open		= setup_data_open,
+	.llseek		= default_llseek,
 };
 
 static int __init
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 770ebfb..1cbd54c 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -230,9 +230,6 @@
 	return 0;
 }
 
-/* Dummy buffers for kallsyms_lookup */
-static char __dummy_buf[KSYM_NAME_LEN];
-
 /* Check if paddr is at an instruction boundary */
 static int __kprobes can_probe(unsigned long paddr)
 {
@@ -241,7 +238,7 @@
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
-	if (!kallsyms_lookup(paddr, NULL, &offset, NULL, __dummy_buf))
+	if (!kallsyms_lookup_size_offset(paddr, NULL, &offset))
 		return 0;
 
 	/* Decode instructions */
@@ -1129,7 +1126,7 @@
 	*(unsigned long *)addr = val;
 }
 
-void __kprobes kprobes_optinsn_template_holder(void)
+static void __used __kprobes kprobes_optinsn_template_holder(void)
 {
 	asm volatile (
 			".global optprobe_template_entry\n"
@@ -1221,7 +1218,8 @@
 	}
 	/* Check whether the address range is reserved */
 	if (ftrace_text_reserved(src, src + len - 1) ||
-	    alternatives_text_reserved(src, src + len - 1))
+	    alternatives_text_reserved(src, src + len - 1) ||
+	    jump_label_text_reserved(src, src + len - 1))
 		return -EBUSY;
 
 	return len;
@@ -1269,11 +1267,9 @@
 	unsigned long addr, size = 0, offset = 0;
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
-	/* Dummy buffers for lookup_symbol_attrs */
-	static char __dummy_buf[KSYM_NAME_LEN];
 
 	/* Lookup symbol including addr */
-	if (!kallsyms_lookup(paddr, &size, &offset, NULL, __dummy_buf))
+	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
 		return 0;
 
 	/* Check there is enough space for a relative jump. */
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 035c8c5..b3ea9db 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -36,7 +36,7 @@
 		if (!page)
 			goto out;
 		pud = (pud_t *)page_address(page);
-		memset(pud, 0, PAGE_SIZE);
+		clear_page(pud);
 		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
 	}
 	pud = pud_offset(pgd, addr);
@@ -45,7 +45,7 @@
 		if (!page)
 			goto out;
 		pmd = (pmd_t *)page_address(page);
-		memset(pmd, 0, PAGE_SIZE);
+		clear_page(pmd);
 		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
 	}
 	pmd = pmd_offset(pud, addr);
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index fa6551d..0b3d37e 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -232,6 +232,7 @@
 	.owner			= THIS_MODULE,
 	.write			= microcode_write,
 	.open			= microcode_open,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice microcode_dev = {
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 1c355c5..8f29560 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -239,6 +239,9 @@
 		apply_paravirt(pseg, pseg + para->sh_size);
 	}
 
+	/* make jump label nops */
+	jump_label_apply_nops(me);
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index d7b6f7f..9af64d9 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/bitops.h>
@@ -657,7 +658,7 @@
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
 
-	reserve_early_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc");
+	memblock_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc");
 }
 
 static int __init smp_scan_config(unsigned long base, unsigned long length)
@@ -686,7 +687,7 @@
 			       mpf, (u64)virt_to_phys(mpf));
 
 			mem = virt_to_phys(mpf);
-			reserve_early_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf");
+			memblock_x86_reserve_range(mem, mem + sizeof(*mpf), "* MP-table mpf");
 			if (mpf->physptr)
 				smp_reserve_memory(mpf);
 
diff --git a/arch/x86/kernel/olpc-xo1.c b/arch/x86/kernel/olpc-xo1.c
new file mode 100644
index 0000000..f5442c0
--- /dev/null
+++ b/arch/x86/kernel/olpc-xo1.c
@@ -0,0 +1,140 @@
+/*
+ * Support for features of the OLPC XO-1 laptop
+ *
+ * Copyright (C) 2010 One Laptop per Child
+ * Copyright (C) 2006 Red Hat, Inc.
+ * Copyright (C) 2006 Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+
+#include <asm/io.h>
+#include <asm/olpc.h>
+
+#define DRV_NAME "olpc-xo1"
+
+#define PMS_BAR		4
+#define ACPI_BAR	5
+
+/* PMC registers (PMS block) */
+#define PM_SCLK		0x10
+#define PM_IN_SLPCTL	0x20
+#define PM_WKXD		0x34
+#define PM_WKD		0x30
+#define PM_SSC		0x54
+
+/* PM registers (ACPI block) */
+#define PM1_CNT		0x08
+#define PM_GPE0_STS	0x18
+
+static unsigned long acpi_base;
+static unsigned long pms_base;
+
+static void xo1_power_off(void)
+{
+	printk(KERN_INFO "OLPC XO-1 power off sequence...\n");
+
+	/* Enable all of these controls with 0 delay */
+	outl(0x40000000, pms_base + PM_SCLK);
+	outl(0x40000000, pms_base + PM_IN_SLPCTL);
+	outl(0x40000000, pms_base + PM_WKXD);
+	outl(0x40000000, pms_base + PM_WKD);
+
+	/* Clear status bits (possibly unnecessary) */
+	outl(0x0002ffff, pms_base  + PM_SSC);
+	outl(0xffffffff, acpi_base + PM_GPE0_STS);
+
+	/* Write SLP_EN bit to start the machinery */
+	outl(0x00002000, acpi_base + PM1_CNT);
+}
+
+/* Read the base addresses from the PCI BAR info */
+static int __devinit setup_bases(struct pci_dev *pdev)
+{
+	int r;
+
+	r = pci_enable_device_io(pdev);
+	if (r) {
+		dev_err(&pdev->dev, "can't enable device IO\n");
+		return r;
+	}
+
+	r = pci_request_region(pdev, ACPI_BAR, DRV_NAME);
+	if (r) {
+		dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", ACPI_BAR);
+		return r;
+	}
+
+	r = pci_request_region(pdev, PMS_BAR, DRV_NAME);
+	if (r) {
+		dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", PMS_BAR);
+		pci_release_region(pdev, ACPI_BAR);
+		return r;
+	}
+
+	acpi_base = pci_resource_start(pdev, ACPI_BAR);
+	pms_base = pci_resource_start(pdev, PMS_BAR);
+
+	return 0;
+}
+
+static int __devinit olpc_xo1_probe(struct platform_device *pdev)
+{
+	struct pci_dev *pcidev;
+	int r;
+
+	pcidev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA,
+				NULL);
+	if (!pdev)
+		return -ENODEV;
+
+	r = setup_bases(pcidev);
+	if (r)
+		return r;
+
+	pm_power_off = xo1_power_off;
+
+	printk(KERN_INFO "OLPC XO-1 support registered\n");
+	return 0;
+}
+
+static int __devexit olpc_xo1_remove(struct platform_device *pdev)
+{
+	pm_power_off = NULL;
+	return 0;
+}
+
+static struct platform_driver olpc_xo1_driver = {
+	.driver = {
+		.name = DRV_NAME,
+		.owner = THIS_MODULE,
+	},
+	.probe = olpc_xo1_probe,
+	.remove = __devexit_p(olpc_xo1_remove),
+};
+
+static int __init olpc_xo1_init(void)
+{
+	return platform_driver_register(&olpc_xo1_driver);
+}
+
+static void __exit olpc_xo1_exit(void)
+{
+	platform_driver_unregister(&olpc_xo1_driver);
+}
+
+MODULE_AUTHOR("Daniel Drake <dsd@laptop.org>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:olpc-xo1");
+
+module_init(olpc_xo1_init);
+module_exit(olpc_xo1_exit);
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 0e0cdde..edaf3fe 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -17,6 +17,7 @@
 #include <linux/spinlock.h>
 #include <linux/io.h>
 #include <linux/string.h>
+#include <linux/platform_device.h>
 
 #include <asm/geode.h>
 #include <asm/setup.h>
@@ -114,6 +115,7 @@
 	unsigned long flags;
 	int ret = -EIO;
 	int i;
+	int restarts = 0;
 
 	spin_lock_irqsave(&ec_lock, flags);
 
@@ -169,7 +171,9 @@
 			if (wait_on_obf(0x6c, 1)) {
 				printk(KERN_ERR "olpc-ec:  timeout waiting for"
 						" EC to provide data!\n");
-				goto restart;
+				if (restarts++ < 10)
+					goto restart;
+				goto err;
 			}
 			outbuf[i] = inb(0x68);
 			pr_devel("olpc-ec:  received 0x%x\n", outbuf[i]);
@@ -183,8 +187,21 @@
 }
 EXPORT_SYMBOL_GPL(olpc_ec_cmd);
 
-#ifdef CONFIG_OLPC_OPENFIRMWARE
-static void __init platform_detect(void)
+static bool __init check_ofw_architecture(void)
+{
+	size_t propsize;
+	char olpc_arch[5];
+	const void *args[] = { NULL, "architecture", olpc_arch, (void *)5 };
+	void *res[] = { &propsize };
+
+	if (olpc_ofw("getprop", args, res)) {
+		printk(KERN_ERR "ofw: getprop call failed!\n");
+		return false;
+	}
+	return propsize == 5 && strncmp("OLPC", olpc_arch, 5) == 0;
+}
+
+static u32 __init get_board_revision(void)
 {
 	size_t propsize;
 	__be32 rev;
@@ -193,46 +210,44 @@
 
 	if (olpc_ofw("getprop", args, res) || propsize != 4) {
 		printk(KERN_ERR "ofw: getprop call failed!\n");
-		rev = cpu_to_be32(0);
+		return cpu_to_be32(0);
 	}
-	olpc_platform_info.boardrev = be32_to_cpu(rev);
+	return be32_to_cpu(rev);
 }
-#else
-static void __init platform_detect(void)
+
+static bool __init platform_detect(void)
 {
-	/* stopgap until OFW support is added to the kernel */
-	olpc_platform_info.boardrev = olpc_board(0xc2);
+	if (!check_ofw_architecture())
+		return false;
+	olpc_platform_info.flags |= OLPC_F_PRESENT;
+	olpc_platform_info.boardrev = get_board_revision();
+	return true;
 }
-#endif
+
+static int __init add_xo1_platform_devices(void)
+{
+	struct platform_device *pdev;
+
+	pdev = platform_device_register_simple("xo1-rfkill", -1, NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	return 0;
+}
 
 static int __init olpc_init(void)
 {
-	unsigned char *romsig;
+	int r = 0;
 
-	/* The ioremap check is dangerous; limit what we run it on */
-	if (!is_geode() || cs5535_has_vsa2())
+	if (!olpc_ofw_present() || !platform_detect())
 		return 0;
 
 	spin_lock_init(&ec_lock);
 
-	romsig = ioremap(0xffffffc0, 16);
-	if (!romsig)
-		return 0;
-
-	if (strncmp(romsig, "CL1   Q", 7))
-		goto unmap;
-	if (strncmp(romsig+6, romsig+13, 3)) {
-		printk(KERN_INFO "OLPC BIOS signature looks invalid.  "
-				"Assuming not OLPC\n");
-		goto unmap;
-	}
-
-	printk(KERN_INFO "OLPC board with OpenFirmware %.16s\n", romsig);
-	olpc_platform_info.flags |= OLPC_F_PRESENT;
-
-	/* get the platform revision */
-	platform_detect();
-
 	/* assume B1 and above models always have a DCON */
 	if (olpc_board_at_least(olpc_board(0xb1)))
 		olpc_platform_info.flags |= OLPC_F_DCON;
@@ -242,8 +257,10 @@
 			(unsigned char *) &olpc_platform_info.ecver, 1);
 
 #ifdef CONFIG_PCI_OLPC
-	/* If the VSA exists let it emulate PCI, if not emulate in kernel */
-	if (!cs5535_has_vsa2())
+	/* If the VSA exists let it emulate PCI, if not emulate in kernel.
+	 * XO-1 only. */
+	if (olpc_platform_info.boardrev < olpc_board_pre(0xd0) &&
+			!cs5535_has_vsa2())
 		x86_init.pci.arch_init = pci_olpc_init;
 #endif
 
@@ -252,8 +269,12 @@
 			olpc_platform_info.boardrev >> 4,
 			olpc_platform_info.ecver);
 
-unmap:
-	iounmap(romsig);
+	if (olpc_platform_info.boardrev < olpc_board_pre(0xd0)) { /* XO-1 */
+		r = add_xo1_platform_devices();
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/olpc_ofw.c b/arch/x86/kernel/olpc_ofw.c
index 3218aa7..7873204 100644
--- a/arch/x86/kernel/olpc_ofw.c
+++ b/arch/x86/kernel/olpc_ofw.c
@@ -74,6 +74,12 @@
 }
 EXPORT_SYMBOL_GPL(__olpc_ofw);
 
+bool olpc_ofw_present(void)
+{
+	return olpc_ofw_cif != NULL;
+}
+EXPORT_SYMBOL_GPL(olpc_ofw_present);
+
 /* OFW cif _should_ be above this address */
 #define OFW_MIN 0xff000000
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1db183e..c5b2500 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -413,7 +413,6 @@
 
 	.alloc_pte = paravirt_nop,
 	.alloc_pmd = paravirt_nop,
-	.alloc_pmd_clone = paravirt_nop,
 	.alloc_pud = paravirt_nop,
 	.release_pte = paravirt_nop,
 	.release_pmd = paravirt_nop,
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 078d4ec..f56a117 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -47,6 +47,7 @@
 #include <asm/rio.h>
 #include <asm/bios_ebda.h>
 #include <asm/x86_init.h>
+#include <asm/iommu_table.h>
 
 #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
 int use_calgary __read_mostly = 1;
@@ -1364,7 +1365,7 @@
 	return 0;
 }
 
-void __init detect_calgary(void)
+int __init detect_calgary(void)
 {
 	int bus;
 	void *tbl;
@@ -1378,13 +1379,13 @@
 	 * another HW IOMMU already, bail out.
 	 */
 	if (no_iommu || iommu_detected)
-		return;
+		return -ENODEV;
 
 	if (!use_calgary)
-		return;
+		return -ENODEV;
 
 	if (!early_pci_allowed())
-		return;
+		return -ENODEV;
 
 	printk(KERN_DEBUG "Calgary: detecting Calgary via BIOS EBDA area\n");
 
@@ -1410,13 +1411,13 @@
 	if (!rio_table_hdr) {
 		printk(KERN_DEBUG "Calgary: Unable to locate Rio Grande table "
 		       "in EBDA - bailing!\n");
-		return;
+		return -ENODEV;
 	}
 
 	ret = build_detail_arrays();
 	if (ret) {
 		printk(KERN_DEBUG "Calgary: build_detail_arrays ret %d\n", ret);
-		return;
+		return -ENOMEM;
 	}
 
 	specified_table_size = determine_tce_table_size((is_kdump_kernel() ?
@@ -1464,7 +1465,7 @@
 
 		x86_init.iommu.iommu_init = calgary_iommu_init;
 	}
-	return;
+	return calgary_found;
 
 cleanup:
 	for (--bus; bus >= 0; --bus) {
@@ -1473,6 +1474,7 @@
 		if (info->tce_space)
 			free_tce_table(info->tce_space);
 	}
+	return -ENOMEM;
 }
 
 static int __init calgary_parse_options(char *p)
@@ -1594,3 +1596,5 @@
  * and before device_initcall.
  */
 rootfs_initcall(calgary_fixup_tce_spaces);
+
+IOMMU_INIT_POST(detect_calgary);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 9f07cfc..9ea999a 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -11,9 +11,8 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/calgary.h>
-#include <asm/amd_iommu.h>
 #include <asm/x86_init.h>
-#include <asm/xen/swiotlb-xen.h>
+#include <asm/iommu_table.h>
 
 static int forbid_dac __read_mostly;
 
@@ -45,6 +44,8 @@
  */
 int iommu_pass_through __read_mostly;
 
+extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
+
 /* Dummy device used for NULL arguments (normally ISA). */
 struct device x86_dma_fallback_dev = {
 	.init_name = "fallback device",
@@ -130,26 +131,24 @@
 
 void __init pci_iommu_alloc(void)
 {
+	struct iommu_table_entry *p;
+
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
 
-	if (pci_xen_swiotlb_detect() || pci_swiotlb_detect())
-		goto out;
+	sort_iommu_table(__iommu_table, __iommu_table_end);
+	check_iommu_entries(__iommu_table, __iommu_table_end);
 
-	gart_iommu_hole_init();
-
-	detect_calgary();
-
-	detect_intel_iommu();
-
-	/* needs to be called after gart_iommu_hole_init */
-	amd_iommu_detect();
-out:
-	pci_xen_swiotlb_init();
-
-	pci_swiotlb_init();
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && p->detect && p->detect() > 0) {
+			p->flags |= IOMMU_DETECTED;
+			if (p->early_init)
+				p->early_init();
+			if (p->flags & IOMMU_FINISH_IF_DETECTED)
+				break;
+		}
+	}
 }
-
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 dma_addr_t *dma_addr, gfp_t flag)
 {
@@ -292,6 +291,7 @@
 
 static int __init pci_iommu_init(void)
 {
+	struct iommu_table_entry *p;
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 
 #ifdef CONFIG_PCI
@@ -299,12 +299,10 @@
 #endif
 	x86_init.iommu.iommu_init();
 
-	if (swiotlb || xen_swiotlb) {
-		printk(KERN_INFO "PCI-DMA: "
-		       "Using software bounce buffering for IO (SWIOTLB)\n");
-		swiotlb_print_info();
-	} else
-		swiotlb_free();
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
+			p->late_init();
+	}
 
 	return 0;
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 0f7f130..ba0f0ca 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -39,8 +39,9 @@
 #include <asm/cacheflush.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/x86_init.h>
+#include <asm/iommu_table.h>
 
 static unsigned long iommu_bus_base;	/* GART remapping area (physical) */
 static unsigned long iommu_size;	/* size of remapping area bytes */
@@ -560,8 +561,11 @@
 {
 	int i;
 
-	for (i = 0; i < num_k8_northbridges; i++) {
-		struct pci_dev *dev = k8_northbridges[i];
+	if (!k8_northbridges.gart_supported)
+		return;
+
+	for (i = 0; i < k8_northbridges.num; i++) {
+		struct pci_dev *dev = k8_northbridges.nb_misc[i];
 
 		enable_gart_translation(dev, __pa(agp_gatt_table));
 	}
@@ -592,16 +596,19 @@
 	if (!fix_up_north_bridges)
 		return;
 
+	if (!k8_northbridges.gart_supported)
+		return;
+
 	pr_info("PCI-DMA: Restoring GART aperture settings\n");
 
-	for (i = 0; i < num_k8_northbridges; i++) {
-		struct pci_dev *dev = k8_northbridges[i];
+	for (i = 0; i < k8_northbridges.num; i++) {
+		struct pci_dev *dev = k8_northbridges.nb_misc[i];
 
 		/*
 		 * Don't enable translations just yet.  That is the next
 		 * step.  Restore the pre-suspend aperture settings.
 		 */
-		pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, aperture_order << 1);
+		gart_set_size_and_enable(dev, aperture_order);
 		pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE, aperture_alloc >> 25);
 	}
 }
@@ -649,8 +656,8 @@
 
 	aper_size = aper_base = info->aper_size = 0;
 	dev = NULL;
-	for (i = 0; i < num_k8_northbridges; i++) {
-		dev = k8_northbridges[i];
+	for (i = 0; i < k8_northbridges.num; i++) {
+		dev = k8_northbridges.nb_misc[i];
 		new_aper_base = read_aperture(dev, &new_aper_size);
 		if (!new_aper_base)
 			goto nommu;
@@ -718,10 +725,13 @@
 	if (!no_agp)
 		return;
 
-	for (i = 0; i < num_k8_northbridges; i++) {
+	if (!k8_northbridges.gart_supported)
+		return;
+
+	for (i = 0; i < k8_northbridges.num; i++) {
 		u32 ctl;
 
-		dev = k8_northbridges[i];
+		dev = k8_northbridges.nb_misc[i];
 		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
 
 		ctl &= ~GARTEN;
@@ -739,7 +749,7 @@
 	unsigned long scratch;
 	long i;
 
-	if (num_k8_northbridges == 0)
+	if (!k8_northbridges.gart_supported)
 		return 0;
 
 #ifndef CONFIG_AGP_AMD64
@@ -896,3 +906,4 @@
 		}
 	}
 }
+IOMMU_INIT_POST(gart_iommu_hole_init);
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
new file mode 100644
index 0000000..55d745e
--- /dev/null
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -0,0 +1,89 @@
+#include <linux/dma-mapping.h>
+#include <asm/iommu_table.h>
+#include <linux/string.h>
+#include <linux/kallsyms.h>
+
+
+#define DEBUG 1
+
+static struct iommu_table_entry * __init
+find_dependents_of(struct iommu_table_entry *start,
+		   struct iommu_table_entry *finish,
+		   struct iommu_table_entry *q)
+{
+	struct iommu_table_entry *p;
+
+	if (!q)
+		return NULL;
+
+	for (p = start; p < finish; p++)
+		if (p->detect == q->depend)
+			return p;
+
+	return NULL;
+}
+
+
+void __init sort_iommu_table(struct iommu_table_entry *start,
+			     struct iommu_table_entry *finish) {
+
+	struct iommu_table_entry *p, *q, tmp;
+
+	for (p = start; p < finish; p++) {
+again:
+		q = find_dependents_of(start, finish, p);
+		/* We are bit sneaky here. We use the memory address to figure
+		 * out if the node we depend on is past our point, if so, swap.
+		 */
+		if (q > p) {
+			tmp = *p;
+			memmove(p, q, sizeof(*p));
+			*q = tmp;
+			goto again;
+		}
+	}
+
+}
+
+#ifdef DEBUG
+void __init check_iommu_entries(struct iommu_table_entry *start,
+				struct iommu_table_entry *finish)
+{
+	struct iommu_table_entry *p, *q, *x;
+	char sym_p[KSYM_SYMBOL_LEN];
+	char sym_q[KSYM_SYMBOL_LEN];
+
+	/* Simple cyclic dependency checker. */
+	for (p = start; p < finish; p++) {
+		q = find_dependents_of(start, finish, p);
+		x = find_dependents_of(start, finish, q);
+		if (p == x) {
+			sprint_symbol(sym_p, (unsigned long)p->detect);
+			sprint_symbol(sym_q, (unsigned long)q->detect);
+
+			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %s depends" \
+					" on %s and vice-versa. BREAKING IT.\n",
+					sym_p, sym_q);
+			/* Heavy handed way..*/
+			x->depend = 0;
+		}
+	}
+
+	for (p = start; p < finish; p++) {
+		q = find_dependents_of(p, finish, p);
+		if (q && q > p) {
+			sprint_symbol(sym_p, (unsigned long)p->detect);
+			sprint_symbol(sym_q, (unsigned long)q->detect);
+
+			printk(KERN_ERR "EXECUTION ORDER INVALID! %s "\
+					"should be called before %s!\n",
+					sym_p, sym_q);
+		}
+	}
+}
+#else
+inline void check_iommu_entries(struct iommu_table_entry *start,
+				       struct iommu_table_entry *finish)
+{
+}
+#endif
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index a5bc528..8f972cb 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -10,7 +10,8 @@
 #include <asm/iommu.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
-
+#include <asm/xen/swiotlb-xen.h>
+#include <asm/iommu_table.h>
 int swiotlb __read_mostly;
 
 static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
@@ -41,25 +42,42 @@
 };
 
 /*
- * pci_swiotlb_detect - set swiotlb to 1 if necessary
+ * pci_swiotlb_detect_override - set swiotlb to 1 if necessary
  *
  * This returns non-zero if we are forced to use swiotlb (by the boot
  * option).
  */
-int __init pci_swiotlb_detect(void)
+int __init pci_swiotlb_detect_override(void)
 {
 	int use_swiotlb = swiotlb | swiotlb_force;
 
-	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-#ifdef CONFIG_X86_64
-	if (!no_iommu && max_pfn > MAX_DMA32_PFN)
-		swiotlb = 1;
-#endif
 	if (swiotlb_force)
 		swiotlb = 1;
 
 	return use_swiotlb;
 }
+IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
+		  pci_xen_swiotlb_detect,
+		  pci_swiotlb_init,
+		  pci_swiotlb_late_init);
+
+/*
+ * if 4GB or more detected (and iommu=off not set) return 1
+ * and set swiotlb to 1.
+ */
+int __init pci_swiotlb_detect_4gb(void)
+{
+	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
+#ifdef CONFIG_X86_64
+	if (!no_iommu && max_pfn > MAX_DMA32_PFN)
+		swiotlb = 1;
+#endif
+	return swiotlb;
+}
+IOMMU_INIT(pci_swiotlb_detect_4gb,
+	   pci_swiotlb_detect_override,
+	   pci_swiotlb_init,
+	   pci_swiotlb_late_init);
 
 void __init pci_swiotlb_init(void)
 {
@@ -68,3 +86,15 @@
 		dma_ops = &swiotlb_dma_ops;
 	}
 }
+
+void __init pci_swiotlb_late_init(void)
+{
+	/* An IOMMU turned us off. */
+	if (!swiotlb)
+		swiotlb_free();
+	else {
+		printk(KERN_INFO "PCI-DMA: "
+		       "Using software bounce buffering for IO (SWIOTLB)\n");
+		swiotlb_print_info();
+	}
+}
diff --git a/arch/x86/kernel/pmtimer_64.c b/arch/x86/kernel/pmtimer_64.c
deleted file mode 100644
index b112406..0000000
--- a/arch/x86/kernel/pmtimer_64.c
+++ /dev/null
@@ -1,69 +0,0 @@
-/* Ported over from i386 by AK, original copyright was:
- *
- * (C) Dominik Brodowski <linux@brodo.de> 2003
- *
- * Driver to use the Power Management Timer (PMTMR) available in some
- * southbridges as primary timing source for the Linux kernel.
- *
- * Based on parts of linux/drivers/acpi/hardware/hwtimer.c, timer_pit.c,
- * timer_hpet.c, and on Arjan van de Ven's implementation for 2.4.
- *
- * This file is licensed under the GPL v2.
- *
- * Dropped all the hardware bug workarounds for now. Hopefully they
- * are not needed on 64bit chipsets.
- */
-
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/init.h>
-#include <linux/cpumask.h>
-#include <linux/acpi_pmtmr.h>
-
-#include <asm/io.h>
-#include <asm/proto.h>
-#include <asm/msr.h>
-#include <asm/vsyscall.h>
-
-static inline u32 cyc2us(u32 cycles)
-{
-	/* The Power Management Timer ticks at 3.579545 ticks per microsecond.
-	 * 1 / PM_TIMER_FREQUENCY == 0.27936511 =~ 286/1024 [error: 0.024%]
-	 *
-	 * Even with HZ = 100, delta is at maximum 35796 ticks, so it can
-	 * easily be multiplied with 286 (=0x11E) without having to fear
-	 * u32 overflows.
-	 */
-	cycles *= 286;
-	return (cycles >> 10);
-}
-
-static unsigned pmtimer_wait_tick(void)
-{
-	u32 a, b;
-	for (a = b = inl(pmtmr_ioport) & ACPI_PM_MASK;
-	     a == b;
-	     b = inl(pmtmr_ioport) & ACPI_PM_MASK)
-		cpu_relax();
-	return b;
-}
-
-/* note: wait time is rounded up to one tick */
-void pmtimer_wait(unsigned us)
-{
-	u32 a, b;
-	a = pmtimer_wait_tick();
-	do {
-		b = inl(pmtmr_ioport);
-		cpu_relax();
-	} while (cyc2us(b - a) < us);
-}
-
-static int __init nopmtimer_setup(char *s)
-{
-	pmtmr_ioport = 0;
-	return 1;
-}
-
-__setup("nopmtimer", nopmtimer_setup);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3d9ea53..b3d7a3a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -424,7 +424,7 @@
 	load_TLS(next, cpu);
 
 	/* Must be after DS reload */
-	unlazy_fpu(prev_p);
+	__unlazy_fpu(prev_p);
 
 	/* Make sure cpu is ready for new context */
 	if (preload_fpu)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e3af342..7a4cf14 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -84,7 +84,7 @@
 			}
 				/* we will leave sorting out the final value
 				   when we are ready to reboot, since we might not
-				   have set up boot_cpu_id or smp_num_cpu */
+				   have detected BSP APIC ID or smp_num_cpu */
 			break;
 #endif /* CONFIG_SMP */
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c3a4fbb..420e641 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -31,6 +31,7 @@
 #include <linux/apm_bios.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/seq_file.h>
 #include <linux/console.h>
 #include <linux/mca.h>
@@ -83,7 +84,6 @@
 #include <asm/dmi.h>
 #include <asm/io_apic.h>
 #include <asm/ist.h>
-#include <asm/vmi.h>
 #include <asm/setup_arch.h>
 #include <asm/bios_ebda.h>
 #include <asm/cacheflush.h>
@@ -107,11 +107,12 @@
 #include <asm/percpu.h>
 #include <asm/topology.h>
 #include <asm/apicdef.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #ifdef CONFIG_X86_64
 #include <asm/numa_64.h>
 #endif
 #include <asm/mce.h>
+#include <asm/alternative.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -125,7 +126,6 @@
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
 
-unsigned int boot_cpu_id __read_mostly;
 
 static __initdata unsigned long _brk_start = (unsigned long)__brk_base;
 unsigned long _brk_end = (unsigned long)__brk_base;
@@ -302,7 +302,7 @@
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
-		reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK");
+		memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK");
 
 	/* Mark brk area as locked down and no longer taking any
 	   new allocations */
@@ -324,17 +324,16 @@
 	char *p, *q;
 
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
+	ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
-	if (ramdisk_here == -1ULL)
+	if (ramdisk_here == MEMBLOCK_ERROR)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
 			 ramdisk_size);
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + area_size,
-			 "NEW RAMDISK");
+	memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
@@ -390,7 +389,7 @@
 	initrd_start = 0;
 
 	if (ramdisk_size >= (end_of_lowmem>>1)) {
-		free_early(ramdisk_image, ramdisk_end);
+		memblock_x86_free_range(ramdisk_image, ramdisk_end);
 		printk(KERN_ERR "initrd too large to handle, "
 		       "disabling initrd\n");
 		return;
@@ -413,7 +412,7 @@
 
 	relocate_initrd();
 
-	free_early(ramdisk_image, ramdisk_end);
+	memblock_x86_free_range(ramdisk_image, ramdisk_end);
 }
 #else
 static void __init reserve_initrd(void)
@@ -469,7 +468,7 @@
 	e820_print_map("reserve setup_data");
 }
 
-static void __init reserve_early_setup_data(void)
+static void __init memblock_x86_reserve_range_setup_data(void)
 {
 	struct setup_data *data;
 	u64 pa_data;
@@ -481,7 +480,7 @@
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
 		sprintf(buf, "setup data %x", data->type);
-		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+		memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf);
 		pa_data = data->next;
 		early_iounmap(data, sizeof(*data));
 	}
@@ -502,6 +501,7 @@
 	return total << PAGE_SHIFT;
 }
 
+#define DEFAULT_BZIMAGE_ADDR_MAX 0x37FFFFFF
 static void __init reserve_crashkernel(void)
 {
 	unsigned long long total_mem;
@@ -519,23 +519,27 @@
 	if (crash_base <= 0) {
 		const unsigned long long alignment = 16<<20;	/* 16M */
 
-		crash_base = find_e820_area(alignment, ULONG_MAX, crash_size,
-				 alignment);
-		if (crash_base == -1ULL) {
+		/*
+		 *  kexec want bzImage is below DEFAULT_BZIMAGE_ADDR_MAX
+		 */
+		crash_base = memblock_find_in_range(alignment,
+			       DEFAULT_BZIMAGE_ADDR_MAX, crash_size, alignment);
+
+		if (crash_base == MEMBLOCK_ERROR) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
 	} else {
 		unsigned long long start;
 
-		start = find_e820_area(crash_base, ULONG_MAX, crash_size,
-				 1<<20);
+		start = memblock_find_in_range(crash_base,
+				 crash_base + crash_size, crash_size, 1<<20);
 		if (start != crash_base) {
 			pr_info("crashkernel reservation failed - memory is in use.\n");
 			return;
 		}
 	}
-	reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL");
+	memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL");
 
 	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
 			"for crashkernel (System RAM: %ldMB)\n",
@@ -615,82 +619,10 @@
 	addr = find_ibft_region(&size);
 
 	if (size)
-		reserve_early_overlap_ok(addr, addr + size, "ibft");
+		memblock_x86_reserve_range(addr, addr + size, "* ibft");
 }
 
-#ifdef CONFIG_X86_RESERVE_LOW_64K
-static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
-{
-	printk(KERN_NOTICE
-		"%s detected: BIOS may corrupt low RAM, working around it.\n",
-		d->ident);
-
-	e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED);
-	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-
-	return 0;
-}
-#endif
-
-/* List of systems that have known low memory corruption BIOS problems */
-static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
-#ifdef CONFIG_X86_RESERVE_LOW_64K
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "AMI BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
-		},
-	},
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "Phoenix BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"),
-		},
-	},
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "Phoenix/MSC BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
-		},
-	},
-	/*
-	 * AMI BIOS with low memory corruption was found on Intel DG45ID and
-	 * DG45FC boards.
-	 * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
-	 * match only DMI_BOARD_NAME and see if there is more bad products
-	 * with this vendor.
-	 */
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "AMI BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "DG45ID"),
-		},
-	},
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "AMI BIOS",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
-		},
-	},
-	/*
-	 * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so
-	 * match on the product name.
-	 */
-	{
-		.callback = dmi_low_memory_corruption,
-		.ident = "Phoenix BIOS",
-		.matches = {
-			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"),
-		},
-	},
-#endif
-	{}
-};
+static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
 static void __init trim_bios_range(void)
 {
@@ -698,8 +630,14 @@
 	 * A special case is the first 4Kb of memory;
 	 * This is a BIOS owned area, not kernel ram, but generally
 	 * not listed as such in the E820 table.
+	 *
+	 * This typically reserves additional memory (64KiB by default)
+	 * since some BIOSes are known to corrupt low memory.  See the
+	 * Kconfig help text for X86_RESERVE_LOW.
 	 */
-	e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+	e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE),
+			  E820_RAM, E820_RESERVED);
+
 	/*
 	 * special case: Some BIOSen report the PC BIOS
 	 * area (640->1Mb) as ram even though it is not.
@@ -709,6 +647,37 @@
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
+static int __init parse_reservelow(char *p)
+{
+	unsigned long long size;
+
+	if (!p)
+		return -EINVAL;
+
+	size = memparse(p, &p);
+
+	if (size < 4096)
+		size = 4096;
+
+	if (size > 640*1024)
+		size = 640*1024;
+
+	reserve_low = size;
+
+	return 0;
+}
+
+early_param("reservelow", parse_reservelow);
+
+static u64 __init get_max_mapped(void)
+{
+	u64 end = max_pfn_mapped;
+
+	end <<= PAGE_SHIFT;
+
+	return end;
+}
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -726,6 +695,7 @@
 {
 	int acpi = 0;
 	int k8 = 0;
+	unsigned long flags;
 
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
@@ -734,10 +704,10 @@
 	printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
 
-	/* VMI may relocate the fixmap; do this before touching ioremap area */
-	vmi_init();
-
-	/* OFW also may relocate the fixmap */
+	/*
+	 * If we have OLPC OFW, we might end up relocating the fixmap due to
+	 * reserve_top(), so do this before touching the ioremap area.
+	 */
 	olpc_ofw_detect();
 
 	early_trap_init();
@@ -782,7 +752,7 @@
 #endif
 	 4)) {
 		efi_enabled = 1;
-		efi_reserve_early();
+		efi_memblock_x86_reserve_range();
 	}
 #endif
 
@@ -838,11 +808,8 @@
 
 	x86_report_nx();
 
-	/* Must be before kernel pagetables are setup */
-	vmi_activate();
-
 	/* after early param, so could get panic from serial */
-	reserve_early_setup_data();
+	memblock_x86_reserve_range_setup_data();
 
 	if (acpi_mps_check()) {
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -863,8 +830,6 @@
 
 	dmi_scan_machine();
 
-	dmi_check_system(bad_bios_dmi_table);
-
 	/*
 	 * VMware detection requires dmi to be available, so this
 	 * needs to be done after dmi_scan_machine, for the BP.
@@ -897,8 +862,6 @@
 	 */
 	max_pfn = e820_end_of_ram_pfn();
 
-	/* preallocate 4k for mptable mpc */
-	early_reserve_e820_mpc_new();
 	/* update e820 for memory not covered by WB MTRRs */
 	mtrr_bp_init();
 	if (mtrr_trim_uncached_memory(max_pfn))
@@ -920,18 +883,8 @@
 		max_low_pfn = max_pfn;
 
 	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
-	max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 #endif
 
-#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
-	setup_bios_corruption_check();
-#endif
-
-	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
-			max_pfn_mapped<<PAGE_SHIFT);
-
-	reserve_brk();
-
 	/*
 	 * Find and reserve possible boot-time SMP configuration:
 	 */
@@ -939,6 +892,26 @@
 
 	reserve_ibft_region();
 
+	/*
+	 * Need to conclude brk, before memblock_x86_fill()
+	 *  it could use memblock_find_in_range, could overlap with
+	 *  brk area.
+	 */
+	reserve_brk();
+
+	memblock.current_limit = get_max_mapped();
+	memblock_x86_fill();
+
+	/* preallocate 4k for mptable mpc */
+	early_reserve_e820_mpc_new();
+
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+	setup_bios_corruption_check();
+#endif
+
+	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+			max_pfn_mapped<<PAGE_SHIFT);
+
 	reserve_trampoline_memory();
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -962,6 +935,7 @@
 		max_low_pfn = max_pfn;
 	}
 #endif
+	memblock.current_limit = get_max_mapped();
 
 	/*
 	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
@@ -1000,10 +974,7 @@
 #endif
 
 	initmem_init(0, max_pfn, acpi, k8);
-#ifndef CONFIG_NO_BOOTMEM
-	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
-#endif
-
+	memblock_find_dma_reserve();
 	dma32_reserve_bootmem();
 
 #ifdef CONFIG_KVM_CLOCK
@@ -1071,6 +1042,10 @@
 	x86_init.oem.banner();
 
 	mcheck_init();
+
+	local_irq_save(flags);
+	arch_init_ideal_nop5();
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index a60df9a..002b796 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -131,13 +131,7 @@
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-#ifdef CONFIG_NO_BOOTMEM
-	u64 start = __pa(ptr);
-	u64 end = start + size;
-	free_early_partial(start, end);
-#else
 	free_bootmem(__pa(ptr), size);
-#endif
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
@@ -253,7 +247,7 @@
 		 * Up to this point, the boot CPU has been using .init.data
 		 * area.  Reload any changed state for the boot CPU.
 		 */
-		if (cpu == boot_cpu_id)
+		if (!cpu)
 			switch_to_new_gdt(cpu);
 	}
 
diff --git a/arch/x86/kernel/sfi.c b/arch/x86/kernel/sfi.c
index cb22acf..dd4c281 100644
--- a/arch/x86/kernel/sfi.c
+++ b/arch/x86/kernel/sfi.c
@@ -34,7 +34,7 @@
 #ifdef CONFIG_X86_LOCAL_APIC
 static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 
-void __init mp_sfi_register_lapic_address(unsigned long address)
+static void __init mp_sfi_register_lapic_address(unsigned long address)
 {
 	mp_lapic_addr = address;
 
@@ -46,7 +46,7 @@
 }
 
 /* All CPUs enumerated by SFI must be present and enabled */
-void __cpuinit mp_sfi_register_lapic(u8 id)
+static void __cpuinit mp_sfi_register_lapic(u8 id)
 {
 	if (MAX_APICS - id <= 0) {
 		pr_warning("Processor #%d invalid (max %d)\n",
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8b3bfc4..dfb5089 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -62,7 +62,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
-#include <asm/vmi.h>
+#include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
@@ -311,7 +311,6 @@
 	__flush_tlb_all();
 #endif
 
-	vmi_bringup();
 	cpu_init();
 	preempt_disable();
 	smp_callin();
@@ -324,9 +323,9 @@
 	check_tsc_sync_target();
 
 	if (nmi_watchdog == NMI_IO_APIC) {
-		legacy_pic->chip->mask(0);
+		legacy_pic->mask(0);
 		enable_NMI_through_LVT0();
-		legacy_pic->chip->unmask(0);
+		legacy_pic->unmask(0);
 	}
 
 	/* This must be done before setting cpu_online_mask */
@@ -397,6 +396,19 @@
 		identify_secondary_cpu(c);
 }
 
+static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
+{
+	struct cpuinfo_x86 *c1 = &cpu_data(cpu1);
+	struct cpuinfo_x86 *c2 = &cpu_data(cpu2);
+
+	cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
+	cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
+	cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
+	cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
+	cpumask_set_cpu(cpu1, c2->llc_shared_map);
+	cpumask_set_cpu(cpu2, c1->llc_shared_map);
+}
+
 
 void __cpuinit set_cpu_sibling_map(int cpu)
 {
@@ -409,14 +421,13 @@
 		for_each_cpu(i, cpu_sibling_setup_mask) {
 			struct cpuinfo_x86 *o = &cpu_data(i);
 
-			if (c->phys_proc_id == o->phys_proc_id &&
-			    c->cpu_core_id == o->cpu_core_id) {
-				cpumask_set_cpu(i, cpu_sibling_mask(cpu));
-				cpumask_set_cpu(cpu, cpu_sibling_mask(i));
-				cpumask_set_cpu(i, cpu_core_mask(cpu));
-				cpumask_set_cpu(cpu, cpu_core_mask(i));
-				cpumask_set_cpu(i, c->llc_shared_map);
-				cpumask_set_cpu(cpu, o->llc_shared_map);
+			if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+				if (c->phys_proc_id == o->phys_proc_id &&
+				    c->compute_unit_id == o->compute_unit_id)
+					link_thread_siblings(cpu, i);
+			} else if (c->phys_proc_id == o->phys_proc_id &&
+				   c->cpu_core_id == o->cpu_core_id) {
+				link_thread_siblings(cpu, i);
 			}
 		}
 	} else {
@@ -1109,8 +1120,6 @@
 	}
 	set_cpu_sibling_map(0);
 
-	enable_IR_x2apic();
-	default_setup_apic_routing();
 
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
@@ -1118,6 +1127,8 @@
 		goto out;
 	}
 
+	default_setup_apic_routing();
+
 	preempt_disable();
 	if (read_apic_id() != boot_cpu_physical_apicid) {
 		panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
@@ -1383,11 +1394,88 @@
 	local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
+static inline void mwait_play_dead(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int highest_cstate = 0;
+	unsigned int highest_subcstate = 0;
+	int i;
+	void *mwait_ptr;
+
+	if (!cpu_has(&current_cpu_data, X86_FEATURE_MWAIT))
+		return;
+	if (!cpu_has(&current_cpu_data, X86_FEATURE_CLFLSH))
+		return;
+	if (current_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+		return;
+
+	eax = CPUID_MWAIT_LEAF;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	/*
+	 * eax will be 0 if EDX enumeration is not valid.
+	 * Initialized below to cstate, sub_cstate value when EDX is valid.
+	 */
+	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
+		eax = 0;
+	} else {
+		edx >>= MWAIT_SUBSTATE_SIZE;
+		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
+			if (edx & MWAIT_SUBSTATE_MASK) {
+				highest_cstate = i;
+				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
+			}
+		}
+		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
+			(highest_subcstate - 1);
+	}
+
+	/*
+	 * This should be a memory location in a cache line which is
+	 * unlikely to be touched by other processors.  The actual
+	 * content is immaterial as it is not actually modified in any way.
+	 */
+	mwait_ptr = &current_thread_info()->flags;
+
+	wbinvd();
+
+	while (1) {
+		/*
+		 * The CLFLUSH is a workaround for erratum AAI65 for
+		 * the Xeon 7400 series.  It's not clear it is actually
+		 * needed, but it should be harmless in either case.
+		 * The WBINVD is insufficient due to the spurious-wakeup
+		 * case where we return around the loop.
+		 */
+		clflush(mwait_ptr);
+		__monitor(mwait_ptr, 0, 0);
+		mb();
+		__mwait(eax, 0);
+	}
+}
+
+static inline void hlt_play_dead(void)
+{
+	if (current_cpu_data.x86 >= 4)
+		wbinvd();
+
+	while (1) {
+		native_halt();
+	}
+}
+
 void native_play_dead(void)
 {
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
-	wbinvd_halt();
+
+	mwait_play_dead();	/* Only returns on failure */
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
index d5e0662..0b0cb5f 100644
--- a/arch/x86/kernel/sys_i386_32.c
+++ b/arch/x86/kernel/sys_i386_32.c
@@ -33,8 +33,8 @@
 		  const char *const envp[])
 {
 	long __res;
-	asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx"
+	asm volatile ("int $0x80"
 	: "=a" (__res)
-	: "0" (__NR_execve), "ri" (filename), "c" (argv), "d" (envp) : "memory");
+	: "0" (__NR_execve), "b" (filename), "c" (argv), "d" (envp) : "memory");
 	return __res;
 }
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 312ef02..50ac949 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -1285,6 +1285,7 @@
 	.open		= tunables_open,
 	.read		= tunables_read,
 	.write		= tunables_write,
+	.llseek		= default_llseek,
 };
 
 static int __init uv_ptc_init(void)
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index e2a5952..4c3da56 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -1,8 +1,8 @@
 #include <linux/io.h>
+#include <linux/memblock.h>
 
 #include <asm/trampoline.h>
 #include <asm/pgtable.h>
-#include <asm/e820.h>
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
 #define __trampinit
@@ -17,15 +17,15 @@
 
 void __init reserve_trampoline_memory(void)
 {
-	unsigned long mem;
+	phys_addr_t mem;
 
 	/* Has to be in very low memory so we can execute real-mode AP code. */
-	mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
-	if (mem == -1L)
+	mem = memblock_find_in_range(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
+	if (mem == MEMBLOCK_ERROR)
 		panic("Cannot allocate trampoline\n");
 
 	trampoline_base = __va(mem);
-	reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
+	memblock_x86_reserve_range(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
 }
 
 /*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 60788de..d439685 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -776,21 +776,10 @@
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
-#ifndef CONFIG_MATH_EMULATION
-void math_emulate(struct math_emu_info *info)
-{
-	printk(KERN_EMERG
-		"math-emulation not enabled and no coprocessor found.\n");
-	printk(KERN_EMERG "killing %s.\n", current->comm);
-	force_sig(SIGFPE, current);
-	schedule();
-}
-#endif /* CONFIG_MATH_EMULATION */
-
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {
 		struct math_emu_info info = { };
 
@@ -798,12 +787,12 @@
 
 		info.regs = regs;
 		math_emulate(&info);
-	} else {
-		math_state_restore(); /* interrupts still off */
-		conditional_sti(regs);
+		return;
 	}
-#else
-	math_state_restore();
+#endif
+	math_state_restore(); /* interrupts still off */
+#ifdef CONFIG_X86_32
+	conditional_sti(regs);
 #endif
 }
 
@@ -881,18 +870,6 @@
 #endif
 
 #ifdef CONFIG_X86_32
-	if (cpu_has_fxsr) {
-		printk(KERN_INFO "Enabling fast FPU save and restore... ");
-		set_in_cr4(X86_CR4_OSFXSR);
-		printk("done.\n");
-	}
-	if (cpu_has_xmm) {
-		printk(KERN_INFO
-			"Enabling unmasked SIMD FPU exception support... ");
-		set_in_cr4(X86_CR4_OSXMMEXCPT);
-		printk("done.\n");
-	}
-
 	set_system_trap_gate(SYSCALL_VECTOR, &system_call);
 	set_bit(SYSCALL_VECTOR, used_vectors);
 #endif
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 26a863a..0c40d8b 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -104,10 +104,14 @@
 
 __setup("notsc", notsc_setup);
 
+static int no_sched_irq_time;
+
 static int __init tsc_setup(char *str)
 {
 	if (!strcmp(str, "reliable"))
 		tsc_clocksource_reliable = 1;
+	if (!strncmp(str, "noirqtime", 9))
+		no_sched_irq_time = 1;
 	return 1;
 }
 
@@ -801,6 +805,7 @@
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
 		sched_clock_stable = 0;
+		disable_sched_clock_irqtime();
 		printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
 		/* Change only the rating, when not registered */
 		if (clocksource_tsc.mult)
@@ -892,60 +897,6 @@
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
-#ifdef CONFIG_X86_64
-/*
- * calibrate_cpu is used on systems with fixed rate TSCs to determine
- * processor frequency
- */
-#define TICK_COUNT 100000000
-static unsigned long __init calibrate_cpu(void)
-{
-	int tsc_start, tsc_now;
-	int i, no_ctr_free;
-	unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
-	unsigned long flags;
-
-	for (i = 0; i < 4; i++)
-		if (avail_to_resrv_perfctr_nmi_bit(i))
-			break;
-	no_ctr_free = (i == 4);
-	if (no_ctr_free) {
-		WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
-		     "cpu_khz value may be incorrect.\n");
-		i = 3;
-		rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
-		wrmsrl(MSR_K7_EVNTSEL3, 0);
-		rdmsrl(MSR_K7_PERFCTR3, pmc3);
-	} else {
-		reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-		reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-	local_irq_save(flags);
-	/* start measuring cycles, incrementing from 0 */
-	wrmsrl(MSR_K7_PERFCTR0 + i, 0);
-	wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
-	rdtscl(tsc_start);
-	do {
-		rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
-		tsc_now = get_cycles();
-	} while ((tsc_now - tsc_start) < TICK_COUNT);
-
-	local_irq_restore(flags);
-	if (no_ctr_free) {
-		wrmsrl(MSR_K7_EVNTSEL3, 0);
-		wrmsrl(MSR_K7_PERFCTR3, pmc3);
-		wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
-	} else {
-		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-		release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-
-	return pmc_now * tsc_khz / (tsc_now - tsc_start);
-}
-#else
-static inline unsigned long calibrate_cpu(void) { return cpu_khz; }
-#endif
-
 void __init tsc_init(void)
 {
 	u64 lpj;
@@ -964,10 +915,6 @@
 		return;
 	}
 
-	if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
-			(boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
-		cpu_khz = calibrate_cpu();
-
 	printk("Detected %lu.%03lu MHz processor.\n",
 			(unsigned long)cpu_khz / 1000,
 			(unsigned long)cpu_khz % 1000);
@@ -987,6 +934,9 @@
 	/* now allow native_sched_clock() to use rdtsc */
 	tsc_disabled = 0;
 
+	if (!no_sched_irq_time)
+		enable_sched_clock_irqtime();
+
 	lpj = ((u64)tsc_khz * 1000);
 	do_div(lpj, HZ);
 	lpj_fine = lpj;
diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c
index 1132129..7b24460 100644
--- a/arch/x86/kernel/uv_irq.c
+++ b/arch/x86/kernel/uv_irq.c
@@ -28,34 +28,21 @@
 static spinlock_t		uv_irq_lock;
 static struct rb_root		uv_irq_root;
 
-static int uv_set_irq_affinity(unsigned int, const struct cpumask *);
+static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
 
-static void uv_noop(unsigned int irq)
-{
-}
+static void uv_noop(struct irq_data *data) { }
 
-static unsigned int uv_noop_ret(unsigned int irq)
-{
-	return 0;
-}
-
-static void uv_ack_apic(unsigned int irq)
+static void uv_ack_apic(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
 static struct irq_chip uv_irq_chip = {
-	.name		= "UV-CORE",
-	.startup	= uv_noop_ret,
-	.shutdown	= uv_noop,
-	.enable		= uv_noop,
-	.disable	= uv_noop,
-	.ack		= uv_noop,
-	.mask		= uv_noop,
-	.unmask		= uv_noop,
-	.eoi		= uv_ack_apic,
-	.end		= uv_noop,
-	.set_affinity	= uv_set_irq_affinity,
+	.name			= "UV-CORE",
+	.irq_mask		= uv_noop,
+	.irq_unmask		= uv_noop,
+	.irq_eoi		= uv_ack_apic,
+	.irq_set_affinity	= uv_set_irq_affinity,
 };
 
 /*
@@ -144,26 +131,22 @@
 		       unsigned long mmr_offset, int limit)
 {
 	const struct cpumask *eligible_cpu = cpumask_of(cpu);
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
-	int mmr_pnode;
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 	unsigned long mmr_value;
 	struct uv_IO_APIC_route_entry *entry;
-	int err;
+	int mmr_pnode, err;
 
 	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
 			sizeof(unsigned long));
 
-	cfg = irq_cfg(irq);
-
 	err = assign_irq_vector(irq, cfg, eligible_cpu);
 	if (err != 0)
 		return err;
 
 	if (limit == UV_AFFINITY_CPU)
-		desc->status |= IRQ_NO_BALANCING;
+		irq_set_status_flags(irq, IRQ_NO_BALANCING);
 	else
-		desc->status |= IRQ_MOVE_PCNTXT;
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
 	set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
 				      irq_name);
@@ -206,17 +189,17 @@
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
 }
 
-static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned int dest;
-	unsigned long mmr_value;
+	unsigned long mmr_value, mmr_offset;
 	struct uv_IO_APIC_route_entry *entry;
-	unsigned long mmr_offset;
 	int mmr_pnode;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
 	mmr_value = 0;
@@ -231,7 +214,7 @@
 	entry->dest		= dest;
 
 	/* Get previously stored MMR and pnode of hub sourcing interrupts */
-	if (uv_irq_2_mmr_info(irq, &mmr_offset, &mmr_pnode))
+	if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
 		return -1;
 
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index e680ea5..3371bd0 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -66,10 +66,7 @@
 }
 
 /* Replaces the default init_ISA_irqs in the generic setup */
-static void __init visws_pre_intr_init(void)
-{
-	init_VISWS_APIC_irqs();
-}
+static void __init visws_pre_intr_init(void);
 
 /* Quirk for machine specific memory setup. */
 
@@ -429,67 +426,34 @@
 /*
  * This is the SGI Cobalt (IO-)APIC:
  */
-
-static void enable_cobalt_irq(unsigned int irq)
+static void enable_cobalt_irq(struct irq_data *data)
 {
-	co_apic_set(is_co_apic(irq), irq);
+	co_apic_set(is_co_apic(data->irq), data->irq);
 }
 
-static void disable_cobalt_irq(unsigned int irq)
+static void disable_cobalt_irq(struct irq_data *data)
 {
-	int entry = is_co_apic(irq);
+	int entry = is_co_apic(data->irq);
 
 	co_apic_write(CO_APIC_LO(entry), CO_APIC_MASK);
 	co_apic_read(CO_APIC_LO(entry));
 }
 
-/*
- * "irq" really just serves to identify the device.  Here is where we
- * map this to the Cobalt APIC entry where it's physically wired.
- * This is called via request_irq -> setup_irq -> irq_desc->startup()
- */
-static unsigned int startup_cobalt_irq(unsigned int irq)
-{
-	unsigned long flags;
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	spin_lock_irqsave(&cobalt_lock, flags);
-	if ((desc->status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING)))
-		desc->status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING);
-	enable_cobalt_irq(irq);
-	spin_unlock_irqrestore(&cobalt_lock, flags);
-	return 0;
-}
-
-static void ack_cobalt_irq(unsigned int irq)
+static void ack_cobalt_irq(struct irq_data *data)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	disable_cobalt_irq(irq);
+	disable_cobalt_irq(data);
 	apic_write(APIC_EOI, APIC_EIO_ACK);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
-static void end_cobalt_irq(unsigned int irq)
-{
-	unsigned long flags;
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	spin_lock_irqsave(&cobalt_lock, flags);
-	if (!(desc->status & (IRQ_DISABLED | IRQ_INPROGRESS)))
-		enable_cobalt_irq(irq);
-	spin_unlock_irqrestore(&cobalt_lock, flags);
-}
-
 static struct irq_chip cobalt_irq_type = {
-	.name =		"Cobalt-APIC",
-	.startup =	startup_cobalt_irq,
-	.shutdown =	disable_cobalt_irq,
-	.enable =	enable_cobalt_irq,
-	.disable =	disable_cobalt_irq,
-	.ack =		ack_cobalt_irq,
-	.end =		end_cobalt_irq,
+	.name		= "Cobalt-APIC",
+	.irq_enable	= enable_cobalt_irq,
+	.irq_disable	= disable_cobalt_irq,
+	.irq_ack	= ack_cobalt_irq,
 };
 
 
@@ -503,35 +467,34 @@
  * interrupt controller type, and through a special virtual interrupt-
  * controller. Device drivers only see the virtual interrupt sources.
  */
-static unsigned int startup_piix4_master_irq(unsigned int irq)
+static unsigned int startup_piix4_master_irq(struct irq_data *data)
 {
 	legacy_pic->init(0);
-
-	return startup_cobalt_irq(irq);
+	enable_cobalt_irq(data);
 }
 
-static void end_piix4_master_irq(unsigned int irq)
+static void end_piix4_master_irq(struct irq_data *data)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	enable_cobalt_irq(irq);
+	enable_cobalt_irq(data);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
 static struct irq_chip piix4_master_irq_type = {
-	.name =		"PIIX4-master",
-	.startup =	startup_piix4_master_irq,
-	.ack =		ack_cobalt_irq,
-	.end =		end_piix4_master_irq,
+	.name		= "PIIX4-master",
+	.irq_startup	= startup_piix4_master_irq,
+	.irq_ack	= ack_cobalt_irq,
 };
 
+static void pii4_mask(struct irq_data *data) { }
 
 static struct irq_chip piix4_virtual_irq_type = {
-	.name =		"PIIX4-virtual",
+	.name		= "PIIX4-virtual",
+	.mask		= pii4_mask,
 };
 
-
 /*
  * PIIX4-8259 master/virtual functions to handle interrupt requests
  * from legacy devices: floppy, parallel, serial, rtc.
@@ -549,9 +512,8 @@
  */
 static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 {
-	int realirq;
-	struct irq_desc *desc;
 	unsigned long flags;
+	int realirq;
 
 	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
@@ -592,18 +554,10 @@
 
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 
-	desc = irq_to_desc(realirq);
-
 	/*
 	 * handle this 'virtual interrupt' as a Cobalt one now.
 	 */
-	kstat_incr_irqs_this_cpu(realirq, desc);
-
-	if (likely(desc->action != NULL))
-		handle_IRQ_event(realirq, desc->action);
-
-	if (!(desc->status & IRQ_DISABLED))
-		legacy_pic->chip->unmask(realirq);
+	generic_handle_irq(realirq);
 
 	return IRQ_HANDLED;
 
@@ -624,41 +578,35 @@
 
 static inline void set_piix4_virtual_irq_type(void)
 {
-	piix4_virtual_irq_type.shutdown = i8259A_chip.mask;
 	piix4_virtual_irq_type.enable =	i8259A_chip.unmask;
 	piix4_virtual_irq_type.disable = i8259A_chip.mask;
+	piix4_virtual_irq_type.unmask =	i8259A_chip.unmask;
 }
 
-void init_VISWS_APIC_irqs(void)
+static void __init visws_pre_intr_init(void)
 {
 	int i;
 
+	set_piix4_virtual_irq_type();
+
 	for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
+		struct irq_chip *chip = NULL;
 
-		desc->status = IRQ_DISABLED;
-		desc->action = 0;
-		desc->depth = 1;
+		if (i == 0)
+			chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_IDE0)
+			chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_IDE1)
+			>chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_8259)
+			chip = &piix4_master_irq_type;
+		else if (i < CO_IRQ_APIC0)
+			chip = &piix4_virtual_irq_type;
+		else if (IS_CO_APIC(i))
+			chip = &cobalt_irq_type;
 
-		if (i == 0) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_IDE0) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_IDE1) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_8259) {
-			desc->chip = &piix4_master_irq_type;
-		}
-		else if (i < CO_IRQ_APIC0) {
-			set_piix4_virtual_irq_type();
-			desc->chip = &piix4_virtual_irq_type;
-		}
-		else if (IS_CO_APIC(i)) {
-			desc->chip = &cobalt_irq_type;
-		}
+		if (chip)
+			set_irq_chip(i, chip);
 	}
 
 	setup_irq(CO_IRQ_8259, &master_action);
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
deleted file mode 100644
index ce9fbac..0000000
--- a/arch/x86/kernel/vmi_32.c
+++ /dev/null
@@ -1,893 +0,0 @@
-/*
- * VMI specific paravirt-ops implementation
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to zach@vmware.com
- *
- */
-
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/sched.h>
-#include <linux/gfp.h>
-#include <asm/vmi.h>
-#include <asm/io.h>
-#include <asm/fixmap.h>
-#include <asm/apicdef.h>
-#include <asm/apic.h>
-#include <asm/pgalloc.h>
-#include <asm/processor.h>
-#include <asm/timer.h>
-#include <asm/vmi_time.h>
-#include <asm/kmap_types.h>
-#include <asm/setup.h>
-
-/* Convenient for calling VMI functions indirectly in the ROM */
-typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void);
-typedef u64 __attribute__((regparm(2))) (VROMLONGFUNC)(int);
-
-#define call_vrom_func(rom,func) \
-   (((VROMFUNC *)(rom->func))())
-
-#define call_vrom_long_func(rom,func,arg) \
-   (((VROMLONGFUNC *)(rom->func)) (arg))
-
-static struct vrom_header *vmi_rom;
-static int disable_pge;
-static int disable_pse;
-static int disable_sep;
-static int disable_tsc;
-static int disable_mtrr;
-static int disable_noidle;
-static int disable_vmi_timer;
-
-/* Cached VMI operations */
-static struct {
-	void (*cpuid)(void /* non-c */);
-	void (*_set_ldt)(u32 selector);
-	void (*set_tr)(u32 selector);
-	void (*write_idt_entry)(struct desc_struct *, int, u32, u32);
-	void (*write_gdt_entry)(struct desc_struct *, int, u32, u32);
-	void (*write_ldt_entry)(struct desc_struct *, int, u32, u32);
-	void (*set_kernel_stack)(u32 selector, u32 sp0);
-	void (*allocate_page)(u32, u32, u32, u32, u32);
-	void (*release_page)(u32, u32);
-	void (*set_pte)(pte_t, pte_t *, unsigned);
-	void (*update_pte)(pte_t *, unsigned);
-	void (*set_linear_mapping)(int, void *, u32, u32);
-	void (*_flush_tlb)(int);
-	void (*set_initial_ap_state)(int, int);
-	void (*halt)(void);
-  	void (*set_lazy_mode)(int mode);
-} vmi_ops;
-
-/* Cached VMI operations */
-struct vmi_timer_ops vmi_timer_ops;
-
-/*
- * VMI patching routines.
- */
-#define MNEM_CALL 0xe8
-#define MNEM_JMP  0xe9
-#define MNEM_RET  0xc3
-
-#define IRQ_PATCH_INT_MASK 0
-#define IRQ_PATCH_DISABLE  5
-
-static inline void patch_offset(void *insnbuf,
-				unsigned long ip, unsigned long dest)
-{
-        *(unsigned long *)(insnbuf+1) = dest-ip-5;
-}
-
-static unsigned patch_internal(int call, unsigned len, void *insnbuf,
-			       unsigned long ip)
-{
-	u64 reloc;
-	struct vmi_relocation_info *const rel = (struct vmi_relocation_info *)&reloc;
-	reloc = call_vrom_long_func(vmi_rom, get_reloc,	call);
-	switch(rel->type) {
-		case VMI_RELOCATION_CALL_REL:
-			BUG_ON(len < 5);
-			*(char *)insnbuf = MNEM_CALL;
-			patch_offset(insnbuf, ip, (unsigned long)rel->eip);
-			return 5;
-
-		case VMI_RELOCATION_JUMP_REL:
-			BUG_ON(len < 5);
-			*(char *)insnbuf = MNEM_JMP;
-			patch_offset(insnbuf, ip, (unsigned long)rel->eip);
-			return 5;
-
-		case VMI_RELOCATION_NOP:
-			/* obliterate the whole thing */
-			return 0;
-
-		case VMI_RELOCATION_NONE:
-			/* leave native code in place */
-			break;
-
-		default:
-			BUG();
-	}
-	return len;
-}
-
-/*
- * Apply patch if appropriate, return length of new instruction
- * sequence.  The callee does nop padding for us.
- */
-static unsigned vmi_patch(u8 type, u16 clobbers, void *insns,
-			  unsigned long ip, unsigned len)
-{
-	switch (type) {
-		case PARAVIRT_PATCH(pv_irq_ops.irq_disable):
-			return patch_internal(VMI_CALL_DisableInterrupts, len,
-					      insns, ip);
-		case PARAVIRT_PATCH(pv_irq_ops.irq_enable):
-			return patch_internal(VMI_CALL_EnableInterrupts, len,
-					      insns, ip);
-		case PARAVIRT_PATCH(pv_irq_ops.restore_fl):
-			return patch_internal(VMI_CALL_SetInterruptMask, len,
-					      insns, ip);
-		case PARAVIRT_PATCH(pv_irq_ops.save_fl):
-			return patch_internal(VMI_CALL_GetInterruptMask, len,
-					      insns, ip);
-		case PARAVIRT_PATCH(pv_cpu_ops.iret):
-			return patch_internal(VMI_CALL_IRET, len, insns, ip);
-		case PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit):
-			return patch_internal(VMI_CALL_SYSEXIT, len, insns, ip);
-		default:
-			break;
-	}
-	return len;
-}
-
-/* CPUID has non-C semantics, and paravirt-ops API doesn't match hardware ISA */
-static void vmi_cpuid(unsigned int *ax, unsigned int *bx,
-                               unsigned int *cx, unsigned int *dx)
-{
-	int override = 0;
-	if (*ax == 1)
-		override = 1;
-        asm volatile ("call *%6"
-                      : "=a" (*ax),
-                        "=b" (*bx),
-                        "=c" (*cx),
-                        "=d" (*dx)
-                      : "0" (*ax), "2" (*cx), "r" (vmi_ops.cpuid));
-	if (override) {
-		if (disable_pse)
-			*dx &= ~X86_FEATURE_PSE;
-		if (disable_pge)
-			*dx &= ~X86_FEATURE_PGE;
-		if (disable_sep)
-			*dx &= ~X86_FEATURE_SEP;
-		if (disable_tsc)
-			*dx &= ~X86_FEATURE_TSC;
-		if (disable_mtrr)
-			*dx &= ~X86_FEATURE_MTRR;
-	}
-}
-
-static inline void vmi_maybe_load_tls(struct desc_struct *gdt, int nr, struct desc_struct *new)
-{
-	if (gdt[nr].a != new->a || gdt[nr].b != new->b)
-		write_gdt_entry(gdt, nr, new, 0);
-}
-
-static void vmi_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
-	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 0, &t->tls_array[0]);
-	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 1, &t->tls_array[1]);
-	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 2, &t->tls_array[2]);
-}
-
-static void vmi_set_ldt(const void *addr, unsigned entries)
-{
-	unsigned cpu = smp_processor_id();
-	struct desc_struct desc;
-
-	pack_descriptor(&desc, (unsigned long)addr,
-			entries * sizeof(struct desc_struct) - 1,
-			DESC_LDT, 0);
-	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, &desc, DESC_LDT);
-	vmi_ops._set_ldt(entries ? GDT_ENTRY_LDT*sizeof(struct desc_struct) : 0);
-}
-
-static void vmi_set_tr(void)
-{
-	vmi_ops.set_tr(GDT_ENTRY_TSS*sizeof(struct desc_struct));
-}
-
-static void vmi_write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
-{
-	u32 *idt_entry = (u32 *)g;
-	vmi_ops.write_idt_entry(dt, entry, idt_entry[0], idt_entry[1]);
-}
-
-static void vmi_write_gdt_entry(struct desc_struct *dt, int entry,
-				const void *desc, int type)
-{
-	u32 *gdt_entry = (u32 *)desc;
-	vmi_ops.write_gdt_entry(dt, entry, gdt_entry[0], gdt_entry[1]);
-}
-
-static void vmi_write_ldt_entry(struct desc_struct *dt, int entry,
-				const void *desc)
-{
-	u32 *ldt_entry = (u32 *)desc;
-	vmi_ops.write_ldt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
-}
-
-static void vmi_load_sp0(struct tss_struct *tss,
-				   struct thread_struct *thread)
-{
-	tss->x86_tss.sp0 = thread->sp0;
-
-	/* This can only happen when SEP is enabled, no need to test "SEP"arately */
-	if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
-		tss->x86_tss.ss1 = thread->sysenter_cs;
-		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
-	}
-	vmi_ops.set_kernel_stack(__KERNEL_DS, tss->x86_tss.sp0);
-}
-
-static void vmi_flush_tlb_user(void)
-{
-	vmi_ops._flush_tlb(VMI_FLUSH_TLB);
-}
-
-static void vmi_flush_tlb_kernel(void)
-{
-	vmi_ops._flush_tlb(VMI_FLUSH_TLB | VMI_FLUSH_GLOBAL);
-}
-
-/* Stub to do nothing at all; used for delays and unimplemented calls */
-static void vmi_nop(void)
-{
-}
-
-static void vmi_allocate_pte(struct mm_struct *mm, unsigned long pfn)
-{
-	vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
-}
-
-static void vmi_allocate_pmd(struct mm_struct *mm, unsigned long pfn)
-{
- 	/*
-	 * This call comes in very early, before mem_map is setup.
-	 * It is called only for swapper_pg_dir, which already has
-	 * data on it.
-	 */
-	vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0);
-}
-
-static void vmi_allocate_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count)
-{
-	vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count);
-}
-
-static void vmi_release_pte(unsigned long pfn)
-{
-	vmi_ops.release_page(pfn, VMI_PAGE_L1);
-}
-
-static void vmi_release_pmd(unsigned long pfn)
-{
-	vmi_ops.release_page(pfn, VMI_PAGE_L2);
-}
-
-/*
- * We use the pgd_free hook for releasing the pgd page:
- */
-static void vmi_pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	unsigned long pfn = __pa(pgd) >> PAGE_SHIFT;
-
-	vmi_ops.release_page(pfn, VMI_PAGE_L2);
-}
-
-/*
- * Helper macros for MMU update flags.  We can defer updates until a flush
- * or page invalidation only if the update is to the current address space
- * (otherwise, there is no flush).  We must check against init_mm, since
- * this could be a kernel update, which usually passes init_mm, although
- * sometimes this check can be skipped if we know the particular function
- * is only called on user mode PTEs.  We could change the kernel to pass
- * current->active_mm here, but in particular, I was unsure if changing
- * mm/highmem.c to do this would still be correct on other architectures.
- */
-#define is_current_as(mm, mustbeuser) ((mm) == current->active_mm ||    \
-                                       (!mustbeuser && (mm) == &init_mm))
-#define vmi_flags_addr(mm, addr, level, user)                           \
-        ((level) | (is_current_as(mm, user) ?                           \
-                (VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
-#define vmi_flags_addr_defer(mm, addr, level, user)                     \
-        ((level) | (is_current_as(mm, user) ?                           \
-                (VMI_PAGE_DEFER | VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
-
-static void vmi_update_pte(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	vmi_ops.update_pte(ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_update_pte_defer(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	vmi_ops.update_pte(ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_set_pte(pte_t *ptep, pte_t pte)
-{
-	/* XXX because of set_pmd_pte, this can be called on PT or PD layers */
-	vmi_ops.set_pte(pte, ptep, VMI_PAGE_PT);
-}
-
-static void vmi_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
-{
-	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_set_pmd(pmd_t *pmdp, pmd_t pmdval)
-{
-#ifdef CONFIG_X86_PAE
-	const pte_t pte = { .pte = pmdval.pmd };
-#else
-	const pte_t pte = { pmdval.pud.pgd.pgd };
-#endif
-	vmi_ops.set_pte(pte, (pte_t *)pmdp, VMI_PAGE_PD);
-}
-
-#ifdef CONFIG_X86_PAE
-
-static void vmi_set_pte_atomic(pte_t *ptep, pte_t pteval)
-{
-	/*
-	 * XXX This is called from set_pmd_pte, but at both PT
-	 * and PD layers so the VMI_PAGE_PT flag is wrong.  But
-	 * it is only called for large page mapping changes,
-	 * the Xen backend, doesn't support large pages, and the
-	 * ESX backend doesn't depend on the flag.
-	 */
-	set_64bit((unsigned long long *)ptep,pte_val(pteval));
-	vmi_ops.update_pte(ptep, VMI_PAGE_PT);
-}
-
-static void vmi_set_pud(pud_t *pudp, pud_t pudval)
-{
-	/* Um, eww */
-	const pte_t pte = { .pte = pudval.pgd.pgd };
-	vmi_ops.set_pte(pte, (pte_t *)pudp, VMI_PAGE_PDP);
-}
-
-static void vmi_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	const pte_t pte = { .pte = 0 };
-	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_pmd_clear(pmd_t *pmd)
-{
-	const pte_t pte = { .pte = 0 };
-	vmi_ops.set_pte(pte, (pte_t *)pmd, VMI_PAGE_PD);
-}
-#endif
-
-#ifdef CONFIG_SMP
-static void __devinit
-vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
-		     unsigned long start_esp)
-{
-	struct vmi_ap_state ap;
-
-	/* Default everything to zero.  This is fine for most GPRs. */
-	memset(&ap, 0, sizeof(struct vmi_ap_state));
-
-	ap.gdtr_limit = GDT_SIZE - 1;
-	ap.gdtr_base = (unsigned long) get_cpu_gdt_table(phys_apicid);
-
-	ap.idtr_limit = IDT_ENTRIES * 8 - 1;
-	ap.idtr_base = (unsigned long) idt_table;
-
-	ap.ldtr = 0;
-
-	ap.cs = __KERNEL_CS;
-	ap.eip = (unsigned long) start_eip;
-	ap.ss = __KERNEL_DS;
-	ap.esp = (unsigned long) start_esp;
-
-	ap.ds = __USER_DS;
-	ap.es = __USER_DS;
-	ap.fs = __KERNEL_PERCPU;
-	ap.gs = __KERNEL_STACK_CANARY;
-
-	ap.eflags = 0;
-
-#ifdef CONFIG_X86_PAE
-	/* efer should match BSP efer. */
-	if (cpu_has_nx) {
-		unsigned l, h;
-		rdmsr(MSR_EFER, l, h);
-		ap.efer = (unsigned long long) h << 32 | l;
-	}
-#endif
-
-	ap.cr3 = __pa(swapper_pg_dir);
-	/* Protected mode, paging, AM, WP, NE, MP. */
-	ap.cr0 = 0x80050023;
-	ap.cr4 = mmu_cr4_features;
-	vmi_ops.set_initial_ap_state((u32)&ap, phys_apicid);
-}
-#endif
-
-static void vmi_start_context_switch(struct task_struct *prev)
-{
-	paravirt_start_context_switch(prev);
-	vmi_ops.set_lazy_mode(2);
-}
-
-static void vmi_end_context_switch(struct task_struct *next)
-{
-	vmi_ops.set_lazy_mode(0);
-	paravirt_end_context_switch(next);
-}
-
-static void vmi_enter_lazy_mmu(void)
-{
-	paravirt_enter_lazy_mmu();
-	vmi_ops.set_lazy_mode(1);
-}
-
-static void vmi_leave_lazy_mmu(void)
-{
-	vmi_ops.set_lazy_mode(0);
-	paravirt_leave_lazy_mmu();
-}
-
-static inline int __init check_vmi_rom(struct vrom_header *rom)
-{
-	struct pci_header *pci;
-	struct pnp_header *pnp;
-	const char *manufacturer = "UNKNOWN";
-	const char *product = "UNKNOWN";
-	const char *license = "unspecified";
-
-	if (rom->rom_signature != 0xaa55)
-		return 0;
-	if (rom->vrom_signature != VMI_SIGNATURE)
-		return 0;
-	if (rom->api_version_maj != VMI_API_REV_MAJOR ||
-	    rom->api_version_min+1 < VMI_API_REV_MINOR+1) {
-		printk(KERN_WARNING "VMI: Found mismatched rom version %d.%d\n",
-				rom->api_version_maj,
-				rom->api_version_min);
-		return 0;
-	}
-
-	/*
-	 * Relying on the VMI_SIGNATURE field is not 100% safe, so check
-	 * the PCI header and device type to make sure this is really a
-	 * VMI device.
-	 */
-	if (!rom->pci_header_offs) {
-		printk(KERN_WARNING "VMI: ROM does not contain PCI header.\n");
-		return 0;
-	}
-
-	pci = (struct pci_header *)((char *)rom+rom->pci_header_offs);
-	if (pci->vendorID != PCI_VENDOR_ID_VMWARE ||
-	    pci->deviceID != PCI_DEVICE_ID_VMWARE_VMI) {
-		/* Allow it to run... anyways, but warn */
-		printk(KERN_WARNING "VMI: ROM from unknown manufacturer\n");
-	}
-
-	if (rom->pnp_header_offs) {
-		pnp = (struct pnp_header *)((char *)rom+rom->pnp_header_offs);
-		if (pnp->manufacturer_offset)
-			manufacturer = (const char *)rom+pnp->manufacturer_offset;
-		if (pnp->product_offset)
-			product = (const char *)rom+pnp->product_offset;
-	}
-
-	if (rom->license_offs)
-		license = (char *)rom+rom->license_offs;
-
-	printk(KERN_INFO "VMI: Found %s %s, API version %d.%d, ROM version %d.%d\n",
-		manufacturer, product,
-		rom->api_version_maj, rom->api_version_min,
-		pci->rom_version_maj, pci->rom_version_min);
-
-	/* Don't allow BSD/MIT here for now because we don't want to end up
-	   with any binary only shim layers */
-	if (strcmp(license, "GPL") && strcmp(license, "GPL v2")) {
-		printk(KERN_WARNING "VMI: Non GPL license `%s' found for ROM. Not used.\n",
-			license);
-		return 0;
-	}
-
-	return 1;
-}
-
-/*
- * Probe for the VMI option ROM
- */
-static inline int __init probe_vmi_rom(void)
-{
-	unsigned long base;
-
-	/* VMI ROM is in option ROM area, check signature */
-	for (base = 0xC0000; base < 0xE0000; base += 2048) {
-		struct vrom_header *romstart;
-		romstart = (struct vrom_header *)isa_bus_to_virt(base);
-		if (check_vmi_rom(romstart)) {
-			vmi_rom = romstart;
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * VMI setup common to all processors
- */
-void vmi_bringup(void)
-{
- 	/* We must establish the lowmem mapping for MMU ops to work */
-	if (vmi_ops.set_linear_mapping)
-		vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, MAXMEM_PFN, 0);
-}
-
-/*
- * Return a pointer to a VMI function or NULL if unimplemented
- */
-static void *vmi_get_function(int vmicall)
-{
-	u64 reloc;
-	const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
-	reloc = call_vrom_long_func(vmi_rom, get_reloc,	vmicall);
-	BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL);
-	if (rel->type == VMI_RELOCATION_CALL_REL)
-		return (void *)rel->eip;
-	else
-		return NULL;
-}
-
-/*
- * Helper macro for making the VMI paravirt-ops fill code readable.
- * For unimplemented operations, fall back to default, unless nop
- * is returned by the ROM.
- */
-#define para_fill(opname, vmicall)				\
-do {								\
-	reloc = call_vrom_long_func(vmi_rom, get_reloc,		\
-				    VMI_CALL_##vmicall);	\
-	if (rel->type == VMI_RELOCATION_CALL_REL) 		\
-		opname = (void *)rel->eip;			\
-	else if (rel->type == VMI_RELOCATION_NOP) 		\
-		opname = (void *)vmi_nop;			\
-	else if (rel->type != VMI_RELOCATION_NONE)		\
-		printk(KERN_WARNING "VMI: Unknown relocation "	\
-				    "type %d for " #vmicall"\n",\
-					rel->type);		\
-} while (0)
-
-/*
- * Helper macro for making the VMI paravirt-ops fill code readable.
- * For cached operations which do not match the VMI ROM ABI and must
- * go through a tranlation stub.  Ignore NOPs, since it is not clear
- * a NOP * VMI function corresponds to a NOP paravirt-op when the
- * functions are not in 1-1 correspondence.
- */
-#define para_wrap(opname, wrapper, cache, vmicall)		\
-do {								\
-	reloc = call_vrom_long_func(vmi_rom, get_reloc,		\
-				    VMI_CALL_##vmicall);	\
-	BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL);		\
-	if (rel->type == VMI_RELOCATION_CALL_REL) {		\
-		opname = wrapper;				\
-		vmi_ops.cache = (void *)rel->eip;		\
-	}							\
-} while (0)
-
-/*
- * Activate the VMI interface and switch into paravirtualized mode
- */
-static inline int __init activate_vmi(void)
-{
-	short kernel_cs;
-	u64 reloc;
-	const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
-
-	/*
-	 * Prevent page tables from being allocated in highmem, even if
-	 * CONFIG_HIGHPTE is enabled.
-	 */
-	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-
-	if (call_vrom_func(vmi_rom, vmi_init) != 0) {
-		printk(KERN_ERR "VMI ROM failed to initialize!");
-		return 0;
-	}
-	savesegment(cs, kernel_cs);
-
-	pv_info.paravirt_enabled = 1;
-	pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
-	pv_info.name = "vmi [deprecated]";
-
-	pv_init_ops.patch = vmi_patch;
-
-	/*
-	 * Many of these operations are ABI compatible with VMI.
-	 * This means we can fill in the paravirt-ops with direct
-	 * pointers into the VMI ROM.  If the calling convention for
-	 * these operations changes, this code needs to be updated.
-	 *
-	 * Exceptions
-	 *  CPUID paravirt-op uses pointers, not the native ISA
-	 *  halt has no VMI equivalent; all VMI halts are "safe"
-	 *  no MSR support yet - just trap and emulate.  VMI uses the
-	 *    same ABI as the native ISA, but Linux wants exceptions
-	 *    from bogus MSR read / write handled
-	 *  rdpmc is not yet used in Linux
-	 */
-
-	/* CPUID is special, so very special it gets wrapped like a present */
-	para_wrap(pv_cpu_ops.cpuid, vmi_cpuid, cpuid, CPUID);
-
-	para_fill(pv_cpu_ops.clts, CLTS);
-	para_fill(pv_cpu_ops.get_debugreg, GetDR);
-	para_fill(pv_cpu_ops.set_debugreg, SetDR);
-	para_fill(pv_cpu_ops.read_cr0, GetCR0);
-	para_fill(pv_mmu_ops.read_cr2, GetCR2);
-	para_fill(pv_mmu_ops.read_cr3, GetCR3);
-	para_fill(pv_cpu_ops.read_cr4, GetCR4);
-	para_fill(pv_cpu_ops.write_cr0, SetCR0);
-	para_fill(pv_mmu_ops.write_cr2, SetCR2);
-	para_fill(pv_mmu_ops.write_cr3, SetCR3);
-	para_fill(pv_cpu_ops.write_cr4, SetCR4);
-
-	para_fill(pv_irq_ops.save_fl.func, GetInterruptMask);
-	para_fill(pv_irq_ops.restore_fl.func, SetInterruptMask);
-	para_fill(pv_irq_ops.irq_disable.func, DisableInterrupts);
-	para_fill(pv_irq_ops.irq_enable.func, EnableInterrupts);
-
-	para_fill(pv_cpu_ops.wbinvd, WBINVD);
-	para_fill(pv_cpu_ops.read_tsc, RDTSC);
-
-	/* The following we emulate with trap and emulate for now */
-	/* paravirt_ops.read_msr = vmi_rdmsr */
-	/* paravirt_ops.write_msr = vmi_wrmsr */
-	/* paravirt_ops.rdpmc = vmi_rdpmc */
-
-	/* TR interface doesn't pass TR value, wrap */
-	para_wrap(pv_cpu_ops.load_tr_desc, vmi_set_tr, set_tr, SetTR);
-
-	/* LDT is special, too */
-	para_wrap(pv_cpu_ops.set_ldt, vmi_set_ldt, _set_ldt, SetLDT);
-
-	para_fill(pv_cpu_ops.load_gdt, SetGDT);
-	para_fill(pv_cpu_ops.load_idt, SetIDT);
-	para_fill(pv_cpu_ops.store_gdt, GetGDT);
-	para_fill(pv_cpu_ops.store_idt, GetIDT);
-	para_fill(pv_cpu_ops.store_tr, GetTR);
-	pv_cpu_ops.load_tls = vmi_load_tls;
-	para_wrap(pv_cpu_ops.write_ldt_entry, vmi_write_ldt_entry,
-		  write_ldt_entry, WriteLDTEntry);
-	para_wrap(pv_cpu_ops.write_gdt_entry, vmi_write_gdt_entry,
-		  write_gdt_entry, WriteGDTEntry);
-	para_wrap(pv_cpu_ops.write_idt_entry, vmi_write_idt_entry,
-		  write_idt_entry, WriteIDTEntry);
-	para_wrap(pv_cpu_ops.load_sp0, vmi_load_sp0, set_kernel_stack, UpdateKernelStack);
-	para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
-	para_fill(pv_cpu_ops.io_delay, IODelay);
-
-	para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
-		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
-		  set_lazy_mode, SetLazyMode);
-
-	para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
-		  set_lazy_mode, SetLazyMode);
-	para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
-		  set_lazy_mode, SetLazyMode);
-
-	/* user and kernel flush are just handled with different flags to FlushTLB */
-	para_wrap(pv_mmu_ops.flush_tlb_user, vmi_flush_tlb_user, _flush_tlb, FlushTLB);
-	para_wrap(pv_mmu_ops.flush_tlb_kernel, vmi_flush_tlb_kernel, _flush_tlb, FlushTLB);
-	para_fill(pv_mmu_ops.flush_tlb_single, InvalPage);
-
-	/*
-	 * Until a standard flag format can be agreed on, we need to
-	 * implement these as wrappers in Linux.  Get the VMI ROM
-	 * function pointers for the two backend calls.
-	 */
-#ifdef CONFIG_X86_PAE
-	vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxELong);
-	vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxELong);
-#else
-	vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxE);
-	vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxE);
-#endif
-
-	if (vmi_ops.set_pte) {
-		pv_mmu_ops.set_pte = vmi_set_pte;
-		pv_mmu_ops.set_pte_at = vmi_set_pte_at;
-		pv_mmu_ops.set_pmd = vmi_set_pmd;
-#ifdef CONFIG_X86_PAE
-		pv_mmu_ops.set_pte_atomic = vmi_set_pte_atomic;
-		pv_mmu_ops.set_pud = vmi_set_pud;
-		pv_mmu_ops.pte_clear = vmi_pte_clear;
-		pv_mmu_ops.pmd_clear = vmi_pmd_clear;
-#endif
-	}
-
-	if (vmi_ops.update_pte) {
-		pv_mmu_ops.pte_update = vmi_update_pte;
-		pv_mmu_ops.pte_update_defer = vmi_update_pte_defer;
-	}
-
-	vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage);
-	if (vmi_ops.allocate_page) {
-		pv_mmu_ops.alloc_pte = vmi_allocate_pte;
-		pv_mmu_ops.alloc_pmd = vmi_allocate_pmd;
-		pv_mmu_ops.alloc_pmd_clone = vmi_allocate_pmd_clone;
-	}
-
-	vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage);
-	if (vmi_ops.release_page) {
-		pv_mmu_ops.release_pte = vmi_release_pte;
-		pv_mmu_ops.release_pmd = vmi_release_pmd;
-		pv_mmu_ops.pgd_free = vmi_pgd_free;
-	}
-
-	/* Set linear is needed in all cases */
-	vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping);
-
-	/*
-	 * These MUST always be patched.  Don't support indirect jumps
-	 * through these operations, as the VMI interface may use either
-	 * a jump or a call to get to these operations, depending on
-	 * the backend.  They are performance critical anyway, so requiring
-	 * a patch is not a big problem.
-	 */
-	pv_cpu_ops.irq_enable_sysexit = (void *)0xfeedbab0;
-	pv_cpu_ops.iret = (void *)0xbadbab0;
-
-#ifdef CONFIG_SMP
-	para_wrap(pv_apic_ops.startup_ipi_hook, vmi_startup_ipi_hook, set_initial_ap_state, SetInitialAPState);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-       para_fill(apic->read, APICRead);
-       para_fill(apic->write, APICWrite);
-#endif
-
-	/*
-	 * Check for VMI timer functionality by probing for a cycle frequency method
-	 */
-	reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_GetCycleFrequency);
-	if (!disable_vmi_timer && rel->type != VMI_RELOCATION_NONE) {
-		vmi_timer_ops.get_cycle_frequency = (void *)rel->eip;
-		vmi_timer_ops.get_cycle_counter =
-			vmi_get_function(VMI_CALL_GetCycleCounter);
-		vmi_timer_ops.get_wallclock =
-			vmi_get_function(VMI_CALL_GetWallclockTime);
-		vmi_timer_ops.wallclock_updated =
-			vmi_get_function(VMI_CALL_WallclockUpdated);
-		vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm);
-		vmi_timer_ops.cancel_alarm =
-			 vmi_get_function(VMI_CALL_CancelAlarm);
-		x86_init.timers.timer_init = vmi_time_init;
-#ifdef CONFIG_X86_LOCAL_APIC
-		x86_init.timers.setup_percpu_clockev = vmi_time_bsp_init;
-		x86_cpuinit.setup_percpu_clockev = vmi_time_ap_init;
-#endif
-		pv_time_ops.sched_clock = vmi_sched_clock;
-		x86_platform.calibrate_tsc = vmi_tsc_khz;
-		x86_platform.get_wallclock = vmi_get_wallclock;
-		x86_platform.set_wallclock = vmi_set_wallclock;
-
-		/* We have true wallclock functions; disable CMOS clock sync */
-		no_sync_cmos_clock = 1;
-	} else {
-		disable_noidle = 1;
-		disable_vmi_timer = 1;
-	}
-
-	para_fill(pv_irq_ops.safe_halt, Halt);
-
-	/*
-	 * Alternative instruction rewriting doesn't happen soon enough
-	 * to convert VMI_IRET to a call instead of a jump; so we have
-	 * to do this before IRQs get reenabled.  Fortunately, it is
-	 * idempotent.
-	 */
-	apply_paravirt(__parainstructions, __parainstructions_end);
-
-	vmi_bringup();
-
-	return 1;
-}
-
-#undef para_fill
-
-void __init vmi_init(void)
-{
-	if (!vmi_rom)
-		probe_vmi_rom();
-	else
-		check_vmi_rom(vmi_rom);
-
-	/* In case probing for or validating the ROM failed, basil */
-	if (!vmi_rom)
-		return;
-
-	reserve_top_address(-vmi_rom->virtual_top);
-
-#ifdef CONFIG_X86_IO_APIC
-	/* This is virtual hardware; timer routing is wired correctly */
-	no_timer_check = 1;
-#endif
-}
-
-void __init vmi_activate(void)
-{
-	unsigned long flags;
-
-	if (!vmi_rom)
-		return;
-
-	local_irq_save(flags);
-	activate_vmi();
-	local_irq_restore(flags & X86_EFLAGS_IF);
-}
-
-static int __init parse_vmi(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	if (!strcmp(arg, "disable_pge")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE);
-		disable_pge = 1;
-	} else if (!strcmp(arg, "disable_pse")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PSE);
-		disable_pse = 1;
-	} else if (!strcmp(arg, "disable_sep")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_SEP);
-		disable_sep = 1;
-	} else if (!strcmp(arg, "disable_tsc")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC);
-		disable_tsc = 1;
-	} else if (!strcmp(arg, "disable_mtrr")) {
-		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_MTRR);
-		disable_mtrr = 1;
-	} else if (!strcmp(arg, "disable_timer")) {
-		disable_vmi_timer = 1;
-		disable_noidle = 1;
-	} else if (!strcmp(arg, "disable_noidle"))
-		disable_noidle = 1;
-	return 0;
-}
-
-early_param("vmi", parse_vmi);
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
deleted file mode 100644
index 5e1ff66..0000000
--- a/arch/x86/kernel/vmiclock_32.c
+++ /dev/null
@@ -1,317 +0,0 @@
-/*
- * VMI paravirtual timer support routines.
- *
- * Copyright (C) 2007, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#include <linux/smp.h>
-#include <linux/interrupt.h>
-#include <linux/cpumask.h>
-#include <linux/clocksource.h>
-#include <linux/clockchips.h>
-
-#include <asm/vmi.h>
-#include <asm/vmi_time.h>
-#include <asm/apicdef.h>
-#include <asm/apic.h>
-#include <asm/timer.h>
-#include <asm/i8253.h>
-#include <asm/irq_vectors.h>
-
-#define VMI_ONESHOT  (VMI_ALARM_IS_ONESHOT  | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
-#define VMI_PERIODIC (VMI_ALARM_IS_PERIODIC | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
-
-static DEFINE_PER_CPU(struct clock_event_device, local_events);
-
-static inline u32 vmi_counter(u32 flags)
-{
-	/* Given VMI_ONESHOT or VMI_PERIODIC, return the corresponding
-	 * cycle counter. */
-	return flags & VMI_ALARM_COUNTER_MASK;
-}
-
-/* paravirt_ops.get_wallclock = vmi_get_wallclock */
-unsigned long vmi_get_wallclock(void)
-{
-	unsigned long long wallclock;
-	wallclock = vmi_timer_ops.get_wallclock(); // nsec
-	(void)do_div(wallclock, 1000000000);       // sec
-
-	return wallclock;
-}
-
-/* paravirt_ops.set_wallclock = vmi_set_wallclock */
-int vmi_set_wallclock(unsigned long now)
-{
-	return 0;
-}
-
-/* paravirt_ops.sched_clock = vmi_sched_clock */
-unsigned long long vmi_sched_clock(void)
-{
-	return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE));
-}
-
-/* x86_platform.calibrate_tsc = vmi_tsc_khz */
-unsigned long vmi_tsc_khz(void)
-{
-	unsigned long long khz;
-	khz = vmi_timer_ops.get_cycle_frequency();
-	(void)do_div(khz, 1000);
-	return khz;
-}
-
-static inline unsigned int vmi_get_timer_vector(void)
-{
-	return IRQ0_VECTOR;
-}
-
-/** vmi clockchip */
-#ifdef CONFIG_X86_LOCAL_APIC
-static unsigned int startup_timer_irq(unsigned int irq)
-{
-	unsigned long val = apic_read(APIC_LVTT);
-	apic_write(APIC_LVTT, vmi_get_timer_vector());
-
-	return (val & APIC_SEND_PENDING);
-}
-
-static void mask_timer_irq(unsigned int irq)
-{
-	unsigned long val = apic_read(APIC_LVTT);
-	apic_write(APIC_LVTT, val | APIC_LVT_MASKED);
-}
-
-static void unmask_timer_irq(unsigned int irq)
-{
-	unsigned long val = apic_read(APIC_LVTT);
-	apic_write(APIC_LVTT, val & ~APIC_LVT_MASKED);
-}
-
-static void ack_timer_irq(unsigned int irq)
-{
-	ack_APIC_irq();
-}
-
-static struct irq_chip vmi_chip __read_mostly = {
-	.name 		= "VMI-LOCAL",
-	.startup 	= startup_timer_irq,
-	.mask	 	= mask_timer_irq,
-	.unmask	 	= unmask_timer_irq,
-	.ack 		= ack_timer_irq
-};
-#endif
-
-/** vmi clockevent */
-#define VMI_ALARM_WIRED_IRQ0    0x00000000
-#define VMI_ALARM_WIRED_LVTT    0x00010000
-static int vmi_wiring = VMI_ALARM_WIRED_IRQ0;
-
-static inline int vmi_get_alarm_wiring(void)
-{
-	return vmi_wiring;
-}
-
-static void vmi_timer_set_mode(enum clock_event_mode mode,
-			       struct clock_event_device *evt)
-{
-	cycle_t now, cycles_per_hz;
-	BUG_ON(!irqs_disabled());
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-	case CLOCK_EVT_MODE_RESUME:
-		break;
-	case CLOCK_EVT_MODE_PERIODIC:
-		cycles_per_hz = vmi_timer_ops.get_cycle_frequency();
-		(void)do_div(cycles_per_hz, HZ);
-		now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_PERIODIC));
-		vmi_timer_ops.set_alarm(VMI_PERIODIC, now, cycles_per_hz);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		switch (evt->mode) {
-		case CLOCK_EVT_MODE_ONESHOT:
-			vmi_timer_ops.cancel_alarm(VMI_ONESHOT);
-			break;
-		case CLOCK_EVT_MODE_PERIODIC:
-			vmi_timer_ops.cancel_alarm(VMI_PERIODIC);
-			break;
-		default:
-			break;
-		}
-		break;
-	default:
-		break;
-	}
-}
-
-static int vmi_timer_next_event(unsigned long delta,
-				struct clock_event_device *evt)
-{
-	/* Unfortunately, set_next_event interface only passes relative
-	 * expiry, but we want absolute expiry.  It'd be better if were
-	 * were passed an absolute expiry, since a bunch of time may
-	 * have been stolen between the time the delta is computed and
-	 * when we set the alarm below. */
-	cycle_t now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_ONESHOT));
-
-	BUG_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
-	vmi_timer_ops.set_alarm(VMI_ONESHOT, now + delta, 0);
-	return 0;
-}
-
-static struct clock_event_device vmi_clockevent = {
-	.name		= "vmi-timer",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.shift		= 22,
-	.set_mode	= vmi_timer_set_mode,
-	.set_next_event = vmi_timer_next_event,
-	.rating         = 1000,
-	.irq		= 0,
-};
-
-static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
-{
-	struct clock_event_device *evt = &__get_cpu_var(local_events);
-	evt->event_handler(evt);
-	return IRQ_HANDLED;
-}
-
-static struct irqaction vmi_clock_action  = {
-	.name 		= "vmi-timer",
-	.handler 	= vmi_timer_interrupt,
-	.flags 		= IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER,
-};
-
-static void __devinit vmi_time_init_clockevent(void)
-{
-	cycle_t cycles_per_msec;
-	struct clock_event_device *evt;
-
-	int cpu = smp_processor_id();
-	evt = &__get_cpu_var(local_events);
-
-	/* Use cycles_per_msec since div_sc params are 32-bits. */
-	cycles_per_msec = vmi_timer_ops.get_cycle_frequency();
-	(void)do_div(cycles_per_msec, 1000);
-
-	memcpy(evt, &vmi_clockevent, sizeof(*evt));
-	/* Must pick .shift such that .mult fits in 32-bits.  Choosing
-	 * .shift to be 22 allows 2^(32-22) cycles per nano-seconds
-	 * before overflow. */
-	evt->mult = div_sc(cycles_per_msec, NSEC_PER_MSEC, evt->shift);
-	/* Upper bound is clockevent's use of ulong for cycle deltas. */
-	evt->max_delta_ns = clockevent_delta2ns(ULONG_MAX, evt);
-	evt->min_delta_ns = clockevent_delta2ns(1, evt);
-	evt->cpumask = cpumask_of(cpu);
-
-	printk(KERN_WARNING "vmi: registering clock event %s. mult=%u shift=%u\n",
-	       evt->name, evt->mult, evt->shift);
-	clockevents_register_device(evt);
-}
-
-void __init vmi_time_init(void)
-{
-	unsigned int cpu;
-	/* Disable PIT: BIOSes start PIT CH0 with 18.2hz peridic. */
-	outb_pit(0x3a, PIT_MODE); /* binary, mode 5, LSB/MSB, ch 0 */
-
-	vmi_time_init_clockevent();
-	setup_irq(0, &vmi_clock_action);
-	for_each_possible_cpu(cpu)
-		per_cpu(vector_irq, cpu)[vmi_get_timer_vector()] = 0;
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-void __devinit vmi_time_bsp_init(void)
-{
-	/*
-	 * On APIC systems, we want local timers to fire on each cpu.  We do
-	 * this by programming LVTT to deliver timer events to the IRQ handler
-	 * for IRQ-0, since we can't re-use the APIC local timer handler
-	 * without interfering with that code.
-	 */
-	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
-	local_irq_disable();
-#ifdef CONFIG_SMP
-	/*
-	 * XXX handle_percpu_irq only defined for SMP; we need to switch over
-	 * to using it, since this is a local interrupt, which each CPU must
-	 * handle individually without locking out or dropping simultaneous
-	 * local timers on other CPUs.  We also don't want to trigger the
-	 * quirk workaround code for interrupts which gets invoked from
-	 * handle_percpu_irq via eoi, so we use our own IRQ chip.
-	 */
-	set_irq_chip_and_handler_name(0, &vmi_chip, handle_percpu_irq, "lvtt");
-#else
-	set_irq_chip_and_handler_name(0, &vmi_chip, handle_edge_irq, "lvtt");
-#endif
-	vmi_wiring = VMI_ALARM_WIRED_LVTT;
-	apic_write(APIC_LVTT, vmi_get_timer_vector());
-	local_irq_enable();
-	clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
-}
-
-void __devinit vmi_time_ap_init(void)
-{
-	vmi_time_init_clockevent();
-	apic_write(APIC_LVTT, vmi_get_timer_vector());
-}
-#endif
-
-/** vmi clocksource */
-static struct clocksource clocksource_vmi;
-
-static cycle_t read_real_cycles(struct clocksource *cs)
-{
-	cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
-	return max(ret, clocksource_vmi.cycle_last);
-}
-
-static struct clocksource clocksource_vmi = {
-	.name			= "vmi-timer",
-	.rating			= 450,
-	.read			= read_real_cycles,
-	.mask			= CLOCKSOURCE_MASK(64),
-	.mult			= 0, /* to be set */
-	.shift			= 22,
-	.flags			= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-static int __init init_vmi_clocksource(void)
-{
-	cycle_t cycles_per_msec;
-
-	if (!vmi_timer_ops.get_cycle_frequency)
-		return 0;
-	/* Use khz2mult rather than hz2mult since hz arg is only 32-bits. */
-	cycles_per_msec = vmi_timer_ops.get_cycle_frequency();
-	(void)do_div(cycles_per_msec, 1000);
-
-	/* Note that clocksource.{mult, shift} converts in the opposite direction
-	 * as clockevents.  */
-	clocksource_vmi.mult = clocksource_khz2mult(cycles_per_msec,
-						    clocksource_vmi.shift);
-
-	printk(KERN_WARNING "vmi: registering clock source khz=%lld\n", cycles_per_msec);
-	return clocksource_register(&clocksource_vmi);
-
-}
-module_init(init_vmi_clocksource);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index d0bb522..e03530a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -242,6 +242,12 @@
 		__x86_cpu_dev_end = .;
 	}
 
+	/*
+	 * start address and size of operations which during runtime
+	 * can be patched with virtualization friendly instructions or
+	 * baremetal native ones. Think page table operations.
+	 * Details in paravirt_types.h
+	 */
 	. = ALIGN(8);
 	.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
 		__parainstructions = .;
@@ -249,6 +255,11 @@
 		__parainstructions_end = .;
 	}
 
+	/*
+	 * struct alt_inst entries. From the header (alternative.h):
+	 * "Alternative instructions for different CPU types or capabilities"
+	 * Think locking instructions on spinlocks.
+	 */
 	. = ALIGN(8);
 	.altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
 		__alt_instructions = .;
@@ -256,11 +267,28 @@
 		__alt_instructions_end = .;
 	}
 
+	/*
+	 * And here are the replacement instructions. The linker sticks
+	 * them as binary blobs. The .altinstructions has enough data to
+	 * get the address and the length of them to patch the kernel safely.
+	 */
 	.altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
 		*(.altinstr_replacement)
 	}
 
 	/*
+	 * struct iommu_table_entry entries are injected in this section.
+	 * It is an array of IOMMUs which during run time gets sorted depending
+	 * on its dependency order. After rootfs_initcall is complete
+	 * this section can be safely removed.
+	 */
+	.iommu_table : AT(ADDR(.iommu_table) - LOAD_OFFSET) {
+		__iommu_table = .;
+		*(.iommu_table)
+		__iommu_table_end = .;
+	}
+	. = ALIGN(8);
+	/*
 	 * .exit.text is discard at runtime, not link time, to deal with
 	 *  references from .altinstructions and .eh_frame
 	 */
@@ -273,7 +301,7 @@
 	}
 
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU(PAGE_SIZE)
+	PERCPU(THREAD_SIZE)
 #endif
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 77d8c0f..22b06f7 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1056,14 +1056,13 @@
 
 	vcpu->arch.apic = apic;
 
-	apic->regs_page = alloc_page(GFP_KERNEL);
+	apic->regs_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
 	if (apic->regs_page == NULL) {
 		printk(KERN_ERR "malloc apic regs error for vcpu %x\n",
 		       vcpu->vcpu_id);
 		goto nomem_free_apic;
 	}
 	apic->regs = page_address(apic->regs_page);
-	memset(apic->regs, 0, PAGE_SIZE);
 	apic->vcpu = vcpu;
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3a09c62..6c2ecf0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1991,13 +1991,14 @@
 		0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
 		0 /* Reserved, DCA */ | F(XMM4_1) |
 		F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
-		0 /* Reserved, AES */ | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX);
+		0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
+		F(F16C);
 	/* cpuid 0x80000001.ecx */
 	const u32 kvm_supported_word6_x86_features =
 		F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ |
 		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
-		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(SSE5) |
-		0 /* SKINIT */ | 0 /* WDT */;
+		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
+		0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 9d5f558..73b1e1a 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -791,22 +791,22 @@
  * simple as setting a bit.  We don't actually "ack" interrupts as such, we
  * just mask and unmask them.  I wonder if we should be cleverer?
  */
-static void disable_lguest_irq(unsigned int irq)
+static void disable_lguest_irq(struct irq_data *data)
 {
-	set_bit(irq, lguest_data.blocked_interrupts);
+	set_bit(data->irq, lguest_data.blocked_interrupts);
 }
 
-static void enable_lguest_irq(unsigned int irq)
+static void enable_lguest_irq(struct irq_data *data)
 {
-	clear_bit(irq, lguest_data.blocked_interrupts);
+	clear_bit(data->irq, lguest_data.blocked_interrupts);
 }
 
 /* This structure describes the lguest IRQ controller. */
 static struct irq_chip lguest_irq_controller = {
 	.name		= "lguest",
-	.mask		= disable_lguest_irq,
-	.mask_ack	= disable_lguest_irq,
-	.unmask		= enable_lguest_irq,
+	.irq_mask	= disable_lguest_irq,
+	.irq_mask_ack	= disable_lguest_irq,
+	.irq_unmask	= enable_lguest_irq,
 };
 
 /*
@@ -838,12 +838,12 @@
  * rather than set them in lguest_init_IRQ we are called here every time an
  * lguest device needs an interrupt.
  *
- * FIXME: irq_to_desc_alloc_node() can fail due to lack of memory, we should
+ * FIXME: irq_alloc_desc_at() can fail due to lack of memory, we should
  * pass that up!
  */
 void lguest_setup_irq(unsigned int irq)
 {
-	irq_to_desc_alloc_node(irq, 0);
+	irq_alloc_desc_at(irq, 0);
 	set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
 				      handle_level_irq, "level");
 }
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index 5415a9d..b908a59 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -22,22 +22,187 @@
 
 void *memmove(void *dest, const void *src, size_t n)
 {
-	int d0, d1, d2;
+	int d0,d1,d2,d3,d4,d5;
+	char *ret = dest;
 
-	if (dest < src) {
-		memcpy(dest, src, n);
-	} else {
-		__asm__ __volatile__(
-			"std\n\t"
-			"rep\n\t"
-			"movsb\n\t"
-			"cld"
-			: "=&c" (d0), "=&S" (d1), "=&D" (d2)
-			:"0" (n),
-			 "1" (n-1+src),
-			 "2" (n-1+dest)
-			:"memory");
-	}
-	return dest;
+	__asm__ __volatile__(
+		/* Handle more 16bytes in loop */
+		"cmp $0x10, %0\n\t"
+		"jb	1f\n\t"
+
+		/* Decide forward/backward copy mode */
+		"cmp %2, %1\n\t"
+		"jb	2f\n\t"
+
+		/*
+		 * movs instruction have many startup latency
+		 * so we handle small size by general register.
+		 */
+		"cmp  $680, %0\n\t"
+		"jb 3f\n\t"
+		/*
+		 * movs instruction is only good for aligned case.
+		 */
+		"mov %1, %3\n\t"
+		"xor %2, %3\n\t"
+		"and $0xff, %3\n\t"
+		"jz 4f\n\t"
+		"3:\n\t"
+		"sub $0x10, %0\n\t"
+
+		/*
+		 * We gobble 16byts forward in each loop.
+		 */
+		"3:\n\t"
+		"sub $0x10, %0\n\t"
+		"mov 0*4(%1), %3\n\t"
+		"mov 1*4(%1), %4\n\t"
+		"mov  %3, 0*4(%2)\n\t"
+		"mov  %4, 1*4(%2)\n\t"
+		"mov 2*4(%1), %3\n\t"
+		"mov 3*4(%1), %4\n\t"
+		"mov  %3, 2*4(%2)\n\t"
+		"mov  %4, 3*4(%2)\n\t"
+		"lea  0x10(%1), %1\n\t"
+		"lea  0x10(%2), %2\n\t"
+		"jae 3b\n\t"
+		"add $0x10, %0\n\t"
+		"jmp 1f\n\t"
+
+		/*
+		 * Handle data forward by movs.
+		 */
+		".p2align 4\n\t"
+		"4:\n\t"
+		"mov -4(%1, %0), %3\n\t"
+		"lea -4(%2, %0), %4\n\t"
+		"shr $2, %0\n\t"
+		"rep movsl\n\t"
+		"mov %3, (%4)\n\t"
+		"jmp 11f\n\t"
+		/*
+		 * Handle data backward by movs.
+		 */
+		".p2align 4\n\t"
+		"6:\n\t"
+		"mov (%1), %3\n\t"
+		"mov %2, %4\n\t"
+		"lea -4(%1, %0), %1\n\t"
+		"lea -4(%2, %0), %2\n\t"
+		"shr $2, %0\n\t"
+		"std\n\t"
+		"rep movsl\n\t"
+		"mov %3,(%4)\n\t"
+		"cld\n\t"
+		"jmp 11f\n\t"
+
+		/*
+		 * Start to prepare for backward copy.
+		 */
+		".p2align 4\n\t"
+		"2:\n\t"
+		"cmp  $680, %0\n\t"
+		"jb 5f\n\t"
+		"mov %1, %3\n\t"
+		"xor %2, %3\n\t"
+		"and $0xff, %3\n\t"
+		"jz 6b\n\t"
+
+		/*
+		 * Calculate copy position to tail.
+		 */
+		"5:\n\t"
+		"add %0, %1\n\t"
+		"add %0, %2\n\t"
+		"sub $0x10, %0\n\t"
+
+		/*
+		 * We gobble 16byts backward in each loop.
+		 */
+		"7:\n\t"
+		"sub $0x10, %0\n\t"
+
+		"mov -1*4(%1), %3\n\t"
+		"mov -2*4(%1), %4\n\t"
+		"mov  %3, -1*4(%2)\n\t"
+		"mov  %4, -2*4(%2)\n\t"
+		"mov -3*4(%1), %3\n\t"
+		"mov -4*4(%1), %4\n\t"
+		"mov  %3, -3*4(%2)\n\t"
+		"mov  %4, -4*4(%2)\n\t"
+		"lea  -0x10(%1), %1\n\t"
+		"lea  -0x10(%2), %2\n\t"
+		"jae 7b\n\t"
+		/*
+		 * Calculate copy position to head.
+		 */
+		"add $0x10, %0\n\t"
+		"sub %0, %1\n\t"
+		"sub %0, %2\n\t"
+
+		/*
+		 * Move data from 8 bytes to 15 bytes.
+		 */
+		".p2align 4\n\t"
+		"1:\n\t"
+		"cmp $8, %0\n\t"
+		"jb 8f\n\t"
+		"mov 0*4(%1), %3\n\t"
+		"mov 1*4(%1), %4\n\t"
+		"mov -2*4(%1, %0), %5\n\t"
+		"mov -1*4(%1, %0), %1\n\t"
+
+		"mov  %3, 0*4(%2)\n\t"
+		"mov  %4, 1*4(%2)\n\t"
+		"mov  %5, -2*4(%2, %0)\n\t"
+		"mov  %1, -1*4(%2, %0)\n\t"
+		"jmp 11f\n\t"
+
+		/*
+		 * Move data from 4 bytes to 7 bytes.
+		 */
+		".p2align 4\n\t"
+		"8:\n\t"
+		"cmp $4, %0\n\t"
+		"jb 9f\n\t"
+		"mov 0*4(%1), %3\n\t"
+		"mov -1*4(%1, %0), %4\n\t"
+		"mov  %3, 0*4(%2)\n\t"
+		"mov  %4, -1*4(%2, %0)\n\t"
+		"jmp 11f\n\t"
+
+		/*
+		 * Move data from 2 bytes to 3 bytes.
+		 */
+		".p2align 4\n\t"
+		"9:\n\t"
+		"cmp $2, %0\n\t"
+		"jb 10f\n\t"
+		"movw 0*2(%1), %%dx\n\t"
+		"movw -1*2(%1, %0), %%bx\n\t"
+		"movw %%dx, 0*2(%2)\n\t"
+		"movw %%bx, -1*2(%2, %0)\n\t"
+		"jmp 11f\n\t"
+
+		/*
+		 * Move data for 1 byte.
+		 */
+		".p2align 4\n\t"
+		"10:\n\t"
+		"cmp $1, %0\n\t"
+		"jb 11f\n\t"
+		"movb (%1), %%cl\n\t"
+		"movb %%cl, (%2)\n\t"
+		".p2align 4\n\t"
+		"11:"
+		: "=&c" (d0), "=&S" (d1), "=&D" (d2),
+		  "=r" (d3),"=r" (d4), "=r"(d5)
+		:"0" (n),
+		 "1" (src),
+		 "2" (dest)
+		:"memory");
+
+	return ret;
+
 }
 EXPORT_SYMBOL(memmove);
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index bcbcd1e..75ef61e 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -40,84 +40,132 @@
 ENTRY(__memcpy)
 ENTRY(memcpy)
 	CFI_STARTPROC
-
-	/*
-	 * Put the number of full 64-byte blocks into %ecx.
-	 * Tail portion is handled at the end:
-	 */
 	movq %rdi, %rax
-	movl %edx, %ecx
-	shrl   $6, %ecx
-	jz .Lhandle_tail
 
+	/*
+	 * Use 32bit CMP here to avoid long NOP padding.
+	 */
+	cmp  $0x20, %edx
+	jb .Lhandle_tail
+
+	/*
+	 * We check whether memory false dependece could occur,
+	 * then jump to corresponding copy mode.
+	 */
+	cmp  %dil, %sil
+	jl .Lcopy_backward
+	subl $0x20, %edx
+.Lcopy_forward_loop:
+	subq $0x20,	%rdx
+
+	/*
+	 * Move in blocks of 4x8 bytes:
+	 */
+	movq 0*8(%rsi),	%r8
+	movq 1*8(%rsi),	%r9
+	movq 2*8(%rsi),	%r10
+	movq 3*8(%rsi),	%r11
+	leaq 4*8(%rsi),	%rsi
+
+	movq %r8,	0*8(%rdi)
+	movq %r9,	1*8(%rdi)
+	movq %r10,	2*8(%rdi)
+	movq %r11,	3*8(%rdi)
+	leaq 4*8(%rdi),	%rdi
+	jae  .Lcopy_forward_loop
+	addq $0x20,	%rdx
+	jmp  .Lhandle_tail
+
+.Lcopy_backward:
+	/*
+	 * Calculate copy position to tail.
+	 */
+	addq %rdx,	%rsi
+	addq %rdx,	%rdi
+	subq $0x20,	%rdx
+	/*
+	 * At most 3 ALU operations in one cycle,
+	 * so append NOPS in the same 16bytes trunk.
+	 */
 	.p2align 4
-.Lloop_64:
-	/*
-	 * We decrement the loop index here - and the zero-flag is
-	 * checked at the end of the loop (instructions inbetween do
-	 * not change the zero flag):
-	 */
-	decl %ecx
+.Lcopy_backward_loop:
+	subq $0x20,	%rdx
+	movq -1*8(%rsi),	%r8
+	movq -2*8(%rsi),	%r9
+	movq -3*8(%rsi),	%r10
+	movq -4*8(%rsi),	%r11
+	leaq -4*8(%rsi),	%rsi
+	movq %r8,		-1*8(%rdi)
+	movq %r9,		-2*8(%rdi)
+	movq %r10,		-3*8(%rdi)
+	movq %r11,		-4*8(%rdi)
+	leaq -4*8(%rdi),	%rdi
+	jae  .Lcopy_backward_loop
 
 	/*
-	 * Move in blocks of 4x16 bytes:
+	 * Calculate copy position to head.
 	 */
-	movq 0*8(%rsi),		%r11
-	movq 1*8(%rsi),		%r8
-	movq %r11,		0*8(%rdi)
-	movq %r8,		1*8(%rdi)
-
-	movq 2*8(%rsi),		%r9
-	movq 3*8(%rsi),		%r10
-	movq %r9,		2*8(%rdi)
-	movq %r10,		3*8(%rdi)
-
-	movq 4*8(%rsi),		%r11
-	movq 5*8(%rsi),		%r8
-	movq %r11,		4*8(%rdi)
-	movq %r8,		5*8(%rdi)
-
-	movq 6*8(%rsi),		%r9
-	movq 7*8(%rsi),		%r10
-	movq %r9,		6*8(%rdi)
-	movq %r10,		7*8(%rdi)
-
-	leaq 64(%rsi), %rsi
-	leaq 64(%rdi), %rdi
-
-	jnz  .Lloop_64
-
+	addq $0x20,	%rdx
+	subq %rdx,	%rsi
+	subq %rdx,	%rdi
 .Lhandle_tail:
-	movl %edx, %ecx
-	andl  $63, %ecx
-	shrl   $3, %ecx
-	jz   .Lhandle_7
+	cmpq $16,	%rdx
+	jb   .Lless_16bytes
 
+	/*
+	 * Move data from 16 bytes to 31 bytes.
+	 */
+	movq 0*8(%rsi), %r8
+	movq 1*8(%rsi),	%r9
+	movq -2*8(%rsi, %rdx),	%r10
+	movq -1*8(%rsi, %rdx),	%r11
+	movq %r8,	0*8(%rdi)
+	movq %r9,	1*8(%rdi)
+	movq %r10,	-2*8(%rdi, %rdx)
+	movq %r11,	-1*8(%rdi, %rdx)
+	retq
 	.p2align 4
-.Lloop_8:
-	decl %ecx
-	movq (%rsi),		%r8
-	movq %r8,		(%rdi)
-	leaq 8(%rdi),		%rdi
-	leaq 8(%rsi),		%rsi
-	jnz  .Lloop_8
-
-.Lhandle_7:
-	movl %edx, %ecx
-	andl $7, %ecx
-	jz .Lend
-
+.Lless_16bytes:
+	cmpq $8,	%rdx
+	jb   .Lless_8bytes
+	/*
+	 * Move data from 8 bytes to 15 bytes.
+	 */
+	movq 0*8(%rsi),	%r8
+	movq -1*8(%rsi, %rdx),	%r9
+	movq %r8,	0*8(%rdi)
+	movq %r9,	-1*8(%rdi, %rdx)
+	retq
 	.p2align 4
+.Lless_8bytes:
+	cmpq $4,	%rdx
+	jb   .Lless_3bytes
+
+	/*
+	 * Move data from 4 bytes to 7 bytes.
+	 */
+	movl (%rsi), %ecx
+	movl -4(%rsi, %rdx), %r8d
+	movl %ecx, (%rdi)
+	movl %r8d, -4(%rdi, %rdx)
+	retq
+	.p2align 4
+.Lless_3bytes:
+	cmpl $0, %edx
+	je .Lend
+	/*
+	 * Move data from 1 bytes to 3 bytes.
+	 */
 .Lloop_1:
 	movb (%rsi), %r8b
 	movb %r8b, (%rdi)
 	incq %rdi
 	incq %rsi
-	decl %ecx
+	decl %edx
 	jnz .Lloop_1
 
 .Lend:
-	ret
+	retq
 	CFI_ENDPROC
 ENDPROC(memcpy)
 ENDPROC(__memcpy)
diff --git a/arch/x86/lib/memmove_64.c b/arch/x86/lib/memmove_64.c
index 0a33909..6d0f0ec 100644
--- a/arch/x86/lib/memmove_64.c
+++ b/arch/x86/lib/memmove_64.c
@@ -8,14 +8,185 @@
 #undef memmove
 void *memmove(void *dest, const void *src, size_t count)
 {
-	if (dest < src) {
-		return memcpy(dest, src, count);
-	} else {
-		char *p = dest + count;
-		const char *s = src + count;
-		while (count--)
-			*--p = *--s;
-	}
-	return dest;
+	unsigned long d0,d1,d2,d3,d4,d5,d6,d7;
+	char *ret;
+
+	__asm__ __volatile__(
+		/* Handle more 32bytes in loop */
+		"mov %2, %3\n\t"
+		"cmp $0x20, %0\n\t"
+		"jb	1f\n\t"
+
+		/* Decide forward/backward copy mode */
+		"cmp %2, %1\n\t"
+		"jb	2f\n\t"
+
+		/*
+		 * movsq instruction have many startup latency
+		 * so we handle small size by general register.
+		 */
+		"cmp  $680, %0\n\t"
+		"jb 3f\n\t"
+		/*
+		 * movsq instruction is only good for aligned case.
+		 */
+		"cmpb %%dil, %%sil\n\t"
+		"je 4f\n\t"
+		"3:\n\t"
+		"sub $0x20, %0\n\t"
+		/*
+		 * We gobble 32byts forward in each loop.
+		 */
+		"5:\n\t"
+		"sub $0x20, %0\n\t"
+		"movq 0*8(%1), %4\n\t"
+		"movq 1*8(%1), %5\n\t"
+		"movq 2*8(%1), %6\n\t"
+		"movq 3*8(%1), %7\n\t"
+		"leaq 4*8(%1), %1\n\t"
+
+		"movq %4, 0*8(%2)\n\t"
+		"movq %5, 1*8(%2)\n\t"
+		"movq %6, 2*8(%2)\n\t"
+		"movq %7, 3*8(%2)\n\t"
+		"leaq 4*8(%2), %2\n\t"
+		"jae 5b\n\t"
+		"addq $0x20, %0\n\t"
+		"jmp 1f\n\t"
+		/*
+		 * Handle data forward by movsq.
+		 */
+		".p2align 4\n\t"
+		"4:\n\t"
+		"movq %0, %8\n\t"
+		"movq -8(%1, %0), %4\n\t"
+		"lea -8(%2, %0), %5\n\t"
+		"shrq $3, %8\n\t"
+		"rep movsq\n\t"
+		"movq %4, (%5)\n\t"
+		"jmp 13f\n\t"
+		/*
+		 * Handle data backward by movsq.
+		 */
+		".p2align 4\n\t"
+		"7:\n\t"
+		"movq %0, %8\n\t"
+		"movq (%1), %4\n\t"
+		"movq %2, %5\n\t"
+		"leaq -8(%1, %0), %1\n\t"
+		"leaq -8(%2, %0), %2\n\t"
+		"shrq $3, %8\n\t"
+		"std\n\t"
+		"rep movsq\n\t"
+		"cld\n\t"
+		"movq %4, (%5)\n\t"
+		"jmp 13f\n\t"
+
+		/*
+		 * Start to prepare for backward copy.
+		 */
+		".p2align 4\n\t"
+		"2:\n\t"
+		"cmp $680, %0\n\t"
+		"jb 6f \n\t"
+		"cmp %%dil, %%sil\n\t"
+		"je 7b \n\t"
+		"6:\n\t"
+		/*
+		 * Calculate copy position to tail.
+		 */
+		"addq %0, %1\n\t"
+		"addq %0, %2\n\t"
+		"subq $0x20, %0\n\t"
+		/*
+		 * We gobble 32byts backward in each loop.
+		 */
+		"8:\n\t"
+		"subq $0x20, %0\n\t"
+		"movq -1*8(%1), %4\n\t"
+		"movq -2*8(%1), %5\n\t"
+		"movq -3*8(%1), %6\n\t"
+		"movq -4*8(%1), %7\n\t"
+		"leaq -4*8(%1), %1\n\t"
+
+		"movq %4, -1*8(%2)\n\t"
+		"movq %5, -2*8(%2)\n\t"
+		"movq %6, -3*8(%2)\n\t"
+		"movq %7, -4*8(%2)\n\t"
+		"leaq -4*8(%2), %2\n\t"
+		"jae 8b\n\t"
+		/*
+		 * Calculate copy position to head.
+		 */
+		"addq $0x20, %0\n\t"
+		"subq %0, %1\n\t"
+		"subq %0, %2\n\t"
+		"1:\n\t"
+		"cmpq $16, %0\n\t"
+		"jb 9f\n\t"
+		/*
+		 * Move data from 16 bytes to 31 bytes.
+		 */
+		"movq 0*8(%1), %4\n\t"
+		"movq 1*8(%1), %5\n\t"
+		"movq -2*8(%1, %0), %6\n\t"
+		"movq -1*8(%1, %0), %7\n\t"
+		"movq %4, 0*8(%2)\n\t"
+		"movq %5, 1*8(%2)\n\t"
+		"movq %6, -2*8(%2, %0)\n\t"
+		"movq %7, -1*8(%2, %0)\n\t"
+		"jmp 13f\n\t"
+		".p2align 4\n\t"
+		"9:\n\t"
+		"cmpq $8, %0\n\t"
+		"jb 10f\n\t"
+		/*
+		 * Move data from 8 bytes to 15 bytes.
+		 */
+		"movq 0*8(%1), %4\n\t"
+		"movq -1*8(%1, %0), %5\n\t"
+		"movq %4, 0*8(%2)\n\t"
+		"movq %5, -1*8(%2, %0)\n\t"
+		"jmp 13f\n\t"
+		"10:\n\t"
+		"cmpq $4, %0\n\t"
+		"jb 11f\n\t"
+		/*
+		 * Move data from 4 bytes to 7 bytes.
+		 */
+		"movl (%1), %4d\n\t"
+		"movl -4(%1, %0), %5d\n\t"
+		"movl %4d, (%2)\n\t"
+		"movl %5d, -4(%2, %0)\n\t"
+		"jmp 13f\n\t"
+		"11:\n\t"
+		"cmp $2, %0\n\t"
+		"jb 12f\n\t"
+		/*
+		 * Move data from 2 bytes to 3 bytes.
+		 */
+		"movw (%1), %4w\n\t"
+		"movw -2(%1, %0), %5w\n\t"
+		"movw %4w, (%2)\n\t"
+		"movw %5w, -2(%2, %0)\n\t"
+		"jmp 13f\n\t"
+		"12:\n\t"
+		"cmp $1, %0\n\t"
+		"jb 13f\n\t"
+		/*
+		 * Move data for 1 byte.
+		 */
+		"movb (%1), %4b\n\t"
+		"movb %4b, (%2)\n\t"
+		"13:\n\t"
+		: "=&d" (d0), "=&S" (d1), "=&D" (d2), "=&a" (ret) ,
+		  "=r"(d3), "=r"(d4), "=r"(d5), "=r"(d6), "=&c" (d7)
+		:"0" (count),
+		 "1" (src),
+		 "2" (dest)
+		:"memory");
+
+		return ret;
+
 }
 EXPORT_SYMBOL(memmove);
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index a4c7683..5554339 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -26,4 +26,6 @@
 obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
+obj-$(CONFIG_HAVE_MEMBLOCK)		+= memblock.o
+
 obj-$(CONFIG_MEMTEST)		+= memtest.o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 4c4508e..79b0b37 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -229,7 +229,16 @@
 
 		spin_lock_irqsave(&pgd_lock, flags);
 		list_for_each_entry(page, &pgd_list, lru) {
-			if (!vmalloc_sync_one(page_address(page), address))
+			spinlock_t *pgt_lock;
+			pmd_t *ret;
+
+			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+
+			spin_lock(pgt_lock);
+			ret = vmalloc_sync_one(page_address(page), address);
+			spin_unlock(pgt_lock);
+
+			if (!ret)
 				break;
 		}
 		spin_unlock_irqrestore(&pgd_lock, flags);
@@ -251,6 +260,8 @@
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
+	WARN_ON_ONCE(in_nmi());
+
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
@@ -326,29 +337,7 @@
 
 void vmalloc_sync_all(void)
 {
-	unsigned long address;
-
-	for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
-	     address += PGDIR_SIZE) {
-
-		const pgd_t *pgd_ref = pgd_offset_k(address);
-		unsigned long flags;
-		struct page *page;
-
-		if (pgd_none(*pgd_ref))
-			continue;
-
-		spin_lock_irqsave(&pgd_lock, flags);
-		list_for_each_entry(page, &pgd_list, lru) {
-			pgd_t *pgd;
-			pgd = (pgd_t *)page_address(page) + pgd_index(address);
-			if (pgd_none(*pgd))
-				set_pgd(pgd, *pgd_ref);
-			else
-				BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
-		}
-		spin_unlock_irqrestore(&pgd_lock, flags);
-	}
+	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
 }
 
 /*
@@ -369,6 +358,8 @@
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
+	WARN_ON_ONCE(in_nmi());
+
 	/*
 	 * Copy kernel mappings over when needed. This can also
 	 * happen within a race in page table update. In the later
@@ -894,8 +885,14 @@
 	if (pmd_large(*pmd))
 		return spurious_fault_check(error_code, (pte_t *) pmd);
 
+	/*
+	 * Note: don't use pte_present() here, since it returns true
+	 * if the _PAGE_PROTNONE bit is set.  However, this aliases the
+	 * _PAGE_GLOBAL bit, which for kernel pages give false positives
+	 * when CONFIG_DEBUG_PAGEALLOC is used.
+	 */
 	pte = pte_offset_kernel(pmd, address);
-	if (!pte_present(*pte))
+	if (!(pte_flags(*pte) & _PAGE_PRESENT))
 		return 0;
 
 	ret = spurious_fault_check(error_code, pte);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index b278535..c0e28a1 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -2,6 +2,7 @@
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
+#include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
 #include <asm/e820.h>
@@ -33,6 +34,7 @@
 					  int use_gbpages)
 {
 	unsigned long puds, pmds, ptes, tables, start;
+	phys_addr_t base;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
 	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
@@ -75,12 +77,12 @@
 #else
 	start = 0x8000;
 #endif
-	e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
+	base = memblock_find_in_range(start, max_pfn_mapped<<PAGE_SHIFT,
 					tables, PAGE_SIZE);
-	if (e820_table_start == -1UL)
+	if (base == MEMBLOCK_ERROR)
 		panic("Cannot find space for the kernel page tables");
 
-	e820_table_start >>= PAGE_SHIFT;
+	e820_table_start = base >> PAGE_SHIFT;
 	e820_table_end = e820_table_start;
 	e820_table_top = e820_table_start + (tables >> PAGE_SHIFT);
 
@@ -299,7 +301,7 @@
 	__flush_tlb_all();
 
 	if (!after_bootmem && e820_table_end > e820_table_start)
-		reserve_early(e820_table_start << PAGE_SHIFT,
+		memblock_x86_reserve_range(e820_table_start << PAGE_SHIFT,
 				 e820_table_end << PAGE_SHIFT, "PGTABLE");
 
 	if (!after_bootmem)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bca7909..5d0a671 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,6 +25,7 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
@@ -67,7 +68,7 @@
 		panic("alloc_low_page: ran out of memory");
 
 	adr = __va(pfn * PAGE_SIZE);
-	memset(adr, 0, PAGE_SIZE);
+	clear_page(adr);
 	return adr;
 }
 
@@ -422,49 +423,28 @@
 	totalhigh_pages++;
 }
 
-struct add_highpages_data {
-	unsigned long start_pfn;
-	unsigned long end_pfn;
-};
-
-static int __init add_highpages_work_fn(unsigned long start_pfn,
-					 unsigned long end_pfn, void *datax)
+void __init add_highpages_with_active_regions(int nid,
+			 unsigned long start_pfn, unsigned long end_pfn)
 {
-	int node_pfn;
-	struct page *page;
-	unsigned long final_start_pfn, final_end_pfn;
-	struct add_highpages_data *data;
+	struct range *range;
+	int nr_range;
+	int i;
 
-	data = (struct add_highpages_data *)datax;
+	nr_range = __get_free_all_memory_range(&range, nid, start_pfn, end_pfn);
 
-	final_start_pfn = max(start_pfn, data->start_pfn);
-	final_end_pfn = min(end_pfn, data->end_pfn);
-	if (final_start_pfn >= final_end_pfn)
-		return 0;
+	for (i = 0; i < nr_range; i++) {
+		struct page *page;
+		int node_pfn;
 
-	for (node_pfn = final_start_pfn; node_pfn < final_end_pfn;
-	     node_pfn++) {
-		if (!pfn_valid(node_pfn))
-			continue;
-		page = pfn_to_page(node_pfn);
-		add_one_highpage_init(page);
+		for (node_pfn = range[i].start; node_pfn < range[i].end;
+		     node_pfn++) {
+			if (!pfn_valid(node_pfn))
+				continue;
+			page = pfn_to_page(node_pfn);
+			add_one_highpage_init(page);
+		}
 	}
-
-	return 0;
-
 }
-
-void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn,
-					      unsigned long end_pfn)
-{
-	struct add_highpages_data data;
-
-	data.start_pfn = start_pfn;
-	data.end_pfn = end_pfn;
-
-	work_with_active_regions(nid, add_highpages_work_fn, &data);
-}
-
 #else
 static inline void permanent_kmaps_init(pgd_t *pgd_base)
 {
@@ -558,7 +538,7 @@
 
 static inline void save_pg_dir(void)
 {
-	memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
+	copy_page(swsusp_pg_dir, swapper_pg_dir);
 }
 #else /* !CONFIG_ACPI_SLEEP */
 static inline void save_pg_dir(void)
@@ -712,14 +692,14 @@
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	e820_register_active_regions(0, 0, highend_pfn);
+	memblock_x86_register_active_regions(0, 0, highend_pfn);
 	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	e820_register_active_regions(0, 0, max_low_pfn);
+	memblock_x86_register_active_regions(0, 0, max_low_pfn);
 	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
@@ -750,68 +730,12 @@
 	free_area_init_nodes(max_zone_pfns);
 }
 
-#ifndef CONFIG_NO_BOOTMEM
-static unsigned long __init setup_node_bootmem(int nodeid,
-				 unsigned long start_pfn,
-				 unsigned long end_pfn,
-				 unsigned long bootmap)
-{
-	unsigned long bootmap_size;
-
-	/* don't touch min_low_pfn */
-	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
-					 bootmap >> PAGE_SHIFT,
-					 start_pfn, end_pfn);
-	printk(KERN_INFO "  node %d low ram: %08lx - %08lx\n",
-		nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
-	printk(KERN_INFO "  node %d bootmap %08lx - %08lx\n",
-		 nodeid, bootmap, bootmap + bootmap_size);
-	free_bootmem_with_active_regions(nodeid, end_pfn);
-
-	return bootmap + bootmap_size;
-}
-#endif
-
 void __init setup_bootmem_allocator(void)
 {
-#ifndef CONFIG_NO_BOOTMEM
-	int nodeid;
-	unsigned long bootmap_size, bootmap;
-	/*
-	 * Initialize the boot-time allocator (with low memory only):
-	 */
-	bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
-				 PAGE_SIZE);
-	if (bootmap == -1L)
-		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
-#endif
-
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
 		 max_pfn_mapped<<PAGE_SHIFT);
 	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
 
-#ifndef CONFIG_NO_BOOTMEM
-	for_each_online_node(nodeid) {
-		 unsigned long start_pfn, end_pfn;
-
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-		start_pfn = node_start_pfn[nodeid];
-		end_pfn = node_end_pfn[nodeid];
-		if (start_pfn > max_low_pfn)
-			continue;
-		if (end_pfn > max_low_pfn)
-			end_pfn = max_low_pfn;
-#else
-		start_pfn = 0;
-		end_pfn = max_low_pfn;
-#endif
-		bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
-						 bootmap);
-	}
-#endif
-
 	after_bootmem = 1;
 }
 
@@ -1070,8 +994,3 @@
 }
 #endif
 
-int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
-				   int flags)
-{
-	return reserve_bootmem(phys, len, flags);
-}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a66746..8434620 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -21,6 +21,7 @@
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
 #include <linux/pfn.h>
@@ -52,8 +53,6 @@
 #include <asm/init.h>
 #include <linux/bootmem.h>
 
-static unsigned long dma_reserve __initdata;
-
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -98,6 +97,43 @@
 __setup("noexec32=", nonx32_setup);
 
 /*
+ * When memory was added/removed make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+void sync_global_pgds(unsigned long start, unsigned long end)
+{
+	unsigned long address;
+
+	for (address = start; address <= end; address += PGDIR_SIZE) {
+		const pgd_t *pgd_ref = pgd_offset_k(address);
+		unsigned long flags;
+		struct page *page;
+
+		if (pgd_none(*pgd_ref))
+			continue;
+
+		spin_lock_irqsave(&pgd_lock, flags);
+		list_for_each_entry(page, &pgd_list, lru) {
+			pgd_t *pgd;
+			spinlock_t *pgt_lock;
+
+			pgd = (pgd_t *)page_address(page) + pgd_index(address);
+			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+			spin_lock(pgt_lock);
+
+			if (pgd_none(*pgd))
+				set_pgd(pgd, *pgd_ref);
+			else
+				BUG_ON(pgd_page_vaddr(*pgd)
+				       != pgd_page_vaddr(*pgd_ref));
+
+			spin_unlock(pgt_lock);
+		}
+		spin_unlock_irqrestore(&pgd_lock, flags);
+	}
+}
+
+/*
  * NOTE: This function is marked __ref because it calls __init function
  * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
  */
@@ -293,7 +329,7 @@
 		panic("alloc_low_page: ran out of memory");
 
 	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
-	memset(adr, 0, PAGE_SIZE);
+	clear_page(adr);
 	*phys  = pfn * PAGE_SIZE;
 	return adr;
 }
@@ -534,11 +570,13 @@
 			     unsigned long end,
 			     unsigned long page_size_mask)
 {
-
+	bool pgd_changed = false;
 	unsigned long next, last_map_addr = end;
+	unsigned long addr;
 
 	start = (unsigned long)__va(start);
 	end = (unsigned long)__va(end);
+	addr = start;
 
 	for (; start < end; start = next) {
 		pgd_t *pgd = pgd_offset_k(start);
@@ -563,7 +601,12 @@
 		spin_lock(&init_mm.page_table_lock);
 		pgd_populate(&init_mm, pgd, __va(pud_phys));
 		spin_unlock(&init_mm.page_table_lock);
+		pgd_changed = true;
 	}
+
+	if (pgd_changed)
+		sync_global_pgds(addr, end);
+
 	__flush_tlb_all();
 
 	return last_map_addr;
@@ -573,23 +616,7 @@
 void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 				int acpi, int k8)
 {
-#ifndef CONFIG_NO_BOOTMEM
-	unsigned long bootmap_size, bootmap;
-
-	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
-				 PAGE_SIZE);
-	if (bootmap == -1L)
-		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
-	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
-	/* don't touch min_low_pfn */
-	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
-					 0, end_pfn);
-	e820_register_active_regions(0, start_pfn, end_pfn);
-	free_bootmem_with_active_regions(0, end_pfn);
-#else
-	e820_register_active_regions(0, start_pfn, end_pfn);
-#endif
+	memblock_x86_register_active_regions(0, start_pfn, end_pfn);
 }
 #endif
 
@@ -799,52 +826,6 @@
 
 #endif
 
-int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
-				   int flags)
-{
-#ifdef CONFIG_NUMA
-	int nid, next_nid;
-	int ret;
-#endif
-	unsigned long pfn = phys >> PAGE_SHIFT;
-
-	if (pfn >= max_pfn) {
-		/*
-		 * This can happen with kdump kernels when accessing
-		 * firmware tables:
-		 */
-		if (pfn < max_pfn_mapped)
-			return -EFAULT;
-
-		printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %lu\n",
-				phys, len);
-		return -EFAULT;
-	}
-
-	/* Should check here against the e820 map to avoid double free */
-#ifdef CONFIG_NUMA
-	nid = phys_to_nid(phys);
-	next_nid = phys_to_nid(phys + len - 1);
-	if (nid == next_nid)
-		ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags);
-	else
-		ret = reserve_bootmem(phys, len, flags);
-
-	if (ret != 0)
-		return ret;
-
-#else
-	reserve_bootmem(phys, len, flags);
-#endif
-
-	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
-		dma_reserve += len / PAGE_SIZE;
-		set_dma_reserve(dma_reserve);
-	}
-
-	return 0;
-}
-
 int kern_addr_valid(unsigned long addr)
 {
 	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
@@ -1003,6 +984,7 @@
 		}
 
 	}
+	sync_global_pgds((unsigned long)start_page, end);
 	return 0;
 }
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 3ba6e06..0369843 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -362,6 +362,11 @@
 	return &bm_pte[pte_index(addr)];
 }
 
+bool __init is_early_ioremap_ptep(pte_t *ptep)
+{
+	return ptep >= &bm_pte[0] && ptep < &bm_pte[PAGE_SIZE/sizeof(pte_t)];
+}
+
 static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
 
 void __init early_ioremap_init(void)
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 970ed57..804a3b6 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -11,6 +11,8 @@
 #include <linux/string.h>
 #include <linux/module.h>
 #include <linux/nodemask.h>
+#include <linux/memblock.h>
+
 #include <asm/io.h>
 #include <linux/pci_ids.h>
 #include <linux/acpi.h>
@@ -22,7 +24,7 @@
 #include <asm/numa.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 static struct bootnode __initdata nodes[8];
 static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
@@ -54,8 +56,8 @@
 static __init void early_get_boot_cpu_id(void)
 {
 	/*
-	 * need to get boot_cpu_id so can use that to create apicid_to_node
-	 * in k8_scan_nodes()
+	 * need to get the APIC ID of the BSP so can use that to
+	 * create apicid_to_node in k8_scan_nodes()
 	 */
 #ifdef CONFIG_X86_MPPARSE
 	/*
@@ -212,7 +214,7 @@
 	bits = boot_cpu_data.x86_coreid_bits;
 	cores = (1<<bits);
 	apicid_base = 0;
-	/* need to get boot_cpu_id early for system with apicid lifting */
+	/* get the APIC ID of the BSP early for systems with apicid lifting */
 	early_get_boot_cpu_id();
 	if (boot_cpu_physical_apicid > 0) {
 		pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
@@ -222,7 +224,7 @@
 	for_each_node_mask(i, node_possible_map) {
 		int j;
 
-		e820_register_active_regions(i,
+		memblock_x86_register_active_regions(i,
 				nodes[i].start >> PAGE_SHIFT,
 				nodes[i].end >> PAGE_SHIFT);
 		for (j = apicid_base; j < cores + apicid_base; j++)
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index b3b531a..d87dd6d 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -631,6 +631,8 @@
 	if (!pte)
 		return false;
 
+	WARN_ON_ONCE(in_nmi());
+
 	if (error_code & 2)
 		kmemcheck_access(regs, address, KMEMCHECK_WRITE);
 	else
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
index 63c19e2..324aa3f 100644
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ b/arch/x86/mm/kmemcheck/opcode.c
@@ -9,7 +9,7 @@
 		b == 0xf0 || b == 0xf2 || b == 0xf3
 		/* Group 2 */
 		|| b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26
-		|| b == 0x64 || b == 0x65 || b == 0x2e || b == 0x3e
+		|| b == 0x64 || b == 0x65
 		/* Group 3 */
 		|| b == 0x66
 		/* Group 4 */
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
new file mode 100644
index 0000000..aa11693
--- /dev/null
+++ b/arch/x86/mm/memblock.c
@@ -0,0 +1,348 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/range.h>
+
+/* Check for already reserved areas */
+static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align)
+{
+	struct memblock_region *r;
+	u64 addr = *addrp, last;
+	u64 size = *sizep;
+	bool changed = false;
+
+again:
+	last = addr + size;
+	for_each_memblock(reserved, r) {
+		if (last > r->base && addr < r->base) {
+			size = r->base - addr;
+			changed = true;
+			goto again;
+		}
+		if (last > (r->base + r->size) && addr < (r->base + r->size)) {
+			addr = round_up(r->base + r->size, align);
+			size = last - addr;
+			changed = true;
+			goto again;
+		}
+		if (last <= (r->base + r->size) && addr >= r->base) {
+			*sizep = 0;
+			return false;
+		}
+	}
+	if (changed) {
+		*addrp = addr;
+		*sizep = size;
+	}
+	return changed;
+}
+
+/*
+ * Find next free range after start, and size is returned in *sizep
+ */
+u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
+{
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r) {
+		u64 ei_start = r->base;
+		u64 ei_last = ei_start + r->size;
+		u64 addr;
+
+		addr = round_up(ei_start, align);
+		if (addr < start)
+			addr = round_up(start, align);
+		if (addr >= ei_last)
+			continue;
+		*sizep = ei_last - addr;
+		while (check_with_memblock_reserved_size(&addr, sizep, align))
+			;
+
+		if (*sizep)
+			return addr;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+
+static __init struct range *find_range_array(int count)
+{
+	u64 end, size, mem;
+	struct range *range;
+
+	size = sizeof(struct range) * count;
+	end = memblock.current_limit;
+
+	mem = memblock_find_in_range(0, end, size, sizeof(struct range));
+	if (mem == MEMBLOCK_ERROR)
+		panic("can not find more space for range array");
+
+	/*
+	 * This range is tempoaray, so don't reserve it, it will not be
+	 * overlapped because We will not alloccate new buffer before
+	 * We discard this one
+	 */
+	range = __va(mem);
+	memset(range, 0, size);
+
+	return range;
+}
+
+static void __init memblock_x86_subtract_reserved(struct range *range, int az)
+{
+	u64 final_start, final_end;
+	struct memblock_region *r;
+
+	/* Take out region array itself at first*/
+	memblock_free_reserved_regions();
+
+	memblock_dbg("Subtract (%ld early reservations)\n", memblock.reserved.cnt);
+
+	for_each_memblock(reserved, r) {
+		memblock_dbg("  [%010llx-%010llx]\n", (u64)r->base, (u64)r->base + r->size - 1);
+		final_start = PFN_DOWN(r->base);
+		final_end = PFN_UP(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		subtract_range(range, az, final_start, final_end);
+	}
+
+	/* Put region array back ? */
+	memblock_reserve_reserved_regions();
+}
+
+struct count_data {
+	int nr;
+};
+
+static int __init count_work_fn(unsigned long start_pfn,
+				unsigned long end_pfn, void *datax)
+{
+	struct count_data *data = datax;
+
+	data->nr++;
+
+	return 0;
+}
+
+static int __init count_early_node_map(int nodeid)
+{
+	struct count_data data;
+
+	data.nr = 0;
+	work_with_active_regions(nodeid, count_work_fn, &data);
+
+	return data.nr;
+}
+
+int __init __get_free_all_memory_range(struct range **rangep, int nodeid,
+			 unsigned long start_pfn, unsigned long end_pfn)
+{
+	int count;
+	struct range *range;
+	int nr_range;
+
+	count = (memblock.reserved.cnt + count_early_node_map(nodeid)) * 2;
+
+	range = find_range_array(count);
+	nr_range = 0;
+
+	/*
+	 * Use early_node_map[] and memblock.reserved.region to get range array
+	 * at first
+	 */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+	subtract_range(range, count, 0, start_pfn);
+	subtract_range(range, count, end_pfn, -1ULL);
+
+	memblock_x86_subtract_reserved(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	*rangep = range;
+	return nr_range;
+}
+
+int __init get_free_all_memory_range(struct range **rangep, int nodeid)
+{
+	unsigned long end_pfn = -1UL;
+
+#ifdef CONFIG_X86_32
+	end_pfn = max_low_pfn;
+#endif
+	return __get_free_all_memory_range(rangep, nodeid, 0, end_pfn);
+}
+
+static u64 __init __memblock_x86_memory_in_range(u64 addr, u64 limit, bool get_free)
+{
+	int i, count;
+	struct range *range;
+	int nr_range;
+	u64 final_start, final_end;
+	u64 free_size;
+	struct memblock_region *r;
+
+	count = (memblock.reserved.cnt + memblock.memory.cnt) * 2;
+
+	range = find_range_array(count);
+	nr_range = 0;
+
+	addr = PFN_UP(addr);
+	limit = PFN_DOWN(limit);
+
+	for_each_memblock(memory, r) {
+		final_start = PFN_UP(r->base);
+		final_end = PFN_DOWN(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		if (final_start >= limit || final_end <= addr)
+			continue;
+
+		nr_range = add_range(range, count, nr_range, final_start, final_end);
+	}
+	subtract_range(range, count, 0, addr);
+	subtract_range(range, count, limit, -1ULL);
+
+	/* Subtract memblock.reserved.region in range ? */
+	if (!get_free)
+		goto sort_and_count_them;
+	for_each_memblock(reserved, r) {
+		final_start = PFN_DOWN(r->base);
+		final_end = PFN_UP(r->base + r->size);
+		if (final_start >= final_end)
+			continue;
+		if (final_start >= limit || final_end <= addr)
+			continue;
+
+		subtract_range(range, count, final_start, final_end);
+	}
+
+sort_and_count_them:
+	nr_range = clean_sort_range(range, count);
+
+	free_size = 0;
+	for (i = 0; i < nr_range; i++)
+		free_size += range[i].end - range[i].start;
+
+	return free_size << PAGE_SHIFT;
+}
+
+u64 __init memblock_x86_free_memory_in_range(u64 addr, u64 limit)
+{
+	return __memblock_x86_memory_in_range(addr, limit, true);
+}
+
+u64 __init memblock_x86_memory_in_range(u64 addr, u64 limit)
+{
+	return __memblock_x86_memory_in_range(addr, limit, false);
+}
+
+void __init memblock_x86_reserve_range(u64 start, u64 end, char *name)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "memblock_x86_reserve_range: wrong range [%#llx, %#llx)\n", start, end))
+		return;
+
+	memblock_dbg("    memblock_x86_reserve_range: [%#010llx-%#010llx] %16s\n", start, end - 1, name);
+
+	memblock_reserve(start, end - start);
+}
+
+void __init memblock_x86_free_range(u64 start, u64 end)
+{
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "memblock_x86_free_range: wrong range [%#llx, %#llx)\n", start, end))
+		return;
+
+	memblock_dbg("       memblock_x86_free_range: [%#010llx-%#010llx]\n", start, end - 1);
+
+	memblock_free(start, end - start);
+}
+
+/*
+ * Need to call this function after memblock_x86_register_active_regions,
+ * so early_node_map[] is filled already.
+ */
+u64 __init memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align)
+{
+	u64 addr;
+	addr = find_memory_core_early(nid, size, align, start, end);
+	if (addr != MEMBLOCK_ERROR)
+		return addr;
+
+	/* Fallback, should already have start end within node range */
+	return memblock_find_in_range(start, end, size, align);
+}
+
+/*
+ * Finds an active region in the address range from start_pfn to last_pfn and
+ * returns its range in ei_startpfn and ei_endpfn for the memblock entry.
+ */
+static int __init memblock_x86_find_active_region(const struct memblock_region *ei,
+				  unsigned long start_pfn,
+				  unsigned long last_pfn,
+				  unsigned long *ei_startpfn,
+				  unsigned long *ei_endpfn)
+{
+	u64 align = PAGE_SIZE;
+
+	*ei_startpfn = round_up(ei->base, align) >> PAGE_SHIFT;
+	*ei_endpfn = round_down(ei->base + ei->size, align) >> PAGE_SHIFT;
+
+	/* Skip map entries smaller than a page */
+	if (*ei_startpfn >= *ei_endpfn)
+		return 0;
+
+	/* Skip if map is outside the node */
+	if (*ei_endpfn <= start_pfn || *ei_startpfn >= last_pfn)
+		return 0;
+
+	/* Check for overlaps */
+	if (*ei_startpfn < start_pfn)
+		*ei_startpfn = start_pfn;
+	if (*ei_endpfn > last_pfn)
+		*ei_endpfn = last_pfn;
+
+	return 1;
+}
+
+/* Walk the memblock.memory map and register active regions within a node */
+void __init memblock_x86_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long last_pfn)
+{
+	unsigned long ei_startpfn;
+	unsigned long ei_endpfn;
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r)
+		if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
+					   &ei_startpfn, &ei_endpfn))
+			add_active_range(nid, ei_startpfn, ei_endpfn);
+}
+
+/*
+ * Find the hole size (in bytes) in the memory range.
+ * @start: starting address of the memory range to scan
+ * @end: ending address of the memory range to scan
+ */
+u64 __init memblock_x86_hole_size(u64 start, u64 end)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long last_pfn = end >> PAGE_SHIFT;
+	unsigned long ei_startpfn, ei_endpfn, ram = 0;
+	struct memblock_region *r;
+
+	for_each_memblock(memory, r)
+		if (memblock_x86_find_active_region(r, start_pfn, last_pfn,
+					   &ei_startpfn, &ei_endpfn))
+			ram += ei_endpfn - ei_startpfn;
+
+	return end - start - ((u64)ram << PAGE_SHIFT);
+}
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 18d244f..92faf3a 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -6,8 +6,7 @@
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/pfn.h>
-
-#include <asm/e820.h>
+#include <linux/memblock.h>
 
 static u64 patterns[] __initdata = {
 	0,
@@ -35,7 +34,7 @@
 	       (unsigned long long) pattern,
 	       (unsigned long long) start_bad,
 	       (unsigned long long) end_bad);
-	reserve_early(start_bad, end_bad, "BAD RAM");
+	memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM");
 }
 
 static void __init memtest(u64 pattern, u64 start_phys, u64 size)
@@ -74,7 +73,7 @@
 	u64 size = 0;
 
 	while (start < end) {
-		start = find_e820_area_size(start, &size, 1);
+		start = memblock_x86_find_in_range_size(start, &size, 1);
 
 		/* done ? */
 		if (start >= end)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 809baaa..84a3e4c 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
 
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/highmem.h>
 #include <linux/initrd.h>
@@ -120,7 +121,7 @@
 
 	node_start_pfn[0] = 0;
 	node_end_pfn[0] = max_pfn;
-	e820_register_active_regions(0, 0, max_pfn);
+	memblock_x86_register_active_regions(0, 0, max_pfn);
 	memory_present(0, 0, max_pfn);
 	node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn);
 
@@ -161,14 +162,14 @@
 		NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
 	else {
 		unsigned long pgdat_phys;
-		pgdat_phys = find_e820_area(min_low_pfn<<PAGE_SHIFT,
+		pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT,
 				 max_pfn_mapped<<PAGE_SHIFT,
 				 sizeof(pg_data_t),
 				 PAGE_SIZE);
 		NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT));
 		memset(buf, 0, sizeof(buf));
 		sprintf(buf, "NODE_DATA %d",  nid);
-		reserve_early(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
+		memblock_x86_reserve_range(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf);
 	}
 	printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n",
 		nid, (unsigned long)NODE_DATA(nid));
@@ -291,15 +292,15 @@
 						 PTRS_PER_PTE);
 		node_kva_target <<= PAGE_SHIFT;
 		do {
-			node_kva_final = find_e820_area(node_kva_target,
+			node_kva_final = memblock_find_in_range(node_kva_target,
 					((u64)node_end_pfn[nid])<<PAGE_SHIFT,
 						((u64)size)<<PAGE_SHIFT,
 						LARGE_PAGE_BYTES);
 			node_kva_target -= LARGE_PAGE_BYTES;
-		} while (node_kva_final == -1ULL &&
+		} while (node_kva_final == MEMBLOCK_ERROR &&
 			 (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid]));
 
-		if (node_kva_final == -1ULL)
+		if (node_kva_final == MEMBLOCK_ERROR)
 			panic("Can not get kva ram\n");
 
 		node_remap_size[nid] = size;
@@ -318,15 +319,13 @@
 		 *  but we could have some hole in high memory, and it will only
 		 *  check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide
 		 *  to use it as free.
-		 *  So reserve_early here, hope we don't run out of that array
+		 *  So memblock_x86_reserve_range here, hope we don't run out of that array
 		 */
-		reserve_early(node_kva_final,
+		memblock_x86_reserve_range(node_kva_final,
 			      node_kva_final+(((u64)size)<<PAGE_SHIFT),
 			      "KVA RAM");
 
 		node_remap_start_pfn[nid] = node_kva_final>>PAGE_SHIFT;
-		remove_active_range(nid, node_remap_start_pfn[nid],
-					 node_remap_start_pfn[nid] + size);
 	}
 	printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n",
 			reserve_pages);
@@ -367,14 +366,14 @@
 
 	kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE);
 	do {
-		kva_start_pfn = find_e820_area(kva_target_pfn<<PAGE_SHIFT,
+		kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT,
 					max_low_pfn<<PAGE_SHIFT,
 					kva_pages<<PAGE_SHIFT,
 					PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT;
 		kva_target_pfn -= PTRS_PER_PTE;
-	} while (kva_start_pfn == -1UL && kva_target_pfn > min_low_pfn);
+	} while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn);
 
-	if (kva_start_pfn == -1UL)
+	if (kva_start_pfn == MEMBLOCK_ERROR)
 		panic("Can not get kva space\n");
 
 	printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n",
@@ -382,7 +381,7 @@
 	printk(KERN_INFO "max_pfn = %lx\n", max_pfn);
 
 	/* avoid clash with initrd */
-	reserve_early(kva_start_pfn<<PAGE_SHIFT,
+	memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT,
 		      (kva_start_pfn + kva_pages)<<PAGE_SHIFT,
 		     "KVA PG");
 #ifdef CONFIG_HIGHMEM
@@ -419,9 +418,6 @@
 	for_each_online_node(nid) {
 		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
 		NODE_DATA(nid)->node_id = nid;
-#ifndef CONFIG_NO_BOOTMEM
-		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
-#endif
 	}
 
 	setup_bootmem_allocator();
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index a7bcc23..60f4985 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -7,6 +7,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
@@ -18,7 +19,7 @@
 #include <asm/dma.h>
 #include <asm/numa.h>
 #include <asm/acpi.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
@@ -86,16 +87,16 @@
 
 	addr = 0x8000;
 	nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
-	nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT,
+	nodemap_addr = memblock_find_in_range(addr, max_pfn<<PAGE_SHIFT,
 				      nodemap_size, L1_CACHE_BYTES);
-	if (nodemap_addr == -1UL) {
+	if (nodemap_addr == MEMBLOCK_ERROR) {
 		printk(KERN_ERR
 		       "NUMA: Unable to allocate Memory to Node hash map\n");
 		nodemap_addr = nodemap_size = 0;
 		return -1;
 	}
 	memnodemap = phys_to_virt(nodemap_addr);
-	reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
+	memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
 
 	printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
 	       nodemap_addr, nodemap_addr + nodemap_size);
@@ -171,8 +172,8 @@
 	if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
 	    end > (MAX_DMA32_PFN<<PAGE_SHIFT))
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, align);
-	if (mem != -1L)
+	mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
+	if (mem != MEMBLOCK_ERROR)
 		return __va(mem);
 
 	/* extend the search scope */
@@ -181,8 +182,8 @@
 		start = MAX_DMA32_PFN<<PAGE_SHIFT;
 	else
 		start = MAX_DMA_PFN<<PAGE_SHIFT;
-	mem = find_e820_area(start, end, size, align);
-	if (mem != -1L)
+	mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
+	if (mem != MEMBLOCK_ERROR)
 		return __va(mem);
 
 	printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
@@ -198,10 +199,6 @@
 	unsigned long start_pfn, last_pfn, nodedata_phys;
 	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
-#ifndef CONFIG_NO_BOOTMEM
-	unsigned long bootmap_start, bootmap_pages, bootmap_size;
-	void *bootmap;
-#endif
 
 	if (!end)
 		return;
@@ -226,7 +223,7 @@
 	if (node_data[nodeid] == NULL)
 		return;
 	nodedata_phys = __pa(node_data[nodeid]);
-	reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
+	memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
 	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
 		nodedata_phys + pgdat_size - 1);
 	nid = phys_to_nid(nodedata_phys);
@@ -238,47 +235,6 @@
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
 
-#ifndef CONFIG_NO_BOOTMEM
-	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
-
-	/*
-	 * Find a place for the bootmem map
-	 * nodedata_phys could be on other nodes by alloc_bootmem,
-	 * so need to sure bootmap_start not to be small, otherwise
-	 * early_node_mem will get that with find_e820_area instead
-	 * of alloc_bootmem, that could clash with reserved range
-	 */
-	bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn);
-	bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE);
-	/*
-	 * SMP_CACHE_BYTES could be enough, but init_bootmem_node like
-	 * to use that to align to PAGE_SIZE
-	 */
-	bootmap = early_node_mem(nodeid, bootmap_start, end,
-				 bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
-	if (bootmap == NULL)  {
-		free_early(nodedata_phys, nodedata_phys + pgdat_size);
-		node_data[nodeid] = NULL;
-		return;
-	}
-	bootmap_start = __pa(bootmap);
-	reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT),
-			"BOOTMAP");
-
-	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
-					 bootmap_start >> PAGE_SHIFT,
-					 start_pfn, last_pfn);
-
-	printk(KERN_INFO "  bootmap [%016lx -  %016lx] pages %lx\n",
-		 bootmap_start, bootmap_start + bootmap_size - 1,
-		 bootmap_pages);
-	nid = phys_to_nid(bootmap_start);
-	if (nid != nodeid)
-		printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
-
-	free_bootmem_with_active_regions(nodeid, end);
-#endif
-
 	node_set_online(nodeid);
 }
 
@@ -416,7 +372,7 @@
 		nr_nodes = MAX_NUMNODES;
 	}
 
-	size = (max_addr - addr - e820_hole_size(addr, max_addr)) / nr_nodes;
+	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes;
 	/*
 	 * Calculate the number of big nodes that can be allocated as a result
 	 * of consolidating the remainder.
@@ -452,7 +408,7 @@
 			 * non-reserved memory is less than the per-node size.
 			 */
 			while (end - physnodes[i].start -
-				e820_hole_size(physnodes[i].start, end) < size) {
+				memblock_x86_hole_size(physnodes[i].start, end) < size) {
 				end += FAKE_NODE_MIN_SIZE;
 				if (end > physnodes[i].end) {
 					end = physnodes[i].end;
@@ -466,7 +422,7 @@
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -475,7 +431,7 @@
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    memblock_x86_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -503,7 +459,7 @@
 {
 	u64 end = start + size;
 
-	while (end - start - e820_hole_size(start, end) < size) {
+	while (end - start - memblock_x86_hole_size(start, end) < size) {
 		end += FAKE_NODE_MIN_SIZE;
 		if (end > max_addr) {
 			end = max_addr;
@@ -532,7 +488,7 @@
 	 * creates a uniform distribution of node sizes across the entire
 	 * machine (but not necessarily over physical nodes).
 	 */
-	min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) /
+	min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
 						MAX_NUMNODES;
 	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
 	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
@@ -565,7 +521,7 @@
 			 * this one must extend to the boundary.
 			 */
 			if (end < dma32_end && dma32_end - end -
-			    e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+			    memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
 				end = dma32_end;
 
 			/*
@@ -574,7 +530,7 @@
 			 * physical node.
 			 */
 			if (physnodes[i].end - end -
-			    e820_hole_size(end, physnodes[i].end) < size)
+			    memblock_x86_hole_size(end, physnodes[i].end) < size)
 				end = physnodes[i].end;
 
 			/*
@@ -638,7 +594,7 @@
 	 */
 	remove_all_active_ranges();
 	for_each_node_mask(i, node_possible_map) {
-		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+		memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
 						nodes[i].end >> PAGE_SHIFT);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 	}
@@ -691,7 +647,7 @@
 	node_set(0, node_possible_map);
 	for (i = 0; i < nr_cpu_ids; i++)
 		numa_set_node(i, 0);
-	e820_register_active_regions(0, start_pfn, last_pfn);
+	memblock_x86_register_active_regions(0, start_pfn, last_pfn);
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT);
 }
 
@@ -703,9 +659,7 @@
 	for_each_online_node(i)
 		pages += free_all_bootmem_node(NODE_DATA(i));
 
-#ifdef CONFIG_NO_BOOTMEM
 	pages += free_all_memory_core_early(MAX_NUMNODES);
-#endif
 
 	return pages;
 }
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 5c4ee42..8be8c7d 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -87,7 +87,19 @@
 #define UNSHARED_PTRS_PER_PGD				\
 	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
 
-static void pgd_ctor(pgd_t *pgd)
+
+static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+	BUILD_BUG_ON(sizeof(virt_to_page(pgd)->index) < sizeof(mm));
+	virt_to_page(pgd)->index = (pgoff_t)mm;
+}
+
+struct mm_struct *pgd_page_get_mm(struct page *page)
+{
+	return (struct mm_struct *)page->index;
+}
+
+static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 {
 	/* If the pgd points to a shared pagetable level (either the
 	   ptes in non-PAE, or shared PMD in PAE), then just copy the
@@ -98,15 +110,13 @@
 		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
 				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
 				KERNEL_PGD_PTRS);
-		paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT,
-					 __pa(swapper_pg_dir) >> PAGE_SHIFT,
-					 KERNEL_PGD_BOUNDARY,
-					 KERNEL_PGD_PTRS);
 	}
 
 	/* list required to sync kernel mapping updates */
-	if (!SHARED_KERNEL_PMD)
+	if (!SHARED_KERNEL_PMD) {
+		pgd_set_mm(pgd, mm);
 		pgd_list_add(pgd);
+	}
 }
 
 static void pgd_dtor(pgd_t *pgd)
@@ -272,7 +282,7 @@
 	 */
 	spin_lock_irqsave(&pgd_lock, flags);
 
-	pgd_ctor(pgd);
+	pgd_ctor(mm, pgd);
 	pgd_prepopulate_pmd(mm, pgd, pmds);
 
 	spin_unlock_irqrestore(&pgd_lock, flags);
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 9324f13..a17dffd 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -25,6 +25,7 @@
  */
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mmzone.h>
 #include <linux/acpi.h>
 #include <linux/nodemask.h>
@@ -264,7 +265,7 @@
 		if (node_read_chunk(chunk->nid, chunk))
 			continue;
 
-		e820_register_active_regions(chunk->nid, chunk->start_pfn,
+		memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn,
 					     min(chunk->end_pfn, max_pfn));
 	}
 	/* for out of order entries in SRAT */
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 9c0d0d3..a35cb9d 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/topology.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <asm/proto.h>
 #include <asm/numa.h>
@@ -98,15 +99,15 @@
 	unsigned long phys;
 
 	length = slit->header.length;
-	phys = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, length,
+	phys = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, length,
 		 PAGE_SIZE);
 
-	if (phys == -1L)
+	if (phys == MEMBLOCK_ERROR)
 		panic(" Can not save slit!\n");
 
 	acpi_slit = __va(phys);
 	memcpy(acpi_slit, slit, length);
-	reserve_early(phys, phys + length, "ACPI SLIT");
+	memblock_x86_reserve_range(phys, phys + length, "ACPI SLIT");
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
@@ -324,7 +325,7 @@
 			pxmram = 0;
 	}
 
-	e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
+	e820ram = max_pfn - (memblock_x86_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT);
 	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
 	if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) {
 		printk(KERN_ERR
@@ -421,7 +422,7 @@
 	}
 
 	for (i = 0; i < num_node_memblks; i++)
-		e820_register_active_regions(memblk_nodeid[i],
+		memblock_x86_register_active_regions(memblk_nodeid[i],
 				node_memblk_range[i].start >> PAGE_SHIFT,
 				node_memblk_range[i].end >> PAGE_SHIFT);
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index c03f14a..4935848 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -5,6 +5,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/cpu.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -52,6 +53,8 @@
    want false sharing in the per cpu data segment. */
 static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS];
 
+static DEFINE_PER_CPU_READ_MOSTLY(int, tlb_vector_offset);
+
 /*
  * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
@@ -173,7 +176,7 @@
 	union smp_flush_state *f;
 
 	/* Caller has disabled preemption */
-	sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
+	sender = this_cpu_read(tlb_vector_offset);
 	f = &flush_state[sender];
 
 	/*
@@ -218,6 +221,47 @@
 	flush_tlb_others_ipi(cpumask, mm, va);
 }
 
+static void __cpuinit calculate_tlb_offset(void)
+{
+	int cpu, node, nr_node_vecs;
+	/*
+	 * we are changing tlb_vector_offset for each CPU in runtime, but this
+	 * will not cause inconsistency, as the write is atomic under X86. we
+	 * might see more lock contentions in a short time, but after all CPU's
+	 * tlb_vector_offset are changed, everything should go normal
+	 *
+	 * Note: if NUM_INVALIDATE_TLB_VECTORS % nr_online_nodes !=0, we might
+	 * waste some vectors.
+	 **/
+	if (nr_online_nodes > NUM_INVALIDATE_TLB_VECTORS)
+		nr_node_vecs = 1;
+	else
+		nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes;
+
+	for_each_online_node(node) {
+		int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) *
+			nr_node_vecs;
+		int cpu_offset = 0;
+		for_each_cpu(cpu, cpumask_of_node(node)) {
+			per_cpu(tlb_vector_offset, cpu) = node_offset +
+				cpu_offset;
+			cpu_offset++;
+			cpu_offset = cpu_offset % nr_node_vecs;
+		}
+	}
+}
+
+static int tlb_cpuhp_notify(struct notifier_block *n,
+		unsigned long action, void *hcpu)
+{
+	switch (action & 0xf) {
+	case CPU_ONLINE:
+	case CPU_DEAD:
+		calculate_tlb_offset();
+	}
+	return NOTIFY_OK;
+}
+
 static int __cpuinit init_smp_flush(void)
 {
 	int i;
@@ -225,6 +269,8 @@
 	for (i = 0; i < ARRAY_SIZE(flush_state); i++)
 		raw_spin_lock_init(&flush_state[i].tlbstate_lock);
 
+	calculate_tlb_offset();
+	hotcpu_notifier(tlb_cpuhp_notify, 0);
 	return 0;
 }
 core_initcall(init_smp_flush);
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 3855096..2d49d4e 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -14,6 +14,7 @@
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 #include <asm/stacktrace.h>
+#include <linux/compat.h>
 
 static void backtrace_warning_symbol(void *data, char *msg,
 				     unsigned long symbol)
@@ -48,14 +49,12 @@
 	.walk_stack	= print_context_stack,
 };
 
-struct frame_head {
-	struct frame_head *bp;
-	unsigned long ret;
-} __attribute__((packed));
-
-static struct frame_head *dump_user_backtrace(struct frame_head *head)
+#ifdef CONFIG_COMPAT
+static struct stack_frame_ia32 *
+dump_user_backtrace_32(struct stack_frame_ia32 *head)
 {
-	struct frame_head bufhead[2];
+	struct stack_frame_ia32 bufhead[2];
+	struct stack_frame_ia32 *fp;
 
 	/* Also check accessibility of one struct frame_head beyond */
 	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
@@ -63,20 +62,66 @@
 	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
 		return NULL;
 
-	oprofile_add_trace(bufhead[0].ret);
+	fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame);
+
+	oprofile_add_trace(bufhead[0].return_address);
+
+	/* frame pointers should strictly progress back up the stack
+	* (towards higher addresses) */
+	if (head >= fp)
+		return NULL;
+
+	return fp;
+}
+
+static inline int
+x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
+{
+	struct stack_frame_ia32 *head;
+
+	/* User process is 32-bit */
+	if (!current || !test_thread_flag(TIF_IA32))
+		return 0;
+
+	head = (struct stack_frame_ia32 *) regs->bp;
+	while (depth-- && head)
+		head = dump_user_backtrace_32(head);
+
+	return 1;
+}
+
+#else
+static inline int
+x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
+{
+	return 0;
+}
+#endif /* CONFIG_COMPAT */
+
+static struct stack_frame *dump_user_backtrace(struct stack_frame *head)
+{
+	struct stack_frame bufhead[2];
+
+	/* Also check accessibility of one struct stack_frame beyond */
+	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
+		return NULL;
+	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+		return NULL;
+
+	oprofile_add_trace(bufhead[0].return_address);
 
 	/* frame pointers should strictly progress back up the stack
 	 * (towards higher addresses) */
-	if (head >= bufhead[0].bp)
+	if (head >= bufhead[0].next_frame)
 		return NULL;
 
-	return bufhead[0].bp;
+	return bufhead[0].next_frame;
 }
 
 void
 x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 {
-	struct frame_head *head = (struct frame_head *)frame_pointer(regs);
+	struct stack_frame *head = (struct stack_frame *)frame_pointer(regs);
 
 	if (!user_mode_vm(regs)) {
 		unsigned long stack = kernel_stack_pointer(regs);
@@ -86,6 +131,9 @@
 		return;
 	}
 
+	if (x86_backtrace_32(regs, depth))
+		return;
+
 	while (depth-- && head)
 		head = dump_user_backtrace(head);
 }
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index f1575c9..bd1489c 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -695,9 +695,6 @@
 	return 1;
 }
 
-/* in order to get sysfs right */
-static int using_nmi;
-
 int __init op_nmi_init(struct oprofile_operations *ops)
 {
 	__u8 vendor = boot_cpu_data.x86_vendor;
@@ -705,8 +702,6 @@
 	char *cpu_type = NULL;
 	int ret = 0;
 
-	using_nmi = 0;
-
 	if (!cpu_has_apic)
 		return -ENODEV;
 
@@ -790,13 +785,11 @@
 	if (ret)
 		return ret;
 
-	using_nmi = 1;
 	printk(KERN_INFO "oprofile: using NMI interrupt.\n");
 	return 0;
 }
 
 void op_nmi_exit(void)
 {
-	if (using_nmi)
-		exit_sysfs();
+	exit_sysfs();
 }
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index b67a6b5..42fb46f 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -64,15 +64,22 @@
  * IBS cpuid feature detection
  */
 
-#define IBS_CPUID_FEATURES      0x8000001b
+#define IBS_CPUID_FEATURES		0x8000001b
 
 /*
  * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
  * bit 0 is used to indicate the existence of IBS.
  */
-#define IBS_CAPS_AVAIL			(1LL<<0)
-#define IBS_CAPS_RDWROPCNT		(1LL<<3)
-#define IBS_CAPS_OPCNT			(1LL<<4)
+#define IBS_CAPS_AVAIL			(1U<<0)
+#define IBS_CAPS_RDWROPCNT		(1U<<3)
+#define IBS_CAPS_OPCNT			(1U<<4)
+
+/*
+ * IBS APIC setup
+ */
+#define IBSCTL				0x1cc
+#define IBSCTL_LVT_OFFSET_VALID		(1ULL<<8)
+#define IBSCTL_LVT_OFFSET_MASK		0x0F
 
 /*
  * IBS randomization macros
@@ -266,6 +273,74 @@
 		wrmsrl(MSR_AMD64_IBSOPCTL, 0);
 }
 
+static inline int eilvt_is_available(int offset)
+{
+	/* check if we may assign a vector */
+	return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
+}
+
+static inline int ibs_eilvt_valid(void)
+{
+	u64 val;
+	int offset;
+
+	rdmsrl(MSR_AMD64_IBSCTL, val);
+	if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
+		pr_err(FW_BUG "cpu %d, invalid IBS "
+		       "interrupt offset %d (MSR%08X=0x%016llx)",
+		       smp_processor_id(), offset,
+		       MSR_AMD64_IBSCTL, val);
+		return 0;
+	}
+
+	offset = val & IBSCTL_LVT_OFFSET_MASK;
+
+	if (eilvt_is_available(offset))
+		return !0;
+
+	pr_err(FW_BUG "cpu %d, IBS interrupt offset %d "
+	       "not available (MSR%08X=0x%016llx)",
+	       smp_processor_id(), offset,
+	       MSR_AMD64_IBSCTL, val);
+
+	return 0;
+}
+
+static inline int get_ibs_offset(void)
+{
+	u64 val;
+
+	rdmsrl(MSR_AMD64_IBSCTL, val);
+	if (!(val & IBSCTL_LVT_OFFSET_VALID))
+		return -EINVAL;
+
+	return val & IBSCTL_LVT_OFFSET_MASK;
+}
+
+static void setup_APIC_ibs(void)
+{
+	int offset;
+
+	offset = get_ibs_offset();
+	if (offset < 0)
+		goto failed;
+
+	if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
+		return;
+failed:
+	pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n",
+		smp_processor_id());
+}
+
+static void clear_APIC_ibs(void)
+{
+	int offset;
+
+	offset = get_ibs_offset();
+	if (offset >= 0)
+		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
+}
+
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
 
 static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
@@ -376,13 +451,13 @@
 	}
 
 	if (ibs_caps)
-		setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
+		setup_APIC_ibs();
 }
 
 static void op_amd_cpu_shutdown(void)
 {
 	if (ibs_caps)
-		setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
+		clear_APIC_ibs();
 }
 
 static int op_amd_check_ctrs(struct pt_regs * const regs,
@@ -445,16 +520,11 @@
 	op_amd_stop_ibs();
 }
 
-static int __init_ibs_nmi(void)
+static int setup_ibs_ctl(int ibs_eilvt_off)
 {
-#define IBSCTL_LVTOFFSETVAL		(1 << 8)
-#define IBSCTL				0x1cc
 	struct pci_dev *cpu_cfg;
 	int nodes;
 	u32 value = 0;
-	u8 ibs_eilvt_off;
-
-	ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
 
 	nodes = 0;
 	cpu_cfg = NULL;
@@ -466,24 +536,63 @@
 			break;
 		++nodes;
 		pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
-				       | IBSCTL_LVTOFFSETVAL);
+				       | IBSCTL_LVT_OFFSET_VALID);
 		pci_read_config_dword(cpu_cfg, IBSCTL, &value);
-		if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
+		if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
 			pci_dev_put(cpu_cfg);
 			printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
-				"IBSCTL = 0x%08x", value);
-			return 1;
+			       "IBSCTL = 0x%08x\n", value);
+			return -EINVAL;
 		}
 	} while (1);
 
 	if (!nodes) {
-		printk(KERN_DEBUG "No CPU node configured for IBS");
-		return 1;
+		printk(KERN_DEBUG "No CPU node configured for IBS\n");
+		return -ENODEV;
 	}
 
 	return 0;
 }
 
+static int force_ibs_eilvt_setup(void)
+{
+	int i;
+	int ret;
+
+	/* find the next free available EILVT entry */
+	for (i = 1; i < 4; i++) {
+		if (!eilvt_is_available(i))
+			continue;
+		ret = setup_ibs_ctl(i);
+		if (ret)
+			return ret;
+		return 0;
+	}
+
+	printk(KERN_DEBUG "No EILVT entry available\n");
+
+	return -EBUSY;
+}
+
+static int __init_ibs_nmi(void)
+{
+	int ret;
+
+	if (ibs_eilvt_valid())
+		return 0;
+
+	ret = force_ibs_eilvt_setup();
+	if (ret)
+		return ret;
+
+	if (!ibs_eilvt_valid())
+		return -EFAULT;
+
+	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+
+	return 0;
+}
+
 /* initialize the APIC for the IBS interrupts if available */
 static void init_ibs(void)
 {
diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c
index b348154..13700ec 100644
--- a/arch/x86/pci/olpc.c
+++ b/arch/x86/pci/olpc.c
@@ -304,7 +304,7 @@
 
 int __init pci_olpc_init(void)
 {
-	printk(KERN_INFO "PCI: Using configuration type OLPC\n");
+	printk(KERN_INFO "PCI: Using configuration type OLPC XO-1\n");
 	raw_pci_ops = &pci_olpc_conf;
 	is_lx = is_geode_lx();
 	return 0;
diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c
index 1304bce..7c0fedd 100644
--- a/arch/x86/xen/debugfs.c
+++ b/arch/x86/xen/debugfs.c
@@ -106,6 +106,7 @@
 	.open	= u32_array_open,
 	.release= xen_array_release,
 	.read	= u32_array_read,
+	.llseek = no_llseek,
 };
 
 struct dentry *xen_debugfs_create_u32_array(const char *name, mode_t mode,
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 7d46c84..63b83ce 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -30,6 +30,7 @@
 #include <linux/console.h>
 #include <linux/pci.h>
 #include <linux/gfp.h>
+#include <linux/memblock.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -1183,6 +1184,8 @@
 	local_irq_disable();
 	early_boot_irqs_off();
 
+	memblock_init();
+
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 42086ac..f72d18c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -45,6 +45,7 @@
 #include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <linux/gfp.h>
+#include <linux/memblock.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -55,6 +56,7 @@
 #include <asm/e820.h>
 #include <asm/linkage.h>
 #include <asm/page.h>
+#include <asm/init.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -359,7 +361,8 @@
 	unsigned int level;
 
 	pte = lookup_address(address, &level);
-	BUG_ON(pte == NULL);
+	if (pte == NULL)
+		return;		/* vaddr missing */
 
 	ptev = pte_wrprotect(*pte);
 
@@ -374,7 +377,8 @@
 	unsigned int level;
 
 	pte = lookup_address(address, &level);
-	BUG_ON(pte == NULL);
+	if (pte == NULL)
+		return;		/* vaddr missing */
 
 	ptev = pte_mkwrite(*pte);
 
@@ -1508,13 +1512,25 @@
 #endif
 }
 
-#ifdef CONFIG_X86_32
 static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 {
+	unsigned long pfn = pte_pfn(pte);
+
+#ifdef CONFIG_X86_32
 	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
 	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
 		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
 			       pte_val_ma(pte));
+#endif
+
+	/*
+	 * If the new pfn is within the range of the newly allocated
+	 * kernel pagetable, and it isn't being mapped into an
+	 * early_ioremap fixmap slot, make sure it is RO.
+	 */
+	if (!is_early_ioremap_ptep(ptep) &&
+	    pfn >= e820_table_start && pfn < e820_table_end)
+		pte = pte_wrprotect(pte);
 
 	return pte;
 }
@@ -1527,7 +1543,6 @@
 
 	xen_set_pte(ptep, pte);
 }
-#endif
 
 static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
 {
@@ -1814,7 +1829,7 @@
 	__xen_write_cr3(true, __pa(pgd));
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
 
-	reserve_early(__pa(xen_start_info->pt_base),
+	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
@@ -1852,7 +1867,7 @@
 
 	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
 
-	reserve_early(__pa(xen_start_info->pt_base),
+	memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
 		      __pa(xen_start_info->pt_base +
 			   xen_start_info->nr_pt_frames * PAGE_SIZE),
 		      "XEN PAGETABLES");
@@ -1969,14 +1984,9 @@
 	.alloc_pte = xen_alloc_pte_init,
 	.release_pte = xen_release_pte_init,
 	.alloc_pmd = xen_alloc_pmd_init,
-	.alloc_pmd_clone = paravirt_nop,
 	.release_pmd = xen_release_pmd_init,
 
-#ifdef CONFIG_X86_64
-	.set_pte = xen_set_pte,
-#else
 	.set_pte = xen_set_pte_init,
-#endif
 	.set_pte_at = xen_set_pte_at,
 	.set_pmd = xen_set_pmd_hyper,
 
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index a013ec9..2247100 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -5,6 +5,7 @@
 
 #include <asm/xen/hypervisor.h>
 #include <xen/xen.h>
+#include <asm/iommu_table.h>
 
 int xen_swiotlb __read_mostly;
 
@@ -56,3 +57,7 @@
 		dma_ops = &xen_swiotlb_dma_ops;
 	}
 }
+IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
+		  0,
+		  pci_xen_swiotlb_init,
+		  0);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 328b003..9729c90 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
+#include <linux/memblock.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
@@ -129,7 +130,7 @@
 	 *  - xen_start_info
 	 * See comment above "struct start_info" in <xen/interface/xen.h>
 	 */
-	reserve_early(__pa(xen_start_info->mfn_list),
+	memblock_x86_reserve_range(__pa(xen_start_info->mfn_list),
 		      __pa(xen_start_info->pt_base),
 			"XEN START INFO");
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index e0500646..23e061b 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -224,7 +224,7 @@
 			goto out;
 		}
 
-		flags = __raw_local_save_flags();
+		flags = arch_local_save_flags();
 		if (irq_enable) {
 			ADD_STATS(taken_slow_irqenable, 1);
 			raw_local_irq_enable();
diff --git a/arch/xtensa/include/asm/irqflags.h b/arch/xtensa/include/asm/irqflags.h
new file mode 100644
index 0000000..dae9a8b
--- /dev/null
+++ b/arch/xtensa/include/asm/irqflags.h
@@ -0,0 +1,58 @@
+/*
+ * Xtensa IRQ flags handling functions
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2005 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_IRQFLAGS_H
+#define _XTENSA_IRQFLAGS_H
+
+#include <linux/types.h>
+
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+	asm volatile("rsr %0,"__stringify(PS) : "=a" (flags));
+	return flags;
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+	asm volatile("rsil %0, "__stringify(LOCKLEVEL)
+		     : "=a" (flags) :: "memory");
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	arch_local_irq_save();
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	unsigned long flags;
+	asm volatile("rsil %0, 0" : "=a" (flags) :: "memory");
+}
+
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile("wsr %0, "__stringify(PS)" ; rsync"
+		     :: "a" (flags) : "memory");
+}
+
+static inline bool arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & 0xf) != 0;
+}
+
+static inline bool arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* _XTENSA_IRQFLAGS_H */
diff --git a/arch/xtensa/include/asm/system.h b/arch/xtensa/include/asm/system.h
index 62b1e8f..1e7e09a 100644
--- a/arch/xtensa/include/asm/system.h
+++ b/arch/xtensa/include/asm/system.h
@@ -12,41 +12,10 @@
 #define _XTENSA_SYSTEM_H
 
 #include <linux/stringify.h>
+#include <linux/irqflags.h>
 
 #include <asm/processor.h>
 
-/* interrupt control */
-
-#define local_save_flags(x)						\
-	__asm__ __volatile__ ("rsr %0,"__stringify(PS) : "=a" (x));
-#define local_irq_restore(x)	do {					\
-	__asm__ __volatile__ ("wsr %0, "__stringify(PS)" ; rsync" 	\
-	    		      :: "a" (x) : "memory"); } while(0);
-#define local_irq_save(x)	do {					\
-	__asm__ __volatile__ ("rsil %0, "__stringify(LOCKLEVEL) 	\
-	    		      : "=a" (x) :: "memory");} while(0);
-
-static inline void local_irq_disable(void)
-{
-	unsigned long flags;
-	__asm__ __volatile__ ("rsil %0, "__stringify(LOCKLEVEL)
-	    		      : "=a" (flags) :: "memory");
-}
-static inline void local_irq_enable(void)
-{
-	unsigned long flags;
-	__asm__ __volatile__ ("rsil %0, 0" : "=a" (flags) :: "memory");
-
-}
-
-static inline int irqs_disabled(void)
-{
-	unsigned long flags;
-	local_save_flags(flags);
-	return flags & 0xf;
-}
-
-
 #define smp_read_barrier_depends() do { } while(0)
 #define read_barrier_depends() do { } while(0)
 
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index c64a5d3..8750888 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -92,7 +92,7 @@
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)
diff --git a/block/Kconfig b/block/Kconfig
index 9be0b56..6c9213e 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -77,6 +77,18 @@
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_DEV_THROTTLING
+	bool "Block layer bio throttling support"
+	depends on BLK_CGROUP=y && EXPERIMENTAL
+	default n
+	---help---
+	Block layer bio throttling support. It can be used to limit
+	the IO rate to a device. IO rate policies are per cgroup and
+	one needs to mount and use blkio cgroup controller for creating
+	cgroups and specifying per device IO rate policies.
+
+	See Documentation/cgroups/blkio-controller.txt for more information.
+
 endif # BLOCK
 
 config BLOCK_COMPAT
diff --git a/block/Makefile b/block/Makefile
index 0bb499a..0fec4b3 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -3,12 +3,13 @@
 #
 
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
-			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
+			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
+obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
deleted file mode 100644
index f0faefc..0000000
--- a/block/blk-barrier.c
+++ /dev/null
@@ -1,350 +0,0 @@
-/*
- * Functions related to barrier IO handling
- */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/bio.h>
-#include <linux/blkdev.h>
-#include <linux/gfp.h>
-
-#include "blk.h"
-
-/**
- * blk_queue_ordered - does this queue support ordered writes
- * @q:        the request queue
- * @ordered:  one of QUEUE_ORDERED_*
- *
- * Description:
- *   For journalled file systems, doing ordered writes on a commit
- *   block instead of explicitly doing wait_on_buffer (which is bad
- *   for performance) can be a big win. Block drivers supporting this
- *   feature should call this function and indicate so.
- *
- **/
-int blk_queue_ordered(struct request_queue *q, unsigned ordered)
-{
-	if (ordered != QUEUE_ORDERED_NONE &&
-	    ordered != QUEUE_ORDERED_DRAIN &&
-	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
-	    ordered != QUEUE_ORDERED_DRAIN_FUA &&
-	    ordered != QUEUE_ORDERED_TAG &&
-	    ordered != QUEUE_ORDERED_TAG_FLUSH &&
-	    ordered != QUEUE_ORDERED_TAG_FUA) {
-		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
-		return -EINVAL;
-	}
-
-	q->ordered = ordered;
-	q->next_ordered = ordered;
-
-	return 0;
-}
-EXPORT_SYMBOL(blk_queue_ordered);
-
-/*
- * Cache flushing for ordered writes handling
- */
-unsigned blk_ordered_cur_seq(struct request_queue *q)
-{
-	if (!q->ordseq)
-		return 0;
-	return 1 << ffz(q->ordseq);
-}
-
-unsigned blk_ordered_req_seq(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-
-	BUG_ON(q->ordseq == 0);
-
-	if (rq == &q->pre_flush_rq)
-		return QUEUE_ORDSEQ_PREFLUSH;
-	if (rq == &q->bar_rq)
-		return QUEUE_ORDSEQ_BAR;
-	if (rq == &q->post_flush_rq)
-		return QUEUE_ORDSEQ_POSTFLUSH;
-
-	/*
-	 * !fs requests don't need to follow barrier ordering.  Always
-	 * put them at the front.  This fixes the following deadlock.
-	 *
-	 * http://thread.gmane.org/gmane.linux.kernel/537473
-	 */
-	if (rq->cmd_type != REQ_TYPE_FS)
-		return QUEUE_ORDSEQ_DRAIN;
-
-	if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
-	    (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
-		return QUEUE_ORDSEQ_DRAIN;
-	else
-		return QUEUE_ORDSEQ_DONE;
-}
-
-bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
-{
-	struct request *rq;
-
-	if (error && !q->orderr)
-		q->orderr = error;
-
-	BUG_ON(q->ordseq & seq);
-	q->ordseq |= seq;
-
-	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
-		return false;
-
-	/*
-	 * Okay, sequence complete.
-	 */
-	q->ordseq = 0;
-	rq = q->orig_bar_rq;
-	__blk_end_request_all(rq, q->orderr);
-	return true;
-}
-
-static void pre_flush_end_io(struct request *rq, int error)
-{
-	elv_completed_request(rq->q, rq);
-	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error);
-}
-
-static void bar_end_io(struct request *rq, int error)
-{
-	elv_completed_request(rq->q, rq);
-	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error);
-}
-
-static void post_flush_end_io(struct request *rq, int error)
-{
-	elv_completed_request(rq->q, rq);
-	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
-}
-
-static void queue_flush(struct request_queue *q, unsigned which)
-{
-	struct request *rq;
-	rq_end_io_fn *end_io;
-
-	if (which == QUEUE_ORDERED_DO_PREFLUSH) {
-		rq = &q->pre_flush_rq;
-		end_io = pre_flush_end_io;
-	} else {
-		rq = &q->post_flush_rq;
-		end_io = post_flush_end_io;
-	}
-
-	blk_rq_init(q, rq);
-	rq->cmd_type = REQ_TYPE_FS;
-	rq->cmd_flags = REQ_HARDBARRIER | REQ_FLUSH;
-	rq->rq_disk = q->orig_bar_rq->rq_disk;
-	rq->end_io = end_io;
-
-	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
-}
-
-static inline bool start_ordered(struct request_queue *q, struct request **rqp)
-{
-	struct request *rq = *rqp;
-	unsigned skip = 0;
-
-	q->orderr = 0;
-	q->ordered = q->next_ordered;
-	q->ordseq |= QUEUE_ORDSEQ_STARTED;
-
-	/*
-	 * For an empty barrier, there's no actual BAR request, which
-	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
-	 */
-	if (!blk_rq_sectors(rq)) {
-		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
-				QUEUE_ORDERED_DO_POSTFLUSH);
-		/*
-		 * Empty barrier on a write-through device w/ ordered
-		 * tag has no command to issue and without any command
-		 * to issue, ordering by tag can't be used.  Drain
-		 * instead.
-		 */
-		if ((q->ordered & QUEUE_ORDERED_BY_TAG) &&
-		    !(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) {
-			q->ordered &= ~QUEUE_ORDERED_BY_TAG;
-			q->ordered |= QUEUE_ORDERED_BY_DRAIN;
-		}
-	}
-
-	/* stash away the original request */
-	blk_dequeue_request(rq);
-	q->orig_bar_rq = rq;
-	rq = NULL;
-
-	/*
-	 * Queue ordered sequence.  As we stack them at the head, we
-	 * need to queue in reverse order.  Note that we rely on that
-	 * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
-	 * request gets inbetween ordered sequence.
-	 */
-	if (q->ordered & QUEUE_ORDERED_DO_POSTFLUSH) {
-		queue_flush(q, QUEUE_ORDERED_DO_POSTFLUSH);
-		rq = &q->post_flush_rq;
-	} else
-		skip |= QUEUE_ORDSEQ_POSTFLUSH;
-
-	if (q->ordered & QUEUE_ORDERED_DO_BAR) {
-		rq = &q->bar_rq;
-
-		/* initialize proxy request and queue it */
-		blk_rq_init(q, rq);
-		if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
-			rq->cmd_flags |= REQ_WRITE;
-		if (q->ordered & QUEUE_ORDERED_DO_FUA)
-			rq->cmd_flags |= REQ_FUA;
-		init_request_from_bio(rq, q->orig_bar_rq->bio);
-		rq->end_io = bar_end_io;
-
-		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
-	} else
-		skip |= QUEUE_ORDSEQ_BAR;
-
-	if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) {
-		queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH);
-		rq = &q->pre_flush_rq;
-	} else
-		skip |= QUEUE_ORDSEQ_PREFLUSH;
-
-	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
-		rq = NULL;
-	else
-		skip |= QUEUE_ORDSEQ_DRAIN;
-
-	*rqp = rq;
-
-	/*
-	 * Complete skipped sequences.  If whole sequence is complete,
-	 * return false to tell elevator that this request is gone.
-	 */
-	return !blk_ordered_complete_seq(q, skip, 0);
-}
-
-bool blk_do_ordered(struct request_queue *q, struct request **rqp)
-{
-	struct request *rq = *rqp;
-	const int is_barrier = rq->cmd_type == REQ_TYPE_FS &&
-				(rq->cmd_flags & REQ_HARDBARRIER);
-
-	if (!q->ordseq) {
-		if (!is_barrier)
-			return true;
-
-		if (q->next_ordered != QUEUE_ORDERED_NONE)
-			return start_ordered(q, rqp);
-		else {
-			/*
-			 * Queue ordering not supported.  Terminate
-			 * with prejudice.
-			 */
-			blk_dequeue_request(rq);
-			__blk_end_request_all(rq, -EOPNOTSUPP);
-			*rqp = NULL;
-			return false;
-		}
-	}
-
-	/*
-	 * Ordered sequence in progress
-	 */
-
-	/* Special requests are not subject to ordering rules. */
-	if (rq->cmd_type != REQ_TYPE_FS &&
-	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
-		return true;
-
-	if (q->ordered & QUEUE_ORDERED_BY_TAG) {
-		/* Ordered by tag.  Blocking the next barrier is enough. */
-		if (is_barrier && rq != &q->bar_rq)
-			*rqp = NULL;
-	} else {
-		/* Ordered by draining.  Wait for turn. */
-		WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
-		if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
-			*rqp = NULL;
-	}
-
-	return true;
-}
-
-static void bio_end_empty_barrier(struct bio *bio, int err)
-{
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
-	if (bio->bi_private)
-		complete(bio->bi_private);
-	bio_put(bio);
-}
-
-/**
- * blkdev_issue_flush - queue a flush
- * @bdev:	blockdev to issue flush for
- * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @error_sector:	error sector
- * @flags:	BLKDEV_IFL_* flags to control behaviour
- *
- * Description:
- *    Issue a flush for the block device in question. Caller can supply
- *    room for storing the error offset in case of a flush error, if they
- *    wish to. If WAIT flag is not passed then caller may check only what
- *    request was pushed in some internal queue for later handling.
- */
-int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
-		sector_t *error_sector, unsigned long flags)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	struct request_queue *q;
-	struct bio *bio;
-	int ret = 0;
-
-	if (bdev->bd_disk == NULL)
-		return -ENXIO;
-
-	q = bdev_get_queue(bdev);
-	if (!q)
-		return -ENXIO;
-
-	/*
-	 * some block devices may not have their queue correctly set up here
-	 * (e.g. loop device without a backing file) and so issuing a flush
-	 * here will panic. Ensure there is a request function before issuing
-	 * the barrier.
-	 */
-	if (!q->make_request_fn)
-		return -ENXIO;
-
-	bio = bio_alloc(gfp_mask, 0);
-	bio->bi_end_io = bio_end_empty_barrier;
-	bio->bi_bdev = bdev;
-	if (test_bit(BLKDEV_WAIT, &flags))
-		bio->bi_private = &wait;
-
-	bio_get(bio);
-	submit_bio(WRITE_BARRIER, bio);
-	if (test_bit(BLKDEV_WAIT, &flags)) {
-		wait_for_completion(&wait);
-		/*
-		 * The driver must store the error location in ->bi_sector, if
-		 * it supports it. For non-stacked drivers, this should be
-		 * copied from blk_rq_pos(rq).
-		 */
-		if (error_sector)
-			*error_sector = bio->bi_sector;
-	}
-
-	if (bio_flagged(bio, BIO_EOPNOTSUPP))
-		ret = -EOPNOTSUPP;
-	else if (!bio_flagged(bio, BIO_UPTODATE))
-		ret = -EIO;
-
-	bio_put(bio);
-	return ret;
-}
-EXPORT_SYMBOL(blkdev_issue_flush);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 2fef1ef..b1febd0 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -37,6 +37,12 @@
 static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
 static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
 
+/* for encoding cft->private value on file */
+#define BLKIOFILE_PRIVATE(x, val)	(((x) << 16) | (val))
+/* What policy owns the file, proportional or throttle */
+#define BLKIOFILE_POLICY(val)		(((val) >> 16) & 0xffff)
+#define BLKIOFILE_ATTR(val)		((val) & 0xffff)
+
 struct cgroup_subsys blkio_subsys = {
 	.name = "blkio",
 	.create = blkiocg_create,
@@ -59,6 +65,27 @@
 	list_add(&pn->node, &blkcg->policy_list);
 }
 
+static inline bool cftype_blkg_same_policy(struct cftype *cft,
+			struct blkio_group *blkg)
+{
+	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+
+	if (blkg->plid == plid)
+		return 1;
+
+	return 0;
+}
+
+/* Determines if policy node matches cgroup file being accessed */
+static inline bool pn_matches_cftype(struct cftype *cft,
+			struct blkio_policy_node *pn)
+{
+	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+	int fileid = BLKIOFILE_ATTR(cft->private);
+
+	return (plid == pn->plid && fileid == pn->fileid);
+}
+
 /* Must be called with blkcg->lock held */
 static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
 {
@@ -67,12 +94,13 @@
 
 /* Must be called with blkcg->lock held */
 static struct blkio_policy_node *
-blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev)
+blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev,
+		enum blkio_policy_id plid, int fileid)
 {
 	struct blkio_policy_node *pn;
 
 	list_for_each_entry(pn, &blkcg->policy_list, node) {
-		if (pn->dev == dev)
+		if (pn->dev == dev && pn->plid == plid && pn->fileid == fileid)
 			return pn;
 	}
 
@@ -86,6 +114,67 @@
 }
 EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
 
+static inline void
+blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
+{
+	struct blkio_policy_type *blkiop;
+
+	list_for_each_entry(blkiop, &blkio_list, list) {
+		/* If this policy does not own the blkg, do not send updates */
+		if (blkiop->plid != blkg->plid)
+			continue;
+		if (blkiop->ops.blkio_update_group_weight_fn)
+			blkiop->ops.blkio_update_group_weight_fn(blkg->key,
+							blkg, weight);
+	}
+}
+
+static inline void blkio_update_group_bps(struct blkio_group *blkg, u64 bps,
+				int fileid)
+{
+	struct blkio_policy_type *blkiop;
+
+	list_for_each_entry(blkiop, &blkio_list, list) {
+
+		/* If this policy does not own the blkg, do not send updates */
+		if (blkiop->plid != blkg->plid)
+			continue;
+
+		if (fileid == BLKIO_THROTL_read_bps_device
+		    && blkiop->ops.blkio_update_group_read_bps_fn)
+			blkiop->ops.blkio_update_group_read_bps_fn(blkg->key,
+								blkg, bps);
+
+		if (fileid == BLKIO_THROTL_write_bps_device
+		    && blkiop->ops.blkio_update_group_write_bps_fn)
+			blkiop->ops.blkio_update_group_write_bps_fn(blkg->key,
+								blkg, bps);
+	}
+}
+
+static inline void blkio_update_group_iops(struct blkio_group *blkg,
+			unsigned int iops, int fileid)
+{
+	struct blkio_policy_type *blkiop;
+
+	list_for_each_entry(blkiop, &blkio_list, list) {
+
+		/* If this policy does not own the blkg, do not send updates */
+		if (blkiop->plid != blkg->plid)
+			continue;
+
+		if (fileid == BLKIO_THROTL_read_iops_device
+		    && blkiop->ops.blkio_update_group_read_iops_fn)
+			blkiop->ops.blkio_update_group_read_iops_fn(blkg->key,
+								blkg, iops);
+
+		if (fileid == BLKIO_THROTL_write_iops_device
+		    && blkiop->ops.blkio_update_group_write_iops_fn)
+			blkiop->ops.blkio_update_group_write_iops_fn(blkg->key,
+								blkg,iops);
+	}
+}
+
 /*
  * Add to the appropriate stat variable depending on the request type.
  * This should be called with the blkg->stats_lock held.
@@ -341,7 +430,8 @@
 EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
 
 void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-			struct blkio_group *blkg, void *key, dev_t dev)
+		struct blkio_group *blkg, void *key, dev_t dev,
+		enum blkio_policy_id plid)
 {
 	unsigned long flags;
 
@@ -350,6 +440,7 @@
 	rcu_assign_pointer(blkg->key, key);
 	blkg->blkcg_id = css_id(&blkcg->css);
 	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
+	blkg->plid = plid;
 	spin_unlock_irqrestore(&blkcg->lock, flags);
 	/* Need to take css reference ? */
 	cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
@@ -408,51 +499,6 @@
 }
 EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
 
-#define SHOW_FUNCTION(__VAR)						\
-static u64 blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
-				       struct cftype *cftype)		\
-{									\
-	struct blkio_cgroup *blkcg;					\
-									\
-	blkcg = cgroup_to_blkio_cgroup(cgroup);				\
-	return (u64)blkcg->__VAR;					\
-}
-
-SHOW_FUNCTION(weight);
-#undef SHOW_FUNCTION
-
-static int
-blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
-{
-	struct blkio_cgroup *blkcg;
-	struct blkio_group *blkg;
-	struct hlist_node *n;
-	struct blkio_policy_type *blkiop;
-	struct blkio_policy_node *pn;
-
-	if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
-		return -EINVAL;
-
-	blkcg = cgroup_to_blkio_cgroup(cgroup);
-	spin_lock(&blkio_list_lock);
-	spin_lock_irq(&blkcg->lock);
-	blkcg->weight = (unsigned int)val;
-
-	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
-		pn = blkio_policy_search_node(blkcg, blkg->dev);
-
-		if (pn)
-			continue;
-
-		list_for_each_entry(blkiop, &blkio_list, list)
-			blkiop->ops.blkio_update_group_weight_fn(blkg,
-					blkcg->weight);
-	}
-	spin_unlock_irq(&blkcg->lock);
-	spin_unlock(&blkio_list_lock);
-	return 0;
-}
-
 static int
 blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 {
@@ -593,52 +639,6 @@
 	return disk_total;
 }
 
-#define SHOW_FUNCTION_PER_GROUP(__VAR, type, show_total)		\
-static int blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
-		struct cftype *cftype, struct cgroup_map_cb *cb)	\
-{									\
-	struct blkio_cgroup *blkcg;					\
-	struct blkio_group *blkg;					\
-	struct hlist_node *n;						\
-	uint64_t cgroup_total = 0;					\
-									\
-	if (!cgroup_lock_live_group(cgroup))				\
-		return -ENODEV;						\
-									\
-	blkcg = cgroup_to_blkio_cgroup(cgroup);				\
-	rcu_read_lock();						\
-	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\
-		if (blkg->dev) {					\
-			spin_lock_irq(&blkg->stats_lock);		\
-			cgroup_total += blkio_get_stat(blkg, cb,	\
-						blkg->dev, type);	\
-			spin_unlock_irq(&blkg->stats_lock);		\
-		}							\
-	}								\
-	if (show_total)							\
-		cb->fill(cb, "Total", cgroup_total);			\
-	rcu_read_unlock();						\
-	cgroup_unlock();						\
-	return 0;							\
-}
-
-SHOW_FUNCTION_PER_GROUP(time, BLKIO_STAT_TIME, 0);
-SHOW_FUNCTION_PER_GROUP(sectors, BLKIO_STAT_SECTORS, 0);
-SHOW_FUNCTION_PER_GROUP(io_service_bytes, BLKIO_STAT_SERVICE_BYTES, 1);
-SHOW_FUNCTION_PER_GROUP(io_serviced, BLKIO_STAT_SERVICED, 1);
-SHOW_FUNCTION_PER_GROUP(io_service_time, BLKIO_STAT_SERVICE_TIME, 1);
-SHOW_FUNCTION_PER_GROUP(io_wait_time, BLKIO_STAT_WAIT_TIME, 1);
-SHOW_FUNCTION_PER_GROUP(io_merged, BLKIO_STAT_MERGED, 1);
-SHOW_FUNCTION_PER_GROUP(io_queued, BLKIO_STAT_QUEUED, 1);
-#ifdef CONFIG_DEBUG_BLK_CGROUP
-SHOW_FUNCTION_PER_GROUP(dequeue, BLKIO_STAT_DEQUEUE, 0);
-SHOW_FUNCTION_PER_GROUP(avg_queue_size, BLKIO_STAT_AVG_QUEUE_SIZE, 0);
-SHOW_FUNCTION_PER_GROUP(group_wait_time, BLKIO_STAT_GROUP_WAIT_TIME, 0);
-SHOW_FUNCTION_PER_GROUP(idle_time, BLKIO_STAT_IDLE_TIME, 0);
-SHOW_FUNCTION_PER_GROUP(empty_time, BLKIO_STAT_EMPTY_TIME, 0);
-#endif
-#undef SHOW_FUNCTION_PER_GROUP
-
 static int blkio_check_dev_num(dev_t dev)
 {
 	int part = 0;
@@ -652,13 +652,14 @@
 }
 
 static int blkio_policy_parse_and_set(char *buf,
-				      struct blkio_policy_node *newpn)
+	struct blkio_policy_node *newpn, enum blkio_policy_id plid, int fileid)
 {
 	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
 	int ret;
 	unsigned long major, minor, temp;
 	int i = 0;
 	dev_t dev;
+	u64 bps, iops;
 
 	memset(s, 0, sizeof(s));
 
@@ -705,12 +706,47 @@
 	if (s[1] == NULL)
 		return -EINVAL;
 
-	ret = strict_strtoul(s[1], 10, &temp);
-	if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
-	    temp > BLKIO_WEIGHT_MAX)
-		return -EINVAL;
+	switch (plid) {
+	case BLKIO_POLICY_PROP:
+		ret = strict_strtoul(s[1], 10, &temp);
+		if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
+			temp > BLKIO_WEIGHT_MAX)
+			return -EINVAL;
 
-	newpn->weight =  temp;
+		newpn->plid = plid;
+		newpn->fileid = fileid;
+		newpn->val.weight = temp;
+		break;
+	case BLKIO_POLICY_THROTL:
+		switch(fileid) {
+		case BLKIO_THROTL_read_bps_device:
+		case BLKIO_THROTL_write_bps_device:
+			ret = strict_strtoull(s[1], 10, &bps);
+			if (ret)
+				return -EINVAL;
+
+			newpn->plid = plid;
+			newpn->fileid = fileid;
+			newpn->val.bps = bps;
+			break;
+		case BLKIO_THROTL_read_iops_device:
+		case BLKIO_THROTL_write_iops_device:
+			ret = strict_strtoull(s[1], 10, &iops);
+			if (ret)
+				return -EINVAL;
+
+			if (iops > THROTL_IOPS_MAX)
+				return -EINVAL;
+
+			newpn->plid = plid;
+			newpn->fileid = fileid;
+			newpn->val.iops = (unsigned int)iops;
+			break;
+		}
+		break;
+	default:
+		BUG();
+	}
 
 	return 0;
 }
@@ -720,26 +756,180 @@
 {
 	struct blkio_policy_node *pn;
 
-	pn = blkio_policy_search_node(blkcg, dev);
+	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_PROP,
+				BLKIO_PROP_weight_device);
 	if (pn)
-		return pn->weight;
+		return pn->val.weight;
 	else
 		return blkcg->weight;
 }
 EXPORT_SYMBOL_GPL(blkcg_get_weight);
 
+uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev)
+{
+	struct blkio_policy_node *pn;
 
-static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft,
-				       const char *buffer)
+	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_read_bps_device);
+	if (pn)
+		return pn->val.bps;
+	else
+		return -1;
+}
+
+uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg, dev_t dev)
+{
+	struct blkio_policy_node *pn;
+	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_write_bps_device);
+	if (pn)
+		return pn->val.bps;
+	else
+		return -1;
+}
+
+unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg, dev_t dev)
+{
+	struct blkio_policy_node *pn;
+
+	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_read_iops_device);
+	if (pn)
+		return pn->val.iops;
+	else
+		return -1;
+}
+
+unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg, dev_t dev)
+{
+	struct blkio_policy_node *pn;
+	pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_write_iops_device);
+	if (pn)
+		return pn->val.iops;
+	else
+		return -1;
+}
+
+/* Checks whether user asked for deleting a policy rule */
+static bool blkio_delete_rule_command(struct blkio_policy_node *pn)
+{
+	switch(pn->plid) {
+	case BLKIO_POLICY_PROP:
+		if (pn->val.weight == 0)
+			return 1;
+		break;
+	case BLKIO_POLICY_THROTL:
+		switch(pn->fileid) {
+		case BLKIO_THROTL_read_bps_device:
+		case BLKIO_THROTL_write_bps_device:
+			if (pn->val.bps == 0)
+				return 1;
+			break;
+		case BLKIO_THROTL_read_iops_device:
+		case BLKIO_THROTL_write_iops_device:
+			if (pn->val.iops == 0)
+				return 1;
+		}
+		break;
+	default:
+		BUG();
+	}
+
+	return 0;
+}
+
+static void blkio_update_policy_rule(struct blkio_policy_node *oldpn,
+					struct blkio_policy_node *newpn)
+{
+	switch(oldpn->plid) {
+	case BLKIO_POLICY_PROP:
+		oldpn->val.weight = newpn->val.weight;
+		break;
+	case BLKIO_POLICY_THROTL:
+		switch(newpn->fileid) {
+		case BLKIO_THROTL_read_bps_device:
+		case BLKIO_THROTL_write_bps_device:
+			oldpn->val.bps = newpn->val.bps;
+			break;
+		case BLKIO_THROTL_read_iops_device:
+		case BLKIO_THROTL_write_iops_device:
+			oldpn->val.iops = newpn->val.iops;
+		}
+		break;
+	default:
+		BUG();
+	}
+}
+
+/*
+ * Some rules/values in blkg have changed. Propogate those to respective
+ * policies.
+ */
+static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
+		struct blkio_group *blkg, struct blkio_policy_node *pn)
+{
+	unsigned int weight, iops;
+	u64 bps;
+
+	switch(pn->plid) {
+	case BLKIO_POLICY_PROP:
+		weight = pn->val.weight ? pn->val.weight :
+				blkcg->weight;
+		blkio_update_group_weight(blkg, weight);
+		break;
+	case BLKIO_POLICY_THROTL:
+		switch(pn->fileid) {
+		case BLKIO_THROTL_read_bps_device:
+		case BLKIO_THROTL_write_bps_device:
+			bps = pn->val.bps ? pn->val.bps : (-1);
+			blkio_update_group_bps(blkg, bps, pn->fileid);
+			break;
+		case BLKIO_THROTL_read_iops_device:
+		case BLKIO_THROTL_write_iops_device:
+			iops = pn->val.iops ? pn->val.iops : (-1);
+			blkio_update_group_iops(blkg, iops, pn->fileid);
+			break;
+		}
+		break;
+	default:
+		BUG();
+	}
+}
+
+/*
+ * A policy node rule has been updated. Propogate this update to all the
+ * block groups which might be affected by this update.
+ */
+static void blkio_update_policy_node_blkg(struct blkio_cgroup *blkcg,
+				struct blkio_policy_node *pn)
+{
+	struct blkio_group *blkg;
+	struct hlist_node *n;
+
+	spin_lock(&blkio_list_lock);
+	spin_lock_irq(&blkcg->lock);
+
+	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		if (pn->dev != blkg->dev || pn->plid != blkg->plid)
+			continue;
+		blkio_update_blkg_policy(blkcg, blkg, pn);
+	}
+
+	spin_unlock_irq(&blkcg->lock);
+	spin_unlock(&blkio_list_lock);
+}
+
+static int blkiocg_file_write(struct cgroup *cgrp, struct cftype *cft,
+ 				       const char *buffer)
 {
 	int ret = 0;
 	char *buf;
 	struct blkio_policy_node *newpn, *pn;
 	struct blkio_cgroup *blkcg;
-	struct blkio_group *blkg;
 	int keep_newpn = 0;
-	struct hlist_node *n;
-	struct blkio_policy_type *blkiop;
+	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+	int fileid = BLKIOFILE_ATTR(cft->private);
 
 	buf = kstrdup(buffer, GFP_KERNEL);
 	if (!buf)
@@ -751,7 +941,7 @@
 		goto free_buf;
 	}
 
-	ret = blkio_policy_parse_and_set(buf, newpn);
+	ret = blkio_policy_parse_and_set(buf, newpn, plid, fileid);
 	if (ret)
 		goto free_newpn;
 
@@ -759,9 +949,9 @@
 
 	spin_lock_irq(&blkcg->lock);
 
-	pn = blkio_policy_search_node(blkcg, newpn->dev);
+	pn = blkio_policy_search_node(blkcg, newpn->dev, plid, fileid);
 	if (!pn) {
-		if (newpn->weight != 0) {
+		if (!blkio_delete_rule_command(newpn)) {
 			blkio_policy_insert_node(blkcg, newpn);
 			keep_newpn = 1;
 		}
@@ -769,33 +959,17 @@
 		goto update_io_group;
 	}
 
-	if (newpn->weight == 0) {
-		/* weight == 0 means deleteing a specific weight */
+	if (blkio_delete_rule_command(newpn)) {
 		blkio_policy_delete_node(pn);
 		spin_unlock_irq(&blkcg->lock);
 		goto update_io_group;
 	}
 	spin_unlock_irq(&blkcg->lock);
 
-	pn->weight = newpn->weight;
+	blkio_update_policy_rule(pn, newpn);
 
 update_io_group:
-	/* update weight for each cfqg */
-	spin_lock(&blkio_list_lock);
-	spin_lock_irq(&blkcg->lock);
-
-	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
-		if (newpn->dev == blkg->dev) {
-			list_for_each_entry(blkiop, &blkio_list, list)
-				blkiop->ops.blkio_update_group_weight_fn(blkg,
-							 newpn->weight ?
-							 newpn->weight :
-							 blkcg->weight);
-		}
-	}
-
-	spin_unlock_irq(&blkcg->lock);
-	spin_unlock(&blkio_list_lock);
+	blkio_update_policy_node_blkg(blkcg, newpn);
 
 free_newpn:
 	if (!keep_newpn)
@@ -805,23 +979,256 @@
 	return ret;
 }
 
-static int blkiocg_weight_device_read(struct cgroup *cgrp, struct cftype *cft,
-				      struct seq_file *m)
+static void
+blkio_print_policy_node(struct seq_file *m, struct blkio_policy_node *pn)
 {
-	struct blkio_cgroup *blkcg;
+	switch(pn->plid) {
+		case BLKIO_POLICY_PROP:
+			if (pn->fileid == BLKIO_PROP_weight_device)
+				seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
+					MINOR(pn->dev), pn->val.weight);
+			break;
+		case BLKIO_POLICY_THROTL:
+			switch(pn->fileid) {
+			case BLKIO_THROTL_read_bps_device:
+			case BLKIO_THROTL_write_bps_device:
+				seq_printf(m, "%u:%u\t%llu\n", MAJOR(pn->dev),
+					MINOR(pn->dev), pn->val.bps);
+				break;
+			case BLKIO_THROTL_read_iops_device:
+			case BLKIO_THROTL_write_iops_device:
+				seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
+					MINOR(pn->dev), pn->val.iops);
+				break;
+			}
+			break;
+		default:
+			BUG();
+	}
+}
+
+/* cgroup files which read their data from policy nodes end up here */
+static void blkio_read_policy_node_files(struct cftype *cft,
+			struct blkio_cgroup *blkcg, struct seq_file *m)
+{
 	struct blkio_policy_node *pn;
 
-	seq_printf(m, "dev\tweight\n");
-
-	blkcg = cgroup_to_blkio_cgroup(cgrp);
 	if (!list_empty(&blkcg->policy_list)) {
 		spin_lock_irq(&blkcg->lock);
 		list_for_each_entry(pn, &blkcg->policy_list, node) {
-			seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
-				   MINOR(pn->dev), pn->weight);
+			if (!pn_matches_cftype(cft, pn))
+				continue;
+			blkio_print_policy_node(m, pn);
 		}
 		spin_unlock_irq(&blkcg->lock);
 	}
+}
+
+static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,
+				struct seq_file *m)
+{
+	struct blkio_cgroup *blkcg;
+	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+	int name = BLKIOFILE_ATTR(cft->private);
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+	switch(plid) {
+	case BLKIO_POLICY_PROP:
+		switch(name) {
+		case BLKIO_PROP_weight_device:
+			blkio_read_policy_node_files(cft, blkcg, m);
+			return 0;
+		default:
+			BUG();
+		}
+		break;
+	case BLKIO_POLICY_THROTL:
+		switch(name){
+		case BLKIO_THROTL_read_bps_device:
+		case BLKIO_THROTL_write_bps_device:
+		case BLKIO_THROTL_read_iops_device:
+		case BLKIO_THROTL_write_iops_device:
+			blkio_read_policy_node_files(cft, blkcg, m);
+			return 0;
+		default:
+			BUG();
+		}
+		break;
+	default:
+		BUG();
+	}
+
+	return 0;
+}
+
+static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
+		struct cftype *cft, struct cgroup_map_cb *cb, enum stat_type type,
+		bool show_total)
+{
+	struct blkio_group *blkg;
+	struct hlist_node *n;
+	uint64_t cgroup_total = 0;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		if (blkg->dev) {
+			if (!cftype_blkg_same_policy(cft, blkg))
+				continue;
+			spin_lock_irq(&blkg->stats_lock);
+			cgroup_total += blkio_get_stat(blkg, cb, blkg->dev,
+						type);
+			spin_unlock_irq(&blkg->stats_lock);
+		}
+	}
+	if (show_total)
+		cb->fill(cb, "Total", cgroup_total);
+	rcu_read_unlock();
+	return 0;
+}
+
+/* All map kind of cgroup file get serviced by this function */
+static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
+				struct cgroup_map_cb *cb)
+{
+	struct blkio_cgroup *blkcg;
+	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+	int name = BLKIOFILE_ATTR(cft->private);
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+	switch(plid) {
+	case BLKIO_POLICY_PROP:
+		switch(name) {
+		case BLKIO_PROP_time:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_TIME, 0);
+		case BLKIO_PROP_sectors:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_SECTORS, 0);
+		case BLKIO_PROP_io_service_bytes:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_SERVICE_BYTES, 1);
+		case BLKIO_PROP_io_serviced:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_SERVICED, 1);
+		case BLKIO_PROP_io_service_time:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_SERVICE_TIME, 1);
+		case BLKIO_PROP_io_wait_time:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_WAIT_TIME, 1);
+		case BLKIO_PROP_io_merged:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_MERGED, 1);
+		case BLKIO_PROP_io_queued:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_QUEUED, 1);
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+		case BLKIO_PROP_dequeue:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_DEQUEUE, 0);
+		case BLKIO_PROP_avg_queue_size:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_AVG_QUEUE_SIZE, 0);
+		case BLKIO_PROP_group_wait_time:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_GROUP_WAIT_TIME, 0);
+		case BLKIO_PROP_idle_time:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_IDLE_TIME, 0);
+		case BLKIO_PROP_empty_time:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_EMPTY_TIME, 0);
+#endif
+		default:
+			BUG();
+		}
+		break;
+	case BLKIO_POLICY_THROTL:
+		switch(name){
+		case BLKIO_THROTL_io_service_bytes:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_SERVICE_BYTES, 1);
+		case BLKIO_THROTL_io_serviced:
+			return blkio_read_blkg_stats(blkcg, cft, cb,
+						BLKIO_STAT_SERVICED, 1);
+		default:
+			BUG();
+		}
+		break;
+	default:
+		BUG();
+	}
+
+	return 0;
+}
+
+static int blkio_weight_write(struct blkio_cgroup *blkcg, u64 val)
+{
+	struct blkio_group *blkg;
+	struct hlist_node *n;
+	struct blkio_policy_node *pn;
+
+	if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
+		return -EINVAL;
+
+	spin_lock(&blkio_list_lock);
+	spin_lock_irq(&blkcg->lock);
+	blkcg->weight = (unsigned int)val;
+
+	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		pn = blkio_policy_search_node(blkcg, blkg->dev,
+				BLKIO_POLICY_PROP, BLKIO_PROP_weight_device);
+		if (pn)
+			continue;
+
+		blkio_update_group_weight(blkg, blkcg->weight);
+	}
+	spin_unlock_irq(&blkcg->lock);
+	spin_unlock(&blkio_list_lock);
+	return 0;
+}
+
+static u64 blkiocg_file_read_u64 (struct cgroup *cgrp, struct cftype *cft) {
+	struct blkio_cgroup *blkcg;
+	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+	int name = BLKIOFILE_ATTR(cft->private);
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+	switch(plid) {
+	case BLKIO_POLICY_PROP:
+		switch(name) {
+		case BLKIO_PROP_weight:
+			return (u64)blkcg->weight;
+		}
+		break;
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+static int
+blkiocg_file_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
+{
+	struct blkio_cgroup *blkcg;
+	enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
+	int name = BLKIOFILE_ATTR(cft->private);
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+	switch(plid) {
+	case BLKIO_POLICY_PROP:
+		switch(name) {
+		case BLKIO_PROP_weight:
+			return blkio_weight_write(blkcg, val);
+		}
+		break;
+	default:
+		BUG();
+	}
 
 	return 0;
 }
@@ -829,71 +1236,151 @@
 struct cftype blkio_files[] = {
 	{
 		.name = "weight_device",
-		.read_seq_string = blkiocg_weight_device_read,
-		.write_string = blkiocg_weight_device_write,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_weight_device),
+		.read_seq_string = blkiocg_file_read,
+		.write_string = blkiocg_file_write,
 		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
-		.read_u64 = blkiocg_weight_read,
-		.write_u64 = blkiocg_weight_write,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_weight),
+		.read_u64 = blkiocg_file_read_u64,
+		.write_u64 = blkiocg_file_write_u64,
 	},
 	{
 		.name = "time",
-		.read_map = blkiocg_time_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_time),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "sectors",
-		.read_map = blkiocg_sectors_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_sectors),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "io_service_bytes",
-		.read_map = blkiocg_io_service_bytes_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_io_service_bytes),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "io_serviced",
-		.read_map = blkiocg_io_serviced_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_io_serviced),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "io_service_time",
-		.read_map = blkiocg_io_service_time_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_io_service_time),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "io_wait_time",
-		.read_map = blkiocg_io_wait_time_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_io_wait_time),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "io_merged",
-		.read_map = blkiocg_io_merged_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_io_merged),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "io_queued",
-		.read_map = blkiocg_io_queued_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_io_queued),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "reset_stats",
 		.write_u64 = blkiocg_reset_stats,
 	},
+#ifdef CONFIG_BLK_DEV_THROTTLING
+	{
+		.name = "throttle.read_bps_device",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_read_bps_device),
+		.read_seq_string = blkiocg_file_read,
+		.write_string = blkiocg_file_write,
+		.max_write_len = 256,
+	},
+
+	{
+		.name = "throttle.write_bps_device",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_write_bps_device),
+		.read_seq_string = blkiocg_file_read,
+		.write_string = blkiocg_file_write,
+		.max_write_len = 256,
+	},
+
+	{
+		.name = "throttle.read_iops_device",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_read_iops_device),
+		.read_seq_string = blkiocg_file_read,
+		.write_string = blkiocg_file_write,
+		.max_write_len = 256,
+	},
+
+	{
+		.name = "throttle.write_iops_device",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_write_iops_device),
+		.read_seq_string = blkiocg_file_read,
+		.write_string = blkiocg_file_write,
+		.max_write_len = 256,
+	},
+	{
+		.name = "throttle.io_service_bytes",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_io_service_bytes),
+		.read_map = blkiocg_file_read_map,
+	},
+	{
+		.name = "throttle.io_serviced",
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
+				BLKIO_THROTL_io_serviced),
+		.read_map = blkiocg_file_read_map,
+	},
+#endif /* CONFIG_BLK_DEV_THROTTLING */
+
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 	{
 		.name = "avg_queue_size",
-		.read_map = blkiocg_avg_queue_size_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_avg_queue_size),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "group_wait_time",
-		.read_map = blkiocg_group_wait_time_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_group_wait_time),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "idle_time",
-		.read_map = blkiocg_idle_time_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_idle_time),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "empty_time",
-		.read_map = blkiocg_empty_time_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_empty_time),
+		.read_map = blkiocg_file_read_map,
 	},
 	{
 		.name = "dequeue",
-		.read_map = blkiocg_dequeue_read,
+		.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
+				BLKIO_PROP_dequeue),
+		.read_map = blkiocg_file_read_map,
 	},
 #endif
 };
@@ -932,13 +1419,14 @@
 		/*
 		 * This blkio_group is being unlinked as associated cgroup is
 		 * going away. Let all the IO controlling policies know about
-		 * this event. Currently this is static call to one io
-		 * controlling policy. Once we have more policies in place, we
-		 * need some dynamic registration of callback function.
+		 * this event.
 		 */
 		spin_lock(&blkio_list_lock);
-		list_for_each_entry(blkiop, &blkio_list, list)
+		list_for_each_entry(blkiop, &blkio_list, list) {
+			if (blkiop->plid != blkg->plid)
+				continue;
 			blkiop->ops.blkio_unlink_group_fn(key, blkg);
+		}
 		spin_unlock(&blkio_list_lock);
 	} while (1);
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 2b866ec..ea4861b 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -15,6 +15,14 @@
 
 #include <linux/cgroup.h>
 
+enum blkio_policy_id {
+	BLKIO_POLICY_PROP = 0,		/* Proportional Bandwidth division */
+	BLKIO_POLICY_THROTL,		/* Throttling */
+};
+
+/* Max limits for throttle policy */
+#define THROTL_IOPS_MAX		UINT_MAX
+
 #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
 
 #ifndef CONFIG_BLK_CGROUP
@@ -65,6 +73,35 @@
 	BLKG_empty,
 };
 
+/* cgroup files owned by proportional weight policy */
+enum blkcg_file_name_prop {
+	BLKIO_PROP_weight = 1,
+	BLKIO_PROP_weight_device,
+	BLKIO_PROP_io_service_bytes,
+	BLKIO_PROP_io_serviced,
+	BLKIO_PROP_time,
+	BLKIO_PROP_sectors,
+	BLKIO_PROP_io_service_time,
+	BLKIO_PROP_io_wait_time,
+	BLKIO_PROP_io_merged,
+	BLKIO_PROP_io_queued,
+	BLKIO_PROP_avg_queue_size,
+	BLKIO_PROP_group_wait_time,
+	BLKIO_PROP_idle_time,
+	BLKIO_PROP_empty_time,
+	BLKIO_PROP_dequeue,
+};
+
+/* cgroup files owned by throttle policy */
+enum blkcg_file_name_throtl {
+	BLKIO_THROTL_read_bps_device,
+	BLKIO_THROTL_write_bps_device,
+	BLKIO_THROTL_read_iops_device,
+	BLKIO_THROTL_write_iops_device,
+	BLKIO_THROTL_io_service_bytes,
+	BLKIO_THROTL_io_serviced,
+};
+
 struct blkio_cgroup {
 	struct cgroup_subsys_state css;
 	unsigned int weight;
@@ -112,6 +149,8 @@
 	char path[128];
 	/* The device MKDEV(major, minor), this group has been created for */
 	dev_t dev;
+	/* policy which owns this blk group */
+	enum blkio_policy_id plid;
 
 	/* Need to serialize the stats in the case of reset/update */
 	spinlock_t stats_lock;
@@ -121,24 +160,60 @@
 struct blkio_policy_node {
 	struct list_head node;
 	dev_t dev;
-	unsigned int weight;
+	/* This node belongs to max bw policy or porportional weight policy */
+	enum blkio_policy_id plid;
+	/* cgroup file to which this rule belongs to */
+	int fileid;
+
+	union {
+		unsigned int weight;
+		/*
+		 * Rate read/write in terms of byptes per second
+		 * Whether this rate represents read or write is determined
+		 * by file type "fileid".
+		 */
+		u64 bps;
+		unsigned int iops;
+	} val;
 };
 
 extern unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
 				     dev_t dev);
+extern uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg,
+				     dev_t dev);
+extern uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg,
+				     dev_t dev);
+extern unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg,
+				     dev_t dev);
+extern unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg,
+				     dev_t dev);
 
 typedef void (blkio_unlink_group_fn) (void *key, struct blkio_group *blkg);
-typedef void (blkio_update_group_weight_fn) (struct blkio_group *blkg,
-						unsigned int weight);
+
+typedef void (blkio_update_group_weight_fn) (void *key,
+			struct blkio_group *blkg, unsigned int weight);
+typedef void (blkio_update_group_read_bps_fn) (void * key,
+			struct blkio_group *blkg, u64 read_bps);
+typedef void (blkio_update_group_write_bps_fn) (void *key,
+			struct blkio_group *blkg, u64 write_bps);
+typedef void (blkio_update_group_read_iops_fn) (void *key,
+			struct blkio_group *blkg, unsigned int read_iops);
+typedef void (blkio_update_group_write_iops_fn) (void *key,
+			struct blkio_group *blkg, unsigned int write_iops);
 
 struct blkio_policy_ops {
 	blkio_unlink_group_fn *blkio_unlink_group_fn;
 	blkio_update_group_weight_fn *blkio_update_group_weight_fn;
+	blkio_update_group_read_bps_fn *blkio_update_group_read_bps_fn;
+	blkio_update_group_write_bps_fn *blkio_update_group_write_bps_fn;
+	blkio_update_group_read_iops_fn *blkio_update_group_read_iops_fn;
+	blkio_update_group_write_iops_fn *blkio_update_group_write_iops_fn;
 };
 
 struct blkio_policy_type {
 	struct list_head list;
 	struct blkio_policy_ops ops;
+	enum blkio_policy_id plid;
 };
 
 /* Blkio controller policy registration */
@@ -212,7 +287,8 @@
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
 extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-			struct blkio_group *blkg, void *key, dev_t dev);
+	struct blkio_group *blkg, void *key, dev_t dev,
+	enum blkio_policy_id plid);
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
 extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
 						void *key);
@@ -234,7 +310,8 @@
 cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
 
 static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
-			struct blkio_group *blkg, void *key, dev_t dev) {}
+		struct blkio_group *blkg, void *key, dev_t dev,
+		enum blkio_policy_id plid) {}
 
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
diff --git a/block/blk-core.c b/block/blk-core.c
index 32a1c12..4514146 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -64,13 +64,15 @@
 		return;
 
 	cpu = part_stat_lock();
-	part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
 
-	if (!new_io)
+	if (!new_io) {
+		part = rq->part;
 		part_stat_inc(cpu, part, merges[rw]);
-	else {
+	} else {
+		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
 		part_round_stats(cpu, part);
 		part_inc_in_flight(part, rw);
+		rq->part = part;
 	}
 
 	part_stat_unlock();
@@ -128,6 +130,7 @@
 	rq->ref_count = 1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
+	rq->part = NULL;
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -136,7 +139,7 @@
 {
 	struct request_queue *q = rq->q;
 
-	if (&q->bar_rq != rq) {
+	if (&q->flush_rq != rq) {
 		if (error)
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
@@ -160,13 +163,12 @@
 		if (bio->bi_size == 0)
 			bio_endio(bio, error);
 	} else {
-
 		/*
-		 * Okay, this is the barrier request in progress, just
-		 * record the error;
+		 * Okay, this is the sequenced flush request in
+		 * progress, just record the error;
 		 */
-		if (error && !q->orderr)
-			q->orderr = error;
+		if (error && !q->flush_err)
+			q->flush_err = error;
 	}
 }
 
@@ -382,6 +384,7 @@
 	del_timer_sync(&q->unplug_timer);
 	del_timer_sync(&q->timeout);
 	cancel_work_sync(&q->unplug_work);
+	throtl_shutdown_timer_wq(q);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -459,6 +462,8 @@
 	if (q->elevator)
 		elevator_exit(q->elevator);
 
+	blk_throtl_exit(q);
+
 	blk_put_queue(q);
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
@@ -515,11 +520,17 @@
 		return NULL;
 	}
 
+	if (blk_throtl_init(q)) {
+		kmem_cache_free(blk_requestq_cachep, q);
+		return NULL;
+	}
+
 	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
 	init_timer(&q->unplug_timer);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->timeout_list);
+	INIT_LIST_HEAD(&q->pending_flushes);
 	INIT_WORK(&q->unplug_work, blk_unplug_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
@@ -796,11 +807,16 @@
 	rl->starved[is_sync] = 0;
 
 	priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
-	if (priv)
+	if (priv) {
 		rl->elvpriv++;
 
-	if (blk_queue_io_stat(q))
-		rw_flags |= REQ_IO_STAT;
+		/*
+		 * Don't do stats for non-priv requests
+		 */
+		if (blk_queue_io_stat(q))
+			rw_flags |= REQ_IO_STAT;
+	}
+
 	spin_unlock_irq(q->queue_lock);
 
 	rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
@@ -1037,22 +1053,6 @@
 }
 EXPORT_SYMBOL(blk_insert_request);
 
-/*
- * add-request adds a request to the linked list.
- * queue lock is held and interrupts disabled, as we muck with the
- * request queue list.
- */
-static inline void add_request(struct request_queue *q, struct request *req)
-{
-	drive_stat_acct(req, 1);
-
-	/*
-	 * elevator indicated where it wants this request to be
-	 * inserted at elevator_merge time
-	 */
-	__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
-}
-
 static void part_round_stats_single(int cpu, struct hd_struct *part,
 				    unsigned long now)
 {
@@ -1201,13 +1201,16 @@
 	const bool sync = !!(bio->bi_rw & REQ_SYNC);
 	const bool unplug = !!(bio->bi_rw & REQ_UNPLUG);
 	const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	int where = ELEVATOR_INSERT_SORT;
 	int rw_flags;
 
-	if ((bio->bi_rw & REQ_HARDBARRIER) &&
-	    (q->next_ordered == QUEUE_ORDERED_NONE)) {
+	/* REQ_HARDBARRIER is no more */
+	if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER,
+		"block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
+
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1217,7 +1220,12 @@
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely((bio->bi_rw & REQ_HARDBARRIER)) || elv_queue_empty(q))
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+		where = ELEVATOR_INSERT_FRONT;
+		goto get_rq;
+	}
+
+	if (elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);
@@ -1314,7 +1322,10 @@
 		req->cpu = blk_cpu_to_group(smp_processor_id());
 	if (queue_should_plug(q) && elv_queue_empty(q))
 		blk_plug_device(q);
-	add_request(q, req);
+
+	/* insert the request into the elevator */
+	drive_stat_acct(req, 1);
+	__elv_add_request(q, req, where, 0);
 out:
 	if (unplug || !queue_should_plug(q))
 		__generic_unplug_device(q);
@@ -1514,6 +1525,19 @@
 		if (bio_check_eod(bio, nr_sectors))
 			goto end_io;
 
+		/*
+		 * Filter flush bio's early so that make_request based
+		 * drivers without flush support don't have to worry
+		 * about them.
+		 */
+		if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
+			bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
+			if (!nr_sectors) {
+				err = 0;
+				goto end_io;
+			}
+		}
+
 		if ((bio->bi_rw & REQ_DISCARD) &&
 		    (!blk_queue_discard(q) ||
 		     ((bio->bi_rw & REQ_SECURE) &&
@@ -1522,6 +1546,15 @@
 			goto end_io;
 		}
 
+		blk_throtl_bio(q, &bio);
+
+		/*
+		 * If bio = NULL, bio has been throttled and will be submitted
+		 * later.
+		 */
+		if (!bio)
+			break;
+
 		trace_block_bio_queue(q, bio);
 
 		ret = q->make_request_fn(q, bio);
@@ -1612,11 +1645,12 @@
 
 		if (unlikely(block_dump)) {
 			char b[BDEVNAME_SIZE];
-			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
+			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
 			current->comm, task_pid_nr(current),
 				(rw & WRITE) ? "WRITE" : "READ",
 				(unsigned long long)bio->bi_sector,
-				bdevname(bio->bi_bdev, b));
+				bdevname(bio->bi_bdev, b),
+				count);
 		}
 	}
 
@@ -1759,7 +1793,7 @@
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
 		part_stat_unlock();
 	}
@@ -1768,18 +1802,18 @@
 static void blk_account_io_done(struct request *req)
 {
 	/*
-	 * Account IO completion.  bar_rq isn't accounted as a normal
-	 * IO on queueing nor completion.  Accounting the containing
-	 * request is enough.
+	 * Account IO completion.  flush_rq isn't accounted as a
+	 * normal IO on queueing nor completion.  Accounting the
+	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && req != &req->q->bar_rq) {
+	if (blk_do_io_stat(req) && req != &req->q->flush_rq) {
 		unsigned long duration = jiffies - req->start_time;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);
@@ -2497,9 +2531,7 @@
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE);
-	if (src->cmd_flags & REQ_DISCARD)
-		dst->cmd_flags |= REQ_DISCARD;
+	dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
@@ -2579,6 +2611,13 @@
 }
 EXPORT_SYMBOL(kblockd_schedule_work);
 
+int kblockd_schedule_delayed_work(struct request_queue *q,
+			struct delayed_work *dwork, unsigned long delay)
+{
+	return queue_delayed_work(kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_schedule_delayed_work);
+
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
diff --git a/block/blk-exec.c b/block/blk-exec.c
index e1672f1..cf1456a 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -80,6 +80,7 @@
 	DECLARE_COMPLETION_ONSTACK(wait);
 	char sense[SCSI_SENSE_BUFFERSIZE];
 	int err = 0;
+	unsigned long hang_check;
 
 	/*
 	 * we need an extra reference to the request, so we can look at
@@ -95,7 +96,13 @@
 
 	rq->end_io_data = &wait;
 	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
-	wait_for_completion(&wait);
+
+	/* Prevent hang_check timer from firing at us during very long I/O */
+	hang_check = sysctl_hung_task_timeout_secs;
+	if (hang_check)
+		while (!wait_for_completion_timeout(&wait, hang_check * (HZ/2)));
+	else
+		wait_for_completion(&wait);
 
 	if (rq->errors)
 		err = -EIO;
diff --git a/block/blk-flush.c b/block/blk-flush.c
new file mode 100644
index 0000000..54b123d
--- /dev/null
+++ b/block/blk-flush.c
@@ -0,0 +1,262 @@
+/*
+ * Functions to sequence FLUSH and FUA writes.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/gfp.h>
+
+#include "blk.h"
+
+/* FLUSH/FUA sequences */
+enum {
+	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
+	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
+	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
+	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
+	QUEUE_FSEQ_DONE		= (1 << 4),
+};
+
+static struct request *queue_next_fseq(struct request_queue *q);
+
+unsigned blk_flush_cur_seq(struct request_queue *q)
+{
+	if (!q->flush_seq)
+		return 0;
+	return 1 << ffz(q->flush_seq);
+}
+
+static struct request *blk_flush_complete_seq(struct request_queue *q,
+					      unsigned seq, int error)
+{
+	struct request *next_rq = NULL;
+
+	if (error && !q->flush_err)
+		q->flush_err = error;
+
+	BUG_ON(q->flush_seq & seq);
+	q->flush_seq |= seq;
+
+	if (blk_flush_cur_seq(q) != QUEUE_FSEQ_DONE) {
+		/* not complete yet, queue the next flush sequence */
+		next_rq = queue_next_fseq(q);
+	} else {
+		/* complete this flush request */
+		__blk_end_request_all(q->orig_flush_rq, q->flush_err);
+		q->orig_flush_rq = NULL;
+		q->flush_seq = 0;
+
+		/* dispatch the next flush if there's one */
+		if (!list_empty(&q->pending_flushes)) {
+			next_rq = list_entry_rq(q->pending_flushes.next);
+			list_move(&next_rq->queuelist, &q->queue_head);
+		}
+	}
+	return next_rq;
+}
+
+static void blk_flush_complete_seq_end_io(struct request_queue *q,
+					  unsigned seq, int error)
+{
+	bool was_empty = elv_queue_empty(q);
+	struct request *next_rq;
+
+	next_rq = blk_flush_complete_seq(q, seq, error);
+
+	/*
+	 * Moving a request silently to empty queue_head may stall the
+	 * queue.  Kick the queue in those cases.
+	 */
+	if (was_empty && next_rq)
+		__blk_run_queue(q);
+}
+
+static void pre_flush_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_PREFLUSH, error);
+}
+
+static void flush_data_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_DATA, error);
+}
+
+static void post_flush_end_io(struct request *rq, int error)
+{
+	elv_completed_request(rq->q, rq);
+	blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_POSTFLUSH, error);
+}
+
+static void init_flush_request(struct request *rq, struct gendisk *disk)
+{
+	rq->cmd_type = REQ_TYPE_FS;
+	rq->cmd_flags = WRITE_FLUSH;
+	rq->rq_disk = disk;
+}
+
+static struct request *queue_next_fseq(struct request_queue *q)
+{
+	struct request *orig_rq = q->orig_flush_rq;
+	struct request *rq = &q->flush_rq;
+
+	blk_rq_init(q, rq);
+
+	switch (blk_flush_cur_seq(q)) {
+	case QUEUE_FSEQ_PREFLUSH:
+		init_flush_request(rq, orig_rq->rq_disk);
+		rq->end_io = pre_flush_end_io;
+		break;
+	case QUEUE_FSEQ_DATA:
+		init_request_from_bio(rq, orig_rq->bio);
+		/*
+		 * orig_rq->rq_disk may be different from
+		 * bio->bi_bdev->bd_disk if orig_rq got here through
+		 * remapping drivers.  Make sure rq->rq_disk points
+		 * to the same one as orig_rq.
+		 */
+		rq->rq_disk = orig_rq->rq_disk;
+		rq->cmd_flags &= ~(REQ_FLUSH | REQ_FUA);
+		rq->cmd_flags |= orig_rq->cmd_flags & (REQ_FLUSH | REQ_FUA);
+		rq->end_io = flush_data_end_io;
+		break;
+	case QUEUE_FSEQ_POSTFLUSH:
+		init_flush_request(rq, orig_rq->rq_disk);
+		rq->end_io = post_flush_end_io;
+		break;
+	default:
+		BUG();
+	}
+
+	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+	return rq;
+}
+
+struct request *blk_do_flush(struct request_queue *q, struct request *rq)
+{
+	unsigned int fflags = q->flush_flags; /* may change, cache it */
+	bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA;
+	bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH);
+	bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA);
+	unsigned skip = 0;
+
+	/*
+	 * Special case.  If there's data but flush is not necessary,
+	 * the request can be issued directly.
+	 *
+	 * Flush w/o data should be able to be issued directly too but
+	 * currently some drivers assume that rq->bio contains
+	 * non-zero data if it isn't NULL and empty FLUSH requests
+	 * getting here usually have bio's without data.
+	 */
+	if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) {
+		rq->cmd_flags &= ~REQ_FLUSH;
+		if (!has_fua)
+			rq->cmd_flags &= ~REQ_FUA;
+		return rq;
+	}
+
+	/*
+	 * Sequenced flushes can't be processed in parallel.  If
+	 * another one is already in progress, queue for later
+	 * processing.
+	 */
+	if (q->flush_seq) {
+		list_move_tail(&rq->queuelist, &q->pending_flushes);
+		return NULL;
+	}
+
+	/*
+	 * Start a new flush sequence
+	 */
+	q->flush_err = 0;
+	q->flush_seq |= QUEUE_FSEQ_STARTED;
+
+	/* adjust FLUSH/FUA of the original request and stash it away */
+	rq->cmd_flags &= ~REQ_FLUSH;
+	if (!has_fua)
+		rq->cmd_flags &= ~REQ_FUA;
+	blk_dequeue_request(rq);
+	q->orig_flush_rq = rq;
+
+	/* skip unneded sequences and return the first one */
+	if (!do_preflush)
+		skip |= QUEUE_FSEQ_PREFLUSH;
+	if (!blk_rq_sectors(rq))
+		skip |= QUEUE_FSEQ_DATA;
+	if (!do_postflush)
+		skip |= QUEUE_FSEQ_POSTFLUSH;
+	return blk_flush_complete_seq(q, skip, 0);
+}
+
+static void bio_end_flush(struct bio *bio, int err)
+{
+	if (err)
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	if (bio->bi_private)
+		complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/**
+ * blkdev_issue_flush - queue a flush
+ * @bdev:	blockdev to issue flush for
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @error_sector:	error sector
+ *
+ * Description:
+ *    Issue a flush for the block device in question. Caller can supply
+ *    room for storing the error offset in case of a flush error, if they
+ *    wish to. If WAIT flag is not passed then caller may check only what
+ *    request was pushed in some internal queue for later handling.
+ */
+int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
+		sector_t *error_sector)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	struct request_queue *q;
+	struct bio *bio;
+	int ret = 0;
+
+	if (bdev->bd_disk == NULL)
+		return -ENXIO;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	/*
+	 * some block devices may not have their queue correctly set up here
+	 * (e.g. loop device without a backing file) and so issuing a flush
+	 * here will panic. Ensure there is a request function before issuing
+	 * the flush.
+	 */
+	if (!q->make_request_fn)
+		return -ENXIO;
+
+	bio = bio_alloc(gfp_mask, 0);
+	bio->bi_end_io = bio_end_flush;
+	bio->bi_bdev = bdev;
+	bio->bi_private = &wait;
+
+	bio_get(bio);
+	submit_bio(WRITE_FLUSH, bio);
+	wait_for_completion(&wait);
+
+	/*
+	 * The driver must store the error location in ->bi_sector, if
+	 * it supports it. For non-stacked drivers, this should be
+	 * copied from blk_rq_pos(rq).
+	 */
+	if (error_sector)
+               *error_sector = bio->bi_sector;
+
+	if (!bio_flagged(bio, BIO_UPTODATE))
+		ret = -EIO;
+
+	bio_put(bio);
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_flush);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index edce1ef..54bcba6 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -32,24 +32,37 @@
 
 /**
  * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements
- * @rq:		request with integrity metadata attached
+ * @q:		request queue
+ * @bio:	bio with integrity metadata attached
  *
  * Description: Returns the number of elements required in a
- * scatterlist corresponding to the integrity metadata in a request.
+ * scatterlist corresponding to the integrity metadata in a bio.
  */
-int blk_rq_count_integrity_sg(struct request *rq)
+int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio)
 {
-	struct bio_vec *iv, *ivprv;
-	struct req_iterator iter;
-	unsigned int segments;
+	struct bio_vec *iv, *ivprv = NULL;
+	unsigned int segments = 0;
+	unsigned int seg_size = 0;
+	unsigned int i = 0;
 
-	ivprv = NULL;
-	segments = 0;
+	bio_for_each_integrity_vec(iv, bio, i) {
 
-	rq_for_each_integrity_segment(iv, rq, iter) {
+		if (ivprv) {
+			if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
+				goto new_segment;
 
-		if (!ivprv || !BIOVEC_PHYS_MERGEABLE(ivprv, iv))
+			if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv))
+				goto new_segment;
+
+			if (seg_size + iv->bv_len > queue_max_segment_size(q))
+				goto new_segment;
+
+			seg_size += iv->bv_len;
+		} else {
+new_segment:
 			segments++;
+			seg_size = iv->bv_len;
+		}
 
 		ivprv = iv;
 	}
@@ -60,30 +73,34 @@
 
 /**
  * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
- * @rq:		request with integrity metadata attached
+ * @q:		request queue
+ * @bio:	bio with integrity metadata attached
  * @sglist:	target scatterlist
  *
  * Description: Map the integrity vectors in request into a
  * scatterlist.  The scatterlist must be big enough to hold all
  * elements.  I.e. sized using blk_rq_count_integrity_sg().
  */
-int blk_rq_map_integrity_sg(struct request *rq, struct scatterlist *sglist)
+int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio,
+			    struct scatterlist *sglist)
 {
-	struct bio_vec *iv, *ivprv;
-	struct req_iterator iter;
-	struct scatterlist *sg;
-	unsigned int segments;
+	struct bio_vec *iv, *ivprv = NULL;
+	struct scatterlist *sg = NULL;
+	unsigned int segments = 0;
+	unsigned int i = 0;
 
-	ivprv = NULL;
-	sg = NULL;
-	segments = 0;
-
-	rq_for_each_integrity_segment(iv, rq, iter) {
+	bio_for_each_integrity_vec(iv, bio, i) {
 
 		if (ivprv) {
 			if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
 				goto new_segment;
 
+			if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv))
+				goto new_segment;
+
+			if (sg->length + iv->bv_len > queue_max_segment_size(q))
+				goto new_segment;
+
 			sg->length += iv->bv_len;
 		} else {
 new_segment:
@@ -162,6 +179,40 @@
 }
 EXPORT_SYMBOL(blk_integrity_compare);
 
+int blk_integrity_merge_rq(struct request_queue *q, struct request *req,
+			   struct request *next)
+{
+	if (blk_integrity_rq(req) != blk_integrity_rq(next))
+		return -1;
+
+	if (req->nr_integrity_segments + next->nr_integrity_segments >
+	    q->limits.max_integrity_segments)
+		return -1;
+
+	return 0;
+}
+EXPORT_SYMBOL(blk_integrity_merge_rq);
+
+int blk_integrity_merge_bio(struct request_queue *q, struct request *req,
+			    struct bio *bio)
+{
+	int nr_integrity_segs;
+	struct bio *next = bio->bi_next;
+
+	bio->bi_next = NULL;
+	nr_integrity_segs = blk_rq_count_integrity_sg(q, bio);
+	bio->bi_next = next;
+
+	if (req->nr_integrity_segments + nr_integrity_segs >
+	    q->limits.max_integrity_segments)
+		return -1;
+
+	req->nr_integrity_segments += nr_integrity_segs;
+
+	return 0;
+}
+EXPORT_SYMBOL(blk_integrity_merge_bio);
+
 struct integrity_sysfs_entry {
 	struct attribute attr;
 	ssize_t (*show)(struct blk_integrity *, char *);
@@ -381,7 +432,6 @@
 	kobject_uevent(&bi->kobj, KOBJ_REMOVE);
 	kobject_del(&bi->kobj);
 	kobject_put(&bi->kobj);
-	kmem_cache_free(integrity_cachep, bi);
 	disk->integrity = NULL;
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index c392029..1a320d2 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -39,8 +39,7 @@
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q = bdev_get_queue(bdev);
-	int type = flags & BLKDEV_IFL_BARRIER ?
-		DISCARD_BARRIER : DISCARD_NOBARRIER;
+	int type = REQ_WRITE | REQ_DISCARD;
 	unsigned int max_discard_sectors;
 	struct bio *bio;
 	int ret = 0;
@@ -62,10 +61,10 @@
 		max_discard_sectors &= ~(disc_sects - 1);
 	}
 
-	if (flags & BLKDEV_IFL_SECURE) {
+	if (flags & BLKDEV_DISCARD_SECURE) {
 		if (!blk_queue_secdiscard(q))
 			return -EOPNOTSUPP;
-		type |= DISCARD_SECURE;
+		type |= REQ_SECURE;
 	}
 
 	while (nr_sects && !ret) {
@@ -78,8 +77,7 @@
 		bio->bi_sector = sector;
 		bio->bi_end_io = blkdev_discard_end_io;
 		bio->bi_bdev = bdev;
-		if (flags & BLKDEV_IFL_WAIT)
-			bio->bi_private = &wait;
+		bio->bi_private = &wait;
 
 		if (nr_sects > max_discard_sectors) {
 			bio->bi_size = max_discard_sectors << 9;
@@ -93,8 +91,7 @@
 		bio_get(bio);
 		submit_bio(type, bio);
 
-		if (flags & BLKDEV_IFL_WAIT)
-			wait_for_completion(&wait);
+		wait_for_completion(&wait);
 
 		if (bio_flagged(bio, BIO_EOPNOTSUPP))
 			ret = -EOPNOTSUPP;
@@ -140,7 +137,6 @@
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	BLKDEV_IFL_* flags to control behaviour
  *
  * Description:
  *  Generate and issue number of bios with zerofiled pages.
@@ -149,7 +145,7 @@
  */
 
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+			sector_t nr_sects, gfp_t gfp_mask)
 {
 	int ret;
 	struct bio *bio;
@@ -162,12 +158,6 @@
 	bb.wait = &wait;
 	bb.end_io = NULL;
 
-	if (flags & BLKDEV_IFL_BARRIER) {
-		/* issue async barrier before the data */
-		ret = blkdev_issue_flush(bdev, gfp_mask, NULL, 0);
-		if (ret)
-			return ret;
-	}
 submit:
 	ret = 0;
 	while (nr_sects != 0) {
@@ -181,8 +171,7 @@
 		bio->bi_sector = sector;
 		bio->bi_bdev   = bdev;
 		bio->bi_end_io = bio_batch_end_io;
-		if (flags & BLKDEV_IFL_WAIT)
-			bio->bi_private = &bb;
+		bio->bi_private = &bb;
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
@@ -199,18 +188,10 @@
 		issued++;
 		submit_bio(WRITE, bio);
 	}
-	/*
-	 * When all data bios are in flight. Send final barrier if requeted.
-	 */
-	if (nr_sects == 0 && flags & BLKDEV_IFL_BARRIER)
-		ret = blkdev_issue_flush(bdev, gfp_mask, NULL,
-					flags & BLKDEV_IFL_WAIT);
 
-
-	if (flags & BLKDEV_IFL_WAIT)
-		/* Wait for bios in-flight */
-		while ( issued != atomic_read(&bb.done))
-			wait_for_completion(&wait);
+	/* Wait for bios in-flight */
+	while (issued != atomic_read(&bb.done))
+		wait_for_completion(&wait);
 
 	if (!test_bit(BIO_UPTODATE, &bb.flags))
 		/* One of bios in the batch was completed with error.*/
diff --git a/block/blk-map.c b/block/blk-map.c
index ade0a08..d4a586d 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -54,7 +54,7 @@
 	 * direct dma. else, set up kernel bounce buffers
 	 */
 	uaddr = (unsigned long) ubuf;
-	if (blk_rq_aligned(q, ubuf, len) && !map_data)
+	if (blk_rq_aligned(q, uaddr, len) && !map_data)
 		bio = bio_map_user(q, NULL, uaddr, len, reading, gfp_mask);
 	else
 		bio = bio_copy_user(q, map_data, uaddr, len, reading, gfp_mask);
@@ -288,6 +288,7 @@
 		    unsigned int len, gfp_t gfp_mask)
 {
 	int reading = rq_data_dir(rq) == READ;
+	unsigned long addr = (unsigned long) kbuf;
 	int do_copy = 0;
 	struct bio *bio;
 	int ret;
@@ -297,7 +298,7 @@
 	if (!len || !kbuf)
 		return -EINVAL;
 
-	do_copy = !blk_rq_aligned(q, kbuf, len) || object_is_on_stack(kbuf);
+	do_copy = !blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf);
 	if (do_copy)
 		bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading);
 	else
diff --git a/block/blk-merge.c b/block/blk-merge.c
index eafc94f..0a2fd8a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -205,12 +205,11 @@
 {
 	int nr_phys_segs = bio_phys_segments(q, bio);
 
-	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) {
-		req->cmd_flags |= REQ_NOMERGE;
-		if (req == q->last_merge)
-			q->last_merge = NULL;
-		return 0;
-	}
+	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q))
+		goto no_merge;
+
+	if (bio_integrity(bio) && blk_integrity_merge_bio(q, req, bio))
+		goto no_merge;
 
 	/*
 	 * This will form the start of a new hw segment.  Bump both
@@ -218,6 +217,12 @@
 	 */
 	req->nr_phys_segments += nr_phys_segs;
 	return 1;
+
+no_merge:
+	req->cmd_flags |= REQ_NOMERGE;
+	if (req == q->last_merge)
+		q->last_merge = NULL;
+	return 0;
 }
 
 int ll_back_merge_fn(struct request_queue *q, struct request *req,
@@ -301,6 +306,9 @@
 	if (total_phys_segments > queue_max_segments(q))
 		return 0;
 
+	if (blk_integrity_rq(req) && blk_integrity_merge_rq(q, req, next))
+		return 0;
+
 	/* Merge is OK... */
 	req->nr_phys_segments = total_phys_segments;
 	return 1;
@@ -343,7 +351,7 @@
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+		part = req->part;
 
 		part_round_stats(cpu, part);
 		part_dec_in_flight(part, rq_data_dir(req));
@@ -384,9 +392,6 @@
 	    || next->special)
 		return 0;
 
-	if (blk_integrity_rq(req) != blk_integrity_rq(next))
-		return 0;
-
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn
diff --git a/block/blk-settings.c b/block/blk-settings.c
index a234f4b..701859f 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -111,6 +111,7 @@
 void blk_set_default_limits(struct queue_limits *lim)
 {
 	lim->max_segments = BLK_MAX_SEGMENTS;
+	lim->max_integrity_segments = 0;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = BLK_DEF_MAX_SECTORS;
@@ -213,7 +214,7 @@
 	 */
 	if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
 		dma = 1;
-	q->limits.bounce_pfn = max_low_pfn;
+	q->limits.bounce_pfn = max(max_low_pfn, b_pfn);
 #else
 	if (b_pfn < blk_max_low_pfn)
 		dma = 1;
@@ -343,7 +344,7 @@
  *   hardware can operate on without reverting to read-modify-write
  *   operations.
  */
-void blk_queue_physical_block_size(struct request_queue *q, unsigned short size)
+void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
 {
 	q->limits.physical_block_size = size;
 
@@ -455,11 +456,6 @@
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
-/*
- * Returns the minimum that is _not_ zero, unless both are zero.
- */
-#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
-
 /**
  * blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
  * @t:	the stacking driver (top)
@@ -514,6 +510,8 @@
 					    b->seg_boundary_mask);
 
 	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
+	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
+						 b->max_integrity_segments);
 
 	t->max_segment_size = min_not_zero(t->max_segment_size,
 					   b->max_segment_size);
@@ -794,6 +792,26 @@
 }
 EXPORT_SYMBOL(blk_queue_update_dma_alignment);
 
+/**
+ * blk_queue_flush - configure queue's cache flush capability
+ * @q:		the request queue for the device
+ * @flush:	0, REQ_FLUSH or REQ_FLUSH | REQ_FUA
+ *
+ * Tell block layer cache flush capability of @q.  If it supports
+ * flushing, REQ_FLUSH should be set.  If it supports bypassing
+ * write cache for individual writes, REQ_FUA should be set.
+ */
+void blk_queue_flush(struct request_queue *q, unsigned int flush)
+{
+	WARN_ON_ONCE(flush & ~(REQ_FLUSH | REQ_FUA));
+
+	if (WARN_ON_ONCE(!(flush & REQ_FLUSH) && (flush & REQ_FUA)))
+		flush &= ~REQ_FUA;
+
+	q->flush_flags = flush & (REQ_FLUSH | REQ_FUA);
+}
+EXPORT_SYMBOL_GPL(blk_queue_flush);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 0749b89..da8a8a4 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -112,6 +112,11 @@
 	return queue_var_show(queue_max_segments(q), (page));
 }
 
+static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->limits.max_integrity_segments, (page));
+}
+
 static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
 {
 	if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
@@ -288,6 +293,11 @@
 	.show = queue_max_segments_show,
 };
 
+static struct queue_sysfs_entry queue_max_integrity_segments_entry = {
+	.attr = {.name = "max_integrity_segments", .mode = S_IRUGO },
+	.show = queue_max_integrity_segments_show,
+};
+
 static struct queue_sysfs_entry queue_max_segment_size_entry = {
 	.attr = {.name = "max_segment_size", .mode = S_IRUGO },
 	.show = queue_max_segment_size_show,
@@ -375,6 +385,7 @@
 	&queue_max_hw_sectors_entry.attr,
 	&queue_max_sectors_entry.attr,
 	&queue_max_segments_entry.attr,
+	&queue_max_integrity_segments_entry.attr,
 	&queue_max_segment_size_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
new file mode 100644
index 0000000..56ad453
--- /dev/null
+++ b/block/blk-throttle.c
@@ -0,0 +1,1123 @@
+/*
+ * Interface for controlling IO bandwidth on a request queue
+ *
+ * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/blktrace_api.h>
+#include "blk-cgroup.h"
+
+/* Max dispatch from a group in 1 round */
+static int throtl_grp_quantum = 8;
+
+/* Total max dispatch from all groups in one round */
+static int throtl_quantum = 32;
+
+/* Throttling is performed over 100ms slice and after that slice is renewed */
+static unsigned long throtl_slice = HZ/10;	/* 100 ms */
+
+struct throtl_rb_root {
+	struct rb_root rb;
+	struct rb_node *left;
+	unsigned int count;
+	unsigned long min_disptime;
+};
+
+#define THROTL_RB_ROOT	(struct throtl_rb_root) { .rb = RB_ROOT, .left = NULL, \
+			.count = 0, .min_disptime = 0}
+
+#define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)
+
+struct throtl_grp {
+	/* List of throtl groups on the request queue*/
+	struct hlist_node tg_node;
+
+	/* active throtl group service_tree member */
+	struct rb_node rb_node;
+
+	/*
+	 * Dispatch time in jiffies. This is the estimated time when group
+	 * will unthrottle and is ready to dispatch more bio. It is used as
+	 * key to sort active groups in service tree.
+	 */
+	unsigned long disptime;
+
+	struct blkio_group blkg;
+	atomic_t ref;
+	unsigned int flags;
+
+	/* Two lists for READ and WRITE */
+	struct bio_list bio_lists[2];
+
+	/* Number of queued bios on READ and WRITE lists */
+	unsigned int nr_queued[2];
+
+	/* bytes per second rate limits */
+	uint64_t bps[2];
+
+	/* IOPS limits */
+	unsigned int iops[2];
+
+	/* Number of bytes disptached in current slice */
+	uint64_t bytes_disp[2];
+	/* Number of bio's dispatched in current slice */
+	unsigned int io_disp[2];
+
+	/* When did we start a new slice */
+	unsigned long slice_start[2];
+	unsigned long slice_end[2];
+
+	/* Some throttle limits got updated for the group */
+	bool limits_changed;
+};
+
+struct throtl_data
+{
+	/* List of throtl groups */
+	struct hlist_head tg_list;
+
+	/* service tree for active throtl groups */
+	struct throtl_rb_root tg_service_tree;
+
+	struct throtl_grp root_tg;
+	struct request_queue *queue;
+
+	/* Total Number of queued bios on READ and WRITE lists */
+	unsigned int nr_queued[2];
+
+	/*
+	 * number of total undestroyed groups
+	 */
+	unsigned int nr_undestroyed_grps;
+
+	/* Work for dispatching throttled bios */
+	struct delayed_work throtl_work;
+
+	atomic_t limits_changed;
+};
+
+enum tg_state_flags {
+	THROTL_TG_FLAG_on_rr = 0,	/* on round-robin busy list */
+};
+
+#define THROTL_TG_FNS(name)						\
+static inline void throtl_mark_tg_##name(struct throtl_grp *tg)		\
+{									\
+	(tg)->flags |= (1 << THROTL_TG_FLAG_##name);			\
+}									\
+static inline void throtl_clear_tg_##name(struct throtl_grp *tg)	\
+{									\
+	(tg)->flags &= ~(1 << THROTL_TG_FLAG_##name);			\
+}									\
+static inline int throtl_tg_##name(const struct throtl_grp *tg)		\
+{									\
+	return ((tg)->flags & (1 << THROTL_TG_FLAG_##name)) != 0;	\
+}
+
+THROTL_TG_FNS(on_rr);
+
+#define throtl_log_tg(td, tg, fmt, args...)				\
+	blk_add_trace_msg((td)->queue, "throtl %s " fmt,		\
+				blkg_path(&(tg)->blkg), ##args);      	\
+
+#define throtl_log(td, fmt, args...)	\
+	blk_add_trace_msg((td)->queue, "throtl " fmt, ##args)
+
+static inline struct throtl_grp *tg_of_blkg(struct blkio_group *blkg)
+{
+	if (blkg)
+		return container_of(blkg, struct throtl_grp, blkg);
+
+	return NULL;
+}
+
+static inline int total_nr_queued(struct throtl_data *td)
+{
+	return (td->nr_queued[0] + td->nr_queued[1]);
+}
+
+static inline struct throtl_grp *throtl_ref_get_tg(struct throtl_grp *tg)
+{
+	atomic_inc(&tg->ref);
+	return tg;
+}
+
+static void throtl_put_tg(struct throtl_grp *tg)
+{
+	BUG_ON(atomic_read(&tg->ref) <= 0);
+	if (!atomic_dec_and_test(&tg->ref))
+		return;
+	kfree(tg);
+}
+
+static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
+			struct cgroup *cgroup)
+{
+	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+	struct throtl_grp *tg = NULL;
+	void *key = td;
+	struct backing_dev_info *bdi = &td->queue->backing_dev_info;
+	unsigned int major, minor;
+
+	/*
+	 * TODO: Speed up blkiocg_lookup_group() by maintaining a radix
+	 * tree of blkg (instead of traversing through hash list all
+	 * the time.
+	 */
+	tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
+
+	/* Fill in device details for root group */
+	if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		tg->blkg.dev = MKDEV(major, minor);
+		goto done;
+	}
+
+	if (tg)
+		goto done;
+
+	tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
+	if (!tg)
+		goto done;
+
+	INIT_HLIST_NODE(&tg->tg_node);
+	RB_CLEAR_NODE(&tg->rb_node);
+	bio_list_init(&tg->bio_lists[0]);
+	bio_list_init(&tg->bio_lists[1]);
+
+	/*
+	 * Take the initial reference that will be released on destroy
+	 * This can be thought of a joint reference by cgroup and
+	 * request queue which will be dropped by either request queue
+	 * exit or cgroup deletion path depending on who is exiting first.
+	 */
+	atomic_set(&tg->ref, 1);
+
+	/* Add group onto cgroup list */
+	sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+	blkiocg_add_blkio_group(blkcg, &tg->blkg, (void *)td,
+				MKDEV(major, minor), BLKIO_POLICY_THROTL);
+
+	tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev);
+	tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev);
+	tg->iops[READ] = blkcg_get_read_iops(blkcg, tg->blkg.dev);
+	tg->iops[WRITE] = blkcg_get_write_iops(blkcg, tg->blkg.dev);
+
+	hlist_add_head(&tg->tg_node, &td->tg_list);
+	td->nr_undestroyed_grps++;
+done:
+	return tg;
+}
+
+static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
+{
+	struct cgroup *cgroup;
+	struct throtl_grp *tg = NULL;
+
+	rcu_read_lock();
+	cgroup = task_cgroup(current, blkio_subsys_id);
+	tg = throtl_find_alloc_tg(td, cgroup);
+	if (!tg)
+		tg = &td->root_tg;
+	rcu_read_unlock();
+	return tg;
+}
+
+static struct throtl_grp *throtl_rb_first(struct throtl_rb_root *root)
+{
+	/* Service tree is empty */
+	if (!root->count)
+		return NULL;
+
+	if (!root->left)
+		root->left = rb_first(&root->rb);
+
+	if (root->left)
+		return rb_entry_tg(root->left);
+
+	return NULL;
+}
+
+static void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+
+static void throtl_rb_erase(struct rb_node *n, struct throtl_rb_root *root)
+{
+	if (root->left == n)
+		root->left = NULL;
+	rb_erase_init(n, &root->rb);
+	--root->count;
+}
+
+static void update_min_dispatch_time(struct throtl_rb_root *st)
+{
+	struct throtl_grp *tg;
+
+	tg = throtl_rb_first(st);
+	if (!tg)
+		return;
+
+	st->min_disptime = tg->disptime;
+}
+
+static void
+tg_service_tree_add(struct throtl_rb_root *st, struct throtl_grp *tg)
+{
+	struct rb_node **node = &st->rb.rb_node;
+	struct rb_node *parent = NULL;
+	struct throtl_grp *__tg;
+	unsigned long key = tg->disptime;
+	int left = 1;
+
+	while (*node != NULL) {
+		parent = *node;
+		__tg = rb_entry_tg(parent);
+
+		if (time_before(key, __tg->disptime))
+			node = &parent->rb_left;
+		else {
+			node = &parent->rb_right;
+			left = 0;
+		}
+	}
+
+	if (left)
+		st->left = &tg->rb_node;
+
+	rb_link_node(&tg->rb_node, parent, node);
+	rb_insert_color(&tg->rb_node, &st->rb);
+}
+
+static void __throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	struct throtl_rb_root *st = &td->tg_service_tree;
+
+	tg_service_tree_add(st, tg);
+	throtl_mark_tg_on_rr(tg);
+	st->count++;
+}
+
+static void throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	if (!throtl_tg_on_rr(tg))
+		__throtl_enqueue_tg(td, tg);
+}
+
+static void __throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	throtl_rb_erase(&tg->rb_node, &td->tg_service_tree);
+	throtl_clear_tg_on_rr(tg);
+}
+
+static void throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	if (throtl_tg_on_rr(tg))
+		__throtl_dequeue_tg(td, tg);
+}
+
+static void throtl_schedule_next_dispatch(struct throtl_data *td)
+{
+	struct throtl_rb_root *st = &td->tg_service_tree;
+
+	/*
+	 * If there are more bios pending, schedule more work.
+	 */
+	if (!total_nr_queued(td))
+		return;
+
+	BUG_ON(!st->count);
+
+	update_min_dispatch_time(st);
+
+	if (time_before_eq(st->min_disptime, jiffies))
+		throtl_schedule_delayed_work(td->queue, 0);
+	else
+		throtl_schedule_delayed_work(td->queue,
+				(st->min_disptime - jiffies));
+}
+
+static inline void
+throtl_start_new_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+	tg->bytes_disp[rw] = 0;
+	tg->io_disp[rw] = 0;
+	tg->slice_start[rw] = jiffies;
+	tg->slice_end[rw] = jiffies + throtl_slice;
+	throtl_log_tg(td, tg, "[%c] new slice start=%lu end=%lu jiffies=%lu",
+			rw == READ ? 'R' : 'W', tg->slice_start[rw],
+			tg->slice_end[rw], jiffies);
+}
+
+static inline void throtl_extend_slice(struct throtl_data *td,
+		struct throtl_grp *tg, bool rw, unsigned long jiffy_end)
+{
+	tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+	throtl_log_tg(td, tg, "[%c] extend slice start=%lu end=%lu jiffies=%lu",
+			rw == READ ? 'R' : 'W', tg->slice_start[rw],
+			tg->slice_end[rw], jiffies);
+}
+
+/* Determine if previously allocated or extended slice is complete or not */
+static bool
+throtl_slice_used(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+	if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw]))
+		return 0;
+
+	return 1;
+}
+
+/* Trim the used slices and adjust slice start accordingly */
+static inline void
+throtl_trim_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
+{
+	unsigned long nr_slices, time_elapsed, io_trim;
+	u64 bytes_trim, tmp;
+
+	BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
+
+	/*
+	 * If bps are unlimited (-1), then time slice don't get
+	 * renewed. Don't try to trim the slice if slice is used. A new
+	 * slice will start when appropriate.
+	 */
+	if (throtl_slice_used(td, tg, rw))
+		return;
+
+	time_elapsed = jiffies - tg->slice_start[rw];
+
+	nr_slices = time_elapsed / throtl_slice;
+
+	if (!nr_slices)
+		return;
+	tmp = tg->bps[rw] * throtl_slice * nr_slices;
+	do_div(tmp, HZ);
+	bytes_trim = tmp;
+
+	io_trim = (tg->iops[rw] * throtl_slice * nr_slices)/HZ;
+
+	if (!bytes_trim && !io_trim)
+		return;
+
+	if (tg->bytes_disp[rw] >= bytes_trim)
+		tg->bytes_disp[rw] -= bytes_trim;
+	else
+		tg->bytes_disp[rw] = 0;
+
+	if (tg->io_disp[rw] >= io_trim)
+		tg->io_disp[rw] -= io_trim;
+	else
+		tg->io_disp[rw] = 0;
+
+	tg->slice_start[rw] += nr_slices * throtl_slice;
+
+	throtl_log_tg(td, tg, "[%c] trim slice nr=%lu bytes=%llu io=%lu"
+			" start=%lu end=%lu jiffies=%lu",
+			rw == READ ? 'R' : 'W', nr_slices, bytes_trim, io_trim,
+			tg->slice_start[rw], tg->slice_end[rw], jiffies);
+}
+
+static bool tg_with_in_iops_limit(struct throtl_data *td, struct throtl_grp *tg,
+		struct bio *bio, unsigned long *wait)
+{
+	bool rw = bio_data_dir(bio);
+	unsigned int io_allowed;
+	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
+	u64 tmp;
+
+	jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
+
+	/* Slice has just started. Consider one slice interval */
+	if (!jiffy_elapsed)
+		jiffy_elapsed_rnd = throtl_slice;
+
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+
+	/*
+	 * jiffy_elapsed_rnd should not be a big value as minimum iops can be
+	 * 1 then at max jiffy elapsed should be equivalent of 1 second as we
+	 * will allow dispatch after 1 second and after that slice should
+	 * have been trimmed.
+	 */
+
+	tmp = (u64)tg->iops[rw] * jiffy_elapsed_rnd;
+	do_div(tmp, HZ);
+
+	if (tmp > UINT_MAX)
+		io_allowed = UINT_MAX;
+	else
+		io_allowed = tmp;
+
+	if (tg->io_disp[rw] + 1 <= io_allowed) {
+		if (wait)
+			*wait = 0;
+		return 1;
+	}
+
+	/* Calc approx time to dispatch */
+	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ)/tg->iops[rw] + 1;
+
+	if (jiffy_wait > jiffy_elapsed)
+		jiffy_wait = jiffy_wait - jiffy_elapsed;
+	else
+		jiffy_wait = 1;
+
+	if (wait)
+		*wait = jiffy_wait;
+	return 0;
+}
+
+static bool tg_with_in_bps_limit(struct throtl_data *td, struct throtl_grp *tg,
+		struct bio *bio, unsigned long *wait)
+{
+	bool rw = bio_data_dir(bio);
+	u64 bytes_allowed, extra_bytes, tmp;
+	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
+
+	jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
+
+	/* Slice has just started. Consider one slice interval */
+	if (!jiffy_elapsed)
+		jiffy_elapsed_rnd = throtl_slice;
+
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+
+	tmp = tg->bps[rw] * jiffy_elapsed_rnd;
+	do_div(tmp, HZ);
+	bytes_allowed = tmp;
+
+	if (tg->bytes_disp[rw] + bio->bi_size <= bytes_allowed) {
+		if (wait)
+			*wait = 0;
+		return 1;
+	}
+
+	/* Calc approx time to dispatch */
+	extra_bytes = tg->bytes_disp[rw] + bio->bi_size - bytes_allowed;
+	jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
+
+	if (!jiffy_wait)
+		jiffy_wait = 1;
+
+	/*
+	 * This wait time is without taking into consideration the rounding
+	 * up we did. Add that time also.
+	 */
+	jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed);
+	if (wait)
+		*wait = jiffy_wait;
+	return 0;
+}
+
+/*
+ * Returns whether one can dispatch a bio or not. Also returns approx number
+ * of jiffies to wait before this bio is with-in IO rate and can be dispatched
+ */
+static bool tg_may_dispatch(struct throtl_data *td, struct throtl_grp *tg,
+				struct bio *bio, unsigned long *wait)
+{
+	bool rw = bio_data_dir(bio);
+	unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0;
+
+	/*
+ 	 * Currently whole state machine of group depends on first bio
+	 * queued in the group bio list. So one should not be calling
+	 * this function with a different bio if there are other bios
+	 * queued.
+	 */
+	BUG_ON(tg->nr_queued[rw] && bio != bio_list_peek(&tg->bio_lists[rw]));
+
+	/* If tg->bps = -1, then BW is unlimited */
+	if (tg->bps[rw] == -1 && tg->iops[rw] == -1) {
+		if (wait)
+			*wait = 0;
+		return 1;
+	}
+
+	/*
+	 * If previous slice expired, start a new one otherwise renew/extend
+	 * existing slice to make sure it is at least throtl_slice interval
+	 * long since now.
+	 */
+	if (throtl_slice_used(td, tg, rw))
+		throtl_start_new_slice(td, tg, rw);
+	else {
+		if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
+			throtl_extend_slice(td, tg, rw, jiffies + throtl_slice);
+	}
+
+	if (tg_with_in_bps_limit(td, tg, bio, &bps_wait)
+	    && tg_with_in_iops_limit(td, tg, bio, &iops_wait)) {
+		if (wait)
+			*wait = 0;
+		return 1;
+	}
+
+	max_wait = max(bps_wait, iops_wait);
+
+	if (wait)
+		*wait = max_wait;
+
+	if (time_before(tg->slice_end[rw], jiffies + max_wait))
+		throtl_extend_slice(td, tg, rw, jiffies + max_wait);
+
+	return 0;
+}
+
+static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
+{
+	bool rw = bio_data_dir(bio);
+	bool sync = bio->bi_rw & REQ_SYNC;
+
+	/* Charge the bio to the group */
+	tg->bytes_disp[rw] += bio->bi_size;
+	tg->io_disp[rw]++;
+
+	/*
+	 * TODO: This will take blkg->stats_lock. Figure out a way
+	 * to avoid this cost.
+	 */
+	blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, rw, sync);
+}
+
+static void throtl_add_bio_tg(struct throtl_data *td, struct throtl_grp *tg,
+			struct bio *bio)
+{
+	bool rw = bio_data_dir(bio);
+
+	bio_list_add(&tg->bio_lists[rw], bio);
+	/* Take a bio reference on tg */
+	throtl_ref_get_tg(tg);
+	tg->nr_queued[rw]++;
+	td->nr_queued[rw]++;
+	throtl_enqueue_tg(td, tg);
+}
+
+static void tg_update_disptime(struct throtl_data *td, struct throtl_grp *tg)
+{
+	unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime;
+	struct bio *bio;
+
+	if ((bio = bio_list_peek(&tg->bio_lists[READ])))
+		tg_may_dispatch(td, tg, bio, &read_wait);
+
+	if ((bio = bio_list_peek(&tg->bio_lists[WRITE])))
+		tg_may_dispatch(td, tg, bio, &write_wait);
+
+	min_wait = min(read_wait, write_wait);
+	disptime = jiffies + min_wait;
+
+	/* Update dispatch time */
+	throtl_dequeue_tg(td, tg);
+	tg->disptime = disptime;
+	throtl_enqueue_tg(td, tg);
+}
+
+static void tg_dispatch_one_bio(struct throtl_data *td, struct throtl_grp *tg,
+				bool rw, struct bio_list *bl)
+{
+	struct bio *bio;
+
+	bio = bio_list_pop(&tg->bio_lists[rw]);
+	tg->nr_queued[rw]--;
+	/* Drop bio reference on tg */
+	throtl_put_tg(tg);
+
+	BUG_ON(td->nr_queued[rw] <= 0);
+	td->nr_queued[rw]--;
+
+	throtl_charge_bio(tg, bio);
+	bio_list_add(bl, bio);
+	bio->bi_rw |= REQ_THROTTLED;
+
+	throtl_trim_slice(td, tg, rw);
+}
+
+static int throtl_dispatch_tg(struct throtl_data *td, struct throtl_grp *tg,
+				struct bio_list *bl)
+{
+	unsigned int nr_reads = 0, nr_writes = 0;
+	unsigned int max_nr_reads = throtl_grp_quantum*3/4;
+	unsigned int max_nr_writes = throtl_grp_quantum - nr_reads;
+	struct bio *bio;
+
+	/* Try to dispatch 75% READS and 25% WRITES */
+
+	while ((bio = bio_list_peek(&tg->bio_lists[READ]))
+		&& tg_may_dispatch(td, tg, bio, NULL)) {
+
+		tg_dispatch_one_bio(td, tg, bio_data_dir(bio), bl);
+		nr_reads++;
+
+		if (nr_reads >= max_nr_reads)
+			break;
+	}
+
+	while ((bio = bio_list_peek(&tg->bio_lists[WRITE]))
+		&& tg_may_dispatch(td, tg, bio, NULL)) {
+
+		tg_dispatch_one_bio(td, tg, bio_data_dir(bio), bl);
+		nr_writes++;
+
+		if (nr_writes >= max_nr_writes)
+			break;
+	}
+
+	return nr_reads + nr_writes;
+}
+
+static int throtl_select_dispatch(struct throtl_data *td, struct bio_list *bl)
+{
+	unsigned int nr_disp = 0;
+	struct throtl_grp *tg;
+	struct throtl_rb_root *st = &td->tg_service_tree;
+
+	while (1) {
+		tg = throtl_rb_first(st);
+
+		if (!tg)
+			break;
+
+		if (time_before(jiffies, tg->disptime))
+			break;
+
+		throtl_dequeue_tg(td, tg);
+
+		nr_disp += throtl_dispatch_tg(td, tg, bl);
+
+		if (tg->nr_queued[0] || tg->nr_queued[1]) {
+			tg_update_disptime(td, tg);
+			throtl_enqueue_tg(td, tg);
+		}
+
+		if (nr_disp >= throtl_quantum)
+			break;
+	}
+
+	return nr_disp;
+}
+
+static void throtl_process_limit_change(struct throtl_data *td)
+{
+	struct throtl_grp *tg;
+	struct hlist_node *pos, *n;
+
+	/*
+	 * Make sure atomic_inc() effects from
+	 * throtl_update_blkio_group_read_bps(), group of functions are
+	 * visible.
+	 * Is this required or smp_mb__after_atomic_inc() was suffcient
+	 * after the atomic_inc().
+	 */
+	smp_rmb();
+	if (!atomic_read(&td->limits_changed))
+		return;
+
+	throtl_log(td, "limit changed =%d", atomic_read(&td->limits_changed));
+
+	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
+		/*
+		 * Do I need an smp_rmb() here to make sure tg->limits_changed
+		 * update is visible. I am relying on smp_rmb() at the
+		 * beginning of function and not putting a new one here.
+		 */
+
+		if (throtl_tg_on_rr(tg) && tg->limits_changed) {
+			throtl_log_tg(td, tg, "limit change rbps=%llu wbps=%llu"
+				" riops=%u wiops=%u", tg->bps[READ],
+				tg->bps[WRITE], tg->iops[READ],
+				tg->iops[WRITE]);
+			tg_update_disptime(td, tg);
+			tg->limits_changed = false;
+		}
+	}
+
+	smp_mb__before_atomic_dec();
+	atomic_dec(&td->limits_changed);
+	smp_mb__after_atomic_dec();
+}
+
+/* Dispatch throttled bios. Should be called without queue lock held. */
+static int throtl_dispatch(struct request_queue *q)
+{
+	struct throtl_data *td = q->td;
+	unsigned int nr_disp = 0;
+	struct bio_list bio_list_on_stack;
+	struct bio *bio;
+
+	spin_lock_irq(q->queue_lock);
+
+	throtl_process_limit_change(td);
+
+	if (!total_nr_queued(td))
+		goto out;
+
+	bio_list_init(&bio_list_on_stack);
+
+	throtl_log(td, "dispatch nr_queued=%lu read=%u write=%u",
+			total_nr_queued(td), td->nr_queued[READ],
+			td->nr_queued[WRITE]);
+
+	nr_disp = throtl_select_dispatch(td, &bio_list_on_stack);
+
+	if (nr_disp)
+		throtl_log(td, "bios disp=%u", nr_disp);
+
+	throtl_schedule_next_dispatch(td);
+out:
+	spin_unlock_irq(q->queue_lock);
+
+	/*
+	 * If we dispatched some requests, unplug the queue to make sure
+	 * immediate dispatch
+	 */
+	if (nr_disp) {
+		while((bio = bio_list_pop(&bio_list_on_stack)))
+			generic_make_request(bio);
+		blk_unplug(q);
+	}
+	return nr_disp;
+}
+
+void blk_throtl_work(struct work_struct *work)
+{
+	struct throtl_data *td = container_of(work, struct throtl_data,
+					throtl_work.work);
+	struct request_queue *q = td->queue;
+
+	throtl_dispatch(q);
+}
+
+/* Call with queue lock held */
+void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay)
+{
+
+	struct throtl_data *td = q->td;
+	struct delayed_work *dwork = &td->throtl_work;
+
+	if (total_nr_queued(td) > 0) {
+		/*
+		 * We might have a work scheduled to be executed in future.
+		 * Cancel that and schedule a new one.
+		 */
+		__cancel_delayed_work(dwork);
+		kblockd_schedule_delayed_work(q, dwork, delay);
+		throtl_log(td, "schedule work. delay=%lu jiffies=%lu",
+				delay, jiffies);
+	}
+}
+EXPORT_SYMBOL(throtl_schedule_delayed_work);
+
+static void
+throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg)
+{
+	/* Something wrong if we are trying to remove same group twice */
+	BUG_ON(hlist_unhashed(&tg->tg_node));
+
+	hlist_del_init(&tg->tg_node);
+
+	/*
+	 * Put the reference taken at the time of creation so that when all
+	 * queues are gone, group can be destroyed.
+	 */
+	throtl_put_tg(tg);
+	td->nr_undestroyed_grps--;
+}
+
+static void throtl_release_tgs(struct throtl_data *td)
+{
+	struct hlist_node *pos, *n;
+	struct throtl_grp *tg;
+
+	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
+		/*
+		 * If cgroup removal path got to blk_group first and removed
+		 * it from cgroup list, then it will take care of destroying
+		 * cfqg also.
+		 */
+		if (!blkiocg_del_blkio_group(&tg->blkg))
+			throtl_destroy_tg(td, tg);
+	}
+}
+
+static void throtl_td_free(struct throtl_data *td)
+{
+	kfree(td);
+}
+
+/*
+ * Blk cgroup controller notification saying that blkio_group object is being
+ * delinked as associated cgroup object is going away. That also means that
+ * no new IO will come in this group. So get rid of this group as soon as
+ * any pending IO in the group is finished.
+ *
+ * This function is called under rcu_read_lock(). key is the rcu protected
+ * pointer. That means "key" is a valid throtl_data pointer as long as we are
+ * rcu read lock.
+ *
+ * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
+ * it should not be NULL as even if queue was going away, cgroup deltion
+ * path got to it first.
+ */
+void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg)
+{
+	unsigned long flags;
+	struct throtl_data *td = key;
+
+	spin_lock_irqsave(td->queue->queue_lock, flags);
+	throtl_destroy_tg(td, tg_of_blkg(blkg));
+	spin_unlock_irqrestore(td->queue->queue_lock, flags);
+}
+
+/*
+ * For all update functions, key should be a valid pointer because these
+ * update functions are called under blkcg_lock, that means, blkg is
+ * valid and in turn key is valid. queue exit path can not race becuase
+ * of blkcg_lock
+ *
+ * Can not take queue lock in update functions as queue lock under blkcg_lock
+ * is not allowed. Under other paths we take blkcg_lock under queue_lock.
+ */
+static void throtl_update_blkio_group_read_bps(void *key,
+				struct blkio_group *blkg, u64 read_bps)
+{
+	struct throtl_data *td = key;
+
+	tg_of_blkg(blkg)->bps[READ] = read_bps;
+	/* Make sure read_bps is updated before setting limits_changed */
+	smp_wmb();
+	tg_of_blkg(blkg)->limits_changed = true;
+
+	/* Make sure tg->limits_changed is updated before td->limits_changed */
+	smp_mb__before_atomic_inc();
+	atomic_inc(&td->limits_changed);
+	smp_mb__after_atomic_inc();
+
+	/* Schedule a work now to process the limit change */
+	throtl_schedule_delayed_work(td->queue, 0);
+}
+
+static void throtl_update_blkio_group_write_bps(void *key,
+				struct blkio_group *blkg, u64 write_bps)
+{
+	struct throtl_data *td = key;
+
+	tg_of_blkg(blkg)->bps[WRITE] = write_bps;
+	smp_wmb();
+	tg_of_blkg(blkg)->limits_changed = true;
+	smp_mb__before_atomic_inc();
+	atomic_inc(&td->limits_changed);
+	smp_mb__after_atomic_inc();
+	throtl_schedule_delayed_work(td->queue, 0);
+}
+
+static void throtl_update_blkio_group_read_iops(void *key,
+			struct blkio_group *blkg, unsigned int read_iops)
+{
+	struct throtl_data *td = key;
+
+	tg_of_blkg(blkg)->iops[READ] = read_iops;
+	smp_wmb();
+	tg_of_blkg(blkg)->limits_changed = true;
+	smp_mb__before_atomic_inc();
+	atomic_inc(&td->limits_changed);
+	smp_mb__after_atomic_inc();
+	throtl_schedule_delayed_work(td->queue, 0);
+}
+
+static void throtl_update_blkio_group_write_iops(void *key,
+			struct blkio_group *blkg, unsigned int write_iops)
+{
+	struct throtl_data *td = key;
+
+	tg_of_blkg(blkg)->iops[WRITE] = write_iops;
+	smp_wmb();
+	tg_of_blkg(blkg)->limits_changed = true;
+	smp_mb__before_atomic_inc();
+	atomic_inc(&td->limits_changed);
+	smp_mb__after_atomic_inc();
+	throtl_schedule_delayed_work(td->queue, 0);
+}
+
+void throtl_shutdown_timer_wq(struct request_queue *q)
+{
+	struct throtl_data *td = q->td;
+
+	cancel_delayed_work_sync(&td->throtl_work);
+}
+
+static struct blkio_policy_type blkio_policy_throtl = {
+	.ops = {
+		.blkio_unlink_group_fn = throtl_unlink_blkio_group,
+		.blkio_update_group_read_bps_fn =
+					throtl_update_blkio_group_read_bps,
+		.blkio_update_group_write_bps_fn =
+					throtl_update_blkio_group_write_bps,
+		.blkio_update_group_read_iops_fn =
+					throtl_update_blkio_group_read_iops,
+		.blkio_update_group_write_iops_fn =
+					throtl_update_blkio_group_write_iops,
+	},
+	.plid = BLKIO_POLICY_THROTL,
+};
+
+int blk_throtl_bio(struct request_queue *q, struct bio **biop)
+{
+	struct throtl_data *td = q->td;
+	struct throtl_grp *tg;
+	struct bio *bio = *biop;
+	bool rw = bio_data_dir(bio), update_disptime = true;
+
+	if (bio->bi_rw & REQ_THROTTLED) {
+		bio->bi_rw &= ~REQ_THROTTLED;
+		return 0;
+	}
+
+	spin_lock_irq(q->queue_lock);
+	tg = throtl_get_tg(td);
+
+	if (tg->nr_queued[rw]) {
+		/*
+		 * There is already another bio queued in same dir. No
+		 * need to update dispatch time.
+		 * Still update the disptime if rate limits on this group
+		 * were changed.
+		 */
+		if (!tg->limits_changed)
+			update_disptime = false;
+		else
+			tg->limits_changed = false;
+
+		goto queue_bio;
+	}
+
+	/* Bio is with-in rate limit of group */
+	if (tg_may_dispatch(td, tg, bio, NULL)) {
+		throtl_charge_bio(tg, bio);
+		goto out;
+	}
+
+queue_bio:
+	throtl_log_tg(td, tg, "[%c] bio. bdisp=%u sz=%u bps=%llu"
+			" iodisp=%u iops=%u queued=%d/%d",
+			rw == READ ? 'R' : 'W',
+			tg->bytes_disp[rw], bio->bi_size, tg->bps[rw],
+			tg->io_disp[rw], tg->iops[rw],
+			tg->nr_queued[READ], tg->nr_queued[WRITE]);
+
+	throtl_add_bio_tg(q->td, tg, bio);
+	*biop = NULL;
+
+	if (update_disptime) {
+		tg_update_disptime(td, tg);
+		throtl_schedule_next_dispatch(td);
+	}
+
+out:
+	spin_unlock_irq(q->queue_lock);
+	return 0;
+}
+
+int blk_throtl_init(struct request_queue *q)
+{
+	struct throtl_data *td;
+	struct throtl_grp *tg;
+
+	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
+	if (!td)
+		return -ENOMEM;
+
+	INIT_HLIST_HEAD(&td->tg_list);
+	td->tg_service_tree = THROTL_RB_ROOT;
+	atomic_set(&td->limits_changed, 0);
+
+	/* Init root group */
+	tg = &td->root_tg;
+	INIT_HLIST_NODE(&tg->tg_node);
+	RB_CLEAR_NODE(&tg->rb_node);
+	bio_list_init(&tg->bio_lists[0]);
+	bio_list_init(&tg->bio_lists[1]);
+
+	/* Practically unlimited BW */
+	tg->bps[0] = tg->bps[1] = -1;
+	tg->iops[0] = tg->iops[1] = -1;
+
+	/*
+	 * Set root group reference to 2. One reference will be dropped when
+	 * all groups on tg_list are being deleted during queue exit. Other
+	 * reference will remain there as we don't want to delete this group
+	 * as it is statically allocated and gets destroyed when throtl_data
+	 * goes away.
+	 */
+	atomic_set(&tg->ref, 2);
+	hlist_add_head(&tg->tg_node, &td->tg_list);
+	td->nr_undestroyed_grps++;
+
+	INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work);
+
+	rcu_read_lock();
+	blkiocg_add_blkio_group(&blkio_root_cgroup, &tg->blkg, (void *)td,
+					0, BLKIO_POLICY_THROTL);
+	rcu_read_unlock();
+
+	/* Attach throtl data to request queue */
+	td->queue = q;
+	q->td = td;
+	return 0;
+}
+
+void blk_throtl_exit(struct request_queue *q)
+{
+	struct throtl_data *td = q->td;
+	bool wait = false;
+
+	BUG_ON(!td);
+
+	throtl_shutdown_timer_wq(q);
+
+	spin_lock_irq(q->queue_lock);
+	throtl_release_tgs(td);
+
+	/* If there are other groups */
+	if (td->nr_undestroyed_grps > 0)
+		wait = true;
+
+	spin_unlock_irq(q->queue_lock);
+
+	/*
+	 * Wait for tg->blkg->key accessors to exit their grace periods.
+	 * Do this wait only if there are other undestroyed groups out
+	 * there (other than root group). This can happen if cgroup deletion
+	 * path claimed the responsibility of cleaning up a group before
+	 * queue cleanup code get to the group.
+	 *
+	 * Do not call synchronize_rcu() unconditionally as there are drivers
+	 * which create/delete request queue hundreds of times during scan/boot
+	 * and synchronize_rcu() can take significant time and slow down boot.
+	 */
+	if (wait)
+		synchronize_rcu();
+
+	/*
+	 * Just being safe to make sure after previous flush if some body did
+	 * update limits through cgroup and another work got queued, cancel
+	 * it.
+	 */
+	throtl_shutdown_timer_wq(q);
+	throtl_td_free(td);
+}
+
+static int __init throtl_init(void)
+{
+	blkio_policy_register(&blkio_policy_throtl);
+	return 0;
+}
+
+module_init(throtl_init);
diff --git a/block/blk.h b/block/blk.h
index d6b911a..1e675e5 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -51,6 +51,8 @@
  */
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
+struct request *blk_do_flush(struct request_queue *q, struct request *rq);
+
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
 	struct request *rq;
@@ -58,7 +60,11 @@
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
-			if (blk_do_ordered(q, &rq))
+			if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) ||
+			    rq == &q->flush_rq)
+				return rq;
+			rq = blk_do_flush(q, rq);
+			if (rq)
 				return rq;
 		}
 
@@ -110,10 +116,6 @@
 
 int blk_dev_init(void);
 
-void elv_quiesce_start(struct request_queue *q);
-void elv_quiesce_end(struct request_queue *q);
-
-
 /*
  * Return the threshold (number of used requests) at which the queue is
  * considered to be congested.  It include a little hysteresis to keep the
@@ -132,14 +134,6 @@
 	return q->nr_congestion_off;
 }
 
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-
-#define rq_for_each_integrity_segment(bvl, _rq, _iter)		\
-	__rq_for_each_bio(_iter.bio, _rq)			\
-		bip_for_each_vec(bvl, _iter.bio->bi_integrity, _iter.i)
-
-#endif /* BLK_DEV_INTEGRITY */
-
 static inline int blk_cpu_to_group(int cpu)
 {
 	int group = NR_CPUS;
diff --git a/block/bsg.c b/block/bsg.c
index 0c00870..f20d6a7 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -20,7 +20,6 @@
 #include <linux/uio.h>
 #include <linux/idr.h>
 #include <linux/bsg.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 
 #include <scsi/scsi.h>
@@ -843,9 +842,7 @@
 {
 	struct bsg_device *bd;
 
-	lock_kernel();
 	bd = bsg_get_device(inode, file);
-	unlock_kernel();
 
 	if (IS_ERR(bd))
 		return PTR_ERR(bd);
@@ -968,6 +965,7 @@
 	.release	=	bsg_release,
 	.unlocked_ioctl	=	bsg_ioctl,
 	.owner		=	THIS_MODULE,
+	.llseek		=	default_llseek,
 };
 
 void bsg_unregister_queue(struct request_queue *q)
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 9eba291..4cd59b0 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -160,6 +160,7 @@
 	BE_WORKLOAD = 0,
 	RT_WORKLOAD = 1,
 	IDLE_WORKLOAD = 2,
+	CFQ_PRIO_NR,
 };
 
 /*
@@ -184,10 +185,19 @@
 	/* number of cfqq currently on this group */
 	int nr_cfqq;
 
-	/* Per group busy queus average. Useful for workload slice calc. */
-	unsigned int busy_queues_avg[2];
 	/*
-	 * rr lists of queues with requests, onle rr for each priority class.
+	 * Per group busy queus average. Useful for workload slice calc. We
+	 * create the array for each prio class but at run time it is used
+	 * only for RT and BE class and slot for IDLE class remains unused.
+	 * This is primarily done to avoid confusion and a gcc warning.
+	 */
+	unsigned int busy_queues_avg[CFQ_PRIO_NR];
+	/*
+	 * rr lists of queues with requests. We maintain service trees for
+	 * RT and BE classes. These trees are subdivided in subclasses
+	 * of SYNC, SYNC_NOIDLE and ASYNC based on workload type. For IDLE
+	 * class there is no subclassification and all the cfq queues go on
+	 * a single tree service_tree_idle.
 	 * Counts are embedded in the cfq_rb_root
 	 */
 	struct cfq_rb_root service_trees[2][3];
@@ -221,7 +231,6 @@
 	enum wl_type_t serving_type;
 	unsigned long workload_expires;
 	struct cfq_group *serving_group;
-	bool noidle_tree_requires_idle;
 
 	/*
 	 * Each priority tree is sorted by next_request position.  These
@@ -977,8 +986,8 @@
 	return NULL;
 }
 
-void
-cfq_update_blkio_group_weight(struct blkio_group *blkg, unsigned int weight)
+void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
+					unsigned int weight)
 {
 	cfqg_of_blkg(blkg)->weight = weight;
 }
@@ -2180,7 +2189,6 @@
 	slice = max_t(unsigned, slice, CFQ_MIN_TT);
 	cfq_log(cfqd, "workload slice:%d", slice);
 	cfqd->workload_expires = jiffies + slice;
-	cfqd->noidle_tree_requires_idle = false;
 }
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
@@ -3177,7 +3185,9 @@
 	if (cfqq->queued[0] + cfqq->queued[1] >= 4)
 		cfq_mark_cfqq_deep(cfqq);
 
-	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
+	if (cfqq->next_rq && (cfqq->next_rq->cmd_flags & REQ_NOIDLE))
+		enable_idle = 0;
+	else if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
 	    (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
@@ -3494,17 +3504,7 @@
 			cfq_slice_expired(cfqd, 1);
 		else if (sync && cfqq_empty &&
 			 !cfq_close_cooperator(cfqd, cfqq)) {
-			cfqd->noidle_tree_requires_idle |=
-				!(rq->cmd_flags & REQ_NOIDLE);
-			/*
-			 * Idling is enabled for SYNC_WORKLOAD.
-			 * SYNC_NOIDLE_WORKLOAD idles at the end of the tree
-			 * only if we processed at least one !REQ_NOIDLE request
-			 */
-			if (cfqd->serving_type == SYNC_WORKLOAD
-			    || cfqd->noidle_tree_requires_idle
-			    || cfqq->cfqg->nr_cfqq == 1)
-				cfq_arm_slice_timer(cfqd);
+			cfq_arm_slice_timer(cfqd);
 		}
 	}
 
@@ -4090,6 +4090,7 @@
 		.blkio_unlink_group_fn =	cfq_unlink_blkio_group,
 		.blkio_update_group_weight_fn =	cfq_update_blkio_group_weight,
 	},
+	.plid = BLKIO_POLICY_PROP,
 };
 #else
 static struct blkio_policy_type blkio_policy_cfq;
diff --git a/block/cfq.h b/block/cfq.h
index 93448e5..54a6d90 100644
--- a/block/cfq.h
+++ b/block/cfq.h
@@ -69,7 +69,7 @@
 
 static inline void cfq_blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 			struct blkio_group *blkg, void *key, dev_t dev) {
-	blkiocg_add_blkio_group(blkcg, blkg, key, dev);
+	blkiocg_add_blkio_group(blkcg, blkg, key, dev, BLKIO_POLICY_PROP);
 }
 
 static inline int cfq_blkiocg_del_blkio_group(struct blkio_group *blkg)
diff --git a/block/elevator.c b/block/elevator.c
index 4e11559..282e830 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -617,8 +617,6 @@
 
 void elv_insert(struct request_queue *q, struct request *rq, int where)
 {
-	struct list_head *pos;
-	unsigned ordseq;
 	int unplug_it = 1;
 
 	trace_block_rq_insert(q, rq);
@@ -626,9 +624,16 @@
 	rq->q = q;
 
 	switch (where) {
+	case ELEVATOR_INSERT_REQUEUE:
+		/*
+		 * Most requeues happen because of a busy condition,
+		 * don't force unplug of the queue for that case.
+		 * Clear unplug_it and fall through.
+		 */
+		unplug_it = 0;
+
 	case ELEVATOR_INSERT_FRONT:
 		rq->cmd_flags |= REQ_SOFTBARRIER;
-
 		list_add(&rq->queuelist, &q->queue_head);
 		break;
 
@@ -668,36 +673,6 @@
 		q->elevator->ops->elevator_add_req_fn(q, rq);
 		break;
 
-	case ELEVATOR_INSERT_REQUEUE:
-		/*
-		 * If ordered flush isn't in progress, we do front
-		 * insertion; otherwise, requests should be requeued
-		 * in ordseq order.
-		 */
-		rq->cmd_flags |= REQ_SOFTBARRIER;
-
-		/*
-		 * Most requeues happen because of a busy condition,
-		 * don't force unplug of the queue for that case.
-		 */
-		unplug_it = 0;
-
-		if (q->ordseq == 0) {
-			list_add(&rq->queuelist, &q->queue_head);
-			break;
-		}
-
-		ordseq = blk_ordered_req_seq(rq);
-
-		list_for_each(pos, &q->queue_head) {
-			struct request *pos_rq = list_entry_rq(pos);
-			if (ordseq <= blk_ordered_req_seq(pos_rq))
-				break;
-		}
-
-		list_add_tail(&rq->queuelist, pos);
-		break;
-
 	default:
 		printk(KERN_ERR "%s: bad insertion point %d\n",
 		       __func__, where);
@@ -716,26 +691,8 @@
 void __elv_add_request(struct request_queue *q, struct request *rq, int where,
 		       int plug)
 {
-	if (q->ordcolor)
-		rq->cmd_flags |= REQ_ORDERED_COLOR;
-
 	if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
-		/*
-		 * toggle ordered color
-		 */
-		if (rq->cmd_flags & REQ_HARDBARRIER)
-			q->ordcolor ^= 1;
-
-		/*
-		 * barriers implicitly indicate back insertion
-		 */
-		if (where == ELEVATOR_INSERT_SORT)
-			where = ELEVATOR_INSERT_BACK;
-
-		/*
-		 * this request is scheduling boundary, update
-		 * end_sector
-		 */
+		/* barriers are scheduling boundary, update end_sector */
 		if (rq->cmd_type == REQ_TYPE_FS ||
 		    (rq->cmd_flags & REQ_DISCARD)) {
 			q->end_sector = rq_end_sector(rq);
@@ -855,24 +812,6 @@
 		    e->ops->elevator_completed_req_fn)
 			e->ops->elevator_completed_req_fn(q, rq);
 	}
-
-	/*
-	 * Check if the queue is waiting for fs requests to be
-	 * drained for flush sequence.
-	 */
-	if (unlikely(q->ordseq)) {
-		struct request *next = NULL;
-
-		if (!list_empty(&q->queue_head))
-			next = list_entry_rq(q->queue_head.next);
-
-		if (!queue_in_flight(q) &&
-		    blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
-		    (!next || blk_ordered_req_seq(next) > QUEUE_ORDSEQ_DRAIN)) {
-			blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
-			__blk_run_queue(q);
-		}
-	}
 }
 
 #define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
diff --git a/block/genhd.c b/block/genhd.c
index 59a2db6..8313834 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -541,13 +541,15 @@
 	disk->major = MAJOR(devt);
 	disk->first_minor = MINOR(devt);
 
+	/* Register BDI before referencing it from bdev */ 
+	bdi = &disk->queue->backing_dev_info;
+	bdi_register_dev(bdi, disk_devt(disk));
+
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
 			    exact_match, exact_lock, disk);
 	register_disk(disk);
 	blk_register_queue(disk);
 
-	bdi = &disk->queue->backing_dev_info;
-	bdi_register_dev(bdi, disk_devt(disk));
 	retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj,
 				   "bdi");
 	WARN_ON(retval);
@@ -642,6 +644,7 @@
 		struct hd_struct *part;
 		char name_buf[BDEVNAME_SIZE];
 		char devt_buf[BDEVT_SIZE];
+		u8 uuid[PARTITION_META_INFO_UUIDLTH * 2 + 1];
 
 		/*
 		 * Don't show empty devices or things that have been
@@ -660,10 +663,14 @@
 		while ((part = disk_part_iter_next(&piter))) {
 			bool is_part0 = part == &disk->part0;
 
-			printk("%s%s %10llu %s", is_part0 ? "" : "  ",
+			uuid[0] = 0;
+			if (part->info)
+				part_unpack_uuid(part->info->uuid, uuid);
+
+			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
 			       bdevt_str(part_devt(part), devt_buf),
 			       (unsigned long long)part->nr_sects >> 1,
-			       disk_name(disk, part->partno, name_buf));
+			       disk_name(disk, part->partno, name_buf), uuid);
 			if (is_part0) {
 				if (disk->driverfs_dev != NULL &&
 				    disk->driverfs_dev->driver != NULL)
@@ -925,8 +932,15 @@
 {
 	struct disk_part_tbl *ptbl =
 		container_of(head, struct disk_part_tbl, rcu_head);
+	struct gendisk *disk = ptbl->disk;
+	struct request_queue *q = disk->queue;
+	unsigned long flags;
 
 	kfree(ptbl);
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	elv_quiesce_end(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
 /**
@@ -944,11 +958,17 @@
 				  struct disk_part_tbl *new_ptbl)
 {
 	struct disk_part_tbl *old_ptbl = disk->part_tbl;
+	struct request_queue *q = disk->queue;
 
 	rcu_assign_pointer(disk->part_tbl, new_ptbl);
 
 	if (old_ptbl) {
 		rcu_assign_pointer(old_ptbl->last_lookup, NULL);
+
+		spin_lock_irq(q->queue_lock);
+		elv_quiesce_start(q);
+		spin_unlock_irq(q->queue_lock);
+
 		call_rcu(&old_ptbl->rcu_head, disk_free_ptbl_rcu_cb);
 	}
 }
@@ -989,6 +1009,7 @@
 		return -ENOMEM;
 
 	new_ptbl->len = target;
+	new_ptbl->disk = disk;
 
 	for (i = 0; i < len; i++)
 		rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]);
@@ -1004,6 +1025,7 @@
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
 	free_part_stats(&disk->part0);
+	free_part_info(&disk->part0);
 	kfree(disk);
 }
 struct class block_class = {
diff --git a/block/ioctl.c b/block/ioctl.c
index d8052f0..d724ceb 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -62,7 +62,7 @@
 
 			/* all seems OK */
 			part = add_partition(disk, partno, start, length,
-					     ADDPART_FLAG_NONE);
+					     ADDPART_FLAG_NONE, NULL);
 			mutex_unlock(&bdev->bd_mutex);
 			return IS_ERR(part) ? PTR_ERR(part) : 0;
 		case BLKPG_DEL_PARTITION:
@@ -116,7 +116,7 @@
 static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 			     uint64_t len, int secure)
 {
-	unsigned long flags = BLKDEV_IFL_WAIT;
+	unsigned long flags = 0;
 
 	if (start & 511)
 		return -EINVAL;
@@ -128,7 +128,7 @@
 	if (start + len > (bdev->bd_inode->i_size >> 9))
 		return -EINVAL;
 	if (secure)
-		flags |= BLKDEV_IFL_SECURE;
+		flags |= BLKDEV_DISCARD_SECURE;
 	return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
 }
 
diff --git a/crypto/des_generic.c b/crypto/des_generic.c
index 249f903..873818d 100644
--- a/crypto/des_generic.c
+++ b/crypto/des_generic.c
@@ -614,7 +614,7 @@
 #define T3(x) pt[2 * (x) + 2]
 #define T4(x) pt[2 * (x) + 3]
 
-#define PC2(a, b, c, d) (T4(d) | T3(c) | T2(b) | T1(a))
+#define DES_PC2(a, b, c, d) (T4(d) | T3(c) | T2(b) | T1(a))
 
 /*
  * Encryption key expansion
@@ -639,22 +639,22 @@
 	b = k[6]; b &= 0x0e; b <<= 4; b |= k[2] & 0x1e; b = pc1[b];
 	a = k[7]; a &= 0x0e; a <<= 4; a |= k[3] & 0x1e; a = pc1[a];
 
-	pe[15 * 2 + 0] = PC2(a, b, c, d); d = rs[d];
-	pe[14 * 2 + 0] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[13 * 2 + 0] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[12 * 2 + 0] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[11 * 2 + 0] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[10 * 2 + 0] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[ 9 * 2 + 0] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[ 8 * 2 + 0] = PC2(d, a, b, c); c = rs[c];
-	pe[ 7 * 2 + 0] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[ 6 * 2 + 0] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[ 5 * 2 + 0] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[ 4 * 2 + 0] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[ 3 * 2 + 0] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[ 2 * 2 + 0] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[ 1 * 2 + 0] = PC2(c, d, a, b); b = rs[b];
-	pe[ 0 * 2 + 0] = PC2(b, c, d, a);
+	pe[15 * 2 + 0] = DES_PC2(a, b, c, d); d = rs[d];
+	pe[14 * 2 + 0] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[13 * 2 + 0] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[12 * 2 + 0] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[11 * 2 + 0] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[10 * 2 + 0] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[ 9 * 2 + 0] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[ 8 * 2 + 0] = DES_PC2(d, a, b, c); c = rs[c];
+	pe[ 7 * 2 + 0] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[ 6 * 2 + 0] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[ 5 * 2 + 0] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[ 4 * 2 + 0] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[ 3 * 2 + 0] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[ 2 * 2 + 0] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[ 1 * 2 + 0] = DES_PC2(c, d, a, b); b = rs[b];
+	pe[ 0 * 2 + 0] = DES_PC2(b, c, d, a);
 
 	/* Check if first half is weak */
 	w  = (a ^ c) | (b ^ d) | (rs[a] ^ c) | (b ^ rs[d]);
@@ -670,22 +670,22 @@
 	/* Check if second half is weak */
 	w |= (a ^ c) | (b ^ d) | (rs[a] ^ c) | (b ^ rs[d]);
 
-	pe[15 * 2 + 1] = PC2(a, b, c, d); d = rs[d];
-	pe[14 * 2 + 1] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[13 * 2 + 1] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[12 * 2 + 1] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[11 * 2 + 1] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[10 * 2 + 1] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[ 9 * 2 + 1] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[ 8 * 2 + 1] = PC2(d, a, b, c); c = rs[c];
-	pe[ 7 * 2 + 1] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[ 6 * 2 + 1] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[ 5 * 2 + 1] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[ 4 * 2 + 1] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[ 3 * 2 + 1] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[ 2 * 2 + 1] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[ 1 * 2 + 1] = PC2(c, d, a, b); b = rs[b];
-	pe[ 0 * 2 + 1] = PC2(b, c, d, a);
+	pe[15 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d];
+	pe[14 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[13 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[12 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[11 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[10 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[ 9 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[ 8 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c];
+	pe[ 7 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[ 6 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[ 5 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[ 4 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[ 3 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[ 2 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[ 1 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b];
+	pe[ 0 * 2 + 1] = DES_PC2(b, c, d, a);
 
 	/* Fixup: 2413 5768 -> 1357 2468 */
 	for (d = 0; d < 16; ++d) {
@@ -722,22 +722,22 @@
 	b = k[6]; b &= 0x0e; b <<= 4; b |= k[2] & 0x1e; b = pc1[b];
 	a = k[7]; a &= 0x0e; a <<= 4; a |= k[3] & 0x1e; a = pc1[a];
 
-	pe[ 0 * 2] = PC2(a, b, c, d); d = rs[d];
-	pe[ 1 * 2] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[ 2 * 2] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[ 3 * 2] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[ 4 * 2] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[ 5 * 2] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[ 6 * 2] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[ 7 * 2] = PC2(d, a, b, c); c = rs[c];
-	pe[ 8 * 2] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[ 9 * 2] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[10 * 2] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[11 * 2] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[12 * 2] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[13 * 2] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[14 * 2] = PC2(c, d, a, b); b = rs[b];
-	pe[15 * 2] = PC2(b, c, d, a);
+	pe[ 0 * 2] = DES_PC2(a, b, c, d); d = rs[d];
+	pe[ 1 * 2] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[ 2 * 2] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[ 3 * 2] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[ 4 * 2] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[ 5 * 2] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[ 6 * 2] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[ 7 * 2] = DES_PC2(d, a, b, c); c = rs[c];
+	pe[ 8 * 2] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[ 9 * 2] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[10 * 2] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[11 * 2] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[12 * 2] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[13 * 2] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[14 * 2] = DES_PC2(c, d, a, b); b = rs[b];
+	pe[15 * 2] = DES_PC2(b, c, d, a);
 
 	/* Skip to next table set */
 	pt += 512;
@@ -747,22 +747,22 @@
 	b = k[2]; b &= 0xe0; b >>= 4; b |= k[6] & 0xf0; b = pc1[b + 1];
 	a = k[3]; a &= 0xe0; a >>= 4; a |= k[7] & 0xf0; a = pc1[a + 1];
 
-	pe[ 0 * 2 + 1] = PC2(a, b, c, d); d = rs[d];
-	pe[ 1 * 2 + 1] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[ 2 * 2 + 1] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[ 3 * 2 + 1] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[ 4 * 2 + 1] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[ 5 * 2 + 1] = PC2(d, a, b, c); c = rs[c]; b = rs[b];
-	pe[ 6 * 2 + 1] = PC2(b, c, d, a); a = rs[a]; d = rs[d];
-	pe[ 7 * 2 + 1] = PC2(d, a, b, c); c = rs[c];
-	pe[ 8 * 2 + 1] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[ 9 * 2 + 1] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[10 * 2 + 1] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[11 * 2 + 1] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[12 * 2 + 1] = PC2(c, d, a, b); b = rs[b]; a = rs[a];
-	pe[13 * 2 + 1] = PC2(a, b, c, d); d = rs[d]; c = rs[c];
-	pe[14 * 2 + 1] = PC2(c, d, a, b); b = rs[b];
-	pe[15 * 2 + 1] = PC2(b, c, d, a);
+	pe[ 0 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d];
+	pe[ 1 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[ 2 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[ 3 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[ 4 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[ 5 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b];
+	pe[ 6 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d];
+	pe[ 7 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c];
+	pe[ 8 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[ 9 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[10 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[11 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[12 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a];
+	pe[13 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c];
+	pe[14 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b];
+	pe[15 * 2 + 1] = DES_PC2(b, c, d, a);
 
 	/* Fixup: 2413 5768 -> 1357 2468 */
 	for (d = 0; d < 16; ++d) {
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 6b115f6..6afceb3 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -30,18 +30,13 @@
 #include <linux/slab.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
+#include <asm/mwait.h>
 
 #define ACPI_PROCESSOR_AGGREGATOR_CLASS	"acpi_pad"
 #define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
 #define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80
 static DEFINE_MUTEX(isolated_cpus_lock);
 
-#define MWAIT_SUBSTATE_MASK	(0xf)
-#define MWAIT_CSTATE_MASK	(0xf)
-#define MWAIT_SUBSTATE_SIZE	(4)
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK	(0x2)
 static unsigned long power_saving_mwait_eax;
 
 static unsigned char tsc_detected_unstable;
diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c
index da1228a..de73caf 100644
--- a/drivers/acpi/apei/erst-dbg.c
+++ b/drivers/acpi/apei/erst-dbg.c
@@ -184,6 +184,7 @@
 	.read		= erst_dbg_read,
 	.write		= erst_dbg_write,
 	.unlocked_ioctl	= erst_dbg_ioctl,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice erst_dbg_dev = {
diff --git a/drivers/acpi/debugfs.c b/drivers/acpi/debugfs.c
index 7de27d4..6355b57 100644
--- a/drivers/acpi/debugfs.c
+++ b/drivers/acpi/debugfs.c
@@ -69,6 +69,7 @@
 
 static const struct file_operations cm_fops = {
 	.write = cm_write,
+	.llseek = default_llseek,
 };
 
 int __init acpi_debugfs_init(void)
diff --git a/drivers/acpi/ec_sys.c b/drivers/acpi/ec_sys.c
index 0e869b3..411620e 100644
--- a/drivers/acpi/ec_sys.c
+++ b/drivers/acpi/ec_sys.c
@@ -101,6 +101,7 @@
 	.open  = acpi_ec_open_io,
 	.read  = acpi_ec_read_io,
 	.write = acpi_ec_write_io,
+	.llseek = default_llseek,
 };
 
 int acpi_ec_add_debugfs(struct acpi_ec *ec, unsigned int ec_device_count)
diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index d439314..85d9089 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -110,6 +110,7 @@
 	.read = acpi_system_read_event,
 	.release = acpi_system_close_event,
 	.poll = acpi_system_poll_event,
+	.llseek = default_llseek,
 };
 #endif	/* CONFIG_ACPI_PROC_EVENT */
 
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index d31590e..2737b97 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -298,7 +298,7 @@
 
 		amba_put_disable_pclk(dev);
 
-		if (cid == 0xb105f00d)
+		if (cid == AMBA_CID)
 			dev->periphid = pid;
 
 		if (!dev->periphid)
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index d5df04a..c501af5 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -99,7 +99,7 @@
 # Should be last libata driver
 obj-$(CONFIG_PATA_LEGACY)	+= pata_legacy.o
 
-libata-objs	:= libata-core.o libata-scsi.o libata-eh.o
+libata-y	:= libata-core.o libata-scsi.o libata-eh.o libata-transport.o
 libata-$(CONFIG_ATA_SFF)	+= libata-sff.o
 libata-$(CONFIG_SATA_PMP)	+= libata-pmp.o
 libata-$(CONFIG_ATA_ACPI)	+= libata-acpi.o
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 99d0e5a..3288263 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1208,9 +1208,6 @@
 		ata_port_pbar_desc(ap, AHCI_PCI_BAR,
 				   0x100 + ap->port_no * 0x80, "port");
 
-		/* set initial link pm policy */
-		ap->pm_policy = NOT_AVAILABLE;
-
 		/* set enclosure management message type */
 		if (ap->flags & ATA_FLAG_EM)
 			ap->em_message_type = hpriv->em_msg_type;
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index e5fdeeb..329cbbb 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -72,6 +72,7 @@
 	AHCI_CMD_RESET		= (1 << 8),
 	AHCI_CMD_CLR_BUSY	= (1 << 10),
 
+	RX_FIS_PIO_SETUP	= 0x20,	/* offset of PIO Setup FIS data */
 	RX_FIS_D2H_REG		= 0x40,	/* offset of D2H Register FIS data */
 	RX_FIS_SDB		= 0x58, /* offset of SDB FIS data */
 	RX_FIS_UNK		= 0x60, /* offset of Unknown FIS data */
@@ -201,7 +202,6 @@
 	AHCI_HFLAG_MV_PATA		= (1 << 4), /* PATA port */
 	AHCI_HFLAG_NO_MSI		= (1 << 5), /* no PCI MSI */
 	AHCI_HFLAG_NO_PMP		= (1 << 6), /* no PMP */
-	AHCI_HFLAG_NO_HOTPLUG		= (1 << 7), /* ignore PxSERR.DIAG.N */
 	AHCI_HFLAG_SECT255		= (1 << 8), /* max 255 sectors */
 	AHCI_HFLAG_YES_NCQ		= (1 << 9), /* force NCQ cap on */
 	AHCI_HFLAG_NO_SUSPEND		= (1 << 10), /* don't suspend */
@@ -216,7 +216,7 @@
 	AHCI_FLAG_COMMON		= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
 					  ATA_FLAG_MMIO | ATA_FLAG_PIO_DMA |
 					  ATA_FLAG_ACPI_SATA | ATA_FLAG_AN |
-					  ATA_FLAG_IPM,
+					  ATA_FLAG_LPM,
 
 	ICH_MAP				= 0x90, /* ICH MAP register */
 
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index 84b6432..6fef1fa 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -129,9 +129,6 @@
 		ata_port_desc(ap, "mmio %pR", mem);
 		ata_port_desc(ap, "port 0x%x", 0x100 + ap->port_no * 0x80);
 
-		/* set initial link pm policy */
-		ap->pm_policy = NOT_AVAILABLE;
-
 		/* set enclosure management message type */
 		if (ap->flags & ATA_FLAG_EM)
 			ap->em_message_type = hpriv->em_msg_type;
diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c
index cc5f772..6981f76 100644
--- a/drivers/ata/ata_generic.c
+++ b/drivers/ata/ata_generic.c
@@ -35,6 +35,7 @@
 enum {
 	ATA_GEN_CLASS_MATCH		= (1 << 0),
 	ATA_GEN_FORCE_DMA		= (1 << 1),
+	ATA_GEN_INTEL_IDER		= (1 << 2),
 };
 
 /**
@@ -109,6 +110,49 @@
 static int all_generic_ide;		/* Set to claim all devices */
 
 /**
+ *	is_intel_ider		-	identify intel IDE-R devices
+ *	@dev: PCI device
+ *
+ *	Distinguish Intel IDE-R controller devices from other Intel IDE
+ *	devices. IDE-R devices have no timing registers and are in
+ *	most respects virtual. They should be driven by the ata_generic
+ *	driver.
+ *
+ *	IDE-R devices have PCI offset 0xF8.L as zero, later Intel ATA has
+ *	it non zero. All Intel ATA has 0x40 writable (timing), but it is
+ *	not writable on IDE-R devices (this is guaranteed).
+ */
+
+static int is_intel_ider(struct pci_dev *dev)
+{
+	/* For Intel IDE the value at 0xF8 is only zero on IDE-R
+	   interfaces */
+	u32 r;
+	u16 t;
+
+	/* Check the manufacturing ID, it will be zero for IDE-R */
+	pci_read_config_dword(dev, 0xF8, &r);
+	/* Not IDE-R: punt so that ata_(old)piix gets it */
+	if (r != 0)
+		return 0;
+	/* 0xF8 will also be zero on some early Intel IDE devices
+	   but they will have a sane timing register */
+	pci_read_config_word(dev, 0x40, &t);
+	if (t != 0)
+		return 0;
+	/* Finally check if the timing register is writable so that
+	   we eliminate any early devices hot-docked in a docking
+	   station */
+	pci_write_config_word(dev, 0x40, 1);
+	pci_read_config_word(dev, 0x40, &t);
+	if (t) {
+		pci_write_config_word(dev, 0x40, 0);
+		return 0;
+	}
+	return 1;
+}
+
+/**
  *	ata_generic_init		-	attach generic IDE
  *	@dev: PCI device found
  *	@id: match entry
@@ -134,6 +178,10 @@
 	if ((id->driver_data & ATA_GEN_CLASS_MATCH) && all_generic_ide == 0)
 		return -ENODEV;
 
+	if (id->driver_data & ATA_GEN_INTEL_IDER)
+		if (!is_intel_ider(dev))
+			return -ENODEV;
+
 	/* Devices that need care */
 	if (dev->vendor == PCI_VENDOR_ID_UMC &&
 	    dev->device == PCI_DEVICE_ID_UMC_UM8886A &&
@@ -186,7 +234,11 @@
 	{ PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_2),  },
 	{ PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_3),  },
 	{ PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_5),  },
-#endif	
+#endif
+	/* Intel, IDE class device */
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
+	  PCI_CLASS_STORAGE_IDE << 8, 0xFFFFFF00UL, 
+	  .driver_data = ATA_GEN_INTEL_IDER },
 	/* Must come last. If you add entries adjust this table appropriately */
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_IDE << 8, 0xFFFFFF00UL),
 	  .driver_data = ATA_GEN_CLASS_MATCH },
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index d712675..6cb14ca 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -158,7 +158,6 @@
 struct piix_host_priv {
 	const int *map;
 	u32 saved_iocfg;
-	spinlock_t sidpr_lock;	/* FIXME: remove once locking in EH is fixed */
 	void __iomem *sidpr;
 };
 
@@ -175,6 +174,8 @@
 			       unsigned int reg, u32 *val);
 static int piix_sidpr_scr_write(struct ata_link *link,
 				unsigned int reg, u32 val);
+static int piix_sidpr_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+			      unsigned hints);
 static bool piix_irq_check(struct ata_port *ap);
 #ifdef CONFIG_PM
 static int piix_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg);
@@ -209,6 +210,8 @@
 	{ 0x8086, 0x248A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich_pata_100 },
 	/* Intel ICH3 (E7500/1) UDMA 100 */
 	{ 0x8086, 0x248B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich_pata_100 },
+	/* Intel ICH4-L */
+	{ 0x8086, 0x24C1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich_pata_100 },
 	/* Intel ICH4 (i845GV, i845E, i852, i855) UDMA 100 */
 	{ 0x8086, 0x24CA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich_pata_100 },
 	{ 0x8086, 0x24CB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich_pata_100 },
@@ -348,11 +351,22 @@
 	.set_dmamode		= ich_set_dmamode,
 };
 
+static struct device_attribute *piix_sidpr_shost_attrs[] = {
+	&dev_attr_link_power_management_policy,
+	NULL
+};
+
+static struct scsi_host_template piix_sidpr_sht = {
+	ATA_BMDMA_SHT(DRV_NAME),
+	.shost_attrs		= piix_sidpr_shost_attrs,
+};
+
 static struct ata_port_operations piix_sidpr_sata_ops = {
 	.inherits		= &piix_sata_ops,
 	.hardreset		= sata_std_hardreset,
 	.scr_read		= piix_sidpr_scr_read,
 	.scr_write		= piix_sidpr_scr_write,
+	.set_lpm		= piix_sidpr_set_lpm,
 };
 
 static const struct piix_map_db ich5_map_db = {
@@ -956,15 +970,12 @@
 			       unsigned int reg, u32 *val)
 {
 	struct piix_host_priv *hpriv = link->ap->host->private_data;
-	unsigned long flags;
 
 	if (reg >= ARRAY_SIZE(piix_sidx_map))
 		return -EINVAL;
 
-	spin_lock_irqsave(&hpriv->sidpr_lock, flags);
 	piix_sidpr_sel(link, reg);
 	*val = ioread32(hpriv->sidpr + PIIX_SIDPR_DATA);
-	spin_unlock_irqrestore(&hpriv->sidpr_lock, flags);
 	return 0;
 }
 
@@ -972,18 +983,21 @@
 				unsigned int reg, u32 val)
 {
 	struct piix_host_priv *hpriv = link->ap->host->private_data;
-	unsigned long flags;
 
 	if (reg >= ARRAY_SIZE(piix_sidx_map))
 		return -EINVAL;
 
-	spin_lock_irqsave(&hpriv->sidpr_lock, flags);
 	piix_sidpr_sel(link, reg);
 	iowrite32(val, hpriv->sidpr + PIIX_SIDPR_DATA);
-	spin_unlock_irqrestore(&hpriv->sidpr_lock, flags);
 	return 0;
 }
 
+static int piix_sidpr_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+			      unsigned hints)
+{
+	return sata_link_scr_lpm(link, policy, false);
+}
+
 static bool piix_irq_check(struct ata_port *ap)
 {
 	if (unlikely(!ap->ioaddr.bmdma_addr))
@@ -1543,6 +1557,7 @@
 	struct device *dev = &pdev->dev;
 	struct ata_port_info port_info[2];
 	const struct ata_port_info *ppi[] = { &port_info[0], &port_info[1] };
+	struct scsi_host_template *sht = &piix_sht;
 	unsigned long port_flags;
 	struct ata_host *host;
 	struct piix_host_priv *hpriv;
@@ -1577,7 +1592,6 @@
 	hpriv = devm_kzalloc(dev, sizeof(*hpriv), GFP_KERNEL);
 	if (!hpriv)
 		return -ENOMEM;
-	spin_lock_init(&hpriv->sidpr_lock);
 
 	/* Save IOCFG, this will be used for cable detection, quirk
 	 * detection and restoration on detach.  This is necessary
@@ -1612,6 +1626,8 @@
 		rc = piix_init_sidpr(host);
 		if (rc)
 			return rc;
+		if (host->ports[0]->ops == &piix_sidpr_sata_ops)
+			sht = &piix_sidpr_sht;
 	}
 
 	/* apply IOCFG bit18 quirk */
@@ -1638,7 +1654,7 @@
 	host->flags |= ATA_HOST_PARALLEL_SCAN;
 
 	pci_set_master(pdev);
-	return ata_pci_sff_activate_host(host, ata_bmdma_interrupt, &piix_sht);
+	return ata_pci_sff_activate_host(host, ata_bmdma_interrupt, sht);
 }
 
 static void piix_remove_one(struct pci_dev *pdev)
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 8eea309..ebc08d65 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -56,9 +56,8 @@
 module_param_named(ignore_sss, ahci_ignore_sss, int, 0444);
 MODULE_PARM_DESC(ignore_sss, "Ignore staggered spinup flag (0=don't ignore, 1=ignore)");
 
-static int ahci_enable_alpm(struct ata_port *ap,
-		enum link_pm policy);
-static void ahci_disable_alpm(struct ata_port *ap);
+static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+			unsigned hints);
 static ssize_t ahci_led_show(struct ata_port *ap, char *buf);
 static ssize_t ahci_led_store(struct ata_port *ap, const char *buf,
 			      size_t size);
@@ -164,8 +163,7 @@
 	.pmp_attach		= ahci_pmp_attach,
 	.pmp_detach		= ahci_pmp_detach,
 
-	.enable_pm		= ahci_enable_alpm,
-	.disable_pm		= ahci_disable_alpm,
+	.set_lpm		= ahci_set_lpm,
 	.em_show		= ahci_led_show,
 	.em_store		= ahci_led_store,
 	.sw_activity_show	= ahci_activity_show,
@@ -569,7 +567,7 @@
 	writel(tmp, port_mmio + PORT_CMD);
 
 	/* wait for engine to stop. This could be as long as 500 msec */
-	tmp = ata_wait_register(port_mmio + PORT_CMD,
+	tmp = ata_wait_register(ap, port_mmio + PORT_CMD,
 				PORT_CMD_LIST_ON, PORT_CMD_LIST_ON, 1, 500);
 	if (tmp & PORT_CMD_LIST_ON)
 		return -EIO;
@@ -616,7 +614,7 @@
 	writel(tmp, port_mmio + PORT_CMD);
 
 	/* wait for completion, spec says 500ms, give it 1000 */
-	tmp = ata_wait_register(port_mmio + PORT_CMD, PORT_CMD_FIS_ON,
+	tmp = ata_wait_register(ap, port_mmio + PORT_CMD, PORT_CMD_FIS_ON,
 				PORT_CMD_FIS_ON, 10, 1000);
 	if (tmp & PORT_CMD_FIS_ON)
 		return -EBUSY;
@@ -642,127 +640,56 @@
 	writel(cmd | PORT_CMD_ICC_ACTIVE, port_mmio + PORT_CMD);
 }
 
-static void ahci_disable_alpm(struct ata_port *ap)
+static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+			unsigned int hints)
 {
+	struct ata_port *ap = link->ap;
 	struct ahci_host_priv *hpriv = ap->host->private_data;
-	void __iomem *port_mmio = ahci_port_base(ap);
-	u32 cmd;
 	struct ahci_port_priv *pp = ap->private_data;
-
-	/* IPM bits should be disabled by libata-core */
-	/* get the existing command bits */
-	cmd = readl(port_mmio + PORT_CMD);
-
-	/* disable ALPM and ASP */
-	cmd &= ~PORT_CMD_ASP;
-	cmd &= ~PORT_CMD_ALPE;
-
-	/* force the interface back to active */
-	cmd |= PORT_CMD_ICC_ACTIVE;
-
-	/* write out new cmd value */
-	writel(cmd, port_mmio + PORT_CMD);
-	cmd = readl(port_mmio + PORT_CMD);
-
-	/* wait 10ms to be sure we've come out of any low power state */
-	msleep(10);
-
-	/* clear out any PhyRdy stuff from interrupt status */
-	writel(PORT_IRQ_PHYRDY, port_mmio + PORT_IRQ_STAT);
-
-	/* go ahead and clean out PhyRdy Change from Serror too */
-	ahci_scr_write(&ap->link, SCR_ERROR, ((1 << 16) | (1 << 18)));
-
-	/*
-	 * Clear flag to indicate that we should ignore all PhyRdy
-	 * state changes
-	 */
-	hpriv->flags &= ~AHCI_HFLAG_NO_HOTPLUG;
-
-	/*
-	 * Enable interrupts on Phy Ready.
-	 */
-	pp->intr_mask |= PORT_IRQ_PHYRDY;
-	writel(pp->intr_mask, port_mmio + PORT_IRQ_MASK);
-
-	/*
-	 * don't change the link pm policy - we can be called
-	 * just to turn of link pm temporarily
-	 */
-}
-
-static int ahci_enable_alpm(struct ata_port *ap,
-	enum link_pm policy)
-{
-	struct ahci_host_priv *hpriv = ap->host->private_data;
 	void __iomem *port_mmio = ahci_port_base(ap);
-	u32 cmd;
-	struct ahci_port_priv *pp = ap->private_data;
-	u32 asp;
 
-	/* Make sure the host is capable of link power management */
-	if (!(hpriv->cap & HOST_CAP_ALPM))
-		return -EINVAL;
-
-	switch (policy) {
-	case MAX_PERFORMANCE:
-	case NOT_AVAILABLE:
+	if (policy != ATA_LPM_MAX_POWER) {
 		/*
-		 * if we came here with NOT_AVAILABLE,
-		 * it just means this is the first time we
-		 * have tried to enable - default to max performance,
-		 * and let the user go to lower power modes on request.
+		 * Disable interrupts on Phy Ready. This keeps us from
+		 * getting woken up due to spurious phy ready
+		 * interrupts.
 		 */
-		ahci_disable_alpm(ap);
-		return 0;
-	case MIN_POWER:
-		/* configure HBA to enter SLUMBER */
-		asp = PORT_CMD_ASP;
-		break;
-	case MEDIUM_POWER:
-		/* configure HBA to enter PARTIAL */
-		asp = 0;
-		break;
-	default:
-		return -EINVAL;
+		pp->intr_mask &= ~PORT_IRQ_PHYRDY;
+		writel(pp->intr_mask, port_mmio + PORT_IRQ_MASK);
+
+		sata_link_scr_lpm(link, policy, false);
 	}
 
-	/*
-	 * Disable interrupts on Phy Ready. This keeps us from
-	 * getting woken up due to spurious phy ready interrupts
-	 * TBD - Hot plug should be done via polling now, is
-	 * that even supported?
-	 */
-	pp->intr_mask &= ~PORT_IRQ_PHYRDY;
-	writel(pp->intr_mask, port_mmio + PORT_IRQ_MASK);
+	if (hpriv->cap & HOST_CAP_ALPM) {
+		u32 cmd = readl(port_mmio + PORT_CMD);
 
-	/*
-	 * Set a flag to indicate that we should ignore all PhyRdy
-	 * state changes since these can happen now whenever we
-	 * change link state
-	 */
-	hpriv->flags |= AHCI_HFLAG_NO_HOTPLUG;
+		if (policy == ATA_LPM_MAX_POWER || !(hints & ATA_LPM_HIPM)) {
+			cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
+			cmd |= PORT_CMD_ICC_ACTIVE;
 
-	/* get the existing command bits */
-	cmd = readl(port_mmio + PORT_CMD);
+			writel(cmd, port_mmio + PORT_CMD);
+			readl(port_mmio + PORT_CMD);
 
-	/*
-	 * Set ASP based on Policy
-	 */
-	cmd |= asp;
+			/* wait 10ms to be sure we've come out of LPM state */
+			ata_msleep(ap, 10);
+		} else {
+			cmd |= PORT_CMD_ALPE;
+			if (policy == ATA_LPM_MIN_POWER)
+				cmd |= PORT_CMD_ASP;
 
-	/*
-	 * Setting this bit will instruct the HBA to aggressively
-	 * enter a lower power link state when it's appropriate and
-	 * based on the value set above for ASP
-	 */
-	cmd |= PORT_CMD_ALPE;
+			/* write out new cmd value */
+			writel(cmd, port_mmio + PORT_CMD);
+		}
+	}
 
-	/* write out new cmd value */
-	writel(cmd, port_mmio + PORT_CMD);
-	cmd = readl(port_mmio + PORT_CMD);
+	if (policy == ATA_LPM_MAX_POWER) {
+		sata_link_scr_lpm(link, policy, false);
 
-	/* IPM bits should be set by libata-core */
+		/* turn PHYRDY IRQ back on */
+		pp->intr_mask |= PORT_IRQ_PHYRDY;
+		writel(pp->intr_mask, port_mmio + PORT_IRQ_MASK);
+	}
+
 	return 0;
 }
 
@@ -813,7 +740,7 @@
 							       emp->led_state,
 							       4);
 				if (rc == -EBUSY)
-					msleep(1);
+					ata_msleep(ap, 1);
 				else
 					break;
 			}
@@ -872,7 +799,7 @@
 		 * reset must complete within 1 second, or
 		 * the hardware should be considered fried.
 		 */
-		tmp = ata_wait_register(mmio + HOST_CTL, HOST_RESET,
+		tmp = ata_wait_register(NULL, mmio + HOST_CTL, HOST_RESET,
 					HOST_RESET, 10, 1000);
 
 		if (tmp & HOST_RESET) {
@@ -1252,7 +1179,7 @@
 	writel(tmp, port_mmio + PORT_CMD);
 
 	rc = 0;
-	tmp = ata_wait_register(port_mmio + PORT_CMD,
+	tmp = ata_wait_register(ap, port_mmio + PORT_CMD,
 				PORT_CMD_CLO, PORT_CMD_CLO, 1, 500);
 	if (tmp & PORT_CMD_CLO)
 		rc = -EIO;
@@ -1282,8 +1209,8 @@
 	writel(1, port_mmio + PORT_CMD_ISSUE);
 
 	if (timeout_msec) {
-		tmp = ata_wait_register(port_mmio + PORT_CMD_ISSUE, 0x1, 0x1,
-					1, timeout_msec);
+		tmp = ata_wait_register(ap, port_mmio + PORT_CMD_ISSUE,
+					0x1, 0x1, 1, timeout_msec);
 		if (tmp & 0x1) {
 			ahci_kick_engine(ap);
 			return -EBUSY;
@@ -1330,7 +1257,7 @@
 	}
 
 	/* spec says at least 5us, but be generous and sleep for 1ms */
-	msleep(1);
+	ata_msleep(ap, 1);
 
 	/* issue the second D2H Register FIS */
 	tf.ctl &= ~ATA_SRST;
@@ -1660,15 +1587,10 @@
 	if (unlikely(resetting))
 		status &= ~PORT_IRQ_BAD_PMP;
 
-	/* If we are getting PhyRdy, this is
-	 * just a power state change, we should
-	 * clear out this, plus the PhyRdy/Comm
-	 * Wake bits from Serror
-	 */
-	if ((hpriv->flags & AHCI_HFLAG_NO_HOTPLUG) &&
-		(status & PORT_IRQ_PHYRDY)) {
+	/* if LPM is enabled, PHYRDY doesn't mean anything */
+	if (ap->link.lpm_policy > ATA_LPM_MAX_POWER) {
 		status &= ~PORT_IRQ_PHYRDY;
-		ahci_scr_write(&ap->link, SCR_ERROR, ((1 << 16) | (1 << 18)));
+		ahci_scr_write(&ap->link, SCR_ERROR, SERR_PHYRDY_CHG);
 	}
 
 	if (unlikely(status & PORT_IRQ_ERROR)) {
@@ -1830,12 +1752,24 @@
 static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc)
 {
 	struct ahci_port_priv *pp = qc->ap->private_data;
-	u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
+	u8 *rx_fis = pp->rx_fis;
 
 	if (pp->fbs_enabled)
-		d2h_fis += qc->dev->link->pmp * AHCI_RX_FIS_SZ;
+		rx_fis += qc->dev->link->pmp * AHCI_RX_FIS_SZ;
 
-	ata_tf_from_fis(d2h_fis, &qc->result_tf);
+	/*
+	 * After a successful execution of an ATA PIO data-in command,
+	 * the device doesn't send D2H Reg FIS to update the TF and
+	 * the host should take TF and E_Status from the preceding PIO
+	 * Setup FIS.
+	 */
+	if (qc->tf.protocol == ATA_PROT_PIO && qc->dma_dir == DMA_FROM_DEVICE &&
+	    !(qc->flags & ATA_QCFLAG_FAILED)) {
+		ata_tf_from_fis(rx_fis + RX_FIS_PIO_SETUP, &qc->result_tf);
+		qc->result_tf.command = (rx_fis + RX_FIS_PIO_SETUP)[15];
+	} else
+		ata_tf_from_fis(rx_fis + RX_FIS_D2H_REG, &qc->result_tf);
+
 	return true;
 }
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 932eaee..7f77c67 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -68,7 +68,7 @@
 #include <linux/ratelimit.h>
 
 #include "libata.h"
-
+#include "libata-transport.h"
 
 /* debounce timing parameters in msecs { interval, duration, timeout } */
 const unsigned long sata_deb_timing_normal[]		= {   5,  100, 2000 };
@@ -91,8 +91,6 @@
 static unsigned int ata_dev_init_params(struct ata_device *dev,
 					u16 heads, u16 sectors);
 static unsigned int ata_dev_set_xfermode(struct ata_device *dev);
-static unsigned int ata_dev_set_feature(struct ata_device *dev,
-					u8 enable, u8 feature);
 static void ata_dev_xfermask(struct ata_device *dev);
 static unsigned long ata_dev_blacklisted(const struct ata_device *dev);
 
@@ -1017,7 +1015,7 @@
 	return "<n/a>";
 }
 
-static const char *sata_spd_string(unsigned int spd)
+const char *sata_spd_string(unsigned int spd)
 {
 	static const char * const spd_str[] = {
 		"1.5 Gbps",
@@ -1030,182 +1028,6 @@
 	return spd_str[spd - 1];
 }
 
-static int ata_dev_set_dipm(struct ata_device *dev, enum link_pm policy)
-{
-	struct ata_link *link = dev->link;
-	struct ata_port *ap = link->ap;
-	u32 scontrol;
-	unsigned int err_mask;
-	int rc;
-
-	/*
-	 * disallow DIPM for drivers which haven't set
-	 * ATA_FLAG_IPM.  This is because when DIPM is enabled,
-	 * phy ready will be set in the interrupt status on
-	 * state changes, which will cause some drivers to
-	 * think there are errors - additionally drivers will
-	 * need to disable hot plug.
-	 */
-	if (!(ap->flags & ATA_FLAG_IPM) || !ata_dev_enabled(dev)) {
-		ap->pm_policy = NOT_AVAILABLE;
-		return -EINVAL;
-	}
-
-	/*
-	 * For DIPM, we will only enable it for the
-	 * min_power setting.
-	 *
-	 * Why?  Because Disks are too stupid to know that
-	 * If the host rejects a request to go to SLUMBER
-	 * they should retry at PARTIAL, and instead it
-	 * just would give up.  So, for medium_power to
-	 * work at all, we need to only allow HIPM.
-	 */
-	rc = sata_scr_read(link, SCR_CONTROL, &scontrol);
-	if (rc)
-		return rc;
-
-	switch (policy) {
-	case MIN_POWER:
-		/* no restrictions on IPM transitions */
-		scontrol &= ~(0x3 << 8);
-		rc = sata_scr_write(link, SCR_CONTROL, scontrol);
-		if (rc)
-			return rc;
-
-		/* enable DIPM */
-		if (dev->flags & ATA_DFLAG_DIPM)
-			err_mask = ata_dev_set_feature(dev,
-					SETFEATURES_SATA_ENABLE, SATA_DIPM);
-		break;
-	case MEDIUM_POWER:
-		/* allow IPM to PARTIAL */
-		scontrol &= ~(0x1 << 8);
-		scontrol |= (0x2 << 8);
-		rc = sata_scr_write(link, SCR_CONTROL, scontrol);
-		if (rc)
-			return rc;
-
-		/*
-		 * we don't have to disable DIPM since IPM flags
-		 * disallow transitions to SLUMBER, which effectively
-		 * disable DIPM if it does not support PARTIAL
-		 */
-		break;
-	case NOT_AVAILABLE:
-	case MAX_PERFORMANCE:
-		/* disable all IPM transitions */
-		scontrol |= (0x3 << 8);
-		rc = sata_scr_write(link, SCR_CONTROL, scontrol);
-		if (rc)
-			return rc;
-
-		/*
-		 * we don't have to disable DIPM since IPM flags
-		 * disallow all transitions which effectively
-		 * disable DIPM anyway.
-		 */
-		break;
-	}
-
-	/* FIXME: handle SET FEATURES failure */
-	(void) err_mask;
-
-	return 0;
-}
-
-/**
- *	ata_dev_enable_pm - enable SATA interface power management
- *	@dev:  device to enable power management
- *	@policy: the link power management policy
- *
- *	Enable SATA Interface power management.  This will enable
- *	Device Interface Power Management (DIPM) for min_power
- * 	policy, and then call driver specific callbacks for
- *	enabling Host Initiated Power management.
- *
- *	Locking: Caller.
- *	Returns: -EINVAL if IPM is not supported, 0 otherwise.
- */
-void ata_dev_enable_pm(struct ata_device *dev, enum link_pm policy)
-{
-	int rc = 0;
-	struct ata_port *ap = dev->link->ap;
-
-	/* set HIPM first, then DIPM */
-	if (ap->ops->enable_pm)
-		rc = ap->ops->enable_pm(ap, policy);
-	if (rc)
-		goto enable_pm_out;
-	rc = ata_dev_set_dipm(dev, policy);
-
-enable_pm_out:
-	if (rc)
-		ap->pm_policy = MAX_PERFORMANCE;
-	else
-		ap->pm_policy = policy;
-	return /* rc */;	/* hopefully we can use 'rc' eventually */
-}
-
-#ifdef CONFIG_PM
-/**
- *	ata_dev_disable_pm - disable SATA interface power management
- *	@dev: device to disable power management
- *
- *	Disable SATA Interface power management.  This will disable
- *	Device Interface Power Management (DIPM) without changing
- * 	policy,  call driver specific callbacks for disabling Host
- * 	Initiated Power management.
- *
- *	Locking: Caller.
- *	Returns: void
- */
-static void ata_dev_disable_pm(struct ata_device *dev)
-{
-	struct ata_port *ap = dev->link->ap;
-
-	ata_dev_set_dipm(dev, MAX_PERFORMANCE);
-	if (ap->ops->disable_pm)
-		ap->ops->disable_pm(ap);
-}
-#endif	/* CONFIG_PM */
-
-void ata_lpm_schedule(struct ata_port *ap, enum link_pm policy)
-{
-	ap->pm_policy = policy;
-	ap->link.eh_info.action |= ATA_EH_LPM;
-	ap->link.eh_info.flags |= ATA_EHI_NO_AUTOPSY;
-	ata_port_schedule_eh(ap);
-}
-
-#ifdef CONFIG_PM
-static void ata_lpm_enable(struct ata_host *host)
-{
-	struct ata_link *link;
-	struct ata_port *ap;
-	struct ata_device *dev;
-	int i;
-
-	for (i = 0; i < host->n_ports; i++) {
-		ap = host->ports[i];
-		ata_for_each_link(link, ap, EDGE) {
-			ata_for_each_dev(dev, link, ALL)
-				ata_dev_disable_pm(dev);
-		}
-	}
-}
-
-static void ata_lpm_disable(struct ata_host *host)
-{
-	int i;
-
-	for (i = 0; i < host->n_ports; i++) {
-		struct ata_port *ap = host->ports[i];
-		ata_lpm_schedule(ap, ap->pm_policy);
-	}
-}
-#endif	/* CONFIG_PM */
-
 /**
  *	ata_dev_classify - determine device type based on ATA-spec signature
  *	@tf: ATA taskfile register set for device to be identified
@@ -1806,8 +1628,14 @@
 		}
 	}
 
+	if (ap->ops->error_handler)
+		ata_eh_release(ap);
+
 	rc = wait_for_completion_timeout(&wait, msecs_to_jiffies(timeout));
 
+	if (ap->ops->error_handler)
+		ata_eh_acquire(ap);
+
 	ata_sff_flush_pio_task(ap);
 
 	if (!rc) {
@@ -2564,13 +2392,6 @@
 	if (dev->flags & ATA_DFLAG_LBA48)
 		dev->max_sectors = ATA_MAX_SECTORS_LBA48;
 
-	if (!(dev->horkage & ATA_HORKAGE_IPM)) {
-		if (ata_id_has_hipm(dev->id))
-			dev->flags |= ATA_DFLAG_HIPM;
-		if (ata_id_has_dipm(dev->id))
-			dev->flags |= ATA_DFLAG_DIPM;
-	}
-
 	/* Limit PATA drive on SATA cable bridge transfers to udma5,
 	   200 sectors */
 	if (ata_dev_knobble(dev)) {
@@ -2591,13 +2412,6 @@
 		dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128,
 					 dev->max_sectors);
 
-	if (ata_dev_blacklisted(dev) & ATA_HORKAGE_IPM) {
-		dev->horkage |= ATA_HORKAGE_IPM;
-
-		/* reset link pm_policy for this port to no pm */
-		ap->pm_policy = MAX_PERFORMANCE;
-	}
-
 	if (ap->ops->dev_config)
 		ap->ops->dev_config(dev);
 
@@ -3596,7 +3410,7 @@
 			warned = 1;
 		}
 
-		msleep(50);
+		ata_msleep(link->ap, 50);
 	}
 }
 
@@ -3617,7 +3431,7 @@
 int ata_wait_after_reset(struct ata_link *link, unsigned long deadline,
 				int (*check_ready)(struct ata_link *link))
 {
-	msleep(ATA_WAIT_AFTER_RESET);
+	ata_msleep(link->ap, ATA_WAIT_AFTER_RESET);
 
 	return ata_wait_ready(link, deadline, check_ready);
 }
@@ -3628,7 +3442,7 @@
  *	@params: timing parameters { interval, duratinon, timeout } in msec
  *	@deadline: deadline jiffies for the operation
  *
-*	Make sure SStatus of @link reaches stable state, determined by
+ *	Make sure SStatus of @link reaches stable state, determined by
  *	holding the same value where DET is not 1 for @duration polled
  *	every @interval, before @timeout.  Timeout constraints the
  *	beginning of the stable state.  Because DET gets stuck at 1 on
@@ -3665,7 +3479,7 @@
 	last_jiffies = jiffies;
 
 	while (1) {
-		msleep(interval);
+		ata_msleep(link->ap, interval);
 		if ((rc = sata_scr_read(link, SCR_STATUS, &cur)))
 			return rc;
 		cur &= 0xf;
@@ -3730,7 +3544,7 @@
 		 * immediately after resuming.  Delay 200ms before
 		 * debouncing.
 		 */
-		msleep(200);
+		ata_msleep(link->ap, 200);
 
 		/* is SControl restored correctly? */
 		if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
@@ -3760,6 +3574,72 @@
 }
 
 /**
+ *	sata_link_scr_lpm - manipulate SControl IPM and SPM fields
+ *	@link: ATA link to manipulate SControl for
+ *	@policy: LPM policy to configure
+ *	@spm_wakeup: initiate LPM transition to active state
+ *
+ *	Manipulate the IPM field of the SControl register of @link
+ *	according to @policy.  If @policy is ATA_LPM_MAX_POWER and
+ *	@spm_wakeup is %true, the SPM field is manipulated to wake up
+ *	the link.  This function also clears PHYRDY_CHG before
+ *	returning.
+ *
+ *	LOCKING:
+ *	EH context.
+ *
+ *	RETURNS:
+ *	0 on succes, -errno otherwise.
+ */
+int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+		      bool spm_wakeup)
+{
+	struct ata_eh_context *ehc = &link->eh_context;
+	bool woken_up = false;
+	u32 scontrol;
+	int rc;
+
+	rc = sata_scr_read(link, SCR_CONTROL, &scontrol);
+	if (rc)
+		return rc;
+
+	switch (policy) {
+	case ATA_LPM_MAX_POWER:
+		/* disable all LPM transitions */
+		scontrol |= (0x3 << 8);
+		/* initiate transition to active state */
+		if (spm_wakeup) {
+			scontrol |= (0x4 << 12);
+			woken_up = true;
+		}
+		break;
+	case ATA_LPM_MED_POWER:
+		/* allow LPM to PARTIAL */
+		scontrol &= ~(0x1 << 8);
+		scontrol |= (0x2 << 8);
+		break;
+	case ATA_LPM_MIN_POWER:
+		/* no restrictions on LPM transitions */
+		scontrol &= ~(0x3 << 8);
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	rc = sata_scr_write(link, SCR_CONTROL, scontrol);
+	if (rc)
+		return rc;
+
+	/* give the link time to transit out of LPM state */
+	if (woken_up)
+		msleep(10);
+
+	/* clear PHYRDY_CHG from SError */
+	ehc->i.serror &= ~SERR_PHYRDY_CHG;
+	return sata_scr_write(link, SCR_ERROR, SERR_PHYRDY_CHG);
+}
+
+/**
  *	ata_std_prereset - prepare for reset
  *	@link: ATA link to be reset
  *	@deadline: deadline jiffies for the operation
@@ -3868,7 +3748,7 @@
 	/* Couldn't find anything in SATA I/II specs, but AHCI-1.1
 	 * 10.4.2 says at least 1 ms.
 	 */
-	msleep(1);
+	ata_msleep(link->ap, 1);
 
 	/* bring link back */
 	rc = sata_link_resume(link, timing, deadline);
@@ -4551,6 +4431,7 @@
 	DPRINTK("EXIT, err_mask=%x\n", err_mask);
 	return err_mask;
 }
+
 /**
  *	ata_dev_set_feature - Issue SET FEATURES - SATA FEATURES
  *	@dev: Device to which command will be sent
@@ -4566,8 +4447,7 @@
  *	RETURNS:
  *	0 on success, AC_ERR_* mask otherwise.
  */
-static unsigned int ata_dev_set_feature(struct ata_device *dev, u8 enable,
-					u8 feature)
+unsigned int ata_dev_set_feature(struct ata_device *dev, u8 enable, u8 feature)
 {
 	struct ata_taskfile tf;
 	unsigned int err_mask;
@@ -4943,8 +4823,13 @@
  *	ata_qc_complete - Complete an active ATA command
  *	@qc: Command to complete
  *
- *	Indicate to the mid and upper layers that an ATA
- *	command has completed, with either an ok or not-ok status.
+ *	Indicate to the mid and upper layers that an ATA command has
+ *	completed, with either an ok or not-ok status.
+ *
+ *	Refrain from calling this function multiple times when
+ *	successfully completing multiple NCQ commands.
+ *	ata_qc_complete_multiple() should be used instead, which will
+ *	properly update IRQ expect state.
  *
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
@@ -5037,6 +4922,10 @@
  *	requests normally.  ap->qc_active and @qc_active is compared
  *	and commands are completed accordingly.
  *
+ *	Always use this function when completing multiple NCQ commands
+ *	from IRQ handlers instead of calling ata_qc_complete()
+ *	multiple times to keep IRQ expect status properly in sync.
+ *
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  *
@@ -5422,12 +5311,6 @@
 	int rc;
 
 	/*
-	 * disable link pm on all ports before requesting
-	 * any pm activity
-	 */
-	ata_lpm_enable(host);
-
-	/*
 	 * On some hardware, device fails to respond after spun down
 	 * for suspend.  As the device won't be used before being
 	 * resumed, we don't need to touch the device.  Ask EH to skip
@@ -5460,9 +5343,6 @@
 	ata_host_request_pm(host, PMSG_ON, ATA_EH_RESET,
 			    ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET, 0);
 	host->dev->power.power_state = PMSG_ON;
-
-	/* reenable link pm */
-	ata_lpm_disable(host);
 }
 #endif
 
@@ -5517,7 +5397,8 @@
 	int i;
 
 	/* clear everything except for devices */
-	memset(link, 0, offsetof(struct ata_link, device[0]));
+	memset((void *)link + ATA_LINK_CLEAR_BEGIN, 0,
+	       ATA_LINK_CLEAR_END - ATA_LINK_CLEAR_BEGIN);
 
 	link->ap = ap;
 	link->pmp = pmp;
@@ -5591,7 +5472,7 @@
 	ap = kzalloc(sizeof(*ap), GFP_KERNEL);
 	if (!ap)
 		return NULL;
-
+	
 	ap->pflags |= ATA_PFLAG_INITIALIZING;
 	ap->lock = &host->lock;
 	ap->print_id = -1;
@@ -5695,6 +5576,7 @@
 	dev_set_drvdata(dev, host);
 
 	spin_lock_init(&host->lock);
+	mutex_init(&host->eh_mutex);
 	host->dev = dev;
 	host->n_ports = max_ports;
 
@@ -5992,6 +5874,7 @@
 		   unsigned long flags, struct ata_port_operations *ops)
 {
 	spin_lock_init(&host->lock);
+	mutex_init(&host->eh_mutex);
 	host->dev = dev;
 	host->flags = flags;
 	host->ops = ops;
@@ -6022,7 +5905,7 @@
 		spin_lock_irqsave(ap->lock, flags);
 
 		ehi->probe_mask |= ATA_ALL_DEVICES;
-		ehi->action |= ATA_EH_RESET | ATA_EH_LPM;
+		ehi->action |= ATA_EH_RESET;
 		ehi->flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET;
 
 		ap->pflags &= ~ATA_PFLAG_INITIALIZING;
@@ -6093,9 +5976,18 @@
 	for (i = 0; i < host->n_ports; i++)
 		host->ports[i]->print_id = ata_print_id++;
 
+	
+	/* Create associated sysfs transport objects  */
+	for (i = 0; i < host->n_ports; i++) {
+		rc = ata_tport_add(host->dev,host->ports[i]);
+		if (rc) {
+			goto err_tadd;
+		}
+	}
+
 	rc = ata_scsi_add_hosts(host, sht);
 	if (rc)
-		return rc;
+		goto err_tadd;
 
 	/* associate with ACPI nodes */
 	ata_acpi_associate(host);
@@ -6136,6 +6028,13 @@
 	}
 
 	return 0;
+
+ err_tadd:
+	while (--i >= 0) {
+		ata_tport_delete(host->ports[i]);
+	}
+	return rc;
+
 }
 
 /**
@@ -6226,6 +6125,13 @@
 	cancel_rearming_delayed_work(&ap->hotplug_task);
 
  skip_eh:
+	if (ap->pmp_link) {
+		int i;
+		for (i = 0; i < SATA_PMP_MAX_PORTS; i++)
+			ata_tlink_delete(&ap->pmp_link[i]);
+	}
+	ata_tport_delete(ap);
+
 	/* remove the associated SCSI host */
 	scsi_remove_host(ap->scsi_host);
 }
@@ -6542,7 +6448,7 @@
 
 static int __init ata_init(void)
 {
-	int rc = -ENOMEM;
+	int rc;
 
 	ata_parse_force_param();
 
@@ -6552,12 +6458,25 @@
 		return rc;
 	}
 
+	libata_transport_init();
+	ata_scsi_transport_template = ata_attach_transport();
+	if (!ata_scsi_transport_template) {
+		ata_sff_exit();
+		rc = -ENOMEM;
+		goto err_out;
+	}		
+
 	printk(KERN_DEBUG "libata version " DRV_VERSION " loaded.\n");
 	return 0;
+
+err_out:
+	return rc;
 }
 
 static void __exit ata_exit(void)
 {
+	ata_release_transport(ata_scsi_transport_template);
+	libata_transport_exit();
 	ata_sff_exit();
 	kfree(ata_force_tbl);
 }
@@ -6573,7 +6492,35 @@
 }
 
 /**
+ *	ata_msleep - ATA EH owner aware msleep
+ *	@ap: ATA port to attribute the sleep to
+ *	@msecs: duration to sleep in milliseconds
+ *
+ *	Sleeps @msecs.  If the current task is owner of @ap's EH, the
+ *	ownership is released before going to sleep and reacquired
+ *	after the sleep is complete.  IOW, other ports sharing the
+ *	@ap->host will be allowed to own the EH while this task is
+ *	sleeping.
+ *
+ *	LOCKING:
+ *	Might sleep.
+ */
+void ata_msleep(struct ata_port *ap, unsigned int msecs)
+{
+	bool owns_eh = ap && ap->host->eh_owner == current;
+
+	if (owns_eh)
+		ata_eh_release(ap);
+
+	msleep(msecs);
+
+	if (owns_eh)
+		ata_eh_acquire(ap);
+}
+
+/**
  *	ata_wait_register - wait until register value changes
+ *	@ap: ATA port to wait register for, can be NULL
  *	@reg: IO-mapped register
  *	@mask: Mask to apply to read register value
  *	@val: Wait condition
@@ -6595,7 +6542,7 @@
  *	RETURNS:
  *	The final register value.
  */
-u32 ata_wait_register(void __iomem *reg, u32 mask, u32 val,
+u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask, u32 val,
 		      unsigned long interval, unsigned long timeout)
 {
 	unsigned long deadline;
@@ -6610,7 +6557,7 @@
 	deadline = ata_deadline(jiffies, timeout);
 
 	while ((tmp & mask) == val && time_before(jiffies, deadline)) {
-		msleep(interval);
+		ata_msleep(ap, interval);
 		tmp = ioread32(reg);
 	}
 
@@ -6686,6 +6633,7 @@
 EXPORT_SYMBOL_GPL(ata_wait_after_reset);
 EXPORT_SYMBOL_GPL(sata_link_debounce);
 EXPORT_SYMBOL_GPL(sata_link_resume);
+EXPORT_SYMBOL_GPL(sata_link_scr_lpm);
 EXPORT_SYMBOL_GPL(ata_std_prereset);
 EXPORT_SYMBOL_GPL(sata_link_hardreset);
 EXPORT_SYMBOL_GPL(sata_std_hardreset);
@@ -6693,6 +6641,7 @@
 EXPORT_SYMBOL_GPL(ata_dev_classify);
 EXPORT_SYMBOL_GPL(ata_dev_pair);
 EXPORT_SYMBOL_GPL(ata_ratelimit);
+EXPORT_SYMBOL_GPL(ata_msleep);
 EXPORT_SYMBOL_GPL(ata_wait_register);
 EXPORT_SYMBOL_GPL(ata_scsi_queuecmd);
 EXPORT_SYMBOL_GPL(ata_scsi_slave_config);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index e48302e..5e59050 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -57,6 +57,7 @@
 	/* error flags */
 	ATA_EFLAG_IS_IO			= (1 << 0),
 	ATA_EFLAG_DUBIOUS_XFER		= (1 << 1),
+	ATA_EFLAG_OLD_ER                = (1 << 31),
 
 	/* error categories */
 	ATA_ECAT_NONE			= 0,
@@ -396,14 +397,9 @@
 	return NULL;
 }
 
-static void ata_ering_clear(struct ata_ering *ering)
-{
-	memset(ering, 0, sizeof(*ering));
-}
-
-static int ata_ering_map(struct ata_ering *ering,
-			 int (*map_fn)(struct ata_ering_entry *, void *),
-			 void *arg)
+int ata_ering_map(struct ata_ering *ering,
+		  int (*map_fn)(struct ata_ering_entry *, void *),
+		  void *arg)
 {
 	int idx, rc = 0;
 	struct ata_ering_entry *ent;
@@ -422,6 +418,17 @@
 	return rc;
 }
 
+int ata_ering_clear_cb(struct ata_ering_entry *ent, void *void_arg)
+{
+	ent->eflags |= ATA_EFLAG_OLD_ER;
+	return 0;
+}
+
+static void ata_ering_clear(struct ata_ering *ering)
+{
+	ata_ering_map(ering, ata_ering_clear_cb, NULL);
+}
+
 static unsigned int ata_eh_dev_action(struct ata_device *dev)
 {
 	struct ata_eh_context *ehc = &dev->link->eh_context;
@@ -456,6 +463,41 @@
 }
 
 /**
+ *	ata_eh_acquire - acquire EH ownership
+ *	@ap: ATA port to acquire EH ownership for
+ *
+ *	Acquire EH ownership for @ap.  This is the basic exclusion
+ *	mechanism for ports sharing a host.  Only one port hanging off
+ *	the same host can claim the ownership of EH.
+ *
+ *	LOCKING:
+ *	EH context.
+ */
+void ata_eh_acquire(struct ata_port *ap)
+{
+	mutex_lock(&ap->host->eh_mutex);
+	WARN_ON_ONCE(ap->host->eh_owner);
+	ap->host->eh_owner = current;
+}
+
+/**
+ *	ata_eh_release - release EH ownership
+ *	@ap: ATA port to release EH ownership for
+ *
+ *	Release EH ownership for @ap if the caller.  The caller must
+ *	have acquired EH ownership using ata_eh_acquire() previously.
+ *
+ *	LOCKING:
+ *	EH context.
+ */
+void ata_eh_release(struct ata_port *ap)
+{
+	WARN_ON_ONCE(ap->host->eh_owner != current);
+	ap->host->eh_owner = NULL;
+	mutex_unlock(&ap->host->eh_mutex);
+}
+
+/**
  *	ata_scsi_timed_out - SCSI layer time out callback
  *	@cmd: timed out SCSI command
  *
@@ -572,19 +614,19 @@
 		int nr_timedout = 0;
 
 		spin_lock_irqsave(ap->lock, flags);
-		
+
 		/* This must occur under the ap->lock as we don't want
 		   a polled recovery to race the real interrupt handler
-		   
+
 		   The lost_interrupt handler checks for any completed but
 		   non-notified command and completes much like an IRQ handler.
-		   
+
 		   We then fall into the error recovery code which will treat
 		   this as if normal completion won the race */
 
 		if (ap->ops->lost_interrupt)
 			ap->ops->lost_interrupt(ap);
-			
+
 		list_for_each_entry_safe(scmd, tmp, &host->eh_cmd_q, eh_entry) {
 			struct ata_queued_cmd *qc;
 
@@ -628,15 +670,17 @@
 		ap->eh_tries = ATA_EH_MAX_TRIES;
 	} else
 		spin_unlock_wait(ap->lock);
-		
+
 	/* If we timed raced normal completion and there is nothing to
 	   recover nr_timedout == 0 why exactly are we doing error recovery ? */
 
- repeat:
 	/* invoke error handler */
 	if (ap->ops->error_handler) {
 		struct ata_link *link;
 
+		/* acquire EH ownership */
+		ata_eh_acquire(ap);
+ repeat:
 		/* kill fast drain timer */
 		del_timer_sync(&ap->fastdrain_timer);
 
@@ -711,6 +755,7 @@
 		host->host_eh_scheduled = 0;
 
 		spin_unlock_irqrestore(ap->lock, flags);
+		ata_eh_release(ap);
 	} else {
 		WARN_ON(ata_qc_from_tag(ap, ap->link.active_tag) == NULL);
 		ap->ops->eng_timeout(ap);
@@ -772,7 +817,7 @@
 
 	/* make sure SCSI EH is complete */
 	if (scsi_host_in_recovery(ap->scsi_host)) {
-		msleep(10);
+		ata_msleep(ap, 10);
 		goto retry;
 	}
 }
@@ -1573,9 +1618,9 @@
 	 * host links.  For disabled PMP links, only N bit is
 	 * considered as X bit is left at 1 for link plugging.
 	 */
-	hotplug_mask = 0;
-
-	if (!(link->flags & ATA_LFLAG_DISABLED) || ata_is_host_link(link))
+	if (link->lpm_policy != ATA_LPM_MAX_POWER)
+		hotplug_mask = 0;	/* hotplug doesn't work w/ LPM */
+	else if (!(link->flags & ATA_LFLAG_DISABLED) || ata_is_host_link(link))
 		hotplug_mask = SERR_PHYRDY_CHG | SERR_DEV_XCHG;
 	else
 		hotplug_mask = SERR_PHYRDY_CHG;
@@ -1755,7 +1800,7 @@
 	struct speed_down_verdict_arg *arg = void_arg;
 	int cat;
 
-	if (ent->timestamp < arg->since)
+	if ((ent->eflags & ATA_EFLAG_OLD_ER) || (ent->timestamp < arg->since))
 		return -1;
 
 	cat = ata_eh_categorize_error(ent->eflags, ent->err_mask,
@@ -2777,8 +2822,9 @@
 	ata_eh_done(link, NULL, ATA_EH_RESET);
 	if (slave)
 		ata_eh_done(slave, NULL, ATA_EH_RESET);
-	ehc->last_reset = jiffies;	/* update to completion time */
+	ehc->last_reset = jiffies;		/* update to completion time */
 	ehc->i.action |= ATA_EH_REVALIDATE;
+	link->lpm_policy = ATA_LPM_UNKNOWN;	/* reset LPM state */
 
 	rc = 0;
  out:
@@ -2810,8 +2856,10 @@
 			"reset failed (errno=%d), retrying in %u secs\n",
 			rc, DIV_ROUND_UP(jiffies_to_msecs(delta), 1000));
 
+		ata_eh_release(ap);
 		while (delta)
 			delta = schedule_timeout_uninterruptible(delta);
+		ata_eh_acquire(ap);
 	}
 
 	if (try == max_tries - 1) {
@@ -3204,6 +3252,124 @@
 	return rc;
 }
 
+/**
+ *	ata_eh_set_lpm - configure SATA interface power management
+ *	@link: link to configure power management
+ *	@policy: the link power management policy
+ *	@r_failed_dev: out parameter for failed device
+ *
+ *	Enable SATA Interface power management.  This will enable
+ *	Device Interface Power Management (DIPM) for min_power
+ * 	policy, and then call driver specific callbacks for
+ *	enabling Host Initiated Power management.
+ *
+ *	LOCKING:
+ *	EH context.
+ *
+ *	RETURNS:
+ *	0 on success, -errno on failure.
+ */
+static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+			  struct ata_device **r_failed_dev)
+{
+	struct ata_port *ap = ata_is_host_link(link) ? link->ap : NULL;
+	struct ata_eh_context *ehc = &link->eh_context;
+	struct ata_device *dev, *link_dev = NULL, *lpm_dev = NULL;
+	unsigned int hints = ATA_LPM_EMPTY | ATA_LPM_HIPM;
+	unsigned int err_mask;
+	int rc;
+
+	/* if the link or host doesn't do LPM, noop */
+	if ((link->flags & ATA_LFLAG_NO_LPM) || (ap && !ap->ops->set_lpm))
+		return 0;
+
+	/*
+	 * DIPM is enabled only for MIN_POWER as some devices
+	 * misbehave when the host NACKs transition to SLUMBER.  Order
+	 * device and link configurations such that the host always
+	 * allows DIPM requests.
+	 */
+	ata_for_each_dev(dev, link, ENABLED) {
+		bool hipm = ata_id_has_hipm(dev->id);
+		bool dipm = ata_id_has_dipm(dev->id);
+
+		/* find the first enabled and LPM enabled devices */
+		if (!link_dev)
+			link_dev = dev;
+
+		if (!lpm_dev && (hipm || dipm))
+			lpm_dev = dev;
+
+		hints &= ~ATA_LPM_EMPTY;
+		if (!hipm)
+			hints &= ~ATA_LPM_HIPM;
+
+		/* disable DIPM before changing link config */
+		if (policy != ATA_LPM_MIN_POWER && dipm) {
+			err_mask = ata_dev_set_feature(dev,
+					SETFEATURES_SATA_DISABLE, SATA_DIPM);
+			if (err_mask && err_mask != AC_ERR_DEV) {
+				ata_dev_printk(dev, KERN_WARNING,
+					"failed to disable DIPM, Emask 0x%x\n",
+					err_mask);
+				rc = -EIO;
+				goto fail;
+			}
+		}
+	}
+
+	if (ap) {
+		rc = ap->ops->set_lpm(link, policy, hints);
+		if (!rc && ap->slave_link)
+			rc = ap->ops->set_lpm(ap->slave_link, policy, hints);
+	} else
+		rc = sata_pmp_set_lpm(link, policy, hints);
+
+	/*
+	 * Attribute link config failure to the first (LPM) enabled
+	 * device on the link.
+	 */
+	if (rc) {
+		if (rc == -EOPNOTSUPP) {
+			link->flags |= ATA_LFLAG_NO_LPM;
+			return 0;
+		}
+		dev = lpm_dev ? lpm_dev : link_dev;
+		goto fail;
+	}
+
+	/* host config updated, enable DIPM if transitioning to MIN_POWER */
+	ata_for_each_dev(dev, link, ENABLED) {
+		if (policy == ATA_LPM_MIN_POWER && ata_id_has_dipm(dev->id)) {
+			err_mask = ata_dev_set_feature(dev,
+					SETFEATURES_SATA_ENABLE, SATA_DIPM);
+			if (err_mask && err_mask != AC_ERR_DEV) {
+				ata_dev_printk(dev, KERN_WARNING,
+					"failed to enable DIPM, Emask 0x%x\n",
+					err_mask);
+				rc = -EIO;
+				goto fail;
+			}
+		}
+	}
+
+	link->lpm_policy = policy;
+	if (ap && ap->slave_link)
+		ap->slave_link->lpm_policy = policy;
+	return 0;
+
+fail:
+	/* if no device or only one more chance is left, disable LPM */
+	if (!dev || ehc->tries[dev->devno] <= 2) {
+		ata_link_printk(link, KERN_WARNING,
+				"disabling LPM on the link\n");
+		link->flags |= ATA_LFLAG_NO_LPM;
+	}
+	if (r_failed_dev)
+		*r_failed_dev = dev;
+	return rc;
+}
+
 static int ata_link_nr_enabled(struct ata_link *link)
 {
 	struct ata_device *dev;
@@ -3288,6 +3454,16 @@
 	ehc->saved_xfer_mode[dev->devno] = 0;
 	ehc->saved_ncq_enabled &= ~(1 << dev->devno);
 
+	/* the link maybe in a deep sleep, wake it up */
+	if (link->lpm_policy > ATA_LPM_MAX_POWER) {
+		if (ata_is_host_link(link))
+			link->ap->ops->set_lpm(link, ATA_LPM_MAX_POWER,
+					       ATA_LPM_EMPTY);
+		else
+			sata_pmp_set_lpm(link, ATA_LPM_MAX_POWER,
+					 ATA_LPM_EMPTY);
+	}
+
 	/* Record and count probe trials on the ering.  The specific
 	 * error mask used is irrelevant.  Because a successful device
 	 * detection clears the ering, this count accumulates only if
@@ -3389,8 +3565,7 @@
 {
 	struct ata_link *link;
 	struct ata_device *dev;
-	int nr_failed_devs;
-	int rc;
+	int rc, nr_fails;
 	unsigned long flags, deadline;
 
 	DPRINTK("ENTER\n");
@@ -3431,7 +3606,6 @@
 
  retry:
 	rc = 0;
-	nr_failed_devs = 0;
 
 	/* if UNLOADING, finish immediately */
 	if (ap->pflags & ATA_PFLAG_UNLOADING)
@@ -3501,8 +3675,10 @@
 		if (time_before_eq(deadline, now))
 			break;
 
+		ata_eh_release(ap);
 		deadline = wait_for_completion_timeout(&ap->park_req_pending,
 						       deadline - now);
+		ata_eh_acquire(ap);
 	} while (deadline);
 	ata_for_each_link(link, ap, EDGE) {
 		ata_for_each_dev(dev, link, ALL) {
@@ -3516,13 +3692,17 @@
 	}
 
 	/* the rest */
-	ata_for_each_link(link, ap, EDGE) {
+	nr_fails = 0;
+	ata_for_each_link(link, ap, PMP_FIRST) {
 		struct ata_eh_context *ehc = &link->eh_context;
 
+		if (sata_pmp_attached(ap) && ata_is_host_link(link))
+			goto config_lpm;
+
 		/* revalidate existing devices and attach new ones */
 		rc = ata_eh_revalidate_and_attach(link, &dev);
 		if (rc)
-			goto dev_fail;
+			goto rest_fail;
 
 		/* if PMP got attached, return, pmp EH will take care of it */
 		if (link->device->class == ATA_DEV_PMP) {
@@ -3534,7 +3714,7 @@
 		if (ehc->i.flags & ATA_EHI_SETMODE) {
 			rc = ata_set_mode(link, &dev);
 			if (rc)
-				goto dev_fail;
+				goto rest_fail;
 			ehc->i.flags &= ~ATA_EHI_SETMODE;
 		}
 
@@ -3547,7 +3727,7 @@
 					continue;
 				rc = atapi_eh_clear_ua(dev);
 				if (rc)
-					goto dev_fail;
+					goto rest_fail;
 			}
 		}
 
@@ -3557,21 +3737,25 @@
 				continue;
 			rc = ata_eh_maybe_retry_flush(dev);
 			if (rc)
-				goto dev_fail;
+				goto rest_fail;
 		}
 
+	config_lpm:
 		/* configure link power saving */
-		if (ehc->i.action & ATA_EH_LPM)
-			ata_for_each_dev(dev, link, ALL)
-				ata_dev_enable_pm(dev, ap->pm_policy);
+		if (link->lpm_policy != ap->target_lpm_policy) {
+			rc = ata_eh_set_lpm(link, ap->target_lpm_policy, &dev);
+			if (rc)
+				goto rest_fail;
+		}
 
 		/* this link is okay now */
 		ehc->i.flags = 0;
 		continue;
 
-dev_fail:
-		nr_failed_devs++;
-		ata_eh_handle_dev_fail(dev, rc);
+	rest_fail:
+		nr_fails++;
+		if (dev)
+			ata_eh_handle_dev_fail(dev, rc);
 
 		if (ap->pflags & ATA_PFLAG_FROZEN) {
 			/* PMP reset requires working host port.
@@ -3583,7 +3767,7 @@
 		}
 	}
 
-	if (nr_failed_devs)
+	if (nr_fails)
 		goto retry;
 
  out:
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 224faab..3120596 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -11,6 +11,7 @@
 #include <linux/libata.h>
 #include <linux/slab.h>
 #include "libata.h"
+#include "libata-transport.h"
 
 const struct ata_port_operations sata_pmp_port_ops = {
 	.inherits		= &sata_port_ops,
@@ -185,6 +186,27 @@
 }
 
 /**
+ *	sata_pmp_set_lpm - configure LPM for a PMP link
+ *	@link: PMP link to configure LPM for
+ *	@policy: target LPM policy
+ *	@hints: LPM hints
+ *
+ *	Configure LPM for @link.  This function will contain any PMP
+ *	specific workarounds if necessary.
+ *
+ *	LOCKING:
+ *	EH context.
+ *
+ *	RETURNS:
+ *	0 on success, -errno on failure.
+ */
+int sata_pmp_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+		     unsigned hints)
+{
+	return sata_link_scr_lpm(link, policy, true);
+}
+
+/**
  *	sata_pmp_read_gscr - read GSCR block of SATA PMP
  *	@dev: PMP device
  *	@gscr: buffer to read GSCR block into
@@ -312,10 +334,10 @@
 	return rc;
 }
 
-static int sata_pmp_init_links(struct ata_port *ap, int nr_ports)
+static int sata_pmp_init_links (struct ata_port *ap, int nr_ports)
 {
 	struct ata_link *pmp_link = ap->pmp_link;
-	int i;
+	int i, err;
 
 	if (!pmp_link) {
 		pmp_link = kzalloc(sizeof(pmp_link[0]) * SATA_PMP_MAX_PORTS,
@@ -327,6 +349,13 @@
 			ata_link_init(ap, &pmp_link[i], i);
 
 		ap->pmp_link = pmp_link;
+
+		for (i = 0; i < SATA_PMP_MAX_PORTS; i++) {
+			err = ata_tlink_add(&pmp_link[i]);
+			if (err) {
+				goto err_tlink;
+			}
+		}
 	}
 
 	for (i = 0; i < nr_ports; i++) {
@@ -339,6 +368,12 @@
 	}
 
 	return 0;
+  err_tlink:
+	while (--i >= 0)
+		ata_tlink_delete(&pmp_link[i]);
+	kfree(pmp_link);
+	ap->pmp_link = NULL;
+	return err;
 }
 
 static void sata_pmp_quirks(struct ata_port *ap)
@@ -351,6 +386,9 @@
 	if (vendor == 0x1095 && devid == 0x3726) {
 		/* sil3726 quirks */
 		ata_for_each_link(link, ap, EDGE) {
+			/* link reports offline after LPM */
+			link->flags |= ATA_LFLAG_NO_LPM;
+
 			/* Class code report is unreliable and SRST
 			 * times out under certain configurations.
 			 */
@@ -366,6 +404,9 @@
 	} else if (vendor == 0x1095 && devid == 0x4723) {
 		/* sil4723 quirks */
 		ata_for_each_link(link, ap, EDGE) {
+			/* link reports offline after LPM */
+			link->flags |= ATA_LFLAG_NO_LPM;
+
 			/* class code report is unreliable */
 			if (link->pmp < 2)
 				link->flags |= ATA_LFLAG_ASSUME_ATA;
@@ -378,6 +419,9 @@
 	} else if (vendor == 0x1095 && devid == 0x4726) {
 		/* sil4726 quirks */
 		ata_for_each_link(link, ap, EDGE) {
+			/* link reports offline after LPM */
+			link->flags |= ATA_LFLAG_NO_LPM;
+
 			/* Class code report is unreliable and SRST
 			 * times out under certain configurations.
 			 * Config device can be at port 0 or 5 and
@@ -938,15 +982,25 @@
 	if (rc)
 		goto link_fail;
 
-	/* Connection status might have changed while resetting other
-	 * links, check SATA_PMP_GSCR_ERROR before returning.
-	 */
-
 	/* clear SNotification */
 	rc = sata_scr_read(&ap->link, SCR_NOTIFICATION, &sntf);
 	if (rc == 0)
 		sata_scr_write(&ap->link, SCR_NOTIFICATION, sntf);
 
+	/*
+	 * If LPM is active on any fan-out port, hotplug wouldn't
+	 * work.  Return w/ PHY event notification disabled.
+	 */
+	ata_for_each_link(link, ap, EDGE)
+		if (link->lpm_policy > ATA_LPM_MAX_POWER)
+			return 0;
+
+	/*
+	 * Connection status might have changed while resetting other
+	 * links, enable notification and check SATA_PMP_GSCR_ERROR
+	 * before returning.
+	 */
+
 	/* enable notification */
 	if (pmp_dev->flags & ATA_DFLAG_AN) {
 		gscr[SATA_PMP_GSCR_FEAT_EN] |= SATA_PMP_FEAT_NOTIFY;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index a89172c..d050e07 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -51,8 +51,8 @@
 #include <asm/unaligned.h>
 
 #include "libata.h"
+#include "libata-transport.h"
 
-#define SECTOR_SIZE		512
 #define ATA_SCSI_RBUF_SIZE	4096
 
 static DEFINE_SPINLOCK(ata_scsi_rbuf_lock);
@@ -64,9 +64,6 @@
 					const struct scsi_device *scsidev);
 static struct ata_device *ata_scsi_find_dev(struct ata_port *ap,
 					    const struct scsi_device *scsidev);
-static int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
-			      unsigned int id, unsigned int lun);
-
 
 #define RW_RECOVERY_MPAGE 0x1
 #define RW_RECOVERY_MPAGE_LEN 12
@@ -106,83 +103,55 @@
 	0, 30	/* extended self test time, see 05-359r1 */
 };
 
-/*
- * libata transport template.  libata doesn't do real transport stuff.
- * It just needs the eh_timed_out hook.
- */
-static struct scsi_transport_template ata_scsi_transport_template = {
-	.eh_strategy_handler	= ata_scsi_error,
-	.eh_timed_out		= ata_scsi_timed_out,
-	.user_scan		= ata_scsi_user_scan,
+static const char *ata_lpm_policy_names[] = {
+	[ATA_LPM_UNKNOWN]	= "max_performance",
+	[ATA_LPM_MAX_POWER]	= "max_performance",
+	[ATA_LPM_MED_POWER]	= "medium_power",
+	[ATA_LPM_MIN_POWER]	= "min_power",
 };
 
-
-static const struct {
-	enum link_pm	value;
-	const char	*name;
-} link_pm_policy[] = {
-	{ NOT_AVAILABLE, "max_performance" },
-	{ MIN_POWER, "min_power" },
-	{ MAX_PERFORMANCE, "max_performance" },
-	{ MEDIUM_POWER, "medium_power" },
-};
-
-static const char *ata_scsi_lpm_get(enum link_pm policy)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(link_pm_policy); i++)
-		if (link_pm_policy[i].value == policy)
-			return link_pm_policy[i].name;
-
-	return NULL;
-}
-
-static ssize_t ata_scsi_lpm_put(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t count)
+static ssize_t ata_scsi_lpm_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
 {
 	struct Scsi_Host *shost = class_to_shost(dev);
 	struct ata_port *ap = ata_shost_to_port(shost);
-	enum link_pm policy = 0;
-	int i;
+	enum ata_lpm_policy policy;
+	unsigned long flags;
 
-	/*
-	 * we are skipping array location 0 on purpose - this
-	 * is because a value of NOT_AVAILABLE is displayed
-	 * to the user as max_performance, but when the user
-	 * writes "max_performance", they actually want the
-	 * value to match MAX_PERFORMANCE.
-	 */
-	for (i = 1; i < ARRAY_SIZE(link_pm_policy); i++) {
-		const int len = strlen(link_pm_policy[i].name);
-		if (strncmp(link_pm_policy[i].name, buf, len) == 0) {
-			policy = link_pm_policy[i].value;
+	/* UNKNOWN is internal state, iterate from MAX_POWER */
+	for (policy = ATA_LPM_MAX_POWER;
+	     policy < ARRAY_SIZE(ata_lpm_policy_names); policy++) {
+		const char *name = ata_lpm_policy_names[policy];
+
+		if (strncmp(name, buf, strlen(name)) == 0)
 			break;
-		}
 	}
-	if (!policy)
+	if (policy == ARRAY_SIZE(ata_lpm_policy_names))
 		return -EINVAL;
 
-	ata_lpm_schedule(ap, policy);
+	spin_lock_irqsave(ap->lock, flags);
+	ap->target_lpm_policy = policy;
+	ata_port_schedule_eh(ap);
+	spin_unlock_irqrestore(ap->lock, flags);
+
 	return count;
 }
 
-static ssize_t
-ata_scsi_lpm_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t ata_scsi_lpm_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
 {
 	struct Scsi_Host *shost = class_to_shost(dev);
 	struct ata_port *ap = ata_shost_to_port(shost);
-	const char *policy =
-		ata_scsi_lpm_get(ap->pm_policy);
 
-	if (!policy)
+	if (ap->target_lpm_policy >= ARRAY_SIZE(ata_lpm_policy_names))
 		return -EINVAL;
 
-	return snprintf(buf, 23, "%s\n", policy);
+	return snprintf(buf, PAGE_SIZE, "%s\n",
+			ata_lpm_policy_names[ap->target_lpm_policy]);
 }
 DEVICE_ATTR(link_power_management_policy, S_IRUGO | S_IWUSR,
-		ata_scsi_lpm_show, ata_scsi_lpm_put);
+	    ata_scsi_lpm_show, ata_scsi_lpm_store);
 EXPORT_SYMBOL_GPL(dev_attr_link_power_management_policy);
 
 static ssize_t ata_scsi_park_show(struct device *device,
@@ -516,7 +485,7 @@
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 
 	if (args[3]) {
-		argsize = SECTOR_SIZE * args[3];
+		argsize = ATA_SECT_SIZE * args[3];
 		argbuf = kmalloc(argsize, GFP_KERNEL);
 		if (argbuf == NULL) {
 			rc = -ENOMEM;
@@ -1150,8 +1119,9 @@
 		blk_queue_dma_drain(q, atapi_drain_needed, buf, ATAPI_MAX_DRAIN);
 	} else {
 		/* ATA devices must be sector aligned */
+		sdev->sector_size = ata_id_logical_sector_size(dev->id);
 		blk_queue_update_dma_alignment(sdev->request_queue,
-					       ATA_SECT_SIZE - 1);
+					       sdev->sector_size - 1);
 		sdev->manage_start_stop = 1;
 	}
 
@@ -1166,6 +1136,7 @@
 		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth);
 	}
 
+	dev->sdev = sdev;
 	return 0;
 }
 
@@ -1696,7 +1667,7 @@
 		goto nothing_to_do;
 
 	qc->flags |= ATA_QCFLAG_IO;
-	qc->nbytes = n_block * ATA_SECT_SIZE;
+	qc->nbytes = n_block * scmd->device->sector_size;
 
 	rc = ata_build_rw_tf(&qc->tf, qc->dev, block, n_block, tf_flags,
 			     qc->tag);
@@ -2001,6 +1972,7 @@
 		0x89,	/* page 0x89, ata info page */
 		0xb0,	/* page 0xb0, block limits page */
 		0xb1,	/* page 0xb1, block device characteristics page */
+		0xb2,	/* page 0xb2, thin provisioning page */
 	};
 
 	rbuf[3] = sizeof(pages);	/* number of supported VPD pages */
@@ -2123,7 +2095,7 @@
 
 static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf)
 {
-	u32 min_io_sectors;
+	u16 min_io_sectors;
 
 	rbuf[1] = 0xb0;
 	rbuf[3] = 0x3c;		/* required VPD size with unmap support */
@@ -2135,10 +2107,7 @@
 	 * logical than physical sector size we need to figure out what the
 	 * latter is.
 	 */
-	if (ata_id_has_large_logical_sectors(args->id))
-		min_io_sectors = ata_id_logical_per_physical_sectors(args->id);
-	else
-		min_io_sectors = 1;
+	min_io_sectors = 1 << ata_id_log2_per_physical_sector(args->id);
 	put_unaligned_be16(min_io_sectors, &rbuf[6]);
 
 	/*
@@ -2172,6 +2141,16 @@
 	return 0;
 }
 
+static unsigned int ata_scsiop_inq_b2(struct ata_scsi_args *args, u8 *rbuf)
+{
+	/* SCSI Thin Provisioning VPD page: SBC-3 rev 22 or later */
+	rbuf[1] = 0xb2;
+	rbuf[3] = 0x4;
+	rbuf[5] = 1 << 6;	/* TPWS */
+
+	return 0;
+}
+
 /**
  *	ata_scsiop_noop - Command handler that simply returns success.
  *	@args: device IDENTIFY data / SCSI command of interest.
@@ -2397,21 +2376,13 @@
 {
 	struct ata_device *dev = args->dev;
 	u64 last_lba = dev->n_sectors - 1; /* LBA of the last block */
-	u8 log_per_phys = 0;
-	u16 lowest_aligned = 0;
-	u16 word_106 = dev->id[106];
-	u16 word_209 = dev->id[209];
+	u32 sector_size; /* physical sector size in bytes */
+	u8 log2_per_phys;
+	u16 lowest_aligned;
 
-	if ((word_106 & 0xc000) == 0x4000) {
-		/* Number and offset of logical sectors per physical sector */
-		if (word_106 & (1 << 13))
-			log_per_phys = word_106 & 0xf;
-		if ((word_209 & 0xc000) == 0x4000) {
-			u16 first = dev->id[209] & 0x3fff;
-			if (first > 0)
-				lowest_aligned = (1 << log_per_phys) - first;
-		}
-	}
+	sector_size = ata_id_logical_sector_size(dev->id);
+	log2_per_phys = ata_id_log2_per_physical_sector(dev->id);
+	lowest_aligned = ata_id_logical_sector_offset(dev->id, log2_per_phys);
 
 	VPRINTK("ENTER\n");
 
@@ -2426,8 +2397,10 @@
 		rbuf[3] = last_lba;
 
 		/* sector size */
-		rbuf[6] = ATA_SECT_SIZE >> 8;
-		rbuf[7] = ATA_SECT_SIZE & 0xff;
+		rbuf[4] = sector_size >> (8 * 3);
+		rbuf[5] = sector_size >> (8 * 2);
+		rbuf[6] = sector_size >> (8 * 1);
+		rbuf[7] = sector_size;
 	} else {
 		/* sector count, 64-bit */
 		rbuf[0] = last_lba >> (8 * 7);
@@ -2440,11 +2413,13 @@
 		rbuf[7] = last_lba;
 
 		/* sector size */
-		rbuf[10] = ATA_SECT_SIZE >> 8;
-		rbuf[11] = ATA_SECT_SIZE & 0xff;
+		rbuf[ 8] = sector_size >> (8 * 3);
+		rbuf[ 9] = sector_size >> (8 * 2);
+		rbuf[10] = sector_size >> (8 * 1);
+		rbuf[11] = sector_size;
 
 		rbuf[12] = 0;
-		rbuf[13] = log_per_phys;
+		rbuf[13] = log2_per_phys;
 		rbuf[14] = (lowest_aligned >> 8) & 0x3f;
 		rbuf[15] = lowest_aligned;
 
@@ -2888,9 +2863,8 @@
 	tf->device = dev->devno ?
 		tf->device | ATA_DEV1 : tf->device & ~ATA_DEV1;
 
-	/* READ/WRITE LONG use a non-standard sect_size */
-	qc->sect_size = ATA_SECT_SIZE;
 	switch (tf->command) {
+	/* READ/WRITE LONG use a non-standard sect_size */
 	case ATA_CMD_READ_LONG:
 	case ATA_CMD_READ_LONG_ONCE:
 	case ATA_CMD_WRITE_LONG:
@@ -2898,6 +2872,45 @@
 		if (tf->protocol != ATA_PROT_PIO || tf->nsect != 1)
 			goto invalid_fld;
 		qc->sect_size = scsi_bufflen(scmd);
+		break;
+
+	/* commands using reported Logical Block size (e.g. 512 or 4K) */
+	case ATA_CMD_CFA_WRITE_NE:
+	case ATA_CMD_CFA_TRANS_SECT:
+	case ATA_CMD_CFA_WRITE_MULT_NE:
+	/* XXX: case ATA_CMD_CFA_WRITE_SECTORS_WITHOUT_ERASE: */
+	case ATA_CMD_READ:
+	case ATA_CMD_READ_EXT:
+	case ATA_CMD_READ_QUEUED:
+	/* XXX: case ATA_CMD_READ_QUEUED_EXT: */
+	case ATA_CMD_FPDMA_READ:
+	case ATA_CMD_READ_MULTI:
+	case ATA_CMD_READ_MULTI_EXT:
+	case ATA_CMD_PIO_READ:
+	case ATA_CMD_PIO_READ_EXT:
+	case ATA_CMD_READ_STREAM_DMA_EXT:
+	case ATA_CMD_READ_STREAM_EXT:
+	case ATA_CMD_VERIFY:
+	case ATA_CMD_VERIFY_EXT:
+	case ATA_CMD_WRITE:
+	case ATA_CMD_WRITE_EXT:
+	case ATA_CMD_WRITE_FUA_EXT:
+	case ATA_CMD_WRITE_QUEUED:
+	case ATA_CMD_WRITE_QUEUED_FUA_EXT:
+	case ATA_CMD_FPDMA_WRITE:
+	case ATA_CMD_WRITE_MULTI:
+	case ATA_CMD_WRITE_MULTI_EXT:
+	case ATA_CMD_WRITE_MULTI_FUA_EXT:
+	case ATA_CMD_PIO_WRITE:
+	case ATA_CMD_PIO_WRITE_EXT:
+	case ATA_CMD_WRITE_STREAM_DMA_EXT:
+	case ATA_CMD_WRITE_STREAM_EXT:
+		qc->sect_size = scmd->device->sector_size;
+		break;
+
+	/* Everything else uses 512 byte "sectors" */
+	default:
+		qc->sect_size = ATA_SECT_SIZE;
 	}
 
 	/*
@@ -3250,6 +3263,9 @@
 		case 0xb1:
 			ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b1);
 			break;
+		case 0xb2:
+			ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b2);
+			break;
 		default:
 			ata_scsi_invalid_field(cmd, done);
 			break;
@@ -3334,7 +3350,7 @@
 		*(struct ata_port **)&shost->hostdata[0] = ap;
 		ap->scsi_host = shost;
 
-		shost->transportt = &ata_scsi_transport_template;
+		shost->transportt = ata_scsi_transport_template;
 		shost->unique_id = ap->print_id;
 		shost->max_id = 16;
 		shost->max_lun = 1;
@@ -3393,6 +3409,8 @@
 			if (!IS_ERR(sdev)) {
 				dev->sdev = sdev;
 				scsi_device_put(sdev);
+			} else {
+				dev->sdev = NULL;
 			}
 		}
 	}
@@ -3616,8 +3634,8 @@
  *	RETURNS:
  *	Zero.
  */
-static int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
-			      unsigned int id, unsigned int lun)
+int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
+		       unsigned int id, unsigned int lun)
 {
 	struct ata_port *ap = ata_shost_to_port(shost);
 	unsigned long flags;
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index e30c537..d05387d 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -222,7 +222,7 @@
 	timeout = ata_deadline(timer_start, tmout_pat);
 	while (status != 0xff && (status & ATA_BUSY) &&
 	       time_before(jiffies, timeout)) {
-		msleep(50);
+		ata_msleep(ap, 50);
 		status = ata_sff_busy_wait(ap, ATA_BUSY, 3);
 	}
 
@@ -234,7 +234,7 @@
 	timeout = ata_deadline(timer_start, tmout);
 	while (status != 0xff && (status & ATA_BUSY) &&
 	       time_before(jiffies, timeout)) {
-		msleep(50);
+		ata_msleep(ap, 50);
 		status = ap->ops->sff_check_status(ap);
 	}
 
@@ -360,7 +360,7 @@
 
 	if (wait) {
 		if (can_sleep && ap->link.device[device].class == ATA_DEV_ATAPI)
-			msleep(150);
+			ata_msleep(ap, 150);
 		ata_wait_idle(ap);
 	}
 }
@@ -1356,7 +1356,7 @@
 	 */
 	status = ata_sff_busy_wait(ap, ATA_BUSY, 5);
 	if (status & ATA_BUSY) {
-		msleep(2);
+		ata_msleep(ap, 2);
 		status = ata_sff_busy_wait(ap, ATA_BUSY, 10);
 		if (status & ATA_BUSY) {
 			ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE);
@@ -1937,7 +1937,7 @@
 	unsigned int dev1 = devmask & (1 << 1);
 	int rc, ret = 0;
 
-	msleep(ATA_WAIT_AFTER_RESET);
+	ata_msleep(ap, ATA_WAIT_AFTER_RESET);
 
 	/* always check readiness of the master device */
 	rc = ata_sff_wait_ready(link, deadline);
@@ -1966,7 +1966,7 @@
 			lbal = ioread8(ioaddr->lbal_addr);
 			if ((nsect == 1) && (lbal == 1))
 				break;
-			msleep(50);	/* give drive a breather */
+			ata_msleep(ap, 50);	/* give drive a breather */
 		}
 
 		rc = ata_sff_wait_ready(link, deadline);
@@ -3335,14 +3335,14 @@
 
 int __init ata_sff_init(void)
 {
-	ata_sff_wq = alloc_workqueue("ata_sff", WQ_RESCUER, WQ_MAX_ACTIVE);
+	ata_sff_wq = alloc_workqueue("ata_sff", WQ_MEM_RECLAIM, WQ_MAX_ACTIVE);
 	if (!ata_sff_wq)
 		return -ENOMEM;
 
 	return 0;
 }
 
-void __exit ata_sff_exit(void)
+void ata_sff_exit(void)
 {
 	destroy_workqueue(ata_sff_wq);
 }
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
new file mode 100644
index 0000000..ce9dc62
--- /dev/null
+++ b/drivers/ata/libata-transport.c
@@ -0,0 +1,774 @@
+/*
+ *  Copyright 2008 ioogle, Inc.  All rights reserved.
+ *	Released under GPL v2.
+ *
+ * Libata transport class.
+ *
+ * The ATA transport class contains common code to deal with ATA HBAs,
+ * an approximated representation of ATA topologies in the driver model,
+ * and various sysfs attributes to expose these topologies and management
+ * interfaces to user-space.
+ *
+ * There are 3 objects defined in in this class:
+ * - ata_port
+ * - ata_link
+ * - ata_device
+ * Each port has a link object. Each link can have up to two devices for PATA
+ * and generally one for SATA.
+ * If there is SATA port multiplier [PMP], 15 additional ata_link object are
+ * created.
+ *
+ * These objects are created when the ata host is initialized and when a PMP is
+ * found. They are removed only when the HBA is removed, cleaned before the
+ * error handler runs.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <scsi/scsi_transport.h>
+#include <linux/libata.h>
+#include <linux/hdreg.h>
+#include <linux/uaccess.h>
+
+#include "libata.h"
+#include "libata-transport.h"
+
+#define ATA_PORT_ATTRS		2
+#define ATA_LINK_ATTRS		3
+#define ATA_DEV_ATTRS		9
+
+struct scsi_transport_template;
+struct scsi_transport_template *ata_scsi_transport_template;
+
+struct ata_internal {
+	struct scsi_transport_template t;
+
+	struct device_attribute private_port_attrs[ATA_PORT_ATTRS];
+	struct device_attribute private_link_attrs[ATA_LINK_ATTRS];
+	struct device_attribute private_dev_attrs[ATA_DEV_ATTRS];
+
+	struct transport_container link_attr_cont;
+	struct transport_container dev_attr_cont;
+
+	/*
+	 * The array of null terminated pointers to attributes
+	 * needed by scsi_sysfs.c
+	 */
+	struct device_attribute *link_attrs[ATA_LINK_ATTRS + 1];
+	struct device_attribute *port_attrs[ATA_PORT_ATTRS + 1];
+	struct device_attribute *dev_attrs[ATA_DEV_ATTRS + 1];
+};
+#define to_ata_internal(tmpl)	container_of(tmpl, struct ata_internal, t)
+
+
+#define tdev_to_device(d)					\
+	container_of((d), struct ata_device, tdev)
+#define transport_class_to_dev(dev)				\
+	tdev_to_device((dev)->parent)
+
+#define tdev_to_link(d)						\
+	container_of((d), struct ata_link, tdev)
+#define transport_class_to_link(dev)				\
+	tdev_to_link((dev)->parent)
+
+#define tdev_to_port(d)						\
+	container_of((d), struct ata_port, tdev)
+#define transport_class_to_port(dev)				\
+	tdev_to_port((dev)->parent)
+
+
+/* Device objects are always created whit link objects */
+static int ata_tdev_add(struct ata_device *dev);
+static void ata_tdev_delete(struct ata_device *dev);
+
+
+/*
+ * Hack to allow attributes of the same name in different objects.
+ */
+#define ATA_DEVICE_ATTR(_prefix,_name,_mode,_show,_store) \
+	struct device_attribute device_attr_##_prefix##_##_name = \
+	__ATTR(_name,_mode,_show,_store)
+
+#define ata_bitfield_name_match(title, table)			\
+static ssize_t							\
+get_ata_##title##_names(u32 table_key, char *buf)		\
+{								\
+	char *prefix = "";					\
+	ssize_t len = 0;					\
+	int i;							\
+								\
+	for (i = 0; i < ARRAY_SIZE(table); i++) {		\
+		if (table[i].value & table_key) {		\
+			len += sprintf(buf + len, "%s%s",	\
+				prefix, table[i].name);		\
+			prefix = ", ";				\
+		}						\
+	}							\
+	len += sprintf(buf + len, "\n");			\
+	return len;						\
+}
+
+#define ata_bitfield_name_search(title, table)			\
+static ssize_t							\
+get_ata_##title##_names(u32 table_key, char *buf)		\
+{								\
+	ssize_t len = 0;					\
+	int i;							\
+								\
+	for (i = 0; i < ARRAY_SIZE(table); i++) {		\
+		if (table[i].value == table_key) {		\
+			len += sprintf(buf + len, "%s",		\
+				table[i].name);			\
+			break;					\
+		}						\
+	}							\
+	len += sprintf(buf + len, "\n");			\
+	return len;						\
+}
+
+static struct {
+	u32		value;
+	char		*name;
+} ata_class_names[] = {
+	{ ATA_DEV_UNKNOWN,		"unknown" },
+	{ ATA_DEV_ATA,			"ata" },
+	{ ATA_DEV_ATA_UNSUP,		"ata" },
+	{ ATA_DEV_ATAPI,		"atapi" },
+	{ ATA_DEV_ATAPI_UNSUP,		"atapi" },
+	{ ATA_DEV_PMP,			"pmp" },
+	{ ATA_DEV_PMP_UNSUP,		"pmp" },
+	{ ATA_DEV_SEMB,			"semb" },
+	{ ATA_DEV_SEMB_UNSUP,		"semb" },
+	{ ATA_DEV_NONE,			"none" }
+};
+ata_bitfield_name_search(class, ata_class_names)
+
+
+static struct {
+	u32		value;
+	char		*name;
+} ata_err_names[] = {
+	{ AC_ERR_DEV,			"DeviceError" },
+	{ AC_ERR_HSM,			"HostStateMachineError" },
+	{ AC_ERR_TIMEOUT,		"Timeout" },
+	{ AC_ERR_MEDIA,			"MediaError" },
+	{ AC_ERR_ATA_BUS,		"BusError" },
+	{ AC_ERR_HOST_BUS,		"HostBusError" },
+	{ AC_ERR_SYSTEM,		"SystemError" },
+	{ AC_ERR_INVALID,		"InvalidArg" },
+	{ AC_ERR_OTHER,			"Unknown" },
+	{ AC_ERR_NODEV_HINT,		"NoDeviceHint" },
+	{ AC_ERR_NCQ,		 	"NCQError" }
+};
+ata_bitfield_name_match(err, ata_err_names)
+
+static struct {
+	u32		value;
+	char		*name;
+} ata_xfer_names[] = {
+	{ XFER_UDMA_7,			"XFER_UDMA_7" },
+	{ XFER_UDMA_6,			"XFER_UDMA_6" },
+	{ XFER_UDMA_5,			"XFER_UDMA_5" },
+	{ XFER_UDMA_4,			"XFER_UDMA_4" },
+	{ XFER_UDMA_3,			"XFER_UDMA_3" },
+	{ XFER_UDMA_2,			"XFER_UDMA_2" },
+	{ XFER_UDMA_1,			"XFER_UDMA_1" },
+	{ XFER_UDMA_0,			"XFER_UDMA_0" },
+	{ XFER_MW_DMA_4,		"XFER_MW_DMA_4" },
+	{ XFER_MW_DMA_3,		"XFER_MW_DMA_3" },
+	{ XFER_MW_DMA_2,		"XFER_MW_DMA_2" },
+	{ XFER_MW_DMA_1,		"XFER_MW_DMA_1" },
+	{ XFER_MW_DMA_0,		"XFER_MW_DMA_0" },
+	{ XFER_SW_DMA_2,		"XFER_SW_DMA_2" },
+	{ XFER_SW_DMA_1,		"XFER_SW_DMA_1" },
+	{ XFER_SW_DMA_0,		"XFER_SW_DMA_0" },
+	{ XFER_PIO_6,			"XFER_PIO_6" },
+	{ XFER_PIO_5,			"XFER_PIO_5" },
+	{ XFER_PIO_4,			"XFER_PIO_4" },
+	{ XFER_PIO_3,			"XFER_PIO_3" },
+	{ XFER_PIO_2,			"XFER_PIO_2" },
+	{ XFER_PIO_1,			"XFER_PIO_1" },
+	{ XFER_PIO_0,			"XFER_PIO_0" },
+	{ XFER_PIO_SLOW,		"XFER_PIO_SLOW" }
+};
+ata_bitfield_name_match(xfer,ata_xfer_names)
+
+/*
+ * ATA Port attributes
+ */
+#define ata_port_show_simple(field, name, format_string, cast)		\
+static ssize_t								\
+show_ata_port_##name(struct device *dev,				\
+		     struct device_attribute *attr, char *buf)		\
+{									\
+	struct ata_port *ap = transport_class_to_port(dev);		\
+									\
+	return snprintf(buf, 20, format_string, cast ap->field);	\
+}
+
+#define ata_port_simple_attr(field, name, format_string, type)		\
+	ata_port_show_simple(field, name, format_string, (type))	\
+static DEVICE_ATTR(name, S_IRUGO, show_ata_port_##name, NULL)
+
+ata_port_simple_attr(nr_pmp_links, nr_pmp_links, "%d\n", int);
+ata_port_simple_attr(stats.idle_irq, idle_irq, "%ld\n", unsigned long);
+
+static DECLARE_TRANSPORT_CLASS(ata_port_class,
+			       "ata_port", NULL, NULL, NULL);
+
+static void ata_tport_release(struct device *dev)
+{
+	put_device(dev->parent);
+}
+
+/**
+ * ata_is_port --  check if a struct device represents a ATA port
+ * @dev:	device to check
+ *
+ * Returns:
+ *	%1 if the device represents a ATA Port, %0 else
+ */
+int ata_is_port(const struct device *dev)
+{
+	return dev->release == ata_tport_release;
+}
+
+static int ata_tport_match(struct attribute_container *cont,
+			   struct device *dev)
+{
+	if (!ata_is_port(dev))
+		return 0;
+	return &ata_scsi_transport_template->host_attrs.ac == cont;
+}
+
+/**
+ * ata_tport_delete  --  remove ATA PORT
+ * @port:	ATA PORT to remove
+ *
+ * Removes the specified ATA PORT.  Remove the associated link as well.
+ */
+void ata_tport_delete(struct ata_port *ap)
+{
+	struct device *dev = &ap->tdev;
+
+	ata_tlink_delete(&ap->link);
+
+	transport_remove_device(dev);
+	device_del(dev);
+	transport_destroy_device(dev);
+	put_device(dev);
+}
+
+/** ata_tport_add - initialize a transport ATA port structure
+ *
+ * @parent:	parent device
+ * @ap:		existing ata_port structure
+ *
+ * Initialize a ATA port structure for sysfs.  It will be added to the device
+ * tree below the device specified by @parent which could be a PCI device.
+ *
+ * Returns %0 on success
+ */
+int ata_tport_add(struct device *parent,
+		  struct ata_port *ap)
+{
+	int error;
+	struct device *dev = &ap->tdev;
+
+	device_initialize(dev);
+
+	dev->parent = get_device(parent);
+	dev->release = ata_tport_release;
+	dev_set_name(dev, "ata%d", ap->print_id);
+	transport_setup_device(dev);
+	error = device_add(dev);
+	if (error) {
+		goto tport_err;
+	}
+
+	transport_add_device(dev);
+	transport_configure_device(dev);
+
+	error = ata_tlink_add(&ap->link);
+	if (error) {
+		goto tport_link_err;
+	}
+	return 0;
+
+ tport_link_err:
+	transport_remove_device(dev);
+	device_del(dev);
+
+ tport_err:
+	transport_destroy_device(dev);
+	put_device(dev);
+	return error;
+}
+
+
+/*
+ * ATA link attributes
+ */
+
+
+#define ata_link_show_linkspeed(field)					\
+static ssize_t								\
+show_ata_link_##field(struct device *dev,				\
+		      struct device_attribute *attr, char *buf)		\
+{									\
+	struct ata_link *link = transport_class_to_link(dev);		\
+									\
+	return sprintf(buf,"%s\n", sata_spd_string(fls(link->field)));	\
+}
+
+#define ata_link_linkspeed_attr(field)					\
+	ata_link_show_linkspeed(field)					\
+static DEVICE_ATTR(field, S_IRUGO, show_ata_link_##field, NULL)
+
+ata_link_linkspeed_attr(hw_sata_spd_limit);
+ata_link_linkspeed_attr(sata_spd_limit);
+ata_link_linkspeed_attr(sata_spd);
+
+
+static DECLARE_TRANSPORT_CLASS(ata_link_class,
+		"ata_link", NULL, NULL, NULL);
+
+static void ata_tlink_release(struct device *dev)
+{
+	put_device(dev->parent);
+}
+
+/**
+ * ata_is_link --  check if a struct device represents a ATA link
+ * @dev:	device to check
+ *
+ * Returns:
+ *	%1 if the device represents a ATA link, %0 else
+ */
+int ata_is_link(const struct device *dev)
+{
+	return dev->release == ata_tlink_release;
+}
+
+static int ata_tlink_match(struct attribute_container *cont,
+			   struct device *dev)
+{
+	struct ata_internal* i = to_ata_internal(ata_scsi_transport_template);
+	if (!ata_is_link(dev))
+		return 0;
+	return &i->link_attr_cont.ac == cont;
+}
+
+/**
+ * ata_tlink_delete  --  remove ATA LINK
+ * @port:	ATA LINK to remove
+ *
+ * Removes the specified ATA LINK.  remove associated ATA device(s) as well.
+ */
+void ata_tlink_delete(struct ata_link *link)
+{
+	struct device *dev = &link->tdev;
+	struct ata_device *ata_dev;
+
+	ata_for_each_dev(ata_dev, link, ALL) {
+		ata_tdev_delete(ata_dev);
+	}
+
+	transport_remove_device(dev);
+	device_del(dev);
+	transport_destroy_device(dev);
+	put_device(dev);
+}
+
+/**
+ * ata_tlink_add  --  initialize a transport ATA link structure
+ * @link:	allocated ata_link structure.
+ *
+ * Initialize an ATA LINK structure for sysfs.  It will be added in the
+ * device tree below the ATA PORT it belongs to.
+ *
+ * Returns %0 on success
+ */
+int ata_tlink_add(struct ata_link *link)
+{
+	struct device *dev = &link->tdev;
+	struct ata_port *ap = link->ap;
+	struct ata_device *ata_dev;
+	int error;
+
+	device_initialize(dev);
+	dev->parent = get_device(&ap->tdev);
+	dev->release = ata_tlink_release;
+	if (ata_is_host_link(link))
+		dev_set_name(dev, "link%d", ap->print_id);
+        else
+		dev_set_name(dev, "link%d.%d", ap->print_id, link->pmp);
+
+	transport_setup_device(dev);
+
+	error = device_add(dev);
+	if (error) {
+		goto tlink_err;
+	}
+
+	transport_add_device(dev);
+	transport_configure_device(dev);
+
+	ata_for_each_dev(ata_dev, link, ALL) {
+		error = ata_tdev_add(ata_dev);
+		if (error) {
+			goto tlink_dev_err;
+		}
+	}
+	return 0;
+  tlink_dev_err:
+	while (--ata_dev >= link->device) {
+		ata_tdev_delete(ata_dev);
+	}
+	transport_remove_device(dev);
+	device_del(dev);
+  tlink_err:
+	transport_destroy_device(dev);
+	put_device(dev);
+	return error;
+}
+
+/*
+ * ATA device attributes
+ */
+
+#define ata_dev_show_class(title, field)				\
+static ssize_t								\
+show_ata_dev_##field(struct device *dev,				\
+		     struct device_attribute *attr, char *buf)		\
+{									\
+	struct ata_device *ata_dev = transport_class_to_dev(dev);	\
+									\
+	return get_ata_##title##_names(ata_dev->field, buf);		\
+}
+
+#define ata_dev_attr(title, field)					\
+	ata_dev_show_class(title, field)				\
+static DEVICE_ATTR(field, S_IRUGO, show_ata_dev_##field, NULL)
+
+ata_dev_attr(class, class);
+ata_dev_attr(xfer, pio_mode);
+ata_dev_attr(xfer, dma_mode);
+ata_dev_attr(xfer, xfer_mode);
+
+
+#define ata_dev_show_simple(field, format_string, cast)		\
+static ssize_t								\
+show_ata_dev_##field(struct device *dev,				\
+		     struct device_attribute *attr, char *buf)		\
+{									\
+	struct ata_device *ata_dev = transport_class_to_dev(dev);	\
+									\
+	return snprintf(buf, 20, format_string, cast ata_dev->field);	\
+}
+
+#define ata_dev_simple_attr(field, format_string, type)	\
+	ata_dev_show_simple(field, format_string, (type))	\
+static DEVICE_ATTR(field, S_IRUGO, 			\
+		   show_ata_dev_##field, NULL)
+
+ata_dev_simple_attr(spdn_cnt, "%d\n", int);
+
+struct ata_show_ering_arg {
+	char* buf;
+	int written;
+};
+
+static int ata_show_ering(struct ata_ering_entry *ent, void *void_arg)
+{
+	struct ata_show_ering_arg* arg = void_arg;
+	struct timespec time;
+
+	jiffies_to_timespec(ent->timestamp,&time);
+	arg->written += sprintf(arg->buf + arg->written,
+			       "[%5lu.%06lu]",
+			       time.tv_sec, time.tv_nsec);
+	arg->written += get_ata_err_names(ent->err_mask,
+					  arg->buf + arg->written);
+	return 0;
+}
+
+static ssize_t
+show_ata_dev_ering(struct device *dev,
+		   struct device_attribute *attr, char *buf)
+{
+	struct ata_device *ata_dev = transport_class_to_dev(dev);
+	struct ata_show_ering_arg arg = { buf, 0 };
+
+	ata_ering_map(&ata_dev->ering, ata_show_ering, &arg);
+	return arg.written;
+}
+
+
+static DEVICE_ATTR(ering, S_IRUGO, show_ata_dev_ering, NULL);
+
+static ssize_t
+show_ata_dev_id(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ata_device *ata_dev = transport_class_to_dev(dev);
+	int written = 0, i = 0;
+
+	if (ata_dev->class == ATA_DEV_PMP)
+		return 0;
+	for(i=0;i<ATA_ID_WORDS;i++)  {
+		written += snprintf(buf+written, 20, "%04x%c",
+				    ata_dev->id[i],
+				    ((i+1) & 7) ? ' ' : '\n');
+	}
+	return written;
+}
+
+static DEVICE_ATTR(id, S_IRUGO, show_ata_dev_id, NULL);
+
+static ssize_t
+show_ata_dev_gscr(struct device *dev,
+		  struct device_attribute *attr, char *buf)
+{
+	struct ata_device *ata_dev = transport_class_to_dev(dev);
+	int written = 0, i = 0;
+
+	if (ata_dev->class != ATA_DEV_PMP)
+		return 0;
+	for(i=0;i<SATA_PMP_GSCR_DWORDS;i++)  {
+		written += snprintf(buf+written, 20, "%08x%c",
+				    ata_dev->gscr[i],
+				    ((i+1) & 3) ? ' ' : '\n');
+	}
+	if (SATA_PMP_GSCR_DWORDS & 3)
+		buf[written-1] = '\n';
+	return written;
+}
+
+static DEVICE_ATTR(gscr, S_IRUGO, show_ata_dev_gscr, NULL);
+
+static DECLARE_TRANSPORT_CLASS(ata_dev_class,
+			       "ata_device", NULL, NULL, NULL);
+
+static void ata_tdev_release(struct device *dev)
+{
+	put_device(dev->parent);
+}
+
+/**
+ * ata_is_ata_dev  --  check if a struct device represents a ATA device
+ * @dev:	device to check
+ *
+ * Returns:
+ *	%1 if the device represents a ATA device, %0 else
+ */
+int ata_is_ata_dev(const struct device *dev)
+{
+	return dev->release == ata_tdev_release;
+}
+
+static int ata_tdev_match(struct attribute_container *cont,
+			  struct device *dev)
+{
+	struct ata_internal* i = to_ata_internal(ata_scsi_transport_template);
+	if (!ata_is_ata_dev(dev))
+		return 0;
+	return &i->dev_attr_cont.ac == cont;
+}
+
+/**
+ * ata_tdev_free  --  free a ATA LINK
+ * @dev:	ATA PHY to free
+ *
+ * Frees the specified ATA PHY.
+ *
+ * Note:
+ *   This function must only be called on a PHY that has not
+ *   successfully been added using ata_tdev_add().
+ */
+static void ata_tdev_free(struct ata_device *dev)
+{
+	transport_destroy_device(&dev->tdev);
+	put_device(&dev->tdev);
+}
+
+/**
+ * ata_tdev_delete  --  remove ATA device
+ * @port:	ATA PORT to remove
+ *
+ * Removes the specified ATA device.
+ */
+static void ata_tdev_delete(struct ata_device *ata_dev)
+{
+	struct device *dev = &ata_dev->tdev;
+
+	transport_remove_device(dev);
+	device_del(dev);
+	ata_tdev_free(ata_dev);
+}
+
+
+/**
+ * ata_tdev_add  --  initialize a transport ATA device structure.
+ * @ata_dev:	ata_dev structure.
+ *
+ * Initialize an ATA device structure for sysfs.  It will be added in the
+ * device tree below the ATA LINK device it belongs to.
+ *
+ * Returns %0 on success
+ */
+static int ata_tdev_add(struct ata_device *ata_dev)
+{
+	struct device *dev = &ata_dev->tdev;
+	struct ata_link *link = ata_dev->link;
+	struct ata_port *ap = link->ap;
+	int error;
+
+	device_initialize(dev);
+	dev->parent = get_device(&link->tdev);
+	dev->release = ata_tdev_release;
+	if (ata_is_host_link(link))
+		dev_set_name(dev, "dev%d.%d", ap->print_id,ata_dev->devno);
+        else
+		dev_set_name(dev, "dev%d.%d.0", ap->print_id, link->pmp);
+
+	transport_setup_device(dev);
+	error = device_add(dev);
+	if (error) {
+		ata_tdev_free(ata_dev);
+		return error;
+	}
+
+	transport_add_device(dev);
+	transport_configure_device(dev);
+	return 0;
+}
+
+
+/*
+ * Setup / Teardown code
+ */
+
+#define SETUP_TEMPLATE(attrb, field, perm, test)			\
+	i->private_##attrb[count] = dev_attr_##field;		       	\
+	i->private_##attrb[count].attr.mode = perm;			\
+	i->attrb[count] = &i->private_##attrb[count];			\
+	if (test)							\
+		count++
+
+#define SETUP_LINK_ATTRIBUTE(field)					\
+	SETUP_TEMPLATE(link_attrs, field, S_IRUGO, 1)
+
+#define SETUP_PORT_ATTRIBUTE(field)					\
+	SETUP_TEMPLATE(port_attrs, field, S_IRUGO, 1)
+
+#define SETUP_DEV_ATTRIBUTE(field)					\
+	SETUP_TEMPLATE(dev_attrs, field, S_IRUGO, 1)
+
+/**
+ * ata_attach_transport  --  instantiate ATA transport template
+ */
+struct scsi_transport_template *ata_attach_transport(void)
+{
+	struct ata_internal *i;
+	int count;
+
+	i = kzalloc(sizeof(struct ata_internal), GFP_KERNEL);
+	if (!i)
+		return NULL;
+
+	i->t.eh_strategy_handler	= ata_scsi_error;
+	i->t.eh_timed_out		= ata_scsi_timed_out;
+	i->t.user_scan			= ata_scsi_user_scan;
+
+	i->t.host_attrs.ac.attrs = &i->port_attrs[0];
+	i->t.host_attrs.ac.class = &ata_port_class.class;
+	i->t.host_attrs.ac.match = ata_tport_match;
+	transport_container_register(&i->t.host_attrs);
+
+	i->link_attr_cont.ac.class = &ata_link_class.class;
+	i->link_attr_cont.ac.attrs = &i->link_attrs[0];
+	i->link_attr_cont.ac.match = ata_tlink_match;
+	transport_container_register(&i->link_attr_cont);
+
+	i->dev_attr_cont.ac.class = &ata_dev_class.class;
+	i->dev_attr_cont.ac.attrs = &i->dev_attrs[0];
+	i->dev_attr_cont.ac.match = ata_tdev_match;
+	transport_container_register(&i->dev_attr_cont);
+
+	count = 0;
+	SETUP_PORT_ATTRIBUTE(nr_pmp_links);
+	SETUP_PORT_ATTRIBUTE(idle_irq);
+	BUG_ON(count > ATA_PORT_ATTRS);
+	i->port_attrs[count] = NULL;
+
+	count = 0;
+	SETUP_LINK_ATTRIBUTE(hw_sata_spd_limit);
+	SETUP_LINK_ATTRIBUTE(sata_spd_limit);
+	SETUP_LINK_ATTRIBUTE(sata_spd);
+	BUG_ON(count > ATA_LINK_ATTRS);
+	i->link_attrs[count] = NULL;
+
+	count = 0;
+	SETUP_DEV_ATTRIBUTE(class);
+	SETUP_DEV_ATTRIBUTE(pio_mode);
+	SETUP_DEV_ATTRIBUTE(dma_mode);
+	SETUP_DEV_ATTRIBUTE(xfer_mode);
+	SETUP_DEV_ATTRIBUTE(spdn_cnt);
+	SETUP_DEV_ATTRIBUTE(ering);
+	SETUP_DEV_ATTRIBUTE(id);
+	SETUP_DEV_ATTRIBUTE(gscr);
+	BUG_ON(count > ATA_DEV_ATTRS);
+	i->dev_attrs[count] = NULL;
+
+	return &i->t;
+}
+
+/**
+ * ata_release_transport  --  release ATA transport template instance
+ * @t:		transport template instance
+ */
+void ata_release_transport(struct scsi_transport_template *t)
+{
+	struct ata_internal *i = to_ata_internal(t);
+
+	transport_container_unregister(&i->t.host_attrs);
+	transport_container_unregister(&i->link_attr_cont);
+	transport_container_unregister(&i->dev_attr_cont);
+
+	kfree(i);
+}
+
+__init int libata_transport_init(void)
+{
+	int error;
+
+	error = transport_class_register(&ata_link_class);
+	if (error)
+		goto out_unregister_transport;
+	error = transport_class_register(&ata_port_class);
+	if (error)
+		goto out_unregister_link;
+	error = transport_class_register(&ata_dev_class);
+	if (error)
+		goto out_unregister_port;
+	return 0;
+
+ out_unregister_port:
+	transport_class_unregister(&ata_port_class);
+ out_unregister_link:
+	transport_class_unregister(&ata_link_class);
+ out_unregister_transport:
+	return error;
+
+}
+
+void __exit libata_transport_exit(void)
+{
+	transport_class_unregister(&ata_link_class);
+	transport_class_unregister(&ata_port_class);
+	transport_class_unregister(&ata_dev_class);
+}
diff --git a/drivers/ata/libata-transport.h b/drivers/ata/libata-transport.h
new file mode 100644
index 0000000..2820cf8
--- /dev/null
+++ b/drivers/ata/libata-transport.h
@@ -0,0 +1,18 @@
+#ifndef _LIBATA_TRANSPORT_H
+#define _LIBATA_TRANSPORT_H
+
+
+extern struct scsi_transport_template *ata_scsi_transport_template;
+
+int ata_tlink_add(struct ata_link *link);
+void ata_tlink_delete(struct ata_link *link);
+
+int ata_tport_add(struct device *parent, struct ata_port *ap);
+void ata_tport_delete(struct ata_port *ap);
+
+struct scsi_transport_template *ata_attach_transport(void);
+void ata_release_transport(struct scsi_transport_template *t);
+
+__init int libata_transport_init(void);
+void __exit libata_transport_exit(void);
+#endif
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 9ce1ecc..a9be110 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -86,6 +86,8 @@
 extern int ata_dev_configure(struct ata_device *dev);
 extern int sata_down_spd_limit(struct ata_link *link, u32 spd_limit);
 extern int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel);
+extern unsigned int ata_dev_set_feature(struct ata_device *dev,
+					u8 enable, u8 feature);
 extern void ata_sg_clean(struct ata_queued_cmd *qc);
 extern void ata_qc_free(struct ata_queued_cmd *qc);
 extern void ata_qc_issue(struct ata_queued_cmd *qc);
@@ -100,8 +102,7 @@
 extern int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg);
 extern int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg);
 extern struct ata_port *ata_port_alloc(struct ata_host *host);
-extern void ata_dev_enable_pm(struct ata_device *dev, enum link_pm policy);
-extern void ata_lpm_schedule(struct ata_port *ap, enum link_pm);
+extern const char *sata_spd_string(unsigned int spd);
 
 /* libata-acpi.c */
 #ifdef CONFIG_ATA_ACPI
@@ -137,10 +138,15 @@
 extern void ata_schedule_scsi_eh(struct Scsi_Host *shost);
 extern void ata_scsi_dev_rescan(struct work_struct *work);
 extern int ata_bus_probe(struct ata_port *ap);
+extern int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
+			      unsigned int id, unsigned int lun);
+
 
 /* libata-eh.c */
 extern unsigned long ata_internal_cmd_timeout(struct ata_device *dev, u8 cmd);
 extern void ata_internal_cmd_timed_out(struct ata_device *dev, u8 cmd);
+extern void ata_eh_acquire(struct ata_port *ap);
+extern void ata_eh_release(struct ata_port *ap);
 extern enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd);
 extern void ata_scsi_error(struct Scsi_Host *host);
 extern void ata_port_wait_eh(struct ata_port *ap);
@@ -164,11 +170,16 @@
 			  ata_postreset_fn_t postreset,
 			  struct ata_link **r_failed_disk);
 extern void ata_eh_finish(struct ata_port *ap);
+extern int ata_ering_map(struct ata_ering *ering,
+			 int (*map_fn)(struct ata_ering_entry *, void *),
+		  	 void *arg);
 
 /* libata-pmp.c */
 #ifdef CONFIG_SATA_PMP
 extern int sata_pmp_scr_read(struct ata_link *link, int reg, u32 *val);
 extern int sata_pmp_scr_write(struct ata_link *link, int reg, u32 val);
+extern int sata_pmp_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+			    unsigned hints);
 extern int sata_pmp_attach(struct ata_device *dev);
 #else /* CONFIG_SATA_PMP */
 static inline int sata_pmp_scr_read(struct ata_link *link, int reg, u32 *val)
@@ -181,6 +192,12 @@
 	return -EINVAL;
 }
 
+static inline int sata_pmp_set_lpm(struct ata_link *link,
+				   enum ata_lpm_policy policy, unsigned hints)
+{
+	return -EINVAL;
+}
+
 static inline int sata_pmp_attach(struct ata_device *dev)
 {
 	return -EINVAL;
diff --git a/drivers/ata/pata_bf54x.c b/drivers/ata/pata_bf54x.c
index 9cae65d..ec2c777 100644
--- a/drivers/ata/pata_bf54x.c
+++ b/drivers/ata/pata_bf54x.c
@@ -826,7 +826,7 @@
  *	@ctl: value to write
  */
 
-static u8 bfin_set_devctl(struct ata_port *ap, u8 ctl)
+static void bfin_set_devctl(struct ata_port *ap, u8 ctl)
 {
 	void __iomem *base = (void __iomem *)ap->ioaddr.ctl_addr;
 	write_atapi_register(base, ATA_REG_CTRL, ctl);
@@ -1046,7 +1046,7 @@
 			dev1 = 0;
 			break;
 		}
-		msleep(50);	/* give drive a breather */
+		ata_msleep(ap, 50);	/* give drive a breather */
 	}
 	if (dev1)
 		ata_sff_busy_sleep(ap, ATA_TMOUT_BOOT_QUICK, ATA_TMOUT_BOOT);
@@ -1087,7 +1087,7 @@
 	 *
 	 * Old drivers/ide uses the 2mS rule and then waits for ready
 	 */
-	msleep(150);
+	ata_msleep(ap, 150);
 
 	/* Before we perform post reset processing we want to see if
 	 * the bus shows 0xFF because the odd clown forgets the D7
diff --git a/drivers/ata/pata_cmd640.c b/drivers/ata/pata_cmd640.c
index e5f289f..549d28d 100644
--- a/drivers/ata/pata_cmd640.c
+++ b/drivers/ata/pata_cmd640.c
@@ -161,6 +161,17 @@
 	return 0;
 }
 
+static bool cmd640_sff_irq_check(struct ata_port *ap)
+{
+	struct pci_dev *pdev	= to_pci_dev(ap->host->dev);
+	int irq_reg		= ap->port_no ? ARTIM23 : CFR;
+	u8  irq_stat, irq_mask	= ap->port_no ? 0x10 : 0x04;
+
+	pci_read_config_byte(pdev, irq_reg, &irq_stat);
+
+	return irq_stat & irq_mask;
+}
+
 static struct scsi_host_template cmd640_sht = {
 	ATA_PIO_SHT(DRV_NAME),
 };
@@ -169,6 +180,7 @@
 	.inherits	= &ata_sff_port_ops,
 	/* In theory xfer_noirq is not needed once we kill the prefetcher */
 	.sff_data_xfer	= ata_sff_data_xfer_noirq,
+	.sff_irq_check	= cmd640_sff_irq_check,
 	.qc_issue	= cmd640_qc_issue,
 	.cable_detect	= ata_cable_40wire,
 	.set_piomode	= cmd640_set_piomode,
diff --git a/drivers/ata/pata_pcmcia.c b/drivers/ata/pata_pcmcia.c
index e944aa0..8062921 100644
--- a/drivers/ata/pata_pcmcia.c
+++ b/drivers/ata/pata_pcmcia.c
@@ -34,7 +34,6 @@
 #include <linux/ata.h>
 #include <linux/libata.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 #include <pcmcia/cisreg.h>
@@ -168,63 +167,26 @@
 };
 
 
-struct pcmcia_config_check {
-	unsigned long ctl_base;
-	int skip_vcc;
-	int is_kme;
-};
-
-static int pcmcia_check_one_config(struct pcmcia_device *pdev,
-				   cistpl_cftable_entry_t *cfg,
-				   cistpl_cftable_entry_t *dflt,
-				   unsigned int vcc,
-				   void *priv_data)
+static int pcmcia_check_one_config(struct pcmcia_device *pdev, void *priv_data)
 {
-	struct pcmcia_config_check *stk = priv_data;
+	int *is_kme = priv_data;
 
-	/* Check for matching Vcc, unless we're desperate */
-	if (!stk->skip_vcc) {
-		if (cfg->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-			if (vcc != cfg->vcc.param[CISTPL_POWER_VNOM] / 10000)
-				return -ENODEV;
-		} else if (dflt->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-			if (vcc != dflt->vcc.param[CISTPL_POWER_VNOM] / 10000)
-				return -ENODEV;
-		}
+	if (!(pdev->resource[0]->flags & IO_DATA_PATH_WIDTH_8)) {
+		pdev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+		pdev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 	}
+	pdev->resource[1]->flags &= ~IO_DATA_PATH_WIDTH;
+	pdev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
 
-	if (cfg->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		pdev->conf.Vpp = cfg->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-	else if (dflt->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		pdev->conf.Vpp = dflt->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		pdev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		pdev->resource[0]->start = io->win[0].base;
-		if (!(io->flags & CISTPL_IO_16BIT)) {
-			pdev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-			pdev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-		}
-		if (io->nwin == 2) {
-			pdev->resource[0]->end = 8;
-			pdev->resource[1]->start = io->win[1].base;
-			pdev->resource[1]->end = (stk->is_kme) ? 2 : 1;
-			if (pcmcia_request_io(pdev) != 0)
-				return -ENODEV;
-			stk->ctl_base = pdev->resource[1]->start;
-		} else if ((io->nwin == 1) && (io->win[0].len >= 16)) {
-			pdev->resource[0]->end = io->win[0].len;
-			pdev->resource[1]->end = 0;
-			if (pcmcia_request_io(pdev) != 0)
-				return -ENODEV;
-			stk->ctl_base = pdev->resource[0]->start + 0x0e;
-		} else
+	if (pdev->resource[1]->end) {
+		pdev->resource[0]->end = 8;
+		pdev->resource[1]->end = (*is_kme) ? 2 : 1;
+	} else {
+		if (pdev->resource[0]->end < 16)
 			return -ENODEV;
-		/* If we've got this far, we're done */
-		return 0;
 	}
-	return -ENODEV;
+
+	return pcmcia_request_io(pdev);
 }
 
 /**
@@ -239,7 +201,6 @@
 {
 	struct ata_host *host;
 	struct ata_port *ap;
-	struct pcmcia_config_check *stk = NULL;
 	int is_kme = 0, ret = -ENOMEM, p;
 	unsigned long io_base, ctl_base;
 	void __iomem *io_addr, *ctl_addr;
@@ -247,10 +208,8 @@
 	struct ata_port_operations *ops = &pcmcia_port_ops;
 
 	/* Set up attributes in order to probe card and get resources */
-	pdev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-	pdev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
-	pdev->conf.Attributes = CONF_ENABLE_IRQ;
-	pdev->conf.IntType = INT_MEMORY_AND_IO;
+	pdev->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO |
+		CONF_AUTO_SET_VPP | CONF_AUTO_CHECK_VCC;
 
 	/* See if we have a manufacturer identifier. Use it to set is_kme for
 	   vendor quirks */
@@ -258,25 +217,21 @@
 		  ((pdev->card_id == PRODID_KME_KXLC005_A) ||
 		   (pdev->card_id == PRODID_KME_KXLC005_B)));
 
-	/* Allocate resoure probing structures */
-
-	stk = kzalloc(sizeof(*stk), GFP_KERNEL);
-	if (!stk)
-		goto out1;
-	stk->is_kme = is_kme;
-	stk->skip_vcc = io_base = ctl_base = 0;
-
-	if (pcmcia_loop_config(pdev, pcmcia_check_one_config, stk)) {
-		stk->skip_vcc = 1;
-		if (pcmcia_loop_config(pdev, pcmcia_check_one_config, stk))
+	if (pcmcia_loop_config(pdev, pcmcia_check_one_config, &is_kme)) {
+		pdev->config_flags &= ~CONF_AUTO_CHECK_VCC;
+		if (pcmcia_loop_config(pdev, pcmcia_check_one_config, &is_kme))
 			goto failed; /* No suitable config found */
 	}
 	io_base = pdev->resource[0]->start;
-	ctl_base = stk->ctl_base;
+	if (pdev->resource[1]->end)
+		ctl_base = pdev->resource[1]->start;
+	else
+		ctl_base = pdev->resource[0]->start + 0x0e;
+
 	if (!pdev->irq)
 		goto failed;
 
-	ret = pcmcia_request_configuration(pdev, &pdev->conf);
+	ret = pcmcia_enable_device(pdev);
 	if (ret)
 		goto failed;
 
@@ -329,13 +284,10 @@
 		goto failed;
 
 	pdev->priv = host;
-	kfree(stk);
 	return 0;
 
 failed:
-	kfree(stk);
 	pcmcia_disable_device(pdev);
-out1:
 	return ret;
 }
 
@@ -430,9 +382,7 @@
 
 static struct pcmcia_driver pcmcia_driver = {
 	.owner		= THIS_MODULE,
-	.drv = {
-		.name		= DRV_NAME,
-	},
+	.name		= DRV_NAME,
 	.id_table	= pcmcia_devices,
 	.probe		= pcmcia_init_one,
 	.remove		= pcmcia_remove_one,
diff --git a/drivers/ata/pata_pdc202xx_old.c b/drivers/ata/pata_pdc202xx_old.c
index c39f213..c2ed586 100644
--- a/drivers/ata/pata_pdc202xx_old.c
+++ b/drivers/ata/pata_pdc202xx_old.c
@@ -44,6 +44,27 @@
 	ndelay(400);
 }
 
+static bool pdc202xx_irq_check(struct ata_port *ap)
+{
+	struct pci_dev *pdev	= to_pci_dev(ap->host->dev);
+	unsigned long master	= pci_resource_start(pdev, 4);
+	u8 sc1d			= inb(master + 0x1d);
+
+	if (ap->port_no) {
+		/*
+		 * bit 7: error, bit 6: interrupting,
+		 * bit 5: FIFO full, bit 4: FIFO empty
+		 */
+		return sc1d & 0x40;
+	} else	{
+		/*
+		 * bit 3: error, bit 2: interrupting,
+		 * bit 1: FIFO full, bit 0: FIFO empty
+		 */
+		return sc1d & 0x04;
+	}
+}
+
 /**
  *	pdc202xx_configure_piomode	-	set chip PIO timing
  *	@ap: ATA interface
@@ -282,6 +303,7 @@
 	.set_dmamode		= pdc202xx_set_dmamode,
 
 	.sff_exec_command	= pdc202xx_exec_command,
+	.sff_irq_check		= pdc202xx_irq_check,
 };
 
 static struct ata_port_operations pdc2026x_port_ops = {
@@ -297,6 +319,7 @@
 	.port_start		= pdc2026x_port_start,
 
 	.sff_exec_command	= pdc202xx_exec_command,
+	.sff_irq_check		= pdc202xx_irq_check,
 };
 
 static int pdc202xx_init_one(struct pci_dev *dev, const struct pci_device_id *id)
diff --git a/drivers/ata/pata_samsung_cf.c b/drivers/ata/pata_samsung_cf.c
index 6f9cfb2..8a51d67 100644
--- a/drivers/ata/pata_samsung_cf.c
+++ b/drivers/ata/pata_samsung_cf.c
@@ -322,7 +322,7 @@
 {
 	int rc;
 
-	msleep(ATA_WAIT_AFTER_RESET);
+	ata_msleep(link->ap, ATA_WAIT_AFTER_RESET);
 
 	/* always check readiness of the master device */
 	rc = ata_sff_wait_ready(link, deadline);
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index fe36966..093715c 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -530,7 +530,7 @@
 	 *
 	 * Old drivers/ide uses the 2mS rule and then waits for ready.
 	 */
-	msleep(150);
+	ata_msleep(ap, 150);
 
 	/* always check readiness of the master device */
 	rc = ata_sff_wait_ready(link, deadline);
@@ -559,7 +559,7 @@
 			lbal = in_be32(ioaddr->lbal_addr);
 			if ((nsect == 1) && (lbal == 1))
 				break;
-			msleep(50);	/* give drive a breather */
+			ata_msleep(ap, 50);	/* give drive a breather */
 		}
 
 		rc = ata_sff_wait_ready(link, deadline);
diff --git a/drivers/ata/pata_sil680.c b/drivers/ata/pata_sil680.c
index d3190d7..00eefbd 100644
--- a/drivers/ata/pata_sil680.c
+++ b/drivers/ata/pata_sil680.c
@@ -202,14 +202,25 @@
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void sil680_sff_exec_command(struct ata_port *ap,
-					const struct ata_taskfile *tf)
+static void sil680_sff_exec_command(struct ata_port *ap,
+				    const struct ata_taskfile *tf)
 {
 	DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command);
 	iowrite8(tf->command, ap->ioaddr.command_addr);
 	ioread8(ap->ioaddr.bmdma_addr + ATA_DMA_CMD);
 }
 
+static bool sil680_sff_irq_check(struct ata_port *ap)
+{
+	struct pci_dev *pdev	= to_pci_dev(ap->host->dev);
+	unsigned long addr	= sil680_selreg(ap, 1);
+	u8 val;
+
+	pci_read_config_byte(pdev, addr, &val);
+
+	return val & 0x08;
+}
+
 static struct scsi_host_template sil680_sht = {
 	ATA_BMDMA_SHT(DRV_NAME),
 };
@@ -218,6 +229,7 @@
 static struct ata_port_operations sil680_port_ops = {
 	.inherits		= &ata_bmdma32_port_ops,
 	.sff_exec_command	= sil680_sff_exec_command,
+	.sff_irq_check		= sil680_sff_irq_check,
 	.cable_detect		= sil680_cable_detect,
 	.set_piomode		= sil680_set_piomode,
 	.set_dmamode		= sil680_set_dmamode,
diff --git a/drivers/ata/pata_sl82c105.c b/drivers/ata/pata_sl82c105.c
index 98548f6..7f5d020 100644
--- a/drivers/ata/pata_sl82c105.c
+++ b/drivers/ata/pata_sl82c105.c
@@ -227,6 +227,16 @@
 	return 0;
 }
 
+static bool sl82c105_sff_irq_check(struct ata_port *ap)
+{
+	struct pci_dev *pdev	= to_pci_dev(ap->host->dev);
+	u32 val, mask		= ap->port_no ? CTRL_IDE_IRQB : CTRL_IDE_IRQA;
+
+	pci_read_config_dword(pdev, 0x40, &val);
+
+	return val & mask;
+}
+
 static struct scsi_host_template sl82c105_sht = {
 	ATA_BMDMA_SHT(DRV_NAME),
 };
@@ -239,6 +249,7 @@
 	.cable_detect	= ata_cable_40wire,
 	.set_piomode	= sl82c105_set_piomode,
 	.prereset	= sl82c105_pre_reset,
+	.sff_irq_check	= sl82c105_sff_irq_check,
 };
 
 /**
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 7325f77..b0214d0 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -678,7 +678,7 @@
 	iowrite32(temp, hcr_base + HCONTROL);
 
 	/* Poll for controller to go offline - should happen immediately */
-	ata_wait_register(hcr_base + HSTATUS, ONLINE, ONLINE, 1, 1);
+	ata_wait_register(ap, hcr_base + HSTATUS, ONLINE, ONLINE, 1, 1);
 
 	ap->private_data = NULL;
 	dma_free_coherent(dev, SATA_FSL_PORT_PRIV_DMA_SZ,
@@ -729,7 +729,8 @@
 	iowrite32(temp, hcr_base + HCONTROL);
 
 	/* Poll for controller to go offline */
-	temp = ata_wait_register(hcr_base + HSTATUS, ONLINE, ONLINE, 1, 500);
+	temp = ata_wait_register(ap, hcr_base + HSTATUS, ONLINE, ONLINE,
+				 1, 500);
 
 	if (temp & ONLINE) {
 		ata_port_printk(ap, KERN_ERR,
@@ -752,7 +753,7 @@
 	/*
 	 * PHY reset should remain asserted for atleast 1ms
 	 */
-	msleep(1);
+	ata_msleep(ap, 1);
 
 	/*
 	 * Now, bring the host controller online again, this can take time
@@ -766,7 +767,7 @@
 	temp |= HCONTROL_PMP_ATTACHED;
 	iowrite32(temp, hcr_base + HCONTROL);
 
-	temp = ata_wait_register(hcr_base + HSTATUS, ONLINE, 0, 1, 500);
+	temp = ata_wait_register(ap, hcr_base + HSTATUS, ONLINE, 0, 1, 500);
 
 	if (!(temp & ONLINE)) {
 		ata_port_printk(ap, KERN_ERR,
@@ -784,7 +785,7 @@
 	 * presence
 	 */
 
-	temp = ata_wait_register(hcr_base + HSTATUS, 0xFF, 0, 1, 500);
+	temp = ata_wait_register(ap, hcr_base + HSTATUS, 0xFF, 0, 1, 500);
 	if ((!(temp & 0x10)) || ata_link_offline(link)) {
 		ata_port_printk(ap, KERN_WARNING,
 				"No Device OR PHYRDY change,Hstatus = 0x%x\n",
@@ -797,7 +798,7 @@
 	 * Wait for the first D2H from device,i.e,signature update notification
 	 */
 	start_jiffies = jiffies;
-	temp = ata_wait_register(hcr_base + HSTATUS, 0xFF, 0x10,
+	temp = ata_wait_register(ap, hcr_base + HSTATUS, 0xFF, 0x10,
 			500, jiffies_to_msecs(deadline - start_jiffies));
 
 	if ((temp & 0xFF) != 0x18) {
@@ -880,7 +881,7 @@
 		iowrite32(pmp, CQPMP + hcr_base);
 	iowrite32(1, CQ + hcr_base);
 
-	temp = ata_wait_register(CQ + hcr_base, 0x1, 0x1, 1, 5000);
+	temp = ata_wait_register(ap, CQ + hcr_base, 0x1, 0x1, 1, 5000);
 	if (temp & 0x1) {
 		ata_port_printk(ap, KERN_WARNING, "ATA_SRST issue failed\n");
 
@@ -896,7 +897,7 @@
 		goto err;
 	}
 
-	msleep(1);
+	ata_msleep(ap, 1);
 
 	/*
 	 * SATA device enters reset state after receving a Control register
@@ -915,7 +916,7 @@
 	if (pmp != SATA_PMP_CTRL_PORT)
 		iowrite32(pmp, CQPMP + hcr_base);
 	iowrite32(1, CQ + hcr_base);
-	msleep(150);		/* ?? */
+	ata_msleep(ap, 150);		/* ?? */
 
 	/*
 	 * The above command would have signalled an interrupt on command
@@ -1137,17 +1138,13 @@
 			ioread32(hcr_base + CE));
 
 		for (i = 0; i < SATA_FSL_QUEUE_DEPTH; i++) {
-			if (done_mask & (1 << i)) {
-				qc = ata_qc_from_tag(ap, i);
-				if (qc) {
-					ata_qc_complete(qc);
-				}
+			if (done_mask & (1 << i))
 				DPRINTK
 				    ("completing ncq cmd,tag=%d,CC=0x%x,CA=0x%x\n",
 				     i, ioread32(hcr_base + CC),
 				     ioread32(hcr_base + CA));
-			}
 		}
+		ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
 		return;
 
 	} else if ((ap->qc_active & (1 << ATA_TAG_INTERNAL))) {
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index a36149e..83a4447 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -614,7 +614,7 @@
 
 	writew(IDMA_CTL_RST_ATA, idma_ctl);
 	readw(idma_ctl);	/* flush */
-	msleep(1);
+	ata_msleep(ap, 1);
 	writew(0, idma_ctl);
 
 	rc = sata_link_resume(link, timing, deadline);
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index a9fd970..bf74a36 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -2743,18 +2743,11 @@
 	}
 }
 
-static void mv_process_crpb_response(struct ata_port *ap,
+static bool mv_process_crpb_response(struct ata_port *ap,
 		struct mv_crpb *response, unsigned int tag, int ncq_enabled)
 {
 	u8 ata_status;
 	u16 edma_status = le16_to_cpu(response->flags);
-	struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
-
-	if (unlikely(!qc)) {
-		ata_port_printk(ap, KERN_ERR, "%s: no qc for tag=%d\n",
-				__func__, tag);
-		return;
-	}
 
 	/*
 	 * edma_status from a response queue entry:
@@ -2768,13 +2761,14 @@
 			 * Error will be seen/handled by
 			 * mv_err_intr().  So do nothing at all here.
 			 */
-			return;
+			return false;
 		}
 	}
 	ata_status = edma_status >> CRPB_FLAG_STATUS_SHIFT;
 	if (!ac_err_mask(ata_status))
-		ata_qc_complete(qc);
+		return true;
 	/* else: leave it for mv_err_intr() */
+	return false;
 }
 
 static void mv_process_crpb_entries(struct ata_port *ap, struct mv_port_priv *pp)
@@ -2783,6 +2777,7 @@
 	struct mv_host_priv *hpriv = ap->host->private_data;
 	u32 in_index;
 	bool work_done = false;
+	u32 done_mask = 0;
 	int ncq_enabled = (pp->pp_flags & MV_PP_FLAG_NCQ_EN);
 
 	/* Get the hardware queue position index */
@@ -2803,15 +2798,19 @@
 			/* Gen II/IIE: get command tag from CRPB entry */
 			tag = le16_to_cpu(response->id) & 0x1f;
 		}
-		mv_process_crpb_response(ap, response, tag, ncq_enabled);
+		if (mv_process_crpb_response(ap, response, tag, ncq_enabled))
+			done_mask |= 1 << tag;
 		work_done = true;
 	}
 
-	/* Update the software queue position index in hardware */
-	if (work_done)
+	if (work_done) {
+		ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
+
+		/* Update the software queue position index in hardware */
 		writelfl((pp->crpb_dma & EDMA_RSP_Q_BASE_LO_MASK) |
 			 (pp->resp_idx << EDMA_RSP_Q_PTR_SHIFT),
 			 port_mmio + EDMA_RSP_Q_OUT_PTR);
+	}
 }
 
 static void mv_port_intr(struct ata_port *ap, u32 port_cause)
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index cb89ef8..7254e25 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -873,29 +873,11 @@
 			ata_port_freeze(ap);
 		else
 			ata_port_abort(ap);
-		return 1;
+		return -1;
 	}
 
-	if (likely(flags & NV_CPB_RESP_DONE)) {
-		struct ata_queued_cmd *qc = ata_qc_from_tag(ap, cpb_num);
-		VPRINTK("CPB flags done, flags=0x%x\n", flags);
-		if (likely(qc)) {
-			DPRINTK("Completing qc from tag %d\n", cpb_num);
-			ata_qc_complete(qc);
-		} else {
-			struct ata_eh_info *ehi = &ap->link.eh_info;
-			/* Notifier bits set without a command may indicate the drive
-			   is misbehaving. Raise host state machine violation on this
-			   condition. */
-			ata_port_printk(ap, KERN_ERR,
-					"notifier for tag %d with no cmd?\n",
-					cpb_num);
-			ehi->err_mask |= AC_ERR_HSM;
-			ehi->action |= ATA_EH_RESET;
-			ata_port_freeze(ap);
-			return 1;
-		}
-	}
+	if (likely(flags & NV_CPB_RESP_DONE))
+		return 1;
 	return 0;
 }
 
@@ -1018,6 +1000,7 @@
 			      NV_ADMA_STAT_CPBERR |
 			      NV_ADMA_STAT_CMD_COMPLETE)) {
 			u32 check_commands = notifier_clears[i];
+			u32 done_mask = 0;
 			int pos, rc;
 
 			if (status & NV_ADMA_STAT_CPBERR) {
@@ -1034,10 +1017,13 @@
 				pos--;
 				rc = nv_adma_check_cpb(ap, pos,
 						notifier_error & (1 << pos));
-				if (unlikely(rc))
+				if (rc > 0)
+					done_mask |= 1 << pos;
+				else if (unlikely(rc < 0))
 					check_commands = 0;
 				check_commands &= ~(1 << pos);
 			}
+			ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
 		}
 	}
 
@@ -2132,7 +2118,6 @@
 	struct ata_eh_info *ehi = &ap->link.eh_info;
 	u32 sactive;
 	u32 done_mask;
-	int i;
 	u8 host_stat;
 	u8 lack_dhfis = 0;
 
@@ -2152,27 +2137,11 @@
 	sactive = readl(pp->sactive_block);
 	done_mask = pp->qc_active ^ sactive;
 
-	if (unlikely(done_mask & sactive)) {
-		ata_ehi_clear_desc(ehi);
-		ata_ehi_push_desc(ehi, "illegal SWNCQ:qc_active transition"
-				  "(%08x->%08x)", pp->qc_active, sactive);
-		ehi->err_mask |= AC_ERR_HSM;
-		ehi->action |= ATA_EH_RESET;
-		return -EINVAL;
-	}
-	for (i = 0; i < ATA_MAX_QUEUE; i++) {
-		if (!(done_mask & (1 << i)))
-			continue;
-
-		qc = ata_qc_from_tag(ap, i);
-		if (qc) {
-			ata_qc_complete(qc);
-			pp->qc_active &= ~(1 << i);
-			pp->dhfis_bits &= ~(1 << i);
-			pp->dmafis_bits &= ~(1 << i);
-			pp->sdbfis_bits |= (1 << i);
-		}
-	}
+	pp->qc_active &= ~done_mask;
+	pp->dhfis_bits &= ~done_mask;
+	pp->dmafis_bits &= ~done_mask;
+	pp->sdbfis_bits |= done_mask;
+	ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
 
 	if (!ap->qc_active) {
 		DPRINTK("over\n");
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index be7726d..af41c6f 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -589,9 +589,9 @@
 		sil24_clear_pmp(ap);
 
 	writel(PORT_CS_INIT, port + PORT_CTRL_STAT);
-	ata_wait_register(port + PORT_CTRL_STAT,
+	ata_wait_register(ap, port + PORT_CTRL_STAT,
 			  PORT_CS_INIT, PORT_CS_INIT, 10, 100);
-	tmp = ata_wait_register(port + PORT_CTRL_STAT,
+	tmp = ata_wait_register(ap, port + PORT_CTRL_STAT,
 				PORT_CS_RDY, 0, 10, 100);
 
 	if ((tmp & (PORT_CS_INIT | PORT_CS_RDY)) != PORT_CS_RDY) {
@@ -631,7 +631,7 @@
 	writel((u64)paddr >> 32, port + PORT_CMD_ACTIVATE + 4);
 
 	irq_mask = (PORT_IRQ_COMPLETE | PORT_IRQ_ERROR) << PORT_IRQ_RAW_SHIFT;
-	irq_stat = ata_wait_register(port + PORT_IRQ_STAT, irq_mask, 0x0,
+	irq_stat = ata_wait_register(ap, port + PORT_IRQ_STAT, irq_mask, 0x0,
 				     10, timeout_msec);
 
 	writel(irq_mask, port + PORT_IRQ_STAT); /* clear IRQs */
@@ -719,9 +719,9 @@
 				"state, performing PORT_RST\n");
 
 		writel(PORT_CS_PORT_RST, port + PORT_CTRL_STAT);
-		msleep(10);
+		ata_msleep(ap, 10);
 		writel(PORT_CS_PORT_RST, port + PORT_CTRL_CLR);
-		ata_wait_register(port + PORT_CTRL_STAT, PORT_CS_RDY, 0,
+		ata_wait_register(ap, port + PORT_CTRL_STAT, PORT_CS_RDY, 0,
 				  10, 5000);
 
 		/* restore port configuration */
@@ -740,7 +740,7 @@
 		tout_msec = 5000;
 
 	writel(PORT_CS_DEV_RST, port + PORT_CTRL_STAT);
-	tmp = ata_wait_register(port + PORT_CTRL_STAT,
+	tmp = ata_wait_register(ap, port + PORT_CTRL_STAT,
 				PORT_CS_DEV_RST, PORT_CS_DEV_RST, 10,
 				tout_msec);
 
@@ -1253,7 +1253,7 @@
 		tmp = readl(port + PORT_CTRL_STAT);
 		if (tmp & PORT_CS_PORT_RST) {
 			writel(PORT_CS_PORT_RST, port + PORT_CTRL_CLR);
-			tmp = ata_wait_register(port + PORT_CTRL_STAT,
+			tmp = ata_wait_register(NULL, port + PORT_CTRL_STAT,
 						PORT_CS_PORT_RST,
 						PORT_CS_PORT_RST, 10, 100);
 			if (tmp & PORT_CS_PORT_RST)
diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c
index 4730c42..c215899 100644
--- a/drivers/ata/sata_via.c
+++ b/drivers/ata/sata_via.c
@@ -349,7 +349,7 @@
 
 	/* wait for phy to become ready, if necessary */
 	do {
-		msleep(200);
+		ata_msleep(link->ap, 200);
 		svia_scr_read(link, SCR_STATUS, &sstatus);
 		if ((sstatus & 0xf) != 1)
 			break;
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index cbccf9a..abe46ed 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -3,6 +3,7 @@
 obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
 obj-$(CONFIG_PM_OPS)	+= generic_ops.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
+obj-$(CONFIG_PM_OPP)	+= opp.o
 
 ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
 ccflags-$(CONFIG_PM_VERBOSE)   += -DDEBUG
diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c
index 4b29d49..81f2c84 100644
--- a/drivers/base/power/generic_ops.c
+++ b/drivers/base/power/generic_ops.c
@@ -46,7 +46,7 @@
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	int ret;
 
-	ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : -EINVAL;
+	ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : 0;
 
 	return ret;
 }
@@ -65,7 +65,7 @@
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	int ret;
 
-	ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : -EINVAL;
+	ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : 0;
 
 	return ret;
 }
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 276d5a7..31b5266 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -51,6 +51,8 @@
  */
 static bool transition_started;
 
+static int async_error;
+
 /**
  * device_pm_init - Initialize the PM-related part of a device object.
  * @dev: Device object being initialized.
@@ -60,7 +62,8 @@
 	dev->power.status = DPM_ON;
 	init_completion(&dev->power.completion);
 	complete_all(&dev->power.completion);
-	dev->power.wakeup_count = 0;
+	dev->power.wakeup = NULL;
+	spin_lock_init(&dev->power.lock);
 	pm_runtime_init(dev);
 }
 
@@ -120,6 +123,7 @@
 	mutex_lock(&dpm_list_mtx);
 	list_del_init(&dev->power.entry);
 	mutex_unlock(&dpm_list_mtx);
+	device_wakeup_disable(dev);
 	pm_runtime_remove(dev);
 }
 
@@ -407,7 +411,7 @@
 static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info)
 {
 	ktime_t calltime;
-	s64 usecs64;
+	u64 usecs64;
 	int usecs;
 
 	calltime = ktime_get();
@@ -600,6 +604,7 @@
 	INIT_LIST_HEAD(&list);
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
+	async_error = 0;
 
 	list_for_each_entry(dev, &dpm_list, power.entry) {
 		if (dev->power.status < DPM_OFF)
@@ -829,8 +834,6 @@
 	return error;
 }
 
-static int async_error;
-
 /**
  * device_suspend - Execute "suspend" callbacks for given device.
  * @dev: Device to handle.
@@ -885,6 +888,9 @@
 	device_unlock(dev);
 	complete_all(&dev->power.completion);
 
+	if (error)
+		async_error = error;
+
 	return error;
 }
 
@@ -894,10 +900,8 @@
 	int error;
 
 	error = __device_suspend(dev, pm_transition, true);
-	if (error) {
+	if (error)
 		pm_dev_err(dev, pm_transition, " async", error);
-		async_error = error;
-	}
 
 	put_device(dev);
 }
@@ -1085,8 +1089,9 @@
  * @dev: Device to wait for.
  * @subordinate: Device that needs to wait for @dev.
  */
-void device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
+int device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
 {
 	dpm_wait(dev, subordinate->power.async_suspend);
+	return async_error;
 }
 EXPORT_SYMBOL_GPL(device_pm_wait_for_dev);
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
new file mode 100644
index 0000000..2bb9b4c
--- /dev/null
+++ b/drivers/base/power/opp.c
@@ -0,0 +1,628 @@
+/*
+ * Generic OPP Interface
+ *
+ * Copyright (C) 2009-2010 Texas Instruments Incorporated.
+ *	Nishanth Menon
+ *	Romit Dasgupta
+ *	Kevin Hilman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/cpufreq.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/opp.h>
+
+/*
+ * Internal data structure organization with the OPP layer library is as
+ * follows:
+ * dev_opp_list (root)
+ *	|- device 1 (represents voltage domain 1)
+ *	|	|- opp 1 (availability, freq, voltage)
+ *	|	|- opp 2 ..
+ *	...	...
+ *	|	`- opp n ..
+ *	|- device 2 (represents the next voltage domain)
+ *	...
+ *	`- device m (represents mth voltage domain)
+ * device 1, 2.. are represented by dev_opp structure while each opp
+ * is represented by the opp structure.
+ */
+
+/**
+ * struct opp - Generic OPP description structure
+ * @node:	opp list node. The nodes are maintained throughout the lifetime
+ *		of boot. It is expected only an optimal set of OPPs are
+ *		added to the library by the SoC framework.
+ *		RCU usage: opp list is traversed with RCU locks. node
+ *		modification is possible realtime, hence the modifications
+ *		are protected by the dev_opp_list_lock for integrity.
+ *		IMPORTANT: the opp nodes should be maintained in increasing
+ *		order.
+ * @available:	true/false - marks if this OPP as available or not
+ * @rate:	Frequency in hertz
+ * @u_volt:	Nominal voltage in microvolts corresponding to this OPP
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ *
+ * This structure stores the OPP information for a given device.
+ */
+struct opp {
+	struct list_head node;
+
+	bool available;
+	unsigned long rate;
+	unsigned long u_volt;
+
+	struct device_opp *dev_opp;
+};
+
+/**
+ * struct device_opp - Device opp structure
+ * @node:	list node - contains the devices with OPPs that
+ *		have been registered. Nodes once added are not modified in this
+ *		list.
+ *		RCU usage: nodes are not modified in the list of device_opp,
+ *		however addition is possible and is secured by dev_opp_list_lock
+ * @dev:	device pointer
+ * @opp_list:	list of opps
+ *
+ * This is an internal data structure maintaining the link to opps attached to
+ * a device. This structure is not meant to be shared to users as it is
+ * meant for book keeping and private to OPP library
+ */
+struct device_opp {
+	struct list_head node;
+
+	struct device *dev;
+	struct list_head opp_list;
+};
+
+/*
+ * The root of the list of all devices. All device_opp structures branch off
+ * from here, with each device_opp containing the list of opp it supports in
+ * various states of availability.
+ */
+static LIST_HEAD(dev_opp_list);
+/* Lock to allow exclusive modification to the device and opp lists */
+static DEFINE_MUTEX(dev_opp_list_lock);
+
+/**
+ * find_device_opp() - find device_opp struct using device pointer
+ * @dev:	device pointer used to lookup device OPPs
+ *
+ * Search list of device OPPs for one containing matching device. Does a RCU
+ * reader operation to grab the pointer needed.
+ *
+ * Returns pointer to 'struct device_opp' if found, otherwise -ENODEV or
+ * -EINVAL based on type of error.
+ *
+ * Locking: This function must be called under rcu_read_lock(). device_opp
+ * is a RCU protected pointer. This means that device_opp is valid as long
+ * as we are under RCU lock.
+ */
+static struct device_opp *find_device_opp(struct device *dev)
+{
+	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+
+	if (unlikely(IS_ERR_OR_NULL(dev))) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
+		if (tmp_dev_opp->dev == dev) {
+			dev_opp = tmp_dev_opp;
+			break;
+		}
+	}
+
+	return dev_opp;
+}
+
+/**
+ * opp_get_voltage() - Gets the voltage corresponding to an available opp
+ * @opp:	opp for which voltage has to be returned for
+ *
+ * Return voltage in micro volt corresponding to the opp, else
+ * return 0
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+unsigned long opp_get_voltage(struct opp *opp)
+{
+	struct opp *tmp_opp;
+	unsigned long v = 0;
+
+	tmp_opp = rcu_dereference(opp);
+	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+		pr_err("%s: Invalid parameters\n", __func__);
+	else
+		v = tmp_opp->u_volt;
+
+	return v;
+}
+
+/**
+ * opp_get_freq() - Gets the frequency corresponding to an available opp
+ * @opp:	opp for which frequency has to be returned for
+ *
+ * Return frequency in hertz corresponding to the opp, else
+ * return 0
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+unsigned long opp_get_freq(struct opp *opp)
+{
+	struct opp *tmp_opp;
+	unsigned long f = 0;
+
+	tmp_opp = rcu_dereference(opp);
+	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+		pr_err("%s: Invalid parameters\n", __func__);
+	else
+		f = tmp_opp->rate;
+
+	return f;
+}
+
+/**
+ * opp_get_opp_count() - Get number of opps available in the opp list
+ * @dev:	device for which we do this operation
+ *
+ * This function returns the number of available opps if there are any,
+ * else returns 0 if none or the corresponding error value.
+ *
+ * Locking: This function must be called under rcu_read_lock(). This function
+ * internally references two RCU protected structures: device_opp and opp which
+ * are safe as long as we are under a common RCU locked section.
+ */
+int opp_get_opp_count(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp;
+	int count = 0;
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+		return r;
+	}
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available)
+			count++;
+	}
+
+	return count;
+}
+
+/**
+ * opp_find_freq_exact() - search for an exact frequency
+ * @dev:		device for which we do this operation
+ * @freq:		frequency to search for
+ * @is_available:	true/false - match for available opp
+ *
+ * Searches for exact match in the opp list and returns pointer to the matching
+ * opp if found, else returns ERR_PTR in case of error and should be handled
+ * using IS_ERR.
+ *
+ * Note: available is a modifier for the search. if available=true, then the
+ * match is for exact matching frequency and is available in the stored OPP
+ * table. if false, the match is for exact frequency which is not available.
+ *
+ * This provides a mechanism to enable an opp which is not available currently
+ * or the opposite as well.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
+				bool available)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+		return ERR_PTR(r);
+	}
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available == available &&
+				temp_opp->rate == freq) {
+			opp = temp_opp;
+			break;
+		}
+	}
+
+	return opp;
+}
+
+/**
+ * opp_find_freq_ceil() - Search for an rounded ceil freq
+ * @dev:	device for which we do this operation
+ * @freq:	Start frequency
+ *
+ * Search for the matching ceil *available* OPP from a starting freq
+ * for a device.
+ *
+ * Returns matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+	if (!dev || !freq) {
+		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		return opp;
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available && temp_opp->rate >= *freq) {
+			opp = temp_opp;
+			*freq = opp->rate;
+			break;
+		}
+	}
+
+	return opp;
+}
+
+/**
+ * opp_find_freq_floor() - Search for a rounded floor freq
+ * @dev:	device for which we do this operation
+ * @freq:	Start frequency
+ *
+ * Search for the matching floor *available* OPP from a starting freq
+ * for a device.
+ *
+ * Returns matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+	if (!dev || !freq) {
+		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		return opp;
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available) {
+			/* go to the next node, before choosing prev */
+			if (temp_opp->rate > *freq)
+				break;
+			else
+				opp = temp_opp;
+		}
+	}
+	if (!IS_ERR(opp))
+		*freq = opp->rate;
+
+	return opp;
+}
+
+/**
+ * opp_add()  - Add an OPP table from a table definitions
+ * @dev:	device for which we do this operation
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
+ *
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * opp_enable/disable functions.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+{
+	struct device_opp *dev_opp = NULL;
+	struct opp *opp, *new_opp;
+	struct list_head *head;
+
+	/* allocate new OPP node */
+	new_opp = kzalloc(sizeof(struct opp), GFP_KERNEL);
+	if (!new_opp) {
+		dev_warn(dev, "%s: Unable to create new OPP node\n", __func__);
+		return -ENOMEM;
+	}
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Check for existing list for 'dev' */
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		/*
+		 * Allocate a new device OPP table. In the infrequent case
+		 * where a new device is needed to be added, we pay this
+		 * penalty.
+		 */
+		dev_opp = kzalloc(sizeof(struct device_opp), GFP_KERNEL);
+		if (!dev_opp) {
+			mutex_unlock(&dev_opp_list_lock);
+			kfree(new_opp);
+			dev_warn(dev,
+				"%s: Unable to create device OPP structure\n",
+				__func__);
+			return -ENOMEM;
+		}
+
+		dev_opp->dev = dev;
+		INIT_LIST_HEAD(&dev_opp->opp_list);
+
+		/* Secure the device list modification */
+		list_add_rcu(&dev_opp->node, &dev_opp_list);
+	}
+
+	/* populate the opp table */
+	new_opp->dev_opp = dev_opp;
+	new_opp->rate = freq;
+	new_opp->u_volt = u_volt;
+	new_opp->available = true;
+
+	/* Insert new OPP in order of increasing frequency */
+	head = &dev_opp->opp_list;
+	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+		if (new_opp->rate < opp->rate)
+			break;
+		else
+			head = &opp->node;
+	}
+
+	list_add_rcu(&new_opp->node, head);
+	mutex_unlock(&dev_opp_list_lock);
+
+	return 0;
+}
+
+/**
+ * opp_set_availability() - helper to set the availability of an opp
+ * @dev:		device for which we do this operation
+ * @freq:		OPP frequency to modify availability
+ * @availability_req:	availability status requested for this opp
+ *
+ * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
+ * share a common logic which is isolated here.
+ *
+ * Returns -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks to
+ * keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+static int opp_set_availability(struct device *dev, unsigned long freq,
+		bool availability_req)
+{
+	struct device_opp *tmp_dev_opp, *dev_opp = NULL;
+	struct opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	int r = 0;
+
+	/* keep the node allocated */
+	new_opp = kmalloc(sizeof(struct opp), GFP_KERNEL);
+	if (!new_opp) {
+		dev_warn(dev, "%s: Unable to create OPP\n", __func__);
+		return -ENOMEM;
+	}
+
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Find the device_opp */
+	list_for_each_entry(tmp_dev_opp, &dev_opp_list, node) {
+		if (dev == tmp_dev_opp->dev) {
+			dev_opp = tmp_dev_opp;
+			break;
+		}
+	}
+	if (IS_ERR(dev_opp)) {
+		r = PTR_ERR(dev_opp);
+		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+		goto unlock;
+	}
+
+	/* Do we have the frequency? */
+	list_for_each_entry(tmp_opp, &dev_opp->opp_list, node) {
+		if (tmp_opp->rate == freq) {
+			opp = tmp_opp;
+			break;
+		}
+	}
+	if (IS_ERR(opp)) {
+		r = PTR_ERR(opp);
+		goto unlock;
+	}
+
+	/* Is update really needed? */
+	if (opp->available == availability_req)
+		goto unlock;
+	/* copy the old data over */
+	*new_opp = *opp;
+
+	/* plug in new node */
+	new_opp->available = availability_req;
+
+	list_replace_rcu(&opp->node, &new_opp->node);
+	mutex_unlock(&dev_opp_list_lock);
+	synchronize_rcu();
+
+	/* clean up old opp */
+	new_opp = opp;
+	goto out;
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+out:
+	kfree(new_opp);
+	return r;
+}
+
+/**
+ * opp_enable() - Enable a specific OPP
+ * @dev:	device for which we do this operation
+ * @freq:	OPP frequency to enable
+ *
+ * Enables a provided opp. If the operation is valid, this returns 0, else the
+ * corresponding error value. It is meant to be used for users an OPP available
+ * after being temporarily made unavailable with opp_disable.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU and mutex locks to keep the
+ * integrity of the internal data structures. Callers should ensure that
+ * this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+int opp_enable(struct device *dev, unsigned long freq)
+{
+	return opp_set_availability(dev, freq, true);
+}
+
+/**
+ * opp_disable() - Disable a specific OPP
+ * @dev:	device for which we do this operation
+ * @freq:	OPP frequency to disable
+ *
+ * Disables a provided opp. If the operation is valid, this returns
+ * 0, else the corresponding error value. It is meant to be a temporary
+ * control by users to make this OPP not available until the circumstances are
+ * right to make it available again (with a call to opp_enable).
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU and mutex locks to keep the
+ * integrity of the internal data structures. Callers should ensure that
+ * this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+int opp_disable(struct device *dev, unsigned long freq)
+{
+	return opp_set_availability(dev, freq, false);
+}
+
+#ifdef CONFIG_CPU_FREQ
+/**
+ * opp_init_cpufreq_table() - create a cpufreq table for a device
+ * @dev:	device for which we do this operation
+ * @table:	Cpufreq table returned back to caller
+ *
+ * Generate a cpufreq table for a provided device- this assumes that the
+ * opp list is already initialized and ready for usage.
+ *
+ * This function allocates required memory for the cpufreq table. It is
+ * expected that the caller does the required maintenance such as freeing
+ * the table as required.
+ *
+ * Returns -EINVAL for bad pointers, -ENODEV if the device is not found, -ENOMEM
+ * if no memory available for the operation (table is not populated), returns 0
+ * if successful and table is populated.
+ *
+ * WARNING: It is  important for the callers to ensure refreshing their copy of
+ * the table if any of the mentioned functions have been invoked in the interim.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * To simplify the logic, we pretend we are updater and hold relevant mutex here
+ * Callers should ensure that this function is *NOT* called under RCU protection
+ * or in contexts where mutex locking cannot be used.
+ */
+int opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table)
+{
+	struct device_opp *dev_opp;
+	struct opp *opp;
+	struct cpufreq_frequency_table *freq_table;
+	int i = 0;
+
+	/* Pretend as if I am an updater */
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		mutex_unlock(&dev_opp_list_lock);
+		dev_err(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+		return r;
+	}
+
+	freq_table = kzalloc(sizeof(struct cpufreq_frequency_table) *
+			     (opp_get_opp_count(dev) + 1), GFP_KERNEL);
+	if (!freq_table) {
+		mutex_unlock(&dev_opp_list_lock);
+		dev_warn(dev, "%s: Unable to allocate frequency table\n",
+			__func__);
+		return -ENOMEM;
+	}
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->available) {
+			freq_table[i].index = i;
+			freq_table[i].frequency = opp->rate / 1000;
+			i++;
+		}
+	}
+	mutex_unlock(&dev_opp_list_lock);
+
+	freq_table[i].index = i;
+	freq_table[i].frequency = CPUFREQ_TABLE_END;
+
+	*table = &freq_table[0];
+
+	return 0;
+}
+#endif		/* CONFIG_CPU_FREQ */
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index c0bd03c..698dde7 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -34,6 +34,7 @@
 
 static inline void device_pm_init(struct device *dev)
 {
+	spin_lock_init(&dev->power.lock);
 	pm_runtime_init(dev);
 }
 
@@ -59,6 +60,7 @@
 
 extern int dpm_sysfs_add(struct device *);
 extern void dpm_sysfs_remove(struct device *);
+extern void rpm_sysfs_remove(struct device *);
 
 #else /* CONFIG_PM */
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index b78c401..1dd8676 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -2,127 +2,17 @@
  * drivers/base/power/runtime.c - Helper functions for device run-time PM
  *
  * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu>
  *
  * This file is released under the GPLv2.
  */
 
 #include <linux/sched.h>
 #include <linux/pm_runtime.h>
-#include <linux/jiffies.h>
+#include "power.h"
 
-static int __pm_runtime_resume(struct device *dev, bool from_wq);
-static int __pm_request_idle(struct device *dev);
-static int __pm_request_resume(struct device *dev);
-
-/**
- * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
- * @dev: Device to handle.
- */
-static void pm_runtime_deactivate_timer(struct device *dev)
-{
-	if (dev->power.timer_expires > 0) {
-		del_timer(&dev->power.suspend_timer);
-		dev->power.timer_expires = 0;
-	}
-}
-
-/**
- * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests.
- * @dev: Device to handle.
- */
-static void pm_runtime_cancel_pending(struct device *dev)
-{
-	pm_runtime_deactivate_timer(dev);
-	/*
-	 * In case there's a request pending, make sure its work function will
-	 * return without doing anything.
-	 */
-	dev->power.request = RPM_REQ_NONE;
-}
-
-/**
- * __pm_runtime_idle - Notify device bus type if the device can be suspended.
- * @dev: Device to notify the bus type about.
- *
- * This function must be called under dev->power.lock with interrupts disabled.
- */
-static int __pm_runtime_idle(struct device *dev)
-	__releases(&dev->power.lock) __acquires(&dev->power.lock)
-{
-	int retval = 0;
-
-	if (dev->power.runtime_error)
-		retval = -EINVAL;
-	else if (dev->power.idle_notification)
-		retval = -EINPROGRESS;
-	else if (atomic_read(&dev->power.usage_count) > 0
-	    || dev->power.disable_depth > 0
-	    || dev->power.runtime_status != RPM_ACTIVE)
-		retval = -EAGAIN;
-	else if (!pm_children_suspended(dev))
-		retval = -EBUSY;
-	if (retval)
-		goto out;
-
-	if (dev->power.request_pending) {
-		/*
-		 * If an idle notification request is pending, cancel it.  Any
-		 * other pending request takes precedence over us.
-		 */
-		if (dev->power.request == RPM_REQ_IDLE) {
-			dev->power.request = RPM_REQ_NONE;
-		} else if (dev->power.request != RPM_REQ_NONE) {
-			retval = -EAGAIN;
-			goto out;
-		}
-	}
-
-	dev->power.idle_notification = true;
-
-	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_idle) {
-		spin_unlock_irq(&dev->power.lock);
-
-		dev->bus->pm->runtime_idle(dev);
-
-		spin_lock_irq(&dev->power.lock);
-	} else if (dev->type && dev->type->pm && dev->type->pm->runtime_idle) {
-		spin_unlock_irq(&dev->power.lock);
-
-		dev->type->pm->runtime_idle(dev);
-
-		spin_lock_irq(&dev->power.lock);
-	} else if (dev->class && dev->class->pm
-	    && dev->class->pm->runtime_idle) {
-		spin_unlock_irq(&dev->power.lock);
-
-		dev->class->pm->runtime_idle(dev);
-
-		spin_lock_irq(&dev->power.lock);
-	}
-
-	dev->power.idle_notification = false;
-	wake_up_all(&dev->power.wait_queue);
-
- out:
-	return retval;
-}
-
-/**
- * pm_runtime_idle - Notify device bus type if the device can be suspended.
- * @dev: Device to notify the bus type about.
- */
-int pm_runtime_idle(struct device *dev)
-{
-	int retval;
-
-	spin_lock_irq(&dev->power.lock);
-	retval = __pm_runtime_idle(dev);
-	spin_unlock_irq(&dev->power.lock);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(pm_runtime_idle);
-
+static int rpm_resume(struct device *dev, int rpmflags);
+static int rpm_suspend(struct device *dev, int rpmflags);
 
 /**
  * update_pm_runtime_accounting - Update the time accounting of power states
@@ -163,58 +53,284 @@
 }
 
 /**
- * __pm_runtime_suspend - Carry out run-time suspend of given device.
- * @dev: Device to suspend.
- * @from_wq: If set, the function has been called via pm_wq.
+ * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
+ * @dev: Device to handle.
+ */
+static void pm_runtime_deactivate_timer(struct device *dev)
+{
+	if (dev->power.timer_expires > 0) {
+		del_timer(&dev->power.suspend_timer);
+		dev->power.timer_expires = 0;
+	}
+}
+
+/**
+ * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests.
+ * @dev: Device to handle.
+ */
+static void pm_runtime_cancel_pending(struct device *dev)
+{
+	pm_runtime_deactivate_timer(dev);
+	/*
+	 * In case there's a request pending, make sure its work function will
+	 * return without doing anything.
+	 */
+	dev->power.request = RPM_REQ_NONE;
+}
+
+/*
+ * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time.
+ * @dev: Device to handle.
  *
- * Check if the device can be suspended and run the ->runtime_suspend() callback
- * provided by its bus type.  If another suspend has been started earlier, wait
- * for it to finish.  If an idle notification or suspend request is pending or
- * scheduled, cancel it.
+ * Compute the autosuspend-delay expiration time based on the device's
+ * power.last_busy time.  If the delay has already expired or is disabled
+ * (negative) or the power.use_autosuspend flag isn't set, return 0.
+ * Otherwise return the expiration time in jiffies (adjusted to be nonzero).
+ *
+ * This function may be called either with or without dev->power.lock held.
+ * Either way it can be racy, since power.last_busy may be updated at any time.
+ */
+unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
+{
+	int autosuspend_delay;
+	long elapsed;
+	unsigned long last_busy;
+	unsigned long expires = 0;
+
+	if (!dev->power.use_autosuspend)
+		goto out;
+
+	autosuspend_delay = ACCESS_ONCE(dev->power.autosuspend_delay);
+	if (autosuspend_delay < 0)
+		goto out;
+
+	last_busy = ACCESS_ONCE(dev->power.last_busy);
+	elapsed = jiffies - last_busy;
+	if (elapsed < 0)
+		goto out;	/* jiffies has wrapped around. */
+
+	/*
+	 * If the autosuspend_delay is >= 1 second, align the timer by rounding
+	 * up to the nearest second.
+	 */
+	expires = last_busy + msecs_to_jiffies(autosuspend_delay);
+	if (autosuspend_delay >= 1000)
+		expires = round_jiffies(expires);
+	expires += !expires;
+	if (elapsed >= expires - last_busy)
+		expires = 0;	/* Already expired. */
+
+ out:
+	return expires;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
+
+/**
+ * rpm_check_suspend_allowed - Test whether a device may be suspended.
+ * @dev: Device to test.
+ */
+static int rpm_check_suspend_allowed(struct device *dev)
+{
+	int retval = 0;
+
+	if (dev->power.runtime_error)
+		retval = -EINVAL;
+	else if (atomic_read(&dev->power.usage_count) > 0
+	    || dev->power.disable_depth > 0)
+		retval = -EAGAIN;
+	else if (!pm_children_suspended(dev))
+		retval = -EBUSY;
+
+	/* Pending resume requests take precedence over suspends. */
+	else if ((dev->power.deferred_resume
+			&& dev->power.status == RPM_SUSPENDING)
+	    || (dev->power.request_pending
+			&& dev->power.request == RPM_REQ_RESUME))
+		retval = -EAGAIN;
+	else if (dev->power.runtime_status == RPM_SUSPENDED)
+		retval = 1;
+
+	return retval;
+}
+
+/**
+ * rpm_idle - Notify device bus type if the device can be suspended.
+ * @dev: Device to notify the bus type about.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's run-time PM status allows it to be suspended.  If
+ * another idle notification has been started earlier, return immediately.  If
+ * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise
+ * run the ->runtime_idle() callback directly.
  *
  * This function must be called under dev->power.lock with interrupts disabled.
  */
-int __pm_runtime_suspend(struct device *dev, bool from_wq)
-	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+static int rpm_idle(struct device *dev, int rpmflags)
 {
-	struct device *parent = NULL;
-	bool notify = false;
-	int retval = 0;
+	int (*callback)(struct device *);
+	int retval;
 
-	dev_dbg(dev, "__pm_runtime_suspend()%s!\n",
-		from_wq ? " from workqueue" : "");
+	retval = rpm_check_suspend_allowed(dev);
+	if (retval < 0)
+		;	/* Conditions are wrong. */
 
- repeat:
-	if (dev->power.runtime_error) {
-		retval = -EINVAL;
+	/* Idle notifications are allowed only in the RPM_ACTIVE state. */
+	else if (dev->power.runtime_status != RPM_ACTIVE)
+		retval = -EAGAIN;
+
+	/*
+	 * Any pending request other than an idle notification takes
+	 * precedence over us, except that the timer may be running.
+	 */
+	else if (dev->power.request_pending &&
+	    dev->power.request > RPM_REQ_IDLE)
+		retval = -EAGAIN;
+
+	/* Act as though RPM_NOWAIT is always set. */
+	else if (dev->power.idle_notification)
+		retval = -EINPROGRESS;
+	if (retval)
+		goto out;
+
+	/* Pending requests need to be canceled. */
+	dev->power.request = RPM_REQ_NONE;
+
+	if (dev->power.no_callbacks) {
+		/* Assume ->runtime_idle() callback would have suspended. */
+		retval = rpm_suspend(dev, rpmflags);
 		goto out;
 	}
 
-	/* Pending resume requests take precedence over us. */
-	if (dev->power.request_pending
-	    && dev->power.request == RPM_REQ_RESUME) {
-		retval = -EAGAIN;
+	/* Carry out an asynchronous or a synchronous idle notification. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = RPM_REQ_IDLE;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
 		goto out;
 	}
 
+	dev->power.idle_notification = true;
+
+	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_idle)
+		callback = dev->bus->pm->runtime_idle;
+	else if (dev->type && dev->type->pm && dev->type->pm->runtime_idle)
+		callback = dev->type->pm->runtime_idle;
+	else if (dev->class && dev->class->pm)
+		callback = dev->class->pm->runtime_idle;
+	else
+		callback = NULL;
+
+	if (callback) {
+		spin_unlock_irq(&dev->power.lock);
+
+		callback(dev);
+
+		spin_lock_irq(&dev->power.lock);
+	}
+
+	dev->power.idle_notification = false;
+	wake_up_all(&dev->power.wait_queue);
+
+ out:
+	return retval;
+}
+
+/**
+ * rpm_callback - Run a given runtime PM callback for a given device.
+ * @cb: Runtime PM callback to run.
+ * @dev: Device to run the callback for.
+ */
+static int rpm_callback(int (*cb)(struct device *), struct device *dev)
+	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+	int retval;
+
+	if (!cb)
+		return -ENOSYS;
+
+	spin_unlock_irq(&dev->power.lock);
+
+	retval = cb(dev);
+
+	spin_lock_irq(&dev->power.lock);
+	dev->power.runtime_error = retval;
+
+	return retval;
+}
+
+/**
+ * rpm_suspend - Carry out run-time suspend of given device.
+ * @dev: Device to suspend.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's run-time PM status allows it to be suspended.  If
+ * another suspend has been started earlier, either return immediately or wait
+ * for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC flags.  Cancel a
+ * pending idle notification.  If the RPM_ASYNC flag is set then queue a
+ * suspend request; otherwise run the ->runtime_suspend() callback directly.
+ * If a deferred resume was requested while the callback was running then carry
+ * it out; otherwise send an idle notification for the device (if the suspend
+ * failed) or for its parent (if the suspend succeeded).
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static int rpm_suspend(struct device *dev, int rpmflags)
+	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+	int (*callback)(struct device *);
+	struct device *parent = NULL;
+	int retval;
+
+	dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags);
+
+ repeat:
+	retval = rpm_check_suspend_allowed(dev);
+
+	if (retval < 0)
+		;	/* Conditions are wrong. */
+
+	/* Synchronous suspends are not allowed in the RPM_RESUMING state. */
+	else if (dev->power.runtime_status == RPM_RESUMING &&
+	    !(rpmflags & RPM_ASYNC))
+		retval = -EAGAIN;
+	if (retval)
+		goto out;
+
+	/* If the autosuspend_delay time hasn't expired yet, reschedule. */
+	if ((rpmflags & RPM_AUTO)
+	    && dev->power.runtime_status != RPM_SUSPENDING) {
+		unsigned long expires = pm_runtime_autosuspend_expiration(dev);
+
+		if (expires != 0) {
+			/* Pending requests need to be canceled. */
+			dev->power.request = RPM_REQ_NONE;
+
+			/*
+			 * Optimization: If the timer is already running and is
+			 * set to expire at or before the autosuspend delay,
+			 * avoid the overhead of resetting it.  Just let it
+			 * expire; pm_suspend_timer_fn() will take care of the
+			 * rest.
+			 */
+			if (!(dev->power.timer_expires && time_before_eq(
+			    dev->power.timer_expires, expires))) {
+				dev->power.timer_expires = expires;
+				mod_timer(&dev->power.suspend_timer, expires);
+			}
+			dev->power.timer_autosuspends = 1;
+			goto out;
+		}
+	}
+
 	/* Other scheduled or pending requests need to be canceled. */
 	pm_runtime_cancel_pending(dev);
 
-	if (dev->power.runtime_status == RPM_SUSPENDED)
-		retval = 1;
-	else if (dev->power.runtime_status == RPM_RESUMING
-	    || dev->power.disable_depth > 0
-	    || atomic_read(&dev->power.usage_count) > 0)
-		retval = -EAGAIN;
-	else if (!pm_children_suspended(dev))
-		retval = -EBUSY;
-	if (retval)
-		goto out;
-
 	if (dev->power.runtime_status == RPM_SUSPENDING) {
 		DEFINE_WAIT(wait);
 
-		if (from_wq) {
+		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
 			retval = -EINPROGRESS;
 			goto out;
 		}
@@ -236,46 +352,42 @@
 		goto repeat;
 	}
 
-	__update_runtime_status(dev, RPM_SUSPENDING);
 	dev->power.deferred_resume = false;
+	if (dev->power.no_callbacks)
+		goto no_callback;	/* Assume success. */
 
-	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend) {
-		spin_unlock_irq(&dev->power.lock);
-
-		retval = dev->bus->pm->runtime_suspend(dev);
-
-		spin_lock_irq(&dev->power.lock);
-		dev->power.runtime_error = retval;
-	} else if (dev->type && dev->type->pm
-	    && dev->type->pm->runtime_suspend) {
-		spin_unlock_irq(&dev->power.lock);
-
-		retval = dev->type->pm->runtime_suspend(dev);
-
-		spin_lock_irq(&dev->power.lock);
-		dev->power.runtime_error = retval;
-	} else if (dev->class && dev->class->pm
-	    && dev->class->pm->runtime_suspend) {
-		spin_unlock_irq(&dev->power.lock);
-
-		retval = dev->class->pm->runtime_suspend(dev);
-
-		spin_lock_irq(&dev->power.lock);
-		dev->power.runtime_error = retval;
-	} else {
-		retval = -ENOSYS;
+	/* Carry out an asynchronous or a synchronous suspend. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = (rpmflags & RPM_AUTO) ?
+		    RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
+		goto out;
 	}
 
+	__update_runtime_status(dev, RPM_SUSPENDING);
+
+	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend)
+		callback = dev->bus->pm->runtime_suspend;
+	else if (dev->type && dev->type->pm && dev->type->pm->runtime_suspend)
+		callback = dev->type->pm->runtime_suspend;
+	else if (dev->class && dev->class->pm)
+		callback = dev->class->pm->runtime_suspend;
+	else
+		callback = NULL;
+
+	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_ACTIVE);
-		if (retval == -EAGAIN || retval == -EBUSY) {
-			if (dev->power.timer_expires == 0)
-				notify = true;
+		dev->power.deferred_resume = 0;
+		if (retval == -EAGAIN || retval == -EBUSY)
 			dev->power.runtime_error = 0;
-		} else {
+		else
 			pm_runtime_cancel_pending(dev);
-		}
 	} else {
+ no_callback:
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_deactivate_timer(dev);
 
@@ -287,14 +399,11 @@
 	wake_up_all(&dev->power.wait_queue);
 
 	if (dev->power.deferred_resume) {
-		__pm_runtime_resume(dev, false);
+		rpm_resume(dev, 0);
 		retval = -EAGAIN;
 		goto out;
 	}
 
-	if (notify)
-		__pm_runtime_idle(dev);
-
 	if (parent && !parent->power.ignore_children) {
 		spin_unlock_irq(&dev->power.lock);
 
@@ -304,72 +413,69 @@
 	}
 
  out:
-	dev_dbg(dev, "__pm_runtime_suspend() returns %d!\n", retval);
+	dev_dbg(dev, "%s returns %d\n", __func__, retval);
 
 	return retval;
 }
 
 /**
- * pm_runtime_suspend - Carry out run-time suspend of given device.
- * @dev: Device to suspend.
- */
-int pm_runtime_suspend(struct device *dev)
-{
-	int retval;
-
-	spin_lock_irq(&dev->power.lock);
-	retval = __pm_runtime_suspend(dev, false);
-	spin_unlock_irq(&dev->power.lock);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(pm_runtime_suspend);
-
-/**
- * __pm_runtime_resume - Carry out run-time resume of given device.
+ * rpm_resume - Carry out run-time resume of given device.
  * @dev: Device to resume.
- * @from_wq: If set, the function has been called via pm_wq.
+ * @rpmflags: Flag bits.
  *
- * Check if the device can be woken up and run the ->runtime_resume() callback
- * provided by its bus type.  If another resume has been started earlier, wait
- * for it to finish.  If there's a suspend running in parallel with this
- * function, wait for it to finish and resume the device.  Cancel any scheduled
- * or pending requests.
+ * Check if the device's run-time PM status allows it to be resumed.  Cancel
+ * any scheduled or pending requests.  If another resume has been started
+ * earlier, either return imediately or wait for it to finish, depending on the
+ * RPM_NOWAIT and RPM_ASYNC flags.  Similarly, if there's a suspend running in
+ * parallel with this function, either tell the other process to resume after
+ * suspending (deferred_resume) or wait for it to finish.  If the RPM_ASYNC
+ * flag is set then queue a resume request; otherwise run the
+ * ->runtime_resume() callback directly.  Queue an idle notification for the
+ * device if the resume succeeded.
  *
  * This function must be called under dev->power.lock with interrupts disabled.
  */
-int __pm_runtime_resume(struct device *dev, bool from_wq)
+static int rpm_resume(struct device *dev, int rpmflags)
 	__releases(&dev->power.lock) __acquires(&dev->power.lock)
 {
+	int (*callback)(struct device *);
 	struct device *parent = NULL;
 	int retval = 0;
 
-	dev_dbg(dev, "__pm_runtime_resume()%s!\n",
-		from_wq ? " from workqueue" : "");
+	dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags);
 
  repeat:
-	if (dev->power.runtime_error) {
+	if (dev->power.runtime_error)
 		retval = -EINVAL;
-		goto out;
-	}
-
-	pm_runtime_cancel_pending(dev);
-
-	if (dev->power.runtime_status == RPM_ACTIVE)
-		retval = 1;
 	else if (dev->power.disable_depth > 0)
 		retval = -EAGAIN;
 	if (retval)
 		goto out;
 
+	/*
+	 * Other scheduled or pending requests need to be canceled.  Small
+	 * optimization: If an autosuspend timer is running, leave it running
+	 * rather than cancelling it now only to restart it again in the near
+	 * future.
+	 */
+	dev->power.request = RPM_REQ_NONE;
+	if (!dev->power.timer_autosuspends)
+		pm_runtime_deactivate_timer(dev);
+
+	if (dev->power.runtime_status == RPM_ACTIVE) {
+		retval = 1;
+		goto out;
+	}
+
 	if (dev->power.runtime_status == RPM_RESUMING
 	    || dev->power.runtime_status == RPM_SUSPENDING) {
 		DEFINE_WAIT(wait);
 
-		if (from_wq) {
+		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
 			if (dev->power.runtime_status == RPM_SUSPENDING)
 				dev->power.deferred_resume = true;
-			retval = -EINPROGRESS;
+			else
+				retval = -EINPROGRESS;
 			goto out;
 		}
 
@@ -391,6 +497,34 @@
 		goto repeat;
 	}
 
+	/*
+	 * See if we can skip waking up the parent.  This is safe only if
+	 * power.no_callbacks is set, because otherwise we don't know whether
+	 * the resume will actually succeed.
+	 */
+	if (dev->power.no_callbacks && !parent && dev->parent) {
+		spin_lock(&dev->parent->power.lock);
+		if (dev->parent->power.disable_depth > 0
+		    || dev->parent->power.ignore_children
+		    || dev->parent->power.runtime_status == RPM_ACTIVE) {
+			atomic_inc(&dev->parent->power.child_count);
+			spin_unlock(&dev->parent->power.lock);
+			goto no_callback;	/* Assume success. */
+		}
+		spin_unlock(&dev->parent->power.lock);
+	}
+
+	/* Carry out an asynchronous or a synchronous resume. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = RPM_REQ_RESUME;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
+		retval = 0;
+		goto out;
+	}
+
 	if (!parent && dev->parent) {
 		/*
 		 * Increment the parent's resume counter and resume it if
@@ -408,7 +542,7 @@
 		 */
 		if (!parent->power.disable_depth
 		    && !parent->power.ignore_children) {
-			__pm_runtime_resume(parent, false);
+			rpm_resume(parent, 0);
 			if (parent->power.runtime_status != RPM_ACTIVE)
 				retval = -EBUSY;
 		}
@@ -420,39 +554,26 @@
 		goto repeat;
 	}
 
+	if (dev->power.no_callbacks)
+		goto no_callback;	/* Assume success. */
+
 	__update_runtime_status(dev, RPM_RESUMING);
 
-	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume) {
-		spin_unlock_irq(&dev->power.lock);
+	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume)
+		callback = dev->bus->pm->runtime_resume;
+	else if (dev->type && dev->type->pm && dev->type->pm->runtime_resume)
+		callback = dev->type->pm->runtime_resume;
+	else if (dev->class && dev->class->pm)
+		callback = dev->class->pm->runtime_resume;
+	else
+		callback = NULL;
 
-		retval = dev->bus->pm->runtime_resume(dev);
-
-		spin_lock_irq(&dev->power.lock);
-		dev->power.runtime_error = retval;
-	} else if (dev->type && dev->type->pm
-	    && dev->type->pm->runtime_resume) {
-		spin_unlock_irq(&dev->power.lock);
-
-		retval = dev->type->pm->runtime_resume(dev);
-
-		spin_lock_irq(&dev->power.lock);
-		dev->power.runtime_error = retval;
-	} else if (dev->class && dev->class->pm
-	    && dev->class->pm->runtime_resume) {
-		spin_unlock_irq(&dev->power.lock);
-
-		retval = dev->class->pm->runtime_resume(dev);
-
-		spin_lock_irq(&dev->power.lock);
-		dev->power.runtime_error = retval;
-	} else {
-		retval = -ENOSYS;
-	}
-
+	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_cancel_pending(dev);
 	} else {
+ no_callback:
 		__update_runtime_status(dev, RPM_ACTIVE);
 		if (parent)
 			atomic_inc(&parent->power.child_count);
@@ -460,7 +581,7 @@
 	wake_up_all(&dev->power.wait_queue);
 
 	if (!retval)
-		__pm_request_idle(dev);
+		rpm_idle(dev, RPM_ASYNC);
 
  out:
 	if (parent) {
@@ -471,28 +592,12 @@
 		spin_lock_irq(&dev->power.lock);
 	}
 
-	dev_dbg(dev, "__pm_runtime_resume() returns %d!\n", retval);
+	dev_dbg(dev, "%s returns %d\n", __func__, retval);
 
 	return retval;
 }
 
 /**
- * pm_runtime_resume - Carry out run-time resume of given device.
- * @dev: Device to suspend.
- */
-int pm_runtime_resume(struct device *dev)
-{
-	int retval;
-
-	spin_lock_irq(&dev->power.lock);
-	retval = __pm_runtime_resume(dev, false);
-	spin_unlock_irq(&dev->power.lock);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(pm_runtime_resume);
-
-/**
  * pm_runtime_work - Universal run-time PM work function.
  * @work: Work structure used for scheduling the execution of this function.
  *
@@ -517,13 +622,16 @@
 	case RPM_REQ_NONE:
 		break;
 	case RPM_REQ_IDLE:
-		__pm_runtime_idle(dev);
+		rpm_idle(dev, RPM_NOWAIT);
 		break;
 	case RPM_REQ_SUSPEND:
-		__pm_runtime_suspend(dev, true);
+		rpm_suspend(dev, RPM_NOWAIT);
+		break;
+	case RPM_REQ_AUTOSUSPEND:
+		rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO);
 		break;
 	case RPM_REQ_RESUME:
-		__pm_runtime_resume(dev, true);
+		rpm_resume(dev, RPM_NOWAIT);
 		break;
 	}
 
@@ -532,117 +640,10 @@
 }
 
 /**
- * __pm_request_idle - Submit an idle notification request for given device.
- * @dev: Device to handle.
- *
- * Check if the device's run-time PM status is correct for suspending the device
- * and queue up a request to run __pm_runtime_idle() for it.
- *
- * This function must be called under dev->power.lock with interrupts disabled.
- */
-static int __pm_request_idle(struct device *dev)
-{
-	int retval = 0;
-
-	if (dev->power.runtime_error)
-		retval = -EINVAL;
-	else if (atomic_read(&dev->power.usage_count) > 0
-	    || dev->power.disable_depth > 0
-	    || dev->power.runtime_status == RPM_SUSPENDED
-	    || dev->power.runtime_status == RPM_SUSPENDING)
-		retval = -EAGAIN;
-	else if (!pm_children_suspended(dev))
-		retval = -EBUSY;
-	if (retval)
-		return retval;
-
-	if (dev->power.request_pending) {
-		/* Any requests other then RPM_REQ_IDLE take precedence. */
-		if (dev->power.request == RPM_REQ_NONE)
-			dev->power.request = RPM_REQ_IDLE;
-		else if (dev->power.request != RPM_REQ_IDLE)
-			retval = -EAGAIN;
-		return retval;
-	}
-
-	dev->power.request = RPM_REQ_IDLE;
-	dev->power.request_pending = true;
-	queue_work(pm_wq, &dev->power.work);
-
-	return retval;
-}
-
-/**
- * pm_request_idle - Submit an idle notification request for given device.
- * @dev: Device to handle.
- */
-int pm_request_idle(struct device *dev)
-{
-	unsigned long flags;
-	int retval;
-
-	spin_lock_irqsave(&dev->power.lock, flags);
-	retval = __pm_request_idle(dev);
-	spin_unlock_irqrestore(&dev->power.lock, flags);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(pm_request_idle);
-
-/**
- * __pm_request_suspend - Submit a suspend request for given device.
- * @dev: Device to suspend.
- *
- * This function must be called under dev->power.lock with interrupts disabled.
- */
-static int __pm_request_suspend(struct device *dev)
-{
-	int retval = 0;
-
-	if (dev->power.runtime_error)
-		return -EINVAL;
-
-	if (dev->power.runtime_status == RPM_SUSPENDED)
-		retval = 1;
-	else if (atomic_read(&dev->power.usage_count) > 0
-	    || dev->power.disable_depth > 0)
-		retval = -EAGAIN;
-	else if (dev->power.runtime_status == RPM_SUSPENDING)
-		retval = -EINPROGRESS;
-	else if (!pm_children_suspended(dev))
-		retval = -EBUSY;
-	if (retval < 0)
-		return retval;
-
-	pm_runtime_deactivate_timer(dev);
-
-	if (dev->power.request_pending) {
-		/*
-		 * Pending resume requests take precedence over us, but we can
-		 * overtake any other pending request.
-		 */
-		if (dev->power.request == RPM_REQ_RESUME)
-			retval = -EAGAIN;
-		else if (dev->power.request != RPM_REQ_SUSPEND)
-			dev->power.request = retval ?
-						RPM_REQ_NONE : RPM_REQ_SUSPEND;
-		return retval;
-	} else if (retval) {
-		return retval;
-	}
-
-	dev->power.request = RPM_REQ_SUSPEND;
-	dev->power.request_pending = true;
-	queue_work(pm_wq, &dev->power.work);
-
-	return 0;
-}
-
-/**
  * pm_suspend_timer_fn - Timer function for pm_schedule_suspend().
  * @data: Device pointer passed by pm_schedule_suspend().
  *
- * Check if the time is right and execute __pm_request_suspend() in that case.
+ * Check if the time is right and queue a suspend request.
  */
 static void pm_suspend_timer_fn(unsigned long data)
 {
@@ -656,7 +657,8 @@
 	/* If 'expire' is after 'jiffies' we've been called too early. */
 	if (expires > 0 && !time_after(expires, jiffies)) {
 		dev->power.timer_expires = 0;
-		__pm_request_suspend(dev);
+		rpm_suspend(dev, dev->power.timer_autosuspends ?
+		    (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC);
 	}
 
 	spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -670,47 +672,25 @@
 int pm_schedule_suspend(struct device *dev, unsigned int delay)
 {
 	unsigned long flags;
-	int retval = 0;
+	int retval;
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	if (dev->power.runtime_error) {
-		retval = -EINVAL;
-		goto out;
-	}
-
 	if (!delay) {
-		retval = __pm_request_suspend(dev);
+		retval = rpm_suspend(dev, RPM_ASYNC);
 		goto out;
 	}
 
-	pm_runtime_deactivate_timer(dev);
-
-	if (dev->power.request_pending) {
-		/*
-		 * Pending resume requests take precedence over us, but any
-		 * other pending requests have to be canceled.
-		 */
-		if (dev->power.request == RPM_REQ_RESUME) {
-			retval = -EAGAIN;
-			goto out;
-		}
-		dev->power.request = RPM_REQ_NONE;
-	}
-
-	if (dev->power.runtime_status == RPM_SUSPENDED)
-		retval = 1;
-	else if (atomic_read(&dev->power.usage_count) > 0
-	    || dev->power.disable_depth > 0)
-		retval = -EAGAIN;
-	else if (!pm_children_suspended(dev))
-		retval = -EBUSY;
+	retval = rpm_check_suspend_allowed(dev);
 	if (retval)
 		goto out;
 
+	/* Other scheduled or pending requests need to be canceled. */
+	pm_runtime_cancel_pending(dev);
+
 	dev->power.timer_expires = jiffies + msecs_to_jiffies(delay);
-	if (!dev->power.timer_expires)
-		dev->power.timer_expires = 1;
+	dev->power.timer_expires += !dev->power.timer_expires;
+	dev->power.timer_autosuspends = 0;
 	mod_timer(&dev->power.suspend_timer, dev->power.timer_expires);
 
  out:
@@ -721,103 +701,88 @@
 EXPORT_SYMBOL_GPL(pm_schedule_suspend);
 
 /**
- * pm_request_resume - Submit a resume request for given device.
- * @dev: Device to resume.
+ * __pm_runtime_idle - Entry point for run-time idle operations.
+ * @dev: Device to send idle notification for.
+ * @rpmflags: Flag bits.
  *
- * This function must be called under dev->power.lock with interrupts disabled.
+ * If the RPM_GET_PUT flag is set, decrement the device's usage count and
+ * return immediately if it is larger than zero.  Then carry out an idle
+ * notification, either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
  */
-static int __pm_request_resume(struct device *dev)
-{
-	int retval = 0;
-
-	if (dev->power.runtime_error)
-		return -EINVAL;
-
-	if (dev->power.runtime_status == RPM_ACTIVE)
-		retval = 1;
-	else if (dev->power.runtime_status == RPM_RESUMING)
-		retval = -EINPROGRESS;
-	else if (dev->power.disable_depth > 0)
-		retval = -EAGAIN;
-	if (retval < 0)
-		return retval;
-
-	pm_runtime_deactivate_timer(dev);
-
-	if (dev->power.runtime_status == RPM_SUSPENDING) {
-		dev->power.deferred_resume = true;
-		return retval;
-	}
-	if (dev->power.request_pending) {
-		/* If non-resume request is pending, we can overtake it. */
-		dev->power.request = retval ? RPM_REQ_NONE : RPM_REQ_RESUME;
-		return retval;
-	}
-	if (retval)
-		return retval;
-
-	dev->power.request = RPM_REQ_RESUME;
-	dev->power.request_pending = true;
-	queue_work(pm_wq, &dev->power.work);
-
-	return retval;
-}
-
-/**
- * pm_request_resume - Submit a resume request for given device.
- * @dev: Device to resume.
- */
-int pm_request_resume(struct device *dev)
+int __pm_runtime_idle(struct device *dev, int rpmflags)
 {
 	unsigned long flags;
 	int retval;
 
+	if (rpmflags & RPM_GET_PUT) {
+		if (!atomic_dec_and_test(&dev->power.usage_count))
+			return 0;
+	}
+
 	spin_lock_irqsave(&dev->power.lock, flags);
-	retval = __pm_request_resume(dev);
+	retval = rpm_idle(dev, rpmflags);
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
 	return retval;
 }
-EXPORT_SYMBOL_GPL(pm_request_resume);
+EXPORT_SYMBOL_GPL(__pm_runtime_idle);
 
 /**
- * __pm_runtime_get - Reference count a device and wake it up, if necessary.
- * @dev: Device to handle.
- * @sync: If set and the device is suspended, resume it synchronously.
+ * __pm_runtime_suspend - Entry point for run-time put/suspend operations.
+ * @dev: Device to suspend.
+ * @rpmflags: Flag bits.
  *
- * Increment the usage count of the device and resume it or submit a resume
- * request for it, depending on the value of @sync.
+ * If the RPM_GET_PUT flag is set, decrement the device's usage count and
+ * return immediately if it is larger than zero.  Then carry out a suspend,
+ * either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
  */
-int __pm_runtime_get(struct device *dev, bool sync)
+int __pm_runtime_suspend(struct device *dev, int rpmflags)
 {
+	unsigned long flags;
 	int retval;
 
-	atomic_inc(&dev->power.usage_count);
-	retval = sync ? pm_runtime_resume(dev) : pm_request_resume(dev);
+	if (rpmflags & RPM_GET_PUT) {
+		if (!atomic_dec_and_test(&dev->power.usage_count))
+			return 0;
+	}
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	retval = rpm_suspend(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
 
 	return retval;
 }
-EXPORT_SYMBOL_GPL(__pm_runtime_get);
+EXPORT_SYMBOL_GPL(__pm_runtime_suspend);
 
 /**
- * __pm_runtime_put - Decrement the device's usage counter and notify its bus.
- * @dev: Device to handle.
- * @sync: If the device's bus type is to be notified, do that synchronously.
+ * __pm_runtime_resume - Entry point for run-time resume operations.
+ * @dev: Device to resume.
+ * @rpmflags: Flag bits.
  *
- * Decrement the usage count of the device and if it reaches zero, carry out a
- * synchronous idle notification or submit an idle notification request for it,
- * depending on the value of @sync.
+ * If the RPM_GET_PUT flag is set, increment the device's usage count.  Then
+ * carry out a resume, either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
  */
-int __pm_runtime_put(struct device *dev, bool sync)
+int __pm_runtime_resume(struct device *dev, int rpmflags)
 {
-	int retval = 0;
+	unsigned long flags;
+	int retval;
 
-	if (atomic_dec_and_test(&dev->power.usage_count))
-		retval = sync ? pm_runtime_idle(dev) : pm_request_idle(dev);
+	if (rpmflags & RPM_GET_PUT)
+		atomic_inc(&dev->power.usage_count);
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	retval = rpm_resume(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
 
 	return retval;
 }
-EXPORT_SYMBOL_GPL(__pm_runtime_put);
+EXPORT_SYMBOL_GPL(__pm_runtime_resume);
 
 /**
  * __pm_runtime_set_status - Set run-time PM status of a device.
@@ -968,7 +933,7 @@
 
 	if (dev->power.request_pending
 	    && dev->power.request == RPM_REQ_RESUME) {
-		__pm_runtime_resume(dev, false);
+		rpm_resume(dev, 0);
 		retval = 1;
 	}
 
@@ -1017,7 +982,7 @@
 		 */
 		pm_runtime_get_noresume(dev);
 
-		__pm_runtime_resume(dev, false);
+		rpm_resume(dev, 0);
 
 		pm_runtime_put_noidle(dev);
 	}
@@ -1065,7 +1030,7 @@
 
 	dev->power.runtime_auto = false;
 	atomic_inc(&dev->power.usage_count);
-	__pm_runtime_resume(dev, false);
+	rpm_resume(dev, 0);
 
  out:
 	spin_unlock_irq(&dev->power.lock);
@@ -1086,7 +1051,7 @@
 
 	dev->power.runtime_auto = true;
 	if (atomic_dec_and_test(&dev->power.usage_count))
-		__pm_runtime_idle(dev);
+		rpm_idle(dev, RPM_AUTO);
 
  out:
 	spin_unlock_irq(&dev->power.lock);
@@ -1094,13 +1059,110 @@
 EXPORT_SYMBOL_GPL(pm_runtime_allow);
 
 /**
+ * pm_runtime_no_callbacks - Ignore run-time PM callbacks for a device.
+ * @dev: Device to handle.
+ *
+ * Set the power.no_callbacks flag, which tells the PM core that this
+ * device is power-managed through its parent and has no run-time PM
+ * callbacks of its own.  The run-time sysfs attributes will be removed.
+ *
+ */
+void pm_runtime_no_callbacks(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+	dev->power.no_callbacks = 1;
+	spin_unlock_irq(&dev->power.lock);
+	if (device_is_registered(dev))
+		rpm_sysfs_remove(dev);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks);
+
+/**
+ * update_autosuspend - Handle a change to a device's autosuspend settings.
+ * @dev: Device to handle.
+ * @old_delay: The former autosuspend_delay value.
+ * @old_use: The former use_autosuspend value.
+ *
+ * Prevent runtime suspend if the new delay is negative and use_autosuspend is
+ * set; otherwise allow it.  Send an idle notification if suspends are allowed.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static void update_autosuspend(struct device *dev, int old_delay, int old_use)
+{
+	int delay = dev->power.autosuspend_delay;
+
+	/* Should runtime suspend be prevented now? */
+	if (dev->power.use_autosuspend && delay < 0) {
+
+		/* If it used to be allowed then prevent it. */
+		if (!old_use || old_delay >= 0) {
+			atomic_inc(&dev->power.usage_count);
+			rpm_resume(dev, 0);
+		}
+	}
+
+	/* Runtime suspend should be allowed now. */
+	else {
+
+		/* If it used to be prevented then allow it. */
+		if (old_use && old_delay < 0)
+			atomic_dec(&dev->power.usage_count);
+
+		/* Maybe we can autosuspend now. */
+		rpm_idle(dev, RPM_AUTO);
+	}
+}
+
+/**
+ * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value.
+ * @dev: Device to handle.
+ * @delay: Value of the new delay in milliseconds.
+ *
+ * Set the device's power.autosuspend_delay value.  If it changes to negative
+ * and the power.use_autosuspend flag is set, prevent run-time suspends.  If it
+ * changes the other way, allow run-time suspends.
+ */
+void pm_runtime_set_autosuspend_delay(struct device *dev, int delay)
+{
+	int old_delay, old_use;
+
+	spin_lock_irq(&dev->power.lock);
+	old_delay = dev->power.autosuspend_delay;
+	old_use = dev->power.use_autosuspend;
+	dev->power.autosuspend_delay = delay;
+	update_autosuspend(dev, old_delay, old_use);
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay);
+
+/**
+ * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag.
+ * @dev: Device to handle.
+ * @use: New value for use_autosuspend.
+ *
+ * Set the device's power.use_autosuspend flag, and allow or prevent run-time
+ * suspends as needed.
+ */
+void __pm_runtime_use_autosuspend(struct device *dev, bool use)
+{
+	int old_delay, old_use;
+
+	spin_lock_irq(&dev->power.lock);
+	old_delay = dev->power.autosuspend_delay;
+	old_use = dev->power.use_autosuspend;
+	dev->power.use_autosuspend = use;
+	update_autosuspend(dev, old_delay, old_use);
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend);
+
+/**
  * pm_runtime_init - Initialize run-time PM fields in given device object.
  * @dev: Device object to initialize.
  */
 void pm_runtime_init(struct device *dev)
 {
-	spin_lock_init(&dev->power.lock);
-
 	dev->power.runtime_status = RPM_SUSPENDED;
 	dev->power.idle_notification = false;
 
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index e56b438..0b1e46b 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -75,12 +75,27 @@
  *	attribute is set to "enabled" by bus type code or device drivers and in
  *	that cases it should be safe to leave the default value.
  *
+ *	autosuspend_delay_ms - Report/change a device's autosuspend_delay value
+ *
+ *	Some drivers don't want to carry out a runtime suspend as soon as a
+ *	device becomes idle; they want it always to remain idle for some period
+ *	of time before suspending it.  This period is the autosuspend_delay
+ *	value (expressed in milliseconds) and it can be controlled by the user.
+ *	If the value is negative then the device will never be runtime
+ *	suspended.
+ *
+ *	NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay
+ *	value are used only if the driver calls pm_runtime_use_autosuspend().
+ *
  *	wakeup_count - Report the number of wakeup events related to the device
  */
 
 static const char enabled[] = "enabled";
 static const char disabled[] = "disabled";
 
+const char power_group_name[] = "power";
+EXPORT_SYMBOL_GPL(power_group_name);
+
 #ifdef CONFIG_PM_RUNTIME
 static const char ctrl_auto[] = "auto";
 static const char ctrl_on[] = "on";
@@ -170,6 +185,33 @@
 }
 
 static DEVICE_ATTR(runtime_status, 0444, rtpm_status_show, NULL);
+
+static ssize_t autosuspend_delay_ms_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+	return sprintf(buf, "%d\n", dev->power.autosuspend_delay);
+}
+
+static ssize_t autosuspend_delay_ms_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t n)
+{
+	long delay;
+
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+
+	if (strict_strtol(buf, 10, &delay) != 0 || delay != (int) delay)
+		return -EINVAL;
+
+	pm_runtime_set_autosuspend_delay(dev, delay);
+	return n;
+}
+
+static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
+		autosuspend_delay_ms_store);
+
 #endif
 
 static ssize_t
@@ -210,11 +252,122 @@
 static ssize_t wakeup_count_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%lu\n", dev->power.wakeup_count);
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->event_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
 }
 
 static DEVICE_ATTR(wakeup_count, 0444, wakeup_count_show, NULL);
-#endif
+
+static ssize_t wakeup_active_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->active_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active_count, 0444, wakeup_active_count_show, NULL);
+
+static ssize_t wakeup_hit_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->hit_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_hit_count, 0444, wakeup_hit_count_show, NULL);
+
+static ssize_t wakeup_active_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned int active = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		active = dev->power.wakeup->active;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active, 0444, wakeup_active_show, NULL);
+
+static ssize_t wakeup_total_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->total_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_total_time_ms, 0444, wakeup_total_time_show, NULL);
+
+static ssize_t wakeup_max_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->max_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_max_time_ms, 0444, wakeup_max_time_show, NULL);
+
+static ssize_t wakeup_last_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->last_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_last_time_ms, 0444, wakeup_last_time_show, NULL);
+#endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_ADVANCED_DEBUG
 #ifdef CONFIG_PM_RUNTIME
@@ -279,19 +432,20 @@
 #endif /* CONFIG_PM_ADVANCED_DEBUG */
 
 static struct attribute * power_attrs[] = {
-#ifdef CONFIG_PM_RUNTIME
-	&dev_attr_control.attr,
-	&dev_attr_runtime_status.attr,
-	&dev_attr_runtime_suspended_time.attr,
-	&dev_attr_runtime_active_time.attr,
-#endif
 	&dev_attr_wakeup.attr,
 #ifdef CONFIG_PM_SLEEP
 	&dev_attr_wakeup_count.attr,
+	&dev_attr_wakeup_active_count.attr,
+	&dev_attr_wakeup_hit_count.attr,
+	&dev_attr_wakeup_active.attr,
+	&dev_attr_wakeup_total_time_ms.attr,
+	&dev_attr_wakeup_max_time_ms.attr,
+	&dev_attr_wakeup_last_time_ms.attr,
 #endif
 #ifdef CONFIG_PM_ADVANCED_DEBUG
 	&dev_attr_async.attr,
 #ifdef CONFIG_PM_RUNTIME
+	&dev_attr_runtime_status.attr,
 	&dev_attr_runtime_usage.attr,
 	&dev_attr_runtime_active_kids.attr,
 	&dev_attr_runtime_enabled.attr,
@@ -300,10 +454,53 @@
 	NULL,
 };
 static struct attribute_group pm_attr_group = {
-	.name	= "power",
+	.name	= power_group_name,
 	.attrs	= power_attrs,
 };
 
+#ifdef CONFIG_PM_RUNTIME
+
+static struct attribute *runtime_attrs[] = {
+#ifndef CONFIG_PM_ADVANCED_DEBUG
+	&dev_attr_runtime_status.attr,
+#endif
+	&dev_attr_control.attr,
+	&dev_attr_runtime_suspended_time.attr,
+	&dev_attr_runtime_active_time.attr,
+	&dev_attr_autosuspend_delay_ms.attr,
+	NULL,
+};
+static struct attribute_group pm_runtime_attr_group = {
+	.name	= power_group_name,
+	.attrs	= runtime_attrs,
+};
+
+int dpm_sysfs_add(struct device *dev)
+{
+	int rc;
+
+	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
+	if (rc == 0 && !dev->power.no_callbacks) {
+		rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group);
+		if (rc)
+			sysfs_remove_group(&dev->kobj, &pm_attr_group);
+	}
+	return rc;
+}
+
+void rpm_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
+}
+
+void dpm_sysfs_remove(struct device *dev)
+{
+	rpm_sysfs_remove(dev);
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+}
+
+#else /* CONFIG_PM_RUNTIME */
+
 int dpm_sysfs_add(struct device * dev)
 {
 	return sysfs_create_group(&dev->kobj, &pm_attr_group);
@@ -313,3 +510,5 @@
 {
 	sysfs_remove_group(&dev->kobj, &pm_attr_group);
 }
+
+#endif
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 0a1a2c4..9f4258d 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -188,8 +188,10 @@
 static int show_dev_hash(unsigned int value)
 {
 	int match = 0;
-	struct list_head *entry = dpm_list.prev;
+	struct list_head *entry;
 
+	device_pm_lock();
+	entry = dpm_list.prev;
 	while (entry != &dpm_list) {
 		struct device * dev = to_device(entry);
 		unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH);
@@ -199,11 +201,43 @@
 		}
 		entry = entry->prev;
 	}
+	device_pm_unlock();
 	return match;
 }
 
 static unsigned int hash_value_early_read;
 
+int show_trace_dev_match(char *buf, size_t size)
+{
+	unsigned int value = hash_value_early_read / (USERHASH * FILEHASH);
+	int ret = 0;
+	struct list_head *entry;
+
+	/*
+	 * It's possible that multiple devices will match the hash and we can't
+	 * tell which is the culprit, so it's best to output them all.
+	 */
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (size && entry != &dpm_list) {
+		struct device *dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev),
+						DEVHASH);
+		if (hash == value) {
+			int len = snprintf(buf, size, "%s\n",
+					    dev_driver_string(dev));
+			if (len > size)
+				len = size;
+			buf += len;
+			ret += len;
+			size -= len;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return ret;
+}
+
 static int early_resume_init(void)
 {
 	hash_value_early_read = read_magic_time();
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index eb594fa..71c5528 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -11,7 +11,12 @@
 #include <linux/sched.h>
 #include <linux/capability.h>
 #include <linux/suspend.h>
-#include <linux/pm.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+
+#include "power.h"
+
+#define TIMEOUT		100
 
 /*
  * If set, the suspend/hibernate code will abort transitions to a sleep state
@@ -20,18 +25,244 @@
 bool events_check_enabled;
 
 /* The counter of registered wakeup events. */
-static unsigned long event_count;
+static atomic_t event_count = ATOMIC_INIT(0);
 /* A preserved old value of event_count. */
-static unsigned long saved_event_count;
+static unsigned int saved_count;
 /* The counter of wakeup events being processed. */
-static unsigned long events_in_progress;
+static atomic_t events_in_progress = ATOMIC_INIT(0);
 
 static DEFINE_SPINLOCK(events_lock);
 
 static void pm_wakeup_timer_fn(unsigned long data);
 
-static DEFINE_TIMER(events_timer, pm_wakeup_timer_fn, 0, 0);
-static unsigned long events_timer_expires;
+static LIST_HEAD(wakeup_sources);
+
+/**
+ * wakeup_source_create - Create a struct wakeup_source object.
+ * @name: Name of the new wakeup source.
+ */
+struct wakeup_source *wakeup_source_create(const char *name)
+{
+	struct wakeup_source *ws;
+
+	ws = kzalloc(sizeof(*ws), GFP_KERNEL);
+	if (!ws)
+		return NULL;
+
+	spin_lock_init(&ws->lock);
+	if (name)
+		ws->name = kstrdup(name, GFP_KERNEL);
+
+	return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_create);
+
+/**
+ * wakeup_source_destroy - Destroy a struct wakeup_source object.
+ * @ws: Wakeup source to destroy.
+ */
+void wakeup_source_destroy(struct wakeup_source *ws)
+{
+	if (!ws)
+		return;
+
+	spin_lock_irq(&ws->lock);
+	while (ws->active) {
+		spin_unlock_irq(&ws->lock);
+
+		schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
+
+		spin_lock_irq(&ws->lock);
+	}
+	spin_unlock_irq(&ws->lock);
+
+	kfree(ws->name);
+	kfree(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_destroy);
+
+/**
+ * wakeup_source_add - Add given object to the list of wakeup sources.
+ * @ws: Wakeup source object to add to the list.
+ */
+void wakeup_source_add(struct wakeup_source *ws)
+{
+	if (WARN_ON(!ws))
+		return;
+
+	setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws);
+	ws->active = false;
+
+	spin_lock_irq(&events_lock);
+	list_add_rcu(&ws->entry, &wakeup_sources);
+	spin_unlock_irq(&events_lock);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(wakeup_source_add);
+
+/**
+ * wakeup_source_remove - Remove given object from the wakeup sources list.
+ * @ws: Wakeup source object to remove from the list.
+ */
+void wakeup_source_remove(struct wakeup_source *ws)
+{
+	if (WARN_ON(!ws))
+		return;
+
+	spin_lock_irq(&events_lock);
+	list_del_rcu(&ws->entry);
+	spin_unlock_irq(&events_lock);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(wakeup_source_remove);
+
+/**
+ * wakeup_source_register - Create wakeup source and add it to the list.
+ * @name: Name of the wakeup source to register.
+ */
+struct wakeup_source *wakeup_source_register(const char *name)
+{
+	struct wakeup_source *ws;
+
+	ws = wakeup_source_create(name);
+	if (ws)
+		wakeup_source_add(ws);
+
+	return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_register);
+
+/**
+ * wakeup_source_unregister - Remove wakeup source from the list and remove it.
+ * @ws: Wakeup source object to unregister.
+ */
+void wakeup_source_unregister(struct wakeup_source *ws)
+{
+	wakeup_source_remove(ws);
+	wakeup_source_destroy(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_unregister);
+
+/**
+ * device_wakeup_attach - Attach a wakeup source object to a device object.
+ * @dev: Device to handle.
+ * @ws: Wakeup source object to attach to @dev.
+ *
+ * This causes @dev to be treated as a wakeup device.
+ */
+static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws)
+{
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		spin_unlock_irq(&dev->power.lock);
+		return -EEXIST;
+	}
+	dev->power.wakeup = ws;
+	spin_unlock_irq(&dev->power.lock);
+	return 0;
+}
+
+/**
+ * device_wakeup_enable - Enable given device to be a wakeup source.
+ * @dev: Device to handle.
+ *
+ * Create a wakeup source object, register it and attach it to @dev.
+ */
+int device_wakeup_enable(struct device *dev)
+{
+	struct wakeup_source *ws;
+	int ret;
+
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	ws = wakeup_source_register(dev_name(dev));
+	if (!ws)
+		return -ENOMEM;
+
+	ret = device_wakeup_attach(dev, ws);
+	if (ret)
+		wakeup_source_unregister(ws);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_enable);
+
+/**
+ * device_wakeup_detach - Detach a device's wakeup source object from it.
+ * @dev: Device to detach the wakeup source object from.
+ *
+ * After it returns, @dev will not be treated as a wakeup device any more.
+ */
+static struct wakeup_source *device_wakeup_detach(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	spin_lock_irq(&dev->power.lock);
+	ws = dev->power.wakeup;
+	dev->power.wakeup = NULL;
+	spin_unlock_irq(&dev->power.lock);
+	return ws;
+}
+
+/**
+ * device_wakeup_disable - Do not regard a device as a wakeup source any more.
+ * @dev: Device to handle.
+ *
+ * Detach the @dev's wakeup source object from it, unregister this wakeup source
+ * object and destroy it.
+ */
+int device_wakeup_disable(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	ws = device_wakeup_detach(dev);
+	if (ws)
+		wakeup_source_unregister(ws);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_disable);
+
+/**
+ * device_init_wakeup - Device wakeup initialization.
+ * @dev: Device to handle.
+ * @enable: Whether or not to enable @dev as a wakeup device.
+ *
+ * By default, most devices should leave wakeup disabled.  The exceptions are
+ * devices that everyone expects to be wakeup sources: keyboards, power buttons,
+ * possibly network interfaces, etc.
+ */
+int device_init_wakeup(struct device *dev, bool enable)
+{
+	int ret = 0;
+
+	if (enable) {
+		device_set_wakeup_capable(dev, true);
+		ret = device_wakeup_enable(dev);
+	} else {
+		device_set_wakeup_capable(dev, false);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(device_init_wakeup);
+
+/**
+ * device_set_wakeup_enable - Enable or disable a device to wake up the system.
+ * @dev: Device to handle.
+ */
+int device_set_wakeup_enable(struct device *dev, bool enable)
+{
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev);
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
 
 /*
  * The functions below use the observation that each wakeup event starts a
@@ -55,118 +286,259 @@
  * knowledge, however, may not be available to it, so it can simply specify time
  * to wait before the system can be suspended and pass it as the second
  * argument of pm_wakeup_event().
+ *
+ * It is valid to call pm_relax() after pm_wakeup_event(), in which case the
+ * "no suspend" period will be ended either by the pm_relax(), or by the timer
+ * function executed when the timer expires, whichever comes first.
  */
 
 /**
+ * wakup_source_activate - Mark given wakeup source as active.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and, if @ws has just been activated, notify the PM
+ * core of the event by incrementing the counter of of wakeup events being
+ * processed.
+ */
+static void wakeup_source_activate(struct wakeup_source *ws)
+{
+	ws->active = true;
+	ws->active_count++;
+	ws->timer_expires = jiffies;
+	ws->last_time = ktime_get();
+
+	atomic_inc(&events_in_progress);
+}
+
+/**
+ * __pm_stay_awake - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the source of the event.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_stay_awake(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+	ws->event_count++;
+	if (!ws->active)
+		wakeup_source_activate(ws);
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_stay_awake);
+
+/**
  * pm_stay_awake - Notify the PM core that a wakeup event is being processed.
  * @dev: Device the wakeup event is related to.
  *
- * Notify the PM core of a wakeup event (signaled by @dev) by incrementing the
- * counter of wakeup events being processed.  If @dev is not NULL, the counter
- * of wakeup events related to @dev is incremented too.
+ * Notify the PM core of a wakeup event (signaled by @dev) by calling
+ * __pm_stay_awake for the @dev's wakeup source object.
  *
  * Call this function after detecting of a wakeup event if pm_relax() is going
  * to be called directly after processing the event (and possibly passing it to
  * user space for further processing).
- *
- * It is safe to call this function from interrupt context.
  */
 void pm_stay_awake(struct device *dev)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&events_lock, flags);
-	if (dev)
-		dev->power.wakeup_count++;
+	if (!dev)
+		return;
 
-	events_in_progress++;
-	spin_unlock_irqrestore(&events_lock, flags);
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_stay_awake(dev->power.wakeup);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_stay_awake);
+
+/**
+ * wakup_source_deactivate - Mark given wakeup source as inactive.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and notify the PM core that the wakeup source has
+ * become inactive by decrementing the counter of wakeup events being processed
+ * and incrementing the counter of registered wakeup events.
+ */
+static void wakeup_source_deactivate(struct wakeup_source *ws)
+{
+	ktime_t duration;
+	ktime_t now;
+
+	ws->relax_count++;
+	/*
+	 * __pm_relax() may be called directly or from a timer function.
+	 * If it is called directly right after the timer function has been
+	 * started, but before the timer function calls __pm_relax(), it is
+	 * possible that __pm_stay_awake() will be called in the meantime and
+	 * will set ws->active.  Then, ws->active may be cleared immediately
+	 * by the __pm_relax() called from the timer function, but in such a
+	 * case ws->relax_count will be different from ws->active_count.
+	 */
+	if (ws->relax_count != ws->active_count) {
+		ws->relax_count--;
+		return;
+	}
+
+	ws->active = false;
+
+	now = ktime_get();
+	duration = ktime_sub(now, ws->last_time);
+	ws->total_time = ktime_add(ws->total_time, duration);
+	if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time))
+		ws->max_time = duration;
+
+	del_timer(&ws->timer);
+
+	/*
+	 * event_count has to be incremented before events_in_progress is
+	 * modified, so that the callers of pm_check_wakeup_events() and
+	 * pm_save_wakeup_count() don't see the old value of event_count and
+	 * events_in_progress equal to zero at the same time.
+	 */
+	atomic_inc(&event_count);
+	smp_mb__before_atomic_dec();
+	atomic_dec(&events_in_progress);
 }
 
 /**
- * pm_relax - Notify the PM core that processing of a wakeup event has ended.
- *
- * Notify the PM core that a wakeup event has been processed by decrementing
- * the counter of wakeup events being processed and incrementing the counter
- * of registered wakeup events.
+ * __pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @ws: Wakeup source object associated with the source of the event.
  *
  * Call this function for wakeup events whose processing started with calling
- * pm_stay_awake().
+ * __pm_stay_awake().
  *
  * It is safe to call it from interrupt context.
  */
-void pm_relax(void)
+void __pm_relax(struct wakeup_source *ws)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&events_lock, flags);
-	if (events_in_progress) {
-		events_in_progress--;
-		event_count++;
-	}
-	spin_unlock_irqrestore(&events_lock, flags);
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+	if (ws->active)
+		wakeup_source_deactivate(ws);
+	spin_unlock_irqrestore(&ws->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__pm_relax);
+
+/**
+ * pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @dev: Device that signaled the event.
+ *
+ * Execute __pm_relax() for the @dev's wakeup source object.
+ */
+void pm_relax(struct device *dev)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_relax(dev->power.wakeup);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_relax);
 
 /**
  * pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
+ * @data: Address of the wakeup source object associated with the event source.
  *
- * Decrease the counter of wakeup events being processed after it was increased
- * by pm_wakeup_event().
+ * Call __pm_relax() for the wakeup source whose address is stored in @data.
  */
 static void pm_wakeup_timer_fn(unsigned long data)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&events_lock, flags);
-	if (events_timer_expires
-	    && time_before_eq(events_timer_expires, jiffies)) {
-		events_in_progress--;
-		events_timer_expires = 0;
-	}
-	spin_unlock_irqrestore(&events_lock, flags);
+	__pm_relax((struct wakeup_source *)data);
 }
 
 /**
+ * __pm_wakeup_event - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the event source.
+ * @msec: Anticipated event processing time (in milliseconds).
+ *
+ * Notify the PM core of a wakeup event whose source is @ws that will take
+ * approximately @msec milliseconds to be processed by the kernel.  If @ws is
+ * not active, activate it.  If @msec is nonzero, set up the @ws' timer to
+ * execute pm_wakeup_timer_fn() in future.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec)
+{
+	unsigned long flags;
+	unsigned long expires;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	ws->event_count++;
+	if (!ws->active)
+		wakeup_source_activate(ws);
+
+	if (!msec) {
+		wakeup_source_deactivate(ws);
+		goto unlock;
+	}
+
+	expires = jiffies + msecs_to_jiffies(msec);
+	if (!expires)
+		expires = 1;
+
+	if (time_after(expires, ws->timer_expires)) {
+		mod_timer(&ws->timer, expires);
+		ws->timer_expires = expires;
+	}
+
+ unlock:
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_wakeup_event);
+
+
+/**
  * pm_wakeup_event - Notify the PM core of a wakeup event.
  * @dev: Device the wakeup event is related to.
  * @msec: Anticipated event processing time (in milliseconds).
  *
- * Notify the PM core of a wakeup event (signaled by @dev) that will take
- * approximately @msec milliseconds to be processed by the kernel.  Increment
- * the counter of registered wakeup events and (if @msec is nonzero) set up
- * the wakeup events timer to execute pm_wakeup_timer_fn() in future (if the
- * timer has not been set up already, increment the counter of wakeup events
- * being processed).  If @dev is not NULL, the counter of wakeup events related
- * to @dev is incremented too.
- *
- * It is safe to call this function from interrupt context.
+ * Call __pm_wakeup_event() for the @dev's wakeup source object.
  */
 void pm_wakeup_event(struct device *dev, unsigned int msec)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&events_lock, flags);
-	event_count++;
-	if (dev)
-		dev->power.wakeup_count++;
+	if (!dev)
+		return;
 
-	if (msec) {
-		unsigned long expires;
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_wakeup_event(dev->power.wakeup, msec);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_wakeup_event);
 
-		expires = jiffies + msecs_to_jiffies(msec);
-		if (!expires)
-			expires = 1;
+/**
+ * pm_wakeup_update_hit_counts - Update hit counts of all active wakeup sources.
+ */
+static void pm_wakeup_update_hit_counts(void)
+{
+	unsigned long flags;
+	struct wakeup_source *ws;
 
-		if (!events_timer_expires
-		    || time_after(expires, events_timer_expires)) {
-			if (!events_timer_expires)
-				events_in_progress++;
-
-			mod_timer(&events_timer, expires);
-			events_timer_expires = expires;
-		}
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		spin_lock_irqsave(&ws->lock, flags);
+		if (ws->active)
+			ws->hit_count++;
+		spin_unlock_irqrestore(&ws->lock, flags);
 	}
-	spin_unlock_irqrestore(&events_lock, flags);
+	rcu_read_unlock();
 }
 
 /**
@@ -184,10 +556,13 @@
 
 	spin_lock_irqsave(&events_lock, flags);
 	if (events_check_enabled) {
-		ret = (event_count == saved_event_count) && !events_in_progress;
+		ret = ((unsigned int)atomic_read(&event_count) == saved_count)
+			&& !atomic_read(&events_in_progress);
 		events_check_enabled = ret;
 	}
 	spin_unlock_irqrestore(&events_lock, flags);
+	if (!ret)
+		pm_wakeup_update_hit_counts();
 	return ret;
 }
 
@@ -202,24 +577,20 @@
  * drop down to zero has been interrupted by a signal (and the current number
  * of wakeup events being processed is still nonzero).  Otherwise return true.
  */
-bool pm_get_wakeup_count(unsigned long *count)
+bool pm_get_wakeup_count(unsigned int *count)
 {
 	bool ret;
 
-	spin_lock_irq(&events_lock);
 	if (capable(CAP_SYS_ADMIN))
 		events_check_enabled = false;
 
-	while (events_in_progress && !signal_pending(current)) {
-		spin_unlock_irq(&events_lock);
-
-		schedule_timeout_interruptible(msecs_to_jiffies(100));
-
-		spin_lock_irq(&events_lock);
+	while (atomic_read(&events_in_progress) && !signal_pending(current)) {
+		pm_wakeup_update_hit_counts();
+		schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
 	}
-	*count = event_count;
-	ret = !events_in_progress;
-	spin_unlock_irq(&events_lock);
+
+	ret = !atomic_read(&events_in_progress);
+	*count = atomic_read(&event_count);
 	return ret;
 }
 
@@ -232,16 +603,102 @@
  * old number of registered wakeup events to be used by pm_check_wakeup_events()
  * and return true.  Otherwise return false.
  */
-bool pm_save_wakeup_count(unsigned long count)
+bool pm_save_wakeup_count(unsigned int count)
 {
 	bool ret = false;
 
 	spin_lock_irq(&events_lock);
-	if (count == event_count && !events_in_progress) {
-		saved_event_count = count;
+	if (count == (unsigned int)atomic_read(&event_count)
+	    && !atomic_read(&events_in_progress)) {
+		saved_count = count;
 		events_check_enabled = true;
 		ret = true;
 	}
 	spin_unlock_irq(&events_lock);
+	if (!ret)
+		pm_wakeup_update_hit_counts();
 	return ret;
 }
+
+static struct dentry *wakeup_sources_stats_dentry;
+
+/**
+ * print_wakeup_source_stats - Print wakeup source statistics information.
+ * @m: seq_file to print the statistics into.
+ * @ws: Wakeup source object to print the statistics for.
+ */
+static int print_wakeup_source_stats(struct seq_file *m,
+				     struct wakeup_source *ws)
+{
+	unsigned long flags;
+	ktime_t total_time;
+	ktime_t max_time;
+	unsigned long active_count;
+	ktime_t active_time;
+	int ret;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	total_time = ws->total_time;
+	max_time = ws->max_time;
+	active_count = ws->active_count;
+	if (ws->active) {
+		active_time = ktime_sub(ktime_get(), ws->last_time);
+		total_time = ktime_add(total_time, active_time);
+		if (active_time.tv64 > max_time.tv64)
+			max_time = active_time;
+	} else {
+		active_time = ktime_set(0, 0);
+	}
+
+	ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t"
+			"%lld\t\t%lld\t\t%lld\t\t%lld\n",
+			ws->name, active_count, ws->event_count, ws->hit_count,
+			ktime_to_ms(active_time), ktime_to_ms(total_time),
+			ktime_to_ms(max_time), ktime_to_ms(ws->last_time));
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+
+	return ret;
+}
+
+/**
+ * wakeup_sources_stats_show - Print wakeup sources statistics information.
+ * @m: seq_file to print the statistics into.
+ */
+static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
+{
+	struct wakeup_source *ws;
+
+	seq_puts(m, "name\t\tactive_count\tevent_count\thit_count\t"
+		"active_since\ttotal_time\tmax_time\tlast_change\n");
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+		print_wakeup_source_stats(m, ws);
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wakeup_sources_stats_show, NULL);
+}
+
+static const struct file_operations wakeup_sources_stats_fops = {
+	.owner = THIS_MODULE,
+	.open = wakeup_sources_stats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init wakeup_sources_debugfs_init(void)
+{
+	wakeup_sources_stats_dentry = debugfs_create_file("wakeup_sources",
+			S_IRUGO, NULL, NULL, &wakeup_sources_stats_fops);
+	return 0;
+}
+
+postcore_initcall(wakeup_sources_debugfs_init);
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 9fc630c..f6f37a0 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -45,7 +45,8 @@
 	return sprintf(buf, "%d\n", topology_##name(cpu));	\
 }
 
-#if defined(topology_thread_cpumask) || defined(topology_core_cpumask)
+#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
+    defined(topology_book_cpumask)
 static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
 {
 	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
@@ -114,6 +115,14 @@
 define_one_ro_named(core_siblings, show_core_cpumask);
 define_one_ro_named(core_siblings_list, show_core_cpumask_list);
 
+#ifdef CONFIG_SCHED_BOOK
+define_id_show_func(book_id);
+define_one_ro(book_id);
+define_siblings_show_func(book_cpumask);
+define_one_ro_named(book_siblings, show_book_cpumask);
+define_one_ro_named(book_siblings_list, show_book_cpumask_list);
+#endif
+
 static struct attribute *default_attrs[] = {
 	&attr_physical_package_id.attr,
 	&attr_core_id.attr,
@@ -121,6 +130,11 @@
 	&attr_thread_siblings_list.attr,
 	&attr_core_siblings.attr,
 	&attr_core_siblings_list.attr,
+#ifdef CONFIG_SCHED_BOOK
+	&attr_book_id.attr,
+	&attr_book_siblings.attr,
+	&attr_book_siblings_list.attr,
+#endif
 	NULL
 };
 
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 4e2c367..1f286ab 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -36,7 +36,7 @@
 #include <linux/ioport.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/reboot.h>
@@ -54,6 +54,7 @@
 #define DAC960_GAM_MINOR	252
 
 
+static DEFINE_MUTEX(DAC960_mutex);
 static DAC960_Controller_T *DAC960_Controllers[DAC960_MaxControllers];
 static int DAC960_ControllerCount;
 static struct proc_dir_entry *DAC960_ProcDirectoryEntry;
@@ -81,7 +82,7 @@
 	int drive_nr = (long)disk->private_data;
 	int ret = -ENXIO;
 
-	lock_kernel();
+	mutex_lock(&DAC960_mutex);
 	if (p->FirmwareType == DAC960_V1_Controller) {
 		if (p->V1.LogicalDriveInformation[drive_nr].
 		    LogicalDriveState == DAC960_V1_LogicalDrive_Offline)
@@ -99,7 +100,7 @@
 		goto out;
 	ret = 0;
 out:
-	unlock_kernel();
+	mutex_unlock(&DAC960_mutex);
 	return ret;
 }
 
@@ -6625,7 +6626,7 @@
   long ErrorCode = 0;
   if (!capable(CAP_SYS_ADMIN)) return -EACCES;
 
-  lock_kernel();
+  mutex_lock(&DAC960_mutex);
   switch (Request)
     {
     case DAC960_IOCTL_GET_CONTROLLER_COUNT:
@@ -7056,13 +7057,14 @@
       default:
 	ErrorCode = -ENOTTY;
     }
-  unlock_kernel();
+  mutex_unlock(&DAC960_mutex);
   return ErrorCode;
 }
 
 static const struct file_operations DAC960_gam_fops = {
 	.owner		= THIS_MODULE,
-	.unlocked_ioctl	= DAC960_gam_ioctl
+	.unlocked_ioctl	= DAC960_gam_ioctl,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice DAC960_gam_dev = {
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index de27768..4b9359a 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -488,4 +488,21 @@
 
 	  If unsure, say N.
 
+config BLK_DEV_RBD
+	tristate "Rados block device (RBD)"
+	depends on INET && EXPERIMENTAL && BLOCK
+	select CEPH_LIB
+	select LIBCRC32C
+	select CRYPTO_AES
+	select CRYPTO
+	default n
+	help
+	  Say Y here if you want include the Rados block device, which stripes
+	  a block device over objects stored in the Ceph distributed object
+	  store.
+
+	  More information at http://ceph.newdream.net/.
+
+	  If unsure, say N.
+
 endif # BLK_DEV
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index aff5ac9..d7f463d 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -37,5 +37,6 @@
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)	+= xen-blkfront.o
 obj-$(CONFIG_BLK_DEV_DRBD)     += drbd/
+obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 
 swim_mod-objs	:= swim.o swim_asm.o
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 76f114f..a1725e6 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -60,7 +60,7 @@
 #include <linux/hdreg.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/amifdreg.h>
 #include <linux/amifd.h>
 #include <linux/buffer_head.h>
@@ -109,13 +109,12 @@
 #define FD_HD_3 	0x55555555  /* high-density 3.5" (1760K) drive */
 #define FD_DD_5 	0xaaaaaaaa  /* double-density 5.25" (440K) drive */
 
+static DEFINE_MUTEX(amiflop_mutex);
 static unsigned long int fd_def_df0 = FD_DD_3;     /* default for df0 if it doesn't identify */
 
 module_param(fd_def_df0, ulong, 0);
 MODULE_LICENSE("GPL");
 
-static struct request_queue *floppy_queue;
-
 /*
  *  Macros
  */
@@ -164,6 +163,7 @@
 static int writepending;
 static int writefromint;
 static char *raw_buf;
+static int fdc_queue;
 
 static DEFINE_SPINLOCK(amiflop_lock);
 
@@ -1334,6 +1334,42 @@
 	return -1;
 }
 
+/*
+ * Round-robin between our available drives, doing one request from each
+ */
+static struct request *set_next_request(void)
+{
+	struct request_queue *q;
+	int cnt = FD_MAX_UNITS;
+	struct request *rq;
+
+	/* Find next queue we can dispatch from */
+	fdc_queue = fdc_queue + 1;
+	if (fdc_queue == FD_MAX_UNITS)
+		fdc_queue = 0;
+
+	for(cnt = FD_MAX_UNITS; cnt > 0; cnt--) {
+
+		if (unit[fdc_queue].type->code == FD_NODRIVE) {
+			if (++fdc_queue == FD_MAX_UNITS)
+				fdc_queue = 0;
+			continue;
+		}
+
+		q = unit[fdc_queue].gendisk->queue;
+		if (q) {
+			rq = blk_fetch_request(q);
+			if (rq)
+				break;
+		}
+
+		if (++fdc_queue == FD_MAX_UNITS)
+			fdc_queue = 0;
+	}
+
+	return rq;
+}
+
 static void redo_fd_request(void)
 {
 	struct request *rq;
@@ -1345,7 +1381,7 @@
 	int err;
 
 next_req:
-	rq = blk_fetch_request(floppy_queue);
+	rq = set_next_request();
 	if (!rq) {
 		/* Nothing left to do */
 		return;
@@ -1506,9 +1542,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&amiflop_mutex);
 	ret = fd_locked_ioctl(bdev, mode, cmd, param);
-	unlock_kernel();
+	mutex_unlock(&amiflop_mutex);
 
 	return ret;
 }
@@ -1555,11 +1591,11 @@
 	int old_dev;
 	unsigned long flags;
 
-	lock_kernel();
+	mutex_lock(&amiflop_mutex);
 	old_dev = fd_device[drive];
 
 	if (fd_ref[drive] && old_dev != system) {
-		unlock_kernel();
+		mutex_unlock(&amiflop_mutex);
 		return -EBUSY;
 	}
 
@@ -1575,7 +1611,7 @@
 			rel_fdc();
 
 			if (wrprot) {
-				unlock_kernel();
+				mutex_unlock(&amiflop_mutex);
 				return -EROFS;
 			}
 		}
@@ -1594,7 +1630,7 @@
 	printk(KERN_INFO "fd%d: accessing %s-disk with %s-layout\n",drive,
 	       unit[drive].type->name, data_types[system].name);
 
-	unlock_kernel();
+	mutex_unlock(&amiflop_mutex);
 	return 0;
 }
 
@@ -1603,7 +1639,7 @@
 	struct amiga_floppy_struct *p = disk->private_data;
 	int drive = p - unit;
 
-	lock_kernel();
+	mutex_lock(&amiflop_mutex);
 	if (unit[drive].dirty == 1) {
 		del_timer (flush_track_timer + drive);
 		non_int_flush_track (drive);
@@ -1617,7 +1653,7 @@
 /* the mod_use counter is handled this way */
 	floppy_off (drive | 0x40000000);
 #endif
-	unlock_kernel();
+	mutex_unlock(&amiflop_mutex);
 	return 0;
 }
 
@@ -1682,6 +1718,13 @@
 			continue;
 		}
 		unit[drive].gendisk = disk;
+
+		disk->queue = blk_init_queue(do_fd_request, &amiflop_lock);
+		if (!disk->queue) {
+			unit[drive].type->code = FD_NODRIVE;
+			continue;
+		}
+
 		drives++;
 		if ((unit[drive].trackbuf = kmalloc(FLOPPY_MAX_SECTORS * 512, GFP_KERNEL)) == NULL) {
 			printk("no mem for ");
@@ -1695,7 +1738,6 @@
 		disk->fops = &floppy_fops;
 		sprintf(disk->disk_name, "fd%d", drive);
 		disk->private_data = &unit[drive];
-		disk->queue = floppy_queue;
 		set_capacity(disk, 880*2);
 		add_disk(disk);
 	}
@@ -1743,11 +1785,6 @@
 		goto out_irq2;
 	}
 
-	ret = -ENOMEM;
-	floppy_queue = blk_init_queue(do_fd_request, &amiflop_lock);
-	if (!floppy_queue)
-		goto out_queue;
-
 	ret = -ENODEV;
 	if (fd_probe_drives() < 1) /* No usable drives */
 		goto out_probe;
@@ -1791,8 +1828,6 @@
 	return 0;
 
 out_probe:
-	blk_cleanup_queue(floppy_queue);
-out_queue:
 	free_irq(IRQ_AMIGA_CIAA_TB, NULL);
 out_irq2:
 	free_irq(IRQ_AMIGA_DSKBLK, NULL);
@@ -1810,9 +1845,12 @@
 
 	for( i = 0; i < FD_MAX_UNITS; i++) {
 		if (unit[i].type->code != FD_NODRIVE) {
+			struct request_queue *q = unit[i].gendisk->queue;
 			del_gendisk(unit[i].gendisk);
 			put_disk(unit[i].gendisk);
 			kfree(unit[i].trackbuf);
+			if (q)
+				blk_cleanup_queue(q);
 		}
 	}
 	blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256);
@@ -1820,7 +1858,6 @@
 	free_irq(IRQ_AMIGA_DSKBLK, NULL);
 	custom.dmacon = DMAF_DISK; /* disable DMA */
 	amiga_chip_free(raw_buf);
-	blk_cleanup_queue(floppy_queue);
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 }
 #endif
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index a946929..f21c237 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -12,9 +12,10 @@
 #include <linux/slab.h>
 #include <linux/genhd.h>
 #include <linux/netdevice.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include "aoe.h"
 
+static DEFINE_MUTEX(aoeblk_mutex);
 static struct kmem_cache *buf_pool_cache;
 
 static ssize_t aoedisk_show_state(struct device *dev,
@@ -125,16 +126,16 @@
 	struct aoedev *d = bdev->bd_disk->private_data;
 	ulong flags;
 
-	lock_kernel();
+	mutex_lock(&aoeblk_mutex);
 	spin_lock_irqsave(&d->lock, flags);
 	if (d->flags & DEVFL_UP) {
 		d->nopen++;
 		spin_unlock_irqrestore(&d->lock, flags);
-		unlock_kernel();
+		mutex_unlock(&aoeblk_mutex);
 		return 0;
 	}
 	spin_unlock_irqrestore(&d->lock, flags);
-	unlock_kernel();
+	mutex_unlock(&aoeblk_mutex);
 	return -ENODEV;
 }
 
diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c
index 4a1b9e74..146296c 100644
--- a/drivers/block/aoe/aoechr.c
+++ b/drivers/block/aoe/aoechr.c
@@ -9,7 +9,7 @@
 #include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/skbuff.h>
 #include "aoe.h"
 
@@ -37,6 +37,7 @@
 	char *msg;
 };
 
+static DEFINE_MUTEX(aoechr_mutex);
 static struct ErrMsg emsgs[NMSG];
 static int emsgs_head_idx, emsgs_tail_idx;
 static struct completion emsgs_comp;
@@ -183,16 +184,16 @@
 {
 	int n, i;
 
-	lock_kernel();
+	mutex_lock(&aoechr_mutex);
 	n = iminor(inode);
 	filp->private_data = (void *) (unsigned long) n;
 
 	for (i = 0; i < ARRAY_SIZE(chardevs); ++i)
 		if (chardevs[i].minor == n) {
-			unlock_kernel();
+			mutex_unlock(&aoechr_mutex);
 			return 0;
 		}
-	unlock_kernel();
+	mutex_unlock(&aoechr_mutex);
 	return -EINVAL;
 }
 
@@ -265,6 +266,7 @@
 	.open = aoechr_open,
 	.release = aoechr_rel,
 	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 static char *aoe_devnode(struct device *dev, mode_t *mode)
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index aceb964..4e4cc6c 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -67,7 +67,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <asm/atafd.h>
 #include <asm/atafdreg.h>
@@ -79,8 +79,9 @@
 
 #undef DEBUG
 
-static struct request_queue *floppy_queue;
+static DEFINE_MUTEX(ataflop_mutex);
 static struct request *fd_request;
+static int fdc_queue;
 
 /* Disk types: DD, HD, ED */
 static struct atari_disk_type {
@@ -1391,6 +1392,29 @@
 			ReqTrack, ReqSector, (unsigned long)ReqData ));
 }
 
+/*
+ * Round-robin between our available drives, doing one request from each
+ */
+static struct request *set_next_request(void)
+{
+	struct request_queue *q;
+	int old_pos = fdc_queue;
+	struct request *rq;
+
+	do {
+		q = unit[fdc_queue].disk->queue;
+		if (++fdc_queue == FD_MAX_UNITS)
+			fdc_queue = 0;
+		if (q) {
+			rq = blk_fetch_request(q);
+			if (rq)
+				break;
+		}
+	} while (fdc_queue != old_pos);
+
+	return rq;
+}
+
 
 static void redo_fd_request(void)
 {
@@ -1405,7 +1429,7 @@
 
 repeat:
 	if (!fd_request) {
-		fd_request = blk_fetch_request(floppy_queue);
+		fd_request = set_next_request();
 		if (!fd_request)
 			goto the_end;
 	}
@@ -1671,9 +1695,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ataflop_mutex);
 	ret = fd_locked_ioctl(bdev, mode, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ataflop_mutex);
 
 	return ret;
 }
@@ -1854,9 +1878,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ataflop_mutex);
 	ret = floppy_open(bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&ataflop_mutex);
 
 	return ret;
 }
@@ -1864,14 +1888,14 @@
 static int floppy_release(struct gendisk *disk, fmode_t mode)
 {
 	struct atari_floppy_struct *p = disk->private_data;
-	lock_kernel();
+	mutex_lock(&ataflop_mutex);
 	if (p->ref < 0)
 		p->ref = 0;
 	else if (!p->ref--) {
 		printk(KERN_ERR "floppy_release with fd_ref == 0");
 		p->ref = 0;
 	}
-	unlock_kernel();
+	mutex_unlock(&ataflop_mutex);
 	return 0;
 }
 
@@ -1932,10 +1956,6 @@
 	PhysTrackBuffer = virt_to_phys(TrackBuffer);
 	BufferDrive = BufferSide = BufferTrack = -1;
 
-	floppy_queue = blk_init_queue(do_fd_request, &ataflop_lock);
-	if (!floppy_queue)
-		goto Enomem;
-
 	for (i = 0; i < FD_MAX_UNITS; i++) {
 		unit[i].track = -1;
 		unit[i].flags = 0;
@@ -1944,7 +1964,10 @@
 		sprintf(unit[i].disk->disk_name, "fd%d", i);
 		unit[i].disk->fops = &floppy_fops;
 		unit[i].disk->private_data = &unit[i];
-		unit[i].disk->queue = floppy_queue;
+		unit[i].disk->queue = blk_init_queue(do_fd_request,
+					&ataflop_lock);
+		if (!unit[i].disk->queue)
+			goto Enomem;
 		set_capacity(unit[i].disk, MAX_DISK_SIZE * 2);
 		add_disk(unit[i].disk);
 	}
@@ -1959,10 +1982,14 @@
 
 	return 0;
 Enomem:
-	while (i--)
+	while (i--) {
+		struct request_queue *q = unit[i].disk->queue;
+
 		put_disk(unit[i].disk);
-	if (floppy_queue)
-		blk_cleanup_queue(floppy_queue);
+		if (q)
+			blk_cleanup_queue(q);
+	}
+
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 	return -ENOMEM;
 }
@@ -2011,12 +2038,14 @@
 	int i;
 	blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256);
 	for (i = 0; i < FD_MAX_UNITS; i++) {
+		struct request_queue *q = unit[i].disk->queue;
+
 		del_gendisk(unit[i].disk);
 		put_disk(unit[i].disk);
+		blk_cleanup_queue(q);
 	}
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 
-	blk_cleanup_queue(floppy_queue);
 	del_timer_sync(&fd_timer);
 	atari_stram_free( DMABuffer );
 }
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 1c7f637..b7f51e4 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -15,7 +15,7 @@
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/highmem.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/radix-tree.h>
 #include <linux/buffer_head.h> /* invalidate_bh_lrus() */
 #include <linux/slab.h>
@@ -55,6 +55,7 @@
 /*
  * Look up and return a brd's page for a given sector.
  */
+static DEFINE_MUTEX(brd_mutex);
 static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
 {
 	pgoff_t idx;
@@ -402,7 +403,7 @@
 	 * ram device BLKFLSBUF has special semantics, we want to actually
 	 * release and destroy the ramdisk data.
 	 */
-	lock_kernel();
+	mutex_lock(&brd_mutex);
 	mutex_lock(&bdev->bd_mutex);
 	error = -EBUSY;
 	if (bdev->bd_openers <= 1) {
@@ -419,7 +420,7 @@
 		error = 0;
 	}
 	mutex_unlock(&bdev->bd_mutex);
-	unlock_kernel();
+	mutex_unlock(&brd_mutex);
 
 	return error;
 }
@@ -482,7 +483,6 @@
 	if (!brd->brd_queue)
 		goto out_free_dev;
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
-	blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 5e4fadc..f09e6df 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -26,7 +26,6 @@
 #include <linux/pci.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/delay.h>
 #include <linux/major.h>
 #include <linux/fs.h>
@@ -66,6 +65,7 @@
 MODULE_VERSION("3.6.26");
 MODULE_LICENSE("GPL");
 
+static DEFINE_MUTEX(cciss_mutex);
 static int cciss_allow_hpsa;
 module_param(cciss_allow_hpsa, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(cciss_allow_hpsa,
@@ -105,11 +105,12 @@
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3249},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x324A},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x324B},
-	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3250},
-	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3251},
-	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3252},
-	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3253},
-	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSE,     0x103C, 0x3254},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSF,     0x103C, 0x3350},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSF,     0x103C, 0x3351},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSF,     0x103C, 0x3352},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSF,     0x103C, 0x3353},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSF,     0x103C, 0x3354},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSF,     0x103C, 0x3355},
 	{0,}
 };
 
@@ -149,11 +150,12 @@
 	{0x3249103C, "Smart Array P812", &SA5_access},
 	{0x324A103C, "Smart Array P712m", &SA5_access},
 	{0x324B103C, "Smart Array P711m", &SA5_access},
-	{0x3250103C, "Smart Array", &SA5_access},
-	{0x3251103C, "Smart Array", &SA5_access},
-	{0x3252103C, "Smart Array", &SA5_access},
-	{0x3253103C, "Smart Array", &SA5_access},
-	{0x3254103C, "Smart Array", &SA5_access},
+	{0x3350103C, "Smart Array", &SA5_access},
+	{0x3351103C, "Smart Array", &SA5_access},
+	{0x3352103C, "Smart Array", &SA5_access},
+	{0x3353103C, "Smart Array", &SA5_access},
+	{0x3354103C, "Smart Array", &SA5_access},
+	{0x3355103C, "Smart Array", &SA5_access},
 };
 
 /* How long to wait (in milliseconds) for board to go into simple mode */
@@ -1059,9 +1061,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&cciss_mutex);
 	ret = cciss_open(bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&cciss_mutex);
 
 	return ret;
 }
@@ -1074,13 +1076,13 @@
 	ctlr_info_t *h;
 	drive_info_struct *drv;
 
-	lock_kernel();
+	mutex_lock(&cciss_mutex);
 	h = get_host(disk);
 	drv = get_drv(disk);
 	dev_dbg(&h->pdev->dev, "cciss_release %s\n", disk->disk_name);
 	drv->usage_count--;
 	h->usage_count--;
-	unlock_kernel();
+	mutex_unlock(&cciss_mutex);
 	return 0;
 }
 
@@ -1088,9 +1090,9 @@
 		    unsigned cmd, unsigned long arg)
 {
 	int ret;
-	lock_kernel();
+	mutex_lock(&cciss_mutex);
 	ret = cciss_ioctl(bdev, mode, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&cciss_mutex);
 	return ret;
 }
 
@@ -1232,470 +1234,452 @@
 			c->err_info->ScsiStatus != SAM_STAT_CHECK_CONDITION)
 		(void)check_for_unit_attention(h, c);
 }
-/*
- * ioctl
- */
+
+static int cciss_getpciinfo(ctlr_info_t *h, void __user *argp)
+{
+	cciss_pci_info_struct pciinfo;
+
+	if (!argp)
+		return -EINVAL;
+	pciinfo.domain = pci_domain_nr(h->pdev->bus);
+	pciinfo.bus = h->pdev->bus->number;
+	pciinfo.dev_fn = h->pdev->devfn;
+	pciinfo.board_id = h->board_id;
+	if (copy_to_user(argp, &pciinfo, sizeof(cciss_pci_info_struct)))
+		return -EFAULT;
+	return 0;
+}
+
+static int cciss_getintinfo(ctlr_info_t *h, void __user *argp)
+{
+	cciss_coalint_struct intinfo;
+
+	if (!argp)
+		return -EINVAL;
+	intinfo.delay = readl(&h->cfgtable->HostWrite.CoalIntDelay);
+	intinfo.count = readl(&h->cfgtable->HostWrite.CoalIntCount);
+	if (copy_to_user
+	    (argp, &intinfo, sizeof(cciss_coalint_struct)))
+		return -EFAULT;
+	return 0;
+}
+
+static int cciss_setintinfo(ctlr_info_t *h, void __user *argp)
+{
+	cciss_coalint_struct intinfo;
+	unsigned long flags;
+	int i;
+
+	if (!argp)
+		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (copy_from_user(&intinfo, argp, sizeof(intinfo)))
+		return -EFAULT;
+	if ((intinfo.delay == 0) && (intinfo.count == 0))
+		return -EINVAL;
+	spin_lock_irqsave(&h->lock, flags);
+	/* Update the field, and then ring the doorbell */
+	writel(intinfo.delay, &(h->cfgtable->HostWrite.CoalIntDelay));
+	writel(intinfo.count, &(h->cfgtable->HostWrite.CoalIntCount));
+	writel(CFGTBL_ChangeReq, h->vaddr + SA5_DOORBELL);
+
+	for (i = 0; i < MAX_IOCTL_CONFIG_WAIT; i++) {
+		if (!(readl(h->vaddr + SA5_DOORBELL) & CFGTBL_ChangeReq))
+			break;
+		udelay(1000); /* delay and try again */
+	}
+	spin_unlock_irqrestore(&h->lock, flags);
+	if (i >= MAX_IOCTL_CONFIG_WAIT)
+		return -EAGAIN;
+	return 0;
+}
+
+static int cciss_getnodename(ctlr_info_t *h, void __user *argp)
+{
+	NodeName_type NodeName;
+	int i;
+
+	if (!argp)
+		return -EINVAL;
+	for (i = 0; i < 16; i++)
+		NodeName[i] = readb(&h->cfgtable->ServerName[i]);
+	if (copy_to_user(argp, NodeName, sizeof(NodeName_type)))
+		return -EFAULT;
+	return 0;
+}
+
+static int cciss_setnodename(ctlr_info_t *h, void __user *argp)
+{
+	NodeName_type NodeName;
+	unsigned long flags;
+	int i;
+
+	if (!argp)
+		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (copy_from_user(NodeName, argp, sizeof(NodeName_type)))
+		return -EFAULT;
+	spin_lock_irqsave(&h->lock, flags);
+	/* Update the field, and then ring the doorbell */
+	for (i = 0; i < 16; i++)
+		writeb(NodeName[i], &h->cfgtable->ServerName[i]);
+	writel(CFGTBL_ChangeReq, h->vaddr + SA5_DOORBELL);
+	for (i = 0; i < MAX_IOCTL_CONFIG_WAIT; i++) {
+		if (!(readl(h->vaddr + SA5_DOORBELL) & CFGTBL_ChangeReq))
+			break;
+		udelay(1000); /* delay and try again */
+	}
+	spin_unlock_irqrestore(&h->lock, flags);
+	if (i >= MAX_IOCTL_CONFIG_WAIT)
+		return -EAGAIN;
+	return 0;
+}
+
+static int cciss_getheartbeat(ctlr_info_t *h, void __user *argp)
+{
+	Heartbeat_type heartbeat;
+
+	if (!argp)
+		return -EINVAL;
+	heartbeat = readl(&h->cfgtable->HeartBeat);
+	if (copy_to_user(argp, &heartbeat, sizeof(Heartbeat_type)))
+		return -EFAULT;
+	return 0;
+}
+
+static int cciss_getbustypes(ctlr_info_t *h, void __user *argp)
+{
+	BusTypes_type BusTypes;
+
+	if (!argp)
+		return -EINVAL;
+	BusTypes = readl(&h->cfgtable->BusTypes);
+	if (copy_to_user(argp, &BusTypes, sizeof(BusTypes_type)))
+		return -EFAULT;
+	return 0;
+}
+
+static int cciss_getfirmver(ctlr_info_t *h, void __user *argp)
+{
+	FirmwareVer_type firmware;
+
+	if (!argp)
+		return -EINVAL;
+	memcpy(firmware, h->firm_ver, 4);
+
+	if (copy_to_user
+	    (argp, firmware, sizeof(FirmwareVer_type)))
+		return -EFAULT;
+	return 0;
+}
+
+static int cciss_getdrivver(ctlr_info_t *h, void __user *argp)
+{
+	DriverVer_type DriverVer = DRIVER_VERSION;
+
+	if (!argp)
+		return -EINVAL;
+	if (copy_to_user(argp, &DriverVer, sizeof(DriverVer_type)))
+		return -EFAULT;
+	return 0;
+}
+
+static int cciss_getluninfo(ctlr_info_t *h,
+	struct gendisk *disk, void __user *argp)
+{
+	LogvolInfo_struct luninfo;
+	drive_info_struct *drv = get_drv(disk);
+
+	if (!argp)
+		return -EINVAL;
+	memcpy(&luninfo.LunID, drv->LunID, sizeof(luninfo.LunID));
+	luninfo.num_opens = drv->usage_count;
+	luninfo.num_parts = 0;
+	if (copy_to_user(argp, &luninfo, sizeof(LogvolInfo_struct)))
+		return -EFAULT;
+	return 0;
+}
+
+static int cciss_passthru(ctlr_info_t *h, void __user *argp)
+{
+	IOCTL_Command_struct iocommand;
+	CommandList_struct *c;
+	char *buff = NULL;
+	u64bit temp64;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	if (!argp)
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	if (copy_from_user
+	    (&iocommand, argp, sizeof(IOCTL_Command_struct)))
+		return -EFAULT;
+	if ((iocommand.buf_size < 1) &&
+	    (iocommand.Request.Type.Direction != XFER_NONE)) {
+		return -EINVAL;
+	}
+	if (iocommand.buf_size > 0) {
+		buff = kmalloc(iocommand.buf_size, GFP_KERNEL);
+		if (buff == NULL)
+			return -EFAULT;
+	}
+	if (iocommand.Request.Type.Direction == XFER_WRITE) {
+		/* Copy the data into the buffer we created */
+		if (copy_from_user(buff, iocommand.buf, iocommand.buf_size)) {
+			kfree(buff);
+			return -EFAULT;
+		}
+	} else {
+		memset(buff, 0, iocommand.buf_size);
+	}
+	c = cmd_special_alloc(h);
+	if (!c) {
+		kfree(buff);
+		return -ENOMEM;
+	}
+	/* Fill in the command type */
+	c->cmd_type = CMD_IOCTL_PEND;
+	/* Fill in Command Header */
+	c->Header.ReplyQueue = 0;   /* unused in simple mode */
+	if (iocommand.buf_size > 0) { /* buffer to fill */
+		c->Header.SGList = 1;
+		c->Header.SGTotal = 1;
+	} else { /* no buffers to fill */
+		c->Header.SGList = 0;
+		c->Header.SGTotal = 0;
+	}
+	c->Header.LUN = iocommand.LUN_info;
+	/* use the kernel address the cmd block for tag */
+	c->Header.Tag.lower = c->busaddr;
+
+	/* Fill in Request block */
+	c->Request = iocommand.Request;
+
+	/* Fill in the scatter gather information */
+	if (iocommand.buf_size > 0) {
+		temp64.val = pci_map_single(h->pdev, buff,
+			iocommand.buf_size, PCI_DMA_BIDIRECTIONAL);
+		c->SG[0].Addr.lower = temp64.val32.lower;
+		c->SG[0].Addr.upper = temp64.val32.upper;
+		c->SG[0].Len = iocommand.buf_size;
+		c->SG[0].Ext = 0;  /* we are not chaining */
+	}
+	c->waiting = &wait;
+
+	enqueue_cmd_and_start_io(h, c);
+	wait_for_completion(&wait);
+
+	/* unlock the buffers from DMA */
+	temp64.val32.lower = c->SG[0].Addr.lower;
+	temp64.val32.upper = c->SG[0].Addr.upper;
+	pci_unmap_single(h->pdev, (dma_addr_t) temp64.val, iocommand.buf_size,
+			 PCI_DMA_BIDIRECTIONAL);
+	check_ioctl_unit_attention(h, c);
+
+	/* Copy the error information out */
+	iocommand.error_info = *(c->err_info);
+	if (copy_to_user(argp, &iocommand, sizeof(IOCTL_Command_struct))) {
+		kfree(buff);
+		cmd_special_free(h, c);
+		return -EFAULT;
+	}
+
+	if (iocommand.Request.Type.Direction == XFER_READ) {
+		/* Copy the data out of the buffer we created */
+		if (copy_to_user(iocommand.buf, buff, iocommand.buf_size)) {
+			kfree(buff);
+			cmd_special_free(h, c);
+			return -EFAULT;
+		}
+	}
+	kfree(buff);
+	cmd_special_free(h, c);
+	return 0;
+}
+
+static int cciss_bigpassthru(ctlr_info_t *h, void __user *argp)
+{
+	BIG_IOCTL_Command_struct *ioc;
+	CommandList_struct *c;
+	unsigned char **buff = NULL;
+	int *buff_size = NULL;
+	u64bit temp64;
+	BYTE sg_used = 0;
+	int status = 0;
+	int i;
+	DECLARE_COMPLETION_ONSTACK(wait);
+	__u32 left;
+	__u32 sz;
+	BYTE __user *data_ptr;
+
+	if (!argp)
+		return -EINVAL;
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+	ioc = (BIG_IOCTL_Command_struct *)
+	    kmalloc(sizeof(*ioc), GFP_KERNEL);
+	if (!ioc) {
+		status = -ENOMEM;
+		goto cleanup1;
+	}
+	if (copy_from_user(ioc, argp, sizeof(*ioc))) {
+		status = -EFAULT;
+		goto cleanup1;
+	}
+	if ((ioc->buf_size < 1) &&
+	    (ioc->Request.Type.Direction != XFER_NONE)) {
+		status = -EINVAL;
+		goto cleanup1;
+	}
+	/* Check kmalloc limits  using all SGs */
+	if (ioc->malloc_size > MAX_KMALLOC_SIZE) {
+		status = -EINVAL;
+		goto cleanup1;
+	}
+	if (ioc->buf_size > ioc->malloc_size * MAXSGENTRIES) {
+		status = -EINVAL;
+		goto cleanup1;
+	}
+	buff = kzalloc(MAXSGENTRIES * sizeof(char *), GFP_KERNEL);
+	if (!buff) {
+		status = -ENOMEM;
+		goto cleanup1;
+	}
+	buff_size = kmalloc(MAXSGENTRIES * sizeof(int), GFP_KERNEL);
+	if (!buff_size) {
+		status = -ENOMEM;
+		goto cleanup1;
+	}
+	left = ioc->buf_size;
+	data_ptr = ioc->buf;
+	while (left) {
+		sz = (left > ioc->malloc_size) ? ioc->malloc_size : left;
+		buff_size[sg_used] = sz;
+		buff[sg_used] = kmalloc(sz, GFP_KERNEL);
+		if (buff[sg_used] == NULL) {
+			status = -ENOMEM;
+			goto cleanup1;
+		}
+		if (ioc->Request.Type.Direction == XFER_WRITE) {
+			if (copy_from_user(buff[sg_used], data_ptr, sz)) {
+				status = -EFAULT;
+				goto cleanup1;
+			}
+		} else {
+			memset(buff[sg_used], 0, sz);
+		}
+		left -= sz;
+		data_ptr += sz;
+		sg_used++;
+	}
+	c = cmd_special_alloc(h);
+	if (!c) {
+		status = -ENOMEM;
+		goto cleanup1;
+	}
+	c->cmd_type = CMD_IOCTL_PEND;
+	c->Header.ReplyQueue = 0;
+	c->Header.SGList = sg_used;
+	c->Header.SGTotal = sg_used;
+	c->Header.LUN = ioc->LUN_info;
+	c->Header.Tag.lower = c->busaddr;
+
+	c->Request = ioc->Request;
+	for (i = 0; i < sg_used; i++) {
+		temp64.val = pci_map_single(h->pdev, buff[i], buff_size[i],
+				    PCI_DMA_BIDIRECTIONAL);
+		c->SG[i].Addr.lower = temp64.val32.lower;
+		c->SG[i].Addr.upper = temp64.val32.upper;
+		c->SG[i].Len = buff_size[i];
+		c->SG[i].Ext = 0;	/* we are not chaining */
+	}
+	c->waiting = &wait;
+	enqueue_cmd_and_start_io(h, c);
+	wait_for_completion(&wait);
+	/* unlock the buffers from DMA */
+	for (i = 0; i < sg_used; i++) {
+		temp64.val32.lower = c->SG[i].Addr.lower;
+		temp64.val32.upper = c->SG[i].Addr.upper;
+		pci_unmap_single(h->pdev,
+			(dma_addr_t) temp64.val, buff_size[i],
+			PCI_DMA_BIDIRECTIONAL);
+	}
+	check_ioctl_unit_attention(h, c);
+	/* Copy the error information out */
+	ioc->error_info = *(c->err_info);
+	if (copy_to_user(argp, ioc, sizeof(*ioc))) {
+		cmd_special_free(h, c);
+		status = -EFAULT;
+		goto cleanup1;
+	}
+	if (ioc->Request.Type.Direction == XFER_READ) {
+		/* Copy the data out of the buffer we created */
+		BYTE __user *ptr = ioc->buf;
+		for (i = 0; i < sg_used; i++) {
+			if (copy_to_user(ptr, buff[i], buff_size[i])) {
+				cmd_special_free(h, c);
+				status = -EFAULT;
+				goto cleanup1;
+			}
+			ptr += buff_size[i];
+		}
+	}
+	cmd_special_free(h, c);
+	status = 0;
+cleanup1:
+	if (buff) {
+		for (i = 0; i < sg_used; i++)
+			kfree(buff[i]);
+		kfree(buff);
+	}
+	kfree(buff_size);
+	kfree(ioc);
+	return status;
+}
+
 static int cciss_ioctl(struct block_device *bdev, fmode_t mode,
-		       unsigned int cmd, unsigned long arg)
+	unsigned int cmd, unsigned long arg)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	ctlr_info_t *h = get_host(disk);
-	drive_info_struct *drv = get_drv(disk);
 	void __user *argp = (void __user *)arg;
 
 	dev_dbg(&h->pdev->dev, "cciss_ioctl: Called with cmd=%x %lx\n",
 		cmd, arg);
 	switch (cmd) {
 	case CCISS_GETPCIINFO:
-		{
-			cciss_pci_info_struct pciinfo;
-
-			if (!arg)
-				return -EINVAL;
-			pciinfo.domain = pci_domain_nr(h->pdev->bus);
-			pciinfo.bus = h->pdev->bus->number;
-			pciinfo.dev_fn = h->pdev->devfn;
-			pciinfo.board_id = h->board_id;
-			if (copy_to_user
-			    (argp, &pciinfo, sizeof(cciss_pci_info_struct)))
-				return -EFAULT;
-			return 0;
-		}
+		return cciss_getpciinfo(h, argp);
 	case CCISS_GETINTINFO:
-		{
-			cciss_coalint_struct intinfo;
-			if (!arg)
-				return -EINVAL;
-			intinfo.delay =
-			    readl(&h->cfgtable->HostWrite.CoalIntDelay);
-			intinfo.count =
-			    readl(&h->cfgtable->HostWrite.CoalIntCount);
-			if (copy_to_user
-			    (argp, &intinfo, sizeof(cciss_coalint_struct)))
-				return -EFAULT;
-			return 0;
-		}
+		return cciss_getintinfo(h, argp);
 	case CCISS_SETINTINFO:
-		{
-			cciss_coalint_struct intinfo;
-			unsigned long flags;
-			int i;
-
-			if (!arg)
-				return -EINVAL;
-			if (!capable(CAP_SYS_ADMIN))
-				return -EPERM;
-			if (copy_from_user
-			    (&intinfo, argp, sizeof(cciss_coalint_struct)))
-				return -EFAULT;
-			if ((intinfo.delay == 0) && (intinfo.count == 0))
-				return -EINVAL;
-			spin_lock_irqsave(&h->lock, flags);
-			/* Update the field, and then ring the doorbell */
-			writel(intinfo.delay,
-			       &(h->cfgtable->HostWrite.CoalIntDelay));
-			writel(intinfo.count,
-			       &(h->cfgtable->HostWrite.CoalIntCount));
-			writel(CFGTBL_ChangeReq, h->vaddr + SA5_DOORBELL);
-
-			for (i = 0; i < MAX_IOCTL_CONFIG_WAIT; i++) {
-				if (!(readl(h->vaddr + SA5_DOORBELL)
-				      & CFGTBL_ChangeReq))
-					break;
-				/* delay and try again */
-				udelay(1000);
-			}
-			spin_unlock_irqrestore(&h->lock, flags);
-			if (i >= MAX_IOCTL_CONFIG_WAIT)
-				return -EAGAIN;
-			return 0;
-		}
+		return cciss_setintinfo(h, argp);
 	case CCISS_GETNODENAME:
-		{
-			NodeName_type NodeName;
-			int i;
-
-			if (!arg)
-				return -EINVAL;
-			for (i = 0; i < 16; i++)
-				NodeName[i] =
-				    readb(&h->cfgtable->ServerName[i]);
-			if (copy_to_user(argp, NodeName, sizeof(NodeName_type)))
-				return -EFAULT;
-			return 0;
-		}
+		return cciss_getnodename(h, argp);
 	case CCISS_SETNODENAME:
-		{
-			NodeName_type NodeName;
-			unsigned long flags;
-			int i;
-
-			if (!arg)
-				return -EINVAL;
-			if (!capable(CAP_SYS_ADMIN))
-				return -EPERM;
-
-			if (copy_from_user
-			    (NodeName, argp, sizeof(NodeName_type)))
-				return -EFAULT;
-
-			spin_lock_irqsave(&h->lock, flags);
-
-			/* Update the field, and then ring the doorbell */
-			for (i = 0; i < 16; i++)
-				writeb(NodeName[i],
-				       &h->cfgtable->ServerName[i]);
-
-			writel(CFGTBL_ChangeReq, h->vaddr + SA5_DOORBELL);
-
-			for (i = 0; i < MAX_IOCTL_CONFIG_WAIT; i++) {
-				if (!(readl(h->vaddr + SA5_DOORBELL)
-				      & CFGTBL_ChangeReq))
-					break;
-				/* delay and try again */
-				udelay(1000);
-			}
-			spin_unlock_irqrestore(&h->lock, flags);
-			if (i >= MAX_IOCTL_CONFIG_WAIT)
-				return -EAGAIN;
-			return 0;
-		}
-
+		return cciss_setnodename(h, argp);
 	case CCISS_GETHEARTBEAT:
-		{
-			Heartbeat_type heartbeat;
-
-			if (!arg)
-				return -EINVAL;
-			heartbeat = readl(&h->cfgtable->HeartBeat);
-			if (copy_to_user
-			    (argp, &heartbeat, sizeof(Heartbeat_type)))
-				return -EFAULT;
-			return 0;
-		}
+		return cciss_getheartbeat(h, argp);
 	case CCISS_GETBUSTYPES:
-		{
-			BusTypes_type BusTypes;
-
-			if (!arg)
-				return -EINVAL;
-			BusTypes = readl(&h->cfgtable->BusTypes);
-			if (copy_to_user
-			    (argp, &BusTypes, sizeof(BusTypes_type)))
-				return -EFAULT;
-			return 0;
-		}
+		return cciss_getbustypes(h, argp);
 	case CCISS_GETFIRMVER:
-		{
-			FirmwareVer_type firmware;
-
-			if (!arg)
-				return -EINVAL;
-			memcpy(firmware, h->firm_ver, 4);
-
-			if (copy_to_user
-			    (argp, firmware, sizeof(FirmwareVer_type)))
-				return -EFAULT;
-			return 0;
-		}
+		return cciss_getfirmver(h, argp);
 	case CCISS_GETDRIVVER:
-		{
-			DriverVer_type DriverVer = DRIVER_VERSION;
-
-			if (!arg)
-				return -EINVAL;
-
-			if (copy_to_user
-			    (argp, &DriverVer, sizeof(DriverVer_type)))
-				return -EFAULT;
-			return 0;
-		}
-
+		return cciss_getdrivver(h, argp);
 	case CCISS_DEREGDISK:
 	case CCISS_REGNEWD:
 	case CCISS_REVALIDVOLS:
 		return rebuild_lun_table(h, 0, 1);
-
-	case CCISS_GETLUNINFO:{
-			LogvolInfo_struct luninfo;
-
-			memcpy(&luninfo.LunID, drv->LunID,
-				sizeof(luninfo.LunID));
-			luninfo.num_opens = drv->usage_count;
-			luninfo.num_parts = 0;
-			if (copy_to_user(argp, &luninfo,
-					 sizeof(LogvolInfo_struct)))
-				return -EFAULT;
-			return 0;
-		}
+	case CCISS_GETLUNINFO:
+		return cciss_getluninfo(h, disk, argp);
 	case CCISS_PASSTHRU:
-		{
-			IOCTL_Command_struct iocommand;
-			CommandList_struct *c;
-			char *buff = NULL;
-			u64bit temp64;
-			DECLARE_COMPLETION_ONSTACK(wait);
-
-			if (!arg)
-				return -EINVAL;
-
-			if (!capable(CAP_SYS_RAWIO))
-				return -EPERM;
-
-			if (copy_from_user
-			    (&iocommand, argp, sizeof(IOCTL_Command_struct)))
-				return -EFAULT;
-			if ((iocommand.buf_size < 1) &&
-			    (iocommand.Request.Type.Direction != XFER_NONE)) {
-				return -EINVAL;
-			}
-#if 0				/* 'buf_size' member is 16-bits, and always smaller than kmalloc limit */
-			/* Check kmalloc limits */
-			if (iocommand.buf_size > 128000)
-				return -EINVAL;
-#endif
-			if (iocommand.buf_size > 0) {
-				buff = kmalloc(iocommand.buf_size, GFP_KERNEL);
-				if (buff == NULL)
-					return -EFAULT;
-			}
-			if (iocommand.Request.Type.Direction == XFER_WRITE) {
-				/* Copy the data into the buffer we created */
-				if (copy_from_user
-				    (buff, iocommand.buf, iocommand.buf_size)) {
-					kfree(buff);
-					return -EFAULT;
-				}
-			} else {
-				memset(buff, 0, iocommand.buf_size);
-			}
-			c = cmd_special_alloc(h);
-			if (!c) {
-				kfree(buff);
-				return -ENOMEM;
-			}
-			/* Fill in the command type */
-			c->cmd_type = CMD_IOCTL_PEND;
-			/* Fill in Command Header */
-			c->Header.ReplyQueue = 0;   /* unused in simple mode */
-			if (iocommand.buf_size > 0) /* buffer to fill */
-			{
-				c->Header.SGList = 1;
-				c->Header.SGTotal = 1;
-			} else /* no buffers to fill */
-			{
-				c->Header.SGList = 0;
-				c->Header.SGTotal = 0;
-			}
-			c->Header.LUN = iocommand.LUN_info;
-			/* use the kernel address the cmd block for tag */
-			c->Header.Tag.lower = c->busaddr;
-
-			/* Fill in Request block */
-			c->Request = iocommand.Request;
-
-			/* Fill in the scatter gather information */
-			if (iocommand.buf_size > 0) {
-				temp64.val = pci_map_single(h->pdev, buff,
-					iocommand.buf_size,
-					PCI_DMA_BIDIRECTIONAL);
-				c->SG[0].Addr.lower = temp64.val32.lower;
-				c->SG[0].Addr.upper = temp64.val32.upper;
-				c->SG[0].Len = iocommand.buf_size;
-				c->SG[0].Ext = 0;  /* we are not chaining */
-			}
-			c->waiting = &wait;
-
-			enqueue_cmd_and_start_io(h, c);
-			wait_for_completion(&wait);
-
-			/* unlock the buffers from DMA */
-			temp64.val32.lower = c->SG[0].Addr.lower;
-			temp64.val32.upper = c->SG[0].Addr.upper;
-			pci_unmap_single(h->pdev, (dma_addr_t) temp64.val,
-					 iocommand.buf_size,
-					 PCI_DMA_BIDIRECTIONAL);
-
-			check_ioctl_unit_attention(h, c);
-
-			/* Copy the error information out */
-			iocommand.error_info = *(c->err_info);
-			if (copy_to_user
-			    (argp, &iocommand, sizeof(IOCTL_Command_struct))) {
-				kfree(buff);
-				cmd_special_free(h, c);
-				return -EFAULT;
-			}
-
-			if (iocommand.Request.Type.Direction == XFER_READ) {
-				/* Copy the data out of the buffer we created */
-				if (copy_to_user
-				    (iocommand.buf, buff, iocommand.buf_size)) {
-					kfree(buff);
-					cmd_special_free(h, c);
-					return -EFAULT;
-				}
-			}
-			kfree(buff);
-			cmd_special_free(h, c);
-			return 0;
-		}
-	case CCISS_BIG_PASSTHRU:{
-			BIG_IOCTL_Command_struct *ioc;
-			CommandList_struct *c;
-			unsigned char **buff = NULL;
-			int *buff_size = NULL;
-			u64bit temp64;
-			BYTE sg_used = 0;
-			int status = 0;
-			int i;
-			DECLARE_COMPLETION_ONSTACK(wait);
-			__u32 left;
-			__u32 sz;
-			BYTE __user *data_ptr;
-
-			if (!arg)
-				return -EINVAL;
-			if (!capable(CAP_SYS_RAWIO))
-				return -EPERM;
-			ioc = (BIG_IOCTL_Command_struct *)
-			    kmalloc(sizeof(*ioc), GFP_KERNEL);
-			if (!ioc) {
-				status = -ENOMEM;
-				goto cleanup1;
-			}
-			if (copy_from_user(ioc, argp, sizeof(*ioc))) {
-				status = -EFAULT;
-				goto cleanup1;
-			}
-			if ((ioc->buf_size < 1) &&
-			    (ioc->Request.Type.Direction != XFER_NONE)) {
-				status = -EINVAL;
-				goto cleanup1;
-			}
-			/* Check kmalloc limits  using all SGs */
-			if (ioc->malloc_size > MAX_KMALLOC_SIZE) {
-				status = -EINVAL;
-				goto cleanup1;
-			}
-			if (ioc->buf_size > ioc->malloc_size * MAXSGENTRIES) {
-				status = -EINVAL;
-				goto cleanup1;
-			}
-			buff =
-			    kzalloc(MAXSGENTRIES * sizeof(char *), GFP_KERNEL);
-			if (!buff) {
-				status = -ENOMEM;
-				goto cleanup1;
-			}
-			buff_size = kmalloc(MAXSGENTRIES * sizeof(int),
-						   GFP_KERNEL);
-			if (!buff_size) {
-				status = -ENOMEM;
-				goto cleanup1;
-			}
-			left = ioc->buf_size;
-			data_ptr = ioc->buf;
-			while (left) {
-				sz = (left >
-				      ioc->malloc_size) ? ioc->
-				    malloc_size : left;
-				buff_size[sg_used] = sz;
-				buff[sg_used] = kmalloc(sz, GFP_KERNEL);
-				if (buff[sg_used] == NULL) {
-					status = -ENOMEM;
-					goto cleanup1;
-				}
-				if (ioc->Request.Type.Direction == XFER_WRITE) {
-					if (copy_from_user
-					    (buff[sg_used], data_ptr, sz)) {
-						status = -EFAULT;
-						goto cleanup1;
-					}
-				} else {
-					memset(buff[sg_used], 0, sz);
-				}
-				left -= sz;
-				data_ptr += sz;
-				sg_used++;
-			}
-			c = cmd_special_alloc(h);
-			if (!c) {
-				status = -ENOMEM;
-				goto cleanup1;
-			}
-			c->cmd_type = CMD_IOCTL_PEND;
-			c->Header.ReplyQueue = 0;
-
-			if (ioc->buf_size > 0) {
-				c->Header.SGList = sg_used;
-				c->Header.SGTotal = sg_used;
-			} else {
-				c->Header.SGList = 0;
-				c->Header.SGTotal = 0;
-			}
-			c->Header.LUN = ioc->LUN_info;
-			c->Header.Tag.lower = c->busaddr;
-
-			c->Request = ioc->Request;
-			if (ioc->buf_size > 0) {
-				for (i = 0; i < sg_used; i++) {
-					temp64.val =
-					    pci_map_single(h->pdev, buff[i],
-						    buff_size[i],
-						    PCI_DMA_BIDIRECTIONAL);
-					c->SG[i].Addr.lower =
-					    temp64.val32.lower;
-					c->SG[i].Addr.upper =
-					    temp64.val32.upper;
-					c->SG[i].Len = buff_size[i];
-					c->SG[i].Ext = 0;	/* we are not chaining */
-				}
-			}
-			c->waiting = &wait;
-			enqueue_cmd_and_start_io(h, c);
-			wait_for_completion(&wait);
-			/* unlock the buffers from DMA */
-			for (i = 0; i < sg_used; i++) {
-				temp64.val32.lower = c->SG[i].Addr.lower;
-				temp64.val32.upper = c->SG[i].Addr.upper;
-				pci_unmap_single(h->pdev,
-					(dma_addr_t) temp64.val, buff_size[i],
-					PCI_DMA_BIDIRECTIONAL);
-			}
-			check_ioctl_unit_attention(h, c);
-			/* Copy the error information out */
-			ioc->error_info = *(c->err_info);
-			if (copy_to_user(argp, ioc, sizeof(*ioc))) {
-				cmd_special_free(h, c);
-				status = -EFAULT;
-				goto cleanup1;
-			}
-			if (ioc->Request.Type.Direction == XFER_READ) {
-				/* Copy the data out of the buffer we created */
-				BYTE __user *ptr = ioc->buf;
-				for (i = 0; i < sg_used; i++) {
-					if (copy_to_user
-					    (ptr, buff[i], buff_size[i])) {
-						cmd_special_free(h, c);
-						status = -EFAULT;
-						goto cleanup1;
-					}
-					ptr += buff_size[i];
-				}
-			}
-			cmd_special_free(h, c);
-			status = 0;
-		      cleanup1:
-			if (buff) {
-				for (i = 0; i < sg_used; i++)
-					kfree(buff[i]);
-				kfree(buff);
-			}
-			kfree(buff_size);
-			kfree(ioc);
-			return status;
-		}
+		return cciss_passthru(h, argp);
+	case CCISS_BIG_PASSTHRU:
+		return cciss_bigpassthru(h, argp);
 
 	/* scsi_cmd_ioctl handles these, below, though some are not */
 	/* very meaningful for cciss.  SG_IO is the main one people want. */
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index d53b029..946dad4 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -35,7 +35,7 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/hdreg.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>
 #include <linux/genhd.h>
@@ -68,6 +68,7 @@
 
 #define CPQARRAY_DMA_MASK	0xFFFFFFFF	/* 32 bit DMA */
 
+static DEFINE_MUTEX(cpqarray_mutex);
 static int nr_ctlr;
 static ctlr_info_t *hba[MAX_CTLR];
 
@@ -845,9 +846,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&cpqarray_mutex);
 	ret = ida_open(bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&cpqarray_mutex);
 
 	return ret;
 }
@@ -859,10 +860,10 @@
 {
 	ctlr_info_t *host;
 
-	lock_kernel();
+	mutex_lock(&cpqarray_mutex);
 	host = get_host(disk);
 	host->usage_count--;
-	unlock_kernel();
+	mutex_unlock(&cpqarray_mutex);
 
 	return 0;
 }
@@ -1217,9 +1218,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&cpqarray_mutex);
 	ret = ida_locked_ioctl(bdev, mode, cmd, param);
-	unlock_kernel();
+	mutex_unlock(&cpqarray_mutex);
 
 	return ret;
 }
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 9400845..ac04ef9 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -965,29 +965,30 @@
 	 * ok, (capacity & 7) != 0 sometimes, but who cares...
 	 * we count rs_{total,left} in bits, not sectors.
 	 */
-	spin_lock_irqsave(&mdev->al_lock, flags);
 	count = drbd_bm_clear_bits(mdev, sbnr, ebnr);
-	if (count) {
-		/* we need the lock for drbd_try_clear_on_disk_bm */
-		if (jiffies - mdev->rs_mark_time > HZ*10) {
-			/* should be rolling marks,
-			 * but we estimate only anyways. */
-			if (mdev->rs_mark_left != drbd_bm_total_weight(mdev) &&
+	if (count && get_ldev(mdev)) {
+		unsigned long now = jiffies;
+		unsigned long last = mdev->rs_mark_time[mdev->rs_last_mark];
+		int next = (mdev->rs_last_mark + 1) % DRBD_SYNC_MARKS;
+		if (time_after_eq(now, last + DRBD_SYNC_MARK_STEP)) {
+			unsigned long tw = drbd_bm_total_weight(mdev);
+			if (mdev->rs_mark_left[mdev->rs_last_mark] != tw &&
 			    mdev->state.conn != C_PAUSED_SYNC_T &&
 			    mdev->state.conn != C_PAUSED_SYNC_S) {
-				mdev->rs_mark_time = jiffies;
-				mdev->rs_mark_left = drbd_bm_total_weight(mdev);
+				mdev->rs_mark_time[next] = now;
+				mdev->rs_mark_left[next] = tw;
+				mdev->rs_last_mark = next;
 			}
 		}
-		if (get_ldev(mdev)) {
-			drbd_try_clear_on_disk_bm(mdev, sector, count, TRUE);
-			put_ldev(mdev);
-		}
+		spin_lock_irqsave(&mdev->al_lock, flags);
+		drbd_try_clear_on_disk_bm(mdev, sector, count, TRUE);
+		spin_unlock_irqrestore(&mdev->al_lock, flags);
+
 		/* just wake_up unconditional now, various lc_chaged(),
 		 * lc_put() in drbd_try_clear_on_disk_bm(). */
 		wake_up = 1;
+		put_ldev(mdev);
 	}
-	spin_unlock_irqrestore(&mdev->al_lock, flags);
 	if (wake_up)
 		wake_up(&mdev->al_wait);
 }
@@ -1118,7 +1119,7 @@
  * @mdev:	DRBD device.
  * @sector:	The sector number.
  *
- * This functions sleeps on al_wait. Returns 1 on success, 0 if interrupted.
+ * This functions sleeps on al_wait. Returns 0 on success, -EINTR if interrupted.
  */
 int drbd_rs_begin_io(struct drbd_conf *mdev, sector_t sector)
 {
@@ -1129,10 +1130,10 @@
 	sig = wait_event_interruptible(mdev->al_wait,
 			(bm_ext = _bme_get(mdev, enr)));
 	if (sig)
-		return 0;
+		return -EINTR;
 
 	if (test_bit(BME_LOCKED, &bm_ext->flags))
-		return 1;
+		return 0;
 
 	for (i = 0; i < AL_EXT_PER_BM_SECT; i++) {
 		sig = wait_event_interruptible(mdev->al_wait,
@@ -1145,13 +1146,11 @@
 				wake_up(&mdev->al_wait);
 			}
 			spin_unlock_irq(&mdev->al_lock);
-			return 0;
+			return -EINTR;
 		}
 	}
-
 	set_bit(BME_LOCKED, &bm_ext->flags);
-
-	return 1;
+	return 0;
 }
 
 /**
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index e3f88d6..fd42832 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -569,7 +569,7 @@
  *
  * maybe bm_set should be atomic_t ?
  */
-static unsigned long _drbd_bm_total_weight(struct drbd_conf *mdev)
+unsigned long _drbd_bm_total_weight(struct drbd_conf *mdev)
 {
 	struct drbd_bitmap *b = mdev->bitmap;
 	unsigned long s;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 352441b..9bdcf43 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -337,13 +337,25 @@
  * NOTE that the payload starts at a long aligned offset,
  * regardless of 32 or 64 bit arch!
  */
-struct p_header {
+struct p_header80 {
 	u32	  magic;
 	u16	  command;
 	u16	  length;	/* bytes of data after this header */
 	u8	  payload[0];
 } __packed;
-/* 8 bytes. packet FIXED for the next century! */
+
+/* Header for big packets, Used for data packets exceeding 64kB */
+struct p_header95 {
+	u16	  magic;	/* use DRBD_MAGIC_BIG here */
+	u16	  command;
+	u32	  length;	/* Use only 24 bits of that. Ignore the highest 8 bit. */
+	u8	  payload[0];
+} __packed;
+
+union p_header {
+	struct p_header80 h80;
+	struct p_header95 h95;
+};
 
 /*
  * short commands, packets without payload, plain p_header:
@@ -362,12 +374,16 @@
  */
 
 /* these defines must not be changed without changing the protocol version */
-#define DP_HARDBARRIER	      1
-#define DP_RW_SYNC	      2
+#define DP_HARDBARRIER	      1 /* depricated */
+#define DP_RW_SYNC	      2 /* equals REQ_SYNC    */
 #define DP_MAY_SET_IN_SYNC    4
+#define DP_UNPLUG             8 /* equals REQ_UNPLUG  */
+#define DP_FUA               16 /* equals REQ_FUA     */
+#define DP_FLUSH             32 /* equals REQ_FLUSH   */
+#define DP_DISCARD           64 /* equals REQ_DISCARD */
 
 struct p_data {
-	struct p_header head;
+	union p_header head;
 	u64	    sector;    /* 64 bits sector number */
 	u64	    block_id;  /* to identify the request in protocol B&C */
 	u32	    seq_num;
@@ -383,7 +399,7 @@
  *   P_DATA_REQUEST, P_RS_DATA_REQUEST
  */
 struct p_block_ack {
-	struct p_header head;
+	struct p_header80 head;
 	u64	    sector;
 	u64	    block_id;
 	u32	    blksize;
@@ -392,7 +408,7 @@
 
 
 struct p_block_req {
-	struct p_header head;
+	struct p_header80 head;
 	u64 sector;
 	u64 block_id;
 	u32 blksize;
@@ -409,7 +425,7 @@
  */
 
 struct p_handshake {
-	struct p_header head;	/* 8 bytes */
+	struct p_header80 head;	/* 8 bytes */
 	u32 protocol_min;
 	u32 feature_flags;
 	u32 protocol_max;
@@ -424,19 +440,19 @@
 /* 80 bytes, FIXED for the next century */
 
 struct p_barrier {
-	struct p_header head;
+	struct p_header80 head;
 	u32 barrier;	/* barrier number _handle_ only */
 	u32 pad;	/* to multiple of 8 Byte */
 } __packed;
 
 struct p_barrier_ack {
-	struct p_header head;
+	struct p_header80 head;
 	u32 barrier;
 	u32 set_size;
 } __packed;
 
 struct p_rs_param {
-	struct p_header head;
+	struct p_header80 head;
 	u32 rate;
 
 	      /* Since protocol version 88 and higher. */
@@ -444,20 +460,31 @@
 } __packed;
 
 struct p_rs_param_89 {
-	struct p_header head;
+	struct p_header80 head;
 	u32 rate;
         /* protocol version 89: */
 	char verify_alg[SHARED_SECRET_MAX];
 	char csums_alg[SHARED_SECRET_MAX];
 } __packed;
 
+struct p_rs_param_95 {
+	struct p_header80 head;
+	u32 rate;
+	char verify_alg[SHARED_SECRET_MAX];
+	char csums_alg[SHARED_SECRET_MAX];
+	u32 c_plan_ahead;
+	u32 c_delay_target;
+	u32 c_fill_target;
+	u32 c_max_rate;
+} __packed;
+
 enum drbd_conn_flags {
 	CF_WANT_LOSE = 1,
 	CF_DRY_RUN = 2,
 };
 
 struct p_protocol {
-	struct p_header head;
+	struct p_header80 head;
 	u32 protocol;
 	u32 after_sb_0p;
 	u32 after_sb_1p;
@@ -471,17 +498,17 @@
 } __packed;
 
 struct p_uuids {
-	struct p_header head;
+	struct p_header80 head;
 	u64 uuid[UI_EXTENDED_SIZE];
 } __packed;
 
 struct p_rs_uuid {
-	struct p_header head;
+	struct p_header80 head;
 	u64	    uuid;
 } __packed;
 
 struct p_sizes {
-	struct p_header head;
+	struct p_header80 head;
 	u64	    d_size;  /* size of disk */
 	u64	    u_size;  /* user requested size */
 	u64	    c_size;  /* current exported size */
@@ -491,18 +518,18 @@
 } __packed;
 
 struct p_state {
-	struct p_header head;
+	struct p_header80 head;
 	u32	    state;
 } __packed;
 
 struct p_req_state {
-	struct p_header head;
+	struct p_header80 head;
 	u32	    mask;
 	u32	    val;
 } __packed;
 
 struct p_req_state_reply {
-	struct p_header head;
+	struct p_header80 head;
 	u32	    retcode;
 } __packed;
 
@@ -517,7 +544,7 @@
 } __packed;
 
 struct p_discard {
-	struct p_header head;
+	struct p_header80 head;
 	u64	    block_id;
 	u32	    seq_num;
 	u32	    pad;
@@ -533,7 +560,7 @@
 };
 
 struct p_compressed_bm {
-	struct p_header head;
+	struct p_header80 head;
 	/* (encoding & 0x0f): actual encoding, see enum drbd_bitmap_code
 	 * (encoding & 0x80): polarity (set/unset) of first runlength
 	 * ((encoding >> 4) & 0x07): pad_bits, number of trailing zero bits
@@ -544,10 +571,10 @@
 	u8 code[0];
 } __packed;
 
-struct p_delay_probe {
-	struct p_header head;
-	u32	seq_num; /* sequence number to match the two probe packets */
-	u32	offset;	 /* usecs the probe got sent after the reference time point */
+struct p_delay_probe93 {
+	struct p_header80 head;
+	u32     seq_num; /* sequence number to match the two probe packets */
+	u32     offset;  /* usecs the probe got sent after the reference time point */
 } __packed;
 
 /* DCBP: Drbd Compressed Bitmap Packet ... */
@@ -594,7 +621,7 @@
  * so we need to use the fixed size 4KiB page size
  * most architechtures have used for a long time.
  */
-#define BM_PACKET_PAYLOAD_BYTES (4096 - sizeof(struct p_header))
+#define BM_PACKET_PAYLOAD_BYTES (4096 - sizeof(struct p_header80))
 #define BM_PACKET_WORDS (BM_PACKET_PAYLOAD_BYTES/sizeof(long))
 #define BM_PACKET_VLI_BYTES_MAX (4096 - sizeof(struct p_compressed_bm))
 #if (PAGE_SIZE < 4096)
@@ -603,13 +630,14 @@
 #endif
 
 union p_polymorph {
-        struct p_header          header;
+        union p_header           header;
         struct p_handshake       handshake;
         struct p_data            data;
         struct p_block_ack       block_ack;
         struct p_barrier         barrier;
         struct p_barrier_ack     barrier_ack;
         struct p_rs_param_89     rs_param_89;
+        struct p_rs_param_95     rs_param_95;
         struct p_protocol        protocol;
         struct p_sizes           sizes;
         struct p_uuids           uuids;
@@ -617,6 +645,8 @@
         struct p_req_state       req_state;
         struct p_req_state_reply req_state_reply;
         struct p_block_req       block_req;
+	struct p_delay_probe93   delay_probe93;
+	struct p_rs_uuid         rs_uuid;
 } __packed;
 
 /**********************************************************************/
@@ -697,7 +727,7 @@
 	struct list_head requests; /* requests before */
 	struct drbd_tl_epoch *next; /* pointer to the next barrier */
 	unsigned int br_number;  /* the barriers identifier. */
-	int n_req;	/* number of requests attached before this barrier */
+	int n_writes;	/* number of requests attached before this barrier */
 };
 
 struct drbd_request;
@@ -747,7 +777,7 @@
 struct drbd_epoch_entry {
 	struct drbd_work w;
 	struct hlist_node colision;
-	struct drbd_epoch *epoch;
+	struct drbd_epoch *epoch; /* for writes */
 	struct drbd_conf *mdev;
 	struct page *pages;
 	atomic_t pending_bios;
@@ -755,7 +785,10 @@
 	/* see comments on ee flag bits below */
 	unsigned long flags;
 	sector_t sector;
-	u64 block_id;
+	union {
+		u64 block_id;
+		struct digest_info *digest;
+	};
 };
 
 /* ee flag bits.
@@ -781,12 +814,16 @@
 	 * if any of those fail, we set this flag atomically
 	 * from the endio callback */
 	__EE_WAS_ERROR,
+
+	/* This ee has a pointer to a digest instead of a block id */
+	__EE_HAS_DIGEST,
 };
 #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
 #define EE_MAY_SET_IN_SYNC     (1<<__EE_MAY_SET_IN_SYNC)
 #define EE_IS_BARRIER          (1<<__EE_IS_BARRIER)
 #define	EE_RESUBMITTED         (1<<__EE_RESUBMITTED)
 #define EE_WAS_ERROR           (1<<__EE_WAS_ERROR)
+#define EE_HAS_DIGEST          (1<<__EE_HAS_DIGEST)
 
 /* global flag bits */
 enum {
@@ -794,7 +831,6 @@
 	SIGNAL_ASENDER,		/* whether asender wants to be interrupted */
 	SEND_PING,		/* whether asender should send a ping asap */
 
-	STOP_SYNC_TIMER,	/* tell timer to cancel itself */
 	UNPLUG_QUEUED,		/* only relevant with kernel 2.4 */
 	UNPLUG_REMOTE,		/* sending a "UnplugRemote" could help */
 	MD_DIRTY,		/* current uuids and flags not yet on disk */
@@ -816,6 +852,7 @@
 	BITMAP_IO,		/* suspend application io;
 				   once no more io in flight, start bitmap io */
 	BITMAP_IO_QUEUED,       /* Started bitmap IO */
+	GO_DISKLESS,		/* Disk failed, local_cnt reached zero, we are going diskless */
 	RESYNC_AFTER_NEG,       /* Resync after online grow after the attach&negotiate finished. */
 	NET_CONGESTED,		/* The data socket is congested */
 
@@ -829,6 +866,8 @@
 				 * the peer, if it changed there as well. */
 	CONN_DRY_RUN,		/* Expect disconnect after resync handshake. */
 	GOT_PING_ACK,		/* set when we receive a ping_ack packet, misc wait gets woken */
+	NEW_CUR_UUID,		/* Create new current UUID when thawing IO */
+	AL_SUSPENDED,		/* Activity logging is currently suspended. */
 };
 
 struct drbd_bitmap; /* opaque for drbd_conf */
@@ -838,10 +877,6 @@
 
 /* THINK maybe we actually want to use the default "event/%s" worker threads
  * or similar in linux 2.6, which uses per cpu data and threads.
- *
- * To be general, this might need a spin_lock member.
- * For now, please use the mdev->req_lock to protect list_head,
- * see drbd_queue_work below.
  */
 struct drbd_work_queue {
 	struct list_head q;
@@ -915,6 +950,12 @@
 	WO_bio_barrier
 };
 
+struct fifo_buffer {
+	int *values;
+	unsigned int head_index;
+	unsigned int size;
+};
+
 struct drbd_conf {
 	/* things that are stored as / read from meta data on disk */
 	unsigned long flags;
@@ -936,9 +977,16 @@
 	unsigned int ko_count;
 	struct drbd_work  resync_work,
 			  unplug_work,
+			  go_diskless,
 			  md_sync_work;
 	struct timer_list resync_timer;
 	struct timer_list md_sync_timer;
+#ifdef DRBD_DEBUG_MD_SYNC
+	struct {
+		unsigned int line;
+		const char* func;
+	} last_md_mark_dirty;
+#endif
 
 	/* Used after attach while negotiating new disk state. */
 	union drbd_state new_state_tmp;
@@ -946,6 +994,7 @@
 	union drbd_state state;
 	wait_queue_head_t misc_wait;
 	wait_queue_head_t state_wait;  /* upon each state change. */
+	wait_queue_head_t net_cnt_wait;
 	unsigned int send_cnt;
 	unsigned int recv_cnt;
 	unsigned int read_cnt;
@@ -974,12 +1023,16 @@
 	unsigned long rs_start;
 	/* cumulated time in PausedSyncX state [unit jiffies] */
 	unsigned long rs_paused;
-	/* block not up-to-date at mark [unit BM_BLOCK_SIZE] */
-	unsigned long rs_mark_left;
-	/* marks's time [unit jiffies] */
-	unsigned long rs_mark_time;
-	/* skipped because csum was equeal [unit BM_BLOCK_SIZE] */
+	/* skipped because csum was equal [unit BM_BLOCK_SIZE] */
 	unsigned long rs_same_csum;
+#define DRBD_SYNC_MARKS 8
+#define DRBD_SYNC_MARK_STEP (3*HZ)
+	/* block not up-to-date at mark [unit BM_BLOCK_SIZE] */
+	unsigned long rs_mark_left[DRBD_SYNC_MARKS];
+	/* marks's time [unit jiffies] */
+	unsigned long rs_mark_time[DRBD_SYNC_MARKS];
+	/* current index into rs_mark_{left,time} */
+	int rs_last_mark;
 
 	/* where does the admin want us to start? (sector) */
 	sector_t ov_start_sector;
@@ -1012,10 +1065,10 @@
 	spinlock_t epoch_lock;
 	unsigned int epochs;
 	enum write_ordering_e write_ordering;
-	struct list_head active_ee; /* IO in progress */
-	struct list_head sync_ee;   /* IO in progress */
+	struct list_head active_ee; /* IO in progress (P_DATA gets written to disk) */
+	struct list_head sync_ee;   /* IO in progress (P_RS_DATA_REPLY gets written to disk) */
 	struct list_head done_ee;   /* send ack */
-	struct list_head read_ee;   /* IO in progress */
+	struct list_head read_ee;   /* IO in progress (any read) */
 	struct list_head net_ee;    /* zero-copy network send in progress */
 	struct hlist_head *ee_hash; /* is proteced by req_lock! */
 	unsigned int ee_hash_s;
@@ -1026,7 +1079,8 @@
 	int next_barrier_nr;
 	struct hlist_head *app_reads_hash; /* is proteced by req_lock */
 	struct list_head resync_reads;
-	atomic_t pp_in_use;
+	atomic_t pp_in_use;		/* allocated from page pool */
+	atomic_t pp_in_use_by_net;	/* sendpage()d, still referenced by tcp */
 	wait_queue_head_t ee_wait;
 	struct page *md_io_page;	/* one page buffer for md_io */
 	struct page *md_io_tmpp;	/* for logical_block_size != 512 */
@@ -1054,6 +1108,15 @@
 	u64 ed_uuid; /* UUID of the exposed data */
 	struct mutex state_mutex;
 	char congestion_reason;  /* Why we where congested... */
+	atomic_t rs_sect_in; /* for incoming resync data rate, SyncTarget */
+	atomic_t rs_sect_ev; /* for submitted resync data rate, both */
+	int rs_last_sect_ev; /* counter to compare with */
+	int rs_last_events;  /* counter of read or write "events" (unit sectors)
+			      * on the lower level device when we last looked. */
+	int c_sync_rate; /* current resync rate after syncer throttle magic */
+	struct fifo_buffer rs_plan_s; /* correction values of resync planer */
+	int rs_in_flight; /* resync sectors in flight (to proxy, in proxy and from proxy) */
+	int rs_planed;    /* resync sectors already planed */
 };
 
 static inline struct drbd_conf *minor_to_mdev(unsigned int minor)
@@ -1138,6 +1201,8 @@
 extern void tl_release(struct drbd_conf *mdev, unsigned int barrier_nr,
 		       unsigned int set_size);
 extern void tl_clear(struct drbd_conf *mdev);
+enum drbd_req_event;
+extern void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what);
 extern void _tl_add_barrier(struct drbd_conf *, struct drbd_tl_epoch *);
 extern void drbd_free_sock(struct drbd_conf *mdev);
 extern int drbd_send(struct drbd_conf *mdev, struct socket *sock,
@@ -1150,12 +1215,12 @@
 extern int _drbd_send_state(struct drbd_conf *mdev);
 extern int drbd_send_state(struct drbd_conf *mdev);
 extern int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock,
-			enum drbd_packets cmd, struct p_header *h,
+			enum drbd_packets cmd, struct p_header80 *h,
 			size_t size, unsigned msg_flags);
 #define USE_DATA_SOCKET 1
 #define USE_META_SOCKET 0
 extern int drbd_send_cmd(struct drbd_conf *mdev, int use_data_socket,
-			enum drbd_packets cmd, struct p_header *h,
+			enum drbd_packets cmd, struct p_header80 *h,
 			size_t size);
 extern int drbd_send_cmd2(struct drbd_conf *mdev, enum drbd_packets cmd,
 			char *data, size_t size);
@@ -1167,7 +1232,7 @@
 extern int drbd_send_ack_rp(struct drbd_conf *mdev, enum drbd_packets cmd,
 			struct p_block_req *rp);
 extern int drbd_send_ack_dp(struct drbd_conf *mdev, enum drbd_packets cmd,
-			struct p_data *dp);
+			struct p_data *dp, int data_size);
 extern int drbd_send_ack_ex(struct drbd_conf *mdev, enum drbd_packets cmd,
 			    sector_t sector, int blksize, u64 block_id);
 extern int drbd_send_block(struct drbd_conf *mdev, enum drbd_packets cmd,
@@ -1201,7 +1266,13 @@
 extern void drbd_md_set_flag(struct drbd_conf *mdev, int flags) __must_hold(local);
 extern void drbd_md_clear_flag(struct drbd_conf *mdev, int flags)__must_hold(local);
 extern int drbd_md_test_flag(struct drbd_backing_dev *, int);
+#ifndef DRBD_DEBUG_MD_SYNC
 extern void drbd_md_mark_dirty(struct drbd_conf *mdev);
+#else
+#define drbd_md_mark_dirty(m)	drbd_md_mark_dirty_(m, __LINE__ , __func__ )
+extern void drbd_md_mark_dirty_(struct drbd_conf *mdev,
+		unsigned int line, const char *func);
+#endif
 extern void drbd_queue_bitmap_io(struct drbd_conf *mdev,
 				 int (*io_fn)(struct drbd_conf *),
 				 void (*done)(struct drbd_conf *, int),
@@ -1209,6 +1280,7 @@
 extern int drbd_bmio_set_n_write(struct drbd_conf *mdev);
 extern int drbd_bmio_clear_n_write(struct drbd_conf *mdev);
 extern int drbd_bitmap_io(struct drbd_conf *mdev, int (*io_fn)(struct drbd_conf *), char *why);
+extern void drbd_go_diskless(struct drbd_conf *mdev);
 
 
 /* Meta data layout
@@ -1264,6 +1336,8 @@
  * Bit 1 ==> local node thinks this block needs to be synced.
  */
 
+#define SLEEP_TIME (HZ/10)
+
 #define BM_BLOCK_SHIFT  12			 /* 4k per bit */
 #define BM_BLOCK_SIZE	 (1<<BM_BLOCK_SHIFT)
 /* (9+3) : 512 bytes @ 8 bits; representing 16M storage
@@ -1335,11 +1409,13 @@
 #endif
 
 /* Sector shift value for the "hash" functions of tl_hash and ee_hash tables.
- * With a value of 6 all IO in one 32K block make it to the same slot of the
+ * With a value of 8 all IO in one 128K block make it to the same slot of the
  * hash table. */
-#define HT_SHIFT 6
+#define HT_SHIFT 8
 #define DRBD_MAX_SEGMENT_SIZE (1U<<(9+HT_SHIFT))
 
+#define DRBD_MAX_SIZE_H80_PACKET (1 << 15) /* The old header only allows packets up to 32Kib data */
+
 /* Number of elements in the app_reads_hash */
 #define APP_R_HSIZE 15
 
@@ -1369,6 +1445,7 @@
 /* bm_find_next variants for use while you hold drbd_bm_lock() */
 extern unsigned long _drbd_bm_find_next(struct drbd_conf *mdev, unsigned long bm_fo);
 extern unsigned long _drbd_bm_find_next_zero(struct drbd_conf *mdev, unsigned long bm_fo);
+extern unsigned long _drbd_bm_total_weight(struct drbd_conf *mdev);
 extern unsigned long drbd_bm_total_weight(struct drbd_conf *mdev);
 extern int drbd_bm_rs_done(struct drbd_conf *mdev);
 /* for receive_bitmap */
@@ -1421,7 +1498,8 @@
 extern void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int) __must_hold(local);
 extern int drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role,
 		int force);
-enum drbd_disk_state drbd_try_outdate_peer(struct drbd_conf *mdev);
+extern enum drbd_disk_state drbd_try_outdate_peer(struct drbd_conf *mdev);
+extern void drbd_try_outdate_peer_async(struct drbd_conf *mdev);
 extern int drbd_khelper(struct drbd_conf *mdev, char *cmd);
 
 /* drbd_worker.c */
@@ -1467,10 +1545,12 @@
 extern int w_send_read_req(struct drbd_conf *, struct drbd_work *, int);
 extern int w_prev_work_done(struct drbd_conf *, struct drbd_work *, int);
 extern int w_e_reissue(struct drbd_conf *, struct drbd_work *, int);
+extern int w_restart_disk_io(struct drbd_conf *, struct drbd_work *, int);
 
 extern void resync_timer_fn(unsigned long data);
 
 /* drbd_receiver.c */
+extern int drbd_rs_should_slow_down(struct drbd_conf *mdev);
 extern int drbd_submit_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e,
 		const unsigned rw, const int fault_type);
 extern int drbd_release_ee(struct drbd_conf *mdev, struct list_head *list);
@@ -1479,7 +1559,10 @@
 					    sector_t sector,
 					    unsigned int data_size,
 					    gfp_t gfp_mask) __must_hold(local);
-extern void drbd_free_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e);
+extern void drbd_free_some_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e,
+		int is_net);
+#define drbd_free_ee(m,e)	drbd_free_some_ee(m, e, 0)
+#define drbd_free_net_ee(m,e)	drbd_free_some_ee(m, e, 1)
 extern void drbd_wait_ee_list_empty(struct drbd_conf *mdev,
 		struct list_head *head);
 extern void _drbd_wait_ee_list_empty(struct drbd_conf *mdev,
@@ -1487,6 +1570,7 @@
 extern void drbd_set_recv_tcq(struct drbd_conf *mdev, int tcq_enabled);
 extern void _drbd_clear_done_ee(struct drbd_conf *mdev, struct list_head *to_be_freed);
 extern void drbd_flush_workqueue(struct drbd_conf *mdev);
+extern void drbd_free_tl_hash(struct drbd_conf *mdev);
 
 /* yes, there is kernel_setsockopt, but only since 2.6.18. we don't need to
  * mess with get_fs/set_fs, we know we are KERNEL_DS always. */
@@ -1600,6 +1684,8 @@
 #define susp_MASK 1
 #define user_isp_MASK 1
 #define aftr_isp_MASK 1
+#define susp_nod_MASK 1
+#define susp_fen_MASK 1
 
 #define NS(T, S) \
 	({ union drbd_state mask; mask.i = 0; mask.T = T##_MASK; mask; }), \
@@ -1856,13 +1942,6 @@
 }
 
 static inline void
-_drbd_queue_work(struct drbd_work_queue *q, struct drbd_work *w)
-{
-	list_add_tail(&w->list, &q->q);
-	up(&q->s);
-}
-
-static inline void
 drbd_queue_work_front(struct drbd_work_queue *q, struct drbd_work *w)
 {
 	unsigned long flags;
@@ -1899,19 +1978,19 @@
 static inline int drbd_send_short_cmd(struct drbd_conf *mdev,
 	enum drbd_packets cmd)
 {
-	struct p_header h;
+	struct p_header80 h;
 	return drbd_send_cmd(mdev, USE_DATA_SOCKET, cmd, &h, sizeof(h));
 }
 
 static inline int drbd_send_ping(struct drbd_conf *mdev)
 {
-	struct p_header h;
+	struct p_header80 h;
 	return drbd_send_cmd(mdev, USE_META_SOCKET, P_PING, &h, sizeof(h));
 }
 
 static inline int drbd_send_ping_ack(struct drbd_conf *mdev)
 {
-	struct p_header h;
+	struct p_header80 h;
 	return drbd_send_cmd(mdev, USE_META_SOCKET, P_PING_ACK, &h, sizeof(h));
 }
 
@@ -2013,7 +2092,7 @@
 static inline void put_net_conf(struct drbd_conf *mdev)
 {
 	if (atomic_dec_and_test(&mdev->net_cnt))
-		wake_up(&mdev->misc_wait);
+		wake_up(&mdev->net_cnt_wait);
 }
 
 /**
@@ -2044,10 +2123,14 @@
 
 static inline void put_ldev(struct drbd_conf *mdev)
 {
+	int i = atomic_dec_return(&mdev->local_cnt);
 	__release(local);
-	if (atomic_dec_and_test(&mdev->local_cnt))
+	D_ASSERT(i >= 0);
+	if (i == 0) {
+		if (mdev->state.disk == D_FAILED)
+			drbd_go_diskless(mdev);
 		wake_up(&mdev->misc_wait);
-	D_ASSERT(atomic_read(&mdev->local_cnt) >= 0);
+	}
 }
 
 #ifndef __CHECKER__
@@ -2179,11 +2262,16 @@
 	return 1;
 }
 
+static inline int is_susp(union drbd_state s)
+{
+	return s.susp || s.susp_nod || s.susp_fen;
+}
+
 static inline int __inc_ap_bio_cond(struct drbd_conf *mdev)
 {
 	int mxb = drbd_get_max_buffers(mdev);
 
-	if (mdev->state.susp)
+	if (is_susp(mdev->state))
 		return 0;
 	if (test_bit(SUSPEND_IO, &mdev->flags))
 		return 0;
@@ -2321,8 +2409,7 @@
 	if (test_bit(MD_NO_BARRIER, &mdev->flags))
 		return;
 
-	r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL,
-			BLKDEV_IFL_WAIT);
+	r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL);
 	if (r) {
 		set_bit(MD_NO_BARRIER, &mdev->flags);
 		dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index fa650dd..c5dfe64 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -32,7 +32,7 @@
 #include <asm/types.h>
 #include <net/sock.h>
 #include <linux/ctype.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/proc_fs.h>
@@ -64,6 +64,7 @@
 	struct completion *done;
 };
 
+static DEFINE_MUTEX(drbd_main_mutex);
 int drbdd_init(struct drbd_thread *);
 int drbd_worker(struct drbd_thread *);
 int drbd_asender(struct drbd_thread *);
@@ -77,6 +78,7 @@
 static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused);
 static void md_sync_timer_fn(unsigned long data);
 static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused);
+static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused);
 
 MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, "
 	      "Lars Ellenberg <lars@linbit.com>");
@@ -199,7 +201,7 @@
 	INIT_LIST_HEAD(&b->w.list);
 	b->next = NULL;
 	b->br_number = 4711;
-	b->n_req = 0;
+	b->n_writes = 0;
 	b->w.cb = NULL; /* if this is != NULL, we need to dec_ap_pending in tl_clear */
 
 	mdev->oldest_tle = b;
@@ -240,7 +242,7 @@
 	INIT_LIST_HEAD(&new->w.list);
 	new->w.cb = NULL; /* if this is != NULL, we need to dec_ap_pending in tl_clear */
 	new->next = NULL;
-	new->n_req = 0;
+	new->n_writes = 0;
 
 	newest_before = mdev->newest_tle;
 	/* never send a barrier number == 0, because that is special-cased
@@ -284,9 +286,9 @@
 			barrier_nr, b->br_number);
 		goto bail;
 	}
-	if (b->n_req != set_size) {
-		dev_err(DEV, "BAD! BarrierAck #%u received with n_req=%u, expected n_req=%u!\n",
-			barrier_nr, set_size, b->n_req);
+	if (b->n_writes != set_size) {
+		dev_err(DEV, "BAD! BarrierAck #%u received with n_writes=%u, expected n_writes=%u!\n",
+			barrier_nr, set_size, b->n_writes);
 		goto bail;
 	}
 
@@ -333,6 +335,82 @@
 	drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
 }
 
+/**
+ * _tl_restart() - Walks the transfer log, and applies an action to all requests
+ * @mdev:	DRBD device.
+ * @what:       The action/event to perform with all request objects
+ *
+ * @what might be one of connection_lost_while_pending, resend, fail_frozen_disk_io,
+ * restart_frozen_disk_io.
+ */
+static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
+{
+	struct drbd_tl_epoch *b, *tmp, **pn;
+	struct list_head *le, *tle, carry_reads;
+	struct drbd_request *req;
+	int rv, n_writes, n_reads;
+
+	b = mdev->oldest_tle;
+	pn = &mdev->oldest_tle;
+	while (b) {
+		n_writes = 0;
+		n_reads = 0;
+		INIT_LIST_HEAD(&carry_reads);
+		list_for_each_safe(le, tle, &b->requests) {
+			req = list_entry(le, struct drbd_request, tl_requests);
+			rv = _req_mod(req, what);
+
+			n_writes += (rv & MR_WRITE) >> MR_WRITE_SHIFT;
+			n_reads  += (rv & MR_READ) >> MR_READ_SHIFT;
+		}
+		tmp = b->next;
+
+		if (n_writes) {
+			if (what == resend) {
+				b->n_writes = n_writes;
+				if (b->w.cb == NULL) {
+					b->w.cb = w_send_barrier;
+					inc_ap_pending(mdev);
+					set_bit(CREATE_BARRIER, &mdev->flags);
+				}
+
+				drbd_queue_work(&mdev->data.work, &b->w);
+			}
+			pn = &b->next;
+		} else {
+			if (n_reads)
+				list_add(&carry_reads, &b->requests);
+			/* there could still be requests on that ring list,
+			 * in case local io is still pending */
+			list_del(&b->requests);
+
+			/* dec_ap_pending corresponding to queue_barrier.
+			 * the newest barrier may not have been queued yet,
+			 * in which case w.cb is still NULL. */
+			if (b->w.cb != NULL)
+				dec_ap_pending(mdev);
+
+			if (b == mdev->newest_tle) {
+				/* recycle, but reinit! */
+				D_ASSERT(tmp == NULL);
+				INIT_LIST_HEAD(&b->requests);
+				list_splice(&carry_reads, &b->requests);
+				INIT_LIST_HEAD(&b->w.list);
+				b->w.cb = NULL;
+				b->br_number = net_random();
+				b->n_writes = 0;
+
+				*pn = b;
+				break;
+			}
+			*pn = tmp;
+			kfree(b);
+		}
+		b = tmp;
+		list_splice(&carry_reads, &b->requests);
+	}
+}
+
 
 /**
  * tl_clear() - Clears all requests and &struct drbd_tl_epoch objects out of the TL
@@ -344,48 +422,12 @@
  */
 void tl_clear(struct drbd_conf *mdev)
 {
-	struct drbd_tl_epoch *b, *tmp;
 	struct list_head *le, *tle;
 	struct drbd_request *r;
-	int new_initial_bnr = net_random();
 
 	spin_lock_irq(&mdev->req_lock);
 
-	b = mdev->oldest_tle;
-	while (b) {
-		list_for_each_safe(le, tle, &b->requests) {
-			r = list_entry(le, struct drbd_request, tl_requests);
-			/* It would be nice to complete outside of spinlock.
-			 * But this is easier for now. */
-			_req_mod(r, connection_lost_while_pending);
-		}
-		tmp = b->next;
-
-		/* there could still be requests on that ring list,
-		 * in case local io is still pending */
-		list_del(&b->requests);
-
-		/* dec_ap_pending corresponding to queue_barrier.
-		 * the newest barrier may not have been queued yet,
-		 * in which case w.cb is still NULL. */
-		if (b->w.cb != NULL)
-			dec_ap_pending(mdev);
-
-		if (b == mdev->newest_tle) {
-			/* recycle, but reinit! */
-			D_ASSERT(tmp == NULL);
-			INIT_LIST_HEAD(&b->requests);
-			INIT_LIST_HEAD(&b->w.list);
-			b->w.cb = NULL;
-			b->br_number = new_initial_bnr;
-			b->n_req = 0;
-
-			mdev->oldest_tle = b;
-			break;
-		}
-		kfree(b);
-		b = tmp;
-	}
+	_tl_restart(mdev, connection_lost_while_pending);
 
 	/* we expect this list to be empty. */
 	D_ASSERT(list_empty(&mdev->out_of_sequence_requests));
@@ -401,6 +443,15 @@
 	/* ensure bit indicating barrier is required is clear */
 	clear_bit(CREATE_BARRIER, &mdev->flags);
 
+	memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *));
+
+	spin_unlock_irq(&mdev->req_lock);
+}
+
+void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
+{
+	spin_lock_irq(&mdev->req_lock);
+	_tl_restart(mdev, what);
 	spin_unlock_irq(&mdev->req_lock);
 }
 
@@ -455,7 +506,7 @@
 static int is_valid_state_transition(struct drbd_conf *,
 				     union drbd_state, union drbd_state);
 static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state os,
-				       union drbd_state ns, int *warn_sync_abort);
+				       union drbd_state ns, const char **warn_sync_abort);
 int drbd_send_state_req(struct drbd_conf *,
 			union drbd_state, union drbd_state);
 
@@ -605,7 +656,7 @@
 	    drbd_role_str(ns.peer),
 	    drbd_disk_str(ns.disk),
 	    drbd_disk_str(ns.pdsk),
-	    ns.susp ? 's' : 'r',
+	    is_susp(ns) ? 's' : 'r',
 	    ns.aftr_isp ? 'a' : '-',
 	    ns.peer_isp ? 'p' : '-',
 	    ns.user_isp ? 'u' : '-'
@@ -763,7 +814,7 @@
  * to D_UNKNOWN. This rule and many more along those lines are in this function.
  */
 static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state os,
-				       union drbd_state ns, int *warn_sync_abort)
+				       union drbd_state ns, const char **warn_sync_abort)
 {
 	enum drbd_fencing_p fp;
 
@@ -778,9 +829,10 @@
 	    os.conn <= C_DISCONNECTING)
 		ns.conn = os.conn;
 
-	/* After a network error (+C_TEAR_DOWN) only C_UNCONNECTED or C_DISCONNECTING can follow */
+	/* After a network error (+C_TEAR_DOWN) only C_UNCONNECTED or C_DISCONNECTING can follow.
+	 * If you try to go into some Sync* state, that shall fail (elsewhere). */
 	if (os.conn >= C_TIMEOUT && os.conn <= C_TEAR_DOWN &&
-	    ns.conn != C_UNCONNECTED && ns.conn != C_DISCONNECTING)
+	    ns.conn != C_UNCONNECTED && ns.conn != C_DISCONNECTING && ns.conn <= C_TEAR_DOWN)
 		ns.conn = os.conn;
 
 	/* After C_DISCONNECTING only C_STANDALONE may follow */
@@ -798,14 +850,13 @@
 	if (ns.conn == C_STANDALONE && ns.disk == D_DISKLESS && ns.role == R_SECONDARY)
 		ns.aftr_isp = 0;
 
-	if (ns.conn <= C_DISCONNECTING && ns.disk == D_DISKLESS)
-		ns.pdsk = D_UNKNOWN;
-
 	/* Abort resync if a disk fails/detaches */
 	if (os.conn > C_CONNECTED && ns.conn > C_CONNECTED &&
 	    (ns.disk <= D_FAILED || ns.pdsk <= D_FAILED)) {
 		if (warn_sync_abort)
-			*warn_sync_abort = 1;
+			*warn_sync_abort =
+				os.conn == C_VERIFY_S || os.conn == C_VERIFY_T ?
+				"Online-verify" : "Resync";
 		ns.conn = C_CONNECTED;
 	}
 
@@ -876,7 +927,12 @@
 	if (fp == FP_STONITH &&
 	    (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk > D_OUTDATED) &&
 	    !(os.role == R_PRIMARY && os.conn < C_CONNECTED && os.pdsk > D_OUTDATED))
-		ns.susp = 1;
+		ns.susp_fen = 1; /* Suspend IO while fence-peer handler runs (peer lost) */
+
+	if (mdev->sync_conf.on_no_data == OND_SUSPEND_IO &&
+	    (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE) &&
+	    !(os.role == R_PRIMARY && os.disk < D_UP_TO_DATE && os.pdsk < D_UP_TO_DATE))
+		ns.susp_nod = 1; /* Suspend IO while no data available (no accessible data available) */
 
 	if (ns.aftr_isp || ns.peer_isp || ns.user_isp) {
 		if (ns.conn == C_SYNC_SOURCE)
@@ -912,6 +968,12 @@
 	}
 }
 
+static void drbd_resume_al(struct drbd_conf *mdev)
+{
+	if (test_and_clear_bit(AL_SUSPENDED, &mdev->flags))
+		dev_info(DEV, "Resumed AL updates\n");
+}
+
 /**
  * __drbd_set_state() - Set a new DRBD state
  * @mdev:	DRBD device.
@@ -927,7 +989,7 @@
 {
 	union drbd_state os;
 	int rv = SS_SUCCESS;
-	int warn_sync_abort = 0;
+	const char *warn_sync_abort = NULL;
 	struct after_state_chg_work *ascw;
 
 	os = mdev->state;
@@ -946,14 +1008,8 @@
 			/* If the old state was illegal as well, then let
 			   this happen...*/
 
-			if (is_valid_state(mdev, os) == rv) {
-				dev_err(DEV, "Considering state change from bad state. "
-				    "Error would be: '%s'\n",
-				    drbd_set_st_err_str(rv));
-				print_st(mdev, "old", os);
-				print_st(mdev, "new", ns);
+			if (is_valid_state(mdev, os) == rv)
 				rv = is_valid_state_transition(mdev, ns, os);
-			}
 		} else
 			rv = is_valid_state_transition(mdev, ns, os);
 	}
@@ -965,7 +1021,7 @@
 	}
 
 	if (warn_sync_abort)
-		dev_warn(DEV, "Resync aborted.\n");
+		dev_warn(DEV, "%s aborted.\n", warn_sync_abort);
 
 	{
 		char *pbp, pb[300];
@@ -976,7 +1032,10 @@
 		PSC(conn);
 		PSC(disk);
 		PSC(pdsk);
-		PSC(susp);
+		if (is_susp(ns) != is_susp(os))
+			pbp += sprintf(pbp, "susp( %s -> %s ) ",
+				       drbd_susp_str(is_susp(os)),
+				       drbd_susp_str(is_susp(ns)));
 		PSC(aftr_isp);
 		PSC(peer_isp);
 		PSC(user_isp);
@@ -1001,12 +1060,6 @@
 	wake_up(&mdev->misc_wait);
 	wake_up(&mdev->state_wait);
 
-	/*   post-state-change actions   */
-	if (os.conn >= C_SYNC_SOURCE   && ns.conn <= C_CONNECTED) {
-		set_bit(STOP_SYNC_TIMER, &mdev->flags);
-		mod_timer(&mdev->resync_timer, jiffies);
-	}
-
 	/* aborted verify run. log the last position */
 	if ((os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) &&
 	    ns.conn < C_CONNECTED) {
@@ -1019,41 +1072,42 @@
 	if ((os.conn == C_PAUSED_SYNC_T || os.conn == C_PAUSED_SYNC_S) &&
 	    (ns.conn == C_SYNC_TARGET  || ns.conn == C_SYNC_SOURCE)) {
 		dev_info(DEV, "Syncer continues.\n");
-		mdev->rs_paused += (long)jiffies-(long)mdev->rs_mark_time;
-		if (ns.conn == C_SYNC_TARGET) {
-			if (!test_and_clear_bit(STOP_SYNC_TIMER, &mdev->flags))
-				mod_timer(&mdev->resync_timer, jiffies);
-			/* This if (!test_bit) is only needed for the case
-			   that a device that has ceased to used its timer,
-			   i.e. it is already in drbd_resync_finished() gets
-			   paused and resumed. */
-		}
+		mdev->rs_paused += (long)jiffies
+				  -(long)mdev->rs_mark_time[mdev->rs_last_mark];
+		if (ns.conn == C_SYNC_TARGET)
+			mod_timer(&mdev->resync_timer, jiffies);
 	}
 
 	if ((os.conn == C_SYNC_TARGET  || os.conn == C_SYNC_SOURCE) &&
 	    (ns.conn == C_PAUSED_SYNC_T || ns.conn == C_PAUSED_SYNC_S)) {
 		dev_info(DEV, "Resync suspended\n");
-		mdev->rs_mark_time = jiffies;
-		if (ns.conn == C_PAUSED_SYNC_T)
-			set_bit(STOP_SYNC_TIMER, &mdev->flags);
+		mdev->rs_mark_time[mdev->rs_last_mark] = jiffies;
 	}
 
 	if (os.conn == C_CONNECTED &&
 	    (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T)) {
+		unsigned long now = jiffies;
+		int i;
+
 		mdev->ov_position = 0;
-		mdev->rs_total =
-		mdev->rs_mark_left = drbd_bm_bits(mdev);
+		mdev->rs_total = drbd_bm_bits(mdev);
 		if (mdev->agreed_pro_version >= 90)
 			set_ov_position(mdev, ns.conn);
 		else
 			mdev->ov_start_sector = 0;
 		mdev->ov_left = mdev->rs_total
 			      - BM_SECT_TO_BIT(mdev->ov_position);
-		mdev->rs_start     =
-		mdev->rs_mark_time = jiffies;
+		mdev->rs_start = now;
+		mdev->rs_last_events = 0;
+		mdev->rs_last_sect_ev = 0;
 		mdev->ov_last_oos_size = 0;
 		mdev->ov_last_oos_start = 0;
 
+		for (i = 0; i < DRBD_SYNC_MARKS; i++) {
+			mdev->rs_mark_left[i] = mdev->rs_total;
+			mdev->rs_mark_time[i] = now;
+		}
+
 		if (ns.conn == C_VERIFY_S) {
 			dev_info(DEV, "Starting Online Verify from sector %llu\n",
 					(unsigned long long)mdev->ov_position);
@@ -1106,6 +1160,10 @@
 	    ns.conn <= C_TEAR_DOWN && ns.conn >= C_TIMEOUT)
 		drbd_thread_restart_nowait(&mdev->receiver);
 
+	/* Resume AL writing if we get a connection */
+	if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED)
+		drbd_resume_al(mdev);
+
 	ascw = kmalloc(sizeof(*ascw), GFP_ATOMIC);
 	if (ascw) {
 		ascw->os = os;
@@ -1164,6 +1222,8 @@
 			   union drbd_state ns, enum chg_state_flags flags)
 {
 	enum drbd_fencing_p fp;
+	enum drbd_req_event what = nothing;
+	union drbd_state nsm = (union drbd_state){ .i = -1 };
 
 	if (os.conn != C_CONNECTED && ns.conn == C_CONNECTED) {
 		clear_bit(CRASHED_PRIMARY, &mdev->flags);
@@ -1187,17 +1247,49 @@
 	/* Here we have the actions that are performed after a
 	   state change. This function might sleep */
 
-	if (fp == FP_STONITH && ns.susp) {
-		/* case1: The outdate peer handler is successful:
-		 * case2: The connection was established again: */
-		if ((os.pdsk > D_OUTDATED  && ns.pdsk <= D_OUTDATED) ||
-		    (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED)) {
+	nsm.i = -1;
+	if (ns.susp_nod) {
+		if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED) {
+			if (ns.conn == C_CONNECTED)
+				what = resend, nsm.susp_nod = 0;
+			else /* ns.conn > C_CONNECTED */
+				dev_err(DEV, "Unexpected Resynd going on!\n");
+		}
+
+		if (os.disk == D_ATTACHING && ns.disk > D_ATTACHING)
+			what = restart_frozen_disk_io, nsm.susp_nod = 0;
+
+	}
+
+	if (ns.susp_fen) {
+		/* case1: The outdate peer handler is successful: */
+		if (os.pdsk > D_OUTDATED  && ns.pdsk <= D_OUTDATED) {
 			tl_clear(mdev);
+			if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
+				drbd_uuid_new_current(mdev);
+				clear_bit(NEW_CUR_UUID, &mdev->flags);
+				drbd_md_sync(mdev);
+			}
 			spin_lock_irq(&mdev->req_lock);
-			_drbd_set_state(_NS(mdev, susp, 0), CS_VERBOSE, NULL);
+			_drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL);
 			spin_unlock_irq(&mdev->req_lock);
 		}
+		/* case2: The connection was established again: */
+		if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED) {
+			clear_bit(NEW_CUR_UUID, &mdev->flags);
+			what = resend;
+			nsm.susp_fen = 0;
+		}
 	}
+
+	if (what != nothing) {
+		spin_lock_irq(&mdev->req_lock);
+		_tl_restart(mdev, what);
+		nsm.i &= mdev->state.i;
+		_drbd_set_state(mdev, nsm, CS_VERBOSE, NULL);
+		spin_unlock_irq(&mdev->req_lock);
+	}
+
 	/* Do not change the order of the if above and the two below... */
 	if (os.pdsk == D_DISKLESS && ns.pdsk > D_DISKLESS) {      /* attach on the peer */
 		drbd_send_uuids(mdev);
@@ -1216,16 +1308,22 @@
 		if (get_ldev(mdev)) {
 			if ((ns.role == R_PRIMARY || ns.peer == R_PRIMARY) &&
 			    mdev->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) {
-				drbd_uuid_new_current(mdev);
-				drbd_send_uuids(mdev);
+				if (is_susp(mdev->state)) {
+					set_bit(NEW_CUR_UUID, &mdev->flags);
+				} else {
+					drbd_uuid_new_current(mdev);
+					drbd_send_uuids(mdev);
+				}
 			}
 			put_ldev(mdev);
 		}
 	}
 
 	if (ns.pdsk < D_INCONSISTENT && get_ldev(mdev)) {
-		if (ns.peer == R_PRIMARY && mdev->ldev->md.uuid[UI_BITMAP] == 0)
+		if (ns.peer == R_PRIMARY && mdev->ldev->md.uuid[UI_BITMAP] == 0) {
 			drbd_uuid_new_current(mdev);
+			drbd_send_uuids(mdev);
+		}
 
 		/* D_DISKLESS Peer becomes secondary */
 		if (os.peer == R_PRIMARY && ns.peer == R_SECONDARY)
@@ -1267,42 +1365,51 @@
 	    os.disk > D_INCONSISTENT && ns.disk == D_INCONSISTENT)
 		drbd_queue_bitmap_io(mdev, &drbd_bmio_set_n_write, NULL, "set_n_write from invalidate");
 
+	/* first half of local IO error */
 	if (os.disk > D_FAILED && ns.disk == D_FAILED) {
-		enum drbd_io_error_p eh;
+		enum drbd_io_error_p eh = EP_PASS_ON;
 
-		eh = EP_PASS_ON;
+		if (drbd_send_state(mdev))
+			dev_warn(DEV, "Notified peer that my disk is broken.\n");
+		else
+			dev_err(DEV, "Sending state for drbd_io_error() failed\n");
+
+		drbd_rs_cancel_all(mdev);
+
 		if (get_ldev_if_state(mdev, D_FAILED)) {
 			eh = mdev->ldev->dc.on_io_error;
 			put_ldev(mdev);
 		}
-
-		drbd_rs_cancel_all(mdev);
-		/* since get_ldev() only works as long as disk>=D_INCONSISTENT,
-		   and it is D_DISKLESS here, local_cnt can only go down, it can
-		   not increase... It will reach zero */
-		wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
-		mdev->rs_total = 0;
-		mdev->rs_failed = 0;
-		atomic_set(&mdev->rs_pending_cnt, 0);
-
-		spin_lock_irq(&mdev->req_lock);
-		_drbd_set_state(_NS(mdev, disk, D_DISKLESS), CS_HARD, NULL);
-		spin_unlock_irq(&mdev->req_lock);
-
 		if (eh == EP_CALL_HELPER)
 			drbd_khelper(mdev, "local-io-error");
 	}
 
+
+	/* second half of local IO error handling,
+	 * after local_cnt references have reached zero: */
+	if (os.disk == D_FAILED && ns.disk == D_DISKLESS) {
+		mdev->rs_total = 0;
+		mdev->rs_failed = 0;
+		atomic_set(&mdev->rs_pending_cnt, 0);
+	}
+
 	if (os.disk > D_DISKLESS && ns.disk == D_DISKLESS) {
+		/* We must still be diskless,
+		 * re-attach has to be serialized with this! */
+		if (mdev->state.disk != D_DISKLESS)
+			dev_err(DEV,
+				"ASSERT FAILED: disk is %s while going diskless\n",
+				drbd_disk_str(mdev->state.disk));
 
-		if (os.disk == D_FAILED) /* && ns.disk == D_DISKLESS*/ {
-			if (drbd_send_state(mdev))
-				dev_warn(DEV, "Notified peer that my disk is broken.\n");
-			else
-				dev_err(DEV, "Sending state in drbd_io_error() failed\n");
-		}
+		/* we cannot assert local_cnt == 0 here, as get_ldev_if_state
+		 * will inc/dec it frequently. Since we became D_DISKLESS, no
+		 * one has touched the protected members anymore, though, so we
+		 * are safe to free them here. */
+		if (drbd_send_state(mdev))
+			dev_warn(DEV, "Notified peer that I detached my disk.\n");
+		else
+			dev_err(DEV, "Sending state for detach failed\n");
 
-		wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
 		lc_destroy(mdev->resync);
 		mdev->resync = NULL;
 		lc_destroy(mdev->act_log);
@@ -1311,8 +1418,10 @@
 			drbd_free_bc(mdev->ldev);
 			mdev->ldev = NULL;);
 
-		if (mdev->md_io_tmpp)
+		if (mdev->md_io_tmpp) {
 			__free_page(mdev->md_io_tmpp);
+			mdev->md_io_tmpp = NULL;
+		}
 	}
 
 	/* Disks got bigger while they were detached */
@@ -1328,6 +1437,15 @@
 	    (os.user_isp && !ns.user_isp))
 		resume_next_sg(mdev);
 
+	/* sync target done with resync.  Explicitly notify peer, even though
+	 * it should (at least for non-empty resyncs) already know itself. */
+	if (os.disk < D_UP_TO_DATE && os.conn >= C_SYNC_SOURCE && ns.conn == C_CONNECTED)
+		drbd_send_state(mdev);
+
+	/* free tl_hash if we Got thawed and are C_STANDALONE */
+	if (ns.conn == C_STANDALONE && !is_susp(ns) && mdev->tl_hash)
+		drbd_free_tl_hash(mdev);
+
 	/* Upon network connection, we need to start the receiver */
 	if (os.conn == C_STANDALONE && ns.conn == C_UNCONNECTED)
 		drbd_thread_start(&mdev->receiver);
@@ -1554,7 +1672,7 @@
 
 /* the appropriate socket mutex must be held already */
 int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock,
-			  enum drbd_packets cmd, struct p_header *h,
+			  enum drbd_packets cmd, struct p_header80 *h,
 			  size_t size, unsigned msg_flags)
 {
 	int sent, ok;
@@ -1564,7 +1682,7 @@
 
 	h->magic   = BE_DRBD_MAGIC;
 	h->command = cpu_to_be16(cmd);
-	h->length  = cpu_to_be16(size-sizeof(struct p_header));
+	h->length  = cpu_to_be16(size-sizeof(struct p_header80));
 
 	sent = drbd_send(mdev, sock, h, size, msg_flags);
 
@@ -1579,7 +1697,7 @@
  * when we hold the appropriate socket mutex.
  */
 int drbd_send_cmd(struct drbd_conf *mdev, int use_data_socket,
-		  enum drbd_packets cmd, struct p_header *h, size_t size)
+		  enum drbd_packets cmd, struct p_header80 *h, size_t size)
 {
 	int ok = 0;
 	struct socket *sock;
@@ -1607,7 +1725,7 @@
 int drbd_send_cmd2(struct drbd_conf *mdev, enum drbd_packets cmd, char *data,
 		   size_t size)
 {
-	struct p_header h;
+	struct p_header80 h;
 	int ok;
 
 	h.magic   = BE_DRBD_MAGIC;
@@ -1629,7 +1747,7 @@
 
 int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc)
 {
-	struct p_rs_param_89 *p;
+	struct p_rs_param_95 *p;
 	struct socket *sock;
 	int size, rv;
 	const int apv = mdev->agreed_pro_version;
@@ -1637,7 +1755,8 @@
 	size = apv <= 87 ? sizeof(struct p_rs_param)
 		: apv == 88 ? sizeof(struct p_rs_param)
 			+ strlen(mdev->sync_conf.verify_alg) + 1
-		: /* 89 */    sizeof(struct p_rs_param_89);
+		: apv <= 94 ? sizeof(struct p_rs_param_89)
+		: /* apv >= 95 */ sizeof(struct p_rs_param_95);
 
 	/* used from admin command context and receiver/worker context.
 	 * to avoid kmalloc, grab the socket right here,
@@ -1648,12 +1767,16 @@
 	if (likely(sock != NULL)) {
 		enum drbd_packets cmd = apv >= 89 ? P_SYNC_PARAM89 : P_SYNC_PARAM;
 
-		p = &mdev->data.sbuf.rs_param_89;
+		p = &mdev->data.sbuf.rs_param_95;
 
 		/* initialize verify_alg and csums_alg */
 		memset(p->verify_alg, 0, 2 * SHARED_SECRET_MAX);
 
 		p->rate = cpu_to_be32(sc->rate);
+		p->c_plan_ahead = cpu_to_be32(sc->c_plan_ahead);
+		p->c_delay_target = cpu_to_be32(sc->c_delay_target);
+		p->c_fill_target = cpu_to_be32(sc->c_fill_target);
+		p->c_max_rate = cpu_to_be32(sc->c_max_rate);
 
 		if (apv >= 88)
 			strcpy(p->verify_alg, mdev->sync_conf.verify_alg);
@@ -1709,7 +1832,7 @@
 		strcpy(p->integrity_alg, mdev->net_conf->integrity_alg);
 
 	rv = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_PROTOCOL,
-			   (struct p_header *)p, size);
+			   (struct p_header80 *)p, size);
 	kfree(p);
 	return rv;
 }
@@ -1735,7 +1858,7 @@
 	put_ldev(mdev);
 
 	return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_UUIDS,
-			     (struct p_header *)&p, sizeof(p));
+			     (struct p_header80 *)&p, sizeof(p));
 }
 
 int drbd_send_uuids(struct drbd_conf *mdev)
@@ -1756,7 +1879,7 @@
 	p.uuid = cpu_to_be64(val);
 
 	return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SYNC_UUID,
-			     (struct p_header *)&p, sizeof(p));
+			     (struct p_header80 *)&p, sizeof(p));
 }
 
 int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags flags)
@@ -1786,7 +1909,7 @@
 	p.dds_flags = cpu_to_be16(flags);
 
 	ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SIZES,
-			   (struct p_header *)&p, sizeof(p));
+			   (struct p_header80 *)&p, sizeof(p));
 	return ok;
 }
 
@@ -1811,7 +1934,7 @@
 
 	if (likely(sock != NULL)) {
 		ok = _drbd_send_cmd(mdev, sock, P_STATE,
-				    (struct p_header *)&p, sizeof(p), 0);
+				    (struct p_header80 *)&p, sizeof(p), 0);
 	}
 
 	mutex_unlock(&mdev->data.mutex);
@@ -1829,7 +1952,7 @@
 	p.val     = cpu_to_be32(val.i);
 
 	return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_STATE_CHG_REQ,
-			     (struct p_header *)&p, sizeof(p));
+			     (struct p_header80 *)&p, sizeof(p));
 }
 
 int drbd_send_sr_reply(struct drbd_conf *mdev, int retcode)
@@ -1839,7 +1962,7 @@
 	p.retcode    = cpu_to_be32(retcode);
 
 	return drbd_send_cmd(mdev, USE_META_SOCKET, P_STATE_CHG_REPLY,
-			     (struct p_header *)&p, sizeof(p));
+			     (struct p_header80 *)&p, sizeof(p));
 }
 
 int fill_bitmap_rle_bits(struct drbd_conf *mdev,
@@ -1938,7 +2061,7 @@
 
 enum { OK, FAILED, DONE }
 send_bitmap_rle_or_plain(struct drbd_conf *mdev,
-	struct p_header *h, struct bm_xfer_ctx *c)
+	struct p_header80 *h, struct bm_xfer_ctx *c)
 {
 	struct p_compressed_bm *p = (void*)h;
 	unsigned long num_words;
@@ -1968,12 +2091,12 @@
 		if (len)
 			drbd_bm_get_lel(mdev, c->word_offset, num_words, (unsigned long*)h->payload);
 		ok = _drbd_send_cmd(mdev, mdev->data.socket, P_BITMAP,
-				   h, sizeof(struct p_header) + len, 0);
+				   h, sizeof(struct p_header80) + len, 0);
 		c->word_offset += num_words;
 		c->bit_offset = c->word_offset * BITS_PER_LONG;
 
 		c->packets[1]++;
-		c->bytes[1] += sizeof(struct p_header) + len;
+		c->bytes[1] += sizeof(struct p_header80) + len;
 
 		if (c->bit_offset > c->bm_bits)
 			c->bit_offset = c->bm_bits;
@@ -1989,14 +2112,14 @@
 int _drbd_send_bitmap(struct drbd_conf *mdev)
 {
 	struct bm_xfer_ctx c;
-	struct p_header *p;
+	struct p_header80 *p;
 	int ret;
 
 	ERR_IF(!mdev->bitmap) return FALSE;
 
 	/* maybe we should use some per thread scratch page,
 	 * and allocate that during initial device creation? */
-	p = (struct p_header *) __get_free_page(GFP_NOIO);
+	p = (struct p_header80 *) __get_free_page(GFP_NOIO);
 	if (!p) {
 		dev_err(DEV, "failed to allocate one page buffer in %s\n", __func__);
 		return FALSE;
@@ -2054,7 +2177,7 @@
 	if (mdev->state.conn < C_CONNECTED)
 		return FALSE;
 	ok = drbd_send_cmd(mdev, USE_META_SOCKET, P_BARRIER_ACK,
-			(struct p_header *)&p, sizeof(p));
+			(struct p_header80 *)&p, sizeof(p));
 	return ok;
 }
 
@@ -2082,17 +2205,18 @@
 	if (!mdev->meta.socket || mdev->state.conn < C_CONNECTED)
 		return FALSE;
 	ok = drbd_send_cmd(mdev, USE_META_SOCKET, cmd,
-				(struct p_header *)&p, sizeof(p));
+				(struct p_header80 *)&p, sizeof(p));
 	return ok;
 }
 
+/* dp->sector and dp->block_id already/still in network byte order,
+ * data_size is payload size according to dp->head,
+ * and may need to be corrected for digest size. */
 int drbd_send_ack_dp(struct drbd_conf *mdev, enum drbd_packets cmd,
-		     struct p_data *dp)
+		     struct p_data *dp, int data_size)
 {
-	const int header_size = sizeof(struct p_data)
-			      - sizeof(struct p_header);
-	int data_size  = ((struct p_header *)dp)->length - header_size;
-
+	data_size -= (mdev->agreed_pro_version >= 87 && mdev->integrity_r_tfm) ?
+		crypto_hash_digestsize(mdev->integrity_r_tfm) : 0;
 	return _drbd_send_ack(mdev, cmd, dp->sector, cpu_to_be32(data_size),
 			      dp->block_id);
 }
@@ -2140,7 +2264,7 @@
 	p.blksize  = cpu_to_be32(size);
 
 	ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, cmd,
-				(struct p_header *)&p, sizeof(p));
+				(struct p_header80 *)&p, sizeof(p));
 	return ok;
 }
 
@@ -2158,7 +2282,7 @@
 
 	p.head.magic   = BE_DRBD_MAGIC;
 	p.head.command = cpu_to_be16(cmd);
-	p.head.length  = cpu_to_be16(sizeof(p) - sizeof(struct p_header) + digest_size);
+	p.head.length  = cpu_to_be16(sizeof(p) - sizeof(struct p_header80) + digest_size);
 
 	mutex_lock(&mdev->data.mutex);
 
@@ -2180,7 +2304,7 @@
 	p.blksize  = cpu_to_be32(size);
 
 	ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_OV_REQUEST,
-			   (struct p_header *)&p, sizeof(p));
+			   (struct p_header80 *)&p, sizeof(p));
 	return ok;
 }
 
@@ -2332,6 +2456,18 @@
 	return 1;
 }
 
+static u32 bio_flags_to_wire(struct drbd_conf *mdev, unsigned long bi_rw)
+{
+	if (mdev->agreed_pro_version >= 95)
+		return  (bi_rw & REQ_SYNC ? DP_RW_SYNC : 0) |
+			(bi_rw & REQ_UNPLUG ? DP_UNPLUG : 0) |
+			(bi_rw & REQ_FUA ? DP_FUA : 0) |
+			(bi_rw & REQ_FLUSH ? DP_FLUSH : 0) |
+			(bi_rw & REQ_DISCARD ? DP_DISCARD : 0);
+	else
+		return bi_rw & (REQ_SYNC | REQ_UNPLUG) ? DP_RW_SYNC : 0;
+}
+
 /* Used to send write requests
  * R_PRIMARY -> Peer	(P_DATA)
  */
@@ -2349,30 +2485,25 @@
 	dgs = (mdev->agreed_pro_version >= 87 && mdev->integrity_w_tfm) ?
 		crypto_hash_digestsize(mdev->integrity_w_tfm) : 0;
 
-	p.head.magic   = BE_DRBD_MAGIC;
-	p.head.command = cpu_to_be16(P_DATA);
-	p.head.length  =
-		cpu_to_be16(sizeof(p) - sizeof(struct p_header) + dgs + req->size);
+	if (req->size <= DRBD_MAX_SIZE_H80_PACKET) {
+		p.head.h80.magic   = BE_DRBD_MAGIC;
+		p.head.h80.command = cpu_to_be16(P_DATA);
+		p.head.h80.length  =
+			cpu_to_be16(sizeof(p) - sizeof(union p_header) + dgs + req->size);
+	} else {
+		p.head.h95.magic   = BE_DRBD_MAGIC_BIG;
+		p.head.h95.command = cpu_to_be16(P_DATA);
+		p.head.h95.length  =
+			cpu_to_be32(sizeof(p) - sizeof(union p_header) + dgs + req->size);
+	}
 
 	p.sector   = cpu_to_be64(req->sector);
 	p.block_id = (unsigned long)req;
 	p.seq_num  = cpu_to_be32(req->seq_num =
 				 atomic_add_return(1, &mdev->packet_seq));
-	dp_flags = 0;
 
-	/* NOTE: no need to check if barriers supported here as we would
-	 *       not pass the test in make_request_common in that case
-	 */
-	if (req->master_bio->bi_rw & REQ_HARDBARRIER) {
-		dev_err(DEV, "ASSERT FAILED would have set DP_HARDBARRIER\n");
-		/* dp_flags |= DP_HARDBARRIER; */
-	}
-	if (req->master_bio->bi_rw & REQ_SYNC)
-		dp_flags |= DP_RW_SYNC;
-	/* for now handle SYNCIO and UNPLUG
-	 * as if they still were one and the same flag */
-	if (req->master_bio->bi_rw & REQ_UNPLUG)
-		dp_flags |= DP_RW_SYNC;
+	dp_flags = bio_flags_to_wire(mdev, req->master_bio->bi_rw);
+
 	if (mdev->state.conn >= C_SYNC_SOURCE &&
 	    mdev->state.conn <= C_PAUSED_SYNC_T)
 		dp_flags |= DP_MAY_SET_IN_SYNC;
@@ -2413,10 +2544,17 @@
 	dgs = (mdev->agreed_pro_version >= 87 && mdev->integrity_w_tfm) ?
 		crypto_hash_digestsize(mdev->integrity_w_tfm) : 0;
 
-	p.head.magic   = BE_DRBD_MAGIC;
-	p.head.command = cpu_to_be16(cmd);
-	p.head.length  =
-		cpu_to_be16(sizeof(p) - sizeof(struct p_header) + dgs + e->size);
+	if (e->size <= DRBD_MAX_SIZE_H80_PACKET) {
+		p.head.h80.magic   = BE_DRBD_MAGIC;
+		p.head.h80.command = cpu_to_be16(cmd);
+		p.head.h80.length  =
+			cpu_to_be16(sizeof(p) - sizeof(struct p_header80) + dgs + e->size);
+	} else {
+		p.head.h95.magic   = BE_DRBD_MAGIC_BIG;
+		p.head.h95.command = cpu_to_be16(cmd);
+		p.head.h95.length  =
+			cpu_to_be32(sizeof(p) - sizeof(struct p_header80) + dgs + e->size);
+	}
 
 	p.sector   = cpu_to_be64(e->sector);
 	p.block_id = e->block_id;
@@ -2429,8 +2567,7 @@
 	if (!drbd_get_data_sock(mdev))
 		return 0;
 
-	ok = sizeof(p) == drbd_send(mdev, mdev->data.socket, &p,
-					sizeof(p), dgs ? MSG_MORE : 0);
+	ok = sizeof(p) == drbd_send(mdev, mdev->data.socket, &p, sizeof(p), dgs ? MSG_MORE : 0);
 	if (ok && dgs) {
 		dgb = mdev->int_dig_out;
 		drbd_csum_ee(mdev, mdev->integrity_w_tfm, e, dgb);
@@ -2536,7 +2673,7 @@
 	unsigned long flags;
 	int rv = 0;
 
-	lock_kernel();
+	mutex_lock(&drbd_main_mutex);
 	spin_lock_irqsave(&mdev->req_lock, flags);
 	/* to have a stable mdev->state.role
 	 * and no race with updating open_cnt */
@@ -2551,7 +2688,7 @@
 	if (!rv)
 		mdev->open_cnt++;
 	spin_unlock_irqrestore(&mdev->req_lock, flags);
-	unlock_kernel();
+	mutex_unlock(&drbd_main_mutex);
 
 	return rv;
 }
@@ -2559,9 +2696,9 @@
 static int drbd_release(struct gendisk *gd, fmode_t mode)
 {
 	struct drbd_conf *mdev = gd->private_data;
-	lock_kernel();
+	mutex_lock(&drbd_main_mutex);
 	mdev->open_cnt--;
-	unlock_kernel();
+	mutex_unlock(&drbd_main_mutex);
 	return 0;
 }
 
@@ -2605,7 +2742,13 @@
 		/* .verify_alg = */	{}, 0,
 		/* .cpu_mask = */	{}, 0,
 		/* .csums_alg = */	{}, 0,
-		/* .use_rle = */	0
+		/* .use_rle = */	0,
+		/* .on_no_data = */	DRBD_ON_NO_DATA_DEF,
+		/* .c_plan_ahead = */	DRBD_C_PLAN_AHEAD_DEF,
+		/* .c_delay_target = */	DRBD_C_DELAY_TARGET_DEF,
+		/* .c_fill_target = */	DRBD_C_FILL_TARGET_DEF,
+		/* .c_max_rate = */	DRBD_C_MAX_RATE_DEF,
+		/* .c_min_rate = */	DRBD_C_MIN_RATE_DEF
 	};
 
 	/* Have to use that way, because the layout differs between
@@ -2616,7 +2759,9 @@
 		  .conn = C_STANDALONE,
 		  .disk = D_DISKLESS,
 		  .pdsk = D_UNKNOWN,
-		  .susp = 0
+		  .susp = 0,
+		  .susp_nod = 0,
+		  .susp_fen = 0
 		} };
 }
 
@@ -2640,6 +2785,9 @@
 	atomic_set(&mdev->net_cnt, 0);
 	atomic_set(&mdev->packet_seq, 0);
 	atomic_set(&mdev->pp_in_use, 0);
+	atomic_set(&mdev->pp_in_use_by_net, 0);
+	atomic_set(&mdev->rs_sect_in, 0);
+	atomic_set(&mdev->rs_sect_ev, 0);
 
 	mutex_init(&mdev->md_io_mutex);
 	mutex_init(&mdev->data.mutex);
@@ -2666,11 +2814,13 @@
 	INIT_LIST_HEAD(&mdev->meta.work.q);
 	INIT_LIST_HEAD(&mdev->resync_work.list);
 	INIT_LIST_HEAD(&mdev->unplug_work.list);
+	INIT_LIST_HEAD(&mdev->go_diskless.list);
 	INIT_LIST_HEAD(&mdev->md_sync_work.list);
 	INIT_LIST_HEAD(&mdev->bm_io_work.w.list);
 
 	mdev->resync_work.cb  = w_resync_inactive;
 	mdev->unplug_work.cb  = w_send_write_hint;
+	mdev->go_diskless.cb  = w_go_diskless;
 	mdev->md_sync_work.cb = w_md_sync;
 	mdev->bm_io_work.w.cb = w_bitmap_io;
 	init_timer(&mdev->resync_timer);
@@ -2682,6 +2832,7 @@
 
 	init_waitqueue_head(&mdev->misc_wait);
 	init_waitqueue_head(&mdev->state_wait);
+	init_waitqueue_head(&mdev->net_cnt_wait);
 	init_waitqueue_head(&mdev->ee_wait);
 	init_waitqueue_head(&mdev->al_wait);
 	init_waitqueue_head(&mdev->seq_wait);
@@ -2697,6 +2848,7 @@
 
 void drbd_mdev_cleanup(struct drbd_conf *mdev)
 {
+	int i;
 	if (mdev->receiver.t_state != None)
 		dev_err(DEV, "ASSERT FAILED: receiver t_state == %d expected 0.\n",
 				mdev->receiver.t_state);
@@ -2713,9 +2865,13 @@
 	mdev->p_size       =
 	mdev->rs_start     =
 	mdev->rs_total     =
-	mdev->rs_failed    =
-	mdev->rs_mark_left =
-	mdev->rs_mark_time = 0;
+	mdev->rs_failed    = 0;
+	mdev->rs_last_events = 0;
+	mdev->rs_last_sect_ev = 0;
+	for (i = 0; i < DRBD_SYNC_MARKS; i++) {
+		mdev->rs_mark_left[i] = 0;
+		mdev->rs_mark_time[i] = 0;
+	}
 	D_ASSERT(mdev->net_conf == NULL);
 
 	drbd_set_my_capacity(mdev, 0);
@@ -2726,6 +2882,7 @@
 	}
 
 	drbd_free_resources(mdev);
+	clear_bit(AL_SUSPENDED, &mdev->flags);
 
 	/*
 	 * currently we drbd_init_ee only on module load, so
@@ -2741,6 +2898,7 @@
 	D_ASSERT(list_empty(&mdev->meta.work.q));
 	D_ASSERT(list_empty(&mdev->resync_work.list));
 	D_ASSERT(list_empty(&mdev->unplug_work.list));
+	D_ASSERT(list_empty(&mdev->go_diskless.list));
 
 }
 
@@ -3280,9 +3438,10 @@
 	sector_t sector;
 	int i;
 
+	del_timer(&mdev->md_sync_timer);
+	/* timer may be rearmed by drbd_md_mark_dirty() now. */
 	if (!test_and_clear_bit(MD_DIRTY, &mdev->flags))
 		return;
-	del_timer(&mdev->md_sync_timer);
 
 	/* We use here D_FAILED and not D_ATTACHING because we try to write
 	 * metadata even if we detach due to a disk failure! */
@@ -3310,12 +3469,9 @@
 	D_ASSERT(drbd_md_ss__(mdev, mdev->ldev) == mdev->ldev->md.md_offset);
 	sector = mdev->ldev->md.md_offset;
 
-	if (drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
-		clear_bit(MD_DIRTY, &mdev->flags);
-	} else {
+	if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
 		/* this was a try anyways ... */
 		dev_err(DEV, "meta data update failed!\n");
-
 		drbd_chk_io_error(mdev, 1, TRUE);
 	}
 
@@ -3402,6 +3558,28 @@
 	return rv;
 }
 
+static void debug_drbd_uuid(struct drbd_conf *mdev, enum drbd_uuid_index index)
+{
+	static char *uuid_str[UI_EXTENDED_SIZE] = {
+		[UI_CURRENT] = "CURRENT",
+		[UI_BITMAP] = "BITMAP",
+		[UI_HISTORY_START] = "HISTORY_START",
+		[UI_HISTORY_END] = "HISTORY_END",
+		[UI_SIZE] = "SIZE",
+		[UI_FLAGS] = "FLAGS",
+	};
+
+	if (index >= UI_EXTENDED_SIZE) {
+		dev_warn(DEV, " uuid_index >= EXTENDED_SIZE\n");
+		return;
+	}
+
+	dynamic_dev_dbg(DEV, " uuid[%s] now %016llX\n",
+		 uuid_str[index],
+		 (unsigned long long)mdev->ldev->md.uuid[index]);
+}
+
+
 /**
  * drbd_md_mark_dirty() - Mark meta data super block as dirty
  * @mdev:	DRBD device.
@@ -3410,19 +3588,31 @@
  * the meta-data super block. This function sets MD_DIRTY, and starts a
  * timer that ensures that within five seconds you have to call drbd_md_sync().
  */
+#ifdef DEBUG
+void drbd_md_mark_dirty_(struct drbd_conf *mdev, unsigned int line, const char *func)
+{
+	if (!test_and_set_bit(MD_DIRTY, &mdev->flags)) {
+		mod_timer(&mdev->md_sync_timer, jiffies + HZ);
+		mdev->last_md_mark_dirty.line = line;
+		mdev->last_md_mark_dirty.func = func;
+	}
+}
+#else
 void drbd_md_mark_dirty(struct drbd_conf *mdev)
 {
-	set_bit(MD_DIRTY, &mdev->flags);
-	mod_timer(&mdev->md_sync_timer, jiffies + 5*HZ);
+	if (!test_and_set_bit(MD_DIRTY, &mdev->flags))
+		mod_timer(&mdev->md_sync_timer, jiffies + 5*HZ);
 }
-
+#endif
 
 static void drbd_uuid_move_history(struct drbd_conf *mdev) __must_hold(local)
 {
 	int i;
 
-	for (i = UI_HISTORY_START; i < UI_HISTORY_END; i++)
+	for (i = UI_HISTORY_START; i < UI_HISTORY_END; i++) {
 		mdev->ldev->md.uuid[i+1] = mdev->ldev->md.uuid[i];
+		debug_drbd_uuid(mdev, i+1);
+	}
 }
 
 void _drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local)
@@ -3437,6 +3627,7 @@
 	}
 
 	mdev->ldev->md.uuid[idx] = val;
+	debug_drbd_uuid(mdev, idx);
 	drbd_md_mark_dirty(mdev);
 }
 
@@ -3446,6 +3637,7 @@
 	if (mdev->ldev->md.uuid[idx]) {
 		drbd_uuid_move_history(mdev);
 		mdev->ldev->md.uuid[UI_HISTORY_START] = mdev->ldev->md.uuid[idx];
+		debug_drbd_uuid(mdev, UI_HISTORY_START);
 	}
 	_drbd_uuid_set(mdev, idx, val);
 }
@@ -3464,6 +3656,7 @@
 	dev_info(DEV, "Creating new current UUID\n");
 	D_ASSERT(mdev->ldev->md.uuid[UI_BITMAP] == 0);
 	mdev->ldev->md.uuid[UI_BITMAP] = mdev->ldev->md.uuid[UI_CURRENT];
+	debug_drbd_uuid(mdev, UI_BITMAP);
 
 	get_random_bytes(&val, sizeof(u64));
 	_drbd_uuid_set(mdev, UI_CURRENT, val);
@@ -3478,6 +3671,8 @@
 		drbd_uuid_move_history(mdev);
 		mdev->ldev->md.uuid[UI_HISTORY_START] = mdev->ldev->md.uuid[UI_BITMAP];
 		mdev->ldev->md.uuid[UI_BITMAP] = 0;
+		debug_drbd_uuid(mdev, UI_HISTORY_START);
+		debug_drbd_uuid(mdev, UI_BITMAP);
 	} else {
 		if (mdev->ldev->md.uuid[UI_BITMAP])
 			dev_warn(DEV, "bm UUID already set");
@@ -3485,6 +3680,7 @@
 		mdev->ldev->md.uuid[UI_BITMAP] = val;
 		mdev->ldev->md.uuid[UI_BITMAP] &= ~((u64)1);
 
+		debug_drbd_uuid(mdev, UI_BITMAP);
 	}
 	drbd_md_mark_dirty(mdev);
 }
@@ -3527,6 +3723,7 @@
 {
 	int rv = -EIO;
 
+	drbd_resume_al(mdev);
 	if (get_ldev_if_state(mdev, D_ATTACHING)) {
 		drbd_bm_clear_all(mdev);
 		rv = drbd_bm_write(mdev);
@@ -3559,6 +3756,32 @@
 	return 1;
 }
 
+static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused)
+{
+	D_ASSERT(mdev->state.disk == D_FAILED);
+	/* we cannot assert local_cnt == 0 here, as get_ldev_if_state will
+	 * inc/dec it frequently. Once we are D_DISKLESS, no one will touch
+	 * the protected members anymore, though, so in the after_state_ch work
+	 * it will be safe to free them. */
+	drbd_force_state(mdev, NS(disk, D_DISKLESS));
+	/* We need to wait for return of references checked out while we still
+	 * have been D_FAILED, though (drbd_md_sync, bitmap io). */
+	wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
+
+	clear_bit(GO_DISKLESS, &mdev->flags);
+	return 1;
+}
+
+void drbd_go_diskless(struct drbd_conf *mdev)
+{
+	D_ASSERT(mdev->state.disk == D_FAILED);
+	if (!test_and_set_bit(GO_DISKLESS, &mdev->flags))
+		drbd_queue_work(&mdev->data.work, &mdev->go_diskless);
+		/* don't drbd_queue_work_front,
+		 * we need to serialize with the after_state_ch work
+		 * of the -> D_FAILED transition. */
+}
+
 /**
  * drbd_queue_bitmap_io() - Queues an IO operation on the whole bitmap
  * @mdev:	DRBD device.
@@ -3655,8 +3878,11 @@
 static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused)
 {
 	dev_warn(DEV, "md_sync_timer expired! Worker calls drbd_md_sync().\n");
+#ifdef DEBUG
+	dev_warn(DEV, "last md_mark_dirty: %s:%u\n",
+		mdev->last_md_mark_dirty.func, mdev->last_md_mark_dirty.line);
+#endif
 	drbd_md_sync(mdev);
-
 	return 1;
 }
 
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 73131c5..87925e9 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -33,10 +33,13 @@
 #include <linux/blkpg.h>
 #include <linux/cpumask.h>
 #include "drbd_int.h"
+#include "drbd_req.h"
 #include "drbd_wrappers.h"
 #include <asm/unaligned.h>
 #include <linux/drbd_tag_magic.h>
 #include <linux/drbd_limits.h>
+#include <linux/compiler.h>
+#include <linux/kthread.h>
 
 static unsigned short *tl_add_blob(unsigned short *, enum drbd_tags, const void *, int);
 static unsigned short *tl_add_str(unsigned short *, enum drbd_tags, const char *);
@@ -169,6 +172,10 @@
 		put_net_conf(mdev);
 	}
 
+	/* The helper may take some time.
+	 * write out any unsynced meta data changes now */
+	drbd_md_sync(mdev);
+
 	dev_info(DEV, "helper command: %s %s %s\n", usermode_helper, cmd, mb);
 
 	drbd_bcast_ev_helper(mdev, cmd);
@@ -202,12 +209,10 @@
 		put_ldev(mdev);
 	} else {
 		dev_warn(DEV, "Not fencing peer, I'm not even Consistent myself.\n");
-		return mdev->state.pdsk;
+		nps = mdev->state.pdsk;
+		goto out;
 	}
 
-	if (fp == FP_STONITH)
-		_drbd_request_state(mdev, NS(susp, 1), CS_WAIT_COMPLETE);
-
 	r = drbd_khelper(mdev, "fence-peer");
 
 	switch ((r>>8) & 0xff) {
@@ -252,9 +257,36 @@
 
 	dev_info(DEV, "fence-peer helper returned %d (%s)\n",
 			(r>>8) & 0xff, ex_to_string);
+
+out:
+	if (mdev->state.susp_fen && nps >= D_UNKNOWN) {
+		/* The handler was not successful... unfreeze here, the
+		   state engine can not unfreeze... */
+		_drbd_request_state(mdev, NS(susp_fen, 0), CS_VERBOSE);
+	}
+
 	return nps;
 }
 
+static int _try_outdate_peer_async(void *data)
+{
+	struct drbd_conf *mdev = (struct drbd_conf *)data;
+	enum drbd_disk_state nps;
+
+	nps = drbd_try_outdate_peer(mdev);
+	drbd_request_state(mdev, NS(pdsk, nps));
+
+	return 0;
+}
+
+void drbd_try_outdate_peer_async(struct drbd_conf *mdev)
+{
+	struct task_struct *opa;
+
+	opa = kthread_run(_try_outdate_peer_async, mdev, "drbd%d_a_helper", mdev_to_minor(mdev));
+	if (IS_ERR(opa))
+		dev_err(DEV, "out of mem, failed to invoke fence-peer helper\n");
+}
 
 int drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 {
@@ -394,6 +426,39 @@
 	return r;
 }
 
+static struct drbd_conf *ensure_mdev(int minor, int create)
+{
+	struct drbd_conf *mdev;
+
+	if (minor >= minor_count)
+		return NULL;
+
+	mdev = minor_to_mdev(minor);
+
+	if (!mdev && create) {
+		struct gendisk *disk = NULL;
+		mdev = drbd_new_device(minor);
+
+		spin_lock_irq(&drbd_pp_lock);
+		if (minor_table[minor] == NULL) {
+			minor_table[minor] = mdev;
+			disk = mdev->vdisk;
+			mdev = NULL;
+		} /* else: we lost the race */
+		spin_unlock_irq(&drbd_pp_lock);
+
+		if (disk) /* we won the race above */
+			/* in case we ever add a drbd_delete_device(),
+			 * don't forget the del_gendisk! */
+			add_disk(disk);
+		else /* we lost the race above */
+			drbd_free_mdev(mdev);
+
+		mdev = minor_to_mdev(minor);
+	}
+
+	return mdev;
+}
 
 static int drbd_nl_primary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 			   struct drbd_nl_cfg_reply *reply)
@@ -494,6 +559,8 @@
 void drbd_suspend_io(struct drbd_conf *mdev)
 {
 	set_bit(SUSPEND_IO, &mdev->flags);
+	if (is_susp(mdev->state))
+		return;
 	wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt));
 }
 
@@ -713,9 +780,6 @@
 	blk_queue_segment_boundary(q, PAGE_SIZE-1);
 	blk_stack_limits(&q->limits, &b->limits, 0);
 
-	if (b->merge_bvec_fn)
-		dev_warn(DEV, "Backing device's merge_bvec_fn() = %p\n",
-		     b->merge_bvec_fn);
 	dev_info(DEV, "max_segment_size ( = BIO size ) = %u\n", queue_max_segment_size(q));
 
 	if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) {
@@ -729,14 +793,16 @@
 /* serialize deconfig (worker exiting, doing cleanup)
  * and reconfig (drbdsetup disk, drbdsetup net)
  *
- * wait for a potentially exiting worker, then restart it,
- * or start a new one.
+ * Wait for a potentially exiting worker, then restart it,
+ * or start a new one.  Flush any pending work, there may still be an
+ * after_state_change queued.
  */
 static void drbd_reconfig_start(struct drbd_conf *mdev)
 {
 	wait_event(mdev->state_wait, !test_and_set_bit(CONFIG_PENDING, &mdev->flags));
 	wait_event(mdev->state_wait, !test_bit(DEVICE_DYING, &mdev->flags));
 	drbd_thread_start(&mdev->worker);
+	drbd_flush_workqueue(mdev);
 }
 
 /* if still unconfigured, stops worker again.
@@ -756,6 +822,29 @@
 	wake_up(&mdev->state_wait);
 }
 
+/* Make sure IO is suspended before calling this function(). */
+static void drbd_suspend_al(struct drbd_conf *mdev)
+{
+	int s = 0;
+
+	if (lc_try_lock(mdev->act_log)) {
+		drbd_al_shrink(mdev);
+		lc_unlock(mdev->act_log);
+	} else {
+		dev_warn(DEV, "Failed to lock al in drbd_suspend_al()\n");
+		return;
+	}
+
+	spin_lock_irq(&mdev->req_lock);
+	if (mdev->state.conn < C_CONNECTED)
+		s = !test_and_set_bit(AL_SUSPENDED, &mdev->flags);
+
+	spin_unlock_irq(&mdev->req_lock);
+
+	if (s)
+		dev_info(DEV, "Suspended AL updates\n");
+}
+
 /* does always return 0;
  * interesting return code is in reply->ret_code */
 static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
@@ -769,6 +858,7 @@
 	struct inode *inode, *inode2;
 	struct lru_cache *resync_lru = NULL;
 	union drbd_state ns, os;
+	unsigned int max_seg_s;
 	int rv;
 	int cp_discovered = 0;
 	int logical_block_size;
@@ -803,6 +893,15 @@
 		goto fail;
 	}
 
+	if (get_net_conf(mdev)) {
+		int prot = mdev->net_conf->wire_protocol;
+		put_net_conf(mdev);
+		if (nbc->dc.fencing == FP_STONITH && prot == DRBD_PROT_A) {
+			retcode = ERR_STONITH_AND_PROT_A;
+			goto fail;
+		}
+	}
+
 	nbc->lo_file = filp_open(nbc->dc.backing_dev, O_RDWR, 0);
 	if (IS_ERR(nbc->lo_file)) {
 		dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.backing_dev,
@@ -924,7 +1023,7 @@
 
 	drbd_suspend_io(mdev);
 	/* also wait for the last barrier ack. */
-	wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_pending_cnt));
+	wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_pending_cnt) || is_susp(mdev->state));
 	/* and for any other previously queued work */
 	drbd_flush_workqueue(mdev);
 
@@ -1021,7 +1120,8 @@
 	else
 		clear_bit(CRASHED_PRIMARY, &mdev->flags);
 
-	if (drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND)) {
+	if (drbd_md_test_flag(mdev->ldev, MDF_PRIMARY_IND) &&
+	    !(mdev->state.role == R_PRIMARY && mdev->state.susp_nod)) {
 		set_bit(CRASHED_PRIMARY, &mdev->flags);
 		cp_discovered = 1;
 	}
@@ -1031,7 +1131,20 @@
 	mdev->read_cnt = 0;
 	mdev->writ_cnt = 0;
 
-	drbd_setup_queue_param(mdev, DRBD_MAX_SEGMENT_SIZE);
+	max_seg_s = DRBD_MAX_SEGMENT_SIZE;
+	if (mdev->state.conn == C_CONNECTED) {
+		/* We are Primary, Connected, and now attach a new local
+		 * backing store. We must not increase the user visible maximum
+		 * bio size on this device to something the peer may not be
+		 * able to handle. */
+		if (mdev->agreed_pro_version < 94)
+			max_seg_s = queue_max_segment_size(mdev->rq_queue);
+		else if (mdev->agreed_pro_version == 94)
+			max_seg_s = DRBD_MAX_SIZE_H80_PACKET;
+		/* else: drbd 8.3.9 and later, stay with default */
+	}
+
+	drbd_setup_queue_param(mdev, max_seg_s);
 
 	/* If I am currently not R_PRIMARY,
 	 * but meta data primary indicator is set,
@@ -1079,6 +1192,9 @@
 		drbd_al_to_on_disk_bm(mdev);
 	}
 
+	if (_drbd_bm_total_weight(mdev) == drbd_bm_bits(mdev))
+		drbd_suspend_al(mdev); /* IO is still suspended here... */
+
 	spin_lock_irq(&mdev->req_lock);
 	os = mdev->state;
 	ns.i = os.i;
@@ -1235,7 +1351,16 @@
 	    && (new_conf->wire_protocol != DRBD_PROT_C)) {
 		retcode = ERR_NOT_PROTO_C;
 		goto fail;
-	};
+	}
+
+	if (get_ldev(mdev)) {
+		enum drbd_fencing_p fp = mdev->ldev->dc.fencing;
+		put_ldev(mdev);
+		if (new_conf->wire_protocol == DRBD_PROT_A && fp == FP_STONITH) {
+			retcode = ERR_STONITH_AND_PROT_A;
+			goto fail;
+		}
+	}
 
 	if (mdev->state.role == R_PRIMARY && new_conf->want_lose) {
 		retcode = ERR_DISCARD;
@@ -1350,6 +1475,7 @@
 		}
 	}
 
+	drbd_flush_workqueue(mdev);
 	spin_lock_irq(&mdev->req_lock);
 	if (mdev->net_conf != NULL) {
 		retcode = ERR_NET_CONFIGURED;
@@ -1388,10 +1514,9 @@
 	mdev->int_dig_out=int_dig_out;
 	mdev->int_dig_in=int_dig_in;
 	mdev->int_dig_vv=int_dig_vv;
+	retcode = _drbd_set_state(_NS(mdev, conn, C_UNCONNECTED), CS_VERBOSE, NULL);
 	spin_unlock_irq(&mdev->req_lock);
 
-	retcode = _drbd_request_state(mdev, NS(conn, C_UNCONNECTED), CS_VERBOSE);
-
 	kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
 	reply->ret_code = retcode;
 	drbd_reconfig_done(mdev);
@@ -1546,6 +1671,8 @@
 	struct crypto_hash *csums_tfm = NULL;
 	struct syncer_conf sc;
 	cpumask_var_t new_cpu_mask;
+	int *rs_plan_s = NULL;
+	int fifo_size;
 
 	if (!zalloc_cpumask_var(&new_cpu_mask, GFP_KERNEL)) {
 		retcode = ERR_NOMEM;
@@ -1557,6 +1684,12 @@
 		sc.rate       = DRBD_RATE_DEF;
 		sc.after      = DRBD_AFTER_DEF;
 		sc.al_extents = DRBD_AL_EXTENTS_DEF;
+		sc.on_no_data  = DRBD_ON_NO_DATA_DEF;
+		sc.c_plan_ahead = DRBD_C_PLAN_AHEAD_DEF;
+		sc.c_delay_target = DRBD_C_DELAY_TARGET_DEF;
+		sc.c_fill_target = DRBD_C_FILL_TARGET_DEF;
+		sc.c_max_rate = DRBD_C_MAX_RATE_DEF;
+		sc.c_min_rate = DRBD_C_MIN_RATE_DEF;
 	} else
 		memcpy(&sc, &mdev->sync_conf, sizeof(struct syncer_conf));
 
@@ -1634,6 +1767,12 @@
 	}
 #undef AL_MAX
 
+	/* to avoid spurious errors when configuring minors before configuring
+	 * the minors they depend on: if necessary, first create the minor we
+	 * depend on */
+	if (sc.after >= 0)
+		ensure_mdev(sc.after, 1);
+
 	/* most sanity checks done, try to assign the new sync-after
 	 * dependency.  need to hold the global lock in there,
 	 * to avoid a race in the dependency loop check. */
@@ -1641,6 +1780,16 @@
 	if (retcode != NO_ERROR)
 		goto fail;
 
+	fifo_size = (sc.c_plan_ahead * 10 * SLEEP_TIME) / HZ;
+	if (fifo_size != mdev->rs_plan_s.size && fifo_size > 0) {
+		rs_plan_s   = kzalloc(sizeof(int) * fifo_size, GFP_KERNEL);
+		if (!rs_plan_s) {
+			dev_err(DEV, "kmalloc of fifo_buffer failed");
+			retcode = ERR_NOMEM;
+			goto fail;
+		}
+	}
+
 	/* ok, assign the rest of it as well.
 	 * lock against receive_SyncParam() */
 	spin_lock(&mdev->peer_seq_lock);
@@ -1657,6 +1806,15 @@
 		mdev->verify_tfm = verify_tfm;
 		verify_tfm = NULL;
 	}
+
+	if (fifo_size != mdev->rs_plan_s.size) {
+		kfree(mdev->rs_plan_s.values);
+		mdev->rs_plan_s.values = rs_plan_s;
+		mdev->rs_plan_s.size   = fifo_size;
+		mdev->rs_planed = 0;
+		rs_plan_s = NULL;
+	}
+
 	spin_unlock(&mdev->peer_seq_lock);
 
 	if (get_ldev(mdev)) {
@@ -1688,6 +1846,7 @@
 
 	kobject_uevent(&disk_to_dev(mdev->vdisk)->kobj, KOBJ_CHANGE);
 fail:
+	kfree(rs_plan_s);
 	free_cpumask_var(new_cpu_mask);
 	crypto_free_hash(csums_tfm);
 	crypto_free_hash(verify_tfm);
@@ -1721,12 +1880,38 @@
 	return 0;
 }
 
+static int drbd_bmio_set_susp_al(struct drbd_conf *mdev)
+{
+	int rv;
+
+	rv = drbd_bmio_set_n_write(mdev);
+	drbd_suspend_al(mdev);
+	return rv;
+}
+
 static int drbd_nl_invalidate_peer(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 				   struct drbd_nl_cfg_reply *reply)
 {
+	int retcode;
 
-	reply->ret_code = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
+	retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S), CS_ORDERED);
 
+	if (retcode < SS_SUCCESS) {
+		if (retcode == SS_NEED_CONNECTION && mdev->state.role == R_PRIMARY) {
+			/* The peer will get a resync upon connect anyways. Just make that
+			   into a full resync. */
+			retcode = drbd_request_state(mdev, NS(pdsk, D_INCONSISTENT));
+			if (retcode >= SS_SUCCESS) {
+				/* open coded drbd_bitmap_io() */
+				if (drbd_bitmap_io(mdev, &drbd_bmio_set_susp_al,
+						   "set_n_write from invalidate_peer"))
+					retcode = ERR_IO_MD_DISK;
+			}
+		} else
+			retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
+	}
+
+	reply->ret_code = retcode;
 	return 0;
 }
 
@@ -1765,7 +1950,21 @@
 static int drbd_nl_resume_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 			     struct drbd_nl_cfg_reply *reply)
 {
-	reply->ret_code = drbd_request_state(mdev, NS(susp, 0));
+	if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
+		drbd_uuid_new_current(mdev);
+		clear_bit(NEW_CUR_UUID, &mdev->flags);
+		drbd_md_sync(mdev);
+	}
+	drbd_suspend_io(mdev);
+	reply->ret_code = drbd_request_state(mdev, NS3(susp, 0, susp_nod, 0, susp_fen, 0));
+	if (reply->ret_code == SS_SUCCESS) {
+		if (mdev->state.conn < C_CONNECTED)
+			tl_clear(mdev);
+		if (mdev->state.disk == D_DISKLESS || mdev->state.disk == D_FAILED)
+			tl_restart(mdev, fail_frozen_disk_io);
+	}
+	drbd_resume_io(mdev);
+
 	return 0;
 }
 
@@ -1941,40 +2140,6 @@
 	return 0;
 }
 
-static struct drbd_conf *ensure_mdev(struct drbd_nl_cfg_req *nlp)
-{
-	struct drbd_conf *mdev;
-
-	if (nlp->drbd_minor >= minor_count)
-		return NULL;
-
-	mdev = minor_to_mdev(nlp->drbd_minor);
-
-	if (!mdev && (nlp->flags & DRBD_NL_CREATE_DEVICE)) {
-		struct gendisk *disk = NULL;
-		mdev = drbd_new_device(nlp->drbd_minor);
-
-		spin_lock_irq(&drbd_pp_lock);
-		if (minor_table[nlp->drbd_minor] == NULL) {
-			minor_table[nlp->drbd_minor] = mdev;
-			disk = mdev->vdisk;
-			mdev = NULL;
-		} /* else: we lost the race */
-		spin_unlock_irq(&drbd_pp_lock);
-
-		if (disk) /* we won the race above */
-			/* in case we ever add a drbd_delete_device(),
-			 * don't forget the del_gendisk! */
-			add_disk(disk);
-		else /* we lost the race above */
-			drbd_free_mdev(mdev);
-
-		mdev = minor_to_mdev(nlp->drbd_minor);
-	}
-
-	return mdev;
-}
-
 struct cn_handler_struct {
 	int (*function)(struct drbd_conf *,
 			 struct drbd_nl_cfg_req *,
@@ -2035,7 +2200,8 @@
 		goto fail;
 	}
 
-	mdev = ensure_mdev(nlp);
+	mdev = ensure_mdev(nlp->drbd_minor,
+			(nlp->flags & DRBD_NL_CREATE_DEVICE));
 	if (!mdev) {
 		retcode = ERR_MINOR_INVALID;
 		goto fail;
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index be3374b..ad325c5 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -57,6 +57,7 @@
 	unsigned long db, dt, dbdt, rt, rs_left;
 	unsigned int res;
 	int i, x, y;
+	int stalled = 0;
 
 	drbd_get_syncer_progress(mdev, &rs_left, &res);
 
@@ -90,18 +91,17 @@
 	 * db: blocks written from mark until now
 	 * rt: remaining time
 	 */
-	dt = (jiffies - mdev->rs_mark_time) / HZ;
-
-	if (dt > 20) {
-		/* if we made no update to rs_mark_time for too long,
-		 * we are stalled. show that. */
-		seq_printf(seq, "stalled\n");
-		return;
-	}
+	/* Rolling marks. last_mark+1 may just now be modified.  last_mark+2 is
+	 * at least (DRBD_SYNC_MARKS-2)*DRBD_SYNC_MARK_STEP old, and has at
+	 * least DRBD_SYNC_MARK_STEP time before it will be modified. */
+	i = (mdev->rs_last_mark + 2) % DRBD_SYNC_MARKS;
+	dt = (jiffies - mdev->rs_mark_time[i]) / HZ;
+	if (dt > (DRBD_SYNC_MARK_STEP * DRBD_SYNC_MARKS))
+		stalled = 1;
 
 	if (!dt)
 		dt++;
-	db = mdev->rs_mark_left - rs_left;
+	db = mdev->rs_mark_left[i] - rs_left;
 	rt = (dt * (rs_left / (db/100+1)))/100; /* seconds */
 
 	seq_printf(seq, "finish: %lu:%02lu:%02lu",
@@ -118,7 +118,7 @@
 	/* mean speed since syncer started
 	 * we do account for PausedSync periods */
 	dt = (jiffies - mdev->rs_start - mdev->rs_paused) / HZ;
-	if (dt <= 0)
+	if (dt == 0)
 		dt = 1;
 	db = mdev->rs_total - rs_left;
 	dbdt = Bit2KB(db/dt);
@@ -128,7 +128,14 @@
 	else
 		seq_printf(seq, " (%ld)", dbdt);
 
-	seq_printf(seq, " K/sec\n");
+	if (mdev->state.conn == C_SYNC_TARGET) {
+		if (mdev->c_sync_rate > 1000)
+			seq_printf(seq, " want: %d,%03d",
+				   mdev->c_sync_rate / 1000, mdev->c_sync_rate % 1000);
+		else
+			seq_printf(seq, " want: %d", mdev->c_sync_rate);
+	}
+	seq_printf(seq, " K/sec%s\n", stalled ? " (stalled)" : "");
 }
 
 static void resync_dump_detail(struct seq_file *seq, struct lc_element *e)
@@ -196,7 +203,7 @@
 			seq_printf(seq, "%2d: cs:Unconfigured\n", i);
 		} else {
 			seq_printf(seq,
-			   "%2d: cs:%s ro:%s/%s ds:%s/%s %c %c%c%c%c%c\n"
+			   "%2d: cs:%s ro:%s/%s ds:%s/%s %c %c%c%c%c%c%c\n"
 			   "    ns:%u nr:%u dw:%u dr:%u al:%u bm:%u "
 			   "lo:%d pe:%d ua:%d ap:%d ep:%d wo:%c",
 			   i, sn,
@@ -206,11 +213,12 @@
 			   drbd_disk_str(mdev->state.pdsk),
 			   (mdev->net_conf == NULL ? ' ' :
 			    (mdev->net_conf->wire_protocol - DRBD_PROT_A+'A')),
-			   mdev->state.susp ? 's' : 'r',
+			   is_susp(mdev->state) ? 's' : 'r',
 			   mdev->state.aftr_isp ? 'a' : '-',
 			   mdev->state.peer_isp ? 'p' : '-',
 			   mdev->state.user_isp ? 'u' : '-',
 			   mdev->congestion_reason ?: '-',
+			   test_bit(AL_SUSPENDED, &mdev->flags) ? 's' : '-',
 			   mdev->send_cnt/2,
 			   mdev->recv_cnt/2,
 			   mdev->writ_cnt/2,
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 081522d..efd6169 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -241,7 +241,7 @@
 	spin_unlock_irq(&mdev->req_lock);
 
 	list_for_each_entry_safe(e, t, &reclaimed, w.list)
-		drbd_free_ee(mdev, e);
+		drbd_free_net_ee(mdev, e);
 }
 
 /**
@@ -298,9 +298,11 @@
  * Is also used from inside an other spin_lock_irq(&mdev->req_lock);
  * Either links the page chain back to the global pool,
  * or returns all pages to the system. */
-static void drbd_pp_free(struct drbd_conf *mdev, struct page *page)
+static void drbd_pp_free(struct drbd_conf *mdev, struct page *page, int is_net)
 {
+	atomic_t *a = is_net ? &mdev->pp_in_use_by_net : &mdev->pp_in_use;
 	int i;
+
 	if (drbd_pp_vacant > (DRBD_MAX_SEGMENT_SIZE/PAGE_SIZE)*minor_count)
 		i = page_chain_free(page);
 	else {
@@ -311,10 +313,10 @@
 		drbd_pp_vacant += i;
 		spin_unlock(&drbd_pp_lock);
 	}
-	atomic_sub(i, &mdev->pp_in_use);
-	i = atomic_read(&mdev->pp_in_use);
+	i = atomic_sub_return(i, a);
 	if (i < 0)
-		dev_warn(DEV, "ASSERTION FAILED: pp_in_use: %d < 0\n", i);
+		dev_warn(DEV, "ASSERTION FAILED: %s: %d < 0\n",
+			is_net ? "pp_in_use_by_net" : "pp_in_use", i);
 	wake_up(&drbd_pp_wait);
 }
 
@@ -365,7 +367,6 @@
 	e->size = data_size;
 	e->flags = 0;
 	e->sector = sector;
-	e->sector = sector;
 	e->block_id = id;
 
 	return e;
@@ -375,9 +376,11 @@
 	return NULL;
 }
 
-void drbd_free_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e)
+void drbd_free_some_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e, int is_net)
 {
-	drbd_pp_free(mdev, e->pages);
+	if (e->flags & EE_HAS_DIGEST)
+		kfree(e->digest);
+	drbd_pp_free(mdev, e->pages, is_net);
 	D_ASSERT(atomic_read(&e->pending_bios) == 0);
 	D_ASSERT(hlist_unhashed(&e->colision));
 	mempool_free(e, drbd_ee_mempool);
@@ -388,13 +391,14 @@
 	LIST_HEAD(work_list);
 	struct drbd_epoch_entry *e, *t;
 	int count = 0;
+	int is_net = list == &mdev->net_ee;
 
 	spin_lock_irq(&mdev->req_lock);
 	list_splice_init(list, &work_list);
 	spin_unlock_irq(&mdev->req_lock);
 
 	list_for_each_entry_safe(e, t, &work_list, w.list) {
-		drbd_free_ee(mdev, e);
+		drbd_free_some_ee(mdev, e, is_net);
 		count++;
 	}
 	return count;
@@ -423,7 +427,7 @@
 	spin_unlock_irq(&mdev->req_lock);
 
 	list_for_each_entry_safe(e, t, &reclaimed, w.list)
-		drbd_free_ee(mdev, e);
+		drbd_free_net_ee(mdev, e);
 
 	/* possible callbacks here:
 	 * e_end_block, and e_end_resync_block, e_send_discard_ack.
@@ -719,14 +723,14 @@
 static int drbd_send_fp(struct drbd_conf *mdev,
 	struct socket *sock, enum drbd_packets cmd)
 {
-	struct p_header *h = (struct p_header *) &mdev->data.sbuf.header;
+	struct p_header80 *h = &mdev->data.sbuf.header.h80;
 
 	return _drbd_send_cmd(mdev, sock, cmd, h, sizeof(*h), 0);
 }
 
 static enum drbd_packets drbd_recv_fp(struct drbd_conf *mdev, struct socket *sock)
 {
-	struct p_header *h = (struct p_header *) &mdev->data.sbuf.header;
+	struct p_header80 *h = &mdev->data.rbuf.header.h80;
 	int rr;
 
 	rr = drbd_recv_short(mdev, sock, h, sizeof(*h), 0);
@@ -776,9 +780,6 @@
 
 	D_ASSERT(!mdev->data.socket);
 
-	if (test_and_clear_bit(CREATE_BARRIER, &mdev->flags))
-		dev_err(DEV, "CREATE_BARRIER flag was set in drbd_connect - now cleared!\n");
-
 	if (drbd_request_state(mdev, NS(conn, C_WF_CONNECTION)) < SS_SUCCESS)
 		return -2;
 
@@ -927,6 +928,11 @@
 
 	drbd_thread_start(&mdev->asender);
 
+	if (mdev->agreed_pro_version < 95 && get_ldev(mdev)) {
+		drbd_setup_queue_param(mdev, DRBD_MAX_SIZE_H80_PACKET);
+		put_ldev(mdev);
+	}
+
 	if (!drbd_send_protocol(mdev))
 		return -1;
 	drbd_send_sync_param(mdev, &mdev->sync_conf);
@@ -946,22 +952,28 @@
 	return -1;
 }
 
-static int drbd_recv_header(struct drbd_conf *mdev, struct p_header *h)
+static int drbd_recv_header(struct drbd_conf *mdev, enum drbd_packets *cmd, unsigned int *packet_size)
 {
+	union p_header *h = &mdev->data.rbuf.header;
 	int r;
 
 	r = drbd_recv(mdev, h, sizeof(*h));
-
 	if (unlikely(r != sizeof(*h))) {
 		dev_err(DEV, "short read expecting header on sock: r=%d\n", r);
 		return FALSE;
-	};
-	h->command = be16_to_cpu(h->command);
-	h->length  = be16_to_cpu(h->length);
-	if (unlikely(h->magic != BE_DRBD_MAGIC)) {
-		dev_err(DEV, "magic?? on data m: 0x%lx c: %d l: %d\n",
-		    (long)be32_to_cpu(h->magic),
-		    h->command, h->length);
+	}
+
+	if (likely(h->h80.magic == BE_DRBD_MAGIC)) {
+		*cmd = be16_to_cpu(h->h80.command);
+		*packet_size = be16_to_cpu(h->h80.length);
+	} else if (h->h95.magic == BE_DRBD_MAGIC_BIG) {
+		*cmd = be16_to_cpu(h->h95.command);
+		*packet_size = be32_to_cpu(h->h95.length);
+	} else {
+		dev_err(DEV, "magic?? on data m: 0x%08x c: %d l: %d\n",
+		    be32_to_cpu(h->h80.magic),
+		    be16_to_cpu(h->h80.command),
+		    be16_to_cpu(h->h80.length));
 		return FALSE;
 	}
 	mdev->last_received = jiffies;
@@ -975,7 +987,7 @@
 
 	if (mdev->write_ordering >= WO_bdev_flush && get_ldev(mdev)) {
 		rv = blkdev_issue_flush(mdev->ldev->backing_bdev, GFP_KERNEL,
-					NULL, BLKDEV_IFL_WAIT);
+					NULL);
 		if (rv) {
 			dev_err(DEV, "local disk flush failed with status %d\n", rv);
 			/* would rather check on EOPNOTSUPP, but that is not reliable.
@@ -1268,17 +1280,12 @@
 	return 1;
 }
 
-static int receive_Barrier(struct drbd_conf *mdev, struct p_header *h)
+static int receive_Barrier(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
 	int rv, issue_flush;
-	struct p_barrier *p = (struct p_barrier *)h;
+	struct p_barrier *p = &mdev->data.rbuf.barrier;
 	struct drbd_epoch *epoch;
 
-	ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE;
-
-	rv = drbd_recv(mdev, h->payload, h->length);
-	ERR_IF(rv != h->length) return FALSE;
-
 	inc_unacked(mdev);
 
 	if (mdev->net_conf->wire_protocol != DRBD_PROT_C)
@@ -1457,7 +1464,7 @@
 		data_size -= rr;
 	}
 	kunmap(page);
-	drbd_pp_free(mdev, page);
+	drbd_pp_free(mdev, page, 0);
 	return rv;
 }
 
@@ -1562,30 +1569,29 @@
 	list_add(&e->w.list, &mdev->sync_ee);
 	spin_unlock_irq(&mdev->req_lock);
 
+	atomic_add(data_size >> 9, &mdev->rs_sect_ev);
 	if (drbd_submit_ee(mdev, e, WRITE, DRBD_FAULT_RS_WR) == 0)
 		return TRUE;
 
+	/* drbd_submit_ee currently fails for one reason only:
+	 * not being able to allocate enough bios.
+	 * Is dropping the connection going to help? */
+	spin_lock_irq(&mdev->req_lock);
+	list_del(&e->w.list);
+	spin_unlock_irq(&mdev->req_lock);
+
 	drbd_free_ee(mdev, e);
 fail:
 	put_ldev(mdev);
 	return FALSE;
 }
 
-static int receive_DataReply(struct drbd_conf *mdev, struct p_header *h)
+static int receive_DataReply(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
 	struct drbd_request *req;
 	sector_t sector;
-	unsigned int header_size, data_size;
 	int ok;
-	struct p_data *p = (struct p_data *)h;
-
-	header_size = sizeof(*p) - sizeof(*h);
-	data_size   = h->length  - header_size;
-
-	ERR_IF(data_size == 0) return FALSE;
-
-	if (drbd_recv(mdev, h->payload, header_size) != header_size)
-		return FALSE;
+	struct p_data *p = &mdev->data.rbuf.data;
 
 	sector = be64_to_cpu(p->sector);
 
@@ -1611,20 +1617,11 @@
 	return ok;
 }
 
-static int receive_RSDataReply(struct drbd_conf *mdev, struct p_header *h)
+static int receive_RSDataReply(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
 	sector_t sector;
-	unsigned int header_size, data_size;
 	int ok;
-	struct p_data *p = (struct p_data *)h;
-
-	header_size = sizeof(*p) - sizeof(*h);
-	data_size   = h->length  - header_size;
-
-	ERR_IF(data_size == 0) return FALSE;
-
-	if (drbd_recv(mdev, h->payload, header_size) != header_size)
-		return FALSE;
+	struct p_data *p = &mdev->data.rbuf.data;
 
 	sector = be64_to_cpu(p->sector);
 	D_ASSERT(p->block_id == ID_SYNCER);
@@ -1640,9 +1637,11 @@
 
 		ok = drbd_drain_block(mdev, data_size);
 
-		drbd_send_ack_dp(mdev, P_NEG_ACK, p);
+		drbd_send_ack_dp(mdev, P_NEG_ACK, p, data_size);
 	}
 
+	atomic_add(data_size >> 9, &mdev->rs_sect_in);
+
 	return ok;
 }
 
@@ -1765,24 +1764,27 @@
 	return ret;
 }
 
+static unsigned long write_flags_to_bio(struct drbd_conf *mdev, u32 dpf)
+{
+	if (mdev->agreed_pro_version >= 95)
+		return  (dpf & DP_RW_SYNC ? REQ_SYNC : 0) |
+			(dpf & DP_UNPLUG ? REQ_UNPLUG : 0) |
+			(dpf & DP_FUA ? REQ_FUA : 0) |
+			(dpf & DP_FLUSH ? REQ_FUA : 0) |
+			(dpf & DP_DISCARD ? REQ_DISCARD : 0);
+	else
+		return dpf & DP_RW_SYNC ? (REQ_SYNC | REQ_UNPLUG) : 0;
+}
+
 /* mirrored write */
-static int receive_Data(struct drbd_conf *mdev, struct p_header *h)
+static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
 	sector_t sector;
 	struct drbd_epoch_entry *e;
-	struct p_data *p = (struct p_data *)h;
-	int header_size, data_size;
+	struct p_data *p = &mdev->data.rbuf.data;
 	int rw = WRITE;
 	u32 dp_flags;
 
-	header_size = sizeof(*p) - sizeof(*h);
-	data_size   = h->length  - header_size;
-
-	ERR_IF(data_size == 0) return FALSE;
-
-	if (drbd_recv(mdev, h->payload, header_size) != header_size)
-		return FALSE;
-
 	if (!get_ldev(mdev)) {
 		if (__ratelimit(&drbd_ratelimit_state))
 			dev_err(DEV, "Can not write mirrored data block "
@@ -1792,7 +1794,7 @@
 			mdev->peer_seq++;
 		spin_unlock(&mdev->peer_seq_lock);
 
-		drbd_send_ack_dp(mdev, P_NEG_ACK, p);
+		drbd_send_ack_dp(mdev, P_NEG_ACK, p, data_size);
 		atomic_inc(&mdev->current_epoch->epoch_size);
 		return drbd_drain_block(mdev, data_size);
 	}
@@ -1839,12 +1841,8 @@
 	spin_unlock(&mdev->epoch_lock);
 
 	dp_flags = be32_to_cpu(p->dp_flags);
-	if (dp_flags & DP_HARDBARRIER) {
-		dev_err(DEV, "ASSERT FAILED would have submitted barrier request\n");
-		/* rw |= REQ_HARDBARRIER; */
-	}
-	if (dp_flags & DP_RW_SYNC)
-		rw |= REQ_SYNC | REQ_UNPLUG;
+	rw |= write_flags_to_bio(mdev, dp_flags);
+
 	if (dp_flags & DP_MAY_SET_IN_SYNC)
 		e->flags |= EE_MAY_SET_IN_SYNC;
 
@@ -2007,6 +2005,16 @@
 	if (drbd_submit_ee(mdev, e, rw, DRBD_FAULT_DT_WR) == 0)
 		return TRUE;
 
+	/* drbd_submit_ee currently fails for one reason only:
+	 * not being able to allocate enough bios.
+	 * Is dropping the connection going to help? */
+	spin_lock_irq(&mdev->req_lock);
+	list_del(&e->w.list);
+	hlist_del_init(&e->colision);
+	spin_unlock_irq(&mdev->req_lock);
+	if (e->flags & EE_CALL_AL_COMPLETE_IO)
+		drbd_al_complete_io(mdev, e->sector);
+
 out_interrupted:
 	/* yes, the epoch_size now is imbalanced.
 	 * but we drop the connection anyways, so we don't have a chance to
@@ -2016,20 +2024,64 @@
 	return FALSE;
 }
 
-static int receive_DataRequest(struct drbd_conf *mdev, struct p_header *h)
+/* We may throttle resync, if the lower device seems to be busy,
+ * and current sync rate is above c_min_rate.
+ *
+ * To decide whether or not the lower device is busy, we use a scheme similar
+ * to MD RAID is_mddev_idle(): if the partition stats reveal "significant"
+ * (more than 64 sectors) of activity we cannot account for with our own resync
+ * activity, it obviously is "busy".
+ *
+ * The current sync rate used here uses only the most recent two step marks,
+ * to have a short time average so we can react faster.
+ */
+int drbd_rs_should_slow_down(struct drbd_conf *mdev)
+{
+	struct gendisk *disk = mdev->ldev->backing_bdev->bd_contains->bd_disk;
+	unsigned long db, dt, dbdt;
+	int curr_events;
+	int throttle = 0;
+
+	/* feature disabled? */
+	if (mdev->sync_conf.c_min_rate == 0)
+		return 0;
+
+	curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
+		      (int)part_stat_read(&disk->part0, sectors[1]) -
+			atomic_read(&mdev->rs_sect_ev);
+	if (!mdev->rs_last_events || curr_events - mdev->rs_last_events > 64) {
+		unsigned long rs_left;
+		int i;
+
+		mdev->rs_last_events = curr_events;
+
+		/* sync speed average over the last 2*DRBD_SYNC_MARK_STEP,
+		 * approx. */
+		i = (mdev->rs_last_mark + DRBD_SYNC_MARKS-2) % DRBD_SYNC_MARKS;
+		rs_left = drbd_bm_total_weight(mdev) - mdev->rs_failed;
+
+		dt = ((long)jiffies - (long)mdev->rs_mark_time[i]) / HZ;
+		if (!dt)
+			dt++;
+		db = mdev->rs_mark_left[i] - rs_left;
+		dbdt = Bit2KB(db/dt);
+
+		if (dbdt > mdev->sync_conf.c_min_rate)
+			throttle = 1;
+	}
+	return throttle;
+}
+
+
+static int receive_DataRequest(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int digest_size)
 {
 	sector_t sector;
 	const sector_t capacity = drbd_get_capacity(mdev->this_bdev);
 	struct drbd_epoch_entry *e;
 	struct digest_info *di = NULL;
-	int size, digest_size;
+	int size, verb;
 	unsigned int fault_type;
-	struct p_block_req *p =
-		(struct p_block_req *)h;
-	const int brps = sizeof(*p)-sizeof(*h);
-
-	if (drbd_recv(mdev, h->payload, brps) != brps)
-		return FALSE;
+	struct p_block_req *p =	&mdev->data.rbuf.block_req;
 
 	sector = be64_to_cpu(p->sector);
 	size   = be32_to_cpu(p->blksize);
@@ -2046,12 +2098,31 @@
 	}
 
 	if (!get_ldev_if_state(mdev, D_UP_TO_DATE)) {
-		if (__ratelimit(&drbd_ratelimit_state))
+		verb = 1;
+		switch (cmd) {
+		case P_DATA_REQUEST:
+			drbd_send_ack_rp(mdev, P_NEG_DREPLY, p);
+			break;
+		case P_RS_DATA_REQUEST:
+		case P_CSUM_RS_REQUEST:
+		case P_OV_REQUEST:
+			drbd_send_ack_rp(mdev, P_NEG_RS_DREPLY , p);
+			break;
+		case P_OV_REPLY:
+			verb = 0;
+			dec_rs_pending(mdev);
+			drbd_send_ack_ex(mdev, P_OV_RESULT, sector, size, ID_IN_SYNC);
+			break;
+		default:
+			dev_err(DEV, "unexpected command (%s) in receive_DataRequest\n",
+				cmdname(cmd));
+		}
+		if (verb && __ratelimit(&drbd_ratelimit_state))
 			dev_err(DEV, "Can not satisfy peer's read request, "
 			    "no local data.\n");
-		drbd_send_ack_rp(mdev, h->command == P_DATA_REQUEST ? P_NEG_DREPLY :
-				 P_NEG_RS_DREPLY , p);
-		return drbd_drain_block(mdev, h->length - brps);
+
+		/* drain possibly payload */
+		return drbd_drain_block(mdev, digest_size);
 	}
 
 	/* GFP_NOIO, because we must not cause arbitrary write-out: in a DRBD
@@ -2063,31 +2134,21 @@
 		return FALSE;
 	}
 
-	switch (h->command) {
+	switch (cmd) {
 	case P_DATA_REQUEST:
 		e->w.cb = w_e_end_data_req;
 		fault_type = DRBD_FAULT_DT_RD;
-		break;
+		/* application IO, don't drbd_rs_begin_io */
+		goto submit;
+
 	case P_RS_DATA_REQUEST:
 		e->w.cb = w_e_end_rsdata_req;
 		fault_type = DRBD_FAULT_RS_RD;
-		/* Eventually this should become asynchronously. Currently it
-		 * blocks the whole receiver just to delay the reading of a
-		 * resync data block.
-		 * the drbd_work_queue mechanism is made for this...
-		 */
-		if (!drbd_rs_begin_io(mdev, sector)) {
-			/* we have been interrupted,
-			 * probably connection lost! */
-			D_ASSERT(signal_pending(current));
-			goto out_free_e;
-		}
 		break;
 
 	case P_OV_REPLY:
 	case P_CSUM_RS_REQUEST:
 		fault_type = DRBD_FAULT_RS_RD;
-		digest_size = h->length - brps ;
 		di = kmalloc(sizeof(*di) + digest_size, GFP_NOIO);
 		if (!di)
 			goto out_free_e;
@@ -2095,31 +2156,25 @@
 		di->digest_size = digest_size;
 		di->digest = (((char *)di)+sizeof(struct digest_info));
 
+		e->digest = di;
+		e->flags |= EE_HAS_DIGEST;
+
 		if (drbd_recv(mdev, di->digest, digest_size) != digest_size)
 			goto out_free_e;
 
-		e->block_id = (u64)(unsigned long)di;
-		if (h->command == P_CSUM_RS_REQUEST) {
+		if (cmd == P_CSUM_RS_REQUEST) {
 			D_ASSERT(mdev->agreed_pro_version >= 89);
 			e->w.cb = w_e_end_csum_rs_req;
-		} else if (h->command == P_OV_REPLY) {
+		} else if (cmd == P_OV_REPLY) {
 			e->w.cb = w_e_end_ov_reply;
 			dec_rs_pending(mdev);
-			break;
-		}
-
-		if (!drbd_rs_begin_io(mdev, sector)) {
-			/* we have been interrupted, probably connection lost! */
-			D_ASSERT(signal_pending(current));
-			goto out_free_e;
+			/* drbd_rs_begin_io done when we sent this request,
+			 * but accounting still needs to be done. */
+			goto submit_for_resync;
 		}
 		break;
 
 	case P_OV_REQUEST:
-		if (mdev->state.conn >= C_CONNECTED &&
-		    mdev->state.conn != C_VERIFY_T)
-			dev_warn(DEV, "ASSERT FAILED: got P_OV_REQUEST while being %s\n",
-				drbd_conn_str(mdev->state.conn));
 		if (mdev->ov_start_sector == ~(sector_t)0 &&
 		    mdev->agreed_pro_version >= 90) {
 			mdev->ov_start_sector = sector;
@@ -2130,37 +2185,63 @@
 		}
 		e->w.cb = w_e_end_ov_req;
 		fault_type = DRBD_FAULT_RS_RD;
-		/* Eventually this should become asynchronous. Currently it
-		 * blocks the whole receiver just to delay the reading of a
-		 * resync data block.
-		 * the drbd_work_queue mechanism is made for this...
-		 */
-		if (!drbd_rs_begin_io(mdev, sector)) {
-			/* we have been interrupted,
-			 * probably connection lost! */
-			D_ASSERT(signal_pending(current));
-			goto out_free_e;
-		}
 		break;
 
-
 	default:
 		dev_err(DEV, "unexpected command (%s) in receive_DataRequest\n",
-		    cmdname(h->command));
+		    cmdname(cmd));
 		fault_type = DRBD_FAULT_MAX;
+		goto out_free_e;
 	}
 
-	spin_lock_irq(&mdev->req_lock);
-	list_add(&e->w.list, &mdev->read_ee);
-	spin_unlock_irq(&mdev->req_lock);
+	/* Throttle, drbd_rs_begin_io and submit should become asynchronous
+	 * wrt the receiver, but it is not as straightforward as it may seem.
+	 * Various places in the resync start and stop logic assume resync
+	 * requests are processed in order, requeuing this on the worker thread
+	 * introduces a bunch of new code for synchronization between threads.
+	 *
+	 * Unlimited throttling before drbd_rs_begin_io may stall the resync
+	 * "forever", throttling after drbd_rs_begin_io will lock that extent
+	 * for application writes for the same time.  For now, just throttle
+	 * here, where the rest of the code expects the receiver to sleep for
+	 * a while, anyways.
+	 */
 
+	/* Throttle before drbd_rs_begin_io, as that locks out application IO;
+	 * this defers syncer requests for some time, before letting at least
+	 * on request through.  The resync controller on the receiving side
+	 * will adapt to the incoming rate accordingly.
+	 *
+	 * We cannot throttle here if remote is Primary/SyncTarget:
+	 * we would also throttle its application reads.
+	 * In that case, throttling is done on the SyncTarget only.
+	 */
+	if (mdev->state.peer != R_PRIMARY && drbd_rs_should_slow_down(mdev))
+		msleep(100);
+	if (drbd_rs_begin_io(mdev, e->sector))
+		goto out_free_e;
+
+submit_for_resync:
+	atomic_add(size >> 9, &mdev->rs_sect_ev);
+
+submit:
 	inc_unacked(mdev);
+	spin_lock_irq(&mdev->req_lock);
+	list_add_tail(&e->w.list, &mdev->read_ee);
+	spin_unlock_irq(&mdev->req_lock);
 
 	if (drbd_submit_ee(mdev, e, READ, fault_type) == 0)
 		return TRUE;
 
+	/* drbd_submit_ee currently fails for one reason only:
+	 * not being able to allocate enough bios.
+	 * Is dropping the connection going to help? */
+	spin_lock_irq(&mdev->req_lock);
+	list_del(&e->w.list);
+	spin_unlock_irq(&mdev->req_lock);
+	/* no drbd_rs_complete_io(), we are dropping the connection anyways */
+
 out_free_e:
-	kfree(di);
 	put_ldev(mdev);
 	drbd_free_ee(mdev, e);
 	return FALSE;
@@ -2699,20 +2780,13 @@
 	return 1;
 }
 
-static int receive_protocol(struct drbd_conf *mdev, struct p_header *h)
+static int receive_protocol(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
-	struct p_protocol *p = (struct p_protocol *)h;
-	int header_size, data_size;
+	struct p_protocol *p = &mdev->data.rbuf.protocol;
 	int p_proto, p_after_sb_0p, p_after_sb_1p, p_after_sb_2p;
 	int p_want_lose, p_two_primaries, cf;
 	char p_integrity_alg[SHARED_SECRET_MAX] = "";
 
-	header_size = sizeof(*p) - sizeof(*h);
-	data_size   = h->length  - header_size;
-
-	if (drbd_recv(mdev, h->payload, header_size) != header_size)
-		return FALSE;
-
 	p_proto		= be32_to_cpu(p->protocol);
 	p_after_sb_0p	= be32_to_cpu(p->after_sb_0p);
 	p_after_sb_1p	= be32_to_cpu(p->after_sb_1p);
@@ -2805,39 +2879,46 @@
 	return tfm;
 }
 
-static int receive_SyncParam(struct drbd_conf *mdev, struct p_header *h)
+static int receive_SyncParam(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int packet_size)
 {
 	int ok = TRUE;
-	struct p_rs_param_89 *p = (struct p_rs_param_89 *)h;
+	struct p_rs_param_95 *p = &mdev->data.rbuf.rs_param_95;
 	unsigned int header_size, data_size, exp_max_sz;
 	struct crypto_hash *verify_tfm = NULL;
 	struct crypto_hash *csums_tfm = NULL;
 	const int apv = mdev->agreed_pro_version;
+	int *rs_plan_s = NULL;
+	int fifo_size = 0;
 
 	exp_max_sz  = apv <= 87 ? sizeof(struct p_rs_param)
 		    : apv == 88 ? sizeof(struct p_rs_param)
 					+ SHARED_SECRET_MAX
-		    : /* 89 */    sizeof(struct p_rs_param_89);
+		    : apv <= 94 ? sizeof(struct p_rs_param_89)
+		    : /* apv >= 95 */ sizeof(struct p_rs_param_95);
 
-	if (h->length > exp_max_sz) {
+	if (packet_size > exp_max_sz) {
 		dev_err(DEV, "SyncParam packet too long: received %u, expected <= %u bytes\n",
-		    h->length, exp_max_sz);
+		    packet_size, exp_max_sz);
 		return FALSE;
 	}
 
 	if (apv <= 88) {
-		header_size = sizeof(struct p_rs_param) - sizeof(*h);
-		data_size   = h->length  - header_size;
-	} else /* apv >= 89 */ {
-		header_size = sizeof(struct p_rs_param_89) - sizeof(*h);
-		data_size   = h->length  - header_size;
+		header_size = sizeof(struct p_rs_param) - sizeof(struct p_header80);
+		data_size   = packet_size  - header_size;
+	} else if (apv <= 94) {
+		header_size = sizeof(struct p_rs_param_89) - sizeof(struct p_header80);
+		data_size   = packet_size  - header_size;
+		D_ASSERT(data_size == 0);
+	} else {
+		header_size = sizeof(struct p_rs_param_95) - sizeof(struct p_header80);
+		data_size   = packet_size  - header_size;
 		D_ASSERT(data_size == 0);
 	}
 
 	/* initialize verify_alg and csums_alg */
 	memset(p->verify_alg, 0, 2 * SHARED_SECRET_MAX);
 
-	if (drbd_recv(mdev, h->payload, header_size) != header_size)
+	if (drbd_recv(mdev, &p->head.payload, header_size) != header_size)
 		return FALSE;
 
 	mdev->sync_conf.rate	  = be32_to_cpu(p->rate);
@@ -2896,6 +2977,22 @@
 			}
 		}
 
+		if (apv > 94) {
+			mdev->sync_conf.rate	  = be32_to_cpu(p->rate);
+			mdev->sync_conf.c_plan_ahead = be32_to_cpu(p->c_plan_ahead);
+			mdev->sync_conf.c_delay_target = be32_to_cpu(p->c_delay_target);
+			mdev->sync_conf.c_fill_target = be32_to_cpu(p->c_fill_target);
+			mdev->sync_conf.c_max_rate = be32_to_cpu(p->c_max_rate);
+
+			fifo_size = (mdev->sync_conf.c_plan_ahead * 10 * SLEEP_TIME) / HZ;
+			if (fifo_size != mdev->rs_plan_s.size && fifo_size > 0) {
+				rs_plan_s   = kzalloc(sizeof(int) * fifo_size, GFP_KERNEL);
+				if (!rs_plan_s) {
+					dev_err(DEV, "kmalloc of fifo_buffer failed");
+					goto disconnect;
+				}
+			}
+		}
 
 		spin_lock(&mdev->peer_seq_lock);
 		/* lock against drbd_nl_syncer_conf() */
@@ -2913,6 +3010,12 @@
 			mdev->csums_tfm = csums_tfm;
 			dev_info(DEV, "using csums-alg: \"%s\"\n", p->csums_alg);
 		}
+		if (fifo_size != mdev->rs_plan_s.size) {
+			kfree(mdev->rs_plan_s.values);
+			mdev->rs_plan_s.values = rs_plan_s;
+			mdev->rs_plan_s.size   = fifo_size;
+			mdev->rs_planed = 0;
+		}
 		spin_unlock(&mdev->peer_seq_lock);
 	}
 
@@ -2946,19 +3049,15 @@
 		     (unsigned long long)a, (unsigned long long)b);
 }
 
-static int receive_sizes(struct drbd_conf *mdev, struct p_header *h)
+static int receive_sizes(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
-	struct p_sizes *p = (struct p_sizes *)h;
+	struct p_sizes *p = &mdev->data.rbuf.sizes;
 	enum determine_dev_size dd = unchanged;
 	unsigned int max_seg_s;
 	sector_t p_size, p_usize, my_usize;
 	int ldsc = 0; /* local disk size changed */
 	enum dds_flags ddsf;
 
-	ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE;
-	if (drbd_recv(mdev, h->payload, h->length) != h->length)
-		return FALSE;
-
 	p_size = be64_to_cpu(p->d_size);
 	p_usize = be64_to_cpu(p->u_size);
 
@@ -2972,7 +3071,6 @@
 	 * we still need to figure out whether we accept that. */
 	mdev->p_size = p_size;
 
-#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
 	if (get_ldev(mdev)) {
 		warn_if_differ_considerably(mdev, "lower level device sizes",
 			   p_size, drbd_get_max_capacity(mdev->ldev));
@@ -3029,6 +3127,8 @@
 
 		if (mdev->agreed_pro_version < 94)
 			max_seg_s = be32_to_cpu(p->max_segment_size);
+		else if (mdev->agreed_pro_version == 94)
+			max_seg_s = DRBD_MAX_SIZE_H80_PACKET;
 		else /* drbd 8.3.8 onwards */
 			max_seg_s = DRBD_MAX_SEGMENT_SIZE;
 
@@ -3062,16 +3162,12 @@
 	return TRUE;
 }
 
-static int receive_uuids(struct drbd_conf *mdev, struct p_header *h)
+static int receive_uuids(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
-	struct p_uuids *p = (struct p_uuids *)h;
+	struct p_uuids *p = &mdev->data.rbuf.uuids;
 	u64 *p_uuid;
 	int i;
 
-	ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE;
-	if (drbd_recv(mdev, h->payload, h->length) != h->length)
-		return FALSE;
-
 	p_uuid = kmalloc(sizeof(u64)*UI_EXTENDED_SIZE, GFP_NOIO);
 
 	for (i = UI_CURRENT; i < UI_EXTENDED_SIZE; i++)
@@ -3107,6 +3203,11 @@
 			drbd_md_sync(mdev);
 		}
 		put_ldev(mdev);
+	} else if (mdev->state.disk < D_INCONSISTENT &&
+		   mdev->state.role == R_PRIMARY) {
+		/* I am a diskless primary, the peer just created a new current UUID
+		   for me. */
+		drbd_set_ed_uuid(mdev, p_uuid[UI_CURRENT]);
 	}
 
 	/* Before we test for the disk state, we should wait until an eventually
@@ -3150,16 +3251,12 @@
 	return ms;
 }
 
-static int receive_req_state(struct drbd_conf *mdev, struct p_header *h)
+static int receive_req_state(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
-	struct p_req_state *p = (struct p_req_state *)h;
+	struct p_req_state *p = &mdev->data.rbuf.req_state;
 	union drbd_state mask, val;
 	int rv;
 
-	ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE;
-	if (drbd_recv(mdev, h->payload, h->length) != h->length)
-		return FALSE;
-
 	mask.i = be32_to_cpu(p->mask);
 	val.i = be32_to_cpu(p->val);
 
@@ -3180,20 +3277,14 @@
 	return TRUE;
 }
 
-static int receive_state(struct drbd_conf *mdev, struct p_header *h)
+static int receive_state(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
-	struct p_state *p = (struct p_state *)h;
-	enum drbd_conns nconn, oconn;
-	union drbd_state ns, peer_state;
+	struct p_state *p = &mdev->data.rbuf.state;
+	union drbd_state os, ns, peer_state;
 	enum drbd_disk_state real_peer_disk;
+	enum chg_state_flags cs_flags;
 	int rv;
 
-	ERR_IF(h->length != (sizeof(*p)-sizeof(*h)))
-		return FALSE;
-
-	if (drbd_recv(mdev, h->payload, h->length) != h->length)
-		return FALSE;
-
 	peer_state.i = be32_to_cpu(p->state);
 
 	real_peer_disk = peer_state.disk;
@@ -3204,38 +3295,72 @@
 
 	spin_lock_irq(&mdev->req_lock);
  retry:
-	oconn = nconn = mdev->state.conn;
+	os = ns = mdev->state;
 	spin_unlock_irq(&mdev->req_lock);
 
-	if (nconn == C_WF_REPORT_PARAMS)
-		nconn = C_CONNECTED;
+	/* peer says his disk is uptodate, while we think it is inconsistent,
+	 * and this happens while we think we have a sync going on. */
+	if (os.pdsk == D_INCONSISTENT && real_peer_disk == D_UP_TO_DATE &&
+	    os.conn > C_CONNECTED && os.disk == D_UP_TO_DATE) {
+		/* If we are (becoming) SyncSource, but peer is still in sync
+		 * preparation, ignore its uptodate-ness to avoid flapping, it
+		 * will change to inconsistent once the peer reaches active
+		 * syncing states.
+		 * It may have changed syncer-paused flags, however, so we
+		 * cannot ignore this completely. */
+		if (peer_state.conn > C_CONNECTED &&
+		    peer_state.conn < C_SYNC_SOURCE)
+			real_peer_disk = D_INCONSISTENT;
+
+		/* if peer_state changes to connected at the same time,
+		 * it explicitly notifies us that it finished resync.
+		 * Maybe we should finish it up, too? */
+		else if (os.conn >= C_SYNC_SOURCE &&
+			 peer_state.conn == C_CONNECTED) {
+			if (drbd_bm_total_weight(mdev) <= mdev->rs_failed)
+				drbd_resync_finished(mdev);
+			return TRUE;
+		}
+	}
+
+	/* peer says his disk is inconsistent, while we think it is uptodate,
+	 * and this happens while the peer still thinks we have a sync going on,
+	 * but we think we are already done with the sync.
+	 * We ignore this to avoid flapping pdsk.
+	 * This should not happen, if the peer is a recent version of drbd. */
+	if (os.pdsk == D_UP_TO_DATE && real_peer_disk == D_INCONSISTENT &&
+	    os.conn == C_CONNECTED && peer_state.conn > C_SYNC_SOURCE)
+		real_peer_disk = D_UP_TO_DATE;
+
+	if (ns.conn == C_WF_REPORT_PARAMS)
+		ns.conn = C_CONNECTED;
 
 	if (mdev->p_uuid && peer_state.disk >= D_NEGOTIATING &&
 	    get_ldev_if_state(mdev, D_NEGOTIATING)) {
 		int cr; /* consider resync */
 
 		/* if we established a new connection */
-		cr  = (oconn < C_CONNECTED);
+		cr  = (os.conn < C_CONNECTED);
 		/* if we had an established connection
 		 * and one of the nodes newly attaches a disk */
-		cr |= (oconn == C_CONNECTED &&
+		cr |= (os.conn == C_CONNECTED &&
 		       (peer_state.disk == D_NEGOTIATING ||
-			mdev->state.disk == D_NEGOTIATING));
+			os.disk == D_NEGOTIATING));
 		/* if we have both been inconsistent, and the peer has been
 		 * forced to be UpToDate with --overwrite-data */
 		cr |= test_bit(CONSIDER_RESYNC, &mdev->flags);
 		/* if we had been plain connected, and the admin requested to
 		 * start a sync by "invalidate" or "invalidate-remote" */
-		cr |= (oconn == C_CONNECTED &&
+		cr |= (os.conn == C_CONNECTED &&
 				(peer_state.conn >= C_STARTING_SYNC_S &&
 				 peer_state.conn <= C_WF_BITMAP_T));
 
 		if (cr)
-			nconn = drbd_sync_handshake(mdev, peer_state.role, real_peer_disk);
+			ns.conn = drbd_sync_handshake(mdev, peer_state.role, real_peer_disk);
 
 		put_ldev(mdev);
-		if (nconn == C_MASK) {
-			nconn = C_CONNECTED;
+		if (ns.conn == C_MASK) {
+			ns.conn = C_CONNECTED;
 			if (mdev->state.disk == D_NEGOTIATING) {
 				drbd_force_state(mdev, NS(disk, D_DISKLESS));
 			} else if (peer_state.disk == D_NEGOTIATING) {
@@ -3245,7 +3370,7 @@
 			} else {
 				if (test_and_clear_bit(CONN_DRY_RUN, &mdev->flags))
 					return FALSE;
-				D_ASSERT(oconn == C_WF_REPORT_PARAMS);
+				D_ASSERT(os.conn == C_WF_REPORT_PARAMS);
 				drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
 				return FALSE;
 			}
@@ -3253,18 +3378,28 @@
 	}
 
 	spin_lock_irq(&mdev->req_lock);
-	if (mdev->state.conn != oconn)
+	if (mdev->state.i != os.i)
 		goto retry;
 	clear_bit(CONSIDER_RESYNC, &mdev->flags);
-	ns.i = mdev->state.i;
-	ns.conn = nconn;
 	ns.peer = peer_state.role;
 	ns.pdsk = real_peer_disk;
 	ns.peer_isp = (peer_state.aftr_isp | peer_state.user_isp);
-	if ((nconn == C_CONNECTED || nconn == C_WF_BITMAP_S) && ns.disk == D_NEGOTIATING)
+	if ((ns.conn == C_CONNECTED || ns.conn == C_WF_BITMAP_S) && ns.disk == D_NEGOTIATING)
 		ns.disk = mdev->new_state_tmp.disk;
-
-	rv = _drbd_set_state(mdev, ns, CS_VERBOSE | CS_HARD, NULL);
+	cs_flags = CS_VERBOSE + (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED ? 0 : CS_HARD);
+	if (ns.pdsk == D_CONSISTENT && is_susp(ns) && ns.conn == C_CONNECTED && os.conn < C_CONNECTED &&
+	    test_bit(NEW_CUR_UUID, &mdev->flags)) {
+		/* Do not allow tl_restart(resend) for a rebooted peer. We can only allow this
+		   for temporal network outages! */
+		spin_unlock_irq(&mdev->req_lock);
+		dev_err(DEV, "Aborting Connect, can not thaw IO with an only Consistent peer\n");
+		tl_clear(mdev);
+		drbd_uuid_new_current(mdev);
+		clear_bit(NEW_CUR_UUID, &mdev->flags);
+		drbd_force_state(mdev, NS2(conn, C_PROTOCOL_ERROR, susp, 0));
+		return FALSE;
+	}
+	rv = _drbd_set_state(mdev, ns, cs_flags, NULL);
 	ns = mdev->state;
 	spin_unlock_irq(&mdev->req_lock);
 
@@ -3273,8 +3408,8 @@
 		return FALSE;
 	}
 
-	if (oconn > C_WF_REPORT_PARAMS) {
-		if (nconn > C_CONNECTED && peer_state.conn <= C_CONNECTED &&
+	if (os.conn > C_WF_REPORT_PARAMS) {
+		if (ns.conn > C_CONNECTED && peer_state.conn <= C_CONNECTED &&
 		    peer_state.disk != D_NEGOTIATING ) {
 			/* we want resync, peer has not yet decided to sync... */
 			/* Nowadays only used when forcing a node into primary role and
@@ -3291,9 +3426,9 @@
 	return TRUE;
 }
 
-static int receive_sync_uuid(struct drbd_conf *mdev, struct p_header *h)
+static int receive_sync_uuid(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
-	struct p_rs_uuid *p = (struct p_rs_uuid *)h;
+	struct p_rs_uuid *p = &mdev->data.rbuf.rs_uuid;
 
 	wait_event(mdev->misc_wait,
 		   mdev->state.conn == C_WF_SYNC_UUID ||
@@ -3302,10 +3437,6 @@
 
 	/* D_ASSERT( mdev->state.conn == C_WF_SYNC_UUID ); */
 
-	ERR_IF(h->length != (sizeof(*p)-sizeof(*h))) return FALSE;
-	if (drbd_recv(mdev, h->payload, h->length) != h->length)
-		return FALSE;
-
 	/* Here the _drbd_uuid_ functions are right, current should
 	   _not_ be rotated into the history */
 	if (get_ldev_if_state(mdev, D_NEGOTIATING)) {
@@ -3324,14 +3455,14 @@
 enum receive_bitmap_ret { OK, DONE, FAILED };
 
 static enum receive_bitmap_ret
-receive_bitmap_plain(struct drbd_conf *mdev, struct p_header *h,
-	unsigned long *buffer, struct bm_xfer_ctx *c)
+receive_bitmap_plain(struct drbd_conf *mdev, unsigned int data_size,
+		     unsigned long *buffer, struct bm_xfer_ctx *c)
 {
 	unsigned num_words = min_t(size_t, BM_PACKET_WORDS, c->bm_words - c->word_offset);
 	unsigned want = num_words * sizeof(long);
 
-	if (want != h->length) {
-		dev_err(DEV, "%s:want (%u) != h->length (%u)\n", __func__, want, h->length);
+	if (want != data_size) {
+		dev_err(DEV, "%s:want (%u) != data_size (%u)\n", __func__, want, data_size);
 		return FAILED;
 	}
 	if (want == 0)
@@ -3360,7 +3491,7 @@
 	u64 tmp;
 	unsigned long s = c->bit_offset;
 	unsigned long e;
-	int len = p->head.length - (sizeof(*p) - sizeof(p->head));
+	int len = be16_to_cpu(p->head.length) - (sizeof(*p) - sizeof(p->head));
 	int toggle = DCBP_get_start(p);
 	int have;
 	int bits;
@@ -3429,7 +3560,7 @@
 		const char *direction, struct bm_xfer_ctx *c)
 {
 	/* what would it take to transfer it "plaintext" */
-	unsigned plain = sizeof(struct p_header) *
+	unsigned plain = sizeof(struct p_header80) *
 		((c->bm_words+BM_PACKET_WORDS-1)/BM_PACKET_WORDS+1)
 		+ c->bm_words * sizeof(long);
 	unsigned total = c->bytes[0] + c->bytes[1];
@@ -3467,12 +3598,13 @@
    in order to be agnostic to the 32 vs 64 bits issue.
 
    returns 0 on failure, 1 if we successfully received it. */
-static int receive_bitmap(struct drbd_conf *mdev, struct p_header *h)
+static int receive_bitmap(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
 	struct bm_xfer_ctx c;
 	void *buffer;
 	enum receive_bitmap_ret ret;
 	int ok = FALSE;
+	struct p_header80 *h = &mdev->data.rbuf.header.h80;
 
 	wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt));
 
@@ -3492,39 +3624,39 @@
 	};
 
 	do {
-		if (h->command == P_BITMAP) {
-			ret = receive_bitmap_plain(mdev, h, buffer, &c);
-		} else if (h->command == P_COMPRESSED_BITMAP) {
+		if (cmd == P_BITMAP) {
+			ret = receive_bitmap_plain(mdev, data_size, buffer, &c);
+		} else if (cmd == P_COMPRESSED_BITMAP) {
 			/* MAYBE: sanity check that we speak proto >= 90,
 			 * and the feature is enabled! */
 			struct p_compressed_bm *p;
 
-			if (h->length > BM_PACKET_PAYLOAD_BYTES) {
+			if (data_size > BM_PACKET_PAYLOAD_BYTES) {
 				dev_err(DEV, "ReportCBitmap packet too large\n");
 				goto out;
 			}
 			/* use the page buff */
 			p = buffer;
 			memcpy(p, h, sizeof(*h));
-			if (drbd_recv(mdev, p->head.payload, h->length) != h->length)
+			if (drbd_recv(mdev, p->head.payload, data_size) != data_size)
 				goto out;
-			if (p->head.length <= (sizeof(*p) - sizeof(p->head))) {
-				dev_err(DEV, "ReportCBitmap packet too small (l:%u)\n", p->head.length);
+			if (data_size <= (sizeof(*p) - sizeof(p->head))) {
+				dev_err(DEV, "ReportCBitmap packet too small (l:%u)\n", data_size);
 				return FAILED;
 			}
 			ret = decode_bitmap_c(mdev, p, &c);
 		} else {
-			dev_warn(DEV, "receive_bitmap: h->command neither ReportBitMap nor ReportCBitMap (is 0x%x)", h->command);
+			dev_warn(DEV, "receive_bitmap: cmd neither ReportBitMap nor ReportCBitMap (is 0x%x)", cmd);
 			goto out;
 		}
 
-		c.packets[h->command == P_BITMAP]++;
-		c.bytes[h->command == P_BITMAP] += sizeof(struct p_header) + h->length;
+		c.packets[cmd == P_BITMAP]++;
+		c.bytes[cmd == P_BITMAP] += sizeof(struct p_header80) + data_size;
 
 		if (ret != OK)
 			break;
 
-		if (!drbd_recv_header(mdev, h))
+		if (!drbd_recv_header(mdev, &cmd, &data_size))
 			goto out;
 	} while (ret == OK);
 	if (ret == FAILED)
@@ -3555,17 +3687,16 @@
 	return ok;
 }
 
-static int receive_skip_(struct drbd_conf *mdev, struct p_header *h, int silent)
+static int receive_skip(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
 	/* TODO zero copy sink :) */
 	static char sink[128];
 	int size, want, r;
 
-	if (!silent)
-		dev_warn(DEV, "skipping unknown optional packet type %d, l: %d!\n",
-		     h->command, h->length);
+	dev_warn(DEV, "skipping unknown optional packet type %d, l: %d!\n",
+		 cmd, data_size);
 
-	size = h->length;
+	size = data_size;
 	while (size > 0) {
 		want = min_t(int, size, sizeof(sink));
 		r = drbd_recv(mdev, sink, want);
@@ -3575,17 +3706,7 @@
 	return size == 0;
 }
 
-static int receive_skip(struct drbd_conf *mdev, struct p_header *h)
-{
-	return receive_skip_(mdev, h, 0);
-}
-
-static int receive_skip_silent(struct drbd_conf *mdev, struct p_header *h)
-{
-	return receive_skip_(mdev, h, 1);
-}
-
-static int receive_UnplugRemote(struct drbd_conf *mdev, struct p_header *h)
+static int receive_UnplugRemote(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
 	if (mdev->state.disk >= D_INCONSISTENT)
 		drbd_kick_lo(mdev);
@@ -3597,108 +3718,94 @@
 	return TRUE;
 }
 
-typedef int (*drbd_cmd_handler_f)(struct drbd_conf *, struct p_header *);
+typedef int (*drbd_cmd_handler_f)(struct drbd_conf *, enum drbd_packets cmd, unsigned int to_receive);
 
-static drbd_cmd_handler_f drbd_default_handler[] = {
-	[P_DATA]	    = receive_Data,
-	[P_DATA_REPLY]	    = receive_DataReply,
-	[P_RS_DATA_REPLY]   = receive_RSDataReply,
-	[P_BARRIER]	    = receive_Barrier,
-	[P_BITMAP]	    = receive_bitmap,
-	[P_COMPRESSED_BITMAP]    = receive_bitmap,
-	[P_UNPLUG_REMOTE]   = receive_UnplugRemote,
-	[P_DATA_REQUEST]    = receive_DataRequest,
-	[P_RS_DATA_REQUEST] = receive_DataRequest,
-	[P_SYNC_PARAM]	    = receive_SyncParam,
-	[P_SYNC_PARAM89]	   = receive_SyncParam,
-	[P_PROTOCOL]        = receive_protocol,
-	[P_UUIDS]	    = receive_uuids,
-	[P_SIZES]	    = receive_sizes,
-	[P_STATE]	    = receive_state,
-	[P_STATE_CHG_REQ]   = receive_req_state,
-	[P_SYNC_UUID]       = receive_sync_uuid,
-	[P_OV_REQUEST]      = receive_DataRequest,
-	[P_OV_REPLY]        = receive_DataRequest,
-	[P_CSUM_RS_REQUEST]    = receive_DataRequest,
-	[P_DELAY_PROBE]     = receive_skip_silent,
-	/* anything missing from this table is in
-	 * the asender_tbl, see get_asender_cmd */
-	[P_MAX_CMD]	    = NULL,
+struct data_cmd {
+	int expect_payload;
+	size_t pkt_size;
+	drbd_cmd_handler_f function;
 };
 
-static drbd_cmd_handler_f *drbd_cmd_handler = drbd_default_handler;
-static drbd_cmd_handler_f *drbd_opt_cmd_handler;
+static struct data_cmd drbd_cmd_handler[] = {
+	[P_DATA]	    = { 1, sizeof(struct p_data), receive_Data },
+	[P_DATA_REPLY]	    = { 1, sizeof(struct p_data), receive_DataReply },
+	[P_RS_DATA_REPLY]   = { 1, sizeof(struct p_data), receive_RSDataReply } ,
+	[P_BARRIER]	    = { 0, sizeof(struct p_barrier), receive_Barrier } ,
+	[P_BITMAP]	    = { 1, sizeof(struct p_header80), receive_bitmap } ,
+	[P_COMPRESSED_BITMAP] = { 1, sizeof(struct p_header80), receive_bitmap } ,
+	[P_UNPLUG_REMOTE]   = { 0, sizeof(struct p_header80), receive_UnplugRemote },
+	[P_DATA_REQUEST]    = { 0, sizeof(struct p_block_req), receive_DataRequest },
+	[P_RS_DATA_REQUEST] = { 0, sizeof(struct p_block_req), receive_DataRequest },
+	[P_SYNC_PARAM]	    = { 1, sizeof(struct p_header80), receive_SyncParam },
+	[P_SYNC_PARAM89]    = { 1, sizeof(struct p_header80), receive_SyncParam },
+	[P_PROTOCOL]        = { 1, sizeof(struct p_protocol), receive_protocol },
+	[P_UUIDS]	    = { 0, sizeof(struct p_uuids), receive_uuids },
+	[P_SIZES]	    = { 0, sizeof(struct p_sizes), receive_sizes },
+	[P_STATE]	    = { 0, sizeof(struct p_state), receive_state },
+	[P_STATE_CHG_REQ]   = { 0, sizeof(struct p_req_state), receive_req_state },
+	[P_SYNC_UUID]       = { 0, sizeof(struct p_rs_uuid), receive_sync_uuid },
+	[P_OV_REQUEST]      = { 0, sizeof(struct p_block_req), receive_DataRequest },
+	[P_OV_REPLY]        = { 1, sizeof(struct p_block_req), receive_DataRequest },
+	[P_CSUM_RS_REQUEST] = { 1, sizeof(struct p_block_req), receive_DataRequest },
+	[P_DELAY_PROBE]     = { 0, sizeof(struct p_delay_probe93), receive_skip },
+	/* anything missing from this table is in
+	 * the asender_tbl, see get_asender_cmd */
+	[P_MAX_CMD]	    = { 0, 0, NULL },
+};
+
+/* All handler functions that expect a sub-header get that sub-heder in
+   mdev->data.rbuf.header.head.payload.
+
+   Usually in mdev->data.rbuf.header.head the callback can find the usual
+   p_header, but they may not rely on that. Since there is also p_header95 !
+ */
 
 static void drbdd(struct drbd_conf *mdev)
 {
-	drbd_cmd_handler_f handler;
-	struct p_header *header = &mdev->data.rbuf.header;
+	union p_header *header = &mdev->data.rbuf.header;
+	unsigned int packet_size;
+	enum drbd_packets cmd;
+	size_t shs; /* sub header size */
+	int rv;
 
 	while (get_t_state(&mdev->receiver) == Running) {
 		drbd_thread_current_set_cpu(mdev);
-		if (!drbd_recv_header(mdev, header)) {
-			drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
-			break;
+		if (!drbd_recv_header(mdev, &cmd, &packet_size))
+			goto err_out;
+
+		if (unlikely(cmd >= P_MAX_CMD || !drbd_cmd_handler[cmd].function)) {
+			dev_err(DEV, "unknown packet type %d, l: %d!\n", cmd, packet_size);
+			goto err_out;
 		}
 
-		if (header->command < P_MAX_CMD)
-			handler = drbd_cmd_handler[header->command];
-		else if (P_MAY_IGNORE < header->command
-		     && header->command < P_MAX_OPT_CMD)
-			handler = drbd_opt_cmd_handler[header->command-P_MAY_IGNORE];
-		else if (header->command > P_MAX_OPT_CMD)
-			handler = receive_skip;
-		else
-			handler = NULL;
-
-		if (unlikely(!handler)) {
-			dev_err(DEV, "unknown packet type %d, l: %d!\n",
-			    header->command, header->length);
-			drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
-			break;
+		shs = drbd_cmd_handler[cmd].pkt_size - sizeof(union p_header);
+		rv = drbd_recv(mdev, &header->h80.payload, shs);
+		if (unlikely(rv != shs)) {
+			dev_err(DEV, "short read while reading sub header: rv=%d\n", rv);
+			goto err_out;
 		}
-		if (unlikely(!handler(mdev, header))) {
+
+		if (packet_size - shs > 0 && !drbd_cmd_handler[cmd].expect_payload) {
+			dev_err(DEV, "No payload expected %s l:%d\n", cmdname(cmd), packet_size);
+			goto err_out;
+		}
+
+		rv = drbd_cmd_handler[cmd].function(mdev, cmd, packet_size - shs);
+
+		if (unlikely(!rv)) {
 			dev_err(DEV, "error receiving %s, l: %d!\n",
-			    cmdname(header->command), header->length);
-			drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
-			break;
+			    cmdname(cmd), packet_size);
+			goto err_out;
 		}
 	}
-}
 
-static void drbd_fail_pending_reads(struct drbd_conf *mdev)
-{
-	struct hlist_head *slot;
-	struct hlist_node *pos;
-	struct hlist_node *tmp;
-	struct drbd_request *req;
-	int i;
-
-	/*
-	 * Application READ requests
-	 */
-	spin_lock_irq(&mdev->req_lock);
-	for (i = 0; i < APP_R_HSIZE; i++) {
-		slot = mdev->app_reads_hash+i;
-		hlist_for_each_entry_safe(req, pos, tmp, slot, colision) {
-			/* it may (but should not any longer!)
-			 * be on the work queue; if that assert triggers,
-			 * we need to also grab the
-			 * spin_lock_irq(&mdev->data.work.q_lock);
-			 * and list_del_init here. */
-			D_ASSERT(list_empty(&req->w.list));
-			/* It would be nice to complete outside of spinlock.
-			 * But this is easier for now. */
-			_req_mod(req, connection_lost_while_pending);
-		}
+	if (0) {
+	err_out:
+		drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
 	}
-	for (i = 0; i < APP_R_HSIZE; i++)
-		if (!hlist_empty(mdev->app_reads_hash+i))
-			dev_warn(DEV, "ASSERT FAILED: app_reads_hash[%d].first: "
-				"%p, should be NULL\n", i, mdev->app_reads_hash[i].first);
-
-	memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *));
-	spin_unlock_irq(&mdev->req_lock);
+	/* If we leave here, we probably want to update at least the
+	 * "Connected" indicator on stable storage. Do so explicitly here. */
+	drbd_md_sync(mdev);
 }
 
 void drbd_flush_workqueue(struct drbd_conf *mdev)
@@ -3711,6 +3818,36 @@
 	wait_for_completion(&barr.done);
 }
 
+void drbd_free_tl_hash(struct drbd_conf *mdev)
+{
+	struct hlist_head *h;
+
+	spin_lock_irq(&mdev->req_lock);
+
+	if (!mdev->tl_hash || mdev->state.conn != C_STANDALONE) {
+		spin_unlock_irq(&mdev->req_lock);
+		return;
+	}
+	/* paranoia code */
+	for (h = mdev->ee_hash; h < mdev->ee_hash + mdev->ee_hash_s; h++)
+		if (h->first)
+			dev_err(DEV, "ASSERT FAILED ee_hash[%u].first == %p, expected NULL\n",
+				(int)(h - mdev->ee_hash), h->first);
+	kfree(mdev->ee_hash);
+	mdev->ee_hash = NULL;
+	mdev->ee_hash_s = 0;
+
+	/* paranoia code */
+	for (h = mdev->tl_hash; h < mdev->tl_hash + mdev->tl_hash_s; h++)
+		if (h->first)
+			dev_err(DEV, "ASSERT FAILED tl_hash[%u] == %p, expected NULL\n",
+				(int)(h - mdev->tl_hash), h->first);
+	kfree(mdev->tl_hash);
+	mdev->tl_hash = NULL;
+	mdev->tl_hash_s = 0;
+	spin_unlock_irq(&mdev->req_lock);
+}
+
 static void drbd_disconnect(struct drbd_conf *mdev)
 {
 	enum drbd_fencing_p fp;
@@ -3728,6 +3865,7 @@
 	drbd_thread_stop(&mdev->asender);
 	drbd_free_sock(mdev);
 
+	/* wait for current activity to cease. */
 	spin_lock_irq(&mdev->req_lock);
 	_drbd_wait_ee_list_empty(mdev, &mdev->active_ee);
 	_drbd_wait_ee_list_empty(mdev, &mdev->sync_ee);
@@ -3752,7 +3890,6 @@
 
 	/* make sure syncer is stopped and w_resume_next_sg queued */
 	del_timer_sync(&mdev->resync_timer);
-	set_bit(STOP_SYNC_TIMER, &mdev->flags);
 	resync_timer_fn((unsigned long)mdev);
 
 	/* wait for all w_e_end_data_req, w_e_end_rsdata_req, w_send_barrier,
@@ -3767,11 +3904,9 @@
 	kfree(mdev->p_uuid);
 	mdev->p_uuid = NULL;
 
-	if (!mdev->state.susp)
+	if (!is_susp(mdev->state))
 		tl_clear(mdev);
 
-	drbd_fail_pending_reads(mdev);
-
 	dev_info(DEV, "Connection closed\n");
 
 	drbd_md_sync(mdev);
@@ -3782,12 +3917,8 @@
 		put_ldev(mdev);
 	}
 
-	if (mdev->state.role == R_PRIMARY) {
-		if (fp >= FP_RESOURCE && mdev->state.pdsk >= D_UNKNOWN) {
-			enum drbd_disk_state nps = drbd_try_outdate_peer(mdev);
-			drbd_request_state(mdev, NS(pdsk, nps));
-		}
-	}
+	if (mdev->state.role == R_PRIMARY && fp >= FP_RESOURCE && mdev->state.pdsk >= D_UNKNOWN)
+		drbd_try_outdate_peer_async(mdev);
 
 	spin_lock_irq(&mdev->req_lock);
 	os = mdev->state;
@@ -3800,32 +3931,14 @@
 	spin_unlock_irq(&mdev->req_lock);
 
 	if (os.conn == C_DISCONNECTING) {
-		struct hlist_head *h;
-		wait_event(mdev->misc_wait, atomic_read(&mdev->net_cnt) == 0);
+		wait_event(mdev->net_cnt_wait, atomic_read(&mdev->net_cnt) == 0);
 
-		/* we must not free the tl_hash
-		 * while application io is still on the fly */
-		wait_event(mdev->misc_wait, atomic_read(&mdev->ap_bio_cnt) == 0);
-
-		spin_lock_irq(&mdev->req_lock);
-		/* paranoia code */
-		for (h = mdev->ee_hash; h < mdev->ee_hash + mdev->ee_hash_s; h++)
-			if (h->first)
-				dev_err(DEV, "ASSERT FAILED ee_hash[%u].first == %p, expected NULL\n",
-						(int)(h - mdev->ee_hash), h->first);
-		kfree(mdev->ee_hash);
-		mdev->ee_hash = NULL;
-		mdev->ee_hash_s = 0;
-
-		/* paranoia code */
-		for (h = mdev->tl_hash; h < mdev->tl_hash + mdev->tl_hash_s; h++)
-			if (h->first)
-				dev_err(DEV, "ASSERT FAILED tl_hash[%u] == %p, expected NULL\n",
-						(int)(h - mdev->tl_hash), h->first);
-		kfree(mdev->tl_hash);
-		mdev->tl_hash = NULL;
-		mdev->tl_hash_s = 0;
-		spin_unlock_irq(&mdev->req_lock);
+		if (!is_susp(mdev->state)) {
+			/* we must not free the tl_hash
+			 * while application io is still on the fly */
+			wait_event(mdev->misc_wait, !atomic_read(&mdev->ap_bio_cnt));
+			drbd_free_tl_hash(mdev);
+		}
 
 		crypto_free_hash(mdev->cram_hmac_tfm);
 		mdev->cram_hmac_tfm = NULL;
@@ -3845,6 +3958,9 @@
 	i = drbd_release_ee(mdev, &mdev->net_ee);
 	if (i)
 		dev_info(DEV, "net_ee not empty, killed %u entries\n", i);
+	i = atomic_read(&mdev->pp_in_use_by_net);
+	if (i)
+		dev_info(DEV, "pp_in_use_by_net = %d, expected 0\n", i);
 	i = atomic_read(&mdev->pp_in_use);
 	if (i)
 		dev_info(DEV, "pp_in_use = %d, expected 0\n", i);
@@ -3888,7 +4004,7 @@
 	p->protocol_min = cpu_to_be32(PRO_VERSION_MIN);
 	p->protocol_max = cpu_to_be32(PRO_VERSION_MAX);
 	ok = _drbd_send_cmd( mdev, mdev->data.socket, P_HAND_SHAKE,
-			     (struct p_header *)p, sizeof(*p), 0 );
+			     (struct p_header80 *)p, sizeof(*p), 0 );
 	mutex_unlock(&mdev->data.mutex);
 	return ok;
 }
@@ -3904,27 +4020,28 @@
 {
 	/* ASSERT current == mdev->receiver ... */
 	struct p_handshake *p = &mdev->data.rbuf.handshake;
-	const int expect = sizeof(struct p_handshake)
-			  -sizeof(struct p_header);
+	const int expect = sizeof(struct p_handshake) - sizeof(struct p_header80);
+	unsigned int length;
+	enum drbd_packets cmd;
 	int rv;
 
 	rv = drbd_send_handshake(mdev);
 	if (!rv)
 		return 0;
 
-	rv = drbd_recv_header(mdev, &p->head);
+	rv = drbd_recv_header(mdev, &cmd, &length);
 	if (!rv)
 		return 0;
 
-	if (p->head.command != P_HAND_SHAKE) {
+	if (cmd != P_HAND_SHAKE) {
 		dev_err(DEV, "expected HandShake packet, received: %s (0x%04x)\n",
-		     cmdname(p->head.command), p->head.command);
+		     cmdname(cmd), cmd);
 		return -1;
 	}
 
-	if (p->head.length != expect) {
+	if (length != expect) {
 		dev_err(DEV, "expected HandShake length: %u, received: %u\n",
-		     expect, p->head.length);
+		     expect, length);
 		return -1;
 	}
 
@@ -3982,10 +4099,11 @@
 	char *response = NULL;
 	char *right_response = NULL;
 	char *peers_ch = NULL;
-	struct p_header p;
 	unsigned int key_len = strlen(mdev->net_conf->shared_secret);
 	unsigned int resp_size;
 	struct hash_desc desc;
+	enum drbd_packets cmd;
+	unsigned int length;
 	int rv;
 
 	desc.tfm = mdev->cram_hmac_tfm;
@@ -4005,33 +4123,33 @@
 	if (!rv)
 		goto fail;
 
-	rv = drbd_recv_header(mdev, &p);
+	rv = drbd_recv_header(mdev, &cmd, &length);
 	if (!rv)
 		goto fail;
 
-	if (p.command != P_AUTH_CHALLENGE) {
+	if (cmd != P_AUTH_CHALLENGE) {
 		dev_err(DEV, "expected AuthChallenge packet, received: %s (0x%04x)\n",
-		    cmdname(p.command), p.command);
+		    cmdname(cmd), cmd);
 		rv = 0;
 		goto fail;
 	}
 
-	if (p.length > CHALLENGE_LEN*2) {
+	if (length > CHALLENGE_LEN * 2) {
 		dev_err(DEV, "expected AuthChallenge payload too big.\n");
 		rv = -1;
 		goto fail;
 	}
 
-	peers_ch = kmalloc(p.length, GFP_NOIO);
+	peers_ch = kmalloc(length, GFP_NOIO);
 	if (peers_ch == NULL) {
 		dev_err(DEV, "kmalloc of peers_ch failed\n");
 		rv = -1;
 		goto fail;
 	}
 
-	rv = drbd_recv(mdev, peers_ch, p.length);
+	rv = drbd_recv(mdev, peers_ch, length);
 
-	if (rv != p.length) {
+	if (rv != length) {
 		dev_err(DEV, "short read AuthChallenge: l=%u\n", rv);
 		rv = 0;
 		goto fail;
@@ -4046,7 +4164,7 @@
 	}
 
 	sg_init_table(&sg, 1);
-	sg_set_buf(&sg, peers_ch, p.length);
+	sg_set_buf(&sg, peers_ch, length);
 
 	rv = crypto_hash_digest(&desc, &sg, sg.length, response);
 	if (rv) {
@@ -4059,18 +4177,18 @@
 	if (!rv)
 		goto fail;
 
-	rv = drbd_recv_header(mdev, &p);
+	rv = drbd_recv_header(mdev, &cmd, &length);
 	if (!rv)
 		goto fail;
 
-	if (p.command != P_AUTH_RESPONSE) {
+	if (cmd != P_AUTH_RESPONSE) {
 		dev_err(DEV, "expected AuthResponse packet, received: %s (0x%04x)\n",
-		    cmdname(p.command), p.command);
+			cmdname(cmd), cmd);
 		rv = 0;
 		goto fail;
 	}
 
-	if (p.length != resp_size) {
+	if (length != resp_size) {
 		dev_err(DEV, "expected AuthResponse payload of wrong size\n");
 		rv = 0;
 		goto fail;
@@ -4155,7 +4273,7 @@
 
 /* ********* acknowledge sender ******** */
 
-static int got_RqSReply(struct drbd_conf *mdev, struct p_header *h)
+static int got_RqSReply(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	struct p_req_state_reply *p = (struct p_req_state_reply *)h;
 
@@ -4173,13 +4291,13 @@
 	return TRUE;
 }
 
-static int got_Ping(struct drbd_conf *mdev, struct p_header *h)
+static int got_Ping(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	return drbd_send_ping_ack(mdev);
 
 }
 
-static int got_PingAck(struct drbd_conf *mdev, struct p_header *h)
+static int got_PingAck(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	/* restore idle timeout */
 	mdev->meta.socket->sk->sk_rcvtimeo = mdev->net_conf->ping_int*HZ;
@@ -4189,7 +4307,7 @@
 	return TRUE;
 }
 
-static int got_IsInSync(struct drbd_conf *mdev, struct p_header *h)
+static int got_IsInSync(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	struct p_block_ack *p = (struct p_block_ack *)h;
 	sector_t sector = be64_to_cpu(p->sector);
@@ -4199,11 +4317,15 @@
 
 	update_peer_seq(mdev, be32_to_cpu(p->seq_num));
 
-	drbd_rs_complete_io(mdev, sector);
-	drbd_set_in_sync(mdev, sector, blksize);
-	/* rs_same_csums is supposed to count in units of BM_BLOCK_SIZE */
-	mdev->rs_same_csum += (blksize >> BM_BLOCK_SHIFT);
+	if (get_ldev(mdev)) {
+		drbd_rs_complete_io(mdev, sector);
+		drbd_set_in_sync(mdev, sector, blksize);
+		/* rs_same_csums is supposed to count in units of BM_BLOCK_SIZE */
+		mdev->rs_same_csum += (blksize >> BM_BLOCK_SHIFT);
+		put_ldev(mdev);
+	}
 	dec_rs_pending(mdev);
+	atomic_add(blksize >> 9, &mdev->rs_sect_in);
 
 	return TRUE;
 }
@@ -4259,7 +4381,7 @@
 	return TRUE;
 }
 
-static int got_BlockAck(struct drbd_conf *mdev, struct p_header *h)
+static int got_BlockAck(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	struct p_block_ack *p = (struct p_block_ack *)h;
 	sector_t sector = be64_to_cpu(p->sector);
@@ -4299,7 +4421,7 @@
 		_ack_id_to_req, __func__ , what);
 }
 
-static int got_NegAck(struct drbd_conf *mdev, struct p_header *h)
+static int got_NegAck(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	struct p_block_ack *p = (struct p_block_ack *)h;
 	sector_t sector = be64_to_cpu(p->sector);
@@ -4319,7 +4441,7 @@
 		_ack_id_to_req, __func__ , neg_acked);
 }
 
-static int got_NegDReply(struct drbd_conf *mdev, struct p_header *h)
+static int got_NegDReply(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	struct p_block_ack *p = (struct p_block_ack *)h;
 	sector_t sector = be64_to_cpu(p->sector);
@@ -4332,7 +4454,7 @@
 		_ar_id_to_req, __func__ , neg_acked);
 }
 
-static int got_NegRSDReply(struct drbd_conf *mdev, struct p_header *h)
+static int got_NegRSDReply(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	sector_t sector;
 	int size;
@@ -4354,7 +4476,7 @@
 	return TRUE;
 }
 
-static int got_BarrierAck(struct drbd_conf *mdev, struct p_header *h)
+static int got_BarrierAck(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	struct p_barrier_ack *p = (struct p_barrier_ack *)h;
 
@@ -4363,7 +4485,7 @@
 	return TRUE;
 }
 
-static int got_OVResult(struct drbd_conf *mdev, struct p_header *h)
+static int got_OVResult(struct drbd_conf *mdev, struct p_header80 *h)
 {
 	struct p_block_ack *p = (struct p_block_ack *)h;
 	struct drbd_work *w;
@@ -4380,6 +4502,9 @@
 	else
 		ov_oos_print(mdev);
 
+	if (!get_ldev(mdev))
+		return TRUE;
+
 	drbd_rs_complete_io(mdev, sector);
 	dec_rs_pending(mdev);
 
@@ -4394,18 +4519,18 @@
 			drbd_resync_finished(mdev);
 		}
 	}
+	put_ldev(mdev);
 	return TRUE;
 }
 
-static int got_something_to_ignore_m(struct drbd_conf *mdev, struct p_header *h)
+static int got_skip(struct drbd_conf *mdev, struct p_header80 *h)
 {
-	/* IGNORE */
 	return TRUE;
 }
 
 struct asender_cmd {
 	size_t pkt_size;
-	int (*process)(struct drbd_conf *mdev, struct p_header *h);
+	int (*process)(struct drbd_conf *mdev, struct p_header80 *h);
 };
 
 static struct asender_cmd *get_asender_cmd(int cmd)
@@ -4414,8 +4539,8 @@
 		/* anything missing from this table is in
 		 * the drbd_cmd_handler (drbd_default_handler) table,
 		 * see the beginning of drbdd() */
-	[P_PING]	    = { sizeof(struct p_header), got_Ping },
-	[P_PING_ACK]	    = { sizeof(struct p_header), got_PingAck },
+	[P_PING]	    = { sizeof(struct p_header80), got_Ping },
+	[P_PING_ACK]	    = { sizeof(struct p_header80), got_PingAck },
 	[P_RECV_ACK]	    = { sizeof(struct p_block_ack), got_BlockAck },
 	[P_WRITE_ACK]	    = { sizeof(struct p_block_ack), got_BlockAck },
 	[P_RS_WRITE_ACK]    = { sizeof(struct p_block_ack), got_BlockAck },
@@ -4427,7 +4552,7 @@
 	[P_BARRIER_ACK]	    = { sizeof(struct p_barrier_ack), got_BarrierAck },
 	[P_STATE_CHG_REPLY] = { sizeof(struct p_req_state_reply), got_RqSReply },
 	[P_RS_IS_IN_SYNC]   = { sizeof(struct p_block_ack), got_IsInSync },
-	[P_DELAY_PROBE]     = { sizeof(struct p_delay_probe), got_something_to_ignore_m },
+	[P_DELAY_PROBE]     = { sizeof(struct p_delay_probe93), got_skip },
 	[P_MAX_CMD]	    = { 0, NULL },
 	};
 	if (cmd > P_MAX_CMD || asender_tbl[cmd].process == NULL)
@@ -4438,13 +4563,13 @@
 int drbd_asender(struct drbd_thread *thi)
 {
 	struct drbd_conf *mdev = thi->mdev;
-	struct p_header *h = &mdev->meta.rbuf.header;
+	struct p_header80 *h = &mdev->meta.rbuf.header.h80;
 	struct asender_cmd *cmd = NULL;
 
 	int rv, len;
 	void *buf    = h;
 	int received = 0;
-	int expect   = sizeof(struct p_header);
+	int expect   = sizeof(struct p_header80);
 	int empty;
 
 	sprintf(current->comm, "drbd%d_asender", mdev_to_minor(mdev));
@@ -4468,10 +4593,8 @@
 		while (1) {
 			clear_bit(SIGNAL_ASENDER, &mdev->flags);
 			flush_signals(current);
-			if (!drbd_process_done_ee(mdev)) {
-				dev_err(DEV, "process_done_ee() = NOT_OK\n");
+			if (!drbd_process_done_ee(mdev))
 				goto reconnect;
-			}
 			/* to avoid race with newly queued ACKs */
 			set_bit(SIGNAL_ASENDER, &mdev->flags);
 			spin_lock_irq(&mdev->req_lock);
@@ -4530,21 +4653,23 @@
 
 		if (received == expect && cmd == NULL) {
 			if (unlikely(h->magic != BE_DRBD_MAGIC)) {
-				dev_err(DEV, "magic?? on meta m: 0x%lx c: %d l: %d\n",
-				    (long)be32_to_cpu(h->magic),
-				    h->command, h->length);
+				dev_err(DEV, "magic?? on meta m: 0x%08x c: %d l: %d\n",
+				    be32_to_cpu(h->magic),
+				    be16_to_cpu(h->command),
+				    be16_to_cpu(h->length));
 				goto reconnect;
 			}
 			cmd = get_asender_cmd(be16_to_cpu(h->command));
 			len = be16_to_cpu(h->length);
 			if (unlikely(cmd == NULL)) {
-				dev_err(DEV, "unknown command?? on meta m: 0x%lx c: %d l: %d\n",
-				    (long)be32_to_cpu(h->magic),
-				    h->command, h->length);
+				dev_err(DEV, "unknown command?? on meta m: 0x%08x c: %d l: %d\n",
+				    be32_to_cpu(h->magic),
+				    be16_to_cpu(h->command),
+				    be16_to_cpu(h->length));
 				goto disconnect;
 			}
 			expect = cmd->pkt_size;
-			ERR_IF(len != expect-sizeof(struct p_header))
+			ERR_IF(len != expect-sizeof(struct p_header80))
 				goto reconnect;
 		}
 		if (received == expect) {
@@ -4554,7 +4679,7 @@
 
 			buf	 = h;
 			received = 0;
-			expect	 = sizeof(struct p_header);
+			expect	 = sizeof(struct p_header80);
 			cmd	 = NULL;
 		}
 	}
@@ -4562,10 +4687,12 @@
 	if (0) {
 reconnect:
 		drbd_force_state(mdev, NS(conn, C_NETWORK_FAILURE));
+		drbd_md_sync(mdev);
 	}
 	if (0) {
 disconnect:
 		drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
+		drbd_md_sync(mdev);
 	}
 	clear_bit(SIGNAL_ASENDER, &mdev->flags);
 
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index f761d98..9e91a25 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -59,17 +59,19 @@
 static void _req_is_done(struct drbd_conf *mdev, struct drbd_request *req, const int rw)
 {
 	const unsigned long s = req->rq_state;
+
+	/* remove it from the transfer log.
+	 * well, only if it had been there in the first
+	 * place... if it had not (local only or conflicting
+	 * and never sent), it should still be "empty" as
+	 * initialized in drbd_req_new(), so we can list_del() it
+	 * here unconditionally */
+	list_del(&req->tl_requests);
+
 	/* if it was a write, we may have to set the corresponding
 	 * bit(s) out-of-sync first. If it had a local part, we need to
 	 * release the reference to the activity log. */
 	if (rw == WRITE) {
-		/* remove it from the transfer log.
-		 * well, only if it had been there in the first
-		 * place... if it had not (local only or conflicting
-		 * and never sent), it should still be "empty" as
-		 * initialized in drbd_req_new(), so we can list_del() it
-		 * here unconditionally */
-		list_del(&req->tl_requests);
 		/* Set out-of-sync unless both OK flags are set
 		 * (local only or remote failed).
 		 * Other places where we set out-of-sync:
@@ -92,7 +94,8 @@
 		 */
 		if (s & RQ_LOCAL_MASK) {
 			if (get_ldev_if_state(mdev, D_FAILED)) {
-				drbd_al_complete_io(mdev, req->sector);
+				if (s & RQ_IN_ACT_LOG)
+					drbd_al_complete_io(mdev, req->sector);
 				put_ldev(mdev);
 			} else if (__ratelimit(&drbd_ratelimit_state)) {
 				dev_warn(DEV, "Should have called drbd_al_complete_io(, %llu), "
@@ -280,6 +283,14 @@
 	 * protocol A or B, barrier ack still pending... */
 }
 
+static void _req_may_be_done_not_susp(struct drbd_request *req, struct bio_and_error *m)
+{
+	struct drbd_conf *mdev = req->mdev;
+
+	if (!is_susp(mdev->state))
+		_req_may_be_done(req, m);
+}
+
 /*
  * checks whether there was an overlapping request
  * or ee already registered.
@@ -380,10 +391,11 @@
  *  and it enforces that we have to think in a very structured manner
  *  about the "events" that may happen to a request during its life time ...
  */
-void __req_mod(struct drbd_request *req, enum drbd_req_event what,
+int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		struct bio_and_error *m)
 {
 	struct drbd_conf *mdev = req->mdev;
+	int rv = 0;
 	m->bio = NULL;
 
 	switch (what) {
@@ -420,7 +432,7 @@
 		req->rq_state |= (RQ_LOCAL_COMPLETED|RQ_LOCAL_OK);
 		req->rq_state &= ~RQ_LOCAL_PENDING;
 
-		_req_may_be_done(req, m);
+		_req_may_be_done_not_susp(req, m);
 		put_ldev(mdev);
 		break;
 
@@ -429,7 +441,7 @@
 		req->rq_state &= ~RQ_LOCAL_PENDING;
 
 		__drbd_chk_io_error(mdev, FALSE);
-		_req_may_be_done(req, m);
+		_req_may_be_done_not_susp(req, m);
 		put_ldev(mdev);
 		break;
 
@@ -437,7 +449,7 @@
 		/* it is legal to fail READA */
 		req->rq_state |= RQ_LOCAL_COMPLETED;
 		req->rq_state &= ~RQ_LOCAL_PENDING;
-		_req_may_be_done(req, m);
+		_req_may_be_done_not_susp(req, m);
 		put_ldev(mdev);
 		break;
 
@@ -455,7 +467,7 @@
 		/* no point in retrying if there is no good remote data,
 		 * or we have no connection. */
 		if (mdev->state.pdsk != D_UP_TO_DATE) {
-			_req_may_be_done(req, m);
+			_req_may_be_done_not_susp(req, m);
 			break;
 		}
 
@@ -517,11 +529,9 @@
 		D_ASSERT(test_bit(CREATE_BARRIER, &mdev->flags) == 0);
 
 		req->epoch = mdev->newest_tle->br_number;
-		list_add_tail(&req->tl_requests,
-				&mdev->newest_tle->requests);
 
 		/* increment size of current epoch */
-		mdev->newest_tle->n_req++;
+		mdev->newest_tle->n_writes++;
 
 		/* queue work item to send data */
 		D_ASSERT(req->rq_state & RQ_NET_PENDING);
@@ -530,7 +540,7 @@
 		drbd_queue_work(&mdev->data.work, &req->w);
 
 		/* close the epoch, in case it outgrew the limit */
-		if (mdev->newest_tle->n_req >= mdev->net_conf->max_epoch_size)
+		if (mdev->newest_tle->n_writes >= mdev->net_conf->max_epoch_size)
 			queue_barrier(mdev);
 
 		break;
@@ -543,7 +553,7 @@
 		req->rq_state &= ~RQ_NET_QUEUED;
 		/* if we did it right, tl_clear should be scheduled only after
 		 * this, so this should not be necessary! */
-		_req_may_be_done(req, m);
+		_req_may_be_done_not_susp(req, m);
 		break;
 
 	case handed_over_to_network:
@@ -568,7 +578,7 @@
 		 * "completed_ok" events came in, once we return from
 		 * _drbd_send_zc_bio (drbd_send_dblock), we have to check
 		 * whether it is done already, and end it.  */
-		_req_may_be_done(req, m);
+		_req_may_be_done_not_susp(req, m);
 		break;
 
 	case read_retry_remote_canceled:
@@ -584,7 +594,7 @@
 		/* if it is still queued, we may not complete it here.
 		 * it will be canceled soon. */
 		if (!(req->rq_state & RQ_NET_QUEUED))
-			_req_may_be_done(req, m);
+			_req_may_be_done(req, m); /* Allowed while state.susp */
 		break;
 
 	case write_acked_by_peer_and_sis:
@@ -619,7 +629,7 @@
 		D_ASSERT(req->rq_state & RQ_NET_PENDING);
 		dec_ap_pending(mdev);
 		req->rq_state &= ~RQ_NET_PENDING;
-		_req_may_be_done(req, m);
+		_req_may_be_done_not_susp(req, m);
 		break;
 
 	case neg_acked:
@@ -629,11 +639,50 @@
 		req->rq_state &= ~(RQ_NET_OK|RQ_NET_PENDING);
 
 		req->rq_state |= RQ_NET_DONE;
-		_req_may_be_done(req, m);
+		_req_may_be_done_not_susp(req, m);
 		/* else: done by handed_over_to_network */
 		break;
 
+	case fail_frozen_disk_io:
+		if (!(req->rq_state & RQ_LOCAL_COMPLETED))
+			break;
+
+		_req_may_be_done(req, m); /* Allowed while state.susp */
+		break;
+
+	case restart_frozen_disk_io:
+		if (!(req->rq_state & RQ_LOCAL_COMPLETED))
+			break;
+
+		req->rq_state &= ~RQ_LOCAL_COMPLETED;
+
+		rv = MR_READ;
+		if (bio_data_dir(req->master_bio) == WRITE)
+			rv = MR_WRITE;
+
+		get_ldev(mdev);
+		req->w.cb = w_restart_disk_io;
+		drbd_queue_work(&mdev->data.work, &req->w);
+		break;
+
+	case resend:
+		/* If RQ_NET_OK is already set, we got a P_WRITE_ACK or P_RECV_ACK
+		   before the connection loss (B&C only); only P_BARRIER_ACK was missing.
+		   Trowing them out of the TL here by pretending we got a BARRIER_ACK
+		   We ensure that the peer was not rebooted */
+		if (!(req->rq_state & RQ_NET_OK)) {
+			if (req->w.cb) {
+				drbd_queue_work(&mdev->data.work, &req->w);
+				rv = req->rq_state & RQ_WRITE ? MR_WRITE : MR_READ;
+			}
+			break;
+		}
+		/* else, fall through to barrier_acked */
+
 	case barrier_acked:
+		if (!(req->rq_state & RQ_WRITE))
+			break;
+
 		if (req->rq_state & RQ_NET_PENDING) {
 			/* barrier came in before all requests have been acked.
 			 * this is bad, because if the connection is lost now,
@@ -643,7 +692,7 @@
 		}
 		D_ASSERT(req->rq_state & RQ_NET_SENT);
 		req->rq_state |= RQ_NET_DONE;
-		_req_may_be_done(req, m);
+		_req_may_be_done(req, m); /* Allowed while state.susp */
 		break;
 
 	case data_received:
@@ -651,9 +700,11 @@
 		dec_ap_pending(mdev);
 		req->rq_state &= ~RQ_NET_PENDING;
 		req->rq_state |= (RQ_NET_OK|RQ_NET_DONE);
-		_req_may_be_done(req, m);
+		_req_may_be_done_not_susp(req, m);
 		break;
 	};
+
+	return rv;
 }
 
 /* we may do a local read if:
@@ -752,14 +803,16 @@
 	 * resync extent to finish, and, if necessary, pulls in the target
 	 * extent into the activity log, which involves further disk io because
 	 * of transactional on-disk meta data updates. */
-	if (rw == WRITE && local)
+	if (rw == WRITE && local && !test_bit(AL_SUSPENDED, &mdev->flags)) {
+		req->rq_state |= RQ_IN_ACT_LOG;
 		drbd_al_begin_io(mdev, sector);
+	}
 
 	remote = remote && (mdev->state.pdsk == D_UP_TO_DATE ||
 			    (mdev->state.pdsk == D_INCONSISTENT &&
 			     mdev->state.conn >= C_CONNECTED));
 
-	if (!(local || remote) && !mdev->state.susp) {
+	if (!(local || remote) && !is_susp(mdev->state)) {
 		dev_err(DEV, "IO ERROR: neither local nor remote disk\n");
 		goto fail_free_complete;
 	}
@@ -785,7 +838,7 @@
 	/* GOOD, everything prepared, grab the spin_lock */
 	spin_lock_irq(&mdev->req_lock);
 
-	if (mdev->state.susp) {
+	if (is_susp(mdev->state)) {
 		/* If we got suspended, use the retry mechanism of
 		   generic_make_request() to restart processing of this
 		   bio. In the next call to drbd_make_request_26
@@ -867,30 +920,10 @@
 	/* check this request on the collision detection hash tables.
 	 * if we have a conflict, just complete it here.
 	 * THINK do we want to check reads, too? (I don't think so...) */
-	if (rw == WRITE && _req_conflicts(req)) {
-		/* this is a conflicting request.
-		 * even though it may have been only _partially_
-		 * overlapping with one of the currently pending requests,
-		 * without even submitting or sending it, we will
-		 * pretend that it was successfully served right now.
-		 */
-		if (local) {
-			bio_put(req->private_bio);
-			req->private_bio = NULL;
-			drbd_al_complete_io(mdev, req->sector);
-			put_ldev(mdev);
-			local = 0;
-		}
-		if (remote)
-			dec_ap_pending(mdev);
-		_drbd_end_io_acct(mdev, req);
-		/* THINK: do we want to fail it (-EIO), or pretend success? */
-		bio_endio(req->master_bio, 0);
-		req->master_bio = NULL;
-		dec_ap_bio(mdev);
-		drbd_req_free(req);
-		remote = 0;
-	}
+	if (rw == WRITE && _req_conflicts(req))
+		goto fail_conflicting;
+
+	list_add_tail(&req->tl_requests, &mdev->newest_tle->requests);
 
 	/* NOTE remote first: to get the concurrent write detection right,
 	 * we must register the request before start of local IO.  */
@@ -923,6 +956,21 @@
 
 	return 0;
 
+fail_conflicting:
+	/* this is a conflicting request.
+	 * even though it may have been only _partially_
+	 * overlapping with one of the currently pending requests,
+	 * without even submitting or sending it, we will
+	 * pretend that it was successfully served right now.
+	 */
+	_drbd_end_io_acct(mdev, req);
+	spin_unlock_irq(&mdev->req_lock);
+	if (remote)
+		dec_ap_pending(mdev);
+	/* THINK: do we want to fail it (-EIO), or pretend success?
+	 * this pretends success. */
+	err = 0;
+
 fail_free_complete:
 	if (rw == WRITE && local)
 		drbd_al_complete_io(mdev, sector);
@@ -961,21 +1009,6 @@
 		return 1;
 	}
 
-	/*
-	 * Paranoia: we might have been primary, but sync target, or
-	 * even diskless, then lost the connection.
-	 * This should have been handled (panic? suspend?) somewhere
-	 * else. But maybe it was not, so check again here.
-	 * Caution: as long as we do not have a read/write lock on mdev,
-	 * to serialize state changes, this is racy, since we may lose
-	 * the connection *after* we test for the cstate.
-	 */
-	if (mdev->state.disk < D_UP_TO_DATE && mdev->state.pdsk < D_UP_TO_DATE) {
-		if (__ratelimit(&drbd_ratelimit_state))
-			dev_err(DEV, "Sorry, I have no access to good data anymore.\n");
-		return 1;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index 02d575d..181ea03 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -104,6 +104,9 @@
 	read_ahead_completed_with_error,
 	write_completed_with_error,
 	completed_ok,
+	resend,
+	fail_frozen_disk_io,
+	restart_frozen_disk_io,
 	nothing, /* for tracing only */
 };
 
@@ -183,6 +186,12 @@
 
 	/* keep this last, its for the RQ_NET_MASK */
 	__RQ_NET_MAX,
+
+	/* Set when this is a write, clear for a read */
+	__RQ_WRITE,
+
+	/* Should call drbd_al_complete_io() for this request... */
+	__RQ_IN_ACT_LOG,
 };
 
 #define RQ_LOCAL_PENDING   (1UL << __RQ_LOCAL_PENDING)
@@ -201,6 +210,16 @@
 /* 0x1f8 */
 #define RQ_NET_MASK        (((1UL << __RQ_NET_MAX)-1) & ~RQ_LOCAL_MASK)
 
+#define RQ_WRITE           (1UL << __RQ_WRITE)
+#define RQ_IN_ACT_LOG      (1UL << __RQ_IN_ACT_LOG)
+
+/* For waking up the frozen transfer log mod_req() has to return if the request
+   should be counted in the epoch object*/
+#define MR_WRITE_SHIFT 0
+#define MR_WRITE       (1 << MR_WRITE_SHIFT)
+#define MR_READ_SHIFT  1
+#define MR_READ        (1 << MR_READ_SHIFT)
+
 /* epoch entries */
 static inline
 struct hlist_head *ee_hash_slot(struct drbd_conf *mdev, sector_t sector)
@@ -244,30 +263,36 @@
 	return NULL;
 }
 
+static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
+{
+	struct bio *bio;
+	bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */
+
+	req->private_bio = bio;
+
+	bio->bi_private  = req;
+	bio->bi_end_io   = drbd_endio_pri;
+	bio->bi_next     = NULL;
+}
+
 static inline struct drbd_request *drbd_req_new(struct drbd_conf *mdev,
 	struct bio *bio_src)
 {
-	struct bio *bio;
 	struct drbd_request *req =
 		mempool_alloc(drbd_request_mempool, GFP_NOIO);
 	if (likely(req)) {
-		bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */
+		drbd_req_make_private_bio(req, bio_src);
 
-		req->rq_state    = 0;
+		req->rq_state    = bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0;
 		req->mdev        = mdev;
 		req->master_bio  = bio_src;
-		req->private_bio = bio;
 		req->epoch       = 0;
-		req->sector      = bio->bi_sector;
-		req->size        = bio->bi_size;
+		req->sector      = bio_src->bi_sector;
+		req->size        = bio_src->bi_size;
 		req->start_time  = jiffies;
 		INIT_HLIST_NODE(&req->colision);
 		INIT_LIST_HEAD(&req->tl_requests);
 		INIT_LIST_HEAD(&req->w.list);
-
-		bio->bi_private  = req;
-		bio->bi_end_io   = drbd_endio_pri;
-		bio->bi_next     = NULL;
 	}
 	return req;
 }
@@ -292,36 +317,43 @@
 
 extern void _req_may_be_done(struct drbd_request *req,
 		struct bio_and_error *m);
-extern void __req_mod(struct drbd_request *req, enum drbd_req_event what,
+extern int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		struct bio_and_error *m);
 extern void complete_master_bio(struct drbd_conf *mdev,
 		struct bio_and_error *m);
 
 /* use this if you don't want to deal with calling complete_master_bio()
  * outside the spinlock, e.g. when walking some list on cleanup. */
-static inline void _req_mod(struct drbd_request *req, enum drbd_req_event what)
+static inline int _req_mod(struct drbd_request *req, enum drbd_req_event what)
 {
 	struct drbd_conf *mdev = req->mdev;
 	struct bio_and_error m;
+	int rv;
 
 	/* __req_mod possibly frees req, do not touch req after that! */
-	__req_mod(req, what, &m);
+	rv = __req_mod(req, what, &m);
 	if (m.bio)
 		complete_master_bio(mdev, &m);
+
+	return rv;
 }
 
 /* completion of master bio is outside of spinlock.
  * If you need it irqsave, do it your self! */
-static inline void req_mod(struct drbd_request *req,
+static inline int req_mod(struct drbd_request *req,
 		enum drbd_req_event what)
 {
 	struct drbd_conf *mdev = req->mdev;
 	struct bio_and_error m;
+	int rv;
+
 	spin_lock_irq(&mdev->req_lock);
-	__req_mod(req, what, &m);
+	rv = __req_mod(req, what, &m);
 	spin_unlock_irq(&mdev->req_lock);
 
 	if (m.bio)
 		complete_master_bio(mdev, &m);
+
+	return rv;
 }
 #endif
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index ca4a16c..108d580 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -39,8 +39,6 @@
 #include "drbd_int.h"
 #include "drbd_req.h"
 
-#define SLEEP_TIME (HZ/10)
-
 static int w_make_ov_request(struct drbd_conf *mdev, struct drbd_work *w, int cancel);
 
 
@@ -217,10 +215,8 @@
  */
 void drbd_endio_pri(struct bio *bio, int error)
 {
-	unsigned long flags;
 	struct drbd_request *req = bio->bi_private;
 	struct drbd_conf *mdev = req->mdev;
-	struct bio_and_error m;
 	enum drbd_req_event what;
 	int uptodate = bio_flagged(bio, BIO_UPTODATE);
 
@@ -246,12 +242,7 @@
 	bio_put(req->private_bio);
 	req->private_bio = ERR_PTR(error);
 
-	spin_lock_irqsave(&mdev->req_lock, flags);
-	__req_mod(req, what, &m);
-	spin_unlock_irqrestore(&mdev->req_lock, flags);
-
-	if (m.bio)
-		complete_master_bio(mdev, &m);
+	req_mod(req, what);
 }
 
 int w_read_retry_remote(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
@@ -376,54 +367,145 @@
 	struct drbd_epoch_entry *e;
 
 	if (!get_ldev(mdev))
-		return 0;
+		return -EIO;
+
+	if (drbd_rs_should_slow_down(mdev))
+		goto defer;
 
 	/* GFP_TRY, because if there is no memory available right now, this may
 	 * be rescheduled for later. It is "only" background resync, after all. */
 	e = drbd_alloc_ee(mdev, DRBD_MAGIC+0xbeef, sector, size, GFP_TRY);
 	if (!e)
-		goto fail;
+		goto defer;
 
+	e->w.cb = w_e_send_csum;
 	spin_lock_irq(&mdev->req_lock);
 	list_add(&e->w.list, &mdev->read_ee);
 	spin_unlock_irq(&mdev->req_lock);
 
-	e->w.cb = w_e_send_csum;
+	atomic_add(size >> 9, &mdev->rs_sect_ev);
 	if (drbd_submit_ee(mdev, e, READ, DRBD_FAULT_RS_RD) == 0)
-		return 1;
+		return 0;
+
+	/* drbd_submit_ee currently fails for one reason only:
+	 * not being able to allocate enough bios.
+	 * Is dropping the connection going to help? */
+	spin_lock_irq(&mdev->req_lock);
+	list_del(&e->w.list);
+	spin_unlock_irq(&mdev->req_lock);
 
 	drbd_free_ee(mdev, e);
-fail:
+defer:
 	put_ldev(mdev);
-	return 2;
+	return -EAGAIN;
 }
 
 void resync_timer_fn(unsigned long data)
 {
-	unsigned long flags;
 	struct drbd_conf *mdev = (struct drbd_conf *) data;
 	int queue;
 
-	spin_lock_irqsave(&mdev->req_lock, flags);
-
-	if (likely(!test_and_clear_bit(STOP_SYNC_TIMER, &mdev->flags))) {
-		queue = 1;
-		if (mdev->state.conn == C_VERIFY_S)
-			mdev->resync_work.cb = w_make_ov_request;
-		else
-			mdev->resync_work.cb = w_make_resync_request;
-	} else {
+	queue = 1;
+	switch (mdev->state.conn) {
+	case C_VERIFY_S:
+		mdev->resync_work.cb = w_make_ov_request;
+		break;
+	case C_SYNC_TARGET:
+		mdev->resync_work.cb = w_make_resync_request;
+		break;
+	default:
 		queue = 0;
 		mdev->resync_work.cb = w_resync_inactive;
 	}
 
-	spin_unlock_irqrestore(&mdev->req_lock, flags);
-
 	/* harmless race: list_empty outside data.work.q_lock */
 	if (list_empty(&mdev->resync_work.list) && queue)
 		drbd_queue_work(&mdev->data.work, &mdev->resync_work);
 }
 
+static void fifo_set(struct fifo_buffer *fb, int value)
+{
+	int i;
+
+	for (i = 0; i < fb->size; i++)
+		fb->values[i] = value;
+}
+
+static int fifo_push(struct fifo_buffer *fb, int value)
+{
+	int ov;
+
+	ov = fb->values[fb->head_index];
+	fb->values[fb->head_index++] = value;
+
+	if (fb->head_index >= fb->size)
+		fb->head_index = 0;
+
+	return ov;
+}
+
+static void fifo_add_val(struct fifo_buffer *fb, int value)
+{
+	int i;
+
+	for (i = 0; i < fb->size; i++)
+		fb->values[i] += value;
+}
+
+int drbd_rs_controller(struct drbd_conf *mdev)
+{
+	unsigned int sect_in;  /* Number of sectors that came in since the last turn */
+	unsigned int want;     /* The number of sectors we want in the proxy */
+	int req_sect; /* Number of sectors to request in this turn */
+	int correction; /* Number of sectors more we need in the proxy*/
+	int cps; /* correction per invocation of drbd_rs_controller() */
+	int steps; /* Number of time steps to plan ahead */
+	int curr_corr;
+	int max_sect;
+
+	sect_in = atomic_xchg(&mdev->rs_sect_in, 0); /* Number of sectors that came in */
+	mdev->rs_in_flight -= sect_in;
+
+	spin_lock(&mdev->peer_seq_lock); /* get an atomic view on mdev->rs_plan_s */
+
+	steps = mdev->rs_plan_s.size; /* (mdev->sync_conf.c_plan_ahead * 10 * SLEEP_TIME) / HZ; */
+
+	if (mdev->rs_in_flight + sect_in == 0) { /* At start of resync */
+		want = ((mdev->sync_conf.rate * 2 * SLEEP_TIME) / HZ) * steps;
+	} else { /* normal path */
+		want = mdev->sync_conf.c_fill_target ? mdev->sync_conf.c_fill_target :
+			sect_in * mdev->sync_conf.c_delay_target * HZ / (SLEEP_TIME * 10);
+	}
+
+	correction = want - mdev->rs_in_flight - mdev->rs_planed;
+
+	/* Plan ahead */
+	cps = correction / steps;
+	fifo_add_val(&mdev->rs_plan_s, cps);
+	mdev->rs_planed += cps * steps;
+
+	/* What we do in this step */
+	curr_corr = fifo_push(&mdev->rs_plan_s, 0);
+	spin_unlock(&mdev->peer_seq_lock);
+	mdev->rs_planed -= curr_corr;
+
+	req_sect = sect_in + curr_corr;
+	if (req_sect < 0)
+		req_sect = 0;
+
+	max_sect = (mdev->sync_conf.c_max_rate * 2 * SLEEP_TIME) / HZ;
+	if (req_sect > max_sect)
+		req_sect = max_sect;
+
+	/*
+	dev_warn(DEV, "si=%u if=%d wa=%u co=%d st=%d cps=%d pl=%d cc=%d rs=%d\n",
+		 sect_in, mdev->rs_in_flight, want, correction,
+		 steps, cps, mdev->rs_planed, curr_corr, req_sect);
+	*/
+
+	return req_sect;
+}
+
 int w_make_resync_request(struct drbd_conf *mdev,
 		struct drbd_work *w, int cancel)
 {
@@ -431,8 +513,9 @@
 	sector_t sector;
 	const sector_t capacity = drbd_get_capacity(mdev->this_bdev);
 	int max_segment_size;
-	int number, i, size, pe, mx;
+	int number, rollback_i, size, pe, mx;
 	int align, queued, sndbuf;
+	int i = 0;
 
 	if (unlikely(cancel))
 		return 1;
@@ -446,6 +529,12 @@
 		dev_err(DEV, "%s in w_make_resync_request\n",
 			drbd_conn_str(mdev->state.conn));
 
+	if (mdev->rs_total == 0) {
+		/* empty resync? */
+		drbd_resync_finished(mdev);
+		return 1;
+	}
+
 	if (!get_ldev(mdev)) {
 		/* Since we only need to access mdev->rsync a
 		   get_ldev_if_state(mdev,D_FAILED) would be sufficient, but
@@ -458,11 +547,25 @@
 
 	/* starting with drbd 8.3.8, we can handle multi-bio EEs,
 	 * if it should be necessary */
-	max_segment_size = mdev->agreed_pro_version < 94 ?
-		queue_max_segment_size(mdev->rq_queue) : DRBD_MAX_SEGMENT_SIZE;
+	max_segment_size =
+		mdev->agreed_pro_version < 94 ? queue_max_segment_size(mdev->rq_queue) :
+		mdev->agreed_pro_version < 95 ?	DRBD_MAX_SIZE_H80_PACKET : DRBD_MAX_SEGMENT_SIZE;
 
-	number = SLEEP_TIME * mdev->sync_conf.rate  / ((BM_BLOCK_SIZE / 1024) * HZ);
-	pe = atomic_read(&mdev->rs_pending_cnt);
+	if (mdev->rs_plan_s.size) { /* mdev->sync_conf.c_plan_ahead */
+		number = drbd_rs_controller(mdev) >> (BM_BLOCK_SHIFT - 9);
+		mdev->c_sync_rate = number * HZ * (BM_BLOCK_SIZE / 1024) / SLEEP_TIME;
+	} else {
+		mdev->c_sync_rate = mdev->sync_conf.rate;
+		number = SLEEP_TIME * mdev->c_sync_rate  / ((BM_BLOCK_SIZE / 1024) * HZ);
+	}
+
+	/* Throttle resync on lower level disk activity, which may also be
+	 * caused by application IO on Primary/SyncTarget.
+	 * Keep this after the call to drbd_rs_controller, as that assumes
+	 * to be called as precisely as possible every SLEEP_TIME,
+	 * and would be confused otherwise. */
+	if (drbd_rs_should_slow_down(mdev))
+		goto requeue;
 
 	mutex_lock(&mdev->data.mutex);
 	if (mdev->data.socket)
@@ -476,6 +579,7 @@
 		mx = number;
 
 	/* Limit the number of pending RS requests to no more than the peer's receive buffer */
+	pe = atomic_read(&mdev->rs_pending_cnt);
 	if ((pe + number) > mx) {
 		number = mx - pe;
 	}
@@ -526,6 +630,7 @@
 		 * be prepared for all stripe sizes of software RAIDs.
 		 */
 		align = 1;
+		rollback_i = i;
 		for (;;) {
 			if (size + BM_BLOCK_SIZE > max_segment_size)
 				break;
@@ -561,14 +666,19 @@
 			size = (capacity-sector)<<9;
 		if (mdev->agreed_pro_version >= 89 && mdev->csums_tfm) {
 			switch (read_for_csum(mdev, sector, size)) {
-			case 0: /* Disk failure*/
+			case -EIO: /* Disk failure */
 				put_ldev(mdev);
 				return 0;
-			case 2: /* Allocation failed */
+			case -EAGAIN: /* allocation failed, or ldev busy */
 				drbd_rs_complete_io(mdev, sector);
 				mdev->bm_resync_fo = BM_SECT_TO_BIT(sector);
+				i = rollback_i;
 				goto requeue;
-			/* case 1: everything ok */
+			case 0:
+				/* everything ok */
+				break;
+			default:
+				BUG();
 			}
 		} else {
 			inc_rs_pending(mdev);
@@ -595,6 +705,7 @@
 	}
 
  requeue:
+	mdev->rs_in_flight += (i << (BM_BLOCK_SHIFT - 9));
 	mod_timer(&mdev->resync_timer, jiffies + SLEEP_TIME);
 	put_ldev(mdev);
 	return 1;
@@ -670,6 +781,14 @@
 	return 1;
 }
 
+static void ping_peer(struct drbd_conf *mdev)
+{
+	clear_bit(GOT_PING_ACK, &mdev->flags);
+	request_ping(mdev);
+	wait_event(mdev->misc_wait,
+		   test_bit(GOT_PING_ACK, &mdev->flags) || mdev->state.conn < C_CONNECTED);
+}
+
 int drbd_resync_finished(struct drbd_conf *mdev)
 {
 	unsigned long db, dt, dbdt;
@@ -709,6 +828,8 @@
 	if (!get_ldev(mdev))
 		goto out;
 
+	ping_peer(mdev);
+
 	spin_lock_irq(&mdev->req_lock);
 	os = mdev->state;
 
@@ -801,6 +922,8 @@
 	mdev->rs_paused = 0;
 	mdev->ov_start_sector = 0;
 
+	drbd_md_sync(mdev);
+
 	if (test_and_clear_bit(WRITE_BM_AFTER_RESYNC, &mdev->flags)) {
 		dev_warn(DEV, "Writing the whole bitmap, due to failed kmalloc\n");
 		drbd_queue_bitmap_io(mdev, &drbd_bm_write, NULL, "write from resync_finished");
@@ -817,9 +940,13 @@
 {
 	if (drbd_ee_has_active_page(e)) {
 		/* This might happen if sendpage() has not finished */
+		int i = (e->size + PAGE_SIZE -1) >> PAGE_SHIFT;
+		atomic_add(i, &mdev->pp_in_use_by_net);
+		atomic_sub(i, &mdev->pp_in_use);
 		spin_lock_irq(&mdev->req_lock);
 		list_add_tail(&e->w.list, &mdev->net_ee);
 		spin_unlock_irq(&mdev->req_lock);
+		wake_up(&drbd_pp_wait);
 	} else
 		drbd_free_ee(mdev, e);
 }
@@ -926,9 +1053,12 @@
 		return 1;
 	}
 
-	drbd_rs_complete_io(mdev, e->sector);
+	if (get_ldev(mdev)) {
+		drbd_rs_complete_io(mdev, e->sector);
+		put_ldev(mdev);
+	}
 
-	di = (struct digest_info *)(unsigned long)e->block_id;
+	di = e->digest;
 
 	if (likely((e->flags & EE_WAS_ERROR) == 0)) {
 		/* quick hack to try to avoid a race against reconfiguration.
@@ -952,7 +1082,9 @@
 			ok = drbd_send_ack(mdev, P_RS_IS_IN_SYNC, e);
 		} else {
 			inc_rs_pending(mdev);
-			e->block_id = ID_SYNCER;
+			e->block_id = ID_SYNCER; /* By setting block_id, digest pointer becomes invalid! */
+			e->flags &= ~EE_HAS_DIGEST; /* This e no longer has a digest pointer */
+			kfree(di);
 			ok = drbd_send_block(mdev, P_RS_DATA_REPLY, e);
 		}
 	} else {
@@ -962,9 +1094,6 @@
 	}
 
 	dec_unacked(mdev);
-
-	kfree(di);
-
 	move_to_net_ee_or_free(mdev, e);
 
 	if (unlikely(!ok))
@@ -1034,9 +1163,12 @@
 
 	/* after "cancel", because after drbd_disconnect/drbd_rs_cancel_all
 	 * the resync lru has been cleaned up already */
-	drbd_rs_complete_io(mdev, e->sector);
+	if (get_ldev(mdev)) {
+		drbd_rs_complete_io(mdev, e->sector);
+		put_ldev(mdev);
+	}
 
-	di = (struct digest_info *)(unsigned long)e->block_id;
+	di = e->digest;
 
 	if (likely((e->flags & EE_WAS_ERROR) == 0)) {
 		digest_size = crypto_hash_digestsize(mdev->verify_tfm);
@@ -1055,9 +1187,6 @@
 	}
 
 	dec_unacked(mdev);
-
-	kfree(di);
-
 	if (!eq)
 		drbd_ov_oos_found(mdev, e->sector, e->size);
 	else
@@ -1108,7 +1237,7 @@
 	 * dec_ap_pending will be done in got_BarrierAck
 	 * or (on connection loss) in w_clear_epoch.  */
 	ok = _drbd_send_cmd(mdev, mdev->data.socket, P_BARRIER,
-				(struct p_header *)p, sizeof(*p), 0);
+				(struct p_header80 *)p, sizeof(*p), 0);
 	drbd_put_data_sock(mdev);
 
 	return ok;
@@ -1173,6 +1302,24 @@
 	return ok;
 }
 
+int w_restart_disk_io(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
+{
+	struct drbd_request *req = container_of(w, struct drbd_request, w);
+
+	if (bio_data_dir(req->master_bio) == WRITE && req->rq_state & RQ_IN_ACT_LOG)
+		drbd_al_begin_io(mdev, req->sector);
+	/* Calling drbd_al_begin_io() out of the worker might deadlocks
+	   theoretically. Practically it can not deadlock, since this is
+	   only used when unfreezing IOs. All the extents of the requests
+	   that made it into the TL are already active */
+
+	drbd_req_make_private_bio(req, req->master_bio);
+	req->private_bio->bi_bdev = mdev->ldev->backing_bdev;
+	generic_make_request(req->private_bio);
+
+	return 1;
+}
+
 static int _drbd_may_sync_now(struct drbd_conf *mdev)
 {
 	struct drbd_conf *odev = mdev;
@@ -1298,14 +1445,6 @@
 	return retcode;
 }
 
-static void ping_peer(struct drbd_conf *mdev)
-{
-	clear_bit(GOT_PING_ACK, &mdev->flags);
-	request_ping(mdev);
-	wait_event(mdev->misc_wait,
-		   test_bit(GOT_PING_ACK, &mdev->flags) || mdev->state.conn < C_CONNECTED);
-}
-
 /**
  * drbd_start_resync() - Start the resync process
  * @mdev:	DRBD device.
@@ -1379,13 +1518,21 @@
 		r = SS_UNKNOWN_ERROR;
 
 	if (r == SS_SUCCESS) {
-		mdev->rs_total     =
-		mdev->rs_mark_left = drbd_bm_total_weight(mdev);
+		unsigned long tw = drbd_bm_total_weight(mdev);
+		unsigned long now = jiffies;
+		int i;
+
 		mdev->rs_failed    = 0;
 		mdev->rs_paused    = 0;
-		mdev->rs_start     =
-		mdev->rs_mark_time = jiffies;
 		mdev->rs_same_csum = 0;
+		mdev->rs_last_events = 0;
+		mdev->rs_last_sect_ev = 0;
+		mdev->rs_total     = tw;
+		mdev->rs_start     = now;
+		for (i = 0; i < DRBD_SYNC_MARKS; i++) {
+			mdev->rs_mark_left[i] = tw;
+			mdev->rs_mark_time[i] = now;
+		}
 		_drbd_pause_after(mdev);
 	}
 	write_unlock_irq(&global_state_lock);
@@ -1397,12 +1544,31 @@
 		     (unsigned long) mdev->rs_total << (BM_BLOCK_SHIFT-10),
 		     (unsigned long) mdev->rs_total);
 
-		if (mdev->rs_total == 0) {
-			/* Peer still reachable? Beware of failing before-resync-target handlers! */
-			ping_peer(mdev);
+		if (mdev->agreed_pro_version < 95 && mdev->rs_total == 0) {
+			/* This still has a race (about when exactly the peers
+			 * detect connection loss) that can lead to a full sync
+			 * on next handshake. In 8.3.9 we fixed this with explicit
+			 * resync-finished notifications, but the fix
+			 * introduces a protocol change.  Sleeping for some
+			 * time longer than the ping interval + timeout on the
+			 * SyncSource, to give the SyncTarget the chance to
+			 * detect connection loss, then waiting for a ping
+			 * response (implicit in drbd_resync_finished) reduces
+			 * the race considerably, but does not solve it. */
+			if (side == C_SYNC_SOURCE)
+				schedule_timeout_interruptible(
+					mdev->net_conf->ping_int * HZ +
+					mdev->net_conf->ping_timeo*HZ/9);
 			drbd_resync_finished(mdev);
 		}
 
+		atomic_set(&mdev->rs_sect_in, 0);
+		atomic_set(&mdev->rs_sect_ev, 0);
+		mdev->rs_in_flight = 0;
+		mdev->rs_planed = 0;
+		spin_lock(&mdev->peer_seq_lock);
+		fifo_set(&mdev->rs_plan_s, 0);
+		spin_unlock(&mdev->peer_seq_lock);
 		/* ns.conn may already be != mdev->state.conn,
 		 * we may have been paused in between, or become paused until
 		 * the timer triggers.
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index cf04c1b..767107c 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -178,7 +178,6 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/bio.h>
-#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/jiffies.h>
 #include <linux/fcntl.h>
@@ -199,6 +198,7 @@
  * It's been recommended that take about 1/4 of the default speed
  * in some more extreme cases.
  */
+static DEFINE_MUTEX(floppy_mutex);
 static int slow_floppy;
 
 #include <asm/dma.h>
@@ -258,8 +258,8 @@
 #include <linux/completion.h>
 
 static struct request *current_req;
-static struct request_queue *floppy_queue;
 static void do_fd_request(struct request_queue *q);
+static int set_next_request(void);
 
 #ifndef fd_get_dma_residue
 #define fd_get_dma_residue() get_dma_residue(FLOPPY_DMA)
@@ -413,6 +413,7 @@
 static struct block_device *opened_bdev[N_DRIVE];
 static DEFINE_MUTEX(open_lock);
 static struct floppy_raw_cmd *raw_cmd, default_raw_cmd;
+static int fdc_queue;
 
 /*
  * This struct defines the different floppy types.
@@ -890,8 +891,8 @@
 	del_timer(&fd_timeout);
 	cont = NULL;
 	clear_bit(0, &fdc_busy);
-	if (current_req || blk_peek_request(floppy_queue))
-		do_fd_request(floppy_queue);
+	if (current_req || set_next_request())
+		do_fd_request(current_req->q);
 	spin_unlock_irqrestore(&floppy_lock, flags);
 	wake_up(&fdc_wait);
 }
@@ -2243,8 +2244,8 @@
  * logical buffer */
 static void request_done(int uptodate)
 {
-	struct request_queue *q = floppy_queue;
 	struct request *req = current_req;
+	struct request_queue *q;
 	unsigned long flags;
 	int block;
 	char msg[sizeof("request done ") + sizeof(int) * 3];
@@ -2258,6 +2259,8 @@
 		return;
 	}
 
+	q = req->q;
+
 	if (uptodate) {
 		/* maintain values for invalidation on geometry
 		 * change */
@@ -2811,6 +2814,28 @@
 	return 2;
 }
 
+/*
+ * Round-robin between our available drives, doing one request from each
+ */
+static int set_next_request(void)
+{
+	struct request_queue *q;
+	int old_pos = fdc_queue;
+
+	do {
+		q = disks[fdc_queue]->queue;
+		if (++fdc_queue == N_DRIVE)
+			fdc_queue = 0;
+		if (q) {
+			current_req = blk_fetch_request(q);
+			if (current_req)
+				break;
+		}
+	} while (fdc_queue != old_pos);
+
+	return current_req != NULL;
+}
+
 static void redo_fd_request(void)
 {
 	int drive;
@@ -2822,17 +2847,17 @@
 
 do_request:
 	if (!current_req) {
-		struct request *req;
+		int pending;
 
-		spin_lock_irq(floppy_queue->queue_lock);
-		req = blk_fetch_request(floppy_queue);
-		spin_unlock_irq(floppy_queue->queue_lock);
-		if (!req) {
+		spin_lock_irq(&floppy_lock);
+		pending = set_next_request();
+		spin_unlock_irq(&floppy_lock);
+
+		if (!pending) {
 			do_floppy = NULL;
 			unlock_fdc();
 			return;
 		}
-		current_req = req;
 	}
 	drive = (long)current_req->rq_disk->private_data;
 	set_fdc(drive);
@@ -3553,9 +3578,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&floppy_mutex);
 	ret = fd_locked_ioctl(bdev, mode, cmd, param);
-	unlock_kernel();
+	mutex_unlock(&floppy_mutex);
 
 	return ret;
 }
@@ -3616,7 +3641,7 @@
 {
 	int drive = (long)disk->private_data;
 
-	lock_kernel();
+	mutex_lock(&floppy_mutex);
 	mutex_lock(&open_lock);
 	if (UDRS->fd_ref < 0)
 		UDRS->fd_ref = 0;
@@ -3627,7 +3652,7 @@
 	if (!UDRS->fd_ref)
 		opened_bdev[drive] = NULL;
 	mutex_unlock(&open_lock);
-	unlock_kernel();
+	mutex_unlock(&floppy_mutex);
 
 	return 0;
 }
@@ -3645,7 +3670,7 @@
 	int res = -EBUSY;
 	char *tmp;
 
-	lock_kernel();
+	mutex_lock(&floppy_mutex);
 	mutex_lock(&open_lock);
 	old_dev = UDRS->fd_device;
 	if (opened_bdev[drive] && opened_bdev[drive] != bdev)
@@ -3722,7 +3747,7 @@
 			goto out;
 	}
 	mutex_unlock(&open_lock);
-	unlock_kernel();
+	mutex_unlock(&floppy_mutex);
 	return 0;
 out:
 	if (UDRS->fd_ref < 0)
@@ -3733,7 +3758,7 @@
 		opened_bdev[drive] = NULL;
 out2:
 	mutex_unlock(&open_lock);
-	unlock_kernel();
+	mutex_unlock(&floppy_mutex);
 	return res;
 }
 
@@ -4165,6 +4190,13 @@
 			goto out_put_disk;
 		}
 
+		disks[dr]->queue = blk_init_queue(do_fd_request, &floppy_lock);
+		if (!disks[dr]->queue) {
+			err = -ENOMEM;
+			goto out_put_disk;
+		}
+
+		blk_queue_max_hw_sectors(disks[dr]->queue, 64);
 		disks[dr]->major = FLOPPY_MAJOR;
 		disks[dr]->first_minor = TOMINOR(dr);
 		disks[dr]->fops = &floppy_fops;
@@ -4183,13 +4215,6 @@
 	if (err)
 		goto out_unreg_blkdev;
 
-	floppy_queue = blk_init_queue(do_fd_request, &floppy_lock);
-	if (!floppy_queue) {
-		err = -ENOMEM;
-		goto out_unreg_driver;
-	}
-	blk_queue_max_hw_sectors(floppy_queue, 64);
-
 	blk_register_region(MKDEV(FLOPPY_MAJOR, 0), 256, THIS_MODULE,
 			    floppy_find, NULL, NULL);
 
@@ -4317,7 +4342,6 @@
 
 		/* to be cleaned up... */
 		disks[drive]->private_data = (void *)(long)drive;
-		disks[drive]->queue = floppy_queue;
 		disks[drive]->flags |= GENHD_FL_REMOVABLE;
 		disks[drive]->driverfs_dev = &floppy_device[drive].dev;
 		add_disk(disks[drive]);
@@ -4333,8 +4357,6 @@
 		floppy_release_irq_and_dma();
 out_unreg_region:
 	blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256);
-	blk_cleanup_queue(floppy_queue);
-out_unreg_driver:
 	platform_driver_unregister(&floppy_driver);
 out_unreg_blkdev:
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
@@ -4342,6 +4364,8 @@
 	while (dr--) {
 		del_timer(&motor_off_timer[dr]);
 		put_disk(disks[dr]);
+		if (disks[dr]->queue)
+			blk_cleanup_queue(disks[dr]->queue);
 	}
 	return err;
 }
@@ -4550,11 +4574,11 @@
 			platform_device_unregister(&floppy_device[drive]);
 		}
 		put_disk(disks[drive]);
+		blk_cleanup_queue(disks[drive]->queue);
 	}
 
 	del_timer_sync(&fd_timeout);
 	del_timer_sync(&fd_timer);
-	blk_cleanup_queue(floppy_queue);
 
 	if (atomic_read(&usage_count))
 		floppy_release_irq_and_dma();
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 91797bb..6c48b35 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -67,16 +67,18 @@
 #include <linux/compat.h>
 #include <linux/suspend.h>
 #include <linux/freezer.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>		/* for invalidate_bdev() */
 #include <linux/completion.h>
 #include <linux/highmem.h>
 #include <linux/kthread.h>
 #include <linux/splice.h>
+#include <linux/sysfs.h>
 
 #include <asm/uaccess.h>
 
+static DEFINE_MUTEX(loop_mutex);
 static LIST_HEAD(loop_devices);
 static DEFINE_MUTEX(loop_devices_mutex);
 
@@ -477,17 +479,17 @@
 	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
 
 	if (bio_rw(bio) == WRITE) {
-		bool barrier = !!(bio->bi_rw & REQ_HARDBARRIER);
 		struct file *file = lo->lo_backing_file;
 
-		if (barrier) {
-			if (unlikely(!file->f_op->fsync)) {
-				ret = -EOPNOTSUPP;
-				goto out;
-			}
+		/* REQ_HARDBARRIER is deprecated */
+		if (bio->bi_rw & REQ_HARDBARRIER) {
+			ret = -EOPNOTSUPP;
+			goto out;
+		}
 
+		if (bio->bi_rw & REQ_FLUSH) {
 			ret = vfs_fsync(file, 0);
-			if (unlikely(ret)) {
+			if (unlikely(ret && ret != -EINVAL)) {
 				ret = -EIO;
 				goto out;
 			}
@@ -495,9 +497,9 @@
 
 		ret = lo_send(lo, bio, pos);
 
-		if (barrier && !ret) {
+		if ((bio->bi_rw & REQ_FUA) && !ret) {
 			ret = vfs_fsync(file, 0);
-			if (unlikely(ret))
+			if (unlikely(ret && ret != -EINVAL))
 				ret = -EIO;
 		}
 	} else
@@ -737,6 +739,103 @@
 	return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
 }
 
+/* loop sysfs attributes */
+
+static ssize_t loop_attr_show(struct device *dev, char *page,
+			      ssize_t (*callback)(struct loop_device *, char *))
+{
+	struct loop_device *l, *lo = NULL;
+
+	mutex_lock(&loop_devices_mutex);
+	list_for_each_entry(l, &loop_devices, lo_list)
+		if (disk_to_dev(l->lo_disk) == dev) {
+			lo = l;
+			break;
+		}
+	mutex_unlock(&loop_devices_mutex);
+
+	return lo ? callback(lo, page) : -EIO;
+}
+
+#define LOOP_ATTR_RO(_name)						\
+static ssize_t loop_attr_##_name##_show(struct loop_device *, char *);	\
+static ssize_t loop_attr_do_show_##_name(struct device *d,		\
+				struct device_attribute *attr, char *b)	\
+{									\
+	return loop_attr_show(d, b, loop_attr_##_name##_show);		\
+}									\
+static struct device_attribute loop_attr_##_name =			\
+	__ATTR(_name, S_IRUGO, loop_attr_do_show_##_name, NULL);
+
+static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
+{
+	ssize_t ret;
+	char *p = NULL;
+
+	mutex_lock(&lo->lo_ctl_mutex);
+	if (lo->lo_backing_file)
+		p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1);
+	mutex_unlock(&lo->lo_ctl_mutex);
+
+	if (IS_ERR_OR_NULL(p))
+		ret = PTR_ERR(p);
+	else {
+		ret = strlen(p);
+		memmove(buf, p, ret);
+		buf[ret++] = '\n';
+		buf[ret] = 0;
+	}
+
+	return ret;
+}
+
+static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf)
+{
+	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_offset);
+}
+
+static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf)
+{
+	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit);
+}
+
+static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf)
+{
+	int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR);
+
+	return sprintf(buf, "%s\n", autoclear ? "1" : "0");
+}
+
+LOOP_ATTR_RO(backing_file);
+LOOP_ATTR_RO(offset);
+LOOP_ATTR_RO(sizelimit);
+LOOP_ATTR_RO(autoclear);
+
+static struct attribute *loop_attrs[] = {
+	&loop_attr_backing_file.attr,
+	&loop_attr_offset.attr,
+	&loop_attr_sizelimit.attr,
+	&loop_attr_autoclear.attr,
+	NULL,
+};
+
+static struct attribute_group loop_attribute_group = {
+	.name = "loop",
+	.attrs= loop_attrs,
+};
+
+static int loop_sysfs_init(struct loop_device *lo)
+{
+	return sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
+				  &loop_attribute_group);
+}
+
+static void loop_sysfs_exit(struct loop_device *lo)
+{
+	sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
+			   &loop_attribute_group);
+}
+
 static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 		       struct block_device *bdev, unsigned int arg)
 {
@@ -832,10 +931,11 @@
 	lo->lo_queue->unplug_fn = loop_unplug;
 
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
-		blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN);
+		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
 	set_capacity(lo->lo_disk, size);
 	bd_set_size(bdev, size << 9);
+	loop_sysfs_init(lo);
 	/* let user-space know about the new size */
 	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
 
@@ -854,6 +954,7 @@
 	return 0;
 
 out_clr:
+	loop_sysfs_exit(lo);
 	lo->lo_thread = NULL;
 	lo->lo_device = NULL;
 	lo->lo_backing_file = NULL;
@@ -950,6 +1051,7 @@
 	set_capacity(lo->lo_disk, 0);
 	if (bdev) {
 		bd_set_size(bdev, 0);
+		loop_sysfs_exit(lo);
 		/* let user-space know about this change */
 		kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
 	}
@@ -1409,11 +1511,11 @@
 {
 	struct loop_device *lo = bdev->bd_disk->private_data;
 
-	lock_kernel();
+	mutex_lock(&loop_mutex);
 	mutex_lock(&lo->lo_ctl_mutex);
 	lo->lo_refcnt++;
 	mutex_unlock(&lo->lo_ctl_mutex);
-	unlock_kernel();
+	mutex_unlock(&loop_mutex);
 
 	return 0;
 }
@@ -1423,7 +1525,7 @@
 	struct loop_device *lo = disk->private_data;
 	int err;
 
-	lock_kernel();
+	mutex_lock(&loop_mutex);
 	mutex_lock(&lo->lo_ctl_mutex);
 
 	if (--lo->lo_refcnt)
@@ -1448,7 +1550,7 @@
 out:
 	mutex_unlock(&lo->lo_ctl_mutex);
 out_unlocked:
-	lock_kernel();
+	mutex_unlock(&loop_mutex);
 	return 0;
 }
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 0daa422..a32fb41 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -24,7 +24,7 @@
 #include <linux/errno.h>
 #include <linux/file.h>
 #include <linux/ioctl.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/compiler.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -53,6 +53,7 @@
 #define DBG_BLKDEV      0x0100
 #define DBG_RX          0x0200
 #define DBG_TX          0x0400
+static DEFINE_MUTEX(nbd_mutex);
 static unsigned int debugflags;
 #endif /* NDEBUG */
 
@@ -717,11 +718,11 @@
 	dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n",
 			lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg);
 
-	lock_kernel();
+	mutex_lock(&nbd_mutex);
 	mutex_lock(&lo->tx_lock);
 	error = __nbd_ioctl(bdev, lo, cmd, arg);
 	mutex_unlock(&lo->tx_lock);
-	unlock_kernel();
+	mutex_unlock(&nbd_mutex);
 
 	return error;
 }
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 2284b4f..87311eb 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -310,8 +310,7 @@
 			break;
 
 		/* filter out block requests we don't understand */
-		if (rq->cmd_type != REQ_TYPE_FS &&
-		    !(rq->cmd_flags & REQ_HARDBARRIER)) {
+		if (rq->cmd_type != REQ_TYPE_FS) {
 			blk_end_request_all(rq, 0);
 			continue;
 		}
@@ -439,7 +438,7 @@
 	blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
 
 	blk_queue_prep_rq(q, blk_queue_start_tag);
-	blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH);
+	blk_queue_flush(q, REQ_FLUSH);
 
 	disk->queue = q;
 
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 76f8565..62cec6a 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -138,9 +138,10 @@
 #include <linux/cdrom.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <asm/uaccess.h>
 
+static DEFINE_MUTEX(pcd_mutex);
 static DEFINE_SPINLOCK(pcd_lock);
 
 module_param(verbose, bool, 0644);
@@ -227,9 +228,9 @@
 	struct pcd_unit *cd = bdev->bd_disk->private_data;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&pcd_mutex);
 	ret = cdrom_open(&cd->info, bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&pcd_mutex);
 
 	return ret;
 }
@@ -237,9 +238,9 @@
 static int pcd_block_release(struct gendisk *disk, fmode_t mode)
 {
 	struct pcd_unit *cd = disk->private_data;
-	lock_kernel();
+	mutex_lock(&pcd_mutex);
 	cdrom_release(&cd->info, mode);
-	unlock_kernel();
+	mutex_unlock(&pcd_mutex);
 	return 0;
 }
 
@@ -249,9 +250,9 @@
 	struct pcd_unit *cd = bdev->bd_disk->private_data;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&pcd_mutex);
 	ret = cdrom_ioctl(&cd->info, bdev, mode, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&pcd_mutex);
 
 	return ret;
 }
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 985f0d4..c0ee155 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -153,10 +153,11 @@
 #include <linux/blkdev.h>
 #include <linux/blkpg.h>
 #include <linux/kernel.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <asm/uaccess.h>
 #include <linux/workqueue.h>
 
+static DEFINE_MUTEX(pd_mutex);
 static DEFINE_SPINLOCK(pd_lock);
 
 module_param(verbose, bool, 0);
@@ -736,14 +737,14 @@
 {
 	struct pd_unit *disk = bdev->bd_disk->private_data;
 
-	lock_kernel();
+	mutex_lock(&pd_mutex);
 	disk->access++;
 
 	if (disk->removable) {
 		pd_special_command(disk, pd_media_check);
 		pd_special_command(disk, pd_door_lock);
 	}
-	unlock_kernel();
+	mutex_unlock(&pd_mutex);
 	return 0;
 }
 
@@ -771,10 +772,10 @@
 
 	switch (cmd) {
 	case CDROMEJECT:
-		lock_kernel();
+		mutex_lock(&pd_mutex);
 		if (disk->access == 1)
 			pd_special_command(disk, pd_eject);
-		unlock_kernel();
+		mutex_unlock(&pd_mutex);
 		return 0;
 	default:
 		return -EINVAL;
@@ -785,10 +786,10 @@
 {
 	struct pd_unit *disk = p->private_data;
 
-	lock_kernel();
+	mutex_lock(&pd_mutex);
 	if (!--disk->access && disk->removable)
 		pd_special_command(disk, pd_door_unlock);
-	unlock_kernel();
+	mutex_unlock(&pd_mutex);
 
 	return 0;
 }
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index 4457b49..635f25d 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -152,9 +152,10 @@
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>
 #include <linux/blkpg.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <asm/uaccess.h>
 
+static DEFINE_MUTEX(pf_mutex);
 static DEFINE_SPINLOCK(pf_spin_lock);
 
 module_param(verbose, bool, 0644);
@@ -302,7 +303,7 @@
 	struct pf_unit *pf = bdev->bd_disk->private_data;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&pf_mutex);
 	pf_identify(pf);
 
 	ret = -ENODEV;
@@ -318,7 +319,7 @@
 	if (pf->removable)
 		pf_lock(pf, 1);
 out:
-	unlock_kernel();
+	mutex_unlock(&pf_mutex);
 	return ret;
 }
 
@@ -349,9 +350,9 @@
 
 	if (pf->access != 1)
 		return -EBUSY;
-	lock_kernel();
+	mutex_lock(&pf_mutex);
 	pf_eject(pf);
-	unlock_kernel();
+	mutex_unlock(&pf_mutex);
 
 	return 0;
 }
@@ -360,9 +361,9 @@
 {
 	struct pf_unit *pf = disk->private_data;
 
-	lock_kernel();
+	mutex_lock(&pf_mutex);
 	if (pf->access <= 0) {
-		unlock_kernel();
+		mutex_unlock(&pf_mutex);
 		return -EINVAL;
 	}
 
@@ -371,7 +372,7 @@
 	if (!pf->access && pf->removable)
 		pf_lock(pf, 0);
 
-	unlock_kernel();
+	mutex_unlock(&pf_mutex);
 	return 0;
 
 }
diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c
index c397b3d..6b9a200 100644
--- a/drivers/block/paride/pg.c
+++ b/drivers/block/paride/pg.c
@@ -162,7 +162,7 @@
 #include <linux/pg.h>
 #include <linux/device.h>
 #include <linux/sched.h>	/* current, TASK_* */
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/jiffies.h>
 
 #include <asm/uaccess.h>
@@ -193,6 +193,7 @@
 
 #define ATAPI_IDENTIFY		0x12
 
+static DEFINE_MUTEX(pg_mutex);
 static int pg_open(struct inode *inode, struct file *file);
 static int pg_release(struct inode *inode, struct file *file);
 static ssize_t pg_read(struct file *filp, char __user *buf,
@@ -234,6 +235,7 @@
 	.write = pg_write,
 	.open = pg_open,
 	.release = pg_release,
+	.llseek = noop_llseek,
 };
 
 static void pg_init_units(void)
@@ -518,7 +520,7 @@
 	struct pg *dev = &devices[unit];
 	int ret = 0;
 
-	lock_kernel();
+	mutex_lock(&pg_mutex);
 	if ((unit >= PG_UNITS) || (!dev->present)) {
 		ret = -ENODEV;
 		goto out;
@@ -547,7 +549,7 @@
 	file->private_data = dev;
 
 out:
-	unlock_kernel();
+	mutex_unlock(&pg_mutex);
 	return ret;
 }
 
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index bc5825f..7179f79 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -146,7 +146,7 @@
 #include <linux/mtio.h>
 #include <linux/device.h>
 #include <linux/sched.h>	/* current, TASK_*, schedule_timeout() */
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <asm/uaccess.h>
 
@@ -189,6 +189,7 @@
 #define ATAPI_MODE_SENSE	0x1a
 #define ATAPI_LOG_SENSE		0x4d
 
+static DEFINE_MUTEX(pt_mutex);
 static int pt_open(struct inode *inode, struct file *file);
 static long pt_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 static int pt_release(struct inode *inode, struct file *file);
@@ -239,6 +240,7 @@
 	.unlocked_ioctl = pt_ioctl,
 	.open = pt_open,
 	.release = pt_release,
+	.llseek = noop_llseek,
 };
 
 /* sysfs class support */
@@ -650,9 +652,9 @@
 	struct pt_unit *tape = pt + unit;
 	int err;
 
-	lock_kernel();
+	mutex_lock(&pt_mutex);
 	if (unit >= PT_UNITS || (!tape->present)) {
-		unlock_kernel();
+		mutex_unlock(&pt_mutex);
 		return -ENODEV;
 	}
 
@@ -681,12 +683,12 @@
 	}
 
 	file->private_data = tape;
-	unlock_kernel();
+	mutex_unlock(&pt_mutex);
 	return 0;
 
 out:
 	atomic_inc(&tape->available);
-	unlock_kernel();
+	mutex_unlock(&pt_mutex);
 	return err;
 }
 
@@ -704,15 +706,15 @@
 		switch (mtop.mt_op) {
 
 		case MTREW:
-			lock_kernel();
+			mutex_lock(&pt_mutex);
 			pt_rewind(tape);
-			unlock_kernel();
+			mutex_unlock(&pt_mutex);
 			return 0;
 
 		case MTWEOF:
-			lock_kernel();
+			mutex_lock(&pt_mutex);
 			pt_write_fm(tape);
-			unlock_kernel();
+			mutex_unlock(&pt_mutex);
 			return 0;
 
 		default:
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 37a2bb5..19b3568 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -57,7 +57,6 @@
 #include <linux/seq_file.h>
 #include <linux/miscdevice.h>
 #include <linux/freezer.h>
-#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <scsi/scsi_cmnd.h>
@@ -86,6 +85,7 @@
 
 #define ZONE(sector, pd) (((sector) + (pd)->offset) & ~((pd)->settings.size - 1))
 
+static DEFINE_MUTEX(pktcdvd_mutex);
 static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
 static struct proc_dir_entry *pkt_proc;
 static int pktdev_major;
@@ -753,7 +753,6 @@
 
 	rq->timeout = 60*HZ;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->cmd_flags |= REQ_HARDBARRIER;
 	if (cgc->quiet)
 		rq->cmd_flags |= REQ_QUIET;
 
@@ -2383,7 +2382,7 @@
 
 	VPRINTK(DRIVER_NAME": entering open\n");
 
-	lock_kernel();
+	mutex_lock(&pktcdvd_mutex);
 	mutex_lock(&ctl_mutex);
 	pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev));
 	if (!pd) {
@@ -2411,7 +2410,7 @@
 	}
 
 	mutex_unlock(&ctl_mutex);
-	unlock_kernel();
+	mutex_unlock(&pktcdvd_mutex);
 	return 0;
 
 out_dec:
@@ -2419,7 +2418,7 @@
 out:
 	VPRINTK(DRIVER_NAME": failed open (%d)\n", ret);
 	mutex_unlock(&ctl_mutex);
-	unlock_kernel();
+	mutex_unlock(&pktcdvd_mutex);
 	return ret;
 }
 
@@ -2428,7 +2427,7 @@
 	struct pktcdvd_device *pd = disk->private_data;
 	int ret = 0;
 
-	lock_kernel();
+	mutex_lock(&pktcdvd_mutex);
 	mutex_lock(&ctl_mutex);
 	pd->refcnt--;
 	BUG_ON(pd->refcnt < 0);
@@ -2437,7 +2436,7 @@
 		pkt_release_dev(pd, flush);
 	}
 	mutex_unlock(&ctl_mutex);
-	unlock_kernel();
+	mutex_unlock(&pktcdvd_mutex);
 	return ret;
 }
 
@@ -2773,7 +2772,7 @@
 	VPRINTK("pkt_ioctl: cmd %x, dev %d:%d\n", cmd,
 		MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
 
-	lock_kernel();
+	mutex_lock(&pktcdvd_mutex);
 	switch (cmd) {
 	case CDROMEJECT:
 		/*
@@ -2798,7 +2797,7 @@
 		VPRINTK(DRIVER_NAME": Unknown ioctl for %s (%x)\n", pd->name, cmd);
 		ret = -ENOTTY;
 	}
-	unlock_kernel();
+	mutex_unlock(&pktcdvd_mutex);
 
 	return ret;
 }
@@ -3046,6 +3045,7 @@
 	.compat_ioctl	= pkt_ctl_compat_ioctl,
 #endif
 	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice pkt_misc = {
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 03688c2..8e1ce2e 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -468,7 +468,7 @@
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
 	blk_queue_logical_block_size(queue, dev->blk_size);
 
-	blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH);
+	blk_queue_flush(queue, REQ_FLUSH);
 
 	blk_queue_max_segments(queue, -1);
 	blk_queue_max_segment_size(queue, dev->bounce_size);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
new file mode 100644
index 0000000..6ec9d53
--- /dev/null
+++ b/drivers/block/rbd.c
@@ -0,0 +1,1841 @@
+/*
+   rbd.c -- Export ceph rados objects as a Linux block device
+
+
+   based on drivers/block/osdblk.c:
+
+   Copyright 2009 Red Hat, Inc.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; see the file COPYING.  If not, write to
+   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+
+
+   Instructions for use
+   --------------------
+
+   1) Map a Linux block device to an existing rbd image.
+
+      Usage: <mon ip addr> <options> <pool name> <rbd image name> [snap name]
+
+      $ echo "192.168.0.1 name=admin rbd foo" > /sys/class/rbd/add
+
+      The snapshot name can be "-" or omitted to map the image read/write.
+
+   2) List all active blkdev<->object mappings.
+
+      In this example, we have performed step #1 twice, creating two blkdevs,
+      mapped to two separate rados objects in the rados rbd pool
+
+      $ cat /sys/class/rbd/list
+      #id     major   client_name     pool    name    snap    KB
+      0       254     client4143      rbd     foo     -      1024000
+
+      The columns, in order, are:
+      - blkdev unique id
+      - blkdev assigned major
+      - rados client id
+      - rados pool name
+      - rados block device name
+      - mapped snapshot ("-" if none)
+      - device size in KB
+
+
+   3) Create a snapshot.
+
+      Usage: <blkdev id> <snapname>
+
+      $ echo "0 mysnap" > /sys/class/rbd/snap_create
+
+
+   4) Listing a snapshot.
+
+      $ cat /sys/class/rbd/snaps_list
+      #id     snap    KB
+      0       -       1024000 (*)
+      0       foo     1024000
+
+      The columns, in order, are:
+      - blkdev unique id
+      - snapshot name, '-' means none (active read/write version)
+      - size of device at time of snapshot
+      - the (*) indicates this is the active version
+
+   5) Rollback to snapshot.
+
+      Usage: <blkdev id> <snapname>
+
+      $ echo "0 mysnap" > /sys/class/rbd/snap_rollback
+
+
+   6) Mapping an image using snapshot.
+
+      A snapshot mapping is read-only. This is being done by passing
+      snap=<snapname> to the options when adding a device.
+
+      $ echo "192.168.0.1 name=admin,snap=mysnap rbd foo" > /sys/class/rbd/add
+
+
+   7) Remove an active blkdev<->rbd image mapping.
+
+      In this example, we remove the mapping with blkdev unique id 1.
+
+      $ echo 1 > /sys/class/rbd/remove
+
+
+   NOTE:  The actual creation and deletion of rados objects is outside the scope
+   of this driver.
+
+ */
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osd_client.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/decode.h>
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+
+#include "rbd_types.h"
+
+#define DRV_NAME "rbd"
+#define DRV_NAME_LONG "rbd (rados block device)"
+
+#define RBD_MINORS_PER_MAJOR	256		/* max minors per blkdev */
+
+#define RBD_MAX_MD_NAME_LEN	(96 + sizeof(RBD_SUFFIX))
+#define RBD_MAX_POOL_NAME_LEN	64
+#define RBD_MAX_SNAP_NAME_LEN	32
+#define RBD_MAX_OPT_LEN		1024
+
+#define RBD_SNAP_HEAD_NAME	"-"
+
+#define DEV_NAME_LEN		32
+
+/*
+ * block device image metadata (in-memory version)
+ */
+struct rbd_image_header {
+	u64 image_size;
+	char block_name[32];
+	__u8 obj_order;
+	__u8 crypt_type;
+	__u8 comp_type;
+	struct rw_semaphore snap_rwsem;
+	struct ceph_snap_context *snapc;
+	size_t snap_names_len;
+	u64 snap_seq;
+	u32 total_snaps;
+
+	char *snap_names;
+	u64 *snap_sizes;
+};
+
+/*
+ * an instance of the client.  multiple devices may share a client.
+ */
+struct rbd_client {
+	struct ceph_client	*client;
+	struct kref		kref;
+	struct list_head	node;
+};
+
+/*
+ * a single io request
+ */
+struct rbd_request {
+	struct request		*rq;		/* blk layer request */
+	struct bio		*bio;		/* cloned bio */
+	struct page		**pages;	/* list of used pages */
+	u64			len;
+};
+
+/*
+ * a single device
+ */
+struct rbd_device {
+	int			id;		/* blkdev unique id */
+
+	int			major;		/* blkdev assigned major */
+	struct gendisk		*disk;		/* blkdev's gendisk and rq */
+	struct request_queue	*q;
+
+	struct ceph_client	*client;
+	struct rbd_client	*rbd_client;
+
+	char			name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */
+
+	spinlock_t		lock;		/* queue lock */
+
+	struct rbd_image_header	header;
+	char			obj[RBD_MAX_OBJ_NAME_LEN]; /* rbd image name */
+	int			obj_len;
+	char			obj_md_name[RBD_MAX_MD_NAME_LEN]; /* hdr nm. */
+	char			pool_name[RBD_MAX_POOL_NAME_LEN];
+	int			poolid;
+
+	char                    snap_name[RBD_MAX_SNAP_NAME_LEN];
+	u32 cur_snap;	/* index+1 of current snapshot within snap context
+			   0 - for the head */
+	int read_only;
+
+	struct list_head	node;
+};
+
+static spinlock_t node_lock;      /* protects client get/put */
+
+static struct class *class_rbd;	  /* /sys/class/rbd */
+static DEFINE_MUTEX(ctl_mutex);	  /* Serialize open/close/setup/teardown */
+static LIST_HEAD(rbd_dev_list);    /* devices */
+static LIST_HEAD(rbd_client_list);      /* clients */
+
+
+static int rbd_open(struct block_device *bdev, fmode_t mode)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct rbd_device *rbd_dev = disk->private_data;
+
+	set_device_ro(bdev, rbd_dev->read_only);
+
+	if ((mode & FMODE_WRITE) && rbd_dev->read_only)
+		return -EROFS;
+
+	return 0;
+}
+
+static const struct block_device_operations rbd_bd_ops = {
+	.owner			= THIS_MODULE,
+	.open			= rbd_open,
+};
+
+/*
+ * Initialize an rbd client instance.
+ * We own *opt.
+ */
+static struct rbd_client *rbd_client_create(struct ceph_options *opt)
+{
+	struct rbd_client *rbdc;
+	int ret = -ENOMEM;
+
+	dout("rbd_client_create\n");
+	rbdc = kmalloc(sizeof(struct rbd_client), GFP_KERNEL);
+	if (!rbdc)
+		goto out_opt;
+
+	kref_init(&rbdc->kref);
+	INIT_LIST_HEAD(&rbdc->node);
+
+	rbdc->client = ceph_create_client(opt, rbdc);
+	if (IS_ERR(rbdc->client))
+		goto out_rbdc;
+	opt = NULL; /* Now rbdc->client is responsible for opt */
+
+	ret = ceph_open_session(rbdc->client);
+	if (ret < 0)
+		goto out_err;
+
+	spin_lock(&node_lock);
+	list_add_tail(&rbdc->node, &rbd_client_list);
+	spin_unlock(&node_lock);
+
+	dout("rbd_client_create created %p\n", rbdc);
+	return rbdc;
+
+out_err:
+	ceph_destroy_client(rbdc->client);
+out_rbdc:
+	kfree(rbdc);
+out_opt:
+	if (opt)
+		ceph_destroy_options(opt);
+	return ERR_PTR(ret);
+}
+
+/*
+ * Find a ceph client with specific addr and configuration.
+ */
+static struct rbd_client *__rbd_client_find(struct ceph_options *opt)
+{
+	struct rbd_client *client_node;
+
+	if (opt->flags & CEPH_OPT_NOSHARE)
+		return NULL;
+
+	list_for_each_entry(client_node, &rbd_client_list, node)
+		if (ceph_compare_options(opt, client_node->client) == 0)
+			return client_node;
+	return NULL;
+}
+
+/*
+ * Get a ceph client with specific addr and configuration, if one does
+ * not exist create it.
+ */
+static int rbd_get_client(struct rbd_device *rbd_dev, const char *mon_addr,
+			  char *options)
+{
+	struct rbd_client *rbdc;
+	struct ceph_options *opt;
+	int ret;
+
+	ret = ceph_parse_options(&opt, options, mon_addr,
+				 mon_addr + strlen(mon_addr), NULL, NULL);
+	if (ret < 0)
+		return ret;
+
+	spin_lock(&node_lock);
+	rbdc = __rbd_client_find(opt);
+	if (rbdc) {
+		ceph_destroy_options(opt);
+
+		/* using an existing client */
+		kref_get(&rbdc->kref);
+		rbd_dev->rbd_client = rbdc;
+		rbd_dev->client = rbdc->client;
+		spin_unlock(&node_lock);
+		return 0;
+	}
+	spin_unlock(&node_lock);
+
+	rbdc = rbd_client_create(opt);
+	if (IS_ERR(rbdc))
+		return PTR_ERR(rbdc);
+
+	rbd_dev->rbd_client = rbdc;
+	rbd_dev->client = rbdc->client;
+	return 0;
+}
+
+/*
+ * Destroy ceph client
+ */
+static void rbd_client_release(struct kref *kref)
+{
+	struct rbd_client *rbdc = container_of(kref, struct rbd_client, kref);
+
+	dout("rbd_release_client %p\n", rbdc);
+	spin_lock(&node_lock);
+	list_del(&rbdc->node);
+	spin_unlock(&node_lock);
+
+	ceph_destroy_client(rbdc->client);
+	kfree(rbdc);
+}
+
+/*
+ * Drop reference to ceph client node. If it's not referenced anymore, release
+ * it.
+ */
+static void rbd_put_client(struct rbd_device *rbd_dev)
+{
+	kref_put(&rbd_dev->rbd_client->kref, rbd_client_release);
+	rbd_dev->rbd_client = NULL;
+	rbd_dev->client = NULL;
+}
+
+
+/*
+ * Create a new header structure, translate header format from the on-disk
+ * header.
+ */
+static int rbd_header_from_disk(struct rbd_image_header *header,
+				 struct rbd_image_header_ondisk *ondisk,
+				 int allocated_snaps,
+				 gfp_t gfp_flags)
+{
+	int i;
+	u32 snap_count = le32_to_cpu(ondisk->snap_count);
+	int ret = -ENOMEM;
+
+	init_rwsem(&header->snap_rwsem);
+
+	header->snap_names_len = le64_to_cpu(ondisk->snap_names_len);
+	header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
+				snap_count *
+				 sizeof(struct rbd_image_snap_ondisk),
+				gfp_flags);
+	if (!header->snapc)
+		return -ENOMEM;
+	if (snap_count) {
+		header->snap_names = kmalloc(header->snap_names_len,
+					     GFP_KERNEL);
+		if (!header->snap_names)
+			goto err_snapc;
+		header->snap_sizes = kmalloc(snap_count * sizeof(u64),
+					     GFP_KERNEL);
+		if (!header->snap_sizes)
+			goto err_names;
+	} else {
+		header->snap_names = NULL;
+		header->snap_sizes = NULL;
+	}
+	memcpy(header->block_name, ondisk->block_name,
+	       sizeof(ondisk->block_name));
+
+	header->image_size = le64_to_cpu(ondisk->image_size);
+	header->obj_order = ondisk->options.order;
+	header->crypt_type = ondisk->options.crypt_type;
+	header->comp_type = ondisk->options.comp_type;
+
+	atomic_set(&header->snapc->nref, 1);
+	header->snap_seq = le64_to_cpu(ondisk->snap_seq);
+	header->snapc->num_snaps = snap_count;
+	header->total_snaps = snap_count;
+
+	if (snap_count &&
+	    allocated_snaps == snap_count) {
+		for (i = 0; i < snap_count; i++) {
+			header->snapc->snaps[i] =
+				le64_to_cpu(ondisk->snaps[i].id);
+			header->snap_sizes[i] =
+				le64_to_cpu(ondisk->snaps[i].image_size);
+		}
+
+		/* copy snapshot names */
+		memcpy(header->snap_names, &ondisk->snaps[i],
+			header->snap_names_len);
+	}
+
+	return 0;
+
+err_names:
+	kfree(header->snap_names);
+err_snapc:
+	kfree(header->snapc);
+	return ret;
+}
+
+static int snap_index(struct rbd_image_header *header, int snap_num)
+{
+	return header->total_snaps - snap_num;
+}
+
+static u64 cur_snap_id(struct rbd_device *rbd_dev)
+{
+	struct rbd_image_header *header = &rbd_dev->header;
+
+	if (!rbd_dev->cur_snap)
+		return 0;
+
+	return header->snapc->snaps[snap_index(header, rbd_dev->cur_snap)];
+}
+
+static int snap_by_name(struct rbd_image_header *header, const char *snap_name,
+			u64 *seq, u64 *size)
+{
+	int i;
+	char *p = header->snap_names;
+
+	for (i = 0; i < header->total_snaps; i++, p += strlen(p) + 1) {
+		if (strcmp(snap_name, p) == 0)
+			break;
+	}
+	if (i == header->total_snaps)
+		return -ENOENT;
+	if (seq)
+		*seq = header->snapc->snaps[i];
+
+	if (size)
+		*size = header->snap_sizes[i];
+
+	return i;
+}
+
+static int rbd_header_set_snap(struct rbd_device *dev,
+			       const char *snap_name,
+			       u64 *size)
+{
+	struct rbd_image_header *header = &dev->header;
+	struct ceph_snap_context *snapc = header->snapc;
+	int ret = -ENOENT;
+
+	down_write(&header->snap_rwsem);
+
+	if (!snap_name ||
+	    !*snap_name ||
+	    strcmp(snap_name, "-") == 0 ||
+	    strcmp(snap_name, RBD_SNAP_HEAD_NAME) == 0) {
+		if (header->total_snaps)
+			snapc->seq = header->snap_seq;
+		else
+			snapc->seq = 0;
+		dev->cur_snap = 0;
+		dev->read_only = 0;
+		if (size)
+			*size = header->image_size;
+	} else {
+		ret = snap_by_name(header, snap_name, &snapc->seq, size);
+		if (ret < 0)
+			goto done;
+
+		dev->cur_snap = header->total_snaps - ret;
+		dev->read_only = 1;
+	}
+
+	ret = 0;
+done:
+	up_write(&header->snap_rwsem);
+	return ret;
+}
+
+static void rbd_header_free(struct rbd_image_header *header)
+{
+	kfree(header->snapc);
+	kfree(header->snap_names);
+	kfree(header->snap_sizes);
+}
+
+/*
+ * get the actual striped segment name, offset and length
+ */
+static u64 rbd_get_segment(struct rbd_image_header *header,
+			   const char *block_name,
+			   u64 ofs, u64 len,
+			   char *seg_name, u64 *segofs)
+{
+	u64 seg = ofs >> header->obj_order;
+
+	if (seg_name)
+		snprintf(seg_name, RBD_MAX_SEG_NAME_LEN,
+			 "%s.%012llx", block_name, seg);
+
+	ofs = ofs & ((1 << header->obj_order) - 1);
+	len = min_t(u64, len, (1 << header->obj_order) - ofs);
+
+	if (segofs)
+		*segofs = ofs;
+
+	return len;
+}
+
+/*
+ * bio helpers
+ */
+
+static void bio_chain_put(struct bio *chain)
+{
+	struct bio *tmp;
+
+	while (chain) {
+		tmp = chain;
+		chain = chain->bi_next;
+		bio_put(tmp);
+	}
+}
+
+/*
+ * zeros a bio chain, starting at specific offset
+ */
+static void zero_bio_chain(struct bio *chain, int start_ofs)
+{
+	struct bio_vec *bv;
+	unsigned long flags;
+	void *buf;
+	int i;
+	int pos = 0;
+
+	while (chain) {
+		bio_for_each_segment(bv, chain, i) {
+			if (pos + bv->bv_len > start_ofs) {
+				int remainder = max(start_ofs - pos, 0);
+				buf = bvec_kmap_irq(bv, &flags);
+				memset(buf + remainder, 0,
+				       bv->bv_len - remainder);
+				bvec_kunmap_irq(buf, &flags);
+			}
+			pos += bv->bv_len;
+		}
+
+		chain = chain->bi_next;
+	}
+}
+
+/*
+ * bio_chain_clone - clone a chain of bios up to a certain length.
+ * might return a bio_pair that will need to be released.
+ */
+static struct bio *bio_chain_clone(struct bio **old, struct bio **next,
+				   struct bio_pair **bp,
+				   int len, gfp_t gfpmask)
+{
+	struct bio *tmp, *old_chain = *old, *new_chain = NULL, *tail = NULL;
+	int total = 0;
+
+	if (*bp) {
+		bio_pair_release(*bp);
+		*bp = NULL;
+	}
+
+	while (old_chain && (total < len)) {
+		tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs);
+		if (!tmp)
+			goto err_out;
+
+		if (total + old_chain->bi_size > len) {
+			struct bio_pair *bp;
+
+			/*
+			 * this split can only happen with a single paged bio,
+			 * split_bio will BUG_ON if this is not the case
+			 */
+			dout("bio_chain_clone split! total=%d remaining=%d"
+			     "bi_size=%d\n",
+			     (int)total, (int)len-total,
+			     (int)old_chain->bi_size);
+
+			/* split the bio. We'll release it either in the next
+			   call, or it will have to be released outside */
+			bp = bio_split(old_chain, (len - total) / 512ULL);
+			if (!bp)
+				goto err_out;
+
+			__bio_clone(tmp, &bp->bio1);
+
+			*next = &bp->bio2;
+		} else {
+			__bio_clone(tmp, old_chain);
+			*next = old_chain->bi_next;
+		}
+
+		tmp->bi_bdev = NULL;
+		gfpmask &= ~__GFP_WAIT;
+		tmp->bi_next = NULL;
+
+		if (!new_chain) {
+			new_chain = tail = tmp;
+		} else {
+			tail->bi_next = tmp;
+			tail = tmp;
+		}
+		old_chain = old_chain->bi_next;
+
+		total += tmp->bi_size;
+	}
+
+	BUG_ON(total < len);
+
+	if (tail)
+		tail->bi_next = NULL;
+
+	*old = old_chain;
+
+	return new_chain;
+
+err_out:
+	dout("bio_chain_clone with err\n");
+	bio_chain_put(new_chain);
+	return NULL;
+}
+
+/*
+ * helpers for osd request op vectors.
+ */
+static int rbd_create_rw_ops(struct ceph_osd_req_op **ops,
+			    int num_ops,
+			    int opcode,
+			    u32 payload_len)
+{
+	*ops = kzalloc(sizeof(struct ceph_osd_req_op) * (num_ops + 1),
+		       GFP_NOIO);
+	if (!*ops)
+		return -ENOMEM;
+	(*ops)[0].op = opcode;
+	/*
+	 * op extent offset and length will be set later on
+	 * in calc_raw_layout()
+	 */
+	(*ops)[0].payload_len = payload_len;
+	return 0;
+}
+
+static void rbd_destroy_ops(struct ceph_osd_req_op *ops)
+{
+	kfree(ops);
+}
+
+/*
+ * Send ceph osd request
+ */
+static int rbd_do_request(struct request *rq,
+			  struct rbd_device *dev,
+			  struct ceph_snap_context *snapc,
+			  u64 snapid,
+			  const char *obj, u64 ofs, u64 len,
+			  struct bio *bio,
+			  struct page **pages,
+			  int num_pages,
+			  int flags,
+			  struct ceph_osd_req_op *ops,
+			  int num_reply,
+			  void (*rbd_cb)(struct ceph_osd_request *req,
+					 struct ceph_msg *msg))
+{
+	struct ceph_osd_request *req;
+	struct ceph_file_layout *layout;
+	int ret;
+	u64 bno;
+	struct timespec mtime = CURRENT_TIME;
+	struct rbd_request *req_data;
+	struct ceph_osd_request_head *reqhead;
+	struct rbd_image_header *header = &dev->header;
+
+	ret = -ENOMEM;
+	req_data = kzalloc(sizeof(*req_data), GFP_NOIO);
+	if (!req_data)
+		goto done;
+
+	dout("rbd_do_request len=%lld ofs=%lld\n", len, ofs);
+
+	down_read(&header->snap_rwsem);
+
+	req = ceph_osdc_alloc_request(&dev->client->osdc, flags,
+				      snapc,
+				      ops,
+				      false,
+				      GFP_NOIO, pages, bio);
+	if (IS_ERR(req)) {
+		up_read(&header->snap_rwsem);
+		ret = PTR_ERR(req);
+		goto done_pages;
+	}
+
+	req->r_callback = rbd_cb;
+
+	req_data->rq = rq;
+	req_data->bio = bio;
+	req_data->pages = pages;
+	req_data->len = len;
+
+	req->r_priv = req_data;
+
+	reqhead = req->r_request->front.iov_base;
+	reqhead->snapid = cpu_to_le64(CEPH_NOSNAP);
+
+	strncpy(req->r_oid, obj, sizeof(req->r_oid));
+	req->r_oid_len = strlen(req->r_oid);
+
+	layout = &req->r_file_layout;
+	memset(layout, 0, sizeof(*layout));
+	layout->fl_stripe_unit = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
+	layout->fl_stripe_count = cpu_to_le32(1);
+	layout->fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
+	layout->fl_pg_preferred = cpu_to_le32(-1);
+	layout->fl_pg_pool = cpu_to_le32(dev->poolid);
+	ceph_calc_raw_layout(&dev->client->osdc, layout, snapid,
+			     ofs, &len, &bno, req, ops);
+
+	ceph_osdc_build_request(req, ofs, &len,
+				ops,
+				snapc,
+				&mtime,
+				req->r_oid, req->r_oid_len);
+	up_read(&header->snap_rwsem);
+
+	ret = ceph_osdc_start_request(&dev->client->osdc, req, false);
+	if (ret < 0)
+		goto done_err;
+
+	if (!rbd_cb) {
+		ret = ceph_osdc_wait_request(&dev->client->osdc, req);
+		ceph_osdc_put_request(req);
+	}
+	return ret;
+
+done_err:
+	bio_chain_put(req_data->bio);
+	ceph_osdc_put_request(req);
+done_pages:
+	kfree(req_data);
+done:
+	if (rq)
+		blk_end_request(rq, ret, len);
+	return ret;
+}
+
+/*
+ * Ceph osd op callback
+ */
+static void rbd_req_cb(struct ceph_osd_request *req, struct ceph_msg *msg)
+{
+	struct rbd_request *req_data = req->r_priv;
+	struct ceph_osd_reply_head *replyhead;
+	struct ceph_osd_op *op;
+	__s32 rc;
+	u64 bytes;
+	int read_op;
+
+	/* parse reply */
+	replyhead = msg->front.iov_base;
+	WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
+	op = (void *)(replyhead + 1);
+	rc = le32_to_cpu(replyhead->result);
+	bytes = le64_to_cpu(op->extent.length);
+	read_op = (le32_to_cpu(op->op) == CEPH_OSD_OP_READ);
+
+	dout("rbd_req_cb bytes=%lld readop=%d rc=%d\n", bytes, read_op, rc);
+
+	if (rc == -ENOENT && read_op) {
+		zero_bio_chain(req_data->bio, 0);
+		rc = 0;
+	} else if (rc == 0 && read_op && bytes < req_data->len) {
+		zero_bio_chain(req_data->bio, bytes);
+		bytes = req_data->len;
+	}
+
+	blk_end_request(req_data->rq, rc, bytes);
+
+	if (req_data->bio)
+		bio_chain_put(req_data->bio);
+
+	ceph_osdc_put_request(req);
+	kfree(req_data);
+}
+
+/*
+ * Do a synchronous ceph osd operation
+ */
+static int rbd_req_sync_op(struct rbd_device *dev,
+			   struct ceph_snap_context *snapc,
+			   u64 snapid,
+			   int opcode,
+			   int flags,
+			   struct ceph_osd_req_op *orig_ops,
+			   int num_reply,
+			   const char *obj,
+			   u64 ofs, u64 len,
+			   char *buf)
+{
+	int ret;
+	struct page **pages;
+	int num_pages;
+	struct ceph_osd_req_op *ops = orig_ops;
+	u32 payload_len;
+
+	num_pages = calc_pages_for(ofs , len);
+	pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	if (!orig_ops) {
+		payload_len = (flags & CEPH_OSD_FLAG_WRITE ? len : 0);
+		ret = rbd_create_rw_ops(&ops, 1, opcode, payload_len);
+		if (ret < 0)
+			goto done;
+
+		if ((flags & CEPH_OSD_FLAG_WRITE) && buf) {
+			ret = ceph_copy_to_page_vector(pages, buf, ofs, len);
+			if (ret < 0)
+				goto done_ops;
+		}
+	}
+
+	ret = rbd_do_request(NULL, dev, snapc, snapid,
+			  obj, ofs, len, NULL,
+			  pages, num_pages,
+			  flags,
+			  ops,
+			  2,
+			  NULL);
+	if (ret < 0)
+		goto done_ops;
+
+	if ((flags & CEPH_OSD_FLAG_READ) && buf)
+		ret = ceph_copy_from_page_vector(pages, buf, ofs, ret);
+
+done_ops:
+	if (!orig_ops)
+		rbd_destroy_ops(ops);
+done:
+	ceph_release_page_vector(pages, num_pages);
+	return ret;
+}
+
+/*
+ * Do an asynchronous ceph osd operation
+ */
+static int rbd_do_op(struct request *rq,
+		     struct rbd_device *rbd_dev ,
+		     struct ceph_snap_context *snapc,
+		     u64 snapid,
+		     int opcode, int flags, int num_reply,
+		     u64 ofs, u64 len,
+		     struct bio *bio)
+{
+	char *seg_name;
+	u64 seg_ofs;
+	u64 seg_len;
+	int ret;
+	struct ceph_osd_req_op *ops;
+	u32 payload_len;
+
+	seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
+	if (!seg_name)
+		return -ENOMEM;
+
+	seg_len = rbd_get_segment(&rbd_dev->header,
+				  rbd_dev->header.block_name,
+				  ofs, len,
+				  seg_name, &seg_ofs);
+
+	payload_len = (flags & CEPH_OSD_FLAG_WRITE ? seg_len : 0);
+
+	ret = rbd_create_rw_ops(&ops, 1, opcode, payload_len);
+	if (ret < 0)
+		goto done;
+
+	/* we've taken care of segment sizes earlier when we
+	   cloned the bios. We should never have a segment
+	   truncated at this point */
+	BUG_ON(seg_len < len);
+
+	ret = rbd_do_request(rq, rbd_dev, snapc, snapid,
+			     seg_name, seg_ofs, seg_len,
+			     bio,
+			     NULL, 0,
+			     flags,
+			     ops,
+			     num_reply,
+			     rbd_req_cb);
+done:
+	kfree(seg_name);
+	return ret;
+}
+
+/*
+ * Request async osd write
+ */
+static int rbd_req_write(struct request *rq,
+			 struct rbd_device *rbd_dev,
+			 struct ceph_snap_context *snapc,
+			 u64 ofs, u64 len,
+			 struct bio *bio)
+{
+	return rbd_do_op(rq, rbd_dev, snapc, CEPH_NOSNAP,
+			 CEPH_OSD_OP_WRITE,
+			 CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+			 2,
+			 ofs, len, bio);
+}
+
+/*
+ * Request async osd read
+ */
+static int rbd_req_read(struct request *rq,
+			 struct rbd_device *rbd_dev,
+			 u64 snapid,
+			 u64 ofs, u64 len,
+			 struct bio *bio)
+{
+	return rbd_do_op(rq, rbd_dev, NULL,
+			 (snapid ? snapid : CEPH_NOSNAP),
+			 CEPH_OSD_OP_READ,
+			 CEPH_OSD_FLAG_READ,
+			 2,
+			 ofs, len, bio);
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_read(struct rbd_device *dev,
+			  struct ceph_snap_context *snapc,
+			  u64 snapid,
+			  const char *obj,
+			  u64 ofs, u64 len,
+			  char *buf)
+{
+	return rbd_req_sync_op(dev, NULL,
+			       (snapid ? snapid : CEPH_NOSNAP),
+			       CEPH_OSD_OP_READ,
+			       CEPH_OSD_FLAG_READ,
+			       NULL,
+			       1, obj, ofs, len, buf);
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_rollback_obj(struct rbd_device *dev,
+				     u64 snapid,
+				     const char *obj)
+{
+	struct ceph_osd_req_op *ops;
+	int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_ROLLBACK, 0);
+	if (ret < 0)
+		return ret;
+
+	ops[0].snap.snapid = snapid;
+
+	ret = rbd_req_sync_op(dev, NULL,
+			       CEPH_NOSNAP,
+			       0,
+			       CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+			       ops,
+			       1, obj, 0, 0, NULL);
+
+	rbd_destroy_ops(ops);
+
+	if (ret < 0)
+		return ret;
+
+	return ret;
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_exec(struct rbd_device *dev,
+			     const char *obj,
+			     const char *cls,
+			     const char *method,
+			     const char *data,
+			     int len)
+{
+	struct ceph_osd_req_op *ops;
+	int cls_len = strlen(cls);
+	int method_len = strlen(method);
+	int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_CALL,
+				    cls_len + method_len + len);
+	if (ret < 0)
+		return ret;
+
+	ops[0].cls.class_name = cls;
+	ops[0].cls.class_len = (__u8)cls_len;
+	ops[0].cls.method_name = method;
+	ops[0].cls.method_len = (__u8)method_len;
+	ops[0].cls.argc = 0;
+	ops[0].cls.indata = data;
+	ops[0].cls.indata_len = len;
+
+	ret = rbd_req_sync_op(dev, NULL,
+			       CEPH_NOSNAP,
+			       0,
+			       CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+			       ops,
+			       1, obj, 0, 0, NULL);
+
+	rbd_destroy_ops(ops);
+
+	dout("cls_exec returned %d\n", ret);
+	return ret;
+}
+
+/*
+ * block device queue callback
+ */
+static void rbd_rq_fn(struct request_queue *q)
+{
+	struct rbd_device *rbd_dev = q->queuedata;
+	struct request *rq;
+	struct bio_pair *bp = NULL;
+
+	rq = blk_fetch_request(q);
+
+	while (1) {
+		struct bio *bio;
+		struct bio *rq_bio, *next_bio = NULL;
+		bool do_write;
+		int size, op_size = 0;
+		u64 ofs;
+
+		/* peek at request from block layer */
+		if (!rq)
+			break;
+
+		dout("fetched request\n");
+
+		/* filter out block requests we don't understand */
+		if ((rq->cmd_type != REQ_TYPE_FS)) {
+			__blk_end_request_all(rq, 0);
+			goto next;
+		}
+
+		/* deduce our operation (read, write) */
+		do_write = (rq_data_dir(rq) == WRITE);
+
+		size = blk_rq_bytes(rq);
+		ofs = blk_rq_pos(rq) * 512ULL;
+		rq_bio = rq->bio;
+		if (do_write && rbd_dev->read_only) {
+			__blk_end_request_all(rq, -EROFS);
+			goto next;
+		}
+
+		spin_unlock_irq(q->queue_lock);
+
+		dout("%s 0x%x bytes at 0x%llx\n",
+		     do_write ? "write" : "read",
+		     size, blk_rq_pos(rq) * 512ULL);
+
+		do {
+			/* a bio clone to be passed down to OSD req */
+			dout("rq->bio->bi_vcnt=%d\n", rq->bio->bi_vcnt);
+			op_size = rbd_get_segment(&rbd_dev->header,
+						  rbd_dev->header.block_name,
+						  ofs, size,
+						  NULL, NULL);
+			bio = bio_chain_clone(&rq_bio, &next_bio, &bp,
+					      op_size, GFP_ATOMIC);
+			if (!bio) {
+				spin_lock_irq(q->queue_lock);
+				__blk_end_request_all(rq, -ENOMEM);
+				goto next;
+			}
+
+			/* init OSD command: write or read */
+			if (do_write)
+				rbd_req_write(rq, rbd_dev,
+					      rbd_dev->header.snapc,
+					      ofs,
+					      op_size, bio);
+			else
+				rbd_req_read(rq, rbd_dev,
+					     cur_snap_id(rbd_dev),
+					     ofs,
+					     op_size, bio);
+
+			size -= op_size;
+			ofs += op_size;
+
+			rq_bio = next_bio;
+		} while (size > 0);
+
+		if (bp)
+			bio_pair_release(bp);
+
+		spin_lock_irq(q->queue_lock);
+next:
+		rq = blk_fetch_request(q);
+	}
+}
+
+/*
+ * a queue callback. Makes sure that we don't create a bio that spans across
+ * multiple osd objects. One exception would be with a single page bios,
+ * which we handle later at bio_chain_clone
+ */
+static int rbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
+			  struct bio_vec *bvec)
+{
+	struct rbd_device *rbd_dev = q->queuedata;
+	unsigned int chunk_sectors = 1 << (rbd_dev->header.obj_order - 9);
+	sector_t sector = bmd->bi_sector + get_start_sect(bmd->bi_bdev);
+	unsigned int bio_sectors = bmd->bi_size >> 9;
+	int max;
+
+	max =  (chunk_sectors - ((sector & (chunk_sectors - 1))
+				 + bio_sectors)) << 9;
+	if (max < 0)
+		max = 0; /* bio_add cannot handle a negative return */
+	if (max <= bvec->bv_len && bio_sectors == 0)
+		return bvec->bv_len;
+	return max;
+}
+
+static void rbd_free_disk(struct rbd_device *rbd_dev)
+{
+	struct gendisk *disk = rbd_dev->disk;
+
+	if (!disk)
+		return;
+
+	rbd_header_free(&rbd_dev->header);
+
+	if (disk->flags & GENHD_FL_UP)
+		del_gendisk(disk);
+	if (disk->queue)
+		blk_cleanup_queue(disk->queue);
+	put_disk(disk);
+}
+
+/*
+ * reload the ondisk the header 
+ */
+static int rbd_read_header(struct rbd_device *rbd_dev,
+			   struct rbd_image_header *header)
+{
+	ssize_t rc;
+	struct rbd_image_header_ondisk *dh;
+	int snap_count = 0;
+	u64 snap_names_len = 0;
+
+	while (1) {
+		int len = sizeof(*dh) +
+			  snap_count * sizeof(struct rbd_image_snap_ondisk) +
+			  snap_names_len;
+
+		rc = -ENOMEM;
+		dh = kmalloc(len, GFP_KERNEL);
+		if (!dh)
+			return -ENOMEM;
+
+		rc = rbd_req_sync_read(rbd_dev,
+				       NULL, CEPH_NOSNAP,
+				       rbd_dev->obj_md_name,
+				       0, len,
+				       (char *)dh);
+		if (rc < 0)
+			goto out_dh;
+
+		rc = rbd_header_from_disk(header, dh, snap_count, GFP_KERNEL);
+		if (rc < 0)
+			goto out_dh;
+
+		if (snap_count != header->total_snaps) {
+			snap_count = header->total_snaps;
+			snap_names_len = header->snap_names_len;
+			rbd_header_free(header);
+			kfree(dh);
+			continue;
+		}
+		break;
+	}
+
+out_dh:
+	kfree(dh);
+	return rc;
+}
+
+/*
+ * create a snapshot
+ */
+static int rbd_header_add_snap(struct rbd_device *dev,
+			       const char *snap_name,
+			       gfp_t gfp_flags)
+{
+	int name_len = strlen(snap_name);
+	u64 new_snapid;
+	int ret;
+	void *data, *data_start, *data_end;
+
+	/* we should create a snapshot only if we're pointing at the head */
+	if (dev->cur_snap)
+		return -EINVAL;
+
+	ret = ceph_monc_create_snapid(&dev->client->monc, dev->poolid,
+				      &new_snapid);
+	dout("created snapid=%lld\n", new_snapid);
+	if (ret < 0)
+		return ret;
+
+	data = kmalloc(name_len + 16, gfp_flags);
+	if (!data)
+		return -ENOMEM;
+
+	data_start = data;
+	data_end = data + name_len + 16;
+
+	ceph_encode_string_safe(&data, data_end, snap_name, name_len, bad);
+	ceph_encode_64_safe(&data, data_end, new_snapid, bad);
+
+	ret = rbd_req_sync_exec(dev, dev->obj_md_name, "rbd", "snap_add",
+				data_start, data - data_start);
+
+	kfree(data_start);
+
+	if (ret < 0)
+		return ret;
+
+	dev->header.snapc->seq =  new_snapid;
+
+	return 0;
+bad:
+	return -ERANGE;
+}
+
+/*
+ * only read the first part of the ondisk header, without the snaps info
+ */
+static int rbd_update_snaps(struct rbd_device *rbd_dev)
+{
+	int ret;
+	struct rbd_image_header h;
+	u64 snap_seq;
+
+	ret = rbd_read_header(rbd_dev, &h);
+	if (ret < 0)
+		return ret;
+
+	down_write(&rbd_dev->header.snap_rwsem);
+
+	snap_seq = rbd_dev->header.snapc->seq;
+
+	kfree(rbd_dev->header.snapc);
+	kfree(rbd_dev->header.snap_names);
+	kfree(rbd_dev->header.snap_sizes);
+
+	rbd_dev->header.total_snaps = h.total_snaps;
+	rbd_dev->header.snapc = h.snapc;
+	rbd_dev->header.snap_names = h.snap_names;
+	rbd_dev->header.snap_sizes = h.snap_sizes;
+	rbd_dev->header.snapc->seq = snap_seq;
+
+	up_write(&rbd_dev->header.snap_rwsem);
+
+	return 0;
+}
+
+static int rbd_init_disk(struct rbd_device *rbd_dev)
+{
+	struct gendisk *disk;
+	struct request_queue *q;
+	int rc;
+	u64 total_size = 0;
+
+	/* contact OSD, request size info about the object being mapped */
+	rc = rbd_read_header(rbd_dev, &rbd_dev->header);
+	if (rc)
+		return rc;
+
+	rc = rbd_header_set_snap(rbd_dev, rbd_dev->snap_name, &total_size);
+	if (rc)
+		return rc;
+
+	/* create gendisk info */
+	rc = -ENOMEM;
+	disk = alloc_disk(RBD_MINORS_PER_MAJOR);
+	if (!disk)
+		goto out;
+
+	sprintf(disk->disk_name, DRV_NAME "%d", rbd_dev->id);
+	disk->major = rbd_dev->major;
+	disk->first_minor = 0;
+	disk->fops = &rbd_bd_ops;
+	disk->private_data = rbd_dev;
+
+	/* init rq */
+	rc = -ENOMEM;
+	q = blk_init_queue(rbd_rq_fn, &rbd_dev->lock);
+	if (!q)
+		goto out_disk;
+	blk_queue_merge_bvec(q, rbd_merge_bvec);
+	disk->queue = q;
+
+	q->queuedata = rbd_dev;
+
+	rbd_dev->disk = disk;
+	rbd_dev->q = q;
+
+	/* finally, announce the disk to the world */
+	set_capacity(disk, total_size / 512ULL);
+	add_disk(disk);
+
+	pr_info("%s: added with size 0x%llx\n",
+		disk->disk_name, (unsigned long long)total_size);
+	return 0;
+
+out_disk:
+	put_disk(disk);
+out:
+	return rc;
+}
+
+/********************************************************************
+ * /sys/class/rbd/
+ *                   add	map rados objects to blkdev
+ *                   remove	unmap rados objects
+ *                   list	show mappings
+ *******************************************************************/
+
+static void class_rbd_release(struct class *cls)
+{
+	kfree(cls);
+}
+
+static ssize_t class_rbd_list(struct class *c,
+			      struct class_attribute *attr,
+			      char *data)
+{
+	int n = 0;
+	struct list_head *tmp;
+	int max = PAGE_SIZE;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	n += snprintf(data, max,
+		      "#id\tmajor\tclient_name\tpool\tname\tsnap\tKB\n");
+
+	list_for_each(tmp, &rbd_dev_list) {
+		struct rbd_device *rbd_dev;
+
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		n += snprintf(data+n, max-n,
+			      "%d\t%d\tclient%lld\t%s\t%s\t%s\t%lld\n",
+			      rbd_dev->id,
+			      rbd_dev->major,
+			      ceph_client_id(rbd_dev->client),
+			      rbd_dev->pool_name,
+			      rbd_dev->obj, rbd_dev->snap_name,
+			      rbd_dev->header.image_size >> 10);
+		if (n == max)
+			break;
+	}
+
+	mutex_unlock(&ctl_mutex);
+	return n;
+}
+
+static ssize_t class_rbd_add(struct class *c,
+			     struct class_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct ceph_osd_client *osdc;
+	struct rbd_device *rbd_dev;
+	ssize_t rc = -ENOMEM;
+	int irc, new_id = 0;
+	struct list_head *tmp;
+	char *mon_dev_name;
+	char *options;
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	mon_dev_name = kmalloc(RBD_MAX_OPT_LEN, GFP_KERNEL);
+	if (!mon_dev_name)
+		goto err_out_mod;
+
+	options = kmalloc(RBD_MAX_OPT_LEN, GFP_KERNEL);
+	if (!options)
+		goto err_mon_dev;
+
+	/* new rbd_device object */
+	rbd_dev = kzalloc(sizeof(*rbd_dev), GFP_KERNEL);
+	if (!rbd_dev)
+		goto err_out_opt;
+
+	/* static rbd_device initialization */
+	spin_lock_init(&rbd_dev->lock);
+	INIT_LIST_HEAD(&rbd_dev->node);
+
+	/* generate unique id: find highest unique id, add one */
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	list_for_each(tmp, &rbd_dev_list) {
+		struct rbd_device *rbd_dev;
+
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		if (rbd_dev->id >= new_id)
+			new_id = rbd_dev->id + 1;
+	}
+
+	rbd_dev->id = new_id;
+
+	/* add to global list */
+	list_add_tail(&rbd_dev->node, &rbd_dev_list);
+
+	/* parse add command */
+	if (sscanf(buf, "%" __stringify(RBD_MAX_OPT_LEN) "s "
+		   "%" __stringify(RBD_MAX_OPT_LEN) "s "
+		   "%" __stringify(RBD_MAX_POOL_NAME_LEN) "s "
+		   "%" __stringify(RBD_MAX_OBJ_NAME_LEN) "s"
+		   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+		   mon_dev_name, options, rbd_dev->pool_name,
+		   rbd_dev->obj, rbd_dev->snap_name) < 4) {
+		rc = -EINVAL;
+		goto err_out_slot;
+	}
+
+	if (rbd_dev->snap_name[0] == 0)
+		rbd_dev->snap_name[0] = '-';
+
+	rbd_dev->obj_len = strlen(rbd_dev->obj);
+	snprintf(rbd_dev->obj_md_name, sizeof(rbd_dev->obj_md_name), "%s%s",
+		 rbd_dev->obj, RBD_SUFFIX);
+
+	/* initialize rest of new object */
+	snprintf(rbd_dev->name, DEV_NAME_LEN, DRV_NAME "%d", rbd_dev->id);
+	rc = rbd_get_client(rbd_dev, mon_dev_name, options);
+	if (rc < 0)
+		goto err_out_slot;
+
+	mutex_unlock(&ctl_mutex);
+
+	/* pick the pool */
+	osdc = &rbd_dev->client->osdc;
+	rc = ceph_pg_poolid_by_name(osdc->osdmap, rbd_dev->pool_name);
+	if (rc < 0)
+		goto err_out_client;
+	rbd_dev->poolid = rc;
+
+	/* register our block device */
+	irc = register_blkdev(0, rbd_dev->name);
+	if (irc < 0) {
+		rc = irc;
+		goto err_out_client;
+	}
+	rbd_dev->major = irc;
+
+	/* set up and announce blkdev mapping */
+	rc = rbd_init_disk(rbd_dev);
+	if (rc)
+		goto err_out_blkdev;
+
+	return count;
+
+err_out_blkdev:
+	unregister_blkdev(rbd_dev->major, rbd_dev->name);
+err_out_client:
+	rbd_put_client(rbd_dev);
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+err_out_slot:
+	list_del_init(&rbd_dev->node);
+	mutex_unlock(&ctl_mutex);
+
+	kfree(rbd_dev);
+err_out_opt:
+	kfree(options);
+err_mon_dev:
+	kfree(mon_dev_name);
+err_out_mod:
+	dout("Error adding device %s\n", buf);
+	module_put(THIS_MODULE);
+	return rc;
+}
+
+static struct rbd_device *__rbd_get_dev(unsigned long id)
+{
+	struct list_head *tmp;
+	struct rbd_device *rbd_dev;
+
+	list_for_each(tmp, &rbd_dev_list) {
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		if (rbd_dev->id == id)
+			return rbd_dev;
+	}
+	return NULL;
+}
+
+static ssize_t class_rbd_remove(struct class *c,
+				struct class_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct rbd_device *rbd_dev = NULL;
+	int target_id, rc;
+	unsigned long ul;
+
+	rc = strict_strtoul(buf, 10, &ul);
+	if (rc)
+		return rc;
+
+	/* convert to int; abort if we lost anything in the conversion */
+	target_id = (int) ul;
+	if (target_id != ul)
+		return -EINVAL;
+
+	/* remove object from list immediately */
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	rbd_dev = __rbd_get_dev(target_id);
+	if (rbd_dev)
+		list_del_init(&rbd_dev->node);
+
+	mutex_unlock(&ctl_mutex);
+
+	if (!rbd_dev)
+		return -ENOENT;
+
+	rbd_put_client(rbd_dev);
+
+	/* clean up and free blkdev */
+	rbd_free_disk(rbd_dev);
+	unregister_blkdev(rbd_dev->major, rbd_dev->name);
+	kfree(rbd_dev);
+
+	/* release module ref */
+	module_put(THIS_MODULE);
+
+	return count;
+}
+
+static ssize_t class_rbd_snaps_list(struct class *c,
+			      struct class_attribute *attr,
+			      char *data)
+{
+	struct rbd_device *rbd_dev = NULL;
+	struct list_head *tmp;
+	struct rbd_image_header *header;
+	int i, n = 0, max = PAGE_SIZE;
+	int ret;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	n += snprintf(data, max, "#id\tsnap\tKB\n");
+
+	list_for_each(tmp, &rbd_dev_list) {
+		char *names, *p;
+		struct ceph_snap_context *snapc;
+
+		rbd_dev = list_entry(tmp, struct rbd_device, node);
+		header = &rbd_dev->header;
+
+		down_read(&header->snap_rwsem);
+
+		names = header->snap_names;
+		snapc = header->snapc;
+
+		n += snprintf(data + n, max - n, "%d\t%s\t%lld%s\n",
+			      rbd_dev->id, RBD_SNAP_HEAD_NAME,
+			      header->image_size >> 10,
+			      (!rbd_dev->cur_snap ? " (*)" : ""));
+		if (n == max)
+			break;
+
+		p = names;
+		for (i = 0; i < header->total_snaps; i++, p += strlen(p) + 1) {
+			n += snprintf(data + n, max - n, "%d\t%s\t%lld%s\n",
+			      rbd_dev->id, p, header->snap_sizes[i] >> 10,
+			      (rbd_dev->cur_snap &&
+			       (snap_index(header, i) == rbd_dev->cur_snap) ?
+			       " (*)" : ""));
+			if (n == max)
+				break;
+		}
+
+		up_read(&header->snap_rwsem);
+	}
+
+
+	ret = n;
+	mutex_unlock(&ctl_mutex);
+	return ret;
+}
+
+static ssize_t class_rbd_snaps_refresh(struct class *c,
+				struct class_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct rbd_device *rbd_dev = NULL;
+	int target_id, rc;
+	unsigned long ul;
+	int ret = count;
+
+	rc = strict_strtoul(buf, 10, &ul);
+	if (rc)
+		return rc;
+
+	/* convert to int; abort if we lost anything in the conversion */
+	target_id = (int) ul;
+	if (target_id != ul)
+		return -EINVAL;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	rbd_dev = __rbd_get_dev(target_id);
+	if (!rbd_dev) {
+		ret = -ENOENT;
+		goto done;
+	}
+
+	rc = rbd_update_snaps(rbd_dev);
+	if (rc < 0)
+		ret = rc;
+
+done:
+	mutex_unlock(&ctl_mutex);
+	return ret;
+}
+
+static ssize_t class_rbd_snap_create(struct class *c,
+				struct class_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct rbd_device *rbd_dev = NULL;
+	int target_id, ret;
+	char *name;
+
+	name = kmalloc(RBD_MAX_SNAP_NAME_LEN + 1, GFP_KERNEL);
+	if (!name)
+		return -ENOMEM;
+
+	/* parse snaps add command */
+	if (sscanf(buf, "%d "
+		   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+		   &target_id,
+		   name) != 2) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	rbd_dev = __rbd_get_dev(target_id);
+	if (!rbd_dev) {
+		ret = -ENOENT;
+		goto done_unlock;
+	}
+
+	ret = rbd_header_add_snap(rbd_dev,
+				  name, GFP_KERNEL);
+	if (ret < 0)
+		goto done_unlock;
+
+	ret = rbd_update_snaps(rbd_dev);
+	if (ret < 0)
+		goto done_unlock;
+
+	ret = count;
+done_unlock:
+	mutex_unlock(&ctl_mutex);
+done:
+	kfree(name);
+	return ret;
+}
+
+static ssize_t class_rbd_rollback(struct class *c,
+				struct class_attribute *attr,
+				const char *buf,
+				size_t count)
+{
+	struct rbd_device *rbd_dev = NULL;
+	int target_id, ret;
+	u64 snapid;
+	char snap_name[RBD_MAX_SNAP_NAME_LEN];
+	u64 cur_ofs;
+	char *seg_name;
+
+	/* parse snaps add command */
+	if (sscanf(buf, "%d "
+		   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+		   &target_id,
+		   snap_name) != 2) {
+		return -EINVAL;
+	}
+
+	ret = -ENOMEM;
+	seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
+	if (!seg_name)
+		return ret;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	rbd_dev = __rbd_get_dev(target_id);
+	if (!rbd_dev) {
+		ret = -ENOENT;
+		goto done_unlock;
+	}
+
+	ret = snap_by_name(&rbd_dev->header, snap_name, &snapid, NULL);
+	if (ret < 0)
+		goto done_unlock;
+
+	dout("snapid=%lld\n", snapid);
+
+	cur_ofs = 0;
+	while (cur_ofs < rbd_dev->header.image_size) {
+		cur_ofs += rbd_get_segment(&rbd_dev->header,
+					   rbd_dev->obj,
+					   cur_ofs, (u64)-1,
+					   seg_name, NULL);
+		dout("seg_name=%s\n", seg_name);
+
+		ret = rbd_req_sync_rollback_obj(rbd_dev, snapid, seg_name);
+		if (ret < 0)
+			pr_warning("could not roll back obj %s err=%d\n",
+				   seg_name, ret);
+	}
+
+	ret = rbd_update_snaps(rbd_dev);
+	if (ret < 0)
+		goto done_unlock;
+
+	ret = count;
+
+done_unlock:
+	mutex_unlock(&ctl_mutex);
+	kfree(seg_name);
+
+	return ret;
+}
+
+static struct class_attribute class_rbd_attrs[] = {
+	__ATTR(add,		0200, NULL, class_rbd_add),
+	__ATTR(remove,		0200, NULL, class_rbd_remove),
+	__ATTR(list,		0444, class_rbd_list, NULL),
+	__ATTR(snaps_refresh,	0200, NULL, class_rbd_snaps_refresh),
+	__ATTR(snap_create,	0200, NULL, class_rbd_snap_create),
+	__ATTR(snaps_list,	0444, class_rbd_snaps_list, NULL),
+	__ATTR(snap_rollback,	0200, NULL, class_rbd_rollback),
+	__ATTR_NULL
+};
+
+/*
+ * create control files in sysfs
+ * /sys/class/rbd/...
+ */
+static int rbd_sysfs_init(void)
+{
+	int ret = -ENOMEM;
+
+	class_rbd = kzalloc(sizeof(*class_rbd), GFP_KERNEL);
+	if (!class_rbd)
+		goto out;
+
+	class_rbd->name = DRV_NAME;
+	class_rbd->owner = THIS_MODULE;
+	class_rbd->class_release = class_rbd_release;
+	class_rbd->class_attrs = class_rbd_attrs;
+
+	ret = class_register(class_rbd);
+	if (ret)
+		goto out_class;
+	return 0;
+
+out_class:
+	kfree(class_rbd);
+	class_rbd = NULL;
+	pr_err(DRV_NAME ": failed to create class rbd\n");
+out:
+	return ret;
+}
+
+static void rbd_sysfs_cleanup(void)
+{
+	if (class_rbd)
+		class_destroy(class_rbd);
+	class_rbd = NULL;
+}
+
+int __init rbd_init(void)
+{
+	int rc;
+
+	rc = rbd_sysfs_init();
+	if (rc)
+		return rc;
+	spin_lock_init(&node_lock);
+	pr_info("loaded " DRV_NAME_LONG "\n");
+	return 0;
+}
+
+void __exit rbd_exit(void)
+{
+	rbd_sysfs_cleanup();
+}
+
+module_init(rbd_init);
+module_exit(rbd_exit);
+
+MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
+MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
+MODULE_DESCRIPTION("rados block device");
+
+/* following authorship retained from original osdblk.c */
+MODULE_AUTHOR("Jeff Garzik <jeff@garzik.org>");
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/block/rbd_types.h b/drivers/block/rbd_types.h
new file mode 100644
index 0000000..fc6c678
--- /dev/null
+++ b/drivers/block/rbd_types.h
@@ -0,0 +1,73 @@
+/*
+ * Ceph - scalable distributed file system
+ *
+ * Copyright (C) 2004-2010 Sage Weil <sage@newdream.net>
+ *
+ * This is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2.1, as published by the Free Software
+ * Foundation.  See file COPYING.
+ *
+ */
+
+#ifndef CEPH_RBD_TYPES_H
+#define CEPH_RBD_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * rbd image 'foo' consists of objects
+ *   foo.rbd      - image metadata
+ *   foo.00000000
+ *   foo.00000001
+ *   ...          - data
+ */
+
+#define RBD_SUFFIX		".rbd"
+#define RBD_DIRECTORY           "rbd_directory"
+#define RBD_INFO                "rbd_info"
+
+#define RBD_DEFAULT_OBJ_ORDER	22   /* 4MB */
+#define RBD_MIN_OBJ_ORDER       16
+#define RBD_MAX_OBJ_ORDER       30
+
+#define RBD_MAX_OBJ_NAME_LEN	96
+#define RBD_MAX_SEG_NAME_LEN	128
+
+#define RBD_COMP_NONE		0
+#define RBD_CRYPT_NONE		0
+
+#define RBD_HEADER_TEXT		"<<< Rados Block Device Image >>>\n"
+#define RBD_HEADER_SIGNATURE	"RBD"
+#define RBD_HEADER_VERSION	"001.005"
+
+struct rbd_info {
+	__le64 max_id;
+} __attribute__ ((packed));
+
+struct rbd_image_snap_ondisk {
+	__le64 id;
+	__le64 image_size;
+} __attribute__((packed));
+
+struct rbd_image_header_ondisk {
+	char text[40];
+	char block_name[24];
+	char signature[4];
+	char version[8];
+	struct {
+		__u8 order;
+		__u8 crypt_type;
+		__u8 comp_type;
+		__u8 unused;
+	} __attribute__((packed)) options;
+	__le64 image_size;
+	__le64 snap_seq;
+	__le32 snap_count;
+	__le32 reserved;
+	__le64 snap_names_len;
+	struct rbd_image_snap_ondisk snaps[0];
+} __attribute__((packed));
+
+
+#endif
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 2e46815..75333d0 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -20,7 +20,7 @@
 #include <linux/fd.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/hdreg.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
@@ -222,6 +222,7 @@
 extern int swim_read_sector_data(struct swim __iomem *base,
 				 unsigned char *data);
 
+static DEFINE_MUTEX(swim_mutex);
 static inline void set_swim_mode(struct swim __iomem *base, int enable)
 {
 	struct iwm __iomem *iwm_base;
@@ -666,9 +667,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&swim_mutex);
 	ret = floppy_open(bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&swim_mutex);
 
 	return ret;
 }
@@ -678,7 +679,7 @@
 	struct floppy_state *fs = disk->private_data;
 	struct swim __iomem *base = fs->swd->base;
 
-	lock_kernel();
+	mutex_lock(&swim_mutex);
 	if (fs->ref_count < 0)
 		fs->ref_count = 0;
 	else if (fs->ref_count > 0)
@@ -686,7 +687,7 @@
 
 	if (fs->ref_count == 0)
 		swim_motor(base, OFF);
-	unlock_kernel();
+	mutex_unlock(&swim_mutex);
 
 	return 0;
 }
@@ -704,9 +705,9 @@
 	case FDEJECT:
 		if (fs->ref_count != 1)
 			return -EBUSY;
-		lock_kernel();
+		mutex_lock(&swim_mutex);
 		err = floppy_eject(fs);
-		unlock_kernel();
+		mutex_unlock(&swim_mutex);
 		return err;
 
 	case FDGETPRM:
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index cc6a386..bf3a5b8 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -25,7 +25,7 @@
 #include <linux/ioctl.h>
 #include <linux/blkdev.h>
 #include <linux/interrupt.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <asm/io.h>
@@ -36,6 +36,7 @@
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
 
+static DEFINE_MUTEX(swim3_mutex);
 static struct request_queue *swim3_queue;
 static struct gendisk *disks[2];
 static struct request *fd_req;
@@ -873,9 +874,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&swim3_mutex);
 	ret = floppy_locked_ioctl(bdev, mode, cmd, param);
-	unlock_kernel();
+	mutex_unlock(&swim3_mutex);
 
 	return ret;
 }
@@ -953,9 +954,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&swim3_mutex);
 	ret = floppy_open(bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&swim3_mutex);
 
 	return ret;
 }
@@ -964,13 +965,13 @@
 {
 	struct floppy_state *fs = disk->private_data;
 	struct swim3 __iomem *sw = fs->swim3;
-	lock_kernel();
+	mutex_lock(&swim3_mutex);
 	if (fs->ref_count > 0 && --fs->ref_count == 0) {
 		swim3_action(fs, MOTOR_OFF);
 		out_8(&sw->control_bic, 0xff);
 		swim3_select(fs, RELAX);
 	}
-	unlock_kernel();
+	mutex_unlock(&swim3_mutex);
 	return 0;
 }
 
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index c48e148..b5690a0 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -28,7 +28,7 @@
 #include <linux/timer.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <scsi/scsi.h>
 
 #define DRV_NAME "ub"
@@ -248,6 +248,7 @@
 	spinlock_t lock;
 };
 
+static DEFINE_MUTEX(ub_mutex);
 static inline void ub_init_completion(struct ub_completion *x)
 {
 	x->done = 0;
@@ -1715,9 +1716,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ub_mutex);
 	ret = ub_bd_open(bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&ub_mutex);
 
 	return ret;
 }
@@ -1730,9 +1731,9 @@
 	struct ub_lun *lun = disk->private_data;
 	struct ub_dev *sc = lun->udev;
 
-	lock_kernel();
+	mutex_lock(&ub_mutex);
 	ub_put(sc);
-	unlock_kernel();
+	mutex_unlock(&ub_mutex);
 
 	return 0;
 }
@@ -1747,9 +1748,9 @@
 	void __user *usermem = (void __user *) arg;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ub_mutex);
 	ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, usermem);
-	unlock_kernel();
+	mutex_unlock(&ub_mutex);
 
 	return ret;
 }
diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c
index f651e51..e2ff697 100644
--- a/drivers/block/viodasd.c
+++ b/drivers/block/viodasd.c
@@ -41,7 +41,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/dma-mapping.h>
 #include <linux/completion.h>
 #include <linux/device.h>
@@ -73,6 +73,7 @@
 	MAX_DISK_NAME = FIELD_SIZEOF(struct gendisk, disk_name)
 };
 
+static DEFINE_MUTEX(viodasd_mutex);
 static DEFINE_SPINLOCK(viodasd_spinlock);
 
 #define VIOMAXREQ		16
@@ -180,9 +181,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&viodasd_mutex);
 	ret = viodasd_open(bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&viodasd_mutex);
 
 	return ret;
 }
@@ -196,7 +197,7 @@
 	struct viodasd_device *d = disk->private_data;
 	HvLpEvent_Rc hvrc;
 
-	lock_kernel();
+	mutex_lock(&viodasd_mutex);
 	/* Send the event to OS/400.  We DON'T expect a response */
 	hvrc = HvCallEvent_signalLpEventFast(viopath_hostLp,
 			HvLpEvent_Type_VirtualIo,
@@ -210,7 +211,7 @@
 	if (hvrc != 0)
 		pr_warning("HV close call failed %d\n", (int)hvrc);
 
-	unlock_kernel();
+	mutex_unlock(&viodasd_mutex);
 
 	return 0;
 }
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 1101e25..6ecf89c 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -2,7 +2,6 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
 #include <linux/hdreg.h>
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
@@ -128,9 +127,6 @@
 		}
 	}
 
-	if (vbr->req->cmd_flags & REQ_HARDBARRIER)
-		vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER;
-
 	sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
 
 	/*
@@ -222,8 +218,8 @@
 	return err;
 }
 
-static int virtblk_locked_ioctl(struct block_device *bdev, fmode_t mode,
-			 unsigned cmd, unsigned long data)
+static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long data)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	struct virtio_blk *vblk = disk->private_data;
@@ -238,18 +234,6 @@
 			      (void __user *)data);
 }
 
-static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long param)
-{
-	int ret;
-
-	lock_kernel();
-	ret = virtblk_locked_ioctl(bdev, mode, cmd, param);
-	unlock_kernel();
-
-	return ret;
-}
-
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
@@ -392,31 +376,9 @@
 	vblk->disk->driverfs_dev = &vdev->dev;
 	index++;
 
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH)) {
-		/*
-		 * If the FLUSH feature is supported we do have support for
-		 * flushing a volatile write cache on the host.  Use that
-		 * to implement write barrier support.
-		 */
-		blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH);
-	} else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER)) {
-		/*
-		 * If the BARRIER feature is supported the host expects us
-		 * to order request by tags.  This implies there is not
-		 * volatile write cache on the host, and that the host
-		 * never re-orders outstanding I/O.  This feature is not
-		 * useful for real life scenarious and deprecated.
-		 */
-		blk_queue_ordered(q, QUEUE_ORDERED_TAG);
-	} else {
-		/*
-		 * If the FLUSH feature is not supported we must assume that
-		 * the host does not perform any kind of volatile write
-		 * caching. We still need to drain the queue to provider
-		 * proper barrier semantics.
-		 */
-		blk_queue_ordered(q, QUEUE_ORDERED_DRAIN);
-	}
+	/* configure queue flush support */
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
+		blk_queue_flush(q, REQ_FLUSH);
 
 	/* If disk is read-only in the host, the guest should obey */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
@@ -535,9 +497,9 @@
 };
 
 static unsigned int features[] = {
-	VIRTIO_BLK_F_BARRIER, VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX,
-	VIRTIO_BLK_F_GEOMETRY, VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
-	VIRTIO_BLK_F_SCSI, VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY
+	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
+	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
+	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY
 };
 
 /*
diff --git a/drivers/block/xd.c b/drivers/block/xd.c
index d5a3cd7..4abd2bc 100644
--- a/drivers/block/xd.c
+++ b/drivers/block/xd.c
@@ -46,7 +46,7 @@
 #include <linux/init.h>
 #include <linux/wait.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/blkpg.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -58,6 +58,7 @@
 
 #include "xd.h"
 
+static DEFINE_MUTEX(xd_mutex);
 static void __init do_xd_setup (int *integers);
 #ifdef MODULE
 static int xd[5] = { -1,-1,-1,-1, };
@@ -381,9 +382,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&xd_mutex);
 	ret = xd_locked_ioctl(bdev, mode, cmd, param);
-	unlock_kernel();
+	mutex_unlock(&xd_mutex);
 
 	return ret;
 }
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index ab735a6..4b33a18 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -41,7 +41,7 @@
 #include <linux/cdrom.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/scatterlist.h>
 
 #include <xen/xen.h>
@@ -69,6 +69,7 @@
 	unsigned long frame[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 };
 
+static DEFINE_MUTEX(blkfront_mutex);
 static const struct block_device_operations xlvbd_block_fops;
 
 #define BLK_RING_SIZE __RING_SIZE((struct blkif_sring *)0, PAGE_SIZE)
@@ -95,7 +96,7 @@
 	struct gnttab_free_callback callback;
 	struct blk_shadow shadow[BLK_RING_SIZE];
 	unsigned long shadow_free;
-	int feature_barrier;
+	unsigned int feature_flush;
 	int is_ready;
 };
 
@@ -418,26 +419,12 @@
 }
 
 
-static int xlvbd_barrier(struct blkfront_info *info)
+static void xlvbd_flush(struct blkfront_info *info)
 {
-	int err;
-	const char *barrier;
-
-	switch (info->feature_barrier) {
-	case QUEUE_ORDERED_DRAIN:	barrier = "enabled (drain)"; break;
-	case QUEUE_ORDERED_TAG:		barrier = "enabled (tag)"; break;
-	case QUEUE_ORDERED_NONE:	barrier = "disabled"; break;
-	default:			return -EINVAL;
-	}
-
-	err = blk_queue_ordered(info->rq, info->feature_barrier);
-
-	if (err)
-		return err;
-
+	blk_queue_flush(info->rq, info->feature_flush);
 	printk(KERN_INFO "blkfront: %s: barriers %s\n",
-	       info->gd->disk_name, barrier);
-	return 0;
+	       info->gd->disk_name,
+	       info->feature_flush ? "enabled" : "disabled");
 }
 
 
@@ -516,7 +503,7 @@
 	info->rq = gd->queue;
 	info->gd = gd;
 
-	xlvbd_barrier(info);
+	xlvbd_flush(info);
 
 	if (vdisk_info & VDISK_READONLY)
 		set_disk_ro(gd, 1);
@@ -662,8 +649,8 @@
 				printk(KERN_WARNING "blkfront: %s: write barrier op failed\n",
 				       info->gd->disk_name);
 				error = -EOPNOTSUPP;
-				info->feature_barrier = QUEUE_ORDERED_NONE;
-				xlvbd_barrier(info);
+				info->feature_flush = 0;
+				xlvbd_flush(info);
 			}
 			/* fall through */
 		case BLKIF_OP_READ:
@@ -1076,20 +1063,20 @@
 	/*
 	 * If there's no "feature-barrier" defined, then it means
 	 * we're dealing with a very old backend which writes
-	 * synchronously; draining will do what needs to get done.
+	 * synchronously; nothing to do.
 	 *
-	 * If there are barriers, then we can do full queued writes
-	 * with tagged barriers.
-	 *
-	 * If barriers are not supported, then there's no much we can
-	 * do, so just set ordering to NONE.
+	 * If there are barriers, then we use flush.
 	 */
-	if (err)
-		info->feature_barrier = QUEUE_ORDERED_DRAIN;
-	else if (barrier)
-		info->feature_barrier = QUEUE_ORDERED_TAG;
-	else
-		info->feature_barrier = QUEUE_ORDERED_NONE;
+	info->feature_flush = 0;
+
+	/*
+	 * The driver doesn't properly handled empty flushes, so
+	 * lets disable barrier support for now.
+	 */
+#if 0
+	if (!err && barrier)
+		info->feature_flush = REQ_FLUSH;
+#endif
 
 	err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
 	if (err) {
@@ -1201,7 +1188,7 @@
 	struct blkfront_info *info;
 	int err = 0;
 
-	lock_kernel();
+	mutex_lock(&blkfront_mutex);
 
 	info = disk->private_data;
 	if (!info) {
@@ -1219,7 +1206,7 @@
 	mutex_unlock(&info->mutex);
 
 out:
-	unlock_kernel();
+	mutex_unlock(&blkfront_mutex);
 	return err;
 }
 
@@ -1229,7 +1216,7 @@
 	struct block_device *bdev;
 	struct xenbus_device *xbdev;
 
-	lock_kernel();
+	mutex_lock(&blkfront_mutex);
 
 	bdev = bdget_disk(disk, 0);
 	bdput(bdev);
@@ -1263,7 +1250,7 @@
 	}
 
 out:
-	unlock_kernel();
+	mutex_unlock(&blkfront_mutex);
 	return 0;
 }
 
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 057413b..6e968cd 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -89,7 +89,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/ata.h>
 #include <linux/hdreg.h>
 #include <linux/platform_device.h>
@@ -214,6 +214,7 @@
 	u16 cf_id[ATA_ID_WORDS];
 };
 
+static DEFINE_MUTEX(xsysace_mutex);
 static int ace_major;
 
 /* ---------------------------------------------------------------------
@@ -903,13 +904,13 @@
 
 	dev_dbg(ace->dev, "ace_open() users=%i\n", ace->users + 1);
 
-	lock_kernel();
+	mutex_lock(&xsysace_mutex);
 	spin_lock_irqsave(&ace->lock, flags);
 	ace->users++;
 	spin_unlock_irqrestore(&ace->lock, flags);
 
 	check_disk_change(bdev);
-	unlock_kernel();
+	mutex_unlock(&xsysace_mutex);
 
 	return 0;
 }
@@ -922,7 +923,7 @@
 
 	dev_dbg(ace->dev, "ace_release() users=%i\n", ace->users - 1);
 
-	lock_kernel();
+	mutex_lock(&xsysace_mutex);
 	spin_lock_irqsave(&ace->lock, flags);
 	ace->users--;
 	if (ace->users == 0) {
@@ -930,7 +931,7 @@
 		ace_out(ace, ACE_CTRL, val & ~ACE_CTRL_LOCKREQ);
 	}
 	spin_unlock_irqrestore(&ace->lock, flags);
-	unlock_kernel();
+	mutex_unlock(&xsysace_mutex);
 	return 0;
 }
 
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index d75b2bb..dcd4cfc 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -33,7 +33,7 @@
 #include <linux/module.h>
 #include <linux/blkdev.h>
 #include <linux/bitops.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 
 #include <asm/setup.h>
@@ -57,6 +57,7 @@
 
 #define Z2RAM_CHUNK1024       ( Z2RAM_CHUNKSIZE >> 10 )
 
+static DEFINE_MUTEX(z2ram_mutex);
 static u_long *z2ram_map    = NULL;
 static u_long z2ram_size    = 0;
 static int z2_count         = 0;
@@ -154,7 +155,7 @@
 
     device = MINOR(bdev->bd_dev);
 
-    lock_kernel();
+    mutex_lock(&z2ram_mutex);
     if ( current_device != -1 && current_device != device )
     {
 	rc = -EBUSY;
@@ -296,25 +297,25 @@
 	set_capacity(z2ram_gendisk, z2ram_size >> 9);
     }
 
-    unlock_kernel();
+    mutex_unlock(&z2ram_mutex);
     return 0;
 
 err_out_kfree:
     kfree(z2ram_map);
 err_out:
-    unlock_kernel();
+    mutex_unlock(&z2ram_mutex);
     return rc;
 }
 
 static int
 z2_release(struct gendisk *disk, fmode_t mode)
 {
-    lock_kernel();
+    mutex_lock(&z2ram_mutex);
     if ( current_device == -1 ) {
-    	unlock_kernel();
+    	mutex_unlock(&z2ram_mutex);
     	return 0;
     }
-    unlock_kernel();
+    mutex_unlock(&z2ram_mutex);
     /*
      * FIXME: unmap memory
      */
diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c
index d52e90a5..4104b7f 100644
--- a/drivers/bluetooth/bluecard_cs.c
+++ b/drivers/bluetooth/bluecard_cs.c
@@ -39,7 +39,6 @@
 #include <linux/skbuff.h>
 #include <linux/io.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -865,8 +864,7 @@
 	info->p_dev = link;
 	link->priv = info;
 
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
+	link->config_flags |= CONF_ENABLE_IRQ;
 
 	return bluecard_config(link);
 }
@@ -886,7 +884,7 @@
 	bluecard_info_t *info = link->priv;
 	int i, n;
 
-	link->conf.ConfigIndex = 0x20;
+	link->config_index = 0x20;
 
 	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
 	link->resource[0]->end = 64;
@@ -906,7 +904,7 @@
 	if (i != 0)
 		goto failed;
 
-	i = pcmcia_request_configuration(link, &link->conf);
+	i = pcmcia_enable_device(link);
 	if (i != 0)
 		goto failed;
 
@@ -942,9 +940,7 @@
 
 static struct pcmcia_driver bluecard_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "bluecard_cs",
-	},
+	.name		= "bluecard_cs",
 	.probe		= bluecard_probe,
 	.remove		= bluecard_detach,
 	.id_table	= bluecard_ids,
diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c
index 7ab8f29..0c8a655 100644
--- a/drivers/bluetooth/bt3c_cs.c
+++ b/drivers/bluetooth/bt3c_cs.c
@@ -45,7 +45,6 @@
 #include <linux/device.h>
 #include <linux/firmware.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -657,11 +656,8 @@
 	info->p_dev = link;
 	link->priv = info;
 
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-	link->resource[0]->end = 8;
-
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_VPP |
+		CONF_AUTO_SET_IO;
 
 	return bt3c_config(link);
 }
@@ -675,43 +671,41 @@
 	kfree(info);
 }
 
-static int bt3c_check_config(struct pcmcia_device *p_dev,
-			     cistpl_cftable_entry_t *cf,
-			     cistpl_cftable_entry_t *dflt,
-			     unsigned int vcc,
-			     void *priv_data)
+static int bt3c_check_config(struct pcmcia_device *p_dev, void *priv_data)
 {
-	unsigned long try = (unsigned long) priv_data;
+	int *try = priv_data;
 
-	p_dev->io_lines = (try == 0) ? 16 : cf->io.flags & CISTPL_IO_LINES_MASK;
+	if (try == 0)
+		p_dev->io_lines = 16;
 
-	if (cf->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = cf->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-	if ((cf->io.nwin > 0) && (cf->io.win[0].len == 8) &&
-	    (cf->io.win[0].base != 0)) {
-		p_dev->resource[0]->start = cf->io.win[0].base;
-		if (!pcmcia_request_io(p_dev))
-			return 0;
-	}
-	return -ENODEV;
+	if ((p_dev->resource[0]->end != 8) || (p_dev->resource[0]->start == 0))
+		return -EINVAL;
+
+	p_dev->resource[0]->end = 8;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+
+	return pcmcia_request_io(p_dev);
 }
 
 static int bt3c_check_config_notpicky(struct pcmcia_device *p_dev,
-				      cistpl_cftable_entry_t *cf,
-				      cistpl_cftable_entry_t *dflt,
-				      unsigned int vcc,
 				      void *priv_data)
 {
 	static unsigned int base[5] = { 0x3f8, 0x2f8, 0x3e8, 0x2e8, 0x0 };
 	int j;
 
-	if ((cf->io.nwin > 0) && ((cf->io.flags & CISTPL_IO_LINES_MASK) <= 3)) {
-		for (j = 0; j < 5; j++) {
-			p_dev->resource[0]->start = base[j];
-			p_dev->io_lines = base[j] ? 16 : 3;
-			if (!pcmcia_request_io(p_dev))
-				return 0;
-		}
+	if (p_dev->io_lines > 3)
+		return -ENODEV;
+
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->resource[0]->end = 8;
+
+	for (j = 0; j < 5; j++) {
+		p_dev->resource[0]->start = base[j];
+		p_dev->io_lines = base[j] ? 16 : 3;
+		if (!pcmcia_request_io(p_dev))
+			return 0;
 	}
 	return -ENODEV;
 }
@@ -742,7 +736,7 @@
 	if (i != 0)
 		goto failed;
 
-	i = pcmcia_request_configuration(link, &link->conf);
+	i = pcmcia_enable_device(link);
 	if (i != 0)
 		goto failed;
 
@@ -775,9 +769,7 @@
 
 static struct pcmcia_driver bt3c_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "bt3c_cs",
-	},
+	.name		= "bt3c_cs",
 	.probe		= bt3c_probe,
 	.remove		= bt3c_detach,
 	.id_table	= bt3c_ids,
diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c
index 54739b0..fd6305b 100644
--- a/drivers/bluetooth/btmrvl_debugfs.c
+++ b/drivers/bluetooth/btmrvl_debugfs.c
@@ -92,6 +92,7 @@
 	.read	= btmrvl_hscfgcmd_read,
 	.write	= btmrvl_hscfgcmd_write,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_psmode_write(struct file *file, const char __user *ubuf,
@@ -130,6 +131,7 @@
 	.read	= btmrvl_psmode_read,
 	.write	= btmrvl_psmode_write,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_pscmd_write(struct file *file, const char __user *ubuf,
@@ -173,6 +175,7 @@
 	.read = btmrvl_pscmd_read,
 	.write = btmrvl_pscmd_write,
 	.open = btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_gpiogap_write(struct file *file, const char __user *ubuf,
@@ -211,6 +214,7 @@
 	.read	= btmrvl_gpiogap_read,
 	.write	= btmrvl_gpiogap_write,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_hscmd_write(struct file *file, const char __user *ubuf,
@@ -252,6 +256,7 @@
 	.read	= btmrvl_hscmd_read,
 	.write	= btmrvl_hscmd_write,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_hsmode_write(struct file *file, const char __user *ubuf,
@@ -289,6 +294,7 @@
 	.read	= btmrvl_hsmode_read,
 	.write	= btmrvl_hsmode_write,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_curpsmode_read(struct file *file, char __user *userbuf,
@@ -306,6 +312,7 @@
 static const struct file_operations btmrvl_curpsmode_fops = {
 	.read	= btmrvl_curpsmode_read,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_psstate_read(struct file *file, char __user * userbuf,
@@ -323,6 +330,7 @@
 static const struct file_operations btmrvl_psstate_fops = {
 	.read	= btmrvl_psstate_read,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_hsstate_read(struct file *file, char __user *userbuf,
@@ -340,6 +348,7 @@
 static const struct file_operations btmrvl_hsstate_fops = {
 	.read	= btmrvl_hsstate_read,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t btmrvl_txdnldready_read(struct file *file, char __user *userbuf,
@@ -358,6 +367,7 @@
 static const struct file_operations btmrvl_txdnldready_fops = {
 	.read	= btmrvl_txdnldready_read,
 	.open	= btmrvl_open_generic,
+	.llseek = default_llseek,
 };
 
 void btmrvl_debugfs_init(struct hci_dev *hdev)
diff --git a/drivers/bluetooth/btuart_cs.c b/drivers/bluetooth/btuart_cs.c
index 1c4f5e8..f8a0708 100644
--- a/drivers/bluetooth/btuart_cs.c
+++ b/drivers/bluetooth/btuart_cs.c
@@ -41,7 +41,6 @@
 #include <asm/system.h>
 #include <asm/io.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -586,11 +585,8 @@
 	info->p_dev = link;
 	link->priv = info;
 
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-	link->resource[0]->end = 8;
-
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_VPP |
+		CONF_AUTO_SET_IO;
 
 	return btuart_config(link);
 }
@@ -604,43 +600,41 @@
 	kfree(info);
 }
 
-static int btuart_check_config(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cf,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int btuart_check_config(struct pcmcia_device *p_dev, void *priv_data)
 {
 	int *try = priv_data;
 
-	p_dev->io_lines = (try == 0) ? 16 : cf->io.flags & CISTPL_IO_LINES_MASK;
+	if (try == 0)
+		p_dev->io_lines = 16;
 
-	if (cf->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = cf->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-	if ((cf->io.nwin > 0) && (cf->io.win[0].len == 8) &&
-	    (cf->io.win[0].base != 0)) {
-		p_dev->resource[0]->start = cf->io.win[0].base;
-		if (!pcmcia_request_io(p_dev))
-			return 0;
-	}
-	return -ENODEV;
+	if ((p_dev->resource[0]->end != 8) || (p_dev->resource[0]->start == 0))
+		return -EINVAL;
+
+	p_dev->resource[0]->end = 8;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+
+	return pcmcia_request_io(p_dev);
 }
 
 static int btuart_check_config_notpicky(struct pcmcia_device *p_dev,
-					cistpl_cftable_entry_t *cf,
-					cistpl_cftable_entry_t *dflt,
-					unsigned int vcc,
 					void *priv_data)
 {
 	static unsigned int base[5] = { 0x3f8, 0x2f8, 0x3e8, 0x2e8, 0x0 };
 	int j;
 
-	if ((cf->io.nwin > 0) && ((cf->io.flags & CISTPL_IO_LINES_MASK) <= 3)) {
-		for (j = 0; j < 5; j++) {
-			p_dev->resource[0]->start = base[j];
-			p_dev->io_lines = base[j] ? 16 : 3;
-			if (!pcmcia_request_io(p_dev))
-				return 0;
-		}
+	if (p_dev->io_lines > 3)
+		return -ENODEV;
+
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->resource[0]->end = 8;
+
+	for (j = 0; j < 5; j++) {
+		p_dev->resource[0]->start = base[j];
+		p_dev->io_lines = base[j] ? 16 : 3;
+		if (!pcmcia_request_io(p_dev))
+			return 0;
 	}
 	return -ENODEV;
 }
@@ -671,7 +665,7 @@
 	if (i != 0)
 		goto failed;
 
-	i = pcmcia_request_configuration(link, &link->conf);
+	i = pcmcia_enable_device(link);
 	if (i != 0)
 		goto failed;
 
@@ -703,9 +697,7 @@
 
 static struct pcmcia_driver btuart_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "btuart_cs",
-	},
+	.name		= "btuart_cs",
 	.probe		= btuart_probe,
 	.remove		= btuart_detach,
 	.id_table	= btuart_ids,
diff --git a/drivers/bluetooth/dtl1_cs.c b/drivers/bluetooth/dtl1_cs.c
index db7c8db..26ee0cf 100644
--- a/drivers/bluetooth/dtl1_cs.c
+++ b/drivers/bluetooth/dtl1_cs.c
@@ -41,7 +41,6 @@
 #include <asm/system.h>
 #include <asm/io.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -572,11 +571,7 @@
 	info->p_dev = link;
 	link->priv = info;
 
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-	link->resource[0]->end = 8;
-
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
 
 	return dtl1_config(link);
 }
@@ -591,18 +586,14 @@
 	kfree(info);
 }
 
-static int dtl1_confcheck(struct pcmcia_device *p_dev,
-			  cistpl_cftable_entry_t *cf,
-			  cistpl_cftable_entry_t *dflt,
-			  unsigned int vcc,
-			  void *priv_data)
+static int dtl1_confcheck(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if ((cf->io.nwin != 1) || (cf->io.win[0].len <= 8))
+	if ((p_dev->resource[1]->end) || (p_dev->resource[1]->end < 8))
 		return -ENODEV;
 
-	p_dev->resource[0]->start = cf->io.win[0].base;
-	p_dev->resource[0]->end = cf->io.win[0].len;	/*yo */
-	p_dev->io_lines = cf->io.flags & CISTPL_IO_LINES_MASK;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+
 	return pcmcia_request_io(p_dev);
 }
 
@@ -620,7 +611,7 @@
 	if (i != 0)
 		goto failed;
 
-	i = pcmcia_request_configuration(link, &link->conf);
+	i = pcmcia_enable_device(link);
 	if (i != 0)
 		goto failed;
 
@@ -656,9 +647,7 @@
 
 static struct pcmcia_driver dtl1_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "dtl1_cs",
-	},
+	.name		= "dtl1_cs",
 	.probe		= dtl1_probe,
 	.remove		= dtl1_detach,
 	.id_table	= dtl1_ids,
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 998833d..17361ba 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -256,9 +256,16 @@
 
 	BT_DBG("tty %p", tty);
 
+	/* FIXME: This btw is bogus, nothing requires the old ldisc to clear
+	   the pointer */
 	if (hu)
 		return -EEXIST;
 
+	/* Error if the tty has no write op instead of leaving an exploitable
+	   hole */
+	if (tty->ops->write == NULL)
+		return -EOPNOTSUPP;
+
 	if (!(hu = kzalloc(sizeof(struct hci_uart), GFP_KERNEL))) {
 		BT_ERR("Can't allocate control structure");
 		return -ENFILE;
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 3aa7b2a..67c180c 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -282,6 +282,7 @@
 	.poll		= vhci_poll,
 	.open		= vhci_open,
 	.release	= vhci_release,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice vhci_miscdev= {
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 261107d..3af6516 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -34,7 +34,7 @@
 #include <linux/blkdev.h>
 #include <linux/interrupt.h>
 #include <linux/device.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 #include <linux/platform_device.h>
@@ -81,6 +81,7 @@
 
 #define GDROM_DEFAULT_TIMEOUT	(HZ * 7)
 
+static DEFINE_MUTEX(gdrom_mutex);
 static const struct {
 	int sense_key;
 	const char * const text;
@@ -494,17 +495,17 @@
 static int gdrom_bdops_open(struct block_device *bdev, fmode_t mode)
 {
 	int ret;
-	lock_kernel();
+	mutex_lock(&gdrom_mutex);
 	ret = cdrom_open(gd.cd_info, bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&gdrom_mutex);
 	return ret;
 }
 
 static int gdrom_bdops_release(struct gendisk *disk, fmode_t mode)
 {
-	lock_kernel();
+	mutex_lock(&gdrom_mutex);
 	cdrom_release(gd.cd_info, mode);
-	unlock_kernel();
+	mutex_unlock(&gdrom_mutex);
 	return 0;
 }
 
@@ -518,9 +519,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&gdrom_mutex);
 	ret = cdrom_ioctl(gd.cd_info, bdev, mode, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&gdrom_mutex);
 
 	return ret;
 }
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index 56bf9f4..be73a9b 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -42,7 +42,7 @@
 #include <linux/module.h>
 #include <linux/completion.h>
 #include <linux/proc_fs.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/seq_file.h>
 #include <linux/scatterlist.h>
 
@@ -61,6 +61,7 @@
  */
 #define VIOCD_MAX_CD	HVMAXARCHITECTEDVIRTUALCDROMS
 
+static DEFINE_MUTEX(viocd_mutex);
 static const struct vio_error_entry viocd_err_table[] = {
 	{0x0201, EINVAL, "Invalid Range"},
 	{0x0202, EINVAL, "Invalid Token"},
@@ -156,9 +157,9 @@
 	struct disk_info *di = bdev->bd_disk->private_data;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&viocd_mutex);
 	ret = cdrom_open(&di->viocd_info, bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&viocd_mutex);
 
 	return ret;
 }
@@ -166,9 +167,9 @@
 static int viocd_blk_release(struct gendisk *disk, fmode_t mode)
 {
 	struct disk_info *di = disk->private_data;
-	lock_kernel();
+	mutex_lock(&viocd_mutex);
 	cdrom_release(&di->viocd_info, mode);
-	unlock_kernel();
+	mutex_unlock(&viocd_mutex);
 	return 0;
 }
 
@@ -178,9 +179,9 @@
 	struct disk_info *di = bdev->bd_disk->private_data;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&viocd_mutex);
 	ret = cdrom_ioctl(&di->viocd_info, bdev, mode, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&viocd_mutex);
 
 	return ret;
 }
diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig
index 4b66c69..5ddf67e 100644
--- a/drivers/char/agp/Kconfig
+++ b/drivers/char/agp/Kconfig
@@ -57,7 +57,7 @@
 
 config AGP_AMD64
 	tristate "AMD Opteron/Athlon64 on-CPU GART support"
-	depends on AGP && X86 && K8_NB
+	depends on AGP && X86 && AMD_NB
 	help
 	  This option gives you AGP support for the GLX component of
 	  X using the on-CPU northbridge of the AMD Athlon64/Opteron CPUs.
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index 70312da..42396df 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -15,7 +15,7 @@
 #include <linux/mmzone.h>
 #include <asm/page.h>		/* PAGE_SIZE */
 #include <asm/e820.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/gart.h>
 #include "agp.h"
 
@@ -124,7 +124,7 @@
 	u32 temp;
 	struct aper_size_info_32 *values;
 
-	dev = k8_northbridges[0];
+	dev = k8_northbridges.nb_misc[0];
 	if (dev==NULL)
 		return 0;
 
@@ -181,10 +181,14 @@
 	unsigned long gatt_bus = virt_to_phys(agp_bridge->gatt_table_real);
 	int i;
 
+	if (!k8_northbridges.gart_supported)
+		return 0;
+
 	/* Configure AGP regs in each x86-64 host bridge. */
-        for (i = 0; i < num_k8_northbridges; i++) {
+	for (i = 0; i < k8_northbridges.num; i++) {
 		agp_bridge->gart_bus_addr =
-				amd64_configure(k8_northbridges[i], gatt_bus);
+				amd64_configure(k8_northbridges.nb_misc[i],
+						gatt_bus);
 	}
 	k8_flush_garts();
 	return 0;
@@ -195,11 +199,15 @@
 {
 	u32 tmp;
 	int i;
-        for (i = 0; i < num_k8_northbridges; i++) {
-		struct pci_dev *dev = k8_northbridges[i];
+
+	if (!k8_northbridges.gart_supported)
+		return;
+
+	for (i = 0; i < k8_northbridges.num; i++) {
+		struct pci_dev *dev = k8_northbridges.nb_misc[i];
 		/* disable gart translation */
 		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &tmp);
-		tmp &= ~AMD64_GARTEN;
+		tmp &= ~GARTEN;
 		pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, tmp);
 	}
 }
@@ -313,22 +321,25 @@
 	if (order < 0 || !agp_aperture_valid(aper, (32*1024*1024)<<order))
 		return -1;
 
-	pci_write_config_dword(nb, AMD64_GARTAPERTURECTL, order << 1);
+	gart_set_size_and_enable(nb, order);
 	pci_write_config_dword(nb, AMD64_GARTAPERTUREBASE, aper >> 25);
 
 	return 0;
 }
 
-static __devinit int cache_nbs (struct pci_dev *pdev, u32 cap_ptr)
+static __devinit int cache_nbs(struct pci_dev *pdev, u32 cap_ptr)
 {
 	int i;
 
 	if (cache_k8_northbridges() < 0)
 		return -ENODEV;
 
+	if (!k8_northbridges.gart_supported)
+		return -ENODEV;
+
 	i = 0;
-	for (i = 0; i < num_k8_northbridges; i++) {
-		struct pci_dev *dev = k8_northbridges[i];
+	for (i = 0; i < k8_northbridges.num; i++) {
+		struct pci_dev *dev = k8_northbridges.nb_misc[i];
 		if (fix_northbridge(dev, pdev, cap_ptr) < 0) {
 			dev_err(&dev->dev, "no usable aperture found\n");
 #ifdef __x86_64__
@@ -405,7 +416,8 @@
 	}
 
 	/* shadow x86-64 registers into ULi registers */
-	pci_read_config_dword (k8_northbridges[0], AMD64_GARTAPERTUREBASE, &httfea);
+	pci_read_config_dword (k8_northbridges.nb_misc[0], AMD64_GARTAPERTUREBASE,
+			       &httfea);
 
 	/* if x86-64 aperture base is beyond 4G, exit here */
 	if ((httfea & 0x7fff) >> (32 - 25)) {
@@ -472,7 +484,8 @@
 	pci_write_config_dword(dev1, NVIDIA_X86_64_1_APSIZE, tmp);
 
 	/* shadow x86-64 registers into NVIDIA registers */
-	pci_read_config_dword (k8_northbridges[0], AMD64_GARTAPERTUREBASE, &apbase);
+	pci_read_config_dword (k8_northbridges.nb_misc[0], AMD64_GARTAPERTUREBASE,
+			       &apbase);
 
 	/* if x86-64 aperture base is beyond 4G, exit here */
 	if ( (apbase & 0x7fff) >> (32 - 25) ) {
diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c
index d2abf51..64255ce 100644
--- a/drivers/char/agp/generic.c
+++ b/drivers/char/agp/generic.c
@@ -984,7 +984,9 @@
 
 	bridge->driver->cache_flush();
 #ifdef CONFIG_X86
-	set_memory_uc((unsigned long)table, 1 << page_order);
+	if (set_memory_uc((unsigned long)table, 1 << page_order))
+		printk(KERN_WARNING "Could not set GATT table memory to UC!");
+
 	bridge->gatt_table = (void *)table;
 #else
 	bridge->gatt_table = ioremap_nocache(virt_to_phys(table),
diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c
index 033e150..3022801 100644
--- a/drivers/char/apm-emulation.c
+++ b/drivers/char/apm-emulation.c
@@ -13,7 +13,7 @@
 #include <linux/module.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/miscdevice.h>
@@ -126,6 +126,7 @@
 /*
  * Local variables
  */
+static DEFINE_MUTEX(apm_mutex);
 static atomic_t suspend_acks_pending = ATOMIC_INIT(0);
 static atomic_t userspace_notification_inhibit = ATOMIC_INIT(0);
 static int apm_disabled;
@@ -274,7 +275,7 @@
 	if (!as->suser || !as->writer)
 		return -EPERM;
 
-	lock_kernel();
+	mutex_lock(&apm_mutex);
 	switch (cmd) {
 	case APM_IOC_SUSPEND:
 		mutex_lock(&state_lock);
@@ -335,7 +336,7 @@
 		mutex_unlock(&state_lock);
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&apm_mutex);
 
 	return err;
 }
@@ -370,7 +371,7 @@
 {
 	struct apm_user *as;
 
-	lock_kernel();
+	mutex_lock(&apm_mutex);
 	as = kzalloc(sizeof(*as), GFP_KERNEL);
 	if (as) {
 		/*
@@ -390,7 +391,7 @@
 
 		filp->private_data = as;
 	}
-	unlock_kernel();
+	mutex_unlock(&apm_mutex);
 
 	return as ? 0 : -ENOMEM;
 }
@@ -402,6 +403,7 @@
 	.unlocked_ioctl	= apm_ioctl,
 	.open		= apm_open,
 	.release	= apm_release,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice apm_device = {
diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c
index f4ae0e0..e7ba774 100644
--- a/drivers/char/applicom.c
+++ b/drivers/char/applicom.c
@@ -26,7 +26,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/miscdevice.h>
 #include <linux/pci.h>
 #include <linux/wait.h>
@@ -60,6 +60,7 @@
 #define PCI_DEVICE_ID_APPLICOM_PCI2000PFB     0x0003
 #endif
 
+static DEFINE_MUTEX(ac_mutex);
 static char *applicom_pci_devnames[] = {
 	"PCI board",
 	"PCI2000IBS / PCI2000CAN",
@@ -707,7 +708,7 @@
 	if (IS_ERR(adgl))
 		return PTR_ERR(adgl);
 
-	lock_kernel();	
+	mutex_lock(&ac_mutex);	
 	IndexCard = adgl->num_card-1;
 	 
 	if(cmd != 6 && ((IndexCard >= MAX_BOARD) || !apbs[IndexCard].RamIO)) {
@@ -717,7 +718,7 @@
 			warncount--;
 		}
 		kfree(adgl);
-		unlock_kernel();
+		mutex_unlock(&ac_mutex);
 		return -EINVAL;
 	}
 
@@ -835,7 +836,7 @@
 	}
 	Dummy = readb(apbs[IndexCard].RamIO + VERS);
 	kfree(adgl);
-	unlock_kernel();
+	mutex_unlock(&ac_mutex);
 	return 0;
 }
 
diff --git a/drivers/char/bfin-otp.c b/drivers/char/bfin-otp.c
index 836d4f0..44660f1 100644
--- a/drivers/char/bfin-otp.c
+++ b/drivers/char/bfin-otp.c
@@ -222,6 +222,7 @@
 	.unlocked_ioctl = bfin_otp_ioctl,
 	.read           = bfin_otp_read,
 	.write          = bfin_otp_write,
+	.llseek		= default_llseek,
 };
 
 static struct miscdevice bfin_otp_misc_device = {
diff --git a/drivers/char/briq_panel.c b/drivers/char/briq_panel.c
index d5fa113..f6718f0 100644
--- a/drivers/char/briq_panel.c
+++ b/drivers/char/briq_panel.c
@@ -186,6 +186,7 @@
 	.write		= briq_panel_write,
 	.open		= briq_panel_open,
 	.release	= briq_panel_release,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice briq_panel_miscdev = {
diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c
index 9191713..a4a6c2f 100644
--- a/drivers/char/bsr.c
+++ b/drivers/char/bsr.c
@@ -155,6 +155,7 @@
 	.owner = THIS_MODULE,
 	.mmap  = bsr_mmap,
 	.open  = bsr_open,
+	.llseek = noop_llseek,
 };
 
 static void bsr_cleanup_devs(void)
diff --git a/drivers/char/cs5535_gpio.c b/drivers/char/cs5535_gpio.c
index 4d830dc..0cf1e5f 100644
--- a/drivers/char/cs5535_gpio.c
+++ b/drivers/char/cs5535_gpio.c
@@ -169,7 +169,8 @@
 	.owner	= THIS_MODULE,
 	.write	= cs5535_gpio_write,
 	.read	= cs5535_gpio_read,
-	.open	= cs5535_gpio_open
+	.open	= cs5535_gpio_open,
+	.llseek = no_llseek,
 };
 
 static int __init cs5535_gpio_init(void)
diff --git a/drivers/char/ds1302.c b/drivers/char/ds1302.c
index 170693c..ed8303f9 100644
--- a/drivers/char/ds1302.c
+++ b/drivers/char/ds1302.c
@@ -20,7 +20,7 @@
 #include <linux/miscdevice.h>
 #include <linux/delay.h>
 #include <linux/bcd.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
@@ -32,6 +32,7 @@
 
 #define RTC_MAJOR_NR 121 /* local major, change later */
 
+static DEFINE_MUTEX(rtc_mutex);
 static const char ds1302_name[] = "ds1302";
 
 /* Send 8 bits. */
@@ -164,9 +165,9 @@
 			struct rtc_time rtc_tm;
 
 			memset(&rtc_tm, 0, sizeof (struct rtc_time));
-			lock_kernel();
+			mutex_lock(&rtc_mutex);
 			get_rtc_time(&rtc_tm);
-			unlock_kernel();
+			mutex_unlock(&rtc_mutex);
 			if (copy_to_user((struct rtc_time*)arg, &rtc_tm, sizeof(struct rtc_time)))
 				return -EFAULT;
 			return 0;
@@ -218,7 +219,7 @@
 			mon = bin2bcd(mon);
 			yrs = bin2bcd(yrs);
 
-			lock_kernel();
+			mutex_lock(&rtc_mutex);
 			local_irq_save(flags);
 			CMOS_WRITE(yrs, RTC_YEAR);
 			CMOS_WRITE(mon, RTC_MONTH);
@@ -227,7 +228,7 @@
 			CMOS_WRITE(min, RTC_MINUTES);
 			CMOS_WRITE(sec, RTC_SECONDS);
 			local_irq_restore(flags);
-			unlock_kernel();
+			mutex_unlock(&rtc_mutex);
 
 			/* Notice that at this point, the RTC is updated but
 			 * the kernel is still running with the old time.
@@ -247,10 +248,10 @@
 			if(copy_from_user(&tcs_val, (int*)arg, sizeof(int)))
 				return -EFAULT;
 
-			lock_kernel();
+			mutex_lock(&rtc_mutex);
 			tcs_val = RTC_TCR_PATTERN | (tcs_val & 0x0F);
 			ds1302_writereg(RTC_TRICKLECHARGER, tcs_val);
-			unlock_kernel();
+			mutex_unlock(&rtc_mutex);
 			return 0;
 		}
 		default:
@@ -288,6 +289,7 @@
 static const struct file_operations rtc_fops = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= rtc_ioctl,
+	.llseek		= noop_llseek,
 };
 
 /* Probe for the chip by writing something to its RAM and try reading it back. */
diff --git a/drivers/char/ds1620.c b/drivers/char/ds1620.c
index dbee868..aab9605 100644
--- a/drivers/char/ds1620.c
+++ b/drivers/char/ds1620.c
@@ -8,7 +8,7 @@
 #include <linux/proc_fs.h>
 #include <linux/capability.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@@ -34,6 +34,7 @@
 #define CFG_CPU			2
 #define CFG_1SHOT		1
 
+static DEFINE_MUTEX(ds1620_mutex);
 static const char *fan_state[] = { "off", "on", "on (hardwired)" };
 
 /*
@@ -210,7 +211,6 @@
 
 static int ds1620_open(struct inode *inode, struct file *file)
 {
-	cycle_kernel_lock();
 	return nonseekable_open(inode, file);
 }
 
@@ -321,9 +321,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ds1620_mutex);
 	ret = ds1620_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ds1620_mutex);
 
 	return ret;
 }
@@ -357,6 +357,7 @@
 	.open		= ds1620_open,
 	.read		= ds1620_read,
 	.unlocked_ioctl	= ds1620_unlocked_ioctl,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice ds1620_miscdev = {
diff --git a/drivers/char/dsp56k.c b/drivers/char/dsp56k.c
index 8a1b28a..052797b 100644
--- a/drivers/char/dsp56k.c
+++ b/drivers/char/dsp56k.c
@@ -32,7 +32,7 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/device.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
 #include <linux/uaccess.h>	/* For put_user and get_user */
@@ -94,6 +94,7 @@
 	} \
 }
 
+static DEFINE_MUTEX(dsp56k_mutex);
 static struct dsp56k_device {
 	unsigned long in_use;
 	long maxio, timeout;
@@ -330,9 +331,9 @@
 			if (len > DSP56K_MAX_BINARY_LENGTH) {
 				return -EINVAL;
 			}
-			lock_kernel();
+			mutex_lock(&dsp56k_mutex);
 			r = dsp56k_upload(bin, len);
-			unlock_kernel();
+			mutex_unlock(&dsp56k_mutex);
 			if (r < 0) {
 				return r;
 			}
@@ -342,16 +343,16 @@
 		case DSP56K_SET_TX_WSIZE:
 			if (arg > 4 || arg < 1)
 				return -EINVAL;
-			lock_kernel();
+			mutex_lock(&dsp56k_mutex);
 			dsp56k.tx_wsize = (int) arg;
-			unlock_kernel();
+			mutex_unlock(&dsp56k_mutex);
 			break;
 		case DSP56K_SET_RX_WSIZE:
 			if (arg > 4 || arg < 1)
 				return -EINVAL;
-			lock_kernel();
+			mutex_lock(&dsp56k_mutex);
 			dsp56k.rx_wsize = (int) arg;
-			unlock_kernel();
+			mutex_unlock(&dsp56k_mutex);
 			break;
 		case DSP56K_HOST_FLAGS:
 		{
@@ -363,7 +364,7 @@
 			if(get_user(out, &hf->out) < 0)
 				return -EFAULT;
 
-			lock_kernel();
+			mutex_lock(&dsp56k_mutex);
 			if ((dir & 0x1) && (out & 0x1))
 				dsp56k_host_interface.icr |= DSP56K_ICR_HF0;
 			else if (dir & 0x1)
@@ -378,16 +379,16 @@
 			if (dsp56k_host_interface.icr & DSP56K_ICR_HF1) status |= 0x2;
 			if (dsp56k_host_interface.isr & DSP56K_ISR_HF2) status |= 0x4;
 			if (dsp56k_host_interface.isr & DSP56K_ISR_HF3) status |= 0x8;
-			unlock_kernel();
+			mutex_unlock(&dsp56k_mutex);
 			return put_user(status, &hf->status);
 		}
 		case DSP56K_HOST_CMD:
 			if (arg > 31 || arg < 0)
 				return -EINVAL;
-			lock_kernel();
+			mutex_lock(&dsp56k_mutex);
 			dsp56k_host_interface.cvr = (u_char)((arg & DSP56K_CVR_HV_MASK) |
 							     DSP56K_CVR_HC);
-			unlock_kernel();
+			mutex_unlock(&dsp56k_mutex);
 			break;
 		default:
 			return -EINVAL;
@@ -427,7 +428,7 @@
 	int dev = iminor(inode) & 0x0f;
 	int ret = 0;
 
-	lock_kernel();
+	mutex_lock(&dsp56k_mutex);
 	switch(dev)
 	{
 	case DSP56K_DEV_56001:
@@ -454,7 +455,7 @@
 		ret = -ENODEV;
 	}
 out:
-	unlock_kernel();
+	mutex_unlock(&dsp56k_mutex);
 	return ret;
 }
 
@@ -482,6 +483,7 @@
 	.unlocked_ioctl	= dsp56k_ioctl,
 	.open		= dsp56k_open,
 	.release	= dsp56k_release,
+	.llseek		= noop_llseek,
 };
 
 
diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c
index e3859d4..85156dd 100644
--- a/drivers/char/dtlk.c
+++ b/drivers/char/dtlk.c
@@ -57,7 +57,7 @@
 #include <linux/ioport.h>	/* for request_region */
 #include <linux/delay.h>	/* for loops_per_jiffy */
 #include <linux/sched.h>
-#include <linux/smp_lock.h>	/* cycle_kernel_lock() */
+#include <linux/mutex.h>
 #include <asm/io.h>		/* for inb_p, outb_p, inb, outb, etc. */
 #include <asm/uaccess.h>	/* for get_user, etc. */
 #include <linux/wait.h>		/* for wait_queue */
@@ -73,6 +73,7 @@
 #define TRACE_RET ((void) 0)
 #endif				/* TRACING */
 
+static DEFINE_MUTEX(dtlk_mutex);
 static void dtlk_timer_tick(unsigned long data);
 
 static int dtlk_major;
@@ -105,6 +106,7 @@
 	.unlocked_ioctl	= dtlk_ioctl,
 	.open		= dtlk_open,
 	.release	= dtlk_release,
+	.llseek		= no_llseek,
 };
 
 /* local prototypes */
@@ -275,9 +277,9 @@
 	switch (cmd) {
 
 	case DTLK_INTERROGATE:
-		lock_kernel();
+		mutex_lock(&dtlk_mutex);
 		sp = dtlk_interrogate();
-		unlock_kernel();
+		mutex_unlock(&dtlk_mutex);
 		if (copy_to_user(argp, sp, sizeof(struct dtlk_settings)))
 			return -EINVAL;
 		return 0;
@@ -296,7 +298,6 @@
 {
 	TRACE_TEXT("(dtlk_open");
 
-	cycle_kernel_lock();
 	nonseekable_open(inode, file);
 	switch (iminor(inode)) {
 	case DTLK_MINOR:
diff --git a/drivers/char/generic_nvram.c b/drivers/char/generic_nvram.c
index 82b5a88..0e941b5 100644
--- a/drivers/char/generic_nvram.c
+++ b/drivers/char/generic_nvram.c
@@ -19,7 +19,7 @@
 #include <linux/miscdevice.h>
 #include <linux/fcntl.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <asm/uaccess.h>
 #include <asm/nvram.h>
 #ifdef CONFIG_PPC_PMAC
@@ -28,6 +28,7 @@
 
 #define NVRAM_SIZE	8192
 
+static DEFINE_MUTEX(nvram_mutex);
 static ssize_t nvram_len;
 
 static loff_t nvram_llseek(struct file *file, loff_t offset, int origin)
@@ -120,9 +121,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&nvram_mutex);
 	ret = nvram_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&nvram_mutex);
 
 	return ret;
 }
diff --git a/drivers/char/genrtc.c b/drivers/char/genrtc.c
index b6c2cc1..f773a9d 100644
--- a/drivers/char/genrtc.c
+++ b/drivers/char/genrtc.c
@@ -52,7 +52,7 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/proc_fs.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/workqueue.h>
 
 #include <asm/uaccess.h>
@@ -66,6 +66,7 @@
  *	ioctls.
  */
 
+static DEFINE_MUTEX(gen_rtc_mutex);
 static DECLARE_WAIT_QUEUE_HEAD(gen_rtc_wait);
 
 /*
@@ -337,9 +338,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&gen_rtc_mutex);
 	ret = gen_rtc_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&gen_rtc_mutex);
 
 	return ret;
 }
@@ -352,16 +353,16 @@
 
 static int gen_rtc_open(struct inode *inode, struct file *file)
 {
-	lock_kernel();
+	mutex_lock(&gen_rtc_mutex);
 	if (gen_rtc_status & RTC_IS_OPEN) {
-		unlock_kernel();
+		mutex_unlock(&gen_rtc_mutex);
 		return -EBUSY;
 	}
 
 	gen_rtc_status |= RTC_IS_OPEN;
 	gen_rtc_irq_data = 0;
 	irq_active = 0;
-	unlock_kernel();
+	mutex_unlock(&gen_rtc_mutex);
 
 	return 0;
 }
@@ -497,6 +498,7 @@
 	.unlocked_ioctl	= gen_rtc_unlocked_ioctl,
 	.open		= gen_rtc_open,
 	.release	= gen_rtc_release,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice rtc_gen_dev =
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index a0a1829..a4eee32 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -30,6 +30,7 @@
 #include <linux/bcd.h>
 #include <linux/seq_file.h>
 #include <linux/bitops.h>
+#include <linux/compat.h>
 #include <linux/clocksource.h>
 #include <linux/slab.h>
 
@@ -67,6 +68,7 @@
 #define	read_counter(MC)	readl(MC)
 #endif
 
+static DEFINE_MUTEX(hpet_mutex); /* replaces BKL */
 static u32 hpet_nhpet, hpet_max_freq = HPET_USER_FREQ;
 
 /* This clocksource driver currently only works on ia64 */
@@ -250,7 +252,7 @@
 	if (file->f_mode & FMODE_WRITE)
 		return -EINVAL;
 
-	lock_kernel();
+	mutex_lock(&hpet_mutex);
 	spin_lock_irq(&hpet_lock);
 
 	for (devp = NULL, hpetp = hpets; hpetp && !devp; hpetp = hpetp->hp_next)
@@ -264,7 +266,7 @@
 
 	if (!devp) {
 		spin_unlock_irq(&hpet_lock);
-		unlock_kernel();
+		mutex_unlock(&hpet_mutex);
 		return -EBUSY;
 	}
 
@@ -272,7 +274,7 @@
 	devp->hd_irqdata = 0;
 	devp->hd_flags |= HPET_OPEN;
 	spin_unlock_irq(&hpet_lock);
-	unlock_kernel();
+	mutex_unlock(&hpet_mutex);
 
 	hpet_timer_set_irq(devp);
 
@@ -429,22 +431,6 @@
 	return 0;
 }
 
-static int hpet_ioctl_common(struct hpet_dev *, int, unsigned long, int);
-
-static long hpet_ioctl(struct file *file, unsigned int cmd,
-			unsigned long arg)
-{
-	struct hpet_dev *devp;
-	int ret;
-
-	devp = file->private_data;
-	lock_kernel();
-	ret = hpet_ioctl_common(devp, cmd, arg, 0);
-	unlock_kernel();
-
-	return ret;
-}
-
 static int hpet_ioctl_ieon(struct hpet_dev *devp)
 {
 	struct hpet_timer __iomem *timer;
@@ -553,7 +539,8 @@
 }
 
 static int
-hpet_ioctl_common(struct hpet_dev *devp, int cmd, unsigned long arg, int kernel)
+hpet_ioctl_common(struct hpet_dev *devp, int cmd, unsigned long arg,
+		  struct hpet_info *info)
 {
 	struct hpet_timer __iomem *timer;
 	struct hpet __iomem *hpet;
@@ -594,23 +581,15 @@
 		break;
 	case HPET_INFO:
 		{
-			struct hpet_info info;
-
 			if (devp->hd_ireqfreq)
-				info.hi_ireqfreq =
+				info->hi_ireqfreq =
 					hpet_time_div(hpetp, devp->hd_ireqfreq);
 			else
-				info.hi_ireqfreq = 0;
-			info.hi_flags =
+				info->hi_ireqfreq = 0;
+			info->hi_flags =
 			    readq(&timer->hpet_config) & Tn_PER_INT_CAP_MASK;
-			info.hi_hpet = hpetp->hp_which;
-			info.hi_timer = devp - hpetp->hp_dev;
-			if (kernel)
-				memcpy((void *)arg, &info, sizeof(info));
-			else
-				if (copy_to_user((void __user *)arg, &info,
-						 sizeof(info)))
-					err = -EFAULT;
+			info->hi_hpet = hpetp->hp_which;
+			info->hi_timer = devp - hpetp->hp_dev;
 			break;
 		}
 	case HPET_EPI:
@@ -636,7 +615,7 @@
 		devp->hd_flags &= ~HPET_PERIODIC;
 		break;
 	case HPET_IRQFREQ:
-		if (!kernel && (arg > hpet_max_freq) &&
+		if ((arg > hpet_max_freq) &&
 		    !capable(CAP_SYS_RESOURCE)) {
 			err = -EACCES;
 			break;
@@ -653,12 +632,63 @@
 	return err;
 }
 
+static long
+hpet_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct hpet_info info;
+	int err;
+
+	mutex_lock(&hpet_mutex);
+	err = hpet_ioctl_common(file->private_data, cmd, arg, &info);
+	mutex_unlock(&hpet_mutex);
+
+	if ((cmd == HPET_INFO) && !err &&
+	    (copy_to_user((void __user *)arg, &info, sizeof(info))))
+		err = -EFAULT;
+
+	return err;
+}
+
+#ifdef CONFIG_COMPAT
+struct compat_hpet_info {
+	compat_ulong_t hi_ireqfreq;	/* Hz */
+	compat_ulong_t hi_flags;	/* information */
+	unsigned short hi_hpet;
+	unsigned short hi_timer;
+};
+
+static long
+hpet_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct hpet_info info;
+	int err;
+
+	mutex_lock(&hpet_mutex);
+	err = hpet_ioctl_common(file->private_data, cmd, arg, &info);
+	mutex_unlock(&hpet_mutex);
+
+	if ((cmd == HPET_INFO) && !err) {
+		struct compat_hpet_info __user *u = compat_ptr(arg);
+		if (put_user(info.hi_ireqfreq, &u->hi_ireqfreq) ||
+		    put_user(info.hi_flags, &u->hi_flags) ||
+		    put_user(info.hi_hpet, &u->hi_hpet) ||
+		    put_user(info.hi_timer, &u->hi_timer))
+			err = -EFAULT;
+	}
+
+	return err;
+}
+#endif
+
 static const struct file_operations hpet_fops = {
 	.owner = THIS_MODULE,
 	.llseek = no_llseek,
 	.read = hpet_read,
 	.poll = hpet_poll,
 	.unlocked_ioctl = hpet_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = hpet_compat_ioctl,
+#endif
 	.open = hpet_open,
 	.release = hpet_release,
 	.fasync = hpet_fasync,
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 3d9c61e..788da05 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -170,6 +170,7 @@
 	.owner		= THIS_MODULE,
 	.open		= rng_dev_open,
 	.read		= rng_dev_read,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice rng_miscdev = {
diff --git a/drivers/char/i8k.c b/drivers/char/i8k.c
index 4cd8b22..3bc0eef 100644
--- a/drivers/char/i8k.c
+++ b/drivers/char/i8k.c
@@ -23,7 +23,7 @@
 #include <linux/seq_file.h>
 #include <linux/dmi.h>
 #include <linux/capability.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 
@@ -56,6 +56,7 @@
 
 #define I8K_TEMPERATURE_BUG	1
 
+static DEFINE_MUTEX(i8k_mutex);
 static char bios_version[4];
 
 MODULE_AUTHOR("Massimo Dal Zotto (dz@debian.org)");
@@ -399,9 +400,9 @@
 {
 	long ret;
 
-	lock_kernel();
+	mutex_lock(&i8k_mutex);
 	ret = i8k_ioctl_unlocked(fp, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&i8k_mutex);
 
 	return ret;
 }
diff --git a/drivers/char/ip2/ip2main.c b/drivers/char/ip2/ip2main.c
index d4b71e8..64a439c 100644
--- a/drivers/char/ip2/ip2main.c
+++ b/drivers/char/ip2/ip2main.c
@@ -98,7 +98,7 @@
 #include <linux/major.h>
 #include <linux/wait.h>
 #include <linux/device.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
 
@@ -138,6 +138,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
+static DEFINE_MUTEX(ip2_mutex);
 static const struct file_operations ip2mem_proc_fops;
 static const struct file_operations ip2_proc_fops;
 
@@ -236,6 +237,7 @@
 	.write		= ip2_ipl_write,
 	.unlocked_ioctl	= ip2_ipl_ioctl,
 	.open		= ip2_ipl_open,
+	.llseek		= noop_llseek,
 }; 
 
 static unsigned long irq_counter;
@@ -2897,7 +2899,7 @@
 	printk (KERN_DEBUG "IP2IPL: ioctl cmd %d, arg %ld\n", cmd, arg );
 #endif
 
-	lock_kernel();
+	mutex_lock(&ip2_mutex);
 
 	switch ( iplminor ) {
 	case 0:	    // IPL device
@@ -2961,7 +2963,7 @@
 		rc = -ENODEV;
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&ip2_mutex);
 	return rc;
 }
 
@@ -2982,7 +2984,6 @@
 #ifdef IP2DEBUG_IPL
 	printk (KERN_DEBUG "IP2IPL: open\n" );
 #endif
-	cycle_kernel_lock();
 	return 0;
 }
 
diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c
index d8ec92a..1fc8876 100644
--- a/drivers/char/ipmi/ipmi_devintf.c
+++ b/drivers/char/ipmi/ipmi_devintf.c
@@ -44,7 +44,6 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/compat.h>
-#include <linux/smp_lock.h>
 
 struct ipmi_file_private
 {
@@ -59,6 +58,7 @@
 	unsigned int         default_retry_time_ms;
 };
 
+static DEFINE_MUTEX(ipmi_mutex);
 static void file_receive_handler(struct ipmi_recv_msg *msg,
 				 void                 *handler_data)
 {
@@ -102,9 +102,9 @@
 	struct ipmi_file_private *priv = file->private_data;
 	int                      result;
 
-	lock_kernel(); /* could race against open() otherwise */
+	mutex_lock(&ipmi_mutex); /* could race against open() otherwise */
 	result = fasync_helper(fd, file, on, &priv->fasync_queue);
-	unlock_kernel();
+	mutex_unlock(&ipmi_mutex);
 
 	return (result);
 }
@@ -125,7 +125,7 @@
 	if (!priv)
 		return -ENOMEM;
 
-	lock_kernel();
+	mutex_lock(&ipmi_mutex);
 	priv->file = file;
 
 	rv = ipmi_create_user(if_num,
@@ -150,7 +150,7 @@
 	priv->default_retry_time_ms = 0;
 
 out:
-	unlock_kernel();
+	mutex_unlock(&ipmi_mutex);
 	return rv;
 }
 
@@ -639,9 +639,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ipmi_mutex);
 	ret = ipmi_ioctl(file, cmd, data);
-	unlock_kernel();
+	mutex_unlock(&ipmi_mutex);
 
 	return ret;
 }
@@ -850,6 +850,7 @@
 	.release	= ipmi_release,
 	.fasync		= ipmi_fasync,
 	.poll		= ipmi_poll,
+	.llseek		= noop_llseek,
 };
 
 #define DEVICE_NAME     "ipmidev"
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 654d566..f4d334f 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -35,7 +35,7 @@
 #include <linux/moduleparam.h>
 #include <linux/ipmi.h>
 #include <linux/ipmi_smi.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/watchdog.h>
 #include <linux/miscdevice.h>
 #include <linux/init.h>
@@ -149,6 +149,7 @@
 #define	WDIOC_GET_PRETIMEOUT     _IOW(WATCHDOG_IOCTL_BASE, 22, int)
 #endif
 
+static DEFINE_MUTEX(ipmi_watchdog_mutex);
 static int nowayout = WATCHDOG_NOWAYOUT;
 
 static ipmi_user_t watchdog_user;
@@ -748,9 +749,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ipmi_watchdog_mutex);
 	ret = ipmi_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ipmi_watchdog_mutex);
 
 	return ret;
 }
@@ -844,7 +845,6 @@
 		if (test_and_set_bit(0, &ipmi_wdog_open))
 			return -EBUSY;
 
-		cycle_kernel_lock();
 
 		/*
 		 * Don't start the timer now, let it start on the
@@ -909,6 +909,7 @@
 	.open    = ipmi_open,
 	.release = ipmi_close,
 	.fasync  = ipmi_fasync,
+	.llseek  = no_llseek,
 };
 
 static struct miscdevice ipmi_wdog_miscdev = {
diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index be28391..667abd23 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -704,6 +704,7 @@
 	.read		= stli_memread,
 	.write		= stli_memwrite,
 	.unlocked_ioctl	= stli_memioctl,
+	.llseek		= default_llseek,
 };
 
 /*****************************************************************************/
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index 938a3a2..97c3edb 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -126,7 +126,7 @@
 #include <linux/device.h>
 #include <linux/wait.h>
 #include <linux/jiffies.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/compat.h>
 
 #include <linux/parport.h>
@@ -140,6 +140,7 @@
 /* if you have more than 8 printers, remember to increase LP_NO */
 #define LP_NO 8
 
+static DEFINE_MUTEX(lp_mutex);
 static struct lp_struct lp_table[LP_NO];
 
 static unsigned int lp_count = 0;
@@ -493,7 +494,7 @@
 	unsigned int minor = iminor(inode);
 	int ret = 0;
 
-	lock_kernel();
+	mutex_lock(&lp_mutex);
 	if (minor >= LP_NO) {
 		ret = -ENXIO;
 		goto out;
@@ -554,7 +555,7 @@
 	lp_release_parport (&lp_table[minor]);
 	lp_table[minor].current_mode = IEEE1284_MODE_COMPAT;
 out:
-	unlock_kernel();
+	mutex_unlock(&lp_mutex);
 	return ret;
 }
 
@@ -680,7 +681,7 @@
 	int ret;
 
 	minor = iminor(file->f_path.dentry->d_inode);
-	lock_kernel();
+	mutex_lock(&lp_mutex);
 	switch (cmd) {
 	case LPSETTIMEOUT:
 		if (copy_from_user(&par_timeout, (void __user *)arg,
@@ -694,7 +695,7 @@
 		ret = lp_do_ioctl(minor, cmd, arg, (void __user *)arg);
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&lp_mutex);
 
 	return ret;
 }
@@ -709,7 +710,7 @@
 	int ret;
 
 	minor = iminor(file->f_path.dentry->d_inode);
-	lock_kernel();
+	mutex_lock(&lp_mutex);
 	switch (cmd) {
 	case LPSETTIMEOUT:
 		tc = compat_ptr(arg);
@@ -730,7 +731,7 @@
 		ret = lp_do_ioctl(minor, cmd, arg, compat_ptr(arg));
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&lp_mutex);
 
 	return ret;
 }
@@ -748,6 +749,7 @@
 #ifdef CONFIG_PARPORT_1284
 	.read		= lp_read,
 #endif
+	.llseek		= noop_llseek,
 };
 
 /* --- support for console on the line printer ----------------- */
diff --git a/drivers/char/mbcs.c b/drivers/char/mbcs.c
index 83bef4e..1aeaaba 100644
--- a/drivers/char/mbcs.c
+++ b/drivers/char/mbcs.c
@@ -25,7 +25,6 @@
 #include <linux/mm.h>
 #include <linux/uio.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
@@ -42,6 +41,7 @@
 #else
 #define DBG(fmt...)
 #endif
+static DEFINE_MUTEX(mbcs_mutex);
 static int mbcs_major;
 
 static LIST_HEAD(soft_list);
@@ -385,19 +385,19 @@
 	struct mbcs_soft *soft;
 	int minor;
 
-	lock_kernel();
+	mutex_lock(&mbcs_mutex);
 	minor = iminor(ip);
 
 	/* Nothing protects access to this list... */
 	list_for_each_entry(soft, &soft_list, list) {
 		if (soft->nasid == minor) {
 			fp->private_data = soft->cxdev;
-			unlock_kernel();
+			mutex_unlock(&mbcs_mutex);
 			return 0;
 		}
 	}
 
-	unlock_kernel();
+	mutex_unlock(&mbcs_mutex);
 	return -ENODEV;
 }
 
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 1f528fa..e985b1c 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -805,6 +805,7 @@
 static const struct file_operations oldmem_fops = {
 	.read	= read_oldmem,
 	.open	= open_oldmem,
+	.llseek = default_llseek,
 };
 #endif
 
@@ -831,6 +832,7 @@
 
 static const struct file_operations kmsg_fops = {
 	.write = kmsg_write,
+	.llseek = noop_llseek,
 };
 
 static const struct memdev {
@@ -882,6 +884,7 @@
 
 static const struct file_operations memory_fops = {
 	.open = memory_open,
+	.llseek = noop_llseek,
 };
 
 static char *mem_devnode(struct device *dev, mode_t *mode)
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index abdafd4..778273c 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -162,6 +162,7 @@
 static const struct file_operations misc_fops = {
 	.owner		= THIS_MODULE,
 	.open		= misc_open,
+	.llseek		= noop_llseek,
 };
 
 /**
diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
index ea7c99f..c070b53 100644
--- a/drivers/char/mmtimer.c
+++ b/drivers/char/mmtimer.c
@@ -32,7 +32,7 @@
 #include <linux/interrupt.h>
 #include <linux/time.h>
 #include <linux/math64.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 
 #include <asm/uaccess.h>
@@ -59,6 +59,7 @@
 
 #define rtc_time()              (*RTC_COUNTER_ADDR)
 
+static DEFINE_MUTEX(mmtimer_mutex);
 static long mmtimer_ioctl(struct file *file, unsigned int cmd,
 						unsigned long arg);
 static int mmtimer_mmap(struct file *file, struct vm_area_struct *vma);
@@ -72,6 +73,7 @@
 	.owner = THIS_MODULE,
 	.mmap =	mmtimer_mmap,
 	.unlocked_ioctl = mmtimer_ioctl,
+	.llseek = noop_llseek,
 };
 
 /*
@@ -371,7 +373,7 @@
 {
 	int ret = 0;
 
-	lock_kernel();
+	mutex_lock(&mmtimer_mutex);
 
 	switch (cmd) {
 	case MMTIMER_GETOFFSET:	/* offset of the counter */
@@ -414,7 +416,7 @@
 		ret = -ENOTTY;
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&mmtimer_mutex);
 	return ret;
 }
 
diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c
index ecb89d7..966a95b 100644
--- a/drivers/char/mspec.c
+++ b/drivers/char/mspec.c
@@ -316,7 +316,8 @@
 
 static const struct file_operations fetchop_fops = {
 	.owner = THIS_MODULE,
-	.mmap = fetchop_mmap
+	.mmap = fetchop_mmap,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice fetchop_miscdev = {
@@ -327,7 +328,8 @@
 
 static const struct file_operations cached_fops = {
 	.owner = THIS_MODULE,
-	.mmap = cached_mmap
+	.mmap = cached_mmap,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice cached_miscdev = {
@@ -338,7 +340,8 @@
 
 static const struct file_operations uncached_fops = {
 	.owner = THIS_MODULE,
-	.mmap = uncached_mmap
+	.mmap = uncached_mmap,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice uncached_miscdev = {
diff --git a/drivers/char/mwave/mwavedd.c b/drivers/char/mwave/mwavedd.c
index a4ec50c..1d82d58 100644
--- a/drivers/char/mwave/mwavedd.c
+++ b/drivers/char/mwave/mwavedd.c
@@ -56,7 +56,7 @@
 #include <linux/serial.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/serial_8250.h>
 #include "smapi.h"
@@ -73,6 +73,7 @@
 * checks are made against other devices (ie. superio) for conflicts.
 * We'll depend on users using the tpctl utility to do that for now
 */
+static DEFINE_MUTEX(mwave_mutex);
 int mwave_debug = 0;
 int mwave_3780i_irq = 0;
 int mwave_3780i_io = 0;
@@ -101,7 +102,6 @@
 	PRINTK_2(TRACE_MWAVE,
 		"mwavedd::mwave_open, exit return retval %x\n", retval);
 
-	cycle_kernel_lock();
 	return retval;
 }
 
@@ -136,9 +136,9 @@
 			PRINTK_1(TRACE_MWAVE,
 				"mwavedd::mwave_ioctl, IOCTL_MW_RESET"
 				" calling tp3780I_ResetDSP\n");
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			retval = tp3780I_ResetDSP(&pDrvData->rBDData);
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 			PRINTK_2(TRACE_MWAVE,
 				"mwavedd::mwave_ioctl, IOCTL_MW_RESET"
 				" retval %x from tp3780I_ResetDSP\n",
@@ -149,9 +149,9 @@
 			PRINTK_1(TRACE_MWAVE,
 				"mwavedd::mwave_ioctl, IOCTL_MW_RUN"
 				" calling tp3780I_StartDSP\n");
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			retval = tp3780I_StartDSP(&pDrvData->rBDData);
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 			PRINTK_2(TRACE_MWAVE,
 				"mwavedd::mwave_ioctl, IOCTL_MW_RUN"
 				" retval %x from tp3780I_StartDSP\n",
@@ -165,10 +165,10 @@
 				"mwavedd::mwave_ioctl,"
 				" IOCTL_MW_DSP_ABILITIES calling"
 				" tp3780I_QueryAbilities\n");
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			retval = tp3780I_QueryAbilities(&pDrvData->rBDData,
 					&rAbilities);
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 			PRINTK_2(TRACE_MWAVE,
 				"mwavedd::mwave_ioctl, IOCTL_MW_DSP_ABILITIES"
 				" retval %x from tp3780I_QueryAbilities\n",
@@ -199,13 +199,13 @@
 				"mwavedd::mwave_ioctl IOCTL_MW_READ_DATA,"
 				" size %lx, ioarg %lx pusBuffer %p\n",
 				rReadData.ulDataLength, ioarg, pusBuffer);
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			retval = tp3780I_ReadWriteDspDStore(&pDrvData->rBDData,
 					iocmd,
 					pusBuffer,
 					rReadData.ulDataLength,
 					rReadData.usDspAddress);
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 		}
 			break;
 	
@@ -223,12 +223,12 @@
 				" size %lx, ioarg %lx pusBuffer %p\n",
 				rReadData.ulDataLength / 2, ioarg,
 				pusBuffer);
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			retval = tp3780I_ReadWriteDspDStore(&pDrvData->rBDData,
 				iocmd, pusBuffer,
 				rReadData.ulDataLength / 2,
 				rReadData.usDspAddress);
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 		}
 			break;
 	
@@ -246,12 +246,12 @@
 				" size %lx, ioarg %lx pusBuffer %p\n",
 				rWriteData.ulDataLength, ioarg,
 				pusBuffer);
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			retval = tp3780I_ReadWriteDspDStore(&pDrvData->rBDData,
 					iocmd, pusBuffer,
 					rWriteData.ulDataLength,
 					rWriteData.usDspAddress);
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 		}
 			break;
 	
@@ -269,12 +269,12 @@
 				" size %lx, ioarg %lx pusBuffer %p\n",
 				rWriteData.ulDataLength, ioarg,
 				pusBuffer);
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			retval = tp3780I_ReadWriteDspIStore(&pDrvData->rBDData,
 					iocmd, pusBuffer,
 					rWriteData.ulDataLength,
 					rWriteData.usDspAddress);
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 		}
 			break;
 	
@@ -295,10 +295,10 @@
 				ipcnum,
 				pDrvData->IPCs[ipcnum].usIntCount);
 
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			pDrvData->IPCs[ipcnum].bIsHere = FALSE;
 			pDrvData->IPCs[ipcnum].bIsEnabled = TRUE;
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 	
 			PRINTK_2(TRACE_MWAVE,
 				"mwavedd::mwave_ioctl IOCTL_MW_REGISTER_IPC"
@@ -323,7 +323,7 @@
 				ipcnum,
 				pDrvData->IPCs[ipcnum].usIntCount);
 	
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			if (pDrvData->IPCs[ipcnum].bIsEnabled == TRUE) {
 				DECLARE_WAITQUEUE(wait, current);
 
@@ -364,7 +364,7 @@
 					" processing\n",
 					ipcnum);
 			}
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 		}
 			break;
 	
@@ -383,14 +383,14 @@
 						ipcnum);
 				return -EINVAL;
 			}
-			lock_kernel();
+			mutex_lock(&mwave_mutex);
 			if (pDrvData->IPCs[ipcnum].bIsEnabled == TRUE) {
 				pDrvData->IPCs[ipcnum].bIsEnabled = FALSE;
 				if (pDrvData->IPCs[ipcnum].bIsHere == TRUE) {
 					wake_up_interruptible(&pDrvData->IPCs[ipcnum].ipc_wait_queue);
 				}
 			}
-			unlock_kernel();
+			mutex_unlock(&mwave_mutex);
 		}
 			break;
 	
@@ -479,7 +479,8 @@
 	.write		= mwave_write,
 	.unlocked_ioctl	= mwave_ioctl,
 	.open		= mwave_open,
-	.release	= mwave_close
+	.release	= mwave_close,
+	.llseek		= default_llseek,
 };
 
 
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index 66d2917..166f1e7 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -109,10 +109,11 @@
 #include <linux/spinlock.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <asm/system.h>
 
+static DEFINE_MUTEX(nvram_mutex);
 static DEFINE_SPINLOCK(nvram_state_lock);
 static int nvram_open_cnt;	/* #times opened */
 static int nvram_open_mode;	/* special open modes */
@@ -308,7 +309,7 @@
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 
-		lock_kernel();
+		mutex_lock(&nvram_mutex);
 		spin_lock_irq(&rtc_lock);
 
 		for (i = 0; i < NVRAM_BYTES; ++i)
@@ -316,7 +317,7 @@
 		__nvram_set_checksum();
 
 		spin_unlock_irq(&rtc_lock);
-		unlock_kernel();
+		mutex_unlock(&nvram_mutex);
 		return 0;
 
 	case NVRAM_SETCKS:
@@ -325,11 +326,11 @@
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 
-		lock_kernel();
+		mutex_lock(&nvram_mutex);
 		spin_lock_irq(&rtc_lock);
 		__nvram_set_checksum();
 		spin_unlock_irq(&rtc_lock);
-		unlock_kernel();
+		mutex_unlock(&nvram_mutex);
 		return 0;
 
 	default:
diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c
index 2604246..8994ce3 100644
--- a/drivers/char/nwbutton.c
+++ b/drivers/char/nwbutton.c
@@ -182,6 +182,7 @@
 static const struct file_operations button_fops = {
 	.owner		= THIS_MODULE,
 	.read		= button_read,
+	.llseek		= noop_llseek,
 };
 
 /* 
diff --git a/drivers/char/nwflash.c b/drivers/char/nwflash.c
index 043a1c7..a12f524 100644
--- a/drivers/char/nwflash.c
+++ b/drivers/char/nwflash.c
@@ -25,7 +25,6 @@
 #include <linux/spinlock.h>
 #include <linux/rwsem.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/jiffies.h>
 
@@ -41,6 +40,7 @@
 
 #define	NWFLASH_VERSION "6.4"
 
+static DEFINE_MUTEX(flash_mutex);
 static void kick_open(void);
 static int get_flash_id(void);
 static int erase_block(int nBlock);
@@ -96,7 +96,7 @@
 
 static long flash_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 {
-	lock_kernel();
+	mutex_lock(&flash_mutex);
 	switch (cmd) {
 	case CMD_WRITE_DISABLE:
 		gbWriteBase64Enable = 0;
@@ -114,10 +114,10 @@
 	default:
 		gbWriteBase64Enable = 0;
 		gbWriteEnable = 0;
-		unlock_kernel();
+		mutex_unlock(&flash_mutex);
 		return -EINVAL;
 	}
-	unlock_kernel();
+	mutex_unlock(&flash_mutex);
 	return 0;
 }
 
@@ -282,7 +282,7 @@
 {
 	loff_t ret;
 
-	lock_kernel();
+	mutex_lock(&flash_mutex);
 	if (flashdebug)
 		printk(KERN_DEBUG "flash_llseek: offset=0x%X, orig=0x%X.\n",
 		       (unsigned int) offset, orig);
@@ -317,7 +317,7 @@
 	default:
 		ret = -EINVAL;
 	}
-	unlock_kernel();
+	mutex_unlock(&flash_mutex);
 	return ret;
 }
 
diff --git a/drivers/char/pc8736x_gpio.c b/drivers/char/pc8736x_gpio.c
index 8ecbcc1..b304ec0 100644
--- a/drivers/char/pc8736x_gpio.c
+++ b/drivers/char/pc8736x_gpio.c
@@ -234,6 +234,7 @@
 	.open	= pc8736x_gpio_open,
 	.write	= nsc_gpio_write,
 	.read	= nsc_gpio_read,
+	.llseek = no_llseek,
 };
 
 static void __init pc8736x_init_shadow(void)
diff --git a/drivers/char/pcmcia/cm4000_cs.c b/drivers/char/pcmcia/cm4000_cs.c
index ec73d9f..6835c23 100644
--- a/drivers/char/pcmcia/cm4000_cs.c
+++ b/drivers/char/pcmcia/cm4000_cs.c
@@ -30,11 +30,10 @@
 #include <linux/fs.h>
 #include <linux/delay.h>
 #include <linux/bitrev.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ciscode.h>
@@ -55,7 +54,7 @@
 			   __func__ , ## args);		\
 	} while (0)
 
-static char *version = "cm4000_cs.c v2.4.0gm6 - All bugs added by Harald Welte";
+static DEFINE_MUTEX(cmm_mutex);
 
 #define	T_1SEC		(HZ)
 #define	T_10MSEC	msecs_to_jiffies(10)
@@ -1418,7 +1417,7 @@
 	       iminor(inode), ioctl_names[_IOC_NR(cmd)]);
 #endif
 
-	lock_kernel();
+	mutex_lock(&cmm_mutex);
 	rc = -ENODEV;
 	link = dev_table[iminor(inode)];
 	if (!pcmcia_dev_present(link)) {
@@ -1626,7 +1625,7 @@
 		rc = -ENOTTY;
 	}
 out:
-	unlock_kernel();
+	mutex_unlock(&cmm_mutex);
 	return rc;
 }
 
@@ -1640,7 +1639,7 @@
 	if (minor >= CM4000_MAX_DEV)
 		return -ENODEV;
 
-	lock_kernel();
+	mutex_lock(&cmm_mutex);
 	link = dev_table[minor];
 	if (link == NULL || !pcmcia_dev_present(link)) {
 		ret = -ENODEV;
@@ -1685,7 +1684,7 @@
 	DEBUGP(2, dev, "<- cmm_open\n");
 	ret = nonseekable_open(inode, filp);
 out:
-	unlock_kernel();
+	mutex_unlock(&cmm_mutex);
 	return ret;
 }
 
@@ -1742,20 +1741,8 @@
 
 /*==== Interface to PCMCIA Layer =======================================*/
 
-static int cm4000_config_check(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cfg,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int cm4000_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (!cfg->io.nwin)
-		return -ENODEV;
-
-	p_dev->resource[0]->start = cfg->io.win[0].base;
-	p_dev->resource[0]->end = cfg->io.win[0].len;
-	p_dev->resource[0]->flags |= pcmcia_io_cfg_data_width(cfg->io.flags);
-	p_dev->io_lines = cfg->io.flags & CISTPL_IO_LINES_MASK;
-
 	return pcmcia_request_io(p_dev);
 }
 
@@ -1763,13 +1750,13 @@
 {
 	struct cm4000_dev *dev;
 
+	link->config_flags |= CONF_AUTO_SET_IO;
+
 	/* read the config-tuples */
 	if (pcmcia_loop_config(link, cm4000_config_check, NULL))
 		goto cs_release;
 
-	link->conf.IntType = 00000002;
-
-	if (pcmcia_request_configuration(link, &link->conf))
+	if (pcmcia_enable_device(link))
 		goto cs_release;
 
 	dev = link->priv;
@@ -1829,7 +1816,6 @@
 
 	dev->p_dev = link;
 	link->priv = dev;
-	link->conf.IntType = INT_MEMORY_AND_IO;
 	dev_table[i] = link;
 
 	init_waitqueue_head(&dev->devq);
@@ -1880,6 +1866,7 @@
 	.unlocked_ioctl	= cmm_ioctl,
 	.open	= cmm_open,
 	.release= cmm_close,
+	.llseek = no_llseek,
 };
 
 static struct pcmcia_device_id cm4000_ids[] = {
@@ -1891,9 +1878,7 @@
 
 static struct pcmcia_driver cm4000_driver = {
 	.owner	  = THIS_MODULE,
-	.drv	  = {
-		.name = "cm4000_cs",
-		},
+	.name	  = "cm4000_cs",
 	.probe    = cm4000_probe,
 	.remove   = cm4000_detach,
 	.suspend  = cm4000_suspend,
@@ -1905,8 +1890,6 @@
 {
 	int rc;
 
-	printk(KERN_INFO "%s\n", version);
-
 	cmm_class = class_create(THIS_MODULE, "cardman_4000");
 	if (IS_ERR(cmm_class))
 		return PTR_ERR(cmm_class);
@@ -1931,7 +1914,6 @@
 
 static void __exit cmm_exit(void)
 {
-	printk(KERN_INFO MODULE_NAME ": unloading\n");
 	pcmcia_unregister_driver(&cm4000_driver);
 	unregister_chrdev(major, DEVICE_NAME);
 	class_destroy(cmm_class);
diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c
index 815cde1..5d8d59e 100644
--- a/drivers/char/pcmcia/cm4040_cs.c
+++ b/drivers/char/pcmcia/cm4040_cs.c
@@ -24,12 +24,11 @@
 #include <linux/fs.h>
 #include <linux/delay.h>
 #include <linux/poll.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/wait.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ciscode.h>
@@ -49,8 +48,7 @@
 			   __func__ , ## args);		\
 	} while (0)
 
-static char *version =
-"OMNIKEY CardMan 4040 v1.1.0gm5 - All bugs added by Harald Welte";
+static DEFINE_MUTEX(cm4040_mutex);
 
 #define	CCID_DRIVER_BULK_DEFAULT_TIMEOUT  	(150*HZ)
 #define	CCID_DRIVER_ASYNC_POWERUP_TIMEOUT 	(35*HZ)
@@ -444,7 +442,7 @@
 	if (minor >= CM_MAX_DEV)
 		return -ENODEV;
 
-	lock_kernel();
+	mutex_lock(&cm4040_mutex);
 	link = dev_table[minor];
 	if (link == NULL || !pcmcia_dev_present(link)) {
 		ret = -ENODEV;
@@ -473,7 +471,7 @@
 	DEBUGP(2, dev, "<- cm4040_open (successfully)\n");
 	ret = nonseekable_open(inode, filp);
 out:
-	unlock_kernel();
+	mutex_unlock(&cm4040_mutex);
 	return ret;
 }
 
@@ -516,26 +514,9 @@
 	return;
 }
 
-static int cm4040_config_check(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cfg,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int cm4040_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	int rc;
-	if (!cfg->io.nwin)
-		return -ENODEV;
-
-	/* Get the IOaddr */
-	p_dev->resource[0]->start = cfg->io.win[0].base;
-	p_dev->resource[0]->end = cfg->io.win[0].len;
-	p_dev->resource[0]->flags |= pcmcia_io_cfg_data_width(cfg->io.flags);
-	p_dev->io_lines = cfg->io.flags & CISTPL_IO_LINES_MASK;
-	rc = pcmcia_request_io(p_dev);
-
-	dev_printk(KERN_INFO, &p_dev->dev,
-		   "pcmcia_request_io returned 0x%x\n", rc);
-	return rc;
+	return pcmcia_request_io(p_dev);
 }
 
 
@@ -544,15 +525,15 @@
 	struct reader_dev *dev;
 	int fail_rc;
 
+	link->config_flags |= CONF_AUTO_SET_IO;
+
 	if (pcmcia_loop_config(link, cm4040_config_check, NULL))
 		goto cs_release;
 
-	link->conf.IntType = 00000002;
-
-	fail_rc = pcmcia_request_configuration(link, &link->conf);
+	fail_rc = pcmcia_enable_device(link);
 	if (fail_rc != 0) {
 		dev_printk(KERN_INFO, &link->dev,
-			   "pcmcia_request_configuration failed 0x%x\n",
+			   "pcmcia_enable_device failed 0x%x\n",
 			   fail_rc);
 		goto cs_release;
 	}
@@ -599,7 +580,6 @@
 	link->priv = dev;
 	dev->p_dev = link;
 
-	link->conf.IntType = INT_MEMORY_AND_IO;
 	dev_table[i] = link;
 
 	init_waitqueue_head(&dev->devq);
@@ -650,6 +630,7 @@
 	.open		= cm4040_open,
 	.release	= cm4040_close,
 	.poll		= cm4040_poll,
+	.llseek		= no_llseek,
 };
 
 static struct pcmcia_device_id cm4040_ids[] = {
@@ -662,9 +643,7 @@
 
 static struct pcmcia_driver reader_driver = {
   	.owner		= THIS_MODULE,
-  	.drv		= {
-		.name	= "cm4040_cs",
-	},
+	.name		= "cm4040_cs",
 	.probe		= reader_probe,
 	.remove		= reader_detach,
 	.id_table	= cm4040_ids,
@@ -674,7 +653,6 @@
 {
 	int rc;
 
-	printk(KERN_INFO "%s\n", version);
 	cmx_class = class_create(THIS_MODULE, "cardman_4040");
 	if (IS_ERR(cmx_class))
 		return PTR_ERR(cmx_class);
@@ -699,7 +677,6 @@
 
 static void __exit cm4040_exit(void)
 {
-	printk(KERN_INFO MODULE_NAME ": unloading\n");
 	pcmcia_unregister_driver(&reader_driver);
 	unregister_chrdev(major, DEVICE_NAME);
 	class_destroy(cmx_class);
diff --git a/drivers/char/pcmcia/ipwireless/main.c b/drivers/char/pcmcia/ipwireless/main.c
index 67bdb05..94b8eb4 100644
--- a/drivers/char/pcmcia/ipwireless/main.c
+++ b/drivers/char/pcmcia/ipwireless/main.c
@@ -32,7 +32,6 @@
 #include <pcmcia/device_id.h>
 #include <pcmcia/ss.h>
 #include <pcmcia/ds.h>
-#include <pcmcia/cs.h>
 
 static struct pcmcia_device_id ipw_ids[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x02f2, 0x0100),
@@ -76,23 +75,18 @@
 	schedule_work(&ipw->work_reboot);
 }
 
-static int ipwireless_probe(struct pcmcia_device *p_dev,
-			    cistpl_cftable_entry_t *cfg,
-			    cistpl_cftable_entry_t *dflt,
-			    unsigned int vcc,
-			    void *priv_data)
+static int ipwireless_probe(struct pcmcia_device *p_dev, void *priv_data)
 {
 	struct ipw_dev *ipw = priv_data;
 	struct resource *io_resource;
 	int ret;
 
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
 	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-	p_dev->resource[0]->start = cfg->io.win[0].base;
-	p_dev->resource[0]->end = cfg->io.win[0].len;
 
 	/* 0x40 causes it to generate level mode interrupts. */
 	/* 0x04 enables IREQ pin. */
-	p_dev->conf.ConfigIndex = cfg->index | 0x44;
+	p_dev->config_index |= 0x44;
 	p_dev->io_lines = 16;
 	ret = pcmcia_request_io(p_dev);
 	if (ret)
@@ -102,65 +96,49 @@
 				resource_size(p_dev->resource[0]),
 				IPWIRELESS_PCCARD_NAME);
 
-	if (cfg->mem.nwin == 0)
-		return 0;
-
-	ipw->request_common_memory.Attributes =
+	p_dev->resource[2]->flags |=
 		WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM | WIN_ENABLE;
-	ipw->request_common_memory.Base = cfg->mem.win[0].host_addr;
-	ipw->request_common_memory.Size = cfg->mem.win[0].len;
-	if (ipw->request_common_memory.Size < 0x1000)
-		ipw->request_common_memory.Size = 0x1000;
-	ipw->request_common_memory.AccessSpeed = 0;
 
-	ret = pcmcia_request_window(p_dev, &ipw->request_common_memory,
-				&ipw->handle_common_memory);
-
+	ret = pcmcia_request_window(p_dev, p_dev->resource[2], 0);
 	if (ret != 0)
 		goto exit1;
 
-	ret = pcmcia_map_mem_page(p_dev, ipw->handle_common_memory,
-				cfg->mem.win[0].card_addr);
-
+	ret = pcmcia_map_mem_page(p_dev, p_dev->resource[2], p_dev->card_addr);
 	if (ret != 0)
 		goto exit2;
 
-	ipw->is_v2_card = cfg->mem.win[0].len == 0x100;
+	ipw->is_v2_card = resource_size(p_dev->resource[2]) == 0x100;
 
-	ipw->common_memory = ioremap(ipw->request_common_memory.Base,
-				ipw->request_common_memory.Size);
-	request_mem_region(ipw->request_common_memory.Base,
-			ipw->request_common_memory.Size,
+	ipw->attr_memory = ioremap(p_dev->resource[2]->start,
+				resource_size(p_dev->resource[2]));
+	request_mem_region(p_dev->resource[2]->start,
+			resource_size(p_dev->resource[2]),
 			IPWIRELESS_PCCARD_NAME);
 
-	ipw->request_attr_memory.Attributes =
-		WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_AM | WIN_ENABLE;
-	ipw->request_attr_memory.Base = 0;
-	ipw->request_attr_memory.Size = 0;	/* this used to be 0x1000 */
-	ipw->request_attr_memory.AccessSpeed = 0;
-
-	ret = pcmcia_request_window(p_dev, &ipw->request_attr_memory,
-				&ipw->handle_attr_memory);
-
+	p_dev->resource[3]->flags |= WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_AM |
+					WIN_ENABLE;
+	p_dev->resource[3]->end = 0; /* this used to be 0x1000 */
+	ret = pcmcia_request_window(p_dev, p_dev->resource[3], 0);
 	if (ret != 0)
 		goto exit2;
 
-	ret = pcmcia_map_mem_page(p_dev, ipw->handle_attr_memory, 0);
+	ret = pcmcia_map_mem_page(p_dev, p_dev->resource[3], 0);
 	if (ret != 0)
 		goto exit3;
 
-	ipw->attr_memory = ioremap(ipw->request_attr_memory.Base,
-				ipw->request_attr_memory.Size);
-	request_mem_region(ipw->request_attr_memory.Base,
-			ipw->request_attr_memory.Size, IPWIRELESS_PCCARD_NAME);
+	ipw->attr_memory = ioremap(p_dev->resource[3]->start,
+				resource_size(p_dev->resource[3]));
+	request_mem_region(p_dev->resource[3]->start,
+			resource_size(p_dev->resource[3]),
+			IPWIRELESS_PCCARD_NAME);
 
 	return 0;
 
 exit3:
 exit2:
 	if (ipw->common_memory) {
-		release_mem_region(ipw->request_common_memory.Base,
-				ipw->request_common_memory.Size);
+		release_mem_region(p_dev->resource[2]->start,
+				resource_size(p_dev->resource[2]));
 		iounmap(ipw->common_memory);
 	}
 exit1:
@@ -175,14 +153,13 @@
 	int ret = 0;
 
 	ipw->is_v2_card = 0;
+	link->config_flags |= CONF_AUTO_SET_IO | CONF_AUTO_SET_IOMEM |
+		CONF_ENABLE_IRQ;
 
 	ret = pcmcia_loop_config(link, ipwireless_probe, ipw);
 	if (ret != 0)
 		return ret;
 
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	INIT_WORK(&ipw->work_reboot, signalled_reboot_work);
 
 	ipwireless_init_hardware_v1(ipw->hardware, link->resource[0]->start,
@@ -201,13 +178,9 @@
 			(unsigned int) link->irq);
 	if (ipw->attr_memory && ipw->common_memory)
 		printk(KERN_INFO IPWIRELESS_PCCARD_NAME
-			": attr memory 0x%08lx-0x%08lx, common memory 0x%08lx-0x%08lx\n",
-			ipw->request_attr_memory.Base,
-			ipw->request_attr_memory.Base
-			+ ipw->request_attr_memory.Size - 1,
-			ipw->request_common_memory.Base,
-			ipw->request_common_memory.Base
-			+ ipw->request_common_memory.Size - 1);
+			": attr memory %pR, common memory %pR\n",
+			link->resource[3],
+			link->resource[2]);
 
 	ipw->network = ipwireless_network_create(ipw->hardware);
 	if (!ipw->network)
@@ -223,25 +196,23 @@
 	 * Do the RequestConfiguration last, because it enables interrupts.
 	 * Then we don't get any interrupts before we're ready for them.
 	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
-
+	ret = pcmcia_enable_device(link);
 	if (ret != 0)
 		goto exit;
 
 	return 0;
 
 exit:
-	if (ipw->attr_memory) {
-		release_mem_region(ipw->request_attr_memory.Base,
-				ipw->request_attr_memory.Size);
-		iounmap(ipw->attr_memory);
-
-	}
 	if (ipw->common_memory) {
-		release_mem_region(ipw->request_common_memory.Base,
-				ipw->request_common_memory.Size);
+		release_mem_region(link->resource[2]->start,
+				resource_size(link->resource[2]));
 		iounmap(ipw->common_memory);
 	}
+	if (ipw->attr_memory) {
+		release_mem_region(link->resource[3]->start,
+				resource_size(link->resource[3]));
+		iounmap(ipw->attr_memory);
+	}
 	pcmcia_disable_device(link);
 	return -1;
 }
@@ -249,13 +220,13 @@
 static void release_ipwireless(struct ipw_dev *ipw)
 {
 	if (ipw->common_memory) {
-		release_mem_region(ipw->request_common_memory.Base,
-				ipw->request_common_memory.Size);
+		release_mem_region(ipw->link->resource[2]->start,
+				resource_size(ipw->link->resource[2]));
 		iounmap(ipw->common_memory);
 	}
 	if (ipw->attr_memory) {
-		release_mem_region(ipw->request_attr_memory.Base,
-				ipw->request_attr_memory.Size);
+		release_mem_region(ipw->link->resource[3]->start,
+				resource_size(ipw->link->resource[3]));
 		iounmap(ipw->attr_memory);
 	}
 	pcmcia_disable_device(ipw->link);
@@ -324,7 +295,7 @@
 	.owner		= THIS_MODULE,
 	.probe          = ipwireless_attach,
 	.remove         = ipwireless_detach,
-	.drv = { .name  = IPWIRELESS_PCCARD_NAME },
+	.name		= IPWIRELESS_PCCARD_NAME,
 	.id_table       = ipw_ids
 };
 
@@ -336,9 +307,6 @@
 {
 	int ret;
 
-	printk(KERN_INFO IPWIRELESS_PCCARD_NAME " "
-	       IPWIRELESS_PCMCIA_VERSION " by " IPWIRELESS_PCMCIA_AUTHOR "\n");
-
 	ret = ipwireless_tty_init();
 	if (ret != 0)
 		return ret;
@@ -355,9 +323,6 @@
  */
 static void __exit exit_ipwireless(void)
 {
-	printk(KERN_INFO IPWIRELESS_PCCARD_NAME " "
-			IPWIRELESS_PCMCIA_VERSION " removed\n");
-
 	pcmcia_unregister_driver(&me);
 	ipwireless_tty_release();
 }
diff --git a/drivers/char/pcmcia/ipwireless/main.h b/drivers/char/pcmcia/ipwireless/main.h
index c207be8..f2cbb11 100644
--- a/drivers/char/pcmcia/ipwireless/main.h
+++ b/drivers/char/pcmcia/ipwireless/main.h
@@ -21,7 +21,6 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -45,13 +44,9 @@
 	struct pcmcia_device *link;
 	int is_v2_card;
 
-	window_handle_t handle_attr_memory;
 	void __iomem *attr_memory;
-	win_req_t request_attr_memory;
 
-	window_handle_t handle_common_memory;
 	void __iomem *common_memory;
-	win_req_t request_common_memory;
 
 	/* Reference to attribute memory, containing CIS data */
 	void *attribute_memory;
diff --git a/drivers/char/pcmcia/ipwireless/tty.h b/drivers/char/pcmcia/ipwireless/tty.h
index 3e163d4..747b2d6 100644
--- a/drivers/char/pcmcia/ipwireless/tty.h
+++ b/drivers/char/pcmcia/ipwireless/tty.h
@@ -21,7 +21,6 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index 9ecd6be..be18100 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -70,7 +70,6 @@
 #include <linux/workqueue.h>
 #include <linux/hdlc.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -550,9 +549,6 @@
 
     /* Initialize the struct pcmcia_device structure */
 
-    link->conf.Attributes = 0;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-
     ret = mgslpc_config(link);
     if (ret)
 	    return ret;
@@ -565,20 +561,8 @@
 /* Card has been inserted.
  */
 
-static int mgslpc_ioprobe(struct pcmcia_device *p_dev,
-			  cistpl_cftable_entry_t *cfg,
-			  cistpl_cftable_entry_t *dflt,
-			  unsigned int vcc,
-			  void *priv_data)
+static int mgslpc_ioprobe(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (!cfg->io.nwin)
-		return -ENODEV;
-
-	p_dev->resource[0]->start = cfg->io.win[0].base;
-	p_dev->resource[0]->end = cfg->io.win[0].len;
-	p_dev->resource[0]->flags |= pcmcia_io_cfg_data_width(cfg->io.flags);
-	p_dev->io_lines = cfg->io.flags & CISTPL_IO_LINES_MASK;
-
 	return pcmcia_request_io(p_dev);
 }
 
@@ -590,32 +574,24 @@
     if (debug_level >= DEBUG_LEVEL_INFO)
 	    printk("mgslpc_config(0x%p)\n", link);
 
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+
     ret = pcmcia_loop_config(link, mgslpc_ioprobe, NULL);
     if (ret != 0)
 	    goto failed;
 
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-    link->conf.ConfigIndex = 8;
-    link->conf.Present = PRESENT_OPTION;
+    link->config_index = 8;
+    link->config_regs = PRESENT_OPTION;
 
     ret = pcmcia_request_irq(link, mgslpc_isr);
     if (ret)
 	    goto failed;
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
     info->io_base = link->resource[0]->start;
     info->irq_level = link->irq;
-
-    dev_info(&link->dev, "index 0x%02x:",
-	    link->conf.ConfigIndex);
-    if (link->conf.Attributes & CONF_ENABLE_IRQ)
-	    printk(", irq %d", link->irq);
-    if (link->resource[0])
-	    printk(", io %pR", link->resource[0]);
-    printk("\n");
     return 0;
 
 failed:
@@ -2797,9 +2773,7 @@
 
 static struct pcmcia_driver mgslpc_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "synclink_cs",
-	},
+	.name		= "synclink_cs",
 	.probe		= mgslpc_probe,
 	.remove		= mgslpc_detach,
 	.id_table	= mgslpc_ids,
@@ -2835,8 +2809,6 @@
 {
 	int rc;
 
-	printk("Unloading %s: version %s\n", driver_name, driver_version);
-
 	while(mgslpc_device_list)
 		mgslpc_remove_device(mgslpc_device_list);
 
@@ -2859,8 +2831,6 @@
 	    BREAKPOINT();
     }
 
-    printk("%s %s\n", driver_name, driver_version);
-
     if ((rc = pcmcia_register_driver(&mgslpc_driver)) < 0)
 	    return rc;
 
@@ -4127,6 +4097,8 @@
 	if (cmd != SIOCWANDEV)
 		return hdlc_ioctl(dev, ifr, cmd);
 
+	memset(&new_line, 0, size);
+
 	switch(ifr->ifr_settings.type) {
 	case IF_GET_IFACE: /* return current sync_serial_settings */
 
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index 02abfdd..723152d 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -67,7 +67,7 @@
 #include <linux/slab.h>
 #include <linux/major.h>
 #include <linux/ppdev.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/uaccess.h>
 
 #define PP_VERSION "ppdev: user-space parallel port driver"
@@ -97,6 +97,7 @@
 /* ROUND_UP macro from fs/select.c */
 #define ROUND_UP(x,y) (((x)+(y)-1)/(y))
 
+static DEFINE_MUTEX(pp_do_mutex);
 static inline void pp_enable_irq (struct pp_struct *pp)
 {
 	struct parport *port = pp->pdev->port;
@@ -630,9 +631,9 @@
 static long pp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	long ret;
-	lock_kernel();
+	mutex_lock(&pp_do_mutex);
 	ret = pp_do_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&pp_do_mutex);
 	return ret;
 }
 
@@ -641,7 +642,6 @@
 	unsigned int minor = iminor(inode);
 	struct pp_struct *pp;
 
-	cycle_kernel_lock();
 	if (minor >= PARPORT_MAX)
 		return -ENXIO;
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index caef35a..5a1aa64 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1165,6 +1165,7 @@
 	.poll  = random_poll,
 	.unlocked_ioctl = random_ioctl,
 	.fasync = random_fasync,
+	.llseek = noop_llseek,
 };
 
 const struct file_operations urandom_fops = {
@@ -1172,6 +1173,7 @@
 	.write = random_write,
 	.unlocked_ioctl = random_ioctl,
 	.fasync = random_fasync,
+	.llseek = noop_llseek,
 };
 
 /***************************************************************
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index b38942f..bfe25ea 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -19,8 +19,8 @@
 #include <linux/cdev.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/gfp.h>
+#include <linux/compat.h>
 
 #include <asm/uaccess.h>
 
@@ -55,7 +55,6 @@
 		return 0;
 	}
 
-	lock_kernel();
 	mutex_lock(&raw_mutex);
 
 	/*
@@ -82,7 +81,6 @@
 			bdev->bd_inode->i_mapping;
 	filp->private_data = bdev;
 	mutex_unlock(&raw_mutex);
-	unlock_kernel();
 	return 0;
 
 out2:
@@ -91,7 +89,6 @@
 	blkdev_put(bdev, filp->f_mode);
 out:
 	mutex_unlock(&raw_mutex);
-	unlock_kernel();
 	return err;
 }
 
@@ -125,20 +122,84 @@
 raw_ioctl(struct file *filp, unsigned int command, unsigned long arg)
 {
 	struct block_device *bdev = filp->private_data;
-	int ret;
-
-	lock_kernel();
-	ret = blkdev_ioctl(bdev, 0, command, arg);
-	unlock_kernel();
-
-	return ret;
+	return blkdev_ioctl(bdev, 0, command, arg);
 }
 
-static void bind_device(struct raw_config_request *rq)
+static int bind_set(int number, u64 major, u64 minor)
 {
-	device_destroy(raw_class, MKDEV(RAW_MAJOR, rq->raw_minor));
-	device_create(raw_class, NULL, MKDEV(RAW_MAJOR, rq->raw_minor), NULL,
-		      "raw%d", rq->raw_minor);
+	dev_t dev = MKDEV(major, minor);
+	struct raw_device_data *rawdev;
+	int err = 0;
+
+	if (number <= 0 || number >= MAX_RAW_MINORS)
+		return -EINVAL;
+
+	if (MAJOR(dev) != major || MINOR(dev) != minor)
+		return -EINVAL;
+
+	rawdev = &raw_devices[number];
+
+	/*
+	 * This is like making block devices, so demand the
+	 * same capability
+	 */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/*
+	 * For now, we don't need to check that the underlying
+	 * block device is present or not: we can do that when
+	 * the raw device is opened.  Just check that the
+	 * major/minor numbers make sense.
+	 */
+
+	if (MAJOR(dev) == 0 && dev != 0)
+		return -EINVAL;
+
+	mutex_lock(&raw_mutex);
+	if (rawdev->inuse) {
+		mutex_unlock(&raw_mutex);
+		return -EBUSY;
+	}
+	if (rawdev->binding) {
+		bdput(rawdev->binding);
+		module_put(THIS_MODULE);
+	}
+	if (!dev) {
+		/* unbind */
+		rawdev->binding = NULL;
+		device_destroy(raw_class, MKDEV(RAW_MAJOR, number));
+	} else {
+		rawdev->binding = bdget(dev);
+		if (rawdev->binding == NULL) {
+			err = -ENOMEM;
+		} else {
+			dev_t raw = MKDEV(RAW_MAJOR, number);
+			__module_get(THIS_MODULE);
+			device_destroy(raw_class, raw);
+			device_create(raw_class, NULL, raw, NULL,
+				      "raw%d", number);
+		}
+	}
+	mutex_unlock(&raw_mutex);
+	return err;
+}
+
+static int bind_get(int number, dev_t *dev)
+{
+	struct raw_device_data *rawdev;
+	struct block_device *bdev;
+
+	if (number <= 0 || number >= MAX_RAW_MINORS)
+		return -EINVAL;
+
+	rawdev = &raw_devices[number];
+
+	mutex_lock(&raw_mutex);
+	bdev = rawdev->binding;
+	*dev = bdev ? bdev->bd_dev : 0;
+	mutex_unlock(&raw_mutex);
+	return 0;
 }
 
 /*
@@ -149,106 +210,79 @@
 			  unsigned long arg)
 {
 	struct raw_config_request rq;
-	struct raw_device_data *rawdev;
-	int err = 0;
+	dev_t dev;
+	int err;
 
-	lock_kernel();
 	switch (command) {
 	case RAW_SETBIND:
+		if (copy_from_user(&rq, (void __user *) arg, sizeof(rq)))
+			return -EFAULT;
+
+		return bind_set(rq.raw_minor, rq.block_major, rq.block_minor);
+
 	case RAW_GETBIND:
+		if (copy_from_user(&rq, (void __user *) arg, sizeof(rq)))
+			return -EFAULT;
 
-		/* First, find out which raw minor we want */
+		err = bind_get(rq.raw_minor, &dev);
+		if (err)
+			return err;
 
-		if (copy_from_user(&rq, (void __user *) arg, sizeof(rq))) {
-			err = -EFAULT;
-			goto out;
-		}
+		rq.block_major = MAJOR(dev);
+		rq.block_minor = MINOR(dev);
 
-		if (rq.raw_minor <= 0 || rq.raw_minor >= MAX_RAW_MINORS) {
-			err = -EINVAL;
-			goto out;
-		}
-		rawdev = &raw_devices[rq.raw_minor];
+		if (copy_to_user((void __user *)arg, &rq, sizeof(rq)))
+			return -EFAULT;
 
-		if (command == RAW_SETBIND) {
-			dev_t dev;
-
-			/*
-			 * This is like making block devices, so demand the
-			 * same capability
-			 */
-			if (!capable(CAP_SYS_ADMIN)) {
-				err = -EPERM;
-				goto out;
-			}
-
-			/*
-			 * For now, we don't need to check that the underlying
-			 * block device is present or not: we can do that when
-			 * the raw device is opened.  Just check that the
-			 * major/minor numbers make sense.
-			 */
-
-			dev = MKDEV(rq.block_major, rq.block_minor);
-			if ((rq.block_major == 0 && rq.block_minor != 0) ||
-					MAJOR(dev) != rq.block_major ||
-					MINOR(dev) != rq.block_minor) {
-				err = -EINVAL;
-				goto out;
-			}
-
-			mutex_lock(&raw_mutex);
-			if (rawdev->inuse) {
-				mutex_unlock(&raw_mutex);
-				err = -EBUSY;
-				goto out;
-			}
-			if (rawdev->binding) {
-				bdput(rawdev->binding);
-				module_put(THIS_MODULE);
-			}
-			if (rq.block_major == 0 && rq.block_minor == 0) {
-				/* unbind */
-				rawdev->binding = NULL;
-				device_destroy(raw_class,
-						MKDEV(RAW_MAJOR, rq.raw_minor));
-			} else {
-				rawdev->binding = bdget(dev);
-				if (rawdev->binding == NULL)
-					err = -ENOMEM;
-				else {
-					__module_get(THIS_MODULE);
-					bind_device(&rq);
-				}
-			}
-			mutex_unlock(&raw_mutex);
-		} else {
-			struct block_device *bdev;
-
-			mutex_lock(&raw_mutex);
-			bdev = rawdev->binding;
-			if (bdev) {
-				rq.block_major = MAJOR(bdev->bd_dev);
-				rq.block_minor = MINOR(bdev->bd_dev);
-			} else {
-				rq.block_major = rq.block_minor = 0;
-			}
-			mutex_unlock(&raw_mutex);
-			if (copy_to_user((void __user *)arg, &rq, sizeof(rq))) {
-				err = -EFAULT;
-				goto out;
-			}
-		}
-		break;
-	default:
-		err = -EINVAL;
-		break;
+		return 0;
 	}
-out:
-	unlock_kernel();
-	return err;
+
+	return -EINVAL;
 }
 
+#ifdef CONFIG_COMPAT
+struct raw32_config_request {
+	compat_int_t	raw_minor;
+	compat_u64	block_major;
+	compat_u64	block_minor;
+};
+
+static long raw_ctl_compat_ioctl(struct file *file, unsigned int cmd,
+				unsigned long arg)
+{
+	struct raw32_config_request __user *user_req = compat_ptr(arg);
+	struct raw32_config_request rq;
+	dev_t dev;
+	int err = 0;
+
+	switch (cmd) {
+	case RAW_SETBIND:
+		if (copy_from_user(&rq, user_req, sizeof(rq)))
+			return -EFAULT;
+
+		return bind_set(rq.raw_minor, rq.block_major, rq.block_minor);
+
+	case RAW_GETBIND:
+		if (copy_from_user(&rq, user_req, sizeof(rq)))
+			return -EFAULT;
+
+		err = bind_get(rq.raw_minor, &dev);
+		if (err)
+			return err;
+
+		rq.block_major = MAJOR(dev);
+		rq.block_minor = MINOR(dev);
+
+		if (copy_to_user(user_req, &rq, sizeof(rq)))
+			return -EFAULT;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+#endif
+
 static const struct file_operations raw_fops = {
 	.read		= do_sync_read,
 	.aio_read	= generic_file_aio_read,
@@ -258,13 +292,18 @@
 	.open		= raw_open,
 	.release	= raw_release,
 	.unlocked_ioctl = raw_ioctl,
+	.llseek		= default_llseek,
 	.owner		= THIS_MODULE,
 };
 
 static const struct file_operations raw_ctl_fops = {
 	.unlocked_ioctl = raw_ctl_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= raw_ctl_compat_ioctl,
+#endif
 	.open		= raw_open,
 	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
 };
 
 static struct cdev raw_cdev;
diff --git a/drivers/char/rio/rio_linux.c b/drivers/char/rio/rio_linux.c
index d58c2eb..5e33293 100644
--- a/drivers/char/rio/rio_linux.c
+++ b/drivers/char/rio/rio_linux.c
@@ -44,7 +44,7 @@
 #include <linux/delay.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/miscdevice.h>
 #include <linux/init.h>
 
@@ -122,6 +122,7 @@
 
 
 /* These constants are derived from SCO Source */
+static DEFINE_MUTEX(rio_fw_mutex);
 static struct Conf
  RIOConf = {
 	/* locator */ "RIO Config here",
@@ -241,6 +242,7 @@
 static const struct file_operations rio_fw_fops = {
 	.owner = THIS_MODULE,
 	.unlocked_ioctl = rio_fw_ioctl,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice rio_fw_device = {
@@ -566,9 +568,9 @@
 	func_enter();
 
 	/* The "dev" argument isn't used. */
-	lock_kernel();
+	mutex_lock(&rio_fw_mutex);
 	rc = riocontrol(p, 0, cmd, arg, capable(CAP_SYS_ADMIN));
-	unlock_kernel();
+	mutex_unlock(&rio_fw_mutex);
 
 	func_exit();
 	return rc;
diff --git a/drivers/char/scx200_gpio.c b/drivers/char/scx200_gpio.c
index 99e5272..0bc135b 100644
--- a/drivers/char/scx200_gpio.c
+++ b/drivers/char/scx200_gpio.c
@@ -67,6 +67,7 @@
 	.read    = nsc_gpio_read,
 	.open    = scx200_gpio_open,
 	.release = scx200_gpio_release,
+	.llseek  = no_llseek,
 };
 
 static struct cdev scx200_gpio_cdev;  /* use 1 cdev for all pins */
diff --git a/drivers/char/snsc.c b/drivers/char/snsc.c
index 32b74de..5816b39 100644
--- a/drivers/char/snsc.c
+++ b/drivers/char/snsc.c
@@ -21,7 +21,7 @@
 #include <linux/poll.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <asm/sn/io.h>
 #include <asm/sn/sn_sal.h>
 #include <asm/sn/module.h>
@@ -34,6 +34,7 @@
 #define SCDRV_BUFSZ	2048
 #define SCDRV_TIMEOUT	1000
 
+static DEFINE_MUTEX(scdrv_mutex);
 static irqreturn_t
 scdrv_interrupt(int irq, void *subch_data)
 {
@@ -105,7 +106,7 @@
 	file->private_data = sd;
 
 	/* hook this subchannel up to the system controller interrupt */
-	lock_kernel();
+	mutex_lock(&scdrv_mutex);
 	rv = request_irq(SGI_UART_VECTOR, scdrv_interrupt,
 			 IRQF_SHARED | IRQF_DISABLED,
 			 SYSCTL_BASENAME, sd);
@@ -113,10 +114,10 @@
 		ia64_sn_irtr_close(sd->sd_nasid, sd->sd_subch);
 		kfree(sd);
 		printk("%s: irq request failed (%d)\n", __func__, rv);
-		unlock_kernel();
+		mutex_unlock(&scdrv_mutex);
 		return -EBUSY;
 	}
-	unlock_kernel();
+	mutex_unlock(&scdrv_mutex);
 	return 0;
 }
 
@@ -357,6 +358,7 @@
 	.poll =		scdrv_poll,
 	.open =		scdrv_open,
 	.release =	scdrv_release,
+	.llseek =	noop_llseek,
 };
 
 static struct class *snsc_class;
diff --git a/drivers/char/stallion.c b/drivers/char/stallion.c
index f2167f8..8ef1649 100644
--- a/drivers/char/stallion.c
+++ b/drivers/char/stallion.c
@@ -608,6 +608,7 @@
 static const struct file_operations	stl_fsiomem = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= stl_memioctl,
+	.llseek		= noop_llseek,
 };
 
 static struct class *stallion_class;
diff --git a/drivers/char/sx.c b/drivers/char/sx.c
index 5b24db4..e53f168 100644
--- a/drivers/char/sx.c
+++ b/drivers/char/sx.c
@@ -397,6 +397,7 @@
 static const struct file_operations sx_fw_fops = {
 	.owner = THIS_MODULE,
 	.unlocked_ioctl = sx_fw_ioctl,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice sx_fw_device = {
diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c
index ef31bb8..f3019f5 100644
--- a/drivers/char/sysrq.c
+++ b/drivers/char/sysrq.c
@@ -772,6 +772,7 @@
 
 static const struct file_operations proc_sysrq_trigger_operations = {
 	.write		= write_sysrq_trigger,
+	.llseek		= noop_llseek,
 };
 
 static void sysrq_init_procfs(void)
diff --git a/drivers/char/tb0219.c b/drivers/char/tb0219.c
index cad4eb6..ad26418 100644
--- a/drivers/char/tb0219.c
+++ b/drivers/char/tb0219.c
@@ -261,6 +261,7 @@
 	.write		= tanbac_tb0219_write,
 	.open		= tanbac_tb0219_open,
 	.release	= tanbac_tb0219_release,
+	.llseek		= no_llseek,
 };
 
 static void tb0219_restart(char *command)
diff --git a/drivers/char/tlclk.c b/drivers/char/tlclk.c
index 80ea6bc..0c964cd 100644
--- a/drivers/char/tlclk.c
+++ b/drivers/char/tlclk.c
@@ -37,7 +37,7 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/timer.h>
 #include <linux/sysfs.h>
 #include <linux/device.h>
@@ -206,7 +206,7 @@
 {
 	int result;
 
-	lock_kernel();
+	mutex_lock(&tlclk_mutex);
 	if (test_and_set_bit(0, &useflags)) {
 		result = -EBUSY;
 		/* this legacy device is always one per system and it doesn't
@@ -229,7 +229,7 @@
 		inb(TLCLK_REG6);	/* Clear interrupt events */
 
 out:
-	unlock_kernel();
+	mutex_unlock(&tlclk_mutex);
 	return result;
 }
 
@@ -267,6 +267,7 @@
 	.read = tlclk_read,
 	.open = tlclk_open,
 	.release = tlclk_release,
+	.llseek = noop_llseek,
 
 };
 
diff --git a/drivers/char/toshiba.c b/drivers/char/toshiba.c
index f8bc79f..014c9d9 100644
--- a/drivers/char/toshiba.c
+++ b/drivers/char/toshiba.c
@@ -68,7 +68,7 @@
 #include <linux/stat.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/toshiba.h>
 
 #define TOSH_MINOR_DEV 181
@@ -78,6 +78,7 @@
 MODULE_DESCRIPTION("Toshiba laptop SMM driver");
 MODULE_SUPPORTED_DEVICE("toshiba");
 
+static DEFINE_MUTEX(tosh_mutex);
 static int tosh_fn;
 module_param_named(fn, tosh_fn, int, 0);
 MODULE_PARM_DESC(fn, "User specified Fn key detection port");
@@ -95,6 +96,7 @@
 static const struct file_operations tosh_fops = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= tosh_ioctl,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice tosh_device = {
@@ -274,16 +276,16 @@
 				return -EINVAL;
 
 			/* do we need to emulate the fan ? */
-			lock_kernel();
+			mutex_lock(&tosh_mutex);
 			if (tosh_fan==1) {
 				if (((ax==0xf300) || (ax==0xf400)) && (bx==0x0004)) {
 					err = tosh_emulate_fan(&regs);
-					unlock_kernel();
+					mutex_unlock(&tosh_mutex);
 					break;
 				}
 			}
 			err = tosh_smm(&regs);
-			unlock_kernel();
+			mutex_unlock(&tosh_mutex);
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c
index 05ad4a1..7c41335 100644
--- a/drivers/char/tpm/tpm.c
+++ b/drivers/char/tpm/tpm.c
@@ -47,6 +47,16 @@
 #define TPM_MAX_PROTECTED_ORDINAL 12
 #define TPM_PROTECTED_ORDINAL_MASK 0xFF
 
+/*
+ * Bug workaround - some TPM's don't flush the most
+ * recently changed pcr on suspend, so force the flush
+ * with an extend to the selected _unused_ non-volatile pcr.
+ */
+static int tpm_suspend_pcr;
+module_param_named(suspend_pcr, tpm_suspend_pcr, uint, 0644);
+MODULE_PARM_DESC(suspend_pcr,
+		 "PCR to use for dummy writes to faciltate flush on suspend.");
+
 static LIST_HEAD(tpm_chip_list);
 static DEFINE_SPINLOCK(driver_lock);
 static DECLARE_BITMAP(dev_mask, TPM_NUM_DEVICES);
@@ -1077,18 +1087,6 @@
 	.ordinal = TPM_ORD_SAVESTATE
 };
 
-/* Bug workaround - some TPM's don't flush the most
- * recently changed pcr on suspend, so force the flush
- * with an extend to the selected _unused_ non-volatile pcr.
- */
-static int tpm_suspend_pcr;
-static int __init tpm_suspend_setup(char *str)
-{
-	get_option(&str, &tpm_suspend_pcr);
-	return 1;
-}
-__setup("tpm_suspend_pcr=", tpm_suspend_setup);
-
 /*
  * We are about to suspend. Save the TPM state
  * so that it can be restored.
diff --git a/drivers/char/uv_mmtimer.c b/drivers/char/uv_mmtimer.c
index c7072ba..493b47a 100644
--- a/drivers/char/uv_mmtimer.c
+++ b/drivers/char/uv_mmtimer.c
@@ -52,6 +52,7 @@
 	.owner = THIS_MODULE,
 	.mmap =	uv_mmtimer_mmap,
 	.unlocked_ioctl = uv_mmtimer_ioctl,
+	.llseek = noop_llseek,
 };
 
 /**
diff --git a/drivers/char/viotape.c b/drivers/char/viotape.c
index 42f7fa4..ad6e64a 100644
--- a/drivers/char/viotape.c
+++ b/drivers/char/viotape.c
@@ -46,7 +46,7 @@
 #include <linux/completion.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 
 #include <asm/uaccess.h>
@@ -64,6 +64,7 @@
 #define VIOTAPE_KERN_WARN	KERN_WARNING "viotape: "
 #define VIOTAPE_KERN_INFO	KERN_INFO "viotape: "
 
+static DEFINE_MUTEX(proc_viotape_mutex);
 static int viotape_numdev;
 
 /*
@@ -684,9 +685,9 @@
 {
 	long rc;
 
-	lock_kernel();
+	mutex_lock(&proc_viotape_mutex);
 	rc = viotap_ioctl(file->f_path.dentry->d_inode, file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&proc_viotape_mutex);
 	return rc;
 }
 
@@ -700,7 +701,7 @@
 	if (op == NULL)
 		return -ENOMEM;
 
-	lock_kernel();
+	mutex_lock(&proc_viotape_mutex);
 	get_dev_info(file->f_path.dentry->d_inode, &devi);
 
 	/* Note: We currently only support one mode! */
@@ -731,7 +732,7 @@
 
 free_op:
 	free_op_struct(op);
-	unlock_kernel();
+	mutex_unlock(&proc_viotape_mutex);
 	return ret;
 }
 
@@ -804,6 +805,7 @@
 	.unlocked_ioctl =	viotap_unlocked_ioctl,
 	.open =			viotap_open,
 	.release =		viotap_release,
+	.llseek = 		noop_llseek,
 };
 
 /* Handle interrupt events for tape */
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 0f69c5e..6c1b676 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -48,6 +48,9 @@
 	/* Used for exporting per-port information to debugfs */
 	struct dentry *debugfs_dir;
 
+	/* List of all the devices we're handling */
+	struct list_head portdevs;
+
 	/* Number of devices this driver is handling */
 	unsigned int index;
 
@@ -108,6 +111,9 @@
  * ports for that device (vdev->priv).
  */
 struct ports_device {
+	/* Next portdev in the list, head is in the pdrvdata struct */
+	struct list_head list;
+
 	/*
 	 * Workqueue handlers where we process deferred work after
 	 * notification
@@ -178,15 +184,21 @@
 	struct console cons;
 
 	/* Each port associates with a separate char device */
-	struct cdev cdev;
+	struct cdev *cdev;
 	struct device *dev;
 
+	/* Reference-counting to handle port hot-unplugs and file operations */
+	struct kref kref;
+
 	/* A waitqueue for poll() or blocking read operations */
 	wait_queue_head_t waitqueue;
 
 	/* The 'name' of the port that we expose via sysfs properties */
 	char *name;
 
+	/* We can notify apps of host connect / disconnect events via SIGIO */
+	struct fasync_struct *async_queue;
+
 	/* The 'id' to identify the port with the Host */
 	u32 id;
 
@@ -221,6 +233,41 @@
 	return port;
 }
 
+static struct port *find_port_by_devt_in_portdev(struct ports_device *portdev,
+						 dev_t dev)
+{
+	struct port *port;
+	unsigned long flags;
+
+	spin_lock_irqsave(&portdev->ports_lock, flags);
+	list_for_each_entry(port, &portdev->ports, list)
+		if (port->cdev->dev == dev)
+			goto out;
+	port = NULL;
+out:
+	spin_unlock_irqrestore(&portdev->ports_lock, flags);
+
+	return port;
+}
+
+static struct port *find_port_by_devt(dev_t dev)
+{
+	struct ports_device *portdev;
+	struct port *port;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdrvdata_lock, flags);
+	list_for_each_entry(portdev, &pdrvdata.portdevs, list) {
+		port = find_port_by_devt_in_portdev(portdev, dev);
+		if (port)
+			goto out;
+	}
+	port = NULL;
+out:
+	spin_unlock_irqrestore(&pdrvdata_lock, flags);
+	return port;
+}
+
 static struct port *find_port_by_id(struct ports_device *portdev, u32 id)
 {
 	struct port *port;
@@ -410,7 +457,10 @@
 static ssize_t send_control_msg(struct port *port, unsigned int event,
 				unsigned int value)
 {
-	return __send_control_msg(port->portdev, port->id, event, value);
+	/* Did the port get unplugged before userspace closed it? */
+	if (port->portdev)
+		return __send_control_msg(port->portdev, port->id, event, value);
+	return 0;
 }
 
 /* Callers must take the port->outvq_lock */
@@ -525,6 +575,10 @@
 /* The condition that must be true for polling to end */
 static bool will_read_block(struct port *port)
 {
+	if (!port->guest_connected) {
+		/* Port got hot-unplugged. Let's exit. */
+		return false;
+	}
 	return !port_has_data(port) && port->host_connected;
 }
 
@@ -575,6 +629,9 @@
 		if (ret < 0)
 			return ret;
 	}
+	/* Port got hot-unplugged. */
+	if (!port->guest_connected)
+		return -ENODEV;
 	/*
 	 * We could've received a disconnection message while we were
 	 * waiting for more data.
@@ -616,6 +673,9 @@
 		if (ret < 0)
 			return ret;
 	}
+	/* Port got hot-unplugged. */
+	if (!port->guest_connected)
+		return -ENODEV;
 
 	count = min((size_t)(32 * 1024), count);
 
@@ -656,6 +716,10 @@
 	port = filp->private_data;
 	poll_wait(filp, &port->waitqueue, wait);
 
+	if (!port->guest_connected) {
+		/* Port got unplugged */
+		return POLLHUP;
+	}
 	ret = 0;
 	if (!will_read_block(port))
 		ret |= POLLIN | POLLRDNORM;
@@ -667,6 +731,8 @@
 	return ret;
 }
 
+static void remove_port(struct kref *kref);
+
 static int port_fops_release(struct inode *inode, struct file *filp)
 {
 	struct port *port;
@@ -687,6 +753,16 @@
 	reclaim_consumed_buffers(port);
 	spin_unlock_irq(&port->outvq_lock);
 
+	/*
+	 * Locks aren't necessary here as a port can't be opened after
+	 * unplug, and if a port isn't unplugged, a kref would already
+	 * exist for the port.  Plus, taking ports_lock here would
+	 * create a dependency on other locks taken by functions
+	 * inside remove_port if we're the last holder of the port,
+	 * creating many problems.
+	 */
+	kref_put(&port->kref, remove_port);
+
 	return 0;
 }
 
@@ -694,22 +770,31 @@
 {
 	struct cdev *cdev = inode->i_cdev;
 	struct port *port;
+	int ret;
 
-	port = container_of(cdev, struct port, cdev);
+	port = find_port_by_devt(cdev->dev);
 	filp->private_data = port;
 
+	/* Prevent against a port getting hot-unplugged at the same time */
+	spin_lock_irq(&port->portdev->ports_lock);
+	kref_get(&port->kref);
+	spin_unlock_irq(&port->portdev->ports_lock);
+
 	/*
 	 * Don't allow opening of console port devices -- that's done
 	 * via /dev/hvc
 	 */
-	if (is_console_port(port))
-		return -ENXIO;
+	if (is_console_port(port)) {
+		ret = -ENXIO;
+		goto out;
+	}
 
 	/* Allow only one process to open a particular port at a time */
 	spin_lock_irq(&port->inbuf_lock);
 	if (port->guest_connected) {
 		spin_unlock_irq(&port->inbuf_lock);
-		return -EMFILE;
+		ret = -EMFILE;
+		goto out;
 	}
 
 	port->guest_connected = true;
@@ -724,10 +809,23 @@
 	reclaim_consumed_buffers(port);
 	spin_unlock_irq(&port->outvq_lock);
 
+	nonseekable_open(inode, filp);
+
 	/* Notify host of port being opened */
 	send_control_msg(filp->private_data, VIRTIO_CONSOLE_PORT_OPEN, 1);
 
 	return 0;
+out:
+	kref_put(&port->kref, remove_port);
+	return ret;
+}
+
+static int port_fops_fasync(int fd, struct file *filp, int mode)
+{
+	struct port *port;
+
+	port = filp->private_data;
+	return fasync_helper(fd, filp, mode, &port->async_queue);
 }
 
 /*
@@ -743,6 +841,8 @@
 	.write = port_fops_write,
 	.poll  = port_fops_poll,
 	.release = port_fops_release,
+	.fasync = port_fops_fasync,
+	.llseek = no_llseek,
 };
 
 /*
@@ -1001,6 +1101,12 @@
 	return nr_added_bufs;
 }
 
+static void send_sigio_to_port(struct port *port)
+{
+	if (port->async_queue && port->guest_connected)
+		kill_fasync(&port->async_queue, SIGIO, POLL_OUT);
+}
+
 static int add_port(struct ports_device *portdev, u32 id)
 {
 	char debugfs_name[16];
@@ -1015,6 +1121,7 @@
 		err = -ENOMEM;
 		goto fail;
 	}
+	kref_init(&port->kref);
 
 	port->portdev = portdev;
 	port->id = id;
@@ -1022,6 +1129,7 @@
 	port->name = NULL;
 	port->inbuf = NULL;
 	port->cons.hvc = NULL;
+	port->async_queue = NULL;
 
 	port->cons.ws.ws_row = port->cons.ws.ws_col = 0;
 
@@ -1032,14 +1140,20 @@
 	port->in_vq = portdev->in_vqs[port->id];
 	port->out_vq = portdev->out_vqs[port->id];
 
-	cdev_init(&port->cdev, &port_fops);
+	port->cdev = cdev_alloc();
+	if (!port->cdev) {
+		dev_err(&port->portdev->vdev->dev, "Error allocating cdev\n");
+		err = -ENOMEM;
+		goto free_port;
+	}
+	port->cdev->ops = &port_fops;
 
 	devt = MKDEV(portdev->chr_major, id);
-	err = cdev_add(&port->cdev, devt, 1);
+	err = cdev_add(port->cdev, devt, 1);
 	if (err < 0) {
 		dev_err(&port->portdev->vdev->dev,
 			"Error %d adding cdev for port %u\n", err, id);
-		goto free_port;
+		goto free_cdev;
 	}
 	port->dev = device_create(pdrvdata.class, &port->portdev->vdev->dev,
 				  devt, port, "vport%up%u",
@@ -1104,7 +1218,7 @@
 free_device:
 	device_destroy(pdrvdata.class, port->dev->devt);
 free_cdev:
-	cdev_del(&port->cdev);
+	cdev_del(port->cdev);
 free_port:
 	kfree(port);
 fail:
@@ -1113,21 +1227,45 @@
 	return err;
 }
 
-/* Remove all port-specific data. */
-static int remove_port(struct port *port)
+/* No users remain, remove all port-specific data. */
+static void remove_port(struct kref *kref)
+{
+	struct port *port;
+
+	port = container_of(kref, struct port, kref);
+
+	sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
+	device_destroy(pdrvdata.class, port->dev->devt);
+	cdev_del(port->cdev);
+
+	kfree(port->name);
+
+	debugfs_remove(port->debugfs_file);
+
+	kfree(port);
+}
+
+/*
+ * Port got unplugged.  Remove port from portdev's list and drop the
+ * kref reference.  If no userspace has this port opened, it will
+ * result in immediate removal the port.
+ */
+static void unplug_port(struct port *port)
 {
 	struct port_buffer *buf;
 
+	spin_lock_irq(&port->portdev->ports_lock);
+	list_del(&port->list);
+	spin_unlock_irq(&port->portdev->ports_lock);
+
 	if (port->guest_connected) {
 		port->guest_connected = false;
 		port->host_connected = false;
 		wake_up_interruptible(&port->waitqueue);
-		send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 0);
-	}
 
-	spin_lock_irq(&port->portdev->ports_lock);
-	list_del(&port->list);
-	spin_unlock_irq(&port->portdev->ports_lock);
+		/* Let the app know the port is going down. */
+		send_sigio_to_port(port);
+	}
 
 	if (is_console_port(port)) {
 		spin_lock_irq(&pdrvdata_lock);
@@ -1146,9 +1284,6 @@
 		hvc_remove(port->cons.hvc);
 #endif
 	}
-	sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
-	device_destroy(pdrvdata.class, port->dev->devt);
-	cdev_del(&port->cdev);
 
 	/* Remove unused data this port might have received. */
 	discard_port_data(port);
@@ -1159,12 +1294,19 @@
 	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
 		free_buf(buf);
 
-	kfree(port->name);
+	/*
+	 * We should just assume the device itself has gone off --
+	 * else a close on an open port later will try to send out a
+	 * control message.
+	 */
+	port->portdev = NULL;
 
-	debugfs_remove(port->debugfs_file);
-
-	kfree(port);
-	return 0;
+	/*
+	 * Locks around here are not necessary - a port can't be
+	 * opened after we removed the port struct from ports_list
+	 * above.
+	 */
+	kref_put(&port->kref, remove_port);
 }
 
 /* Any private messages that the Host and Guest want to share */
@@ -1203,7 +1345,7 @@
 		add_port(portdev, cpkt->id);
 		break;
 	case VIRTIO_CONSOLE_PORT_REMOVE:
-		remove_port(port);
+		unplug_port(port);
 		break;
 	case VIRTIO_CONSOLE_CONSOLE_PORT:
 		if (!cpkt->value)
@@ -1245,6 +1387,12 @@
 		spin_lock_irq(&port->outvq_lock);
 		reclaim_consumed_buffers(port);
 		spin_unlock_irq(&port->outvq_lock);
+
+		/*
+		 * If the guest is connected, it'll be interested in
+		 * knowing the host connection state changed.
+		 */
+		send_sigio_to_port(port);
 		break;
 	case VIRTIO_CONSOLE_PORT_NAME:
 		/*
@@ -1341,6 +1489,9 @@
 
 	wake_up_interruptible(&port->waitqueue);
 
+	/* Send a SIGIO indicating new data in case the process asked for it */
+	send_sigio_to_port(port);
+
 	if (is_console_port(port) && hvc_poll(port->cons.hvc))
 		hvc_kick();
 }
@@ -1577,6 +1728,10 @@
 		add_port(portdev, 0);
 	}
 
+	spin_lock_irq(&pdrvdata_lock);
+	list_add_tail(&portdev->list, &pdrvdata.portdevs);
+	spin_unlock_irq(&pdrvdata_lock);
+
 	__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
 			   VIRTIO_CONSOLE_DEVICE_READY, 1);
 	return 0;
@@ -1600,23 +1755,41 @@
 {
 	struct ports_device *portdev;
 	struct port *port, *port2;
-	struct port_buffer *buf;
-	unsigned int len;
 
 	portdev = vdev->priv;
 
+	spin_lock_irq(&pdrvdata_lock);
+	list_del(&portdev->list);
+	spin_unlock_irq(&pdrvdata_lock);
+
+	/* Disable interrupts for vqs */
+	vdev->config->reset(vdev);
+	/* Finish up work that's lined up */
 	cancel_work_sync(&portdev->control_work);
 
 	list_for_each_entry_safe(port, port2, &portdev->ports, list)
-		remove_port(port);
+		unplug_port(port);
 
 	unregister_chrdev(portdev->chr_major, "virtio-portsdev");
 
-	while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
-		free_buf(buf);
+	/*
+	 * When yanking out a device, we immediately lose the
+	 * (device-side) queues.  So there's no point in keeping the
+	 * guest side around till we drop our final reference.  This
+	 * also means that any ports which are in an open state will
+	 * have to just stop using the port, as the vqs are going
+	 * away.
+	 */
+	if (use_multiport(portdev)) {
+		struct port_buffer *buf;
+		unsigned int len;
 
-	while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
-		free_buf(buf);
+		while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
+			free_buf(buf);
+
+		while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
+			free_buf(buf);
+	}
 
 	vdev->config->del_vqs(vdev);
 	kfree(portdev->in_vqs);
@@ -1663,6 +1836,7 @@
 			   PTR_ERR(pdrvdata.debugfs_dir));
 	}
 	INIT_LIST_HEAD(&pdrvdata.consoles);
+	INIT_LIST_HEAD(&pdrvdata.portdevs);
 
 	return register_virtio_driver(&virtio_console);
 }
diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c
index b663d57..9f2272e 100644
--- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c
+++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c
@@ -81,7 +81,6 @@
 #include <linux/poll.h>
 #include <linux/proc_fs.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/sysctl.h>
 #include <linux/fs.h>
 #include <linux/cdev.h>
@@ -112,6 +111,7 @@
 #define HWICAP_DEVICES 1
 
 /* An array, which is set to true when the device is registered. */
+static DEFINE_MUTEX(hwicap_mutex);
 static bool probed_devices[HWICAP_DEVICES];
 static struct mutex icap_sem;
 
@@ -502,7 +502,7 @@
 	struct hwicap_drvdata *drvdata;
 	int status;
 
-	lock_kernel();
+	mutex_lock(&hwicap_mutex);
 	drvdata = container_of(inode->i_cdev, struct hwicap_drvdata, cdev);
 
 	status = mutex_lock_interruptible(&drvdata->sem);
@@ -528,7 +528,7 @@
  error:
 	mutex_unlock(&drvdata->sem);
  out:
-	unlock_kernel();
+	mutex_unlock(&hwicap_mutex);
 	return status;
 }
 
@@ -567,6 +567,7 @@
 	.read = hwicap_read,
 	.open = hwicap_open,
 	.release = hwicap_release,
+	.llseek = noop_llseek,
 };
 
 static int __devinit hwicap_setup(struct device *dev, int id,
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index 557e227..ae2b871 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -157,6 +157,7 @@
 	.owner		= THIS_MODULE,
 	.open		= coh901318_debugfs_open,
 	.read		= coh901318_debugfs_read,
+	.llseek		= default_llseek,
 };
 
 
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 70bb350..9dbb28b 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -39,7 +39,7 @@
 	  there're four debug levels (x=0,1,2,3 from low to high).
 	  Usually you should select 'N'.
 
- config EDAC_DECODE_MCE
+config EDAC_DECODE_MCE
 	tristate "Decode MCEs in human-readable form (only on AMD for now)"
 	depends on CPU_SUP_AMD && X86_MCE
 	default y
@@ -51,6 +51,16 @@
 	  which occur really early upon boot, before the module infrastructure
 	  has been initialized.
 
+config EDAC_MCE_INJ
+	tristate "Simple MCE injection interface over /sysfs"
+	depends on EDAC_DECODE_MCE
+	default n
+	help
+	  This is a simple interface to inject MCEs over /sysfs and test
+	  the MCE decoding code in EDAC.
+
+	  This is currently AMD-only.
+
 config EDAC_MM_EDAC
 	tristate "Main Memory EDAC (Error Detection And Correction) reporting"
 	help
@@ -66,13 +76,13 @@
 
 config EDAC_AMD64
 	tristate "AMD64 (Opteron, Athlon64) K8, F10h, F11h"
-	depends on EDAC_MM_EDAC && K8_NB && X86_64 && PCI && EDAC_DECODE_MCE
+	depends on EDAC_MM_EDAC && AMD_NB && X86_64 && PCI && EDAC_DECODE_MCE
 	help
 	  Support for error detection and correction on the AMD 64
 	  Families of Memory Controllers (K8, F10h and F11h)
 
 config EDAC_AMD64_ERROR_INJECTION
-	bool "Sysfs Error Injection facilities"
+	bool "Sysfs HW Error injection facilities"
 	depends on EDAC_AMD64
 	help
 	  Recent Opterons (Family 10h and later) provide for Memory Error
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index ca6b1bb..32c7bc9 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -17,6 +17,9 @@
 edac_core-objs	+= edac_pci.o edac_pci_sysfs.o
 endif
 
+obj-$(CONFIG_EDAC_MCE_INJ)		+= mce_amd_inj.o
+
+edac_mce_amd-objs			:= mce_amd.o
 obj-$(CONFIG_EDAC_DECODE_MCE)		+= edac_mce_amd.o
 
 obj-$(CONFIG_EDAC_AMD76X)		+= amd76x_edac.o
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index e7d5d6b..8521401 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1,5 +1,5 @@
 #include "amd64_edac.h"
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 static struct edac_pci_ctl_info *amd64_ctl_pci;
 
@@ -2073,11 +2073,18 @@
 		amd64_handle_ue(mci, info);
 }
 
-void amd64_decode_bus_error(int node_id, struct err_regs *regs)
+void amd64_decode_bus_error(int node_id, struct mce *m, u32 nbcfg)
 {
 	struct mem_ctl_info *mci = mci_lookup[node_id];
+	struct err_regs regs;
 
-	__amd64_decode_bus_error(mci, regs);
+	regs.nbsl  = (u32) m->status;
+	regs.nbsh  = (u32)(m->status >> 32);
+	regs.nbeal = (u32) m->addr;
+	regs.nbeah = (u32)(m->addr >> 32);
+	regs.nbcfg = nbcfg;
+
+	__amd64_decode_bus_error(mci, &regs);
 
 	/*
 	 * Check the UE bit of the NB status high register, if set generate some
@@ -2086,7 +2093,7 @@
 	 *
 	 * FIXME: this should go somewhere else, if at all.
 	 */
-	if (regs->nbsh & K8_NBSH_UC_ERR && !report_gart_errors)
+	if (regs.nbsh & K8_NBSH_UC_ERR && !report_gart_errors)
 		edac_mc_handle_ue_no_info(mci, "UE bit is set");
 
 }
@@ -2927,7 +2934,7 @@
 	 * to finish initialization of the MC instances.
 	 */
 	err = -ENODEV;
-	for (nb = 0; nb < num_k8_northbridges; nb++) {
+	for (nb = 0; nb < k8_northbridges.num; nb++) {
 		if (!pvt_lookup[nb])
 			continue;
 
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 613b938..044aee4 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -72,7 +72,7 @@
 #include <linux/edac.h>
 #include <asm/msr.h>
 #include "edac_core.h"
-#include "edac_mce_amd.h"
+#include "mce_amd.h"
 
 #define amd64_printk(level, fmt, arg...) \
 	edac_printk(level, "amd64", fmt, ##arg)
@@ -482,11 +482,10 @@
 extern const char *to_msgs[2];
 extern const char *pp_msgs[4];
 extern const char *ii_msgs[4];
-extern const char *ext_msgs[32];
 extern const char *htlink_msgs[8];
 
 #ifdef CONFIG_EDAC_DEBUG
-#define NUM_DBG_ATTRS 9
+#define NUM_DBG_ATTRS 5
 #else
 #define NUM_DBG_ATTRS 0
 #endif
diff --git a/drivers/edac/amd64_edac_dbg.c b/drivers/edac/amd64_edac_dbg.c
index 59cf2cf..e356228 100644
--- a/drivers/edac/amd64_edac_dbg.c
+++ b/drivers/edac/amd64_edac_dbg.c
@@ -1,167 +1,16 @@
 #include "amd64_edac.h"
 
-/*
- * accept a hex value and store it into the virtual error register file, field:
- * nbeal and nbeah. Assume virtual error values have already been set for: NBSL,
- * NBSH and NBCFG. Then proceed to map the error values to a MC, CSROW and
- * CHANNEL
- */
-static ssize_t amd64_nbea_store(struct mem_ctl_info *mci, const char *data,
-				size_t count)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-	unsigned long long value;
-	int ret = 0;
-
-	ret = strict_strtoull(data, 16, &value);
-	if (ret != -EINVAL) {
-		debugf0("received NBEA= 0x%llx\n", value);
-
-		/* place the value into the virtual error packet */
-		pvt->ctl_error_info.nbeal = (u32) value;
-		value >>= 32;
-		pvt->ctl_error_info.nbeah = (u32) value;
-
-		/* Process the Mapping request */
-		/* TODO: Add race prevention */
-		amd_decode_nb_mce(pvt->mc_node_id, &pvt->ctl_error_info, 1);
-
-		return count;
-	}
-	return ret;
+#define EDAC_DCT_ATTR_SHOW(reg)						\
+static ssize_t amd64_##reg##_show(struct mem_ctl_info *mci, char *data)	\
+{									\
+	struct amd64_pvt *pvt = mci->pvt_info;				\
+		return sprintf(data, "0x%016llx\n", (u64)pvt->reg);	\
 }
 
-/* display back what the last NBEA (MCA NB Address (MC4_ADDR)) was written */
-static ssize_t amd64_nbea_show(struct mem_ctl_info *mci, char *data)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-	u64 value;
-
-	value = pvt->ctl_error_info.nbeah;
-	value <<= 32;
-	value |= pvt->ctl_error_info.nbeal;
-
-	return sprintf(data, "%llx\n", value);
-}
-
-/* store the NBSL (MCA NB Status Low (MC4_STATUS)) value user desires */
-static ssize_t amd64_nbsl_store(struct mem_ctl_info *mci, const char *data,
-				size_t count)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-	unsigned long value;
-	int ret = 0;
-
-	ret = strict_strtoul(data, 16, &value);
-	if (ret != -EINVAL) {
-		debugf0("received NBSL= 0x%lx\n", value);
-
-		pvt->ctl_error_info.nbsl = (u32) value;
-
-		return count;
-	}
-	return ret;
-}
-
-/* display back what the last NBSL value written */
-static ssize_t amd64_nbsl_show(struct mem_ctl_info *mci, char *data)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-	u32 value;
-
-	value = pvt->ctl_error_info.nbsl;
-
-	return sprintf(data, "%x\n", value);
-}
-
-/* store the NBSH (MCA NB Status High) value user desires */
-static ssize_t amd64_nbsh_store(struct mem_ctl_info *mci, const char *data,
-				size_t count)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-	unsigned long value;
-	int ret = 0;
-
-	ret = strict_strtoul(data, 16, &value);
-	if (ret != -EINVAL) {
-		debugf0("received NBSH= 0x%lx\n", value);
-
-		pvt->ctl_error_info.nbsh = (u32) value;
-
-		return count;
-	}
-	return ret;
-}
-
-/* display back what the last NBSH value written */
-static ssize_t amd64_nbsh_show(struct mem_ctl_info *mci, char *data)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-	u32 value;
-
-	value = pvt->ctl_error_info.nbsh;
-
-	return sprintf(data, "%x\n", value);
-}
-
-/* accept and store the NBCFG (MCA NB Configuration) value user desires */
-static ssize_t amd64_nbcfg_store(struct mem_ctl_info *mci,
-					const char *data, size_t count)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-	unsigned long value;
-	int ret = 0;
-
-	ret = strict_strtoul(data, 16, &value);
-	if (ret != -EINVAL) {
-		debugf0("received NBCFG= 0x%lx\n", value);
-
-		pvt->ctl_error_info.nbcfg = (u32) value;
-
-		return count;
-	}
-	return ret;
-}
-
-/* various show routines for the controls of a MCI */
-static ssize_t amd64_nbcfg_show(struct mem_ctl_info *mci, char *data)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-
-	return sprintf(data, "%x\n", pvt->ctl_error_info.nbcfg);
-}
-
-
-static ssize_t amd64_dhar_show(struct mem_ctl_info *mci, char *data)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-
-	return sprintf(data, "%x\n", pvt->dhar);
-}
-
-
-static ssize_t amd64_dbam_show(struct mem_ctl_info *mci, char *data)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-
-	return sprintf(data, "%x\n", pvt->dbam0);
-}
-
-
-static ssize_t amd64_topmem_show(struct mem_ctl_info *mci, char *data)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-
-	return sprintf(data, "%llx\n", pvt->top_mem);
-}
-
-
-static ssize_t amd64_topmem2_show(struct mem_ctl_info *mci, char *data)
-{
-	struct amd64_pvt *pvt = mci->pvt_info;
-
-	return sprintf(data, "%llx\n", pvt->top_mem2);
-}
+EDAC_DCT_ATTR_SHOW(dhar);
+EDAC_DCT_ATTR_SHOW(dbam0);
+EDAC_DCT_ATTR_SHOW(top_mem);
+EDAC_DCT_ATTR_SHOW(top_mem2);
 
 static ssize_t amd64_hole_show(struct mem_ctl_info *mci, char *data)
 {
@@ -182,38 +31,6 @@
 
 	{
 		.attr = {
-			.name = "nbea_ctl",
-			.mode = (S_IRUGO | S_IWUSR)
-		},
-		.show = amd64_nbea_show,
-		.store = amd64_nbea_store,
-	},
-	{
-		.attr = {
-			.name = "nbsl_ctl",
-			.mode = (S_IRUGO | S_IWUSR)
-		},
-		.show = amd64_nbsl_show,
-		.store = amd64_nbsl_store,
-	},
-	{
-		.attr = {
-			.name = "nbsh_ctl",
-			.mode = (S_IRUGO | S_IWUSR)
-		},
-		.show = amd64_nbsh_show,
-		.store = amd64_nbsh_store,
-	},
-	{
-		.attr = {
-			.name = "nbcfg_ctl",
-			.mode = (S_IRUGO | S_IWUSR)
-		},
-		.show = amd64_nbcfg_show,
-		.store = amd64_nbcfg_store,
-	},
-	{
-		.attr = {
 			.name = "dhar",
 			.mode = (S_IRUGO)
 		},
@@ -225,7 +42,7 @@
 			.name = "dbam",
 			.mode = (S_IRUGO)
 		},
-		.show = amd64_dbam_show,
+		.show = amd64_dbam0_show,
 		.store = NULL,
 	},
 	{
@@ -233,7 +50,7 @@
 			.name = "topmem",
 			.mode = (S_IRUGO)
 		},
-		.show = amd64_topmem_show,
+		.show = amd64_top_mem_show,
 		.store = NULL,
 	},
 	{
@@ -241,7 +58,7 @@
 			.name = "topmem2",
 			.mode = (S_IRUGO)
 		},
-		.show = amd64_topmem2_show,
+		.show = amd64_top_mem2_show,
 		.store = NULL,
 	},
 	{
diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c
index 0709681..2941dca 100644
--- a/drivers/edac/edac_device_sysfs.c
+++ b/drivers/edac/edac_device_sysfs.c
@@ -13,6 +13,7 @@
 #include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/edac.h>
 
 #include "edac_core.h"
 #include "edac_module.h"
@@ -235,7 +236,7 @@
 	debugf1("%s()\n", __func__);
 
 	/* get the /sys/devices/system/edac reference */
-	edac_class = edac_get_edac_class();
+	edac_class = edac_get_sysfs_class();
 	if (edac_class == NULL) {
 		debugf1("%s() no edac_class error\n", __func__);
 		err = -ENODEV;
@@ -255,7 +256,7 @@
 
 	if (!try_module_get(edac_dev->owner)) {
 		err = -ENODEV;
-		goto err_out;
+		goto err_mod_get;
 	}
 
 	/* register */
@@ -282,6 +283,9 @@
 err_kobj_reg:
 	module_put(edac_dev->owner);
 
+err_mod_get:
+	edac_put_sysfs_class();
+
 err_out:
 	return err;
 }
@@ -290,12 +294,11 @@
  * edac_device_unregister_sysfs_main_kobj:
  *	the '..../edac/<name>' kobject
  */
-void edac_device_unregister_sysfs_main_kobj(
-					struct edac_device_ctl_info *edac_dev)
+void edac_device_unregister_sysfs_main_kobj(struct edac_device_ctl_info *dev)
 {
 	debugf0("%s()\n", __func__);
 	debugf4("%s() name of kobject is: %s\n",
-		__func__, kobject_name(&edac_dev->kobj));
+		__func__, kobject_name(&dev->kobj));
 
 	/*
 	 * Unregister the edac device's kobject and
@@ -304,7 +307,8 @@
 	 *   a) module_put() this module
 	 *   b) 'kfree' the memory
 	 */
-	kobject_put(&edac_dev->kobj);
+	kobject_put(&dev->kobj);
+	edac_put_sysfs_class();
 }
 
 /* edac_dev -> instance information */
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 8aad94d..a413586 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -11,6 +11,7 @@
 
 #include <linux/ctype.h>
 #include <linux/slab.h>
+#include <linux/edac.h>
 #include <linux/bug.h>
 
 #include "edac_core.h"
@@ -1011,13 +1012,13 @@
  */
 int edac_sysfs_setup_mc_kset(void)
 {
-	int err = 0;
+	int err = -EINVAL;
 	struct sysdev_class *edac_class;
 
 	debugf1("%s()\n", __func__);
 
 	/* get the /sys/devices/system/edac class reference */
-	edac_class = edac_get_edac_class();
+	edac_class = edac_get_sysfs_class();
 	if (edac_class == NULL) {
 		debugf1("%s() no edac_class error=%d\n", __func__, err);
 		goto fail_out;
@@ -1028,15 +1029,16 @@
 	if (!mc_kset) {
 		err = -ENOMEM;
 		debugf1("%s() Failed to register '.../edac/mc'\n", __func__);
-		goto fail_out;
+		goto fail_kset;
 	}
 
 	debugf1("%s() Registered '.../edac/mc' kobject\n", __func__);
 
 	return 0;
 
+fail_kset:
+	edac_put_sysfs_class();
 
-	/* error unwind stack */
 fail_out:
 	return err;
 }
@@ -1049,5 +1051,6 @@
 void edac_sysfs_teardown_mc_kset(void)
 {
 	kset_unregister(mc_kset);
+	edac_put_sysfs_class();
 }
 
diff --git a/drivers/edac/edac_mce_amd.c b/drivers/edac/edac_mce_amd.c
deleted file mode 100644
index 9014df6..0000000
--- a/drivers/edac/edac_mce_amd.c
+++ /dev/null
@@ -1,452 +0,0 @@
-#include <linux/module.h>
-#include "edac_mce_amd.h"
-
-static bool report_gart_errors;
-static void (*nb_bus_decoder)(int node_id, struct err_regs *regs);
-
-void amd_report_gart_errors(bool v)
-{
-	report_gart_errors = v;
-}
-EXPORT_SYMBOL_GPL(amd_report_gart_errors);
-
-void amd_register_ecc_decoder(void (*f)(int, struct err_regs *))
-{
-	nb_bus_decoder = f;
-}
-EXPORT_SYMBOL_GPL(amd_register_ecc_decoder);
-
-void amd_unregister_ecc_decoder(void (*f)(int, struct err_regs *))
-{
-	if (nb_bus_decoder) {
-		WARN_ON(nb_bus_decoder != f);
-
-		nb_bus_decoder = NULL;
-	}
-}
-EXPORT_SYMBOL_GPL(amd_unregister_ecc_decoder);
-
-/*
- * string representation for the different MCA reported error types, see F3x48
- * or MSR0000_0411.
- */
-const char *tt_msgs[] = {        /* transaction type */
-	"instruction",
-	"data",
-	"generic",
-	"reserved"
-};
-EXPORT_SYMBOL_GPL(tt_msgs);
-
-const char *ll_msgs[] = {	/* cache level */
-	"L0",
-	"L1",
-	"L2",
-	"L3/generic"
-};
-EXPORT_SYMBOL_GPL(ll_msgs);
-
-const char *rrrr_msgs[] = {
-	"generic",
-	"generic read",
-	"generic write",
-	"data read",
-	"data write",
-	"inst fetch",
-	"prefetch",
-	"evict",
-	"snoop",
-	"reserved RRRR= 9",
-	"reserved RRRR= 10",
-	"reserved RRRR= 11",
-	"reserved RRRR= 12",
-	"reserved RRRR= 13",
-	"reserved RRRR= 14",
-	"reserved RRRR= 15"
-};
-EXPORT_SYMBOL_GPL(rrrr_msgs);
-
-const char *pp_msgs[] = {	/* participating processor */
-	"local node originated (SRC)",
-	"local node responded to request (RES)",
-	"local node observed as 3rd party (OBS)",
-	"generic"
-};
-EXPORT_SYMBOL_GPL(pp_msgs);
-
-const char *to_msgs[] = {
-	"no timeout",
-	"timed out"
-};
-EXPORT_SYMBOL_GPL(to_msgs);
-
-const char *ii_msgs[] = {	/* memory or i/o */
-	"mem access",
-	"reserved",
-	"i/o access",
-	"generic"
-};
-EXPORT_SYMBOL_GPL(ii_msgs);
-
-/*
- * Map the 4 or 5 (family-specific) bits of Extended Error code to the
- * string table.
- */
-const char *ext_msgs[] = {
-	"K8 ECC error",					/* 0_0000b */
-	"CRC error on link",				/* 0_0001b */
-	"Sync error packets on link",			/* 0_0010b */
-	"Master Abort during link operation",		/* 0_0011b */
-	"Target Abort during link operation",		/* 0_0100b */
-	"Invalid GART PTE entry during table walk",	/* 0_0101b */
-	"Unsupported atomic RMW command received",	/* 0_0110b */
-	"WDT error: NB transaction timeout",		/* 0_0111b */
-	"ECC/ChipKill ECC error",			/* 0_1000b */
-	"SVM DEV Error",				/* 0_1001b */
-	"Link Data error",				/* 0_1010b */
-	"Link/L3/Probe Filter Protocol error",		/* 0_1011b */
-	"NB Internal Arrays Parity error",		/* 0_1100b */
-	"DRAM Address/Control Parity error",		/* 0_1101b */
-	"Link Transmission error",			/* 0_1110b */
-	"GART/DEV Table Walk Data error"		/* 0_1111b */
-	"Res 0x100 error",				/* 1_0000b */
-	"Res 0x101 error",				/* 1_0001b */
-	"Res 0x102 error",				/* 1_0010b */
-	"Res 0x103 error",				/* 1_0011b */
-	"Res 0x104 error",				/* 1_0100b */
-	"Res 0x105 error",				/* 1_0101b */
-	"Res 0x106 error",				/* 1_0110b */
-	"Res 0x107 error",				/* 1_0111b */
-	"Res 0x108 error",				/* 1_1000b */
-	"Res 0x109 error",				/* 1_1001b */
-	"Res 0x10A error",				/* 1_1010b */
-	"Res 0x10B error",				/* 1_1011b */
-	"ECC error in L3 Cache Data",			/* 1_1100b */
-	"L3 Cache Tag error",				/* 1_1101b */
-	"L3 Cache LRU Parity error",			/* 1_1110b */
-	"Probe Filter error"				/* 1_1111b */
-};
-EXPORT_SYMBOL_GPL(ext_msgs);
-
-static void amd_decode_dc_mce(u64 mc0_status)
-{
-	u32 ec  = mc0_status & 0xffff;
-	u32 xec = (mc0_status >> 16) & 0xf;
-
-	pr_emerg("Data Cache Error");
-
-	if (xec == 1 && TLB_ERROR(ec))
-		pr_cont(": %s TLB multimatch.\n", LL_MSG(ec));
-	else if (xec == 0) {
-		if (mc0_status & (1ULL << 40))
-			pr_cont(" during Data Scrub.\n");
-		else if (TLB_ERROR(ec))
-			pr_cont(": %s TLB parity error.\n", LL_MSG(ec));
-		else if (MEM_ERROR(ec)) {
-			u8 ll   = ec & 0x3;
-			u8 tt   = (ec >> 2) & 0x3;
-			u8 rrrr = (ec >> 4) & 0xf;
-
-			/* see F10h BKDG (31116), Table 92. */
-			if (ll == 0x1) {
-				if (tt != 0x1)
-					goto wrong_dc_mce;
-
-				pr_cont(": Data/Tag %s error.\n", RRRR_MSG(ec));
-
-			} else if (ll == 0x2 && rrrr == 0x3)
-				pr_cont(" during L1 linefill from L2.\n");
-			else
-				goto wrong_dc_mce;
-		} else if (BUS_ERROR(ec) && boot_cpu_data.x86 == 0xf)
-			pr_cont(" during system linefill.\n");
-		else
-			goto wrong_dc_mce;
-	} else
-		goto wrong_dc_mce;
-
-	return;
-
-wrong_dc_mce:
-	pr_warning("Corrupted DC MCE info?\n");
-}
-
-static void amd_decode_ic_mce(u64 mc1_status)
-{
-	u32 ec  = mc1_status & 0xffff;
-	u32 xec = (mc1_status >> 16) & 0xf;
-
-	pr_emerg("Instruction Cache Error");
-
-	if (xec == 1 && TLB_ERROR(ec))
-		pr_cont(": %s TLB multimatch.\n", LL_MSG(ec));
-	else if (xec == 0) {
-		if (TLB_ERROR(ec))
-			pr_cont(": %s TLB Parity error.\n", LL_MSG(ec));
-		else if (BUS_ERROR(ec)) {
-			if (boot_cpu_data.x86 == 0xf &&
-			    (mc1_status & (1ULL << 58)))
-				pr_cont(" during system linefill.\n");
-			else
-				pr_cont(" during attempted NB data read.\n");
-		} else if (MEM_ERROR(ec)) {
-			u8 ll   = ec & 0x3;
-			u8 rrrr = (ec >> 4) & 0xf;
-
-			if (ll == 0x2)
-				pr_cont(" during a linefill from L2.\n");
-			else if (ll == 0x1) {
-
-				switch (rrrr) {
-				case 0x5:
-					pr_cont(": Parity error during "
-					       "data load.\n");
-					break;
-
-				case 0x7:
-					pr_cont(": Copyback Parity/Victim"
-						" error.\n");
-					break;
-
-				case 0x8:
-					pr_cont(": Tag Snoop error.\n");
-					break;
-
-				default:
-					goto wrong_ic_mce;
-					break;
-				}
-			}
-		} else
-			goto wrong_ic_mce;
-	} else
-		goto wrong_ic_mce;
-
-	return;
-
-wrong_ic_mce:
-	pr_warning("Corrupted IC MCE info?\n");
-}
-
-static void amd_decode_bu_mce(u64 mc2_status)
-{
-	u32 ec = mc2_status & 0xffff;
-	u32 xec = (mc2_status >> 16) & 0xf;
-
-	pr_emerg("Bus Unit Error");
-
-	if (xec == 0x1)
-		pr_cont(" in the write data buffers.\n");
-	else if (xec == 0x3)
-		pr_cont(" in the victim data buffers.\n");
-	else if (xec == 0x2 && MEM_ERROR(ec))
-		pr_cont(": %s error in the L2 cache tags.\n", RRRR_MSG(ec));
-	else if (xec == 0x0) {
-		if (TLB_ERROR(ec))
-			pr_cont(": %s error in a Page Descriptor Cache or "
-				"Guest TLB.\n", TT_MSG(ec));
-		else if (BUS_ERROR(ec))
-			pr_cont(": %s/ECC error in data read from NB: %s.\n",
-				RRRR_MSG(ec), PP_MSG(ec));
-		else if (MEM_ERROR(ec)) {
-			u8 rrrr = (ec >> 4) & 0xf;
-
-			if (rrrr >= 0x7)
-				pr_cont(": %s error during data copyback.\n",
-					RRRR_MSG(ec));
-			else if (rrrr <= 0x1)
-				pr_cont(": %s parity/ECC error during data "
-					"access from L2.\n", RRRR_MSG(ec));
-			else
-				goto wrong_bu_mce;
-		} else
-			goto wrong_bu_mce;
-	} else
-		goto wrong_bu_mce;
-
-	return;
-
-wrong_bu_mce:
-	pr_warning("Corrupted BU MCE info?\n");
-}
-
-static void amd_decode_ls_mce(u64 mc3_status)
-{
-	u32 ec  = mc3_status & 0xffff;
-	u32 xec = (mc3_status >> 16) & 0xf;
-
-	pr_emerg("Load Store Error");
-
-	if (xec == 0x0) {
-		u8 rrrr = (ec >> 4) & 0xf;
-
-		if (!BUS_ERROR(ec) || (rrrr != 0x3 && rrrr != 0x4))
-			goto wrong_ls_mce;
-
-		pr_cont(" during %s.\n", RRRR_MSG(ec));
-	}
-	return;
-
-wrong_ls_mce:
-	pr_warning("Corrupted LS MCE info?\n");
-}
-
-void amd_decode_nb_mce(int node_id, struct err_regs *regs, int handle_errors)
-{
-	u32 ec  = ERROR_CODE(regs->nbsl);
-
-	if (!handle_errors)
-		return;
-
-	/*
-	 * GART TLB error reporting is disabled by default. Bail out early.
-	 */
-	if (TLB_ERROR(ec) && !report_gart_errors)
-		return;
-
-	pr_emerg("Northbridge Error, node %d", node_id);
-
-	/*
-	 * F10h, revD can disable ErrCpu[3:0] so check that first and also the
-	 * value encoding has changed so interpret those differently
-	 */
-	if ((boot_cpu_data.x86 == 0x10) &&
-	    (boot_cpu_data.x86_model > 7)) {
-		if (regs->nbsh & K8_NBSH_ERR_CPU_VAL)
-			pr_cont(", core: %u\n", (u8)(regs->nbsh & 0xf));
-	} else {
-		u8 assoc_cpus = regs->nbsh & 0xf;
-
-		if (assoc_cpus > 0)
-			pr_cont(", core: %d", fls(assoc_cpus) - 1);
-
-		pr_cont("\n");
-	}
-
-	pr_emerg("%s.\n", EXT_ERR_MSG(regs->nbsl));
-
-	if (BUS_ERROR(ec) && nb_bus_decoder)
-		nb_bus_decoder(node_id, regs);
-}
-EXPORT_SYMBOL_GPL(amd_decode_nb_mce);
-
-static void amd_decode_fr_mce(u64 mc5_status)
-{
-	/* we have only one error signature so match all fields at once. */
-	if ((mc5_status & 0xffff) == 0x0f0f)
-		pr_emerg(" FR Error: CPU Watchdog timer expire.\n");
-	else
-		pr_warning("Corrupted FR MCE info?\n");
-}
-
-static inline void amd_decode_err_code(unsigned int ec)
-{
-	if (TLB_ERROR(ec)) {
-		pr_emerg("Transaction: %s, Cache Level %s\n",
-			 TT_MSG(ec), LL_MSG(ec));
-	} else if (MEM_ERROR(ec)) {
-		pr_emerg("Transaction: %s, Type: %s, Cache Level: %s",
-			 RRRR_MSG(ec), TT_MSG(ec), LL_MSG(ec));
-	} else if (BUS_ERROR(ec)) {
-		pr_emerg("Transaction type: %s(%s), %s, Cache Level: %s, "
-			 "Participating Processor: %s\n",
-			  RRRR_MSG(ec), II_MSG(ec), TO_MSG(ec), LL_MSG(ec),
-			  PP_MSG(ec));
-	} else
-		pr_warning("Huh? Unknown MCE error 0x%x\n", ec);
-}
-
-static int amd_decode_mce(struct notifier_block *nb, unsigned long val,
-			   void *data)
-{
-	struct mce *m = (struct mce *)data;
-	struct err_regs regs;
-	int node, ecc;
-
-	pr_emerg("MC%d_STATUS: ", m->bank);
-
-	pr_cont("%sorrected error, other errors lost: %s, "
-		 "CPU context corrupt: %s",
-		 ((m->status & MCI_STATUS_UC) ? "Unc"  : "C"),
-		 ((m->status & MCI_STATUS_OVER) ? "yes"  : "no"),
-		 ((m->status & MCI_STATUS_PCC) ? "yes" : "no"));
-
-	/* do the two bits[14:13] together */
-	ecc = (m->status >> 45) & 0x3;
-	if (ecc)
-		pr_cont(", %sECC Error", ((ecc == 2) ? "C" : "U"));
-
-	pr_cont("\n");
-
-	switch (m->bank) {
-	case 0:
-		amd_decode_dc_mce(m->status);
-		break;
-
-	case 1:
-		amd_decode_ic_mce(m->status);
-		break;
-
-	case 2:
-		amd_decode_bu_mce(m->status);
-		break;
-
-	case 3:
-		amd_decode_ls_mce(m->status);
-		break;
-
-	case 4:
-		regs.nbsl  = (u32) m->status;
-		regs.nbsh  = (u32)(m->status >> 32);
-		regs.nbeal = (u32) m->addr;
-		regs.nbeah = (u32)(m->addr >> 32);
-		node       = amd_get_nb_id(m->extcpu);
-
-		amd_decode_nb_mce(node, &regs, 1);
-		break;
-
-	case 5:
-		amd_decode_fr_mce(m->status);
-		break;
-
-	default:
-		break;
-	}
-
-	amd_decode_err_code(m->status & 0xffff);
-
-	return NOTIFY_STOP;
-}
-
-static struct notifier_block amd_mce_dec_nb = {
-	.notifier_call	= amd_decode_mce,
-};
-
-static int __init mce_amd_init(void)
-{
-	/*
-	 * We can decode MCEs for K8, F10h and F11h CPUs:
-	 */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
-		return 0;
-
-	if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
-		return 0;
-
-	atomic_notifier_chain_register(&x86_mce_decoder_chain, &amd_mce_dec_nb);
-
-	return 0;
-}
-early_initcall(mce_amd_init);
-
-#ifdef MODULE
-static void __exit mce_amd_exit(void)
-{
-	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &amd_mce_dec_nb);
-}
-
-MODULE_DESCRIPTION("AMD MCE decoder");
-MODULE_ALIAS("edac-mce-amd");
-MODULE_LICENSE("GPL");
-module_exit(mce_amd_exit);
-#endif
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index 7e1374a..be4b075 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -27,15 +27,6 @@
 struct workqueue_struct *edac_workqueue;
 
 /*
- * sysfs object: /sys/devices/system/edac
- *	need to export to other files in this modules
- */
-static struct sysdev_class edac_class = {
-	.name = "edac",
-};
-static int edac_class_valid;
-
-/*
  * edac_op_state_to_string()
  */
 char *edac_op_state_to_string(int opstate)
@@ -55,60 +46,6 @@
 }
 
 /*
- * edac_get_edac_class()
- *
- *	return pointer to the edac class of 'edac'
- */
-struct sysdev_class *edac_get_edac_class(void)
-{
-	struct sysdev_class *classptr = NULL;
-
-	if (edac_class_valid)
-		classptr = &edac_class;
-
-	return classptr;
-}
-
-/*
- * edac_register_sysfs_edac_name()
- *
- *	register the 'edac' into /sys/devices/system
- *
- * return:
- *	0  success
- *	!0 error
- */
-static int edac_register_sysfs_edac_name(void)
-{
-	int err;
-
-	/* create the /sys/devices/system/edac directory */
-	err = sysdev_class_register(&edac_class);
-
-	if (err) {
-		debugf1("%s() error=%d\n", __func__, err);
-		return err;
-	}
-
-	edac_class_valid = 1;
-	return 0;
-}
-
-/*
- * sysdev_class_unregister()
- *
- *	unregister the 'edac' from /sys/devices/system
- */
-static void edac_unregister_sysfs_edac_name(void)
-{
-	/* only if currently registered, then unregister it */
-	if (edac_class_valid)
-		sysdev_class_unregister(&edac_class);
-
-	edac_class_valid = 0;
-}
-
-/*
  * edac_workqueue_setup
  *	initialize the edac work queue for polling operations
  */
@@ -154,21 +91,11 @@
 	edac_pci_clear_parity_errors();
 
 	/*
-	 * perform the registration of the /sys/devices/system/edac class object
-	 */
-	if (edac_register_sysfs_edac_name()) {
-		edac_printk(KERN_ERR, EDAC_MC,
-			"Error initializing 'edac' kobject\n");
-		err = -ENODEV;
-		goto error;
-	}
-
-	/*
 	 * now set up the mc_kset under the edac class object
 	 */
 	err = edac_sysfs_setup_mc_kset();
 	if (err)
-		goto sysfs_setup_fail;
+		goto error;
 
 	/* Setup/Initialize the workq for this core */
 	err = edac_workqueue_setup();
@@ -183,9 +110,6 @@
 workq_fail:
 	edac_sysfs_teardown_mc_kset();
 
-sysfs_setup_fail:
-	edac_unregister_sysfs_edac_name();
-
 error:
 	return err;
 }
@@ -201,7 +125,6 @@
 	/* tear down the various subsystems */
 	edac_workqueue_teardown();
 	edac_sysfs_teardown_mc_kset();
-	edac_unregister_sysfs_edac_name();
 }
 
 /*
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index 233d479..17aabb7 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -42,7 +42,6 @@
 				struct edac_device_ctl_info *edac_dev);
 extern int edac_device_create_sysfs(struct edac_device_ctl_info *edac_dev);
 extern void edac_device_remove_sysfs(struct edac_device_ctl_info *edac_dev);
-extern struct sysdev_class *edac_get_edac_class(void);
 
 /* edac core workqueue: single CPU mode */
 extern struct workqueue_struct *edac_workqueue;
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index c39697d..023b01c 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -7,7 +7,7 @@
  *
  */
 #include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/edac.h>
 #include <linux/slab.h>
 #include <linux/ctype.h>
 
@@ -354,7 +354,7 @@
 	/* First time, so create the main kobject and its
 	 * controls and atributes
 	 */
-	edac_class = edac_get_edac_class();
+	edac_class = edac_get_sysfs_class();
 	if (edac_class == NULL) {
 		debugf1("%s() no edac_class\n", __func__);
 		err = -ENODEV;
@@ -368,7 +368,7 @@
 	if (!try_module_get(THIS_MODULE)) {
 		debugf1("%s() try_module_get() failed\n", __func__);
 		err = -ENODEV;
-		goto decrement_count_fail;
+		goto mod_get_fail;
 	}
 
 	edac_pci_top_main_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL);
@@ -403,6 +403,9 @@
 kzalloc_fail:
 	module_put(THIS_MODULE);
 
+mod_get_fail:
+	edac_put_sysfs_class();
+
 decrement_count_fail:
 	/* if are on this error exit, nothing to tear down */
 	atomic_dec(&edac_pci_sysfs_refcount);
@@ -429,6 +432,7 @@
 			__func__);
 		kobject_put(edac_pci_top_main_kobj);
 	}
+	edac_put_sysfs_class();
 }
 
 /*
diff --git a/drivers/edac/edac_stub.c b/drivers/edac/edac_stub.c
index 20b428a..aab9707 100644
--- a/drivers/edac/edac_stub.c
+++ b/drivers/edac/edac_stub.c
@@ -3,10 +3,13 @@
  *
  * Author: Dave Jiang <djiang@mvista.com>
  *
- * 2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
+ * 2007 (c) MontaVista Software, Inc.
+ * 2010 (c) Advanced Micro Devices Inc.
+ *	    Borislav Petkov <borislav.petkov@amd.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
  *
  */
 #include <linux/module.h>
@@ -23,6 +26,8 @@
 int edac_err_assert = 0;
 EXPORT_SYMBOL_GPL(edac_err_assert);
 
+static atomic_t edac_class_valid = ATOMIC_INIT(0);
+
 /*
  * called to determine if there is an EDAC driver interested in
  * knowing an event (such as NMI) occurred
@@ -44,3 +49,41 @@
 	edac_err_assert++;
 }
 EXPORT_SYMBOL_GPL(edac_atomic_assert_error);
+
+/*
+ * sysfs object: /sys/devices/system/edac
+ *	need to export to other files
+ */
+struct sysdev_class edac_class = {
+	.name = "edac",
+};
+EXPORT_SYMBOL_GPL(edac_class);
+
+/* return pointer to the 'edac' node in sysfs */
+struct sysdev_class *edac_get_sysfs_class(void)
+{
+	int err = 0;
+
+	if (atomic_read(&edac_class_valid))
+		goto out;
+
+	/* create the /sys/devices/system/edac directory */
+	err = sysdev_class_register(&edac_class);
+	if (err) {
+		printk(KERN_ERR "Error registering toplevel EDAC sysfs dir\n");
+		return NULL;
+	}
+
+out:
+	atomic_inc(&edac_class_valid);
+	return &edac_class;
+}
+EXPORT_SYMBOL_GPL(edac_get_sysfs_class);
+
+void edac_put_sysfs_class(void)
+{
+	/* last user unregisters it */
+	if (atomic_dec_and_test(&edac_class_valid))
+		sysdev_class_unregister(&edac_class);
+}
+EXPORT_SYMBOL_GPL(edac_put_sysfs_class);
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
new file mode 100644
index 0000000..c018109
--- /dev/null
+++ b/drivers/edac/mce_amd.c
@@ -0,0 +1,680 @@
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "mce_amd.h"
+
+static struct amd_decoder_ops *fam_ops;
+
+static u8 nb_err_cpumask = 0xf;
+
+static bool report_gart_errors;
+static void (*nb_bus_decoder)(int node_id, struct mce *m, u32 nbcfg);
+
+void amd_report_gart_errors(bool v)
+{
+	report_gart_errors = v;
+}
+EXPORT_SYMBOL_GPL(amd_report_gart_errors);
+
+void amd_register_ecc_decoder(void (*f)(int, struct mce *, u32))
+{
+	nb_bus_decoder = f;
+}
+EXPORT_SYMBOL_GPL(amd_register_ecc_decoder);
+
+void amd_unregister_ecc_decoder(void (*f)(int, struct mce *, u32))
+{
+	if (nb_bus_decoder) {
+		WARN_ON(nb_bus_decoder != f);
+
+		nb_bus_decoder = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(amd_unregister_ecc_decoder);
+
+/*
+ * string representation for the different MCA reported error types, see F3x48
+ * or MSR0000_0411.
+ */
+
+/* transaction type */
+const char *tt_msgs[] = { "INSN", "DATA", "GEN", "RESV" };
+EXPORT_SYMBOL_GPL(tt_msgs);
+
+/* cache level */
+const char *ll_msgs[] = { "RESV", "L1", "L2", "L3/GEN" };
+EXPORT_SYMBOL_GPL(ll_msgs);
+
+/* memory transaction type */
+const char *rrrr_msgs[] = {
+       "GEN", "RD", "WR", "DRD", "DWR", "IRD", "PRF", "EV", "SNP"
+};
+EXPORT_SYMBOL_GPL(rrrr_msgs);
+
+/* participating processor */
+const char *pp_msgs[] = { "SRC", "RES", "OBS", "GEN" };
+EXPORT_SYMBOL_GPL(pp_msgs);
+
+/* request timeout */
+const char *to_msgs[] = { "no timeout",	"timed out" };
+EXPORT_SYMBOL_GPL(to_msgs);
+
+/* memory or i/o */
+const char *ii_msgs[] = { "MEM", "RESV", "IO", "GEN" };
+EXPORT_SYMBOL_GPL(ii_msgs);
+
+static const char *f10h_nb_mce_desc[] = {
+	"HT link data error",
+	"Protocol error (link, L3, probe filter, etc.)",
+	"Parity error in NB-internal arrays",
+	"Link Retry due to IO link transmission error",
+	"L3 ECC data cache error",
+	"ECC error in L3 cache tag",
+	"L3 LRU parity bits error",
+	"ECC Error in the Probe Filter directory"
+};
+
+static bool f12h_dc_mce(u16 ec)
+{
+	bool ret = false;
+
+	if (MEM_ERROR(ec)) {
+		u8 ll = ec & 0x3;
+		ret = true;
+
+		if (ll == LL_L2)
+			pr_cont("during L1 linefill from L2.\n");
+		else if (ll == LL_L1)
+			pr_cont("Data/Tag %s error.\n", RRRR_MSG(ec));
+		else
+			ret = false;
+	}
+	return ret;
+}
+
+static bool f10h_dc_mce(u16 ec)
+{
+	u8 r4  = (ec >> 4) & 0xf;
+	u8 ll  = ec & 0x3;
+
+	if (r4 == R4_GEN && ll == LL_L1) {
+		pr_cont("during data scrub.\n");
+		return true;
+	}
+	return f12h_dc_mce(ec);
+}
+
+static bool k8_dc_mce(u16 ec)
+{
+	if (BUS_ERROR(ec)) {
+		pr_cont("during system linefill.\n");
+		return true;
+	}
+
+	return f10h_dc_mce(ec);
+}
+
+static bool f14h_dc_mce(u16 ec)
+{
+	u8 r4	 = (ec >> 4) & 0xf;
+	u8 ll	 = ec & 0x3;
+	u8 tt	 = (ec >> 2) & 0x3;
+	u8 ii	 = tt;
+	bool ret = true;
+
+	if (MEM_ERROR(ec)) {
+
+		if (tt != TT_DATA || ll != LL_L1)
+			return false;
+
+		switch (r4) {
+		case R4_DRD:
+		case R4_DWR:
+			pr_cont("Data/Tag parity error due to %s.\n",
+				(r4 == R4_DRD ? "load/hw prf" : "store"));
+			break;
+		case R4_EVICT:
+			pr_cont("Copyback parity error on a tag miss.\n");
+			break;
+		case R4_SNOOP:
+			pr_cont("Tag parity error during snoop.\n");
+			break;
+		default:
+			ret = false;
+		}
+	} else if (BUS_ERROR(ec)) {
+
+		if ((ii != II_MEM && ii != II_IO) || ll != LL_LG)
+			return false;
+
+		pr_cont("System read data error on a ");
+
+		switch (r4) {
+		case R4_RD:
+			pr_cont("TLB reload.\n");
+			break;
+		case R4_DWR:
+			pr_cont("store.\n");
+			break;
+		case R4_DRD:
+			pr_cont("load.\n");
+			break;
+		default:
+			ret = false;
+		}
+	} else {
+		ret = false;
+	}
+
+	return ret;
+}
+
+static void amd_decode_dc_mce(struct mce *m)
+{
+	u16 ec = m->status & 0xffff;
+	u8 xec = (m->status >> 16) & 0xf;
+
+	pr_emerg(HW_ERR "Data Cache Error: ");
+
+	/* TLB error signatures are the same across families */
+	if (TLB_ERROR(ec)) {
+		u8 tt = (ec >> 2) & 0x3;
+
+		if (tt == TT_DATA) {
+			pr_cont("%s TLB %s.\n", LL_MSG(ec),
+				(xec ? "multimatch" : "parity error"));
+			return;
+		}
+		else
+			goto wrong_dc_mce;
+	}
+
+	if (!fam_ops->dc_mce(ec))
+		goto wrong_dc_mce;
+
+	return;
+
+wrong_dc_mce:
+	pr_emerg(HW_ERR "Corrupted DC MCE info?\n");
+}
+
+static bool k8_ic_mce(u16 ec)
+{
+	u8 ll	 = ec & 0x3;
+	u8 r4	 = (ec >> 4) & 0xf;
+	bool ret = true;
+
+	if (!MEM_ERROR(ec))
+		return false;
+
+	if (ll == 0x2)
+		pr_cont("during a linefill from L2.\n");
+	else if (ll == 0x1) {
+		switch (r4) {
+		case R4_IRD:
+			pr_cont("Parity error during data load.\n");
+			break;
+
+		case R4_EVICT:
+			pr_cont("Copyback Parity/Victim error.\n");
+			break;
+
+		case R4_SNOOP:
+			pr_cont("Tag Snoop error.\n");
+			break;
+
+		default:
+			ret = false;
+			break;
+		}
+	} else
+		ret = false;
+
+	return ret;
+}
+
+static bool f14h_ic_mce(u16 ec)
+{
+	u8 ll    = ec & 0x3;
+	u8 tt    = (ec >> 2) & 0x3;
+	u8 r4  = (ec >> 4) & 0xf;
+	bool ret = true;
+
+	if (MEM_ERROR(ec)) {
+		if (tt != 0 || ll != 1)
+			ret = false;
+
+		if (r4 == R4_IRD)
+			pr_cont("Data/tag array parity error for a tag hit.\n");
+		else if (r4 == R4_SNOOP)
+			pr_cont("Tag error during snoop/victimization.\n");
+		else
+			ret = false;
+	}
+	return ret;
+}
+
+static void amd_decode_ic_mce(struct mce *m)
+{
+	u16 ec = m->status & 0xffff;
+	u8 xec = (m->status >> 16) & 0xf;
+
+	pr_emerg(HW_ERR "Instruction Cache Error: ");
+
+	if (TLB_ERROR(ec))
+		pr_cont("%s TLB %s.\n", LL_MSG(ec),
+			(xec ? "multimatch" : "parity error"));
+	else if (BUS_ERROR(ec)) {
+		bool k8 = (boot_cpu_data.x86 == 0xf && (m->status & BIT_64(58)));
+
+		pr_cont("during %s.\n", (k8 ? "system linefill" : "NB data read"));
+	} else if (fam_ops->ic_mce(ec))
+		;
+	else
+		pr_emerg(HW_ERR "Corrupted IC MCE info?\n");
+}
+
+static void amd_decode_bu_mce(struct mce *m)
+{
+	u32 ec = m->status & 0xffff;
+	u32 xec = (m->status >> 16) & 0xf;
+
+	pr_emerg(HW_ERR "Bus Unit Error");
+
+	if (xec == 0x1)
+		pr_cont(" in the write data buffers.\n");
+	else if (xec == 0x3)
+		pr_cont(" in the victim data buffers.\n");
+	else if (xec == 0x2 && MEM_ERROR(ec))
+		pr_cont(": %s error in the L2 cache tags.\n", RRRR_MSG(ec));
+	else if (xec == 0x0) {
+		if (TLB_ERROR(ec))
+			pr_cont(": %s error in a Page Descriptor Cache or "
+				"Guest TLB.\n", TT_MSG(ec));
+		else if (BUS_ERROR(ec))
+			pr_cont(": %s/ECC error in data read from NB: %s.\n",
+				RRRR_MSG(ec), PP_MSG(ec));
+		else if (MEM_ERROR(ec)) {
+			u8 rrrr = (ec >> 4) & 0xf;
+
+			if (rrrr >= 0x7)
+				pr_cont(": %s error during data copyback.\n",
+					RRRR_MSG(ec));
+			else if (rrrr <= 0x1)
+				pr_cont(": %s parity/ECC error during data "
+					"access from L2.\n", RRRR_MSG(ec));
+			else
+				goto wrong_bu_mce;
+		} else
+			goto wrong_bu_mce;
+	} else
+		goto wrong_bu_mce;
+
+	return;
+
+wrong_bu_mce:
+	pr_emerg(HW_ERR "Corrupted BU MCE info?\n");
+}
+
+static void amd_decode_ls_mce(struct mce *m)
+{
+	u16 ec = m->status & 0xffff;
+	u8 xec = (m->status >> 16) & 0xf;
+
+	if (boot_cpu_data.x86 == 0x14) {
+		pr_emerg("You shouldn't be seeing an LS MCE on this cpu family,"
+			 " please report on LKML.\n");
+		return;
+	}
+
+	pr_emerg(HW_ERR "Load Store Error");
+
+	if (xec == 0x0) {
+		u8 r4 = (ec >> 4) & 0xf;
+
+		if (!BUS_ERROR(ec) || (r4 != R4_DRD && r4 != R4_DWR))
+			goto wrong_ls_mce;
+
+		pr_cont(" during %s.\n", RRRR_MSG(ec));
+	} else
+		goto wrong_ls_mce;
+
+	return;
+
+wrong_ls_mce:
+	pr_emerg(HW_ERR "Corrupted LS MCE info?\n");
+}
+
+static bool k8_nb_mce(u16 ec, u8 xec)
+{
+	bool ret = true;
+
+	switch (xec) {
+	case 0x1:
+		pr_cont("CRC error detected on HT link.\n");
+		break;
+
+	case 0x5:
+		pr_cont("Invalid GART PTE entry during GART table walk.\n");
+		break;
+
+	case 0x6:
+		pr_cont("Unsupported atomic RMW received from an IO link.\n");
+		break;
+
+	case 0x0:
+	case 0x8:
+		if (boot_cpu_data.x86 == 0x11)
+			return false;
+
+		pr_cont("DRAM ECC error detected on the NB.\n");
+		break;
+
+	case 0xd:
+		pr_cont("Parity error on the DRAM addr/ctl signals.\n");
+		break;
+
+	default:
+		ret = false;
+		break;
+	}
+
+	return ret;
+}
+
+static bool f10h_nb_mce(u16 ec, u8 xec)
+{
+	bool ret = true;
+	u8 offset = 0;
+
+	if (k8_nb_mce(ec, xec))
+		return true;
+
+	switch(xec) {
+	case 0xa ... 0xc:
+		offset = 10;
+		break;
+
+	case 0xe:
+		offset = 11;
+		break;
+
+	case 0xf:
+		if (TLB_ERROR(ec))
+			pr_cont("GART Table Walk data error.\n");
+		else if (BUS_ERROR(ec))
+			pr_cont("DMA Exclusion Vector Table Walk error.\n");
+		else
+			ret = false;
+
+		goto out;
+		break;
+
+	case 0x1c ... 0x1f:
+		offset = 24;
+		break;
+
+	default:
+		ret = false;
+
+		goto out;
+		break;
+	}
+
+	pr_cont("%s.\n", f10h_nb_mce_desc[xec - offset]);
+
+out:
+	return ret;
+}
+
+static bool nb_noop_mce(u16 ec, u8 xec)
+{
+	return false;
+}
+
+void amd_decode_nb_mce(int node_id, struct mce *m, u32 nbcfg)
+{
+	u8 xec   = (m->status >> 16) & 0x1f;
+	u16 ec   = m->status & 0xffff;
+	u32 nbsh = (u32)(m->status >> 32);
+
+	pr_emerg(HW_ERR "Northbridge Error, node %d: ", node_id);
+
+	/*
+	 * F10h, revD can disable ErrCpu[3:0] so check that first and also the
+	 * value encoding has changed so interpret those differently
+	 */
+	if ((boot_cpu_data.x86 == 0x10) &&
+	    (boot_cpu_data.x86_model > 7)) {
+		if (nbsh & K8_NBSH_ERR_CPU_VAL)
+			pr_cont(", core: %u", (u8)(nbsh & nb_err_cpumask));
+	} else {
+		u8 assoc_cpus = nbsh & nb_err_cpumask;
+
+		if (assoc_cpus > 0)
+			pr_cont(", core: %d", fls(assoc_cpus) - 1);
+	}
+
+	switch (xec) {
+	case 0x2:
+		pr_cont("Sync error (sync packets on HT link detected).\n");
+		return;
+
+	case 0x3:
+		pr_cont("HT Master abort.\n");
+		return;
+
+	case 0x4:
+		pr_cont("HT Target abort.\n");
+		return;
+
+	case 0x7:
+		pr_cont("NB Watchdog timeout.\n");
+		return;
+
+	case 0x9:
+		pr_cont("SVM DMA Exclusion Vector error.\n");
+		return;
+
+	default:
+		break;
+	}
+
+	if (!fam_ops->nb_mce(ec, xec))
+		goto wrong_nb_mce;
+
+	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10)
+		if ((xec == 0x8 || xec == 0x0) && nb_bus_decoder)
+			nb_bus_decoder(node_id, m, nbcfg);
+
+	return;
+
+wrong_nb_mce:
+	pr_emerg(HW_ERR "Corrupted NB MCE info?\n");
+}
+EXPORT_SYMBOL_GPL(amd_decode_nb_mce);
+
+static void amd_decode_fr_mce(struct mce *m)
+{
+	if (boot_cpu_data.x86 == 0xf ||
+	    boot_cpu_data.x86 == 0x11)
+		goto wrong_fr_mce;
+
+	/* we have only one error signature so match all fields at once. */
+	if ((m->status & 0xffff) == 0x0f0f) {
+		pr_emerg(HW_ERR "FR Error: CPU Watchdog timer expire.\n");
+		return;
+	}
+
+wrong_fr_mce:
+	pr_emerg(HW_ERR "Corrupted FR MCE info?\n");
+}
+
+static inline void amd_decode_err_code(u16 ec)
+{
+	if (TLB_ERROR(ec)) {
+		pr_emerg(HW_ERR "Transaction: %s, Cache Level: %s\n",
+			 TT_MSG(ec), LL_MSG(ec));
+	} else if (MEM_ERROR(ec)) {
+		pr_emerg(HW_ERR "Transaction: %s, Type: %s, Cache Level: %s\n",
+			 RRRR_MSG(ec), TT_MSG(ec), LL_MSG(ec));
+	} else if (BUS_ERROR(ec)) {
+		pr_emerg(HW_ERR "Transaction: %s (%s), %s, Cache Level: %s, "
+			 "Participating Processor: %s\n",
+			  RRRR_MSG(ec), II_MSG(ec), TO_MSG(ec), LL_MSG(ec),
+			  PP_MSG(ec));
+	} else
+		pr_emerg(HW_ERR "Huh? Unknown MCE error 0x%x\n", ec);
+}
+
+/*
+ * Filter out unwanted MCE signatures here.
+ */
+static bool amd_filter_mce(struct mce *m)
+{
+	u8 xec = (m->status >> 16) & 0x1f;
+
+	/*
+	 * NB GART TLB error reporting is disabled by default.
+	 */
+	if (m->bank == 4 && xec == 0x5 && !report_gart_errors)
+		return true;
+
+	return false;
+}
+
+int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
+{
+	struct mce *m = (struct mce *)data;
+	int node, ecc;
+
+	if (amd_filter_mce(m))
+		return NOTIFY_STOP;
+
+	pr_emerg(HW_ERR "MC%d_STATUS: ", m->bank);
+
+	pr_cont("%sorrected error, other errors lost: %s, "
+		 "CPU context corrupt: %s",
+		 ((m->status & MCI_STATUS_UC) ? "Unc"  : "C"),
+		 ((m->status & MCI_STATUS_OVER) ? "yes"  : "no"),
+		 ((m->status & MCI_STATUS_PCC) ? "yes" : "no"));
+
+	/* do the two bits[14:13] together */
+	ecc = (m->status >> 45) & 0x3;
+	if (ecc)
+		pr_cont(", %sECC Error", ((ecc == 2) ? "C" : "U"));
+
+	pr_cont("\n");
+
+	switch (m->bank) {
+	case 0:
+		amd_decode_dc_mce(m);
+		break;
+
+	case 1:
+		amd_decode_ic_mce(m);
+		break;
+
+	case 2:
+		amd_decode_bu_mce(m);
+		break;
+
+	case 3:
+		amd_decode_ls_mce(m);
+		break;
+
+	case 4:
+		node = amd_get_nb_id(m->extcpu);
+		amd_decode_nb_mce(node, m, 0);
+		break;
+
+	case 5:
+		amd_decode_fr_mce(m);
+		break;
+
+	default:
+		break;
+	}
+
+	amd_decode_err_code(m->status & 0xffff);
+
+	return NOTIFY_STOP;
+}
+EXPORT_SYMBOL_GPL(amd_decode_mce);
+
+static struct notifier_block amd_mce_dec_nb = {
+	.notifier_call	= amd_decode_mce,
+};
+
+static int __init mce_amd_init(void)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return 0;
+
+	if ((boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x12) &&
+	    (boot_cpu_data.x86 != 0x14 || boot_cpu_data.x86_model > 0xf))
+		return 0;
+
+	fam_ops = kzalloc(sizeof(struct amd_decoder_ops), GFP_KERNEL);
+	if (!fam_ops)
+		return -ENOMEM;
+
+	switch (boot_cpu_data.x86) {
+	case 0xf:
+		fam_ops->dc_mce = k8_dc_mce;
+		fam_ops->ic_mce = k8_ic_mce;
+		fam_ops->nb_mce = k8_nb_mce;
+		break;
+
+	case 0x10:
+		fam_ops->dc_mce = f10h_dc_mce;
+		fam_ops->ic_mce = k8_ic_mce;
+		fam_ops->nb_mce = f10h_nb_mce;
+		break;
+
+	case 0x11:
+		fam_ops->dc_mce = k8_dc_mce;
+		fam_ops->ic_mce = k8_ic_mce;
+		fam_ops->nb_mce = f10h_nb_mce;
+		break;
+
+	case 0x12:
+		fam_ops->dc_mce = f12h_dc_mce;
+		fam_ops->ic_mce = k8_ic_mce;
+		fam_ops->nb_mce = nb_noop_mce;
+		break;
+
+	case 0x14:
+		nb_err_cpumask  = 0x3;
+		fam_ops->dc_mce = f14h_dc_mce;
+		fam_ops->ic_mce = f14h_ic_mce;
+		fam_ops->nb_mce = nb_noop_mce;
+		break;
+
+	default:
+		printk(KERN_WARNING "Huh? What family is that: %d?!\n",
+				    boot_cpu_data.x86);
+		kfree(fam_ops);
+		return -EINVAL;
+	}
+
+	pr_info("MCE: In-kernel MCE decoding enabled.\n");
+
+	atomic_notifier_chain_register(&x86_mce_decoder_chain, &amd_mce_dec_nb);
+
+	return 0;
+}
+early_initcall(mce_amd_init);
+
+#ifdef MODULE
+static void __exit mce_amd_exit(void)
+{
+	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &amd_mce_dec_nb);
+	kfree(fam_ops);
+}
+
+MODULE_DESCRIPTION("AMD MCE decoder");
+MODULE_ALIAS("edac-mce-amd");
+MODULE_LICENSE("GPL");
+module_exit(mce_amd_exit);
+#endif
diff --git a/drivers/edac/edac_mce_amd.h b/drivers/edac/mce_amd.h
similarity index 65%
rename from drivers/edac/edac_mce_amd.h
rename to drivers/edac/mce_amd.h
index df23ee0..35f6e0e 100644
--- a/drivers/edac/edac_mce_amd.h
+++ b/drivers/edac/mce_amd.h
@@ -1,11 +1,14 @@
 #ifndef _EDAC_MCE_AMD_H
 #define _EDAC_MCE_AMD_H
 
+#include <linux/notifier.h>
+
 #include <asm/mce.h>
 
+#define BIT_64(n)			(U64_C(1) << (n))
+
 #define ERROR_CODE(x)			((x) & 0xffff)
 #define EXT_ERROR_CODE(x)		(((x) >> 16) & 0x1f)
-#define EXT_ERR_MSG(x)			ext_msgs[EXT_ERROR_CODE(x)]
 
 #define LOW_SYNDROME(x)			(((x) >> 15) & 0xff)
 #define HIGH_SYNDROME(x)		(((x) >> 24) & 0xff)
@@ -20,13 +23,14 @@
 #define II_MSG(x)			ii_msgs[II(x)]
 #define LL(x)				(((x) >> 0) & 0x3)
 #define LL_MSG(x)			ll_msgs[LL(x)]
-#define RRRR(x)				(((x) >> 4) & 0xf)
-#define RRRR_MSG(x)			rrrr_msgs[RRRR(x)]
 #define TO(x)				(((x) >> 8) & 0x1)
 #define TO_MSG(x)			to_msgs[TO(x)]
 #define PP(x)				(((x) >> 9) & 0x3)
 #define PP_MSG(x)			pp_msgs[PP(x)]
 
+#define RRRR(x)				(((x) >> 4) & 0xf)
+#define RRRR_MSG(x)			((RRRR(x) < 9) ?  rrrr_msgs[RRRR(x)] : "Wrong R4!")
+
 #define K8_NBSH				0x4C
 
 #define K8_NBSH_VALID_BIT		BIT(31)
@@ -41,13 +45,45 @@
 #define K8_NBSH_UECC			BIT(13)
 #define K8_NBSH_ERR_SCRUBER		BIT(8)
 
+enum tt_ids {
+	TT_INSTR = 0,
+	TT_DATA,
+	TT_GEN,
+	TT_RESV,
+};
+
+enum ll_ids {
+	LL_RESV = 0,
+	LL_L1,
+	LL_L2,
+	LL_LG,
+};
+
+enum ii_ids {
+	II_MEM = 0,
+	II_RESV,
+	II_IO,
+	II_GEN,
+};
+
+enum rrrr_ids {
+	R4_GEN	= 0,
+	R4_RD,
+	R4_WR,
+	R4_DRD,
+	R4_DWR,
+	R4_IRD,
+	R4_PREF,
+	R4_EVICT,
+	R4_SNOOP,
+};
+
 extern const char *tt_msgs[];
 extern const char *ll_msgs[];
 extern const char *rrrr_msgs[];
 extern const char *pp_msgs[];
 extern const char *to_msgs[];
 extern const char *ii_msgs[];
-extern const char *ext_msgs[];
 
 /*
  * relevant NB regs
@@ -60,10 +96,19 @@
 	u32 nbeal;
 };
 
+/*
+ * per-family decoder ops
+ */
+struct amd_decoder_ops {
+	bool (*dc_mce)(u16);
+	bool (*ic_mce)(u16);
+	bool (*nb_mce)(u16, u8);
+};
 
 void amd_report_gart_errors(bool);
-void amd_register_ecc_decoder(void (*f)(int, struct err_regs *));
-void amd_unregister_ecc_decoder(void (*f)(int, struct err_regs *));
-void amd_decode_nb_mce(int, struct err_regs *, int);
+void amd_register_ecc_decoder(void (*f)(int, struct mce *, u32));
+void amd_unregister_ecc_decoder(void (*f)(int, struct mce *, u32));
+void amd_decode_nb_mce(int, struct mce *, u32);
+int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data);
 
 #endif /* _EDAC_MCE_AMD_H */
diff --git a/drivers/edac/mce_amd_inj.c b/drivers/edac/mce_amd_inj.c
new file mode 100644
index 0000000..8d0688f
--- /dev/null
+++ b/drivers/edac/mce_amd_inj.c
@@ -0,0 +1,171 @@
+/*
+ * A simple MCE injection facility for testing the MCE decoding code. This
+ * driver should be built as module so that it can be loaded on production
+ * kernels for testing purposes.
+ *
+ * This file may be distributed under the terms of the GNU General Public
+ * License version 2.
+ *
+ * Copyright (c) 2010:  Borislav Petkov <borislav.petkov@amd.com>
+ *			Advanced Micro Devices Inc.
+ */
+
+#include <linux/kobject.h>
+#include <linux/sysdev.h>
+#include <linux/edac.h>
+#include <asm/mce.h>
+
+#include "mce_amd.h"
+
+struct edac_mce_attr {
+	struct attribute attr;
+	ssize_t (*show) (struct kobject *kobj, struct edac_mce_attr *attr, char *buf);
+	ssize_t (*store)(struct kobject *kobj, struct edac_mce_attr *attr,
+			 const char *buf, size_t count);
+};
+
+#define EDAC_MCE_ATTR(_name, _mode, _show, _store)			\
+static struct edac_mce_attr mce_attr_##_name = __ATTR(_name, _mode, _show, _store)
+
+static struct kobject *mce_kobj;
+
+/*
+ * Collect all the MCi_XXX settings
+ */
+static struct mce i_mce;
+
+#define MCE_INJECT_STORE(reg)						\
+static ssize_t edac_inject_##reg##_store(struct kobject *kobj,		\
+					 struct edac_mce_attr *attr,	\
+					 const char *data, size_t count)\
+{									\
+	int ret = 0;							\
+	unsigned long value;						\
+									\
+	ret = strict_strtoul(data, 16, &value);				\
+	if (ret < 0)							\
+		printk(KERN_ERR "Error writing MCE " #reg " field.\n");	\
+									\
+	i_mce.reg = value;						\
+									\
+	return count;							\
+}
+
+MCE_INJECT_STORE(status);
+MCE_INJECT_STORE(misc);
+MCE_INJECT_STORE(addr);
+
+#define MCE_INJECT_SHOW(reg)						\
+static ssize_t edac_inject_##reg##_show(struct kobject *kobj,		\
+					struct edac_mce_attr *attr,	\
+					char *buf)			\
+{									\
+	return sprintf(buf, "0x%016llx\n", i_mce.reg);			\
+}
+
+MCE_INJECT_SHOW(status);
+MCE_INJECT_SHOW(misc);
+MCE_INJECT_SHOW(addr);
+
+EDAC_MCE_ATTR(status, 0644, edac_inject_status_show, edac_inject_status_store);
+EDAC_MCE_ATTR(misc, 0644, edac_inject_misc_show, edac_inject_misc_store);
+EDAC_MCE_ATTR(addr, 0644, edac_inject_addr_show, edac_inject_addr_store);
+
+/*
+ * This denotes into which bank we're injecting and triggers
+ * the injection, at the same time.
+ */
+static ssize_t edac_inject_bank_store(struct kobject *kobj,
+				      struct edac_mce_attr *attr,
+				      const char *data, size_t count)
+{
+	int ret = 0;
+	unsigned long value;
+
+	ret = strict_strtoul(data, 10, &value);
+	if (ret < 0) {
+		printk(KERN_ERR "Invalid bank value!\n");
+		return -EINVAL;
+	}
+
+	if (value > 5) {
+		printk(KERN_ERR "Non-existant MCE bank: %lu\n", value);
+		return -EINVAL;
+	}
+
+	i_mce.bank = value;
+
+	amd_decode_mce(NULL, 0, &i_mce);
+
+	return count;
+}
+
+static ssize_t edac_inject_bank_show(struct kobject *kobj,
+				     struct edac_mce_attr *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", i_mce.bank);
+}
+
+EDAC_MCE_ATTR(bank, 0644, edac_inject_bank_show, edac_inject_bank_store);
+
+static struct edac_mce_attr *sysfs_attrs[] = { &mce_attr_status, &mce_attr_misc,
+					       &mce_attr_addr, &mce_attr_bank
+};
+
+static int __init edac_init_mce_inject(void)
+{
+	struct sysdev_class *edac_class = NULL;
+	int i, err = 0;
+
+	edac_class = edac_get_sysfs_class();
+	if (!edac_class)
+		return -EINVAL;
+
+	mce_kobj = kobject_create_and_add("mce", &edac_class->kset.kobj);
+	if (!mce_kobj) {
+		printk(KERN_ERR "Error creating a mce kset.\n");
+		err = -ENOMEM;
+		goto err_mce_kobj;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(sysfs_attrs); i++) {
+		err = sysfs_create_file(mce_kobj, &sysfs_attrs[i]->attr);
+		if (err) {
+			printk(KERN_ERR "Error creating %s in sysfs.\n",
+					sysfs_attrs[i]->attr.name);
+			goto err_sysfs_create;
+		}
+	}
+	return 0;
+
+err_sysfs_create:
+	while (i-- >= 0)
+		sysfs_remove_file(mce_kobj, &sysfs_attrs[i]->attr);
+
+	kobject_del(mce_kobj);
+
+err_mce_kobj:
+	edac_put_sysfs_class();
+
+	return err;
+}
+
+static void __exit edac_exit_mce_inject(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sysfs_attrs); i++)
+		sysfs_remove_file(mce_kobj, &sysfs_attrs[i]->attr);
+
+	kobject_del(mce_kobj);
+
+	edac_put_sysfs_class();
+}
+
+module_init(edac_init_mce_inject);
+module_exit(edac_exit_mce_inject);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Borislav Petkov <borislav.petkov@amd.com>");
+MODULE_AUTHOR("AMD Inc.");
+MODULE_DESCRIPTION("MCE injection facility for testing MCE decoding");
diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c
index 8528b10..bf184fb 100644
--- a/drivers/firewire/nosy.c
+++ b/drivers/firewire/nosy.c
@@ -405,6 +405,7 @@
 	.poll =			nosy_poll,
 	.open =			nosy_open,
 	.release =		nosy_release,
+	.llseek =		noop_llseek,
 };
 
 #define PHY_PACKET_SIZE 12 /* 1 payload, 1 inverse, 1 ack = 3 quadlets */
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 280c9b5..88a3ae6 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -125,7 +125,7 @@
 config ISCSI_IBFT
 	tristate "iSCSI Boot Firmware Table Attributes module"
 	select ISCSI_BOOT_SYSFS
-	depends on ISCSI_IBFT_FIND && SCSI
+	depends on ISCSI_IBFT_FIND && SCSI && SCSI_LOWLEVEL
 	default	n
 	help
 	  This option enables support for detection and exposing of iSCSI
diff --git a/drivers/gpio/tc35892-gpio.c b/drivers/gpio/tc35892-gpio.c
index 1be6288..7e10c93 100644
--- a/drivers/gpio/tc35892-gpio.c
+++ b/drivers/gpio/tc35892-gpio.c
@@ -322,6 +322,9 @@
 		goto out_freeirq;
 	}
 
+	if (pdata->setup)
+		pdata->setup(tc35892, tc35892_gpio->chip.base);
+
 	platform_set_drvdata(pdev, tc35892_gpio);
 
 	return 0;
@@ -338,9 +341,14 @@
 static int __devexit tc35892_gpio_remove(struct platform_device *pdev)
 {
 	struct tc35892_gpio *tc35892_gpio = platform_get_drvdata(pdev);
+	struct tc35892 *tc35892 = tc35892_gpio->tc35892;
+	struct tc35892_gpio_platform_data *pdata = tc35892->pdata->gpio;
 	int irq = platform_get_irq(pdev, 0);
 	int ret;
 
+	if (pdata->remove)
+		pdata->remove(tc35892, tc35892_gpio->chip.base);
+
 	ret = gpiochip_remove(&tc35892_gpio->chip);
 	if (ret < 0) {
 		dev_err(tc35892_gpio->dev,
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 4cab0c6..7af4436 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -73,7 +73,8 @@
 
 config DRM_I810
 	tristate "Intel I810"
-	depends on DRM && AGP && AGP_INTEL
+	# BKL usage in order to avoid AB-BA deadlocks, may become BROKEN_ON_SMP
+	depends on DRM && AGP && AGP_INTEL && BKL
 	help
 	  Choose this option if you have an Intel I810 graphics card.  If M is
 	  selected, the module will be called i810.  AGP support is required
@@ -86,6 +87,8 @@
 
 config DRM_I830
 	tristate "i830 driver"
+	# BKL usage in order to avoid AB-BA deadlocks, i830 may get removed
+	depends on BKL
 	help
 	  Choose this option if you have a system that has Intel 830M, 845G,
 	  852GM, 855GM or 865G integrated graphics.  If M is selected, the
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 84da748..ff6690f 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -284,7 +284,8 @@
 /** File operations structure */
 static const struct file_operations drm_stub_fops = {
 	.owner = THIS_MODULE,
-	.open = drm_stub_open
+	.open = drm_stub_open,
+	.llseek = noop_llseek,
 };
 
 static int __init drm_core_init(void)
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index fb07e73..ff33e53 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -119,6 +119,7 @@
 	.unlocked_ioctl = i810_ioctl,
 	.mmap = i810_mmap_buffers,
 	.fasync = drm_fasync,
+	.llseek = noop_llseek,
 };
 
 static int i810_map_buffer(struct drm_buf *buf, struct drm_file *file_priv)
diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c
index b4250b2..fe69914c 100644
--- a/drivers/gpu/drm/i810/i810_drv.c
+++ b/drivers/gpu/drm/i810/i810_drv.c
@@ -63,6 +63,7 @@
 		 .mmap = drm_mmap,
 		 .poll = drm_poll,
 		 .fasync = drm_fasync,
+		 .llseek = noop_llseek,
 	},
 
 	.pci_driver = {
diff --git a/drivers/gpu/drm/i830/i830_dma.c b/drivers/gpu/drm/i830/i830_dma.c
index cc92c7e..ca6f31f 100644
--- a/drivers/gpu/drm/i830/i830_dma.c
+++ b/drivers/gpu/drm/i830/i830_dma.c
@@ -121,6 +121,7 @@
 	.unlocked_ioctl = i830_ioctl,
 	.mmap = i830_mmap_buffers,
 	.fasync = drm_fasync,
+	.llseek = noop_llseek,
 };
 
 static int i830_map_buffer(struct drm_buf *buf, struct drm_file *file_priv)
diff --git a/drivers/gpu/drm/i830/i830_drv.c b/drivers/gpu/drm/i830/i830_drv.c
index a5c66aa..5b6298b 100644
--- a/drivers/gpu/drm/i830/i830_drv.c
+++ b/drivers/gpu/drm/i830/i830_drv.c
@@ -74,6 +74,7 @@
 		 .mmap = drm_mmap,
 		 .poll = drm_poll,
 		 .fasync = drm_fasync,
+		 .llseek = noop_llseek,
 	},
 
 	.pci_driver = {
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 5e43d70..0481497 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -782,6 +782,7 @@
 	.open = i915_wedged_open,
 	.read = i915_wedged_read,
 	.write = i915_wedged_write,
+	.llseek = default_llseek,
 };
 
 /* As the drm_debugfs_init() routines are called before dev->dev_private is
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 6dbe14c..895ab89 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -548,6 +548,7 @@
 #ifdef CONFIG_COMPAT
 		 .compat_ioctl = i915_compat_ioctl,
 #endif
+		 .llseek = noop_llseek,
 	},
 
 	.pci_driver = {
diff --git a/drivers/gpu/drm/mga/mga_drv.c b/drivers/gpu/drm/mga/mga_drv.c
index 26d0d8c..ac64f0b 100644
--- a/drivers/gpu/drm/mga/mga_drv.c
+++ b/drivers/gpu/drm/mga/mga_drv.c
@@ -75,6 +75,7 @@
 #ifdef CONFIG_COMPAT
 		.compat_ioctl = mga_compat_ioctl,
 #endif
+		.llseek = noop_llseek,
 	},
 	.pci_driver = {
 		.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.c b/drivers/gpu/drm/nouveau/nouveau_drv.c
index 1de5eb5..eb15345 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.c
@@ -393,6 +393,7 @@
 #if defined(CONFIG_COMPAT)
 		.compat_ioctl = nouveau_compat_ioctl,
 #endif
+		.llseek = noop_llseek,
 	},
 	.pci_driver = {
 		.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/r128/r128_drv.c b/drivers/gpu/drm/r128/r128_drv.c
index 1e2971f..d42c76c 100644
--- a/drivers/gpu/drm/r128/r128_drv.c
+++ b/drivers/gpu/drm/r128/r128_drv.c
@@ -71,6 +71,7 @@
 #ifdef CONFIG_COMPAT
 		.compat_ioctl = r128_compat_ioctl,
 #endif
+		.llseek = noop_llseek,
 	},
 	.pci_driver = {
 		.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 795403b..29c1237 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -219,6 +219,7 @@
 #ifdef CONFIG_COMPAT
 		 .compat_ioctl = radeon_compat_ioctl,
 #endif
+		 .llseek = noop_llseek,
 	},
 
 	.pci_driver = {
diff --git a/drivers/gpu/drm/savage/savage_drv.c b/drivers/gpu/drm/savage/savage_drv.c
index 021de44..2a2830f 100644
--- a/drivers/gpu/drm/savage/savage_drv.c
+++ b/drivers/gpu/drm/savage/savage_drv.c
@@ -54,6 +54,7 @@
 		 .mmap = drm_mmap,
 		 .poll = drm_poll,
 		 .fasync = drm_fasync,
+		 .llseek = noop_llseek,
 	},
 
 	.pci_driver = {
diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c
index 776bf9e..4bb10ef 100644
--- a/drivers/gpu/drm/sis/sis_drv.c
+++ b/drivers/gpu/drm/sis/sis_drv.c
@@ -83,6 +83,7 @@
 		 .mmap = drm_mmap,
 		 .poll = drm_poll,
 		 .fasync = drm_fasync,
+		 .llseek = noop_llseek,
 	},
 	.pci_driver = {
 		 .name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/tdfx/tdfx_drv.c b/drivers/gpu/drm/tdfx/tdfx_drv.c
index ec5a43e..640567e 100644
--- a/drivers/gpu/drm/tdfx/tdfx_drv.c
+++ b/drivers/gpu/drm/tdfx/tdfx_drv.c
@@ -52,6 +52,7 @@
 		 .mmap = drm_mmap,
 		 .poll = drm_poll,
 		 .fasync = drm_fasync,
+		 .llseek = noop_llseek,
 	},
 	.pci_driver = {
 		 .name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/via/via_drv.c b/drivers/gpu/drm/via/via_drv.c
index 7a1b210..b8984a5 100644
--- a/drivers/gpu/drm/via/via_drv.c
+++ b/drivers/gpu/drm/via/via_drv.c
@@ -62,6 +62,7 @@
 		.mmap = drm_mmap,
 		.poll = drm_poll,
 		.fasync = drm_fasync,
+		.llseek = noop_llseek,
 		},
 	.pci_driver = {
 		.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index a96ed6d..2ef93df 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -820,6 +820,7 @@
 #if defined(CONFIG_COMPAT)
 		 .compat_ioctl = drm_compat_ioctl,
 #endif
+		 .llseek = noop_llseek,
 		 },
 	.pci_driver = {
 		       .name = VMWGFX_DRIVER_NAME,
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index f366f96..c380c65 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -1211,6 +1211,7 @@
 	.poll = vga_arb_fpoll,
 	.open = vga_arb_open,
 	.release = vga_arb_release,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice vga_arb_device = {
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index 850d02a..61a3e57 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -1051,6 +1051,7 @@
 	.read           = hid_debug_events_read,
 	.poll		= hid_debug_events_poll,
 	.release        = hid_debug_events_release,
+	.llseek		= noop_llseek,
 };
 
 
diff --git a/drivers/hid/hid-roccat.c b/drivers/hid/hid-roccat.c
index f6e80c7..5a6879e 100644
--- a/drivers/hid/hid-roccat.c
+++ b/drivers/hid/hid-roccat.c
@@ -384,6 +384,7 @@
 	.poll = roccat_poll,
 	.open = roccat_open,
 	.release = roccat_release,
+	.llseek = noop_llseek,
 };
 
 static int __init roccat_init(void)
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index a3866b5..925992f 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -340,6 +340,7 @@
 	.open =         hidraw_open,
 	.release =      hidraw_release,
 	.unlocked_ioctl = hidraw_ioctl,
+	.llseek =	noop_llseek,
 };
 
 void hidraw_report_event(struct hid_device *hid, u8 *data, int len)
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 681e620..dfcb276 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -847,6 +847,7 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= hiddev_compat_ioctl,
 #endif
+	.llseek		= noop_llseek,
 };
 
 static char *hiddev_devnode(struct device *dev, mode_t *mode)
diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c
index 653db1b..23b8555 100644
--- a/drivers/hwmon/asus_atk0110.c
+++ b/drivers/hwmon/asus_atk0110.c
@@ -762,6 +762,7 @@
 	.read		= atk_debugfs_ggrp_read,
 	.open		= atk_debugfs_ggrp_open,
 	.release	= atk_debugfs_ggrp_release,
+	.llseek		= no_llseek,
 };
 
 static void atk_debugfs_init(struct atk_data *data)
diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c
index b7ca2a9..d4d4ca6 100644
--- a/drivers/hwmon/fschmd.c
+++ b/drivers/hwmon/fschmd.c
@@ -38,7 +38,6 @@
 #include <linux/i2c.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
-#include <linux/smp_lock.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
 #include <linux/sysfs.h>
@@ -50,6 +49,7 @@
 #include <linux/kref.h>
 
 /* Addresses to scan */
+static DEFINE_MUTEX(watchdog_mutex);
 static const unsigned short normal_i2c[] = { 0x73, I2C_CLIENT_END };
 
 /* Insmod parameters */
@@ -858,7 +858,7 @@
 	int i, ret = 0;
 	struct fschmd_data *data = filp->private_data;
 
-	lock_kernel();
+	mutex_lock(&watchdog_mutex);
 	switch (cmd) {
 	case WDIOC_GETSUPPORT:
 		ident.firmware_version = data->revision;
@@ -915,7 +915,7 @@
 	default:
 		ret = -ENOTTY;
 	}
-	unlock_kernel();
+	mutex_unlock(&watchdog_mutex);
 	return ret;
 }
 
diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c
index 697202e..8e540ad 100644
--- a/drivers/hwmon/w83793.c
+++ b/drivers/hwmon/w83793.c
@@ -35,7 +35,6 @@
 #include <linux/slab.h>
 #include <linux/i2c.h>
 #include <linux/hwmon.h>
-#include <linux/smp_lock.h>
 #include <linux/hwmon-vid.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/err.h>
@@ -52,6 +51,7 @@
 #define WATCHDOG_TIMEOUT 2	/* 2 minute default timeout */
 
 /* Addresses to scan */
+static DEFINE_MUTEX(watchdog_mutex);
 static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, 0x2f,
 						I2C_CLIENT_END };
 
@@ -1333,7 +1333,7 @@
 	int val, ret = 0;
 	struct w83793_data *data = filp->private_data;
 
-	lock_kernel();
+	mutex_lock(&watchdog_mutex);
 	switch (cmd) {
 	case WDIOC_GETSUPPORT:
 		if (!nowayout)
@@ -1387,7 +1387,7 @@
 	default:
 		ret = -ENOTTY;
 	}
-	unlock_kernel();
+	mutex_unlock(&watchdog_mutex);
 	return ret;
 }
 
diff --git a/drivers/i2c/busses/i2c-pasemi.c b/drivers/i2c/busses/i2c-pasemi.c
index 4174101..837b8c1 100644
--- a/drivers/i2c/busses/i2c-pasemi.c
+++ b/drivers/i2c/busses/i2c-pasemi.c
@@ -88,7 +88,7 @@
 	reg_write(smbus, REG_SMSTA, status);
 }
 
-static unsigned int pasemi_smb_waitready(struct pasemi_smbus *smbus)
+static int pasemi_smb_waitready(struct pasemi_smbus *smbus)
 {
 	int timeout = 10;
 	unsigned int status;
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 31fc769..0c73fe3 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -31,7 +31,6 @@
 #include <linux/delay.h>
 #include <linux/timer.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/errno.h>
@@ -52,6 +51,7 @@
 
 #include "ide-cd.h"
 
+static DEFINE_MUTEX(ide_cd_mutex);
 static DEFINE_MUTEX(idecd_ref_mutex);
 
 static void ide_cd_release(struct device *);
@@ -1602,7 +1602,7 @@
 	struct cdrom_info *info;
 	int rc = -ENXIO;
 
-	lock_kernel();
+	mutex_lock(&ide_cd_mutex);
 	info = ide_cd_get(bdev->bd_disk);
 	if (!info)
 		goto out;
@@ -1611,7 +1611,7 @@
 	if (rc < 0)
 		ide_cd_put(info);
 out:
-	unlock_kernel();
+	mutex_unlock(&ide_cd_mutex);
 	return rc;
 }
 
@@ -1619,11 +1619,11 @@
 {
 	struct cdrom_info *info = ide_drv_g(disk, cdrom_info);
 
-	lock_kernel();
+	mutex_lock(&ide_cd_mutex);
 	cdrom_release(&info->devinfo, mode);
 
 	ide_cd_put(info);
-	unlock_kernel();
+	mutex_unlock(&ide_cd_mutex);
 
 	return 0;
 }
@@ -1694,9 +1694,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ide_cd_mutex);
 	ret = idecd_locked_ioctl(bdev, mode, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ide_cd_mutex);
 
 	return ret;
 }
diff --git a/drivers/ide/ide-cs.c b/drivers/ide/ide-cs.c
index 2a4cb9c..404843e 100644
--- a/drivers/ide/ide-cs.c
+++ b/drivers/ide/ide-cs.c
@@ -43,7 +43,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 #include <pcmcia/cisreg.h>
@@ -72,17 +71,6 @@
 
 static void ide_detach(struct pcmcia_device *p_dev);
 
-
-
-
-/*======================================================================
-
-    ide_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-======================================================================*/
-
 static int ide_probe(struct pcmcia_device *link)
 {
     ide_info_t *info;
@@ -97,23 +85,12 @@
     info->p_dev = link;
     link->priv = info;
 
-    link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-    link->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO |
+	    CONF_AUTO_SET_VPP | CONF_AUTO_CHECK_VCC;
 
     return ide_config(link);
 } /* ide_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void ide_detach(struct pcmcia_device *link)
 {
     ide_info_t *info = link->priv;
@@ -187,79 +164,31 @@
     return NULL;
 }
 
-/*======================================================================
-
-    ide_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ide device available to the system.
-
-======================================================================*/
-
-struct pcmcia_config_check {
-	unsigned long ctl_base;
-	int skip_vcc;
-	int is_kme;
-};
-
-static int pcmcia_check_one_config(struct pcmcia_device *pdev,
-				   cistpl_cftable_entry_t *cfg,
-				   cistpl_cftable_entry_t *dflt,
-				   unsigned int vcc,
-				   void *priv_data)
+static int pcmcia_check_one_config(struct pcmcia_device *pdev, void *priv_data)
 {
-	struct pcmcia_config_check *stk = priv_data;
+	int *is_kme = priv_data;
 
-	/* Check for matching Vcc, unless we're desperate */
-	if (!stk->skip_vcc) {
-		if (cfg->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-			if (vcc != cfg->vcc.param[CISTPL_POWER_VNOM] / 10000)
-				return -ENODEV;
-		} else if (dflt->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-			if (vcc != dflt->vcc.param[CISTPL_POWER_VNOM] / 10000)
-				return -ENODEV;
-		}
+	if (!(pdev->resource[0]->flags & IO_DATA_PATH_WIDTH_8)) {
+		pdev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+		pdev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 	}
+	pdev->resource[1]->flags &= ~IO_DATA_PATH_WIDTH;
+	pdev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
 
-	if (cfg->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		pdev->conf.Vpp = cfg->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-	else if (dflt->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		pdev->conf.Vpp = dflt->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		pdev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-
-		pdev->conf.ConfigIndex = cfg->index;
-		pdev->resource[0]->start = io->win[0].base;
-		if (!(io->flags & CISTPL_IO_16BIT)) {
-			pdev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-			pdev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-		}
-		if (io->nwin == 2) {
-			pdev->resource[0]->end = 8;
-			pdev->resource[1]->start = io->win[1].base;
-			pdev->resource[1]->end = (stk->is_kme) ? 2 : 1;
-			if (pcmcia_request_io(pdev) != 0)
-				return -ENODEV;
-			stk->ctl_base = pdev->resource[1]->start;
-		} else if ((io->nwin == 1) && (io->win[0].len >= 16)) {
-			pdev->resource[0]->end = io->win[0].len;
-			pdev->resource[1]->end = 0;
-			if (pcmcia_request_io(pdev) != 0)
-				return -ENODEV;
-			stk->ctl_base = pdev->resource[0]->start + 0x0e;
-		} else
+	if (pdev->resource[1]->end) {
+		pdev->resource[0]->end = 8;
+		pdev->resource[1]->end = (*is_kme) ? 2 : 1;
+	} else {
+		if (pdev->resource[0]->end < 16)
 			return -ENODEV;
-		/* If we've got this far, we're done */
-		return 0;
 	}
-	return -ENODEV;
+
+	return pcmcia_request_io(pdev);
 }
 
 static int ide_config(struct pcmcia_device *link)
 {
     ide_info_t *info = link->priv;
-    struct pcmcia_config_check *stk = NULL;
     int ret = 0, is_kme = 0;
     unsigned long io_base, ctl_base;
     struct ide_host *host;
@@ -270,23 +199,21 @@
 	      ((link->card_id == PRODID_KME_KXLC005_A) ||
 	       (link->card_id == PRODID_KME_KXLC005_B)));
 
-    stk = kzalloc(sizeof(*stk), GFP_KERNEL);
-    if (!stk)
-	    goto err_mem;
-    stk->is_kme = is_kme;
-    stk->skip_vcc = io_base = ctl_base = 0;
-
-    if (pcmcia_loop_config(link, pcmcia_check_one_config, stk)) {
-	    stk->skip_vcc = 1;
-	    if (pcmcia_loop_config(link, pcmcia_check_one_config, stk))
+    if (pcmcia_loop_config(link, pcmcia_check_one_config, &is_kme)) {
+	    link->config_flags &= ~CONF_AUTO_CHECK_VCC;
+	    if (pcmcia_loop_config(link, pcmcia_check_one_config, &is_kme))
 		    goto failed; /* No suitable config found */
     }
     io_base = link->resource[0]->start;
-    ctl_base = stk->ctl_base;
+    if (link->resource[1]->end)
+	    ctl_base = link->resource[1]->start;
+    else
+	    ctl_base = link->resource[0]->start + 0x0e;
 
     if (!link->irq)
 	    goto failed;
-    ret = pcmcia_request_configuration(link, &link->conf);
+
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
@@ -311,29 +238,15 @@
     info->host = host;
     dev_info(&link->dev, "ide-cs: hd%c: Vpp = %d.%d\n",
 	    'a' + host->ports[0]->index * 2,
-	    link->conf.Vpp / 10, link->conf.Vpp % 10);
+	    link->vpp / 10, link->vpp % 10);
 
-    kfree(stk);
     return 0;
 
-err_mem:
-    printk(KERN_NOTICE "ide-cs: ide_config failed memory allocation\n");
-    goto failed;
-
 failed:
-    kfree(stk);
     ide_release(link);
     return -ENODEV;
 } /* ide_config */
 
-/*======================================================================
-
-    After a card is removed, ide_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void ide_release(struct pcmcia_device *link)
 {
     ide_info_t *info = link->priv;
@@ -359,15 +272,6 @@
 } /* ide_release */
 
 
-/*======================================================================
-
-    The card status event handler.  Mostly, this schedules other
-    stuff to run after an event is received.  A CARD_REMOVAL event
-    also sets some flags to discourage the ide drivers from
-    talking to the ports.
-
-======================================================================*/
-
 static struct pcmcia_device_id ide_ids[] = {
 	PCMCIA_DEVICE_FUNC_ID(4),
 	PCMCIA_DEVICE_MANF_CARD(0x0000, 0x0000),	/* Corsair */
@@ -440,9 +344,7 @@
 
 static struct pcmcia_driver ide_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "ide-cs",
-	},
+	.name		= "ide-cs",
 	.probe		= ide_probe,
 	.remove		= ide_detach,
 	.id_table       = ide_ids,
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 7433e07..7c5b01c 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -516,10 +516,10 @@
 	return ide_no_data_taskfile(drive, &cmd);
 }
 
-static void update_ordered(ide_drive_t *drive)
+static void update_flush(ide_drive_t *drive)
 {
 	u16 *id = drive->id;
-	unsigned ordered = QUEUE_ORDERED_NONE;
+	unsigned flush = 0;
 
 	if (drive->dev_flags & IDE_DFLAG_WCACHE) {
 		unsigned long long capacity;
@@ -543,13 +543,12 @@
 		       drive->name, barrier ? "" : "not ");
 
 		if (barrier) {
-			ordered = QUEUE_ORDERED_DRAIN_FLUSH;
+			flush = REQ_FLUSH;
 			blk_queue_prep_rq(drive->queue, idedisk_prep_fn);
 		}
-	} else
-		ordered = QUEUE_ORDERED_DRAIN;
+	}
 
-	blk_queue_ordered(drive->queue, ordered);
+	blk_queue_flush(drive->queue, flush);
 }
 
 ide_devset_get_flag(wcache, IDE_DFLAG_WCACHE);
@@ -572,7 +571,7 @@
 		}
 	}
 
-	update_ordered(drive);
+	update_flush(drive);
 
 	return err;
 }
diff --git a/drivers/ide/ide-disk_ioctl.c b/drivers/ide/ide-disk_ioctl.c
index ec94c66..da36f72 100644
--- a/drivers/ide/ide-disk_ioctl.c
+++ b/drivers/ide/ide-disk_ioctl.c
@@ -1,10 +1,11 @@
 #include <linux/kernel.h>
 #include <linux/ide.h>
 #include <linux/hdreg.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include "ide-disk.h"
 
+static DEFINE_MUTEX(ide_disk_ioctl_mutex);
 static const struct ide_ioctl_devset ide_disk_ioctl_settings[] = {
 { HDIO_GET_ADDRESS,	HDIO_SET_ADDRESS,   &ide_devset_address   },
 { HDIO_GET_MULTCOUNT,	HDIO_SET_MULTCOUNT, &ide_devset_multcount },
@@ -19,13 +20,13 @@
 {
 	int err;
 
-	lock_kernel();
+	mutex_lock(&ide_disk_ioctl_mutex);
 	err = ide_setting_ioctl(drive, bdev, cmd, arg, ide_disk_ioctl_settings);
 	if (err != -EOPNOTSUPP)
 		goto out;
 
 	err = generic_ide_ioctl(drive, bdev, cmd, arg);
 out:
-	unlock_kernel();
+	mutex_unlock(&ide_disk_ioctl_mutex);
 	return err;
 }
diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c
index fd3d05a..d267b7a 100644
--- a/drivers/ide/ide-floppy_ioctl.c
+++ b/drivers/ide/ide-floppy_ioctl.c
@@ -5,7 +5,7 @@
 #include <linux/kernel.h>
 #include <linux/ide.h>
 #include <linux/cdrom.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <asm/unaligned.h>
 
@@ -32,6 +32,7 @@
  * On exit we set nformats to the number of records we've actually initialized.
  */
 
+static DEFINE_MUTEX(ide_floppy_ioctl_mutex);
 static int ide_floppy_get_format_capacities(ide_drive_t *drive,
 					    struct ide_atapi_pc *pc,
 					    int __user *arg)
@@ -276,7 +277,7 @@
 	void __user *argp = (void __user *)arg;
 	int err;
 
-	lock_kernel();
+	mutex_lock(&ide_floppy_ioctl_mutex);
 	if (cmd == CDROMEJECT || cmd == CDROM_LOCKDOOR) {
 		err = ide_floppy_lockdoor(drive, &pc, arg, cmd);
 		goto out;
@@ -298,6 +299,6 @@
 		err = generic_ide_ioctl(drive, bdev, cmd, arg);
 
 out:
-	unlock_kernel();
+	mutex_unlock(&ide_floppy_ioctl_mutex);
 	return err;
 }
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index 70aeeb1..35c4b43 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -1,4 +1,3 @@
-#include <linux/smp_lock.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -23,6 +22,7 @@
 #define IDE_GD_VERSION	"1.18"
 
 /* module parameters */
+static DEFINE_MUTEX(ide_gd_mutex);
 static unsigned long debug_mask;
 module_param(debug_mask, ulong, 0644);
 
@@ -242,9 +242,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ide_gd_mutex);
 	ret = ide_gd_open(bdev, mode);
-	unlock_kernel();
+	mutex_unlock(&ide_gd_mutex);
 
 	return ret;
 }
@@ -257,7 +257,7 @@
 
 	ide_debug_log(IDE_DBG_FUNC, "enter");
 
-	lock_kernel();
+	mutex_lock(&ide_gd_mutex);
 	if (idkp->openers == 1)
 		drive->disk_ops->flush(drive);
 
@@ -269,7 +269,7 @@
 	idkp->openers--;
 
 	ide_disk_put(idkp);
-	unlock_kernel();
+	mutex_unlock(&ide_gd_mutex);
 
 	return 0;
 }
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index a381be8..999dac0 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -441,19 +441,6 @@
 	struct request	*rq = NULL;
 	ide_startstop_t	startstop;
 
-	/*
-	 * drive is doing pre-flush, ordered write, post-flush sequence. even
-	 * though that is 3 requests, it must be seen as a single transaction.
-	 * we must not preempt this drive until that is complete
-	 */
-	if (blk_queue_flushing(q))
-		/*
-		 * small race where queue could get replugged during
-		 * the 3-request flush cycle, just yank the plug since
-		 * we want it to finish asap
-		 */
-		blk_remove_plug(q);
-
 	spin_unlock_irq(q->queue_lock);
 
 	/* HLD do_request() callback might sleep, make sure it's okay */
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 6d622cb..7ecb1ad 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -32,11 +32,9 @@
 #include <linux/errno.h>
 #include <linux/genhd.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/ide.h>
-#include <linux/smp_lock.h>
 #include <linux/completion.h>
 #include <linux/bitops.h>
 #include <linux/mutex.h>
@@ -220,6 +218,7 @@
 	char write_prot;
 } idetape_tape_t;
 
+static DEFINE_MUTEX(ide_tape_mutex);
 static DEFINE_MUTEX(idetape_ref_mutex);
 
 static DEFINE_MUTEX(idetape_chrdev_mutex);
@@ -1426,9 +1425,9 @@
 				unsigned int cmd, unsigned long arg)
 {
 	long ret;
-	lock_kernel();
+	mutex_lock(&ide_tape_mutex);
 	ret = do_idetape_chrdev_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ide_tape_mutex);
 	return ret;
 }
 
@@ -1903,15 +1902,16 @@
 	.unlocked_ioctl	= idetape_chrdev_ioctl,
 	.open		= idetape_chrdev_open,
 	.release	= idetape_chrdev_release,
+	.llseek		= noop_llseek,
 };
 
 static int idetape_open(struct block_device *bdev, fmode_t mode)
 {
 	struct ide_tape_obj *tape;
 
-	lock_kernel();
+	mutex_lock(&ide_tape_mutex);
 	tape = ide_tape_get(bdev->bd_disk, false, 0);
-	unlock_kernel();
+	mutex_unlock(&ide_tape_mutex);
 
 	if (!tape)
 		return -ENXIO;
@@ -1923,9 +1923,9 @@
 {
 	struct ide_tape_obj *tape = ide_drv_g(disk, ide_tape_obj);
 
-	lock_kernel();
+	mutex_lock(&ide_tape_mutex);
 	ide_tape_put(tape);
-	unlock_kernel();
+	mutex_unlock(&ide_tape_mutex);
 
 	return 0;
 }
@@ -1937,11 +1937,11 @@
 	ide_drive_t *drive = tape->drive;
 	int err;
 
-	lock_kernel();
+	mutex_lock(&ide_tape_mutex);
 	err = generic_ide_ioctl(drive, bdev, cmd, arg);
 	if (err == -EINVAL)
 		err = idetape_blkdev_ioctl(drive, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ide_tape_mutex);
 
 	return err;
 }
diff --git a/drivers/idle/i7300_idle.c b/drivers/idle/i7300_idle.c
index 15341fc..c976285 100644
--- a/drivers/idle/i7300_idle.c
+++ b/drivers/idle/i7300_idle.c
@@ -536,6 +536,7 @@
 static const struct file_operations idle_fops = {
 	.open	= stats_open_generic,
 	.read	= stats_read_ul,
+	.llseek = default_llseek,
 };
 
 struct debugfs_file_info {
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index c37ef64..cb3ccf3 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -59,18 +59,11 @@
 #include <linux/hrtimer.h>	/* ktime_get_real() */
 #include <trace/events/power.h>
 #include <linux/sched.h>
+#include <asm/mwait.h>
 
 #define INTEL_IDLE_VERSION "0.4"
 #define PREFIX "intel_idle: "
 
-#define MWAIT_SUBSTATE_MASK	(0xf)
-#define MWAIT_CSTATE_MASK	(0xf)
-#define MWAIT_SUBSTATE_SIZE	(4)
-#define MWAIT_MAX_NUM_CSTATES	8
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK	(0x2)
-
 static struct cpuidle_driver intel_idle_driver = {
 	.name = "intel_idle",
 	.owner = THIS_MODULE,
diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c
index d4ce8b6..daef61d 100644
--- a/drivers/infiniband/hw/ipath/ipath_diag.c
+++ b/drivers/infiniband/hw/ipath/ipath_diag.c
@@ -65,7 +65,8 @@
 	.write = ipath_diag_write,
 	.read = ipath_diag_read,
 	.open = ipath_diag_open,
-	.release = ipath_diag_release
+	.release = ipath_diag_release,
+	.llseek = default_llseek,
 };
 
 static ssize_t ipath_diagpkt_write(struct file *fp,
@@ -75,6 +76,7 @@
 static const struct file_operations diagpkt_file_ops = {
 	.owner = THIS_MODULE,
 	.write = ipath_diagpkt_write,
+	.llseek = noop_llseek,
 };
 
 static atomic_t diagpkt_count = ATOMIC_INIT(0);
diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c
index 65eb892..6078992 100644
--- a/drivers/infiniband/hw/ipath/ipath_file_ops.c
+++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c
@@ -63,7 +63,8 @@
 	.open = ipath_open,
 	.release = ipath_close,
 	.poll = ipath_poll,
-	.mmap = ipath_mmap
+	.mmap = ipath_mmap,
+	.llseek = noop_llseek,
 };
 
 /*
diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c
index 2fca708..d13e726 100644
--- a/drivers/infiniband/hw/ipath/ipath_fs.c
+++ b/drivers/infiniband/hw/ipath/ipath_fs.c
@@ -103,6 +103,7 @@
 
 static const struct file_operations atomic_stats_ops = {
 	.read = atomic_stats_read,
+	.llseek = default_llseek,
 };
 
 static ssize_t atomic_counters_read(struct file *file, char __user *buf,
@@ -120,6 +121,7 @@
 
 static const struct file_operations atomic_counters_ops = {
 	.read = atomic_counters_read,
+	.llseek = default_llseek,
 };
 
 static ssize_t flash_read(struct file *file, char __user *buf,
@@ -224,6 +226,7 @@
 static const struct file_operations flash_ops = {
 	.read = flash_read,
 	.write = flash_write,
+	.llseek = default_llseek,
 };
 
 static int create_device_files(struct super_block *sb,
diff --git a/drivers/infiniband/hw/qib/qib_diag.c b/drivers/infiniband/hw/qib/qib_diag.c
index 05dcf0d..204c4dd 100644
--- a/drivers/infiniband/hw/qib/qib_diag.c
+++ b/drivers/infiniband/hw/qib/qib_diag.c
@@ -136,7 +136,8 @@
 	.write = qib_diag_write,
 	.read = qib_diag_read,
 	.open = qib_diag_open,
-	.release = qib_diag_release
+	.release = qib_diag_release,
+	.llseek = default_llseek,
 };
 
 static atomic_t diagpkt_count = ATOMIC_INIT(0);
@@ -149,6 +150,7 @@
 static const struct file_operations diagpkt_file_ops = {
 	.owner = THIS_MODULE,
 	.write = qib_diagpkt_write,
+	.llseek = noop_llseek,
 };
 
 int qib_diag_add(struct qib_devdata *dd)
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 6b11645..aa2be21 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -63,7 +63,8 @@
 	.open = qib_open,
 	.release = qib_close,
 	.poll = qib_poll,
-	.mmap = qib_mmapf
+	.mmap = qib_mmapf,
+	.llseek = noop_llseek,
 };
 
 /*
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index 9f989c0..a0e6613 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -367,6 +367,7 @@
 static const struct file_operations flash_ops = {
 	.read = flash_read,
 	.write = flash_write,
+	.llseek = default_llseek,
 };
 
 static int add_cntr_files(struct super_block *sb, struct qib_devdata *dd)
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index 9ddafc3..535fea4 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -28,7 +28,7 @@
 	int minor;
 	struct input_handle handle;
 	wait_queue_head_t wait;
-	struct evdev_client *grab;
+	struct evdev_client __rcu *grab;
 	struct list_head client_list;
 	spinlock_t client_lock; /* protects client_list */
 	struct mutex mutex;
@@ -767,7 +767,8 @@
 	.compat_ioctl	= evdev_ioctl_compat,
 #endif
 	.fasync		= evdev_fasync,
-	.flush		= evdev_flush
+	.flush		= evdev_flush,
+	.llseek		= no_llseek,
 };
 
 static int evdev_install_chrdev(struct evdev *evdev)
diff --git a/drivers/input/input.c b/drivers/input/input.c
index ab69820..7919c25 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -2047,6 +2047,7 @@
 static const struct file_operations input_fops = {
 	.owner = THIS_MODULE,
 	.open = input_open_file,
+	.llseek = noop_llseek,
 };
 
 static int __init input_init(void)
diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index 22239e9..9d424ceb 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -739,6 +739,7 @@
 	.compat_ioctl	= joydev_compat_ioctl,
 #endif
 	.fasync		= joydev_fasync,
+	.llseek		= no_llseek,
 };
 
 static int joydev_install_chrdev(struct joydev *joydev)
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 9cc488d2..aa037fe 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -338,7 +338,7 @@
 
 config KEYBOARD_PXA27x
 	tristate "PXA27x/PXA3xx keypad support"
-	depends on PXA27x || PXA3xx
+	depends on PXA27x || PXA3xx || ARCH_MMP
 	help
 	  Enable support for PXA27x/PXA3xx keypad controller.
 
diff --git a/drivers/input/keyboard/pxa27x_keypad.c b/drivers/input/keyboard/pxa27x_keypad.c
index f32404f..4b0ec35 100644
--- a/drivers/input/keyboard/pxa27x_keypad.c
+++ b/drivers/input/keyboard/pxa27x_keypad.c
@@ -32,7 +32,7 @@
 #include <asm/mach/map.h>
 
 #include <mach/hardware.h>
-#include <mach/pxa27x_keypad.h>
+#include <plat/pxa27x_keypad.h>
 /*
  * Keypad Controller registers
  */
@@ -330,11 +330,21 @@
 	keypad->direct_key_state = new_state;
 }
 
+static void clear_wakeup_event(struct pxa27x_keypad *keypad)
+{
+	struct pxa27x_keypad_platform_data *pdata = keypad->pdata;
+
+	if (pdata->clear_wakeup_event)
+		(pdata->clear_wakeup_event)();
+}
+
 static irqreturn_t pxa27x_keypad_irq_handler(int irq, void *dev_id)
 {
 	struct pxa27x_keypad *keypad = dev_id;
 	unsigned long kpc = keypad_readl(KPC);
 
+	clear_wakeup_event(keypad);
+
 	if (kpc & KPC_DI)
 		pxa27x_keypad_scan_direct(keypad);
 
diff --git a/drivers/input/misc/hp_sdc_rtc.c b/drivers/input/misc/hp_sdc_rtc.c
index c190664..0b4f542 100644
--- a/drivers/input/misc/hp_sdc_rtc.c
+++ b/drivers/input/misc/hp_sdc_rtc.c
@@ -43,7 +43,7 @@
 #include <linux/proc_fs.h>
 #include <linux/poll.h>
 #include <linux/rtc.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/semaphore.h>
 
 MODULE_AUTHOR("Brian S. Julin <bri@calyx.com>");
@@ -52,6 +52,7 @@
 
 #define RTC_VERSION "1.10d"
 
+static DEFINE_MUTEX(hp_sdc_rtc_mutex);
 static unsigned long epoch = 2000;
 
 static struct semaphore i8042tregs;
@@ -104,7 +105,7 @@
 	t.endidx =		91;
 	t.seq =			tseq;
 	t.act.semaphore =	&tsem;
-	init_MUTEX_LOCKED(&tsem);
+	sema_init(&tsem, 0);
 	
 	if (hp_sdc_enqueue_transaction(&t)) return -1;
 	
@@ -665,9 +666,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&hp_sdc_rtc_mutex);
 	ret = hp_sdc_rtc_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&hp_sdc_rtc_mutex);
 
 	return ret;
 }
@@ -698,7 +699,7 @@
 		return -ENODEV;
 #endif
 
-	init_MUTEX(&i8042tregs);
+	sema_init(&i8042tregs, 1);
 
 	if ((ret = hp_sdc_request_timer_irq(&hp_sdc_rtc_isr)))
 		return ret;
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 3606985..b941078 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -811,6 +811,7 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= uinput_compat_ioctl,
 #endif
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice uinput_misc = {
diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c
index d528a2d..31ec726 100644
--- a/drivers/input/mousedev.c
+++ b/drivers/input/mousedev.c
@@ -792,6 +792,7 @@
 	.open =		mousedev_open,
 	.release =	mousedev_release,
 	.fasync =	mousedev_fasync,
+	.llseek = noop_llseek,
 };
 
 static int mousedev_install_chrdev(struct mousedev *mousedev)
diff --git a/drivers/input/serio/hil_mlc.c b/drivers/input/serio/hil_mlc.c
index c92f4ed..e5624d8 100644
--- a/drivers/input/serio/hil_mlc.c
+++ b/drivers/input/serio/hil_mlc.c
@@ -915,15 +915,15 @@
 	mlc->ostarted = 0;
 
 	rwlock_init(&mlc->lock);
-	init_MUTEX(&mlc->osem);
+	sema_init(&mlc->osem, 1);
 
-	init_MUTEX(&mlc->isem);
+	sema_init(&mlc->isem, 1);
 	mlc->icount = -1;
 	mlc->imatch = 0;
 
 	mlc->opercnt = 0;
 
-	init_MUTEX_LOCKED(&(mlc->csem));
+	sema_init(&(mlc->csem), 0);
 
 	hil_mlc_clear_di_scratch(mlc);
 	hil_mlc_clear_di_map(mlc, 0);
diff --git a/drivers/input/serio/hp_sdc.c b/drivers/input/serio/hp_sdc.c
index bcc2d30..8c0b51c 100644
--- a/drivers/input/serio/hp_sdc.c
+++ b/drivers/input/serio/hp_sdc.c
@@ -905,7 +905,7 @@
 	ts_sync[1]	= 0x0f;
 	ts_sync[2] = ts_sync[3]	= ts_sync[4] = ts_sync[5] = 0;
 	t_sync.act.semaphore = &s_sync;
-	init_MUTEX_LOCKED(&s_sync);
+	sema_init(&s_sync, 0);
 	hp_sdc_enqueue_transaction(&t_sync);
 	down(&s_sync); /* Wait for t_sync to complete */
 
@@ -1039,7 +1039,7 @@
 		return hp_sdc.dev_err;
 	}
 
-	init_MUTEX_LOCKED(&tq_init_sem);
+	sema_init(&tq_init_sem, 0);
 
 	tq_init.actidx		= 0;
 	tq_init.idx		= 1;
diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c
index 9986648..cd82bb1 100644
--- a/drivers/input/serio/serio_raw.c
+++ b/drivers/input/serio/serio_raw.c
@@ -243,6 +243,7 @@
 	.write =	serio_raw_write,
 	.poll =		serio_raw_poll,
 	.fasync =	serio_raw_fasync,
+	.llseek = noop_llseek,
 };
 
 
diff --git a/drivers/isdn/act2000/act2000.h b/drivers/isdn/act2000/act2000.h
index d4c5051..88c9423 100644
--- a/drivers/isdn/act2000/act2000.h
+++ b/drivers/isdn/act2000/act2000.h
@@ -141,9 +141,9 @@
 	__u8            rcvhdr[8];
 } irq_data_isa;
 
-typedef union irq_data {
+typedef union act2000_irq_data {
 	irq_data_isa isa;
-} irq_data;
+} act2000_irq_data;
 
 /*
  * Per card driver data
@@ -176,7 +176,7 @@
 	char   *status_buf_read;
 	char   *status_buf_write;
 	char   *status_buf_end;
-	irq_data idat;			/* Data used for IRQ handler        */
+	act2000_irq_data idat;		/* Data used for IRQ handler        */
 	isdn_if interface;		/* Interface to upper layer         */
 	char regname[35];		/* Name used for request_region     */
 } act2000_card;
diff --git a/drivers/isdn/hardware/avm/avm_cs.c b/drivers/isdn/hardware/avm/avm_cs.c
index 09b1795..91f06a3 100644
--- a/drivers/isdn/hardware/avm/avm_cs.c
+++ b/drivers/isdn/hardware/avm/avm_cs.c
@@ -20,7 +20,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -39,87 +38,32 @@
 
 /*====================================================================*/
 
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card insertion
-   and ejection events.  They are invoked from the skeleton event
-   handler.
-*/
-
 static int avmcs_config(struct pcmcia_device *link);
 static void avmcs_release(struct pcmcia_device *link);
-
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static void avmcs_detach(struct pcmcia_device *p_dev);
 
-/*======================================================================
-
-    avmcs_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-    
-======================================================================*/
-
 static int avmcs_probe(struct pcmcia_device *p_dev)
 {
-
-    /* The io structure describes IO port mapping */
-    p_dev->resource[0]->end = 16;
-    p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-
     /* General socket configuration */
-    p_dev->conf.Attributes = CONF_ENABLE_IRQ;
-    p_dev->conf.IntType = INT_MEMORY_AND_IO;
-    p_dev->conf.ConfigIndex = 1;
-    p_dev->conf.Present = PRESENT_OPTION;
+    p_dev->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+    p_dev->config_index = 1;
+    p_dev->config_regs = PRESENT_OPTION;
 
     return avmcs_config(p_dev);
 } /* avmcs_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
 
 static void avmcs_detach(struct pcmcia_device *link)
 {
 	avmcs_release(link);
 } /* avmcs_detach */
 
-/*======================================================================
-
-    avmcs_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ethernet device available to the system.
-    
-======================================================================*/
-
-static int avmcs_configcheck(struct pcmcia_device *p_dev,
-			     cistpl_cftable_entry_t *cf,
-			     cistpl_cftable_entry_t *dflt,
-			     unsigned int vcc,
-			     void *priv_data)
+static int avmcs_configcheck(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cf->io.nwin <= 0)
-		return -ENODEV;
+	p_dev->resource[0]->end = 16;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
 
-	p_dev->resource[0]->start = cf->io.win[0].base;
-	p_dev->resource[0]->end = cf->io.win[0].len;
 	return pcmcia_request_io(p_dev);
 }
 
@@ -150,7 +94,7 @@
 	/*
          * configure the PCMCIA socket
 	  */
-	i = pcmcia_request_configuration(link, &link->conf);
+	i = pcmcia_enable_device(link);
 	if (i != 0) {
 	    pcmcia_disable_device(link);
 	    break;
@@ -197,13 +141,6 @@
 
 } /* avmcs_config */
 
-/*======================================================================
-
-    After a card is removed, avmcs_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-    
-======================================================================*/
 
 static void avmcs_release(struct pcmcia_device *link)
 {
@@ -222,9 +159,7 @@
 
 static struct pcmcia_driver avmcs_driver = {
 	.owner	= THIS_MODULE,
-	.drv	= {
-		.name	= "avm_cs",
-	},
+	.name		= "avm_cs",
 	.probe = avmcs_probe,
 	.remove	= avmcs_detach,
 	.id_table = avmcs_ids,
diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c
index ed9c555..f332b60 100644
--- a/drivers/isdn/hardware/eicon/divasmain.c
+++ b/drivers/isdn/hardware/eicon/divasmain.c
@@ -15,7 +15,6 @@
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/ioport.h>
-#include <linux/workqueue.h>
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
@@ -546,7 +545,6 @@
 		void *mem;
 
 		tasklet_kill(&pdpc->divas_task);
-		flush_scheduled_work();
 		mem = psoft_isr->object;
 		psoft_isr->object = NULL;
 		diva_os_free(0, mem);
diff --git a/drivers/isdn/hisax/avma1_cs.c b/drivers/isdn/hisax/avma1_cs.c
index 94263c2..ac4dd78 100644
--- a/drivers/isdn/hisax/avma1_cs.c
+++ b/drivers/isdn/hisax/avma1_cs.c
@@ -20,7 +20,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 #include "hisax_cfg.h"
@@ -40,67 +39,22 @@
 
 /*====================================================================*/
 
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card insertion
-   and ejection events.  They are invoked from the skeleton event
-   handler.
-*/
-
 static int avma1cs_config(struct pcmcia_device *link) __devinit ;
 static void avma1cs_release(struct pcmcia_device *link);
-
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static void avma1cs_detach(struct pcmcia_device *p_dev) __devexit ;
 
-
-/*======================================================================
-
-    avma1cs_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-    
-======================================================================*/
-
 static int __devinit avma1cs_probe(struct pcmcia_device *p_dev)
 {
     dev_dbg(&p_dev->dev, "avma1cs_attach()\n");
 
-    /* The io structure describes IO port mapping */
-    p_dev->resource[0]->end = 16;
-    p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-    p_dev->resource[1]->end = 16;
-    p_dev->resource[1]->flags |= IO_DATA_PATH_WIDTH_16;
-
     /* General socket configuration */
-    p_dev->conf.Attributes = CONF_ENABLE_IRQ;
-    p_dev->conf.IntType = INT_MEMORY_AND_IO;
-    p_dev->conf.ConfigIndex = 1;
-    p_dev->conf.Present = PRESENT_OPTION;
+    p_dev->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+    p_dev->config_index = 1;
+    p_dev->config_regs = PRESENT_OPTION;
 
     return avma1cs_config(p_dev);
 } /* avma1cs_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void __devexit avma1cs_detach(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "avma1cs_detach(0x%p)\n", link);
@@ -108,26 +62,13 @@
 	kfree(link->priv);
 } /* avma1cs_detach */
 
-/*======================================================================
-
-    avma1cs_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ethernet device available to the system.
-    
-======================================================================*/
-
-static int avma1cs_configcheck(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cf,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int avma1cs_configcheck(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cf->io.nwin <= 0)
-		return -ENODEV;
-
-	p_dev->resource[0]->start = cf->io.win[0].base;
-	p_dev->resource[0]->end = cf->io.win[0].len;
+	p_dev->resource[0]->end = 16;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
 	p_dev->io_lines = 5;
+
 	return pcmcia_request_io(p_dev);
 }
 
@@ -161,7 +102,7 @@
 	/*
 	 * configure the PCMCIA socket
 	 */
-	i = pcmcia_request_configuration(link, &link->conf);
+	i = pcmcia_enable_device(link);
 	if (i != 0) {
 	    pcmcia_disable_device(link);
 	    break;
@@ -175,9 +116,6 @@
 	return -ENODEV;
     }
 
-    printk(KERN_NOTICE "avma1_cs: checking at i/o %#x, irq %d\n",
-		(unsigned int) link->resource[0]->start, link->irq);
-
     icard.para[0] = link->irq;
     icard.para[1] = link->resource[0]->start;
     icard.protocol = isdnprot;
@@ -196,14 +134,6 @@
     return 0;
 } /* avma1cs_config */
 
-/*======================================================================
-
-    After a card is removed, avma1cs_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-    
-======================================================================*/
-
 static void avma1cs_release(struct pcmcia_device *link)
 {
 	unsigned long minor = (unsigned long) link->priv;
@@ -216,7 +146,6 @@
 	pcmcia_disable_device(link);
 } /* avma1cs_release */
 
-
 static struct pcmcia_device_id avma1cs_ids[] = {
 	PCMCIA_DEVICE_PROD_ID12("AVM", "ISDN A", 0x95d42008, 0xadc9d4bb),
 	PCMCIA_DEVICE_PROD_ID12("ISDN", "CARD", 0x8d9761c8, 0x01c5aa7b),
@@ -226,19 +155,15 @@
 
 static struct pcmcia_driver avma1cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "avma1_cs",
-	},
+	.name		= "avma1_cs",
 	.probe		= avma1cs_probe,
 	.remove		= __devexit_p(avma1cs_detach),
 	.id_table	= avma1cs_ids,
 };
 
-/*====================================================================*/
-
 static int __init init_avma1_cs(void)
 {
-	return(pcmcia_register_driver(&avma1cs_driver));
+	return pcmcia_register_driver(&avma1cs_driver);
 }
 
 static void __exit exit_avma1_cs(void)
diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c
index 6f9afcd..b133378 100644
--- a/drivers/isdn/hisax/config.c
+++ b/drivers/isdn/hisax/config.c
@@ -801,6 +801,16 @@
 	ll_unload(csta);
 }
 
+static irqreturn_t card_irq(int intno, void *dev_id)
+{
+	struct IsdnCardState *cs = dev_id;
+	irqreturn_t ret = cs->irq_func(intno, cs);
+
+	if (ret == IRQ_HANDLED)
+		cs->irq_cnt++;
+	return ret;
+}
+
 static int init_card(struct IsdnCardState *cs)
 {
 	int 	irq_cnt, cnt = 3, ret;
@@ -809,10 +819,10 @@
 		ret = cs->cardmsg(cs, CARD_INIT, NULL);
 		return(ret);
 	}
-	irq_cnt = kstat_irqs(cs->irq);
+	irq_cnt = cs->irq_cnt = 0;
 	printk(KERN_INFO "%s: IRQ %d count %d\n", CardType[cs->typ],
 	       cs->irq, irq_cnt);
-	if (request_irq(cs->irq, cs->irq_func, cs->irq_flags, "HiSax", cs)) {
+	if (request_irq(cs->irq, card_irq, cs->irq_flags, "HiSax", cs)) {
 		printk(KERN_WARNING "HiSax: couldn't get interrupt %d\n",
 		       cs->irq);
 		return 1;
@@ -822,8 +832,8 @@
 		/* Timeout 10ms */
 		msleep(10);
 		printk(KERN_INFO "%s: IRQ %d count %d\n",
-		       CardType[cs->typ], cs->irq, kstat_irqs(cs->irq));
-		if (kstat_irqs(cs->irq) == irq_cnt) {
+		       CardType[cs->typ], cs->irq, cs->irq_cnt);
+		if (cs->irq_cnt == irq_cnt) {
 			printk(KERN_WARNING
 			       "%s: IRQ(%d) getting no interrupts during init %d\n",
 			       CardType[cs->typ], cs->irq, 4 - cnt);
diff --git a/drivers/isdn/hisax/elsa_cs.c b/drivers/isdn/hisax/elsa_cs.c
index b3c08aa..496d477 100644
--- a/drivers/isdn/hisax/elsa_cs.c
+++ b/drivers/isdn/hisax/elsa_cs.c
@@ -46,7 +46,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -64,26 +63,8 @@
 static int protocol = 2;        /* EURO-ISDN Default */
 module_param(protocol, int, 0);
 
-/*====================================================================*/
-
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card insertion
-   and ejection events.  They are invoked from the elsa_cs event
-   handler.
-*/
-
 static int elsa_cs_config(struct pcmcia_device *link) __devinit ;
 static void elsa_cs_release(struct pcmcia_device *link);
-
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static void elsa_cs_detach(struct pcmcia_device *p_dev) __devexit;
 
 typedef struct local_info_t {
@@ -92,18 +73,6 @@
     int			cardnr;
 } local_info_t;
 
-/*======================================================================
-
-    elsa_cs_attach() creates an "instance" of the driver, allocatingx
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-
-======================================================================*/
-
 static int __devinit elsa_cs_probe(struct pcmcia_device *link)
 {
     local_info_t *local;
@@ -119,31 +88,9 @@
 
     local->cardnr = -1;
 
-    /*
-      General socket configuration defaults can go here.  In this
-      client, we assume very little, and rely on the CIS for almost
-      everything.  In most clients, many details (i.e., number, sizes,
-      and attributes of IO windows) are fixed by the nature of the
-      device, and can be hard-wired here.
-    */
-    link->resource[0]->end = 8;
-    link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-
     return elsa_cs_config(link);
 } /* elsa_cs_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void __devexit elsa_cs_detach(struct pcmcia_device *link)
 {
 	local_info_t *info = link->priv;
@@ -156,27 +103,17 @@
 	kfree(info);
 } /* elsa_cs_detach */
 
-/*======================================================================
-
-    elsa_cs_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-
-======================================================================*/
-
-static int elsa_cs_configcheck(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cf,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int elsa_cs_configcheck(struct pcmcia_device *p_dev, void *priv_data)
 {
 	int j;
 
 	p_dev->io_lines = 3;
+	p_dev->resource[0]->end = 8;
+	p_dev->resource[0]->flags &= IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 
-	if ((cf->io.nwin > 0) && cf->io.win[0].base) {
+	if ((p_dev->resource[0]->end) && p_dev->resource[0]->start) {
 		printk(KERN_INFO "(elsa_cs: looks like the 96 model)\n");
-		p_dev->resource[0]->start = cf->io.win[0].base;
 		if (!pcmcia_request_io(p_dev))
 			return 0;
 	} else {
@@ -199,6 +136,8 @@
     dev_dbg(&link->dev, "elsa_config(0x%p)\n", link);
     dev = link->priv;
 
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+
     i = pcmcia_loop_config(link, elsa_cs_configcheck, NULL);
     if (i != 0)
 	goto failed;
@@ -206,21 +145,10 @@
     if (!link->irq)
 	goto failed;
 
-    i = pcmcia_request_configuration(link, &link->conf);
+    i = pcmcia_enable_device(link);
     if (i != 0)
 	goto failed;
 
-    /* Finally, report what we've done */
-    dev_info(&link->dev, "index 0x%02x: ",
-	    link->conf.ConfigIndex);
-    if (link->conf.Attributes & CONF_ENABLE_IRQ)
-	printk(", irq %d", link->irq);
-    if (link->resource[0])
-	printk(" & %pR", link->resource[0]);
-    if (link->resource[1])
-	printk(" & %pR", link->resource[1]);
-    printk("\n");
-
     icard.para[0] = link->irq;
     icard.para[1] = link->resource[0]->start;
     icard.protocol = protocol;
@@ -240,14 +168,6 @@
     return -ENODEV;
 } /* elsa_cs_config */
 
-/*======================================================================
-
-    After a card is removed, elsa_cs_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void elsa_cs_release(struct pcmcia_device *link)
 {
     local_info_t *local = link->priv;
@@ -291,9 +211,7 @@
 
 static struct pcmcia_driver elsa_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "elsa_cs",
-	},
+	.name		= "elsa_cs",
 	.probe		= elsa_cs_probe,
 	.remove		= __devexit_p(elsa_cs_detach),
 	.id_table	= elsa_ids,
diff --git a/drivers/isdn/hisax/hisax.h b/drivers/isdn/hisax/hisax.h
index 832a878..32ab392 100644
--- a/drivers/isdn/hisax/hisax.h
+++ b/drivers/isdn/hisax/hisax.h
@@ -959,6 +959,7 @@
 	u_long		event;
 	struct work_struct tqueue;
 	struct timer_list dbusytimer;
+	unsigned int	irq_cnt;
 #ifdef ERROR_STATISTIC
 	int		err_crc;
 	int		err_tx;
diff --git a/drivers/isdn/hisax/sedlbauer_cs.c b/drivers/isdn/hisax/sedlbauer_cs.c
index a024192..360204b 100644
--- a/drivers/isdn/hisax/sedlbauer_cs.c
+++ b/drivers/isdn/hisax/sedlbauer_cs.c
@@ -46,7 +46,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -64,26 +63,9 @@
 static int protocol = 2;        /* EURO-ISDN Default */
 module_param(protocol, int, 0);
 
-/*====================================================================*/
-
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card
-   insertion and ejection events.  They are invoked from the sedlbauer
-   event handler. 
-*/
-
 static int sedlbauer_config(struct pcmcia_device *link) __devinit ;
 static void sedlbauer_release(struct pcmcia_device *link);
 
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static void sedlbauer_detach(struct pcmcia_device *p_dev) __devexit;
 
 typedef struct local_info_t {
@@ -92,18 +74,6 @@
     int			cardnr;
 } local_info_t;
 
-/*======================================================================
-
-    sedlbauer_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-    
-======================================================================*/
-
 static int __devinit sedlbauer_probe(struct pcmcia_device *link)
 {
     local_info_t *local;
@@ -118,35 +88,9 @@
     local->p_dev = link;
     link->priv = local;
 
-    /*
-      General socket configuration defaults can go here.  In this
-      client, we assume very little, and rely on the CIS for almost
-      everything.  In most clients, many details (i.e., number, sizes,
-      and attributes of IO windows) are fixed by the nature of the
-      device, and can be hard-wired here.
-    */
-
-    /* from old sedl_cs 
-    */
-    /* The io structure describes IO port mapping */
-    link->resource[0]->end = 8;
-    link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-
-    link->conf.Attributes = 0;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-
     return sedlbauer_config(link);
 } /* sedlbauer_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void __devexit sedlbauer_detach(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "sedlbauer_detach(0x%p)\n", link);
@@ -158,70 +102,15 @@
 	kfree(link->priv);
 } /* sedlbauer_detach */
 
-/*======================================================================
-
-    sedlbauer_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-    
-======================================================================*/
-static int sedlbauer_config_check(struct pcmcia_device *p_dev,
-				  cistpl_cftable_entry_t *cfg,
-				  cistpl_cftable_entry_t *dflt,
-				  unsigned int vcc,
-				  void *priv_data)
+static int sedlbauer_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Does this card need audio output? */
-	if (cfg->flags & CISTPL_CFTABLE_AUDIO) {
-		p_dev->conf.Attributes |= CONF_ENABLE_SPKR;
-		p_dev->conf.Status = CCSR_AUDIO_ENA;
-	}
-
-	/* Use power settings for Vcc and Vpp if present */
-	/*  Note that the CIS values need to be rescaled */
-	if (cfg->vcc.present & (1<<CISTPL_POWER_VNOM)) {
-		if (vcc != cfg->vcc.param[CISTPL_POWER_VNOM]/10000)
-			return -ENODEV;
-	} else if (dflt->vcc.present & (1<<CISTPL_POWER_VNOM)) {
-		if (vcc != dflt->vcc.param[CISTPL_POWER_VNOM]/10000)
-			return -ENODEV;
-	}
-
-	if (cfg->vpp1.present & (1<<CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = cfg->vpp1.param[CISTPL_POWER_VNOM]/10000;
-	else if (dflt->vpp1.present & (1<<CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = dflt->vpp1.param[CISTPL_POWER_VNOM]/10000;
-
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-					pcmcia_io_cfg_data_width(io->flags);
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-		/* This reserves IO space but doesn't actually enable it */
-		p_dev->io_lines = 3;
-		if (pcmcia_request_io(p_dev) != 0)
-			return -ENODEV;
-	}
-
-	return 0;
+	p_dev->io_lines = 3;
+	return pcmcia_request_io(p_dev);
 }
 
-
-
 static int __devinit sedlbauer_config(struct pcmcia_device *link)
 {
     int ret;
@@ -229,44 +118,17 @@
 
     dev_dbg(&link->dev, "sedlbauer_config(0x%p)\n", link);
 
-    /*
-      In this loop, we scan the CIS for configuration table entries,
-      each of which describes a valid card configuration, including
-      voltage, IO window, memory window, and interrupt settings.
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_CHECK_VCC |
+	    CONF_AUTO_SET_VPP | CONF_AUTO_AUDIO | CONF_AUTO_SET_IO;
 
-      We make no assumptions about the card to be configured: we use
-      just the information available in the CIS.  In an ideal world,
-      this would work for any PCMCIA card, but it requires a complete
-      and accurate CIS.  In practice, a driver usually "knows" most of
-      these things without consulting the CIS, and most client drivers
-      will only use the CIS to fill in implementation-defined details.
-    */
     ret = pcmcia_loop_config(link, sedlbauer_config_check, NULL);
     if (ret)
 	    goto failed;
 
-    /*
-       This actually configures the PCMCIA socket -- setting up
-       the I/O windows and the interrupt mapping, and putting the
-       card and host interface into "Memory and IO" mode.
-    */
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
-    /* Finally, report what we've done */
-    dev_info(&link->dev, "index 0x%02x:",
-	   link->conf.ConfigIndex);
-    if (link->conf.Vpp)
-	printk(", Vpp %d.%d", link->conf.Vpp/10, link->conf.Vpp%10);
-    if (link->conf.Attributes & CONF_ENABLE_IRQ)
-	printk(", irq %d", link->irq);
-    if (link->resource[0])
-	printk(" & %pR", link->resource[0]);
-    if (link->resource[1])
-	printk(" & %pR", link->resource[1]);
-    printk("\n");
-
     icard.para[0] = link->irq;
     icard.para[1] = link->resource[0]->start;
     icard.protocol = protocol;
@@ -290,14 +152,6 @@
 
 } /* sedlbauer_config */
 
-/*======================================================================
-
-    After a card is removed, sedlbauer_release() will unregister the
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-    
-======================================================================*/
-
 static void sedlbauer_release(struct pcmcia_device *link)
 {
     local_info_t *local = link->priv;
@@ -346,9 +200,7 @@
 
 static struct pcmcia_driver sedlbauer_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "sedlbauer_cs",
-	},
+	.name		= "sedlbauer_cs",
 	.probe		= sedlbauer_probe,
 	.remove		= __devexit_p(sedlbauer_detach),
 	.id_table	= sedlbauer_ids,
diff --git a/drivers/isdn/hisax/teles_cs.c b/drivers/isdn/hisax/teles_cs.c
index 7296102..282a446 100644
--- a/drivers/isdn/hisax/teles_cs.c
+++ b/drivers/isdn/hisax/teles_cs.c
@@ -27,7 +27,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -45,26 +44,8 @@
 static int protocol = 2;        /* EURO-ISDN Default */
 module_param(protocol, int, 0);
 
-/*====================================================================*/
-
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card insertion
-   and ejection events.  They are invoked from the teles_cs event
-   handler.
-*/
-
 static int teles_cs_config(struct pcmcia_device *link) __devinit ;
 static void teles_cs_release(struct pcmcia_device *link);
-
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static void teles_detach(struct pcmcia_device *p_dev) __devexit ;
 
 typedef struct local_info_t {
@@ -73,18 +54,6 @@
     int			cardnr;
 } local_info_t;
 
-/*======================================================================
-
-    teles_attach() creates an "instance" of the driver, allocatingx
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-
-======================================================================*/
-
 static int __devinit teles_probe(struct pcmcia_device *link)
 {
     local_info_t *local;
@@ -99,31 +68,11 @@
     local->p_dev = link;
     link->priv = local;
 
-    /*
-      General socket configuration defaults can go here.  In this
-      client, we assume very little, and rely on the CIS for almost
-      everything.  In most clients, many details (i.e., number, sizes,
-      and attributes of IO windows) are fixed by the nature of the
-      device, and can be hard-wired here.
-    */
-    link->resource[0]->end = 96;
-    link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
 
     return teles_cs_config(link);
 } /* teles_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void __devexit teles_detach(struct pcmcia_device *link)
 {
 	local_info_t *info = link->priv;
@@ -136,27 +85,17 @@
 	kfree(info);
 } /* teles_detach */
 
-/*======================================================================
-
-    teles_cs_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-
-======================================================================*/
-
-static int teles_cs_configcheck(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cf,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
-				void *priv_data)
+static int teles_cs_configcheck(struct pcmcia_device *p_dev, void *priv_data)
 {
 	int j;
 
 	p_dev->io_lines = 5;
+	p_dev->resource[0]->end = 96;
+	p_dev->resource[0]->flags &= IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 
-	if ((cf->io.nwin > 0) && cf->io.win[0].base) {
+	if ((p_dev->resource[0]->end) && p_dev->resource[0]->start) {
 		printk(KERN_INFO "(teles_cs: looks like the 96 model)\n");
-		p_dev->resource[0]->start = cf->io.win[0].base;
 		if (!pcmcia_request_io(p_dev))
 			return 0;
 	} else {
@@ -186,21 +125,10 @@
     if (!link->irq)
         goto cs_failed;
 
-    i = pcmcia_request_configuration(link, &link->conf);
+    i = pcmcia_enable_device(link);
     if (i != 0)
       goto cs_failed;
 
-    /* Finally, report what we've done */
-    dev_info(&link->dev, "index 0x%02x:",
-	    link->conf.ConfigIndex);
-    if (link->conf.Attributes & CONF_ENABLE_IRQ)
-	    printk(", irq %d", link->irq);
-    if (link->resource[0])
-	printk(" & %pR", link->resource[0]);
-    if (link->resource[1])
-	printk(" & %pR", link->resource[1]);
-    printk("\n");
-
     icard.para[0] = link->irq;
     icard.para[1] = link->resource[0]->start;
     icard.protocol = protocol;
@@ -222,14 +150,6 @@
     return -ENODEV;
 } /* teles_cs_config */
 
-/*======================================================================
-
-    After a card is removed, teles_cs_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void teles_cs_release(struct pcmcia_device *link)
 {
     local_info_t *local = link->priv;
@@ -273,9 +193,7 @@
 
 static struct pcmcia_driver teles_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "teles_cs",
-	},
+	.name		= "teles_cs",
 	.probe		= teles_probe,
 	.remove		= __devexit_p(teles_detach),
 	.id_table       = teles_ids,
diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c
index de43c8c..859c81e 100644
--- a/drivers/isdn/mISDN/timerdev.c
+++ b/drivers/isdn/mISDN/timerdev.c
@@ -267,6 +267,7 @@
 	.unlocked_ioctl	= mISDN_ioctl,
 	.open		= mISDN_open,
 	.release	= mISDN_close,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice mISDNtimer = {
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index e411262..cc2a88d 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -304,13 +304,22 @@
 
 config LEDS_NS2
 	tristate "LED support for Network Space v2 GPIO LEDs"
-	depends on MACH_NETSPACE_V2 || MACH_INETSPACE_V2 || MACH_NETSPACE_MAX_V2
+	depends on MACH_NETSPACE_V2 || MACH_INETSPACE_V2 || MACH_NETSPACE_MAX_V2 || D2NET_V2
 	default y
 	help
 	  This option enable support for the dual-GPIO LED found on the
 	  Network Space v2 board (and parents). This include Internet Space v2,
 	  Network Space (Max) v2 and d2 Network v2 boards.
 
+config LEDS_NETXBIG
+	tristate "LED support for Big Network series LEDs"
+	depends on MACH_NET2BIG_V2 || MACH_NET5BIG_V2
+	default y
+	help
+	  This option enable support for LEDs found on the LaCie 2Big
+	  and 5Big Network v2 boards. The LEDs are wired to a CPLD and are
+	  controlled through a GPIO extension bus.
+
 config LEDS_TRIGGERS
 	bool "LED Trigger support"
 	help
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 7d6b958..9c96db4 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -38,6 +38,7 @@
 obj-$(CONFIG_LEDS_DELL_NETBOOKS)	+= dell-led.o
 obj-$(CONFIG_LEDS_MC13783)		+= leds-mc13783.o
 obj-$(CONFIG_LEDS_NS2)			+= leds-ns2.o
+obj-$(CONFIG_LEDS_NETXBIG)		+= leds-netxbig.o
 
 # LED SPI Drivers
 obj-$(CONFIG_LEDS_DAC124S085)		+= leds-dac124s085.o
diff --git a/drivers/leds/leds-netxbig.c b/drivers/leds/leds-netxbig.c
new file mode 100644
index 0000000..f2e51c1
--- /dev/null
+++ b/drivers/leds/leds-netxbig.c
@@ -0,0 +1,449 @@
+/*
+ * leds-netxbig.c - Driver for the 2Big and 5Big Network series LEDs
+ *
+ * Copyright (C) 2010 LaCie
+ *
+ * Author: Simon Guinot <sguinot@lacie.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+#include <linux/leds.h>
+#include <mach/leds-netxbig.h>
+
+/*
+ * GPIO extension bus.
+ */
+
+static DEFINE_SPINLOCK(gpio_ext_lock);
+
+static void gpio_ext_set_addr(struct netxbig_gpio_ext *gpio_ext, int addr)
+{
+	int pin;
+
+	for (pin = 0; pin < gpio_ext->num_addr; pin++)
+		gpio_set_value(gpio_ext->addr[pin], (addr >> pin) & 1);
+}
+
+static void gpio_ext_set_data(struct netxbig_gpio_ext *gpio_ext, int data)
+{
+	int pin;
+
+	for (pin = 0; pin < gpio_ext->num_data; pin++)
+		gpio_set_value(gpio_ext->data[pin], (data >> pin) & 1);
+}
+
+static void gpio_ext_enable_select(struct netxbig_gpio_ext *gpio_ext)
+{
+	/* Enable select is done on the raising edge. */
+	gpio_set_value(gpio_ext->enable, 0);
+	gpio_set_value(gpio_ext->enable, 1);
+}
+
+static void gpio_ext_set_value(struct netxbig_gpio_ext *gpio_ext,
+			       int addr, int value)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&gpio_ext_lock, flags);
+	gpio_ext_set_addr(gpio_ext, addr);
+	gpio_ext_set_data(gpio_ext, value);
+	gpio_ext_enable_select(gpio_ext);
+	spin_unlock_irqrestore(&gpio_ext_lock, flags);
+}
+
+static int __devinit gpio_ext_init(struct netxbig_gpio_ext *gpio_ext)
+{
+	int err;
+	int i;
+
+	if (unlikely(!gpio_ext))
+		return -EINVAL;
+
+	/* Configure address GPIOs. */
+	for (i = 0; i < gpio_ext->num_addr; i++) {
+		err = gpio_request(gpio_ext->addr[i], "GPIO extension addr");
+		if (err)
+			goto err_free_addr;
+		err = gpio_direction_output(gpio_ext->addr[i], 0);
+		if (err) {
+			gpio_free(gpio_ext->addr[i]);
+			goto err_free_addr;
+		}
+	}
+	/* Configure data GPIOs. */
+	for (i = 0; i < gpio_ext->num_data; i++) {
+		err = gpio_request(gpio_ext->data[i], "GPIO extension data");
+		if (err)
+			goto err_free_data;
+		err = gpio_direction_output(gpio_ext->data[i], 0);
+		if (err) {
+			gpio_free(gpio_ext->data[i]);
+			goto err_free_data;
+		}
+	}
+	/* Configure "enable select" GPIO. */
+	err = gpio_request(gpio_ext->enable, "GPIO extension enable");
+	if (err)
+		goto err_free_data;
+	err = gpio_direction_output(gpio_ext->enable, 0);
+	if (err) {
+		gpio_free(gpio_ext->enable);
+		goto err_free_data;
+	}
+
+	return 0;
+
+err_free_data:
+	for (i = i - 1; i >= 0; i--)
+		gpio_free(gpio_ext->data[i]);
+	i = gpio_ext->num_addr;
+err_free_addr:
+	for (i = i - 1; i >= 0; i--)
+		gpio_free(gpio_ext->addr[i]);
+
+	return err;
+}
+
+static void __devexit gpio_ext_free(struct netxbig_gpio_ext *gpio_ext)
+{
+	int i;
+
+	gpio_free(gpio_ext->enable);
+	for (i = gpio_ext->num_addr - 1; i >= 0; i--)
+		gpio_free(gpio_ext->addr[i]);
+	for (i = gpio_ext->num_data - 1; i >= 0; i--)
+		gpio_free(gpio_ext->data[i]);
+}
+
+/*
+ * Class LED driver.
+ */
+
+struct netxbig_led_data {
+	struct netxbig_gpio_ext	*gpio_ext;
+	struct led_classdev	cdev;
+	int			mode_addr;
+	int			*mode_val;
+	int			bright_addr;
+	int			bright_max;
+	struct			netxbig_led_timer *timer;
+	int			num_timer;
+	enum netxbig_led_mode	mode;
+	int			sata;
+	spinlock_t		lock;
+};
+
+static int netxbig_led_get_timer_mode(enum netxbig_led_mode *mode,
+				      unsigned long delay_on,
+				      unsigned long delay_off,
+				      struct netxbig_led_timer *timer,
+				      int num_timer)
+{
+	int i;
+
+	for (i = 0; i < num_timer; i++) {
+		if (timer[i].delay_on == delay_on &&
+		    timer[i].delay_off == delay_off) {
+			*mode = timer[i].mode;
+			return 0;
+		}
+	}
+	return -EINVAL;
+}
+
+static int netxbig_led_blink_set(struct led_classdev *led_cdev,
+				 unsigned long *delay_on,
+				 unsigned long *delay_off)
+{
+	struct netxbig_led_data *led_dat =
+		container_of(led_cdev, struct netxbig_led_data, cdev);
+	enum netxbig_led_mode mode;
+	int mode_val;
+	int ret;
+
+	/* Look for a LED mode with the requested timer frequency. */
+	ret = netxbig_led_get_timer_mode(&mode, *delay_on, *delay_off,
+					 led_dat->timer, led_dat->num_timer);
+	if (ret < 0)
+		return ret;
+
+	mode_val = led_dat->mode_val[mode];
+	if (mode_val == NETXBIG_LED_INVALID_MODE)
+		return -EINVAL;
+
+	spin_lock_irq(&led_dat->lock);
+
+	gpio_ext_set_value(led_dat->gpio_ext, led_dat->mode_addr, mode_val);
+	led_dat->mode = mode;
+
+	spin_unlock_irq(&led_dat->lock);
+
+	return 0;
+}
+
+static void netxbig_led_set(struct led_classdev *led_cdev,
+			    enum led_brightness value)
+{
+	struct netxbig_led_data *led_dat =
+		container_of(led_cdev, struct netxbig_led_data, cdev);
+	enum netxbig_led_mode mode;
+	int mode_val, bright_val;
+	int set_brightness = 1;
+	unsigned long flags;
+
+	spin_lock_irqsave(&led_dat->lock, flags);
+
+	if (value == LED_OFF) {
+		mode = NETXBIG_LED_OFF;
+		set_brightness = 0;
+	} else {
+		if (led_dat->sata)
+			mode = NETXBIG_LED_SATA;
+		else if (led_dat->mode == NETXBIG_LED_OFF)
+			mode = NETXBIG_LED_ON;
+		else /* Keep 'timer' mode. */
+			mode = led_dat->mode;
+	}
+	mode_val = led_dat->mode_val[mode];
+
+	gpio_ext_set_value(led_dat->gpio_ext, led_dat->mode_addr, mode_val);
+	led_dat->mode = mode;
+	/*
+	 * Note that the brightness register is shared between all the
+	 * SATA LEDs. So, change the brightness setting for a single
+	 * SATA LED will affect all the others.
+	 */
+	if (set_brightness) {
+		bright_val = DIV_ROUND_UP(value * led_dat->bright_max,
+					  LED_FULL);
+		gpio_ext_set_value(led_dat->gpio_ext,
+				   led_dat->bright_addr, bright_val);
+	}
+
+	spin_unlock_irqrestore(&led_dat->lock, flags);
+}
+
+static ssize_t netxbig_led_sata_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buff, size_t count)
+{
+	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct netxbig_led_data *led_dat =
+		container_of(led_cdev, struct netxbig_led_data, cdev);
+	unsigned long enable;
+	enum netxbig_led_mode mode;
+	int mode_val;
+	int ret;
+
+	ret = strict_strtoul(buff, 10, &enable);
+	if (ret < 0)
+		return ret;
+
+	enable = !!enable;
+
+	spin_lock_irq(&led_dat->lock);
+
+	if (led_dat->sata == enable) {
+		ret = count;
+		goto exit_unlock;
+	}
+
+	if (led_dat->mode != NETXBIG_LED_ON &&
+	    led_dat->mode != NETXBIG_LED_SATA)
+		mode = led_dat->mode; /* Keep modes 'off' and 'timer'. */
+	else if (enable)
+		mode = NETXBIG_LED_SATA;
+	else
+		mode = NETXBIG_LED_ON;
+
+	mode_val = led_dat->mode_val[mode];
+	if (mode_val == NETXBIG_LED_INVALID_MODE) {
+		ret = -EINVAL;
+		goto exit_unlock;
+	}
+
+	gpio_ext_set_value(led_dat->gpio_ext, led_dat->mode_addr, mode_val);
+	led_dat->mode = mode;
+	led_dat->sata = enable;
+
+	ret = count;
+
+exit_unlock:
+	spin_unlock_irq(&led_dat->lock);
+
+	return ret;
+}
+
+static ssize_t netxbig_led_sata_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct netxbig_led_data *led_dat =
+		container_of(led_cdev, struct netxbig_led_data, cdev);
+
+	return sprintf(buf, "%d\n", led_dat->sata);
+}
+
+static DEVICE_ATTR(sata, 0644, netxbig_led_sata_show, netxbig_led_sata_store);
+
+static void __devexit delete_netxbig_led(struct netxbig_led_data *led_dat)
+{
+	if (led_dat->mode_val[NETXBIG_LED_SATA] != NETXBIG_LED_INVALID_MODE)
+		device_remove_file(led_dat->cdev.dev, &dev_attr_sata);
+	led_classdev_unregister(&led_dat->cdev);
+}
+
+static int __devinit
+create_netxbig_led(struct platform_device *pdev,
+		   struct netxbig_led_data *led_dat,
+		   const struct netxbig_led *template)
+{
+	struct netxbig_led_platform_data *pdata = pdev->dev.platform_data;
+	int ret;
+
+	spin_lock_init(&led_dat->lock);
+	led_dat->gpio_ext = pdata->gpio_ext;
+	led_dat->cdev.name = template->name;
+	led_dat->cdev.default_trigger = template->default_trigger;
+	led_dat->cdev.blink_set = netxbig_led_blink_set;
+	led_dat->cdev.brightness_set = netxbig_led_set;
+	/*
+	 * Because the GPIO extension bus don't allow to read registers
+	 * value, there is no way to probe the LED initial state.
+	 * So, the initial sysfs LED value for the "brightness" and "sata"
+	 * attributes are inconsistent.
+	 *
+	 * Note that the initial LED state can't be reconfigured.
+	 * The reason is that the LED behaviour must stay uniform during
+	 * the whole boot process (bootloader+linux).
+	 */
+	led_dat->sata = 0;
+	led_dat->cdev.brightness = LED_OFF;
+	led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
+	led_dat->mode_addr = template->mode_addr;
+	led_dat->mode_val = template->mode_val;
+	led_dat->bright_addr = template->bright_addr;
+	led_dat->bright_max = (1 << pdata->gpio_ext->num_data) - 1;
+	led_dat->timer = pdata->timer;
+	led_dat->num_timer = pdata->num_timer;
+
+	ret = led_classdev_register(&pdev->dev, &led_dat->cdev);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * If available, expose the SATA activity blink capability through
+	 * a "sata" sysfs attribute.
+	 */
+	if (led_dat->mode_val[NETXBIG_LED_SATA] != NETXBIG_LED_INVALID_MODE) {
+		ret = device_create_file(led_dat->cdev.dev, &dev_attr_sata);
+		if (ret)
+			led_classdev_unregister(&led_dat->cdev);
+	}
+
+	return ret;
+}
+
+static int __devinit netxbig_led_probe(struct platform_device *pdev)
+{
+	struct netxbig_led_platform_data *pdata = pdev->dev.platform_data;
+	struct netxbig_led_data *leds_data;
+	int i;
+	int ret;
+
+	if (!pdata)
+		return -EINVAL;
+
+	leds_data = kzalloc(sizeof(struct netxbig_led_data) * pdata->num_leds,
+			    GFP_KERNEL);
+	if (!leds_data)
+		return -ENOMEM;
+
+	ret = gpio_ext_init(pdata->gpio_ext);
+	if (ret < 0)
+		goto err_free_data;
+
+	for (i = 0; i < pdata->num_leds; i++) {
+		ret = create_netxbig_led(pdev, &leds_data[i], &pdata->leds[i]);
+		if (ret < 0)
+			goto err_free_leds;
+	}
+
+	platform_set_drvdata(pdev, leds_data);
+
+	return 0;
+
+err_free_leds:
+	for (i = i - 1; i >= 0; i--)
+		delete_netxbig_led(&leds_data[i]);
+
+	gpio_ext_free(pdata->gpio_ext);
+err_free_data:
+	kfree(leds_data);
+
+	return ret;
+}
+
+static int __devexit netxbig_led_remove(struct platform_device *pdev)
+{
+	struct netxbig_led_platform_data *pdata = pdev->dev.platform_data;
+	struct netxbig_led_data *leds_data;
+	int i;
+
+	leds_data = platform_get_drvdata(pdev);
+
+	for (i = 0; i < pdata->num_leds; i++)
+		delete_netxbig_led(&leds_data[i]);
+
+	gpio_ext_free(pdata->gpio_ext);
+	kfree(leds_data);
+
+	return 0;
+}
+
+static struct platform_driver netxbig_led_driver = {
+	.probe		= netxbig_led_probe,
+	.remove		= __devexit_p(netxbig_led_remove),
+	.driver		= {
+		.name	= "leds-netxbig",
+		.owner	= THIS_MODULE,
+	},
+};
+MODULE_ALIAS("platform:leds-netxbig");
+
+static int __init netxbig_led_init(void)
+{
+	return platform_driver_register(&netxbig_led_driver);
+}
+
+static void __exit netxbig_led_exit(void)
+{
+	platform_driver_unregister(&netxbig_led_driver);
+}
+
+module_init(netxbig_led_init);
+module_exit(netxbig_led_exit);
+
+MODULE_AUTHOR("Simon Guinot <sguinot@lacie.com>");
+MODULE_DESCRIPTION("LED driver for LaCie xBig Network boards");
+MODULE_LICENSE("GPL");
diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c
index 350eb34..f77d48d 100644
--- a/drivers/leds/leds-ns2.c
+++ b/drivers/leds/leds-ns2.c
@@ -141,10 +141,12 @@
 				  struct device_attribute *attr,
 				  const char *buff, size_t count)
 {
+	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct ns2_led_data *led_dat =
+		container_of(led_cdev, struct ns2_led_data, cdev);
 	int ret;
 	unsigned long enable;
 	enum ns2_led_modes mode;
-	struct ns2_led_data *led_dat = dev_get_drvdata(dev);
 
 	ret = strict_strtoul(buff, 10, &enable);
 	if (ret < 0)
@@ -172,7 +174,9 @@
 static ssize_t ns2_led_sata_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
-	struct ns2_led_data *led_dat = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct ns2_led_data *led_dat =
+		container_of(led_cdev, struct ns2_led_data, cdev);
 
 	return sprintf(buf, "%d\n", led_dat->sata);
 }
@@ -234,7 +238,6 @@
 	if (ret < 0)
 		goto err_free_slow;
 
-	dev_set_drvdata(led_dat->cdev.dev, led_dat);
 	ret = device_create_file(led_dat->cdev.dev, &dev_attr_sata);
 	if (ret < 0)
 		goto err_free_cdev;
diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c
index 85b714d..3c781cd 100644
--- a/drivers/lguest/lguest_user.c
+++ b/drivers/lguest/lguest_user.c
@@ -514,6 +514,7 @@
 	.release = close,
 	.write	 = write,
 	.read	 = read,
+	.llseek  = default_llseek,
 };
 
 /*
diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c
index 1c4ee6e..75049e7 100644
--- a/drivers/macintosh/adb.c
+++ b/drivers/macintosh/adb.c
@@ -24,7 +24,6 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/adb.h>
 #include <linux/cuda.h>
 #include <linux/pmu.h>
@@ -55,6 +54,7 @@
 extern struct adb_driver via_pmu_driver;
 extern struct adb_driver macio_adb_driver;
 
+static DEFINE_MUTEX(adb_mutex);
 static struct adb_driver *adb_driver_list[] = {
 #ifdef CONFIG_ADB_MACII
 	&via_macii_driver,
@@ -83,7 +83,7 @@
 BLOCKING_NOTIFIER_HEAD(adb_client_list);
 static int adb_got_sleep;
 static int adb_inited;
-static DECLARE_MUTEX(adb_probe_mutex);
+static DEFINE_SEMAPHORE(adb_probe_mutex);
 static int sleepy_trackpad;
 static int autopoll_devs;
 int __adb_probe_sync;
@@ -647,7 +647,7 @@
 	struct adbdev_state *state;
 	int ret = 0;
 
-	lock_kernel();
+	mutex_lock(&adb_mutex);
 	if (iminor(inode) > 0 || adb_controller == NULL) {
 		ret = -ENXIO;
 		goto out;
@@ -665,7 +665,7 @@
 	state->inuse = 1;
 
 out:
-	unlock_kernel();
+	mutex_unlock(&adb_mutex);
 	return ret;
 }
 
@@ -674,7 +674,7 @@
 	struct adbdev_state *state = file->private_data;
 	unsigned long flags;
 
-	lock_kernel();
+	mutex_lock(&adb_mutex);
 	if (state) {
 		file->private_data = NULL;
 		spin_lock_irqsave(&state->lock, flags);
@@ -687,7 +687,7 @@
 			spin_unlock_irqrestore(&state->lock, flags);
 		}
 	}
-	unlock_kernel();
+	mutex_unlock(&adb_mutex);
 	return 0;
 }
 
diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c
index a3d25da..1a57e88 100644
--- a/drivers/macintosh/ans-lcd.c
+++ b/drivers/macintosh/ans-lcd.c
@@ -137,6 +137,7 @@
 	.write		= anslcd_write,
 	.unlocked_ioctl	= anslcd_ioctl,
 	.open		= anslcd_open,
+	.llseek		= default_llseek,
 };
 
 static struct miscdevice anslcd_dev = {
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index e58c3d3..290cb32 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -19,7 +19,6 @@
  *    the userland interface
  */
 
-#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
@@ -97,6 +96,7 @@
  * I don't think there will ever be more than one SMU, so
  * for now, just hard code that
  */
+static DEFINE_MUTEX(smu_mutex);
 static struct smu_device	*smu;
 static DEFINE_MUTEX(smu_part_access);
 static int smu_irq_inited;
@@ -1095,12 +1095,12 @@
 	pp->mode = smu_file_commands;
 	init_waitqueue_head(&pp->wait);
 
-	lock_kernel();
+	mutex_lock(&smu_mutex);
 	spin_lock_irqsave(&smu_clist_lock, flags);
 	list_add(&pp->list, &smu_clist);
 	spin_unlock_irqrestore(&smu_clist_lock, flags);
 	file->private_data = pp;
-	unlock_kernel();
+	mutex_unlock(&smu_mutex);
 
 	return 0;
 }
diff --git a/drivers/macintosh/via-pmu-led.c b/drivers/macintosh/via-pmu-led.c
index d242976..19c3718 100644
--- a/drivers/macintosh/via-pmu-led.c
+++ b/drivers/macintosh/via-pmu-led.c
@@ -92,8 +92,10 @@
 	if (dt == NULL)
 		return -ENODEV;
 	model = of_get_property(dt, "model", NULL);
-	if (model == NULL)
+	if (model == NULL) {
+		of_node_put(dt);
 		return -ENODEV;
+	}
 	if (strncmp(model, "PowerBook", strlen("PowerBook")) != 0 &&
 	    strncmp(model, "iBook", strlen("iBook")) != 0 &&
 	    strcmp(model, "PowerMac7,2") != 0 &&
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 2d17e76..cd29c82 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -18,7 +18,7 @@
  *
  */
 #include <stdarg.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -73,6 +73,7 @@
 /* How many iterations between battery polls */
 #define BATTERY_POLLING_COUNT	2
 
+static DEFINE_MUTEX(pmu_info_proc_mutex);
 static volatile unsigned char __iomem *via;
 
 /* VIA registers - spaced 0x200 bytes apart */
@@ -2078,7 +2079,7 @@
 	pp->rb_get = pp->rb_put = 0;
 	spin_lock_init(&pp->lock);
 	init_waitqueue_head(&pp->wait);
-	lock_kernel();
+	mutex_lock(&pmu_info_proc_mutex);
 	spin_lock_irqsave(&all_pvt_lock, flags);
 #if defined(CONFIG_INPUT_ADBHID) && defined(CONFIG_PMAC_BACKLIGHT)
 	pp->backlight_locker = 0;
@@ -2086,7 +2087,7 @@
 	list_add(&pp->list, &all_pmu_pvt);
 	spin_unlock_irqrestore(&all_pvt_lock, flags);
 	file->private_data = pp;
-	unlock_kernel();
+	mutex_unlock(&pmu_info_proc_mutex);
 	return 0;
 }
 
@@ -2343,9 +2344,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&pmu_info_proc_mutex);
 	ret = pmu_ioctl(filp, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&pmu_info_proc_mutex);
 
 	return ret;
 }
@@ -2398,6 +2399,7 @@
 #endif
 	.open		= pmu_open,
 	.release	= pmu_release,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice pmu_device = {
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 368e8e9..d5b0e4c 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1278,7 +1278,7 @@
 	struct dm_crypt_io *io;
 	struct crypt_config *cc;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		cc = ti->private;
 		bio->bi_bdev = cc->dev->bdev;
 		return DM_MAPIO_REMAPPED;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 0590c75..136d4f7 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -31,7 +31,6 @@
  */
 struct io {
 	unsigned long error_bits;
-	unsigned long eopnotsupp_bits;
 	atomic_t count;
 	struct task_struct *sleeper;
 	struct dm_io_client *client;
@@ -130,11 +129,8 @@
  *---------------------------------------------------------------*/
 static void dec_count(struct io *io, unsigned int region, int error)
 {
-	if (error) {
+	if (error)
 		set_bit(region, &io->error_bits);
-		if (error == -EOPNOTSUPP)
-			set_bit(region, &io->eopnotsupp_bits);
-	}
 
 	if (atomic_dec_and_test(&io->count)) {
 		if (io->sleeper)
@@ -310,8 +306,8 @@
 	sector_t remaining = where->count;
 
 	/*
-	 * where->count may be zero if rw holds a write barrier and we
-	 * need to send a zero-sized barrier.
+	 * where->count may be zero if rw holds a flush and we need to
+	 * send a zero-sized flush.
 	 */
 	do {
 		/*
@@ -364,7 +360,7 @@
 	 */
 	for (i = 0; i < num_regions; i++) {
 		*dp = old_pages;
-		if (where[i].count || (rw & REQ_HARDBARRIER))
+		if (where[i].count || (rw & REQ_FLUSH))
 			do_region(rw, i, where + i, dp, io);
 	}
 
@@ -393,9 +389,7 @@
 		return -EIO;
 	}
 
-retry:
 	io->error_bits = 0;
-	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = current;
 	io->client = client;
@@ -412,11 +406,6 @@
 	}
 	set_current_state(TASK_RUNNING);
 
-	if (io->eopnotsupp_bits && (rw & REQ_HARDBARRIER)) {
-		rw &= ~REQ_HARDBARRIER;
-		goto retry;
-	}
-
 	if (error_bits)
 		*error_bits = io->error_bits;
 
@@ -437,7 +426,6 @@
 
 	io = mempool_alloc(client->pool, GFP_NOIO);
 	io->error_bits = 0;
-	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = NULL;
 	io->client = client;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 3e39193..4b54618 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1596,6 +1596,7 @@
 	.unlocked_ioctl	 = dm_ctl_ioctl,
 	.compat_ioctl = dm_compat_ctl_ioctl,
 	.owner	 = THIS_MODULE,
+	.llseek  = noop_llseek,
 };
 
 static struct miscdevice _dm_misc = {
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 5a08be0..33420e6 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -300,7 +300,7 @@
 		.count = 0,
 	};
 
-	lc->io_req.bi_rw = WRITE_BARRIER;
+	lc->io_req.bi_rw = WRITE_FLUSH;
 
 	return dm_io(&lc->io_req, 1, &null_location, NULL);
 }
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 7c081bc..19a59b0 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -259,7 +259,7 @@
 	struct dm_io_region io[ms->nr_mirrors];
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE_BARRIER,
+		.bi_rw = WRITE_FLUSH,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.bvec = NULL,
 		.client = ms->io_client,
@@ -629,7 +629,7 @@
 	struct dm_io_region io[ms->nr_mirrors], *dest = io;
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE | (bio->bi_rw & WRITE_BARRIER),
+		.bi_rw = WRITE | (bio->bi_rw & WRITE_FLUSH_FUA),
 		.mem.type = DM_IO_BVEC,
 		.mem.ptr.bvec = bio->bi_io_vec + bio->bi_idx,
 		.notify.fn = write_callback,
@@ -670,7 +670,7 @@
 	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		if (unlikely(bio_empty_barrier(bio))) {
+		if (bio->bi_rw & REQ_FLUSH) {
 			bio_list_add(&sync, bio);
 			continue;
 		}
@@ -1203,7 +1203,7 @@
 	 * We need to dec pending if this was a write.
 	 */
 	if (rw == WRITE) {
-		if (likely(!bio_empty_barrier(bio)))
+		if (!(bio->bi_rw & REQ_FLUSH))
 			dm_rh_dec(ms->rh, map_context->ll);
 		return error;
 	}
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index bd5c58b..dad011a 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -81,9 +81,9 @@
 	struct list_head failed_recovered_regions;
 
 	/*
-	 * If there was a barrier failure no regions can be marked clean.
+	 * If there was a flush failure no regions can be marked clean.
 	 */
-	int barrier_failure;
+	int flush_failure;
 
 	void *context;
 	sector_t target_begin;
@@ -217,7 +217,7 @@
 	INIT_LIST_HEAD(&rh->quiesced_regions);
 	INIT_LIST_HEAD(&rh->recovered_regions);
 	INIT_LIST_HEAD(&rh->failed_recovered_regions);
-	rh->barrier_failure = 0;
+	rh->flush_failure = 0;
 
 	rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
 						      sizeof(struct dm_region));
@@ -399,8 +399,8 @@
 	region_t region = dm_rh_bio_to_region(rh, bio);
 	int recovering = 0;
 
-	if (bio_empty_barrier(bio)) {
-		rh->barrier_failure = 1;
+	if (bio->bi_rw & REQ_FLUSH) {
+		rh->flush_failure = 1;
 		return;
 	}
 
@@ -524,7 +524,7 @@
 	struct bio *bio;
 
 	for (bio = bios->head; bio; bio = bio->bi_next) {
-		if (bio_empty_barrier(bio))
+		if (bio->bi_rw & REQ_FLUSH)
 			continue;
 		rh_inc(rh, dm_rh_bio_to_region(rh, bio));
 	}
@@ -555,9 +555,9 @@
 		 */
 
 		/* do nothing for DM_RH_NOSYNC */
-		if (unlikely(rh->barrier_failure)) {
+		if (unlikely(rh->flush_failure)) {
 			/*
-			 * If a write barrier failed some time ago, we
+			 * If a write flush failed some time ago, we
 			 * don't know whether or not this write made it
 			 * to the disk, so we must resync the device.
 			 */
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index cc2bdb8..0b61792 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -687,7 +687,7 @@
 	/*
 	 * Commit exceptions to disk.
 	 */
-	if (ps->valid && area_io(ps, WRITE_BARRIER))
+	if (ps->valid && area_io(ps, WRITE_FLUSH_FUA))
 		ps->valid = 0;
 
 	/*
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 5974d30..53cf79d 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -706,8 +706,6 @@
 	return 0;
 }
 
-#define min_not_zero(l, r) (((l) == 0) ? (r) : (((r) == 0) ? (l) : min(l, r)))
-
 /*
  * Return a minimum chunk size of all snapshots that have the specified origin.
  * Return zero if the origin has no snapshots.
@@ -1587,7 +1585,7 @@
 	chunk_t chunk;
 	struct dm_snap_pending_exception *pe = NULL;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		bio->bi_bdev = s->cow->bdev;
 		return DM_MAPIO_REMAPPED;
 	}
@@ -1691,7 +1689,7 @@
 	int r = DM_MAPIO_REMAPPED;
 	chunk_t chunk;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		if (!map_context->target_request_nr)
 			bio->bi_bdev = s->origin->bdev;
 		else
@@ -2135,7 +2133,7 @@
 	struct dm_dev *dev = ti->private;
 	bio->bi_bdev = dev->bdev;
 
-	if (unlikely(bio_empty_barrier(bio)))
+	if (bio->bi_rw & REQ_FLUSH)
 		return DM_MAPIO_REMAPPED;
 
 	/* Only tell snapshots if this is a write */
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index c297f6d..f0371b4 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -271,7 +271,7 @@
 	uint32_t stripe;
 	unsigned target_request_nr;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		target_request_nr = map_context->target_request_nr;
 		BUG_ON(target_request_nr >= sc->stripes);
 		bio->bi_bdev = sc->stripe[target_request_nr].dev->bdev;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index f9fc07d..90267f8 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -486,11 +486,6 @@
 	return 0;
 }
 
-/*
- * Returns the minimum that is _not_ zero, unless both are zero.
- */
-#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
-
 int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 			 sector_t start, sector_t len, void *data)
 {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ac384b2..7cb1352 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -15,7 +15,6 @@
 #include <linux/blkpg.h>
 #include <linux/bio.h>
 #include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
 #include <linux/mempool.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
@@ -33,6 +32,7 @@
 #define DM_COOKIE_ENV_VAR_NAME "DM_COOKIE"
 #define DM_COOKIE_LENGTH 24
 
+static DEFINE_MUTEX(dm_mutex);
 static const char *_name = DM_NAME;
 
 static unsigned int major = 0;
@@ -110,7 +110,6 @@
 #define DMF_FREEING 3
 #define DMF_DELETING 4
 #define DMF_NOFLUSH_SUSPENDING 5
-#define DMF_QUEUE_IO_TO_THREAD 6
 
 /*
  * Work processed by per-device workqueue.
@@ -144,24 +143,9 @@
 	spinlock_t deferred_lock;
 
 	/*
-	 * An error from the barrier request currently being processed.
-	 */
-	int barrier_error;
-
-	/*
-	 * Protect barrier_error from concurrent endio processing
-	 * in request-based dm.
-	 */
-	spinlock_t barrier_error_lock;
-
-	/*
-	 * Processing queue (flush/barriers)
+	 * Processing queue (flush)
 	 */
 	struct workqueue_struct *wq;
-	struct work_struct barrier_work;
-
-	/* A pointer to the currently processing pre/post flush request */
-	struct request *flush_request;
 
 	/*
 	 * The current mapping.
@@ -200,8 +184,8 @@
 	/* sysfs handle */
 	struct kobject kobj;
 
-	/* zero-length barrier that will be cloned and submitted to targets */
-	struct bio barrier_bio;
+	/* zero-length flush that will be cloned and submitted to targets */
+	struct bio flush_bio;
 };
 
 /*
@@ -344,7 +328,7 @@
 {
 	struct mapped_device *md;
 
-	lock_kernel();
+	mutex_lock(&dm_mutex);
 	spin_lock(&_minor_lock);
 
 	md = bdev->bd_disk->private_data;
@@ -362,7 +346,7 @@
 
 out:
 	spin_unlock(&_minor_lock);
-	unlock_kernel();
+	mutex_unlock(&dm_mutex);
 
 	return md ? 0 : -ENXIO;
 }
@@ -371,10 +355,10 @@
 {
 	struct mapped_device *md = disk->private_data;
 
-	lock_kernel();
+	mutex_lock(&dm_mutex);
 	atomic_dec(&md->open_count);
 	dm_put(md);
-	unlock_kernel();
+	mutex_unlock(&dm_mutex);
 
 	return 0;
 }
@@ -512,7 +496,7 @@
 
 	/*
 	 * After this is decremented the bio must not be touched if it is
-	 * a barrier.
+	 * a flush.
 	 */
 	dm_disk(md)->part0.in_flight[rw] = pending =
 		atomic_dec_return(&md->pending[rw]);
@@ -528,16 +512,12 @@
  */
 static void queue_io(struct mapped_device *md, struct bio *bio)
 {
-	down_write(&md->io_lock);
+	unsigned long flags;
 
-	spin_lock_irq(&md->deferred_lock);
+	spin_lock_irqsave(&md->deferred_lock, flags);
 	bio_list_add(&md->deferred, bio);
-	spin_unlock_irq(&md->deferred_lock);
-
-	if (!test_and_set_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags))
-		queue_work(md->wq, &md->work);
-
-	up_write(&md->io_lock);
+	spin_unlock_irqrestore(&md->deferred_lock, flags);
+	queue_work(md->wq, &md->work);
 }
 
 /*
@@ -625,11 +605,9 @@
 			 * Target requested pushing back the I/O.
 			 */
 			spin_lock_irqsave(&md->deferred_lock, flags);
-			if (__noflush_suspending(md)) {
-				if (!(io->bio->bi_rw & REQ_HARDBARRIER))
-					bio_list_add_head(&md->deferred,
-							  io->bio);
-			} else
+			if (__noflush_suspending(md))
+				bio_list_add_head(&md->deferred, io->bio);
+			else
 				/* noflush suspend was interrupted. */
 				io->error = -EIO;
 			spin_unlock_irqrestore(&md->deferred_lock, flags);
@@ -637,32 +615,23 @@
 
 		io_error = io->error;
 		bio = io->bio;
+		end_io_acct(io);
+		free_io(md, io);
 
-		if (bio->bi_rw & REQ_HARDBARRIER) {
+		if (io_error == DM_ENDIO_REQUEUE)
+			return;
+
+		if ((bio->bi_rw & REQ_FLUSH) && bio->bi_size) {
 			/*
-			 * There can be just one barrier request so we use
-			 * a per-device variable for error reporting.
-			 * Note that you can't touch the bio after end_io_acct
-			 *
-			 * We ignore -EOPNOTSUPP for empty flush reported by
-			 * underlying devices. We assume that if the device
-			 * doesn't support empty barriers, it doesn't need
-			 * cache flushing commands.
+			 * Preflush done for flush with data, reissue
+			 * without REQ_FLUSH.
 			 */
-			if (!md->barrier_error &&
-			    !(bio_empty_barrier(bio) && io_error == -EOPNOTSUPP))
-				md->barrier_error = io_error;
-			end_io_acct(io);
-			free_io(md, io);
+			bio->bi_rw &= ~REQ_FLUSH;
+			queue_io(md, bio);
 		} else {
-			end_io_acct(io);
-			free_io(md, io);
-
-			if (io_error != DM_ENDIO_REQUEUE) {
-				trace_block_bio_complete(md->queue, bio);
-
-				bio_endio(bio, io_error);
-			}
+			/* done with normal IO or empty flush */
+			trace_block_bio_complete(md->queue, bio);
+			bio_endio(bio, io_error);
 		}
 	}
 }
@@ -755,23 +724,6 @@
 	blk_update_request(tio->orig, 0, nr_bytes);
 }
 
-static void store_barrier_error(struct mapped_device *md, int error)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&md->barrier_error_lock, flags);
-	/*
-	 * Basically, the first error is taken, but:
-	 *   -EOPNOTSUPP supersedes any I/O error.
-	 *   Requeue request supersedes any I/O error but -EOPNOTSUPP.
-	 */
-	if (!md->barrier_error || error == -EOPNOTSUPP ||
-	    (md->barrier_error != -EOPNOTSUPP &&
-	     error == DM_ENDIO_REQUEUE))
-		md->barrier_error = error;
-	spin_unlock_irqrestore(&md->barrier_error_lock, flags);
-}
-
 /*
  * Don't touch any member of the md after calling this function because
  * the md may be freed in dm_put() at the end of this function.
@@ -809,13 +761,11 @@
 static void dm_end_request(struct request *clone, int error)
 {
 	int rw = rq_data_dir(clone);
-	int run_queue = 1;
-	bool is_barrier = clone->cmd_flags & REQ_HARDBARRIER;
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct mapped_device *md = tio->md;
 	struct request *rq = tio->orig;
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !is_barrier) {
+	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		rq->errors = clone->errors;
 		rq->resid_len = clone->resid_len;
 
@@ -829,15 +779,8 @@
 	}
 
 	free_rq_clone(clone);
-
-	if (unlikely(is_barrier)) {
-		if (unlikely(error))
-			store_barrier_error(md, error);
-		run_queue = 0;
-	} else
-		blk_end_request_all(rq, error);
-
-	rq_completed(md, rw, run_queue);
+	blk_end_request_all(rq, error);
+	rq_completed(md, rw, true);
 }
 
 static void dm_unprep_request(struct request *rq)
@@ -862,16 +805,6 @@
 	struct request_queue *q = rq->q;
 	unsigned long flags;
 
-	if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
-		/*
-		 * Barrier clones share an original request.
-		 * Leave it to dm_end_request(), which handles this special
-		 * case.
-		 */
-		dm_end_request(clone, DM_ENDIO_REQUEUE);
-		return;
-	}
-
 	dm_unprep_request(rq);
 
 	spin_lock_irqsave(q->queue_lock, flags);
@@ -961,19 +894,6 @@
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct request *rq = tio->orig;
 
-	if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
-		/*
-		 * Barrier clones share an original request.  So can't use
-		 * softirq_done with the original.
-		 * Pass the clone to dm_done() directly in this special case.
-		 * It is safe (even if clone->q->queue_lock is held here)
-		 * because there is no I/O dispatching during the completion
-		 * of barrier clone.
-		 */
-		dm_done(clone, error, true);
-		return;
-	}
-
 	tio->error = error;
 	rq->completion_data = clone;
 	blk_complete_request(rq);
@@ -990,17 +910,6 @@
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct request *rq = tio->orig;
 
-	if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) {
-		/*
-		 * Barrier clones share an original request.
-		 * Leave it to dm_end_request(), which handles this special
-		 * case.
-		 */
-		BUG_ON(error > 0);
-		dm_end_request(clone, error);
-		return;
-	}
-
 	rq->cmd_flags |= REQ_FAILED;
 	dm_complete_request(clone, error);
 }
@@ -1119,7 +1028,7 @@
 }
 
 /*
- * Creates a little bio that is just does part of a bvec.
+ * Creates a little bio that just does part of a bvec.
  */
 static struct bio *split_bvec(struct bio *bio, sector_t sector,
 			      unsigned short idx, unsigned int offset,
@@ -1134,7 +1043,7 @@
 
 	clone->bi_sector = sector;
 	clone->bi_bdev = bio->bi_bdev;
-	clone->bi_rw = bio->bi_rw & ~REQ_HARDBARRIER;
+	clone->bi_rw = bio->bi_rw;
 	clone->bi_vcnt = 1;
 	clone->bi_size = to_bytes(len);
 	clone->bi_io_vec->bv_offset = offset;
@@ -1161,7 +1070,6 @@
 
 	clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
 	__bio_clone(clone, bio);
-	clone->bi_rw &= ~REQ_HARDBARRIER;
 	clone->bi_destructor = dm_bio_destructor;
 	clone->bi_sector = sector;
 	clone->bi_idx = idx;
@@ -1225,16 +1133,15 @@
 		__issue_target_request(ci, ti, request_nr, len);
 }
 
-static int __clone_and_map_empty_barrier(struct clone_info *ci)
+static int __clone_and_map_empty_flush(struct clone_info *ci)
 {
 	unsigned target_nr = 0;
 	struct dm_target *ti;
 
+	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
 		__issue_target_requests(ci, ti, ti->num_flush_requests, 0);
 
-	ci->sector_count = 0;
-
 	return 0;
 }
 
@@ -1289,9 +1196,6 @@
 	sector_t len = 0, max;
 	struct dm_target_io *tio;
 
-	if (unlikely(bio_empty_barrier(bio)))
-		return __clone_and_map_empty_barrier(ci);
-
 	if (unlikely(bio->bi_rw & REQ_DISCARD))
 		return __clone_and_map_discard(ci);
 
@@ -1383,16 +1287,11 @@
 
 	ci.map = dm_get_live_table(md);
 	if (unlikely(!ci.map)) {
-		if (!(bio->bi_rw & REQ_HARDBARRIER))
-			bio_io_error(bio);
-		else
-			if (!md->barrier_error)
-				md->barrier_error = -EIO;
+		bio_io_error(bio);
 		return;
 	}
 
 	ci.md = md;
-	ci.bio = bio;
 	ci.io = alloc_io(md);
 	ci.io->error = 0;
 	atomic_set(&ci.io->io_count, 1);
@@ -1400,14 +1299,20 @@
 	ci.io->md = md;
 	spin_lock_init(&ci.io->endio_lock);
 	ci.sector = bio->bi_sector;
-	ci.sector_count = bio_sectors(bio);
-	if (unlikely(bio_empty_barrier(bio)))
-		ci.sector_count = 1;
 	ci.idx = bio->bi_idx;
 
 	start_io_acct(ci.io);
-	while (ci.sector_count && !error)
-		error = __clone_and_map(&ci);
+	if (bio->bi_rw & REQ_FLUSH) {
+		ci.bio = &ci.md->flush_bio;
+		ci.sector_count = 0;
+		error = __clone_and_map_empty_flush(&ci);
+		/* dec_pending submits any data associated with flush */
+	} else {
+		ci.bio = bio;
+		ci.sector_count = bio_sectors(bio);
+		while (ci.sector_count && !error)
+			error = __clone_and_map(&ci);
+	}
 
 	/* drop the extra reference count */
 	dec_pending(ci.io, error);
@@ -1491,22 +1396,14 @@
 	part_stat_add(cpu, &dm_disk(md)->part0, sectors[rw], bio_sectors(bio));
 	part_stat_unlock();
 
-	/*
-	 * If we're suspended or the thread is processing barriers
-	 * we have to queue this io for later.
-	 */
-	if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) ||
-	    unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
+	/* if we're suspended, we have to queue this io for later */
+	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
 		up_read(&md->io_lock);
 
-		if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) &&
-		    bio_rw(bio) == READA) {
+		if (bio_rw(bio) != READA)
+			queue_io(md, bio);
+		else
 			bio_io_error(bio);
-			return 0;
-		}
-
-		queue_io(md, bio);
-
 		return 0;
 	}
 
@@ -1537,14 +1434,6 @@
 	return _dm_request(q, bio);
 }
 
-static bool dm_rq_is_flush_request(struct request *rq)
-{
-	if (rq->cmd_flags & REQ_FLUSH)
-		return true;
-	else
-		return false;
-}
-
 void dm_dispatch_request(struct request *rq)
 {
 	int r;
@@ -1592,22 +1481,15 @@
 {
 	int r;
 
-	if (dm_rq_is_flush_request(rq)) {
-		blk_rq_init(NULL, clone);
-		clone->cmd_type = REQ_TYPE_FS;
-		clone->cmd_flags |= (REQ_HARDBARRIER | WRITE);
-	} else {
-		r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC,
-				      dm_rq_bio_constructor, tio);
-		if (r)
-			return r;
+	r = blk_rq_prep_clone(clone, rq, tio->md->bs, GFP_ATOMIC,
+			      dm_rq_bio_constructor, tio);
+	if (r)
+		return r;
 
-		clone->cmd = rq->cmd;
-		clone->cmd_len = rq->cmd_len;
-		clone->sense = rq->sense;
-		clone->buffer = rq->buffer;
-	}
-
+	clone->cmd = rq->cmd;
+	clone->cmd_len = rq->cmd_len;
+	clone->sense = rq->sense;
+	clone->buffer = rq->buffer;
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
 
@@ -1648,9 +1530,6 @@
 	struct mapped_device *md = q->queuedata;
 	struct request *clone;
 
-	if (unlikely(dm_rq_is_flush_request(rq)))
-		return BLKPREP_OK;
-
 	if (unlikely(rq->special)) {
 		DMWARN("Already has something in rq->special.");
 		return BLKPREP_KILL;
@@ -1727,6 +1606,7 @@
 	struct dm_table *map = dm_get_live_table(md);
 	struct dm_target *ti;
 	struct request *rq, *clone;
+	sector_t pos;
 
 	/*
 	 * For suspend, check blk_queue_stopped() and increment
@@ -1739,15 +1619,14 @@
 		if (!rq)
 			goto plug_and_out;
 
-		if (unlikely(dm_rq_is_flush_request(rq))) {
-			BUG_ON(md->flush_request);
-			md->flush_request = rq;
-			blk_start_request(rq);
-			queue_work(md->wq, &md->barrier_work);
-			goto out;
-		}
+		/* always use block 0 to find the target for flushes for now */
+		pos = 0;
+		if (!(rq->cmd_flags & REQ_FLUSH))
+			pos = blk_rq_pos(rq);
 
-		ti = dm_table_find_target(map, blk_rq_pos(rq));
+		ti = dm_table_find_target(map, pos);
+		BUG_ON(!dm_target_is_valid(ti));
+
 		if (ti->type->busy && ti->type->busy(ti))
 			goto plug_and_out;
 
@@ -1918,7 +1797,6 @@
 static const struct block_device_operations dm_blk_dops;
 
 static void dm_wq_work(struct work_struct *work);
-static void dm_rq_barrier_work(struct work_struct *work);
 
 static void dm_init_md_queue(struct mapped_device *md)
 {
@@ -1940,6 +1818,7 @@
 	blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
 	md->queue->unplug_fn = dm_unplug_all;
 	blk_queue_merge_bvec(md->queue, dm_merge_bvec);
+	blk_queue_flush(md->queue, REQ_FLUSH | REQ_FUA);
 }
 
 /*
@@ -1972,7 +1851,6 @@
 	mutex_init(&md->suspend_lock);
 	mutex_init(&md->type_lock);
 	spin_lock_init(&md->deferred_lock);
-	spin_lock_init(&md->barrier_error_lock);
 	rwlock_init(&md->map_lock);
 	atomic_set(&md->holders, 1);
 	atomic_set(&md->open_count, 0);
@@ -1995,7 +1873,6 @@
 	atomic_set(&md->pending[1], 0);
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
-	INIT_WORK(&md->barrier_work, dm_rq_barrier_work);
 	init_waitqueue_head(&md->eventq);
 
 	md->disk->major = _major;
@@ -2015,6 +1892,10 @@
 	if (!md->bdev)
 		goto bad_bdev;
 
+	bio_init(&md->flush_bio);
+	md->flush_bio.bi_bdev = md->bdev;
+	md->flush_bio.bi_rw = WRITE_FLUSH;
+
 	/* Populate the mapping, nobody knows we exist yet */
 	spin_lock(&_minor_lock);
 	old_md = idr_replace(&_minor_idr, md, minor);
@@ -2245,7 +2126,6 @@
 	blk_queue_softirq_done(md->queue, dm_softirq_done);
 	blk_queue_prep_rq(md->queue, dm_prep_fn);
 	blk_queue_lld_busy(md->queue, dm_lld_busy);
-	blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH);
 
 	elv_register_queue(md->queue);
 
@@ -2406,43 +2286,6 @@
 	return r;
 }
 
-static void dm_flush(struct mapped_device *md)
-{
-	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
-
-	bio_init(&md->barrier_bio);
-	md->barrier_bio.bi_bdev = md->bdev;
-	md->barrier_bio.bi_rw = WRITE_BARRIER;
-	__split_and_process_bio(md, &md->barrier_bio);
-
-	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
-}
-
-static void process_barrier(struct mapped_device *md, struct bio *bio)
-{
-	md->barrier_error = 0;
-
-	dm_flush(md);
-
-	if (!bio_empty_barrier(bio)) {
-		__split_and_process_bio(md, bio);
-		/*
-		 * If the request isn't supported, don't waste time with
-		 * the second flush.
-		 */
-		if (md->barrier_error != -EOPNOTSUPP)
-			dm_flush(md);
-	}
-
-	if (md->barrier_error != DM_ENDIO_REQUEUE)
-		bio_endio(bio, md->barrier_error);
-	else {
-		spin_lock_irq(&md->deferred_lock);
-		bio_list_add_head(&md->deferred, bio);
-		spin_unlock_irq(&md->deferred_lock);
-	}
-}
-
 /*
  * Process the deferred bios
  */
@@ -2452,33 +2295,27 @@
 						work);
 	struct bio *c;
 
-	down_write(&md->io_lock);
+	down_read(&md->io_lock);
 
 	while (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
 		spin_lock_irq(&md->deferred_lock);
 		c = bio_list_pop(&md->deferred);
 		spin_unlock_irq(&md->deferred_lock);
 
-		if (!c) {
-			clear_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags);
+		if (!c)
 			break;
-		}
 
-		up_write(&md->io_lock);
+		up_read(&md->io_lock);
 
 		if (dm_request_based(md))
 			generic_make_request(c);
-		else {
-			if (c->bi_rw & REQ_HARDBARRIER)
-				process_barrier(md, c);
-			else
-				__split_and_process_bio(md, c);
-		}
+		else
+			__split_and_process_bio(md, c);
 
-		down_write(&md->io_lock);
+		down_read(&md->io_lock);
 	}
 
-	up_write(&md->io_lock);
+	up_read(&md->io_lock);
 }
 
 static void dm_queue_flush(struct mapped_device *md)
@@ -2488,73 +2325,6 @@
 	queue_work(md->wq, &md->work);
 }
 
-static void dm_rq_set_target_request_nr(struct request *clone, unsigned request_nr)
-{
-	struct dm_rq_target_io *tio = clone->end_io_data;
-
-	tio->info.target_request_nr = request_nr;
-}
-
-/* Issue barrier requests to targets and wait for their completion. */
-static int dm_rq_barrier(struct mapped_device *md)
-{
-	int i, j;
-	struct dm_table *map = dm_get_live_table(md);
-	unsigned num_targets = dm_table_get_num_targets(map);
-	struct dm_target *ti;
-	struct request *clone;
-
-	md->barrier_error = 0;
-
-	for (i = 0; i < num_targets; i++) {
-		ti = dm_table_get_target(map, i);
-		for (j = 0; j < ti->num_flush_requests; j++) {
-			clone = clone_rq(md->flush_request, md, GFP_NOIO);
-			dm_rq_set_target_request_nr(clone, j);
-			atomic_inc(&md->pending[rq_data_dir(clone)]);
-			map_request(ti, clone, md);
-		}
-	}
-
-	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
-	dm_table_put(map);
-
-	return md->barrier_error;
-}
-
-static void dm_rq_barrier_work(struct work_struct *work)
-{
-	int error;
-	struct mapped_device *md = container_of(work, struct mapped_device,
-						barrier_work);
-	struct request_queue *q = md->queue;
-	struct request *rq;
-	unsigned long flags;
-
-	/*
-	 * Hold the md reference here and leave it at the last part so that
-	 * the md can't be deleted by device opener when the barrier request
-	 * completes.
-	 */
-	dm_get(md);
-
-	error = dm_rq_barrier(md);
-
-	rq = md->flush_request;
-	md->flush_request = NULL;
-
-	if (error == DM_ENDIO_REQUEUE) {
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_requeue_request(q, rq);
-		spin_unlock_irqrestore(q->queue_lock, flags);
-	} else
-		blk_end_request_all(rq, error);
-
-	blk_run_queue(q);
-
-	dm_put(md);
-}
-
 /*
  * Swap in a new table, returning the old one for the caller to destroy.
  */
@@ -2677,23 +2447,17 @@
 	 *
 	 * To get all processes out of __split_and_process_bio in dm_request,
 	 * we take the write lock. To prevent any process from reentering
-	 * __split_and_process_bio from dm_request, we set
-	 * DMF_QUEUE_IO_TO_THREAD.
-	 *
-	 * To quiesce the thread (dm_wq_work), we set DMF_BLOCK_IO_FOR_SUSPEND
-	 * and call flush_workqueue(md->wq). flush_workqueue will wait until
-	 * dm_wq_work exits and DMF_BLOCK_IO_FOR_SUSPEND will prevent any
-	 * further calls to __split_and_process_bio from dm_wq_work.
+	 * __split_and_process_bio from dm_request and quiesce the thread
+	 * (dm_wq_work), we set BMF_BLOCK_IO_FOR_SUSPEND and call
+	 * flush_workqueue(md->wq).
 	 */
 	down_write(&md->io_lock);
 	set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
-	set_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags);
 	up_write(&md->io_lock);
 
 	/*
-	 * Request-based dm uses md->wq for barrier (dm_rq_barrier_work) which
-	 * can be kicked until md->queue is stopped.  So stop md->queue before
-	 * flushing md->wq.
+	 * Stop md->queue before flushing md->wq in case request-based
+	 * dm defers requests to md->wq from md->queue.
 	 */
 	if (dm_request_based(md))
 		stop_queue(md->queue);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index ba19060..8a2f767 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -294,8 +294,8 @@
 	dev_info_t *tmp_dev;
 	sector_t start_sector;
 
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
-		md_barrier_request(mddev, bio);
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
 		return 0;
 	}
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f20d13e..2258151 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -36,7 +36,7 @@
 #include <linux/blkdev.h>
 #include <linux/sysctl.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/buffer_head.h> /* for invalidate_bdev */
 #include <linux/poll.h>
 #include <linux/ctype.h>
@@ -57,6 +57,7 @@
 #define DEBUG 0
 #define dprintk(x...) ((void)(DEBUG && printk(x)))
 
+static DEFINE_MUTEX(md_mutex);
 
 #ifndef MODULE
 static void autostart_arrays(int part);
@@ -226,12 +227,12 @@
 		return 0;
 	}
 	rcu_read_lock();
-	if (mddev->suspended || mddev->barrier) {
+	if (mddev->suspended) {
 		DEFINE_WAIT(__wait);
 		for (;;) {
 			prepare_to_wait(&mddev->sb_wait, &__wait,
 					TASK_UNINTERRUPTIBLE);
-			if (!mddev->suspended && !mddev->barrier)
+			if (!mddev->suspended)
 				break;
 			rcu_read_unlock();
 			schedule();
@@ -282,40 +283,29 @@
 
 int mddev_congested(mddev_t *mddev, int bits)
 {
-	if (mddev->barrier)
-		return 1;
 	return mddev->suspended;
 }
 EXPORT_SYMBOL(mddev_congested);
 
 /*
- * Generic barrier handling for md
+ * Generic flush handling for md
  */
 
-#define POST_REQUEST_BARRIER ((void*)1)
-
-static void md_end_barrier(struct bio *bio, int err)
+static void md_end_flush(struct bio *bio, int err)
 {
 	mdk_rdev_t *rdev = bio->bi_private;
 	mddev_t *mddev = rdev->mddev;
-	if (err == -EOPNOTSUPP && mddev->barrier != POST_REQUEST_BARRIER)
-		set_bit(BIO_EOPNOTSUPP, &mddev->barrier->bi_flags);
 
 	rdev_dec_pending(rdev, mddev);
 
 	if (atomic_dec_and_test(&mddev->flush_pending)) {
-		if (mddev->barrier == POST_REQUEST_BARRIER) {
-			/* This was a post-request barrier */
-			mddev->barrier = NULL;
-			wake_up(&mddev->sb_wait);
-		} else
-			/* The pre-request barrier has finished */
-			schedule_work(&mddev->barrier_work);
+		/* The pre-request flush has finished */
+		schedule_work(&mddev->flush_work);
 	}
 	bio_put(bio);
 }
 
-static void submit_barriers(mddev_t *mddev)
+static void submit_flushes(mddev_t *mddev)
 {
 	mdk_rdev_t *rdev;
 
@@ -332,60 +322,56 @@
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
 			bi = bio_alloc(GFP_KERNEL, 0);
-			bi->bi_end_io = md_end_barrier;
+			bi->bi_end_io = md_end_flush;
 			bi->bi_private = rdev;
 			bi->bi_bdev = rdev->bdev;
 			atomic_inc(&mddev->flush_pending);
-			submit_bio(WRITE_BARRIER, bi);
+			submit_bio(WRITE_FLUSH, bi);
 			rcu_read_lock();
 			rdev_dec_pending(rdev, mddev);
 		}
 	rcu_read_unlock();
 }
 
-static void md_submit_barrier(struct work_struct *ws)
+static void md_submit_flush_data(struct work_struct *ws)
 {
-	mddev_t *mddev = container_of(ws, mddev_t, barrier_work);
-	struct bio *bio = mddev->barrier;
+	mddev_t *mddev = container_of(ws, mddev_t, flush_work);
+	struct bio *bio = mddev->flush_bio;
 
 	atomic_set(&mddev->flush_pending, 1);
 
-	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
-		bio_endio(bio, -EOPNOTSUPP);
-	else if (bio->bi_size == 0)
+	if (bio->bi_size == 0)
 		/* an empty barrier - all done */
 		bio_endio(bio, 0);
 	else {
-		bio->bi_rw &= ~REQ_HARDBARRIER;
+		bio->bi_rw &= ~REQ_FLUSH;
 		if (mddev->pers->make_request(mddev, bio))
 			generic_make_request(bio);
-		mddev->barrier = POST_REQUEST_BARRIER;
-		submit_barriers(mddev);
 	}
 	if (atomic_dec_and_test(&mddev->flush_pending)) {
-		mddev->barrier = NULL;
+		mddev->flush_bio = NULL;
 		wake_up(&mddev->sb_wait);
 	}
 }
 
-void md_barrier_request(mddev_t *mddev, struct bio *bio)
+void md_flush_request(mddev_t *mddev, struct bio *bio)
 {
 	spin_lock_irq(&mddev->write_lock);
 	wait_event_lock_irq(mddev->sb_wait,
-			    !mddev->barrier,
+			    !mddev->flush_bio,
 			    mddev->write_lock, /*nothing*/);
-	mddev->barrier = bio;
+	mddev->flush_bio = bio;
 	spin_unlock_irq(&mddev->write_lock);
 
 	atomic_set(&mddev->flush_pending, 1);
-	INIT_WORK(&mddev->barrier_work, md_submit_barrier);
+	INIT_WORK(&mddev->flush_work, md_submit_flush_data);
 
-	submit_barriers(mddev);
+	submit_flushes(mddev);
 
 	if (atomic_dec_and_test(&mddev->flush_pending))
-		schedule_work(&mddev->barrier_work);
+		schedule_work(&mddev->flush_work);
 }
-EXPORT_SYMBOL(md_barrier_request);
+EXPORT_SYMBOL(md_flush_request);
 
 /* Support for plugging.
  * This mirrors the plugging support in request_queue, but does not
@@ -696,31 +682,6 @@
 	bio_put(bio);
 }
 
-static void super_written_barrier(struct bio *bio, int error)
-{
-	struct bio *bio2 = bio->bi_private;
-	mdk_rdev_t *rdev = bio2->bi_private;
-	mddev_t *mddev = rdev->mddev;
-
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
-	    error == -EOPNOTSUPP) {
-		unsigned long flags;
-		/* barriers don't appear to be supported :-( */
-		set_bit(BarriersNotsupp, &rdev->flags);
-		mddev->barriers_work = 0;
-		spin_lock_irqsave(&mddev->write_lock, flags);
-		bio2->bi_next = mddev->biolist;
-		mddev->biolist = bio2;
-		spin_unlock_irqrestore(&mddev->write_lock, flags);
-		wake_up(&mddev->sb_wait);
-		bio_put(bio);
-	} else {
-		bio_put(bio2);
-		bio->bi_private = rdev;
-		super_written(bio, error);
-	}
-}
-
 void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
 		   sector_t sector, int size, struct page *page)
 {
@@ -729,51 +690,28 @@
 	 * and decrement it on completion, waking up sb_wait
 	 * if zero is reached.
 	 * If an error occurred, call md_error
-	 *
-	 * As we might need to resubmit the request if REQ_HARDBARRIER
-	 * causes ENOTSUPP, we allocate a spare bio...
 	 */
 	struct bio *bio = bio_alloc(GFP_NOIO, 1);
-	int rw = REQ_WRITE | REQ_SYNC | REQ_UNPLUG;
 
 	bio->bi_bdev = rdev->bdev;
 	bio->bi_sector = sector;
 	bio_add_page(bio, page, size, 0);
 	bio->bi_private = rdev;
 	bio->bi_end_io = super_written;
-	bio->bi_rw = rw;
 
 	atomic_inc(&mddev->pending_writes);
-	if (!test_bit(BarriersNotsupp, &rdev->flags)) {
-		struct bio *rbio;
-		rw |= REQ_HARDBARRIER;
-		rbio = bio_clone(bio, GFP_NOIO);
-		rbio->bi_private = bio;
-		rbio->bi_end_io = super_written_barrier;
-		submit_bio(rw, rbio);
-	} else
-		submit_bio(rw, bio);
+	submit_bio(REQ_WRITE | REQ_SYNC | REQ_UNPLUG | REQ_FLUSH | REQ_FUA,
+		   bio);
 }
 
 void md_super_wait(mddev_t *mddev)
 {
-	/* wait for all superblock writes that were scheduled to complete.
-	 * if any had to be retried (due to BARRIER problems), retry them
-	 */
+	/* wait for all superblock writes that were scheduled to complete */
 	DEFINE_WAIT(wq);
 	for(;;) {
 		prepare_to_wait(&mddev->sb_wait, &wq, TASK_UNINTERRUPTIBLE);
 		if (atomic_read(&mddev->pending_writes)==0)
 			break;
-		while (mddev->biolist) {
-			struct bio *bio;
-			spin_lock_irq(&mddev->write_lock);
-			bio = mddev->biolist;
-			mddev->biolist = bio->bi_next ;
-			bio->bi_next = NULL;
-			spin_unlock_irq(&mddev->write_lock);
-			submit_bio(bio->bi_rw, bio);
-		}
 		schedule();
 	}
 	finish_wait(&mddev->sb_wait, &wq);
@@ -1070,7 +1008,6 @@
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
-	clear_bit(BarriersNotsupp, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
 		mddev->major_version = 0;
@@ -1485,7 +1422,6 @@
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
-	clear_bit(BarriersNotsupp, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
 		mddev->major_version = 1;
@@ -4504,7 +4440,6 @@
 	/* may be over-ridden by personality */
 	mddev->resync_max_sectors = mddev->dev_sectors;
 
-	mddev->barriers_work = 1;
 	mddev->ok_start_degraded = start_dirty_degraded;
 
 	if (start_readonly && mddev->ro == 0)
@@ -4683,7 +4618,6 @@
 	mddev->recovery = 0;
 	mddev->in_sync = 0;
 	mddev->degraded = 0;
-	mddev->barriers_work = 0;
 	mddev->safemode = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
@@ -5951,7 +5885,7 @@
 	mddev_t *mddev = mddev_find(bdev->bd_dev);
 	int err;
 
-	lock_kernel();
+	mutex_lock(&md_mutex);
 	if (mddev->gendisk != bdev->bd_disk) {
 		/* we are racing with mddev_put which is discarding this
 		 * bd_disk.
@@ -5960,7 +5894,7 @@
 		/* Wait until bdev->bd_disk is definitely gone */
 		flush_scheduled_work();
 		/* Then retry the open from the top */
-		unlock_kernel();
+		mutex_unlock(&md_mutex);
 		return -ERESTARTSYS;
 	}
 	BUG_ON(mddev != bdev->bd_disk->private_data);
@@ -5974,7 +5908,7 @@
 
 	check_disk_size_change(mddev->gendisk, bdev);
  out:
-	unlock_kernel();
+	mutex_unlock(&md_mutex);
 	return err;
 }
 
@@ -5983,10 +5917,10 @@
  	mddev_t *mddev = disk->private_data;
 
 	BUG_ON(!mddev);
-	lock_kernel();
+	mutex_lock(&md_mutex);
 	atomic_dec(&mddev->openers);
 	mddev_put(mddev);
-	unlock_kernel();
+	mutex_unlock(&md_mutex);
 
 	return 0;
 }
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 3931299..112a2c3 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -87,7 +87,6 @@
 #define	Faulty		1		/* device is known to have a fault */
 #define	In_sync		2		/* device is in_sync with rest of array */
 #define	WriteMostly	4		/* Avoid reading if at all possible */
-#define	BarriersNotsupp	5		/* REQ_HARDBARRIER is not supported */
 #define	AllReserved	6		/* If whole device is reserved for
 					 * one array */
 #define	AutoDetected	7		/* added by auto-detect */
@@ -273,13 +272,6 @@
 	int				degraded;	/* whether md should consider
 							 * adding a spare
 							 */
-	int				barriers_work;	/* initialised to true, cleared as soon
-							 * as a barrier request to slave
-							 * fails.  Only supported
-							 */
-	struct bio			*biolist; 	/* bios that need to be retried
-							 * because REQ_HARDBARRIER is not supported
-							 */
 
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
@@ -339,16 +331,13 @@
 	struct attribute_group		*to_remove;
 	struct plug_handle		*plug; /* if used by personality */
 
-	/* Generic barrier handling.
-	 * If there is a pending barrier request, all other
-	 * writes are blocked while the devices are flushed.
-	 * The last to finish a flush schedules a worker to
-	 * submit the barrier request (without the barrier flag),
-	 * then submit more flush requests.
+	/* Generic flush handling.
+	 * The last to finish preflush schedules a worker to submit
+	 * the rest of the request (without the REQ_FLUSH flag).
 	 */
-	struct bio *barrier;
+	struct bio *flush_bio;
 	atomic_t flush_pending;
-	struct work_struct barrier_work;
+	struct work_struct flush_work;
 	struct work_struct event_work;	/* used by dm to report failure event */
 };
 
@@ -502,7 +491,7 @@
 extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
 
 extern int mddev_congested(mddev_t *mddev, int bits);
-extern void md_barrier_request(mddev_t *mddev, struct bio *bio);
+extern void md_flush_request(mddev_t *mddev, struct bio *bio);
 extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
 			   sector_t sector, int size, struct page *page);
 extern void md_super_wait(mddev_t *mddev);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 0307d21..6d7ddf3 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -142,8 +142,8 @@
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
 
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
-		md_barrier_request(mddev, bio);
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
 		return 0;
 	}
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 6f7af46..a39f4c3 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -483,8 +483,8 @@
 	struct strip_zone *zone;
 	mdk_rdev_t *tmp_dev;
 
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
-		md_barrier_request(mddev, bio);
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
 		return 0;
 	}
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 0b830bb..378a258 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -319,83 +319,74 @@
 		if (r1_bio->bios[mirror] == bio)
 			break;
 
-	if (error == -EOPNOTSUPP && test_bit(R1BIO_Barrier, &r1_bio->state)) {
-		set_bit(BarriersNotsupp, &conf->mirrors[mirror].rdev->flags);
-		set_bit(R1BIO_BarrierRetry, &r1_bio->state);
-		r1_bio->mddev->barriers_work = 0;
-		/* Don't rdev_dec_pending in this branch - keep it for the retry */
-	} else {
+	/*
+	 * 'one mirror IO has finished' event handler:
+	 */
+	r1_bio->bios[mirror] = NULL;
+	to_put = bio;
+	if (!uptodate) {
+		md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
+		/* an I/O failed, we can't clear the bitmap */
+		set_bit(R1BIO_Degraded, &r1_bio->state);
+	} else
 		/*
-		 * this branch is our 'one mirror IO has finished' event handler:
+		 * Set R1BIO_Uptodate in our master bio, so that we
+		 * will return a good error code for to the higher
+		 * levels even if IO on some other mirrored buffer
+		 * fails.
+		 *
+		 * The 'master' represents the composite IO operation
+		 * to user-side. So if something waits for IO, then it
+		 * will wait for the 'master' bio.
 		 */
-		r1_bio->bios[mirror] = NULL;
-		to_put = bio;
-		if (!uptodate) {
-			md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
-			/* an I/O failed, we can't clear the bitmap */
-			set_bit(R1BIO_Degraded, &r1_bio->state);
-		} else
-			/*
-			 * Set R1BIO_Uptodate in our master bio, so that
-			 * we will return a good error code for to the higher
-			 * levels even if IO on some other mirrored buffer fails.
-			 *
-			 * The 'master' represents the composite IO operation to
-			 * user-side. So if something waits for IO, then it will
-			 * wait for the 'master' bio.
-			 */
-			set_bit(R1BIO_Uptodate, &r1_bio->state);
+		set_bit(R1BIO_Uptodate, &r1_bio->state);
 
-		update_head_pos(mirror, r1_bio);
+	update_head_pos(mirror, r1_bio);
 
-		if (behind) {
-			if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
-				atomic_dec(&r1_bio->behind_remaining);
+	if (behind) {
+		if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
+			atomic_dec(&r1_bio->behind_remaining);
 
-			/* In behind mode, we ACK the master bio once the I/O has safely
-			 * reached all non-writemostly disks. Setting the Returned bit
-			 * ensures that this gets done only once -- we don't ever want to
-			 * return -EIO here, instead we'll wait */
-
-			if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
-			    test_bit(R1BIO_Uptodate, &r1_bio->state)) {
-				/* Maybe we can return now */
-				if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
-					struct bio *mbio = r1_bio->master_bio;
-					PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
-					       (unsigned long long) mbio->bi_sector,
-					       (unsigned long long) mbio->bi_sector +
-					       (mbio->bi_size >> 9) - 1);
-					bio_endio(mbio, 0);
-				}
+		/*
+		 * In behind mode, we ACK the master bio once the I/O
+		 * has safely reached all non-writemostly
+		 * disks. Setting the Returned bit ensures that this
+		 * gets done only once -- we don't ever want to return
+		 * -EIO here, instead we'll wait
+		 */
+		if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
+		    test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+			/* Maybe we can return now */
+			if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
+				struct bio *mbio = r1_bio->master_bio;
+				PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
+				       (unsigned long long) mbio->bi_sector,
+				       (unsigned long long) mbio->bi_sector +
+				       (mbio->bi_size >> 9) - 1);
+				bio_endio(mbio, 0);
 			}
 		}
-		rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
 	}
+	rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
+
 	/*
-	 *
 	 * Let's see if all mirrored write operations have finished
 	 * already.
 	 */
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		if (test_bit(R1BIO_BarrierRetry, &r1_bio->state))
-			reschedule_retry(r1_bio);
-		else {
-			/* it really is the end of this request */
-			if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
-				/* free extra copy of the data pages */
-				int i = bio->bi_vcnt;
-				while (i--)
-					safe_put_page(bio->bi_io_vec[i].bv_page);
-			}
-			/* clear the bitmap if all writes complete successfully */
-			bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
-					r1_bio->sectors,
-					!test_bit(R1BIO_Degraded, &r1_bio->state),
-					behind);
-			md_write_end(r1_bio->mddev);
-			raid_end_bio_io(r1_bio);
+		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
+			/* free extra copy of the data pages */
+			int i = bio->bi_vcnt;
+			while (i--)
+				safe_put_page(bio->bi_io_vec[i].bv_page);
 		}
+		/* clear the bitmap if all writes complete successfully */
+		bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
+				r1_bio->sectors,
+				!test_bit(R1BIO_Degraded, &r1_bio->state),
+				behind);
+		md_write_end(r1_bio->mddev);
+		raid_end_bio_io(r1_bio);
 	}
 
 	if (to_put)
@@ -788,16 +779,13 @@
 	struct page **behind_pages = NULL;
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
-	unsigned long do_barriers;
+	const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
 	mdk_rdev_t *blocked_rdev;
 
 	/*
 	 * Register the new request and wait if the reconstruction
 	 * thread has put up a bar for new requests.
 	 * Continue immediately if no resync is active currently.
-	 * We test barriers_work *after* md_write_start as md_write_start
-	 * may cause the first superblock write, and that will check out
-	 * if barriers work.
 	 */
 
 	md_write_start(mddev, bio); /* wait on superblock update early */
@@ -821,13 +809,6 @@
 		}
 		finish_wait(&conf->wait_barrier, &w);
 	}
-	if (unlikely(!mddev->barriers_work &&
-		     (bio->bi_rw & REQ_HARDBARRIER))) {
-		if (rw == WRITE)
-			md_write_end(mddev);
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
-	}
 
 	wait_barrier(conf);
 
@@ -959,10 +940,6 @@
 	atomic_set(&r1_bio->remaining, 0);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
-	do_barriers = bio->bi_rw & REQ_HARDBARRIER;
-	if (do_barriers)
-		set_bit(R1BIO_Barrier, &r1_bio->state);
-
 	bio_list_init(&bl);
 	for (i = 0; i < disks; i++) {
 		struct bio *mbio;
@@ -975,7 +952,7 @@
 		mbio->bi_sector	= r1_bio->sector + conf->mirrors[i].rdev->data_offset;
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
-		mbio->bi_rw = WRITE | do_barriers | do_sync;
+		mbio->bi_rw = WRITE | do_flush_fua | do_sync;
 		mbio->bi_private = r1_bio;
 
 		if (behind_pages) {
@@ -1634,41 +1611,6 @@
 		if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
 			sync_request_write(mddev, r1_bio);
 			unplug = 1;
-		} else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
-			/* some requests in the r1bio were REQ_HARDBARRIER
-			 * requests which failed with -EOPNOTSUPP.  Hohumm..
-			 * Better resubmit without the barrier.
-			 * We know which devices to resubmit for, because
-			 * all others have had their bios[] entry cleared.
-			 * We already have a nr_pending reference on these rdevs.
-			 */
-			int i;
-			const unsigned long do_sync = (r1_bio->master_bio->bi_rw & REQ_SYNC);
-			clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
-			clear_bit(R1BIO_Barrier, &r1_bio->state);
-			for (i=0; i < conf->raid_disks; i++)
-				if (r1_bio->bios[i])
-					atomic_inc(&r1_bio->remaining);
-			for (i=0; i < conf->raid_disks; i++)
-				if (r1_bio->bios[i]) {
-					struct bio_vec *bvec;
-					int j;
-
-					bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
-					/* copy pages from the failed bio, as
-					 * this might be a write-behind device */
-					__bio_for_each_segment(bvec, bio, j, 0)
-						bvec->bv_page = bio_iovec_idx(r1_bio->bios[i], j)->bv_page;
-					bio_put(r1_bio->bios[i]);
-					bio->bi_sector = r1_bio->sector +
-						conf->mirrors[i].rdev->data_offset;
-					bio->bi_bdev = conf->mirrors[i].rdev->bdev;
-					bio->bi_end_io = raid1_end_write_request;
-					bio->bi_rw = WRITE | do_sync;
-					bio->bi_private = r1_bio;
-					r1_bio->bios[i] = bio;
-					generic_make_request(bio);
-				}
 		} else {
 			int disk;
 
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 5f2d443..adf8cfd 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -117,8 +117,6 @@
 #define	R1BIO_IsSync	1
 #define	R1BIO_Degraded	2
 #define	R1BIO_BehindIO	3
-#define	R1BIO_Barrier	4
-#define R1BIO_BarrierRetry 5
 /* For write-behind requests, we call bi_end_io when
  * the last non-write-behind device completes, providing
  * any write was successful.  Otherwise we call when
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8471838..f0d082f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -800,12 +800,13 @@
 	int chunk_sects = conf->chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
+	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
 	struct bio_list bl;
 	unsigned long flags;
 	mdk_rdev_t *blocked_rdev;
 
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
-		md_barrier_request(mddev, bio);
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
 		return 0;
 	}
 
@@ -965,7 +966,7 @@
 			conf->mirrors[d].rdev->data_offset;
 		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
 		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync;
+		mbio->bi_rw = WRITE | do_sync | do_fua;
 		mbio->bi_private = r10_bio;
 
 		atomic_inc(&r10_bio->remaining);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 69b0a16..31140d1 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -506,9 +506,12 @@
 		int rw;
 		struct bio *bi;
 		mdk_rdev_t *rdev;
-		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
-			rw = WRITE;
-		else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
+		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
+			if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
+				rw = WRITE_FUA;
+			else
+				rw = WRITE;
+		} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
 			rw = READ;
 		else
 			continue;
@@ -1031,6 +1034,8 @@
 
 			while (wbi && wbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
+				if (wbi->bi_rw & REQ_FUA)
+					set_bit(R5_WantFUA, &dev->flags);
 				tx = async_copy_data(1, wbi, dev->page,
 					dev->sector, tx);
 				wbi = r5_next_bio(wbi, dev->sector);
@@ -1048,15 +1053,22 @@
 	int pd_idx = sh->pd_idx;
 	int qd_idx = sh->qd_idx;
 	int i;
+	bool fua = false;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
+	for (i = disks; i--; )
+		fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
+
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
-		if (dev->written || i == pd_idx || i == qd_idx)
+		if (dev->written || i == pd_idx || i == qd_idx) {
 			set_bit(R5_UPTODATE, &dev->flags);
+			if (fua)
+				set_bit(R5_WantFUA, &dev->flags);
+		}
 	}
 
 	if (sh->reconstruct_state == reconstruct_state_drain_run)
@@ -3281,7 +3293,7 @@
 
 	if (dec_preread_active) {
 		/* We delay this until after ops_run_io so that if make_request
-		 * is waiting on a barrier, it won't continue until the writes
+		 * is waiting on a flush, it won't continue until the writes
 		 * have actually been submitted.
 		 */
 		atomic_dec(&conf->preread_active_stripes);
@@ -3583,7 +3595,7 @@
 
 	if (dec_preread_active) {
 		/* We delay this until after ops_run_io so that if make_request
-		 * is waiting on a barrier, it won't continue until the writes
+		 * is waiting on a flush, it won't continue until the writes
 		 * have actually been submitted.
 		 */
 		atomic_dec(&conf->preread_active_stripes);
@@ -3978,14 +3990,8 @@
 	const int rw = bio_data_dir(bi);
 	int remaining;
 
-	if (unlikely(bi->bi_rw & REQ_HARDBARRIER)) {
-		/* Drain all pending writes.  We only really need
-		 * to ensure they have been submitted, but this is
-		 * easier.
-		 */
-		mddev->pers->quiesce(mddev, 1);
-		mddev->pers->quiesce(mddev, 0);
-		md_barrier_request(mddev, bi);
+	if (unlikely(bi->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bi);
 		return 0;
 	}
 
@@ -4103,7 +4109,7 @@
 			finish_wait(&conf->wait_for_overlap, &w);
 			set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
-			if (mddev->barrier && 
+			if ((bi->bi_rw & REQ_SYNC) &&
 			    !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 				atomic_inc(&conf->preread_active_stripes);
 			release_stripe(sh);
@@ -4126,13 +4132,6 @@
 		bio_endio(bi, 0);
 	}
 
-	if (mddev->barrier) {
-		/* We need to wait for the stripes to all be handled.
-		 * So: wait for preread_active_stripes to drop to 0.
-		 */
-		wait_event(mddev->thread->wqueue,
-			   atomic_read(&conf->preread_active_stripes) == 0);
-	}
 	return 0;
 }
 
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 36eaed5..2ace058 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -275,6 +275,7 @@
 				    * filling
 				    */
 #define R5_Wantdrain	13 /* dev->towrite needs to be drained */
+#define R5_WantFUA	14	/* Write should be FUA */
 /*
  * Write method
  */
diff --git a/drivers/media/IR/imon.c b/drivers/media/IR/imon.c
index c185422..faed5a3 100644
--- a/drivers/media/IR/imon.c
+++ b/drivers/media/IR/imon.c
@@ -151,7 +151,8 @@
 	.owner		= THIS_MODULE,
 	.open		= &display_open,
 	.write		= &vfd_write,
-	.release	= &display_close
+	.release	= &display_close,
+	.llseek		= noop_llseek,
 };
 
 /* lcd character device file operations */
@@ -159,7 +160,8 @@
 	.owner		= THIS_MODULE,
 	.open		= &display_open,
 	.write		= &lcd_write,
-	.release	= &display_close
+	.release	= &display_close,
+	.llseek		= noop_llseek,
 };
 
 enum {
diff --git a/drivers/media/IR/ir-lirc-codec.c b/drivers/media/IR/ir-lirc-codec.c
index e63f757..1983cd3 100644
--- a/drivers/media/IR/ir-lirc-codec.c
+++ b/drivers/media/IR/ir-lirc-codec.c
@@ -235,6 +235,7 @@
 	.poll		= lirc_dev_fop_poll,
 	.open		= lirc_dev_fop_open,
 	.release	= lirc_dev_fop_close,
+	.llseek		= no_llseek,
 };
 
 static int ir_lirc_register(struct input_dev *input_dev)
diff --git a/drivers/media/IR/lirc_dev.c b/drivers/media/IR/lirc_dev.c
index 899891b..0acf639 100644
--- a/drivers/media/IR/lirc_dev.c
+++ b/drivers/media/IR/lirc_dev.c
@@ -163,6 +163,7 @@
 	.unlocked_ioctl	= lirc_dev_fop_ioctl,
 	.open		= lirc_dev_fop_open,
 	.release	= lirc_dev_fop_close,
+	.llseek		= noop_llseek,
 };
 
 static int lirc_cdev_add(struct irctl *ir)
@@ -460,6 +461,8 @@
 
 	mutex_unlock(&lirc_dev_lock);
 
+	nonseekable_open(inode, file);
+
 	return retval;
 }
 EXPORT_SYMBOL(lirc_dev_fop_open);
diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig
index a28541b..bad2ced 100644
--- a/drivers/media/Kconfig
+++ b/drivers/media/Kconfig
@@ -19,6 +19,7 @@
 
 config VIDEO_DEV
 	tristate "Video For Linux"
+	depends on BKL # used in many drivers for ioctl handling, need to kill
 	---help---
 	  V4L core support for video capture and overlay devices, webcams and
 	  AM/FM radio cards.
diff --git a/drivers/media/dvb/bt8xx/dst_ca.c b/drivers/media/dvb/bt8xx/dst_ca.c
index cf87051..48e48e8 100644
--- a/drivers/media/dvb/bt8xx/dst_ca.c
+++ b/drivers/media/dvb/bt8xx/dst_ca.c
@@ -22,7 +22,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/string.h>
 #include <linux/dvb/ca.h>
 #include "dvbdev.h"
@@ -52,6 +52,7 @@
 } while(0)
 
 
+static DEFINE_MUTEX(dst_ca_mutex);
 static unsigned int verbose = 5;
 module_param(verbose, int, 0644);
 MODULE_PARM_DESC(verbose, "verbose startup messages, default is 1 (yes)");
@@ -564,7 +565,7 @@
 	void __user *arg = (void __user *)ioctl_arg;
 	int result = 0;
 
-	lock_kernel();
+	mutex_lock(&dst_ca_mutex);
 	dvbdev = file->private_data;
 	state = (struct dst_state *)dvbdev->priv;
 	p_ca_message = kmalloc(sizeof (struct ca_msg), GFP_KERNEL);
@@ -652,7 +653,7 @@
 	kfree (p_ca_slot_info);
 	kfree (p_ca_caps);
 
-	unlock_kernel();
+	mutex_unlock(&dst_ca_mutex);
 	return result;
 }
 
@@ -694,7 +695,8 @@
 	.open = dst_ca_open,
 	.release = dst_ca_release,
 	.read = dst_ca_read,
-	.write = dst_ca_write
+	.write = dst_ca_write,
+	.llseek = noop_llseek,
 };
 
 static struct dvb_device dvbdev_ca = {
diff --git a/drivers/media/dvb/dvb-core/dmxdev.c b/drivers/media/dvb/dvb-core/dmxdev.c
index 0042306..ad1f61d 100644
--- a/drivers/media/dvb/dvb-core/dmxdev.c
+++ b/drivers/media/dvb/dvb-core/dmxdev.c
@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/poll.h>
 #include <linux/ioctl.h>
 #include <linux/wait.h>
@@ -1088,13 +1087,7 @@
 static long dvb_demux_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg)
 {
-	int ret;
-
-	lock_kernel();
-	ret = dvb_usercopy(file, cmd, arg, dvb_demux_do_ioctl);
-	unlock_kernel();
-
-	return ret;
+	return dvb_usercopy(file, cmd, arg, dvb_demux_do_ioctl);
 }
 
 static unsigned int dvb_demux_poll(struct file *file, poll_table *wait)
@@ -1150,6 +1143,7 @@
 	.open = dvb_demux_open,
 	.release = dvb_demux_release,
 	.poll = dvb_demux_poll,
+	.llseek = default_llseek,
 };
 
 static struct dvb_device dvbdev_demux = {
@@ -1186,13 +1180,7 @@
 static long dvb_dvr_ioctl(struct file *file,
 			 unsigned int cmd, unsigned long arg)
 {
-	int ret;
-
-	lock_kernel();
-	ret = dvb_usercopy(file, cmd, arg, dvb_dvr_do_ioctl);
-	unlock_kernel();
-
-	return ret;
+	return dvb_usercopy(file, cmd, arg, dvb_dvr_do_ioctl);
 }
 
 static unsigned int dvb_dvr_poll(struct file *file, poll_table *wait)
@@ -1225,6 +1213,7 @@
 	.open = dvb_dvr_open,
 	.release = dvb_dvr_release,
 	.poll = dvb_dvr_poll,
+	.llseek = default_llseek,
 };
 
 static struct dvb_device dvbdev_dvr = {
diff --git a/drivers/media/dvb/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb/dvb-core/dvb_ca_en50221.c
index cb97e6b..4d0646d 100644
--- a/drivers/media/dvb/dvb-core/dvb_ca_en50221.c
+++ b/drivers/media/dvb/dvb-core/dvb_ca_en50221.c
@@ -1259,13 +1259,7 @@
 static long dvb_ca_en50221_io_ioctl(struct file *file,
 				    unsigned int cmd, unsigned long arg)
 {
-	int ret;
-
-	lock_kernel();
-	ret = dvb_usercopy(file, cmd, arg, dvb_ca_en50221_io_do_ioctl);
-	unlock_kernel();
-
-	return ret;
+	return dvb_usercopy(file, cmd, arg, dvb_ca_en50221_io_do_ioctl);
 }
 
 
@@ -1628,6 +1622,7 @@
 	.open = dvb_ca_en50221_io_open,
 	.release = dvb_ca_en50221_io_release,
 	.poll = dvb_ca_en50221_io_poll,
+	.llseek = noop_llseek,
 };
 
 static struct dvb_device dvbdev_ca = {
diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.c b/drivers/media/dvb/dvb-core/dvb_frontend.c
index 4d45b7d..970c9b8 100644
--- a/drivers/media/dvb/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb/dvb-core/dvb_frontend.c
@@ -2034,7 +2034,8 @@
 	.unlocked_ioctl	= dvb_generic_ioctl,
 	.poll		= dvb_frontend_poll,
 	.open		= dvb_frontend_open,
-	.release	= dvb_frontend_release
+	.release	= dvb_frontend_release,
+	.llseek		= noop_llseek,
 };
 
 int dvb_register_frontend(struct dvb_adapter* dvb,
diff --git a/drivers/media/dvb/dvb-core/dvb_net.c b/drivers/media/dvb/dvb-core/dvb_net.c
index 6c3a8a0..4df42aa 100644
--- a/drivers/media/dvb/dvb-core/dvb_net.c
+++ b/drivers/media/dvb/dvb-core/dvb_net.c
@@ -59,7 +59,6 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/dvb/net.h>
-#include <linux/smp_lock.h>
 #include <linux/uio.h>
 #include <asm/uaccess.h>
 #include <linux/crc32.h>
@@ -1445,13 +1444,7 @@
 static long dvb_net_ioctl(struct file *file,
 	      unsigned int cmd, unsigned long arg)
 {
-	int ret;
-
-	lock_kernel();
-	ret = dvb_usercopy(file, cmd, arg, dvb_net_do_ioctl);
-	unlock_kernel();
-
-	return ret;
+	return dvb_usercopy(file, cmd, arg, dvb_net_do_ioctl);
 }
 
 static int dvb_net_close(struct inode *inode, struct file *file)
@@ -1475,6 +1468,7 @@
 	.unlocked_ioctl = dvb_net_ioctl,
 	.open =	dvb_generic_open,
 	.release = dvb_net_close,
+	.llseek = noop_llseek,
 };
 
 static struct dvb_device dvbdev_net = {
diff --git a/drivers/media/dvb/dvb-core/dvbdev.c b/drivers/media/dvb/dvb-core/dvbdev.c
index b915c39..f732877 100644
--- a/drivers/media/dvb/dvb-core/dvbdev.c
+++ b/drivers/media/dvb/dvb-core/dvbdev.c
@@ -32,9 +32,9 @@
 #include <linux/fs.h>
 #include <linux/cdev.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include "dvbdev.h"
 
+static DEFINE_MUTEX(dvbdev_mutex);
 static int dvbdev_debug;
 
 module_param(dvbdev_debug, int, 0644);
@@ -68,7 +68,7 @@
 {
 	struct dvb_device *dvbdev;
 
-	lock_kernel();
+	mutex_lock(&dvbdev_mutex);
 	down_read(&minor_rwsem);
 	dvbdev = dvb_minors[iminor(inode)];
 
@@ -91,12 +91,12 @@
 		}
 		fops_put(old_fops);
 		up_read(&minor_rwsem);
-		unlock_kernel();
+		mutex_unlock(&dvbdev_mutex);
 		return err;
 	}
 fail:
 	up_read(&minor_rwsem);
-	unlock_kernel();
+	mutex_unlock(&dvbdev_mutex);
 	return -ENODEV;
 }
 
@@ -105,6 +105,7 @@
 {
 	.owner =	THIS_MODULE,
 	.open =		dvb_device_open,
+	.llseek =	noop_llseek,
 };
 
 static struct cdev dvb_device_cdev;
@@ -158,7 +159,6 @@
 		       unsigned int cmd, unsigned long arg)
 {
 	struct dvb_device *dvbdev = file->private_data;
-	int ret;
 
 	if (!dvbdev)
 		return -ENODEV;
@@ -166,11 +166,7 @@
 	if (!dvbdev->kernel_ioctl)
 		return -EINVAL;
 
-	lock_kernel();
-	ret = dvb_usercopy(file, cmd, arg, dvbdev->kernel_ioctl);
-	unlock_kernel();
-
-	return ret;
+	return dvb_usercopy(file, cmd, arg, dvbdev->kernel_ioctl);
 }
 EXPORT_SYMBOL(dvb_generic_ioctl);
 
@@ -421,8 +417,10 @@
 	}
 
 	/* call driver */
+	mutex_lock(&dvbdev_mutex);
 	if ((err = func(file, cmd, parg)) == -ENOIOCTLCMD)
 		err = -EINVAL;
+	mutex_unlock(&dvbdev_mutex);
 
 	if (err < 0)
 		goto out;
diff --git a/drivers/media/dvb/firewire/firedtv-ci.c b/drivers/media/dvb/firewire/firedtv-ci.c
index d3c2cf6..8ffb565 100644
--- a/drivers/media/dvb/firewire/firedtv-ci.c
+++ b/drivers/media/dvb/firewire/firedtv-ci.c
@@ -220,6 +220,7 @@
 	.open		= dvb_generic_open,
 	.release	= dvb_generic_release,
 	.poll		= fdtv_ca_io_poll,
+	.llseek		= noop_llseek,
 };
 
 static struct dvb_device fdtv_ca = {
diff --git a/drivers/media/dvb/ttpci/av7110.c b/drivers/media/dvb/ttpci/av7110.c
index a6be529..893fbc5 100644
--- a/drivers/media/dvb/ttpci/av7110.c
+++ b/drivers/media/dvb/ttpci/av7110.c
@@ -730,6 +730,7 @@
 	.unlocked_ioctl	= dvb_generic_ioctl,
 	.open		= dvb_generic_open,
 	.release	= dvb_generic_release,
+	.llseek		= noop_llseek,
 };
 
 static struct dvb_device dvbdev_osd = {
diff --git a/drivers/media/dvb/ttpci/av7110_av.c b/drivers/media/dvb/ttpci/av7110_av.c
index 13efba9..6ef3996 100644
--- a/drivers/media/dvb/ttpci/av7110_av.c
+++ b/drivers/media/dvb/ttpci/av7110_av.c
@@ -1521,6 +1521,7 @@
 	.open		= dvb_video_open,
 	.release	= dvb_video_release,
 	.poll		= dvb_video_poll,
+	.llseek		= noop_llseek,
 };
 
 static struct dvb_device dvbdev_video = {
@@ -1539,6 +1540,7 @@
 	.open		= dvb_audio_open,
 	.release	= dvb_audio_release,
 	.poll		= dvb_audio_poll,
+	.llseek		= noop_llseek,
 };
 
 static struct dvb_device dvbdev_audio = {
diff --git a/drivers/media/dvb/ttpci/av7110_ca.c b/drivers/media/dvb/ttpci/av7110_ca.c
index 4eba35a..43f61f2 100644
--- a/drivers/media/dvb/ttpci/av7110_ca.c
+++ b/drivers/media/dvb/ttpci/av7110_ca.c
@@ -353,6 +353,7 @@
 	.open		= dvb_ca_open,
 	.release	= dvb_generic_release,
 	.poll		= dvb_ca_poll,
+	.llseek		= default_llseek,
 };
 
 static struct dvb_device dvbdev_ca = {
diff --git a/drivers/media/dvb/ttpci/av7110_ir.c b/drivers/media/dvb/ttpci/av7110_ir.c
index b070e88..908f272 100644
--- a/drivers/media/dvb/ttpci/av7110_ir.c
+++ b/drivers/media/dvb/ttpci/av7110_ir.c
@@ -312,6 +312,7 @@
 static const struct file_operations av7110_ir_proc_fops = {
 	.owner		= THIS_MODULE,
 	.write		= av7110_ir_proc_write,
+	.llseek		= noop_llseek,
 };
 
 /* interrupt handler */
diff --git a/drivers/media/video/dabusb.c b/drivers/media/video/dabusb.c
index 5b176bd..f3e25e9 100644
--- a/drivers/media/video/dabusb.c
+++ b/drivers/media/video/dabusb.c
@@ -32,7 +32,6 @@
 #include <linux/list.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <asm/uaccess.h>
 #include <asm/atomic.h>
@@ -621,7 +620,6 @@
 	if (devnum < DABUSB_MINOR || devnum >= (DABUSB_MINOR + NRDABUSB))
 		return -EIO;
 
-	lock_kernel();
 	s = &dabusb[devnum - DABUSB_MINOR];
 
 	dbg("dabusb_open");
@@ -630,21 +628,17 @@
 	while (!s->usbdev || s->opened) {
 		mutex_unlock(&s->mutex);
 
-		if (file->f_flags & O_NONBLOCK) {
+		if (file->f_flags & O_NONBLOCK)
 			return -EBUSY;
-		}
 		msleep_interruptible(500);
 
-		if (signal_pending (current)) {
-			unlock_kernel();
+		if (signal_pending (current))
 			return -EAGAIN;
-		}
 		mutex_lock(&s->mutex);
 	}
 	if (usb_set_interface (s->usbdev, _DABUSB_IF, 1) < 0) {
 		mutex_unlock(&s->mutex);
 		dev_err(&s->usbdev->dev, "set_interface failed\n");
-		unlock_kernel();
 		return -EINVAL;
 	}
 	s->opened = 1;
@@ -654,7 +648,6 @@
 	file->private_data = s;
 
 	r = nonseekable_open(inode, file);
-	unlock_kernel();
 	return r;
 }
 
@@ -689,17 +682,13 @@
 
 	dbg("dabusb_ioctl");
 
-	lock_kernel();
-	if (s->remove_pending) {
-		unlock_kernel();
+	if (s->remove_pending)
 		return -EIO;
-	}
 
 	mutex_lock(&s->mutex);
 
 	if (!s->usbdev) {
 		mutex_unlock(&s->mutex);
-		unlock_kernel();
 		return -EIO;
 	}
 
@@ -735,7 +724,6 @@
 		break;
 	}
 	mutex_unlock(&s->mutex);
-	unlock_kernel();
 	return ret;
 }
 
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index d3f1a08..02362ec 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -18,11 +18,12 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/memstick.h>
 
 #define DRIVER_NAME "mspro_block"
 
+static DEFINE_MUTEX(mspro_block_mutex);
 static int major;
 module_param(major, int, 0644);
 
@@ -180,7 +181,7 @@
 	struct mspro_block_data *msb = disk->private_data;
 	int rc = -ENXIO;
 
-	lock_kernel();
+	mutex_lock(&mspro_block_mutex);
 	mutex_lock(&mspro_block_disk_lock);
 
 	if (msb && msb->card) {
@@ -192,7 +193,7 @@
 	}
 
 	mutex_unlock(&mspro_block_disk_lock);
-	unlock_kernel();
+	mutex_unlock(&mspro_block_mutex);
 
 	return rc;
 }
@@ -225,9 +226,9 @@
 static int mspro_block_bd_release(struct gendisk *disk, fmode_t mode)
 {
 	int ret;
-	lock_kernel();
+	mutex_lock(&mspro_block_mutex);
 	ret = mspro_block_disk_release(disk);
-	unlock_kernel();
+	mutex_unlock(&mspro_block_mutex);
 	return ret;
 }
 
diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index d8ddfdf..a3856ed 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -54,7 +54,7 @@
 #include <linux/pci.h>
 #include <linux/delay.h>	/* for mdelay */
 #include <linux/miscdevice.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/compat.h>
 
 #include <asm/io.h>
@@ -83,6 +83,7 @@
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
 
+static DEFINE_MUTEX(mpctl_mutex);
 static u8 mptctl_id = MPT_MAX_PROTOCOL_DRIVERS;
 static u8 mptctl_taskmgmt_id = MPT_MAX_PROTOCOL_DRIVERS;
 
@@ -601,12 +602,12 @@
 	MPT_ADAPTER	*ioc;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&mpctl_mutex);
 	list_for_each_entry(ioc, &ioc_list, list)
 		ioc->aen_event_read_flag=0;
 
 	ret = fasync_helper(fd, filep, mode, &async_queue);
-	unlock_kernel();
+	mutex_unlock(&mpctl_mutex);
 	return ret;
 }
 
@@ -698,9 +699,9 @@
 mptctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	long ret;
-	lock_kernel();
+	mutex_lock(&mpctl_mutex);
 	ret = __mptctl_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&mpctl_mutex);
 	return ret;
 }
 
@@ -2926,7 +2927,7 @@
 static long compat_mpctl_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 {
 	long ret;
-	lock_kernel();
+	mutex_lock(&mpctl_mutex);
 	switch (cmd) {
 	case MPTIOCINFO:
 	case MPTIOCINFO1:
@@ -2951,7 +2952,7 @@
 		ret = -ENOIOCTLCMD;
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&mpctl_mutex);
 	return ret;
 }
 
diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c
index f0f1e66..f87a9d4 100644
--- a/drivers/message/i2o/i2o_block.c
+++ b/drivers/message/i2o/i2o_block.c
@@ -53,7 +53,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/i2o.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <linux/mempool.h>
 
@@ -69,6 +69,7 @@
 #define OSM_VERSION	"1.325"
 #define OSM_DESCRIPTION	"I2O Block Device OSM"
 
+static DEFINE_MUTEX(i2o_block_mutex);
 static struct i2o_driver i2o_block_driver;
 
 /* global Block OSM request mempool */
@@ -578,7 +579,7 @@
 	if (!dev->i2o_dev)
 		return -ENODEV;
 
-	lock_kernel();
+	mutex_lock(&i2o_block_mutex);
 	if (dev->power > 0x1f)
 		i2o_block_device_power(dev, 0x02);
 
@@ -587,7 +588,7 @@
 	i2o_block_device_lock(dev->i2o_dev, -1);
 
 	osm_debug("Ready.\n");
-	unlock_kernel();
+	mutex_unlock(&i2o_block_mutex);
 
 	return 0;
 };
@@ -618,7 +619,7 @@
 	if (!dev->i2o_dev)
 		return 0;
 
-	lock_kernel();
+	mutex_lock(&i2o_block_mutex);
 	i2o_block_device_flush(dev->i2o_dev);
 
 	i2o_block_device_unlock(dev->i2o_dev, -1);
@@ -629,7 +630,7 @@
 		operation = 0x24;
 
 	i2o_block_device_power(dev, operation);
-	unlock_kernel();
+	mutex_unlock(&i2o_block_mutex);
 
 	return 0;
 }
@@ -664,7 +665,7 @@
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	lock_kernel();
+	mutex_lock(&i2o_block_mutex);
 	switch (cmd) {
 	case BLKI2OGRSTRAT:
 		ret = put_user(dev->rcache, (int __user *)arg);
@@ -688,7 +689,7 @@
 		ret = 0;
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&i2o_block_mutex);
 
 	return ret;
 };
diff --git a/drivers/message/i2o/i2o_config.c b/drivers/message/i2o/i2o_config.c
index 068ba07..7d3cc57 100644
--- a/drivers/message/i2o/i2o_config.c
+++ b/drivers/message/i2o/i2o_config.c
@@ -31,7 +31,7 @@
  */
 
 #include <linux/miscdevice.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/compat.h>
 #include <linux/slab.h>
 
@@ -41,6 +41,7 @@
 
 #define SG_TABLESIZE		30
 
+static DEFINE_MUTEX(i2o_cfg_mutex);
 static long i2o_cfg_ioctl(struct file *, unsigned int, unsigned long);
 
 static spinlock_t i2o_config_lock;
@@ -741,7 +742,7 @@
 				 unsigned long arg)
 {
 	int ret;
-	lock_kernel();
+	mutex_lock(&i2o_cfg_mutex);
 	switch (cmd) {
 	case I2OGETIOPS:
 		ret = i2o_cfg_ioctl(file, cmd, arg);
@@ -753,7 +754,7 @@
 		ret = -ENOIOCTLCMD;
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&i2o_cfg_mutex);
 	return ret;
 }
 
@@ -981,7 +982,7 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&i2o_cfg_mutex);
 	switch (cmd) {
 	case I2OGETIOPS:
 		ret = i2o_cfg_getiops(arg);
@@ -1037,7 +1038,7 @@
 		osm_debug("unknown ioctl called!\n");
 		ret = -EINVAL;
 	}
-	unlock_kernel();
+	mutex_unlock(&i2o_cfg_mutex);
 	return ret;
 }
 
@@ -1051,7 +1052,7 @@
 	if (!tmp)
 		return -ENOMEM;
 
-	lock_kernel();
+	mutex_lock(&i2o_cfg_mutex);
 	file->private_data = (void *)(i2o_cfg_info_id++);
 	tmp->fp = file;
 	tmp->fasync = NULL;
@@ -1065,7 +1066,7 @@
 	spin_lock_irqsave(&i2o_config_lock, flags);
 	open_files = tmp;
 	spin_unlock_irqrestore(&i2o_config_lock, flags);
-	unlock_kernel();
+	mutex_unlock(&i2o_cfg_mutex);
 
 	return 0;
 }
@@ -1076,14 +1077,14 @@
 	struct i2o_cfg_info *p;
 	int ret = -EBADF;
 
-	lock_kernel();
+	mutex_lock(&i2o_cfg_mutex);
 	for (p = open_files; p; p = p->next)
 		if (p->q_id == id)
 			break;
 
 	if (p)
 		ret = fasync_helper(fd, fp, on, &p->fasync);
-	unlock_kernel();
+	mutex_unlock(&i2o_cfg_mutex);
 	return ret;
 }
 
@@ -1093,7 +1094,7 @@
 	struct i2o_cfg_info *p, **q;
 	unsigned long flags;
 
-	lock_kernel();
+	mutex_lock(&i2o_cfg_mutex);
 	spin_lock_irqsave(&i2o_config_lock, flags);
 	for (q = &open_files; (p = *q) != NULL; q = &p->next) {
 		if (p->q_id == id) {
@@ -1103,7 +1104,7 @@
 		}
 	}
 	spin_unlock_irqrestore(&i2o_config_lock, flags);
-	unlock_kernel();
+	mutex_unlock(&i2o_cfg_mutex);
 
 	return 0;
 }
diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c
index 66379b4..b048ecc 100644
--- a/drivers/mfd/ab3100-core.c
+++ b/drivers/mfd/ab3100-core.c
@@ -583,6 +583,7 @@
 static const struct file_operations ab3100_get_set_reg_fops = {
 	.open = ab3100_get_set_reg_open_file,
 	.write = ab3100_get_set_reg,
+	.llseek = noop_llseek,
 };
 
 static struct dentry *ab3100_dir;
diff --git a/drivers/mfd/ab8500-spi.c b/drivers/mfd/ab8500-spi.c
index e1c8b62..01b6d58 100644
--- a/drivers/mfd/ab8500-spi.c
+++ b/drivers/mfd/ab8500-spi.c
@@ -83,6 +83,11 @@
 	struct ab8500 *ab8500;
 	int ret;
 
+	spi->bits_per_word = 24;
+	ret = spi_setup(spi);
+	if (ret < 0)
+		return ret;
+
 	ab8500 = kzalloc(sizeof *ab8500, GFP_KERNEL);
 	if (!ab8500)
 		return -ENOMEM;
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index 097f24d..b9fda70 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -78,7 +78,7 @@
 	u8	irq_lines;		/* number of supported irq lines */
 
 	/* SIR ignored -- set interrupt, for testing only */
-	struct irq_data {
+	struct sih_irq_data {
 		u8	isr_offset;
 		u8	imr_offset;
 	} mask[2];
@@ -810,7 +810,7 @@
 	twl4030_irq_chip = dummy_irq_chip;
 	twl4030_irq_chip.name = "twl4030";
 
-	twl4030_sih_irq_chip.ack = dummy_irq_chip.ack;
+	twl4030_sih_irq_chip.irq_ack = dummy_irq_chip.irq_ack;
 
 	for (i = irq_base; i < irq_end; i++) {
 		set_irq_chip_and_handler(i, &twl4030_irq_chip,
diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c
index 557a8c2..69c1f2f 100644
--- a/drivers/misc/hpilo.c
+++ b/drivers/misc/hpilo.c
@@ -640,6 +640,7 @@
 	.poll		= ilo_poll,
 	.open 		= ilo_open,
 	.release 	= ilo_close,
+	.llseek		= noop_llseek,
 };
 
 static irqreturn_t ilo_isr(int irq, void *data)
diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c
index 8844a3f..af2497a 100644
--- a/drivers/misc/ibmasm/ibmasmfs.c
+++ b/drivers/misc/ibmasm/ibmasmfs.c
@@ -584,6 +584,7 @@
 	.release =	command_file_close,
 	.read =		command_file_read,
 	.write =	command_file_write,
+	.llseek =	generic_file_llseek,
 };
 
 static const struct file_operations event_fops = {
@@ -591,6 +592,7 @@
 	.release =	event_file_close,
 	.read =		event_file_read,
 	.write =	event_file_write,
+	.llseek =	generic_file_llseek,
 };
 
 static const struct file_operations r_heartbeat_fops = {
@@ -598,6 +600,7 @@
 	.release =	r_heartbeat_file_close,
 	.read =		r_heartbeat_file_read,
 	.write =	r_heartbeat_file_write,
+	.llseek =	generic_file_llseek,
 };
 
 static const struct file_operations remote_settings_fops = {
@@ -605,6 +608,7 @@
 	.release =	remote_settings_file_close,
 	.read =		remote_settings_file_read,
 	.write =	remote_settings_file_write,
+	.llseek =	generic_file_llseek,
 };
 
 
diff --git a/drivers/misc/iwmc3200top/debugfs.c b/drivers/misc/iwmc3200top/debugfs.c
index e9eda47..62fbaec 100644
--- a/drivers/misc/iwmc3200top/debugfs.c
+++ b/drivers/misc/iwmc3200top/debugfs.c
@@ -71,6 +71,7 @@
 	static const struct file_operations iwmct_dbgfs_##name##_ops = {  \
 		.read = iwmct_dbgfs_##name##_read,			\
 		.open = iwmct_dbgfs_open_file_generic,			\
+		.llseek = generic_file_llseek,				\
 	};
 
 #define DEBUGFS_WRITE_FILE_OPS(name)					\
@@ -78,6 +79,7 @@
 	static const struct file_operations iwmct_dbgfs_##name##_ops = {  \
 		.write = iwmct_dbgfs_##name##_write,			\
 		.open = iwmct_dbgfs_open_file_generic,			\
+		.llseek = generic_file_llseek,				\
 	};
 
 #define DEBUGFS_READ_WRITE_FILE_OPS(name)				\
@@ -87,6 +89,7 @@
 		.write = iwmct_dbgfs_##name##_write,			\
 		.read = iwmct_dbgfs_##name##_read,			\
 		.open = iwmct_dbgfs_open_file_generic,			\
+		.llseek = generic_file_llseek,				\
 	};
 
 
diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c
index ef34de7..343b5d8 100644
--- a/drivers/misc/lkdtm.c
+++ b/drivers/misc/lkdtm.c
@@ -575,30 +575,39 @@
 
 static const struct crash_entry crash_entries[] = {
 	{"DIRECT", {.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = direct_entry} },
 	{"INT_HARDWARE_ENTRY", {.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = int_hardware_entry} },
 	{"INT_HW_IRQ_EN", {.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = int_hw_irq_en} },
 	{"INT_TASKLET_ENTRY", {.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = int_tasklet_entry} },
 	{"FS_DEVRW", {.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = fs_devrw_entry} },
 	{"MEM_SWAPOUT", {.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = mem_swapout_entry} },
 	{"TIMERADD", {.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = timeradd_entry} },
 	{"SCSI_DISPATCH_CMD", {.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = scsi_dispatch_cmd_entry} },
 	{"IDE_CORE_CP",	{.read = lkdtm_debugfs_read,
+			.llseek = generic_file_llseek,
 			.open = lkdtm_debugfs_open,
 			.write = ide_core_cp_entry} },
 };
diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c
index 75ee0d3..4197a3c 100644
--- a/drivers/misc/phantom.c
+++ b/drivers/misc/phantom.c
@@ -24,7 +24,7 @@
 #include <linux/slab.h>
 #include <linux/phantom.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include <asm/atomic.h>
 #include <asm/io.h>
@@ -38,6 +38,7 @@
 #define PHB_RUNNING		1
 #define PHB_NOT_OH		2
 
+static DEFINE_MUTEX(phantom_mutex);
 static struct class *phantom_class;
 static int phantom_major;
 
@@ -215,17 +216,17 @@
 	struct phantom_device *dev = container_of(inode->i_cdev,
 			struct phantom_device, cdev);
 
-	lock_kernel();
+	mutex_lock(&phantom_mutex);
 	nonseekable_open(inode, file);
 
 	if (mutex_lock_interruptible(&dev->open_lock)) {
-		unlock_kernel();
+		mutex_unlock(&phantom_mutex);
 		return -ERESTARTSYS;
 	}
 
 	if (dev->opened) {
 		mutex_unlock(&dev->open_lock);
-		unlock_kernel();
+		mutex_unlock(&phantom_mutex);
 		return -EINVAL;
 	}
 
@@ -236,7 +237,7 @@
 	atomic_set(&dev->counter, 0);
 	dev->opened++;
 	mutex_unlock(&dev->open_lock);
-	unlock_kernel();
+	mutex_unlock(&phantom_mutex);
 	return 0;
 }
 
@@ -279,6 +280,7 @@
 	.unlocked_ioctl = phantom_ioctl,
 	.compat_ioctl = phantom_compat_ioctl,
 	.poll = phantom_poll,
+	.llseek = no_llseek,
 };
 
 static irqreturn_t phantom_isr(int irq, void *data)
diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c
index cb3b4d2..28852df 100644
--- a/drivers/misc/sgi-gru/grufile.c
+++ b/drivers/misc/sgi-gru/grufile.c
@@ -587,6 +587,7 @@
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= gru_file_unlocked_ioctl,
 	.mmap		= gru_file_mmap,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice gru_miscdev = {
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index d545f79..00073b7 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -29,7 +29,6 @@
 #include <linux/kdev_t.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/scatterlist.h>
 #include <linux/string_helpers.h>
 
@@ -51,6 +50,7 @@
 #define MMC_SHIFT	3
 #define MMC_NUM_MINORS	(256 >> MMC_SHIFT)
 
+static DEFINE_MUTEX(block_mutex);
 static DECLARE_BITMAP(dev_use, MMC_NUM_MINORS);
 
 /*
@@ -108,7 +108,7 @@
 	struct mmc_blk_data *md = mmc_blk_get(bdev->bd_disk);
 	int ret = -ENXIO;
 
-	lock_kernel();
+	mutex_lock(&block_mutex);
 	if (md) {
 		if (md->usage == 2)
 			check_disk_change(bdev);
@@ -119,7 +119,7 @@
 			ret = -EROFS;
 		}
 	}
-	unlock_kernel();
+	mutex_unlock(&block_mutex);
 
 	return ret;
 }
@@ -128,9 +128,9 @@
 {
 	struct mmc_blk_data *md = disk->private_data;
 
-	lock_kernel();
+	mutex_lock(&block_mutex);
 	mmc_blk_put(md);
-	unlock_kernel();
+	mutex_unlock(&block_mutex);
 	return 0;
 }
 
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index e876678..9c0b42b 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -128,7 +128,6 @@
 	mq->req = NULL;
 
 	blk_queue_prep_rq(mq->queue, mmc_prep_request);
-	blk_queue_ordered(mq->queue, QUEUE_ORDERED_DRAIN);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);
 	if (mmc_can_erase(card)) {
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mq->queue);
diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c
index 53cb380c..46bc6d7 100644
--- a/drivers/mmc/core/debugfs.c
+++ b/drivers/mmc/core/debugfs.c
@@ -245,6 +245,7 @@
 	.open		= mmc_ext_csd_open,
 	.read		= mmc_ext_csd_read,
 	.release	= mmc_ext_csd_release,
+	.llseek		= default_llseek,
 };
 
 void mmc_add_card_debugfs(struct mmc_card *card)
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 840b301..f2e02d7 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -41,23 +41,35 @@
  * @clkreg: default value for MCICLOCK register
  * @clkreg_enable: enable value for MMCICLOCK register
  * @datalength_bits: number of bits in the MMCIDATALENGTH register
+ * @fifosize: number of bytes that can be written when MMCI_TXFIFOEMPTY
+ *	      is asserted (likewise for RX)
+ * @fifohalfsize: number of bytes that can be written when MCI_TXFIFOHALFEMPTY
+ *		  is asserted (likewise for RX)
  */
 struct variant_data {
 	unsigned int		clkreg;
 	unsigned int		clkreg_enable;
 	unsigned int		datalength_bits;
+	unsigned int		fifosize;
+	unsigned int		fifohalfsize;
 };
 
 static struct variant_data variant_arm = {
+	.fifosize		= 16 * 4,
+	.fifohalfsize		= 8 * 4,
 	.datalength_bits	= 16,
 };
 
 static struct variant_data variant_u300 = {
+	.fifosize		= 16 * 4,
+	.fifohalfsize		= 8 * 4,
 	.clkreg_enable		= 1 << 13, /* HWFCEN */
 	.datalength_bits	= 16,
 };
 
 static struct variant_data variant_ux500 = {
+	.fifosize		= 30 * 4,
+	.fifohalfsize		= 8 * 4,
 	.clkreg			= MCI_CLK_ENABLE,
 	.clkreg_enable		= 1 << 14, /* HWFCEN */
 	.datalength_bits	= 24,
@@ -138,6 +150,7 @@
 
 static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 {
+	struct variant_data *variant = host->variant;
 	unsigned int datactrl, timeout, irqmask;
 	unsigned long long clks;
 	void __iomem *base;
@@ -173,7 +186,7 @@
 		 * If we have less than a FIFOSIZE of bytes to transfer,
 		 * trigger a PIO interrupt as soon as any data is available.
 		 */
-		if (host->size < MCI_FIFOSIZE)
+		if (host->size < variant->fifosize)
 			irqmask |= MCI_RXDATAAVLBLMASK;
 	} else {
 		/*
@@ -332,13 +345,15 @@
 
 static int mmci_pio_write(struct mmci_host *host, char *buffer, unsigned int remain, u32 status)
 {
+	struct variant_data *variant = host->variant;
 	void __iomem *base = host->base;
 	char *ptr = buffer;
 
 	do {
 		unsigned int count, maxcnt;
 
-		maxcnt = status & MCI_TXFIFOEMPTY ? MCI_FIFOSIZE : MCI_FIFOHALFSIZE;
+		maxcnt = status & MCI_TXFIFOEMPTY ?
+			 variant->fifosize : variant->fifohalfsize;
 		count = min(remain, maxcnt);
 
 		writesl(base + MMCIFIFO, ptr, count >> 2);
@@ -362,6 +377,7 @@
 {
 	struct mmci_host *host = dev_id;
 	struct sg_mapping_iter *sg_miter = &host->sg_miter;
+	struct variant_data *variant = host->variant;
 	void __iomem *base = host->base;
 	unsigned long flags;
 	u32 status;
@@ -420,7 +436,7 @@
 	 * If we're nearing the end of the read, switch to
 	 * "any data available" mode.
 	 */
-	if (status & MCI_RXACTIVE && host->size < MCI_FIFOSIZE)
+	if (status & MCI_RXACTIVE && host->size < variant->fifosize)
 		writel(MCI_RXDATAAVLBLMASK, base + MMCIMASK1);
 
 	/*
@@ -564,18 +580,23 @@
 	if (host->gpio_wp == -ENOSYS)
 		return -ENOSYS;
 
-	return gpio_get_value(host->gpio_wp);
+	return gpio_get_value_cansleep(host->gpio_wp);
 }
 
 static int mmci_get_cd(struct mmc_host *mmc)
 {
 	struct mmci_host *host = mmc_priv(mmc);
+	struct mmci_platform_data *plat = host->plat;
 	unsigned int status;
 
-	if (host->gpio_cd == -ENOSYS)
-		status = host->plat->status(mmc_dev(host->mmc));
-	else
-		status = !gpio_get_value(host->gpio_cd);
+	if (host->gpio_cd == -ENOSYS) {
+		if (!plat->status)
+			return 1; /* Assume always present */
+
+		status = plat->status(mmc_dev(host->mmc));
+	} else
+		status = !!gpio_get_value_cansleep(host->gpio_cd)
+			^ plat->cd_invert;
 
 	/*
 	 * Use positive logic throughout - status is zero for no card,
@@ -584,6 +605,15 @@
 	return status;
 }
 
+static irqreturn_t mmci_cd_irq(int irq, void *dev_id)
+{
+	struct mmci_host *host = dev_id;
+
+	mmc_detect_change(host->mmc, msecs_to_jiffies(500));
+
+	return IRQ_HANDLED;
+}
+
 static const struct mmc_host_ops mmci_ops = {
 	.request	= mmci_request,
 	.set_ios	= mmci_set_ios,
@@ -620,6 +650,7 @@
 
 	host->gpio_wp = -ENOSYS;
 	host->gpio_cd = -ENOSYS;
+	host->gpio_cd_irq = -1;
 
 	host->hw_designer = amba_manf(dev);
 	host->hw_revision = amba_rev(dev);
@@ -699,7 +730,6 @@
 	if (host->vcc == NULL)
 		mmc->ocr_avail = plat->ocr_mask;
 	mmc->caps = plat->capabilities;
-	mmc->caps |= MMC_CAP_NEEDS_POLL;
 
 	/*
 	 * We can do SGIO
@@ -744,6 +774,12 @@
 			host->gpio_cd = plat->gpio_cd;
 		else if (ret != -ENOSYS)
 			goto err_gpio_cd;
+
+		ret = request_any_context_irq(gpio_to_irq(plat->gpio_cd),
+					      mmci_cd_irq, 0,
+					      DRIVER_NAME " (cd)", host);
+		if (ret >= 0)
+			host->gpio_cd_irq = gpio_to_irq(plat->gpio_cd);
 	}
 	if (gpio_is_valid(plat->gpio_wp)) {
 		ret = gpio_request(plat->gpio_wp, DRIVER_NAME " (wp)");
@@ -755,6 +791,10 @@
 			goto err_gpio_wp;
 	}
 
+	if ((host->plat->status || host->gpio_cd != -ENOSYS)
+	    && host->gpio_cd_irq < 0)
+		mmc->caps |= MMC_CAP_NEEDS_POLL;
+
 	ret = request_irq(dev->irq[0], mmci_irq, IRQF_SHARED, DRIVER_NAME " (cmd)", host);
 	if (ret)
 		goto unmap;
@@ -781,6 +821,8 @@
 	if (host->gpio_wp != -ENOSYS)
 		gpio_free(host->gpio_wp);
  err_gpio_wp:
+	if (host->gpio_cd_irq >= 0)
+		free_irq(host->gpio_cd_irq, host);
 	if (host->gpio_cd != -ENOSYS)
 		gpio_free(host->gpio_cd);
  err_gpio_cd:
@@ -819,6 +861,8 @@
 
 		if (host->gpio_wp != -ENOSYS)
 			gpio_free(host->gpio_wp);
+		if (host->gpio_cd_irq >= 0)
+			free_irq(host->gpio_cd_irq, host);
 		if (host->gpio_cd != -ENOSYS)
 			gpio_free(host->gpio_cd);
 
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 68970cf..4ae887f 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -54,10 +54,16 @@
 #define MCI_DPSM_MODE		(1 << 2)
 #define MCI_DPSM_DMAENABLE	(1 << 3)
 #define MCI_DPSM_BLOCKSIZE	(1 << 4)
-#define MCI_DPSM_RWSTART	(1 << 8)
-#define MCI_DPSM_RWSTOP		(1 << 9)
-#define MCI_DPSM_RWMOD		(1 << 10)
-#define MCI_DPSM_SDIOEN		(1 << 11)
+/* Control register extensions in the ST Micro U300 and Ux500 versions */
+#define MCI_ST_DPSM_RWSTART	(1 << 8)
+#define MCI_ST_DPSM_RWSTOP	(1 << 9)
+#define MCI_ST_DPSM_RWMOD	(1 << 10)
+#define MCI_ST_DPSM_SDIOEN	(1 << 11)
+/* Control register extensions in the ST Micro Ux500 versions */
+#define MCI_ST_DPSM_DMAREQCTL	(1 << 12)
+#define MCI_ST_DPSM_DBOOTMODEEN	(1 << 13)
+#define MCI_ST_DPSM_BUSYMODE	(1 << 14)
+#define MCI_ST_DPSM_DDRMODE	(1 << 15)
 
 #define MMCIDATACNT		0x030
 #define MMCISTATUS		0x034
@@ -133,13 +139,6 @@
 	MCI_DATATIMEOUTMASK|MCI_TXUNDERRUNMASK|MCI_RXOVERRUNMASK|	\
 	MCI_CMDRESPENDMASK|MCI_CMDSENTMASK|MCI_DATABLOCKENDMASK)
 
-/*
- * The size of the FIFO in bytes.
- */
-#define MCI_FIFOSIZE	(16*4)
-	
-#define MCI_FIFOHALFSIZE (MCI_FIFOSIZE / 2)
-
 #define NR_SG		16
 
 struct clk;
@@ -154,6 +153,7 @@
 	struct clk		*clk;
 	int			gpio_cd;
 	int			gpio_wp;
+	int			gpio_cd_irq;
 
 	unsigned int		data_xfered;
 
diff --git a/drivers/mmc/host/sdricoh_cs.c b/drivers/mmc/host/sdricoh_cs.c
index 7aa65bb..f472c27 100644
--- a/drivers/mmc/host/sdricoh_cs.c
+++ b/drivers/mmc/host/sdricoh_cs.c
@@ -30,7 +30,6 @@
 #include <linux/ioport.h>
 #include <linux/scatterlist.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 #include <linux/io.h>
@@ -536,9 +535,7 @@
 #endif
 
 static struct pcmcia_driver sdricoh_driver = {
-	.drv = {
-		.name = DRIVER_NAME,
-		},
+	.name = DRIVER_NAME,
 	.probe = sdricoh_pcmcia_probe,
 	.remove = sdricoh_pcmcia_detach,
 	.id_table = pcmcia_ids,
diff --git a/drivers/mtd/maps/pcmciamtd.c b/drivers/mtd/maps/pcmciamtd.c
index e9ca5ba..57a1acf 100644
--- a/drivers/mtd/maps/pcmciamtd.c
+++ b/drivers/mtd/maps/pcmciamtd.c
@@ -16,7 +16,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -101,7 +100,7 @@
 static caddr_t remap_window(struct map_info *map, unsigned long to)
 {
 	struct pcmciamtd_dev *dev = (struct pcmciamtd_dev *)map->map_priv_1;
-	window_handle_t win = (window_handle_t)map->map_priv_2;
+	struct resource *win = (struct resource *) map->map_priv_2;
 	unsigned int offset;
 	int ret;
 
@@ -316,30 +315,19 @@
 {
 	struct pcmciamtd_dev *dev = (struct pcmciamtd_dev *)map->map_priv_1;
 	struct pcmcia_device *link = dev->p_dev;
-	modconf_t mod;
-	int ret;
-
-	mod.Attributes = CONF_VPP1_CHANGE_VALID | CONF_VPP2_CHANGE_VALID;
-	mod.Vcc = 0;
-	mod.Vpp1 = mod.Vpp2 = on ? dev->vpp : 0;
 
 	DEBUG(2, "dev = %p on = %d vpp = %d\n", dev, on, dev->vpp);
-	ret = pcmcia_modify_configuration(link, &mod);
+	pcmcia_fixup_vpp(link, on ? dev->vpp : 0);
 }
 
 
-/* After a card is removed, pcmciamtd_release() will unregister the
- * device, and release the PCMCIA configuration.  If the device is
- * still open, this will be postponed until it is closed.
- */
-
 static void pcmciamtd_release(struct pcmcia_device *link)
 {
 	struct pcmciamtd_dev *dev = link->priv;
 
 	DEBUG(3, "link = 0x%p", link);
 
-	if (link->win) {
+	if (link->resource[2]->end) {
 		if(dev->win_base) {
 			iounmap(dev->win_base);
 			dev->win_base = NULL;
@@ -482,18 +470,12 @@
 }
 
 
-/* pcmciamtd_config() is scheduled to run after a CARD_INSERTION event
- * is received, to configure the PCMCIA socket, and to make the
- * MTD device available to the system.
- */
-
 static int pcmciamtd_config(struct pcmcia_device *link)
 {
 	struct pcmciamtd_dev *dev = link->priv;
 	struct mtd_info *mtd = NULL;
-	win_req_t req;
 	int ret;
-	int i;
+	int i, j = 0;
 	static char *probes[] = { "jedec_probe", "cfi_probe" };
 	int new_name = 0;
 
@@ -520,28 +502,34 @@
 	 * smaller windows until we succeed
 	 */
 
-	req.Attributes =  WIN_MEMORY_TYPE_CM | WIN_ENABLE;
-	req.Attributes |= (dev->pcmcia_map.bankwidth == 1) ? WIN_DATA_WIDTH_8 : WIN_DATA_WIDTH_16;
-	req.Base = 0;
-	req.AccessSpeed = mem_speed;
-	link->win = (window_handle_t)link;
-	req.Size = (force_size) ? force_size << 20 : MAX_PCMCIA_ADDR;
+	link->resource[2]->flags |=  WIN_MEMORY_TYPE_CM | WIN_ENABLE;
+	link->resource[2]->flags |= (dev->pcmcia_map.bankwidth == 1) ?
+					WIN_DATA_WIDTH_8 : WIN_DATA_WIDTH_16;
+	link->resource[2]->start = 0;
+	link->resource[2]->end = (force_size) ? force_size << 20 :
+					MAX_PCMCIA_ADDR;
 	dev->win_size = 0;
 
 	do {
 		int ret;
-		DEBUG(2, "requesting window with size = %dKiB memspeed = %d",
-		      req.Size >> 10, req.AccessSpeed);
-		ret = pcmcia_request_window(link, &req, &link->win);
+		DEBUG(2, "requesting window with size = %luKiB memspeed = %d",
+			(unsigned long) resource_size(link->resource[2]) >> 10,
+			mem_speed);
+		ret = pcmcia_request_window(link, link->resource[2], mem_speed);
 		DEBUG(2, "ret = %d dev->win_size = %d", ret, dev->win_size);
 		if(ret) {
-			req.Size >>= 1;
+			j++;
+			link->resource[2]->start = 0;
+			link->resource[2]->end = (force_size) ?
+					force_size << 20 : MAX_PCMCIA_ADDR;
+			link->resource[2]->end >>= j;
 		} else {
-			DEBUG(2, "Got window of size %dKiB", req.Size >> 10);
-			dev->win_size = req.Size;
+			DEBUG(2, "Got window of size %luKiB", (unsigned long)
+				resource_size(link->resource[2]) >> 10);
+			dev->win_size = resource_size(link->resource[2]);
 			break;
 		}
-	} while(req.Size >= 0x1000);
+	} while (link->resource[2]->end >= 0x1000);
 
 	DEBUG(2, "dev->win_size = %d", dev->win_size);
 
@@ -553,33 +541,31 @@
 	DEBUG(1, "Allocated a window of %dKiB", dev->win_size >> 10);
 
 	/* Get write protect status */
-	DEBUG(2, "window handle = 0x%8.8lx", (unsigned long)link->win);
-	dev->win_base = ioremap(req.Base, req.Size);
+	dev->win_base = ioremap(link->resource[2]->start,
+				resource_size(link->resource[2]));
 	if(!dev->win_base) {
-		dev_err(&dev->p_dev->dev, "ioremap(%lu, %u) failed\n",
-			req.Base, req.Size);
+		dev_err(&dev->p_dev->dev, "ioremap(%pR) failed\n",
+			link->resource[2]);
 		pcmciamtd_release(link);
 		return -ENODEV;
 	}
-	DEBUG(1, "mapped window dev = %p req.base = 0x%lx base = %p size = 0x%x",
-	      dev, req.Base, dev->win_base, req.Size);
+	DEBUG(1, "mapped window dev = %p @ %pR, base = %p",
+	      dev, link->resource[2], dev->win_base);
 
 	dev->offset = 0;
 	dev->pcmcia_map.map_priv_1 = (unsigned long)dev;
-	dev->pcmcia_map.map_priv_2 = (unsigned long)link->win;
+	dev->pcmcia_map.map_priv_2 = (unsigned long)link->resource[2];
 
 	dev->vpp = (vpp) ? vpp : link->socket->socket.Vpp;
-	link->conf.Attributes = 0;
 	if(setvpp == 2) {
-		link->conf.Vpp = dev->vpp;
+		link->vpp = dev->vpp;
 	} else {
-		link->conf.Vpp = 0;
+		link->vpp = 0;
 	}
 
-	link->conf.IntType = INT_MEMORY;
-	link->conf.ConfigIndex = 0;
+	link->config_index = 0;
 	DEBUG(2, "Setting Configuration");
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret != 0) {
 		if (dev->win_base) {
 			iounmap(dev->win_base);
@@ -680,12 +666,6 @@
 }
 
 
-/* This deletes a driver "instance".  The device is de-registered
- * with Card Services.  If it has been released, all local data
- * structures are freed.  Otherwise, the structures will be freed
- * when the device is released.
- */
-
 static void pcmciamtd_detach(struct pcmcia_device *link)
 {
 	struct pcmciamtd_dev *dev = link->priv;
@@ -703,11 +683,6 @@
 }
 
 
-/* pcmciamtd_attach() creates an "instance" of the driver, allocating
- * local data structures for one device.  The device is registered
- * with Card Services.
- */
-
 static int pcmciamtd_probe(struct pcmcia_device *link)
 {
 	struct pcmciamtd_dev *dev;
@@ -720,9 +695,6 @@
 	dev->p_dev = link;
 	link->priv = dev;
 
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY;
-
 	return pcmciamtd_config(link);
 }
 
@@ -757,9 +729,7 @@
 MODULE_DEVICE_TABLE(pcmcia, pcmciamtd_ids);
 
 static struct pcmcia_driver pcmciamtd_driver = {
-	.drv		= {
-		.name	= "pcmciamtd"
-	},
+	.name		= "pcmciamtd",
 	.probe		= pcmciamtd_probe,
 	.remove		= pcmciamtd_detach,
 	.owner		= THIS_MODULE,
@@ -771,8 +741,6 @@
 
 static int __init init_pcmciamtd(void)
 {
-	info(DRIVER_DESC);
-
 	if(bankwidth && bankwidth != 1 && bankwidth != 2) {
 		info("bad bankwidth (%d), using default", bankwidth);
 		bankwidth = 2;
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 62e6870..50ab431 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -29,7 +29,6 @@
 #include <linux/blkdev.h>
 #include <linux/blkpg.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
 #include <linux/hdreg.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
@@ -38,6 +37,7 @@
 
 #include "mtdcore.h"
 
+static DEFINE_MUTEX(mtd_blkdevs_mutex);
 static LIST_HEAD(blktrans_majors);
 static DEFINE_MUTEX(blktrans_ref_mutex);
 
@@ -181,7 +181,7 @@
 	if (!dev)
 		return -ERESTARTSYS; /* FIXME: busy loop! -arnd*/
 
-	lock_kernel();
+	mutex_lock(&mtd_blkdevs_mutex);
 	mutex_lock(&dev->lock);
 
 	if (!dev->mtd) {
@@ -198,7 +198,7 @@
 unlock:
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
-	unlock_kernel();
+	mutex_unlock(&mtd_blkdevs_mutex);
 	return ret;
 }
 
@@ -210,7 +210,7 @@
 	if (!dev)
 		return ret;
 
-	lock_kernel();
+	mutex_lock(&mtd_blkdevs_mutex);
 	mutex_lock(&dev->lock);
 
 	/* Release one reference, we sure its not the last one here*/
@@ -223,7 +223,7 @@
 unlock:
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
-	unlock_kernel();
+	mutex_unlock(&mtd_blkdevs_mutex);
 	return ret;
 }
 
@@ -256,7 +256,7 @@
 	if (!dev)
 		return ret;
 
-	lock_kernel();
+	mutex_lock(&mtd_blkdevs_mutex);
 	mutex_lock(&dev->lock);
 
 	if (!dev->mtd)
@@ -271,7 +271,7 @@
 	}
 unlock:
 	mutex_unlock(&dev->lock);
-	unlock_kernel();
+	mutex_unlock(&mtd_blkdevs_mutex);
 	blktrans_dev_put(dev);
 	return ret;
 }
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index a825002..5ef4548 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -26,7 +26,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/backing-dev.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
@@ -37,6 +37,7 @@
 #include <asm/uaccess.h>
 
 #define MTD_INODE_FS_MAGIC 0x11307854
+static DEFINE_MUTEX(mtd_mutex);
 static struct vfsmount *mtd_inode_mnt __read_mostly;
 
 /*
@@ -90,7 +91,7 @@
 	if ((file->f_mode & FMODE_WRITE) && (minor & 1))
 		return -EACCES;
 
-	lock_kernel();
+	mutex_lock(&mtd_mutex);
 	mtd = get_mtd_device(NULL, devnum);
 
 	if (IS_ERR(mtd)) {
@@ -138,7 +139,7 @@
 	file->private_data = mfi;
 
 out:
-	unlock_kernel();
+	mutex_unlock(&mtd_mutex);
 	return ret;
 } /* mtd_open */
 
@@ -866,9 +867,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&mtd_mutex);
 	ret = mtd_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&mtd_mutex);
 
 	return ret;
 }
@@ -892,7 +893,7 @@
 	void __user *argp = compat_ptr(arg);
 	int ret = 0;
 
-	lock_kernel();
+	mutex_lock(&mtd_mutex);
 
 	switch (cmd) {
 	case MEMWRITEOOB32:
@@ -927,7 +928,7 @@
 		ret = mtd_ioctl(file, cmd, (unsigned long)argp);
 	}
 
-	unlock_kernel();
+	mutex_unlock(&mtd_mutex);
 
 	return ret;
 }
diff --git a/drivers/mtd/ubi/Kconfig b/drivers/mtd/ubi/Kconfig
index f702a16..3cf193f 100644
--- a/drivers/mtd/ubi/Kconfig
+++ b/drivers/mtd/ubi/Kconfig
@@ -1,9 +1,5 @@
-menu "UBI - Unsorted block images"
-	depends on MTD
-
-config MTD_UBI
-	tristate "Enable UBI"
-	depends on MTD
+menuconfig MTD_UBI
+	tristate "Enable UBI - Unsorted block images"
 	select CRC32
 	help
 	  UBI is a software layer above MTD layer which admits of LVM-like
@@ -12,11 +8,12 @@
 	  capabilities. Please, consult the MTD web site for more details
 	  (www.linux-mtd.infradead.org).
 
+if MTD_UBI
+
 config MTD_UBI_WL_THRESHOLD
 	int "UBI wear-leveling threshold"
 	default 4096
 	range 2 65536
-	depends on MTD_UBI
 	help
 	  This parameter defines the maximum difference between the highest
 	  erase counter value and the lowest erase counter value of eraseblocks
@@ -34,7 +31,6 @@
 	int "Percentage of reserved eraseblocks for bad eraseblocks handling"
 	default 1
 	range 0 25
-	depends on MTD_UBI
 	help
 	  If the MTD device admits of bad eraseblocks (e.g. NAND flash), UBI
 	  reserves some amount of physical eraseblocks to handle new bad
@@ -48,8 +44,6 @@
 
 config MTD_UBI_GLUEBI
 	tristate "MTD devices emulation driver (gluebi)"
-	default n
-	depends on MTD_UBI
 	help
 	   This option enables gluebi - an additional driver which emulates MTD
 	   devices on top of UBI volumes: for each UBI volumes an MTD device is
@@ -59,4 +53,5 @@
 	   software.
 
 source "drivers/mtd/ubi/Kconfig.debug"
-endmenu
+
+endif # MTD_UBI
diff --git a/drivers/mtd/ubi/Kconfig.debug b/drivers/mtd/ubi/Kconfig.debug
index 61f6e5e..fad4adc 100644
--- a/drivers/mtd/ubi/Kconfig.debug
+++ b/drivers/mtd/ubi/Kconfig.debug
@@ -1,94 +1,73 @@
 comment "UBI debugging options"
-	depends on MTD_UBI
 
 config MTD_UBI_DEBUG
 	bool "UBI debugging"
 	depends on SYSFS
-	depends on MTD_UBI
 	select DEBUG_FS
 	select KALLSYMS_ALL if KALLSYMS && DEBUG_KERNEL
 	help
 	  This option enables UBI debugging.
 
+if MTD_UBI_DEBUG
+
 config MTD_UBI_DEBUG_MSG
 	bool "UBI debugging messages"
-	depends on MTD_UBI_DEBUG
-	default n
 	help
 	  This option enables UBI debugging messages.
 
 config MTD_UBI_DEBUG_PARANOID
 	bool "Extra self-checks"
-	default n
-	depends on MTD_UBI_DEBUG
 	help
 	  This option enables extra checks in UBI code. Note this slows UBI down
 	  significantly.
 
 config MTD_UBI_DEBUG_DISABLE_BGT
 	bool "Do not enable the UBI background thread"
-	depends on MTD_UBI_DEBUG
-	default n
 	help
 	  This option switches the background thread off by default. The thread
 	  may be also be enabled/disabled via UBI sysfs.
 
 config MTD_UBI_DEBUG_EMULATE_BITFLIPS
 	bool "Emulate flash bit-flips"
-	depends on MTD_UBI_DEBUG
-	default n
 	help
 	  This option emulates bit-flips with probability 1/50, which in turn
 	  causes scrubbing. Useful for debugging and stressing UBI.
 
 config MTD_UBI_DEBUG_EMULATE_WRITE_FAILURES
 	bool "Emulate flash write failures"
-	depends on MTD_UBI_DEBUG
-	default n
 	help
 	  This option emulates write failures with probability 1/100. Useful for
 	  debugging and testing how UBI handlines errors.
 
 config MTD_UBI_DEBUG_EMULATE_ERASE_FAILURES
 	bool "Emulate flash erase failures"
-	depends on MTD_UBI_DEBUG
-	default n
 	help
 	  This option emulates erase failures with probability 1/100. Useful for
 	  debugging and testing how UBI handlines errors.
 
-menu "Additional UBI debugging messages"
-	depends on MTD_UBI_DEBUG
+comment "Additional UBI debugging messages"
 
 config MTD_UBI_DEBUG_MSG_BLD
 	bool "Additional UBI initialization and build messages"
-	default n
-	depends on MTD_UBI_DEBUG
 	help
 	  This option enables detailed UBI initialization and device build
 	  debugging messages.
 
 config MTD_UBI_DEBUG_MSG_EBA
 	bool "Eraseblock association unit messages"
-	default n
-	depends on MTD_UBI_DEBUG
 	help
 	  This option enables debugging messages from the UBI eraseblock
 	  association unit.
 
 config MTD_UBI_DEBUG_MSG_WL
 	bool "Wear-leveling unit messages"
-	default n
-	depends on MTD_UBI_DEBUG
 	help
 	  This option enables debugging messages from the UBI wear-leveling
 	  unit.
 
 config MTD_UBI_DEBUG_MSG_IO
 	bool "Input/output unit messages"
-	default n
-	depends on MTD_UBI_DEBUG
 	help
 	  This option enables debugging messages from the UBI input/output unit.
 
-endmenu # UBI debugging messages
+endif # MTD_UBI_DEBUG
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index 78ae894..5ebe280 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -95,8 +95,8 @@
 static DEFINE_SPINLOCK(ubi_devices_lock);
 
 /* "Show" method for files in '/<sysfs>/class/ubi/' */
-static ssize_t ubi_version_show(struct class *class, struct class_attribute *attr,
-				char *buf)
+static ssize_t ubi_version_show(struct class *class,
+				struct class_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", UBI_VERSION);
 }
@@ -591,6 +591,7 @@
 
 	ubi->bad_peb_count = si->bad_peb_count;
 	ubi->good_peb_count = ubi->peb_count - ubi->bad_peb_count;
+	ubi->corr_peb_count = si->corr_peb_count;
 	ubi->max_ec = si->max_ec;
 	ubi->mean_ec = si->mean_ec;
 	ubi_msg("max. sequence number:       %llu", si->max_sqnum);
@@ -972,6 +973,7 @@
 	ubi_msg("MTD device size:            %llu MiB", ubi->flash_size >> 20);
 	ubi_msg("number of good PEBs:        %d", ubi->good_peb_count);
 	ubi_msg("number of bad PEBs:         %d", ubi->bad_peb_count);
+	ubi_msg("number of corrupted PEBs:   %d", ubi->corr_peb_count);
 	ubi_msg("max. allowed volumes:       %d", ubi->vtbl_slots);
 	ubi_msg("wear-leveling threshold:    %d", CONFIG_MTD_UBI_WL_THRESHOLD);
 	ubi_msg("number of internal volumes: %d", UBI_INT_VOL_COUNT);
diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c
index 3d2d1a6..af9fb0f 100644
--- a/drivers/mtd/ubi/cdev.c
+++ b/drivers/mtd/ubi/cdev.c
@@ -1100,4 +1100,5 @@
 	.owner          = THIS_MODULE,
 	.unlocked_ioctl = ctrl_cdev_ioctl,
 	.compat_ioctl   = ctrl_cdev_compat_ioctl,
+	.llseek		= noop_llseek,
 };
diff --git a/drivers/mtd/ubi/debug.h b/drivers/mtd/ubi/debug.h
index 17a1071..9eca950 100644
--- a/drivers/mtd/ubi/debug.h
+++ b/drivers/mtd/ubi/debug.h
@@ -57,6 +57,9 @@
 void ubi_dbg_dump_mkvol_req(const struct ubi_mkvol_req *req);
 void ubi_dbg_dump_flash(struct ubi_device *ubi, int pnum, int offset, int len);
 
+#define ubi_dbg_print_hex_dump(l, ps, pt, r, g, b, len, a)  \
+		print_hex_dump(l, ps, pt, r, g, b, len, a)
+
 #ifdef CONFIG_MTD_UBI_DEBUG_MSG
 /* General debugging messages */
 #define dbg_gen(fmt, ...) dbg_msg(fmt, ##__VA_ARGS__)
@@ -172,6 +175,7 @@
 #define ubi_dbg_dump_seb(seb, type)      ({})
 #define ubi_dbg_dump_mkvol_req(req)      ({})
 #define ubi_dbg_dump_flash(ubi, pnum, offset, len) ({})
+#define ubi_dbg_print_hex_dump(l, ps, pt, r, g, b, len, a)  ({})
 
 #define UBI_IO_DEBUG               0
 #define DBG_DISABLE_BGT            0
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index fe74749..4be67181 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -418,7 +418,7 @@
 				 * may try to recover data. FIXME: but this is
 				 * not implemented.
 				 */
-				if (err == UBI_IO_BAD_HDR_READ ||
+				if (err == UBI_IO_BAD_HDR_EBADMSG ||
 				    err == UBI_IO_BAD_HDR) {
 					ubi_warn("corrupted VID header at PEB "
 						 "%d, LEB %d:%d", pnum, vol_id,
@@ -963,7 +963,7 @@
 static int is_error_sane(int err)
 {
 	if (err == -EIO || err == -ENOMEM || err == UBI_IO_BAD_HDR ||
-	    err == UBI_IO_BAD_HDR_READ || err == -ETIMEDOUT)
+	    err == UBI_IO_BAD_HDR_EBADMSG || err == -ETIMEDOUT)
 		return 0;
 	return 1;
 }
@@ -1201,6 +1201,9 @@
 
 	ubi_warn("cannot reserve enough PEBs for bad PEB handling, reserved %d,"
 		 " need %d", ubi->beb_rsvd_pebs, ubi->beb_rsvd_level);
+	if (ubi->corr_peb_count)
+		ubi_warn("%d PEBs are corrupted and not used",
+			ubi->corr_peb_count);
 }
 
 /**
@@ -1263,6 +1266,9 @@
 	if (ubi->avail_pebs < EBA_RESERVED_PEBS) {
 		ubi_err("no enough physical eraseblocks (%d, need %d)",
 			ubi->avail_pebs, EBA_RESERVED_PEBS);
+		if (ubi->corr_peb_count)
+			ubi_err("%d PEBs are corrupted and not used",
+				ubi->corr_peb_count);
 		err = -ENOSPC;
 		goto out_free;
 	}
diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c
index 332f992..c2960ac 100644
--- a/drivers/mtd/ubi/io.c
+++ b/drivers/mtd/ubi/io.c
@@ -376,25 +376,6 @@
 	return 0;
 }
 
-/**
- * check_pattern - check if buffer contains only a certain byte pattern.
- * @buf: buffer to check
- * @patt: the pattern to check
- * @size: buffer size in bytes
- *
- * This function returns %1 in there are only @patt bytes in @buf, and %0 if
- * something else was also found.
- */
-static int check_pattern(const void *buf, uint8_t patt, int size)
-{
-	int i;
-
-	for (i = 0; i < size; i++)
-		if (((const uint8_t *)buf)[i] != patt)
-			return 0;
-	return 1;
-}
-
 /* Patterns to write to a physical eraseblock when torturing it */
 static uint8_t patterns[] = {0xa5, 0x5a, 0x0};
 
@@ -426,7 +407,7 @@
 		if (err)
 			goto out;
 
-		err = check_pattern(ubi->peb_buf1, 0xFF, ubi->peb_size);
+		err = ubi_check_pattern(ubi->peb_buf1, 0xFF, ubi->peb_size);
 		if (err == 0) {
 			ubi_err("erased PEB %d, but a non-0xFF byte found",
 				pnum);
@@ -445,7 +426,8 @@
 		if (err)
 			goto out;
 
-		err = check_pattern(ubi->peb_buf1, patterns[i], ubi->peb_size);
+		err = ubi_check_pattern(ubi->peb_buf1, patterns[i],
+					ubi->peb_size);
 		if (err == 0) {
 			ubi_err("pattern %x checking failed for PEB %d",
 				patterns[i], pnum);
@@ -517,7 +499,7 @@
 	 * In this case we probably anyway have garbage in this PEB.
 	 */
 	err1 = ubi_io_read_vid_hdr(ubi, pnum, &vid_hdr, 0);
-	if (err1 == UBI_IO_BAD_HDR_READ || err1 == UBI_IO_BAD_HDR)
+	if (err1 == UBI_IO_BAD_HDR_EBADMSG || err1 == UBI_IO_BAD_HDR)
 		/*
 		 * The VID header is corrupted, so we can safely erase this
 		 * PEB and not afraid that it will be treated as a valid PEB in
@@ -712,47 +694,47 @@
  *   and corrected by the flash driver; this is harmless but may indicate that
  *   this eraseblock may become bad soon (but may be not);
  * o %UBI_IO_BAD_HDR if the erase counter header is corrupted (a CRC error);
- * o %UBI_IO_PEB_EMPTY if the physical eraseblock is empty;
+ * o %UBI_IO_BAD_HDR_EBADMSG is the same as %UBI_IO_BAD_HDR, but there also was
+ *   a data integrity error (uncorrectable ECC error in case of NAND);
+ * o %UBI_IO_FF if only 0xFF bytes were read (the PEB is supposedly empty)
  * o a negative error code in case of failure.
  */
 int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum,
 		       struct ubi_ec_hdr *ec_hdr, int verbose)
 {
-	int err, read_err = 0;
+	int err, read_err;
 	uint32_t crc, magic, hdr_crc;
 
 	dbg_io("read EC header from PEB %d", pnum);
 	ubi_assert(pnum >= 0 && pnum < ubi->peb_count);
 
-	err = ubi_io_read(ubi, ec_hdr, pnum, 0, UBI_EC_HDR_SIZE);
-	if (err) {
-		if (err != UBI_IO_BITFLIPS && err != -EBADMSG)
-			return err;
+	read_err = ubi_io_read(ubi, ec_hdr, pnum, 0, UBI_EC_HDR_SIZE);
+	if (read_err) {
+		if (read_err != UBI_IO_BITFLIPS && read_err != -EBADMSG)
+			return read_err;
 
 		/*
 		 * We read all the data, but either a correctable bit-flip
-		 * occurred, or MTD reported about some data integrity error,
-		 * like an ECC error in case of NAND. The former is harmless,
-		 * the later may mean that the read data is corrupted. But we
-		 * have a CRC check-sum and we will detect this. If the EC
-		 * header is still OK, we just report this as there was a
-		 * bit-flip.
+		 * occurred, or MTD reported a data integrity error
+		 * (uncorrectable ECC error in case of NAND). The former is
+		 * harmless, the later may mean that the read data is
+		 * corrupted. But we have a CRC check-sum and we will detect
+		 * this. If the EC header is still OK, we just report this as
+		 * there was a bit-flip, to force scrubbing.
 		 */
-		if (err == -EBADMSG)
-			read_err = UBI_IO_BAD_HDR_READ;
 	}
 
 	magic = be32_to_cpu(ec_hdr->magic);
 	if (magic != UBI_EC_HDR_MAGIC) {
-		if (read_err)
-			return read_err;
+		if (read_err == -EBADMSG)
+			return UBI_IO_BAD_HDR_EBADMSG;
 
 		/*
 		 * The magic field is wrong. Let's check if we have read all
 		 * 0xFF. If yes, this physical eraseblock is assumed to be
 		 * empty.
 		 */
-		if (check_pattern(ec_hdr, 0xFF, UBI_EC_HDR_SIZE)) {
+		if (ubi_check_pattern(ec_hdr, 0xFF, UBI_EC_HDR_SIZE)) {
 			/* The physical eraseblock is supposedly empty */
 			if (verbose)
 				ubi_warn("no EC header found at PEB %d, "
@@ -760,7 +742,10 @@
 			else if (UBI_IO_DEBUG)
 				dbg_msg("no EC header found at PEB %d, "
 					"only 0xFF bytes", pnum);
-			return UBI_IO_PEB_EMPTY;
+			if (!read_err)
+				return UBI_IO_FF;
+			else
+				return UBI_IO_FF_BITFLIPS;
 		}
 
 		/*
@@ -788,7 +773,11 @@
 		} else if (UBI_IO_DEBUG)
 			dbg_msg("bad EC header CRC at PEB %d, calculated "
 				"%#08x, read %#08x", pnum, crc, hdr_crc);
-		return read_err ?: UBI_IO_BAD_HDR;
+
+		if (!read_err)
+			return UBI_IO_BAD_HDR;
+		else
+			return UBI_IO_BAD_HDR_EBADMSG;
 	}
 
 	/* And of course validate what has just been read from the media */
@@ -975,22 +964,16 @@
  *
  * This function reads the volume identifier header from physical eraseblock
  * @pnum and stores it in @vid_hdr. It also checks CRC checksum of the read
- * volume identifier header. The following codes may be returned:
+ * volume identifier header. The error codes are the same as in
+ * 'ubi_io_read_ec_hdr()'.
  *
- * o %0 if the CRC checksum is correct and the header was successfully read;
- * o %UBI_IO_BITFLIPS if the CRC is correct, but bit-flips were detected
- *   and corrected by the flash driver; this is harmless but may indicate that
- *   this eraseblock may become bad soon;
- * o %UBI_IO_BAD_HDR if the volume identifier header is corrupted (a CRC
- *   error detected);
- * o %UBI_IO_PEB_FREE if the physical eraseblock is free (i.e., there is no VID
- *   header there);
- * o a negative error code in case of failure.
+ * Note, the implementation of this function is also very similar to
+ * 'ubi_io_read_ec_hdr()', so refer commentaries in 'ubi_io_read_ec_hdr()'.
  */
 int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
 			struct ubi_vid_hdr *vid_hdr, int verbose)
 {
-	int err, read_err = 0;
+	int err, read_err;
 	uint32_t crc, magic, hdr_crc;
 	void *p;
 
@@ -998,48 +981,29 @@
 	ubi_assert(pnum >= 0 &&  pnum < ubi->peb_count);
 
 	p = (char *)vid_hdr - ubi->vid_hdr_shift;
-	err = ubi_io_read(ubi, p, pnum, ubi->vid_hdr_aloffset,
+	read_err = ubi_io_read(ubi, p, pnum, ubi->vid_hdr_aloffset,
 			  ubi->vid_hdr_alsize);
-	if (err) {
-		if (err != UBI_IO_BITFLIPS && err != -EBADMSG)
-			return err;
-
-		/*
-		 * We read all the data, but either a correctable bit-flip
-		 * occurred, or MTD reported about some data integrity error,
-		 * like an ECC error in case of NAND. The former is harmless,
-		 * the later may mean the read data is corrupted. But we have a
-		 * CRC check-sum and we will identify this. If the VID header is
-		 * still OK, we just report this as there was a bit-flip.
-		 */
-		if (err == -EBADMSG)
-			read_err = UBI_IO_BAD_HDR_READ;
-	}
+	if (read_err && read_err != UBI_IO_BITFLIPS && read_err != -EBADMSG)
+		return read_err;
 
 	magic = be32_to_cpu(vid_hdr->magic);
 	if (magic != UBI_VID_HDR_MAGIC) {
-		if (read_err)
-			return read_err;
+		if (read_err == -EBADMSG)
+			return UBI_IO_BAD_HDR_EBADMSG;
 
-		/*
-		 * If we have read all 0xFF bytes, the VID header probably does
-		 * not exist and the physical eraseblock is assumed to be free.
-		 */
-		if (check_pattern(vid_hdr, 0xFF, UBI_VID_HDR_SIZE)) {
-			/* The physical eraseblock is supposedly free */
+		if (ubi_check_pattern(vid_hdr, 0xFF, UBI_VID_HDR_SIZE)) {
 			if (verbose)
 				ubi_warn("no VID header found at PEB %d, "
 					 "only 0xFF bytes", pnum);
 			else if (UBI_IO_DEBUG)
 				dbg_msg("no VID header found at PEB %d, "
 					"only 0xFF bytes", pnum);
-			return UBI_IO_PEB_FREE;
+			if (!read_err)
+				return UBI_IO_FF;
+			else
+				return UBI_IO_FF_BITFLIPS;
 		}
 
-		/*
-		 * This is not a valid VID header, and these are not 0xFF
-		 * bytes. Report that the header is corrupted.
-		 */
 		if (verbose) {
 			ubi_warn("bad magic number at PEB %d: %08x instead of "
 				 "%08x", pnum, magic, UBI_VID_HDR_MAGIC);
@@ -1061,20 +1025,18 @@
 		} else if (UBI_IO_DEBUG)
 			dbg_msg("bad CRC at PEB %d, calculated %#08x, "
 				"read %#08x", pnum, crc, hdr_crc);
-		return read_err ?: UBI_IO_BAD_HDR;
+		if (!read_err)
+			return UBI_IO_BAD_HDR;
+		else
+			return UBI_IO_BAD_HDR_EBADMSG;
 	}
 
-	/* Validate the VID header that we have just read */
 	err = validate_vid_hdr(ubi, vid_hdr);
 	if (err) {
 		ubi_err("validation failed for PEB %d", pnum);
 		return -EINVAL;
 	}
 
-	/*
-	 * If there was a read error (%-EBADMSG), but the header CRC is still
-	 * OK, report about a bit-flip to force scrubbing on this PEB.
-	 */
 	return read_err ? UBI_IO_BITFLIPS : 0;
 }
 
@@ -1383,7 +1345,7 @@
 		goto error;
 	}
 
-	err = check_pattern(ubi->dbg_peb_buf, 0xFF, len);
+	err = ubi_check_pattern(ubi->dbg_peb_buf, 0xFF, len);
 	if (err == 0) {
 		ubi_err("flash region at PEB %d:%d, length %d does not "
 			"contain all 0xFF bytes", pnum, offset, len);
diff --git a/drivers/mtd/ubi/misc.c b/drivers/mtd/ubi/misc.c
index 22ad314..ff2a65c 100644
--- a/drivers/mtd/ubi/misc.c
+++ b/drivers/mtd/ubi/misc.c
@@ -103,3 +103,22 @@
 	if (ubi->beb_rsvd_level < MIN_RESEVED_PEBS)
 		ubi->beb_rsvd_level = MIN_RESEVED_PEBS;
 }
+
+/**
+ * ubi_check_pattern - check if buffer contains only a certain byte pattern.
+ * @buf: buffer to check
+ * @patt: the pattern to check
+ * @size: buffer size in bytes
+ *
+ * This function returns %1 in there are only @patt bytes in @buf, and %0 if
+ * something else was also found.
+ */
+int ubi_check_pattern(const void *buf, uint8_t patt, int size)
+{
+	int i;
+
+	for (i = 0; i < size; i++)
+		if (((const uint8_t *)buf)[i] != patt)
+			return 0;
+	return 1;
+}
diff --git a/drivers/mtd/ubi/scan.c b/drivers/mtd/ubi/scan.c
index 69b52e9..3c63186 100644
--- a/drivers/mtd/ubi/scan.c
+++ b/drivers/mtd/ubi/scan.c
@@ -29,7 +29,7 @@
  * objects which are kept in volume RB-tree with root at the @volumes field.
  * The RB-tree is indexed by the volume ID.
  *
- * Found logical eraseblocks are represented by &struct ubi_scan_leb objects.
+ * Scanned logical eraseblocks are represented by &struct ubi_scan_leb objects.
  * These objects are kept in per-volume RB-trees with the root at the
  * corresponding &struct ubi_scan_volume object. To put it differently, we keep
  * an RB-tree of per-volume objects and each of these objects is the root of
@@ -38,6 +38,33 @@
  * Corrupted physical eraseblocks are put to the @corr list, free physical
  * eraseblocks are put to the @free list and the physical eraseblock to be
  * erased are put to the @erase list.
+ *
+ * UBI tries to distinguish between 2 types of corruptions.
+ * 1. Corruptions caused by power cuts. These are harmless and expected
+ *    corruptions and UBI tries to handle them gracefully, without printing too
+ *    many warnings and error messages. The idea is that we do not lose
+ *    important data in these case - we may lose only the data which was being
+ *    written to the media just before the power cut happened, and the upper
+ *    layers (e.g., UBIFS) are supposed to handle these situations. UBI puts
+ *    these PEBs to the head of the @erase list and they are scheduled for
+ *    erasure.
+ *
+ * 2. Unexpected corruptions which are not caused by power cuts. During
+ *    scanning, such PEBs are put to the @corr list and UBI preserves them.
+ *    Obviously, this lessens the amount of available PEBs, and if at some
+ *    point UBI runs out of free PEBs, it switches to R/O mode. UBI also loudly
+ *    informs about such PEBs every time the MTD device is attached.
+ *
+ * However, it is difficult to reliably distinguish between these types of
+ * corruptions and UBI's strategy is as follows. UBI assumes (2.) if the VID
+ * header is corrupted and the data area does not contain all 0xFFs, and there
+ * were not bit-flips or integrity errors while reading the data area. Otherwise
+ * UBI assumes (1.). The assumptions are:
+ *   o if the data area contains only 0xFFs, there is no data, and it is safe
+ *     to just erase this PEB.
+ *   o if the data area has bit-flips and data integrity errors (ECC errors on
+ *     NAND), it is probably a PEB which was being erased when power cut
+ *     happened.
  */
 
 #include <linux/err.h>
@@ -62,26 +89,26 @@
  * @si: scanning information
  * @pnum: physical eraseblock number to add
  * @ec: erase counter of the physical eraseblock
+ * @to_head: if not zero, add to the head of the list
  * @list: the list to add to
  *
- * This function adds physical eraseblock @pnum to free, erase, corrupted or
- * alien lists. Returns zero in case of success and a negative error code in
- * case of failure.
+ * This function adds physical eraseblock @pnum to free, erase, or alien lists.
+ * If @to_head is not zero, PEB will be added to the head of the list, which
+ * basically means it will be processed first later. E.g., we add corrupted
+ * PEBs (corrupted due to power cuts) to the head of the erase list to make
+ * sure we erase them first and get rid of corruptions ASAP. This function
+ * returns zero in case of success and a negative error code in case of
+ * failure.
  */
-static int add_to_list(struct ubi_scan_info *si, int pnum, int ec,
+static int add_to_list(struct ubi_scan_info *si, int pnum, int ec, int to_head,
 		       struct list_head *list)
 {
 	struct ubi_scan_leb *seb;
 
 	if (list == &si->free) {
 		dbg_bld("add to free: PEB %d, EC %d", pnum, ec);
-		si->free_peb_count += 1;
 	} else if (list == &si->erase) {
 		dbg_bld("add to erase: PEB %d, EC %d", pnum, ec);
-		si->erase_peb_count += 1;
-	} else if (list == &si->corr) {
-		dbg_bld("add to corrupted: PEB %d, EC %d", pnum, ec);
-		si->corr_peb_count += 1;
 	} else if (list == &si->alien) {
 		dbg_bld("add to alien: PEB %d, EC %d", pnum, ec);
 		si->alien_peb_count += 1;
@@ -94,7 +121,37 @@
 
 	seb->pnum = pnum;
 	seb->ec = ec;
-	list_add_tail(&seb->u.list, list);
+	if (to_head)
+		list_add(&seb->u.list, list);
+	else
+		list_add_tail(&seb->u.list, list);
+	return 0;
+}
+
+/**
+ * add_corrupted - add a corrupted physical eraseblock.
+ * @si: scanning information
+ * @pnum: physical eraseblock number to add
+ * @ec: erase counter of the physical eraseblock
+ *
+ * This function adds corrupted physical eraseblock @pnum to the 'corr' list.
+ * The corruption was presumably not caused by a power cut. Returns zero in
+ * case of success and a negative error code in case of failure.
+ */
+static int add_corrupted(struct ubi_scan_info *si, int pnum, int ec)
+{
+	struct ubi_scan_leb *seb;
+
+	dbg_bld("add to corrupted: PEB %d, EC %d", pnum, ec);
+
+	seb = kmalloc(sizeof(struct ubi_scan_leb), GFP_KERNEL);
+	if (!seb)
+		return -ENOMEM;
+
+	si->corr_peb_count += 1;
+	seb->pnum = pnum;
+	seb->ec = ec;
+	list_add(&seb->u.list, &si->corr);
 	return 0;
 }
 
@@ -258,8 +315,8 @@
 		 * created before sequence numbers support has been added. At
 		 * that times we used 32-bit LEB versions stored in logical
 		 * eraseblocks. That was before UBI got into mainline. We do not
-		 * support these images anymore. Well, those images will work
-		 * still work, but only if no unclean reboots happened.
+		 * support these images anymore. Well, those images still work,
+		 * but only if no unclean reboots happened.
 		 */
 		ubi_err("unsupported on-flash UBI format\n");
 		return -EINVAL;
@@ -285,19 +342,25 @@
 			return 1;
 		}
 	} else {
-		pnum = seb->pnum;
+		if (!seb->copy_flag) {
+			/* It is not a copy, so it is newer */
+			dbg_bld("first PEB %d is newer, copy_flag is unset",
+				pnum);
+			return bitflips << 1;
+		}
 
 		vh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL);
 		if (!vh)
 			return -ENOMEM;
 
+		pnum = seb->pnum;
 		err = ubi_io_read_vid_hdr(ubi, pnum, vh, 0);
 		if (err) {
 			if (err == UBI_IO_BITFLIPS)
 				bitflips = 1;
 			else {
 				dbg_err("VID of PEB %d header is bad, but it "
-					"was OK earlier", pnum);
+					"was OK earlier, err %d", pnum, err);
 				if (err > 0)
 					err = -EIO;
 
@@ -305,14 +368,6 @@
 			}
 		}
 
-		if (!vh->copy_flag) {
-			/* It is not a copy, so it is newer */
-			dbg_bld("first PEB %d is newer, copy_flag is unset",
-				pnum);
-			err = bitflips << 1;
-			goto out_free_vidh;
-		}
-
 		vid_hdr = vh;
 	}
 
@@ -463,18 +518,15 @@
 			if (err)
 				return err;
 
-			if (cmp_res & 4)
-				err = add_to_list(si, seb->pnum, seb->ec,
-						  &si->corr);
-			else
-				err = add_to_list(si, seb->pnum, seb->ec,
-						  &si->erase);
+			err = add_to_list(si, seb->pnum, seb->ec, cmp_res & 4,
+					  &si->erase);
 			if (err)
 				return err;
 
 			seb->ec = ec;
 			seb->pnum = pnum;
 			seb->scrub = ((cmp_res & 2) || bitflips);
+			seb->copy_flag = vid_hdr->copy_flag;
 			seb->sqnum = sqnum;
 
 			if (sv->highest_lnum == lnum)
@@ -487,10 +539,8 @@
 			 * This logical eraseblock is older than the one found
 			 * previously.
 			 */
-			if (cmp_res & 4)
-				return add_to_list(si, pnum, ec, &si->corr);
-			else
-				return add_to_list(si, pnum, ec, &si->erase);
+			return add_to_list(si, pnum, ec, cmp_res & 4,
+					   &si->erase);
 		}
 	}
 
@@ -510,8 +560,9 @@
 	seb->ec = ec;
 	seb->pnum = pnum;
 	seb->lnum = lnum;
-	seb->sqnum = sqnum;
 	seb->scrub = bitflips;
+	seb->copy_flag = vid_hdr->copy_flag;
+	seb->sqnum = sqnum;
 
 	if (sv->highest_lnum <= lnum) {
 		sv->highest_lnum = lnum;
@@ -521,7 +572,6 @@
 	sv->leb_count += 1;
 	rb_link_node(&seb->u.rb, parent, p);
 	rb_insert_color(&seb->u.rb, &sv->root);
-	si->used_peb_count += 1;
 	return 0;
 }
 
@@ -668,8 +718,8 @@
 struct ubi_scan_leb *ubi_scan_get_free_peb(struct ubi_device *ubi,
 					   struct ubi_scan_info *si)
 {
-	int err = 0, i;
-	struct ubi_scan_leb *seb;
+	int err = 0;
+	struct ubi_scan_leb *seb, *tmp_seb;
 
 	if (!list_empty(&si->free)) {
 		seb = list_entry(si->free.next, struct ubi_scan_leb, u.list);
@@ -678,41 +728,89 @@
 		return seb;
 	}
 
-	for (i = 0; i < 2; i++) {
-		struct list_head *head;
-		struct ubi_scan_leb *tmp_seb;
+	/*
+	 * We try to erase the first physical eraseblock from the erase list
+	 * and pick it if we succeed, or try to erase the next one if not. And
+	 * so forth. We don't want to take care about bad eraseblocks here -
+	 * they'll be handled later.
+	 */
+	list_for_each_entry_safe(seb, tmp_seb, &si->erase, u.list) {
+		if (seb->ec == UBI_SCAN_UNKNOWN_EC)
+			seb->ec = si->mean_ec;
 
-		if (i == 0)
-			head = &si->erase;
-		else
-			head = &si->corr;
+		err = ubi_scan_erase_peb(ubi, si, seb->pnum, seb->ec+1);
+		if (err)
+			continue;
 
-		/*
-		 * We try to erase the first physical eraseblock from the @head
-		 * list and pick it if we succeed, or try to erase the
-		 * next one if not. And so forth. We don't want to take care
-		 * about bad eraseblocks here - they'll be handled later.
-		 */
-		list_for_each_entry_safe(seb, tmp_seb, head, u.list) {
-			if (seb->ec == UBI_SCAN_UNKNOWN_EC)
-				seb->ec = si->mean_ec;
-
-			err = ubi_scan_erase_peb(ubi, si, seb->pnum, seb->ec+1);
-			if (err)
-				continue;
-
-			seb->ec += 1;
-			list_del(&seb->u.list);
-			dbg_bld("return PEB %d, EC %d", seb->pnum, seb->ec);
-			return seb;
-		}
+		seb->ec += 1;
+		list_del(&seb->u.list);
+		dbg_bld("return PEB %d, EC %d", seb->pnum, seb->ec);
+		return seb;
 	}
 
-	ubi_err("no eraseblocks found");
+	ubi_err("no free eraseblocks");
 	return ERR_PTR(-ENOSPC);
 }
 
 /**
+ * check_corruption - check the data area of PEB.
+ * @ubi: UBI device description object
+ * @vid_hrd: the (corrupted) VID header of this PEB
+ * @pnum: the physical eraseblock number to check
+ *
+ * This is a helper function which is used to distinguish between VID header
+ * corruptions caused by power cuts and other reasons. If the PEB contains only
+ * 0xFF bytes in the data area, the VID header is most probably corrupted
+ * because of a power cut (%0 is returned in this case). Otherwise, it was
+ * probably corrupted for some other reasons (%1 is returned in this case). A
+ * negative error code is returned if a read error occurred.
+ *
+ * If the corruption reason was a power cut, UBI can safely erase this PEB.
+ * Otherwise, it should preserve it to avoid possibly destroying important
+ * information.
+ */
+static int check_corruption(struct ubi_device *ubi, struct ubi_vid_hdr *vid_hdr,
+			    int pnum)
+{
+	int err;
+
+	mutex_lock(&ubi->buf_mutex);
+	memset(ubi->peb_buf1, 0x00, ubi->leb_size);
+
+	err = ubi_io_read(ubi, ubi->peb_buf1, pnum, ubi->leb_start,
+			  ubi->leb_size);
+	if (err == UBI_IO_BITFLIPS || err == -EBADMSG) {
+		/*
+		 * Bit-flips or integrity errors while reading the data area.
+		 * It is difficult to say for sure what type of corruption is
+		 * this, but presumably a power cut happened while this PEB was
+		 * erased, so it became unstable and corrupted, and should be
+		 * erased.
+		 */
+		return 0;
+	}
+
+	if (err)
+		return err;
+
+	if (ubi_check_pattern(ubi->peb_buf1, 0xFF, ubi->leb_size)) {
+		mutex_unlock(&ubi->buf_mutex);
+		return 0;
+	}
+
+	ubi_err("PEB %d contains corrupted VID header, and the data does not "
+		"contain all 0xFF, this may be a non-UBI PEB or a severe VID "
+		"header corruption which requires manual inspection", pnum);
+	ubi_dbg_dump_vid_hdr(vid_hdr);
+	dbg_msg("hexdump of PEB %d offset %d, length %d",
+		pnum, ubi->leb_start, ubi->leb_size);
+	ubi_dbg_print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 32, 1,
+			       ubi->peb_buf1, ubi->leb_size, 1);
+	mutex_unlock(&ubi->buf_mutex);
+	return 1;
+}
+
+/**
  * process_eb - read, check UBI headers, and add them to scanning information.
  * @ubi: UBI device description object
  * @si: scanning information
@@ -725,7 +823,7 @@
 		      int pnum)
 {
 	long long uninitialized_var(ec);
-	int err, bitflips = 0, vol_id, ec_corr = 0;
+	int err, bitflips = 0, vol_id, ec_err = 0;
 
 	dbg_bld("scan PEB %d", pnum);
 
@@ -746,22 +844,37 @@
 	err = ubi_io_read_ec_hdr(ubi, pnum, ech, 0);
 	if (err < 0)
 		return err;
-	else if (err == UBI_IO_BITFLIPS)
+	switch (err) {
+	case 0:
+		break;
+	case UBI_IO_BITFLIPS:
 		bitflips = 1;
-	else if (err == UBI_IO_PEB_EMPTY)
-		return add_to_list(si, pnum, UBI_SCAN_UNKNOWN_EC, &si->erase);
-	else if (err == UBI_IO_BAD_HDR_READ || err == UBI_IO_BAD_HDR) {
+		break;
+	case UBI_IO_FF:
+		si->empty_peb_count += 1;
+		return add_to_list(si, pnum, UBI_SCAN_UNKNOWN_EC, 0,
+				   &si->erase);
+	case UBI_IO_FF_BITFLIPS:
+		si->empty_peb_count += 1;
+		return add_to_list(si, pnum, UBI_SCAN_UNKNOWN_EC, 1,
+				   &si->erase);
+	case UBI_IO_BAD_HDR_EBADMSG:
+	case UBI_IO_BAD_HDR:
 		/*
 		 * We have to also look at the VID header, possibly it is not
 		 * corrupted. Set %bitflips flag in order to make this PEB be
 		 * moved and EC be re-created.
 		 */
-		ec_corr = err;
+		ec_err = err;
 		ec = UBI_SCAN_UNKNOWN_EC;
 		bitflips = 1;
+		break;
+	default:
+		ubi_err("'ubi_io_read_ec_hdr()' returned unknown code %d", err);
+		return -EINVAL;
 	}
 
-	if (!ec_corr) {
+	if (!ec_err) {
 		int image_seq;
 
 		/* Make sure UBI version is OK */
@@ -814,24 +927,67 @@
 	err = ubi_io_read_vid_hdr(ubi, pnum, vidh, 0);
 	if (err < 0)
 		return err;
-	else if (err == UBI_IO_BITFLIPS)
+	switch (err) {
+	case 0:
+		break;
+	case UBI_IO_BITFLIPS:
 		bitflips = 1;
-	else if (err == UBI_IO_BAD_HDR_READ || err == UBI_IO_BAD_HDR ||
-		 (err == UBI_IO_PEB_FREE && ec_corr)) {
-		/* VID header is corrupted */
-		if (err == UBI_IO_BAD_HDR_READ ||
-		    ec_corr == UBI_IO_BAD_HDR_READ)
-			si->read_err_count += 1;
-		err = add_to_list(si, pnum, ec, &si->corr);
+		break;
+	case UBI_IO_BAD_HDR_EBADMSG:
+		if (ec_err == UBI_IO_BAD_HDR_EBADMSG)
+			/*
+			 * Both EC and VID headers are corrupted and were read
+			 * with data integrity error, probably this is a bad
+			 * PEB, bit it is not marked as bad yet. This may also
+			 * be a result of power cut during erasure.
+			 */
+			si->maybe_bad_peb_count += 1;
+	case UBI_IO_BAD_HDR:
+		if (ec_err)
+			/*
+			 * Both headers are corrupted. There is a possibility
+			 * that this a valid UBI PEB which has corresponding
+			 * LEB, but the headers are corrupted. However, it is
+			 * impossible to distinguish it from a PEB which just
+			 * contains garbage because of a power cut during erase
+			 * operation. So we just schedule this PEB for erasure.
+			 */
+			err = 0;
+		else
+			/*
+			 * The EC was OK, but the VID header is corrupted. We
+			 * have to check what is in the data area.
+			 */
+			err = check_corruption(ubi, vidh, pnum);
+
+		if (err < 0)
+			return err;
+		else if (!err)
+			/* This corruption is caused by a power cut */
+			err = add_to_list(si, pnum, ec, 1, &si->erase);
+		else
+			/* This is an unexpected corruption */
+			err = add_corrupted(si, pnum, ec);
 		if (err)
 			return err;
 		goto adjust_mean_ec;
-	} else if (err == UBI_IO_PEB_FREE) {
-		/* No VID header - the physical eraseblock is free */
-		err = add_to_list(si, pnum, ec, &si->free);
+	case UBI_IO_FF_BITFLIPS:
+		err = add_to_list(si, pnum, ec, 1, &si->erase);
 		if (err)
 			return err;
 		goto adjust_mean_ec;
+	case UBI_IO_FF:
+		if (ec_err)
+			err = add_to_list(si, pnum, ec, 1, &si->erase);
+		else
+			err = add_to_list(si, pnum, ec, 0, &si->free);
+		if (err)
+			return err;
+		goto adjust_mean_ec;
+	default:
+		ubi_err("'ubi_io_read_vid_hdr()' returned unknown code %d",
+			err);
+		return -EINVAL;
 	}
 
 	vol_id = be32_to_cpu(vidh->vol_id);
@@ -843,7 +999,7 @@
 		case UBI_COMPAT_DELETE:
 			ubi_msg("\"delete\" compatible internal volume %d:%d"
 				" found, will remove it", vol_id, lnum);
-			err = add_to_list(si, pnum, ec, &si->erase);
+			err = add_to_list(si, pnum, ec, 1, &si->erase);
 			if (err)
 				return err;
 			return 0;
@@ -858,7 +1014,7 @@
 		case UBI_COMPAT_PRESERVE:
 			ubi_msg("\"preserve\" compatible internal volume %d:%d"
 				" found", vol_id, lnum);
-			err = add_to_list(si, pnum, ec, &si->alien);
+			err = add_to_list(si, pnum, ec, 0, &si->alien);
 			if (err)
 				return err;
 			return 0;
@@ -870,7 +1026,7 @@
 		}
 	}
 
-	if (ec_corr)
+	if (ec_err)
 		ubi_warn("valid VID header but corrupted EC header at PEB %d",
 			 pnum);
 	err = ubi_scan_add_used(ubi, si, pnum, ec, vidh, bitflips);
@@ -878,7 +1034,7 @@
 		return err;
 
 adjust_mean_ec:
-	if (!ec_corr) {
+	if (!ec_err) {
 		si->ec_sum += ec;
 		si->ec_count += 1;
 		if (ec > si->max_ec)
@@ -904,19 +1060,20 @@
 static int check_what_we_have(struct ubi_device *ubi, struct ubi_scan_info *si)
 {
 	struct ubi_scan_leb *seb;
-	int max_corr;
+	int max_corr, peb_count;
 
-	max_corr = ubi->peb_count - si->bad_peb_count - si->alien_peb_count;
-	max_corr = max_corr / 20 ?: 8;
+	peb_count = ubi->peb_count - si->bad_peb_count - si->alien_peb_count;
+	max_corr = peb_count / 20 ?: 8;
 
 	/*
-	 * Few corrupted PEBs are not a problem and may be just a result of
+	 * Few corrupted PEBs is not a problem and may be just a result of
 	 * unclean reboots. However, many of them may indicate some problems
 	 * with the flash HW or driver.
 	 */
-	if (si->corr_peb_count >= 8) {
-		ubi_warn("%d PEBs are corrupted", si->corr_peb_count);
-		printk(KERN_WARNING "corrupted PEBs are:");
+	if (si->corr_peb_count) {
+		ubi_err("%d PEBs are corrupted and preserved",
+			si->corr_peb_count);
+		printk(KERN_ERR "Corrupted PEBs are:");
 		list_for_each_entry(seb, &si->corr, u.list)
 			printk(KERN_CONT " %d", seb->pnum);
 		printk(KERN_CONT "\n");
@@ -931,41 +1088,35 @@
 		}
 	}
 
-	if (si->free_peb_count + si->used_peb_count +
-	    si->alien_peb_count == 0) {
-		/* No UBI-formatted eraseblocks were found */
-		if (si->corr_peb_count == si->read_err_count &&
-		    si->corr_peb_count < 8) {
-			/* No or just few corrupted PEBs, and all of them had a
-			 * read error. We assume that those are bad PEBs, which
-			 * were just not marked as bad so far.
-			 *
-			 * This piece of code basically tries to distinguish
-			 * between the following 2 situations:
-			 *
-			 * 1. Flash is empty, but there are few bad PEBs, which
-			 *    are not marked as bad so far, and which were read
-			 *    with error. We want to go ahead and format this
-			 *    flash. While formating, the faulty PEBs will
-			 *    probably be marked as bad.
-			 *
-			 * 2. Flash probably contains non-UBI data and we do
-			 * not want to format it and destroy possibly needed
-			 * data (e.g., consider the case when the bootloader
-			 * MTD partition was accidentally fed to UBI).
-			 */
+	if (si->empty_peb_count + si->maybe_bad_peb_count == peb_count) {
+		/*
+		 * All PEBs are empty, or almost all - a couple PEBs look like
+		 * they may be bad PEBs which were not marked as bad yet.
+		 *
+		 * This piece of code basically tries to distinguish between
+		 * the following situations:
+		 *
+		 * 1. Flash is empty, but there are few bad PEBs, which are not
+		 *    marked as bad so far, and which were read with error. We
+		 *    want to go ahead and format this flash. While formatting,
+		 *    the faulty PEBs will probably be marked as bad.
+		 *
+		 * 2. Flash contains non-UBI data and we do not want to format
+		 *    it and destroy possibly important information.
+		 */
+		if (si->maybe_bad_peb_count <= 2) {
 			si->is_empty = 1;
 			ubi_msg("empty MTD device detected");
-			get_random_bytes(&ubi->image_seq, sizeof(ubi->image_seq));
+			get_random_bytes(&ubi->image_seq,
+					 sizeof(ubi->image_seq));
 		} else {
-			ubi_err("MTD device possibly contains non-UBI data, "
-				"refusing it");
+			ubi_err("MTD device is not UBI-formatted and possibly "
+				"contains non-UBI data - refusing it");
 			return -EINVAL;
 		}
+
 	}
 
-	if (si->corr_peb_count > 0)
-		ubi_msg("corrupted PEBs will be formatted");
 	return 0;
 }
 
diff --git a/drivers/mtd/ubi/scan.h b/drivers/mtd/ubi/scan.h
index 2576a8d..a3264f0 100644
--- a/drivers/mtd/ubi/scan.h
+++ b/drivers/mtd/ubi/scan.h
@@ -30,6 +30,7 @@
  * @pnum: physical eraseblock number
  * @lnum: logical eraseblock number
  * @scrub: if this physical eraseblock needs scrubbing
+ * @copy_flag: this LEB is a copy (@copy_flag is set in VID header of this LEB)
  * @sqnum: sequence number
  * @u: unions RB-tree or @list links
  * @u.rb: link in the per-volume RB-tree of &struct ubi_scan_leb objects
@@ -42,7 +43,8 @@
 	int ec;
 	int pnum;
 	int lnum;
-	int scrub;
+	unsigned int scrub:1;
+	unsigned int copy_flag:1;
 	unsigned long long sqnum;
 	union {
 		struct rb_node rb;
@@ -91,14 +93,13 @@
  * @erase: list of physical eraseblocks which have to be erased
  * @alien: list of physical eraseblocks which should not be used by UBI (e.g.,
  *         those belonging to "preserve"-compatible internal volumes)
- * @used_peb_count: count of used PEBs
  * @corr_peb_count: count of PEBs in the @corr list
- * @read_err_count: count of PEBs read with error (%UBI_IO_BAD_HDR_READ was
- *                  returned)
- * @free_peb_count: count of PEBs in the @free list
- * @erase_peb_count: count of PEBs in the @erase list
+ * @empty_peb_count: count of PEBs which are presumably empty (contain only
+ *                   0xFF bytes)
  * @alien_peb_count: count of PEBs in the @alien list
  * @bad_peb_count: count of bad physical eraseblocks
+ * @maybe_bad_peb_count: count of bad physical eraseblocks which are not marked
+ *                       as bad yet, but which look like bad
  * @vols_found: number of volumes found during scanning
  * @highest_vol_id: highest volume ID
  * @is_empty: flag indicating whether the MTD device is empty or not
@@ -119,13 +120,11 @@
 	struct list_head free;
 	struct list_head erase;
 	struct list_head alien;
-	int used_peb_count;
 	int corr_peb_count;
-	int read_err_count;
-	int free_peb_count;
-	int erase_peb_count;
+	int empty_peb_count;
 	int alien_peb_count;
 	int bad_peb_count;
+	int maybe_bad_peb_count;
 	int vols_found;
 	int highest_vol_id;
 	int is_empty;
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index 0359e0c..0b0149c 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -85,21 +85,26 @@
 /*
  * Error codes returned by the I/O sub-system.
  *
- * UBI_IO_PEB_EMPTY: the physical eraseblock is empty, i.e. it contains only
- *                   %0xFF bytes
- * UBI_IO_PEB_FREE: the physical eraseblock is free, i.e. it contains only a
- *                  valid erase counter header, and the rest are %0xFF bytes
+ * UBI_IO_FF: the read region of flash contains only 0xFFs
+ * UBI_IO_FF_BITFLIPS: the same as %UBI_IO_FF, but also also there was a data
+ *                     integrity error reported by the MTD driver
+ *                     (uncorrectable ECC error in case of NAND)
  * UBI_IO_BAD_HDR: the EC or VID header is corrupted (bad magic or CRC)
- * UBI_IO_BAD_HDR_READ: the same as %UBI_IO_BAD_HDR, but also there was a read
- * 			error reported by the flash driver
+ * UBI_IO_BAD_HDR_EBADMSG: the same as %UBI_IO_BAD_HDR, but also there was a
+ *                         data integrity error reported by the MTD driver
+ *                         (uncorrectable ECC error in case of NAND)
  * UBI_IO_BITFLIPS: bit-flips were detected and corrected
+ *
+ * Note, it is probably better to have bit-flip and ebadmsg as flags which can
+ * be or'ed with other error code. But this is a big change because there are
+ * may callers, so it does not worth the risk of introducing a bug
  */
 enum {
-	UBI_IO_PEB_EMPTY = 1,
-	UBI_IO_PEB_FREE,
+	UBI_IO_FF = 1,
+	UBI_IO_FF_BITFLIPS,
 	UBI_IO_BAD_HDR,
-	UBI_IO_BAD_HDR_READ,
-	UBI_IO_BITFLIPS
+	UBI_IO_BAD_HDR_EBADMSG,
+	UBI_IO_BITFLIPS,
 };
 
 /*
@@ -356,6 +361,8 @@
  * @peb_size: physical eraseblock size
  * @bad_peb_count: count of bad physical eraseblocks
  * @good_peb_count: count of good physical eraseblocks
+ * @corr_peb_count: count of corrupted physical eraseblocks (preserved and not
+ *                  used by UBI)
  * @erroneous_peb_count: count of erroneous physical eraseblocks in @erroneous
  * @max_erroneous: maximum allowed amount of erroneous physical eraseblocks
  * @min_io_size: minimal input/output unit size of the underlying MTD device
@@ -442,6 +449,7 @@
 	int peb_size;
 	int bad_peb_count;
 	int good_peb_count;
+	int corr_peb_count;
 	int erroneous_peb_count;
 	int max_erroneous;
 	int min_io_size;
@@ -506,6 +514,7 @@
 		      int length);
 int ubi_check_volume(struct ubi_device *ubi, int vol_id);
 void ubi_calculate_reserved(struct ubi_device *ubi);
+int ubi_check_pattern(const void *buf, uint8_t patt, int size);
 
 /* eba.c */
 int ubi_eba_unmap_leb(struct ubi_device *ubi, struct ubi_volume *vol,
diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c
index e42afab..c47620d 100644
--- a/drivers/mtd/ubi/vmt.c
+++ b/drivers/mtd/ubi/vmt.c
@@ -261,6 +261,9 @@
 	/* Reserve physical eraseblocks */
 	if (vol->reserved_pebs > ubi->avail_pebs) {
 		dbg_err("not enough PEBs, only %d available", ubi->avail_pebs);
+		if (ubi->corr_peb_count)
+			dbg_err("%d PEBs are corrupted and not used",
+				ubi->corr_peb_count);
 		err = -ENOSPC;
 		goto out_unlock;
 	}
@@ -527,6 +530,9 @@
 		if (pebs > ubi->avail_pebs) {
 			dbg_err("not enough PEBs: requested %d, available %d",
 				pebs, ubi->avail_pebs);
+			if (ubi->corr_peb_count)
+				dbg_err("%d PEBs are corrupted and not used",
+					ubi->corr_peb_count);
 			spin_unlock(&ubi->volumes_lock);
 			err = -ENOSPC;
 			goto out_free;
diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c
index 14c10be..fcdb7f6 100644
--- a/drivers/mtd/ubi/vtbl.c
+++ b/drivers/mtd/ubi/vtbl.c
@@ -366,7 +366,7 @@
 		 * Probably this physical eraseblock went bad, try to pick
 		 * another one.
 		 */
-		list_add_tail(&new_seb->u.list, &si->corr);
+		list_add(&new_seb->u.list, &si->erase);
 		goto retry;
 	}
 	kfree(new_seb);
@@ -662,9 +662,13 @@
 	ubi->vol_count += 1;
 	vol->ubi = ubi;
 
-	if (reserved_pebs > ubi->avail_pebs)
+	if (reserved_pebs > ubi->avail_pebs) {
 		ubi_err("not enough PEBs, required %d, available %d",
 			reserved_pebs, ubi->avail_pebs);
+		if (ubi->corr_peb_count)
+			ubi_err("%d PEBs are corrupted and not used",
+				ubi->corr_peb_count);
+	}
 	ubi->rsvd_pebs += reserved_pebs;
 	ubi->avail_pebs -= reserved_pebs;
 
@@ -837,7 +841,7 @@
 			return PTR_ERR(ubi->vtbl);
 	}
 
-	ubi->avail_pebs = ubi->good_peb_count;
+	ubi->avail_pebs = ubi->good_peb_count - ubi->corr_peb_count;
 
 	/*
 	 * The layout volume is OK, initialize the corresponding in-RAM data
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 97a4356..655bbbe 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -745,7 +745,7 @@
 
 	err = ubi_io_read_vid_hdr(ubi, e1->pnum, vid_hdr, 0);
 	if (err && err != UBI_IO_BITFLIPS) {
-		if (err == UBI_IO_PEB_FREE) {
+		if (err == UBI_IO_FF) {
 			/*
 			 * We are trying to move PEB without a VID header. UBI
 			 * always write VID headers shortly after the PEB was
@@ -759,6 +759,16 @@
 			dbg_wl("PEB %d has no VID header", e1->pnum);
 			protect = 1;
 			goto out_not_moved;
+		} else if (err == UBI_IO_FF_BITFLIPS) {
+			/*
+			 * The same situation as %UBI_IO_FF, but bit-flips were
+			 * detected. It is better to schedule this PEB for
+			 * scrubbing.
+			 */
+			dbg_wl("PEB %d has no VID header but has bit-flips",
+			       e1->pnum);
+			scrubbing = 1;
+			goto out_not_moved;
 		}
 
 		ubi_err("error %d while reading VID header from PEB %d",
@@ -1468,22 +1478,6 @@
 		ubi->lookuptbl[e->pnum] = e;
 	}
 
-	list_for_each_entry(seb, &si->corr, u.list) {
-		cond_resched();
-
-		e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
-		if (!e)
-			goto out_free;
-
-		e->pnum = seb->pnum;
-		e->ec = seb->ec;
-		ubi->lookuptbl[e->pnum] = e;
-		if (schedule_erase(ubi, e, 0)) {
-			kmem_cache_free(ubi_wl_entry_slab, e);
-			goto out_free;
-		}
-	}
-
 	ubi_rb_for_each_entry(rb1, sv, &si->volumes, rb) {
 		ubi_rb_for_each_entry(rb2, seb, &sv->root, u.rb) {
 			cond_resched();
@@ -1510,6 +1504,9 @@
 	if (ubi->avail_pebs < WL_RESERVED_PEBS) {
 		ubi_err("no enough physical eraseblocks (%d, need %d)",
 			ubi->avail_pebs, WL_RESERVED_PEBS);
+		if (ubi->corr_peb_count)
+			ubi_err("%d PEBs are corrupted and not used",
+				ubi->corr_peb_count);
 		goto out_free;
 	}
 	ubi->avail_pebs -= WL_RESERVED_PEBS;
diff --git a/drivers/net/3c527.c b/drivers/net/3c527.c
index 70705d1..eca55c5 100644
--- a/drivers/net/3c527.c
+++ b/drivers/net/3c527.c
@@ -522,7 +522,7 @@
 	lp->tx_len 		= lp->exec_box->data[9];   /* Transmit list count */
 	lp->rx_len 		= lp->exec_box->data[11];  /* Receive list count */
 
-	init_MUTEX_LOCKED(&lp->cmd_mutex);
+	sema_init(&lp->cmd_mutex, 0);
 	init_completion(&lp->execution_cmd);
 	init_completion(&lp->xceiver_cmd);
 
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 5db667c..77efe46 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2,6 +2,9 @@
 # Network device configuration
 #
 
+config HAVE_NET_MACB
+	bool
+
 menuconfig NETDEVICES
 	default y if UML
 	depends on NET
@@ -221,7 +224,7 @@
 
 config MACB
 	tristate "Atmel MACB support"
-	depends on AVR32 || ARCH_AT91SAM9260 || ARCH_AT91SAM9263 || ARCH_AT91SAM9G20 || ARCH_AT91SAM9G45 || ARCH_AT91CAP9
+	depends on HAVE_NET_MACB
 	select PHYLIB
 	help
 	  The Atmel MACB ethernet interface is found on many AT32 and AT91
diff --git a/drivers/net/appletalk/Kconfig b/drivers/net/appletalk/Kconfig
index 0a0e0cd..20f97e7 100644
--- a/drivers/net/appletalk/Kconfig
+++ b/drivers/net/appletalk/Kconfig
@@ -3,6 +3,7 @@
 #
 config ATALK
 	tristate "Appletalk protocol support"
+	depends on BKL # waiting to be removed from net/appletalk/ddp.c
 	select LLC
 	---help---
 	  AppleTalk is the protocol that Apple computers can use to communicate
diff --git a/drivers/net/bfin_mac.c b/drivers/net/bfin_mac.c
index 012613f..03d0635 100644
--- a/drivers/net/bfin_mac.c
+++ b/drivers/net/bfin_mac.c
@@ -38,6 +38,7 @@
 #include <asm/blackfin.h>
 #include <asm/cacheflush.h>
 #include <asm/portmux.h>
+#include <mach/pll.h>
 
 #include "bfin_mac.h"
 
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
index f5058ff..8427533 100644
--- a/drivers/net/caif/caif_spi.c
+++ b/drivers/net/caif/caif_spi.c
@@ -240,13 +240,15 @@
 static const struct file_operations dbgfs_state_fops = {
 	.open = dbgfs_open,
 	.read = dbgfs_state,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations dbgfs_frame_fops = {
 	.open = dbgfs_open,
 	.read = dbgfs_frame,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 static inline void dev_debugfs_add(struct cfspi *cfspi)
diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index c327527..e2bf10d 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -2026,6 +2026,7 @@
 	.owner   = THIS_MODULE,
 	.open    = mem_open,
 	.read    = mem_read,
+	.llseek  = default_llseek,
 };
 
 static void __devinit add_debugfs_mem(struct adapter *adap, const char *name,
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 4b52c76..3e5d0b6 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -608,7 +608,7 @@
 
 	spin_lock_init(&sp->lock);
 	atomic_set(&sp->refcnt, 1);
-	init_MUTEX_LOCKED(&sp->dead_sem);
+	sema_init(&sp->dead_sem, 0);
 
 	/* !!! length of the buffers. MTU is IP MTU, not PACLEN!  */
 
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 66e88bd..4c62839 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -747,7 +747,7 @@
 
 	spin_lock_init(&ax->buflock);
 	atomic_set(&ax->refcnt, 1);
-	init_MUTEX_LOCKED(&ax->dead_sem);
+	sema_init(&ax->dead_sem, 0);
 
 	ax->tty = tty;
 	tty->disc_data = ax;
diff --git a/drivers/net/irda/sir_dev.c b/drivers/net/irda/sir_dev.c
index 1b051da..51d7444 100644
--- a/drivers/net/irda/sir_dev.c
+++ b/drivers/net/irda/sir_dev.c
@@ -909,7 +909,7 @@
 	dev->tx_skb = NULL;
 
 	spin_lock_init(&dev->tx_lock);
-	init_MUTEX(&dev->fsm.sem);
+	sema_init(&dev->fsm.sem, 1);
 
 	dev->drv = drv;
 	dev->netdev = ndev;
diff --git a/drivers/net/pcmcia/3c574_cs.c b/drivers/net/pcmcia/3c574_cs.c
index c683f77..ff824e11 100644
--- a/drivers/net/pcmcia/3c574_cs.c
+++ b/drivers/net/pcmcia/3c574_cs.c
@@ -87,7 +87,6 @@
 #include <linux/bitops.h>
 #include <linux/mii.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ciscode.h>
@@ -280,25 +279,15 @@
 	spin_lock_init(&lp->window_lock);
 	link->resource[0]->end = 32;
 	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-	link->conf.ConfigIndex = 1;
+	link->config_flags |= CONF_ENABLE_IRQ;
+	link->config_index = 1;
 
 	dev->netdev_ops = &el3_netdev_ops;
 	SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
 	dev->watchdog_timeo = TX_TIMEOUT;
 
 	return tc574_config(link);
-} /* tc574_attach */
-
-/*
-
-	This deletes a driver "instance".  The device is de-registered
-	with Card Services.  If it has been released, all local data
-	structures are freed.  Otherwise, the structures will be freed
-	when the device is released.
-
-*/
+}
 
 static void tc574_detach(struct pcmcia_device *link)
 {
@@ -313,12 +302,6 @@
 	free_netdev(dev);
 } /* tc574_detach */
 
-/*
-	tc574_config() is scheduled to run after a CARD_INSERTION event
-	is received, to configure the PCMCIA socket, and to make the
-	ethernet device available to the system.
-*/
-
 static const char *ram_split[] = {"5:3", "3:1", "1:1", "3:5"};
 
 static int tc574_config(struct pcmcia_device *link)
@@ -352,7 +335,7 @@
 	if (ret)
 		goto failed;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -465,12 +448,6 @@
 
 } /* tc574_config */
 
-/*
-	After a card is removed, tc574_release() will unregister the net
-	device, and release the PCMCIA configuration.  If the device is
-	still open, this will be postponed until it is closed.
-*/
-
 static void tc574_release(struct pcmcia_device *link)
 {
 	pcmcia_disable_device(link);
@@ -1198,9 +1175,7 @@
 
 static struct pcmcia_driver tc574_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "3c574_cs",
-	},
+	.name		= "3c574_cs",
 	.probe		= tc574_probe,
 	.remove		= tc574_detach,
 	.id_table       = tc574_ids,
diff --git a/drivers/net/pcmcia/3c589_cs.c b/drivers/net/pcmcia/3c589_cs.c
index 61f9cf2..a07e222 100644
--- a/drivers/net/pcmcia/3c589_cs.c
+++ b/drivers/net/pcmcia/3c589_cs.c
@@ -41,7 +41,6 @@
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ciscode.h>
@@ -176,14 +175,6 @@
 
 static void tc589_detach(struct pcmcia_device *p_dev);
 
-/*======================================================================
-
-    tc589_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-======================================================================*/
-
 static const struct net_device_ops el3_netdev_ops = {
 	.ndo_open		= el3_open,
 	.ndo_stop		= el3_close,
@@ -216,9 +207,8 @@
     link->resource[0]->end = 16;
     link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
 
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-    link->conf.ConfigIndex = 1;
+    link->config_flags |= CONF_ENABLE_IRQ;
+    link->config_index = 1;
 
     dev->netdev_ops = &el3_netdev_ops;
     dev->watchdog_timeo = TX_TIMEOUT;
@@ -226,16 +216,7 @@
     SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
 
     return tc589_config(link);
-} /* tc589_attach */
-
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
+}
 
 static void tc589_detach(struct pcmcia_device *link)
 {
@@ -250,14 +231,6 @@
     free_netdev(dev);
 } /* tc589_detach */
 
-/*======================================================================
-
-    tc589_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ethernet device available to the system.
-
-======================================================================*/
-
 static int tc589_config(struct pcmcia_device *link)
 {
     struct net_device *dev = link->priv;
@@ -294,7 +267,7 @@
     if (ret)
 	    goto failed;
 
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
@@ -352,14 +325,6 @@
     return -ENODEV;
 } /* tc589_config */
 
-/*======================================================================
-
-    After a card is removed, tc589_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void tc589_release(struct pcmcia_device *link)
 {
 	pcmcia_disable_device(link);
@@ -955,9 +920,7 @@
 
 static struct pcmcia_driver tc589_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "3c589_cs",
-	},
+	.name		= "3c589_cs",
 	.probe		= tc589_probe,
 	.remove		= tc589_detach,
 	.id_table	= tc589_ids,
diff --git a/drivers/net/pcmcia/axnet_cs.c b/drivers/net/pcmcia/axnet_cs.c
index 5f05ffb..9e8b28b 100644
--- a/drivers/net/pcmcia/axnet_cs.c
+++ b/drivers/net/pcmcia/axnet_cs.c
@@ -39,7 +39,6 @@
 #include <linux/mii.h>
 #include "../8390.h"
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -140,14 +139,6 @@
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-/*======================================================================
-
-    axnet_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-======================================================================*/
-
 static int axnet_probe(struct pcmcia_device *link)
 {
     axnet_dev_t *info;
@@ -166,8 +157,7 @@
     info = PRIV(dev);
     info->p_dev = link;
     link->priv = dev;
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
+    link->config_flags |= CONF_ENABLE_IRQ;
 
     dev->netdev_ops = &axnet_netdev_ops;
 
@@ -177,15 +167,6 @@
     return axnet_config(link);
 } /* axnet_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void axnet_detach(struct pcmcia_device *link)
 {
     struct net_device *dev = link->priv;
@@ -231,7 +212,7 @@
     };
 
     /* Not much of a test, but the alternatives are messy */
-    if (link->conf.ConfigBase != 0x03c0)
+    if (link->config_base != 0x03c0)
 	return 0;
 
     axnet_reset_8390(dev);
@@ -248,14 +229,6 @@
     return 1;
 } /* get_prom */
 
-/*======================================================================
-
-    axnet_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ethernet device available to the system.
-
-======================================================================*/
-
 static int try_io_port(struct pcmcia_device *link)
 {
     int j, ret;
@@ -286,35 +259,16 @@
     }
 }
 
-static int axnet_configcheck(struct pcmcia_device *p_dev,
-			     cistpl_cftable_entry_t *cfg,
-			     cistpl_cftable_entry_t *dflt,
-			     unsigned int vcc,
-			     void *priv_data)
+static int axnet_configcheck(struct pcmcia_device *p_dev, void *priv_data)
 {
-	int i;
-	cistpl_io_t *io = &cfg->io;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	if (cfg->index == 0 || cfg->io.nwin == 0)
+	p_dev->config_index = 0x05;
+	if (p_dev->resource[0]->end + p_dev->resource[1]->end < 32)
 		return -ENODEV;
 
-	p_dev->conf.ConfigIndex = 0x05;
-	/* For multifunction cards, by convention, we configure the
-	   network function with window 0, and serial with window 1 */
-	if (io->nwin > 1) {
-		i = (io->win[1].len > io->win[0].len);
-		p_dev->resource[1]->start = io->win[1-i].base;
-		p_dev->resource[1]->end = io->win[1-i].len;
-	} else {
-		i = p_dev->resource[1]->end = 0;
-	}
-	p_dev->resource[0]->start = io->win[i].base;
-	p_dev->resource[0]->end = io->win[i].len;
-	p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-	if (p_dev->resource[0]->end + p_dev->resource[1]->end >= 32)
-		return try_io_port(p_dev);
-
-	return -ENODEV;
+	return try_io_port(p_dev);
 }
 
 static int axnet_config(struct pcmcia_device *link)
@@ -326,20 +280,19 @@
     dev_dbg(&link->dev, "axnet_config(0x%p)\n", link);
 
     /* don't trust the CIS on this; Linksys got it wrong */
-    link->conf.Present = 0x63;
+    link->config_regs = 0x63;
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
     ret = pcmcia_loop_config(link, axnet_configcheck, NULL);
     if (ret != 0)
 	goto failed;
 
     if (!link->irq)
 	    goto failed;
+
+    if (resource_size(link->resource[1]) == 8)
+	link->config_flags |= CONF_ENABLE_SPKR;
     
-    if (resource_size(link->resource[1]) == 8) {
-	link->conf.Attributes |= CONF_ENABLE_SPKR;
-	link->conf.Status = CCSR_AUDIO_ENA;
-    }
-    
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
@@ -414,14 +367,6 @@
     return -ENODEV;
 } /* axnet_config */
 
-/*======================================================================
-
-    After a card is removed, axnet_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void axnet_release(struct pcmcia_device *link)
 {
 	pcmcia_disable_device(link);
@@ -783,9 +728,7 @@
 
 static struct pcmcia_driver axnet_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "axnet_cs",
-	},
+	.name		= "axnet_cs",
 	.probe		= axnet_probe,
 	.remove		= axnet_detach,
 	.id_table       = axnet_ids,
diff --git a/drivers/net/pcmcia/com20020_cs.c b/drivers/net/pcmcia/com20020_cs.c
index 3c400cf..b706a72 100644
--- a/drivers/net/pcmcia/com20020_cs.c
+++ b/drivers/net/pcmcia/com20020_cs.c
@@ -43,7 +43,6 @@
 #include <linux/arcdevice.h>
 #include <linux/com20020.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -123,14 +122,6 @@
     struct net_device       *dev;
 } com20020_dev_t;
 
-/*======================================================================
-
-    com20020_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-======================================================================*/
-
 static int com20020_probe(struct pcmcia_device *p_dev)
 {
     com20020_dev_t *info;
@@ -160,8 +151,7 @@
 
     p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
     p_dev->resource[0]->end = 16;
-    p_dev->conf.Attributes = CONF_ENABLE_IRQ;
-    p_dev->conf.IntType = INT_MEMORY_AND_IO;
+    p_dev->config_flags |= CONF_ENABLE_IRQ;
 
     info->dev = dev;
     p_dev->priv = info;
@@ -174,15 +164,6 @@
     return -ENOMEM;
 } /* com20020_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void com20020_detach(struct pcmcia_device *link)
 {
     struct com20020_dev_t *info = link->priv;
@@ -221,14 +202,6 @@
 
 } /* com20020_detach */
 
-/*======================================================================
-
-    com20020_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-
-======================================================================*/
-
 static int com20020_config(struct pcmcia_device *link)
 {
     struct arcnet_local *lp;
@@ -282,7 +255,7 @@
 
     dev->irq = link->irq;
 
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
@@ -316,14 +289,6 @@
     return -ENODEV;
 } /* com20020_config */
 
-/*======================================================================
-
-    After a card is removed, com20020_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void com20020_release(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "com20020_release\n");
@@ -366,9 +331,7 @@
 
 static struct pcmcia_driver com20020_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "com20020_cs",
-	},
+	.name		= "com20020_cs",
 	.probe		= com20020_probe,
 	.remove		= com20020_detach,
 	.id_table	= com20020_ids,
diff --git a/drivers/net/pcmcia/fmvj18x_cs.c b/drivers/net/pcmcia/fmvj18x_cs.c
index 98fffb0..1c32759 100644
--- a/drivers/net/pcmcia/fmvj18x_cs.c
+++ b/drivers/net/pcmcia/fmvj18x_cs.c
@@ -49,7 +49,6 @@
 #include <linux/ioport.h>
 #include <linux/crc32.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -252,8 +251,7 @@
     link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 
     /* General socket configuration */
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
+    link->config_flags |= CONF_ENABLE_IRQ;
 
     dev->netdev_ops = &fjn_netdev_ops;
     dev->watchdog_timeo = TX_TIMEOUT;
@@ -313,7 +311,7 @@
 	ret = pcmcia_request_io(link);
 	if (ret == 0) {
 	    /* calculate ConfigIndex value */
-	    link->conf.ConfigIndex = 
+	    link->config_index =
 		((link->resource[0]->start & 0x0f0) >> 3) | 0x22;
 	    return ret;
 	}
@@ -321,11 +319,7 @@
     return ret;	/* RequestIO failed */
 }
 
-static int fmvj18x_ioprobe(struct pcmcia_device *p_dev,
-			   cistpl_cftable_entry_t *cfg,
-			   cistpl_cftable_entry_t *dflt,
-			   unsigned int vcc,
-			   void *priv_data)
+static int fmvj18x_ioprobe(struct pcmcia_device *p_dev, void *priv_data)
 {
 	return 0; /* strange, but that's what the code did already before... */
 }
@@ -362,28 +356,28 @@
 		link->card_id == PRODID_TDK_NP9610 ||
 		link->card_id == PRODID_TDK_MN3200) {
 		/* MultiFunction Card */
-		link->conf.ConfigBase = 0x800;
-		link->conf.ConfigIndex = 0x47;
+		link->config_base = 0x800;
+		link->config_index = 0x47;
 		link->resource[1]->end = 8;
 	    }
 	    break;
 	case MANFID_NEC:
 	    cardtype = NEC; /* MultiFunction Card */
-	    link->conf.ConfigBase = 0x800;
-	    link->conf.ConfigIndex = 0x47;
+	    link->config_base = 0x800;
+	    link->config_index = 0x47;
 	    link->resource[1]->end = 8;
 	    break;
 	case MANFID_KME:
 	    cardtype = KME; /* MultiFunction Card */
-	    link->conf.ConfigBase = 0x800;
-	    link->conf.ConfigIndex = 0x47;
+	    link->config_base = 0x800;
+	    link->config_index = 0x47;
 	    link->resource[1]->end = 8;
 	    break;
 	case MANFID_CONTEC:
 	    cardtype = CONTEC;
 	    break;
 	case MANFID_FUJITSU:
-	    if (link->conf.ConfigBase == 0x0fe0)
+	    if (link->config_base == 0x0fe0)
 		cardtype = MBH10302;
 	    else if (link->card_id == PRODID_FUJITSU_MBH10302) 
                 /* RATOC REX-5588/9822/4886's PRODID are 0004(=MBH10302),
@@ -403,10 +397,10 @@
 	case MANFID_FUJITSU:
 	    if (link->card_id == PRODID_FUJITSU_MBH10304) {
 		cardtype = XXX10304;    /* MBH10304 with buggy CIS */
-	        link->conf.ConfigIndex = 0x20;
+		link->config_index = 0x20;
 	    } else {
 		cardtype = MBH10302;    /* NextCom NC5310, etc. */
-		link->conf.ConfigIndex = 1;
+		link->config_index = 1;
 	    }
 	    break;
 	case MANFID_UNGERMANN:
@@ -414,7 +408,7 @@
 	    break;
 	default:
 	    cardtype = MBH10302;
-	    link->conf.ConfigIndex = 1;
+	    link->config_index = 1;
 	}
     }
 
@@ -432,7 +426,7 @@
     ret = pcmcia_request_irq(link, fjn_interrupt);
     if (ret)
 	    goto failed;
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
@@ -544,20 +538,18 @@
 
 static int fmvj18x_get_hwinfo(struct pcmcia_device *link, u_char *node_id)
 {
-    win_req_t req;
     u_char __iomem *base;
     int i, j;
 
     /* Allocate a small memory window */
-    req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
-    req.Base = 0; req.Size = 0;
-    req.AccessSpeed = 0;
-    i = pcmcia_request_window(link, &req, &link->win);
+    link->resource[2]->flags |= WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
+    link->resource[2]->start = 0; link->resource[2]->end = 0;
+    i = pcmcia_request_window(link, link->resource[2], 0);
     if (i != 0)
 	return -1;
 
-    base = ioremap(req.Base, req.Size);
-    pcmcia_map_mem_page(link, link->win, 0);
+    base = ioremap(link->resource[2]->start, resource_size(link->resource[2]));
+    pcmcia_map_mem_page(link, link->resource[2], 0);
 
     /*
      *  MBH10304 CISTPL_FUNCE_LAN_NODE_ID format
@@ -582,7 +574,7 @@
     }
 
     iounmap(base);
-    j = pcmcia_release_window(link, link->win);
+    j = pcmcia_release_window(link, link->resource[2]);
     return (i != 0x200) ? 0 : -1;
 
 } /* fmvj18x_get_hwinfo */
@@ -590,27 +582,26 @@
 
 static int fmvj18x_setup_mfc(struct pcmcia_device *link)
 {
-    win_req_t req;
     int i;
     struct net_device *dev = link->priv;
     unsigned int ioaddr;
     local_info_t *lp = netdev_priv(dev);
 
     /* Allocate a small memory window */
-    req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
-    req.Base = 0; req.Size = 0;
-    req.AccessSpeed = 0;
-    i = pcmcia_request_window(link, &req, &link->win);
+    link->resource[3]->flags = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
+    link->resource[3]->start = link->resource[3]->end = 0;
+    i = pcmcia_request_window(link, link->resource[3], 0);
     if (i != 0)
 	return -1;
 
-    lp->base = ioremap(req.Base, req.Size);
+    lp->base = ioremap(link->resource[3]->start,
+		       resource_size(link->resource[3]));
     if (lp->base == NULL) {
 	printk(KERN_NOTICE "fmvj18x_cs: ioremap failed\n");
 	return -1;
     }
 
-    i = pcmcia_map_mem_page(link, link->win, 0);
+    i = pcmcia_map_mem_page(link, link->resource[3], 0);
     if (i != 0) {
 	iounmap(lp->base);
 	lp->base = NULL;
@@ -638,7 +629,6 @@
     struct net_device *dev = link->priv;
     local_info_t *lp = netdev_priv(dev);
     u_char __iomem *tmp;
-    int j;
 
     dev_dbg(&link->dev, "fmvj18x_release\n");
 
@@ -646,7 +636,6 @@
 	tmp = lp->base;
 	lp->base = NULL;    /* set NULL before iounmap */
 	iounmap(tmp);
-	j = pcmcia_release_window(link, link->win);
     }
 
     pcmcia_disable_device(link);
@@ -708,9 +697,7 @@
 
 static struct pcmcia_driver fmvj18x_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "fmvj18x_cs",
-	},
+	.name		= "fmvj18x_cs",
 	.probe		= fmvj18x_probe,
 	.remove		= fmvj18x_detach,
 	.id_table       = fmvj18x_ids,
diff --git a/drivers/net/pcmcia/ibmtr_cs.c b/drivers/net/pcmcia/ibmtr_cs.c
index b0d06a3..bf7dff9 100644
--- a/drivers/net/pcmcia/ibmtr_cs.c
+++ b/drivers/net/pcmcia/ibmtr_cs.c
@@ -57,7 +57,6 @@
 #include <linux/trdevice.h>
 #include <linux/ibmtr.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -102,9 +101,8 @@
 
 typedef struct ibmtr_dev_t {
 	struct pcmcia_device	*p_dev;
-    struct net_device	*dev;
-    window_handle_t     sram_win_handle;
-    struct tok_info	*ti;
+	struct net_device	*dev;
+	struct tok_info		*ti;
 } ibmtr_dev_t;
 
 static void netdev_get_drvinfo(struct net_device *dev,
@@ -123,14 +121,6 @@
 	return tok_interrupt(irq, dev);
 };
 
-/*======================================================================
-
-    ibmtr_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-======================================================================*/
-
 static int __devinit ibmtr_attach(struct pcmcia_device *link)
 {
     ibmtr_dev_t *info;
@@ -153,9 +143,8 @@
 
     link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
     link->resource[0]->end = 4;
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-    link->conf.Present = PRESENT_OPTION;
+    link->config_flags |= CONF_ENABLE_IRQ;
+    link->config_regs = PRESENT_OPTION;
 
     info->dev = dev;
 
@@ -164,15 +153,6 @@
     return ibmtr_config(link);
 } /* ibmtr_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void ibmtr_detach(struct pcmcia_device *link)
 {
     struct ibmtr_dev_t *info = link->priv;
@@ -197,26 +177,17 @@
     kfree(info);
 } /* ibmtr_detach */
 
-/*======================================================================
-
-    ibmtr_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    token-ring device available to the system.
-
-======================================================================*/
-
 static int __devinit ibmtr_config(struct pcmcia_device *link)
 {
     ibmtr_dev_t *info = link->priv;
     struct net_device *dev = info->dev;
     struct tok_info *ti = netdev_priv(dev);
-    win_req_t req;
     int i, ret;
 
     dev_dbg(&link->dev, "ibmtr_config\n");
 
-    link->conf.ConfigIndex = 0x61;
     link->io_lines = 16;
+    link->config_index = 0x61;
 
     /* Determine if this is PRIMARY or ALTERNATE. */
 
@@ -240,39 +211,39 @@
     ti->global_int_enable=GLOBAL_INT_ENABLE+((dev->irq==9) ? 2 : dev->irq);
 
     /* Allocate the MMIO memory window */
-    req.Attributes = WIN_DATA_WIDTH_16|WIN_MEMORY_TYPE_CM|WIN_ENABLE;
-    req.Attributes |= WIN_USE_WAIT;
-    req.Base = 0; 
-    req.Size = 0x2000;
-    req.AccessSpeed = 250;
-    ret = pcmcia_request_window(link, &req, &link->win);
+    link->resource[2]->flags |= WIN_DATA_WIDTH_16|WIN_MEMORY_TYPE_CM|WIN_ENABLE;
+    link->resource[2]->flags |= WIN_USE_WAIT;
+    link->resource[2]->start = 0;
+    link->resource[2]->end = 0x2000;
+    ret = pcmcia_request_window(link, link->resource[2], 250);
     if (ret)
 	    goto failed;
 
-    ret = pcmcia_map_mem_page(link, link->win, mmiobase);
+    ret = pcmcia_map_mem_page(link, link->resource[2], mmiobase);
     if (ret)
 	    goto failed;
-    ti->mmio = ioremap(req.Base, req.Size);
+    ti->mmio = ioremap(link->resource[2]->start,
+		    resource_size(link->resource[2]));
 
     /* Allocate the SRAM memory window */
-    req.Attributes = WIN_DATA_WIDTH_16|WIN_MEMORY_TYPE_CM|WIN_ENABLE;
-    req.Attributes |= WIN_USE_WAIT;
-    req.Base = 0;
-    req.Size = sramsize * 1024;
-    req.AccessSpeed = 250;
-    ret = pcmcia_request_window(link, &req, &info->sram_win_handle);
+    link->resource[3]->flags = WIN_DATA_WIDTH_16|WIN_MEMORY_TYPE_CM|WIN_ENABLE;
+    link->resource[3]->flags |= WIN_USE_WAIT;
+    link->resource[3]->start = 0;
+    link->resource[3]->end = sramsize * 1024;
+    ret = pcmcia_request_window(link, link->resource[3], 250);
     if (ret)
 	    goto failed;
 
-    ret = pcmcia_map_mem_page(link, info->sram_win_handle, srambase);
+    ret = pcmcia_map_mem_page(link, link->resource[3], srambase);
     if (ret)
 	    goto failed;
 
     ti->sram_base = srambase >> 12;
-    ti->sram_virt = ioremap(req.Base, req.Size);
-    ti->sram_phys = req.Base;
+    ti->sram_virt = ioremap(link->resource[3]->start,
+		    resource_size(link->resource[3]));
+    ti->sram_phys = link->resource[3]->start;
 
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
@@ -301,14 +272,6 @@
     return -ENODEV;
 } /* ibmtr_config */
 
-/*======================================================================
-
-    After a card is removed, ibmtr_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void ibmtr_release(struct pcmcia_device *link)
 {
 	ibmtr_dev_t *info = link->priv;
@@ -316,7 +279,7 @@
 
 	dev_dbg(&link->dev, "ibmtr_release\n");
 
-	if (link->win) {
+	if (link->resource[2]->end) {
 		struct tok_info *ti = netdev_priv(dev);
 		iounmap(ti->mmio);
 	}
@@ -398,9 +361,7 @@
 
 static struct pcmcia_driver ibmtr_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "ibmtr_cs",
-	},
+	.name		= "ibmtr_cs",
 	.probe		= ibmtr_attach,
 	.remove		= ibmtr_detach,
 	.id_table       = ibmtr_ids,
diff --git a/drivers/net/pcmcia/nmclan_cs.c b/drivers/net/pcmcia/nmclan_cs.c
index 68f2dee..1eca4f5 100644
--- a/drivers/net/pcmcia/nmclan_cs.c
+++ b/drivers/net/pcmcia/nmclan_cs.c
@@ -146,7 +146,6 @@
 #include <linux/ioport.h>
 #include <linux/bitops.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
@@ -435,13 +434,6 @@
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-/* ----------------------------------------------------------------------------
-nmclan_attach
-	Creates an "instance" of the driver, allocating local data
-	structures for one device.  The device is registered with Card
-	Services.
----------------------------------------------------------------------------- */
-
 static int nmclan_probe(struct pcmcia_device *link)
 {
     mace_private *lp;
@@ -460,10 +452,9 @@
     spin_lock_init(&lp->bank_lock);
     link->resource[0]->end = 32;
     link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-    link->conf.ConfigIndex = 1;
-    link->conf.Present = PRESENT_OPTION;
+    link->config_flags |= CONF_ENABLE_IRQ;
+    link->config_index = 1;
+    link->config_regs = PRESENT_OPTION;
 
     lp->tx_free_frames=AM2150_MAX_TX_FRAMES;
 
@@ -474,14 +465,6 @@
     return nmclan_config(link);
 } /* nmclan_attach */
 
-/* ----------------------------------------------------------------------------
-nmclan_detach
-	This deletes a driver "instance".  The device is de-registered
-	with Card Services.  If it has been released, all local data
-	structures are freed.  Otherwise, the structures will be freed
-	when the device is released.
----------------------------------------------------------------------------- */
-
 static void nmclan_detach(struct pcmcia_device *link)
 {
     struct net_device *dev = link->priv;
@@ -625,13 +608,6 @@
   return 0;
 } /* mace_init */
 
-/* ----------------------------------------------------------------------------
-nmclan_config
-	This routine is scheduled to run after a CARD_INSERTION event
-	is received, to configure the PCMCIA socket, and to make the
-	ethernet device available to the system.
----------------------------------------------------------------------------- */
-
 static int nmclan_config(struct pcmcia_device *link)
 {
   struct net_device *dev = link->priv;
@@ -650,7 +626,7 @@
   ret = pcmcia_request_exclusive_irq(link, mace_interrupt);
   if (ret)
 	  goto failed;
-  ret = pcmcia_request_configuration(link, &link->conf);
+  ret = pcmcia_enable_device(link);
   if (ret)
 	  goto failed;
 
@@ -712,12 +688,6 @@
 	return -ENODEV;
 } /* nmclan_config */
 
-/* ----------------------------------------------------------------------------
-nmclan_release
-	After a card is removed, nmclan_release() will unregister the
-	net device, and release the PCMCIA configuration.  If the device
-	is still open, this will be postponed until it is closed.
----------------------------------------------------------------------------- */
 static void nmclan_release(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "nmclan_release\n");
@@ -1535,9 +1505,7 @@
 
 static struct pcmcia_driver nmclan_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "nmclan_cs",
-	},
+	.name		= "nmclan_cs",
 	.probe		= nmclan_probe,
 	.remove		= nmclan_detach,
 	.id_table       = nmclan_ids,
diff --git a/drivers/net/pcmcia/pcnet_cs.c b/drivers/net/pcmcia/pcnet_cs.c
index f9b509a..5d7d1d3 100644
--- a/drivers/net/pcmcia/pcnet_cs.c
+++ b/drivers/net/pcmcia/pcnet_cs.c
@@ -42,7 +42,6 @@
 #include <linux/mii.h>
 #include "../8390.h"
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -238,14 +237,6 @@
 #endif
 };
 
-/*======================================================================
-
-    pcnet_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-======================================================================*/
-
 static int pcnet_probe(struct pcmcia_device *link)
 {
     pcnet_dev_t *info;
@@ -260,23 +251,13 @@
     info->p_dev = link;
     link->priv = dev;
 
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
 
     dev->netdev_ops = &pcnet_netdev_ops;
 
     return pcnet_config(link);
 } /* pcnet_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void pcnet_detach(struct pcmcia_device *link)
 {
 	struct net_device *dev = link->priv;
@@ -300,22 +281,22 @@
 static hw_info_t *get_hwinfo(struct pcmcia_device *link)
 {
     struct net_device *dev = link->priv;
-    win_req_t req;
     u_char __iomem *base, *virt;
     int i, j;
 
     /* Allocate a small memory window */
-    req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
-    req.Base = 0; req.Size = 0;
-    req.AccessSpeed = 0;
-    i = pcmcia_request_window(link, &req, &link->win);
+    link->resource[2]->flags |= WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
+    link->resource[2]->start = 0; link->resource[2]->end = 0;
+    i = pcmcia_request_window(link, link->resource[2], 0);
     if (i != 0)
 	return NULL;
 
-    virt = ioremap(req.Base, req.Size);
+    virt = ioremap(link->resource[2]->start,
+	    resource_size(link->resource[2]));
     for (i = 0; i < NR_INFO; i++) {
-	pcmcia_map_mem_page(link, link->win, hw_info[i].offset & ~(req.Size-1));
-	base = &virt[hw_info[i].offset & (req.Size-1)];
+	pcmcia_map_mem_page(link, link->resource[2],
+		hw_info[i].offset & ~(resource_size(link->resource[2])-1));
+	base = &virt[hw_info[i].offset & (resource_size(link->resource[2])-1)];
 	if ((readb(base+0) == hw_info[i].a0) &&
 	    (readb(base+2) == hw_info[i].a1) &&
 	    (readb(base+4) == hw_info[i].a2)) {
@@ -326,7 +307,7 @@
     }
 
     iounmap(virt);
-    j = pcmcia_release_window(link, link->win);
+    j = pcmcia_release_window(link, link->resource[2]);
     return (i < NR_INFO) ? hw_info+i : NULL;
 } /* get_hwinfo */
 
@@ -421,7 +402,7 @@
     int i, j;
 
     /* Not much of a test, but the alternatives are messy */
-    if (link->conf.ConfigBase != 0x03c0)
+    if (link->config_base != 0x03c0)
 	return NULL;
 
     outb_p(0x01, ioaddr + EN0_DCFG);	/* Set word-wide access. */
@@ -463,14 +444,6 @@
     return &default_info;
 } /* get_hwired */
 
-/*======================================================================
-
-    pcnet_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ethernet device available to the system.
-
-======================================================================*/
-
 static int try_io_port(struct pcmcia_device *link)
 {
     int j, ret;
@@ -502,43 +475,22 @@
     }
 }
 
-static int pcnet_confcheck(struct pcmcia_device *p_dev,
-			   cistpl_cftable_entry_t *cfg,
-			   cistpl_cftable_entry_t *dflt,
-			   unsigned int vcc,
-			   void *priv_data)
+static int pcnet_confcheck(struct pcmcia_device *p_dev, void *priv_data)
 {
 	int *priv = priv_data;
 	int try = (*priv & 0x1);
-	int i;
-	cistpl_io_t *io = &cfg->io;
 
-	if (cfg->index == 0 || cfg->io.nwin == 0)
+	*priv &= (p_dev->resource[2]->end >= 0x4000) ? 0x10 : ~0x10;
+
+	if (p_dev->config_index == 0)
 		return -EINVAL;
 
-	/* For multifunction cards, by convention, we configure the
-	   network function with window 0, and serial with window 1 */
-	if (io->nwin > 1) {
-		i = (io->win[1].len > io->win[0].len);
-		p_dev->resource[1]->start = io->win[1-i].base;
-		p_dev->resource[1]->end = io->win[1-i].len;
-	} else {
-		i = p_dev->resource[1]->end = 0;
-	}
+	if (p_dev->resource[0]->end + p_dev->resource[1]->end < 32)
+		return -EINVAL;
 
-	*priv &= ((cfg->mem.nwin == 1) &&
-		  (cfg->mem.win[0].len >= 0x4000)) ? 0x10 : ~0x10;
-
-	p_dev->resource[0]->start = io->win[i].base;
-	p_dev->resource[0]->end = io->win[i].len;
-	if (!try)
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-	else
+	if (try)
 		p_dev->io_lines = 16;
-	if (p_dev->resource[0]->end + p_dev->resource[1]->end >= 32)
-		return try_io_port(p_dev);
-
-	return -EINVAL;
+	return try_io_port(p_dev);
 }
 
 static hw_info_t *pcnet_try_config(struct pcmcia_device *link,
@@ -560,15 +512,14 @@
 	if (!link->irq)
 		return NULL;
 
-	if (resource_size(link->resource[1]) == 8) {
-		link->conf.Attributes |= CONF_ENABLE_SPKR;
-		link->conf.Status = CCSR_AUDIO_ENA;
-	}
+	if (resource_size(link->resource[1]) == 8)
+		link->config_flags |= CONF_ENABLE_SPKR;
+
 	if ((link->manf_id == MANFID_IBM) &&
 	    (link->card_id == PRODID_IBM_HOME_AND_AWAY))
-		link->conf.ConfigIndex |= 0x10;
+		link->config_index |= 0x10;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		return NULL;
 
@@ -583,7 +534,7 @@
 	} else
 		dev->if_port = 0;
 
-	if ((link->conf.ConfigBase == 0x03c0) &&
+	if ((link->config_base == 0x03c0) &&
 	    (link->manf_id == 0x149) && (link->card_id == 0xc1ab)) {
 		dev_info(&link->dev,
 			"this is an AX88190 card - use axnet_cs instead.\n");
@@ -689,14 +640,6 @@
     return -ENODEV;
 } /* pcnet_config */
 
-/*======================================================================
-
-    After a card is removed, pcnet_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void pcnet_release(struct pcmcia_device *link)
 {
 	pcnet_dev_t *info = PRIV(link->priv);
@@ -709,15 +652,6 @@
 	pcmcia_disable_device(link);
 }
 
-/*======================================================================
-
-    The card status event handler.  Mostly, this schedules other
-    stuff to run after an event is received.  A CARD_REMOVAL event
-    also sets some flags to discourage the net drivers from trying
-    to talk to the card any more.
-
-======================================================================*/
-
 static int pcnet_suspend(struct pcmcia_device *link)
 {
 	struct net_device *dev = link->priv;
@@ -1486,7 +1420,6 @@
 {
     struct net_device *dev = link->priv;
     pcnet_dev_t *info = PRIV(dev);
-    win_req_t req;
     int i, window_size, offset, ret;
 
     window_size = (stop_pg - start_pg) << 8;
@@ -1497,22 +1430,22 @@
     window_size = roundup_pow_of_two(window_size);
 
     /* Allocate a memory window */
-    req.Attributes = WIN_DATA_WIDTH_16|WIN_MEMORY_TYPE_CM|WIN_ENABLE;
-    req.Attributes |= WIN_USE_WAIT;
-    req.Base = 0; req.Size = window_size;
-    req.AccessSpeed = mem_speed;
-    ret = pcmcia_request_window(link, &req, &link->win);
+    link->resource[3]->flags |= WIN_DATA_WIDTH_16|WIN_MEMORY_TYPE_CM|WIN_ENABLE;
+    link->resource[3]->flags |= WIN_USE_WAIT;
+    link->resource[3]->start = 0; link->resource[3]->end = window_size;
+    ret = pcmcia_request_window(link, link->resource[3], mem_speed);
     if (ret)
 	    goto failed;
 
     offset = (start_pg << 8) + cm_offset;
     offset -= offset % window_size;
-    ret = pcmcia_map_mem_page(link, link->win, offset);
+    ret = pcmcia_map_mem_page(link, link->resource[3], offset);
     if (ret)
 	    goto failed;
 
     /* Try scribbling on the buffer */
-    info->base = ioremap(req.Base, window_size);
+    info->base = ioremap(link->resource[3]->start,
+			resource_size(link->resource[3]));
     for (i = 0; i < (TX_PAGES<<8); i += 2)
 	__raw_writew((i>>1), info->base+offset+i);
     udelay(100);
@@ -1521,19 +1454,20 @@
     pcnet_reset_8390(dev);
     if (i != (TX_PAGES<<8)) {
 	iounmap(info->base);
-	pcmcia_release_window(link, link->win);
-	info->base = NULL; link->win = 0;
+	pcmcia_release_window(link, link->resource[3]);
+	info->base = NULL;
 	goto failed;
     }
 
     ei_status.mem = info->base + offset;
-    ei_status.priv = req.Size;
+    ei_status.priv = resource_size(link->resource[3]);
     dev->mem_start = (u_long)ei_status.mem;
-    dev->mem_end = dev->mem_start + req.Size;
+    dev->mem_end = dev->mem_start + resource_size(link->resource[3]);
 
     ei_status.tx_start_page = start_pg;
     ei_status.rx_start_page = start_pg + TX_PAGES;
-    ei_status.stop_page = start_pg + ((req.Size - offset) >> 8);
+    ei_status.stop_page = start_pg + (
+	    (resource_size(link->resource[3]) - offset) >> 8);
 
     /* set up block i/o functions */
     ei_status.get_8390_hdr = &shmem_get_8390_hdr;
@@ -1772,9 +1706,7 @@
 MODULE_FIRMWARE("cis/tamarack.cis");
 
 static struct pcmcia_driver pcnet_driver = {
-	.drv		= {
-		.name	= "pcnet_cs",
-	},
+	.name		= "pcnet_cs",
 	.probe		= pcnet_probe,
 	.remove		= pcnet_detach,
 	.owner		= THIS_MODULE,
diff --git a/drivers/net/pcmcia/smc91c92_cs.c b/drivers/net/pcmcia/smc91c92_cs.c
index 377367d..0af2fc8 100644
--- a/drivers/net/pcmcia/smc91c92_cs.c
+++ b/drivers/net/pcmcia/smc91c92_cs.c
@@ -44,7 +44,6 @@
 #include <linux/jiffies.h>
 #include <linux/firmware.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ciscode.h>
@@ -300,14 +299,6 @@
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-/*======================================================================
-
-  smc91c92_attach() creates an "instance" of the driver, allocating
-  local data structures for one device.  The device is registered
-  with Card Services.
-
-======================================================================*/
-
 static int smc91c92_probe(struct pcmcia_device *link)
 {
     struct smc_private *smc;
@@ -324,10 +315,6 @@
     link->priv = dev;
 
     spin_lock_init(&smc->lock);
-    link->resource[0]->end = 16;
-    link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
 
     /* The SMC91c92-specific entries in the device structure. */
     dev->netdev_ops = &smc_netdev_ops;
@@ -343,15 +330,6 @@
     return smc91c92_config(link);
 } /* smc91c92_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void smc91c92_detach(struct pcmcia_device *link)
 {
     struct net_device *dev = link->priv;
@@ -412,26 +390,28 @@
     mdelay(200);
 
     /* Now read and write the COR... */
-    tmp = readb(smc->base + link->conf.ConfigBase + CISREG_COR);
+    tmp = readb(smc->base + link->config_base + CISREG_COR);
     udelay(5);
-    writeb(tmp, smc->base + link->conf.ConfigBase + CISREG_COR);
+    writeb(tmp, smc->base + link->config_base + CISREG_COR);
 
     return 0;
 }
 
-static int mhz_mfc_config_check(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cf,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
-				void *priv_data)
+static int mhz_mfc_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
 	int k;
-	p_dev->resource[1]->start = cf->io.win[0].base;
+	p_dev->io_lines = 16;
+	p_dev->resource[1]->start = p_dev->resource[0]->start;
+	p_dev->resource[1]->end = 8;
+	p_dev->resource[1]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->resource[0]->end = 16;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 	for (k = 0; k < 0x400; k += 0x10) {
 		if (k & 0x80)
 			continue;
 		p_dev->resource[0]->start = k ^ 0x300;
-		p_dev->io_lines = 16;
 		if (!pcmcia_request_io(p_dev))
 			return 0;
 	}
@@ -442,14 +422,11 @@
 {
     struct net_device *dev = link->priv;
     struct smc_private *smc = netdev_priv(dev);
-    win_req_t req;
     unsigned int offset;
     int i;
 
-    link->conf.Attributes |= CONF_ENABLE_SPKR;
-    link->conf.Status = CCSR_AUDIO_ENA;
-    link->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
-    link->resource[1]->end = 8;
+    link->config_flags |= CONF_ENABLE_SPKR | CONF_ENABLE_IRQ |
+	    CONF_AUTO_SET_IO;
 
     /* The Megahertz combo cards have modem-like CIS entries, so
        we have to explicitly try a bunch of port combinations. */
@@ -459,16 +436,16 @@
     dev->base_addr = link->resource[0]->start;
 
     /* Allocate a memory window, for accessing the ISR */
-    req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
-    req.Base = req.Size = 0;
-    req.AccessSpeed = 0;
-    i = pcmcia_request_window(link, &req, &link->win);
+    link->resource[2]->flags = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
+    link->resource[2]->start = link->resource[2]->end = 0;
+    i = pcmcia_request_window(link, link->resource[2], 0);
     if (i != 0)
 	    return -ENODEV;
 
-    smc->base = ioremap(req.Base, req.Size);
-    offset = (smc->manfid == MANFID_MOTOROLA) ? link->conf.ConfigBase : 0;
-    i = pcmcia_map_mem_page(link, link->win, offset);
+    smc->base = ioremap(link->resource[2]->start,
+		    resource_size(link->resource[2]));
+    offset = (smc->manfid == MANFID_MOTOROLA) ? link->config_base : 0;
+    i = pcmcia_map_mem_page(link, link->resource[2], offset);
     if ((i == 0) &&
 	(smc->manfid == MANFID_MEGAHERTZ) &&
 	(smc->cardid == PRODID_MEGAHERTZ_EM3288))
@@ -591,14 +568,12 @@
 
 /*====================================================================*/
 
-static int smc_configcheck(struct pcmcia_device *p_dev,
-			   cistpl_cftable_entry_t *cf,
-			   cistpl_cftable_entry_t *dflt,
-			   unsigned int vcc,
-			   void *priv_data)
+static int smc_configcheck(struct pcmcia_device *p_dev, void *priv_data)
 {
-	p_dev->resource[0]->start = cf->io.win[0].base;
-	p_dev->io_lines = cf->io.flags & CISTPL_IO_LINES_MASK;
+	p_dev->resource[0]->end = 16;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
+
 	return pcmcia_request_io(p_dev);
 }
 
@@ -607,7 +582,8 @@
     struct net_device *dev = link->priv;
     int i;
 
-    link->resource[0]->end = 16;
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+
     i = pcmcia_loop_config(link, smc_configcheck, NULL);
     if (!i)
 	    dev->base_addr = link->resource[0]->start;
@@ -640,15 +616,14 @@
     static const unsigned int com[4] = { 0x3f8, 0x2f8, 0x3e8, 0x2e8 };
     int i, j;
 
-    link->conf.Attributes |= CONF_ENABLE_SPKR;
-    link->conf.Status = CCSR_AUDIO_ENA;
+    link->config_flags |= CONF_ENABLE_SPKR | CONF_ENABLE_IRQ;
     link->resource[0]->end = 64;
     link->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
     link->resource[1]->end = 8;
 
     /* Enable Hard Decode, LAN, Modem */
-    link->conf.ConfigIndex = 0x23;
     link->io_lines = 16;
+    link->config_index = 0x23;
 
     for (i = j = 0; j < 4; j++) {
 	link->resource[1]->start = com[j];
@@ -658,7 +633,7 @@
     }
     if (i != 0) {
 	/* Fallback: turn off hard decode */
-	link->conf.ConfigIndex = 0x03;
+	link->config_index = 0x03;
 	link->resource[1]->end = 0;
 	i = pcmcia_request_io(link);
     }
@@ -817,27 +792,16 @@
     }
 
     if (width) {
-	    modconf_t mod = {
-		    .Attributes = CONF_IO_CHANGE_WIDTH,
-	    };
 	    printk(KERN_INFO "smc91c92_cs: using 8-bit IO window.\n");
 
 	    smc91c92_suspend(link);
-	    pcmcia_modify_configuration(link, &mod);
+	    pcmcia_fixup_iowidth(link);
 	    smc91c92_resume(link);
 	    return check_sig(link);
     }
     return -ENODEV;
 }
 
-/*======================================================================
-
-    smc91c92_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ethernet device available to the system.
-
-======================================================================*/
-
 static int smc91c92_config(struct pcmcia_device *link)
 {
     struct net_device *dev = link->priv;
@@ -869,7 +833,7 @@
     i = pcmcia_request_irq(link, smc_interrupt);
     if (i)
 	    goto config_failed;
-    i = pcmcia_request_configuration(link, &link->conf);
+    i = pcmcia_enable_device(link);
     if (i)
 	    goto config_failed;
 
@@ -988,18 +952,10 @@
     return -ENODEV;
 } /* smc91c92_config */
 
-/*======================================================================
-
-    After a card is removed, smc91c92_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void smc91c92_release(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "smc91c92_release\n");
-	if (link->win) {
+	if (link->resource[2]->end) {
 		struct net_device *dev = link->priv;
 		struct smc_private *smc = netdev_priv(dev);
 		iounmap(smc->base);
@@ -2101,9 +2057,7 @@
 
 static struct pcmcia_driver smc91c92_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "smc91c92_cs",
-	},
+	.name		= "smc91c92_cs",
 	.probe		= smc91c92_probe,
 	.remove		= smc91c92_detach,
 	.id_table       = smc91c92_ids,
diff --git a/drivers/net/pcmcia/xirc2ps_cs.c b/drivers/net/pcmcia/xirc2ps_cs.c
index f5819526..1fece61 100644
--- a/drivers/net/pcmcia/xirc2ps_cs.c
+++ b/drivers/net/pcmcia/xirc2ps_cs.c
@@ -82,7 +82,6 @@
 #include <linux/bitops.h>
 #include <linux/mii.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ciscode.h>
@@ -267,33 +266,11 @@
 static void mii_wr(unsigned int ioaddr, u_char phyaddr, u_char phyreg,
 		   unsigned data, int len);
 
-/*
- * The event() function is this driver's Card Services event handler.
- * It will be called by Card Services when an appropriate card status
- * event is received.  The config() and release() entry points are
- * used to configure or release a socket, in response to card insertion
- * and ejection events.  They are invoked from the event handler.
- */
-
 static int has_ce2_string(struct pcmcia_device * link);
 static int xirc2ps_config(struct pcmcia_device * link);
 static void xirc2ps_release(struct pcmcia_device * link);
-
-/****************
- * The attach() and detach() entry points are used to create and destroy
- * "instances" of the driver, where each instance represents everything
- * needed to manage one actual PCMCIA card.
- */
-
 static void xirc2ps_detach(struct pcmcia_device *p_dev);
 
-/****************
- * You'll also need to prototype all the functions that will actually
- * be used to talk to your device.  See 'pcmem_cs' for a good example
- * of a fully self-sufficient driver; the other drivers rely more or
- * less on other parts of the kernel.
- */
-
 static irqreturn_t xirc2ps_interrupt(int irq, void *dev_id);
 
 typedef struct local_info_t {
@@ -501,16 +478,6 @@
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-/****************
- * xirc2ps_attach() creates an "instance" of the driver, allocating
- * local data structures for one device.  The device is registered
- * with Card Services.
- *
- * The dev_link structure is initialized, but we don't actually
- * configure the card at this point -- we wait until we receive a
- * card insertion event.
- */
-
 static int
 xirc2ps_probe(struct pcmcia_device *link)
 {
@@ -529,9 +496,7 @@
     link->priv = dev;
 
     /* General socket configuration */
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-    link->conf.ConfigIndex = 1;
+    link->config_index = 1;
 
     /* Fill in card specific entries */
     dev->netdev_ops = &netdev_ops;
@@ -542,13 +507,6 @@
     return xirc2ps_config(link);
 } /* xirc2ps_attach */
 
-/****************
- *  This deletes a driver "instance".  The device is de-registered
- *  with Card Services.  If it has been released, all local data
- *  structures are freed.  Otherwise, the structures will be freed
- *  when the device is released.
- */
-
 static void
 xirc2ps_detach(struct pcmcia_device *link)
 {
@@ -667,44 +625,53 @@
 }
 
 static int
-xirc2ps_config_modem(struct pcmcia_device *p_dev,
-		     cistpl_cftable_entry_t *cf,
-		     cistpl_cftable_entry_t *dflt,
-		     unsigned int vcc,
-		     void *priv_data)
+xirc2ps_config_modem(struct pcmcia_device *p_dev, void *priv_data)
 {
 	unsigned int ioaddr;
 
-	if (cf->io.nwin > 0  &&  (cf->io.win[0].base & 0xf) == 8) {
-		for (ioaddr = 0x300; ioaddr < 0x400; ioaddr += 0x10) {
-			p_dev->resource[1]->start = cf->io.win[0].base;
-			p_dev->resource[0]->start = ioaddr;
-			if (!pcmcia_request_io(p_dev))
-				return 0;
-		}
+	if ((p_dev->resource[0]->start & 0xf) == 8)
+		return -ENODEV;
+
+	p_dev->resource[0]->end = 16;
+	p_dev->resource[1]->end = 8;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
+	p_dev->resource[1]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->io_lines = 10;
+
+	p_dev->resource[1]->start = p_dev->resource[0]->start;
+	for (ioaddr = 0x300; ioaddr < 0x400; ioaddr += 0x10) {
+		p_dev->resource[0]->start = ioaddr;
+		if (!pcmcia_request_io(p_dev))
+			return 0;
 	}
 	return -ENODEV;
 }
 
 static int
-xirc2ps_config_check(struct pcmcia_device *p_dev,
-		     cistpl_cftable_entry_t *cf,
-		     cistpl_cftable_entry_t *dflt,
-		     unsigned int vcc,
-		     void *priv_data)
+xirc2ps_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
 	int *pass = priv_data;
+	resource_size_t tmp = p_dev->resource[1]->start;
 
-	if (cf->io.nwin > 0 && (cf->io.win[0].base & 0xf) == 8) {
-		p_dev->resource[1]->start = cf->io.win[0].base;
-		p_dev->resource[0]->start = p_dev->resource[1]->start
-			+ (*pass ? (cf->index & 0x20 ? -24:8)
-			   : (cf->index & 0x20 ?   8:-24));
-		if (!pcmcia_request_io(p_dev))
-			return 0;
-	}
-	return -ENODEV;
+	tmp += (*pass ? (p_dev->config_index & 0x20 ? -24 : 8)
+		: (p_dev->config_index & 0x20 ?   8 : -24));
 
+	if ((p_dev->resource[0]->start & 0xf) == 8)
+		return -ENODEV;
+
+	p_dev->resource[0]->end = 18;
+	p_dev->resource[1]->end = 8;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
+	p_dev->resource[1]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->io_lines = 10;
+
+	p_dev->resource[1]->start = p_dev->resource[0]->start;
+	p_dev->resource[0]->start = tmp;
+	return pcmcia_request_io(p_dev);
 }
 
 
@@ -727,11 +694,6 @@
 };
 
 
-/****************
- * xirc2ps_config() is scheduled to run after a CARD_INSERTION event
- * is received, to configure the PCMCIA socket, and to make the
- * ethernet device available to the system.
- */
 static int
 xirc2ps_config(struct pcmcia_device * link)
 {
@@ -807,32 +769,24 @@
 	goto failure;
     }
 
-    link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
-    link->io_lines = 10;
     if (local->modem) {
 	int pass;
+	link->config_flags |= CONF_AUTO_SET_IO;
 
-	if (do_sound) {
-	    link->conf.Attributes |= CONF_ENABLE_SPKR;
-	    link->conf.Status |= CCSR_AUDIO_ENA;
-	}
-	link->resource[1]->end = 8;
-	link->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
 	if (local->dingo) {
 	    /* Take the Modem IO port from the CIS and scan for a free
 	     * Ethernet port */
-	    link->resource[0]->end = 16; /* no Mako stuff anymore */
 	    if (!pcmcia_loop_config(link, xirc2ps_config_modem, NULL))
 		    goto port_found;
 	} else {
-	    link->resource[0]->end = 18;
 	    /* We do 2 passes here: The first one uses the regular mapping and
 	     * the second tries again, thereby considering that the 32 ports are
 	     * mirrored every 32 bytes. Actually we use a mirrored port for
 	     * the Mako if (on the first pass) the COR bit 5 is set.
 	     */
 	    for (pass=0; pass < 2; pass++)
-		    if (!pcmcia_loop_config(link, xirc2ps_config_check, &pass))
+		    if (!pcmcia_loop_config(link, xirc2ps_config_check,
+						    &pass))
 			    goto port_found;
 	    /* if special option:
 	     * try to configure as Ethernet only.
@@ -840,7 +794,9 @@
 	}
 	printk(KNOT_XIRC "no ports available\n");
     } else {
+	link->io_lines = 10;
 	link->resource[0]->end = 16;
+	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
 	for (ioaddr = 0x300; ioaddr < 0x400; ioaddr += 0x10) {
 	    link->resource[0]->start = ioaddr;
 	    if (!(err = pcmcia_request_io(link)))
@@ -861,16 +817,14 @@
     if ((err=pcmcia_request_irq(link, xirc2ps_interrupt)))
 	goto config_error;
 
-    /****************
-     * This actually configures the PCMCIA socket -- setting up
-     * the I/O windows and the interrupt mapping.
-     */
-    if ((err=pcmcia_request_configuration(link, &link->conf)))
+    link->config_flags |= CONF_ENABLE_IRQ;
+    if (do_sound)
+	    link->config_flags |= CONF_ENABLE_SPKR;
+
+    if ((err = pcmcia_enable_device(link)))
 	goto config_error;
 
     if (local->dingo) {
-	win_req_t req;
-
 	/* Reset the modem's BAR to the correct value
 	 * This is necessary because in the RequestConfiguration call,
 	 * the base address of the ethernet port (BasePort1) is written
@@ -890,14 +844,14 @@
 	 * is at 0x0800. So we allocate a window into the attribute
 	 * memory and write direct to the CIS registers
 	 */
-	req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE;
-	req.Base = req.Size = 0;
-	req.AccessSpeed = 0;
-	if ((err = pcmcia_request_window(link, &req, &link->win)))
+	link->resource[2]->flags = WIN_DATA_WIDTH_8 | WIN_MEMORY_TYPE_AM |
+					WIN_ENABLE;
+	link->resource[2]->start = link->resource[2]->end = 0;
+	if ((err = pcmcia_request_window(link, link->resource[2], 0)))
 	    goto config_error;
 
-	local->dingo_ccr = ioremap(req.Base,0x1000) + 0x0800;
-	if ((err = pcmcia_map_mem_page(link, link->win, 0)))
+	local->dingo_ccr = ioremap(link->resource[2]->start, 0x1000) + 0x0800;
+	if ((err = pcmcia_map_mem_page(link, link->resource[2], 0)))
 	    goto config_error;
 
 	/* Setup the CCRs; there are no infos in the CIS about the Ethernet
@@ -978,17 +932,12 @@
     return -ENODEV;
 } /* xirc2ps_config */
 
-/****************
- * After a card is removed, xirc2ps_release() will unregister the net
- * device, and release the PCMCIA configuration.  If the device is
- * still open, this will be postponed until it is closed.
- */
 static void
 xirc2ps_release(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "release\n");
 
-	if (link->win) {
+	if (link->resource[2]->end) {
 		struct net_device *dev = link->priv;
 		local_info_t *local = netdev_priv(dev);
 		if (local->dingo)
@@ -1830,9 +1779,7 @@
 
 static struct pcmcia_driver xirc2ps_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "xirc2ps_cs",
-	},
+	.name		= "xirc2ps_cs",
 	.probe		= xirc2ps_probe,
 	.remove		= xirc2ps_detach,
 	.id_table       = xirc2ps_ids,
diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c
index af50a53..78d70a6 100644
--- a/drivers/net/ppp_async.c
+++ b/drivers/net/ppp_async.c
@@ -184,7 +184,7 @@
 	tasklet_init(&ap->tsk, ppp_async_process, (unsigned long) ap);
 
 	atomic_set(&ap->refcnt, 1);
-	init_MUTEX_LOCKED(&ap->dead_sem);
+	sema_init(&ap->dead_sem, 0);
 
 	ap->chan.private = ap;
 	ap->chan.ops = &async_ops;
diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c
index 736b917..4bddb2a 100644
--- a/drivers/net/ppp_generic.c
+++ b/drivers/net/ppp_generic.c
@@ -856,7 +856,8 @@
 	.poll		= ppp_poll,
 	.unlocked_ioctl	= ppp_ioctl,
 	.open		= ppp_open,
-	.release	= ppp_release
+	.release	= ppp_release,
+	.llseek		= noop_llseek,
 };
 
 static __net_init int ppp_init_net(struct net *net)
diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c
index 10cf0cb..726df61 100644
--- a/drivers/net/smc91x.c
+++ b/drivers/net/smc91x.c
@@ -72,6 +72,7 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
 #include <linux/crc32.h>
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index 04c6cd4..10bafd5 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -575,7 +575,7 @@
 
 		/* Initialize the chardev data structures */
 		mutex_init(&chan->rlock);
-		init_MUTEX(&chan->wsem);
+		sema_init(&chan->wsem, 1);
 
 		/* Register the network interface */
 		if (!(chan->netdev = alloc_hdlcdev(chan))) {
diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/net/wimax/i2400m/debugfs.c
index b1aec3e..9c70b5f 100644
--- a/drivers/net/wimax/i2400m/debugfs.c
+++ b/drivers/net/wimax/i2400m/debugfs.c
@@ -119,6 +119,7 @@
 	.open =		i2400m_stats_open,
 	.read =		i2400m_rx_stats_read,
 	.write =	i2400m_rx_stats_write,
+	.llseek =	default_llseek,
 };
 
 
@@ -171,6 +172,7 @@
 	.open =		i2400m_stats_open,
 	.read =		i2400m_tx_stats_read,
 	.write =	i2400m_tx_stats_write,
+	.llseek =	default_llseek,
 };
 
 
diff --git a/drivers/net/wireless/airo.c b/drivers/net/wireless/airo.c
index 1d05445..ce77575 100644
--- a/drivers/net/wireless/airo.c
+++ b/drivers/net/wireless/airo.c
@@ -4430,21 +4430,24 @@
 	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.open		= proc_statsdelta_open,
-	.release	= proc_close
+	.release	= proc_close,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations proc_stats_ops = {
 	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.open		= proc_stats_open,
-	.release	= proc_close
+	.release	= proc_close,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations proc_status_ops = {
 	.owner		= THIS_MODULE,
 	.read		= proc_read,
 	.open		= proc_status_open,
-	.release	= proc_close
+	.release	= proc_close,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations proc_SSID_ops = {
@@ -4452,7 +4455,8 @@
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_SSID_open,
-	.release	= proc_close
+	.release	= proc_close,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations proc_BSSList_ops = {
@@ -4460,7 +4464,8 @@
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_BSSList_open,
-	.release	= proc_close
+	.release	= proc_close,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations proc_APList_ops = {
@@ -4468,7 +4473,8 @@
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_APList_open,
-	.release	= proc_close
+	.release	= proc_close,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations proc_config_ops = {
@@ -4476,7 +4482,8 @@
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_config_open,
-	.release	= proc_close
+	.release	= proc_close,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations proc_wepkey_ops = {
@@ -4484,7 +4491,8 @@
 	.read		= proc_read,
 	.write		= proc_write,
 	.open		= proc_wepkey_open,
-	.release	= proc_close
+	.release	= proc_close,
+	.llseek		= default_llseek,
 };
 
 static struct proc_dir_entry *airo_entry;
diff --git a/drivers/net/wireless/airo_cs.c b/drivers/net/wireless/airo_cs.c
index 9a121a5..df2484d 100644
--- a/drivers/net/wireless/airo_cs.c
+++ b/drivers/net/wireless/airo_cs.c
@@ -32,7 +32,6 @@
 #include <linux/timer.h>
 #include <linux/netdevice.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -54,58 +53,21 @@
 
 /*====================================================================*/
 
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card
-   insertion and ejection events.  They are invoked from the airo_cs
-   event handler.
-*/
-
 static int airo_config(struct pcmcia_device *link);
 static void airo_release(struct pcmcia_device *link);
 
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static void airo_detach(struct pcmcia_device *p_dev);
 
 typedef struct local_info_t {
 	struct net_device *eth_dev;
 } local_info_t;
 
-/*======================================================================
-
-  airo_attach() creates an "instance" of the driver, allocating
-  local data structures for one device.  The device is registered
-  with Card Services.
-
-  The dev_link structure is initialized, but we don't actually
-  configure the card at this point -- we wait until we receive a
-  card insertion event.
-
-  ======================================================================*/
-
 static int airo_probe(struct pcmcia_device *p_dev)
 {
 	local_info_t *local;
 
 	dev_dbg(&p_dev->dev, "airo_attach()\n");
 
-	/*
-	  General socket configuration defaults can go here.  In this
-	  client, we assume very little, and rely on the CIS for almost
-	  everything.  In most clients, many details (i.e., number, sizes,
-	  and attributes of IO windows) are fixed by the nature of the
-	  device, and can be hard-wired here.
-	*/
-	p_dev->conf.Attributes = 0;
-	p_dev->conf.IntType = INT_MEMORY_AND_IO;
-
 	/* Allocate space for private device-specific data */
 	local = kzalloc(sizeof(local_info_t), GFP_KERNEL);
 	if (!local) {
@@ -117,15 +79,6 @@
 	return airo_config(p_dev);
 } /* airo_attach */
 
-/*======================================================================
-
-  This deletes a driver "instance".  The device is de-registered
-  with Card Services.  If it has been released, all local data
-  structures are freed.  Otherwise, the structures will be freed
-  when the device is released.
-
-  ======================================================================*/
-
 static void airo_detach(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "airo_detach\n");
@@ -140,60 +93,12 @@
 	kfree(link->priv);
 } /* airo_detach */
 
-/*======================================================================
-
-  airo_config() is scheduled to run after a CARD_INSERTION event
-  is received, to configure the PCMCIA socket, and to make the
-  device available to the system.
-
-  ======================================================================*/
-
-static int airo_cs_config_check(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
-				void *priv_data)
+static int airo_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Does this card need audio output? */
-	if (cfg->flags & CISTPL_CFTABLE_AUDIO) {
-		p_dev->conf.Attributes |= CONF_ENABLE_SPKR;
-		p_dev->conf.Status = CCSR_AUDIO_ENA;
-	}
-
-	/* Use power settings for Vcc and Vpp if present */
-	/*  Note that the CIS values need to be rescaled */
-	if (cfg->vpp1.present & (1<<CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = cfg->vpp1.param[CISTPL_POWER_VNOM]/10000;
-	else if (dflt->vpp1.present & (1<<CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = dflt->vpp1.param[CISTPL_POWER_VNOM]/10000;
-
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-					pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-	}
-
-	/* This reserves IO space but doesn't actually enable it */
-	if (pcmcia_request_io(p_dev) != 0)
-		return -ENODEV;
-
-	/* If we got this far, we're cool! */
-	return 0;
+	return pcmcia_request_io(p_dev);
 }
 
 
@@ -206,20 +111,9 @@
 
 	dev_dbg(&link->dev, "airo_config\n");
 
-	/*
-	 * In this loop, we scan the CIS for configuration table
-	 * entries, each of which describes a valid card
-	 * configuration, including voltage, IO window, memory window,
-	 * and interrupt settings.
-	 *
-	 * We make no assumptions about the card to be configured: we
-	 * use just the information available in the CIS.  In an ideal
-	 * world, this would work for any PCMCIA card, but it requires
-	 * a complete and accurate CIS.  In practice, a driver usually
-	 * "knows" most of these things without consulting the CIS,
-	 * and most client drivers will only use the CIS to fill in
-	 * implementation-defined details.
-	 */
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_VPP |
+		CONF_AUTO_AUDIO | CONF_AUTO_SET_IO;
+
 	ret = pcmcia_loop_config(link, airo_cs_config_check, NULL);
 	if (ret)
 		goto failed;
@@ -227,12 +121,7 @@
 	if (!link->irq)
 		goto failed;
 
-	/*
-	  This actually configures the PCMCIA socket -- setting up
-	  the I/O windows and the interrupt mapping, and putting the
-	  card and host interface into "Memory and IO" mode.
-	*/
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 	((local_info_t *)link->priv)->eth_dev =
@@ -241,17 +130,6 @@
 	if (!((local_info_t *)link->priv)->eth_dev)
 		goto failed;
 
-	/* Finally, report what we've done */
-	dev_info(&link->dev, "index 0x%02x: ",
-	       link->conf.ConfigIndex);
-	if (link->conf.Vpp)
-		printk(", Vpp %d.%d", link->conf.Vpp/10, link->conf.Vpp%10);
-	printk(", irq %d", link->irq);
-	if (link->resource[0])
-		printk(" & %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(" & %pR", link->resource[1]);
-	printk("\n");
 	return 0;
 
  failed:
@@ -259,14 +137,6 @@
 	return -ENODEV;
 } /* airo_config */
 
-/*======================================================================
-
-  After a card is removed, airo_release() will unregister the
-  device, and release the PCMCIA configuration.  If the device is
-  still open, this will be postponed until it is closed.
-
-  ======================================================================*/
-
 static void airo_release(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "airo_release\n");
@@ -305,9 +175,7 @@
 
 static struct pcmcia_driver airo_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "airo_cs",
-	},
+	.name		= "airo_cs",
 	.probe		= airo_probe,
 	.remove		= airo_detach,
 	.id_table       = airo_ids,
@@ -315,12 +183,12 @@
 	.resume		= airo_resume,
 };
 
-static int airo_cs_init(void)
+static int __init airo_cs_init(void)
 {
 	return pcmcia_register_driver(&airo_driver);
 }
 
-static void airo_cs_cleanup(void)
+static void __exit airo_cs_cleanup(void)
 {
 	pcmcia_unregister_driver(&airo_driver);
 }
diff --git a/drivers/net/wireless/ath/ath5k/debug.c b/drivers/net/wireless/ath/ath5k/debug.c
index 4cccc29..fb339c3 100644
--- a/drivers/net/wireless/ath/ath5k/debug.c
+++ b/drivers/net/wireless/ath/ath5k/debug.c
@@ -271,6 +271,7 @@
 	.write = write_file_beacon,
 	.open = ath5k_debugfs_open,
 	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
@@ -290,6 +291,7 @@
 	.write = write_file_reset,
 	.open = ath5k_debugfs_open,
 	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 
@@ -369,6 +371,7 @@
 	.write = write_file_debug,
 	.open = ath5k_debugfs_open,
 	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
@@ -480,6 +483,7 @@
 	.write = write_file_antenna,
 	.open = ath5k_debugfs_open,
 	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
@@ -591,6 +595,7 @@
 	.write = write_file_frameerrors,
 	.open = ath5k_debugfs_open,
 	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
@@ -748,6 +753,7 @@
 	.write = write_file_ani,
 	.open = ath5k_debugfs_open,
 	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
@@ -811,6 +817,7 @@
 	.write = write_file_queue,
 	.open = ath5k_debugfs_open,
 	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index 54aae93..cf500bf 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -71,7 +71,8 @@
 	.read = read_file_debug,
 	.write = write_file_debug,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 #endif
@@ -116,7 +117,8 @@
 	.read = read_file_tx_chainmask,
 	.write = write_file_tx_chainmask,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
@@ -158,7 +160,8 @@
 	.read = read_file_rx_chainmask,
 	.write = write_file_rx_chainmask,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
@@ -259,7 +262,8 @@
 static const struct file_operations fops_dma = {
 	.read = read_file_dma,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 
@@ -375,7 +379,8 @@
 static const struct file_operations fops_interrupt = {
 	.read = read_file_interrupt,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 void ath_debug_stat_rc(struct ath_softc *sc, int final_rate)
@@ -464,7 +469,8 @@
 static const struct file_operations fops_rcstat = {
 	.read = read_file_rcstat,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 static const char * ath_wiphy_state_str(enum ath_wiphy_state state)
@@ -623,7 +629,8 @@
 	.read = read_file_wiphy,
 	.write = write_file_wiphy,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 #define PR(str, elem)							\
@@ -702,7 +709,8 @@
 static const struct file_operations fops_xmit = {
 	.read = read_file_xmit,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 static ssize_t read_file_recv(struct file *file, char __user *user_buf,
@@ -814,7 +822,8 @@
 static const struct file_operations fops_recv = {
 	.read = read_file_recv,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 static ssize_t read_file_regidx(struct file *file, char __user *user_buf,
@@ -852,7 +861,8 @@
 	.read = read_file_regidx,
 	.write = write_file_regidx,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 static ssize_t read_file_regval(struct file *file, char __user *user_buf,
@@ -894,7 +904,8 @@
 	.read = read_file_regval,
 	.write = write_file_regval,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 int ath9k_init_debug(struct ath_hw *ah)
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 7d09b4b..bc2ca7d 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -536,7 +536,8 @@
 static const struct file_operations fops_tgt_stats = {
 	.read = read_file_tgt_stats,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 static ssize_t read_file_xmit(struct file *file, char __user *user_buf,
@@ -584,7 +585,8 @@
 static const struct file_operations fops_xmit = {
 	.read = read_file_xmit,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 static ssize_t read_file_recv(struct file *file, char __user *user_buf,
@@ -613,7 +615,8 @@
 static const struct file_operations fops_recv = {
 	.read = read_file_recv,
 	.open = ath9k_debugfs_open,
-	.owner = THIS_MODULE
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 int ath9k_htc_init_debug(struct ath_hw *ah)
diff --git a/drivers/net/wireless/atmel_cs.c b/drivers/net/wireless/atmel_cs.c
index 3b63216..c96e19d 100644
--- a/drivers/net/wireless/atmel_cs.c
+++ b/drivers/net/wireless/atmel_cs.c
@@ -42,7 +42,6 @@
 #include <linux/moduleparam.h>
 #include <linux/device.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -64,58 +63,21 @@
 
 /*====================================================================*/
 
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card
-   insertion and ejection events.  They are invoked from the atmel_cs
-   event handler.
-*/
-
 static int atmel_config(struct pcmcia_device *link);
 static void atmel_release(struct pcmcia_device *link);
 
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static void atmel_detach(struct pcmcia_device *p_dev);
 
 typedef struct local_info_t {
 	struct net_device *eth_dev;
 } local_info_t;
 
-/*======================================================================
-
-  atmel_attach() creates an "instance" of the driver, allocating
-  local data structures for one device.  The device is registered
-  with Card Services.
-
-  The dev_link structure is initialized, but we don't actually
-  configure the card at this point -- we wait until we receive a
-  card insertion event.
-
-  ======================================================================*/
-
 static int atmel_probe(struct pcmcia_device *p_dev)
 {
 	local_info_t *local;
 
 	dev_dbg(&p_dev->dev, "atmel_attach()\n");
 
-	/*
-	  General socket configuration defaults can go here.  In this
-	  client, we assume very little, and rely on the CIS for almost
-	  everything.  In most clients, many details (i.e., number, sizes,
-	  and attributes of IO windows) are fixed by the nature of the
-	  device, and can be hard-wired here.
-	*/
-	p_dev->conf.Attributes = 0;
-	p_dev->conf.IntType = INT_MEMORY_AND_IO;
-
 	/* Allocate space for private device-specific data */
 	local = kzalloc(sizeof(local_info_t), GFP_KERNEL);
 	if (!local) {
@@ -127,15 +89,6 @@
 	return atmel_config(p_dev);
 } /* atmel_attach */
 
-/*======================================================================
-
-  This deletes a driver "instance".  The device is de-registered
-  with Card Services.  If it has been released, all local data
-  structures are freed.  Otherwise, the structures will be freed
-  when the device is released.
-
-  ======================================================================*/
-
 static void atmel_detach(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "atmel_detach\n");
@@ -145,14 +98,6 @@
 	kfree(link->priv);
 }
 
-/*======================================================================
-
-  atmel_config() is scheduled to run after a CARD_INSERTION event
-  is received, to configure the PCMCIA socket, and to make the
-  device available to the system.
-
-  ======================================================================*/
-
 /* Call-back function to interrogate PCMCIA-specific information
    about the current existance of the card */
 static int card_present(void *arg)
@@ -165,47 +110,11 @@
 	return 0;
 }
 
-static int atmel_config_check(struct pcmcia_device *p_dev,
-			      cistpl_cftable_entry_t *cfg,
-			      cistpl_cftable_entry_t *dflt,
-			      unsigned int vcc,
-			      void *priv_data)
+static int atmel_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Does this card need audio output? */
-	if (cfg->flags & CISTPL_CFTABLE_AUDIO) {
-		p_dev->conf.Attributes |= CONF_ENABLE_SPKR;
-		p_dev->conf.Status = CCSR_AUDIO_ENA;
-	}
-
-	/* Use power settings for Vcc and Vpp if present */
-	/*  Note that the CIS values need to be rescaled */
-	if (cfg->vpp1.present & (1<<CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = cfg->vpp1.param[CISTPL_POWER_VNOM]/10000;
-	else if (dflt->vpp1.present & (1<<CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = dflt->vpp1.param[CISTPL_POWER_VNOM]/10000;
-
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-					pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-	}
-
-	/* This reserves IO space but doesn't actually enable it */
 	return pcmcia_request_io(p_dev);
 }
 
@@ -220,18 +129,9 @@
 
 	dev_dbg(&link->dev, "atmel_config\n");
 
-	/*
-	  In this loop, we scan the CIS for configuration table entries,
-	  each of which describes a valid card configuration, including
-	  voltage, IO window, memory window, and interrupt settings.
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_VPP |
+		CONF_AUTO_AUDIO | CONF_AUTO_SET_IO;
 
-	  We make no assumptions about the card to be configured: we use
-	  just the information available in the CIS.  In an ideal world,
-	  this would work for any PCMCIA card, but it requires a complete
-	  and accurate CIS.  In practice, a driver usually "knows" most of
-	  these things without consulting the CIS, and most client drivers
-	  will only use the CIS to fill in implementation-defined details.
-	*/
 	if (pcmcia_loop_config(link, atmel_config_check, NULL))
 		goto failed;
 
@@ -240,12 +140,7 @@
 		goto failed;
 	}
 
-	/*
-	  This actually configures the PCMCIA socket -- setting up
-	  the I/O windows and the interrupt mapping, and putting the
-	  card and host interface into "Memory and IO" mode.
-	*/
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -267,14 +162,6 @@
 	return -ENODEV;
 }
 
-/*======================================================================
-
-  After a card is removed, atmel_release() will unregister the
-  device, and release the PCMCIA configuration.  If the device is
-  still open, this will be postponed until it is closed.
-
-  ======================================================================*/
-
 static void atmel_release(struct pcmcia_device *link)
 {
 	struct net_device *dev = ((local_info_t*)link->priv)->eth_dev;
@@ -353,9 +240,7 @@
 
 static struct pcmcia_driver atmel_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "atmel_cs",
-        },
+	.name		= "atmel_cs",
 	.probe          = atmel_probe,
 	.remove		= atmel_detach,
 	.id_table	= atmel_ids,
@@ -363,12 +248,12 @@
 	.resume		= atmel_resume,
 };
 
-static int atmel_cs_init(void)
+static int __init atmel_cs_init(void)
 {
         return pcmcia_register_driver(&atmel_driver);
 }
 
-static void atmel_cs_cleanup(void)
+static void __exit atmel_cs_cleanup(void)
 {
         pcmcia_unregister_driver(&atmel_driver);
 }
diff --git a/drivers/net/wireless/b43/debugfs.c b/drivers/net/wireless/b43/debugfs.c
index 80b19a4..59f59fa 100644
--- a/drivers/net/wireless/b43/debugfs.c
+++ b/drivers/net/wireless/b43/debugfs.c
@@ -627,6 +627,7 @@
 			.open	= b43_debugfs_open,		\
 			.read	= b43_debugfs_read,		\
 			.write	= b43_debugfs_write,		\
+			.llseek = generic_file_llseek,		\
 		},						\
 		.file_struct_offset = offsetof(struct b43_dfsentry, \
 					       file_##name),	\
diff --git a/drivers/net/wireless/b43/pcmcia.c b/drivers/net/wireless/b43/pcmcia.c
index dfbc41d..7dcba5f 100644
--- a/drivers/net/wireless/b43/pcmcia.c
+++ b/drivers/net/wireless/b43/pcmcia.c
@@ -26,7 +26,6 @@
 #include <linux/ssb/ssb.h>
 #include <linux/slab.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -63,7 +62,6 @@
 static int __devinit b43_pcmcia_probe(struct pcmcia_device *dev)
 {
 	struct ssb_bus *ssb;
-	win_req_t win;
 	int err = -ENOMEM;
 	int res = 0;
 
@@ -73,30 +71,28 @@
 
 	err = -ENODEV;
 
-	dev->conf.Attributes = CONF_ENABLE_IRQ;
-	dev->conf.IntType = INT_MEMORY_AND_IO;
+	dev->config_flags |= CONF_ENABLE_IRQ;
 
-	win.Attributes =  WIN_ENABLE | WIN_DATA_WIDTH_16 |
+	dev->resource[2]->flags |=  WIN_ENABLE | WIN_DATA_WIDTH_16 |
 			 WIN_USE_WAIT;
-	win.Base = 0;
-	win.Size = SSB_CORE_SIZE;
-	win.AccessSpeed = 250;
-	res = pcmcia_request_window(dev, &win, &dev->win);
+	dev->resource[2]->start = 0;
+	dev->resource[2]->end = SSB_CORE_SIZE;
+	res = pcmcia_request_window(dev, dev->resource[2], 250);
 	if (res != 0)
 		goto err_kfree_ssb;
 
-	res = pcmcia_map_mem_page(dev, dev->win, 0);
+	res = pcmcia_map_mem_page(dev, dev->resource[2], 0);
 	if (res != 0)
 		goto err_disable;
 
 	if (!dev->irq)
 		goto err_disable;
 
-	res = pcmcia_request_configuration(dev, &dev->conf);
+	res = pcmcia_enable_device(dev);
 	if (res != 0)
 		goto err_disable;
 
-	err = ssb_bus_pcmciabus_register(ssb, dev, win.Base);
+	err = ssb_bus_pcmciabus_register(ssb, dev, dev->resource[2]->start);
 	if (err)
 		goto err_disable;
 	dev->priv = ssb;
@@ -125,9 +121,7 @@
 
 static struct pcmcia_driver b43_pcmcia_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-				.name = "b43-pcmcia",
-			},
+	.name		= "b43-pcmcia",
 	.id_table	= b43_pcmcia_tbl,
 	.probe		= b43_pcmcia_probe,
 	.remove		= __devexit_p(b43_pcmcia_remove),
diff --git a/drivers/net/wireless/b43legacy/debugfs.c b/drivers/net/wireless/b43legacy/debugfs.c
index 1f85ac5..f232618 100644
--- a/drivers/net/wireless/b43legacy/debugfs.c
+++ b/drivers/net/wireless/b43legacy/debugfs.c
@@ -334,6 +334,7 @@
 			.open	= b43legacy_debugfs_open,		\
 			.read	= b43legacy_debugfs_read,		\
 			.write	= b43legacy_debugfs_write,		\
+			.llseek = generic_file_llseek,			\
 		},						\
 		.file_struct_offset = offsetof(struct b43legacy_dfsentry, \
 					       file_##name),	\
diff --git a/drivers/net/wireless/hostap/hostap_cs.c b/drivers/net/wireless/hostap/hostap_cs.c
index ba54d1b..bd8a413 100644
--- a/drivers/net/wireless/hostap/hostap_cs.c
+++ b/drivers/net/wireless/hostap/hostap_cs.c
@@ -12,7 +12,6 @@
 #include <linux/wireless.h>
 #include <net/iw_handler.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -437,7 +436,6 @@
 	int ret;
 
 	PDEBUG(DEBUG_HW, "%s: setting Vcc=33 (constant)\n", dev_info);
-	p_dev->conf.IntType = INT_MEMORY_AND_IO;
 
 	ret = prism2_config(p_dev);
 	if (ret) {
@@ -468,74 +466,11 @@
 }
 
 
-/* run after a CARD_INSERTION event is received to configure the PCMCIA
- * socket and make the device available to the system */
-
-static int prism2_config_check(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cfg,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int prism2_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	PDEBUG(DEBUG_EXTRA, "Checking CFTABLE_ENTRY 0x%02X "
-	       "(default 0x%02X)\n", cfg->index, dflt->index);
-
-	/* Does this card need audio output? */
-	if (cfg->flags & CISTPL_CFTABLE_AUDIO) {
-		p_dev->conf.Attributes |= CONF_ENABLE_SPKR;
-		p_dev->conf.Status = CCSR_AUDIO_ENA;
-	}
-
-	/* Use power settings for Vcc and Vpp if present */
-	/*  Note that the CIS values need to be rescaled */
-	if (cfg->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-		if (vcc != cfg->vcc.param[CISTPL_POWER_VNOM] /
-		    10000 && !ignore_cis_vcc) {
-			PDEBUG(DEBUG_EXTRA, "  Vcc mismatch - skipping"
-			       " this entry\n");
-			return -ENODEV;
-		}
-	} else if (dflt->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-		if (vcc != dflt->vcc.param[CISTPL_POWER_VNOM] /
-		    10000 && !ignore_cis_vcc) {
-			PDEBUG(DEBUG_EXTRA, "  Vcc (default) mismatch "
-			       "- skipping this entry\n");
-			return -ENODEV;
-		}
-	}
-
-	if (cfg->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = cfg->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-	else if (dflt->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp = dflt->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	PDEBUG(DEBUG_EXTRA, "IO window settings: cfg->io.nwin=%d "
-	       "dflt->io.nwin=%d\n",
-	       cfg->io.nwin, dflt->io.nwin);
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-					pcmcia_io_cfg_data_width(io->flags);
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-	}
-
-	/* This reserves IO space but doesn't actually enable it */
 	return pcmcia_request_io(p_dev);
 }
 
@@ -557,6 +492,10 @@
 	}
 
 	/* Look for an appropriate configuration table entry in the CIS */
+	link->config_flags |= CONF_AUTO_SET_VPP | CONF_AUTO_AUDIO |
+		CONF_AUTO_CHECK_VCC | CONF_AUTO_SET_IO | CONF_ENABLE_IRQ;
+	if (ignore_cis_vcc)
+		link->config_flags &= ~CONF_AUTO_CHECK_VCC;
 	ret = pcmcia_loop_config(link, prism2_config_check, NULL);
 	if (ret) {
 		if (!ignore_cis_vcc)
@@ -588,12 +527,7 @@
 	if (ret)
 		goto failed_unlock;
 
-	/*
-	 * This actually configures the PCMCIA socket -- setting up
-	 * the I/O windows and the interrupt mapping, and putting the
-	 * card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed_unlock;
 
@@ -602,20 +536,6 @@
 
 	spin_unlock_irqrestore(&local->irq_init_lock, flags);
 
-	/* Finally, report what we've done */
-	printk(KERN_INFO "%s: index 0x%02x: ",
-	       dev_info, link->conf.ConfigIndex);
-	if (link->conf.Vpp)
-		printk(", Vpp %d.%d", link->conf.Vpp / 10,
-		       link->conf.Vpp % 10);
-	if (link->conf.Attributes & CONF_ENABLE_IRQ)
-		printk(", irq %d", link->irq);
-	if (link->resource[0])
-		printk(" & %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(" & %pR", link->resource[1]);
-	printk("\n");
-
 	local->shutdown = 0;
 
 	sandisk_enable_wireless(dev);
@@ -627,7 +547,7 @@
 	return ret;
 
  failed_unlock:
-	 spin_unlock_irqrestore(&local->irq_init_lock, flags);
+	spin_unlock_irqrestore(&local->irq_init_lock, flags);
  failed:
 	kfree(hw_priv);
 	prism2_release((u_long)link);
@@ -779,9 +699,7 @@
 
 
 static struct pcmcia_driver hostap_driver = {
-	.drv		= {
-		.name	= "hostap_cs",
-	},
+	.name		= "hostap_cs",
 	.probe		= hostap_cs_probe,
 	.remove		= prism2_detach,
 	.owner		= THIS_MODULE,
diff --git a/drivers/net/wireless/iwlwifi/iwl-3945-rs.c b/drivers/net/wireless/iwlwifi/iwl-3945-rs.c
index 8e84a08..293e1db 100644
--- a/drivers/net/wireless/iwlwifi/iwl-3945-rs.c
+++ b/drivers/net/wireless/iwlwifi/iwl-3945-rs.c
@@ -873,6 +873,7 @@
 static const struct file_operations rs_sta_dbgfs_stats_table_ops = {
 	.read = iwl3945_sta_dbgfs_stats_table_read,
 	.open = iwl3945_open_file_generic,
+	.llseek = default_llseek,
 };
 
 static void iwl3945_add_debugfs(void *priv, void *priv_sta,
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c
index 23e5c42..a4378ba 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c
@@ -2873,6 +2873,7 @@
 	.write = rs_sta_dbgfs_scale_table_write,
 	.read = rs_sta_dbgfs_scale_table_read,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 static ssize_t rs_sta_dbgfs_stats_table_read(struct file *file,
 			char __user *user_buf, size_t count, loff_t *ppos)
@@ -2915,6 +2916,7 @@
 static const struct file_operations rs_sta_dbgfs_stats_table_ops = {
 	.read = rs_sta_dbgfs_stats_table_read,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t rs_sta_dbgfs_rate_scale_data_read(struct file *file,
@@ -2946,6 +2948,7 @@
 static const struct file_operations rs_sta_dbgfs_rate_scale_data_ops = {
 	.read = rs_sta_dbgfs_rate_scale_data_read,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 
 static void rs_add_debugfs(void *priv, void *priv_sta,
diff --git a/drivers/net/wireless/iwlwifi/iwl-debugfs.c b/drivers/net/wireless/iwlwifi/iwl-debugfs.c
index e96a1bb..a32d5d3 100644
--- a/drivers/net/wireless/iwlwifi/iwl-debugfs.c
+++ b/drivers/net/wireless/iwlwifi/iwl-debugfs.c
@@ -87,6 +87,7 @@
 static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 	.read = iwl_dbgfs_##name##_read,                       		\
 	.open = iwl_dbgfs_open_file_generic,                    	\
+	.llseek = generic_file_llseek,					\
 };
 
 #define DEBUGFS_WRITE_FILE_OPS(name)                                    \
@@ -94,6 +95,7 @@
 static const struct file_operations iwl_dbgfs_##name##_ops = {          \
 	.write = iwl_dbgfs_##name##_write,                              \
 	.open = iwl_dbgfs_open_file_generic,                    	\
+	.llseek = generic_file_llseek,					\
 };
 
 
@@ -104,6 +106,7 @@
 	.write = iwl_dbgfs_##name##_write,                              \
 	.read = iwl_dbgfs_##name##_read,                                \
 	.open = iwl_dbgfs_open_file_generic,                            \
+	.llseek = generic_file_llseek,					\
 };
 
 static ssize_t iwl_dbgfs_tx_statistics_read(struct file *file,
diff --git a/drivers/net/wireless/iwmc3200wifi/debugfs.c b/drivers/net/wireless/iwmc3200wifi/debugfs.c
index 53b0b77..0a0cc96 100644
--- a/drivers/net/wireless/iwmc3200wifi/debugfs.c
+++ b/drivers/net/wireless/iwmc3200wifi/debugfs.c
@@ -402,24 +402,28 @@
 	.owner =	THIS_MODULE,
 	.open =		iwm_generic_open,
 	.read =		iwm_debugfs_txq_read,
+	.llseek =	default_llseek,
 };
 
 static const struct file_operations iwm_debugfs_tx_credit_fops = {
 	.owner =	THIS_MODULE,
 	.open =		iwm_generic_open,
 	.read =		iwm_debugfs_tx_credit_read,
+	.llseek =	default_llseek,
 };
 
 static const struct file_operations iwm_debugfs_rx_ticket_fops = {
 	.owner =	THIS_MODULE,
 	.open =		iwm_generic_open,
 	.read =		iwm_debugfs_rx_ticket_read,
+	.llseek =	default_llseek,
 };
 
 static const struct file_operations iwm_debugfs_fw_err_fops = {
 	.owner =	THIS_MODULE,
 	.open =		iwm_generic_open,
 	.read =		iwm_debugfs_fw_err_read,
+	.llseek =	default_llseek,
 };
 
 void iwm_debugfs_init(struct iwm_priv *iwm)
diff --git a/drivers/net/wireless/iwmc3200wifi/sdio.c b/drivers/net/wireless/iwmc3200wifi/sdio.c
index edcb523..56383e7 100644
--- a/drivers/net/wireless/iwmc3200wifi/sdio.c
+++ b/drivers/net/wireless/iwmc3200wifi/sdio.c
@@ -364,6 +364,7 @@
 	.owner =	THIS_MODULE,
 	.open =		iwm_debugfs_sdio_open,
 	.read =		iwm_debugfs_sdio_read,
+	.llseek =	default_llseek,
 };
 
 static void if_sdio_debugfs_init(struct iwm_priv *iwm, struct dentry *parent_dir)
diff --git a/drivers/net/wireless/libertas/debugfs.c b/drivers/net/wireless/libertas/debugfs.c
index 651a79c..fbf3b033 100644
--- a/drivers/net/wireless/libertas/debugfs.c
+++ b/drivers/net/wireless/libertas/debugfs.c
@@ -696,6 +696,7 @@
 	.open = open_file_generic, \
 	.read = (fread), \
 	.write = (fwrite), \
+	.llseek = generic_file_llseek, \
 }
 
 struct lbs_debugfs_files {
@@ -961,6 +962,7 @@
 	.open = open_file_generic,
 	.write = lbs_debugfs_write,
 	.read = lbs_debugfs_read,
+	.llseek = default_llseek,
 };
 
 /**
diff --git a/drivers/net/wireless/libertas/if_cs.c b/drivers/net/wireless/libertas/if_cs.c
index 9c29839..ff1280f 100644
--- a/drivers/net/wireless/libertas/if_cs.c
+++ b/drivers/net/wireless/libertas/if_cs.c
@@ -28,7 +28,6 @@
 #include <linux/firmware.h>
 #include <linux/netdevice.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -761,15 +760,6 @@
 }
 
 
-/********************************************************************/
-/* Card Services                                                    */
-/********************************************************************/
-
-/*
- * After a card is removed, if_cs_release() will unregister the
- * device, and release the PCMCIA configuration.  If the device is
- * still open, this will be postponed until it is closed.
- */
 static void if_cs_release(struct pcmcia_device *p_dev)
 {
 	struct if_cs_card *card = p_dev->priv;
@@ -785,31 +775,12 @@
 }
 
 
-/*
- * This creates an "instance" of the driver, allocating local data
- * structures for one device.  The device is registered with Card
- * Services.
- *
- * The dev_link structure is initialized, but we don't actually
- * configure the card at this point -- we wait until we receive a card
- * insertion event.
- */
-
-static int if_cs_ioprobe(struct pcmcia_device *p_dev,
-			 cistpl_cftable_entry_t *cfg,
-			 cistpl_cftable_entry_t *dflt,
-			 unsigned int vcc,
-			 void *priv_data)
+static int if_cs_ioprobe(struct pcmcia_device *p_dev, void *priv_data)
 {
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
 	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-	p_dev->resource[0]->start = cfg->io.win[0].base;
-	p_dev->resource[0]->end = cfg->io.win[0].len;
 
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	if (cfg->io.nwin != 1) {
+	if (p_dev->resource[1]->end) {
 		lbs_pr_err("wrong CIS (check number of IO windows)\n");
 		return -ENODEV;
 	}
@@ -835,15 +806,13 @@
 	card->p_dev = p_dev;
 	p_dev->priv = card;
 
-	p_dev->conf.Attributes = 0;
-	p_dev->conf.IntType = INT_MEMORY_AND_IO;
+	p_dev->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
 
 	if (pcmcia_loop_config(p_dev, if_cs_ioprobe, NULL)) {
 		lbs_pr_err("error in pcmcia_loop_config\n");
 		goto out1;
 	}
 
-
 	/*
 	 * Allocate an interrupt line.  Note that this does not assign
 	 * a handler to the interrupt, unless the 'Handler' member of
@@ -861,14 +830,9 @@
 		goto out1;
 	}
 
-	/*
-	 * This actually configures the PCMCIA socket -- setting up
-	 * the I/O windows and the interrupt mapping, and putting the
-	 * card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(p_dev, &p_dev->conf);
+	ret = pcmcia_enable_device(p_dev);
 	if (ret) {
-		lbs_pr_err("error in pcmcia_request_configuration\n");
+		lbs_pr_err("error in pcmcia_enable_device\n");
 		goto out2;
 	}
 
@@ -962,12 +926,6 @@
 }
 
 
-/*
- * This deletes a driver "instance".  The device is de-registered with
- * Card Services.  If it has been released, all local data structures
- * are freed.  Otherwise, the structures will be freed when the device
- * is released.
- */
 static void if_cs_detach(struct pcmcia_device *p_dev)
 {
 	struct if_cs_card *card = p_dev->priv;
@@ -1000,9 +958,7 @@
 
 static struct pcmcia_driver lbs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= DRV_NAME,
-	},
+	.name		= DRV_NAME,
 	.probe		= if_cs_probe,
 	.remove		= if_cs_detach,
 	.id_table       = if_cs_ids,
diff --git a/drivers/net/wireless/orinoco/orinoco_cs.c b/drivers/net/wireless/orinoco/orinoco_cs.c
index ef46a2d..71b3d68 100644
--- a/drivers/net/wireless/orinoco/orinoco_cs.c
+++ b/drivers/net/wireless/orinoco/orinoco_cs.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -93,14 +92,6 @@
 /* PCMCIA stuff     						    */
 /********************************************************************/
 
-/*
- * This creates an "instance" of the driver, allocating local data
- * structures for one device.  The device is registered with Card
- * Services.
- *
- * The dev_link structure is initialized, but we don't actually
- * configure the card at this point -- we wait until we receive a card
- * insertion event.  */
 static int
 orinoco_cs_probe(struct pcmcia_device *link)
 {
@@ -117,23 +108,9 @@
 	card->p_dev = link;
 	link->priv = priv;
 
-	/* General socket configuration defaults can go here.  In this
-	 * client, we assume very little, and rely on the CIS for
-	 * almost everything.  In most clients, many details (i.e.,
-	 * number, sizes, and attributes of IO windows) are fixed by
-	 * the nature of the device, and can be hard-wired here. */
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	return orinoco_cs_config(link);
 }				/* orinoco_cs_attach */
 
-/*
- * This deletes a driver "instance".  The device is de-registered with
- * Card Services.  If it has been released, all local data structures
- * are freed.  Otherwise, the structures will be freed when the device
- * is released.
- */
 static void orinoco_cs_detach(struct pcmcia_device *link)
 {
 	struct orinoco_private *priv = link->priv;
@@ -145,76 +122,12 @@
 	free_orinocodev(priv);
 }				/* orinoco_cs_detach */
 
-/*
- * orinoco_cs_config() is scheduled to run after a CARD_INSERTION
- * event is received, to configure the PCMCIA socket, and to make the
- * device available to the system.
- */
-
-static int orinoco_cs_config_check(struct pcmcia_device *p_dev,
-				   cistpl_cftable_entry_t *cfg,
-				   cistpl_cftable_entry_t *dflt,
-				   unsigned int vcc,
-				   void *priv_data)
+static int orinoco_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cfg->index == 0)
-		goto next_entry;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Use power settings for Vcc and Vpp if present */
-	/* Note that the CIS values need to be rescaled */
-	if (cfg->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-		if (vcc != cfg->vcc.param[CISTPL_POWER_VNOM] / 10000) {
-			DEBUG(2, "%s: Vcc mismatch (vcc = %d, CIS = %d)\n",
-			      __func__, vcc,
-			      cfg->vcc.param[CISTPL_POWER_VNOM] / 10000);
-			if (!ignore_cis_vcc)
-				goto next_entry;
-		}
-	} else if (dflt->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-		if (vcc != dflt->vcc.param[CISTPL_POWER_VNOM] / 10000) {
-			DEBUG(2, "%s: Vcc mismatch (vcc = %d, CIS = %d)\n",
-			      __func__, vcc,
-			      dflt->vcc.param[CISTPL_POWER_VNOM] / 10000);
-			if (!ignore_cis_vcc)
-				goto next_entry;
-		}
-	}
-
-	if (cfg->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp =
-			cfg->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-	else if (dflt->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp =
-			dflt->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-			pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-
-		/* This reserves IO space but doesn't actually enable it */
-		if (pcmcia_request_io(p_dev) != 0)
-			goto next_entry;
-	}
-	return 0;
-
-next_entry:
-	pcmcia_disable_device(p_dev);
-	return -ENODEV;
+	return pcmcia_request_io(p_dev);
 };
 
 static int
@@ -225,20 +138,10 @@
 	int ret;
 	void __iomem *mem;
 
-	/*
-	 * In this loop, we scan the CIS for configuration table
-	 * entries, each of which describes a valid card
-	 * configuration, including voltage, IO window, memory window,
-	 * and interrupt settings.
-	 *
-	 * We make no assumptions about the card to be configured: we
-	 * use just the information available in the CIS.  In an ideal
-	 * world, this would work for any PCMCIA card, but it requires
-	 * a complete and accurate CIS.  In practice, a driver usually
-	 * "knows" most of these things without consulting the CIS,
-	 * and most client drivers will only use the CIS to fill in
-	 * implementation-defined details.
-	 */
+	link->config_flags |= CONF_AUTO_SET_VPP | CONF_AUTO_CHECK_VCC |
+		CONF_AUTO_SET_IO | CONF_ENABLE_IRQ;
+	if (ignore_cis_vcc)
+		link->config_flags &= ~CONF_AUTO_CHECK_VCC;
 	ret = pcmcia_loop_config(link, orinoco_cs_config_check, NULL);
 	if (ret) {
 		if (!ignore_cis_vcc)
@@ -262,12 +165,7 @@
 
 	hermes_struct_init(hw, mem, HERMES_16BIT_REGSPACING);
 
-	/*
-	 * This actually configures the PCMCIA socket -- setting up
-	 * the I/O windows and the interrupt mapping, and putting the
-	 * card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -291,11 +189,6 @@
 	return -ENODEV;
 }				/* orinoco_cs_config */
 
-/*
- * After a card is removed, orinoco_cs_release() will unregister the
- * device, and release the PCMCIA configuration.  If the device is
- * still open, this will be postponed until it is closed.
- */
 static void
 orinoco_cs_release(struct pcmcia_device *link)
 {
@@ -344,12 +237,6 @@
 /* Module initialization					    */
 /********************************************************************/
 
-/* Can't be declared "const" or the whole __initdata section will
- * become const */
-static char version[] __initdata = DRIVER_NAME " " DRIVER_VERSION
-	" (David Gibson <hermes@gibson.dropbear.id.au>, "
-	"Pavel Roskin <proski@gnu.org>, et al)";
-
 static struct pcmcia_device_id orinoco_cs_ids[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x0101, 0x0777), /* 3Com AirConnect PCI 777A */
 	PCMCIA_DEVICE_MANF_CARD(0x0156, 0x0002), /* Lucent Orinoco and old Intersil */
@@ -441,9 +328,7 @@
 
 static struct pcmcia_driver orinoco_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= DRIVER_NAME,
-	},
+	.name		= DRIVER_NAME,
 	.probe		= orinoco_cs_probe,
 	.remove		= orinoco_cs_detach,
 	.id_table       = orinoco_cs_ids,
@@ -454,8 +339,6 @@
 static int __init
 init_orinoco_cs(void)
 {
-	printk(KERN_DEBUG "%s\n", version);
-
 	return pcmcia_register_driver(&orinoco_driver);
 }
 
diff --git a/drivers/net/wireless/orinoco/spectrum_cs.c b/drivers/net/wireless/orinoco/spectrum_cs.c
index 873877e..fb859a5 100644
--- a/drivers/net/wireless/orinoco/spectrum_cs.c
+++ b/drivers/net/wireless/orinoco/spectrum_cs.c
@@ -25,7 +25,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -154,14 +153,6 @@
 /* PCMCIA stuff     						    */
 /********************************************************************/
 
-/*
- * This creates an "instance" of the driver, allocating local data
- * structures for one device.  The device is registered with Card
- * Services.
- *
- * The dev_link structure is initialized, but we don't actually
- * configure the card at this point -- we wait until we receive a card
- * insertion event.  */
 static int
 spectrum_cs_probe(struct pcmcia_device *link)
 {
@@ -179,23 +170,9 @@
 	card->p_dev = link;
 	link->priv = priv;
 
-	/* General socket configuration defaults can go here.  In this
-	 * client, we assume very little, and rely on the CIS for
-	 * almost everything.  In most clients, many details (i.e.,
-	 * number, sizes, and attributes of IO windows) are fixed by
-	 * the nature of the device, and can be hard-wired here. */
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	return spectrum_cs_config(link);
 }				/* spectrum_cs_attach */
 
-/*
- * This deletes a driver "instance".  The device is de-registered with
- * Card Services.  If it has been released, all local data structures
- * are freed.  Otherwise, the structures will be freed when the device
- * is released.
- */
 static void spectrum_cs_detach(struct pcmcia_device *link)
 {
 	struct orinoco_private *priv = link->priv;
@@ -207,76 +184,13 @@
 	free_orinocodev(priv);
 }				/* spectrum_cs_detach */
 
-/*
- * spectrum_cs_config() is scheduled to run after a CARD_INSERTION
- * event is received, to configure the PCMCIA socket, and to make the
- * device available to the system.
- */
-
 static int spectrum_cs_config_check(struct pcmcia_device *p_dev,
-				    cistpl_cftable_entry_t *cfg,
-				    cistpl_cftable_entry_t *dflt,
-				    unsigned int vcc,
 				    void *priv_data)
 {
-	if (cfg->index == 0)
-		goto next_entry;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Use power settings for Vcc and Vpp if present */
-	/* Note that the CIS values need to be rescaled */
-	if (cfg->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-		if (vcc != cfg->vcc.param[CISTPL_POWER_VNOM] / 10000) {
-			DEBUG(2, "%s: Vcc mismatch (vcc = %d, CIS = %d)\n",
-			      __func__, vcc,
-			      cfg->vcc.param[CISTPL_POWER_VNOM] / 10000);
-			if (!ignore_cis_vcc)
-				goto next_entry;
-		}
-	} else if (dflt->vcc.present & (1 << CISTPL_POWER_VNOM)) {
-		if (vcc != dflt->vcc.param[CISTPL_POWER_VNOM] / 10000) {
-			DEBUG(2, "%s: Vcc mismatch (vcc = %d, CIS = %d)\n",
-			      __func__, vcc,
-			      dflt->vcc.param[CISTPL_POWER_VNOM] / 10000);
-			if (!ignore_cis_vcc)
-				goto next_entry;
-		}
-	}
-
-	if (cfg->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp =
-			cfg->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-	else if (dflt->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp =
-			dflt->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-			pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-
-		/* This reserves IO space but doesn't actually enable it */
-		if (pcmcia_request_io(p_dev) != 0)
-			goto next_entry;
-	}
-	return 0;
-
-next_entry:
-	pcmcia_disable_device(p_dev);
-	return -ENODEV;
+	return pcmcia_request_io(p_dev);
 };
 
 static int
@@ -287,20 +201,10 @@
 	int ret;
 	void __iomem *mem;
 
-	/*
-	 * In this loop, we scan the CIS for configuration table
-	 * entries, each of which describes a valid card
-	 * configuration, including voltage, IO window, memory window,
-	 * and interrupt settings.
-	 *
-	 * We make no assumptions about the card to be configured: we
-	 * use just the information available in the CIS.  In an ideal
-	 * world, this would work for any PCMCIA card, but it requires
-	 * a complete and accurate CIS.  In practice, a driver usually
-	 * "knows" most of these things without consulting the CIS,
-	 * and most client drivers will only use the CIS to fill in
-	 * implementation-defined details.
-	 */
+	link->config_flags |= CONF_AUTO_SET_VPP | CONF_AUTO_CHECK_VCC |
+		CONF_AUTO_SET_IO | CONF_ENABLE_IRQ;
+	if (ignore_cis_vcc)
+		link->config_flags &= ~CONF_AUTO_CHECK_VCC;
 	ret = pcmcia_loop_config(link, spectrum_cs_config_check, NULL);
 	if (ret) {
 		if (!ignore_cis_vcc)
@@ -325,12 +229,7 @@
 	hermes_struct_init(hw, mem, HERMES_16BIT_REGSPACING);
 	hw->eeprom_pda = true;
 
-	/*
-	 * This actually configures the PCMCIA socket -- setting up
-	 * the I/O windows and the interrupt mapping, and putting the
-	 * card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -358,11 +257,6 @@
 	return -ENODEV;
 }				/* spectrum_cs_config */
 
-/*
- * After a card is removed, spectrum_cs_release() will unregister the
- * device, and release the PCMCIA configuration.  If the device is
- * still open, this will be postponed until it is closed.
- */
 static void
 spectrum_cs_release(struct pcmcia_device *link)
 {
@@ -407,12 +301,6 @@
 /* Module initialization					    */
 /********************************************************************/
 
-/* Can't be declared "const" or the whole __initdata section will
- * become const */
-static char version[] __initdata = DRIVER_NAME " " DRIVER_VERSION
-	" (Pavel Roskin <proski@gnu.org>,"
-	" David Gibson <hermes@gibson.dropbear.id.au>, et al)";
-
 static struct pcmcia_device_id spectrum_cs_ids[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x026c, 0x0001), /* Symbol Spectrum24 LA4137 */
 	PCMCIA_DEVICE_MANF_CARD(0x0104, 0x0001), /* Socket Communications CF */
@@ -423,9 +311,7 @@
 
 static struct pcmcia_driver orinoco_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= DRIVER_NAME,
-	},
+	.name		= DRIVER_NAME,
 	.probe		= spectrum_cs_probe,
 	.remove		= spectrum_cs_detach,
 	.suspend	= spectrum_cs_suspend,
@@ -436,8 +322,6 @@
 static int __init
 init_spectrum_cs(void)
 {
-	printk(KERN_DEBUG "%s\n", version);
-
 	return pcmcia_register_driver(&orinoco_driver);
 }
 
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 88560d0..46da037 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -46,7 +46,6 @@
 #include <linux/ethtool.h>
 #include <linux/ieee80211.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -169,13 +168,6 @@
  */
 static char *phy_addr = NULL;
 
-
-/* A struct pcmcia_device structure has fields for most things that are needed
-   to keep track of a socket, but there will usually be some device
-   specific information that also needs to be kept track of.  The
-   'priv' pointer in a struct pcmcia_device structure can be used to point to
-   a device-specific private data structure, like this.
-*/
 static unsigned int ray_mem_speed = 500;
 
 /* WARNING: THIS DRIVER IS NOT CAPABLE OF HANDLING MULTIPLE DEVICES! */
@@ -290,14 +282,6 @@
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-/*=============================================================================
-    ray_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-=============================================================================*/
 static int ray_probe(struct pcmcia_device *p_dev)
 {
 	ray_dev_t *local;
@@ -318,9 +302,8 @@
 	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
 
 	/* General socket configuration */
-	p_dev->conf.Attributes = CONF_ENABLE_IRQ;
-	p_dev->conf.IntType = INT_MEMORY_AND_IO;
-	p_dev->conf.ConfigIndex = 1;
+	p_dev->config_flags |= CONF_ENABLE_IRQ;
+	p_dev->config_index = 1;
 
 	p_dev->priv = dev;
 
@@ -353,12 +336,6 @@
 	return -ENOMEM;
 } /* ray_attach */
 
-/*=============================================================================
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-=============================================================================*/
 static void ray_detach(struct pcmcia_device *link)
 {
 	struct net_device *dev;
@@ -381,17 +358,11 @@
 	dev_dbg(&link->dev, "ray_cs ray_detach ending\n");
 } /* ray_detach */
 
-/*=============================================================================
-    ray_config() is run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ethernet device available to the system.
-=============================================================================*/
 #define MAX_TUPLE_SIZE 128
 static int ray_config(struct pcmcia_device *link)
 {
 	int ret = 0;
 	int i;
-	win_req_t req;
 	struct net_device *dev = (struct net_device *)link->priv;
 	ray_dev_t *local = netdev_priv(dev);
 
@@ -412,54 +383,50 @@
 		goto failed;
 	dev->irq = link->irq;
 
-	/* This actually configures the PCMCIA socket -- setting up
-	   the I/O windows and the interrupt mapping.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
 /*** Set up 32k window for shared memory (transmit and control) ************/
-	req.Attributes =
-	    WIN_DATA_WIDTH_8 | WIN_MEMORY_TYPE_CM | WIN_ENABLE | WIN_USE_WAIT;
-	req.Base = 0;
-	req.Size = 0x8000;
-	req.AccessSpeed = ray_mem_speed;
-	ret = pcmcia_request_window(link, &req, &link->win);
+	link->resource[2]->flags |= WIN_DATA_WIDTH_8 | WIN_MEMORY_TYPE_CM | WIN_ENABLE | WIN_USE_WAIT;
+	link->resource[2]->start = 0;
+	link->resource[2]->end = 0x8000;
+	ret = pcmcia_request_window(link, link->resource[2], ray_mem_speed);
 	if (ret)
 		goto failed;
-	ret = pcmcia_map_mem_page(link, link->win, 0);
+	ret = pcmcia_map_mem_page(link, link->resource[2], 0);
 	if (ret)
 		goto failed;
-	local->sram = ioremap(req.Base, req.Size);
+	local->sram = ioremap(link->resource[2]->start,
+			resource_size(link->resource[2]));
 
 /*** Set up 16k window for shared memory (receive buffer) ***************/
-	req.Attributes =
+	link->resource[3]->flags |=
 	    WIN_DATA_WIDTH_8 | WIN_MEMORY_TYPE_CM | WIN_ENABLE | WIN_USE_WAIT;
-	req.Base = 0;
-	req.Size = 0x4000;
-	req.AccessSpeed = ray_mem_speed;
-	ret = pcmcia_request_window(link, &req, &local->rmem_handle);
+	link->resource[3]->start = 0;
+	link->resource[3]->end = 0x4000;
+	ret = pcmcia_request_window(link, link->resource[3], ray_mem_speed);
 	if (ret)
 		goto failed;
-	ret = pcmcia_map_mem_page(link, local->rmem_handle, 0x8000);
+	ret = pcmcia_map_mem_page(link, link->resource[3], 0x8000);
 	if (ret)
 		goto failed;
-	local->rmem = ioremap(req.Base, req.Size);
+	local->rmem = ioremap(link->resource[3]->start,
+			resource_size(link->resource[3]));
 
 /*** Set up window for attribute memory ***********************************/
-	req.Attributes =
+	link->resource[4]->flags |=
 	    WIN_DATA_WIDTH_8 | WIN_MEMORY_TYPE_AM | WIN_ENABLE | WIN_USE_WAIT;
-	req.Base = 0;
-	req.Size = 0x1000;
-	req.AccessSpeed = ray_mem_speed;
-	ret = pcmcia_request_window(link, &req, &local->amem_handle);
+	link->resource[4]->start = 0;
+	link->resource[4]->end = 0x1000;
+	ret = pcmcia_request_window(link, link->resource[4], ray_mem_speed);
 	if (ret)
 		goto failed;
-	ret = pcmcia_map_mem_page(link, local->amem_handle, 0);
+	ret = pcmcia_map_mem_page(link, link->resource[4], 0);
 	if (ret)
 		goto failed;
-	local->amem = ioremap(req.Base, req.Size);
+	local->amem = ioremap(link->resource[4]->start,
+			resource_size(link->resource[4]));
 
 	dev_dbg(&link->dev, "ray_config sram=%p\n", local->sram);
 	dev_dbg(&link->dev, "ray_config rmem=%p\n", local->rmem);
@@ -775,11 +742,7 @@
 	local->card_status = CARD_DOING_ACQ;
 }
 
-/*============================================================================
-    After a card is removed, ray_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-=============================================================================*/
+
 static void ray_release(struct pcmcia_device *link)
 {
 	struct net_device *dev = link->priv;
@@ -2802,6 +2765,7 @@
 static const struct file_operations ray_cs_essid_proc_fops = {
 	.owner		= THIS_MODULE,
 	.write		= ray_cs_essid_proc_write,
+	.llseek		= noop_llseek,
 };
 
 static ssize_t int_proc_write(struct file *file, const char __user *buffer,
@@ -2835,6 +2799,7 @@
 static const struct file_operations int_proc_fops = {
 	.owner		= THIS_MODULE,
 	.write		= int_proc_write,
+	.llseek		= noop_llseek,
 };
 #endif
 
@@ -2847,9 +2812,7 @@
 
 static struct pcmcia_driver ray_driver = {
 	.owner = THIS_MODULE,
-	.drv = {
-		.name = "ray_cs",
-		},
+	.name = "ray_cs",
 	.probe = ray_probe,
 	.remove = ray_detach,
 	.id_table = ray_ids,
diff --git a/drivers/net/wireless/ray_cs.h b/drivers/net/wireless/ray_cs.h
index 9f01ddb..e79848f 100644
--- a/drivers/net/wireless/ray_cs.h
+++ b/drivers/net/wireless/ray_cs.h
@@ -25,8 +25,6 @@
 typedef struct ray_dev_t {
     int card_status;
     int authentication_state;
-    window_handle_t amem_handle;   /* handle to window for attribute memory  */
-    window_handle_t rmem_handle;   /* handle to window for rx buffer on card */
     void __iomem *sram;            /* pointer to beginning of shared RAM     */
     void __iomem *amem;            /* pointer to attribute mem window        */
     void __iomem *rmem;            /* pointer to receive buffer window       */
diff --git a/drivers/net/wireless/rt2x00/rt2x00debug.c b/drivers/net/wireless/rt2x00/rt2x00debug.c
index b0498e7..cea81e4 100644
--- a/drivers/net/wireless/rt2x00/rt2x00debug.c
+++ b/drivers/net/wireless/rt2x00/rt2x00debug.c
@@ -315,6 +315,7 @@
 	.poll		= rt2x00debug_poll_queue_dump,
 	.open		= rt2x00debug_open_queue_dump,
 	.release	= rt2x00debug_release_queue_dump,
+	.llseek		= default_llseek,
 };
 
 static ssize_t rt2x00debug_read_queue_stats(struct file *file,
@@ -371,6 +372,7 @@
 	.read		= rt2x00debug_read_queue_stats,
 	.open		= rt2x00debug_file_open,
 	.release	= rt2x00debug_file_release,
+	.llseek		= default_llseek,
 };
 
 #ifdef CONFIG_RT2X00_LIB_CRYPTO
@@ -423,6 +425,7 @@
 	.read		= rt2x00debug_read_crypto_stats,
 	.open		= rt2x00debug_file_open,
 	.release	= rt2x00debug_file_release,
+	.llseek		= default_llseek,
 };
 #endif
 
@@ -509,6 +512,7 @@
 	.write		= rt2x00debug_write_##__name,		\
 	.open		= rt2x00debug_file_open,		\
 	.release	= rt2x00debug_file_release,		\
+	.llseek		= generic_file_llseek,			\
 };
 
 RT2X00DEBUGFS_OPS(csr, "0x%.8x\n", u32);
@@ -542,6 +546,7 @@
 	.read		= rt2x00debug_read_dev_flags,
 	.open		= rt2x00debug_file_open,
 	.release	= rt2x00debug_file_release,
+	.llseek		= default_llseek,
 };
 
 static struct dentry *rt2x00debug_create_file_driver(const char *name,
diff --git a/drivers/net/wireless/wl12xx/wl1251_debugfs.c b/drivers/net/wireless/wl12xx/wl1251_debugfs.c
index 5e4465a..fa620a5 100644
--- a/drivers/net/wireless/wl12xx/wl1251_debugfs.c
+++ b/drivers/net/wireless/wl12xx/wl1251_debugfs.c
@@ -50,6 +50,7 @@
 static const struct file_operations name## _ops = {			\
 	.read = name## _read,						\
 	.open = wl1251_open_file_generic,				\
+	.llseek	= generic_file_llseek,					\
 };
 
 #define DEBUGFS_ADD(name, parent)					\
@@ -86,6 +87,7 @@
 static const struct file_operations sub## _ ##name## _ops = {		\
 	.read = sub## _ ##name## _read,					\
 	.open = wl1251_open_file_generic,				\
+	.llseek	= generic_file_llseek,					\
 };
 
 #define DEBUGFS_FWSTATS_ADD(sub, name)				\
@@ -236,6 +238,7 @@
 static const struct file_operations tx_queue_len_ops = {
 	.read = tx_queue_len_read,
 	.open = wl1251_open_file_generic,
+	.llseek = generic_file_llseek,
 };
 
 static ssize_t tx_queue_status_read(struct file *file, char __user *userbuf,
@@ -257,6 +260,7 @@
 static const struct file_operations tx_queue_status_ops = {
 	.read = tx_queue_status_read,
 	.open = wl1251_open_file_generic,
+	.llseek = generic_file_llseek,
 };
 
 static void wl1251_debugfs_delete_files(struct wl1251 *wl)
diff --git a/drivers/net/wireless/wl12xx/wl1271_debugfs.c b/drivers/net/wireless/wl12xx/wl1271_debugfs.c
index c239ef4..66c2b90 100644
--- a/drivers/net/wireless/wl12xx/wl1271_debugfs.c
+++ b/drivers/net/wireless/wl12xx/wl1271_debugfs.c
@@ -51,6 +51,7 @@
 static const struct file_operations name## _ops = {			\
 	.read = name## _read,						\
 	.open = wl1271_open_file_generic,				\
+	.llseek	= generic_file_llseek,					\
 };
 
 #define DEBUGFS_ADD(name, parent)					\
@@ -87,6 +88,7 @@
 static const struct file_operations sub## _ ##name## _ops = {		\
 	.read = sub## _ ##name## _read,					\
 	.open = wl1271_open_file_generic,				\
+	.llseek	= generic_file_llseek,					\
 };
 
 #define DEBUGFS_FWSTATS_ADD(sub, name)				\
@@ -237,6 +239,7 @@
 static const struct file_operations tx_queue_len_ops = {
 	.read = tx_queue_len_read,
 	.open = wl1271_open_file_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t gpio_power_read(struct file *file, char __user *user_buf,
@@ -291,7 +294,8 @@
 static const struct file_operations gpio_power_ops = {
 	.read = gpio_power_read,
 	.write = gpio_power_write,
-	.open = wl1271_open_file_generic
+	.open = wl1271_open_file_generic,
+	.llseek = default_llseek,
 };
 
 static void wl1271_debugfs_delete_files(struct wl1271 *wl)
diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c
index a1cc2d4..ca3f896 100644
--- a/drivers/net/wireless/wl3501_cs.c
+++ b/drivers/net/wireless/wl3501_cs.c
@@ -48,7 +48,6 @@
 
 #include <net/iw_handler.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -78,13 +77,6 @@
 #define WL3501_RESUME	0
 #define WL3501_SUSPEND	1
 
-/*
- * The event() function is this driver's Card Services event handler.  It will
- * be called by Card Services when an appropriate card status event is
- * received. The config() and release() entry points are used to configure or
- * release a socket, in response to card insertion and ejection events.  They
- * are invoked from the wl24 event handler.
- */
 static int wl3501_config(struct pcmcia_device *link);
 static void wl3501_release(struct pcmcia_device *link);
 
@@ -1869,15 +1861,6 @@
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-/**
- * wl3501_attach - creates an "instance" of the driver
- *
- * Creates an "instance" of the driver, allocating local data structures for
- * one device.  The device is registered with Card Services.
- *
- * The dev_link structure is initialized, but we don't actually configure the
- * card at this point -- we wait until we receive a card insertion event.
- */
 static int wl3501_probe(struct pcmcia_device *p_dev)
 {
 	struct net_device *dev;
@@ -1888,9 +1871,8 @@
 	p_dev->resource[0]->flags	= IO_DATA_PATH_WIDTH_8;
 
 	/* General socket configuration */
-	p_dev->conf.Attributes	= CONF_ENABLE_IRQ;
-	p_dev->conf.IntType	= INT_MEMORY_AND_IO;
-	p_dev->conf.ConfigIndex	= 1;
+	p_dev->config_flags	= CONF_ENABLE_IRQ;
+	p_dev->config_index	= 1;
 
 	dev = alloc_etherdev(sizeof(struct wl3501_card));
 	if (!dev)
@@ -1914,14 +1896,6 @@
 	return -ENOMEM;
 }
 
-/**
- * wl3501_config - configure the PCMCIA socket and make eth device available
- * @link - FILL_IN
- *
- * wl3501_config() is scheduled to run after a CARD_INSERTION event is
- * received, to configure the PCMCIA socket, and to make the ethernet device
- * available to the system.
- */
 static int wl3501_config(struct pcmcia_device *link)
 {
 	struct net_device *dev = link->priv;
@@ -1952,10 +1926,7 @@
 	if (ret)
 		goto failed;
 
-	/* This actually configures the PCMCIA socket -- setting up the I/O
-	 * windows and the interrupt mapping.  */
-
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -2010,14 +1981,6 @@
 	return -ENODEV;
 }
 
-/**
- * wl3501_release - unregister the net, release PCMCIA configuration
- * @arg - link
- *
- * After a card is removed, wl3501_release() will unregister the net device,
- * and release the PCMCIA configuration.  If the device is still open, this
- * will be postponed until it is closed.
- */
 static void wl3501_release(struct pcmcia_device *link)
 {
 	pcmcia_disable_device(link);
@@ -2056,9 +2019,7 @@
 
 static struct pcmcia_driver wl3501_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "wl3501_cs",
-	},
+	.name		= "wl3501_cs",
 	.probe		= wl3501_probe,
 	.remove		= wl3501_detach,
 	.id_table	= wl3501_ids,
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index b336cd9..f9bda64 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -225,26 +225,17 @@
 	mutex_unlock(&start_mutex);
 }
 
-int oprofile_set_backtrace(unsigned long val)
+int oprofile_set_ulong(unsigned long *addr, unsigned long val)
 {
-	int err = 0;
+	int err = -EBUSY;
 
 	mutex_lock(&start_mutex);
-
-	if (oprofile_started) {
-		err = -EBUSY;
-		goto out;
+	if (!oprofile_started) {
+		*addr = val;
+		err = 0;
 	}
-
-	if (!oprofile_ops.backtrace) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	oprofile_backtrace_depth = val;
-
-out:
 	mutex_unlock(&start_mutex);
+
 	return err;
 }
 
@@ -257,16 +248,9 @@
 		printk(KERN_INFO "oprofile: using timer interrupt.\n");
 		err = oprofile_timer_init(&oprofile_ops);
 		if (err)
-			goto out_arch;
+			return err;
 	}
-	err = oprofilefs_register();
-	if (err)
-		goto out_arch;
-	return 0;
-
-out_arch:
-	oprofile_arch_exit();
-	return err;
+	return oprofilefs_register();
 }
 
 
diff --git a/drivers/oprofile/oprof.h b/drivers/oprofile/oprof.h
index 47e12cb..177b73d 100644
--- a/drivers/oprofile/oprof.h
+++ b/drivers/oprofile/oprof.h
@@ -37,7 +37,7 @@
 int oprofile_timer_init(struct oprofile_operations *ops);
 void oprofile_timer_exit(void);
 
-int oprofile_set_backtrace(unsigned long depth);
+int oprofile_set_ulong(unsigned long *addr, unsigned long val);
 int oprofile_set_timeout(unsigned long time);
 
 #endif /* OPROF_H */
diff --git a/drivers/oprofile/oprofile_files.c b/drivers/oprofile/oprofile_files.c
index bbd7516..89f6345 100644
--- a/drivers/oprofile/oprofile_files.c
+++ b/drivers/oprofile/oprofile_files.c
@@ -59,6 +59,7 @@
 static const struct file_operations timeout_fops = {
 	.read		= timeout_read,
 	.write		= timeout_write,
+	.llseek		= default_llseek,
 };
 
 #endif
@@ -79,21 +80,25 @@
 	if (*offset)
 		return -EINVAL;
 
+	if (!oprofile_ops.backtrace)
+		return -EINVAL;
+
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
 	if (retval)
 		return retval;
 
-	retval = oprofile_set_backtrace(val);
-
+	retval = oprofile_set_ulong(&oprofile_backtrace_depth, val);
 	if (retval)
 		return retval;
+
 	return count;
 }
 
 
 static const struct file_operations depth_fops = {
 	.read		= depth_read,
-	.write		= depth_write
+	.write		= depth_write,
+	.llseek		= default_llseek,
 };
 
 
@@ -105,6 +110,7 @@
 
 static const struct file_operations pointer_size_fops = {
 	.read		= pointer_size_read,
+	.llseek		= default_llseek,
 };
 
 
@@ -116,6 +122,7 @@
 
 static const struct file_operations cpu_type_fops = {
 	.read		= cpu_type_read,
+	.llseek		= default_llseek,
 };
 
 
@@ -151,6 +158,7 @@
 static const struct file_operations enable_fops = {
 	.read		= enable_read,
 	.write		= enable_write,
+	.llseek		= default_llseek,
 };
 
 
@@ -163,6 +171,7 @@
 
 static const struct file_operations dump_fops = {
 	.write		= dump_write,
+	.llseek		= noop_llseek,
 };
 
 void oprofile_create_files(struct super_block *sb, struct dentry *root)
diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c
new file mode 100644
index 0000000..9046f7b
--- /dev/null
+++ b/drivers/oprofile/oprofile_perf.c
@@ -0,0 +1,328 @@
+/*
+ * Copyright 2010 ARM Ltd.
+ *
+ * Perf-events backend for OProfile.
+ */
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/oprofile.h>
+#include <linux/slab.h>
+
+/*
+ * Per performance monitor configuration as set via oprofilefs.
+ */
+struct op_counter_config {
+	unsigned long count;
+	unsigned long enabled;
+	unsigned long event;
+	unsigned long unit_mask;
+	unsigned long kernel;
+	unsigned long user;
+	struct perf_event_attr attr;
+};
+
+static int oprofile_perf_enabled;
+static DEFINE_MUTEX(oprofile_perf_mutex);
+
+static struct op_counter_config *counter_config;
+static struct perf_event **perf_events[nr_cpumask_bits];
+static int num_counters;
+
+/*
+ * Overflow callback for oprofile.
+ */
+static void op_overflow_handler(struct perf_event *event, int unused,
+			struct perf_sample_data *data, struct pt_regs *regs)
+{
+	int id;
+	u32 cpu = smp_processor_id();
+
+	for (id = 0; id < num_counters; ++id)
+		if (perf_events[cpu][id] == event)
+			break;
+
+	if (id != num_counters)
+		oprofile_add_sample(regs, id);
+	else
+		pr_warning("oprofile: ignoring spurious overflow "
+				"on cpu %u\n", cpu);
+}
+
+/*
+ * Called by oprofile_perf_setup to create perf attributes to mirror the oprofile
+ * settings in counter_config. Attributes are created as `pinned' events and
+ * so are permanently scheduled on the PMU.
+ */
+static void op_perf_setup(void)
+{
+	int i;
+	u32 size = sizeof(struct perf_event_attr);
+	struct perf_event_attr *attr;
+
+	for (i = 0; i < num_counters; ++i) {
+		attr = &counter_config[i].attr;
+		memset(attr, 0, size);
+		attr->type		= PERF_TYPE_RAW;
+		attr->size		= size;
+		attr->config		= counter_config[i].event;
+		attr->sample_period	= counter_config[i].count;
+		attr->pinned		= 1;
+	}
+}
+
+static int op_create_counter(int cpu, int event)
+{
+	struct perf_event *pevent;
+
+	if (!counter_config[event].enabled || perf_events[cpu][event])
+		return 0;
+
+	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
+						  cpu, NULL,
+						  op_overflow_handler);
+
+	if (IS_ERR(pevent))
+		return PTR_ERR(pevent);
+
+	if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		perf_event_release_kernel(pevent);
+		pr_warning("oprofile: failed to enable event %d "
+				"on CPU %d\n", event, cpu);
+		return -EBUSY;
+	}
+
+	perf_events[cpu][event] = pevent;
+
+	return 0;
+}
+
+static void op_destroy_counter(int cpu, int event)
+{
+	struct perf_event *pevent = perf_events[cpu][event];
+
+	if (pevent) {
+		perf_event_release_kernel(pevent);
+		perf_events[cpu][event] = NULL;
+	}
+}
+
+/*
+ * Called by oprofile_perf_start to create active perf events based on the
+ * perviously configured attributes.
+ */
+static int op_perf_start(void)
+{
+	int cpu, event, ret = 0;
+
+	for_each_online_cpu(cpu) {
+		for (event = 0; event < num_counters; ++event) {
+			ret = op_create_counter(cpu, event);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Called by oprofile_perf_stop at the end of a profiling run.
+ */
+static void op_perf_stop(void)
+{
+	int cpu, event;
+
+	for_each_online_cpu(cpu)
+		for (event = 0; event < num_counters; ++event)
+			op_destroy_counter(cpu, event);
+}
+
+static int oprofile_perf_create_files(struct super_block *sb, struct dentry *root)
+{
+	unsigned int i;
+
+	for (i = 0; i < num_counters; i++) {
+		struct dentry *dir;
+		char buf[4];
+
+		snprintf(buf, sizeof buf, "%d", i);
+		dir = oprofilefs_mkdir(sb, root, buf);
+		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
+		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
+		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
+		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
+		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
+		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+	}
+
+	return 0;
+}
+
+static int oprofile_perf_setup(void)
+{
+	spin_lock(&oprofilefs_lock);
+	op_perf_setup();
+	spin_unlock(&oprofilefs_lock);
+	return 0;
+}
+
+static int oprofile_perf_start(void)
+{
+	int ret = -EBUSY;
+
+	mutex_lock(&oprofile_perf_mutex);
+	if (!oprofile_perf_enabled) {
+		ret = 0;
+		op_perf_start();
+		oprofile_perf_enabled = 1;
+	}
+	mutex_unlock(&oprofile_perf_mutex);
+	return ret;
+}
+
+static void oprofile_perf_stop(void)
+{
+	mutex_lock(&oprofile_perf_mutex);
+	if (oprofile_perf_enabled)
+		op_perf_stop();
+	oprofile_perf_enabled = 0;
+	mutex_unlock(&oprofile_perf_mutex);
+}
+
+#ifdef CONFIG_PM
+
+static int oprofile_perf_suspend(struct platform_device *dev, pm_message_t state)
+{
+	mutex_lock(&oprofile_perf_mutex);
+	if (oprofile_perf_enabled)
+		op_perf_stop();
+	mutex_unlock(&oprofile_perf_mutex);
+	return 0;
+}
+
+static int oprofile_perf_resume(struct platform_device *dev)
+{
+	mutex_lock(&oprofile_perf_mutex);
+	if (oprofile_perf_enabled && op_perf_start())
+		oprofile_perf_enabled = 0;
+	mutex_unlock(&oprofile_perf_mutex);
+	return 0;
+}
+
+static struct platform_driver oprofile_driver = {
+	.driver		= {
+		.name		= "oprofile-perf",
+	},
+	.resume		= oprofile_perf_resume,
+	.suspend	= oprofile_perf_suspend,
+};
+
+static struct platform_device *oprofile_pdev;
+
+static int __init init_driverfs(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&oprofile_driver);
+	if (ret)
+		return ret;
+
+	oprofile_pdev =	platform_device_register_simple(
+				oprofile_driver.driver.name, 0, NULL, 0);
+	if (IS_ERR(oprofile_pdev)) {
+		ret = PTR_ERR(oprofile_pdev);
+		platform_driver_unregister(&oprofile_driver);
+	}
+
+	return ret;
+}
+
+static void exit_driverfs(void)
+{
+	platform_device_unregister(oprofile_pdev);
+	platform_driver_unregister(&oprofile_driver);
+}
+
+#else
+
+static inline int  init_driverfs(void) { return 0; }
+static inline void exit_driverfs(void) { }
+
+#endif /* CONFIG_PM */
+
+void oprofile_perf_exit(void)
+{
+	int cpu, id;
+	struct perf_event *event;
+
+	for_each_possible_cpu(cpu) {
+		for (id = 0; id < num_counters; ++id) {
+			event = perf_events[cpu][id];
+			if (event)
+				perf_event_release_kernel(event);
+		}
+
+		kfree(perf_events[cpu]);
+	}
+
+	kfree(counter_config);
+	exit_driverfs();
+}
+
+int __init oprofile_perf_init(struct oprofile_operations *ops)
+{
+	int cpu, ret = 0;
+
+	ret = init_driverfs();
+	if (ret)
+		return ret;
+
+	memset(&perf_events, 0, sizeof(perf_events));
+
+	num_counters = perf_num_counters();
+	if (num_counters <= 0) {
+		pr_info("oprofile: no performance counters\n");
+		ret = -ENODEV;
+		goto out;
+	}
+
+	counter_config = kcalloc(num_counters,
+			sizeof(struct op_counter_config), GFP_KERNEL);
+
+	if (!counter_config) {
+		pr_info("oprofile: failed to allocate %d "
+				"counters\n", num_counters);
+		ret = -ENOMEM;
+		num_counters = 0;
+		goto out;
+	}
+
+	for_each_possible_cpu(cpu) {
+		perf_events[cpu] = kcalloc(num_counters,
+				sizeof(struct perf_event *), GFP_KERNEL);
+		if (!perf_events[cpu]) {
+			pr_info("oprofile: failed to allocate %d perf events "
+					"for cpu %d\n", num_counters, cpu);
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+
+	ops->create_files	= oprofile_perf_create_files;
+	ops->setup		= oprofile_perf_setup;
+	ops->start		= oprofile_perf_start;
+	ops->stop		= oprofile_perf_stop;
+	ops->shutdown		= oprofile_perf_stop;
+	ops->cpu_type		= op_name_from_perf_id();
+
+	if (!ops->cpu_type)
+		ret = -ENODEV;
+	else
+		pr_info("oprofile: using %s\n", ops->cpu_type);
+
+out:
+	if (ret)
+		oprofile_perf_exit();
+
+	return ret;
+}
diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c
index 2766a6d..95f711b 100644
--- a/drivers/oprofile/oprofilefs.c
+++ b/drivers/oprofile/oprofilefs.c
@@ -91,16 +91,20 @@
 
 static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
 {
-	unsigned long *value = file->private_data;
+	unsigned long value;
 	int retval;
 
 	if (*offset)
 		return -EINVAL;
 
-	retval = oprofilefs_ulong_from_user(value, buf, count);
-
+	retval = oprofilefs_ulong_from_user(&value, buf, count);
 	if (retval)
 		return retval;
+
+	retval = oprofile_set_ulong(file->private_data, value);
+	if (retval)
+		return retval;
+
 	return count;
 }
 
@@ -117,59 +121,52 @@
 	.read		= ulong_read_file,
 	.write		= ulong_write_file,
 	.open		= default_open,
+	.llseek		= default_llseek,
 };
 
 
 static const struct file_operations ulong_ro_fops = {
 	.read		= ulong_read_file,
 	.open		= default_open,
+	.llseek		= default_llseek,
 };
 
 
-static struct dentry *__oprofilefs_create_file(struct super_block *sb,
+static int __oprofilefs_create_file(struct super_block *sb,
 	struct dentry *root, char const *name, const struct file_operations *fops,
-	int perm)
+	int perm, void *priv)
 {
 	struct dentry *dentry;
 	struct inode *inode;
 
 	dentry = d_alloc_name(root, name);
 	if (!dentry)
-		return NULL;
+		return -ENOMEM;
 	inode = oprofilefs_get_inode(sb, S_IFREG | perm);
 	if (!inode) {
 		dput(dentry);
-		return NULL;
+		return -ENOMEM;
 	}
 	inode->i_fop = fops;
 	d_add(dentry, inode);
-	return dentry;
+	dentry->d_inode->i_private = priv;
+	return 0;
 }
 
 
 int oprofilefs_create_ulong(struct super_block *sb, struct dentry *root,
 	char const *name, unsigned long *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
-						     &ulong_fops, 0644);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name,
+					&ulong_fops, 0644, val);
 }
 
 
 int oprofilefs_create_ro_ulong(struct super_block *sb, struct dentry *root,
 	char const *name, unsigned long *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
-						     &ulong_ro_fops, 0444);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name,
+					&ulong_ro_fops, 0444, val);
 }
 
 
@@ -183,37 +180,29 @@
 static const struct file_operations atomic_ro_fops = {
 	.read		= atomic_read_file,
 	.open		= default_open,
+	.llseek		= default_llseek,
 };
 
 
 int oprofilefs_create_ro_atomic(struct super_block *sb, struct dentry *root,
 	char const *name, atomic_t *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
-						     &atomic_ro_fops, 0444);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name,
+					&atomic_ro_fops, 0444, val);
 }
 
 
 int oprofilefs_create_file(struct super_block *sb, struct dentry *root,
 	char const *name, const struct file_operations *fops)
 {
-	if (!__oprofilefs_create_file(sb, root, name, fops, 0644))
-		return -EFAULT;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name, fops, 0644, NULL);
 }
 
 
 int oprofilefs_create_file_perm(struct super_block *sb, struct dentry *root,
 	char const *name, const struct file_operations *fops, int perm)
 {
-	if (!__oprofilefs_create_file(sb, root, name, fops, perm))
-		return -EFAULT;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name, fops, perm, NULL);
 }
 
 
diff --git a/drivers/parport/parport_cs.c b/drivers/parport/parport_cs.c
index 23e50f4..787ebde 100644
--- a/drivers/parport/parport_cs.c
+++ b/drivers/parport/parport_cs.c
@@ -48,7 +48,6 @@
 #include <linux/parport.h>
 #include <linux/parport_pc.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 #include <pcmcia/cisreg.h>
@@ -81,14 +80,6 @@
 static int parport_config(struct pcmcia_device *link);
 static void parport_cs_release(struct pcmcia_device *);
 
-/*======================================================================
-
-    parport_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-======================================================================*/
-
 static int parport_probe(struct pcmcia_device *link)
 {
     parport_info_t *info;
@@ -101,23 +92,11 @@
     link->priv = info;
     info->p_dev = link;
 
-    link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-    link->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
 
     return parport_config(link);
 } /* parport_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void parport_detach(struct pcmcia_device *link)
 {
     dev_dbg(&link->dev, "parport_detach\n");
@@ -127,36 +106,14 @@
     kfree(link->priv);
 } /* parport_detach */
 
-/*======================================================================
-
-    parport_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    parport device available to the system.
-
-======================================================================*/
-
-static int parport_config_check(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
-				void *priv_data)
+static int parport_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		if (epp_mode)
-			p_dev->conf.ConfigIndex |= FORCE_EPP_MODE;
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin == 2) {
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-		if (pcmcia_request_io(p_dev) != 0)
-			return -ENODEV;
-		return 0;
-	}
-	return -ENODEV;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->resource[1]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
+
+	return pcmcia_request_io(p_dev);
 }
 
 static int parport_config(struct pcmcia_device *link)
@@ -167,13 +124,16 @@
 
     dev_dbg(&link->dev, "parport_config\n");
 
+    if (epp_mode)
+	    link->config_index |= FORCE_EPP_MODE;
+
     ret = pcmcia_loop_config(link, parport_config_check, NULL);
     if (ret)
 	    goto failed;
 
     if (!link->irq)
 	    goto failed;
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
@@ -202,14 +162,6 @@
     return -ENODEV;
 } /* parport_config */
 
-/*======================================================================
-
-    After a card is removed, parport_cs_release() will unregister the
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-    
-======================================================================*/
-
 static void parport_cs_release(struct pcmcia_device *link)
 {
 	parport_info_t *info = link->priv;
@@ -236,9 +188,7 @@
 
 static struct pcmcia_driver parport_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "parport_cs",
-	},
+	.name		= "parport_cs",
 	.probe		= parport_probe,
 	.remove		= parport_detach,
 	.id_table	= parport_ids,
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index dffa5d4..a2d9d1e 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -306,7 +306,7 @@
 	spin_lock_init(&tmp->pardevice_lock);
 	tmp->ieee1284.mode = IEEE1284_MODE_COMPAT;
 	tmp->ieee1284.phase = IEEE1284_PH_FWD_IDLE;
-	init_MUTEX_LOCKED (&tmp->ieee1284.irq); /* actually a semaphore at 0 */
+	sema_init(&tmp->ieee1284.irq, 0);
 	tmp->spintime = parport_default_spintime;
 	atomic_set (&tmp->ref_count, 1);
 	INIT_LIST_HEAD(&tmp->full_list);
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 0a19708..0157708 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -36,6 +36,7 @@
 #include <linux/tboot.h>
 #include <linux/dmi.h>
 #include <linux/slab.h>
+#include <asm/iommu_table.h>
 
 #define PREFIX "DMAR: "
 
@@ -687,7 +688,7 @@
 	return 0;
 }
 
-void __init detect_intel_iommu(void)
+int __init detect_intel_iommu(void)
 {
 	int ret;
 
@@ -723,6 +724,8 @@
 	}
 	early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
+
+	return ret ? 1 : -ENODEV;
 }
 
 
@@ -1221,9 +1224,9 @@
 	}
 }
 
-void dmar_msi_unmask(unsigned int irq)
+void dmar_msi_unmask(struct irq_data *data)
 {
-	struct intel_iommu *iommu = get_irq_data(irq);
+	struct intel_iommu *iommu = irq_data_get_irq_data(data);
 	unsigned long flag;
 
 	/* unmask it */
@@ -1234,10 +1237,10 @@
 	spin_unlock_irqrestore(&iommu->register_lock, flag);
 }
 
-void dmar_msi_mask(unsigned int irq)
+void dmar_msi_mask(struct irq_data *data)
 {
 	unsigned long flag;
-	struct intel_iommu *iommu = get_irq_data(irq);
+	struct intel_iommu *iommu = irq_data_get_irq_data(data);
 
 	/* mask it */
 	spin_lock_irqsave(&iommu->register_lock, flag);
@@ -1455,3 +1458,4 @@
 		return 0;
 	return dmar->flags & 0x1;
 }
+IOMMU_INIT_POST(detect_intel_iommu);
diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c
index 5621532..4cb3044 100644
--- a/drivers/pci/hotplug/cpqphp_sysfs.c
+++ b/drivers/pci/hotplug/cpqphp_sysfs.c
@@ -34,10 +34,11 @@
 #include <linux/workqueue.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/debugfs.h>
 #include "cpqphp.h"
 
+static DEFINE_MUTEX(cpqphp_mutex);
 static int show_ctrl (struct controller *ctrl, char *buf)
 {
 	char *out = buf;
@@ -147,7 +148,7 @@
 	struct ctrl_dbg *dbg;
 	int retval = -ENOMEM;
 
-	lock_kernel();
+	mutex_lock(&cpqphp_mutex);
 	dbg = kmalloc(sizeof(*dbg), GFP_KERNEL);
 	if (!dbg)
 		goto exit;
@@ -160,7 +161,7 @@
 	file->private_data = dbg;
 	retval = 0;
 exit:
-	unlock_kernel();
+	mutex_unlock(&cpqphp_mutex);
 	return retval;
 }
 
@@ -169,7 +170,7 @@
 	struct ctrl_dbg *dbg;
 	loff_t new = -1;
 
-	lock_kernel();
+	mutex_lock(&cpqphp_mutex);
 	dbg = file->private_data;
 
 	switch (whence) {
@@ -181,10 +182,10 @@
 		break;
 	}
 	if (new < 0 || new > dbg->size) {
-		unlock_kernel();
+		mutex_unlock(&cpqphp_mutex);
 		return -EINVAL;
 	}
-	unlock_kernel();
+	mutex_unlock(&cpqphp_mutex);
 	return (file->f_pos = new);
 }
 
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 73d5139..838f571 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -36,6 +36,7 @@
 #include <linux/sched.h>		/* signal_pending() */
 #include <linux/pcieport_if.h>
 #include <linux/mutex.h>
+#include <linux/workqueue.h>
 
 #define MY_NAME	"pciehp"
 
@@ -44,6 +45,7 @@
 extern int pciehp_debug;
 extern int pciehp_force;
 extern struct workqueue_struct *pciehp_wq;
+extern struct workqueue_struct *pciehp_ordered_wq;
 
 #define dbg(format, arg...)						\
 do {									\
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index aa5f3ff..7ac8358 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -43,6 +43,7 @@
 int pciehp_poll_time;
 int pciehp_force;
 struct workqueue_struct *pciehp_wq;
+struct workqueue_struct *pciehp_ordered_wq;
 
 #define DRIVER_VERSION	"0.4"
 #define DRIVER_AUTHOR	"Dan Zink <dan.zink@compaq.com>, Greg Kroah-Hartman <greg@kroah.com>, Dely Sy <dely.l.sy@intel.com>"
@@ -340,18 +341,33 @@
 {
 	int retval = 0;
 
+	pciehp_wq = alloc_workqueue("pciehp", 0, 0);
+	if (!pciehp_wq)
+		return -ENOMEM;
+
+	pciehp_ordered_wq = alloc_ordered_workqueue("pciehp_ordered", 0);
+	if (!pciehp_ordered_wq) {
+		destroy_workqueue(pciehp_wq);
+		return -ENOMEM;
+	}
+
 	pciehp_firmware_init();
 	retval = pcie_port_service_register(&hpdriver_portdrv);
  	dbg("pcie_port_service_register = %d\n", retval);
   	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
- 	if (retval)
+ 	if (retval) {
+		destroy_workqueue(pciehp_ordered_wq);
+		destroy_workqueue(pciehp_wq);
 		dbg("Failure to register service\n");
+	}
 	return retval;
 }
 
 static void __exit pcied_cleanup(void)
 {
 	dbg("unload_pciehpd()\n");
+	destroy_workqueue(pciehp_ordered_wq);
+	destroy_workqueue(pciehp_wq);
 	pcie_port_service_unregister(&hpdriver_portdrv);
 	info(DRIVER_DESC " version: " DRIVER_VERSION " unloaded\n");
 }
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 8f58148..085dbb5 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -32,7 +32,6 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
-#include <linux/workqueue.h>
 #include "../pci.h"
 #include "pciehp.h"
 
@@ -50,7 +49,7 @@
 	info->p_slot = p_slot;
 	INIT_WORK(&info->work, interrupt_event_handler);
 
-	schedule_work(&info->work);
+	queue_work(pciehp_wq, &info->work);
 
 	return 0;
 }
@@ -345,7 +344,7 @@
 		kfree(info);
 		goto out;
 	}
-	queue_work(pciehp_wq, &info->work);
+	queue_work(pciehp_ordered_wq, &info->work);
  out:
 	mutex_unlock(&p_slot->lock);
 }
@@ -378,7 +377,7 @@
 		if (ATTN_LED(ctrl))
 			pciehp_set_attention_status(p_slot, 0);
 
-		schedule_delayed_work(&p_slot->work, 5*HZ);
+		queue_delayed_work(pciehp_wq, &p_slot->work, 5*HZ);
 		break;
 	case BLINKINGOFF_STATE:
 	case BLINKINGON_STATE:
@@ -440,7 +439,7 @@
 	else
 		p_slot->state = POWERON_STATE;
 
-	queue_work(pciehp_wq, &info->work);
+	queue_work(pciehp_ordered_wq, &info->work);
 }
 
 static void interrupt_event_handler(struct work_struct *work)
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 0cd4204..50a23da 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -41,8 +41,6 @@
 #include "../pci.h"
 #include "pciehp.h"
 
-static atomic_t pciehp_num_controllers = ATOMIC_INIT(0);
-
 static inline int pciehp_readw(struct controller *ctrl, int reg, u16 *value)
 {
 	struct pci_dev *dev = ctrl->pcie->port;
@@ -805,8 +803,8 @@
 {
 	struct slot *slot = ctrl->slot;
 	cancel_delayed_work(&slot->work);
-	flush_scheduled_work();
 	flush_workqueue(pciehp_wq);
+	flush_workqueue(pciehp_ordered_wq);
 	kfree(slot);
 }
 
@@ -912,16 +910,6 @@
 	/* Disable sotfware notification */
 	pcie_disable_notification(ctrl);
 
-	/*
-	 * If this is the first controller to be initialized,
-	 * initialize the pciehp work queue
-	 */
-	if (atomic_add_return(1, &pciehp_num_controllers) == 1) {
-		pciehp_wq = create_singlethread_workqueue("pciehpd");
-		if (!pciehp_wq)
-			goto abort_ctrl;
-	}
-
 	ctrl_info(ctrl, "HPC vendor_id %x device_id %x ss_vid %x ss_did %x\n",
 		  pdev->vendor, pdev->device, pdev->subsystem_vendor,
 		  pdev->subsystem_device);
@@ -941,11 +929,5 @@
 {
 	pcie_shutdown_notification(ctrl);
 	pcie_cleanup_slot(ctrl);
-	/*
-	 * If this is the last controller to be released, destroy the
-	 * pciehp work queue
-	 */
-	if (atomic_dec_and_test(&pciehp_num_controllers))
-		destroy_workqueue(pciehp_wq);
 	kfree(ctrl);
 }
diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h
index d2627e1..e0c90e6 100644
--- a/drivers/pci/hotplug/shpchp.h
+++ b/drivers/pci/hotplug/shpchp.h
@@ -35,6 +35,7 @@
 #include <linux/delay.h>
 #include <linux/sched.h>	/* signal_pending(), struct timer_list */
 #include <linux/mutex.h>
+#include <linux/workqueue.h>
 
 #if !defined(MODULE)
 	#define MY_NAME	"shpchp"
@@ -46,6 +47,7 @@
 extern int shpchp_poll_time;
 extern int shpchp_debug;
 extern struct workqueue_struct *shpchp_wq;
+extern struct workqueue_struct *shpchp_ordered_wq;
 
 #define dbg(format, arg...)						\
 do {									\
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index a7bd504..aca972b 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -33,7 +33,6 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
-#include <linux/workqueue.h>
 #include "shpchp.h"
 
 /* Global variables */
@@ -41,6 +40,7 @@
 int shpchp_poll_mode;
 int shpchp_poll_time;
 struct workqueue_struct *shpchp_wq;
+struct workqueue_struct *shpchp_ordered_wq;
 
 #define DRIVER_VERSION	"0.4"
 #define DRIVER_AUTHOR	"Dan Zink <dan.zink@compaq.com>, Greg Kroah-Hartman <greg@kroah.com>, Dely Sy <dely.l.sy@intel.com>"
@@ -174,8 +174,8 @@
 		slot = list_entry(tmp, struct slot, slot_list);
 		list_del(&slot->slot_list);
 		cancel_delayed_work(&slot->work);
-		flush_scheduled_work();
 		flush_workqueue(shpchp_wq);
+		flush_workqueue(shpchp_ordered_wq);
 		pci_hp_deregister(slot->hotplug_slot);
 	}
 }
@@ -360,9 +360,23 @@
 {
 	int retval = 0;
 
+	shpchp_wq = alloc_ordered_workqueue("shpchp", 0);
+	if (!shpchp_wq)
+		return -ENOMEM;
+
+	shpchp_ordered_wq = alloc_ordered_workqueue("shpchp_ordered", 0);
+	if (!shpchp_ordered_wq) {
+		destroy_workqueue(shpchp_wq);
+		return -ENOMEM;
+	}
+
 	retval = pci_register_driver(&shpc_driver);
 	dbg("%s: pci_register_driver = %d\n", __func__, retval);
 	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+	if (retval) {
+		destroy_workqueue(shpchp_ordered_wq);
+		destroy_workqueue(shpchp_wq);
+	}
 	return retval;
 }
 
@@ -370,6 +384,8 @@
 {
 	dbg("unload_shpchpd()\n");
 	pci_unregister_driver(&shpc_driver);
+	destroy_workqueue(shpchp_ordered_wq);
+	destroy_workqueue(shpchp_wq);
 	info(DRIVER_DESC " version: " DRIVER_VERSION " unloaded\n");
 }
 
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index 3387fbf..b00b09b 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -32,7 +32,6 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
-#include <linux/workqueue.h>
 #include "../pci.h"
 #include "shpchp.h"
 
@@ -52,7 +51,7 @@
 	info->p_slot = p_slot;
 	INIT_WORK(&info->work, interrupt_event_handler);
 
-	schedule_work(&info->work);
+	queue_work(shpchp_wq, &info->work);
 
 	return 0;
 }
@@ -457,7 +456,7 @@
 		kfree(info);
 		goto out;
 	}
-	queue_work(shpchp_wq, &info->work);
+	queue_work(shpchp_ordered_wq, &info->work);
  out:
 	mutex_unlock(&p_slot->lock);
 }
@@ -505,7 +504,7 @@
 		p_slot->hpc_ops->green_led_blink(p_slot);
 		p_slot->hpc_ops->set_attention_status(p_slot, 0);
 
-		schedule_delayed_work(&p_slot->work, 5*HZ);
+		queue_delayed_work(shpchp_wq, &p_slot->work, 5*HZ);
 		break;
 	case BLINKINGOFF_STATE:
 	case BLINKINGON_STATE:
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index d3985e7..36547f0 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -179,8 +179,6 @@
 #define SLOT_EVENT_LATCH	0x2
 #define SLOT_SERR_INT_MASK	0x3
 
-static atomic_t shpchp_num_controllers = ATOMIC_INIT(0);
-
 static irqreturn_t shpc_isr(int irq, void *dev_id);
 static void start_int_poll_timer(struct controller *ctrl, int sec);
 static int hpc_check_cmd_status(struct controller *ctrl);
@@ -614,13 +612,6 @@
 
 	iounmap(ctrl->creg);
 	release_mem_region(ctrl->mmio_base, ctrl->mmio_size);
-
-	/*
-	 * If this is the last controller to be released, destroy the
-	 * shpchpd work queue
-	 */
-	if (atomic_dec_and_test(&shpchp_num_controllers))
-		destroy_workqueue(shpchp_wq);
 }
 
 static int hpc_power_on_slot(struct slot * slot)
@@ -1077,9 +1068,8 @@
 
 		rc = request_irq(ctrl->pci_dev->irq, shpc_isr, IRQF_SHARED,
 				 MY_NAME, (void *)ctrl);
-		ctrl_dbg(ctrl, "request_irq %d for hpc%d (returns %d)\n",
-			 ctrl->pci_dev->irq,
-		    atomic_read(&shpchp_num_controllers), rc);
+		ctrl_dbg(ctrl, "request_irq %d (returns %d)\n",
+			 ctrl->pci_dev->irq, rc);
 		if (rc) {
 			ctrl_err(ctrl, "Can't get irq %d for the hotplug "
 				 "controller\n", ctrl->pci_dev->irq);
@@ -1092,18 +1082,6 @@
 	shpc_get_cur_bus_speed(ctrl);
 
 	/*
-	 * If this is the first controller to be initialized,
-	 * initialize the shpchpd work queue
-	 */
-	if (atomic_add_return(1, &shpchp_num_controllers) == 1) {
-		shpchp_wq = create_singlethread_workqueue("shpchpd");
-		if (!shpchp_wq) {
-			rc = -ENOMEM;
-			goto abort_iounmap;
-		}
-	}
-
-	/*
 	 * Unmask all event interrupts of all slots
 	 */
 	for (hp_slot = 0; hp_slot < ctrl->num_slots; hp_slot++) {
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index 98abf8b..834842a 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -57,28 +57,22 @@
 	*msg = cfg->msg;
 }
 
-void mask_ht_irq(unsigned int irq)
+void mask_ht_irq(struct irq_data *data)
 {
-	struct ht_irq_cfg *cfg;
-	struct ht_irq_msg msg;
+	struct ht_irq_cfg *cfg = irq_data_get_irq_data(data);
+	struct ht_irq_msg msg = cfg->msg;
 
-	cfg = get_irq_data(irq);
-
-	msg = cfg->msg;
 	msg.address_lo |= 1;
-	write_ht_irq_msg(irq, &msg);
+	write_ht_irq_msg(data->irq, &msg);
 }
 
-void unmask_ht_irq(unsigned int irq)
+void unmask_ht_irq(struct irq_data *data)
 {
-	struct ht_irq_cfg *cfg;
-	struct ht_irq_msg msg;
+	struct ht_irq_cfg *cfg = irq_data_get_irq_data(data);
+	struct ht_irq_msg msg = cfg->msg;
 
-	cfg = get_irq_data(irq);
-
-	msg = cfg->msg;
 	msg.address_lo &= ~1;
-	write_ht_irq_msg(irq, &msg);
+	write_ht_irq_msg(data->irq, &msg);
 }
 
 /**
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index fd1d286..ec87cd6 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -46,109 +46,24 @@
 }
 early_param("intremap", setup_intremap);
 
-struct irq_2_iommu {
-	struct intel_iommu *iommu;
-	u16 irte_index;
-	u16 sub_handle;
-	u8  irte_mask;
-};
-
-#ifdef CONFIG_GENERIC_HARDIRQS
-static struct irq_2_iommu *get_one_free_irq_2_iommu(int node)
-{
-	struct irq_2_iommu *iommu;
-
-	iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, node);
-	printk(KERN_DEBUG "alloc irq_2_iommu on node %d\n", node);
-
-	return iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	if (WARN_ON_ONCE(!desc))
-		return NULL;
-
-	return desc->irq_2_iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
-{
-	struct irq_desc *desc;
-	struct irq_2_iommu *irq_iommu;
-
-	desc = irq_to_desc(irq);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc for %d\n", irq);
-		return NULL;
-	}
-
-	irq_iommu = desc->irq_2_iommu;
-
-	if (!irq_iommu)
-		desc->irq_2_iommu = get_one_free_irq_2_iommu(irq_node(irq));
-
-	return desc->irq_2_iommu;
-}
-
-#else /* !CONFIG_SPARSE_IRQ */
-
-static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-	if (irq < nr_irqs)
-		return &irq_2_iommuX[irq];
-
-	return NULL;
-}
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
-{
-	return irq_2_iommu(irq);
-}
-#endif
-
 static DEFINE_SPINLOCK(irq_2_ir_lock);
 
-static struct irq_2_iommu *valid_irq_2_iommu(unsigned int irq)
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
 {
-	struct irq_2_iommu *irq_iommu;
-
-	irq_iommu = irq_2_iommu(irq);
-
-	if (!irq_iommu)
-		return NULL;
-
-	if (!irq_iommu->iommu)
-		return NULL;
-
-	return irq_iommu;
-}
-
-int irq_remapped(int irq)
-{
-	return valid_irq_2_iommu(irq) != NULL;
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
+	return cfg ? &cfg->irq_2_iommu : NULL;
 }
 
 int get_irte(int irq, struct irte *entry)
 {
-	int index;
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
+	int index;
 
-	if (!entry)
+	if (!entry || !irq_iommu)
 		return -1;
 
 	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
 
 	index = irq_iommu->irte_index + irq_iommu->sub_handle;
 	*entry = *(irq_iommu->iommu->ir_table->base + index);
@@ -160,21 +75,15 @@
 int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 {
 	struct ir_table *table = iommu->ir_table;
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	u16 index, start_index;
 	unsigned int mask = 0;
 	unsigned long flags;
 	int i;
 
-	if (!count)
+	if (!count || !irq_iommu)
 		return -1;
 
-#ifndef CONFIG_SPARSE_IRQ
-	/* protect irq_2_iommu_alloc later */
-	if (irq >= nr_irqs)
-		return -1;
-#endif
-
 	/*
 	 * start the IRTE search from index 0.
 	 */
@@ -214,13 +123,6 @@
 	for (i = index; i < index + count; i++)
 		table->base[i].present = 1;
 
-	irq_iommu = irq_2_iommu_alloc(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		printk(KERN_ERR "can't allocate irq_2_iommu\n");
-		return -1;
-	}
-
 	irq_iommu->iommu = iommu;
 	irq_iommu->irte_index =  index;
 	irq_iommu->sub_handle = 0;
@@ -244,17 +146,14 @@
 
 int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 {
-	int index;
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
+	int index;
+
+	if (!irq_iommu)
+		return -1;
 
 	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
-
 	*sub_handle = irq_iommu->sub_handle;
 	index = irq_iommu->irte_index;
 	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
@@ -263,18 +162,13 @@
 
 int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 {
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
 
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-	irq_iommu = irq_2_iommu_alloc(irq);
-
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		printk(KERN_ERR "can't allocate irq_2_iommu\n");
+	if (!irq_iommu)
 		return -1;
-	}
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 
 	irq_iommu->iommu = iommu;
 	irq_iommu->irte_index = index;
@@ -286,43 +180,18 @@
 	return 0;
 }
 
-int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
-{
-	struct irq_2_iommu *irq_iommu;
-	unsigned long flags;
-
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
-
-	irq_iommu->iommu = NULL;
-	irq_iommu->irte_index = 0;
-	irq_iommu->sub_handle = 0;
-	irq_2_iommu(irq)->irte_mask = 0;
-
-	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-	return 0;
-}
-
 int modify_irte(int irq, struct irte *irte_modified)
 {
-	int rc;
-	int index;
-	struct irte *irte;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	struct intel_iommu *iommu;
-	struct irq_2_iommu *irq_iommu;
 	unsigned long flags;
+	struct irte *irte;
+	int rc, index;
+
+	if (!irq_iommu)
+		return -1;
 
 	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
 
 	iommu = irq_iommu->iommu;
 
@@ -339,31 +208,6 @@
 	return rc;
 }
 
-int flush_irte(int irq)
-{
-	int rc;
-	int index;
-	struct intel_iommu *iommu;
-	struct irq_2_iommu *irq_iommu;
-	unsigned long flags;
-
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
-
-	iommu = irq_iommu->iommu;
-
-	index = irq_iommu->irte_index + irq_iommu->sub_handle;
-
-	rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask);
-	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-	return rc;
-}
-
 struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
 {
 	int i;
@@ -420,16 +264,14 @@
 
 int free_irte(int irq)
 {
-	int rc = 0;
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
+	int rc;
+
+	if (!irq_iommu)
+		return -1;
 
 	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
 
 	rc = clear_entries(irq_iommu);
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 69b7be3..5fcf5ae 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -170,33 +170,31 @@
 	desc->masked = __msix_mask_irq(desc, flag);
 }
 
-static void msi_set_mask_bit(unsigned irq, u32 flag)
+static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 {
-	struct msi_desc *desc = get_irq_msi(irq);
+	struct msi_desc *desc = irq_data_get_msi(data);
 
 	if (desc->msi_attrib.is_msix) {
 		msix_mask_irq(desc, flag);
 		readl(desc->mask_base);		/* Flush write to device */
 	} else {
-		unsigned offset = irq - desc->dev->irq;
+		unsigned offset = data->irq - desc->dev->irq;
 		msi_mask_irq(desc, 1 << offset, flag << offset);
 	}
 }
 
-void mask_msi_irq(unsigned int irq)
+void mask_msi_irq(struct irq_data *data)
 {
-	msi_set_mask_bit(irq, 1);
+	msi_set_mask_bit(data, 1);
 }
 
-void unmask_msi_irq(unsigned int irq)
+void unmask_msi_irq(struct irq_data *data)
 {
-	msi_set_mask_bit(irq, 0);
+	msi_set_mask_bit(data, 0);
 }
 
-void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-	struct msi_desc *entry = get_irq_desc_msi(desc);
-
 	BUG_ON(entry->dev->current_state != PCI_D0);
 
 	if (entry->msi_attrib.is_msix) {
@@ -227,15 +225,13 @@
 
 void read_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct msi_desc *entry = get_irq_msi(irq);
 
-	read_msi_msg_desc(desc, msg);
+	__read_msi_msg(entry, msg);
 }
 
-void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-	struct msi_desc *entry = get_irq_desc_msi(desc);
-
 	/* Assert that the cache is valid, assuming that
 	 * valid messages are not all-zeroes. */
 	BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo |
@@ -246,15 +242,13 @@
 
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct msi_desc *entry = get_irq_msi(irq);
 
-	get_cached_msi_msg_desc(desc, msg);
+	__get_cached_msi_msg(entry, msg);
 }
 
-void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-	struct msi_desc *entry = get_irq_desc_msi(desc);
-
 	if (entry->dev->current_state != PCI_D0) {
 		/* Don't touch the hardware now */
 	} else if (entry->msi_attrib.is_msix) {
@@ -292,9 +286,9 @@
 
 void write_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct msi_desc *entry = get_irq_msi(irq);
 
-	write_msi_msg_desc(desc, msg);
+	__write_msi_msg(entry, msg);
 }
 
 static void free_msi_irqs(struct pci_dev *dev)
diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
index 9099246..b3cf622 100644
--- a/drivers/pci/pcie/aer/aer_inject.c
+++ b/drivers/pci/pcie/aer/aer_inject.c
@@ -472,6 +472,7 @@
 static const struct file_operations aer_inject_fops = {
 	.write = aer_inject_write,
 	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice aer_inject_device = {
diff --git a/drivers/pcmcia/au1000_generic.c b/drivers/pcmcia/au1000_generic.c
index 88c4c40..95dd7c6 100644
--- a/drivers/pcmcia/au1000_generic.c
+++ b/drivers/pcmcia/au1000_generic.c
@@ -441,14 +441,12 @@
 
 
 out_err:
-	flush_scheduled_work();
 	ops->hw_shutdown(skt);
 	while (i-- > 0) {
 		skt = PCMCIA_SOCKET(i);
 
 		del_timer_sync(&skt->poll_timer);
 		pcmcia_unregister_socket(&skt->socket);
-		flush_scheduled_work();
 		if (i == 0) {
 			iounmap(skt->virt_io + (u32)mips_io_port_base);
 			skt->virt_io = NULL;
@@ -480,7 +478,6 @@
 
 		del_timer_sync(&skt->poll_timer);
 		pcmcia_unregister_socket(&skt->socket);
-		flush_scheduled_work();
 		skt->ops->hw_shutdown(skt);
 		au1x00_pcmcia_config_skt(skt, &dead_socket);
 		iounmap(skt->virt_io + (u32)mips_io_port_base);
diff --git a/drivers/pcmcia/au1000_generic.h b/drivers/pcmcia/au1000_generic.h
index 67530ce..5c36bda 100644
--- a/drivers/pcmcia/au1000_generic.h
+++ b/drivers/pcmcia/au1000_generic.h
@@ -23,7 +23,6 @@
 
 /* include the world */
 
-#include <pcmcia/cs.h>
 #include <pcmcia/ss.h>
 #include <pcmcia/cistpl.h>
 #include "cs_internal.h"
diff --git a/drivers/pcmcia/au1000_pb1x00.c b/drivers/pcmcia/au1000_pb1x00.c
index 807f2d7..b239664 100644
--- a/drivers/pcmcia/au1000_pb1x00.c
+++ b/drivers/pcmcia/au1000_pb1x00.c
@@ -31,7 +31,6 @@
 #include <linux/proc_fs.h>
 #include <linux/types.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/ss.h>
 #include <pcmcia/cistpl.h>
 
diff --git a/drivers/pcmcia/cistpl.c b/drivers/pcmcia/cistpl.c
index 91414a0..884a984 100644
--- a/drivers/pcmcia/cistpl.c
+++ b/drivers/pcmcia/cistpl.c
@@ -28,7 +28,6 @@
 #include <asm/unaligned.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/cistpl.h>
 #include "cs_internal.h"
diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c
index 2ec8ac9..d9ea192 100644
--- a/drivers/pcmcia/cs.c
+++ b/drivers/pcmcia/cs.c
@@ -33,7 +33,6 @@
 #include <asm/irq.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -845,7 +844,7 @@
 	return __pcmcia_pm_op(dev, socket_early_resume);
 }
 
-static int pcmcia_socket_dev_resume(struct device *dev)
+static int __used pcmcia_socket_dev_resume(struct device *dev)
 {
 	return __pcmcia_pm_op(dev, socket_late_resume);
 }
diff --git a/drivers/pcmcia/cs_internal.h b/drivers/pcmcia/cs_internal.h
index da055dc..7f1953f 100644
--- a/drivers/pcmcia/cs_internal.h
+++ b/drivers/pcmcia/cs_internal.h
@@ -33,18 +33,9 @@
 typedef struct config_t {
 	struct kref	ref;
 	unsigned int	state;
-	unsigned int	Attributes;
-	unsigned int	IntType;
-	unsigned int	ConfigBase;
-	unsigned char	Status, Pin, Copy, Option, ExtStatus;
-	unsigned int	CardValues;
 
 	struct resource io[MAX_IO_WIN]; /* io ports */
 	struct resource mem[MAX_WIN];   /* mem areas */
-
-	struct {
-		u_int	Attributes;
-	} irq;
 } config_t;
 
 
diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index 55570d9..100c441 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -26,7 +26,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 #include <pcmcia/ss.h>
@@ -52,7 +51,7 @@
 
 	if (!p_drv->probe || !p_drv->remove)
 		printk(KERN_DEBUG "pcmcia: %s lacks a requisite callback "
-		       "function\n", p_drv->drv.name);
+		       "function\n", p_drv->name);
 
 	while (did && did->match_flags) {
 		for (i = 0; i < 4; i++) {
@@ -65,7 +64,7 @@
 
 			printk(KERN_DEBUG "pcmcia: %s: invalid hash for "
 			       "product string \"%s\": is 0x%x, should "
-			       "be 0x%x\n", p_drv->drv.name, did->prod_id[i],
+			       "be 0x%x\n", p_drv->name, did->prod_id[i],
 			       did->prod_id_hash[i], hash);
 			printk(KERN_DEBUG "pcmcia: see "
 				"Documentation/pcmcia/devicetable.txt for "
@@ -180,10 +179,11 @@
 	/* initialize common fields */
 	driver->drv.bus = &pcmcia_bus_type;
 	driver->drv.owner = driver->owner;
+	driver->drv.name = driver->name;
 	mutex_init(&driver->dynids.lock);
 	INIT_LIST_HEAD(&driver->dynids.list);
 
-	pr_debug("registering driver %s\n", driver->drv.name);
+	pr_debug("registering driver %s\n", driver->name);
 
 	error = driver_register(&driver->drv);
 	if (error < 0)
@@ -203,7 +203,7 @@
  */
 void pcmcia_unregister_driver(struct pcmcia_driver *driver)
 {
-	pr_debug("unregistering driver %s\n", driver->drv.name);
+	pr_debug("unregistering driver %s\n", driver->name);
 	driver_unregister(&driver->drv);
 	pcmcia_free_dynids(driver);
 }
@@ -264,7 +264,7 @@
 	p_drv = to_pcmcia_drv(dev->driver);
 	s = p_dev->socket;
 
-	dev_dbg(dev, "trying to bind to %s\n", p_drv->drv.name);
+	dev_dbg(dev, "trying to bind to %s\n", p_drv->name);
 
 	if ((!p_drv->probe) || (!p_dev->function_config) ||
 	    (!try_module_get(p_drv->owner))) {
@@ -276,21 +276,28 @@
 	ret = pccard_read_tuple(p_dev->socket, p_dev->func, CISTPL_CONFIG,
 				&cis_config);
 	if (!ret) {
-		p_dev->conf.ConfigBase = cis_config.base;
-		p_dev->conf.Present = cis_config.rmask[0];
+		p_dev->config_base = cis_config.base;
+		p_dev->config_regs = cis_config.rmask[0];
+		dev_dbg(dev, "base %x, regs %x", p_dev->config_base,
+			p_dev->config_regs);
 	} else {
 		dev_printk(KERN_INFO, dev,
 			   "pcmcia: could not parse base and rmask0 of CIS\n");
-		p_dev->conf.ConfigBase = 0;
-		p_dev->conf.Present = 0;
+		p_dev->config_base = 0;
+		p_dev->config_regs = 0;
 	}
 
 	ret = p_drv->probe(p_dev);
 	if (ret) {
 		dev_dbg(dev, "binding to %s failed with %d\n",
-			   p_drv->drv.name, ret);
+			   p_drv->name, ret);
 		goto put_module;
 	}
+	dev_dbg(dev, "%s bound: Vpp %d.%d, idx %x, IRQ %d", p_drv->name,
+		p_dev->vpp/10, p_dev->vpp%10, p_dev->config_index, p_dev->irq);
+	dev_dbg(dev, "resources: ioport %pR %pR iomem %pR %pR %pR",
+		p_dev->resource[0], p_dev->resource[1], p_dev->resource[2],
+		p_dev->resource[3], p_dev->resource[4]);
 
 	mutex_lock(&s->ops_mutex);
 	if ((s->pcmcia_pfc) &&
@@ -374,13 +381,13 @@
 	if (p_dev->_irq || p_dev->_io || p_dev->_locked)
 		dev_printk(KERN_INFO, dev,
 			"pcmcia: driver %s did not release config properly\n",
-			p_drv->drv.name);
+			p_drv->name);
 
 	for (i = 0; i < MAX_WIN; i++)
 		if (p_dev->_win & CLIENT_WIN_REQ(i))
 			dev_printk(KERN_INFO, dev,
 			  "pcmcia: driver %s did not release window properly\n",
-			   p_drv->drv.name);
+			   p_drv->name);
 
 	/* references from pcmcia_probe_device */
 	pcmcia_put_dev(p_dev);
@@ -1136,7 +1143,7 @@
 			dev_printk(KERN_ERR, dev,
 				   "pcmcia: device %s (driver %s) did "
 				   "not want to go to sleep (%d)\n",
-				   p_dev->devname, p_drv->drv.name, ret);
+				   p_dev->devname, p_drv->name, ret);
 			mutex_lock(&p_dev->socket->ops_mutex);
 			p_dev->suspended = 0;
 			mutex_unlock(&p_dev->socket->ops_mutex);
@@ -1178,7 +1185,7 @@
 
 	if (p_dev->device_no == p_dev->func) {
 		dev_dbg(dev, "requesting configuration\n");
-		ret = pcmcia_request_configuration(p_dev, &p_dev->conf);
+		ret = pcmcia_enable_device(p_dev);
 		if (ret)
 			goto out;
 	}
diff --git a/drivers/pcmcia/i82092.c b/drivers/pcmcia/i82092.c
index 05d0879..fc7906e 100644
--- a/drivers/pcmcia/i82092.c
+++ b/drivers/pcmcia/i82092.c
@@ -16,7 +16,6 @@
 #include <linux/device.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 
 #include <asm/system.h>
 #include <asm/io.h>
diff --git a/drivers/pcmcia/i82365.c b/drivers/pcmcia/i82365.c
index 61746bd..72a033a 100644
--- a/drivers/pcmcia/i82365.c
+++ b/drivers/pcmcia/i82365.c
@@ -51,7 +51,6 @@
 #include <asm/system.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 
 #include <linux/isapnp.h>
 
diff --git a/drivers/pcmcia/m32r_cfc.c b/drivers/pcmcia/m32r_cfc.c
index 24de499..2adb010 100644
--- a/drivers/pcmcia/m32r_cfc.c
+++ b/drivers/pcmcia/m32r_cfc.c
@@ -27,7 +27,6 @@
 #include <asm/system.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 
 #undef MAX_IO_WIN	/* FIXME */
 #define MAX_IO_WIN 1
diff --git a/drivers/pcmcia/m32r_pcc.c b/drivers/pcmcia/m32r_pcc.c
index 8e47238..1511ff7 100644
--- a/drivers/pcmcia/m32r_pcc.c
+++ b/drivers/pcmcia/m32r_pcc.c
@@ -28,7 +28,6 @@
 #include <asm/addrspace.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 
 /* XXX: should be moved into asm/irq.h */
 #define PCC0_IRQ 24
diff --git a/drivers/pcmcia/m8xx_pcmcia.c b/drivers/pcmcia/m8xx_pcmcia.c
index f0ecad9..99d4f23 100644
--- a/drivers/pcmcia/m8xx_pcmcia.c
+++ b/drivers/pcmcia/m8xx_pcmcia.c
@@ -59,7 +59,6 @@
 #include <asm/irq.h>
 #include <asm/fs_pd.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/ss.h>
 
 #define pcmcia_info(args...) printk(KERN_INFO "m8xx_pcmcia: "args)
diff --git a/drivers/pcmcia/o2micro.h b/drivers/pcmcia/o2micro.h
index e74beba..5096e92 100644
--- a/drivers/pcmcia/o2micro.h
+++ b/drivers/pcmcia/o2micro.h
@@ -153,14 +153,14 @@
 
 		if (use_speedup) {
 			dev_info(&socket->dev->dev,
-				"O2: enabling read prefetch/write burst\n");
+				"O2: enabling read prefetch/write burst. If you experience problems or performance issues, use the yenta_socket parameter 'o2_speedup=off'\n");
 			config_writeb(socket, O2_RESERVED1,
 				      a | O2_RES_READ_PREFETCH | O2_RES_WRITE_BURST);
 			config_writeb(socket, O2_RESERVED2,
 				      b | O2_RES_READ_PREFETCH | O2_RES_WRITE_BURST);
 		} else {
 			dev_info(&socket->dev->dev,
-				"O2: disabling read prefetch/write burst\n");
+				"O2: disabling read prefetch/write burst. If you experience problems or performance issues, use the yenta_socket parameter 'o2_speedup=on'\n");
 			config_writeb(socket, O2_RESERVED1,
 				      a & ~(O2_RES_READ_PREFETCH | O2_RES_WRITE_BURST));
 			config_writeb(socket, O2_RESERVED2,
diff --git a/drivers/pcmcia/pcmcia_cis.c b/drivers/pcmcia/pcmcia_cis.c
index 0ac54da..e2c9241 100644
--- a/drivers/pcmcia/pcmcia_cis.c
+++ b/drivers/pcmcia/pcmcia_cis.c
@@ -6,7 +6,7 @@
  * are Copyright (C) 1999 David A. Hinds.  All Rights Reserved.
  *
  * Copyright (C) 1999	     David A. Hinds
- * Copyright (C) 2004-2009   Dominik Brodowski
+ * Copyright (C) 2004-2010   Dominik Brodowski
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -22,7 +22,6 @@
 #include <pcmcia/cisreg.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/ds.h>
 #include "cs_internal.h"
 
@@ -126,14 +125,24 @@
 	return ret;
 }
 
+
+/**
+ * pcmcia_io_cfg_data_width() - convert cfgtable to data path width parameter
+ */
+static int pcmcia_io_cfg_data_width(unsigned int flags)
+{
+	if (!(flags & CISTPL_IO_8BIT))
+		return IO_DATA_PATH_WIDTH_16;
+	if (!(flags & CISTPL_IO_16BIT))
+		return IO_DATA_PATH_WIDTH_8;
+	return IO_DATA_PATH_WIDTH_AUTO;
+}
+
+
 struct pcmcia_cfg_mem {
 	struct pcmcia_device *p_dev;
+	int (*conf_check) (struct pcmcia_device *p_dev, void *priv_data);
 	void *priv_data;
-	int (*conf_check) (struct pcmcia_device *p_dev,
-			   cistpl_cftable_entry_t *cfg,
-			   cistpl_cftable_entry_t *dflt,
-			   unsigned int vcc,
-			   void *priv_data);
 	cisparse_t parse;
 	cistpl_cftable_entry_t dflt;
 };
@@ -147,25 +156,102 @@
  */
 static int pcmcia_do_loop_config(tuple_t *tuple, cisparse_t *parse, void *priv)
 {
-	cistpl_cftable_entry_t *cfg = &parse->cftable_entry;
 	struct pcmcia_cfg_mem *cfg_mem = priv;
+	struct pcmcia_device *p_dev = cfg_mem->p_dev;
+	cistpl_cftable_entry_t *cfg = &parse->cftable_entry;
+	cistpl_cftable_entry_t *dflt = &cfg_mem->dflt;
+	unsigned int flags = p_dev->config_flags;
+	unsigned int vcc = p_dev->socket->socket.Vcc;
+
+	dev_dbg(&p_dev->dev, "testing configuration %x, autoconf %x\n",
+		cfg->index, flags);
 
 	/* default values */
-	cfg_mem->p_dev->conf.ConfigIndex = cfg->index;
+	cfg_mem->p_dev->config_index = cfg->index;
 	if (cfg->flags & CISTPL_CFTABLE_DEFAULT)
 		cfg_mem->dflt = *cfg;
 
-	return cfg_mem->conf_check(cfg_mem->p_dev, cfg, &cfg_mem->dflt,
-				   cfg_mem->p_dev->socket->socket.Vcc,
-				   cfg_mem->priv_data);
+	/* check for matching Vcc? */
+	if (flags & CONF_AUTO_CHECK_VCC) {
+		if (cfg->vcc.present & (1 << CISTPL_POWER_VNOM)) {
+			if (vcc != cfg->vcc.param[CISTPL_POWER_VNOM] / 10000)
+				return -ENODEV;
+		} else if (dflt->vcc.present & (1 << CISTPL_POWER_VNOM)) {
+			if (vcc != dflt->vcc.param[CISTPL_POWER_VNOM] / 10000)
+				return -ENODEV;
+		}
+	}
+
+	/* set Vpp? */
+	if (flags & CONF_AUTO_SET_VPP) {
+		if (cfg->vpp1.present & (1 << CISTPL_POWER_VNOM))
+			p_dev->vpp = cfg->vpp1.param[CISTPL_POWER_VNOM] / 10000;
+		else if (dflt->vpp1.present & (1 << CISTPL_POWER_VNOM))
+			p_dev->vpp =
+				dflt->vpp1.param[CISTPL_POWER_VNOM] / 10000;
+	}
+
+	/* enable audio? */
+	if ((flags & CONF_AUTO_AUDIO) && (cfg->flags & CISTPL_CFTABLE_AUDIO))
+		p_dev->config_flags |= CONF_ENABLE_SPKR;
+
+
+	/* IO window settings? */
+	if (flags & CONF_AUTO_SET_IO) {
+		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
+		int i = 0;
+
+		p_dev->resource[0]->start = p_dev->resource[0]->end = 0;
+		p_dev->resource[1]->start = p_dev->resource[1]->end = 0;
+		if (io->nwin == 0)
+			return -ENODEV;
+
+		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+		p_dev->resource[0]->flags |=
+					pcmcia_io_cfg_data_width(io->flags);
+		if (io->nwin > 1) {
+			/* For multifunction cards, by convention, we
+			 * configure the network function with window 0,
+			 * and serial with window 1 */
+			i = (io->win[1].len > io->win[0].len);
+			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
+			p_dev->resource[1]->start = io->win[1-i].base;
+			p_dev->resource[1]->end = io->win[1-i].len;
+		}
+		p_dev->resource[0]->start = io->win[i].base;
+		p_dev->resource[0]->end = io->win[i].len;
+		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
+	}
+
+	/* MEM window settings? */
+	if (flags & CONF_AUTO_SET_IOMEM) {
+		/* so far, we only set one memory window */
+		cistpl_mem_t *mem = (cfg->mem.nwin) ? &cfg->mem : &dflt->mem;
+
+		p_dev->resource[2]->start = p_dev->resource[2]->end = 0;
+		if (mem->nwin == 0)
+			return -ENODEV;
+
+		p_dev->resource[2]->start = mem->win[0].host_addr;
+		p_dev->resource[2]->end = mem->win[0].len;
+		if (p_dev->resource[2]->end < 0x1000)
+			p_dev->resource[2]->end = 0x1000;
+		p_dev->card_addr = mem->win[0].card_addr;
+	}
+
+	dev_dbg(&p_dev->dev,
+		"checking configuration %x: %pr %pr %pr (%d lines)\n",
+		p_dev->config_index, p_dev->resource[0], p_dev->resource[1],
+		p_dev->resource[2], p_dev->io_lines);
+
+	return cfg_mem->conf_check(p_dev, cfg_mem->priv_data);
 }
 
 /**
  * pcmcia_loop_config() - loop over configuration options
  * @p_dev:	the struct pcmcia_device which we need to loop for.
  * @conf_check:	function to call for each configuration option.
- *		It gets passed the struct pcmcia_device, the CIS data
- *		describing the configuration option, and private data
+ *		It gets passed the struct pcmcia_device and private data
  *		being passed to pcmcia_loop_config()
  * @priv_data:	private data to be passed to the conf_check function.
  *
@@ -175,9 +261,6 @@
  */
 int pcmcia_loop_config(struct pcmcia_device *p_dev,
 		       int	(*conf_check)	(struct pcmcia_device *p_dev,
-						 cistpl_cftable_entry_t *cfg,
-						 cistpl_cftable_entry_t *dflt,
-						 unsigned int vcc,
 						 void *priv_data),
 		       void *priv_data)
 {
diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c
index 9ba4dad..0bdda5b3 100644
--- a/drivers/pcmcia/pcmcia_resource.c
+++ b/drivers/pcmcia/pcmcia_resource.c
@@ -6,7 +6,7 @@
  * are Copyright (C) 1999 David A. Hinds.  All Rights Reserved.
  *
  * Copyright (C) 1999	     David A. Hinds
- * Copyright (C) 2004-2005   Dominik Brodowski
+ * Copyright (C) 2004-2010   Dominik Brodowski
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -26,7 +26,6 @@
 #include <asm/irq.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -56,6 +55,12 @@
 }
 
 
+/**
+ * release_io_space() - release IO ports allocated with alloc_io_space()
+ * @s: pcmcia socket
+ * @res: resource to release
+ *
+ */
 static void release_io_space(struct pcmcia_socket *s, struct resource *res)
 {
 	resource_size_t num = resource_size(res);
@@ -81,9 +86,14 @@
 			}
 		}
 	}
-} /* release_io_space */
+}
 
-/** alloc_io_space
+
+/**
+ * alloc_io_space() - allocate IO ports for use by a PCMCIA device
+ * @s: pcmcia socket
+ * @res: resource to allocate (begin: begin, end: size)
+ * @lines: number of IO lines decoded by the PCMCIA card
  *
  * Special stuff for managing IO windows, because they are scarce
  */
@@ -135,7 +145,7 @@
 	}
 	dev_dbg(&s->dev, "alloc_io_space request result %d: %pR\n", ret, res);
 	return ret;
-} /* alloc_io_space */
+}
 
 
 /**
@@ -168,14 +178,14 @@
 		return -EACCES;
 	}
 
-	addr = (c->ConfigBase + where) >> 1;
+	addr = (p_dev->config_base + where) >> 1;
 
 	ret = accessf(s, 1, addr, 1, val);
 
 	mutex_unlock(&s->ops_mutex);
 
 	return ret;
-} /* pcmcia_access_config */
+}
 
 
 /**
@@ -204,11 +214,20 @@
 EXPORT_SYMBOL(pcmcia_write_config_byte);
 
 
-int pcmcia_map_mem_page(struct pcmcia_device *p_dev, window_handle_t wh,
+/**
+ * pcmcia_map_mem_page() - modify iomem window to point to a different offset
+ * @p_dev: pcmcia device
+ * @res: iomem resource already enabled by pcmcia_request_window()
+ * @offset: card_offset to map
+ *
+ * pcmcia_map_mem_page() modifies what can be read and written by accessing
+ * an iomem range previously enabled by pcmcia_request_window(), by setting
+ * the card_offset value to @offset.
+ */
+int pcmcia_map_mem_page(struct pcmcia_device *p_dev, struct resource *res,
 			unsigned int offset)
 {
 	struct pcmcia_socket *s = p_dev->socket;
-	struct resource *res = wh;
 	unsigned int w;
 	int ret;
 
@@ -223,98 +242,111 @@
 		dev_warn(&p_dev->dev, "failed to set_mem_map\n");
 	mutex_unlock(&s->ops_mutex);
 	return ret;
-} /* pcmcia_map_mem_page */
+}
 EXPORT_SYMBOL(pcmcia_map_mem_page);
 
 
-/** pcmcia_modify_configuration
+/**
+ * pcmcia_fixup_iowidth() - reduce io width to 8bit
+ * @p_dev: pcmcia device
  *
- * Modify a locked socket configuration
+ * pcmcia_fixup_iowidth() allows a PCMCIA device driver to reduce the
+ * IO width to 8bit after having called pcmcia_enable_device()
+ * previously.
  */
-int pcmcia_modify_configuration(struct pcmcia_device *p_dev,
-				modconf_t *mod)
+int pcmcia_fixup_iowidth(struct pcmcia_device *p_dev)
 {
-	struct pcmcia_socket *s;
-	config_t *c;
-	int ret;
-
-	s = p_dev->socket;
+	struct pcmcia_socket *s = p_dev->socket;
+	pccard_io_map io_off = { 0, 0, 0, 0, 1 };
+	pccard_io_map io_on;
+	int i, ret = 0;
 
 	mutex_lock(&s->ops_mutex);
-	c = p_dev->function_config;
 
-	if (!(s->state & SOCKET_PRESENT)) {
-		dev_dbg(&p_dev->dev, "No card present\n");
-		ret = -ENODEV;
-		goto unlock;
-	}
-	if (!(c->state & CONFIG_LOCKED)) {
-		dev_dbg(&p_dev->dev, "Configuration isnt't locked\n");
+	dev_dbg(&p_dev->dev, "fixup iowidth to 8bit\n");
+
+	if (!(s->state & SOCKET_PRESENT) ||
+		!(p_dev->function_config->state & CONFIG_LOCKED)) {
+		dev_dbg(&p_dev->dev, "No card? Config not locked?\n");
 		ret = -EACCES;
 		goto unlock;
 	}
 
-	if (mod->Attributes & (CONF_IRQ_CHANGE_VALID | CONF_VCC_CHANGE_VALID)) {
-		dev_dbg(&p_dev->dev,
-			"changing Vcc or IRQ is not allowed at this time\n");
-		ret = -EINVAL;
-		goto unlock;
+	io_on.speed = io_speed;
+	for (i = 0; i < MAX_IO_WIN; i++) {
+		if (!s->io[i].res)
+			continue;
+		io_off.map = i;
+		io_on.map = i;
+
+		io_on.flags = MAP_ACTIVE | IO_DATA_PATH_WIDTH_8;
+		io_on.start = s->io[i].res->start;
+		io_on.stop = s->io[i].res->end;
+
+		s->ops->set_io_map(s, &io_off);
+		mdelay(40);
+		s->ops->set_io_map(s, &io_on);
 	}
-
-	/* We only allow changing Vpp1 and Vpp2 to the same value */
-	if ((mod->Attributes & CONF_VPP1_CHANGE_VALID) &&
-	    (mod->Attributes & CONF_VPP2_CHANGE_VALID)) {
-		if (mod->Vpp1 != mod->Vpp2) {
-			dev_dbg(&p_dev->dev,
-				"Vpp1 and Vpp2 must be the same\n");
-			ret = -EINVAL;
-			goto unlock;
-		}
-		s->socket.Vpp = mod->Vpp1;
-		if (s->ops->set_socket(s, &s->socket)) {
-			dev_printk(KERN_WARNING, &p_dev->dev,
-				   "Unable to set VPP\n");
-			ret = -EIO;
-			goto unlock;
-		}
-	} else if ((mod->Attributes & CONF_VPP1_CHANGE_VALID) ||
-		   (mod->Attributes & CONF_VPP2_CHANGE_VALID)) {
-		dev_dbg(&p_dev->dev,
-			"changing Vcc is not allowed at this time\n");
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	if (mod->Attributes & CONF_IO_CHANGE_WIDTH) {
-		pccard_io_map io_off = { 0, 0, 0, 0, 1 };
-		pccard_io_map io_on;
-		int i;
-
-		io_on.speed = io_speed;
-		for (i = 0; i < MAX_IO_WIN; i++) {
-			if (!s->io[i].res)
-				continue;
-			io_off.map = i;
-			io_on.map = i;
-
-			io_on.flags = MAP_ACTIVE | IO_DATA_PATH_WIDTH_8;
-			io_on.start = s->io[i].res->start;
-			io_on.stop = s->io[i].res->end;
-
-			s->ops->set_io_map(s, &io_off);
-			mdelay(40);
-			s->ops->set_io_map(s, &io_on);
-		}
-	}
-	ret = 0;
 unlock:
 	mutex_unlock(&s->ops_mutex);
 
 	return ret;
-} /* modify_configuration */
-EXPORT_SYMBOL(pcmcia_modify_configuration);
+}
+EXPORT_SYMBOL(pcmcia_fixup_iowidth);
 
 
+/**
+ * pcmcia_fixup_vpp() - set Vpp to a new voltage level
+ * @p_dev: pcmcia device
+ * @new_vpp: new Vpp voltage
+ *
+ * pcmcia_fixup_vpp() allows a PCMCIA device driver to set Vpp to
+ * a new voltage level between calls to pcmcia_enable_device()
+ * and pcmcia_disable_device().
+ */
+int pcmcia_fixup_vpp(struct pcmcia_device *p_dev, unsigned char new_vpp)
+{
+	struct pcmcia_socket *s = p_dev->socket;
+	int ret = 0;
+
+	mutex_lock(&s->ops_mutex);
+
+	dev_dbg(&p_dev->dev, "fixup Vpp to %d\n", new_vpp);
+
+	if (!(s->state & SOCKET_PRESENT) ||
+		!(p_dev->function_config->state & CONFIG_LOCKED)) {
+		dev_dbg(&p_dev->dev, "No card? Config not locked?\n");
+		ret = -EACCES;
+		goto unlock;
+	}
+
+	s->socket.Vpp = new_vpp;
+	if (s->ops->set_socket(s, &s->socket)) {
+		dev_warn(&p_dev->dev, "Unable to set VPP\n");
+		ret = -EIO;
+		goto unlock;
+	}
+	p_dev->vpp = new_vpp;
+
+unlock:
+	mutex_unlock(&s->ops_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL(pcmcia_fixup_vpp);
+
+
+/**
+ * pcmcia_release_configuration() - physically disable a PCMCIA device
+ * @p_dev: pcmcia device
+ *
+ * pcmcia_release_configuration() is the 1:1 counterpart to
+ * pcmcia_enable_device(): If a PCMCIA device is no longer used by any
+ * driver, the Vpp voltage is set to 0, IRQs will no longer be generated,
+ * and I/O ranges will be disabled. As pcmcia_release_io() and
+ * pcmcia_release_window() still need to be called, device drivers are
+ * expected to call pcmcia_disable_device() instead.
+ */
 int pcmcia_release_configuration(struct pcmcia_device *p_dev)
 {
 	pccard_io_map io = { 0, 0, 0, 0, 1 };
@@ -327,7 +359,7 @@
 	if (p_dev->_locked) {
 		p_dev->_locked = 0;
 		if (--(s->lock_count) == 0) {
-			s->socket.flags = SS_OUTPUT_ENA;   /* Is this correct? */
+			s->socket.flags = SS_OUTPUT_ENA; /* Is this correct? */
 			s->socket.Vpp = 0;
 			s->socket.io_irq = 0;
 			s->ops->set_socket(s, &s->socket);
@@ -349,16 +381,18 @@
 	mutex_unlock(&s->ops_mutex);
 
 	return 0;
-} /* pcmcia_release_configuration */
+}
 
 
-/** pcmcia_release_io
+/**
+ * pcmcia_release_io() - release I/O allocated by a PCMCIA device
+ * @p_dev: pcmcia device
  *
- * Release_io() releases the I/O ranges allocated by a client.  This
- * may be invoked some time after a card ejection has already dumped
- * the actual socket configuration, so if the client is "stale", we
- * don't bother checking the port ranges against the current socket
- * values.
+ * pcmcia_release_io() releases the I/O ranges allocated by a PCMCIA
+ * device.  This may be invoked some time after a card ejection has
+ * already dumped the actual socket configuration, so if the client is
+ * "stale", we don't bother checking the port ranges against the
+ * current socket values.
  */
 static int pcmcia_release_io(struct pcmcia_device *p_dev)
 {
@@ -387,6 +421,14 @@
 } /* pcmcia_release_io */
 
 
+/**
+ * pcmcia_release_window() - release reserved iomem for PCMCIA devices
+ * @p_dev: pcmcia device
+ * @res: iomem resource to release
+ *
+ * pcmcia_release_window() releases &struct resource *res which was
+ * previously reserved by calling pcmcia_request_window().
+ */
 int pcmcia_release_window(struct pcmcia_device *p_dev, struct resource *res)
 {
 	struct pcmcia_socket *s = p_dev->socket;
@@ -420,6 +462,8 @@
 		kfree(win->res);
 		win->res = NULL;
 	}
+	res->start = res->end = 0;
+	res->flags = IORESOURCE_MEM;
 	p_dev->_win &= ~CLIENT_WIN_REQ(w);
 	mutex_unlock(&s->ops_mutex);
 
@@ -428,23 +472,30 @@
 EXPORT_SYMBOL(pcmcia_release_window);
 
 
-int pcmcia_request_configuration(struct pcmcia_device *p_dev,
-				 config_req_t *req)
+/**
+ * pcmcia_enable_device() - set up and activate a PCMCIA device
+ * @p_dev: the associated PCMCIA device
+ *
+ * pcmcia_enable_device() physically enables a PCMCIA device. It parses
+ * the flags passed to in @flags and stored in @p_dev->flags and sets up
+ * the Vpp voltage, enables the speaker line, I/O ports and store proper
+ * values to configuration registers.
+ */
+int pcmcia_enable_device(struct pcmcia_device *p_dev)
 {
 	int i;
-	u_int base;
+	unsigned int base;
 	struct pcmcia_socket *s = p_dev->socket;
 	config_t *c;
 	pccard_io_map iomap;
+	unsigned char status = 0;
+	unsigned char ext_status = 0;
+	unsigned char option = 0;
+	unsigned int flags = p_dev->config_flags;
 
 	if (!(s->state & SOCKET_PRESENT))
 		return -ENODEV;
 
-	if (req->IntType & INT_CARDBUS) {
-		dev_dbg(&p_dev->dev, "IntType may not be INT_CARDBUS\n");
-		return -EINVAL;
-	}
-
 	mutex_lock(&s->ops_mutex);
 	c = p_dev->function_config;
 	if (c->state & CONFIG_LOCKED) {
@@ -454,7 +505,7 @@
 	}
 
 	/* Do power control.  We don't allow changes in Vcc. */
-	s->socket.Vpp = req->Vpp;
+	s->socket.Vpp = p_dev->vpp;
 	if (s->ops->set_socket(s, &s->socket)) {
 		mutex_unlock(&s->ops_mutex);
 		dev_printk(KERN_WARNING, &p_dev->dev,
@@ -463,64 +514,74 @@
 	}
 
 	/* Pick memory or I/O card, DMA mode, interrupt */
-	c->IntType = req->IntType;
-	c->Attributes = req->Attributes;
-	if (req->IntType & INT_MEMORY_AND_IO)
+	if (p_dev->_io || flags & CONF_ENABLE_IRQ)
+		flags |= CONF_ENABLE_IOCARD;
+	if (flags & CONF_ENABLE_IOCARD)
 		s->socket.flags |= SS_IOCARD;
-	if (req->IntType & INT_ZOOMED_VIDEO)
-		s->socket.flags |= SS_ZVCARD | SS_IOCARD;
-	if (req->Attributes & CONF_ENABLE_DMA)
-		s->socket.flags |= SS_DMA_MODE;
-	if (req->Attributes & CONF_ENABLE_SPKR)
+	if (flags & CONF_ENABLE_SPKR) {
 		s->socket.flags |= SS_SPKR_ENA;
-	if (req->Attributes & CONF_ENABLE_IRQ)
+		status = CCSR_AUDIO_ENA;
+		if (!(p_dev->config_regs & PRESENT_STATUS))
+			dev_warn(&p_dev->dev, "speaker requested, but "
+					      "PRESENT_STATUS not set!\n");
+	}
+	if (flags & CONF_ENABLE_IRQ)
 		s->socket.io_irq = s->pcmcia_irq;
 	else
 		s->socket.io_irq = 0;
+	if (flags & CONF_ENABLE_ESR) {
+		p_dev->config_regs |= PRESENT_EXT_STATUS;
+		ext_status = ESR_REQ_ATTN_ENA;
+	}
 	s->ops->set_socket(s, &s->socket);
 	s->lock_count++;
 
+	dev_dbg(&p_dev->dev,
+		"enable_device: V %d, flags %x, base %x, regs %x, idx %x\n",
+		p_dev->vpp, flags, p_dev->config_base, p_dev->config_regs,
+		p_dev->config_index);
+
 	/* Set up CIS configuration registers */
-	base = c->ConfigBase = req->ConfigBase;
-	c->CardValues = req->Present;
-	if (req->Present & PRESENT_COPY) {
-		c->Copy = req->Copy;
-		pcmcia_write_cis_mem(s, 1, (base + CISREG_SCR)>>1, 1, &c->Copy);
+	base = p_dev->config_base;
+	if (p_dev->config_regs & PRESENT_COPY) {
+		u16 tmp = 0;
+		dev_dbg(&p_dev->dev, "clearing CISREG_SCR\n");
+		pcmcia_write_cis_mem(s, 1, (base + CISREG_SCR)>>1, 1, &tmp);
 	}
-	if (req->Present & PRESENT_OPTION) {
+	if (p_dev->config_regs & PRESENT_PIN_REPLACE) {
+		u16 tmp = 0;
+		dev_dbg(&p_dev->dev, "clearing CISREG_PRR\n");
+		pcmcia_write_cis_mem(s, 1, (base + CISREG_PRR)>>1, 1, &tmp);
+	}
+	if (p_dev->config_regs & PRESENT_OPTION) {
 		if (s->functions == 1) {
-			c->Option = req->ConfigIndex & COR_CONFIG_MASK;
+			option = p_dev->config_index & COR_CONFIG_MASK;
 		} else {
-			c->Option = req->ConfigIndex & COR_MFC_CONFIG_MASK;
-			c->Option |= COR_FUNC_ENA|COR_IREQ_ENA;
-			if (req->Present & PRESENT_IOBASE_0)
-				c->Option |= COR_ADDR_DECODE;
+			option = p_dev->config_index & COR_MFC_CONFIG_MASK;
+			option |= COR_FUNC_ENA|COR_IREQ_ENA;
+			if (p_dev->config_regs & PRESENT_IOBASE_0)
+				option |= COR_ADDR_DECODE;
 		}
-		if ((req->Attributes & CONF_ENABLE_IRQ) &&
-			!(req->Attributes & CONF_ENABLE_PULSE_IRQ))
-			c->Option |= COR_LEVEL_REQ;
-		pcmcia_write_cis_mem(s, 1, (base + CISREG_COR)>>1, 1, &c->Option);
+		if ((flags & CONF_ENABLE_IRQ) &&
+			!(flags & CONF_ENABLE_PULSE_IRQ))
+			option |= COR_LEVEL_REQ;
+		pcmcia_write_cis_mem(s, 1, (base + CISREG_COR)>>1, 1, &option);
 		mdelay(40);
 	}
-	if (req->Present & PRESENT_STATUS) {
-		c->Status = req->Status;
-		pcmcia_write_cis_mem(s, 1, (base + CISREG_CCSR)>>1, 1, &c->Status);
-	}
-	if (req->Present & PRESENT_PIN_REPLACE) {
-		c->Pin = req->Pin;
-		pcmcia_write_cis_mem(s, 1, (base + CISREG_PRR)>>1, 1, &c->Pin);
-	}
-	if (req->Present & PRESENT_EXT_STATUS) {
-		c->ExtStatus = req->ExtStatus;
-		pcmcia_write_cis_mem(s, 1, (base + CISREG_ESR)>>1, 1, &c->ExtStatus);
-	}
-	if (req->Present & PRESENT_IOBASE_0) {
+	if (p_dev->config_regs & PRESENT_STATUS)
+		pcmcia_write_cis_mem(s, 1, (base + CISREG_CCSR)>>1, 1, &status);
+
+	if (p_dev->config_regs & PRESENT_EXT_STATUS)
+		pcmcia_write_cis_mem(s, 1, (base + CISREG_ESR)>>1, 1,
+					&ext_status);
+
+	if (p_dev->config_regs & PRESENT_IOBASE_0) {
 		u8 b = c->io[0].start & 0xff;
 		pcmcia_write_cis_mem(s, 1, (base + CISREG_IOBASE_0)>>1, 1, &b);
 		b = (c->io[0].start >> 8) & 0xff;
 		pcmcia_write_cis_mem(s, 1, (base + CISREG_IOBASE_1)>>1, 1, &b);
 	}
-	if (req->Present & PRESENT_IOSIZE) {
+	if (p_dev->config_regs & PRESENT_IOSIZE) {
 		u8 b = resource_size(&c->io[0]) + resource_size(&c->io[1]) - 1;
 		pcmcia_write_cis_mem(s, 1, (base + CISREG_IOSIZE)>>1, 1, &b);
 	}
@@ -551,14 +612,15 @@
 	p_dev->_locked = 1;
 	mutex_unlock(&s->ops_mutex);
 	return 0;
-} /* pcmcia_request_configuration */
-EXPORT_SYMBOL(pcmcia_request_configuration);
+} /* pcmcia_enable_device */
+EXPORT_SYMBOL(pcmcia_enable_device);
 
 
 /**
  * pcmcia_request_io() - attempt to reserve port ranges for PCMCIA devices
+ * @p_dev: the associated PCMCIA device
  *
- * pcmcia_request_io() attepts to reserve the IO port ranges specified in
+ * pcmcia_request_io() attempts to reserve the IO port ranges specified in
  * &struct pcmcia_device @p_dev->resource[0] and @p_dev->resource[1]. The
  * "start" value is the requested start of the IO port resource; "end"
  * reflects the number of ports requested. The number of IO lines requested
@@ -622,11 +684,13 @@
 
 /**
  * pcmcia_request_irq() - attempt to request a IRQ for a PCMCIA device
+ * @p_dev: the associated PCMCIA device
+ * @handler: IRQ handler to register
  *
- * pcmcia_request_irq() is a wrapper around request_irq which will allow
+ * pcmcia_request_irq() is a wrapper around request_irq() which allows
  * the PCMCIA core to clean up the registration in pcmcia_disable_device().
  * Drivers are free to use request_irq() directly, but then they need to
- * call free_irq themselfves, too. Also, only IRQF_SHARED capable IRQ
+ * call free_irq() themselfves, too. Also, only %IRQF_SHARED capable IRQ
  * handlers are allowed.
  */
 int __must_check pcmcia_request_irq(struct pcmcia_device *p_dev,
@@ -649,12 +713,14 @@
 
 /**
  * pcmcia_request_exclusive_irq() - attempt to request an exclusive IRQ first
+ * @p_dev: the associated PCMCIA device
+ * @handler: IRQ handler to register
  *
- * pcmcia_request_exclusive_irq() is a wrapper around request_irq which
+ * pcmcia_request_exclusive_irq() is a wrapper around request_irq() which
  * attempts first to request an exclusive IRQ. If it fails, it also accepts
  * a shared IRQ, but prints out a warning. PCMCIA drivers should allow for
  * IRQ sharing and either use request_irq directly (then they need to call
- * free_irq themselves, too), or the pcmcia_request_irq() function.
+ * free_irq() themselves, too), or the pcmcia_request_irq() function.
  */
 int __must_check
 __pcmcia_request_exclusive_irq(struct pcmcia_device *p_dev,
@@ -795,38 +861,47 @@
 }
 
 
-/** pcmcia_request_window
+/**
+ * pcmcia_request_window() - attempt to reserve iomem for PCMCIA devices
+ * @p_dev: the associated PCMCIA device
+ * @res: &struct resource pointing to p_dev->resource[2..5]
+ * @speed: access speed
  *
- * Request_window() establishes a mapping between card memory space
- * and system memory space.
+ * pcmcia_request_window() attepts to reserve an iomem ranges specified in
+ * &struct resource @res pointing to one of the entries in
+ * &struct pcmcia_device @p_dev->resource[2..5]. The "start" value is the
+ * requested start of the IO mem resource; "end" reflects the size
+ * requested.
  */
-int pcmcia_request_window(struct pcmcia_device *p_dev, win_req_t *req, window_handle_t *wh)
+int pcmcia_request_window(struct pcmcia_device *p_dev, struct resource *res,
+			unsigned int speed)
 {
 	struct pcmcia_socket *s = p_dev->socket;
 	pccard_mem_map *win;
 	u_long align;
-	struct resource *res;
 	int w;
 
+	dev_dbg(&p_dev->dev, "request_window %pR %d\n", res, speed);
+
 	if (!(s->state & SOCKET_PRESENT)) {
 		dev_dbg(&p_dev->dev, "No card present\n");
 		return -ENODEV;
 	}
 
 	/* Window size defaults to smallest available */
-	if (req->Size == 0)
-		req->Size = s->map_size;
-	align = (s->features & SS_CAP_MEM_ALIGN) ? req->Size : s->map_size;
-	if (req->Size & (s->map_size-1)) {
+	if (res->end == 0)
+		res->end = s->map_size;
+	align = (s->features & SS_CAP_MEM_ALIGN) ? res->end : s->map_size;
+	if (res->end & (s->map_size-1)) {
 		dev_dbg(&p_dev->dev, "invalid map size\n");
 		return -EINVAL;
 	}
-	if ((req->Base && (s->features & SS_CAP_STATIC_MAP)) ||
-	    (req->Base & (align-1))) {
+	if ((res->start && (s->features & SS_CAP_STATIC_MAP)) ||
+	    (res->start & (align-1))) {
 		dev_dbg(&p_dev->dev, "invalid base address\n");
 		return -EINVAL;
 	}
-	if (req->Base)
+	if (res->start)
 		align = 0;
 
 	/* Allocate system memory window */
@@ -843,7 +918,7 @@
 	win = &s->win[w];
 
 	if (!(s->features & SS_CAP_STATIC_MAP)) {
-		win->res = pcmcia_find_mem_region(req->Base, req->Size, align,
+		win->res = pcmcia_find_mem_region(res->start, res->end, align,
 						0, s);
 		if (!win->res) {
 			dev_dbg(&p_dev->dev, "allocating mem region failed\n");
@@ -855,8 +930,8 @@
 
 	/* Configure the socket controller */
 	win->map = w+1;
-	win->flags = req->Attributes;
-	win->speed = req->AccessSpeed;
+	win->flags = res->flags & WIN_FLAGS_MAP;
+	win->speed = speed;
 	win->card_start = 0;
 
 	if (s->ops->set_mem_map(s, win) != 0) {
@@ -868,17 +943,14 @@
 
 	/* Return window handle */
 	if (s->features & SS_CAP_STATIC_MAP)
-		req->Base = win->static_start;
+		res->start = win->static_start;
 	else
-		req->Base = win->res->start;
+		res->start = win->res->start;
 
 	/* convert to new-style resources */
-	res = p_dev->resource[w + MAX_IO_WIN];
-	res->start = req->Base;
-	res->end = req->Base + req->Size - 1;
-	res->flags &= ~IORESOURCE_BITS;
-	res->flags |= (req->Attributes & WIN_FLAGS_MAP) | (win->map << 2);
-	res->flags |= IORESOURCE_MEM;
+	res->end += res->start - 1;
+	res->flags &= ~WIN_FLAGS_REQ;
+	res->flags |= (win->map << 2) | IORESOURCE_MEM;
 	res->parent = win->res;
 	if (win->res)
 		request_resource(&iomem_resource, res);
@@ -886,15 +958,30 @@
 	dev_dbg(&p_dev->dev, "request_window results in %pR\n", res);
 
 	mutex_unlock(&s->ops_mutex);
-	*wh = res;
 
 	return 0;
 } /* pcmcia_request_window */
 EXPORT_SYMBOL(pcmcia_request_window);
 
+
+/**
+ * pcmcia_disable_device() - disable and clean up a PCMCIA device
+ * @p_dev: the associated PCMCIA device
+ *
+ * pcmcia_disable_device() is the driver-callable counterpart to
+ * pcmcia_enable_device(): If a PCMCIA device is no longer used,
+ * drivers are expected to clean up and disable the device by calling
+ * this function. Any I/O ranges (iomem and ioports) will be released,
+ * the Vpp voltage will be set to 0, and IRQs will no longer be
+ * generated -- at least if there is no other card function (of
+ * multifunction devices) being used.
+ */
 void pcmcia_disable_device(struct pcmcia_device *p_dev)
 {
 	int i;
+
+	dev_dbg(&p_dev->dev, "disabling device\n");
+
 	for (i = 0; i < MAX_WIN; i++) {
 		struct resource *res = p_dev->resource[MAX_IO_WIN + i];
 		if (res->flags & WIN_FLAGS_REQ)
diff --git a/drivers/pcmcia/pd6729.c b/drivers/pcmcia/pd6729.c
index deef665..8cbfa06 100644
--- a/drivers/pcmcia/pd6729.c
+++ b/drivers/pcmcia/pd6729.c
@@ -18,7 +18,6 @@
 #include <linux/io.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 
 #include <asm/system.h>
 
diff --git a/drivers/pcmcia/rsrc_iodyn.c b/drivers/pcmcia/rsrc_iodyn.c
index 8510c35..523eb69 100644
--- a/drivers/pcmcia/rsrc_iodyn.c
+++ b/drivers/pcmcia/rsrc_iodyn.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include "cs_internal.h"
 
diff --git a/drivers/pcmcia/rsrc_mgr.c b/drivers/pcmcia/rsrc_mgr.c
index 4e80421..aa628ed 100644
--- a/drivers/pcmcia/rsrc_mgr.c
+++ b/drivers/pcmcia/rsrc_mgr.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include "cs_internal.h"
 
diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c
index 96f348b..b187555 100644
--- a/drivers/pcmcia/rsrc_nonstatic.c
+++ b/drivers/pcmcia/rsrc_nonstatic.c
@@ -29,7 +29,6 @@
 #include <asm/irq.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include "cs_internal.h"
 
diff --git a/drivers/pcmcia/sa1100_generic.c b/drivers/pcmcia/sa1100_generic.c
index e098514..945857f 100644
--- a/drivers/pcmcia/sa1100_generic.c
+++ b/drivers/pcmcia/sa1100_generic.c
@@ -35,7 +35,6 @@
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/ss.h>
 
 #include <asm/hardware/scoop.h>
diff --git a/drivers/pcmcia/soc_common.c b/drivers/pcmcia/soc_common.c
index 6f1a86b..689e3c0 100644
--- a/drivers/pcmcia/soc_common.c
+++ b/drivers/pcmcia/soc_common.c
@@ -627,8 +627,6 @@
 
 	pcmcia_unregister_socket(&skt->socket);
 
-	flush_scheduled_work();
-
 	skt->ops->hw_shutdown(skt);
 
 	soc_common_pcmcia_config_skt(skt, &dead_socket);
@@ -720,8 +718,6 @@
 	pcmcia_unregister_socket(&skt->socket);
 
  out_err_7:
-	flush_scheduled_work();
-
 	skt->ops->hw_shutdown(skt);
  out_err_6:
 	list_del(&skt->node);
diff --git a/drivers/pcmcia/soc_common.h b/drivers/pcmcia/soc_common.h
index 3fba3a6..bbcd538 100644
--- a/drivers/pcmcia/soc_common.h
+++ b/drivers/pcmcia/soc_common.h
@@ -11,7 +11,6 @@
 
 /* include the world */
 #include <linux/cpufreq.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/ss.h>
 #include <pcmcia/cistpl.h>
 
diff --git a/drivers/pcmcia/socket_sysfs.c b/drivers/pcmcia/socket_sysfs.c
index cb0d3ac..71aeed9 100644
--- a/drivers/pcmcia/socket_sysfs.c
+++ b/drivers/pcmcia/socket_sysfs.c
@@ -27,7 +27,6 @@
 #include <asm/irq.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
diff --git a/drivers/pcmcia/tcic.c b/drivers/pcmcia/tcic.c
index be0d841..310160b 100644
--- a/drivers/pcmcia/tcic.c
+++ b/drivers/pcmcia/tcic.c
@@ -49,7 +49,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/ss.h>
 #include "tcic.h"
 
diff --git a/drivers/pcmcia/vrc4173_cardu.c b/drivers/pcmcia/vrc4173_cardu.c
index 9b3c158..c6d36b3 100644
--- a/drivers/pcmcia/vrc4173_cardu.c
+++ b/drivers/pcmcia/vrc4173_cardu.c
@@ -461,7 +461,7 @@
 {
 	vrc4173_socket_t *socket;
 	unsigned long start, len, flags;
-	int slot, err;
+	int slot, err, ret;
 
 	slot = vrc4173_cardu_slots++;
 	socket = &cardu_sockets[slot];
@@ -474,43 +474,63 @@
 		return err;
 
 	start = pci_resource_start(dev, 0);
-	if (start == 0)
-		return -ENODEV;
+	if (start == 0) {
+		ret = -ENODEV;
+		goto disable;
+	}
 
 	len = pci_resource_len(dev, 0);
-	if (len == 0)
-		return -ENODEV;
+	if (len == 0) {
+		ret = -ENODEV;
+		goto disable;
+	}
 
-	if (((flags = pci_resource_flags(dev, 0)) & IORESOURCE_MEM) == 0)
-		return -EBUSY;
+	flags = pci_resource_flags(dev, 0);
+	if ((flags & IORESOURCE_MEM) == 0) {
+		ret = -EBUSY;
+		goto disable;
+	}
 
-	if ((err = pci_request_regions(dev, socket->name)) < 0)
-		return err;
+	err = pci_request_regions(dev, socket->name);
+	if (err < 0) {
+		ret = err;
+		goto disable;
+	}
 
 	socket->base = ioremap(start, len);
-	if (socket->base == NULL)
-		return -ENODEV;
+	if (socket->base == NULL) {
+		ret = -ENODEV;
+		goto release;
+	}
 
 	socket->dev = dev;
 
 	socket->pcmcia_socket = pcmcia_register_socket(slot, &cardu_operations, 1);
 	if (socket->pcmcia_socket == NULL) {
-		iounmap(socket->base);
-		socket->base = NULL;
-		return -ENOMEM;
+		ret =  -ENOMEM;
+		goto unmap;
 	}
 
 	if (request_irq(dev->irq, cardu_interrupt, IRQF_SHARED, socket->name, socket) < 0) {
-		pcmcia_unregister_socket(socket->pcmcia_socket);
-		socket->pcmcia_socket = NULL;
-		iounmap(socket->base);
-		socket->base = NULL;
-		return -EBUSY;
+		ret = -EBUSY;
+		goto unregister;
 	}
 
 	printk(KERN_INFO "%s at %#08lx, IRQ %d\n", socket->name, start, dev->irq);
 
 	return 0;
+
+unregister:
+	pcmcia_unregister_socket(socket->pcmcia_socket);
+	socket->pcmcia_socket = NULL;
+unmap:
+	iounmap(socket->base);
+	socket->base = NULL;
+release:
+	pci_release_regions(dev);
+disable:
+	pci_disable_device(dev);
+	return ret;
 }
 
 static int __devinit vrc4173_cardu_setup(char *options)
diff --git a/drivers/pcmcia/xxs1500_ss.c b/drivers/pcmcia/xxs1500_ss.c
index fa88c36..3b67a1b 100644
--- a/drivers/pcmcia/xxs1500_ss.c
+++ b/drivers/pcmcia/xxs1500_ss.c
@@ -17,7 +17,6 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/ss.h>
 #include <pcmcia/cistpl.h>
 
diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c
index 414d9a6..408dbaa 100644
--- a/drivers/pcmcia/yenta_socket.c
+++ b/drivers/pcmcia/yenta_socket.c
@@ -20,7 +20,6 @@
 #include <linux/slab.h>
 
 #include <pcmcia/ss.h>
-#include <pcmcia/cs.h>
 
 #include "yenta_socket.h"
 #include "i82365.h"
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index e3154ff..f200677 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -2360,6 +2360,7 @@
 	.release	= sonypi_misc_release,
 	.fasync		= sonypi_misc_fasync,
 	.unlocked_ioctl	= sonypi_misc_ioctl,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice sonypi_misc_device = {
diff --git a/drivers/pnp/isapnp/proc.c b/drivers/pnp/isapnp/proc.c
index 3f94eda..e73ebef 100644
--- a/drivers/pnp/isapnp/proc.c
+++ b/drivers/pnp/isapnp/proc.c
@@ -31,8 +31,9 @@
 static loff_t isapnp_proc_bus_lseek(struct file *file, loff_t off, int whence)
 {
 	loff_t new = -1;
+	struct inode *inode = file->f_path.dentry->d_inode;
 
-	lock_kernel();
+	mutex_lock(&inode->i_mutex);
 	switch (whence) {
 	case 0:
 		new = off;
@@ -44,12 +45,12 @@
 		new = 256 + off;
 		break;
 	}
-	if (new < 0 || new > 256) {
-		unlock_kernel();
-		return -EINVAL;
-	}
-	unlock_kernel();
-	return (file->f_pos = new);
+	if (new < 0 || new > 256)
+		new = -EINVAL;
+	else
+		file->f_pos = new;
+	mutex_unlock(&inode->i_mutex);
+	return new;
 }
 
 static ssize_t isapnp_proc_bus_read(struct file *file, char __user * buf,
diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c
index d60557c..5a8daa3 100644
--- a/drivers/rtc/rtc-m41t80.c
+++ b/drivers/rtc/rtc-m41t80.c
@@ -20,7 +20,7 @@
 #include <linux/module.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/string.h>
 #ifdef CONFIG_RTC_DRV_M41T80_WDT
 #include <linux/fs.h>
@@ -68,6 +68,7 @@
 
 #define DRV_VERSION "0.05"
 
+static DEFINE_MUTEX(m41t80_rtc_mutex);
 static const struct i2c_device_id m41t80_id[] = {
 	{ "m41t62", M41T80_FEATURE_SQ | M41T80_FEATURE_SQ_ALT },
 	{ "m41t65", M41T80_FEATURE_HT | M41T80_FEATURE_WD },
@@ -677,9 +678,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&m41t80_rtc_mutex);
 	ret = wdt_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&m41t80_rtc_mutex);
 
 	return ret;
 }
@@ -693,16 +694,16 @@
 static int wdt_open(struct inode *inode, struct file *file)
 {
 	if (MINOR(inode->i_rdev) == WATCHDOG_MINOR) {
-		lock_kernel();
+		mutex_lock(&m41t80_rtc_mutex);
 		if (test_and_set_bit(0, &wdt_is_open)) {
-			unlock_kernel();
+			mutex_unlock(&m41t80_rtc_mutex);
 			return -EBUSY;
 		}
 		/*
 		 *	Activate
 		 */
 		wdt_is_open = 1;
-		unlock_kernel();
+		mutex_unlock(&m41t80_rtc_mutex);
 		return nonseekable_open(inode, file);
 	}
 	return -ENODEV;
@@ -748,6 +749,7 @@
 	.write	= wdt_write,
 	.open	= wdt_open,
 	.release = wdt_release,
+	.llseek = no_llseek,
 };
 
 static struct miscdevice wdt_dev = {
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 8373ca0..aa95f10 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -21,7 +21,6 @@
 #include <linux/hdreg.h>
 #include <linux/async.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 
 #include <asm/ccwdev.h>
 #include <asm/ebcdic.h>
@@ -2197,7 +2196,6 @@
 	 */
 	blk_queue_max_segment_size(block->request_queue, PAGE_SIZE);
 	blk_queue_segment_boundary(block->request_queue, PAGE_SIZE - 1);
-	blk_queue_ordered(block->request_queue, QUEUE_ORDERED_DRAIN);
 }
 
 /*
@@ -2236,7 +2234,6 @@
 	if (!block)
 		return -ENODEV;
 
-	lock_kernel();
 	base = block->base;
 	atomic_inc(&block->open_count);
 	if (test_bit(DASD_FLAG_OFFLINE, &base->flags)) {
@@ -2271,14 +2268,12 @@
 		goto out;
 	}
 
-	unlock_kernel();
 	return 0;
 
 out:
 	module_put(base->discipline->owner);
 unlock:
 	atomic_dec(&block->open_count);
-	unlock_kernel();
 	return rc;
 }
 
@@ -2286,10 +2281,8 @@
 {
 	struct dasd_block *block = disk->private_data;
 
-	lock_kernel();
 	atomic_dec(&block->open_count);
 	module_put(block->base->discipline->owner);
-	unlock_kernel();
 	return 0;
 }
 
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index 7158f95..c71d89d 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -670,6 +670,7 @@
 	.read		= &dasd_eer_read,
 	.poll		= &dasd_eer_poll,
 	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice *dasd_eer_dev = NULL;
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 1557214..26075e9 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -16,7 +16,6 @@
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/blkpg.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <asm/compat.h>
 #include <asm/ccwdev.h>
@@ -370,9 +369,8 @@
 	return ret;
 }
 
-static int
-dasd_do_ioctl(struct block_device *bdev, fmode_t mode,
-	      unsigned int cmd, unsigned long arg)
+int dasd_ioctl(struct block_device *bdev, fmode_t mode,
+	       unsigned int cmd, unsigned long arg)
 {
 	struct dasd_block *block = bdev->bd_disk->private_data;
 	void __user *argp;
@@ -430,14 +428,3 @@
 		return -EINVAL;
 	}
 }
-
-int dasd_ioctl(struct block_device *bdev, fmode_t mode,
-	       unsigned int cmd, unsigned long arg)
-{
-	int rc;
-
-	lock_kernel();
-	rc = dasd_do_ioctl(bdev, mode, cmd, arg);
-	unlock_kernel();
-	return rc;
-}
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 2bd72aa..9b43ae9 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
 #include <linux/completion.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
@@ -776,7 +775,6 @@
 	struct dcssblk_dev_info *dev_info;
 	int rc;
 
-	lock_kernel();
 	dev_info = bdev->bd_disk->private_data;
 	if (NULL == dev_info) {
 		rc = -ENODEV;
@@ -786,7 +784,6 @@
 	bdev->bd_block_size = 4096;
 	rc = 0;
 out:
-	unlock_kernel();
 	return rc;
 }
 
@@ -797,7 +794,6 @@
 	struct segment_info *entry;
 	int rc;
 
-	lock_kernel();
 	if (!dev_info) {
 		rc = -ENODEV;
 		goto out;
@@ -815,7 +811,6 @@
 	up_write(&dcssblk_devices_sem);
 	rc = 0;
 out:
-	unlock_kernel();
 	return rc;
 }
 
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index 857dfcb..eb28fb0 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -520,6 +520,7 @@
 	.compat_ioctl	 = fs3270_ioctl,	/* ioctl */
 	.open		 = fs3270_open,		/* open */
 	.release	 = fs3270_close,	/* release */
+	.llseek		= no_llseek,
 };
 
 /*
diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c
index e021ec6..5b8b859 100644
--- a/drivers/s390/char/monreader.c
+++ b/drivers/s390/char/monreader.c
@@ -447,6 +447,7 @@
 	.release = &mon_close,
 	.read    = &mon_read,
 	.poll    = &mon_poll,
+	.llseek  = noop_llseek,
 };
 
 static struct miscdevice mon_dev = {
diff --git a/drivers/s390/char/monwriter.c b/drivers/s390/char/monwriter.c
index 572a1e7..e0702d3 100644
--- a/drivers/s390/char/monwriter.c
+++ b/drivers/s390/char/monwriter.c
@@ -274,6 +274,7 @@
 	.open	 = &monwrite_open,
 	.release = &monwrite_close,
 	.write	 = &monwrite_write,
+	.llseek  = noop_llseek,
 };
 
 static struct miscdevice mon_dev = {
diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c
index f6d72e1..5707a80 100644
--- a/drivers/s390/char/sclp.c
+++ b/drivers/s390/char/sclp.c
@@ -468,7 +468,7 @@
 	cr0_sync &= 0xffff00a0;
 	cr0_sync |= 0x00000200;
 	__ctl_load(cr0_sync, 0, 0);
-	__raw_local_irq_stosm(0x01);
+	__arch_local_irq_stosm(0x01);
 	/* Loop until driver state indicates finished request */
 	while (sclp_running_state != sclp_running_state_idle) {
 		/* Check for expired request timer */
diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c
index 85cf607..f0fa9ca 100644
--- a/drivers/s390/char/tape_block.c
+++ b/drivers/s390/char/tape_block.c
@@ -16,7 +16,7 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/interrupt.h>
 #include <linux/buffer_head.h>
 #include <linux/kernel.h>
@@ -45,6 +45,7 @@
 /*
  * file operation structure for tape block frontend
  */
+static DEFINE_MUTEX(tape_block_mutex);
 static int tapeblock_open(struct block_device *, fmode_t);
 static int tapeblock_release(struct gendisk *, fmode_t);
 static int tapeblock_medium_changed(struct gendisk *);
@@ -361,7 +362,7 @@
 	struct tape_device *	device;
 	int			rc;
 
-	lock_kernel();
+	mutex_lock(&tape_block_mutex);
 	device = tape_get_device(disk->private_data);
 
 	if (device->required_tapemarks) {
@@ -385,14 +386,14 @@
 	 *       is called.
 	 */
 	tape_state_set(device, TS_BLKUSE);
-	unlock_kernel();
+	mutex_unlock(&tape_block_mutex);
 	return 0;
 
 release:
 	tape_release(device);
  put_device:
 	tape_put_device(device);
-	unlock_kernel();
+	mutex_unlock(&tape_block_mutex);
 	return rc;
 }
 
@@ -407,11 +408,11 @@
 {
 	struct tape_device *device = disk->private_data;
  
-	lock_kernel();
+	mutex_lock(&tape_block_mutex);
 	tape_state_set(device, TS_IN_USE);
 	tape_release(device);
 	tape_put_device(device);
-	unlock_kernel();
+	mutex_unlock(&tape_block_mutex);
 
 	return 0;
 }
diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c
index 539045a..883e2db 100644
--- a/drivers/s390/char/tape_char.c
+++ b/drivers/s390/char/tape_char.c
@@ -53,6 +53,7 @@
 #endif
 	.open = tapechar_open,
 	.release = tapechar_release,
+	.llseek = no_llseek,
 };
 
 static int tapechar_major = TAPECHAR_MAJOR;
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 04e532e..0e7cb1a 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -177,6 +177,7 @@
 	.write		= vmcp_write,
 	.unlocked_ioctl	= vmcp_ioctl,
 	.compat_ioctl	= vmcp_ioctl,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice vmcp_dev = {
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index e40a1b8..0d6dc4b 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -97,6 +97,7 @@
 	.open    = vmlogrdr_open,
 	.release = vmlogrdr_release,
 	.read    = vmlogrdr_read,
+	.llseek  = no_llseek,
 };
 
 
diff --git a/drivers/s390/char/vmwatchdog.c b/drivers/s390/char/vmwatchdog.c
index e13508c..12ef912 100644
--- a/drivers/s390/char/vmwatchdog.c
+++ b/drivers/s390/char/vmwatchdog.c
@@ -297,6 +297,7 @@
 	.unlocked_ioctl = &vmwdt_ioctl,
 	.write   = &vmwdt_write,
 	.owner   = THIS_MODULE,
+	.llseek  = noop_llseek,
 };
 
 static struct miscdevice vmwdt_dev = {
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index f5ea338..3b94044 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -459,6 +459,7 @@
 	.read		= zcore_memmap_read,
 	.open		= zcore_memmap_open,
 	.release	= zcore_memmap_release,
+	.llseek		= no_llseek,
 };
 
 static ssize_t zcore_reipl_write(struct file *filp, const char __user *buf,
@@ -486,6 +487,7 @@
 	.write		= zcore_reipl_write,
 	.open		= zcore_reipl_open,
 	.release	= zcore_reipl_release,
+	.llseek		= no_llseek,
 };
 
 #ifdef CONFIG_32BIT
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index a83877c..f2b77e7 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -806,6 +806,7 @@
 	.open = nonseekable_open,
 	.unlocked_ioctl = chsc_ioctl,
 	.compat_ioctl = chsc_ioctl,
+	.llseek = no_llseek,
 };
 
 static struct miscdevice chsc_misc_device = {
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index ac94ac75..ca8e1c2 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -1067,6 +1067,7 @@
 static const struct file_operations cio_settle_proc_fops = {
 	.open = nonseekable_open,
 	.write = cio_settle_write,
+	.llseek = no_llseek,
 };
 
 static int __init cio_settle_init(void)
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 41e0aae..f522174 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -897,7 +897,8 @@
 	.compat_ioctl	= zcrypt_compat_ioctl,
 #endif
 	.open		= zcrypt_open,
-	.release	= zcrypt_release
+	.release	= zcrypt_release,
+	.llseek		= no_llseek,
 };
 
 /*
diff --git a/drivers/s390/scsi/zfcp_cfdc.c b/drivers/s390/scsi/zfcp_cfdc.c
index fcbd2b7..1838cda 100644
--- a/drivers/s390/scsi/zfcp_cfdc.c
+++ b/drivers/s390/scsi/zfcp_cfdc.c
@@ -251,8 +251,9 @@
 	.open = nonseekable_open,
 	.unlocked_ioctl = zfcp_cfdc_dev_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl = zfcp_cfdc_dev_ioctl
+	.compat_ioctl = zfcp_cfdc_dev_ioctl,
 #endif
+	.llseek = no_llseek,
 };
 
 struct miscdevice zfcp_cfdc_misc = {
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index cb000c9..208256e 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -681,6 +681,7 @@
 	    adapter->adapter_features & FSF_FEATURE_DIX_PROT_TCPIP) {
 		mask |= SHOST_DIX_TYPE1_PROTECTION;
 		scsi_host_set_guard(shost, SHOST_DIX_GUARD_IP);
+		shost->sg_prot_tablesize = ZFCP_QDIO_MAX_SBALES_PER_REQ / 2;
 		shost->sg_tablesize = ZFCP_QDIO_MAX_SBALES_PER_REQ / 2;
 		shost->max_sectors = ZFCP_QDIO_MAX_SBALES_PER_REQ * 8 / 2;
 	}
diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c
index 1690e53..55f71ea 100644
--- a/drivers/sbus/char/display7seg.c
+++ b/drivers/sbus/char/display7seg.c
@@ -162,6 +162,7 @@
 	.compat_ioctl =		d7s_ioctl,
 	.open =			d7s_open,
 	.release =		d7s_release,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice d7s_miscdev = {
diff --git a/drivers/sbus/char/envctrl.c b/drivers/sbus/char/envctrl.c
index 078e5f4..8ce414e 100644
--- a/drivers/sbus/char/envctrl.c
+++ b/drivers/sbus/char/envctrl.c
@@ -720,6 +720,7 @@
 #endif
 	.open =			envctrl_open,
 	.release =		envctrl_release,
+	.llseek =		noop_llseek,
 };	
 
 static struct miscdevice envctrl_dev = {
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
index 4942050..13f48e2 100644
--- a/drivers/sbus/char/jsflash.c
+++ b/drivers/sbus/char/jsflash.c
@@ -27,7 +27,7 @@
  */
 
 #include <linux/module.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/miscdevice.h>
@@ -68,6 +68,8 @@
 #define JSF_PART_BITS	 2	/* 2 bits of minors to cover JSF_NPART */
 #define JSF_PART_MASK	 0x3	/* 2 bits mask */
 
+static DEFINE_MUTEX(jsf_mutex);
+
 /*
  * Access functions.
  * We could ioremap(), but it's easier this way.
@@ -225,7 +227,7 @@
 {
 	loff_t ret;
 
-	lock_kernel();
+	mutex_lock(&jsf_mutex);
 	switch (orig) {
 		case 0:
 			file->f_pos = offset;
@@ -238,7 +240,7 @@
 		default:
 			ret = -EINVAL;
 	}
-	unlock_kernel();
+	mutex_unlock(&jsf_mutex);
 	return ret;
 }
 
@@ -384,18 +386,18 @@
 
 static long jsf_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 {
-	lock_kernel();
+	mutex_lock(&jsf_mutex);
 	int error = -ENOTTY;
 	void __user *argp = (void __user *)arg;
 
 	if (!capable(CAP_SYS_ADMIN)) {
-		unlock_kernel();
+		mutex_unlock(&jsf_mutex);
 		return -EPERM;
 	}
 	switch (cmd) {
 	case JSFLASH_IDENT:
 		if (copy_to_user(argp, &jsf0.id, JSFIDSZ)) {
-			unlock_kernel();
+			mutex_unlock(&jsf_mutex);
 			return -EFAULT;
 		}
 		break;
@@ -407,7 +409,7 @@
 		break;
 	}
 
-	unlock_kernel();
+	mutex_unlock(&jsf_mutex);
 	return error;
 }
 
@@ -418,17 +420,17 @@
 
 static int jsf_open(struct inode * inode, struct file * filp)
 {
-	lock_kernel();
+	mutex_lock(&jsf_mutex);
 	if (jsf0.base == 0) {
-		unlock_kernel();
+		mutex_unlock(&jsf_mutex);
 		return -ENXIO;
 	}
 	if (test_and_set_bit(0, (void *)&jsf0.busy) != 0) {
-		unlock_kernel();
+		mutex_unlock(&jsf_mutex);
 		return -EBUSY;
 	}
 
-	unlock_kernel();
+	mutex_unlock(&jsf_mutex);
 	return 0;	/* XXX What security? */
 }
 
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index e20b7bd..fcf08b3 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -92,7 +92,6 @@
 #include <linux/pci.h>
 #include <linux/time.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/irq.h>
@@ -105,6 +104,7 @@
 
 /* Globals */
 #define TW_DRIVER_VERSION "2.26.02.014"
+static DEFINE_MUTEX(twa_chrdev_mutex);
 static TW_Device_Extension *twa_device_extension_list[TW_MAX_SLOT];
 static unsigned int twa_device_extension_count;
 static int twa_major = -1;
@@ -222,7 +222,8 @@
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= twa_chrdev_ioctl,
 	.open		= twa_chrdev_open,
-	.release	= NULL
+	.release	= NULL,
+	.llseek		= noop_llseek,
 };
 
 /* This function will complete an aen request from the isr */
@@ -658,7 +659,7 @@
 	int retval = TW_IOCTL_ERROR_OS_EFAULT;
 	void __user *argp = (void __user *)arg;
 
-	lock_kernel();
+	mutex_lock(&twa_chrdev_mutex);
 
 	/* Only let one of these through at a time */
 	if (mutex_lock_interruptible(&tw_dev->ioctl_lock)) {
@@ -879,7 +880,7 @@
 out2:
 	mutex_unlock(&tw_dev->ioctl_lock);
 out:
-	unlock_kernel();
+	mutex_unlock(&twa_chrdev_mutex);
 	return retval;
 } /* End twa_chrdev_ioctl() */
 
@@ -890,7 +891,6 @@
 	unsigned int minor_number;
 	int retval = TW_IOCTL_ERROR_OS_ENODEV;
 
-	cycle_kernel_lock();
 	minor_number = iminor(inode);
 	if (minor_number >= twa_device_extension_count)
 		goto out;
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index f481e73..6a95d11 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -64,7 +64,6 @@
 #include <linux/pci.h>
 #include <linux/time.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/irq.h>
@@ -77,6 +76,7 @@
 
 /* Globals */
 #define TW_DRIVER_VERSION "3.26.02.000"
+static DEFINE_MUTEX(twl_chrdev_mutex);
 static TW_Device_Extension *twl_device_extension_list[TW_MAX_SLOT];
 static unsigned int twl_device_extension_count;
 static int twl_major = -1;
@@ -764,7 +764,7 @@
 	int retval = -EFAULT;
 	void __user *argp = (void __user *)arg;
 
-	lock_kernel();
+	mutex_lock(&twl_chrdev_mutex);
 
 	/* Only let one of these through at a time */
 	if (mutex_lock_interruptible(&tw_dev->ioctl_lock)) {
@@ -861,7 +861,7 @@
 out2:
 	mutex_unlock(&tw_dev->ioctl_lock);
 out:
-	unlock_kernel();
+	mutex_unlock(&twl_chrdev_mutex);
 	return retval;
 } /* End twl_chrdev_ioctl() */
 
@@ -876,7 +876,6 @@
 		goto out;
 	}
 
-	cycle_kernel_lock();
 	minor_number = iminor(inode);
 	if (minor_number >= twl_device_extension_count)
 		goto out;
@@ -890,7 +889,8 @@
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= twl_chrdev_ioctl,
 	.open		= twl_chrdev_open,
-	.release	= NULL
+	.release	= NULL,
+	.llseek		= noop_llseek,
 };
 
 /* This function passes sense data from firmware to scsi layer */
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 30d735a..b112534 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -199,7 +199,6 @@
 
 #include <linux/module.h>
 #include <linux/reboot.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/moduleparam.h>
@@ -221,6 +220,7 @@
 
 /* Globals */
 #define TW_DRIVER_VERSION "1.26.02.003"
+static DEFINE_MUTEX(tw_mutex);
 static TW_Device_Extension *tw_device_extension_list[TW_MAX_SLOT];
 static int tw_device_extension_count = 0;
 static int twe_major = -1;
@@ -900,10 +900,10 @@
 
 	dprintk(KERN_WARNING "3w-xxxx: tw_chrdev_ioctl()\n");
 
-	lock_kernel();
+	mutex_lock(&tw_mutex);
 	/* Only let one of these through at a time */
 	if (mutex_lock_interruptible(&tw_dev->ioctl_lock)) {
-		unlock_kernel();
+		mutex_unlock(&tw_mutex);
 		return -EINTR;
 	}
 
@@ -1034,7 +1034,7 @@
 	dma_free_coherent(&tw_dev->tw_pci_dev->dev, data_buffer_length_adjusted+sizeof(TW_New_Ioctl) - 1, cpu_addr, dma_handle);
 out:
 	mutex_unlock(&tw_dev->ioctl_lock);
-	unlock_kernel();
+	mutex_unlock(&tw_mutex);
 	return retval;
 } /* End tw_chrdev_ioctl() */
 
@@ -1044,7 +1044,6 @@
 {
 	unsigned int minor_number;
 
-	cycle_kernel_lock();
 	dprintk(KERN_WARNING "3w-xxxx: tw_ioctl_open()\n");
 
 	minor_number = iminor(inode);
@@ -1059,7 +1058,8 @@
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= tw_chrdev_ioctl,
 	.open		= tw_chrdev_open,
-	.release	= NULL
+	.release	= NULL,
+	.llseek		= noop_llseek,
 };
 
 /* This function will free up device extension resources */
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index cad6f9a..dae46d7 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -38,7 +38,7 @@
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/syscalls.h>
 #include <linux/delay.h>
@@ -76,6 +76,7 @@
 MODULE_LICENSE("GPL");
 MODULE_VERSION(AAC_DRIVER_FULL_VERSION);
 
+static DEFINE_MUTEX(aac_mutex);
 static LIST_HEAD(aac_devices);
 static int aac_cfg_major = -1;
 char aac_driver_version[] = AAC_DRIVER_FULL_VERSION;
@@ -678,7 +679,7 @@
 	unsigned minor_number = iminor(inode);
 	int err = -ENODEV;
 
-	lock_kernel();  /* BKL pushdown: nothing else protects this list */
+	mutex_lock(&aac_mutex);  /* BKL pushdown: nothing else protects this list */
 	list_for_each_entry(aac, &aac_devices, entry) {
 		if (aac->id == minor_number) {
 			file->private_data = aac;
@@ -686,7 +687,7 @@
 			break;
 		}
 	}
-	unlock_kernel();
+	mutex_unlock(&aac_mutex);
 
 	return err;
 }
@@ -711,9 +712,9 @@
 	int ret;
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
-	lock_kernel();
+	mutex_lock(&aac_mutex);
 	ret = aac_do_ioctl(file->private_data, cmd, (void __user *)arg);
-	unlock_kernel();
+	mutex_unlock(&aac_mutex);
 
 	return ret;
 }
@@ -722,7 +723,7 @@
 static long aac_compat_do_ioctl(struct aac_dev *dev, unsigned cmd, unsigned long arg)
 {
 	long ret;
-	lock_kernel();
+	mutex_lock(&aac_mutex);
 	switch (cmd) {
 	case FSACTL_MINIPORT_REV_CHECK:
 	case FSACTL_SENDFIB:
@@ -756,7 +757,7 @@
 		ret = -ENOIOCTLCMD;
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&aac_mutex);
 	return ret;
 }
 
@@ -1039,6 +1040,7 @@
 	.compat_ioctl   = aac_compat_cfg_ioctl,
 #endif
 	.open		= aac_cfg_open,
+	.llseek		= noop_llseek,
 };
 
 static struct scsi_host_template aac_driver_template = {
diff --git a/drivers/scsi/aic7xxx_old.c b/drivers/scsi/aic7xxx_old.c
index 93984c9..aee73fa 100644
--- a/drivers/scsi/aic7xxx_old.c
+++ b/drivers/scsi/aic7xxx_old.c
@@ -2850,12 +2850,6 @@
       aic_dev->r_total++;
       ptr = aic_dev->r_bins;
     }
-    if(cmd->device->simple_tags && cmd->request->cmd_flags & REQ_HARDBARRIER)
-    {
-      aic_dev->barrier_total++;
-      if(scb->tag_action == MSG_ORDERED_Q_TAG)
-        aic_dev->ordered_total++;
-    }
     x = scb->sg_length;
     x >>= 10;
     for(i=0; i<6; i++)
@@ -10125,7 +10119,6 @@
   struct aic_dev_data *aic_dev = cmd->device->hostdata;
   struct scsi_device *sdptr = cmd->device;
   unsigned char tindex = TARGET_INDEX(cmd);
-  struct request *req = cmd->request;
   int use_sg;
 
   mask = (0x01 << tindex);
@@ -10144,19 +10137,8 @@
     /* We always force TEST_UNIT_READY to untagged */
     if (cmd->cmnd[0] != TEST_UNIT_READY && sdptr->simple_tags)
     {
-      if (req->cmd_flags & REQ_HARDBARRIER)
-      {
-	if(sdptr->ordered_tags)
-	{
-          hscb->control |= MSG_ORDERED_Q_TAG;
-          scb->tag_action = MSG_ORDERED_Q_TAG;
-	}
-      }
-      else
-      {
-        hscb->control |= MSG_SIMPLE_Q_TAG;
-        scb->tag_action = MSG_SIMPLE_Q_TAG;
-      }
+      hscb->control |= MSG_SIMPLE_Q_TAG;
+      scb->tag_action = MSG_SIMPLE_Q_TAG;
     }
   }
   if ( !(aic_dev->dtr_pending) &&
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index d653218..a15474e 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -22,7 +22,6 @@
 #include <linux/chio.h>			/* here are all the ioctls */
 #include <linux/mutex.h>
 #include <linux/idr.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 
 #include <scsi/scsi.h>
@@ -44,6 +43,7 @@
 MODULE_ALIAS_CHARDEV_MAJOR(SCSI_CHANGER_MAJOR);
 MODULE_ALIAS_SCSI_DEVICE(TYPE_MEDIUM_CHANGER);
 
+static DEFINE_MUTEX(ch_mutex);
 static int init = 1;
 module_param(init, int, 0444);
 MODULE_PARM_DESC(init, \
@@ -581,19 +581,19 @@
 	scsi_changer *ch;
 	int minor = iminor(inode);
 
-	lock_kernel();
+	mutex_lock(&ch_mutex);
 	spin_lock(&ch_index_lock);
 	ch = idr_find(&ch_index_idr, minor);
 
 	if (NULL == ch || scsi_device_get(ch->device)) {
 		spin_unlock(&ch_index_lock);
-		unlock_kernel();
+		mutex_unlock(&ch_mutex);
 		return -ENXIO;
 	}
 	spin_unlock(&ch_index_lock);
 
 	file->private_data = ch;
-	unlock_kernel();
+	mutex_unlock(&ch_mutex);
 	return 0;
 }
 
@@ -981,6 +981,7 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ch_ioctl_compat,
 #endif
+	.llseek		= noop_llseek,
 };
 
 static int __init init_ch_module(void)
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index ffc1edf..23dec00 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -49,7 +49,6 @@
 #include <linux/kernel.h>	/* for printk */
 #include <linux/sched.h>
 #include <linux/reboot.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/dma-mapping.h>
 
@@ -76,6 +75,7 @@
  * Needed for our management apps
  *============================================================================
  */
+static DEFINE_MUTEX(adpt_mutex);
 static dpt_sig_S DPTI_sig = {
 	{'d', 'P', 't', 'S', 'i', 'G'}, SIG_VERSION,
 #ifdef __i386__
@@ -126,6 +126,7 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= compat_adpt_ioctl,
 #endif
+	.llseek		= noop_llseek,
 };
 
 /* Structures and definitions for synchronous message posting.
@@ -1732,12 +1733,12 @@
 	int minor;
 	adpt_hba* pHba;
 
-	lock_kernel();
+	mutex_lock(&adpt_mutex);
 	//TODO check for root access
 	//
 	minor = iminor(inode);
 	if (minor >= hba_count) {
-		unlock_kernel();
+		mutex_unlock(&adpt_mutex);
 		return -ENXIO;
 	}
 	mutex_lock(&adpt_configuration_lock);
@@ -1748,7 +1749,7 @@
 	}
 	if (pHba == NULL) {
 		mutex_unlock(&adpt_configuration_lock);
-		unlock_kernel();
+		mutex_unlock(&adpt_mutex);
 		return -ENXIO;
 	}
 
@@ -1759,7 +1760,7 @@
 
 	pHba->in_use = 1;
 	mutex_unlock(&adpt_configuration_lock);
-	unlock_kernel();
+	mutex_unlock(&adpt_mutex);
 
 	return 0;
 }
@@ -2160,9 +2161,9 @@
  
 	inode = file->f_dentry->d_inode;
  
-	lock_kernel();
+	mutex_lock(&adpt_mutex);
 	ret = adpt_ioctl(inode, file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&adpt_mutex);
 
 	return ret;
 }
@@ -2176,7 +2177,7 @@
  
 	inode = file->f_dentry->d_inode;
  
-	lock_kernel();
+	mutex_lock(&adpt_mutex);
  
 	switch(cmd) {
 		case DPT_SIGNATURE:
@@ -2194,7 +2195,7 @@
 			ret =  -ENOIOCTLCMD;
 	}
  
-	unlock_kernel();
+	mutex_unlock(&adpt_mutex);
  
 	return ret;
 }
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index b860d65..5a3f931 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -120,7 +120,7 @@
 #include <linux/timer.h>
 #include <linux/dma-mapping.h>
 #include <linux/list.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 
 #ifdef GDTH_RTC
@@ -140,6 +140,7 @@
 #include <scsi/scsi_host.h>
 #include "gdth.h"
 
+static DEFINE_MUTEX(gdth_mutex);
 static void gdth_delay(int milliseconds);
 static void gdth_eval_mapping(u32 size, u32 *cyls, int *heads, int *secs);
 static irqreturn_t gdth_interrupt(int irq, void *dev_id);
@@ -372,6 +373,7 @@
     .unlocked_ioctl   = gdth_unlocked_ioctl,
     .open    = gdth_open,
     .release = gdth_close,
+    .llseek = noop_llseek,
 };
 
 #include "gdth_proc.h"
@@ -4042,12 +4044,12 @@
 {
     gdth_ha_str *ha;
 
-    lock_kernel();
+    mutex_lock(&gdth_mutex);
     list_for_each_entry(ha, &gdth_instances, list) {
         if (!ha->sdev)
             ha->sdev = scsi_get_host_dev(ha->shost);
     }
-    unlock_kernel();
+    mutex_unlock(&gdth_mutex);
 
     TRACE(("gdth_open()\n"));
     return 0;
@@ -4615,9 +4617,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&gdth_mutex);
 	ret = gdth_ioctl(file, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&gdth_mutex);
 
 	return ret;
 }
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 8a8f803..1047815 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -376,6 +376,7 @@
 	shost->this_id = sht->this_id;
 	shost->can_queue = sht->can_queue;
 	shost->sg_tablesize = sht->sg_tablesize;
+	shost->sg_prot_tablesize = sht->sg_prot_tablesize;
 	shost->cmd_per_lun = sht->cmd_per_lun;
 	shost->unchecked_isa_dma = sht->unchecked_isa_dma;
 	shost->use_clustering = sht->use_clustering;
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index f0cfba9..535085c 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -130,17 +130,6 @@
 	sc->scsi_done(sc);
 }
 
-static enum task_attribute sas_scsi_get_task_attr(struct scsi_cmnd *cmd)
-{
-	enum task_attribute ta = TASK_ATTR_SIMPLE;
-	if (cmd->request && blk_rq_tagged(cmd->request)) {
-		if (cmd->device->ordered_tags &&
-		    (cmd->request->cmd_flags & REQ_HARDBARRIER))
-			ta = TASK_ATTR_ORDERED;
-	}
-	return ta;
-}
-
 static struct sas_task *sas_create_task(struct scsi_cmnd *cmd,
 					       struct domain_device *dev,
 					       gfp_t gfp_flags)
@@ -160,7 +149,7 @@
 	task->ssp_task.retry_count = 1;
 	int_to_scsilun(cmd->device->lun, &lun);
 	memcpy(task->ssp_task.LUN, &lun.scsi_lun, 8);
-	task->ssp_task.task_attr = sas_scsi_get_task_attr(cmd);
+	task->ssp_task.task_attr = TASK_ATTR_SIMPLE;
 	memcpy(task->ssp_task.cdb, cmd->cmnd, 16);
 
 	task->scatter = scsi_sglist(cmd);
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 0b6e322..7ceb5cf 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -46,7 +46,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <scsi/scsicam.h>
 
@@ -62,6 +62,7 @@
 MODULE_LICENSE ("GPL");
 MODULE_VERSION(MEGARAID_MODULE_VERSION);
 
+static DEFINE_MUTEX(megadev_mutex);
 static unsigned int max_cmd_per_lun = DEF_CMD_PER_LUN;
 module_param(max_cmd_per_lun, uint, 0);
 MODULE_PARM_DESC(max_cmd_per_lun, "Maximum number of commands which can be issued to a single LUN (default=DEF_CMD_PER_LUN=63)");
@@ -101,6 +102,7 @@
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= megadev_unlocked_ioctl,
 	.open		= megadev_open,
+	.llseek		= noop_llseek,
 };
 
 /*
@@ -3282,7 +3284,6 @@
 static int
 megadev_open (struct inode *inode, struct file *filep)
 {
-	cycle_kernel_lock();
 	/*
 	 * Only allow superuser to access private ioctl interface
 	 */
@@ -3701,9 +3702,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&megadev_mutex);
 	ret = megadev_ioctl(filep, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&megadev_mutex);
 
 	return ret;
 }
diff --git a/drivers/scsi/megaraid/megaraid_mm.c b/drivers/scsi/megaraid/megaraid_mm.c
index 41f82f7..a7008c0 100644
--- a/drivers/scsi/megaraid/megaraid_mm.c
+++ b/drivers/scsi/megaraid/megaraid_mm.c
@@ -16,11 +16,12 @@
  */
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include "megaraid_mm.h"
 
 
 // Entry points for char node driver
+static DEFINE_MUTEX(mraid_mm_mutex);
 static int mraid_mm_open(struct inode *, struct file *);
 static long mraid_mm_unlocked_ioctl(struct file *, uint, unsigned long);
 
@@ -75,6 +76,7 @@
 	.compat_ioctl = mraid_mm_compat_ioctl,
 #endif
 	.owner	= THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice megaraid_mm_dev = {
@@ -98,7 +100,6 @@
 	 */
 	if (!capable(CAP_SYS_ADMIN)) return (-EACCES);
 
-	cycle_kernel_lock();
 	return 0;
 }
 
@@ -224,9 +225,9 @@
 	int err;
 
 	/* inconsistant: mraid_mm_compat_ioctl doesn't take the BKL */
-	lock_kernel();
+	mutex_lock(&mraid_mm_mutex);
 	err = mraid_mm_ioctl(filep, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&mraid_mm_mutex);
 
 	return err;
 }
diff --git a/drivers/scsi/megaraid/megaraid_sas.c b/drivers/scsi/megaraid/megaraid_sas.c
index 99e4478..51e2579a 100644
--- a/drivers/scsi/megaraid/megaraid_sas.c
+++ b/drivers/scsi/megaraid/megaraid_sas.c
@@ -33,7 +33,6 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
-#include <linux/smp_lock.h>
 #include <linux/uio.h>
 #include <linux/slab.h>
 #include <asm/uaccess.h>
@@ -3557,7 +3556,6 @@
  */
 static int megasas_mgmt_open(struct inode *inode, struct file *filep)
 {
-	cycle_kernel_lock();
 	/*
 	 * Allow only those users with admin rights
 	 */
@@ -3957,6 +3955,7 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = megasas_mgmt_compat_ioctl,
 #endif
+	.llseek = noop_llseek,
 };
 
 /*
diff --git a/drivers/scsi/mpt2sas/mpt2sas_ctl.c b/drivers/scsi/mpt2sas/mpt2sas_ctl.c
index b774973..40cb8ae 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_ctl.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_ctl.c
@@ -51,7 +51,7 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/delay.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/compat.h>
 #include <linux/poll.h>
 
@@ -61,6 +61,7 @@
 #include "mpt2sas_base.h"
 #include "mpt2sas_ctl.h"
 
+static DEFINE_MUTEX(_ctl_mutex);
 static struct fasync_struct *async_queue;
 static DECLARE_WAIT_QUEUE_HEAD(ctl_poll_wait);
 
@@ -2238,9 +2239,9 @@
 {
 	long ret;
 
-	lock_kernel();
+	mutex_lock(&_ctl_mutex);
 	ret = _ctl_ioctl_main(file, cmd, (void __user *)arg);
-	unlock_kernel();
+	mutex_unlock(&_ctl_mutex);
 	return ret;
 }
 
@@ -2309,12 +2310,12 @@
 {
 	long ret;
 
-	lock_kernel();
+	mutex_lock(&_ctl_mutex);
 	if (cmd == MPT2COMMAND32)
 		ret = _ctl_compat_mpt_command(file, cmd, arg);
 	else
 		ret = _ctl_ioctl_main(file, cmd, (void __user *)arg);
-	unlock_kernel();
+	mutex_unlock(&_ctl_mutex);
 	return ret;
 }
 #endif
@@ -2952,6 +2953,7 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = _ctl_ioctl_compat,
 #endif
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice ctl_dev = {
diff --git a/drivers/scsi/osd/osd_uld.c b/drivers/scsi/osd/osd_uld.c
index ffdd9fd..b31a8e3 100644
--- a/drivers/scsi/osd/osd_uld.c
+++ b/drivers/scsi/osd/osd_uld.c
@@ -182,6 +182,7 @@
 	.open           = osd_uld_open,
 	.release        = osd_uld_release,
 	.unlocked_ioctl = osd_uld_ioctl,
+	.llseek		= noop_llseek,
 };
 
 struct osd_dev *osduld_path_lookup(const char *name)
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 278b352..54de1d1 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -51,7 +51,7 @@
 #include <linux/moduleparam.h>
 #include <linux/delay.h>
 #include <linux/jiffies.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <asm/uaccess.h>
 #include <asm/dma.h>
 #include <asm/system.h>
@@ -80,6 +80,7 @@
 #include "osst_options.h"
 #include "osst_detect.h"
 
+static DEFINE_MUTEX(osst_int_mutex);
 static int max_dev = 0;
 static int write_threshold_kbs = 0;
 static int max_sg_segs = 0;
@@ -4807,9 +4808,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&osst_int_mutex);
 	ret = __os_scsi_tape_open(inode, filp);
-	unlock_kernel();
+	mutex_unlock(&osst_int_mutex);
 	return ret;
 }
 
@@ -4943,9 +4944,9 @@
 	char		    * name  = tape_name(STp);
 	void	    __user  * p     = (void __user *)arg;
 
-	lock_kernel();
+	mutex_lock(&osst_int_mutex);
 	if (mutex_lock_interruptible(&STp->lock)) {
-		unlock_kernel();
+		mutex_unlock(&osst_int_mutex);
 		return -ERESTARTSYS;
 	}
 
@@ -5260,14 +5261,14 @@
 	mutex_unlock(&STp->lock);
 
 	retval = scsi_ioctl(STp->device, cmd_in, p);
-	unlock_kernel();
+	mutex_unlock(&osst_int_mutex);
 	return retval;
 
 out:
 	if (SRpnt) osst_release_request(SRpnt);
 
 	mutex_unlock(&STp->lock);
-	unlock_kernel();
+	mutex_unlock(&osst_int_mutex);
 
 	return retval;
 }
diff --git a/drivers/scsi/pcmcia/aha152x_stub.c b/drivers/scsi/pcmcia/aha152x_stub.c
index 61f49bd..e77dd02 100644
--- a/drivers/scsi/pcmcia/aha152x_stub.c
+++ b/drivers/scsi/pcmcia/aha152x_stub.c
@@ -49,7 +49,6 @@
 #include <scsi/scsi_host.h>
 #include "aha152x.h"
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -86,8 +85,6 @@
 static void aha152x_detach(struct pcmcia_device *p_dev);
 static int aha152x_config_cs(struct pcmcia_device *link);
 
-static struct pcmcia_device *dev_list;
-
 static int aha152x_probe(struct pcmcia_device *link)
 {
     scsi_info_t *info;
@@ -100,11 +97,8 @@
     info->p_dev = link;
     link->priv = info;
 
-    link->resource[0]->end = 0x20;
-    link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-    link->conf.Attributes = CONF_ENABLE_IRQ;
-    link->conf.IntType = INT_MEMORY_AND_IO;
-    link->conf.Present = PRESENT_OPTION;
+    link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+    link->config_regs = PRESENT_OPTION;
 
     return aha152x_config_cs(link);
 } /* aha152x_attach */
@@ -123,25 +117,24 @@
 
 /*====================================================================*/
 
-static int aha152x_config_check(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
-				void *priv_data)
+static int aha152x_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
 	p_dev->io_lines = 10;
+
 	/* For New Media T&J, look for a SCSI window */
-	if (cfg->io.win[0].len >= 0x20)
-		p_dev->resource[0]->start = cfg->io.win[0].base;
-	else if ((cfg->io.nwin > 1) &&
-		 (cfg->io.win[1].len >= 0x20))
-		p_dev->resource[0]->start = cfg->io.win[1].base;
-	if ((cfg->io.nwin > 0) &&
-	    (p_dev->resource[0]->start < 0xffff)) {
-		if (!pcmcia_request_io(p_dev))
-			return 0;
-	}
-	return -EINVAL;
+	if ((p_dev->resource[0]->end < 0x20) &&
+		(p_dev->resource[1]->end >= 0x20))
+		p_dev->resource[0]->start = p_dev->resource[1]->start;
+
+	if (p_dev->resource[0]->start >= 0xffff)
+		return -EINVAL;
+
+	p_dev->resource[1]->start = p_dev->resource[1]->end = 0;
+	p_dev->resource[0]->end = 0x20;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
+
+	return pcmcia_request_io(p_dev);
 }
 
 static int aha152x_config_cs(struct pcmcia_device *link)
@@ -160,7 +153,7 @@
     if (!link->irq)
 	    goto failed;
 
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
     
@@ -221,9 +214,7 @@
 
 static struct pcmcia_driver aha152x_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "aha152x_cs",
-	},
+	.name		= "aha152x_cs",
 	.probe		= aha152x_probe,
 	.remove		= aha152x_detach,
 	.id_table       = aha152x_ids,
@@ -238,7 +229,6 @@
 static void __exit exit_aha152x_cs(void)
 {
 	pcmcia_unregister_driver(&aha152x_cs_driver);
-	BUG_ON(dev_list != NULL);
 }
 
 module_init(init_aha152x_cs);
diff --git a/drivers/scsi/pcmcia/fdomain_stub.c b/drivers/scsi/pcmcia/fdomain_stub.c
index 13dbe5c..cd69c26 100644
--- a/drivers/scsi/pcmcia/fdomain_stub.c
+++ b/drivers/scsi/pcmcia/fdomain_stub.c
@@ -46,7 +46,6 @@
 #include <scsi/scsi_host.h>
 #include "fdomain.h"
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -83,11 +82,8 @@
 
 	info->p_dev = link;
 	link->priv = info;
-	link->resource[0]->end = 0x10;
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-	link->conf.Present = PRESENT_OPTION;
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+	link->config_regs = PRESENT_OPTION;
 
 	return fdomain_config(link);
 } /* fdomain_attach */
@@ -105,14 +101,12 @@
 
 /*====================================================================*/
 
-static int fdomain_config_check(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
-				void *priv_data)
+static int fdomain_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
 	p_dev->io_lines = 10;
-	p_dev->resource[0]->start = cfg->io.win[0].base;
+	p_dev->resource[0]->end = 0x10;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 	return pcmcia_request_io(p_dev);
 }
 
@@ -132,7 +126,7 @@
 
     if (!link->irq)
 	    goto failed;
-    ret = pcmcia_request_configuration(link, &link->conf);
+    ret = pcmcia_enable_device(link);
     if (ret)
 	    goto failed;
 
@@ -194,9 +188,7 @@
 
 static struct pcmcia_driver fdomain_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "fdomain_cs",
-	},
+	.name		= "fdomain_cs",
 	.probe		= fdomain_probe,
 	.remove		= fdomain_detach,
 	.id_table       = fdomain_ids,
diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c
index dd9b403..9326c2c 100644
--- a/drivers/scsi/pcmcia/nsp_cs.c
+++ b/drivers/scsi/pcmcia/nsp_cs.c
@@ -47,7 +47,6 @@
 #include <scsi/scsi.h>
 #include <scsi/scsi_ioctl.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -1531,15 +1530,6 @@
   PCMCIA functions
 **********************************************************************/
 
-/*======================================================================
-    nsp_cs_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-======================================================================*/
 static int nsp_cs_probe(struct pcmcia_device *link)
 {
 	scsi_info_t  *info;
@@ -1557,14 +1547,6 @@
 
 	nsp_dbg(NSP_DEBUG_INIT, "info=0x%p", info);
 
-	/* The io structure describes IO port mapping */
-	link->resource[0]->end	 = 0x10;
-	link->resource[0]->flags = IO_DATA_PATH_WIDTH_AUTO;
-
-	/* General socket configuration */
-	link->conf.Attributes	 = CONF_ENABLE_IRQ;
-	link->conf.IntType	 = INT_MEMORY_AND_IO;
-
 	ret = nsp_cs_config(link);
 
 	nsp_dbg(NSP_DEBUG_INIT, "link=0x%p", link);
@@ -1572,12 +1554,6 @@
 } /* nsp_cs_attach */
 
 
-/*======================================================================
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.	 If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-======================================================================*/
 static void nsp_cs_detach(struct pcmcia_device *link)
 {
 	nsp_dbg(NSP_DEBUG_INIT, "in, link=0x%p", link);
@@ -1590,98 +1566,36 @@
 } /* nsp_cs_detach */
 
 
-/*======================================================================
-    nsp_cs_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    ethernet device available to the system.
-======================================================================*/
-
-struct nsp_cs_configdata {
-	nsp_hw_data		*data;
-	win_req_t		req;
-};
-
-static int nsp_cs_config_check(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cfg,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int nsp_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	struct nsp_cs_configdata *cfg_mem = priv_data;
+	nsp_hw_data		*data = priv_data;
 
-	if (cfg->index == 0)
+	if (p_dev->config_index == 0)
 		return -ENODEV;
 
-	/* Does this card need audio output? */
-	if (cfg->flags & CISTPL_CFTABLE_AUDIO) {
-		p_dev->conf.Attributes |= CONF_ENABLE_SPKR;
-		p_dev->conf.Status = CCSR_AUDIO_ENA;
+	/* This reserves IO space but doesn't actually enable it */
+	if (pcmcia_request_io(p_dev) != 0)
+		goto next_entry;
+
+	if (resource_size(p_dev->resource[2])) {
+		p_dev->resource[2]->flags |= (WIN_DATA_WIDTH_16 |
+					WIN_MEMORY_TYPE_CM |
+					WIN_ENABLE);
+		if (p_dev->resource[2]->end < 0x1000)
+			p_dev->resource[2]->end = 0x1000;
+		if (pcmcia_request_window(p_dev, p_dev->resource[2], 0) != 0)
+			goto next_entry;
+		if (pcmcia_map_mem_page(p_dev, p_dev->resource[2],
+						p_dev->card_addr) != 0)
+			goto next_entry;
+
+		data->MmioAddress = (unsigned long)
+			ioremap_nocache(p_dev->resource[2]->start,
+					resource_size(p_dev->resource[2]));
+		data->MmioLength  = resource_size(p_dev->resource[2]);
 	}
-
-	/* Use power settings for Vcc and Vpp if present */
-	/*  Note that the CIS values need to be rescaled */
-	if (cfg->vcc.present & (1<<CISTPL_POWER_VNOM)) {
-		if (vcc != cfg->vcc.param[CISTPL_POWER_VNOM]/10000)
-			return -ENODEV;
-		else if (dflt->vcc.present & (1<<CISTPL_POWER_VNOM)) {
-			if (vcc != dflt->vcc.param[CISTPL_POWER_VNOM]/10000)
-				return -ENODEV;
-		}
-
-		if (cfg->vpp1.present & (1 << CISTPL_POWER_VNOM)) {
-			p_dev->conf.Vpp =
-				cfg->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-		} else if (dflt->vpp1.present & (1 << CISTPL_POWER_VNOM)) {
-			p_dev->conf.Vpp =
-				dflt->vpp1.param[CISTPL_POWER_VNOM] / 10000;
-		}
-
-		/* Do we need to allocate an interrupt? */
-		p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-		/* IO window settings */
-		p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-		if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-			cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-			p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-			p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-			p_dev->resource[0]->flags |=
-				pcmcia_io_cfg_data_width(io->flags);
-			p_dev->resource[0]->start = io->win[0].base;
-			p_dev->resource[0]->end = io->win[0].len;
-			if (io->nwin > 1) {
-				p_dev->resource[1]->flags =
-					p_dev->resource[0]->flags;
-				p_dev->resource[1]->start = io->win[1].base;
-				p_dev->resource[1]->end = io->win[1].len;
-			}
-			/* This reserves IO space but doesn't actually enable it */
-			if (pcmcia_request_io(p_dev) != 0)
-				goto next_entry;
-		}
-
-		if ((cfg->mem.nwin > 0) || (dflt->mem.nwin > 0)) {
-			cistpl_mem_t	*mem =
-				(cfg->mem.nwin) ? &cfg->mem : &dflt->mem;
-			cfg_mem->req.Attributes = WIN_DATA_WIDTH_16|WIN_MEMORY_TYPE_CM;
-			cfg_mem->req.Attributes |= WIN_ENABLE;
-			cfg_mem->req.Base = mem->win[0].host_addr;
-			cfg_mem->req.Size = mem->win[0].len;
-			if (cfg_mem->req.Size < 0x1000)
-				cfg_mem->req.Size = 0x1000;
-			cfg_mem->req.AccessSpeed = 0;
-			if (pcmcia_request_window(p_dev, &cfg_mem->req, &p_dev->win) != 0)
-				goto next_entry;
-			if (pcmcia_map_mem_page(p_dev, p_dev->win,
-					mem->win[0].card_addr) != 0)
-				goto next_entry;
-
-			cfg_mem->data->MmioAddress = (unsigned long) ioremap_nocache(cfg_mem->req.Base, cfg_mem->req.Size);
-			cfg_mem->data->MmioLength  = cfg_mem->req.Size;
-		}
-		/* If we got this far, we're cool! */
-		return 0;
-	}
+	/* If we got this far, we're cool! */
+	return 0;
 
 next_entry:
 	nsp_dbg(NSP_DEBUG_INIT, "next");
@@ -1693,25 +1607,23 @@
 {
 	int		  ret;
 	scsi_info_t	 *info	 = link->priv;
-	struct nsp_cs_configdata *cfg_mem;
 	struct Scsi_Host *host;
 	nsp_hw_data      *data = &nsp_data_base;
 
 	nsp_dbg(NSP_DEBUG_INIT, "in");
 
-	cfg_mem = kzalloc(sizeof(*cfg_mem), GFP_KERNEL);
-	if (!cfg_mem)
-		return -ENOMEM;
-	cfg_mem->data = data;
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_CHECK_VCC |
+		CONF_AUTO_SET_VPP | CONF_AUTO_AUDIO | CONF_AUTO_SET_IOMEM |
+		CONF_AUTO_SET_IO;
 
-	ret = pcmcia_loop_config(link, nsp_cs_config_check, cfg_mem);
+	ret = pcmcia_loop_config(link, nsp_cs_config_check, data);
 	if (ret)
 		goto cs_failed;
 
 	if (pcmcia_request_irq(link, nspintr))
 		goto cs_failed;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto cs_failed;
 
@@ -1754,41 +1666,16 @@
 
 	info->host = host;
 
-	/* Finally, report what we've done */
-	printk(KERN_INFO "nsp_cs: index 0x%02x: ",
-	       link->conf.ConfigIndex);
-	if (link->conf.Vpp) {
-		printk(", Vpp %d.%d", link->conf.Vpp/10, link->conf.Vpp%10);
-	}
-	if (link->conf.Attributes & CONF_ENABLE_IRQ) {
-		printk(", irq %d", link->irq);
-	}
-	if (link->resource[0])
-		printk(", io %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(" & %pR", link->resource[1]);
-	if (link->win)
-		printk(", mem 0x%06lx-0x%06lx", cfg_mem->req.Base,
-		       cfg_mem->req.Base+cfg_mem->req.Size-1);
-	printk("\n");
-
-	kfree(cfg_mem);
 	return 0;
 
  cs_failed:
 	nsp_dbg(NSP_DEBUG_INIT, "config fail");
 	nsp_cs_release(link);
-	kfree(cfg_mem);
 
 	return -ENODEV;
 } /* nsp_cs_config */
 
 
-/*======================================================================
-    After a card is removed, nsp_cs_release() will unregister the net
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-======================================================================*/
 static void nsp_cs_release(struct pcmcia_device *link)
 {
 	scsi_info_t *info = link->priv;
@@ -1807,7 +1694,7 @@
 		scsi_remove_host(info->host);
 	}
 
-	if (link->win) {
+	if (resource_size(link->resource[2])) {
 		if (data != NULL) {
 			iounmap((void *)(data->MmioAddress));
 		}
@@ -1877,9 +1764,7 @@
 
 static struct pcmcia_driver nsp_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "nsp_cs",
-	},
+	.name		= "nsp_cs",
 	.probe		= nsp_cs_probe,
 	.remove		= nsp_cs_detach,
 	.id_table	= nsp_cs_ids,
@@ -1889,14 +1774,11 @@
 
 static int __init nsp_cs_init(void)
 {
-	nsp_msg(KERN_INFO, "loading...");
-
 	return pcmcia_register_driver(&nsp_driver);
 }
 
 static void __exit nsp_cs_exit(void)
 {
-	nsp_msg(KERN_INFO, "unloading...");
 	pcmcia_unregister_driver(&nsp_driver);
 }
 
diff --git a/drivers/scsi/pcmcia/qlogic_stub.c b/drivers/scsi/pcmcia/qlogic_stub.c
index eb775f1..9c96ca8 100644
--- a/drivers/scsi/pcmcia/qlogic_stub.c
+++ b/drivers/scsi/pcmcia/qlogic_stub.c
@@ -48,7 +48,6 @@
 #include <scsi/scsi_host.h>
 #include "../qlogicfas408.h"
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 #include <pcmcia/ciscode.h>
@@ -156,11 +155,8 @@
 		return -ENOMEM;
 	info->p_dev = link;
 	link->priv = info;
-	link->resource[0]->end = 16;
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-	link->conf.Present = PRESENT_OPTION;
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+	link->config_regs = PRESENT_OPTION;
 
 	return qlogic_config(link);
 }				/* qlogic_attach */
@@ -178,15 +174,11 @@
 
 /*====================================================================*/
 
-static int qlogic_config_check(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cfg,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int qlogic_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
 	p_dev->io_lines = 10;
-	p_dev->resource[0]->start = cfg->io.win[0].base;
-	p_dev->resource[0]->end = cfg->io.win[0].len;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 
 	if (p_dev->resource[0]->start == 0)
 		return -ENODEV;
@@ -209,7 +201,7 @@
 	if (!link->irq)
 		goto failed;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -264,7 +256,7 @@
 {
 	scsi_info_t *info = link->priv;
 
-	pcmcia_request_configuration(link, &link->conf);
+	pcmcia_enable_device(link);
 	if ((info->manf_id == MANFID_MACNICA) ||
 	    (info->manf_id == MANFID_PIONEER) ||
 	    (info->manf_id == 0x0098)) {
@@ -302,9 +294,7 @@
 
 static struct pcmcia_driver qlogic_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
 	.name		= "qlogic_cs",
-	},
 	.probe		= qlogic_probe,
 	.remove		= qlogic_detach,
 	.id_table       = qlogic_ids,
diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c
index 321e390..0ae27cb 100644
--- a/drivers/scsi/pcmcia/sym53c500_cs.c
+++ b/drivers/scsi/pcmcia/sym53c500_cs.c
@@ -71,7 +71,6 @@
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 #include <pcmcia/ciscode.h>
@@ -684,15 +683,11 @@
      .shost_attrs		= SYM53C500_shost_attrs
 };
 
-static int SYM53C500_config_check(struct pcmcia_device *p_dev,
-				  cistpl_cftable_entry_t *cfg,
-				  cistpl_cftable_entry_t *dflt,
-				  unsigned int vcc,
-				  void *priv_data)
+static int SYM53C500_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
 	p_dev->io_lines = 10;
-	p_dev->resource[0]->start = cfg->io.win[0].base;
-	p_dev->resource[0]->end = cfg->io.win[0].len;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 
 	if (p_dev->resource[0]->start == 0)
 		return -ENODEV;
@@ -721,7 +716,7 @@
 	if (!link->irq)
 		goto failed;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -859,10 +854,7 @@
 		return -ENOMEM;
 	info->p_dev = link;
 	link->priv = info;
-	link->resource[0]->end = 16;
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
 
 	return SYM53C500_config(link);
 } /* SYM53C500_attach */
@@ -881,9 +873,7 @@
 
 static struct pcmcia_driver sym53c500_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "sym53c500_cs",
-	},
+	.name		= "sym53c500_cs",
 	.probe		= SYM53C500_probe,
 	.remove		= SYM53C500_detach,
 	.id_table       = sym53c500_ids,
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index ecc45c8..4b87657 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -4165,6 +4165,7 @@
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = pmcraid_chr_ioctl,
 #endif
+	.llseek = noop_llseek,
 };
 
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1e4bff6..9946fac 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3948,6 +3948,7 @@
 
 static struct file_operations apidev_fops = {
 	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 /**
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ee02d38..8041fe1 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -968,11 +968,13 @@
  */
 int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask)
 {
-	int error = scsi_init_sgtable(cmd->request, &cmd->sdb, gfp_mask);
+	struct request *rq = cmd->request;
+
+	int error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask);
 	if (error)
 		goto err_exit;
 
-	if (blk_bidi_rq(cmd->request)) {
+	if (blk_bidi_rq(rq)) {
 		struct scsi_data_buffer *bidi_sdb = kmem_cache_zalloc(
 			scsi_sdb_cache, GFP_ATOMIC);
 		if (!bidi_sdb) {
@@ -980,28 +982,28 @@
 			goto err_exit;
 		}
 
-		cmd->request->next_rq->special = bidi_sdb;
-		error = scsi_init_sgtable(cmd->request->next_rq, bidi_sdb,
-								    GFP_ATOMIC);
+		rq->next_rq->special = bidi_sdb;
+		error = scsi_init_sgtable(rq->next_rq, bidi_sdb, GFP_ATOMIC);
 		if (error)
 			goto err_exit;
 	}
 
-	if (blk_integrity_rq(cmd->request)) {
+	if (blk_integrity_rq(rq)) {
 		struct scsi_data_buffer *prot_sdb = cmd->prot_sdb;
 		int ivecs, count;
 
 		BUG_ON(prot_sdb == NULL);
-		ivecs = blk_rq_count_integrity_sg(cmd->request);
+		ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio);
 
 		if (scsi_alloc_sgtable(prot_sdb, ivecs, gfp_mask)) {
 			error = BLKPREP_DEFER;
 			goto err_exit;
 		}
 
-		count = blk_rq_map_integrity_sg(cmd->request,
+		count = blk_rq_map_integrity_sg(rq->q, rq->bio,
 						prot_sdb->table.sgl);
 		BUG_ON(unlikely(count > ivecs));
+		BUG_ON(unlikely(count > queue_max_integrity_segments(rq->q)));
 
 		cmd->prot_sdb = prot_sdb;
 		cmd->prot_sdb->table.nents = count;
@@ -1625,6 +1627,14 @@
 	blk_queue_max_segments(q, min_t(unsigned short, shost->sg_tablesize,
 					SCSI_MAX_SG_CHAIN_SEGMENTS));
 
+	if (scsi_host_prot_dma(shost)) {
+		shost->sg_prot_tablesize =
+			min_not_zero(shost->sg_prot_tablesize,
+				     (unsigned short)SCSI_MAX_PROT_SG_SEGMENTS);
+		BUG_ON(shost->sg_prot_tablesize < shost->sg_tablesize);
+		blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
+	}
+
 	blk_queue_max_hw_sectors(q, shost->max_sectors);
 	blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost));
 	blk_queue_segment_boundary(q, shost->dma_boundary);
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index c3f6737..20ad59d 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -251,6 +251,7 @@
 shost_rd_attr(cmd_per_lun, "%hd\n");
 shost_rd_attr(can_queue, "%hd\n");
 shost_rd_attr(sg_tablesize, "%hu\n");
+shost_rd_attr(sg_prot_tablesize, "%hu\n");
 shost_rd_attr(unchecked_isa_dma, "%d\n");
 shost_rd_attr(prot_capabilities, "%u\n");
 shost_rd_attr(prot_guard_type, "%hd\n");
@@ -262,6 +263,7 @@
 	&dev_attr_cmd_per_lun.attr,
 	&dev_attr_can_queue.attr,
 	&dev_attr_sg_tablesize.attr,
+	&dev_attr_sg_prot_tablesize.attr,
 	&dev_attr_unchecked_isa_dma.attr,
 	&dev_attr_proc_name.attr,
 	&dev_attr_scan.attr,
diff --git a/drivers/scsi/scsi_tgt_if.c b/drivers/scsi/scsi_tgt_if.c
index a87e21c..0172de1 100644
--- a/drivers/scsi/scsi_tgt_if.c
+++ b/drivers/scsi/scsi_tgt_if.c
@@ -22,7 +22,6 @@
 #include <linux/miscdevice.h>
 #include <linux/gfp.h>
 #include <linux/file.h>
-#include <linux/smp_lock.h>
 #include <net/tcp.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -323,7 +322,6 @@
 {
 	tx_ring.tr_idx = rx_ring.tr_idx = 0;
 
-	cycle_kernel_lock();
 	return 0;
 }
 
@@ -333,6 +331,7 @@
 	.poll		= tgt_poll,
 	.write		= tgt_write,
 	.mmap		= tgt_mmap,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice tgt_miscdev = {
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index ffa0689..20514c4 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2109,7 +2109,7 @@
 	struct scsi_disk *sdkp = scsi_disk(disk);
 	struct scsi_device *sdp = sdkp->device;
 	unsigned char *buffer;
-	unsigned ordered;
+	unsigned flush = 0;
 
 	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
 				      "sd_revalidate_disk\n"));
@@ -2151,17 +2151,15 @@
 
 	/*
 	 * We now have all cache related info, determine how we deal
-	 * with ordered requests.  Note that as the current SCSI
-	 * dispatch function can alter request order, we cannot use
-	 * QUEUE_ORDERED_TAG_* even when ordered tag is supported.
+	 * with flush requests.
 	 */
-	if (sdkp->WCE)
-		ordered = sdkp->DPOFUA
-			? QUEUE_ORDERED_DRAIN_FUA : QUEUE_ORDERED_DRAIN_FLUSH;
-	else
-		ordered = QUEUE_ORDERED_DRAIN;
+	if (sdkp->WCE) {
+		flush |= REQ_FLUSH;
+		if (sdkp->DPOFUA)
+			flush |= REQ_FUA;
+	}
 
-	blk_queue_ordered(sdkp->disk->queue, ordered);
+	blk_queue_flush(sdkp->disk->queue, flush);
 
 	set_capacity(disk, sdkp->capacity);
 	kfree(buffer);
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 84be621..0cb39ff 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -375,21 +375,20 @@
 	unsigned int i, j;
 	u32 phys, virt;
 
-	/* Already remapped? */
-	if (rq->cmd_flags & REQ_INTEGRITY)
-		return 0;
-
 	sdkp = rq->bio->bi_bdev->bd_disk->private_data;
 
 	if (sdkp->protection_type == SD_DIF_TYPE3_PROTECTION)
 		return 0;
 
-	rq->cmd_flags |= REQ_INTEGRITY;
 	phys = hw_sector & 0xffffffff;
 
 	__rq_for_each_bio(bio, rq) {
 		struct bio_vec *iv;
 
+		/* Already remapped? */
+		if (bio_flagged(bio, BIO_MAPPED_INTEGRITY))
+			break;
+
 		virt = bio->bi_integrity->bip_sector & 0xffffffff;
 
 		bip_for_each_vec(iv, bio->bi_integrity, i) {
@@ -408,6 +407,8 @@
 
 			kunmap_atomic(sdt, KM_USER0);
 		}
+
+		bio->bi_flags |= BIO_MAPPED_INTEGRITY;
 	}
 
 	return 0;
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 78d6163..5428d53 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -49,7 +49,7 @@
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/blktrace_api.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include "scsi.h"
 #include <scsi/scsi_dbg.h>
@@ -103,6 +103,8 @@
 static int sg_add(struct device *, struct class_interface *);
 static void sg_remove(struct device *, struct class_interface *);
 
+static DEFINE_MUTEX(sg_mutex);
+
 static DEFINE_IDR(sg_index_idr);
 static DEFINE_RWLOCK(sg_index_lock);	/* Also used to lock
 							   file descriptor list for device */
@@ -229,7 +231,7 @@
 	int res;
 	int retval;
 
-	lock_kernel();
+	mutex_lock(&sg_mutex);
 	nonseekable_open(inode, filp);
 	SCSI_LOG_TIMEOUT(3, printk("sg_open: dev=%d, flags=0x%x\n", dev, flags));
 	sdp = sg_get_dev(dev);
@@ -314,7 +316,7 @@
 sg_put:
 	if (sdp)
 		sg_put_dev(sdp);
-	unlock_kernel();
+	mutex_unlock(&sg_mutex);
 	return retval;
 }
 
@@ -1092,9 +1094,9 @@
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&sg_mutex);
 	ret = sg_ioctl(filp, cmd_in, arg);
-	unlock_kernel();
+	mutex_unlock(&sg_mutex);
 
 	return ret;
 }
@@ -1351,6 +1353,7 @@
 	.mmap = sg_mmap,
 	.release = sg_release,
 	.fasync = sg_fasync,
+	.llseek = no_llseek,
 };
 
 static struct class *sg_sysfs_class;
@@ -1657,7 +1660,7 @@
 	if (sg_allow_dio && hp->flags & SG_FLAG_DIRECT_IO &&
 	    dxfer_dir != SG_DXFER_UNKNOWN && !iov_count &&
 	    !sfp->parentdp->device->host->unchecked_isa_dma &&
-	    blk_rq_aligned(q, hp->dxferp, dxfer_len))
+	    blk_rq_aligned(q, (unsigned long)hp->dxferp, dxfer_len))
 		md = NULL;
 	else
 		md = &map_data;
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index ba9c3e0..e148341 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -44,7 +44,6 @@
 #include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <asm/uaccess.h>
 
@@ -76,6 +75,7 @@
 	 CDC_CD_R|CDC_CD_RW|CDC_DVD|CDC_DVD_R|CDC_DVD_RAM|CDC_GENERIC_PACKET| \
 	 CDC_MRW|CDC_MRW_W|CDC_RAM)
 
+static DEFINE_MUTEX(sr_mutex);
 static int sr_probe(struct device *);
 static int sr_remove(struct device *);
 static int sr_done(struct scsi_cmnd *);
@@ -470,24 +470,24 @@
 	struct scsi_cd *cd;
 	int ret = -ENXIO;
 
-	lock_kernel();
+	mutex_lock(&sr_mutex);
 	cd = scsi_cd_get(bdev->bd_disk);
 	if (cd) {
 		ret = cdrom_open(&cd->cdi, bdev, mode);
 		if (ret)
 			scsi_cd_put(cd);
 	}
-	unlock_kernel();
+	mutex_unlock(&sr_mutex);
 	return ret;
 }
 
 static int sr_block_release(struct gendisk *disk, fmode_t mode)
 {
 	struct scsi_cd *cd = scsi_cd(disk);
-	lock_kernel();
+	mutex_lock(&sr_mutex);
 	cdrom_release(&cd->cdi, mode);
 	scsi_cd_put(cd);
-	unlock_kernel();
+	mutex_unlock(&sr_mutex);
 	return 0;
 }
 
@@ -499,7 +499,7 @@
 	void __user *argp = (void __user *)arg;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&sr_mutex);
 
 	/*
 	 * Send SCSI addressing ioctls directly to mid level, send other
@@ -529,7 +529,7 @@
 	ret = scsi_ioctl(sdev, cmd, argp);
 
 out:
-	unlock_kernel();
+	mutex_unlock(&sr_mutex);
 	return ret;
 }
 
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 24211d0..afdc3f5d 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -39,7 +39,6 @@
 #include <linux/cdev.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 
 #include <asm/uaccess.h>
 #include <asm/dma.h>
@@ -76,6 +75,7 @@
 #include "st_options.h"
 #include "st.h"
 
+static DEFINE_MUTEX(st_mutex);
 static int buffer_kbs;
 static int max_sg_segs;
 static int try_direct_io = TRY_DIRECT_IO;
@@ -1180,7 +1180,7 @@
 	int dev = TAPE_NR(inode);
 	char *name;
 
-	lock_kernel();
+	mutex_lock(&st_mutex);
 	/*
 	 * We really want to do nonseekable_open(inode, filp); here, but some
 	 * versions of tar incorrectly call lseek on tapes and bail out if that
@@ -1189,7 +1189,7 @@
 	filp->f_mode &= ~(FMODE_PREAD | FMODE_PWRITE);
 
 	if (!(STp = scsi_tape_get(dev))) {
-		unlock_kernel();
+		mutex_unlock(&st_mutex);
 		return -ENXIO;
 	}
 
@@ -1200,7 +1200,7 @@
 	if (STp->in_use) {
 		write_unlock(&st_dev_arr_lock);
 		scsi_tape_put(STp);
-		unlock_kernel();
+		mutex_unlock(&st_mutex);
 		DEB( printk(ST_DEB_MSG "%s: Device already in use.\n", name); )
 		return (-EBUSY);
 	}
@@ -1249,14 +1249,14 @@
 			retval = (-EIO);
 		goto err_out;
 	}
-	unlock_kernel();
+	mutex_unlock(&st_mutex);
 	return 0;
 
  err_out:
 	normalize_buffer(STp->buffer);
 	STp->in_use = 0;
 	scsi_tape_put(STp);
-	unlock_kernel();
+	mutex_unlock(&st_mutex);
 	return retval;
 
 }
diff --git a/drivers/serial/Kconfig b/drivers/serial/Kconfig
index 12900f7..3198c53 100644
--- a/drivers/serial/Kconfig
+++ b/drivers/serial/Kconfig
@@ -458,6 +458,7 @@
 	int
 	depends on ARM && PLAT_SAMSUNG
 	default 2 if ARCH_S3C2400
+	default 6 if ARCH_S5P6450
 	default 4 if SERIAL_SAMSUNG_UARTS_4
 	default 3
 	help
@@ -526,12 +527,12 @@
 	  Serial port support for the Samsung S3C24A0 SoC
 
 config SERIAL_S3C6400
-	tristate "Samsung S3C6400/S3C6410/S5P6440/S5PC100 Serial port support"
-	depends on SERIAL_SAMSUNG && (CPU_S3C6400 || CPU_S3C6410 || CPU_S5P6440 || CPU_S5PC100)
+	tristate "Samsung S3C6400/S3C6410/S5P6440/S5P6450/S5PC100 Serial port support"
+	depends on SERIAL_SAMSUNG && (CPU_S3C6400 || CPU_S3C6410 || CPU_S5P6440 || CPU_S5P6450 || CPU_S5PC100)
 	select SERIAL_SAMSUNG_UARTS_4
 	default y
 	help
-	  Serial port support for the Samsung S3C6400, S3C6410, S5P6440
+	  Serial port support for the Samsung S3C6400, S3C6410, S5P6440, S5P6450
 	  and S5PC100 SoCs
 
 config SERIAL_S5PV210
diff --git a/drivers/serial/ioc3_serial.c b/drivers/serial/ioc3_serial.c
index 800c546..ee43efc 100644
--- a/drivers/serial/ioc3_serial.c
+++ b/drivers/serial/ioc3_serial.c
@@ -2017,6 +2017,7 @@
 	struct ioc3_port *port;
 	struct ioc3_port *ports[PORTS_PER_CARD];
 	int phys_port;
+	int cnt;
 
 	DPRINT_CONFIG(("%s (0x%p, 0x%p)\n", __func__, is, idd));
 
@@ -2147,6 +2148,9 @@
 
 	/* error exits that give back resources */
 out4:
+	for (cnt = 0; cnt < phys_port; cnt++)
+		kfree(ports[cnt]);
+
 	kfree(card_ptr);
 	return ret;
 }
diff --git a/drivers/serial/mfd.c b/drivers/serial/mfd.c
index 5dff45c..dc0967f 100644
--- a/drivers/serial/mfd.c
+++ b/drivers/serial/mfd.c
@@ -228,12 +228,14 @@
 	.owner		= THIS_MODULE,
 	.open		= hsu_show_regs_open,
 	.read		= port_show_regs,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations dma_regs_ops = {
 	.owner		= THIS_MODULE,
 	.open		= hsu_show_regs_open,
 	.read		= dma_show_regs,
+	.llseek		= default_llseek,
 };
 
 static int hsu_debugfs_init(struct hsu_port *hsu)
diff --git a/drivers/serial/samsung.c b/drivers/serial/samsung.c
index b1156ba..7ac2bf5 100644
--- a/drivers/serial/samsung.c
+++ b/drivers/serial/samsung.c
@@ -1101,7 +1101,7 @@
 	dbg("resource %p (%lx..%lx)\n", res, res->start, res->end);
 
 	port->mapbase = res->start;
-	port->membase = S3C_VA_UART + res->start - (S3C_PA_UART & 0xfff00000);
+	port->membase = S3C_VA_UART + (res->start & 0xfffff);
 	ret = platform_get_irq(platdev, 0);
 	if (ret < 0)
 		port->irq = 0;
diff --git a/drivers/serial/serial_cs.c b/drivers/serial/serial_cs.c
index 7d475b2..93760b2 100644
--- a/drivers/serial/serial_cs.c
+++ b/drivers/serial/serial_cs.c
@@ -45,7 +45,6 @@
 #include <asm/io.h>
 #include <asm/system.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
@@ -183,10 +182,8 @@
 {
 	struct serial_info *info = link->priv;
 
-	if (info->multi) {
-		link->conf.Present |= PRESENT_EXT_STATUS;
-		link->conf.ExtStatus = ESR_REQ_ATTN_ENA;
-	}
+	if (info->multi)
+		link->config_flags |= CONF_ENABLE_ESR;
 }
 
 static const struct serial_quirk quirks[] = {
@@ -265,13 +262,6 @@
 static int serial_config(struct pcmcia_device * link);
 
 
-/*======================================================================
-
-    After a card is removed, serial_remove() will unregister
-    the serial device(s), and release the PCMCIA configuration.
-    
-======================================================================*/
-
 static void serial_remove(struct pcmcia_device *link)
 {
 	struct serial_info *info = link->priv;
@@ -314,14 +304,6 @@
 	return 0;
 }
 
-/*======================================================================
-
-    serial_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-======================================================================*/
-
 static int serial_probe(struct pcmcia_device *link)
 {
 	struct serial_info *info;
@@ -335,25 +317,13 @@
 	info->p_dev = link;
 	link->priv = info;
 
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	if (do_sound) {
-		link->conf.Attributes |= CONF_ENABLE_SPKR;
-		link->conf.Status = CCSR_AUDIO_ENA;
-	}
-	link->conf.IntType = INT_MEMORY_AND_IO;
+	link->config_flags |= CONF_ENABLE_IRQ;
+	if (do_sound)
+		link->config_flags |= CONF_ENABLE_SPKR;
 
 	return serial_config(link);
 }
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void serial_detach(struct pcmcia_device *link)
 {
 	struct serial_info *info = link->priv;
@@ -361,11 +331,6 @@
 	dev_dbg(&link->dev, "serial_detach\n");
 
 	/*
-	 * Ensure any outstanding scheduled tasks are completed.
-	 */
-	flush_scheduled_work();
-
-	/*
 	 * Ensure that the ports have been released.
 	 */
 	serial_remove(link);
@@ -430,47 +395,45 @@
 	return -ENODEV;
 }
 
-static int simple_config_check(struct pcmcia_device *p_dev,
-			       cistpl_cftable_entry_t *cf,
-			       cistpl_cftable_entry_t *dflt,
-			       unsigned int vcc,
-			       void *priv_data)
+static int simple_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
 	static const int size_table[2] = { 8, 16 };
 	int *try = priv_data;
 
-	if (cf->vpp1.present & (1 << CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp =
-			cf->vpp1.param[CISTPL_POWER_VNOM] / 10000;
+	if (p_dev->resource[0]->start == 0)
+		return -ENODEV;
 
-	p_dev->io_lines = ((*try & 0x1) == 0) ?
-			16 : cf->io.flags & CISTPL_IO_LINES_MASK;
+	if ((*try & 0x1) == 0)
+		p_dev->io_lines = 16;
 
-	if ((cf->io.nwin > 0) && (cf->io.win[0].len == size_table[(*try >> 1)])
-	    && (cf->io.win[0].base != 0)) {
-		p_dev->resource[0]->start = cf->io.win[0].base;
-		if (!pcmcia_request_io(p_dev))
-			return 0;
-	}
-	return -EINVAL;
+	if (p_dev->resource[0]->end != size_table[(*try >> 1)])
+		return -ENODEV;
+
+	p_dev->resource[0]->end = 8;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+
+	return pcmcia_request_io(p_dev);
 }
 
 static int simple_config_check_notpicky(struct pcmcia_device *p_dev,
-					cistpl_cftable_entry_t *cf,
-					cistpl_cftable_entry_t *dflt,
-					unsigned int vcc,
 					void *priv_data)
 {
 	static const unsigned int base[5] = { 0x3f8, 0x2f8, 0x3e8, 0x2e8, 0x0 };
 	int j;
 
-	if ((cf->io.nwin > 0) && ((cf->io.flags & CISTPL_IO_LINES_MASK) <= 3)) {
-		for (j = 0; j < 5; j++) {
-			p_dev->resource[0]->start = base[j];
-			p_dev->io_lines = base[j] ? 16 : 3;
-			if (!pcmcia_request_io(p_dev))
-				return 0;
-		}
+	if (p_dev->io_lines > 3)
+		return -ENODEV;
+
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->resource[0]->end = 8;
+
+	for (j = 0; j < 5; j++) {
+		p_dev->resource[0]->start = base[j];
+		p_dev->io_lines = base[j] ? 16 : 3;
+		if (!pcmcia_request_io(p_dev))
+			return 0;
 	}
 	return -ENODEV;
 }
@@ -480,11 +443,9 @@
 	struct serial_info *info = link->priv;
 	int i = -ENODEV, try;
 
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-	link->resource[0]->end = 8;
-
 	/* First pass: look for a config entry that looks normal.
 	 * Two tries: without IO aliases, then with aliases */
+	link->config_flags |= CONF_AUTO_SET_VPP | CONF_AUTO_SET_IO;
 	for (try = 0; try < 4; try++)
 		if (!pcmcia_loop_config(link, simple_config_check, &try))
 			goto found_port;
@@ -500,7 +461,7 @@
 
 found_port:
 	if (info->multi && (info->manfid == MANFID_3COM))
-		link->conf.ConfigIndex &= ~(0x08);
+		link->config_index &= ~(0x08);
 
 	/*
 	 * Apply any configuration quirks.
@@ -508,51 +469,50 @@
 	if (info->quirk && info->quirk->config)
 		info->quirk->config(link);
 
-	i = pcmcia_request_configuration(link, &link->conf);
+	i = pcmcia_enable_device(link);
 	if (i != 0)
 		return -1;
 	return setup_serial(link, info, link->resource[0]->start, link->irq);
 }
 
-static int multi_config_check(struct pcmcia_device *p_dev,
-			      cistpl_cftable_entry_t *cf,
-			      cistpl_cftable_entry_t *dflt,
-			      unsigned int vcc,
-			      void *priv_data)
+static int multi_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	int *base2 = priv_data;
+	int *multi = priv_data;
+
+	if (p_dev->resource[1]->end)
+		return -EINVAL;
 
 	/* The quad port cards have bad CIS's, so just look for a
 	   window larger than 8 ports and assume it will be right */
-	if ((cf->io.nwin == 1) && (cf->io.win[0].len > 8)) {
-		p_dev->resource[0]->start = cf->io.win[0].base;
-		p_dev->io_lines = cf->io.flags & CISTPL_IO_LINES_MASK;
-		if (!pcmcia_request_io(p_dev)) {
-			*base2 = p_dev->resource[0]->start + 8;
-			return 0;
-		}
-	}
-	return -ENODEV;
+	if (p_dev->resource[0]->end <= 8)
+		return -EINVAL;
+
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->resource[0]->end = *multi * 8;
+
+	if (pcmcia_request_io(p_dev))
+		return -ENODEV;
+	return 0;
 }
 
 static int multi_config_check_notpicky(struct pcmcia_device *p_dev,
-				       cistpl_cftable_entry_t *cf,
-				       cistpl_cftable_entry_t *dflt,
-				       unsigned int vcc,
 				       void *priv_data)
 {
 	int *base2 = priv_data;
 
-	if (cf->io.nwin == 2) {
-		p_dev->resource[0]->start = cf->io.win[0].base;
-		p_dev->resource[1]->start = cf->io.win[1].base;
-		p_dev->io_lines = cf->io.flags & CISTPL_IO_LINES_MASK;
-		if (!pcmcia_request_io(p_dev)) {
-			*base2 = p_dev->resource[1]->start;
-			return 0;
-		}
-	}
-	return -ENODEV;
+	if (!p_dev->resource[0]->end || !p_dev->resource[1]->end)
+		return -ENODEV;
+
+	p_dev->resource[0]->end = p_dev->resource[1]->end = 8;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+
+	if (pcmcia_request_io(p_dev))
+		return -ENODEV;
+
+	*base2 = p_dev->resource[0]->start + 8;
+	return 0;
 }
 
 static int multi_config(struct pcmcia_device *link)
@@ -560,12 +520,12 @@
 	struct serial_info *info = link->priv;
 	int i, base2 = 0;
 
+	link->config_flags |= CONF_AUTO_SET_IO;
 	/* First, look for a generic full-sized window */
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-	link->resource[0]->end = info->multi * 8;
-	if (pcmcia_loop_config(link, multi_config_check, &base2)) {
+	if (!pcmcia_loop_config(link, multi_config_check, &info->multi))
+		base2 = link->resource[0]->start + 8;
+	else {
 		/* If that didn't work, look for two windows */
-		link->resource[0]->end = link->resource[1]->end = 8;
 		info->multi = 2;
 		if (pcmcia_loop_config(link, multi_config_check_notpicky,
 				       &base2)) {
@@ -584,7 +544,7 @@
 	if (info->quirk && info->quirk->config)
 		info->quirk->config(link);
 
-	i = pcmcia_request_configuration(link, &link->conf);
+	i = pcmcia_enable_device(link);
 	if (i != 0)
 		return -ENODEV;
 
@@ -596,11 +556,11 @@
 				info->prodid == PRODID_POSSIO_GCC)) {
 		int err;
 
-		if (link->conf.ConfigIndex == 1 ||
-		    link->conf.ConfigIndex == 3) {
+		if (link->config_index == 1 ||
+		    link->config_index == 3) {
 			err = setup_serial(link, info, base2,
 					link->irq);
-			base2 = link->resource[0]->start;;
+			base2 = link->resource[0]->start;
 		} else {
 			err = setup_serial(link, info, link->resource[0]->start,
 					link->irq);
@@ -624,33 +584,24 @@
 	return 0;
 }
 
-static int serial_check_for_multi(struct pcmcia_device *p_dev,
-				  cistpl_cftable_entry_t *cf,
-				  cistpl_cftable_entry_t *dflt,
-				  unsigned int vcc,
-				  void *priv_data)
+static int serial_check_for_multi(struct pcmcia_device *p_dev,  void *priv_data)
 {
 	struct serial_info *info = p_dev->priv;
 
-	if ((cf->io.nwin == 1) && (cf->io.win[0].len % 8 == 0))
-		info->multi = cf->io.win[0].len >> 3;
+	if (!p_dev->resource[0]->end)
+		return -EINVAL;
 
-	if ((cf->io.nwin == 2) && (cf->io.win[0].len == 8) &&
-		(cf->io.win[1].len == 8))
+	if ((!p_dev->resource[1]->end) && (p_dev->resource[0]->end % 8 == 0))
+		info->multi = p_dev->resource[0]->end >> 3;
+
+	if ((p_dev->resource[1]->end) && (p_dev->resource[0]->end == 8)
+		&& (p_dev->resource[1]->end == 8))
 		info->multi = 2;
 
 	return 0; /* break */
 }
 
 
-/*======================================================================
-
-    serial_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    serial device available to the system.
-
-======================================================================*/
-
 static int serial_config(struct pcmcia_device * link)
 {
 	struct serial_info *info = link->priv;
@@ -894,9 +845,7 @@
 
 static struct pcmcia_driver serial_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "serial_cs",
-	},
+	.name		= "serial_cs",
 	.probe		= serial_probe,
 	.remove		= serial_detach,
 	.id_table	= serial_ids,
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 91c2f4f..4b9eec6 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -143,10 +143,26 @@
 	  GPIO operations, you should be able to leverage that for better
 	  speed with a custom version of this driver; see the source code.
 
+config SPI_IMX_VER_IMX1
+	def_bool y if SOC_IMX1
+
+config SPI_IMX_VER_0_0
+	def_bool y if SOC_IMX21 || SOC_IMX27
+
+config SPI_IMX_VER_0_4
+	def_bool y if ARCH_MX31
+
+config SPI_IMX_VER_0_7
+	def_bool y if ARCH_MX25 || ARCH_MX35 || ARCH_MX51
+
+config SPI_IMX_VER_2_3
+	def_bool y if ARCH_MX51
+
 config SPI_IMX
 	tristate "Freescale i.MX SPI controllers"
 	depends on ARCH_MXC
 	select SPI_BITBANG
+	default m if IMX_HAVE_PLATFORM_SPI_IMX
 	help
 	  This enables using the Freescale i.MX SPI controllers in master
 	  mode.
@@ -182,12 +198,27 @@
 	  This enables using the Freescale MPC5121 Programmable Serial
 	  Controller in SPI master mode.
 
-config SPI_MPC8xxx
-	tristate "Freescale MPC8xxx SPI controller"
+config SPI_FSL_LIB
+	tristate
 	depends on FSL_SOC
+
+config SPI_FSL_SPI
+	tristate "Freescale SPI controller"
+	depends on FSL_SOC
+	select SPI_FSL_LIB
 	help
-	  This enables using the Freescale MPC8xxx SPI controllers in master
-	  mode.
+	  This enables using the Freescale SPI controllers in master mode.
+	  MPC83xx platform uses the controller in cpu mode or CPM/QE mode.
+	  MPC8569 uses the controller in QE mode, MPC8610 in cpu mode.
+
+config SPI_FSL_ESPI
+	tristate "Freescale eSPI controller"
+	depends on FSL_SOC
+	select SPI_FSL_LIB
+	help
+	  This enables using the Freescale eSPI controllers in master mode.
+	  From MPC8536, 85xx platform uses the controller, and all P10xx,
+	  P20xx, P30xx,P40xx, P50xx uses this controller.
 
 config SPI_OMAP_UWIRE
 	tristate "OMAP1 MicroWire"
@@ -298,6 +329,13 @@
 	help
 	  SPI driver for Freescale STMP37xx/378x SoC SSP interface
 
+config SPI_TOPCLIFF_PCH
+	tristate "Topcliff PCH SPI Controller"
+	depends on PCI
+	help
+	  SPI driver for the Topcliff PCH (Platform Controller Hub) SPI bus
+	  used in some x86 embedded processors.
+
 config SPI_TXX9
 	tristate "Toshiba TXx9 SPI controller"
 	depends on GENERIC_GPIO && CPU_TX49XX
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index e9cbd18..557aaad 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -2,9 +2,7 @@
 # Makefile for kernel SPI drivers.
 #
 
-ifeq ($(CONFIG_SPI_DEBUG),y)
-EXTRA_CFLAGS += -DDEBUG
-endif
+ccflags-$(CONFIG_SPI_DEBUG) := -DDEBUG
 
 # small core, mostly translating board-specific
 # config declarations into driver model code
@@ -34,11 +32,14 @@
 obj-$(CONFIG_SPI_MPC512x_PSC)		+= mpc512x_psc_spi.o
 obj-$(CONFIG_SPI_MPC52xx_PSC)		+= mpc52xx_psc_spi.o
 obj-$(CONFIG_SPI_MPC52xx)		+= mpc52xx_spi.o
-obj-$(CONFIG_SPI_MPC8xxx)		+= spi_mpc8xxx.o
+obj-$(CONFIG_SPI_FSL_LIB)		+= spi_fsl_lib.o
+obj-$(CONFIG_SPI_FSL_ESPI)		+= spi_fsl_espi.o
+obj-$(CONFIG_SPI_FSL_SPI)		+= spi_fsl_spi.o
 obj-$(CONFIG_SPI_PPC4xx)		+= spi_ppc4xx.o
 obj-$(CONFIG_SPI_S3C24XX_GPIO)		+= spi_s3c24xx_gpio.o
 obj-$(CONFIG_SPI_S3C24XX)		+= spi_s3c24xx_hw.o
 obj-$(CONFIG_SPI_S3C64XX)		+= spi_s3c64xx.o
+obj-$(CONFIG_SPI_TOPCLIFF_PCH)		+= spi_topcliff_pch.o
 obj-$(CONFIG_SPI_TXX9)			+= spi_txx9.o
 obj-$(CONFIG_SPI_XILINX)		+= xilinx_spi.o
 obj-$(CONFIG_SPI_XILINX_OF)		+= xilinx_spi_of.o
diff --git a/drivers/spi/amba-pl022.c b/drivers/spi/amba-pl022.c
index 4c37c4e2..fb3d1b3 100644
--- a/drivers/spi/amba-pl022.c
+++ b/drivers/spi/amba-pl022.c
@@ -27,7 +27,6 @@
 /*
  * TODO:
  * - add timeout on polled transfers
- * - add generic DMA framework support
  */
 
 #include <linux/init.h>
@@ -45,6 +44,9 @@
 #include <linux/amba/pl022.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
 
 /*
  * This macro is used to define some register default values.
@@ -381,6 +383,14 @@
 	enum ssp_reading		read;
 	enum ssp_writing		write;
 	u32				exp_fifo_level;
+	/* DMA settings */
+#ifdef CONFIG_DMA_ENGINE
+	struct dma_chan			*dma_rx_channel;
+	struct dma_chan			*dma_tx_channel;
+	struct sg_table			sgt_rx;
+	struct sg_table			sgt_tx;
+	char				*dummypage;
+#endif
 };
 
 /**
@@ -406,7 +416,7 @@
 	u16 dmacr;
 	u16 cpsr;
 	u8 n_bytes;
-	u8 enable_dma:1;
+	bool enable_dma;
 	enum ssp_reading read;
 	enum ssp_writing write;
 	void (*cs_control) (u32 command);
@@ -763,6 +773,371 @@
 	}
 	return STATE_DONE;
 }
+
+/*
+ * This DMA functionality is only compiled in if we have
+ * access to the generic DMA devices/DMA engine.
+ */
+#ifdef CONFIG_DMA_ENGINE
+static void unmap_free_dma_scatter(struct pl022 *pl022)
+{
+	/* Unmap and free the SG tables */
+	dma_unmap_sg(&pl022->adev->dev, pl022->sgt_tx.sgl,
+		     pl022->sgt_tx.nents, DMA_TO_DEVICE);
+	dma_unmap_sg(&pl022->adev->dev, pl022->sgt_rx.sgl,
+		     pl022->sgt_rx.nents, DMA_FROM_DEVICE);
+	sg_free_table(&pl022->sgt_rx);
+	sg_free_table(&pl022->sgt_tx);
+}
+
+static void dma_callback(void *data)
+{
+	struct pl022 *pl022 = data;
+	struct spi_message *msg = pl022->cur_msg;
+
+	BUG_ON(!pl022->sgt_rx.sgl);
+
+#ifdef VERBOSE_DEBUG
+	/*
+	 * Optionally dump out buffers to inspect contents, this is
+	 * good if you want to convince yourself that the loopback
+	 * read/write contents are the same, when adopting to a new
+	 * DMA engine.
+	 */
+	{
+		struct scatterlist *sg;
+		unsigned int i;
+
+		dma_sync_sg_for_cpu(&pl022->adev->dev,
+				    pl022->sgt_rx.sgl,
+				    pl022->sgt_rx.nents,
+				    DMA_FROM_DEVICE);
+
+		for_each_sg(pl022->sgt_rx.sgl, sg, pl022->sgt_rx.nents, i) {
+			dev_dbg(&pl022->adev->dev, "SPI RX SG ENTRY: %d", i);
+			print_hex_dump(KERN_ERR, "SPI RX: ",
+				       DUMP_PREFIX_OFFSET,
+				       16,
+				       1,
+				       sg_virt(sg),
+				       sg_dma_len(sg),
+				       1);
+		}
+		for_each_sg(pl022->sgt_tx.sgl, sg, pl022->sgt_tx.nents, i) {
+			dev_dbg(&pl022->adev->dev, "SPI TX SG ENTRY: %d", i);
+			print_hex_dump(KERN_ERR, "SPI TX: ",
+				       DUMP_PREFIX_OFFSET,
+				       16,
+				       1,
+				       sg_virt(sg),
+				       sg_dma_len(sg),
+				       1);
+		}
+	}
+#endif
+
+	unmap_free_dma_scatter(pl022);
+
+	/* Update total bytes transfered */
+	msg->actual_length += pl022->cur_transfer->len;
+	if (pl022->cur_transfer->cs_change)
+		pl022->cur_chip->
+			cs_control(SSP_CHIP_DESELECT);
+
+	/* Move to next transfer */
+	msg->state = next_transfer(pl022);
+	tasklet_schedule(&pl022->pump_transfers);
+}
+
+static void setup_dma_scatter(struct pl022 *pl022,
+			      void *buffer,
+			      unsigned int length,
+			      struct sg_table *sgtab)
+{
+	struct scatterlist *sg;
+	int bytesleft = length;
+	void *bufp = buffer;
+	int mapbytes;
+	int i;
+
+	if (buffer) {
+		for_each_sg(sgtab->sgl, sg, sgtab->nents, i) {
+			/*
+			 * If there are less bytes left than what fits
+			 * in the current page (plus page alignment offset)
+			 * we just feed in this, else we stuff in as much
+			 * as we can.
+			 */
+			if (bytesleft < (PAGE_SIZE - offset_in_page(bufp)))
+				mapbytes = bytesleft;
+			else
+				mapbytes = PAGE_SIZE - offset_in_page(bufp);
+			sg_set_page(sg, virt_to_page(bufp),
+				    mapbytes, offset_in_page(bufp));
+			bufp += mapbytes;
+			bytesleft -= mapbytes;
+			dev_dbg(&pl022->adev->dev,
+				"set RX/TX target page @ %p, %d bytes, %d left\n",
+				bufp, mapbytes, bytesleft);
+		}
+	} else {
+		/* Map the dummy buffer on every page */
+		for_each_sg(sgtab->sgl, sg, sgtab->nents, i) {
+			if (bytesleft < PAGE_SIZE)
+				mapbytes = bytesleft;
+			else
+				mapbytes = PAGE_SIZE;
+			sg_set_page(sg, virt_to_page(pl022->dummypage),
+				    mapbytes, 0);
+			bytesleft -= mapbytes;
+			dev_dbg(&pl022->adev->dev,
+				"set RX/TX to dummy page %d bytes, %d left\n",
+				mapbytes, bytesleft);
+
+		}
+	}
+	BUG_ON(bytesleft);
+}
+
+/**
+ * configure_dma - configures the channels for the next transfer
+ * @pl022: SSP driver's private data structure
+ */
+static int configure_dma(struct pl022 *pl022)
+{
+	struct dma_slave_config rx_conf = {
+		.src_addr = SSP_DR(pl022->phybase),
+		.direction = DMA_FROM_DEVICE,
+		.src_maxburst = pl022->vendor->fifodepth >> 1,
+	};
+	struct dma_slave_config tx_conf = {
+		.dst_addr = SSP_DR(pl022->phybase),
+		.direction = DMA_TO_DEVICE,
+		.dst_maxburst = pl022->vendor->fifodepth >> 1,
+	};
+	unsigned int pages;
+	int ret;
+	int sglen;
+	struct dma_chan *rxchan = pl022->dma_rx_channel;
+	struct dma_chan *txchan = pl022->dma_tx_channel;
+	struct dma_async_tx_descriptor *rxdesc;
+	struct dma_async_tx_descriptor *txdesc;
+	dma_cookie_t cookie;
+
+	/* Check that the channels are available */
+	if (!rxchan || !txchan)
+		return -ENODEV;
+
+	switch (pl022->read) {
+	case READING_NULL:
+		/* Use the same as for writing */
+		rx_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
+		break;
+	case READING_U8:
+		rx_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		break;
+	case READING_U16:
+		rx_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		break;
+	case READING_U32:
+		rx_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		break;
+	}
+
+	switch (pl022->write) {
+	case WRITING_NULL:
+		/* Use the same as for reading */
+		tx_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
+		break;
+	case WRITING_U8:
+		tx_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		break;
+	case WRITING_U16:
+		tx_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		break;
+	case WRITING_U32:
+		tx_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;;
+		break;
+	}
+
+	/* SPI pecularity: we need to read and write the same width */
+	if (rx_conf.src_addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
+		rx_conf.src_addr_width = tx_conf.dst_addr_width;
+	if (tx_conf.dst_addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
+		tx_conf.dst_addr_width = rx_conf.src_addr_width;
+	BUG_ON(rx_conf.src_addr_width != tx_conf.dst_addr_width);
+
+	rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG,
+				       (unsigned long) &rx_conf);
+	txchan->device->device_control(txchan, DMA_SLAVE_CONFIG,
+				       (unsigned long) &tx_conf);
+
+	/* Create sglists for the transfers */
+	pages = (pl022->cur_transfer->len >> PAGE_SHIFT) + 1;
+	dev_dbg(&pl022->adev->dev, "using %d pages for transfer\n", pages);
+
+	ret = sg_alloc_table(&pl022->sgt_rx, pages, GFP_KERNEL);
+	if (ret)
+		goto err_alloc_rx_sg;
+
+	ret = sg_alloc_table(&pl022->sgt_tx, pages, GFP_KERNEL);
+	if (ret)
+		goto err_alloc_tx_sg;
+
+	/* Fill in the scatterlists for the RX+TX buffers */
+	setup_dma_scatter(pl022, pl022->rx,
+			  pl022->cur_transfer->len, &pl022->sgt_rx);
+	setup_dma_scatter(pl022, pl022->tx,
+			  pl022->cur_transfer->len, &pl022->sgt_tx);
+
+	/* Map DMA buffers */
+	sglen = dma_map_sg(&pl022->adev->dev, pl022->sgt_rx.sgl,
+			   pl022->sgt_rx.nents, DMA_FROM_DEVICE);
+	if (!sglen)
+		goto err_rx_sgmap;
+
+	sglen = dma_map_sg(&pl022->adev->dev, pl022->sgt_tx.sgl,
+			   pl022->sgt_tx.nents, DMA_TO_DEVICE);
+	if (!sglen)
+		goto err_tx_sgmap;
+
+	/* Send both scatterlists */
+	rxdesc = rxchan->device->device_prep_slave_sg(rxchan,
+				      pl022->sgt_rx.sgl,
+				      pl022->sgt_rx.nents,
+				      DMA_FROM_DEVICE,
+				      DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!rxdesc)
+		goto err_rxdesc;
+
+	txdesc = txchan->device->device_prep_slave_sg(txchan,
+				      pl022->sgt_tx.sgl,
+				      pl022->sgt_tx.nents,
+				      DMA_TO_DEVICE,
+				      DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!txdesc)
+		goto err_txdesc;
+
+	/* Put the callback on the RX transfer only, that should finish last */
+	rxdesc->callback = dma_callback;
+	rxdesc->callback_param = pl022;
+
+	/* Submit and fire RX and TX with TX last so we're ready to read! */
+	cookie = rxdesc->tx_submit(rxdesc);
+	if (dma_submit_error(cookie))
+		goto err_submit_rx;
+	cookie = txdesc->tx_submit(txdesc);
+	if (dma_submit_error(cookie))
+		goto err_submit_tx;
+	rxchan->device->device_issue_pending(rxchan);
+	txchan->device->device_issue_pending(txchan);
+
+	return 0;
+
+err_submit_tx:
+err_submit_rx:
+err_txdesc:
+	txchan->device->device_control(txchan, DMA_TERMINATE_ALL, 0);
+err_rxdesc:
+	rxchan->device->device_control(rxchan, DMA_TERMINATE_ALL, 0);
+	dma_unmap_sg(&pl022->adev->dev, pl022->sgt_tx.sgl,
+		     pl022->sgt_tx.nents, DMA_TO_DEVICE);
+err_tx_sgmap:
+	dma_unmap_sg(&pl022->adev->dev, pl022->sgt_rx.sgl,
+		     pl022->sgt_tx.nents, DMA_FROM_DEVICE);
+err_rx_sgmap:
+	sg_free_table(&pl022->sgt_tx);
+err_alloc_tx_sg:
+	sg_free_table(&pl022->sgt_rx);
+err_alloc_rx_sg:
+	return -ENOMEM;
+}
+
+static int __init pl022_dma_probe(struct pl022 *pl022)
+{
+	dma_cap_mask_t mask;
+
+	/* Try to acquire a generic DMA engine slave channel */
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+	/*
+	 * We need both RX and TX channels to do DMA, else do none
+	 * of them.
+	 */
+	pl022->dma_rx_channel = dma_request_channel(mask,
+					    pl022->master_info->dma_filter,
+					    pl022->master_info->dma_rx_param);
+	if (!pl022->dma_rx_channel) {
+		dev_err(&pl022->adev->dev, "no RX DMA channel!\n");
+		goto err_no_rxchan;
+	}
+
+	pl022->dma_tx_channel = dma_request_channel(mask,
+					    pl022->master_info->dma_filter,
+					    pl022->master_info->dma_tx_param);
+	if (!pl022->dma_tx_channel) {
+		dev_err(&pl022->adev->dev, "no TX DMA channel!\n");
+		goto err_no_txchan;
+	}
+
+	pl022->dummypage = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!pl022->dummypage) {
+		dev_err(&pl022->adev->dev, "no DMA dummypage!\n");
+		goto err_no_dummypage;
+	}
+
+	dev_info(&pl022->adev->dev, "setup for DMA on RX %s, TX %s\n",
+		 dma_chan_name(pl022->dma_rx_channel),
+		 dma_chan_name(pl022->dma_tx_channel));
+
+	return 0;
+
+err_no_dummypage:
+	dma_release_channel(pl022->dma_tx_channel);
+err_no_txchan:
+	dma_release_channel(pl022->dma_rx_channel);
+	pl022->dma_rx_channel = NULL;
+err_no_rxchan:
+	return -ENODEV;
+}
+
+static void terminate_dma(struct pl022 *pl022)
+{
+	struct dma_chan *rxchan = pl022->dma_rx_channel;
+	struct dma_chan *txchan = pl022->dma_tx_channel;
+
+	rxchan->device->device_control(rxchan, DMA_TERMINATE_ALL, 0);
+	txchan->device->device_control(txchan, DMA_TERMINATE_ALL, 0);
+	unmap_free_dma_scatter(pl022);
+}
+
+static void pl022_dma_remove(struct pl022 *pl022)
+{
+	if (pl022->busy)
+		terminate_dma(pl022);
+	if (pl022->dma_tx_channel)
+		dma_release_channel(pl022->dma_tx_channel);
+	if (pl022->dma_rx_channel)
+		dma_release_channel(pl022->dma_rx_channel);
+	kfree(pl022->dummypage);
+}
+
+#else
+static inline int configure_dma(struct pl022 *pl022)
+{
+	return -ENODEV;
+}
+
+static inline int pl022_dma_probe(struct pl022 *pl022)
+{
+	return 0;
+}
+
+static inline void pl022_dma_remove(struct pl022 *pl022)
+{
+}
+#endif
+
 /**
  * pl022_interrupt_handler - Interrupt handler for SSP controller
  *
@@ -794,14 +1169,17 @@
 	if (unlikely(!irq_status))
 		return IRQ_NONE;
 
-	/* This handles the error code interrupts */
+	/*
+	 * This handles the FIFO interrupts, the timeout
+	 * interrupts are flatly ignored, they cannot be
+	 * trusted.
+	 */
 	if (unlikely(irq_status & SSP_MIS_MASK_RORMIS)) {
 		/*
 		 * Overrun interrupt - bail out since our Data has been
 		 * corrupted
 		 */
-		dev_err(&pl022->adev->dev,
-			"FIFO overrun\n");
+		dev_err(&pl022->adev->dev, "FIFO overrun\n");
 		if (readw(SSP_SR(pl022->virtbase)) & SSP_SR_MASK_RFF)
 			dev_err(&pl022->adev->dev,
 				"RXFIFO is full\n");
@@ -896,8 +1274,8 @@
 }
 
 /**
- * pump_transfers - Tasklet function which schedules next interrupt transfer
- * when running in interrupt transfer mode.
+ * pump_transfers - Tasklet function which schedules next transfer
+ * when running in interrupt or DMA transfer mode.
  * @data: SSP driver private data structure
  *
  */
@@ -954,65 +1332,23 @@
 	}
 	/* Flush the FIFOs and let's go! */
 	flush(pl022);
+
+	if (pl022->cur_chip->enable_dma) {
+		if (configure_dma(pl022)) {
+			dev_dbg(&pl022->adev->dev,
+				"configuration of DMA failed, fall back to interrupt mode\n");
+			goto err_config_dma;
+		}
+		return;
+	}
+
+err_config_dma:
 	writew(ENABLE_ALL_INTERRUPTS, SSP_IMSC(pl022->virtbase));
 }
 
-/**
- * NOT IMPLEMENTED
- * configure_dma - It configures the DMA pipes for DMA transfers
- * @data: SSP driver's private data structure
- *
- */
-static int configure_dma(void *data)
+static void do_interrupt_dma_transfer(struct pl022 *pl022)
 {
-	struct pl022 *pl022 = data;
-	dev_dbg(&pl022->adev->dev, "configure DMA\n");
-	return -ENOTSUPP;
-}
-
-/**
- * do_dma_transfer - It handles transfers of the current message
- * if it is DMA xfer.
- * NOT FULLY IMPLEMENTED
- * @data: SSP driver's private data structure
- */
-static void do_dma_transfer(void *data)
-{
-	struct pl022 *pl022 = data;
-
-	if (configure_dma(data)) {
-		dev_dbg(&pl022->adev->dev, "configuration of DMA Failed!\n");
-		goto err_config_dma;
-	}
-
-	/* TODO: Implememt DMA setup of pipes here */
-
-	/* Enable target chip, set up transfer */
-	pl022->cur_chip->cs_control(SSP_CHIP_SELECT);
-	if (set_up_next_transfer(pl022, pl022->cur_transfer)) {
-		/* Error path */
-		pl022->cur_msg->state = STATE_ERROR;
-		pl022->cur_msg->status = -EIO;
-		giveback(pl022);
-		return;
-	}
-	/* Enable SSP */
-	writew((readw(SSP_CR1(pl022->virtbase)) | SSP_CR1_MASK_SSE),
-	       SSP_CR1(pl022->virtbase));
-
-	/* TODO: Enable the DMA transfer here */
-	return;
-
- err_config_dma:
-	pl022->cur_msg->state = STATE_ERROR;
-	pl022->cur_msg->status = -EIO;
-	giveback(pl022);
-	return;
-}
-
-static void do_interrupt_transfer(void *data)
-{
-	struct pl022 *pl022 = data;
+	u32 irqflags = ENABLE_ALL_INTERRUPTS;
 
 	/* Enable target chip */
 	pl022->cur_chip->cs_control(SSP_CHIP_SELECT);
@@ -1023,15 +1359,26 @@
 		giveback(pl022);
 		return;
 	}
+	/* If we're using DMA, set up DMA here */
+	if (pl022->cur_chip->enable_dma) {
+		/* Configure DMA transfer */
+		if (configure_dma(pl022)) {
+			dev_dbg(&pl022->adev->dev,
+				"configuration of DMA failed, fall back to interrupt mode\n");
+			goto err_config_dma;
+		}
+		/* Disable interrupts in DMA mode, IRQ from DMA controller */
+		irqflags = DISABLE_ALL_INTERRUPTS;
+	}
+err_config_dma:
 	/* Enable SSP, turn on interrupts */
 	writew((readw(SSP_CR1(pl022->virtbase)) | SSP_CR1_MASK_SSE),
 	       SSP_CR1(pl022->virtbase));
-	writew(ENABLE_ALL_INTERRUPTS, SSP_IMSC(pl022->virtbase));
+	writew(irqflags, SSP_IMSC(pl022->virtbase));
 }
 
-static void do_polling_transfer(void *data)
+static void do_polling_transfer(struct pl022 *pl022)
 {
-	struct pl022 *pl022 = data;
 	struct spi_message *message = NULL;
 	struct spi_transfer *transfer = NULL;
 	struct spi_transfer *previous = NULL;
@@ -1101,7 +1448,7 @@
  *
  * This function checks if there is any spi message in the queue that
  * needs processing and delegate control to appropriate function
- * do_polling_transfer()/do_interrupt_transfer()/do_dma_transfer()
+ * do_polling_transfer()/do_interrupt_dma_transfer()
  * based on the kind of the transfer
  *
  */
@@ -1150,10 +1497,8 @@
 
 	if (pl022->cur_chip->xfer_type == POLLING_TRANSFER)
 		do_polling_transfer(pl022);
-	else if (pl022->cur_chip->xfer_type == INTERRUPT_TRANSFER)
-		do_interrupt_transfer(pl022);
 	else
-		do_dma_transfer(pl022);
+		do_interrupt_dma_transfer(pl022);
 }
 
 
@@ -1248,100 +1593,56 @@
 }
 
 static int verify_controller_parameters(struct pl022 *pl022,
-					struct pl022_config_chip *chip_info)
+				struct pl022_config_chip const *chip_info)
 {
-	if ((chip_info->lbm != LOOPBACK_ENABLED)
-	    && (chip_info->lbm != LOOPBACK_DISABLED)) {
-		dev_err(chip_info->dev,
-			"loopback Mode is configured incorrectly\n");
-		return -EINVAL;
-	}
 	if ((chip_info->iface < SSP_INTERFACE_MOTOROLA_SPI)
 	    || (chip_info->iface > SSP_INTERFACE_UNIDIRECTIONAL)) {
-		dev_err(chip_info->dev,
+		dev_err(&pl022->adev->dev,
 			"interface is configured incorrectly\n");
 		return -EINVAL;
 	}
 	if ((chip_info->iface == SSP_INTERFACE_UNIDIRECTIONAL) &&
 	    (!pl022->vendor->unidir)) {
-		dev_err(chip_info->dev,
+		dev_err(&pl022->adev->dev,
 			"unidirectional mode not supported in this "
 			"hardware version\n");
 		return -EINVAL;
 	}
 	if ((chip_info->hierarchy != SSP_MASTER)
 	    && (chip_info->hierarchy != SSP_SLAVE)) {
-		dev_err(chip_info->dev,
+		dev_err(&pl022->adev->dev,
 			"hierarchy is configured incorrectly\n");
 		return -EINVAL;
 	}
-	if (((chip_info->clk_freq).cpsdvsr < CPSDVR_MIN)
-	    || ((chip_info->clk_freq).cpsdvsr > CPSDVR_MAX)) {
-		dev_err(chip_info->dev,
-			"cpsdvsr is configured incorrectly\n");
-		return -EINVAL;
-	}
-	if ((chip_info->endian_rx != SSP_RX_MSB)
-	    && (chip_info->endian_rx != SSP_RX_LSB)) {
-		dev_err(chip_info->dev,
-			"RX FIFO endianess is configured incorrectly\n");
-		return -EINVAL;
-	}
-	if ((chip_info->endian_tx != SSP_TX_MSB)
-	    && (chip_info->endian_tx != SSP_TX_LSB)) {
-		dev_err(chip_info->dev,
-			"TX FIFO endianess is configured incorrectly\n");
-		return -EINVAL;
-	}
-	if ((chip_info->data_size < SSP_DATA_BITS_4)
-	    || (chip_info->data_size > SSP_DATA_BITS_32)) {
-		dev_err(chip_info->dev,
-			"DATA Size is configured incorrectly\n");
-		return -EINVAL;
-	}
 	if ((chip_info->com_mode != INTERRUPT_TRANSFER)
 	    && (chip_info->com_mode != DMA_TRANSFER)
 	    && (chip_info->com_mode != POLLING_TRANSFER)) {
-		dev_err(chip_info->dev,
+		dev_err(&pl022->adev->dev,
 			"Communication mode is configured incorrectly\n");
 		return -EINVAL;
 	}
 	if ((chip_info->rx_lev_trig < SSP_RX_1_OR_MORE_ELEM)
 	    || (chip_info->rx_lev_trig > SSP_RX_32_OR_MORE_ELEM)) {
-		dev_err(chip_info->dev,
+		dev_err(&pl022->adev->dev,
 			"RX FIFO Trigger Level is configured incorrectly\n");
 		return -EINVAL;
 	}
 	if ((chip_info->tx_lev_trig < SSP_TX_1_OR_MORE_EMPTY_LOC)
 	    || (chip_info->tx_lev_trig > SSP_TX_32_OR_MORE_EMPTY_LOC)) {
-		dev_err(chip_info->dev,
+		dev_err(&pl022->adev->dev,
 			"TX FIFO Trigger Level is configured incorrectly\n");
 		return -EINVAL;
 	}
-	if (chip_info->iface == SSP_INTERFACE_MOTOROLA_SPI) {
-		if ((chip_info->clk_phase != SSP_CLK_FIRST_EDGE)
-		    && (chip_info->clk_phase != SSP_CLK_SECOND_EDGE)) {
-			dev_err(chip_info->dev,
-				"Clock Phase is configured incorrectly\n");
-			return -EINVAL;
-		}
-		if ((chip_info->clk_pol != SSP_CLK_POL_IDLE_LOW)
-		    && (chip_info->clk_pol != SSP_CLK_POL_IDLE_HIGH)) {
-			dev_err(chip_info->dev,
-				"Clock Polarity is configured incorrectly\n");
-			return -EINVAL;
-		}
-	}
 	if (chip_info->iface == SSP_INTERFACE_NATIONAL_MICROWIRE) {
 		if ((chip_info->ctrl_len < SSP_BITS_4)
 		    || (chip_info->ctrl_len > SSP_BITS_32)) {
-			dev_err(chip_info->dev,
+			dev_err(&pl022->adev->dev,
 				"CTRL LEN is configured incorrectly\n");
 			return -EINVAL;
 		}
 		if ((chip_info->wait_state != SSP_MWIRE_WAIT_ZERO)
 		    && (chip_info->wait_state != SSP_MWIRE_WAIT_ONE)) {
-			dev_err(chip_info->dev,
+			dev_err(&pl022->adev->dev,
 				"Wait State is configured incorrectly\n");
 			return -EINVAL;
 		}
@@ -1350,24 +1651,20 @@
 			if ((chip_info->duplex !=
 			     SSP_MICROWIRE_CHANNEL_FULL_DUPLEX)
 			    && (chip_info->duplex !=
-				SSP_MICROWIRE_CHANNEL_HALF_DUPLEX))
-				dev_err(chip_info->dev,
+				SSP_MICROWIRE_CHANNEL_HALF_DUPLEX)) {
+				dev_err(&pl022->adev->dev,
 					"Microwire duplex mode is configured incorrectly\n");
 				return -EINVAL;
+			}
 		} else {
 			if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX)
-				dev_err(chip_info->dev,
+				dev_err(&pl022->adev->dev,
 					"Microwire half duplex mode requested,"
 					" but this is only available in the"
 					" ST version of PL022\n");
 			return -EINVAL;
 		}
 	}
-	if (chip_info->cs_control == NULL) {
-		dev_warn(chip_info->dev,
-			"Chip Select Function is NULL for this chip\n");
-		chip_info->cs_control = null_cs_control;
-	}
 	return 0;
 }
 
@@ -1467,22 +1764,24 @@
 	return 0;
 }
 
-/**
- * NOT IMPLEMENTED
- * process_dma_info - Processes the DMA info provided by client drivers
- * @chip_info: chip info provided by client device
- * @chip: Runtime state maintained by the SSP controller for each spi device
- *
- * This function processes and stores DMA config provided by client driver
- * into the runtime state maintained by the SSP controller driver
+
+/*
+ * A piece of default chip info unless the platform
+ * supplies it.
  */
-static int process_dma_info(struct pl022_config_chip *chip_info,
-			    struct chip_data *chip)
-{
-	dev_err(chip_info->dev,
-		"cannot process DMA info, DMA not implemented!\n");
-	return -ENOTSUPP;
-}
+static const struct pl022_config_chip pl022_default_chip_info = {
+	.com_mode = POLLING_TRANSFER,
+	.iface = SSP_INTERFACE_MOTOROLA_SPI,
+	.hierarchy = SSP_SLAVE,
+	.slave_tx_disable = DO_NOT_DRIVE_TX,
+	.rx_lev_trig = SSP_RX_1_OR_MORE_ELEM,
+	.tx_lev_trig = SSP_TX_1_OR_MORE_EMPTY_LOC,
+	.ctrl_len = SSP_BITS_8,
+	.wait_state = SSP_MWIRE_WAIT_ZERO,
+	.duplex = SSP_MICROWIRE_CHANNEL_FULL_DUPLEX,
+	.cs_control = null_cs_control,
+};
+
 
 /**
  * pl022_setup - setup function registered to SPI master framework
@@ -1496,23 +1795,15 @@
  * controller hardware here, that is not done until the actual transfer
  * commence.
  */
-
-/* FIXME: JUST GUESSING the spi->mode bits understood by this driver */
-#define MODEBITS	(SPI_CPOL | SPI_CPHA | SPI_CS_HIGH \
-			| SPI_LSB_FIRST | SPI_LOOP)
-
 static int pl022_setup(struct spi_device *spi)
 {
-	struct pl022_config_chip *chip_info;
+	struct pl022_config_chip const *chip_info;
 	struct chip_data *chip;
+	struct ssp_clock_params clk_freq;
 	int status = 0;
 	struct pl022 *pl022 = spi_master_get_devdata(spi->master);
-
-	if (spi->mode & ~MODEBITS) {
-		dev_dbg(&spi->dev, "unsupported mode bits %x\n",
-			spi->mode & ~MODEBITS);
-		return -EINVAL;
-	}
+	unsigned int bits = spi->bits_per_word;
+	u32 tmp;
 
 	if (!spi->max_speed_hz)
 		return -EINVAL;
@@ -1535,48 +1826,13 @@
 	chip_info = spi->controller_data;
 
 	if (chip_info == NULL) {
+		chip_info = &pl022_default_chip_info;
 		/* spi_board_info.controller_data not is supplied */
 		dev_dbg(&spi->dev,
 			"using default controller_data settings\n");
-
-		chip_info =
-			kzalloc(sizeof(struct pl022_config_chip), GFP_KERNEL);
-
-		if (!chip_info) {
-			dev_err(&spi->dev,
-				"cannot allocate controller data\n");
-			status = -ENOMEM;
-			goto err_first_setup;
-		}
-
-		dev_dbg(&spi->dev, "allocated memory for controller data\n");
-
-		/* Pointer back to the SPI device */
-		chip_info->dev = &spi->dev;
-		/*
-		 * Set controller data default values:
-		 * Polling is supported by default
-		 */
-		chip_info->lbm = LOOPBACK_DISABLED;
-		chip_info->com_mode = POLLING_TRANSFER;
-		chip_info->iface = SSP_INTERFACE_MOTOROLA_SPI;
-		chip_info->hierarchy = SSP_SLAVE;
-		chip_info->slave_tx_disable = DO_NOT_DRIVE_TX;
-		chip_info->endian_tx = SSP_TX_LSB;
-		chip_info->endian_rx = SSP_RX_LSB;
-		chip_info->data_size = SSP_DATA_BITS_12;
-		chip_info->rx_lev_trig = SSP_RX_1_OR_MORE_ELEM;
-		chip_info->tx_lev_trig = SSP_TX_1_OR_MORE_EMPTY_LOC;
-		chip_info->clk_phase = SSP_CLK_SECOND_EDGE;
-		chip_info->clk_pol = SSP_CLK_POL_IDLE_LOW;
-		chip_info->ctrl_len = SSP_BITS_8;
-		chip_info->wait_state = SSP_MWIRE_WAIT_ZERO;
-		chip_info->duplex = SSP_MICROWIRE_CHANNEL_FULL_DUPLEX;
-		chip_info->cs_control = null_cs_control;
-	} else {
+	} else
 		dev_dbg(&spi->dev,
 			"using user supplied controller_data settings\n");
-	}
 
 	/*
 	 * We can override with custom divisors, else we use the board
@@ -1586,29 +1842,48 @@
 	    && (0 == chip_info->clk_freq.scr)) {
 		status = calculate_effective_freq(pl022,
 						  spi->max_speed_hz,
-						  &chip_info->clk_freq);
+						  &clk_freq);
 		if (status < 0)
 			goto err_config_params;
 	} else {
-		if ((chip_info->clk_freq.cpsdvsr % 2) != 0)
-			chip_info->clk_freq.cpsdvsr =
-				chip_info->clk_freq.cpsdvsr - 1;
+		memcpy(&clk_freq, &chip_info->clk_freq, sizeof(clk_freq));
+		if ((clk_freq.cpsdvsr % 2) != 0)
+			clk_freq.cpsdvsr =
+				clk_freq.cpsdvsr - 1;
 	}
+	if ((clk_freq.cpsdvsr < CPSDVR_MIN)
+	    || (clk_freq.cpsdvsr > CPSDVR_MAX)) {
+		dev_err(&spi->dev,
+			"cpsdvsr is configured incorrectly\n");
+		goto err_config_params;
+	}
+
+
 	status = verify_controller_parameters(pl022, chip_info);
 	if (status) {
 		dev_err(&spi->dev, "controller data is incorrect");
 		goto err_config_params;
 	}
+
 	/* Now set controller state based on controller data */
 	chip->xfer_type = chip_info->com_mode;
-	chip->cs_control = chip_info->cs_control;
+	if (!chip_info->cs_control) {
+		chip->cs_control = null_cs_control;
+		dev_warn(&spi->dev,
+			 "chip select function is NULL for this chip\n");
+	} else
+		chip->cs_control = chip_info->cs_control;
 
-	if (chip_info->data_size <= 8) {
-		dev_dbg(&spi->dev, "1 <= n <=8 bits per word\n");
+	if (bits <= 3) {
+		/* PL022 doesn't support less than 4-bits */
+		status = -ENOTSUPP;
+		goto err_config_params;
+	} else if (bits <= 8) {
+		dev_dbg(&spi->dev, "4 <= n <=8 bits per word\n");
 		chip->n_bytes = 1;
 		chip->read = READING_U8;
 		chip->write = WRITING_U8;
-	} else if (chip_info->data_size <= 16) {
+	} else if (bits <= 16) {
 		dev_dbg(&spi->dev, "9 <= n <= 16 bits per word\n");
 		chip->n_bytes = 2;
 		chip->read = READING_U16;
@@ -1625,6 +1900,7 @@
 			dev_err(&spi->dev,
 				"a standard pl022 can only handle "
 				"1 <= n <= 16 bit words\n");
+			status = -ENOTSUPP;
 			goto err_config_params;
 		}
 	}
@@ -1636,9 +1912,8 @@
 	chip->cpsr = 0;
 	if ((chip_info->com_mode == DMA_TRANSFER)
 	    && ((pl022->master_info)->enable_dma)) {
-		chip->enable_dma = 1;
+		chip->enable_dma = true;
 		dev_dbg(&spi->dev, "DMA mode set in controller state\n");
-		status = process_dma_info(chip_info, chip);
 		if (status < 0)
 			goto err_config_params;
 		SSP_WRITE_BITS(chip->dmacr, SSP_DMA_ENABLED,
@@ -1646,7 +1921,7 @@
 		SSP_WRITE_BITS(chip->dmacr, SSP_DMA_ENABLED,
 			       SSP_DMACR_MASK_TXDMAE, 1);
 	} else {
-		chip->enable_dma = 0;
+		chip->enable_dma = false;
 		dev_dbg(&spi->dev, "DMA mode NOT set in controller state\n");
 		SSP_WRITE_BITS(chip->dmacr, SSP_DMA_DISABLED,
 			       SSP_DMACR_MASK_RXDMAE, 0);
@@ -1654,10 +1929,12 @@
 			       SSP_DMACR_MASK_TXDMAE, 1);
 	}
 
-	chip->cpsr = chip_info->clk_freq.cpsdvsr;
+	chip->cpsr = clk_freq.cpsdvsr;
 
 	/* Special setup for the ST micro extended control registers */
 	if (pl022->vendor->extended_cr) {
+		u32 etx;
+
 		if (pl022->vendor->pl023) {
 			/* These bits are only in the PL023 */
 			SSP_WRITE_BITS(chip->cr1, chip_info->clkdelay,
@@ -1673,29 +1950,51 @@
 			SSP_WRITE_BITS(chip->cr1, chip_info->wait_state,
 				       SSP_CR1_MASK_MWAIT_ST, 6);
 		}
-		SSP_WRITE_BITS(chip->cr0, chip_info->data_size,
+		SSP_WRITE_BITS(chip->cr0, bits - 1,
 			       SSP_CR0_MASK_DSS_ST, 0);
-		SSP_WRITE_BITS(chip->cr1, chip_info->endian_rx,
-			       SSP_CR1_MASK_RENDN_ST, 4);
-		SSP_WRITE_BITS(chip->cr1, chip_info->endian_tx,
-			       SSP_CR1_MASK_TENDN_ST, 5);
+
+		if (spi->mode & SPI_LSB_FIRST) {
+			tmp = SSP_RX_LSB;
+			etx = SSP_TX_LSB;
+		} else {
+			tmp = SSP_RX_MSB;
+			etx = SSP_TX_MSB;
+		}
+		SSP_WRITE_BITS(chip->cr1, tmp, SSP_CR1_MASK_RENDN_ST, 4);
+		SSP_WRITE_BITS(chip->cr1, etx, SSP_CR1_MASK_TENDN_ST, 5);
 		SSP_WRITE_BITS(chip->cr1, chip_info->rx_lev_trig,
 			       SSP_CR1_MASK_RXIFLSEL_ST, 7);
 		SSP_WRITE_BITS(chip->cr1, chip_info->tx_lev_trig,
 			       SSP_CR1_MASK_TXIFLSEL_ST, 10);
 	} else {
-		SSP_WRITE_BITS(chip->cr0, chip_info->data_size,
+		SSP_WRITE_BITS(chip->cr0, bits - 1,
 			       SSP_CR0_MASK_DSS, 0);
 		SSP_WRITE_BITS(chip->cr0, chip_info->iface,
 			       SSP_CR0_MASK_FRF, 4);
 	}
+
 	/* Stuff that is common for all versions */
-	SSP_WRITE_BITS(chip->cr0, chip_info->clk_pol, SSP_CR0_MASK_SPO, 6);
-	SSP_WRITE_BITS(chip->cr0, chip_info->clk_phase, SSP_CR0_MASK_SPH, 7);
-	SSP_WRITE_BITS(chip->cr0, chip_info->clk_freq.scr, SSP_CR0_MASK_SCR, 8);
+	if (spi->mode & SPI_CPOL)
+		tmp = SSP_CLK_POL_IDLE_HIGH;
+	else
+		tmp = SSP_CLK_POL_IDLE_LOW;
+	SSP_WRITE_BITS(chip->cr0, tmp, SSP_CR0_MASK_SPO, 6);
+
+	if (spi->mode & SPI_CPHA)
+		tmp = SSP_CLK_SECOND_EDGE;
+	else
+		tmp = SSP_CLK_FIRST_EDGE;
+	SSP_WRITE_BITS(chip->cr0, tmp, SSP_CR0_MASK_SPH, 7);
+
+	SSP_WRITE_BITS(chip->cr0, clk_freq.scr, SSP_CR0_MASK_SCR, 8);
 	/* Loopback is available on all versions except PL023 */
-	if (!pl022->vendor->pl023)
-		SSP_WRITE_BITS(chip->cr1, chip_info->lbm, SSP_CR1_MASK_LBM, 0);
+	if (!pl022->vendor->pl023) {
+		if (spi->mode & SPI_LOOP)
+			tmp = LOOPBACK_ENABLED;
+		else
+			tmp = LOOPBACK_DISABLED;
+		SSP_WRITE_BITS(chip->cr1, tmp, SSP_CR1_MASK_LBM, 0);
+	}
 	SSP_WRITE_BITS(chip->cr1, SSP_DISABLED, SSP_CR1_MASK_SSE, 1);
 	SSP_WRITE_BITS(chip->cr1, chip_info->hierarchy, SSP_CR1_MASK_MS, 2);
 	SSP_WRITE_BITS(chip->cr1, chip_info->slave_tx_disable, SSP_CR1_MASK_SOD, 3);
@@ -1704,7 +2003,7 @@
 	spi_set_ctldata(spi, chip);
 	return status;
  err_config_params:
- err_first_setup:
+	spi_set_ctldata(spi, NULL);
 	kfree(chip);
 	return status;
 }
@@ -1766,12 +2065,21 @@
 	master->setup = pl022_setup;
 	master->transfer = pl022_transfer;
 
+	/*
+	 * Supports mode 0-3, loopback, and active low CS. Transfers are
+	 * always MS bit first on the original pl022.
+	 */
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP;
+	if (pl022->vendor->extended_cr)
+		master->mode_bits |= SPI_LSB_FIRST;
+
 	dev_dbg(&adev->dev, "BUSNO: %d\n", master->bus_num);
 
 	status = amba_request_regions(adev, NULL);
 	if (status)
 		goto err_no_ioregion;
 
+	pl022->phybase = adev->res.start;
 	pl022->virtbase = ioremap(adev->res.start, resource_size(&adev->res));
 	if (pl022->virtbase == NULL) {
 		status = -ENOMEM;
@@ -1798,6 +2106,14 @@
 		dev_err(&adev->dev, "probe - cannot get IRQ (%d)\n", status);
 		goto err_no_irq;
 	}
+
+	/* Get DMA channels */
+	if (platform_info->enable_dma) {
+		status = pl022_dma_probe(pl022);
+		if (status != 0)
+			goto err_no_dma;
+	}
+
 	/* Initialize and start queue */
 	status = init_queue(pl022);
 	if (status != 0) {
@@ -1826,6 +2142,8 @@
  err_start_queue:
  err_init_queue:
 	destroy_queue(pl022);
+	pl022_dma_remove(pl022);
+ err_no_dma:
 	free_irq(adev->irq[0], pl022);
  err_no_irq:
 	clk_put(pl022->clk);
@@ -1856,6 +2174,7 @@
 		return status;
 	}
 	load_ssp_default_config(pl022);
+	pl022_dma_remove(pl022);
 	free_irq(adev->irq[0], pl022);
 	clk_disable(pl022->clk);
 	clk_put(pl022->clk);
diff --git a/drivers/spi/atmel_spi.c b/drivers/spi/atmel_spi.c
index c4e0442..154529a 100644
--- a/drivers/spi/atmel_spi.c
+++ b/drivers/spi/atmel_spi.c
@@ -654,6 +654,8 @@
 	struct spi_transfer	*xfer;
 	unsigned long		flags;
 	struct device		*controller = spi->master->dev.parent;
+	u8			bits;
+	struct atmel_spi_device	*asd;
 
 	as = spi_master_get_devdata(spi->master);
 
@@ -672,8 +674,18 @@
 			return -EINVAL;
 		}
 
+		if (xfer->bits_per_word) {
+			asd = spi->controller_state;
+			bits = (asd->csr >> 4) & 0xf;
+			if (bits != xfer->bits_per_word - 8) {
+				dev_dbg(&spi->dev, "you can't yet change "
+					 "bits_per_word in transfers\n");
+				return -ENOPROTOOPT;
+			}
+		}
+
 		/* FIXME implement these protocol options!! */
-		if (xfer->bits_per_word || xfer->speed_hz) {
+		if (xfer->speed_hz) {
 			dev_dbg(&spi->dev, "no protocol options yet\n");
 			return -ENOPROTOOPT;
 		}
diff --git a/drivers/spi/dw_spi.c b/drivers/spi/dw_spi.c
index 5624785..9043931 100644
--- a/drivers/spi/dw_spi.c
+++ b/drivers/spi/dw_spi.c
@@ -131,6 +131,7 @@
 	.owner		= THIS_MODULE,
 	.open		= spi_show_regs_open,
 	.read		= spi_show_regs,
+	.llseek		= default_llseek,
 };
 
 static int mrst_spi_debugfs_init(struct dw_spi *dws)
diff --git a/drivers/spi/omap2_mcspi.c b/drivers/spi/omap2_mcspi.c
index b3a94ca..2a651e6 100644
--- a/drivers/spi/omap2_mcspi.c
+++ b/drivers/spi/omap2_mcspi.c
@@ -296,6 +296,19 @@
 	return 0;
 }
 
+static int mcspi_wait_for_reg_bit(void __iomem *reg, unsigned long bit)
+{
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(1000);
+	while (!(__raw_readl(reg) & bit)) {
+		if (time_after(jiffies, timeout))
+			return -1;
+		cpu_relax();
+	}
+	return 0;
+}
+
 static unsigned
 omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 {
@@ -309,11 +322,14 @@
 	u32			l;
 	u8			* rx;
 	const u8		* tx;
+	void __iomem		*chstat_reg;
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
 	l = mcspi_cached_chconf0(spi);
 
+	chstat_reg = cs->base + OMAP2_MCSPI_CHSTAT0;
+
 	count = xfer->len;
 	c = count;
 	word_len = cs->word_len;
@@ -382,6 +398,16 @@
 	if (tx != NULL) {
 		wait_for_completion(&mcspi_dma->dma_tx_completion);
 		dma_unmap_single(NULL, xfer->tx_dma, count, DMA_TO_DEVICE);
+
+		/* for TX_ONLY mode, be sure all words have shifted out */
+		if (rx == NULL) {
+			if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_TXS) < 0)
+				dev_err(&spi->dev, "TXS timed out\n");
+			else if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_EOT) < 0)
+				dev_err(&spi->dev, "EOT timed out\n");
+		}
 	}
 
 	if (rx != NULL) {
@@ -435,19 +461,6 @@
 	return count;
 }
 
-static int mcspi_wait_for_reg_bit(void __iomem *reg, unsigned long bit)
-{
-	unsigned long timeout;
-
-	timeout = jiffies + msecs_to_jiffies(1000);
-	while (!(__raw_readl(reg) & bit)) {
-		if (time_after(jiffies, timeout))
-			return -1;
-		cpu_relax();
-	}
-	return 0;
-}
-
 static unsigned
 omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer)
 {
@@ -489,10 +502,8 @@
 					dev_err(&spi->dev, "TXS timed out\n");
 					goto out;
 				}
-#ifdef VERBOSE
-				dev_dbg(&spi->dev, "write-%d %02x\n",
+				dev_vdbg(&spi->dev, "write-%d %02x\n",
 						word_len, *tx);
-#endif
 				__raw_writel(*tx++, tx_reg);
 			}
 			if (rx != NULL) {
@@ -506,10 +517,8 @@
 				    (l & OMAP2_MCSPI_CHCONF_TURBO)) {
 					omap2_mcspi_set_enable(spi, 0);
 					*rx++ = __raw_readl(rx_reg);
-#ifdef VERBOSE
-					dev_dbg(&spi->dev, "read-%d %02x\n",
+					dev_vdbg(&spi->dev, "read-%d %02x\n",
 						    word_len, *(rx - 1));
-#endif
 					if (mcspi_wait_for_reg_bit(chstat_reg,
 						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
 						dev_err(&spi->dev,
@@ -522,10 +531,8 @@
 				}
 
 				*rx++ = __raw_readl(rx_reg);
-#ifdef VERBOSE
-				dev_dbg(&spi->dev, "read-%d %02x\n",
+				dev_vdbg(&spi->dev, "read-%d %02x\n",
 						word_len, *(rx - 1));
-#endif
 			}
 		} while (c);
 	} else if (word_len <= 16) {
@@ -542,10 +549,8 @@
 					dev_err(&spi->dev, "TXS timed out\n");
 					goto out;
 				}
-#ifdef VERBOSE
-				dev_dbg(&spi->dev, "write-%d %04x\n",
+				dev_vdbg(&spi->dev, "write-%d %04x\n",
 						word_len, *tx);
-#endif
 				__raw_writel(*tx++, tx_reg);
 			}
 			if (rx != NULL) {
@@ -559,10 +564,8 @@
 				    (l & OMAP2_MCSPI_CHCONF_TURBO)) {
 					omap2_mcspi_set_enable(spi, 0);
 					*rx++ = __raw_readl(rx_reg);
-#ifdef VERBOSE
-					dev_dbg(&spi->dev, "read-%d %04x\n",
+					dev_vdbg(&spi->dev, "read-%d %04x\n",
 						    word_len, *(rx - 1));
-#endif
 					if (mcspi_wait_for_reg_bit(chstat_reg,
 						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
 						dev_err(&spi->dev,
@@ -575,10 +578,8 @@
 				}
 
 				*rx++ = __raw_readl(rx_reg);
-#ifdef VERBOSE
-				dev_dbg(&spi->dev, "read-%d %04x\n",
+				dev_vdbg(&spi->dev, "read-%d %04x\n",
 						word_len, *(rx - 1));
-#endif
 			}
 		} while (c);
 	} else if (word_len <= 32) {
@@ -595,10 +596,8 @@
 					dev_err(&spi->dev, "TXS timed out\n");
 					goto out;
 				}
-#ifdef VERBOSE
-				dev_dbg(&spi->dev, "write-%d %08x\n",
+				dev_vdbg(&spi->dev, "write-%d %08x\n",
 						word_len, *tx);
-#endif
 				__raw_writel(*tx++, tx_reg);
 			}
 			if (rx != NULL) {
@@ -612,10 +611,8 @@
 				    (l & OMAP2_MCSPI_CHCONF_TURBO)) {
 					omap2_mcspi_set_enable(spi, 0);
 					*rx++ = __raw_readl(rx_reg);
-#ifdef VERBOSE
-					dev_dbg(&spi->dev, "read-%d %08x\n",
+					dev_vdbg(&spi->dev, "read-%d %08x\n",
 						    word_len, *(rx - 1));
-#endif
 					if (mcspi_wait_for_reg_bit(chstat_reg,
 						OMAP2_MCSPI_CHSTAT_RXS) < 0) {
 						dev_err(&spi->dev,
@@ -628,10 +625,8 @@
 				}
 
 				*rx++ = __raw_readl(rx_reg);
-#ifdef VERBOSE
-				dev_dbg(&spi->dev, "read-%d %08x\n",
+				dev_vdbg(&spi->dev, "read-%d %08x\n",
 						word_len, *(rx - 1));
-#endif
 			}
 		} while (c);
 	}
@@ -644,6 +639,12 @@
 		} else if (mcspi_wait_for_reg_bit(chstat_reg,
 				OMAP2_MCSPI_CHSTAT_EOT) < 0)
 			dev_err(&spi->dev, "EOT timed out\n");
+
+		/* disable chan to purge rx datas received in TX_ONLY transfer,
+		 * otherwise these rx datas will affect the direct following
+		 * RX_ONLY transfer.
+		 */
+		omap2_mcspi_set_enable(spi, 0);
 	}
 out:
 	omap2_mcspi_set_enable(spi, 1);
diff --git a/drivers/spi/orion_spi.c b/drivers/spi/orion_spi.c
index 3aea50d..0b677dc 100644
--- a/drivers/spi/orion_spi.c
+++ b/drivers/spi/orion_spi.c
@@ -404,7 +404,7 @@
 			goto msg_rejected;
 		}
 
-		if ((t != NULL) && t->bits_per_word)
+		if (t->bits_per_word)
 			bits_per_word = t->bits_per_word;
 
 		if ((bits_per_word != 8) && (bits_per_word != 16)) {
@@ -415,7 +415,7 @@
 			goto msg_rejected;
 		}
 		/*make sure buffer length is even when working in 16 bit mode*/
-		if ((t != NULL) && (t->bits_per_word == 16) && (t->len & 1)) {
+		if ((t->bits_per_word == 16) && (t->len & 1)) {
 			dev_err(&spi->dev,
 				"message rejected : "
 				"odd data length (%d) while in 16 bit mode\n",
diff --git a/drivers/spi/spi_bfin5xx.c b/drivers/spi/spi_bfin5xx.c
index 10a6dc3..ab483a0 100644
--- a/drivers/spi/spi_bfin5xx.c
+++ b/drivers/spi/spi_bfin5xx.c
@@ -1,7 +1,7 @@
 /*
  * Blackfin On-Chip SPI Driver
  *
- * Copyright 2004-2007 Analog Devices Inc.
+ * Copyright 2004-2010 Analog Devices Inc.
  *
  * Enter bugs at http://blackfin.uclinux.org/
  *
@@ -41,13 +41,16 @@
 #define RUNNING_STATE	((void *)1)
 #define DONE_STATE	((void *)2)
 #define ERROR_STATE	((void *)-1)
-#define QUEUE_RUNNING	0
-#define QUEUE_STOPPED	1
 
-/* Value to send if no TX value is supplied */
-#define SPI_IDLE_TXVAL 0x0000
+struct bfin_spi_master_data;
 
-struct driver_data {
+struct bfin_spi_transfer_ops {
+	void (*write) (struct bfin_spi_master_data *);
+	void (*read) (struct bfin_spi_master_data *);
+	void (*duplex) (struct bfin_spi_master_data *);
+};
+
+struct bfin_spi_master_data {
 	/* Driver model hookup */
 	struct platform_device *pdev;
 
@@ -69,7 +72,7 @@
 	spinlock_t lock;
 	struct list_head queue;
 	int busy;
-	int run;
+	bool running;
 
 	/* Message Transfer pump */
 	struct tasklet_struct pump_transfers;
@@ -77,7 +80,7 @@
 	/* Current message transfer state info */
 	struct spi_message *cur_msg;
 	struct spi_transfer *cur_transfer;
-	struct chip_data *cur_chip;
+	struct bfin_spi_slave_data *cur_chip;
 	size_t len_in_bytes;
 	size_t len;
 	void *tx;
@@ -92,38 +95,37 @@
 	dma_addr_t rx_dma;
 	dma_addr_t tx_dma;
 
+	int irq_requested;
+	int spi_irq;
+
 	size_t rx_map_len;
 	size_t tx_map_len;
 	u8 n_bytes;
+	u16 ctrl_reg;
+	u16 flag_reg;
+
 	int cs_change;
-	void (*write) (struct driver_data *);
-	void (*read) (struct driver_data *);
-	void (*duplex) (struct driver_data *);
+	const struct bfin_spi_transfer_ops *ops;
 };
 
-struct chip_data {
+struct bfin_spi_slave_data {
 	u16 ctl_reg;
 	u16 baud;
 	u16 flag;
 
 	u8 chip_select_num;
-	u8 n_bytes;
-	u8 width;		/* 0 or 1 */
 	u8 enable_dma;
-	u8 bits_per_word;	/* 8 or 16 */
-	u8 cs_change_per_word;
 	u16 cs_chg_udelay;	/* Some devices require > 255usec delay */
 	u32 cs_gpio;
 	u16 idle_tx_val;
-	void (*write) (struct driver_data *);
-	void (*read) (struct driver_data *);
-	void (*duplex) (struct driver_data *);
+	u8 pio_interrupt;	/* use spi data irq */
+	const struct bfin_spi_transfer_ops *ops;
 };
 
 #define DEFINE_SPI_REG(reg, off) \
-static inline u16 read_##reg(struct driver_data *drv_data) \
+static inline u16 read_##reg(struct bfin_spi_master_data *drv_data) \
 	{ return bfin_read16(drv_data->regs_base + off); } \
-static inline void write_##reg(struct driver_data *drv_data, u16 v) \
+static inline void write_##reg(struct bfin_spi_master_data *drv_data, u16 v) \
 	{ bfin_write16(drv_data->regs_base + off, v); }
 
 DEFINE_SPI_REG(CTRL, 0x00)
@@ -134,7 +136,7 @@
 DEFINE_SPI_REG(BAUD, 0x14)
 DEFINE_SPI_REG(SHAW, 0x18)
 
-static void bfin_spi_enable(struct driver_data *drv_data)
+static void bfin_spi_enable(struct bfin_spi_master_data *drv_data)
 {
 	u16 cr;
 
@@ -142,7 +144,7 @@
 	write_CTRL(drv_data, (cr | BIT_CTL_ENABLE));
 }
 
-static void bfin_spi_disable(struct driver_data *drv_data)
+static void bfin_spi_disable(struct bfin_spi_master_data *drv_data)
 {
 	u16 cr;
 
@@ -165,7 +167,7 @@
 	return spi_baud;
 }
 
-static int bfin_spi_flush(struct driver_data *drv_data)
+static int bfin_spi_flush(struct bfin_spi_master_data *drv_data)
 {
 	unsigned long limit = loops_per_jiffy << 1;
 
@@ -179,13 +181,12 @@
 }
 
 /* Chip select operation functions for cs_change flag */
-static void bfin_spi_cs_active(struct driver_data *drv_data, struct chip_data *chip)
+static void bfin_spi_cs_active(struct bfin_spi_master_data *drv_data, struct bfin_spi_slave_data *chip)
 {
-	if (likely(chip->chip_select_num)) {
+	if (likely(chip->chip_select_num < MAX_CTRL_CS)) {
 		u16 flag = read_FLAG(drv_data);
 
-		flag |= chip->flag;
-		flag &= ~(chip->flag << 8);
+		flag &= ~chip->flag;
 
 		write_FLAG(drv_data, flag);
 	} else {
@@ -193,13 +194,13 @@
 	}
 }
 
-static void bfin_spi_cs_deactive(struct driver_data *drv_data, struct chip_data *chip)
+static void bfin_spi_cs_deactive(struct bfin_spi_master_data *drv_data,
+                                 struct bfin_spi_slave_data *chip)
 {
-	if (likely(chip->chip_select_num)) {
+	if (likely(chip->chip_select_num < MAX_CTRL_CS)) {
 		u16 flag = read_FLAG(drv_data);
 
-		flag &= ~chip->flag;
-		flag |= (chip->flag << 8);
+		flag |= chip->flag;
 
 		write_FLAG(drv_data, flag);
 	} else {
@@ -211,16 +212,43 @@
 		udelay(chip->cs_chg_udelay);
 }
 
-/* stop controller and re-config current chip*/
-static void bfin_spi_restore_state(struct driver_data *drv_data)
+/* enable or disable the pin muxed by GPIO and SPI CS to work as SPI CS */
+static inline void bfin_spi_cs_enable(struct bfin_spi_master_data *drv_data,
+                                      struct bfin_spi_slave_data *chip)
 {
-	struct chip_data *chip = drv_data->cur_chip;
+	if (chip->chip_select_num < MAX_CTRL_CS) {
+		u16 flag = read_FLAG(drv_data);
+
+		flag |= (chip->flag >> 8);
+
+		write_FLAG(drv_data, flag);
+	}
+}
+
+static inline void bfin_spi_cs_disable(struct bfin_spi_master_data *drv_data,
+                                       struct bfin_spi_slave_data *chip)
+{
+	if (chip->chip_select_num < MAX_CTRL_CS) {
+		u16 flag = read_FLAG(drv_data);
+
+		flag &= ~(chip->flag >> 8);
+
+		write_FLAG(drv_data, flag);
+	}
+}
+
+/* stop controller and re-config current chip*/
+static void bfin_spi_restore_state(struct bfin_spi_master_data *drv_data)
+{
+	struct bfin_spi_slave_data *chip = drv_data->cur_chip;
 
 	/* Clear status and disable clock */
 	write_STAT(drv_data, BIT_STAT_CLR);
 	bfin_spi_disable(drv_data);
 	dev_dbg(&drv_data->pdev->dev, "restoring spi ctl state\n");
 
+	SSYNC();
+
 	/* Load the registers */
 	write_CTRL(drv_data, chip->ctl_reg);
 	write_BAUD(drv_data, chip->baud);
@@ -230,49 +258,12 @@
 }
 
 /* used to kick off transfer in rx mode and read unwanted RX data */
-static inline void bfin_spi_dummy_read(struct driver_data *drv_data)
+static inline void bfin_spi_dummy_read(struct bfin_spi_master_data *drv_data)
 {
 	(void) read_RDBR(drv_data);
 }
 
-static void bfin_spi_null_writer(struct driver_data *drv_data)
-{
-	u8 n_bytes = drv_data->n_bytes;
-	u16 tx_val = drv_data->cur_chip->idle_tx_val;
-
-	/* clear RXS (we check for RXS inside the loop) */
-	bfin_spi_dummy_read(drv_data);
-
-	while (drv_data->tx < drv_data->tx_end) {
-		write_TDBR(drv_data, tx_val);
-		drv_data->tx += n_bytes;
-		/* wait until transfer finished.
-		   checking SPIF or TXS may not guarantee transfer completion */
-		while (!(read_STAT(drv_data) & BIT_STAT_RXS))
-			cpu_relax();
-		/* discard RX data and clear RXS */
-		bfin_spi_dummy_read(drv_data);
-	}
-}
-
-static void bfin_spi_null_reader(struct driver_data *drv_data)
-{
-	u8 n_bytes = drv_data->n_bytes;
-	u16 tx_val = drv_data->cur_chip->idle_tx_val;
-
-	/* discard old RX data and clear RXS */
-	bfin_spi_dummy_read(drv_data);
-
-	while (drv_data->rx < drv_data->rx_end) {
-		write_TDBR(drv_data, tx_val);
-		drv_data->rx += n_bytes;
-		while (!(read_STAT(drv_data) & BIT_STAT_RXS))
-			cpu_relax();
-		bfin_spi_dummy_read(drv_data);
-	}
-}
-
-static void bfin_spi_u8_writer(struct driver_data *drv_data)
+static void bfin_spi_u8_writer(struct bfin_spi_master_data *drv_data)
 {
 	/* clear RXS (we check for RXS inside the loop) */
 	bfin_spi_dummy_read(drv_data);
@@ -288,25 +279,7 @@
 	}
 }
 
-static void bfin_spi_u8_cs_chg_writer(struct driver_data *drv_data)
-{
-	struct chip_data *chip = drv_data->cur_chip;
-
-	/* clear RXS (we check for RXS inside the loop) */
-	bfin_spi_dummy_read(drv_data);
-
-	while (drv_data->tx < drv_data->tx_end) {
-		bfin_spi_cs_active(drv_data, chip);
-		write_TDBR(drv_data, (*(u8 *) (drv_data->tx++)));
-		/* make sure transfer finished before deactiving CS */
-		while (!(read_STAT(drv_data) & BIT_STAT_RXS))
-			cpu_relax();
-		bfin_spi_dummy_read(drv_data);
-		bfin_spi_cs_deactive(drv_data, chip);
-	}
-}
-
-static void bfin_spi_u8_reader(struct driver_data *drv_data)
+static void bfin_spi_u8_reader(struct bfin_spi_master_data *drv_data)
 {
 	u16 tx_val = drv_data->cur_chip->idle_tx_val;
 
@@ -321,25 +294,7 @@
 	}
 }
 
-static void bfin_spi_u8_cs_chg_reader(struct driver_data *drv_data)
-{
-	struct chip_data *chip = drv_data->cur_chip;
-	u16 tx_val = chip->idle_tx_val;
-
-	/* discard old RX data and clear RXS */
-	bfin_spi_dummy_read(drv_data);
-
-	while (drv_data->rx < drv_data->rx_end) {
-		bfin_spi_cs_active(drv_data, chip);
-		write_TDBR(drv_data, tx_val);
-		while (!(read_STAT(drv_data) & BIT_STAT_RXS))
-			cpu_relax();
-		*(u8 *) (drv_data->rx++) = read_RDBR(drv_data);
-		bfin_spi_cs_deactive(drv_data, chip);
-	}
-}
-
-static void bfin_spi_u8_duplex(struct driver_data *drv_data)
+static void bfin_spi_u8_duplex(struct bfin_spi_master_data *drv_data)
 {
 	/* discard old RX data and clear RXS */
 	bfin_spi_dummy_read(drv_data);
@@ -352,24 +307,13 @@
 	}
 }
 
-static void bfin_spi_u8_cs_chg_duplex(struct driver_data *drv_data)
-{
-	struct chip_data *chip = drv_data->cur_chip;
+static const struct bfin_spi_transfer_ops bfin_bfin_spi_transfer_ops_u8 = {
+	.write  = bfin_spi_u8_writer,
+	.read   = bfin_spi_u8_reader,
+	.duplex = bfin_spi_u8_duplex,
+};
 
-	/* discard old RX data and clear RXS */
-	bfin_spi_dummy_read(drv_data);
-
-	while (drv_data->rx < drv_data->rx_end) {
-		bfin_spi_cs_active(drv_data, chip);
-		write_TDBR(drv_data, (*(u8 *) (drv_data->tx++)));
-		while (!(read_STAT(drv_data) & BIT_STAT_RXS))
-			cpu_relax();
-		*(u8 *) (drv_data->rx++) = read_RDBR(drv_data);
-		bfin_spi_cs_deactive(drv_data, chip);
-	}
-}
-
-static void bfin_spi_u16_writer(struct driver_data *drv_data)
+static void bfin_spi_u16_writer(struct bfin_spi_master_data *drv_data)
 {
 	/* clear RXS (we check for RXS inside the loop) */
 	bfin_spi_dummy_read(drv_data);
@@ -386,26 +330,7 @@
 	}
 }
 
-static void bfin_spi_u16_cs_chg_writer(struct driver_data *drv_data)
-{
-	struct chip_data *chip = drv_data->cur_chip;
-
-	/* clear RXS (we check for RXS inside the loop) */
-	bfin_spi_dummy_read(drv_data);
-
-	while (drv_data->tx < drv_data->tx_end) {
-		bfin_spi_cs_active(drv_data, chip);
-		write_TDBR(drv_data, (*(u16 *) (drv_data->tx)));
-		drv_data->tx += 2;
-		/* make sure transfer finished before deactiving CS */
-		while (!(read_STAT(drv_data) & BIT_STAT_RXS))
-			cpu_relax();
-		bfin_spi_dummy_read(drv_data);
-		bfin_spi_cs_deactive(drv_data, chip);
-	}
-}
-
-static void bfin_spi_u16_reader(struct driver_data *drv_data)
+static void bfin_spi_u16_reader(struct bfin_spi_master_data *drv_data)
 {
 	u16 tx_val = drv_data->cur_chip->idle_tx_val;
 
@@ -421,26 +346,7 @@
 	}
 }
 
-static void bfin_spi_u16_cs_chg_reader(struct driver_data *drv_data)
-{
-	struct chip_data *chip = drv_data->cur_chip;
-	u16 tx_val = chip->idle_tx_val;
-
-	/* discard old RX data and clear RXS */
-	bfin_spi_dummy_read(drv_data);
-
-	while (drv_data->rx < drv_data->rx_end) {
-		bfin_spi_cs_active(drv_data, chip);
-		write_TDBR(drv_data, tx_val);
-		while (!(read_STAT(drv_data) & BIT_STAT_RXS))
-			cpu_relax();
-		*(u16 *) (drv_data->rx) = read_RDBR(drv_data);
-		drv_data->rx += 2;
-		bfin_spi_cs_deactive(drv_data, chip);
-	}
-}
-
-static void bfin_spi_u16_duplex(struct driver_data *drv_data)
+static void bfin_spi_u16_duplex(struct bfin_spi_master_data *drv_data)
 {
 	/* discard old RX data and clear RXS */
 	bfin_spi_dummy_read(drv_data);
@@ -455,27 +361,14 @@
 	}
 }
 
-static void bfin_spi_u16_cs_chg_duplex(struct driver_data *drv_data)
-{
-	struct chip_data *chip = drv_data->cur_chip;
+static const struct bfin_spi_transfer_ops bfin_bfin_spi_transfer_ops_u16 = {
+	.write  = bfin_spi_u16_writer,
+	.read   = bfin_spi_u16_reader,
+	.duplex = bfin_spi_u16_duplex,
+};
 
-	/* discard old RX data and clear RXS */
-	bfin_spi_dummy_read(drv_data);
-
-	while (drv_data->rx < drv_data->rx_end) {
-		bfin_spi_cs_active(drv_data, chip);
-		write_TDBR(drv_data, (*(u16 *) (drv_data->tx)));
-		drv_data->tx += 2;
-		while (!(read_STAT(drv_data) & BIT_STAT_RXS))
-			cpu_relax();
-		*(u16 *) (drv_data->rx) = read_RDBR(drv_data);
-		drv_data->rx += 2;
-		bfin_spi_cs_deactive(drv_data, chip);
-	}
-}
-
-/* test if ther is more transfer to be done */
-static void *bfin_spi_next_transfer(struct driver_data *drv_data)
+/* test if there is more transfer to be done */
+static void *bfin_spi_next_transfer(struct bfin_spi_master_data *drv_data)
 {
 	struct spi_message *msg = drv_data->cur_msg;
 	struct spi_transfer *trans = drv_data->cur_transfer;
@@ -494,9 +387,9 @@
  * caller already set message->status;
  * dma and pio irqs are blocked give finished message back
  */
-static void bfin_spi_giveback(struct driver_data *drv_data)
+static void bfin_spi_giveback(struct bfin_spi_master_data *drv_data)
 {
-	struct chip_data *chip = drv_data->cur_chip;
+	struct bfin_spi_slave_data *chip = drv_data->cur_chip;
 	struct spi_transfer *last_transfer;
 	unsigned long flags;
 	struct spi_message *msg;
@@ -525,10 +418,83 @@
 		msg->complete(msg->context);
 }
 
+/* spi data irq handler */
+static irqreturn_t bfin_spi_pio_irq_handler(int irq, void *dev_id)
+{
+	struct bfin_spi_master_data *drv_data = dev_id;
+	struct bfin_spi_slave_data *chip = drv_data->cur_chip;
+	struct spi_message *msg = drv_data->cur_msg;
+	int n_bytes = drv_data->n_bytes;
+
+	/* wait until transfer finished. */
+	while (!(read_STAT(drv_data) & BIT_STAT_RXS))
+		cpu_relax();
+
+	if ((drv_data->tx && drv_data->tx >= drv_data->tx_end) ||
+		(drv_data->rx && drv_data->rx >= (drv_data->rx_end - n_bytes))) {
+		/* last read */
+		if (drv_data->rx) {
+			dev_dbg(&drv_data->pdev->dev, "last read\n");
+			if (n_bytes == 2)
+				*(u16 *) (drv_data->rx) = read_RDBR(drv_data);
+			else if (n_bytes == 1)
+				*(u8 *) (drv_data->rx) = read_RDBR(drv_data);
+			drv_data->rx += n_bytes;
+		}
+
+		msg->actual_length += drv_data->len_in_bytes;
+		if (drv_data->cs_change)
+			bfin_spi_cs_deactive(drv_data, chip);
+		/* Move to next transfer */
+		msg->state = bfin_spi_next_transfer(drv_data);
+
+		disable_irq_nosync(drv_data->spi_irq);
+
+		/* Schedule transfer tasklet */
+		tasklet_schedule(&drv_data->pump_transfers);
+		return IRQ_HANDLED;
+	}
+
+	if (drv_data->rx && drv_data->tx) {
+		/* duplex */
+		dev_dbg(&drv_data->pdev->dev, "duplex: write_TDBR\n");
+		if (drv_data->n_bytes == 2) {
+			*(u16 *) (drv_data->rx) = read_RDBR(drv_data);
+			write_TDBR(drv_data, (*(u16 *) (drv_data->tx)));
+		} else if (drv_data->n_bytes == 1) {
+			*(u8 *) (drv_data->rx) = read_RDBR(drv_data);
+			write_TDBR(drv_data, (*(u8 *) (drv_data->tx)));
+		}
+	} else if (drv_data->rx) {
+		/* read */
+		dev_dbg(&drv_data->pdev->dev, "read: write_TDBR\n");
+		if (drv_data->n_bytes == 2)
+			*(u16 *) (drv_data->rx) = read_RDBR(drv_data);
+		else if (drv_data->n_bytes == 1)
+			*(u8 *) (drv_data->rx) = read_RDBR(drv_data);
+		write_TDBR(drv_data, chip->idle_tx_val);
+	} else if (drv_data->tx) {
+		/* write */
+		dev_dbg(&drv_data->pdev->dev, "write: write_TDBR\n");
+		bfin_spi_dummy_read(drv_data);
+		if (drv_data->n_bytes == 2)
+			write_TDBR(drv_data, (*(u16 *) (drv_data->tx)));
+		else if (drv_data->n_bytes == 1)
+			write_TDBR(drv_data, (*(u8 *) (drv_data->tx)));
+	}
+
+	if (drv_data->tx)
+		drv_data->tx += n_bytes;
+	if (drv_data->rx)
+		drv_data->rx += n_bytes;
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t bfin_spi_dma_irq_handler(int irq, void *dev_id)
 {
-	struct driver_data *drv_data = dev_id;
-	struct chip_data *chip = drv_data->cur_chip;
+	struct bfin_spi_master_data *drv_data = dev_id;
+	struct bfin_spi_slave_data *chip = drv_data->cur_chip;
 	struct spi_message *msg = drv_data->cur_msg;
 	unsigned long timeout;
 	unsigned short dmastat = get_dma_curr_irqstat(drv_data->dma_channel);
@@ -540,10 +506,6 @@
 
 	clear_dma_irqstat(drv_data->dma_channel);
 
-	/* Wait for DMA to complete */
-	while (get_dma_curr_irqstat(drv_data->dma_channel) & DMA_RUN)
-		cpu_relax();
-
 	/*
 	 * wait for the last transaction shifted out.  HRM states:
 	 * at this point there may still be data in the SPI DMA FIFO waiting
@@ -551,8 +513,8 @@
 	 * register until it goes low for 2 successive reads
 	 */
 	if (drv_data->tx != NULL) {
-		while ((read_STAT(drv_data) & TXS) ||
-		       (read_STAT(drv_data) & TXS))
+		while ((read_STAT(drv_data) & BIT_STAT_TXS) ||
+		       (read_STAT(drv_data) & BIT_STAT_TXS))
 			cpu_relax();
 	}
 
@@ -561,14 +523,14 @@
 		dmastat, read_STAT(drv_data));
 
 	timeout = jiffies + HZ;
-	while (!(read_STAT(drv_data) & SPIF))
+	while (!(read_STAT(drv_data) & BIT_STAT_SPIF))
 		if (!time_before(jiffies, timeout)) {
 			dev_warn(&drv_data->pdev->dev, "timeout waiting for SPIF");
 			break;
 		} else
 			cpu_relax();
 
-	if ((dmastat & DMA_ERR) && (spistat & RBSY)) {
+	if ((dmastat & DMA_ERR) && (spistat & BIT_STAT_RBSY)) {
 		msg->state = ERROR_STATE;
 		dev_err(&drv_data->pdev->dev, "dma receive: fifo/buffer overflow\n");
 	} else {
@@ -588,20 +550,20 @@
 	dev_dbg(&drv_data->pdev->dev,
 		"disable dma channel irq%d\n",
 		drv_data->dma_channel);
-	dma_disable_irq(drv_data->dma_channel);
+	dma_disable_irq_nosync(drv_data->dma_channel);
 
 	return IRQ_HANDLED;
 }
 
 static void bfin_spi_pump_transfers(unsigned long data)
 {
-	struct driver_data *drv_data = (struct driver_data *)data;
+	struct bfin_spi_master_data *drv_data = (struct bfin_spi_master_data *)data;
 	struct spi_message *message = NULL;
 	struct spi_transfer *transfer = NULL;
 	struct spi_transfer *previous = NULL;
-	struct chip_data *chip = NULL;
-	u8 width;
-	u16 cr, dma_width, dma_config;
+	struct bfin_spi_slave_data *chip = NULL;
+	unsigned int bits_per_word;
+	u16 cr, cr_width, dma_width, dma_config;
 	u32 tranf_success = 1;
 	u8 full_duplex = 0;
 
@@ -639,7 +601,7 @@
 			udelay(previous->delay_usecs);
 	}
 
-	/* Setup the transfer state based on the type of transfer */
+	/* Flush any existing transfers that may be sitting in the hardware */
 	if (bfin_spi_flush(drv_data) == 0) {
 		dev_err(&drv_data->pdev->dev, "pump_transfers: flush failed\n");
 		message->status = -EIO;
@@ -679,52 +641,31 @@
 	drv_data->cs_change = transfer->cs_change;
 
 	/* Bits per word setup */
-	switch (transfer->bits_per_word) {
-	case 8:
+	bits_per_word = transfer->bits_per_word ? : message->spi->bits_per_word;
+	if (bits_per_word == 8) {
 		drv_data->n_bytes = 1;
-		width = CFG_SPI_WORDSIZE8;
-		drv_data->read = chip->cs_change_per_word ?
-			bfin_spi_u8_cs_chg_reader : bfin_spi_u8_reader;
-		drv_data->write = chip->cs_change_per_word ?
-			bfin_spi_u8_cs_chg_writer : bfin_spi_u8_writer;
-		drv_data->duplex = chip->cs_change_per_word ?
-			bfin_spi_u8_cs_chg_duplex : bfin_spi_u8_duplex;
-		break;
-
-	case 16:
+		drv_data->len = transfer->len;
+		cr_width = 0;
+		drv_data->ops = &bfin_bfin_spi_transfer_ops_u8;
+	} else if (bits_per_word == 16) {
 		drv_data->n_bytes = 2;
-		width = CFG_SPI_WORDSIZE16;
-		drv_data->read = chip->cs_change_per_word ?
-			bfin_spi_u16_cs_chg_reader : bfin_spi_u16_reader;
-		drv_data->write = chip->cs_change_per_word ?
-			bfin_spi_u16_cs_chg_writer : bfin_spi_u16_writer;
-		drv_data->duplex = chip->cs_change_per_word ?
-			bfin_spi_u16_cs_chg_duplex : bfin_spi_u16_duplex;
-		break;
-
-	default:
-		/* No change, the same as default setting */
-		drv_data->n_bytes = chip->n_bytes;
-		width = chip->width;
-		drv_data->write = drv_data->tx ? chip->write : bfin_spi_null_writer;
-		drv_data->read = drv_data->rx ? chip->read : bfin_spi_null_reader;
-		drv_data->duplex = chip->duplex ? chip->duplex : bfin_spi_null_writer;
-		break;
+		drv_data->len = (transfer->len) >> 1;
+		cr_width = BIT_CTL_WORDSIZE;
+		drv_data->ops = &bfin_bfin_spi_transfer_ops_u16;
+	} else {
+		dev_err(&drv_data->pdev->dev, "transfer: unsupported bits_per_word\n");
+		message->status = -EINVAL;
+		bfin_spi_giveback(drv_data);
+		return;
 	}
-	cr = (read_CTRL(drv_data) & (~BIT_CTL_TIMOD));
-	cr |= (width << 8);
+	cr = read_CTRL(drv_data) & ~(BIT_CTL_TIMOD | BIT_CTL_WORDSIZE);
+	cr |= cr_width;
 	write_CTRL(drv_data, cr);
 
-	if (width == CFG_SPI_WORDSIZE16) {
-		drv_data->len = (transfer->len) >> 1;
-	} else {
-		drv_data->len = transfer->len;
-	}
 	dev_dbg(&drv_data->pdev->dev,
-		"transfer: drv_data->write is %p, chip->write is %p, null_wr is %p\n",
-		drv_data->write, chip->write, bfin_spi_null_writer);
+		"transfer: drv_data->ops is %p, chip->ops is %p, u8_ops is %p\n",
+		drv_data->ops, chip->ops, &bfin_bfin_spi_transfer_ops_u8);
 
-	/* speed and width has been set on per message */
 	message->state = RUNNING_STATE;
 	dma_config = 0;
 
@@ -735,13 +676,11 @@
 		write_BAUD(drv_data, chip->baud);
 
 	write_STAT(drv_data, BIT_STAT_CLR);
-	cr = (read_CTRL(drv_data) & (~BIT_CTL_TIMOD));
-	if (drv_data->cs_change)
-		bfin_spi_cs_active(drv_data, chip);
+	bfin_spi_cs_active(drv_data, chip);
 
 	dev_dbg(&drv_data->pdev->dev,
 		"now pumping a transfer: width is %d, len is %d\n",
-		width, transfer->len);
+		cr_width, transfer->len);
 
 	/*
 	 * Try to map dma buffer and do a dma transfer.  If successful use,
@@ -760,7 +699,7 @@
 		/* config dma channel */
 		dev_dbg(&drv_data->pdev->dev, "doing dma transfer\n");
 		set_dma_x_count(drv_data->dma_channel, drv_data->len);
-		if (width == CFG_SPI_WORDSIZE16) {
+		if (cr_width == BIT_CTL_WORDSIZE) {
 			set_dma_x_modify(drv_data->dma_channel, 2);
 			dma_width = WDSIZE_16;
 		} else {
@@ -846,73 +785,100 @@
 		dma_enable_irq(drv_data->dma_channel);
 		local_irq_restore(flags);
 
-	} else {
-		/* IO mode write then read */
-		dev_dbg(&drv_data->pdev->dev, "doing IO transfer\n");
-
-		/* we always use SPI_WRITE mode. SPI_READ mode
-		   seems to have problems with setting up the
-		   output value in TDBR prior to the transfer. */
-		write_CTRL(drv_data, (cr | CFG_SPI_WRITE));
-
-		if (full_duplex) {
-			/* full duplex mode */
-			BUG_ON((drv_data->tx_end - drv_data->tx) !=
-			       (drv_data->rx_end - drv_data->rx));
-			dev_dbg(&drv_data->pdev->dev,
-				"IO duplex: cr is 0x%x\n", cr);
-
-			drv_data->duplex(drv_data);
-
-			if (drv_data->tx != drv_data->tx_end)
-				tranf_success = 0;
-		} else if (drv_data->tx != NULL) {
-			/* write only half duplex */
-			dev_dbg(&drv_data->pdev->dev,
-				"IO write: cr is 0x%x\n", cr);
-
-			drv_data->write(drv_data);
-
-			if (drv_data->tx != drv_data->tx_end)
-				tranf_success = 0;
-		} else if (drv_data->rx != NULL) {
-			/* read only half duplex */
-			dev_dbg(&drv_data->pdev->dev,
-				"IO read: cr is 0x%x\n", cr);
-
-			drv_data->read(drv_data);
-			if (drv_data->rx != drv_data->rx_end)
-				tranf_success = 0;
-		}
-
-		if (!tranf_success) {
-			dev_dbg(&drv_data->pdev->dev,
-				"IO write error!\n");
-			message->state = ERROR_STATE;
-		} else {
-			/* Update total byte transfered */
-			message->actual_length += drv_data->len_in_bytes;
-			/* Move to next transfer of this msg */
-			message->state = bfin_spi_next_transfer(drv_data);
-			if (drv_data->cs_change)
-				bfin_spi_cs_deactive(drv_data, chip);
-		}
-		/* Schedule next transfer tasklet */
-		tasklet_schedule(&drv_data->pump_transfers);
+		return;
 	}
+
+	/*
+	 * We always use SPI_WRITE mode (transfer starts with TDBR write).
+	 * SPI_READ mode (transfer starts with RDBR read) seems to have
+	 * problems with setting up the output value in TDBR prior to the
+	 * start of the transfer.
+	 */
+	write_CTRL(drv_data, cr | BIT_CTL_TXMOD);
+
+	if (chip->pio_interrupt) {
+		/* SPI irq should have been disabled by now */
+
+		/* discard old RX data and clear RXS */
+		bfin_spi_dummy_read(drv_data);
+
+		/* start transfer */
+		if (drv_data->tx == NULL)
+			write_TDBR(drv_data, chip->idle_tx_val);
+		else {
+			if (bits_per_word == 8)
+				write_TDBR(drv_data, (*(u8 *) (drv_data->tx)));
+			else
+				write_TDBR(drv_data, (*(u16 *) (drv_data->tx)));
+			drv_data->tx += drv_data->n_bytes;
+		}
+
+		/* once TDBR is empty, interrupt is triggered */
+		enable_irq(drv_data->spi_irq);
+		return;
+	}
+
+	/* IO mode */
+	dev_dbg(&drv_data->pdev->dev, "doing IO transfer\n");
+
+	if (full_duplex) {
+		/* full duplex mode */
+		BUG_ON((drv_data->tx_end - drv_data->tx) !=
+		       (drv_data->rx_end - drv_data->rx));
+		dev_dbg(&drv_data->pdev->dev,
+			"IO duplex: cr is 0x%x\n", cr);
+
+		drv_data->ops->duplex(drv_data);
+
+		if (drv_data->tx != drv_data->tx_end)
+			tranf_success = 0;
+	} else if (drv_data->tx != NULL) {
+		/* write only half duplex */
+		dev_dbg(&drv_data->pdev->dev,
+			"IO write: cr is 0x%x\n", cr);
+
+		drv_data->ops->write(drv_data);
+
+		if (drv_data->tx != drv_data->tx_end)
+			tranf_success = 0;
+	} else if (drv_data->rx != NULL) {
+		/* read only half duplex */
+		dev_dbg(&drv_data->pdev->dev,
+			"IO read: cr is 0x%x\n", cr);
+
+		drv_data->ops->read(drv_data);
+		if (drv_data->rx != drv_data->rx_end)
+			tranf_success = 0;
+	}
+
+	if (!tranf_success) {
+		dev_dbg(&drv_data->pdev->dev,
+			"IO write error!\n");
+		message->state = ERROR_STATE;
+	} else {
+		/* Update total byte transfered */
+		message->actual_length += drv_data->len_in_bytes;
+		/* Move to next transfer of this msg */
+		message->state = bfin_spi_next_transfer(drv_data);
+		if (drv_data->cs_change)
+			bfin_spi_cs_deactive(drv_data, chip);
+	}
+
+	/* Schedule next transfer tasklet */
+	tasklet_schedule(&drv_data->pump_transfers);
 }
 
 /* pop a msg from queue and kick off real transfer */
 static void bfin_spi_pump_messages(struct work_struct *work)
 {
-	struct driver_data *drv_data;
+	struct bfin_spi_master_data *drv_data;
 	unsigned long flags;
 
-	drv_data = container_of(work, struct driver_data, pump_messages);
+	drv_data = container_of(work, struct bfin_spi_master_data, pump_messages);
 
 	/* Lock queue and check for queue work */
 	spin_lock_irqsave(&drv_data->lock, flags);
-	if (list_empty(&drv_data->queue) || drv_data->run == QUEUE_STOPPED) {
+	if (list_empty(&drv_data->queue) || !drv_data->running) {
 		/* pumper kicked off but no work to do */
 		drv_data->busy = 0;
 		spin_unlock_irqrestore(&drv_data->lock, flags);
@@ -962,12 +928,12 @@
  */
 static int bfin_spi_transfer(struct spi_device *spi, struct spi_message *msg)
 {
-	struct driver_data *drv_data = spi_master_get_devdata(spi->master);
+	struct bfin_spi_master_data *drv_data = spi_master_get_devdata(spi->master);
 	unsigned long flags;
 
 	spin_lock_irqsave(&drv_data->lock, flags);
 
-	if (drv_data->run == QUEUE_STOPPED) {
+	if (!drv_data->running) {
 		spin_unlock_irqrestore(&drv_data->lock, flags);
 		return -ESHUTDOWN;
 	}
@@ -979,7 +945,7 @@
 	dev_dbg(&spi->dev, "adding an msg in transfer() \n");
 	list_add_tail(&msg->queue, &drv_data->queue);
 
-	if (drv_data->run == QUEUE_RUNNING && !drv_data->busy)
+	if (drv_data->running && !drv_data->busy)
 		queue_work(drv_data->workqueue, &drv_data->pump_messages);
 
 	spin_unlock_irqrestore(&drv_data->lock, flags);
@@ -1003,147 +969,184 @@
 	P_SPI2_SSEL6, P_SPI2_SSEL7},
 };
 
-/* first setup for new devices */
+/* setup for devices (may be called multiple times -- not just first setup) */
 static int bfin_spi_setup(struct spi_device *spi)
 {
-	struct bfin5xx_spi_chip *chip_info = NULL;
-	struct chip_data *chip;
-	struct driver_data *drv_data = spi_master_get_devdata(spi->master);
-	int ret;
-
-	if (spi->bits_per_word != 8 && spi->bits_per_word != 16)
-		return -EINVAL;
+	struct bfin5xx_spi_chip *chip_info;
+	struct bfin_spi_slave_data *chip = NULL;
+	struct bfin_spi_master_data *drv_data = spi_master_get_devdata(spi->master);
+	u16 bfin_ctl_reg;
+	int ret = -EINVAL;
 
 	/* Only alloc (or use chip_info) on first setup */
+	chip_info = NULL;
 	chip = spi_get_ctldata(spi);
 	if (chip == NULL) {
-		chip = kzalloc(sizeof(struct chip_data), GFP_KERNEL);
-		if (!chip)
-			return -ENOMEM;
+		chip = kzalloc(sizeof(*chip), GFP_KERNEL);
+		if (!chip) {
+			dev_err(&spi->dev, "cannot allocate chip data\n");
+			ret = -ENOMEM;
+			goto error;
+		}
 
 		chip->enable_dma = 0;
 		chip_info = spi->controller_data;
 	}
 
+	/* Let people set non-standard bits directly */
+	bfin_ctl_reg = BIT_CTL_OPENDRAIN | BIT_CTL_EMISO |
+		BIT_CTL_PSSE | BIT_CTL_GM | BIT_CTL_SZ;
+
 	/* chip_info isn't always needed */
 	if (chip_info) {
 		/* Make sure people stop trying to set fields via ctl_reg
 		 * when they should actually be using common SPI framework.
-		 * Currently we let through: WOM EMISO PSSE GM SZ TIMOD.
+		 * Currently we let through: WOM EMISO PSSE GM SZ.
 		 * Not sure if a user actually needs/uses any of these,
 		 * but let's assume (for now) they do.
 		 */
-		if (chip_info->ctl_reg & (SPE|MSTR|CPOL|CPHA|LSBF|SIZE)) {
+		if (chip_info->ctl_reg & ~bfin_ctl_reg) {
 			dev_err(&spi->dev, "do not set bits in ctl_reg "
 				"that the SPI framework manages\n");
-			return -EINVAL;
+			goto error;
 		}
-
 		chip->enable_dma = chip_info->enable_dma != 0
 		    && drv_data->master_info->enable_dma;
 		chip->ctl_reg = chip_info->ctl_reg;
-		chip->bits_per_word = chip_info->bits_per_word;
-		chip->cs_change_per_word = chip_info->cs_change_per_word;
 		chip->cs_chg_udelay = chip_info->cs_chg_udelay;
-		chip->cs_gpio = chip_info->cs_gpio;
 		chip->idle_tx_val = chip_info->idle_tx_val;
+		chip->pio_interrupt = chip_info->pio_interrupt;
+		spi->bits_per_word = chip_info->bits_per_word;
+	} else {
+		/* force a default base state */
+		chip->ctl_reg &= bfin_ctl_reg;
+	}
+
+	if (spi->bits_per_word != 8 && spi->bits_per_word != 16) {
+		dev_err(&spi->dev, "%d bits_per_word is not supported\n",
+				spi->bits_per_word);
+		goto error;
 	}
 
 	/* translate common spi framework into our register */
-	if (spi->mode & SPI_CPOL)
-		chip->ctl_reg |= CPOL;
-	if (spi->mode & SPI_CPHA)
-		chip->ctl_reg |= CPHA;
-	if (spi->mode & SPI_LSB_FIRST)
-		chip->ctl_reg |= LSBF;
-	/* we dont support running in slave mode (yet?) */
-	chip->ctl_reg |= MSTR;
-
-	/*
-	 * if any one SPI chip is registered and wants DMA, request the
-	 * DMA channel for it
-	 */
-	if (chip->enable_dma && !drv_data->dma_requested) {
-		/* register dma irq handler */
-		if (request_dma(drv_data->dma_channel, "BFIN_SPI_DMA") < 0) {
-			dev_dbg(&spi->dev,
-				"Unable to request BlackFin SPI DMA channel\n");
-			return -ENODEV;
-		}
-		if (set_dma_callback(drv_data->dma_channel,
-		    bfin_spi_dma_irq_handler, drv_data) < 0) {
-			dev_dbg(&spi->dev, "Unable to set dma callback\n");
-			return -EPERM;
-		}
-		dma_disable_irq(drv_data->dma_channel);
-		drv_data->dma_requested = 1;
+	if (spi->mode & ~(SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST)) {
+		dev_err(&spi->dev, "unsupported spi modes detected\n");
+		goto error;
 	}
+	if (spi->mode & SPI_CPOL)
+		chip->ctl_reg |= BIT_CTL_CPOL;
+	if (spi->mode & SPI_CPHA)
+		chip->ctl_reg |= BIT_CTL_CPHA;
+	if (spi->mode & SPI_LSB_FIRST)
+		chip->ctl_reg |= BIT_CTL_LSBF;
+	/* we dont support running in slave mode (yet?) */
+	chip->ctl_reg |= BIT_CTL_MASTER;
 
 	/*
 	 * Notice: for blackfin, the speed_hz is the value of register
 	 * SPI_BAUD, not the real baudrate
 	 */
 	chip->baud = hz_to_spi_baud(spi->max_speed_hz);
-	chip->flag = 1 << (spi->chip_select);
 	chip->chip_select_num = spi->chip_select;
+	if (chip->chip_select_num < MAX_CTRL_CS) {
+		if (!(spi->mode & SPI_CPHA))
+			dev_warn(&spi->dev, "Warning: SPI CPHA not set:"
+				" Slave Select not under software control!\n"
+				" See Documentation/blackfin/bfin-spi-notes.txt");
 
-	if (chip->chip_select_num == 0) {
+		chip->flag = (1 << spi->chip_select) << 8;
+	} else
+		chip->cs_gpio = chip->chip_select_num - MAX_CTRL_CS;
+
+	if (chip->enable_dma && chip->pio_interrupt) {
+		dev_err(&spi->dev, "enable_dma is set, "
+				"do not set pio_interrupt\n");
+		goto error;
+	}
+	/*
+	 * if any one SPI chip is registered and wants DMA, request the
+	 * DMA channel for it
+	 */
+	if (chip->enable_dma && !drv_data->dma_requested) {
+		/* register dma irq handler */
+		ret = request_dma(drv_data->dma_channel, "BFIN_SPI_DMA");
+		if (ret) {
+			dev_err(&spi->dev,
+				"Unable to request BlackFin SPI DMA channel\n");
+			goto error;
+		}
+		drv_data->dma_requested = 1;
+
+		ret = set_dma_callback(drv_data->dma_channel,
+			bfin_spi_dma_irq_handler, drv_data);
+		if (ret) {
+			dev_err(&spi->dev, "Unable to set dma callback\n");
+			goto error;
+		}
+		dma_disable_irq(drv_data->dma_channel);
+	}
+
+	if (chip->pio_interrupt && !drv_data->irq_requested) {
+		ret = request_irq(drv_data->spi_irq, bfin_spi_pio_irq_handler,
+			IRQF_DISABLED, "BFIN_SPI", drv_data);
+		if (ret) {
+			dev_err(&spi->dev, "Unable to register spi IRQ\n");
+			goto error;
+		}
+		drv_data->irq_requested = 1;
+		/* we use write mode, spi irq has to be disabled here */
+		disable_irq(drv_data->spi_irq);
+	}
+
+	if (chip->chip_select_num >= MAX_CTRL_CS) {
 		ret = gpio_request(chip->cs_gpio, spi->modalias);
 		if (ret) {
-			if (drv_data->dma_requested)
-				free_dma(drv_data->dma_channel);
-			return ret;
+			dev_err(&spi->dev, "gpio_request() error\n");
+			goto pin_error;
 		}
 		gpio_direction_output(chip->cs_gpio, 1);
 	}
 
-	switch (chip->bits_per_word) {
-	case 8:
-		chip->n_bytes = 1;
-		chip->width = CFG_SPI_WORDSIZE8;
-		chip->read = chip->cs_change_per_word ?
-			bfin_spi_u8_cs_chg_reader : bfin_spi_u8_reader;
-		chip->write = chip->cs_change_per_word ?
-			bfin_spi_u8_cs_chg_writer : bfin_spi_u8_writer;
-		chip->duplex = chip->cs_change_per_word ?
-			bfin_spi_u8_cs_chg_duplex : bfin_spi_u8_duplex;
-		break;
-
-	case 16:
-		chip->n_bytes = 2;
-		chip->width = CFG_SPI_WORDSIZE16;
-		chip->read = chip->cs_change_per_word ?
-			bfin_spi_u16_cs_chg_reader : bfin_spi_u16_reader;
-		chip->write = chip->cs_change_per_word ?
-			bfin_spi_u16_cs_chg_writer : bfin_spi_u16_writer;
-		chip->duplex = chip->cs_change_per_word ?
-			bfin_spi_u16_cs_chg_duplex : bfin_spi_u16_duplex;
-		break;
-
-	default:
-		dev_err(&spi->dev, "%d bits_per_word is not supported\n",
-				chip->bits_per_word);
-		if (chip_info)
-			kfree(chip);
-		return -ENODEV;
-	}
-
 	dev_dbg(&spi->dev, "setup spi chip %s, width is %d, dma is %d\n",
-			spi->modalias, chip->width, chip->enable_dma);
+			spi->modalias, spi->bits_per_word, chip->enable_dma);
 	dev_dbg(&spi->dev, "ctl_reg is 0x%x, flag_reg is 0x%x\n",
 			chip->ctl_reg, chip->flag);
 
 	spi_set_ctldata(spi, chip);
 
 	dev_dbg(&spi->dev, "chip select number is %d\n", chip->chip_select_num);
-	if ((chip->chip_select_num > 0)
-		&& (chip->chip_select_num <= spi->master->num_chipselect))
-		peripheral_request(ssel[spi->master->bus_num]
-			[chip->chip_select_num-1], spi->modalias);
+	if (chip->chip_select_num < MAX_CTRL_CS) {
+		ret = peripheral_request(ssel[spi->master->bus_num]
+		                         [chip->chip_select_num-1], spi->modalias);
+		if (ret) {
+			dev_err(&spi->dev, "peripheral_request() error\n");
+			goto pin_error;
+		}
+	}
 
+	bfin_spi_cs_enable(drv_data, chip);
 	bfin_spi_cs_deactive(drv_data, chip);
 
 	return 0;
+
+ pin_error:
+	if (chip->chip_select_num >= MAX_CTRL_CS)
+		gpio_free(chip->cs_gpio);
+	else
+		peripheral_free(ssel[spi->master->bus_num]
+			[chip->chip_select_num - 1]);
+ error:
+	if (chip) {
+		if (drv_data->dma_requested)
+			free_dma(drv_data->dma_channel);
+		drv_data->dma_requested = 0;
+
+		kfree(chip);
+		/* prevent free 'chip' twice */
+		spi_set_ctldata(spi, NULL);
+	}
+
+	return ret;
 }
 
 /*
@@ -1152,28 +1155,30 @@
  */
 static void bfin_spi_cleanup(struct spi_device *spi)
 {
-	struct chip_data *chip = spi_get_ctldata(spi);
+	struct bfin_spi_slave_data *chip = spi_get_ctldata(spi);
+	struct bfin_spi_master_data *drv_data = spi_master_get_devdata(spi->master);
 
 	if (!chip)
 		return;
 
-	if ((chip->chip_select_num > 0)
-		&& (chip->chip_select_num <= spi->master->num_chipselect))
+	if (chip->chip_select_num < MAX_CTRL_CS) {
 		peripheral_free(ssel[spi->master->bus_num]
 					[chip->chip_select_num-1]);
-
-	if (chip->chip_select_num == 0)
+		bfin_spi_cs_disable(drv_data, chip);
+	} else
 		gpio_free(chip->cs_gpio);
 
 	kfree(chip);
+	/* prevent free 'chip' twice */
+	spi_set_ctldata(spi, NULL);
 }
 
-static inline int bfin_spi_init_queue(struct driver_data *drv_data)
+static inline int bfin_spi_init_queue(struct bfin_spi_master_data *drv_data)
 {
 	INIT_LIST_HEAD(&drv_data->queue);
 	spin_lock_init(&drv_data->lock);
 
-	drv_data->run = QUEUE_STOPPED;
+	drv_data->running = false;
 	drv_data->busy = 0;
 
 	/* init transfer tasklet */
@@ -1190,18 +1195,18 @@
 	return 0;
 }
 
-static inline int bfin_spi_start_queue(struct driver_data *drv_data)
+static inline int bfin_spi_start_queue(struct bfin_spi_master_data *drv_data)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&drv_data->lock, flags);
 
-	if (drv_data->run == QUEUE_RUNNING || drv_data->busy) {
+	if (drv_data->running || drv_data->busy) {
 		spin_unlock_irqrestore(&drv_data->lock, flags);
 		return -EBUSY;
 	}
 
-	drv_data->run = QUEUE_RUNNING;
+	drv_data->running = true;
 	drv_data->cur_msg = NULL;
 	drv_data->cur_transfer = NULL;
 	drv_data->cur_chip = NULL;
@@ -1212,7 +1217,7 @@
 	return 0;
 }
 
-static inline int bfin_spi_stop_queue(struct driver_data *drv_data)
+static inline int bfin_spi_stop_queue(struct bfin_spi_master_data *drv_data)
 {
 	unsigned long flags;
 	unsigned limit = 500;
@@ -1226,7 +1231,7 @@
 	 * execution path (pump_messages) would be required to call wake_up or
 	 * friends on every SPI message. Do this instead
 	 */
-	drv_data->run = QUEUE_STOPPED;
+	drv_data->running = false;
 	while (!list_empty(&drv_data->queue) && drv_data->busy && limit--) {
 		spin_unlock_irqrestore(&drv_data->lock, flags);
 		msleep(10);
@@ -1241,7 +1246,7 @@
 	return status;
 }
 
-static inline int bfin_spi_destroy_queue(struct driver_data *drv_data)
+static inline int bfin_spi_destroy_queue(struct bfin_spi_master_data *drv_data)
 {
 	int status;
 
@@ -1259,14 +1264,14 @@
 	struct device *dev = &pdev->dev;
 	struct bfin5xx_spi_master *platform_info;
 	struct spi_master *master;
-	struct driver_data *drv_data = 0;
+	struct bfin_spi_master_data *drv_data;
 	struct resource *res;
 	int status = 0;
 
 	platform_info = dev->platform_data;
 
 	/* Allocate master with space for drv_data */
-	master = spi_alloc_master(dev, sizeof(struct driver_data) + 16);
+	master = spi_alloc_master(dev, sizeof(*drv_data));
 	if (!master) {
 		dev_err(&pdev->dev, "can not alloc spi_master\n");
 		return -ENOMEM;
@@ -1302,11 +1307,19 @@
 		goto out_error_ioremap;
 	}
 
-	drv_data->dma_channel = platform_get_irq(pdev, 0);
-	if (drv_data->dma_channel < 0) {
+	res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
+	if (res == NULL) {
 		dev_err(dev, "No DMA channel specified\n");
 		status = -ENOENT;
-		goto out_error_no_dma_ch;
+		goto out_error_free_io;
+	}
+	drv_data->dma_channel = res->start;
+
+	drv_data->spi_irq = platform_get_irq(pdev, 0);
+	if (drv_data->spi_irq < 0) {
+		dev_err(dev, "No spi pio irq specified\n");
+		status = -ENOENT;
+		goto out_error_free_io;
 	}
 
 	/* Initial and start queue */
@@ -1328,6 +1341,12 @@
 		goto out_error_queue_alloc;
 	}
 
+	/* Reset SPI registers. If these registers were used by the boot loader,
+	 * the sky may fall on your head if you enable the dma controller.
+	 */
+	write_CTRL(drv_data, BIT_CTL_CPHA | BIT_CTL_MASTER);
+	write_FLAG(drv_data, 0xFF00);
+
 	/* Register with the SPI framework */
 	platform_set_drvdata(pdev, drv_data);
 	status = spi_register_master(master);
@@ -1343,7 +1362,7 @@
 
 out_error_queue_alloc:
 	bfin_spi_destroy_queue(drv_data);
-out_error_no_dma_ch:
+out_error_free_io:
 	iounmap((void *) drv_data->regs_base);
 out_error_ioremap:
 out_error_get_res:
@@ -1355,7 +1374,7 @@
 /* stop hardware and remove the driver */
 static int __devexit bfin_spi_remove(struct platform_device *pdev)
 {
-	struct driver_data *drv_data = platform_get_drvdata(pdev);
+	struct bfin_spi_master_data *drv_data = platform_get_drvdata(pdev);
 	int status = 0;
 
 	if (!drv_data)
@@ -1375,6 +1394,11 @@
 			free_dma(drv_data->dma_channel);
 	}
 
+	if (drv_data->irq_requested) {
+		free_irq(drv_data->spi_irq, drv_data);
+		drv_data->irq_requested = 0;
+	}
+
 	/* Disconnect from the SPI framework */
 	spi_unregister_master(drv_data->master);
 
@@ -1389,26 +1413,32 @@
 #ifdef CONFIG_PM
 static int bfin_spi_suspend(struct platform_device *pdev, pm_message_t state)
 {
-	struct driver_data *drv_data = platform_get_drvdata(pdev);
+	struct bfin_spi_master_data *drv_data = platform_get_drvdata(pdev);
 	int status = 0;
 
 	status = bfin_spi_stop_queue(drv_data);
 	if (status != 0)
 		return status;
 
-	/* stop hardware */
-	bfin_spi_disable(drv_data);
+	drv_data->ctrl_reg = read_CTRL(drv_data);
+	drv_data->flag_reg = read_FLAG(drv_data);
+
+	/*
+	 * reset SPI_CTL and SPI_FLG registers
+	 */
+	write_CTRL(drv_data, BIT_CTL_CPHA | BIT_CTL_MASTER);
+	write_FLAG(drv_data, 0xFF00);
 
 	return 0;
 }
 
 static int bfin_spi_resume(struct platform_device *pdev)
 {
-	struct driver_data *drv_data = platform_get_drvdata(pdev);
+	struct bfin_spi_master_data *drv_data = platform_get_drvdata(pdev);
 	int status = 0;
 
-	/* Enable the SPI interface */
-	bfin_spi_enable(drv_data);
+	write_CTRL(drv_data, drv_data->ctrl_reg);
+	write_FLAG(drv_data, drv_data->flag_reg);
 
 	/* Start the queue running */
 	status = bfin_spi_start_queue(drv_data);
@@ -1439,7 +1469,7 @@
 {
 	return platform_driver_probe(&bfin_spi_driver, bfin_spi_probe);
 }
-module_init(bfin_spi_init);
+subsys_initcall(bfin_spi_init);
 
 static void __exit bfin_spi_exit(void)
 {
diff --git a/drivers/spi/spi_fsl_espi.c b/drivers/spi/spi_fsl_espi.c
new file mode 100644
index 0000000..e3b4f64
--- /dev/null
+++ b/drivers/spi/spi_fsl_espi.c
@@ -0,0 +1,748 @@
+/*
+ * Freescale eSPI controller driver.
+ *
+ * Copyright 2010 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/spi/spi.h>
+#include <linux/platform_device.h>
+#include <linux/fsl_devices.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/of_spi.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <sysdev/fsl_soc.h>
+
+#include "spi_fsl_lib.h"
+
+/* eSPI Controller registers */
+struct fsl_espi_reg {
+	__be32 mode;		/* 0x000 - eSPI mode register */
+	__be32 event;		/* 0x004 - eSPI event register */
+	__be32 mask;		/* 0x008 - eSPI mask register */
+	__be32 command;		/* 0x00c - eSPI command register */
+	__be32 transmit;	/* 0x010 - eSPI transmit FIFO access register*/
+	__be32 receive;		/* 0x014 - eSPI receive FIFO access register*/
+	u8 res[8];		/* 0x018 - 0x01c reserved */
+	__be32 csmode[4];	/* 0x020 - 0x02c eSPI cs mode register */
+};
+
+struct fsl_espi_transfer {
+	const void *tx_buf;
+	void *rx_buf;
+	unsigned len;
+	unsigned n_tx;
+	unsigned n_rx;
+	unsigned actual_length;
+	int status;
+};
+
+/* eSPI Controller mode register definitions */
+#define SPMODE_ENABLE		(1 << 31)
+#define SPMODE_LOOP		(1 << 30)
+#define SPMODE_TXTHR(x)		((x) << 8)
+#define SPMODE_RXTHR(x)		((x) << 0)
+
+/* eSPI Controller CS mode register definitions */
+#define CSMODE_CI_INACTIVEHIGH	(1 << 31)
+#define CSMODE_CP_BEGIN_EDGECLK	(1 << 30)
+#define CSMODE_REV		(1 << 29)
+#define CSMODE_DIV16		(1 << 28)
+#define CSMODE_PM(x)		((x) << 24)
+#define CSMODE_POL_1		(1 << 20)
+#define CSMODE_LEN(x)		((x) << 16)
+#define CSMODE_BEF(x)		((x) << 12)
+#define CSMODE_AFT(x)		((x) << 8)
+#define CSMODE_CG(x)		((x) << 3)
+
+/* Default mode/csmode for eSPI controller */
+#define SPMODE_INIT_VAL (SPMODE_TXTHR(4) | SPMODE_RXTHR(3))
+#define CSMODE_INIT_VAL (CSMODE_POL_1 | CSMODE_BEF(0) \
+		| CSMODE_AFT(0) | CSMODE_CG(1))
+
+/* SPIE register values */
+#define	SPIE_NE		0x00000200	/* Not empty */
+#define	SPIE_NF		0x00000100	/* Not full */
+
+/* SPIM register values */
+#define	SPIM_NE		0x00000200	/* Not empty */
+#define	SPIM_NF		0x00000100	/* Not full */
+#define SPIE_RXCNT(reg)     ((reg >> 24) & 0x3F)
+#define SPIE_TXCNT(reg)     ((reg >> 16) & 0x3F)
+
+/* SPCOM register values */
+#define SPCOM_CS(x)		((x) << 30)
+#define SPCOM_TRANLEN(x)	((x) << 0)
+#define	SPCOM_TRANLEN_MAX	0xFFFF	/* Max transaction length */
+
+static void fsl_espi_change_mode(struct spi_device *spi)
+{
+	struct mpc8xxx_spi *mspi = spi_master_get_devdata(spi->master);
+	struct spi_mpc8xxx_cs *cs = spi->controller_state;
+	struct fsl_espi_reg *reg_base = mspi->reg_base;
+	__be32 __iomem *mode = &reg_base->csmode[spi->chip_select];
+	__be32 __iomem *espi_mode = &reg_base->mode;
+	u32 tmp;
+	unsigned long flags;
+
+	/* Turn off IRQs locally to minimize time that SPI is disabled. */
+	local_irq_save(flags);
+
+	/* Turn off SPI unit prior changing mode */
+	tmp = mpc8xxx_spi_read_reg(espi_mode);
+	mpc8xxx_spi_write_reg(espi_mode, tmp & ~SPMODE_ENABLE);
+	mpc8xxx_spi_write_reg(mode, cs->hw_mode);
+	mpc8xxx_spi_write_reg(espi_mode, tmp);
+
+	local_irq_restore(flags);
+}
+
+static u32 fsl_espi_tx_buf_lsb(struct mpc8xxx_spi *mpc8xxx_spi)
+{
+	u32 data;
+	u16 data_h;
+	u16 data_l;
+	const u32 *tx = mpc8xxx_spi->tx;
+
+	if (!tx)
+		return 0;
+
+	data = *tx++ << mpc8xxx_spi->tx_shift;
+	data_l = data & 0xffff;
+	data_h = (data >> 16) & 0xffff;
+	swab16s(&data_l);
+	swab16s(&data_h);
+	data = data_h | data_l;
+
+	mpc8xxx_spi->tx = tx;
+	return data;
+}
+
+static int fsl_espi_setup_transfer(struct spi_device *spi,
+					struct spi_transfer *t)
+{
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
+	int bits_per_word = 0;
+	u8 pm;
+	u32 hz = 0;
+	struct spi_mpc8xxx_cs *cs = spi->controller_state;
+
+	if (t) {
+		bits_per_word = t->bits_per_word;
+		hz = t->speed_hz;
+	}
+
+	/* spi_transfer level calls that work per-word */
+	if (!bits_per_word)
+		bits_per_word = spi->bits_per_word;
+
+	/* Make sure its a bit width we support [4..16] */
+	if ((bits_per_word < 4) || (bits_per_word > 16))
+		return -EINVAL;
+
+	if (!hz)
+		hz = spi->max_speed_hz;
+
+	cs->rx_shift = 0;
+	cs->tx_shift = 0;
+	cs->get_rx = mpc8xxx_spi_rx_buf_u32;
+	cs->get_tx = mpc8xxx_spi_tx_buf_u32;
+	if (bits_per_word <= 8) {
+		cs->rx_shift = 8 - bits_per_word;
+	} else if (bits_per_word <= 16) {
+		cs->rx_shift = 16 - bits_per_word;
+		if (spi->mode & SPI_LSB_FIRST)
+			cs->get_tx = fsl_espi_tx_buf_lsb;
+	} else {
+		return -EINVAL;
+	}
+
+	mpc8xxx_spi->rx_shift = cs->rx_shift;
+	mpc8xxx_spi->tx_shift = cs->tx_shift;
+	mpc8xxx_spi->get_rx = cs->get_rx;
+	mpc8xxx_spi->get_tx = cs->get_tx;
+
+	bits_per_word = bits_per_word - 1;
+
+	/* mask out bits we are going to set */
+	cs->hw_mode &= ~(CSMODE_LEN(0xF) | CSMODE_DIV16 | CSMODE_PM(0xF));
+
+	cs->hw_mode |= CSMODE_LEN(bits_per_word);
+
+	if ((mpc8xxx_spi->spibrg / hz) > 64) {
+		cs->hw_mode |= CSMODE_DIV16;
+		pm = (mpc8xxx_spi->spibrg - 1) / (hz * 64) + 1;
+
+		WARN_ONCE(pm > 16, "%s: Requested speed is too low: %d Hz. "
+			  "Will use %d Hz instead.\n", dev_name(&spi->dev),
+			  hz, mpc8xxx_spi->spibrg / 1024);
+		if (pm > 16)
+			pm = 16;
+	} else {
+		pm = (mpc8xxx_spi->spibrg - 1) / (hz * 4) + 1;
+	}
+	if (pm)
+		pm--;
+
+	cs->hw_mode |= CSMODE_PM(pm);
+
+	fsl_espi_change_mode(spi);
+	return 0;
+}
+
+static int fsl_espi_cpu_bufs(struct mpc8xxx_spi *mspi, struct spi_transfer *t,
+		unsigned int len)
+{
+	u32 word;
+	struct fsl_espi_reg *reg_base = mspi->reg_base;
+
+	mspi->count = len;
+
+	/* enable rx ints */
+	mpc8xxx_spi_write_reg(&reg_base->mask, SPIM_NE);
+
+	/* transmit word */
+	word = mspi->get_tx(mspi);
+	mpc8xxx_spi_write_reg(&reg_base->transmit, word);
+
+	return 0;
+}
+
+static int fsl_espi_bufs(struct spi_device *spi, struct spi_transfer *t)
+{
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
+	struct fsl_espi_reg *reg_base = mpc8xxx_spi->reg_base;
+	unsigned int len = t->len;
+	u8 bits_per_word;
+	int ret;
+
+	bits_per_word = spi->bits_per_word;
+	if (t->bits_per_word)
+		bits_per_word = t->bits_per_word;
+
+	mpc8xxx_spi->len = t->len;
+	len = roundup(len, 4) / 4;
+
+	mpc8xxx_spi->tx = t->tx_buf;
+	mpc8xxx_spi->rx = t->rx_buf;
+
+	INIT_COMPLETION(mpc8xxx_spi->done);
+
+	/* Set SPCOM[CS] and SPCOM[TRANLEN] field */
+	if ((t->len - 1) > SPCOM_TRANLEN_MAX) {
+		dev_err(mpc8xxx_spi->dev, "Transaction length (%d)"
+				" beyond the SPCOM[TRANLEN] field\n", t->len);
+		return -EINVAL;
+	}
+	mpc8xxx_spi_write_reg(&reg_base->command,
+		(SPCOM_CS(spi->chip_select) | SPCOM_TRANLEN(t->len - 1)));
+
+	ret = fsl_espi_cpu_bufs(mpc8xxx_spi, t, len);
+	if (ret)
+		return ret;
+
+	wait_for_completion(&mpc8xxx_spi->done);
+
+	/* disable rx ints */
+	mpc8xxx_spi_write_reg(&reg_base->mask, 0);
+
+	return mpc8xxx_spi->count;
+}
+
+static void fsl_espi_addr2cmd(unsigned int addr, u8 *cmd)
+{
+	if (cmd[1] && cmd[2] && cmd[3]) {
+		cmd[1] = (u8)(addr >> 16);
+		cmd[2] = (u8)(addr >> 8);
+		cmd[3] = (u8)(addr >> 0);
+	}
+}
+
+static unsigned int fsl_espi_cmd2addr(u8 *cmd)
+{
+	if (cmd[1] && cmd[2] && cmd[3])
+		return cmd[1] << 16 | cmd[2] << 8 | cmd[3] << 0;
+
+	return 0;
+}
+
+static void fsl_espi_do_trans(struct spi_message *m,
+				struct fsl_espi_transfer *tr)
+{
+	struct spi_device *spi = m->spi;
+	struct mpc8xxx_spi *mspi = spi_master_get_devdata(spi->master);
+	struct fsl_espi_transfer *espi_trans = tr;
+	struct spi_message message;
+	struct spi_transfer *t, *first, trans;
+	int status = 0;
+
+	spi_message_init(&message);
+	memset(&trans, 0, sizeof(trans));
+
+	first = list_first_entry(&m->transfers, struct spi_transfer,
+			transfer_list);
+	list_for_each_entry(t, &m->transfers, transfer_list) {
+		if ((first->bits_per_word != t->bits_per_word) ||
+			(first->speed_hz != t->speed_hz)) {
+			espi_trans->status = -EINVAL;
+			dev_err(mspi->dev, "bits_per_word/speed_hz should be"
+					" same for the same SPI transfer\n");
+			return;
+		}
+
+		trans.speed_hz = t->speed_hz;
+		trans.bits_per_word = t->bits_per_word;
+		trans.delay_usecs = max(first->delay_usecs, t->delay_usecs);
+	}
+
+	trans.len = espi_trans->len;
+	trans.tx_buf = espi_trans->tx_buf;
+	trans.rx_buf = espi_trans->rx_buf;
+	spi_message_add_tail(&trans, &message);
+
+	list_for_each_entry(t, &message.transfers, transfer_list) {
+		if (t->bits_per_word || t->speed_hz) {
+			status = -EINVAL;
+
+			status = fsl_espi_setup_transfer(spi, t);
+			if (status < 0)
+				break;
+		}
+
+		if (t->len)
+			status = fsl_espi_bufs(spi, t);
+
+		if (status) {
+			status = -EMSGSIZE;
+			break;
+		}
+
+		if (t->delay_usecs)
+			udelay(t->delay_usecs);
+	}
+
+	espi_trans->status = status;
+	fsl_espi_setup_transfer(spi, NULL);
+}
+
+static void fsl_espi_cmd_trans(struct spi_message *m,
+				struct fsl_espi_transfer *trans, u8 *rx_buff)
+{
+	struct spi_transfer *t;
+	u8 *local_buf;
+	int i = 0;
+	struct fsl_espi_transfer *espi_trans = trans;
+
+	local_buf = kzalloc(SPCOM_TRANLEN_MAX, GFP_KERNEL);
+	if (!local_buf) {
+		espi_trans->status = -ENOMEM;
+		return;
+	}
+
+	list_for_each_entry(t, &m->transfers, transfer_list) {
+		if (t->tx_buf) {
+			memcpy(local_buf + i, t->tx_buf, t->len);
+			i += t->len;
+		}
+	}
+
+	espi_trans->tx_buf = local_buf;
+	espi_trans->rx_buf = local_buf + espi_trans->n_tx;
+	fsl_espi_do_trans(m, espi_trans);
+
+	espi_trans->actual_length = espi_trans->len;
+	kfree(local_buf);
+}
+
+static void fsl_espi_rw_trans(struct spi_message *m,
+				struct fsl_espi_transfer *trans, u8 *rx_buff)
+{
+	struct fsl_espi_transfer *espi_trans = trans;
+	unsigned int n_tx = espi_trans->n_tx;
+	unsigned int n_rx = espi_trans->n_rx;
+	struct spi_transfer *t;
+	u8 *local_buf;
+	u8 *rx_buf = rx_buff;
+	unsigned int trans_len;
+	unsigned int addr;
+	int i, pos, loop;
+
+	local_buf = kzalloc(SPCOM_TRANLEN_MAX, GFP_KERNEL);
+	if (!local_buf) {
+		espi_trans->status = -ENOMEM;
+		return;
+	}
+
+	for (pos = 0, loop = 0; pos < n_rx; pos += trans_len, loop++) {
+		trans_len = n_rx - pos;
+		if (trans_len > SPCOM_TRANLEN_MAX - n_tx)
+			trans_len = SPCOM_TRANLEN_MAX - n_tx;
+
+		i = 0;
+		list_for_each_entry(t, &m->transfers, transfer_list) {
+			if (t->tx_buf) {
+				memcpy(local_buf + i, t->tx_buf, t->len);
+				i += t->len;
+			}
+		}
+
+		addr = fsl_espi_cmd2addr(local_buf);
+		addr += pos;
+		fsl_espi_addr2cmd(addr, local_buf);
+
+		espi_trans->n_tx = n_tx;
+		espi_trans->n_rx = trans_len;
+		espi_trans->len = trans_len + n_tx;
+		espi_trans->tx_buf = local_buf;
+		espi_trans->rx_buf = local_buf + n_tx;
+		fsl_espi_do_trans(m, espi_trans);
+
+		memcpy(rx_buf + pos, espi_trans->rx_buf + n_tx, trans_len);
+
+		if (loop > 0)
+			espi_trans->actual_length += espi_trans->len - n_tx;
+		else
+			espi_trans->actual_length += espi_trans->len;
+	}
+
+	kfree(local_buf);
+}
+
+static void fsl_espi_do_one_msg(struct spi_message *m)
+{
+	struct spi_transfer *t;
+	u8 *rx_buf = NULL;
+	unsigned int n_tx = 0;
+	unsigned int n_rx = 0;
+	struct fsl_espi_transfer espi_trans;
+
+	list_for_each_entry(t, &m->transfers, transfer_list) {
+		if (t->tx_buf)
+			n_tx += t->len;
+		if (t->rx_buf) {
+			n_rx += t->len;
+			rx_buf = t->rx_buf;
+		}
+	}
+
+	espi_trans.n_tx = n_tx;
+	espi_trans.n_rx = n_rx;
+	espi_trans.len = n_tx + n_rx;
+	espi_trans.actual_length = 0;
+	espi_trans.status = 0;
+
+	if (!rx_buf)
+		fsl_espi_cmd_trans(m, &espi_trans, NULL);
+	else
+		fsl_espi_rw_trans(m, &espi_trans, rx_buf);
+
+	m->actual_length = espi_trans.actual_length;
+	m->status = espi_trans.status;
+	m->complete(m->context);
+}
+
+static int fsl_espi_setup(struct spi_device *spi)
+{
+	struct mpc8xxx_spi *mpc8xxx_spi;
+	struct fsl_espi_reg *reg_base;
+	int retval;
+	u32 hw_mode;
+	u32 loop_mode;
+	struct spi_mpc8xxx_cs *cs = spi->controller_state;
+
+	if (!spi->max_speed_hz)
+		return -EINVAL;
+
+	if (!cs) {
+		cs = kzalloc(sizeof *cs, GFP_KERNEL);
+		if (!cs)
+			return -ENOMEM;
+		spi->controller_state = cs;
+	}
+
+	mpc8xxx_spi = spi_master_get_devdata(spi->master);
+	reg_base = mpc8xxx_spi->reg_base;
+
+	hw_mode = cs->hw_mode; /* Save orginal settings */
+	cs->hw_mode = mpc8xxx_spi_read_reg(
+			&reg_base->csmode[spi->chip_select]);
+	/* mask out bits we are going to set */
+	cs->hw_mode &= ~(CSMODE_CP_BEGIN_EDGECLK | CSMODE_CI_INACTIVEHIGH
+			 | CSMODE_REV);
+
+	if (spi->mode & SPI_CPHA)
+		cs->hw_mode |= CSMODE_CP_BEGIN_EDGECLK;
+	if (spi->mode & SPI_CPOL)
+		cs->hw_mode |= CSMODE_CI_INACTIVEHIGH;
+	if (!(spi->mode & SPI_LSB_FIRST))
+		cs->hw_mode |= CSMODE_REV;
+
+	/* Handle the loop mode */
+	loop_mode = mpc8xxx_spi_read_reg(&reg_base->mode);
+	loop_mode &= ~SPMODE_LOOP;
+	if (spi->mode & SPI_LOOP)
+		loop_mode |= SPMODE_LOOP;
+	mpc8xxx_spi_write_reg(&reg_base->mode, loop_mode);
+
+	retval = fsl_espi_setup_transfer(spi, NULL);
+	if (retval < 0) {
+		cs->hw_mode = hw_mode; /* Restore settings */
+		return retval;
+	}
+	return 0;
+}
+
+void fsl_espi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
+{
+	struct fsl_espi_reg *reg_base = mspi->reg_base;
+
+	/* We need handle RX first */
+	if (events & SPIE_NE) {
+		u32 rx_data;
+
+		/* Spin until RX is done */
+		while (SPIE_RXCNT(events) < min(4, mspi->len)) {
+			cpu_relax();
+			events = mpc8xxx_spi_read_reg(&reg_base->event);
+		}
+		mspi->len -= 4;
+
+		rx_data = mpc8xxx_spi_read_reg(&reg_base->receive);
+
+		if (mspi->rx)
+			mspi->get_rx(rx_data, mspi);
+	}
+
+	if (!(events & SPIE_NF)) {
+		int ret;
+
+		/* spin until TX is done */
+		ret = spin_event_timeout(((events = mpc8xxx_spi_read_reg(
+				&reg_base->event)) & SPIE_NF) == 0, 1000, 0);
+		if (!ret) {
+			dev_err(mspi->dev, "tired waiting for SPIE_NF\n");
+			return;
+		}
+	}
+
+	/* Clear the events */
+	mpc8xxx_spi_write_reg(&reg_base->event, events);
+
+	mspi->count -= 1;
+	if (mspi->count) {
+		u32 word = mspi->get_tx(mspi);
+
+		mpc8xxx_spi_write_reg(&reg_base->transmit, word);
+	} else {
+		complete(&mspi->done);
+	}
+}
+
+static irqreturn_t fsl_espi_irq(s32 irq, void *context_data)
+{
+	struct mpc8xxx_spi *mspi = context_data;
+	struct fsl_espi_reg *reg_base = mspi->reg_base;
+	irqreturn_t ret = IRQ_NONE;
+	u32 events;
+
+	/* Get interrupt events(tx/rx) */
+	events = mpc8xxx_spi_read_reg(&reg_base->event);
+	if (events)
+		ret = IRQ_HANDLED;
+
+	dev_vdbg(mspi->dev, "%s: events %x\n", __func__, events);
+
+	fsl_espi_cpu_irq(mspi, events);
+
+	return ret;
+}
+
+static void fsl_espi_remove(struct mpc8xxx_spi *mspi)
+{
+	iounmap(mspi->reg_base);
+}
+
+static struct spi_master * __devinit fsl_espi_probe(struct device *dev,
+		struct resource *mem, unsigned int irq)
+{
+	struct fsl_spi_platform_data *pdata = dev->platform_data;
+	struct spi_master *master;
+	struct mpc8xxx_spi *mpc8xxx_spi;
+	struct fsl_espi_reg *reg_base;
+	u32 regval;
+	int i, ret = 0;
+
+	master = spi_alloc_master(dev, sizeof(struct mpc8xxx_spi));
+	if (!master) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	dev_set_drvdata(dev, master);
+
+	ret = mpc8xxx_spi_probe(dev, mem, irq);
+	if (ret)
+		goto err_probe;
+
+	master->setup = fsl_espi_setup;
+
+	mpc8xxx_spi = spi_master_get_devdata(master);
+	mpc8xxx_spi->spi_do_one_msg = fsl_espi_do_one_msg;
+	mpc8xxx_spi->spi_remove = fsl_espi_remove;
+
+	mpc8xxx_spi->reg_base = ioremap(mem->start, resource_size(mem));
+	if (!mpc8xxx_spi->reg_base) {
+		ret = -ENOMEM;
+		goto err_probe;
+	}
+
+	reg_base = mpc8xxx_spi->reg_base;
+
+	/* Register for SPI Interrupt */
+	ret = request_irq(mpc8xxx_spi->irq, fsl_espi_irq,
+			  0, "fsl_espi", mpc8xxx_spi);
+	if (ret)
+		goto free_irq;
+
+	if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE) {
+		mpc8xxx_spi->rx_shift = 16;
+		mpc8xxx_spi->tx_shift = 24;
+	}
+
+	/* SPI controller initializations */
+	mpc8xxx_spi_write_reg(&reg_base->mode, 0);
+	mpc8xxx_spi_write_reg(&reg_base->mask, 0);
+	mpc8xxx_spi_write_reg(&reg_base->command, 0);
+	mpc8xxx_spi_write_reg(&reg_base->event, 0xffffffff);
+
+	/* Init eSPI CS mode register */
+	for (i = 0; i < pdata->max_chipselect; i++)
+		mpc8xxx_spi_write_reg(&reg_base->csmode[i], CSMODE_INIT_VAL);
+
+	/* Enable SPI interface */
+	regval = pdata->initial_spmode | SPMODE_INIT_VAL | SPMODE_ENABLE;
+
+	mpc8xxx_spi_write_reg(&reg_base->mode, regval);
+
+	ret = spi_register_master(master);
+	if (ret < 0)
+		goto unreg_master;
+
+	dev_info(dev, "at 0x%p (irq = %d)\n", reg_base, mpc8xxx_spi->irq);
+
+	return master;
+
+unreg_master:
+	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
+free_irq:
+	iounmap(mpc8xxx_spi->reg_base);
+err_probe:
+	spi_master_put(master);
+err:
+	return ERR_PTR(ret);
+}
+
+static int of_fsl_espi_get_chipselects(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct fsl_spi_platform_data *pdata = dev->platform_data;
+	const u32 *prop;
+	int len;
+
+	prop = of_get_property(np, "fsl,espi-num-chipselects", &len);
+	if (!prop || len < sizeof(*prop)) {
+		dev_err(dev, "No 'fsl,espi-num-chipselects' property\n");
+		return -EINVAL;
+	}
+
+	pdata->max_chipselect = *prop;
+	pdata->cs_control = NULL;
+
+	return 0;
+}
+
+static int __devinit of_fsl_espi_probe(struct platform_device *ofdev,
+					const struct of_device_id *ofid)
+{
+	struct device *dev = &ofdev->dev;
+	struct device_node *np = ofdev->dev.of_node;
+	struct spi_master *master;
+	struct resource mem;
+	struct resource irq;
+	int ret = -ENOMEM;
+
+	ret = of_mpc8xxx_spi_probe(ofdev, ofid);
+	if (ret)
+		return ret;
+
+	ret = of_fsl_espi_get_chipselects(dev);
+	if (ret)
+		goto err;
+
+	ret = of_address_to_resource(np, 0, &mem);
+	if (ret)
+		goto err;
+
+	ret = of_irq_to_resource(np, 0, &irq);
+	if (!ret) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	master = fsl_espi_probe(dev, &mem, irq.start);
+	if (IS_ERR(master)) {
+		ret = PTR_ERR(master);
+		goto err;
+	}
+
+	return 0;
+
+err:
+	return ret;
+}
+
+static int __devexit of_fsl_espi_remove(struct platform_device *dev)
+{
+	return mpc8xxx_spi_remove(&dev->dev);
+}
+
+static const struct of_device_id of_fsl_espi_match[] = {
+	{ .compatible = "fsl,mpc8536-espi" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, of_fsl_espi_match);
+
+static struct of_platform_driver fsl_espi_driver = {
+	.driver = {
+		.name = "fsl_espi",
+		.owner = THIS_MODULE,
+		.of_match_table = of_fsl_espi_match,
+	},
+	.probe		= of_fsl_espi_probe,
+	.remove		= __devexit_p(of_fsl_espi_remove),
+};
+
+static int __init fsl_espi_init(void)
+{
+	return of_register_platform_driver(&fsl_espi_driver);
+}
+module_init(fsl_espi_init);
+
+static void __exit fsl_espi_exit(void)
+{
+	of_unregister_platform_driver(&fsl_espi_driver);
+}
+module_exit(fsl_espi_exit);
+
+MODULE_AUTHOR("Mingkai Hu");
+MODULE_DESCRIPTION("Enhanced Freescale SPI Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi_fsl_lib.c b/drivers/spi/spi_fsl_lib.c
new file mode 100644
index 0000000..5cd741f
--- /dev/null
+++ b/drivers/spi/spi_fsl_lib.c
@@ -0,0 +1,237 @@
+/*
+ * Freescale SPI/eSPI controller driver library.
+ *
+ * Maintainer: Kumar Gala
+ *
+ * Copyright (C) 2006 Polycom, Inc.
+ *
+ * CPM SPI and QE buffer descriptors mode support:
+ * Copyright (c) 2009  MontaVista Software, Inc.
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * Copyright 2010 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/fsl_devices.h>
+#include <linux/dma-mapping.h>
+#include <linux/mm.h>
+#include <linux/of_platform.h>
+#include <linux/of_spi.h>
+#include <sysdev/fsl_soc.h>
+
+#include "spi_fsl_lib.h"
+
+#define MPC8XXX_SPI_RX_BUF(type) 					  \
+void mpc8xxx_spi_rx_buf_##type(u32 data, struct mpc8xxx_spi *mpc8xxx_spi) \
+{									  \
+	type *rx = mpc8xxx_spi->rx;					  \
+	*rx++ = (type)(data >> mpc8xxx_spi->rx_shift);			  \
+	mpc8xxx_spi->rx = rx;						  \
+}
+
+#define MPC8XXX_SPI_TX_BUF(type)				\
+u32 mpc8xxx_spi_tx_buf_##type(struct mpc8xxx_spi *mpc8xxx_spi)	\
+{								\
+	u32 data;						\
+	const type *tx = mpc8xxx_spi->tx;			\
+	if (!tx)						\
+		return 0;					\
+	data = *tx++ << mpc8xxx_spi->tx_shift;			\
+	mpc8xxx_spi->tx = tx;					\
+	return data;						\
+}
+
+MPC8XXX_SPI_RX_BUF(u8)
+MPC8XXX_SPI_RX_BUF(u16)
+MPC8XXX_SPI_RX_BUF(u32)
+MPC8XXX_SPI_TX_BUF(u8)
+MPC8XXX_SPI_TX_BUF(u16)
+MPC8XXX_SPI_TX_BUF(u32)
+
+struct mpc8xxx_spi_probe_info *to_of_pinfo(struct fsl_spi_platform_data *pdata)
+{
+	return container_of(pdata, struct mpc8xxx_spi_probe_info, pdata);
+}
+
+void mpc8xxx_spi_work(struct work_struct *work)
+{
+	struct mpc8xxx_spi *mpc8xxx_spi = container_of(work, struct mpc8xxx_spi,
+						       work);
+
+	spin_lock_irq(&mpc8xxx_spi->lock);
+	while (!list_empty(&mpc8xxx_spi->queue)) {
+		struct spi_message *m = container_of(mpc8xxx_spi->queue.next,
+						   struct spi_message, queue);
+
+		list_del_init(&m->queue);
+		spin_unlock_irq(&mpc8xxx_spi->lock);
+
+		if (mpc8xxx_spi->spi_do_one_msg)
+			mpc8xxx_spi->spi_do_one_msg(m);
+
+		spin_lock_irq(&mpc8xxx_spi->lock);
+	}
+	spin_unlock_irq(&mpc8xxx_spi->lock);
+}
+
+int mpc8xxx_spi_transfer(struct spi_device *spi,
+				struct spi_message *m)
+{
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
+	unsigned long flags;
+
+	m->actual_length = 0;
+	m->status = -EINPROGRESS;
+
+	spin_lock_irqsave(&mpc8xxx_spi->lock, flags);
+	list_add_tail(&m->queue, &mpc8xxx_spi->queue);
+	queue_work(mpc8xxx_spi->workqueue, &mpc8xxx_spi->work);
+	spin_unlock_irqrestore(&mpc8xxx_spi->lock, flags);
+
+	return 0;
+}
+
+void mpc8xxx_spi_cleanup(struct spi_device *spi)
+{
+	kfree(spi->controller_state);
+}
+
+const char *mpc8xxx_spi_strmode(unsigned int flags)
+{
+	if (flags & SPI_QE_CPU_MODE) {
+		return "QE CPU";
+	} else if (flags & SPI_CPM_MODE) {
+		if (flags & SPI_QE)
+			return "QE";
+		else if (flags & SPI_CPM2)
+			return "CPM2";
+		else
+			return "CPM1";
+	}
+	return "CPU";
+}
+
+int mpc8xxx_spi_probe(struct device *dev, struct resource *mem,
+			unsigned int irq)
+{
+	struct fsl_spi_platform_data *pdata = dev->platform_data;
+	struct spi_master *master;
+	struct mpc8xxx_spi *mpc8xxx_spi;
+	int ret = 0;
+
+	master = dev_get_drvdata(dev);
+
+	/* the spi->mode bits understood by this driver: */
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH
+			| SPI_LSB_FIRST | SPI_LOOP;
+
+	master->transfer = mpc8xxx_spi_transfer;
+	master->cleanup = mpc8xxx_spi_cleanup;
+	master->dev.of_node = dev->of_node;
+
+	mpc8xxx_spi = spi_master_get_devdata(master);
+	mpc8xxx_spi->dev = dev;
+	mpc8xxx_spi->get_rx = mpc8xxx_spi_rx_buf_u8;
+	mpc8xxx_spi->get_tx = mpc8xxx_spi_tx_buf_u8;
+	mpc8xxx_spi->flags = pdata->flags;
+	mpc8xxx_spi->spibrg = pdata->sysclk;
+	mpc8xxx_spi->irq = irq;
+
+	mpc8xxx_spi->rx_shift = 0;
+	mpc8xxx_spi->tx_shift = 0;
+
+	init_completion(&mpc8xxx_spi->done);
+
+	master->bus_num = pdata->bus_num;
+	master->num_chipselect = pdata->max_chipselect;
+
+	spin_lock_init(&mpc8xxx_spi->lock);
+	init_completion(&mpc8xxx_spi->done);
+	INIT_WORK(&mpc8xxx_spi->work, mpc8xxx_spi_work);
+	INIT_LIST_HEAD(&mpc8xxx_spi->queue);
+
+	mpc8xxx_spi->workqueue = create_singlethread_workqueue(
+		dev_name(master->dev.parent));
+	if (mpc8xxx_spi->workqueue == NULL) {
+		ret = -EBUSY;
+		goto err;
+	}
+
+	return 0;
+
+err:
+	return ret;
+}
+
+int __devexit mpc8xxx_spi_remove(struct device *dev)
+{
+	struct mpc8xxx_spi *mpc8xxx_spi;
+	struct spi_master *master;
+
+	master = dev_get_drvdata(dev);
+	mpc8xxx_spi = spi_master_get_devdata(master);
+
+	flush_workqueue(mpc8xxx_spi->workqueue);
+	destroy_workqueue(mpc8xxx_spi->workqueue);
+	spi_unregister_master(master);
+
+	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
+
+	if (mpc8xxx_spi->spi_remove)
+		mpc8xxx_spi->spi_remove(mpc8xxx_spi);
+
+	return 0;
+}
+
+int __devinit of_mpc8xxx_spi_probe(struct platform_device *ofdev,
+					const struct of_device_id *ofid)
+{
+	struct device *dev = &ofdev->dev;
+	struct device_node *np = ofdev->dev.of_node;
+	struct mpc8xxx_spi_probe_info *pinfo;
+	struct fsl_spi_platform_data *pdata;
+	const void *prop;
+	int ret = -ENOMEM;
+
+	pinfo = kzalloc(sizeof(*pinfo), GFP_KERNEL);
+	if (!pinfo)
+		return -ENOMEM;
+
+	pdata = &pinfo->pdata;
+	dev->platform_data = pdata;
+
+	/* Allocate bus num dynamically. */
+	pdata->bus_num = -1;
+
+	/* SPI controller is either clocked from QE or SoC clock. */
+	pdata->sysclk = get_brgfreq();
+	if (pdata->sysclk == -1) {
+		pdata->sysclk = fsl_get_sys_freq();
+		if (pdata->sysclk == -1) {
+			ret = -ENODEV;
+			goto err;
+		}
+	}
+
+	prop = of_get_property(np, "mode", NULL);
+	if (prop && !strcmp(prop, "cpu-qe"))
+		pdata->flags = SPI_QE_CPU_MODE;
+	else if (prop && !strcmp(prop, "qe"))
+		pdata->flags = SPI_CPM_MODE | SPI_QE;
+	else if (of_device_is_compatible(np, "fsl,cpm2-spi"))
+		pdata->flags = SPI_CPM_MODE | SPI_CPM2;
+	else if (of_device_is_compatible(np, "fsl,cpm1-spi"))
+		pdata->flags = SPI_CPM_MODE | SPI_CPM1;
+
+	return 0;
+
+err:
+	kfree(pinfo);
+	return ret;
+}
diff --git a/drivers/spi/spi_fsl_lib.h b/drivers/spi/spi_fsl_lib.h
new file mode 100644
index 0000000..281e060
--- /dev/null
+++ b/drivers/spi/spi_fsl_lib.h
@@ -0,0 +1,124 @@
+/*
+ * Freescale SPI/eSPI controller driver library.
+ *
+ * Maintainer: Kumar Gala
+ *
+ * Copyright 2010 Freescale Semiconductor, Inc.
+ * Copyright (C) 2006 Polycom, Inc.
+ *
+ * CPM SPI and QE buffer descriptors mode support:
+ * Copyright (c) 2009  MontaVista Software, Inc.
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#ifndef __SPI_FSL_LIB_H__
+#define __SPI_FSL_LIB_H__
+
+#include <asm/io.h>
+
+/* SPI/eSPI Controller driver's private data. */
+struct mpc8xxx_spi {
+	struct device *dev;
+	void *reg_base;
+
+	/* rx & tx bufs from the spi_transfer */
+	const void *tx;
+	void *rx;
+#ifdef CONFIG_SPI_FSL_ESPI
+	int len;
+#endif
+
+	int subblock;
+	struct spi_pram __iomem *pram;
+	struct cpm_buf_desc __iomem *tx_bd;
+	struct cpm_buf_desc __iomem *rx_bd;
+
+	struct spi_transfer *xfer_in_progress;
+
+	/* dma addresses for CPM transfers */
+	dma_addr_t tx_dma;
+	dma_addr_t rx_dma;
+	bool map_tx_dma;
+	bool map_rx_dma;
+
+	dma_addr_t dma_dummy_tx;
+	dma_addr_t dma_dummy_rx;
+
+	/* functions to deal with different sized buffers */
+	void (*get_rx) (u32 rx_data, struct mpc8xxx_spi *);
+	u32(*get_tx) (struct mpc8xxx_spi *);
+
+	/* hooks for different controller driver */
+	void (*spi_do_one_msg) (struct spi_message *m);
+	void (*spi_remove) (struct mpc8xxx_spi *mspi);
+
+	unsigned int count;
+	unsigned int irq;
+
+	unsigned nsecs;		/* (clock cycle time)/2 */
+
+	u32 spibrg;		/* SPIBRG input clock */
+	u32 rx_shift;		/* RX data reg shift when in qe mode */
+	u32 tx_shift;		/* TX data reg shift when in qe mode */
+
+	unsigned int flags;
+
+	struct workqueue_struct *workqueue;
+	struct work_struct work;
+
+	struct list_head queue;
+	spinlock_t lock;
+
+	struct completion done;
+};
+
+struct spi_mpc8xxx_cs {
+	/* functions to deal with different sized buffers */
+	void (*get_rx) (u32 rx_data, struct mpc8xxx_spi *);
+	u32 (*get_tx) (struct mpc8xxx_spi *);
+	u32 rx_shift;		/* RX data reg shift when in qe mode */
+	u32 tx_shift;		/* TX data reg shift when in qe mode */
+	u32 hw_mode;		/* Holds HW mode register settings */
+};
+
+static inline void mpc8xxx_spi_write_reg(__be32 __iomem *reg, u32 val)
+{
+	out_be32(reg, val);
+}
+
+static inline u32 mpc8xxx_spi_read_reg(__be32 __iomem *reg)
+{
+	return in_be32(reg);
+}
+
+struct mpc8xxx_spi_probe_info {
+	struct fsl_spi_platform_data pdata;
+	int *gpios;
+	bool *alow_flags;
+};
+
+extern u32 mpc8xxx_spi_tx_buf_u8(struct mpc8xxx_spi *mpc8xxx_spi);
+extern u32 mpc8xxx_spi_tx_buf_u16(struct mpc8xxx_spi *mpc8xxx_spi);
+extern u32 mpc8xxx_spi_tx_buf_u32(struct mpc8xxx_spi *mpc8xxx_spi);
+extern void mpc8xxx_spi_rx_buf_u8(u32 data, struct mpc8xxx_spi *mpc8xxx_spi);
+extern void mpc8xxx_spi_rx_buf_u16(u32 data, struct mpc8xxx_spi *mpc8xxx_spi);
+extern void mpc8xxx_spi_rx_buf_u32(u32 data, struct mpc8xxx_spi *mpc8xxx_spi);
+
+extern struct mpc8xxx_spi_probe_info *to_of_pinfo(
+		struct fsl_spi_platform_data *pdata);
+extern int mpc8xxx_spi_bufs(struct mpc8xxx_spi *mspi,
+		struct spi_transfer *t, unsigned int len);
+extern int mpc8xxx_spi_transfer(struct spi_device *spi, struct spi_message *m);
+extern void mpc8xxx_spi_cleanup(struct spi_device *spi);
+extern const char *mpc8xxx_spi_strmode(unsigned int flags);
+extern int mpc8xxx_spi_probe(struct device *dev, struct resource *mem,
+		unsigned int irq);
+extern int mpc8xxx_spi_remove(struct device *dev);
+extern int of_mpc8xxx_spi_probe(struct platform_device *ofdev,
+				const struct of_device_id *ofid);
+
+#endif /* __SPI_FSL_LIB_H__ */
diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_fsl_spi.c
similarity index 64%
rename from drivers/spi/spi_mpc8xxx.c
rename to drivers/spi/spi_fsl_spi.c
index 1dd86b8..7ca52d3 100644
--- a/drivers/spi/spi_mpc8xxx.c
+++ b/drivers/spi/spi_fsl_spi.c
@@ -1,9 +1,10 @@
 /*
- * MPC8xxx SPI controller driver.
+ * Freescale SPI controller driver.
  *
  * Maintainer: Kumar Gala
  *
  * Copyright (C) 2006 Polycom, Inc.
+ * Copyright 2010 Freescale Semiconductor, Inc.
  *
  * CPM SPI and QE buffer descriptors mode support:
  * Copyright (c) 2009  MontaVista Software, Inc.
@@ -15,18 +16,11 @@
  * option) any later version.
  */
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/bug.h>
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/completion.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
-#include <linux/device.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 #include <linux/platform_device.h>
@@ -38,12 +32,12 @@
 #include <linux/of_platform.h>
 #include <linux/gpio.h>
 #include <linux/of_gpio.h>
-#include <linux/slab.h>
 
 #include <sysdev/fsl_soc.h>
 #include <asm/cpm.h>
 #include <asm/qe.h>
-#include <asm/irq.h>
+
+#include "spi_fsl_lib.h"
 
 /* CPM1 and CPM2 are mutually exclusive. */
 #ifdef CONFIG_CPM1
@@ -55,7 +49,7 @@
 #endif
 
 /* SPI Controller registers */
-struct mpc8xxx_spi_reg {
+struct fsl_spi_reg {
 	u8 res1[0x20];
 	__be32 mode;
 	__be32 event;
@@ -80,7 +74,7 @@
 
 /*
  * Default for SPI Mode:
- * 	SPI MODE 0 (inactive low, phase middle, MSB, 8-bit length, slow clk
+ *	SPI MODE 0 (inactive low, phase middle, MSB, 8-bit length, slow clk
  */
 #define	SPMODE_INIT_VAL (SPMODE_CI_INACTIVEHIGH | SPMODE_DIV16 | SPMODE_REV | \
 			 SPMODE_MS | SPMODE_LEN(7) | SPMODE_PM(0xf))
@@ -102,112 +96,16 @@
 #define	SPI_PRAM_SIZE	0x100
 #define	SPI_MRBLR	((unsigned int)PAGE_SIZE)
 
-/* SPI Controller driver's private data. */
-struct mpc8xxx_spi {
-	struct device *dev;
-	struct mpc8xxx_spi_reg __iomem *base;
+static void *fsl_dummy_rx;
+static DEFINE_MUTEX(fsl_dummy_rx_lock);
+static int fsl_dummy_rx_refcnt;
 
-	/* rx & tx bufs from the spi_transfer */
-	const void *tx;
-	void *rx;
-
-	int subblock;
-	struct spi_pram __iomem *pram;
-	struct cpm_buf_desc __iomem *tx_bd;
-	struct cpm_buf_desc __iomem *rx_bd;
-
-	struct spi_transfer *xfer_in_progress;
-
-	/* dma addresses for CPM transfers */
-	dma_addr_t tx_dma;
-	dma_addr_t rx_dma;
-	bool map_tx_dma;
-	bool map_rx_dma;
-
-	dma_addr_t dma_dummy_tx;
-	dma_addr_t dma_dummy_rx;
-
-	/* functions to deal with different sized buffers */
-	void (*get_rx) (u32 rx_data, struct mpc8xxx_spi *);
-	u32(*get_tx) (struct mpc8xxx_spi *);
-
-	unsigned int count;
-	unsigned int irq;
-
-	unsigned nsecs;		/* (clock cycle time)/2 */
-
-	u32 spibrg;		/* SPIBRG input clock */
-	u32 rx_shift;		/* RX data reg shift when in qe mode */
-	u32 tx_shift;		/* TX data reg shift when in qe mode */
-
-	unsigned int flags;
-
-	struct workqueue_struct *workqueue;
-	struct work_struct work;
-
-	struct list_head queue;
-	spinlock_t lock;
-
-	struct completion done;
-};
-
-static void *mpc8xxx_dummy_rx;
-static DEFINE_MUTEX(mpc8xxx_dummy_rx_lock);
-static int mpc8xxx_dummy_rx_refcnt;
-
-struct spi_mpc8xxx_cs {
-	/* functions to deal with different sized buffers */
-	void (*get_rx) (u32 rx_data, struct mpc8xxx_spi *);
-	u32 (*get_tx) (struct mpc8xxx_spi *);
-	u32 rx_shift;		/* RX data reg shift when in qe mode */
-	u32 tx_shift;		/* TX data reg shift when in qe mode */
-	u32 hw_mode;		/* Holds HW mode register settings */
-};
-
-static inline void mpc8xxx_spi_write_reg(__be32 __iomem *reg, u32 val)
-{
-	out_be32(reg, val);
-}
-
-static inline u32 mpc8xxx_spi_read_reg(__be32 __iomem *reg)
-{
-	return in_be32(reg);
-}
-
-#define MPC83XX_SPI_RX_BUF(type) 					  \
-static									  \
-void mpc8xxx_spi_rx_buf_##type(u32 data, struct mpc8xxx_spi *mpc8xxx_spi) \
-{									  \
-	type *rx = mpc8xxx_spi->rx;					  \
-	*rx++ = (type)(data >> mpc8xxx_spi->rx_shift);			  \
-	mpc8xxx_spi->rx = rx;						  \
-}
-
-#define MPC83XX_SPI_TX_BUF(type)				\
-static								\
-u32 mpc8xxx_spi_tx_buf_##type(struct mpc8xxx_spi *mpc8xxx_spi)	\
-{								\
-	u32 data;						\
-	const type *tx = mpc8xxx_spi->tx;			\
-	if (!tx)						\
-		return 0;					\
-	data = *tx++ << mpc8xxx_spi->tx_shift;			\
-	mpc8xxx_spi->tx = tx;					\
-	return data;						\
-}
-
-MPC83XX_SPI_RX_BUF(u8)
-MPC83XX_SPI_RX_BUF(u16)
-MPC83XX_SPI_RX_BUF(u32)
-MPC83XX_SPI_TX_BUF(u8)
-MPC83XX_SPI_TX_BUF(u16)
-MPC83XX_SPI_TX_BUF(u32)
-
-static void mpc8xxx_spi_change_mode(struct spi_device *spi)
+static void fsl_spi_change_mode(struct spi_device *spi)
 {
 	struct mpc8xxx_spi *mspi = spi_master_get_devdata(spi->master);
 	struct spi_mpc8xxx_cs *cs = spi->controller_state;
-	__be32 __iomem *mode = &mspi->base->mode;
+	struct fsl_spi_reg *reg_base = mspi->reg_base;
+	__be32 __iomem *mode = &reg_base->mode;
 	unsigned long flags;
 
 	if (cs->hw_mode == mpc8xxx_spi_read_reg(mode))
@@ -238,7 +136,7 @@
 	local_irq_restore(flags);
 }
 
-static void mpc8xxx_spi_chipselect(struct spi_device *spi, int value)
+static void fsl_spi_chipselect(struct spi_device *spi, int value)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
 	struct fsl_spi_platform_data *pdata = spi->dev.parent->platform_data;
@@ -256,18 +154,17 @@
 		mpc8xxx_spi->get_rx = cs->get_rx;
 		mpc8xxx_spi->get_tx = cs->get_tx;
 
-		mpc8xxx_spi_change_mode(spi);
+		fsl_spi_change_mode(spi);
 
 		if (pdata->cs_control)
 			pdata->cs_control(spi, pol);
 	}
 }
 
-static int
-mspi_apply_cpu_mode_quirks(struct spi_mpc8xxx_cs *cs,
-			   struct spi_device *spi,
-			   struct mpc8xxx_spi *mpc8xxx_spi,
-			   int bits_per_word)
+static int mspi_apply_cpu_mode_quirks(struct spi_mpc8xxx_cs *cs,
+				struct spi_device *spi,
+				struct mpc8xxx_spi *mpc8xxx_spi,
+				int bits_per_word)
 {
 	cs->rx_shift = 0;
 	cs->tx_shift = 0;
@@ -307,10 +204,9 @@
 	return bits_per_word;
 }
 
-static int
-mspi_apply_qe_mode_quirks(struct spi_mpc8xxx_cs *cs,
-			  struct spi_device *spi,
-			  int bits_per_word)
+static int mspi_apply_qe_mode_quirks(struct spi_mpc8xxx_cs *cs,
+				struct spi_device *spi,
+				int bits_per_word)
 {
 	/* QE uses Little Endian for words > 8
 	 * so transform all words > 8 into 8 bits
@@ -326,13 +222,13 @@
 	return bits_per_word;
 }
 
-static
-int mpc8xxx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
+static int fsl_spi_setup_transfer(struct spi_device *spi,
+					struct spi_transfer *t)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi;
-	int bits_per_word;
+	int bits_per_word = 0;
 	u8 pm;
-	u32 hz;
+	u32 hz = 0;
 	struct spi_mpc8xxx_cs	*cs = spi->controller_state;
 
 	mpc8xxx_spi = spi_master_get_devdata(spi->master);
@@ -340,9 +236,6 @@
 	if (t) {
 		bits_per_word = t->bits_per_word;
 		hz = t->speed_hz;
-	} else {
-		bits_per_word = 0;
-		hz = 0;
 	}
 
 	/* spi_transfer level calls that work per-word */
@@ -388,23 +281,25 @@
 			  hz, mpc8xxx_spi->spibrg / 1024);
 		if (pm > 16)
 			pm = 16;
-	} else
+	} else {
 		pm = (mpc8xxx_spi->spibrg - 1) / (hz * 4) + 1;
+	}
 	if (pm)
 		pm--;
 
 	cs->hw_mode |= SPMODE_PM(pm);
 
-	mpc8xxx_spi_change_mode(spi);
+	fsl_spi_change_mode(spi);
 	return 0;
 }
 
-static void mpc8xxx_spi_cpm_bufs_start(struct mpc8xxx_spi *mspi)
+static void fsl_spi_cpm_bufs_start(struct mpc8xxx_spi *mspi)
 {
 	struct cpm_buf_desc __iomem *tx_bd = mspi->tx_bd;
 	struct cpm_buf_desc __iomem *rx_bd = mspi->rx_bd;
 	unsigned int xfer_len = min(mspi->count, SPI_MRBLR);
 	unsigned int xfer_ofs;
+	struct fsl_spi_reg *reg_base = mspi->reg_base;
 
 	xfer_ofs = mspi->xfer_in_progress->len - mspi->count;
 
@@ -424,13 +319,14 @@
 				 BD_SC_LAST);
 
 	/* start transfer */
-	mpc8xxx_spi_write_reg(&mspi->base->command, SPCOM_STR);
+	mpc8xxx_spi_write_reg(&reg_base->command, SPCOM_STR);
 }
 
-static int mpc8xxx_spi_cpm_bufs(struct mpc8xxx_spi *mspi,
+static int fsl_spi_cpm_bufs(struct mpc8xxx_spi *mspi,
 				struct spi_transfer *t, bool is_dma_mapped)
 {
 	struct device *dev = mspi->dev;
+	struct fsl_spi_reg *reg_base = mspi->reg_base;
 
 	if (is_dma_mapped) {
 		mspi->map_tx_dma = 0;
@@ -475,13 +371,13 @@
 	}
 
 	/* enable rx ints */
-	mpc8xxx_spi_write_reg(&mspi->base->mask, SPIE_RXB);
+	mpc8xxx_spi_write_reg(&reg_base->mask, SPIE_RXB);
 
 	mspi->xfer_in_progress = t;
 	mspi->count = t->len;
 
 	/* start CPM transfers */
-	mpc8xxx_spi_cpm_bufs_start(mspi);
+	fsl_spi_cpm_bufs_start(mspi);
 
 	return 0;
 
@@ -491,7 +387,7 @@
 	return -ENOMEM;
 }
 
-static void mpc8xxx_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi)
+static void fsl_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi)
 {
 	struct device *dev = mspi->dev;
 	struct spi_transfer *t = mspi->xfer_in_progress;
@@ -503,31 +399,34 @@
 	mspi->xfer_in_progress = NULL;
 }
 
-static int mpc8xxx_spi_cpu_bufs(struct mpc8xxx_spi *mspi,
+static int fsl_spi_cpu_bufs(struct mpc8xxx_spi *mspi,
 				struct spi_transfer *t, unsigned int len)
 {
 	u32 word;
+	struct fsl_spi_reg *reg_base = mspi->reg_base;
 
 	mspi->count = len;
 
 	/* enable rx ints */
-	mpc8xxx_spi_write_reg(&mspi->base->mask, SPIM_NE);
+	mpc8xxx_spi_write_reg(&reg_base->mask, SPIM_NE);
 
 	/* transmit word */
 	word = mspi->get_tx(mspi);
-	mpc8xxx_spi_write_reg(&mspi->base->transmit, word);
+	mpc8xxx_spi_write_reg(&reg_base->transmit, word);
 
 	return 0;
 }
 
-static int mpc8xxx_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
+static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
 			    bool is_dma_mapped)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
+	struct fsl_spi_reg *reg_base;
 	unsigned int len = t->len;
 	u8 bits_per_word;
 	int ret;
 
+	reg_base = mpc8xxx_spi->reg_base;
 	bits_per_word = spi->bits_per_word;
 	if (t->bits_per_word)
 		bits_per_word = t->bits_per_word;
@@ -551,24 +450,24 @@
 	INIT_COMPLETION(mpc8xxx_spi->done);
 
 	if (mpc8xxx_spi->flags & SPI_CPM_MODE)
-		ret = mpc8xxx_spi_cpm_bufs(mpc8xxx_spi, t, is_dma_mapped);
+		ret = fsl_spi_cpm_bufs(mpc8xxx_spi, t, is_dma_mapped);
 	else
-		ret = mpc8xxx_spi_cpu_bufs(mpc8xxx_spi, t, len);
+		ret = fsl_spi_cpu_bufs(mpc8xxx_spi, t, len);
 	if (ret)
 		return ret;
 
 	wait_for_completion(&mpc8xxx_spi->done);
 
 	/* disable rx ints */
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->mask, 0);
+	mpc8xxx_spi_write_reg(&reg_base->mask, 0);
 
 	if (mpc8xxx_spi->flags & SPI_CPM_MODE)
-		mpc8xxx_spi_cpm_bufs_complete(mpc8xxx_spi);
+		fsl_spi_cpm_bufs_complete(mpc8xxx_spi);
 
 	return mpc8xxx_spi->count;
 }
 
-static void mpc8xxx_spi_do_one_msg(struct spi_message *m)
+static void fsl_spi_do_one_msg(struct spi_message *m)
 {
 	struct spi_device *spi = m->spi;
 	struct spi_transfer *t;
@@ -584,18 +483,18 @@
 			status = -EINVAL;
 
 			if (cs_change)
-				status = mpc8xxx_spi_setup_transfer(spi, t);
+				status = fsl_spi_setup_transfer(spi, t);
 			if (status < 0)
 				break;
 		}
 
 		if (cs_change) {
-			mpc8xxx_spi_chipselect(spi, BITBANG_CS_ACTIVE);
+			fsl_spi_chipselect(spi, BITBANG_CS_ACTIVE);
 			ndelay(nsecs);
 		}
 		cs_change = t->cs_change;
 		if (t->len)
-			status = mpc8xxx_spi_bufs(spi, t, m->is_dma_mapped);
+			status = fsl_spi_bufs(spi, t, m->is_dma_mapped);
 		if (status) {
 			status = -EMSGSIZE;
 			break;
@@ -607,7 +506,7 @@
 
 		if (cs_change) {
 			ndelay(nsecs);
-			mpc8xxx_spi_chipselect(spi, BITBANG_CS_INACTIVE);
+			fsl_spi_chipselect(spi, BITBANG_CS_INACTIVE);
 			ndelay(nsecs);
 		}
 	}
@@ -617,35 +516,16 @@
 
 	if (status || !cs_change) {
 		ndelay(nsecs);
-		mpc8xxx_spi_chipselect(spi, BITBANG_CS_INACTIVE);
+		fsl_spi_chipselect(spi, BITBANG_CS_INACTIVE);
 	}
 
-	mpc8xxx_spi_setup_transfer(spi, NULL);
+	fsl_spi_setup_transfer(spi, NULL);
 }
 
-static void mpc8xxx_spi_work(struct work_struct *work)
-{
-	struct mpc8xxx_spi *mpc8xxx_spi = container_of(work, struct mpc8xxx_spi,
-						       work);
-
-	spin_lock_irq(&mpc8xxx_spi->lock);
-	while (!list_empty(&mpc8xxx_spi->queue)) {
-		struct spi_message *m = container_of(mpc8xxx_spi->queue.next,
-						   struct spi_message, queue);
-
-		list_del_init(&m->queue);
-		spin_unlock_irq(&mpc8xxx_spi->lock);
-
-		mpc8xxx_spi_do_one_msg(m);
-
-		spin_lock_irq(&mpc8xxx_spi->lock);
-	}
-	spin_unlock_irq(&mpc8xxx_spi->lock);
-}
-
-static int mpc8xxx_spi_setup(struct spi_device *spi)
+static int fsl_spi_setup(struct spi_device *spi)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi;
+	struct fsl_spi_reg *reg_base;
 	int retval;
 	u32 hw_mode;
 	struct spi_mpc8xxx_cs	*cs = spi->controller_state;
@@ -661,8 +541,10 @@
 	}
 	mpc8xxx_spi = spi_master_get_devdata(spi->master);
 
+	reg_base = mpc8xxx_spi->reg_base;
+
 	hw_mode = cs->hw_mode; /* Save original settings */
-	cs->hw_mode = mpc8xxx_spi_read_reg(&mpc8xxx_spi->base->mode);
+	cs->hw_mode = mpc8xxx_spi_read_reg(&reg_base->mode);
 	/* mask out bits we are going to set */
 	cs->hw_mode &= ~(SPMODE_CP_BEGIN_EDGECLK | SPMODE_CI_INACTIVEHIGH
 			 | SPMODE_REV | SPMODE_LOOP);
@@ -676,7 +558,7 @@
 	if (spi->mode & SPI_LOOP)
 		cs->hw_mode |= SPMODE_LOOP;
 
-	retval = mpc8xxx_spi_setup_transfer(spi, NULL);
+	retval = fsl_spi_setup_transfer(spi, NULL);
 	if (retval < 0) {
 		cs->hw_mode = hw_mode; /* Restore settings */
 		return retval;
@@ -684,9 +566,10 @@
 	return 0;
 }
 
-static void mpc8xxx_spi_cpm_irq(struct mpc8xxx_spi *mspi, u32 events)
+static void fsl_spi_cpm_irq(struct mpc8xxx_spi *mspi, u32 events)
 {
 	u16 len;
+	struct fsl_spi_reg *reg_base = mspi->reg_base;
 
 	dev_dbg(mspi->dev, "%s: bd datlen %d, count %d\n", __func__,
 		in_be16(&mspi->rx_bd->cbd_datlen), mspi->count);
@@ -698,20 +581,22 @@
 	}
 
 	/* Clear the events */
-	mpc8xxx_spi_write_reg(&mspi->base->event, events);
+	mpc8xxx_spi_write_reg(&reg_base->event, events);
 
 	mspi->count -= len;
 	if (mspi->count)
-		mpc8xxx_spi_cpm_bufs_start(mspi);
+		fsl_spi_cpm_bufs_start(mspi);
 	else
 		complete(&mspi->done);
 }
 
-static void mpc8xxx_spi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
+static void fsl_spi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
 {
+	struct fsl_spi_reg *reg_base = mspi->reg_base;
+
 	/* We need handle RX first */
 	if (events & SPIE_NE) {
-		u32 rx_data = mpc8xxx_spi_read_reg(&mspi->base->receive);
+		u32 rx_data = mpc8xxx_spi_read_reg(&reg_base->receive);
 
 		if (mspi->rx)
 			mspi->get_rx(rx_data, mspi);
@@ -720,102 +605,80 @@
 	if ((events & SPIE_NF) == 0)
 		/* spin until TX is done */
 		while (((events =
-			mpc8xxx_spi_read_reg(&mspi->base->event)) &
+			mpc8xxx_spi_read_reg(&reg_base->event)) &
 						SPIE_NF) == 0)
 			cpu_relax();
 
 	/* Clear the events */
-	mpc8xxx_spi_write_reg(&mspi->base->event, events);
+	mpc8xxx_spi_write_reg(&reg_base->event, events);
 
 	mspi->count -= 1;
 	if (mspi->count) {
 		u32 word = mspi->get_tx(mspi);
 
-		mpc8xxx_spi_write_reg(&mspi->base->transmit, word);
+		mpc8xxx_spi_write_reg(&reg_base->transmit, word);
 	} else {
 		complete(&mspi->done);
 	}
 }
 
-static irqreturn_t mpc8xxx_spi_irq(s32 irq, void *context_data)
+static irqreturn_t fsl_spi_irq(s32 irq, void *context_data)
 {
 	struct mpc8xxx_spi *mspi = context_data;
 	irqreturn_t ret = IRQ_NONE;
 	u32 events;
+	struct fsl_spi_reg *reg_base = mspi->reg_base;
 
 	/* Get interrupt events(tx/rx) */
-	events = mpc8xxx_spi_read_reg(&mspi->base->event);
+	events = mpc8xxx_spi_read_reg(&reg_base->event);
 	if (events)
 		ret = IRQ_HANDLED;
 
 	dev_dbg(mspi->dev, "%s: events %x\n", __func__, events);
 
 	if (mspi->flags & SPI_CPM_MODE)
-		mpc8xxx_spi_cpm_irq(mspi, events);
+		fsl_spi_cpm_irq(mspi, events);
 	else
-		mpc8xxx_spi_cpu_irq(mspi, events);
+		fsl_spi_cpu_irq(mspi, events);
 
 	return ret;
 }
 
-static int mpc8xxx_spi_transfer(struct spi_device *spi,
-				struct spi_message *m)
+static void *fsl_spi_alloc_dummy_rx(void)
 {
-	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
-	unsigned long flags;
+	mutex_lock(&fsl_dummy_rx_lock);
 
-	m->actual_length = 0;
-	m->status = -EINPROGRESS;
+	if (!fsl_dummy_rx)
+		fsl_dummy_rx = kmalloc(SPI_MRBLR, GFP_KERNEL);
+	if (fsl_dummy_rx)
+		fsl_dummy_rx_refcnt++;
 
-	spin_lock_irqsave(&mpc8xxx_spi->lock, flags);
-	list_add_tail(&m->queue, &mpc8xxx_spi->queue);
-	queue_work(mpc8xxx_spi->workqueue, &mpc8xxx_spi->work);
-	spin_unlock_irqrestore(&mpc8xxx_spi->lock, flags);
+	mutex_unlock(&fsl_dummy_rx_lock);
 
-	return 0;
+	return fsl_dummy_rx;
 }
 
-
-static void mpc8xxx_spi_cleanup(struct spi_device *spi)
+static void fsl_spi_free_dummy_rx(void)
 {
-	kfree(spi->controller_state);
-}
+	mutex_lock(&fsl_dummy_rx_lock);
 
-static void *mpc8xxx_spi_alloc_dummy_rx(void)
-{
-	mutex_lock(&mpc8xxx_dummy_rx_lock);
-
-	if (!mpc8xxx_dummy_rx)
-		mpc8xxx_dummy_rx = kmalloc(SPI_MRBLR, GFP_KERNEL);
-	if (mpc8xxx_dummy_rx)
-		mpc8xxx_dummy_rx_refcnt++;
-
-	mutex_unlock(&mpc8xxx_dummy_rx_lock);
-
-	return mpc8xxx_dummy_rx;
-}
-
-static void mpc8xxx_spi_free_dummy_rx(void)
-{
-	mutex_lock(&mpc8xxx_dummy_rx_lock);
-
-	switch (mpc8xxx_dummy_rx_refcnt) {
+	switch (fsl_dummy_rx_refcnt) {
 	case 0:
 		WARN_ON(1);
 		break;
 	case 1:
-		kfree(mpc8xxx_dummy_rx);
-		mpc8xxx_dummy_rx = NULL;
+		kfree(fsl_dummy_rx);
+		fsl_dummy_rx = NULL;
 		/* fall through */
 	default:
-		mpc8xxx_dummy_rx_refcnt--;
+		fsl_dummy_rx_refcnt--;
 		break;
 	}
 
-	mutex_unlock(&mpc8xxx_dummy_rx_lock);
+	mutex_unlock(&fsl_dummy_rx_lock);
 }
 
-static unsigned long mpc8xxx_spi_cpm_get_pram(struct mpc8xxx_spi *mspi)
+static unsigned long fsl_spi_cpm_get_pram(struct mpc8xxx_spi *mspi)
 {
 	struct device *dev = mspi->dev;
 	struct device_node *np = dev->of_node;
@@ -869,7 +732,7 @@
 	return pram_ofs;
 }
 
-static int mpc8xxx_spi_cpm_init(struct mpc8xxx_spi *mspi)
+static int fsl_spi_cpm_init(struct mpc8xxx_spi *mspi)
 {
 	struct device *dev = mspi->dev;
 	struct device_node *np = dev->of_node;
@@ -881,7 +744,7 @@
 	if (!(mspi->flags & SPI_CPM_MODE))
 		return 0;
 
-	if (!mpc8xxx_spi_alloc_dummy_rx())
+	if (!fsl_spi_alloc_dummy_rx())
 		return -ENOMEM;
 
 	if (mspi->flags & SPI_QE) {
@@ -902,7 +765,7 @@
 		}
 	}
 
-	pram_ofs = mpc8xxx_spi_cpm_get_pram(mspi);
+	pram_ofs = fsl_spi_cpm_get_pram(mspi);
 	if (IS_ERR_VALUE(pram_ofs)) {
 		dev_err(dev, "can't allocate spi parameter ram\n");
 		goto err_pram;
@@ -922,7 +785,7 @@
 		goto err_dummy_tx;
 	}
 
-	mspi->dma_dummy_rx = dma_map_single(dev, mpc8xxx_dummy_rx, SPI_MRBLR,
+	mspi->dma_dummy_rx = dma_map_single(dev, fsl_dummy_rx, SPI_MRBLR,
 					    DMA_FROM_DEVICE);
 	if (dma_mapping_error(dev, mspi->dma_dummy_rx)) {
 		dev_err(dev, "unable to map dummy rx buffer\n");
@@ -960,11 +823,11 @@
 err_bds:
 	cpm_muram_free(pram_ofs);
 err_pram:
-	mpc8xxx_spi_free_dummy_rx();
+	fsl_spi_free_dummy_rx();
 	return -ENOMEM;
 }
 
-static void mpc8xxx_spi_cpm_free(struct mpc8xxx_spi *mspi)
+static void fsl_spi_cpm_free(struct mpc8xxx_spi *mspi)
 {
 	struct device *dev = mspi->dev;
 
@@ -972,30 +835,22 @@
 	dma_unmap_single(dev, mspi->dma_dummy_tx, PAGE_SIZE, DMA_TO_DEVICE);
 	cpm_muram_free(cpm_muram_offset(mspi->tx_bd));
 	cpm_muram_free(cpm_muram_offset(mspi->pram));
-	mpc8xxx_spi_free_dummy_rx();
+	fsl_spi_free_dummy_rx();
 }
 
-static const char *mpc8xxx_spi_strmode(unsigned int flags)
+static void fsl_spi_remove(struct mpc8xxx_spi *mspi)
 {
-	if (flags & SPI_QE_CPU_MODE) {
-		return "QE CPU";
-	} else if (flags & SPI_CPM_MODE) {
-		if (flags & SPI_QE)
-			return "QE";
-		else if (flags & SPI_CPM2)
-			return "CPM2";
-		else
-			return "CPM1";
-	}
-	return "CPU";
+	iounmap(mspi->reg_base);
+	fsl_spi_cpm_free(mspi);
 }
 
-static struct spi_master * __devinit
-mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq)
+static struct spi_master * __devinit fsl_spi_probe(struct device *dev,
+		struct resource *mem, unsigned int irq)
 {
 	struct fsl_spi_platform_data *pdata = dev->platform_data;
 	struct spi_master *master;
 	struct mpc8xxx_spi *mpc8xxx_spi;
+	struct fsl_spi_reg *reg_base;
 	u32 regval;
 	int ret = 0;
 
@@ -1007,132 +862,77 @@
 
 	dev_set_drvdata(dev, master);
 
-	/* the spi->mode bits understood by this driver: */
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH
-			| SPI_LSB_FIRST | SPI_LOOP;
+	ret = mpc8xxx_spi_probe(dev, mem, irq);
+	if (ret)
+		goto err_probe;
 
-	master->setup = mpc8xxx_spi_setup;
-	master->transfer = mpc8xxx_spi_transfer;
-	master->cleanup = mpc8xxx_spi_cleanup;
-	master->dev.of_node = dev->of_node;
+	master->setup = fsl_spi_setup;
 
 	mpc8xxx_spi = spi_master_get_devdata(master);
-	mpc8xxx_spi->dev = dev;
-	mpc8xxx_spi->get_rx = mpc8xxx_spi_rx_buf_u8;
-	mpc8xxx_spi->get_tx = mpc8xxx_spi_tx_buf_u8;
-	mpc8xxx_spi->flags = pdata->flags;
-	mpc8xxx_spi->spibrg = pdata->sysclk;
+	mpc8xxx_spi->spi_do_one_msg = fsl_spi_do_one_msg;
+	mpc8xxx_spi->spi_remove = fsl_spi_remove;
 
-	ret = mpc8xxx_spi_cpm_init(mpc8xxx_spi);
+
+	ret = fsl_spi_cpm_init(mpc8xxx_spi);
 	if (ret)
 		goto err_cpm_init;
 
-	mpc8xxx_spi->rx_shift = 0;
-	mpc8xxx_spi->tx_shift = 0;
 	if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE) {
 		mpc8xxx_spi->rx_shift = 16;
 		mpc8xxx_spi->tx_shift = 24;
 	}
 
-	init_completion(&mpc8xxx_spi->done);
-
-	mpc8xxx_spi->base = ioremap(mem->start, resource_size(mem));
-	if (mpc8xxx_spi->base == NULL) {
+	mpc8xxx_spi->reg_base = ioremap(mem->start, resource_size(mem));
+	if (mpc8xxx_spi->reg_base == NULL) {
 		ret = -ENOMEM;
 		goto err_ioremap;
 	}
 
-	mpc8xxx_spi->irq = irq;
-
 	/* Register for SPI Interrupt */
-	ret = request_irq(mpc8xxx_spi->irq, mpc8xxx_spi_irq,
-			  0, "mpc8xxx_spi", mpc8xxx_spi);
+	ret = request_irq(mpc8xxx_spi->irq, fsl_spi_irq,
+			  0, "fsl_spi", mpc8xxx_spi);
 
 	if (ret != 0)
-		goto unmap_io;
+		goto free_irq;
 
-	master->bus_num = pdata->bus_num;
-	master->num_chipselect = pdata->max_chipselect;
+	reg_base = mpc8xxx_spi->reg_base;
 
 	/* SPI controller initializations */
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->mode, 0);
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->mask, 0);
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->command, 0);
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->event, 0xffffffff);
+	mpc8xxx_spi_write_reg(&reg_base->mode, 0);
+	mpc8xxx_spi_write_reg(&reg_base->mask, 0);
+	mpc8xxx_spi_write_reg(&reg_base->command, 0);
+	mpc8xxx_spi_write_reg(&reg_base->event, 0xffffffff);
 
 	/* Enable SPI interface */
 	regval = pdata->initial_spmode | SPMODE_INIT_VAL | SPMODE_ENABLE;
 	if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE)
 		regval |= SPMODE_OP;
 
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->mode, regval);
-	spin_lock_init(&mpc8xxx_spi->lock);
-	init_completion(&mpc8xxx_spi->done);
-	INIT_WORK(&mpc8xxx_spi->work, mpc8xxx_spi_work);
-	INIT_LIST_HEAD(&mpc8xxx_spi->queue);
-
-	mpc8xxx_spi->workqueue = create_singlethread_workqueue(
-		dev_name(master->dev.parent));
-	if (mpc8xxx_spi->workqueue == NULL) {
-		ret = -EBUSY;
-		goto free_irq;
-	}
+	mpc8xxx_spi_write_reg(&reg_base->mode, regval);
 
 	ret = spi_register_master(master);
 	if (ret < 0)
 		goto unreg_master;
 
-	dev_info(dev, "at 0x%p (irq = %d), %s mode\n", mpc8xxx_spi->base,
+	dev_info(dev, "at 0x%p (irq = %d), %s mode\n", reg_base,
 		 mpc8xxx_spi->irq, mpc8xxx_spi_strmode(mpc8xxx_spi->flags));
 
 	return master;
 
 unreg_master:
-	destroy_workqueue(mpc8xxx_spi->workqueue);
-free_irq:
 	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
-unmap_io:
-	iounmap(mpc8xxx_spi->base);
+free_irq:
+	iounmap(mpc8xxx_spi->reg_base);
 err_ioremap:
-	mpc8xxx_spi_cpm_free(mpc8xxx_spi);
+	fsl_spi_cpm_free(mpc8xxx_spi);
 err_cpm_init:
+err_probe:
 	spi_master_put(master);
 err:
 	return ERR_PTR(ret);
 }
 
-static int __devexit mpc8xxx_spi_remove(struct device *dev)
-{
-	struct mpc8xxx_spi *mpc8xxx_spi;
-	struct spi_master *master;
-
-	master = dev_get_drvdata(dev);
-	mpc8xxx_spi = spi_master_get_devdata(master);
-
-	flush_workqueue(mpc8xxx_spi->workqueue);
-	destroy_workqueue(mpc8xxx_spi->workqueue);
-	spi_unregister_master(master);
-
-	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
-	iounmap(mpc8xxx_spi->base);
-	mpc8xxx_spi_cpm_free(mpc8xxx_spi);
-
-	return 0;
-}
-
-struct mpc8xxx_spi_probe_info {
-	struct fsl_spi_platform_data pdata;
-	int *gpios;
-	bool *alow_flags;
-};
-
-static struct mpc8xxx_spi_probe_info *
-to_of_pinfo(struct fsl_spi_platform_data *pdata)
-{
-	return container_of(pdata, struct mpc8xxx_spi_probe_info, pdata);
-}
-
-static void mpc8xxx_spi_cs_control(struct spi_device *spi, bool on)
+static void fsl_spi_cs_control(struct spi_device *spi, bool on)
 {
 	struct device *dev = spi->dev.parent;
 	struct mpc8xxx_spi_probe_info *pinfo = to_of_pinfo(dev->platform_data);
@@ -1143,7 +943,7 @@
 	gpio_set_value(gpio, on ^ alow);
 }
 
-static int of_mpc8xxx_spi_get_chipselects(struct device *dev)
+static int of_fsl_spi_get_chipselects(struct device *dev)
 {
 	struct device_node *np = dev->of_node;
 	struct fsl_spi_platform_data *pdata = dev->platform_data;
@@ -1204,7 +1004,7 @@
 	}
 
 	pdata->max_chipselect = ngpios;
-	pdata->cs_control = mpc8xxx_spi_cs_control;
+	pdata->cs_control = fsl_spi_cs_control;
 
 	return 0;
 
@@ -1223,7 +1023,7 @@
 	return ret;
 }
 
-static int of_mpc8xxx_spi_free_chipselects(struct device *dev)
+static int of_fsl_spi_free_chipselects(struct device *dev)
 {
 	struct fsl_spi_platform_data *pdata = dev->platform_data;
 	struct mpc8xxx_spi_probe_info *pinfo = to_of_pinfo(pdata);
@@ -1242,50 +1042,21 @@
 	return 0;
 }
 
-static int __devinit of_mpc8xxx_spi_probe(struct platform_device *ofdev,
-					  const struct of_device_id *ofid)
+static int __devinit of_fsl_spi_probe(struct platform_device *ofdev,
+					const struct of_device_id *ofid)
 {
 	struct device *dev = &ofdev->dev;
 	struct device_node *np = ofdev->dev.of_node;
-	struct mpc8xxx_spi_probe_info *pinfo;
-	struct fsl_spi_platform_data *pdata;
 	struct spi_master *master;
 	struct resource mem;
 	struct resource irq;
-	const void *prop;
 	int ret = -ENOMEM;
 
-	pinfo = kzalloc(sizeof(*pinfo), GFP_KERNEL);
-	if (!pinfo)
-		return -ENOMEM;
+	ret = of_mpc8xxx_spi_probe(ofdev, ofid);
+	if (ret)
+		return ret;
 
-	pdata = &pinfo->pdata;
-	dev->platform_data = pdata;
-
-	/* Allocate bus num dynamically. */
-	pdata->bus_num = -1;
-
-	/* SPI controller is either clocked from QE or SoC clock. */
-	pdata->sysclk = get_brgfreq();
-	if (pdata->sysclk == -1) {
-		pdata->sysclk = fsl_get_sys_freq();
-		if (pdata->sysclk == -1) {
-			ret = -ENODEV;
-			goto err_clk;
-		}
-	}
-
-	prop = of_get_property(np, "mode", NULL);
-	if (prop && !strcmp(prop, "cpu-qe"))
-		pdata->flags = SPI_QE_CPU_MODE;
-	else if (prop && !strcmp(prop, "qe"))
-		pdata->flags = SPI_CPM_MODE | SPI_QE;
-	else if (of_device_is_compatible(np, "fsl,cpm2-spi"))
-		pdata->flags = SPI_CPM_MODE | SPI_CPM2;
-	else if (of_device_is_compatible(np, "fsl,cpm1-spi"))
-		pdata->flags = SPI_CPM_MODE | SPI_CPM1;
-
-	ret = of_mpc8xxx_spi_get_chipselects(dev);
+	ret = of_fsl_spi_get_chipselects(dev);
 	if (ret)
 		goto err;
 
@@ -1299,7 +1070,7 @@
 		goto err;
 	}
 
-	master = mpc8xxx_spi_probe(dev, &mem, irq.start);
+	master = fsl_spi_probe(dev, &mem, irq.start);
 	if (IS_ERR(master)) {
 		ret = PTR_ERR(master);
 		goto err;
@@ -1308,42 +1079,40 @@
 	return 0;
 
 err:
-	of_mpc8xxx_spi_free_chipselects(dev);
-err_clk:
-	kfree(pinfo);
+	of_fsl_spi_free_chipselects(dev);
 	return ret;
 }
 
-static int __devexit of_mpc8xxx_spi_remove(struct platform_device *ofdev)
+static int __devexit of_fsl_spi_remove(struct platform_device *ofdev)
 {
 	int ret;
 
 	ret = mpc8xxx_spi_remove(&ofdev->dev);
 	if (ret)
 		return ret;
-	of_mpc8xxx_spi_free_chipselects(&ofdev->dev);
+	of_fsl_spi_free_chipselects(&ofdev->dev);
 	return 0;
 }
 
-static const struct of_device_id of_mpc8xxx_spi_match[] = {
+static const struct of_device_id of_fsl_spi_match[] = {
 	{ .compatible = "fsl,spi" },
-	{},
+	{}
 };
-MODULE_DEVICE_TABLE(of, of_mpc8xxx_spi_match);
+MODULE_DEVICE_TABLE(of, of_fsl_spi_match);
 
-static struct of_platform_driver of_mpc8xxx_spi_driver = {
+static struct of_platform_driver of_fsl_spi_driver = {
 	.driver = {
-		.name = "mpc8xxx_spi",
+		.name = "fsl_spi",
 		.owner = THIS_MODULE,
-		.of_match_table = of_mpc8xxx_spi_match,
+		.of_match_table = of_fsl_spi_match,
 	},
-	.probe		= of_mpc8xxx_spi_probe,
-	.remove		= __devexit_p(of_mpc8xxx_spi_remove),
+	.probe		= of_fsl_spi_probe,
+	.remove		= __devexit_p(of_fsl_spi_remove),
 };
 
 #ifdef CONFIG_MPC832x_RDB
 /*
- * 				XXX XXX XXX
+ * XXX XXX XXX
  * This is "legacy" platform driver, was used by the MPC8323E-RDB boards
  * only. The driver should go away soon, since newer MPC8323E-RDB's device
  * tree can work with OpenFirmware driver. But for now we support old trees
@@ -1366,7 +1135,7 @@
 	if (irq <= 0)
 		return -EINVAL;
 
-	master = mpc8xxx_spi_probe(&pdev->dev, mem, irq);
+	master = fsl_spi_probe(&pdev->dev, mem, irq);
 	if (IS_ERR(master))
 		return PTR_ERR(master);
 	return 0;
@@ -1405,21 +1174,20 @@
 static void __exit legacy_driver_unregister(void) {}
 #endif /* CONFIG_MPC832x_RDB */
 
-static int __init mpc8xxx_spi_init(void)
+static int __init fsl_spi_init(void)
 {
 	legacy_driver_register();
-	return of_register_platform_driver(&of_mpc8xxx_spi_driver);
+	return of_register_platform_driver(&of_fsl_spi_driver);
 }
+module_init(fsl_spi_init);
 
-static void __exit mpc8xxx_spi_exit(void)
+static void __exit fsl_spi_exit(void)
 {
-	of_unregister_platform_driver(&of_mpc8xxx_spi_driver);
+	of_unregister_platform_driver(&of_fsl_spi_driver);
 	legacy_driver_unregister();
 }
-
-module_init(mpc8xxx_spi_init);
-module_exit(mpc8xxx_spi_exit);
+module_exit(fsl_spi_exit);
 
 MODULE_AUTHOR("Kumar Gala");
-MODULE_DESCRIPTION("Simple MPC8xxx SPI Driver");
+MODULE_DESCRIPTION("Simple Freescale SPI Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi_imx.c b/drivers/spi/spi_imx.c
index 7972e90..55a38e2 100644
--- a/drivers/spi/spi_imx.c
+++ b/drivers/spi/spi_imx.c
@@ -56,7 +56,28 @@
 	unsigned int speed_hz;
 	unsigned int bpw;
 	unsigned int mode;
-	int cs;
+	u8 cs;
+};
+
+enum spi_imx_devtype {
+	SPI_IMX_VER_IMX1,
+	SPI_IMX_VER_0_0,
+	SPI_IMX_VER_0_4,
+	SPI_IMX_VER_0_5,
+	SPI_IMX_VER_0_7,
+	SPI_IMX_VER_2_3,
+	SPI_IMX_VER_AUTODETECT,
+};
+
+struct spi_imx_data;
+
+struct spi_imx_devtype_data {
+	void (*intctrl)(struct spi_imx_data *, int);
+	int (*config)(struct spi_imx_data *, struct spi_imx_config *);
+	void (*trigger)(struct spi_imx_data *);
+	int (*rx_available)(struct spi_imx_data *);
+	void (*reset)(struct spi_imx_data *);
+	unsigned int fifosize;
 };
 
 struct spi_imx_data {
@@ -76,11 +97,7 @@
 	const void *tx_buf;
 	unsigned int txfifo; /* number of words pushed in tx FIFO */
 
-	/* SoC specific functions */
-	void (*intctrl)(struct spi_imx_data *, int);
-	int (*config)(struct spi_imx_data *, struct spi_imx_config *);
-	void (*trigger)(struct spi_imx_data *);
-	int (*rx_available)(struct spi_imx_data *);
+	struct spi_imx_devtype_data devtype_data;
 };
 
 #define MXC_SPI_BUF_RX(type)						\
@@ -140,7 +157,7 @@
 	return max;
 }
 
-/* MX1, MX31, MX35 */
+/* MX1, MX31, MX35, MX51 CSPI */
 static unsigned int spi_imx_clkdiv_2(unsigned int fin,
 		unsigned int fspi)
 {
@@ -155,6 +172,128 @@
 	return 7;
 }
 
+#define SPI_IMX2_3_CTRL		0x08
+#define SPI_IMX2_3_CTRL_ENABLE		(1 <<  0)
+#define SPI_IMX2_3_CTRL_XCH		(1 <<  2)
+#define SPI_IMX2_3_CTRL_MODE(cs)	(1 << ((cs) +  4))
+#define SPI_IMX2_3_CTRL_POSTDIV_OFFSET	8
+#define SPI_IMX2_3_CTRL_PREDIV_OFFSET	12
+#define SPI_IMX2_3_CTRL_CS(cs)		((cs) << 18)
+#define SPI_IMX2_3_CTRL_BL_OFFSET	20
+
+#define SPI_IMX2_3_CONFIG	0x0c
+#define SPI_IMX2_3_CONFIG_SCLKPHA(cs)	(1 << ((cs) +  0))
+#define SPI_IMX2_3_CONFIG_SCLKPOL(cs)	(1 << ((cs) +  4))
+#define SPI_IMX2_3_CONFIG_SBBCTRL(cs)	(1 << ((cs) +  8))
+#define SPI_IMX2_3_CONFIG_SSBPOL(cs)	(1 << ((cs) + 12))
+
+#define SPI_IMX2_3_INT		0x10
+#define SPI_IMX2_3_INT_TEEN		(1 <<  0)
+#define SPI_IMX2_3_INT_RREN		(1 <<  3)
+
+#define SPI_IMX2_3_STAT		0x18
+#define SPI_IMX2_3_STAT_RR		(1 <<  3)
+
+/* MX51 eCSPI */
+static unsigned int spi_imx2_3_clkdiv(unsigned int fin, unsigned int fspi)
+{
+	/*
+	 * there are two 4-bit dividers, the pre-divider divides by
+	 * $pre, the post-divider by 2^$post
+	 */
+	unsigned int pre, post;
+
+	if (unlikely(fspi > fin))
+		return 0;
+
+	post = fls(fin) - fls(fspi);
+	if (fin > fspi << post)
+		post++;
+
+	/* now we have: (fin <= fspi << post) with post being minimal */
+
+	post = max(4U, post) - 4;
+	if (unlikely(post > 0xf)) {
+		pr_err("%s: cannot set clock freq: %u (base freq: %u)\n",
+				__func__, fspi, fin);
+		return 0xff;
+	}
+
+	pre = DIV_ROUND_UP(fin, fspi << post) - 1;
+
+	pr_debug("%s: fin: %u, fspi: %u, post: %u, pre: %u\n",
+			__func__, fin, fspi, post, pre);
+	return (pre << SPI_IMX2_3_CTRL_PREDIV_OFFSET) |
+		(post << SPI_IMX2_3_CTRL_POSTDIV_OFFSET);
+}
+
+static void __maybe_unused spi_imx2_3_intctrl(struct spi_imx_data *spi_imx, int enable)
+{
+	unsigned val = 0;
+
+	if (enable & MXC_INT_TE)
+		val |= SPI_IMX2_3_INT_TEEN;
+
+	if (enable & MXC_INT_RR)
+		val |= SPI_IMX2_3_INT_RREN;
+
+	writel(val, spi_imx->base + SPI_IMX2_3_INT);
+}
+
+static void __maybe_unused spi_imx2_3_trigger(struct spi_imx_data *spi_imx)
+{
+	u32 reg;
+
+	reg = readl(spi_imx->base + SPI_IMX2_3_CTRL);
+	reg |= SPI_IMX2_3_CTRL_XCH;
+	writel(reg, spi_imx->base + SPI_IMX2_3_CTRL);
+}
+
+static int __maybe_unused spi_imx2_3_config(struct spi_imx_data *spi_imx,
+		struct spi_imx_config *config)
+{
+	u32 ctrl = SPI_IMX2_3_CTRL_ENABLE, cfg = 0;
+
+	/* set master mode */
+	ctrl |= SPI_IMX2_3_CTRL_MODE(config->cs);
+
+	/* set clock speed */
+	ctrl |= spi_imx2_3_clkdiv(spi_imx->spi_clk, config->speed_hz);
+
+	/* set chip select to use */
+	ctrl |= SPI_IMX2_3_CTRL_CS(config->cs);
+
+	ctrl |= (config->bpw - 1) << SPI_IMX2_3_CTRL_BL_OFFSET;
+
+	cfg |= SPI_IMX2_3_CONFIG_SBBCTRL(config->cs);
+
+	if (config->mode & SPI_CPHA)
+		cfg |= SPI_IMX2_3_CONFIG_SCLKPHA(config->cs);
+
+	if (config->mode & SPI_CPOL)
+		cfg |= SPI_IMX2_3_CONFIG_SCLKPOL(config->cs);
+
+	if (config->mode & SPI_CS_HIGH)
+		cfg |= SPI_IMX2_3_CONFIG_SSBPOL(config->cs);
+
+	writel(ctrl, spi_imx->base + SPI_IMX2_3_CTRL);
+	writel(cfg, spi_imx->base + SPI_IMX2_3_CONFIG);
+
+	return 0;
+}
+
+static int __maybe_unused spi_imx2_3_rx_available(struct spi_imx_data *spi_imx)
+{
+	return readl(spi_imx->base + SPI_IMX2_3_STAT) & SPI_IMX2_3_STAT_RR;
+}
+
+static void __maybe_unused spi_imx2_3_reset(struct spi_imx_data *spi_imx)
+{
+	/* drain receive buffer */
+	while (spi_imx2_3_rx_available(spi_imx))
+		readl(spi_imx->base + MXC_CSPIRXDATA);
+}
+
 #define MX31_INTREG_TEEN	(1 << 0)
 #define MX31_INTREG_RREN	(1 << 3)
 
@@ -178,7 +317,7 @@
  * the i.MX35 has a slightly different register layout for bits
  * we do not use here.
  */
-static void mx31_intctrl(struct spi_imx_data *spi_imx, int enable)
+static void __maybe_unused mx31_intctrl(struct spi_imx_data *spi_imx, int enable)
 {
 	unsigned int val = 0;
 
@@ -190,7 +329,7 @@
 	writel(val, spi_imx->base + MXC_CSPIINT);
 }
 
-static void mx31_trigger(struct spi_imx_data *spi_imx)
+static void __maybe_unused mx31_trigger(struct spi_imx_data *spi_imx)
 {
 	unsigned int reg;
 
@@ -199,20 +338,16 @@
 	writel(reg, spi_imx->base + MXC_CSPICTRL);
 }
 
-static int mx31_config(struct spi_imx_data *spi_imx,
+static int __maybe_unused spi_imx0_4_config(struct spi_imx_data *spi_imx,
 		struct spi_imx_config *config)
 {
 	unsigned int reg = MX31_CSPICTRL_ENABLE | MX31_CSPICTRL_MASTER;
+	int cs = spi_imx->chipselect[config->cs];
 
 	reg |= spi_imx_clkdiv_2(spi_imx->spi_clk, config->speed_hz) <<
 		MX31_CSPICTRL_DR_SHIFT;
 
-	if (cpu_is_mx31())
-		reg |= (config->bpw - 1) << MX31_CSPICTRL_BC_SHIFT;
-	else if (cpu_is_mx25() || cpu_is_mx35()) {
-		reg |= (config->bpw - 1) << MX35_CSPICTRL_BL_SHIFT;
-		reg |= MX31_CSPICTRL_SSCTL;
-	}
+	reg |= (config->bpw - 1) << MX31_CSPICTRL_BC_SHIFT;
 
 	if (config->mode & SPI_CPHA)
 		reg |= MX31_CSPICTRL_PHA;
@@ -220,23 +355,52 @@
 		reg |= MX31_CSPICTRL_POL;
 	if (config->mode & SPI_CS_HIGH)
 		reg |= MX31_CSPICTRL_SSPOL;
-	if (config->cs < 0) {
-		if (cpu_is_mx31())
-			reg |= (config->cs + 32) << MX31_CSPICTRL_CS_SHIFT;
-		else if (cpu_is_mx25() || cpu_is_mx35())
-			reg |= (config->cs + 32) << MX35_CSPICTRL_CS_SHIFT;
-	}
+	if (cs < 0)
+		reg |= (cs + 32) << MX31_CSPICTRL_CS_SHIFT;
 
 	writel(reg, spi_imx->base + MXC_CSPICTRL);
 
 	return 0;
 }
 
-static int mx31_rx_available(struct spi_imx_data *spi_imx)
+static int __maybe_unused spi_imx0_7_config(struct spi_imx_data *spi_imx,
+		struct spi_imx_config *config)
+{
+	unsigned int reg = MX31_CSPICTRL_ENABLE | MX31_CSPICTRL_MASTER;
+	int cs = spi_imx->chipselect[config->cs];
+
+	reg |= spi_imx_clkdiv_2(spi_imx->spi_clk, config->speed_hz) <<
+		MX31_CSPICTRL_DR_SHIFT;
+
+	reg |= (config->bpw - 1) << MX35_CSPICTRL_BL_SHIFT;
+	reg |= MX31_CSPICTRL_SSCTL;
+
+	if (config->mode & SPI_CPHA)
+		reg |= MX31_CSPICTRL_PHA;
+	if (config->mode & SPI_CPOL)
+		reg |= MX31_CSPICTRL_POL;
+	if (config->mode & SPI_CS_HIGH)
+		reg |= MX31_CSPICTRL_SSPOL;
+	if (cs < 0)
+		reg |= (cs + 32) << MX35_CSPICTRL_CS_SHIFT;
+
+	writel(reg, spi_imx->base + MXC_CSPICTRL);
+
+	return 0;
+}
+
+static int __maybe_unused mx31_rx_available(struct spi_imx_data *spi_imx)
 {
 	return readl(spi_imx->base + MX31_CSPISTATUS) & MX31_STATUS_RR;
 }
 
+static void __maybe_unused spi_imx0_4_reset(struct spi_imx_data *spi_imx)
+{
+	/* drain receive buffer */
+	while (readl(spi_imx->base + MX3_CSPISTAT) & MX3_CSPISTAT_RR)
+		readl(spi_imx->base + MXC_CSPIRXDATA);
+}
+
 #define MX27_INTREG_RR		(1 << 4)
 #define MX27_INTREG_TEEN	(1 << 9)
 #define MX27_INTREG_RREN	(1 << 13)
@@ -250,7 +414,7 @@
 #define MX27_CSPICTRL_DR_SHIFT	14
 #define MX27_CSPICTRL_CS_SHIFT	19
 
-static void mx27_intctrl(struct spi_imx_data *spi_imx, int enable)
+static void __maybe_unused mx27_intctrl(struct spi_imx_data *spi_imx, int enable)
 {
 	unsigned int val = 0;
 
@@ -262,7 +426,7 @@
 	writel(val, spi_imx->base + MXC_CSPIINT);
 }
 
-static void mx27_trigger(struct spi_imx_data *spi_imx)
+static void __maybe_unused mx27_trigger(struct spi_imx_data *spi_imx)
 {
 	unsigned int reg;
 
@@ -271,10 +435,11 @@
 	writel(reg, spi_imx->base + MXC_CSPICTRL);
 }
 
-static int mx27_config(struct spi_imx_data *spi_imx,
+static int __maybe_unused mx27_config(struct spi_imx_data *spi_imx,
 		struct spi_imx_config *config)
 {
 	unsigned int reg = MX27_CSPICTRL_ENABLE | MX27_CSPICTRL_MASTER;
+	int cs = spi_imx->chipselect[config->cs];
 
 	reg |= spi_imx_clkdiv_1(spi_imx->spi_clk, config->speed_hz) <<
 		MX27_CSPICTRL_DR_SHIFT;
@@ -286,19 +451,24 @@
 		reg |= MX27_CSPICTRL_POL;
 	if (config->mode & SPI_CS_HIGH)
 		reg |= MX27_CSPICTRL_SSPOL;
-	if (config->cs < 0)
-		reg |= (config->cs + 32) << MX27_CSPICTRL_CS_SHIFT;
+	if (cs < 0)
+		reg |= (cs + 32) << MX27_CSPICTRL_CS_SHIFT;
 
 	writel(reg, spi_imx->base + MXC_CSPICTRL);
 
 	return 0;
 }
 
-static int mx27_rx_available(struct spi_imx_data *spi_imx)
+static int __maybe_unused mx27_rx_available(struct spi_imx_data *spi_imx)
 {
 	return readl(spi_imx->base + MXC_CSPIINT) & MX27_INTREG_RR;
 }
 
+static void __maybe_unused spi_imx0_0_reset(struct spi_imx_data *spi_imx)
+{
+	writel(1, spi_imx->base + MXC_RESET);
+}
+
 #define MX1_INTREG_RR		(1 << 3)
 #define MX1_INTREG_TEEN		(1 << 8)
 #define MX1_INTREG_RREN		(1 << 11)
@@ -310,7 +480,7 @@
 #define MX1_CSPICTRL_MASTER	(1 << 10)
 #define MX1_CSPICTRL_DR_SHIFT	13
 
-static void mx1_intctrl(struct spi_imx_data *spi_imx, int enable)
+static void __maybe_unused mx1_intctrl(struct spi_imx_data *spi_imx, int enable)
 {
 	unsigned int val = 0;
 
@@ -322,7 +492,7 @@
 	writel(val, spi_imx->base + MXC_CSPIINT);
 }
 
-static void mx1_trigger(struct spi_imx_data *spi_imx)
+static void __maybe_unused mx1_trigger(struct spi_imx_data *spi_imx)
 {
 	unsigned int reg;
 
@@ -331,7 +501,7 @@
 	writel(reg, spi_imx->base + MXC_CSPICTRL);
 }
 
-static int mx1_config(struct spi_imx_data *spi_imx,
+static int __maybe_unused mx1_config(struct spi_imx_data *spi_imx,
 		struct spi_imx_config *config)
 {
 	unsigned int reg = MX1_CSPICTRL_ENABLE | MX1_CSPICTRL_MASTER;
@@ -350,11 +520,73 @@
 	return 0;
 }
 
-static int mx1_rx_available(struct spi_imx_data *spi_imx)
+static int __maybe_unused mx1_rx_available(struct spi_imx_data *spi_imx)
 {
 	return readl(spi_imx->base + MXC_CSPIINT) & MX1_INTREG_RR;
 }
 
+static void __maybe_unused mx1_reset(struct spi_imx_data *spi_imx)
+{
+	writel(1, spi_imx->base + MXC_RESET);
+}
+
+/*
+ * These version numbers are taken from the Freescale driver.  Unfortunately it
+ * doesn't support i.MX1, so this entry doesn't match the scheme. :-(
+ */
+static struct spi_imx_devtype_data spi_imx_devtype_data[] __devinitdata = {
+#ifdef CONFIG_SPI_IMX_VER_IMX1
+	[SPI_IMX_VER_IMX1] = {
+		.intctrl = mx1_intctrl,
+		.config = mx1_config,
+		.trigger = mx1_trigger,
+		.rx_available = mx1_rx_available,
+		.reset = mx1_reset,
+		.fifosize = 8,
+	},
+#endif
+#ifdef CONFIG_SPI_IMX_VER_0_0
+	[SPI_IMX_VER_0_0] = {
+		.intctrl = mx27_intctrl,
+		.config = mx27_config,
+		.trigger = mx27_trigger,
+		.rx_available = mx27_rx_available,
+		.reset = spi_imx0_0_reset,
+		.fifosize = 8,
+	},
+#endif
+#ifdef CONFIG_SPI_IMX_VER_0_4
+	[SPI_IMX_VER_0_4] = {
+		.intctrl = mx31_intctrl,
+		.config = spi_imx0_4_config,
+		.trigger = mx31_trigger,
+		.rx_available = mx31_rx_available,
+		.reset = spi_imx0_4_reset,
+		.fifosize = 8,
+	},
+#endif
+#ifdef CONFIG_SPI_IMX_VER_0_7
+	[SPI_IMX_VER_0_7] = {
+		.intctrl = mx31_intctrl,
+		.config = spi_imx0_7_config,
+		.trigger = mx31_trigger,
+		.rx_available = mx31_rx_available,
+		.reset = spi_imx0_4_reset,
+		.fifosize = 8,
+	},
+#endif
+#ifdef CONFIG_SPI_IMX_VER_2_3
+	[SPI_IMX_VER_2_3] = {
+		.intctrl = spi_imx2_3_intctrl,
+		.config = spi_imx2_3_config,
+		.trigger = spi_imx2_3_trigger,
+		.rx_available = spi_imx2_3_rx_available,
+		.reset = spi_imx2_3_reset,
+		.fifosize = 64,
+	},
+#endif
+};
+
 static void spi_imx_chipselect(struct spi_device *spi, int is_active)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
@@ -370,21 +602,21 @@
 
 static void spi_imx_push(struct spi_imx_data *spi_imx)
 {
-	while (spi_imx->txfifo < 8) {
+	while (spi_imx->txfifo < spi_imx->devtype_data.fifosize) {
 		if (!spi_imx->count)
 			break;
 		spi_imx->tx(spi_imx);
 		spi_imx->txfifo++;
 	}
 
-	spi_imx->trigger(spi_imx);
+	spi_imx->devtype_data.trigger(spi_imx);
 }
 
 static irqreturn_t spi_imx_isr(int irq, void *dev_id)
 {
 	struct spi_imx_data *spi_imx = dev_id;
 
-	while (spi_imx->rx_available(spi_imx)) {
+	while (spi_imx->devtype_data.rx_available(spi_imx)) {
 		spi_imx->rx(spi_imx);
 		spi_imx->txfifo--;
 	}
@@ -398,11 +630,12 @@
 		/* No data left to push, but still waiting for rx data,
 		 * enable receive data available interrupt.
 		 */
-		spi_imx->intctrl(spi_imx, MXC_INT_RR);
+		spi_imx->devtype_data.intctrl(
+				spi_imx, MXC_INT_RR);
 		return IRQ_HANDLED;
 	}
 
-	spi_imx->intctrl(spi_imx, 0);
+	spi_imx->devtype_data.intctrl(spi_imx, 0);
 	complete(&spi_imx->xfer_done);
 
 	return IRQ_HANDLED;
@@ -417,7 +650,7 @@
 	config.bpw = t ? t->bits_per_word : spi->bits_per_word;
 	config.speed_hz  = t ? t->speed_hz : spi->max_speed_hz;
 	config.mode = spi->mode;
-	config.cs = spi_imx->chipselect[spi->chip_select];
+	config.cs = spi->chip_select;
 
 	if (!config.speed_hz)
 		config.speed_hz = spi->max_speed_hz;
@@ -439,7 +672,7 @@
 	} else
 		BUG();
 
-	spi_imx->config(spi_imx, &config);
+	spi_imx->devtype_data.config(spi_imx, &config);
 
 	return 0;
 }
@@ -458,7 +691,7 @@
 
 	spi_imx_push(spi_imx);
 
-	spi_imx->intctrl(spi_imx, MXC_INT_TE);
+	spi_imx->devtype_data.intctrl(spi_imx, MXC_INT_TE);
 
 	wait_for_completion(&spi_imx->xfer_done);
 
@@ -485,6 +718,39 @@
 {
 }
 
+static struct platform_device_id spi_imx_devtype[] = {
+	{
+		.name = DRIVER_NAME,
+		.driver_data = SPI_IMX_VER_AUTODETECT,
+	}, {
+		.name = "imx1-cspi",
+		.driver_data = SPI_IMX_VER_IMX1,
+	}, {
+		.name = "imx21-cspi",
+		.driver_data = SPI_IMX_VER_0_0,
+	}, {
+		.name = "imx25-cspi",
+		.driver_data = SPI_IMX_VER_0_7,
+	}, {
+		.name = "imx27-cspi",
+		.driver_data = SPI_IMX_VER_0_0,
+	}, {
+		.name = "imx31-cspi",
+		.driver_data = SPI_IMX_VER_0_4,
+	}, {
+		.name = "imx35-cspi",
+		.driver_data = SPI_IMX_VER_0_7,
+	}, {
+		.name = "imx51-cspi",
+		.driver_data = SPI_IMX_VER_0_7,
+	}, {
+		.name = "imx51-ecspi",
+		.driver_data = SPI_IMX_VER_2_3,
+	}, {
+		/* sentinel */
+	}
+};
+
 static int __devinit spi_imx_probe(struct platform_device *pdev)
 {
 	struct spi_imx_master *mxc_platform_info;
@@ -536,6 +802,31 @@
 
 	init_completion(&spi_imx->xfer_done);
 
+	if (pdev->id_entry->driver_data == SPI_IMX_VER_AUTODETECT) {
+		if (cpu_is_mx25() || cpu_is_mx35())
+			spi_imx->devtype_data =
+				spi_imx_devtype_data[SPI_IMX_VER_0_7];
+		else if (cpu_is_mx25() || cpu_is_mx31() || cpu_is_mx35())
+			spi_imx->devtype_data =
+				spi_imx_devtype_data[SPI_IMX_VER_0_4];
+		else if (cpu_is_mx27() || cpu_is_mx21())
+			spi_imx->devtype_data =
+				spi_imx_devtype_data[SPI_IMX_VER_0_0];
+		else if (cpu_is_mx1())
+			spi_imx->devtype_data =
+				spi_imx_devtype_data[SPI_IMX_VER_IMX1];
+		else
+			BUG();
+	} else
+		spi_imx->devtype_data =
+			spi_imx_devtype_data[pdev->id_entry->driver_data];
+
+	if (!spi_imx->devtype_data.intctrl) {
+		dev_err(&pdev->dev, "no support for this device compiled in\n");
+		ret = -ENODEV;
+		goto out_gpio_free;
+	}
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(&pdev->dev, "can't get platform resource\n");
@@ -567,24 +858,6 @@
 		goto out_iounmap;
 	}
 
-	if (cpu_is_mx25() || cpu_is_mx31() || cpu_is_mx35()) {
-		spi_imx->intctrl = mx31_intctrl;
-		spi_imx->config = mx31_config;
-		spi_imx->trigger = mx31_trigger;
-		spi_imx->rx_available = mx31_rx_available;
-	} else  if (cpu_is_mx27() || cpu_is_mx21()) {
-		spi_imx->intctrl = mx27_intctrl;
-		spi_imx->config = mx27_config;
-		spi_imx->trigger = mx27_trigger;
-		spi_imx->rx_available = mx27_rx_available;
-	} else if (cpu_is_mx1()) {
-		spi_imx->intctrl = mx1_intctrl;
-		spi_imx->config = mx1_config;
-		spi_imx->trigger = mx1_trigger;
-		spi_imx->rx_available = mx1_rx_available;
-	} else
-		BUG();
-
 	spi_imx->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(spi_imx->clk)) {
 		dev_err(&pdev->dev, "unable to get clock\n");
@@ -595,15 +868,9 @@
 	clk_enable(spi_imx->clk);
 	spi_imx->spi_clk = clk_get_rate(spi_imx->clk);
 
-	if (cpu_is_mx1() || cpu_is_mx21() || cpu_is_mx27())
-		writel(1, spi_imx->base + MXC_RESET);
+	spi_imx->devtype_data.reset(spi_imx);
 
-	/* drain receive buffer */
-	if (cpu_is_mx25() || cpu_is_mx31() || cpu_is_mx35())
-		while (readl(spi_imx->base + MX3_CSPISTAT) & MX3_CSPISTAT_RR)
-			readl(spi_imx->base + MXC_CSPIRXDATA);
-
-	spi_imx->intctrl(spi_imx, 0);
+	spi_imx->devtype_data.intctrl(spi_imx, 0);
 
 	ret = spi_bitbang_start(&spi_imx->bitbang);
 	if (ret) {
@@ -668,6 +935,7 @@
 		   .name = DRIVER_NAME,
 		   .owner = THIS_MODULE,
 		   },
+	.id_table = spi_imx_devtype,
 	.probe = spi_imx_probe,
 	.remove = __devexit_p(spi_imx_remove),
 };
diff --git a/drivers/spi/spi_s3c64xx.c b/drivers/spi/spi_s3c64xx.c
index c3038da..795828b 100644
--- a/drivers/spi/spi_s3c64xx.c
+++ b/drivers/spi/spi_s3c64xx.c
@@ -261,15 +261,25 @@
 		chcfg |= S3C64XX_SPI_CH_TXCH_ON;
 		if (dma_mode) {
 			modecfg |= S3C64XX_SPI_MODE_TXDMA_ON;
-			s3c2410_dma_config(sdd->tx_dmach, 1);
+			s3c2410_dma_config(sdd->tx_dmach, sdd->cur_bpw / 8);
 			s3c2410_dma_enqueue(sdd->tx_dmach, (void *)sdd,
 						xfer->tx_dma, xfer->len);
 			s3c2410_dma_ctrl(sdd->tx_dmach, S3C2410_DMAOP_START);
 		} else {
-			unsigned char *buf = (unsigned char *) xfer->tx_buf;
-			int i = 0;
-			while (i < xfer->len)
-				writeb(buf[i++], regs + S3C64XX_SPI_TX_DATA);
+			switch (sdd->cur_bpw) {
+			case 32:
+				iowrite32_rep(regs + S3C64XX_SPI_TX_DATA,
+					xfer->tx_buf, xfer->len / 4);
+				break;
+			case 16:
+				iowrite16_rep(regs + S3C64XX_SPI_TX_DATA,
+					xfer->tx_buf, xfer->len / 2);
+				break;
+			default:
+				iowrite8_rep(regs + S3C64XX_SPI_TX_DATA,
+					xfer->tx_buf, xfer->len);
+				break;
+			}
 		}
 	}
 
@@ -286,7 +296,7 @@
 			writel(((xfer->len * 8 / sdd->cur_bpw) & 0xffff)
 					| S3C64XX_SPI_PACKET_CNT_EN,
 					regs + S3C64XX_SPI_PACKET_CNT);
-			s3c2410_dma_config(sdd->rx_dmach, 1);
+			s3c2410_dma_config(sdd->rx_dmach, sdd->cur_bpw / 8);
 			s3c2410_dma_enqueue(sdd->rx_dmach, (void *)sdd,
 						xfer->rx_dma, xfer->len);
 			s3c2410_dma_ctrl(sdd->rx_dmach, S3C2410_DMAOP_START);
@@ -366,20 +376,26 @@
 				return -EIO;
 		}
 	} else {
-		unsigned char *buf;
-		int i;
-
 		/* If it was only Tx */
 		if (xfer->rx_buf == NULL) {
 			sdd->state &= ~TXBUSY;
 			return 0;
 		}
 
-		i = 0;
-		buf = xfer->rx_buf;
-		while (i < xfer->len)
-			buf[i++] = readb(regs + S3C64XX_SPI_RX_DATA);
-
+		switch (sdd->cur_bpw) {
+		case 32:
+			ioread32_rep(regs + S3C64XX_SPI_RX_DATA,
+				xfer->rx_buf, xfer->len / 4);
+			break;
+		case 16:
+			ioread16_rep(regs + S3C64XX_SPI_RX_DATA,
+				xfer->rx_buf, xfer->len / 2);
+			break;
+		default:
+			ioread8_rep(regs + S3C64XX_SPI_RX_DATA,
+				xfer->rx_buf, xfer->len);
+			break;
+		}
 		sdd->state &= ~RXBUSY;
 	}
 
@@ -399,13 +415,18 @@
 
 static void s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd)
 {
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	void __iomem *regs = sdd->regs;
 	u32 val;
 
 	/* Disable Clock */
-	val = readl(regs + S3C64XX_SPI_CLK_CFG);
-	val &= ~S3C64XX_SPI_ENCLK_ENABLE;
-	writel(val, regs + S3C64XX_SPI_CLK_CFG);
+	if (sci->clk_from_cmu) {
+		clk_disable(sdd->src_clk);
+	} else {
+		val = readl(regs + S3C64XX_SPI_CLK_CFG);
+		val &= ~S3C64XX_SPI_ENCLK_ENABLE;
+		writel(val, regs + S3C64XX_SPI_CLK_CFG);
+	}
 
 	/* Set Polarity and Phase */
 	val = readl(regs + S3C64XX_SPI_CH_CFG);
@@ -429,29 +450,39 @@
 	switch (sdd->cur_bpw) {
 	case 32:
 		val |= S3C64XX_SPI_MODE_BUS_TSZ_WORD;
+		val |= S3C64XX_SPI_MODE_CH_TSZ_WORD;
 		break;
 	case 16:
 		val |= S3C64XX_SPI_MODE_BUS_TSZ_HALFWORD;
+		val |= S3C64XX_SPI_MODE_CH_TSZ_HALFWORD;
 		break;
 	default:
 		val |= S3C64XX_SPI_MODE_BUS_TSZ_BYTE;
+		val |= S3C64XX_SPI_MODE_CH_TSZ_BYTE;
 		break;
 	}
-	val |= S3C64XX_SPI_MODE_CH_TSZ_BYTE; /* Always 8bits wide */
 
 	writel(val, regs + S3C64XX_SPI_MODE_CFG);
 
-	/* Configure Clock */
-	val = readl(regs + S3C64XX_SPI_CLK_CFG);
-	val &= ~S3C64XX_SPI_PSR_MASK;
-	val |= ((clk_get_rate(sdd->src_clk) / sdd->cur_speed / 2 - 1)
-			& S3C64XX_SPI_PSR_MASK);
-	writel(val, regs + S3C64XX_SPI_CLK_CFG);
+	if (sci->clk_from_cmu) {
+		/* Configure Clock */
+		/* There is half-multiplier before the SPI */
+		clk_set_rate(sdd->src_clk, sdd->cur_speed * 2);
+		/* Enable Clock */
+		clk_enable(sdd->src_clk);
+	} else {
+		/* Configure Clock */
+		val = readl(regs + S3C64XX_SPI_CLK_CFG);
+		val &= ~S3C64XX_SPI_PSR_MASK;
+		val |= ((clk_get_rate(sdd->src_clk) / sdd->cur_speed / 2 - 1)
+				& S3C64XX_SPI_PSR_MASK);
+		writel(val, regs + S3C64XX_SPI_CLK_CFG);
 
-	/* Enable Clock */
-	val = readl(regs + S3C64XX_SPI_CLK_CFG);
-	val |= S3C64XX_SPI_ENCLK_ENABLE;
-	writel(val, regs + S3C64XX_SPI_CLK_CFG);
+		/* Enable Clock */
+		val = readl(regs + S3C64XX_SPI_CLK_CFG);
+		val |= S3C64XX_SPI_ENCLK_ENABLE;
+		writel(val, regs + S3C64XX_SPI_CLK_CFG);
+	}
 }
 
 static void s3c64xx_spi_dma_rxcb(struct s3c2410_dma_chan *chan, void *buf_id,
@@ -499,6 +530,7 @@
 static int s3c64xx_spi_map_mssg(struct s3c64xx_spi_driver_data *sdd,
 						struct spi_message *msg)
 {
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	struct device *dev = &sdd->pdev->dev;
 	struct spi_transfer *xfer;
 
@@ -514,6 +546,9 @@
 	/* Map until end or first fail */
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 
+		if (xfer->len <= ((sci->fifo_lvl_mask >> 1) + 1))
+			continue;
+
 		if (xfer->tx_buf != NULL) {
 			xfer->tx_dma = dma_map_single(dev,
 					(void *)xfer->tx_buf, xfer->len,
@@ -545,6 +580,7 @@
 static void s3c64xx_spi_unmap_mssg(struct s3c64xx_spi_driver_data *sdd,
 						struct spi_message *msg)
 {
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	struct device *dev = &sdd->pdev->dev;
 	struct spi_transfer *xfer;
 
@@ -553,6 +589,9 @@
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 
+		if (xfer->len <= ((sci->fifo_lvl_mask >> 1) + 1))
+			continue;
+
 		if (xfer->rx_buf != NULL
 				&& xfer->rx_dma != XFER_DMAADDR_INVALID)
 			dma_unmap_single(dev, xfer->rx_dma,
@@ -608,6 +647,14 @@
 		bpw = xfer->bits_per_word ? : spi->bits_per_word;
 		speed = xfer->speed_hz ? : spi->max_speed_hz;
 
+		if (xfer->len % (bpw / 8)) {
+			dev_err(&spi->dev,
+				"Xfer length(%u) not a multiple of word size(%u)\n",
+				xfer->len, bpw / 8);
+			status = -EIO;
+			goto out;
+		}
+
 		if (bpw != sdd->cur_bpw || speed != sdd->cur_speed) {
 			sdd->cur_bpw = bpw;
 			sdd->cur_speed = speed;
@@ -798,7 +845,6 @@
 	struct s3c64xx_spi_driver_data *sdd;
 	struct s3c64xx_spi_info *sci;
 	struct spi_message *msg;
-	u32 psr, speed;
 	unsigned long flags;
 	int err = 0;
 
@@ -841,31 +887,36 @@
 	}
 
 	/* Check if we can provide the requested rate */
-	speed = clk_get_rate(sdd->src_clk) / 2 / (0 + 1); /* Max possible */
+	if (!sci->clk_from_cmu) {
+		u32 psr, speed;
 
-	if (spi->max_speed_hz > speed)
-		spi->max_speed_hz = speed;
+		/* Max possible */
+		speed = clk_get_rate(sdd->src_clk) / 2 / (0 + 1);
 
-	psr = clk_get_rate(sdd->src_clk) / 2 / spi->max_speed_hz - 1;
-	psr &= S3C64XX_SPI_PSR_MASK;
-	if (psr == S3C64XX_SPI_PSR_MASK)
-		psr--;
+		if (spi->max_speed_hz > speed)
+			spi->max_speed_hz = speed;
 
-	speed = clk_get_rate(sdd->src_clk) / 2 / (psr + 1);
-	if (spi->max_speed_hz < speed) {
-		if (psr+1 < S3C64XX_SPI_PSR_MASK) {
-			psr++;
-		} else {
-			err = -EINVAL;
-			goto setup_exit;
+		psr = clk_get_rate(sdd->src_clk) / 2 / spi->max_speed_hz - 1;
+		psr &= S3C64XX_SPI_PSR_MASK;
+		if (psr == S3C64XX_SPI_PSR_MASK)
+			psr--;
+
+		speed = clk_get_rate(sdd->src_clk) / 2 / (psr + 1);
+		if (spi->max_speed_hz < speed) {
+			if (psr+1 < S3C64XX_SPI_PSR_MASK) {
+				psr++;
+			} else {
+				err = -EINVAL;
+				goto setup_exit;
+			}
 		}
-	}
 
-	speed = clk_get_rate(sdd->src_clk) / 2 / (psr + 1);
-	if (spi->max_speed_hz >= speed)
-		spi->max_speed_hz = speed;
-	else
-		err = -EINVAL;
+		speed = clk_get_rate(sdd->src_clk) / 2 / (psr + 1);
+		if (spi->max_speed_hz >= speed)
+			spi->max_speed_hz = speed;
+		else
+			err = -EINVAL;
+	}
 
 setup_exit:
 
@@ -888,7 +939,8 @@
 	/* Disable Interrupts - we use Polling if not DMA mode */
 	writel(0, regs + S3C64XX_SPI_INT_EN);
 
-	writel(sci->src_clk_nr << S3C64XX_SPI_CLKSEL_SRCSHFT,
+	if (!sci->clk_from_cmu)
+		writel(sci->src_clk_nr << S3C64XX_SPI_CLKSEL_SRCSHFT,
 				regs + S3C64XX_SPI_CLK_CFG);
 	writel(0, regs + S3C64XX_SPI_MODE_CFG);
 	writel(0, regs + S3C64XX_SPI_PACKET_CNT);
diff --git a/drivers/spi/spi_topcliff_pch.c b/drivers/spi/spi_topcliff_pch.c
new file mode 100644
index 0000000..58e187f
--- /dev/null
+++ b/drivers/spi/spi_topcliff_pch.c
@@ -0,0 +1,1303 @@
+/*
+ * SPI bus driver for the Topcliff PCH used by Intel SoCs
+ *
+ * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307, USA.
+ */
+
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/wait.h>
+#include <linux/spi/spi.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/spi/spidev.h>
+#include <linux/module.h>
+#include <linux/device.h>
+
+/* Register offsets */
+#define PCH_SPCR		0x00	/* SPI control register */
+#define PCH_SPBRR		0x04	/* SPI baud rate register */
+#define PCH_SPSR		0x08	/* SPI status register */
+#define PCH_SPDWR		0x0C	/* SPI write data register */
+#define PCH_SPDRR		0x10	/* SPI read data register */
+#define PCH_SSNXCR		0x18	/* SSN Expand Control Register */
+#define PCH_SRST		0x1C	/* SPI reset register */
+
+#define PCH_SPSR_TFD		0x000007C0
+#define PCH_SPSR_RFD		0x0000F800
+
+#define PCH_READABLE(x)		(((x) & PCH_SPSR_RFD)>>11)
+#define PCH_WRITABLE(x)		(((x) & PCH_SPSR_TFD)>>6)
+
+#define PCH_RX_THOLD		7
+#define PCH_RX_THOLD_MAX	15
+
+#define PCH_MAX_BAUDRATE	5000000
+#define PCH_MAX_FIFO_DEPTH	16
+
+#define STATUS_RUNNING		1
+#define STATUS_EXITING		2
+#define PCH_SLEEP_TIME		10
+
+#define PCH_ADDRESS_SIZE	0x20
+
+#define SSN_LOW			0x02U
+#define SSN_NO_CONTROL		0x00U
+#define PCH_MAX_CS		0xFF
+#define PCI_DEVICE_ID_GE_SPI	0x8816
+
+#define SPCR_SPE_BIT		(1 << 0)
+#define SPCR_MSTR_BIT		(1 << 1)
+#define SPCR_LSBF_BIT		(1 << 4)
+#define SPCR_CPHA_BIT		(1 << 5)
+#define SPCR_CPOL_BIT		(1 << 6)
+#define SPCR_TFIE_BIT		(1 << 8)
+#define SPCR_RFIE_BIT		(1 << 9)
+#define SPCR_FIE_BIT		(1 << 10)
+#define SPCR_ORIE_BIT		(1 << 11)
+#define SPCR_MDFIE_BIT		(1 << 12)
+#define SPCR_FICLR_BIT		(1 << 24)
+#define SPSR_TFI_BIT		(1 << 0)
+#define SPSR_RFI_BIT		(1 << 1)
+#define SPSR_FI_BIT		(1 << 2)
+#define SPBRR_SIZE_BIT		(1 << 10)
+
+#define PCH_ALL			(SPCR_TFIE_BIT|SPCR_RFIE_BIT|SPCR_FIE_BIT|SPCR_ORIE_BIT|SPCR_MDFIE_BIT)
+
+#define SPCR_RFIC_FIELD		20
+#define SPCR_TFIC_FIELD		16
+
+#define SPSR_INT_BITS		0x1F
+#define MASK_SPBRR_SPBR_BITS	(~((1 << 10) - 1))
+#define MASK_RFIC_SPCR_BITS	(~(0xf << 20))
+#define MASK_TFIC_SPCR_BITS	(~(0xf000f << 12))
+
+#define PCH_CLOCK_HZ		50000000
+#define PCH_MAX_SPBR		1023
+
+
+/**
+ * struct pch_spi_data - Holds the SPI channel specific details
+ * @io_remap_addr:		The remapped PCI base address
+ * @master:			Pointer to the SPI master structure
+ * @work:			Reference to work queue handler
+ * @wk:				Workqueue for carrying out execution of the
+ *				requests
+ * @wait:			Wait queue for waking up upon receiving an
+ *				interrupt.
+ * @transfer_complete:		Status of SPI Transfer
+ * @bcurrent_msg_processing:	Status flag for message processing
+ * @lock:			Lock for protecting this structure
+ * @queue:			SPI Message queue
+ * @status:			Status of the SPI driver
+ * @bpw_len:			Length of data to be transferred in bits per
+ *				word
+ * @transfer_active:		Flag showing active transfer
+ * @tx_index:			Transmit data count; for bookkeeping during
+ *				transfer
+ * @rx_index:			Receive data count; for bookkeeping during
+ *				transfer
+ * @tx_buff:			Buffer for data to be transmitted
+ * @rx_index:			Buffer for Received data
+ * @n_curnt_chip:		The chip number that this SPI driver currently
+ *				operates on
+ * @current_chip:		Reference to the current chip that this SPI
+ *				driver currently operates on
+ * @current_msg:		The current message that this SPI driver is
+ *				handling
+ * @cur_trans:			The current transfer that this SPI driver is
+ *				handling
+ * @board_dat:			Reference to the SPI device data structure
+ */
+struct pch_spi_data {
+	void __iomem *io_remap_addr;
+	struct spi_master *master;
+	struct work_struct work;
+	struct workqueue_struct *wk;
+	wait_queue_head_t wait;
+	u8 transfer_complete;
+	u8 bcurrent_msg_processing;
+	spinlock_t lock;
+	struct list_head queue;
+	u8 status;
+	u32 bpw_len;
+	u8 transfer_active;
+	u32 tx_index;
+	u32 rx_index;
+	u16 *pkt_tx_buff;
+	u16 *pkt_rx_buff;
+	u8 n_curnt_chip;
+	struct spi_device *current_chip;
+	struct spi_message *current_msg;
+	struct spi_transfer *cur_trans;
+	struct pch_spi_board_data *board_dat;
+};
+
+/**
+ * struct pch_spi_board_data - Holds the SPI device specific details
+ * @pdev:		Pointer to the PCI device
+ * @irq_reg_sts:	Status of IRQ registration
+ * @pci_req_sts:	Status of pci_request_regions
+ * @suspend_sts:	Status of suspend
+ * @data:		Pointer to SPI channel data structure
+ */
+struct pch_spi_board_data {
+	struct pci_dev *pdev;
+	u8 irq_reg_sts;
+	u8 pci_req_sts;
+	u8 suspend_sts;
+	struct pch_spi_data *data;
+};
+
+static struct pci_device_id pch_spi_pcidev_id[] = {
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_GE_SPI)},
+	{0,}
+};
+
+/**
+ * pch_spi_writereg() - Performs  register writes
+ * @master:	Pointer to struct spi_master.
+ * @idx:	Register offset.
+ * @val:	Value to be written to register.
+ */
+static inline void pch_spi_writereg(struct spi_master *master, int idx, u32 val)
+{
+	struct pch_spi_data *data = spi_master_get_devdata(master);
+	iowrite32(val, (data->io_remap_addr + idx));
+}
+
+/**
+ * pch_spi_readreg() - Performs register reads
+ * @master:	Pointer to struct spi_master.
+ * @idx:	Register offset.
+ */
+static inline u32 pch_spi_readreg(struct spi_master *master, int idx)
+{
+	struct pch_spi_data *data = spi_master_get_devdata(master);
+	return ioread32(data->io_remap_addr + idx);
+}
+
+static inline void pch_spi_setclr_reg(struct spi_master *master, int idx,
+				      u32 set, u32 clr)
+{
+	u32 tmp = pch_spi_readreg(master, idx);
+	tmp = (tmp & ~clr) | set;
+	pch_spi_writereg(master, idx, tmp);
+}
+
+static void pch_spi_set_master_mode(struct spi_master *master)
+{
+	pch_spi_setclr_reg(master, PCH_SPCR, SPCR_MSTR_BIT, 0);
+}
+
+/**
+ * pch_spi_clear_fifo() - Clears the Transmit and Receive FIFOs
+ * @master:	Pointer to struct spi_master.
+ */
+static void pch_spi_clear_fifo(struct spi_master *master)
+{
+	pch_spi_setclr_reg(master, PCH_SPCR, SPCR_FICLR_BIT, 0);
+	pch_spi_setclr_reg(master, PCH_SPCR, 0, SPCR_FICLR_BIT);
+}
+
+static void pch_spi_handler_sub(struct pch_spi_data *data, u32 reg_spsr_val,
+				void __iomem *io_remap_addr)
+{
+	u32 n_read, tx_index, rx_index, bpw_len;
+	u16 *pkt_rx_buffer, *pkt_tx_buff;
+	int read_cnt;
+	u32 reg_spcr_val;
+	void __iomem *spsr;
+	void __iomem *spdrr;
+	void __iomem *spdwr;
+
+	spsr = io_remap_addr + PCH_SPSR;
+	iowrite32(reg_spsr_val, spsr);
+
+	if (data->transfer_active) {
+		rx_index = data->rx_index;
+		tx_index = data->tx_index;
+		bpw_len = data->bpw_len;
+		pkt_rx_buffer = data->pkt_rx_buff;
+		pkt_tx_buff = data->pkt_tx_buff;
+
+		spdrr = io_remap_addr + PCH_SPDRR;
+		spdwr = io_remap_addr + PCH_SPDWR;
+
+		n_read = PCH_READABLE(reg_spsr_val);
+
+		for (read_cnt = 0; (read_cnt < n_read); read_cnt++) {
+			pkt_rx_buffer[rx_index++] = ioread32(spdrr);
+			if (tx_index < bpw_len)
+				iowrite32(pkt_tx_buff[tx_index++], spdwr);
+		}
+
+		/* disable RFI if not needed */
+		if ((bpw_len - rx_index) <= PCH_MAX_FIFO_DEPTH) {
+			reg_spcr_val = ioread32(io_remap_addr + PCH_SPCR);
+			reg_spcr_val &= ~SPCR_RFIE_BIT; /* disable RFI */
+
+			/* reset rx threshold */
+			reg_spcr_val &= MASK_RFIC_SPCR_BITS;
+			reg_spcr_val |= (PCH_RX_THOLD_MAX << SPCR_RFIC_FIELD);
+			iowrite32(((reg_spcr_val) &= (~(SPCR_RFIE_BIT))),
+				 (io_remap_addr + PCH_SPCR));
+		}
+
+		/* update counts */
+		data->tx_index = tx_index;
+		data->rx_index = rx_index;
+
+	}
+
+	/* if transfer complete interrupt */
+	if (reg_spsr_val & SPSR_FI_BIT) {
+		/* disable FI & RFI interrupts */
+		pch_spi_setclr_reg(data->master, PCH_SPCR, 0,
+				   SPCR_FIE_BIT | SPCR_TFIE_BIT);
+
+		/* transfer is completed;inform pch_spi_process_messages */
+		data->transfer_complete = true;
+		wake_up(&data->wait);
+	}
+}
+
+/**
+ * pch_spi_handler() - Interrupt handler
+ * @irq:	The interrupt number.
+ * @dev_id:	Pointer to struct pch_spi_board_data.
+ */
+static irqreturn_t pch_spi_handler(int irq, void *dev_id)
+{
+	u32 reg_spsr_val;
+	struct pch_spi_data *data;
+	void __iomem *spsr;
+	void __iomem *io_remap_addr;
+	irqreturn_t ret = IRQ_NONE;
+	struct pch_spi_board_data *board_dat = dev_id;
+
+	if (board_dat->suspend_sts) {
+		dev_dbg(&board_dat->pdev->dev,
+			"%s returning due to suspend\n", __func__);
+		return IRQ_NONE;
+	}
+
+	data = board_dat->data;
+	io_remap_addr = data->io_remap_addr;
+	spsr = io_remap_addr + PCH_SPSR;
+
+	reg_spsr_val = ioread32(spsr);
+
+	/* Check if the interrupt is for SPI device */
+	if (reg_spsr_val & (SPSR_FI_BIT | SPSR_RFI_BIT)) {
+		pch_spi_handler_sub(data, reg_spsr_val, io_remap_addr);
+		ret = IRQ_HANDLED;
+	}
+
+	dev_dbg(&board_dat->pdev->dev, "%s EXIT return value=%d\n",
+		__func__, ret);
+
+	return ret;
+}
+
+/**
+ * pch_spi_set_baud_rate() - Sets SPBR field in SPBRR
+ * @master:	Pointer to struct spi_master.
+ * @speed_hz:	Baud rate.
+ */
+static void pch_spi_set_baud_rate(struct spi_master *master, u32 speed_hz)
+{
+	u32 n_spbr = PCH_CLOCK_HZ / (speed_hz * 2);
+
+	/* if baud rate is less than we can support limit it */
+	if (n_spbr > PCH_MAX_SPBR)
+		n_spbr = PCH_MAX_SPBR;
+
+	pch_spi_setclr_reg(master, PCH_SPBRR, n_spbr, ~MASK_SPBRR_SPBR_BITS);
+}
+
+/**
+ * pch_spi_set_bits_per_word() - Sets SIZE field in SPBRR
+ * @master:		Pointer to struct spi_master.
+ * @bits_per_word:	Bits per word for SPI transfer.
+ */
+static void pch_spi_set_bits_per_word(struct spi_master *master,
+				      u8 bits_per_word)
+{
+	if (bits_per_word == 8)
+		pch_spi_setclr_reg(master, PCH_SPBRR, 0, SPBRR_SIZE_BIT);
+	else
+		pch_spi_setclr_reg(master, PCH_SPBRR, SPBRR_SIZE_BIT, 0);
+}
+
+/**
+ * pch_spi_setup_transfer() - Configures the PCH SPI hardware for transfer
+ * @spi:	Pointer to struct spi_device.
+ */
+static void pch_spi_setup_transfer(struct spi_device *spi)
+{
+	u32 flags = 0;
+
+	dev_dbg(&spi->dev, "%s SPBRR content =%x setting baud rate=%d\n",
+		__func__, pch_spi_readreg(spi->master, PCH_SPBRR),
+		spi->max_speed_hz);
+	pch_spi_set_baud_rate(spi->master, spi->max_speed_hz);
+
+	/* set bits per word */
+	pch_spi_set_bits_per_word(spi->master, spi->bits_per_word);
+
+	if (!(spi->mode & SPI_LSB_FIRST))
+		flags |= SPCR_LSBF_BIT;
+	if (spi->mode & SPI_CPOL)
+		flags |= SPCR_CPOL_BIT;
+	if (spi->mode & SPI_CPHA)
+		flags |= SPCR_CPHA_BIT;
+	pch_spi_setclr_reg(spi->master, PCH_SPCR, flags,
+			   (SPCR_LSBF_BIT | SPCR_CPOL_BIT | SPCR_CPHA_BIT));
+
+	/* Clear the FIFO by toggling  FICLR to 1 and back to 0 */
+	pch_spi_clear_fifo(spi->master);
+}
+
+/**
+ * pch_spi_reset() - Clears SPI registers
+ * @master:	Pointer to struct spi_master.
+ */
+static void pch_spi_reset(struct spi_master *master)
+{
+	/* write 1 to reset SPI */
+	pch_spi_writereg(master, PCH_SRST, 0x1);
+
+	/* clear reset */
+	pch_spi_writereg(master, PCH_SRST, 0x0);
+}
+
+static int pch_spi_setup(struct spi_device *pspi)
+{
+	/* check bits per word */
+	if (pspi->bits_per_word == 0) {
+		pspi->bits_per_word = 8;
+		dev_dbg(&pspi->dev, "%s 8 bits per word\n", __func__);
+	}
+
+	if ((pspi->bits_per_word != 8) && (pspi->bits_per_word != 16)) {
+		dev_err(&pspi->dev, "%s Invalid bits per word\n", __func__);
+		return -EINVAL;
+	}
+
+	/* Check baud rate setting */
+	/* if baud rate of chip is greater than
+	   max we can support,return error */
+	if ((pspi->max_speed_hz) > PCH_MAX_BAUDRATE)
+		pspi->max_speed_hz = PCH_MAX_BAUDRATE;
+
+	dev_dbg(&pspi->dev, "%s MODE = %x\n", __func__,
+		(pspi->mode) & (SPI_CPOL | SPI_CPHA));
+
+	return 0;
+}
+
+static int pch_spi_transfer(struct spi_device *pspi, struct spi_message *pmsg)
+{
+
+	struct spi_transfer *transfer;
+	struct pch_spi_data *data = spi_master_get_devdata(pspi->master);
+	int retval;
+	unsigned long flags;
+
+	/* validate spi message and baud rate */
+	if (unlikely(list_empty(&pmsg->transfers) == 1)) {
+		dev_err(&pspi->dev, "%s list empty\n", __func__);
+		retval = -EINVAL;
+		goto err_out;
+	}
+
+	if (unlikely(pspi->max_speed_hz == 0)) {
+		dev_err(&pspi->dev, "%s pch_spi_tranfer maxspeed=%d\n",
+			__func__, pspi->max_speed_hz);
+		retval = -EINVAL;
+		goto err_out;
+	}
+
+	dev_dbg(&pspi->dev, "%s Transfer List not empty. "
+		"Transfer Speed is set.\n", __func__);
+
+	/* validate Tx/Rx buffers and Transfer length */
+	list_for_each_entry(transfer, &pmsg->transfers, transfer_list) {
+		if (!transfer->tx_buf && !transfer->rx_buf) {
+			dev_err(&pspi->dev,
+				"%s Tx and Rx buffer NULL\n", __func__);
+			retval = -EINVAL;
+			goto err_out;
+		}
+
+		if (!transfer->len) {
+			dev_err(&pspi->dev, "%s Transfer length invalid\n",
+				__func__);
+			retval = -EINVAL;
+			goto err_out;
+		}
+
+		dev_dbg(&pspi->dev, "%s Tx/Rx buffer valid. Transfer length"
+			" valid\n", __func__);
+
+		/* if baud rate hs been specified validate the same */
+		if (transfer->speed_hz > PCH_MAX_BAUDRATE)
+			transfer->speed_hz = PCH_MAX_BAUDRATE;
+
+		/* if bits per word has been specified validate the same */
+		if (transfer->bits_per_word) {
+			if ((transfer->bits_per_word != 8)
+			    && (transfer->bits_per_word != 16)) {
+				retval = -EINVAL;
+				dev_err(&pspi->dev,
+					"%s Invalid bits per word\n", __func__);
+				goto err_out;
+			}
+		}
+	}
+
+	spin_lock_irqsave(&data->lock, flags);
+
+	/* We won't process any messages if we have been asked to terminate */
+	if (data->status == STATUS_EXITING) {
+		dev_err(&pspi->dev, "%s status = STATUS_EXITING.\n", __func__);
+		retval = -ESHUTDOWN;
+		goto err_return_spinlock;
+	}
+
+	/* If suspended ,return -EINVAL */
+	if (data->board_dat->suspend_sts) {
+		dev_err(&pspi->dev, "%s suspend; returning EINVAL\n", __func__);
+		retval = -EINVAL;
+		goto err_return_spinlock;
+	}
+
+	/* set status of message */
+	pmsg->actual_length = 0;
+	dev_dbg(&pspi->dev, "%s - pmsg->status =%d\n", __func__, pmsg->status);
+
+	pmsg->status = -EINPROGRESS;
+
+	/* add message to queue */
+	list_add_tail(&pmsg->queue, &data->queue);
+	dev_dbg(&pspi->dev, "%s - Invoked list_add_tail\n", __func__);
+
+	/* schedule work queue to run */
+	queue_work(data->wk, &data->work);
+	dev_dbg(&pspi->dev, "%s - Invoked queue work\n", __func__);
+
+	retval = 0;
+
+err_return_spinlock:
+	spin_unlock_irqrestore(&data->lock, flags);
+err_out:
+	dev_dbg(&pspi->dev, "%s RETURN=%d\n", __func__, retval);
+	return retval;
+}
+
+static inline void pch_spi_select_chip(struct pch_spi_data *data,
+				       struct spi_device *pspi)
+{
+	if (data->current_chip != NULL) {
+		if (pspi->chip_select != data->n_curnt_chip) {
+			dev_dbg(&pspi->dev, "%s : different slave\n", __func__);
+			data->current_chip = NULL;
+		}
+	}
+
+	data->current_chip = pspi;
+
+	data->n_curnt_chip = data->current_chip->chip_select;
+
+	dev_dbg(&pspi->dev, "%s :Invoking pch_spi_setup_transfer\n", __func__);
+	pch_spi_setup_transfer(pspi);
+}
+
+static void pch_spi_set_tx(struct pch_spi_data *data, int *bpw,
+			   struct spi_message **ppmsg)
+{
+	int size;
+	u32 n_writes;
+	int j;
+	struct spi_message *pmsg;
+	const u8 *tx_buf;
+	const u16 *tx_sbuf;
+
+	pmsg = *ppmsg;
+
+	/* set baud rate if needed */
+	if (data->cur_trans->speed_hz) {
+		dev_dbg(&data->master->dev, "%s:setting baud rate\n", __func__);
+		pch_spi_set_baud_rate(data->master, data->cur_trans->speed_hz);
+	}
+
+	/* set bits per word if needed */
+	if (data->cur_trans->bits_per_word &&
+	    (data->current_msg->spi->bits_per_word != data->cur_trans->bits_per_word)) {
+		dev_dbg(&data->master->dev, "%s:set bits per word\n", __func__);
+		pch_spi_set_bits_per_word(data->master,
+					  data->cur_trans->bits_per_word);
+		*bpw = data->cur_trans->bits_per_word;
+	} else {
+		*bpw = data->current_msg->spi->bits_per_word;
+	}
+
+	/* reset Tx/Rx index */
+	data->tx_index = 0;
+	data->rx_index = 0;
+
+	data->bpw_len = data->cur_trans->len / (*bpw / 8);
+
+	/* find alloc size */
+	size = data->cur_trans->len * sizeof(*data->pkt_tx_buff);
+
+	/* allocate memory for pkt_tx_buff & pkt_rx_buffer */
+	data->pkt_tx_buff = kzalloc(size, GFP_KERNEL);
+	if (data->pkt_tx_buff != NULL) {
+		data->pkt_rx_buff = kzalloc(size, GFP_KERNEL);
+		if (!data->pkt_rx_buff)
+			kfree(data->pkt_tx_buff);
+	}
+
+	if (!data->pkt_rx_buff) {
+		/* flush queue and set status of all transfers to -ENOMEM */
+		dev_err(&data->master->dev, "%s :kzalloc failed\n", __func__);
+		list_for_each_entry(pmsg, data->queue.next, queue) {
+			pmsg->status = -ENOMEM;
+
+			if (pmsg->complete != 0)
+				pmsg->complete(pmsg->context);
+
+			/* delete from queue */
+			list_del_init(&pmsg->queue);
+		}
+		return;
+	}
+
+	/* copy Tx Data */
+	if (data->cur_trans->tx_buf != NULL) {
+		if (*bpw == 8) {
+			tx_buf = data->cur_trans->tx_buf;
+			for (j = 0; j < data->bpw_len; j++)
+				data->pkt_tx_buff[j] = *tx_buf++;
+		} else {
+			tx_sbuf = data->cur_trans->tx_buf;
+			for (j = 0; j < data->bpw_len; j++)
+				data->pkt_tx_buff[j] = *tx_sbuf++;
+		}
+	}
+
+	/* if len greater than PCH_MAX_FIFO_DEPTH, write 16,else len bytes */
+	n_writes = data->bpw_len;
+	if (n_writes > PCH_MAX_FIFO_DEPTH)
+		n_writes = PCH_MAX_FIFO_DEPTH;
+
+	dev_dbg(&data->master->dev, "\n%s:Pulling down SSN low - writing "
+		"0x2 to SSNXCR\n", __func__);
+	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_LOW);
+
+	for (j = 0; j < n_writes; j++)
+		pch_spi_writereg(data->master, PCH_SPDWR, data->pkt_tx_buff[j]);
+
+	/* update tx_index */
+	data->tx_index = j;
+
+	/* reset transfer complete flag */
+	data->transfer_complete = false;
+	data->transfer_active = true;
+}
+
+
+static void pch_spi_nomore_transfer(struct pch_spi_data *data,
+						struct spi_message *pmsg)
+{
+	dev_dbg(&data->master->dev, "%s called\n", __func__);
+	/* Invoke complete callback
+	 * [To the spi core..indicating end of transfer] */
+	data->current_msg->status = 0;
+
+	if (data->current_msg->complete != 0) {
+		dev_dbg(&data->master->dev,
+			"%s:Invoking callback of SPI core\n", __func__);
+		data->current_msg->complete(data->current_msg->context);
+	}
+
+	/* update status in global variable */
+	data->bcurrent_msg_processing = false;
+
+	dev_dbg(&data->master->dev,
+		"%s:data->bcurrent_msg_processing = false\n", __func__);
+
+	data->current_msg = NULL;
+	data->cur_trans = NULL;
+
+	/* check if we have items in list and not suspending
+	 * return 1 if list empty */
+	if ((list_empty(&data->queue) == 0) &&
+	    (!data->board_dat->suspend_sts) &&
+	    (data->status != STATUS_EXITING)) {
+		/* We have some more work to do (either there is more tranint
+		 * bpw;sfer requests in the current message or there are
+		 *more messages)
+		 */
+		dev_dbg(&data->master->dev, "%s:Invoke queue_work\n", __func__);
+		queue_work(data->wk, &data->work);
+	} else if (data->board_dat->suspend_sts ||
+		   data->status == STATUS_EXITING) {
+		dev_dbg(&data->master->dev,
+			"%s suspend/remove initiated, flushing queue\n",
+			__func__);
+		list_for_each_entry(pmsg, data->queue.next, queue) {
+			pmsg->status = -EIO;
+
+			if (pmsg->complete)
+				pmsg->complete(pmsg->context);
+
+			/* delete from queue */
+			list_del_init(&pmsg->queue);
+		}
+	}
+}
+
+static void pch_spi_set_ir(struct pch_spi_data *data)
+{
+	/* enable interrupts */
+	if ((data->bpw_len) > PCH_MAX_FIFO_DEPTH) {
+		/* set receive threhold to PCH_RX_THOLD */
+		pch_spi_setclr_reg(data->master, PCH_SPCR,
+				   PCH_RX_THOLD << SPCR_TFIC_FIELD,
+				   ~MASK_TFIC_SPCR_BITS);
+		/* enable FI and RFI interrupts */
+		pch_spi_setclr_reg(data->master, PCH_SPCR,
+				   SPCR_RFIE_BIT | SPCR_TFIE_BIT, 0);
+	} else {
+		/* set receive threhold to maximum */
+		pch_spi_setclr_reg(data->master, PCH_SPCR,
+				   PCH_RX_THOLD_MAX << SPCR_TFIC_FIELD,
+				   ~MASK_TFIC_SPCR_BITS);
+		/* enable FI interrupt */
+		pch_spi_setclr_reg(data->master, PCH_SPCR, SPCR_FIE_BIT, 0);
+	}
+
+	dev_dbg(&data->master->dev,
+		"%s:invoking pch_spi_set_enable to enable SPI\n", __func__);
+
+	/* SPI set enable */
+	pch_spi_setclr_reg(data->current_chip->master, PCH_SPCR, SPCR_SPE_BIT, 0);
+
+	/* Wait until the transfer completes; go to sleep after
+				 initiating the transfer. */
+	dev_dbg(&data->master->dev,
+		"%s:waiting for transfer to get over\n", __func__);
+
+	wait_event_interruptible(data->wait, data->transfer_complete);
+
+	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_NO_CONTROL);
+	dev_dbg(&data->master->dev,
+		"%s:no more control over SSN-writing 0 to SSNXCR.", __func__);
+
+	data->transfer_active = false;
+	dev_dbg(&data->master->dev,
+		"%s set data->transfer_active = false\n", __func__);
+
+	/* clear all interrupts */
+	pch_spi_writereg(data->master, PCH_SPSR,
+			 pch_spi_readreg(data->master, PCH_SPSR));
+	/* disable interrupts */
+	pch_spi_setclr_reg(data->master, PCH_SPCR, 0, PCH_ALL);
+}
+
+static void pch_spi_copy_rx_data(struct pch_spi_data *data, int bpw)
+{
+	int j;
+	u8 *rx_buf;
+	u16 *rx_sbuf;
+
+	/* copy Rx Data */
+	if (!data->cur_trans->rx_buf)
+		return;
+
+	if (bpw == 8) {
+		rx_buf = data->cur_trans->rx_buf;
+		for (j = 0; j < data->bpw_len; j++)
+			*rx_buf++ = data->pkt_rx_buff[j] & 0xFF;
+	} else {
+		rx_sbuf = data->cur_trans->rx_buf;
+		for (j = 0; j < data->bpw_len; j++)
+			*rx_sbuf++ = data->pkt_rx_buff[j];
+	}
+}
+
+
+static void pch_spi_process_messages(struct work_struct *pwork)
+{
+	struct spi_message *pmsg;
+	struct pch_spi_data *data;
+	int bpw;
+
+	data = container_of(pwork, struct pch_spi_data, work);
+	dev_dbg(&data->master->dev, "%s data initialized\n", __func__);
+
+	spin_lock(&data->lock);
+
+	/* check if suspend has been initiated;if yes flush queue */
+	if (data->board_dat->suspend_sts || (data->status == STATUS_EXITING)) {
+		dev_dbg(&data->master->dev,
+			"%s suspend/remove initiated,flushing queue\n",
+			__func__);
+
+		list_for_each_entry(pmsg, data->queue.next, queue) {
+			pmsg->status = -EIO;
+
+			if (pmsg->complete != 0) {
+				spin_unlock(&data->lock);
+				pmsg->complete(pmsg->context);
+				spin_lock(&data->lock);
+			}
+
+			/* delete from queue */
+			list_del_init(&pmsg->queue);
+		}
+
+		spin_unlock(&data->lock);
+		return;
+	}
+
+	data->bcurrent_msg_processing = true;
+	dev_dbg(&data->master->dev,
+		"%s Set data->bcurrent_msg_processing= true\n", __func__);
+
+	/* Get the message from the queue and delete it from there. */
+	data->current_msg = list_entry(data->queue.next, struct spi_message,
+					queue);
+
+	list_del_init(&data->current_msg->queue);
+
+	data->current_msg->status = 0;
+
+	pch_spi_select_chip(data, data->current_msg->spi);
+
+	spin_unlock(&data->lock);
+
+	do {
+		/* If we are already processing a message get the next
+		transfer structure from the message otherwise retrieve
+		the 1st transfer request from the message. */
+		spin_lock(&data->lock);
+
+		if (data->cur_trans == NULL) {
+			data->cur_trans =
+			    list_entry(data->current_msg->transfers.
+				       next, struct spi_transfer,
+				       transfer_list);
+			dev_dbg(&data->master->dev,
+				"%s :Getting 1st transfer message\n", __func__);
+		} else {
+			data->cur_trans =
+			    list_entry(data->cur_trans->transfer_list.next,
+				       struct spi_transfer,
+				       transfer_list);
+			dev_dbg(&data->master->dev,
+				"%s :Getting next transfer message\n",
+				__func__);
+		}
+
+		spin_unlock(&data->lock);
+
+		pch_spi_set_tx(data, &bpw, &pmsg);
+
+		/* Control interrupt*/
+		pch_spi_set_ir(data);
+
+		/* Disable SPI transfer */
+		pch_spi_setclr_reg(data->current_chip->master, PCH_SPCR, 0,
+				   SPCR_SPE_BIT);
+
+		/* clear FIFO */
+		pch_spi_clear_fifo(data->master);
+
+		/* copy Rx Data */
+		pch_spi_copy_rx_data(data, bpw);
+
+		/* free memory */
+		kfree(data->pkt_rx_buff);
+		data->pkt_rx_buff = NULL;
+
+		kfree(data->pkt_tx_buff);
+		data->pkt_tx_buff = NULL;
+
+		/* increment message count */
+		data->current_msg->actual_length += data->cur_trans->len;
+
+		dev_dbg(&data->master->dev,
+			"%s:data->current_msg->actual_length=%d\n",
+			__func__, data->current_msg->actual_length);
+
+		/* check for delay */
+		if (data->cur_trans->delay_usecs) {
+			dev_dbg(&data->master->dev, "%s:"
+				"delay in usec=%d\n", __func__,
+				data->cur_trans->delay_usecs);
+			udelay(data->cur_trans->delay_usecs);
+		}
+
+		spin_lock(&data->lock);
+
+		/* No more transfer in this message. */
+		if ((data->cur_trans->transfer_list.next) ==
+		    &(data->current_msg->transfers)) {
+			pch_spi_nomore_transfer(data, pmsg);
+		}
+
+		spin_unlock(&data->lock);
+
+	} while (data->cur_trans != NULL);
+}
+
+static void pch_spi_free_resources(struct pch_spi_board_data *board_dat)
+{
+	dev_dbg(&board_dat->pdev->dev, "%s ENTRY\n", __func__);
+
+	/* free workqueue */
+	if (board_dat->data->wk != NULL) {
+		destroy_workqueue(board_dat->data->wk);
+		board_dat->data->wk = NULL;
+		dev_dbg(&board_dat->pdev->dev,
+			"%s destroy_workqueue invoked successfully\n",
+			__func__);
+	}
+
+	/* disable interrupts & free IRQ */
+	if (board_dat->irq_reg_sts) {
+		/* disable interrupts */
+		pch_spi_setclr_reg(board_dat->data->master, PCH_SPCR, 0,
+				   PCH_ALL);
+
+		/* free IRQ */
+		free_irq(board_dat->pdev->irq, board_dat);
+
+		dev_dbg(&board_dat->pdev->dev,
+			"%s free_irq invoked successfully\n", __func__);
+
+		board_dat->irq_reg_sts = false;
+	}
+
+	/* unmap PCI base address */
+	if (board_dat->data->io_remap_addr != 0) {
+		pci_iounmap(board_dat->pdev, board_dat->data->io_remap_addr);
+
+		board_dat->data->io_remap_addr = 0;
+
+		dev_dbg(&board_dat->pdev->dev,
+			"%s pci_iounmap invoked successfully\n", __func__);
+	}
+
+	/* release PCI region */
+	if (board_dat->pci_req_sts) {
+		pci_release_regions(board_dat->pdev);
+		dev_dbg(&board_dat->pdev->dev,
+			"%s pci_release_regions invoked successfully\n",
+			__func__);
+		board_dat->pci_req_sts = false;
+	}
+}
+
+static int pch_spi_get_resources(struct pch_spi_board_data *board_dat)
+{
+	void __iomem *io_remap_addr;
+	int retval;
+	dev_dbg(&board_dat->pdev->dev, "%s ENTRY\n", __func__);
+
+	/* create workqueue */
+	board_dat->data->wk = create_singlethread_workqueue(KBUILD_MODNAME);
+	if (!board_dat->data->wk) {
+		dev_err(&board_dat->pdev->dev,
+			"%s create_singlet hread_workqueue failed\n", __func__);
+		retval = -EBUSY;
+		goto err_return;
+	}
+
+	dev_dbg(&board_dat->pdev->dev,
+		"%s create_singlethread_workqueue success\n", __func__);
+
+	retval = pci_request_regions(board_dat->pdev, KBUILD_MODNAME);
+	if (retval != 0) {
+		dev_err(&board_dat->pdev->dev,
+			"%s request_region failed\n", __func__);
+		goto err_return;
+	}
+
+	board_dat->pci_req_sts = true;
+
+	io_remap_addr = pci_iomap(board_dat->pdev, 1, 0);
+	if (io_remap_addr == 0) {
+		dev_err(&board_dat->pdev->dev,
+			"%s pci_iomap failed\n", __func__);
+		retval = -ENOMEM;
+		goto err_return;
+	}
+
+	/* calculate base address for all channels */
+	board_dat->data->io_remap_addr = io_remap_addr;
+
+	/* reset PCH SPI h/w */
+	pch_spi_reset(board_dat->data->master);
+	dev_dbg(&board_dat->pdev->dev,
+		"%s pch_spi_reset invoked successfully\n", __func__);
+
+	/* register IRQ */
+	retval = request_irq(board_dat->pdev->irq, pch_spi_handler,
+			     IRQF_SHARED, KBUILD_MODNAME, board_dat);
+	if (retval != 0) {
+		dev_err(&board_dat->pdev->dev,
+			"%s request_irq failed\n", __func__);
+		goto err_return;
+	}
+
+	dev_dbg(&board_dat->pdev->dev, "%s request_irq returned=%d\n",
+		__func__, retval);
+
+	board_dat->irq_reg_sts = true;
+	dev_dbg(&board_dat->pdev->dev, "%s data->irq_reg_sts=true\n", __func__);
+
+err_return:
+	if (retval != 0) {
+		dev_err(&board_dat->pdev->dev,
+			"%s FAIL:invoking pch_spi_free_resources\n", __func__);
+		pch_spi_free_resources(board_dat);
+	}
+
+	dev_dbg(&board_dat->pdev->dev, "%s Return=%d\n", __func__, retval);
+
+	return retval;
+}
+
+static int pch_spi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+
+	struct spi_master *master;
+
+	struct pch_spi_board_data *board_dat;
+	int retval;
+
+	dev_dbg(&pdev->dev, "%s ENTRY\n", __func__);
+
+	/* allocate memory for private data */
+	board_dat = kzalloc(sizeof(struct pch_spi_board_data), GFP_KERNEL);
+	if (board_dat == NULL) {
+		dev_err(&pdev->dev,
+			" %s memory allocation for private data failed\n",
+			__func__);
+		retval = -ENOMEM;
+		goto err_kmalloc;
+	}
+
+	dev_dbg(&pdev->dev,
+		"%s memory allocation for private data success\n", __func__);
+
+	/* enable PCI device */
+	retval = pci_enable_device(pdev);
+	if (retval != 0) {
+		dev_err(&pdev->dev, "%s pci_enable_device FAILED\n", __func__);
+
+		goto err_pci_en_device;
+	}
+
+	dev_dbg(&pdev->dev, "%s pci_enable_device returned=%d\n",
+		__func__, retval);
+
+	board_dat->pdev = pdev;
+
+	/* alllocate memory for SPI master */
+	master = spi_alloc_master(&pdev->dev, sizeof(struct pch_spi_data));
+	if (master == NULL) {
+		retval = -ENOMEM;
+		dev_err(&pdev->dev, "%s Fail.\n", __func__);
+		goto err_spi_alloc_master;
+	}
+
+	dev_dbg(&pdev->dev,
+		"%s spi_alloc_master returned non NULL\n", __func__);
+
+	/* initialize members of SPI master */
+	master->bus_num = -1;
+	master->num_chipselect = PCH_MAX_CS;
+	master->setup = pch_spi_setup;
+	master->transfer = pch_spi_transfer;
+	dev_dbg(&pdev->dev,
+		"%s transfer member of SPI master initialized\n", __func__);
+
+	board_dat->data = spi_master_get_devdata(master);
+
+	board_dat->data->master = master;
+	board_dat->data->n_curnt_chip = 255;
+	board_dat->data->board_dat = board_dat;
+	board_dat->data->status = STATUS_RUNNING;
+
+	INIT_LIST_HEAD(&board_dat->data->queue);
+	spin_lock_init(&board_dat->data->lock);
+	INIT_WORK(&board_dat->data->work, pch_spi_process_messages);
+	init_waitqueue_head(&board_dat->data->wait);
+
+	/* allocate resources for PCH SPI */
+	retval = pch_spi_get_resources(board_dat);
+	if (retval) {
+		dev_err(&pdev->dev, "%s fail(retval=%d)\n", __func__, retval);
+		goto err_spi_get_resources;
+	}
+
+	dev_dbg(&pdev->dev, "%s pch_spi_get_resources returned=%d\n",
+		__func__, retval);
+
+	/* save private data in dev */
+	pci_set_drvdata(pdev, board_dat);
+	dev_dbg(&pdev->dev, "%s invoked pci_set_drvdata\n", __func__);
+
+	/* set master mode */
+	pch_spi_set_master_mode(master);
+	dev_dbg(&pdev->dev,
+		"%s invoked pch_spi_set_master_mode\n", __func__);
+
+	/* Register the controller with the SPI core. */
+	retval = spi_register_master(master);
+	if (retval != 0) {
+		dev_err(&pdev->dev,
+			"%s spi_register_master FAILED\n", __func__);
+		goto err_spi_reg_master;
+	}
+
+	dev_dbg(&pdev->dev, "%s spi_register_master returned=%d\n",
+		__func__, retval);
+
+
+	return 0;
+
+err_spi_reg_master:
+	spi_unregister_master(master);
+err_spi_get_resources:
+err_spi_alloc_master:
+	spi_master_put(master);
+	pci_disable_device(pdev);
+err_pci_en_device:
+	kfree(board_dat);
+err_kmalloc:
+	return retval;
+}
+
+static void pch_spi_remove(struct pci_dev *pdev)
+{
+	struct pch_spi_board_data *board_dat = pci_get_drvdata(pdev);
+	int count;
+
+	dev_dbg(&pdev->dev, "%s ENTRY\n", __func__);
+
+	if (!board_dat) {
+		dev_err(&pdev->dev,
+			"%s pci_get_drvdata returned NULL\n", __func__);
+		return;
+	}
+
+	/* check for any pending messages; no action is taken if the queue
+	 * is still full; but at least we tried.  Unload anyway */
+	count = 500;
+	spin_lock(&board_dat->data->lock);
+	board_dat->data->status = STATUS_EXITING;
+	while ((list_empty(&board_dat->data->queue) == 0) && --count) {
+		dev_dbg(&board_dat->pdev->dev, "%s :queue not empty\n",
+			__func__);
+		spin_unlock(&board_dat->data->lock);
+		msleep(PCH_SLEEP_TIME);
+		spin_lock(&board_dat->data->lock);
+	}
+	spin_unlock(&board_dat->data->lock);
+
+	/* Free resources allocated for PCH SPI */
+	pch_spi_free_resources(board_dat);
+
+	spi_unregister_master(board_dat->data->master);
+
+	/* free memory for private data */
+	kfree(board_dat);
+
+	pci_set_drvdata(pdev, NULL);
+
+	/* disable PCI device */
+	pci_disable_device(pdev);
+
+	dev_dbg(&pdev->dev, "%s invoked pci_disable_device\n", __func__);
+}
+
+#ifdef CONFIG_PM
+static int pch_spi_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	u8 count;
+	int retval;
+
+	struct pch_spi_board_data *board_dat = pci_get_drvdata(pdev);
+
+	dev_dbg(&pdev->dev, "%s ENTRY\n", __func__);
+
+	if (!board_dat) {
+		dev_err(&pdev->dev,
+			"%s pci_get_drvdata returned NULL\n", __func__);
+		return -EFAULT;
+	}
+
+	retval = 0;
+	board_dat->suspend_sts = true;
+
+	/* check if the current message is processed:
+	   Only after thats done the transfer will be suspended */
+	count = 255;
+	while ((--count) > 0) {
+		if (!(board_dat->data->bcurrent_msg_processing)) {
+			dev_dbg(&pdev->dev, "%s board_dat->data->bCurrent_"
+				"msg_processing = false\n", __func__);
+			break;
+		} else {
+			dev_dbg(&pdev->dev, "%s board_dat->data->bCurrent_msg_"
+				"processing = true\n", __func__);
+		}
+		msleep(PCH_SLEEP_TIME);
+	}
+
+	/* Free IRQ */
+	if (board_dat->irq_reg_sts) {
+		/* disable all interrupts */
+		pch_spi_setclr_reg(board_dat->data->master, PCH_SPCR, 0,
+				   PCH_ALL);
+		pch_spi_reset(board_dat->data->master);
+
+		free_irq(board_dat->pdev->irq, board_dat);
+
+		board_dat->irq_reg_sts = false;
+		dev_dbg(&pdev->dev,
+			"%s free_irq invoked successfully.\n", __func__);
+	}
+
+	/* save config space */
+	retval = pci_save_state(pdev);
+
+	if (retval == 0) {
+		dev_dbg(&pdev->dev, "%s pci_save_state returned=%d\n",
+			__func__, retval);
+		/* disable PM notifications */
+		pci_enable_wake(pdev, PCI_D3hot, 0);
+		dev_dbg(&pdev->dev,
+			"%s pci_enable_wake invoked successfully\n", __func__);
+		/* disable PCI device */
+		pci_disable_device(pdev);
+		dev_dbg(&pdev->dev,
+			"%s pci_disable_device invoked successfully\n",
+			__func__);
+		/* move device to D3hot  state */
+		pci_set_power_state(pdev, PCI_D3hot);
+		dev_dbg(&pdev->dev,
+			"%s pci_set_power_state invoked successfully\n",
+			__func__);
+	} else {
+		dev_err(&pdev->dev, "%s pci_save_state failed\n", __func__);
+	}
+
+	dev_dbg(&pdev->dev, "%s return=%d\n", __func__, retval);
+
+	return retval;
+}
+
+static int pch_spi_resume(struct pci_dev *pdev)
+{
+	int retval;
+
+	struct pch_spi_board_data *board = pci_get_drvdata(pdev);
+	dev_dbg(&pdev->dev, "%s ENTRY\n", __func__);
+
+	if (!board) {
+		dev_err(&pdev->dev,
+			"%s pci_get_drvdata returned NULL\n", __func__);
+		return -EFAULT;
+	}
+
+	/* move device to DO power state */
+	pci_set_power_state(pdev, PCI_D0);
+
+	/* restore state */
+	pci_restore_state(pdev);
+
+	retval = pci_enable_device(pdev);
+	if (retval < 0) {
+		dev_err(&pdev->dev,
+			"%s pci_enable_device failed\n", __func__);
+	} else {
+		/* disable PM notifications */
+		pci_enable_wake(pdev, PCI_D3hot, 0);
+
+		/* register IRQ handler */
+		if (!board->irq_reg_sts) {
+			/* register IRQ */
+			retval = request_irq(board->pdev->irq, pch_spi_handler,
+					     IRQF_SHARED, KBUILD_MODNAME,
+					     board);
+			if (retval < 0) {
+				dev_err(&pdev->dev,
+					"%s request_irq failed\n", __func__);
+				return retval;
+			}
+			board->irq_reg_sts = true;
+
+			/* reset PCH SPI h/w */
+			pch_spi_reset(board->data->master);
+			pch_spi_set_master_mode(board->data->master);
+
+			/* set suspend status to false */
+			board->suspend_sts = false;
+
+		}
+	}
+
+	dev_dbg(&pdev->dev, "%s returning=%d\n", __func__, retval);
+
+	return retval;
+}
+#else
+#define pch_spi_suspend NULL
+#define pch_spi_resume NULL
+
+#endif
+
+static struct pci_driver pch_spi_pcidev = {
+	.name = "pch_spi",
+	.id_table = pch_spi_pcidev_id,
+	.probe = pch_spi_probe,
+	.remove = pch_spi_remove,
+	.suspend = pch_spi_suspend,
+	.resume = pch_spi_resume,
+};
+
+static int __init pch_spi_init(void)
+{
+	return pci_register_driver(&pch_spi_pcidev);
+}
+module_init(pch_spi_init);
+
+static void __exit pch_spi_exit(void)
+{
+	pci_unregister_driver(&pch_spi_pcidev);
+}
+module_exit(pch_spi_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Topcliff PCH SPI PCI Driver");
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index ea1bec3..4e6245e 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -545,6 +545,7 @@
 	.unlocked_ioctl = spidev_ioctl,
 	.open =		spidev_open,
 	.release =	spidev_release,
+	.llseek =	no_llseek,
 };
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 7892ac1..c68b3dc 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -20,7 +20,6 @@
 #include <linux/mmc/sdio_func.h>
 #include <linux/slab.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c
index 526682d..c7345db 100644
--- a/drivers/ssb/pcmcia.c
+++ b/drivers/ssb/pcmcia.c
@@ -13,7 +13,6 @@
 #include <linux/io.h>
 #include <linux/etherdevice.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c
index 9738cad..ee079ab 100644
--- a/drivers/ssb/scan.c
+++ b/drivers/ssb/scan.c
@@ -17,7 +17,6 @@
 #include <linux/pci.h>
 #include <linux/io.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index 1409131..fecb89e 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -1922,6 +1922,7 @@
 	.mmap = comedi_mmap,
 	.poll = comedi_poll,
 	.fasync = comedi_fasync,
+	.llseek = noop_llseek,
 };
 
 struct class *comedi_class;
diff --git a/drivers/staging/comedi/drivers/cb_das16_cs.c b/drivers/staging/comedi/drivers/cb_das16_cs.c
index f8ede11..0345b4c 100644
--- a/drivers/staging/comedi/drivers/cb_das16_cs.c
+++ b/drivers/staging/comedi/drivers/cb_das16_cs.c
@@ -37,7 +37,6 @@
 #include <linux/delay.h>
 #include <linux/pci.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -692,10 +691,6 @@
 	local->link = link;
 	link->priv = local;
 
-	/* Initialize the pcmcia_device structure */
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	cur_dev = link;
 
 	das16cs_pcmcia_config(link);
@@ -715,37 +710,12 @@
 
 
 static int das16cs_pcmcia_config_loop(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
 				void *priv_data)
 {
-	if (cfg->index == 0)
+	if (p_dev->config_index == 0)
 		return -EINVAL;
 
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-			pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-		/* This reserves IO space but doesn't actually enable it */
-		return pcmcia_request_io(p_dev);
-	}
-
-	return 0;
+	return pcmcia_request_io(p_dev);
 }
 
 static void das16cs_pcmcia_config(struct pcmcia_device *link)
@@ -754,6 +724,9 @@
 
 	dev_dbg(&link->dev, "das16cs_pcmcia_config\n");
 
+	/* Do we need to allocate an interrupt? */
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+
 	ret = pcmcia_loop_config(link, das16cs_pcmcia_config_loop, NULL);
 	if (ret) {
 		dev_warn(&link->dev, "no configuration found\n");
@@ -763,25 +736,10 @@
 	if (!link->irq)
 		goto failed;
 
-	/*
-	   This actually configures the PCMCIA socket -- setting up
-	   the I/O windows and the interrupt mapping, and putting the
-	   card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
-	/* Finally, report what we've done */
-	dev_info(&link->dev, "index 0x%02x", link->conf.ConfigIndex);
-	if (link->conf.Attributes & CONF_ENABLE_IRQ)
-		printk(", irq %u", link->irq);
-	if (link->resource[0])
-		printk(", io %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(", io %pR", link->resource[1]);
-	printk("\n");
-
 	return;
 
 failed:
@@ -832,9 +790,7 @@
 	.resume = das16cs_pcmcia_resume,
 	.id_table = das16cs_id_table,
 	.owner = THIS_MODULE,
-	.drv = {
-		.name = "cb_das16_cs",
-		},
+	.name = "cb_das16_cs",
 };
 
 static int __init init_das16cs_pcmcia_cs(void)
diff --git a/drivers/staging/comedi/drivers/das08_cs.c b/drivers/staging/comedi/drivers/das08_cs.c
index 48d9fb1..0b32a2d 100644
--- a/drivers/staging/comedi/drivers/das08_cs.c
+++ b/drivers/staging/comedi/drivers/das08_cs.c
@@ -48,7 +48,6 @@
 #include "das08.h"
 
 /* pcmcia includes */
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -115,40 +114,15 @@
 static int das08_pcmcia_suspend(struct pcmcia_device *p_dev);
 static int das08_pcmcia_resume(struct pcmcia_device *p_dev);
 
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static int das08_pcmcia_attach(struct pcmcia_device *);
 static void das08_pcmcia_detach(struct pcmcia_device *);
 
-/*
-   You'll also need to prototype all the functions that will actually
-   be used to talk to your device.  See 'memory_cs' for a good example
-   of a fully self-sufficient driver; the other drivers rely more or
-   less on other parts of the kernel.
-*/
-
 struct local_info_t {
 	struct pcmcia_device *link;
 	int stop;
 	struct bus_operations *bus;
 };
 
-/*======================================================================
-
-    das08_pcmcia_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-
-======================================================================*/
-
 static int das08_pcmcia_attach(struct pcmcia_device *link)
 {
 	struct local_info_t *local;
@@ -162,16 +136,6 @@
 	local->link = link;
 	link->priv = local;
 
-	/*
-	   General socket configuration defaults can go here.  In this
-	   client, we assume very little, and rely on the CIS for almost
-	   everything.  In most clients, many details (i.e., number, sizes,
-	   and attributes of IO windows) are fixed by the nature of the
-	   device, and can be hard-wired here.
-	 */
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	cur_dev = link;
 
 	das08_pcmcia_config(link);
@@ -179,15 +143,6 @@
 	return 0;
 }				/* das08_pcmcia_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void das08_pcmcia_detach(struct pcmcia_device *link)
 {
 
@@ -203,53 +158,22 @@
 
 
 static int das08_pcmcia_config_loop(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
 				void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-			pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-		/* This reserves IO space but doesn't actually enable it */
-		return pcmcia_request_io(p_dev);
-	}
-	return 0;
+	return pcmcia_request_io(p_dev);
 }
 
-
-/*======================================================================
-
-    das08_pcmcia_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-
-======================================================================*/
-
 static void das08_pcmcia_config(struct pcmcia_device *link)
 {
 	int ret;
 
 	dev_dbg(&link->dev, "das08_pcmcia_config\n");
 
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+
 	ret = pcmcia_loop_config(link, das08_pcmcia_config_loop, NULL);
 	if (ret) {
 		dev_warn(&link->dev, "no configuration found\n");
@@ -259,25 +183,10 @@
 	if (!link->irq)
 		goto failed;
 
-	/*
-	   This actually configures the PCMCIA socket -- setting up
-	   the I/O windows and the interrupt mapping, and putting the
-	   card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
-	/* Finally, report what we've done */
-	dev_info(&link->dev, "index 0x%02x", link->conf.ConfigIndex);
-	if (link->conf.Attributes & CONF_ENABLE_IRQ)
-		printk(", irq %u", link->irq);
-	if (link->resource[0])
-		printk(", io %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(" & %pR", link->resource[1]);
-	printk("\n");
-
 	return;
 
 failed:
@@ -285,32 +194,12 @@
 
 }				/* das08_pcmcia_config */
 
-/*======================================================================
-
-    After a card is removed, das08_pcmcia_release() will unregister the
-    device, and release the PCMCIA configuration.  If the device is
-    still open, this will be postponed until it is closed.
-
-======================================================================*/
-
 static void das08_pcmcia_release(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "das08_pcmcia_release\n");
 	pcmcia_disable_device(link);
 }				/* das08_pcmcia_release */
 
-/*======================================================================
-
-    The card status event handler.  Mostly, this schedules other
-    stuff to run after an event is received.
-
-    When a CARD_REMOVAL event is received, we immediately set a
-    private flag to block future accesses to this device.  All the
-    functions that actually access the device should check this flag
-    to make sure the card is still present.
-
-======================================================================*/
-
 static int das08_pcmcia_suspend(struct pcmcia_device *link)
 {
 	struct local_info_t *local = link->priv;
@@ -348,9 +237,7 @@
 	.resume = das08_pcmcia_resume,
 	.id_table = das08_cs_id_table,
 	.owner = THIS_MODULE,
-	.drv = {
-		.name = "pcm-das08",
-		},
+	.name = "pcm-das08",
 };
 
 static int __init init_das08_pcmcia_cs(void)
diff --git a/drivers/staging/comedi/drivers/ni_daq_700.c b/drivers/staging/comedi/drivers/ni_daq_700.c
index cc15666..6b7372e 100644
--- a/drivers/staging/comedi/drivers/ni_daq_700.c
+++ b/drivers/staging/comedi/drivers/ni_daq_700.c
@@ -47,7 +47,6 @@
 
 #include <linux/ioport.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -435,47 +434,20 @@
 	return 0;
 };
 
-/* PCMCIA crap -- watch your words, please! */
-
 static void dio700_config(struct pcmcia_device *link);
 static void dio700_release(struct pcmcia_device *link);
 static int dio700_cs_suspend(struct pcmcia_device *p_dev);
 static int dio700_cs_resume(struct pcmcia_device *p_dev);
 
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static int dio700_cs_attach(struct pcmcia_device *);
 static void dio700_cs_detach(struct pcmcia_device *);
 
-/*
-   You'll also need to prototype all the functions that will actually
-   be used to talk to your device.  See 'memory_cs' for a good example
-   of a fully self-sufficient driver; the other drivers rely more or
-   less on other parts of the kernel.
-*/
-
 struct local_info_t {
 	struct pcmcia_device *link;
 	int stop;
 	struct bus_operations *bus;
 };
 
-/*======================================================================
-
-    dio700_cs_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-
-======================================================================*/
-
 static int dio700_cs_attach(struct pcmcia_device *link)
 {
 	struct local_info_t *local;
@@ -491,16 +463,6 @@
 	local->link = link;
 	link->priv = local;
 
-	/*
-	   General socket configuration defaults can go here.  In this
-	   client, we assume very little, and rely on the CIS for almost
-	   everything.  In most clients, many details (i.e., number, sizes,
-	   and attributes of IO windows) are fixed by the nature of the
-	   device, and can be hard-wired here.
-	 */
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	pcmcia_cur_dev = link;
 
 	dio700_config(link);
@@ -508,15 +470,6 @@
 	return 0;
 }				/* dio700_cs_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void dio700_cs_detach(struct pcmcia_device *link)
 {
 
@@ -532,65 +485,26 @@
 
 }				/* dio700_cs_detach */
 
-/*======================================================================
-
-    dio700_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-
-======================================================================*/
-
 static int dio700_pcmcia_config_loop(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
 				void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Does this card need audio output? */
-	if (cfg->flags & CISTPL_CFTABLE_AUDIO) {
-		p_dev->conf.Attributes |= CONF_ENABLE_SPKR;
-		p_dev->conf.Status = CCSR_AUDIO_ENA;
-	}
-
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-			pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-		/* This reserves IO space but doesn't actually enable it */
-		if (pcmcia_request_io(p_dev) != 0)
-			return -ENODEV;
-	}
-
-	/* If we got this far, we're cool! */
-	return 0;
+	return pcmcia_request_io(p_dev);
 }
 
 static void dio700_config(struct pcmcia_device *link)
 {
-	win_req_t req;
 	int ret;
 
 	printk(KERN_INFO "ni_daq_700:  cs-config\n");
 
 	dev_dbg(&link->dev, "dio700_config\n");
 
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_AUDIO |
+		CONF_AUTO_SET_IO;
+
 	ret = pcmcia_loop_config(link, dio700_pcmcia_config_loop, NULL);
 	if (ret) {
 		dev_warn(&link->dev, "no configuration found\n");
@@ -600,25 +514,10 @@
 	if (!link->irq)
 		goto failed;
 
-	/*
-	   This actually configures the PCMCIA socket -- setting up
-	   the I/O windows and the interrupt mapping, and putting the
-	   card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret != 0)
 		goto failed;
 
-	/* Finally, report what we've done */
-	dev_info(&link->dev, "index 0x%02x", link->conf.ConfigIndex);
-	if (link->conf.Attributes & CONF_ENABLE_IRQ)
-		printk(", irq %d", link->irq);
-	if (link->resource[0])
-		printk(", io %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(" & %pR", link->resource[1]);
-	printk("\n");
-
 	return;
 
 failed:
@@ -634,18 +533,6 @@
 	pcmcia_disable_device(link);
 }				/* dio700_release */
 
-/*======================================================================
-
-    The card status event handler.  Mostly, this schedules other
-    stuff to run after an event is received.
-
-    When a CARD_REMOVAL event is received, we immediately set a
-    private flag to block future accesses to this device.  All the
-    functions that actually access the device should check this flag
-    to make sure the card is still present.
-
-======================================================================*/
-
 static int dio700_cs_suspend(struct pcmcia_device *link)
 {
 	struct local_info_t *local = link->priv;
@@ -685,9 +572,7 @@
 	.resume = dio700_cs_resume,
 	.id_table = dio700_cs_ids,
 	.owner = THIS_MODULE,
-	.drv = {
-		.name = "ni_daq_700",
-		},
+	.name = "ni_daq_700",
 };
 
 static int __init init_dio700_cs(void)
diff --git a/drivers/staging/comedi/drivers/ni_daq_dio24.c b/drivers/staging/comedi/drivers/ni_daq_dio24.c
index 773ae20..c9c2858 100644
--- a/drivers/staging/comedi/drivers/ni_daq_dio24.c
+++ b/drivers/staging/comedi/drivers/ni_daq_dio24.c
@@ -48,7 +48,6 @@
 
 #include "8255.h"
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -187,47 +186,20 @@
 	return 0;
 };
 
-/* PCMCIA crap -- watch your words! */
-
 static void dio24_config(struct pcmcia_device *link);
 static void dio24_release(struct pcmcia_device *link);
 static int dio24_cs_suspend(struct pcmcia_device *p_dev);
 static int dio24_cs_resume(struct pcmcia_device *p_dev);
 
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static int dio24_cs_attach(struct pcmcia_device *);
 static void dio24_cs_detach(struct pcmcia_device *);
 
-/*
-   You'll also need to prototype all the functions that will actually
-   be used to talk to your device.  See 'memory_cs' for a good example
-   of a fully self-sufficient driver; the other drivers rely more or
-   less on other parts of the kernel.
-*/
-
 struct local_info_t {
 	struct pcmcia_device *link;
 	int stop;
 	struct bus_operations *bus;
 };
 
-/*======================================================================
-
-    dio24_cs_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-
-======================================================================*/
-
 static int dio24_cs_attach(struct pcmcia_device *link)
 {
 	struct local_info_t *local;
@@ -243,16 +215,6 @@
 	local->link = link;
 	link->priv = local;
 
-	/*
-	   General socket configuration defaults can go here.  In this
-	   client, we assume very little, and rely on the CIS for almost
-	   everything.  In most clients, many details (i.e., number, sizes,
-	   and attributes of IO windows) are fixed by the nature of the
-	   device, and can be hard-wired here.
-	 */
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	pcmcia_cur_dev = link;
 
 	dio24_config(link);
@@ -260,15 +222,6 @@
 	return 0;
 }				/* dio24_cs_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void dio24_cs_detach(struct pcmcia_device *link)
 {
 
@@ -284,54 +237,13 @@
 
 }				/* dio24_cs_detach */
 
-/*======================================================================
-
-    dio24_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-
-======================================================================*/
-
 static int dio24_pcmcia_config_loop(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
 				void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Does this card need audio output? */
-	if (cfg->flags & CISTPL_CFTABLE_AUDIO) {
-		p_dev->conf.Attributes |= CONF_ENABLE_SPKR;
-		p_dev->conf.Status = CCSR_AUDIO_ENA;
-	}
-
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-			pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-		/* This reserves IO space but doesn't actually enable it */
-		if (pcmcia_request_io(p_dev) != 0)
-			return -ENODEV;
-	}
-
-	/* If we got this far, we're cool! */
-	return 0;
+	return pcmcia_request_io(p_dev);
 }
 
 static void dio24_config(struct pcmcia_device *link)
@@ -342,6 +254,9 @@
 
 	dev_dbg(&link->dev, "dio24_config\n");
 
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_AUDIO |
+		CONF_AUTO_SET_IO;
+
 	ret = pcmcia_loop_config(link, dio24_pcmcia_config_loop, NULL);
 	if (ret) {
 		dev_warn(&link->dev, "no configuration found\n");
@@ -351,25 +266,10 @@
 	if (!link->irq)
 		goto failed;
 
-	/*
-	   This actually configures the PCMCIA socket -- setting up
-	   the I/O windows and the interrupt mapping, and putting the
-	   card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
-	/* Finally, report what we've done */
-	dev_info(&link->dev, "index 0x%02x", link->conf.ConfigIndex);
-	if (link->conf.Attributes & CONF_ENABLE_IRQ)
-		printk(", irq %d", link->irq);
-	if (link->resource[0])
-		printk(" & %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(" & %pR", link->resource[1]);
-	printk("\n");
-
 	return;
 
 failed:
@@ -385,18 +285,6 @@
 	pcmcia_disable_device(link);
 }				/* dio24_release */
 
-/*======================================================================
-
-    The card status event handler.  Mostly, this schedules other
-    stuff to run after an event is received.
-
-    When a CARD_REMOVAL event is received, we immediately set a
-    private flag to block future accesses to this device.  All the
-    functions that actually access the device should check this flag
-    to make sure the card is still present.
-
-======================================================================*/
-
 static int dio24_cs_suspend(struct pcmcia_device *link)
 {
 	struct local_info_t *local = link->priv;
@@ -435,9 +323,7 @@
 	.resume = dio24_cs_resume,
 	.id_table = dio24_cs_ids,
 	.owner = THIS_MODULE,
-	.drv = {
-		.name = "ni_daq_dio24",
-		},
+	.name = "ni_daq_dio24",
 };
 
 static int __init init_dio24_cs(void)
diff --git a/drivers/staging/comedi/drivers/ni_labpc_cs.c b/drivers/staging/comedi/drivers/ni_labpc_cs.c
index 68c4ecb..6facbc8 100644
--- a/drivers/staging/comedi/drivers/ni_labpc_cs.c
+++ b/drivers/staging/comedi/drivers/ni_labpc_cs.c
@@ -71,7 +71,6 @@
 #include "comedi_fc.h"
 #include "ni_labpc.h"
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -153,59 +152,20 @@
 	return labpc_common_attach(dev, iobase, irq, 0);
 }
 
-/*====================================================================*/
-
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card
-   insertion and ejection events.  They are invoked from the dummy
-   event handler.
-
-   Kernel version 2.6.16 upwards uses suspend() and resume() functions
-   instead of an event() function.
-*/
-
 static void labpc_config(struct pcmcia_device *link);
 static void labpc_release(struct pcmcia_device *link);
 static int labpc_cs_suspend(struct pcmcia_device *p_dev);
 static int labpc_cs_resume(struct pcmcia_device *p_dev);
 
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static int labpc_cs_attach(struct pcmcia_device *);
 static void labpc_cs_detach(struct pcmcia_device *);
 
-/*
-   You'll also need to prototype all the functions that will actually
-   be used to talk to your device.  See 'memory_cs' for a good example
-   of a fully self-sufficient driver; the other drivers rely more or
-   less on other parts of the kernel.
-*/
-
 struct local_info_t {
 	struct pcmcia_device *link;
 	int stop;
 	struct bus_operations *bus;
 };
 
-/*======================================================================
-
-    labpc_cs_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-
-======================================================================*/
-
 static int labpc_cs_attach(struct pcmcia_device *link)
 {
 	struct local_info_t *local;
@@ -219,16 +179,6 @@
 	local->link = link;
 	link->priv = local;
 
-	/*
-	   General socket configuration defaults can go here.  In this
-	   client, we assume very little, and rely on the CIS for almost
-	   everything.  In most clients, many details (i.e., number, sizes,
-	   and attributes of IO windows) are fixed by the nature of the
-	   device, and can be hard-wired here.
-	 */
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	pcmcia_cur_dev = link;
 
 	labpc_config(link);
@@ -236,15 +186,6 @@
 	return 0;
 }				/* labpc_cs_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void labpc_cs_detach(struct pcmcia_device *link)
 {
 	dev_dbg(&link->dev, "labpc_cs_detach\n");
@@ -263,54 +204,13 @@
 
 }				/* labpc_cs_detach */
 
-/*======================================================================
-
-    labpc_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-
-======================================================================*/
-
 static int labpc_pcmcia_config_loop(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
 				void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Does this card need audio output? */
-	if (cfg->flags & CISTPL_CFTABLE_AUDIO) {
-		p_dev->conf.Attributes |= CONF_ENABLE_SPKR;
-		p_dev->conf.Status = CCSR_AUDIO_ENA;
-	}
-
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ | CONF_ENABLE_PULSE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-			pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-		/* This reserves IO space but doesn't actually enable it */
-		if (pcmcia_request_io(p_dev) != 0)
-			return -ENODEV;
-	}
-
-	/* If we got this far, we're cool! */
-	return 0;
+	return pcmcia_request_io(p_dev);
 }
 
 
@@ -320,6 +220,9 @@
 
 	dev_dbg(&link->dev, "labpc_config\n");
 
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_ENABLE_PULSE_IRQ |
+		CONF_AUTO_AUDIO | CONF_AUTO_SET_IO;
+
 	ret = pcmcia_loop_config(link, labpc_pcmcia_config_loop, NULL);
 	if (ret) {
 		dev_warn(&link->dev, "no configuration found\n");
@@ -329,25 +232,10 @@
 	if (!link->irq)
 		goto failed;
 
-	/*
-	   This actually configures the PCMCIA socket -- setting up
-	   the I/O windows and the interrupt mapping, and putting the
-	   card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
-	/* Finally, report what we've done */
-	dev_info(&link->dev, "index 0x%02x", link->conf.ConfigIndex);
-	if (link->conf.Attributes & CONF_ENABLE_IRQ)
-		printk(", irq %d", link->irq);
-	if (link->resource[0])
-		printk(" & %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(" & %pR", link->resource[1]);
-	printk("\n");
-
 	return;
 
 failed:
@@ -362,18 +250,6 @@
 	pcmcia_disable_device(link);
 }				/* labpc_release */
 
-/*======================================================================
-
-    The card status event handler.  Mostly, this schedules other
-    stuff to run after an event is received.
-
-    When a CARD_REMOVAL event is received, we immediately set a
-    private flag to block future accesses to this device.  All the
-    functions that actually access the device should check this flag
-    to make sure the card is still present.
-
-======================================================================*/
-
 static int labpc_cs_suspend(struct pcmcia_device *link)
 {
 	struct local_info_t *local = link->priv;
@@ -391,8 +267,6 @@
 	return 0;
 }				/* labpc_cs_resume */
 
-/*====================================================================*/
-
 static struct pcmcia_device_id labpc_cs_ids[] = {
 	/* N.B. These IDs should match those in labpc_cs_boards (ni_labpc.c) */
 	PCMCIA_DEVICE_MANF_CARD(0x010b, 0x0103),	/* daqcard-1200 */
@@ -411,9 +285,7 @@
 	.resume = labpc_cs_resume,
 	.id_table = labpc_cs_ids,
 	.owner = THIS_MODULE,
-	.drv = {
-		.name = "daqcard-1200",
-		},
+	.name = "daqcard-1200",
 };
 
 static int __init init_labpc_cs(void)
diff --git a/drivers/staging/comedi/drivers/ni_mio_cs.c b/drivers/staging/comedi/drivers/ni_mio_cs.c
index 1f24263..4956327 100644
--- a/drivers/staging/comedi/drivers/ni_mio_cs.c
+++ b/drivers/staging/comedi/drivers/ni_mio_cs.c
@@ -48,7 +48,6 @@
 #include "ni_stc.h"
 #include "8255.h"
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -263,11 +262,6 @@
 
 static int cs_attach(struct pcmcia_device *link)
 {
-	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
-	link->resource[0]->end = 16;
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	cur_dev = link;
 
 	mio_cs_config(link);
@@ -301,16 +295,12 @@
 }
 
 
-static int mio_pcmcia_config_loop(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
-				void *priv_data)
+static int mio_pcmcia_config_loop(struct pcmcia_device *p_dev, void *priv_data)
 {
 	int base, ret;
 
-	p_dev->resource[0]->end = cfg->io.win[0].len;
-	p_dev->io_lines = cfg->io.flags & CISTPL_IO_LINES_MASK;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
 
 	for (base = 0x000; base < 0x400; base += 0x20) {
 		p_dev->resource[0]->start = base;
@@ -327,6 +317,7 @@
 	int ret;
 
 	DPRINTK("mio_cs_config(link=%p)\n", link);
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
 
 	ret = pcmcia_loop_config(link, mio_pcmcia_config_loop, NULL);
 	if (ret) {
@@ -337,7 +328,7 @@
 	if (!link->irq)
 		dev_info(&link->dev, "no IRQ available\n");
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 }
 
 static int mio_cs_attach(struct comedi_device *dev, struct comedi_devconfig *it)
@@ -446,9 +437,7 @@
 	.resume = &mio_cs_resume,
 	.id_table = ni_mio_cs_ids,
 	.owner = THIS_MODULE,
-	.drv = {
-		.name = "ni_mio_cs",
-		},
+	.name = "ni_mio_cs",
 };
 
 int init_module(void)
diff --git a/drivers/staging/comedi/drivers/quatech_daqp_cs.c b/drivers/staging/comedi/drivers/quatech_daqp_cs.c
index bf489d7..ebba9bb 100644
--- a/drivers/staging/comedi/drivers/quatech_daqp_cs.c
+++ b/drivers/staging/comedi/drivers/quatech_daqp_cs.c
@@ -50,7 +50,6 @@
 #include "../comedidev.h"
 #include <linux/semaphore.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -969,43 +968,14 @@
 
 ======================================================================*/
 
-/*
-   The event() function is this driver's Card Services event handler.
-   It will be called by Card Services when an appropriate card status
-   event is received.  The config() and release() entry points are
-   used to configure or release a socket, in response to card
-   insertion and ejection events.
-
-   Kernel version 2.6.16 upwards uses suspend() and resume() functions
-   instead of an event() function.
-*/
-
 static void daqp_cs_config(struct pcmcia_device *link);
 static void daqp_cs_release(struct pcmcia_device *link);
 static int daqp_cs_suspend(struct pcmcia_device *p_dev);
 static int daqp_cs_resume(struct pcmcia_device *p_dev);
 
-/*
-   The attach() and detach() entry points are used to create and destroy
-   "instances" of the driver, where each instance represents everything
-   needed to manage one actual PCMCIA card.
-*/
-
 static int daqp_cs_attach(struct pcmcia_device *);
 static void daqp_cs_detach(struct pcmcia_device *);
 
-/*======================================================================
-
-    daqp_cs_attach() creates an "instance" of the driver, allocating
-    local data structures for one device.  The device is registered
-    with Card Services.
-
-    The dev_link structure is initialized, but we don't actually
-    configure the card at this point -- we wait until we receive a
-    card insertion event.
-
-======================================================================*/
-
 static int daqp_cs_attach(struct pcmcia_device *link)
 {
 	struct local_info_t *local;
@@ -1031,30 +1001,11 @@
 	local->link = link;
 	link->priv = local;
 
-	/*
-	   General socket configuration defaults can go here.  In this
-	   client, we assume very little, and rely on the CIS for almost
-	   everything.  In most clients, many details (i.e., number, sizes,
-	   and attributes of IO windows) are fixed by the nature of the
-	   device, and can be hard-wired here.
-	 */
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	daqp_cs_config(link);
 
 	return 0;
 }				/* daqp_cs_attach */
 
-/*======================================================================
-
-    This deletes a driver "instance".  The device is de-registered
-    with Card Services.  If it has been released, all local data
-    structures are freed.  Otherwise, the structures will be freed
-    when the device is released.
-
-======================================================================*/
-
 static void daqp_cs_detach(struct pcmcia_device *link)
 {
 	struct local_info_t *dev = link->priv;
@@ -1070,45 +1021,11 @@
 
 }				/* daqp_cs_detach */
 
-/*======================================================================
-
-    daqp_cs_config() is scheduled to run after a CARD_INSERTION event
-    is received, to configure the PCMCIA socket, and to make the
-    device available to the system.
-
-======================================================================*/
-
-
-static int daqp_pcmcia_config_loop(struct pcmcia_device *p_dev,
-				cistpl_cftable_entry_t *cfg,
-				cistpl_cftable_entry_t *dflt,
-				unsigned int vcc,
-				void *priv_data)
+static int daqp_pcmcia_config_loop(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Do we need to allocate an interrupt? */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-		p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
-		p_dev->resource[0]->flags |=
-			pcmcia_io_cfg_data_width(io->flags);
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		if (io->nwin > 1) {
-			p_dev->resource[1]->flags = p_dev->resource[0]->flags;
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-	}
-
-	/* This reserves IO space but doesn't actually enable it */
 	return pcmcia_request_io(p_dev);
 }
 
@@ -1118,6 +1035,8 @@
 
 	dev_dbg(&link->dev, "daqp_cs_config\n");
 
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO;
+
 	ret = pcmcia_loop_config(link, daqp_pcmcia_config_loop, NULL);
 	if (ret) {
 		dev_warn(&link->dev, "no configuration found\n");
@@ -1128,25 +1047,10 @@
 	if (ret)
 		goto failed;
 
-	/*
-	   This actually configures the PCMCIA socket -- setting up
-	   the I/O windows and the interrupt mapping, and putting the
-	   card and host interface into "Memory and IO" mode.
-	 */
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
-	/* Finally, report what we've done */
-	dev_info(&link->dev, "index 0x%02x", link->conf.ConfigIndex);
-	if (link->conf.Attributes & CONF_ENABLE_IRQ)
-		printk(", irq %u", link->irq);
-	if (link->resource[0])
-		printk(" & %pR", link->resource[0]);
-	if (link->resource[1])
-		printk(" & %pR", link->resource[1]);
-	printk("\n");
-
 	return;
 
 failed:
@@ -1161,18 +1065,6 @@
 	pcmcia_disable_device(link);
 }				/* daqp_cs_release */
 
-/*======================================================================
-
-    The card status event handler.  Mostly, this schedules other
-    stuff to run after an event is received.
-
-    When a CARD_REMOVAL event is received, we immediately set a
-    private flag to block future accesses to this device.  All the
-    functions that actually access the device should check this flag
-    to make sure the card is still present.
-
-======================================================================*/
-
 static int daqp_cs_suspend(struct pcmcia_device *link)
 {
 	struct local_info_t *local = link->priv;
@@ -1212,9 +1104,7 @@
 	.resume = daqp_cs_resume,
 	.id_table = daqp_cs_id_table,
 	.owner = THIS_MODULE,
-	.drv = {
-		.name = "quatech_daqp_cs",
-		},
+	.name = "quatech_daqp_cs",
 };
 
 int __init init_module(void)
diff --git a/drivers/staging/crystalhd/crystalhd_lnx.c b/drivers/staging/crystalhd/crystalhd_lnx.c
index fbb80f0..af25899 100644
--- a/drivers/staging/crystalhd/crystalhd_lnx.c
+++ b/drivers/staging/crystalhd/crystalhd_lnx.c
@@ -351,6 +351,7 @@
 	.unlocked_ioctl = chd_dec_ioctl,
 	.open    = chd_dec_open,
 	.release = chd_dec_close,
+	.llseek = noop_llseek,
 };
 
 static int __devinit chd_dec_init_chdev(struct crystalhd_adp *adp)
diff --git a/drivers/staging/cx25821/Kconfig b/drivers/staging/cx25821/Kconfig
index df7756a..813cb35 100644
--- a/drivers/staging/cx25821/Kconfig
+++ b/drivers/staging/cx25821/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_CX25821
 	tristate "Conexant cx25821 support"
 	depends on DVB_CORE && VIDEO_DEV && PCI && I2C && INPUT
+	depends on BKL # please fix
 	select I2C_ALGOBIT
 	select VIDEO_BTCX
 	select VIDEO_TVEEPROM
diff --git a/drivers/staging/dream/camera/msm_camera.c b/drivers/staging/dream/camera/msm_camera.c
index 81bd71f..de4ab61 100644
--- a/drivers/staging/dream/camera/msm_camera.c
+++ b/drivers/staging/dream/camera/msm_camera.c
@@ -1941,6 +1941,7 @@
 	.open = msm_open,
 	.unlocked_ioctl = msm_ioctl_config,
 	.release = msm_release_config,
+	.llseek = no_llseek,
 };
 
 static const struct file_operations msm_fops_control = {
@@ -1948,6 +1949,7 @@
 	.open = msm_open_control,
 	.unlocked_ioctl = msm_ioctl_control,
 	.release = msm_release_control,
+	.llseek = no_llseek,
 };
 
 static const struct file_operations msm_fops_frame = {
@@ -1956,6 +1958,7 @@
 	.unlocked_ioctl = msm_ioctl_frame,
 	.release = msm_release_frame,
 	.poll = msm_poll_frame,
+	.llseek = no_llseek,
 };
 
 static int msm_setup_cdev(struct msm_device *msm,
diff --git a/drivers/staging/dream/pmem.c b/drivers/staging/dream/pmem.c
index 7d6bbad..3640d1f 100644
--- a/drivers/staging/dream/pmem.c
+++ b/drivers/staging/dream/pmem.c
@@ -180,6 +180,7 @@
 	.mmap = pmem_mmap,
 	.open = pmem_open,
 	.unlocked_ioctl = pmem_ioctl,
+	.llseek = noop_llseek,
 };
 
 static int get_id(struct file *file)
@@ -1204,6 +1205,7 @@
 static struct file_operations debug_fops = {
 	.read = debug_read,
 	.open = debug_open,
+	.llseek = default_llseek,
 };
 #endif
 
diff --git a/drivers/staging/dream/qdsp5/adsp_driver.c b/drivers/staging/dream/qdsp5/adsp_driver.c
index 8197765..28a6f8d 100644
--- a/drivers/staging/dream/qdsp5/adsp_driver.c
+++ b/drivers/staging/dream/qdsp5/adsp_driver.c
@@ -582,6 +582,7 @@
 	.open = adsp_open,
 	.unlocked_ioctl = adsp_ioctl,
 	.release = adsp_release,
+	.llseek = no_llseek,
 };
 
 static void adsp_create(struct adsp_device *adev, const char *name,
diff --git a/drivers/staging/dream/qdsp5/audio_aac.c b/drivers/staging/dream/qdsp5/audio_aac.c
index a373f35..45f4c78 100644
--- a/drivers/staging/dream/qdsp5/audio_aac.c
+++ b/drivers/staging/dream/qdsp5/audio_aac.c
@@ -1030,6 +1030,7 @@
 	.read = audio_read,
 	.write = audio_write,
 	.unlocked_ioctl = audio_ioctl,
+	.llseek = noop_llseek,
 };
 
 struct miscdevice audio_aac_misc = {
diff --git a/drivers/staging/dream/qdsp5/audio_amrnb.c b/drivers/staging/dream/qdsp5/audio_amrnb.c
index 07b79d5..402bbc1 100644
--- a/drivers/staging/dream/qdsp5/audio_amrnb.c
+++ b/drivers/staging/dream/qdsp5/audio_amrnb.c
@@ -841,6 +841,7 @@
 	.read = audamrnb_read,
 	.write = audamrnb_write,
 	.unlocked_ioctl = audamrnb_ioctl,
+	.llseek = noop_llseek,
 };
 
 struct miscdevice audio_amrnb_misc = {
diff --git a/drivers/staging/dream/qdsp5/audio_evrc.c b/drivers/staging/dream/qdsp5/audio_evrc.c
index ad989ee..24a8926 100644
--- a/drivers/staging/dream/qdsp5/audio_evrc.c
+++ b/drivers/staging/dream/qdsp5/audio_evrc.c
@@ -813,6 +813,7 @@
 	.read = audevrc_read,
 	.write = audevrc_write,
 	.unlocked_ioctl = audevrc_ioctl,
+	.llseek = noop_llseek,
 };
 
 struct miscdevice audio_evrc_misc = {
diff --git a/drivers/staging/dream/qdsp5/audio_in.c b/drivers/staging/dream/qdsp5/audio_in.c
index 6ae48e7..b51fa09 100644
--- a/drivers/staging/dream/qdsp5/audio_in.c
+++ b/drivers/staging/dream/qdsp5/audio_in.c
@@ -921,12 +921,14 @@
 	.read		= audio_in_read,
 	.write		= audio_in_write,
 	.unlocked_ioctl	= audio_in_ioctl,
+	.llseek		= noop_llseek,
 };
 
 static struct file_operations audpre_fops = {
 	.owner          = THIS_MODULE,
 	.open           = audpre_open,
 	.unlocked_ioctl = audpre_ioctl,
+	.llseek		= noop_llseek,
 };
 
 struct miscdevice audio_in_misc = {
diff --git a/drivers/staging/dream/qdsp5/audio_mp3.c b/drivers/staging/dream/qdsp5/audio_mp3.c
index 530e1f3..409a19c 100644
--- a/drivers/staging/dream/qdsp5/audio_mp3.c
+++ b/drivers/staging/dream/qdsp5/audio_mp3.c
@@ -948,6 +948,7 @@
 	.read		= audio_read,
 	.write		= audio_write,
 	.unlocked_ioctl	= audio_ioctl,
+	.llseek		= noop_llseek,
 };
 
 struct miscdevice audio_mp3_misc = {
diff --git a/drivers/staging/dream/qdsp5/audio_out.c b/drivers/staging/dream/qdsp5/audio_out.c
index 76d7fa5..d20e895 100644
--- a/drivers/staging/dream/qdsp5/audio_out.c
+++ b/drivers/staging/dream/qdsp5/audio_out.c
@@ -807,12 +807,14 @@
 	.read		= audio_read,
 	.write		= audio_write,
 	.unlocked_ioctl	= audio_ioctl,
+	.llseek		= noop_llseek,
 };
 
 static struct file_operations audpp_fops = {
 	.owner		= THIS_MODULE,
 	.open		= audpp_open,
 	.unlocked_ioctl	= audpp_ioctl,
+	.llseek		= noop_llseek,
 };
 
 struct miscdevice audio_misc = {
diff --git a/drivers/staging/dream/qdsp5/audio_qcelp.c b/drivers/staging/dream/qdsp5/audio_qcelp.c
index effa96f3..911bab4 100644
--- a/drivers/staging/dream/qdsp5/audio_qcelp.c
+++ b/drivers/staging/dream/qdsp5/audio_qcelp.c
@@ -824,6 +824,7 @@
 	.read = audqcelp_read,
 	.write = audqcelp_write,
 	.unlocked_ioctl = audqcelp_ioctl,
+	.llseek = noop_llseek,
 };
 
 struct miscdevice audio_qcelp_misc = {
diff --git a/drivers/staging/dream/qdsp5/evlog.h b/drivers/staging/dream/qdsp5/evlog.h
index 922ce67..e5ab86b 100644
--- a/drivers/staging/dream/qdsp5/evlog.h
+++ b/drivers/staging/dream/qdsp5/evlog.h
@@ -123,6 +123,7 @@
 static const struct file_operations ev_log_ops = {
 	.read = ev_log_read,
 	.open = ev_log_open,
+	.llseek = default_llseek,
 };
 
 static int ev_log_init(struct ev_log *log)
diff --git a/drivers/staging/dream/qdsp5/snd.c b/drivers/staging/dream/qdsp5/snd.c
index 037d7ff..e0f2f7b 100644
--- a/drivers/staging/dream/qdsp5/snd.c
+++ b/drivers/staging/dream/qdsp5/snd.c
@@ -247,6 +247,7 @@
 	.open		= snd_open,
 	.release	= snd_release,
 	.unlocked_ioctl	= snd_ioctl,
+	.llseek		= noop_llseek,
 };
 
 struct miscdevice snd_misc = {
diff --git a/drivers/staging/easycap/Kconfig b/drivers/staging/easycap/Kconfig
index bd96f39..9d5fe4d 100644
--- a/drivers/staging/easycap/Kconfig
+++ b/drivers/staging/easycap/Kconfig
@@ -1,6 +1,7 @@
 config EASYCAP
 	tristate "EasyCAP USB ID 05e1:0408 support"
 	depends on USB && VIDEO_DEV
+	depends on BKL # please fix
 
 	---help---
 	  This is an integrated audio/video driver for EasyCAP cards with
diff --git a/drivers/staging/frontier/alphatrack.c b/drivers/staging/frontier/alphatrack.c
index 4e52105..689099b 100644
--- a/drivers/staging/frontier/alphatrack.c
+++ b/drivers/staging/frontier/alphatrack.c
@@ -641,6 +641,7 @@
 	.open = usb_alphatrack_open,
 	.release = usb_alphatrack_release,
 	.poll = usb_alphatrack_poll,
+	.llseek = no_llseek,
 };
 
 /*
diff --git a/drivers/staging/frontier/tranzport.c b/drivers/staging/frontier/tranzport.c
index eed74f0..3d12c17 100644
--- a/drivers/staging/frontier/tranzport.c
+++ b/drivers/staging/frontier/tranzport.c
@@ -767,6 +767,7 @@
 	.open = usb_tranzport_open,
 	.release = usb_tranzport_release,
 	.poll = usb_tranzport_poll,
+	.llseek = no_llseek,
 };
 
 /*
diff --git a/drivers/staging/go7007/Kconfig b/drivers/staging/go7007/Kconfig
index e47f683..75fa468 100644
--- a/drivers/staging/go7007/Kconfig
+++ b/drivers/staging/go7007/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_GO7007
 	tristate "WIS GO7007 MPEG encoder support"
 	depends on VIDEO_DEV && PCI && I2C && INPUT
+	depends on BKL # please fix
 	depends on SND
 	select VIDEOBUF_DMA_SG
 	select VIDEO_IR
diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c
index ff1d247..8284297 100644
--- a/drivers/staging/hv/blkvsc_drv.c
+++ b/drivers/staging/hv/blkvsc_drv.c
@@ -25,7 +25,7 @@
 #include <linux/major.h>
 #include <linux/delay.h>
 #include <linux/hdreg.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -124,6 +124,7 @@
 };
 
 /* Static decl */
+static DEFINE_MUTEX(blkvsc_mutex);
 static int blkvsc_probe(struct device *dev);
 static int blkvsc_remove(struct device *device);
 static void blkvsc_shutdown(struct device *device);
@@ -1309,7 +1310,7 @@
 	DPRINT_DBG(BLKVSC_DRV, "- users %d disk %s\n", blkdev->users,
 		   blkdev->gd->disk_name);
 
-	lock_kernel();
+	mutex_lock(&blkvsc_mutex);
 	spin_lock(&blkdev->lock);
 
 	if (!blkdev->users && blkdev->device_type == DVD_TYPE) {
@@ -1321,7 +1322,7 @@
 	blkdev->users++;
 
 	spin_unlock(&blkdev->lock);
-	unlock_kernel();
+	mutex_unlock(&blkvsc_mutex);
 	return 0;
 }
 
@@ -1332,7 +1333,7 @@
 	DPRINT_DBG(BLKVSC_DRV, "- users %d disk %s\n", blkdev->users,
 		   blkdev->gd->disk_name);
 
-	lock_kernel();
+	mutex_lock(&blkvsc_mutex);
 	spin_lock(&blkdev->lock);
 	if (blkdev->users == 1) {
 		spin_unlock(&blkdev->lock);
@@ -1343,7 +1344,7 @@
 	blkdev->users--;
 
 	spin_unlock(&blkdev->lock);
-	unlock_kernel();
+	mutex_unlock(&blkvsc_mutex);
 	return 0;
 }
 
diff --git a/drivers/staging/iio/industrialio-core.c b/drivers/staging/iio/industrialio-core.c
index dd4d87a..92a212f 100644
--- a/drivers/staging/iio/industrialio-core.c
+++ b/drivers/staging/iio/industrialio-core.c
@@ -349,6 +349,7 @@
 	.release = iio_event_chrdev_release,
 	.open = iio_event_chrdev_open,
 	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 static void iio_event_dev_release(struct device *dev)
diff --git a/drivers/staging/iio/industrialio-ring.c b/drivers/staging/iio/industrialio-ring.c
index 6ab578e..1c5f672 100644
--- a/drivers/staging/iio/industrialio-ring.c
+++ b/drivers/staging/iio/industrialio-ring.c
@@ -133,6 +133,7 @@
 	.release = iio_ring_release,
 	.open = iio_ring_open,
 	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 /**
diff --git a/drivers/staging/lirc/lirc_imon.c b/drivers/staging/lirc/lirc_imon.c
index 6649325..ed5c5fe 100644
--- a/drivers/staging/lirc/lirc_imon.c
+++ b/drivers/staging/lirc/lirc_imon.c
@@ -115,7 +115,8 @@
 	.owner		= THIS_MODULE,
 	.open		= &display_open,
 	.write		= &vfd_write,
-	.release	= &display_close
+	.release	= &display_close,
+	.llseek		= noop_llseek,
 };
 
 /*
diff --git a/drivers/staging/lirc/lirc_it87.c b/drivers/staging/lirc/lirc_it87.c
index ec11c0e..543c5c3b 100644
--- a/drivers/staging/lirc/lirc_it87.c
+++ b/drivers/staging/lirc/lirc_it87.c
@@ -342,6 +342,7 @@
 	.unlocked_ioctl	= lirc_ioctl,
 	.open		= lirc_open,
 	.release	= lirc_close,
+	.llseek		= noop_llseek,
 };
 
 static int set_use_inc(void *data)
diff --git a/drivers/staging/lirc/lirc_sasem.c b/drivers/staging/lirc/lirc_sasem.c
index 73166c3..8f72a84 100644
--- a/drivers/staging/lirc/lirc_sasem.c
+++ b/drivers/staging/lirc/lirc_sasem.c
@@ -125,6 +125,7 @@
 	.write		= &vfd_write,
 	.unlocked_ioctl	= &vfd_ioctl,
 	.release	= &vfd_close,
+	.llseek		= noop_llseek,
 };
 
 /* USB Device ID for Sasem USB Control Board */
diff --git a/drivers/staging/lirc/lirc_serial.c b/drivers/staging/lirc/lirc_serial.c
index 9456f8e..8da3824 100644
--- a/drivers/staging/lirc/lirc_serial.c
+++ b/drivers/staging/lirc/lirc_serial.c
@@ -1058,6 +1058,7 @@
 	.poll		= lirc_dev_fop_poll,
 	.open		= lirc_dev_fop_open,
 	.release	= lirc_dev_fop_close,
+	.llseek		= no_llseek,
 };
 
 static struct lirc_driver driver = {
diff --git a/drivers/staging/lirc/lirc_sir.c b/drivers/staging/lirc/lirc_sir.c
index eb08fa7..2478871 100644
--- a/drivers/staging/lirc/lirc_sir.c
+++ b/drivers/staging/lirc/lirc_sir.c
@@ -459,6 +459,7 @@
 	.unlocked_ioctl	= lirc_ioctl,
 	.open		= lirc_dev_fop_open,
 	.release	= lirc_dev_fop_close,
+	.llseek		= no_llseek,
 };
 
 static int set_use_inc(void *data)
diff --git a/drivers/staging/memrar/memrar_handler.c b/drivers/staging/memrar/memrar_handler.c
index a98b3f1..cfcaa8e 100644
--- a/drivers/staging/memrar/memrar_handler.c
+++ b/drivers/staging/memrar/memrar_handler.c
@@ -890,6 +890,7 @@
 	.mmap           = memrar_mmap,
 	.open           = memrar_open,
 	.release        = memrar_release,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice memrar_miscdev = {
diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c
index 3221814..6885f9a 100644
--- a/drivers/staging/panel/panel.c
+++ b/drivers/staging/panel/panel.c
@@ -1631,6 +1631,7 @@
 	.read    = keypad_read,		/* read */
 	.open    = keypad_open,		/* open */
 	.release = keypad_release,	/* close */
+	.llseek  = default_llseek,
 };
 
 static struct miscdevice keypad_dev = {
diff --git a/drivers/staging/spectra/ffsport.c b/drivers/staging/spectra/ffsport.c
index fa21a0f..c7932da 100644
--- a/drivers/staging/spectra/ffsport.c
+++ b/drivers/staging/spectra/ffsport.c
@@ -27,7 +27,6 @@
 #include <linux/kthread.h>
 #include <linux/log2.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 
 /**** Helper functions used for Div, Remainder operation on u64 ****/
@@ -590,14 +589,16 @@
 	return -ENOTTY;
 }
 
+static DEFINE_MUTEX(ffsport_mutex);
+
 int GLOB_SBD_unlocked_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, unsigned long arg)
 {
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&ffsport_mutex);
 	ret = GLOB_SBD_ioctl(bdev, mode, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ffsport_mutex);
 
 	return ret;
 }
diff --git a/drivers/staging/tidspbridge/rmgr/drv_interface.c b/drivers/staging/tidspbridge/rmgr/drv_interface.c
index 7ee8949..7b3a7d0 100644
--- a/drivers/staging/tidspbridge/rmgr/drv_interface.c
+++ b/drivers/staging/tidspbridge/rmgr/drv_interface.c
@@ -144,6 +144,7 @@
 	.release = bridge_release,
 	.unlocked_ioctl = bridge_ioctl,
 	.mmap = bridge_mmap,
+	.llseek = noop_llseek,
 };
 
 #ifdef CONFIG_PM
diff --git a/drivers/staging/usbip/Kconfig b/drivers/staging/usbip/Kconfig
index 2c1d10a..b11ec37 100644
--- a/drivers/staging/usbip/Kconfig
+++ b/drivers/staging/usbip/Kconfig
@@ -1,6 +1,6 @@
 config USB_IP_COMMON
 	tristate "USB IP support (EXPERIMENTAL)"
-	depends on USB && NET && EXPERIMENTAL
+	depends on USB && NET && EXPERIMENTAL && BKL
 	default N
 	---help---
 	  This enables pushing USB packets over IP to allow remote
diff --git a/drivers/staging/wlags49_h2/wl_cs.c b/drivers/staging/wlags49_h2/wl_cs.c
index 19c3354..6555891 100644
--- a/drivers/staging/wlags49_h2/wl_cs.c
+++ b/drivers/staging/wlags49_h2/wl_cs.c
@@ -83,7 +83,6 @@
 #include <linux/if_arp.h>
 #include <linux/ioport.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ciscode.h>
@@ -147,10 +146,9 @@
 
 	link->resource[0]->end  = HCF_NUM_IO_PORTS;
 	link->resource[0]->flags= IO_DATA_PATH_WIDTH_16;
-	link->conf.Attributes   = CONF_ENABLE_IRQ;
-	link->conf.IntType      = INT_MEMORY_AND_IO;
-	link->conf.ConfigIndex  = 5;
-	link->conf.Present      = PRESENT_OPTION;
+	link->config_flags     |= CONF_ENABLE_IRQ;
+	link->config_index      = 5;
+	link->config_regs       = PRESENT_OPTION;
 
 	link->priv = dev;
 	lp = wl_priv(dev);
@@ -165,27 +163,6 @@
 
 
 
-/*******************************************************************************
- *	wl_adapter_detach()
- *******************************************************************************
- *
- *  DESCRIPTION:
- *
- *      This deletes a driver "instance". The device is de-registered with Card
- *  Services. If it has been released, then the net device is unregistered, and
- *  all local data structures are freed. Otherwise, the structures will be
- *  freed when the device is released.
- *
- *  PARAMETERS:
- *
- *      link    - pointer to the dev_link_t structure representing the device to
- *                detach
- *
- *  RETURNS:
- *
- *      N/A
- *
- ******************************************************************************/
 static void wl_adapter_detach(struct pcmcia_device *link)
 {
 	struct net_device   *dev = link->priv;
@@ -209,26 +186,6 @@
 /*============================================================================*/
 
 
-/*******************************************************************************
- *	wl_adapter_release()
- *******************************************************************************
- *
- *  DESCRIPTION:
- *
- *      After a card is removed, this routine will release the PCMCIA
- *  configuration. If the device is still open, this will be postponed until it
- *  is closed.
- *
- *  PARAMETERS:
- *
- *      arg - a u_long representing a pointer to a dev_link_t structure for the
- *            device to be released.
- *
- *  RETURNS:
- *
- *      N/A
- *
- ******************************************************************************/
 void wl_adapter_release(struct pcmcia_device *link)
 {
 	DBG_FUNC("wl_adapter_release");
@@ -268,26 +225,6 @@
 	return 0;
 } /* wl_adapter_resume */
 
-/*******************************************************************************
- *	wl_adapter_insert()
- *******************************************************************************
- *
- *  DESCRIPTION:
- *
- *      wl_adapter_insert() is scheduled to run after a CARD_INSERTION event is
- *  received, to configure the PCMCIA socket, and to make the ethernet device
- *  available to the system.
- *
- *  PARAMETERS:
- *
- *      link    - pointer to the dev_link_t structure representing the device to
- *                insert
- *
- *  RETURNS:
- *
- *      N/A
- *
- ******************************************************************************/
 void wl_adapter_insert(struct pcmcia_device *link)
 {
 	struct net_device *dev;
@@ -302,7 +239,7 @@
 	dev     = link->priv;
 
 	/* Do we need to allocate an interrupt? */
-	link->conf.Attributes |= CONF_ENABLE_IRQ;
+	link->config_flags |= CONF_ENABLE_IRQ;
 	link->io_lines = 6;
 
 	ret = pcmcia_request_io(link);
@@ -313,7 +250,7 @@
 	if (ret != 0)
 		goto failed;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret != 0)
 		goto failed;
 
@@ -457,9 +394,7 @@
 
 static struct pcmcia_driver wlags49_driver = {
 	.owner	    = THIS_MODULE,
-	.drv	    = {
-		.name = DRIVER_NAME,
-	},
+	.name	    = DRIVER_NAME,
 	.probe	    = wl_adapter_attach,
 	.remove	    = wl_adapter_detach,
 	.id_table   = wl_adapter_ids,
diff --git a/drivers/staging/wlags49_h2/wl_internal.h b/drivers/staging/wlags49_h2/wl_internal.h
index 02f0a20..cd129b3 100644
--- a/drivers/staging/wlags49_h2/wl_internal.h
+++ b/drivers/staging/wlags49_h2/wl_internal.h
@@ -69,7 +69,6 @@
  ******************************************************************************/
 #include <linux/version.h>
 #ifdef BUS_PCMCIA
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ciscode.h>
diff --git a/drivers/staging/wlags49_h2/wl_main.c b/drivers/staging/wlags49_h2/wl_main.c
index 88d0d47..8e3536a 100644
--- a/drivers/staging/wlags49_h2/wl_main.c
+++ b/drivers/staging/wlags49_h2/wl_main.c
@@ -414,25 +414,6 @@
 #endif /* HCF_STA */
 
 
-/*******************************************************************************
- *	wl_insert()
- *******************************************************************************
- *
- *  DESCRIPTION:
- *
- *      wl_insert() is scheduled to run after a CARD_INSERTION event is
- *  received, to configure the PCMCIA socket, and to make the ethernet device
- *  available to the system.
- *
- *  PARAMETERS:
- *
- *      dev - a pointer to the net_device struct of the wireless device
- *
- *  RETURNS:
- *
- *      TRUE or FALSE
- *
- ******************************************************************************/
 int wl_insert( struct net_device *dev )
 {
 	int                     result = 0;
diff --git a/drivers/telephony/ixj.c b/drivers/telephony/ixj.c
index b53deee..0d236f4 100644
--- a/drivers/telephony/ixj.c
+++ b/drivers/telephony/ixj.c
@@ -257,7 +257,7 @@
 #include <linux/fs.h>		/* everything... */
 #include <linux/errno.h>	/* error codes */
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/mm.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
@@ -277,6 +277,7 @@
 #define TYPE(inode) (iminor(inode) >> 4)
 #define NUM(inode) (iminor(inode) & 0xf)
 
+static DEFINE_MUTEX(ixj_mutex);
 static int ixjdebug;
 static int hertz = HZ;
 static int samplerate = 100;
@@ -6655,9 +6656,9 @@
 static long ixj_ioctl(struct file *file_p, unsigned int cmd, unsigned long arg)
 {
 	long ret;
-	lock_kernel();
+	mutex_lock(&ixj_mutex);
 	ret = do_ixj_ioctl(file_p, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&ixj_mutex);
 	return ret;
 }
 
@@ -6676,7 +6677,8 @@
         .poll           = ixj_poll,
         .unlocked_ioctl = ixj_ioctl,
         .release        = ixj_release,
-        .fasync         = ixj_fasync
+        .fasync         = ixj_fasync,
+        .llseek	 = default_llseek,
 };
 
 static int ixj_linetest(IXJ *j)
diff --git a/drivers/telephony/ixj_pcmcia.c b/drivers/telephony/ixj_pcmcia.c
index a1900e5..d005b9e 100644
--- a/drivers/telephony/ixj_pcmcia.c
+++ b/drivers/telephony/ixj_pcmcia.c
@@ -8,7 +8,6 @@
 #include <linux/errno.h>	/* error codes */
 #include <linux/slab.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
@@ -32,9 +31,6 @@
 {
 	dev_dbg(&p_dev->dev, "ixj_attach()\n");
 	/* Create new ixj device */
-	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-	p_dev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
-	p_dev->conf.IntType = INT_MEMORY_AND_IO;
 	p_dev->priv = kzalloc(sizeof(struct ixj_info_t), GFP_KERNEL);
 	if (!p_dev->priv) {
 		return -ENOMEM;
@@ -111,40 +107,31 @@
 	return;
 }
 
-static int ixj_config_check(struct pcmcia_device *p_dev,
-			    cistpl_cftable_entry_t *cfg,
-			    cistpl_cftable_entry_t *dflt,
-			    unsigned int vcc,
-			    void *priv_data)
+static int ixj_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-		p_dev->io_lines = 3;
-		if (io->nwin == 2) {
-			p_dev->resource[1]->start = io->win[1].base;
-			p_dev->resource[1]->end = io->win[1].len;
-		}
-		if (!pcmcia_request_io(p_dev))
-			return 0;
-	}
-	return -ENODEV;
+	p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->resource[1]->flags &= ~IO_DATA_PATH_WIDTH;
+	p_dev->resource[1]->flags |= IO_DATA_PATH_WIDTH_8;
+	p_dev->io_lines = 3;
+
+	return pcmcia_request_io(p_dev);
 }
 
 static int ixj_config(struct pcmcia_device * link)
 {
 	IXJ *j;
 	ixj_info_t *info;
-	cistpl_cftable_entry_t dflt = { 0 };
 
 	info = link->priv;
 	dev_dbg(&link->dev, "ixj_config\n");
 
-	if (pcmcia_loop_config(link, ixj_config_check, &dflt))
+	link->config_flags = CONF_AUTO_SET_IO;
+
+	if (pcmcia_loop_config(link, ixj_config_check, NULL))
 		goto failed;
 
-	if (pcmcia_request_configuration(link, &link->conf))
+	if (pcmcia_enable_device(link))
 		goto failed;
 
 	/*
@@ -178,9 +165,7 @@
 
 static struct pcmcia_driver ixj_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "ixj_cs",
-	},
+	.name		= "ixj_cs",
 	.probe		= ixj_probe,
 	.remove		= ixj_detach,
 	.id_table	= ixj_ids,
diff --git a/drivers/telephony/phonedev.c b/drivers/telephony/phonedev.c
index f3873f6..1915af2 100644
--- a/drivers/telephony/phonedev.c
+++ b/drivers/telephony/phonedev.c
@@ -130,6 +130,7 @@
 {
 	.owner		= THIS_MODULE,
 	.open		= phone_open,
+	.llseek		= noop_llseek,
 };
 
 /*
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index bff1afb..4d3a6fd 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -740,6 +740,7 @@
 	.mmap		= uio_mmap,
 	.poll		= uio_poll,
 	.fasync		= uio_fasync,
+	.llseek		= noop_llseek,
 };
 
 static int uio_major_init(void)
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 094c76b..6ee4451 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -584,7 +584,8 @@
 	.open =		wdm_open,
 	.flush =	wdm_flush,
 	.release =	wdm_release,
-	.poll =		wdm_poll
+	.poll =		wdm_poll,
+	.llseek =	noop_llseek,
 };
 
 static struct usb_class_driver wdm_class = {
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index e325162..9eca405 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -1043,6 +1043,7 @@
 	.compat_ioctl =		usblp_ioctl,
 	.open =		usblp_open,
 	.release =	usblp_release,
+	.llseek =	noop_llseek,
 };
 
 static char *usblp_devnode(struct device *dev, mode_t *mode)
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 3e7c1b8..6a54634 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -987,6 +987,7 @@
 	.open		= usbtmc_open,
 	.release	= usbtmc_release,
 	.unlocked_ioctl	= usbtmc_ioctl,
+	.llseek		= default_llseek,
 };
 
 static struct usb_class_driver usbtmc_class = {
diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c
index 1e6ccef..9fe34fb 100644
--- a/drivers/usb/core/file.c
+++ b/drivers/usb/core/file.c
@@ -59,6 +59,7 @@
 static const struct file_operations usb_fops = {
 	.owner =	THIS_MODULE,
 	.open =		usb_open,
+	.llseek =	noop_llseek,
 };
 
 static struct usb_class {
diff --git a/drivers/usb/gadget/f_hid.c b/drivers/usb/gadget/f_hid.c
index 53e1202..2b98bd2 100644
--- a/drivers/usb/gadget/f_hid.c
+++ b/drivers/usb/gadget/f_hid.c
@@ -451,6 +451,7 @@
 	.write		= f_hidg_write,
 	.read		= f_hidg_read,
 	.poll		= f_hidg_poll,
+	.llseek		= noop_llseek,
 };
 
 static int __init hidg_bind(struct usb_configuration *c, struct usb_function *f)
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index fc35406..3f1d771 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -33,7 +33,6 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
-#include <linux/smp_lock.h>
 
 #include <linux/device.h>
 #include <linux/moduleparam.h>
diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c
index cf241c3..327a92a 100644
--- a/drivers/usb/gadget/printer.c
+++ b/drivers/usb/gadget/printer.c
@@ -884,7 +884,8 @@
 	.fsync =	printer_fsync,
 	.poll =		printer_poll,
 	.unlocked_ioctl = printer_ioctl,
-	.release =	printer_close
+	.release =	printer_close,
+	.llseek =	noop_llseek,
 };
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/host/ehci-dbg.c b/drivers/usb/host/ehci-dbg.c
index 76b7fd2..86afdc7 100644
--- a/drivers/usb/host/ehci-dbg.c
+++ b/drivers/usb/host/ehci-dbg.c
@@ -369,18 +369,21 @@
 	.open		= debug_async_open,
 	.read		= debug_output,
 	.release	= debug_close,
+	.llseek		= default_llseek,
 };
 static const struct file_operations debug_periodic_fops = {
 	.owner		= THIS_MODULE,
 	.open		= debug_periodic_open,
 	.read		= debug_output,
 	.release	= debug_close,
+	.llseek		= default_llseek,
 };
 static const struct file_operations debug_registers_fops = {
 	.owner		= THIS_MODULE,
 	.open		= debug_registers_open,
 	.read		= debug_output,
 	.release	= debug_close,
+	.llseek		= default_llseek,
 };
 static const struct file_operations debug_lpm_fops = {
 	.owner		= THIS_MODULE,
@@ -388,6 +391,7 @@
 	.read		= debug_lpm_read,
 	.write		= debug_lpm_write,
 	.release	= debug_lpm_close,
+	.llseek		= noop_llseek,
 };
 
 static struct dentry *ehci_debug_root;
diff --git a/drivers/usb/host/ohci-dbg.c b/drivers/usb/host/ohci-dbg.c
index 36abd2b..d7d3449 100644
--- a/drivers/usb/host/ohci-dbg.c
+++ b/drivers/usb/host/ohci-dbg.c
@@ -413,18 +413,21 @@
 	.open		= debug_async_open,
 	.read		= debug_output,
 	.release	= debug_close,
+	.llseek		= default_llseek,
 };
 static const struct file_operations debug_periodic_fops = {
 	.owner		= THIS_MODULE,
 	.open		= debug_periodic_open,
 	.read		= debug_output,
 	.release	= debug_close,
+	.llseek		= default_llseek,
 };
 static const struct file_operations debug_registers_fops = {
 	.owner		= THIS_MODULE,
 	.open		= debug_registers_open,
 	.read		= debug_output,
 	.release	= debug_close,
+	.llseek		= default_llseek,
 };
 
 static struct dentry *ohci_debug_root;
diff --git a/drivers/usb/host/ohci-pxa27x.c b/drivers/usb/host/ohci-pxa27x.c
index 4181638..afef7b0 100644
--- a/drivers/usb/host/ohci-pxa27x.c
+++ b/drivers/usb/host/ohci-pxa27x.c
@@ -24,6 +24,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <mach/ohci.h>
+#include <mach/pxa3xx-u2d.h>
 
 /*
  * UHC: USB Host Controller (OHCI-like) register definitions
@@ -235,6 +236,9 @@
 	if (retval < 0)
 		return retval;
 
+	if (cpu_is_pxa3xx())
+		pxa3xx_u2d_start_hc(&ohci_to_hcd(&ohci->ohci)->self);
+
 	uhchr = __raw_readl(ohci->mmio_base + UHCHR) & ~UHCHR_SSE;
 	__raw_writel(uhchr, ohci->mmio_base + UHCHR);
 	__raw_writel(UHCHIE_UPRIE | UHCHIE_RWIE, ohci->mmio_base + UHCHIE);
@@ -251,6 +255,9 @@
 
 	inf = dev->platform_data;
 
+	if (cpu_is_pxa3xx())
+		pxa3xx_u2d_stop_hc(&ohci_to_hcd(&ohci->ohci)->self);
+
 	if (inf->exit)
 		inf->exit(dev);
 
diff --git a/drivers/usb/host/sl811_cs.c b/drivers/usb/host/sl811_cs.c
index 0e13a00..3775c03 100644
--- a/drivers/usb/host/sl811_cs.c
+++ b/drivers/usb/host/sl811_cs.c
@@ -20,7 +20,6 @@
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/cisreg.h>
 #include <pcmcia/ds.h>
@@ -132,49 +131,12 @@
 	platform_device_unregister(&platform_dev);
 }
 
-static int sl811_cs_config_check(struct pcmcia_device *p_dev,
-				 cistpl_cftable_entry_t *cfg,
-				 cistpl_cftable_entry_t *dflt,
-				 unsigned int vcc,
-				 void *priv_data)
+static int sl811_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
 {
-	if (cfg->index == 0)
-		return -ENODEV;
+	if (p_dev->config_index == 0)
+		return -EINVAL;
 
-	/* Use power settings for Vcc and Vpp if present */
-	/*  Note that the CIS values need to be rescaled */
-	if (cfg->vcc.present & (1<<CISTPL_POWER_VNOM)) {
-		if (cfg->vcc.param[CISTPL_POWER_VNOM]/10000 != vcc)
-			return -ENODEV;
-	} else if (dflt->vcc.present & (1<<CISTPL_POWER_VNOM)) {
-		if (dflt->vcc.param[CISTPL_POWER_VNOM]/10000 != vcc)
-			return -ENODEV;
-		}
-
-	if (cfg->vpp1.present & (1<<CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp =
-			cfg->vpp1.param[CISTPL_POWER_VNOM]/10000;
-	else if (dflt->vpp1.present & (1<<CISTPL_POWER_VNOM))
-		p_dev->conf.Vpp =
-			dflt->vpp1.param[CISTPL_POWER_VNOM]/10000;
-
-	/* we need an interrupt */
-	p_dev->conf.Attributes |= CONF_ENABLE_IRQ;
-
-	/* IO window settings */
-	p_dev->resource[0]->end = p_dev->resource[1]->end = 0;
-	if ((cfg->io.nwin > 0) || (dflt->io.nwin > 0)) {
-		cistpl_io_t *io = (cfg->io.nwin) ? &cfg->io : &dflt->io;
-		p_dev->io_lines = io->flags & CISTPL_IO_LINES_MASK;
-
-		p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8;
-		p_dev->resource[0]->start = io->win[0].base;
-		p_dev->resource[0]->end = io->win[0].len;
-
-		return pcmcia_request_io(p_dev);
-	}
-	pcmcia_disable_device(p_dev);
-	return -ENODEV;
+	return pcmcia_request_io(p_dev);
 }
 
 
@@ -185,6 +147,9 @@
 
 	dev_dbg(&link->dev, "sl811_cs_config\n");
 
+	link->config_flags |= CONF_ENABLE_IRQ |	CONF_AUTO_SET_VPP |
+		CONF_AUTO_CHECK_VCC | CONF_AUTO_SET_IO;
+
 	if (pcmcia_loop_config(link, sl811_cs_config_check, NULL))
 		goto failed;
 
@@ -195,18 +160,10 @@
 	if (!link->irq)
 		goto failed;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
-	dev_info(&link->dev, "index 0x%02x: ",
-		link->conf.ConfigIndex);
-	if (link->conf.Vpp)
-		printk(", Vpp %d.%d", link->conf.Vpp/10, link->conf.Vpp%10);
-	printk(", irq %d", link->irq);
-	printk(", io %pR", link->resource[0]);
-	printk("\n");
-
 	if (sl811_hc_init(parent, link->resource[0]->start, link->irq)
 			< 0) {
 failed:
@@ -227,9 +184,6 @@
 	local->p_dev = link;
 	link->priv = local;
 
-	link->conf.Attributes = 0;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-
 	return sl811_cs_config(link);
 }
 
@@ -241,9 +195,7 @@
 
 static struct pcmcia_driver sl811_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "sl811_cs",
-	},
+	.name		= "sl811_cs",
 	.probe		= sl811_cs_probe,
 	.remove		= sl811_cs_detach,
 	.id_table	= sl811_ids,
diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c
index e192e8f..575b56c 100644
--- a/drivers/usb/image/mdc800.c
+++ b/drivers/usb/image/mdc800.c
@@ -963,6 +963,7 @@
 	.write =	mdc800_device_write,
 	.open =		mdc800_device_open,
 	.release =	mdc800_device_release,
+	.llseek =	noop_llseek,
 };
 
 
diff --git a/drivers/usb/misc/adutux.c b/drivers/usb/misc/adutux.c
index 801324a..44f8b922 100644
--- a/drivers/usb/misc/adutux.c
+++ b/drivers/usb/misc/adutux.c
@@ -679,6 +679,7 @@
 	.write = adu_write,
 	.open = adu_open,
 	.release = adu_release,
+	.llseek = noop_llseek,
 };
 
 /*
diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c
index a54c3cb..c6184b4 100644
--- a/drivers/usb/misc/idmouse.c
+++ b/drivers/usb/misc/idmouse.c
@@ -105,6 +105,7 @@
 	.read = idmouse_read,
 	.open = idmouse_open,
 	.release = idmouse_release,
+	.llseek = default_llseek,
 };
 
 /* class driver information */
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index bc88c79..9b50db2 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -730,6 +730,7 @@
 	.open = iowarrior_open,
 	.release = iowarrior_release,
 	.poll = iowarrior_poll,
+	.llseek = noop_llseek,
 };
 
 static char *iowarrior_devnode(struct device *dev, mode_t *mode)
diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c
index dd41d87..edffef6 100644
--- a/drivers/usb/misc/ldusb.c
+++ b/drivers/usb/misc/ldusb.c
@@ -613,6 +613,7 @@
 	.open =		ld_usb_open,
 	.release =	ld_usb_release,
 	.poll =		ld_usb_poll,
+	.llseek =	no_llseek,
 };
 
 /*
diff --git a/drivers/usb/misc/rio500.c b/drivers/usb/misc/rio500.c
index cc13ae6..4e23d38 100644
--- a/drivers/usb/misc/rio500.c
+++ b/drivers/usb/misc/rio500.c
@@ -439,6 +439,7 @@
 	.unlocked_ioctl = ioctl_rio,
 	.open =		open_rio,
 	.release =	close_rio,
+	.llseek =	noop_llseek,
 };
 
 static struct usb_class_driver usb_rio_class = {
diff --git a/drivers/usb/misc/usblcd.c b/drivers/usb/misc/usblcd.c
index d00dde1..5164815 100644
--- a/drivers/usb/misc/usblcd.c
+++ b/drivers/usb/misc/usblcd.c
@@ -282,6 +282,7 @@
         .open =         lcd_open,
 	.unlocked_ioctl = lcd_ioctl,
         .release =      lcd_release,
+        .llseek =	 noop_llseek,
 };
 
 /*
diff --git a/drivers/usb/usb-skeleton.c b/drivers/usb/usb-skeleton.c
index 552679b..e24ce31 100644
--- a/drivers/usb/usb-skeleton.c
+++ b/drivers/usb/usb-skeleton.c
@@ -507,6 +507,7 @@
 	.open =		skel_open,
 	.release =	skel_release,
 	.flush =	skel_flush,
+	.llseek =	noop_llseek,
 };
 
 /*
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 7c80082..861af4a 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -127,7 +127,10 @@
 	size_t len, total_len = 0;
 	int err, wmem;
 	size_t hdr_size;
-	struct socket *sock = rcu_dereference(vq->private_data);
+	struct socket *sock;
+
+	sock = rcu_dereference_check(vq->private_data,
+				     lockdep_is_held(&vq->mutex));
 	if (!sock)
 		return;
 
@@ -582,7 +585,10 @@
 static void vhost_net_enable_vq(struct vhost_net *n,
 				struct vhost_virtqueue *vq)
 {
-	struct socket *sock = vq->private_data;
+	struct socket *sock;
+
+	sock = rcu_dereference_protected(vq->private_data,
+					 lockdep_is_held(&vq->mutex));
 	if (!sock)
 		return;
 	if (vq == n->vqs + VHOST_NET_VQ_TX) {
@@ -598,7 +604,8 @@
 	struct socket *sock;
 
 	mutex_lock(&vq->mutex);
-	sock = vq->private_data;
+	sock = rcu_dereference_protected(vq->private_data,
+					 lockdep_is_held(&vq->mutex));
 	vhost_net_disable_vq(n, vq);
 	rcu_assign_pointer(vq->private_data, NULL);
 	mutex_unlock(&vq->mutex);
@@ -736,7 +743,8 @@
 	}
 
 	/* start polling new socket */
-	oldsock = vq->private_data;
+	oldsock = rcu_dereference_protected(vq->private_data,
+					    lockdep_is_held(&vq->mutex));
 	if (sock != oldsock) {
                 vhost_net_disable_vq(n, vq);
                 rcu_assign_pointer(vq->private_data, sock);
@@ -869,6 +877,7 @@
 	.compat_ioctl   = vhost_net_compat_ioctl,
 #endif
 	.open           = vhost_net_open,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice vhost_net_misc = {
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index dd3d6f7..8b5a1b3 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -320,7 +320,7 @@
 	vhost_dev_cleanup(dev);
 
 	memory->nregions = 0;
-	dev->memory = memory;
+	RCU_INIT_POINTER(dev->memory, memory);
 	return 0;
 }
 
@@ -352,8 +352,9 @@
 		fput(dev->log_file);
 	dev->log_file = NULL;
 	/* No one will access memory at this point */
-	kfree(dev->memory);
-	dev->memory = NULL;
+	kfree(rcu_dereference_protected(dev->memory,
+					lockdep_is_held(&dev->mutex)));
+	RCU_INIT_POINTER(dev->memory, NULL);
 	if (dev->mm)
 		mmput(dev->mm);
 	dev->mm = NULL;
@@ -440,14 +441,22 @@
 /* Caller should have device mutex but not vq mutex */
 int vhost_log_access_ok(struct vhost_dev *dev)
 {
-	return memory_access_ok(dev, dev->memory, 1);
+	struct vhost_memory *mp;
+
+	mp = rcu_dereference_protected(dev->memory,
+				       lockdep_is_held(&dev->mutex));
+	return memory_access_ok(dev, mp, 1);
 }
 
 /* Verify access for write logging. */
 /* Caller should have vq mutex and device mutex */
 static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
 {
-	return vq_memory_access_ok(log_base, vq->dev->memory,
+	struct vhost_memory *mp;
+
+	mp = rcu_dereference_protected(vq->dev->memory,
+				       lockdep_is_held(&vq->mutex));
+	return vq_memory_access_ok(log_base, mp,
 			    vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
 		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
 					sizeof *vq->used +
@@ -487,7 +496,8 @@
 		kfree(newmem);
 		return -EFAULT;
 	}
-	oldmem = d->memory;
+	oldmem = rcu_dereference_protected(d->memory,
+					   lockdep_is_held(&d->mutex));
 	rcu_assign_pointer(d->memory, newmem);
 	synchronize_rcu();
 	kfree(oldmem);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index afd7729..af3c11d 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -106,7 +106,7 @@
 	 * vhost_work execution acts instead of rcu_read_lock() and the end of
 	 * vhost_work execution acts instead of rcu_read_lock().
 	 * Writers use virtqueue mutex. */
-	void *private_data;
+	void __rcu *private_data;
 	/* Log write descriptors */
 	void __user *log_base;
 	struct vhost_log log[VHOST_NET_MAX_SG];
@@ -116,7 +116,7 @@
 	/* Readers use RCU to access memory table pointer
 	 * log base pointer and features.
 	 * Writers use mutex below.*/
-	struct vhost_memory *memory;
+	struct vhost_memory __rcu *memory;
 	struct mm_struct *mm;
 	struct mutex mutex;
 	unsigned acked_features;
@@ -173,7 +173,11 @@
 
 static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
 {
-	unsigned acked_features = rcu_dereference(dev->acked_features);
+	unsigned acked_features;
+
+	acked_features =
+		rcu_dereference_index_check(dev->acked_features,
+					    lockdep_is_held(&dev->mutex));
 	return acked_features & (1 << bit);
 }
 
diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
index b066475..42e303f 100644
--- a/drivers/video/fbmem.c
+++ b/drivers/video/fbmem.c
@@ -1439,6 +1439,7 @@
 #ifdef CONFIG_FB_DEFERRED_IO
 	.fsync =	fb_deferred_io_fsync,
 #endif
+	.llseek =	default_llseek,
 };
 
 struct class *fb_class;
diff --git a/drivers/video/mbx/mbxdebugfs.c b/drivers/video/mbx/mbxdebugfs.c
index ecad965..12dec76 100644
--- a/drivers/video/mbx/mbxdebugfs.c
+++ b/drivers/video/mbx/mbxdebugfs.c
@@ -175,36 +175,42 @@
 	.read = sysconf_read_file,
 	.write = write_file_dummy,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations clock_fops = {
 	.read = clock_read_file,
 	.write = write_file_dummy,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations display_fops = {
 	.read = display_read_file,
 	.write = write_file_dummy,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations gsctl_fops = {
 	.read = gsctl_read_file,
 	.write = write_file_dummy,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations sdram_fops = {
 	.read = sdram_read_file,
 	.write = write_file_dummy,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations misc_fops = {
 	.read = misc_read_file,
 	.write = write_file_dummy,
 	.open = open_file_generic,
+	.llseek = default_llseek,
 };
 
 static void __devinit mbxfb_debugfs_init(struct fb_info *fbi)
diff --git a/drivers/video/omap2/vram.c b/drivers/video/omap2/vram.c
index f6fdc20..fed2a72 100644
--- a/drivers/video/omap2/vram.c
+++ b/drivers/video/omap2/vram.c
@@ -554,12 +554,8 @@
 	size = PAGE_ALIGN(size);
 
 	if (paddr) {
-		struct memblock_property res;
-
-		res.base = paddr;
-		res.size = size;
-		if ((paddr & ~PAGE_MASK) || memblock_find(&res) ||
-		    res.base != paddr || res.size != size) {
+		if ((paddr & ~PAGE_MASK) ||
+		    !memblock_is_region_memory(paddr, size)) {
 			pr_err("Illegal SDRAM region for VRAM\n");
 			return;
 		}
diff --git a/drivers/video/pxa168fb.c b/drivers/video/pxa168fb.c
index a31a77f..cea6403 100644
--- a/drivers/video/pxa168fb.c
+++ b/drivers/video/pxa168fb.c
@@ -784,12 +784,53 @@
 	return ret;
 }
 
+static int __devexit pxa168fb_remove(struct platform_device *pdev)
+{
+	struct pxa168fb_info *fbi = platform_get_drvdata(pdev);
+	struct fb_info *info;
+	int irq;
+	unsigned int data;
+
+	if (!fbi)
+		return 0;
+
+	/* disable DMA transfer */
+	data = readl(fbi->reg_base + LCD_SPU_DMA_CTRL0);
+	data &= ~CFG_GRA_ENA_MASK;
+	writel(data, fbi->reg_base + LCD_SPU_DMA_CTRL0);
+
+	info = fbi->info;
+
+	unregister_framebuffer(info);
+
+	writel(GRA_FRAME_IRQ0_ENA(0x0), fbi->reg_base + SPU_IRQ_ENA);
+
+	if (info->cmap.len)
+		fb_dealloc_cmap(&info->cmap);
+
+	irq = platform_get_irq(pdev, 0);
+	free_irq(irq, fbi);
+
+	dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+				info->screen_base, info->fix.smem_start);
+
+	iounmap(fbi->reg_base);
+
+	clk_disable(fbi->clk);
+	clk_put(fbi->clk);
+
+	framebuffer_release(info);
+
+	return 0;
+}
+
 static struct platform_driver pxa168fb_driver = {
 	.driver		= {
 		.name	= "pxa168-fb",
 		.owner	= THIS_MODULE,
 	},
 	.probe		= pxa168fb_probe,
+	.remove		= __devexit_p(pxa168fb_remove),
 };
 
 static int __init pxa168fb_init(void)
@@ -798,6 +839,12 @@
 }
 module_init(pxa168fb_init);
 
+static void __exit pxa168fb_exit(void)
+{
+	platform_driver_unregister(&pxa168fb_driver);
+}
+module_exit(pxa168fb_exit);
+
 MODULE_AUTHOR("Lennert Buytenhek <buytenh@marvell.com> "
 	      "Green Wan <gwan@marvell.com>");
 MODULE_DESCRIPTION("Framebuffer driver for PXA168/910");
diff --git a/drivers/vlynq/vlynq.c b/drivers/vlynq/vlynq.c
index f2d9e66..f885c86 100644
--- a/drivers/vlynq/vlynq.c
+++ b/drivers/vlynq/vlynq.c
@@ -31,6 +31,7 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/irq.h>
 
 #include <linux/vlynq.h>
 
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 24efd8e..c356146 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -957,12 +957,32 @@
 	  the Warp platform.
 
 config BOOKE_WDT
-	bool "PowerPC Book-E Watchdog Timer"
+	tristate "PowerPC Book-E Watchdog Timer"
 	depends on BOOKE || 4xx
 	---help---
+	  Watchdog driver for PowerPC Book-E chips, such as the Freescale
+	  MPC85xx SOCs and the IBM PowerPC 440.
+
 	  Please see Documentation/watchdog/watchdog-api.txt for
 	  more information.
 
+config BOOKE_WDT_DEFAULT_TIMEOUT
+	int "PowerPC Book-E Watchdog Timer Default Timeout"
+	depends on BOOKE_WDT
+	default 38 if FSL_BOOKE
+	range 0 63 if FSL_BOOKE
+	default 3 if !FSL_BOOKE
+	range 0 3 if !FSL_BOOKE
+	help
+	  Select the default watchdog timer period to be used by the PowerPC
+	  Book-E watchdog driver.  A watchdog "event" occurs when the bit
+	  position represented by this number transitions from zero to one.
+
+	  For Freescale Book-E processors, this is a number between 0 and 63.
+	  For other Book-E processors, this is a number between 0 and 3.
+
+	  The value can be overidden by the wdt_period command-line parameter.
+
 # PPC64 Architecture
 
 config WATCHDOG_RTAS
diff --git a/drivers/watchdog/ar7_wdt.c b/drivers/watchdog/ar7_wdt.c
index c764c52..b292217 100644
--- a/drivers/watchdog/ar7_wdt.c
+++ b/drivers/watchdog/ar7_wdt.c
@@ -267,6 +267,7 @@
 	.unlocked_ioctl	= ar7_wdt_ioctl,
 	.open		= ar7_wdt_open,
 	.release	= ar7_wdt_release,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice ar7_wdt_miscdev = {
diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c
index 3d49671..d11ffb0 100644
--- a/drivers/watchdog/booke_wdt.c
+++ b/drivers/watchdog/booke_wdt.c
@@ -4,7 +4,7 @@
  * Author: Matthew McClintock
  * Maintainer: Kumar Gala <galak@kernel.crashing.org>
  *
- * Copyright 2005, 2008 Freescale Semiconductor Inc.
+ * Copyright 2005, 2008, 2010 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -33,14 +33,8 @@
  * occur, and the final time the board will reset.
  */
 
-#ifdef	CONFIG_FSL_BOOKE
-#define WDT_PERIOD_DEFAULT 38	/* Ex. wdt_period=28 bus=333Mhz,reset=~40sec */
-#else
-#define WDT_PERIOD_DEFAULT 3	/* Refer to the PPC40x and PPC4xx manuals */
-#endif				/* for timing information */
-
 u32 booke_wdt_enabled;
-u32 booke_wdt_period = WDT_PERIOD_DEFAULT;
+u32 booke_wdt_period = CONFIG_BOOKE_WDT_DEFAULT_TIMEOUT;
 
 #ifdef	CONFIG_FSL_BOOKE
 #define WDTP(x)		((((x)&0x3)<<30)|(((x)&0x3c)<<15))
@@ -114,6 +108,27 @@
 	mtspr(SPRN_TCR, val);
 }
 
+/**
+ * booke_wdt_disable - disable the watchdog on the given CPU
+ *
+ * This function is called on each CPU.  It disables the watchdog on that CPU.
+ *
+ * TCR[WRC] cannot be changed once it has been set to non-zero, but we can
+ * effectively disable the watchdog by setting its period to the maximum value.
+ */
+static void __booke_wdt_disable(void *data)
+{
+	u32 val;
+
+	val = mfspr(SPRN_TCR);
+	val &= ~(TCR_WIE | WDTP_MASK);
+	mtspr(SPRN_TCR, val);
+
+	/* clear status to make sure nothing is pending */
+	__booke_wdt_ping(NULL);
+
+}
+
 static ssize_t booke_wdt_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -193,12 +208,21 @@
 	return nonseekable_open(inode, file);
 }
 
+static int booke_wdt_release(struct inode *inode, struct file *file)
+{
+	on_each_cpu(__booke_wdt_disable, NULL, 0);
+	booke_wdt_enabled = 0;
+
+	return 0;
+}
+
 static const struct file_operations booke_wdt_fops = {
 	.owner = THIS_MODULE,
 	.llseek = no_llseek,
 	.write = booke_wdt_write,
 	.unlocked_ioctl = booke_wdt_ioctl,
 	.open = booke_wdt_open,
+	.release = booke_wdt_release,
 };
 
 static struct miscdevice booke_wdt_miscdev = {
@@ -237,4 +261,9 @@
 
 	return ret;
 }
-device_initcall(booke_wdt_init);
+
+module_init(booke_wdt_init);
+module_exit(booke_wdt_exit);
+
+MODULE_DESCRIPTION("PowerPC Book-E watchdog driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c
index 566343b..eca855a 100644
--- a/drivers/watchdog/cpwd.c
+++ b/drivers/watchdog/cpwd.c
@@ -25,7 +25,7 @@
 #include <linux/ioport.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -89,6 +89,7 @@
 	} devs[WD_NUMDEVS];
 };
 
+static DEFINE_MUTEX(cpwd_mutex);
 static struct cpwd *cpwd_device;
 
 /* Sun uses Altera PLD EPF8820ATC144-4
@@ -368,7 +369,7 @@
 {
 	struct cpwd *p = cpwd_device;
 
-	lock_kernel();
+	mutex_lock(&cpwd_mutex);
 	switch (iminor(inode)) {
 	case WD0_MINOR:
 	case WD1_MINOR:
@@ -376,7 +377,7 @@
 		break;
 
 	default:
-		unlock_kernel();
+		mutex_unlock(&cpwd_mutex);
 		return -ENODEV;
 	}
 
@@ -386,13 +387,13 @@
 				IRQF_SHARED, DRIVER_NAME, p)) {
 			printk(KERN_ERR PFX "Cannot register IRQ %d\n",
 				p->irq);
-			unlock_kernel();
+			mutex_unlock(&cpwd_mutex);
 			return -EBUSY;
 		}
 		p->initialized = true;
 	}
 
-	unlock_kernel();
+	mutex_unlock(&cpwd_mutex);
 
 	return nonseekable_open(inode, f);
 }
@@ -482,9 +483,9 @@
 	case WIOCSTART:
 	case WIOCSTOP:
 	case WIOCGSTAT:
-		lock_kernel();
+		mutex_lock(&cpwd_mutex);
 		rval = cpwd_ioctl(file, cmd, arg);
-		unlock_kernel();
+		mutex_unlock(&cpwd_mutex);
 		break;
 
 	/* everything else is handled by the generic compat layer */
@@ -524,6 +525,7 @@
 	.write =		cpwd_write,
 	.read =			cpwd_read,
 	.release =		cpwd_release,
+	.llseek =		no_llseek,
 };
 
 static int __devinit cpwd_probe(struct platform_device *op,
diff --git a/drivers/watchdog/ep93xx_wdt.c b/drivers/watchdog/ep93xx_wdt.c
index 59359c9..726b7df 100644
--- a/drivers/watchdog/ep93xx_wdt.c
+++ b/drivers/watchdog/ep93xx_wdt.c
@@ -188,6 +188,7 @@
 	.unlocked_ioctl	= ep93xx_wdt_ioctl,
 	.open		= ep93xx_wdt_open,
 	.release	= ep93xx_wdt_release,
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice ep93xx_wdt_miscdev = {
diff --git a/drivers/watchdog/octeon-wdt-main.c b/drivers/watchdog/octeon-wdt-main.c
index 2a41017..9099238 100644
--- a/drivers/watchdog/octeon-wdt-main.c
+++ b/drivers/watchdog/octeon-wdt-main.c
@@ -64,6 +64,7 @@
 #include <linux/cpu.h>
 #include <linux/smp.h>
 #include <linux/fs.h>
+#include <linux/irq.h>
 
 #include <asm/mipsregs.h>
 #include <asm/uasm.h>
diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c
index 76b58ab..81e3d61 100644
--- a/drivers/watchdog/omap_wdt.c
+++ b/drivers/watchdog/omap_wdt.c
@@ -258,6 +258,7 @@
 	.unlocked_ioctl = omap_wdt_ioctl,
 	.open = omap_wdt_open,
 	.release = omap_wdt_release,
+	.llseek = no_llseek,
 };
 
 static int __devinit omap_wdt_probe(struct platform_device *pdev)
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 13365ba..7d24b0d 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -338,30 +338,29 @@
 
 static int find_unbound_irq(void)
 {
-	int irq;
-	struct irq_desc *desc;
+	struct irq_data *data;
+	int irq, res;
 
 	for (irq = 0; irq < nr_irqs; irq++) {
-		desc = irq_to_desc(irq);
+		data = irq_get_irq_data(irq);
 		/* only 0->15 have init'd desc; handle irq > 16 */
-		if (desc == NULL)
+		if (!data)
 			break;
-		if (desc->chip == &no_irq_chip)
+		if (data->chip == &no_irq_chip)
 			break;
-		if (desc->chip != &xen_dynamic_chip)
+		if (data->chip != &xen_dynamic_chip)
 			continue;
 		if (irq_info[irq].type == IRQT_UNBOUND)
-			break;
+			return irq;
 	}
 
 	if (irq == nr_irqs)
 		panic("No available IRQ to bind to: increase nr_irqs!\n");
 
-	desc = irq_to_desc_alloc_node(irq, 0);
-	if (WARN_ON(desc == NULL))
-		return -1;
+	res = irq_alloc_desc_at(irq, 0);
 
-	dynamic_irq_init_keep_chip_data(irq);
+	if (WARN_ON(res != irq))
+		return -1;
 
 	return irq;
 }
@@ -495,7 +494,7 @@
 	if (irq_info[irq].type != IRQT_UNBOUND) {
 		irq_info[irq] = mk_unbound_info();
 
-		dynamic_irq_cleanup(irq);
+		irq_free_desc(irq);
 	}
 
 	spin_unlock(&irq_mapping_update_lock);
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 66e185c..fec6ba3 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -467,6 +467,7 @@
 	.fasync  = evtchn_fasync,
 	.open    = evtchn_open,
 	.release = evtchn_release,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice evtchn_miscdev = {
diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c
index 78bfab0..bd96340 100644
--- a/drivers/xen/xenfs/super.c
+++ b/drivers/xen/xenfs/super.c
@@ -35,6 +35,7 @@
 
 static const struct file_operations capabilities_file_ops = {
 	.read = capabilities_read,
+	.llseek = default_llseek,
 };
 
 static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
diff --git a/drivers/xen/xenfs/xenbus.c b/drivers/xen/xenfs/xenbus.c
index 3b39c37..1c12360 100644
--- a/drivers/xen/xenfs/xenbus.c
+++ b/drivers/xen/xenfs/xenbus.c
@@ -594,4 +594,5 @@
 	.open = xenbus_file_open,
 	.release = xenbus_file_release,
 	.poll = xenbus_file_poll,
+	.llseek = no_llseek,
 };
diff --git a/fs/Kconfig b/fs/Kconfig
index 3d18530..65781de 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -50,6 +50,7 @@
 config FILE_LOCKING
 	bool "Enable POSIX file locking API" if EMBEDDED
 	default y
+	select BKL # while lockd still uses it.
 	help
 	  This option enables standard file locking support, required
           for filesystems like NFS and for the flock() system
diff --git a/fs/adfs/Kconfig b/fs/adfs/Kconfig
index e55182a..1dd5f34 100644
--- a/fs/adfs/Kconfig
+++ b/fs/adfs/Kconfig
@@ -1,6 +1,7 @@
 config ADFS_FS
 	tristate "ADFS file system support (EXPERIMENTAL)"
 	depends on BLOCK && EXPERIMENTAL
+	depends on BKL # need to fix
 	help
 	  The Acorn Disc Filing System is the standard file system of the
 	  RiscOS operating system which runs on Acorn's ARM-based Risc PC
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 4a3af70..d9803f7 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -352,11 +352,15 @@
 	struct adfs_sb_info *asb;
 	struct inode *root;
 
+	lock_kernel();
+
 	sb->s_flags |= MS_NODIRATIME;
 
 	asb = kzalloc(sizeof(*asb), GFP_KERNEL);
-	if (!asb)
+	if (!asb) {
+		unlock_kernel();
 		return -ENOMEM;
+	}
 	sb->s_fs_info = asb;
 
 	/* set default options */
@@ -474,6 +478,7 @@
 		goto error;
 	} else
 		sb->s_root->d_op = &adfs_dentry_operations;
+	unlock_kernel();
 	return 0;
 
 error_free_bh:
@@ -481,6 +486,7 @@
 error:
 	sb->s_fs_info = NULL;
 	kfree(asb);
+	unlock_kernel();
 	return -EINVAL;
 }
 
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 33c4e7e..fa4fbe1 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -16,7 +16,6 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include "affs.h"
 
@@ -46,8 +45,6 @@
 	struct affs_sb_info *sbi = AFFS_SB(sb);
 	pr_debug("AFFS: put_super()\n");
 
-	lock_kernel();
-
 	if (!(sb->s_flags & MS_RDONLY) && sb->s_dirt)
 		affs_commit_super(sb, 1, 1);
 
@@ -56,8 +53,6 @@
 	affs_brelse(sbi->s_root_bh);
 	kfree(sbi);
 	sb->s_fs_info = NULL;
-
-	unlock_kernel();
 }
 
 static void
@@ -109,8 +104,8 @@
 {
 	struct affs_inode_info *ei = (struct affs_inode_info *) foo;
 
-	init_MUTEX(&ei->i_link_lock);
-	init_MUTEX(&ei->i_ext_lock);
+	sema_init(&ei->i_link_lock, 1);
+	sema_init(&ei->i_ext_lock, 1);
 	inode_init_once(&ei->vfs_inode);
 }
 
@@ -302,6 +297,7 @@
 	sbi = kzalloc(sizeof(struct affs_sb_info), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
+
 	sb->s_fs_info = sbi;
 	mutex_init(&sbi->s_bmlock);
 	spin_lock_init(&sbi->symlink_lock);
@@ -527,7 +523,7 @@
 		kfree(new_opts);
 		return -EINVAL;
 	}
-	lock_kernel();
+
 	replace_mount_options(sb, new_opts);
 
 	sbi->s_flags = mount_flags;
@@ -543,17 +539,15 @@
 	memcpy(sbi->s_volume, volume, 32);
 	spin_unlock(&sbi->symlink_lock);
 
-	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
-		unlock_kernel();
+	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
-	}
+
 	if (*flags & MS_RDONLY) {
 		affs_write_super(sb);
 		affs_free_bitmap(sb);
 	} else
 		res = affs_init_bitmap(sb, flags);
 
-	unlock_kernel();
 	return res;
 }
 
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 0931bc1..757d6645 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -9,7 +9,6 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/smp_lock.h>
 #include "internal.h"
 
 #define AFS_LOCK_GRANTED	0
@@ -274,7 +273,7 @@
 
 	type = (fl->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE;
 
-	lock_kernel();
+	lock_flocks();
 
 	/* make sure we've got a callback on this file and that our view of the
 	 * data version is up to date */
@@ -421,7 +420,7 @@
 	afs_vnode_fetch_status(vnode, NULL, key);
 
 error:
-	unlock_kernel();
+	unlock_flocks();
 	_leave(" = %d", ret);
 	return ret;
 
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 6d55268..6153417 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -29,6 +29,7 @@
 
 const struct file_operations afs_mntpt_file_operations = {
 	.open		= afs_mntpt_open,
+	.llseek		= noop_llseek,
 };
 
 const struct inode_operations afs_mntpt_inode_operations = {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 77e1e5a..eacf76d 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -19,7 +19,6 @@
 #include <linux/mount.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/parser.h>
@@ -453,12 +452,8 @@
 
 	_enter("");
 
-	lock_kernel();
-
 	afs_put_volume(as->volume);
 
-	unlock_kernel();
-
 	_leave("");
 }
 
diff --git a/fs/autofs/Kconfig b/fs/autofs/Kconfig
index 5f3bea9..480e210 100644
--- a/fs/autofs/Kconfig
+++ b/fs/autofs/Kconfig
@@ -1,5 +1,6 @@
 config AUTOFS_FS
 	tristate "Kernel automounter support"
+	depends on BKL # unfixable, just use autofs4
 	help
 	  The automounter is a tool to automatically mount remote file systems
 	  on demand. This implementation is partially kernel-based to reduce
diff --git a/fs/autofs/root.c b/fs/autofs/root.c
index 11b1ea7..0c4ca81 100644
--- a/fs/autofs/root.c
+++ b/fs/autofs/root.c
@@ -27,7 +27,9 @@
 static int autofs_root_rmdir(struct inode *,struct dentry *);
 static int autofs_root_mkdir(struct inode *,struct dentry *,int);
 static long autofs_root_ioctl(struct file *,unsigned int,unsigned long);
+#ifdef CONFIG_COMPAT
 static long autofs_root_compat_ioctl(struct file *,unsigned int,unsigned long);
+#endif
 
 const struct file_operations autofs_root_operations = {
 	.llseek		= generic_file_llseek,
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index ba4a38b..eff9a41 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -724,6 +724,7 @@
 	.unlocked_ioctl	 = autofs_dev_ioctl,
 	.compat_ioctl = autofs_dev_ioctl_compat,
 	.owner	 = THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice _autofs_dev_ioctl_misc = {
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index cb1bd38..d5c1401 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -19,7 +19,7 @@
 #include <linux/param.h>
 #include <linux/time.h>
 #include <linux/compat.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 
 #include "autofs_i.h"
 
@@ -28,7 +28,9 @@
 static int autofs4_dir_rmdir(struct inode *,struct dentry *);
 static int autofs4_dir_mkdir(struct inode *,struct dentry *,int);
 static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long);
+#ifdef CONFIG_COMPAT
 static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
+#endif
 static int autofs4_dir_open(struct inode *inode, struct file *file);
 static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
 static void *autofs4_follow_link(struct dentry *, struct nameidata *);
@@ -978,15 +980,17 @@
 	}
 }
 
+static DEFINE_MUTEX(autofs4_ioctl_mutex);
+
 static long autofs4_root_ioctl(struct file *filp,
 			       unsigned int cmd, unsigned long arg)
 {
 	long ret;
 	struct inode *inode = filp->f_dentry->d_inode;
 
-	lock_kernel();
+	mutex_lock(&autofs4_ioctl_mutex);
 	ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
-	unlock_kernel();
+	mutex_unlock(&autofs4_ioctl_mutex);
 
 	return ret;
 }
@@ -998,13 +1002,13 @@
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	int ret;
 
-	lock_kernel();
+	mutex_lock(&autofs4_ioctl_mutex);
 	if (cmd == AUTOFS_IOC_READY || cmd == AUTOFS_IOC_FAIL)
 		ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
 	else
 		ret = autofs4_root_ioctl_unlocked(inode, filp, cmd,
 			(unsigned long)compat_ptr(arg));
-	unlock_kernel();
+	mutex_unlock(&autofs4_ioctl_mutex);
 
 	return ret;
 }
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index c4daf0f..883e77a 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -12,7 +12,6 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/fs.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
 #include <linux/writeback.h>
@@ -215,14 +214,10 @@
 	if (!info)
 		return;
 
-	lock_kernel();
-
 	mutex_destroy(&info->bfs_lock);
 	kfree(info->si_imap);
 	kfree(info);
 	s->s_fs_info = NULL;
-
-	unlock_kernel();
 }
 
 static int bfs_statfs(struct dentry *dentry, struct kstatfs *buf)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 535e763..6884e19 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -800,7 +800,7 @@
 			 * default mmap base, as well as whatever program they
 			 * might try to exec.  This is because the brk will
 			 * follow the loader, and is not movable.  */
-#ifdef CONFIG_X86
+#if defined(CONFIG_X86) || defined(CONFIG_ARM)
 			load_bias = 0;
 #else
 			load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index fd0cc0b..139fc80 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -576,6 +576,7 @@
 static const struct file_operations bm_entry_operations = {
 	.read		= bm_entry_read,
 	.write		= bm_entry_write,
+	.llseek		= default_llseek,
 };
 
 /* /register */
@@ -643,6 +644,7 @@
 
 static const struct file_operations bm_register_operations = {
 	.write		= bm_register_write,
+	.llseek		= noop_llseek,
 };
 
 /* /status */
@@ -680,6 +682,7 @@
 static const struct file_operations bm_status_operations = {
 	.read		= bm_status_read,
 	.write		= bm_status_write,
+	.llseek		= default_llseek,
 };
 
 /* Superblock handling */
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 50e8c85..b737451 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -370,7 +370,7 @@
 	 */
 	mutex_unlock(&bd_inode->i_mutex);
 
-	error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL, BLKDEV_IFL_WAIT);
+	error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL);
 	if (error == -EOPNOTSUPP)
 		error = 0;
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 64f1008..5e789f4 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2063,7 +2063,7 @@
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
-		if (!buffer_eopnotsupp(bh) && printk_ratelimit()) {
+		if (printk_ratelimit()) {
 			printk(KERN_WARNING "lost page write due to "
 					"I/O error on %s\n",
 				       bdevname(bh->b_bdev, b));
@@ -2200,21 +2200,10 @@
 			bh->b_end_io = btrfs_end_buffer_write_sync;
 		}
 
-		if (i == last_barrier && do_barriers && device->barriers) {
-			ret = submit_bh(WRITE_BARRIER, bh);
-			if (ret == -EOPNOTSUPP) {
-				printk("btrfs: disabling barriers on dev %s\n",
-				       device->name);
-				set_buffer_uptodate(bh);
-				device->barriers = 0;
-				/* one reference for submit_bh */
-				get_bh(bh);
-				lock_buffer(bh);
-				ret = submit_bh(WRITE_SYNC, bh);
-			}
-		} else {
+		if (i == last_barrier && do_barriers)
+			ret = submit_bh(WRITE_FLUSH_FUA, bh);
+		else
 			ret = submit_bh(WRITE_SYNC, bh);
-		}
 
 		if (ret)
 			errors++;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 32d0940..0b81ecd 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1695,8 +1695,7 @@
 static void btrfs_issue_discard(struct block_device *bdev,
 				u64 start, u64 len)
 {
-	blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL,
-			BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+	blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0);
 }
 
 static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 1776dbd..144f8a5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -815,6 +815,7 @@
 	.unlocked_ioctl	 = btrfs_control_ioctl,
 	.compat_ioctl = btrfs_control_ioctl,
 	.owner	 = THIS_MODULE,
+	.llseek = noop_llseek,
 };
 
 static struct miscdevice btrfs_misc = {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index dd318ff..e25e46a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -398,7 +398,6 @@
 		device->work.func = pending_bios_fn;
 		memcpy(device->uuid, disk_super->dev_item.uuid,
 		       BTRFS_UUID_SIZE);
-		device->barriers = 1;
 		spin_lock_init(&device->io_lock);
 		device->name = kstrdup(path, GFP_NOFS);
 		if (!device->name) {
@@ -462,7 +461,6 @@
 		device->devid = orig_dev->devid;
 		device->work.func = pending_bios_fn;
 		memcpy(device->uuid, orig_dev->uuid, sizeof(device->uuid));
-		device->barriers = 1;
 		spin_lock_init(&device->io_lock);
 		INIT_LIST_HEAD(&device->dev_list);
 		INIT_LIST_HEAD(&device->dev_alloc_list);
@@ -1489,7 +1487,6 @@
 	trans = btrfs_start_transaction(root, 0);
 	lock_chunks(root);
 
-	device->barriers = 1;
 	device->writeable = 1;
 	device->work.func = pending_bios_fn;
 	generate_random_uuid(device->uuid);
@@ -3084,7 +3081,6 @@
 		return NULL;
 	list_add(&device->dev_list,
 		 &fs_devices->devices);
-	device->barriers = 1;
 	device->dev_root = root->fs_info->dev_root;
 	device->devid = devid;
 	device->work.func = pending_bios_fn;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 31b0fab..2b638b6 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -42,7 +42,6 @@
 	int running_pending;
 	u64 generation;
 
-	int barriers;
 	int writeable;
 	int in_fs_metadata;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 3e7dca2..7f0b9b0 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -156,7 +156,7 @@
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
-		if (!buffer_eopnotsupp(bh) && !quiet_error(bh)) {
+		if (!quiet_error(bh)) {
 			buffer_io_error(bh);
 			printk(KERN_WARNING "lost page write due to "
 					"I/O error on %s\n",
@@ -2891,7 +2891,6 @@
 
 	if (err == -EOPNOTSUPP) {
 		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		set_bit(BH_Eopnotsupp, &bh->b_state);
 	}
 
 	if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
@@ -3031,10 +3030,6 @@
 		bh->b_end_io = end_buffer_write_sync;
 		ret = submit_bh(rw, bh);
 		wait_on_buffer(bh);
-		if (buffer_eopnotsupp(bh)) {
-			clear_buffer_eopnotsupp(bh);
-			ret = -EOPNOTSUPP;
-		}
 		if (!ret && !buffer_uptodate(bh))
 			ret = -EIO;
 	} else {
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 727caed..0a1467b 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -55,6 +55,7 @@
 	.read		= cachefiles_daemon_read,
 	.write		= cachefiles_daemon_write,
 	.poll		= cachefiles_daemon_poll,
+	.llseek		= noop_llseek,
 };
 
 struct cachefiles_daemon_cmd {
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 0fcd264..9eb134e 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -1,9 +1,11 @@
 config CEPH_FS
         tristate "Ceph distributed file system (EXPERIMENTAL)"
 	depends on INET && EXPERIMENTAL
+	select CEPH_LIB
 	select LIBCRC32C
 	select CRYPTO_AES
 	select CRYPTO
+	default n
 	help
 	  Choose Y or M here to include support for mounting the
 	  experimental Ceph distributed file system.  Ceph is an extremely
@@ -14,15 +16,3 @@
 
 	  If unsure, say N.
 
-config CEPH_FS_PRETTYDEBUG
-	bool "Include file:line in ceph debug output"
-	depends on CEPH_FS
-	default n
-	help
-	  If you say Y here, debug output will include a filename and
-	  line to aid debugging.  This icnreases kernel size and slows
-	  execution slightly when debug call sites are enabled (e.g.,
-	  via CONFIG_DYNAMIC_DEBUG).
-
-	  If unsure, say N.
-
diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
index 278e117..9e6c4f2 100644
--- a/fs/ceph/Makefile
+++ b/fs/ceph/Makefile
@@ -8,15 +8,8 @@
 
 ceph-objs := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
 	export.o caps.o snap.o xattr.o \
-	messenger.o msgpool.o buffer.o pagelist.o \
-	mds_client.o mdsmap.o \
-	mon_client.o \
-	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
-	debugfs.o \
-	auth.o auth_none.o \
-	crypto.o armor.o \
-	auth_x.o \
-	ceph_fs.o ceph_strings.o ceph_hash.o ceph_frag.o
+	mds_client.o mdsmap.o strings.o ceph_frag.o \
+	debugfs.o
 
 else
 #Otherwise we were called directly from the command
diff --git a/fs/ceph/README b/fs/ceph/README
deleted file mode 100644
index 18352fa..0000000
--- a/fs/ceph/README
+++ /dev/null
@@ -1,20 +0,0 @@
-#
-# The following files are shared by (and manually synchronized
-# between) the Ceph userland and kernel client.
-#
-# userland                  kernel
-src/include/ceph_fs.h	    fs/ceph/ceph_fs.h
-src/include/ceph_fs.cc	    fs/ceph/ceph_fs.c
-src/include/msgr.h	    fs/ceph/msgr.h
-src/include/rados.h	    fs/ceph/rados.h
-src/include/ceph_strings.cc fs/ceph/ceph_strings.c
-src/include/ceph_frag.h	    fs/ceph/ceph_frag.h
-src/include/ceph_frag.cc    fs/ceph/ceph_frag.c
-src/include/ceph_hash.h	    fs/ceph/ceph_hash.h
-src/include/ceph_hash.cc    fs/ceph/ceph_hash.c
-src/crush/crush.c	    fs/ceph/crush/crush.c
-src/crush/crush.h	    fs/ceph/crush/crush.h
-src/crush/mapper.c	    fs/ceph/crush/mapper.c
-src/crush/mapper.h	    fs/ceph/crush/mapper.h
-src/crush/hash.h	    fs/ceph/crush/hash.h
-src/crush/hash.c	    fs/ceph/crush/hash.c
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index efbc604..51bcc5c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/backing-dev.h>
 #include <linux/fs.h>
@@ -10,7 +10,8 @@
 #include <linux/task_io_accounting_ops.h>
 
 #include "super.h"
-#include "osd_client.h"
+#include "mds_client.h"
+#include <linux/ceph/osd_client.h>
 
 /*
  * Ceph address space ops.
@@ -193,7 +194,8 @@
 {
 	struct inode *inode = filp->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
+	struct ceph_osd_client *osdc = 
+		&ceph_inode_to_client(inode)->client->osdc;
 	int err = 0;
 	u64 len = PAGE_CACHE_SIZE;
 
@@ -265,7 +267,8 @@
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
+	struct ceph_osd_client *osdc =
+		&ceph_inode_to_client(inode)->client->osdc;
 	int rc = 0;
 	struct page **pages;
 	loff_t offset;
@@ -365,7 +368,7 @@
 {
 	struct inode *inode;
 	struct ceph_inode_info *ci;
-	struct ceph_client *client;
+	struct ceph_fs_client *fsc;
 	struct ceph_osd_client *osdc;
 	loff_t page_off = page->index << PAGE_CACHE_SHIFT;
 	int len = PAGE_CACHE_SIZE;
@@ -383,8 +386,8 @@
 	}
 	inode = page->mapping->host;
 	ci = ceph_inode(inode);
-	client = ceph_inode_to_client(inode);
-	osdc = &client->osdc;
+	fsc = ceph_inode_to_client(inode);
+	osdc = &fsc->client->osdc;
 
 	/* verify this is a writeable snap context */
 	snapc = (void *)page->private;
@@ -414,10 +417,10 @@
 	dout("writepage %p page %p index %lu on %llu~%u snapc %p\n",
 	     inode, page, page->index, page_off, len, snapc);
 
-	writeback_stat = atomic_long_inc_return(&client->writeback_count);
+	writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
 	if (writeback_stat >
-	    CONGESTION_ON_THRESH(client->mount_args->congestion_kb))
-		set_bdi_congested(&client->backing_dev_info, BLK_RW_ASYNC);
+	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
+		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
 
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
@@ -496,7 +499,7 @@
 	struct address_space *mapping = inode->i_mapping;
 	__s32 rc = -EIO;
 	u64 bytes = 0;
-	struct ceph_client *client = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	long writeback_stat;
 	unsigned issued = ceph_caps_issued(ci);
 
@@ -529,10 +532,10 @@
 		WARN_ON(!PageUptodate(page));
 
 		writeback_stat =
-			atomic_long_dec_return(&client->writeback_count);
+			atomic_long_dec_return(&fsc->writeback_count);
 		if (writeback_stat <
-		    CONGESTION_OFF_THRESH(client->mount_args->congestion_kb))
-			clear_bdi_congested(&client->backing_dev_info,
+		    CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
+			clear_bdi_congested(&fsc->backing_dev_info,
 					    BLK_RW_ASYNC);
 
 		ceph_put_snap_context((void *)page->private);
@@ -569,13 +572,13 @@
  * mempool.  we avoid the mempool if we can because req->r_num_pages
  * may be less than the maximum write size.
  */
-static void alloc_page_vec(struct ceph_client *client,
+static void alloc_page_vec(struct ceph_fs_client *fsc,
 			   struct ceph_osd_request *req)
 {
 	req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages,
 			       GFP_NOFS);
 	if (!req->r_pages) {
-		req->r_pages = mempool_alloc(client->wb_pagevec_pool, GFP_NOFS);
+		req->r_pages = mempool_alloc(fsc->wb_pagevec_pool, GFP_NOFS);
 		req->r_pages_from_pool = 1;
 		WARN_ON(!req->r_pages);
 	}
@@ -590,7 +593,7 @@
 	struct inode *inode = mapping->host;
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_client *client;
+	struct ceph_fs_client *fsc;
 	pgoff_t index, start, end;
 	int range_whole = 0;
 	int should_loop = 1;
@@ -617,13 +620,13 @@
 	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
 	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
 
-	client = ceph_inode_to_client(inode);
-	if (client->mount_state == CEPH_MOUNT_SHUTDOWN) {
+	fsc = ceph_inode_to_client(inode);
+	if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
 		pr_warning("writepage_start %p on forced umount\n", inode);
 		return -EIO; /* we're in a forced umount, don't write! */
 	}
-	if (client->mount_args->wsize && client->mount_args->wsize < wsize)
-		wsize = client->mount_args->wsize;
+	if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
+		wsize = fsc->mount_options->wsize;
 	if (wsize < PAGE_CACHE_SIZE)
 		wsize = PAGE_CACHE_SIZE;
 	max_pages_ever = wsize >> PAGE_CACHE_SHIFT;
@@ -769,7 +772,7 @@
 				offset = (unsigned long long)page->index
 					<< PAGE_CACHE_SHIFT;
 				len = wsize;
-				req = ceph_osdc_new_request(&client->osdc,
+				req = ceph_osdc_new_request(&fsc->client->osdc,
 					    &ci->i_layout,
 					    ceph_vino(inode),
 					    offset, &len,
@@ -782,7 +785,7 @@
 					    &inode->i_mtime, true, 1);
 				max_pages = req->r_num_pages;
 
-				alloc_page_vec(client, req);
+				alloc_page_vec(fsc, req);
 				req->r_callback = writepages_finish;
 				req->r_inode = inode;
 			}
@@ -794,10 +797,10 @@
 			     inode, page, page->index);
 
 			writeback_stat =
-			       atomic_long_inc_return(&client->writeback_count);
+			       atomic_long_inc_return(&fsc->writeback_count);
 			if (writeback_stat > CONGESTION_ON_THRESH(
-				    client->mount_args->congestion_kb)) {
-				set_bdi_congested(&client->backing_dev_info,
+				    fsc->mount_options->congestion_kb)) {
+				set_bdi_congested(&fsc->backing_dev_info,
 						  BLK_RW_ASYNC);
 			}
 
@@ -846,7 +849,7 @@
 		op->payload_len = cpu_to_le32(len);
 		req->r_request->hdr.data_len = cpu_to_le32(len);
 
-		ceph_osdc_start_request(&client->osdc, req, true);
+		ceph_osdc_start_request(&fsc->client->osdc, req, true);
 		req = NULL;
 
 		/* continue? */
@@ -915,7 +918,7 @@
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	loff_t page_off = pos & PAGE_CACHE_MASK;
 	int pos_in_page = pos & ~PAGE_CACHE_MASK;
 	int end_in_page = pos_in_page + len;
@@ -1053,8 +1056,8 @@
 			  struct page *page, void *fsdata)
 {
 	struct inode *inode = file->f_dentry->d_inode;
-	struct ceph_client *client = ceph_inode_to_client(inode);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
 	int check_cap = 0;
 
@@ -1123,7 +1126,7 @@
 {
 	struct inode *inode = vma->vm_file->f_dentry->d_inode;
 	struct page *page = vmf->page;
-	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	loff_t off = page->index << PAGE_CACHE_SHIFT;
 	loff_t size, len;
 	int ret;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 5e9da99..98ab13e 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/fs.h>
 #include <linux/kernel.h>
@@ -9,8 +9,9 @@
 #include <linux/writeback.h>
 
 #include "super.h"
-#include "decode.h"
-#include "messenger.h"
+#include "mds_client.h"
+#include <linux/ceph/decode.h>
+#include <linux/ceph/messenger.h>
 
 /*
  * Capability management
@@ -287,11 +288,11 @@
 	spin_unlock(&mdsc->caps_list_lock);
 }
 
-void ceph_reservation_status(struct ceph_client *client,
+void ceph_reservation_status(struct ceph_fs_client *fsc,
 			     int *total, int *avail, int *used, int *reserved,
 			     int *min)
 {
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 
 	if (total)
 		*total = mdsc->caps_total_count;
@@ -399,7 +400,7 @@
 static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
 			       struct ceph_inode_info *ci)
 {
-	struct ceph_mount_args *ma = mdsc->client->mount_args;
+	struct ceph_mount_options *ma = mdsc->fsc->mount_options;
 
 	ci->i_hold_caps_min = round_jiffies(jiffies +
 					    ma->caps_wanted_delay_min * HZ);
@@ -515,7 +516,7 @@
 		 unsigned seq, unsigned mseq, u64 realmino, int flags,
 		 struct ceph_cap_reservation *caps_reservation)
 {
-	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_cap *new_cap = NULL;
 	struct ceph_cap *cap;
@@ -873,7 +874,7 @@
 	struct ceph_mds_session *session = cap->session;
 	struct ceph_inode_info *ci = cap->ci;
 	struct ceph_mds_client *mdsc =
-		&ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+		ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
 	int removed = 0;
 
 	dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
@@ -1210,7 +1211,7 @@
 	int mds;
 	struct ceph_cap_snap *capsnap;
 	u32 mseq;
-	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_mds_session *session = NULL; /* if session != NULL, we hold
 						    session->s_mutex */
 	u64 next_follows = 0;  /* keep track of how far we've gotten through the
@@ -1336,7 +1337,7 @@
 void __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask)
 {
 	struct ceph_mds_client *mdsc =
-		&ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+		ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
 	struct inode *inode = &ci->vfs_inode;
 	int was = ci->i_dirty_caps;
 	int dirty = 0;
@@ -1378,7 +1379,7 @@
 static int __mark_caps_flushing(struct inode *inode,
 				 struct ceph_mds_session *session)
 {
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int flushing;
 
@@ -1416,17 +1417,6 @@
 /*
  * try to invalidate mapping pages without blocking.
  */
-static int mapping_is_empty(struct address_space *mapping)
-{
-	struct page *page = find_get_page(mapping, 0);
-
-	if (!page)
-		return 1;
-
-	put_page(page);
-	return 0;
-}
-
 static int try_nonblocking_invalidate(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1436,7 +1426,7 @@
 	invalidate_mapping_pages(&inode->i_data, 0, -1);
 	spin_lock(&inode->i_lock);
 
-	if (mapping_is_empty(&inode->i_data) &&
+	if (inode->i_data.nrpages == 0 &&
 	    invalidating_gen == ci->i_rdcache_gen) {
 		/* success. */
 		dout("try_nonblocking_invalidate %p success\n", inode);
@@ -1462,8 +1452,8 @@
 void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 		     struct ceph_mds_session *session)
 {
-	struct ceph_client *client = ceph_inode_to_client(&ci->vfs_inode);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap *cap;
 	int file_wanted, used;
@@ -1533,7 +1523,7 @@
 	 */
 	if ((!is_delayed || mdsc->stopping) &&
 	    ci->i_wrbuffer_ref == 0 &&               /* no dirty pages... */
-	    ci->i_rdcache_gen &&                     /* may have cached pages */
+	    inode->i_data.nrpages &&                 /* have cached pages */
 	    (file_wanted == 0 ||                     /* no open files */
 	     (revoking & (CEPH_CAP_FILE_CACHE|
 			  CEPH_CAP_FILE_LAZYIO))) && /*  or revoking cache */
@@ -1706,7 +1696,7 @@
 static int try_flush_caps(struct inode *inode, struct ceph_mds_session *session,
 			  unsigned *flush_tid)
 {
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int unlock_session = session ? 0 : 1;
 	int flushing = 0;
@@ -1872,7 +1862,7 @@
 				       caps_are_flushed(inode, flush_tid));
 	} else {
 		struct ceph_mds_client *mdsc =
-			&ceph_sb_to_client(inode->i_sb)->mdsc;
+			ceph_sb_to_client(inode->i_sb)->mdsc;
 
 		spin_lock(&inode->i_lock);
 		if (__ceph_caps_dirty(ci))
@@ -2465,7 +2455,7 @@
 	__releases(inode->i_lock)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	unsigned seq = le32_to_cpu(m->seq);
 	int dirty = le32_to_cpu(m->dirty);
 	int cleaned = 0;
@@ -2713,7 +2703,7 @@
 		      struct ceph_msg *msg)
 {
 	struct ceph_mds_client *mdsc = session->s_mdsc;
-	struct super_block *sb = mdsc->client->sb;
+	struct super_block *sb = mdsc->fsc->sb;
 	struct inode *inode;
 	struct ceph_cap *cap;
 	struct ceph_mds_caps *h;
diff --git a/fs/ceph/ceph_frag.c b/fs/ceph/ceph_frag.c
index ab6cf35..bdce8b1 100644
--- a/fs/ceph/ceph_frag.c
+++ b/fs/ceph/ceph_frag.c
@@ -1,7 +1,8 @@
 /*
  * Ceph 'frag' type
  */
-#include "types.h"
+#include <linux/module.h>
+#include <linux/ceph/types.h>
 
 int ceph_frag_compare(__u32 a, __u32 b)
 {
diff --git a/fs/ceph/ceph_strings.c b/fs/ceph/ceph_strings.c
deleted file mode 100644
index c6179d3..0000000
--- a/fs/ceph/ceph_strings.c
+++ /dev/null
@@ -1,193 +0,0 @@
-/*
- * Ceph string constants
- */
-#include "types.h"
-
-const char *ceph_entity_type_name(int type)
-{
-	switch (type) {
-	case CEPH_ENTITY_TYPE_MDS: return "mds";
-	case CEPH_ENTITY_TYPE_OSD: return "osd";
-	case CEPH_ENTITY_TYPE_MON: return "mon";
-	case CEPH_ENTITY_TYPE_CLIENT: return "client";
-	case CEPH_ENTITY_TYPE_AUTH: return "auth";
-	default: return "unknown";
-	}
-}
-
-const char *ceph_osd_op_name(int op)
-{
-	switch (op) {
-	case CEPH_OSD_OP_READ: return "read";
-	case CEPH_OSD_OP_STAT: return "stat";
-
-	case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
-
-	case CEPH_OSD_OP_WRITE: return "write";
-	case CEPH_OSD_OP_DELETE: return "delete";
-	case CEPH_OSD_OP_TRUNCATE: return "truncate";
-	case CEPH_OSD_OP_ZERO: return "zero";
-	case CEPH_OSD_OP_WRITEFULL: return "writefull";
-	case CEPH_OSD_OP_ROLLBACK: return "rollback";
-
-	case CEPH_OSD_OP_APPEND: return "append";
-	case CEPH_OSD_OP_STARTSYNC: return "startsync";
-	case CEPH_OSD_OP_SETTRUNC: return "settrunc";
-	case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
-
-	case CEPH_OSD_OP_TMAPUP: return "tmapup";
-	case CEPH_OSD_OP_TMAPGET: return "tmapget";
-	case CEPH_OSD_OP_TMAPPUT: return "tmapput";
-
-	case CEPH_OSD_OP_GETXATTR: return "getxattr";
-	case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
-	case CEPH_OSD_OP_SETXATTR: return "setxattr";
-	case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
-	case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
-	case CEPH_OSD_OP_RMXATTR: return "rmxattr";
-	case CEPH_OSD_OP_CMPXATTR: return "cmpxattr";
-
-	case CEPH_OSD_OP_PULL: return "pull";
-	case CEPH_OSD_OP_PUSH: return "push";
-	case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
-	case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
-	case CEPH_OSD_OP_SCRUB: return "scrub";
-
-	case CEPH_OSD_OP_WRLOCK: return "wrlock";
-	case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
-	case CEPH_OSD_OP_RDLOCK: return "rdlock";
-	case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
-	case CEPH_OSD_OP_UPLOCK: return "uplock";
-	case CEPH_OSD_OP_DNLOCK: return "dnlock";
-
-	case CEPH_OSD_OP_CALL: return "call";
-
-	case CEPH_OSD_OP_PGLS: return "pgls";
-	}
-	return "???";
-}
-
-const char *ceph_mds_state_name(int s)
-{
-	switch (s) {
-		/* down and out */
-	case CEPH_MDS_STATE_DNE:        return "down:dne";
-	case CEPH_MDS_STATE_STOPPED:    return "down:stopped";
-		/* up and out */
-	case CEPH_MDS_STATE_BOOT:       return "up:boot";
-	case CEPH_MDS_STATE_STANDBY:    return "up:standby";
-	case CEPH_MDS_STATE_STANDBY_REPLAY:    return "up:standby-replay";
-	case CEPH_MDS_STATE_CREATING:   return "up:creating";
-	case CEPH_MDS_STATE_STARTING:   return "up:starting";
-		/* up and in */
-	case CEPH_MDS_STATE_REPLAY:     return "up:replay";
-	case CEPH_MDS_STATE_RESOLVE:    return "up:resolve";
-	case CEPH_MDS_STATE_RECONNECT:  return "up:reconnect";
-	case CEPH_MDS_STATE_REJOIN:     return "up:rejoin";
-	case CEPH_MDS_STATE_CLIENTREPLAY: return "up:clientreplay";
-	case CEPH_MDS_STATE_ACTIVE:     return "up:active";
-	case CEPH_MDS_STATE_STOPPING:   return "up:stopping";
-	}
-	return "???";
-}
-
-const char *ceph_session_op_name(int op)
-{
-	switch (op) {
-	case CEPH_SESSION_REQUEST_OPEN: return "request_open";
-	case CEPH_SESSION_OPEN: return "open";
-	case CEPH_SESSION_REQUEST_CLOSE: return "request_close";
-	case CEPH_SESSION_CLOSE: return "close";
-	case CEPH_SESSION_REQUEST_RENEWCAPS: return "request_renewcaps";
-	case CEPH_SESSION_RENEWCAPS: return "renewcaps";
-	case CEPH_SESSION_STALE: return "stale";
-	case CEPH_SESSION_RECALL_STATE: return "recall_state";
-	}
-	return "???";
-}
-
-const char *ceph_mds_op_name(int op)
-{
-	switch (op) {
-	case CEPH_MDS_OP_LOOKUP:  return "lookup";
-	case CEPH_MDS_OP_LOOKUPHASH:  return "lookuphash";
-	case CEPH_MDS_OP_LOOKUPPARENT:  return "lookupparent";
-	case CEPH_MDS_OP_GETATTR:  return "getattr";
-	case CEPH_MDS_OP_SETXATTR: return "setxattr";
-	case CEPH_MDS_OP_SETATTR: return "setattr";
-	case CEPH_MDS_OP_RMXATTR: return "rmxattr";
-	case CEPH_MDS_OP_READDIR: return "readdir";
-	case CEPH_MDS_OP_MKNOD: return "mknod";
-	case CEPH_MDS_OP_LINK: return "link";
-	case CEPH_MDS_OP_UNLINK: return "unlink";
-	case CEPH_MDS_OP_RENAME: return "rename";
-	case CEPH_MDS_OP_MKDIR: return "mkdir";
-	case CEPH_MDS_OP_RMDIR: return "rmdir";
-	case CEPH_MDS_OP_SYMLINK: return "symlink";
-	case CEPH_MDS_OP_CREATE: return "create";
-	case CEPH_MDS_OP_OPEN: return "open";
-	case CEPH_MDS_OP_LOOKUPSNAP: return "lookupsnap";
-	case CEPH_MDS_OP_LSSNAP: return "lssnap";
-	case CEPH_MDS_OP_MKSNAP: return "mksnap";
-	case CEPH_MDS_OP_RMSNAP: return "rmsnap";
-	case CEPH_MDS_OP_SETFILELOCK: return "setfilelock";
-	case CEPH_MDS_OP_GETFILELOCK: return "getfilelock";
-	}
-	return "???";
-}
-
-const char *ceph_cap_op_name(int op)
-{
-	switch (op) {
-	case CEPH_CAP_OP_GRANT: return "grant";
-	case CEPH_CAP_OP_REVOKE: return "revoke";
-	case CEPH_CAP_OP_TRUNC: return "trunc";
-	case CEPH_CAP_OP_EXPORT: return "export";
-	case CEPH_CAP_OP_IMPORT: return "import";
-	case CEPH_CAP_OP_UPDATE: return "update";
-	case CEPH_CAP_OP_DROP: return "drop";
-	case CEPH_CAP_OP_FLUSH: return "flush";
-	case CEPH_CAP_OP_FLUSH_ACK: return "flush_ack";
-	case CEPH_CAP_OP_FLUSHSNAP: return "flushsnap";
-	case CEPH_CAP_OP_FLUSHSNAP_ACK: return "flushsnap_ack";
-	case CEPH_CAP_OP_RELEASE: return "release";
-	case CEPH_CAP_OP_RENEW: return "renew";
-	}
-	return "???";
-}
-
-const char *ceph_lease_op_name(int o)
-{
-	switch (o) {
-	case CEPH_MDS_LEASE_REVOKE: return "revoke";
-	case CEPH_MDS_LEASE_RELEASE: return "release";
-	case CEPH_MDS_LEASE_RENEW: return "renew";
-	case CEPH_MDS_LEASE_REVOKE_ACK: return "revoke_ack";
-	}
-	return "???";
-}
-
-const char *ceph_snap_op_name(int o)
-{
-	switch (o) {
-	case CEPH_SNAP_OP_UPDATE: return "update";
-	case CEPH_SNAP_OP_CREATE: return "create";
-	case CEPH_SNAP_OP_DESTROY: return "destroy";
-	case CEPH_SNAP_OP_SPLIT: return "split";
-	}
-	return "???";
-}
-
-const char *ceph_pool_op_name(int op)
-{
-	switch (op) {
-	case POOL_OP_CREATE: return "create";
-	case POOL_OP_DELETE: return "delete";
-	case POOL_OP_AUID_CHANGE: return "auid change";
-	case POOL_OP_CREATE_SNAP: return "create snap";
-	case POOL_OP_DELETE_SNAP: return "delete snap";
-	case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
-	case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
-	}
-	return "???";
-}
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 6fd8b20..7ae1b3d 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/device.h>
 #include <linux/slab.h>
@@ -7,143 +7,49 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+
 #include "super.h"
-#include "mds_client.h"
-#include "mon_client.h"
-#include "auth.h"
 
 #ifdef CONFIG_DEBUG_FS
 
-/*
- * Implement /sys/kernel/debug/ceph fun
- *
- * /sys/kernel/debug/ceph/client*  - an instance of the ceph client
- *      .../osdmap      - current osdmap
- *      .../mdsmap      - current mdsmap
- *      .../monmap      - current monmap
- *      .../osdc        - active osd requests
- *      .../mdsc        - active mds requests
- *      .../monc        - mon client state
- *      .../dentry_lru  - dump contents of dentry lru
- *      .../caps        - expose cap (reservation) stats
- *      .../bdi         - symlink to ../../bdi/something
- */
-
-static struct dentry *ceph_debugfs_dir;
-
-static int monmap_show(struct seq_file *s, void *p)
-{
-	int i;
-	struct ceph_client *client = s->private;
-
-	if (client->monc.monmap == NULL)
-		return 0;
-
-	seq_printf(s, "epoch %d\n", client->monc.monmap->epoch);
-	for (i = 0; i < client->monc.monmap->num_mon; i++) {
-		struct ceph_entity_inst *inst =
-			&client->monc.monmap->mon_inst[i];
-
-		seq_printf(s, "\t%s%lld\t%s\n",
-			   ENTITY_NAME(inst->name),
-			   pr_addr(&inst->addr.in_addr));
-	}
-	return 0;
-}
+#include "mds_client.h"
 
 static int mdsmap_show(struct seq_file *s, void *p)
 {
 	int i;
-	struct ceph_client *client = s->private;
+	struct ceph_fs_client *fsc = s->private;
 
-	if (client->mdsc.mdsmap == NULL)
+	if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL)
 		return 0;
-	seq_printf(s, "epoch %d\n", client->mdsc.mdsmap->m_epoch);
-	seq_printf(s, "root %d\n", client->mdsc.mdsmap->m_root);
+	seq_printf(s, "epoch %d\n", fsc->mdsc->mdsmap->m_epoch);
+	seq_printf(s, "root %d\n", fsc->mdsc->mdsmap->m_root);
 	seq_printf(s, "session_timeout %d\n",
-		       client->mdsc.mdsmap->m_session_timeout);
+		       fsc->mdsc->mdsmap->m_session_timeout);
 	seq_printf(s, "session_autoclose %d\n",
-		       client->mdsc.mdsmap->m_session_autoclose);
-	for (i = 0; i < client->mdsc.mdsmap->m_max_mds; i++) {
+		       fsc->mdsc->mdsmap->m_session_autoclose);
+	for (i = 0; i < fsc->mdsc->mdsmap->m_max_mds; i++) {
 		struct ceph_entity_addr *addr =
-			&client->mdsc.mdsmap->m_info[i].addr;
-		int state = client->mdsc.mdsmap->m_info[i].state;
+			&fsc->mdsc->mdsmap->m_info[i].addr;
+		int state = fsc->mdsc->mdsmap->m_info[i].state;
 
-		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, pr_addr(&addr->in_addr),
+		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
+			       ceph_pr_addr(&addr->in_addr),
 			       ceph_mds_state_name(state));
 	}
 	return 0;
 }
 
-static int osdmap_show(struct seq_file *s, void *p)
-{
-	int i;
-	struct ceph_client *client = s->private;
-	struct rb_node *n;
-
-	if (client->osdc.osdmap == NULL)
-		return 0;
-	seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
-	seq_printf(s, "flags%s%s\n",
-		   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
-		   " NEARFULL" : "",
-		   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
-		   " FULL" : "");
-	for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
-		struct ceph_pg_pool_info *pool =
-			rb_entry(n, struct ceph_pg_pool_info, node);
-		seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n",
-			   pool->id, pool->v.pg_num, pool->pg_num_mask,
-			   pool->v.lpg_num, pool->lpg_num_mask);
-	}
-	for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
-		struct ceph_entity_addr *addr =
-			&client->osdc.osdmap->osd_addr[i];
-		int state = client->osdc.osdmap->osd_state[i];
-		char sb[64];
-
-		seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
-			   i, pr_addr(&addr->in_addr),
-			   ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
-			   ceph_osdmap_state_str(sb, sizeof(sb), state));
-	}
-	return 0;
-}
-
-static int monc_show(struct seq_file *s, void *p)
-{
-	struct ceph_client *client = s->private;
-	struct ceph_mon_generic_request *req;
-	struct ceph_mon_client *monc = &client->monc;
-	struct rb_node *rp;
-
-	mutex_lock(&monc->mutex);
-
-	if (monc->have_mdsmap)
-		seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap);
-	if (monc->have_osdmap)
-		seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap);
-	if (monc->want_next_osdmap)
-		seq_printf(s, "want next osdmap\n");
-
-	for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) {
-		__u16 op;
-		req = rb_entry(rp, struct ceph_mon_generic_request, node);
-		op = le16_to_cpu(req->request->hdr.type);
-		if (op == CEPH_MSG_STATFS)
-			seq_printf(s, "%lld statfs\n", req->tid);
-		else
-			seq_printf(s, "%lld unknown\n", req->tid);
-	}
-
-	mutex_unlock(&monc->mutex);
-	return 0;
-}
-
+/*
+ * mdsc debugfs
+ */
 static int mdsc_show(struct seq_file *s, void *p)
 {
-	struct ceph_client *client = s->private;
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	struct rb_node *rp;
 	int pathlen;
@@ -214,61 +120,12 @@
 	return 0;
 }
 
-static int osdc_show(struct seq_file *s, void *pp)
-{
-	struct ceph_client *client = s->private;
-	struct ceph_osd_client *osdc = &client->osdc;
-	struct rb_node *p;
-
-	mutex_lock(&osdc->request_mutex);
-	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
-		struct ceph_osd_request *req;
-		struct ceph_osd_request_head *head;
-		struct ceph_osd_op *op;
-		int num_ops;
-		int opcode, olen;
-		int i;
-
-		req = rb_entry(p, struct ceph_osd_request, r_node);
-
-		seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid,
-			   req->r_osd ? req->r_osd->o_osd : -1,
-			   le32_to_cpu(req->r_pgid.pool),
-			   le16_to_cpu(req->r_pgid.ps));
-
-		head = req->r_request->front.iov_base;
-		op = (void *)(head + 1);
-
-		num_ops = le16_to_cpu(head->num_ops);
-		olen = le32_to_cpu(head->object_len);
-		seq_printf(s, "%.*s", olen,
-			   (const char *)(head->ops + num_ops));
-
-		if (req->r_reassert_version.epoch)
-			seq_printf(s, "\t%u'%llu",
-			   (unsigned)le32_to_cpu(req->r_reassert_version.epoch),
-			   le64_to_cpu(req->r_reassert_version.version));
-		else
-			seq_printf(s, "\t");
-
-		for (i = 0; i < num_ops; i++) {
-			opcode = le16_to_cpu(op->op);
-			seq_printf(s, "\t%s", ceph_osd_op_name(opcode));
-			op++;
-		}
-
-		seq_printf(s, "\n");
-	}
-	mutex_unlock(&osdc->request_mutex);
-	return 0;
-}
-
 static int caps_show(struct seq_file *s, void *p)
 {
-	struct ceph_client *client = s->private;
+	struct ceph_fs_client *fsc = s->private;
 	int total, avail, used, reserved, min;
 
-	ceph_reservation_status(client, &total, &avail, &used, &reserved, &min);
+	ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min);
 	seq_printf(s, "total\t\t%d\n"
 		   "avail\t\t%d\n"
 		   "used\t\t%d\n"
@@ -280,8 +137,8 @@
 
 static int dentry_lru_show(struct seq_file *s, void *ptr)
 {
-	struct ceph_client *client = s->private;
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_dentry_info *di;
 
 	spin_lock(&mdsc->dentry_lru_lock);
@@ -295,199 +152,124 @@
 	return 0;
 }
 
-#define DEFINE_SHOW_FUNC(name)						\
-static int name##_open(struct inode *inode, struct file *file)		\
-{									\
-	struct seq_file *sf;						\
-	int ret;							\
-									\
-	ret = single_open(file, name, NULL);				\
-	sf = file->private_data;					\
-	sf->private = inode->i_private;					\
-	return ret;							\
-}									\
-									\
-static const struct file_operations name##_fops = {			\
-	.open		= name##_open,					\
-	.read		= seq_read,					\
-	.llseek		= seq_lseek,					\
-	.release	= single_release,				\
-};
+CEPH_DEFINE_SHOW_FUNC(mdsmap_show)
+CEPH_DEFINE_SHOW_FUNC(mdsc_show)
+CEPH_DEFINE_SHOW_FUNC(caps_show)
+CEPH_DEFINE_SHOW_FUNC(dentry_lru_show)
 
-DEFINE_SHOW_FUNC(monmap_show)
-DEFINE_SHOW_FUNC(mdsmap_show)
-DEFINE_SHOW_FUNC(osdmap_show)
-DEFINE_SHOW_FUNC(monc_show)
-DEFINE_SHOW_FUNC(mdsc_show)
-DEFINE_SHOW_FUNC(osdc_show)
-DEFINE_SHOW_FUNC(dentry_lru_show)
-DEFINE_SHOW_FUNC(caps_show)
 
+/*
+ * debugfs
+ */
 static int congestion_kb_set(void *data, u64 val)
 {
-	struct ceph_client *client = (struct ceph_client *)data;
+	struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
 
-	if (client)
-		client->mount_args->congestion_kb = (int)val;
-
+	fsc->mount_options->congestion_kb = (int)val;
 	return 0;
 }
 
 static int congestion_kb_get(void *data, u64 *val)
 {
-	struct ceph_client *client = (struct ceph_client *)data;
+	struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
 
-	if (client)
-		*val = (u64)client->mount_args->congestion_kb;
-
+	*val = (u64)fsc->mount_options->congestion_kb;
 	return 0;
 }
 
-
 DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get,
 			congestion_kb_set, "%llu\n");
 
-int __init ceph_debugfs_init(void)
+
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 {
-	ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
-	if (!ceph_debugfs_dir)
-		return -ENOMEM;
-	return 0;
+	dout("ceph_fs_debugfs_cleanup\n");
+	debugfs_remove(fsc->debugfs_bdi);
+	debugfs_remove(fsc->debugfs_congestion_kb);
+	debugfs_remove(fsc->debugfs_mdsmap);
+	debugfs_remove(fsc->debugfs_caps);
+	debugfs_remove(fsc->debugfs_mdsc);
+	debugfs_remove(fsc->debugfs_dentry_lru);
 }
 
-void ceph_debugfs_cleanup(void)
+int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 {
-	debugfs_remove(ceph_debugfs_dir);
-}
+	char name[100];
+	int err = -ENOMEM;
 
-int ceph_debugfs_client_init(struct ceph_client *client)
-{
-	int ret = 0;
-	char name[80];
-
-	snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
-		 client->monc.auth->global_id);
-
-	client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
-	if (!client->debugfs_dir)
-		goto out;
-
-	client->monc.debugfs_file = debugfs_create_file("monc",
-						      0600,
-						      client->debugfs_dir,
-						      client,
-						      &monc_show_fops);
-	if (!client->monc.debugfs_file)
-		goto out;
-
-	client->mdsc.debugfs_file = debugfs_create_file("mdsc",
-						      0600,
-						      client->debugfs_dir,
-						      client,
-						      &mdsc_show_fops);
-	if (!client->mdsc.debugfs_file)
-		goto out;
-
-	client->osdc.debugfs_file = debugfs_create_file("osdc",
-						      0600,
-						      client->debugfs_dir,
-						      client,
-						      &osdc_show_fops);
-	if (!client->osdc.debugfs_file)
-		goto out;
-
-	client->debugfs_monmap = debugfs_create_file("monmap",
-					0600,
-					client->debugfs_dir,
-					client,
-					&monmap_show_fops);
-	if (!client->debugfs_monmap)
-		goto out;
-
-	client->debugfs_mdsmap = debugfs_create_file("mdsmap",
-					0600,
-					client->debugfs_dir,
-					client,
-					&mdsmap_show_fops);
-	if (!client->debugfs_mdsmap)
-		goto out;
-
-	client->debugfs_osdmap = debugfs_create_file("osdmap",
-					0600,
-					client->debugfs_dir,
-					client,
-					&osdmap_show_fops);
-	if (!client->debugfs_osdmap)
-		goto out;
-
-	client->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
-					0600,
-					client->debugfs_dir,
-					client,
-					&dentry_lru_show_fops);
-	if (!client->debugfs_dentry_lru)
-		goto out;
-
-	client->debugfs_caps = debugfs_create_file("caps",
-						   0400,
-						   client->debugfs_dir,
-						   client,
-						   &caps_show_fops);
-	if (!client->debugfs_caps)
-		goto out;
-
-	client->debugfs_congestion_kb =
+	dout("ceph_fs_debugfs_init\n");
+	fsc->debugfs_congestion_kb =
 		debugfs_create_file("writeback_congestion_kb",
 				    0600,
-				    client->debugfs_dir,
-				    client,
+				    fsc->client->debugfs_dir,
+				    fsc,
 				    &congestion_kb_fops);
-	if (!client->debugfs_congestion_kb)
+	if (!fsc->debugfs_congestion_kb)
 		goto out;
 
-	sprintf(name, "../../bdi/%s", dev_name(client->sb->s_bdi->dev));
-	client->debugfs_bdi = debugfs_create_symlink("bdi", client->debugfs_dir,
-						     name);
+	dout("a\n");
+
+	snprintf(name, sizeof(name), "../../bdi/%s",
+		 dev_name(fsc->backing_dev_info.dev));
+	fsc->debugfs_bdi =
+		debugfs_create_symlink("bdi",
+				       fsc->client->debugfs_dir,
+				       name);
+	if (!fsc->debugfs_bdi)
+		goto out;
+
+	dout("b\n");
+	fsc->debugfs_mdsmap = debugfs_create_file("mdsmap",
+					0600,
+					fsc->client->debugfs_dir,
+					fsc,
+					&mdsmap_show_fops);
+	if (!fsc->debugfs_mdsmap)
+		goto out;
+
+	dout("ca\n");
+	fsc->debugfs_mdsc = debugfs_create_file("mdsc",
+						0600,
+						fsc->client->debugfs_dir,
+						fsc,
+						&mdsc_show_fops);
+	if (!fsc->debugfs_mdsc)
+		goto out;
+
+	dout("da\n");
+	fsc->debugfs_caps = debugfs_create_file("caps",
+						   0400,
+						   fsc->client->debugfs_dir,
+						   fsc,
+						   &caps_show_fops);
+	if (!fsc->debugfs_caps)
+		goto out;
+
+	dout("ea\n");
+	fsc->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
+					0600,
+					fsc->client->debugfs_dir,
+					fsc,
+					&dentry_lru_show_fops);
+	if (!fsc->debugfs_dentry_lru)
+		goto out;
 
 	return 0;
 
 out:
-	ceph_debugfs_client_cleanup(client);
-	return ret;
+	ceph_fs_debugfs_cleanup(fsc);
+	return err;
 }
 
-void ceph_debugfs_client_cleanup(struct ceph_client *client)
-{
-	debugfs_remove(client->debugfs_bdi);
-	debugfs_remove(client->debugfs_caps);
-	debugfs_remove(client->debugfs_dentry_lru);
-	debugfs_remove(client->debugfs_osdmap);
-	debugfs_remove(client->debugfs_mdsmap);
-	debugfs_remove(client->debugfs_monmap);
-	debugfs_remove(client->osdc.debugfs_file);
-	debugfs_remove(client->mdsc.debugfs_file);
-	debugfs_remove(client->monc.debugfs_file);
-	debugfs_remove(client->debugfs_congestion_kb);
-	debugfs_remove(client->debugfs_dir);
-}
 
 #else  /* CONFIG_DEBUG_FS */
 
-int __init ceph_debugfs_init(void)
+int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 {
 	return 0;
 }
 
-void ceph_debugfs_cleanup(void)
-{
-}
-
-int ceph_debugfs_client_init(struct ceph_client *client)
-{
-	return 0;
-}
-
-void ceph_debugfs_client_cleanup(struct ceph_client *client)
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 {
 }
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index a1986eb..e0a2dc6 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/spinlock.h>
 #include <linux/fs_struct.h>
@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 
 #include "super.h"
+#include "mds_client.h"
 
 /*
  * Directory operations: readdir, lookup, create, link, unlink,
@@ -94,10 +95,7 @@
  */
 static int __dcache_readdir(struct file *filp,
 			    void *dirent, filldir_t filldir)
-		__releases(inode->i_lock)
-		__acquires(inode->i_lock)
 {
-	struct inode *inode = filp->f_dentry->d_inode;
 	struct ceph_file_info *fi = filp->private_data;
 	struct dentry *parent = filp->f_dentry;
 	struct inode *dir = parent->d_inode;
@@ -153,7 +151,6 @@
 
 	atomic_inc(&dentry->d_count);
 	spin_unlock(&dcache_lock);
-	spin_unlock(&inode->i_lock);
 
 	dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos,
 	     dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
@@ -171,35 +168,30 @@
 		} else {
 			dput(last);
 		}
-		last = NULL;
 	}
-
-	spin_lock(&inode->i_lock);
-	spin_lock(&dcache_lock);
-
 	last = dentry;
 
 	if (err < 0)
-		goto out_unlock;
+		goto out;
 
-	p = p->prev;
 	filp->f_pos++;
 
 	/* make sure a dentry wasn't dropped while we didn't have dcache_lock */
-	if ((ceph_inode(dir)->i_ceph_flags & CEPH_I_COMPLETE))
-		goto more;
-	dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
-	err = -EAGAIN;
+	if (!ceph_i_test(dir, CEPH_I_COMPLETE)) {
+		dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
+		err = -EAGAIN;
+		goto out;
+	}
+
+	spin_lock(&dcache_lock);
+	p = p->prev;	/* advance to next dentry */
+	goto more;
 
 out_unlock:
 	spin_unlock(&dcache_lock);
-
-	if (last) {
-		spin_unlock(&inode->i_lock);
+out:
+	if (last)
 		dput(last);
-		spin_lock(&inode->i_lock);
-	}
-
 	return err;
 }
 
@@ -227,15 +219,15 @@
 	struct ceph_file_info *fi = filp->private_data;
 	struct inode *inode = filp->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_client *client = ceph_inode_to_client(inode);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	unsigned frag = fpos_frag(filp->f_pos);
 	int off = fpos_off(filp->f_pos);
 	int err;
 	u32 ftype;
 	struct ceph_mds_reply_info_parsed *rinfo;
-	const int max_entries = client->mount_args->max_readdir;
-	const int max_bytes = client->mount_args->max_readdir_bytes;
+	const int max_entries = fsc->mount_options->max_readdir;
+	const int max_bytes = fsc->mount_options->max_readdir_bytes;
 
 	dout("readdir %p filp %p frag %u off %u\n", inode, filp, frag, off);
 	if (fi->at_end)
@@ -267,17 +259,17 @@
 	/* can we use the dcache? */
 	spin_lock(&inode->i_lock);
 	if ((filp->f_pos == 2 || fi->dentry) &&
-	    !ceph_test_opt(client, NOASYNCREADDIR) &&
+	    !ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
 	    ceph_snap(inode) != CEPH_SNAPDIR &&
 	    (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
 	    __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
+		spin_unlock(&inode->i_lock);
 		err = __dcache_readdir(filp, dirent, filldir);
-		if (err != -EAGAIN) {
-			spin_unlock(&inode->i_lock);
+		if (err != -EAGAIN)
 			return err;
-		}
+	} else {
+		spin_unlock(&inode->i_lock);
 	}
-	spin_unlock(&inode->i_lock);
 	if (fi->dentry) {
 		err = note_last_dentry(fi, fi->dentry->d_name.name,
 				       fi->dentry->d_name.len);
@@ -487,14 +479,13 @@
 struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
 				  struct dentry *dentry, int err)
 {
-	struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
 	struct inode *parent = dentry->d_parent->d_inode;
 
 	/* .snap dir? */
 	if (err == -ENOENT &&
-	    ceph_vino(parent).ino != CEPH_INO_ROOT && /* no .snap in root dir */
 	    strcmp(dentry->d_name.name,
-		   client->mount_args->snapdir_name) == 0) {
+		   fsc->mount_options->snapdir_name) == 0) {
 		struct inode *inode = ceph_get_snapdir(parent);
 		dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
 		     dentry, dentry->d_name.len, dentry->d_name.name, inode);
@@ -539,8 +530,8 @@
 static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 				  struct nameidata *nd)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int op;
 	int err;
@@ -572,7 +563,7 @@
 		spin_lock(&dir->i_lock);
 		dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
 		if (strncmp(dentry->d_name.name,
-			    client->mount_args->snapdir_name,
+			    fsc->mount_options->snapdir_name,
 			    dentry->d_name.len) &&
 		    !is_root_ceph_dentry(dir, dentry) &&
 		    (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
@@ -629,8 +620,8 @@
 static int ceph_mknod(struct inode *dir, struct dentry *dentry,
 		      int mode, dev_t rdev)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -685,8 +676,8 @@
 static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 			    const char *dest)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -716,8 +707,8 @@
 
 static int ceph_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err = -EROFS;
 	int op;
@@ -758,8 +749,8 @@
 static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 		     struct dentry *dentry)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -813,8 +804,8 @@
  */
 static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = dentry->d_inode;
 	struct ceph_mds_request *req;
 	int err = -EROFS;
@@ -854,8 +845,8 @@
 static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
 		       struct inode *new_dir, struct dentry *new_dentry)
 {
-	struct ceph_client *client = ceph_sb_to_client(old_dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(old_dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -1076,7 +1067,7 @@
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int left;
 
-	if (!ceph_test_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
+	if (!ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
 		return -EISDIR;
 
 	if (!cf->dir_info) {
@@ -1177,7 +1168,7 @@
 	dout("dentry_lru_add %p %p '%.*s'\n", di, dn,
 	     dn->d_name.len, dn->d_name.name);
 	if (di) {
-		mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
 		spin_lock(&mdsc->dentry_lru_lock);
 		list_add_tail(&di->lru, &mdsc->dentry_lru);
 		mdsc->num_dentry++;
@@ -1193,7 +1184,7 @@
 	dout("dentry_lru_touch %p %p '%.*s' (offset %lld)\n", di, dn,
 	     dn->d_name.len, dn->d_name.name, di->offset);
 	if (di) {
-		mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
 		spin_lock(&mdsc->dentry_lru_lock);
 		list_move_tail(&di->lru, &mdsc->dentry_lru);
 		spin_unlock(&mdsc->dentry_lru_lock);
@@ -1208,7 +1199,7 @@
 	dout("dentry_lru_del %p %p '%.*s'\n", di, dn,
 	     dn->d_name.len, dn->d_name.name);
 	if (di) {
-		mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+		mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
 		spin_lock(&mdsc->dentry_lru_lock);
 		list_del_init(&di->lru);
 		mdsc->num_dentry--;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index e38423e..2297d94 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -1,10 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/exportfs.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
 
 #include "super.h"
+#include "mds_client.h"
 
 /*
  * NFS export support
@@ -120,7 +121,7 @@
 static struct dentry *__cfh_to_dentry(struct super_block *sb,
 				      struct ceph_nfs_confh *cfh)
 {
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
 	struct dentry *dentry;
 	struct ceph_vino vino;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 66e4da6..e77c28c 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1,5 +1,6 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/file.h>
@@ -38,8 +39,8 @@
 static struct ceph_mds_request *
 prepare_open_request(struct super_block *sb, int flags, int create_mode)
 {
-	struct ceph_client *client = ceph_sb_to_client(sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int want_auth = USE_ANY_MDS;
 	int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;
@@ -117,8 +118,8 @@
 int ceph_open(struct inode *inode, struct file *file)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_client *client = ceph_sb_to_client(inode->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	struct ceph_file_info *cf = file->private_data;
 	struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
@@ -216,8 +217,8 @@
 				struct nameidata *nd, int mode,
 				int locked_dir)
 {
-	struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct file *file = nd->intent.open.file;
 	struct inode *parent_inode = get_dentry_parent_inode(file->f_dentry);
 	struct ceph_mds_request *req;
@@ -270,163 +271,6 @@
 }
 
 /*
- * build a vector of user pages
- */
-static struct page **get_direct_page_vector(const char __user *data,
-					    int num_pages,
-					    loff_t off, size_t len)
-{
-	struct page **pages;
-	int rc;
-
-	pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
-	if (!pages)
-		return ERR_PTR(-ENOMEM);
-
-	down_read(&current->mm->mmap_sem);
-	rc = get_user_pages(current, current->mm, (unsigned long)data,
-			    num_pages, 0, 0, pages, NULL);
-	up_read(&current->mm->mmap_sem);
-	if (rc < 0)
-		goto fail;
-	return pages;
-
-fail:
-	kfree(pages);
-	return ERR_PTR(rc);
-}
-
-static void put_page_vector(struct page **pages, int num_pages)
-{
-	int i;
-
-	for (i = 0; i < num_pages; i++)
-		put_page(pages[i]);
-	kfree(pages);
-}
-
-void ceph_release_page_vector(struct page **pages, int num_pages)
-{
-	int i;
-
-	for (i = 0; i < num_pages; i++)
-		__free_pages(pages[i], 0);
-	kfree(pages);
-}
-
-/*
- * allocate a vector new pages
- */
-static struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags)
-{
-	struct page **pages;
-	int i;
-
-	pages = kmalloc(sizeof(*pages) * num_pages, flags);
-	if (!pages)
-		return ERR_PTR(-ENOMEM);
-	for (i = 0; i < num_pages; i++) {
-		pages[i] = __page_cache_alloc(flags);
-		if (pages[i] == NULL) {
-			ceph_release_page_vector(pages, i);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
-	return pages;
-}
-
-/*
- * copy user data into a page vector
- */
-static int copy_user_to_page_vector(struct page **pages,
-				    const char __user *data,
-				    loff_t off, size_t len)
-{
-	int i = 0;
-	int po = off & ~PAGE_CACHE_MASK;
-	int left = len;
-	int l, bad;
-
-	while (left > 0) {
-		l = min_t(int, PAGE_CACHE_SIZE-po, left);
-		bad = copy_from_user(page_address(pages[i]) + po, data, l);
-		if (bad == l)
-			return -EFAULT;
-		data += l - bad;
-		left -= l - bad;
-		po += l - bad;
-		if (po == PAGE_CACHE_SIZE) {
-			po = 0;
-			i++;
-		}
-	}
-	return len;
-}
-
-/*
- * copy user data from a page vector into a user pointer
- */
-static int copy_page_vector_to_user(struct page **pages, char __user *data,
-				    loff_t off, size_t len)
-{
-	int i = 0;
-	int po = off & ~PAGE_CACHE_MASK;
-	int left = len;
-	int l, bad;
-
-	while (left > 0) {
-		l = min_t(int, left, PAGE_CACHE_SIZE-po);
-		bad = copy_to_user(data, page_address(pages[i]) + po, l);
-		if (bad == l)
-			return -EFAULT;
-		data += l - bad;
-		left -= l - bad;
-		if (po) {
-			po += l - bad;
-			if (po == PAGE_CACHE_SIZE)
-				po = 0;
-		}
-		i++;
-	}
-	return len;
-}
-
-/*
- * Zero an extent within a page vector.  Offset is relative to the
- * start of the first page.
- */
-static void zero_page_vector_range(int off, int len, struct page **pages)
-{
-	int i = off >> PAGE_CACHE_SHIFT;
-
-	off &= ~PAGE_CACHE_MASK;
-
-	dout("zero_page_vector_page %u~%u\n", off, len);
-
-	/* leading partial page? */
-	if (off) {
-		int end = min((int)PAGE_CACHE_SIZE, off + len);
-		dout("zeroing %d %p head from %d\n", i, pages[i],
-		     (int)off);
-		zero_user_segment(pages[i], off, end);
-		len -= (end - off);
-		i++;
-	}
-	while (len >= PAGE_CACHE_SIZE) {
-		dout("zeroing %d %p len=%d\n", i, pages[i], len);
-		zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
-		len -= PAGE_CACHE_SIZE;
-		i++;
-	}
-	/* trailing partial page? */
-	if (len) {
-		dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len);
-		zero_user_segment(pages[i], 0, len);
-	}
-}
-
-
-/*
  * Read a range of bytes striped over one or more objects.  Iterate over
  * objects we stripe over.  (That's not atomic, but good enough for now.)
  *
@@ -438,7 +282,7 @@
 			struct page **pages, int num_pages,
 			int *checkeof)
 {
-	struct ceph_client *client = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 pos, this_len;
 	int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
@@ -459,7 +303,7 @@
 
 more:
 	this_len = left;
-	ret = ceph_osdc_readpages(&client->osdc, ceph_vino(inode),
+	ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
 				  &ci->i_layout, pos, &this_len,
 				  ci->i_truncate_seq,
 				  ci->i_truncate_size,
@@ -477,8 +321,8 @@
 
 		if (read < pos - off) {
 			dout(" zero gap %llu to %llu\n", off + read, pos);
-			zero_page_vector_range(page_off + read,
-					       pos - off - read, pages);
+			ceph_zero_page_vector_range(page_off + read,
+						    pos - off - read, pages);
 		}
 		pos += ret;
 		read = pos - off;
@@ -495,8 +339,8 @@
 		/* was original extent fully inside i_size? */
 		if (pos + left <= inode->i_size) {
 			dout("zero tail\n");
-			zero_page_vector_range(page_off + read, len - read,
-					       pages);
+			ceph_zero_page_vector_range(page_off + read, len - read,
+						    pages);
 			read = len;
 			goto out;
 		}
@@ -531,7 +375,7 @@
 	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
 
 	if (file->f_flags & O_DIRECT) {
-		pages = get_direct_page_vector(data, num_pages, off, len);
+		pages = ceph_get_direct_page_vector(data, num_pages, off, len);
 
 		/*
 		 * flush any page cache pages in this range.  this
@@ -552,13 +396,13 @@
 	ret = striped_read(inode, off, len, pages, num_pages, checkeof);
 
 	if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
-		ret = copy_page_vector_to_user(pages, data, off, ret);
+		ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
 	if (ret >= 0)
 		*poff = off + ret;
 
 done:
 	if (file->f_flags & O_DIRECT)
-		put_page_vector(pages, num_pages);
+		ceph_put_page_vector(pages, num_pages);
 	else
 		ceph_release_page_vector(pages, num_pages);
 	dout("sync_read result %d\n", ret);
@@ -594,7 +438,7 @@
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_client *client = ceph_inode_to_client(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_osd_request *req;
 	struct page **pages;
 	int num_pages;
@@ -642,7 +486,7 @@
 	 */
 more:
 	len = left;
-	req = ceph_osdc_new_request(&client->osdc, &ci->i_layout,
+	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), pos, &len,
 				    CEPH_OSD_OP_WRITE, flags,
 				    ci->i_snap_realm->cached_context,
@@ -655,7 +499,7 @@
 	num_pages = calc_pages_for(pos, len);
 
 	if (file->f_flags & O_DIRECT) {
-		pages = get_direct_page_vector(data, num_pages, pos, len);
+		pages = ceph_get_direct_page_vector(data, num_pages, pos, len);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
 			goto out;
@@ -673,7 +517,7 @@
 			ret = PTR_ERR(pages);
 			goto out;
 		}
-		ret = copy_user_to_page_vector(pages, data, pos, len);
+		ret = ceph_copy_user_to_page_vector(pages, data, pos, len);
 		if (ret < 0) {
 			ceph_release_page_vector(pages, num_pages);
 			goto out;
@@ -689,7 +533,7 @@
 	req->r_num_pages = num_pages;
 	req->r_inode = inode;
 
-	ret = ceph_osdc_start_request(&client->osdc, req, false);
+	ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
 	if (!ret) {
 		if (req->r_safe_callback) {
 			/*
@@ -701,11 +545,11 @@
 			spin_unlock(&ci->i_unsafe_lock);
 			ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
 		}
-		ret = ceph_osdc_wait_request(&client->osdc, req);
+		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
 	}
 
 	if (file->f_flags & O_DIRECT)
-		put_page_vector(pages, num_pages);
+		ceph_put_page_vector(pages, num_pages);
 	else if (file->f_flags & O_SYNC)
 		ceph_release_page_vector(pages, num_pages);
 
@@ -814,7 +658,8 @@
 	struct ceph_file_info *fi = file->private_data;
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc;
+	struct ceph_osd_client *osdc =
+		&ceph_sb_to_client(inode->i_sb)->client->osdc;
 	loff_t endoff = pos + iov->iov_len;
 	int want, got = 0;
 	int ret, err;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 62377ec..1d6a45b 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/module.h>
 #include <linux/fs.h>
@@ -13,7 +13,8 @@
 #include <linux/pagevec.h>
 
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+#include <linux/ceph/decode.h>
 
 /*
  * Ceph inode operations
@@ -384,7 +385,7 @@
 	 */
 	if (ci->i_snap_realm) {
 		struct ceph_mds_client *mdsc =
-			&ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+			ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
 		struct ceph_snap_realm *realm = ci->i_snap_realm;
 
 		dout(" dropping residual ref to snap realm %p\n", realm);
@@ -685,7 +686,7 @@
 		}
 
 		/* it may be better to set st_size in getattr instead? */
-		if (ceph_test_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
+		if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
 			inode->i_size = ci->i_rbytes;
 		break;
 	default:
@@ -901,7 +902,7 @@
 	struct inode *in = NULL;
 	struct ceph_mds_reply_inode *ininfo;
 	struct ceph_vino vino;
-	struct ceph_client *client = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 	int i = 0;
 	int err = 0;
 
@@ -965,7 +966,7 @@
 	 */
 	if (rinfo->head->is_dentry && !req->r_aborted &&
 	    (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
-					       client->mount_args->snapdir_name,
+					       fsc->mount_options->snapdir_name,
 					       req->r_dentry->d_name.len))) {
 		/*
 		 * lookup link rename   : null -> possibly existing inode
@@ -1533,7 +1534,7 @@
 	struct inode *parent_inode = dentry->d_parent->d_inode;
 	const unsigned int ia_valid = attr->ia_valid;
 	struct ceph_mds_request *req;
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(dentry->d_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
 	int issued;
 	int release = 0, dirtied = 0;
 	int mask = 0;
@@ -1728,8 +1729,8 @@
  */
 int ceph_do_getattr(struct inode *inode, int mask)
 {
-	struct ceph_client *client = ceph_sb_to_client(inode->i_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 76e307d..8888c9ba 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -1,8 +1,10 @@
 #include <linux/in.h>
 
-#include "ioctl.h"
 #include "super.h"
-#include "ceph_debug.h"
+#include "mds_client.h"
+#include <linux/ceph/ceph_debug.h>
+
+#include "ioctl.h"
 
 
 /*
@@ -37,7 +39,7 @@
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_mds_request *req;
 	struct ceph_ioctl_layout l;
 	int err, i;
@@ -90,6 +92,68 @@
 }
 
 /*
+ * Set a layout policy on a directory inode. All items in the tree
+ * rooted at this inode will inherit this layout on creation,
+ * (It doesn't apply retroactively )
+ * unless a subdirectory has its own layout policy.
+ */
+static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	struct ceph_mds_request *req;
+	struct ceph_ioctl_layout l;
+	int err, i;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+
+	/* copy and validate */
+	if (copy_from_user(&l, arg, sizeof(l)))
+		return -EFAULT;
+
+	if ((l.object_size & ~PAGE_MASK) ||
+	    (l.stripe_unit & ~PAGE_MASK) ||
+	    !l.stripe_unit ||
+	    (l.object_size &&
+	        (unsigned)l.object_size % (unsigned)l.stripe_unit))
+		return -EINVAL;
+
+	/* make sure it's a valid data pool */
+	if (l.data_pool > 0) {
+		mutex_lock(&mdsc->mutex);
+		err = -EINVAL;
+		for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
+			if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
+				err = 0;
+				break;
+			}
+		mutex_unlock(&mdsc->mutex);
+		if (err)
+			return err;
+	}
+
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
+				       USE_AUTH_MDS);
+
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	req->r_inode = igrab(inode);
+
+	req->r_args.setlayout.layout.fl_stripe_unit =
+			cpu_to_le32(l.stripe_unit);
+	req->r_args.setlayout.layout.fl_stripe_count =
+			cpu_to_le32(l.stripe_count);
+	req->r_args.setlayout.layout.fl_object_size =
+			cpu_to_le32(l.object_size);
+	req->r_args.setlayout.layout.fl_pg_pool =
+			cpu_to_le32(l.data_pool);
+	req->r_args.setlayout.layout.fl_pg_preferred =
+			cpu_to_le32(l.preferred_osd);
+
+	err = ceph_mdsc_do_request(mdsc, inode, req);
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
+/*
  * Return object name, size/offset information, and location (OSD
  * number, network address) for a given file offset.
  */
@@ -98,7 +162,8 @@
 	struct ceph_ioctl_dataloc dl;
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc;
+	struct ceph_osd_client *osdc =
+		&ceph_sb_to_client(inode->i_sb)->client->osdc;
 	u64 len = 1, olen;
 	u64 tmp;
 	struct ceph_object_layout ol;
@@ -174,11 +239,15 @@
 	case CEPH_IOC_SET_LAYOUT:
 		return ceph_ioctl_set_layout(file, (void __user *)arg);
 
+	case CEPH_IOC_SET_LAYOUT_POLICY:
+		return ceph_ioctl_set_layout_policy(file, (void __user *)arg);
+
 	case CEPH_IOC_GET_DATALOC:
 		return ceph_ioctl_get_dataloc(file, (void __user *)arg);
 
 	case CEPH_IOC_LAZYIO:
 		return ceph_ioctl_lazyio(file);
 	}
+
 	return -ENOTTY;
 }
diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h
index 88451a3..a6ce54e 100644
--- a/fs/ceph/ioctl.h
+++ b/fs/ceph/ioctl.h
@@ -4,7 +4,7 @@
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
-#define CEPH_IOCTL_MAGIC 0x97
+#define CEPH_IOCTL_MAGIC 0x98
 
 /* just use u64 to align sanely on all archs */
 struct ceph_ioctl_layout {
@@ -17,6 +17,8 @@
 				   struct ceph_ioctl_layout)
 #define CEPH_IOC_SET_LAYOUT _IOW(CEPH_IOCTL_MAGIC, 2,		\
 				   struct ceph_ioctl_layout)
+#define CEPH_IOC_SET_LAYOUT_POLICY _IOW(CEPH_IOCTL_MAGIC, 5,	\
+				   struct ceph_ioctl_layout)
 
 /*
  * Extract identity, address of the OSD and object storing a given
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ff4e753..40abde9 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -1,11 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/file.h>
 #include <linux/namei.h>
 
 #include "super.h"
 #include "mds_client.h"
-#include "pagelist.h"
+#include <linux/ceph/pagelist.h>
 
 /**
  * Implement fcntl and flock locking functions.
@@ -16,7 +16,7 @@
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct ceph_mds_client *mdsc =
-		&ceph_sb_to_client(inode->i_sb)->mdsc;
+		ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 
@@ -181,8 +181,9 @@
  * Encode the flock and fcntl locks for the given inode into the pagelist.
  * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
  * sequential flock locks.
- * Must be called with BLK already held, and the lock numbers should have
- * been gathered under the same lock holding window.
+ * Must be called with lock_flocks() already held.
+ * If we encounter more of a specific lock type than expected,
+ * we return the value 1.
  */
 int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
 		      int num_fcntl_locks, int num_flock_locks)
@@ -190,6 +191,8 @@
 	struct file_lock *lock;
 	struct ceph_filelock cephlock;
 	int err = 0;
+	int seen_fcntl = 0;
+	int seen_flock = 0;
 
 	dout("encoding %d flock and %d fcntl locks", num_flock_locks,
 	     num_fcntl_locks);
@@ -198,6 +201,11 @@
 		goto fail;
 	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
 		if (lock->fl_flags & FL_POSIX) {
+			++seen_fcntl;
+			if (seen_fcntl > num_fcntl_locks) {
+				err = -ENOSPC;
+				goto fail;
+			}
 			err = lock_to_ceph_filelock(lock, &cephlock);
 			if (err)
 				goto fail;
@@ -213,6 +221,11 @@
 		goto fail;
 	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
 		if (lock->fl_flags & FL_FLOCK) {
+			++seen_flock;
+			if (seen_flock > num_flock_locks) {
+				err = -ENOSPC;
+				goto fail;
+			}
 			err = lock_to_ceph_filelock(lock, &cephlock);
 			if (err)
 				goto fail;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index fad95f8..3142b15 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1,17 +1,21 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/fs.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 #include <linux/smp_lock.h>
 
-#include "mds_client.h"
-#include "mon_client.h"
 #include "super.h"
-#include "messenger.h"
-#include "decode.h"
-#include "auth.h"
-#include "pagelist.h"
+#include "mds_client.h"
+
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/pagelist.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
 
 /*
  * A cluster of MDS (metadata server) daemons is responsible for
@@ -286,8 +290,9 @@
 	     atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
 	if (atomic_dec_and_test(&s->s_ref)) {
 		if (s->s_authorizer)
-			s->s_mdsc->client->monc.auth->ops->destroy_authorizer(
-				s->s_mdsc->client->monc.auth, s->s_authorizer);
+		     s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer(
+			     s->s_mdsc->fsc->client->monc.auth,
+			     s->s_authorizer);
 		kfree(s);
 	}
 }
@@ -344,7 +349,7 @@
 	s->s_seq = 0;
 	mutex_init(&s->s_mutex);
 
-	ceph_con_init(mdsc->client->msgr, &s->s_con);
+	ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
 	s->s_con.private = s;
 	s->s_con.ops = &mds_con_ops;
 	s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
@@ -599,7 +604,7 @@
 	} else if (req->r_dentry) {
 		struct inode *dir = req->r_dentry->d_parent->d_inode;
 
-		if (dir->i_sb != mdsc->client->sb) {
+		if (dir->i_sb != mdsc->fsc->sb) {
 			/* not this fs! */
 			inode = req->r_dentry->d_inode;
 		} else if (ceph_snap(dir) != CEPH_NOSNAP) {
@@ -884,7 +889,7 @@
 	__ceph_remove_cap(cap);
 	if (!__ceph_is_any_real_caps(ci)) {
 		struct ceph_mds_client *mdsc =
-			&ceph_sb_to_client(inode->i_sb)->mdsc;
+			ceph_sb_to_client(inode->i_sb)->mdsc;
 
 		spin_lock(&mdsc->cap_dirty_lock);
 		if (!list_empty(&ci->i_dirty_item)) {
@@ -1146,7 +1151,7 @@
 	struct ceph_msg *msg, *partial = NULL;
 	struct ceph_mds_cap_release *head;
 	int err = -ENOMEM;
-	int extra = mdsc->client->mount_args->cap_release_safety;
+	int extra = mdsc->fsc->mount_options->cap_release_safety;
 	int num;
 
 	dout("add_cap_releases %p mds%d extra %d\n", session, session->s_mds,
@@ -2085,7 +2090,7 @@
 
 	/* insert trace into our cache */
 	mutex_lock(&req->r_fill_mutex);
-	err = ceph_fill_trace(mdsc->client->sb, req, req->r_session);
+	err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
 	if (err == 0) {
 		if (result == 0 && rinfo->dir_nr)
 			ceph_readdir_prepopulate(req, req->r_session);
@@ -2361,19 +2366,35 @@
 
 	if (recon_state->flock) {
 		int num_fcntl_locks, num_flock_locks;
+		struct ceph_pagelist_cursor trunc_point;
 
-		lock_kernel();
-		ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
-		rec.v2.flock_len = (2*sizeof(u32) +
-				    (num_fcntl_locks+num_flock_locks) *
-				    sizeof(struct ceph_filelock));
+		ceph_pagelist_set_cursor(pagelist, &trunc_point);
+		do {
+			lock_flocks();
+			ceph_count_locks(inode, &num_fcntl_locks,
+					 &num_flock_locks);
+			rec.v2.flock_len = (2*sizeof(u32) +
+					    (num_fcntl_locks+num_flock_locks) *
+					    sizeof(struct ceph_filelock));
+			unlock_flocks();
 
-		err = ceph_pagelist_append(pagelist, &rec, reclen);
-		if (!err)
-			err = ceph_encode_locks(inode, pagelist,
-						num_fcntl_locks,
-						num_flock_locks);
-		unlock_kernel();
+			/* pre-alloc pagelist */
+			ceph_pagelist_truncate(pagelist, &trunc_point);
+			err = ceph_pagelist_append(pagelist, &rec, reclen);
+			if (!err)
+				err = ceph_pagelist_reserve(pagelist,
+							    rec.v2.flock_len);
+
+			/* encode locks */
+			if (!err) {
+				lock_flocks();
+				err = ceph_encode_locks(inode,
+							pagelist,
+							num_fcntl_locks,
+							num_flock_locks);
+				unlock_flocks();
+			}
+		} while (err == -ENOSPC);
 	} else {
 		err = ceph_pagelist_append(pagelist, &rec, reclen);
 	}
@@ -2613,7 +2634,7 @@
 			 struct ceph_mds_session *session,
 			 struct ceph_msg *msg)
 {
-	struct super_block *sb = mdsc->client->sb;
+	struct super_block *sb = mdsc->fsc->sb;
 	struct inode *inode;
 	struct ceph_inode_info *ci;
 	struct dentry *parent, *dentry;
@@ -2891,10 +2912,16 @@
 	schedule_delayed(mdsc);
 }
 
+int ceph_mdsc_init(struct ceph_fs_client *fsc)
 
-int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client)
 {
-	mdsc->client = client;
+	struct ceph_mds_client *mdsc;
+
+	mdsc = kzalloc(sizeof(struct ceph_mds_client), GFP_NOFS);
+	if (!mdsc)
+		return -ENOMEM;
+	mdsc->fsc = fsc;
+	fsc->mdsc = mdsc;
 	mutex_init(&mdsc->mutex);
 	mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS);
 	if (mdsc->mdsmap == NULL)
@@ -2927,7 +2954,7 @@
 	INIT_LIST_HEAD(&mdsc->dentry_lru);
 
 	ceph_caps_init(mdsc);
-	ceph_adjust_min_caps(mdsc, client->min_caps);
+	ceph_adjust_min_caps(mdsc, fsc->min_caps);
 
 	return 0;
 }
@@ -2939,7 +2966,7 @@
 static void wait_requests(struct ceph_mds_client *mdsc)
 {
 	struct ceph_mds_request *req;
-	struct ceph_client *client = mdsc->client;
+	struct ceph_fs_client *fsc = mdsc->fsc;
 
 	mutex_lock(&mdsc->mutex);
 	if (__get_oldest_req(mdsc)) {
@@ -2947,7 +2974,7 @@
 
 		dout("wait_requests waiting for requests\n");
 		wait_for_completion_timeout(&mdsc->safe_umount_waiters,
-				    client->mount_args->mount_timeout * HZ);
+				    fsc->client->options->mount_timeout * HZ);
 
 		/* tear down remaining requests */
 		mutex_lock(&mdsc->mutex);
@@ -3030,7 +3057,7 @@
 {
 	u64 want_tid, want_flush;
 
-	if (mdsc->client->mount_state == CEPH_MOUNT_SHUTDOWN)
+	if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
 		return;
 
 	dout("sync\n");
@@ -3053,7 +3080,7 @@
 {
 	int i, n = 0;
 
-	if (mdsc->client->mount_state == CEPH_MOUNT_SHUTDOWN)
+	if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
 		return true;
 
 	mutex_lock(&mdsc->mutex);
@@ -3071,8 +3098,8 @@
 {
 	struct ceph_mds_session *session;
 	int i;
-	struct ceph_client *client = mdsc->client;
-	unsigned long timeout = client->mount_args->mount_timeout * HZ;
+	struct ceph_fs_client *fsc = mdsc->fsc;
+	unsigned long timeout = fsc->client->options->mount_timeout * HZ;
 
 	dout("close_sessions\n");
 
@@ -3119,7 +3146,7 @@
 	dout("stopped\n");
 }
 
-void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
+static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 {
 	dout("stop\n");
 	cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
@@ -3129,6 +3156,15 @@
 	ceph_caps_finalize(mdsc);
 }
 
+void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
+{
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+
+	ceph_mdsc_stop(mdsc);
+	fsc->mdsc = NULL;
+	kfree(mdsc);
+}
+
 
 /*
  * handle mds map update.
@@ -3145,14 +3181,14 @@
 
 	ceph_decode_need(&p, end, sizeof(fsid)+2*sizeof(u32), bad);
 	ceph_decode_copy(&p, &fsid, sizeof(fsid));
-	if (ceph_check_fsid(mdsc->client, &fsid) < 0)
+	if (ceph_check_fsid(mdsc->fsc->client, &fsid) < 0)
 		return;
 	epoch = ceph_decode_32(&p);
 	maplen = ceph_decode_32(&p);
 	dout("handle_map epoch %u len %d\n", epoch, (int)maplen);
 
 	/* do we need it? */
-	ceph_monc_got_mdsmap(&mdsc->client->monc, epoch);
+	ceph_monc_got_mdsmap(&mdsc->fsc->client->monc, epoch);
 	mutex_lock(&mdsc->mutex);
 	if (mdsc->mdsmap && epoch <= mdsc->mdsmap->m_epoch) {
 		dout("handle_map epoch %u <= our %u\n",
@@ -3176,7 +3212,7 @@
 	} else {
 		mdsc->mdsmap = newmap;  /* first mds map */
 	}
-	mdsc->client->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size;
+	mdsc->fsc->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size;
 
 	__wake_requests(mdsc, &mdsc->waiting_for_map);
 
@@ -3277,7 +3313,7 @@
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
-	struct ceph_auth_client *ac = mdsc->client->monc.auth;
+	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 	int ret = 0;
 
 	if (force_new && s->s_authorizer) {
@@ -3311,7 +3347,7 @@
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
-	struct ceph_auth_client *ac = mdsc->client->monc.auth;
+	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
 	return ac->ops->verify_authorizer_reply(ac, s->s_authorizer, len);
 }
@@ -3320,12 +3356,12 @@
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
-	struct ceph_auth_client *ac = mdsc->client->monc.auth;
+	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
 	if (ac->ops->invalidate_authorizer)
 		ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_MDS);
 
-	return ceph_monc_validate_auth(&mdsc->client->monc);
+	return ceph_monc_validate_auth(&mdsc->fsc->client->monc);
 }
 
 static const struct ceph_connection_operations mds_con_ops = {
@@ -3338,7 +3374,4 @@
 	.peer_reset = peer_reset,
 };
 
-
-
-
 /* eof */
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index c98267c..d66d63c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -8,9 +8,9 @@
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
 
-#include "types.h"
-#include "messenger.h"
-#include "mdsmap.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/mdsmap.h>
 
 /*
  * Some lock dependencies:
@@ -26,7 +26,7 @@
  *
  */
 
-struct ceph_client;
+struct ceph_fs_client;
 struct ceph_cap;
 
 /*
@@ -230,7 +230,7 @@
  * mds client state
  */
 struct ceph_mds_client {
-	struct ceph_client      *client;
+	struct ceph_fs_client  *fsc;
 	struct mutex            mutex;         /* all nested structures */
 
 	struct ceph_mdsmap      *mdsmap;
@@ -289,11 +289,6 @@
 	int		caps_avail_count;    /* unused, unreserved */
 	int		caps_min_count;      /* keep at least this many
 						(unreserved) */
-
-#ifdef CONFIG_DEBUG_FS
-	struct dentry 	  *debugfs_file;
-#endif
-
 	spinlock_t	  dentry_lru_lock;
 	struct list_head  dentry_lru;
 	int		  num_dentry;
@@ -316,10 +311,9 @@
 extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
 			     struct ceph_msg *msg, int mds);
 
-extern int ceph_mdsc_init(struct ceph_mds_client *mdsc,
-			   struct ceph_client *client);
+extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
 extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
-extern void ceph_mdsc_stop(struct ceph_mds_client *mdsc);
+extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
 
 extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
 
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 040be6d..73b7d44 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/bug.h>
 #include <linux/err.h>
@@ -6,9 +6,9 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#include "mdsmap.h"
-#include "messenger.h"
-#include "decode.h"
+#include <linux/ceph/mdsmap.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
 
 #include "super.h"
 
@@ -117,7 +117,8 @@
 		}
 
 		dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n",
-		     i+1, n, global_id, mds, inc, pr_addr(&addr.in_addr),
+		     i+1, n, global_id, mds, inc,
+		     ceph_pr_addr(&addr.in_addr),
 		     ceph_mds_state_name(state));
 		if (mds >= 0 && mds < m->m_max_mds && state > 0) {
 			m->m_info[mds].global_id = global_id;
diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c
deleted file mode 100644
index 46a368b..0000000
--- a/fs/ceph/pagelist.c
+++ /dev/null
@@ -1,63 +0,0 @@
-
-#include <linux/gfp.h>
-#include <linux/pagemap.h>
-#include <linux/highmem.h>
-
-#include "pagelist.h"
-
-static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
-{
-	struct page *page = list_entry(pl->head.prev, struct page,
-				       lru);
-	kunmap(page);
-}
-
-int ceph_pagelist_release(struct ceph_pagelist *pl)
-{
-	if (pl->mapped_tail)
-		ceph_pagelist_unmap_tail(pl);
-
-	while (!list_empty(&pl->head)) {
-		struct page *page = list_first_entry(&pl->head, struct page,
-						     lru);
-		list_del(&page->lru);
-		__free_page(page);
-	}
-	return 0;
-}
-
-static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
-{
-	struct page *page = __page_cache_alloc(GFP_NOFS);
-	if (!page)
-		return -ENOMEM;
-	pl->room += PAGE_SIZE;
-	list_add_tail(&page->lru, &pl->head);
-	if (pl->mapped_tail)
-		ceph_pagelist_unmap_tail(pl);
-	pl->mapped_tail = kmap(page);
-	return 0;
-}
-
-int ceph_pagelist_append(struct ceph_pagelist *pl, void *buf, size_t len)
-{
-	while (pl->room < len) {
-		size_t bit = pl->room;
-		int ret;
-
-		memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK),
-		       buf, bit);
-		pl->length += bit;
-		pl->room -= bit;
-		buf += bit;
-		len -= bit;
-		ret = ceph_pagelist_addpage(pl);
-		if (ret)
-			return ret;
-	}
-
-	memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len);
-	pl->length += len;
-	pl->room -= len;
-	return 0;
-}
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 190b6c4..39c243a 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1,10 +1,12 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/sort.h>
 #include <linux/slab.h>
 
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
 
 /*
  * Snapshots in ceph are driven in large part by cooperation from the
@@ -526,7 +528,7 @@
 			    struct ceph_cap_snap *capsnap)
 {
 	struct inode *inode = &ci->vfs_inode;
-	struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 
 	BUG_ON(capsnap->writing);
 	capsnap->size = inode->i_size;
@@ -747,7 +749,7 @@
 		      struct ceph_mds_session *session,
 		      struct ceph_msg *msg)
 {
-	struct super_block *sb = mdsc->client->sb;
+	struct super_block *sb = mdsc->fsc->sb;
 	int mds = session->s_mds;
 	u64 split;
 	int op;
diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c
new file mode 100644
index 0000000..cd5097d
--- /dev/null
+++ b/fs/ceph/strings.c
@@ -0,0 +1,117 @@
+/*
+ * Ceph fs string constants
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+
+const char *ceph_mds_state_name(int s)
+{
+	switch (s) {
+		/* down and out */
+	case CEPH_MDS_STATE_DNE:        return "down:dne";
+	case CEPH_MDS_STATE_STOPPED:    return "down:stopped";
+		/* up and out */
+	case CEPH_MDS_STATE_BOOT:       return "up:boot";
+	case CEPH_MDS_STATE_STANDBY:    return "up:standby";
+	case CEPH_MDS_STATE_STANDBY_REPLAY:    return "up:standby-replay";
+	case CEPH_MDS_STATE_CREATING:   return "up:creating";
+	case CEPH_MDS_STATE_STARTING:   return "up:starting";
+		/* up and in */
+	case CEPH_MDS_STATE_REPLAY:     return "up:replay";
+	case CEPH_MDS_STATE_RESOLVE:    return "up:resolve";
+	case CEPH_MDS_STATE_RECONNECT:  return "up:reconnect";
+	case CEPH_MDS_STATE_REJOIN:     return "up:rejoin";
+	case CEPH_MDS_STATE_CLIENTREPLAY: return "up:clientreplay";
+	case CEPH_MDS_STATE_ACTIVE:     return "up:active";
+	case CEPH_MDS_STATE_STOPPING:   return "up:stopping";
+	}
+	return "???";
+}
+
+const char *ceph_session_op_name(int op)
+{
+	switch (op) {
+	case CEPH_SESSION_REQUEST_OPEN: return "request_open";
+	case CEPH_SESSION_OPEN: return "open";
+	case CEPH_SESSION_REQUEST_CLOSE: return "request_close";
+	case CEPH_SESSION_CLOSE: return "close";
+	case CEPH_SESSION_REQUEST_RENEWCAPS: return "request_renewcaps";
+	case CEPH_SESSION_RENEWCAPS: return "renewcaps";
+	case CEPH_SESSION_STALE: return "stale";
+	case CEPH_SESSION_RECALL_STATE: return "recall_state";
+	}
+	return "???";
+}
+
+const char *ceph_mds_op_name(int op)
+{
+	switch (op) {
+	case CEPH_MDS_OP_LOOKUP:  return "lookup";
+	case CEPH_MDS_OP_LOOKUPHASH:  return "lookuphash";
+	case CEPH_MDS_OP_LOOKUPPARENT:  return "lookupparent";
+	case CEPH_MDS_OP_GETATTR:  return "getattr";
+	case CEPH_MDS_OP_SETXATTR: return "setxattr";
+	case CEPH_MDS_OP_SETATTR: return "setattr";
+	case CEPH_MDS_OP_RMXATTR: return "rmxattr";
+	case CEPH_MDS_OP_READDIR: return "readdir";
+	case CEPH_MDS_OP_MKNOD: return "mknod";
+	case CEPH_MDS_OP_LINK: return "link";
+	case CEPH_MDS_OP_UNLINK: return "unlink";
+	case CEPH_MDS_OP_RENAME: return "rename";
+	case CEPH_MDS_OP_MKDIR: return "mkdir";
+	case CEPH_MDS_OP_RMDIR: return "rmdir";
+	case CEPH_MDS_OP_SYMLINK: return "symlink";
+	case CEPH_MDS_OP_CREATE: return "create";
+	case CEPH_MDS_OP_OPEN: return "open";
+	case CEPH_MDS_OP_LOOKUPSNAP: return "lookupsnap";
+	case CEPH_MDS_OP_LSSNAP: return "lssnap";
+	case CEPH_MDS_OP_MKSNAP: return "mksnap";
+	case CEPH_MDS_OP_RMSNAP: return "rmsnap";
+	case CEPH_MDS_OP_SETFILELOCK: return "setfilelock";
+	case CEPH_MDS_OP_GETFILELOCK: return "getfilelock";
+	}
+	return "???";
+}
+
+const char *ceph_cap_op_name(int op)
+{
+	switch (op) {
+	case CEPH_CAP_OP_GRANT: return "grant";
+	case CEPH_CAP_OP_REVOKE: return "revoke";
+	case CEPH_CAP_OP_TRUNC: return "trunc";
+	case CEPH_CAP_OP_EXPORT: return "export";
+	case CEPH_CAP_OP_IMPORT: return "import";
+	case CEPH_CAP_OP_UPDATE: return "update";
+	case CEPH_CAP_OP_DROP: return "drop";
+	case CEPH_CAP_OP_FLUSH: return "flush";
+	case CEPH_CAP_OP_FLUSH_ACK: return "flush_ack";
+	case CEPH_CAP_OP_FLUSHSNAP: return "flushsnap";
+	case CEPH_CAP_OP_FLUSHSNAP_ACK: return "flushsnap_ack";
+	case CEPH_CAP_OP_RELEASE: return "release";
+	case CEPH_CAP_OP_RENEW: return "renew";
+	}
+	return "???";
+}
+
+const char *ceph_lease_op_name(int o)
+{
+	switch (o) {
+	case CEPH_MDS_LEASE_REVOKE: return "revoke";
+	case CEPH_MDS_LEASE_RELEASE: return "release";
+	case CEPH_MDS_LEASE_RENEW: return "renew";
+	case CEPH_MDS_LEASE_REVOKE_ACK: return "revoke_ack";
+	}
+	return "???";
+}
+
+const char *ceph_snap_op_name(int o)
+{
+	switch (o) {
+	case CEPH_SNAP_OP_UPDATE: return "update";
+	case CEPH_SNAP_OP_CREATE: return "create";
+	case CEPH_SNAP_OP_DESTROY: return "destroy";
+	case CEPH_SNAP_OP_SPLIT: return "split";
+	}
+	return "???";
+}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 9922628..d6e0e04 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1,5 +1,5 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/backing-dev.h>
 #include <linux/ctype.h>
@@ -15,10 +15,13 @@
 #include <linux/statfs.h>
 #include <linux/string.h>
 
-#include "decode.h"
 #include "super.h"
-#include "mon_client.h"
-#include "auth.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
 
 /*
  * Ceph superblock operations
@@ -26,36 +29,22 @@
  * Handle the basics of mounting, unmounting.
  */
 
-
-/*
- * find filename portion of a path (/foo/bar/baz -> baz)
- */
-const char *ceph_file_part(const char *s, int len)
-{
-	const char *e = s + len;
-
-	while (e != s && *(e-1) != '/')
-		e--;
-	return e;
-}
-
-
 /*
  * super ops
  */
 static void ceph_put_super(struct super_block *s)
 {
-	struct ceph_client *client = ceph_sb_to_client(s);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
 
 	dout("put_super\n");
-	ceph_mdsc_close_sessions(&client->mdsc);
+	ceph_mdsc_close_sessions(fsc->mdsc);
 
 	/*
 	 * ensure we release the bdi before put_anon_super releases
 	 * the device name.
 	 */
-	if (s->s_bdi == &client->backing_dev_info) {
-		bdi_unregister(&client->backing_dev_info);
+	if (s->s_bdi == &fsc->backing_dev_info) {
+		bdi_unregister(&fsc->backing_dev_info);
 		s->s_bdi = NULL;
 	}
 
@@ -64,14 +53,14 @@
 
 static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct ceph_client *client = ceph_inode_to_client(dentry->d_inode);
-	struct ceph_monmap *monmap = client->monc.monmap;
+	struct ceph_fs_client *fsc = ceph_inode_to_client(dentry->d_inode);
+	struct ceph_monmap *monmap = fsc->client->monc.monmap;
 	struct ceph_statfs st;
 	u64 fsid;
 	int err;
 
 	dout("statfs\n");
-	err = ceph_monc_do_statfs(&client->monc, &st);
+	err = ceph_monc_do_statfs(&fsc->client->monc, &st);
 	if (err < 0)
 		return err;
 
@@ -104,49 +93,237 @@
 
 static int ceph_sync_fs(struct super_block *sb, int wait)
 {
-	struct ceph_client *client = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 
 	if (!wait) {
 		dout("sync_fs (non-blocking)\n");
-		ceph_flush_dirty_caps(&client->mdsc);
+		ceph_flush_dirty_caps(fsc->mdsc);
 		dout("sync_fs (non-blocking) done\n");
 		return 0;
 	}
 
 	dout("sync_fs (blocking)\n");
-	ceph_osdc_sync(&ceph_sb_to_client(sb)->osdc);
-	ceph_mdsc_sync(&ceph_sb_to_client(sb)->mdsc);
+	ceph_osdc_sync(&fsc->client->osdc);
+	ceph_mdsc_sync(fsc->mdsc);
 	dout("sync_fs (blocking) done\n");
 	return 0;
 }
 
-static int default_congestion_kb(void)
+/*
+ * mount options
+ */
+enum {
+	Opt_wsize,
+	Opt_rsize,
+	Opt_caps_wanted_delay_min,
+	Opt_caps_wanted_delay_max,
+	Opt_cap_release_safety,
+	Opt_readdir_max_entries,
+	Opt_readdir_max_bytes,
+	Opt_congestion_kb,
+	Opt_last_int,
+	/* int args above */
+	Opt_snapdirname,
+	Opt_last_string,
+	/* string args above */
+	Opt_dirstat,
+	Opt_nodirstat,
+	Opt_rbytes,
+	Opt_norbytes,
+	Opt_noasyncreaddir,
+};
+
+static match_table_t fsopt_tokens = {
+	{Opt_wsize, "wsize=%d"},
+	{Opt_rsize, "rsize=%d"},
+	{Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"},
+	{Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"},
+	{Opt_cap_release_safety, "cap_release_safety=%d"},
+	{Opt_readdir_max_entries, "readdir_max_entries=%d"},
+	{Opt_readdir_max_bytes, "readdir_max_bytes=%d"},
+	{Opt_congestion_kb, "write_congestion_kb=%d"},
+	/* int args above */
+	{Opt_snapdirname, "snapdirname=%s"},
+	/* string args above */
+	{Opt_dirstat, "dirstat"},
+	{Opt_nodirstat, "nodirstat"},
+	{Opt_rbytes, "rbytes"},
+	{Opt_norbytes, "norbytes"},
+	{Opt_noasyncreaddir, "noasyncreaddir"},
+	{-1, NULL}
+};
+
+static int parse_fsopt_token(char *c, void *private)
 {
-	int congestion_kb;
+	struct ceph_mount_options *fsopt = private;
+	substring_t argstr[MAX_OPT_ARGS];
+	int token, intval, ret;
 
-	/*
-	 * Copied from NFS
-	 *
-	 * congestion size, scale with available memory.
-	 *
-	 *  64MB:    8192k
-	 * 128MB:   11585k
-	 * 256MB:   16384k
-	 * 512MB:   23170k
-	 *   1GB:   32768k
-	 *   2GB:   46340k
-	 *   4GB:   65536k
-	 *   8GB:   92681k
-	 *  16GB:  131072k
-	 *
-	 * This allows larger machines to have larger/more transfers.
-	 * Limit the default to 256M
-	 */
-	congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
-	if (congestion_kb > 256*1024)
-		congestion_kb = 256*1024;
+	token = match_token((char *)c, fsopt_tokens, argstr);
+	if (token < 0)
+		return -EINVAL;
 
-	return congestion_kb;
+	if (token < Opt_last_int) {
+		ret = match_int(&argstr[0], &intval);
+		if (ret < 0) {
+			pr_err("bad mount option arg (not int) "
+			       "at '%s'\n", c);
+			return ret;
+		}
+		dout("got int token %d val %d\n", token, intval);
+	} else if (token > Opt_last_int && token < Opt_last_string) {
+		dout("got string token %d val %s\n", token,
+		     argstr[0].from);
+	} else {
+		dout("got token %d\n", token);
+	}
+
+	switch (token) {
+	case Opt_snapdirname:
+		kfree(fsopt->snapdir_name);
+		fsopt->snapdir_name = kstrndup(argstr[0].from,
+					       argstr[0].to-argstr[0].from,
+					       GFP_KERNEL);
+		if (!fsopt->snapdir_name)
+			return -ENOMEM;
+		break;
+
+		/* misc */
+	case Opt_wsize:
+		fsopt->wsize = intval;
+		break;
+	case Opt_rsize:
+		fsopt->rsize = intval;
+		break;
+	case Opt_caps_wanted_delay_min:
+		fsopt->caps_wanted_delay_min = intval;
+		break;
+	case Opt_caps_wanted_delay_max:
+		fsopt->caps_wanted_delay_max = intval;
+		break;
+	case Opt_readdir_max_entries:
+		fsopt->max_readdir = intval;
+		break;
+	case Opt_readdir_max_bytes:
+		fsopt->max_readdir_bytes = intval;
+		break;
+	case Opt_congestion_kb:
+		fsopt->congestion_kb = intval;
+		break;
+	case Opt_dirstat:
+		fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT;
+		break;
+	case Opt_nodirstat:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT;
+		break;
+	case Opt_rbytes:
+		fsopt->flags |= CEPH_MOUNT_OPT_RBYTES;
+		break;
+	case Opt_norbytes:
+		fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
+		break;
+	case Opt_noasyncreaddir:
+		fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
+		break;
+	default:
+		BUG_ON(token);
+	}
+	return 0;
+}
+
+static void destroy_mount_options(struct ceph_mount_options *args)
+{
+	dout("destroy_mount_options %p\n", args);
+	kfree(args->snapdir_name);
+	kfree(args);
+}
+
+static int strcmp_null(const char *s1, const char *s2)
+{
+	if (!s1 && !s2)
+		return 0;
+	if (s1 && !s2)
+		return -1;
+	if (!s1 && s2)
+		return 1;
+	return strcmp(s1, s2);
+}
+
+static int compare_mount_options(struct ceph_mount_options *new_fsopt,
+				 struct ceph_options *new_opt,
+				 struct ceph_fs_client *fsc)
+{
+	struct ceph_mount_options *fsopt1 = new_fsopt;
+	struct ceph_mount_options *fsopt2 = fsc->mount_options;
+	int ofs = offsetof(struct ceph_mount_options, snapdir_name);
+	int ret;
+
+	ret = memcmp(fsopt1, fsopt2, ofs);
+	if (ret)
+		return ret;
+
+	ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name);
+	if (ret)
+		return ret;
+
+	return ceph_compare_options(new_opt, fsc->client);
+}
+
+static int parse_mount_options(struct ceph_mount_options **pfsopt,
+			       struct ceph_options **popt,
+			       int flags, char *options,
+			       const char *dev_name,
+			       const char **path)
+{
+	struct ceph_mount_options *fsopt;
+	const char *dev_name_end;
+	int err = -ENOMEM;
+
+	fsopt = kzalloc(sizeof(*fsopt), GFP_KERNEL);
+	if (!fsopt)
+		return -ENOMEM;
+
+	dout("parse_mount_options %p, dev_name '%s'\n", fsopt, dev_name);
+
+        fsopt->sb_flags = flags;
+        fsopt->flags = CEPH_MOUNT_OPT_DEFAULT;
+
+        fsopt->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
+        fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
+        fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
+        fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
+        fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
+        fsopt->congestion_kb = default_congestion_kb();
+	
+        /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */
+        err = -EINVAL;
+        if (!dev_name)
+                goto out;
+        *path = strstr(dev_name, ":/");
+        if (*path == NULL) {
+                pr_err("device name is missing path (no :/ in %s)\n",
+                       dev_name);
+                goto out;
+        }
+	dev_name_end = *path;
+	dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name);
+
+	/* path on server */
+	*path += 2;
+	dout("server path '%s'\n", *path);
+
+	err = ceph_parse_options(popt, options, dev_name, dev_name_end,
+				 parse_fsopt_token, (void *)fsopt);
+	if (err)
+		goto out;
+
+	/* success */
+	*pfsopt = fsopt;
+	return 0;
+
+out:
+	destroy_mount_options(fsopt);
+	return err;
 }
 
 /**
@@ -156,60 +333,176 @@
  */
 static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt)
 {
-	struct ceph_client *client = ceph_sb_to_client(mnt->mnt_sb);
-	struct ceph_mount_args *args = client->mount_args;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(mnt->mnt_sb);
+	struct ceph_mount_options *fsopt = fsc->mount_options;
+	struct ceph_options *opt = fsc->client->options;
 
-	if (args->flags & CEPH_OPT_FSID)
-		seq_printf(m, ",fsid=%pU", &args->fsid);
-	if (args->flags & CEPH_OPT_NOSHARE)
+	if (opt->flags & CEPH_OPT_FSID)
+		seq_printf(m, ",fsid=%pU", &opt->fsid);
+	if (opt->flags & CEPH_OPT_NOSHARE)
 		seq_puts(m, ",noshare");
-	if (args->flags & CEPH_OPT_DIRSTAT)
-		seq_puts(m, ",dirstat");
-	if ((args->flags & CEPH_OPT_RBYTES) == 0)
-		seq_puts(m, ",norbytes");
-	if (args->flags & CEPH_OPT_NOCRC)
+	if (opt->flags & CEPH_OPT_NOCRC)
 		seq_puts(m, ",nocrc");
-	if (args->flags & CEPH_OPT_NOASYNCREADDIR)
+
+	if (opt->name)
+		seq_printf(m, ",name=%s", opt->name);
+	if (opt->secret)
+		seq_puts(m, ",secret=<hidden>");
+
+	if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
+		seq_printf(m, ",mount_timeout=%d", opt->mount_timeout);
+	if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
+		seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl);
+	if (opt->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
+		seq_printf(m, ",osdtimeout=%d", opt->osd_timeout);
+	if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
+		seq_printf(m, ",osdkeepalivetimeout=%d",
+			   opt->osd_keepalive_timeout);
+
+	if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT)
+		seq_puts(m, ",dirstat");
+	if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES) == 0)
+		seq_puts(m, ",norbytes");
+	if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR)
 		seq_puts(m, ",noasyncreaddir");
 
-	if (args->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
-		seq_printf(m, ",mount_timeout=%d", args->mount_timeout);
-	if (args->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
-		seq_printf(m, ",osd_idle_ttl=%d", args->osd_idle_ttl);
-	if (args->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
-		seq_printf(m, ",osdtimeout=%d", args->osd_timeout);
-	if (args->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
-		seq_printf(m, ",osdkeepalivetimeout=%d",
-			 args->osd_keepalive_timeout);
-	if (args->wsize)
-		seq_printf(m, ",wsize=%d", args->wsize);
-	if (args->rsize != CEPH_MOUNT_RSIZE_DEFAULT)
-		seq_printf(m, ",rsize=%d", args->rsize);
-	if (args->congestion_kb != default_congestion_kb())
-		seq_printf(m, ",write_congestion_kb=%d", args->congestion_kb);
-	if (args->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
+	if (fsopt->wsize)
+		seq_printf(m, ",wsize=%d", fsopt->wsize);
+	if (fsopt->rsize != CEPH_MOUNT_RSIZE_DEFAULT)
+		seq_printf(m, ",rsize=%d", fsopt->rsize);
+	if (fsopt->congestion_kb != default_congestion_kb())
+		seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb);
+	if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
 		seq_printf(m, ",caps_wanted_delay_min=%d",
-			 args->caps_wanted_delay_min);
-	if (args->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT)
+			 fsopt->caps_wanted_delay_min);
+	if (fsopt->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT)
 		seq_printf(m, ",caps_wanted_delay_max=%d",
-			   args->caps_wanted_delay_max);
-	if (args->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT)
+			   fsopt->caps_wanted_delay_max);
+	if (fsopt->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT)
 		seq_printf(m, ",cap_release_safety=%d",
-			   args->cap_release_safety);
-	if (args->max_readdir != CEPH_MAX_READDIR_DEFAULT)
-		seq_printf(m, ",readdir_max_entries=%d", args->max_readdir);
-	if (args->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT)
-		seq_printf(m, ",readdir_max_bytes=%d", args->max_readdir_bytes);
-	if (strcmp(args->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT))
-		seq_printf(m, ",snapdirname=%s", args->snapdir_name);
-	if (args->name)
-		seq_printf(m, ",name=%s", args->name);
-	if (args->secret)
-		seq_puts(m, ",secret=<hidden>");
+			   fsopt->cap_release_safety);
+	if (fsopt->max_readdir != CEPH_MAX_READDIR_DEFAULT)
+		seq_printf(m, ",readdir_max_entries=%d", fsopt->max_readdir);
+	if (fsopt->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT)
+		seq_printf(m, ",readdir_max_bytes=%d", fsopt->max_readdir_bytes);
+	if (strcmp(fsopt->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT))
+		seq_printf(m, ",snapdirname=%s", fsopt->snapdir_name);
 	return 0;
 }
 
 /*
+ * handle any mon messages the standard library doesn't understand.
+ * return error if we don't either.
+ */
+static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg)
+{
+	struct ceph_fs_client *fsc = client->private;
+	int type = le16_to_cpu(msg->hdr.type);
+
+	switch (type) {
+	case CEPH_MSG_MDS_MAP:
+		ceph_mdsc_handle_map(fsc->mdsc, msg);
+		return 0;
+
+	default:
+		return -1;
+	}
+}
+
+/*
+ * create a new fs client
+ */
+struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
+					struct ceph_options *opt)
+{
+	struct ceph_fs_client *fsc;
+	int err = -ENOMEM;
+
+	fsc = kzalloc(sizeof(*fsc), GFP_KERNEL);
+	if (!fsc)
+		return ERR_PTR(-ENOMEM);
+
+	fsc->client = ceph_create_client(opt, fsc);
+	if (IS_ERR(fsc->client)) {
+		err = PTR_ERR(fsc->client);
+		goto fail;
+	}
+	fsc->client->extra_mon_dispatch = extra_mon_dispatch;
+	fsc->client->supported_features |= CEPH_FEATURE_FLOCK;
+	fsc->client->monc.want_mdsmap = 1;
+
+	fsc->mount_options = fsopt;
+
+	fsc->sb = NULL;
+	fsc->mount_state = CEPH_MOUNT_MOUNTING;
+
+	atomic_long_set(&fsc->writeback_count, 0);
+
+	err = bdi_init(&fsc->backing_dev_info);
+	if (err < 0)
+		goto fail_client;
+
+	err = -ENOMEM;
+	fsc->wb_wq = create_workqueue("ceph-writeback");
+	if (fsc->wb_wq == NULL)
+		goto fail_bdi;
+	fsc->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid");
+	if (fsc->pg_inv_wq == NULL)
+		goto fail_wb_wq;
+	fsc->trunc_wq = create_singlethread_workqueue("ceph-trunc");
+	if (fsc->trunc_wq == NULL)
+		goto fail_pg_inv_wq;
+
+	/* set up mempools */
+	err = -ENOMEM;
+	fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10,
+			      fsc->mount_options->wsize >> PAGE_CACHE_SHIFT);
+	if (!fsc->wb_pagevec_pool)
+		goto fail_trunc_wq;
+
+	/* caps */
+	fsc->min_caps = fsopt->max_readdir;
+
+	return fsc;
+
+fail_trunc_wq:
+	destroy_workqueue(fsc->trunc_wq);
+fail_pg_inv_wq:
+	destroy_workqueue(fsc->pg_inv_wq);
+fail_wb_wq:
+	destroy_workqueue(fsc->wb_wq);
+fail_bdi:
+	bdi_destroy(&fsc->backing_dev_info);
+fail_client:
+	ceph_destroy_client(fsc->client);
+fail:
+	kfree(fsc);
+	return ERR_PTR(err);
+}
+
+void destroy_fs_client(struct ceph_fs_client *fsc)
+{
+	dout("destroy_fs_client %p\n", fsc);
+
+	destroy_workqueue(fsc->wb_wq);
+	destroy_workqueue(fsc->pg_inv_wq);
+	destroy_workqueue(fsc->trunc_wq);
+
+	bdi_destroy(&fsc->backing_dev_info);
+
+	mempool_destroy(fsc->wb_pagevec_pool);
+
+	destroy_mount_options(fsc->mount_options);
+
+	ceph_fs_debugfs_cleanup(fsc);
+
+	ceph_destroy_client(fsc->client);
+
+	kfree(fsc);
+	dout("destroy_fs_client %p done\n", fsc);
+}
+
+/*
  * caches
  */
 struct kmem_cache *ceph_inode_cachep;
@@ -274,12 +567,12 @@
  */
 static void ceph_umount_begin(struct super_block *sb)
 {
-	struct ceph_client *client = ceph_sb_to_client(sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 
 	dout("ceph_umount_begin - starting forced umount\n");
-	if (!client)
+	if (!fsc)
 		return;
-	client->mount_state = CEPH_MOUNT_SHUTDOWN;
+	fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
 	return;
 }
 
@@ -294,483 +587,15 @@
 	.umount_begin   = ceph_umount_begin,
 };
 
-
-const char *ceph_msg_type_name(int type)
-{
-	switch (type) {
-	case CEPH_MSG_SHUTDOWN: return "shutdown";
-	case CEPH_MSG_PING: return "ping";
-	case CEPH_MSG_AUTH: return "auth";
-	case CEPH_MSG_AUTH_REPLY: return "auth_reply";
-	case CEPH_MSG_MON_MAP: return "mon_map";
-	case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
-	case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
-	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
-	case CEPH_MSG_STATFS: return "statfs";
-	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
-	case CEPH_MSG_MDS_MAP: return "mds_map";
-	case CEPH_MSG_CLIENT_SESSION: return "client_session";
-	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
-	case CEPH_MSG_CLIENT_REQUEST: return "client_request";
-	case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
-	case CEPH_MSG_CLIENT_REPLY: return "client_reply";
-	case CEPH_MSG_CLIENT_CAPS: return "client_caps";
-	case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
-	case CEPH_MSG_CLIENT_SNAP: return "client_snap";
-	case CEPH_MSG_CLIENT_LEASE: return "client_lease";
-	case CEPH_MSG_OSD_MAP: return "osd_map";
-	case CEPH_MSG_OSD_OP: return "osd_op";
-	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
-	default: return "unknown";
-	}
-}
-
-
-/*
- * mount options
- */
-enum {
-	Opt_wsize,
-	Opt_rsize,
-	Opt_osdtimeout,
-	Opt_osdkeepalivetimeout,
-	Opt_mount_timeout,
-	Opt_osd_idle_ttl,
-	Opt_caps_wanted_delay_min,
-	Opt_caps_wanted_delay_max,
-	Opt_cap_release_safety,
-	Opt_readdir_max_entries,
-	Opt_readdir_max_bytes,
-	Opt_congestion_kb,
-	Opt_last_int,
-	/* int args above */
-	Opt_fsid,
-	Opt_snapdirname,
-	Opt_name,
-	Opt_secret,
-	Opt_last_string,
-	/* string args above */
-	Opt_ip,
-	Opt_noshare,
-	Opt_dirstat,
-	Opt_nodirstat,
-	Opt_rbytes,
-	Opt_norbytes,
-	Opt_nocrc,
-	Opt_noasyncreaddir,
-};
-
-static match_table_t arg_tokens = {
-	{Opt_wsize, "wsize=%d"},
-	{Opt_rsize, "rsize=%d"},
-	{Opt_osdtimeout, "osdtimeout=%d"},
-	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
-	{Opt_mount_timeout, "mount_timeout=%d"},
-	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
-	{Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"},
-	{Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"},
-	{Opt_cap_release_safety, "cap_release_safety=%d"},
-	{Opt_readdir_max_entries, "readdir_max_entries=%d"},
-	{Opt_readdir_max_bytes, "readdir_max_bytes=%d"},
-	{Opt_congestion_kb, "write_congestion_kb=%d"},
-	/* int args above */
-	{Opt_fsid, "fsid=%s"},
-	{Opt_snapdirname, "snapdirname=%s"},
-	{Opt_name, "name=%s"},
-	{Opt_secret, "secret=%s"},
-	/* string args above */
-	{Opt_ip, "ip=%s"},
-	{Opt_noshare, "noshare"},
-	{Opt_dirstat, "dirstat"},
-	{Opt_nodirstat, "nodirstat"},
-	{Opt_rbytes, "rbytes"},
-	{Opt_norbytes, "norbytes"},
-	{Opt_nocrc, "nocrc"},
-	{Opt_noasyncreaddir, "noasyncreaddir"},
-	{-1, NULL}
-};
-
-static int parse_fsid(const char *str, struct ceph_fsid *fsid)
-{
-	int i = 0;
-	char tmp[3];
-	int err = -EINVAL;
-	int d;
-
-	dout("parse_fsid '%s'\n", str);
-	tmp[2] = 0;
-	while (*str && i < 16) {
-		if (ispunct(*str)) {
-			str++;
-			continue;
-		}
-		if (!isxdigit(str[0]) || !isxdigit(str[1]))
-			break;
-		tmp[0] = str[0];
-		tmp[1] = str[1];
-		if (sscanf(tmp, "%x", &d) < 1)
-			break;
-		fsid->fsid[i] = d & 0xff;
-		i++;
-		str += 2;
-	}
-
-	if (i == 16)
-		err = 0;
-	dout("parse_fsid ret %d got fsid %pU", err, fsid);
-	return err;
-}
-
-static struct ceph_mount_args *parse_mount_args(int flags, char *options,
-						const char *dev_name,
-						const char **path)
-{
-	struct ceph_mount_args *args;
-	const char *c;
-	int err = -ENOMEM;
-	substring_t argstr[MAX_OPT_ARGS];
-
-	args = kzalloc(sizeof(*args), GFP_KERNEL);
-	if (!args)
-		return ERR_PTR(-ENOMEM);
-	args->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*args->mon_addr),
-				 GFP_KERNEL);
-	if (!args->mon_addr)
-		goto out;
-
-	dout("parse_mount_args %p, dev_name '%s'\n", args, dev_name);
-
-	/* start with defaults */
-	args->sb_flags = flags;
-	args->flags = CEPH_OPT_DEFAULT;
-	args->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
-	args->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
-	args->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
-	args->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
-	args->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
-	args->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
-	args->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
-	args->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
-	args->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
-	args->max_readdir = CEPH_MAX_READDIR_DEFAULT;
-	args->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
-	args->congestion_kb = default_congestion_kb();
-
-	/* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */
-	err = -EINVAL;
-	if (!dev_name)
-		goto out;
-	*path = strstr(dev_name, ":/");
-	if (*path == NULL) {
-		pr_err("device name is missing path (no :/ in %s)\n",
-		       dev_name);
-		goto out;
-	}
-
-	/* get mon ip(s) */
-	err = ceph_parse_ips(dev_name, *path, args->mon_addr,
-			     CEPH_MAX_MON, &args->num_mon);
-	if (err < 0)
-		goto out;
-
-	/* path on server */
-	*path += 2;
-	dout("server path '%s'\n", *path);
-
-	/* parse mount options */
-	while ((c = strsep(&options, ",")) != NULL) {
-		int token, intval, ret;
-		if (!*c)
-			continue;
-		err = -EINVAL;
-		token = match_token((char *)c, arg_tokens, argstr);
-		if (token < 0) {
-			pr_err("bad mount option at '%s'\n", c);
-			goto out;
-		}
-		if (token < Opt_last_int) {
-			ret = match_int(&argstr[0], &intval);
-			if (ret < 0) {
-				pr_err("bad mount option arg (not int) "
-				       "at '%s'\n", c);
-				continue;
-			}
-			dout("got int token %d val %d\n", token, intval);
-		} else if (token > Opt_last_int && token < Opt_last_string) {
-			dout("got string token %d val %s\n", token,
-			     argstr[0].from);
-		} else {
-			dout("got token %d\n", token);
-		}
-		switch (token) {
-		case Opt_ip:
-			err = ceph_parse_ips(argstr[0].from,
-					     argstr[0].to,
-					     &args->my_addr,
-					     1, NULL);
-			if (err < 0)
-				goto out;
-			args->flags |= CEPH_OPT_MYIP;
-			break;
-
-		case Opt_fsid:
-			err = parse_fsid(argstr[0].from, &args->fsid);
-			if (err == 0)
-				args->flags |= CEPH_OPT_FSID;
-			break;
-		case Opt_snapdirname:
-			kfree(args->snapdir_name);
-			args->snapdir_name = kstrndup(argstr[0].from,
-					      argstr[0].to-argstr[0].from,
-					      GFP_KERNEL);
-			break;
-		case Opt_name:
-			args->name = kstrndup(argstr[0].from,
-					      argstr[0].to-argstr[0].from,
-					      GFP_KERNEL);
-			break;
-		case Opt_secret:
-			args->secret = kstrndup(argstr[0].from,
-						argstr[0].to-argstr[0].from,
-						GFP_KERNEL);
-			break;
-
-			/* misc */
-		case Opt_wsize:
-			args->wsize = intval;
-			break;
-		case Opt_rsize:
-			args->rsize = intval;
-			break;
-		case Opt_osdtimeout:
-			args->osd_timeout = intval;
-			break;
-		case Opt_osdkeepalivetimeout:
-			args->osd_keepalive_timeout = intval;
-			break;
-		case Opt_osd_idle_ttl:
-			args->osd_idle_ttl = intval;
-			break;
-		case Opt_mount_timeout:
-			args->mount_timeout = intval;
-			break;
-		case Opt_caps_wanted_delay_min:
-			args->caps_wanted_delay_min = intval;
-			break;
-		case Opt_caps_wanted_delay_max:
-			args->caps_wanted_delay_max = intval;
-			break;
-		case Opt_readdir_max_entries:
-			args->max_readdir = intval;
-			break;
-		case Opt_readdir_max_bytes:
-			args->max_readdir_bytes = intval;
-			break;
-		case Opt_congestion_kb:
-			args->congestion_kb = intval;
-			break;
-
-		case Opt_noshare:
-			args->flags |= CEPH_OPT_NOSHARE;
-			break;
-
-		case Opt_dirstat:
-			args->flags |= CEPH_OPT_DIRSTAT;
-			break;
-		case Opt_nodirstat:
-			args->flags &= ~CEPH_OPT_DIRSTAT;
-			break;
-		case Opt_rbytes:
-			args->flags |= CEPH_OPT_RBYTES;
-			break;
-		case Opt_norbytes:
-			args->flags &= ~CEPH_OPT_RBYTES;
-			break;
-		case Opt_nocrc:
-			args->flags |= CEPH_OPT_NOCRC;
-			break;
-		case Opt_noasyncreaddir:
-			args->flags |= CEPH_OPT_NOASYNCREADDIR;
-			break;
-
-		default:
-			BUG_ON(token);
-		}
-	}
-	return args;
-
-out:
-	kfree(args->mon_addr);
-	kfree(args);
-	return ERR_PTR(err);
-}
-
-static void destroy_mount_args(struct ceph_mount_args *args)
-{
-	dout("destroy_mount_args %p\n", args);
-	kfree(args->snapdir_name);
-	args->snapdir_name = NULL;
-	kfree(args->name);
-	args->name = NULL;
-	kfree(args->secret);
-	args->secret = NULL;
-	kfree(args);
-}
-
-/*
- * create a fresh client instance
- */
-static struct ceph_client *ceph_create_client(struct ceph_mount_args *args)
-{
-	struct ceph_client *client;
-	int err = -ENOMEM;
-
-	client = kzalloc(sizeof(*client), GFP_KERNEL);
-	if (client == NULL)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_init(&client->mount_mutex);
-
-	init_waitqueue_head(&client->auth_wq);
-
-	client->sb = NULL;
-	client->mount_state = CEPH_MOUNT_MOUNTING;
-	client->mount_args = args;
-
-	client->msgr = NULL;
-
-	client->auth_err = 0;
-	atomic_long_set(&client->writeback_count, 0);
-
-	err = bdi_init(&client->backing_dev_info);
-	if (err < 0)
-		goto fail;
-
-	err = -ENOMEM;
-	client->wb_wq = create_workqueue("ceph-writeback");
-	if (client->wb_wq == NULL)
-		goto fail_bdi;
-	client->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid");
-	if (client->pg_inv_wq == NULL)
-		goto fail_wb_wq;
-	client->trunc_wq = create_singlethread_workqueue("ceph-trunc");
-	if (client->trunc_wq == NULL)
-		goto fail_pg_inv_wq;
-
-	/* set up mempools */
-	err = -ENOMEM;
-	client->wb_pagevec_pool = mempool_create_kmalloc_pool(10,
-			      client->mount_args->wsize >> PAGE_CACHE_SHIFT);
-	if (!client->wb_pagevec_pool)
-		goto fail_trunc_wq;
-
-	/* caps */
-	client->min_caps = args->max_readdir;
-
-	/* subsystems */
-	err = ceph_monc_init(&client->monc, client);
-	if (err < 0)
-		goto fail_mempool;
-	err = ceph_osdc_init(&client->osdc, client);
-	if (err < 0)
-		goto fail_monc;
-	err = ceph_mdsc_init(&client->mdsc, client);
-	if (err < 0)
-		goto fail_osdc;
-	return client;
-
-fail_osdc:
-	ceph_osdc_stop(&client->osdc);
-fail_monc:
-	ceph_monc_stop(&client->monc);
-fail_mempool:
-	mempool_destroy(client->wb_pagevec_pool);
-fail_trunc_wq:
-	destroy_workqueue(client->trunc_wq);
-fail_pg_inv_wq:
-	destroy_workqueue(client->pg_inv_wq);
-fail_wb_wq:
-	destroy_workqueue(client->wb_wq);
-fail_bdi:
-	bdi_destroy(&client->backing_dev_info);
-fail:
-	kfree(client);
-	return ERR_PTR(err);
-}
-
-static void ceph_destroy_client(struct ceph_client *client)
-{
-	dout("destroy_client %p\n", client);
-
-	/* unmount */
-	ceph_mdsc_stop(&client->mdsc);
-	ceph_osdc_stop(&client->osdc);
-
-	/*
-	 * make sure mds and osd connections close out before destroying
-	 * the auth module, which is needed to free those connections'
-	 * ceph_authorizers.
-	 */
-	ceph_msgr_flush();
-
-	ceph_monc_stop(&client->monc);
-
-	ceph_debugfs_client_cleanup(client);
-	destroy_workqueue(client->wb_wq);
-	destroy_workqueue(client->pg_inv_wq);
-	destroy_workqueue(client->trunc_wq);
-
-	bdi_destroy(&client->backing_dev_info);
-
-	if (client->msgr)
-		ceph_messenger_destroy(client->msgr);
-	mempool_destroy(client->wb_pagevec_pool);
-
-	destroy_mount_args(client->mount_args);
-
-	kfree(client);
-	dout("destroy_client %p done\n", client);
-}
-
-/*
- * Initially learn our fsid, or verify an fsid matches.
- */
-int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
-{
-	if (client->have_fsid) {
-		if (ceph_fsid_compare(&client->fsid, fsid)) {
-			pr_err("bad fsid, had %pU got %pU",
-			       &client->fsid, fsid);
-			return -1;
-		}
-	} else {
-		pr_info("client%lld fsid %pU\n", client->monc.auth->global_id,
-			fsid);
-		memcpy(&client->fsid, fsid, sizeof(*fsid));
-		ceph_debugfs_client_init(client);
-		client->have_fsid = true;
-	}
-	return 0;
-}
-
-/*
- * true if we have the mon map (and have thus joined the cluster)
- */
-static int have_mon_and_osd_map(struct ceph_client *client)
-{
-	return client->monc.monmap && client->monc.monmap->epoch &&
-	       client->osdc.osdmap && client->osdc.osdmap->epoch;
-}
-
 /*
  * Bootstrap mount by opening the root directory.  Note the mount
  * @started time from caller, and time out if this takes too long.
  */
-static struct dentry *open_root_dentry(struct ceph_client *client,
+static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
 				       const char *path,
 				       unsigned long started)
 {
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req = NULL;
 	int err;
 	struct dentry *root;
@@ -784,14 +609,14 @@
 	req->r_ino1.ino = CEPH_INO_ROOT;
 	req->r_ino1.snap = CEPH_NOSNAP;
 	req->r_started = started;
-	req->r_timeout = client->mount_args->mount_timeout * HZ;
+	req->r_timeout = fsc->client->options->mount_timeout * HZ;
 	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
 	req->r_num_caps = 2;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	if (err == 0) {
 		dout("open_root_inode success\n");
 		if (ceph_ino(req->r_target_inode) == CEPH_INO_ROOT &&
-		    client->sb->s_root == NULL)
+		    fsc->sb->s_root == NULL)
 			root = d_alloc_root(req->r_target_inode);
 		else
 			root = d_obtain_alias(req->r_target_inode);
@@ -804,105 +629,86 @@
 	return root;
 }
 
+
+
+
 /*
  * mount: join the ceph cluster, and open root directory.
  */
-static int ceph_mount(struct ceph_client *client, struct vfsmount *mnt,
+static int ceph_mount(struct ceph_fs_client *fsc, struct vfsmount *mnt,
 		      const char *path)
 {
-	struct ceph_entity_addr *myaddr = NULL;
 	int err;
-	unsigned long timeout = client->mount_args->mount_timeout * HZ;
 	unsigned long started = jiffies;  /* note the start time */
 	struct dentry *root;
+	int first = 0;   /* first vfsmount for this super_block */
 
 	dout("mount start\n");
-	mutex_lock(&client->mount_mutex);
+	mutex_lock(&fsc->client->mount_mutex);
 
-	/* initialize the messenger */
-	if (client->msgr == NULL) {
-		if (ceph_test_opt(client, MYIP))
-			myaddr = &client->mount_args->my_addr;
-		client->msgr = ceph_messenger_create(myaddr);
-		if (IS_ERR(client->msgr)) {
-			err = PTR_ERR(client->msgr);
-			client->msgr = NULL;
-			goto out;
-		}
-		client->msgr->nocrc = ceph_test_opt(client, NOCRC);
-	}
-
-	/* open session, and wait for mon, mds, and osd maps */
-	err = ceph_monc_open_session(&client->monc);
+	err = __ceph_open_session(fsc->client, started);
 	if (err < 0)
 		goto out;
 
-	while (!have_mon_and_osd_map(client)) {
-		err = -EIO;
-		if (timeout && time_after_eq(jiffies, started + timeout))
-			goto out;
-
-		/* wait */
-		dout("mount waiting for mon_map\n");
-		err = wait_event_interruptible_timeout(client->auth_wq,
-		       have_mon_and_osd_map(client) || (client->auth_err < 0),
-		       timeout);
-		if (err == -EINTR || err == -ERESTARTSYS)
-			goto out;
-		if (client->auth_err < 0) {
-			err = client->auth_err;
-			goto out;
-		}
-	}
-
 	dout("mount opening root\n");
-	root = open_root_dentry(client, "", started);
+	root = open_root_dentry(fsc, "", started);
 	if (IS_ERR(root)) {
 		err = PTR_ERR(root);
 		goto out;
 	}
-	if (client->sb->s_root)
+	if (fsc->sb->s_root) {
 		dput(root);
-	else
-		client->sb->s_root = root;
+	} else {
+		fsc->sb->s_root = root;
+		first = 1;
+
+		err = ceph_fs_debugfs_init(fsc);
+		if (err < 0)
+			goto fail;
+	}
 
 	if (path[0] == 0) {
 		dget(root);
 	} else {
 		dout("mount opening base mountpoint\n");
-		root = open_root_dentry(client, path, started);
+		root = open_root_dentry(fsc, path, started);
 		if (IS_ERR(root)) {
 			err = PTR_ERR(root);
-			dput(client->sb->s_root);
-			client->sb->s_root = NULL;
-			goto out;
+			goto fail;
 		}
 	}
 
 	mnt->mnt_root = root;
-	mnt->mnt_sb = client->sb;
+	mnt->mnt_sb = fsc->sb;
 
-	client->mount_state = CEPH_MOUNT_MOUNTED;
+	fsc->mount_state = CEPH_MOUNT_MOUNTED;
 	dout("mount success\n");
 	err = 0;
 
 out:
-	mutex_unlock(&client->mount_mutex);
+	mutex_unlock(&fsc->client->mount_mutex);
 	return err;
+
+fail:
+	if (first) {
+		dput(fsc->sb->s_root);
+		fsc->sb->s_root = NULL;
+	}
+	goto out;
 }
 
 static int ceph_set_super(struct super_block *s, void *data)
 {
-	struct ceph_client *client = data;
+	struct ceph_fs_client *fsc = data;
 	int ret;
 
 	dout("set_super %p data %p\n", s, data);
 
-	s->s_flags = client->mount_args->sb_flags;
+	s->s_flags = fsc->mount_options->sb_flags;
 	s->s_maxbytes = 1ULL << 40;  /* temp value until we get mdsmap */
 
-	s->s_fs_info = client;
-	client->sb = s;
+	s->s_fs_info = fsc;
+	fsc->sb = s;
 
 	s->s_op = &ceph_super_ops;
 	s->s_export_op = &ceph_export_ops;
@@ -917,7 +723,7 @@
 
 fail:
 	s->s_fs_info = NULL;
-	client->sb = NULL;
+	fsc->sb = NULL;
 	return ret;
 }
 
@@ -926,30 +732,23 @@
  */
 static int ceph_compare_super(struct super_block *sb, void *data)
 {
-	struct ceph_client *new = data;
-	struct ceph_mount_args *args = new->mount_args;
-	struct ceph_client *other = ceph_sb_to_client(sb);
-	int i;
+	struct ceph_fs_client *new = data;
+	struct ceph_mount_options *fsopt = new->mount_options;
+	struct ceph_options *opt = new->client->options;
+	struct ceph_fs_client *other = ceph_sb_to_client(sb);
 
 	dout("ceph_compare_super %p\n", sb);
-	if (args->flags & CEPH_OPT_FSID) {
-		if (ceph_fsid_compare(&args->fsid, &other->fsid)) {
-			dout("fsid doesn't match\n");
-			return 0;
-		}
-	} else {
-		/* do we share (a) monitor? */
-		for (i = 0; i < new->monc.monmap->num_mon; i++)
-			if (ceph_monmap_contains(other->monc.monmap,
-					 &new->monc.monmap->mon_inst[i].addr))
-				break;
-		if (i == new->monc.monmap->num_mon) {
-			dout("mon ip not part of monmap\n");
-			return 0;
-		}
-		dout("mon ip matches existing sb %p\n", sb);
+
+	if (compare_mount_options(fsopt, opt, other)) {
+		dout("monitor(s)/mount options don't match\n");
+		return 0;
 	}
-	if (args->sb_flags != other->mount_args->sb_flags) {
+	if ((opt->flags & CEPH_OPT_FSID) &&
+	    ceph_fsid_compare(&opt->fsid, &other->client->fsid)) {
+		dout("fsid doesn't match\n");
+		return 0;
+	}
+	if (fsopt->sb_flags != other->mount_options->sb_flags) {
 		dout("flags differ\n");
 		return 0;
 	}
@@ -961,19 +760,20 @@
  */
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-static int ceph_register_bdi(struct super_block *sb, struct ceph_client *client)
+static int ceph_register_bdi(struct super_block *sb,
+			     struct ceph_fs_client *fsc)
 {
 	int err;
 
 	/* set ra_pages based on rsize mount option? */
-	if (client->mount_args->rsize >= PAGE_CACHE_SIZE)
-		client->backing_dev_info.ra_pages =
-			(client->mount_args->rsize + PAGE_CACHE_SIZE - 1)
+	if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
+		fsc->backing_dev_info.ra_pages =
+			(fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
 			>> PAGE_SHIFT;
-	err = bdi_register(&client->backing_dev_info, NULL, "ceph-%d",
+	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%d",
 			   atomic_long_inc_return(&bdi_seq));
 	if (!err)
-		sb->s_bdi = &client->backing_dev_info;
+		sb->s_bdi = &fsc->backing_dev_info;
 	return err;
 }
 
@@ -982,46 +782,52 @@
 		       struct vfsmount *mnt)
 {
 	struct super_block *sb;
-	struct ceph_client *client;
+	struct ceph_fs_client *fsc;
 	int err;
 	int (*compare_super)(struct super_block *, void *) = ceph_compare_super;
 	const char *path = NULL;
-	struct ceph_mount_args *args;
+	struct ceph_mount_options *fsopt = NULL;
+	struct ceph_options *opt = NULL;
 
 	dout("ceph_get_sb\n");
-	args = parse_mount_args(flags, data, dev_name, &path);
-	if (IS_ERR(args)) {
-		err = PTR_ERR(args);
+	err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
+	if (err < 0)
 		goto out_final;
-	}
 
 	/* create client (which we may/may not use) */
-	client = ceph_create_client(args);
-	if (IS_ERR(client)) {
-		err = PTR_ERR(client);
+	fsc = create_fs_client(fsopt, opt);
+	if (IS_ERR(fsc)) {
+		err = PTR_ERR(fsc);
+		kfree(fsopt);
+		kfree(opt);
 		goto out_final;
 	}
 
-	if (client->mount_args->flags & CEPH_OPT_NOSHARE)
+	err = ceph_mdsc_init(fsc);
+	if (err < 0)
+		goto out;
+
+	if (ceph_test_opt(fsc->client, NOSHARE))
 		compare_super = NULL;
-	sb = sget(fs_type, compare_super, ceph_set_super, client);
+	sb = sget(fs_type, compare_super, ceph_set_super, fsc);
 	if (IS_ERR(sb)) {
 		err = PTR_ERR(sb);
 		goto out;
 	}
 
-	if (ceph_sb_to_client(sb) != client) {
-		ceph_destroy_client(client);
-		client = ceph_sb_to_client(sb);
-		dout("get_sb got existing client %p\n", client);
+	if (ceph_sb_to_client(sb) != fsc) {
+		ceph_mdsc_destroy(fsc);
+		destroy_fs_client(fsc);
+		fsc = ceph_sb_to_client(sb);
+		dout("get_sb got existing client %p\n", fsc);
 	} else {
-		dout("get_sb using new client %p\n", client);
-		err = ceph_register_bdi(sb, client);
+		dout("get_sb using new client %p\n", fsc);
+		err = ceph_register_bdi(sb, fsc);
 		if (err < 0)
 			goto out_splat;
 	}
 
-	err = ceph_mount(client, mnt, path);
+	err = ceph_mount(fsc, mnt, path);
 	if (err < 0)
 		goto out_splat;
 	dout("root %p inode %p ino %llx.%llx\n", mnt->mnt_root,
@@ -1029,12 +835,13 @@
 	return 0;
 
 out_splat:
-	ceph_mdsc_close_sessions(&client->mdsc);
+	ceph_mdsc_close_sessions(fsc->mdsc);
 	deactivate_locked_super(sb);
 	goto out_final;
 
 out:
-	ceph_destroy_client(client);
+	ceph_mdsc_destroy(fsc);
+	destroy_fs_client(fsc);
 out_final:
 	dout("ceph_get_sb fail %d\n", err);
 	return err;
@@ -1042,11 +849,12 @@
 
 static void ceph_kill_sb(struct super_block *s)
 {
-	struct ceph_client *client = ceph_sb_to_client(s);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(s);
 	dout("kill_sb %p\n", s);
-	ceph_mdsc_pre_umount(&client->mdsc);
+	ceph_mdsc_pre_umount(fsc->mdsc);
 	kill_anon_super(s);    /* will call put_super after sb is r/o */
-	ceph_destroy_client(client);
+	ceph_mdsc_destroy(fsc);
+	destroy_fs_client(fsc);
 }
 
 static struct file_system_type ceph_fs_type = {
@@ -1062,36 +870,20 @@
 
 static int __init init_ceph(void)
 {
-	int ret = 0;
-
-	ret = ceph_debugfs_init();
-	if (ret < 0)
-		goto out;
-
-	ret = ceph_msgr_init();
-	if (ret < 0)
-		goto out_debugfs;
-
-	ret = init_caches();
+	int ret = init_caches();
 	if (ret)
-		goto out_msgr;
+		goto out;
 
 	ret = register_filesystem(&ceph_fs_type);
 	if (ret)
 		goto out_icache;
 
-	pr_info("loaded (mon/mds/osd proto %d/%d/%d, osdmap %d/%d %d/%d)\n",
-		CEPH_MONC_PROTOCOL, CEPH_MDSC_PROTOCOL, CEPH_OSDC_PROTOCOL,
-		CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
-		CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
+	pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL);
+
 	return 0;
 
 out_icache:
 	destroy_caches();
-out_msgr:
-	ceph_msgr_exit();
-out_debugfs:
-	ceph_debugfs_cleanup();
 out:
 	return ret;
 }
@@ -1101,8 +893,6 @@
 	dout("exit_ceph\n");
 	unregister_filesystem(&ceph_fs_type);
 	destroy_caches();
-	ceph_msgr_exit();
-	ceph_debugfs_cleanup();
 }
 
 module_init(init_ceph);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b87638e..1886294 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1,7 +1,7 @@
 #ifndef _FS_CEPH_SUPER_H
 #define _FS_CEPH_SUPER_H
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <asm/unaligned.h>
 #include <linux/backing-dev.h>
@@ -14,13 +14,7 @@
 #include <linux/writeback.h>
 #include <linux/slab.h>
 
-#include "types.h"
-#include "messenger.h"
-#include "msgpool.h"
-#include "mon_client.h"
-#include "mds_client.h"
-#include "osd_client.h"
-#include "ceph_fs.h"
+#include <linux/ceph/libceph.h>
 
 /* f_type in struct statfs */
 #define CEPH_SUPER_MAGIC 0x00c36400
@@ -30,42 +24,25 @@
 #define CEPH_BLOCK_SHIFT   20  /* 1 MB */
 #define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
 
-/*
- * Supported features
- */
-#define CEPH_FEATURE_SUPPORTED CEPH_FEATURE_NOSRCADDR | CEPH_FEATURE_FLOCK
-#define CEPH_FEATURE_REQUIRED  CEPH_FEATURE_NOSRCADDR
+#define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
+#define CEPH_MOUNT_OPT_RBYTES          (1<<5) /* dir st_bytes = rbytes */
+#define CEPH_MOUNT_OPT_NOASYNCREADDIR  (1<<7) /* no dcache readdir */
 
-/*
- * mount options
- */
-#define CEPH_OPT_FSID             (1<<0)
-#define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
-#define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
-#define CEPH_OPT_DIRSTAT          (1<<4) /* funky `cat dirname` for stats */
-#define CEPH_OPT_RBYTES           (1<<5) /* dir st_bytes = rbytes */
-#define CEPH_OPT_NOCRC            (1<<6) /* no data crc on writes */
-#define CEPH_OPT_NOASYNCREADDIR   (1<<7) /* no dcache readdir */
+#define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES)
 
-#define CEPH_OPT_DEFAULT   (CEPH_OPT_RBYTES)
+#define ceph_set_mount_opt(fsc, opt) \
+	(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
+#define ceph_test_mount_opt(fsc, opt) \
+	(!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
 
-#define ceph_set_opt(client, opt) \
-	(client)->mount_args->flags |= CEPH_OPT_##opt;
-#define ceph_test_opt(client, opt) \
-	(!!((client)->mount_args->flags & CEPH_OPT_##opt))
+#define CEPH_MAX_READDIR_DEFAULT        1024
+#define CEPH_MAX_READDIR_BYTES_DEFAULT  (512*1024)
+#define CEPH_SNAPDIRNAME_DEFAULT        ".snap"
 
-
-struct ceph_mount_args {
-	int sb_flags;
+struct ceph_mount_options {
 	int flags;
-	struct ceph_fsid fsid;
-	struct ceph_entity_addr my_addr;
-	int num_mon;
-	struct ceph_entity_addr *mon_addr;
-	int mount_timeout;
-	int osd_idle_ttl;
-	int osd_timeout;
-	int osd_keepalive_timeout;
+	int sb_flags;
+
 	int wsize;
 	int rsize;            /* max readahead */
 	int congestion_kb;    /* max writeback in flight */
@@ -73,82 +50,25 @@
 	int cap_release_safety;
 	int max_readdir;       /* max readdir result (entires) */
 	int max_readdir_bytes; /* max readdir result (bytes) */
+
+	/*
+	 * everything above this point can be memcmp'd; everything below
+	 * is handled in compare_mount_options()
+	 */
+
 	char *snapdir_name;   /* default ".snap" */
-	char *name;
-	char *secret;
 };
 
-/*
- * defaults
- */
-#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
-#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
-#define CEPH_OSD_KEEPALIVE_DEFAULT  5
-#define CEPH_OSD_IDLE_TTL_DEFAULT    60
-#define CEPH_MOUNT_RSIZE_DEFAULT    (512*1024) /* readahead */
-#define CEPH_MAX_READDIR_DEFAULT    1024
-#define CEPH_MAX_READDIR_BYTES_DEFAULT    (512*1024)
-
-#define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
-#define CEPH_MSG_MAX_DATA_LEN	(16*1024*1024)
-
-#define CEPH_SNAPDIRNAME_DEFAULT ".snap"
-#define CEPH_AUTH_NAME_DEFAULT   "guest"
-/*
- * Delay telling the MDS we no longer want caps, in case we reopen
- * the file.  Delay a minimum amount of time, even if we send a cap
- * message for some other reason.  Otherwise, take the oppotunity to
- * update the mds to avoid sending another message later.
- */
-#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
-#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */
-
-#define CEPH_CAP_RELEASE_SAFETY_DEFAULT        (CEPH_CAPS_PER_RELEASE * 4)
-
-/* mount state */
-enum {
-	CEPH_MOUNT_MOUNTING,
-	CEPH_MOUNT_MOUNTED,
-	CEPH_MOUNT_UNMOUNTING,
-	CEPH_MOUNT_UNMOUNTED,
-	CEPH_MOUNT_SHUTDOWN,
-};
-
-/*
- * subtract jiffies
- */
-static inline unsigned long time_sub(unsigned long a, unsigned long b)
-{
-	BUG_ON(time_after(b, a));
-	return (long)a - (long)b;
-}
-
-/*
- * per-filesystem client state
- *
- * possibly shared by multiple mount points, if they are
- * mounting the same ceph filesystem/cluster.
- */
-struct ceph_client {
-	struct ceph_fsid fsid;
-	bool have_fsid;
-
-	struct mutex mount_mutex;       /* serialize mount attempts */
-	struct ceph_mount_args *mount_args;
-
+struct ceph_fs_client {
 	struct super_block *sb;
 
+	struct ceph_mount_options *mount_options;
+	struct ceph_client *client;
+
 	unsigned long mount_state;
-	wait_queue_head_t auth_wq;
-
-	int auth_err;
-
 	int min_caps;                  /* min caps i added */
 
-	struct ceph_messenger *msgr;   /* messenger instance */
-	struct ceph_mon_client monc;
-	struct ceph_mds_client mdsc;
-	struct ceph_osd_client osdc;
+	struct ceph_mds_client *mdsc;
 
 	/* writeback */
 	mempool_t *wb_pagevec_pool;
@@ -160,14 +80,14 @@
 	struct backing_dev_info backing_dev_info;
 
 #ifdef CONFIG_DEBUG_FS
-	struct dentry *debugfs_monmap;
-	struct dentry *debugfs_mdsmap, *debugfs_osdmap;
-	struct dentry *debugfs_dir, *debugfs_dentry_lru, *debugfs_caps;
+	struct dentry *debugfs_dentry_lru, *debugfs_caps;
 	struct dentry *debugfs_congestion_kb;
 	struct dentry *debugfs_bdi;
+	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
 #endif
 };
 
+
 /*
  * File i/o capability.  This tracks shared state with the metadata
  * server that allows us to cache or writeback attributes or to read
@@ -275,6 +195,20 @@
 	int should_free_val;
 };
 
+/*
+ * Ceph dentry state
+ */
+struct ceph_dentry_info {
+	struct ceph_mds_session *lease_session;
+	u32 lease_gen, lease_shared_gen;
+	u32 lease_seq;
+	unsigned long lease_renew_after, lease_renew_from;
+	struct list_head lru;
+	struct dentry *dentry;
+	u64 time;
+	u64 offset;
+};
+
 struct ceph_inode_xattrs_info {
 	/*
 	 * (still encoded) xattr blob. we avoid the overhead of parsing
@@ -296,11 +230,6 @@
 /*
  * Ceph inode.
  */
-#define CEPH_I_COMPLETE  1  /* we have complete directory cached */
-#define CEPH_I_NODELAY   4  /* do not delay cap release */
-#define CEPH_I_FLUSH     8  /* do not delay flush of dirty metadata */
-#define CEPH_I_NOFLUSH  16  /* do not flush dirty caps */
-
 struct ceph_inode_info {
 	struct ceph_vino i_vino;   /* ceph ino + snap */
 
@@ -391,69 +320,9 @@
 	return container_of(inode, struct ceph_inode_info, vfs_inode);
 }
 
-static inline void ceph_i_clear(struct inode *inode, unsigned mask)
+static inline struct ceph_vino ceph_vino(struct inode *inode)
 {
-	struct ceph_inode_info *ci = ceph_inode(inode);
-
-	spin_lock(&inode->i_lock);
-	ci->i_ceph_flags &= ~mask;
-	spin_unlock(&inode->i_lock);
-}
-
-static inline void ceph_i_set(struct inode *inode, unsigned mask)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-
-	spin_lock(&inode->i_lock);
-	ci->i_ceph_flags |= mask;
-	spin_unlock(&inode->i_lock);
-}
-
-static inline bool ceph_i_test(struct inode *inode, unsigned mask)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	bool r;
-
-	smp_mb();
-	r = (ci->i_ceph_flags & mask) == mask;
-	return r;
-}
-
-
-/* find a specific frag @f */
-extern struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci,
-						u32 f);
-
-/*
- * choose fragment for value @v.  copy frag content to pfrag, if leaf
- * exists
- */
-extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
-			    struct ceph_inode_frag *pfrag,
-			    int *found);
-
-/*
- * Ceph dentry state
- */
-struct ceph_dentry_info {
-	struct ceph_mds_session *lease_session;
-	u32 lease_gen, lease_shared_gen;
-	u32 lease_seq;
-	unsigned long lease_renew_after, lease_renew_from;
-	struct list_head lru;
-	struct dentry *dentry;
-	u64 time;
-	u64 offset;
-};
-
-static inline struct ceph_dentry_info *ceph_dentry(struct dentry *dentry)
-{
-	return (struct ceph_dentry_info *)dentry->d_fsdata;
-}
-
-static inline loff_t ceph_make_fpos(unsigned frag, unsigned off)
-{
-	return ((loff_t)frag << 32) | (loff_t)off;
+	return ceph_inode(inode)->i_vino;
 }
 
 /*
@@ -472,18 +341,6 @@
 	return ino;
 }
 
-static inline int ceph_set_ino_cb(struct inode *inode, void *data)
-{
-	ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
-	inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
-	return 0;
-}
-
-static inline struct ceph_vino ceph_vino(struct inode *inode)
-{
-	return ceph_inode(inode)->i_vino;
-}
-
 /* for printf-style formatting */
 #define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
 
@@ -513,6 +370,73 @@
 
 
 /*
+ * Ceph inode.
+ */
+#define CEPH_I_COMPLETE  1  /* we have complete directory cached */
+#define CEPH_I_NODELAY   4  /* do not delay cap release */
+#define CEPH_I_FLUSH     8  /* do not delay flush of dirty metadata */
+#define CEPH_I_NOFLUSH  16  /* do not flush dirty caps */
+
+static inline void ceph_i_clear(struct inode *inode, unsigned mask)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	spin_lock(&inode->i_lock);
+	ci->i_ceph_flags &= ~mask;
+	spin_unlock(&inode->i_lock);
+}
+
+static inline void ceph_i_set(struct inode *inode, unsigned mask)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	spin_lock(&inode->i_lock);
+	ci->i_ceph_flags |= mask;
+	spin_unlock(&inode->i_lock);
+}
+
+static inline bool ceph_i_test(struct inode *inode, unsigned mask)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool r;
+
+	spin_lock(&inode->i_lock);
+	r = (ci->i_ceph_flags & mask) == mask;
+	spin_unlock(&inode->i_lock);
+	return r;
+}
+
+
+/* find a specific frag @f */
+extern struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci,
+						u32 f);
+
+/*
+ * choose fragment for value @v.  copy frag content to pfrag, if leaf
+ * exists
+ */
+extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+			    struct ceph_inode_frag *pfrag,
+			    int *found);
+
+static inline struct ceph_dentry_info *ceph_dentry(struct dentry *dentry)
+{
+	return (struct ceph_dentry_info *)dentry->d_fsdata;
+}
+
+static inline loff_t ceph_make_fpos(unsigned frag, unsigned off)
+{
+	return ((loff_t)frag << 32) | (loff_t)off;
+}
+
+static inline int ceph_set_ino_cb(struct inode *inode, void *data)
+{
+	ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
+	inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
+	return 0;
+}
+
+/*
  * caps helpers
  */
 static inline bool __ceph_is_any_real_caps(struct ceph_inode_info *ci)
@@ -576,18 +500,18 @@
 			     struct ceph_cap_reservation *ctx, int need);
 extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
 			       struct ceph_cap_reservation *ctx);
-extern void ceph_reservation_status(struct ceph_client *client,
+extern void ceph_reservation_status(struct ceph_fs_client *client,
 				    int *total, int *avail, int *used,
 				    int *reserved, int *min);
 
-static inline struct ceph_client *ceph_inode_to_client(struct inode *inode)
+static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
 {
-	return (struct ceph_client *)inode->i_sb->s_fs_info;
+	return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
 }
 
-static inline struct ceph_client *ceph_sb_to_client(struct super_block *sb)
+static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
 {
-	return (struct ceph_client *)sb->s_fs_info;
+	return (struct ceph_fs_client *)sb->s_fs_info;
 }
 
 
@@ -617,51 +541,6 @@
 
 
 /*
- * snapshots
- */
-
-/*
- * A "snap context" is the set of existing snapshots when we
- * write data.  It is used by the OSD to guide its COW behavior.
- *
- * The ceph_snap_context is refcounted, and attached to each dirty
- * page, indicating which context the dirty data belonged when it was
- * dirtied.
- */
-struct ceph_snap_context {
-	atomic_t nref;
-	u64 seq;
-	int num_snaps;
-	u64 snaps[];
-};
-
-static inline struct ceph_snap_context *
-ceph_get_snap_context(struct ceph_snap_context *sc)
-{
-	/*
-	printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
-	       atomic_read(&sc->nref)+1);
-	*/
-	if (sc)
-		atomic_inc(&sc->nref);
-	return sc;
-}
-
-static inline void ceph_put_snap_context(struct ceph_snap_context *sc)
-{
-	if (!sc)
-		return;
-	/*
-	printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
-	       atomic_read(&sc->nref)-1);
-	*/
-	if (atomic_dec_and_test(&sc->nref)) {
-		/*printk(" deleting snap_context %p\n", sc);*/
-		kfree(sc);
-	}
-}
-
-/*
  * A "snap realm" describes a subset of the file hierarchy sharing
  * the same set of snapshots that apply to it.  The realms themselves
  * are organized into a hierarchy, such that children inherit (some of)
@@ -699,16 +578,33 @@
 	spinlock_t inodes_with_caps_lock;
 };
 
-
-
-/*
- * calculate the number of pages a given length and offset map onto,
- * if we align the data.
- */
-static inline int calc_pages_for(u64 off, u64 len)
+static inline int default_congestion_kb(void)
 {
-	return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
-		(off >> PAGE_CACHE_SHIFT);
+	int congestion_kb;
+
+	/*
+	 * Copied from NFS
+	 *
+	 * congestion size, scale with available memory.
+	 *
+	 *  64MB:    8192k
+	 * 128MB:   11585k
+	 * 256MB:   16384k
+	 * 512MB:   23170k
+	 *   1GB:   32768k
+	 *   2GB:   46340k
+	 *   4GB:   65536k
+	 *   8GB:   92681k
+	 *  16GB:  131072k
+	 *
+	 * This allows larger machines to have larger/more transfers.
+	 * Limit the default to 256M
+	 */
+	congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
+	if (congestion_kb > 256*1024)
+		congestion_kb = 256*1024;
+
+	return congestion_kb;
 }
 
 
@@ -741,16 +637,6 @@
 			   ci_item)->writing;
 }
 
-
-/* super.c */
-extern struct kmem_cache *ceph_inode_cachep;
-extern struct kmem_cache *ceph_cap_cachep;
-extern struct kmem_cache *ceph_dentry_cachep;
-extern struct kmem_cache *ceph_file_cachep;
-
-extern const char *ceph_msg_type_name(int type);
-extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
-
 /* inode.c */
 extern const struct inode_operations ceph_file_iops;
 
@@ -857,12 +743,18 @@
 /* file.c */
 extern const struct file_operations ceph_file_fops;
 extern const struct address_space_operations ceph_aops;
+extern int ceph_copy_to_page_vector(struct page **pages,
+				    const char *data,
+				    loff_t off, size_t len);
+extern int ceph_copy_from_page_vector(struct page **pages,
+				    char *data,
+				    loff_t off, size_t len);
+extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
 				       struct nameidata *nd, int mode,
 				       int locked_dir);
 extern int ceph_release(struct inode *inode, struct file *filp);
-extern void ceph_release_page_vector(struct page **pages, int num_pages);
 
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
@@ -892,12 +784,6 @@
 /* export.c */
 extern const struct export_operations ceph_export_ops;
 
-/* debugfs.c */
-extern int ceph_debugfs_init(void);
-extern void ceph_debugfs_cleanup(void);
-extern int ceph_debugfs_client_init(struct ceph_client *client);
-extern void ceph_debugfs_client_cleanup(struct ceph_client *client);
-
 /* locks.c */
 extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
 extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
@@ -914,4 +800,8 @@
 	return NULL;
 }
 
+/* debugfs.c */
+extern int ceph_fs_debugfs_init(struct ceph_fs_client *client);
+extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client);
+
 #endif /* _FS_CEPH_SUPER_H */
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 9578af6..6e12a6b 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1,6 +1,9 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
+
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
 
 #include <linux/xattr.h>
 #include <linux/slab.h>
@@ -620,12 +623,12 @@
 static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 			      const char *value, size_t size, int flags)
 {
-	struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
 	struct inode *inode = dentry->d_inode;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct inode *parent_inode = dentry->d_parent->d_inode;
 	struct ceph_mds_request *req;
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	int err;
 	int i, nr_pages;
 	struct page **pages = NULL;
@@ -713,10 +716,9 @@
 
 	/* preallocate memory for xattr name, value, index node */
 	err = -ENOMEM;
-	newname = kmalloc(name_len + 1, GFP_NOFS);
+	newname = kmemdup(name, name_len + 1, GFP_NOFS);
 	if (!newname)
 		goto out;
-	memcpy(newname, name, name_len + 1);
 
 	if (val_len) {
 		newval = kmalloc(val_len + 1, GFP_NOFS);
@@ -777,8 +779,8 @@
 
 static int ceph_send_removexattr(struct dentry *dentry, const char *name)
 {
-	struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
-	struct ceph_mds_client *mdsc = &client->mdsc;
+	struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = dentry->d_inode;
 	struct inode *parent_inode = dentry->d_parent->d_inode;
 	struct ceph_mds_request *req;
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 143d393..e5b9df9 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -456,6 +456,7 @@
  */
 const struct file_operations def_chr_fops = {
 	.open = chrdev_open,
+	.llseek = noop_llseek,
 };
 
 static struct kobject *exact_match(dev_t dev, int *part, void *data)
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index b7431af..50208c1 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -35,7 +35,6 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
-#include <linux/smp_lock.h>
 #include "cifsfs.h"
 #include "cifspdu.h"
 #define DECLARE_GLOBALS_HERE
@@ -200,8 +199,6 @@
 		return;
 	}
 
-	lock_kernel();
-
 	rc = cifs_umount(sb, cifs_sb);
 	if (rc)
 		cERROR(1, "cifs_umount failed with return code %d", rc);
@@ -215,8 +212,6 @@
 	unload_nls(cifs_sb->local_nls);
 	bdi_destroy(&cifs_sb->bdi);
 	kfree(cifs_sb);
-
-	unlock_kernel();
 }
 
 static int
@@ -514,7 +509,9 @@
 	    int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
 	int rc;
-	struct super_block *sb = sget(fs_type, NULL, set_anon_super, NULL);
+	struct super_block *sb;
+
+	sb = sget(fs_type, NULL, set_anon_super, NULL);
 
 	cFYI(1, "Devname: %s flags: %d ", dev_name, flags);
 
@@ -565,8 +562,8 @@
 
 static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
 {
-	/* note that this is called by vfs setlease with the BKL held
-	   although I doubt that BKL is needed here in cifs */
+	/* note that this is called by vfs setlease with lock_flocks held
+	   to protect *lease from going away */
 	struct inode *inode = file->f_path.dentry->d_inode;
 
 	if (!(S_ISREG(inode->i_mode)))
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 6526e6f..bfe8179 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -148,6 +148,8 @@
 	int error;
 	int idx;
 
+	lock_kernel();
+
 	idx = get_device_index((struct coda_mount_data *) data);
 
 	/* Ignore errors in data, for backward compatibility */
@@ -159,11 +161,13 @@
 	vc = &coda_comms[idx];
 	if (!vc->vc_inuse) {
 		printk("coda_read_super: No pseudo device\n");
+		unlock_kernel();
 		return -EINVAL;
 	}
 
         if ( vc->vc_sb ) {
 		printk("coda_read_super: Device already mounted\n");
+		unlock_kernel();
 		return -EBUSY;
 	}
 
@@ -202,7 +206,8 @@
 	sb->s_root = d_alloc_root(root);
 	if (!sb->s_root)
 		goto error;
-        return 0;
+	unlock_kernel();
+	return 0;
 
  error:
 	bdi_destroy(&vc->bdi);
@@ -212,6 +217,7 @@
 	if (vc)
 		vc->vc_sb = NULL;
 
+	unlock_kernel();
 	return -EINVAL;
 }
 
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index ca25d96..028a9a0 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -39,6 +39,7 @@
 const struct file_operations coda_ioctl_operations = {
 	.owner		= THIS_MODULE,
 	.unlocked_ioctl	= coda_pioctl,
+	.llseek		= noop_llseek,
 };
 
 /* the coda pioctl inode ops */
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 116af75..fdc2f3e 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -346,6 +346,7 @@
 	.unlocked_ioctl	= coda_psdev_ioctl,
 	.open		= coda_psdev_open,
 	.release	= coda_psdev_release,
+	.llseek		= noop_llseek,
 };
 
 static int init_coda_psdev(void)
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 03e59aa..d0ad09d 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -599,69 +599,6 @@
 #define HIDPGETCONNLIST	_IOR('H', 210, int)
 #define HIDPGETCONNINFO	_IOR('H', 211, int)
 
-#ifdef CONFIG_BLOCK
-struct raw32_config_request
-{
-        compat_int_t    raw_minor;
-        __u64   block_major;
-        __u64   block_minor;
-} __attribute__((packed));
-
-static int get_raw32_request(struct raw_config_request *req, struct raw32_config_request __user *user_req)
-{
-        int ret;
-
-        if (!access_ok(VERIFY_READ, user_req, sizeof(struct raw32_config_request)))
-                return -EFAULT;
-
-        ret = __get_user(req->raw_minor, &user_req->raw_minor);
-        ret |= __get_user(req->block_major, &user_req->block_major);
-        ret |= __get_user(req->block_minor, &user_req->block_minor);
-
-        return ret ? -EFAULT : 0;
-}
-
-static int set_raw32_request(struct raw_config_request *req, struct raw32_config_request __user *user_req)
-{
-	int ret;
-
-        if (!access_ok(VERIFY_WRITE, user_req, sizeof(struct raw32_config_request)))
-                return -EFAULT;
-
-        ret = __put_user(req->raw_minor, &user_req->raw_minor);
-        ret |= __put_user(req->block_major, &user_req->block_major);
-        ret |= __put_user(req->block_minor, &user_req->block_minor);
-
-        return ret ? -EFAULT : 0;
-}
-
-static int raw_ioctl(unsigned fd, unsigned cmd,
-		struct raw32_config_request __user *user_req)
-{
-        int ret;
-
-        switch (cmd) {
-        case RAW_SETBIND:
-	default: {	/* RAW_GETBIND */
-                struct raw_config_request req;
-                mm_segment_t oldfs = get_fs();
-
-                if ((ret = get_raw32_request(&req, user_req)))
-                        return ret;
-
-                set_fs(KERNEL_DS);
-                ret = sys_ioctl(fd,cmd,(unsigned long)&req);
-                set_fs(oldfs);
-
-                if ((!ret) && (cmd == RAW_GETBIND)) {
-                        ret = set_raw32_request(&req, user_req);
-                }
-                break;
-        }
-        }
-        return ret;
-}
-#endif /* CONFIG_BLOCK */
 
 struct serial_struct32 {
         compat_int_t    type;
@@ -1262,9 +1199,6 @@
 COMPATIBLE_IOCTL(SOUND_MIXER_GETLEVELS)
 COMPATIBLE_IOCTL(SOUND_MIXER_SETLEVELS)
 COMPATIBLE_IOCTL(OSS_GETVERSION)
-/* Raw devices */
-COMPATIBLE_IOCTL(RAW_SETBIND)
-COMPATIBLE_IOCTL(RAW_GETBIND)
 /* SMB ioctls which do not need any translations */
 COMPATIBLE_IOCTL(SMB_IOC_NEWCONN)
 /* Watchdog */
@@ -1523,10 +1457,6 @@
 	case MTIOCGET32:
 	case MTIOCPOS32:
 		return mt_ioctl_trans(fd, cmd, argp);
-	/* Raw devices */
-	case RAW_SETBIND:
-	case RAW_GETBIND:
-		return raw_ioctl(fd, cmd, argp);
 #endif
 	/* One SMB ioctl needs translations. */
 #define SMB_IOC_GETMOUNTUID_32 _IOR('u', 1, compat_uid_t)
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 0210898..89d394d 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -43,6 +43,7 @@
 	.read =		default_read_file,
 	.write =	default_write_file,
 	.open =		default_open,
+	.llseek =	noop_llseek,
 };
 
 static void *debugfs_follow_link(struct dentry *dentry, struct nameidata *nd)
@@ -454,6 +455,7 @@
 	.read =		read_file_bool,
 	.write =	write_file_bool,
 	.open =		default_open,
+	.llseek =	default_llseek,
 };
 
 /**
@@ -498,6 +500,7 @@
 static const struct file_operations fops_blob = {
 	.read =		read_file_blob,
 	.open =		default_open,
+	.llseek =	default_llseek,
 };
 
 /**
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index c6cf251..6b42ba8 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -643,7 +643,8 @@
 static const struct file_operations waiters_fops = {
 	.owner   = THIS_MODULE,
 	.open    = waiters_open,
-	.read    = waiters_read
+	.read    = waiters_read,
+	.llseek  = default_llseek,
 };
 
 void dlm_delete_debug_file(struct dlm_ls *ls)
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 031dbe3..64e5f3e 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1846,6 +1846,9 @@
 	struct dlm_lkb *gr;
 
 	list_for_each_entry(gr, head, lkb_statequeue) {
+		/* skip self when sending basts to convertqueue */
+		if (gr == lkb)
+			continue;
 		if (gr->lkb_bastfn && modes_require_bast(gr, lkb)) {
 			queue_bast(r, gr, lkb->lkb_rqmode);
 			gr->lkb_highbast = lkb->lkb_rqmode;
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index d45c02d..30d8b85 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -412,7 +412,8 @@
 	.read    = dev_read,
 	.write   = dev_write,
 	.poll    = dev_poll,
-	.owner   = THIS_MODULE
+	.owner   = THIS_MODULE,
+	.llseek  = noop_llseek,
 };
 
 static struct miscdevice plock_dev_misc = {
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index b627285..66d6c16 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -1009,6 +1009,7 @@
 	.write   = device_write,
 	.poll    = device_poll,
 	.owner   = THIS_MODULE,
+	.llseek  = noop_llseek,
 };
 
 static const struct file_operations ctl_device_fops = {
@@ -1017,6 +1018,7 @@
 	.read    = device_read,
 	.write   = device_write,
 	.owner   = THIS_MODULE,
+	.llseek  = noop_llseek,
 };
 
 static struct miscdevice ctl_device = {
@@ -1029,6 +1031,7 @@
 	.open    = monitor_device_open,
 	.release = monitor_device_close,
 	.owner   = THIS_MODULE,
+	.llseek  = noop_llseek,
 };
 
 static struct miscdevice monitor_device = {
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 622c9514..91da029 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -31,7 +31,6 @@
 #include <linux/security.h>
 #include <linux/compat.h>
 #include <linux/fs_stack.h>
-#include <linux/smp_lock.h>
 #include "ecryptfs_kernel.h"
 
 /**
@@ -284,11 +283,9 @@
 	int rc = 0;
 	struct file *lower_file = NULL;
 
-	lock_kernel();
 	lower_file = ecryptfs_file_to_lower(file);
 	if (lower_file->f_op && lower_file->f_op->fasync)
 		rc = lower_file->f_op->fasync(fd, lower_file, flag);
-	unlock_kernel();
 	return rc;
 }
 
@@ -332,6 +329,7 @@
 	.fsync = ecryptfs_fsync,
 	.fasync = ecryptfs_fasync,
 	.splice_read = generic_file_splice_read,
+	.llseek = default_llseek,
 };
 
 const struct file_operations ecryptfs_main_fops = {
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 00208c3..940a82e 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -482,6 +482,7 @@
 	.read    = ecryptfs_miscdev_read,
 	.write   = ecryptfs_miscdev_write,
 	.release = ecryptfs_miscdev_release,
+	.llseek  = noop_llseek,
 };
 
 static struct miscdevice ecryptfs_miscdev = {
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 6bd3f76..e0194b3 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -293,6 +293,7 @@
 	.poll		= eventfd_poll,
 	.read		= eventfd_read,
 	.write		= eventfd_write,
+	.llseek		= noop_llseek,
 };
 
 /**
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3817149..256bb7b 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -674,7 +674,8 @@
 /* File callbacks that implement the eventpoll file behaviour */
 static const struct file_operations eventpoll_fops = {
 	.release	= ep_eventpoll_release,
-	.poll		= ep_eventpoll_poll
+	.poll		= ep_eventpoll_poll,
+	.llseek		= noop_llseek,
 };
 
 /* Fast test to see if the file is an evenpoll file */
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 1ec6026..85df87d 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -747,15 +747,16 @@
 	__le32 features;
 	int err;
 
+	err = -ENOMEM;
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
-		return -ENOMEM;
+		goto failed_unlock;
 
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
 	if (!sbi->s_blockgroup_lock) {
 		kfree(sbi);
-		return -ENOMEM;
+		goto failed_unlock;
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_sb_block = sb_block;
@@ -1107,6 +1108,7 @@
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
+failed_unlock:
 	return ret;
 }
 
diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c
index d7e9f74..09b13bb 100644
--- a/fs/ext3/fsync.c
+++ b/fs/ext3/fsync.c
@@ -90,7 +90,6 @@
 	 * storage
 	 */
 	if (needs_barrier)
-		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
-				BLKDEV_IFL_WAIT);
+		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 	return ret;
 }
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 5dbf4db..3777680 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -411,9 +411,6 @@
 	int i, err;
 
 	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
-
-	lock_kernel();
-
 	ext3_xattr_put_super(sb);
 	err = journal_destroy(sbi->s_journal);
 	sbi->s_journal = NULL;
@@ -462,8 +459,6 @@
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-
-	unlock_kernel();
 }
 
 static struct kmem_cache *ext3_inode_cachep;
@@ -1627,8 +1622,6 @@
 	sbi->s_resgid = EXT3_DEF_RESGID;
 	sbi->s_sb_block = sb_block;
 
-	unlock_kernel();
-
 	blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE);
 	if (!blocksize) {
 		ext3_msg(sb, KERN_ERR, "error: unable to set blocksize");
@@ -1849,8 +1842,8 @@
 		goto failed_mount;
 	}
 
-	if (le32_to_cpu(es->s_blocks_count) >
-		    (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
+	if (generic_check_addressable(sb->s_blocksize_bits,
+				      le32_to_cpu(es->s_blocks_count))) {
 		ext3_msg(sb, KERN_ERR,
 			"error: filesystem is too large to mount safely");
 		if (sizeof(sector_t) < 8)
@@ -2025,7 +2018,6 @@
 		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
 		"writeback");
 
-	lock_kernel();
 	return 0;
 
 cantfind_ext3:
@@ -2055,7 +2047,6 @@
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-	lock_kernel();
 	return ret;
 }
 
@@ -2538,8 +2529,6 @@
 	int i;
 #endif
 
-	lock_kernel();
-
 	/* Store the original options */
 	lock_super(sb);
 	old_sb_flags = sb->s_flags;
@@ -2648,7 +2637,6 @@
 			kfree(old_opts.s_qf_names[i]);
 #endif
 	unlock_super(sb);
-	unlock_kernel();
 
 	if (enable_quota)
 		dquot_resume(sb, -1);
@@ -2669,7 +2657,6 @@
 	}
 #endif
 	unlock_super(sb);
-	unlock_kernel();
 	return err;
 }
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 592adf2..3f3ff5e 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -128,10 +128,9 @@
 		    (journal->j_fs_dev != journal->j_dev) &&
 		    (journal->j_flags & JBD2_BARRIER))
 			blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL,
-					NULL, BLKDEV_IFL_WAIT);
+					NULL);
 		ret = jbd2_log_wait_commit(journal, commit_tid);
 	} else if (journal->j_flags & JBD2_BARRIER)
-		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
-			BLKDEV_IFL_WAIT);
+		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 	return ret;
 }
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4b4ad4b..19aa0d4 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2566,7 +2566,7 @@
 	discard_block = block + ext4_group_first_block_no(sb, block_group);
 	trace_ext4_discard_blocks(sb,
 			(unsigned long long) discard_block, count);
-	ret = sb_issue_discard(sb, discard_block, count);
+	ret = sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
 	if (ret == EOPNOTSUPP) {
 		ext4_warning(sb, "discard not supported, disabling");
 		clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2614774..8ecc1e5 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -26,7 +26,6 @@
 #include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/parser.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
 #include <linux/vfs.h>
@@ -708,7 +707,6 @@
 	destroy_workqueue(sbi->dio_unwritten_wq);
 
 	lock_super(sb);
-	lock_kernel();
 	if (sb->s_dirt)
 		ext4_commit_super(sb, 1);
 
@@ -775,7 +773,6 @@
 	 * Now that we are completely done shutting down the
 	 * superblock, we need to actually destroy the kobject.
 	 */
-	unlock_kernel();
 	unlock_super(sb);
 	kobject_put(&sbi->s_kobj);
 	wait_for_completion(&sbi->s_kobj_unregister);
@@ -2588,8 +2585,6 @@
 		sbi->s_sectors_written_start =
 			part_stat_read(sb->s_bdev->bd_part, sectors[1]);
 
-	unlock_kernel();
-
 	/* Cleanup superblock name */
 	for (cp = sb->s_id; (cp = strchr(cp, '/'));)
 		*cp = '!';
@@ -2831,15 +2826,13 @@
 	 * Test whether we have more sectors than will fit in sector_t,
 	 * and whether the max offset is addressable by the page cache.
 	 */
-	if ((ext4_blocks_count(es) >
-	     (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) ||
-	    (ext4_blocks_count(es) >
-	     (pgoff_t)(~0ULL) >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits))) {
+	ret = generic_check_addressable(sb->s_blocksize_bits,
+					ext4_blocks_count(es));
+	if (ret) {
 		ext4_msg(sb, KERN_ERR, "filesystem"
 			 " too large to mount safely on this system");
 		if (sizeof(sector_t) < 8)
 			ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
-		ret = -EFBIG;
 		goto failed_mount;
 	}
 
@@ -3166,7 +3159,6 @@
 	if (es->s_error_count)
 		mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
 
-	lock_kernel();
 	kfree(orig_data);
 	return 0;
 
@@ -3213,7 +3205,6 @@
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-	lock_kernel();
 out_free_orig:
 	kfree(orig_data);
 	return ret;
@@ -3722,8 +3713,6 @@
 #endif
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 
-	lock_kernel();
-
 	/* Store the original options */
 	lock_super(sb);
 	old_sb_flags = sb->s_flags;
@@ -3858,7 +3847,6 @@
 			kfree(old_opts.s_qf_names[i]);
 #endif
 	unlock_super(sb);
-	unlock_kernel();
 	if (enable_quota)
 		dquot_resume(sb, -1);
 
@@ -3884,7 +3872,6 @@
 	}
 #endif
 	unlock_super(sb);
-	unlock_kernel();
 	kfree(orig_data);
 	return err;
 }
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index 81184d3..b47d2c9 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -577,7 +577,8 @@
 
 				sb_issue_discard(sb,
 					fat_clus_to_blknr(sbi, first_cl),
-					nr_clus * sbi->sec_per_clus);
+					nr_clus * sbi->sec_per_clus,
+					GFP_NOFS, 0);
 
 				first_cl = cluster;
 			}
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 8300580..ad6998a 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/time.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/seq_file.h>
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
@@ -489,8 +488,6 @@
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 
-	lock_kernel();
-
 	if (sb->s_dirt)
 		fat_write_super(sb);
 
@@ -504,8 +501,6 @@
 
 	sb->s_fs_info = NULL;
 	kfree(sbi);
-
-	unlock_kernel();
 }
 
 static struct kmem_cache *fat_inode_cachep;
diff --git a/fs/fat/misc.c b/fs/fat/misc.c
index 1736f23..970e682 100644
--- a/fs/fat/misc.c
+++ b/fs/fat/misc.c
@@ -255,10 +255,7 @@
 
 	for (i = 0; i < nr_bhs; i++) {
 		wait_on_buffer(bhs[i]);
-		if (buffer_eopnotsupp(bhs[i])) {
-			clear_buffer_eopnotsupp(bhs[i]);
-			err = -EOPNOTSUPP;
-		} else if (!err && !buffer_uptodate(bhs[i]))
+		if (!err && !buffer_uptodate(bhs[i]))
 			err = -EIO;
 	}
 	return err;
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index bbc94ae..bbca5c1 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -662,12 +662,16 @@
 {
 	int res;
 
+	lock_super(sb);
 	res = fat_fill_super(sb, data, silent, &msdos_dir_inode_operations, 0);
-	if (res)
+	if (res) {
+		unlock_super(sb);
 		return res;
+	}
 
 	sb->s_flags |= MS_NOATIME;
 	sb->s_root->d_op = &msdos_dentry_operations;
+	unlock_super(sb);
 	return 0;
 }
 
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 6fcc7e7..6f0f6c9 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -1055,15 +1055,19 @@
 {
 	int res;
 
+	lock_super(sb);
 	res = fat_fill_super(sb, data, silent, &vfat_dir_inode_operations, 1);
-	if (res)
+	if (res) {
+		unlock_super(sb);
 		return res;
+	}
 
 	if (MSDOS_SB(sb)->options.name_check != 's')
 		sb->s_root->d_op = &vfat_ci_dentry_ops;
 	else
 		sb->s_root->d_op = &vfat_dentry_ops;
 
+	unlock_super(sb);
 	return 0;
 }
 
diff --git a/fs/fifo.c b/fs/fifo.c
index 5d6606f..4e303c2 100644
--- a/fs/fifo.c
+++ b/fs/fifo.c
@@ -151,4 +151,5 @@
  */
 const struct file_operations def_fifo_fops = {
 	.open		= fifo_open,	/* will set read_ or write_pipefifo_fops */
+	.llseek		= noop_llseek,
 };
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index 0ec7bb2..6c5131d 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -36,7 +36,6 @@
 #include <linux/highmem.h>
 #include <linux/kernel.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 
 #include "vxfs.h"
 #include "vxfs_dir.h"
@@ -212,16 +211,12 @@
 	if (dp->d_name.len > VXFS_NAMELEN)
 		return ERR_PTR(-ENAMETOOLONG);
 				 
-	lock_kernel();
 	ino = vxfs_inode_by_name(dip, dp);
 	if (ino) {
 		ip = vxfs_iget(dip->i_sb, ino);
-		if (IS_ERR(ip)) {
-			unlock_kernel();
+		if (IS_ERR(ip))
 			return ERR_CAST(ip);
-		}
 	}
-	unlock_kernel();
 	d_add(dp, ip);
 	return NULL;
 }
@@ -248,8 +243,6 @@
 	u_long			page, npages, block, pblocks, nblocks, offset;
 	loff_t			pos;
 
-	lock_kernel();
-
 	switch ((long)fp->f_pos) {
 	case 0:
 		if (filler(retp, ".", 1, fp->f_pos, ip->i_ino, DT_DIR) < 0)
@@ -265,10 +258,8 @@
 
 	pos = fp->f_pos - 2;
 	
-	if (pos > VXFS_DIRROUND(ip->i_size)) {
-		unlock_kernel();
+	if (pos > VXFS_DIRROUND(ip->i_size))
 		return 0;
-	}
 
 	npages = dir_pages(ip);
 	nblocks = dir_blocks(ip);
@@ -327,6 +318,5 @@
 done:
 	fp->f_pos = ((page << PAGE_CACHE_SHIFT) | offset) + 2;
 out:
-	unlock_kernel();
 	return 0;
 }
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index dc0c041..71b0148 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -38,7 +38,6 @@
 #include <linux/buffer_head.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/stat.h>
 #include <linux/vfs.h>
 #include <linux/mount.h>
@@ -81,16 +80,12 @@
 {
 	struct vxfs_sb_info	*infp = VXFS_SBI(sbp);
 
-	lock_kernel();
-
 	vxfs_put_fake_inode(infp->vsi_fship);
 	vxfs_put_fake_inode(infp->vsi_ilist);
 	vxfs_put_fake_inode(infp->vsi_stilist);
 
 	brelse(infp->vsi_bp);
 	kfree(infp);
-
-	unlock_kernel();
 }
 
 /**
@@ -148,7 +143,7 @@
  *   The superblock on success, else %NULL.
  *
  * Locking:
- *   We are under the bkl and @sbp->s_lock.
+ *   We are under @sbp->s_lock.
  */
 static int vxfs_fill_super(struct super_block *sbp, void *dp, int silent)
 {
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 3773fd6..7367e17 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -179,23 +179,27 @@
 static const struct file_operations fuse_ctl_abort_ops = {
 	.open = nonseekable_open,
 	.write = fuse_conn_abort_write,
+	.llseek = no_llseek,
 };
 
 static const struct file_operations fuse_ctl_waiting_ops = {
 	.open = nonseekable_open,
 	.read = fuse_conn_waiting_read,
+	.llseek = no_llseek,
 };
 
 static const struct file_operations fuse_conn_max_background_ops = {
 	.open = nonseekable_open,
 	.read = fuse_conn_max_background_read,
 	.write = fuse_conn_max_background_write,
+	.llseek = no_llseek,
 };
 
 static const struct file_operations fuse_conn_congestion_threshold_ops = {
 	.open = nonseekable_open,
 	.read = fuse_conn_congestion_threshold_read,
 	.write = fuse_conn_congestion_threshold_write,
+	.llseek = no_llseek,
 };
 
 static struct dentry *fuse_ctl_add_dentry(struct dentry *parent,
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index e1f8171..3e87cce 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -182,6 +182,7 @@
 	.unlocked_ioctl		= cuse_file_ioctl,
 	.compat_ioctl		= cuse_file_compat_ioctl,
 	.poll			= fuse_file_poll,
+	.llseek		= noop_llseek,
 };
 
 
diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
index cc96655..c465ae0 100644
--- a/fs/gfs2/Kconfig
+++ b/fs/gfs2/Kconfig
@@ -1,6 +1,6 @@
 config GFS2_FS
 	tristate "GFS2 file system support"
-	depends on EXPERIMENTAL && (64BIT || LBDAF)
+	depends on (64BIT || LBDAF)
 	select DLM if GFS2_FS_LOCKING_DLM
 	select CONFIGFS_FS if GFS2_FS_LOCKING_DLM
 	select SYSFS if GFS2_FS_LOCKING_DLM
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 194fe16..6b24afb 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -36,8 +36,8 @@
 #include "glops.h"
 
 
-static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
-				   unsigned int from, unsigned int to)
+void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+			    unsigned int from, unsigned int to)
 {
 	struct buffer_head *head = page_buffers(page);
 	unsigned int bsize = head->b_size;
@@ -615,7 +615,7 @@
 	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
 	int alloc_required;
 	int error = 0;
-	struct gfs2_alloc *al;
+	struct gfs2_alloc *al = NULL;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
 	unsigned to = from + len;
@@ -663,6 +663,8 @@
 		rblocks += RES_STATFS + RES_QUOTA;
 	if (&ip->i_inode == sdp->sd_rindex)
 		rblocks += 2 * RES_STATFS;
+	if (alloc_required)
+		rblocks += gfs2_rg_blocks(al);
 
 	error = gfs2_trans_begin(sdp, rblocks,
 				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
@@ -696,13 +698,11 @@
 
 	page_cache_release(page);
 
-	/*
-	 * XXX(truncate): the call below should probably be replaced with
-	 * a call to the gfs2-specific truncate blocks helper to actually
-	 * release disk blocks..
-	 */
+	gfs2_trans_end(sdp);
 	if (pos + len > ip->i_inode.i_size)
-		truncate_setsize(&ip->i_inode, ip->i_inode.i_size);
+		gfs2_trim_blocks(&ip->i_inode);
+	goto out_trans_fail;
+
 out_endtrans:
 	gfs2_trans_end(sdp);
 out_trans_fail:
@@ -802,10 +802,8 @@
 	page_cache_release(page);
 
 	if (copied) {
-		if (inode->i_size < to) {
+		if (inode->i_size < to)
 			i_size_write(inode, to);
-			ip->i_disksize = inode->i_size;
-		}
 		gfs2_dinode_out(ip, di);
 		mark_inode_dirty(inode);
 	}
@@ -876,8 +874,6 @@
 
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
 	if (ret > 0) {
-		if (inode->i_size > ip->i_disksize)
-			ip->i_disksize = inode->i_size;
 		gfs2_dinode_out(ip, dibh->b_data);
 		mark_inode_dirty(inode);
 	}
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 6f48280..5476c06 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -50,7 +50,7 @@
  * @ip: the inode
  * @dibh: the dinode buffer
  * @block: the block number that was allocated
- * @private: any locked page held by the caller process
+ * @page: The (optional) page. This is looked up if @page is NULL
  *
  * Returns: errno
  */
@@ -109,8 +109,7 @@
 /**
  * gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big
  * @ip: The GFS2 inode to unstuff
- * @unstuffer: the routine that handles unstuffing a non-zero length file
- * @private: private data for the unstuffer
+ * @page: The (optional) page. This is looked up if the @page is NULL
  *
  * This routine unstuffs a dinode and returns it to a "normal" state such
  * that the height can be grown in the traditional way.
@@ -132,7 +131,7 @@
 	if (error)
 		goto out;
 
-	if (ip->i_disksize) {
+	if (i_size_read(&ip->i_inode)) {
 		/* Get a free block, fill it with the stuffed data,
 		   and write it out to disk */
 
@@ -161,7 +160,7 @@
 	di = (struct gfs2_dinode *)dibh->b_data;
 	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
 
-	if (ip->i_disksize) {
+	if (i_size_read(&ip->i_inode)) {
 		*(__be64 *)(di + 1) = cpu_to_be64(block);
 		gfs2_add_inode_blocks(&ip->i_inode, 1);
 		di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
@@ -885,83 +884,14 @@
 }
 
 /**
- * do_grow - Make a file look bigger than it is
- * @ip: the inode
- * @size: the size to set the file to
- *
- * Called with an exclusive lock on @ip.
- *
- * Returns: errno
- */
-
-static int do_grow(struct gfs2_inode *ip, u64 size)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc *al;
-	struct buffer_head *dibh;
-	int error;
-
-	al = gfs2_alloc_get(ip);
-	if (!al)
-		return -ENOMEM;
-
-	error = gfs2_quota_lock_check(ip);
-	if (error)
-		goto out;
-
-	al->al_requested = sdp->sd_max_height + RES_DATA;
-
-	error = gfs2_inplace_reserve(ip);
-	if (error)
-		goto out_gunlock_q;
-
-	error = gfs2_trans_begin(sdp,
-			sdp->sd_max_height + al->al_rgd->rd_length +
-			RES_JDATA + RES_DINODE + RES_STATFS + RES_QUOTA, 0);
-	if (error)
-		goto out_ipres;
-
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (error)
-		goto out_end_trans;
-
-	if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
-		if (gfs2_is_stuffed(ip)) {
-			error = gfs2_unstuff_dinode(ip, NULL);
-			if (error)
-				goto out_brelse;
-		}
-	}
-
-	ip->i_disksize = size;
-	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-	gfs2_dinode_out(ip, dibh->b_data);
-
-out_brelse:
-	brelse(dibh);
-out_end_trans:
-	gfs2_trans_end(sdp);
-out_ipres:
-	gfs2_inplace_release(ip);
-out_gunlock_q:
-	gfs2_quota_unlock(ip);
-out:
-	gfs2_alloc_put(ip);
-	return error;
-}
-
-
-/**
  * gfs2_block_truncate_page - Deal with zeroing out data for truncate
  *
  * This is partly borrowed from ext3.
  */
-static int gfs2_block_truncate_page(struct address_space *mapping)
+static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
 {
 	struct inode *inode = mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
-	loff_t from = inode->i_size;
 	unsigned long index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
 	unsigned blocksize, iblock, length, pos;
@@ -1023,9 +953,11 @@
 	return err;
 }
 
-static int trunc_start(struct gfs2_inode *ip, u64 size)
+static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct address_space *mapping = inode->i_mapping;
 	struct buffer_head *dibh;
 	int journaled = gfs2_is_jdata(ip);
 	int error;
@@ -1039,31 +971,26 @@
 	if (error)
 		goto out;
 
-	if (gfs2_is_stuffed(ip)) {
-		u64 dsize = size + sizeof(struct gfs2_dinode);
-		ip->i_disksize = size;
-		ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
-		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-		gfs2_dinode_out(ip, dibh->b_data);
-		if (dsize > dibh->b_size)
-			dsize = dibh->b_size;
-		gfs2_buffer_clear_tail(dibh, dsize);
-		error = 1;
-	} else {
-		if (size & (u64)(sdp->sd_sb.sb_bsize - 1))
-			error = gfs2_block_truncate_page(ip->i_inode.i_mapping);
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
 
-		if (!error) {
-			ip->i_disksize = size;
-			ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
-			ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG;
-			gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-			gfs2_dinode_out(ip, dibh->b_data);
+	if (gfs2_is_stuffed(ip)) {
+		gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize);
+	} else {
+		if (newsize & (u64)(sdp->sd_sb.sb_bsize - 1)) {
+			error = gfs2_block_truncate_page(mapping, newsize);
+			if (error)
+				goto out_brelse;
 		}
+		ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG;
 	}
 
-	brelse(dibh);
+	i_size_write(inode, newsize);
+	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+	gfs2_dinode_out(ip, dibh->b_data);
 
+	truncate_pagecache(inode, oldsize, newsize);
+out_brelse:
+	brelse(dibh);
 out:
 	gfs2_trans_end(sdp);
 	return error;
@@ -1123,7 +1050,7 @@
 	if (error)
 		goto out;
 
-	if (!ip->i_disksize) {
+	if (!i_size_read(&ip->i_inode)) {
 		ip->i_height = 0;
 		ip->i_goal = ip->i_no_addr;
 		gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
@@ -1143,92 +1070,154 @@
 
 /**
  * do_shrink - make a file smaller
- * @ip: the inode
- * @size: the size to make the file
- * @truncator: function to truncate the last partial block
+ * @inode: the inode
+ * @oldsize: the current inode size
+ * @newsize: the size to make the file
  *
- * Called with an exclusive lock on @ip.
+ * Called with an exclusive lock on @inode. The @size must
+ * be equal to or smaller than the current inode size.
  *
  * Returns: errno
  */
 
-static int do_shrink(struct gfs2_inode *ip, u64 size)
+static int do_shrink(struct inode *inode, u64 oldsize, u64 newsize)
 {
+	struct gfs2_inode *ip = GFS2_I(inode);
 	int error;
 
-	error = trunc_start(ip, size);
+	error = trunc_start(inode, oldsize, newsize);
 	if (error < 0)
 		return error;
-	if (error > 0)
+	if (gfs2_is_stuffed(ip))
 		return 0;
 
-	error = trunc_dealloc(ip, size);
-	if (!error)
+	error = trunc_dealloc(ip, newsize);
+	if (error == 0)
 		error = trunc_end(ip);
 
 	return error;
 }
 
-static int do_touch(struct gfs2_inode *ip, u64 size)
+void gfs2_trim_blocks(struct inode *inode)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	u64 size = inode->i_size;
+	int ret;
+
+	ret = do_shrink(inode, size, size);
+	WARN_ON(ret != 0);
+}
+
+/**
+ * do_grow - Touch and update inode size
+ * @inode: The inode
+ * @size: The new size
+ *
+ * This function updates the timestamps on the inode and
+ * may also increase the size of the inode. This function
+ * must not be called with @size any smaller than the current
+ * inode size.
+ *
+ * Although it is not strictly required to unstuff files here,
+ * earlier versions of GFS2 have a bug in the stuffed file reading
+ * code which will result in a buffer overrun if the size is larger
+ * than the max stuffed file size. In order to prevent this from
+ * occuring, such files are unstuffed, but in other cases we can
+ * just update the inode size directly.
+ *
+ * Returns: 0 on success, or -ve on error
+ */
+
+static int do_grow(struct inode *inode, u64 size)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct buffer_head *dibh;
+	struct gfs2_alloc *al = NULL;
 	int error;
 
-	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
-	if (error)
-		return error;
+	if (gfs2_is_stuffed(ip) &&
+	    (size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) {
+		al = gfs2_alloc_get(ip);
+		if (al == NULL)
+			return -ENOMEM;
 
-	down_write(&ip->i_rw_mutex);
+		error = gfs2_quota_lock_check(ip);
+		if (error)
+			goto do_grow_alloc_put;
+
+		al->al_requested = 1;
+		error = gfs2_inplace_reserve(ip);
+		if (error)
+			goto do_grow_qunlock;
+	}
+
+	error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT, 0);
+	if (error)
+		goto do_grow_release;
+
+	if (al) {
+		error = gfs2_unstuff_dinode(ip, NULL);
+		if (error)
+			goto do_end_trans;
+	}
 
 	error = gfs2_meta_inode_buffer(ip, &dibh);
 	if (error)
-		goto do_touch_out;
+		goto do_end_trans;
 
+	i_size_write(inode, size);
 	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
 	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
 	gfs2_dinode_out(ip, dibh->b_data);
 	brelse(dibh);
 
-do_touch_out:
-	up_write(&ip->i_rw_mutex);
+do_end_trans:
 	gfs2_trans_end(sdp);
+do_grow_release:
+	if (al) {
+		gfs2_inplace_release(ip);
+do_grow_qunlock:
+		gfs2_quota_unlock(ip);
+do_grow_alloc_put:
+		gfs2_alloc_put(ip);
+	}
 	return error;
 }
 
 /**
- * gfs2_truncatei - make a file a given size
- * @ip: the inode
- * @size: the size to make the file
- * @truncator: function to truncate the last partial block
+ * gfs2_setattr_size - make a file a given size
+ * @inode: the inode
+ * @newsize: the size to make the file
  *
- * The file size can grow, shrink, or stay the same size.
+ * The file size can grow, shrink, or stay the same size. This
+ * is called holding i_mutex and an exclusive glock on the inode
+ * in question.
  *
  * Returns: errno
  */
 
-int gfs2_truncatei(struct gfs2_inode *ip, u64 size)
+int gfs2_setattr_size(struct inode *inode, u64 newsize)
 {
-	int error;
+	int ret;
+	u64 oldsize;
 
-	if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), S_ISREG(ip->i_inode.i_mode)))
-		return -EINVAL;
+	BUG_ON(!S_ISREG(inode->i_mode));
 
-	if (size > ip->i_disksize)
-		error = do_grow(ip, size);
-	else if (size < ip->i_disksize)
-		error = do_shrink(ip, size);
-	else
-		/* update time stamps */
-		error = do_touch(ip, size);
+	ret = inode_newsize_ok(inode, newsize);
+	if (ret)
+		return ret;
 
-	return error;
+	oldsize = inode->i_size;
+	if (newsize >= oldsize)
+		return do_grow(inode, newsize);
+
+	return do_shrink(inode, oldsize, newsize);
 }
 
 int gfs2_truncatei_resume(struct gfs2_inode *ip)
 {
 	int error;
-	error = trunc_dealloc(ip, ip->i_disksize);
+	error = trunc_dealloc(ip, i_size_read(&ip->i_inode));
 	if (!error)
 		error = trunc_end(ip);
 	return error;
@@ -1269,7 +1258,7 @@
 
 	shift = sdp->sd_sb.sb_bsize_shift;
 	BUG_ON(gfs2_is_dir(ip));
-	end_of_file = (ip->i_disksize + sdp->sd_sb.sb_bsize - 1) >> shift;
+	end_of_file = (i_size_read(&ip->i_inode) + sdp->sd_sb.sb_bsize - 1) >> shift;
 	lblock = offset >> shift;
 	lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift;
 	if (lblock_stop > end_of_file)
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index a20a521..42fea03 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -44,14 +44,16 @@
 	}
 }
 
-int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
-int gfs2_block_map(struct inode *inode, sector_t lblock, struct buffer_head *bh, int create);
-int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen);
-
-int gfs2_truncatei(struct gfs2_inode *ip, u64 size);
-int gfs2_truncatei_resume(struct gfs2_inode *ip);
-int gfs2_file_dealloc(struct gfs2_inode *ip);
-int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
-			      unsigned int len);
+extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
+extern int gfs2_block_map(struct inode *inode, sector_t lblock,
+			  struct buffer_head *bh, int create);
+extern int gfs2_extent_map(struct inode *inode, u64 lblock, int *new,
+			   u64 *dblock, unsigned *extlen);
+extern int gfs2_setattr_size(struct inode *inode, u64 size);
+extern void gfs2_trim_blocks(struct inode *inode);
+extern int gfs2_truncatei_resume(struct gfs2_inode *ip);
+extern int gfs2_file_dealloc(struct gfs2_inode *ip);
+extern int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
+				     unsigned int len);
 
 #endif /* __BMAP_DOT_H__ */
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index bb7907b..6798755 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -49,7 +49,7 @@
 		ip = GFS2_I(inode);
 	}
 
-	if (sdp->sd_args.ar_localcaching)
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
 		goto valid;
 
 	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index b9dd88a..5c356d0 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -79,6 +79,9 @@
 #define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1)
 #define gfs2_dir_offset2hash(p) ((u32)(((u64)(p)) << 1))
 
+struct qstr gfs2_qdot __read_mostly;
+struct qstr gfs2_qdotdot __read_mostly;
+
 typedef int (*leaf_call_t) (struct gfs2_inode *dip, u32 index, u32 len,
 			    u64 leaf_no, void *data);
 typedef int (*gfs2_dscan_t)(const struct gfs2_dirent *dent,
@@ -127,8 +130,8 @@
 
 	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
 	memcpy(dibh->b_data + offset + sizeof(struct gfs2_dinode), buf, size);
-	if (ip->i_disksize < offset + size)
-		ip->i_disksize = offset + size;
+	if (ip->i_inode.i_size < offset + size)
+		i_size_write(&ip->i_inode, offset + size);
 	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
 	gfs2_dinode_out(ip, dibh->b_data);
 
@@ -225,8 +228,8 @@
 	if (error)
 		return error;
 
-	if (ip->i_disksize < offset + copied)
-		ip->i_disksize = offset + copied;
+	if (ip->i_inode.i_size < offset + copied)
+		i_size_write(&ip->i_inode, offset + copied);
 	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
 
 	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
@@ -275,12 +278,13 @@
 	unsigned int o;
 	int copied = 0;
 	int error = 0;
+	u64 disksize = i_size_read(&ip->i_inode);
 
-	if (offset >= ip->i_disksize)
+	if (offset >= disksize)
 		return 0;
 
-	if (offset + size > ip->i_disksize)
-		size = ip->i_disksize - offset;
+	if (offset + size > disksize)
+		size = disksize - offset;
 
 	if (!size)
 		return 0;
@@ -727,7 +731,7 @@
 		unsigned hsize = 1 << ip->i_depth;
 		unsigned index;
 		u64 ln;
-		if (hsize * sizeof(u64) != ip->i_disksize) {
+		if (hsize * sizeof(u64) != i_size_read(inode)) {
 			gfs2_consist_inode(ip);
 			return ERR_PTR(-EIO);
 		}
@@ -879,7 +883,7 @@
 	for (x = sdp->sd_hash_ptrs; x--; lp++)
 		*lp = cpu_to_be64(bn);
 
-	dip->i_disksize = sdp->sd_sb.sb_bsize / 2;
+	i_size_write(inode, sdp->sd_sb.sb_bsize / 2);
 	gfs2_add_inode_blocks(&dip->i_inode, 1);
 	dip->i_diskflags |= GFS2_DIF_EXHASH;
 
@@ -1057,11 +1061,12 @@
 	u64 *buf;
 	u64 *from, *to;
 	u64 block;
+	u64 disksize = i_size_read(&dip->i_inode);
 	int x;
 	int error = 0;
 
 	hsize = 1 << dip->i_depth;
-	if (hsize * sizeof(u64) != dip->i_disksize) {
+	if (hsize * sizeof(u64) != disksize) {
 		gfs2_consist_inode(dip);
 		return -EIO;
 	}
@@ -1072,7 +1077,7 @@
 	if (!buf)
 		return -ENOMEM;
 
-	for (block = dip->i_disksize >> sdp->sd_hash_bsize_shift; block--;) {
+	for (block = disksize >> sdp->sd_hash_bsize_shift; block--;) {
 		error = gfs2_dir_read_data(dip, (char *)buf,
 					    block * sdp->sd_hash_bsize,
 					    sdp->sd_hash_bsize, 1);
@@ -1370,7 +1375,7 @@
 	unsigned depth = 0;
 
 	hsize = 1 << dip->i_depth;
-	if (hsize * sizeof(u64) != dip->i_disksize) {
+	if (hsize * sizeof(u64) != i_size_read(inode)) {
 		gfs2_consist_inode(dip);
 		return -EIO;
 	}
@@ -1784,7 +1789,7 @@
 	int error = 0;
 
 	hsize = 1 << dip->i_depth;
-	if (hsize * sizeof(u64) != dip->i_disksize) {
+	if (hsize * sizeof(u64) != i_size_read(&dip->i_inode)) {
 		gfs2_consist_inode(dip);
 		return -EIO;
 	}
diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h
index 4f91944..a98f644 100644
--- a/fs/gfs2/dir.h
+++ b/fs/gfs2/dir.h
@@ -17,23 +17,24 @@
 struct gfs2_inode;
 struct gfs2_inum;
 
-struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *filename);
-int gfs2_dir_check(struct inode *dir, const struct qstr *filename,
-		   const struct gfs2_inode *ip);
-int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
-		 const struct gfs2_inode *ip, unsigned int type);
-int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *filename);
-int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
-		  filldir_t filldir);
-int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
-		   const struct gfs2_inode *nip, unsigned int new_type);
+extern struct inode *gfs2_dir_search(struct inode *dir,
+				     const struct qstr *filename);
+extern int gfs2_dir_check(struct inode *dir, const struct qstr *filename,
+			  const struct gfs2_inode *ip);
+extern int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
+			const struct gfs2_inode *ip, unsigned int type);
+extern int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *filename);
+extern int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
+			 filldir_t filldir);
+extern int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
+			  const struct gfs2_inode *nip, unsigned int new_type);
 
-int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
+extern int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
 
-int gfs2_diradd_alloc_required(struct inode *dir,
-			       const struct qstr *filename);
-int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
-			    struct buffer_head **bhp);
+extern int gfs2_diradd_alloc_required(struct inode *dir,
+				      const struct qstr *filename);
+extern int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
+				   struct buffer_head **bhp);
 
 static inline u32 gfs2_disk_hash(const char *data, int len)
 {
@@ -61,4 +62,7 @@
 	memcpy(dent + 1, name->name, name->len);
 }
 
+extern struct qstr gfs2_qdot;
+extern struct qstr gfs2_qdotdot;
+
 #endif /* __DIR_DOT_H__ */
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index dfe237a..06d5827 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -126,16 +126,9 @@
 
 static struct dentry *gfs2_get_parent(struct dentry *child)
 {
-	struct qstr dotdot;
 	struct dentry *dentry;
 
-	/*
-	 * XXX(hch): it would be a good idea to keep this around as a
-	 *	     static variable.
-	 */
-	gfs2_str2qstr(&dotdot, "..");
-
-	dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &dotdot, 1));
+	dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &gfs2_qdotdot, 1));
 	if (!IS_ERR(dentry))
 		dentry->d_op = &gfs2_dops;
 	return dentry;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4edd662..aa99647 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -382,8 +382,10 @@
 	rblocks = RES_DINODE + ind_blocks;
 	if (gfs2_is_jdata(ip))
 		rblocks += data_blocks ? data_blocks : 1;
-	if (ind_blocks || data_blocks)
+	if (ind_blocks || data_blocks) {
 		rblocks += RES_STATFS + RES_QUOTA;
+		rblocks += gfs2_rg_blocks(al);
+	}
 	ret = gfs2_trans_begin(sdp, rblocks, 0);
 	if (ret)
 		goto out_trans_fail;
@@ -491,7 +493,7 @@
 			goto fail;
 
 		if (!(file->f_flags & O_LARGEFILE) &&
-		    ip->i_disksize > MAX_NON_LFS) {
+		    i_size_read(inode) > MAX_NON_LFS) {
 			error = -EOVERFLOW;
 			goto fail_gunlock;
 		}
@@ -620,6 +622,8 @@
  * cluster; until we do, disable leases (by just returning -EINVAL),
  * unless the administrator has requested purely local locking.
  *
+ * Locking: called under lock_flocks
+ *
  * Returns: errno
  */
 
@@ -771,6 +775,7 @@
 	.fsync		= gfs2_fsync,
 	.lock		= gfs2_lock,
 	.flock		= gfs2_flock,
+	.llseek		= default_llseek,
 };
 
 #endif /* CONFIG_GFS2_FS_LOCKING_DLM */
@@ -797,5 +802,6 @@
 	.open		= gfs2_open,
 	.release	= gfs2_close,
 	.fsync		= gfs2_fsync,
+	.llseek		= default_llseek,
 };
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9adf8f9..8777885 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -441,6 +441,8 @@
 		else
 			gfs2_glock_put_nolock(gl);
 	}
+	if (held1 && held2 && list_empty(&gl->gl_holders))
+		clear_bit(GLF_QUEUED, &gl->gl_flags);
 
 	gl->gl_state = new_state;
 	gl->gl_tchange = jiffies;
@@ -1012,6 +1014,7 @@
 		if (unlikely((gh->gh_flags & LM_FLAG_PRIORITY) && !insert_pt))
 			insert_pt = &gh2->gh_list;
 	}
+	set_bit(GLF_QUEUED, &gl->gl_flags);
 	if (likely(insert_pt == NULL)) {
 		list_add_tail(&gh->gh_list, &gl->gl_holders);
 		if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
@@ -1310,10 +1313,12 @@
 
 	gfs2_glock_hold(gl);
 	holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
-	if (time_before(now, holdtime))
-		delay = holdtime - now;
-	if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
-		delay = gl->gl_ops->go_min_hold_time;
+	if (test_bit(GLF_QUEUED, &gl->gl_flags)) {
+		if (time_before(now, holdtime))
+			delay = holdtime - now;
+		if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+			delay = gl->gl_ops->go_min_hold_time;
+	}
 
 	spin_lock(&gl->gl_spin);
 	handle_callback(gl, state, delay);
@@ -1512,7 +1517,7 @@
 	spin_unlock(&lru_lock);
 
 	spin_lock(&gl->gl_spin);
-	if (find_first_holder(gl) == NULL && gl->gl_state != LM_ST_UNLOCKED)
+	if (gl->gl_state != LM_ST_UNLOCKED)
 		handle_callback(gl, LM_ST_UNLOCKED, 0);
 	spin_unlock(&gl->gl_spin);
 	gfs2_glock_hold(gl);
@@ -1660,6 +1665,8 @@
 		*p++ = 'I';
 	if (test_bit(GLF_FROZEN, gflags))
 		*p++ = 'F';
+	if (test_bit(GLF_QUEUED, gflags))
+		*p++ = 'q';
 	*p = 0;
 	return buf;
 }
@@ -1776,10 +1783,12 @@
 	}
 #endif
 
-	glock_workqueue = create_workqueue("glock_workqueue");
+	glock_workqueue = alloc_workqueue("glock_workqueue", WQ_RESCUER |
+					  WQ_HIGHPRI | WQ_FREEZEABLE, 0);
 	if (IS_ERR(glock_workqueue))
 		return PTR_ERR(glock_workqueue);
-	gfs2_delete_workqueue = create_workqueue("delete_workqueue");
+	gfs2_delete_workqueue = alloc_workqueue("delete_workqueue", WQ_RESCUER |
+						WQ_FREEZEABLE, 0);
 	if (IS_ERR(gfs2_delete_workqueue)) {
 		destroy_workqueue(glock_workqueue);
 		return PTR_ERR(gfs2_delete_workqueue);
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 2bda191..db1c26d 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -215,7 +215,7 @@
 void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
 
 /**
- * gfs2_glock_nq_init - intialize a holder and enqueue it on a glock
+ * gfs2_glock_nq_init - initialize a holder and enqueue it on a glock
  * @gl: the glock
  * @state: the state we're requesting
  * @flags: the modifier flags
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 49f97d3..0d149dc 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -262,13 +262,12 @@
 	const struct gfs2_inode *ip = gl->gl_object;
 	if (ip == NULL)
 		return 0;
-	gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu/%llu\n",
+	gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu\n",
 		  (unsigned long long)ip->i_no_formal_ino,
 		  (unsigned long long)ip->i_no_addr,
 		  IF2DT(ip->i_inode.i_mode), ip->i_flags,
 		  (unsigned int)ip->i_diskflags,
-		  (unsigned long long)ip->i_inode.i_size,
-		  (unsigned long long)ip->i_disksize);
+		  (unsigned long long)i_size_read(&ip->i_inode));
 	return 0;
 }
 
@@ -453,7 +452,6 @@
 	[LM_TYPE_META] = &gfs2_meta_glops,
 	[LM_TYPE_INODE] = &gfs2_inode_glops,
 	[LM_TYPE_RGRP] = &gfs2_rgrp_glops,
-	[LM_TYPE_NONDISK] = &gfs2_trans_glops,
 	[LM_TYPE_IOPEN] = &gfs2_iopen_glops,
 	[LM_TYPE_FLOCK] = &gfs2_flock_glops,
 	[LM_TYPE_NONDISK] = &gfs2_nondisk_glops,
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index fdbf4b3..764fbb4 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -196,6 +196,7 @@
 	GLF_REPLY_PENDING		= 9,
 	GLF_INITIAL			= 10,
 	GLF_FROZEN			= 11,
+	GLF_QUEUED			= 12,
 };
 
 struct gfs2_glock {
@@ -267,7 +268,6 @@
 	u64 i_no_formal_ino;
 	u64 i_generation;
 	u64 i_eattr;
-	loff_t i_disksize;
 	unsigned long i_flags;		/* GIF_... */
 	struct gfs2_glock *i_gl; /* Move into i_gh? */
 	struct gfs2_holder i_iopen_gh;
@@ -416,11 +416,8 @@
 	char ar_locktable[GFS2_LOCKNAME_LEN];	/* Name of the Lock Table */
 	char ar_hostdata[GFS2_LOCKNAME_LEN];	/* Host specific data */
 	unsigned int ar_spectator:1;		/* Don't get a journal */
-	unsigned int ar_ignore_local_fs:1;	/* Ignore optimisations */
 	unsigned int ar_localflocks:1;		/* Let the VFS do flock|fcntl */
-	unsigned int ar_localcaching:1;		/* Local caching */
 	unsigned int ar_debug:1;		/* Oops on errors */
-	unsigned int ar_upgrade:1;		/* Upgrade ondisk format */
 	unsigned int ar_posix_acl:1;		/* Enable posix acls */
 	unsigned int ar_quota:2;		/* off/account/on */
 	unsigned int ar_suiddir:1;		/* suiddir support */
@@ -497,7 +494,7 @@
  */
 
 struct lm_lockstruct {
-	unsigned int ls_jid;
+	int ls_jid;
 	unsigned int ls_first;
 	unsigned int ls_first_done;
 	unsigned int ls_nodir;
@@ -572,6 +569,7 @@
 	struct list_head sd_rindex_mru_list;
 	struct gfs2_rgrpd *sd_rindex_forward;
 	unsigned int sd_rgrps;
+	unsigned int sd_max_rg_data;
 
 	/* Journal index stuff */
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 08140f1..06370f8 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -359,8 +359,7 @@
 	 * to do that.
 	 */
 	ip->i_inode.i_nlink = be32_to_cpu(str->di_nlink);
-	ip->i_disksize = be64_to_cpu(str->di_size);
-	i_size_write(&ip->i_inode, ip->i_disksize);
+	i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
 	gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
 	atime.tv_sec = be64_to_cpu(str->di_atime);
 	atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
@@ -1055,7 +1054,7 @@
 	str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
 	str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
 	str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
-	str->di_size = cpu_to_be64(ip->i_disksize);
+	str->di_size = cpu_to_be64(i_size_read(&ip->i_inode));
 	str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
 	str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
 	str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
@@ -1085,8 +1084,8 @@
 	       (unsigned long long)ip->i_no_formal_ino);
 	printk(KERN_INFO "  no_addr = %llu\n",
 	       (unsigned long long)ip->i_no_addr);
-	printk(KERN_INFO "  i_disksize = %llu\n",
-	       (unsigned long long)ip->i_disksize);
+	printk(KERN_INFO "  i_size = %llu\n",
+	       (unsigned long long)i_size_read(&ip->i_inode));
 	printk(KERN_INFO "  blocks = %llu\n",
 	       (unsigned long long)gfs2_get_inode_blocks(&ip->i_inode));
 	printk(KERN_INFO "  i_goal = %llu\n",
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 300ada3..6720d7d 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -19,6 +19,8 @@
 extern int gfs2_internal_read(struct gfs2_inode *ip,
 			      struct file_ra_state *ra_state,
 			      char *buf, loff_t *pos, unsigned size);
+extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+				   unsigned int from, unsigned int to);
 extern void gfs2_set_aops(struct inode *inode);
 
 static inline int gfs2_is_stuffed(const struct gfs2_inode *ip)
@@ -80,6 +82,19 @@
 	dent->de_inum.no_addr = cpu_to_be64(ip->i_no_addr);
 }
 
+static inline int gfs2_check_internal_file_size(struct inode *inode,
+						u64 minsize, u64 maxsize)
+{
+	u64 size = i_size_read(inode);
+	if (size < minsize || size > maxsize)
+		goto err;
+	if (size & ((1 << inode->i_blkbits) - 1))
+		goto err;
+	return 0;
+err:
+	gfs2_consist_inode(GFS2_I(inode));
+	return -EIO;
+}
 
 extern void gfs2_set_iop(struct inode *inode);
 extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 0e0470e..1c09425 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -42,9 +42,9 @@
 		ret |= LM_OUT_CANCELED;
 		goto out;
 	case -EAGAIN: /* Try lock fails */
+	case -EDEADLK: /* Deadlock detected */
 		goto out;
-	case -EINVAL: /* Invalid */
-	case -ENOMEM: /* Out of memory */
+	case -ETIMEDOUT: /* Canceled due to timeout */
 		ret |= LM_OUT_ERROR;
 		goto out;
 	case 0: /* Success */
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index ac750bd..eb01f35 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -592,22 +592,13 @@
 	lh->lh_hash = cpu_to_be32(hash);
 
 	bh->b_end_io = end_buffer_write_sync;
-	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
-		goto skip_barrier;
 	get_bh(bh);
-	submit_bh(WRITE_BARRIER | REQ_META, bh);
-	wait_on_buffer(bh);
-	if (buffer_eopnotsupp(bh)) {
-		clear_buffer_eopnotsupp(bh);
-		set_buffer_uptodate(bh);
-		fs_info(sdp, "barrier sync failed - disabling barriers\n");
-		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
-		lock_buffer(bh);
-skip_barrier:
-		get_bh(bh);
+	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
 		submit_bh(WRITE_SYNC | REQ_META, bh);
-		wait_on_buffer(bh);
-	}
+	else
+		submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
+	wait_on_buffer(bh);
+
 	if (!buffer_uptodate(bh))
 		gfs2_io_error_bh(sdp, bh);
 	brelse(bh);
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index b1e9630..ebef7ab 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -24,6 +24,7 @@
 #include "glock.h"
 #include "quota.h"
 #include "recovery.h"
+#include "dir.h"
 
 static struct shrinker qd_shrinker = {
 	.shrink = gfs2_shrink_qd_memory,
@@ -78,6 +79,9 @@
 {
 	int error;
 
+	gfs2_str2qstr(&gfs2_qdot, ".");
+	gfs2_str2qstr(&gfs2_qdotdot, "..");
+
 	error = gfs2_sys_init();
 	if (error)
 		return error;
@@ -140,7 +144,7 @@
 
 	error = -ENOMEM;
 	gfs_recovery_wq = alloc_workqueue("gfs_recovery",
-					  WQ_NON_REENTRANT | WQ_RESCUER, 0);
+					  WQ_MEM_RECLAIM | WQ_FREEZEABLE, 0);
 	if (!gfs_recovery_wq)
 		goto fail_wq;
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 4d4b1e8..aeafc23 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -38,14 +38,6 @@
 #define DO 0
 #define UNDO 1
 
-static const u32 gfs2_old_fs_formats[] = {
-        0
-};
-
-static const u32 gfs2_old_multihost_formats[] = {
-        0
-};
-
 /**
  * gfs2_tune_init - Fill a gfs2_tune structure with default values
  * @gt: tune
@@ -135,8 +127,6 @@
 
 static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
 {
-	unsigned int x;
-
 	if (sb->sb_magic != GFS2_MAGIC ||
 	    sb->sb_type != GFS2_METATYPE_SB) {
 		if (!silent)
@@ -150,55 +140,9 @@
 	    sb->sb_multihost_format == GFS2_FORMAT_MULTI)
 		return 0;
 
-	if (sb->sb_fs_format != GFS2_FORMAT_FS) {
-		for (x = 0; gfs2_old_fs_formats[x]; x++)
-			if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
-				break;
+	fs_warn(sdp, "Unknown on-disk format, unable to mount\n");
 
-		if (!gfs2_old_fs_formats[x]) {
-			printk(KERN_WARNING
-			       "GFS2: code version (%u, %u) is incompatible "
-			       "with ondisk format (%u, %u)\n",
-			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-			       sb->sb_fs_format, sb->sb_multihost_format);
-			printk(KERN_WARNING
-			       "GFS2: I don't know how to upgrade this FS\n");
-			return -EINVAL;
-		}
-	}
-
-	if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
-		for (x = 0; gfs2_old_multihost_formats[x]; x++)
-			if (gfs2_old_multihost_formats[x] ==
-			    sb->sb_multihost_format)
-				break;
-
-		if (!gfs2_old_multihost_formats[x]) {
-			printk(KERN_WARNING
-			       "GFS2: code version (%u, %u) is incompatible "
-			       "with ondisk format (%u, %u)\n",
-			       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-			       sb->sb_fs_format, sb->sb_multihost_format);
-			printk(KERN_WARNING
-			       "GFS2: I don't know how to upgrade this FS\n");
-			return -EINVAL;
-		}
-	}
-
-	if (!sdp->sd_args.ar_upgrade) {
-		printk(KERN_WARNING
-		       "GFS2: code version (%u, %u) is incompatible "
-		       "with ondisk format (%u, %u)\n",
-		       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-		       sb->sb_fs_format, sb->sb_multihost_format);
-		printk(KERN_INFO
-		       "GFS2: Use the \"upgrade\" mount option to upgrade "
-		       "the FS\n");
-		printk(KERN_INFO "GFS2: See the manual for more details\n");
-		return -EINVAL;
-	}
-
-	return 0;
+	return -EINVAL;
 }
 
 static void end_bio_io_page(struct bio *bio, int error)
@@ -586,7 +530,7 @@
 
 	prev_db = 0;
 
-	for (lb = 0; lb < ip->i_disksize >> sdp->sd_sb.sb_bsize_shift; lb++) {
+	for (lb = 0; lb < i_size_read(jd->jd_inode) >> sdp->sd_sb.sb_bsize_shift; lb++) {
 		bh.b_state = 0;
 		bh.b_blocknr = 0;
 		bh.b_size = 1 << ip->i_inode.i_blkbits;
@@ -1022,7 +966,6 @@
 	if (!strcmp("lock_nolock", proto)) {
 		lm = &nolock_ops;
 		sdp->sd_args.ar_localflocks = 1;
-		sdp->sd_args.ar_localcaching = 1;
 #ifdef CONFIG_GFS2_FS_LOCKING_DLM
 	} else if (!strcmp("lock_dlm", proto)) {
 		lm = &gfs2_dlm_ops;
@@ -1113,8 +1056,6 @@
 
 static int wait_on_journal(struct gfs2_sbd *sdp)
 {
-	if (sdp->sd_args.ar_spectator)
-		return 0;
 	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
 		return 0;
 
@@ -1217,6 +1158,20 @@
 	if (error)
 		goto fail_sb;
 
+	/*
+	 * If user space has failed to join the cluster or some similar
+	 * failure has occurred, then the journal id will contain a
+	 * negative (error) number. This will then be returned to the
+	 * caller (of the mount syscall). We do this even for spectator
+	 * mounts (which just write a jid of 0 to indicate "ok" even though
+	 * the jid is unused in the spectator case)
+	 */
+	if (sdp->sd_lockstruct.ls_jid < 0) {
+		error = sdp->sd_lockstruct.ls_jid;
+		sdp->sd_lockstruct.ls_jid = 0;
+		goto fail_sb;
+	}
+
 	error = init_inodes(sdp, DO);
 	if (error)
 		goto fail_sb;
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 1009be2..0534510 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -18,6 +18,8 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 #include <linux/fiemap.h>
+#include <linux/swap.h>
+#include <linux/falloc.h>
 #include <asm/uaccess.h>
 
 #include "gfs2.h"
@@ -217,7 +219,7 @@
 			goto out_gunlock_q;
 
 		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-					 al->al_rgd->rd_length +
+					 gfs2_rg_blocks(al) +
 					 2 * RES_DINODE + RES_STATFS +
 					 RES_QUOTA, 0);
 		if (error)
@@ -406,7 +408,6 @@
 
 	ip = ghs[1].gh_gl->gl_object;
 
-	ip->i_disksize = size;
 	i_size_write(inode, size);
 
 	error = gfs2_meta_inode_buffer(ip, &dibh);
@@ -461,7 +462,7 @@
 	ip = ghs[1].gh_gl->gl_object;
 
 	ip->i_inode.i_nlink = 2;
-	ip->i_disksize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode);
+	i_size_write(inode, sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode));
 	ip->i_diskflags |= GFS2_DIF_JDATA;
 	ip->i_entries = 2;
 
@@ -470,18 +471,15 @@
 	if (!gfs2_assert_withdraw(sdp, !error)) {
 		struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
 		struct gfs2_dirent *dent = (struct gfs2_dirent *)(di+1);
-		struct qstr str;
 
-		gfs2_str2qstr(&str, ".");
 		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-		gfs2_qstr2dirent(&str, GFS2_DIRENT_SIZE(str.len), dent);
+		gfs2_qstr2dirent(&gfs2_qdot, GFS2_DIRENT_SIZE(gfs2_qdot.len), dent);
 		dent->de_inum = di->di_num; /* already GFS2 endian */
 		dent->de_type = cpu_to_be16(DT_DIR);
 		di->di_entries = cpu_to_be32(1);
 
-		gfs2_str2qstr(&str, "..");
 		dent = (struct gfs2_dirent *)((char*)dent + GFS2_DIRENT_SIZE(1));
-		gfs2_qstr2dirent(&str, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent);
+		gfs2_qstr2dirent(&gfs2_qdotdot, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent);
 
 		gfs2_inum_out(dip, dent);
 		dent->de_type = cpu_to_be16(DT_DIR);
@@ -522,7 +520,6 @@
 static int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
 		       struct gfs2_inode *ip)
 {
-	struct qstr dotname;
 	int error;
 
 	if (ip->i_entries != 2) {
@@ -539,13 +536,11 @@
 	if (error)
 		return error;
 
-	gfs2_str2qstr(&dotname, ".");
-	error = gfs2_dir_del(ip, &dotname);
+	error = gfs2_dir_del(ip, &gfs2_qdot);
 	if (error)
 		return error;
 
-	gfs2_str2qstr(&dotname, "..");
-	error = gfs2_dir_del(ip, &dotname);
+	error = gfs2_dir_del(ip, &gfs2_qdotdot);
 	if (error)
 		return error;
 
@@ -694,11 +689,8 @@
 	struct inode *dir = &to->i_inode;
 	struct super_block *sb = dir->i_sb;
 	struct inode *tmp;
-	struct qstr dotdot;
 	int error = 0;
 
-	gfs2_str2qstr(&dotdot, "..");
-
 	igrab(dir);
 
 	for (;;) {
@@ -711,7 +703,7 @@
 			break;
 		}
 
-		tmp = gfs2_lookupi(dir, &dotdot, 1);
+		tmp = gfs2_lookupi(dir, &gfs2_qdotdot, 1);
 		if (IS_ERR(tmp)) {
 			error = PTR_ERR(tmp);
 			break;
@@ -744,7 +736,7 @@
 	struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
 	struct gfs2_inode *nip = NULL;
 	struct gfs2_sbd *sdp = GFS2_SB(odir);
-	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
+	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, }, ri_gh;
 	struct gfs2_rgrpd *nrgd;
 	unsigned int num_gh;
 	int dir_rename = 0;
@@ -758,6 +750,9 @@
 			return 0;
 	}
 
+	error = gfs2_rindex_hold(sdp, &ri_gh);
+	if (error)
+		return error;
 
 	if (odip != ndip) {
 		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
@@ -887,12 +882,12 @@
 
 		al->al_requested = sdp->sd_max_dirres;
 
-		error = gfs2_inplace_reserve(ndip);
+		error = gfs2_inplace_reserve_ri(ndip);
 		if (error)
 			goto out_gunlock_q;
 
 		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-					 al->al_rgd->rd_length +
+					 gfs2_rg_blocks(al) +
 					 4 * RES_DINODE + 4 * RES_LEAF +
 					 RES_STATFS + RES_QUOTA + 4, 0);
 		if (error)
@@ -920,9 +915,6 @@
 	}
 
 	if (dir_rename) {
-		struct qstr name;
-		gfs2_str2qstr(&name, "..");
-
 		error = gfs2_change_nlink(ndip, +1);
 		if (error)
 			goto out_end_trans;
@@ -930,7 +922,7 @@
 		if (error)
 			goto out_end_trans;
 
-		error = gfs2_dir_mvino(ip, &name, ndip, DT_DIR);
+		error = gfs2_dir_mvino(ip, &gfs2_qdotdot, ndip, DT_DIR);
 		if (error)
 			goto out_end_trans;
 	} else {
@@ -972,6 +964,7 @@
 	if (r_gh.gh_gl)
 		gfs2_glock_dq_uninit(&r_gh);
 out:
+	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
 
@@ -990,7 +983,7 @@
 	struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
 	struct gfs2_holder i_gh;
 	struct buffer_head *dibh;
-	unsigned int x;
+	unsigned int x, size;
 	char *buf;
 	int error;
 
@@ -1002,7 +995,8 @@
 		return NULL;
 	}
 
-	if (!ip->i_disksize) {
+	size = (unsigned int)i_size_read(&ip->i_inode);
+	if (size == 0) {
 		gfs2_consist_inode(ip);
 		buf = ERR_PTR(-EIO);
 		goto out;
@@ -1014,7 +1008,7 @@
 		goto out;
 	}
 
-	x = ip->i_disksize + 1;
+	x = size + 1;
 	buf = kmalloc(x, GFP_NOFS);
 	if (!buf)
 		buf = ERR_PTR(-ENOMEM);
@@ -1071,30 +1065,6 @@
 	return error;
 }
 
-/*
- * XXX(truncate): the truncate_setsize calls should be moved to the end.
- */
-static int setattr_size(struct inode *inode, struct iattr *attr)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	int error;
-
-	if (attr->ia_size != ip->i_disksize) {
-		error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
-		if (error)
-			return error;
-		truncate_setsize(inode, attr->ia_size);
-		gfs2_trans_end(sdp);
-	}
-
-	error = gfs2_truncatei(ip, attr->ia_size);
-	if (error && (inode->i_size != ip->i_disksize))
-		i_size_write(inode, ip->i_disksize);
-
-	return error;
-}
-
 static int setattr_chown(struct inode *inode, struct iattr *attr)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
@@ -1195,7 +1165,7 @@
 		goto out;
 
 	if (attr->ia_valid & ATTR_SIZE)
-		error = setattr_size(inode, attr);
+		error = gfs2_setattr_size(inode, attr->ia_size);
 	else if (attr->ia_valid & (ATTR_UID | ATTR_GID))
 		error = setattr_chown(inode, attr);
 	else if ((attr->ia_valid & ATTR_MODE) && IS_POSIXACL(inode))
@@ -1301,6 +1271,257 @@
 	return ret;
 }
 
+static void empty_write_end(struct page *page, unsigned from,
+			   unsigned to)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+
+	page_zero_new_buffers(page, from, to);
+	flush_dcache_page(page);
+	mark_page_accessed(page);
+
+	if (!gfs2_is_writeback(ip))
+		gfs2_page_add_databufs(ip, page, from, to);
+
+	block_commit_write(page, from, to);
+}
+
+
+static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
+{
+	unsigned start, end, next;
+	struct buffer_head *bh, *head;
+	int error;
+
+	if (!page_has_buffers(page)) {
+		error = block_prepare_write(page, from, to, gfs2_block_map);
+		if (unlikely(error))
+			return error;
+
+		empty_write_end(page, from, to);
+		return 0;
+	}
+
+	bh = head = page_buffers(page);
+	next = end = 0;
+	while (next < from) {
+		next += bh->b_size;
+		bh = bh->b_this_page;
+	}
+	start = next;
+	do {
+		next += bh->b_size;
+		if (buffer_mapped(bh)) {
+			if (end) {
+				error = block_prepare_write(page, start, end,
+							    gfs2_block_map);
+				if (unlikely(error))
+					return error;
+				empty_write_end(page, start, end);
+				end = 0;
+			}
+			start = next;
+		}
+		else
+			end = next;
+		bh = bh->b_this_page;
+	} while (next < to);
+
+	if (end) {
+		error = block_prepare_write(page, start, end, gfs2_block_map);
+		if (unlikely(error))
+			return error;
+		empty_write_end(page, start, end);
+	}
+
+	return 0;
+}
+
+static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
+			   int mode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct buffer_head *dibh;
+	int error;
+	u64 start = offset >> PAGE_CACHE_SHIFT;
+	unsigned int start_offset = offset & ~PAGE_CACHE_MASK;
+	u64 end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+	pgoff_t curr;
+	struct page *page;
+	unsigned int end_offset = (offset + len) & ~PAGE_CACHE_MASK;
+	unsigned int from, to;
+
+	if (!end_offset)
+		end_offset = PAGE_CACHE_SIZE;
+
+	error = gfs2_meta_inode_buffer(ip, &dibh);
+	if (unlikely(error))
+		goto out;
+
+	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
+	if (gfs2_is_stuffed(ip)) {
+		error = gfs2_unstuff_dinode(ip, NULL);
+		if (unlikely(error))
+			goto out;
+	}
+
+	curr = start;
+	offset = start << PAGE_CACHE_SHIFT;
+	from = start_offset;
+	to = PAGE_CACHE_SIZE;
+	while (curr <= end) {
+		page = grab_cache_page_write_begin(inode->i_mapping, curr,
+						   AOP_FLAG_NOFS);
+		if (unlikely(!page)) {
+			error = -ENOMEM;
+			goto out;
+		}
+
+		if (curr == end)
+			to = end_offset;
+		error = write_empty_blocks(page, from, to);
+		if (!error && offset + to > inode->i_size &&
+		    !(mode & FALLOC_FL_KEEP_SIZE)) {
+			i_size_write(inode, offset + to);
+		}
+		unlock_page(page);
+		page_cache_release(page);
+		if (error)
+			goto out;
+		curr++;
+		offset += PAGE_CACHE_SIZE;
+		from = 0;
+	}
+
+	gfs2_dinode_out(ip, dibh->b_data);
+	mark_inode_dirty(inode);
+
+	brelse(dibh);
+
+out:
+	return error;
+}
+
+static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
+			    unsigned int *data_blocks, unsigned int *ind_blocks)
+{
+	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	unsigned int max_blocks = ip->i_alloc->al_rgd->rd_free_clone;
+	unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);
+
+	for (tmp = max_data; tmp > sdp->sd_diptrs;) {
+		tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
+		max_data -= tmp;
+	}
+	/* This calculation isn't the exact reverse of gfs2_write_calc_reserve,
+	   so it might end up with fewer data blocks */
+	if (max_data <= *data_blocks)
+		return;
+	*data_blocks = max_data;
+	*ind_blocks = max_blocks - max_data;
+	*len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift;
+	if (*len > max) {
+		*len = max;
+		gfs2_write_calc_reserv(ip, max, data_blocks, ind_blocks);
+	}
+}
+
+static long gfs2_fallocate(struct inode *inode, int mode, loff_t offset,
+			   loff_t len)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
+	loff_t bytes, max_bytes;
+	struct gfs2_alloc *al;
+	int error;
+	loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
+	next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
+
+	offset = (offset >> sdp->sd_sb.sb_bsize_shift) <<
+		 sdp->sd_sb.sb_bsize_shift;
+
+	len = next - offset;
+	bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
+	if (!bytes)
+		bytes = UINT_MAX;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+	error = gfs2_glock_nq(&ip->i_gh);
+	if (unlikely(error))
+		goto out_uninit;
+
+	if (!gfs2_write_alloc_required(ip, offset, len))
+		goto out_unlock;
+
+	while (len > 0) {
+		if (len < bytes)
+			bytes = len;
+		al = gfs2_alloc_get(ip);
+		if (!al) {
+			error = -ENOMEM;
+			goto out_unlock;
+		}
+
+		error = gfs2_quota_lock_check(ip);
+		if (error)
+			goto out_alloc_put;
+
+retry:
+		gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
+
+		al->al_requested = data_blocks + ind_blocks;
+		error = gfs2_inplace_reserve(ip);
+		if (error) {
+			if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
+				bytes >>= 1;
+				goto retry;
+			}
+			goto out_qunlock;
+		}
+		max_bytes = bytes;
+		calc_max_reserv(ip, len, &max_bytes, &data_blocks, &ind_blocks);
+		al->al_requested = data_blocks + ind_blocks;
+
+		rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
+			  RES_RG_HDR + gfs2_rg_blocks(al);
+		if (gfs2_is_jdata(ip))
+			rblocks += data_blocks ? data_blocks : 1;
+
+		error = gfs2_trans_begin(sdp, rblocks,
+					 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
+		if (error)
+			goto out_trans_fail;
+
+		error = fallocate_chunk(inode, offset, max_bytes, mode);
+		gfs2_trans_end(sdp);
+
+		if (error)
+			goto out_trans_fail;
+
+		len -= max_bytes;
+		offset += max_bytes;
+		gfs2_inplace_release(ip);
+		gfs2_quota_unlock(ip);
+		gfs2_alloc_put(ip);
+	}
+	goto out_unlock;
+
+out_trans_fail:
+	gfs2_inplace_release(ip);
+out_qunlock:
+	gfs2_quota_unlock(ip);
+out_alloc_put:
+	gfs2_alloc_put(ip);
+out_unlock:
+	gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_gh);
+	return error;
+}
+
+
 static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		       u64 start, u64 len)
 {
@@ -1351,6 +1572,7 @@
 	.getxattr = gfs2_getxattr,
 	.listxattr = gfs2_listxattr,
 	.removexattr = gfs2_removexattr,
+	.fallocate = gfs2_fallocate,
 	.fiemap = gfs2_fiemap,
 };
 
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 1bc6b56..58a9b99 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -735,10 +735,8 @@
 		goto out;
 
 	size = loc + sizeof(struct gfs2_quota);
-	if (size > inode->i_size) {
-		ip->i_disksize = size;
+	if (size > inode->i_size)
 		i_size_write(inode, size);
-	}
 	inode->i_mtime = inode->i_atime = CURRENT_TIME;
 	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
 	gfs2_dinode_out(ip, dibh->b_data);
@@ -817,7 +815,7 @@
 		goto out_alloc;
 
 	if (nalloc)
-		blocks += al->al_rgd->rd_length + nalloc * ind_blocks + RES_STATFS;
+		blocks += gfs2_rg_blocks(al) + nalloc * ind_blocks + RES_STATFS;
 
 	error = gfs2_trans_begin(sdp, blocks, 0);
 	if (error)
@@ -1190,18 +1188,17 @@
 int gfs2_quota_init(struct gfs2_sbd *sdp)
 {
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
-	unsigned int blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
+	u64 size = i_size_read(sdp->sd_qc_inode);
+	unsigned int blocks = size >> sdp->sd_sb.sb_bsize_shift;
 	unsigned int x, slot = 0;
 	unsigned int found = 0;
 	u64 dblock;
 	u32 extlen = 0;
 	int error;
 
-	if (!ip->i_disksize || ip->i_disksize > (64 << 20) ||
-	    ip->i_disksize & (sdp->sd_sb.sb_bsize - 1)) {
-		gfs2_consist_inode(ip);
+	if (gfs2_check_internal_file_size(sdp->sd_qc_inode, 1, 64 << 20))
 		return -EIO;
-	}
+
 	sdp->sd_quota_slots = blocks * sdp->sd_qc_per_block;
 	sdp->sd_quota_chunks = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * PAGE_SIZE);
 
@@ -1589,6 +1586,7 @@
 		error = gfs2_inplace_reserve(ip);
 		if (error)
 			goto out_alloc;
+		blocks += gfs2_rg_blocks(al);
 	}
 
 	error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 1, 0);
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index f7f89a9..f2a02ed 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -455,11 +455,13 @@
 	int ro = 0;
 	unsigned int pass;
 	int error;
+	int jlocked = 0;
 
-	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) {
+	if (sdp->sd_args.ar_spectator ||
+	    (jd->jd_jid != sdp->sd_lockstruct.ls_jid)) {
 		fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n",
 			jd->jd_jid);
-
+		jlocked = 1;
 		/* Acquire the journal lock so we can do recovery */
 
 		error = gfs2_glock_nq_num(sdp, jd->jd_jid, &gfs2_journal_glops,
@@ -554,13 +556,12 @@
 			jd->jd_jid, t);
 	}
 
-	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid)
-		gfs2_glock_dq_uninit(&ji_gh);
-
 	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_SUCCESS);
 
-	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid)
+	if (jlocked) {
+		gfs2_glock_dq_uninit(&ji_gh);
 		gfs2_glock_dq_uninit(&j_gh);
+	}
 
 	fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
 	goto done;
@@ -568,7 +569,7 @@
 fail_gunlock_tr:
 	gfs2_glock_dq_uninit(&t_gh);
 fail_gunlock_ji:
-	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) {
+	if (jlocked) {
 		gfs2_glock_dq_uninit(&ji_gh);
 fail_gunlock_j:
 		gfs2_glock_dq_uninit(&j_gh);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 171a744..bef3ab6 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -500,7 +500,7 @@
 	for (rgrps = 0;; rgrps++) {
 		loff_t pos = rgrps * sizeof(struct gfs2_rindex);
 
-		if (pos + sizeof(struct gfs2_rindex) >= ip->i_disksize)
+		if (pos + sizeof(struct gfs2_rindex) >= i_size_read(inode))
 			break;
 		error = gfs2_internal_read(ip, &ra_state, buf, &pos,
 					   sizeof(struct gfs2_rindex));
@@ -588,7 +588,9 @@
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct inode *inode = &ip->i_inode;
 	struct file_ra_state ra_state;
-	u64 rgrp_count = ip->i_disksize;
+	u64 rgrp_count = i_size_read(inode);
+	struct gfs2_rgrpd *rgd;
+	unsigned int max_data = 0;
 	int error;
 
 	do_div(rgrp_count, sizeof(struct gfs2_rindex));
@@ -603,6 +605,10 @@
 		}
 	}
 
+	list_for_each_entry(rgd, &sdp->sd_rindex_list, rd_list)
+		if (rgd->rd_data > max_data)
+			max_data = rgd->rd_data;
+	sdp->sd_max_rg_data = max_data;
 	sdp->sd_rindex_uptodate = 1;
 	return 0;
 }
@@ -622,13 +628,15 @@
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct inode *inode = &ip->i_inode;
 	struct file_ra_state ra_state;
+	struct gfs2_rgrpd *rgd;
+	unsigned int max_data = 0;
 	int error;
 
 	file_ra_state_init(&ra_state, inode->i_mapping);
 	for (sdp->sd_rgrps = 0;; sdp->sd_rgrps++) {
 		/* Ignore partials */
 		if ((sdp->sd_rgrps + 1) * sizeof(struct gfs2_rindex) >
-		    ip->i_disksize)
+		    i_size_read(inode))
 			break;
 		error = read_rindex_entry(ip, &ra_state);
 		if (error) {
@@ -636,6 +644,10 @@
 			return error;
 		}
 	}
+	list_for_each_entry(rgd, &sdp->sd_rindex_list, rd_list)
+		if (rgd->rd_data > max_data)
+			max_data = rgd->rd_data;
+	sdp->sd_max_rg_data = max_data;
 
 	sdp->sd_rindex_uptodate = 1;
 	return 0;
@@ -854,8 +866,7 @@
 				if ((start + nr_sects) != blk) {
 					rv = blkdev_issue_discard(bdev, start,
 							    nr_sects, GFP_NOFS,
-							    BLKDEV_IFL_WAIT |
-							    BLKDEV_IFL_BARRIER);
+							    0);
 					if (rv)
 						goto fail;
 					nr_sects = 0;
@@ -869,8 +880,7 @@
 		}
 	}
 	if (nr_sects) {
-		rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS,
-					 BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+		rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, 0);
 		if (rv)
 			goto fail;
 	}
@@ -1188,7 +1198,8 @@
  * Returns: errno
  */
 
-int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line)
+int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
+			   char *file, unsigned int line)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_alloc *al = ip->i_alloc;
@@ -1199,12 +1210,15 @@
 		return -EINVAL;
 
 try_again:
-	/* We need to hold the rindex unless the inode we're using is
-	   the rindex itself, in which case it's already held. */
-	if (ip != GFS2_I(sdp->sd_rindex))
-		error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
-	else if (!sdp->sd_rgrps) /* We may not have the rindex read in, so: */
-		error = gfs2_ri_update_special(ip);
+	if (hold_rindex) {
+		/* We need to hold the rindex unless the inode we're using is
+		   the rindex itself, in which case it's already held. */
+		if (ip != GFS2_I(sdp->sd_rindex))
+			error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
+		else if (!sdp->sd_rgrps) /* We may not have the rindex read
+					    in, so: */
+			error = gfs2_ri_update_special(ip);
+	}
 
 	if (error)
 		return error;
@@ -1215,7 +1229,7 @@
 	   try to free it, and try the allocation again. */
 	error = get_local_rgrp(ip, &unlinked, &last_unlinked);
 	if (error) {
-		if (ip != GFS2_I(sdp->sd_rindex))
+		if (hold_rindex && ip != GFS2_I(sdp->sd_rindex))
 			gfs2_glock_dq_uninit(&al->al_ri_gh);
 		if (error != -EAGAIN)
 			return error;
@@ -1257,7 +1271,7 @@
 	al->al_rgd = NULL;
 	if (al->al_rgd_gh.gh_gl)
 		gfs2_glock_dq_uninit(&al->al_rgd_gh);
-	if (ip != GFS2_I(sdp->sd_rindex))
+	if (ip != GFS2_I(sdp->sd_rindex) && al->al_ri_gh.gh_gl)
 		gfs2_glock_dq_uninit(&al->al_ri_gh);
 }
 
@@ -1496,11 +1510,19 @@
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct buffer_head *dibh;
 	struct gfs2_alloc *al = ip->i_alloc;
-	struct gfs2_rgrpd *rgd = al->al_rgd;
+	struct gfs2_rgrpd *rgd;
 	u32 goal, blk;
 	u64 block;
 	int error;
 
+	/* Only happens if there is a bug in gfs2, return something distinctive
+	 * to ensure that it is noticed.
+	 */
+	if (al == NULL)
+		return -ECANCELED;
+
+	rgd = al->al_rgd;
+
 	if (rgrp_contains_block(rgd, ip->i_goal))
 		goal = ip->i_goal - rgd->rd_data0;
 	else
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index f07119d..0e35c04 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -39,10 +39,12 @@
 	ip->i_alloc = NULL;
 }
 
-extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file,
-				  unsigned int line);
+extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
+				  char *file, unsigned int line);
 #define gfs2_inplace_reserve(ip) \
-gfs2_inplace_reserve_i((ip), __FILE__, __LINE__)
+	gfs2_inplace_reserve_i((ip), 1, __FILE__, __LINE__)
+#define gfs2_inplace_reserve_ri(ip) \
+	gfs2_inplace_reserve_i((ip), 0, __FILE__, __LINE__)
 
 extern void gfs2_inplace_release(struct gfs2_inode *ip);
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 77cb9f8..047d117 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -85,6 +85,7 @@
 	{Opt_locktable, "locktable=%s"},
 	{Opt_hostdata, "hostdata=%s"},
 	{Opt_spectator, "spectator"},
+	{Opt_spectator, "norecovery"},
 	{Opt_ignore_local_fs, "ignore_local_fs"},
 	{Opt_localflocks, "localflocks"},
 	{Opt_localcaching, "localcaching"},
@@ -159,13 +160,13 @@
 			args->ar_spectator = 1;
 			break;
 		case Opt_ignore_local_fs:
-			args->ar_ignore_local_fs = 1;
+			/* Retained for backwards compat only */
 			break;
 		case Opt_localflocks:
 			args->ar_localflocks = 1;
 			break;
 		case Opt_localcaching:
-			args->ar_localcaching = 1;
+			/* Retained for backwards compat only */
 			break;
 		case Opt_debug:
 			if (args->ar_errors == GFS2_ERRORS_PANIC) {
@@ -179,7 +180,7 @@
 			args->ar_debug = 0;
 			break;
 		case Opt_upgrade:
-			args->ar_upgrade = 1;
+			/* Retained for backwards compat only */
 			break;
 		case Opt_acl:
 			args->ar_posix_acl = 1;
@@ -342,15 +343,14 @@
 {
 	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
 	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+	u64 size = i_size_read(jd->jd_inode);
 
-	if (ip->i_disksize < (8 << 20) || ip->i_disksize > (1 << 30) ||
-	    (ip->i_disksize & (sdp->sd_sb.sb_bsize - 1))) {
-		gfs2_consist_inode(ip);
+	if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, 1 << 30))
 		return -EIO;
-	}
-	jd->jd_blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
 
-	if (gfs2_write_alloc_required(ip, 0, ip->i_disksize)) {
+	jd->jd_blocks = size >> sdp->sd_sb.sb_bsize_shift;
+
+	if (gfs2_write_alloc_required(ip, 0, size)) {
 		gfs2_consist_inode(ip);
 		return -EIO;
 	}
@@ -1129,9 +1129,7 @@
 
 	/* Some flags must not be changed */
 	if (args_neq(&args, &sdp->sd_args, spectator) ||
-	    args_neq(&args, &sdp->sd_args, ignore_local_fs) ||
 	    args_neq(&args, &sdp->sd_args, localflocks) ||
-	    args_neq(&args, &sdp->sd_args, localcaching) ||
 	    args_neq(&args, &sdp->sd_args, meta))
 		return -EINVAL;
 
@@ -1234,16 +1232,10 @@
 		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
 	if (args->ar_spectator)
 		seq_printf(s, ",spectator");
-	if (args->ar_ignore_local_fs)
-		seq_printf(s, ",ignore_local_fs");
 	if (args->ar_localflocks)
 		seq_printf(s, ",localflocks");
-	if (args->ar_localcaching)
-		seq_printf(s, ",localcaching");
 	if (args->ar_debug)
 		seq_printf(s, ",debug");
-	if (args->ar_upgrade)
-		seq_printf(s, ",upgrade");
 	if (args->ar_posix_acl)
 		seq_printf(s, ",acl");
 	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index ccacffd..748ccb5 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -230,7 +230,10 @@
 
 	if (gltype > LM_TYPE_JOURNAL)
 		return -EINVAL;
-	glops = gfs2_glops_list[gltype];
+	if (gltype == LM_TYPE_NONDISK && glnum == GFS2_TRANS_LOCK)
+		glops = &gfs2_trans_glops;
+	else
+		glops = gfs2_glops_list[gltype];
 	if (glops == NULL)
 		return -EINVAL;
 	if (!test_and_set_bit(SDF_DEMOTE, &sdp->sd_flags))
@@ -399,31 +402,32 @@
 
 static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
 {
-	return sprintf(buf, "%u\n", sdp->sd_lockstruct.ls_jid);
+	return sprintf(buf, "%d\n", sdp->sd_lockstruct.ls_jid);
 }
 
 static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 {
-        unsigned jid;
+        int jid;
 	int rv;
 
-	rv = sscanf(buf, "%u", &jid);
+	rv = sscanf(buf, "%d", &jid);
 	if (rv != 1)
 		return -EINVAL;
 
 	spin_lock(&sdp->sd_jindex_spin);
 	rv = -EINVAL;
-	if (sdp->sd_args.ar_spectator)
-		goto out;
 	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
 		goto out;
 	rv = -EBUSY;
-	if (test_and_clear_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
+	if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
 		goto out;
+	rv = 0;
+	if (sdp->sd_args.ar_spectator && jid > 0)
+		rv = jid = -EINVAL;
 	sdp->sd_lockstruct.ls_jid = jid;
+	clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
 	smp_mb__after_clear_bit();
 	wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
-	rv = 0;
 out:
 	spin_unlock(&sdp->sd_jindex_spin);
 	return rv ? rv : len;
@@ -617,7 +621,7 @@
 	add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
 	add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
 	if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags))
-		add_uevent_var(env, "JOURNALID=%u", sdp->sd_lockstruct.ls_jid);
+		add_uevent_var(env, "JOURNALID=%d", sdp->sd_lockstruct.ls_jid);
 	if (gfs2_uuid_valid(uuid))
 		add_uevent_var(env, "UUID=%pUB", uuid);
 	return 0;
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index 148d55c..cedb0bb 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -39,7 +39,8 @@
 	{(1UL << GLF_INVALIDATE_IN_PROGRESS),	"i" },		\
 	{(1UL << GLF_REPLY_PENDING),		"r" },		\
 	{(1UL << GLF_INITIAL),			"I" },		\
-	{(1UL << GLF_FROZEN),			"F" })
+	{(1UL << GLF_FROZEN),			"F" },		\
+	{(1UL << GLF_QUEUED),			"q" })
 
 #ifndef NUMPTY
 #define NUMPTY
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index edf9d4b..fb56b78 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -20,11 +20,20 @@
 #define RES_JDATA	1
 #define RES_DATA	1
 #define RES_LEAF	1
+#define RES_RG_HDR	1
 #define RES_RG_BIT	2
 #define RES_EATTR	1
 #define RES_STATFS	1
 #define RES_QUOTA	2
 
+/* reserve either the number of blocks to be allocated plus the rg header
+ * block, or all of the blocks in the rg, whichever is smaller */
+static inline unsigned int gfs2_rg_blocks(const struct gfs2_alloc *al)
+{
+	return (al->al_requested < al->al_rgd->rd_length)?
+	       al->al_requested + 1 : al->al_rgd->rd_length;
+}
+
 int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 		     unsigned int revokes);
 
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 776af6e..30b58f07 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -734,7 +734,7 @@
 		goto out_gunlock_q;
 
 	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode),
-				 blks + al->al_rgd->rd_length +
+				 blks + gfs2_rg_blocks(al) +
 				 RES_DINODE + RES_STATFS + RES_QUOTA, 0);
 	if (error)
 		goto out_ipres;
diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c
index 4129cdb..571abe9 100644
--- a/fs/hfs/bfind.c
+++ b/fs/hfs/bfind.c
@@ -23,7 +23,7 @@
 	fd->search_key = ptr;
 	fd->key = ptr + tree->max_key_len + 2;
 	dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0));
-	down(&tree->tree_lock);
+	mutex_lock(&tree->tree_lock);
 	return 0;
 }
 
@@ -32,7 +32,7 @@
 	hfs_bnode_put(fd->bnode);
 	kfree(fd->search_key);
 	dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0));
-	up(&fd->tree->tree_lock);
+	mutex_unlock(&fd->tree->tree_lock);
 	fd->tree = NULL;
 }
 
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 38a0a99..3ebc437 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -27,7 +27,7 @@
 	if (!tree)
 		return NULL;
 
-	init_MUTEX(&tree->tree_lock);
+	mutex_init(&tree->tree_lock);
 	spin_lock_init(&tree->hash_lock);
 	/* Set the correct compare function */
 	tree->sb = sb;
diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h
index cc51905..2a1d712 100644
--- a/fs/hfs/btree.h
+++ b/fs/hfs/btree.h
@@ -33,7 +33,7 @@
 	unsigned int depth;
 
 	//unsigned int map1_size, map_size;
-	struct semaphore tree_lock;
+	struct mutex tree_lock;
 
 	unsigned int pages_per_bnode;
 	spinlock_t hash_lock;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 34235d4..3325416 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -20,7 +20,6 @@
 #include <linux/parser.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 
 #include "hfs_fs.h"
@@ -79,15 +78,11 @@
  */
 static void hfs_put_super(struct super_block *sb)
 {
-	lock_kernel();
-
 	if (sb->s_dirt)
 		hfs_write_super(sb);
 	hfs_mdb_close(sb);
 	/* release the MDB's resources */
 	hfs_mdb_put(sb);
-
-	unlock_kernel();
 }
 
 /*
@@ -385,6 +380,7 @@
 	sbi = kzalloc(sizeof(struct hfs_sb_info), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
+
 	sb->s_fs_info = sbi;
 	INIT_HLIST_HEAD(&sbi->rsrc_inodes);
 
diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
index 5007a41..d182438 100644
--- a/fs/hfsplus/bfind.c
+++ b/fs/hfsplus/bfind.c
@@ -23,7 +23,7 @@
 	fd->search_key = ptr;
 	fd->key = ptr + tree->max_key_len + 2;
 	dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0));
-	down(&tree->tree_lock);
+	mutex_lock(&tree->tree_lock);
 	return 0;
 }
 
@@ -32,7 +32,7 @@
 	hfs_bnode_put(fd->bnode);
 	kfree(fd->search_key);
 	dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0));
-	up(&fd->tree->tree_lock);
+	mutex_unlock(&fd->tree->tree_lock);
 	fd->tree = NULL;
 }
 
@@ -52,6 +52,10 @@
 		rec = (e + b) / 2;
 		len = hfs_brec_lenoff(bnode, rec, &off);
 		keylen = hfs_brec_keylen(bnode, rec);
+		if (keylen == 0) {
+			res = -EINVAL;
+			goto fail;
+		}
 		hfs_bnode_read(bnode, fd->key, off, keylen);
 		cmpval = bnode->tree->keycmp(fd->key, fd->search_key);
 		if (!cmpval) {
@@ -67,6 +71,10 @@
 	if (rec != e && e >= 0) {
 		len = hfs_brec_lenoff(bnode, e, &off);
 		keylen = hfs_brec_keylen(bnode, e);
+		if (keylen == 0) {
+			res = -EINVAL;
+			goto fail;
+		}
 		hfs_bnode_read(bnode, fd->key, off, keylen);
 	}
 done:
@@ -75,6 +83,7 @@
 	fd->keylength = keylen;
 	fd->entryoffset = off + keylen;
 	fd->entrylength = len - keylen;
+fail:
 	return res;
 }
 
@@ -198,6 +207,10 @@
 
 	len = hfs_brec_lenoff(bnode, fd->record, &off);
 	keylen = hfs_brec_keylen(bnode, fd->record);
+	if (keylen == 0) {
+		res = -EINVAL;
+		goto out;
+	}
 	fd->keyoffset = off;
 	fd->keylength = keylen;
 	fd->entryoffset = off + keylen;
diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c
index ea30afc..ad57f59 100644
--- a/fs/hfsplus/bitmap.c
+++ b/fs/hfsplus/bitmap.c
@@ -17,6 +17,7 @@
 
 int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *max)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct page *page;
 	struct address_space *mapping;
 	__be32 *pptr, *curr, *end;
@@ -29,8 +30,8 @@
 		return size;
 
 	dprint(DBG_BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len);
-	mutex_lock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
-	mapping = HFSPLUS_SB(sb).alloc_file->i_mapping;
+	mutex_lock(&sbi->alloc_mutex);
+	mapping = sbi->alloc_file->i_mapping;
 	page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL);
 	if (IS_ERR(page)) {
 		start = size;
@@ -150,16 +151,17 @@
 	set_page_dirty(page);
 	kunmap(page);
 	*max = offset + (curr - pptr) * 32 + i - start;
-	HFSPLUS_SB(sb).free_blocks -= *max;
+	sbi->free_blocks -= *max;
 	sb->s_dirt = 1;
 	dprint(DBG_BITMAP, "-> %u,%u\n", start, *max);
 out:
-	mutex_unlock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
+	mutex_unlock(&sbi->alloc_mutex);
 	return start;
 }
 
 int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct page *page;
 	struct address_space *mapping;
 	__be32 *pptr, *curr, *end;
@@ -172,11 +174,11 @@
 
 	dprint(DBG_BITMAP, "block_free: %u,%u\n", offset, count);
 	/* are all of the bits in range? */
-	if ((offset + count) > HFSPLUS_SB(sb).total_blocks)
+	if ((offset + count) > sbi->total_blocks)
 		return -2;
 
-	mutex_lock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
-	mapping = HFSPLUS_SB(sb).alloc_file->i_mapping;
+	mutex_lock(&sbi->alloc_mutex);
+	mapping = sbi->alloc_file->i_mapping;
 	pnr = offset / PAGE_CACHE_BITS;
 	page = read_mapping_page(mapping, pnr, NULL);
 	pptr = kmap(page);
@@ -224,9 +226,9 @@
 out:
 	set_page_dirty(page);
 	kunmap(page);
-	HFSPLUS_SB(sb).free_blocks += len;
+	sbi->free_blocks += len;
 	sb->s_dirt = 1;
-	mutex_unlock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
+	mutex_unlock(&sbi->alloc_mutex);
 
 	return 0;
 }
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index c88e5d7..2f39d05 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -42,10 +42,13 @@
 		recoff = hfs_bnode_read_u16(node, node->tree->node_size - (rec + 1) * 2);
 		if (!recoff)
 			return 0;
-		if (node->tree->attributes & HFS_TREE_BIGKEYS)
-			retval = hfs_bnode_read_u16(node, recoff) + 2;
-		else
-			retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1;
+
+		retval = hfs_bnode_read_u16(node, recoff) + 2;
+		if (retval > node->tree->max_key_len + 2) {
+			printk(KERN_ERR "hfs: keylen %d too large\n",
+				retval);
+			retval = 0;
+		}
 	}
 	return retval;
 }
@@ -216,7 +219,7 @@
 static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
 {
 	struct hfs_btree *tree;
-	struct hfs_bnode *node, *new_node;
+	struct hfs_bnode *node, *new_node, *next_node;
 	struct hfs_bnode_desc node_desc;
 	int num_recs, new_rec_off, new_off, old_rec_off;
 	int data_start, data_end, size;
@@ -235,6 +238,17 @@
 	new_node->type = node->type;
 	new_node->height = node->height;
 
+	if (node->next)
+		next_node = hfs_bnode_find(tree, node->next);
+	else
+		next_node = NULL;
+
+	if (IS_ERR(next_node)) {
+		hfs_bnode_put(node);
+		hfs_bnode_put(new_node);
+		return next_node;
+	}
+
 	size = tree->node_size / 2 - node->num_recs * 2 - 14;
 	old_rec_off = tree->node_size - 4;
 	num_recs = 1;
@@ -248,6 +262,8 @@
 		/* panic? */
 		hfs_bnode_put(node);
 		hfs_bnode_put(new_node);
+		if (next_node)
+			hfs_bnode_put(next_node);
 		return ERR_PTR(-ENOSPC);
 	}
 
@@ -302,8 +318,7 @@
 	hfs_bnode_write(node, &node_desc, 0, sizeof(node_desc));
 
 	/* update next bnode header */
-	if (new_node->next) {
-		struct hfs_bnode *next_node = hfs_bnode_find(tree, new_node->next);
+	if (next_node) {
 		next_node->prev = new_node->this;
 		hfs_bnode_read(next_node, &node_desc, 0, sizeof(node_desc));
 		node_desc.prev = cpu_to_be32(next_node->prev);
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index e49fcee..22e4d4e 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -30,7 +30,7 @@
 	if (!tree)
 		return NULL;
 
-	init_MUTEX(&tree->tree_lock);
+	mutex_init(&tree->tree_lock);
 	spin_lock_init(&tree->hash_lock);
 	tree->sb = sb;
 	tree->cnid = id;
@@ -39,10 +39,16 @@
 		goto free_tree;
 	tree->inode = inode;
 
+	if (!HFSPLUS_I(tree->inode)->first_blocks) {
+		printk(KERN_ERR
+		       "hfs: invalid btree extent records (0 size).\n");
+		goto free_inode;
+	}
+
 	mapping = tree->inode->i_mapping;
 	page = read_mapping_page(mapping, 0, NULL);
 	if (IS_ERR(page))
-		goto free_tree;
+		goto free_inode;
 
 	/* Load the header */
 	head = (struct hfs_btree_header_rec *)(kmap(page) + sizeof(struct hfs_bnode_desc));
@@ -57,27 +63,56 @@
 	tree->max_key_len = be16_to_cpu(head->max_key_len);
 	tree->depth = be16_to_cpu(head->depth);
 
-	/* Set the correct compare function */
-	if (id == HFSPLUS_EXT_CNID) {
+	/* Verify the tree and set the correct compare function */
+	switch (id) {
+	case HFSPLUS_EXT_CNID:
+		if (tree->max_key_len != HFSPLUS_EXT_KEYLEN - sizeof(u16)) {
+			printk(KERN_ERR "hfs: invalid extent max_key_len %d\n",
+				tree->max_key_len);
+			goto fail_page;
+		}
+		if (tree->attributes & HFS_TREE_VARIDXKEYS) {
+			printk(KERN_ERR "hfs: invalid extent btree flag\n");
+			goto fail_page;
+		}
+
 		tree->keycmp = hfsplus_ext_cmp_key;
-	} else if (id == HFSPLUS_CAT_CNID) {
-		if ((HFSPLUS_SB(sb).flags & HFSPLUS_SB_HFSX) &&
+		break;
+	case HFSPLUS_CAT_CNID:
+		if (tree->max_key_len != HFSPLUS_CAT_KEYLEN - sizeof(u16)) {
+			printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n",
+				tree->max_key_len);
+			goto fail_page;
+		}
+		if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) {
+			printk(KERN_ERR "hfs: invalid catalog btree flag\n");
+			goto fail_page;
+		}
+
+		if (test_bit(HFSPLUS_SB_HFSX, &HFSPLUS_SB(sb)->flags) &&
 		    (head->key_type == HFSPLUS_KEY_BINARY))
 			tree->keycmp = hfsplus_cat_bin_cmp_key;
 		else {
 			tree->keycmp = hfsplus_cat_case_cmp_key;
-			HFSPLUS_SB(sb).flags |= HFSPLUS_SB_CASEFOLD;
+			set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
 		}
-	} else {
+		break;
+	default:
 		printk(KERN_ERR "hfs: unknown B*Tree requested\n");
 		goto fail_page;
 	}
 
+	if (!(tree->attributes & HFS_TREE_BIGKEYS)) {
+		printk(KERN_ERR "hfs: invalid btree flag\n");
+		goto fail_page;
+	}
+
 	size = tree->node_size;
 	if (!is_power_of_2(size))
 		goto fail_page;
 	if (!tree->node_count)
 		goto fail_page;
+
 	tree->node_size_shift = ffs(size) - 1;
 
 	tree->pages_per_bnode = (tree->node_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
@@ -87,10 +122,11 @@
 	return tree;
 
  fail_page:
-	tree->inode->i_mapping->a_ops = &hfsplus_aops;
 	page_cache_release(page);
- free_tree:
+ free_inode:
+	tree->inode->i_mapping->a_ops = &hfsplus_aops;
 	iput(tree->inode);
+ free_tree:
 	kfree(tree);
 	return NULL;
 }
@@ -192,17 +228,18 @@
 
 	while (!tree->free_nodes) {
 		struct inode *inode = tree->inode;
+		struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 		u32 count;
 		int res;
 
 		res = hfsplus_file_extend(inode);
 		if (res)
 			return ERR_PTR(res);
-		HFSPLUS_I(inode).phys_size = inode->i_size =
-				(loff_t)HFSPLUS_I(inode).alloc_blocks <<
-				HFSPLUS_SB(tree->sb).alloc_blksz_shift;
-		HFSPLUS_I(inode).fs_blocks = HFSPLUS_I(inode).alloc_blocks <<
-					     HFSPLUS_SB(tree->sb).fs_shift;
+		hip->phys_size = inode->i_size =
+			(loff_t)hip->alloc_blocks <<
+				HFSPLUS_SB(tree->sb)->alloc_blksz_shift;
+		hip->fs_blocks =
+			hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift;
 		inode_set_bytes(inode, inode->i_size);
 		count = inode->i_size >> tree->node_size_shift;
 		tree->free_nodes = count - tree->node_count;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index f6874ac..8af45fc 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -67,7 +67,7 @@
 	key->key_len = cpu_to_be16(6 + ustrlen);
 }
 
-static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
+void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms)
 {
 	if (inode->i_flags & S_IMMUTABLE)
 		perms->rootflags |= HFSPLUS_FLG_IMMUTABLE;
@@ -77,15 +77,24 @@
 		perms->rootflags |= HFSPLUS_FLG_APPEND;
 	else
 		perms->rootflags &= ~HFSPLUS_FLG_APPEND;
-	HFSPLUS_I(inode).rootflags = perms->rootflags;
-	HFSPLUS_I(inode).userflags = perms->userflags;
+
+	perms->userflags = HFSPLUS_I(inode)->userflags;
 	perms->mode = cpu_to_be16(inode->i_mode);
 	perms->owner = cpu_to_be32(inode->i_uid);
 	perms->group = cpu_to_be32(inode->i_gid);
+
+	if (S_ISREG(inode->i_mode))
+		perms->dev = cpu_to_be32(inode->i_nlink);
+	else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode))
+		perms->dev = cpu_to_be32(inode->i_rdev);
+	else
+		perms->dev = 0;
 }
 
 static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct inode *inode)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
+
 	if (S_ISDIR(inode->i_mode)) {
 		struct hfsplus_cat_folder *folder;
 
@@ -93,13 +102,13 @@
 		memset(folder, 0, sizeof(*folder));
 		folder->type = cpu_to_be16(HFSPLUS_FOLDER);
 		folder->id = cpu_to_be32(inode->i_ino);
-		HFSPLUS_I(inode).create_date =
+		HFSPLUS_I(inode)->create_date =
 			folder->create_date =
 			folder->content_mod_date =
 			folder->attribute_mod_date =
 			folder->access_date = hfsp_now2mt();
-		hfsplus_set_perms(inode, &folder->permissions);
-		if (inode == HFSPLUS_SB(inode->i_sb).hidden_dir)
+		hfsplus_cat_set_perms(inode, &folder->permissions);
+		if (inode == sbi->hidden_dir)
 			/* invisible and namelocked */
 			folder->user_info.frFlags = cpu_to_be16(0x5000);
 		return sizeof(*folder);
@@ -111,19 +120,19 @@
 		file->type = cpu_to_be16(HFSPLUS_FILE);
 		file->flags = cpu_to_be16(HFSPLUS_FILE_THREAD_EXISTS);
 		file->id = cpu_to_be32(cnid);
-		HFSPLUS_I(inode).create_date =
+		HFSPLUS_I(inode)->create_date =
 			file->create_date =
 			file->content_mod_date =
 			file->attribute_mod_date =
 			file->access_date = hfsp_now2mt();
 		if (cnid == inode->i_ino) {
-			hfsplus_set_perms(inode, &file->permissions);
+			hfsplus_cat_set_perms(inode, &file->permissions);
 			if (S_ISLNK(inode->i_mode)) {
 				file->user_info.fdType = cpu_to_be32(HFSP_SYMLINK_TYPE);
 				file->user_info.fdCreator = cpu_to_be32(HFSP_SYMLINK_CREATOR);
 			} else {
-				file->user_info.fdType = cpu_to_be32(HFSPLUS_SB(inode->i_sb).type);
-				file->user_info.fdCreator = cpu_to_be32(HFSPLUS_SB(inode->i_sb).creator);
+				file->user_info.fdType = cpu_to_be32(sbi->type);
+				file->user_info.fdCreator = cpu_to_be32(sbi->creator);
 			}
 			if ((file->permissions.rootflags | file->permissions.userflags) & HFSPLUS_FLG_IMMUTABLE)
 				file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED);
@@ -131,8 +140,8 @@
 			file->user_info.fdType = cpu_to_be32(HFSP_HARDLINK_TYPE);
 			file->user_info.fdCreator = cpu_to_be32(HFSP_HFSPLUS_CREATOR);
 			file->user_info.fdFlags = cpu_to_be16(0x100);
-			file->create_date = HFSPLUS_I(HFSPLUS_SB(inode->i_sb).hidden_dir).create_date;
-			file->permissions.dev = cpu_to_be32(HFSPLUS_I(inode).dev);
+			file->create_date = HFSPLUS_I(sbi->hidden_dir)->create_date;
+			file->permissions.dev = cpu_to_be32(HFSPLUS_I(inode)->linkid);
 		}
 		return sizeof(*file);
 	}
@@ -180,15 +189,14 @@
 
 int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str, struct inode *inode)
 {
+	struct super_block *sb = dir->i_sb;
 	struct hfs_find_data fd;
-	struct super_block *sb;
 	hfsplus_cat_entry entry;
 	int entry_size;
 	int err;
 
 	dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink);
-	sb = dir->i_sb;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 
 	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry, S_ISDIR(inode->i_mode) ?
@@ -234,7 +242,7 @@
 
 int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 {
-	struct super_block *sb;
+	struct super_block *sb = dir->i_sb;
 	struct hfs_find_data fd;
 	struct hfsplus_fork_raw fork;
 	struct list_head *pos;
@@ -242,8 +250,7 @@
 	u16 type;
 
 	dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid);
-	sb = dir->i_sb;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 
 	if (!str) {
 		int len;
@@ -279,7 +286,7 @@
 		hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_RSRC);
 	}
 
-	list_for_each(pos, &HFSPLUS_I(dir).open_dir_list) {
+	list_for_each(pos, &HFSPLUS_I(dir)->open_dir_list) {
 		struct hfsplus_readdir_data *rd =
 			list_entry(pos, struct hfsplus_readdir_data, list);
 		if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0)
@@ -312,7 +319,7 @@
 		       struct inode *src_dir, struct qstr *src_name,
 		       struct inode *dst_dir, struct qstr *dst_name)
 {
-	struct super_block *sb;
+	struct super_block *sb = src_dir->i_sb;
 	struct hfs_find_data src_fd, dst_fd;
 	hfsplus_cat_entry entry;
 	int entry_size, type;
@@ -320,8 +327,7 @@
 
 	dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name,
 		dst_dir->i_ino, dst_name->name);
-	sb = src_dir->i_sb;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &src_fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd);
 	dst_fd = src_fd;
 
 	/* find the old dir entry and read the data */
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 764fd1b..d236d85 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -39,7 +39,7 @@
 
 	dentry->d_op = &hfsplus_dentry_operations;
 	dentry->d_fsdata = NULL;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
 again:
 	err = hfs_brec_read(&fd, &entry, sizeof(entry));
@@ -68,9 +68,9 @@
 		cnid = be32_to_cpu(entry.file.id);
 		if (entry.file.user_info.fdType == cpu_to_be32(HFSP_HARDLINK_TYPE) &&
 		    entry.file.user_info.fdCreator == cpu_to_be32(HFSP_HFSPLUS_CREATOR) &&
-		    (entry.file.create_date == HFSPLUS_I(HFSPLUS_SB(sb).hidden_dir).create_date ||
-		     entry.file.create_date == HFSPLUS_I(sb->s_root->d_inode).create_date) &&
-		    HFSPLUS_SB(sb).hidden_dir) {
+		    (entry.file.create_date == HFSPLUS_I(HFSPLUS_SB(sb)->hidden_dir)->create_date ||
+		     entry.file.create_date == HFSPLUS_I(sb->s_root->d_inode)->create_date) &&
+		    HFSPLUS_SB(sb)->hidden_dir) {
 			struct qstr str;
 			char name[32];
 
@@ -86,7 +86,8 @@
 				linkid = be32_to_cpu(entry.file.permissions.dev);
 				str.len = sprintf(name, "iNode%d", linkid);
 				str.name = name;
-				hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_SB(sb).hidden_dir->i_ino, &str);
+				hfsplus_cat_build_key(sb, fd.search_key,
+					HFSPLUS_SB(sb)->hidden_dir->i_ino, &str);
 				goto again;
 			}
 		} else if (!dentry->d_fsdata)
@@ -101,7 +102,7 @@
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 	if (S_ISREG(inode->i_mode))
-		HFSPLUS_I(inode).dev = linkid;
+		HFSPLUS_I(inode)->linkid = linkid;
 out:
 	d_add(dentry, inode);
 	return NULL;
@@ -124,7 +125,7 @@
 	if (filp->f_pos >= inode->i_size)
 		return 0;
 
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
 	err = hfs_brec_find(&fd);
 	if (err)
@@ -180,8 +181,9 @@
 				err = -EIO;
 				goto out;
 			}
-			if (HFSPLUS_SB(sb).hidden_dir &&
-			    HFSPLUS_SB(sb).hidden_dir->i_ino == be32_to_cpu(entry.folder.id))
+			if (HFSPLUS_SB(sb)->hidden_dir &&
+			    HFSPLUS_SB(sb)->hidden_dir->i_ino ==
+					be32_to_cpu(entry.folder.id))
 				goto next;
 			if (filldir(dirent, strbuf, len, filp->f_pos,
 				    be32_to_cpu(entry.folder.id), DT_DIR))
@@ -217,7 +219,7 @@
 		}
 		filp->private_data = rd;
 		rd->file = filp;
-		list_add(&rd->list, &HFSPLUS_I(inode).open_dir_list);
+		list_add(&rd->list, &HFSPLUS_I(inode)->open_dir_list);
 	}
 	memcpy(&rd->key, fd.key, sizeof(struct hfsplus_cat_key));
 out:
@@ -229,38 +231,18 @@
 {
 	struct hfsplus_readdir_data *rd = file->private_data;
 	if (rd) {
+		mutex_lock(&inode->i_mutex);
 		list_del(&rd->list);
+		mutex_unlock(&inode->i_mutex);
 		kfree(rd);
 	}
 	return 0;
 }
 
-static int hfsplus_create(struct inode *dir, struct dentry *dentry, int mode,
-			  struct nameidata *nd)
-{
-	struct inode *inode;
-	int res;
-
-	inode = hfsplus_new_inode(dir->i_sb, mode);
-	if (!inode)
-		return -ENOSPC;
-
-	res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
-	if (res) {
-		inode->i_nlink = 0;
-		hfsplus_delete_inode(inode);
-		iput(inode);
-		return res;
-	}
-	hfsplus_instantiate(dentry, inode, inode->i_ino);
-	mark_inode_dirty(inode);
-	return 0;
-}
-
 static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
 			struct dentry *dst_dentry)
 {
-	struct super_block *sb = dst_dir->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dst_dir->i_sb);
 	struct inode *inode = src_dentry->d_inode;
 	struct inode *src_dir = src_dentry->d_parent->d_inode;
 	struct qstr str;
@@ -270,7 +252,10 @@
 
 	if (HFSPLUS_IS_RSRC(inode))
 		return -EPERM;
+	if (!S_ISREG(inode->i_mode))
+		return -EPERM;
 
+	mutex_lock(&sbi->vh_mutex);
 	if (inode->i_ino == (u32)(unsigned long)src_dentry->d_fsdata) {
 		for (;;) {
 			get_random_bytes(&id, sizeof(cnid));
@@ -279,40 +264,41 @@
 			str.len = sprintf(name, "iNode%d", id);
 			res = hfsplus_rename_cat(inode->i_ino,
 						 src_dir, &src_dentry->d_name,
-						 HFSPLUS_SB(sb).hidden_dir, &str);
+						 sbi->hidden_dir, &str);
 			if (!res)
 				break;
 			if (res != -EEXIST)
-				return res;
+				goto out;
 		}
-		HFSPLUS_I(inode).dev = id;
-		cnid = HFSPLUS_SB(sb).next_cnid++;
+		HFSPLUS_I(inode)->linkid = id;
+		cnid = sbi->next_cnid++;
 		src_dentry->d_fsdata = (void *)(unsigned long)cnid;
 		res = hfsplus_create_cat(cnid, src_dir, &src_dentry->d_name, inode);
 		if (res)
 			/* panic? */
-			return res;
-		HFSPLUS_SB(sb).file_count++;
+			goto out;
+		sbi->file_count++;
 	}
-	cnid = HFSPLUS_SB(sb).next_cnid++;
+	cnid = sbi->next_cnid++;
 	res = hfsplus_create_cat(cnid, dst_dir, &dst_dentry->d_name, inode);
 	if (res)
-		return res;
+		goto out;
 
 	inc_nlink(inode);
 	hfsplus_instantiate(dst_dentry, inode, cnid);
 	atomic_inc(&inode->i_count);
 	inode->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
-	HFSPLUS_SB(sb).file_count++;
-	sb->s_dirt = 1;
-
-	return 0;
+	sbi->file_count++;
+	dst_dir->i_sb->s_dirt = 1;
+out:
+	mutex_unlock(&sbi->vh_mutex);
+	return res;
 }
 
 static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
 {
-	struct super_block *sb = dir->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
 	struct inode *inode = dentry->d_inode;
 	struct qstr str;
 	char name[32];
@@ -322,21 +308,22 @@
 	if (HFSPLUS_IS_RSRC(inode))
 		return -EPERM;
 
+	mutex_lock(&sbi->vh_mutex);
 	cnid = (u32)(unsigned long)dentry->d_fsdata;
 	if (inode->i_ino == cnid &&
-	    atomic_read(&HFSPLUS_I(inode).opencnt)) {
+	    atomic_read(&HFSPLUS_I(inode)->opencnt)) {
 		str.name = name;
 		str.len = sprintf(name, "temp%lu", inode->i_ino);
 		res = hfsplus_rename_cat(inode->i_ino,
 					 dir, &dentry->d_name,
-					 HFSPLUS_SB(sb).hidden_dir, &str);
+					 sbi->hidden_dir, &str);
 		if (!res)
 			inode->i_flags |= S_DEAD;
-		return res;
+		goto out;
 	}
 	res = hfsplus_delete_cat(cnid, dir, &dentry->d_name);
 	if (res)
-		return res;
+		goto out;
 
 	if (inode->i_nlink > 0)
 		drop_nlink(inode);
@@ -344,10 +331,10 @@
 		clear_nlink(inode);
 	if (!inode->i_nlink) {
 		if (inode->i_ino != cnid) {
-			HFSPLUS_SB(sb).file_count--;
-			if (!atomic_read(&HFSPLUS_I(inode).opencnt)) {
+			sbi->file_count--;
+			if (!atomic_read(&HFSPLUS_I(inode)->opencnt)) {
 				res = hfsplus_delete_cat(inode->i_ino,
-							 HFSPLUS_SB(sb).hidden_dir,
+							 sbi->hidden_dir,
 							 NULL);
 				if (!res)
 					hfsplus_delete_inode(inode);
@@ -356,107 +343,108 @@
 		} else
 			hfsplus_delete_inode(inode);
 	} else
-		HFSPLUS_SB(sb).file_count--;
+		sbi->file_count--;
 	inode->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
-
+out:
+	mutex_unlock(&sbi->vh_mutex);
 	return res;
 }
 
-static int hfsplus_mkdir(struct inode *dir, struct dentry *dentry, int mode)
-{
-	struct inode *inode;
-	int res;
-
-	inode = hfsplus_new_inode(dir->i_sb, S_IFDIR | mode);
-	if (!inode)
-		return -ENOSPC;
-
-	res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
-	if (res) {
-		inode->i_nlink = 0;
-		hfsplus_delete_inode(inode);
-		iput(inode);
-		return res;
-	}
-	hfsplus_instantiate(dentry, inode, inode->i_ino);
-	mark_inode_dirty(inode);
-	return 0;
-}
-
 static int hfsplus_rmdir(struct inode *dir, struct dentry *dentry)
 {
-	struct inode *inode;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+	struct inode *inode = dentry->d_inode;
 	int res;
 
-	inode = dentry->d_inode;
 	if (inode->i_size != 2)
 		return -ENOTEMPTY;
+
+	mutex_lock(&sbi->vh_mutex);
 	res = hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name);
 	if (res)
-		return res;
+		goto out;
 	clear_nlink(inode);
 	inode->i_ctime = CURRENT_TIME_SEC;
 	hfsplus_delete_inode(inode);
 	mark_inode_dirty(inode);
-	return 0;
+out:
+	mutex_unlock(&sbi->vh_mutex);
+	return res;
 }
 
 static int hfsplus_symlink(struct inode *dir, struct dentry *dentry,
 			   const char *symname)
 {
-	struct super_block *sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
 	struct inode *inode;
-	int res;
+	int res = -ENOSPC;
 
-	sb = dir->i_sb;
-	inode = hfsplus_new_inode(sb, S_IFLNK | S_IRWXUGO);
+	mutex_lock(&sbi->vh_mutex);
+	inode = hfsplus_new_inode(dir->i_sb, S_IFLNK | S_IRWXUGO);
 	if (!inode)
-		return -ENOSPC;
+		goto out;
 
 	res = page_symlink(inode, symname, strlen(symname) + 1);
-	if (res) {
-		inode->i_nlink = 0;
-		hfsplus_delete_inode(inode);
-		iput(inode);
-		return res;
-	}
+	if (res)
+		goto out_err;
 
-	mark_inode_dirty(inode);
 	res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
+	if (res)
+		goto out_err;
 
-	if (!res) {
-		hfsplus_instantiate(dentry, inode, inode->i_ino);
-		mark_inode_dirty(inode);
-	}
+	hfsplus_instantiate(dentry, inode, inode->i_ino);
+	mark_inode_dirty(inode);
+	goto out;
 
+out_err:
+	inode->i_nlink = 0;
+	hfsplus_delete_inode(inode);
+	iput(inode);
+out:
+	mutex_unlock(&sbi->vh_mutex);
 	return res;
 }
 
 static int hfsplus_mknod(struct inode *dir, struct dentry *dentry,
 			 int mode, dev_t rdev)
 {
-	struct super_block *sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
 	struct inode *inode;
-	int res;
+	int res = -ENOSPC;
 
-	sb = dir->i_sb;
-	inode = hfsplus_new_inode(sb, mode);
+	mutex_lock(&sbi->vh_mutex);
+	inode = hfsplus_new_inode(dir->i_sb, mode);
 	if (!inode)
-		return -ENOSPC;
+		goto out;
+
+	if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode))
+		init_special_inode(inode, mode, rdev);
 
 	res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
 	if (res) {
 		inode->i_nlink = 0;
 		hfsplus_delete_inode(inode);
 		iput(inode);
-		return res;
+		goto out;
 	}
-	init_special_inode(inode, mode, rdev);
+
 	hfsplus_instantiate(dentry, inode, inode->i_ino);
 	mark_inode_dirty(inode);
+out:
+	mutex_unlock(&sbi->vh_mutex);
+	return res;
+}
 
-	return 0;
+static int hfsplus_create(struct inode *dir, struct dentry *dentry, int mode,
+			  struct nameidata *nd)
+{
+	return hfsplus_mknod(dir, dentry, mode, 0);
+}
+
+static int hfsplus_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+	return hfsplus_mknod(dir, dentry, mode | S_IFDIR, 0);
 }
 
 static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
@@ -466,7 +454,10 @@
 
 	/* Unlink destination if it already exists */
 	if (new_dentry->d_inode) {
-		res = hfsplus_unlink(new_dir, new_dentry);
+		if (S_ISDIR(new_dentry->d_inode->i_mode))
+			res = hfsplus_rmdir(new_dir, new_dentry);
+		else
+			res = hfsplus_unlink(new_dir, new_dentry);
 		if (res)
 			return res;
 	}
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 0022eec..0c9cb18 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -85,33 +85,47 @@
 
 static void __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data *fd)
 {
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	int res;
 
-	hfsplus_ext_build_key(fd->search_key, inode->i_ino, HFSPLUS_I(inode).cached_start,
-			      HFSPLUS_IS_RSRC(inode) ?  HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+	WARN_ON(!mutex_is_locked(&hip->extents_lock));
+
+	hfsplus_ext_build_key(fd->search_key, inode->i_ino, hip->cached_start,
+			      HFSPLUS_IS_RSRC(inode) ?
+				HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+
 	res = hfs_brec_find(fd);
-	if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_NEW) {
+	if (hip->flags & HFSPLUS_FLG_EXT_NEW) {
 		if (res != -ENOENT)
 			return;
-		hfs_brec_insert(fd, HFSPLUS_I(inode).cached_extents, sizeof(hfsplus_extent_rec));
-		HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+		hfs_brec_insert(fd, hip->cached_extents,
+				sizeof(hfsplus_extent_rec));
+		hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
 	} else {
 		if (res)
 			return;
-		hfs_bnode_write(fd->bnode, HFSPLUS_I(inode).cached_extents, fd->entryoffset, fd->entrylength);
-		HFSPLUS_I(inode).flags &= ~HFSPLUS_FLG_EXT_DIRTY;
+		hfs_bnode_write(fd->bnode, hip->cached_extents,
+				fd->entryoffset, fd->entrylength);
+		hip->flags &= ~HFSPLUS_FLG_EXT_DIRTY;
+	}
+}
+
+static void hfsplus_ext_write_extent_locked(struct inode *inode)
+{
+	if (HFSPLUS_I(inode)->flags & HFSPLUS_FLG_EXT_DIRTY) {
+		struct hfs_find_data fd;
+
+		hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd);
+		__hfsplus_ext_write_extent(inode, &fd);
+		hfs_find_exit(&fd);
 	}
 }
 
 void hfsplus_ext_write_extent(struct inode *inode)
 {
-	if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_DIRTY) {
-		struct hfs_find_data fd;
-
-		hfs_find_init(HFSPLUS_SB(inode->i_sb).ext_tree, &fd);
-		__hfsplus_ext_write_extent(inode, &fd);
-		hfs_find_exit(&fd);
-	}
+	mutex_lock(&HFSPLUS_I(inode)->extents_lock);
+	hfsplus_ext_write_extent_locked(inode);
+	mutex_unlock(&HFSPLUS_I(inode)->extents_lock);
 }
 
 static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd,
@@ -136,33 +150,39 @@
 
 static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, struct inode *inode, u32 block)
 {
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	int res;
 
-	if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_DIRTY)
+	WARN_ON(!mutex_is_locked(&hip->extents_lock));
+
+	if (hip->flags & HFSPLUS_FLG_EXT_DIRTY)
 		__hfsplus_ext_write_extent(inode, fd);
 
-	res = __hfsplus_ext_read_extent(fd, HFSPLUS_I(inode).cached_extents, inode->i_ino,
-					block, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+	res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino,
+					block, HFSPLUS_IS_RSRC(inode) ?
+						HFSPLUS_TYPE_RSRC :
+						HFSPLUS_TYPE_DATA);
 	if (!res) {
-		HFSPLUS_I(inode).cached_start = be32_to_cpu(fd->key->ext.start_block);
-		HFSPLUS_I(inode).cached_blocks = hfsplus_ext_block_count(HFSPLUS_I(inode).cached_extents);
+		hip->cached_start = be32_to_cpu(fd->key->ext.start_block);
+		hip->cached_blocks = hfsplus_ext_block_count(hip->cached_extents);
 	} else {
-		HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).cached_blocks = 0;
-		HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+		hip->cached_start = hip->cached_blocks = 0;
+		hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
 	}
 	return res;
 }
 
 static int hfsplus_ext_read_extent(struct inode *inode, u32 block)
 {
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	struct hfs_find_data fd;
 	int res;
 
-	if (block >= HFSPLUS_I(inode).cached_start &&
-	    block < HFSPLUS_I(inode).cached_start + HFSPLUS_I(inode).cached_blocks)
+	if (block >= hip->cached_start &&
+	    block < hip->cached_start + hip->cached_blocks)
 		return 0;
 
-	hfs_find_init(HFSPLUS_SB(inode->i_sb).ext_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd);
 	res = __hfsplus_ext_cache_extent(&fd, inode, block);
 	hfs_find_exit(&fd);
 	return res;
@@ -172,21 +192,21 @@
 int hfsplus_get_block(struct inode *inode, sector_t iblock,
 		      struct buffer_head *bh_result, int create)
 {
-	struct super_block *sb;
+	struct super_block *sb = inode->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	int res = -EIO;
 	u32 ablock, dblock, mask;
 	int shift;
 
-	sb = inode->i_sb;
-
 	/* Convert inode block to disk allocation block */
-	shift = HFSPLUS_SB(sb).alloc_blksz_shift - sb->s_blocksize_bits;
-	ablock = iblock >> HFSPLUS_SB(sb).fs_shift;
+	shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
+	ablock = iblock >> sbi->fs_shift;
 
-	if (iblock >= HFSPLUS_I(inode).fs_blocks) {
-		if (iblock > HFSPLUS_I(inode).fs_blocks || !create)
+	if (iblock >= hip->fs_blocks) {
+		if (iblock > hip->fs_blocks || !create)
 			return -EIO;
-		if (ablock >= HFSPLUS_I(inode).alloc_blocks) {
+		if (ablock >= hip->alloc_blocks) {
 			res = hfsplus_file_extend(inode);
 			if (res)
 				return res;
@@ -194,33 +214,33 @@
 	} else
 		create = 0;
 
-	if (ablock < HFSPLUS_I(inode).first_blocks) {
-		dblock = hfsplus_ext_find_block(HFSPLUS_I(inode).first_extents, ablock);
+	if (ablock < hip->first_blocks) {
+		dblock = hfsplus_ext_find_block(hip->first_extents, ablock);
 		goto done;
 	}
 
 	if (inode->i_ino == HFSPLUS_EXT_CNID)
 		return -EIO;
 
-	mutex_lock(&HFSPLUS_I(inode).extents_lock);
+	mutex_lock(&hip->extents_lock);
 	res = hfsplus_ext_read_extent(inode, ablock);
 	if (!res) {
-		dblock = hfsplus_ext_find_block(HFSPLUS_I(inode).cached_extents, ablock -
-					     HFSPLUS_I(inode).cached_start);
+		dblock = hfsplus_ext_find_block(hip->cached_extents,
+						ablock - hip->cached_start);
 	} else {
-		mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+		mutex_unlock(&hip->extents_lock);
 		return -EIO;
 	}
-	mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+	mutex_unlock(&hip->extents_lock);
 
 done:
 	dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock);
-	mask = (1 << HFSPLUS_SB(sb).fs_shift) - 1;
-	map_bh(bh_result, sb, (dblock << HFSPLUS_SB(sb).fs_shift) + HFSPLUS_SB(sb).blockoffset + (iblock & mask));
+	mask = (1 << sbi->fs_shift) - 1;
+	map_bh(bh_result, sb, (dblock << sbi->fs_shift) + sbi->blockoffset + (iblock & mask));
 	if (create) {
 		set_buffer_new(bh_result);
-		HFSPLUS_I(inode).phys_size += sb->s_blocksize;
-		HFSPLUS_I(inode).fs_blocks++;
+		hip->phys_size += sb->s_blocksize;
+		hip->fs_blocks++;
 		inode_add_bytes(inode, sb->s_blocksize);
 		mark_inode_dirty(inode);
 	}
@@ -327,7 +347,7 @@
 	if (total_blocks == blocks)
 		return 0;
 
-	hfs_find_init(HFSPLUS_SB(sb).ext_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd);
 	do {
 		res = __hfsplus_ext_read_extent(&fd, ext_entry, cnid,
 						total_blocks, type);
@@ -348,29 +368,33 @@
 int hfsplus_file_extend(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	u32 start, len, goal;
 	int res;
 
-	if (HFSPLUS_SB(sb).alloc_file->i_size * 8 < HFSPLUS_SB(sb).total_blocks - HFSPLUS_SB(sb).free_blocks + 8) {
+	if (sbi->alloc_file->i_size * 8 <
+	    sbi->total_blocks - sbi->free_blocks + 8) {
 		// extend alloc file
-		printk(KERN_ERR "hfs: extend alloc file! (%Lu,%u,%u)\n", HFSPLUS_SB(sb).alloc_file->i_size * 8,
-			HFSPLUS_SB(sb).total_blocks, HFSPLUS_SB(sb).free_blocks);
+		printk(KERN_ERR "hfs: extend alloc file! (%Lu,%u,%u)\n",
+				sbi->alloc_file->i_size * 8,
+				sbi->total_blocks, sbi->free_blocks);
 		return -ENOSPC;
 	}
 
-	mutex_lock(&HFSPLUS_I(inode).extents_lock);
-	if (HFSPLUS_I(inode).alloc_blocks == HFSPLUS_I(inode).first_blocks)
-		goal = hfsplus_ext_lastblock(HFSPLUS_I(inode).first_extents);
+	mutex_lock(&hip->extents_lock);
+	if (hip->alloc_blocks == hip->first_blocks)
+		goal = hfsplus_ext_lastblock(hip->first_extents);
 	else {
-		res = hfsplus_ext_read_extent(inode, HFSPLUS_I(inode).alloc_blocks);
+		res = hfsplus_ext_read_extent(inode, hip->alloc_blocks);
 		if (res)
 			goto out;
-		goal = hfsplus_ext_lastblock(HFSPLUS_I(inode).cached_extents);
+		goal = hfsplus_ext_lastblock(hip->cached_extents);
 	}
 
-	len = HFSPLUS_I(inode).clump_blocks;
-	start = hfsplus_block_allocate(sb, HFSPLUS_SB(sb).total_blocks, goal, &len);
-	if (start >= HFSPLUS_SB(sb).total_blocks) {
+	len = hip->clump_blocks;
+	start = hfsplus_block_allocate(sb, sbi->total_blocks, goal, &len);
+	if (start >= sbi->total_blocks) {
 		start = hfsplus_block_allocate(sb, goal, 0, &len);
 		if (start >= goal) {
 			res = -ENOSPC;
@@ -379,56 +403,56 @@
 	}
 
 	dprint(DBG_EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len);
-	if (HFSPLUS_I(inode).alloc_blocks <= HFSPLUS_I(inode).first_blocks) {
-		if (!HFSPLUS_I(inode).first_blocks) {
+
+	if (hip->alloc_blocks <= hip->first_blocks) {
+		if (!hip->first_blocks) {
 			dprint(DBG_EXTENT, "first extents\n");
 			/* no extents yet */
-			HFSPLUS_I(inode).first_extents[0].start_block = cpu_to_be32(start);
-			HFSPLUS_I(inode).first_extents[0].block_count = cpu_to_be32(len);
+			hip->first_extents[0].start_block = cpu_to_be32(start);
+			hip->first_extents[0].block_count = cpu_to_be32(len);
 			res = 0;
 		} else {
 			/* try to append to extents in inode */
-			res = hfsplus_add_extent(HFSPLUS_I(inode).first_extents,
-						 HFSPLUS_I(inode).alloc_blocks,
+			res = hfsplus_add_extent(hip->first_extents,
+						 hip->alloc_blocks,
 						 start, len);
 			if (res == -ENOSPC)
 				goto insert_extent;
 		}
 		if (!res) {
-			hfsplus_dump_extent(HFSPLUS_I(inode).first_extents);
-			HFSPLUS_I(inode).first_blocks += len;
+			hfsplus_dump_extent(hip->first_extents);
+			hip->first_blocks += len;
 		}
 	} else {
-		res = hfsplus_add_extent(HFSPLUS_I(inode).cached_extents,
-					 HFSPLUS_I(inode).alloc_blocks -
-					 HFSPLUS_I(inode).cached_start,
+		res = hfsplus_add_extent(hip->cached_extents,
+					 hip->alloc_blocks - hip->cached_start,
 					 start, len);
 		if (!res) {
-			hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
-			HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY;
-			HFSPLUS_I(inode).cached_blocks += len;
+			hfsplus_dump_extent(hip->cached_extents);
+			hip->flags |= HFSPLUS_FLG_EXT_DIRTY;
+			hip->cached_blocks += len;
 		} else if (res == -ENOSPC)
 			goto insert_extent;
 	}
 out:
-	mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+	mutex_unlock(&hip->extents_lock);
 	if (!res) {
-		HFSPLUS_I(inode).alloc_blocks += len;
+		hip->alloc_blocks += len;
 		mark_inode_dirty(inode);
 	}
 	return res;
 
 insert_extent:
 	dprint(DBG_EXTENT, "insert new extent\n");
-	hfsplus_ext_write_extent(inode);
+	hfsplus_ext_write_extent_locked(inode);
 
-	memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-	HFSPLUS_I(inode).cached_extents[0].start_block = cpu_to_be32(start);
-	HFSPLUS_I(inode).cached_extents[0].block_count = cpu_to_be32(len);
-	hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
-	HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW;
-	HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).alloc_blocks;
-	HFSPLUS_I(inode).cached_blocks = len;
+	memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+	hip->cached_extents[0].start_block = cpu_to_be32(start);
+	hip->cached_extents[0].block_count = cpu_to_be32(len);
+	hfsplus_dump_extent(hip->cached_extents);
+	hip->flags |= HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW;
+	hip->cached_start = hip->alloc_blocks;
+	hip->cached_blocks = len;
 
 	res = 0;
 	goto out;
@@ -437,13 +461,15 @@
 void hfsplus_file_truncate(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	struct hfs_find_data fd;
 	u32 alloc_cnt, blk_cnt, start;
 	int res;
 
-	dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n", inode->i_ino,
-	       (long long)HFSPLUS_I(inode).phys_size, inode->i_size);
-	if (inode->i_size > HFSPLUS_I(inode).phys_size) {
+	dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n",
+		inode->i_ino, (long long)hip->phys_size, inode->i_size);
+
+	if (inode->i_size > hip->phys_size) {
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page;
 		void *fsdata;
@@ -460,47 +486,48 @@
 			return;
 		mark_inode_dirty(inode);
 		return;
-	} else if (inode->i_size == HFSPLUS_I(inode).phys_size)
+	} else if (inode->i_size == hip->phys_size)
 		return;
 
-	blk_cnt = (inode->i_size + HFSPLUS_SB(sb).alloc_blksz - 1) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-	alloc_cnt = HFSPLUS_I(inode).alloc_blocks;
+	blk_cnt = (inode->i_size + HFSPLUS_SB(sb)->alloc_blksz - 1) >>
+			HFSPLUS_SB(sb)->alloc_blksz_shift;
+	alloc_cnt = hip->alloc_blocks;
 	if (blk_cnt == alloc_cnt)
 		goto out;
 
-	mutex_lock(&HFSPLUS_I(inode).extents_lock);
-	hfs_find_init(HFSPLUS_SB(sb).ext_tree, &fd);
+	mutex_lock(&hip->extents_lock);
+	hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd);
 	while (1) {
-		if (alloc_cnt == HFSPLUS_I(inode).first_blocks) {
-			hfsplus_free_extents(sb, HFSPLUS_I(inode).first_extents,
+		if (alloc_cnt == hip->first_blocks) {
+			hfsplus_free_extents(sb, hip->first_extents,
 					     alloc_cnt, alloc_cnt - blk_cnt);
-			hfsplus_dump_extent(HFSPLUS_I(inode).first_extents);
-			HFSPLUS_I(inode).first_blocks = blk_cnt;
+			hfsplus_dump_extent(hip->first_extents);
+			hip->first_blocks = blk_cnt;
 			break;
 		}
 		res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt);
 		if (res)
 			break;
-		start = HFSPLUS_I(inode).cached_start;
-		hfsplus_free_extents(sb, HFSPLUS_I(inode).cached_extents,
+		start = hip->cached_start;
+		hfsplus_free_extents(sb, hip->cached_extents,
 				     alloc_cnt - start, alloc_cnt - blk_cnt);
-		hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
+		hfsplus_dump_extent(hip->cached_extents);
 		if (blk_cnt > start) {
-			HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY;
+			hip->flags |= HFSPLUS_FLG_EXT_DIRTY;
 			break;
 		}
 		alloc_cnt = start;
-		HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).cached_blocks = 0;
-		HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+		hip->cached_start = hip->cached_blocks = 0;
+		hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
 		hfs_brec_remove(&fd);
 	}
 	hfs_find_exit(&fd);
-	mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+	mutex_unlock(&hip->extents_lock);
 
-	HFSPLUS_I(inode).alloc_blocks = blk_cnt;
+	hip->alloc_blocks = blk_cnt;
 out:
-	HFSPLUS_I(inode).phys_size = inode->i_size;
-	HFSPLUS_I(inode).fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
-	inode_set_bytes(inode, HFSPLUS_I(inode).fs_blocks << sb->s_blocksize_bits);
+	hip->phys_size = inode->i_size;
+	hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+	inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits);
 	mark_inode_dirty(inode);
 }
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index dc856be..cb3653e 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -62,7 +62,7 @@
 	unsigned int depth;
 
 	//unsigned int map1_size, map_size;
-	struct semaphore tree_lock;
+	struct mutex tree_lock;
 
 	unsigned int pages_per_bnode;
 	spinlock_t hash_lock;
@@ -121,16 +121,21 @@
 	u32 sect_count;
 	int fs_shift;
 
-	/* Stuff in host order from Vol Header */
+	/* immutable data from the volume header */
 	u32 alloc_blksz;
 	int alloc_blksz_shift;
 	u32 total_blocks;
+	u32 data_clump_blocks, rsrc_clump_blocks;
+
+	/* mutable data from the volume header, protected by alloc_mutex */
 	u32 free_blocks;
-	u32 next_alloc;
+	struct mutex alloc_mutex;
+
+	/* mutable data from the volume header, protected by vh_mutex */
 	u32 next_cnid;
 	u32 file_count;
 	u32 folder_count;
-	u32 data_clump_blocks, rsrc_clump_blocks;
+	struct mutex vh_mutex;
 
 	/* Config options */
 	u32 creator;
@@ -143,40 +148,50 @@
 	int part, session;
 
 	unsigned long flags;
-
-	struct hlist_head rsrc_inodes;
 };
 
-#define HFSPLUS_SB_WRITEBACKUP	0x0001
-#define HFSPLUS_SB_NODECOMPOSE	0x0002
-#define HFSPLUS_SB_FORCE	0x0004
-#define HFSPLUS_SB_HFSX		0x0008
-#define HFSPLUS_SB_CASEFOLD	0x0010
+#define HFSPLUS_SB_WRITEBACKUP	0
+#define HFSPLUS_SB_NODECOMPOSE	1
+#define HFSPLUS_SB_FORCE	2
+#define HFSPLUS_SB_HFSX		3
+#define HFSPLUS_SB_CASEFOLD	4
 
 
 struct hfsplus_inode_info {
-	struct mutex extents_lock;
-	u32 clump_blocks, alloc_blocks;
-	sector_t fs_blocks;
-	/* Allocation extents from catalog record or volume header */
-	hfsplus_extent_rec first_extents;
-	u32 first_blocks;
-	hfsplus_extent_rec cached_extents;
-	u32 cached_start, cached_blocks;
 	atomic_t opencnt;
 
-	struct inode *rsrc_inode;
+	/*
+	 * Extent allocation information, protected by extents_lock.
+	 */
+	u32 first_blocks;
+	u32 clump_blocks;
+	u32 alloc_blocks;
+	u32 cached_start;
+	u32 cached_blocks;
+	hfsplus_extent_rec first_extents;
+	hfsplus_extent_rec cached_extents;
 	unsigned long flags;
+	struct mutex extents_lock;
 
+	/*
+	 * Immutable data.
+	 */
+	struct inode *rsrc_inode;
 	__be32 create_date;
-	/* Device number in hfsplus_permissions in catalog */
-	u32 dev;
-	/* BSD system and user file flags */
-	u8 rootflags;
-	u8 userflags;
 
+	/*
+	 * Protected by sbi->vh_mutex.
+	 */
+	u32 linkid;
+
+	/*
+	 * Protected by i_mutex.
+	 */
+	sector_t fs_blocks;
+	u8 userflags;		/* BSD user file flags */
 	struct list_head open_dir_list;
 	loff_t phys_size;
+
 	struct inode vfs_inode;
 };
 
@@ -184,8 +199,8 @@
 #define HFSPLUS_FLG_EXT_DIRTY	0x0002
 #define HFSPLUS_FLG_EXT_NEW	0x0004
 
-#define HFSPLUS_IS_DATA(inode)   (!(HFSPLUS_I(inode).flags & HFSPLUS_FLG_RSRC))
-#define HFSPLUS_IS_RSRC(inode)   (HFSPLUS_I(inode).flags & HFSPLUS_FLG_RSRC)
+#define HFSPLUS_IS_DATA(inode)   (!(HFSPLUS_I(inode)->flags & HFSPLUS_FLG_RSRC))
+#define HFSPLUS_IS_RSRC(inode)   (HFSPLUS_I(inode)->flags & HFSPLUS_FLG_RSRC)
 
 struct hfs_find_data {
 	/* filled by caller */
@@ -311,6 +326,7 @@
 int hfsplus_delete_cat(u32, struct inode *, struct qstr *);
 int hfsplus_rename_cat(u32, struct inode *, struct qstr *,
 		       struct inode *, struct qstr *);
+void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms);
 
 /* dir.c */
 extern const struct inode_operations hfsplus_dir_inode_operations;
@@ -372,26 +388,15 @@
 int hfs_part_find(struct super_block *, sector_t *, sector_t *);
 
 /* access macros */
-/*
 static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
 }
+
 static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
 {
 	return list_entry(inode, struct hfsplus_inode_info, vfs_inode);
 }
-*/
-#define HFSPLUS_SB(super)	(*(struct hfsplus_sb_info *)(super)->s_fs_info)
-#define HFSPLUS_I(inode)	(*list_entry(inode, struct hfsplus_inode_info, vfs_inode))
-
-#if 1
-#define hfsplus_kmap(p)		({ struct page *__p = (p); kmap(__p); })
-#define hfsplus_kunmap(p)	({ struct page *__p = (p); kunmap(__p); __p; })
-#else
-#define hfsplus_kmap(p)		kmap(p)
-#define hfsplus_kunmap(p)	kunmap(p)
-#endif
 
 #define sb_bread512(sb, sec, data) ({			\
 	struct buffer_head *__bh;			\
@@ -419,6 +424,4 @@
 #define hfsp_ut2mt(t)		__hfsp_ut2mt((t).tv_sec)
 #define hfsp_now2mt()		__hfsp_ut2mt(get_seconds())
 
-#define kdev_t_to_nr(x)		(x)
-
 #endif
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index fe99fe8..6892899 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -200,6 +200,7 @@
 	struct hfsplus_unistr name;
 } __packed;
 
+#define HFSPLUS_CAT_KEYLEN	(sizeof(struct hfsplus_cat_key))
 
 /* Structs from hfs.h */
 struct hfsp_point {
@@ -323,7 +324,7 @@
 	__be32 start_block;
 } __packed;
 
-#define HFSPLUS_EXT_KEYLEN 12
+#define HFSPLUS_EXT_KEYLEN	sizeof(struct hfsplus_ext_key)
 
 /* HFS+ generic BTree key */
 typedef union {
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index c5a979d..7844928 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -36,7 +36,7 @@
 	*pagep = NULL;
 	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
 				hfsplus_get_block,
-				&HFSPLUS_I(mapping->host).phys_size);
+				&HFSPLUS_I(mapping->host)->phys_size);
 	if (unlikely(ret)) {
 		loff_t isize = mapping->host->i_size;
 		if (pos + len > isize)
@@ -62,13 +62,13 @@
 
 	switch (inode->i_ino) {
 	case HFSPLUS_EXT_CNID:
-		tree = HFSPLUS_SB(sb).ext_tree;
+		tree = HFSPLUS_SB(sb)->ext_tree;
 		break;
 	case HFSPLUS_CAT_CNID:
-		tree = HFSPLUS_SB(sb).cat_tree;
+		tree = HFSPLUS_SB(sb)->cat_tree;
 		break;
 	case HFSPLUS_ATTR_CNID:
-		tree = HFSPLUS_SB(sb).attr_tree;
+		tree = HFSPLUS_SB(sb)->attr_tree;
 		break;
 	default:
 		BUG();
@@ -172,12 +172,13 @@
 	struct hfs_find_data fd;
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = NULL;
+	struct hfsplus_inode_info *hip;
 	int err;
 
 	if (HFSPLUS_IS_RSRC(dir) || strcmp(dentry->d_name.name, "rsrc"))
 		goto out;
 
-	inode = HFSPLUS_I(dir).rsrc_inode;
+	inode = HFSPLUS_I(dir)->rsrc_inode;
 	if (inode)
 		goto out;
 
@@ -185,12 +186,13 @@
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
+	hip = HFSPLUS_I(inode);
 	inode->i_ino = dir->i_ino;
-	INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-	mutex_init(&HFSPLUS_I(inode).extents_lock);
-	HFSPLUS_I(inode).flags = HFSPLUS_FLG_RSRC;
+	INIT_LIST_HEAD(&hip->open_dir_list);
+	mutex_init(&hip->extents_lock);
+	hip->flags = HFSPLUS_FLG_RSRC;
 
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	err = hfsplus_find_cat(sb, dir->i_ino, &fd);
 	if (!err)
 		err = hfsplus_cat_read_inode(inode, &fd);
@@ -199,10 +201,18 @@
 		iput(inode);
 		return ERR_PTR(err);
 	}
-	HFSPLUS_I(inode).rsrc_inode = dir;
-	HFSPLUS_I(dir).rsrc_inode = inode;
+	hip->rsrc_inode = dir;
+	HFSPLUS_I(dir)->rsrc_inode = inode;
 	igrab(dir);
-	hlist_add_head(&inode->i_hash, &HFSPLUS_SB(sb).rsrc_inodes);
+
+	/*
+	 * __mark_inode_dirty expects inodes to be hashed.  Since we don't
+	 * want resource fork inodes in the regular inode space, we make them
+	 * appear hashed, but do not put on any lists.  hlist_del()
+	 * will work fine and require no locking.
+	 */
+	inode->i_hash.pprev = &inode->i_hash.next;
+
 	mark_inode_dirty(inode);
 out:
 	d_add(dentry, inode);
@@ -211,30 +221,27 @@
 
 static void hfsplus_get_perms(struct inode *inode, struct hfsplus_perm *perms, int dir)
 {
-	struct super_block *sb = inode->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
 	u16 mode;
 
 	mode = be16_to_cpu(perms->mode);
 
 	inode->i_uid = be32_to_cpu(perms->owner);
 	if (!inode->i_uid && !mode)
-		inode->i_uid = HFSPLUS_SB(sb).uid;
+		inode->i_uid = sbi->uid;
 
 	inode->i_gid = be32_to_cpu(perms->group);
 	if (!inode->i_gid && !mode)
-		inode->i_gid = HFSPLUS_SB(sb).gid;
+		inode->i_gid = sbi->gid;
 
 	if (dir) {
-		mode = mode ? (mode & S_IALLUGO) :
-			(S_IRWXUGO & ~(HFSPLUS_SB(sb).umask));
+		mode = mode ? (mode & S_IALLUGO) : (S_IRWXUGO & ~(sbi->umask));
 		mode |= S_IFDIR;
 	} else if (!mode)
-		mode = S_IFREG | ((S_IRUGO|S_IWUGO) &
-			~(HFSPLUS_SB(sb).umask));
+		mode = S_IFREG | ((S_IRUGO|S_IWUGO) & ~(sbi->umask));
 	inode->i_mode = mode;
 
-	HFSPLUS_I(inode).rootflags = perms->rootflags;
-	HFSPLUS_I(inode).userflags = perms->userflags;
+	HFSPLUS_I(inode)->userflags = perms->userflags;
 	if (perms->rootflags & HFSPLUS_FLG_IMMUTABLE)
 		inode->i_flags |= S_IMMUTABLE;
 	else
@@ -245,30 +252,13 @@
 		inode->i_flags &= ~S_APPEND;
 }
 
-static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
-{
-	if (inode->i_flags & S_IMMUTABLE)
-		perms->rootflags |= HFSPLUS_FLG_IMMUTABLE;
-	else
-		perms->rootflags &= ~HFSPLUS_FLG_IMMUTABLE;
-	if (inode->i_flags & S_APPEND)
-		perms->rootflags |= HFSPLUS_FLG_APPEND;
-	else
-		perms->rootflags &= ~HFSPLUS_FLG_APPEND;
-	perms->userflags = HFSPLUS_I(inode).userflags;
-	perms->mode = cpu_to_be16(inode->i_mode);
-	perms->owner = cpu_to_be32(inode->i_uid);
-	perms->group = cpu_to_be32(inode->i_gid);
-	perms->dev = cpu_to_be32(HFSPLUS_I(inode).dev);
-}
-
 static int hfsplus_file_open(struct inode *inode, struct file *file)
 {
 	if (HFSPLUS_IS_RSRC(inode))
-		inode = HFSPLUS_I(inode).rsrc_inode;
+		inode = HFSPLUS_I(inode)->rsrc_inode;
 	if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
 		return -EOVERFLOW;
-	atomic_inc(&HFSPLUS_I(inode).opencnt);
+	atomic_inc(&HFSPLUS_I(inode)->opencnt);
 	return 0;
 }
 
@@ -277,12 +267,13 @@
 	struct super_block *sb = inode->i_sb;
 
 	if (HFSPLUS_IS_RSRC(inode))
-		inode = HFSPLUS_I(inode).rsrc_inode;
-	if (atomic_dec_and_test(&HFSPLUS_I(inode).opencnt)) {
+		inode = HFSPLUS_I(inode)->rsrc_inode;
+	if (atomic_dec_and_test(&HFSPLUS_I(inode)->opencnt)) {
 		mutex_lock(&inode->i_mutex);
 		hfsplus_file_truncate(inode);
 		if (inode->i_flags & S_DEAD) {
-			hfsplus_delete_cat(inode->i_ino, HFSPLUS_SB(sb).hidden_dir, NULL);
+			hfsplus_delete_cat(inode->i_ino,
+					   HFSPLUS_SB(sb)->hidden_dir, NULL);
 			hfsplus_delete_inode(inode);
 		}
 		mutex_unlock(&inode->i_mutex);
@@ -361,47 +352,52 @@
 
 struct inode *hfsplus_new_inode(struct super_block *sb, int mode)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct inode *inode = new_inode(sb);
+	struct hfsplus_inode_info *hip;
+
 	if (!inode)
 		return NULL;
 
-	inode->i_ino = HFSPLUS_SB(sb).next_cnid++;
+	inode->i_ino = sbi->next_cnid++;
 	inode->i_mode = mode;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();
 	inode->i_nlink = 1;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
-	INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-	mutex_init(&HFSPLUS_I(inode).extents_lock);
-	atomic_set(&HFSPLUS_I(inode).opencnt, 0);
-	HFSPLUS_I(inode).flags = 0;
-	memset(HFSPLUS_I(inode).first_extents, 0, sizeof(hfsplus_extent_rec));
-	memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-	HFSPLUS_I(inode).alloc_blocks = 0;
-	HFSPLUS_I(inode).first_blocks = 0;
-	HFSPLUS_I(inode).cached_start = 0;
-	HFSPLUS_I(inode).cached_blocks = 0;
-	HFSPLUS_I(inode).phys_size = 0;
-	HFSPLUS_I(inode).fs_blocks = 0;
-	HFSPLUS_I(inode).rsrc_inode = NULL;
+
+	hip = HFSPLUS_I(inode);
+	INIT_LIST_HEAD(&hip->open_dir_list);
+	mutex_init(&hip->extents_lock);
+	atomic_set(&hip->opencnt, 0);
+	hip->flags = 0;
+	memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
+	memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+	hip->alloc_blocks = 0;
+	hip->first_blocks = 0;
+	hip->cached_start = 0;
+	hip->cached_blocks = 0;
+	hip->phys_size = 0;
+	hip->fs_blocks = 0;
+	hip->rsrc_inode = NULL;
 	if (S_ISDIR(inode->i_mode)) {
 		inode->i_size = 2;
-		HFSPLUS_SB(sb).folder_count++;
+		sbi->folder_count++;
 		inode->i_op = &hfsplus_dir_inode_operations;
 		inode->i_fop = &hfsplus_dir_operations;
 	} else if (S_ISREG(inode->i_mode)) {
-		HFSPLUS_SB(sb).file_count++;
+		sbi->file_count++;
 		inode->i_op = &hfsplus_file_inode_operations;
 		inode->i_fop = &hfsplus_file_operations;
 		inode->i_mapping->a_ops = &hfsplus_aops;
-		HFSPLUS_I(inode).clump_blocks = HFSPLUS_SB(sb).data_clump_blocks;
+		hip->clump_blocks = sbi->data_clump_blocks;
 	} else if (S_ISLNK(inode->i_mode)) {
-		HFSPLUS_SB(sb).file_count++;
+		sbi->file_count++;
 		inode->i_op = &page_symlink_inode_operations;
 		inode->i_mapping->a_ops = &hfsplus_aops;
-		HFSPLUS_I(inode).clump_blocks = 1;
+		hip->clump_blocks = 1;
 	} else
-		HFSPLUS_SB(sb).file_count++;
+		sbi->file_count++;
 	insert_inode_hash(inode);
 	mark_inode_dirty(inode);
 	sb->s_dirt = 1;
@@ -414,11 +410,11 @@
 	struct super_block *sb = inode->i_sb;
 
 	if (S_ISDIR(inode->i_mode)) {
-		HFSPLUS_SB(sb).folder_count--;
+		HFSPLUS_SB(sb)->folder_count--;
 		sb->s_dirt = 1;
 		return;
 	}
-	HFSPLUS_SB(sb).file_count--;
+	HFSPLUS_SB(sb)->file_count--;
 	if (S_ISREG(inode->i_mode)) {
 		if (!inode->i_nlink) {
 			inode->i_size = 0;
@@ -434,34 +430,39 @@
 void hfsplus_inode_read_fork(struct inode *inode, struct hfsplus_fork_raw *fork)
 {
 	struct super_block *sb = inode->i_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
 	u32 count;
 	int i;
 
-	memcpy(&HFSPLUS_I(inode).first_extents, &fork->extents,
-	       sizeof(hfsplus_extent_rec));
+	memcpy(&hip->first_extents, &fork->extents, sizeof(hfsplus_extent_rec));
 	for (count = 0, i = 0; i < 8; i++)
 		count += be32_to_cpu(fork->extents[i].block_count);
-	HFSPLUS_I(inode).first_blocks = count;
-	memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-	HFSPLUS_I(inode).cached_start = 0;
-	HFSPLUS_I(inode).cached_blocks = 0;
+	hip->first_blocks = count;
+	memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+	hip->cached_start = 0;
+	hip->cached_blocks = 0;
 
-	HFSPLUS_I(inode).alloc_blocks = be32_to_cpu(fork->total_blocks);
-	inode->i_size = HFSPLUS_I(inode).phys_size = be64_to_cpu(fork->total_size);
-	HFSPLUS_I(inode).fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
-	inode_set_bytes(inode, HFSPLUS_I(inode).fs_blocks << sb->s_blocksize_bits);
-	HFSPLUS_I(inode).clump_blocks = be32_to_cpu(fork->clump_size) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-	if (!HFSPLUS_I(inode).clump_blocks)
-		HFSPLUS_I(inode).clump_blocks = HFSPLUS_IS_RSRC(inode) ? HFSPLUS_SB(sb).rsrc_clump_blocks :
-				HFSPLUS_SB(sb).data_clump_blocks;
+	hip->alloc_blocks = be32_to_cpu(fork->total_blocks);
+	hip->phys_size = inode->i_size = be64_to_cpu(fork->total_size);
+	hip->fs_blocks =
+		(inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+	inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits);
+	hip->clump_blocks =
+		be32_to_cpu(fork->clump_size) >> sbi->alloc_blksz_shift;
+	if (!hip->clump_blocks) {
+		hip->clump_blocks = HFSPLUS_IS_RSRC(inode) ?
+			sbi->rsrc_clump_blocks :
+			sbi->data_clump_blocks;
+	}
 }
 
 void hfsplus_inode_write_fork(struct inode *inode, struct hfsplus_fork_raw *fork)
 {
-	memcpy(&fork->extents, &HFSPLUS_I(inode).first_extents,
+	memcpy(&fork->extents, &HFSPLUS_I(inode)->first_extents,
 	       sizeof(hfsplus_extent_rec));
 	fork->total_size = cpu_to_be64(inode->i_size);
-	fork->total_blocks = cpu_to_be32(HFSPLUS_I(inode).alloc_blocks);
+	fork->total_blocks = cpu_to_be32(HFSPLUS_I(inode)->alloc_blocks);
 }
 
 int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
@@ -472,7 +473,7 @@
 
 	type = hfs_bnode_read_u16(fd->bnode, fd->entryoffset);
 
-	HFSPLUS_I(inode).dev = 0;
+	HFSPLUS_I(inode)->linkid = 0;
 	if (type == HFSPLUS_FOLDER) {
 		struct hfsplus_cat_folder *folder = &entry.folder;
 
@@ -486,8 +487,8 @@
 		inode->i_atime = hfsp_mt2ut(folder->access_date);
 		inode->i_mtime = hfsp_mt2ut(folder->content_mod_date);
 		inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
-		HFSPLUS_I(inode).create_date = folder->create_date;
-		HFSPLUS_I(inode).fs_blocks = 0;
+		HFSPLUS_I(inode)->create_date = folder->create_date;
+		HFSPLUS_I(inode)->fs_blocks = 0;
 		inode->i_op = &hfsplus_dir_inode_operations;
 		inode->i_fop = &hfsplus_dir_operations;
 	} else if (type == HFSPLUS_FILE) {
@@ -518,7 +519,7 @@
 		inode->i_atime = hfsp_mt2ut(file->access_date);
 		inode->i_mtime = hfsp_mt2ut(file->content_mod_date);
 		inode->i_ctime = hfsp_mt2ut(file->attribute_mod_date);
-		HFSPLUS_I(inode).create_date = file->create_date;
+		HFSPLUS_I(inode)->create_date = file->create_date;
 	} else {
 		printk(KERN_ERR "hfs: bad catalog entry used to create inode\n");
 		res = -EIO;
@@ -533,12 +534,12 @@
 	hfsplus_cat_entry entry;
 
 	if (HFSPLUS_IS_RSRC(inode))
-		main_inode = HFSPLUS_I(inode).rsrc_inode;
+		main_inode = HFSPLUS_I(inode)->rsrc_inode;
 
 	if (!main_inode->i_nlink)
 		return 0;
 
-	if (hfs_find_init(HFSPLUS_SB(main_inode->i_sb).cat_tree, &fd))
+	if (hfs_find_init(HFSPLUS_SB(main_inode->i_sb)->cat_tree, &fd))
 		/* panic? */
 		return -EIO;
 
@@ -554,7 +555,7 @@
 		hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
 					sizeof(struct hfsplus_cat_folder));
 		/* simple node checks? */
-		hfsplus_set_perms(inode, &folder->permissions);
+		hfsplus_cat_set_perms(inode, &folder->permissions);
 		folder->access_date = hfsp_ut2mt(inode->i_atime);
 		folder->content_mod_date = hfsp_ut2mt(inode->i_mtime);
 		folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime);
@@ -576,11 +577,7 @@
 		hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
 					sizeof(struct hfsplus_cat_file));
 		hfsplus_inode_write_fork(inode, &file->data_fork);
-		if (S_ISREG(inode->i_mode))
-			HFSPLUS_I(inode).dev = inode->i_nlink;
-		if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
-			HFSPLUS_I(inode).dev = kdev_t_to_nr(inode->i_rdev);
-		hfsplus_set_perms(inode, &file->permissions);
+		hfsplus_cat_set_perms(inode, &file->permissions);
 		if ((file->permissions.rootflags | file->permissions.userflags) & HFSPLUS_FLG_IMMUTABLE)
 			file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED);
 		else
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index ac405f0..5b4667e 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -17,83 +17,98 @@
 #include <linux/mount.h>
 #include <linux/sched.h>
 #include <linux/xattr.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 #include "hfsplus_fs.h"
 
-long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags)
 {
-	struct inode *inode = filp->f_path.dentry->d_inode;
-	unsigned int flags;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+	unsigned int flags = 0;
 
-	lock_kernel();
+	if (inode->i_flags & S_IMMUTABLE)
+		flags |= FS_IMMUTABLE_FL;
+	if (inode->i_flags |= S_APPEND)
+		flags |= FS_APPEND_FL;
+	if (hip->userflags & HFSPLUS_FLG_NODUMP)
+		flags |= FS_NODUMP_FL;
+
+	return put_user(flags, user_flags);
+}
+
+static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+	unsigned int flags;
+	int err = 0;
+
+	err = mnt_want_write(file->f_path.mnt);
+	if (err)
+		goto out;
+
+	if (!is_owner_or_cap(inode)) {
+		err = -EACCES;
+		goto out_drop_write;
+	}
+
+	if (get_user(flags, user_flags)) {
+		err = -EFAULT;
+		goto out_drop_write;
+	}
+
+	mutex_lock(&inode->i_mutex);
+
+	if ((flags & (FS_IMMUTABLE_FL|FS_APPEND_FL)) ||
+	    inode->i_flags & (S_IMMUTABLE|S_APPEND)) {
+		if (!capable(CAP_LINUX_IMMUTABLE)) {
+			err = -EPERM;
+			goto out_unlock_inode;
+		}
+	}
+
+	/* don't silently ignore unsupported ext2 flags */
+	if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) {
+		err = -EOPNOTSUPP;
+		goto out_unlock_inode;
+	}
+
+	if (flags & FS_IMMUTABLE_FL)
+		inode->i_flags |= S_IMMUTABLE;
+	else
+		inode->i_flags &= ~S_IMMUTABLE;
+
+	if (flags & FS_APPEND_FL)
+		inode->i_flags |= S_APPEND;
+	else
+		inode->i_flags &= ~S_APPEND;
+
+	if (flags & FS_NODUMP_FL)
+		hip->userflags |= HFSPLUS_FLG_NODUMP;
+	else
+		hip->userflags &= ~HFSPLUS_FLG_NODUMP;
+
+	inode->i_ctime = CURRENT_TIME_SEC;
+	mark_inode_dirty(inode);
+
+out_unlock_inode:
+	mutex_lock(&inode->i_mutex);
+out_drop_write:
+	mnt_drop_write(file->f_path.mnt);
+out:
+	return err;
+}
+
+long hfsplus_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+
 	switch (cmd) {
 	case HFSPLUS_IOC_EXT2_GETFLAGS:
-		flags = 0;
-		if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_IMMUTABLE)
-			flags |= FS_IMMUTABLE_FL; /* EXT2_IMMUTABLE_FL */
-		if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_APPEND)
-			flags |= FS_APPEND_FL; /* EXT2_APPEND_FL */
-		if (HFSPLUS_I(inode).userflags & HFSPLUS_FLG_NODUMP)
-			flags |= FS_NODUMP_FL; /* EXT2_NODUMP_FL */
-		return put_user(flags, (int __user *)arg);
-	case HFSPLUS_IOC_EXT2_SETFLAGS: {
-		int err = 0;
-		err = mnt_want_write(filp->f_path.mnt);
-		if (err) {
-			unlock_kernel();
-			return err;
-		}
-
-		if (!is_owner_or_cap(inode)) {
-			err = -EACCES;
-			goto setflags_out;
-		}
-		if (get_user(flags, (int __user *)arg)) {
-			err = -EFAULT;
-			goto setflags_out;
-		}
-		if (flags & (FS_IMMUTABLE_FL|FS_APPEND_FL) ||
-		    HFSPLUS_I(inode).rootflags & (HFSPLUS_FLG_IMMUTABLE|HFSPLUS_FLG_APPEND)) {
-			if (!capable(CAP_LINUX_IMMUTABLE)) {
-				err = -EPERM;
-				goto setflags_out;
-			}
-		}
-
-		/* don't silently ignore unsupported ext2 flags */
-		if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) {
-			err = -EOPNOTSUPP;
-			goto setflags_out;
-		}
-		if (flags & FS_IMMUTABLE_FL) { /* EXT2_IMMUTABLE_FL */
-			inode->i_flags |= S_IMMUTABLE;
-			HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_IMMUTABLE;
-		} else {
-			inode->i_flags &= ~S_IMMUTABLE;
-			HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_IMMUTABLE;
-		}
-		if (flags & FS_APPEND_FL) { /* EXT2_APPEND_FL */
-			inode->i_flags |= S_APPEND;
-			HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_APPEND;
-		} else {
-			inode->i_flags &= ~S_APPEND;
-			HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_APPEND;
-		}
-		if (flags & FS_NODUMP_FL) /* EXT2_NODUMP_FL */
-			HFSPLUS_I(inode).userflags |= HFSPLUS_FLG_NODUMP;
-		else
-			HFSPLUS_I(inode).userflags &= ~HFSPLUS_FLG_NODUMP;
-
-		inode->i_ctime = CURRENT_TIME_SEC;
-		mark_inode_dirty(inode);
-setflags_out:
-		mnt_drop_write(filp->f_path.mnt);
-		unlock_kernel();
-		return err;
-	}
+		return hfsplus_ioctl_getflags(file, argp);
+	case HFSPLUS_IOC_EXT2_SETFLAGS:
+		return hfsplus_ioctl_setflags(file, argp);
 	default:
-		unlock_kernel();
 		return -ENOTTY;
 	}
 }
@@ -110,7 +125,7 @@
 	if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
 		return -EOPNOTSUPP;
 
-	res = hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
+	res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
 	if (res)
 		return res;
 	res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
@@ -153,7 +168,7 @@
 		return -EOPNOTSUPP;
 
 	if (size) {
-		res = hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
+		res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
 		if (res)
 			return res;
 		res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
@@ -177,7 +192,7 @@
 		} else
 			res = size ? -ERANGE : 4;
 	} else
-		res = -ENODATA;
+		res = -EOPNOTSUPP;
 out:
 	if (size)
 		hfs_find_exit(&fd);
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 572628b..f9ab276 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -143,13 +143,13 @@
 			kfree(p);
 			break;
 		case opt_decompose:
-			sbi->flags &= ~HFSPLUS_SB_NODECOMPOSE;
+			clear_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
 			break;
 		case opt_nodecompose:
-			sbi->flags |= HFSPLUS_SB_NODECOMPOSE;
+			set_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
 			break;
 		case opt_force:
-			sbi->flags |= HFSPLUS_SB_FORCE;
+			set_bit(HFSPLUS_SB_FORCE, &sbi->flags);
 			break;
 		default:
 			return 0;
@@ -171,7 +171,7 @@
 
 int hfsplus_show_options(struct seq_file *seq, struct vfsmount *mnt)
 {
-	struct hfsplus_sb_info *sbi = &HFSPLUS_SB(mnt->mnt_sb);
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(mnt->mnt_sb);
 
 	if (sbi->creator != HFSPLUS_DEF_CR_TYPE)
 		seq_printf(seq, ",creator=%.4s", (char *)&sbi->creator);
@@ -184,7 +184,7 @@
 		seq_printf(seq, ",session=%u", sbi->session);
 	if (sbi->nls)
 		seq_printf(seq, ",nls=%s", sbi->nls->charset);
-	if (sbi->flags & HFSPLUS_SB_NODECOMPOSE)
+	if (test_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags))
 		seq_printf(seq, ",nodecompose");
 	return 0;
 }
diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c
index 1528a6f..208b16c 100644
--- a/fs/hfsplus/part_tbl.c
+++ b/fs/hfsplus/part_tbl.c
@@ -74,6 +74,7 @@
 int hfs_part_find(struct super_block *sb,
 		  sector_t *part_start, sector_t *part_size)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct buffer_head *bh;
 	__be16 *data;
 	int i, size, res;
@@ -95,7 +96,7 @@
 		for (i = 0; i < size; p++, i++) {
 			if (p->pdStart && p->pdSize &&
 			    p->pdFSID == cpu_to_be32(0x54465331)/*"TFS1"*/ &&
-			    (HFSPLUS_SB(sb).part < 0 || HFSPLUS_SB(sb).part == i)) {
+			    (sbi->part < 0 || sbi->part == i)) {
 				*part_start += be32_to_cpu(p->pdStart);
 				*part_size = be32_to_cpu(p->pdSize);
 				res = 0;
@@ -111,7 +112,7 @@
 		size = be32_to_cpu(pm->pmMapBlkCnt);
 		for (i = 0; i < size;) {
 			if (!memcmp(pm->pmPartType,"Apple_HFS", 9) &&
-			    (HFSPLUS_SB(sb).part < 0 || HFSPLUS_SB(sb).part == i)) {
+			    (sbi->part < 0 || sbi->part == i)) {
 				*part_start += be32_to_cpu(pm->pmPyPartStart);
 				*part_size = be32_to_cpu(pm->pmPartBlkCnt);
 				res = 0;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 3b55c05..9a88d75 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -12,7 +12,6 @@
 #include <linux/pagemap.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 #include <linux/nls.h>
 
@@ -21,40 +20,11 @@
 
 #include "hfsplus_fs.h"
 
-struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
+static int hfsplus_system_read_inode(struct inode *inode)
 {
-	struct hfs_find_data fd;
-	struct hfsplus_vh *vhdr;
-	struct inode *inode;
-	long err = -EIO;
+	struct hfsplus_vh *vhdr = HFSPLUS_SB(inode->i_sb)->s_vhdr;
 
-	inode = iget_locked(sb, ino);
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
-	if (!(inode->i_state & I_NEW))
-		return inode;
-
-	INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-	mutex_init(&HFSPLUS_I(inode).extents_lock);
-	HFSPLUS_I(inode).flags = 0;
-	HFSPLUS_I(inode).rsrc_inode = NULL;
-	atomic_set(&HFSPLUS_I(inode).opencnt, 0);
-
-	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID) {
-	read_inode:
-		hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
-		err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
-		if (!err)
-			err = hfsplus_cat_read_inode(inode, &fd);
-		hfs_find_exit(&fd);
-		if (err)
-			goto bad_inode;
-		goto done;
-	}
-	vhdr = HFSPLUS_SB(inode->i_sb).s_vhdr;
-	switch(inode->i_ino) {
-	case HFSPLUS_ROOT_CNID:
-		goto read_inode;
+	switch (inode->i_ino) {
 	case HFSPLUS_EXT_CNID:
 		hfsplus_inode_read_fork(inode, &vhdr->ext_file);
 		inode->i_mapping->a_ops = &hfsplus_btree_aops;
@@ -75,74 +45,101 @@
 		inode->i_mapping->a_ops = &hfsplus_btree_aops;
 		break;
 	default:
-		goto bad_inode;
+		return -EIO;
 	}
 
-done:
+	return 0;
+}
+
+struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
+{
+	struct hfs_find_data fd;
+	struct inode *inode;
+	int err;
+
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+
+	INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list);
+	mutex_init(&HFSPLUS_I(inode)->extents_lock);
+	HFSPLUS_I(inode)->flags = 0;
+	HFSPLUS_I(inode)->rsrc_inode = NULL;
+	atomic_set(&HFSPLUS_I(inode)->opencnt, 0);
+
+	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
+	    inode->i_ino == HFSPLUS_ROOT_CNID) {
+		hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
+		err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
+		if (!err)
+			err = hfsplus_cat_read_inode(inode, &fd);
+		hfs_find_exit(&fd);
+	} else {
+		err = hfsplus_system_read_inode(inode);
+	}
+
+	if (err) {
+		iget_failed(inode);
+		return ERR_PTR(err);
+	}
+
 	unlock_new_inode(inode);
 	return inode;
+}
 
-bad_inode:
-	iget_failed(inode);
-	return ERR_PTR(err);
+static int hfsplus_system_write_inode(struct inode *inode)
+{
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
+	struct hfsplus_vh *vhdr = sbi->s_vhdr;
+	struct hfsplus_fork_raw *fork;
+	struct hfs_btree *tree = NULL;
+
+	switch (inode->i_ino) {
+	case HFSPLUS_EXT_CNID:
+		fork = &vhdr->ext_file;
+		tree = sbi->ext_tree;
+		break;
+	case HFSPLUS_CAT_CNID:
+		fork = &vhdr->cat_file;
+		tree = sbi->cat_tree;
+		break;
+	case HFSPLUS_ALLOC_CNID:
+		fork = &vhdr->alloc_file;
+		break;
+	case HFSPLUS_START_CNID:
+		fork = &vhdr->start_file;
+		break;
+	case HFSPLUS_ATTR_CNID:
+		fork = &vhdr->attr_file;
+		tree = sbi->attr_tree;
+	default:
+		return -EIO;
+	}
+
+	if (fork->total_size != cpu_to_be64(inode->i_size)) {
+		set_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags);
+		inode->i_sb->s_dirt = 1;
+	}
+	hfsplus_inode_write_fork(inode, fork);
+	if (tree)
+		hfs_btree_write(tree);
+	return 0;
 }
 
 static int hfsplus_write_inode(struct inode *inode,
 		struct writeback_control *wbc)
 {
-	struct hfsplus_vh *vhdr;
-	int ret = 0;
-
 	dprint(DBG_INODE, "hfsplus_write_inode: %lu\n", inode->i_ino);
+
 	hfsplus_ext_write_extent(inode);
-	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID) {
+
+	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
+	    inode->i_ino == HFSPLUS_ROOT_CNID)
 		return hfsplus_cat_write_inode(inode);
-	}
-	vhdr = HFSPLUS_SB(inode->i_sb).s_vhdr;
-	switch (inode->i_ino) {
-	case HFSPLUS_ROOT_CNID:
-		ret = hfsplus_cat_write_inode(inode);
-		break;
-	case HFSPLUS_EXT_CNID:
-		if (vhdr->ext_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->ext_file);
-		hfs_btree_write(HFSPLUS_SB(inode->i_sb).ext_tree);
-		break;
-	case HFSPLUS_CAT_CNID:
-		if (vhdr->cat_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->cat_file);
-		hfs_btree_write(HFSPLUS_SB(inode->i_sb).cat_tree);
-		break;
-	case HFSPLUS_ALLOC_CNID:
-		if (vhdr->alloc_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->alloc_file);
-		break;
-	case HFSPLUS_START_CNID:
-		if (vhdr->start_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->start_file);
-		break;
-	case HFSPLUS_ATTR_CNID:
-		if (vhdr->attr_file.total_size != cpu_to_be64(inode->i_size)) {
-			HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-			inode->i_sb->s_dirt = 1;
-		}
-		hfsplus_inode_write_fork(inode, &vhdr->attr_file);
-		hfs_btree_write(HFSPLUS_SB(inode->i_sb).attr_tree);
-		break;
-	}
-	return ret;
+	else
+		return hfsplus_system_write_inode(inode);
 }
 
 static void hfsplus_evict_inode(struct inode *inode)
@@ -151,51 +148,53 @@
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
 	if (HFSPLUS_IS_RSRC(inode)) {
-		HFSPLUS_I(HFSPLUS_I(inode).rsrc_inode).rsrc_inode = NULL;
-		iput(HFSPLUS_I(inode).rsrc_inode);
+		HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
+		iput(HFSPLUS_I(inode)->rsrc_inode);
 	}
 }
 
 int hfsplus_sync_fs(struct super_block *sb, int wait)
 {
-	struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+	struct hfsplus_vh *vhdr = sbi->s_vhdr;
 
 	dprint(DBG_SUPER, "hfsplus_write_super\n");
 
-	lock_super(sb);
+	mutex_lock(&sbi->vh_mutex);
+	mutex_lock(&sbi->alloc_mutex);
 	sb->s_dirt = 0;
 
-	vhdr->free_blocks = cpu_to_be32(HFSPLUS_SB(sb).free_blocks);
-	vhdr->next_alloc = cpu_to_be32(HFSPLUS_SB(sb).next_alloc);
-	vhdr->next_cnid = cpu_to_be32(HFSPLUS_SB(sb).next_cnid);
-	vhdr->folder_count = cpu_to_be32(HFSPLUS_SB(sb).folder_count);
-	vhdr->file_count = cpu_to_be32(HFSPLUS_SB(sb).file_count);
+	vhdr->free_blocks = cpu_to_be32(sbi->free_blocks);
+	vhdr->next_cnid = cpu_to_be32(sbi->next_cnid);
+	vhdr->folder_count = cpu_to_be32(sbi->folder_count);
+	vhdr->file_count = cpu_to_be32(sbi->file_count);
 
-	mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-	if (HFSPLUS_SB(sb).flags & HFSPLUS_SB_WRITEBACKUP) {
-		if (HFSPLUS_SB(sb).sect_count) {
+	mark_buffer_dirty(sbi->s_vhbh);
+	if (test_and_clear_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags)) {
+		if (sbi->sect_count) {
 			struct buffer_head *bh;
 			u32 block, offset;
 
-			block = HFSPLUS_SB(sb).blockoffset;
-			block += (HFSPLUS_SB(sb).sect_count - 2) >> (sb->s_blocksize_bits - 9);
-			offset = ((HFSPLUS_SB(sb).sect_count - 2) << 9) & (sb->s_blocksize - 1);
-			printk(KERN_DEBUG "hfs: backup: %u,%u,%u,%u\n", HFSPLUS_SB(sb).blockoffset,
-				HFSPLUS_SB(sb).sect_count, block, offset);
+			block = sbi->blockoffset;
+			block += (sbi->sect_count - 2) >> (sb->s_blocksize_bits - 9);
+			offset = ((sbi->sect_count - 2) << 9) & (sb->s_blocksize - 1);
+			printk(KERN_DEBUG "hfs: backup: %u,%u,%u,%u\n",
+					  sbi->blockoffset, sbi->sect_count,
+					  block, offset);
 			bh = sb_bread(sb, block);
 			if (bh) {
 				vhdr = (struct hfsplus_vh *)(bh->b_data + offset);
 				if (be16_to_cpu(vhdr->signature) == HFSPLUS_VOLHEAD_SIG) {
-					memcpy(vhdr, HFSPLUS_SB(sb).s_vhdr, sizeof(*vhdr));
+					memcpy(vhdr, sbi->s_vhdr, sizeof(*vhdr));
 					mark_buffer_dirty(bh);
 					brelse(bh);
 				} else
 					printk(KERN_WARNING "hfs: backup not found!\n");
 			}
 		}
-		HFSPLUS_SB(sb).flags &= ~HFSPLUS_SB_WRITEBACKUP;
 	}
-	unlock_super(sb);
+	mutex_unlock(&sbi->alloc_mutex);
+	mutex_unlock(&sbi->vh_mutex);
 	return 0;
 }
 
@@ -209,48 +208,48 @@
 
 static void hfsplus_put_super(struct super_block *sb)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+
 	dprint(DBG_SUPER, "hfsplus_put_super\n");
+
 	if (!sb->s_fs_info)
 		return;
 
-	lock_kernel();
-
 	if (sb->s_dirt)
 		hfsplus_write_super(sb);
-	if (!(sb->s_flags & MS_RDONLY) && HFSPLUS_SB(sb).s_vhdr) {
-		struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+	if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) {
+		struct hfsplus_vh *vhdr = sbi->s_vhdr;
 
 		vhdr->modify_date = hfsp_now2mt();
 		vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_UNMNT);
 		vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_INCNSTNT);
-		mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-		sync_dirty_buffer(HFSPLUS_SB(sb).s_vhbh);
+		mark_buffer_dirty(sbi->s_vhbh);
+		sync_dirty_buffer(sbi->s_vhbh);
 	}
 
-	hfs_btree_close(HFSPLUS_SB(sb).cat_tree);
-	hfs_btree_close(HFSPLUS_SB(sb).ext_tree);
-	iput(HFSPLUS_SB(sb).alloc_file);
-	iput(HFSPLUS_SB(sb).hidden_dir);
-	brelse(HFSPLUS_SB(sb).s_vhbh);
-	unload_nls(HFSPLUS_SB(sb).nls);
+	hfs_btree_close(sbi->cat_tree);
+	hfs_btree_close(sbi->ext_tree);
+	iput(sbi->alloc_file);
+	iput(sbi->hidden_dir);
+	brelse(sbi->s_vhbh);
+	unload_nls(sbi->nls);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
-
-	unlock_kernel();
 }
 
 static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = HFSPLUS_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
-	buf->f_blocks = HFSPLUS_SB(sb).total_blocks << HFSPLUS_SB(sb).fs_shift;
-	buf->f_bfree = HFSPLUS_SB(sb).free_blocks << HFSPLUS_SB(sb).fs_shift;
+	buf->f_blocks = sbi->total_blocks << sbi->fs_shift;
+	buf->f_bfree = sbi->free_blocks << sbi->fs_shift;
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = 0xFFFFFFFF;
-	buf->f_ffree = 0xFFFFFFFF - HFSPLUS_SB(sb).next_cnid;
+	buf->f_ffree = 0xFFFFFFFF - sbi->next_cnid;
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = HFSPLUS_MAX_STRLEN;
@@ -263,11 +262,11 @@
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
 	if (!(*flags & MS_RDONLY)) {
-		struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+		struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr;
 		struct hfsplus_sb_info sbi;
 
 		memset(&sbi, 0, sizeof(struct hfsplus_sb_info));
-		sbi.nls = HFSPLUS_SB(sb).nls;
+		sbi.nls = HFSPLUS_SB(sb)->nls;
 		if (!hfsplus_parse_options(data, &sbi))
 			return -EINVAL;
 
@@ -276,7 +275,7 @@
 			       "running fsck.hfsplus is recommended.  leaving read-only.\n");
 			sb->s_flags |= MS_RDONLY;
 			*flags |= MS_RDONLY;
-		} else if (sbi.flags & HFSPLUS_SB_FORCE) {
+		} else if (test_bit(HFSPLUS_SB_FORCE, &sbi.flags)) {
 			/* nothing */
 		} else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
 			printk(KERN_WARNING "hfs: filesystem is marked locked, leaving read-only.\n");
@@ -320,7 +319,8 @@
 		return -ENOMEM;
 
 	sb->s_fs_info = sbi;
-	INIT_HLIST_HEAD(&sbi->rsrc_inodes);
+	mutex_init(&sbi->alloc_mutex);
+	mutex_init(&sbi->vh_mutex);
 	hfsplus_fill_defaults(sbi);
 	if (!hfsplus_parse_options(data, sbi)) {
 		printk(KERN_ERR "hfs: unable to parse mount options\n");
@@ -344,7 +344,7 @@
 		err = -EINVAL;
 		goto cleanup;
 	}
-	vhdr = HFSPLUS_SB(sb).s_vhdr;
+	vhdr = sbi->s_vhdr;
 
 	/* Copy parts of the volume header into the superblock */
 	sb->s_magic = HFSPLUS_VOLHEAD_SIG;
@@ -353,18 +353,19 @@
 		printk(KERN_ERR "hfs: wrong filesystem version\n");
 		goto cleanup;
 	}
-	HFSPLUS_SB(sb).total_blocks = be32_to_cpu(vhdr->total_blocks);
-	HFSPLUS_SB(sb).free_blocks = be32_to_cpu(vhdr->free_blocks);
-	HFSPLUS_SB(sb).next_alloc = be32_to_cpu(vhdr->next_alloc);
-	HFSPLUS_SB(sb).next_cnid = be32_to_cpu(vhdr->next_cnid);
-	HFSPLUS_SB(sb).file_count = be32_to_cpu(vhdr->file_count);
-	HFSPLUS_SB(sb).folder_count = be32_to_cpu(vhdr->folder_count);
-	HFSPLUS_SB(sb).data_clump_blocks = be32_to_cpu(vhdr->data_clump_sz) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-	if (!HFSPLUS_SB(sb).data_clump_blocks)
-		HFSPLUS_SB(sb).data_clump_blocks = 1;
-	HFSPLUS_SB(sb).rsrc_clump_blocks = be32_to_cpu(vhdr->rsrc_clump_sz) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-	if (!HFSPLUS_SB(sb).rsrc_clump_blocks)
-		HFSPLUS_SB(sb).rsrc_clump_blocks = 1;
+	sbi->total_blocks = be32_to_cpu(vhdr->total_blocks);
+	sbi->free_blocks = be32_to_cpu(vhdr->free_blocks);
+	sbi->next_cnid = be32_to_cpu(vhdr->next_cnid);
+	sbi->file_count = be32_to_cpu(vhdr->file_count);
+	sbi->folder_count = be32_to_cpu(vhdr->folder_count);
+	sbi->data_clump_blocks =
+		be32_to_cpu(vhdr->data_clump_sz) >> sbi->alloc_blksz_shift;
+	if (!sbi->data_clump_blocks)
+		sbi->data_clump_blocks = 1;
+	sbi->rsrc_clump_blocks =
+		be32_to_cpu(vhdr->rsrc_clump_sz) >> sbi->alloc_blksz_shift;
+	if (!sbi->rsrc_clump_blocks)
+		sbi->rsrc_clump_blocks = 1;
 
 	/* Set up operations so we can load metadata */
 	sb->s_op = &hfsplus_sops;
@@ -374,7 +375,7 @@
 		printk(KERN_WARNING "hfs: Filesystem was not cleanly unmounted, "
 		       "running fsck.hfsplus is recommended.  mounting read-only.\n");
 		sb->s_flags |= MS_RDONLY;
-	} else if (sbi->flags & HFSPLUS_SB_FORCE) {
+	} else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) {
 		/* nothing */
 	} else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
 		printk(KERN_WARNING "hfs: Filesystem is marked locked, mounting read-only.\n");
@@ -384,16 +385,15 @@
 		       "use the force option at your own risk, mounting read-only.\n");
 		sb->s_flags |= MS_RDONLY;
 	}
-	sbi->flags &= ~HFSPLUS_SB_FORCE;
 
 	/* Load metadata objects (B*Trees) */
-	HFSPLUS_SB(sb).ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
-	if (!HFSPLUS_SB(sb).ext_tree) {
+	sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
+	if (!sbi->ext_tree) {
 		printk(KERN_ERR "hfs: failed to load extents file\n");
 		goto cleanup;
 	}
-	HFSPLUS_SB(sb).cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
-	if (!HFSPLUS_SB(sb).cat_tree) {
+	sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
+	if (!sbi->cat_tree) {
 		printk(KERN_ERR "hfs: failed to load catalog file\n");
 		goto cleanup;
 	}
@@ -404,7 +404,7 @@
 		err = PTR_ERR(inode);
 		goto cleanup;
 	}
-	HFSPLUS_SB(sb).alloc_file = inode;
+	sbi->alloc_file = inode;
 
 	/* Load the root directory */
 	root = hfsplus_iget(sb, HFSPLUS_ROOT_CNID);
@@ -423,7 +423,7 @@
 
 	str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
 	str.name = HFSP_HIDDENDIR_NAME;
-	hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+	hfs_find_init(sbi->cat_tree, &fd);
 	hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
 	if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
 		hfs_find_exit(&fd);
@@ -434,7 +434,7 @@
 			err = PTR_ERR(inode);
 			goto cleanup;
 		}
-		HFSPLUS_SB(sb).hidden_dir = inode;
+		sbi->hidden_dir = inode;
 	} else
 		hfs_find_exit(&fd);
 
@@ -449,15 +449,19 @@
 	be32_add_cpu(&vhdr->write_count, 1);
 	vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
 	vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
-	mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-	sync_dirty_buffer(HFSPLUS_SB(sb).s_vhbh);
+	mark_buffer_dirty(sbi->s_vhbh);
+	sync_dirty_buffer(sbi->s_vhbh);
 
-	if (!HFSPLUS_SB(sb).hidden_dir) {
+	if (!sbi->hidden_dir) {
 		printk(KERN_DEBUG "hfs: create hidden dir...\n");
-		HFSPLUS_SB(sb).hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
-		hfsplus_create_cat(HFSPLUS_SB(sb).hidden_dir->i_ino, sb->s_root->d_inode,
-				   &str, HFSPLUS_SB(sb).hidden_dir);
-		mark_inode_dirty(HFSPLUS_SB(sb).hidden_dir);
+
+		mutex_lock(&sbi->vh_mutex);
+		sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
+		hfsplus_create_cat(sbi->hidden_dir->i_ino, sb->s_root->d_inode,
+				   &str, sbi->hidden_dir);
+		mutex_unlock(&sbi->vh_mutex);
+
+		mark_inode_dirty(sbi->hidden_dir);
 	}
 out:
 	unload_nls(sbi->nls);
@@ -486,7 +490,7 @@
 
 static void hfsplus_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(hfsplus_inode_cachep, &HFSPLUS_I(inode));
+	kmem_cache_free(hfsplus_inode_cachep, HFSPLUS_I(inode));
 }
 
 #define HFSPLUS_INODE_SIZE	sizeof(struct hfsplus_inode_info)
diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
index 628ccf6..b66d67d 100644
--- a/fs/hfsplus/unicode.c
+++ b/fs/hfsplus/unicode.c
@@ -121,7 +121,7 @@
 int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, char *astr, int *len_p)
 {
 	const hfsplus_unichr *ip;
-	struct nls_table *nls = HFSPLUS_SB(sb).nls;
+	struct nls_table *nls = HFSPLUS_SB(sb)->nls;
 	u8 *op;
 	u16 cc, c0, c1;
 	u16 *ce1, *ce2;
@@ -132,7 +132,7 @@
 	ustrlen = be16_to_cpu(ustr->length);
 	len = *len_p;
 	ce1 = NULL;
-	compose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+	compose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 
 	while (ustrlen > 0) {
 		c0 = be16_to_cpu(*ip++);
@@ -246,7 +246,7 @@
 static inline int asc2unichar(struct super_block *sb, const char *astr, int len,
 			      wchar_t *uc)
 {
-	int size = HFSPLUS_SB(sb).nls->char2uni(astr, len, uc);
+	int size = HFSPLUS_SB(sb)->nls->char2uni(astr, len, uc);
 	if (size <= 0) {
 		*uc = '?';
 		size = 1;
@@ -293,7 +293,7 @@
 	u16 *dstr, outlen = 0;
 	wchar_t c;
 
-	decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 	while (outlen < HFSPLUS_MAX_STRLEN && len > 0) {
 		size = asc2unichar(sb, astr, len, &c);
 
@@ -330,8 +330,8 @@
 	wchar_t c;
 	u16 c2;
 
-	casefold = (HFSPLUS_SB(sb).flags & HFSPLUS_SB_CASEFOLD);
-	decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+	casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
+	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 	hash = init_name_hash();
 	astr = str->name;
 	len = str->len;
@@ -373,8 +373,8 @@
 	u16 c1, c2;
 	wchar_t c;
 
-	casefold = (HFSPLUS_SB(sb).flags & HFSPLUS_SB_CASEFOLD);
-	decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+	casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
+	decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 	astr1 = s1->name;
 	len1 = s1->len;
 	astr2 = s2->name;
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index bed78ac8..8972c20 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -65,8 +65,8 @@
 	*start = 0;
 	*size = sb->s_bdev->bd_inode->i_size >> 9;
 
-	if (HFSPLUS_SB(sb).session >= 0) {
-		te.cdte_track = HFSPLUS_SB(sb).session;
+	if (HFSPLUS_SB(sb)->session >= 0) {
+		te.cdte_track = HFSPLUS_SB(sb)->session;
 		te.cdte_format = CDROM_LBA;
 		res = ioctl_by_bdev(sb->s_bdev, CDROMREADTOCENTRY, (unsigned long)&te);
 		if (!res && (te.cdte_ctrl & CDROM_DATA_TRACK) == 4) {
@@ -87,6 +87,7 @@
 /* Takes in super block, returns true if good data read */
 int hfsplus_read_wrapper(struct super_block *sb)
 {
+	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
 	struct buffer_head *bh;
 	struct hfsplus_vh *vhdr;
 	struct hfsplus_wd wd;
@@ -122,7 +123,7 @@
 		if (vhdr->signature == cpu_to_be16(HFSPLUS_VOLHEAD_SIG))
 			break;
 		if (vhdr->signature == cpu_to_be16(HFSPLUS_VOLHEAD_SIGX)) {
-			HFSPLUS_SB(sb).flags |= HFSPLUS_SB_HFSX;
+			set_bit(HFSPLUS_SB_HFSX, &sbi->flags);
 			break;
 		}
 		brelse(bh);
@@ -143,11 +144,11 @@
 	if (blocksize < HFSPLUS_SECTOR_SIZE ||
 	    ((blocksize - 1) & blocksize))
 		return -EINVAL;
-	HFSPLUS_SB(sb).alloc_blksz = blocksize;
-	HFSPLUS_SB(sb).alloc_blksz_shift = 0;
+	sbi->alloc_blksz = blocksize;
+	sbi->alloc_blksz_shift = 0;
 	while ((blocksize >>= 1) != 0)
-		HFSPLUS_SB(sb).alloc_blksz_shift++;
-	blocksize = min(HFSPLUS_SB(sb).alloc_blksz, (u32)PAGE_SIZE);
+		sbi->alloc_blksz_shift++;
+	blocksize = min(sbi->alloc_blksz, (u32)PAGE_SIZE);
 
 	/* align block size to block offset */
 	while (part_start & ((blocksize >> HFSPLUS_SECTOR_SHIFT) - 1))
@@ -158,23 +159,26 @@
 		return -EINVAL;
 	}
 
-	HFSPLUS_SB(sb).blockoffset = part_start >>
-			(sb->s_blocksize_bits - HFSPLUS_SECTOR_SHIFT);
-	HFSPLUS_SB(sb).sect_count = part_size;
-	HFSPLUS_SB(sb).fs_shift = HFSPLUS_SB(sb).alloc_blksz_shift -
-			sb->s_blocksize_bits;
+	sbi->blockoffset =
+		part_start >> (sb->s_blocksize_bits - HFSPLUS_SECTOR_SHIFT);
+	sbi->sect_count = part_size;
+	sbi->fs_shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
 
 	bh = sb_bread512(sb, part_start + HFSPLUS_VOLHEAD_SECTOR, vhdr);
 	if (!bh)
 		return -EIO;
 
 	/* should still be the same... */
-	if (vhdr->signature != (HFSPLUS_SB(sb).flags & HFSPLUS_SB_HFSX ?
-				cpu_to_be16(HFSPLUS_VOLHEAD_SIGX) :
-				cpu_to_be16(HFSPLUS_VOLHEAD_SIG)))
-		goto error;
-	HFSPLUS_SB(sb).s_vhbh = bh;
-	HFSPLUS_SB(sb).s_vhdr = vhdr;
+	if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+		if (vhdr->signature != cpu_to_be16(HFSPLUS_VOLHEAD_SIGX))
+			goto error;
+	} else {
+		if (vhdr->signature != cpu_to_be16(HFSPLUS_VOLHEAD_SIG))
+			goto error;
+	}
+
+	sbi->s_vhbh = bh;
+	sbi->s_vhdr = vhdr;
 
 	return 0;
  error:
diff --git a/fs/hpfs/Kconfig b/fs/hpfs/Kconfig
index 56bd15c..63b6f56 100644
--- a/fs/hpfs/Kconfig
+++ b/fs/hpfs/Kconfig
@@ -1,6 +1,7 @@
 config HPFS_FS
 	tristate "OS/2 HPFS file system support"
 	depends on BLOCK
+	depends on BKL # nontrivial to fix
 	help
 	  OS/2 is IBM's operating system for PC's, the same as Warp, and HPFS
 	  is the file system used for organizing files on OS/2 hard disk
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 2607010..c969a1a 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -477,11 +477,15 @@
 
 	int o;
 
+	lock_kernel();
+
 	save_mount_options(s, options);
 
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
-	if (!sbi)
+	if (!sbi) {
+		unlock_kernel();
 		return -ENOMEM;
+	}
 	s->s_fs_info = sbi;
 
 	sbi->sb_bmp_dir = NULL;
@@ -666,6 +670,7 @@
 			root->i_blocks = 5;
 		hpfs_brelse4(&qbh);
 	}
+	unlock_kernel();
 	return 0;
 
 bail4:	brelse(bh2);
@@ -677,6 +682,7 @@
 	kfree(sbi->sb_cp_table);
 	s->s_fs_info = NULL;
 	kfree(sbi);
+	unlock_kernel();
 	return -EINVAL;
 }
 
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 7b02772..4e2a45e 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -598,6 +598,7 @@
 	.readdir	= hppfs_readdir,
 	.open		= hppfs_dir_open,
 	.fsync		= hppfs_fsync,
+	.llseek		= default_llseek,
 };
 
 static int hppfs_statfs(struct dentry *dentry, struct kstatfs *sf)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 6e5bd42..113eba3 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -674,6 +674,7 @@
 	.mmap			= hugetlbfs_file_mmap,
 	.fsync			= noop_fsync,
 	.get_unmapped_area	= hugetlb_get_unmapped_area,
+	.llseek		= default_llseek,
 };
 
 static const struct inode_operations hugetlbfs_dir_inode_operations = {
diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c
index e0aca9a..0542b6e 100644
--- a/fs/isofs/dir.c
+++ b/fs/isofs/dir.c
@@ -10,7 +10,6 @@
  *
  *  isofs directory handling functions
  */
-#include <linux/smp_lock.h>
 #include <linux/gfp.h>
 #include "isofs.h"
 
@@ -255,18 +254,19 @@
 	char *tmpname;
 	struct iso_directory_record *tmpde;
 	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb);
 
 	tmpname = (char *)__get_free_page(GFP_KERNEL);
 	if (tmpname == NULL)
 		return -ENOMEM;
 
-	lock_kernel();
+	mutex_lock(&sbi->s_mutex);
 	tmpde = (struct iso_directory_record *) (tmpname+1024);
 
 	result = do_isofs_readdir(inode, filp, dirent, filldir, tmpname, tmpde);
 
 	free_page((unsigned long) tmpname);
-	unlock_kernel();
+	mutex_unlock(&sbi->s_mutex);
 	return result;
 }
 
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 5a44811..09ff41a 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -17,7 +17,6 @@
 #include <linux/slab.h>
 #include <linux/nls.h>
 #include <linux/ctype.h>
-#include <linux/smp_lock.h>
 #include <linux/statfs.h>
 #include <linux/cdrom.h>
 #include <linux/parser.h>
@@ -44,11 +43,7 @@
 	struct isofs_sb_info *sbi = ISOFS_SB(sb);
 
 #ifdef CONFIG_JOLIET
-	lock_kernel();
-
 	unload_nls(sbi->s_nls_iocharset);
-
-	unlock_kernel();
 #endif
 
 	kfree(sbi);
@@ -823,6 +818,7 @@
 	sbi->s_utf8 = opt.utf8;
 	sbi->s_nocompress = opt.nocompress;
 	sbi->s_overriderockperm = opt.overriderockperm;
+	mutex_init(&sbi->s_mutex);
 	/*
 	 * It would be incredibly stupid to allow people to mark every file
 	 * on the disk as suid, so we merely allow them to set the default
@@ -977,8 +973,6 @@
 	int section, rv, error;
 	struct iso_inode_info *ei = ISOFS_I(inode);
 
-	lock_kernel();
-
 	error = -EIO;
 	rv = 0;
 	if (iblock < 0 || iblock != iblock_s) {
@@ -1054,7 +1048,6 @@
 
 	error = 0;
 abort:
-	unlock_kernel();
 	return rv != 0 ? rv : error;
 }
 
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 7d33de8..2882dc0 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -55,6 +55,7 @@
 	gid_t s_gid;
 	uid_t s_uid;
 	struct nls_table *s_nls_iocharset; /* Native language support table */
+	struct mutex s_mutex; /* replaces BKL, please remove if possible */
 };
 
 #define ISOFS_INVALID_MODE ((mode_t) -1)
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index ab438be..0d23abf 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -6,7 +6,6 @@
  *  (C) 1991  Linus Torvalds - minix filesystem
  */
 
-#include <linux/smp_lock.h>
 #include <linux/gfp.h>
 #include "isofs.h"
 
@@ -168,6 +167,7 @@
 	int found;
 	unsigned long uninitialized_var(block);
 	unsigned long uninitialized_var(offset);
+	struct isofs_sb_info *sbi = ISOFS_SB(dir->i_sb);
 	struct inode *inode;
 	struct page *page;
 
@@ -177,7 +177,7 @@
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
-	lock_kernel();
+	mutex_lock(&sbi->s_mutex);
 	found = isofs_find_entry(dir, dentry,
 				&block, &offset,
 				page_address(page),
@@ -188,10 +188,10 @@
 	if (found) {
 		inode = isofs_iget(dir->i_sb, block, offset);
 		if (IS_ERR(inode)) {
-			unlock_kernel();
+			mutex_unlock(&sbi->s_mutex);
 			return ERR_CAST(inode);
 		}
 	}
-	unlock_kernel();
+	mutex_unlock(&sbi->s_mutex);
 	return d_splice_alias(inode, dentry);
 }
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index 96a685c..f9cd04d 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -8,7 +8,6 @@
 
 #include <linux/slab.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 
 #include "isofs.h"
 #include "rock.h"
@@ -661,6 +660,7 @@
 {
 	struct inode *inode = page->mapping->host;
 	struct iso_inode_info *ei = ISOFS_I(inode);
+	struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb);
 	char *link = kmap(page);
 	unsigned long bufsize = ISOFS_BUFFER_SIZE(inode);
 	struct buffer_head *bh;
@@ -673,12 +673,12 @@
 	struct rock_state rs;
 	int ret;
 
-	if (!ISOFS_SB(inode->i_sb)->s_rock)
+	if (!sbi->s_rock)
 		goto error;
 
 	init_rock_state(&rs, inode);
 	block = ei->i_iget5_block;
-	lock_kernel();
+	mutex_lock(&sbi->s_mutex);
 	bh = sb_bread(inode->i_sb, block);
 	if (!bh)
 		goto out_noread;
@@ -748,7 +748,7 @@
 		goto fail;
 	brelse(bh);
 	*rpnt = '\0';
-	unlock_kernel();
+	mutex_unlock(&sbi->s_mutex);
 	SetPageUptodate(page);
 	kunmap(page);
 	unlock_page(page);
@@ -765,7 +765,7 @@
 	printk("symlink spans iso9660 blocks\n");
 fail:
 	brelse(bh);
-	unlock_kernel();
+	mutex_unlock(&sbi->s_mutex);
 error:
 	SetPageError(page);
 	kunmap(page);
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 95d8c11..85a6883 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -137,34 +137,10 @@
 	JBUFFER_TRACE(descriptor, "write commit block");
 	set_buffer_dirty(bh);
 
-	if (journal->j_flags & JFS_BARRIER) {
-		ret = __sync_dirty_buffer(bh, WRITE_SYNC | WRITE_BARRIER);
-
-		/*
-		 * Is it possible for another commit to fail at roughly
-		 * the same time as this one?  If so, we don't want to
-		 * trust the barrier flag in the super, but instead want
-		 * to remember if we sent a barrier request
-		 */
-		if (ret == -EOPNOTSUPP) {
-			char b[BDEVNAME_SIZE];
-
-			printk(KERN_WARNING
-				"JBD: barrier-based sync failed on %s - "
-				"disabling barriers\n",
-				bdevname(journal->j_dev, b));
-			spin_lock(&journal->j_state_lock);
-			journal->j_flags &= ~JFS_BARRIER;
-			spin_unlock(&journal->j_state_lock);
-
-			/* And try again, without the barrier */
-			set_buffer_uptodate(bh);
-			set_buffer_dirty(bh);
-			ret = sync_dirty_buffer(bh);
-		}
-	} else {
+	if (journal->j_flags & JFS_BARRIER)
+		ret = __sync_dirty_buffer(bh, WRITE_SYNC | WRITE_FLUSH_FUA);
+	else
 		ret = sync_dirty_buffer(bh);
-	}
 
 	put_bh(bh);		/* One for getblk() */
 	journal_put_journal_head(descriptor);
@@ -318,7 +294,7 @@
 	int first_tag = 0;
 	int tag_flag;
 	int i;
-	int write_op = WRITE;
+	int write_op = WRITE_SYNC;
 
 	/*
 	 * First job: lock down the current transaction and wait for
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 5247e7f..6571a05 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -532,8 +532,7 @@
 	 */
 	if ((journal->j_fs_dev != journal->j_dev) &&
 	    (journal->j_flags & JBD2_BARRIER))
-		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL,
-			BLKDEV_IFL_WAIT);
+		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
 	if (!(journal->j_flags & JBD2_ABORT))
 		jbd2_journal_update_superblock(journal, 1);
 	return 0;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 7c068c1..bc6be8b 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -134,25 +134,11 @@
 
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !JBD2_HAS_INCOMPAT_FEATURE(journal,
-				       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
-		ret = submit_bh(WRITE_SYNC_PLUG | WRITE_BARRIER, bh);
-		if (ret == -EOPNOTSUPP) {
-			printk(KERN_WARNING
-			       "JBD2: Disabling barriers on %s, "
-			       "not supported by device\n", journal->j_devname);
-			write_lock(&journal->j_state_lock);
-			journal->j_flags &= ~JBD2_BARRIER;
-			write_unlock(&journal->j_state_lock);
-
-			/* And try again, without the barrier */
-			lock_buffer(bh);
-			set_buffer_uptodate(bh);
-			clear_buffer_dirty(bh);
-			ret = submit_bh(WRITE_SYNC_PLUG, bh);
-		}
-	} else {
+				       JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT))
+		ret = submit_bh(WRITE_SYNC_PLUG | WRITE_FLUSH_FUA, bh);
+	else
 		ret = submit_bh(WRITE_SYNC_PLUG, bh);
-	}
+
 	*cbh = bh;
 	return ret;
 }
@@ -166,29 +152,8 @@
 {
 	int ret = 0;
 
-retry:
 	clear_buffer_dirty(bh);
 	wait_on_buffer(bh);
-	if (buffer_eopnotsupp(bh) && (journal->j_flags & JBD2_BARRIER)) {
-		printk(KERN_WARNING
-		       "JBD2: %s: disabling barries on %s - not supported "
-		       "by device\n", __func__, journal->j_devname);
-		write_lock(&journal->j_state_lock);
-		journal->j_flags &= ~JBD2_BARRIER;
-		write_unlock(&journal->j_state_lock);
-
-		lock_buffer(bh);
-		clear_buffer_dirty(bh);
-		set_buffer_uptodate(bh);
-		bh->b_end_io = journal_end_buffer_io_sync;
-
-		ret = submit_bh(WRITE_SYNC_PLUG, bh);
-		if (ret) {
-			unlock_buffer(bh);
-			return ret;
-		}
-		goto retry;
-	}
 
 	if (unlikely(!buffer_uptodate(bh)))
 		ret = -EIO;
@@ -360,7 +325,7 @@
 	int tag_bytes = journal_tag_bytes(journal);
 	struct buffer_head *cbh = NULL; /* For transactional checksums */
 	__u32 crc32_sum = ~0;
-	int write_op = WRITE;
+	int write_op = WRITE_SYNC;
 
 	/*
 	 * First job: lock down the current transaction and wait for
@@ -701,29 +666,6 @@
 		}
 	}
 
-	/* 
-	 * If the journal is not located on the file system device,
-	 * then we must flush the file system device before we issue
-	 * the commit record
-	 */
-	if (commit_transaction->t_flushed_data_blocks &&
-	    (journal->j_fs_dev != journal->j_dev) &&
-	    (journal->j_flags & JBD2_BARRIER))
-		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL,
-			BLKDEV_IFL_WAIT);
-
-	/* Done it all: now write the commit record asynchronously. */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-				      JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
-		err = journal_submit_commit_record(journal, commit_transaction,
-						 &cbh, crc32_sum);
-		if (err)
-			__jbd2_journal_abort_hard(journal);
-		if (journal->j_flags & JBD2_BARRIER)
-			blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL,
-				BLKDEV_IFL_WAIT);
-	}
-
 	err = journal_finish_inode_data_buffers(journal, commit_transaction);
 	if (err) {
 		printk(KERN_WARNING
@@ -734,6 +676,25 @@
 		err = 0;
 	}
 
+	/* 
+	 * If the journal is not located on the file system device,
+	 * then we must flush the file system device before we issue
+	 * the commit record
+	 */
+	if (commit_transaction->t_flushed_data_blocks &&
+	    (journal->j_fs_dev != journal->j_dev) &&
+	    (journal->j_flags & JBD2_BARRIER))
+		blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+
+	/* Done it all: now write the commit record asynchronously. */
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal,
+				      JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+		err = journal_submit_commit_record(journal, commit_transaction,
+						 &cbh, crc32_sum);
+		if (err)
+			__jbd2_journal_abort_hard(journal);
+	}
+
 	/* Lo and behold: we have just managed to send a transaction to
            the log.  Before we can commit it, wait for the IO so far to
            complete.  Control buffers being written are on the
@@ -845,6 +806,11 @@
 	}
 	if (!err && !is_journal_aborted(journal))
 		err = journal_wait_on_commit_record(journal, cbh);
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal,
+				      JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) &&
+	    journal->j_flags & JBD2_BARRIER) {
+		blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL);
+	}
 
 	if (err)
 		jbd2_journal_abort(journal, err);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0e8014e..262419f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1371,6 +1371,10 @@
 
 	if (!compat && !ro && !incompat)
 		return 1;
+	/* Load journal superblock if it is not loaded yet. */
+	if (journal->j_format_version == 0 &&
+	    journal_get_superblock(journal) != 0)
+		return 0;
 	if (journal->j_format_version == 1)
 		return 0;
 
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 6b2964a..d9beb06 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -21,7 +21,6 @@
 #include <linux/vmalloc.h>
 #include <linux/vfs.h>
 #include <linux/crc32.h>
-#include <linux/smp_lock.h>
 #include "nodelist.h"
 
 static int jffs2_flash_setup(struct jffs2_sb_info *c);
@@ -391,7 +390,6 @@
 	   This also catches the case where it was stopped and this
 	   is just a remount to restart it.
 	   Flush the writebuffer, if neccecary, else we loose it */
-	lock_kernel();
 	if (!(sb->s_flags & MS_RDONLY)) {
 		jffs2_stop_garbage_collect_thread(c);
 		mutex_lock(&c->alloc_sem);
@@ -403,8 +401,6 @@
 		jffs2_start_garbage_collect_thread(c);
 
 	*flags |= MS_NOATIME;
-
-	unlock_kernel();
 	return 0;
 }
 
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 662bba0..d1ae5df 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/fs.h>
@@ -146,6 +145,7 @@
 static int jffs2_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct jffs2_sb_info *c;
+	int ret;
 
 	D1(printk(KERN_DEBUG "jffs2_get_sb_mtd():"
 		  " New superblock for device %d (\"%s\")\n",
@@ -175,7 +175,8 @@
 #ifdef CONFIG_JFFS2_FS_POSIX_ACL
 	sb->s_flags |= MS_POSIXACL;
 #endif
-	return jffs2_do_fill_super(sb, data, silent);
+	ret = jffs2_do_fill_super(sb, data, silent);
+	return ret;
 }
 
 static int jffs2_get_sb(struct file_system_type *fs_type,
@@ -192,8 +193,6 @@
 
 	D2(printk(KERN_DEBUG "jffs2: jffs2_put_super()\n"));
 
-	lock_kernel();
-
 	if (sb->s_dirt)
 		jffs2_write_super(sb);
 
@@ -215,8 +214,6 @@
 	if (c->mtd->sync)
 		c->mtd->sync(c->mtd);
 
-	unlock_kernel();
-
 	D1(printk(KERN_DEBUG "jffs2_put_super returning\n"));
 }
 
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index ec8c3e4..68eee2b 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -33,7 +33,6 @@
 #include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 
 #include "jfs_incore.h"
 #include "jfs_filsys.h"
@@ -176,8 +175,6 @@
 
 	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
-	lock_kernel();
-
 	rc = jfs_umount(sb);
 	if (rc)
 		jfs_err("jfs_umount failed with return code %d", rc);
@@ -188,8 +185,6 @@
 	iput(sbi->direct_inode);
 
 	kfree(sbi);
-
-	unlock_kernel();
 }
 
 enum {
@@ -369,19 +364,16 @@
 	if (!parse_options(data, sb, &newLVSize, &flag)) {
 		return -EINVAL;
 	}
-	lock_kernel();
+
 	if (newLVSize) {
 		if (sb->s_flags & MS_RDONLY) {
 			printk(KERN_ERR
 		  "JFS: resize requires volume to be mounted read-write\n");
-			unlock_kernel();
 			return -EROFS;
 		}
 		rc = jfs_extendfs(sb, newLVSize, 0);
-		if (rc) {
-			unlock_kernel();
+		if (rc)
 			return rc;
-		}
 	}
 
 	if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {
@@ -397,36 +389,30 @@
 		/* mark the fs r/w for quota activity */
 		sb->s_flags &= ~MS_RDONLY;
 
-		unlock_kernel();
 		dquot_resume(sb, -1);
 		return ret;
 	}
 	if ((!(sb->s_flags & MS_RDONLY)) && (*flags & MS_RDONLY)) {
 		rc = dquot_suspend(sb, -1);
 		if (rc < 0) {
-			unlock_kernel();
 			return rc;
 		}
 		rc = jfs_umount_rw(sb);
 		JFS_SBI(sb)->flag = flag;
-		unlock_kernel();
 		return rc;
 	}
 	if ((JFS_SBI(sb)->flag & JFS_NOINTEGRITY) != (flag & JFS_NOINTEGRITY))
 		if (!(sb->s_flags & MS_RDONLY)) {
 			rc = jfs_umount_rw(sb);
-			if (rc) {
-				unlock_kernel();
+			if (rc)
 				return rc;
-			}
+
 			JFS_SBI(sb)->flag = flag;
 			ret = jfs_mount_rw(sb, 1);
-			unlock_kernel();
 			return ret;
 		}
 	JFS_SBI(sb)->flag = flag;
 
-	unlock_kernel();
 	return 0;
 }
 
@@ -446,6 +432,7 @@
 	sbi = kzalloc(sizeof (struct jfs_sb_info), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
+
 	sb->s_fs_info = sbi;
 	sbi->sb = sb;
 	sbi->uid = sbi->gid = sbi->umask = -1;
diff --git a/fs/libfs.c b/fs/libfs.c
index 0a9da95..62baa03 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -913,6 +913,35 @@
 }
 EXPORT_SYMBOL(generic_file_fsync);
 
+/**
+ * generic_check_addressable - Check addressability of file system
+ * @blocksize_bits:	log of file system block size
+ * @num_blocks:		number of blocks in file system
+ *
+ * Determine whether a file system with @num_blocks blocks (and a
+ * block size of 2**@blocksize_bits) is addressable by the sector_t
+ * and page cache of the system.  Return 0 if so and -EFBIG otherwise.
+ */
+int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks)
+{
+	u64 last_fs_block = num_blocks - 1;
+	u64 last_fs_page =
+		last_fs_block >> (PAGE_CACHE_SHIFT - blocksize_bits);
+
+	if (unlikely(num_blocks == 0))
+		return 0;
+
+	if ((blocksize_bits < 9) || (blocksize_bits > PAGE_CACHE_SHIFT))
+		return -EINVAL;
+
+	if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) ||
+	    (last_fs_page > (pgoff_t)(~0ULL))) {
+		return -EFBIG;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(generic_check_addressable);
+
 /*
  * No-op implementation of ->fsync for in-memory filesystems.
  */
diff --git a/fs/locks.c b/fs/locks.c
index ab24d49..8b2b6ad 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -143,6 +143,22 @@
 static LIST_HEAD(file_lock_list);
 static LIST_HEAD(blocked_list);
 
+/*
+ * Protects the two list heads above, plus the inode->i_flock list
+ * FIXME: should use a spinlock, once lockd and ceph are ready.
+ */
+void lock_flocks(void)
+{
+	lock_kernel();
+}
+EXPORT_SYMBOL_GPL(lock_flocks);
+
+void unlock_flocks(void)
+{
+	unlock_kernel();
+}
+EXPORT_SYMBOL_GPL(unlock_flocks);
+
 static struct kmem_cache *filelock_cache __read_mostly;
 
 /* Allocate an empty lock structure. */
@@ -511,9 +527,9 @@
  */
 static void locks_delete_block(struct file_lock *waiter)
 {
-	lock_kernel();
+	lock_flocks();
 	__locks_delete_block(waiter);
-	unlock_kernel();
+	unlock_flocks();
 }
 
 /* Insert waiter into blocker's block list.
@@ -644,7 +660,7 @@
 {
 	struct file_lock *cfl;
 
-	lock_kernel();
+	lock_flocks();
 	for (cfl = filp->f_path.dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) {
 		if (!IS_POSIX(cfl))
 			continue;
@@ -657,7 +673,7 @@
 			fl->fl_pid = pid_vnr(cfl->fl_nspid);
 	} else
 		fl->fl_type = F_UNLCK;
-	unlock_kernel();
+	unlock_flocks();
 	return;
 }
 EXPORT_SYMBOL(posix_test_lock);
@@ -730,18 +746,16 @@
 	int error = 0;
 	int found = 0;
 
-	lock_kernel();
+	if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) {
+		new_fl = locks_alloc_lock();
+		if (!new_fl)
+			return -ENOMEM;
+	}
+
+	lock_flocks();
 	if (request->fl_flags & FL_ACCESS)
 		goto find_conflict;
 
-	if (request->fl_type != F_UNLCK) {
-		error = -ENOMEM;
-		new_fl = locks_alloc_lock();
-		if (new_fl == NULL)
-			goto out;
-		error = 0;
-	}
-
 	for_each_lock(inode, before) {
 		struct file_lock *fl = *before;
 		if (IS_POSIX(fl))
@@ -767,8 +781,11 @@
 	 * If a higher-priority process was blocked on the old file lock,
 	 * give it the opportunity to lock the file.
 	 */
-	if (found)
+	if (found) {
+		unlock_flocks();
 		cond_resched();
+		lock_flocks();
+	}
 
 find_conflict:
 	for_each_lock(inode, before) {
@@ -794,7 +811,7 @@
 	error = 0;
 
 out:
-	unlock_kernel();
+	unlock_flocks();
 	if (new_fl)
 		locks_free_lock(new_fl);
 	return error;
@@ -823,7 +840,7 @@
 		new_fl2 = locks_alloc_lock();
 	}
 
-	lock_kernel();
+	lock_flocks();
 	if (request->fl_type != F_UNLCK) {
 		for_each_lock(inode, before) {
 			fl = *before;
@@ -991,7 +1008,7 @@
 		locks_wake_up_blocks(left);
 	}
  out:
-	unlock_kernel();
+	unlock_flocks();
 	/*
 	 * Free any unused locks.
 	 */
@@ -1066,14 +1083,14 @@
 	/*
 	 * Search the lock list for this inode for any POSIX locks.
 	 */
-	lock_kernel();
+	lock_flocks();
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!IS_POSIX(fl))
 			continue;
 		if (fl->fl_owner != owner)
 			break;
 	}
-	unlock_kernel();
+	unlock_flocks();
 	return fl ? -EAGAIN : 0;
 }
 
@@ -1186,7 +1203,7 @@
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 
-	lock_kernel();
+	lock_flocks();
 
 	time_out_leases(inode);
 
@@ -1247,8 +1264,10 @@
 			break_time++;
 	}
 	locks_insert_block(flock, new_fl);
+	unlock_flocks();
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
 						!new_fl->fl_next, break_time);
+	lock_flocks();
 	__locks_delete_block(new_fl);
 	if (error >= 0) {
 		if (error == 0)
@@ -1263,7 +1282,7 @@
 	}
 
 out:
-	unlock_kernel();
+	unlock_flocks();
 	if (!IS_ERR(new_fl))
 		locks_free_lock(new_fl);
 	return error;
@@ -1319,7 +1338,7 @@
 	struct file_lock *fl;
 	int type = F_UNLCK;
 
-	lock_kernel();
+	lock_flocks();
 	time_out_leases(filp->f_path.dentry->d_inode);
 	for (fl = filp->f_path.dentry->d_inode->i_flock; fl && IS_LEASE(fl);
 			fl = fl->fl_next) {
@@ -1328,7 +1347,7 @@
 			break;
 		}
 	}
-	unlock_kernel();
+	unlock_flocks();
 	return type;
 }
 
@@ -1341,7 +1360,7 @@
  *	The (input) flp->fl_lmops->fl_break function is required
  *	by break_lease().
  *
- *	Called with kernel lock held.
+ *	Called with file_lock_lock held.
  */
 int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 {
@@ -1436,7 +1455,15 @@
 }
 EXPORT_SYMBOL(generic_setlease);
 
- /**
+static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
+{
+	if (filp->f_op && filp->f_op->setlease)
+		return filp->f_op->setlease(filp, arg, lease);
+	else
+		return generic_setlease(filp, arg, lease);
+}
+
+/**
  *	vfs_setlease        -       sets a lease on an open file
  *	@filp: file pointer
  *	@arg: type of lease to obtain
@@ -1467,12 +1494,9 @@
 {
 	int error;
 
-	lock_kernel();
-	if (filp->f_op && filp->f_op->setlease)
-		error = filp->f_op->setlease(filp, arg, lease);
-	else
-		error = generic_setlease(filp, arg, lease);
-	unlock_kernel();
+	lock_flocks();
+	error = __vfs_setlease(filp, arg, lease);
+	unlock_flocks();
 
 	return error;
 }
@@ -1499,9 +1523,9 @@
 	if (error)
 		return error;
 
-	lock_kernel();
+	lock_flocks();
 
-	error = vfs_setlease(filp, arg, &flp);
+	error = __vfs_setlease(filp, arg, &flp);
 	if (error || arg == F_UNLCK)
 		goto out_unlock;
 
@@ -1516,7 +1540,7 @@
 
 	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
 out_unlock:
-	unlock_kernel();
+	unlock_flocks();
 	return error;
 }
 
@@ -2020,7 +2044,7 @@
 			fl.fl_ops->fl_release_private(&fl);
 	}
 
-	lock_kernel();
+	lock_flocks();
 	before = &inode->i_flock;
 
 	while ((fl = *before) != NULL) {
@@ -2038,7 +2062,7 @@
  		}
 		before = &fl->fl_next;
 	}
-	unlock_kernel();
+	unlock_flocks();
 }
 
 /**
@@ -2053,12 +2077,12 @@
 {
 	int status = 0;
 
-	lock_kernel();
+	lock_flocks();
 	if (waiter->fl_next)
 		__locks_delete_block(waiter);
 	else
 		status = -ENOENT;
-	unlock_kernel();
+	unlock_flocks();
 	return status;
 }
 
@@ -2172,7 +2196,7 @@
 
 static void *locks_start(struct seq_file *f, loff_t *pos)
 {
-	lock_kernel();
+	lock_flocks();
 	f->private = (void *)1;
 	return seq_list_start(&file_lock_list, *pos);
 }
@@ -2184,7 +2208,7 @@
 
 static void locks_stop(struct seq_file *f, void *v)
 {
-	unlock_kernel();
+	unlock_flocks();
 }
 
 static const struct seq_operations locks_seq_operations = {
@@ -2231,7 +2255,7 @@
 {
 	struct file_lock *fl;
 	int result = 1;
-	lock_kernel();
+	lock_flocks();
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (IS_POSIX(fl)) {
 			if (fl->fl_type == F_RDLCK)
@@ -2248,7 +2272,7 @@
 		result = 0;
 		break;
 	}
-	unlock_kernel();
+	unlock_flocks();
 	return result;
 }
 
@@ -2271,7 +2295,7 @@
 {
 	struct file_lock *fl;
 	int result = 1;
-	lock_kernel();
+	lock_flocks();
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (IS_POSIX(fl)) {
 			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
@@ -2286,7 +2310,7 @@
 		result = 0;
 		break;
 	}
-	unlock_kernel();
+	unlock_flocks();
 	return result;
 }
 
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index 9777eb5..1eb4e89 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -827,4 +827,5 @@
 	.unlocked_ioctl	= logfs_ioctl,
 	.readdir	= logfs_readdir,
 	.read		= generic_read_dir,
+	.llseek		= default_llseek,
 };
diff --git a/fs/namespace.c b/fs/namespace.c
index a72eaab..7ca5182 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1744,9 +1744,7 @@
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	lock_kernel();
 	mnt = do_kern_mount(type, flags, name, data);
-	unlock_kernel();
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 9578cbe..aac8832e 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -95,6 +95,34 @@
 };
 
 
+#define ncp_namespace(i)	(NCP_SERVER(i)->name_space[NCP_FINFO(i)->volNumber])
+
+static inline int ncp_preserve_entry_case(struct inode *i, __u32 nscreator)
+{
+#ifdef CONFIG_NCPFS_SMALLDOS
+	int ns = ncp_namespace(i);
+
+	if ((ns == NW_NS_DOS)
+#ifdef CONFIG_NCPFS_OS2_NS
+		|| ((ns == NW_NS_OS2) && (nscreator == NW_NS_DOS))
+#endif /* CONFIG_NCPFS_OS2_NS */
+	   )
+		return 0;
+#endif /* CONFIG_NCPFS_SMALLDOS */
+	return 1;
+}
+
+#define ncp_preserve_case(i)	(ncp_namespace(i) != NW_NS_DOS)
+
+static inline int ncp_case_sensitive(struct dentry *dentry)
+{
+#ifdef CONFIG_NCPFS_NFS_NS
+	return ncp_namespace(dentry->d_inode) == NW_NS_NFS;
+#else
+	return 0;
+#endif /* CONFIG_NCPFS_NFS_NS */
+}
+
 /*
  * Note: leave the hash unchanged if the directory
  * is case-sensitive.
@@ -102,13 +130,12 @@
 static int 
 ncp_hash_dentry(struct dentry *dentry, struct qstr *this)
 {
-	struct nls_table *t;
-	unsigned long hash;
-	int i;
+	if (!ncp_case_sensitive(dentry)) {
+		struct nls_table *t;
+		unsigned long hash;
+		int i;
 
-	t = NCP_IO_TABLE(dentry);
-
-	if (!ncp_case_sensitive(dentry->d_inode)) {
+		t = NCP_IO_TABLE(dentry);
 		hash = init_name_hash();
 		for (i=0; i<this->len ; i++)
 			hash = partial_name_hash(ncp_tolower(t, this->name[i]),
@@ -124,7 +151,7 @@
 	if (a->len != b->len)
 		return 1;
 
-	if (ncp_case_sensitive(dentry->d_inode))
+	if (ncp_case_sensitive(dentry))
 		return strncmp(a->name, b->name, a->len);
 
 	return ncp_strnicmp(NCP_IO_TABLE(dentry), a->name, b->name, a->len);
@@ -266,7 +293,7 @@
 
 
 static int
-__ncp_lookup_validate(struct dentry *dentry)
+ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd)
 {
 	struct ncp_server *server;
 	struct dentry *parent;
@@ -283,9 +310,6 @@
 
 	server = NCP_SERVER(dir);
 
-	if (!ncp_conn_valid(server))
-		goto finished;
-
 	/*
 	 * Inspired by smbfs:
 	 * The default validation is based on dentry age:
@@ -304,8 +328,11 @@
 	if (ncp_is_server_root(dir)) {
 		res = ncp_io2vol(server, __name, &len, dentry->d_name.name,
 				 dentry->d_name.len, 1);
-		if (!res)
+		if (!res) {
 			res = ncp_lookup_volume(server, __name, &(finfo.i));
+			if (!res)
+				ncp_update_known_namespace(server, finfo.i.volNumber, NULL);
+		}
 	} else {
 		res = ncp_io2vol(server, __name, &len, dentry->d_name.name,
 				 dentry->d_name.len, !ncp_preserve_case(dir));
@@ -320,13 +347,17 @@
 	 * what we remember, it's not valid any more.
 	 */
 	if (!res) {
-		if (finfo.i.dirEntNum == NCP_FINFO(dentry->d_inode)->dirEntNum) {
+		struct inode *inode = dentry->d_inode;
+
+		mutex_lock(&inode->i_mutex);
+		if (finfo.i.dirEntNum == NCP_FINFO(inode)->dirEntNum) {
 			ncp_new_dentry(dentry);
 			val=1;
 		} else
 			DDPRINTK("ncp_lookup_validate: found, but dirEntNum changed\n");
 
-		ncp_update_inode2(dentry->d_inode, &finfo);
+		ncp_update_inode2(inode, &finfo);
+		mutex_unlock(&inode->i_mutex);
 	}
 
 finished:
@@ -335,16 +366,6 @@
 	return val;
 }
 
-static int
-ncp_lookup_validate(struct dentry * dentry, struct nameidata *nd)
-{
-	int res;
-	lock_kernel();
-	res = __ncp_lookup_validate(dentry);
-	unlock_kernel();
-	return res;
-}
-
 static struct dentry *
 ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 {
@@ -411,8 +432,6 @@
 	int result, mtime_valid = 0;
 	time_t mtime = 0;
 
-	lock_kernel();
-
 	ctl.page  = NULL;
 	ctl.cache = NULL;
 
@@ -421,6 +440,7 @@
 		(int) filp->f_pos);
 
 	result = -EIO;
+	/* Do not generate '.' and '..' when server is dead. */
 	if (!ncp_conn_valid(server))
 		goto out;
 
@@ -532,6 +552,12 @@
 	ctl.head.end = ctl.fpos - 1;
 	ctl.head.eof = ctl.valid;
 finished:
+	if (ctl.page) {
+		kunmap(ctl.page);
+		SetPageUptodate(ctl.page);
+		unlock_page(ctl.page);
+		page_cache_release(ctl.page);
+	}
 	if (page) {
 		cache->head = ctl.head;
 		kunmap(page);
@@ -539,23 +565,17 @@
 		unlock_page(page);
 		page_cache_release(page);
 	}
-	if (ctl.page) {
-		kunmap(ctl.page);
-		SetPageUptodate(ctl.page);
-		unlock_page(ctl.page);
-		page_cache_release(ctl.page);
-	}
 out:
-	unlock_kernel();
 	return result;
 }
 
 static int
 ncp_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
-		struct ncp_cache_control *ctrl, struct ncp_entry_info *entry)
+		struct ncp_cache_control *ctrl, struct ncp_entry_info *entry,
+		int inval_childs)
 {
 	struct dentry *newdent, *dentry = filp->f_path.dentry;
-	struct inode *newino, *inode = dentry->d_inode;
+	struct inode *dir = dentry->d_inode;
 	struct ncp_cache_control ctl = *ctrl;
 	struct qstr qname;
 	int valid = 0;
@@ -564,9 +584,9 @@
 	__u8 __name[NCP_MAXPATHLEN + 1];
 
 	qname.len = sizeof(__name);
-	if (ncp_vol2io(NCP_SERVER(inode), __name, &qname.len,
+	if (ncp_vol2io(NCP_SERVER(dir), __name, &qname.len,
 			entry->i.entryName, entry->i.nameLen,
-			!ncp_preserve_entry_case(inode, entry->i.NSCreator)))
+			!ncp_preserve_entry_case(dir, entry->i.NSCreator)))
 		return 1; /* I'm not sure */
 
 	qname.name = __name;
@@ -584,22 +604,64 @@
 			goto end_advance;
 	} else {
 		hashed = 1;
-		memcpy((char *) newdent->d_name.name, qname.name,
-							newdent->d_name.len);
+
+		/* If case sensitivity changed for this volume, all entries below this one
+		   should be thrown away.  This entry itself is not affected, as its case
+		   sensitivity is controlled by its own parent. */
+		if (inval_childs)
+			shrink_dcache_parent(newdent);
+
+		/*
+		 * It is not as dangerous as it looks.  NetWare's OS2 namespace is
+		 * case preserving yet case insensitive.  So we update dentry's name
+		 * as received from server.  We found dentry via d_lookup with our
+		 * hash, so we know that hash does not change, and so replacing name
+		 * should be reasonably safe.
+		 */
+		if (qname.len == newdent->d_name.len &&
+		    memcmp(newdent->d_name.name, qname.name, newdent->d_name.len)) {
+			struct inode *inode = newdent->d_inode;
+
+			/*
+			 * Inside ncpfs all uses of d_name are either for debugging,
+			 * or on functions which acquire inode mutex (mknod, creat,
+			 * lookup).  So grab i_mutex here, to be sure.  d_path
+			 * uses dcache_lock when generating path, so we should too.
+			 * And finally d_compare is protected by dentry's d_lock, so
+			 * here we go.
+			 */
+			if (inode)
+				mutex_lock(&inode->i_mutex);
+			spin_lock(&dcache_lock);
+			spin_lock(&newdent->d_lock);
+			memcpy((char *) newdent->d_name.name, qname.name,
+								newdent->d_name.len);
+			spin_unlock(&newdent->d_lock);
+			spin_unlock(&dcache_lock);
+			if (inode)
+				mutex_unlock(&inode->i_mutex);
+		}
 	}
 
 	if (!newdent->d_inode) {
+		struct inode *inode;
+
 		entry->opened = 0;
-		entry->ino = iunique(inode->i_sb, 2);
-		newino = ncp_iget(inode->i_sb, entry);
-		if (newino) {
+		entry->ino = iunique(dir->i_sb, 2);
+		inode = ncp_iget(dir->i_sb, entry);
+		if (inode) {
 			newdent->d_op = &ncp_dentry_operations;
-			d_instantiate(newdent, newino);
+			d_instantiate(newdent, inode);
 			if (!hashed)
 				d_rehash(newdent);
 		}
-	} else
-		ncp_update_inode2(newdent->d_inode, entry);
+	} else {
+		struct inode *inode = newdent->d_inode;
+
+		mutex_lock(&inode->i_mutex);
+		ncp_update_inode2(inode, entry);
+		mutex_unlock(&inode->i_mutex);
+	}
 
 	if (newdent->d_inode) {
 		ino = newdent->d_inode->i_ino;
@@ -617,7 +679,7 @@
 		ctl.cache = NULL;
 		ctl.idx  -= NCP_DIRCACHE_SIZE;
 		ctl.ofs  += 1;
-		ctl.page  = grab_cache_page(&inode->i_data, ctl.ofs);
+		ctl.page  = grab_cache_page(&dir->i_data, ctl.ofs);
 		if (ctl.page)
 			ctl.cache = kmap(ctl.page);
 	}
@@ -633,7 +695,7 @@
 		if (!ino)
 			ino = find_inode_number(dentry, &qname);
 		if (!ino)
-			ino = iunique(inode->i_sb, 2);
+			ino = iunique(dir->i_sb, 2);
 		ctl.filled = filldir(dirent, qname.name, qname.len,
 				     filp->f_pos, ino, DT_UNKNOWN);
 		if (!ctl.filled)
@@ -660,6 +722,7 @@
 			(unsigned long) filp->f_pos);
 
 	for (i = 0; i < NCP_NUMBER_OF_VOLUMES; i++) {
+		int inval_dentry;
 
 		if (ncp_get_volume_info_with_number(server, i, &info) != 0)
 			return;
@@ -675,8 +738,9 @@
 				info.volume_name);
 			continue;
 		}
+		inval_dentry = ncp_update_known_namespace(server, entry.i.volNumber, NULL);
 		entry.volume = entry.i.volNumber;
-		if (!ncp_fill_cache(filp, dirent, filldir, ctl, &entry))
+		if (!ncp_fill_cache(filp, dirent, filldir, ctl, &entry, inval_dentry))
 			return;
 	}
 }
@@ -739,7 +803,7 @@
 			rpl += onerpl;
 			rpls -= onerpl;
 			entry.volume = entry.i.volNumber;
-			if (!ncp_fill_cache(filp, dirent, filldir, ctl, &entry))
+			if (!ncp_fill_cache(filp, dirent, filldir, ctl, &entry, 0))
 				break;
 		}
 	} while (more);
@@ -775,17 +839,19 @@
 		if (dent) {
 			struct inode* ino = dent->d_inode;
 			if (ino) {
+				ncp_update_known_namespace(server, volNumber, NULL);
 				NCP_FINFO(ino)->volNumber = volNumber;
 				NCP_FINFO(ino)->dirEntNum = dirEntNum;
 				NCP_FINFO(ino)->DosDirNum = DosDirNum;
+				result = 0;
 			} else {
 				DPRINTK("ncpfs: sb->s_root->d_inode == NULL!\n");
 			}
 		} else {
 			DPRINTK("ncpfs: sb->s_root == NULL!\n");
 		}
-	}
-	result = 0;
+	} else
+		result = 0;
 
 out:
 	return result;
@@ -799,7 +865,6 @@
 	int error, res, len;
 	__u8 __name[NCP_MAXPATHLEN + 1];
 
-	lock_kernel();
 	error = -EIO;
 	if (!ncp_conn_valid(server))
 		goto finished;
@@ -813,6 +878,8 @@
 				 dentry->d_name.len, 1);
 		if (!res)
 			res = ncp_lookup_volume(server, __name, &(finfo.i));
+			if (!res)
+				ncp_update_known_namespace(server, finfo.i.volNumber, NULL);
 	} else {
 		res = ncp_io2vol(server, __name, &len, dentry->d_name.name,
 				 dentry->d_name.len, !ncp_preserve_case(dir));
@@ -846,7 +913,6 @@
 
 finished:
 	PPRINTK("ncp_lookup: result=%d\n", error);
-	unlock_kernel();
 	return ERR_PTR(error);
 }
 
@@ -887,11 +953,6 @@
 	PPRINTK("ncp_create_new: creating %s/%s, mode=%x\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name, mode);
 
-	error = -EIO;
-	lock_kernel();
-	if (!ncp_conn_valid(server))
-		goto out;
-
 	ncp_age_dentry(server, dentry);
 	len = sizeof(__name);
 	error = ncp_io2vol(server, __name, &len, dentry->d_name.name,
@@ -917,6 +978,8 @@
 		if (result) {
 			if (result == 0x87)
 				error = -ENAMETOOLONG;
+			else if (result < 0)
+				error = result;
 			DPRINTK("ncp_create: %s/%s failed\n",
 				dentry->d_parent->d_name.name, dentry->d_name.name);
 			goto out;
@@ -935,7 +998,6 @@
 
 	error = ncp_instantiate(dir, dentry, &finfo);
 out:
-	unlock_kernel();
 	return error;
 }
 
@@ -955,11 +1017,6 @@
 	DPRINTK("ncp_mkdir: making %s/%s\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	error = -EIO;
-	lock_kernel();
-	if (!ncp_conn_valid(server))
-		goto out;
-
 	ncp_age_dentry(server, dentry);
 	len = sizeof(__name);
 	error = ncp_io2vol(server, __name, &len, dentry->d_name.name,
@@ -967,12 +1024,11 @@
 	if (error)
 		goto out;
 
-	error = -EACCES;
-	if (ncp_open_create_file_or_subdir(server, dir, __name,
+	error = ncp_open_create_file_or_subdir(server, dir, __name,
 					   OC_MODE_CREATE, aDIR,
 					   cpu_to_le16(0xffff),
-					   &finfo) == 0)
-	{
+					   &finfo);
+	if (error == 0) {
 		if (ncp_is_nfs_extras(server, finfo.volume)) {
 			mode |= S_IFDIR;
 			finfo.i.nfs.mode = mode;
@@ -983,9 +1039,10 @@
 				goto out;
 		}
 		error = ncp_instantiate(dir, dentry, &finfo);
+	} else if (error > 0) {
+		error = -EACCES;
 	}
 out:
-	unlock_kernel();
 	return error;
 }
 
@@ -998,11 +1055,6 @@
 	DPRINTK("ncp_rmdir: removing %s/%s\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	error = -EIO;
-	lock_kernel();
-	if (!ncp_conn_valid(server))
-		goto out;
-
 	error = -EBUSY;
 	if (!d_unhashed(dentry))
 		goto out;
@@ -1036,11 +1088,10 @@
 			error = -ENOENT;
 			break;
 		default:
-			error = -EACCES;
+			error = result < 0 ? result : -EACCES;
 			break;
        	}
 out:
-	unlock_kernel();
 	return error;
 }
 
@@ -1050,15 +1101,10 @@
 	struct ncp_server *server;
 	int error;
 
-	lock_kernel();
 	server = NCP_SERVER(dir);
 	DPRINTK("ncp_unlink: unlinking %s/%s\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 	
-	error = -EIO;
-	if (!ncp_conn_valid(server))
-		goto out;
-
 	/*
 	 * Check whether to close the file ...
 	 */
@@ -1097,12 +1143,9 @@
 			error = -ENOENT;
 			break;
 		default:
-			error = -EACCES;
+			error = error < 0 ? error : -EACCES;
 			break;
 	}
-		
-out:
-	unlock_kernel();
 	return error;
 }
 
@@ -1118,11 +1161,6 @@
 		old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		new_dentry->d_parent->d_name.name, new_dentry->d_name.name);
 
-	error = -EIO;
-	lock_kernel();
-	if (!ncp_conn_valid(server))
-		goto out;
-
 	ncp_age_dentry(server, old_dentry);
 	ncp_age_dentry(server, new_dentry);
 
@@ -1161,11 +1199,10 @@
 			error = -ENOENT;
 			break;
 		default:
-			error = -EACCES;
+			error = error < 0 ? error : -EACCES;
 			break;
 	}
 out:
-	unlock_kernel();
 	return error;
 }
 
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 3639cc5..6c754f7 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -113,9 +113,6 @@
 	DPRINTK("ncp_file_read: enter %s/%s\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	if (!ncp_conn_valid(NCP_SERVER(inode)))
-		return -EIO;
-
 	pos = *ppos;
 
 	if ((ssize_t) count < 0) {
@@ -192,13 +189,11 @@
 
 	DPRINTK("ncp_file_write: enter %s/%s\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name);
-	if (!ncp_conn_valid(NCP_SERVER(inode)))
-		return -EIO;
 	if ((ssize_t) count < 0)
 		return -EINVAL;
 	pos = *ppos;
 	if (file->f_flags & O_APPEND) {
-		pos = inode->i_size;
+		pos = i_size_read(inode);
 	}
 
 	if (pos + count > MAX_NON_LFS && !(file->f_flags&O_LARGEFILE)) {
@@ -264,8 +259,11 @@
 
 	*ppos = pos;
 
-	if (pos > inode->i_size) {
-		inode->i_size = pos;
+	if (pos > i_size_read(inode)) {
+		mutex_lock(&inode->i_mutex);
+		if (pos > i_size_read(inode))
+			i_size_write(inode, pos);
+		mutex_unlock(&inode->i_mutex);
 	}
 	DPRINTK("ncp_file_write: exit %s/%s\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name);
@@ -281,18 +279,9 @@
 	return 0;
 }
 
-static loff_t ncp_remote_llseek(struct file *file, loff_t offset, int origin)
-{
-	loff_t ret;
-	lock_kernel();
-	ret = generic_file_llseek_unlocked(file, offset, origin);
-	unlock_kernel();
-	return ret;
-}
-
 const struct file_operations ncp_file_operations =
 {
-	.llseek 	= ncp_remote_llseek,
+	.llseek		= generic_file_llseek,
 	.read		= ncp_file_read,
 	.write		= ncp_file_write,
 	.unlocked_ioctl	= ncp_ioctl,
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index b4de38c..985fabb 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -139,7 +139,7 @@
 		inode->i_mode = nwi->nfs.mode;
 	}
 
-	inode->i_blocks = (inode->i_size + NCP_BLOCK_SIZE - 1) >> NCP_BLOCK_SHIFT;
+	inode->i_blocks = (i_size_read(inode) + NCP_BLOCK_SIZE - 1) >> NCP_BLOCK_SHIFT;
 
 	inode->i_mtime.tv_sec = ncp_date_dos2unix(nwi->modifyTime, nwi->modifyDate);
 	inode->i_ctime.tv_sec = ncp_date_dos2unix(nwi->creationTime, nwi->creationDate);
@@ -158,18 +158,21 @@
 		inode->i_mode = server->m.dir_mode;
 		/* for directories dataStreamSize seems to be some
 		   Object ID ??? */
-		inode->i_size = NCP_BLOCK_SIZE;
+		i_size_write(inode, NCP_BLOCK_SIZE);
 	} else {
+		u32 size;
+
 		inode->i_mode = server->m.file_mode;
-		inode->i_size = le32_to_cpu(nwi->dataStreamSize);
+		size = le32_to_cpu(nwi->dataStreamSize);
+		i_size_write(inode, size);
 #ifdef CONFIG_NCPFS_EXTRAS
 		if ((server->m.flags & (NCP_MOUNT_EXTRAS|NCP_MOUNT_SYMLINKS)) 
 		 && (nwi->attributes & aSHARED)) {
 			switch (nwi->attributes & (aHIDDEN|aSYSTEM)) {
 				case aHIDDEN:
 					if (server->m.flags & NCP_MOUNT_SYMLINKS) {
-						if (/* (inode->i_size >= NCP_MIN_SYMLINK_SIZE)
-						 && */ (inode->i_size <= NCP_MAX_SYMLINK_SIZE)) {
+						if (/* (size >= NCP_MIN_SYMLINK_SIZE)
+						 && */ (size <= NCP_MAX_SYMLINK_SIZE)) {
 							inode->i_mode = (inode->i_mode & ~S_IFMT) | S_IFLNK;
 							NCP_FINFO(inode)->flags |= NCPI_KLUDGE_SYMLINK;
 							break;
@@ -208,7 +211,7 @@
 }
 
 /*
- * Fill in the inode based on the ncp_entry_info structure.
+ * Fill in the inode based on the ncp_entry_info structure.  Used only for brand new inodes.
  */
 static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo)
 {
@@ -254,6 +257,7 @@
 	if (inode) {
 		atomic_set(&NCP_FINFO(inode)->opened, info->opened);
 
+		inode->i_mapping->backing_dev_info = sb->s_bdi;
 		inode->i_ino = info->ino;
 		ncp_set_attr(inode, info);
 		if (S_ISREG(inode->i_mode)) {
@@ -299,10 +303,12 @@
 
 static void ncp_stop_tasks(struct ncp_server *server) {
 	struct sock* sk = server->ncp_sock->sk;
-		
+
+	lock_sock(sk);
 	sk->sk_error_report = server->error_report;
 	sk->sk_data_ready   = server->data_ready;
 	sk->sk_write_space  = server->write_space;
+	release_sock(sk);
 	del_timer_sync(&server->timeout_tm);
 	flush_scheduled_work();
 }
@@ -565,10 +571,12 @@
 /*	server->conn_status = 0;	*/
 /*	server->root_dentry = NULL;	*/
 /*	server->root_setuped = 0;	*/
+	mutex_init(&server->root_setup_lock);
 #ifdef CONFIG_NCPFS_PACKET_SIGNING
 /*	server->sign_wanted = 0;	*/
 /*	server->sign_active = 0;	*/
 #endif
+	init_rwsem(&server->auth_rwsem);
 	server->auth.auth_type = NCP_AUTH_NONE;
 /*	server->auth.object_name_len = 0;	*/
 /*	server->auth.object_name = NULL;	*/
@@ -593,16 +601,12 @@
 	server->nls_io = load_nls_default();
 #endif /* CONFIG_NCPFS_NLS */
 
-	server->dentry_ttl = 0;	/* no caching */
+	atomic_set(&server->dentry_ttl, 0);	/* no caching */
 
 	INIT_LIST_HEAD(&server->tx.requests);
 	mutex_init(&server->rcv.creq_mutex);
 	server->tx.creq		= NULL;
 	server->rcv.creq	= NULL;
-	server->data_ready	= sock->sk->sk_data_ready;
-	server->write_space	= sock->sk->sk_write_space;
-	server->error_report	= sock->sk->sk_error_report;
-	sock->sk->sk_user_data	= server;
 
 	init_timer(&server->timeout_tm);
 #undef NCP_PACKET_SIZE
@@ -619,6 +623,11 @@
 	if (server->rxbuf == NULL)
 		goto out_txbuf;
 
+	lock_sock(sock->sk);
+	server->data_ready	= sock->sk->sk_data_ready;
+	server->write_space	= sock->sk->sk_write_space;
+	server->error_report	= sock->sk->sk_error_report;
+	sock->sk->sk_user_data	= server;
 	sock->sk->sk_data_ready	  = ncp_tcp_data_ready;
 	sock->sk->sk_error_report = ncp_tcp_error_report;
 	if (sock->type == SOCK_STREAM) {
@@ -634,6 +643,7 @@
 		server->timeout_tm.data = (unsigned long)server;
 		server->timeout_tm.function = ncpdgram_timeout_call;
 	}
+	release_sock(sock->sk);
 
 	ncp_lock_server(server);
 	error = ncp_connect(server);
@@ -658,8 +668,10 @@
 				goto out_disconnect;
 			}
 		}
+		ncp_lock_server(server);
 		if (options & 2)
 			server->sign_wanted = 1;
+		ncp_unlock_server(server);
 	}
 	else 
 #endif	/* CONFIG_NCPFS_PACKET_SIGNING */
@@ -720,6 +732,9 @@
 	unload_nls(server->nls_io);
 	unload_nls(server->nls_vol);
 #endif
+	mutex_destroy(&server->rcv.creq_mutex);
+	mutex_destroy(&server->root_setup_lock);
+	mutex_destroy(&server->mutex);
 out_fput2:
 	if (server->info_filp)
 		fput(server->info_filp);
@@ -743,8 +758,6 @@
 {
 	struct ncp_server *server = NCP_SBP(sb);
 
-	lock_kernel();
-
 	ncp_lock_server(server);
 	ncp_disconnect(server);
 	ncp_unlock_server(server);
@@ -756,6 +769,9 @@
 	unload_nls(server->nls_vol);
 	unload_nls(server->nls_io);
 #endif /* CONFIG_NCPFS_NLS */
+	mutex_destroy(&server->rcv.creq_mutex);
+	mutex_destroy(&server->root_setup_lock);
+	mutex_destroy(&server->mutex);
 
 	if (server->info_filp)
 		fput(server->info_filp);
@@ -771,8 +787,6 @@
 	vfree(server->packet);
 	sb->s_fs_info = NULL;
 	kfree(server);
-
-	unlock_kernel();
 }
 
 static int ncp_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -851,10 +865,8 @@
 
 	result = -EIO;
 
-	lock_kernel();	
-
 	server = NCP_SERVER(inode);
-	if ((!server) || !ncp_conn_valid(server))
+	if (!server)	/* How this could happen? */
 		goto out;
 
 	/* ageing the dentry to force validation */
@@ -981,8 +993,6 @@
 		result = ncp_modify_file_or_subdir_dos_info(NCP_SERVER(inode),
 				      inode, info_mask, &info);
 		if (result != 0) {
-			result = -EACCES;
-
 			if (info_mask == (DM_CREATE_TIME | DM_CREATE_DATE)) {
 				/* NetWare seems not to allow this. I
 				   do not know why. So, just tell the
@@ -1005,7 +1015,8 @@
 	mark_inode_dirty(inode);
 
 out:
-	unlock_kernel();
+	if (result > 0)
+		result = -EACCES;
 	return result;
 }
 
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 84a8cfc..c2a1f9a 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -35,16 +35,11 @@
 #define NCP_PACKET_SIZE_INTERNAL 65536
 
 static int
-ncp_get_fs_info(struct ncp_server * server, struct file *file,
+ncp_get_fs_info(struct ncp_server * server, struct inode *inode,
 		struct ncp_fs_info __user *arg)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
 	struct ncp_fs_info info;
 
-	if (file_permission(file, MAY_WRITE) != 0
-	    && current_uid() != server->m.mounted_uid)
-		return -EACCES;
-
 	if (copy_from_user(&info, arg, sizeof(info)))
 		return -EFAULT;
 
@@ -65,16 +60,11 @@
 }
 
 static int
-ncp_get_fs_info_v2(struct ncp_server * server, struct file *file,
+ncp_get_fs_info_v2(struct ncp_server * server, struct inode *inode,
 		   struct ncp_fs_info_v2 __user * arg)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
 	struct ncp_fs_info_v2 info2;
 
-	if (file_permission(file, MAY_WRITE) != 0
-	    && current_uid() != server->m.mounted_uid)
-		return -EACCES;
-
 	if (copy_from_user(&info2, arg, sizeof(info2)))
 		return -EFAULT;
 
@@ -136,16 +126,11 @@
 #define NCP_IOC_SETPRIVATEDATA_32	_IOR('n', 10, struct compat_ncp_privatedata_ioctl)
 
 static int
-ncp_get_compat_fs_info_v2(struct ncp_server * server, struct file *file,
+ncp_get_compat_fs_info_v2(struct ncp_server * server, struct inode *inode,
 		   struct compat_ncp_fs_info_v2 __user * arg)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
 	struct compat_ncp_fs_info_v2 info2;
 
-	if (file_permission(file, MAY_WRITE) != 0
-	    && current_uid() != server->m.mounted_uid)
-		return -EACCES;
-
 	if (copy_from_user(&info2, arg, sizeof(info2)))
 		return -EFAULT;
 
@@ -182,11 +167,8 @@
 	struct nls_table *iocharset;
 	struct nls_table *oldset_io;
 	struct nls_table *oldset_cp;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EACCES;
-	if (server->root_setuped)
-		return -EBUSY;
+	int utf8;
+	int err;
 
 	if (copy_from_user(&user, arg, sizeof(user)))
 		return -EFAULT;
@@ -206,28 +188,40 @@
 	user.iocharset[NCP_IOCSNAME_LEN] = 0;
 	if (!user.iocharset[0] || !strcmp(user.iocharset, "default")) {
 		iocharset = load_nls_default();
-		NCP_CLR_FLAG(server, NCP_FLAG_UTF8);
+		utf8 = 0;
 	} else if (!strcmp(user.iocharset, "utf8")) {
 		iocharset = load_nls_default();
-		NCP_SET_FLAG(server, NCP_FLAG_UTF8);
+		utf8 = 1;
 	} else {
 		iocharset = load_nls(user.iocharset);
 		if (!iocharset) {
 			unload_nls(codepage);
 			return -EBADRQC;
 		}
-		NCP_CLR_FLAG(server, NCP_FLAG_UTF8);
+		utf8 = 0;
 	}
 
-	oldset_cp = server->nls_vol;
-	server->nls_vol = codepage;
-	oldset_io = server->nls_io;
-	server->nls_io = iocharset;
-
+	mutex_lock(&server->root_setup_lock);
+	if (server->root_setuped) {
+		oldset_cp = codepage;
+		oldset_io = iocharset;
+		err = -EBUSY;
+	} else {
+		if (utf8)
+			NCP_SET_FLAG(server, NCP_FLAG_UTF8);
+		else
+			NCP_CLR_FLAG(server, NCP_FLAG_UTF8);
+		oldset_cp = server->nls_vol;
+		server->nls_vol = codepage;
+		oldset_io = server->nls_io;
+		server->nls_io = iocharset;
+		err = 0;
+	}
+	mutex_unlock(&server->root_setup_lock);
 	unload_nls(oldset_cp);
 	unload_nls(oldset_io);
 
-	return 0;
+	return err;
 }
 
 static int
@@ -237,6 +231,7 @@
 	int len;
 
 	memset(&user, 0, sizeof(user));
+	mutex_lock(&server->root_setup_lock);
 	if (server->nls_vol && server->nls_vol->charset) {
 		len = strlen(server->nls_vol->charset);
 		if (len > NCP_IOCSNAME_LEN)
@@ -254,6 +249,7 @@
 		strncpy(user.iocharset,	server->nls_io->charset, len);
 		user.iocharset[len] = 0;
 	}
+	mutex_unlock(&server->root_setup_lock);
 
 	if (copy_to_user(arg, &user, sizeof(user)))
 		return -EFAULT;
@@ -261,25 +257,19 @@
 }
 #endif /* CONFIG_NCPFS_NLS */
 
-static long __ncp_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg)
 {
-	struct inode *inode = filp->f_dentry->d_inode;
 	struct ncp_server *server = NCP_SERVER(inode);
 	int result;
 	struct ncp_ioctl_request request;
 	char* bouncebuffer;
 	void __user *argp = (void __user *)arg;
-	uid_t uid = current_uid();
 
 	switch (cmd) {
 #ifdef CONFIG_COMPAT
 	case NCP_IOC_NCPREQUEST_32:
 #endif
 	case NCP_IOC_NCPREQUEST:
-		if (file_permission(filp, MAY_WRITE) != 0
-		    && uid != server->m.mounted_uid)
-			return -EACCES;
-
 #ifdef CONFIG_COMPAT
 		if (cmd == NCP_IOC_NCPREQUEST_32) {
 			struct compat_ncp_ioctl_request request32;
@@ -314,7 +304,7 @@
 		server->current_size = request.size;
 		memcpy(server->packet, bouncebuffer, request.size);
 
-		result = ncp_request2(server, request.function, 
+		result = ncp_request2(server, request.function,
 			bouncebuffer, NCP_PACKET_SIZE_INTERNAL);
 		if (result < 0)
 			result = -EIO;
@@ -331,69 +321,69 @@
 
 	case NCP_IOC_CONN_LOGGED_IN:
 
-		if (!capable(CAP_SYS_ADMIN))
-			return -EACCES;
 		if (!(server->m.int_flags & NCP_IMOUNT_LOGGEDIN_POSSIBLE))
 			return -EINVAL;
+		mutex_lock(&server->root_setup_lock);
 		if (server->root_setuped)
-			return -EBUSY;
-		server->root_setuped = 1;
-		return ncp_conn_logged_in(inode->i_sb);
+			result = -EBUSY;
+		else {
+			result = ncp_conn_logged_in(inode->i_sb);
+			if (result == 0)
+				server->root_setuped = 1;
+		}
+		mutex_unlock(&server->root_setup_lock);
+		return result;
 
 	case NCP_IOC_GET_FS_INFO:
-		return ncp_get_fs_info(server, filp, argp);
+		return ncp_get_fs_info(server, inode, argp);
 
 	case NCP_IOC_GET_FS_INFO_V2:
-		return ncp_get_fs_info_v2(server, filp, argp);
+		return ncp_get_fs_info_v2(server, inode, argp);
 
 #ifdef CONFIG_COMPAT
 	case NCP_IOC_GET_FS_INFO_V2_32:
-		return ncp_get_compat_fs_info_v2(server, filp, argp);
+		return ncp_get_compat_fs_info_v2(server, inode, argp);
 #endif
 	/* we have too many combinations of CONFIG_COMPAT,
 	 * CONFIG_64BIT and CONFIG_UID16, so just handle
 	 * any of the possible ioctls */
 	case NCP_IOC_GETMOUNTUID16:
-	case NCP_IOC_GETMOUNTUID32:
-	case NCP_IOC_GETMOUNTUID64:
-		if (file_permission(filp, MAY_READ) != 0
-			&& uid != server->m.mounted_uid)
-			return -EACCES;
-
-		if (cmd == NCP_IOC_GETMOUNTUID16) {
+		{
 			u16 uid;
+
 			SET_UID(uid, server->m.mounted_uid);
 			if (put_user(uid, (u16 __user *)argp))
 				return -EFAULT;
-		} else if (cmd == NCP_IOC_GETMOUNTUID32) {
-			if (put_user(server->m.mounted_uid,
-						(u32 __user *)argp))
-				return -EFAULT;
-		} else {
-			if (put_user(server->m.mounted_uid,
-						(u64 __user *)argp))
-				return -EFAULT;
+			return 0;
 		}
+	case NCP_IOC_GETMOUNTUID32:
+		if (put_user(server->m.mounted_uid,
+			     (u32 __user *)argp))
+			return -EFAULT;
+		return 0;
+	case NCP_IOC_GETMOUNTUID64:
+		if (put_user(server->m.mounted_uid,
+			     (u64 __user *)argp))
+			return -EFAULT;
 		return 0;
 
 	case NCP_IOC_GETROOT:
 		{
 			struct ncp_setroot_ioctl sr;
 
-			if (file_permission(filp, MAY_READ) != 0
-			    && uid != server->m.mounted_uid)
-				return -EACCES;
-
+			result = -EACCES;
+			mutex_lock(&server->root_setup_lock);
 			if (server->m.mounted_vol[0]) {
 				struct dentry* dentry = inode->i_sb->s_root;
 
 				if (dentry) {
 					struct inode* s_inode = dentry->d_inode;
-				
+
 					if (s_inode) {
 						sr.volNumber = NCP_FINFO(s_inode)->volNumber;
 						sr.dirEntNum = NCP_FINFO(s_inode)->dirEntNum;
 						sr.namespace = server->name_space[sr.volNumber];
+						result = 0;
 					} else
 						DPRINTK("ncpfs: s_root->d_inode==NULL\n");
 				} else
@@ -402,10 +392,12 @@
 				sr.volNumber = -1;
 				sr.namespace = 0;
 				sr.dirEntNum = 0;
+				result = 0;
 			}
-			if (copy_to_user(argp, &sr, sizeof(sr)))
-				return -EFAULT;
-			return 0;
+			mutex_unlock(&server->root_setup_lock);
+			if (!result && copy_to_user(argp, &sr, sizeof(sr)))
+				result = -EFAULT;
+			return result;
 		}
 
 	case NCP_IOC_SETROOT:
@@ -416,103 +408,114 @@
 			__le32 dosde;
 			struct dentry* dentry;
 
-			if (!capable(CAP_SYS_ADMIN))
-			{
-				return -EACCES;
-			}
-			if (server->root_setuped) return -EBUSY;
 			if (copy_from_user(&sr, argp, sizeof(sr)))
 				return -EFAULT;
-			if (sr.volNumber < 0) {
-				server->m.mounted_vol[0] = 0;
-				vnum = NCP_NUMBER_OF_VOLUMES;
-				de = 0;
-				dosde = 0;
-			} else if (sr.volNumber >= NCP_NUMBER_OF_VOLUMES) {
-				return -EINVAL;
-			} else if (ncp_mount_subdir(server, sr.volNumber,
-						sr.namespace, sr.dirEntNum,
-						&vnum, &de, &dosde)) {
-				return -ENOENT;
-			}
-			
-			dentry = inode->i_sb->s_root;
-			server->root_setuped = 1;
-			if (dentry) {
-				struct inode* s_inode = dentry->d_inode;
-				
-				if (s_inode) {
-					NCP_FINFO(s_inode)->volNumber = vnum;
-					NCP_FINFO(s_inode)->dirEntNum = de;
-					NCP_FINFO(s_inode)->DosDirNum = dosde;
+			mutex_lock(&server->root_setup_lock);
+			if (server->root_setuped)
+				result = -EBUSY;
+			else {
+				if (sr.volNumber < 0) {
+					server->m.mounted_vol[0] = 0;
+					vnum = NCP_NUMBER_OF_VOLUMES;
+					de = 0;
+					dosde = 0;
+					result = 0;
+				} else if (sr.volNumber >= NCP_NUMBER_OF_VOLUMES) {
+					result = -EINVAL;
+				} else if (ncp_mount_subdir(server, sr.volNumber,
+							sr.namespace, sr.dirEntNum,
+							&vnum, &de, &dosde)) {
+					result = -ENOENT;
 				} else
-					DPRINTK("ncpfs: s_root->d_inode==NULL\n");
-			} else
-				DPRINTK("ncpfs: s_root==NULL\n");
+					result = 0;
 
+				if (result == 0) {
+					dentry = inode->i_sb->s_root;
+					if (dentry) {
+						struct inode* s_inode = dentry->d_inode;
+
+						if (s_inode) {
+							NCP_FINFO(s_inode)->volNumber = vnum;
+							NCP_FINFO(s_inode)->dirEntNum = de;
+							NCP_FINFO(s_inode)->DosDirNum = dosde;
+							server->root_setuped = 1;
+						} else {
+							DPRINTK("ncpfs: s_root->d_inode==NULL\n");
+							result = -EIO;
+						}
+					} else {
+						DPRINTK("ncpfs: s_root==NULL\n");
+						result = -EIO;
+					}
+				}
+				result = 0;
+			}
+			mutex_unlock(&server->root_setup_lock);
+
+			return result;
+		}
+
+#ifdef CONFIG_NCPFS_PACKET_SIGNING
+	case NCP_IOC_SIGN_INIT:
+		{
+			struct ncp_sign_init sign;
+
+			if (argp)
+				if (copy_from_user(&sign, argp, sizeof(sign)))
+					return -EFAULT;
+			ncp_lock_server(server);
+			mutex_lock(&server->rcv.creq_mutex);
+			if (argp) {
+				if (server->sign_wanted) {
+					memcpy(server->sign_root,sign.sign_root,8);
+					memcpy(server->sign_last,sign.sign_last,16);
+					server->sign_active = 1;
+				}
+				/* ignore when signatures not wanted */
+			} else {
+				server->sign_active = 0;
+			}
+			mutex_unlock(&server->rcv.creq_mutex);
+			ncp_unlock_server(server);
 			return 0;
 		}
 
-#ifdef CONFIG_NCPFS_PACKET_SIGNING	
-	case NCP_IOC_SIGN_INIT:
-		if (file_permission(filp, MAY_WRITE) != 0
-		    && uid != server->m.mounted_uid)
-			return -EACCES;
-
-		if (argp) {
-			if (server->sign_wanted)
-			{
-				struct ncp_sign_init sign;
-
-				if (copy_from_user(&sign, argp, sizeof(sign)))
-					return -EFAULT;
-				memcpy(server->sign_root,sign.sign_root,8);
-				memcpy(server->sign_last,sign.sign_last,16);
-				server->sign_active = 1;
-			}
-			/* ignore when signatures not wanted */
-		} else {
-			server->sign_active = 0;
-		}
-		return 0;		
-		
         case NCP_IOC_SIGN_WANTED:
-		if (file_permission(filp, MAY_READ) != 0
-		    && uid != server->m.mounted_uid)
-			return -EACCES;
-		
-                if (put_user(server->sign_wanted, (int __user *)argp))
-			return -EFAULT;
-                return 0;
+		{
+			int state;
+
+			ncp_lock_server(server);
+			state = server->sign_wanted;
+			ncp_unlock_server(server);
+			if (put_user(state, (int __user *)argp))
+				return -EFAULT;
+			return 0;
+		}
 
 	case NCP_IOC_SET_SIGN_WANTED:
 		{
 			int newstate;
 
-			if (file_permission(filp, MAY_WRITE) != 0
-			    && uid != server->m.mounted_uid)
-				return -EACCES;
-
 			/* get only low 8 bits... */
 			if (get_user(newstate, (unsigned char __user *)argp))
 				return -EFAULT;
+			result = 0;
+			ncp_lock_server(server);
 			if (server->sign_active) {
 				/* cannot turn signatures OFF when active */
-				if (!newstate) return -EINVAL;
+				if (!newstate)
+					result = -EINVAL;
 			} else {
 				server->sign_wanted = newstate != 0;
 			}
-			return 0;
+			ncp_unlock_server(server);
+			return result;
 		}
 
 #endif /* CONFIG_NCPFS_PACKET_SIGNING */
 
 #ifdef CONFIG_NCPFS_IOCTL_LOCKING
 	case NCP_IOC_LOCKUNLOCK:
-		if (file_permission(filp, MAY_WRITE) != 0
-		    && uid != server->m.mounted_uid)
-			return -EACCES;
-
 		{
 			struct ncp_lock_ioctl	 rqdata;
 
@@ -541,16 +544,13 @@
 			{
 				return result;
 			}
-			result = -EIO;
-			if (!ncp_conn_valid(server))
-				goto outrel;
 			result = -EISDIR;
 			if (!S_ISREG(inode->i_mode))
 				goto outrel;
 			if (rqdata.cmd == NCP_LOCK_CLEAR)
 			{
 				result = ncp_ClearPhysicalRecord(NCP_SERVER(inode),
-							NCP_FINFO(inode)->file_handle, 
+							NCP_FINFO(inode)->file_handle,
 							rqdata.offset,
 							rqdata.length);
 				if (result > 0) result = 0;	/* no such lock */
@@ -573,7 +573,7 @@
 							rqdata.timeout);
 				if (result > 0) result = -EAGAIN;
 			}
-outrel:			
+outrel:
 			ncp_inode_close(inode);
 			return result;
 		}
@@ -581,60 +581,62 @@
 
 #ifdef CONFIG_COMPAT
 	case NCP_IOC_GETOBJECTNAME_32:
-		if (uid != server->m.mounted_uid)
-			return -EACCES;
 		{
 			struct compat_ncp_objectname_ioctl user;
 			size_t outl;
 
 			if (copy_from_user(&user, argp, sizeof(user)))
 				return -EFAULT;
+			down_read(&server->auth_rwsem);
 			user.auth_type = server->auth.auth_type;
 			outl = user.object_name_len;
 			user.object_name_len = server->auth.object_name_len;
 			if (outl > user.object_name_len)
 				outl = user.object_name_len;
+			result = 0;
 			if (outl) {
 				if (copy_to_user(compat_ptr(user.object_name),
 						 server->auth.object_name,
-						 outl)) return -EFAULT;
+						 outl))
+					result = -EFAULT;
 			}
-			if (copy_to_user(argp, &user, sizeof(user)))
-				return -EFAULT;
-			return 0;
+			up_read(&server->auth_rwsem);
+			if (!result && copy_to_user(argp, &user, sizeof(user)))
+				result = -EFAULT;
+			return result;
 		}
 #endif
 
 	case NCP_IOC_GETOBJECTNAME:
-		if (uid != server->m.mounted_uid)
-			return -EACCES;
 		{
 			struct ncp_objectname_ioctl user;
 			size_t outl;
 
 			if (copy_from_user(&user, argp, sizeof(user)))
 				return -EFAULT;
+			down_read(&server->auth_rwsem);
 			user.auth_type = server->auth.auth_type;
 			outl = user.object_name_len;
 			user.object_name_len = server->auth.object_name_len;
 			if (outl > user.object_name_len)
 				outl = user.object_name_len;
+			result = 0;
 			if (outl) {
 				if (copy_to_user(user.object_name,
 						 server->auth.object_name,
-						 outl)) return -EFAULT;
+						 outl))
+					result = -EFAULT;
 			}
-			if (copy_to_user(argp, &user, sizeof(user)))
-				return -EFAULT;
-			return 0;
+			up_read(&server->auth_rwsem);
+			if (!result && copy_to_user(argp, &user, sizeof(user)))
+				result = -EFAULT;
+			return result;
 		}
 
 #ifdef CONFIG_COMPAT
 	case NCP_IOC_SETOBJECTNAME_32:
 #endif
 	case NCP_IOC_SETOBJECTNAME:
-		if (uid != server->m.mounted_uid)
-			return -EACCES;
 		{
 			struct ncp_objectname_ioctl user;
 			void* newname;
@@ -666,9 +668,7 @@
 			} else {
 				newname = NULL;
 			}
-			/* enter critical section */
-			/* maybe that kfree can sleep so do that this way */
-			/* it is at least more SMP friendly (in future...) */
+			down_write(&server->auth_rwsem);
 			oldname = server->auth.object_name;
 			oldnamelen = server->auth.object_name_len;
 			oldprivate = server->priv.data;
@@ -678,7 +678,7 @@
 			server->auth.object_name = newname;
 			server->priv.len = 0;
 			server->priv.data = NULL;
-			/* leave critical section */
+			up_write(&server->auth_rwsem);
 			kfree(oldprivate);
 			kfree(oldname);
 			return 0;
@@ -688,8 +688,6 @@
 	case NCP_IOC_GETPRIVATEDATA_32:
 #endif
 	case NCP_IOC_GETPRIVATEDATA:
-		if (uid != server->m.mounted_uid)
-			return -EACCES;
 		{
 			struct ncp_privatedata_ioctl user;
 			size_t outl;
@@ -706,14 +704,20 @@
 			if (copy_from_user(&user, argp, sizeof(user)))
 				return -EFAULT;
 
+			down_read(&server->auth_rwsem);
 			outl = user.len;
 			user.len = server->priv.len;
 			if (outl > user.len) outl = user.len;
+			result = 0;
 			if (outl) {
 				if (copy_to_user(user.data,
 						 server->priv.data,
-						 outl)) return -EFAULT;
+						 outl))
+					result = -EFAULT;
 			}
+			up_read(&server->auth_rwsem);
+			if (result)
+				return result;
 #ifdef CONFIG_COMPAT
 			if (cmd == NCP_IOC_GETPRIVATEDATA_32) {
 				struct compat_ncp_privatedata_ioctl user32;
@@ -733,8 +737,6 @@
 	case NCP_IOC_SETPRIVATEDATA_32:
 #endif
 	case NCP_IOC_SETPRIVATEDATA:
-		if (uid != server->m.mounted_uid)
-			return -EACCES;
 		{
 			struct ncp_privatedata_ioctl user;
 			void* new;
@@ -762,12 +764,12 @@
 			} else {
 				new = NULL;
 			}
-			/* enter critical section */
+			down_write(&server->auth_rwsem);
 			old = server->priv.data;
 			oldlen = server->priv.len;
 			server->priv.len = user.len;
 			server->priv.data = new;
-			/* leave critical section */
+			up_write(&server->auth_rwsem);
 			kfree(old);
 			return 0;
 		}
@@ -775,17 +777,13 @@
 #ifdef CONFIG_NCPFS_NLS
 	case NCP_IOC_SETCHARSETS:
 		return ncp_set_charsets(server, argp);
-		
+
 	case NCP_IOC_GETCHARSETS:
 		return ncp_get_charsets(server, argp);
 
 #endif /* CONFIG_NCPFS_NLS */
 
 	case NCP_IOC_SETDENTRYTTL:
-		if (file_permission(filp, MAY_WRITE) != 0 &&
-		    uid != server->m.mounted_uid)
-			return -EACCES;
-
 		{
 			u_int32_t user;
 
@@ -795,13 +793,13 @@
 			if (user > 20000)
 				return -EINVAL;
 			user = (user * HZ) / 1000;
-			server->dentry_ttl = user;
+			atomic_set(&server->dentry_ttl, user);
 			return 0;
 		}
-		
+
 	case NCP_IOC_GETDENTRYTTL:
 		{
-			u_int32_t user = (server->dentry_ttl * 1000) / HZ;
+			u_int32_t user = (atomic_read(&server->dentry_ttl) * 1000) / HZ;
 			if (copy_to_user(argp, &user, sizeof(user)))
 				return -EFAULT;
 			return 0;
@@ -811,59 +809,103 @@
 	return -EINVAL;
 }
 
-static int ncp_ioctl_need_write(unsigned int cmd)
-{
-	switch (cmd) {
-	case NCP_IOC_GET_FS_INFO:
-	case NCP_IOC_GET_FS_INFO_V2:
-	case NCP_IOC_NCPREQUEST:
-	case NCP_IOC_SETDENTRYTTL:
-	case NCP_IOC_SIGN_INIT:
-	case NCP_IOC_LOCKUNLOCK:
-	case NCP_IOC_SET_SIGN_WANTED:
-		return 1;
-	case NCP_IOC_GETOBJECTNAME:
-	case NCP_IOC_SETOBJECTNAME:
-	case NCP_IOC_GETPRIVATEDATA:
-	case NCP_IOC_SETPRIVATEDATA:
-	case NCP_IOC_SETCHARSETS:
-	case NCP_IOC_GETCHARSETS:
-	case NCP_IOC_CONN_LOGGED_IN:
-	case NCP_IOC_GETDENTRYTTL:
-	case NCP_IOC_GETMOUNTUID2:
-	case NCP_IOC_SIGN_WANTED:
-	case NCP_IOC_GETROOT:
-	case NCP_IOC_SETROOT:
-		return 0;
-	default:
-		/* unknown IOCTL command, assume write */
-		return 1;
-	}
-}
-
 long ncp_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct ncp_server *server = NCP_SERVER(inode);
+	uid_t uid = current_uid();
+	int need_drop_write = 0;
 	long ret;
 
-	lock_kernel();
-	if (ncp_ioctl_need_write(cmd)) {
-		/*
-		 * inside the ioctl(), any failures which
-		 * are because of file_permission() are
-		 * -EACCESS, so it seems consistent to keep
-		 *  that here.
-		 */
-		if (mnt_want_write(filp->f_path.mnt)) {
+	switch (cmd) {
+	case NCP_IOC_SETCHARSETS:
+	case NCP_IOC_CONN_LOGGED_IN:
+	case NCP_IOC_SETROOT:
+		if (!capable(CAP_SYS_ADMIN)) {
 			ret = -EACCES;
 			goto out;
 		}
+		break;
 	}
-	ret = __ncp_ioctl(filp, cmd, arg);
-	if (ncp_ioctl_need_write(cmd))
+	if (server->m.mounted_uid != uid) {
+		switch (cmd) {
+		/*
+		 * Only mount owner can issue these ioctls.  Information
+		 * necessary to authenticate to other NDS servers are
+		 * stored here.
+		 */
+		case NCP_IOC_GETOBJECTNAME:
+		case NCP_IOC_SETOBJECTNAME:
+		case NCP_IOC_GETPRIVATEDATA:
+		case NCP_IOC_SETPRIVATEDATA:
+#ifdef CONFIG_COMPAT
+		case NCP_IOC_GETOBJECTNAME_32:
+		case NCP_IOC_SETOBJECTNAME_32:
+		case NCP_IOC_GETPRIVATEDATA_32:
+		case NCP_IOC_SETPRIVATEDATA_32:
+#endif
+			ret = -EACCES;
+			goto out;
+		/*
+		 * These require write access on the inode if user id
+		 * does not match.  Note that they do not write to the
+		 * file...  But old code did mnt_want_write, so I keep
+		 * it as is.  Of course not for mountpoint owner, as
+		 * that breaks read-only mounts altogether as ncpmount
+		 * needs working NCP_IOC_NCPREQUEST and
+		 * NCP_IOC_GET_FS_INFO.  Some of these codes (setdentryttl,
+		 * signinit, setsignwanted) should be probably restricted
+		 * to owner only, or even more to CAP_SYS_ADMIN).
+		 */
+		case NCP_IOC_GET_FS_INFO:
+		case NCP_IOC_GET_FS_INFO_V2:
+		case NCP_IOC_NCPREQUEST:
+		case NCP_IOC_SETDENTRYTTL:
+		case NCP_IOC_SIGN_INIT:
+		case NCP_IOC_LOCKUNLOCK:
+		case NCP_IOC_SET_SIGN_WANTED:
+#ifdef CONFIG_COMPAT
+		case NCP_IOC_GET_FS_INFO_V2_32:
+		case NCP_IOC_NCPREQUEST_32:
+#endif
+			ret = mnt_want_write_file(filp);
+			if (ret)
+				goto out;
+			need_drop_write = 1;
+			ret = inode_permission(inode, MAY_WRITE);
+			if (ret)
+				goto outDropWrite;
+			break;
+		/*
+		 * Read access required.
+		 */
+		case NCP_IOC_GETMOUNTUID16:
+		case NCP_IOC_GETMOUNTUID32:
+		case NCP_IOC_GETMOUNTUID64:
+		case NCP_IOC_GETROOT:
+		case NCP_IOC_SIGN_WANTED:
+			ret = inode_permission(inode, MAY_READ);
+			if (ret)
+				goto out;
+			break;
+		/*
+		 * Anybody can read these.
+		 */
+		case NCP_IOC_GETCHARSETS:
+		case NCP_IOC_GETDENTRYTTL:
+		default:
+		/* Three codes below are protected by CAP_SYS_ADMIN above. */
+		case NCP_IOC_SETCHARSETS:
+		case NCP_IOC_CONN_LOGGED_IN:
+		case NCP_IOC_SETROOT:
+			break;
+		}
+	}
+	ret = __ncp_ioctl(inode, cmd, arg);
+outDropWrite:
+	if (need_drop_write)
 		mnt_drop_write(filp->f_path.mnt);
-
 out:
-	unlock_kernel();
 	return ret;
 }
 
@@ -872,10 +914,8 @@
 {
 	long ret;
 
-	lock_kernel();
 	arg = (unsigned long) compat_ptr(arg);
 	ret = ncp_ioctl(file, cmd, arg);
-	unlock_kernel();
 	return ret;
 }
 #endif
diff --git a/fs/ncpfs/ncplib_kernel.c b/fs/ncpfs/ncplib_kernel.c
index 0ec6237..a95615a 100644
--- a/fs/ncpfs/ncplib_kernel.c
+++ b/fs/ncpfs/ncplib_kernel.c
@@ -107,17 +107,17 @@
 	return &(server->packet[sizeof(struct ncp_reply_header) + offset]);
 }
 
-static inline u8 BVAL(void *data)
+static inline u8 BVAL(const void *data)
 {
-	return *(u8 *)data;
+	return *(const u8 *)data;
 }
 
 static u8 ncp_reply_byte(struct ncp_server *server, int offset)
 {
-	return *(u8 *)ncp_reply_data(server, offset);
+	return *(const u8 *)ncp_reply_data(server, offset);
 }
 
-static inline u16 WVAL_LH(void *data)
+static inline u16 WVAL_LH(const void *data)
 {
 	return get_unaligned_le16(data);
 }
@@ -134,7 +134,7 @@
 	return get_unaligned_be16(ncp_reply_data(server, offset));
 }
 
-static inline u32 DVAL_LH(void *data)
+static inline u32 DVAL_LH(const void *data)
 {
 	return get_unaligned_le32(data);
 }
@@ -349,9 +349,9 @@
 	return result;
 }
 
-void ncp_extract_file_info(void *structure, struct nw_info_struct *target)
+void ncp_extract_file_info(const void *structure, struct nw_info_struct *target)
 {
-	__u8 *name_len;
+	const __u8 *name_len;
 	const int info_struct_size = offsetof(struct nw_info_struct, nameLen);
 
 	memcpy(target, structure, info_struct_size);
@@ -364,7 +364,7 @@
 }
 
 #ifdef CONFIG_NCPFS_NFS_NS
-static inline void ncp_extract_nfs_info(unsigned char *structure,
+static inline void ncp_extract_nfs_info(const unsigned char *structure,
 				 struct nw_nfs_info *target)
 {
 	target->mode = DVAL_LH(structure);
@@ -417,7 +417,7 @@
  * Returns information for a (one-component) name relative to
  * the specified directory.
  */
-int ncp_obtain_info(struct ncp_server *server, struct inode *dir, char *path,
+int ncp_obtain_info(struct ncp_server *server, struct inode *dir, const char *path,
 			struct nw_info_struct *target)
 {
 	__u8  volnum = NCP_FINFO(dir)->volNumber;
@@ -452,16 +452,16 @@
 #ifdef CONFIG_NCPFS_NFS_NS
 static int
 ncp_obtain_DOS_dir_base(struct ncp_server *server,
-		__u8 volnum, __le32 dirent,
-		char *path, /* At most 1 component */
+		__u8 ns, __u8 volnum, __le32 dirent,
+		const char *path, /* At most 1 component */
 		__le32 *DOS_dir_base)
 {
 	int result;
 
 	ncp_init_request(server);
 	ncp_add_byte(server, 6); /* subfunction */
-	ncp_add_byte(server, server->name_space[volnum]);
-	ncp_add_byte(server, server->name_space[volnum]);
+	ncp_add_byte(server, ns);
+	ncp_add_byte(server, ns);
 	ncp_add_word(server, cpu_to_le16(0x8006)); /* get all */
 	ncp_add_dword(server, RIM_DIRECTORY);
 	ncp_add_handle_path(server, volnum, dirent, 1, path);
@@ -523,10 +523,27 @@
 #endif	/* defined(CONFIG_NCPFS_OS2_NS) || defined(CONFIG_NCPFS_NFS_NS) */
 }
 
+int
+ncp_update_known_namespace(struct ncp_server *server, __u8 volume, int *ret_ns)
+{
+	int ns = ncp_get_known_namespace(server, volume);
+
+	if (ret_ns)
+		*ret_ns = ns;
+
+	DPRINTK("lookup_vol: namespace[%d] = %d\n",
+		volume, server->name_space[volume]);
+
+	if (server->name_space[volume] == ns)
+		return 0;
+	server->name_space[volume] = ns;
+	return 1;
+}
+
 static int
 ncp_ObtainSpecificDirBase(struct ncp_server *server,
 		__u8 nsSrc, __u8 nsDst, __u8 vol_num, __le32 dir_base,
-		char *path, /* At most 1 component */
+		const char *path, /* At most 1 component */
 		__le32 *dirEntNum, __le32 *DosDirNum)
 {
 	int result;
@@ -560,14 +577,13 @@
 {
 	int dstNS;
 	int result;
-	
-	dstNS = ncp_get_known_namespace(server, volNumber);
+
+	ncp_update_known_namespace(server, volNumber, &dstNS);
 	if ((result = ncp_ObtainSpecificDirBase(server, srcNS, dstNS, volNumber, 
 				      dirEntNum, NULL, newDirEnt, newDosEnt)) != 0)
 	{
 		return result;
 	}
-	server->name_space[volNumber] = dstNS;
 	*volume = volNumber;
 	server->m.mounted_vol[1] = 0;
 	server->m.mounted_vol[0] = 'X';
@@ -575,11 +591,10 @@
 }
 
 int 
-ncp_get_volume_root(struct ncp_server *server, const char *volname,
-		    __u32* volume, __le32* dirent, __le32* dosdirent)
+ncp_get_volume_root(struct ncp_server *server,
+		    const char *volname, __u32* volume, __le32* dirent, __le32* dosdirent)
 {
 	int result;
-	__u8 volnum;
 
 	DPRINTK("ncp_get_volume_root: looking up vol %s\n", volname);
 
@@ -601,21 +616,14 @@
 		return result;
 	}
 	*dirent = *dosdirent = ncp_reply_dword(server, 4);
-	volnum = ncp_reply_byte(server, 8);
+	*volume = ncp_reply_byte(server, 8);
 	ncp_unlock_server(server);
-	*volume = volnum;
-
-	server->name_space[volnum] = ncp_get_known_namespace(server, volnum);
-
-	DPRINTK("lookup_vol: namespace[%d] = %d\n",
-		volnum, server->name_space[volnum]);
-
 	return 0;
 }
 
 int
-ncp_lookup_volume(struct ncp_server *server, const char *volname,
-		  struct nw_info_struct *target)
+ncp_lookup_volume(struct ncp_server *server,
+		  const char *volname, struct nw_info_struct *target)
 {
 	int result;
 
@@ -625,6 +633,7 @@
 	if (result) {
 		return result;
 	}
+	ncp_update_known_namespace(server, target->volNumber, NULL);
 	target->nameLen = strlen(volname);
 	memcpy(target->entryName, volname, target->nameLen+1);
 	target->attributes = aDIR;
@@ -676,8 +685,8 @@
 {
 	int result = 0;
 
+	ncp_init_request(server);
 	if (server->name_space[volnum] == NW_NS_NFS) {
-		ncp_init_request(server);
 		ncp_add_byte(server, 25);	/* subfunction */
 		ncp_add_byte(server, server->name_space[volnum]);
 		ncp_add_byte(server, NW_NS_NFS);
@@ -690,8 +699,8 @@
 		ncp_add_dword_lh(server, 1);	/* nlinks */
 		ncp_add_dword_lh(server, rdev);
 		result = ncp_request(server, 87);
-		ncp_unlock_server(server);
 	}
+	ncp_unlock_server(server);
 	return result;
 }
 #endif
@@ -700,7 +709,7 @@
 static int
 ncp_DeleteNSEntry(struct ncp_server *server,
 		  __u8 have_dir_base, __u8 volnum, __le32 dirent,
-		  char* name, __u8 ns, __le16 attr)
+		  const char* name, __u8 ns, __le16 attr)
 {
 	int result;
 
@@ -734,23 +743,25 @@
 
 int
 ncp_del_file_or_subdir(struct ncp_server *server,
-		       struct inode *dir, char *name)
+		       struct inode *dir, const char *name)
 {
 	__u8  volnum = NCP_FINFO(dir)->volNumber;
 	__le32 dirent = NCP_FINFO(dir)->dirEntNum;
+	int name_space;
 
+	name_space = server->name_space[volnum];
 #ifdef CONFIG_NCPFS_NFS_NS
-	if (server->name_space[volnum]==NW_NS_NFS)
+	if (name_space == NW_NS_NFS)
  	{
  		int result;
  
- 		result=ncp_obtain_DOS_dir_base(server, volnum, dirent, name, &dirent);
+		result=ncp_obtain_DOS_dir_base(server, name_space, volnum, dirent, name, &dirent);
  		if (result) return result;
- 		return ncp_DeleteNSEntry(server, 1, volnum, dirent, NULL, NW_NS_DOS, cpu_to_le16(0x8006));
+		name = NULL;
+		name_space = NW_NS_DOS;
  	}
- 	else
 #endif	/* CONFIG_NCPFS_NFS_NS */
- 		return ncp_DeleteNSEntry(server, 1, volnum, dirent, name, server->name_space[volnum], cpu_to_le16(0x8006));
+	return ncp_DeleteNSEntry(server, 1, volnum, dirent, name, name_space, cpu_to_le16(0x8006));
 }
 
 static inline void ConvertToNWfromDWORD(__u16 v0, __u16 v1, __u8 ret[6])
@@ -765,7 +776,7 @@
 /* If both dir and name are NULL, then in target there's already a
    looked-up entry that wants to be opened. */
 int ncp_open_create_file_or_subdir(struct ncp_server *server,
-				   struct inode *dir, char *name,
+				   struct inode *dir, const char *name,
 				   int open_create_mode,
 				   __le32 create_attributes,
 				   __le16 desired_acc_rights,
@@ -890,8 +901,8 @@
 
 static int
 ncp_RenameNSEntry(struct ncp_server *server,
-		  struct inode *old_dir, char *old_name, __le16 old_type,
-		  struct inode *new_dir, char *new_name)
+		  struct inode *old_dir, const char *old_name, __le16 old_type,
+		  struct inode *new_dir, const char *new_name)
 {
 	int result = -EINVAL;
 
@@ -929,8 +940,8 @@
 }
 
 int ncp_ren_or_mov_file_or_subdir(struct ncp_server *server,
-				struct inode *old_dir, char *old_name,
-				struct inode *new_dir, char *new_name)
+				struct inode *old_dir, const char *old_name,
+				struct inode *new_dir, const char *new_name)
 {
         int result;
         __le16 old_type = cpu_to_le16(0x06);
@@ -958,7 +969,7 @@
 ncp_read_kernel(struct ncp_server *server, const char *file_id,
 	     __u32 offset, __u16 to_read, char *target, int *bytes_read)
 {
-	char *source;
+	const char *source;
 	int result;
 
 	ncp_init_request(server);
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 2441d1a..3c57eca 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -65,10 +65,11 @@
 	atomic_dec(&NCP_FINFO(inode)->opened);
 }
 
-void ncp_extract_file_info(void* src, struct nw_info_struct* target);
-int ncp_obtain_info(struct ncp_server *server, struct inode *, char *,
+void ncp_extract_file_info(const void* src, struct nw_info_struct* target);
+int ncp_obtain_info(struct ncp_server *server, struct inode *, const char *,
 		struct nw_info_struct *target);
 int ncp_obtain_nfs_info(struct ncp_server *server, struct nw_info_struct *target);
+int ncp_update_known_namespace(struct ncp_server *server, __u8 volume, int *ret_ns);
 int ncp_get_volume_root(struct ncp_server *server, const char *volname,
 			__u32 *volume, __le32 *dirent, __le32 *dosdirent);
 int ncp_lookup_volume(struct ncp_server *, const char *, struct nw_info_struct *);
@@ -80,8 +81,8 @@
 			__u32 mode, __u32 rdev);
 
 int ncp_del_file_or_subdir2(struct ncp_server *, struct dentry*);
-int ncp_del_file_or_subdir(struct ncp_server *, struct inode *, char *);
-int ncp_open_create_file_or_subdir(struct ncp_server *, struct inode *, char *,
+int ncp_del_file_or_subdir(struct ncp_server *, struct inode *, const char *);
+int ncp_open_create_file_or_subdir(struct ncp_server *, struct inode *, const char *,
 				int, __le32, __le16, struct ncp_entry_info *);
 
 int ncp_initialize_search(struct ncp_server *, struct inode *,
@@ -93,7 +94,7 @@
 			   char** rbuf, size_t* rsize);
 
 int ncp_ren_or_mov_file_or_subdir(struct ncp_server *server,
-			      struct inode *, char *, struct inode *, char *);
+			      struct inode *, const char *, struct inode *, const char *);
 
 
 int
@@ -170,13 +171,13 @@
 #endif /* CONFIG_NCPFS_NLS */
 
 #define NCP_GET_AGE(dentry)	(jiffies - (dentry)->d_time)
-#define NCP_MAX_AGE(server)	((server)->dentry_ttl)
+#define NCP_MAX_AGE(server)	atomic_read(&(server)->dentry_ttl)
 #define NCP_TEST_AGE(server,dentry)	(NCP_GET_AGE(dentry) < NCP_MAX_AGE(server))
 
 static inline void
 ncp_age_dentry(struct ncp_server* server, struct dentry* dentry)
 {
-	dentry->d_time = jiffies - server->dentry_ttl;
+	dentry->d_time = jiffies - NCP_MAX_AGE(server);
 }
 
 static inline void
diff --git a/fs/ncpfs/ncpsign_kernel.c b/fs/ncpfs/ncpsign_kernel.c
index 7c0b5c2..d8b2d7e 100644
--- a/fs/ncpfs/ncpsign_kernel.c
+++ b/fs/ncpfs/ncpsign_kernel.c
@@ -15,21 +15,21 @@
 
 /* i386: 32-bit, little endian, handles mis-alignment */
 #ifdef __i386__
-#define GET_LE32(p) (*(int *)(p))
+#define GET_LE32(p) (*(const int *)(p))
 #define PUT_LE32(p,v) { *(int *)(p)=v; }
 #else
 /* from include/ncplib.h */
-#define BVAL(buf,pos) (((__u8 *)(buf))[pos])
+#define BVAL(buf,pos) (((const __u8 *)(buf))[pos])
 #define PVAL(buf,pos) ((unsigned)BVAL(buf,pos))
-#define BSET(buf,pos,val) (BVAL(buf,pos) = (val))
+#define BSET(buf,pos,val) (((__u8 *)(buf))[pos] = (val))
 
 static inline __u16
-WVAL_LH(__u8 * buf, int pos)
+WVAL_LH(const __u8 * buf, int pos)
 {
 	return PVAL(buf, pos) | PVAL(buf, pos + 1) << 8;
 }
 static inline __u32
-DVAL_LH(__u8 * buf, int pos)
+DVAL_LH(const __u8 * buf, int pos)
 {
 	return WVAL_LH(buf, pos) | WVAL_LH(buf, pos + 2) << 16;
 }
diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index c7ff6c7..668bd26 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -746,7 +746,6 @@
 		return -EIO;
 	}
 	if (!ncp_conn_valid(server)) {
-		printk(KERN_ERR "ncpfs: Connection invalid!\n");
 		return -EIO;
 	}
 	{
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index f7e13db..b950415 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -1,6 +1,7 @@
 config NFS_FS
 	tristate "NFS client support"
 	depends on INET && FILE_LOCKING
+	depends on BKL # fix as soon as lockd is done
 	select LOCKD
 	select SUNRPC
 	select NFS_ACL_SUPPORT if NFS_V3_ACL
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index b9c3c43..232a7ee 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -71,20 +71,20 @@
 	if (inode->i_flock == NULL)
 		goto out;
 
-	/* Protect inode->i_flock using the BKL */
-	lock_kernel();
+	/* Protect inode->i_flock using the file locks lock */
+	lock_flocks();
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
 			continue;
 		if (nfs_file_open_context(fl->fl_file) != ctx)
 			continue;
-		unlock_kernel();
+		unlock_flocks();
 		status = nfs4_lock_delegation_recall(state, fl);
 		if (status < 0)
 			goto out;
-		lock_kernel();
+		lock_flocks();
 	}
-	unlock_kernel();
+	unlock_flocks();
 out:
 	return status;
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 3e2f19b..96524c5 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -40,7 +40,7 @@
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/fs.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_idmap.h>
 #include <linux/kthread.h>
@@ -970,13 +970,13 @@
 	/* Guard against delegation returns and new lock/unlock calls */
 	down_write(&nfsi->rwsem);
 	/* Protect inode->i_flock using the BKL */
-	lock_kernel();
+	lock_flocks();
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
 			continue;
 		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
-		unlock_kernel();
+		unlock_flocks();
 		status = ops->recover_lock(state, fl);
 		switch (status) {
 			case 0:
@@ -1003,9 +1003,9 @@
 				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
 				status = 0;
 		}
-		lock_kernel();
+		lock_flocks();
 	}
-	unlock_kernel();
+	unlock_flocks();
 out:
 	up_write(&nfsi->rwsem);
 	return status;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 4264377..7cf4dda 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -2,6 +2,7 @@
 	tristate "NFS server support"
 	depends on INET
 	depends on FILE_LOCKING
+	depends on BKL # fix as soon as lockd is done
 	select LOCKD
 	select SUNRPC
 	select EXPORTFS
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index cf0d2ff..a7292fc 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -33,7 +33,7 @@
 */
 
 #include <linux/file.h>
-#include <linux/smp_lock.h>
+#include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/namei.h>
 #include <linux/swap.h>
@@ -3895,7 +3895,7 @@
 	struct inode *inode = filp->fi_inode;
 	int status = 0;
 
-	lock_kernel();
+	lock_flocks();
 	for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) {
 		if ((*flpp)->fl_owner == (fl_owner_t)lowner) {
 			status = 1;
@@ -3903,7 +3903,7 @@
 		}
 	}
 out:
-	unlock_kernel();
+	unlock_flocks();
 	return status;
 }
 
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index b53b1d0..06fa87e 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -137,6 +137,7 @@
 	.write		= nfsctl_transaction_write,
 	.read		= nfsctl_transaction_read,
 	.release	= simple_transaction_release,
+	.llseek		= default_llseek,
 };
 
 static int exports_open(struct inode *inode, struct file *file)
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index f90a33d..0442ee3 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -22,7 +22,6 @@
 
 #include <linux/fs.h>
 #include <linux/wait.h>
-#include <linux/smp_lock.h>	/* lock_kernel(), unlock_kernel() */
 #include <linux/slab.h>
 #include <linux/capability.h>	/* capable() */
 #include <linux/uaccess.h>	/* copy_from_user(), copy_to_user() */
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 9222633..f3b7520 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -45,7 +45,6 @@
 #include <linux/parser.h>
 #include <linux/random.h>
 #include <linux/crc32.h>
-#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 #include <linux/writeback.h>
 #include <linux/kobject.h>
@@ -178,17 +177,9 @@
 
  retry:
 	set_buffer_dirty(nilfs->ns_sbh[0]);
-
 	if (nilfs_test_opt(sbi, BARRIER)) {
 		err = __sync_dirty_buffer(nilfs->ns_sbh[0],
-					  WRITE_SYNC | WRITE_BARRIER);
-		if (err == -EOPNOTSUPP) {
-			nilfs_warning(sbi->s_super, __func__,
-				      "barrier-based sync failed. "
-				      "disabling barriers\n");
-			nilfs_clear_opt(sbi, BARRIER);
-			goto retry;
-		}
+					  WRITE_SYNC | WRITE_FLUSH_FUA);
 	} else {
 		err = sync_dirty_buffer(nilfs->ns_sbh[0]);
 	}
@@ -342,8 +333,6 @@
 	struct nilfs_sb_info *sbi = NILFS_SB(sb);
 	struct the_nilfs *nilfs = sbi->s_nilfs;
 
-	lock_kernel();
-
 	nilfs_detach_segment_constructor(sbi);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
@@ -361,8 +350,6 @@
 	sbi->s_super = NULL;
 	sb->s_fs_info = NULL;
 	nilfs_put_sbinfo(sbi);
-
-	unlock_kernel();
 }
 
 static int nilfs_sync_fs(struct super_block *sb, int wait)
@@ -949,8 +936,6 @@
 	struct nilfs_mount_options old_opts;
 	int was_snapshot, err;
 
-	lock_kernel();
-
 	down_write(&nilfs->ns_super_sem);
 	old_sb_flags = sb->s_flags;
 	old_opts.mount_opt = sbi->s_mount_opt;
@@ -1024,7 +1009,6 @@
 	}
  out:
 	up_write(&nilfs->ns_super_sem);
-	unlock_kernel();
 	return 0;
 
  restore_opts:
@@ -1032,7 +1016,6 @@
 	sbi->s_mount_opt = old_opts.mount_opt;
 	sbi->s_snapshot_cno = old_opts.snapshot_cno;
 	up_write(&nilfs->ns_super_sem);
-	unlock_kernel();
 	return err;
 }
 
@@ -1205,7 +1188,6 @@
 	put_nilfs(nilfs);
  failed:
 	close_bdev_exclusive(sd.bdev, mode);
-
 	return err;
 
  cancel_new:
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index ba7c10c..d277151 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -775,9 +775,7 @@
 			ret = blkdev_issue_discard(nilfs->ns_bdev,
 						   start * sects_per_block,
 						   nblocks * sects_per_block,
-						   GFP_NOFS,
-						   BLKDEV_IFL_WAIT |
-						   BLKDEV_IFL_BARRIER);
+						   GFP_NOFS, 0);
 			if (ret < 0)
 				return ret;
 			nblocks = 0;
@@ -787,8 +785,7 @@
 		ret = blkdev_issue_discard(nilfs->ns_bdev,
 					   start * sects_per_block,
 					   nblocks * sects_per_block,
-					   GFP_NOFS,
-					  BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+					   GFP_NOFS, 0);
 	return ret;
 }
 
diff --git a/fs/no-block.c b/fs/no-block.c
index d269a93..6e40e42 100644
--- a/fs/no-block.c
+++ b/fs/no-block.c
@@ -19,4 +19,5 @@
 
 const struct file_operations def_blk_fops = {
 	.open		= no_blkdev_open,
+	.llseek		= noop_llseek,
 };
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 5ed8e58..bbcb98e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -433,6 +433,7 @@
 	.release	= fanotify_release,
 	.unlocked_ioctl	= fanotify_ioctl,
 	.compat_ioctl	= fanotify_ioctl,
+	.llseek		= noop_llseek,
 };
 
 static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index bf7f6d7..24edc11 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -344,6 +344,7 @@
 	.release	= inotify_release,
 	.unlocked_ioctl	= inotify_ioctl,
 	.compat_ioctl	= inotify_ioctl,
+	.llseek		= noop_llseek,
 };
 
 
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 5128061..19c5180 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -30,7 +30,6 @@
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
 #include <linux/moduleparam.h>
-#include <linux/smp_lock.h>
 #include <linux/bitmap.h>
 
 #include "sysctl.h"
@@ -445,7 +444,6 @@
 
 	ntfs_debug("Entering with remount options string: %s", opt);
 
-	lock_kernel();
 #ifndef NTFS_RW
 	/* For read-only compiled driver, enforce read-only flag. */
 	*flags |= MS_RDONLY;
@@ -469,18 +467,15 @@
 		if (NVolErrors(vol)) {
 			ntfs_error(sb, "Volume has errors and is read-only%s",
 					es);
-			unlock_kernel();
 			return -EROFS;
 		}
 		if (vol->vol_flags & VOLUME_IS_DIRTY) {
 			ntfs_error(sb, "Volume is dirty and read-only%s", es);
-			unlock_kernel();
 			return -EROFS;
 		}
 		if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
 			ntfs_error(sb, "Volume has been modified by chkdsk "
 					"and is read-only%s", es);
-			unlock_kernel();
 			return -EROFS;
 		}
 		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
@@ -488,13 +483,11 @@
 					"(0x%x) and is read-only%s",
 					(unsigned)le16_to_cpu(vol->vol_flags),
 					es);
-			unlock_kernel();
 			return -EROFS;
 		}
 		if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
 			ntfs_error(sb, "Failed to set dirty bit in volume "
 					"information flags%s", es);
-			unlock_kernel();
 			return -EROFS;
 		}
 #if 0
@@ -514,21 +507,18 @@
 			ntfs_error(sb, "Failed to empty journal $LogFile%s",
 					es);
 			NVolSetErrors(vol);
-			unlock_kernel();
 			return -EROFS;
 		}
 		if (!ntfs_mark_quotas_out_of_date(vol)) {
 			ntfs_error(sb, "Failed to mark quotas out of date%s",
 					es);
 			NVolSetErrors(vol);
-			unlock_kernel();
 			return -EROFS;
 		}
 		if (!ntfs_stamp_usnjrnl(vol)) {
 			ntfs_error(sb, "Failed to stamp transation log "
 					"($UsnJrnl)%s", es);
 			NVolSetErrors(vol);
-			unlock_kernel();
 			return -EROFS;
 		}
 	} else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {
@@ -544,11 +534,9 @@
 
 	// TODO: Deal with *flags.
 
-	if (!parse_options(vol, opt)) {
-		unlock_kernel();
+	if (!parse_options(vol, opt))
 		return -EINVAL;
-	}
-	unlock_kernel();
+
 	ntfs_debug("Done.");
 	return 0;
 }
@@ -2261,8 +2249,6 @@
 
 	ntfs_debug("Entering.");
 
-	lock_kernel();
-
 #ifdef NTFS_RW
 	/*
 	 * Commit all inodes while they are still open in case some of them
@@ -2433,8 +2419,6 @@
 
 	sb->s_fs_info = NULL;
 	kfree(vol);
-
-	unlock_kernel();
 }
 
 /**
@@ -2772,8 +2756,6 @@
 	init_rwsem(&vol->mftbmp_lock);
 	init_rwsem(&vol->lcnbmp_lock);
 
-	unlock_kernel();
-
 	/* By default, enable sparse support. */
 	NVolSetSparseEnabled(vol);
 
@@ -2940,7 +2922,6 @@
 		}
 		mutex_unlock(&ntfs_lock);
 		sb->s_export_op = &ntfs_export_ops;
-		lock_kernel();
 		lockdep_on();
 		return 0;
 	}
@@ -3057,7 +3038,6 @@
 	}
 	/* Errors at this stage are irrelevant. */
 err_out_now:
-	lock_kernel();
 	sb->s_fs_info = NULL;
 	kfree(vol);
 	ntfs_debug("Failed, returning -EINVAL.");
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 0de69c9..5cfeee1 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -883,8 +883,8 @@
 	 * out in so that future reads from that region will get
 	 * zero's.
 	 */
-	struct page			*w_pages[OCFS2_MAX_CTXT_PAGES];
 	unsigned int			w_num_pages;
+	struct page			*w_pages[OCFS2_MAX_CTXT_PAGES];
 	struct page			*w_target_page;
 
 	/*
@@ -1642,7 +1642,8 @@
 	return ret;
 }
 
-int ocfs2_write_begin_nolock(struct address_space *mapping,
+int ocfs2_write_begin_nolock(struct file *filp,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned flags,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page)
@@ -1692,7 +1693,7 @@
 		mlog_errno(ret);
 		goto out;
 	} else if (ret == 1) {
-		ret = ocfs2_refcount_cow(inode, di_bh,
+		ret = ocfs2_refcount_cow(inode, filp, di_bh,
 					 wc->w_cpos, wc->w_clen, UINT_MAX);
 		if (ret) {
 			mlog_errno(ret);
@@ -1854,7 +1855,7 @@
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = ocfs2_write_begin_nolock(mapping, pos, len, flags, pagep,
+	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, flags, pagep,
 				       fsdata, di_bh, NULL);
 	if (ret) {
 		mlog_errno(ret);
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index c48e93f..7606f66 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -48,7 +48,8 @@
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata);
 
-int ocfs2_write_begin_nolock(struct address_space *mapping,
+int ocfs2_write_begin_nolock(struct file *filp,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned flags,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 41d5f1f..52c7557 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -62,10 +62,51 @@
 static LIST_HEAD(o2hb_node_events);
 static DECLARE_WAIT_QUEUE_HEAD(o2hb_steady_queue);
 
+/*
+ * In global heartbeat, we maintain a series of region bitmaps.
+ * 	- o2hb_region_bitmap allows us to limit the region number to max region.
+ * 	- o2hb_live_region_bitmap tracks live regions (seen steady iterations).
+ * 	- o2hb_quorum_region_bitmap tracks live regions that have seen all nodes
+ * 		heartbeat on it.
+ * 	- o2hb_failed_region_bitmap tracks the regions that have seen io timeouts.
+ */
+static unsigned long o2hb_region_bitmap[BITS_TO_LONGS(O2NM_MAX_REGIONS)];
+static unsigned long o2hb_live_region_bitmap[BITS_TO_LONGS(O2NM_MAX_REGIONS)];
+static unsigned long o2hb_quorum_region_bitmap[BITS_TO_LONGS(O2NM_MAX_REGIONS)];
+static unsigned long o2hb_failed_region_bitmap[BITS_TO_LONGS(O2NM_MAX_REGIONS)];
+
+#define O2HB_DB_TYPE_LIVENODES		0
+#define O2HB_DB_TYPE_LIVEREGIONS	1
+#define O2HB_DB_TYPE_QUORUMREGIONS	2
+#define O2HB_DB_TYPE_FAILEDREGIONS	3
+#define O2HB_DB_TYPE_REGION_LIVENODES	4
+#define O2HB_DB_TYPE_REGION_NUMBER	5
+#define O2HB_DB_TYPE_REGION_ELAPSED_TIME	6
+struct o2hb_debug_buf {
+	int db_type;
+	int db_size;
+	int db_len;
+	void *db_data;
+};
+
+static struct o2hb_debug_buf *o2hb_db_livenodes;
+static struct o2hb_debug_buf *o2hb_db_liveregions;
+static struct o2hb_debug_buf *o2hb_db_quorumregions;
+static struct o2hb_debug_buf *o2hb_db_failedregions;
+
 #define O2HB_DEBUG_DIR			"o2hb"
 #define O2HB_DEBUG_LIVENODES		"livenodes"
+#define O2HB_DEBUG_LIVEREGIONS		"live_regions"
+#define O2HB_DEBUG_QUORUMREGIONS	"quorum_regions"
+#define O2HB_DEBUG_FAILEDREGIONS	"failed_regions"
+#define O2HB_DEBUG_REGION_NUMBER	"num"
+#define O2HB_DEBUG_REGION_ELAPSED_TIME	"elapsed_time_in_ms"
+
 static struct dentry *o2hb_debug_dir;
 static struct dentry *o2hb_debug_livenodes;
+static struct dentry *o2hb_debug_liveregions;
+static struct dentry *o2hb_debug_quorumregions;
+static struct dentry *o2hb_debug_failedregions;
 
 static LIST_HEAD(o2hb_all_regions);
 
@@ -77,7 +118,19 @@
 
 #define O2HB_DEFAULT_BLOCK_BITS       9
 
+enum o2hb_heartbeat_modes {
+	O2HB_HEARTBEAT_LOCAL		= 0,
+	O2HB_HEARTBEAT_GLOBAL,
+	O2HB_HEARTBEAT_NUM_MODES,
+};
+
+char *o2hb_heartbeat_mode_desc[O2HB_HEARTBEAT_NUM_MODES] = {
+		"local",	/* O2HB_HEARTBEAT_LOCAL */
+		"global",	/* O2HB_HEARTBEAT_GLOBAL */
+};
+
 unsigned int o2hb_dead_threshold = O2HB_DEFAULT_DEAD_THRESHOLD;
+unsigned int o2hb_heartbeat_mode = O2HB_HEARTBEAT_LOCAL;
 
 /* Only sets a new threshold if there are no active regions.
  *
@@ -94,6 +147,22 @@
 	}
 }
 
+static int o2hb_global_hearbeat_mode_set(unsigned int hb_mode)
+{
+	int ret = -1;
+
+	if (hb_mode < O2HB_HEARTBEAT_NUM_MODES) {
+		spin_lock(&o2hb_live_lock);
+		if (list_empty(&o2hb_all_regions)) {
+			o2hb_heartbeat_mode = hb_mode;
+			ret = 0;
+		}
+		spin_unlock(&o2hb_live_lock);
+	}
+
+	return ret;
+}
+
 struct o2hb_node_event {
 	struct list_head        hn_item;
 	enum o2hb_callback_type hn_event_type;
@@ -135,6 +204,18 @@
 	struct block_device	*hr_bdev;
 	struct o2hb_disk_slot	*hr_slots;
 
+	/* live node map of this region */
+	unsigned long		hr_live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned int		hr_region_num;
+
+	struct dentry		*hr_debug_dir;
+	struct dentry		*hr_debug_livenodes;
+	struct dentry		*hr_debug_regnum;
+	struct dentry		*hr_debug_elapsed_time;
+	struct o2hb_debug_buf	*hr_db_livenodes;
+	struct o2hb_debug_buf	*hr_db_regnum;
+	struct o2hb_debug_buf	*hr_db_elapsed_time;
+
 	/* let the person setting up hb wait for it to return until it
 	 * has reached a 'steady' state.  This will be fixed when we have
 	 * a more complete api that doesn't lead to this sort of fragility. */
@@ -163,8 +244,19 @@
 	int               wc_error;
 };
 
+static int o2hb_pop_count(void *map, int count)
+{
+	int i = -1, pop = 0;
+
+	while ((i = find_next_bit(map, count, i + 1)) < count)
+		pop++;
+	return pop;
+}
+
 static void o2hb_write_timeout(struct work_struct *work)
 {
+	int failed, quorum;
+	unsigned long flags;
 	struct o2hb_region *reg =
 		container_of(work, struct o2hb_region,
 			     hr_write_timeout_work.work);
@@ -172,6 +264,28 @@
 	mlog(ML_ERROR, "Heartbeat write timeout to device %s after %u "
 	     "milliseconds\n", reg->hr_dev_name,
 	     jiffies_to_msecs(jiffies - reg->hr_last_timeout_start));
+
+	if (o2hb_global_heartbeat_active()) {
+		spin_lock_irqsave(&o2hb_live_lock, flags);
+		if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
+			set_bit(reg->hr_region_num, o2hb_failed_region_bitmap);
+		failed = o2hb_pop_count(&o2hb_failed_region_bitmap,
+					O2NM_MAX_REGIONS);
+		quorum = o2hb_pop_count(&o2hb_quorum_region_bitmap,
+					O2NM_MAX_REGIONS);
+		spin_unlock_irqrestore(&o2hb_live_lock, flags);
+
+		mlog(ML_HEARTBEAT, "Number of regions %d, failed regions %d\n",
+		     quorum, failed);
+
+		/*
+		 * Fence if the number of failed regions >= half the number
+		 * of  quorum regions
+		 */
+		if ((failed << 1) < quorum)
+			return;
+	}
+
 	o2quo_disk_timeout();
 }
 
@@ -180,6 +294,11 @@
 	mlog(ML_HEARTBEAT, "Queue write timeout for %u ms\n",
 	     O2HB_MAX_WRITE_TIMEOUT_MS);
 
+	if (o2hb_global_heartbeat_active()) {
+		spin_lock(&o2hb_live_lock);
+		clear_bit(reg->hr_region_num, o2hb_failed_region_bitmap);
+		spin_unlock(&o2hb_live_lock);
+	}
 	cancel_delayed_work(&reg->hr_write_timeout_work);
 	reg->hr_last_timeout_start = jiffies;
 	schedule_delayed_work(&reg->hr_write_timeout_work,
@@ -513,6 +632,8 @@
 {
 	assert_spin_locked(&o2hb_live_lock);
 
+	BUG_ON((!node) && (type != O2HB_NODE_DOWN_CB));
+
 	event->hn_event_type = type;
 	event->hn_node = node;
 	event->hn_node_num = node_num;
@@ -554,6 +675,35 @@
 	o2nm_node_put(node);
 }
 
+static void o2hb_set_quorum_device(struct o2hb_region *reg,
+				   struct o2hb_disk_slot *slot)
+{
+	assert_spin_locked(&o2hb_live_lock);
+
+	if (!o2hb_global_heartbeat_active())
+		return;
+
+	if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
+		return;
+
+	/*
+	 * A region can be added to the quorum only when it sees all
+	 * live nodes heartbeat on it. In other words, the region has been
+	 * added to all nodes.
+	 */
+	if (memcmp(reg->hr_live_node_bitmap, o2hb_live_node_bitmap,
+		   sizeof(o2hb_live_node_bitmap)))
+		return;
+
+	if (slot->ds_changed_samples < O2HB_LIVE_THRESHOLD)
+		return;
+
+	printk(KERN_NOTICE "o2hb: Region %s is now a quorum device\n",
+	       config_item_name(&reg->hr_item));
+
+	set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
+}
+
 static int o2hb_check_slot(struct o2hb_region *reg,
 			   struct o2hb_disk_slot *slot)
 {
@@ -565,14 +715,22 @@
 	u64 cputime;
 	unsigned int dead_ms = o2hb_dead_threshold * O2HB_REGION_TIMEOUT_MS;
 	unsigned int slot_dead_ms;
+	int tmp;
 
 	memcpy(hb_block, slot->ds_raw_block, reg->hr_block_bytes);
 
-	/* Is this correct? Do we assume that the node doesn't exist
-	 * if we're not configured for him? */
+	/*
+	 * If a node is no longer configured but is still in the livemap, we
+	 * may need to clear that bit from the livemap.
+	 */
 	node = o2nm_get_node_by_num(slot->ds_node_num);
-	if (!node)
-		return 0;
+	if (!node) {
+		spin_lock(&o2hb_live_lock);
+		tmp = test_bit(slot->ds_node_num, o2hb_live_node_bitmap);
+		spin_unlock(&o2hb_live_lock);
+		if (!tmp)
+			return 0;
+	}
 
 	if (!o2hb_verify_crc(reg, hb_block)) {
 		/* all paths from here will drop o2hb_live_lock for
@@ -639,8 +797,12 @@
 		mlog(ML_HEARTBEAT, "Node %d (id 0x%llx) joined my region\n",
 		     slot->ds_node_num, (long long)slot->ds_last_generation);
 
+		set_bit(slot->ds_node_num, reg->hr_live_node_bitmap);
+
 		/* first on the list generates a callback */
 		if (list_empty(&o2hb_live_slots[slot->ds_node_num])) {
+			mlog(ML_HEARTBEAT, "o2hb: Add node %d to live nodes "
+			     "bitmap\n", slot->ds_node_num);
 			set_bit(slot->ds_node_num, o2hb_live_node_bitmap);
 
 			o2hb_queue_node_event(&event, O2HB_NODE_UP_CB, node,
@@ -684,13 +846,18 @@
 		mlog(ML_HEARTBEAT, "Node %d left my region\n",
 		     slot->ds_node_num);
 
+		clear_bit(slot->ds_node_num, reg->hr_live_node_bitmap);
+
 		/* last off the live_slot generates a callback */
 		list_del_init(&slot->ds_live_item);
 		if (list_empty(&o2hb_live_slots[slot->ds_node_num])) {
+			mlog(ML_HEARTBEAT, "o2hb: Remove node %d from live "
+			     "nodes bitmap\n", slot->ds_node_num);
 			clear_bit(slot->ds_node_num, o2hb_live_node_bitmap);
 
-			o2hb_queue_node_event(&event, O2HB_NODE_DOWN_CB, node,
-					      slot->ds_node_num);
+			/* node can be null */
+			o2hb_queue_node_event(&event, O2HB_NODE_DOWN_CB,
+					      node, slot->ds_node_num);
 
 			changed = 1;
 		}
@@ -706,11 +873,14 @@
 		slot->ds_equal_samples = 0;
 	}
 out:
+	o2hb_set_quorum_device(reg, slot);
+
 	spin_unlock(&o2hb_live_lock);
 
 	o2hb_run_event_list(&event);
 
-	o2nm_node_put(node);
+	if (node)
+		o2nm_node_put(node);
 	return changed;
 }
 
@@ -737,6 +907,7 @@
 {
 	int i, ret, highest_node, change = 0;
 	unsigned long configured_nodes[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	struct o2hb_bio_wait_ctxt write_wc;
 
 	ret = o2nm_configured_node_map(configured_nodes,
@@ -746,6 +917,17 @@
 		return ret;
 	}
 
+	/*
+	 * If a node is not configured but is in the livemap, we still need
+	 * to read the slot so as to be able to remove it from the livemap.
+	 */
+	o2hb_fill_node_map(live_node_bitmap, sizeof(live_node_bitmap));
+	i = -1;
+	while ((i = find_next_bit(live_node_bitmap,
+				  O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) {
+		set_bit(i, configured_nodes);
+	}
+
 	highest_node = o2hb_highest_node(configured_nodes, O2NM_MAX_NODES);
 	if (highest_node >= O2NM_MAX_NODES) {
 		mlog(ML_NOTICE, "ocfs2_heartbeat: no configured nodes found!\n");
@@ -917,21 +1099,59 @@
 #ifdef CONFIG_DEBUG_FS
 static int o2hb_debug_open(struct inode *inode, struct file *file)
 {
+	struct o2hb_debug_buf *db = inode->i_private;
+	struct o2hb_region *reg;
 	unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	char *buf = NULL;
 	int i = -1;
 	int out = 0;
 
+	/* max_nodes should be the largest bitmap we pass here */
+	BUG_ON(sizeof(map) < db->db_size);
+
 	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!buf)
 		goto bail;
 
-	o2hb_fill_node_map(map, sizeof(map));
+	switch (db->db_type) {
+	case O2HB_DB_TYPE_LIVENODES:
+	case O2HB_DB_TYPE_LIVEREGIONS:
+	case O2HB_DB_TYPE_QUORUMREGIONS:
+	case O2HB_DB_TYPE_FAILEDREGIONS:
+		spin_lock(&o2hb_live_lock);
+		memcpy(map, db->db_data, db->db_size);
+		spin_unlock(&o2hb_live_lock);
+		break;
 
-	while ((i = find_next_bit(map, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES)
+	case O2HB_DB_TYPE_REGION_LIVENODES:
+		spin_lock(&o2hb_live_lock);
+		reg = (struct o2hb_region *)db->db_data;
+		memcpy(map, reg->hr_live_node_bitmap, db->db_size);
+		spin_unlock(&o2hb_live_lock);
+		break;
+
+	case O2HB_DB_TYPE_REGION_NUMBER:
+		reg = (struct o2hb_region *)db->db_data;
+		out += snprintf(buf + out, PAGE_SIZE - out, "%d\n",
+				reg->hr_region_num);
+		goto done;
+
+	case O2HB_DB_TYPE_REGION_ELAPSED_TIME:
+		reg = (struct o2hb_region *)db->db_data;
+		out += snprintf(buf + out, PAGE_SIZE - out, "%u\n",
+				jiffies_to_msecs(jiffies -
+						 reg->hr_last_timeout_start));
+		goto done;
+
+	default:
+		goto done;
+	}
+
+	while ((i = find_next_bit(map, db->db_len, i + 1)) < db->db_len)
 		out += snprintf(buf + out, PAGE_SIZE - out, "%d ", i);
 	out += snprintf(buf + out, PAGE_SIZE - out, "\n");
 
+done:
 	i_size_write(inode, out);
 
 	file->private_data = buf;
@@ -978,10 +1198,104 @@
 
 void o2hb_exit(void)
 {
-	if (o2hb_debug_livenodes)
-		debugfs_remove(o2hb_debug_livenodes);
-	if (o2hb_debug_dir)
-		debugfs_remove(o2hb_debug_dir);
+	kfree(o2hb_db_livenodes);
+	kfree(o2hb_db_liveregions);
+	kfree(o2hb_db_quorumregions);
+	kfree(o2hb_db_failedregions);
+	debugfs_remove(o2hb_debug_failedregions);
+	debugfs_remove(o2hb_debug_quorumregions);
+	debugfs_remove(o2hb_debug_liveregions);
+	debugfs_remove(o2hb_debug_livenodes);
+	debugfs_remove(o2hb_debug_dir);
+}
+
+static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir,
+					struct o2hb_debug_buf **db, int db_len,
+					int type, int size, int len, void *data)
+{
+	*db = kmalloc(db_len, GFP_KERNEL);
+	if (!*db)
+		return NULL;
+
+	(*db)->db_type = type;
+	(*db)->db_size = size;
+	(*db)->db_len = len;
+	(*db)->db_data = data;
+
+	return debugfs_create_file(name, S_IFREG|S_IRUSR, dir, *db,
+				   &o2hb_debug_fops);
+}
+
+static int o2hb_debug_init(void)
+{
+	int ret = -ENOMEM;
+
+	o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL);
+	if (!o2hb_debug_dir) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	o2hb_debug_livenodes = o2hb_debug_create(O2HB_DEBUG_LIVENODES,
+						 o2hb_debug_dir,
+						 &o2hb_db_livenodes,
+						 sizeof(*o2hb_db_livenodes),
+						 O2HB_DB_TYPE_LIVENODES,
+						 sizeof(o2hb_live_node_bitmap),
+						 O2NM_MAX_NODES,
+						 o2hb_live_node_bitmap);
+	if (!o2hb_debug_livenodes) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	o2hb_debug_liveregions = o2hb_debug_create(O2HB_DEBUG_LIVEREGIONS,
+						   o2hb_debug_dir,
+						   &o2hb_db_liveregions,
+						   sizeof(*o2hb_db_liveregions),
+						   O2HB_DB_TYPE_LIVEREGIONS,
+						   sizeof(o2hb_live_region_bitmap),
+						   O2NM_MAX_REGIONS,
+						   o2hb_live_region_bitmap);
+	if (!o2hb_debug_liveregions) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	o2hb_debug_quorumregions =
+			o2hb_debug_create(O2HB_DEBUG_QUORUMREGIONS,
+					  o2hb_debug_dir,
+					  &o2hb_db_quorumregions,
+					  sizeof(*o2hb_db_quorumregions),
+					  O2HB_DB_TYPE_QUORUMREGIONS,
+					  sizeof(o2hb_quorum_region_bitmap),
+					  O2NM_MAX_REGIONS,
+					  o2hb_quorum_region_bitmap);
+	if (!o2hb_debug_quorumregions) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	o2hb_debug_failedregions =
+			o2hb_debug_create(O2HB_DEBUG_FAILEDREGIONS,
+					  o2hb_debug_dir,
+					  &o2hb_db_failedregions,
+					  sizeof(*o2hb_db_failedregions),
+					  O2HB_DB_TYPE_FAILEDREGIONS,
+					  sizeof(o2hb_failed_region_bitmap),
+					  O2NM_MAX_REGIONS,
+					  o2hb_failed_region_bitmap);
+	if (!o2hb_debug_failedregions) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	ret = 0;
+bail:
+	if (ret)
+		o2hb_exit();
+
+	return ret;
 }
 
 int o2hb_init(void)
@@ -997,24 +1311,12 @@
 	INIT_LIST_HEAD(&o2hb_node_events);
 
 	memset(o2hb_live_node_bitmap, 0, sizeof(o2hb_live_node_bitmap));
+	memset(o2hb_region_bitmap, 0, sizeof(o2hb_region_bitmap));
+	memset(o2hb_live_region_bitmap, 0, sizeof(o2hb_live_region_bitmap));
+	memset(o2hb_quorum_region_bitmap, 0, sizeof(o2hb_quorum_region_bitmap));
+	memset(o2hb_failed_region_bitmap, 0, sizeof(o2hb_failed_region_bitmap));
 
-	o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL);
-	if (!o2hb_debug_dir) {
-		mlog_errno(-ENOMEM);
-		return -ENOMEM;
-	}
-
-	o2hb_debug_livenodes = debugfs_create_file(O2HB_DEBUG_LIVENODES,
-						   S_IFREG|S_IRUSR,
-						   o2hb_debug_dir, NULL,
-						   &o2hb_debug_fops);
-	if (!o2hb_debug_livenodes) {
-		mlog_errno(-ENOMEM);
-		debugfs_remove(o2hb_debug_dir);
-		return -ENOMEM;
-	}
-
-	return 0;
+	return o2hb_debug_init();
 }
 
 /* if we're already in a callback then we're already serialized by the sem */
@@ -1078,6 +1380,13 @@
 	if (reg->hr_slots)
 		kfree(reg->hr_slots);
 
+	kfree(reg->hr_db_regnum);
+	kfree(reg->hr_db_livenodes);
+	debugfs_remove(reg->hr_debug_livenodes);
+	debugfs_remove(reg->hr_debug_regnum);
+	debugfs_remove(reg->hr_debug_elapsed_time);
+	debugfs_remove(reg->hr_debug_dir);
+
 	spin_lock(&o2hb_live_lock);
 	list_del(&reg->hr_all_item);
 	spin_unlock(&o2hb_live_lock);
@@ -1441,6 +1750,8 @@
 	/* Ok, we were woken.  Make sure it wasn't by drop_item() */
 	spin_lock(&o2hb_live_lock);
 	hb_task = reg->hr_task;
+	if (o2hb_global_heartbeat_active())
+		set_bit(reg->hr_region_num, o2hb_live_region_bitmap);
 	spin_unlock(&o2hb_live_lock);
 
 	if (hb_task)
@@ -1448,6 +1759,10 @@
 	else
 		ret = -EIO;
 
+	if (hb_task && o2hb_global_heartbeat_active())
+		printk(KERN_NOTICE "o2hb: Heartbeat started on region %s\n",
+		       config_item_name(&reg->hr_item));
+
 out:
 	if (filp)
 		fput(filp);
@@ -1586,21 +1901,94 @@
 		: NULL;
 }
 
+static int o2hb_debug_region_init(struct o2hb_region *reg, struct dentry *dir)
+{
+	int ret = -ENOMEM;
+
+	reg->hr_debug_dir =
+		debugfs_create_dir(config_item_name(&reg->hr_item), dir);
+	if (!reg->hr_debug_dir) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	reg->hr_debug_livenodes =
+			o2hb_debug_create(O2HB_DEBUG_LIVENODES,
+					  reg->hr_debug_dir,
+					  &(reg->hr_db_livenodes),
+					  sizeof(*(reg->hr_db_livenodes)),
+					  O2HB_DB_TYPE_REGION_LIVENODES,
+					  sizeof(reg->hr_live_node_bitmap),
+					  O2NM_MAX_NODES, reg);
+	if (!reg->hr_debug_livenodes) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	reg->hr_debug_regnum =
+			o2hb_debug_create(O2HB_DEBUG_REGION_NUMBER,
+					  reg->hr_debug_dir,
+					  &(reg->hr_db_regnum),
+					  sizeof(*(reg->hr_db_regnum)),
+					  O2HB_DB_TYPE_REGION_NUMBER,
+					  0, O2NM_MAX_NODES, reg);
+	if (!reg->hr_debug_regnum) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	reg->hr_debug_elapsed_time =
+			o2hb_debug_create(O2HB_DEBUG_REGION_ELAPSED_TIME,
+					  reg->hr_debug_dir,
+					  &(reg->hr_db_elapsed_time),
+					  sizeof(*(reg->hr_db_elapsed_time)),
+					  O2HB_DB_TYPE_REGION_ELAPSED_TIME,
+					  0, 0, reg);
+	if (!reg->hr_debug_elapsed_time) {
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	ret = 0;
+bail:
+	return ret;
+}
+
 static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *group,
 							  const char *name)
 {
 	struct o2hb_region *reg = NULL;
+	int ret;
 
 	reg = kzalloc(sizeof(struct o2hb_region), GFP_KERNEL);
 	if (reg == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	config_item_init_type_name(&reg->hr_item, name, &o2hb_region_type);
+	if (strlen(name) > O2HB_MAX_REGION_NAME_LEN)
+		return ERR_PTR(-ENAMETOOLONG);
 
 	spin_lock(&o2hb_live_lock);
+	reg->hr_region_num = 0;
+	if (o2hb_global_heartbeat_active()) {
+		reg->hr_region_num = find_first_zero_bit(o2hb_region_bitmap,
+							 O2NM_MAX_REGIONS);
+		if (reg->hr_region_num >= O2NM_MAX_REGIONS) {
+			spin_unlock(&o2hb_live_lock);
+			return ERR_PTR(-EFBIG);
+		}
+		set_bit(reg->hr_region_num, o2hb_region_bitmap);
+	}
 	list_add_tail(&reg->hr_all_item, &o2hb_all_regions);
 	spin_unlock(&o2hb_live_lock);
 
+	config_item_init_type_name(&reg->hr_item, name, &o2hb_region_type);
+
+	ret = o2hb_debug_region_init(reg, o2hb_debug_dir);
+	if (ret) {
+		config_item_put(&reg->hr_item);
+		return ERR_PTR(ret);
+	}
+
 	return &reg->hr_item;
 }
 
@@ -1612,6 +2000,10 @@
 
 	/* stop the thread when the user removes the region dir */
 	spin_lock(&o2hb_live_lock);
+	if (o2hb_global_heartbeat_active()) {
+		clear_bit(reg->hr_region_num, o2hb_region_bitmap);
+		clear_bit(reg->hr_region_num, o2hb_live_region_bitmap);
+	}
 	hb_task = reg->hr_task;
 	reg->hr_task = NULL;
 	spin_unlock(&o2hb_live_lock);
@@ -1628,6 +2020,9 @@
 		wake_up(&o2hb_steady_queue);
 	}
 
+	if (o2hb_global_heartbeat_active())
+		printk(KERN_NOTICE "o2hb: Heartbeat stopped on region %s\n",
+		       config_item_name(&reg->hr_item));
 	config_item_put(item);
 }
 
@@ -1688,6 +2083,41 @@
 	return count;
 }
 
+static
+ssize_t o2hb_heartbeat_group_mode_show(struct o2hb_heartbeat_group *group,
+				       char *page)
+{
+	return sprintf(page, "%s\n",
+		       o2hb_heartbeat_mode_desc[o2hb_heartbeat_mode]);
+}
+
+static
+ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group,
+					const char *page, size_t count)
+{
+	unsigned int i;
+	int ret;
+	size_t len;
+
+	len = (page[count - 1] == '\n') ? count - 1 : count;
+	if (!len)
+		return -EINVAL;
+
+	for (i = 0; i < O2HB_HEARTBEAT_NUM_MODES; ++i) {
+		if (strnicmp(page, o2hb_heartbeat_mode_desc[i], len))
+			continue;
+
+		ret = o2hb_global_hearbeat_mode_set(i);
+		if (!ret)
+			printk(KERN_NOTICE "o2hb: Heartbeat mode set to %s\n",
+			       o2hb_heartbeat_mode_desc[i]);
+		return count;
+	}
+
+	return -EINVAL;
+
+}
+
 static struct o2hb_heartbeat_group_attribute o2hb_heartbeat_group_attr_threshold = {
 	.attr	= { .ca_owner = THIS_MODULE,
 		    .ca_name = "dead_threshold",
@@ -1696,8 +2126,17 @@
 	.store	= o2hb_heartbeat_group_threshold_store,
 };
 
+static struct o2hb_heartbeat_group_attribute o2hb_heartbeat_group_attr_mode = {
+	.attr   = { .ca_owner = THIS_MODULE,
+		.ca_name = "mode",
+		.ca_mode = S_IRUGO | S_IWUSR },
+	.show   = o2hb_heartbeat_group_mode_show,
+	.store  = o2hb_heartbeat_group_mode_store,
+};
+
 static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
 	&o2hb_heartbeat_group_attr_threshold.attr,
+	&o2hb_heartbeat_group_attr_mode.attr,
 	NULL,
 };
 
@@ -1963,3 +2402,34 @@
 	spin_unlock(&o2hb_live_lock);
 }
 EXPORT_SYMBOL_GPL(o2hb_stop_all_regions);
+
+int o2hb_get_all_regions(char *region_uuids, u8 max_regions)
+{
+	struct o2hb_region *reg;
+	int numregs = 0;
+	char *p;
+
+	spin_lock(&o2hb_live_lock);
+
+	p = region_uuids;
+	list_for_each_entry(reg, &o2hb_all_regions, hr_all_item) {
+		mlog(0, "Region: %s\n", config_item_name(&reg->hr_item));
+		if (numregs < max_regions) {
+			memcpy(p, config_item_name(&reg->hr_item),
+			       O2HB_MAX_REGION_NAME_LEN);
+			p += O2HB_MAX_REGION_NAME_LEN;
+		}
+		numregs++;
+	}
+
+	spin_unlock(&o2hb_live_lock);
+
+	return numregs;
+}
+EXPORT_SYMBOL_GPL(o2hb_get_all_regions);
+
+int o2hb_global_heartbeat_active(void)
+{
+	return (o2hb_heartbeat_mode == O2HB_HEARTBEAT_GLOBAL);
+}
+EXPORT_SYMBOL(o2hb_global_heartbeat_active);
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index 2f16492..00ad8e8 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -31,6 +31,8 @@
 
 #define O2HB_REGION_TIMEOUT_MS		2000
 
+#define O2HB_MAX_REGION_NAME_LEN	32
+
 /* number of changes to be seen as live */
 #define O2HB_LIVE_THRESHOLD	   2
 /* number of equal samples to be seen as dead */
@@ -81,5 +83,7 @@
 int o2hb_check_node_heartbeating_from_callback(u8 node_num);
 int o2hb_check_local_node_heartbeating(void);
 void o2hb_stop_all_regions(void);
+int o2hb_get_all_regions(char *region_uuids, u8 numregions);
+int o2hb_global_heartbeat_active(void);
 
 #endif /* O2CLUSTER_HEARTBEAT_H */
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index fd96e2a..ea2ed9f 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -119,7 +119,8 @@
 #define ML_ERROR	0x0000000100000000ULL /* sent to KERN_ERR */
 #define ML_NOTICE	0x0000000200000000ULL /* setn to KERN_NOTICE */
 #define ML_KTHREAD	0x0000000400000000ULL /* kernel thread activity */
-#define	ML_RESERVATIONS	0x0000000800000000ULL /* ocfs2 alloc reservations */
+#define ML_RESERVATIONS	0x0000000800000000ULL /* ocfs2 alloc reservations */
+#define ML_CLUSTER	0x0000001000000000ULL /* cluster stack */
 
 #define MLOG_INITIAL_AND_MASK (ML_ERROR|ML_NOTICE)
 #define MLOG_INITIAL_NOT_MASK (ML_ENTRY|ML_EXIT)
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index ed0c9f3..bb24064 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -711,6 +711,8 @@
 	config_item_init_type_name(&node->nd_item, name, &o2nm_node_type);
 	spin_lock_init(&node->nd_lock);
 
+	mlog(ML_CLUSTER, "o2nm: Registering node %s\n", name);
+
 	return &node->nd_item;
 }
 
@@ -744,6 +746,9 @@
 	}
 	write_unlock(&cluster->cl_nodes_lock);
 
+	mlog(ML_CLUSTER, "o2nm: Unregistered node %s\n",
+	     config_item_name(&node->nd_item));
+
 	config_item_put(item);
 }
 
diff --git a/fs/ocfs2/cluster/ocfs2_nodemanager.h b/fs/ocfs2/cluster/ocfs2_nodemanager.h
index 5b9854b..49b5943 100644
--- a/fs/ocfs2/cluster/ocfs2_nodemanager.h
+++ b/fs/ocfs2/cluster/ocfs2_nodemanager.h
@@ -36,4 +36,10 @@
 /* host name, group name, cluster name all 64 bytes */
 #define O2NM_MAX_NAME_LEN        64    // __NEW_UTS_LEN
 
+/*
+ * Maximum number of global heartbeat regions allowed.
+ * **CAUTION**  Changing this number will break dlm compatibility.
+ */
+#define O2NM_MAX_REGIONS	32
+
 #endif /* _OCFS2_NODEMANAGER_H */
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index cbe2f05..9aa426e 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1696,6 +1696,9 @@
 {
 	o2quo_hb_down(node_num);
 
+	if (!node)
+		return;
+
 	if (node_num != o2nm_this_node())
 		o2net_disconnect_node(node);
 
@@ -1709,6 +1712,8 @@
 
 	o2quo_hb_up(node_num);
 
+	BUG_ON(!node);
+
 	/* ensure an immediate connect attempt */
 	nn->nn_last_connect_attempt = jiffies -
 		(msecs_to_jiffies(o2net_reconnect_delay()) + 1);
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index b4957c7..edaded4 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -40,6 +40,14 @@
 #include "inode.h"
 #include "super.h"
 
+void ocfs2_dentry_attach_gen(struct dentry *dentry)
+{
+	unsigned long gen =
+		OCFS2_I(dentry->d_parent->d_inode)->ip_dir_lock_gen;
+	BUG_ON(dentry->d_inode);
+	dentry->d_fsdata = (void *)gen;
+}
+
 
 static int ocfs2_dentry_revalidate(struct dentry *dentry,
 				   struct nameidata *nd)
@@ -51,11 +59,20 @@
 	mlog_entry("(0x%p, '%.*s')\n", dentry,
 		   dentry->d_name.len, dentry->d_name.name);
 
-	/* Never trust a negative dentry - force a new lookup. */
+	/* For a negative dentry -
+	 * check the generation number of the parent and compare with the
+	 * one stored in the inode.
+	 */
 	if (inode == NULL) {
-		mlog(0, "negative dentry: %.*s\n", dentry->d_name.len,
-		     dentry->d_name.name);
-		goto bail;
+		unsigned long gen = (unsigned long) dentry->d_fsdata;
+		unsigned long pgen =
+			OCFS2_I(dentry->d_parent->d_inode)->ip_dir_lock_gen;
+		mlog(0, "negative dentry: %.*s parent gen: %lu "
+			"dentry gen: %lu\n",
+			dentry->d_name.len, dentry->d_name.name, pgen, gen);
+		if (gen != pgen)
+			goto bail;
+		goto valid;
 	}
 
 	BUG_ON(!osb);
@@ -96,6 +113,7 @@
 		goto bail;
 	}
 
+valid:
 	ret = 1;
 
 bail:
@@ -227,6 +245,12 @@
 	if (!inode)
 		return 0;
 
+	if (!dentry->d_inode && dentry->d_fsdata) {
+		/* Converting a negative dentry to positive
+		   Clear dentry->d_fsdata */
+		dentry->d_fsdata = dl = NULL;
+	}
+
 	if (dl) {
 		mlog_bug_on_msg(dl->dl_parent_blkno != parent_blkno,
 				" \"%.*s\": old parent: %llu, new: %llu\n",
@@ -452,6 +476,7 @@
 
 out:
 	iput(inode);
+	ocfs2_dentry_attach_gen(dentry);
 }
 
 /*
diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h
index f5dd178..b79eff7 100644
--- a/fs/ocfs2/dcache.h
+++ b/fs/ocfs2/dcache.h
@@ -64,5 +64,6 @@
 		       struct inode *old_dir, struct inode *new_dir);
 
 extern spinlock_t dentry_attach_lock;
+void ocfs2_dentry_attach_gen(struct dentry *dentry);
 
 #endif /* OCFS2_DCACHE_H */
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 7652989..b36d0bf 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -445,7 +445,9 @@
 	DLM_LOCK_REQUEST_MSG,	 /* 515 */
 	DLM_RECO_DATA_DONE_MSG,	 /* 516 */
 	DLM_BEGIN_RECO_MSG,	 /* 517 */
-	DLM_FINALIZE_RECO_MSG	 /* 518 */
+	DLM_FINALIZE_RECO_MSG,	 /* 518 */
+	DLM_QUERY_REGION,	 /* 519 */
+	DLM_QUERY_NODEINFO,	 /* 520 */
 };
 
 struct dlm_reco_node_data
@@ -727,6 +729,31 @@
 	u8 domain[O2NM_MAX_NAME_LEN];
 };
 
+struct dlm_query_region {
+	u8 qr_node;
+	u8 qr_numregions;
+	u8 qr_namelen;
+	u8 pad1;
+	u8 qr_domain[O2NM_MAX_NAME_LEN];
+	u8 qr_regions[O2HB_MAX_REGION_NAME_LEN * O2NM_MAX_REGIONS];
+};
+
+struct dlm_node_info {
+	u8 ni_nodenum;
+	u8 pad1;
+	u16 ni_ipv4_port;
+	u32 ni_ipv4_address;
+};
+
+struct dlm_query_nodeinfo {
+	u8 qn_nodenum;
+	u8 qn_numnodes;
+	u8 qn_namelen;
+	u8 pad1;
+	u8 qn_domain[O2NM_MAX_NAME_LEN];
+	struct dlm_node_info qn_nodes[O2NM_MAX_NODES];
+};
+
 struct dlm_exit_domain
 {
 	u8 node_idx;
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 901ca52..272ec86 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -493,7 +493,7 @@
 	struct hlist_head *bucket;
 	struct hlist_node *list;
 	int i, out = 0;
-	unsigned long total = 0, longest = 0, bktcnt;
+	unsigned long total = 0, longest = 0, bucket_count = 0;
 
 	out += snprintf(db->buf + out, db->len - out,
 			"Dumping MLEs for Domain: %s\n", dlm->name);
@@ -505,13 +505,13 @@
 			mle = hlist_entry(list, struct dlm_master_list_entry,
 					  master_hash_node);
 			++total;
-			++bktcnt;
+			++bucket_count;
 			if (db->len - out < 200)
 				continue;
 			out += dump_mle(mle, db->buf + out, db->len - out);
 		}
-		longest = max(longest, bktcnt);
-		bktcnt = 0;
+		longest = max(longest, bucket_count);
+		bucket_count = 0;
 	}
 	spin_unlock(&dlm->master_lock);
 
@@ -782,7 +782,9 @@
 
 	/* Domain: xxxxxxxxxx  Key: 0xdfbac769 */
 	out += snprintf(db->buf + out, db->len - out,
-			"Domain: %s  Key: 0x%08x\n", dlm->name, dlm->key);
+			"Domain: %s  Key: 0x%08x  Protocol: %d.%d\n",
+			dlm->name, dlm->key, dlm->dlm_locking_proto.pv_major,
+			dlm->dlm_locking_proto.pv_minor);
 
 	/* Thread Pid: xxx  Node: xxx  State: xxxxx */
 	out += snprintf(db->buf + out, db->len - out,
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 11a5c87..58a93b9 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -128,10 +128,14 @@
  * will have a negotiated version with the same major number and a minor
  * number equal or smaller.  The dlm_ctxt->dlm_locking_proto field should
  * be used to determine what a running domain is actually using.
+ *
+ * New in version 1.1:
+ *	- Message DLM_QUERY_REGION added to support global heartbeat
+ *	- Message DLM_QUERY_NODEINFO added to allow online node removes
  */
 static const struct dlm_protocol_version dlm_protocol = {
 	.pv_major = 1,
-	.pv_minor = 0,
+	.pv_minor = 1,
 };
 
 #define DLM_DOMAIN_BACKOFF_MS 200
@@ -142,6 +146,8 @@
 				     void **ret_data);
 static int dlm_cancel_join_handler(struct o2net_msg *msg, u32 len, void *data,
 				   void **ret_data);
+static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
+				    void *data, void **ret_data);
 static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data,
 				   void **ret_data);
 static int dlm_protocol_compare(struct dlm_protocol_version *existing,
@@ -921,6 +927,370 @@
 	return 0;
 }
 
+static int dlm_match_regions(struct dlm_ctxt *dlm,
+			     struct dlm_query_region *qr)
+{
+	char *local = NULL, *remote = qr->qr_regions;
+	char *l, *r;
+	int localnr, i, j, foundit;
+	int status = 0;
+
+	if (!o2hb_global_heartbeat_active()) {
+		if (qr->qr_numregions) {
+			mlog(ML_ERROR, "Domain %s: Joining node %d has global "
+			     "heartbeat enabled but local node %d does not\n",
+			     qr->qr_domain, qr->qr_node, dlm->node_num);
+			status = -EINVAL;
+		}
+		goto bail;
+	}
+
+	if (o2hb_global_heartbeat_active() && !qr->qr_numregions) {
+		mlog(ML_ERROR, "Domain %s: Local node %d has global "
+		     "heartbeat enabled but joining node %d does not\n",
+		     qr->qr_domain, dlm->node_num, qr->qr_node);
+		status = -EINVAL;
+		goto bail;
+	}
+
+	r = remote;
+	for (i = 0; i < qr->qr_numregions; ++i) {
+		mlog(0, "Region %.*s\n", O2HB_MAX_REGION_NAME_LEN, r);
+		r += O2HB_MAX_REGION_NAME_LEN;
+	}
+
+	local = kmalloc(sizeof(qr->qr_regions), GFP_KERNEL);
+	if (!local) {
+		status = -ENOMEM;
+		goto bail;
+	}
+
+	localnr = o2hb_get_all_regions(local, O2NM_MAX_REGIONS);
+
+	/* compare local regions with remote */
+	l = local;
+	for (i = 0; i < localnr; ++i) {
+		foundit = 0;
+		r = remote;
+		for (j = 0; j <= qr->qr_numregions; ++j) {
+			if (!memcmp(l, r, O2HB_MAX_REGION_NAME_LEN)) {
+				foundit = 1;
+				break;
+			}
+			r += O2HB_MAX_REGION_NAME_LEN;
+		}
+		if (!foundit) {
+			status = -EINVAL;
+			mlog(ML_ERROR, "Domain %s: Region '%.*s' registered "
+			     "in local node %d but not in joining node %d\n",
+			     qr->qr_domain, O2HB_MAX_REGION_NAME_LEN, l,
+			     dlm->node_num, qr->qr_node);
+			goto bail;
+		}
+		l += O2HB_MAX_REGION_NAME_LEN;
+	}
+
+	/* compare remote with local regions */
+	r = remote;
+	for (i = 0; i < qr->qr_numregions; ++i) {
+		foundit = 0;
+		l = local;
+		for (j = 0; j < localnr; ++j) {
+			if (!memcmp(r, l, O2HB_MAX_REGION_NAME_LEN)) {
+				foundit = 1;
+				break;
+			}
+			l += O2HB_MAX_REGION_NAME_LEN;
+		}
+		if (!foundit) {
+			status = -EINVAL;
+			mlog(ML_ERROR, "Domain %s: Region '%.*s' registered "
+			     "in joining node %d but not in local node %d\n",
+			     qr->qr_domain, O2HB_MAX_REGION_NAME_LEN, r,
+			     qr->qr_node, dlm->node_num);
+			goto bail;
+		}
+		r += O2HB_MAX_REGION_NAME_LEN;
+	}
+
+bail:
+	kfree(local);
+
+	return status;
+}
+
+static int dlm_send_regions(struct dlm_ctxt *dlm, unsigned long *node_map)
+{
+	struct dlm_query_region *qr = NULL;
+	int status, ret = 0, i;
+	char *p;
+
+	if (find_next_bit(node_map, O2NM_MAX_NODES, 0) >= O2NM_MAX_NODES)
+		goto bail;
+
+	qr = kzalloc(sizeof(struct dlm_query_region), GFP_KERNEL);
+	if (!qr) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	qr->qr_node = dlm->node_num;
+	qr->qr_namelen = strlen(dlm->name);
+	memcpy(qr->qr_domain, dlm->name, qr->qr_namelen);
+	/* if local hb, the numregions will be zero */
+	if (o2hb_global_heartbeat_active())
+		qr->qr_numregions = o2hb_get_all_regions(qr->qr_regions,
+							 O2NM_MAX_REGIONS);
+
+	p = qr->qr_regions;
+	for (i = 0; i < qr->qr_numregions; ++i, p += O2HB_MAX_REGION_NAME_LEN)
+		mlog(0, "Region %.*s\n", O2HB_MAX_REGION_NAME_LEN, p);
+
+	i = -1;
+	while ((i = find_next_bit(node_map, O2NM_MAX_NODES,
+				  i + 1)) < O2NM_MAX_NODES) {
+		if (i == dlm->node_num)
+			continue;
+
+		mlog(0, "Sending regions to node %d\n", i);
+
+		ret = o2net_send_message(DLM_QUERY_REGION, DLM_MOD_KEY, qr,
+					 sizeof(struct dlm_query_region),
+					 i, &status);
+		if (ret >= 0)
+			ret = status;
+		if (ret) {
+			mlog(ML_ERROR, "Region mismatch %d, node %d\n",
+			     ret, i);
+			break;
+		}
+	}
+
+bail:
+	kfree(qr);
+	return ret;
+}
+
+static int dlm_query_region_handler(struct o2net_msg *msg, u32 len,
+				    void *data, void **ret_data)
+{
+	struct dlm_query_region *qr;
+	struct dlm_ctxt *dlm = NULL;
+	int status = 0;
+	int locked = 0;
+
+	qr = (struct dlm_query_region *) msg->buf;
+
+	mlog(0, "Node %u queries hb regions on domain %s\n", qr->qr_node,
+	     qr->qr_domain);
+
+	status = -EINVAL;
+
+	spin_lock(&dlm_domain_lock);
+	dlm = __dlm_lookup_domain_full(qr->qr_domain, qr->qr_namelen);
+	if (!dlm) {
+		mlog(ML_ERROR, "Node %d queried hb regions on domain %s "
+		     "before join domain\n", qr->qr_node, qr->qr_domain);
+		goto bail;
+	}
+
+	spin_lock(&dlm->spinlock);
+	locked = 1;
+	if (dlm->joining_node != qr->qr_node) {
+		mlog(ML_ERROR, "Node %d queried hb regions on domain %s "
+		     "but joining node is %d\n", qr->qr_node, qr->qr_domain,
+		     dlm->joining_node);
+		goto bail;
+	}
+
+	/* Support for global heartbeat was added in 1.1 */
+	if (dlm->dlm_locking_proto.pv_major == 1 &&
+	    dlm->dlm_locking_proto.pv_minor == 0) {
+		mlog(ML_ERROR, "Node %d queried hb regions on domain %s "
+		     "but active dlm protocol is %d.%d\n", qr->qr_node,
+		     qr->qr_domain, dlm->dlm_locking_proto.pv_major,
+		     dlm->dlm_locking_proto.pv_minor);
+		goto bail;
+	}
+
+	status = dlm_match_regions(dlm, qr);
+
+bail:
+	if (locked)
+		spin_unlock(&dlm->spinlock);
+	spin_unlock(&dlm_domain_lock);
+
+	return status;
+}
+
+static int dlm_match_nodes(struct dlm_ctxt *dlm, struct dlm_query_nodeinfo *qn)
+{
+	struct o2nm_node *local;
+	struct dlm_node_info *remote;
+	int i, j;
+	int status = 0;
+
+	for (j = 0; j < qn->qn_numnodes; ++j)
+		mlog(0, "Node %3d, %pI4:%u\n", qn->qn_nodes[j].ni_nodenum,
+		     &(qn->qn_nodes[j].ni_ipv4_address),
+		     ntohs(qn->qn_nodes[j].ni_ipv4_port));
+
+	for (i = 0; i < O2NM_MAX_NODES && !status; ++i) {
+		local = o2nm_get_node_by_num(i);
+		remote = NULL;
+		for (j = 0; j < qn->qn_numnodes; ++j) {
+			if (qn->qn_nodes[j].ni_nodenum == i) {
+				remote = &(qn->qn_nodes[j]);
+				break;
+			}
+		}
+
+		if (!local && !remote)
+			continue;
+
+		if ((local && !remote) || (!local && remote))
+			status = -EINVAL;
+
+		if (!status &&
+		    ((remote->ni_nodenum != local->nd_num) ||
+		     (remote->ni_ipv4_port != local->nd_ipv4_port) ||
+		     (remote->ni_ipv4_address != local->nd_ipv4_address)))
+			status = -EINVAL;
+
+		if (status) {
+			if (remote && !local)
+				mlog(ML_ERROR, "Domain %s: Node %d (%pI4:%u) "
+				     "registered in joining node %d but not in "
+				     "local node %d\n", qn->qn_domain,
+				     remote->ni_nodenum,
+				     &(remote->ni_ipv4_address),
+				     ntohs(remote->ni_ipv4_port),
+				     qn->qn_nodenum, dlm->node_num);
+			if (local && !remote)
+				mlog(ML_ERROR, "Domain %s: Node %d (%pI4:%u) "
+				     "registered in local node %d but not in "
+				     "joining node %d\n", qn->qn_domain,
+				     local->nd_num, &(local->nd_ipv4_address),
+				     ntohs(local->nd_ipv4_port),
+				     dlm->node_num, qn->qn_nodenum);
+			BUG_ON((!local && !remote));
+		}
+
+		if (local)
+			o2nm_node_put(local);
+	}
+
+	return status;
+}
+
+static int dlm_send_nodeinfo(struct dlm_ctxt *dlm, unsigned long *node_map)
+{
+	struct dlm_query_nodeinfo *qn = NULL;
+	struct o2nm_node *node;
+	int ret = 0, status, count, i;
+
+	if (find_next_bit(node_map, O2NM_MAX_NODES, 0) >= O2NM_MAX_NODES)
+		goto bail;
+
+	qn = kzalloc(sizeof(struct dlm_query_nodeinfo), GFP_KERNEL);
+	if (!qn) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto bail;
+	}
+
+	for (i = 0, count = 0; i < O2NM_MAX_NODES; ++i) {
+		node = o2nm_get_node_by_num(i);
+		if (!node)
+			continue;
+		qn->qn_nodes[count].ni_nodenum = node->nd_num;
+		qn->qn_nodes[count].ni_ipv4_port = node->nd_ipv4_port;
+		qn->qn_nodes[count].ni_ipv4_address = node->nd_ipv4_address;
+		mlog(0, "Node %3d, %pI4:%u\n", node->nd_num,
+		     &(node->nd_ipv4_address), ntohs(node->nd_ipv4_port));
+		++count;
+		o2nm_node_put(node);
+	}
+
+	qn->qn_nodenum = dlm->node_num;
+	qn->qn_numnodes = count;
+	qn->qn_namelen = strlen(dlm->name);
+	memcpy(qn->qn_domain, dlm->name, qn->qn_namelen);
+
+	i = -1;
+	while ((i = find_next_bit(node_map, O2NM_MAX_NODES,
+				  i + 1)) < O2NM_MAX_NODES) {
+		if (i == dlm->node_num)
+			continue;
+
+		mlog(0, "Sending nodeinfo to node %d\n", i);
+
+		ret = o2net_send_message(DLM_QUERY_NODEINFO, DLM_MOD_KEY,
+					 qn, sizeof(struct dlm_query_nodeinfo),
+					 i, &status);
+		if (ret >= 0)
+			ret = status;
+		if (ret) {
+			mlog(ML_ERROR, "node mismatch %d, node %d\n", ret, i);
+			break;
+		}
+	}
+
+bail:
+	kfree(qn);
+	return ret;
+}
+
+static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
+				      void *data, void **ret_data)
+{
+	struct dlm_query_nodeinfo *qn;
+	struct dlm_ctxt *dlm = NULL;
+	int locked = 0, status = -EINVAL;
+
+	qn = (struct dlm_query_nodeinfo *) msg->buf;
+
+	mlog(0, "Node %u queries nodes on domain %s\n", qn->qn_nodenum,
+	     qn->qn_domain);
+
+	spin_lock(&dlm_domain_lock);
+	dlm = __dlm_lookup_domain_full(qn->qn_domain, qn->qn_namelen);
+	if (!dlm) {
+		mlog(ML_ERROR, "Node %d queried nodes on domain %s before "
+		     "join domain\n", qn->qn_nodenum, qn->qn_domain);
+		goto bail;
+	}
+
+	spin_lock(&dlm->spinlock);
+	locked = 1;
+	if (dlm->joining_node != qn->qn_nodenum) {
+		mlog(ML_ERROR, "Node %d queried nodes on domain %s but "
+		     "joining node is %d\n", qn->qn_nodenum, qn->qn_domain,
+		     dlm->joining_node);
+		goto bail;
+	}
+
+	/* Support for node query was added in 1.1 */
+	if (dlm->dlm_locking_proto.pv_major == 1 &&
+	    dlm->dlm_locking_proto.pv_minor == 0) {
+		mlog(ML_ERROR, "Node %d queried nodes on domain %s "
+		     "but active dlm protocol is %d.%d\n", qn->qn_nodenum,
+		     qn->qn_domain, dlm->dlm_locking_proto.pv_major,
+		     dlm->dlm_locking_proto.pv_minor);
+		goto bail;
+	}
+
+	status = dlm_match_nodes(dlm, qn);
+
+bail:
+	if (locked)
+		spin_unlock(&dlm->spinlock);
+	spin_unlock(&dlm_domain_lock);
+
+	return status;
+}
+
 static int dlm_cancel_join_handler(struct o2net_msg *msg, u32 len, void *data,
 				   void **ret_data)
 {
@@ -1241,6 +1611,20 @@
 	set_bit(dlm->node_num, dlm->domain_map);
 	spin_unlock(&dlm->spinlock);
 
+	/* Support for global heartbeat and node info was added in 1.1 */
+	if (dlm_protocol.pv_major > 1 || dlm_protocol.pv_minor > 0) {
+		status = dlm_send_nodeinfo(dlm, ctxt->yes_resp_map);
+		if (status) {
+			mlog_errno(status);
+			goto bail;
+		}
+		status = dlm_send_regions(dlm, ctxt->yes_resp_map);
+		if (status) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	dlm_send_join_asserts(dlm, ctxt->yes_resp_map);
 
 	/* Joined state *must* be set before the joining node
@@ -1807,7 +2191,21 @@
 					sizeof(struct dlm_cancel_join),
 					dlm_cancel_join_handler,
 					NULL, NULL, &dlm_join_handlers);
+	if (status)
+		goto bail;
 
+	status = o2net_register_handler(DLM_QUERY_REGION, DLM_MOD_KEY,
+					sizeof(struct dlm_query_region),
+					dlm_query_region_handler,
+					NULL, NULL, &dlm_join_handlers);
+
+	if (status)
+		goto bail;
+
+	status = o2net_register_handler(DLM_QUERY_NODEINFO, DLM_MOD_KEY,
+					sizeof(struct dlm_query_nodeinfo),
+					dlm_query_nodeinfo_handler,
+					NULL, NULL, &dlm_join_handlers);
 bail:
 	if (status < 0)
 		dlm_unregister_net_handlers();
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index c2903b8..a7ebd9d 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -612,6 +612,7 @@
 	.poll		= dlmfs_file_poll,
 	.read		= dlmfs_file_read,
 	.write		= dlmfs_file_write,
+	.llseek		= default_llseek,
 };
 
 static const struct inode_operations dlmfs_dir_inode_operations = {
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 5e02a89..e8d94d7 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3635,10 +3635,18 @@
 {
 	struct inode *inode;
 	struct address_space *mapping;
+	struct ocfs2_inode_info *oi;
 
        	inode = ocfs2_lock_res_inode(lockres);
 	mapping = inode->i_mapping;
 
+	if (S_ISDIR(inode->i_mode)) {
+		oi = OCFS2_I(inode);
+		oi->ip_dir_lock_gen++;
+		mlog(0, "generation: %u\n", oi->ip_dir_lock_gen);
+		goto out;
+	}
+
 	if (!S_ISREG(inode->i_mode))
 		goto out;
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 9a03c15..9e8cc43 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -64,12 +64,6 @@
 
 #include "buffer_head_io.h"
 
-static int ocfs2_sync_inode(struct inode *inode)
-{
-	filemap_fdatawrite(inode->i_mapping);
-	return sync_mapping_buffers(inode->i_mapping);
-}
-
 static int ocfs2_init_file_private(struct inode *inode, struct file *file)
 {
 	struct ocfs2_file_private *fp;
@@ -180,16 +174,12 @@
 {
 	int err = 0;
 	journal_t *journal;
-	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = file->f_mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	mlog_entry("(0x%p, 0x%p, %d, '%.*s')\n", file, dentry, datasync,
-		   dentry->d_name.len, dentry->d_name.name);
-
-	err = ocfs2_sync_inode(dentry->d_inode);
-	if (err)
-		goto bail;
+	mlog_entry("(0x%p, %d, 0x%p, '%.*s')\n", file, datasync,
+		   file->f_path.dentry, file->f_path.dentry->d_name.len,
+		   file->f_path.dentry->d_name.name);
 
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) {
 		/*
@@ -370,7 +360,7 @@
 	if (!(ext_flags & OCFS2_EXT_REFCOUNTED))
 		goto out;
 
-	return ocfs2_refcount_cow(inode, fe_bh, cpos, 1, cpos+1);
+	return ocfs2_refcount_cow(inode, NULL, fe_bh, cpos, 1, cpos+1);
 
 out:
 	return status;
@@ -913,8 +903,8 @@
 		zero_clusters = last_cpos - zero_cpos;
 
 	if (needs_cow) {
-		rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos, zero_clusters,
-					UINT_MAX);
+		rc = ocfs2_refcount_cow(inode, NULL, di_bh, zero_cpos,
+					zero_clusters, UINT_MAX);
 		if (rc) {
 			mlog_errno(rc);
 			goto out;
@@ -2062,6 +2052,7 @@
 }
 
 static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
+					    struct file *file,
 					    loff_t pos, size_t count,
 					    int *meta_level)
 {
@@ -2079,7 +2070,7 @@
 
 	*meta_level = 1;
 
-	ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
+	ret = ocfs2_refcount_cow(inode, file, di_bh, cpos, clusters, UINT_MAX);
 	if (ret)
 		mlog_errno(ret);
 out:
@@ -2087,7 +2078,7 @@
 	return ret;
 }
 
-static int ocfs2_prepare_inode_for_write(struct dentry *dentry,
+static int ocfs2_prepare_inode_for_write(struct file *file,
 					 loff_t *ppos,
 					 size_t count,
 					 int appending,
@@ -2095,6 +2086,7 @@
 					 int *has_refcount)
 {
 	int ret = 0, meta_level = 0;
+	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	loff_t saved_pos, end;
 
@@ -2150,6 +2142,7 @@
 			meta_level = -1;
 
 			ret = ocfs2_prepare_inode_for_refcount(inode,
+							       file,
 							       saved_pos,
 							       count,
 							       &meta_level);
@@ -2232,6 +2225,8 @@
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+			       OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	mlog_entry("(0x%p, %u, '%.*s')\n", file,
 		   (unsigned int)nr_segs,
@@ -2255,16 +2250,39 @@
 		have_alloc_sem = 1;
 	}
 
-	/* concurrent O_DIRECT writes are allowed */
-	rw_level = !direct_io;
+	/*
+	 * Concurrent O_DIRECT writes are allowed with
+	 * mount_option "coherency=buffered".
+	 */
+	rw_level = (!direct_io || full_coherency);
+
 	ret = ocfs2_rw_lock(inode, rw_level);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out_sems;
 	}
 
+	/*
+	 * O_DIRECT writes with "coherency=full" need to take EX cluster
+	 * inode_lock to guarantee coherency.
+	 */
+	if (direct_io && full_coherency) {
+		/*
+		 * We need to take and drop the inode lock to force
+		 * other nodes to drop their caches.  Buffered I/O
+		 * already does this in write_begin().
+		 */
+		ret = ocfs2_inode_lock(inode, NULL, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out_sems;
+		}
+
+		ocfs2_inode_unlock(inode, 1);
+	}
+
 	can_do_direct = direct_io;
-	ret = ocfs2_prepare_inode_for_write(file->f_path.dentry, ppos,
+	ret = ocfs2_prepare_inode_for_write(file, ppos,
 					    iocb->ki_left, appending,
 					    &can_do_direct, &has_refcount);
 	if (ret < 0) {
@@ -2312,17 +2330,6 @@
 		written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
 						    ppos, count, ocount);
 		if (written < 0) {
-			/*
-			 * direct write may have instantiated a few
-			 * blocks outside i_size. Trim these off again.
-			 * Don't need i_size_read because we hold i_mutex.
-			 *
-			 * XXX(truncate): this looks buggy because ocfs2 did not
-			 * actually implement ->truncate.  Take a look at
-			 * the new truncate sequence and update this accordingly
-			 */
-			if (*ppos + count > inode->i_size)
-				truncate_setsize(inode, inode->i_size);
 			ret = written;
 			goto out_dio;
 		}
@@ -2394,7 +2401,7 @@
 {
 	int ret;
 
-	ret = ocfs2_prepare_inode_for_write(out->f_path.dentry,	&sd->pos,
+	ret = ocfs2_prepare_inode_for_write(out, &sd->pos,
 					    sd->total_len, 0, NULL, NULL);
 	if (ret < 0) {
 		mlog_errno(ret);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index eece3e0..f935fd6 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -335,6 +335,7 @@
 		    else
 			    inode->i_fop = &ocfs2_dops_no_plocks;
 		    i_size_write(inode, le64_to_cpu(fe->i_size));
+		    OCFS2_I(inode)->ip_dir_lock_gen = 1;
 		    break;
 	    case S_IFLNK:
 		    if (ocfs2_inode_is_fast_symlink(inode))
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 6de5a86..1c508b1 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -46,30 +46,28 @@
 	/* These fields are protected by ip_lock */
 	spinlock_t			ip_lock;
 	u32				ip_open_count;
-	u32				ip_clusters;
 	struct list_head		ip_io_markers;
+	u32				ip_clusters;
 
+	u16				ip_dyn_features;
 	struct mutex			ip_io_mutex;
-
 	u32				ip_flags; /* see below */
 	u32				ip_attr; /* inode attributes */
-	u16				ip_dyn_features;
 
 	/* protected by recovery_lock. */
 	struct inode			*ip_next_orphan;
 
-	u32				ip_dir_start_lookup;
-
 	struct ocfs2_caching_info	ip_metadata_cache;
-
 	struct ocfs2_extent_map		ip_extent_map;
-
 	struct inode			vfs_inode;
 	struct jbd2_inode		ip_jinode;
 
+	u32				ip_dir_start_lookup;
+
 	/* Only valid if the inode is the dir. */
 	u32				ip_last_used_slot;
 	u64				ip_last_used_group;
+	u32				ip_dir_lock_gen;
 
 	struct ocfs2_alloc_reservation	ip_la_data_resv;
 };
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 7d9d9c1..7a48681 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -26,6 +26,26 @@
 
 #include <linux/ext2_fs.h>
 
+#define o2info_from_user(a, b)	\
+		copy_from_user(&(a), (b), sizeof(a))
+#define o2info_to_user(a, b)	\
+		copy_to_user((typeof(a) __user *)b, &(a), sizeof(a))
+
+/*
+ * This call is void because we are already reporting an error that may
+ * be -EFAULT.  The error will be returned from the ioctl(2) call.  It's
+ * just a best-effort to tell userspace that this request caused the error.
+ */
+static inline void __o2info_set_request_error(struct ocfs2_info_request *kreq,
+					struct ocfs2_info_request __user *req)
+{
+	kreq->ir_flags |= OCFS2_INFO_FL_ERROR;
+	(void)put_user(kreq->ir_flags, (__u32 __user *)&(req->ir_flags));
+}
+
+#define o2info_set_request_error(a, b) \
+		__o2info_set_request_error((struct ocfs2_info_request *)&(a), b)
+
 static int ocfs2_get_inode_attr(struct inode *inode, unsigned *flags)
 {
 	int status;
@@ -109,6 +129,328 @@
 	return status;
 }
 
+int ocfs2_info_handle_blocksize(struct inode *inode,
+				struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_blocksize oib;
+
+	if (o2info_from_user(oib, req))
+		goto bail;
+
+	oib.ib_blocksize = inode->i_sb->s_blocksize;
+	oib.ib_req.ir_flags |= OCFS2_INFO_FL_FILLED;
+
+	if (o2info_to_user(oib, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(oib, req);
+
+	return status;
+}
+
+int ocfs2_info_handle_clustersize(struct inode *inode,
+				  struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_clustersize oic;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (o2info_from_user(oic, req))
+		goto bail;
+
+	oic.ic_clustersize = osb->s_clustersize;
+	oic.ic_req.ir_flags |= OCFS2_INFO_FL_FILLED;
+
+	if (o2info_to_user(oic, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(oic, req);
+
+	return status;
+}
+
+int ocfs2_info_handle_maxslots(struct inode *inode,
+			       struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_maxslots oim;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (o2info_from_user(oim, req))
+		goto bail;
+
+	oim.im_max_slots = osb->max_slots;
+	oim.im_req.ir_flags |= OCFS2_INFO_FL_FILLED;
+
+	if (o2info_to_user(oim, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(oim, req);
+
+	return status;
+}
+
+int ocfs2_info_handle_label(struct inode *inode,
+			    struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_label oil;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (o2info_from_user(oil, req))
+		goto bail;
+
+	memcpy(oil.il_label, osb->vol_label, OCFS2_MAX_VOL_LABEL_LEN);
+	oil.il_req.ir_flags |= OCFS2_INFO_FL_FILLED;
+
+	if (o2info_to_user(oil, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(oil, req);
+
+	return status;
+}
+
+int ocfs2_info_handle_uuid(struct inode *inode,
+			   struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_uuid oiu;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (o2info_from_user(oiu, req))
+		goto bail;
+
+	memcpy(oiu.iu_uuid_str, osb->uuid_str, OCFS2_TEXT_UUID_LEN + 1);
+	oiu.iu_req.ir_flags |= OCFS2_INFO_FL_FILLED;
+
+	if (o2info_to_user(oiu, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(oiu, req);
+
+	return status;
+}
+
+int ocfs2_info_handle_fs_features(struct inode *inode,
+				  struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_fs_features oif;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (o2info_from_user(oif, req))
+		goto bail;
+
+	oif.if_compat_features = osb->s_feature_compat;
+	oif.if_incompat_features = osb->s_feature_incompat;
+	oif.if_ro_compat_features = osb->s_feature_ro_compat;
+	oif.if_req.ir_flags |= OCFS2_INFO_FL_FILLED;
+
+	if (o2info_to_user(oif, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(oif, req);
+
+	return status;
+}
+
+int ocfs2_info_handle_journal_size(struct inode *inode,
+				   struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_journal_size oij;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+	if (o2info_from_user(oij, req))
+		goto bail;
+
+	oij.ij_journal_size = osb->journal->j_inode->i_size;
+
+	oij.ij_req.ir_flags |= OCFS2_INFO_FL_FILLED;
+
+	if (o2info_to_user(oij, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(oij, req);
+
+	return status;
+}
+
+int ocfs2_info_handle_unknown(struct inode *inode,
+			      struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_request oir;
+
+	if (o2info_from_user(oir, req))
+		goto bail;
+
+	oir.ir_flags &= ~OCFS2_INFO_FL_FILLED;
+
+	if (o2info_to_user(oir, req))
+		goto bail;
+
+	status = 0;
+bail:
+	if (status)
+		o2info_set_request_error(oir, req);
+
+	return status;
+}
+
+/*
+ * Validate and distinguish OCFS2_IOC_INFO requests.
+ *
+ * - validate the magic number.
+ * - distinguish different requests.
+ * - validate size of different requests.
+ */
+int ocfs2_info_handle_request(struct inode *inode,
+			      struct ocfs2_info_request __user *req)
+{
+	int status = -EFAULT;
+	struct ocfs2_info_request oir;
+
+	if (o2info_from_user(oir, req))
+		goto bail;
+
+	status = -EINVAL;
+	if (oir.ir_magic != OCFS2_INFO_MAGIC)
+		goto bail;
+
+	switch (oir.ir_code) {
+	case OCFS2_INFO_BLOCKSIZE:
+		if (oir.ir_size == sizeof(struct ocfs2_info_blocksize))
+			status = ocfs2_info_handle_blocksize(inode, req);
+		break;
+	case OCFS2_INFO_CLUSTERSIZE:
+		if (oir.ir_size == sizeof(struct ocfs2_info_clustersize))
+			status = ocfs2_info_handle_clustersize(inode, req);
+		break;
+	case OCFS2_INFO_MAXSLOTS:
+		if (oir.ir_size == sizeof(struct ocfs2_info_maxslots))
+			status = ocfs2_info_handle_maxslots(inode, req);
+		break;
+	case OCFS2_INFO_LABEL:
+		if (oir.ir_size == sizeof(struct ocfs2_info_label))
+			status = ocfs2_info_handle_label(inode, req);
+		break;
+	case OCFS2_INFO_UUID:
+		if (oir.ir_size == sizeof(struct ocfs2_info_uuid))
+			status = ocfs2_info_handle_uuid(inode, req);
+		break;
+	case OCFS2_INFO_FS_FEATURES:
+		if (oir.ir_size == sizeof(struct ocfs2_info_fs_features))
+			status = ocfs2_info_handle_fs_features(inode, req);
+		break;
+	case OCFS2_INFO_JOURNAL_SIZE:
+		if (oir.ir_size == sizeof(struct ocfs2_info_journal_size))
+			status = ocfs2_info_handle_journal_size(inode, req);
+		break;
+	default:
+		status = ocfs2_info_handle_unknown(inode, req);
+		break;
+	}
+
+bail:
+	return status;
+}
+
+int ocfs2_get_request_ptr(struct ocfs2_info *info, int idx,
+			  u64 *req_addr, int compat_flag)
+{
+	int status = -EFAULT;
+	u64 __user *bp = NULL;
+
+	if (compat_flag) {
+#ifdef CONFIG_COMPAT
+		/*
+		 * pointer bp stores the base address of a pointers array,
+		 * which collects all addresses of separate request.
+		 */
+		bp = (u64 __user *)(unsigned long)compat_ptr(info->oi_requests);
+#else
+		BUG();
+#endif
+	} else
+		bp = (u64 __user *)(unsigned long)(info->oi_requests);
+
+	if (o2info_from_user(*req_addr, bp + idx))
+		goto bail;
+
+	status = 0;
+bail:
+	return status;
+}
+
+/*
+ * OCFS2_IOC_INFO handles an array of requests passed from userspace.
+ *
+ * ocfs2_info_handle() recevies a large info aggregation, grab and
+ * validate the request count from header, then break it into small
+ * pieces, later specific handlers can handle them one by one.
+ *
+ * Idea here is to make each separate request small enough to ensure
+ * a better backward&forward compatibility, since a small piece of
+ * request will be less likely to be broken if disk layout get changed.
+ */
+int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info,
+		      int compat_flag)
+{
+	int i, status = 0;
+	u64 req_addr;
+	struct ocfs2_info_request __user *reqp;
+
+	if ((info->oi_count > OCFS2_INFO_MAX_REQUEST) ||
+	    (!info->oi_requests)) {
+		status = -EINVAL;
+		goto bail;
+	}
+
+	for (i = 0; i < info->oi_count; i++) {
+
+		status = ocfs2_get_request_ptr(info, i, &req_addr, compat_flag);
+		if (status)
+			break;
+
+		reqp = (struct ocfs2_info_request *)(unsigned long)req_addr;
+		if (!reqp) {
+			status = -EINVAL;
+			goto bail;
+		}
+
+		status = ocfs2_info_handle_request(inode, reqp);
+		if (status)
+			break;
+	}
+
+bail:
+	return status;
+}
+
 long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = filp->f_path.dentry->d_inode;
@@ -120,6 +462,7 @@
 	struct reflink_arguments args;
 	const char *old_path, *new_path;
 	bool preserve;
+	struct ocfs2_info info;
 
 	switch (cmd) {
 	case OCFS2_IOC_GETFLAGS:
@@ -174,6 +517,12 @@
 		preserve = (args.preserve != 0);
 
 		return ocfs2_reflink_ioctl(inode, old_path, new_path, preserve);
+	case OCFS2_IOC_INFO:
+		if (copy_from_user(&info, (struct ocfs2_info __user *)arg,
+				   sizeof(struct ocfs2_info)))
+			return -EFAULT;
+
+		return ocfs2_info_handle(inode, &info, 0);
 	default:
 		return -ENOTTY;
 	}
@@ -185,6 +534,7 @@
 	bool preserve;
 	struct reflink_arguments args;
 	struct inode *inode = file->f_path.dentry->d_inode;
+	struct ocfs2_info info;
 
 	switch (cmd) {
 	case OCFS2_IOC32_GETFLAGS:
@@ -209,6 +559,12 @@
 
 		return ocfs2_reflink_ioctl(inode, compat_ptr(args.old_path),
 					   compat_ptr(args.new_path), preserve);
+	case OCFS2_IOC_INFO:
+		if (copy_from_user(&info, (struct ocfs2_info __user *)arg,
+				   sizeof(struct ocfs2_info)))
+			return -EFAULT;
+
+		return ocfs2_info_handle(inode, &info, 1);
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 9b57c03..faa2303 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -301,7 +301,6 @@
 {
 	int status = 0;
 	unsigned int flushed;
-	unsigned long old_id;
 	struct ocfs2_journal *journal = NULL;
 
 	mlog_entry_void();
@@ -326,7 +325,7 @@
 		goto finally;
 	}
 
-	old_id = ocfs2_inc_trans_id(journal);
+	ocfs2_inc_trans_id(journal);
 
 	flushed = atomic_read(&journal->j_num_trans);
 	atomic_set(&journal->j_num_trans, 0);
@@ -342,9 +341,6 @@
 	return status;
 }
 
-/* pass it NULL and it will allocate a new handle object for you.  If
- * you pass it a handle however, it may still return error, in which
- * case it has free'd the passed handle for you. */
 handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
 {
 	journal_t *journal = osb->journal->j_journal;
@@ -1888,6 +1884,8 @@
 
 	os = &osb->osb_orphan_scan;
 
+	mlog(0, "Begin orphan scan\n");
+
 	if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE)
 		goto out;
 
@@ -1920,6 +1918,7 @@
 unlock:
 	ocfs2_orphan_scan_unlock(osb, seqno);
 out:
+	mlog(0, "Orphan scan completed\n");
 	return;
 }
 
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index b5baaa8..43e56b9 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -67,11 +67,12 @@
 	struct buffer_head        *j_bh;      /* Journal disk inode block */
 	atomic_t                  j_num_trans; /* Number of transactions
 					        * currently in the system. */
+	spinlock_t                j_lock;
 	unsigned long             j_trans_id;
 	struct rw_semaphore       j_trans_barrier;
 	wait_queue_head_t         j_checkpointed;
 
-	spinlock_t                j_lock;
+	/* both fields protected by j_lock*/
 	struct list_head          j_la_cleanups;
 	struct work_struct        j_recovery_work;
 };
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 4c18f4a..7e32db9 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -59,10 +59,11 @@
 	return ret;
 }
 
-static int __ocfs2_page_mkwrite(struct inode *inode, struct buffer_head *di_bh,
+static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
 				struct page *page)
 {
 	int ret;
+	struct inode *inode = file->f_path.dentry->d_inode;
 	struct address_space *mapping = inode->i_mapping;
 	loff_t pos = page_offset(page);
 	unsigned int len = PAGE_CACHE_SIZE;
@@ -111,7 +112,7 @@
 	if (page->index == last_index)
 		len = ((size - 1) & ~PAGE_CACHE_MASK) + 1;
 
-	ret = ocfs2_write_begin_nolock(mapping, pos, len, 0, &locked_page,
+	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, 0, &locked_page,
 				       &fsdata, di_bh, page);
 	if (ret) {
 		if (ret != -ENOSPC)
@@ -159,7 +160,7 @@
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = __ocfs2_page_mkwrite(inode, di_bh, page);
+	ret = __ocfs2_page_mkwrite(vma->vm_file, di_bh, page);
 
 	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index a00dda2..e7bde21 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -171,7 +171,8 @@
 			ret = ERR_PTR(status);
 			goto bail_unlock;
 		}
-	}
+	} else
+		ocfs2_dentry_attach_gen(dentry);
 
 bail_unlock:
 	/* Don't drop the cluster lock until *after* the d_add --
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index c67003b..d840821 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -150,26 +150,33 @@
 struct ocfs2_lock_res {
 	void                    *l_priv;
 	struct ocfs2_lock_res_ops *l_ops;
-	spinlock_t               l_lock;
+
 
 	struct list_head         l_blocked_list;
 	struct list_head         l_mask_waiters;
 
-	enum ocfs2_lock_type     l_type;
 	unsigned long		 l_flags;
 	char                     l_name[OCFS2_LOCK_ID_MAX_LEN];
-	int                      l_level;
 	unsigned int             l_ro_holders;
 	unsigned int             l_ex_holders;
-	struct ocfs2_dlm_lksb    l_lksb;
+	unsigned char            l_level;
+
+	/* Data packed - type enum ocfs2_lock_type */
+	unsigned char            l_type;
 
 	/* used from AST/BAST funcs. */
-	enum ocfs2_ast_action    l_action;
-	enum ocfs2_unlock_action l_unlock_action;
-	int                      l_requested;
-	int                      l_blocking;
+	/* Data packed - enum type ocfs2_ast_action */
+	unsigned char            l_action;
+	/* Data packed - enum type ocfs2_unlock_action */
+	unsigned char            l_unlock_action;
+	unsigned char            l_requested;
+	unsigned char            l_blocking;
 	unsigned int             l_pending_gen;
 
+	spinlock_t               l_lock;
+
+	struct ocfs2_dlm_lksb    l_lksb;
+
 	wait_queue_head_t        l_event;
 
 	struct list_head         l_debug_list;
@@ -243,7 +250,7 @@
 
 enum ocfs2_mount_options
 {
-	OCFS2_MOUNT_HB_LOCAL   = 1 << 0, /* Heartbeat started in local mode */
+	OCFS2_MOUNT_HB_LOCAL = 1 << 0, /* Local heartbeat */
 	OCFS2_MOUNT_BARRIER = 1 << 1,	/* Use block barriers */
 	OCFS2_MOUNT_NOINTR  = 1 << 2,   /* Don't catch signals */
 	OCFS2_MOUNT_ERRORS_PANIC = 1 << 3, /* Panic on errors */
@@ -256,6 +263,10 @@
 						   control lists */
 	OCFS2_MOUNT_USRQUOTA = 1 << 10, /* We support user quotas */
 	OCFS2_MOUNT_GRPQUOTA = 1 << 11, /* We support group quotas */
+	OCFS2_MOUNT_COHERENCY_BUFFERED = 1 << 12, /* Allow concurrent O_DIRECT
+						     writes */
+	OCFS2_MOUNT_HB_NONE = 1 << 13, /* No heartbeat */
+	OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */
 };
 
 #define OCFS2_OSB_SOFT_RO			0x0001
@@ -277,7 +288,8 @@
 	struct super_block *sb;
 	struct inode *root_inode;
 	struct inode *sys_root_inode;
-	struct inode *system_inodes[NUM_SYSTEM_INODES];
+	struct inode *global_system_inodes[NUM_GLOBAL_SYSTEM_INODES];
+	struct inode **local_system_inodes;
 
 	struct ocfs2_slot_info *slot_info;
 
@@ -368,6 +380,8 @@
 	struct ocfs2_alloc_stats alloc_stats;
 	char dev_str[20];		/* "major,minor" of the device */
 
+	u8 osb_stackflags;
+
 	char osb_cluster_stack[OCFS2_STACK_LABEL_LEN + 1];
 	struct ocfs2_cluster_connection *cconn;
 	struct ocfs2_lock_res osb_super_lockres;
@@ -601,10 +615,35 @@
 	return ret;
 }
 
-static inline int ocfs2_userspace_stack(struct ocfs2_super *osb)
+static inline int ocfs2_clusterinfo_valid(struct ocfs2_super *osb)
 {
 	return (osb->s_feature_incompat &
-		OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK);
+		(OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK |
+		 OCFS2_FEATURE_INCOMPAT_CLUSTERINFO));
+}
+
+static inline int ocfs2_userspace_stack(struct ocfs2_super *osb)
+{
+	if (ocfs2_clusterinfo_valid(osb) &&
+	    memcmp(osb->osb_cluster_stack, OCFS2_CLASSIC_CLUSTER_STACK,
+		   OCFS2_STACK_LABEL_LEN))
+		return 1;
+	return 0;
+}
+
+static inline int ocfs2_o2cb_stack(struct ocfs2_super *osb)
+{
+	if (ocfs2_clusterinfo_valid(osb) &&
+	    !memcmp(osb->osb_cluster_stack, OCFS2_CLASSIC_CLUSTER_STACK,
+		   OCFS2_STACK_LABEL_LEN))
+		return 1;
+	return 0;
+}
+
+static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb)
+{
+	return ocfs2_o2cb_stack(osb) &&
+		(osb->osb_stackflags & OCFS2_CLUSTER_O2CB_GLOBAL_HEARTBEAT);
 }
 
 static inline int ocfs2_mount_local(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index fa31d05..c2e4f82 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -101,7 +101,8 @@
 					 | OCFS2_FEATURE_INCOMPAT_META_ECC \
 					 | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS \
 					 | OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE \
-					 | OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG)
+					 | OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG	\
+					 | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP	(OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \
 					 | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \
 					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
@@ -170,6 +171,13 @@
 #define OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG	0x2000
 
 /*
+ * Incompat bit to indicate useable clusterinfo with stackflags for all
+ * cluster stacks (userspace adnd o2cb). If this bit is set,
+ * INCOMPAT_USERSPACE_STACK becomes superfluous and thus should not be set.
+ */
+#define OCFS2_FEATURE_INCOMPAT_CLUSTERINFO	0x4000
+
+/*
  * backup superblock flag is used to indicate that this volume
  * has backup superblocks.
  */
@@ -292,10 +300,13 @@
 #define OCFS2_VOL_UUID_LEN		16
 #define OCFS2_MAX_VOL_LABEL_LEN		64
 
-/* The alternate, userspace stack fields */
+/* The cluster stack fields */
 #define OCFS2_STACK_LABEL_LEN		4
 #define OCFS2_CLUSTER_NAME_LEN		16
 
+/* Classic (historically speaking) cluster stack */
+#define OCFS2_CLASSIC_CLUSTER_STACK	"o2cb"
+
 /* Journal limits (in bytes) */
 #define OCFS2_MIN_JOURNAL_SIZE		(4 * 1024 * 1024)
 
@@ -305,6 +316,11 @@
  */
 #define OCFS2_MIN_XATTR_INLINE_SIZE     256
 
+/*
+ * Cluster info flags (ocfs2_cluster_info.ci_stackflags)
+ */
+#define OCFS2_CLUSTER_O2CB_GLOBAL_HEARTBEAT	(0x01)
+
 struct ocfs2_system_inode_info {
 	char	*si_name;
 	int	si_iflags;
@@ -322,6 +338,7 @@
 	USER_QUOTA_SYSTEM_INODE,
 	GROUP_QUOTA_SYSTEM_INODE,
 #define OCFS2_LAST_GLOBAL_SYSTEM_INODE GROUP_QUOTA_SYSTEM_INODE
+#define OCFS2_FIRST_LOCAL_SYSTEM_INODE ORPHAN_DIR_SYSTEM_INODE
 	ORPHAN_DIR_SYSTEM_INODE,
 	EXTENT_ALLOC_SYSTEM_INODE,
 	INODE_ALLOC_SYSTEM_INODE,
@@ -330,8 +347,12 @@
 	TRUNCATE_LOG_SYSTEM_INODE,
 	LOCAL_USER_QUOTA_SYSTEM_INODE,
 	LOCAL_GROUP_QUOTA_SYSTEM_INODE,
+#define OCFS2_LAST_LOCAL_SYSTEM_INODE LOCAL_GROUP_QUOTA_SYSTEM_INODE
 	NUM_SYSTEM_INODES
 };
+#define NUM_GLOBAL_SYSTEM_INODES OCFS2_LAST_GLOBAL_SYSTEM_INODE
+#define NUM_LOCAL_SYSTEM_INODES	\
+		(NUM_SYSTEM_INODES - OCFS2_FIRST_LOCAL_SYSTEM_INODE)
 
 static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = {
 	/* Global system inodes (single copy) */
@@ -360,6 +381,7 @@
 /* Parameter passed from mount.ocfs2 to module */
 #define OCFS2_HB_NONE			"heartbeat=none"
 #define OCFS2_HB_LOCAL			"heartbeat=local"
+#define OCFS2_HB_GLOBAL			"heartbeat=global"
 
 /*
  * OCFS2 directory file types.  Only the low 3 bits are used.  The
@@ -566,9 +588,21 @@
  */
 };
 
+/*
+ * ci_stackflags is only valid if the incompat bit
+ * OCFS2_FEATURE_INCOMPAT_CLUSTERINFO is set.
+ */
 struct ocfs2_cluster_info {
 /*00*/	__u8   ci_stack[OCFS2_STACK_LABEL_LEN];
-	__le32 ci_reserved;
+	union {
+		__le32 ci_reserved;
+		struct {
+			__u8 ci_stackflags;
+			__u8 ci_reserved1;
+			__u8 ci_reserved2;
+			__u8 ci_reserved3;
+		};
+	};
 /*08*/	__u8   ci_cluster[OCFS2_CLUSTER_NAME_LEN];
 /*18*/
 };
@@ -605,9 +639,9 @@
 					 * group header */
 /*50*/	__u8  s_label[OCFS2_MAX_VOL_LABEL_LEN];	/* Label for mounting, etc. */
 /*90*/	__u8  s_uuid[OCFS2_VOL_UUID_LEN];	/* 128-bit uuid */
-/*A0*/  struct ocfs2_cluster_info s_cluster_info; /* Selected userspace
-						     stack.  Only valid
-						     with INCOMPAT flag. */
+/*A0*/  struct ocfs2_cluster_info s_cluster_info; /* Only valid if either
+						     userspace or clusterinfo
+						     INCOMPAT flag set. */
 /*B8*/	__le16 s_xattr_inline_size;	/* extended attribute inline size
 					   for this fs*/
 	__le16 s_reserved0;
diff --git a/fs/ocfs2/ocfs2_ioctl.h b/fs/ocfs2/ocfs2_ioctl.h
index 5d24150..b46f39b 100644
--- a/fs/ocfs2/ocfs2_ioctl.h
+++ b/fs/ocfs2/ocfs2_ioctl.h
@@ -76,4 +76,99 @@
 };
 #define OCFS2_IOC_REFLINK	_IOW('o', 4, struct reflink_arguments)
 
+/* Following definitions dedicated for ocfs2_info_request ioctls. */
+#define OCFS2_INFO_MAX_REQUEST		(50)
+#define OCFS2_TEXT_UUID_LEN		(OCFS2_VOL_UUID_LEN * 2)
+
+/* Magic number of all requests */
+#define OCFS2_INFO_MAGIC		(0x4F32494E)
+
+/*
+ * Always try to separate info request into small pieces to
+ * guarantee the backward&forward compatibility.
+ */
+struct ocfs2_info {
+	__u64 oi_requests;	/* Array of __u64 pointers to requests */
+	__u32 oi_count;		/* Number of requests in info_requests */
+	__u32 oi_pad;
+};
+
+struct ocfs2_info_request {
+/*00*/	__u32 ir_magic;	/* Magic number */
+	__u32 ir_code;	/* Info request code */
+	__u32 ir_size;	/* Size of request */
+	__u32 ir_flags;	/* Request flags */
+/*10*/			/* Request specific fields */
+};
+
+struct ocfs2_info_clustersize {
+	struct ocfs2_info_request ic_req;
+	__u32 ic_clustersize;
+	__u32 ic_pad;
+};
+
+struct ocfs2_info_blocksize {
+	struct ocfs2_info_request ib_req;
+	__u32 ib_blocksize;
+	__u32 ib_pad;
+};
+
+struct ocfs2_info_maxslots {
+	struct ocfs2_info_request im_req;
+	__u32 im_max_slots;
+	__u32 im_pad;
+};
+
+struct ocfs2_info_label {
+	struct ocfs2_info_request il_req;
+	__u8	il_label[OCFS2_MAX_VOL_LABEL_LEN];
+} __attribute__ ((packed));
+
+struct ocfs2_info_uuid {
+	struct ocfs2_info_request iu_req;
+	__u8	iu_uuid_str[OCFS2_TEXT_UUID_LEN + 1];
+} __attribute__ ((packed));
+
+struct ocfs2_info_fs_features {
+	struct ocfs2_info_request if_req;
+	__u32 if_compat_features;
+	__u32 if_incompat_features;
+	__u32 if_ro_compat_features;
+	__u32 if_pad;
+};
+
+struct ocfs2_info_journal_size {
+	struct ocfs2_info_request ij_req;
+	__u64 ij_journal_size;
+};
+
+/* Codes for ocfs2_info_request */
+enum ocfs2_info_type {
+	OCFS2_INFO_CLUSTERSIZE = 1,
+	OCFS2_INFO_BLOCKSIZE,
+	OCFS2_INFO_MAXSLOTS,
+	OCFS2_INFO_LABEL,
+	OCFS2_INFO_UUID,
+	OCFS2_INFO_FS_FEATURES,
+	OCFS2_INFO_JOURNAL_SIZE,
+	OCFS2_INFO_NUM_TYPES
+};
+
+/* Flags for struct ocfs2_info_request */
+/* Filled by the caller */
+#define OCFS2_INFO_FL_NON_COHERENT	(0x00000001)	/* Cluster coherency not
+							   required. This is a hint.
+							   It is up to ocfs2 whether
+							   the request can be fulfilled
+							   without locking. */
+/* Filled by ocfs2 */
+#define OCFS2_INFO_FL_FILLED		(0x40000000)	/* Filesystem understood
+							   this request and
+							   filled in the answer */
+
+#define OCFS2_INFO_FL_ERROR		(0x80000000)	/* Error happened during
+							   request handling. */
+
+#define OCFS2_IOC_INFO		_IOR('o', 5, struct ocfs2_info)
+
 #endif /* OCFS2_IOCTL_H */
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index efdd756..b5f9160 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -49,6 +49,7 @@
 
 struct ocfs2_cow_context {
 	struct inode *inode;
+	struct file *file;
 	u32 cow_start;
 	u32 cow_len;
 	struct ocfs2_extent_tree data_et;
@@ -2932,13 +2933,16 @@
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
 	struct page *page;
 	pgoff_t page_index;
-	unsigned int from, to;
+	unsigned int from, to, readahead_pages;
 	loff_t offset, end, map_end;
 	struct address_space *mapping = context->inode->i_mapping;
 
 	mlog(0, "old_cluster %u, new %u, len %u at offset %u\n", old_cluster,
 	     new_cluster, new_len, cpos);
 
+	readahead_pages =
+		(ocfs2_cow_contig_clusters(sb) <<
+		 OCFS2_SB(sb)->s_clustersize_bits) >> PAGE_CACHE_SHIFT;
 	offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits;
 	end = offset + (new_len << OCFS2_SB(sb)->s_clustersize_bits);
 	/*
@@ -2969,6 +2973,14 @@
 		if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
 			BUG_ON(PageDirty(page));
 
+		if (PageReadahead(page) && context->file) {
+			page_cache_async_readahead(mapping,
+						   &context->file->f_ra,
+						   context->file,
+						   page, page_index,
+						   readahead_pages);
+		}
+
 		if (!PageUptodate(page)) {
 			ret = block_read_full_page(page, ocfs2_get_block);
 			if (ret) {
@@ -3409,12 +3421,35 @@
 	return ret;
 }
 
+static void ocfs2_readahead_for_cow(struct inode *inode,
+				    struct file *file,
+				    u32 start, u32 len)
+{
+	struct address_space *mapping;
+	pgoff_t index;
+	unsigned long num_pages;
+	int cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+
+	if (!file)
+		return;
+
+	mapping = file->f_mapping;
+	num_pages = (len << cs_bits) >> PAGE_CACHE_SHIFT;
+	if (!num_pages)
+		num_pages = 1;
+
+	index = ((loff_t)start << cs_bits) >> PAGE_CACHE_SHIFT;
+	page_cache_sync_readahead(mapping, &file->f_ra, file,
+				  index, num_pages);
+}
+
 /*
  * Starting at cpos, try to CoW write_len clusters.  Don't CoW
  * past max_cpos.  This will stop when it runs into a hole or an
  * unrefcounted extent.
  */
 static int ocfs2_refcount_cow_hunk(struct inode *inode,
+				   struct file *file,
 				   struct buffer_head *di_bh,
 				   u32 cpos, u32 write_len, u32 max_cpos)
 {
@@ -3443,6 +3478,8 @@
 
 	BUG_ON(cow_len == 0);
 
+	ocfs2_readahead_for_cow(inode, file, cow_start, cow_len);
+
 	context = kzalloc(sizeof(struct ocfs2_cow_context), GFP_NOFS);
 	if (!context) {
 		ret = -ENOMEM;
@@ -3464,6 +3501,7 @@
 	context->ref_root_bh = ref_root_bh;
 	context->cow_duplicate_clusters = ocfs2_duplicate_clusters_by_page;
 	context->get_clusters = ocfs2_di_get_clusters;
+	context->file = file;
 
 	ocfs2_init_dinode_extent_tree(&context->data_et,
 				      INODE_CACHE(inode), di_bh);
@@ -3492,6 +3530,7 @@
  * clusters between cpos and cpos+write_len are safe to modify.
  */
 int ocfs2_refcount_cow(struct inode *inode,
+		       struct file *file,
 		       struct buffer_head *di_bh,
 		       u32 cpos, u32 write_len, u32 max_cpos)
 {
@@ -3511,7 +3550,7 @@
 			num_clusters = write_len;
 
 		if (ext_flags & OCFS2_EXT_REFCOUNTED) {
-			ret = ocfs2_refcount_cow_hunk(inode, di_bh, cpos,
+			ret = ocfs2_refcount_cow_hunk(inode, file, di_bh, cpos,
 						      num_clusters, max_cpos);
 			if (ret) {
 				mlog_errno(ret);
diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h
index 9983ba1..c8ce46f7 100644
--- a/fs/ocfs2/refcounttree.h
+++ b/fs/ocfs2/refcounttree.h
@@ -21,14 +21,14 @@
 	struct rb_node rf_node;
 	u64 rf_blkno;
 	u32 rf_generation;
+	struct kref rf_getcnt;
 	struct rw_semaphore rf_sem;
 	struct ocfs2_lock_res rf_lockres;
-	struct kref rf_getcnt;
 	int rf_removed;
 
 	/* the following 4 fields are used by caching_info. */
-	struct ocfs2_caching_info rf_ci;
 	spinlock_t rf_lock;
+	struct ocfs2_caching_info rf_ci;
 	struct mutex rf_io_mutex;
 	struct super_block *rf_sb;
 };
@@ -52,7 +52,8 @@
 					  u32 clusters,
 					  int *credits,
 					  int *ref_blocks);
-int ocfs2_refcount_cow(struct inode *inode, struct buffer_head *di_bh,
+int ocfs2_refcount_cow(struct inode *inode,
+		       struct file *filep, struct buffer_head *di_bh,
 		       u32 cpos, u32 write_len, u32 max_cpos);
 
 typedef int (ocfs2_post_refcount_func)(struct inode *inode,
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index bfbd7e9..ab4e017 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -357,7 +357,7 @@
 {
 	int status = 0;
 	u64 blkno;
-	unsigned long long blocks, bytes;
+	unsigned long long blocks, bytes = 0;
 	unsigned int i;
 	struct buffer_head *bh;
 
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index 0d3049f..19965b0 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -283,6 +283,8 @@
 	/* for now we only have one cluster/node, make sure we see it
 	 * in the heartbeat universe */
 	if (!o2hb_check_local_node_heartbeating()) {
+		if (o2hb_global_heartbeat_active())
+			mlog(ML_ERROR, "Global heartbeat not started\n");
 		rc = -EINVAL;
 		goto out;
 	}
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 2dc57bc..252e7c8 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -22,7 +22,6 @@
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/reboot.h>
 #include <asm/uaccess.h>
 
@@ -612,12 +611,10 @@
 		return -ENOMEM;
 	p->op_this_node = -1;
 
-	lock_kernel();
 	mutex_lock(&ocfs2_control_lock);
 	file->private_data = p;
 	list_add(&p->op_list, &ocfs2_control_private_list);
 	mutex_unlock(&ocfs2_control_lock);
-	unlock_kernel();
 
 	return 0;
 }
@@ -628,6 +625,7 @@
 	.read    = ocfs2_control_read,
 	.write   = ocfs2_control_write,
 	.owner   = THIS_MODULE,
+	.llseek  = default_llseek,
 };
 
 static struct miscdevice ocfs2_control_device = {
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 849c2f0..5fed60d 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1380,6 +1380,14 @@
 	}
 
 	le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
+	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
+		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
+			    " count %u but claims %u are freed. num_bits %d",
+			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
+			    le16_to_cpu(bg->bg_bits),
+			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
+		return -EROFS;
+	}
 	while(num_bits--)
 		ocfs2_set_bit(bit_off++, bitmap);
 
@@ -2419,6 +2427,14 @@
 				(unsigned long *) undo_bg->bg_bitmap);
 	}
 	le16_add_cpu(&bg->bg_free_bits_count, num_bits);
+	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
+		ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
+			    " count %u but claims %u are freed. num_bits %d",
+			    (unsigned long long)le64_to_cpu(bg->bg_blkno),
+			    le16_to_cpu(bg->bg_bits),
+			    le16_to_cpu(bg->bg_free_bits_count), num_bits);
+		return -EROFS;
+	}
 
 	if (undo_fn)
 		jbd_unlock_bh_state(group_bh);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index fa1be1b..56f0cb3 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -162,6 +162,7 @@
 	Opt_nointr,
 	Opt_hb_none,
 	Opt_hb_local,
+	Opt_hb_global,
 	Opt_data_ordered,
 	Opt_data_writeback,
 	Opt_atime_quantum,
@@ -177,6 +178,8 @@
 	Opt_noacl,
 	Opt_usrquota,
 	Opt_grpquota,
+	Opt_coherency_buffered,
+	Opt_coherency_full,
 	Opt_resv_level,
 	Opt_dir_resv_level,
 	Opt_err,
@@ -190,6 +193,7 @@
 	{Opt_nointr, "nointr"},
 	{Opt_hb_none, OCFS2_HB_NONE},
 	{Opt_hb_local, OCFS2_HB_LOCAL},
+	{Opt_hb_global, OCFS2_HB_GLOBAL},
 	{Opt_data_ordered, "data=ordered"},
 	{Opt_data_writeback, "data=writeback"},
 	{Opt_atime_quantum, "atime_quantum=%u"},
@@ -205,6 +209,8 @@
 	{Opt_noacl, "noacl"},
 	{Opt_usrquota, "usrquota"},
 	{Opt_grpquota, "grpquota"},
+	{Opt_coherency_buffered, "coherency=buffered"},
+	{Opt_coherency_full, "coherency=full"},
 	{Opt_resv_level, "resv_level=%u"},
 	{Opt_dir_resv_level, "dir_resv_level=%u"},
 	{Opt_err, NULL}
@@ -514,11 +520,11 @@
 
 	mlog_entry_void();
 
-	for (i = 0; i < NUM_SYSTEM_INODES; i++) {
-		inode = osb->system_inodes[i];
+	for (i = 0; i < NUM_GLOBAL_SYSTEM_INODES; i++) {
+		inode = osb->global_system_inodes[i];
 		if (inode) {
 			iput(inode);
-			osb->system_inodes[i] = NULL;
+			osb->global_system_inodes[i] = NULL;
 		}
 	}
 
@@ -534,6 +540,20 @@
 		osb->root_inode = NULL;
 	}
 
+	if (!osb->local_system_inodes)
+		goto out;
+
+	for (i = 0; i < NUM_LOCAL_SYSTEM_INODES * osb->max_slots; i++) {
+		if (osb->local_system_inodes[i]) {
+			iput(osb->local_system_inodes[i]);
+			osb->local_system_inodes[i] = NULL;
+		}
+	}
+
+	kfree(osb->local_system_inodes);
+	osb->local_system_inodes = NULL;
+
+out:
 	mlog_exit(0);
 }
 
@@ -608,8 +628,7 @@
 	int ret = 0;
 	struct mount_options parsed_options;
 	struct ocfs2_super *osb = OCFS2_SB(sb);
-
-	lock_kernel();
+	u32 tmp;
 
 	if (!ocfs2_parse_options(sb, data, &parsed_options, 1) ||
 	    !ocfs2_check_set_options(sb, &parsed_options)) {
@@ -617,8 +636,9 @@
 		goto out;
 	}
 
-	if ((osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) !=
-	    (parsed_options.mount_opt & OCFS2_MOUNT_HB_LOCAL)) {
+	tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
+		OCFS2_MOUNT_HB_NONE;
+	if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
 		ret = -EINVAL;
 		mlog(ML_ERROR, "Cannot change heartbeat mode on remount\n");
 		goto out;
@@ -717,7 +737,6 @@
 							MS_POSIXACL : 0);
 	}
 out:
-	unlock_kernel();
 	return ret;
 }
 
@@ -809,23 +828,29 @@
 
 static int ocfs2_verify_heartbeat(struct ocfs2_super *osb)
 {
-	if (ocfs2_mount_local(osb)) {
-		if (osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) {
+	u32 hb_enabled = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL;
+
+	if (osb->s_mount_opt & hb_enabled) {
+		if (ocfs2_mount_local(osb)) {
 			mlog(ML_ERROR, "Cannot heartbeat on a locally "
 			     "mounted device.\n");
 			return -EINVAL;
 		}
-	}
-
-	if (ocfs2_userspace_stack(osb)) {
-		if (osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) {
+		if (ocfs2_userspace_stack(osb)) {
 			mlog(ML_ERROR, "Userspace stack expected, but "
 			     "o2cb heartbeat arguments passed to mount\n");
 			return -EINVAL;
 		}
+		if (((osb->s_mount_opt & OCFS2_MOUNT_HB_GLOBAL) &&
+		     !ocfs2_cluster_o2cb_global_heartbeat(osb)) ||
+		    ((osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) &&
+		     ocfs2_cluster_o2cb_global_heartbeat(osb))) {
+			mlog(ML_ERROR, "Mismatching o2cb heartbeat modes\n");
+			return -EINVAL;
+		}
 	}
 
-	if (!(osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL)) {
+	if (!(osb->s_mount_opt & hb_enabled)) {
 		if (!ocfs2_mount_local(osb) && !ocfs2_is_hard_readonly(osb) &&
 		    !ocfs2_userspace_stack(osb)) {
 			mlog(ML_ERROR, "Heartbeat has to be started to mount "
@@ -1291,6 +1316,7 @@
 {
 	int status;
 	char *p;
+	u32 tmp;
 
 	mlog_entry("remount: %d, options: \"%s\"\n", is_remount,
 		   options ? options : "(none)");
@@ -1322,7 +1348,10 @@
 			mopt->mount_opt |= OCFS2_MOUNT_HB_LOCAL;
 			break;
 		case Opt_hb_none:
-			mopt->mount_opt &= ~OCFS2_MOUNT_HB_LOCAL;
+			mopt->mount_opt |= OCFS2_MOUNT_HB_NONE;
+			break;
+		case Opt_hb_global:
+			mopt->mount_opt |= OCFS2_MOUNT_HB_GLOBAL;
 			break;
 		case Opt_barrier:
 			if (match_int(&args[0], &option)) {
@@ -1438,6 +1467,12 @@
 		case Opt_grpquota:
 			mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA;
 			break;
+		case Opt_coherency_buffered:
+			mopt->mount_opt |= OCFS2_MOUNT_COHERENCY_BUFFERED;
+			break;
+		case Opt_coherency_full:
+			mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED;
+			break;
 		case Opt_acl:
 			mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL;
 			mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL;
@@ -1477,6 +1512,15 @@
 		}
 	}
 
+	/* Ensure only one heartbeat mode */
+	tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
+				 OCFS2_MOUNT_HB_NONE);
+	if (hweight32(tmp) != 1) {
+		mlog(ML_ERROR, "Invalid heartbeat mount options\n");
+		status = 0;
+		goto bail;
+	}
+
 	status = 1;
 
 bail:
@@ -1490,10 +1534,14 @@
 	unsigned long opts = osb->s_mount_opt;
 	unsigned int local_alloc_megs;
 
-	if (opts & OCFS2_MOUNT_HB_LOCAL)
-		seq_printf(s, ",_netdev,heartbeat=local");
-	else
-		seq_printf(s, ",heartbeat=none");
+	if (opts & (OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL)) {
+		seq_printf(s, ",_netdev");
+		if (opts & OCFS2_MOUNT_HB_LOCAL)
+			seq_printf(s, ",%s", OCFS2_HB_LOCAL);
+		else
+			seq_printf(s, ",%s", OCFS2_HB_GLOBAL);
+	} else
+		seq_printf(s, ",%s", OCFS2_HB_NONE);
 
 	if (opts & OCFS2_MOUNT_NOINTR)
 		seq_printf(s, ",nointr");
@@ -1536,6 +1584,11 @@
 	if (opts & OCFS2_MOUNT_GRPQUOTA)
 		seq_printf(s, ",grpquota");
 
+	if (opts & OCFS2_MOUNT_COHERENCY_BUFFERED)
+		seq_printf(s, ",coherency=buffered");
+	else
+		seq_printf(s, ",coherency=full");
+
 	if (opts & OCFS2_MOUNT_NOUSERXATTR)
 		seq_printf(s, ",nouser_xattr");
 	else
@@ -1640,13 +1693,9 @@
 {
 	mlog_entry("(0x%p)\n", sb);
 
-	lock_kernel();
-
 	ocfs2_sync_blockdev(sb);
 	ocfs2_dismount_volume(sb, 0);
 
-	unlock_kernel();
-
 	mlog_exit_void();
 }
 
@@ -1990,6 +2039,36 @@
 	return 0;
 }
 
+/* Make sure entire volume is addressable by our journal.  Requires
+   osb_clusters_at_boot to be valid and for the journal to have been
+   initialized by ocfs2_journal_init(). */
+static int ocfs2_journal_addressable(struct ocfs2_super *osb)
+{
+	int status = 0;
+	u64 max_block =
+		ocfs2_clusters_to_blocks(osb->sb,
+					 osb->osb_clusters_at_boot) - 1;
+
+	/* 32-bit block number is always OK. */
+	if (max_block <= (u32)~0ULL)
+		goto out;
+
+	/* Volume is "huge", so see if our journal is new enough to
+	   support it. */
+	if (!(OCFS2_HAS_COMPAT_FEATURE(osb->sb,
+				       OCFS2_FEATURE_COMPAT_JBD2_SB) &&
+	      jbd2_journal_check_used_features(osb->journal->j_journal, 0, 0,
+					       JBD2_FEATURE_INCOMPAT_64BIT))) {
+		mlog(ML_ERROR, "The journal cannot address the entire volume. "
+		     "Enable the 'block64' journal option with tunefs.ocfs2");
+		status = -EFBIG;
+		goto out;
+	}
+
+ out:
+	return status;
+}
+
 static int ocfs2_initialize_super(struct super_block *sb,
 				  struct buffer_head *bh,
 				  int sector_size,
@@ -2002,6 +2081,7 @@
 	struct ocfs2_journal *journal;
 	__le32 uuid_net_key;
 	struct ocfs2_super *osb;
+	u64 total_blocks;
 
 	mlog_entry_void();
 
@@ -2060,6 +2140,15 @@
 	snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u",
 		 MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
 
+	osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots);
+	if (osb->max_slots > OCFS2_MAX_SLOTS || osb->max_slots == 0) {
+		mlog(ML_ERROR, "Invalid number of node slots (%u)\n",
+		     osb->max_slots);
+		status = -EINVAL;
+		goto bail;
+	}
+	mlog(0, "max_slots for this device: %u\n", osb->max_slots);
+
 	ocfs2_orphan_scan_init(osb);
 
 	status = ocfs2_recovery_init(osb);
@@ -2098,15 +2187,6 @@
 		goto bail;
 	}
 
-	osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots);
-	if (osb->max_slots > OCFS2_MAX_SLOTS || osb->max_slots == 0) {
-		mlog(ML_ERROR, "Invalid number of node slots (%u)\n",
-		     osb->max_slots);
-		status = -EINVAL;
-		goto bail;
-	}
-	mlog(0, "max_slots for this device: %u\n", osb->max_slots);
-
 	osb->slot_recovery_generations =
 		kcalloc(osb->max_slots, sizeof(*osb->slot_recovery_generations),
 			GFP_KERNEL);
@@ -2149,7 +2229,9 @@
 		goto bail;
 	}
 
-	if (ocfs2_userspace_stack(osb)) {
+	if (ocfs2_clusterinfo_valid(osb)) {
+		osb->osb_stackflags =
+			OCFS2_RAW_SB(di)->s_cluster_info.ci_stackflags;
 		memcpy(osb->osb_cluster_stack,
 		       OCFS2_RAW_SB(di)->s_cluster_info.ci_stack,
 		       OCFS2_STACK_LABEL_LEN);
@@ -2214,11 +2296,15 @@
 		goto bail;
 	}
 
-	if (ocfs2_clusters_to_blocks(osb->sb, le32_to_cpu(di->i_clusters) - 1)
-	    > (u32)~0UL) {
-		mlog(ML_ERROR, "Volume might try to write to blocks beyond "
-		     "what jbd can address in 32 bits.\n");
-		status = -EINVAL;
+	total_blocks = ocfs2_clusters_to_blocks(osb->sb,
+						le32_to_cpu(di->i_clusters));
+
+	status = generic_check_addressable(osb->sb->s_blocksize_bits,
+					   total_blocks);
+	if (status) {
+		mlog(ML_ERROR, "Volume too large "
+		     "to mount safely on this system");
+		status = -EFBIG;
 		goto bail;
 	}
 
@@ -2380,6 +2466,12 @@
 		goto finally;
 	}
 
+	/* Now that journal has been initialized, check to make sure
+	   entire volume is addressable. */
+	status = ocfs2_journal_addressable(osb);
+	if (status)
+		goto finally;
+
 	/* If the journal was unmounted cleanly then we don't want to
 	 * recover anything. Otherwise, journal_load will do that
 	 * dirty work for us :) */
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index bfe7190..902efb2 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -44,11 +44,6 @@
 						   int type,
 						   u32 slot);
 
-static inline int is_global_system_inode(int type);
-static inline int is_in_system_inode_array(struct ocfs2_super *osb,
-					   int type,
-					   u32 slot);
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key ocfs2_sysfile_cluster_lock_key[NUM_SYSTEM_INODES];
 #endif
@@ -59,11 +54,52 @@
 		type <= OCFS2_LAST_GLOBAL_SYSTEM_INODE;
 }
 
-static inline int is_in_system_inode_array(struct ocfs2_super *osb,
-					   int type,
-					   u32 slot)
+static struct inode **get_local_system_inode(struct ocfs2_super *osb,
+					     int type,
+					     u32 slot)
 {
-	return slot == osb->slot_num || is_global_system_inode(type);
+	int index;
+	struct inode **local_system_inodes, **free = NULL;
+
+	BUG_ON(slot == OCFS2_INVALID_SLOT);
+	BUG_ON(type < OCFS2_FIRST_LOCAL_SYSTEM_INODE ||
+	       type > OCFS2_LAST_LOCAL_SYSTEM_INODE);
+
+	spin_lock(&osb->osb_lock);
+	local_system_inodes = osb->local_system_inodes;
+	spin_unlock(&osb->osb_lock);
+
+	if (unlikely(!local_system_inodes)) {
+		local_system_inodes = kzalloc(sizeof(struct inode *) *
+					      NUM_LOCAL_SYSTEM_INODES *
+					      osb->max_slots,
+					      GFP_NOFS);
+		if (!local_system_inodes) {
+			mlog_errno(-ENOMEM);
+			/*
+			 * return NULL here so that ocfs2_get_sytem_file_inodes
+			 * will try to create an inode and use it. We will try
+			 * to initialize local_system_inodes next time.
+			 */
+			return NULL;
+		}
+
+		spin_lock(&osb->osb_lock);
+		if (osb->local_system_inodes) {
+			/* Someone has initialized it for us. */
+			free = local_system_inodes;
+			local_system_inodes = osb->local_system_inodes;
+		} else
+			osb->local_system_inodes = local_system_inodes;
+		spin_unlock(&osb->osb_lock);
+		if (unlikely(free))
+			kfree(free);
+	}
+
+	index = (slot * NUM_LOCAL_SYSTEM_INODES) +
+		(type - OCFS2_FIRST_LOCAL_SYSTEM_INODE);
+
+	return &local_system_inodes[index];
 }
 
 struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
@@ -74,8 +110,10 @@
 	struct inode **arr = NULL;
 
 	/* avoid the lookup if cached in local system file array */
-	if (is_in_system_inode_array(osb, type, slot))
-		arr = &(osb->system_inodes[type]);
+	if (is_global_system_inode(type)) {
+		arr = &(osb->global_system_inodes[type]);
+	} else
+		arr = get_local_system_inode(osb, type, slot);
 
 	if (arr && ((inode = *arr) != NULL)) {
 		/* get a ref in addition to the array ref */
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 06fa5e7..67cd439 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -7081,7 +7081,7 @@
 		goto out;
 	}
 
-	if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED))
+	if (!indexed)
 		ret = ocfs2_reflink_xattr_block(args, blk_bh, new_blk_bh);
 	else
 		ret = ocfs2_reflink_xattr_tree(args, blk_bh, new_blk_bh);
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 79fbf3f..30f46c2 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -352,6 +352,7 @@
 {
 	struct hd_struct *p = dev_to_part(dev);
 	free_part_stats(p);
+	free_part_info(p);
 	kfree(p);
 }
 
@@ -364,17 +365,25 @@
 static void delete_partition_rcu_cb(struct rcu_head *head)
 {
 	struct hd_struct *part = container_of(head, struct hd_struct, rcu_head);
+	struct gendisk *disk = part_to_disk(part);
+	struct request_queue *q = disk->queue;
+	unsigned long flags;
 
 	part->start_sect = 0;
 	part->nr_sects = 0;
 	part_stat_set_all(part, 0);
 	put_device(part_to_dev(part));
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	elv_quiesce_end(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
 void delete_partition(struct gendisk *disk, int partno)
 {
 	struct disk_part_tbl *ptbl = disk->part_tbl;
 	struct hd_struct *part;
+	struct request_queue *q = disk->queue;
 
 	if (partno >= ptbl->len)
 		return;
@@ -389,6 +398,10 @@
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
 
+	spin_lock_irq(q->queue_lock);
+	elv_quiesce_start(q);
+	spin_unlock_irq(q->queue_lock);
+
 	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
 }
 
@@ -401,7 +414,8 @@
 		   whole_disk_show, NULL);
 
 struct hd_struct *add_partition(struct gendisk *disk, int partno,
-				sector_t start, sector_t len, int flags)
+				sector_t start, sector_t len, int flags,
+				struct partition_meta_info *info)
 {
 	struct hd_struct *p;
 	dev_t devt = MKDEV(0, 0);
@@ -438,6 +452,14 @@
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
 
+	if (info) {
+		struct partition_meta_info *pinfo = alloc_part_info(disk);
+		if (!pinfo)
+			goto out_free_stats;
+		memcpy(pinfo, info, sizeof(*info));
+		p->info = pinfo;
+	}
+
 	dname = dev_name(ddev);
 	if (isdigit(dname[strlen(dname) - 1]))
 		dev_set_name(pdev, "%sp%d", dname, partno);
@@ -451,7 +473,7 @@
 
 	err = blk_alloc_devt(p, &devt);
 	if (err)
-		goto out_free_stats;
+		goto out_free_info;
 	pdev->devt = devt;
 
 	/* delay uevent until 'holders' subdir is created */
@@ -481,6 +503,8 @@
 
 	return p;
 
+out_free_info:
+	free_part_info(p);
 out_free_stats:
 	free_part_stats(p);
 out_free:
@@ -642,6 +666,7 @@
 	/* add partitions */
 	for (p = 1; p < state->limit; p++) {
 		sector_t size, from;
+		struct partition_meta_info *info = NULL;
 
 		size = state->parts[p].size;
 		if (!size)
@@ -675,8 +700,12 @@
 				size = get_capacity(disk) - from;
 			}
 		}
+
+		if (state->parts[p].has_info)
+			info = &state->parts[p].info;
 		part = add_partition(disk, p, from, size,
-				     state->parts[p].flags);
+				     state->parts[p].flags,
+				     &state->parts[p].info);
 		if (IS_ERR(part)) {
 			printk(KERN_ERR " %s: p%d could not be added: %ld\n",
 			       disk->disk_name, p, -PTR_ERR(part));
diff --git a/fs/partitions/check.h b/fs/partitions/check.h
index 8e4e103..d68bf4d 100644
--- a/fs/partitions/check.h
+++ b/fs/partitions/check.h
@@ -1,5 +1,6 @@
 #include <linux/pagemap.h>
 #include <linux/blkdev.h>
+#include <linux/genhd.h>
 
 /*
  * add_gd_partition adds a partitions details to the devices partition
@@ -12,6 +13,8 @@
 		sector_t from;
 		sector_t size;
 		int flags;
+		bool has_info;
+		struct partition_meta_info info;
 	} parts[DISK_MAX_PARTS];
 	int next;
 	int limit;
diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c
index dbb44d4..ac0ccb5 100644
--- a/fs/partitions/efi.c
+++ b/fs/partitions/efi.c
@@ -94,6 +94,7 @@
  *
  ************************************************************/
 #include <linux/crc32.h>
+#include <linux/ctype.h>
 #include <linux/math64.h>
 #include <linux/slab.h>
 #include "check.h"
@@ -604,6 +605,7 @@
 	gpt_entry *ptes = NULL;
 	u32 i;
 	unsigned ssz = bdev_logical_block_size(state->bdev) / 512;
+	u8 unparsed_guid[37];
 
 	if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) {
 		kfree(gpt);
@@ -614,6 +616,9 @@
 	pr_debug("GUID Partition Table is valid!  Yea!\n");
 
 	for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
+		struct partition_meta_info *info;
+		unsigned label_count = 0;
+		unsigned label_max;
 		u64 start = le64_to_cpu(ptes[i].starting_lba);
 		u64 size = le64_to_cpu(ptes[i].ending_lba) -
 			   le64_to_cpu(ptes[i].starting_lba) + 1ULL;
@@ -627,6 +632,26 @@
 		if (!efi_guidcmp(ptes[i].partition_type_guid,
 				 PARTITION_LINUX_RAID_GUID))
 			state->parts[i + 1].flags = ADDPART_FLAG_RAID;
+
+		info = &state->parts[i + 1].info;
+		/* Instead of doing a manual swap to big endian, reuse the
+		 * common ASCII hex format as the interim.
+		 */
+		efi_guid_unparse(&ptes[i].unique_partition_guid, unparsed_guid);
+		part_pack_uuid(unparsed_guid, info->uuid);
+
+		/* Naively convert UTF16-LE to 7 bits. */
+		label_max = min(sizeof(info->volname) - 1,
+				sizeof(ptes[i].partition_name));
+		info->volname[label_max] = 0;
+		while (label_count < label_max) {
+			u8 c = ptes[i].partition_name[label_count] & 0xff;
+			if (c && !isprint(c))
+				c = '!';
+			info->volname[label_count] = c;
+			label_count++;
+		}
+		state->parts[i + 1].has_info = true;
 	}
 	kfree(ptes);
 	kfree(gpt);
diff --git a/fs/pipe.c b/fs/pipe.c
index 279eef9..37eb1eb 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -382,7 +382,7 @@
 			error = ops->confirm(pipe, buf);
 			if (error) {
 				if (!ret)
-					error = ret;
+					ret = error;
 				break;
 			}
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8e4adda..dc5d5f5 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1151,6 +1151,7 @@
 static const struct file_operations proc_oom_score_adj_operations = {
 	.read		= oom_score_adj_read,
 	.write		= oom_score_adj_write,
+	.llseek		= default_llseek,
 };
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -2039,11 +2040,13 @@
 static const struct file_operations proc_fdinfo_file_operations = {
 	.open           = nonseekable_open,
 	.read		= proc_fdinfo_read,
+	.llseek		= no_llseek,
 };
 
 static const struct file_operations proc_fd_operations = {
 	.read		= generic_read_dir,
 	.readdir	= proc_readfd,
+	.llseek		= default_llseek,
 };
 
 /*
@@ -2112,6 +2115,7 @@
 static const struct file_operations proc_fdinfo_operations = {
 	.read		= generic_read_dir,
 	.readdir	= proc_readfdinfo,
+	.llseek		= default_llseek,
 };
 
 /*
@@ -2343,6 +2347,7 @@
 static const struct file_operations proc_attr_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= proc_attr_dir_readdir,
+	.llseek		= default_llseek,
 };
 
 static struct dentry *proc_attr_dir_lookup(struct inode *dir,
@@ -2751,6 +2756,7 @@
 static const struct file_operations proc_tgid_base_operations = {
 	.read		= generic_read_dir,
 	.readdir	= proc_tgid_base_readdir,
+	.llseek		= default_llseek,
 };
 
 static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
@@ -3088,6 +3094,7 @@
 static const struct file_operations proc_tid_base_operations = {
 	.read		= generic_read_dir,
 	.readdir	= proc_tid_base_readdir,
+	.llseek		= default_llseek,
 };
 
 static const struct inode_operations proc_tid_base_inode_operations = {
@@ -3324,4 +3331,5 @@
 static const struct file_operations proc_task_operations = {
 	.read		= generic_read_dir,
 	.readdir	= proc_task_readdir,
+	.llseek		= default_llseek,
 };
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5be436e..2fc5255 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -364,6 +364,7 @@
 static const struct file_operations proc_sys_file_operations = {
 	.read		= proc_sys_read,
 	.write		= proc_sys_write,
+	.llseek		= default_llseek,
 };
 
 static const struct file_operations proc_sys_dir_file_operations = {
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 4258384..93d99b3 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -179,6 +179,7 @@
 static const struct file_operations proc_root_operations = {
 	.read		 = generic_read_dir,
 	.readdir	 = proc_root_readdir,
+	.llseek		= default_llseek,
 };
 
 /*
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 1dbca4e8..871e25e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -539,6 +539,7 @@
 
 const struct file_operations proc_clear_refs_operations = {
 	.write		= clear_refs_write,
+	.llseek		= noop_llseek,
 };
 
 struct pagemapread {
diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c
index 6e8fc62..7b03294 100644
--- a/fs/qnx4/dir.c
+++ b/fs/qnx4/dir.c
@@ -11,7 +11,6 @@
  * 20-06-1998 by Frank Denis : Linux 2.1.99+ & dcache support.
  */
 
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include "qnx4.h"
 
@@ -29,8 +28,6 @@
 	QNX4DEBUG((KERN_INFO "qnx4_readdir:i_size = %ld\n", (long) inode->i_size));
 	QNX4DEBUG((KERN_INFO "filp->f_pos         = %ld\n", (long) filp->f_pos));
 
-	lock_kernel();
-
 	while (filp->f_pos < inode->i_size) {
 		blknum = qnx4_block_map( inode, filp->f_pos >> QNX4_BLOCK_SIZE_BITS );
 		bh = sb_bread(inode->i_sb, blknum);
@@ -71,7 +68,6 @@
 		brelse(bh);
 	}
 out:
-	unlock_kernel();
 	return 0;
 }
 
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 1682972..01bad30 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -16,7 +16,6 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/highuid.h>
-#include <linux/smp_lock.h>
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
@@ -157,8 +156,6 @@
 	struct super_block *sb = dentry->d_sb;
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
-	lock_kernel();
-
 	buf->f_type    = sb->s_magic;
 	buf->f_bsize   = sb->s_blocksize;
 	buf->f_blocks  = le32_to_cpu(qnx4_sb(sb)->BitMap->di_size) * 8;
@@ -168,8 +165,6 @@
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 
-	unlock_kernel();
-
 	return 0;
 }
 
@@ -283,7 +278,6 @@
  		goto outi;
 
 	brelse(bh);
-
 	return 0;
 
       outi:
diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c
index 58703eb..275327b 100644
--- a/fs/qnx4/namei.c
+++ b/fs/qnx4/namei.c
@@ -12,7 +12,6 @@
  * 04-07-1998 by Frank Denis : first step for rmdir/unlink.
  */
 
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include "qnx4.h"
 
@@ -109,7 +108,6 @@
 	int len = dentry->d_name.len;
 	struct inode *foundinode = NULL;
 
-	lock_kernel();
 	if (!(bh = qnx4_find_entry(len, dir, name, &de, &ino)))
 		goto out;
 	/* The entry is linked, let's get the real info */
@@ -123,13 +121,11 @@
 
 	foundinode = qnx4_iget(dir->i_sb, ino);
 	if (IS_ERR(foundinode)) {
-		unlock_kernel();
 		QNX4DEBUG((KERN_ERR "qnx4: lookup->iget -> error %ld\n",
 			   PTR_ERR(foundinode)));
 		return ERR_CAST(foundinode);
 	}
 out:
-	unlock_kernel();
 	d_add(dentry, foundinode);
 
 	return NULL;
diff --git a/fs/read_write.c b/fs/read_write.c
index 74e3658..e757ef2 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -124,7 +124,7 @@
 {
 	loff_t retval;
 
-	lock_kernel();
+	mutex_lock(&file->f_dentry->d_inode->i_mutex);
 	switch (origin) {
 		case SEEK_END:
 			offset += i_size_read(file->f_path.dentry->d_inode);
@@ -145,7 +145,7 @@
 		retval = offset;
 	}
 out:
-	unlock_kernel();
+	mutex_unlock(&file->f_dentry->d_inode->i_mutex);
 	return retval;
 }
 EXPORT_SYMBOL(default_llseek);
@@ -156,7 +156,6 @@
 
 	fn = no_llseek;
 	if (file->f_mode & FMODE_LSEEK) {
-		fn = default_llseek;
 		if (file->f_op && file->f_op->llseek)
 			fn = file->f_op->llseek;
 	}
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 6846371..91f080c 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -152,8 +152,7 @@
 	barrier_done = reiserfs_commit_for_inode(inode);
 	reiserfs_write_unlock(inode->i_sb);
 	if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb))
-		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, 
-			BLKDEV_IFL_WAIT);
+		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 	if (barrier_done < 0)
 		return barrier_done;
 	return (err < 0) ? -EIO : 0;
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 812e2c0..076c8b1 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -138,13 +138,6 @@
 	return 0;
 }
 
-static void disable_barrier(struct super_block *s)
-{
-	REISERFS_SB(s)->s_mount_opt &= ~(1 << REISERFS_BARRIER_FLUSH);
-	printk("reiserfs: disabling flush barriers on %s\n",
-	       reiserfs_bdevname(s));
-}
-
 static struct reiserfs_bitmap_node *allocate_bitmap_node(struct super_block
 							 *sb)
 {
@@ -677,30 +670,6 @@
 	submit_bh(WRITE, bh);
 }
 
-static int submit_barrier_buffer(struct buffer_head *bh)
-{
-	get_bh(bh);
-	bh->b_end_io = reiserfs_end_ordered_io;
-	clear_buffer_dirty(bh);
-	if (!buffer_uptodate(bh))
-		BUG();
-	return submit_bh(WRITE_BARRIER, bh);
-}
-
-static void check_barrier_completion(struct super_block *s,
-				     struct buffer_head *bh)
-{
-	if (buffer_eopnotsupp(bh)) {
-		clear_buffer_eopnotsupp(bh);
-		disable_barrier(s);
-		set_buffer_uptodate(bh);
-		set_buffer_dirty(bh);
-		reiserfs_write_unlock(s);
-		sync_dirty_buffer(bh);
-		reiserfs_write_lock(s);
-	}
-}
-
 #define CHUNK_SIZE 32
 struct buffer_chunk {
 	struct buffer_head *bh[CHUNK_SIZE];
@@ -1009,7 +978,6 @@
 	struct buffer_head *tbh = NULL;
 	unsigned int trans_id = jl->j_trans_id;
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
-	int barrier = 0;
 	int retval = 0;
 	int write_len;
 
@@ -1094,24 +1062,6 @@
 	}
 	atomic_dec(&journal->j_async_throttle);
 
-	/* We're skipping the commit if there's an error */
-	if (retval || reiserfs_is_journal_aborted(journal))
-		barrier = 0;
-
-	/* wait on everything written so far before writing the commit
-	 * if we are in barrier mode, send the commit down now
-	 */
-	barrier = reiserfs_barrier_flush(s);
-	if (barrier) {
-		int ret;
-		lock_buffer(jl->j_commit_bh);
-		ret = submit_barrier_buffer(jl->j_commit_bh);
-		if (ret == -EOPNOTSUPP) {
-			set_buffer_uptodate(jl->j_commit_bh);
-			disable_barrier(s);
-			barrier = 0;
-		}
-	}
 	for (i = 0; i < (jl->j_len + 1); i++) {
 		bn = SB_ONDISK_JOURNAL_1st_BLOCK(s) +
 		    (jl->j_start + i) % SB_ONDISK_JOURNAL_SIZE(s);
@@ -1143,27 +1093,22 @@
 
 	BUG_ON(atomic_read(&(jl->j_commit_left)) != 1);
 
-	if (!barrier) {
-		/* If there was a write error in the journal - we can't commit
-		 * this transaction - it will be invalid and, if successful,
-		 * will just end up propagating the write error out to
-		 * the file system. */
-		if (likely(!retval && !reiserfs_is_journal_aborted (journal))) {
-			if (buffer_dirty(jl->j_commit_bh))
-				BUG();
-			mark_buffer_dirty(jl->j_commit_bh) ;
-			reiserfs_write_unlock(s);
-			sync_dirty_buffer(jl->j_commit_bh) ;
-			reiserfs_write_lock(s);
-		}
-	} else {
+	/* If there was a write error in the journal - we can't commit
+	 * this transaction - it will be invalid and, if successful,
+	 * will just end up propagating the write error out to
+	 * the file system. */
+	if (likely(!retval && !reiserfs_is_journal_aborted (journal))) {
+		if (buffer_dirty(jl->j_commit_bh))
+			BUG();
+		mark_buffer_dirty(jl->j_commit_bh) ;
 		reiserfs_write_unlock(s);
-		wait_on_buffer(jl->j_commit_bh);
+		if (reiserfs_barrier_flush(s))
+			__sync_dirty_buffer(jl->j_commit_bh, WRITE_FLUSH_FUA);
+		else
+			sync_dirty_buffer(jl->j_commit_bh);
 		reiserfs_write_lock(s);
 	}
 
-	check_barrier_completion(s, jl->j_commit_bh);
-
 	/* If there was a write error in the journal - we can't commit this
 	 * transaction - it will be invalid and, if successful, will just end
 	 * up propagating the write error out to the filesystem. */
@@ -1319,26 +1264,15 @@
 		jh->j_first_unflushed_offset = cpu_to_le32(offset);
 		jh->j_mount_id = cpu_to_le32(journal->j_mount_id);
 
-		if (reiserfs_barrier_flush(sb)) {
-			int ret;
-			lock_buffer(journal->j_header_bh);
-			ret = submit_barrier_buffer(journal->j_header_bh);
-			if (ret == -EOPNOTSUPP) {
-				set_buffer_uptodate(journal->j_header_bh);
-				disable_barrier(sb);
-				goto sync;
-			}
-			reiserfs_write_unlock(sb);
-			wait_on_buffer(journal->j_header_bh);
-			reiserfs_write_lock(sb);
-			check_barrier_completion(sb, journal->j_header_bh);
-		} else {
-		      sync:
-			set_buffer_dirty(journal->j_header_bh);
-			reiserfs_write_unlock(sb);
+		set_buffer_dirty(journal->j_header_bh);
+		reiserfs_write_unlock(sb);
+
+		if (reiserfs_barrier_flush(sb))
+			__sync_dirty_buffer(journal->j_header_bh, WRITE_FLUSH_FUA);
+		else
 			sync_dirty_buffer(journal->j_header_bh);
-			reiserfs_write_lock(sb);
-		}
+
+		reiserfs_write_lock(sb);
 		if (!buffer_uptodate(journal->j_header_bh)) {
 			reiserfs_warning(sb, "journal-837",
 					 "IO error during journal replay");
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 42d2135..2685805 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -282,6 +282,7 @@
 static const struct file_operations romfs_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= romfs_readdir,
+	.llseek		= default_llseek,
 };
 
 static const struct inode_operations romfs_dir_inode_operations = {
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 1c5a6ad..7404730 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -206,6 +206,7 @@
 	.release	= signalfd_release,
 	.poll		= signalfd_poll,
 	.read		= signalfd_read,
+	.llseek		= noop_llseek,
 };
 
 SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask,
diff --git a/fs/smbfs/Kconfig b/fs/smbfs/Kconfig
index e668127..2bc24a8 100644
--- a/fs/smbfs/Kconfig
+++ b/fs/smbfs/Kconfig
@@ -1,5 +1,6 @@
 config SMB_FS
 	tristate "SMB file system support (OBSOLETE, please use CIFS)"
+	depends on BKL # probably unfixable
 	depends on INET
 	select NLS
 	help
diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c
index 450c919..8fc5e50 100644
--- a/fs/smbfs/inode.c
+++ b/fs/smbfs/inode.c
@@ -501,6 +501,8 @@
 	void *mem;
 	static int warn_count;
 
+	lock_kernel();
+
 	if (warn_count < 5) {
 		warn_count++;
 		printk(KERN_EMERG "smbfs is deprecated and will be removed"
@@ -621,6 +623,7 @@
 
 	smb_new_dentry(sb->s_root);
 
+	unlock_kernel();
 	return 0;
 
 out_no_root:
@@ -643,9 +646,11 @@
 out_no_data:
 	printk(KERN_ERR "smb_fill_super: missing data argument\n");
 out_fail:
+	unlock_kernel();
 	return -EINVAL;
 out_no_server:
 	printk(KERN_ERR "smb_fill_super: cannot allocate struct smb_sb_info\n");
+	unlock_kernel();
 	return -ENOMEM;
 }
 
diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c
index 12b933a..0dc340a 100644
--- a/fs/squashfs/dir.c
+++ b/fs/squashfs/dir.c
@@ -230,5 +230,6 @@
 
 const struct file_operations squashfs_dir_ops = {
 	.read = generic_read_dir,
-	.readdir = squashfs_readdir
+	.readdir = squashfs_readdir,
+	.llseek = default_llseek,
 };
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 88b4f86..07a4f11 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -30,7 +30,6 @@
 #include <linux/fs.h>
 #include <linux/vfs.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
@@ -354,8 +353,6 @@
 
 static void squashfs_put_super(struct super_block *sb)
 {
-	lock_kernel();
-
 	if (sb->s_fs_info) {
 		struct squashfs_sb_info *sbi = sb->s_fs_info;
 		squashfs_cache_delete(sbi->block_cache);
@@ -370,8 +367,6 @@
 		kfree(sb->s_fs_info);
 		sb->s_fs_info = NULL;
 	}
-
-	unlock_kernel();
 }
 
 
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 23c1e59..442f34f 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -148,6 +148,65 @@
 	sysfs_put(sd);
 }
 
+/**
+ * sysfs_merge_group - merge files into a pre-existing attribute group.
+ * @kobj:	The kobject containing the group.
+ * @grp:	The files to create and the attribute group they belong to.
+ *
+ * This function returns an error if the group doesn't exist or any of the
+ * files already exist in that group, in which case none of the new files
+ * are created.
+ */
+int sysfs_merge_group(struct kobject *kobj,
+		       const struct attribute_group *grp)
+{
+	struct sysfs_dirent *dir_sd;
+	int error = 0;
+	struct attribute *const *attr;
+	int i;
+
+	if (grp)
+		dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+	else
+		dir_sd = sysfs_get(kobj->sd);
+	if (!dir_sd)
+		return -ENOENT;
+
+	for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr))
+		error = sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR);
+	if (error) {
+		while (--i >= 0)
+			sysfs_hash_and_remove(dir_sd, NULL, (*--attr)->name);
+	}
+	sysfs_put(dir_sd);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(sysfs_merge_group);
+
+/**
+ * sysfs_unmerge_group - remove files from a pre-existing attribute group.
+ * @kobj:	The kobject containing the group.
+ * @grp:	The files to remove and the attribute group they belong to.
+ */
+void sysfs_unmerge_group(struct kobject *kobj,
+		       const struct attribute_group *grp)
+{
+	struct sysfs_dirent *dir_sd;
+	struct attribute *const *attr;
+
+	if (grp)
+		dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+	else
+		dir_sd = sysfs_get(kobj->sd);
+	if (dir_sd) {
+		for (attr = grp->attrs; *attr; ++attr)
+			sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name);
+		sysfs_put(dir_sd);
+	}
+}
+EXPORT_SYMBOL_GPL(sysfs_unmerge_group);
+
 
 EXPORT_SYMBOL_GPL(sysfs_create_group);
 EXPORT_SYMBOL_GPL(sysfs_update_group);
diff --git a/fs/timerfd.c b/fs/timerfd.c
index b86ab8e..8c4fc14 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -144,6 +144,7 @@
 	.release	= timerfd_release,
 	.poll		= timerfd_poll,
 	.read		= timerfd_read,
+	.llseek		= noop_llseek,
 };
 
 static struct file *timerfd_fget(int fd)
diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index 37fa7ed..02429d8 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -63,7 +63,9 @@
 	struct ubifs_lp_stats lst;
 
 	dbg_cmt("start");
-	if (c->ro_media) {
+	ubifs_assert(!c->ro_media && !c->ro_mount);
+
+	if (c->ro_error) {
 		err = -EROFS;
 		goto out_up;
 	}
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index c2a68ba..0bee4db 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -2239,6 +2239,162 @@
 	return err;
 }
 
+/**
+ * dbg_check_data_nodes_order - check that list of data nodes is sorted.
+ * @c: UBIFS file-system description object
+ * @head: the list of nodes ('struct ubifs_scan_node' objects)
+ *
+ * This function returns zero if the list of data nodes is sorted correctly,
+ * and %-EINVAL if not.
+ */
+int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head)
+{
+	struct list_head *cur;
+	struct ubifs_scan_node *sa, *sb;
+
+	if (!(ubifs_chk_flags & UBIFS_CHK_GEN))
+		return 0;
+
+	for (cur = head->next; cur->next != head; cur = cur->next) {
+		ino_t inuma, inumb;
+		uint32_t blka, blkb;
+
+		cond_resched();
+		sa = container_of(cur, struct ubifs_scan_node, list);
+		sb = container_of(cur->next, struct ubifs_scan_node, list);
+
+		if (sa->type != UBIFS_DATA_NODE) {
+			ubifs_err("bad node type %d", sa->type);
+			dbg_dump_node(c, sa->node);
+			return -EINVAL;
+		}
+		if (sb->type != UBIFS_DATA_NODE) {
+			ubifs_err("bad node type %d", sb->type);
+			dbg_dump_node(c, sb->node);
+			return -EINVAL;
+		}
+
+		inuma = key_inum(c, &sa->key);
+		inumb = key_inum(c, &sb->key);
+
+		if (inuma < inumb)
+			continue;
+		if (inuma > inumb) {
+			ubifs_err("larger inum %lu goes before inum %lu",
+				  (unsigned long)inuma, (unsigned long)inumb);
+			goto error_dump;
+		}
+
+		blka = key_block(c, &sa->key);
+		blkb = key_block(c, &sb->key);
+
+		if (blka > blkb) {
+			ubifs_err("larger block %u goes before %u", blka, blkb);
+			goto error_dump;
+		}
+		if (blka == blkb) {
+			ubifs_err("two data nodes for the same block");
+			goto error_dump;
+		}
+	}
+
+	return 0;
+
+error_dump:
+	dbg_dump_node(c, sa->node);
+	dbg_dump_node(c, sb->node);
+	return -EINVAL;
+}
+
+/**
+ * dbg_check_nondata_nodes_order - check that list of data nodes is sorted.
+ * @c: UBIFS file-system description object
+ * @head: the list of nodes ('struct ubifs_scan_node' objects)
+ *
+ * This function returns zero if the list of non-data nodes is sorted correctly,
+ * and %-EINVAL if not.
+ */
+int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head)
+{
+	struct list_head *cur;
+	struct ubifs_scan_node *sa, *sb;
+
+	if (!(ubifs_chk_flags & UBIFS_CHK_GEN))
+		return 0;
+
+	for (cur = head->next; cur->next != head; cur = cur->next) {
+		ino_t inuma, inumb;
+		uint32_t hasha, hashb;
+
+		cond_resched();
+		sa = container_of(cur, struct ubifs_scan_node, list);
+		sb = container_of(cur->next, struct ubifs_scan_node, list);
+
+		if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE &&
+		    sa->type != UBIFS_XENT_NODE) {
+			ubifs_err("bad node type %d", sa->type);
+			dbg_dump_node(c, sa->node);
+			return -EINVAL;
+		}
+		if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE &&
+		    sa->type != UBIFS_XENT_NODE) {
+			ubifs_err("bad node type %d", sb->type);
+			dbg_dump_node(c, sb->node);
+			return -EINVAL;
+		}
+
+		if (sa->type != UBIFS_INO_NODE && sb->type == UBIFS_INO_NODE) {
+			ubifs_err("non-inode node goes before inode node");
+			goto error_dump;
+		}
+
+		if (sa->type == UBIFS_INO_NODE && sb->type != UBIFS_INO_NODE)
+			continue;
+
+		if (sa->type == UBIFS_INO_NODE && sb->type == UBIFS_INO_NODE) {
+			/* Inode nodes are sorted in descending size order */
+			if (sa->len < sb->len) {
+				ubifs_err("smaller inode node goes first");
+				goto error_dump;
+			}
+			continue;
+		}
+
+		/*
+		 * This is either a dentry or xentry, which should be sorted in
+		 * ascending (parent ino, hash) order.
+		 */
+		inuma = key_inum(c, &sa->key);
+		inumb = key_inum(c, &sb->key);
+
+		if (inuma < inumb)
+			continue;
+		if (inuma > inumb) {
+			ubifs_err("larger inum %lu goes before inum %lu",
+				  (unsigned long)inuma, (unsigned long)inumb);
+			goto error_dump;
+		}
+
+		hasha = key_block(c, &sa->key);
+		hashb = key_block(c, &sb->key);
+
+		if (hasha > hashb) {
+			ubifs_err("larger hash %u goes before %u", hasha, hashb);
+			goto error_dump;
+		}
+	}
+
+	return 0;
+
+error_dump:
+	ubifs_msg("dumping first node");
+	dbg_dump_node(c, sa->node);
+	ubifs_msg("dumping second node");
+	dbg_dump_node(c, sb->node);
+	return -EINVAL;
+	return 0;
+}
+
 static int invocation_cnt;
 
 int dbg_force_in_the_gaps(void)
@@ -2625,6 +2781,7 @@
 	.open = open_debugfs_file,
 	.write = write_debugfs_file,
 	.owner = THIS_MODULE,
+	.llseek = default_llseek,
 };
 
 /**
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index 29d9601..69ebe47 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -324,6 +324,8 @@
 			int row, int col);
 int dbg_check_inode_size(struct ubifs_info *c, const struct inode *inode,
 			 loff_t size);
+int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head);
+int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head);
 
 /* Force the use of in-the-gaps method for testing */
 
@@ -465,6 +467,8 @@
 #define dbg_check_lprops(c)                        0
 #define dbg_check_lpt_nodes(c, cnode, row, col)    0
 #define dbg_check_inode_size(c, inode, size)       0
+#define dbg_check_data_nodes_order(c, head)        0
+#define dbg_check_nondata_nodes_order(c, head)     0
 #define dbg_force_in_the_gaps_enabled              0
 #define dbg_force_in_the_gaps()                    0
 #define dbg_failure_mode                           0
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 03ae894..d77db7e 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -433,8 +433,9 @@
 	struct page *page;
 
 	ubifs_assert(ubifs_inode(inode)->ui_size == inode->i_size);
+	ubifs_assert(!c->ro_media && !c->ro_mount);
 
-	if (unlikely(c->ro_media))
+	if (unlikely(c->ro_error))
 		return -EROFS;
 
 	/* Try out the fast-path part first */
@@ -1439,9 +1440,9 @@
 
 	dbg_gen("ino %lu, pg %lu, i_size %lld",	inode->i_ino, page->index,
 		i_size_read(inode));
-	ubifs_assert(!(inode->i_sb->s_flags & MS_RDONLY));
+	ubifs_assert(!c->ro_media && !c->ro_mount);
 
-	if (unlikely(c->ro_media))
+	if (unlikely(c->ro_error))
 		return VM_FAULT_SIGBUS; /* -EROFS */
 
 	/*
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index 918d158..151f108 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -125,10 +125,16 @@
 	struct ubifs_scan_node *sa, *sb;
 
 	cond_resched();
+	if (a == b)
+		return 0;
+
 	sa = list_entry(a, struct ubifs_scan_node, list);
 	sb = list_entry(b, struct ubifs_scan_node, list);
+
 	ubifs_assert(key_type(c, &sa->key) == UBIFS_DATA_KEY);
 	ubifs_assert(key_type(c, &sb->key) == UBIFS_DATA_KEY);
+	ubifs_assert(sa->type == UBIFS_DATA_NODE);
+	ubifs_assert(sb->type == UBIFS_DATA_NODE);
 
 	inuma = key_inum(c, &sa->key);
 	inumb = key_inum(c, &sb->key);
@@ -157,28 +163,40 @@
  */
 int nondata_nodes_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
-	int typea, typeb;
 	ino_t inuma, inumb;
 	struct ubifs_info *c = priv;
 	struct ubifs_scan_node *sa, *sb;
 
 	cond_resched();
+	if (a == b)
+		return 0;
+
 	sa = list_entry(a, struct ubifs_scan_node, list);
 	sb = list_entry(b, struct ubifs_scan_node, list);
-	typea = key_type(c, &sa->key);
-	typeb = key_type(c, &sb->key);
-	ubifs_assert(typea != UBIFS_DATA_KEY && typeb != UBIFS_DATA_KEY);
+
+	ubifs_assert(key_type(c, &sa->key) != UBIFS_DATA_KEY &&
+		     key_type(c, &sb->key) != UBIFS_DATA_KEY);
+	ubifs_assert(sa->type != UBIFS_DATA_NODE &&
+		     sb->type != UBIFS_DATA_NODE);
 
 	/* Inodes go before directory entries */
-	if (typea == UBIFS_INO_KEY) {
-		if (typeb == UBIFS_INO_KEY)
+	if (sa->type == UBIFS_INO_NODE) {
+		if (sb->type == UBIFS_INO_NODE)
 			return sb->len - sa->len;
 		return -1;
 	}
-	if (typeb == UBIFS_INO_KEY)
+	if (sb->type == UBIFS_INO_NODE)
 		return 1;
 
-	ubifs_assert(typea == UBIFS_DENT_KEY && typeb == UBIFS_DENT_KEY);
+	ubifs_assert(key_type(c, &sa->key) == UBIFS_DENT_KEY ||
+		     key_type(c, &sa->key) == UBIFS_XENT_KEY);
+	ubifs_assert(key_type(c, &sb->key) == UBIFS_DENT_KEY ||
+		     key_type(c, &sb->key) == UBIFS_XENT_KEY);
+	ubifs_assert(sa->type == UBIFS_DENT_NODE ||
+		     sa->type == UBIFS_XENT_NODE);
+	ubifs_assert(sb->type == UBIFS_DENT_NODE ||
+		     sb->type == UBIFS_XENT_NODE);
+
 	inuma = key_inum(c, &sa->key);
 	inumb = key_inum(c, &sb->key);
 
@@ -224,17 +242,33 @@
 static int sort_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 		      struct list_head *nondata, int *min)
 {
+	int err;
 	struct ubifs_scan_node *snod, *tmp;
 
 	*min = INT_MAX;
 
 	/* Separate data nodes and non-data nodes */
 	list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) {
-		int err;
+		ubifs_assert(snod->type == UBIFS_INO_NODE  ||
+			     snod->type == UBIFS_DATA_NODE ||
+			     snod->type == UBIFS_DENT_NODE ||
+			     snod->type == UBIFS_XENT_NODE ||
+			     snod->type == UBIFS_TRUN_NODE);
 
-		ubifs_assert(snod->type != UBIFS_IDX_NODE);
-		ubifs_assert(snod->type != UBIFS_REF_NODE);
-		ubifs_assert(snod->type != UBIFS_CS_NODE);
+		if (snod->type != UBIFS_INO_NODE  &&
+		    snod->type != UBIFS_DATA_NODE &&
+		    snod->type != UBIFS_DENT_NODE &&
+		    snod->type != UBIFS_XENT_NODE) {
+			/* Probably truncation node, zap it */
+			list_del(&snod->list);
+			kfree(snod);
+			continue;
+		}
+
+		ubifs_assert(key_type(c, &snod->key) == UBIFS_DATA_KEY ||
+			     key_type(c, &snod->key) == UBIFS_INO_KEY  ||
+			     key_type(c, &snod->key) == UBIFS_DENT_KEY ||
+			     key_type(c, &snod->key) == UBIFS_XENT_KEY);
 
 		err = ubifs_tnc_has_node(c, &snod->key, 0, sleb->lnum,
 					 snod->offs, 0);
@@ -258,6 +292,13 @@
 	/* Sort data and non-data nodes */
 	list_sort(c, &sleb->nodes, &data_nodes_cmp);
 	list_sort(c, nondata, &nondata_nodes_cmp);
+
+	err = dbg_check_data_nodes_order(c, &sleb->nodes);
+	if (err)
+		return err;
+	err = dbg_check_nondata_nodes_order(c, nondata);
+	if (err)
+		return err;
 	return 0;
 }
 
@@ -575,13 +616,14 @@
 	struct ubifs_wbuf *wbuf = &c->jheads[GCHD].wbuf;
 
 	ubifs_assert_cmt_locked(c);
+	ubifs_assert(!c->ro_media && !c->ro_mount);
 
 	if (ubifs_gc_should_commit(c))
 		return -EAGAIN;
 
 	mutex_lock_nested(&wbuf->io_mutex, wbuf->jhead);
 
-	if (c->ro_media) {
+	if (c->ro_error) {
 		ret = -EROFS;
 		goto out_unlock;
 	}
@@ -677,14 +719,12 @@
 
 		ret = ubifs_garbage_collect_leb(c, &lp);
 		if (ret < 0) {
-			if (ret == -EAGAIN || ret == -ENOSPC) {
+			if (ret == -EAGAIN) {
 				/*
-				 * These codes are not errors, so we have to
-				 * return the LEB to lprops. But if the
-				 * 'ubifs_return_leb()' function fails, its
-				 * failure code is propagated to the caller
-				 * instead of the original '-EAGAIN' or
-				 * '-ENOSPC'.
+				 * This is not error, so we have to return the
+				 * LEB to lprops. But if 'ubifs_return_leb()'
+				 * fails, its failure code is propagated to the
+				 * caller instead of the original '-EAGAIN'.
 				 */
 				err = ubifs_return_leb(c, lp.lnum);
 				if (err)
@@ -774,8 +814,8 @@
 out:
 	ubifs_assert(ret < 0);
 	ubifs_assert(ret != -ENOSPC && ret != -EAGAIN);
-	ubifs_ro_mode(c, ret);
 	ubifs_wbuf_sync_nolock(wbuf);
+	ubifs_ro_mode(c, ret);
 	mutex_unlock(&wbuf->io_mutex);
 	ubifs_return_leb(c, lp.lnum);
 	return ret;
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index bcf5a16..d821731 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -61,8 +61,8 @@
  */
 void ubifs_ro_mode(struct ubifs_info *c, int err)
 {
-	if (!c->ro_media) {
-		c->ro_media = 1;
+	if (!c->ro_error) {
+		c->ro_error = 1;
 		c->no_chk_data_crc = 0;
 		c->vfs_sb->s_flags |= MS_RDONLY;
 		ubifs_warn("switched to read-only mode, error %d", err);
@@ -356,11 +356,11 @@
 
 	dbg_io("LEB %d:%d, %d bytes, jhead %s",
 	       wbuf->lnum, wbuf->offs, wbuf->used, dbg_jhead(wbuf->jhead));
-	ubifs_assert(!(c->vfs_sb->s_flags & MS_RDONLY));
 	ubifs_assert(!(wbuf->avail & 7));
 	ubifs_assert(wbuf->offs + c->min_io_size <= c->leb_size);
+	ubifs_assert(!c->ro_media && !c->ro_mount);
 
-	if (c->ro_media)
+	if (c->ro_error)
 		return -EROFS;
 
 	ubifs_pad(c, wbuf->buf + wbuf->used, wbuf->avail);
@@ -440,11 +440,12 @@
 {
 	int err, i;
 
+	ubifs_assert(!c->ro_media && !c->ro_mount);
 	if (!c->need_wbuf_sync)
 		return 0;
 	c->need_wbuf_sync = 0;
 
-	if (c->ro_media) {
+	if (c->ro_error) {
 		err = -EROFS;
 		goto out_timers;
 	}
@@ -519,6 +520,7 @@
 	ubifs_assert(!(wbuf->offs & 7) && wbuf->offs <= c->leb_size);
 	ubifs_assert(wbuf->avail > 0 && wbuf->avail <= c->min_io_size);
 	ubifs_assert(mutex_is_locked(&wbuf->io_mutex));
+	ubifs_assert(!c->ro_media && !c->ro_mount);
 
 	if (c->leb_size - wbuf->offs - wbuf->used < aligned_len) {
 		err = -ENOSPC;
@@ -527,7 +529,7 @@
 
 	cancel_wbuf_timer_nolock(wbuf);
 
-	if (c->ro_media)
+	if (c->ro_error)
 		return -EROFS;
 
 	if (aligned_len <= wbuf->avail) {
@@ -663,8 +665,9 @@
 	       buf_len);
 	ubifs_assert(lnum >= 0 && lnum < c->leb_cnt && offs >= 0);
 	ubifs_assert(offs % c->min_io_size == 0 && offs < c->leb_size);
+	ubifs_assert(!c->ro_media && !c->ro_mount);
 
-	if (c->ro_media)
+	if (c->ro_error)
 		return -EROFS;
 
 	ubifs_prepare_node(c, buf, len, 1);
@@ -815,7 +818,8 @@
 	return 0;
 
 out:
-	ubifs_err("bad node at LEB %d:%d", lnum, offs);
+	ubifs_err("bad node at LEB %d:%d, LEB mapping status %d", lnum, offs,
+		  ubi_is_mapped(c->ubi, lnum));
 	dbg_dump_node(c, buf);
 	dbg_dump_stack();
 	return -EINVAL;
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index d321bae..914f1bd 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -122,11 +122,12 @@
 	 * better to try to allocate space at the ends of eraseblocks. This is
 	 * what the squeeze parameter does.
 	 */
+	ubifs_assert(!c->ro_media && !c->ro_mount);
 	squeeze = (jhead == BASEHD);
 again:
 	mutex_lock_nested(&wbuf->io_mutex, wbuf->jhead);
 
-	if (c->ro_media) {
+	if (c->ro_error) {
 		err = -EROFS;
 		goto out_unlock;
 	}
diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h
index 0f530c6..92a8491 100644
--- a/fs/ubifs/key.h
+++ b/fs/ubifs/key.h
@@ -306,6 +306,20 @@
 }
 
 /**
+ * invalid_key_init - initialize invalid node key.
+ * @c: UBIFS file-system description object
+ * @key: key to initialize
+ *
+ * This is a helper function which marks a @key object as invalid.
+ */
+static inline void invalid_key_init(const struct ubifs_info *c,
+				    union ubifs_key *key)
+{
+	key->u32[0] = 0xDEADBEAF;
+	key->u32[1] = UBIFS_INVALID_KEY;
+}
+
+/**
  * key_type - get key type.
  * @c: UBIFS file-system description object
  * @key: key to get type of
diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c
index c345e12..4d0cb12 100644
--- a/fs/ubifs/log.c
+++ b/fs/ubifs/log.c
@@ -159,7 +159,7 @@
 		jhead = &c->jheads[bud->jhead];
 		list_add_tail(&bud->list, &jhead->buds_list);
 	} else
-		ubifs_assert(c->replaying && (c->vfs_sb->s_flags & MS_RDONLY));
+		ubifs_assert(c->replaying && c->ro_mount);
 
 	/*
 	 * Note, although this is a new bud, we anyway account this space now,
@@ -223,8 +223,8 @@
 	}
 
 	mutex_lock(&c->log_mutex);
-
-	if (c->ro_media) {
+	ubifs_assert(!c->ro_media && !c->ro_mount);
+	if (c->ro_error) {
 		err = -EROFS;
 		goto out_unlock;
 	}
diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c
index 0084a33..72775d3 100644
--- a/fs/ubifs/lpt.c
+++ b/fs/ubifs/lpt.c
@@ -1363,6 +1363,7 @@
 		goto out;
 	for (i = 0; i < c->lsave_cnt; i++) {
 		int lnum = c->lsave[i];
+		struct ubifs_lprops *lprops;
 
 		/*
 		 * Due to automatic resizing, the values in the lsave table
@@ -1370,7 +1371,11 @@
 		 */
 		if (lnum >= c->leb_cnt)
 			continue;
-		ubifs_lpt_lookup(c, lnum);
+		lprops = ubifs_lpt_lookup(c, lnum);
+		if (IS_ERR(lprops)) {
+			err = PTR_ERR(lprops);
+			goto out;
+		}
 	}
 out:
 	vfree(buf);
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index d12535b..5c90dec 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -705,6 +705,9 @@
 	struct ubifs_pnode *pnode;
 
 	pnode = pnode_lookup(c, 0);
+	if (IS_ERR(pnode))
+		return PTR_ERR(pnode);
+
 	while (pnode) {
 		do_make_pnode_dirty(c, pnode);
 		pnode = next_pnode_to_dirty(c, pnode);
diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c
index 28beaee..21f47af 100644
--- a/fs/ubifs/master.c
+++ b/fs/ubifs/master.c
@@ -361,7 +361,8 @@
 {
 	int err, lnum, offs, len;
 
-	if (c->ro_media)
+	ubifs_assert(!c->ro_media && !c->ro_mount);
+	if (c->ro_error)
 		return -EROFS;
 
 	lnum = UBIFS_MST_LNUM;
diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h
index 4fa81d8..c3de04d 100644
--- a/fs/ubifs/misc.h
+++ b/fs/ubifs/misc.h
@@ -132,7 +132,8 @@
 {
 	int err;
 
-	if (c->ro_media)
+	ubifs_assert(!c->ro_media && !c->ro_mount);
+	if (c->ro_error)
 		return -EROFS;
 	err = ubi_leb_unmap(c->ubi, lnum);
 	if (err) {
@@ -159,7 +160,8 @@
 {
 	int err;
 
-	if (c->ro_media)
+	ubifs_assert(!c->ro_media && !c->ro_mount);
+	if (c->ro_error)
 		return -EROFS;
 	err = ubi_leb_write(c->ubi, lnum, buf, offs, len, dtype);
 	if (err) {
@@ -186,7 +188,8 @@
 {
 	int err;
 
-	if (c->ro_media)
+	ubifs_assert(!c->ro_media && !c->ro_mount);
+	if (c->ro_error)
 		return -EROFS;
 	err = ubi_leb_change(c->ubi, lnum, buf, len, dtype);
 	if (err) {
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index daae9e1..77e9b87 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -292,7 +292,7 @@
 
 	memcpy(c->mst_node, mst, UBIFS_MST_NODE_SZ);
 
-	if ((c->vfs_sb->s_flags & MS_RDONLY)) {
+	if (c->ro_mount) {
 		/* Read-only mode. Keep a copy for switching to rw mode */
 		c->rcvrd_mst_node = kmalloc(sz, GFP_KERNEL);
 		if (!c->rcvrd_mst_node) {
@@ -469,7 +469,7 @@
 		endpt = snod->offs + snod->len;
 	}
 
-	if ((c->vfs_sb->s_flags & MS_RDONLY) && !c->remounting_rw) {
+	if (c->ro_mount && !c->remounting_rw) {
 		/* Add to recovery list */
 		struct ubifs_unclean_leb *ucleb;
 
@@ -772,7 +772,8 @@
  * @sbuf: LEB-sized buffer to use
  *
  * This function does a scan of a LEB, but caters for errors that might have
- * been caused by the unclean unmount from which we are attempting to recover.
+ * been caused by unclean reboots from which we are attempting to recover
+ * (assume that only the last log LEB can be corrupted by an unclean reboot).
  *
  * This function returns %0 on success and a negative error code on failure.
  */
@@ -883,7 +884,7 @@
 {
 	int err;
 
-	ubifs_assert(!(c->vfs_sb->s_flags & MS_RDONLY) || c->remounting_rw);
+	ubifs_assert(!c->ro_mount || c->remounting_rw);
 
 	dbg_rcvry("checking index head at %d:%d", c->ihead_lnum, c->ihead_offs);
 	err = recover_head(c, c->ihead_lnum, c->ihead_offs, sbuf);
@@ -1461,7 +1462,7 @@
 			}
 		}
 		if (e->exists && e->i_size < e->d_size) {
-			if (!e->inode && (c->vfs_sb->s_flags & MS_RDONLY)) {
+			if (!e->inode && c->ro_mount) {
 				/* Fix the inode size and pin it in memory */
 				struct inode *inode;
 
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 5c2d6d7..eed0fcf 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -627,8 +627,7 @@
 	ubifs_assert(sleb->endpt - offs >= used);
 	ubifs_assert(sleb->endpt % c->min_io_size == 0);
 
-	if (sleb->endpt + c->min_io_size <= c->leb_size &&
-	    !(c->vfs_sb->s_flags & MS_RDONLY))
+	if (sleb->endpt + c->min_io_size <= c->leb_size && !c->ro_mount)
 		err = ubifs_wbuf_seek_nolock(&c->jheads[jhead].wbuf, lnum,
 					     sleb->endpt, UBI_SHORTTERM);
 
@@ -840,6 +839,11 @@
 	if (IS_ERR(sleb)) {
 		if (PTR_ERR(sleb) != -EUCLEAN || !c->need_recovery)
 			return PTR_ERR(sleb);
+		/*
+		 * Note, the below function will recover this log LEB only if
+		 * it is the last, because unclean reboots can possibly corrupt
+		 * only the tail of the log.
+		 */
 		sleb = ubifs_recover_log_leb(c, lnum, offs, sbuf);
 		if (IS_ERR(sleb))
 			return PTR_ERR(sleb);
@@ -851,7 +855,6 @@
 	}
 
 	node = sleb->buf;
-
 	snod = list_entry(sleb->nodes.next, struct ubifs_scan_node, list);
 	if (c->cs_sqnum == 0) {
 		/*
@@ -898,7 +901,6 @@
 	}
 
 	list_for_each_entry(snod, &sleb->nodes, list) {
-
 		cond_resched();
 
 		if (snod->sqnum >= SQNUM_WATERMARK) {
@@ -1011,7 +1013,6 @@
 int ubifs_replay_journal(struct ubifs_info *c)
 {
 	int err, i, lnum, offs, free;
-	void *sbuf = NULL;
 
 	BUILD_BUG_ON(UBIFS_TRUN_KEY > 5);
 
@@ -1026,14 +1027,8 @@
 		return -EINVAL;
 	}
 
-	sbuf = vmalloc(c->leb_size);
-	if (!sbuf)
-		return -ENOMEM;
-
 	dbg_mnt("start replaying the journal");
-
 	c->replaying = 1;
-
 	lnum = c->ltail_lnum = c->lhead_lnum;
 	offs = c->lhead_offs;
 
@@ -1046,7 +1041,7 @@
 			lnum = UBIFS_LOG_LNUM;
 			offs = 0;
 		}
-		err = replay_log_leb(c, lnum, offs, sbuf);
+		err = replay_log_leb(c, lnum, offs, c->sbuf);
 		if (err == 1)
 			/* We hit the end of the log */
 			break;
@@ -1079,7 +1074,6 @@
 out:
 	destroy_replay_tree(c);
 	destroy_bud_list(c);
-	vfree(sbuf);
 	c->replaying = 0;
 	return err;
 }
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index 96cb62c..bf31b47 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -542,11 +542,8 @@
 	 * due to the unavailability of time-travelling equipment.
 	 */
 	if (c->fmt_version > UBIFS_FORMAT_VERSION) {
-		struct super_block *sb = c->vfs_sb;
-		int mounting_ro = sb->s_flags & MS_RDONLY;
-
-		ubifs_assert(!c->ro_media || mounting_ro);
-		if (!mounting_ro ||
+		ubifs_assert(!c->ro_media || c->ro_mount);
+		if (!c->ro_mount ||
 		    c->ro_compat_version > UBIFS_RO_COMPAT_VERSION) {
 			ubifs_err("on-flash format version is w%d/r%d, but "
 				  "software only supports up to version "
@@ -624,7 +621,7 @@
 	c->old_leb_cnt = c->leb_cnt;
 	if (c->leb_cnt < c->vi.size && c->leb_cnt < c->max_leb_cnt) {
 		c->leb_cnt = min_t(int, c->max_leb_cnt, c->vi.size);
-		if (c->vfs_sb->s_flags & MS_RDONLY)
+		if (c->ro_mount)
 			dbg_mnt("Auto resizing (ro) from %d LEBs to %d LEBs",
 				c->old_leb_cnt,	c->leb_cnt);
 		else {
diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c
index 96c5253..3e1ee57 100644
--- a/fs/ubifs/scan.c
+++ b/fs/ubifs/scan.c
@@ -197,7 +197,7 @@
 	struct ubifs_ino_node *ino = buf;
 	struct ubifs_scan_node *snod;
 
-	snod = kzalloc(sizeof(struct ubifs_scan_node), GFP_NOFS);
+	snod = kmalloc(sizeof(struct ubifs_scan_node), GFP_NOFS);
 	if (!snod)
 		return -ENOMEM;
 
@@ -212,13 +212,15 @@
 	case UBIFS_DENT_NODE:
 	case UBIFS_XENT_NODE:
 	case UBIFS_DATA_NODE:
-	case UBIFS_TRUN_NODE:
 		/*
 		 * The key is in the same place in all keyed
 		 * nodes.
 		 */
 		key_read(c, &ino->key, &snod->key);
 		break;
+	default:
+		invalid_key_init(c, &snod->key);
+		break;
 	}
 	list_add_tail(&snod->list, &sleb->nodes);
 	sleb->nodes_cnt += 1;
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index 0b20111..46961c0 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -250,7 +250,7 @@
 			dirty_zn_cnt = atomic_long_read(&c->dirty_zn_cnt);
 
 			if (!dirty_zn_cnt || c->cmt_state == COMMIT_BROKEN ||
-			    c->ro_media) {
+			    c->ro_mount || c->ro_error) {
 				mutex_unlock(&c->umount_mutex);
 				continue;
 			}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index cd5900b..9a47c9f 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1137,11 +1137,11 @@
  */
 static int mount_ubifs(struct ubifs_info *c)
 {
-	struct super_block *sb = c->vfs_sb;
-	int err, mounted_read_only = (sb->s_flags & MS_RDONLY);
+	int err;
 	long long x;
 	size_t sz;
 
+	c->ro_mount = !!(c->vfs_sb->s_flags & MS_RDONLY);
 	err = init_constants_early(c);
 	if (err)
 		return err;
@@ -1154,7 +1154,7 @@
 	if (err)
 		goto out_free;
 
-	if (c->empty && (mounted_read_only || c->ro_media)) {
+	if (c->empty && (c->ro_mount || c->ro_media)) {
 		/*
 		 * This UBI volume is empty, and read-only, or the file system
 		 * is mounted read-only - we cannot format it.
@@ -1165,7 +1165,7 @@
 		goto out_free;
 	}
 
-	if (c->ro_media && !mounted_read_only) {
+	if (c->ro_media && !c->ro_mount) {
 		ubifs_err("cannot mount read-write - read-only media");
 		err = -EROFS;
 		goto out_free;
@@ -1185,7 +1185,7 @@
 	if (!c->sbuf)
 		goto out_free;
 
-	if (!mounted_read_only) {
+	if (!c->ro_mount) {
 		c->ileb_buf = vmalloc(c->leb_size);
 		if (!c->ileb_buf)
 			goto out_free;
@@ -1228,7 +1228,7 @@
 	}
 
 	sprintf(c->bgt_name, BGT_NAME_PATTERN, c->vi.ubi_num, c->vi.vol_id);
-	if (!mounted_read_only) {
+	if (!c->ro_mount) {
 		err = alloc_wbufs(c);
 		if (err)
 			goto out_cbuf;
@@ -1254,12 +1254,12 @@
 	if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) {
 		ubifs_msg("recovery needed");
 		c->need_recovery = 1;
-		if (!mounted_read_only) {
+		if (!c->ro_mount) {
 			err = ubifs_recover_inl_heads(c, c->sbuf);
 			if (err)
 				goto out_master;
 		}
-	} else if (!mounted_read_only) {
+	} else if (!c->ro_mount) {
 		/*
 		 * Set the "dirty" flag so that if we reboot uncleanly we
 		 * will notice this immediately on the next mount.
@@ -1270,7 +1270,7 @@
 			goto out_master;
 	}
 
-	err = ubifs_lpt_init(c, 1, !mounted_read_only);
+	err = ubifs_lpt_init(c, 1, !c->ro_mount);
 	if (err)
 		goto out_lpt;
 
@@ -1285,11 +1285,11 @@
 	/* Calculate 'min_idx_lebs' after journal replay */
 	c->min_idx_lebs = ubifs_calc_min_idx_lebs(c);
 
-	err = ubifs_mount_orphans(c, c->need_recovery, mounted_read_only);
+	err = ubifs_mount_orphans(c, c->need_recovery, c->ro_mount);
 	if (err)
 		goto out_orphans;
 
-	if (!mounted_read_only) {
+	if (!c->ro_mount) {
 		int lnum;
 
 		err = check_free_space(c);
@@ -1351,7 +1351,7 @@
 	spin_unlock(&ubifs_infos_lock);
 
 	if (c->need_recovery) {
-		if (mounted_read_only)
+		if (c->ro_mount)
 			ubifs_msg("recovery deferred");
 		else {
 			c->need_recovery = 0;
@@ -1378,7 +1378,7 @@
 
 	ubifs_msg("mounted UBI device %d, volume %d, name \"%s\"",
 		  c->vi.ubi_num, c->vi.vol_id, c->vi.name);
-	if (mounted_read_only)
+	if (c->ro_mount)
 		ubifs_msg("mounted read-only");
 	x = (long long)c->main_lebs * c->leb_size;
 	ubifs_msg("file system size:   %lld bytes (%lld KiB, %lld MiB, %d "
@@ -1640,7 +1640,7 @@
 	}
 
 	dbg_gen("re-mounted read-write");
-	c->vfs_sb->s_flags &= ~MS_RDONLY;
+	c->ro_mount = 0;
 	c->remounting_rw = 0;
 	c->always_chk_crc = 0;
 	err = dbg_check_space_info(c);
@@ -1676,7 +1676,7 @@
 	int i, err;
 
 	ubifs_assert(!c->need_recovery);
-	ubifs_assert(!(c->vfs_sb->s_flags & MS_RDONLY));
+	ubifs_assert(!c->ro_mount);
 
 	mutex_lock(&c->umount_mutex);
 	if (c->bgt) {
@@ -1686,10 +1686,8 @@
 
 	dbg_save_space_info(c);
 
-	for (i = 0; i < c->jhead_cnt; i++) {
+	for (i = 0; i < c->jhead_cnt; i++)
 		ubifs_wbuf_sync(&c->jheads[i].wbuf);
-		hrtimer_cancel(&c->jheads[i].wbuf.timer);
-	}
 
 	c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY);
 	c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
@@ -1704,6 +1702,7 @@
 	vfree(c->ileb_buf);
 	c->ileb_buf = NULL;
 	ubifs_lpt_free(c, 1);
+	c->ro_mount = 1;
 	err = dbg_check_space_info(c);
 	if (err)
 		ubifs_ro_mode(c, err);
@@ -1735,7 +1734,7 @@
 	 * the mutex is locked.
 	 */
 	mutex_lock(&c->umount_mutex);
-	if (!(c->vfs_sb->s_flags & MS_RDONLY)) {
+	if (!c->ro_mount) {
 		/*
 		 * First of all kill the background thread to make sure it does
 		 * not interfere with un-mounting and freeing resources.
@@ -1745,23 +1744,22 @@
 			c->bgt = NULL;
 		}
 
-		/* Synchronize write-buffers */
-		if (c->jheads)
+		/*
+		 * On fatal errors c->ro_error is set to 1, in which case we do
+		 * not write the master node.
+		 */
+		if (!c->ro_error) {
+			int err;
+
+			/* Synchronize write-buffers */
 			for (i = 0; i < c->jhead_cnt; i++)
 				ubifs_wbuf_sync(&c->jheads[i].wbuf);
 
-		/*
-		 * On fatal errors c->ro_media is set to 1, in which case we do
-		 * not write the master node.
-		 */
-		if (!c->ro_media) {
 			/*
 			 * We are being cleanly unmounted which means the
 			 * orphans were killed - indicate this in the master
 			 * node. Also save the reserved GC LEB number.
 			 */
-			int err;
-
 			c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY);
 			c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
 			c->mst_node->gc_lnum = cpu_to_le32(c->gc_lnum);
@@ -1774,6 +1772,10 @@
 				 */
 				ubifs_err("failed to write master node, "
 					  "error %d", err);
+		} else {
+			for (i = 0; i < c->jhead_cnt; i++)
+				/* Make sure write-buffer timers are canceled */
+				hrtimer_cancel(&c->jheads[i].wbuf.timer);
 		}
 	}
 
@@ -1797,17 +1799,21 @@
 		return err;
 	}
 
-	if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {
+	if (c->ro_mount && !(*flags & MS_RDONLY)) {
+		if (c->ro_error) {
+			ubifs_msg("cannot re-mount R/W due to prior errors");
+			return -EROFS;
+		}
 		if (c->ro_media) {
-			ubifs_msg("cannot re-mount due to prior errors");
+			ubifs_msg("cannot re-mount R/W - UBI volume is R/O");
 			return -EROFS;
 		}
 		err = ubifs_remount_rw(c);
 		if (err)
 			return err;
-	} else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {
-		if (c->ro_media) {
-			ubifs_msg("cannot re-mount due to prior errors");
+	} else if (!c->ro_mount && (*flags & MS_RDONLY)) {
+		if (c->ro_error) {
+			ubifs_msg("cannot re-mount R/O due to prior errors");
 			return -EROFS;
 		}
 		ubifs_remount_ro(c);
@@ -2049,8 +2055,8 @@
 	 */
 	ubi = open_ubi(name, UBI_READONLY);
 	if (IS_ERR(ubi)) {
-		ubifs_err("cannot open \"%s\", error %d",
-			  name, (int)PTR_ERR(ubi));
+		dbg_err("cannot open \"%s\", error %d",
+			name, (int)PTR_ERR(ubi));
 		return PTR_ERR(ubi);
 	}
 	ubi_get_volume_info(ubi, &vi);
@@ -2064,9 +2070,11 @@
 	}
 
 	if (sb->s_root) {
+		struct ubifs_info *c1 = sb->s_fs_info;
+
 		/* A new mount point for already mounted UBIFS */
 		dbg_gen("this ubi volume is already mounted");
-		if ((flags ^ sb->s_flags) & MS_RDONLY) {
+		if (!!(flags & MS_RDONLY) != c1->ro_mount) {
 			err = -EBUSY;
 			goto out_deact;
 		}
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 2194915..ad9cf01 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -1177,6 +1177,7 @@
 	unsigned long time = get_seconds();
 
 	dbg_tnc("search key %s", DBGKEY(key));
+	ubifs_assert(key_type(c, key) < UBIFS_INVALID_KEY);
 
 	znode = c->zroot.znode;
 	if (unlikely(!znode)) {
@@ -2966,7 +2967,7 @@
  *
  * This function searches an indexing node by its first key @key and its
  * address @lnum:@offs. It looks up the indexing tree by pulling all indexing
- * nodes it traverses to TNC. This function is called fro indexing nodes which
+ * nodes it traverses to TNC. This function is called for indexing nodes which
  * were found on the media by scanning, for example when garbage-collecting or
  * when doing in-the-gaps commit. This means that the indexing node which is
  * looked for does not have to have exactly the same leftmost key @key, because
@@ -2988,6 +2989,8 @@
 	struct ubifs_znode *znode, *zn;
 	int n, nn;
 
+	ubifs_assert(key_type(c, key) < UBIFS_INVALID_KEY);
+
 	/*
 	 * The arguments have probably been read off flash, so don't assume
 	 * they are valid.
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 0c9876b..381d6b2 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -119,8 +119,12 @@
  * in TNC. However, when replaying, it is handy to introduce fake "truncation"
  * keys for truncation nodes because the code becomes simpler. So we define
  * %UBIFS_TRUN_KEY type.
+ *
+ * But otherwise, out of the journal reply scope, the truncation keys are
+ * invalid.
  */
-#define UBIFS_TRUN_KEY UBIFS_KEY_TYPES_CNT
+#define UBIFS_TRUN_KEY    UBIFS_KEY_TYPES_CNT
+#define UBIFS_INVALID_KEY UBIFS_KEY_TYPES_CNT
 
 /*
  * How much a directory entry/extended attribute entry adds to the parent/host
@@ -1028,6 +1032,8 @@
  * @max_leb_cnt: maximum count of logical eraseblocks
  * @old_leb_cnt: count of logical eraseblocks before re-size
  * @ro_media: the underlying UBI volume is read-only
+ * @ro_mount: the file-system was mounted as read-only
+ * @ro_error: UBIFS switched to R/O mode because an error happened
  *
  * @dirty_pg_cnt: number of dirty pages (not used)
  * @dirty_zn_cnt: number of dirty znodes
@@ -1168,11 +1174,14 @@
  * @replay_sqnum: sequence number of node currently being replayed
  * @need_recovery: file-system needs recovery
  * @replaying: set to %1 during journal replay
- * @unclean_leb_list: LEBs to recover when mounting ro to rw
- * @rcvrd_mst_node: recovered master node to write when mounting ro to rw
+ * @unclean_leb_list: LEBs to recover when re-mounting R/O mounted FS to R/W
+ *                    mode
+ * @rcvrd_mst_node: recovered master node to write when re-mounting R/O mounted
+ *                  FS to R/W mode
  * @size_tree: inode size information for recovery
- * @remounting_rw: set while remounting from ro to rw (sb flags have MS_RDONLY)
- * @always_chk_crc: always check CRCs (while mounting and remounting rw)
+ * @remounting_rw: set while re-mounting from R/O mode to R/W mode
+ * @always_chk_crc: always check CRCs (while mounting and remounting to R/W
+ *                  mode)
  * @mount_opts: UBIFS-specific mount options
  *
  * @dbg: debugging-related information
@@ -1268,7 +1277,9 @@
 	int leb_cnt;
 	int max_leb_cnt;
 	int old_leb_cnt;
-	int ro_media;
+	unsigned int ro_media:1;
+	unsigned int ro_mount:1;
+	unsigned int ro_error:1;
 
 	atomic_long_t dirty_pg_cnt;
 	atomic_long_t dirty_zn_cnt;
diff --git a/fs/udf/Kconfig b/fs/udf/Kconfig
index 0e0e99b..f8def3c 100644
--- a/fs/udf/Kconfig
+++ b/fs/udf/Kconfig
@@ -1,5 +1,6 @@
 config UDF_FS
 	tristate "UDF file system support"
+	depends on BKL # needs serious work to remove
 	select CRC_ITU_T
 	help
 	  This is the new file system used on some CD-ROMs and DVDs. Say Y if
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 65412d8..76f3d6d 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -1880,6 +1880,8 @@
 	struct kernel_lb_addr rootdir, fileset;
 	struct udf_sb_info *sbi;
 
+	lock_kernel();
+
 	uopt.flags = (1 << UDF_FLAG_USE_AD_IN_ICB) | (1 << UDF_FLAG_STRICT);
 	uopt.uid = -1;
 	uopt.gid = -1;
@@ -1888,8 +1890,10 @@
 	uopt.dmode = UDF_INVALID_MODE;
 
 	sbi = kzalloc(sizeof(struct udf_sb_info), GFP_KERNEL);
-	if (!sbi)
+	if (!sbi) {
+		unlock_kernel();
 		return -ENOMEM;
+	}
 
 	sb->s_fs_info = sbi;
 
@@ -2035,6 +2039,7 @@
 		goto error_out;
 	}
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	unlock_kernel();
 	return 0;
 
 error_out:
@@ -2055,6 +2060,7 @@
 	kfree(sbi);
 	sb->s_fs_info = NULL;
 
+	unlock_kernel();
 	return -EINVAL;
 }
 
diff --git a/fs/ufs/Kconfig b/fs/ufs/Kconfig
index e4f10a4..30c8f22 100644
--- a/fs/ufs/Kconfig
+++ b/fs/ufs/Kconfig
@@ -1,6 +1,7 @@
 config UFS_FS
 	tristate "UFS file system support (read only)"
 	depends on BLOCK
+	depends on BKL # probably fixable
 	help
 	  BSD and derivate versions of Unix (such as SunOS, FreeBSD, NetBSD,
 	  OpenBSD and NeXTstep) use a file system called UFS. Some System V
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index d510c1b..6b9be90 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -696,6 +696,8 @@
 	unsigned maxsymlen;
 	int ret = -EINVAL;
 
+	lock_kernel();
+
 	uspi = NULL;
 	ubh = NULL;
 	flags = 0;
@@ -1163,6 +1165,7 @@
 			goto failed;
 
 	UFSD("EXIT\n");
+	unlock_kernel();
 	return 0;
 
 dalloc_failed:
@@ -1174,10 +1177,12 @@
 	kfree(sbi);
 	sb->s_fs_info = NULL;
 	UFSD("EXIT (FAILED)\n");
+	unlock_kernel();
 	return ret;
 
 failed_nomem:
 	UFSD("EXIT (NOMEM)\n");
+	unlock_kernel();
 	return -ENOMEM;
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 286e36e..ba53128 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -188,8 +188,8 @@
 	atomic_set(&bp->b_hold, 1);
 	init_completion(&bp->b_iowait);
 	INIT_LIST_HEAD(&bp->b_list);
-	INIT_LIST_HEAD(&bp->b_hash_list);
-	init_MUTEX_LOCKED(&bp->b_sema); /* held, no waiters */
+	RB_CLEAR_NODE(&bp->b_rbnode);
+	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	XB_SET_OWNER(bp);
 	bp->b_target = target;
 	bp->b_file_offset = range_base;
@@ -262,8 +262,6 @@
 {
 	trace_xfs_buf_free(bp, _RET_IP_);
 
-	ASSERT(list_empty(&bp->b_hash_list));
-
 	if (bp->b_flags & (_XBF_PAGE_CACHE|_XBF_PAGES)) {
 		uint		i;
 
@@ -422,8 +420,10 @@
 {
 	xfs_off_t		range_base;
 	size_t			range_length;
-	xfs_bufhash_t		*hash;
-	xfs_buf_t		*bp, *n;
+	struct xfs_perag	*pag;
+	struct rb_node		**rbp;
+	struct rb_node		*parent;
+	xfs_buf_t		*bp;
 
 	range_base = (ioff << BBSHIFT);
 	range_length = (isize << BBSHIFT);
@@ -432,14 +432,37 @@
 	ASSERT(!(range_length < (1 << btp->bt_sshift)));
 	ASSERT(!(range_base & (xfs_off_t)btp->bt_smask));
 
-	hash = &btp->bt_hash[hash_long((unsigned long)ioff, btp->bt_hashshift)];
+	/* get tree root */
+	pag = xfs_perag_get(btp->bt_mount,
+				xfs_daddr_to_agno(btp->bt_mount, ioff));
 
-	spin_lock(&hash->bh_lock);
+	/* walk tree */
+	spin_lock(&pag->pag_buf_lock);
+	rbp = &pag->pag_buf_tree.rb_node;
+	parent = NULL;
+	bp = NULL;
+	while (*rbp) {
+		parent = *rbp;
+		bp = rb_entry(parent, struct xfs_buf, b_rbnode);
 
-	list_for_each_entry_safe(bp, n, &hash->bh_list, b_hash_list) {
-		ASSERT(btp == bp->b_target);
-		if (bp->b_file_offset == range_base &&
-		    bp->b_buffer_length == range_length) {
+		if (range_base < bp->b_file_offset)
+			rbp = &(*rbp)->rb_left;
+		else if (range_base > bp->b_file_offset)
+			rbp = &(*rbp)->rb_right;
+		else {
+			/*
+			 * found a block offset match. If the range doesn't
+			 * match, the only way this is allowed is if the buffer
+			 * in the cache is stale and the transaction that made
+			 * it stale has not yet committed. i.e. we are
+			 * reallocating a busy extent. Skip this buffer and
+			 * continue searching to the right for an exact match.
+			 */
+			if (bp->b_buffer_length != range_length) {
+				ASSERT(bp->b_flags & XBF_STALE);
+				rbp = &(*rbp)->rb_right;
+				continue;
+			}
 			atomic_inc(&bp->b_hold);
 			goto found;
 		}
@@ -449,17 +472,21 @@
 	if (new_bp) {
 		_xfs_buf_initialize(new_bp, btp, range_base,
 				range_length, flags);
-		new_bp->b_hash = hash;
-		list_add(&new_bp->b_hash_list, &hash->bh_list);
+		rb_link_node(&new_bp->b_rbnode, parent, rbp);
+		rb_insert_color(&new_bp->b_rbnode, &pag->pag_buf_tree);
+		/* the buffer keeps the perag reference until it is freed */
+		new_bp->b_pag = pag;
+		spin_unlock(&pag->pag_buf_lock);
 	} else {
 		XFS_STATS_INC(xb_miss_locked);
+		spin_unlock(&pag->pag_buf_lock);
+		xfs_perag_put(pag);
 	}
-
-	spin_unlock(&hash->bh_lock);
 	return new_bp;
 
 found:
-	spin_unlock(&hash->bh_lock);
+	spin_unlock(&pag->pag_buf_lock);
+	xfs_perag_put(pag);
 
 	/* Attempt to get the semaphore without sleeping,
 	 * if this does not work then we need to drop the
@@ -625,8 +652,7 @@
 xfs_buf_readahead(
 	xfs_buftarg_t		*target,
 	xfs_off_t		ioff,
-	size_t			isize,
-	xfs_buf_flags_t		flags)
+	size_t			isize)
 {
 	struct backing_dev_info *bdi;
 
@@ -634,8 +660,42 @@
 	if (bdi_read_congested(bdi))
 		return;
 
-	flags |= (XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
-	xfs_buf_read(target, ioff, isize, flags);
+	xfs_buf_read(target, ioff, isize,
+		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD|XBF_DONT_BLOCK);
+}
+
+/*
+ * Read an uncached buffer from disk. Allocates and returns a locked
+ * buffer containing the disk contents or nothing.
+ */
+struct xfs_buf *
+xfs_buf_read_uncached(
+	struct xfs_mount	*mp,
+	struct xfs_buftarg	*target,
+	xfs_daddr_t		daddr,
+	size_t			length,
+	int			flags)
+{
+	xfs_buf_t		*bp;
+	int			error;
+
+	bp = xfs_buf_get_uncached(target, length, flags);
+	if (!bp)
+		return NULL;
+
+	/* set up the buffer for a read IO */
+	xfs_buf_lock(bp);
+	XFS_BUF_SET_ADDR(bp, daddr);
+	XFS_BUF_READ(bp);
+	XFS_BUF_BUSY(bp);
+
+	xfsbdstrat(mp, bp);
+	error = xfs_buf_iowait(bp);
+	if (error || bp->b_error) {
+		xfs_buf_relse(bp);
+		return NULL;
+	}
+	return bp;
 }
 
 xfs_buf_t *
@@ -707,9 +767,10 @@
 }
 
 xfs_buf_t *
-xfs_buf_get_noaddr(
+xfs_buf_get_uncached(
+	struct xfs_buftarg	*target,
 	size_t			len,
-	xfs_buftarg_t		*target)
+	int			flags)
 {
 	unsigned long		page_count = PAGE_ALIGN(len) >> PAGE_SHIFT;
 	int			error, i;
@@ -725,7 +786,7 @@
 		goto fail_free_buf;
 
 	for (i = 0; i < page_count; i++) {
-		bp->b_pages[i] = alloc_page(GFP_KERNEL);
+		bp->b_pages[i] = alloc_page(xb_to_gfp(flags));
 		if (!bp->b_pages[i])
 			goto fail_free_mem;
 	}
@@ -740,7 +801,7 @@
 
 	xfs_buf_unlock(bp);
 
-	trace_xfs_buf_get_noaddr(bp, _RET_IP_);
+	trace_xfs_buf_get_uncached(bp, _RET_IP_);
 	return bp;
 
  fail_free_mem:
@@ -774,29 +835,30 @@
 xfs_buf_rele(
 	xfs_buf_t		*bp)
 {
-	xfs_bufhash_t		*hash = bp->b_hash;
+	struct xfs_perag	*pag = bp->b_pag;
 
 	trace_xfs_buf_rele(bp, _RET_IP_);
 
-	if (unlikely(!hash)) {
+	if (!pag) {
 		ASSERT(!bp->b_relse);
+		ASSERT(RB_EMPTY_NODE(&bp->b_rbnode));
 		if (atomic_dec_and_test(&bp->b_hold))
 			xfs_buf_free(bp);
 		return;
 	}
 
+	ASSERT(!RB_EMPTY_NODE(&bp->b_rbnode));
 	ASSERT(atomic_read(&bp->b_hold) > 0);
-	if (atomic_dec_and_lock(&bp->b_hold, &hash->bh_lock)) {
+	if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
 		if (bp->b_relse) {
 			atomic_inc(&bp->b_hold);
-			spin_unlock(&hash->bh_lock);
-			(*(bp->b_relse)) (bp);
-		} else if (bp->b_flags & XBF_FS_MANAGED) {
-			spin_unlock(&hash->bh_lock);
+			spin_unlock(&pag->pag_buf_lock);
+			bp->b_relse(bp);
 		} else {
 			ASSERT(!(bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q)));
-			list_del_init(&bp->b_hash_list);
-			spin_unlock(&hash->bh_lock);
+			rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
+			spin_unlock(&pag->pag_buf_lock);
+			xfs_perag_put(pag);
 			xfs_buf_free(bp);
 		}
 	}
@@ -859,7 +921,7 @@
 	trace_xfs_buf_lock(bp, _RET_IP_);
 
 	if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
-		xfs_log_force(bp->b_mount, 0);
+		xfs_log_force(bp->b_target->bt_mount, 0);
 	if (atomic_read(&bp->b_io_remaining))
 		blk_run_address_space(bp->b_target->bt_mapping);
 	down(&bp->b_sema);
@@ -924,19 +986,7 @@
 	xfs_buf_t		*bp =
 		container_of(work, xfs_buf_t, b_iodone_work);
 
-	/*
-	 * We can get an EOPNOTSUPP to ordered writes.  Here we clear the
-	 * ordered flag and reissue them.  Because we can't tell the higher
-	 * layers directly that they should not issue ordered I/O anymore, they
-	 * need to check if the _XFS_BARRIER_FAILED flag was set during I/O completion.
-	 */
-	if ((bp->b_error == EOPNOTSUPP) &&
-	    (bp->b_flags & (XBF_ORDERED|XBF_ASYNC)) == (XBF_ORDERED|XBF_ASYNC)) {
-		trace_xfs_buf_ordered_retry(bp, _RET_IP_);
-		bp->b_flags &= ~XBF_ORDERED;
-		bp->b_flags |= _XFS_BARRIER_FAILED;
-		xfs_buf_iorequest(bp);
-	} else if (bp->b_iodone)
+	if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
 	else if (bp->b_flags & XBF_ASYNC)
 		xfs_buf_relse(bp);
@@ -982,7 +1032,6 @@
 {
 	int			error;
 
-	bp->b_mount = mp;
 	bp->b_flags |= XBF_WRITE;
 	bp->b_flags &= ~(XBF_ASYNC | XBF_READ);
 
@@ -1003,8 +1052,6 @@
 {
 	trace_xfs_buf_bdwrite(bp, _RET_IP_);
 
-	bp->b_mount = mp;
-
 	bp->b_flags &= ~XBF_READ;
 	bp->b_flags |= (XBF_DELWRI | XBF_ASYNC);
 
@@ -1013,7 +1060,7 @@
 
 /*
  * Called when we want to stop a buffer from getting written or read.
- * We attach the EIO error, muck with its flags, and call biodone
+ * We attach the EIO error, muck with its flags, and call xfs_buf_ioend
  * so that the proper iodone callbacks get called.
  */
 STATIC int
@@ -1030,21 +1077,21 @@
 	XFS_BUF_ERROR(bp, EIO);
 
 	/*
-	 * We're calling biodone, so delete XBF_DONE flag.
+	 * We're calling xfs_buf_ioend, so delete XBF_DONE flag.
 	 */
 	XFS_BUF_UNREAD(bp);
 	XFS_BUF_UNDELAYWRITE(bp);
 	XFS_BUF_UNDONE(bp);
 	XFS_BUF_STALE(bp);
 
-	xfs_biodone(bp);
+	xfs_buf_ioend(bp, 0);
 
 	return EIO;
 }
 
 /*
  * Same as xfs_bioerror, except that we are releasing the buffer
- * here ourselves, and avoiding the biodone call.
+ * here ourselves, and avoiding the xfs_buf_ioend call.
  * This is meant for userdata errors; metadata bufs come with
  * iodone functions attached, so that we can track down errors.
  */
@@ -1093,7 +1140,7 @@
 xfs_bdstrat_cb(
 	struct xfs_buf	*bp)
 {
-	if (XFS_FORCED_SHUTDOWN(bp->b_mount)) {
+	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
 		trace_xfs_bdstrat_shut(bp, _RET_IP_);
 		/*
 		 * Metadata write that didn't get logged but
@@ -1195,7 +1242,7 @@
 
 	if (bp->b_flags & XBF_ORDERED) {
 		ASSERT(!(bp->b_flags & XBF_READ));
-		rw = WRITE_BARRIER;
+		rw = WRITE_FLUSH_FUA;
 	} else if (bp->b_flags & XBF_LOG_BUFFER) {
 		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
 		bp->b_flags &= ~_XBF_RUN_QUEUES;
@@ -1399,63 +1446,25 @@
  */
 void
 xfs_wait_buftarg(
-	xfs_buftarg_t	*btp)
+	struct xfs_buftarg	*btp)
 {
-	xfs_buf_t	*bp, *n;
-	xfs_bufhash_t	*hash;
-	uint		i;
+	struct xfs_perag	*pag;
+	uint			i;
 
-	for (i = 0; i < (1 << btp->bt_hashshift); i++) {
-		hash = &btp->bt_hash[i];
-again:
-		spin_lock(&hash->bh_lock);
-		list_for_each_entry_safe(bp, n, &hash->bh_list, b_hash_list) {
-			ASSERT(btp == bp->b_target);
-			if (!(bp->b_flags & XBF_FS_MANAGED)) {
-				spin_unlock(&hash->bh_lock);
-				/*
-				 * Catch superblock reference count leaks
-				 * immediately
-				 */
-				BUG_ON(bp->b_bn == 0);
-				delay(100);
-				goto again;
-			}
+	for (i = 0; i < btp->bt_mount->m_sb.sb_agcount; i++) {
+		pag = xfs_perag_get(btp->bt_mount, i);
+		spin_lock(&pag->pag_buf_lock);
+		while (rb_first(&pag->pag_buf_tree)) {
+			spin_unlock(&pag->pag_buf_lock);
+			delay(100);
+			spin_lock(&pag->pag_buf_lock);
 		}
-		spin_unlock(&hash->bh_lock);
+		spin_unlock(&pag->pag_buf_lock);
+		xfs_perag_put(pag);
 	}
 }
 
 /*
- *	Allocate buffer hash table for a given target.
- *	For devices containing metadata (i.e. not the log/realtime devices)
- *	we need to allocate a much larger hash table.
- */
-STATIC void
-xfs_alloc_bufhash(
-	xfs_buftarg_t		*btp,
-	int			external)
-{
-	unsigned int		i;
-
-	btp->bt_hashshift = external ? 3 : 12;	/* 8 or 4096 buckets */
-	btp->bt_hash = kmem_zalloc_large((1 << btp->bt_hashshift) *
-					 sizeof(xfs_bufhash_t));
-	for (i = 0; i < (1 << btp->bt_hashshift); i++) {
-		spin_lock_init(&btp->bt_hash[i].bh_lock);
-		INIT_LIST_HEAD(&btp->bt_hash[i].bh_list);
-	}
-}
-
-STATIC void
-xfs_free_bufhash(
-	xfs_buftarg_t		*btp)
-{
-	kmem_free_large(btp->bt_hash);
-	btp->bt_hash = NULL;
-}
-
-/*
  *	buftarg list for delwrite queue processing
  */
 static LIST_HEAD(xfs_buftarg_list);
@@ -1487,7 +1496,6 @@
 	xfs_flush_buftarg(btp, 1);
 	if (mp->m_flags & XFS_MOUNT_BARRIER)
 		xfs_blkdev_issue_flush(btp);
-	xfs_free_bufhash(btp);
 	iput(btp->bt_mapping->host);
 
 	/* Unregister the buftarg first so that we don't get a
@@ -1609,6 +1617,7 @@
 
 xfs_buftarg_t *
 xfs_alloc_buftarg(
+	struct xfs_mount	*mp,
 	struct block_device	*bdev,
 	int			external,
 	const char		*fsname)
@@ -1617,6 +1626,7 @@
 
 	btp = kmem_zalloc(sizeof(*btp), KM_SLEEP);
 
+	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
 	if (xfs_setsize_buftarg_early(btp, bdev))
@@ -1625,7 +1635,6 @@
 		goto error;
 	if (xfs_alloc_delwrite_queue(btp, fsname))
 		goto error;
-	xfs_alloc_bufhash(btp, external);
 	return btp;
 
 error:
@@ -1916,7 +1925,7 @@
 			bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
 
 			list_del_init(&bp->b_list);
-			xfs_iowait(bp);
+			xfs_buf_iowait(bp);
 			xfs_buf_relse(bp);
 		}
 	}
@@ -1933,7 +1942,7 @@
 		goto out;
 
 	xfslogd_workqueue = alloc_workqueue("xfslogd",
-					WQ_RESCUER | WQ_HIGHPRI, 1);
+					WQ_MEM_RECLAIM | WQ_HIGHPRI, 1);
 	if (!xfslogd_workqueue)
 		goto out_free_buf_zone;
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 2a05614..383a3f3 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -51,7 +51,6 @@
 #define XBF_DONE	(1 << 5) /* all pages in the buffer uptodate */
 #define XBF_DELWRI	(1 << 6) /* buffer has dirty pages */
 #define XBF_STALE	(1 << 7) /* buffer has been staled, do not find it */
-#define XBF_FS_MANAGED	(1 << 8) /* filesystem controls freeing memory */
 #define XBF_ORDERED	(1 << 11)/* use ordered writes */
 #define XBF_READ_AHEAD	(1 << 12)/* asynchronous read-ahead */
 #define XBF_LOG_BUFFER	(1 << 13)/* this is a buffer used for the log */
@@ -86,14 +85,6 @@
  */
 #define _XBF_PAGE_LOCKED	(1 << 22)
 
-/*
- * If we try a barrier write, but it fails we have to communicate
- * this to the upper layers.  Unfortunately b_error gets overwritten
- * when the buffer is re-issued so we have to add another flag to
- * keep this information.
- */
-#define _XFS_BARRIER_FAILED	(1 << 23)
-
 typedef unsigned int xfs_buf_flags_t;
 
 #define XFS_BUF_FLAGS \
@@ -104,7 +95,6 @@
 	{ XBF_DONE,		"DONE" }, \
 	{ XBF_DELWRI,		"DELWRI" }, \
 	{ XBF_STALE,		"STALE" }, \
-	{ XBF_FS_MANAGED,	"FS_MANAGED" }, \
 	{ XBF_ORDERED,		"ORDERED" }, \
 	{ XBF_READ_AHEAD,	"READ_AHEAD" }, \
 	{ XBF_LOCK,		"LOCK" },  	/* should never be set */\
@@ -114,8 +104,7 @@
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_RUN_QUEUES,	"RUN_QUEUES" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
-	{ _XBF_PAGE_LOCKED,	"PAGE_LOCKED" }, \
-	{ _XFS_BARRIER_FAILED,	"BARRIER_FAILED" }
+	{ _XBF_PAGE_LOCKED,	"PAGE_LOCKED" }
 
 
 typedef enum {
@@ -132,14 +121,11 @@
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
 	struct address_space	*bt_mapping;
+	struct xfs_mount	*bt_mount;
 	unsigned int		bt_bsize;
 	unsigned int		bt_sshift;
 	size_t			bt_smask;
 
-	/* per device buffer hash table */
-	uint			bt_hashshift;
-	xfs_bufhash_t		*bt_hash;
-
 	/* per device delwri queue */
 	struct task_struct	*bt_task;
 	struct list_head	bt_list;
@@ -167,34 +153,41 @@
 #define XB_PAGES	2
 
 typedef struct xfs_buf {
-	struct semaphore	b_sema;		/* semaphore for lockables */
-	unsigned long		b_queuetime;	/* time buffer was queued */
-	atomic_t		b_pin_count;	/* pin count */
-	wait_queue_head_t	b_waiters;	/* unpin waiters */
-	struct list_head	b_list;
-	xfs_buf_flags_t		b_flags;	/* status flags */
-	struct list_head	b_hash_list;	/* hash table list */
-	xfs_bufhash_t		*b_hash;	/* hash table list start */
-	xfs_buftarg_t		*b_target;	/* buffer target (device) */
-	atomic_t		b_hold;		/* reference count */
-	xfs_daddr_t		b_bn;		/* block number for I/O */
+	/*
+	 * first cacheline holds all the fields needed for an uncontended cache
+	 * hit to be fully processed. The semaphore straddles the cacheline
+	 * boundary, but the counter and lock sits on the first cacheline,
+	 * which is the only bit that is touched if we hit the semaphore
+	 * fast-path on locking.
+	 */
+	struct rb_node		b_rbnode;	/* rbtree node */
 	xfs_off_t		b_file_offset;	/* offset in file */
 	size_t			b_buffer_length;/* size of buffer in bytes */
+	atomic_t		b_hold;		/* reference count */
+	xfs_buf_flags_t		b_flags;	/* status flags */
+	struct semaphore	b_sema;		/* semaphore for lockables */
+
+	wait_queue_head_t	b_waiters;	/* unpin waiters */
+	struct list_head	b_list;
+	struct xfs_perag	*b_pag;		/* contains rbtree root */
+	xfs_buftarg_t		*b_target;	/* buffer target (device) */
+	xfs_daddr_t		b_bn;		/* block number for I/O */
 	size_t			b_count_desired;/* desired transfer size */
 	void			*b_addr;	/* virtual address of buffer */
 	struct work_struct	b_iodone_work;
-	atomic_t		b_io_remaining;	/* #outstanding I/O requests */
 	xfs_buf_iodone_t	b_iodone;	/* I/O completion function */
 	xfs_buf_relse_t		b_relse;	/* releasing function */
 	struct completion	b_iowait;	/* queue for I/O waiters */
 	void			*b_fspriv;
 	void			*b_fspriv2;
-	struct xfs_mount	*b_mount;
-	unsigned short		b_error;	/* error code on I/O */
-	unsigned int		b_page_count;	/* size of page array */
-	unsigned int		b_offset;	/* page offset in first page */
 	struct page		**b_pages;	/* array of page pointers */
 	struct page		*b_page_array[XB_PAGES]; /* inline pages */
+	unsigned long		b_queuetime;	/* time buffer was queued */
+	atomic_t		b_pin_count;	/* pin count */
+	atomic_t		b_io_remaining;	/* #outstanding I/O requests */
+	unsigned int		b_page_count;	/* size of page array */
+	unsigned int		b_offset;	/* page offset in first page */
+	unsigned short		b_error;	/* error code on I/O */
 #ifdef XFS_BUF_LOCK_TRACKING
 	int			b_last_holder;
 #endif
@@ -213,11 +206,13 @@
 				xfs_buf_flags_t);
 
 extern xfs_buf_t *xfs_buf_get_empty(size_t, xfs_buftarg_t *);
-extern xfs_buf_t *xfs_buf_get_noaddr(size_t, xfs_buftarg_t *);
+extern xfs_buf_t *xfs_buf_get_uncached(struct xfs_buftarg *, size_t, int);
 extern int xfs_buf_associate_memory(xfs_buf_t *, void *, size_t);
 extern void xfs_buf_hold(xfs_buf_t *);
-extern void xfs_buf_readahead(xfs_buftarg_t *, xfs_off_t, size_t,
-				xfs_buf_flags_t);
+extern void xfs_buf_readahead(xfs_buftarg_t *, xfs_off_t, size_t);
+struct xfs_buf *xfs_buf_read_uncached(struct xfs_mount *mp,
+				struct xfs_buftarg *target,
+				xfs_daddr_t daddr, size_t length, int flags);
 
 /* Releasing Buffers */
 extern void xfs_buf_free(xfs_buf_t *);
@@ -242,6 +237,8 @@
 extern int xfs_buf_iowait(xfs_buf_t *);
 extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 				xfs_buf_rw_t);
+#define xfs_buf_zero(bp, off, len) \
+	    xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
 
 static inline int xfs_buf_geterror(xfs_buf_t *bp)
 {
@@ -276,8 +273,6 @@
 					XFS_BUF_DONE(bp);	\
 				} while (0)
 
-#define XFS_BUF_UNMANAGE(bp)	((bp)->b_flags &= ~XBF_FS_MANAGED)
-
 #define XFS_BUF_DELAYWRITE(bp)		((bp)->b_flags |= XBF_DELWRI)
 #define XFS_BUF_UNDELAYWRITE(bp)	xfs_buf_delwri_dequeue(bp)
 #define XFS_BUF_ISDELAYWRITE(bp)	((bp)->b_flags & XBF_DELWRI)
@@ -356,25 +351,11 @@
 	xfs_buf_rele(bp);
 }
 
-#define xfs_biodone(bp)		xfs_buf_ioend(bp, 0)
-
-#define xfs_biomove(bp, off, len, data, rw) \
-	    xfs_buf_iomove((bp), (off), (len), (data), \
-		((rw) == XBF_WRITE) ? XBRW_WRITE : XBRW_READ)
-
-#define xfs_biozero(bp, off, len) \
-	    xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
-
-#define xfs_iowait(bp)	xfs_buf_iowait(bp)
-
-#define xfs_baread(target, rablkno, ralen)  \
-	xfs_buf_readahead((target), (rablkno), (ralen), XBF_DONT_BLOCK)
-
-
 /*
  *	Handling of buftargs.
  */
-extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int, const char *);
+extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
+			struct block_device *, int, const char *);
 extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
 extern void xfs_wait_buftarg(xfs_buftarg_t *);
 extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
diff --git a/fs/xfs/linux-2.6/xfs_cred.h b/fs/xfs/linux-2.6/xfs_cred.h
deleted file mode 100644
index 55bddf3..0000000
--- a/fs/xfs/linux-2.6/xfs_cred.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_CRED_H__
-#define __XFS_CRED_H__
-
-#include <linux/capability.h>
-
-/*
- * Credentials
- */
-typedef const struct cred cred_t;
-
-#endif  /* __XFS_CRED_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c
index 1f279b0..ed88ed1 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.c
+++ b/fs/xfs/linux-2.6/xfs_fs_subr.c
@@ -32,10 +32,9 @@
 	xfs_off_t	last,
 	int		fiopt)
 {
-	struct address_space *mapping = VFS_I(ip)->i_mapping;
-
-	if (mapping->nrpages)
-		truncate_inode_pages(mapping, first);
+	/* can't toss partial tail pages, so mask them out */
+	last &= ~(PAGE_SIZE - 1);
+	truncate_inode_pages_range(VFS_I(ip)->i_mapping, first, last - 1);
 }
 
 int
@@ -50,12 +49,11 @@
 
 	trace_xfs_pagecache_inval(ip, first, last);
 
-	if (mapping->nrpages) {
-		xfs_iflags_clear(ip, XFS_ITRUNCATED);
-		ret = filemap_write_and_wait(mapping);
-		if (!ret)
-			truncate_inode_pages(mapping, first);
-	}
+	xfs_iflags_clear(ip, XFS_ITRUNCATED);
+	ret = filemap_write_and_wait_range(mapping, first,
+				last == -1 ? LLONG_MAX : last);
+	if (!ret)
+		truncate_inode_pages_range(mapping, first, last);
 	return -ret;
 }
 
@@ -71,10 +69,9 @@
 	int		ret = 0;
 	int		ret2;
 
-	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		xfs_iflags_clear(ip, XFS_ITRUNCATED);
-		ret = -filemap_fdatawrite(mapping);
-	}
+	xfs_iflags_clear(ip, XFS_ITRUNCATED);
+	ret = -filemap_fdatawrite_range(mapping, first,
+				last == -1 ? LLONG_MAX : last);
 	if (flags & XBF_ASYNC)
 		return ret;
 	ret2 = xfs_wait_on_pages(ip, first, last);
@@ -91,7 +88,9 @@
 {
 	struct address_space *mapping = VFS_I(ip)->i_mapping;
 
-	if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
-		return -filemap_fdatawait(mapping);
+	if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) {
+		return -filemap_fdatawait_range(mapping, first,
+					last == -1 ? ip->i_size - 1 : last);
+	}
 	return 0;
 }
diff --git a/fs/xfs/linux-2.6/xfs_globals.c b/fs/xfs/linux-2.6/xfs_globals.c
index 2ae8b1c..76e81cf 100644
--- a/fs/xfs/linux-2.6/xfs_globals.c
+++ b/fs/xfs/linux-2.6/xfs_globals.c
@@ -16,7 +16,6 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include "xfs.h"
-#include "xfs_cred.h"
 #include "xfs_sysctl.h"
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_globals.h b/fs/xfs/linux-2.6/xfs_globals.h
deleted file mode 100644
index 69f71ca..0000000
--- a/fs/xfs/linux-2.6/xfs_globals.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_GLOBALS_H__
-#define __XFS_GLOBALS_H__
-
-extern uint64_t	xfs_panic_mask;		/* set to cause more panics */
-
-#endif	/* __XFS_GLOBALS_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index 3b9e626..2ea238f6 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -790,7 +790,7 @@
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	fa.fsx_xflags = xfs_ip2xflags(ip);
 	fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
-	fa.fsx_projid = ip->i_d.di_projid;
+	fa.fsx_projid = xfs_get_projid(ip);
 
 	if (attr) {
 		if (ip->i_afp) {
@@ -909,10 +909,10 @@
 		return XFS_ERROR(EIO);
 
 	/*
-	 * Disallow 32bit project ids because on-disk structure
-	 * is 16bit only.
+	 * Disallow 32bit project ids when projid32bit feature is not enabled.
 	 */
-	if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1))
+	if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) &&
+			!xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
 		return XFS_ERROR(EINVAL);
 
 	/*
@@ -961,7 +961,7 @@
 	if (mask & FSX_PROJID) {
 		if (XFS_IS_QUOTA_RUNNING(mp) &&
 		    XFS_IS_PQUOTA_ON(mp) &&
-		    ip->i_d.di_projid != fa->fsx_projid) {
+		    xfs_get_projid(ip) != fa->fsx_projid) {
 			ASSERT(tp);
 			code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
 						capable(CAP_FOWNER) ?
@@ -1063,12 +1063,12 @@
 		 * Change the ownerships and register quota modifications
 		 * in the transaction.
 		 */
-		if (ip->i_d.di_projid != fa->fsx_projid) {
+		if (xfs_get_projid(ip) != fa->fsx_projid) {
 			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
 				olddquot = xfs_qm_vop_chown(tp, ip,
 							&ip->i_gdquot, gdqp);
 			}
-			ip->i_d.di_projid = fa->fsx_projid;
+			xfs_set_projid(ip, fa->fsx_projid);
 
 			/*
 			 * We may have to rev the inode as well as
@@ -1088,8 +1088,8 @@
 		xfs_diflags_to_linux(ip);
 	}
 
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
 
 	XFS_STATS_INC(xs_ig_attrchg);
 
@@ -1301,7 +1301,8 @@
 	case XFS_IOC_ALLOCSP64:
 	case XFS_IOC_FREESP64:
 	case XFS_IOC_RESVSP64:
-	case XFS_IOC_UNRESVSP64: {
+	case XFS_IOC_UNRESVSP64:
+	case XFS_IOC_ZERO_RANGE: {
 		xfs_flock64_t		bf;
 
 		if (copy_from_user(&bf, arg, sizeof(bf)))
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index 6c83f7f..b3486df 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -164,7 +164,8 @@
 	    get_user(bstat->bs_extsize,	&bstat32->bs_extsize)	||
 	    get_user(bstat->bs_extents,	&bstat32->bs_extents)	||
 	    get_user(bstat->bs_gen,	&bstat32->bs_gen)	||
-	    get_user(bstat->bs_projid,	&bstat32->bs_projid)	||
+	    get_user(bstat->bs_projid_lo, &bstat32->bs_projid_lo) ||
+	    get_user(bstat->bs_projid_hi, &bstat32->bs_projid_hi) ||
 	    get_user(bstat->bs_dmevmask, &bstat32->bs_dmevmask)	||
 	    get_user(bstat->bs_dmstate,	&bstat32->bs_dmstate)	||
 	    get_user(bstat->bs_aextents, &bstat32->bs_aextents))
@@ -218,6 +219,7 @@
 	    put_user(buffer->bs_extents,  &p32->bs_extents)	||
 	    put_user(buffer->bs_gen,	  &p32->bs_gen)		||
 	    put_user(buffer->bs_projid,	  &p32->bs_projid)	||
+	    put_user(buffer->bs_projid_hi,	&p32->bs_projid_hi)	||
 	    put_user(buffer->bs_dmevmask, &p32->bs_dmevmask)	||
 	    put_user(buffer->bs_dmstate,  &p32->bs_dmstate)	||
 	    put_user(buffer->bs_aextents, &p32->bs_aextents))
@@ -574,6 +576,7 @@
 	case XFS_IOC_FSGEOMETRY_V1:
 	case XFS_IOC_FSGROWFSDATA:
 	case XFS_IOC_FSGROWFSRT:
+	case XFS_IOC_ZERO_RANGE:
 		return xfs_file_ioctl(filp, cmd, p);
 #else
 	case XFS_IOC_ALLOCSP_32:
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.h b/fs/xfs/linux-2.6/xfs_ioctl32.h
index 1024c4f..08b6057 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.h
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.h
@@ -65,8 +65,10 @@
 	__s32		bs_extsize;	/* extent size			*/
 	__s32		bs_extents;	/* number of extents		*/
 	__u32		bs_gen;		/* generation count		*/
-	__u16		bs_projid;	/* project id			*/
-	unsigned char	bs_pad[14];	/* pad space, unused		*/
+	__u16		bs_projid_lo;	/* lower part of project id	*/
+#define	bs_projid	bs_projid_lo	/* (previously just bs_projid)	*/
+	__u16		bs_projid_hi;	/* high part of project id	*/
+	unsigned char	bs_pad[12];	/* pad space, unused		*/
 	__u32		bs_dmevmask;	/* DMIG event mask		*/
 	__u16		bs_dmstate;	/* DMIG state info		*/
 	__u16		bs_aextents;	/* attribute number of extents	*/
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index b1fc2a6..ec858e0 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -95,41 +95,6 @@
 }
 
 /*
- * Change the requested timestamp in the given inode.
- * We don't lock across timestamp updates, and we don't log them but
- * we do record the fact that there is dirty information in core.
- */
-void
-xfs_ichgtime(
-	xfs_inode_t	*ip,
-	int		flags)
-{
-	struct inode	*inode = VFS_I(ip);
-	timespec_t	tv;
-	int		sync_it = 0;
-
-	tv = current_fs_time(inode->i_sb);
-
-	if ((flags & XFS_ICHGTIME_MOD) &&
-	    !timespec_equal(&inode->i_mtime, &tv)) {
-		inode->i_mtime = tv;
-		sync_it = 1;
-	}
-	if ((flags & XFS_ICHGTIME_CHG) &&
-	    !timespec_equal(&inode->i_ctime, &tv)) {
-		inode->i_ctime = tv;
-		sync_it = 1;
-	}
-
-	/*
-	 * Update complete - now make sure everyone knows that the inode
-	 * is dirty.
-	 */
-	if (sync_it)
-		xfs_mark_inode_dirty_sync(ip);
-}
-
-/*
  * Hook in SELinux.  This is not quite correct yet, what we really need
  * here (as we do for default ACLs) is a mechanism by which creation of
  * these attrs can be journalled at inode creation time (along with the
@@ -224,7 +189,7 @@
 	}
 
 	xfs_dentry_to_name(&name, dentry);
-	error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL);
+	error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
 	if (unlikely(error))
 		goto out_free_acl;
 
@@ -397,7 +362,7 @@
 		(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
 	xfs_dentry_to_name(&name, dentry);
 
-	error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip, NULL);
+	error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip);
 	if (unlikely(error))
 		goto out;
 
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 2fa0bd9..214ddd7 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -71,6 +71,7 @@
 #include <linux/random.h>
 #include <linux/ctype.h>
 #include <linux/writeback.h>
+#include <linux/capability.h>
 
 #include <asm/page.h>
 #include <asm/div64.h>
@@ -79,14 +80,12 @@
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
-#include <xfs_cred.h>
 #include <xfs_vnode.h>
 #include <xfs_stats.h>
 #include <xfs_sysctl.h>
 #include <xfs_iops.h>
 #include <xfs_aops.h>
 #include <xfs_super.h>
-#include <xfs_globals.h>
 #include <xfs_buf.h>
 
 /*
@@ -144,7 +143,7 @@
 #define SYNCHRONIZE()	barrier()
 #define __return_address __builtin_return_address(0)
 
-#define dfltprid	0
+#define XFS_PROJID_DEFAULT	0
 #define MAXPATHLEN	1024
 
 #define MIN(a,b)	(min(a,b))
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index a4e0797..ab31ce5 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -44,7 +44,6 @@
 #include "xfs_buf_item.h"
 #include "xfs_utils.h"
 #include "xfs_vnodeops.h"
-#include "xfs_version.h"
 #include "xfs_log_priv.h"
 #include "xfs_trans_priv.h"
 #include "xfs_filestream.h"
@@ -645,7 +644,7 @@
 	XFS_BUF_ORDERED(sbp);
 
 	xfsbdstrat(mp, sbp);
-	error = xfs_iowait(sbp);
+	error = xfs_buf_iowait(sbp);
 
 	/*
 	 * Clear all the flags we set and possible error state in the
@@ -693,8 +692,7 @@
 xfs_blkdev_issue_flush(
 	xfs_buftarg_t		*buftarg)
 {
-	blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL,
-			BLKDEV_IFL_WAIT);
+	blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL);
 }
 
 STATIC void
@@ -758,18 +756,20 @@
 	 * Setup xfs_mount buffer target pointers
 	 */
 	error = ENOMEM;
-	mp->m_ddev_targp = xfs_alloc_buftarg(ddev, 0, mp->m_fsname);
+	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, 0, mp->m_fsname);
 	if (!mp->m_ddev_targp)
 		goto out_close_rtdev;
 
 	if (rtdev) {
-		mp->m_rtdev_targp = xfs_alloc_buftarg(rtdev, 1, mp->m_fsname);
+		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, 1,
+							mp->m_fsname);
 		if (!mp->m_rtdev_targp)
 			goto out_free_ddev_targ;
 	}
 
 	if (logdev && logdev != ddev) {
-		mp->m_logdev_targp = xfs_alloc_buftarg(logdev, 1, mp->m_fsname);
+		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, 1,
+							mp->m_fsname);
 		if (!mp->m_logdev_targp)
 			goto out_free_rtdev_targ;
 	} else {
@@ -972,12 +972,7 @@
 
 /*
  * Dirty the XFS inode when mark_inode_dirty_sync() is called so that
- * we catch unlogged VFS level updates to the inode. Care must be taken
- * here - the transaction code calls mark_inode_dirty_sync() to mark the
- * VFS inode dirty in a transaction and clears the i_update_core field;
- * it must clear the field after calling mark_inode_dirty_sync() to
- * correctly indicate that the dirty state has been propagated into the
- * inode log item.
+ * we catch unlogged VFS level updates to the inode.
  *
  * We need the barrier() to maintain correct ordering between unlogged
  * updates and the transaction commit code that clears the i_update_core
@@ -1521,8 +1516,9 @@
 	if (error)
 		goto out_free_fsname;
 
-	if (xfs_icsb_init_counters(mp))
-		mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB;
+	error = xfs_icsb_init_counters(mp);
+	if (error)
+		goto out_close_devices;
 
 	error = xfs_readsb(mp, flags);
 	if (error)
@@ -1583,6 +1579,7 @@
 	xfs_freesb(mp);
  out_destroy_counters:
 	xfs_icsb_destroy_counters(mp);
+ out_close_devices:
 	xfs_close_devices(mp);
  out_free_fsname:
 	xfs_free_fsname(mp);
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h
index 1ef4a4d..50a3266 100644
--- a/fs/xfs/linux-2.6/xfs_super.h
+++ b/fs/xfs/linux-2.6/xfs_super.h
@@ -62,6 +62,7 @@
 # define XFS_DBG_STRING		"no debug"
 #endif
 
+#define XFS_VERSION_STRING	"SGI XFS"
 #define XFS_BUILD_OPTIONS	XFS_ACL_STRING \
 				XFS_SECURITY_STRING \
 				XFS_REALTIME_STRING \
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 81976ff..37d3325 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -39,42 +39,39 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 
+/*
+ * The inode lookup is done in batches to keep the amount of lock traffic and
+ * radix tree lookups to a minimum. The batch size is a trade off between
+ * lookup reduction and stack usage. This is in the reclaim path, so we can't
+ * be too greedy.
+ */
+#define XFS_LOOKUP_BATCH	32
 
-STATIC xfs_inode_t *
-xfs_inode_ag_lookup(
-	struct xfs_mount	*mp,
-	struct xfs_perag	*pag,
-	uint32_t		*first_index,
-	int			tag)
+STATIC int
+xfs_inode_ag_walk_grab(
+	struct xfs_inode	*ip)
 {
-	int			nr_found;
-	struct xfs_inode	*ip;
+	struct inode		*inode = VFS_I(ip);
 
-	/*
-	 * use a gang lookup to find the next inode in the tree
-	 * as the tree is sparse and a gang lookup walks to find
-	 * the number of objects requested.
-	 */
-	if (tag == XFS_ICI_NO_TAG) {
-		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
-				(void **)&ip, *first_index, 1);
-	} else {
-		nr_found = radix_tree_gang_lookup_tag(&pag->pag_ici_root,
-				(void **)&ip, *first_index, 1, tag);
+	/* nothing to sync during shutdown */
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return EFSCORRUPTED;
+
+	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
+	if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+		return ENOENT;
+
+	/* If we can't grab the inode, it must on it's way to reclaim. */
+	if (!igrab(inode))
+		return ENOENT;
+
+	if (is_bad_inode(inode)) {
+		IRELE(ip);
+		return ENOENT;
 	}
-	if (!nr_found)
-		return NULL;
 
-	/*
-	 * Update the index for the next lookup. Catch overflows
-	 * into the next AG range which can occur if we have inodes
-	 * in the last block of the AG and we are currently
-	 * pointing to the last inode.
-	 */
-	*first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
-	if (*first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
-		return NULL;
-	return ip;
+	/* inode is valid */
+	return 0;
 }
 
 STATIC int
@@ -83,49 +80,75 @@
 	struct xfs_perag	*pag,
 	int			(*execute)(struct xfs_inode *ip,
 					   struct xfs_perag *pag, int flags),
-	int			flags,
-	int			tag,
-	int			exclusive,
-	int			*nr_to_scan)
+	int			flags)
 {
 	uint32_t		first_index;
 	int			last_error = 0;
 	int			skipped;
+	int			done;
+	int			nr_found;
 
 restart:
+	done = 0;
 	skipped = 0;
 	first_index = 0;
+	nr_found = 0;
 	do {
+		struct xfs_inode *batch[XFS_LOOKUP_BATCH];
 		int		error = 0;
-		xfs_inode_t	*ip;
+		int		i;
 
-		if (exclusive)
-			write_lock(&pag->pag_ici_lock);
-		else
-			read_lock(&pag->pag_ici_lock);
-		ip = xfs_inode_ag_lookup(mp, pag, &first_index, tag);
-		if (!ip) {
-			if (exclusive)
-				write_unlock(&pag->pag_ici_lock);
-			else
-				read_unlock(&pag->pag_ici_lock);
+		read_lock(&pag->pag_ici_lock);
+		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
+					(void **)batch, first_index,
+					XFS_LOOKUP_BATCH);
+		if (!nr_found) {
+			read_unlock(&pag->pag_ici_lock);
 			break;
 		}
 
-		/* execute releases pag->pag_ici_lock */
-		error = execute(ip, pag, flags);
-		if (error == EAGAIN) {
-			skipped++;
-			continue;
+		/*
+		 * Grab the inodes before we drop the lock. if we found
+		 * nothing, nr == 0 and the loop will be skipped.
+		 */
+		for (i = 0; i < nr_found; i++) {
+			struct xfs_inode *ip = batch[i];
+
+			if (done || xfs_inode_ag_walk_grab(ip))
+				batch[i] = NULL;
+
+			/*
+			 * Update the index for the next lookup. Catch overflows
+			 * into the next AG range which can occur if we have inodes
+			 * in the last block of the AG and we are currently
+			 * pointing to the last inode.
+			 */
+			first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+			if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
+				done = 1;
 		}
-		if (error)
-			last_error = error;
+
+		/* unlock now we've grabbed the inodes. */
+		read_unlock(&pag->pag_ici_lock);
+
+		for (i = 0; i < nr_found; i++) {
+			if (!batch[i])
+				continue;
+			error = execute(batch[i], pag, flags);
+			IRELE(batch[i]);
+			if (error == EAGAIN) {
+				skipped++;
+				continue;
+			}
+			if (error && last_error != EFSCORRUPTED)
+				last_error = error;
+		}
 
 		/* bail out if the filesystem is corrupted.  */
 		if (error == EFSCORRUPTED)
 			break;
 
-	} while ((*nr_to_scan)--);
+	} while (nr_found && !done);
 
 	if (skipped) {
 		delay(1);
@@ -134,110 +157,32 @@
 	return last_error;
 }
 
-/*
- * Select the next per-ag structure to iterate during the walk. The reclaim
- * walk is optimised only to walk AGs with reclaimable inodes in them.
- */
-static struct xfs_perag *
-xfs_inode_ag_iter_next_pag(
-	struct xfs_mount	*mp,
-	xfs_agnumber_t		*first,
-	int			tag)
-{
-	struct xfs_perag	*pag = NULL;
-
-	if (tag == XFS_ICI_RECLAIM_TAG) {
-		int found;
-		int ref;
-
-		spin_lock(&mp->m_perag_lock);
-		found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
-				(void **)&pag, *first, 1, tag);
-		if (found <= 0) {
-			spin_unlock(&mp->m_perag_lock);
-			return NULL;
-		}
-		*first = pag->pag_agno + 1;
-		/* open coded pag reference increment */
-		ref = atomic_inc_return(&pag->pag_ref);
-		spin_unlock(&mp->m_perag_lock);
-		trace_xfs_perag_get_reclaim(mp, pag->pag_agno, ref, _RET_IP_);
-	} else {
-		pag = xfs_perag_get(mp, *first);
-		(*first)++;
-	}
-	return pag;
-}
-
 int
 xfs_inode_ag_iterator(
 	struct xfs_mount	*mp,
 	int			(*execute)(struct xfs_inode *ip,
 					   struct xfs_perag *pag, int flags),
-	int			flags,
-	int			tag,
-	int			exclusive,
-	int			*nr_to_scan)
+	int			flags)
 {
 	struct xfs_perag	*pag;
 	int			error = 0;
 	int			last_error = 0;
 	xfs_agnumber_t		ag;
-	int			nr;
 
-	nr = nr_to_scan ? *nr_to_scan : INT_MAX;
 	ag = 0;
-	while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag, tag))) {
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, tag,
-						exclusive, &nr);
+	while ((pag = xfs_perag_get(mp, ag))) {
+		ag = pag->pag_agno + 1;
+		error = xfs_inode_ag_walk(mp, pag, execute, flags);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
 			if (error == EFSCORRUPTED)
 				break;
 		}
-		if (nr <= 0)
-			break;
 	}
-	if (nr_to_scan)
-		*nr_to_scan = nr;
 	return XFS_ERROR(last_error);
 }
 
-/* must be called with pag_ici_lock held and releases it */
-int
-xfs_sync_inode_valid(
-	struct xfs_inode	*ip,
-	struct xfs_perag	*pag)
-{
-	struct inode		*inode = VFS_I(ip);
-	int			error = EFSCORRUPTED;
-
-	/* nothing to sync during shutdown */
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		goto out_unlock;
-
-	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
-	error = ENOENT;
-	if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
-		goto out_unlock;
-
-	/* If we can't grab the inode, it must on it's way to reclaim. */
-	if (!igrab(inode))
-		goto out_unlock;
-
-	if (is_bad_inode(inode)) {
-		IRELE(ip);
-		goto out_unlock;
-	}
-
-	/* inode is valid */
-	error = 0;
-out_unlock:
-	read_unlock(&pag->pag_ici_lock);
-	return error;
-}
-
 STATIC int
 xfs_sync_inode_data(
 	struct xfs_inode	*ip,
@@ -248,10 +193,6 @@
 	struct address_space *mapping = inode->i_mapping;
 	int			error = 0;
 
-	error = xfs_sync_inode_valid(ip, pag);
-	if (error)
-		return error;
-
 	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		goto out_wait;
 
@@ -268,7 +209,6 @@
  out_wait:
 	if (flags & SYNC_WAIT)
 		xfs_ioend_wait(ip);
-	IRELE(ip);
 	return error;
 }
 
@@ -280,10 +220,6 @@
 {
 	int			error = 0;
 
-	error = xfs_sync_inode_valid(ip, pag);
-	if (error)
-		return error;
-
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	if (xfs_inode_clean(ip))
 		goto out_unlock;
@@ -302,7 +238,6 @@
 
  out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	IRELE(ip);
 	return error;
 }
 
@@ -318,8 +253,7 @@
 
 	ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0);
 
-	error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags,
-				      XFS_ICI_NO_TAG, 0, NULL);
+	error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags);
 	if (error)
 		return XFS_ERROR(error);
 
@@ -337,8 +271,7 @@
 {
 	ASSERT((flags & ~SYNC_WAIT) == 0);
 
-	return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags,
-				     XFS_ICI_NO_TAG, 0, NULL);
+	return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags);
 }
 
 STATIC int
@@ -698,6 +631,43 @@
 }
 
 /*
+ * Grab the inode for reclaim exclusively.
+ * Return 0 if we grabbed it, non-zero otherwise.
+ */
+STATIC int
+xfs_reclaim_inode_grab(
+	struct xfs_inode	*ip,
+	int			flags)
+{
+
+	/*
+	 * do some unlocked checks first to avoid unnecceary lock traffic.
+	 * The first is a flush lock check, the second is a already in reclaim
+	 * check. Only do these checks if we are not going to block on locks.
+	 */
+	if ((flags & SYNC_TRYLOCK) &&
+	    (!ip->i_flush.done || __xfs_iflags_test(ip, XFS_IRECLAIM))) {
+		return 1;
+	}
+
+	/*
+	 * The radix tree lock here protects a thread in xfs_iget from racing
+	 * with us starting reclaim on the inode.  Once we have the
+	 * XFS_IRECLAIM flag set it will not touch us.
+	 */
+	spin_lock(&ip->i_flags_lock);
+	ASSERT_ALWAYS(__xfs_iflags_test(ip, XFS_IRECLAIMABLE));
+	if (__xfs_iflags_test(ip, XFS_IRECLAIM)) {
+		/* ignore as it is already under reclaim */
+		spin_unlock(&ip->i_flags_lock);
+		return 1;
+	}
+	__xfs_iflags_set(ip, XFS_IRECLAIM);
+	spin_unlock(&ip->i_flags_lock);
+	return 0;
+}
+
+/*
  * Inodes in different states need to be treated differently, and the return
  * value of xfs_iflush is not sufficient to get this right. The following table
  * lists the inode states and the reclaim actions necessary for non-blocking
@@ -755,23 +725,6 @@
 {
 	int	error = 0;
 
-	/*
-	 * The radix tree lock here protects a thread in xfs_iget from racing
-	 * with us starting reclaim on the inode.  Once we have the
-	 * XFS_IRECLAIM flag set it will not touch us.
-	 */
-	spin_lock(&ip->i_flags_lock);
-	ASSERT_ALWAYS(__xfs_iflags_test(ip, XFS_IRECLAIMABLE));
-	if (__xfs_iflags_test(ip, XFS_IRECLAIM)) {
-		/* ignore as it is already under reclaim */
-		spin_unlock(&ip->i_flags_lock);
-		write_unlock(&pag->pag_ici_lock);
-		return 0;
-	}
-	__xfs_iflags_set(ip, XFS_IRECLAIM);
-	spin_unlock(&ip->i_flags_lock);
-	write_unlock(&pag->pag_ici_lock);
-
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	if (!xfs_iflock_nowait(ip)) {
 		if (!(sync_mode & SYNC_WAIT))
@@ -868,13 +821,126 @@
 
 }
 
+/*
+ * Walk the AGs and reclaim the inodes in them. Even if the filesystem is
+ * corrupted, we still want to try to reclaim all the inodes. If we don't,
+ * then a shut down during filesystem unmount reclaim walk leak all the
+ * unreclaimed inodes.
+ */
+int
+xfs_reclaim_inodes_ag(
+	struct xfs_mount	*mp,
+	int			flags,
+	int			*nr_to_scan)
+{
+	struct xfs_perag	*pag;
+	int			error = 0;
+	int			last_error = 0;
+	xfs_agnumber_t		ag;
+	int			trylock = flags & SYNC_TRYLOCK;
+	int			skipped;
+
+restart:
+	ag = 0;
+	skipped = 0;
+	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
+		unsigned long	first_index = 0;
+		int		done = 0;
+		int		nr_found = 0;
+
+		ag = pag->pag_agno + 1;
+
+		if (trylock) {
+			if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) {
+				skipped++;
+				continue;
+			}
+			first_index = pag->pag_ici_reclaim_cursor;
+		} else
+			mutex_lock(&pag->pag_ici_reclaim_lock);
+
+		do {
+			struct xfs_inode *batch[XFS_LOOKUP_BATCH];
+			int	i;
+
+			write_lock(&pag->pag_ici_lock);
+			nr_found = radix_tree_gang_lookup_tag(
+					&pag->pag_ici_root,
+					(void **)batch, first_index,
+					XFS_LOOKUP_BATCH,
+					XFS_ICI_RECLAIM_TAG);
+			if (!nr_found) {
+				write_unlock(&pag->pag_ici_lock);
+				break;
+			}
+
+			/*
+			 * Grab the inodes before we drop the lock. if we found
+			 * nothing, nr == 0 and the loop will be skipped.
+			 */
+			for (i = 0; i < nr_found; i++) {
+				struct xfs_inode *ip = batch[i];
+
+				if (done || xfs_reclaim_inode_grab(ip, flags))
+					batch[i] = NULL;
+
+				/*
+				 * Update the index for the next lookup. Catch
+				 * overflows into the next AG range which can
+				 * occur if we have inodes in the last block of
+				 * the AG and we are currently pointing to the
+				 * last inode.
+				 */
+				first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+				if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
+					done = 1;
+			}
+
+			/* unlock now we've grabbed the inodes. */
+			write_unlock(&pag->pag_ici_lock);
+
+			for (i = 0; i < nr_found; i++) {
+				if (!batch[i])
+					continue;
+				error = xfs_reclaim_inode(batch[i], pag, flags);
+				if (error && last_error != EFSCORRUPTED)
+					last_error = error;
+			}
+
+			*nr_to_scan -= XFS_LOOKUP_BATCH;
+
+		} while (nr_found && !done && *nr_to_scan > 0);
+
+		if (trylock && !done)
+			pag->pag_ici_reclaim_cursor = first_index;
+		else
+			pag->pag_ici_reclaim_cursor = 0;
+		mutex_unlock(&pag->pag_ici_reclaim_lock);
+		xfs_perag_put(pag);
+	}
+
+	/*
+	 * if we skipped any AG, and we still have scan count remaining, do
+	 * another pass this time using blocking reclaim semantics (i.e
+	 * waiting on the reclaim locks and ignoring the reclaim cursors). This
+	 * ensure that when we get more reclaimers than AGs we block rather
+	 * than spin trying to execute reclaim.
+	 */
+	if (trylock && skipped && *nr_to_scan > 0) {
+		trylock = 0;
+		goto restart;
+	}
+	return XFS_ERROR(last_error);
+}
+
 int
 xfs_reclaim_inodes(
 	xfs_mount_t	*mp,
 	int		mode)
 {
-	return xfs_inode_ag_iterator(mp, xfs_reclaim_inode, mode,
-					XFS_ICI_RECLAIM_TAG, 1, NULL);
+	int		nr_to_scan = INT_MAX;
+
+	return xfs_reclaim_inodes_ag(mp, mode, &nr_to_scan);
 }
 
 /*
@@ -896,17 +962,16 @@
 		if (!(gfp_mask & __GFP_FS))
 			return -1;
 
-		xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0,
-					XFS_ICI_RECLAIM_TAG, 1, &nr_to_scan);
-		/* if we don't exhaust the scan, don't bother coming back */
+		xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK, &nr_to_scan);
+		/* terminate if we don't exhaust the scan */
 		if (nr_to_scan > 0)
 			return -1;
        }
 
 	reclaimable = 0;
 	ag = 0;
-	while ((pag = xfs_inode_ag_iter_next_pag(mp, &ag,
-					XFS_ICI_RECLAIM_TAG))) {
+	while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) {
+		ag = pag->pag_agno + 1;
 		reclaimable += pag->pag_ici_reclaimable;
 		xfs_perag_put(pag);
 	}
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index fe78726..32ba662 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -47,10 +47,10 @@
 void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
 				struct xfs_inode *ip);
 
-int xfs_sync_inode_valid(struct xfs_inode *ip, struct xfs_perag *pag);
+int xfs_sync_inode_grab(struct xfs_inode *ip);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags),
-	int flags, int tag, int write_lock, int *nr_to_scan);
+	int flags);
 
 void xfs_inode_shrinker_register(struct xfs_mount *mp);
 void xfs_inode_shrinker_unregister(struct xfs_mount *mp);
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index be5dffd..acef2e9 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -124,7 +124,7 @@
 		 unsigned long caller_ip),					\
 	TP_ARGS(mp, agno, refcount, caller_ip))
 DEFINE_PERAG_REF_EVENT(xfs_perag_get);
-DEFINE_PERAG_REF_EVENT(xfs_perag_get_reclaim);
+DEFINE_PERAG_REF_EVENT(xfs_perag_get_tag);
 DEFINE_PERAG_REF_EVENT(xfs_perag_put);
 DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim);
 DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim);
@@ -325,13 +325,12 @@
 DEFINE_BUF_EVENT(xfs_buf_lock_done);
 DEFINE_BUF_EVENT(xfs_buf_cond_lock);
 DEFINE_BUF_EVENT(xfs_buf_unlock);
-DEFINE_BUF_EVENT(xfs_buf_ordered_retry);
 DEFINE_BUF_EVENT(xfs_buf_iowait);
 DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
 DEFINE_BUF_EVENT(xfs_buf_delwri_dequeue);
 DEFINE_BUF_EVENT(xfs_buf_delwri_split);
-DEFINE_BUF_EVENT(xfs_buf_get_noaddr);
+DEFINE_BUF_EVENT(xfs_buf_get_uncached);
 DEFINE_BUF_EVENT(xfs_bdstrat_shut);
 DEFINE_BUF_EVENT(xfs_buf_item_relse);
 DEFINE_BUF_EVENT(xfs_buf_item_iodone);
diff --git a/fs/xfs/linux-2.6/xfs_version.h b/fs/xfs/linux-2.6/xfs_version.h
deleted file mode 100644
index f8d279d..0000000
--- a/fs/xfs/linux-2.6/xfs_version.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright (c) 2001-2002,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_VERSION_H__
-#define __XFS_VERSION_H__
-
-/*
- * Dummy file that can contain a timestamp to put into the
- * XFS init string, to help users keep track of what they're
- * running
- */
-
-#define XFS_VERSION_STRING "SGI XFS"
-
-#endif /* __XFS_VERSION_H__ */
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index e1a2f68..faf8e1a 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -463,88 +463,69 @@
 	uint			flags)
 {
 	xfs_bmbt_irec_t map;
-	int		nmaps, error;
+	int		nmaps = 1, error;
 	xfs_buf_t	*bp;
-	xfs_inode_t	*quotip;
-	xfs_mount_t	*mp;
+	xfs_inode_t	*quotip = XFS_DQ_TO_QIP(dqp);
+	xfs_mount_t	*mp = dqp->q_mount;
 	xfs_disk_dquot_t *ddq;
-	xfs_dqid_t	id;
-	boolean_t	newdquot;
+	xfs_dqid_t	id = be32_to_cpu(dqp->q_core.d_id);
 	xfs_trans_t	*tp = (tpp ? *tpp : NULL);
 
-	mp = dqp->q_mount;
-	id = be32_to_cpu(dqp->q_core.d_id);
-	nmaps = 1;
-	newdquot = B_FALSE;
+	dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
 
-	/*
-	 * If we don't know where the dquot lives, find out.
-	 */
-	if (dqp->q_blkno == (xfs_daddr_t) 0) {
-		/* We use the id as an index */
-		dqp->q_fileoffset = (xfs_fileoff_t)id /
-					mp->m_quotainfo->qi_dqperchunk;
-		nmaps = 1;
-		quotip = XFS_DQ_TO_QIP(dqp);
-		xfs_ilock(quotip, XFS_ILOCK_SHARED);
+	xfs_ilock(quotip, XFS_ILOCK_SHARED);
+	if (XFS_IS_THIS_QUOTA_OFF(dqp)) {
 		/*
-		 * Return if this type of quotas is turned off while we didn't
-		 * have an inode lock
+		 * Return if this type of quotas is turned off while we
+		 * didn't have the quota inode lock.
 		 */
-		if (XFS_IS_THIS_QUOTA_OFF(dqp)) {
-			xfs_iunlock(quotip, XFS_ILOCK_SHARED);
-			return (ESRCH);
-		}
-		/*
-		 * Find the block map; no allocations yet
-		 */
-		error = xfs_bmapi(NULL, quotip, dqp->q_fileoffset,
-				  XFS_DQUOT_CLUSTER_SIZE_FSB,
-				  XFS_BMAPI_METADATA,
-				  NULL, 0, &map, &nmaps, NULL);
-
 		xfs_iunlock(quotip, XFS_ILOCK_SHARED);
-		if (error)
-			return (error);
-		ASSERT(nmaps == 1);
-		ASSERT(map.br_blockcount == 1);
-
-		/*
-		 * offset of dquot in the (fixed sized) dquot chunk.
-		 */
-		dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) *
-			sizeof(xfs_dqblk_t);
-		if (map.br_startblock == HOLESTARTBLOCK) {
-			/*
-			 * We don't allocate unless we're asked to
-			 */
-			if (!(flags & XFS_QMOPT_DQALLOC))
-				return (ENOENT);
-
-			ASSERT(tp);
-			if ((error = xfs_qm_dqalloc(tpp, mp, dqp, quotip,
-						dqp->q_fileoffset, &bp)))
-				return (error);
-			tp = *tpp;
-			newdquot = B_TRUE;
-		} else {
-			/*
-			 * store the blkno etc so that we don't have to do the
-			 * mapping all the time
-			 */
-			dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
-		}
+		return ESRCH;
 	}
-	ASSERT(dqp->q_blkno != DELAYSTARTBLOCK);
-	ASSERT(dqp->q_blkno != HOLESTARTBLOCK);
 
 	/*
-	 * Read in the buffer, unless we've just done the allocation
-	 * (in which case we already have the buf).
+	 * Find the block map; no allocations yet
 	 */
-	if (!newdquot) {
+	error = xfs_bmapi(NULL, quotip, dqp->q_fileoffset,
+			  XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
+			  NULL, 0, &map, &nmaps, NULL);
+
+	xfs_iunlock(quotip, XFS_ILOCK_SHARED);
+	if (error)
+		return error;
+
+	ASSERT(nmaps == 1);
+	ASSERT(map.br_blockcount == 1);
+
+	/*
+	 * Offset of dquot in the (fixed sized) dquot chunk.
+	 */
+	dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) *
+		sizeof(xfs_dqblk_t);
+
+	ASSERT(map.br_startblock != DELAYSTARTBLOCK);
+	if (map.br_startblock == HOLESTARTBLOCK) {
+		/*
+		 * We don't allocate unless we're asked to
+		 */
+		if (!(flags & XFS_QMOPT_DQALLOC))
+			return ENOENT;
+
+		ASSERT(tp);
+		error = xfs_qm_dqalloc(tpp, mp, dqp, quotip,
+					dqp->q_fileoffset, &bp);
+		if (error)
+			return error;
+		tp = *tpp;
+	} else {
 		trace_xfs_dqtobp_read(dqp);
 
+		/*
+		 * store the blkno etc so that we don't have to do the
+		 * mapping all the time
+		 */
+		dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
+
 		error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 					   dqp->q_blkno,
 					   mp->m_quotainfo->qi_dqchunklen,
@@ -552,13 +533,14 @@
 		if (error || !bp)
 			return XFS_ERROR(error);
 	}
+
 	ASSERT(XFS_BUF_ISBUSY(bp));
 	ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
 
 	/*
 	 * calculate the location of the dquot inside the buffer.
 	 */
-	ddq = (xfs_disk_dquot_t *)((char *)XFS_BUF_PTR(bp) + dqp->q_bufoffset);
+	ddq = (struct xfs_disk_dquot *)(XFS_BUF_PTR(bp) + dqp->q_bufoffset);
 
 	/*
 	 * A simple sanity check in case we got a corrupted dquot...
@@ -1176,18 +1158,18 @@
 	xfs_dquot_t		*dqp,
 	uint			flags)
 {
-	xfs_mount_t		*mp;
-	xfs_buf_t		*bp;
-	xfs_disk_dquot_t	*ddqp;
+	struct xfs_mount	*mp = dqp->q_mount;
+	struct xfs_buf		*bp;
+	struct xfs_disk_dquot	*ddqp;
 	int			error;
 
 	ASSERT(XFS_DQ_IS_LOCKED(dqp));
 	ASSERT(!completion_done(&dqp->q_flush));
+
 	trace_xfs_dqflush(dqp);
 
 	/*
-	 * If not dirty, or it's pinned and we are not supposed to
-	 * block, nada.
+	 * If not dirty, or it's pinned and we are not supposed to block, nada.
 	 */
 	if (!XFS_DQ_IS_DIRTY(dqp) ||
 	    (!(flags & SYNC_WAIT) && atomic_read(&dqp->q_pincount) > 0)) {
@@ -1201,40 +1183,46 @@
 	 * down forcibly. If that's the case we must not write this dquot
 	 * to disk, because the log record didn't make it to disk!
 	 */
-	if (XFS_FORCED_SHUTDOWN(dqp->q_mount)) {
-		dqp->dq_flags &= ~(XFS_DQ_DIRTY);
+	if (XFS_FORCED_SHUTDOWN(mp)) {
+		dqp->dq_flags &= ~XFS_DQ_DIRTY;
 		xfs_dqfunlock(dqp);
 		return XFS_ERROR(EIO);
 	}
 
 	/*
 	 * Get the buffer containing the on-disk dquot
-	 * We don't need a transaction envelope because we know that the
-	 * the ondisk-dquot has already been allocated for.
 	 */
-	if ((error = xfs_qm_dqtobp(NULL, dqp, &ddqp, &bp, XFS_QMOPT_DOWARN))) {
+	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
+				   mp->m_quotainfo->qi_dqchunklen, 0, &bp);
+	if (error) {
 		ASSERT(error != ENOENT);
-		/*
-		 * Quotas could have gotten turned off (ESRCH)
-		 */
 		xfs_dqfunlock(dqp);
-		return (error);
+		return error;
 	}
 
-	if (xfs_qm_dqcheck(&dqp->q_core, be32_to_cpu(ddqp->d_id),
-			   0, XFS_QMOPT_DOWARN, "dqflush (incore copy)")) {
-		xfs_force_shutdown(dqp->q_mount, SHUTDOWN_CORRUPT_INCORE);
+	/*
+	 * Calculate the location of the dquot inside the buffer.
+	 */
+	ddqp = (struct xfs_disk_dquot *)(XFS_BUF_PTR(bp) + dqp->q_bufoffset);
+
+	/*
+	 * A simple sanity check in case we got a corrupted dquot..
+	 */
+	if (xfs_qm_dqcheck(&dqp->q_core, be32_to_cpu(ddqp->d_id), 0,
+			   XFS_QMOPT_DOWARN, "dqflush (incore copy)")) {
+		xfs_buf_relse(bp);
+		xfs_dqfunlock(dqp);
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 		return XFS_ERROR(EIO);
 	}
 
 	/* This is the only portion of data that needs to persist */
-	memcpy(ddqp, &(dqp->q_core), sizeof(xfs_disk_dquot_t));
+	memcpy(ddqp, &dqp->q_core, sizeof(xfs_disk_dquot_t));
 
 	/*
 	 * Clear the dirty field and remember the flush lsn for later use.
 	 */
-	dqp->dq_flags &= ~(XFS_DQ_DIRTY);
-	mp = dqp->q_mount;
+	dqp->dq_flags &= ~XFS_DQ_DIRTY;
 
 	xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn,
 					&dqp->q_logitem.qli_item.li_lsn);
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 9a92407..f8e854b 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -55,8 +55,6 @@
 kmem_zone_t	*qm_dqzone;
 kmem_zone_t	*qm_dqtrxzone;
 
-static cred_t	xfs_zerocr;
-
 STATIC void	xfs_qm_list_init(xfs_dqlist_t *, char *, int);
 STATIC void	xfs_qm_list_destroy(xfs_dqlist_t *);
 
@@ -837,7 +835,7 @@
 			xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP,
 						flags & XFS_QMOPT_DQALLOC,
 						ip->i_udquot, &ip->i_gdquot) :
-			xfs_qm_dqattach_one(ip, ip->i_d.di_projid, XFS_DQ_PROJ,
+			xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ,
 						flags & XFS_QMOPT_DQALLOC,
 						ip->i_udquot, &ip->i_gdquot);
 		/*
@@ -1199,87 +1197,6 @@
 	mutex_destroy(&(list->qh_lock));
 }
 
-
-/*
- * Stripped down version of dqattach. This doesn't attach, or even look at the
- * dquots attached to the inode. The rationale is that there won't be any
- * attached at the time this is called from quotacheck.
- */
-STATIC int
-xfs_qm_dqget_noattach(
-	xfs_inode_t	*ip,
-	xfs_dquot_t	**O_udqpp,
-	xfs_dquot_t	**O_gdqpp)
-{
-	int		error;
-	xfs_mount_t	*mp;
-	xfs_dquot_t	*udqp, *gdqp;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	mp = ip->i_mount;
-	udqp = NULL;
-	gdqp = NULL;
-
-	if (XFS_IS_UQUOTA_ON(mp)) {
-		ASSERT(ip->i_udquot == NULL);
-		/*
-		 * We want the dquot allocated if it doesn't exist.
-		 */
-		if ((error = xfs_qm_dqget(mp, ip, ip->i_d.di_uid, XFS_DQ_USER,
-					 XFS_QMOPT_DQALLOC | XFS_QMOPT_DOWARN,
-					 &udqp))) {
-			/*
-			 * Shouldn't be able to turn off quotas here.
-			 */
-			ASSERT(error != ESRCH);
-			ASSERT(error != ENOENT);
-			return error;
-		}
-		ASSERT(udqp);
-	}
-
-	if (XFS_IS_OQUOTA_ON(mp)) {
-		ASSERT(ip->i_gdquot == NULL);
-		if (udqp)
-			xfs_dqunlock(udqp);
-		error = XFS_IS_GQUOTA_ON(mp) ?
-				xfs_qm_dqget(mp, ip,
-					     ip->i_d.di_gid, XFS_DQ_GROUP,
-					     XFS_QMOPT_DQALLOC|XFS_QMOPT_DOWARN,
-					     &gdqp) :
-				xfs_qm_dqget(mp, ip,
-					     ip->i_d.di_projid, XFS_DQ_PROJ,
-					     XFS_QMOPT_DQALLOC|XFS_QMOPT_DOWARN,
-					     &gdqp);
-		if (error) {
-			if (udqp)
-				xfs_qm_dqrele(udqp);
-			ASSERT(error != ESRCH);
-			ASSERT(error != ENOENT);
-			return error;
-		}
-		ASSERT(gdqp);
-
-		/* Reacquire the locks in the right order */
-		if (udqp) {
-			if (! xfs_qm_dqlock_nowait(udqp)) {
-				xfs_dqunlock(gdqp);
-				xfs_dqlock(udqp);
-				xfs_dqlock(gdqp);
-			}
-		}
-	}
-
-	*O_udqpp = udqp;
-	*O_gdqpp = gdqp;
-
-#ifdef QUOTADEBUG
-	if (udqp) ASSERT(XFS_DQ_IS_LOCKED(udqp));
-	if (gdqp) ASSERT(XFS_DQ_IS_LOCKED(gdqp));
-#endif
-	return 0;
-}
-
 /*
  * Create an inode and return with a reference already taken, but unlocked
  * This is how we create quota inodes
@@ -1305,8 +1222,8 @@
 		return error;
 	}
 
-	if ((error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0,
-				   &xfs_zerocr, 0, 1, ip, &committed))) {
+	error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, 1, ip, &committed);
+	if (error) {
 		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES |
 				 XFS_TRANS_ABORT);
 		return error;
@@ -1516,7 +1433,7 @@
 				rablkcnt =  map[i+1].br_blockcount;
 				rablkno = map[i+1].br_startblock;
 				while (rablkcnt--) {
-					xfs_baread(mp->m_ddev_targp,
+					xfs_buf_readahead(mp->m_ddev_targp,
 					       XFS_FSB_TO_DADDR(mp, rablkno),
 					       mp->m_quotainfo->qi_dqchunklen);
 					rablkno++;
@@ -1546,18 +1463,34 @@
 
 /*
  * Called by dqusage_adjust in doing a quotacheck.
- * Given the inode, and a dquot (either USR or GRP, doesn't matter),
- * this updates its incore copy as well as the buffer copy. This is
- * so that once the quotacheck is done, we can just log all the buffers,
- * as opposed to logging numerous updates to individual dquots.
+ *
+ * Given the inode, and a dquot id this updates both the incore dqout as well
+ * as the buffer copy. This is so that once the quotacheck is done, we can
+ * just log all the buffers, as opposed to logging numerous updates to
+ * individual dquots.
  */
-STATIC void
+STATIC int
 xfs_qm_quotacheck_dqadjust(
-	xfs_dquot_t		*dqp,
+	struct xfs_inode	*ip,
+	xfs_dqid_t		id,
+	uint			type,
 	xfs_qcnt_t		nblks,
 	xfs_qcnt_t		rtblks)
 {
-	ASSERT(XFS_DQ_IS_LOCKED(dqp));
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_dquot	*dqp;
+	int			error;
+
+	error = xfs_qm_dqget(mp, ip, id, type,
+			     XFS_QMOPT_DQALLOC | XFS_QMOPT_DOWARN, &dqp);
+	if (error) {
+		/*
+		 * Shouldn't be able to turn off quotas here.
+		 */
+		ASSERT(error != ESRCH);
+		ASSERT(error != ENOENT);
+		return error;
+	}
 
 	trace_xfs_dqadjust(dqp);
 
@@ -1582,11 +1515,13 @@
 	 * There are no timers for the default values set in the root dquot.
 	 */
 	if (dqp->q_core.d_id) {
-		xfs_qm_adjust_dqlimits(dqp->q_mount, &dqp->q_core);
-		xfs_qm_adjust_dqtimers(dqp->q_mount, &dqp->q_core);
+		xfs_qm_adjust_dqlimits(mp, &dqp->q_core);
+		xfs_qm_adjust_dqtimers(mp, &dqp->q_core);
 	}
 
 	dqp->dq_flags |= XFS_DQ_DIRTY;
+	xfs_qm_dqput(dqp);
+	return 0;
 }
 
 STATIC int
@@ -1629,8 +1564,7 @@
 	int		*res)		/* result code value */
 {
 	xfs_inode_t	*ip;
-	xfs_dquot_t	*udqp, *gdqp;
-	xfs_qcnt_t	nblks, rtblks;
+	xfs_qcnt_t	nblks, rtblks = 0;
 	int		error;
 
 	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
@@ -1650,51 +1584,24 @@
 	 * the case in all other instances. It's OK that we do this because
 	 * quotacheck is done only at mount time.
 	 */
-	if ((error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip))) {
+	error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip);
+	if (error) {
 		*res = BULKSTAT_RV_NOTHING;
 		return error;
 	}
 
-	/*
-	 * Obtain the locked dquots. In case of an error (eg. allocation
-	 * fails for ENOSPC), we return the negative of the error number
-	 * to bulkstat, so that it can get propagated to quotacheck() and
-	 * making us disable quotas for the file system.
-	 */
-	if ((error = xfs_qm_dqget_noattach(ip, &udqp, &gdqp))) {
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		IRELE(ip);
-		*res = BULKSTAT_RV_GIVEUP;
-		return error;
-	}
+	ASSERT(ip->i_delayed_blks == 0);
 
-	rtblks = 0;
-	if (! XFS_IS_REALTIME_INODE(ip)) {
-		nblks = (xfs_qcnt_t)ip->i_d.di_nblocks;
-	} else {
+	if (XFS_IS_REALTIME_INODE(ip)) {
 		/*
 		 * Walk thru the extent list and count the realtime blocks.
 		 */
-		if ((error = xfs_qm_get_rtblks(ip, &rtblks))) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			IRELE(ip);
-			if (udqp)
-				xfs_qm_dqput(udqp);
-			if (gdqp)
-				xfs_qm_dqput(gdqp);
-			*res = BULKSTAT_RV_GIVEUP;
-			return error;
-		}
-		nblks = (xfs_qcnt_t)ip->i_d.di_nblocks - rtblks;
+		error = xfs_qm_get_rtblks(ip, &rtblks);
+		if (error)
+			goto error0;
 	}
-	ASSERT(ip->i_delayed_blks == 0);
 
-	/*
-	 * We can't release the inode while holding its dquot locks.
-	 * The inode can go into inactive and might try to acquire the dquotlocks.
-	 * So, just unlock here and do a vn_rele at the end.
-	 */
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	nblks = (xfs_qcnt_t)ip->i_d.di_nblocks - rtblks;
 
 	/*
 	 * Add the (disk blocks and inode) resources occupied by this
@@ -1709,26 +1616,36 @@
 	 * and quotaoffs don't race. (Quotachecks happen at mount time only).
 	 */
 	if (XFS_IS_UQUOTA_ON(mp)) {
-		ASSERT(udqp);
-		xfs_qm_quotacheck_dqadjust(udqp, nblks, rtblks);
-		xfs_qm_dqput(udqp);
+		error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_uid,
+						   XFS_DQ_USER, nblks, rtblks);
+		if (error)
+			goto error0;
 	}
-	if (XFS_IS_OQUOTA_ON(mp)) {
-		ASSERT(gdqp);
-		xfs_qm_quotacheck_dqadjust(gdqp, nblks, rtblks);
-		xfs_qm_dqput(gdqp);
-	}
-	/*
-	 * Now release the inode. This will send it to 'inactive', and
-	 * possibly even free blocks.
-	 */
-	IRELE(ip);
 
-	/*
-	 * Goto next inode.
-	 */
+	if (XFS_IS_GQUOTA_ON(mp)) {
+		error = xfs_qm_quotacheck_dqadjust(ip, ip->i_d.di_gid,
+						   XFS_DQ_GROUP, nblks, rtblks);
+		if (error)
+			goto error0;
+	}
+
+	if (XFS_IS_PQUOTA_ON(mp)) {
+		error = xfs_qm_quotacheck_dqadjust(ip, xfs_get_projid(ip),
+						   XFS_DQ_PROJ, nblks, rtblks);
+		if (error)
+			goto error0;
+	}
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	IRELE(ip);
 	*res = BULKSTAT_RV_DIDONE;
 	return 0;
+
+error0:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	IRELE(ip);
+	*res = BULKSTAT_RV_GIVEUP;
+	return error;
 }
 
 /*
@@ -2224,7 +2141,7 @@
 
 
 /*
- * Given an inode, a uid and gid (from cred_t) make sure that we have
+ * Given an inode, a uid, gid and prid make sure that we have
  * allocated relevant dquot(s) on disk, and that we won't exceed inode
  * quotas by creating this file.
  * This also attaches dquot(s) to the given inode after locking it,
@@ -2332,7 +2249,7 @@
 			xfs_dqunlock(gq);
 		}
 	} else if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) {
-		if (ip->i_d.di_projid != prid) {
+		if (xfs_get_projid(ip) != prid) {
 			xfs_iunlock(ip, lockflags);
 			if ((error = xfs_qm_dqget(mp, NULL, (xfs_dqid_t)prid,
 						 XFS_DQ_PROJ,
@@ -2454,7 +2371,7 @@
 	}
 	if (XFS_IS_OQUOTA_ON(ip->i_mount) && gdqp) {
 		if (XFS_IS_PQUOTA_ON(ip->i_mount) &&
-		     ip->i_d.di_projid != be32_to_cpu(gdqp->q_core.d_id))
+		     xfs_get_projid(ip) != be32_to_cpu(gdqp->q_core.d_id))
 			prjflags = XFS_QMOPT_ENOSPC;
 
 		if (prjflags ||
@@ -2558,7 +2475,7 @@
 		ip->i_gdquot = gdqp;
 		ASSERT(XFS_IS_OQUOTA_ON(mp));
 		ASSERT((XFS_IS_GQUOTA_ON(mp) ?
-			ip->i_d.di_gid : ip->i_d.di_projid) ==
+			ip->i_d.di_gid : xfs_get_projid(ip)) ==
 				be32_to_cpu(gdqp->q_core.d_id));
 		xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1);
 	}
diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c
index bea02d7..45b5cb1 100644
--- a/fs/xfs/quota/xfs_qm_bhv.c
+++ b/fs/xfs/quota/xfs_qm_bhv.c
@@ -81,7 +81,7 @@
 	xfs_mount_t		*mp = ip->i_mount;
 	xfs_dquot_t		*dqp;
 
-	if (!xfs_qm_dqget(mp, NULL, ip->i_d.di_projid, XFS_DQ_PROJ, 0, &dqp)) {
+	if (!xfs_qm_dqget(mp, NULL, xfs_get_projid(ip), XFS_DQ_PROJ, 0, &dqp)) {
 		xfs_fill_statvfs_from_dquot(statp, &dqp->q_core);
 		xfs_qm_dqput(dqp);
 	}
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 45e5849..bdebc18 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -276,7 +276,7 @@
 		goto out_unlock;
 	}
 
-	xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
 
 out_unlock:
@@ -875,21 +875,14 @@
 	struct xfs_perag	*pag,
 	int			flags)
 {
-	int			error;
-
 	/* skip quota inodes */
 	if (ip == ip->i_mount->m_quotainfo->qi_uquotaip ||
 	    ip == ip->i_mount->m_quotainfo->qi_gquotaip) {
 		ASSERT(ip->i_udquot == NULL);
 		ASSERT(ip->i_gdquot == NULL);
-		read_unlock(&pag->pag_ici_lock);
 		return 0;
 	}
 
-	error = xfs_sync_inode_valid(ip, pag);
-	if (error)
-		return error;
-
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	if ((flags & XFS_UQUOTA_ACCT) && ip->i_udquot) {
 		xfs_qm_dqrele(ip->i_udquot);
@@ -900,8 +893,6 @@
 		ip->i_gdquot = NULL;
 	}
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-	IRELE(ip);
 	return 0;
 }
 
@@ -918,8 +909,7 @@
 	uint		 flags)
 {
 	ASSERT(mp->m_quotainfo);
-	xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags,
-				XFS_ICI_NO_TAG, 0, NULL);
+	xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags);
 }
 
 /*------------------------------------------------------------------------*/
@@ -1175,7 +1165,7 @@
 	}
 	xfs_qm_internalqcheck_get_dquots(mp,
 					(xfs_dqid_t) ip->i_d.di_uid,
-					(xfs_dqid_t) ip->i_d.di_projid,
+					(xfs_dqid_t) xfs_get_projid(ip),
 					(xfs_dqid_t) ip->i_d.di_gid,
 					&ud, &gd);
 	if (XFS_IS_UQUOTA_ON(mp)) {
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 4917d4e..63c7a1a 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -230,6 +230,15 @@
 	rwlock_t	pag_ici_lock;	/* incore inode lock */
 	struct radix_tree_root pag_ici_root;	/* incore inode cache root */
 	int		pag_ici_reclaimable;	/* reclaimable inodes */
+	struct mutex	pag_ici_reclaim_lock;	/* serialisation point */
+	unsigned long	pag_ici_reclaim_cursor;	/* reclaim restart point */
+
+	/* buffer cache index */
+	spinlock_t	pag_buf_lock;	/* lock for pag_buf_tree */
+	struct rb_root	pag_buf_tree;	/* ordered tree of active buffers */
+
+	/* for rcu-safe freeing */
+	struct rcu_head	rcu_head;
 #endif
 	int		pagb_count;	/* pagb slots in use */
 } xfs_perag_t;
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index af168fa..112abc4 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -675,7 +675,7 @@
 	xfs_agblock_t	gtbnoa;		/* aligned ... */
 	xfs_extlen_t	gtdiff;		/* difference to right side entry */
 	xfs_extlen_t	gtlen;		/* length of right side entry */
-	xfs_extlen_t	gtlena;		/* aligned ... */
+	xfs_extlen_t	gtlena = 0;	/* aligned ... */
 	xfs_agblock_t	gtnew;		/* useful start bno of right side */
 	int		error;		/* error code */
 	int		i;		/* result code, temporary */
@@ -684,7 +684,7 @@
 	xfs_agblock_t	ltbnoa;		/* aligned ... */
 	xfs_extlen_t	ltdiff;		/* difference to left side entry */
 	xfs_extlen_t	ltlen;		/* length of left side entry */
-	xfs_extlen_t	ltlena;		/* aligned ... */
+	xfs_extlen_t	ltlena = 0;	/* aligned ... */
 	xfs_agblock_t	ltnew;		/* useful start bno of left side */
 	xfs_extlen_t	rlen;		/* length of returned extent */
 #if defined(DEBUG) && defined(__KERNEL__)
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index 97f7328..3916925 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -280,38 +280,6 @@
 	return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
 }
 
-STATIC int
-xfs_allocbt_kill_root(
-	struct xfs_btree_cur	*cur,
-	struct xfs_buf		*bp,
-	int			level,
-	union xfs_btree_ptr	*newroot)
-{
-	int			error;
-
-	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
-	XFS_BTREE_STATS_INC(cur, killroot);
-
-	/*
-	 * Update the root pointer, decreasing the level by 1 and then
-	 * free the old root.
-	 */
-	xfs_allocbt_set_root(cur, newroot, -1);
-	error = xfs_allocbt_free_block(cur, bp);
-	if (error) {
-		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
-		return error;
-	}
-
-	XFS_BTREE_STATS_INC(cur, free);
-
-	xfs_btree_setbuf(cur, level, NULL);
-	cur->bc_nlevels--;
-
-	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
-	return 0;
-}
-
 #ifdef DEBUG
 STATIC int
 xfs_allocbt_keys_inorder(
@@ -423,7 +391,6 @@
 
 	.dup_cursor		= xfs_allocbt_dup_cursor,
 	.set_root		= xfs_allocbt_set_root,
-	.kill_root		= xfs_allocbt_kill_root,
 	.alloc_block		= xfs_allocbt_alloc_block,
 	.free_block		= xfs_allocbt_free_block,
 	.update_lastrec		= xfs_allocbt_update_lastrec,
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index c256824..c863753 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -355,16 +355,15 @@
 			if (mp->m_flags & XFS_MOUNT_WSYNC) {
 				xfs_trans_set_sync(args.trans);
 			}
+
+			if (!error && (flags & ATTR_KERNOTIME) == 0) {
+				xfs_trans_ichgtime(args.trans, dp,
+							XFS_ICHGTIME_CHG);
+			}
 			err2 = xfs_trans_commit(args.trans,
 						 XFS_TRANS_RELEASE_LOG_RES);
 			xfs_iunlock(dp, XFS_ILOCK_EXCL);
 
-			/*
-			 * Hit the inode change time.
-			 */
-			if (!error && (flags & ATTR_KERNOTIME) == 0) {
-				xfs_ichgtime(dp, XFS_ICHGTIME_CHG);
-			}
 			return(error == 0 ? err2 : error);
 		}
 
@@ -420,6 +419,9 @@
 		xfs_trans_set_sync(args.trans);
 	}
 
+	if ((flags & ATTR_KERNOTIME) == 0)
+		xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
+
 	/*
 	 * Commit the last in the sequence of transactions.
 	 */
@@ -427,13 +429,6 @@
 	error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
 
-	/*
-	 * Hit the inode change time.
-	 */
-	if (!error && (flags & ATTR_KERNOTIME) == 0) {
-		xfs_ichgtime(dp, XFS_ICHGTIME_CHG);
-	}
-
 	return(error);
 
 out:
@@ -567,6 +562,9 @@
 		xfs_trans_set_sync(args.trans);
 	}
 
+	if ((flags & ATTR_KERNOTIME) == 0)
+		xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
+
 	/*
 	 * Commit the last in the sequence of transactions.
 	 */
@@ -574,13 +572,6 @@
 	error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
 
-	/*
-	 * Hit the inode change time.
-	 */
-	if (!error && (flags & ATTR_KERNOTIME) == 0) {
-		xfs_ichgtime(dp, XFS_ICHGTIME_CHG);
-	}
-
 	return(error);
 
 out:
@@ -1995,7 +1986,7 @@
 
 			tmp = (valuelen < XFS_BUF_SIZE(bp))
 				? valuelen : XFS_BUF_SIZE(bp);
-			xfs_biomove(bp, 0, tmp, dst, XBF_READ);
+			xfs_buf_iomove(bp, 0, tmp, dst, XBRW_READ);
 			xfs_buf_relse(bp);
 			dst += tmp;
 			valuelen -= tmp;
@@ -2125,9 +2116,9 @@
 
 		tmp = (valuelen < XFS_BUF_SIZE(bp)) ? valuelen :
 							XFS_BUF_SIZE(bp);
-		xfs_biomove(bp, 0, tmp, src, XBF_WRITE);
+		xfs_buf_iomove(bp, 0, tmp, src, XBRW_WRITE);
 		if (tmp < XFS_BUF_SIZE(bp))
-			xfs_biozero(bp, tmp, XFS_BUF_SIZE(bp) - tmp);
+			xfs_buf_zero(bp, tmp, XFS_BUF_SIZE(bp) - tmp);
 		if ((error = xfs_bwrite(mp, bp))) {/* GROT: NOTE: synchronous write */
 			return (error);
 		}
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index f90dadd..8abd12e 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -614,7 +614,7 @@
 			nblks += cur->bc_private.b.allocated;
 		ASSERT(nblks <= da_old);
 		if (nblks < da_old)
-			xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS,
+			xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS,
 				(int64_t)(da_old - nblks), rsvd);
 	}
 	/*
@@ -1079,7 +1079,8 @@
 		diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
 			(cur ? cur->bc_private.b.allocated : 0));
 		if (diff > 0 &&
-		    xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd)) {
+		    xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS,
+					     -((int64_t)diff), rsvd)) {
 			/*
 			 * Ick gross gag me with a spoon.
 			 */
@@ -1089,16 +1090,18 @@
 					temp--;
 					diff--;
 					if (!diff ||
-					    !xfs_mod_incore_sb(ip->i_mount,
-						    XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd))
+					    !xfs_icsb_modify_counters(ip->i_mount,
+						    XFS_SBS_FDBLOCKS,
+						    -((int64_t)diff), rsvd))
 						break;
 				}
 				if (temp2) {
 					temp2--;
 					diff--;
 					if (!diff ||
-					    !xfs_mod_incore_sb(ip->i_mount,
-						    XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd))
+					    !xfs_icsb_modify_counters(ip->i_mount,
+						    XFS_SBS_FDBLOCKS,
+						    -((int64_t)diff), rsvd))
 						break;
 				}
 			}
@@ -1766,7 +1769,7 @@
 	}
 	if (oldlen != newlen) {
 		ASSERT(oldlen > newlen);
-		xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS,
+		xfs_icsb_modify_counters(ip->i_mount, XFS_SBS_FDBLOCKS,
 			(int64_t)(oldlen - newlen), rsvd);
 		/*
 		 * Nothing to do for disk quota accounting here.
@@ -3111,9 +3114,10 @@
 	 * Nothing to do for disk quota accounting here.
 	 */
 	ASSERT(da_old >= da_new);
-	if (da_old > da_new)
-		xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, (int64_t)(da_old - da_new),
-			rsvd);
+	if (da_old > da_new) {
+		xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS,
+			(int64_t)(da_old - da_new), rsvd);
+	}
 done:
 	*logflagsp = flags;
 	return error;
@@ -4526,13 +4530,13 @@
 							-((int64_t)extsz), (flags &
 							XFS_BMAPI_RSVBLOCKS));
 				} else {
-					error = xfs_mod_incore_sb(mp,
+					error = xfs_icsb_modify_counters(mp,
 							XFS_SBS_FDBLOCKS,
 							-((int64_t)alen), (flags &
 							XFS_BMAPI_RSVBLOCKS));
 				}
 				if (!error) {
-					error = xfs_mod_incore_sb(mp,
+					error = xfs_icsb_modify_counters(mp,
 							XFS_SBS_FDBLOCKS,
 							-((int64_t)indlen), (flags &
 							XFS_BMAPI_RSVBLOCKS));
@@ -4542,7 +4546,7 @@
 							(int64_t)extsz, (flags &
 							XFS_BMAPI_RSVBLOCKS));
 					else if (error)
-						xfs_mod_incore_sb(mp,
+						xfs_icsb_modify_counters(mp,
 							XFS_SBS_FDBLOCKS,
 							(int64_t)alen, (flags &
 							XFS_BMAPI_RSVBLOCKS));
@@ -4744,8 +4748,12 @@
 		 * Check if writing previously allocated but
 		 * unwritten extents.
 		 */
-		if (wr && mval->br_state == XFS_EXT_UNWRITTEN &&
-		    ((flags & (XFS_BMAPI_PREALLOC|XFS_BMAPI_DELAY)) == 0)) {
+		if (wr &&
+		    ((mval->br_state == XFS_EXT_UNWRITTEN &&
+		      ((flags & (XFS_BMAPI_PREALLOC|XFS_BMAPI_DELAY)) == 0)) ||
+		     (mval->br_state == XFS_EXT_NORM &&
+		      ((flags & (XFS_BMAPI_PREALLOC|XFS_BMAPI_CONVERT)) ==
+				(XFS_BMAPI_PREALLOC|XFS_BMAPI_CONVERT))))) {
 			/*
 			 * Modify (by adding) the state flag, if writing.
 			 */
@@ -4757,7 +4765,9 @@
 					*firstblock;
 				cur->bc_private.b.flist = flist;
 			}
-			mval->br_state = XFS_EXT_NORM;
+			mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
+						? XFS_EXT_NORM
+						: XFS_EXT_UNWRITTEN;
 			error = xfs_bmap_add_extent(ip, lastx, &cur, mval,
 				firstblock, flist, &tmp_logflags,
 				whichfork, (flags & XFS_BMAPI_RSVBLOCKS));
@@ -5200,7 +5210,7 @@
 					ip, -((long)del.br_blockcount), 0,
 					XFS_QMOPT_RES_RTBLKS);
 			} else {
-				xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS,
+				xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS,
 						(int64_t)del.br_blockcount, rsvd);
 				(void)xfs_trans_reserve_quota_nblks(NULL,
 					ip, -((long)del.br_blockcount), 0,
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index b13569a..71ec9b6 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -74,9 +74,12 @@
 #define	XFS_BMAPI_IGSTATE	0x080	/* Ignore state - */
 					/* combine contig. space */
 #define	XFS_BMAPI_CONTIG	0x100	/* must allocate only one extent */
-#define XFS_BMAPI_CONVERT	0x200	/* unwritten extent conversion - */
-					/* need write cache flushing and no */
-					/* additional allocation alignments */
+/*
+ * unwritten extent conversion - this needs write cache flushing and no additional
+ * allocation alignments. When specified with XFS_BMAPI_PREALLOC it converts
+ * from written to unwritten, otherwise convert from unwritten to written.
+ */
+#define XFS_BMAPI_CONVERT	0x200
 
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_WRITE,	"WRITE" }, \
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index 829af92..04f9cca 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -217,7 +217,7 @@
 	 */
 	for (i = 0; i < cur->bc_nlevels; i++) {
 		if (cur->bc_bufs[i])
-			xfs_btree_setbuf(cur, i, NULL);
+			xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[i]);
 		else if (!error)
 			break;
 	}
@@ -656,7 +656,7 @@
 
 	ASSERT(fsbno != NULLFSBLOCK);
 	d = XFS_FSB_TO_DADDR(mp, fsbno);
-	xfs_baread(mp->m_ddev_targp, d, mp->m_bsize * count);
+	xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count);
 }
 
 /*
@@ -676,7 +676,7 @@
 	ASSERT(agno != NULLAGNUMBER);
 	ASSERT(agbno != NULLAGBLOCK);
 	d = XFS_AGB_TO_DADDR(mp, agno, agbno);
-	xfs_baread(mp->m_ddev_targp, d, mp->m_bsize * count);
+	xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count);
 }
 
 STATIC int
@@ -763,22 +763,19 @@
  * Set the buffer for level "lev" in the cursor to bp, releasing
  * any previous buffer.
  */
-void
+STATIC void
 xfs_btree_setbuf(
 	xfs_btree_cur_t		*cur,	/* btree cursor */
 	int			lev,	/* level in btree */
 	xfs_buf_t		*bp)	/* new buffer to set */
 {
 	struct xfs_btree_block	*b;	/* btree block */
-	xfs_buf_t		*obp;	/* old buffer pointer */
 
-	obp = cur->bc_bufs[lev];
-	if (obp)
-		xfs_trans_brelse(cur->bc_tp, obp);
+	if (cur->bc_bufs[lev])
+		xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[lev]);
 	cur->bc_bufs[lev] = bp;
 	cur->bc_ra[lev] = 0;
-	if (!bp)
-		return;
+
 	b = XFS_BUF_TO_BLOCK(bp);
 	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		if (be64_to_cpu(b->bb_u.l.bb_leftsib) == NULLDFSBNO)
@@ -3011,6 +3008,43 @@
 	return 0;
 }
 
+/*
+ * Kill the current root node, and replace it with it's only child node.
+ */
+STATIC int
+xfs_btree_kill_root(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	int			level,
+	union xfs_btree_ptr	*newroot)
+{
+	int			error;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_STATS_INC(cur, killroot);
+
+	/*
+	 * Update the root pointer, decreasing the level by 1 and then
+	 * free the old root.
+	 */
+	cur->bc_ops->set_root(cur, newroot, -1);
+
+	error = cur->bc_ops->free_block(cur, bp);
+	if (error) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+		return error;
+	}
+
+	XFS_BTREE_STATS_INC(cur, free);
+
+	cur->bc_bufs[level] = NULL;
+	cur->bc_ra[level] = 0;
+	cur->bc_nlevels--;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	return 0;
+}
+
 STATIC int
 xfs_btree_dec_cursor(
 	struct xfs_btree_cur	*cur,
@@ -3195,7 +3229,7 @@
 			 * Make it the new root of the btree.
 			 */
 			pp = xfs_btree_ptr_addr(cur, 1, block);
-			error = cur->bc_ops->kill_root(cur, bp, level, pp);
+			error = xfs_btree_kill_root(cur, bp, level, pp);
 			if (error)
 				goto error0;
 		} else if (level > 0) {
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index 7fa0706..82fafc6 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -152,9 +152,7 @@
 
 	/* update btree root pointer */
 	void	(*set_root)(struct xfs_btree_cur *cur,
-				union xfs_btree_ptr *nptr, int level_change);
-	int	(*kill_root)(struct xfs_btree_cur *cur, struct xfs_buf *bp,
-				int level, union xfs_btree_ptr *newroot);
+			    union xfs_btree_ptr *nptr, int level_change);
 
 	/* block allocation / freeing */
 	int	(*alloc_block)(struct xfs_btree_cur *cur,
@@ -399,16 +397,6 @@
 	xfs_agblock_t		agbno,	/* allocation group block number */
 	xfs_extlen_t		count);	/* count of filesystem blocks */
 
-/*
- * Set the buffer for level "lev" in the cursor to bp, releasing
- * any previous buffer.
- */
-void
-xfs_btree_setbuf(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			lev,	/* level in btree */
-	struct xfs_buf		*bp);	/* new buffer to set */
-
 
 /*
  * Common btree core entry points.
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 1b09d7a..2686d0d 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -692,8 +692,7 @@
 	 * the first.  If we do already have one, there is
 	 * nothing to do here so return.
 	 */
-	if (bp->b_mount != mp)
-		bp->b_mount = mp;
+	ASSERT(bp->b_target->bt_mount == mp);
 	if (XFS_BUF_FSPRIVATE(bp, void *) != NULL) {
 		lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
 		if (lip->li_type == XFS_LI_BUF) {
@@ -974,7 +973,7 @@
 			xfs_buf_do_callbacks(bp, lip);
 			XFS_BUF_SET_FSPRIVATE(bp, NULL);
 			XFS_BUF_CLR_IODONE_FUNC(bp);
-			xfs_biodone(bp);
+			xfs_buf_ioend(bp, 0);
 			return;
 		}
 
@@ -1033,7 +1032,7 @@
 	xfs_buf_do_callbacks(bp, lip);
 	XFS_BUF_SET_FSPRIVATE(bp, NULL);
 	XFS_BUF_CLR_IODONE_FUNC(bp);
-	xfs_biodone(bp);
+	xfs_buf_ioend(bp, 0);
 }
 
 /*
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 30fa0e2..1c00bed 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -2042,7 +2042,7 @@
 				mappedbno, nmapped, 0, &bp);
 			break;
 		case 3:
-			xfs_baread(mp->m_ddev_targp, mappedbno, nmapped);
+			xfs_buf_readahead(mp->m_ddev_targp, mappedbno, nmapped);
 			error = 0;
 			bp = NULL;
 			break;
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index e5b153b..dffba9b 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -49,8 +49,9 @@
 	__be32		di_uid;		/* owner's user id */
 	__be32		di_gid;		/* owner's group id */
 	__be32		di_nlink;	/* number of links to file */
-	__be16		di_projid;	/* owner's project id */
-	__u8		di_pad[8];	/* unused, zeroed space */
+	__be16		di_projid_lo;	/* lower part of owner's project id */
+	__be16		di_projid_hi;	/* higher part owner's project id */
+	__u8		di_pad[6];	/* unused, zeroed space */
 	__be16		di_flushiter;	/* incremented on flush */
 	xfs_timestamp_t	di_atime;	/* time last accessed */
 	xfs_timestamp_t	di_mtime;	/* time last modified */
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index 504be86..ae89122 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -961,7 +961,7 @@
 				if (i > ra_current &&
 				    map[ra_index].br_blockcount >=
 				    mp->m_dirblkfsbs) {
-					xfs_baread(mp->m_ddev_targp,
+					xfs_buf_readahead(mp->m_ddev_targp,
 						XFS_FSB_TO_DADDR(mp,
 						   map[ra_index].br_startblock +
 						   ra_offset),
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index 87c2e9d..8f6fc1a 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -293,9 +293,11 @@
 	__s32		bs_extsize;	/* extent size			*/
 	__s32		bs_extents;	/* number of extents		*/
 	__u32		bs_gen;		/* generation count		*/
-	__u16		bs_projid;	/* project id			*/
+	__u16		bs_projid_lo;	/* lower part of project id	*/
+#define	bs_projid	bs_projid_lo	/* (previously just bs_projid)	*/
 	__u16		bs_forkoff;	/* inode fork offset in bytes	*/
-	unsigned char	bs_pad[12];	/* pad space, unused		*/
+	__u16		bs_projid_hi;	/* higher part of project id	*/
+	unsigned char	bs_pad[10];	/* pad space, unused		*/
 	__u32		bs_dmevmask;	/* DMIG event mask		*/
 	__u16		bs_dmstate;	/* DMIG state info		*/
 	__u16		bs_aextents;	/* attribute number of extents	*/
@@ -448,6 +450,7 @@
 /*	XFS_IOC_SETBIOSIZE ---- deprecated 46	   */
 /*	XFS_IOC_GETBIOSIZE ---- deprecated 47	   */
 #define XFS_IOC_GETBMAPX	_IOWR('X', 56, struct getbmap)
+#define XFS_IOC_ZERO_RANGE	_IOW ('X', 57, struct xfs_flock64)
 
 /*
  * ioctl commands that replace IRIX syssgi()'s
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 43b1d56..a7c116e 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -144,12 +144,11 @@
 	if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
 		return error;
 	dpct = pct - mp->m_sb.sb_imax_pct;
-	error = xfs_read_buf(mp, mp->m_ddev_targp,
-			XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
-			XFS_FSS_TO_BB(mp, 1), 0, &bp);
-	if (error)
-		return error;
-	ASSERT(bp);
+	bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
+				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
+				BBTOB(XFS_FSS_TO_BB(mp, 1)), 0);
+	if (!bp)
+		return EIO;
 	xfs_buf_relse(bp);
 
 	new = nb;	/* use new as a temporary here */
@@ -597,7 +596,8 @@
 		 * the extra reserve blocks from the reserve.....
 		 */
 		int error;
-		error = xfs_mod_incore_sb(mp, XFS_SBS_FDBLOCKS, fdblks_delta, 0);
+		error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS,
+						 fdblks_delta, 0);
 		if (error == ENOSPC)
 			goto retry;
 	}
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 5371d2d..0626a32 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -212,7 +212,7 @@
 		 *	to log a whole cluster of inodes instead of all the
 		 *	individual transactions causing a lot of log traffic.
 		 */
-		xfs_biozero(fbuf, 0, ninodes << mp->m_sb.sb_inodelog);
+		xfs_buf_zero(fbuf, 0, ninodes << mp->m_sb.sb_inodelog);
 		for (i = 0; i < ninodes; i++) {
 			int	ioffset = i << mp->m_sb.sb_inodelog;
 			uint	isize = sizeof(struct xfs_dinode);
diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c
index d352862..16921f5 100644
--- a/fs/xfs/xfs_ialloc_btree.c
+++ b/fs/xfs/xfs_ialloc_btree.c
@@ -183,38 +183,6 @@
 			  cur->bc_rec.i.ir_startino;
 }
 
-STATIC int
-xfs_inobt_kill_root(
-	struct xfs_btree_cur	*cur,
-	struct xfs_buf		*bp,
-	int			level,
-	union xfs_btree_ptr	*newroot)
-{
-	int			error;
-
-	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
-	XFS_BTREE_STATS_INC(cur, killroot);
-
-	/*
-	 * Update the root pointer, decreasing the level by 1 and then
-	 * free the old root.
-	 */
-	xfs_inobt_set_root(cur, newroot, -1);
-	error = xfs_inobt_free_block(cur, bp);
-	if (error) {
-		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
-		return error;
-	}
-
-	XFS_BTREE_STATS_INC(cur, free);
-
-	cur->bc_bufs[level] = NULL;
-	cur->bc_nlevels--;
-
-	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
-	return 0;
-}
-
 #ifdef DEBUG
 STATIC int
 xfs_inobt_keys_inorder(
@@ -309,7 +277,6 @@
 
 	.dup_cursor		= xfs_inobt_dup_cursor,
 	.set_root		= xfs_inobt_set_root,
-	.kill_root		= xfs_inobt_kill_root,
 	.alloc_block		= xfs_inobt_alloc_block,
 	.free_block		= xfs_inobt_free_block,
 	.get_minrecs		= xfs_inobt_get_minrecs,
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index b1ecc6f..0cdd269 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -365,8 +365,8 @@
 	xfs_perag_t	*pag;
 	xfs_agino_t	agino;
 
-	/* the radix tree exists only in inode capable AGs */
-	if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_maxagi)
+	/* reject inode numbers outside existing AGs */
+	if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
 		return EINVAL;
 
 	/* get the perag structure and ensure that it's inode capable */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 34798f3..108c7a0 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -660,7 +660,8 @@
 	to->di_uid = be32_to_cpu(from->di_uid);
 	to->di_gid = be32_to_cpu(from->di_gid);
 	to->di_nlink = be32_to_cpu(from->di_nlink);
-	to->di_projid = be16_to_cpu(from->di_projid);
+	to->di_projid_lo = be16_to_cpu(from->di_projid_lo);
+	to->di_projid_hi = be16_to_cpu(from->di_projid_hi);
 	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
 	to->di_flushiter = be16_to_cpu(from->di_flushiter);
 	to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
@@ -695,7 +696,8 @@
 	to->di_uid = cpu_to_be32(from->di_uid);
 	to->di_gid = cpu_to_be32(from->di_gid);
 	to->di_nlink = cpu_to_be32(from->di_nlink);
-	to->di_projid = cpu_to_be16(from->di_projid);
+	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
+	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
 	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
 	to->di_flushiter = cpu_to_be16(from->di_flushiter);
 	to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
@@ -874,7 +876,7 @@
 	if (ip->i_d.di_version == 1) {
 		ip->i_d.di_nlink = ip->i_d.di_onlink;
 		ip->i_d.di_onlink = 0;
-		ip->i_d.di_projid = 0;
+		xfs_set_projid(ip, 0);
 	}
 
 	ip->i_delayed_blks = 0;
@@ -982,8 +984,7 @@
 	mode_t		mode,
 	xfs_nlink_t	nlink,
 	xfs_dev_t	rdev,
-	cred_t		*cr,
-	xfs_prid_t	prid,
+	prid_t		prid,
 	int		okalloc,
 	xfs_buf_t	**ialloc_context,
 	boolean_t	*call_again,
@@ -1027,7 +1028,7 @@
 	ASSERT(ip->i_d.di_nlink == nlink);
 	ip->i_d.di_uid = current_fsuid();
 	ip->i_d.di_gid = current_fsgid();
-	ip->i_d.di_projid = prid;
+	xfs_set_projid(ip, prid);
 	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 
 	/*
@@ -2725,7 +2726,7 @@
 			XFS_BUF_UNDONE(bp);
 			XFS_BUF_STALE(bp);
 			XFS_BUF_ERROR(bp,EIO);
-			xfs_biodone(bp);
+			xfs_buf_ioend(bp, 0);
 		} else {
 			XFS_BUF_STALE(bp);
 			xfs_buf_relse(bp);
@@ -3008,7 +3009,7 @@
 			memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 			memset(&(dip->di_pad[0]), 0,
 			      sizeof(dip->di_pad));
-			ASSERT(ip->i_d.di_projid == 0);
+			ASSERT(xfs_get_projid(ip) == 0);
 		}
 	}
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 0898c54..fac5229 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -134,8 +134,9 @@
 	__uint32_t	di_uid;		/* owner's user id */
 	__uint32_t	di_gid;		/* owner's group id */
 	__uint32_t	di_nlink;	/* number of links to file */
-	__uint16_t	di_projid;	/* owner's project id */
-	__uint8_t	di_pad[8];	/* unused, zeroed space */
+	__uint16_t	di_projid_lo;	/* lower part of owner's project id */
+	__uint16_t	di_projid_hi;	/* higher part of owner's project id */
+	__uint8_t	di_pad[6];	/* unused, zeroed space */
 	__uint16_t	di_flushiter;	/* incremented on flush */
 	xfs_ictimestamp_t di_atime;	/* time last accessed */
 	xfs_ictimestamp_t di_mtime;	/* time last modified */
@@ -212,7 +213,6 @@
 #ifdef __KERNEL__
 
 struct bhv_desc;
-struct cred;
 struct xfs_buf;
 struct xfs_bmap_free;
 struct xfs_bmbt_irec;
@@ -335,6 +335,25 @@
 }
 
 /*
+ * Project quota id helpers (previously projid was 16bit only
+ * and using two 16bit values to hold new 32bit projid was choosen
+ * to retain compatibility with "old" filesystems).
+ */
+static inline prid_t
+xfs_get_projid(struct xfs_inode *ip)
+{
+	return (prid_t)ip->i_d.di_projid_hi << 16 | ip->i_d.di_projid_lo;
+}
+
+static inline void
+xfs_set_projid(struct xfs_inode *ip,
+		prid_t projid)
+{
+	ip->i_d.di_projid_hi = (__uint16_t) (projid >> 16);
+	ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff);
+}
+
+/*
  * Manage the i_flush queue embedded in the inode.  This completion
  * queue synchronizes processes attempting to flush the in-core
  * inode back to disk.
@@ -456,8 +475,8 @@
  * xfs_inode.c prototypes.
  */
 int		xfs_ialloc(struct xfs_trans *, xfs_inode_t *, mode_t,
-			   xfs_nlink_t, xfs_dev_t, cred_t *, xfs_prid_t,
-			   int, struct xfs_buf **, boolean_t *, xfs_inode_t **);
+			   xfs_nlink_t, xfs_dev_t, prid_t, int,
+			   struct xfs_buf **, boolean_t *, xfs_inode_t **);
 
 uint		xfs_ip2xflags(struct xfs_inode *);
 uint		xfs_dic2xflags(struct xfs_dinode *);
@@ -471,7 +490,6 @@
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
 void		xfs_iunpin_wait(xfs_inode_t *);
 int		xfs_iflush(xfs_inode_t *, uint);
-void		xfs_ichgtime(xfs_inode_t *, int);
 void		xfs_lock_inodes(xfs_inode_t **, int, uint);
 void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index fe00777..c7ac020 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -223,15 +223,6 @@
 	nvecs	     = 1;
 
 	/*
-	 * Make sure the linux inode is dirty. We do this before
-	 * clearing i_update_core as the VFS will call back into
-	 * XFS here and set i_update_core, so we need to dirty the
-	 * inode first so that the ordering of i_update_core and
-	 * unlogged modifications still works as described below.
-	 */
-	xfs_mark_inode_dirty_sync(ip);
-
-	/*
 	 * Clear i_update_core if the timestamps (or any other
 	 * non-transactional modification) need flushing/logging
 	 * and we're about to log them with the rest of the core.
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 7e3626e..dc1882a 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -92,7 +92,8 @@
 	 * further change.
 	 */
 	buf->bs_nlink = dic->di_nlink;
-	buf->bs_projid = dic->di_projid;
+	buf->bs_projid_lo = dic->di_projid_lo;
+	buf->bs_projid_hi = dic->di_projid_hi;
 	buf->bs_ino = ino;
 	buf->bs_mode = dic->di_mode;
 	buf->bs_uid = dic->di_uid;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 33f718f..cee4ab9 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -917,19 +917,6 @@
 	l = iclog->ic_log;
 
 	/*
-	 * If the _XFS_BARRIER_FAILED flag was set by a lower
-	 * layer, it means the underlying device no longer supports
-	 * barrier I/O. Warn loudly and turn off barriers.
-	 */
-	if (bp->b_flags & _XFS_BARRIER_FAILED) {
-		bp->b_flags &= ~_XFS_BARRIER_FAILED;
-		l->l_mp->m_flags &= ~XFS_MOUNT_BARRIER;
-		xfs_fs_cmn_err(CE_WARN, l->l_mp,
-				"xlog_iodone: Barriers are no longer supported"
-				" by device. Disabling barriers\n");
-	}
-
-	/*
 	 * Race to shutdown the filesystem if we see an error.
 	 */
 	if (XFS_TEST_ERROR((XFS_BUF_GETERROR(bp)), l->l_mp,
@@ -1131,7 +1118,8 @@
 		iclog->ic_prev = prev_iclog;
 		prev_iclog = iclog;
 
-		bp = xfs_buf_get_noaddr(log->l_iclog_size, mp->m_logdev_targp);
+		bp = xfs_buf_get_uncached(mp->m_logdev_targp,
+						log->l_iclog_size, 0);
 		if (!bp)
 			goto out_free_iclog;
 		if (!XFS_BUF_CPSEMA(bp))
@@ -1309,7 +1297,7 @@
 	if (iclog->ic_state & XLOG_STATE_IOERROR) {
 		XFS_BUF_ERROR(bp, EIO);
 		XFS_BUF_STALE(bp);
-		xfs_biodone(bp);
+		xfs_buf_ioend(bp, 0);
 		/*
 		 * It would seem logical to return EIO here, but we rely on
 		 * the log state machine to propagate I/O errors instead of
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 7e206fc..23d6ceb 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -146,102 +146,6 @@
 }
 
 /*
- * Insert the log item into the CIL and calculate the difference in space
- * consumed by the item. Add the space to the checkpoint ticket and calculate
- * if the change requires additional log metadata. If it does, take that space
- * as well. Remove the amount of space we addded to the checkpoint ticket from
- * the current transaction ticket so that the accounting works out correctly.
- *
- * If this is the first time the item is being placed into the CIL in this
- * context, pin it so it can't be written to disk until the CIL is flushed to
- * the iclog and the iclog written to disk.
- */
-static void
-xlog_cil_insert(
-	struct log		*log,
-	struct xlog_ticket	*ticket,
-	struct xfs_log_item	*item,
-	struct xfs_log_vec	*lv)
-{
-	struct xfs_cil		*cil = log->l_cilp;
-	struct xfs_log_vec	*old = lv->lv_item->li_lv;
-	struct xfs_cil_ctx	*ctx = cil->xc_ctx;
-	int			len;
-	int			diff_iovecs;
-	int			iclog_space;
-
-	if (old) {
-		/* existing lv on log item, space used is a delta */
-		ASSERT(!list_empty(&item->li_cil));
-		ASSERT(old->lv_buf && old->lv_buf_len && old->lv_niovecs);
-
-		len = lv->lv_buf_len - old->lv_buf_len;
-		diff_iovecs = lv->lv_niovecs - old->lv_niovecs;
-		kmem_free(old->lv_buf);
-		kmem_free(old);
-	} else {
-		/* new lv, must pin the log item */
-		ASSERT(!lv->lv_item->li_lv);
-		ASSERT(list_empty(&item->li_cil));
-
-		len = lv->lv_buf_len;
-		diff_iovecs = lv->lv_niovecs;
-		IOP_PIN(lv->lv_item);
-
-	}
-	len += diff_iovecs * sizeof(xlog_op_header_t);
-
-	/* attach new log vector to log item */
-	lv->lv_item->li_lv = lv;
-
-	spin_lock(&cil->xc_cil_lock);
-	list_move_tail(&item->li_cil, &cil->xc_cil);
-	ctx->nvecs += diff_iovecs;
-
-	/*
-	 * If this is the first time the item is being committed to the CIL,
-	 * store the sequence number on the log item so we can tell
-	 * in future commits whether this is the first checkpoint the item is
-	 * being committed into.
-	 */
-	if (!item->li_seq)
-		item->li_seq = ctx->sequence;
-
-	/*
-	 * Now transfer enough transaction reservation to the context ticket
-	 * for the checkpoint. The context ticket is special - the unit
-	 * reservation has to grow as well as the current reservation as we
-	 * steal from tickets so we can correctly determine the space used
-	 * during the transaction commit.
-	 */
-	if (ctx->ticket->t_curr_res == 0) {
-		/* first commit in checkpoint, steal the header reservation */
-		ASSERT(ticket->t_curr_res >= ctx->ticket->t_unit_res + len);
-		ctx->ticket->t_curr_res = ctx->ticket->t_unit_res;
-		ticket->t_curr_res -= ctx->ticket->t_unit_res;
-	}
-
-	/* do we need space for more log record headers? */
-	iclog_space = log->l_iclog_size - log->l_iclog_hsize;
-	if (len > 0 && (ctx->space_used / iclog_space !=
-				(ctx->space_used + len) / iclog_space)) {
-		int hdrs;
-
-		hdrs = (len + iclog_space - 1) / iclog_space;
-		/* need to take into account split region headers, too */
-		hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
-		ctx->ticket->t_unit_res += hdrs;
-		ctx->ticket->t_curr_res += hdrs;
-		ticket->t_curr_res -= hdrs;
-		ASSERT(ticket->t_curr_res >= len);
-	}
-	ticket->t_curr_res -= len;
-	ctx->space_used += len;
-
-	spin_unlock(&cil->xc_cil_lock);
-}
-
-/*
  * Format log item into a flat buffers
  *
  * For delayed logging, we need to hold a formatted buffer containing all the
@@ -286,7 +190,7 @@
 			len += lv->lv_iovecp[index].i_len;
 
 		lv->lv_buf_len = len;
-		lv->lv_buf = kmem_zalloc(lv->lv_buf_len, KM_SLEEP|KM_NOFS);
+		lv->lv_buf = kmem_alloc(lv->lv_buf_len, KM_SLEEP|KM_NOFS);
 		ptr = lv->lv_buf;
 
 		for (index = 0; index < lv->lv_niovecs; index++) {
@@ -300,21 +204,136 @@
 	}
 }
 
+/*
+ * Prepare the log item for insertion into the CIL. Calculate the difference in
+ * log space and vectors it will consume, and if it is a new item pin it as
+ * well.
+ */
+STATIC void
+xfs_cil_prepare_item(
+	struct log		*log,
+	struct xfs_log_vec	*lv,
+	int			*len,
+	int			*diff_iovecs)
+{
+	struct xfs_log_vec	*old = lv->lv_item->li_lv;
+
+	if (old) {
+		/* existing lv on log item, space used is a delta */
+		ASSERT(!list_empty(&lv->lv_item->li_cil));
+		ASSERT(old->lv_buf && old->lv_buf_len && old->lv_niovecs);
+
+		*len += lv->lv_buf_len - old->lv_buf_len;
+		*diff_iovecs += lv->lv_niovecs - old->lv_niovecs;
+		kmem_free(old->lv_buf);
+		kmem_free(old);
+	} else {
+		/* new lv, must pin the log item */
+		ASSERT(!lv->lv_item->li_lv);
+		ASSERT(list_empty(&lv->lv_item->li_cil));
+
+		*len += lv->lv_buf_len;
+		*diff_iovecs += lv->lv_niovecs;
+		IOP_PIN(lv->lv_item);
+
+	}
+
+	/* attach new log vector to log item */
+	lv->lv_item->li_lv = lv;
+
+	/*
+	 * If this is the first time the item is being committed to the
+	 * CIL, store the sequence number on the log item so we can
+	 * tell in future commits whether this is the first checkpoint
+	 * the item is being committed into.
+	 */
+	if (!lv->lv_item->li_seq)
+		lv->lv_item->li_seq = log->l_cilp->xc_ctx->sequence;
+}
+
+/*
+ * Insert the log items into the CIL and calculate the difference in space
+ * consumed by the item. Add the space to the checkpoint ticket and calculate
+ * if the change requires additional log metadata. If it does, take that space
+ * as well. Remove the amount of space we addded to the checkpoint ticket from
+ * the current transaction ticket so that the accounting works out correctly.
+ */
 static void
 xlog_cil_insert_items(
 	struct log		*log,
 	struct xfs_log_vec	*log_vector,
-	struct xlog_ticket	*ticket,
-	xfs_lsn_t		*start_lsn)
+	struct xlog_ticket	*ticket)
 {
-	struct xfs_log_vec *lv;
-
-	if (start_lsn)
-		*start_lsn = log->l_cilp->xc_ctx->sequence;
+	struct xfs_cil		*cil = log->l_cilp;
+	struct xfs_cil_ctx	*ctx = cil->xc_ctx;
+	struct xfs_log_vec	*lv;
+	int			len = 0;
+	int			diff_iovecs = 0;
+	int			iclog_space;
 
 	ASSERT(log_vector);
+
+	/*
+	 * Do all the accounting aggregation and switching of log vectors
+	 * around in a separate loop to the insertion of items into the CIL.
+	 * Then we can do a separate loop to update the CIL within a single
+	 * lock/unlock pair. This reduces the number of round trips on the CIL
+	 * lock from O(nr_logvectors) to O(1) and greatly reduces the overall
+	 * hold time for the transaction commit.
+	 *
+	 * If this is the first time the item is being placed into the CIL in
+	 * this context, pin it so it can't be written to disk until the CIL is
+	 * flushed to the iclog and the iclog written to disk.
+	 *
+	 * We can do this safely because the context can't checkpoint until we
+	 * are done so it doesn't matter exactly how we update the CIL.
+	 */
 	for (lv = log_vector; lv; lv = lv->lv_next)
-		xlog_cil_insert(log, ticket, lv->lv_item, lv);
+		xfs_cil_prepare_item(log, lv, &len, &diff_iovecs);
+
+	/* account for space used by new iovec headers  */
+	len += diff_iovecs * sizeof(xlog_op_header_t);
+
+	spin_lock(&cil->xc_cil_lock);
+
+	/* move the items to the tail of the CIL */
+	for (lv = log_vector; lv; lv = lv->lv_next)
+		list_move_tail(&lv->lv_item->li_cil, &cil->xc_cil);
+
+	ctx->nvecs += diff_iovecs;
+
+	/*
+	 * Now transfer enough transaction reservation to the context ticket
+	 * for the checkpoint. The context ticket is special - the unit
+	 * reservation has to grow as well as the current reservation as we
+	 * steal from tickets so we can correctly determine the space used
+	 * during the transaction commit.
+	 */
+	if (ctx->ticket->t_curr_res == 0) {
+		/* first commit in checkpoint, steal the header reservation */
+		ASSERT(ticket->t_curr_res >= ctx->ticket->t_unit_res + len);
+		ctx->ticket->t_curr_res = ctx->ticket->t_unit_res;
+		ticket->t_curr_res -= ctx->ticket->t_unit_res;
+	}
+
+	/* do we need space for more log record headers? */
+	iclog_space = log->l_iclog_size - log->l_iclog_hsize;
+	if (len > 0 && (ctx->space_used / iclog_space !=
+				(ctx->space_used + len) / iclog_space)) {
+		int hdrs;
+
+		hdrs = (len + iclog_space - 1) / iclog_space;
+		/* need to take into account split region headers, too */
+		hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
+		ctx->ticket->t_unit_res += hdrs;
+		ctx->ticket->t_curr_res += hdrs;
+		ticket->t_curr_res -= hdrs;
+		ASSERT(ticket->t_curr_res >= len);
+	}
+	ticket->t_curr_res -= len;
+	ctx->space_used += len;
+
+	spin_unlock(&cil->xc_cil_lock);
 }
 
 static void
@@ -638,7 +657,10 @@
 
 	/* lock out background commit */
 	down_read(&log->l_cilp->xc_ctx_lock);
-	xlog_cil_insert_items(log, log_vector, tp->t_ticket, commit_lsn);
+	if (commit_lsn)
+		*commit_lsn = log->l_cilp->xc_ctx->sequence;
+
+	xlog_cil_insert_items(log, log_vector, tp->t_ticket);
 
 	/* check we didn't blow the reservation */
 	if (tp->t_ticket->t_curr_res < 0)
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 6f3f5fa..966d3f9 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -107,7 +107,8 @@
 		nbblks += log->l_sectBBsize;
 	nbblks = round_up(nbblks, log->l_sectBBsize);
 
-	return xfs_buf_get_noaddr(BBTOB(nbblks), log->l_mp->m_logdev_targp);
+	return xfs_buf_get_uncached(log->l_mp->m_logdev_targp,
+					BBTOB(nbblks), 0);
 }
 
 STATIC void
@@ -167,7 +168,7 @@
 	XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp);
 
 	xfsbdstrat(log->l_mp, bp);
-	error = xfs_iowait(bp);
+	error = xfs_buf_iowait(bp);
 	if (error)
 		xfs_ioerror_alert("xlog_bread", log->l_mp,
 				  bp, XFS_BUF_ADDR(bp));
@@ -321,12 +322,13 @@
 		 * this during recovery. One strike!
 		 */
 		xfs_ioerror_alert("xlog_recover_iodone",
-				  bp->b_mount, bp, XFS_BUF_ADDR(bp));
-		xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR);
+					bp->b_target->bt_mount, bp,
+					XFS_BUF_ADDR(bp));
+		xfs_force_shutdown(bp->b_target->bt_mount,
+					SHUTDOWN_META_IO_ERROR);
 	}
-	bp->b_mount = NULL;
 	XFS_BUF_CLR_IODONE_FUNC(bp);
-	xfs_biodone(bp);
+	xfs_buf_ioend(bp, 0);
 }
 
 /*
@@ -2275,8 +2277,7 @@
 		XFS_BUF_STALE(bp);
 		error = xfs_bwrite(mp, bp);
 	} else {
-		ASSERT(bp->b_mount == NULL || bp->b_mount == mp);
-		bp->b_mount = mp;
+		ASSERT(bp->b_target->bt_mount == mp);
 		XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
 		xfs_bdwrite(mp, bp);
 	}
@@ -2540,8 +2541,7 @@
 	}
 
 write_inode_buffer:
-	ASSERT(bp->b_mount == NULL || bp->b_mount == mp);
-	bp->b_mount = mp;
+	ASSERT(bp->b_target->bt_mount == mp);
 	XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
 	xfs_bdwrite(mp, bp);
 error:
@@ -2678,8 +2678,7 @@
 	memcpy(ddq, recddq, item->ri_buf[1].i_len);
 
 	ASSERT(dq_f->qlf_size == 2);
-	ASSERT(bp->b_mount == NULL || bp->b_mount == mp);
-	bp->b_mount = mp;
+	ASSERT(bp->b_target->bt_mount == mp);
 	XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
 	xfs_bdwrite(mp, bp);
 
@@ -3817,7 +3816,7 @@
 	XFS_BUF_READ(bp);
 	XFS_BUF_UNASYNC(bp);
 	xfsbdstrat(log->l_mp, bp);
-	error = xfs_iowait(bp);
+	error = xfs_buf_iowait(bp);
 	if (error) {
 		xfs_ioerror_alert("xlog_do_recover",
 				  log->l_mp, bp, XFS_BUF_ADDR(bp));
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index aeb9d72..b1498ab 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -52,16 +52,11 @@
 						int);
 STATIC void	xfs_icsb_balance_counter_locked(xfs_mount_t *, xfs_sb_field_t,
 						int);
-STATIC int	xfs_icsb_modify_counters(xfs_mount_t *, xfs_sb_field_t,
-						int64_t, int);
 STATIC void	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
-
 #else
 
 #define xfs_icsb_balance_counter(mp, a, b)		do { } while (0)
 #define xfs_icsb_balance_counter_locked(mp, a, b)	do { } while (0)
-#define xfs_icsb_modify_counters(mp, a, b, c)		do { } while (0)
-
 #endif
 
 static const struct {
@@ -199,6 +194,8 @@
 
 /*
  * Reference counting access wrappers to the perag structures.
+ * Because we never free per-ag structures, the only thing we
+ * have to protect against changes is the tree structure itself.
  */
 struct xfs_perag *
 xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno)
@@ -206,19 +203,43 @@
 	struct xfs_perag	*pag;
 	int			ref = 0;
 
-	spin_lock(&mp->m_perag_lock);
+	rcu_read_lock();
 	pag = radix_tree_lookup(&mp->m_perag_tree, agno);
 	if (pag) {
 		ASSERT(atomic_read(&pag->pag_ref) >= 0);
-		/* catch leaks in the positive direction during testing */
-		ASSERT(atomic_read(&pag->pag_ref) < 1000);
 		ref = atomic_inc_return(&pag->pag_ref);
 	}
-	spin_unlock(&mp->m_perag_lock);
+	rcu_read_unlock();
 	trace_xfs_perag_get(mp, agno, ref, _RET_IP_);
 	return pag;
 }
 
+/*
+ * search from @first to find the next perag with the given tag set.
+ */
+struct xfs_perag *
+xfs_perag_get_tag(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		first,
+	int			tag)
+{
+	struct xfs_perag	*pag;
+	int			found;
+	int			ref;
+
+	rcu_read_lock();
+	found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
+					(void **)&pag, first, 1, tag);
+	if (found <= 0) {
+		rcu_read_unlock();
+		return NULL;
+	}
+	ref = atomic_inc_return(&pag->pag_ref);
+	rcu_read_unlock();
+	trace_xfs_perag_get_tag(mp, pag->pag_agno, ref, _RET_IP_);
+	return pag;
+}
+
 void
 xfs_perag_put(struct xfs_perag *pag)
 {
@@ -229,10 +250,18 @@
 	trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
 }
 
+STATIC void
+__xfs_free_perag(
+	struct rcu_head	*head)
+{
+	struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
+
+	ASSERT(atomic_read(&pag->pag_ref) == 0);
+	kmem_free(pag);
+}
+
 /*
- * Free up the resources associated with a mount structure.  Assume that
- * the structure was initially zeroed, so we can tell which fields got
- * initialized.
+ * Free up the per-ag resources associated with the mount structure.
  */
 STATIC void
 xfs_free_perag(
@@ -244,10 +273,9 @@
 	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
 		spin_lock(&mp->m_perag_lock);
 		pag = radix_tree_delete(&mp->m_perag_tree, agno);
-		ASSERT(pag);
-		ASSERT(atomic_read(&pag->pag_ref) == 0);
 		spin_unlock(&mp->m_perag_lock);
-		kmem_free(pag);
+		ASSERT(pag);
+		call_rcu(&pag->rcu_head, __xfs_free_perag);
 	}
 }
 
@@ -444,7 +472,10 @@
 		pag->pag_agno = index;
 		pag->pag_mount = mp;
 		rwlock_init(&pag->pag_ici_lock);
+		mutex_init(&pag->pag_ici_reclaim_lock);
 		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
+		spin_lock_init(&pag->pag_buf_lock);
+		pag->pag_buf_tree = RB_ROOT;
 
 		if (radix_tree_preload(GFP_NOFS))
 			goto out_unwind;
@@ -639,7 +670,6 @@
 xfs_readsb(xfs_mount_t *mp, int flags)
 {
 	unsigned int	sector_size;
-	unsigned int	extra_flags;
 	xfs_buf_t	*bp;
 	int		error;
 
@@ -652,28 +682,24 @@
 	 * access to the superblock.
 	 */
 	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-	extra_flags = XBF_LOCK | XBF_FS_MANAGED | XBF_MAPPED;
 
-	bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size),
-			  extra_flags);
-	if (!bp || XFS_BUF_ISERROR(bp)) {
-		xfs_fs_mount_cmn_err(flags, "SB read failed");
-		error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
-		goto fail;
+reread:
+	bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
+					XFS_SB_DADDR, sector_size, 0);
+	if (!bp) {
+		xfs_fs_mount_cmn_err(flags, "SB buffer read failed");
+		return EIO;
 	}
-	ASSERT(XFS_BUF_ISBUSY(bp));
-	ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
 
 	/*
 	 * Initialize the mount structure from the superblock.
 	 * But first do some basic consistency checking.
 	 */
 	xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp));
-
 	error = xfs_mount_validate_sb(mp, &(mp->m_sb), flags);
 	if (error) {
 		xfs_fs_mount_cmn_err(flags, "SB validate failed");
-		goto fail;
+		goto release_buf;
 	}
 
 	/*
@@ -684,7 +710,7 @@
 			"device supports only %u byte sectors (not %u)",
 			sector_size, mp->m_sb.sb_sectsize);
 		error = ENOSYS;
-		goto fail;
+		goto release_buf;
 	}
 
 	/*
@@ -692,33 +718,20 @@
 	 * re-read the superblock so the buffer is correctly sized.
 	 */
 	if (sector_size < mp->m_sb.sb_sectsize) {
-		XFS_BUF_UNMANAGE(bp);
 		xfs_buf_relse(bp);
 		sector_size = mp->m_sb.sb_sectsize;
-		bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR,
-				  BTOBB(sector_size), extra_flags);
-		if (!bp || XFS_BUF_ISERROR(bp)) {
-			xfs_fs_mount_cmn_err(flags, "SB re-read failed");
-			error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
-			goto fail;
-		}
-		ASSERT(XFS_BUF_ISBUSY(bp));
-		ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
+		goto reread;
 	}
 
 	/* Initialize per-cpu counters */
 	xfs_icsb_reinit_counters(mp);
 
 	mp->m_sb_bp = bp;
-	xfs_buf_relse(bp);
-	ASSERT(XFS_BUF_VALUSEMA(bp) > 0);
+	xfs_buf_unlock(bp);
 	return 0;
 
- fail:
-	if (bp) {
-		XFS_BUF_UNMANAGE(bp);
-		xfs_buf_relse(bp);
-	}
+release_buf:
+	xfs_buf_relse(bp);
 	return error;
 }
 
@@ -991,42 +1004,35 @@
 {
 	xfs_buf_t	*bp;
 	xfs_daddr_t	d;
-	int		error;
 
 	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
 	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
-		cmn_err(CE_WARN, "XFS: size check 1 failed");
+		cmn_err(CE_WARN, "XFS: filesystem size mismatch detected");
 		return XFS_ERROR(EFBIG);
 	}
-	error = xfs_read_buf(mp, mp->m_ddev_targp,
-			     d - XFS_FSS_TO_BB(mp, 1),
-			     XFS_FSS_TO_BB(mp, 1), 0, &bp);
-	if (!error) {
-		xfs_buf_relse(bp);
-	} else {
-		cmn_err(CE_WARN, "XFS: size check 2 failed");
-		if (error == ENOSPC)
-			error = XFS_ERROR(EFBIG);
-		return error;
+	bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
+					d - XFS_FSS_TO_BB(mp, 1),
+					BBTOB(XFS_FSS_TO_BB(mp, 1)), 0);
+	if (!bp) {
+		cmn_err(CE_WARN, "XFS: last sector read failed");
+		return EIO;
 	}
+	xfs_buf_relse(bp);
 
 	if (mp->m_logdev_targp != mp->m_ddev_targp) {
 		d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
 		if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
-			cmn_err(CE_WARN, "XFS: size check 3 failed");
+			cmn_err(CE_WARN, "XFS: log size mismatch detected");
 			return XFS_ERROR(EFBIG);
 		}
-		error = xfs_read_buf(mp, mp->m_logdev_targp,
-				     d - XFS_FSB_TO_BB(mp, 1),
-				     XFS_FSB_TO_BB(mp, 1), 0, &bp);
-		if (!error) {
-			xfs_buf_relse(bp);
-		} else {
-			cmn_err(CE_WARN, "XFS: size check 3 failed");
-			if (error == ENOSPC)
-				error = XFS_ERROR(EFBIG);
-			return error;
+		bp = xfs_buf_read_uncached(mp, mp->m_logdev_targp,
+					d - XFS_FSB_TO_BB(mp, 1),
+					XFS_FSB_TO_B(mp, 1), 0);
+		if (!bp) {
+			cmn_err(CE_WARN, "XFS: log device read failed");
+			return EIO;
 		}
+		xfs_buf_relse(bp);
 	}
 	return 0;
 }
@@ -1601,7 +1607,7 @@
 		XFS_BUF_UNASYNC(sbp);
 		ASSERT(XFS_BUF_TARGET(sbp) == mp->m_ddev_targp);
 		xfsbdstrat(mp, sbp);
-		error = xfs_iowait(sbp);
+		error = xfs_buf_iowait(sbp);
 		if (error)
 			xfs_ioerror_alert("xfs_unmountfs_writesb",
 					  mp, sbp, XFS_BUF_ADDR(sbp));
@@ -1832,135 +1838,72 @@
  */
 int
 xfs_mod_incore_sb(
-	xfs_mount_t	*mp,
-	xfs_sb_field_t	field,
-	int64_t		delta,
-	int		rsvd)
+	struct xfs_mount	*mp,
+	xfs_sb_field_t		field,
+	int64_t			delta,
+	int			rsvd)
 {
-	int	status;
+	int			status;
 
-	/* check for per-cpu counters */
-	switch (field) {
 #ifdef HAVE_PERCPU_SB
-	case XFS_SBS_ICOUNT:
-	case XFS_SBS_IFREE:
-	case XFS_SBS_FDBLOCKS:
-		if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) {
-			status = xfs_icsb_modify_counters(mp, field,
-							delta, rsvd);
-			break;
-		}
-		/* FALLTHROUGH */
+	ASSERT(field < XFS_SBS_ICOUNT || field > XFS_SBS_FDBLOCKS);
 #endif
-	default:
-		spin_lock(&mp->m_sb_lock);
-		status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
-		spin_unlock(&mp->m_sb_lock);
-		break;
-	}
+	spin_lock(&mp->m_sb_lock);
+	status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
+	spin_unlock(&mp->m_sb_lock);
 
 	return status;
 }
 
 /*
- * xfs_mod_incore_sb_batch() is used to change more than one field
- * in the in-core superblock structure at a time.  This modification
- * is protected by a lock internal to this module.  The fields and
- * changes to those fields are specified in the array of xfs_mod_sb
- * structures passed in.
+ * Change more than one field in the in-core superblock structure at a time.
  *
- * Either all of the specified deltas will be applied or none of
- * them will.  If any modified field dips below 0, then all modifications
- * will be backed out and EINVAL will be returned.
+ * The fields and changes to those fields are specified in the array of
+ * xfs_mod_sb structures passed in.  Either all of the specified deltas
+ * will be applied or none of them will.  If any modified field dips below 0,
+ * then all modifications will be backed out and EINVAL will be returned.
+ *
+ * Note that this function may not be used for the superblock values that
+ * are tracked with the in-memory per-cpu counters - a direct call to
+ * xfs_icsb_modify_counters is required for these.
  */
 int
-xfs_mod_incore_sb_batch(xfs_mount_t *mp, xfs_mod_sb_t *msb, uint nmsb, int rsvd)
+xfs_mod_incore_sb_batch(
+	struct xfs_mount	*mp,
+	xfs_mod_sb_t		*msb,
+	uint			nmsb,
+	int			rsvd)
 {
-	int		status=0;
-	xfs_mod_sb_t	*msbp;
+	xfs_mod_sb_t		*msbp = &msb[0];
+	int			error = 0;
 
 	/*
-	 * Loop through the array of mod structures and apply each
-	 * individually.  If any fail, then back out all those
-	 * which have already been applied.  Do all of this within
-	 * the scope of the m_sb_lock so that all of the changes will
-	 * be atomic.
+	 * Loop through the array of mod structures and apply each individually.
+	 * If any fail, then back out all those which have already been applied.
+	 * Do all of this within the scope of the m_sb_lock so that all of the
+	 * changes will be atomic.
 	 */
 	spin_lock(&mp->m_sb_lock);
-	msbp = &msb[0];
 	for (msbp = &msbp[0]; msbp < (msb + nmsb); msbp++) {
-		/*
-		 * Apply the delta at index n.  If it fails, break
-		 * from the loop so we'll fall into the undo loop
-		 * below.
-		 */
-		switch (msbp->msb_field) {
-#ifdef HAVE_PERCPU_SB
-		case XFS_SBS_ICOUNT:
-		case XFS_SBS_IFREE:
-		case XFS_SBS_FDBLOCKS:
-			if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) {
-				spin_unlock(&mp->m_sb_lock);
-				status = xfs_icsb_modify_counters(mp,
-							msbp->msb_field,
-							msbp->msb_delta, rsvd);
-				spin_lock(&mp->m_sb_lock);
-				break;
-			}
-			/* FALLTHROUGH */
-#endif
-		default:
-			status = xfs_mod_incore_sb_unlocked(mp,
-						msbp->msb_field,
-						msbp->msb_delta, rsvd);
-			break;
-		}
+		ASSERT(msbp->msb_field < XFS_SBS_ICOUNT ||
+		       msbp->msb_field > XFS_SBS_FDBLOCKS);
 
-		if (status != 0) {
-			break;
-		}
-	}
-
-	/*
-	 * If we didn't complete the loop above, then back out
-	 * any changes made to the superblock.  If you add code
-	 * between the loop above and here, make sure that you
-	 * preserve the value of status. Loop back until
-	 * we step below the beginning of the array.  Make sure
-	 * we don't touch anything back there.
-	 */
-	if (status != 0) {
-		msbp--;
-		while (msbp >= msb) {
-			switch (msbp->msb_field) {
-#ifdef HAVE_PERCPU_SB
-			case XFS_SBS_ICOUNT:
-			case XFS_SBS_IFREE:
-			case XFS_SBS_FDBLOCKS:
-				if (!(mp->m_flags & XFS_MOUNT_NO_PERCPU_SB)) {
-					spin_unlock(&mp->m_sb_lock);
-					status = xfs_icsb_modify_counters(mp,
-							msbp->msb_field,
-							-(msbp->msb_delta),
-							rsvd);
-					spin_lock(&mp->m_sb_lock);
-					break;
-				}
-				/* FALLTHROUGH */
-#endif
-			default:
-				status = xfs_mod_incore_sb_unlocked(mp,
-							msbp->msb_field,
-							-(msbp->msb_delta),
-							rsvd);
-				break;
-			}
-			ASSERT(status == 0);
-			msbp--;
-		}
+		error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field,
+						   msbp->msb_delta, rsvd);
+		if (error)
+			goto unwind;
 	}
 	spin_unlock(&mp->m_sb_lock);
-	return status;
+	return 0;
+
+unwind:
+	while (--msbp >= msb) {
+		error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field,
+						   -msbp->msb_delta, rsvd);
+		ASSERT(error == 0);
+	}
+	spin_unlock(&mp->m_sb_lock);
+	return error;
 }
 
 /*
@@ -1998,18 +1941,13 @@
  */
 void
 xfs_freesb(
-	xfs_mount_t	*mp)
+	struct xfs_mount	*mp)
 {
-	xfs_buf_t	*bp;
+	struct xfs_buf		*bp = mp->m_sb_bp;
 
-	/*
-	 * Use xfs_getsb() so that the buffer will be locked
-	 * when we call xfs_buf_relse().
-	 */
-	bp = xfs_getsb(mp, 0);
-	XFS_BUF_UNMANAGE(bp);
-	xfs_buf_relse(bp);
+	xfs_buf_lock(bp);
 	mp->m_sb_bp = NULL;
+	xfs_buf_relse(bp);
 }
 
 /*
@@ -2496,7 +2434,7 @@
 	spin_unlock(&mp->m_sb_lock);
 }
 
-STATIC int
+int
 xfs_icsb_modify_counters(
 	xfs_mount_t	*mp,
 	xfs_sb_field_t	field,
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 622da21..5861b49 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -53,7 +53,6 @@
 
 #include "xfs_sync.h"
 
-struct cred;
 struct log;
 struct xfs_mount_args;
 struct xfs_inode;
@@ -91,6 +90,8 @@
 extern void	xfs_icsb_destroy_counters(struct xfs_mount *);
 extern void	xfs_icsb_sync_counters(struct xfs_mount *, int);
 extern void	xfs_icsb_sync_counters_locked(struct xfs_mount *, int);
+extern int	xfs_icsb_modify_counters(struct xfs_mount *, xfs_sb_field_t,
+						int64_t, int);
 
 #else
 #define xfs_icsb_init_counters(mp)		(0)
@@ -98,6 +99,8 @@
 #define xfs_icsb_reinit_counters(mp)		do { } while (0)
 #define xfs_icsb_sync_counters(mp, flags)	do { } while (0)
 #define xfs_icsb_sync_counters_locked(mp, flags) do { } while (0)
+#define xfs_icsb_modify_counters(mp, field, delta, rsvd) \
+	xfs_mod_incore_sb(mp, field, delta, rsvd)
 #endif
 
 typedef struct xfs_mount {
@@ -232,8 +235,6 @@
 #define XFS_MOUNT_DIRSYNC	(1ULL << 21)	/* synchronous directory ops */
 #define XFS_MOUNT_COMPAT_IOSIZE	(1ULL << 22)	/* don't report large preferred
 						 * I/O size in stat() */
-#define XFS_MOUNT_NO_PERCPU_SB	(1ULL << 23)	/* don't use per-cpu superblock
-						   counters */
 #define XFS_MOUNT_FILESTREAMS	(1ULL << 24)	/* enable the filestreams
 						   allocator */
 #define XFS_MOUNT_NOATTR2	(1ULL << 25)	/* disable use of attr2 format */
@@ -327,6 +328,8 @@
  * perag get/put wrappers for ref counting
  */
 struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno);
+struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno,
+					int tag);
 void	xfs_perag_put(struct xfs_perag *pag);
 
 /*
diff --git a/fs/xfs/xfs_refcache.h b/fs/xfs/xfs_refcache.h
deleted file mode 100644
index 2dec79e..0000000
--- a/fs/xfs/xfs_refcache.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_REFCACHE_H__
-#define __XFS_REFCACHE_H__
-
-#ifdef HAVE_REFCACHE
-/*
- * Maximum size (in inodes) for the NFS reference cache
- */
-#define XFS_REFCACHE_SIZE_MAX	512
-
-struct xfs_inode;
-struct xfs_mount;
-
-extern void xfs_refcache_insert(struct xfs_inode *);
-extern void xfs_refcache_purge_ip(struct xfs_inode *);
-extern void xfs_refcache_purge_mp(struct xfs_mount *);
-extern void xfs_refcache_purge_some(struct xfs_mount *);
-extern void xfs_refcache_resize(int);
-extern void xfs_refcache_destroy(void);
-
-extern void xfs_refcache_iunlock(struct xfs_inode *, uint);
-
-#else
-
-#define xfs_refcache_insert(ip)		do { } while (0)
-#define xfs_refcache_purge_ip(ip)	do { } while (0)
-#define xfs_refcache_purge_mp(mp)	do { } while (0)
-#define xfs_refcache_purge_some(mp)	do { } while (0)
-#define xfs_refcache_resize(size)	do { } while (0)
-#define xfs_refcache_destroy()		do { } while (0)
-
-#define xfs_refcache_iunlock(ip, flags)	xfs_iunlock(ip, flags)
-
-#endif
-
-#endif	/* __XFS_REFCACHE_H__ */
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index 8fca957..d2af0a8 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -183,7 +183,7 @@
 	 * tree quota mechanism would be circumvented.
 	 */
 	if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
-		     (target_dp->i_d.di_projid != src_ip->i_d.di_projid))) {
+		     (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) {
 		error = XFS_ERROR(EXDEV);
 		goto error_return;
 	}
@@ -211,7 +211,9 @@
 			goto error_return;
 		if (error)
 			goto abort_return;
-		xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+		xfs_trans_ichgtime(tp, target_dp,
+					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
 		if (new_parent && src_is_directory) {
 			error = xfs_bumplink(tp, target_dp);
@@ -249,7 +251,9 @@
 					&first_block, &free_list, spaceres);
 		if (error)
 			goto abort_return;
-		xfs_ichgtime(target_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+		xfs_trans_ichgtime(tp, target_dp,
+					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
 		/*
 		 * Decrement the link count on the target since the target
@@ -292,7 +296,7 @@
 	 * inode isn't really being changed, but old unix file systems did
 	 * it and some incremental backup programs won't work without it.
 	 */
-	xfs_ichgtime(src_ip, XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG);
 
 	/*
 	 * Adjust the link count on src_dp.  This is necessary when
@@ -315,7 +319,7 @@
 	if (error)
 		goto abort_return;
 
-	xfs_ichgtime(src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
 	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 891260f..12a1913 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -39,6 +39,7 @@
 #include "xfs_trans_space.h"
 #include "xfs_utils.h"
 #include "xfs_trace.h"
+#include "xfs_buf.h"
 
 
 /*
@@ -1883,13 +1884,13 @@
 	/*
 	 * Read in the last block of the device, make sure it exists.
 	 */
-	error = xfs_read_buf(mp, mp->m_rtdev_targp,
-			XFS_FSB_TO_BB(mp, nrblocks - 1),
-			XFS_FSB_TO_BB(mp, 1), 0, &bp);
-	if (error)
-		return error;
-	ASSERT(bp);
+	bp = xfs_buf_read_uncached(mp, mp->m_rtdev_targp,
+				XFS_FSB_TO_BB(mp, nrblocks - 1),
+				XFS_FSB_TO_B(mp, 1), 0);
+	if (!bp)
+		return EIO;
 	xfs_buf_relse(bp);
+
 	/*
 	 * Calculate new parameters.  These are the final values to be reached.
 	 */
@@ -2215,7 +2216,6 @@
 {
 	xfs_buf_t	*bp;	/* buffer for last block of subvolume */
 	xfs_daddr_t	d;	/* address of last block of subvolume */
-	int		error;	/* error return value */
 	xfs_sb_t	*sbp;	/* filesystem superblock copy in mount */
 
 	sbp = &mp->m_sb;
@@ -2242,15 +2242,12 @@
 			(unsigned long long) mp->m_sb.sb_rblocks);
 		return XFS_ERROR(EFBIG);
 	}
-	error = xfs_read_buf(mp, mp->m_rtdev_targp,
-				d - XFS_FSB_TO_BB(mp, 1),
-				XFS_FSB_TO_BB(mp, 1), 0, &bp);
-	if (error) {
-		cmn_err(CE_WARN,
-	"XFS: realtime mount -- xfs_read_buf failed, returned %d", error);
-		if (error == ENOSPC)
-			return XFS_ERROR(EFBIG);
-		return error;
+	bp = xfs_buf_read_uncached(mp, mp->m_rtdev_targp,
+					d - XFS_FSB_TO_BB(mp, 1),
+					XFS_FSB_TO_B(mp, 1), 0);
+	if (!bp) {
+		cmn_err(CE_WARN, "XFS: realtime device size check failed");
+		return EIO;
 	}
 	xfs_buf_relse(bp);
 	return 0;
diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h
index 1b017c6..1eb2ba5 100644
--- a/fs/xfs/xfs_sb.h
+++ b/fs/xfs/xfs_sb.h
@@ -80,10 +80,12 @@
 #define XFS_SB_VERSION2_RESERVED4BIT	0x00000004
 #define XFS_SB_VERSION2_ATTR2BIT	0x00000008	/* Inline attr rework */
 #define XFS_SB_VERSION2_PARENTBIT	0x00000010	/* parent pointers */
+#define XFS_SB_VERSION2_PROJID32BIT	0x00000080	/* 32 bit project id */
 
 #define	XFS_SB_VERSION2_OKREALFBITS	\
 	(XFS_SB_VERSION2_LAZYSBCOUNTBIT	| \
-	 XFS_SB_VERSION2_ATTR2BIT)
+	 XFS_SB_VERSION2_ATTR2BIT	| \
+	 XFS_SB_VERSION2_PROJID32BIT)
 #define	XFS_SB_VERSION2_OKSASHFBITS	\
 	(0)
 #define XFS_SB_VERSION2_OKREALBITS	\
@@ -495,6 +497,12 @@
 		sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT;
 }
 
+static inline int xfs_sb_version_hasprojid32bit(xfs_sb_t *sbp)
+{
+	return xfs_sb_version_hasmorebits(sbp) &&
+		(sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT);
+}
+
 /*
  * end of superblock version macros
  */
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 1c47eda..f6d956b 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -696,7 +696,7 @@
 	 * fail if the count would go below zero.
 	 */
 	if (blocks > 0) {
-		error = xfs_mod_incore_sb(tp->t_mountp, XFS_SBS_FDBLOCKS,
+		error = xfs_icsb_modify_counters(tp->t_mountp, XFS_SBS_FDBLOCKS,
 					  -((int64_t)blocks), rsvd);
 		if (error != 0) {
 			current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
@@ -767,7 +767,7 @@
 
 undo_blocks:
 	if (blocks > 0) {
-		(void) xfs_mod_incore_sb(tp->t_mountp, XFS_SBS_FDBLOCKS,
+		xfs_icsb_modify_counters(tp->t_mountp, XFS_SBS_FDBLOCKS,
 					 (int64_t)blocks, rsvd);
 		tp->t_blk_res = 0;
 	}
@@ -1009,7 +1009,7 @@
 xfs_trans_unreserve_and_mod_sb(
 	xfs_trans_t	*tp)
 {
-	xfs_mod_sb_t	msb[14];	/* If you add cases, add entries */
+	xfs_mod_sb_t	msb[9];	/* If you add cases, add entries */
 	xfs_mod_sb_t	*msbp;
 	xfs_mount_t	*mp = tp->t_mountp;
 	/* REFERENCED */
@@ -1017,55 +1017,61 @@
 	int		rsvd;
 	int64_t		blkdelta = 0;
 	int64_t		rtxdelta = 0;
+	int64_t		idelta = 0;
+	int64_t		ifreedelta = 0;
 
 	msbp = msb;
 	rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
 
-	/* calculate free blocks delta */
+	/* calculate deltas */
 	if (tp->t_blk_res > 0)
 		blkdelta = tp->t_blk_res;
-
 	if ((tp->t_fdblocks_delta != 0) &&
 	    (xfs_sb_version_haslazysbcount(&mp->m_sb) ||
 	     (tp->t_flags & XFS_TRANS_SB_DIRTY)))
 	        blkdelta += tp->t_fdblocks_delta;
 
-	if (blkdelta != 0) {
-		msbp->msb_field = XFS_SBS_FDBLOCKS;
-		msbp->msb_delta = blkdelta;
-		msbp++;
-	}
-
-	/* calculate free realtime extents delta */
 	if (tp->t_rtx_res > 0)
 		rtxdelta = tp->t_rtx_res;
-
 	if ((tp->t_frextents_delta != 0) &&
 	    (tp->t_flags & XFS_TRANS_SB_DIRTY))
 		rtxdelta += tp->t_frextents_delta;
 
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb) ||
+	     (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
+		idelta = tp->t_icount_delta;
+		ifreedelta = tp->t_ifree_delta;
+	}
+
+	/* apply the per-cpu counters */
+	if (blkdelta) {
+		error = xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS,
+						 blkdelta, rsvd);
+		if (error)
+			goto out;
+	}
+
+	if (idelta) {
+		error = xfs_icsb_modify_counters(mp, XFS_SBS_ICOUNT,
+						 idelta, rsvd);
+		if (error)
+			goto out_undo_fdblocks;
+	}
+
+	if (ifreedelta) {
+		error = xfs_icsb_modify_counters(mp, XFS_SBS_IFREE,
+						 ifreedelta, rsvd);
+		if (error)
+			goto out_undo_icount;
+	}
+
+	/* apply remaining deltas */
 	if (rtxdelta != 0) {
 		msbp->msb_field = XFS_SBS_FREXTENTS;
 		msbp->msb_delta = rtxdelta;
 		msbp++;
 	}
 
-	/* apply remaining deltas */
-
-	if (xfs_sb_version_haslazysbcount(&mp->m_sb) ||
-	     (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
-		if (tp->t_icount_delta != 0) {
-			msbp->msb_field = XFS_SBS_ICOUNT;
-			msbp->msb_delta = tp->t_icount_delta;
-			msbp++;
-		}
-		if (tp->t_ifree_delta != 0) {
-			msbp->msb_field = XFS_SBS_IFREE;
-			msbp->msb_delta = tp->t_ifree_delta;
-			msbp++;
-		}
-	}
-
 	if (tp->t_flags & XFS_TRANS_SB_DIRTY) {
 		if (tp->t_dblocks_delta != 0) {
 			msbp->msb_field = XFS_SBS_DBLOCKS;
@@ -1115,8 +1121,24 @@
 	if (msbp > msb) {
 		error = xfs_mod_incore_sb_batch(tp->t_mountp, msb,
 			(uint)(msbp - msb), rsvd);
-		ASSERT(error == 0);
+		if (error)
+			goto out_undo_ifreecount;
 	}
+
+	return;
+
+out_undo_ifreecount:
+	if (ifreedelta)
+		xfs_icsb_modify_counters(mp, XFS_SBS_IFREE, -ifreedelta, rsvd);
+out_undo_icount:
+	if (idelta)
+		xfs_icsb_modify_counters(mp, XFS_SBS_ICOUNT, -idelta, rsvd);
+out_undo_fdblocks:
+	if (blkdelta)
+		xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, -blkdelta, rsvd);
+out:
+	ASSERT(error = 0);
+	return;
 }
 
 /*
@@ -1389,15 +1411,12 @@
  */
 STATIC void
 xfs_trans_committed(
-	struct xfs_trans	*tp,
+	void			*arg,
 	int			abortflag)
 {
+	struct xfs_trans	*tp = arg;
 	struct xfs_log_item_desc *lidp, *next;
 
-	/* Call the transaction's completion callback if there is one. */
-	if (tp->t_callback != NULL)
-		tp->t_callback(tp, tp->t_callarg);
-
 	list_for_each_entry_safe(lidp, next, &tp->t_items, lid_trans) {
 		xfs_trans_item_committed(lidp->lid_item, tp->t_lsn, abortflag);
 		xfs_trans_free_item_desc(lidp);
@@ -1525,7 +1544,7 @@
 	 * running in simulation mode (the log is explicitly turned
 	 * off).
 	 */
-	tp->t_logcb.cb_func = (void(*)(void*, int))xfs_trans_committed;
+	tp->t_logcb.cb_func = xfs_trans_committed;
 	tp->t_logcb.cb_arg = tp;
 
 	/*
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index c13c0f9..246286b 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -399,8 +399,6 @@
 						 * transaction. */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
-	xfs_trans_callback_t	t_callback;	/* transaction callback */
-	void			*t_callarg;	/* callback arg */
 	unsigned int		t_flags;	/* misc flags */
 	int64_t			t_icount_delta;	/* superblock icount change */
 	int64_t			t_ifree_delta;	/* superblock ifree change */
@@ -473,6 +471,7 @@
 void		xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *);
 int		xfs_trans_iget(struct xfs_mount *, xfs_trans_t *,
 			       xfs_ino_t , uint, uint, struct xfs_inode **);
+void		xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int);
 void		xfs_trans_ijoin_ref(struct xfs_trans *, struct xfs_inode *, uint);
 void		xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *);
 void		xfs_trans_log_buf(xfs_trans_t *, struct xfs_buf *, uint, uint);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 90af025..c47918c 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -336,7 +336,7 @@
 			ASSERT(!XFS_BUF_ISASYNC(bp));
 			XFS_BUF_READ(bp);
 			xfsbdstrat(tp->t_mountp, bp);
-			error = xfs_iowait(bp);
+			error = xfs_buf_iowait(bp);
 			if (error) {
 				xfs_ioerror_alert("xfs_trans_read_buf", mp,
 						  bp, blkno);
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index cdc53a1..ccb3453 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -118,6 +118,36 @@
 }
 
 /*
+ * Transactional inode timestamp update. Requires the inode to be locked and
+ * joined to the transaction supplied. Relies on the transaction subsystem to
+ * track dirty state and update/writeback the inode accordingly.
+ */
+void
+xfs_trans_ichgtime(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	int			flags)
+{
+	struct inode		*inode = VFS_I(ip);
+	timespec_t		tv;
+
+	ASSERT(tp);
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(ip->i_transp == tp);
+
+	tv = current_fs_time(inode->i_sb);
+
+	if ((flags & XFS_ICHGTIME_MOD) &&
+	    !timespec_equal(&inode->i_mtime, &tv)) {
+		inode->i_mtime = tv;
+	}
+	if ((flags & XFS_ICHGTIME_CHG) &&
+	    !timespec_equal(&inode->i_ctime, &tv)) {
+		inode->i_ctime = tv;
+	}
+}
+
+/*
  * This is called to mark the fields indicated in fieldmask as needing
  * to be logged when the transaction is committed.  The inode must
  * already be associated with the given transaction.
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h
index 3207752..26d1867 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/xfs_types.h
@@ -73,8 +73,6 @@
 typedef	__uint32_t	xfs_dablk_t;	/* dir/attr block number (in file) */
 typedef	__uint32_t	xfs_dahash_t;	/* dir/attr hash value */
 
-typedef __uint16_t	xfs_prid_t;	/* prid_t truncated to 16bits in XFS */
-
 typedef __uint32_t	xlog_tid_t;	/* transaction ID type */
 
 /*
diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c
index b7d5769..8b32d1a 100644
--- a/fs/xfs/xfs_utils.c
+++ b/fs/xfs/xfs_utils.c
@@ -56,7 +56,6 @@
 	mode_t		mode,
 	xfs_nlink_t	nlink,
 	xfs_dev_t	rdev,
-	cred_t		*credp,
 	prid_t		prid,		/* project id */
 	int		okalloc,	/* ok to allocate new space */
 	xfs_inode_t	**ipp,		/* pointer to inode; it will be
@@ -93,7 +92,7 @@
 	 * transaction commit so that no other process can steal
 	 * the inode(s) that we've just allocated.
 	 */
-	code = xfs_ialloc(tp, dp, mode, nlink, rdev, credp, prid, okalloc,
+	code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc,
 			  &ialloc_context, &call_again, &ip);
 
 	/*
@@ -197,7 +196,7 @@
 		 * other allocations in this allocation group,
 		 * this call should always succeed.
 		 */
-		code = xfs_ialloc(tp, dp, mode, nlink, rdev, credp, prid,
+		code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid,
 				  okalloc, &ialloc_context, &call_again, &ip);
 
 		/*
@@ -235,7 +234,7 @@
 {
 	int	error;
 
-	xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
 	ASSERT (ip->i_d.di_nlink > 0);
 	ip->i_d.di_nlink--;
@@ -299,7 +298,7 @@
 {
 	if (ip->i_d.di_nlink >= XFS_MAXLINK)
 		return XFS_ERROR(EMLINK);
-	xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
 	ASSERT(ip->i_d.di_nlink > 0);
 	ip->i_d.di_nlink++;
diff --git a/fs/xfs/xfs_utils.h b/fs/xfs/xfs_utils.h
index f55b967..456fca3 100644
--- a/fs/xfs/xfs_utils.h
+++ b/fs/xfs/xfs_utils.h
@@ -19,8 +19,7 @@
 #define __XFS_UTILS_H__
 
 extern int xfs_dir_ialloc(xfs_trans_t **, xfs_inode_t *, mode_t, xfs_nlink_t,
-				xfs_dev_t, cred_t *, prid_t, int,
-				xfs_inode_t **, int *);
+				xfs_dev_t, prid_t, int, xfs_inode_t **, int *);
 extern int xfs_droplink(xfs_trans_t *, xfs_inode_t *);
 extern int xfs_bumplink(xfs_trans_t *, xfs_inode_t *);
 extern void xfs_bump_ino_vers2(xfs_trans_t *, xfs_inode_t *);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 4c7c7bf..8e4a63c4 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -114,7 +114,7 @@
 		 */
 		ASSERT(udqp == NULL);
 		ASSERT(gdqp == NULL);
-		code = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_d.di_projid,
+		code = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
 					 qflags, &udqp, &gdqp);
 		if (code)
 			return code;
@@ -184,8 +184,11 @@
 		    ip->i_size == 0 && ip->i_d.di_nextents == 0) {
 			xfs_iunlock(ip, XFS_ILOCK_EXCL);
 			lock_flags &= ~XFS_ILOCK_EXCL;
-			if (mask & ATTR_CTIME)
-				xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+			if (mask & ATTR_CTIME) {
+				inode->i_mtime = inode->i_ctime =
+						current_fs_time(inode->i_sb);
+				xfs_mark_inode_dirty_sync(ip);
+			}
 			code = 0;
 			goto error_return;
 		}
@@ -1253,8 +1256,7 @@
 	struct xfs_name		*name,
 	mode_t			mode,
 	xfs_dev_t		rdev,
-	xfs_inode_t		**ipp,
-	cred_t			*credp)
+	xfs_inode_t		**ipp)
 {
 	int			is_dir = S_ISDIR(mode);
 	struct xfs_mount	*mp = dp->i_mount;
@@ -1266,7 +1268,7 @@
 	boolean_t		unlock_dp_on_error = B_FALSE;
 	uint			cancel_flags;
 	int			committed;
-	xfs_prid_t		prid;
+	prid_t			prid;
 	struct xfs_dquot	*udqp = NULL;
 	struct xfs_dquot	*gdqp = NULL;
 	uint			resblks;
@@ -1279,9 +1281,9 @@
 		return XFS_ERROR(EIO);
 
 	if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-		prid = dp->i_d.di_projid;
+		prid = xfs_get_projid(dp);
 	else
-		prid = dfltprid;
+		prid = XFS_PROJID_DEFAULT;
 
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
@@ -1360,7 +1362,7 @@
 	 * entry pointing to them, but a directory also the "." entry
 	 * pointing to itself.
 	 */
-	error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, credp,
+	error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev,
 			       prid, resblks > 0, &ip, &committed);
 	if (error) {
 		if (error == ENOSPC)
@@ -1391,7 +1393,7 @@
 		ASSERT(error != ENOSPC);
 		goto out_trans_abort;
 	}
-	xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
 	if (is_dir) {
@@ -1742,7 +1744,7 @@
 		ASSERT(error != ENOENT);
 		goto out_bmap_cancel;
 	}
-	xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
 	if (is_dir) {
 		/*
@@ -1880,7 +1882,7 @@
 	 * the tree quota mechanism could be circumvented.
 	 */
 	if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
-		     (tdp->i_d.di_projid != sip->i_d.di_projid))) {
+		     (xfs_get_projid(tdp) != xfs_get_projid(sip)))) {
 		error = XFS_ERROR(EXDEV);
 		goto error_return;
 	}
@@ -1895,7 +1897,7 @@
 					&first_block, &free_list, resblks);
 	if (error)
 		goto abort_return;
-	xfs_ichgtime(tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
 
 	error = xfs_bumplink(tp, sip);
@@ -1933,8 +1935,7 @@
 	struct xfs_name		*link_name,
 	const char		*target_path,
 	mode_t			mode,
-	xfs_inode_t		**ipp,
-	cred_t			*credp)
+	xfs_inode_t		**ipp)
 {
 	xfs_mount_t		*mp = dp->i_mount;
 	xfs_trans_t		*tp;
@@ -1955,7 +1956,7 @@
 	int			byte_cnt;
 	int			n;
 	xfs_buf_t		*bp;
-	xfs_prid_t		prid;
+	prid_t			prid;
 	struct xfs_dquot	*udqp, *gdqp;
 	uint			resblks;
 
@@ -1978,9 +1979,9 @@
 
 	udqp = gdqp = NULL;
 	if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-		prid = dp->i_d.di_projid;
+		prid = xfs_get_projid(dp);
 	else
-		prid = (xfs_prid_t)dfltprid;
+		prid = XFS_PROJID_DEFAULT;
 
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
@@ -2046,8 +2047,8 @@
 	/*
 	 * Allocate an inode for the symlink.
 	 */
-	error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT),
-			       1, 0, credp, prid, resblks > 0, &ip, NULL);
+	error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0,
+			       prid, resblks > 0, &ip, NULL);
 	if (error) {
 		if (error == ENOSPC)
 			goto error_return;
@@ -2129,7 +2130,7 @@
 					&first_block, &free_list, resblks);
 	if (error)
 		goto error1;
-	xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
 	/*
@@ -2272,7 +2273,7 @@
 	count = len;
 	imapp = &imaps[0];
 	nimaps = 1;
-	bmapi_flag = XFS_BMAPI_WRITE | (alloc_type ? XFS_BMAPI_PREALLOC : 0);
+	bmapi_flag = XFS_BMAPI_WRITE | alloc_type;
 	startoffset_fsb	= XFS_B_TO_FSBT(mp, offset);
 	allocatesize_fsb = XFS_B_TO_FSB(mp, count);
 
@@ -2431,9 +2432,9 @@
 	if (endoff > ip->i_size)
 		endoff = ip->i_size;
 
-	bp = xfs_buf_get_noaddr(mp->m_sb.sb_blocksize,
-				XFS_IS_REALTIME_INODE(ip) ?
-				mp->m_rtdev_targp : mp->m_ddev_targp);
+	bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
+					mp->m_rtdev_targp : mp->m_ddev_targp,
+				mp->m_sb.sb_blocksize, XBF_DONT_BLOCK);
 	if (!bp)
 		return XFS_ERROR(ENOMEM);
 
@@ -2459,7 +2460,7 @@
 		XFS_BUF_READ(bp);
 		XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
 		xfsbdstrat(mp, bp);
-		error = xfs_iowait(bp);
+		error = xfs_buf_iowait(bp);
 		if (error) {
 			xfs_ioerror_alert("xfs_zero_remaining_bytes(read)",
 					  mp, bp, XFS_BUF_ADDR(bp));
@@ -2472,7 +2473,7 @@
 		XFS_BUF_UNREAD(bp);
 		XFS_BUF_WRITE(bp);
 		xfsbdstrat(mp, bp);
-		error = xfs_iowait(bp);
+		error = xfs_buf_iowait(bp);
 		if (error) {
 			xfs_ioerror_alert("xfs_zero_remaining_bytes(write)",
 					  mp, bp, XFS_BUF_ADDR(bp));
@@ -2711,6 +2712,7 @@
 	xfs_off_t	llen;
 	xfs_trans_t	*tp;
 	struct iattr	iattr;
+	int		prealloc_type;
 
 	if (!S_ISREG(ip->i_d.di_mode))
 		return XFS_ERROR(EINVAL);
@@ -2753,12 +2755,17 @@
 	 * size to be changed.
 	 */
 	setprealloc = clrprealloc = 0;
+	prealloc_type = XFS_BMAPI_PREALLOC;
 
 	switch (cmd) {
+	case XFS_IOC_ZERO_RANGE:
+		prealloc_type |= XFS_BMAPI_CONVERT;
+		xfs_tosspages(ip, startoffset, startoffset + bf->l_len, 0);
+		/* FALLTHRU */
 	case XFS_IOC_RESVSP:
 	case XFS_IOC_RESVSP64:
 		error = xfs_alloc_file_space(ip, startoffset, bf->l_len,
-								1, attr_flags);
+						prealloc_type, attr_flags);
 		if (error)
 			return error;
 		setprealloc = 1;
@@ -2827,7 +2834,7 @@
 		if (ip->i_d.di_mode & S_IXGRP)
 			ip->i_d.di_mode &= ~S_ISGID;
 
-		xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	}
 	if (setprealloc)
 		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h
index d8dfa8d..f6702927 100644
--- a/fs/xfs/xfs_vnodeops.h
+++ b/fs/xfs/xfs_vnodeops.h
@@ -2,7 +2,6 @@
 #define _XFS_VNODEOPS_H 1
 
 struct attrlist_cursor_kern;
-struct cred;
 struct file;
 struct iattr;
 struct inode;
@@ -26,7 +25,7 @@
 int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
 		struct xfs_inode **ipp, struct xfs_name *ci_name);
 int xfs_create(struct xfs_inode *dp, struct xfs_name *name, mode_t mode,
-		xfs_dev_t rdev, struct xfs_inode **ipp, cred_t *credp);
+		xfs_dev_t rdev, struct xfs_inode **ipp);
 int xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
 		struct xfs_inode *ip);
 int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
@@ -34,8 +33,7 @@
 int xfs_readdir(struct xfs_inode	*dp, void *dirent, size_t bufsize,
 		       xfs_off_t *offset, filldir_t filldir);
 int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,
-		const char *target_path, mode_t mode, struct xfs_inode **ipp,
-		cred_t *credp);
+		const char *target_path, mode_t mode, struct xfs_inode **ipp);
 int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state);
 int xfs_change_file_space(struct xfs_inode *ip, int cmd,
 		xfs_flock64_t *bf, xfs_off_t offset, int attr_flags);
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index e53347f..e994197 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -43,6 +43,7 @@
  */
 #define atomic_set(v, i) (((v)->counter) = (i))
 
+#include <linux/irqflags.h>
 #include <asm/system.h>
 
 /**
@@ -57,7 +58,7 @@
 	unsigned long flags;
 	int temp;
 
-	raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
+	raw_local_irq_save(flags); /* Don't trace it in an irqsoff handler */
 	temp = v->counter;
 	temp += i;
 	v->counter = temp;
@@ -78,7 +79,7 @@
 	unsigned long flags;
 	int temp;
 
-	raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
+	raw_local_irq_save(flags); /* Don't trace it in an irqsoff handler */
 	temp = v->counter;
 	temp -= i;
 	v->counter = temp;
@@ -119,14 +120,23 @@
 #define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
 #define atomic_inc_and_test(v)		(atomic_add_return(1, (v)) == 0)
 
-#define atomic_add_unless(v, a, u)				\
-({								\
-	int c, old;						\
-	c = atomic_read(v);					\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
-		c = old;					\
-	c != (u);						\
-})
+#define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
+#define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
+
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+static inline int atomic_add_unless(atomic_t *v, int a, int u)
+{
+  int c, old;
+  c = atomic_read(v);
+  while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
+    c = old;
+  return c != u;
+}
 
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
@@ -140,15 +150,6 @@
 	raw_local_irq_restore(flags);
 }
 
-#define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
-#define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
-
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
 /* Assume that atomic operations are already serializing */
 #define smp_mb__before_atomic_dec()	barrier()
 #define smp_mb__after_atomic_dec()	barrier()
diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 1914e97..110fa70 100644
--- a/include/asm-generic/bitops/find.h
+++ b/include/asm-generic/bitops/find.h
@@ -1,15 +1,50 @@
 #ifndef _ASM_GENERIC_BITOPS_FIND_H_
 #define _ASM_GENERIC_BITOPS_FIND_H_
 
-#ifndef CONFIG_GENERIC_FIND_NEXT_BIT
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
 extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
 		size, unsigned long offset);
 
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
 extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned
 		long size, unsigned long offset);
-#endif
+
+#ifdef CONFIG_GENERIC_FIND_FIRST_BIT
+
+/**
+ * find_first_bit - find the first set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first set bit.
+ */
+extern unsigned long find_first_bit(const unsigned long *addr,
+				    unsigned long size);
+
+/**
+ * find_first_zero_bit - find the first cleared bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first cleared bit.
+ */
+extern unsigned long find_first_zero_bit(const unsigned long *addr,
+					 unsigned long size);
+#else /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
 #define find_first_bit(addr, size) find_next_bit((addr), (size), 0)
 #define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0)
 
+#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
+
 #endif /*_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/include/asm-generic/cmpxchg-local.h b/include/asm-generic/cmpxchg-local.h
index b2ba2fc..2533fdd 100644
--- a/include/asm-generic/cmpxchg-local.h
+++ b/include/asm-generic/cmpxchg-local.h
@@ -2,6 +2,7 @@
 #define __ASM_GENERIC_CMPXCHG_LOCAL_H
 
 #include <linux/types.h>
+#include <linux/irqflags.h>
 
 extern unsigned long wrong_size_cmpxchg(volatile void *ptr);
 
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h
index a70b2d2..0fc16e3 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -122,7 +122,7 @@
 
 struct f_owner_ex {
 	int	type;
-	pid_t	pid;
+	__kernel_pid_t	pid;
 };
 
 /* for F_[GET|SET]FL */
diff --git a/include/asm-generic/hardirq.h b/include/asm-generic/hardirq.h
index 62f5908..04d0a97 100644
--- a/include/asm-generic/hardirq.h
+++ b/include/asm-generic/hardirq.h
@@ -3,13 +3,13 @@
 
 #include <linux/cache.h>
 #include <linux/threads.h>
-#include <linux/irq.h>
 
 typedef struct {
 	unsigned int __softirq_pending;
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+#include <linux/irq.h>
 
 #ifndef ack_bad_irq
 static inline void ack_bad_irq(unsigned int irq)
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 118601f..3577ca1 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -19,7 +19,9 @@
 #include <asm-generic/iomap.h>
 #endif
 
+#ifndef mmiowb
 #define mmiowb() do {} while (0)
+#endif
 
 /*****************************************************************************/
 /*
@@ -28,39 +30,51 @@
  * differently. On the simple architectures, we just read/write the
  * memory location directly.
  */
+#ifndef __raw_readb
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	return *(const volatile u8 __force *) addr;
 }
+#endif
 
+#ifndef __raw_readw
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	return *(const volatile u16 __force *) addr;
 }
+#endif
 
+#ifndef __raw_readl
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	return *(const volatile u32 __force *) addr;
 }
+#endif
 
 #define readb __raw_readb
 #define readw(addr) __le16_to_cpu(__raw_readw(addr))
 #define readl(addr) __le32_to_cpu(__raw_readl(addr))
 
+#ifndef __raw_writeb
 static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
 {
 	*(volatile u8 __force *) addr = b;
 }
+#endif
 
+#ifndef __raw_writew
 static inline void __raw_writew(u16 b, volatile void __iomem *addr)
 {
 	*(volatile u16 __force *) addr = b;
 }
+#endif
 
+#ifndef __raw_writel
 static inline void __raw_writel(u32 b, volatile void __iomem *addr)
 {
 	*(volatile u32 __force *) addr = b;
 }
+#endif
 
 #define writeb __raw_writeb
 #define writew(b,addr) __raw_writew(__cpu_to_le16(b),addr)
@@ -122,6 +136,7 @@
 #define outw_p(x, addr)	outw((x), (addr))
 #define outl_p(x, addr)	outl((x), (addr))
 
+#ifndef insb
 static inline void insb(unsigned long addr, void *buffer, int count)
 {
 	if (count) {
@@ -132,7 +147,9 @@
 		} while (--count);
 	}
 }
+#endif
 
+#ifndef insw
 static inline void insw(unsigned long addr, void *buffer, int count)
 {
 	if (count) {
@@ -143,7 +160,9 @@
 		} while (--count);
 	}
 }
+#endif
 
+#ifndef insl
 static inline void insl(unsigned long addr, void *buffer, int count)
 {
 	if (count) {
@@ -154,7 +173,9 @@
 		} while (--count);
 	}
 }
+#endif
 
+#ifndef outsb
 static inline void outsb(unsigned long addr, const void *buffer, int count)
 {
 	if (count) {
@@ -164,7 +185,9 @@
 		} while (--count);
 	}
 }
+#endif
 
+#ifndef outsw
 static inline void outsw(unsigned long addr, const void *buffer, int count)
 {
 	if (count) {
@@ -174,7 +197,9 @@
 		} while (--count);
 	}
 }
+#endif
 
+#ifndef outsl
 static inline void outsl(unsigned long addr, const void *buffer, int count)
 {
 	if (count) {
@@ -184,6 +209,7 @@
 		} while (--count);
 	}
 }
+#endif
 
 #ifndef CONFIG_GENERIC_IOMAP
 #define ioread8(addr)		readb(addr)
diff --git a/include/asm-generic/irqflags.h b/include/asm-generic/irqflags.h
index 9aebf61..1f40d002 100644
--- a/include/asm-generic/irqflags.h
+++ b/include/asm-generic/irqflags.h
@@ -5,68 +5,62 @@
  * All architectures should implement at least the first two functions,
  * usually inline assembly will be the best way.
  */
-#ifndef RAW_IRQ_DISABLED
-#define RAW_IRQ_DISABLED 0
-#define RAW_IRQ_ENABLED 1
+#ifndef ARCH_IRQ_DISABLED
+#define ARCH_IRQ_DISABLED 0
+#define ARCH_IRQ_ENABLED 1
 #endif
 
 /* read interrupt enabled status */
-#ifndef __raw_local_save_flags
-unsigned long __raw_local_save_flags(void);
+#ifndef arch_local_save_flags
+unsigned long arch_local_save_flags(void);
 #endif
 
 /* set interrupt enabled status */
-#ifndef raw_local_irq_restore
-void raw_local_irq_restore(unsigned long flags);
+#ifndef arch_local_irq_restore
+void arch_local_irq_restore(unsigned long flags);
 #endif
 
 /* get status and disable interrupts */
-#ifndef __raw_local_irq_save
-static inline unsigned long __raw_local_irq_save(void)
+#ifndef arch_local_irq_save
+static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
-	flags = __raw_local_save_flags();
-	raw_local_irq_restore(RAW_IRQ_DISABLED);
+	flags = arch_local_save_flags();
+	arch_local_irq_restore(ARCH_IRQ_DISABLED);
 	return flags;
 }
 #endif
 
 /* test flags */
-#ifndef raw_irqs_disabled_flags
-static inline int raw_irqs_disabled_flags(unsigned long flags)
+#ifndef arch_irqs_disabled_flags
+static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
-	return flags == RAW_IRQ_DISABLED;
+	return flags == ARCH_IRQ_DISABLED;
 }
 #endif
 
 /* unconditionally enable interrupts */
-#ifndef raw_local_irq_enable
-static inline void raw_local_irq_enable(void)
+#ifndef arch_local_irq_enable
+static inline void arch_local_irq_enable(void)
 {
-	raw_local_irq_restore(RAW_IRQ_ENABLED);
+	arch_local_irq_restore(ARCH_IRQ_ENABLED);
 }
 #endif
 
 /* unconditionally disable interrupts */
-#ifndef raw_local_irq_disable
-static inline void raw_local_irq_disable(void)
+#ifndef arch_local_irq_disable
+static inline void arch_local_irq_disable(void)
 {
-	raw_local_irq_restore(RAW_IRQ_DISABLED);
+	arch_local_irq_restore(ARCH_IRQ_DISABLED);
 }
 #endif
 
 /* test hardware interrupt enable bit */
-#ifndef raw_irqs_disabled
-static inline int raw_irqs_disabled(void)
+#ifndef arch_irqs_disabled
+static inline int arch_irqs_disabled(void)
 {
-	return raw_irqs_disabled_flags(__raw_local_save_flags());
+	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 #endif
 
-#define raw_local_save_flags(flags) \
-	do { (flags) = __raw_local_save_flags(); } while (0)
-
-#define raw_local_irq_save(flags) \
-	do { (flags) = __raw_local_irq_save(); } while (0)
-
 #endif /* __ASM_GENERIC_IRQFLAGS_H */
diff --git a/include/asm-generic/kdebug.h b/include/asm-generic/kdebug.h
index 11e57b6..d181449 100644
--- a/include/asm-generic/kdebug.h
+++ b/include/asm-generic/kdebug.h
@@ -3,7 +3,7 @@
 
 enum die_val {
 	DIE_UNUSED,
-	DIE_OOPS=1
+	DIE_OOPS = 1,
 };
 
 #endif /* _ASM_GENERIC_KDEBUG_H */
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 08923b6..d17784e 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -55,14 +55,18 @@
  */
 #define per_cpu(var, cpu) \
 	(*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu)))
-#define __get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(&(var), my_cpu_offset))
-#define __raw_get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(&(var), __my_cpu_offset))
 
-#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#ifndef __this_cpu_ptr
 #define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+#endif
+#ifdef CONFIG_DEBUG_PREEMPT
+#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#else
+#define this_cpu_ptr(ptr) __this_cpu_ptr(ptr)
+#endif
 
+#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
+#define __raw_get_cpu_var(var) (*__this_cpu_ptr(&(var)))
 
 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void setup_per_cpu_areas(void);
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index e2bd73e..f4d4120 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -129,6 +129,10 @@
 #define move_pte(pte, prot, old_addr, new_addr)	(pte)
 #endif
 
+#ifndef flush_tlb_fix_spurious_fault
+#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
+#endif
+
 #ifndef pgprot_noncached
 #define pgprot_noncached(prot)	(prot)
 #endif
diff --git a/include/asm-generic/system.h b/include/asm-generic/system.h
index efa403b..4b0b9cb 100644
--- a/include/asm-generic/system.h
+++ b/include/asm-generic/system.h
@@ -21,6 +21,7 @@
 #include <linux/irqflags.h>
 
 #include <asm/cmpxchg-local.h>
+#include <asm/cmpxchg.h>
 
 struct task_struct;
 
@@ -136,25 +137,6 @@
 #define xchg(ptr, x) \
 	((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
 
-static inline unsigned long __cmpxchg(volatile unsigned long *m,
-				      unsigned long old, unsigned long new)
-{
-	unsigned long retval;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	retval = *m;
-	if (retval == old)
-		*m = new;
-	local_irq_restore(flags);
-	return retval;
-}
-
-#define cmpxchg(ptr, o, n)					\
-	((__typeof__(*(ptr))) __cmpxchg((unsigned long *)(ptr), \
-					(unsigned long)(o),	\
-					(unsigned long)(n)))
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 8a92a17..f4229fb 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -220,6 +220,8 @@
 									\
 	BUG_TABLE							\
 									\
+	JUMP_TABLE							\
+									\
 	/* PCI quirks */						\
 	.pci_fixup        : AT(ADDR(.pci_fixup) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start_pci_fixups_early) = .;		\
@@ -563,6 +565,14 @@
 #define BUG_TABLE
 #endif
 
+#define JUMP_TABLE							\
+	. = ALIGN(8);							\
+	__jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__start___jump_table) = .;		\
+		*(__jump_table)						\
+		VMLINUX_SYMBOL(__stop___jump_table) = .;		\
+	}
+
 #ifdef CONFIG_PM_TRACE
 #define TRACEDATA							\
 	. = ALIGN(4);							\
@@ -677,7 +687,9 @@
 				- LOAD_OFFSET) {			\
 		VMLINUX_SYMBOL(__per_cpu_start) = .;			\
 		*(.data..percpu..first)					\
+		. = ALIGN(PAGE_SIZE);					\
 		*(.data..percpu..page_aligned)				\
+		*(.data..percpu..readmostly)				\
 		*(.data..percpu)					\
 		*(.data..percpu..shared_aligned)			\
 		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
@@ -703,7 +715,9 @@
 		VMLINUX_SYMBOL(__per_cpu_load) = .;			\
 		VMLINUX_SYMBOL(__per_cpu_start) = .;			\
 		*(.data..percpu..first)					\
+		. = ALIGN(PAGE_SIZE);					\
 		*(.data..percpu..page_aligned)				\
+		*(.data..percpu..readmostly)				\
 		*(.data..percpu)					\
 		*(.data..percpu..shared_aligned)			\
 		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h
index 7e3d285..1d0ef1a 100644
--- a/include/linux/acpi_pmtmr.h
+++ b/include/linux/acpi_pmtmr.h
@@ -25,8 +25,6 @@
 	return acpi_pm_read_verified() & ACPI_PM_MASK;
 }
 
-extern void pmtimer_wait(unsigned);
-
 #else
 
 static inline u32 acpi_pm_read_early(void)
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index b0c1740..c6454cc 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -20,6 +20,7 @@
 #include <linux/resource.h>
 
 #define AMBA_NR_IRQS	2
+#define AMBA_CID	0xb105f00d
 
 struct clk;
 
@@ -70,9 +71,15 @@
 #define amba_pclk_disable(d)	\
 	do { if (!IS_ERR((d)->pclk)) clk_disable((d)->pclk); } while (0)
 
-#define amba_config(d)	(((d)->periphid >> 24) & 0xff)
-#define amba_rev(d)	(((d)->periphid >> 20) & 0x0f)
-#define amba_manf(d)	(((d)->periphid >> 12) & 0xff)
-#define amba_part(d)	((d)->periphid & 0xfff)
+/* Some drivers don't use the struct amba_device */
+#define AMBA_CONFIG_BITS(a) (((a) >> 24) & 0xff)
+#define AMBA_REV_BITS(a) (((a) >> 20) & 0x0f)
+#define AMBA_MANF_BITS(a) (((a) >> 12) & 0xff)
+#define AMBA_PART_BITS(a) ((a) & 0xfff)
+
+#define amba_config(d)	AMBA_CONFIG_BITS((d)->periphid)
+#define amba_rev(d)	AMBA_REV_BITS((d)->periphid)
+#define amba_manf(d)	AMBA_MANF_BITS((d)->periphid)
+#define amba_part(d)	AMBA_PART_BITS((d)->periphid)
 
 #endif
diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h
index ca84ce7..f4ee9ac 100644
--- a/include/linux/amba/mmci.h
+++ b/include/linux/amba/mmci.h
@@ -24,6 +24,7 @@
  * whether a card is present in the MMC slot or not
  * @gpio_wp: read this GPIO pin to see if the card is write protected
  * @gpio_cd: read this GPIO pin to detect card insertion
+ * @cd_invert: true if the gpio_cd pin value is active low
  * @capabilities: the capabilities of the block as implemented in
  * this platform, signify anything MMC_CAP_* from mmc/host.h
  */
@@ -35,6 +36,7 @@
 	unsigned int (*status)(struct device *);
 	int	gpio_wp;
 	int	gpio_cd;
+	bool	cd_invert;
 	unsigned long capabilities;
 };
 
diff --git a/include/linux/amba/pl022.h b/include/linux/amba/pl022.h
index abf26cc..4ce98f5 100644
--- a/include/linux/amba/pl022.h
+++ b/include/linux/amba/pl022.h
@@ -228,6 +228,7 @@
 };
 
 
+struct dma_chan;
 /**
  * struct pl022_ssp_master - device.platform_data for SPI controller devices.
  * @num_chipselect: chipselects are used to distinguish individual
@@ -235,11 +236,16 @@
  *     each slave has a chipselect signal, but it's common that not
  *     every chipselect is connected to a slave.
  * @enable_dma: if true enables DMA driven transfers.
+ * @dma_rx_param: parameter to locate an RX DMA channel.
+ * @dma_tx_param: parameter to locate a TX DMA channel.
  */
 struct pl022_ssp_controller {
 	u16 bus_id;
 	u8 num_chipselect;
 	u8 enable_dma:1;
+	bool (*dma_filter)(struct dma_chan *chan, void *filter_param);
+	void *dma_rx_param;
+	void *dma_tx_param;
 };
 
 /**
@@ -270,20 +276,13 @@
  * @dma_config: DMA configuration for SSP controller and peripheral
  */
 struct pl022_config_chip {
-	struct device *dev;
-	enum ssp_loopback lbm;
 	enum ssp_interface iface;
 	enum ssp_hierarchy hierarchy;
 	bool slave_tx_disable;
 	struct ssp_clock_params clk_freq;
-	enum ssp_rx_endian endian_rx;
-	enum ssp_tx_endian endian_tx;
-	enum ssp_data_size data_size;
 	enum ssp_mode com_mode;
 	enum ssp_rx_level_trig rx_lev_trig;
 	enum ssp_tx_level_trig tx_lev_trig;
-	enum ssp_spi_clk_phase clk_phase;
-	enum ssp_spi_clk_pol clk_pol;
 	enum ssp_microwire_ctrl_len ctrl_len;
 	enum ssp_microwire_wait_state wait_state;
 	enum ssp_duplex duplex;
diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index e1b634b..6021588 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -32,7 +32,9 @@
 #define UART01x_RSR		0x04	/* Receive status register (Read). */
 #define UART01x_ECR		0x04	/* Error clear register (Write). */
 #define UART010_LCRH		0x08	/* Line control register, high byte. */
+#define ST_UART011_DMAWM	0x08    /* DMA watermark configure register. */
 #define UART010_LCRM		0x0C	/* Line control register, middle byte. */
+#define ST_UART011_TIMEOUT	0x0C    /* Timeout period register. */
 #define UART010_LCRL		0x10	/* Line control register, low byte. */
 #define UART010_CR		0x14	/* Control register. */
 #define UART01x_FR		0x18	/* Flag register (Read only). */
@@ -51,6 +53,15 @@
 #define UART011_MIS		0x40	/* Masked interrupt status. */
 #define UART011_ICR		0x44	/* Interrupt clear register. */
 #define UART011_DMACR		0x48	/* DMA control register. */
+#define ST_UART011_XFCR		0x50	/* XON/XOFF control register. */
+#define ST_UART011_XON1		0x54	/* XON1 register. */
+#define ST_UART011_XON2		0x58	/* XON2 register. */
+#define ST_UART011_XOFF1	0x5C	/* XON1 register. */
+#define ST_UART011_XOFF2	0x60	/* XON2 register. */
+#define ST_UART011_ITCR		0x80	/* Integration test control register. */
+#define ST_UART011_ITIP		0x84	/* Integration test input register. */
+#define ST_UART011_ABCR		0x100	/* Autobaud control register. */
+#define ST_UART011_ABIMSC	0x15C	/* Autobaud interrupt mask/clear register. */
 
 #define UART011_DR_OE		(1 << 11)
 #define UART011_DR_BE		(1 << 10)
diff --git a/include/linux/ata.h b/include/linux/ata.h
index fe6e681..0c4929f 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -89,6 +89,7 @@
 	ATA_ID_SPG		= 98,
 	ATA_ID_LBA_CAPACITY_2	= 100,
 	ATA_ID_SECTOR_SIZE	= 106,
+	ATA_ID_LOGICAL_SECTOR_SIZE	= 117,	/* and 118 */
 	ATA_ID_LAST_LUN		= 126,
 	ATA_ID_DLF		= 128,
 	ATA_ID_CSFO		= 129,
@@ -640,16 +641,49 @@
 	return (id[ATA_ID_CFS_ENABLE_2] & 0x2400) == 0x2400;
 }
 
-static inline int ata_id_has_large_logical_sectors(const u16 *id)
+static inline u32 ata_id_logical_sector_size(const u16 *id)
 {
-	if ((id[ATA_ID_SECTOR_SIZE] & 0xc000) != 0x4000)
-		return 0;
-	return id[ATA_ID_SECTOR_SIZE] & (1 << 13);
+	/* T13/1699-D Revision 6a, Sep 6, 2008. Page 128.
+	 * IDENTIFY DEVICE data, word 117-118.
+	 * 0xd000 ignores bit 13 (logical:physical > 1)
+	 */
+	if ((id[ATA_ID_SECTOR_SIZE] & 0xd000) == 0x5000)
+		return (((id[ATA_ID_LOGICAL_SECTOR_SIZE+1] << 16)
+			 + id[ATA_ID_LOGICAL_SECTOR_SIZE]) * sizeof(u16)) ;
+	return ATA_SECT_SIZE;
 }
 
-static inline u16 ata_id_logical_per_physical_sectors(const u16 *id)
+static inline u8 ata_id_log2_per_physical_sector(const u16 *id)
 {
-	return 1 << (id[ATA_ID_SECTOR_SIZE] & 0xf);
+	/* T13/1699-D Revision 6a, Sep 6, 2008. Page 128.
+	 * IDENTIFY DEVICE data, word 106.
+	 * 0xe000 ignores bit 12 (logical sector > 512 bytes)
+	 */
+	if ((id[ATA_ID_SECTOR_SIZE] & 0xe000) == 0x6000)
+		return (id[ATA_ID_SECTOR_SIZE] & 0xf);
+	return 0;
+}
+
+/* Offset of logical sectors relative to physical sectors.
+ *
+ * If device has more than one logical sector per physical sector
+ * (aka 512 byte emulation), vendors might offset the "sector 0" address
+ * so sector 63 is "naturally aligned" - e.g. FAT partition table.
+ * This avoids Read/Mod/Write penalties when using FAT partition table
+ * and updating "well aligned" (FS perspective) physical sectors on every
+ * transaction.
+ */
+static inline u16 ata_id_logical_sector_offset(const u16 *id,
+	 u8 log2_per_phys)
+{
+	u16 word_209 = id[209];
+
+	if ((log2_per_phys > 1) && (word_209 & 0xc000) == 0x4000) {
+		u16 first = word_209 & 0x3fff;
+		if (first > 0)
+			return (1 << log2_per_phys) - first;
+	}
+	return 0;
 }
 
 static inline int ata_id_has_lba48(const u16 *id)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5274103..ba67999 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -346,8 +346,15 @@
 }
 
 #else
-#define bvec_kmap_irq(bvec, flags)	(page_address((bvec)->bv_page) + (bvec)->bv_offset)
-#define bvec_kunmap_irq(buf, flags)	do { *(flags) = 0; } while (0)
+static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
+{
+	return page_address(bvec->bv_page) + bvec->bv_offset;
+}
+
+static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
+{
+	*flags = 0;
+}
 #endif
 
 static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx,
@@ -496,6 +503,10 @@
 #define bip_for_each_vec(bvl, bip, i)					\
 	__bip_for_each_vec(bvl, bip, i, (bip)->bip_idx)
 
+#define bio_for_each_integrity_vec(_bvl, _bio, _iter)			\
+	for_each_bio(_bio)						\
+		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
+
 #define bio_integrity(bio) (bio->bi_integrity != NULL)
 
 extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *);
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index fc68053..827cc95 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -136,28 +136,6 @@
 }
 
 #ifdef __KERNEL__
-#ifdef CONFIG_GENERIC_FIND_FIRST_BIT
-
-/**
- * find_first_bit - find the first set bit in a memory region
- * @addr: The address to start the search at
- * @size: The maximum size to search
- *
- * Returns the bit number of the first set bit.
- */
-extern unsigned long find_first_bit(const unsigned long *addr,
-				    unsigned long size);
-
-/**
- * find_first_zero_bit - find the first cleared bit in a memory region
- * @addr: The address to start the search at
- * @size: The maximum size to search
- *
- * Returns the bit number of the first cleared bit.
- */
-extern unsigned long find_first_zero_bit(const unsigned long *addr,
-					 unsigned long size);
-#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
 #ifdef CONFIG_GENERIC_FIND_LAST_BIT
 /**
@@ -171,28 +149,5 @@
 				   unsigned long size);
 #endif /* CONFIG_GENERIC_FIND_LAST_BIT */
 
-#ifdef CONFIG_GENERIC_FIND_NEXT_BIT
-
-/**
- * find_next_bit - find the next set bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The bitmap size in bits
- */
-extern unsigned long find_next_bit(const unsigned long *addr,
-				   unsigned long size, unsigned long offset);
-
-/**
- * find_next_zero_bit - find the next cleared bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The bitmap size in bits
- */
-
-extern unsigned long find_next_zero_bit(const unsigned long *addr,
-					unsigned long size,
-					unsigned long offset);
-
-#endif /* CONFIG_GENERIC_FIND_NEXT_BIT */
 #endif /* __KERNEL__ */
 #endif
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index ca83a97..0437ab6 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -97,6 +97,7 @@
 #define BIO_NULL_MAPPED 9	/* contains invalid user pages */
 #define BIO_FS_INTEGRITY 10	/* fs owns integrity data, not block layer */
 #define BIO_QUIET	11	/* Make BIO Quiet */
+#define BIO_MAPPED_INTEGRITY 12/* integrity metadata has been remapped */
 #define bio_flagged(bio, flag)	((bio)->bi_flags & (1 << (flag)))
 
 /*
@@ -130,6 +131,8 @@
 	/* bio only flags */
 	__REQ_UNPLUG,		/* unplug the immediately after submission */
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
+	__REQ_THROTTLED,	/* This bio has already been subjected to
+				 * throttling rules. Don't do it again. */
 
 	/* request only flags */
 	__REQ_SORTED,		/* elevator knows about this request */
@@ -143,10 +146,8 @@
 	__REQ_FAILED,		/* set if the request failed */
 	__REQ_QUIET,		/* don't worry about errors */
 	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
-	__REQ_ORDERED_COLOR,	/* is before or after barrier */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_COPY_USER,	/* contains copies of user pages */
-	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
 	__REQ_FLUSH,		/* request for cache flush */
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
@@ -168,10 +169,12 @@
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \
-	 REQ_META| REQ_DISCARD | REQ_NOIDLE)
+	 REQ_META | REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
+#define REQ_CLONE_MASK		REQ_COMMON_MASK
 
 #define REQ_UNPLUG		(1 << __REQ_UNPLUG)
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)
+#define REQ_THROTTLED		(1 << __REQ_THROTTLED)
 
 #define REQ_SORTED		(1 << __REQ_SORTED)
 #define REQ_SOFTBARRIER		(1 << __REQ_SOFTBARRIER)
@@ -184,10 +187,8 @@
 #define REQ_FAILED		(1 << __REQ_FAILED)
 #define REQ_QUIET		(1 << __REQ_QUIET)
 #define REQ_PREEMPT		(1 << __REQ_PREEMPT)
-#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
 #define REQ_ALLOCED		(1 << __REQ_ALLOCED)
 #define REQ_COPY_USER		(1 << __REQ_COPY_USER)
-#define REQ_INTEGRITY		(1 << __REQ_INTEGRITY)
 #define REQ_FLUSH		(1 << __REQ_FLUSH)
 #define REQ_IO_STAT		(1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2c54906..009b80e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -115,6 +115,7 @@
 	void *elevator_private3;
 
 	struct gendisk *rq_disk;
+	struct hd_struct *part;
 	unsigned long start_time;
 #ifdef CONFIG_BLK_CGROUP
 	unsigned long long start_time_ns;
@@ -124,6 +125,9 @@
 	 * physical address coalescing is performed.
 	 */
 	unsigned short nr_phys_segments;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	unsigned short nr_integrity_segments;
+#endif
 
 	unsigned short ioprio;
 
@@ -243,6 +247,7 @@
 
 	unsigned short		logical_block_size;
 	unsigned short		max_segments;
+	unsigned short		max_integrity_segments;
 
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
@@ -355,18 +360,25 @@
 	struct blk_trace	*blk_trace;
 #endif
 	/*
-	 * reserved for flush operations
+	 * for flush operations
 	 */
-	unsigned int		ordered, next_ordered, ordseq;
-	int			orderr, ordcolor;
-	struct request		pre_flush_rq, bar_rq, post_flush_rq;
-	struct request		*orig_bar_rq;
+	unsigned int		flush_flags;
+	unsigned int		flush_seq;
+	int			flush_err;
+	struct request		flush_rq;
+	struct request		*orig_flush_rq;
+	struct list_head	pending_flushes;
 
 	struct mutex		sysfs_lock;
 
 #if defined(CONFIG_BLK_DEV_BSG)
 	struct bsg_class_device bsg_dev;
 #endif
+
+#ifdef CONFIG_BLK_DEV_THROTTLING
+	/* Throttle data */
+	struct throtl_data *td;
+#endif
 };
 
 #define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
@@ -462,56 +474,6 @@
 	__clear_bit(flag, &q->queue_flags);
 }
 
-enum {
-	/*
-	 * Hardbarrier is supported with one of the following methods.
-	 *
-	 * NONE		: hardbarrier unsupported
-	 * DRAIN	: ordering by draining is enough
-	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
-	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
-	 * TAG		: ordering by tag is enough
-	 * TAG_FLUSH	: ordering by tag w/ pre and post flushes
-	 * TAG_FUA	: ordering by tag w/ pre flush and FUA write
-	 */
-	QUEUE_ORDERED_BY_DRAIN		= 0x01,
-	QUEUE_ORDERED_BY_TAG		= 0x02,
-	QUEUE_ORDERED_DO_PREFLUSH	= 0x10,
-	QUEUE_ORDERED_DO_BAR		= 0x20,
-	QUEUE_ORDERED_DO_POSTFLUSH	= 0x40,
-	QUEUE_ORDERED_DO_FUA		= 0x80,
-
-	QUEUE_ORDERED_NONE		= 0x00,
-
-	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_BY_DRAIN |
-					  QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_DRAIN_FLUSH	= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_DRAIN_FUA		= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
-	QUEUE_ORDERED_TAG		= QUEUE_ORDERED_BY_TAG |
-					  QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_TAG_FLUSH		= QUEUE_ORDERED_TAG |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_TAG_FUA		= QUEUE_ORDERED_TAG |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
-	/*
-	 * Ordered operation sequence
-	 */
-	QUEUE_ORDSEQ_STARTED	= 0x01,	/* flushing in progress */
-	QUEUE_ORDSEQ_DRAIN	= 0x02,	/* waiting for the queue to be drained */
-	QUEUE_ORDSEQ_PREFLUSH	= 0x04,	/* pre-flushing in progress */
-	QUEUE_ORDSEQ_BAR	= 0x08,	/* original barrier req in progress */
-	QUEUE_ORDSEQ_POSTFLUSH	= 0x10,	/* post-flushing in progress */
-	QUEUE_ORDSEQ_DONE	= 0x20,
-};
-
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
@@ -521,7 +483,6 @@
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
-#define blk_queue_flushing(q)	((q)->ordseq)
 #define blk_queue_stackable(q)	\
 	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
@@ -592,7 +553,8 @@
  * it already be started by driver.
  */
 #define RQ_NOMERGE_FLAGS	\
-	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
+	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \
+	 REQ_FLUSH | REQ_FUA)
 #define rq_mergeable(rq)	\
 	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
 	 (((rq)->cmd_flags & REQ_DISCARD) || \
@@ -851,7 +813,7 @@
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
 extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
-extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
+extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
@@ -881,12 +843,8 @@
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
 extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
+extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
-extern int blk_queue_ordered(struct request_queue *, unsigned);
-extern bool blk_do_ordered(struct request_queue *, struct request **);
-extern unsigned blk_ordered_cur_seq(struct request_queue *);
-extern unsigned blk_ordered_req_seq(struct request *);
-extern bool blk_ordered_complete_seq(struct request_queue *, unsigned, int);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
@@ -919,27 +877,20 @@
 		return NULL;
 	return bqt->tag_index[tag];
 }
-enum{
-	BLKDEV_WAIT,	/* wait for completion */
-	BLKDEV_BARRIER,	/* issue request with barrier */
-	BLKDEV_SECURE,	/* secure discard */
-};
-#define BLKDEV_IFL_WAIT		(1 << BLKDEV_WAIT)
-#define BLKDEV_IFL_BARRIER	(1 << BLKDEV_BARRIER)
-#define BLKDEV_IFL_SECURE	(1 << BLKDEV_SECURE)
-extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *,
-			unsigned long);
+
+#define BLKDEV_DISCARD_SECURE  0x01    /* secure discard */
+
+extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
-static inline int sb_issue_discard(struct super_block *sb,
-				   sector_t block, sector_t nr_blocks)
+			sector_t nr_sects, gfp_t gfp_mask);
+static inline int sb_issue_discard(struct super_block *sb, sector_t block,
+		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
-	block <<= (sb->s_blocksize_bits - 9);
-	nr_blocks <<= (sb->s_blocksize_bits - 9);
-	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS,
-				   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+	return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
+				    nr_blocks << (sb->s_blocksize_bits - 9),
+				    gfp_mask, flags);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
@@ -1004,7 +955,7 @@
 	return q->limits.physical_block_size;
 }
 
-static inline int bdev_physical_block_size(struct block_device *bdev)
+static inline unsigned int bdev_physical_block_size(struct block_device *bdev)
 {
 	return queue_physical_block_size(bdev_get_queue(bdev));
 }
@@ -1093,11 +1044,11 @@
 	return q ? q->dma_alignment : 511;
 }
 
-static inline int blk_rq_aligned(struct request_queue *q, void *addr,
+static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
 				 unsigned int len)
 {
 	unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
-	return !((unsigned long)addr & alignment) && !(len & alignment);
+	return !(addr & alignment) && !(len & alignment);
 }
 
 /* assumes size > 256 */
@@ -1127,6 +1078,7 @@
 
 struct work_struct;
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
+int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay);
 
 #ifdef CONFIG_BLK_CGROUP
 /*
@@ -1170,6 +1122,24 @@
 }
 #endif
 
+#ifdef CONFIG_BLK_DEV_THROTTLING
+extern int blk_throtl_init(struct request_queue *q);
+extern void blk_throtl_exit(struct request_queue *q);
+extern int blk_throtl_bio(struct request_queue *q, struct bio **bio);
+extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay);
+extern void throtl_shutdown_timer_wq(struct request_queue *q);
+#else /* CONFIG_BLK_DEV_THROTTLING */
+static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio)
+{
+	return 0;
+}
+
+static inline int blk_throtl_init(struct request_queue *q) { return 0; }
+static inline int blk_throtl_exit(struct request_queue *q) { return 0; }
+static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {}
+static inline void throtl_shutdown_timer_wq(struct request_queue *q) {}
+#endif /* CONFIG_BLK_DEV_THROTTLING */
+
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
@@ -1213,8 +1183,13 @@
 extern int blk_integrity_register(struct gendisk *, struct blk_integrity *);
 extern void blk_integrity_unregister(struct gendisk *);
 extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
-extern int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
-extern int blk_rq_count_integrity_sg(struct request *);
+extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
+				   struct scatterlist *);
+extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
+extern int blk_integrity_merge_rq(struct request_queue *, struct request *,
+				  struct request *);
+extern int blk_integrity_merge_bio(struct request_queue *, struct request *,
+				   struct bio *);
 
 static inline
 struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
@@ -1235,16 +1210,32 @@
 	return bio_integrity(rq->bio);
 }
 
+static inline void blk_queue_max_integrity_segments(struct request_queue *q,
+						    unsigned int segs)
+{
+	q->limits.max_integrity_segments = segs;
+}
+
+static inline unsigned short
+queue_max_integrity_segments(struct request_queue *q)
+{
+	return q->limits.max_integrity_segments;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 #define blk_integrity_rq(rq)			(0)
-#define blk_rq_count_integrity_sg(a)		(0)
-#define blk_rq_map_integrity_sg(a, b)		(0)
+#define blk_rq_count_integrity_sg(a, b)		(0)
+#define blk_rq_map_integrity_sg(a, b, c)	(0)
 #define bdev_get_integrity(a)			(0)
 #define blk_get_integrity(a)			(0)
 #define blk_integrity_compare(a, b)		(0)
 #define blk_integrity_register(a, b)		(0)
 #define blk_integrity_unregister(a)		do { } while (0);
+#define blk_queue_max_integrity_segments(a, b)	do { } while (0);
+#define queue_max_integrity_segments(a)		(0)
+#define blk_integrity_merge_rq(a, b, c)		(0)
+#define blk_integrity_merge_bio(a, b, c)	(0)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index ec94c12..dd1b25b 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -32,7 +32,6 @@
 	BH_Delay,	/* Buffer is not yet allocated on disk */
 	BH_Boundary,	/* Block is followed by a discontiguity */
 	BH_Write_EIO,	/* I/O error on write */
-	BH_Eopnotsupp,	/* operation not supported (barrier) */
 	BH_Unwritten,	/* Buffer is allocated on disk but not written */
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 
@@ -124,7 +123,6 @@
 BUFFER_FNS(Delay, delay)
 BUFFER_FNS(Boundary, boundary)
 BUFFER_FNS(Write_EIO, write_io_error)
-BUFFER_FNS(Eopnotsupp, eopnotsupp)
 BUFFER_FNS(Unwritten, unwritten)
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
diff --git a/fs/ceph/auth.h b/include/linux/ceph/auth.h
similarity index 97%
rename from fs/ceph/auth.h
rename to include/linux/ceph/auth.h
index d38a2fb..7fff521 100644
--- a/fs/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -1,8 +1,8 @@
 #ifndef _FS_CEPH_AUTH_H
 #define _FS_CEPH_AUTH_H
 
-#include "types.h"
-#include "buffer.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/buffer.h>
 
 /*
  * Abstract interface for communicating with the authenticate module.
diff --git a/fs/ceph/buffer.h b/include/linux/ceph/buffer.h
similarity index 100%
rename from fs/ceph/buffer.h
rename to include/linux/ceph/buffer.h
diff --git a/fs/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h
similarity index 86%
rename from fs/ceph/ceph_debug.h
rename to include/linux/ceph/ceph_debug.h
index 1818c23..aa2e191 100644
--- a/fs/ceph/ceph_debug.h
+++ b/include/linux/ceph/ceph_debug.h
@@ -3,7 +3,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#ifdef CONFIG_CEPH_FS_PRETTYDEBUG
+#ifdef CONFIG_CEPH_LIB_PRETTYDEBUG
 
 /*
  * wrap pr_debug to include a filename:lineno prefix on each line.
@@ -14,7 +14,8 @@
 # if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
 extern const char *ceph_file_part(const char *s, int len);
 #  define dout(fmt, ...)						\
-	pr_debug(" %12.12s:%-4d : " fmt,				\
+	pr_debug("%.*s %12.12s:%-4d : " fmt,				\
+		 8 - (int)sizeof(KBUILD_MODNAME), "    ",		\
 		 ceph_file_part(__FILE__, sizeof(__FILE__)),		\
 		 __LINE__, ##__VA_ARGS__)
 # else
diff --git a/fs/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h
similarity index 100%
rename from fs/ceph/ceph_frag.h
rename to include/linux/ceph/ceph_frag.h
diff --git a/fs/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
similarity index 99%
rename from fs/ceph/ceph_fs.h
rename to include/linux/ceph/ceph_fs.h
index d5619ac..c3c74ae 100644
--- a/fs/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -299,6 +299,7 @@
 	CEPH_MDS_OP_SETATTR    = 0x01108,
 	CEPH_MDS_OP_SETFILELOCK= 0x01109,
 	CEPH_MDS_OP_GETFILELOCK= 0x00110,
+	CEPH_MDS_OP_SETDIRLAYOUT=0x0110a,
 
 	CEPH_MDS_OP_MKNOD      = 0x01201,
 	CEPH_MDS_OP_LINK       = 0x01202,
diff --git a/fs/ceph/ceph_hash.h b/include/linux/ceph/ceph_hash.h
similarity index 100%
rename from fs/ceph/ceph_hash.h
rename to include/linux/ceph/ceph_hash.h
diff --git a/include/linux/ceph/debugfs.h b/include/linux/ceph/debugfs.h
new file mode 100644
index 0000000..2a79702
--- /dev/null
+++ b/include/linux/ceph/debugfs.h
@@ -0,0 +1,33 @@
+#ifndef _FS_CEPH_DEBUGFS_H
+#define _FS_CEPH_DEBUGFS_H
+
+#include "ceph_debug.h"
+#include "types.h"
+
+#define CEPH_DEFINE_SHOW_FUNC(name)					\
+static int name##_open(struct inode *inode, struct file *file)		\
+{									\
+	struct seq_file *sf;						\
+	int ret;							\
+									\
+	ret = single_open(file, name, NULL);				\
+	sf = file->private_data;					\
+	sf->private = inode->i_private;					\
+	return ret;							\
+}									\
+									\
+static const struct file_operations name##_fops = {			\
+	.open		= name##_open,					\
+	.read		= seq_read,					\
+	.llseek		= seq_lseek,					\
+	.release	= single_release,				\
+};
+
+/* debugfs.c */
+extern int ceph_debugfs_init(void);
+extern void ceph_debugfs_cleanup(void);
+extern int ceph_debugfs_client_init(struct ceph_client *client);
+extern void ceph_debugfs_client_cleanup(struct ceph_client *client);
+
+#endif
+
diff --git a/fs/ceph/decode.h b/include/linux/ceph/decode.h
similarity index 96%
rename from fs/ceph/decode.h
rename to include/linux/ceph/decode.h
index 3d25415..c5b6939 100644
--- a/fs/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -191,6 +191,11 @@
 		ceph_encode_need(p, end, n, bad);		\
 		ceph_encode_copy(p, pv, n);			\
 	} while (0)
+#define ceph_encode_string_safe(p, end, s, n, bad)		\
+	do {							\
+		ceph_encode_need(p, end, n, bad);		\
+		ceph_encode_string(p, end, s, n);		\
+	} while (0)
 
 
 #endif
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
new file mode 100644
index 0000000..f22b2e9
--- /dev/null
+++ b/include/linux/ceph/libceph.h
@@ -0,0 +1,249 @@
+#ifndef _FS_CEPH_LIBCEPH_H
+#define _FS_CEPH_LIBCEPH_H
+
+#include "ceph_debug.h"
+
+#include <asm/unaligned.h>
+#include <linux/backing-dev.h>
+#include <linux/completion.h>
+#include <linux/exportfs.h>
+#include <linux/fs.h>
+#include <linux/mempool.h>
+#include <linux/pagemap.h>
+#include <linux/wait.h>
+#include <linux/writeback.h>
+#include <linux/slab.h>
+
+#include "types.h"
+#include "messenger.h"
+#include "msgpool.h"
+#include "mon_client.h"
+#include "osd_client.h"
+#include "ceph_fs.h"
+
+/*
+ * Supported features
+ */
+#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR
+#define CEPH_FEATURE_REQUIRED_DEFAULT  CEPH_FEATURE_NOSRCADDR
+
+/*
+ * mount options
+ */
+#define CEPH_OPT_FSID             (1<<0)
+#define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
+#define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
+#define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes */
+
+#define CEPH_OPT_DEFAULT   (0);
+
+#define ceph_set_opt(client, opt) \
+	(client)->options->flags |= CEPH_OPT_##opt;
+#define ceph_test_opt(client, opt) \
+	(!!((client)->options->flags & CEPH_OPT_##opt))
+
+struct ceph_options {
+	int flags;
+	struct ceph_fsid fsid;
+	struct ceph_entity_addr my_addr;
+	int mount_timeout;
+	int osd_idle_ttl;
+	int osd_timeout;
+	int osd_keepalive_timeout;
+
+	/*
+	 * any type that can't be simply compared or doesn't need need
+	 * to be compared should go beyond this point,
+	 * ceph_compare_options() should be updated accordingly
+	 */
+
+	struct ceph_entity_addr *mon_addr; /* should be the first
+					      pointer type of args */
+	int num_mon;
+	char *name;
+	char *secret;
+};
+
+/*
+ * defaults
+ */
+#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
+#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
+#define CEPH_OSD_KEEPALIVE_DEFAULT  5
+#define CEPH_OSD_IDLE_TTL_DEFAULT    60
+#define CEPH_MOUNT_RSIZE_DEFAULT    (512*1024) /* readahead */
+
+#define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
+#define CEPH_MSG_MAX_DATA_LEN	(16*1024*1024)
+
+#define CEPH_AUTH_NAME_DEFAULT   "guest"
+
+/*
+ * Delay telling the MDS we no longer want caps, in case we reopen
+ * the file.  Delay a minimum amount of time, even if we send a cap
+ * message for some other reason.  Otherwise, take the oppotunity to
+ * update the mds to avoid sending another message later.
+ */
+#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
+#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */
+
+#define CEPH_CAP_RELEASE_SAFETY_DEFAULT        (CEPH_CAPS_PER_RELEASE * 4)
+
+/* mount state */
+enum {
+	CEPH_MOUNT_MOUNTING,
+	CEPH_MOUNT_MOUNTED,
+	CEPH_MOUNT_UNMOUNTING,
+	CEPH_MOUNT_UNMOUNTED,
+	CEPH_MOUNT_SHUTDOWN,
+};
+
+/*
+ * subtract jiffies
+ */
+static inline unsigned long time_sub(unsigned long a, unsigned long b)
+{
+	BUG_ON(time_after(b, a));
+	return (long)a - (long)b;
+}
+
+struct ceph_mds_client;
+
+/*
+ * per client state
+ *
+ * possibly shared by multiple mount points, if they are
+ * mounting the same ceph filesystem/cluster.
+ */
+struct ceph_client {
+	struct ceph_fsid fsid;
+	bool have_fsid;
+
+	void *private;
+
+	struct ceph_options *options;
+
+	struct mutex mount_mutex;      /* serialize mount attempts */
+	wait_queue_head_t auth_wq;
+	int auth_err;
+
+	int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *);
+
+	u32 supported_features;
+	u32 required_features;
+
+	struct ceph_messenger *msgr;   /* messenger instance */
+	struct ceph_mon_client monc;
+	struct ceph_osd_client osdc;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs_dir;
+	struct dentry *debugfs_monmap;
+	struct dentry *debugfs_osdmap;
+#endif
+};
+
+
+
+/*
+ * snapshots
+ */
+
+/*
+ * A "snap context" is the set of existing snapshots when we
+ * write data.  It is used by the OSD to guide its COW behavior.
+ *
+ * The ceph_snap_context is refcounted, and attached to each dirty
+ * page, indicating which context the dirty data belonged when it was
+ * dirtied.
+ */
+struct ceph_snap_context {
+	atomic_t nref;
+	u64 seq;
+	int num_snaps;
+	u64 snaps[];
+};
+
+static inline struct ceph_snap_context *
+ceph_get_snap_context(struct ceph_snap_context *sc)
+{
+	/*
+	printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+	       atomic_read(&sc->nref)+1);
+	*/
+	if (sc)
+		atomic_inc(&sc->nref);
+	return sc;
+}
+
+static inline void ceph_put_snap_context(struct ceph_snap_context *sc)
+{
+	if (!sc)
+		return;
+	/*
+	printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+	       atomic_read(&sc->nref)-1);
+	*/
+	if (atomic_dec_and_test(&sc->nref)) {
+		/*printk(" deleting snap_context %p\n", sc);*/
+		kfree(sc);
+	}
+}
+
+/*
+ * calculate the number of pages a given length and offset map onto,
+ * if we align the data.
+ */
+static inline int calc_pages_for(u64 off, u64 len)
+{
+	return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
+		(off >> PAGE_CACHE_SHIFT);
+}
+
+/* ceph_common.c */
+extern const char *ceph_msg_type_name(int type);
+extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
+extern struct kmem_cache *ceph_inode_cachep;
+extern struct kmem_cache *ceph_cap_cachep;
+extern struct kmem_cache *ceph_dentry_cachep;
+extern struct kmem_cache *ceph_file_cachep;
+
+extern int ceph_parse_options(struct ceph_options **popt, char *options,
+			      const char *dev_name, const char *dev_name_end,
+			      int (*parse_extra_token)(char *c, void *private),
+			      void *private);
+extern void ceph_destroy_options(struct ceph_options *opt);
+extern int ceph_compare_options(struct ceph_options *new_opt,
+				struct ceph_client *client);
+extern struct ceph_client *ceph_create_client(struct ceph_options *opt,
+					      void *private);
+extern u64 ceph_client_id(struct ceph_client *client);
+extern void ceph_destroy_client(struct ceph_client *client);
+extern int __ceph_open_session(struct ceph_client *client,
+			       unsigned long started);
+extern int ceph_open_session(struct ceph_client *client);
+
+/* pagevec.c */
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+
+extern struct page **ceph_get_direct_page_vector(const char __user *data,
+					    int num_pages,
+					    loff_t off, size_t len);
+extern void ceph_put_page_vector(struct page **pages, int num_pages);
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
+extern int ceph_copy_user_to_page_vector(struct page **pages,
+					 const char __user *data,
+					 loff_t off, size_t len);
+extern int ceph_copy_to_page_vector(struct page **pages,
+				    const char *data,
+				    loff_t off, size_t len);
+extern int ceph_copy_from_page_vector(struct page **pages,
+				    char *data,
+				    loff_t off, size_t len);
+extern int ceph_copy_page_vector_to_user(struct page **pages, char __user *data,
+				    loff_t off, size_t len);
+extern void ceph_zero_page_vector_range(int off, int len, struct page **pages);
+
+
+#endif /* _FS_CEPH_SUPER_H */
diff --git a/fs/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
similarity index 100%
rename from fs/ceph/mdsmap.h
rename to include/linux/ceph/mdsmap.h
diff --git a/fs/ceph/messenger.h b/include/linux/ceph/messenger.h
similarity index 95%
rename from fs/ceph/messenger.h
rename to include/linux/ceph/messenger.h
index 76fbc95..5956d62 100644
--- a/fs/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -65,6 +65,9 @@
 	 */
 	u32 global_seq;
 	spinlock_t global_seq_lock;
+
+	u32 supported_features;
+	u32 required_features;
 };
 
 /*
@@ -82,6 +85,10 @@
 	struct ceph_pagelist *pagelist; /* instead of pages */
 	struct list_head list_head;
 	struct kref kref;
+	struct bio  *bio;		/* instead of pages/pagelist */
+	struct bio  *bio_iter;		/* bio iterator */
+	int bio_seg;			/* current bio segment */
+	struct ceph_pagelist *trail;	/* the trailing part of the data */
 	bool front_is_vmalloc;
 	bool more_to_follow;
 	bool needs_out_seq;
@@ -205,7 +212,7 @@
 };
 
 
-extern const char *pr_addr(const struct sockaddr_storage *ss);
+extern const char *ceph_pr_addr(const struct sockaddr_storage *ss);
 extern int ceph_parse_ips(const char *c, const char *end,
 			  struct ceph_entity_addr *addr,
 			  int max_count, int *count);
@@ -216,7 +223,8 @@
 extern void ceph_msgr_flush(void);
 
 extern struct ceph_messenger *ceph_messenger_create(
-	struct ceph_entity_addr *myaddr);
+	struct ceph_entity_addr *myaddr,
+	u32 features, u32 required);
 extern void ceph_messenger_destroy(struct ceph_messenger *);
 
 extern void ceph_con_init(struct ceph_messenger *msgr,
diff --git a/fs/ceph/mon_client.h b/include/linux/ceph/mon_client.h
similarity index 99%
rename from fs/ceph/mon_client.h
rename to include/linux/ceph/mon_client.h
index 8e396f2..545f859 100644
--- a/fs/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -79,6 +79,7 @@
 	u64 last_tid;
 
 	/* mds/osd map */
+	int want_mdsmap;
 	int want_next_osdmap; /* 1 = want, 2 = want+asked */
 	u32 have_osdmap, have_mdsmap;
 
diff --git a/fs/ceph/msgpool.h b/include/linux/ceph/msgpool.h
similarity index 100%
rename from fs/ceph/msgpool.h
rename to include/linux/ceph/msgpool.h
diff --git a/fs/ceph/msgr.h b/include/linux/ceph/msgr.h
similarity index 100%
rename from fs/ceph/msgr.h
rename to include/linux/ceph/msgr.h
diff --git a/fs/ceph/osd_client.h b/include/linux/ceph/osd_client.h
similarity index 75%
rename from fs/ceph/osd_client.h
rename to include/linux/ceph/osd_client.h
index ce77698..6c91fb0 100644
--- a/fs/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -15,6 +15,7 @@
 struct ceph_osd_request;
 struct ceph_osd_client;
 struct ceph_authorizer;
+struct ceph_pagelist;
 
 /*
  * completion callback for async writepages
@@ -68,6 +69,7 @@
 	struct list_head  r_unsafe_item;
 
 	struct inode *r_inode;         	      /* for use by callbacks */
+	void *r_priv;			      /* ditto */
 
 	char              r_oid[40];          /* object name */
 	int               r_oid_len;
@@ -80,6 +82,11 @@
 	struct page     **r_pages;            /* pages for data payload */
 	int               r_pages_from_pool;
 	int               r_own_pages;        /* if true, i own page list */
+#ifdef CONFIG_BLOCK
+	struct bio       *r_bio;	      /* instead of pages */
+#endif
+
+	struct ceph_pagelist *r_trail;	      /* trailing part of the data */
 };
 
 struct ceph_osd_client {
@@ -110,6 +117,42 @@
 	struct ceph_msgpool	msgpool_op_reply;
 };
 
+struct ceph_osd_req_op {
+	u16 op;           /* CEPH_OSD_OP_* */
+	u32 flags;        /* CEPH_OSD_FLAG_* */
+	union {
+		struct {
+			u64 offset, length;
+			u64 truncate_size;
+			u32 truncate_seq;
+		} extent;
+		struct {
+			const char *name;
+			u32 name_len;
+			const char  *val;
+			u32 value_len;
+			__u8 cmp_op;       /* CEPH_OSD_CMPXATTR_OP_* */
+			__u8 cmp_mode;     /* CEPH_OSD_CMPXATTR_MODE_* */
+		} xattr;
+		struct {
+			const char *class_name;
+			__u8 class_len;
+			const char *method_name;
+			__u8 method_len;
+			__u8 argc;
+			const char *indata;
+			u32 indata_len;
+		} cls;
+		struct {
+			u64 cookie, count;
+		} pgls;
+	        struct {
+		        u64 snapid;
+	        } snap;
+	};
+	u32 payload_len;
+};
+
 extern int ceph_osdc_init(struct ceph_osd_client *osdc,
 			  struct ceph_client *client);
 extern void ceph_osdc_stop(struct ceph_osd_client *osdc);
@@ -119,6 +162,30 @@
 extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
 				 struct ceph_msg *msg);
 
+extern void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+			struct ceph_file_layout *layout,
+			u64 snapid,
+			u64 off, u64 *plen, u64 *bno,
+			struct ceph_osd_request *req,
+			struct ceph_osd_req_op *op);
+
+extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+					       int flags,
+					       struct ceph_snap_context *snapc,
+					       struct ceph_osd_req_op *ops,
+					       bool use_mempool,
+					       gfp_t gfp_flags,
+					       struct page **pages,
+					       struct bio *bio);
+
+extern void ceph_osdc_build_request(struct ceph_osd_request *req,
+				    u64 off, u64 *plen,
+				    struct ceph_osd_req_op *src_ops,
+				    struct ceph_snap_context *snapc,
+				    struct timespec *mtime,
+				    const char *oid,
+				    int oid_len);
+
 extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
 				      struct ceph_file_layout *layout,
 				      struct ceph_vino vino,
diff --git a/fs/ceph/osdmap.h b/include/linux/ceph/osdmap.h
similarity index 96%
rename from fs/ceph/osdmap.h
rename to include/linux/ceph/osdmap.h
index 970b547..ba4c205 100644
--- a/fs/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -4,7 +4,7 @@
 #include <linux/rbtree.h>
 #include "types.h"
 #include "ceph_fs.h"
-#include "crush/crush.h"
+#include <linux/crush/crush.h>
 
 /*
  * The osd map describes the current membership of the osd cluster and
@@ -125,4 +125,6 @@
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
 				struct ceph_pg pgid);
 
+extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
+
 #endif
diff --git a/fs/ceph/pagelist.h b/include/linux/ceph/pagelist.h
similarity index 62%
rename from fs/ceph/pagelist.h
rename to include/linux/ceph/pagelist.h
index e8a4187..9660d6b 100644
--- a/fs/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -8,6 +8,14 @@
 	void *mapped_tail;
 	size_t length;
 	size_t room;
+	struct list_head free_list;
+	size_t num_pages_free;
+};
+
+struct ceph_pagelist_cursor {
+	struct ceph_pagelist *pl;   /* pagelist, for error checking */
+	struct list_head *page_lru; /* page in list */
+	size_t room;		    /* room remaining to reset to */
 };
 
 static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
@@ -16,10 +24,23 @@
 	pl->mapped_tail = NULL;
 	pl->length = 0;
 	pl->room = 0;
+	INIT_LIST_HEAD(&pl->free_list);
+	pl->num_pages_free = 0;
 }
+
 extern int ceph_pagelist_release(struct ceph_pagelist *pl);
 
-extern int ceph_pagelist_append(struct ceph_pagelist *pl, void *d, size_t l);
+extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l);
+
+extern int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space);
+
+extern int ceph_pagelist_free_reserve(struct ceph_pagelist *pl);
+
+extern void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
+				     struct ceph_pagelist_cursor *c);
+
+extern int ceph_pagelist_truncate(struct ceph_pagelist *pl,
+				  struct ceph_pagelist_cursor *c);
 
 static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v)
 {
diff --git a/fs/ceph/rados.h b/include/linux/ceph/rados.h
similarity index 100%
rename from fs/ceph/rados.h
rename to include/linux/ceph/rados.h
diff --git a/fs/ceph/types.h b/include/linux/ceph/types.h
similarity index 100%
rename from fs/ceph/types.h
rename to include/linux/ceph/types.h
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0c99102..709dfb9 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -75,7 +75,7 @@
 
 	unsigned long flags;
 	/* ID for this css, if possible */
-	struct css_id *id;
+	struct css_id __rcu *id;
 };
 
 /* bits in struct cgroup_subsys_state flags field */
@@ -205,7 +205,7 @@
 	struct list_head children;	/* my children */
 
 	struct cgroup *parent;		/* my parent */
-	struct dentry *dentry;	  	/* cgroup fs entry, RCU protected */
+	struct dentry __rcu *dentry;	/* cgroup fs entry, RCU protected */
 
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index c1a62c5..320d6c9 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -16,7 +16,11 @@
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
 # define __percpu	__attribute__((noderef, address_space(3)))
+#ifdef CONFIG_SPARSE_RCU_POINTER
+# define __rcu		__attribute__((noderef, address_space(4)))
+#else
 # define __rcu
+#endif
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
 #else
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 4d2c395..4aaeab3 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -84,7 +84,7 @@
 	atomic_t	usage;
 	pid_t		tgid;			/* thread group process ID */
 	spinlock_t	lock;
-	struct key	*session_keyring;	/* keyring inherited over fork */
+	struct key __rcu *session_keyring;	/* keyring inherited over fork */
 	struct key	*process_keyring;	/* keyring private to this process */
 	struct rcu_head	rcu;			/* RCU deletion hook */
 };
diff --git a/fs/ceph/crush/crush.h b/include/linux/crush/crush.h
similarity index 100%
rename from fs/ceph/crush/crush.h
rename to include/linux/crush/crush.h
diff --git a/fs/ceph/crush/hash.h b/include/linux/crush/hash.h
similarity index 100%
rename from fs/ceph/crush/hash.h
rename to include/linux/crush/hash.h
diff --git a/fs/ceph/crush/mapper.h b/include/linux/crush/mapper.h
similarity index 100%
rename from fs/ceph/crush/mapper.h
rename to include/linux/crush/mapper.h
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 29b3ce3..2833452 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -49,7 +49,6 @@
 
 #ifdef CONFIG_LOCKDEP
 extern void debug_show_all_locks(void);
-extern void __debug_show_held_locks(struct task_struct *task);
 extern void debug_show_held_locks(struct task_struct *task);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
 extern void debug_check_no_locks_held(struct task_struct *task);
@@ -58,10 +57,6 @@
 {
 }
 
-static inline void __debug_show_held_locks(struct task_struct *task)
-{
-}
-
 static inline void debug_show_held_locks(struct task_struct *task)
 {
 }
diff --git a/include/linux/dlm.h b/include/linux/dlm.h
index 0b3518c..d4e02f5 100644
--- a/include/linux/dlm.h
+++ b/include/linux/dlm.h
@@ -48,10 +48,10 @@
  *
  * 0 if lock request was successful
  * -EAGAIN if request would block and is flagged DLM_LKF_NOQUEUE
- * -ENOMEM if there is no memory to process request
- * -EINVAL if there are invalid parameters
  * -DLM_EUNLOCK if unlock request was successful
  * -DLM_ECANCEL if a cancel completed successfully
+ * -EDEADLK if a deadlock was detected
+ * -ETIMEDOUT if the lock request was canceled due to a timeout
  */
 
 #define DLM_SBF_DEMOTED		0x01
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index d7cecc9..a7d9dc2 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -57,15 +57,15 @@
 extern int dmar_dev_scope_init(void);
 
 /* Intel IOMMU detection */
-extern void detect_intel_iommu(void);
+extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 
 extern int parse_ioapics_under_ir(void);
 extern int alloc_iommu(struct dmar_drhd_unit *);
 #else
-static inline void detect_intel_iommu(void)
+static inline int detect_intel_iommu(void)
 {
-	return;
+	return -ENODEV;
 }
 
 static inline int dmar_table_init(void)
@@ -106,6 +106,7 @@
 		__u64 high;
 	};
 };
+
 #ifdef CONFIG_INTR_REMAP
 extern int intr_remapping_enabled;
 extern int intr_remapping_supported(void);
@@ -119,11 +120,8 @@
 extern int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index,
    			u16 sub_handle);
 extern int map_irq_to_irte_handle(int irq, u16 *sub_handle);
-extern int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index);
-extern int flush_irte(int irq);
 extern int free_irte(int irq);
 
-extern int irq_remapped(int irq);
 extern struct intel_iommu *map_dev_to_ir(struct pci_dev *dev);
 extern struct intel_iommu *map_ioapic_to_ir(int apic);
 extern struct intel_iommu *map_hpet_to_ir(u8 id);
@@ -177,7 +175,6 @@
 	return 0;
 }
 
-#define irq_remapped(irq)		(0)
 #define enable_intr_remapping(mode)	(-1)
 #define disable_intr_remapping()	(0)
 #define reenable_intr_remapping(mode)	(0)
@@ -187,8 +184,9 @@
 /* Can't use the common MSI interrupt functions
  * since DMAR is not a pci device
  */
-extern void dmar_msi_unmask(unsigned int irq);
-extern void dmar_msi_mask(unsigned int irq);
+struct irq_data;
+extern void dmar_msi_unmask(struct irq_data *data);
+extern void dmar_msi_mask(struct irq_data *data);
 extern void dmar_msi_read(int irq, struct msi_msg *msg);
 extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 479ee3a..9b2a015 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -53,10 +53,10 @@
 
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.3.8.1"
+#define REL_VERSION "8.3.9rc2"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
-#define PRO_VERSION_MAX 94
+#define PRO_VERSION_MAX 95
 
 
 enum drbd_io_error_p {
@@ -91,6 +91,11 @@
 	ASB_VIOLENTLY
 };
 
+enum drbd_on_no_data {
+	OND_IO_ERROR,
+	OND_SUSPEND_IO
+};
+
 /* KEEP the order, do not delete or insert. Only append. */
 enum drbd_ret_codes {
 	ERR_CODE_BASE		= 100,
@@ -140,6 +145,7 @@
 	ERR_CONNECTED		= 151, /* DRBD 8.3 only */
 	ERR_PERM		= 152,
 	ERR_NEED_APV_93		= 153,
+	ERR_STONITH_AND_PROT_A  = 154,
 
 	/* insert new ones above this line */
 	AFTER_LAST_ERR_CODE
@@ -226,13 +232,17 @@
 		unsigned conn:5 ;   /* 17/32	 cstates */
 		unsigned disk:4 ;   /* 8/16	 from D_DISKLESS to D_UP_TO_DATE */
 		unsigned pdsk:4 ;   /* 8/16	 from D_DISKLESS to D_UP_TO_DATE */
-		unsigned susp:1 ;   /* 2/2	 IO suspended  no/yes */
+		unsigned susp:1 ;   /* 2/2	 IO suspended no/yes (by user) */
 		unsigned aftr_isp:1 ; /* isp .. imposed sync pause */
 		unsigned peer_isp:1 ;
 		unsigned user_isp:1 ;
-		unsigned _pad:11;   /* 0	 unused */
+		unsigned susp_nod:1 ; /* IO suspended because no data */
+		unsigned susp_fen:1 ; /* IO suspended because fence peer handler runs*/
+		unsigned _pad:9;   /* 0	 unused */
 #elif defined(__BIG_ENDIAN_BITFIELD)
-		unsigned _pad:11;   /* 0	 unused */
+		unsigned _pad:9;
+		unsigned susp_fen:1 ;
+		unsigned susp_nod:1 ;
 		unsigned user_isp:1 ;
 		unsigned peer_isp:1 ;
 		unsigned aftr_isp:1 ; /* isp .. imposed sync pause */
@@ -312,6 +322,8 @@
 
 #define DRBD_MAGIC 0x83740267
 #define BE_DRBD_MAGIC __constant_cpu_to_be32(DRBD_MAGIC)
+#define DRBD_MAGIC_BIG 0x835a
+#define BE_DRBD_MAGIC_BIG __constant_cpu_to_be16(DRBD_MAGIC_BIG)
 
 /* these are of type "int" */
 #define DRBD_MD_INDEX_INTERNAL -1
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 440b42e..4ac33f3 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -128,26 +128,31 @@
 #define DRBD_AFTER_SB_1P_DEF ASB_DISCONNECT
 #define DRBD_AFTER_SB_2P_DEF ASB_DISCONNECT
 #define DRBD_RR_CONFLICT_DEF ASB_DISCONNECT
+#define DRBD_ON_NO_DATA_DEF OND_IO_ERROR
 
 #define DRBD_MAX_BIO_BVECS_MIN 0
 #define DRBD_MAX_BIO_BVECS_MAX 128
 #define DRBD_MAX_BIO_BVECS_DEF 0
 
-#define DRBD_DP_VOLUME_MIN 4
-#define DRBD_DP_VOLUME_MAX 1048576
-#define DRBD_DP_VOLUME_DEF 16384
+#define DRBD_C_PLAN_AHEAD_MIN  0
+#define DRBD_C_PLAN_AHEAD_MAX  300
+#define DRBD_C_PLAN_AHEAD_DEF  0 /* RS rate controller disabled by default */
 
-#define DRBD_DP_INTERVAL_MIN 1
-#define DRBD_DP_INTERVAL_MAX 600
-#define DRBD_DP_INTERVAL_DEF 5
+#define DRBD_C_DELAY_TARGET_MIN 1
+#define DRBD_C_DELAY_TARGET_MAX 100
+#define DRBD_C_DELAY_TARGET_DEF 10
 
-#define DRBD_RS_THROTTLE_TH_MIN 1
-#define DRBD_RS_THROTTLE_TH_MAX 600
-#define DRBD_RS_THROTTLE_TH_DEF 20
+#define DRBD_C_FILL_TARGET_MIN 0
+#define DRBD_C_FILL_TARGET_MAX (1<<20) /* 500MByte in sec */
+#define DRBD_C_FILL_TARGET_DEF 0 /* By default disabled -> controlled by delay_target */
 
-#define DRBD_RS_HOLD_OFF_TH_MIN 1
-#define DRBD_RS_HOLD_OFF_TH_MAX 6000
-#define DRBD_RS_HOLD_OFF_TH_DEF 100
+#define DRBD_C_MAX_RATE_MIN     250 /* kByte/sec */
+#define DRBD_C_MAX_RATE_MAX     (4 << 20)
+#define DRBD_C_MAX_RATE_DEF     102400
+
+#define DRBD_C_MIN_RATE_MIN     0 /* kByte/sec */
+#define DRBD_C_MIN_RATE_MAX     (4 << 20)
+#define DRBD_C_MIN_RATE_DEF     4096
 
 #undef RANGE
 #endif
diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h
index 5f04281..ade9110 100644
--- a/include/linux/drbd_nl.h
+++ b/include/linux/drbd_nl.h
@@ -87,6 +87,12 @@
 	NL_STRING(      51,     T_MAY_IGNORE,   cpu_mask,       32)
 	NL_STRING(	64,	T_MAY_IGNORE,	csums_alg,	SHARED_SECRET_MAX)
 	NL_BIT(         65,     T_MAY_IGNORE,   use_rle)
+	NL_INTEGER(	75,	T_MAY_IGNORE,	on_no_data)
+	NL_INTEGER(	76,	T_MAY_IGNORE,	c_plan_ahead)
+	NL_INTEGER(     77,	T_MAY_IGNORE,	c_delay_target)
+	NL_INTEGER(     78,	T_MAY_IGNORE,	c_fill_target)
+	NL_INTEGER(     79,	T_MAY_IGNORE,	c_max_rate)
+	NL_INTEGER(     80,	T_MAY_IGNORE,	c_min_rate)
 )
 
 NL_PACKET(invalidate, 9, )
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 52c0da4..a90b389 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -1,6 +1,8 @@
 #ifndef _DYNAMIC_DEBUG_H
 #define _DYNAMIC_DEBUG_H
 
+#include <linux/jump_label.h>
+
 /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which
  * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They
  * use independent hash functions, to reduce the chance of false positives.
@@ -22,8 +24,6 @@
 	const char *function;
 	const char *filename;
 	const char *format;
-	char primary_hash;
-	char secondary_hash;
 	unsigned int lineno:24;
 	/*
  	 * The flags field controls the behaviour at the callsite.
@@ -33,6 +33,7 @@
 #define _DPRINTK_FLAGS_PRINT   (1<<0)  /* printk() a message using the format */
 #define _DPRINTK_FLAGS_DEFAULT 0
 	unsigned int flags:8;
+	char enabled;
 } __attribute__((aligned(8)));
 
 
@@ -42,33 +43,35 @@
 #if defined(CONFIG_DYNAMIC_DEBUG)
 extern int ddebug_remove_module(const char *mod_name);
 
-#define __dynamic_dbg_enabled(dd)  ({	     \
-	int __ret = 0;							     \
-	if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) &&	     \
-			(dynamic_debug_enabled2 & (1LL << DEBUG_HASH2))))   \
-				if (unlikely(dd.flags))			     \
-					__ret = 1;			     \
-	__ret; })
-
 #define dynamic_pr_debug(fmt, ...) do {					\
+	__label__ do_printk;						\
+	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
-	{ KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH,	\
-		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
-	if (__dynamic_dbg_enabled(descriptor))				\
-		printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);		\
+	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
+		_DPRINTK_FLAGS_DEFAULT };				\
+	JUMP_LABEL(&descriptor.enabled, do_printk);			\
+	goto out;							\
+do_printk:								\
+	printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);			\
+out:	;								\
 	} while (0)
 
 
 #define dynamic_dev_dbg(dev, fmt, ...) do {				\
+	__label__ do_printk;						\
+	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
-	{ KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH,	\
-		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
-	if (__dynamic_dbg_enabled(descriptor))				\
-		dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);	\
+	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
+		_DPRINTK_FLAGS_DEFAULT };				\
+	JUMP_LABEL(&descriptor.enabled, do_printk);			\
+	goto out;							\
+do_printk:								\
+	dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);		\
+out:	;								\
 	} while (0)
 
 #else
@@ -80,7 +83,7 @@
 
 #define dynamic_pr_debug(fmt, ...)					\
 	do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0)
-#define dynamic_dev_dbg(dev, format, ...)				\
+#define dynamic_dev_dbg(dev, fmt, ...)					\
 	do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0)
 #endif
 
diff --git a/include/linux/early_res.h b/include/linux/early_res.h
deleted file mode 100644
index 29c09f5..0000000
--- a/include/linux/early_res.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _LINUX_EARLY_RES_H
-#define _LINUX_EARLY_RES_H
-#ifdef __KERNEL__
-
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-void free_early_partial(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
-
-void reserve_early_without_check(u64 start, u64 end, char *name);
-u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align);
-u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align);
-u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align);
-u64 get_max_mapped(void);
-#include <linux/range.h>
-int get_free_all_memory_range(struct range **rangep, int nodeid);
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_EARLY_RES_H */
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 7cf92e8..36c6644 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -13,6 +13,7 @@
 #define _LINUX_EDAC_H_
 
 #include <asm/atomic.h>
+#include <linux/sysdev.h>
 
 #define EDAC_OPSTATE_INVAL	-1
 #define EDAC_OPSTATE_POLL	0
@@ -22,9 +23,12 @@
 extern int edac_op_state;
 extern int edac_err_assert;
 extern atomic_t edac_handlers;
+extern struct sysdev_class edac_class;
 
 extern int edac_handler_set(void);
 extern void edac_atomic_assert_error(void);
+extern struct sysdev_class *edac_get_sysfs_class(void);
+extern void edac_put_sysfs_class(void);
 
 static inline void opstate_init(void)
 {
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 4fd978e..80a0ece 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -122,6 +122,8 @@
 extern int elv_set_request(struct request_queue *, struct request *, gfp_t);
 extern void elv_put_request(struct request_queue *, struct request *);
 extern void elv_drain_elevator(struct request_queue *);
+extern void elv_quiesce_start(struct request_queue *);
+extern void elv_quiesce_end(struct request_queue *);
 
 /*
  * io scheduler registration
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index f59ed29..133c0ba2 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -31,7 +31,7 @@
 
 struct fdtable {
 	unsigned int max_fds;
-	struct file ** fd;      /* current fd array */
+	struct file __rcu **fd;      /* current fd array */
 	fd_set *close_on_exec;
 	fd_set *open_fds;
 	struct rcu_head rcu;
@@ -46,7 +46,7 @@
    * read mostly part
    */
 	atomic_t count;
-	struct fdtable *fdt;
+	struct fdtable __rcu *fdt;
 	struct fdtable fdtab;
   /*
    * written part on a separate cache line in SMP
@@ -55,7 +55,7 @@
 	int next_fd;
 	struct embedded_fd_set close_on_exec_init;
 	struct embedded_fd_set open_fds_init;
-	struct file * fd_array[NR_OPEN_DEFAULT];
+	struct file __rcu * fd_array[NR_OPEN_DEFAULT];
 };
 
 #define rcu_dereference_check_fdtable(files, fdtfd) \
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 63d069b..4f34ff6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -135,12 +135,12 @@
  *			immediately after submission. The write equivalent
  *			of READ_SYNC.
  * WRITE_ODIRECT_PLUG	Special case write for O_DIRECT only.
- * WRITE_BARRIER	Like WRITE_SYNC, but tells the block layer that all
- *			previously submitted writes must be safely on storage
- *			before this one is started. Also guarantees that when
- *			this write is complete, it itself is also safely on
- *			storage. Prevents reordering of writes on both sides
- *			of this IO.
+ * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
+ * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
+ *			non-volatile media on completion.
+ * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA. The IO is preceded
+ *			by a cache flush and data is guaranteed to be on
+ *			non-volatile media on completion.
  *
  */
 #define RW_MASK			REQ_WRITE
@@ -156,16 +156,12 @@
 #define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
 #define WRITE_ODIRECT_PLUG	(WRITE | REQ_SYNC)
 #define WRITE_META		(WRITE | REQ_META)
-#define WRITE_BARRIER		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
-				 REQ_HARDBARRIER)
-
-/*
- * These aren't really reads or writes, they pass down information about
- * parts of device that are now unused by the file system.
- */
-#define DISCARD_NOBARRIER	(WRITE | REQ_DISCARD)
-#define DISCARD_BARRIER		(WRITE | REQ_DISCARD | REQ_HARDBARRIER)
-#define DISCARD_SECURE		(DISCARD_NOBARRIER | REQ_SECURE)
+#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH)
+#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FUA)
+#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH | REQ_FUA)
 
 #define SEL_IN		1
 #define SEL_OUT		2
@@ -1093,10 +1089,6 @@
 
 #include <linux/fcntl.h>
 
-/* temporary stubs for BKL removal */
-#define lock_flocks() lock_kernel()
-#define unlock_flocks() unlock_kernel()
-
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 #ifdef CONFIG_FILE_LOCKING
@@ -1135,6 +1127,8 @@
 extern int lease_modify(struct file_lock **, int);
 extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
 extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
+extern void lock_flocks(void);
+extern void unlock_flocks(void);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, struct flock __user *user)
 {
@@ -1277,6 +1271,14 @@
 	return 1;
 }
 
+static inline void lock_flocks(void)
+{
+}
+
+static inline void unlock_flocks(void)
+{
+}
+
 #endif /* !CONFIG_FILE_LOCKING */
 
 
@@ -1384,7 +1386,7 @@
 	 * Saved mount options for lazy filesystems using
 	 * generic_show_options()
 	 */
-	char *s_options;
+	char __rcu *s_options;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -2378,6 +2380,8 @@
 
 extern int generic_file_fsync(struct file *, int);
 
+extern int generic_check_addressable(unsigned, u64);
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
 				struct page *, struct page *);
@@ -2454,6 +2458,7 @@
 	.release = simple_attr_release,					\
 	.read	 = simple_attr_read,					\
 	.write	 = simple_attr_write,					\
+	.llseek	 = generic_file_llseek,					\
 };
 
 static inline void __attribute__((format(printf, 1, 2)))
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 02b8b24..8beabb9 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -191,8 +191,8 @@
 	unsigned int		flags;
 
 #ifdef CONFIG_PERF_EVENTS
-	int			perf_refcount;
-	struct hlist_head	*perf_events;
+	int				perf_refcount;
+	struct hlist_head __percpu	*perf_events;
 #endif
 };
 
@@ -252,8 +252,8 @@
 
 extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
-extern int  perf_trace_enable(struct perf_event *event);
-extern void perf_trace_disable(struct perf_event *event);
+extern int  perf_trace_add(struct perf_event *event, int flags);
+extern void perf_trace_del(struct perf_event *event, int flags);
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 5f2f4c4..557c392 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/kdev_t.h>
 #include <linux/rcupdate.h>
+#include <linux/slab.h>
 
 #ifdef CONFIG_BLOCK
 
@@ -86,7 +87,15 @@
 	unsigned long io_ticks;
 	unsigned long time_in_queue;
 };
-	
+
+#define PARTITION_META_INFO_VOLNAMELTH	64
+#define PARTITION_META_INFO_UUIDLTH	16
+
+struct partition_meta_info {
+	u8 uuid[PARTITION_META_INFO_UUIDLTH];	/* always big endian */
+	u8 volname[PARTITION_META_INFO_VOLNAMELTH];
+};
+
 struct hd_struct {
 	sector_t start_sect;
 	sector_t nr_sects;
@@ -95,6 +104,7 @@
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
+	struct partition_meta_info *info;
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	int make_it_fail;
 #endif
@@ -129,8 +139,9 @@
 struct disk_part_tbl {
 	struct rcu_head rcu_head;
 	int len;
-	struct hd_struct *last_lookup;
-	struct hd_struct *part[];
+	struct hd_struct __rcu *last_lookup;
+	struct gendisk *disk;
+	struct hd_struct __rcu *part[];
 };
 
 struct gendisk {
@@ -149,7 +160,7 @@
 	 * non-critical accesses use RCU.  Always access through
 	 * helpers.
 	 */
-	struct disk_part_tbl *part_tbl;
+	struct disk_part_tbl __rcu *part_tbl;
 	struct hd_struct part0;
 
 	const struct block_device_operations *fops;
@@ -181,6 +192,30 @@
 	return NULL;
 }
 
+static inline void part_pack_uuid(const u8 *uuid_str, u8 *to)
+{
+	int i;
+	for (i = 0; i < 16; ++i) {
+		*to++ = (hex_to_bin(*uuid_str) << 4) |
+			(hex_to_bin(*(uuid_str + 1)));
+		uuid_str += 2;
+		switch (i) {
+		case 3:
+		case 5:
+		case 7:
+		case 9:
+			uuid_str++;
+			continue;
+		}
+	}
+}
+
+static inline char *part_unpack_uuid(const u8 *uuid, char *out)
+{
+	sprintf(out, "%pU", uuid);
+	return out;
+}
+
 static inline int disk_max_parts(struct gendisk *disk)
 {
 	if (disk->flags & GENHD_FL_EXT_DEVT)
@@ -342,6 +377,19 @@
 	return part->in_flight[0] + part->in_flight[1];
 }
 
+static inline struct partition_meta_info *alloc_part_info(struct gendisk *disk)
+{
+	if (disk)
+		return kzalloc_node(sizeof(struct partition_meta_info),
+				    GFP_KERNEL, disk->node_id);
+	return kzalloc(sizeof(struct partition_meta_info), GFP_KERNEL);
+}
+
+static inline void free_part_info(struct hd_struct *part)
+{
+	kfree(part->info);
+}
+
 /* block/blk-core.c */
 extern void part_round_stats(int cpu, struct hd_struct *part);
 
@@ -533,7 +581,9 @@
 extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev);
 extern struct hd_struct * __must_check add_partition(struct gendisk *disk,
 						     int partno, sector_t start,
-						     sector_t len, int flags);
+						     sector_t len, int flags,
+						     struct partition_meta_info
+						       *info);
 extern void delete_partition(struct gendisk *, int);
 extern void printk_all_partitions(void);
 
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index d5b3876..8a389b6 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -8,7 +8,6 @@
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
 #include <asm/hardirq.h>
-#include <asm/system.h>
 
 /*
  * We put the hardirq and softirq counter into the preemption
@@ -64,6 +63,8 @@
 #define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
 #define NMI_OFFSET	(1UL << NMI_SHIFT)
 
+#define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
+
 #ifndef PREEMPT_ACTIVE
 #define PREEMPT_ACTIVE_BITS	1
 #define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
@@ -82,10 +83,13 @@
 /*
  * Are we doing bottom half or hardware interrupt processing?
  * Are we in a softirq context? Interrupt context?
+ * in_softirq - Are we currently processing softirq or have bh disabled?
+ * in_serving_softirq - Are we currently processing softirq?
  */
 #define in_irq()		(hardirq_count())
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
+#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
 
 /*
  * Are we in NMI context?
@@ -132,14 +136,16 @@
 
 struct task_struct;
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
 static inline void account_system_vtime(struct task_struct *tsk)
 {
 }
+#else
+extern void account_system_vtime(struct task_struct *tsk);
 #endif
 
 #if defined(CONFIG_NO_HZ)
-#if defined(CONFIG_TINY_RCU)
+#if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
 extern void rcu_enter_nohz(void);
 extern void rcu_exit_nohz(void);
 
diff --git a/include/linux/htirq.h b/include/linux/htirq.h
index c96ea46..70a1dbb 100644
--- a/include/linux/htirq.h
+++ b/include/linux/htirq.h
@@ -9,8 +9,9 @@
 /* Helper functions.. */
 void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
 void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-void mask_ht_irq(unsigned int irq);
-void unmask_ht_irq(unsigned int irq);
+struct irq_data;
+void mask_ht_irq(struct irq_data *data);
+void unmask_ht_irq(struct irq_data *data);
 
 /* The arch hook for getting things started */
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev);
diff --git a/include/linux/idr.h b/include/linux/idr.h
index e968db7..cdb715e 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -50,14 +50,14 @@
 
 struct idr_layer {
 	unsigned long		 bitmap; /* A zero bit means "space here" */
-	struct idr_layer	*ary[1<<IDR_BITS];
+	struct idr_layer __rcu	*ary[1<<IDR_BITS];
 	int			 count;	 /* When zero, we can release it */
 	int			 layer;	 /* distance from leaf */
 	struct rcu_head		 rcu_head;
 };
 
 struct idr {
-	struct idr_layer *top;
+	struct idr_layer __rcu *top;
 	struct idr_layer *id_free;
 	int		  layers; /* only valid without concurrent changes */
 	int		  id_free_cnt;
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 1f43fa5..2fea6c8 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -82,11 +82,17 @@
 # define CAP_INIT_BSET  CAP_FULL_SET
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
+#define INIT_TASK_RCU_TREE_PREEMPT()					\
+	.rcu_blocked_node = NULL,
+#else
+#define INIT_TASK_RCU_TREE_PREEMPT(tsk)
+#endif
+#ifdef CONFIG_PREEMPT_RCU
 #define INIT_TASK_RCU_PREEMPT(tsk)					\
 	.rcu_read_lock_nesting = 0,					\
 	.rcu_read_unlock_special = 0,					\
-	.rcu_blocked_node = NULL,					\
-	.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),
+	.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),		\
+	INIT_TASK_RCU_TREE_PREEMPT()
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
@@ -137,8 +143,8 @@
 	.children	= LIST_HEAD_INIT(tsk.children),			\
 	.sibling	= LIST_HEAD_INIT(tsk.sibling),			\
 	.group_leader	= &tsk,						\
-	.real_cred	= &init_cred,					\
-	.cred		= &init_cred,					\
+	RCU_INIT_POINTER(.real_cred, &init_cred),			\
+	RCU_INIT_POINTER(.cred, &init_cred),				\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(tsk.cred_guard_mutex),		\
 	.comm		= "swapper",					\
diff --git a/include/linux/input.h b/include/linux/input.h
index 896a922..d6ae176 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -1196,7 +1196,7 @@
 	int (*flush)(struct input_dev *dev, struct file *file);
 	int (*event)(struct input_dev *dev, unsigned int type, unsigned int code, int value);
 
-	struct input_handle *grab;
+	struct input_handle __rcu *grab;
 
 	spinlock_t event_lock;
 	struct mutex mutex;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a0384a4..4143285 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -18,6 +18,7 @@
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
+#include <trace/events/irq.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
@@ -407,7 +408,12 @@
 asmlinkage void __do_softirq(void);
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
-#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
+static inline void __raise_softirq_irqoff(unsigned int nr)
+{
+	trace_softirq_raise((struct softirq_action *)(unsigned long)nr, NULL);
+	or_softirq_pending(1UL << nr);
+}
+
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 extern void wakeup_softirqd(void);
@@ -641,11 +647,8 @@
 struct seq_file;
 int show_interrupts(struct seq_file *p, void *v);
 
-struct irq_desc;
-
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
-extern int arch_init_chip_data(struct irq_desc *desc, int node);
 
 #endif
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 64d5291..3e70b21 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -53,7 +53,7 @@
 
 	struct radix_tree_root radix_root;
 	struct hlist_head cic_list;
-	void *ioc_data;
+	void __rcu *ioc_data;
 };
 
 static inline struct io_context *ioc_task_link(struct io_context *ioc)
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c03243a..e963911 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -72,6 +72,10 @@
 #define IRQ_ONESHOT		0x08000000	/* IRQ is not unmasked after hardirq */
 #define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
 
+#define IRQF_MODIFY_MASK	\
+	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
+	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL)
+
 #ifdef CONFIG_IRQ_PER_CPU
 # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
 # define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
@@ -80,36 +84,77 @@
 # define IRQ_NO_BALANCING_MASK	IRQ_NO_BALANCING
 #endif
 
-struct proc_dir_entry;
 struct msi_desc;
 
 /**
+ * struct irq_data - per irq and irq chip data passed down to chip functions
+ * @irq:		interrupt number
+ * @node:		node index useful for balancing
+ * @chip:		low level interrupt hardware access
+ * @handler_data:	per-IRQ data for the irq_chip methods
+ * @chip_data:		platform-specific per-chip private data for the chip
+ *			methods, to allow shared chip implementations
+ * @msi_desc:		MSI descriptor
+ * @affinity:		IRQ affinity on SMP
+ *
+ * The fields here need to overlay the ones in irq_desc until we
+ * cleaned up the direct references and switched everything over to
+ * irq_data.
+ */
+struct irq_data {
+	unsigned int		irq;
+	unsigned int		node;
+	struct irq_chip		*chip;
+	void			*handler_data;
+	void			*chip_data;
+	struct msi_desc		*msi_desc;
+#ifdef CONFIG_SMP
+	cpumask_var_t		affinity;
+#endif
+};
+
+/**
  * struct irq_chip - hardware interrupt chip descriptor
  *
  * @name:		name for /proc/interrupts
- * @startup:		start up the interrupt (defaults to ->enable if NULL)
- * @shutdown:		shut down the interrupt (defaults to ->disable if NULL)
- * @enable:		enable the interrupt (defaults to chip->unmask if NULL)
- * @disable:		disable the interrupt
- * @ack:		start of a new interrupt
- * @mask:		mask an interrupt source
- * @mask_ack:		ack and mask an interrupt source
- * @unmask:		unmask an interrupt source
- * @eoi:		end of interrupt - chip level
- * @end:		end of interrupt - flow level
- * @set_affinity:	set the CPU affinity on SMP machines
- * @retrigger:		resend an IRQ to the CPU
- * @set_type:		set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
- * @set_wake:		enable/disable power-management wake-on of an IRQ
+ * @startup:		deprecated, replaced by irq_startup
+ * @shutdown:		deprecated, replaced by irq_shutdown
+ * @enable:		deprecated, replaced by irq_enable
+ * @disable:		deprecated, replaced by irq_disable
+ * @ack:		deprecated, replaced by irq_ack
+ * @mask:		deprecated, replaced by irq_mask
+ * @mask_ack:		deprecated, replaced by irq_mask_ack
+ * @unmask:		deprecated, replaced by irq_unmask
+ * @eoi:		deprecated, replaced by irq_eoi
+ * @end:		deprecated, will go away with __do_IRQ()
+ * @set_affinity:	deprecated, replaced by irq_set_affinity
+ * @retrigger:		deprecated, replaced by irq_retrigger
+ * @set_type:		deprecated, replaced by irq_set_type
+ * @set_wake:		deprecated, replaced by irq_wake
+ * @bus_lock:		deprecated, replaced by irq_bus_lock
+ * @bus_sync_unlock:	deprecated, replaced by irq_bus_sync_unlock
  *
- * @bus_lock:		function to lock access to slow bus (i2c) chips
- * @bus_sync_unlock:	function to sync and unlock slow bus (i2c) chips
+ * @irq_startup:	start up the interrupt (defaults to ->enable if NULL)
+ * @irq_shutdown:	shut down the interrupt (defaults to ->disable if NULL)
+ * @irq_enable:		enable the interrupt (defaults to chip->unmask if NULL)
+ * @irq_disable:	disable the interrupt
+ * @irq_ack:		start of a new interrupt
+ * @irq_mask:		mask an interrupt source
+ * @irq_mask_ack:	ack and mask an interrupt source
+ * @irq_unmask:		unmask an interrupt source
+ * @irq_eoi:		end of interrupt
+ * @irq_set_affinity:	set the CPU affinity on SMP machines
+ * @irq_retrigger:	resend an IRQ to the CPU
+ * @irq_set_type:	set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
+ * @irq_set_wake:	enable/disable power-management wake-on of an IRQ
+ * @irq_bus_lock:	function to lock access to slow bus (i2c) chips
+ * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
  *
  * @release:		release function solely used by UML
- * @typename:		obsoleted by name, kept as migration helper
  */
 struct irq_chip {
 	const char	*name;
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	unsigned int	(*startup)(unsigned int irq);
 	void		(*shutdown)(unsigned int irq);
 	void		(*enable)(unsigned int irq);
@@ -130,154 +175,66 @@
 
 	void		(*bus_lock)(unsigned int irq);
 	void		(*bus_sync_unlock)(unsigned int irq);
+#endif
+	unsigned int	(*irq_startup)(struct irq_data *data);
+	void		(*irq_shutdown)(struct irq_data *data);
+	void		(*irq_enable)(struct irq_data *data);
+	void		(*irq_disable)(struct irq_data *data);
+
+	void		(*irq_ack)(struct irq_data *data);
+	void		(*irq_mask)(struct irq_data *data);
+	void		(*irq_mask_ack)(struct irq_data *data);
+	void		(*irq_unmask)(struct irq_data *data);
+	void		(*irq_eoi)(struct irq_data *data);
+
+	int		(*irq_set_affinity)(struct irq_data *data, const struct cpumask *dest, bool force);
+	int		(*irq_retrigger)(struct irq_data *data);
+	int		(*irq_set_type)(struct irq_data *data, unsigned int flow_type);
+	int		(*irq_set_wake)(struct irq_data *data, unsigned int on);
+
+	void		(*irq_bus_lock)(struct irq_data *data);
+	void		(*irq_bus_sync_unlock)(struct irq_data *data);
 
 	/* Currently used only by UML, might disappear one day.*/
 #ifdef CONFIG_IRQ_RELEASE_METHOD
 	void		(*release)(unsigned int irq, void *dev_id);
 #endif
-	/*
-	 * For compatibility, ->typename is copied into ->name.
-	 * Will disappear.
-	 */
-	const char	*typename;
 };
 
-struct timer_rand_state;
-struct irq_2_iommu;
-/**
- * struct irq_desc - interrupt descriptor
- * @irq:		interrupt number for this descriptor
- * @timer_rand_state:	pointer to timer rand state struct
- * @kstat_irqs:		irq stats per cpu
- * @irq_2_iommu:	iommu with this irq
- * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
- * @chip:		low level interrupt hardware access
- * @msi_desc:		MSI descriptor
- * @handler_data:	per-IRQ data for the irq_chip methods
- * @chip_data:		platform-specific per-chip private data for the chip
- *			methods, to allow shared chip implementations
- * @action:		the irq action chain
- * @status:		status information
- * @depth:		disable-depth, for nested irq_disable() calls
- * @wake_depth:		enable depth, for multiple set_irq_wake() callers
- * @irq_count:		stats field to detect stalled irqs
- * @last_unhandled:	aging timer for unhandled count
- * @irqs_unhandled:	stats field for spurious unhandled interrupts
- * @lock:		locking for SMP
- * @affinity:		IRQ affinity on SMP
- * @node:		node index useful for balancing
- * @pending_mask:	pending rebalanced interrupts
- * @threads_active:	number of irqaction threads currently running
- * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
- * @dir:		/proc/irq/ procfs entry
- * @name:		flow handler name for /proc/interrupts output
- */
-struct irq_desc {
-	unsigned int		irq;
-	struct timer_rand_state *timer_rand_state;
-	unsigned int            *kstat_irqs;
-#ifdef CONFIG_INTR_REMAP
-	struct irq_2_iommu      *irq_2_iommu;
-#endif
-	irq_flow_handler_t	handle_irq;
-	struct irq_chip		*chip;
-	struct msi_desc		*msi_desc;
-	void			*handler_data;
-	void			*chip_data;
-	struct irqaction	*action;	/* IRQ action list */
-	unsigned int		status;		/* IRQ status */
-
-	unsigned int		depth;		/* nested irq disables */
-	unsigned int		wake_depth;	/* nested wake enables */
-	unsigned int		irq_count;	/* For detecting broken IRQs */
-	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
-	unsigned int		irqs_unhandled;
-	raw_spinlock_t		lock;
-#ifdef CONFIG_SMP
-	cpumask_var_t		affinity;
-	const struct cpumask	*affinity_hint;
-	unsigned int		node;
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_var_t		pending_mask;
-#endif
-#endif
-	atomic_t		threads_active;
-	wait_queue_head_t       wait_for_threads;
-#ifdef CONFIG_PROC_FS
-	struct proc_dir_entry	*dir;
-#endif
-	const char		*name;
-} ____cacheline_internodealigned_in_smp;
-
-extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
-					struct irq_desc *desc, int node);
-extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
-
-#ifndef CONFIG_SPARSE_IRQ
-extern struct irq_desc irq_desc[NR_IRQS];
-#endif
-
-#ifdef CONFIG_NUMA_IRQ_DESC
-extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int node);
-#else
-static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
-{
-	return desc;
-}
-#endif
-
-extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
+/* This include will go away once we isolated irq_desc usage to core code */
+#include <linux/irqdesc.h>
 
 /*
  * Pick up the arch-dependent methods:
  */
 #include <asm/hw_irq.h>
 
+#ifndef NR_IRQS_LEGACY
+# define NR_IRQS_LEGACY 0
+#endif
+
+#ifndef ARCH_IRQ_INIT_FLAGS
+# define ARCH_IRQ_INIT_FLAGS	0
+#endif
+
+#define IRQ_DEFAULT_INIT_FLAGS	(IRQ_DISABLED | ARCH_IRQ_INIT_FLAGS)
+
+struct irqaction;
 extern int setup_irq(unsigned int irq, struct irqaction *new);
 extern void remove_irq(unsigned int irq, struct irqaction *act);
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
-#ifdef CONFIG_SMP
-
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
-
-#else /* CONFIG_GENERIC_PENDING_IRQ */
-
-static inline void move_irq(int irq)
-{
-}
-
-static inline void move_native_irq(int irq)
-{
-}
-
-static inline void move_masked_irq(int irq)
-{
-}
-
-#endif /* CONFIG_GENERIC_PENDING_IRQ */
-
-#else /* CONFIG_SMP */
-
-#define move_native_irq(x)
-#define move_masked_irq(x)
-
-#endif /* CONFIG_SMP */
+#else
+static inline void move_native_irq(int irq) { }
+static inline void move_masked_irq(int irq) { }
+#endif
 
 extern int no_irq_affinity;
 
-static inline int irq_balancing_disabled(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status & IRQ_NO_BALANCING_MASK;
-}
-
 /* Handle irq action chains: */
 extern irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action);
 
@@ -293,42 +250,10 @@
 extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
-/*
- * Monolithic do_IRQ implementation.
- */
-#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
-extern unsigned int __do_IRQ(unsigned int irq);
-#endif
-
-/*
- * Architectures call this to let the generic IRQ layer
- * handle an interrupt. If the descriptor is attached to an
- * irqchip-style controller then we call the ->handle_irq() handler,
- * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
- */
-static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-#ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
-	desc->handle_irq(irq, desc);
-#else
-	if (likely(desc->handle_irq))
-		desc->handle_irq(irq, desc);
-	else
-		__do_IRQ(irq);
-#endif
-}
-
-static inline void generic_handle_irq(unsigned int irq)
-{
-	generic_handle_irq_desc(irq, irq_to_desc(irq));
-}
-
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(unsigned int irq, struct irq_desc *desc,
 			   irqreturn_t action_ret);
 
-/* Resending of interrupts :*/
-void check_irq_resend(struct irq_desc *desc, unsigned int irq);
 
 /* Enable/disable irq debugging output: */
 extern int noirqdebug_setup(char *str);
@@ -351,16 +276,6 @@
 __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name);
 
-/* caller has locked the irq_desc and both params are valid */
-static inline void __set_irq_handler_unlocked(int irq,
-					      irq_flow_handler_t handler)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	desc->handle_irq = handler;
-}
-
 /*
  * Set a highlevel flow handler for a given IRQ:
  */
@@ -384,26 +299,42 @@
 
 extern void set_irq_nested_thread(unsigned int irq, int nest);
 
-extern void set_irq_noprobe(unsigned int irq);
-extern void set_irq_probe(unsigned int irq);
+void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
+
+static inline void irq_set_status_flags(unsigned int irq, unsigned long set)
+{
+	irq_modify_status(irq, 0, set);
+}
+
+static inline void irq_clear_status_flags(unsigned int irq, unsigned long clr)
+{
+	irq_modify_status(irq, clr, 0);
+}
+
+static inline void set_irq_noprobe(unsigned int irq)
+{
+	irq_modify_status(irq, 0, IRQ_NOPROBE);
+}
+
+static inline void set_irq_probe(unsigned int irq)
+{
+	irq_modify_status(irq, IRQ_NOPROBE, 0);
+}
 
 /* Handle dynamic irq creation and destruction */
 extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);
 
-/* Test to see if a driver has successfully requested an irq */
-static inline int irq_has_action(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	return desc->action != NULL;
-}
-
-/* Dynamic irq helper functions */
-extern void dynamic_irq_init(unsigned int irq);
-void dynamic_irq_init_keep_chip_data(unsigned int irq);
+/*
+ * Dynamic irq helper functions. Obsolete. Use irq_alloc_desc* and
+ * irq_free_desc instead.
+ */
 extern void dynamic_irq_cleanup(unsigned int irq);
-void dynamic_irq_cleanup_keep_chip_data(unsigned int irq);
+static inline void dynamic_irq_init(unsigned int irq)
+{
+	dynamic_irq_cleanup(irq);
+}
 
 /* Set/get chip/data for an IRQ: */
 extern int set_irq_chip(unsigned int irq, struct irq_chip *chip);
@@ -411,114 +342,78 @@
 extern int set_irq_chip_data(unsigned int irq, void *data);
 extern int set_irq_type(unsigned int irq, unsigned int type);
 extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
+extern struct irq_data *irq_get_irq_data(unsigned int irq);
 
-#define get_irq_chip(irq)	(irq_to_desc(irq)->chip)
-#define get_irq_chip_data(irq)	(irq_to_desc(irq)->chip_data)
-#define get_irq_data(irq)	(irq_to_desc(irq)->handler_data)
-#define get_irq_msi(irq)	(irq_to_desc(irq)->msi_desc)
+static inline struct irq_chip *get_irq_chip(unsigned int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+	return d ? d->chip : NULL;
+}
 
-#define get_irq_desc_chip(desc)		((desc)->chip)
-#define get_irq_desc_chip_data(desc)	((desc)->chip_data)
-#define get_irq_desc_data(desc)		((desc)->handler_data)
-#define get_irq_desc_msi(desc)		((desc)->msi_desc)
+static inline struct irq_chip *irq_data_get_irq_chip(struct irq_data *d)
+{
+	return d->chip;
+}
+
+static inline void *get_irq_chip_data(unsigned int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+	return d ? d->chip_data : NULL;
+}
+
+static inline void *irq_data_get_irq_chip_data(struct irq_data *d)
+{
+	return d->chip_data;
+}
+
+static inline void *get_irq_data(unsigned int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+	return d ? d->handler_data : NULL;
+}
+
+static inline void *irq_data_get_irq_data(struct irq_data *d)
+{
+	return d->handler_data;
+}
+
+static inline struct msi_desc *get_irq_msi(unsigned int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+	return d ? d->msi_desc : NULL;
+}
+
+static inline struct msi_desc *irq_data_get_msi(struct irq_data *d)
+{
+	return d->msi_desc;
+}
+
+int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
+void irq_free_descs(unsigned int irq, unsigned int cnt);
+int irq_reserve_irqs(unsigned int from, unsigned int cnt);
+
+static inline int irq_alloc_desc(int node)
+{
+	return irq_alloc_descs(-1, 0, 1, node);
+}
+
+static inline int irq_alloc_desc_at(unsigned int at, int node)
+{
+	return irq_alloc_descs(at, at, 1, node);
+}
+
+static inline int irq_alloc_desc_from(unsigned int from, int node)
+{
+	return irq_alloc_descs(-1, from, 1, node);
+}
+
+static inline void irq_free_desc(unsigned int irq)
+{
+	irq_free_descs(irq, 1);
+}
 
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
 #endif /* !CONFIG_S390 */
 
-#ifdef CONFIG_SMP
-/**
- * alloc_desc_masks - allocate cpumasks for irq_desc
- * @desc:	pointer to irq_desc struct
- * @node:	node which will be handling the cpumasks
- * @boot:	true if need bootmem
- *
- * Allocates affinity and pending_mask cpumask if required.
- * Returns true if successful (or not required).
- */
-static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
-							bool boot)
-{
-	gfp_t gfp = GFP_ATOMIC;
-
-	if (boot)
-		gfp = GFP_NOWAIT;
-
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	if (!alloc_cpumask_var_node(&desc->affinity, gfp, node))
-		return false;
-
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (!alloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
-		free_cpumask_var(desc->affinity);
-		return false;
-	}
-#endif
-#endif
-	return true;
-}
-
-static inline void init_desc_masks(struct irq_desc *desc)
-{
-	cpumask_setall(desc->affinity);
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_clear(desc->pending_mask);
-#endif
-}
-
-/**
- * init_copy_desc_masks - copy cpumasks for irq_desc
- * @old_desc:	pointer to old irq_desc struct
- * @new_desc:	pointer to new irq_desc struct
- *
- * Insures affinity and pending_masks are copied to new irq_desc.
- * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the
- * irq_desc struct so the copy is redundant.
- */
-
-static inline void init_copy_desc_masks(struct irq_desc *old_desc,
-					struct irq_desc *new_desc)
-{
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	cpumask_copy(new_desc->affinity, old_desc->affinity);
-
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
-#endif
-#endif
-}
-
-static inline void free_desc_masks(struct irq_desc *old_desc,
-				   struct irq_desc *new_desc)
-{
-	free_cpumask_var(old_desc->affinity);
-
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	free_cpumask_var(old_desc->pending_mask);
-#endif
-}
-
-#else /* !CONFIG_SMP */
-
-static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
-								bool boot)
-{
-	return true;
-}
-
-static inline void init_desc_masks(struct irq_desc *desc)
-{
-}
-
-static inline void init_copy_desc_masks(struct irq_desc *old_desc,
-					struct irq_desc *new_desc)
-{
-}
-
-static inline void free_desc_masks(struct irq_desc *old_desc,
-				   struct irq_desc *new_desc)
-{
-}
-#endif	/* CONFIG_SMP */
-
 #endif /* _LINUX_IRQ_H */
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
new file mode 100644
index 0000000..4fa09d4
--- /dev/null
+++ b/include/linux/irq_work.h
@@ -0,0 +1,20 @@
+#ifndef _LINUX_IRQ_WORK_H
+#define _LINUX_IRQ_WORK_H
+
+struct irq_work {
+	struct irq_work *next;
+	void (*func)(struct irq_work *);
+};
+
+static inline
+void init_irq_work(struct irq_work *entry, void (*func)(struct irq_work *))
+{
+	entry->next = NULL;
+	entry->func = func;
+}
+
+bool irq_work_queue(struct irq_work *entry);
+void irq_work_run(void);
+void irq_work_sync(struct irq_work *entry);
+
+#endif /* _LINUX_IRQ_WORK_H */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
new file mode 100644
index 0000000..979c68c
--- /dev/null
+++ b/include/linux/irqdesc.h
@@ -0,0 +1,159 @@
+#ifndef _LINUX_IRQDESC_H
+#define _LINUX_IRQDESC_H
+
+/*
+ * Core internal functions to deal with irq descriptors
+ *
+ * This include will move to kernel/irq once we cleaned up the tree.
+ * For now it's included from <linux/irq.h>
+ */
+
+struct proc_dir_entry;
+struct timer_rand_state;
+/**
+ * struct irq_desc - interrupt descriptor
+ * @irq_data:		per irq and chip data passed down to chip functions
+ * @timer_rand_state:	pointer to timer rand state struct
+ * @kstat_irqs:		irq stats per cpu
+ * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
+ * @action:		the irq action chain
+ * @status:		status information
+ * @depth:		disable-depth, for nested irq_disable() calls
+ * @wake_depth:		enable depth, for multiple set_irq_wake() callers
+ * @irq_count:		stats field to detect stalled irqs
+ * @last_unhandled:	aging timer for unhandled count
+ * @irqs_unhandled:	stats field for spurious unhandled interrupts
+ * @lock:		locking for SMP
+ * @pending_mask:	pending rebalanced interrupts
+ * @threads_active:	number of irqaction threads currently running
+ * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
+ * @dir:		/proc/irq/ procfs entry
+ * @name:		flow handler name for /proc/interrupts output
+ */
+struct irq_desc {
+
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+	struct irq_data		irq_data;
+#else
+	/*
+	 * This union will go away, once we fixed the direct access to
+	 * irq_desc all over the place. The direct fields are a 1:1
+	 * overlay of irq_data.
+	 */
+	union {
+		struct irq_data		irq_data;
+		struct {
+			unsigned int		irq;
+			unsigned int		node;
+			struct irq_chip		*chip;
+			void			*handler_data;
+			void			*chip_data;
+			struct msi_desc		*msi_desc;
+#ifdef CONFIG_SMP
+			cpumask_var_t		affinity;
+#endif
+		};
+	};
+#endif
+
+	struct timer_rand_state *timer_rand_state;
+	unsigned int		*kstat_irqs;
+	irq_flow_handler_t	handle_irq;
+	struct irqaction	*action;	/* IRQ action list */
+	unsigned int		status;		/* IRQ status */
+
+	unsigned int		depth;		/* nested irq disables */
+	unsigned int		wake_depth;	/* nested wake enables */
+	unsigned int		irq_count;	/* For detecting broken IRQs */
+	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
+	unsigned int		irqs_unhandled;
+	raw_spinlock_t		lock;
+#ifdef CONFIG_SMP
+	const struct cpumask	*affinity_hint;
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_var_t		pending_mask;
+#endif
+#endif
+	atomic_t		threads_active;
+	wait_queue_head_t       wait_for_threads;
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry	*dir;
+#endif
+	const char		*name;
+} ____cacheline_internodealigned_in_smp;
+
+#ifndef CONFIG_SPARSE_IRQ
+extern struct irq_desc irq_desc[NR_IRQS];
+#endif
+
+/* Will be removed once the last users in power and sh are gone */
+extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
+static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
+{
+	return desc;
+}
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+
+#define get_irq_desc_chip(desc)		((desc)->irq_data.chip)
+#define get_irq_desc_chip_data(desc)	((desc)->irq_data.chip_data)
+#define get_irq_desc_data(desc)		((desc)->irq_data.handler_data)
+#define get_irq_desc_msi(desc)		((desc)->irq_data.msi_desc)
+
+/*
+ * Monolithic do_IRQ implementation.
+ */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+extern unsigned int __do_IRQ(unsigned int irq);
+#endif
+
+/*
+ * Architectures call this to let the generic IRQ layer
+ * handle an interrupt. If the descriptor is attached to an
+ * irqchip-style controller then we call the ->handle_irq() handler,
+ * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
+ */
+static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+#ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+	desc->handle_irq(irq, desc);
+#else
+	if (likely(desc->handle_irq))
+		desc->handle_irq(irq, desc);
+	else
+		__do_IRQ(irq);
+#endif
+}
+
+static inline void generic_handle_irq(unsigned int irq)
+{
+	generic_handle_irq_desc(irq, irq_to_desc(irq));
+}
+
+/* Test to see if a driver has successfully requested an irq */
+static inline int irq_has_action(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	return desc->action != NULL;
+}
+
+static inline int irq_balancing_disabled(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	return desc->status & IRQ_NO_BALANCING_MASK;
+}
+
+/* caller has locked the irq_desc and both params are valid */
+static inline void __set_irq_handler_unlocked(int irq,
+					      irq_flow_handler_t handler)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->handle_irq = handler;
+}
+#endif
+
+#endif
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 006bf45..d176d65 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -12,6 +12,7 @@
 #define _LINUX_TRACE_IRQFLAGS_H
 
 #include <linux/typecheck.h>
+#include <asm/irqflags.h>
 
 #ifdef CONFIG_TRACE_IRQFLAGS
   extern void trace_softirqs_on(unsigned long ip);
@@ -52,17 +53,45 @@
 # define start_critical_timings() do { } while (0)
 #endif
 
+/*
+ * Wrap the arch provided IRQ routines to provide appropriate checks.
+ */
+#define raw_local_irq_disable()		arch_local_irq_disable()
+#define raw_local_irq_enable()		arch_local_irq_enable()
+#define raw_local_irq_save(flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		flags = arch_local_irq_save();		\
+	} while (0)
+#define raw_local_irq_restore(flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		arch_local_irq_restore(flags);		\
+	} while (0)
+#define raw_local_save_flags(flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		flags = arch_local_save_flags();	\
+	} while (0)
+#define raw_irqs_disabled_flags(flags)			\
+	({						\
+		typecheck(unsigned long, flags);	\
+		arch_irqs_disabled_flags(flags);	\
+	})
+#define raw_irqs_disabled()		(arch_irqs_disabled())
+#define raw_safe_halt()			arch_safe_halt()
+
+/*
+ * The local_irq_*() APIs are equal to the raw_local_irq*()
+ * if !TRACE_IRQFLAGS.
+ */
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
-
-#include <asm/irqflags.h>
-
 #define local_irq_enable() \
 	do { trace_hardirqs_on(); raw_local_irq_enable(); } while (0)
 #define local_irq_disable() \
 	do { raw_local_irq_disable(); trace_hardirqs_off(); } while (0)
 #define local_irq_save(flags)				\
 	do {						\
-		typecheck(unsigned long, flags);	\
 		raw_local_irq_save(flags);		\
 		trace_hardirqs_off();			\
 	} while (0)
@@ -70,7 +99,6 @@
 
 #define local_irq_restore(flags)			\
 	do {						\
-		typecheck(unsigned long, flags);	\
 		if (raw_irqs_disabled_flags(flags)) {	\
 			raw_local_irq_restore(flags);	\
 			trace_hardirqs_off();		\
@@ -79,51 +107,44 @@
 			raw_local_irq_restore(flags);	\
 		}					\
 	} while (0)
-#else /* !CONFIG_TRACE_IRQFLAGS_SUPPORT */
-/*
- * The local_irq_*() APIs are equal to the raw_local_irq*()
- * if !TRACE_IRQFLAGS.
- */
-# define raw_local_irq_disable()	local_irq_disable()
-# define raw_local_irq_enable()		local_irq_enable()
-# define raw_local_irq_save(flags)			\
-	do {						\
-		typecheck(unsigned long, flags);	\
-		local_irq_save(flags);			\
-	} while (0)
-# define raw_local_irq_restore(flags)			\
-	do {						\
-		typecheck(unsigned long, flags);	\
-		local_irq_restore(flags);		\
-	} while (0)
-#endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */
-
-#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
-#define safe_halt()						\
-	do {							\
-		trace_hardirqs_on();				\
-		raw_safe_halt();				\
-	} while (0)
-
 #define local_save_flags(flags)				\
 	do {						\
-		typecheck(unsigned long, flags);	\
 		raw_local_save_flags(flags);		\
 	} while (0)
 
-#define irqs_disabled()						\
-({								\
-	unsigned long _flags;					\
-								\
-	raw_local_save_flags(_flags);				\
-	raw_irqs_disabled_flags(_flags);			\
-})
+#define irqs_disabled_flags(flags)			\
+	({						\
+		raw_irqs_disabled_flags(flags);		\
+	})
 
-#define irqs_disabled_flags(flags)		\
-({						\
-	typecheck(unsigned long, flags);	\
-	raw_irqs_disabled_flags(flags);		\
-})
+#define irqs_disabled()					\
+	({						\
+		unsigned long _flags;			\
+		raw_local_save_flags(_flags);		\
+		raw_irqs_disabled_flags(_flags);	\
+	})
+
+#define safe_halt()				\
+	do {					\
+		trace_hardirqs_on();		\
+		raw_safe_halt();		\
+	} while (0)
+
+
+#else /* !CONFIG_TRACE_IRQFLAGS_SUPPORT */
+
+#define local_irq_enable()	do { raw_local_irq_enable(); } while (0)
+#define local_irq_disable()	do { raw_local_irq_disable(); } while (0)
+#define local_irq_save(flags)					\
+	do {							\
+		raw_local_irq_save(flags);			\
+	} while (0)
+#define local_irq_restore(flags) do { raw_local_irq_restore(flags); } while (0)
+#define local_save_flags(flags)	do { raw_local_save_flags(flags); } while (0)
+#define irqs_disabled()		(raw_irqs_disabled())
+#define irqs_disabled_flags(flags) (raw_irqs_disabled_flags(flags))
+#define safe_halt()		do { raw_safe_halt(); } while (0)
+
 #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */
 
 #endif
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 7bf89bc..05aa8c23 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -25,6 +25,7 @@
 
 extern int nr_irqs;
 extern struct irq_desc *irq_to_desc(unsigned int irq);
+unsigned int irq_get_next_irq(unsigned int offset);
 
 # define for_each_irq_desc(irq, desc)					\
 	for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs;		\
@@ -47,6 +48,10 @@
 #define irq_node(irq)	0
 #endif
 
+# define for_each_active_irq(irq)			\
+	for (irq = irq_get_next_irq(0); irq < nr_irqs;	\
+	     irq = irq_get_next_irq(irq + 1))
+
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
 #define for_each_irq_nr(irq)                   \
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
new file mode 100644
index 0000000..b67cb18
--- /dev/null
+++ b/include/linux/jump_label.h
@@ -0,0 +1,74 @@
+#ifndef _LINUX_JUMP_LABEL_H
+#define _LINUX_JUMP_LABEL_H
+
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL)
+# include <asm/jump_label.h>
+# define HAVE_JUMP_LABEL
+#endif
+
+enum jump_label_type {
+	JUMP_LABEL_ENABLE,
+	JUMP_LABEL_DISABLE
+};
+
+struct module;
+
+#ifdef HAVE_JUMP_LABEL
+
+extern struct jump_entry __start___jump_table[];
+extern struct jump_entry __stop___jump_table[];
+
+extern void arch_jump_label_transform(struct jump_entry *entry,
+				 enum jump_label_type type);
+extern void arch_jump_label_text_poke_early(jump_label_t addr);
+extern void jump_label_update(unsigned long key, enum jump_label_type type);
+extern void jump_label_apply_nops(struct module *mod);
+extern int jump_label_text_reserved(void *start, void *end);
+
+#define jump_label_enable(key) \
+	jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE);
+
+#define jump_label_disable(key) \
+	jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE);
+
+#else
+
+#define JUMP_LABEL(key, label)			\
+do {						\
+	if (unlikely(*key))			\
+		goto label;			\
+} while (0)
+
+#define jump_label_enable(cond_var)	\
+do {					\
+       *(cond_var) = 1;			\
+} while (0)
+
+#define jump_label_disable(cond_var)	\
+do {					\
+       *(cond_var) = 0;			\
+} while (0)
+
+static inline int jump_label_apply_nops(struct module *mod)
+{
+	return 0;
+}
+
+static inline int jump_label_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
+#endif
+
+#define COND_STMT(key, stmt)					\
+do {								\
+	__label__ jl_enabled;					\
+	JUMP_LABEL(key, jl_enabled);				\
+	if (0) {						\
+jl_enabled:							\
+		stmt;						\
+	}							\
+} while (0)
+
+#endif
diff --git a/include/linux/jump_label_ref.h b/include/linux/jump_label_ref.h
new file mode 100644
index 0000000..e5d012a
--- /dev/null
+++ b/include/linux/jump_label_ref.h
@@ -0,0 +1,44 @@
+#ifndef _LINUX_JUMP_LABEL_REF_H
+#define _LINUX_JUMP_LABEL_REF_H
+
+#include <linux/jump_label.h>
+#include <asm/atomic.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+static inline void jump_label_inc(atomic_t *key)
+{
+	if (atomic_add_return(1, key) == 1)
+		jump_label_enable(key);
+}
+
+static inline void jump_label_dec(atomic_t *key)
+{
+	if (atomic_dec_and_test(key))
+		jump_label_disable(key);
+}
+
+#else /* !HAVE_JUMP_LABEL */
+
+static inline void jump_label_inc(atomic_t *key)
+{
+	atomic_inc(key);
+}
+
+static inline void jump_label_dec(atomic_t *key)
+{
+	atomic_dec(key);
+}
+
+#undef JUMP_LABEL
+#define JUMP_LABEL(key, label)						\
+do {									\
+	if (unlikely(__builtin_choose_expr(				\
+	      __builtin_types_compatible_p(typeof(key), atomic_t *),	\
+	      atomic_read((atomic_t *)(key)), *(key))))			\
+		goto label;						\
+} while (0)
+
+#endif /* HAVE_JUMP_LABEL */
+
+#endif /* _LINUX_JUMP_LABEL_REF_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2b0a35e..edef168 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -58,7 +58,18 @@
 
 #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
-#define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y))
+#define roundup(x, y) (					\
+{							\
+	typeof(y) __y = y;				\
+	(((x) + (__y - 1)) / __y) * __y;		\
+}							\
+)
+#define rounddown(x, y) (				\
+{							\
+	typeof(x) __x = (x);				\
+	__x - (__x % (y));				\
+}							\
+)
 #define DIV_ROUND_CLOSEST(x, divisor)(			\
 {							\
 	typeof(divisor) __divisor = divisor;		\
@@ -641,6 +652,16 @@
 	_max1 > _max2 ? _max1 : _max2; })
 
 /**
+ * min_not_zero - return the minimum that is _not_ zero, unless both are zero
+ * @x: value1
+ * @y: value2
+ */
+#define min_not_zero(x, y) ({			\
+	typeof(x) __x = (x);			\
+	typeof(y) __y = (y);			\
+	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+/**
  * clamp - return a value clamped to a given range with strict typechecking
  * @val: current value
  * @min: minimum allowable value
diff --git a/include/linux/key.h b/include/linux/key.h
index cd50dfa..3db0adc 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -178,8 +178,9 @@
 	 */
 	union {
 		unsigned long		value;
+		void __rcu		*rcudata;
 		void			*data;
-		struct keyring_list	*subscriptions;
+		struct keyring_list __rcu *subscriptions;
 	} payload;
 };
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c13cc48..ac740b2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -205,7 +205,7 @@
 
 	struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
-	struct kvm_irq_routing_table *irq_routing;
+	struct kvm_irq_routing_table __rcu *irq_routing;
 	struct hlist_head mask_notifier_list;
 	struct hlist_head irq_ack_notifier_list;
 #endif
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 45fb296..15b77b8 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -37,6 +37,7 @@
 #include <scsi/scsi_host.h>
 #include <linux/acpi.h>
 #include <linux/cdrom.h>
+#include <linux/sched.h>
 
 /*
  * Define if arch has non-standard setup.  This is a _PCI_ standard
@@ -172,6 +173,7 @@
 	ATA_LFLAG_NO_RETRY	= (1 << 5), /* don't retry this link */
 	ATA_LFLAG_DISABLED	= (1 << 6), /* link is disabled */
 	ATA_LFLAG_SW_ACTIVITY	= (1 << 7), /* keep activity stats */
+	ATA_LFLAG_NO_LPM	= (1 << 8), /* disable LPM on this link */
 
 	/* struct ata_port flags */
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
@@ -196,7 +198,7 @@
 	ATA_FLAG_ACPI_SATA	= (1 << 17), /* need native SATA ACPI layout */
 	ATA_FLAG_AN		= (1 << 18), /* controller supports AN */
 	ATA_FLAG_PMP		= (1 << 19), /* controller supports PMP */
-	ATA_FLAG_IPM		= (1 << 20), /* driver can handle IPM */
+	ATA_FLAG_LPM		= (1 << 20), /* driver can handle LPM */
 	ATA_FLAG_EM		= (1 << 21), /* driver supports enclosure
 					      * management */
 	ATA_FLAG_SW_ACTIVITY	= (1 << 22), /* driver supports sw activity
@@ -324,12 +326,11 @@
 	ATA_EH_HARDRESET	= (1 << 2), /* meaningful only in ->prereset */
 	ATA_EH_RESET		= ATA_EH_SOFTRESET | ATA_EH_HARDRESET,
 	ATA_EH_ENABLE_LINK	= (1 << 3),
-	ATA_EH_LPM		= (1 << 4),  /* link power management action */
 	ATA_EH_PARK		= (1 << 5), /* unload heads and stop I/O */
 
 	ATA_EH_PERDEV_MASK	= ATA_EH_REVALIDATE | ATA_EH_PARK,
 	ATA_EH_ALL_ACTIONS	= ATA_EH_REVALIDATE | ATA_EH_RESET |
-				  ATA_EH_ENABLE_LINK | ATA_EH_LPM,
+				  ATA_EH_ENABLE_LINK,
 
 	/* ata_eh_info->flags */
 	ATA_EHI_HOTPLUGGED	= (1 << 0),  /* could have been hotplugged */
@@ -341,7 +342,7 @@
 	ATA_EHI_DID_HARDRESET	= (1 << 17), /* already soft-reset this port */
 	ATA_EHI_PRINTINFO	= (1 << 18), /* print configuration info */
 	ATA_EHI_SETMODE		= (1 << 19), /* configure transfer mode */
-	ATA_EHI_POST_SETMODE	= (1 << 20), /* revaildating after setmode */
+	ATA_EHI_POST_SETMODE	= (1 << 20), /* revalidating after setmode */
 
 	ATA_EHI_DID_RESET	= ATA_EHI_DID_SOFTRESET | ATA_EHI_DID_HARDRESET,
 
@@ -377,7 +378,6 @@
 	ATA_HORKAGE_BROKEN_HPA	= (1 << 4),	/* Broken HPA */
 	ATA_HORKAGE_DISABLE	= (1 << 5),	/* Disable it */
 	ATA_HORKAGE_HPA_SIZE	= (1 << 6),	/* native size off by one */
-	ATA_HORKAGE_IPM		= (1 << 7),	/* Link PM problems */
 	ATA_HORKAGE_IVB		= (1 << 8),	/* cbl det validity bit bugs */
 	ATA_HORKAGE_STUCK_ERR	= (1 << 9),	/* stuck ERR on next PACKET */
 	ATA_HORKAGE_BRIDGE_OK	= (1 << 10),	/* no bridge limits */
@@ -464,6 +464,22 @@
 	AC_ERR_NCQ		= (1 << 10), /* marker for offending NCQ qc */
 };
 
+/*
+ * Link power management policy: If you alter this, you also need to
+ * alter libata-scsi.c (for the ascii descriptions)
+ */
+enum ata_lpm_policy {
+	ATA_LPM_UNKNOWN,
+	ATA_LPM_MAX_POWER,
+	ATA_LPM_MED_POWER,
+	ATA_LPM_MIN_POWER,
+};
+
+enum ata_lpm_hints {
+	ATA_LPM_EMPTY		= (1 << 0), /* port empty/probing */
+	ATA_LPM_HIPM		= (1 << 1), /* may use HIPM */
+};
+
 /* forward declarations */
 struct scsi_device;
 struct ata_port_operations;
@@ -478,16 +494,6 @@
 			      unsigned long deadline);
 typedef void (*ata_postreset_fn_t)(struct ata_link *link, unsigned int *classes);
 
-/*
- * host pm policy: If you alter this, you also need to alter libata-scsi.c
- * (for the ascii descriptions)
- */
-enum link_pm {
-	NOT_AVAILABLE,
-	MIN_POWER,
-	MAX_PERFORMANCE,
-	MEDIUM_POWER,
-};
 extern struct device_attribute dev_attr_link_power_management_policy;
 extern struct device_attribute dev_attr_unload_heads;
 extern struct device_attribute dev_attr_em_message_type;
@@ -530,6 +536,10 @@
 	void			*private_data;
 	struct ata_port_operations *ops;
 	unsigned long		flags;
+
+	struct mutex		eh_mutex;
+	struct task_struct	*eh_owner;
+
 #ifdef CONFIG_ATA_ACPI
 	acpi_handle		acpi_handle;
 #endif
@@ -560,13 +570,13 @@
 	unsigned int		extrabytes;
 	unsigned int		curbytes;
 
-	struct scatterlist	*cursg;
-	unsigned int		cursg_ofs;
-
 	struct scatterlist	sgent;
 
 	struct scatterlist	*sg;
 
+	struct scatterlist	*cursg;
+	unsigned int		cursg_ofs;
+
 	unsigned int		err_mask;
 	struct ata_taskfile	result_tf;
 	ata_qc_cb_t		complete_fn;
@@ -604,6 +614,7 @@
 	union acpi_object	*gtf_cache;
 	unsigned int		gtf_filter;
 #endif
+	struct device		tdev;
 	/* n_sector is CLEAR_BEGIN, read comment above CLEAR_BEGIN */
 	u64			n_sectors;	/* size of device, if ATA */
 	u64			n_native_sectors; /* native size, if ATA */
@@ -690,6 +701,7 @@
 	struct ata_port		*ap;
 	int			pmp;		/* port multiplier port # */
 
+	struct device		tdev;
 	unsigned int		active_tag;	/* active tag on this link */
 	u32			sactive;	/* active NCQ commands */
 
@@ -699,6 +711,7 @@
 	unsigned int		hw_sata_spd_limit;
 	unsigned int		sata_spd_limit;
 	unsigned int		sata_spd;	/* current SATA PHY speed */
+	enum ata_lpm_policy	lpm_policy;
 
 	/* record runtime error info, protected by host_set lock */
 	struct ata_eh_info	eh_info;
@@ -707,6 +720,8 @@
 
 	struct ata_device	device[ATA_MAX_DEVICES];
 };
+#define ATA_LINK_CLEAR_BEGIN		offsetof(struct ata_link, active_tag)
+#define ATA_LINK_CLEAR_END		offsetof(struct ata_link, device[0])
 
 struct ata_port {
 	struct Scsi_Host	*scsi_host; /* our co-allocated scsi host */
@@ -752,6 +767,7 @@
 	struct ata_port_stats	stats;
 	struct ata_host		*host;
 	struct device 		*dev;
+	struct device		tdev;
 
 	struct mutex		scsi_scan_mutex;
 	struct delayed_work	hotplug_task;
@@ -767,7 +783,7 @@
 
 	pm_message_t		pm_mesg;
 	int			*pm_result;
-	enum link_pm		pm_policy;
+	enum ata_lpm_policy	target_lpm_policy;
 
 	struct timer_list	fastdrain_timer;
 	unsigned long		fastdrain_cnt;
@@ -833,8 +849,8 @@
 	int  (*scr_write)(struct ata_link *link, unsigned int sc_reg, u32 val);
 	void (*pmp_attach)(struct ata_port *ap);
 	void (*pmp_detach)(struct ata_port *ap);
-	int  (*enable_pm)(struct ata_port *ap, enum link_pm policy);
-	void (*disable_pm)(struct ata_port *ap);
+	int  (*set_lpm)(struct ata_link *link, enum ata_lpm_policy policy,
+			unsigned hints);
 
 	/*
 	 * Start, stop, suspend and resume
@@ -946,6 +962,8 @@
 			const unsigned long *params, unsigned long deadline);
 extern int sata_link_resume(struct ata_link *link, const unsigned long *params,
 			    unsigned long deadline);
+extern int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+			     bool spm_wakeup);
 extern int sata_link_hardreset(struct ata_link *link,
 			const unsigned long *timing, unsigned long deadline,
 			bool *online, int (*check_ready)(struct ata_link *));
@@ -991,8 +1009,9 @@
 extern void ata_host_resume(struct ata_host *host);
 #endif
 extern int ata_ratelimit(void);
-extern u32 ata_wait_register(void __iomem *reg, u32 mask, u32 val,
-			     unsigned long interval, unsigned long timeout);
+extern void ata_msleep(struct ata_port *ap, unsigned int msecs);
+extern u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask,
+			u32 val, unsigned long interval, unsigned long timeout);
 extern int atapi_cmd_type(u8 opcode);
 extern void ata_tf_to_fis(const struct ata_taskfile *tf,
 			  u8 pmp, int is_cmd, u8 *fis);
diff --git a/include/linux/list.h b/include/linux/list.h
index d167b5d..88a0006 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -5,7 +5,6 @@
 #include <linux/stddef.h>
 #include <linux/poison.h>
 #include <linux/prefetch.h>
-#include <asm/system.h>
 
 /*
  * Simple doubly linked list implementation.
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 06aed83..71c09b26 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -32,6 +32,17 @@
 #define MAX_LOCKDEP_SUBCLASSES		8UL
 
 /*
+ * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
+ * cached in the instance of lockdep_map
+ *
+ * Currently main class (subclass == 0) and signle depth subclass
+ * are cached in lockdep_map. This optimization is mainly targeting
+ * on rq->lock. double_rq_lock() acquires this highly competitive with
+ * single depth.
+ */
+#define NR_LOCKDEP_CACHING_CLASSES	2
+
+/*
  * Lock-classes are keyed via unique addresses, by embedding the
  * lockclass-key into the kernel (or module) .data section. (For
  * static locks we use the lock address itself as the key.)
@@ -138,7 +149,7 @@
  */
 struct lockdep_map {
 	struct lock_class_key		*key;
-	struct lock_class		*class_cache;
+	struct lock_class		*class_cache[NR_LOCKDEP_CACHING_CLASSES];
 	const char			*name;
 #ifdef CONFIG_LOCK_STAT
 	int				cpu;
@@ -424,14 +435,6 @@
 
 #endif /* CONFIG_LOCKDEP */
 
-#ifdef CONFIG_GENERIC_HARDIRQS
-extern void early_init_irq_lock_class(void);
-#else
-static inline void early_init_irq_lock_class(void)
-{
-}
-#endif
-
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void early_boot_irqs_off(void);
 extern void early_boot_irqs_on(void);
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index a59faf2..62a10c2 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -2,6 +2,7 @@
 #define _LINUX_MEMBLOCK_H
 #ifdef __KERNEL__
 
+#ifdef CONFIG_HAVE_MEMBLOCK
 /*
  * Logical memory blocks.
  *
@@ -16,73 +17,150 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 
-#define MAX_MEMBLOCK_REGIONS 128
+#include <asm/memblock.h>
 
-struct memblock_property {
-	u64 base;
-	u64 size;
-};
+#define INIT_MEMBLOCK_REGIONS	128
+#define MEMBLOCK_ERROR		0
 
 struct memblock_region {
-	unsigned long cnt;
-	u64 size;
-	struct memblock_property region[MAX_MEMBLOCK_REGIONS+1];
+	phys_addr_t base;
+	phys_addr_t size;
+};
+
+struct memblock_type {
+	unsigned long cnt;	/* number of regions */
+	unsigned long max;	/* size of the allocated array */
+	struct memblock_region *regions;
 };
 
 struct memblock {
-	unsigned long debug;
-	u64 rmo_size;
-	struct memblock_region memory;
-	struct memblock_region reserved;
+	phys_addr_t current_limit;
+	phys_addr_t memory_size;	/* Updated by memblock_analyze() */
+	struct memblock_type memory;
+	struct memblock_type reserved;
 };
 
 extern struct memblock memblock;
+extern int memblock_debug;
+extern int memblock_can_resize;
 
-extern void __init memblock_init(void);
-extern void __init memblock_analyze(void);
-extern long memblock_add(u64 base, u64 size);
-extern long memblock_remove(u64 base, u64 size);
-extern long __init memblock_free(u64 base, u64 size);
-extern long __init memblock_reserve(u64 base, u64 size);
-extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-				u64 (*nid_range)(u64, u64, int *));
-extern u64 __init memblock_alloc(u64 size, u64 align);
-extern u64 __init memblock_alloc_base(u64 size,
-		u64, u64 max_addr);
-extern u64 __init __memblock_alloc_base(u64 size,
-		u64 align, u64 max_addr);
-extern u64 __init memblock_phys_mem_size(void);
-extern u64 memblock_end_of_DRAM(void);
-extern void __init memblock_enforce_memory_limit(u64 memory_limit);
-extern int __init memblock_is_reserved(u64 addr);
-extern int memblock_is_region_reserved(u64 base, u64 size);
-extern int memblock_find(struct memblock_property *res);
+#define memblock_dbg(fmt, ...) \
+	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
+
+u64 memblock_find_in_range(u64 start, u64 end, u64 size, u64 align);
+int memblock_free_reserved_regions(void);
+int memblock_reserve_reserved_regions(void);
+
+extern void memblock_init(void);
+extern void memblock_analyze(void);
+extern long memblock_add(phys_addr_t base, phys_addr_t size);
+extern long memblock_remove(phys_addr_t base, phys_addr_t size);
+extern long memblock_free(phys_addr_t base, phys_addr_t size);
+extern long memblock_reserve(phys_addr_t base, phys_addr_t size);
+
+/* The numa aware allocator is only available if
+ * CONFIG_ARCH_POPULATES_NODE_MAP is set
+ */
+extern phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align,
+					int nid);
+extern phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
+					    int nid);
+
+extern phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
+
+/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
+#define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
+#define MEMBLOCK_ALLOC_ACCESSIBLE	0
+
+extern phys_addr_t memblock_alloc_base(phys_addr_t size,
+					 phys_addr_t align,
+					 phys_addr_t max_addr);
+extern phys_addr_t __memblock_alloc_base(phys_addr_t size,
+					   phys_addr_t align,
+					   phys_addr_t max_addr);
+extern phys_addr_t memblock_phys_mem_size(void);
+extern phys_addr_t memblock_end_of_DRAM(void);
+extern void memblock_enforce_memory_limit(phys_addr_t memory_limit);
+extern int memblock_is_memory(phys_addr_t addr);
+extern int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
+extern int memblock_is_reserved(phys_addr_t addr);
+extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
 extern void memblock_dump_all(void);
 
-static inline u64
-memblock_size_bytes(struct memblock_region *type, unsigned long region_nr)
+/* Provided by the architecture */
+extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid);
+extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+				   phys_addr_t addr2, phys_addr_t size2);
+
+/**
+ * memblock_set_current_limit - Set the current allocation limit to allow
+ *                         limiting allocations to what is currently
+ *                         accessible during boot
+ * @limit: New limit value (physical address)
+ */
+extern void memblock_set_current_limit(phys_addr_t limit);
+
+
+/*
+ * pfn conversion functions
+ *
+ * While the memory MEMBLOCKs should always be page aligned, the reserved
+ * MEMBLOCKs may not be. This accessor attempt to provide a very clear
+ * idea of what they return for such non aligned MEMBLOCKs.
+ */
+
+/**
+ * memblock_region_memory_base_pfn - Return the lowest pfn intersecting with the memory region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_memory_base_pfn(const struct memblock_region *reg)
 {
-	return type->region[region_nr].size;
-}
-static inline u64
-memblock_size_pages(struct memblock_region *type, unsigned long region_nr)
-{
-	return memblock_size_bytes(type, region_nr) >> PAGE_SHIFT;
-}
-static inline u64
-memblock_start_pfn(struct memblock_region *type, unsigned long region_nr)
-{
-	return type->region[region_nr].base >> PAGE_SHIFT;
-}
-static inline u64
-memblock_end_pfn(struct memblock_region *type, unsigned long region_nr)
-{
-	return memblock_start_pfn(type, region_nr) +
-	       memblock_size_pages(type, region_nr);
+	return PFN_UP(reg->base);
 }
 
-#include <asm/memblock.h>
+/**
+ * memblock_region_memory_end_pfn - Return the end_pfn this region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_memory_end_pfn(const struct memblock_region *reg)
+{
+	return PFN_DOWN(reg->base + reg->size);
+}
+
+/**
+ * memblock_region_reserved_base_pfn - Return the lowest pfn intersecting with the reserved region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_reserved_base_pfn(const struct memblock_region *reg)
+{
+	return PFN_DOWN(reg->base);
+}
+
+/**
+ * memblock_region_reserved_end_pfn - Return the end_pfn this region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_reserved_end_pfn(const struct memblock_region *reg)
+{
+	return PFN_UP(reg->base + reg->size);
+}
+
+#define for_each_memblock(memblock_type, region)					\
+	for (region = memblock.memblock_type.regions;				\
+	     region < (memblock.memblock_type.regions + memblock.memblock_type.cnt);	\
+	     region++)
+
+
+#ifdef ARCH_DISCARD_MEMBLOCK
+#define __init_memblock __init
+#define __initdata_memblock __initdata
+#else
+#define __init_memblock
+#define __initdata_memblock
+#endif
+
+#endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/mfd/tc35892.h b/include/linux/mfd/tc35892.h
index e47f770..eff3094 100644
--- a/include/linux/mfd/tc35892.h
+++ b/include/linux/mfd/tc35892.h
@@ -111,9 +111,13 @@
  * struct tc35892_gpio_platform_data - TC35892 GPIO platform data
  * @gpio_base: first gpio number assigned to TC35892.  A maximum of
  *	       %TC35892_NR_GPIOS GPIOs will be allocated.
+ * @setup: callback for board-specific initialization
+ * @remove: callback for board-specific teardown
  */
 struct tc35892_gpio_platform_data {
 	int gpio_base;
+	void (*setup)(struct tc35892 *tc35892, unsigned gpio_base);
+	void (*remove)(struct tc35892 *tc35892, unsigned gpio_base);
 };
 
 /**
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74949fb..7687228 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1175,6 +1175,8 @@
 						unsigned long max_low_pfn);
 int add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid);
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit);
 void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
 				 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ee7e258..cb57d65 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -299,7 +299,7 @@
 	 * new_owner->mm == mm
 	 * new_owner->alloc_lock is held
 	 */
-	struct task_struct *owner;
+	struct task_struct __rcu *owner;
 #endif
 
 #ifdef CONFIG_PROC_FS
diff --git a/include/linux/module.h b/include/linux/module.h
index aace066..b29e745 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -350,7 +350,10 @@
 	struct tracepoint *tracepoints;
 	unsigned int num_tracepoints;
 #endif
-
+#ifdef HAVE_JUMP_LABEL
+	struct jump_entry *jump_entries;
+	unsigned int num_jump_entries;
+#endif
 #ifdef CONFIG_TRACING
 	const char **trace_bprintk_fmt_start;
 	unsigned int num_trace_bprintk_fmt;
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 91b05c1..05acced 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -10,12 +10,13 @@
 };
 
 /* Helper functions */
-struct irq_desc;
-extern void mask_msi_irq(unsigned int irq);
-extern void unmask_msi_irq(unsigned int irq);
-extern void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
-extern void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
-extern void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
+struct irq_data;
+struct msi_desc;
+extern void mask_msi_irq(struct irq_data *data);
+extern void unmask_msi_irq(struct irq_data *data);
+extern void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+extern void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+extern void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 extern void read_msi_msg(unsigned int irq, struct msi_msg *msg);
 extern void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
 extern void write_msi_msg(unsigned int irq, struct msi_msg *msg);
diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h
index 4522aed..ef66306 100644
--- a/include/linux/ncp_fs.h
+++ b/include/linux/ncp_fs.h
@@ -241,34 +241,6 @@
 /* linux/fs/ncpfs/ncplib_kernel.c */
 int ncp_make_closed(struct inode *);
 
-#define ncp_namespace(i)	(NCP_SERVER(i)->name_space[NCP_FINFO(i)->volNumber])
-
-static inline int ncp_preserve_entry_case(struct inode *i, __u32 nscreator)
-{
-#ifdef CONFIG_NCPFS_SMALLDOS
-	int ns = ncp_namespace(i);
-
-	if ((ns == NW_NS_DOS)
-#ifdef CONFIG_NCPFS_OS2_NS
-		|| ((ns == NW_NS_OS2) && (nscreator == NW_NS_DOS))
-#endif /* CONFIG_NCPFS_OS2_NS */
-				)
-		return 0;
-#endif /* CONFIG_NCPFS_SMALLDOS */
-	return 1;
-}
-
-#define ncp_preserve_case(i)	(ncp_namespace(i) != NW_NS_DOS)
-
-static inline int ncp_case_sensitive(struct inode *i)
-{
-#ifdef CONFIG_NCPFS_NFS_NS
-	return ncp_namespace(i) == NW_NS_NFS;
-#else
-	return 0;
-#endif	/* CONFIG_NCPFS_NFS_NS */
-} 
-
 #endif				/* __KERNEL__ */
 
 #endif				/* _LINUX_NCP_FS_H */
diff --git a/include/linux/ncp_fs_sb.h b/include/linux/ncp_fs_sb.h
index 8da05bc..d64b0e8 100644
--- a/include/linux/ncp_fs_sb.h
+++ b/include/linux/ncp_fs_sb.h
@@ -62,6 +62,7 @@
 	int ncp_reply_size;
 
 	int root_setuped;
+	struct mutex root_setup_lock;
 
 	/* info for packet signing */
 	int sign_wanted;	/* 1=Server needs signed packets */
@@ -81,13 +82,14 @@
 		size_t	len;
 		void*	data;
 	} priv;
+	struct rw_semaphore auth_rwsem;
 
 	/* nls info: codepage for volume and charset for I/O */
 	struct nls_table *nls_vol;
 	struct nls_table *nls_io;
 
 	/* maximum age in jiffies */
-	int dentry_ttl;
+	atomic_t dentry_ttl;
 
 	/* miscellaneous */
 	unsigned int flags;
diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
index 9ed534c..70cd060 100644
--- a/include/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -39,8 +39,9 @@
 	CTA_TUPLE_MASTER,
 	CTA_NAT_SEQ_ADJ_ORIG,
 	CTA_NAT_SEQ_ADJ_REPLY,
-	CTA_SECMARK,
+	CTA_SECMARK,		/* obsolete */
 	CTA_ZONE,
+	CTA_SECCTX,
 	__CTA_MAX
 };
 #define CTA_MAX (__CTA_MAX - 1)
@@ -172,4 +173,11 @@
 };
 #define CTA_HELP_MAX (__CTA_HELP_MAX - 1)
 
+enum ctattr_secctx {
+	CTA_SECCTX_UNSPEC,
+	CTA_SECCTX_NAME,
+	__CTA_SECCTX_MAX
+};
+#define CTA_SECCTX_MAX (__CTA_SECCTX_MAX - 1)
+
 #endif /* _IPCONNTRACK_NETLINK_H */
diff --git a/include/linux/netfilter/xt_SECMARK.h b/include/linux/netfilter/xt_SECMARK.h
index 6fcd344..989092b 100644
--- a/include/linux/netfilter/xt_SECMARK.h
+++ b/include/linux/netfilter/xt_SECMARK.h
@@ -11,18 +11,12 @@
  * packets are being marked for.
  */
 #define SECMARK_MODE_SEL	0x01		/* SELinux */
-#define SECMARK_SELCTX_MAX	256
-
-struct xt_secmark_target_selinux_info {
-	__u32 selsid;
-	char selctx[SECMARK_SELCTX_MAX];
-};
+#define SECMARK_SECCTX_MAX	256
 
 struct xt_secmark_target_info {
 	__u8 mode;
-	union {
-		struct xt_secmark_target_selinux_info sel;
-	} u;
+	__u32 secid;
+	char secctx[SECMARK_SECCTX_MAX];
 };
 
 #endif /*_XT_SECMARK_H_target */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 508f8cf..d0edf7d 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -185,7 +185,7 @@
 	struct nfs4_cached_acl	*nfs4_acl;
         /* NFSv4 state */
 	struct list_head	open_states;
-	struct nfs_delegation	*delegation;
+	struct nfs_delegation __rcu *delegation;
 	fmode_t			 delegation_state;
 	struct rw_semaphore	rwsem;
 #endif /* CONFIG_NFS_V4*/
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index b2f1a4d..2026f9e 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -49,28 +49,28 @@
 
 struct notifier_block {
 	int (*notifier_call)(struct notifier_block *, unsigned long, void *);
-	struct notifier_block *next;
+	struct notifier_block __rcu *next;
 	int priority;
 };
 
 struct atomic_notifier_head {
 	spinlock_t lock;
-	struct notifier_block *head;
+	struct notifier_block __rcu *head;
 };
 
 struct blocking_notifier_head {
 	struct rw_semaphore rwsem;
-	struct notifier_block *head;
+	struct notifier_block __rcu *head;
 };
 
 struct raw_notifier_head {
-	struct notifier_block *head;
+	struct notifier_block __rcu *head;
 };
 
 struct srcu_notifier_head {
 	struct mutex mutex;
 	struct srcu_struct srcu;
-	struct notifier_block *head;
+	struct notifier_block __rcu *head;
 };
 
 #define ATOMIC_INIT_NOTIFIER_HEAD(name) do {	\
diff --git a/include/linux/opp.h b/include/linux/opp.h
new file mode 100644
index 0000000..5449945
--- /dev/null
+++ b/include/linux/opp.h
@@ -0,0 +1,105 @@
+/*
+ * Generic OPP Interface
+ *
+ * Copyright (C) 2009-2010 Texas Instruments Incorporated.
+ *	Nishanth Menon
+ *	Romit Dasgupta
+ *	Kevin Hilman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_OPP_H__
+#define __LINUX_OPP_H__
+
+#include <linux/err.h>
+#include <linux/cpufreq.h>
+
+struct opp;
+
+#if defined(CONFIG_PM_OPP)
+
+unsigned long opp_get_voltage(struct opp *opp);
+
+unsigned long opp_get_freq(struct opp *opp);
+
+int opp_get_opp_count(struct device *dev);
+
+struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
+				bool available);
+
+struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq);
+
+struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq);
+
+int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt);
+
+int opp_enable(struct device *dev, unsigned long freq);
+
+int opp_disable(struct device *dev, unsigned long freq);
+
+#else
+static inline unsigned long opp_get_voltage(struct opp *opp)
+{
+	return 0;
+}
+
+static inline unsigned long opp_get_freq(struct opp *opp)
+{
+	return 0;
+}
+
+static inline int opp_get_opp_count(struct device *dev)
+{
+	return 0;
+}
+
+static inline struct opp *opp_find_freq_exact(struct device *dev,
+					unsigned long freq, bool available)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct opp *opp_find_freq_floor(struct device *dev,
+					unsigned long *freq)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct opp *opp_find_freq_ceil(struct device *dev,
+					unsigned long *freq)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int opp_add(struct device *dev, unsigned long freq,
+					unsigned long u_volt)
+{
+	return -EINVAL;
+}
+
+static inline int opp_enable(struct device *dev, unsigned long freq)
+{
+	return 0;
+}
+
+static inline int opp_disable(struct device *dev, unsigned long freq)
+{
+	return 0;
+}
+#endif		/* CONFIG_PM */
+
+#if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP)
+int opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table);
+#else
+static inline int opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table)
+{
+	return -EINVAL;
+}
+#endif		/* CONFIG_CPU_FREQ */
+
+#endif		/* __LINUX_OPP_H__ */
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 5171639..32fb812 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -15,6 +15,7 @@
 
 #include <linux/types.h>
 #include <linux/spinlock.h>
+#include <linux/init.h>
 #include <asm/atomic.h>
  
 /* Each escaped entry is prefixed by ESCAPE_CODE
@@ -185,4 +186,10 @@
 int oprofile_add_data64(struct op_entry *entry, u64 val);
 int oprofile_write_commit(struct op_entry *entry);
 
+#ifdef CONFIG_PERF_EVENTS
+int __init oprofile_perf_init(struct oprofile_operations *ops);
+void oprofile_perf_exit(void);
+char *op_name_from_perf_id(void);
+#endif /* CONFIG_PERF_EVENTS */
+
 #endif /* OPROFILE_H */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 570fdde..e4471b2 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -517,6 +517,7 @@
 #define PCI_DEVICE_ID_AMD_11H_NB_DRAM	0x1302
 #define PCI_DEVICE_ID_AMD_11H_NB_MISC	0x1303
 #define PCI_DEVICE_ID_AMD_11H_NB_LINK	0x1304
+#define PCI_DEVICE_ID_AMD_15H_NB_MISC	0x1603
 #define PCI_DEVICE_ID_AMD_LANCE		0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME	0x2001
 #define PCI_DEVICE_ID_AMD_SCSI		0x2020
@@ -742,6 +743,7 @@
 #define PCI_DEVICE_ID_HP_CISSC		0x3230
 #define PCI_DEVICE_ID_HP_CISSD		0x3238
 #define PCI_DEVICE_ID_HP_CISSE		0x323a
+#define PCI_DEVICE_ID_HP_CISSF		0x323b
 #define PCI_DEVICE_ID_HP_ZX2_IOC	0x4031
 
 #define PCI_VENDOR_ID_PCTECH		0x1042
@@ -2315,6 +2317,14 @@
 #define PCI_DEVICE_ID_P4080		0x0401
 #define PCI_DEVICE_ID_P4040E		0x0408
 #define PCI_DEVICE_ID_P4040		0x0409
+#define PCI_DEVICE_ID_P2040E		0x0410
+#define PCI_DEVICE_ID_P2040		0x0411
+#define PCI_DEVICE_ID_P3041E		0x041E
+#define PCI_DEVICE_ID_P3041		0x041F
+#define PCI_DEVICE_ID_P5020E		0x0420
+#define PCI_DEVICE_ID_P5020		0x0421
+#define PCI_DEVICE_ID_P5010E		0x0428
+#define PCI_DEVICE_ID_P5010		0x0429
 #define PCI_DEVICE_ID_MPC8641		0x7010
 #define PCI_DEVICE_ID_MPC8641D		0x7011
 #define PCI_DEVICE_ID_MPC8610		0x7018
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index ce2dc65..018db9a 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -139,6 +139,27 @@
 	__aligned(PAGE_SIZE)
 
 /*
+ * Declaration/definition used for per-CPU variables that must be read mostly.
+ */
+#define DECLARE_PER_CPU_READ_MOSTLY(type, name)			\
+	DECLARE_PER_CPU_SECTION(type, name, "..readmostly")
+
+#define DEFINE_PER_CPU_READ_MOSTLY(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, "..readmostly")
+
+/*
+ * Declaration/definition used for large per-CPU variables that must be
+ * aligned to something larger than the pagesize.
+ */
+#define DECLARE_PER_CPU_MULTIPAGE_ALIGNED(type, name, size)		\
+	DECLARE_PER_CPU_SECTION(type, name, "..page_aligned")		\
+	__aligned(size)
+
+#define DEFINE_PER_CPU_MULTIPAGE_ALIGNED(type, name, size)		\
+	DEFINE_PER_CPU_SECTION(type, name, "..page_aligned")		\
+	__aligned(size)
+
+/*
  * Intermodule exports for per-CPU variables.  sparse forgets about
  * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to
  * noop if __CHECKER__.
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 49466b1..5095b83 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -39,10 +39,17 @@
 	preempt_enable();				\
 } while (0)
 
-#ifdef CONFIG_SMP
+#define get_cpu_ptr(var) ({				\
+	preempt_disable();				\
+	this_cpu_ptr(var); })
+
+#define put_cpu_ptr(var) do {				\
+	(void)(var);					\
+	preempt_enable();				\
+} while (0)
 
 /* minimum unit size, also is the maximum supported allocation size */
-#define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
+#define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(32 << 10)
 
 /*
  * Percpu allocator can serve percpu allocations before slab is
@@ -137,37 +144,20 @@
  * dynamically allocated. Non-atomic access to the current CPU's
  * version should probably be combined with get_cpu()/put_cpu().
  */
+#ifdef CONFIG_SMP
 #define per_cpu_ptr(ptr, cpu)	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
+#else
+#define per_cpu_ptr(ptr, cpu)	({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); })
+#endif
 
 extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
 extern bool is_kernel_percpu_address(unsigned long addr);
 
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+#if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
 extern void __init setup_per_cpu_areas(void);
 #endif
 extern void __init percpu_init_late(void);
 
-#else /* CONFIG_SMP */
-
-#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); })
-
-/* can't distinguish from other static vars, always false */
-static inline bool is_kernel_percpu_address(unsigned long addr)
-{
-	return false;
-}
-
-static inline void __init setup_per_cpu_areas(void) { }
-
-static inline void __init percpu_init_late(void) { }
-
-static inline void *pcpu_lpage_remapped(void *kaddr)
-{
-	return NULL;
-}
-
-#endif /* CONFIG_SMP */
-
 extern void __percpu *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void __percpu *__pdata);
 extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 716f99b..057bf22 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -486,6 +486,8 @@
 #include <linux/workqueue.h>
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
+#include <linux/irq_work.h>
+#include <linux/jump_label_ref.h>
 #include <asm/atomic.h>
 #include <asm/local.h>
 
@@ -529,16 +531,22 @@
 			int		last_cpu;
 		};
 		struct { /* software */
-			s64		remaining;
 			struct hrtimer	hrtimer;
 		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		struct { /* breakpoint */
 			struct arch_hw_breakpoint	info;
 			struct list_head		bp_list;
+			/*
+			 * Crufty hack to avoid the chicken and egg
+			 * problem hw_breakpoint has with context
+			 * creation and event initalization.
+			 */
+			struct task_struct		*bp_target;
 		};
 #endif
 	};
+	int				state;
 	local64_t			prev_count;
 	u64				sample_period;
 	u64				last_period;
@@ -550,6 +558,13 @@
 #endif
 };
 
+/*
+ * hw_perf_event::state flags
+ */
+#define PERF_HES_STOPPED	0x01 /* the counter is stopped */
+#define PERF_HES_UPTODATE	0x02 /* event->count up-to-date */
+#define PERF_HES_ARCH		0x04
+
 struct perf_event;
 
 /*
@@ -561,36 +576,70 @@
  * struct pmu - generic performance monitoring unit
  */
 struct pmu {
-	int (*enable)			(struct perf_event *event);
-	void (*disable)			(struct perf_event *event);
-	int (*start)			(struct perf_event *event);
-	void (*stop)			(struct perf_event *event);
+	struct list_head		entry;
+
+	int * __percpu			pmu_disable_count;
+	struct perf_cpu_context * __percpu pmu_cpu_context;
+	int				task_ctx_nr;
+
+	/*
+	 * Fully disable/enable this PMU, can be used to protect from the PMI
+	 * as well as for lazy/batch writing of the MSRs.
+	 */
+	void (*pmu_enable)		(struct pmu *pmu); /* optional */
+	void (*pmu_disable)		(struct pmu *pmu); /* optional */
+
+	/*
+	 * Try and initialize the event for this PMU.
+	 * Should return -ENOENT when the @event doesn't match this PMU.
+	 */
+	int (*event_init)		(struct perf_event *event);
+
+#define PERF_EF_START	0x01		/* start the counter when adding    */
+#define PERF_EF_RELOAD	0x02		/* reload the counter when starting */
+#define PERF_EF_UPDATE	0x04		/* update the counter when stopping */
+
+	/*
+	 * Adds/Removes a counter to/from the PMU, can be done inside
+	 * a transaction, see the ->*_txn() methods.
+	 */
+	int  (*add)			(struct perf_event *event, int flags);
+	void (*del)			(struct perf_event *event, int flags);
+
+	/*
+	 * Starts/Stops a counter present on the PMU. The PMI handler
+	 * should stop the counter when perf_event_overflow() returns
+	 * !0. ->start() will be used to continue.
+	 */
+	void (*start)			(struct perf_event *event, int flags);
+	void (*stop)			(struct perf_event *event, int flags);
+
+	/*
+	 * Updates the counter value of the event.
+	 */
 	void (*read)			(struct perf_event *event);
-	void (*unthrottle)		(struct perf_event *event);
 
 	/*
-	 * Group events scheduling is treated as a transaction, add group
-	 * events as a whole and perform one schedulability test. If the test
-	 * fails, roll back the whole group
+	 * Group events scheduling is treated as a transaction, add
+	 * group events as a whole and perform one schedulability test.
+	 * If the test fails, roll back the whole group
+	 *
+	 * Start the transaction, after this ->add() doesn't need to
+	 * do schedulability tests.
 	 */
-
+	void (*start_txn)	(struct pmu *pmu); /* optional */
 	/*
-	 * Start the transaction, after this ->enable() doesn't need
-	 * to do schedulability tests.
-	 */
-	void (*start_txn)	(const struct pmu *pmu);
-	/*
-	 * If ->start_txn() disabled the ->enable() schedulability test
+	 * If ->start_txn() disabled the ->add() schedulability test
 	 * then ->commit_txn() is required to perform one. On success
 	 * the transaction is closed. On error the transaction is kept
 	 * open until ->cancel_txn() is called.
 	 */
-	int  (*commit_txn)	(const struct pmu *pmu);
+	int  (*commit_txn)	(struct pmu *pmu); /* optional */
 	/*
-	 * Will cancel the transaction, assumes ->disable() is called for
-	 * each successfull ->enable() during the transaction.
+	 * Will cancel the transaction, assumes ->del() is called
+	 * for each successfull ->add() during the transaction.
 	 */
-	void (*cancel_txn)	(const struct pmu *pmu);
+	void (*cancel_txn)	(struct pmu *pmu); /* optional */
 };
 
 /**
@@ -631,11 +680,6 @@
 	void				*data_pages[0];
 };
 
-struct perf_pending_entry {
-	struct perf_pending_entry *next;
-	void (*func)(struct perf_pending_entry *);
-};
-
 struct perf_sample_data;
 
 typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
@@ -656,6 +700,7 @@
 
 #define PERF_ATTACH_CONTEXT	0x01
 #define PERF_ATTACH_GROUP	0x02
+#define PERF_ATTACH_TASK	0x04
 
 /**
  * struct perf_event - performance event kernel representation:
@@ -669,7 +714,7 @@
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
-	const struct pmu		*pmu;
+	struct pmu			*pmu;
 
 	enum perf_event_active_state	state;
 	unsigned int			attach_state;
@@ -743,7 +788,7 @@
 	int				pending_wakeup;
 	int				pending_kill;
 	int				pending_disable;
-	struct perf_pending_entry	pending;
+	struct irq_work			pending;
 
 	atomic_t			event_limit;
 
@@ -763,12 +808,19 @@
 #endif /* CONFIG_PERF_EVENTS */
 };
 
+enum perf_event_context_type {
+	task_context,
+	cpu_context,
+};
+
 /**
  * struct perf_event_context - event context structure
  *
  * Used as a container for task events and CPU events as well:
  */
 struct perf_event_context {
+	enum perf_event_context_type	type;
+	struct pmu			*pmu;
 	/*
 	 * Protect the states of the events in the list,
 	 * nr_active, and the list:
@@ -808,6 +860,12 @@
 	struct rcu_head			rcu_head;
 };
 
+/*
+ * Number of contexts where an event can trigger:
+ * 	task, softirq, hardirq, nmi.
+ */
+#define PERF_NR_CONTEXTS	4
+
 /**
  * struct perf_event_cpu_context - per cpu event context structure
  */
@@ -815,18 +873,9 @@
 	struct perf_event_context	ctx;
 	struct perf_event_context	*task_ctx;
 	int				active_oncpu;
-	int				max_pertask;
 	int				exclusive;
-	struct swevent_hlist		*swevent_hlist;
-	struct mutex			hlist_mutex;
-	int				hlist_refcount;
-
-	/*
-	 * Recursion avoidance:
-	 *
-	 * task, softirq, irq, nmi context
-	 */
-	int				recursion[4];
+	struct list_head		rotation_list;
+	int				jiffies_interval;
 };
 
 struct perf_output_handle {
@@ -842,26 +891,34 @@
 
 #ifdef CONFIG_PERF_EVENTS
 
-/*
- * Set by architecture code:
- */
-extern int perf_max_events;
+extern int perf_pmu_register(struct pmu *pmu);
+extern void perf_pmu_unregister(struct pmu *pmu);
 
-extern const struct pmu *hw_perf_event_init(struct perf_event *event);
+extern int perf_num_counters(void);
+extern const char *perf_pmu_name(void);
+extern void __perf_event_task_sched_in(struct task_struct *task);
+extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
 
-extern void perf_event_task_sched_in(struct task_struct *task);
-extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
-extern void perf_event_task_tick(struct task_struct *task);
+extern atomic_t perf_task_events;
+
+static inline void perf_event_task_sched_in(struct task_struct *task)
+{
+	COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+}
+
+static inline
+void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
+{
+	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+}
+
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
-extern void set_perf_event_pending(void);
-extern void perf_event_do_pending(void);
+extern void perf_event_delayed_put(struct task_struct *task);
 extern void perf_event_print_debug(void);
-extern void __perf_disable(void);
-extern bool __perf_enable(void);
-extern void perf_disable(void);
-extern void perf_enable(void);
+extern void perf_pmu_disable(struct pmu *pmu);
+extern void perf_pmu_enable(struct pmu *pmu);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
 extern void perf_event_update_userpage(struct perf_event *event);
@@ -869,7 +926,7 @@
 extern struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr,
 				int cpu,
-				pid_t pid,
+				struct task_struct *task,
 				perf_overflow_handler_t callback);
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
@@ -920,14 +977,7 @@
  */
 static inline int is_software_event(struct perf_event *event)
 {
-	switch (event->attr.type) {
-	case PERF_TYPE_SOFTWARE:
-	case PERF_TYPE_TRACEPOINT:
-	/* for now the breakpoint stuff also works as software event */
-	case PERF_TYPE_BREAKPOINT:
-		return 1;
-	}
-	return 0;
+	return event->pmu->task_ctx_nr == perf_sw_context;
 }
 
 extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
@@ -954,18 +1004,20 @@
 	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
-static inline void
+static __always_inline void
 perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 {
-	if (atomic_read(&perf_swevent_enabled[event_id])) {
-		struct pt_regs hot_regs;
+	struct pt_regs hot_regs;
 
-		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs);
-			regs = &hot_regs;
-		}
-		__perf_sw_event(event_id, nr, nmi, regs, addr);
+	JUMP_LABEL(&perf_swevent_enabled[event_id], have_event);
+	return;
+
+have_event:
+	if (!regs) {
+		perf_fetch_caller_regs(&hot_regs);
+		regs = &hot_regs;
 	}
+	__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -976,7 +1028,21 @@
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
-extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+/* Callchains */
+DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
+
+extern void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs);
+
+
+static inline void
+perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
+		entry->ip[entry->nr++] = ip;
+}
 
 extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
@@ -1019,21 +1085,18 @@
 extern void perf_swevent_put_recursion_context(int rctx);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
+extern void perf_event_task_tick(void);
 #else
 static inline void
 perf_event_task_sched_in(struct task_struct *task)			{ }
 static inline void
 perf_event_task_sched_out(struct task_struct *task,
 			    struct task_struct *next)			{ }
-static inline void
-perf_event_task_tick(struct task_struct *task)				{ }
 static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)	{ }
 static inline void perf_event_free_task(struct task_struct *task)	{ }
-static inline void perf_event_do_pending(void)				{ }
+static inline void perf_event_delayed_put(struct task_struct *task)	{ }
 static inline void perf_event_print_debug(void)				{ }
-static inline void perf_disable(void)					{ }
-static inline void perf_enable(void)					{ }
 static inline int perf_event_task_disable(void)				{ return -EINVAL; }
 static inline int perf_event_task_enable(void)				{ return -EINVAL; }
 
@@ -1056,6 +1119,7 @@
 static inline void perf_swevent_put_recursion_context(int rctx)		{ }
 static inline void perf_event_enable(struct perf_event *event)		{ }
 static inline void perf_event_disable(struct perf_event *event)		{ }
+static inline void perf_event_task_tick(void)				{ }
 #endif
 
 #define perf_output_put(handle, x) \
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 52e8c55..40f3f45 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -41,6 +41,12 @@
 
 struct device;
 
+#ifdef CONFIG_PM
+extern const char power_group_name[];		/* = "power" */
+#else
+#define power_group_name	NULL
+#endif
+
 typedef struct pm_message {
 	int event;
 } pm_message_t;
@@ -438,6 +444,9 @@
  *
  * RPM_REQ_SUSPEND	Run the device bus type's ->runtime_suspend() callback
  *
+ * RPM_REQ_AUTOSUSPEND	Same as RPM_REQ_SUSPEND, but not until the device has
+ *			been inactive for as long as power.autosuspend_delay
+ *
  * RPM_REQ_RESUME	Run the device bus type's ->runtime_resume() callback
  */
 
@@ -445,26 +454,28 @@
 	RPM_REQ_NONE = 0,
 	RPM_REQ_IDLE,
 	RPM_REQ_SUSPEND,
+	RPM_REQ_AUTOSUSPEND,
 	RPM_REQ_RESUME,
 };
 
+struct wakeup_source;
+
 struct dev_pm_info {
 	pm_message_t		power_state;
 	unsigned int		can_wakeup:1;
-	unsigned int		should_wakeup:1;
 	unsigned		async_suspend:1;
 	enum dpm_state		status;		/* Owned by the PM core */
+	spinlock_t		lock;
 #ifdef CONFIG_PM_SLEEP
 	struct list_head	entry;
 	struct completion	completion;
-	unsigned long		wakeup_count;
+	struct wakeup_source	*wakeup;
 #endif
 #ifdef CONFIG_PM_RUNTIME
 	struct timer_list	suspend_timer;
 	unsigned long		timer_expires;
 	struct work_struct	work;
 	wait_queue_head_t	wait_queue;
-	spinlock_t		lock;
 	atomic_t		usage_count;
 	atomic_t		child_count;
 	unsigned int		disable_depth:3;
@@ -474,9 +485,14 @@
 	unsigned int		deferred_resume:1;
 	unsigned int		run_wake:1;
 	unsigned int		runtime_auto:1;
+	unsigned int		no_callbacks:1;
+	unsigned int		use_autosuspend:1;
+	unsigned int		timer_autosuspends:1;
 	enum rpm_request	request;
 	enum rpm_status		runtime_status;
 	int			runtime_error;
+	int			autosuspend_delay;
+	unsigned long		last_busy;
 	unsigned long		active_jiffies;
 	unsigned long		suspended_jiffies;
 	unsigned long		accounting_timestamp;
@@ -558,12 +574,7 @@
 		__suspend_report_result(__func__, fn, ret);		\
 	} while (0)
 
-extern void device_pm_wait_for_dev(struct device *sub, struct device *dev);
-
-/* drivers/base/power/wakeup.c */
-extern void pm_wakeup_event(struct device *dev, unsigned int msec);
-extern void pm_stay_awake(struct device *dev);
-extern void pm_relax(void);
+extern int device_pm_wait_for_dev(struct device *sub, struct device *dev);
 #else /* !CONFIG_PM_SLEEP */
 
 #define device_pm_lock() do {} while (0)
@@ -576,11 +587,10 @@
 
 #define suspend_report_result(fn, ret)		do {} while (0)
 
-static inline void device_pm_wait_for_dev(struct device *a, struct device *b) {}
-
-static inline void pm_wakeup_event(struct device *dev, unsigned int msec) {}
-static inline void pm_stay_awake(struct device *dev) {}
-static inline void pm_relax(void) {}
+static inline int device_pm_wait_for_dev(struct device *a, struct device *b)
+{
+	return 0;
+}
 #endif /* !CONFIG_PM_SLEEP */
 
 /* How to reorder dpm_list after device_move() */
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 6e81888..3ec2358 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -12,18 +12,24 @@
 #include <linux/device.h>
 #include <linux/pm.h>
 
+#include <linux/jiffies.h>
+
+/* Runtime PM flag argument bits */
+#define RPM_ASYNC		0x01	/* Request is asynchronous */
+#define RPM_NOWAIT		0x02	/* Don't wait for concurrent
+					    state change */
+#define RPM_GET_PUT		0x04	/* Increment/decrement the
+					    usage_count */
+#define RPM_AUTO		0x08	/* Use autosuspend_delay */
+
 #ifdef CONFIG_PM_RUNTIME
 
 extern struct workqueue_struct *pm_wq;
 
-extern int pm_runtime_idle(struct device *dev);
-extern int pm_runtime_suspend(struct device *dev);
-extern int pm_runtime_resume(struct device *dev);
-extern int pm_request_idle(struct device *dev);
+extern int __pm_runtime_idle(struct device *dev, int rpmflags);
+extern int __pm_runtime_suspend(struct device *dev, int rpmflags);
+extern int __pm_runtime_resume(struct device *dev, int rpmflags);
 extern int pm_schedule_suspend(struct device *dev, unsigned int delay);
-extern int pm_request_resume(struct device *dev);
-extern int __pm_runtime_get(struct device *dev, bool sync);
-extern int __pm_runtime_put(struct device *dev, bool sync);
 extern int __pm_runtime_set_status(struct device *dev, unsigned int status);
 extern int pm_runtime_barrier(struct device *dev);
 extern void pm_runtime_enable(struct device *dev);
@@ -33,6 +39,10 @@
 extern int pm_generic_runtime_idle(struct device *dev);
 extern int pm_generic_runtime_suspend(struct device *dev);
 extern int pm_generic_runtime_resume(struct device *dev);
+extern void pm_runtime_no_callbacks(struct device *dev);
+extern void __pm_runtime_use_autosuspend(struct device *dev, bool use);
+extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
+extern unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
 
 static inline bool pm_children_suspended(struct device *dev)
 {
@@ -70,19 +80,29 @@
 	return dev->power.runtime_status == RPM_SUSPENDED;
 }
 
+static inline void pm_runtime_mark_last_busy(struct device *dev)
+{
+	ACCESS_ONCE(dev->power.last_busy) = jiffies;
+}
+
 #else /* !CONFIG_PM_RUNTIME */
 
-static inline int pm_runtime_idle(struct device *dev) { return -ENOSYS; }
-static inline int pm_runtime_suspend(struct device *dev) { return -ENOSYS; }
-static inline int pm_runtime_resume(struct device *dev) { return 0; }
-static inline int pm_request_idle(struct device *dev) { return -ENOSYS; }
+static inline int __pm_runtime_idle(struct device *dev, int rpmflags)
+{
+	return -ENOSYS;
+}
+static inline int __pm_runtime_suspend(struct device *dev, int rpmflags)
+{
+	return -ENOSYS;
+}
+static inline int __pm_runtime_resume(struct device *dev, int rpmflags)
+{
+	return 1;
+}
 static inline int pm_schedule_suspend(struct device *dev, unsigned int delay)
 {
 	return -ENOSYS;
 }
-static inline int pm_request_resume(struct device *dev) { return 0; }
-static inline int __pm_runtime_get(struct device *dev, bool sync) { return 1; }
-static inline int __pm_runtime_put(struct device *dev, bool sync) { return 0; }
 static inline int __pm_runtime_set_status(struct device *dev,
 					    unsigned int status) { return 0; }
 static inline int pm_runtime_barrier(struct device *dev) { return 0; }
@@ -102,27 +122,82 @@
 static inline int pm_generic_runtime_idle(struct device *dev) { return 0; }
 static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; }
 static inline int pm_generic_runtime_resume(struct device *dev) { return 0; }
+static inline void pm_runtime_no_callbacks(struct device *dev) {}
+
+static inline void pm_runtime_mark_last_busy(struct device *dev) {}
+static inline void __pm_runtime_use_autosuspend(struct device *dev,
+						bool use) {}
+static inline void pm_runtime_set_autosuspend_delay(struct device *dev,
+						int delay) {}
+static inline unsigned long pm_runtime_autosuspend_expiration(
+				struct device *dev) { return 0; }
 
 #endif /* !CONFIG_PM_RUNTIME */
 
+static inline int pm_runtime_idle(struct device *dev)
+{
+	return __pm_runtime_idle(dev, 0);
+}
+
+static inline int pm_runtime_suspend(struct device *dev)
+{
+	return __pm_runtime_suspend(dev, 0);
+}
+
+static inline int pm_runtime_autosuspend(struct device *dev)
+{
+	return __pm_runtime_suspend(dev, RPM_AUTO);
+}
+
+static inline int pm_runtime_resume(struct device *dev)
+{
+	return __pm_runtime_resume(dev, 0);
+}
+
+static inline int pm_request_idle(struct device *dev)
+{
+	return __pm_runtime_idle(dev, RPM_ASYNC);
+}
+
+static inline int pm_request_resume(struct device *dev)
+{
+	return __pm_runtime_resume(dev, RPM_ASYNC);
+}
+
+static inline int pm_request_autosuspend(struct device *dev)
+{
+	return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO);
+}
+
 static inline int pm_runtime_get(struct device *dev)
 {
-	return __pm_runtime_get(dev, false);
+	return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC);
 }
 
 static inline int pm_runtime_get_sync(struct device *dev)
 {
-	return __pm_runtime_get(dev, true);
+	return __pm_runtime_resume(dev, RPM_GET_PUT);
 }
 
 static inline int pm_runtime_put(struct device *dev)
 {
-	return __pm_runtime_put(dev, false);
+	return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
+}
+
+static inline int pm_runtime_put_autosuspend(struct device *dev)
+{
+	return __pm_runtime_suspend(dev,
+	    RPM_GET_PUT | RPM_ASYNC | RPM_AUTO);
 }
 
 static inline int pm_runtime_put_sync(struct device *dev)
 {
-	return __pm_runtime_put(dev, true);
+	return __pm_runtime_idle(dev, RPM_GET_PUT);
+}
+
+static inline int pm_runtime_put_sync_autosuspend(struct device *dev)
+{
+	return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO);
 }
 
 static inline int pm_runtime_set_active(struct device *dev)
@@ -140,4 +215,14 @@
 	__pm_runtime_disable(dev, true);
 }
 
+static inline void pm_runtime_use_autosuspend(struct device *dev)
+{
+	__pm_runtime_use_autosuspend(dev, true);
+}
+
+static inline void pm_runtime_dont_use_autosuspend(struct device *dev)
+{
+	__pm_runtime_use_autosuspend(dev, false);
+}
+
 #endif
diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h
index 76aca48..9cff00d 100644
--- a/include/linux/pm_wakeup.h
+++ b/include/linux/pm_wakeup.h
@@ -2,6 +2,7 @@
  *  pm_wakeup.h - Power management wakeup interface
  *
  *  Copyright (C) 2008 Alan Stern
+ *  Copyright (C) 2010 Rafael J. Wysocki, Novell Inc.
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -27,18 +28,39 @@
 
 #include <linux/types.h>
 
-#ifdef CONFIG_PM
-
-/* Changes to device_may_wakeup take effect on the next pm state change.
+/**
+ * struct wakeup_source - Representation of wakeup sources
  *
- * By default, most devices should leave wakeup disabled.  The exceptions
- * are devices that everyone expects to be wakeup sources: keyboards,
- * power buttons, possibly network interfaces, etc.
+ * @total_time: Total time this wakeup source has been active.
+ * @max_time: Maximum time this wakeup source has been continuously active.
+ * @last_time: Monotonic clock when the wakeup source's was activated last time.
+ * @event_count: Number of signaled wakeup events.
+ * @active_count: Number of times the wakeup sorce was activated.
+ * @relax_count: Number of times the wakeup sorce was deactivated.
+ * @hit_count: Number of times the wakeup sorce might abort system suspend.
+ * @active: Status of the wakeup source.
  */
-static inline void device_init_wakeup(struct device *dev, bool val)
-{
-	dev->power.can_wakeup = dev->power.should_wakeup = val;
-}
+struct wakeup_source {
+	char 			*name;
+	struct list_head	entry;
+	spinlock_t		lock;
+	struct timer_list	timer;
+	unsigned long		timer_expires;
+	ktime_t total_time;
+	ktime_t max_time;
+	ktime_t last_time;
+	unsigned long		event_count;
+	unsigned long		active_count;
+	unsigned long		relax_count;
+	unsigned long		hit_count;
+	unsigned int		active:1;
+};
+
+#ifdef CONFIG_PM_SLEEP
+
+/*
+ * Changes to device_may_wakeup take effect on the next pm state change.
+ */
 
 static inline void device_set_wakeup_capable(struct device *dev, bool capable)
 {
@@ -50,23 +72,32 @@
 	return dev->power.can_wakeup;
 }
 
-static inline void device_set_wakeup_enable(struct device *dev, bool enable)
-{
-	dev->power.should_wakeup = enable;
-}
+
 
 static inline bool device_may_wakeup(struct device *dev)
 {
-	return dev->power.can_wakeup && dev->power.should_wakeup;
+	return dev->power.can_wakeup && !!dev->power.wakeup;
 }
 
-#else /* !CONFIG_PM */
+/* drivers/base/power/wakeup.c */
+extern struct wakeup_source *wakeup_source_create(const char *name);
+extern void wakeup_source_destroy(struct wakeup_source *ws);
+extern void wakeup_source_add(struct wakeup_source *ws);
+extern void wakeup_source_remove(struct wakeup_source *ws);
+extern struct wakeup_source *wakeup_source_register(const char *name);
+extern void wakeup_source_unregister(struct wakeup_source *ws);
+extern int device_wakeup_enable(struct device *dev);
+extern int device_wakeup_disable(struct device *dev);
+extern int device_init_wakeup(struct device *dev, bool val);
+extern int device_set_wakeup_enable(struct device *dev, bool enable);
+extern void __pm_stay_awake(struct wakeup_source *ws);
+extern void pm_stay_awake(struct device *dev);
+extern void __pm_relax(struct wakeup_source *ws);
+extern void pm_relax(struct device *dev);
+extern void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec);
+extern void pm_wakeup_event(struct device *dev, unsigned int msec);
 
-/* For some reason the following routines work even without CONFIG_PM */
-static inline void device_init_wakeup(struct device *dev, bool val)
-{
-	dev->power.can_wakeup = val;
-}
+#else /* !CONFIG_PM_SLEEP */
 
 static inline void device_set_wakeup_capable(struct device *dev, bool capable)
 {
@@ -78,15 +109,63 @@
 	return dev->power.can_wakeup;
 }
 
-static inline void device_set_wakeup_enable(struct device *dev, bool enable)
-{
-}
-
 static inline bool device_may_wakeup(struct device *dev)
 {
 	return false;
 }
 
-#endif /* !CONFIG_PM */
+static inline struct wakeup_source *wakeup_source_create(const char *name)
+{
+	return NULL;
+}
+
+static inline void wakeup_source_destroy(struct wakeup_source *ws) {}
+
+static inline void wakeup_source_add(struct wakeup_source *ws) {}
+
+static inline void wakeup_source_remove(struct wakeup_source *ws) {}
+
+static inline struct wakeup_source *wakeup_source_register(const char *name)
+{
+	return NULL;
+}
+
+static inline void wakeup_source_unregister(struct wakeup_source *ws) {}
+
+static inline int device_wakeup_enable(struct device *dev)
+{
+	return -EINVAL;
+}
+
+static inline int device_wakeup_disable(struct device *dev)
+{
+	return 0;
+}
+
+static inline int device_init_wakeup(struct device *dev, bool val)
+{
+	dev->power.can_wakeup = val;
+	return val ? -EINVAL : 0;
+}
+
+
+static inline int device_set_wakeup_enable(struct device *dev, bool enable)
+{
+	return -EINVAL;
+}
+
+static inline void __pm_stay_awake(struct wakeup_source *ws) {}
+
+static inline void pm_stay_awake(struct device *dev) {}
+
+static inline void __pm_relax(struct wakeup_source *ws) {}
+
+static inline void pm_relax(struct device *dev) {}
+
+static inline void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec) {}
+
+static inline void pm_wakeup_event(struct device *dev, unsigned int msec) {}
+
+#endif /* !CONFIG_PM_SLEEP */
 
 #endif /* _LINUX_PM_WAKEUP_H */
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 634b8e6..a39cbed 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -47,6 +47,8 @@
 {
 	return (void *)((unsigned long)ptr & ~RADIX_TREE_INDIRECT_PTR);
 }
+#define radix_tree_indirect_to_ptr(ptr) \
+	radix_tree_indirect_to_ptr((void __force *)(ptr))
 
 static inline int radix_tree_is_indirect_ptr(void *ptr)
 {
@@ -61,7 +63,7 @@
 struct radix_tree_root {
 	unsigned int		height;
 	gfp_t			gfp_mask;
-	struct radix_tree_node	*rnode;
+	struct radix_tree_node	__rcu *rnode;
 };
 
 #define RADIX_TREE_INIT(mask)	{					\
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 4ec3b38..f31ef61 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -10,6 +10,21 @@
 #include <linux/rcupdate.h>
 
 /*
+ * Why is there no list_empty_rcu()?  Because list_empty() serves this
+ * purpose.  The list_empty() function fetches the RCU-protected pointer
+ * and compares it to the address of the list head, but neither dereferences
+ * this pointer itself nor provides this pointer to the caller.  Therefore,
+ * it is not necessary to use rcu_dereference(), so that list_empty() can
+ * be used anywhere you would want to use a list_empty_rcu().
+ */
+
+/*
+ * return the ->next pointer of a list_head in an rcu safe
+ * way, we must not access it directly
+ */
+#define list_next_rcu(list)	(*((struct list_head __rcu **)(&(list)->next)))
+
+/*
  * Insert a new entry between two known consecutive entries.
  *
  * This is only for internal list manipulation where we know
@@ -20,7 +35,7 @@
 {
 	new->next = next;
 	new->prev = prev;
-	rcu_assign_pointer(prev->next, new);
+	rcu_assign_pointer(list_next_rcu(prev), new);
 	next->prev = new;
 }
 
@@ -138,7 +153,7 @@
 {
 	new->next = old->next;
 	new->prev = old->prev;
-	rcu_assign_pointer(new->prev->next, new);
+	rcu_assign_pointer(list_next_rcu(new->prev), new);
 	new->next->prev = new;
 	old->prev = LIST_POISON2;
 }
@@ -193,7 +208,7 @@
 	 */
 
 	last->next = at;
-	rcu_assign_pointer(head->next, first);
+	rcu_assign_pointer(list_next_rcu(head), first);
 	first->prev = head;
 	at->prev = last;
 }
@@ -208,7 +223,9 @@
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
 #define list_entry_rcu(ptr, type, member) \
-	container_of(rcu_dereference_raw(ptr), type, member)
+	({typeof (*ptr) __rcu *__ptr = (typeof (*ptr) __rcu __force *)ptr; \
+	 container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \
+	})
 
 /**
  * list_first_entry_rcu - get the first element from a list
@@ -225,9 +242,9 @@
 	list_entry_rcu((ptr)->next, type, member)
 
 #define __list_for_each_rcu(pos, head) \
-	for (pos = rcu_dereference_raw((head)->next); \
+	for (pos = rcu_dereference_raw(list_next_rcu(head)); \
 		pos != (head); \
-		pos = rcu_dereference_raw(pos->next))
+		pos = rcu_dereference_raw(list_next_rcu((pos)))
 
 /**
  * list_for_each_entry_rcu	-	iterate over rcu list of given type
@@ -257,9 +274,9 @@
  * as long as the traversal is guarded by rcu_read_lock().
  */
 #define list_for_each_continue_rcu(pos, head) \
-	for ((pos) = rcu_dereference_raw((pos)->next); \
+	for ((pos) = rcu_dereference_raw(list_next_rcu(pos)); \
 		prefetch((pos)->next), (pos) != (head); \
-		(pos) = rcu_dereference_raw((pos)->next))
+		(pos) = rcu_dereference_raw(list_next_rcu(pos)))
 
 /**
  * list_for_each_entry_continue_rcu - continue iteration over list of given type
@@ -314,12 +331,19 @@
 
 	new->next = next;
 	new->pprev = old->pprev;
-	rcu_assign_pointer(*new->pprev, new);
+	rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new);
 	if (next)
 		new->next->pprev = &new->next;
 	old->pprev = LIST_POISON2;
 }
 
+/*
+ * return the first or the next element in an RCU protected hlist
+ */
+#define hlist_first_rcu(head)	(*((struct hlist_node __rcu **)(&(head)->first)))
+#define hlist_next_rcu(node)	(*((struct hlist_node __rcu **)(&(node)->next)))
+#define hlist_pprev_rcu(node)	(*((struct hlist_node __rcu **)((node)->pprev)))
+
 /**
  * hlist_add_head_rcu
  * @n: the element to add to the hash list.
@@ -346,7 +370,7 @@
 
 	n->next = first;
 	n->pprev = &h->first;
-	rcu_assign_pointer(h->first, n);
+	rcu_assign_pointer(hlist_first_rcu(h), n);
 	if (first)
 		first->pprev = &n->next;
 }
@@ -374,7 +398,7 @@
 {
 	n->pprev = next->pprev;
 	n->next = next;
-	rcu_assign_pointer(*(n->pprev), n);
+	rcu_assign_pointer(hlist_pprev_rcu(n), n);
 	next->pprev = &n->next;
 }
 
@@ -401,15 +425,15 @@
 {
 	n->next = prev->next;
 	n->pprev = &prev->next;
-	rcu_assign_pointer(prev->next, n);
+	rcu_assign_pointer(hlist_next_rcu(prev), n);
 	if (n->next)
 		n->next->pprev = &n->next;
 }
 
-#define __hlist_for_each_rcu(pos, head)			\
-	for (pos = rcu_dereference((head)->first);	\
-	     pos && ({ prefetch(pos->next); 1; });	\
-	     pos = rcu_dereference(pos->next))
+#define __hlist_for_each_rcu(pos, head)				\
+	for (pos = rcu_dereference(hlist_first_rcu(head));	\
+	     pos && ({ prefetch(pos->next); 1; });		\
+	     pos = rcu_dereference(hlist_next_rcu(pos)))
 
 /**
  * hlist_for_each_entry_rcu - iterate over rcu list of given type
@@ -422,11 +446,11 @@
  * the _rcu list-mutation primitives such as hlist_add_head_rcu()
  * as long as the traversal is guarded by rcu_read_lock().
  */
-#define hlist_for_each_entry_rcu(tpos, pos, head, member)		 \
-	for (pos = rcu_dereference_raw((head)->first);			 \
+#define hlist_for_each_entry_rcu(tpos, pos, head, member)		\
+	for (pos = rcu_dereference_raw(hlist_first_rcu(head));		\
 		pos && ({ prefetch(pos->next); 1; }) &&			 \
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
-		pos = rcu_dereference_raw(pos->next))
+		pos = rcu_dereference_raw(hlist_next_rcu(pos)))
 
 /**
  * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index b70ffe5..2ae1371 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -37,6 +37,12 @@
 	}
 }
 
+#define hlist_nulls_first_rcu(head) \
+	(*((struct hlist_nulls_node __rcu __force **)&(head)->first))
+
+#define hlist_nulls_next_rcu(node) \
+	(*((struct hlist_nulls_node __rcu __force **)&(node)->next))
+
 /**
  * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization
  * @n: the element to delete from the hash list.
@@ -88,7 +94,7 @@
 
 	n->next = first;
 	n->pprev = &h->first;
-	rcu_assign_pointer(h->first, n);
+	rcu_assign_pointer(hlist_nulls_first_rcu(h), n);
 	if (!is_a_nulls(first))
 		first->pprev = &n->next;
 }
@@ -100,11 +106,11 @@
  * @member:	the name of the hlist_nulls_node within the struct.
  *
  */
-#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
-	for (pos = rcu_dereference_raw((head)->first);			 \
-		(!is_a_nulls(pos)) &&			\
+#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member)			\
+	for (pos = rcu_dereference_raw(hlist_nulls_first_rcu(head));		\
+		(!is_a_nulls(pos)) &&						\
 		({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
-		pos = rcu_dereference_raw(pos->next))
+		pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
 
 #endif
 #endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 83af1f8..03cda7b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -41,11 +41,15 @@
 #include <linux/lockdep.h>
 #include <linux/completion.h>
 #include <linux/debugobjects.h>
+#include <linux/compiler.h>
 
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
+#define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
+#define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
+
 /**
  * struct rcu_head - callback structure for use with RCU
  * @next: next update requests in a list
@@ -57,29 +61,94 @@
 };
 
 /* Exported common interfaces */
-extern void rcu_barrier(void);
+extern void call_rcu_sched(struct rcu_head *head,
+			   void (*func)(struct rcu_head *rcu));
+extern void synchronize_sched(void);
 extern void rcu_barrier_bh(void);
 extern void rcu_barrier_sched(void);
 extern void synchronize_sched_expedited(void);
 extern int sched_expedited_torture_stats(char *page);
 
+static inline void __rcu_read_lock_bh(void)
+{
+	local_bh_disable();
+}
+
+static inline void __rcu_read_unlock_bh(void)
+{
+	local_bh_enable();
+}
+
+#ifdef CONFIG_PREEMPT_RCU
+
+extern void __rcu_read_lock(void);
+extern void __rcu_read_unlock(void);
+void synchronize_rcu(void);
+
+/*
+ * Defined as a macro as it is a very low level header included from
+ * areas that don't even know about current.  This gives the rcu_read_lock()
+ * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other
+ * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
+ */
+#define rcu_preempt_depth() (current->rcu_read_lock_nesting)
+
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+
+static inline void __rcu_read_lock(void)
+{
+	preempt_disable();
+}
+
+static inline void __rcu_read_unlock(void)
+{
+	preempt_enable();
+}
+
+static inline void synchronize_rcu(void)
+{
+	synchronize_sched();
+}
+
+static inline int rcu_preempt_depth(void)
+{
+	return 0;
+}
+
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
 /* Internal to kernel */
 extern void rcu_init(void);
+extern void rcu_sched_qs(int cpu);
+extern void rcu_bh_qs(int cpu);
+extern void rcu_check_callbacks(int cpu, int user);
+struct notifier_block;
+
+#ifdef CONFIG_NO_HZ
+
+extern void rcu_enter_nohz(void);
+extern void rcu_exit_nohz(void);
+
+#else /* #ifdef CONFIG_NO_HZ */
+
+static inline void rcu_enter_nohz(void)
+{
+}
+
+static inline void rcu_exit_nohz(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_NO_HZ */
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
-#elif defined(CONFIG_TINY_RCU)
+#elif defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
 #include <linux/rcutiny.h>
 #else
 #error "Unknown RCU implementation specified to kernel configuration"
 #endif
 
-#define RCU_HEAD_INIT	{ .next = NULL, .func = NULL }
-#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
-#define INIT_RCU_HEAD(ptr) do { \
-       (ptr)->next = NULL; (ptr)->func = NULL; \
-} while (0)
-
 /*
  * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
  * initialization and destruction of rcu_head on the stack. rcu_head structures
@@ -120,14 +189,15 @@
 extern int debug_lockdep_rcu_enabled(void);
 
 /**
- * rcu_read_lock_held - might we be in RCU read-side critical section?
+ * rcu_read_lock_held() - might we be in RCU read-side critical section?
  *
  * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
  * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
  * this assumes we are in an RCU read-side critical section unless it can
- * prove otherwise.
+ * prove otherwise.  This is useful for debug checks in functions that
+ * require that they be called within an RCU read-side critical section.
  *
- * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
  * and while lockdep is disabled.
  */
 static inline int rcu_read_lock_held(void)
@@ -144,14 +214,16 @@
 extern int rcu_read_lock_bh_held(void);
 
 /**
- * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
+ * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
  *
  * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
  * RCU-sched read-side critical section.  In absence of
  * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
  * critical section unless it can prove otherwise.  Note that disabling
  * of preemption (including disabling irqs) counts as an RCU-sched
- * read-side critical section.
+ * read-side critical section.  This is useful for debug checks in functions
+ * that required that they be called within an RCU-sched read-side
+ * critical section.
  *
  * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
  * and while lockdep is disabled.
@@ -211,7 +283,11 @@
 
 extern int rcu_my_thread_group_empty(void);
 
-#define __do_rcu_dereference_check(c)					\
+/**
+ * rcu_lockdep_assert - emit lockdep splat if specified condition not met
+ * @c: condition to check
+ */
+#define rcu_lockdep_assert(c)						\
 	do {								\
 		static bool __warned;					\
 		if (debug_lockdep_rcu_enabled() && !__warned && !(c)) {	\
@@ -220,41 +296,163 @@
 		}							\
 	} while (0)
 
+#else /* #ifdef CONFIG_PROVE_RCU */
+
+#define rcu_lockdep_assert(c) do { } while (0)
+
+#endif /* #else #ifdef CONFIG_PROVE_RCU */
+
+/*
+ * Helper functions for rcu_dereference_check(), rcu_dereference_protected()
+ * and rcu_assign_pointer().  Some of these could be folded into their
+ * callers, but they are left separate in order to ease introduction of
+ * multiple flavors of pointers to match the multiple flavors of RCU
+ * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in
+ * the future.
+ */
+
+#ifdef __CHECKER__
+#define rcu_dereference_sparse(p, space) \
+	((void)(((typeof(*p) space *)p) == p))
+#else /* #ifdef __CHECKER__ */
+#define rcu_dereference_sparse(p, space)
+#endif /* #else #ifdef __CHECKER__ */
+
+#define __rcu_access_pointer(p, space) \
+	({ \
+		typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \
+		rcu_dereference_sparse(p, space); \
+		((typeof(*p) __force __kernel *)(_________p1)); \
+	})
+#define __rcu_dereference_check(p, c, space) \
+	({ \
+		typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \
+		rcu_lockdep_assert(c); \
+		rcu_dereference_sparse(p, space); \
+		smp_read_barrier_depends(); \
+		((typeof(*p) __force __kernel *)(_________p1)); \
+	})
+#define __rcu_dereference_protected(p, c, space) \
+	({ \
+		rcu_lockdep_assert(c); \
+		rcu_dereference_sparse(p, space); \
+		((typeof(*p) __force __kernel *)(p)); \
+	})
+
+#define __rcu_dereference_index_check(p, c) \
+	({ \
+		typeof(p) _________p1 = ACCESS_ONCE(p); \
+		rcu_lockdep_assert(c); \
+		smp_read_barrier_depends(); \
+		(_________p1); \
+	})
+#define __rcu_assign_pointer(p, v, space) \
+	({ \
+		if (!__builtin_constant_p(v) || \
+		    ((v) != NULL)) \
+			smp_wmb(); \
+		(p) = (typeof(*v) __force space *)(v); \
+	})
+
+
 /**
- * rcu_dereference_check - rcu_dereference with debug checking
+ * rcu_access_pointer() - fetch RCU pointer with no dereferencing
+ * @p: The pointer to read
+ *
+ * Return the value of the specified RCU-protected pointer, but omit the
+ * smp_read_barrier_depends() and keep the ACCESS_ONCE().  This is useful
+ * when the value of this pointer is accessed, but the pointer is not
+ * dereferenced, for example, when testing an RCU-protected pointer against
+ * NULL.  Although rcu_access_pointer() may also be used in cases where
+ * update-side locks prevent the value of the pointer from changing, you
+ * should instead use rcu_dereference_protected() for this use case.
+ */
+#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)
+
+/**
+ * rcu_dereference_check() - rcu_dereference with debug checking
  * @p: The pointer to read, prior to dereferencing
  * @c: The conditions under which the dereference will take place
  *
  * Do an rcu_dereference(), but check that the conditions under which the
- * dereference will take place are correct.  Typically the conditions indicate
- * the various locking conditions that should be held at that point.  The check
- * should return true if the conditions are satisfied.
+ * dereference will take place are correct.  Typically the conditions
+ * indicate the various locking conditions that should be held at that
+ * point.  The check should return true if the conditions are satisfied.
+ * An implicit check for being in an RCU read-side critical section
+ * (rcu_read_lock()) is included.
  *
  * For example:
  *
- *	bar = rcu_dereference_check(foo->bar, rcu_read_lock_held() ||
- *					      lockdep_is_held(&foo->lock));
+ *	bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock));
  *
  * could be used to indicate to lockdep that foo->bar may only be dereferenced
- * if either the RCU read lock is held, or that the lock required to replace
+ * if either rcu_read_lock() is held, or that the lock required to replace
  * the bar struct at foo->bar is held.
  *
  * Note that the list of conditions may also include indications of when a lock
  * need not be held, for example during initialisation or destruction of the
  * target struct:
  *
- *	bar = rcu_dereference_check(foo->bar, rcu_read_lock_held() ||
- *					      lockdep_is_held(&foo->lock) ||
+ *	bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) ||
  *					      atomic_read(&foo->usage) == 0);
+ *
+ * Inserts memory barriers on architectures that require them
+ * (currently only the Alpha), prevents the compiler from refetching
+ * (and from merging fetches), and, more importantly, documents exactly
+ * which pointers are protected by RCU and checks that the pointer is
+ * annotated as __rcu.
  */
 #define rcu_dereference_check(p, c) \
-	({ \
-		__do_rcu_dereference_check(c); \
-		rcu_dereference_raw(p); \
-	})
+	__rcu_dereference_check((p), rcu_read_lock_held() || (c), __rcu)
 
 /**
- * rcu_dereference_protected - fetch RCU pointer when updates prevented
+ * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * This is the RCU-bh counterpart to rcu_dereference_check().
+ */
+#define rcu_dereference_bh_check(p, c) \
+	__rcu_dereference_check((p), rcu_read_lock_bh_held() || (c), __rcu)
+
+/**
+ * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * This is the RCU-sched counterpart to rcu_dereference_check().
+ */
+#define rcu_dereference_sched_check(p, c) \
+	__rcu_dereference_check((p), rcu_read_lock_sched_held() || (c), \
+				__rcu)
+
+#define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/
+
+/**
+ * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * Similar to rcu_dereference_check(), but omits the sparse checking.
+ * This allows rcu_dereference_index_check() to be used on integers,
+ * which can then be used as array indices.  Attempting to use
+ * rcu_dereference_check() on an integer will give compiler warnings
+ * because the sparse address-space mechanism relies on dereferencing
+ * the RCU-protected pointer.  Dereferencing integers is not something
+ * that even gcc will put up with.
+ *
+ * Note that this function does not implicitly check for RCU read-side
+ * critical sections.  If this function gains lots of uses, it might
+ * make sense to provide versions for each flavor of RCU, but it does
+ * not make sense as of early 2010.
+ */
+#define rcu_dereference_index_check(p, c) \
+	__rcu_dereference_index_check((p), (c))
+
+/**
+ * rcu_dereference_protected() - fetch RCU pointer when updates prevented
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
  *
  * Return the value of the specified RCU-protected pointer, but omit
  * both the smp_read_barrier_depends() and the ACCESS_ONCE().  This
@@ -263,35 +461,61 @@
  * prevent the compiler from repeating this reference or combining it
  * with other references, so it should not be used without protection
  * of appropriate locks.
+ *
+ * This function is only for update-side use.  Using this function
+ * when protected only by rcu_read_lock() will result in infrequent
+ * but very ugly failures.
  */
 #define rcu_dereference_protected(p, c) \
-	({ \
-		__do_rcu_dereference_check(c); \
-		(p); \
-	})
-
-#else /* #ifdef CONFIG_PROVE_RCU */
-
-#define rcu_dereference_check(p, c)	rcu_dereference_raw(p)
-#define rcu_dereference_protected(p, c) (p)
-
-#endif /* #else #ifdef CONFIG_PROVE_RCU */
+	__rcu_dereference_protected((p), (c), __rcu)
 
 /**
- * rcu_access_pointer - fetch RCU pointer with no dereferencing
+ * rcu_dereference_bh_protected() - fetch RCU-bh pointer when updates prevented
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
  *
- * Return the value of the specified RCU-protected pointer, but omit the
- * smp_read_barrier_depends() and keep the ACCESS_ONCE().  This is useful
- * when the value of this pointer is accessed, but the pointer is not
- * dereferenced, for example, when testing an RCU-protected pointer against
- * NULL.  This may also be used in cases where update-side locks prevent
- * the value of the pointer from changing, but rcu_dereference_protected()
- * is a lighter-weight primitive for this use case.
+ * This is the RCU-bh counterpart to rcu_dereference_protected().
  */
-#define rcu_access_pointer(p)	ACCESS_ONCE(p)
+#define rcu_dereference_bh_protected(p, c) \
+	__rcu_dereference_protected((p), (c), __rcu)
 
 /**
- * rcu_read_lock - mark the beginning of an RCU read-side critical section.
+ * rcu_dereference_sched_protected() - fetch RCU-sched pointer when updates prevented
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * This is the RCU-sched counterpart to rcu_dereference_protected().
+ */
+#define rcu_dereference_sched_protected(p, c) \
+	__rcu_dereference_protected((p), (c), __rcu)
+
+
+/**
+ * rcu_dereference() - fetch RCU-protected pointer for dereferencing
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * This is a simple wrapper around rcu_dereference_check().
+ */
+#define rcu_dereference(p) rcu_dereference_check(p, 0)
+
+/**
+ * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0)
+
+/**
+ * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0)
+
+/**
+ * rcu_read_lock() - mark the beginning of an RCU read-side critical section
  *
  * When synchronize_rcu() is invoked on one CPU while other CPUs
  * are within RCU read-side critical sections, then the
@@ -302,7 +526,7 @@
  * until after the all the other CPUs exit their critical sections.
  *
  * Note, however, that RCU callbacks are permitted to run concurrently
- * with RCU read-side critical sections.  One way that this can happen
+ * with new RCU read-side critical sections.  One way that this can happen
  * is via the following sequence of events: (1) CPU 0 enters an RCU
  * read-side critical section, (2) CPU 1 invokes call_rcu() to register
  * an RCU callback, (3) CPU 0 exits the RCU read-side critical section,
@@ -317,7 +541,20 @@
  * will be deferred until the outermost RCU read-side critical section
  * completes.
  *
- * It is illegal to block while in an RCU read-side critical section.
+ * You can avoid reading and understanding the next paragraph by
+ * following this rule: don't put anything in an rcu_read_lock() RCU
+ * read-side critical section that would block in a !PREEMPT kernel.
+ * But if you want the full story, read on!
+ *
+ * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it
+ * is illegal to block while in an RCU read-side critical section.  In
+ * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU)
+ * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may
+ * be preempted, but explicit blocking is illegal.  Finally, in preemptible
+ * RCU implementations in real-time (CONFIG_PREEMPT_RT) kernel builds,
+ * RCU read-side critical sections may be preempted and they may also
+ * block, but only when acquiring spinlocks that are subject to priority
+ * inheritance.
  */
 static inline void rcu_read_lock(void)
 {
@@ -337,7 +574,7 @@
  */
 
 /**
- * rcu_read_unlock - marks the end of an RCU read-side critical section.
+ * rcu_read_unlock() - marks the end of an RCU read-side critical section.
  *
  * See rcu_read_lock() for more information.
  */
@@ -349,15 +586,16 @@
 }
 
 /**
- * rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section
+ * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section
  *
  * This is equivalent of rcu_read_lock(), but to be used when updates
- * are being done using call_rcu_bh(). Since call_rcu_bh() callbacks
- * consider completion of a softirq handler to be a quiescent state,
- * a process in RCU read-side critical section must be protected by
- * disabling softirqs. Read-side critical sections in interrupt context
- * can use just rcu_read_lock().
- *
+ * are being done using call_rcu_bh() or synchronize_rcu_bh(). Since
+ * both call_rcu_bh() and synchronize_rcu_bh() consider completion of a
+ * softirq handler to be a quiescent state, a process in RCU read-side
+ * critical section must be protected by disabling softirqs. Read-side
+ * critical sections in interrupt context can use just rcu_read_lock(),
+ * though this should at least be commented to avoid confusing people
+ * reading the code.
  */
 static inline void rcu_read_lock_bh(void)
 {
@@ -379,13 +617,12 @@
 }
 
 /**
- * rcu_read_lock_sched - mark the beginning of a RCU-classic critical section
+ * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section
  *
- * Should be used with either
- * - synchronize_sched()
- * or
- * - call_rcu_sched() and rcu_barrier_sched()
- * on the write-side to insure proper synchronization.
+ * This is equivalent of rcu_read_lock(), but to be used when updates
+ * are being done using call_rcu_sched() or synchronize_rcu_sched().
+ * Read-side critical sections can also be introduced by anything that
+ * disables preemption, including local_irq_disable() and friends.
  */
 static inline void rcu_read_lock_sched(void)
 {
@@ -420,54 +657,14 @@
 	preempt_enable_notrace();
 }
 
-
 /**
- * rcu_dereference_raw - fetch an RCU-protected pointer
+ * rcu_assign_pointer() - assign to RCU-protected pointer
+ * @p: pointer to assign to
+ * @v: value to assign (publish)
  *
- * The caller must be within some flavor of RCU read-side critical
- * section, or must be otherwise preventing the pointer from changing,
- * for example, by holding an appropriate lock.  This pointer may later
- * be safely dereferenced.  It is the caller's responsibility to have
- * done the right thing, as this primitive does no checking of any kind.
- *
- * Inserts memory barriers on architectures that require them
- * (currently only the Alpha), and, more importantly, documents
- * exactly which pointers are protected by RCU.
- */
-#define rcu_dereference_raw(p)	({ \
-				typeof(p) _________p1 = ACCESS_ONCE(p); \
-				smp_read_barrier_depends(); \
-				(_________p1); \
-				})
-
-/**
- * rcu_dereference - fetch an RCU-protected pointer, checking for RCU
- *
- * Makes rcu_dereference_check() do the dirty work.
- */
-#define rcu_dereference(p) \
-	rcu_dereference_check(p, rcu_read_lock_held())
-
-/**
- * rcu_dereference_bh - fetch an RCU-protected pointer, checking for RCU-bh
- *
- * Makes rcu_dereference_check() do the dirty work.
- */
-#define rcu_dereference_bh(p) \
-		rcu_dereference_check(p, rcu_read_lock_bh_held() || irqs_disabled())
-
-/**
- * rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched
- *
- * Makes rcu_dereference_check() do the dirty work.
- */
-#define rcu_dereference_sched(p) \
-		rcu_dereference_check(p, rcu_read_lock_sched_held())
-
-/**
- * rcu_assign_pointer - assign (publicize) a pointer to a newly
- * initialized structure that will be dereferenced by RCU read-side
- * critical sections.  Returns the value assigned.
+ * Assigns the specified value to the specified RCU-protected
+ * pointer, ensuring that any concurrent RCU readers will see
+ * any prior initialization.  Returns the value assigned.
  *
  * Inserts memory barriers on architectures that require them
  * (pretty much all of them other than x86), and also prevents
@@ -476,14 +673,17 @@
  * call documents which pointers will be dereferenced by RCU read-side
  * code.
  */
-
 #define rcu_assign_pointer(p, v) \
-	({ \
-		if (!__builtin_constant_p(v) || \
-		    ((v) != NULL)) \
-			smp_wmb(); \
-		(p) = (v); \
-	})
+	__rcu_assign_pointer((p), (v), __rcu)
+
+/**
+ * RCU_INIT_POINTER() - initialize an RCU protected pointer
+ *
+ * Initialize an RCU-protected pointer in such a way to avoid RCU-lockdep
+ * splats.
+ */
+#define RCU_INIT_POINTER(p, v) \
+		p = (typeof(*v) __force __rcu *)(v)
 
 /* Infrastructure to implement the synchronize_() primitives. */
 
@@ -494,26 +694,37 @@
 
 extern void wakeme_after_rcu(struct rcu_head  *head);
 
+#ifdef CONFIG_PREEMPT_RCU
+
 /**
- * call_rcu - Queue an RCU callback for invocation after a grace period.
+ * call_rcu() - Queue an RCU callback for invocation after a grace period.
  * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
+ * @func: actual callback function to be invoked after the grace period
  *
- * The update function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed.  RCU read-side critical
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed.  However, the callback function
+ * might well execute concurrently with RCU read-side critical sections
+ * that started after call_rcu() was invoked.  RCU read-side critical
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  */
 extern void call_rcu(struct rcu_head *head,
 			      void (*func)(struct rcu_head *head));
 
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+
+/* In classic RCU, call_rcu() is just call_rcu_sched(). */
+#define	call_rcu	call_rcu_sched
+
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
 /**
- * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
+ * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
+ * @func: actual callback function to be invoked after the grace period
  *
- * The update function will be invoked some time after a full grace
+ * The callback function will be invoked some time after a full grace
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_bh() assumes
  * that the read-side critical sections end on completion of a softirq
@@ -566,37 +777,4 @@
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-#ifndef CONFIG_PROVE_RCU
-#define __do_rcu_dereference_check(c) do { } while (0)
-#endif /* #ifdef CONFIG_PROVE_RCU */
-
-#define __rcu_dereference_index_check(p, c) \
-	({ \
-		typeof(p) _________p1 = ACCESS_ONCE(p); \
-		__do_rcu_dereference_check(c); \
-		smp_read_barrier_depends(); \
-		(_________p1); \
-	})
-
-/**
- * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
- * @p: The pointer to read, prior to dereferencing
- * @c: The conditions under which the dereference will take place
- *
- * Similar to rcu_dereference_check(), but omits the sparse checking.
- * This allows rcu_dereference_index_check() to be used on integers,
- * which can then be used as array indices.  Attempting to use
- * rcu_dereference_check() on an integer will give compiler warnings
- * because the sparse address-space mechanism relies on dereferencing
- * the RCU-protected pointer.  Dereferencing integers is not something
- * that even gcc will put up with.
- *
- * Note that this function does not implicitly check for RCU read-side
- * critical sections.  If this function gains lots of uses, it might
- * make sense to provide versions for each flavor of RCU, but it does
- * not make sense as of early 2010.
- */
-#define rcu_dereference_index_check(p, c) \
-	__rcu_dereference_index_check((p), (c))
-
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index e2e8931..13877cb 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,27 +27,71 @@
 
 #include <linux/cache.h>
 
-void rcu_sched_qs(int cpu);
-void rcu_bh_qs(int cpu);
-static inline void rcu_note_context_switch(int cpu)
+#define rcu_init_sched()	do { } while (0)
+
+#ifdef CONFIG_TINY_RCU
+
+static inline void synchronize_rcu_expedited(void)
 {
-	rcu_sched_qs(cpu);
+	synchronize_sched();	/* Only one CPU, so pretty fast anyway!!! */
 }
 
-#define __rcu_read_lock()	preempt_disable()
-#define __rcu_read_unlock()	preempt_enable()
-#define __rcu_read_lock_bh()	local_bh_disable()
-#define __rcu_read_unlock_bh()	local_bh_enable()
-#define call_rcu_sched		call_rcu
+static inline void rcu_barrier(void)
+{
+	rcu_barrier_sched();  /* Only one CPU, so only one list of callbacks! */
+}
 
-#define rcu_init_sched()	do { } while (0)
-extern void rcu_check_callbacks(int cpu, int user);
+#else /* #ifdef CONFIG_TINY_RCU */
+
+void rcu_barrier(void);
+void synchronize_rcu_expedited(void);
+
+#endif /* #else #ifdef CONFIG_TINY_RCU */
+
+static inline void synchronize_rcu_bh(void)
+{
+	synchronize_sched();
+}
+
+static inline void synchronize_rcu_bh_expedited(void)
+{
+	synchronize_sched();
+}
+
+#ifdef CONFIG_TINY_RCU
+
+static inline void rcu_preempt_note_context_switch(void)
+{
+}
+
+static inline void exit_rcu(void)
+{
+}
 
 static inline int rcu_needs_cpu(int cpu)
 {
 	return 0;
 }
 
+#else /* #ifdef CONFIG_TINY_RCU */
+
+void rcu_preempt_note_context_switch(void);
+extern void exit_rcu(void);
+int rcu_preempt_needs_cpu(void);
+
+static inline int rcu_needs_cpu(int cpu)
+{
+	return rcu_preempt_needs_cpu();
+}
+
+#endif /* #else #ifdef CONFIG_TINY_RCU */
+
+static inline void rcu_note_context_switch(int cpu)
+{
+	rcu_sched_qs(cpu);
+	rcu_preempt_note_context_switch();
+}
+
 /*
  * Return the number of grace periods.
  */
@@ -76,54 +120,8 @@
 {
 }
 
-extern void synchronize_sched(void);
-
-static inline void synchronize_rcu(void)
+static inline void rcu_cpu_stall_reset(void)
 {
-	synchronize_sched();
-}
-
-static inline void synchronize_rcu_bh(void)
-{
-	synchronize_sched();
-}
-
-static inline void synchronize_rcu_expedited(void)
-{
-	synchronize_sched();
-}
-
-static inline void synchronize_rcu_bh_expedited(void)
-{
-	synchronize_sched();
-}
-
-struct notifier_block;
-
-#ifdef CONFIG_NO_HZ
-
-extern void rcu_enter_nohz(void);
-extern void rcu_exit_nohz(void);
-
-#else /* #ifdef CONFIG_NO_HZ */
-
-static inline void rcu_enter_nohz(void)
-{
-}
-
-static inline void rcu_exit_nohz(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_NO_HZ */
-
-static inline void exit_rcu(void)
-{
-}
-
-static inline int rcu_preempt_depth(void)
-{
-	return 0;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index c0ed1c0..95518e6 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,64 +30,23 @@
 #ifndef __LINUX_RCUTREE_H
 #define __LINUX_RCUTREE_H
 
-struct notifier_block;
-
-extern void rcu_sched_qs(int cpu);
-extern void rcu_bh_qs(int cpu);
 extern void rcu_note_context_switch(int cpu);
 extern int rcu_needs_cpu(int cpu);
+extern void rcu_cpu_stall_reset(void);
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
-extern void __rcu_read_lock(void);
-extern void __rcu_read_unlock(void);
-extern void synchronize_rcu(void);
 extern void exit_rcu(void);
 
-/*
- * Defined as macro as it is a very low level header
- * included from areas that don't even know about current
- */
-#define rcu_preempt_depth() (current->rcu_read_lock_nesting)
-
 #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
-static inline void __rcu_read_lock(void)
-{
-	preempt_disable();
-}
-
-static inline void __rcu_read_unlock(void)
-{
-	preempt_enable();
-}
-
-#define synchronize_rcu synchronize_sched
-
 static inline void exit_rcu(void)
 {
 }
 
-static inline int rcu_preempt_depth(void)
-{
-	return 0;
-}
-
 #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
 
-static inline void __rcu_read_lock_bh(void)
-{
-	local_bh_disable();
-}
-static inline void __rcu_read_unlock_bh(void)
-{
-	local_bh_enable();
-}
-
-extern void call_rcu_sched(struct rcu_head *head,
-			   void (*func)(struct rcu_head *rcu));
 extern void synchronize_rcu_bh(void);
-extern void synchronize_sched(void);
 extern void synchronize_rcu_expedited(void);
 
 static inline void synchronize_rcu_bh_expedited(void)
@@ -95,7 +54,7 @@
 	synchronize_sched_expedited();
 }
 
-extern void rcu_check_callbacks(int cpu, int user);
+extern void rcu_barrier(void);
 
 extern long rcu_batches_completed(void);
 extern long rcu_batches_completed_bh(void);
@@ -104,18 +63,6 @@
 extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);
 
-#ifdef CONFIG_NO_HZ
-void rcu_enter_nohz(void);
-void rcu_exit_nohz(void);
-#else /* CONFIG_NO_HZ */
-static inline void rcu_enter_nohz(void)
-{
-}
-static inline void rcu_exit_nohz(void)
-{
-}
-#endif /* CONFIG_NO_HZ */
-
 /* A context switch is a grace period for RCU-sched and RCU-bh. */
 static inline int rcu_blocking_is_gp(void)
 {
diff --git a/include/linux/resume-trace.h b/include/linux/resume-trace.h
index bc8c388..f31db23 100644
--- a/include/linux/resume-trace.h
+++ b/include/linux/resume-trace.h
@@ -3,6 +3,7 @@
 
 #ifdef CONFIG_PM_TRACE
 #include <asm/resume-trace.h>
+#include <linux/types.h>
 
 extern int pm_trace_enabled;
 
@@ -14,6 +15,7 @@
 struct device;
 extern void set_trace_device(struct device *);
 extern void generate_resume_trace(const void *tracedata, unsigned int user);
+extern int show_trace_dev_match(char *buf, size_t size);
 
 #define TRACE_DEVICE(dev) do { \
 	if (pm_trace_enabled) \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1e2a6db..56154bb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -336,6 +336,9 @@
 extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
 					 void __user *buffer,
 					 size_t *lenp, loff_t *ppos);
+#else
+/* Avoid need for ifdefs elsewhere in the code */
+enum { sysctl_hung_task_timeout_secs = 0 };
 #endif
 
 /* Attach to any functions which should be ignored in wchan output. */
@@ -875,6 +878,7 @@
 	SD_LV_NONE = 0,
 	SD_LV_SIBLING,
 	SD_LV_MC,
+	SD_LV_BOOK,
 	SD_LV_CPU,
 	SD_LV_NODE,
 	SD_LV_ALLNODES,
@@ -1160,6 +1164,13 @@
 
 struct rcu_node;
 
+enum perf_event_task_context {
+	perf_invalid_context = -1,
+	perf_hw_context = 0,
+	perf_sw_context,
+	perf_nr_task_contexts,
+};
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
@@ -1202,11 +1213,13 @@
 	unsigned int policy;
 	cpumask_t cpus_allowed;
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 	int rcu_read_lock_nesting;
 	char rcu_read_unlock_special;
-	struct rcu_node *rcu_blocked_node;
 	struct list_head rcu_node_entry;
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TREE_PREEMPT_RCU
+	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
@@ -1288,9 +1301,9 @@
 	struct list_head cpu_timers[3];
 
 /* process credentials */
-	const struct cred *real_cred;	/* objective and real subjective task
+	const struct cred __rcu *real_cred; /* objective and real subjective task
 					 * credentials (COW) */
-	const struct cred *cred;	/* effective (overridable) subjective task
+	const struct cred __rcu *cred;	/* effective (overridable) subjective task
 					 * credentials (COW) */
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
@@ -1418,7 +1431,7 @@
 #endif
 #ifdef CONFIG_CGROUPS
 	/* Control Group info protected by css_set_lock */
-	struct css_set *cgroups;
+	struct css_set __rcu *cgroups;
 	/* cg_list protected by css_set_lock and tsk->alloc_lock */
 	struct list_head cg_list;
 #endif
@@ -1431,7 +1444,7 @@
 	struct futex_pi_state *pi_state_cache;
 #endif
 #ifdef CONFIG_PERF_EVENTS
-	struct perf_event_context *perf_event_ctxp;
+	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
 	struct mutex perf_event_mutex;
 	struct list_head perf_event_list;
 #endif
@@ -1681,8 +1694,7 @@
 /*
  * Per process flags
  */
-#define PF_ALIGNWARN	0x00000001	/* Print alignment warning msgs */
-					/* Not implemented yet, only for 486*/
+#define PF_KSOFTIRQD	0x00000001	/* I am ksoftirqd */
 #define PF_STARTING	0x00000002	/* being created */
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
@@ -1740,7 +1752,7 @@
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 
 #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
 #define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
@@ -1749,7 +1761,9 @@
 {
 	p->rcu_read_lock_nesting = 0;
 	p->rcu_read_unlock_special = 0;
+#ifdef CONFIG_TREE_PREEMPT_RCU
 	p->rcu_blocked_node = NULL;
+#endif
 	INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
@@ -1826,6 +1840,19 @@
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 #endif
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
+ * The reason for this explicit opt-in is not to have perf penalty with
+ * slow sched_clocks.
+ */
+extern void enable_sched_clock_irqtime(void);
+extern void disable_sched_clock_irqtime(void);
+#else
+static inline void enable_sched_clock_irqtime(void) {}
+static inline void disable_sched_clock_irqtime(void) {}
+#endif
+
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
@@ -2367,9 +2394,9 @@
 
 extern int __cond_resched_softirq(void);
 
-#define cond_resched_softirq() ({				\
-	__might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET);	\
-	__cond_resched_softirq();				\
+#define cond_resched_softirq() ({					\
+	__might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
+	__cond_resched_softirq();					\
 })
 
 /*
diff --git a/include/linux/security.h b/include/linux/security.h
index a22219a..b8246a8 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -74,7 +74,7 @@
 extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags);
 extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 			  unsigned long arg4, unsigned long arg5);
-extern int cap_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp);
+extern int cap_task_setscheduler(struct task_struct *p);
 extern int cap_task_setioprio(struct task_struct *p, int ioprio);
 extern int cap_task_setnice(struct task_struct *p, int nice);
 extern int cap_syslog(int type, bool from_file);
@@ -959,6 +959,12 @@
  *	Sets the new child socket's sid to the openreq sid.
  * @inet_conn_established:
  *	Sets the connection's peersid to the secmark on skb.
+ * @secmark_relabel_packet:
+ *	check if the process should be allowed to relabel packets to the given secid
+ * @security_secmark_refcount_inc
+ *	tells the LSM to increment the number of secmark labeling rules loaded
+ * @security_secmark_refcount_dec
+ *	tells the LSM to decrement the number of secmark labeling rules loaded
  * @req_classify_flow:
  *	Sets the flow's sid to the openreq sid.
  * @tun_dev_create:
@@ -1279,9 +1285,13 @@
  *	Return 0 if permission is granted.
  *
  * @secid_to_secctx:
- *	Convert secid to security context.
+ *	Convert secid to security context.  If secdata is NULL the length of
+ *	the result will be returned in seclen, but no secdata will be returned.
+ *	This does mean that the length could change between calls to check the
+ *	length and the next call which actually allocates and returns the secdata.
  *	@secid contains the security ID.
  *	@secdata contains the pointer that stores the converted security context.
+ *	@seclen pointer which contains the length of the data
  * @secctx_to_secid:
  *	Convert security context to secid.
  *	@secid contains the pointer to the generated security ID.
@@ -1501,8 +1511,7 @@
 	int (*task_getioprio) (struct task_struct *p);
 	int (*task_setrlimit) (struct task_struct *p, unsigned int resource,
 			struct rlimit *new_rlim);
-	int (*task_setscheduler) (struct task_struct *p, int policy,
-				  struct sched_param *lp);
+	int (*task_setscheduler) (struct task_struct *p);
 	int (*task_getscheduler) (struct task_struct *p);
 	int (*task_movememory) (struct task_struct *p);
 	int (*task_kill) (struct task_struct *p,
@@ -1594,6 +1603,9 @@
 				  struct request_sock *req);
 	void (*inet_csk_clone) (struct sock *newsk, const struct request_sock *req);
 	void (*inet_conn_established) (struct sock *sk, struct sk_buff *skb);
+	int (*secmark_relabel_packet) (u32 secid);
+	void (*secmark_refcount_inc) (void);
+	void (*secmark_refcount_dec) (void);
 	void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl);
 	int (*tun_dev_create)(void);
 	void (*tun_dev_post_create)(struct sock *sk);
@@ -1752,8 +1764,7 @@
 int security_task_getioprio(struct task_struct *p);
 int security_task_setrlimit(struct task_struct *p, unsigned int resource,
 		struct rlimit *new_rlim);
-int security_task_setscheduler(struct task_struct *p,
-				int policy, struct sched_param *lp);
+int security_task_setscheduler(struct task_struct *p);
 int security_task_getscheduler(struct task_struct *p);
 int security_task_movememory(struct task_struct *p);
 int security_task_kill(struct task_struct *p, struct siginfo *info,
@@ -2320,11 +2331,9 @@
 	return 0;
 }
 
-static inline int security_task_setscheduler(struct task_struct *p,
-					     int policy,
-					     struct sched_param *lp)
+static inline int security_task_setscheduler(struct task_struct *p)
 {
-	return cap_task_setscheduler(p, policy, lp);
+	return cap_task_setscheduler(p);
 }
 
 static inline int security_task_getscheduler(struct task_struct *p)
@@ -2551,6 +2560,9 @@
 			const struct request_sock *req);
 void security_inet_conn_established(struct sock *sk,
 			struct sk_buff *skb);
+int security_secmark_relabel_packet(u32 secid);
+void security_secmark_refcount_inc(void);
+void security_secmark_refcount_dec(void);
 int security_tun_dev_create(void);
 void security_tun_dev_post_create(struct sock *sk);
 int security_tun_dev_attach(struct sock *sk);
@@ -2705,6 +2717,19 @@
 {
 }
 
+static inline int security_secmark_relabel_packet(u32 secid)
+{
+	return 0;
+}
+
+static inline void security_secmark_refcount_inc(void)
+{
+}
+
+static inline void security_secmark_refcount_dec(void)
+{
+}
+
 static inline int security_tun_dev_create(void)
 {
 	return 0;
diff --git a/include/linux/selinux.h b/include/linux/selinux.h
index 82e0f26..44f4596 100644
--- a/include/linux/selinux.h
+++ b/include/linux/selinux.h
@@ -21,74 +21,11 @@
 #ifdef CONFIG_SECURITY_SELINUX
 
 /**
- *     selinux_string_to_sid - map a security context string to a security ID
- *     @str: the security context string to be mapped
- *     @sid: ID value returned via this.
- *
- *     Returns 0 if successful, with the SID stored in sid.  A value
- *     of zero for sid indicates no SID could be determined (but no error
- *     occurred).
- */
-int selinux_string_to_sid(char *str, u32 *sid);
-
-/**
- *     selinux_secmark_relabel_packet_permission - secmark permission check
- *     @sid: SECMARK ID value to be applied to network packet
- *
- *     Returns 0 if the current task is allowed to set the SECMARK label of
- *     packets with the supplied security ID.  Note that it is implicit that
- *     the packet is always being relabeled from the default unlabeled value,
- *     and that the access control decision is made in the AVC.
- */
-int selinux_secmark_relabel_packet_permission(u32 sid);
-
-/**
- *     selinux_secmark_refcount_inc - increments the secmark use counter
- *
- *     SELinux keeps track of the current SECMARK targets in use so it knows
- *     when to apply SECMARK label access checks to network packets.  This
- *     function incements this reference count to indicate that a new SECMARK
- *     target has been configured.
- */
-void selinux_secmark_refcount_inc(void);
-
-/**
- *     selinux_secmark_refcount_dec - decrements the secmark use counter
- *
- *     SELinux keeps track of the current SECMARK targets in use so it knows
- *     when to apply SECMARK label access checks to network packets.  This
- *     function decements this reference count to indicate that one of the
- *     existing SECMARK targets has been removed/flushed.
- */
-void selinux_secmark_refcount_dec(void);
-
-/**
  * selinux_is_enabled - is SELinux enabled?
  */
 bool selinux_is_enabled(void);
 #else
 
-static inline int selinux_string_to_sid(const char *str, u32 *sid)
-{
-       *sid = 0;
-       return 0;
-}
-
-static inline int selinux_secmark_relabel_packet_permission(u32 sid)
-{
-	return 0;
-}
-
-static inline void selinux_secmark_refcount_inc(void)
-{
-	return;
-}
-
-static inline void selinux_secmark_refcount_dec(void)
-{
-	return;
-}
-
 static inline bool selinux_is_enabled(void)
 {
 	return false;
diff --git a/include/linux/smp_lock.h b/include/linux/smp_lock.h
index 2ea1dd1..291f721 100644
--- a/include/linux/smp_lock.h
+++ b/include/linux/smp_lock.h
@@ -54,12 +54,15 @@
 
 #else
 
+#ifdef CONFIG_BKL /* provoke build bug if not set */
 #define lock_kernel()
 #define unlock_kernel()
-#define release_kernel_lock(task)		do { } while(0)
 #define cycle_kernel_lock()			do { } while(0)
-#define reacquire_kernel_lock(task)		0
 #define kernel_locked()				1
+#endif /* CONFIG_BKL */
+
+#define release_kernel_lock(task)		do { } while(0)
+#define reacquire_kernel_lock(task)		0
 
 #endif /* CONFIG_LOCK_KERNEL */
 #endif /* __LINUX_SMPLOCK_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index f885465..80e5358 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -50,6 +50,7 @@
 #include <linux/preempt.h>
 #include <linux/linkage.h>
 #include <linux/compiler.h>
+#include <linux/irqflags.h>
 #include <linux/thread_info.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 4d5d2f5..58971e8 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -108,19 +108,43 @@
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /**
- * srcu_dereference - fetch SRCU-protected pointer with checking
+ * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing
+ * @p: the pointer to fetch and protect for later dereferencing
+ * @sp: pointer to the srcu_struct, which is used to check that we
+ *	really are in an SRCU read-side critical section.
+ * @c: condition to check for update-side use
  *
- * Makes rcu_dereference_check() do the dirty work.
+ * If PROVE_RCU is enabled, invoking this outside of an RCU read-side
+ * critical section will result in an RCU-lockdep splat, unless @c evaluates
+ * to 1.  The @c argument will normally be a logical expression containing
+ * lockdep_is_held() calls.
  */
-#define srcu_dereference(p, sp) \
-		rcu_dereference_check(p, srcu_read_lock_held(sp))
+#define srcu_dereference_check(p, sp, c) \
+	__rcu_dereference_check((p), srcu_read_lock_held(sp) || (c), __rcu)
+
+/**
+ * srcu_dereference - fetch SRCU-protected pointer for later dereferencing
+ * @p: the pointer to fetch and protect for later dereferencing
+ * @sp: pointer to the srcu_struct, which is used to check that we
+ *	really are in an SRCU read-side critical section.
+ *
+ * Makes rcu_dereference_check() do the dirty work.  If PROVE_RCU
+ * is enabled, invoking this outside of an RCU read-side critical
+ * section will result in an RCU-lockdep splat.
+ */
+#define srcu_dereference(p, sp) srcu_dereference_check((p), (sp), 0)
 
 /**
  * srcu_read_lock - register a new reader for an SRCU-protected structure.
  * @sp: srcu_struct in which to register the new reader.
  *
  * Enter an SRCU read-side critical section.  Note that SRCU read-side
- * critical sections may be nested.
+ * critical sections may be nested.  However, it is illegal to
+ * call anything that waits on an SRCU grace period for the same
+ * srcu_struct, whether directly or indirectly.  Please note that
+ * one way to indirectly wait on an SRCU grace period is to acquire
+ * a mutex that is held elsewhere while calling synchronize_srcu() or
+ * synchronize_srcu_expedited().
  */
 static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
 {
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 6b524a0..1808960 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -126,8 +126,8 @@
 
 #else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
 
-static inline int stop_machine(int (*fn)(void *), void *data,
-			       const struct cpumask *cpus)
+static inline int __stop_machine(int (*fn)(void *), void *data,
+				 const struct cpumask *cpus)
 {
 	int ret;
 	local_irq_disable();
@@ -136,5 +136,11 @@
 	return ret;
 }
 
+static inline int stop_machine(int (*fn)(void *), void *data,
+			       const struct cpumask *cpus)
+{
+	return __stop_machine(fn, data, cpus);
+}
+
 #endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
 #endif	/* _LINUX_STOP_MACHINE */
diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h
index 671538d..8eee9db 100644
--- a/include/linux/sunrpc/auth_gss.h
+++ b/include/linux/sunrpc/auth_gss.h
@@ -69,7 +69,7 @@
 	enum rpc_gss_proc	gc_proc;
 	u32			gc_seq;
 	spinlock_t		gc_seq_lock;
-	struct gss_ctx		*gc_gss_ctx;
+	struct gss_ctx __rcu	*gc_gss_ctx;
 	struct xdr_netobj	gc_wire_ctx;
 	u32			gc_win;
 	unsigned long		gc_expiry;
@@ -80,7 +80,7 @@
 struct gss_cred {
 	struct rpc_cred		gc_base;
 	enum rpc_gss_svc	gc_service;
-	struct gss_cl_ctx	*gc_ctx;
+	struct gss_cl_ctx __rcu	*gc_ctx;
 	struct gss_upcall_msg	*gc_upcall;
 	unsigned long		gc_upcall_timestamp;
 	unsigned char		gc_machine_cred : 1;
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 4af270e..2669751 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -293,8 +293,8 @@
 extern bool events_check_enabled;
 
 extern bool pm_check_wakeup_events(void);
-extern bool pm_get_wakeup_count(unsigned long *count);
-extern bool pm_save_wakeup_count(unsigned long count);
+extern bool pm_get_wakeup_count(unsigned int *count);
+extern bool pm_save_wakeup_count(unsigned int count);
 #else /* !CONFIG_PM_SLEEP */
 
 static inline int register_pm_notifier(struct notifier_block *nb)
@@ -308,6 +308,8 @@
 }
 
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
+
+static inline bool pm_check_wakeup_events(void) { return true; }
 #endif /* !CONFIG_PM_SLEEP */
 
 extern struct mutex pm_mutex;
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 96eb576..30b8815 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -164,6 +164,10 @@
 			const struct attribute *attr, const char *group);
 void sysfs_remove_file_from_group(struct kobject *kobj,
 			const struct attribute *attr, const char *group);
+int sysfs_merge_group(struct kobject *kobj,
+		       const struct attribute_group *grp);
+void sysfs_unmerge_group(struct kobject *kobj,
+		       const struct attribute_group *grp);
 
 void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr);
 void sysfs_notify_dirent(struct sysfs_dirent *sd);
@@ -302,6 +306,17 @@
 {
 }
 
+static inline int sysfs_merge_group(struct kobject *kobj,
+		       const struct attribute_group *grp)
+{
+	return 0;
+}
+
+static inline void sysfs_unmerge_group(struct kobject *kobj,
+		       const struct attribute_group *grp)
+{
+}
+
 static inline void sysfs_notify(struct kobject *kobj, const char *dir,
 				const char *attr)
 {
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index a8cc4e1..c9069654 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -23,12 +23,12 @@
 		};
 		/* For futex_wait and futex_wait_requeue_pi */
 		struct {
-			u32 *uaddr;
+			u32 __user *uaddr;
 			u32 val;
 			u32 flags;
 			u32 bitset;
 			u64 time;
-			u32 *uaddr2;
+			u32 __user *uaddr2;
 		} futex;
 		/* For nanosleep */
 		struct {
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 64e084f..b91a40e 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -201,6 +201,12 @@
 	.balance_interval	= 64,					\
 }
 
+#ifdef CONFIG_SCHED_BOOK
+#ifndef SD_BOOK_INIT
+#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
+#endif
+#endif /* CONFIG_SCHED_BOOK */
+
 #ifdef CONFIG_NUMA
 #ifndef SD_NODE_INIT
 #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!!
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 103d1b6..a4a90b67 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/rcupdate.h>
+#include <linux/jump_label.h>
 
 struct module;
 struct tracepoint;
@@ -145,7 +146,9 @@
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		if (unlikely(__tracepoint_##name.state))		\
+		JUMP_LABEL(&__tracepoint_##name.state, do_trace);	\
+		return;							\
+do_trace:								\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args));			\
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 01c2145..63a4fe6 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -117,10 +117,12 @@
 extern struct vm_struct *vmlist;
 extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
 
+#ifdef CONFIG_SMP
 struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 				     const size_t *sizes, int nr_vms,
 				     size_t align, gfp_t gfp_mask);
 
 void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
+#endif
 
 #endif /* _LINUX_VMALLOC_H */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 25e02c9..070bb7a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -243,11 +243,12 @@
 	WQ_NON_REENTRANT	= 1 << 0, /* guarantee non-reentrance */
 	WQ_UNBOUND		= 1 << 1, /* not bound to any cpu */
 	WQ_FREEZEABLE		= 1 << 2, /* freeze during suspend */
-	WQ_RESCUER		= 1 << 3, /* has an rescue worker */
+	WQ_MEM_RECLAIM		= 1 << 3, /* may be used for memory reclaim */
 	WQ_HIGHPRI		= 1 << 4, /* high priority */
 	WQ_CPU_INTENSIVE	= 1 << 5, /* cpu instensive workqueue */
 
 	WQ_DYING		= 1 << 6, /* internal: workqueue is dying */
+	WQ_RESCUER		= 1 << 7, /* internal: workqueue has rescuer */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
@@ -306,12 +307,30 @@
 	__alloc_workqueue_key((name), (flags), (max_active), NULL, NULL)
 #endif
 
+/**
+ * alloc_ordered_workqueue - allocate an ordered workqueue
+ * @name: name of the workqueue
+ * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_MEM_RECLAIM are meaningful)
+ *
+ * Allocate an ordered workqueue.  An ordered workqueue executes at
+ * most one work item at any given time in the queued order.  They are
+ * implemented as unbound workqueues with @max_active of one.
+ *
+ * RETURNS:
+ * Pointer to the allocated workqueue on success, %NULL on failure.
+ */
+static inline struct workqueue_struct *
+alloc_ordered_workqueue(const char *name, unsigned int flags)
+{
+	return alloc_workqueue(name, WQ_UNBOUND | flags, 1);
+}
+
 #define create_workqueue(name)					\
-	alloc_workqueue((name), WQ_RESCUER, 1)
+	alloc_workqueue((name), WQ_MEM_RECLAIM, 1)
 #define create_freezeable_workqueue(name)			\
-	alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1)
+	alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
 #define create_singlethread_workqueue(name)			\
-	alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1)
+	alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
@@ -325,7 +344,6 @@
 
 extern void flush_workqueue(struct workqueue_struct *wq);
 extern void flush_scheduled_work(void);
-extern void flush_delayed_work(struct delayed_work *work);
 
 extern int schedule_work(struct work_struct *work);
 extern int schedule_work_on(int cpu, struct work_struct *work);
@@ -337,8 +355,13 @@
 
 int execute_in_process_context(work_func_t fn, struct execute_work *);
 
-extern int flush_work(struct work_struct *work);
-extern int cancel_work_sync(struct work_struct *work);
+extern bool flush_work(struct work_struct *work);
+extern bool flush_work_sync(struct work_struct *work);
+extern bool cancel_work_sync(struct work_struct *work);
+
+extern bool flush_delayed_work(struct delayed_work *dwork);
+extern bool flush_delayed_work_sync(struct delayed_work *work);
+extern bool cancel_delayed_work_sync(struct delayed_work *dwork);
 
 extern void workqueue_set_max_active(struct workqueue_struct *wq,
 				     int max_active);
@@ -352,9 +375,9 @@
  * it returns 1 and the work doesn't re-arm itself. Run flush_workqueue() or
  * cancel_work_sync() to wait on it.
  */
-static inline int cancel_delayed_work(struct delayed_work *work)
+static inline bool cancel_delayed_work(struct delayed_work *work)
 {
-	int ret;
+	bool ret;
 
 	ret = del_timer_sync(&work->timer);
 	if (ret)
@@ -367,9 +390,9 @@
  * if it returns 0 the timer function may be running and the queueing is in
  * progress.
  */
-static inline int __cancel_delayed_work(struct delayed_work *work)
+static inline bool __cancel_delayed_work(struct delayed_work *work)
 {
-	int ret;
+	bool ret;
 
 	ret = del_timer(&work->timer);
 	if (ret)
@@ -377,8 +400,6 @@
 	return ret;
 }
 
-extern int cancel_delayed_work_sync(struct delayed_work *work);
-
 /* Obsolete. use cancel_delayed_work_sync() */
 static inline
 void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq,
@@ -409,8 +430,4 @@
 extern void thaw_workqueues(void);
 #endif /* CONFIG_FREEZER */
 
-#ifdef CONFIG_LOCKDEP
-int in_workqueue_context(struct workqueue_struct *wq);
-#endif
-
 #endif
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index ef6c24a..a4dc5b0 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -51,7 +51,8 @@
 		return 0;
 
 	rcu_read_lock();
-	id = rcu_dereference(net_cls_subsys_id);
+	id = rcu_dereference_index_check(net_cls_subsys_id,
+					 rcu_read_lock_held());
 	if (id >= 0)
 		classid = container_of(task_subsys_state(p, id),
 				       struct cgroup_cls_state, css)->classid;
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index e624dae..caf17db 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -75,7 +75,7 @@
 /* nf_conn feature for connections that have a helper */
 struct nf_conn_help {
 	/* Helper. if any */
-	struct nf_conntrack_helper *helper;
+	struct nf_conntrack_helper __rcu *helper;
 
 	union nf_conntrack_help help;
 
diff --git a/include/pcmcia/cs.h b/include/pcmcia/cs.h
deleted file mode 100644
index 68d8bde..0000000
--- a/include/pcmcia/cs.h
+++ /dev/null
@@ -1,95 +0,0 @@
-/*
- * cs.h
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * The initial developer of the original code is David A. Hinds
- * <dahinds@users.sourceforge.net>.  Portions created by David A. Hinds
- * are Copyright (C) 1999 David A. Hinds.  All Rights Reserved.
- *
- * (C) 1999             David A. Hinds
- */
-
-#ifndef _LINUX_CS_H
-#define _LINUX_CS_H
-
-#ifdef __KERNEL__
-#include <linux/interrupt.h>
-#endif
-
-/* ModifyConfiguration */
-typedef struct modconf_t {
-    u_int	Attributes;
-    u_int	Vcc, Vpp1, Vpp2;
-} modconf_t;
-
-/* Attributes for ModifyConfiguration */
-#define CONF_IRQ_CHANGE_VALID	0x0100
-#define CONF_VCC_CHANGE_VALID	0x0200
-#define CONF_VPP1_CHANGE_VALID	0x0400
-#define CONF_VPP2_CHANGE_VALID	0x0800
-#define CONF_IO_CHANGE_WIDTH	0x1000
-
-/* For RequestConfiguration */
-typedef struct config_req_t {
-    u_int	Attributes;
-    u_int	Vpp; /* both Vpp1 and Vpp2 */
-    u_int	IntType;
-    u_int	ConfigBase;
-    u_char	Status, Pin, Copy, ExtStatus;
-    u_char	ConfigIndex;
-    u_int	Present;
-} config_req_t;
-
-/* Attributes for RequestConfiguration */
-#define CONF_ENABLE_IRQ		0x01
-#define CONF_ENABLE_DMA		0x02
-#define CONF_ENABLE_SPKR	0x04
-#define CONF_ENABLE_PULSE_IRQ	0x08
-#define CONF_VALID_CLIENT	0x100
-
-/* IntType field */
-#define INT_MEMORY		0x01
-#define INT_MEMORY_AND_IO	0x02
-#define INT_CARDBUS		0x04
-#define INT_ZOOMED_VIDEO	0x08
-
-/* Configuration registers present */
-#define PRESENT_OPTION		0x001
-#define PRESENT_STATUS		0x002
-#define PRESENT_PIN_REPLACE	0x004
-#define PRESENT_COPY		0x008
-#define PRESENT_EXT_STATUS	0x010
-#define PRESENT_IOBASE_0	0x020
-#define PRESENT_IOBASE_1	0x040
-#define PRESENT_IOBASE_2	0x080
-#define PRESENT_IOBASE_3	0x100
-#define PRESENT_IOSIZE		0x200
-
-/* For RequestWindow */
-typedef struct win_req_t {
-    u_int	Attributes;
-    u_long	Base;
-    u_int	Size;
-    u_int	AccessSpeed;
-} win_req_t;
-
-/* Attributes for RequestWindow */
-#define WIN_MEMORY_TYPE_CM	0x00 /* default */
-#define WIN_MEMORY_TYPE_AM	0x20 /* MAP_ATTRIB */
-#define WIN_DATA_WIDTH_8	0x00 /* default */
-#define WIN_DATA_WIDTH_16	0x02 /* MAP_16BIT */
-#define WIN_ENABLE		0x01 /* MAP_ACTIVE */
-#define WIN_USE_WAIT		0x40 /* MAP_USE_WAIT */
-
-#define WIN_FLAGS_MAP		0x63 /* MAP_ATTRIB | MAP_16BIT | MAP_ACTIVE |
-					MAP_USE_WAIT */
-#define WIN_FLAGS_REQ		0x1c /* mapping to socket->win[i]:
-					0x04 -> 0
-					0x08 -> 1
-					0x0c -> 2
-					0x10 -> 3 */
-
-#endif /* _LINUX_CS_H */
diff --git a/include/pcmcia/ds.h b/include/pcmcia/ds.h
index 70c58ed..8479b66 100644
--- a/include/pcmcia/ds.h
+++ b/include/pcmcia/ds.h
@@ -24,9 +24,11 @@
 
 #ifdef __KERNEL__
 #include <linux/device.h>
+#include <linux/interrupt.h>
 #include <pcmcia/ss.h>
 #include <asm/atomic.h>
 
+
 /*
  * PCMCIA device drivers (16-bit cards only; 32-bit cards require CardBus
  * a.k.a. PCI drivers
@@ -36,8 +38,6 @@
 struct config_t;
 struct net_device;
 
-typedef struct resource *window_handle_t;
-
 /* dynamic device IDs for PCMCIA device drivers. See
  * Documentation/pcmcia/driver.txt for details.
 */
@@ -47,6 +47,8 @@
 };
 
 struct pcmcia_driver {
+	const char		*name;
+
 	int (*probe)		(struct pcmcia_device *dev);
 	void (*remove)		(struct pcmcia_device *dev);
 
@@ -90,15 +92,17 @@
 
 	struct list_head	socket_device_list;
 
-	/* deprecated, will be cleaned up soon */
-	config_req_t		conf;
-	window_handle_t		win;
-
 	/* device setup */
 	unsigned int		irq;
 	struct resource		*resource[PCMCIA_NUM_RESOURCES];
+	resource_size_t		card_addr;	/* for the 1st IOMEM resource */
+	unsigned int		vpp;
 
-	unsigned int		io_lines; /* number of I/O lines */
+	unsigned int		config_flags;	/* CONF_ENABLE_ flags below */
+	unsigned int		config_base;
+	unsigned int		config_index;
+	unsigned int		config_regs;	/* PRESENT_ flags below */
+	unsigned int		io_lines;	/* number of I/O lines */
 
 	/* Is the device suspended? */
 	u16			suspended:1;
@@ -174,9 +178,6 @@
 /* loop CIS entries for valid configuration */
 int pcmcia_loop_config(struct pcmcia_device *p_dev,
 		       int	(*conf_check)	(struct pcmcia_device *p_dev,
-						 cistpl_cftable_entry_t *cf,
-						 cistpl_cftable_entry_t *dflt,
-						 unsigned int vcc,
 						 void *priv_data),
 		       void *priv_data);
 
@@ -206,16 +207,17 @@
 int __must_check pcmcia_request_irq(struct pcmcia_device *p_dev,
 				irq_handler_t handler);
 
-int pcmcia_request_configuration(struct pcmcia_device *p_dev,
-				 config_req_t *req);
+int pcmcia_enable_device(struct pcmcia_device *p_dev);
 
-int pcmcia_request_window(struct pcmcia_device *p_dev, win_req_t *req,
-			  window_handle_t *wh);
-int pcmcia_release_window(struct pcmcia_device *p_dev, window_handle_t win);
-int pcmcia_map_mem_page(struct pcmcia_device *p_dev, window_handle_t win,
+int pcmcia_request_window(struct pcmcia_device *p_dev, struct resource *res,
+			unsigned int speed);
+int pcmcia_release_window(struct pcmcia_device *p_dev, struct resource *res);
+int pcmcia_map_mem_page(struct pcmcia_device *p_dev, struct resource *res,
 			unsigned int offset);
 
-int pcmcia_modify_configuration(struct pcmcia_device *p_dev, modconf_t *mod);
+int pcmcia_fixup_vpp(struct pcmcia_device *p_dev, unsigned char new_vpp);
+int pcmcia_fixup_iowidth(struct pcmcia_device *p_dev);
+
 void pcmcia_disable_device(struct pcmcia_device *p_dev);
 
 /* IO ports */
@@ -224,15 +226,48 @@
 #define IO_DATA_PATH_WIDTH_16	0x08
 #define IO_DATA_PATH_WIDTH_AUTO	0x10
 
-/* convert flag found in cfgtable to data path width parameter */
-static inline int pcmcia_io_cfg_data_width(unsigned int flags)
-{
-	if (!(flags & CISTPL_IO_8BIT))
-		return IO_DATA_PATH_WIDTH_16;
-	if (!(flags & CISTPL_IO_16BIT))
-		return IO_DATA_PATH_WIDTH_8;
-	return IO_DATA_PATH_WIDTH_AUTO;
-}
+/* IO memory */
+#define WIN_MEMORY_TYPE_CM	0x00 /* default */
+#define WIN_MEMORY_TYPE_AM	0x20 /* MAP_ATTRIB */
+#define WIN_DATA_WIDTH_8	0x00 /* default */
+#define WIN_DATA_WIDTH_16	0x02 /* MAP_16BIT */
+#define WIN_ENABLE		0x01 /* MAP_ACTIVE */
+#define WIN_USE_WAIT		0x40 /* MAP_USE_WAIT */
+
+#define WIN_FLAGS_MAP		0x63 /* MAP_ATTRIB | MAP_16BIT | MAP_ACTIVE |
+					MAP_USE_WAIT */
+#define WIN_FLAGS_REQ		0x1c /* mapping to socket->win[i]:
+					0x04 -> 0
+					0x08 -> 1
+					0x0c -> 2
+					0x10 -> 3 */
+
+/* config_reg{ister}s present for this PCMCIA device */
+#define PRESENT_OPTION		0x001
+#define PRESENT_STATUS		0x002
+#define PRESENT_PIN_REPLACE	0x004
+#define PRESENT_COPY		0x008
+#define PRESENT_EXT_STATUS	0x010
+#define PRESENT_IOBASE_0	0x020
+#define PRESENT_IOBASE_1	0x040
+#define PRESENT_IOBASE_2	0x080
+#define PRESENT_IOBASE_3	0x100
+#define PRESENT_IOSIZE		0x200
+
+/* flags to be passed to pcmcia_enable_device() */
+#define CONF_ENABLE_IRQ         0x0001
+#define CONF_ENABLE_SPKR        0x0002
+#define CONF_ENABLE_PULSE_IRQ   0x0004
+#define CONF_ENABLE_ESR         0x0008
+#define CONF_ENABLE_IOCARD	0x0010 /* auto-enabled if IO resources or IRQ
+					* (CONF_ENABLE_IRQ) in use */
+
+/* flags used by pcmcia_loop_config() autoconfiguration */
+#define CONF_AUTO_CHECK_VCC	0x0100 /* check for matching Vcc? */
+#define CONF_AUTO_SET_VPP	0x0200 /* set Vpp? */
+#define CONF_AUTO_AUDIO		0x0400 /* enable audio line? */
+#define CONF_AUTO_SET_IO	0x0800 /* set ->resource[0,1] */
+#define CONF_AUTO_SET_IOMEM	0x1000 /* set ->resource[2] */
 
 #endif /* __KERNEL__ */
 
diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h
index 626b63c..731cde0 100644
--- a/include/pcmcia/ss.h
+++ b/include/pcmcia/ss.h
@@ -19,7 +19,6 @@
 #include <linux/sched.h>	/* task_struct, completion */
 #include <linux/mutex.h>
 
-#include <pcmcia/cs.h>
 #ifdef CONFIG_CARDBUS
 #include <linux/pci.h>
 #endif
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 8fcb6e0..d63533a 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -32,6 +32,12 @@
 #endif
 
 /*
+ * DIX-capable adapters effectively support infinite chaining for the
+ * protection information scatterlist
+ */
+#define SCSI_MAX_PROT_SG_SEGMENTS	0xFFFF
+
+/*
  * Special value for scanning to specify scanning or rescanning of all
  * possible channels, (target) ids, or luns on a given shost.
  */
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index b7bdecb..d0a6a84 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -388,6 +388,7 @@
 	 * of scatter-gather.
 	 */
 	unsigned short sg_tablesize;
+	unsigned short sg_prot_tablesize;
 
 	/*
 	 * Set this if the host adapter has limitations beside segment count.
@@ -599,6 +600,7 @@
 	int can_queue;
 	short cmd_per_lun;
 	short unsigned int sg_tablesize;
+	short unsigned int sg_prot_tablesize;
 	short unsigned int max_sectors;
 	unsigned long dma_boundary;
 	/* 
@@ -823,6 +825,11 @@
 	return shost->prot_capabilities;
 }
 
+static inline int scsi_host_prot_dma(struct Scsi_Host *shost)
+{
+	return shost->prot_capabilities >= SHOST_DIX_TYPE0_PROTECTION;
+}
+
 static inline unsigned int scsi_host_dif_capable(struct Scsi_Host *shost, unsigned int target_type)
 {
 	static unsigned char cap[] = { 0,
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 1723138..d6e7994 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -97,13 +97,9 @@
 static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
 {
         struct request *req = cmd->request;
-	struct scsi_device *sdev = cmd->device;
 
         if (blk_rq_tagged(req)) {
-		if (sdev->ordered_tags && req->cmd_flags & REQ_HARDBARRIER)
-        	        *msg++ = MSG_ORDERED_TAG;
-        	else
-        	        *msg++ = MSG_SIMPLE_TAG;
+		*msg++ = MSG_SIMPLE_TAG;
         	*msg++ = req->tag;
         	return 2;
 	}
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index 0e4cfb6..6fa7cbab7 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -5,7 +5,9 @@
 #define _TRACE_IRQ_H
 
 #include <linux/tracepoint.h>
-#include <linux/interrupt.h>
+
+struct irqaction;
+struct softirq_action;
 
 #define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
 #define show_softirq_name(val)				\
@@ -93,7 +95,10 @@
 	),
 
 	TP_fast_assign(
-		__entry->vec = (int)(h - vec);
+		if (vec)
+			__entry->vec = (int)(h - vec);
+		else
+			__entry->vec = (int)(long)h;
 	),
 
 	TP_printk("vec=%d [action=%s]", __entry->vec,
@@ -136,6 +141,23 @@
 	TP_ARGS(h, vec)
 );
 
+/**
+ * softirq_raise - called immediately when a softirq is raised
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the softirq vector number which is
+ * raised. @vec is NULL and it means @h includes vector number not
+ * softirq_action. When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq raise latency.
+ */
+DEFINE_EVENT(softirq, softirq_raise,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec)
+);
+
 #endif /*  _TRACE_IRQ_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
index 188deca..8fe1e93 100644
--- a/include/trace/events/napi.h
+++ b/include/trace/events/napi.h
@@ -6,10 +6,31 @@
 
 #include <linux/netdevice.h>
 #include <linux/tracepoint.h>
+#include <linux/ftrace.h>
 
-DECLARE_TRACE(napi_poll,
+#define NO_DEV "(no_device)"
+
+TRACE_EVENT(napi_poll,
+
 	TP_PROTO(struct napi_struct *napi),
-	TP_ARGS(napi));
+
+	TP_ARGS(napi),
+
+	TP_STRUCT__entry(
+		__field(	struct napi_struct *,	napi)
+		__string(	dev_name, napi->dev ? napi->dev->name : NO_DEV)
+	),
+
+	TP_fast_assign(
+		__entry->napi = napi;
+		__assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV);
+	),
+
+	TP_printk("napi poll on napi struct %p for device %s",
+		__entry->napi, __get_str(dev_name))
+);
+
+#undef NO_DEV
 
 #endif /* _TRACE_NAPI_H_ */
 
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
new file mode 100644
index 0000000..5f247f5
--- /dev/null
+++ b/include/trace/events/net.h
@@ -0,0 +1,82 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM net
+
+#if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NET_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(net_dev_xmit,
+
+	TP_PROTO(struct sk_buff *skb,
+		 int rc),
+
+	TP_ARGS(skb, rc),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__field(	int,		rc		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__entry->rc = rc;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
+		__get_str(name), __entry->skbaddr, __entry->len, __entry->rc)
+);
+
+DECLARE_EVENT_CLASS(net_dev_template,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u",
+		__get_str(name), __entry->skbaddr, __entry->len)
+)
+
+DEFINE_EVENT(net_dev_template, net_dev_queue,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_receive_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_rx,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+#endif /* _TRACE_NET_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 35a2a6e..286784d 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -10,12 +10,17 @@
 #ifndef _TRACE_POWER_ENUM_
 #define _TRACE_POWER_ENUM_
 enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
+	POWER_NONE	= 0,
+	POWER_CSTATE	= 1,	/* C-State */
+	POWER_PSTATE	= 2,	/* Fequency change or DVFS */
+	POWER_SSTATE	= 3,	/* Suspend */
 };
 #endif
 
+/*
+ * The power events are used for cpuidle & suspend (power_start, power_end)
+ *  and for cpufreq (power_frequency)
+ */
 DECLARE_EVENT_CLASS(power,
 
 	TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
@@ -70,6 +75,85 @@
 
 );
 
+/*
+ * The clock events are used for clock enable/disable and for
+ *  clock rate change
+ */
+DECLARE_EVENT_CLASS(clock,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_enable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_disable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_set_rate,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+/*
+ * The power domain events are used for power domains transitions
+ */
+DECLARE_EVENT_CLASS(power_domain,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(power_domain, power_domain_target,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9208c92..f633478 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -362,6 +362,35 @@
 			(unsigned long long)__entry->vruntime)
 );
 
+/*
+ * Tracepoint for showing priority inheritance modifying a tasks
+ * priority.
+ */
+TRACE_EVENT(sched_pi_setprio,
+
+	TP_PROTO(struct task_struct *tsk, int newprio),
+
+	TP_ARGS(tsk, newprio),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( int,	oldprio			)
+		__field( int,	newprio			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		= tsk->pid;
+		__entry->oldprio	= tsk->prio;
+		__entry->newprio	= newprio;
+	),
+
+	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
+			__entry->comm, __entry->pid,
+			__entry->oldprio, __entry->newprio)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 4b2be6d..75ce9d5 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -35,6 +35,23 @@
 		__entry->skbaddr, __entry->protocol, __entry->location)
 );
 
+TRACE_EVENT(consume_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,	skbaddr	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+	),
+
+	TP_printk("skbaddr=%p", __entry->skbaddr)
+);
+
 TRACE_EVENT(skb_copy_datagram_iovec,
 
 	TP_PROTO(const struct sk_buff *skb, int len),
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
index 49682d7..7d49729 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h
@@ -7,6 +7,76 @@
 #include <linux/tracepoint.h>
 #include <linux/workqueue.h>
 
+DECLARE_EVENT_CLASS(workqueue_work,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+	),
+
+	TP_printk("work struct %p", __entry->work)
+);
+
+/**
+ * workqueue_queue_work - called when a work gets queued
+ * @req_cpu:	the requested cpu
+ * @cwq:	pointer to struct cpu_workqueue_struct
+ * @work:	pointer to struct work_struct
+ *
+ * This event occurs when a work is queued immediately or once a
+ * delayed work is actually queued on a workqueue (ie: once the delay
+ * has been reached).
+ */
+TRACE_EVENT(workqueue_queue_work,
+
+	TP_PROTO(unsigned int req_cpu, struct cpu_workqueue_struct *cwq,
+		 struct work_struct *work),
+
+	TP_ARGS(req_cpu, cwq, work),
+
+	TP_STRUCT__entry(
+		__field( void *,	work	)
+		__field( void *,	function)
+		__field( void *,	workqueue)
+		__field( unsigned int,	req_cpu	)
+		__field( unsigned int,	cpu	)
+	),
+
+	TP_fast_assign(
+		__entry->work		= work;
+		__entry->function	= work->func;
+		__entry->workqueue	= cwq->wq;
+		__entry->req_cpu	= req_cpu;
+		__entry->cpu		= cwq->gcwq->cpu;
+	),
+
+	TP_printk("work struct=%p function=%pf workqueue=%p req_cpu=%u cpu=%u",
+		  __entry->work, __entry->function, __entry->workqueue,
+		  __entry->req_cpu, __entry->cpu)
+);
+
+/**
+ * workqueue_activate_work - called when a work gets activated
+ * @work:	pointer to struct work_struct
+ *
+ * This event occurs when a queued work is put on the active queue,
+ * which happens immediately after queueing unless @max_active limit
+ * is reached.
+ */
+DEFINE_EVENT(workqueue_work, workqueue_activate_work,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work)
+);
+
 /**
  * workqueue_execute_start - called immediately before the workqueue callback
  * @work:	pointer to struct work_struct
@@ -38,24 +108,13 @@
  *
  * Allows to track workqueue execution.
  */
-TRACE_EVENT(workqueue_execute_end,
+DEFINE_EVENT(workqueue_work, workqueue_execute_end,
 
 	TP_PROTO(struct work_struct *work),
 
-	TP_ARGS(work),
-
-	TP_STRUCT__entry(
-		__field( void *,	work	)
-	),
-
-	TP_fast_assign(
-		__entry->work		= work;
-	),
-
-	TP_printk("work struct %p", __entry->work)
+	TP_ARGS(work)
 );
 
-
 #endif /*  _TRACE_WORKQUEUE_H */
 
 /* This part must be outside protection */
diff --git a/init/Kconfig b/init/Kconfig
index 2de5b1c..bd125a7 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -21,6 +21,13 @@
 	depends on !UML
 	default y
 
+config HAVE_IRQ_WORK
+	bool
+
+config IRQ_WORK
+	bool
+	depends on HAVE_IRQ_WORK
+
 menu "General setup"
 
 config EXPERIMENTAL
@@ -64,7 +71,7 @@
 
 config LOCK_KERNEL
 	bool
-	depends on SMP || PREEMPT
+	depends on (SMP || PREEMPT) && BKL
 	default y
 
 config INIT_ENV_ARG_LIMIT
@@ -332,6 +339,8 @@
 	depends on AUDITSYSCALL
 	select FSNOTIFY
 
+source "kernel/irq/Kconfig"
+
 menu "RCU Subsystem"
 
 choice
@@ -340,6 +349,7 @@
 
 config TREE_RCU
 	bool "Tree-based hierarchical RCU"
+	depends on !PREEMPT && SMP
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
@@ -347,7 +357,7 @@
 	  smaller systems.
 
 config TREE_PREEMPT_RCU
-	bool "Preemptable tree-based hierarchical RCU"
+	bool "Preemptible tree-based hierarchical RCU"
 	depends on PREEMPT
 	help
 	  This option selects the RCU implementation that is
@@ -365,8 +375,22 @@
 	  is not required.  This option greatly reduces the
 	  memory footprint of RCU.
 
+config TINY_PREEMPT_RCU
+	bool "Preemptible UP-only small-memory-footprint RCU"
+	depends on !SMP && PREEMPT
+	help
+	  This option selects the RCU implementation that is designed
+	  for real-time UP systems.  This option greatly reduces the
+	  memory footprint of RCU.
+
 endchoice
 
+config PREEMPT_RCU
+	def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU )
+	help
+	  This option enables preemptible-RCU code that is common between
+	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
+
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on TREE_RCU || TREE_PREEMPT_RCU
@@ -387,9 +411,12 @@
 	help
 	  This option controls the fanout of hierarchical implementations
 	  of RCU, allowing RCU to work efficiently on machines with
-	  large numbers of CPUs.  This value must be at least the cube
-	  root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
-	  systems and up to 262,144 for 64-bit systems.
+	  large numbers of CPUs.  This value must be at least the fourth
+	  root of NR_CPUS, which allows NR_CPUS to be insanely large.
+	  The default value of RCU_FANOUT should be used for production
+	  systems, but if you are stress-testing the RCU implementation
+	  itself, small RCU_FANOUT values allow you to test large-system
+	  code paths on small(er) systems.
 
 	  Select a specific number if testing RCU itself.
 	  Take the default if unsure.
@@ -634,11 +661,14 @@
 
 	Currently, CFQ IO scheduler uses it to recognize task groups and
 	control disk bandwidth allocation (proportional time slice allocation)
-	to such task groups.
+	to such task groups. It is also used by bio throttling logic in
+	block layer to implement upper limit in IO rates on a device.
 
 	This option only enables generic Block IO controller infrastructure.
-	One needs to also enable actual IO controlling logic in CFQ for it
-	to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y).
+	One needs to also enable actual IO controlling logic/policy. For
+	enabling proportional weight division of disk bandwidth in CFQ seti
+	CONFIG_CFQ_GROUP_IOSCHED=y and for enabling throttling policy set
+	CONFIG_BLK_THROTTLE=y.
 
 	See Documentation/cgroups/blkio-controller.txt for more information.
 
@@ -987,6 +1017,7 @@
 	default y if (PROFILING || PERF_COUNTERS)
 	depends on HAVE_PERF_EVENTS
 	select ANON_INODES
+	select IRQ_WORK
 	help
 	  Enable kernel support for various performance events provided
 	  by software and hardware.
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 02e3ca4..42db055 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -58,6 +58,62 @@
 __setup("ro", readonly);
 __setup("rw", readwrite);
 
+#ifdef CONFIG_BLOCK
+/**
+ * match_dev_by_uuid - callback for finding a partition using its uuid
+ * @dev:	device passed in by the caller
+ * @data:	opaque pointer to a 36 byte char array with a UUID
+ *
+ * Returns 1 if the device matches, and 0 otherwise.
+ */
+static int match_dev_by_uuid(struct device *dev, void *data)
+{
+	u8 *uuid = data;
+	struct hd_struct *part = dev_to_part(dev);
+
+	if (!part->info)
+		goto no_match;
+
+	if (memcmp(uuid, part->info->uuid, sizeof(part->info->uuid)))
+			goto no_match;
+
+	return 1;
+no_match:
+	return 0;
+}
+
+
+/**
+ * devt_from_partuuid - looks up the dev_t of a partition by its UUID
+ * @uuid:	36 byte char array containing a hex ascii UUID
+ *
+ * The function will return the first partition which contains a matching
+ * UUID value in its partition_meta_info struct.  This does not search
+ * by filesystem UUIDs.
+ *
+ * Returns the matching dev_t on success or 0 on failure.
+ */
+static dev_t __init devt_from_partuuid(char *uuid_str)
+{
+	dev_t res = 0;
+	struct device *dev = NULL;
+	u8 uuid[16];
+
+	/* Pack the requested UUID in the expected format. */
+	part_pack_uuid(uuid_str, uuid);
+
+	dev = class_find_device(&block_class, NULL, uuid, &match_dev_by_uuid);
+	if (!dev)
+		goto done;
+
+	res = dev->devt;
+	put_device(dev);
+
+done:
+	return res;
+}
+#endif
+
 /*
  *	Convert a name into device number.  We accept the following variants:
  *
@@ -68,6 +124,8 @@
  *         of partition - device number of disk plus the partition number
  *	5) /dev/<disk_name>p<decimal> - same as the above, that form is
  *	   used when disk name of partitioned disk ends on a digit.
+ *	6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
+ *	   unique id of a partition if the partition table provides it.
  *
  *	If name doesn't have fall into the categories above, we return (0,0).
  *	block_class is used to check if something is a disk name. If the disk
@@ -82,6 +140,18 @@
 	dev_t res = 0;
 	int part;
 
+#ifdef CONFIG_BLOCK
+	if (strncmp(name, "PARTUUID=", 9) == 0) {
+		name += 9;
+		if (strlen(name) != 36)
+			goto fail;
+		res = devt_from_partuuid(name);
+		if (!res)
+			goto fail;
+		goto done;
+	}
+#endif
+
 	if (strncmp(name, "/dev/", 5) != 0) {
 		unsigned maj, min;
 
diff --git a/init/main.c b/init/main.c
index 94ab488..e59af24 100644
--- a/init/main.c
+++ b/init/main.c
@@ -424,7 +424,6 @@
 static __initdata DECLARE_COMPLETION(kthreadd_done);
 
 static noinline void __init_refok rest_init(void)
-	__releases(kernel_lock)
 {
 	int pid;
 
@@ -556,7 +555,6 @@
 
 	local_irq_disable();
 	early_boot_irqs_off();
-	early_init_irq_lock_class();
 
 /*
  * Interrupts are still disabled. Do necessary setups, then
@@ -819,7 +817,6 @@
  * makes it inline to init() and it becomes part of init.text section
  */
 static noinline int init_post(void)
-	__releases(kernel_lock)
 {
 	/* need to finish all async __init code before freeing the memory */
 	async_synchronize_full();
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index c60e519..e1e7b96 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1219,6 +1219,7 @@
 	.flush = mqueue_flush_file,
 	.poll = mqueue_poll_file,
 	.read = mqueue_read_file,
+	.llseek = default_llseek,
 };
 
 static const struct super_operations mqueue_super_ops = {
diff --git a/ipc/shm.c b/ipc/shm.c
index 52ed77e..7bc46a9fe 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -298,6 +298,7 @@
 #ifndef CONFIG_MMU
 	.get_unmapped_area	= shm_get_unmapped_area,
 #endif
+	.llseek		= noop_llseek,
 };
 
 static const struct file_operations shm_file_operations_huge = {
@@ -305,6 +306,7 @@
 	.fsync		= shm_fsync,
 	.release	= shm_release,
 	.get_unmapped_area	= shm_get_unmapped_area,
+	.llseek		= noop_llseek,
 };
 
 int is_file_shm_hugepages(struct file *file)
diff --git a/kernel/Makefile b/kernel/Makefile
index 0b72d1a..0b5ff08 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,8 +10,7 @@
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o range.o
-obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
+	    async.o range.o jump_label.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
@@ -23,6 +22,7 @@
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_perf_event.o = -pg
+CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -86,6 +86,7 @@
 obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
 obj-$(CONFIG_TINY_RCU) += rcutiny.o
+obj-$(CONFIG_TINY_PREEMPT_RCU) += rcutiny.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
@@ -100,6 +101,7 @@
 obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
+obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c9483d8..7b69b8d 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -52,7 +52,6 @@
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
 #include <linux/namei.h>
-#include <linux/smp_lock.h>
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
@@ -138,7 +137,7 @@
 	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
 	 * css_tryget() should be used for avoiding race.
 	 */
-	struct cgroup_subsys_state *css;
+	struct cgroup_subsys_state __rcu *css;
 	/*
 	 * ID of this css.
 	 */
@@ -1222,7 +1221,6 @@
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgroup_sb_opts opts;
 
-	lock_kernel();
 	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -1255,7 +1253,6 @@
 	kfree(opts.name);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
-	unlock_kernel();
 	return ret;
 }
 
@@ -1568,7 +1565,6 @@
  out_err:
 	kfree(opts.release_agent);
 	kfree(opts.name);
-
 	return ret;
 }
 
diff --git a/kernel/configs.c b/kernel/configs.c
index abaee68..b4066b4 100644
--- a/kernel/configs.c
+++ b/kernel/configs.c
@@ -66,6 +66,7 @@
 static const struct file_operations ikconfig_file_ops = {
 	.owner = THIS_MODULE,
 	.read = ikconfig_read_current,
+	.llseek = default_llseek,
 };
 
 static int __init ikconfig_init(void)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b23c097..51b143e 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1397,7 +1397,7 @@
 	if (tsk->flags & PF_THREAD_BOUND)
 		return -EINVAL;
 
-	ret = security_task_setscheduler(tsk, 0, NULL);
+	ret = security_task_setscheduler(tsk);
 	if (ret)
 		return ret;
 	if (threadgroup) {
@@ -1405,7 +1405,7 @@
 
 		rcu_read_lock();
 		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
-			ret = security_task_setscheduler(c, 0, NULL);
+			ret = security_task_setscheduler(c);
 			if (ret) {
 				rcu_read_unlock();
 				return ret;
diff --git a/kernel/early_res.c b/kernel/early_res.c
deleted file mode 100644
index 7bfae88..0000000
--- a/kernel/early_res.c
+++ /dev/null
@@ -1,590 +0,0 @@
-/*
- * early_res, could be used to replace bootmem
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/early_res.h>
-#include <linux/slab.h>
-#include <linux/kmemleak.h>
-
-/*
- * Early reserved memory areas.
- */
-/*
- * need to make sure this one is bigger enough before
- * find_fw_memmap_area could be used
- */
-#define MAX_EARLY_RES_X 32
-
-struct early_res {
-	u64 start, end;
-	char name[15];
-	char overlap_ok;
-};
-static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
-
-static int max_early_res __initdata = MAX_EARLY_RES_X;
-static struct early_res *early_res __initdata = &early_res_x[0];
-static int early_res_count __initdata;
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-		if (end > r->start && start < r->end)
-			break;
-	}
-
-	return i;
-}
-
-/*
- * Drop the i-th range from the early reservation map,
- * by copying any higher ranges down one over it, and
- * clearing what had been the last slot.
- */
-static void __init drop_range(int i)
-{
-	int j;
-
-	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
-		;
-
-	memmove(&early_res[i], &early_res[i + 1],
-	       (j - 1 - i) * sizeof(struct early_res));
-
-	early_res[j - 1].end = 0;
-	early_res_count--;
-}
-
-static void __init drop_range_partial(int i, u64 start, u64 end)
-{
-	u64 common_start, common_end;
-	u64 old_start, old_end;
-
-	old_start = early_res[i].start;
-	old_end = early_res[i].end;
-	common_start = max(old_start, start);
-	common_end = min(old_end, end);
-
-	/* no overlap ? */
-	if (common_start >= common_end)
-		return;
-
-	if (old_start < common_start) {
-		/* make head segment */
-		early_res[i].end = common_start;
-		if (old_end > common_end) {
-			char name[15];
-
-			/*
-			 * Save a local copy of the name, since the
-			 * early_res array could get resized inside
-			 * reserve_early_without_check() ->
-			 * __check_and_double_early_res(), which would
-			 * make the current name pointer invalid.
-			 */
-			strncpy(name, early_res[i].name,
-					 sizeof(early_res[i].name) - 1);
-			/* add another for left over on tail */
-			reserve_early_without_check(common_end, old_end, name);
-		}
-		return;
-	} else {
-		if (old_end > common_end) {
-			/* reuse the entry for tail left */
-			early_res[i].start = common_end;
-			return;
-		}
-		/* all covered */
-		drop_range(i);
-	}
-}
-
-/*
- * Split any existing ranges that:
- *  1) are marked 'overlap_ok', and
- *  2) overlap with the stated range [start, end)
- * into whatever portion (if any) of the existing range is entirely
- * below or entirely above the stated range.  Drop the portion
- * of the existing range that overlaps with the stated range,
- * which will allow the caller of this routine to then add that
- * stated range without conflicting with any existing range.
- */
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-	u64 lower_start, lower_end;
-	u64 upper_start, upper_end;
-	char name[15];
-
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		r = &early_res[i];
-
-		/* Continue past non-overlapping ranges */
-		if (end <= r->start || start >= r->end)
-			continue;
-
-		/*
-		 * Leave non-ok overlaps as is; let caller
-		 * panic "Overlapping early reservations"
-		 * when it hits this overlap.
-		 */
-		if (!r->overlap_ok)
-			return;
-
-		/*
-		 * We have an ok overlap.  We will drop it from the early
-		 * reservation map, and add back in any non-overlapping
-		 * portions (lower or upper) as separate, overlap_ok,
-		 * non-overlapping ranges.
-		 */
-
-		/* 1. Note any non-overlapping (lower or upper) ranges. */
-		strncpy(name, r->name, sizeof(name) - 1);
-
-		lower_start = lower_end = 0;
-		upper_start = upper_end = 0;
-		if (r->start < start) {
-			lower_start = r->start;
-			lower_end = start;
-		}
-		if (r->end > end) {
-			upper_start = end;
-			upper_end = r->end;
-		}
-
-		/* 2. Drop the original ok overlapping range */
-		drop_range(i);
-
-		i--;		/* resume for-loop on copied down entry */
-
-		/* 3. Add back in any non-overlapping ranges. */
-		if (lower_end)
-			reserve_early_overlap_ok(lower_start, lower_end, name);
-		if (upper_end)
-			reserve_early_overlap_ok(upper_start, upper_end, name);
-	}
-}
-
-static void __init __reserve_early(u64 start, u64 end, char *name,
-						int overlap_ok)
-{
-	int i;
-	struct early_res *r;
-
-	i = find_overlapped_early(start, end);
-	if (i >= max_early_res)
-		panic("Too many early reservations");
-	r = &early_res[i];
-	if (r->end)
-		panic("Overlapping early reservations "
-		      "%llx-%llx %s to %llx-%llx %s\n",
-		      start, end - 1, name ? name : "", r->start,
-		      r->end - 1, r->name);
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = overlap_ok;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-/*
- * A few early reservtations come here.
- *
- * The 'overlap_ok' in the name of this routine does -not- mean it
- * is ok for these reservations to overlap an earlier reservation.
- * Rather it means that it is ok for subsequent reservations to
- * overlap this one.
- *
- * Use this entry point to reserve early ranges when you are doing
- * so out of "Paranoia", reserving perhaps more memory than you need,
- * just in case, and don't mind a subsequent overlapping reservation
- * that is known to be needed.
- *
- * The drop_overlaps_that_are_ok() call here isn't really needed.
- * It would be needed if we had two colliding 'overlap_ok'
- * reservations, so that the second such would not panic on the
- * overlap with the first.  We don't have any such as of this
- * writing, but might as well tolerate such if it happens in
- * the future.
- */
-void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
-{
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 1);
-}
-
-static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
-{
-	u64 start, end, size, mem;
-	struct early_res *new;
-
-	/* do we have enough slots left ? */
-	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
-		return;
-
-	/* double it */
-	mem = -1ULL;
-	size = sizeof(struct early_res) * max_early_res * 2;
-	if (early_res == early_res_x)
-		start = 0;
-	else
-		start = early_res[0].end;
-	end = ex_start;
-	if (start + size < end)
-		mem = find_fw_memmap_area(start, end, size,
-					 sizeof(struct early_res));
-	if (mem == -1ULL) {
-		start = ex_end;
-		end = get_max_mapped();
-		if (start + size < end)
-			mem = find_fw_memmap_area(start, end, size,
-						 sizeof(struct early_res));
-	}
-	if (mem == -1ULL)
-		panic("can not find more space for early_res array");
-
-	new = __va(mem);
-	/* save the first one for own */
-	new[0].start = mem;
-	new[0].end = mem + size;
-	new[0].overlap_ok = 0;
-	/* copy old to new */
-	if (early_res == early_res_x) {
-		memcpy(&new[1], &early_res[0],
-			 sizeof(struct early_res) * max_early_res);
-		memset(&new[max_early_res+1], 0,
-			 sizeof(struct early_res) * (max_early_res - 1));
-		early_res_count++;
-	} else {
-		memcpy(&new[1], &early_res[1],
-			 sizeof(struct early_res) * (max_early_res - 1));
-		memset(&new[max_early_res], 0,
-			 sizeof(struct early_res) * max_early_res);
-	}
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = new;
-	max_early_res *= 2;
-	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
-		max_early_res, mem, mem + size - 1);
-}
-
-/*
- * Most early reservations come here.
- *
- * We first have drop_overlaps_that_are_ok() drop any pre-existing
- * 'overlap_ok' ranges, so that we can then reserve this memory
- * range without risk of panic'ing on an overlapping overlap_ok
- * early reservation.
- */
-void __init reserve_early(u64 start, u64 end, char *name)
-{
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 0);
-}
-
-void __init reserve_early_without_check(u64 start, u64 end, char *name)
-{
-	struct early_res *r;
-
-	if (start >= end)
-		return;
-
-	__check_and_double_early_res(start, end);
-
-	r = &early_res[early_res_count];
-
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = 0;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-	early_res_count++;
-}
-
-void __init free_early(u64 start, u64 end)
-{
-	struct early_res *r;
-	int i;
-
-	kmemleak_free_part(__va(start), end - start);
-
-	i = find_overlapped_early(start, end);
-	r = &early_res[i];
-	if (i >= max_early_res || r->end != end || r->start != start)
-		panic("free_early on not reserved area: %llx-%llx!",
-			 start, end - 1);
-
-	drop_range(i);
-}
-
-void __init free_early_partial(u64 start, u64 end)
-{
-	struct early_res *r;
-	int i;
-
-	kmemleak_free_part(__va(start), end - start);
-
-	if (start == end)
-		return;
-
-	if (WARN_ONCE(start > end, "  wrong range [%#llx, %#llx]\n", start, end))
-		return;
-
-try_next:
-	i = find_overlapped_early(start, end);
-	if (i >= max_early_res)
-		return;
-
-	r = &early_res[i];
-	/* hole ? */
-	if (r->end >= end && r->start <= start) {
-		drop_range_partial(i, start, end);
-		return;
-	}
-
-	drop_range_partial(i, start, end);
-	goto try_next;
-}
-
-#ifdef CONFIG_NO_BOOTMEM
-static void __init subtract_early_res(struct range *range, int az)
-{
-	int i, count;
-	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-#define DEBUG_PRINT_EARLY_RES 1
-
-#if DEBUG_PRINT_EARLY_RES
-	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
-#endif
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-#if DEBUG_PRINT_EARLY_RES
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s\n", i,
-			r->start, r->end, r->name);
-#endif
-		final_start = PFN_DOWN(r->start);
-		final_end = PFN_UP(r->end);
-		if (final_start >= final_end)
-			continue;
-		subtract_range(range, az, final_start, final_end);
-	}
-
-}
-
-int __init get_free_all_memory_range(struct range **rangep, int nodeid)
-{
-	int i, count;
-	u64 start = 0, end;
-	u64 size;
-	u64 mem;
-	struct range *range;
-	int nr_range;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	count *= 2;
-
-	size = sizeof(struct range) * count;
-	end = get_max_mapped();
-#ifdef MAX_DMA32_PFN
-	if (end > (MAX_DMA32_PFN << PAGE_SHIFT))
-		start = MAX_DMA32_PFN << PAGE_SHIFT;
-#endif
-	mem = find_fw_memmap_area(start, end, size, sizeof(struct range));
-	if (mem == -1ULL)
-		panic("can not find more space for range free");
-
-	range = __va(mem);
-	/* use early_node_map[] and early_res to get range array at first */
-	memset(range, 0, size);
-	nr_range = 0;
-
-	/* need to go over early_node_map to find out good range for node */
-	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
-#ifdef CONFIG_X86_32
-	subtract_range(range, count, max_low_pfn, -1ULL);
-#endif
-	subtract_early_res(range, count);
-	nr_range = clean_sort_range(range, count);
-
-	/* need to clear it ? */
-	if (nodeid == MAX_NUMNODES) {
-		memset(&early_res[0], 0,
-			 sizeof(struct early_res) * max_early_res);
-		early_res = NULL;
-		max_early_res = 0;
-	}
-
-	*rangep = range;
-	return nr_range;
-}
-#else
-void __init early_res_to_bootmem(u64 start, u64 end)
-{
-	int i, count;
-	u64 final_start, final_end;
-	int idx = 0;
-
-	count  = 0;
-	for (i = 0; i < max_early_res && early_res[i].end; i++)
-		count++;
-
-	/* need to skip first one ?*/
-	if (early_res != early_res_x)
-		idx = 1;
-
-	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
-			 count - idx, max_early_res, start, end);
-	for (i = idx; i < count; i++) {
-		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
-			r->start, r->end, r->name);
-		final_start = max(start, r->start);
-		final_end = min(end, r->end);
-		if (final_start >= final_end) {
-			printk(KERN_CONT "\n");
-			continue;
-		}
-		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
-			final_start, final_end);
-		reserve_bootmem_generic(final_start, final_end - final_start,
-				BOOTMEM_DEFAULT);
-	}
-	/* clear them */
-	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
-	early_res = NULL;
-	max_early_res = 0;
-	early_res_count = 0;
-}
-#endif
-
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
-	int i;
-	u64 addr = *addrp;
-	int changed = 0;
-	struct early_res *r;
-again:
-	i = find_overlapped_early(addr, addr + size);
-	r = &early_res[i];
-	if (i < max_early_res && r->end) {
-		*addrp = addr = round_up(r->end, align);
-		changed = 1;
-		goto again;
-	}
-	return changed;
-}
-
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
-{
-	int i;
-	u64 addr = *addrp, last;
-	u64 size = *sizep;
-	int changed = 0;
-again:
-	last = addr + size;
-	for (i = 0; i < max_early_res && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		if (last > r->start && addr < r->start) {
-			size = r->start - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last > r->end && addr < r->end) {
-			addr = round_up(r->end, align);
-			size = last - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last <= r->end && addr >= r->start) {
-			(*sizep)++;
-			return 0;
-		}
-	}
-	if (changed) {
-		*addrp = addr;
-		*sizep = size;
-	}
-	return changed;
-}
-
-/*
- * Find a free area with specified alignment in a specific range.
- * only with the area.between start to end is active range from early_node_map
- * so they are good as RAM
- */
-u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align)
-{
-	u64 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
-		;
-	last = addr + size;
-	if (last > ei_last)
-		goto out;
-	if (last > end)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
-
-u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align)
-{
-	u64 addr, last;
-
-	addr = round_up(ei_start, align);
-	if (addr < start)
-		addr = round_up(start, align);
-	if (addr >= ei_last)
-		goto out;
-	*sizep = ei_last - addr;
-	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
-		;
-	last = addr + *sizep;
-	if (last > ei_last)
-		goto out;
-
-	return addr;
-
-out:
-	return -1ULL;
-}
diff --git a/kernel/exit.c b/kernel/exit.c
index 0312022..e2bdf37 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -149,9 +149,7 @@
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
-#ifdef CONFIG_PERF_EVENTS
-	WARN_ON_ONCE(tsk->perf_event_ctxp);
-#endif
+	perf_event_delayed_put(tsk);
 	trace_sched_process_free(tsk);
 	put_task_struct(tsk);
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 6a3a5fa..a118bf1 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -91,6 +91,7 @@
 
 /**
  * struct futex_q - The hashed futex queue entry, one per waiting task
+ * @list:		priority-sorted list of tasks waiting on this futex
  * @task:		the task waiting on the futex
  * @lock_ptr:		the hash bucket lock
  * @key:		the key the futex is hashed on
@@ -104,7 +105,7 @@
  *
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.
  * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
- * The order of wakup is always to make the first condition true, then
+ * The order of wakeup is always to make the first condition true, then
  * the second.
  *
  * PI futexes are typically woken before they are removed from the hash list via
@@ -295,7 +296,7 @@
  * Slow path to fixup the fault we just took in the atomic write
  * access to @uaddr.
  *
- * We have no generic implementation of a non destructive write to the
+ * We have no generic implementation of a non-destructive write to the
  * user address. We know that we faulted in the atomic pagefault
  * disabled section so we can as well avoid the #PF overhead by
  * calling get_user_pages() right away.
@@ -515,7 +516,7 @@
 			 */
 			pi_state = this->pi_state;
 			/*
-			 * Userspace might have messed up non PI and PI futexes
+			 * Userspace might have messed up non-PI and PI futexes
 			 */
 			if (unlikely(!pi_state))
 				return -EINVAL;
@@ -736,8 +737,8 @@
 
 	/*
 	 * We set q->lock_ptr = NULL _before_ we wake up the task. If
-	 * a non futex wake up happens on another CPU then the task
-	 * might exit and p would dereference a non existing task
+	 * a non-futex wake up happens on another CPU then the task
+	 * might exit and p would dereference a non-existing task
 	 * struct. Prevent this by holding a reference on p across the
 	 * wake up.
 	 */
@@ -1131,11 +1132,13 @@
 
 /**
  * futex_requeue() - Requeue waiters from uaddr1 to uaddr2
- * uaddr1:	source futex user address
- * uaddr2:	target futex user address
- * nr_wake:	number of waiters to wake (must be 1 for requeue_pi)
- * nr_requeue:	number of waiters to requeue (0-INT_MAX)
- * requeue_pi:	if we are attempting to requeue from a non-pi futex to a
+ * @uaddr1:	source futex user address
+ * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
+ * @uaddr2:	target futex user address
+ * @nr_wake:	number of waiters to wake (must be 1 for requeue_pi)
+ * @nr_requeue:	number of waiters to requeue (0-INT_MAX)
+ * @cmpval:	@uaddr1 expected value (or %NULL)
+ * @requeue_pi:	if we are attempting to requeue from a non-pi futex to a
  * 		pi futex (pi to pi requeue is not supported)
  *
  * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
@@ -1360,10 +1363,10 @@
 
 /* The key must be already stored in q->key. */
 static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
+	__acquires(&hb->lock)
 {
 	struct futex_hash_bucket *hb;
 
-	get_futex_key_refs(&q->key);
 	hb = hash_futex(&q->key);
 	q->lock_ptr = &hb->lock;
 
@@ -1373,9 +1376,9 @@
 
 static inline void
 queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+	__releases(&hb->lock)
 {
 	spin_unlock(&hb->lock);
-	drop_futex_key_refs(&q->key);
 }
 
 /**
@@ -1391,6 +1394,7 @@
  * an example).
  */
 static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+	__releases(&hb->lock)
 {
 	int prio;
 
@@ -1471,6 +1475,7 @@
  * and dropped here.
  */
 static void unqueue_me_pi(struct futex_q *q)
+	__releases(q->lock_ptr)
 {
 	WARN_ON(plist_node_empty(&q->list));
 	plist_del(&q->list, &q->list.plist);
@@ -1480,8 +1485,6 @@
 	q->pi_state = NULL;
 
 	spin_unlock(q->lock_ptr);
-
-	drop_futex_key_refs(&q->key);
 }
 
 /*
@@ -1812,7 +1815,10 @@
 	}
 
 retry:
-	/* Prepare to wait on uaddr. */
+	/*
+	 * Prepare to wait on uaddr. On success, holds hb lock and increments
+	 * q.key refs.
+	 */
 	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
 	if (ret)
 		goto out;
@@ -1822,28 +1828,27 @@
 
 	/* If we were woken (and unqueued), we succeeded, whatever. */
 	ret = 0;
+	/* unqueue_me() drops q.key ref */
 	if (!unqueue_me(&q))
-		goto out_put_key;
+		goto out;
 	ret = -ETIMEDOUT;
 	if (to && !to->task)
-		goto out_put_key;
+		goto out;
 
 	/*
 	 * We expect signal_pending(current), but we might be the
 	 * victim of a spurious wakeup as well.
 	 */
-	if (!signal_pending(current)) {
-		put_futex_key(fshared, &q.key);
+	if (!signal_pending(current))
 		goto retry;
-	}
 
 	ret = -ERESTARTSYS;
 	if (!abs_time)
-		goto out_put_key;
+		goto out;
 
 	restart = &current_thread_info()->restart_block;
 	restart->fn = futex_wait_restart;
-	restart->futex.uaddr = (u32 *)uaddr;
+	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
 	restart->futex.time = abs_time->tv64;
 	restart->futex.bitset = bitset;
@@ -1856,8 +1861,6 @@
 
 	ret = -ERESTART_RESTARTBLOCK;
 
-out_put_key:
-	put_futex_key(fshared, &q.key);
 out:
 	if (to) {
 		hrtimer_cancel(&to->timer);
@@ -1869,7 +1872,7 @@
 
 static long futex_wait_restart(struct restart_block *restart)
 {
-	u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
+	u32 __user *uaddr = restart->futex.uaddr;
 	int fshared = 0;
 	ktime_t t, *tp = NULL;
 
@@ -2236,7 +2239,10 @@
 	q.rt_waiter = &rt_waiter;
 	q.requeue_pi_key = &key2;
 
-	/* Prepare to wait on uaddr. */
+	/*
+	 * Prepare to wait on uaddr. On success, increments q.key (key1) ref
+	 * count.
+	 */
 	ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
 	if (ret)
 		goto out_key2;
@@ -2254,7 +2260,9 @@
 	 * In order for us to be here, we know our q.key == key2, and since
 	 * we took the hb->lock above, we also know that futex_requeue() has
 	 * completed and we no longer have to concern ourselves with a wakeup
-	 * race with the atomic proxy lock acquition by the requeue code.
+	 * race with the atomic proxy lock acquisition by the requeue code. The
+	 * futex_requeue dropped our key1 reference and incremented our key2
+	 * reference count.
 	 */
 
 	/* Check if the requeue code acquired the second futex for us. */
@@ -2458,7 +2466,7 @@
  */
 static inline int fetch_robust_entry(struct robust_list __user **entry,
 				     struct robust_list __user * __user *head,
-				     int *pi)
+				     unsigned int *pi)
 {
 	unsigned long uentry;
 
@@ -2647,7 +2655,7 @@
 	 * of the complex code paths. Also we want to prevent
 	 * registration of robust lists in that case. NULL is
 	 * guaranteed to fault and we get -EFAULT on functional
-	 * implementation, the non functional ones will return
+	 * implementation, the non-functional ones will return
 	 * -ENOSYS.
 	 */
 	curval = cmpxchg_futex_value_locked(NULL, 0, 0);
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index d49afb2..06da4df 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -19,7 +19,7 @@
  */
 static inline int
 fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
-		   compat_uptr_t __user *head, int *pi)
+		   compat_uptr_t __user *head, unsigned int *pi)
 {
 	if (get_user(*uentry, head))
 		return -EFAULT;
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index f83972b..9bd0934 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -561,6 +561,7 @@
 static const struct file_operations gcov_reset_fops = {
 	.write	= reset_write,
 	.read	= reset_read,
+	.llseek = noop_llseek,
 };
 
 /*
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 0c642d5..53ead17 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -98,7 +98,7 @@
 	printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
 			" disables this message.\n");
 	sched_show_task(t);
-	__debug_show_held_locks(t);
+	debug_show_held_locks(t);
 
 	touch_nmi_watchdog();
 
@@ -111,7 +111,7 @@
  * periodically exit the critical section and enter a new one.
  *
  * For preemptible RCU it is sufficient to call rcu_read_unlock in order
- * exit the grace period. For classic RCU, a reschedule is required.
+ * to exit the grace period. For classic RCU, a reschedule is required.
  */
 static void rcu_lock_break(struct task_struct *g, struct task_struct *t)
 {
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index c7c2aed..2c9120f0 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -113,12 +113,12 @@
  */
 static int task_bp_pinned(struct perf_event *bp, enum bp_type_idx type)
 {
-	struct perf_event_context *ctx = bp->ctx;
+	struct task_struct *tsk = bp->hw.bp_target;
 	struct perf_event *iter;
 	int count = 0;
 
 	list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
-		if (iter->ctx == ctx && find_slot_idx(iter) == type)
+		if (iter->hw.bp_target == tsk && find_slot_idx(iter) == type)
 			count += hw_breakpoint_weight(iter);
 	}
 
@@ -134,7 +134,7 @@
 		    enum bp_type_idx type)
 {
 	int cpu = bp->cpu;
-	struct task_struct *tsk = bp->ctx->task;
+	struct task_struct *tsk = bp->hw.bp_target;
 
 	if (cpu >= 0) {
 		slots->pinned = per_cpu(nr_cpu_bp_pinned[type], cpu);
@@ -213,7 +213,7 @@
 	       int weight)
 {
 	int cpu = bp->cpu;
-	struct task_struct *tsk = bp->ctx->task;
+	struct task_struct *tsk = bp->hw.bp_target;
 
 	/* Pinned counter cpu profiling */
 	if (!tsk) {
@@ -433,8 +433,7 @@
 			    perf_overflow_handler_t triggered,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk),
-						triggered);
+	return perf_event_create_kernel_counter(attr, -1, tsk, triggered);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
@@ -516,7 +515,7 @@
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		pevent = per_cpu_ptr(cpu_events, cpu);
-		bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered);
+		bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered);
 
 		*pevent = bp;
 
@@ -566,6 +565,61 @@
 	.priority = 0x7fffffff
 };
 
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+	release_bp_slot(event);
+}
+
+static int hw_breakpoint_event_init(struct perf_event *bp)
+{
+	int err;
+
+	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
+		return -ENOENT;
+
+	err = register_perf_hw_breakpoint(bp);
+	if (err)
+		return err;
+
+	bp->destroy = bp_perf_event_destroy;
+
+	return 0;
+}
+
+static int hw_breakpoint_add(struct perf_event *bp, int flags)
+{
+	if (!(flags & PERF_EF_START))
+		bp->hw.state = PERF_HES_STOPPED;
+
+	return arch_install_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_del(struct perf_event *bp, int flags)
+{
+	arch_uninstall_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_start(struct perf_event *bp, int flags)
+{
+	bp->hw.state = 0;
+}
+
+static void hw_breakpoint_stop(struct perf_event *bp, int flags)
+{
+	bp->hw.state = PERF_HES_STOPPED;
+}
+
+static struct pmu perf_breakpoint = {
+	.task_ctx_nr	= perf_sw_context, /* could eventually get its own */
+
+	.event_init	= hw_breakpoint_event_init,
+	.add		= hw_breakpoint_add,
+	.del		= hw_breakpoint_del,
+	.start		= hw_breakpoint_start,
+	.stop		= hw_breakpoint_stop,
+	.read		= hw_breakpoint_pmu_read,
+};
+
 static int __init init_hw_breakpoint(void)
 {
 	unsigned int **task_bp_pinned;
@@ -587,6 +641,8 @@
 
 	constraints_initialized = 1;
 
+	perf_pmu_register(&perf_breakpoint);
+
 	return register_die_notifier(&hw_breakpoint_exceptions_nb);
 
  err_alloc:
@@ -602,8 +658,3 @@
 core_initcall(init_hw_breakpoint);
 
 
-struct pmu perf_ops_bp = {
-	.enable		= arch_install_hw_breakpoint,
-	.disable	= arch_uninstall_hw_breakpoint,
-	.read		= hw_breakpoint_pmu_read,
-};
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
new file mode 100644
index 0000000..31d766b
--- /dev/null
+++ b/kernel/irq/Kconfig
@@ -0,0 +1,53 @@
+config HAVE_GENERIC_HARDIRQS
+	def_bool n
+
+if HAVE_GENERIC_HARDIRQS
+menu "IRQ subsystem"
+#
+# Interrupt subsystem related configuration options
+#
+config GENERIC_HARDIRQS
+       def_bool y
+
+config GENERIC_HARDIRQS_NO__DO_IRQ
+       def_bool y
+
+# Select this to disable the deprecated stuff
+config GENERIC_HARDIRQS_NO_DEPRECATED
+       def_bool n
+
+# Options selectable by the architecture code
+config HAVE_SPARSE_IRQ
+       def_bool n
+
+config GENERIC_IRQ_PROBE
+	def_bool n
+
+config GENERIC_PENDING_IRQ
+	def_bool n
+
+config AUTO_IRQ_AFFINITY
+       def_bool n
+
+config IRQ_PER_CPU
+       def_bool n
+
+config HARDIRQS_SW_RESEND
+       def_bool n
+
+config SPARSE_IRQ
+	bool "Support sparse irq numbering"
+	depends on HAVE_SPARSE_IRQ
+	---help---
+
+	  Sparse irq numbering is useful for distro kernels that want
+	  to define a high CONFIG_NR_CPUS value but still want to have
+	  low kernel memory footprint on smaller machines.
+
+	  ( Sparse irqs can also be beneficial on NUMA boxes, as they spread
+	    out the interrupt descriptors in a more NUMA-friendly way. )
+
+	  If you don't know what to do here, say N.
+
+endmenu
+endif
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 7d04780..54329cd 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -1,7 +1,6 @@
 
-obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o
+obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
-obj-$(CONFIG_NUMA_IRQ_DESC) += numa_migrate.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 2295a31..505798f 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -57,9 +57,10 @@
 			 * Some chips need to know about probing in
 			 * progress:
 			 */
-			if (desc->chip->set_type)
-				desc->chip->set_type(i, IRQ_TYPE_PROBE);
-			desc->chip->startup(i);
+			if (desc->irq_data.chip->irq_set_type)
+				desc->irq_data.chip->irq_set_type(&desc->irq_data,
+							 IRQ_TYPE_PROBE);
+			desc->irq_data.chip->irq_startup(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -76,7 +77,7 @@
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
 			desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
-			if (desc->chip->startup(i))
+			if (desc->irq_data.chip->irq_startup(&desc->irq_data))
 				desc->status |= IRQ_PENDING;
 		}
 		raw_spin_unlock_irq(&desc->lock);
@@ -98,7 +99,7 @@
 			/* It triggered already - consider it spurious. */
 			if (!(status & IRQ_WAITING)) {
 				desc->status = status & ~IRQ_AUTODETECT;
-				desc->chip->shutdown(i);
+				desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 			} else
 				if (i < 32)
 					mask |= 1 << i;
@@ -137,7 +138,7 @@
 				mask |= 1 << i;
 
 			desc->status = status & ~IRQ_AUTODETECT;
-			desc->chip->shutdown(i);
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -181,7 +182,7 @@
 				nr_of_irqs++;
 			}
 			desc->status = status & ~IRQ_AUTODETECT;
-			desc->chip->shutdown(i);
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b7091d5..baa5c4a 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -18,108 +18,6 @@
 
 #include "internals.h"
 
-static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data)
-{
-	struct irq_desc *desc;
-	unsigned long flags;
-
-	desc = irq_to_desc(irq);
-	if (!desc) {
-		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
-		return;
-	}
-
-	/* Ensure we don't have left over values from a previous use of this irq */
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status = IRQ_DISABLED;
-	desc->chip = &no_irq_chip;
-	desc->handle_irq = handle_bad_irq;
-	desc->depth = 1;
-	desc->msi_desc = NULL;
-	desc->handler_data = NULL;
-	if (!keep_chip_data)
-		desc->chip_data = NULL;
-	desc->action = NULL;
-	desc->irq_count = 0;
-	desc->irqs_unhandled = 0;
-#ifdef CONFIG_SMP
-	cpumask_setall(desc->affinity);
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_clear(desc->pending_mask);
-#endif
-#endif
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-/**
- *	dynamic_irq_init - initialize a dynamically allocated irq
- *	@irq:	irq number to initialize
- */
-void dynamic_irq_init(unsigned int irq)
-{
-	dynamic_irq_init_x(irq, false);
-}
-
-/**
- *	dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq
- *	@irq:	irq number to initialize
- *
- *	does not set irq_to_desc(irq)->chip_data to NULL
- */
-void dynamic_irq_init_keep_chip_data(unsigned int irq)
-{
-	dynamic_irq_init_x(irq, true);
-}
-
-static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	if (!desc) {
-		WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
-		return;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	if (desc->action) {
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
-		WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n",
-			irq);
-		return;
-	}
-	desc->msi_desc = NULL;
-	desc->handler_data = NULL;
-	if (!keep_chip_data)
-		desc->chip_data = NULL;
-	desc->handle_irq = handle_bad_irq;
-	desc->chip = &no_irq_chip;
-	desc->name = NULL;
-	clear_kstat_irqs(desc);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-/**
- *	dynamic_irq_cleanup - cleanup a dynamically allocated irq
- *	@irq:	irq number to initialize
- */
-void dynamic_irq_cleanup(unsigned int irq)
-{
-	dynamic_irq_cleanup_x(irq, false);
-}
-
-/**
- *	dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq
- *	@irq:	irq number to initialize
- *
- *	does not set irq_to_desc(irq)->chip_data to NULL
- */
-void dynamic_irq_cleanup_keep_chip_data(unsigned int irq)
-{
-	dynamic_irq_cleanup_x(irq, true);
-}
-
-
 /**
  *	set_irq_chip - set the irq chip for an irq
  *	@irq:	irq number
@@ -140,7 +38,7 @@
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
-	desc->chip = chip;
+	desc->irq_data.chip = chip;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	return 0;
@@ -193,7 +91,7 @@
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->handler_data = data;
+	desc->irq_data.handler_data = data;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
 }
@@ -218,7 +116,7 @@
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->msi_desc = entry;
+	desc->irq_data.msi_desc = entry;
 	if (entry)
 		entry->irq = irq;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -243,19 +141,27 @@
 		return -EINVAL;
 	}
 
-	if (!desc->chip) {
+	if (!desc->irq_data.chip) {
 		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
 		return -EINVAL;
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->chip_data = data;
+	desc->irq_data.chip_data = data;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	return 0;
 }
 EXPORT_SYMBOL(set_irq_chip_data);
 
+struct irq_data *irq_get_irq_data(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	return desc ? &desc->irq_data : NULL;
+}
+EXPORT_SYMBOL_GPL(irq_get_irq_data);
+
 /**
  *	set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq
  *
@@ -287,93 +193,216 @@
 /*
  * default enable function
  */
-static void default_enable(unsigned int irq)
+static void default_enable(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->unmask(irq);
+	desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	desc->status &= ~IRQ_MASKED;
 }
 
 /*
  * default disable function
  */
-static void default_disable(unsigned int irq)
+static void default_disable(struct irq_data *data)
 {
 }
 
 /*
  * default startup function
  */
-static unsigned int default_startup(unsigned int irq)
+static unsigned int default_startup(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->enable(irq);
+	desc->irq_data.chip->irq_enable(data);
 	return 0;
 }
 
 /*
  * default shutdown function
  */
-static void default_shutdown(unsigned int irq)
+static void default_shutdown(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->mask(irq);
+	desc->irq_data.chip->irq_mask(&desc->irq_data);
 	desc->status |= IRQ_MASKED;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+/* Temporary migration helpers */
+static void compat_irq_mask(struct irq_data *data)
+{
+	data->chip->mask(data->irq);
+}
+
+static void compat_irq_unmask(struct irq_data *data)
+{
+	data->chip->unmask(data->irq);
+}
+
+static void compat_irq_ack(struct irq_data *data)
+{
+	data->chip->ack(data->irq);
+}
+
+static void compat_irq_mask_ack(struct irq_data *data)
+{
+	data->chip->mask_ack(data->irq);
+}
+
+static void compat_irq_eoi(struct irq_data *data)
+{
+	data->chip->eoi(data->irq);
+}
+
+static void compat_irq_enable(struct irq_data *data)
+{
+	data->chip->enable(data->irq);
+}
+
+static void compat_irq_disable(struct irq_data *data)
+{
+	data->chip->disable(data->irq);
+}
+
+static void compat_irq_shutdown(struct irq_data *data)
+{
+	data->chip->shutdown(data->irq);
+}
+
+static unsigned int compat_irq_startup(struct irq_data *data)
+{
+	return data->chip->startup(data->irq);
+}
+
+static int compat_irq_set_affinity(struct irq_data *data,
+				   const struct cpumask *dest, bool force)
+{
+	return data->chip->set_affinity(data->irq, dest);
+}
+
+static int compat_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	return data->chip->set_type(data->irq, type);
+}
+
+static int compat_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	return data->chip->set_wake(data->irq, on);
+}
+
+static int compat_irq_retrigger(struct irq_data *data)
+{
+	return data->chip->retrigger(data->irq);
+}
+
+static void compat_bus_lock(struct irq_data *data)
+{
+	data->chip->bus_lock(data->irq);
+}
+
+static void compat_bus_sync_unlock(struct irq_data *data)
+{
+	data->chip->bus_sync_unlock(data->irq);
+}
+#endif
+
 /*
  * Fixup enable/disable function pointers
  */
 void irq_chip_set_defaults(struct irq_chip *chip)
 {
-	if (!chip->enable)
-		chip->enable = default_enable;
-	if (!chip->disable)
-		chip->disable = default_disable;
-	if (!chip->startup)
-		chip->startup = default_startup;
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	/*
-	 * We use chip->disable, when the user provided its own. When
-	 * we have default_disable set for chip->disable, then we need
+	 * Compat fixup functions need to be before we set the
+	 * defaults for enable/disable/startup/shutdown
+	 */
+	if (chip->enable)
+		chip->irq_enable = compat_irq_enable;
+	if (chip->disable)
+		chip->irq_disable = compat_irq_disable;
+	if (chip->shutdown)
+		chip->irq_shutdown = compat_irq_shutdown;
+	if (chip->startup)
+		chip->irq_startup = compat_irq_startup;
+#endif
+	/*
+	 * The real defaults
+	 */
+	if (!chip->irq_enable)
+		chip->irq_enable = default_enable;
+	if (!chip->irq_disable)
+		chip->irq_disable = default_disable;
+	if (!chip->irq_startup)
+		chip->irq_startup = default_startup;
+	/*
+	 * We use chip->irq_disable, when the user provided its own. When
+	 * we have default_disable set for chip->irq_disable, then we need
 	 * to use default_shutdown, otherwise the irq line is not
 	 * disabled on free_irq():
 	 */
-	if (!chip->shutdown)
-		chip->shutdown = chip->disable != default_disable ?
-			chip->disable : default_shutdown;
-	if (!chip->name)
-		chip->name = chip->typename;
+	if (!chip->irq_shutdown)
+		chip->irq_shutdown = chip->irq_disable != default_disable ?
+			chip->irq_disable : default_shutdown;
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	if (!chip->end)
 		chip->end = dummy_irq_chip.end;
+
+	/*
+	 * Now fix up the remaining compat handlers
+	 */
+	if (chip->bus_lock)
+		chip->irq_bus_lock = compat_bus_lock;
+	if (chip->bus_sync_unlock)
+		chip->irq_bus_sync_unlock = compat_bus_sync_unlock;
+	if (chip->mask)
+		chip->irq_mask = compat_irq_mask;
+	if (chip->unmask)
+		chip->irq_unmask = compat_irq_unmask;
+	if (chip->ack)
+		chip->irq_ack = compat_irq_ack;
+	if (chip->mask_ack)
+		chip->irq_mask_ack = compat_irq_mask_ack;
+	if (chip->eoi)
+		chip->irq_eoi = compat_irq_eoi;
+	if (chip->set_affinity)
+		chip->irq_set_affinity = compat_irq_set_affinity;
+	if (chip->set_type)
+		chip->irq_set_type = compat_irq_set_type;
+	if (chip->set_wake)
+		chip->irq_set_wake = compat_irq_set_wake;
+	if (chip->retrigger)
+		chip->irq_retrigger = compat_irq_retrigger;
+#endif
 }
 
-static inline void mask_ack_irq(struct irq_desc *desc, int irq)
+static inline void mask_ack_irq(struct irq_desc *desc)
 {
-	if (desc->chip->mask_ack)
-		desc->chip->mask_ack(irq);
+	if (desc->irq_data.chip->irq_mask_ack)
+		desc->irq_data.chip->irq_mask_ack(&desc->irq_data);
 	else {
-		desc->chip->mask(irq);
-		if (desc->chip->ack)
-			desc->chip->ack(irq);
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
+		if (desc->irq_data.chip->irq_ack)
+			desc->irq_data.chip->irq_ack(&desc->irq_data);
 	}
 	desc->status |= IRQ_MASKED;
 }
 
-static inline void mask_irq(struct irq_desc *desc, int irq)
+static inline void mask_irq(struct irq_desc *desc)
 {
-	if (desc->chip->mask) {
-		desc->chip->mask(irq);
+	if (desc->irq_data.chip->irq_mask) {
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
 		desc->status |= IRQ_MASKED;
 	}
 }
 
-static inline void unmask_irq(struct irq_desc *desc, int irq)
+static inline void unmask_irq(struct irq_desc *desc)
 {
-	if (desc->chip->unmask) {
-		desc->chip->unmask(irq);
+	if (desc->irq_data.chip->irq_unmask) {
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 		desc->status &= ~IRQ_MASKED;
 	}
 }
@@ -476,7 +505,7 @@
 	irqreturn_t action_ret;
 
 	raw_spin_lock(&desc->lock);
-	mask_ack_irq(desc, irq);
+	mask_ack_irq(desc);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
@@ -502,7 +531,7 @@
 	desc->status &= ~IRQ_INPROGRESS;
 
 	if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
-		unmask_irq(desc, irq);
+		unmask_irq(desc);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -539,7 +568,7 @@
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
 		desc->status |= IRQ_PENDING;
-		mask_irq(desc, irq);
+		mask_irq(desc);
 		goto out;
 	}
 
@@ -554,7 +583,7 @@
 	raw_spin_lock(&desc->lock);
 	desc->status &= ~IRQ_INPROGRESS;
 out:
-	desc->chip->eoi(irq);
+	desc->irq_data.chip->irq_eoi(&desc->irq_data);
 
 	raw_spin_unlock(&desc->lock);
 }
@@ -590,14 +619,13 @@
 	if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
 		    !desc->action)) {
 		desc->status |= (IRQ_PENDING | IRQ_MASKED);
-		mask_ack_irq(desc, irq);
+		mask_ack_irq(desc);
 		goto out_unlock;
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
 	/* Mark the IRQ currently in progress.*/
 	desc->status |= IRQ_INPROGRESS;
@@ -607,7 +635,7 @@
 		irqreturn_t action_ret;
 
 		if (unlikely(!action)) {
-			mask_irq(desc, irq);
+			mask_irq(desc);
 			goto out_unlock;
 		}
 
@@ -619,7 +647,7 @@
 		if (unlikely((desc->status &
 			       (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
 			      (IRQ_PENDING | IRQ_MASKED))) {
-			unmask_irq(desc, irq);
+			unmask_irq(desc);
 		}
 
 		desc->status &= ~IRQ_PENDING;
@@ -650,15 +678,15 @@
 
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	if (desc->irq_data.chip->irq_ack)
+		desc->irq_data.chip->irq_ack(&desc->irq_data);
 
 	action_ret = handle_IRQ_event(irq, desc->action);
 	if (!noirqdebug)
 		note_interrupt(irq, desc, action_ret);
 
-	if (desc->chip->eoi)
-		desc->chip->eoi(irq);
+	if (desc->irq_data.chip->irq_eoi)
+		desc->irq_data.chip->irq_eoi(&desc->irq_data);
 }
 
 void
@@ -676,7 +704,7 @@
 
 	if (!handle)
 		handle = handle_bad_irq;
-	else if (desc->chip == &no_irq_chip) {
+	else if (desc->irq_data.chip == &no_irq_chip) {
 		printk(KERN_WARNING "Trying to install %sinterrupt handler "
 		       "for IRQ%d\n", is_chained ? "chained " : "", irq);
 		/*
@@ -686,16 +714,16 @@
 		 * prevent us to setup the interrupt at all. Switch it to
 		 * dummy_irq_chip for easy transition.
 		 */
-		desc->chip = &dummy_irq_chip;
+		desc->irq_data.chip = &dummy_irq_chip;
 	}
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
 	/* Uninstall? */
 	if (handle == handle_bad_irq) {
-		if (desc->chip != &no_irq_chip)
-			mask_ack_irq(desc, irq);
+		if (desc->irq_data.chip != &no_irq_chip)
+			mask_ack_irq(desc);
 		desc->status |= IRQ_DISABLED;
 		desc->depth = 1;
 	}
@@ -706,10 +734,10 @@
 		desc->status &= ~IRQ_DISABLED;
 		desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
 		desc->depth = 0;
-		desc->chip->startup(irq);
+		desc->irq_data.chip->irq_startup(&desc->irq_data);
 	}
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL_GPL(__set_irq_handler);
 
@@ -729,32 +757,20 @@
 	__set_irq_handler(irq, handle, 0, name);
 }
 
-void set_irq_noprobe(unsigned int irq)
+void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 
-	if (!desc) {
-		printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
+	if (!desc)
 		return;
-	}
+
+	/* Sanitize flags */
+	set &= IRQF_MODIFY_MASK;
+	clr &= IRQF_MODIFY_MASK;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status |= IRQ_NOPROBE;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-void set_irq_probe(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	if (!desc) {
-		printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq);
-		return;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status &= ~IRQ_NOPROBE;
+	desc->status &= ~clr;
+	desc->status |= set;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c
new file mode 100644
index 0000000..20dc547
--- /dev/null
+++ b/kernel/irq/dummychip.c
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
+ * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
+ *
+ * This file contains the dummy interrupt chip implementation
+ */
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+
+#include "internals.h"
+
+/*
+ * What should we do if we get a hw irq event on an illegal vector?
+ * Each architecture has to answer this themself.
+ */
+static void ack_bad(struct irq_data *data)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	print_irq_desc(data->irq, desc);
+	ack_bad_irq(data->irq);
+}
+
+/*
+ * NOP functions
+ */
+static void noop(struct irq_data *data) { }
+
+static unsigned int noop_ret(struct irq_data *data)
+{
+	return 0;
+}
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+static void compat_noop(unsigned int irq) { }
+#define END_INIT .end = compat_noop
+#else
+#define END_INIT
+#endif
+
+/*
+ * Generic no controller implementation
+ */
+struct irq_chip no_irq_chip = {
+	.name		= "none",
+	.irq_startup	= noop_ret,
+	.irq_shutdown	= noop,
+	.irq_enable	= noop,
+	.irq_disable	= noop,
+	.irq_ack	= ack_bad,
+	END_INIT
+};
+
+/*
+ * Generic dummy implementation which can be used for
+ * real dumb interrupt sources
+ */
+struct irq_chip dummy_irq_chip = {
+	.name		= "dummy",
+	.irq_startup	= noop_ret,
+	.irq_shutdown	= noop,
+	.irq_enable	= noop,
+	.irq_disable	= noop,
+	.irq_ack	= noop,
+	.irq_mask	= noop,
+	.irq_unmask	= noop,
+	END_INIT
+};
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 27e5c69..e2347eb 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -11,24 +11,15 @@
  */
 
 #include <linux/irq.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/module.h>
 #include <linux/random.h>
+#include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
-#include <linux/rculist.h>
-#include <linux/hash.h>
-#include <linux/radix-tree.h>
+
 #include <trace/events/irq.h>
 
 #include "internals.h"
 
-/*
- * lockdep: we want to handle all irq_desc locks as a single lock-class:
- */
-struct lock_class_key irq_desc_lock_class;
-
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
  * @irq:       the interrupt number
@@ -43,304 +34,6 @@
 	ack_bad_irq(irq);
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
-static void __init init_irq_default_affinity(void)
-{
-	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
-	cpumask_setall(irq_default_affinity);
-}
-#else
-static void __init init_irq_default_affinity(void)
-{
-}
-#endif
-
-/*
- * Linux has a controller-independent interrupt architecture.
- * Every controller has a 'controller-template', that is used
- * by the main code to do the right thing. Each driver-visible
- * interrupt source is transparently wired to the appropriate
- * controller. Thus drivers need not be aware of the
- * interrupt-controller.
- *
- * The code is designed to be easily extended with new/different
- * interrupt controllers, without having to do assembly magic or
- * having to touch the generic code.
- *
- * Controller mappings for all interrupt sources:
- */
-int nr_irqs = NR_IRQS;
-EXPORT_SYMBOL_GPL(nr_irqs);
-
-#ifdef CONFIG_SPARSE_IRQ
-
-static struct irq_desc irq_desc_init = {
-	.irq	    = -1,
-	.status	    = IRQ_DISABLED,
-	.chip	    = &no_irq_chip,
-	.handle_irq = handle_bad_irq,
-	.depth      = 1,
-	.lock       = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-};
-
-void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
-{
-	void *ptr;
-
-	ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
-			   GFP_ATOMIC, node);
-
-	/*
-	 * don't overwite if can not get new one
-	 * init_copy_kstat_irqs() could still use old one
-	 */
-	if (ptr) {
-		printk(KERN_DEBUG "  alloc kstat_irqs on node %d\n", node);
-		desc->kstat_irqs = ptr;
-	}
-}
-
-static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
-{
-	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
-
-	raw_spin_lock_init(&desc->lock);
-	desc->irq = irq;
-#ifdef CONFIG_SMP
-	desc->node = node;
-#endif
-	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	init_kstat_irqs(desc, node, nr_cpu_ids);
-	if (!desc->kstat_irqs) {
-		printk(KERN_ERR "can not alloc kstat_irqs\n");
-		BUG_ON(1);
-	}
-	if (!alloc_desc_masks(desc, node, false)) {
-		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
-		BUG_ON(1);
-	}
-	init_desc_masks(desc);
-	arch_init_chip_data(desc, node);
-}
-
-/*
- * Protect the sparse_irqs:
- */
-DEFINE_RAW_SPINLOCK(sparse_irq_lock);
-
-static RADIX_TREE(irq_desc_tree, GFP_ATOMIC);
-
-static void set_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-	radix_tree_insert(&irq_desc_tree, irq, desc);
-}
-
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-	return radix_tree_lookup(&irq_desc_tree, irq);
-}
-
-void replace_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-	void **ptr;
-
-	ptr = radix_tree_lookup_slot(&irq_desc_tree, irq);
-	if (ptr)
-		radix_tree_replace_slot(ptr, desc);
-}
-
-static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
-	[0 ... NR_IRQS_LEGACY-1] = {
-		.irq	    = -1,
-		.status	    = IRQ_DISABLED,
-		.chip	    = &no_irq_chip,
-		.handle_irq = handle_bad_irq,
-		.depth	    = 1,
-		.lock	    = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-	}
-};
-
-static unsigned int *kstat_irqs_legacy;
-
-int __init early_irq_init(void)
-{
-	struct irq_desc *desc;
-	int legacy_count;
-	int node;
-	int i;
-
-	init_irq_default_affinity();
-
-	 /* initialize nr_irqs based on nr_cpu_ids */
-	arch_probe_nr_irqs();
-	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
-
-	desc = irq_desc_legacy;
-	legacy_count = ARRAY_SIZE(irq_desc_legacy);
-	node = first_online_node;
-
-	/* allocate based on nr_cpu_ids */
-	kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
-					  sizeof(int), GFP_NOWAIT, node);
-
-	for (i = 0; i < legacy_count; i++) {
-		desc[i].irq = i;
-#ifdef CONFIG_SMP
-		desc[i].node = node;
-#endif
-		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
-		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		alloc_desc_masks(&desc[i], node, true);
-		init_desc_masks(&desc[i]);
-		set_irq_desc(i, &desc[i]);
-	}
-
-	return arch_early_irq_init();
-}
-
-struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
-{
-	struct irq_desc *desc;
-	unsigned long flags;
-
-	if (irq >= nr_irqs) {
-		WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
-			irq, nr_irqs);
-		return NULL;
-	}
-
-	desc = irq_to_desc(irq);
-	if (desc)
-		return desc;
-
-	raw_spin_lock_irqsave(&sparse_irq_lock, flags);
-
-	/* We have to check it to avoid races with another CPU */
-	desc = irq_to_desc(irq);
-	if (desc)
-		goto out_unlock;
-
-	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-
-	printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
-	if (!desc) {
-		printk(KERN_ERR "can not alloc irq_desc\n");
-		BUG_ON(1);
-	}
-	init_one_irq_desc(irq, desc, node);
-
-	set_irq_desc(irq, desc);
-
-out_unlock:
-	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-	return desc;
-}
-
-#else /* !CONFIG_SPARSE_IRQ */
-
-struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
-	[0 ... NR_IRQS-1] = {
-		.status = IRQ_DISABLED,
-		.chip = &no_irq_chip,
-		.handle_irq = handle_bad_irq,
-		.depth = 1,
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
-	}
-};
-
-static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
-int __init early_irq_init(void)
-{
-	struct irq_desc *desc;
-	int count;
-	int i;
-
-	init_irq_default_affinity();
-
-	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
-
-	desc = irq_desc;
-	count = ARRAY_SIZE(irq_desc);
-
-	for (i = 0; i < count; i++) {
-		desc[i].irq = i;
-		alloc_desc_masks(&desc[i], 0, true);
-		init_desc_masks(&desc[i]);
-		desc[i].kstat_irqs = kstat_irqs_all[i];
-	}
-	return arch_early_irq_init();
-}
-
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
-}
-
-struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
-{
-	return irq_to_desc(irq);
-}
-#endif /* !CONFIG_SPARSE_IRQ */
-
-void clear_kstat_irqs(struct irq_desc *desc)
-{
-	memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
-}
-
-/*
- * What should we do if we get a hw irq event on an illegal vector?
- * Each architecture has to answer this themself.
- */
-static void ack_bad(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	print_irq_desc(irq, desc);
-	ack_bad_irq(irq);
-}
-
-/*
- * NOP functions
- */
-static void noop(unsigned int irq)
-{
-}
-
-static unsigned int noop_ret(unsigned int irq)
-{
-	return 0;
-}
-
-/*
- * Generic no controller implementation
- */
-struct irq_chip no_irq_chip = {
-	.name		= "none",
-	.startup	= noop_ret,
-	.shutdown	= noop,
-	.enable		= noop,
-	.disable	= noop,
-	.ack		= ack_bad,
-	.end		= noop,
-};
-
-/*
- * Generic dummy implementation which can be used for
- * real dumb interrupt sources
- */
-struct irq_chip dummy_irq_chip = {
-	.name		= "dummy",
-	.startup	= noop_ret,
-	.shutdown	= noop,
-	.enable		= noop,
-	.disable	= noop,
-	.ack		= noop,
-	.mask		= noop,
-	.unmask		= noop,
-	.end		= noop,
-};
-
 /*
  * Special, empty irq handler:
  */
@@ -457,20 +150,20 @@
 		/*
 		 * No locking required for CPU-local interrupts:
 		 */
-		if (desc->chip->ack)
-			desc->chip->ack(irq);
+		if (desc->irq_data.chip->ack)
+			desc->irq_data.chip->ack(irq);
 		if (likely(!(desc->status & IRQ_DISABLED))) {
 			action_ret = handle_IRQ_event(irq, desc->action);
 			if (!noirqdebug)
 				note_interrupt(irq, desc, action_ret);
 		}
-		desc->chip->end(irq);
+		desc->irq_data.chip->end(irq);
 		return 1;
 	}
 
 	raw_spin_lock(&desc->lock);
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	if (desc->irq_data.chip->ack)
+		desc->irq_data.chip->ack(irq);
 	/*
 	 * REPLAY is when Linux resends an IRQ that was dropped earlier
 	 * WAITING is used by probe to mark irqs that are being tested
@@ -530,27 +223,9 @@
 	 * The ->end() handler has to deal with interrupts which got
 	 * disabled while the handler was running.
 	 */
-	desc->chip->end(irq);
+	desc->irq_data.chip->end(irq);
 	raw_spin_unlock(&desc->lock);
 
 	return 1;
 }
 #endif
-
-void early_init_irq_lock_class(void)
-{
-	struct irq_desc *desc;
-	int i;
-
-	for_each_irq_desc(i, desc) {
-		lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	}
-}
-
-unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	return desc ? desc->kstat_irqs[cpu] : 0;
-}
-EXPORT_SYMBOL(kstat_irqs_cpu);
-
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index c63f3bc..4571ae7 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -1,9 +1,12 @@
 /*
  * IRQ subsystem internal functions and variables:
  */
+#include <linux/irqdesc.h>
 
 extern int noirqdebug;
 
+#define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
+
 /* Set default functions for irq_chip structures: */
 extern void irq_chip_set_defaults(struct irq_chip *chip);
 
@@ -15,21 +18,19 @@
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
-extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
-extern void clear_kstat_irqs(struct irq_desc *desc);
-extern raw_spinlock_t sparse_irq_lock;
 
-#ifdef CONFIG_SPARSE_IRQ
-void replace_irq_desc(unsigned int irq, struct irq_desc *desc);
-#endif
+/* Resending of interrupts :*/
+void check_irq_resend(struct irq_desc *desc, unsigned int irq);
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
+extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void register_handler_proc(unsigned int irq, struct irqaction *action);
 extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
 #else
 static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { }
+static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { }
 static inline void register_handler_proc(unsigned int irq,
 					 struct irqaction *action) { }
 static inline void unregister_handler_proc(unsigned int irq,
@@ -40,17 +41,27 @@
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
-/* Inline functions for support of irq chips on slow busses */
-static inline void chip_bus_lock(unsigned int irq, struct irq_desc *desc)
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+static inline void irq_end(unsigned int irq, struct irq_desc *desc)
 {
-	if (unlikely(desc->chip->bus_lock))
-		desc->chip->bus_lock(irq);
+	if (desc->irq_data.chip && desc->irq_data.chip->end)
+		desc->irq_data.chip->end(irq);
+}
+#else
+static inline void irq_end(unsigned int irq, struct irq_desc *desc) { }
+#endif
+
+/* Inline functions for support of irq chips on slow busses */
+static inline void chip_bus_lock(struct irq_desc *desc)
+{
+	if (unlikely(desc->irq_data.chip->irq_bus_lock))
+		desc->irq_data.chip->irq_bus_lock(&desc->irq_data);
 }
 
-static inline void chip_bus_sync_unlock(unsigned int irq, struct irq_desc *desc)
+static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 {
-	if (unlikely(desc->chip->bus_sync_unlock))
-		desc->chip->bus_sync_unlock(irq);
+	if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock))
+		desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
 /*
@@ -67,8 +78,8 @@
 		irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
 	printk("->handle_irq():  %p, ", desc->handle_irq);
 	print_symbol("%s\n", (unsigned long)desc->handle_irq);
-	printk("->chip(): %p, ", desc->chip);
-	print_symbol("%s\n", (unsigned long)desc->chip);
+	printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
+	print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
 	printk("->action(): %p\n", desc->action);
 	if (desc->action) {
 		printk("->action->handler(): %p, ", desc->action->handler);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
new file mode 100644
index 0000000..9d917ff
--- /dev/null
+++ b/kernel/irq/irqdesc.c
@@ -0,0 +1,395 @@
+/*
+ * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
+ * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
+ *
+ * This file contains the interrupt descriptor management code
+ *
+ * Detailed information is available in Documentation/DocBook/genericirq
+ *
+ */
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/radix-tree.h>
+#include <linux/bitmap.h>
+
+#include "internals.h"
+
+/*
+ * lockdep: we want to handle all irq_desc locks as a single lock-class:
+ */
+static struct lock_class_key irq_desc_lock_class;
+
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
+static void __init init_irq_default_affinity(void)
+{
+	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+	cpumask_setall(irq_default_affinity);
+}
+#else
+static void __init init_irq_default_affinity(void)
+{
+}
+#endif
+
+#ifdef CONFIG_SMP
+static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
+{
+	if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node))
+		return -ENOMEM;
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
+		free_cpumask_var(desc->irq_data.affinity);
+		return -ENOMEM;
+	}
+#endif
+	return 0;
+}
+
+static void desc_smp_init(struct irq_desc *desc, int node)
+{
+	desc->irq_data.node = node;
+	cpumask_copy(desc->irq_data.affinity, irq_default_affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_clear(desc->pending_mask);
+#endif
+}
+
+static inline int desc_node(struct irq_desc *desc)
+{
+	return desc->irq_data.node;
+}
+
+#else
+static inline int
+alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
+static inline void desc_smp_init(struct irq_desc *desc, int node) { }
+static inline int desc_node(struct irq_desc *desc) { return 0; }
+#endif
+
+static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
+{
+	desc->irq_data.irq = irq;
+	desc->irq_data.chip = &no_irq_chip;
+	desc->irq_data.chip_data = NULL;
+	desc->irq_data.handler_data = NULL;
+	desc->irq_data.msi_desc = NULL;
+	desc->status = IRQ_DEFAULT_INIT_FLAGS;
+	desc->handle_irq = handle_bad_irq;
+	desc->depth = 1;
+	desc->irq_count = 0;
+	desc->irqs_unhandled = 0;
+	desc->name = NULL;
+	memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
+	desc_smp_init(desc, node);
+}
+
+int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL_GPL(nr_irqs);
+
+static DEFINE_MUTEX(sparse_irq_lock);
+static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+
+#ifdef CONFIG_SPARSE_IRQ
+
+static RADIX_TREE(irq_desc_tree, GFP_KERNEL);
+
+static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
+{
+	radix_tree_insert(&irq_desc_tree, irq, desc);
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	return radix_tree_lookup(&irq_desc_tree, irq);
+}
+
+static void delete_irq_desc(unsigned int irq)
+{
+	radix_tree_delete(&irq_desc_tree, irq);
+}
+
+#ifdef CONFIG_SMP
+static void free_masks(struct irq_desc *desc)
+{
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	free_cpumask_var(desc->pending_mask);
+#endif
+	free_cpumask_var(desc->irq_data.affinity);
+}
+#else
+static inline void free_masks(struct irq_desc *desc) { }
+#endif
+
+static struct irq_desc *alloc_desc(int irq, int node)
+{
+	struct irq_desc *desc;
+	gfp_t gfp = GFP_KERNEL;
+
+	desc = kzalloc_node(sizeof(*desc), gfp, node);
+	if (!desc)
+		return NULL;
+	/* allocate based on nr_cpu_ids */
+	desc->kstat_irqs = kzalloc_node(nr_cpu_ids * sizeof(*desc->kstat_irqs),
+					 gfp, node);
+	if (!desc->kstat_irqs)
+		goto err_desc;
+
+	if (alloc_masks(desc, gfp, node))
+		goto err_kstat;
+
+	raw_spin_lock_init(&desc->lock);
+	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+
+	desc_set_defaults(irq, desc, node);
+
+	return desc;
+
+err_kstat:
+	kfree(desc->kstat_irqs);
+err_desc:
+	kfree(desc);
+	return NULL;
+}
+
+static void free_desc(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	unregister_irq_proc(irq, desc);
+
+	mutex_lock(&sparse_irq_lock);
+	delete_irq_desc(irq);
+	mutex_unlock(&sparse_irq_lock);
+
+	free_masks(desc);
+	kfree(desc->kstat_irqs);
+	kfree(desc);
+}
+
+static int alloc_descs(unsigned int start, unsigned int cnt, int node)
+{
+	struct irq_desc *desc;
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		desc = alloc_desc(start + i, node);
+		if (!desc)
+			goto err;
+		mutex_lock(&sparse_irq_lock);
+		irq_insert_desc(start + i, desc);
+		mutex_unlock(&sparse_irq_lock);
+	}
+	return start;
+
+err:
+	for (i--; i >= 0; i--)
+		free_desc(start + i);
+
+	mutex_lock(&sparse_irq_lock);
+	bitmap_clear(allocated_irqs, start, cnt);
+	mutex_unlock(&sparse_irq_lock);
+	return -ENOMEM;
+}
+
+struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
+{
+	int res = irq_alloc_descs(irq, irq, 1, node);
+
+	if (res == -EEXIST || res == irq)
+		return irq_to_desc(irq);
+	return NULL;
+}
+
+int __init early_irq_init(void)
+{
+	int i, initcnt, node = first_online_node;
+	struct irq_desc *desc;
+
+	init_irq_default_affinity();
+
+	/* Let arch update nr_irqs and return the nr of preallocated irqs */
+	initcnt = arch_probe_nr_irqs();
+	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
+
+	for (i = 0; i < initcnt; i++) {
+		desc = alloc_desc(i, node);
+		set_bit(i, allocated_irqs);
+		irq_insert_desc(i, desc);
+	}
+	return arch_early_irq_init();
+}
+
+#else /* !CONFIG_SPARSE_IRQ */
+
+struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
+	[0 ... NR_IRQS-1] = {
+		.status		= IRQ_DEFAULT_INIT_FLAGS,
+		.handle_irq	= handle_bad_irq,
+		.depth		= 1,
+		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
+	}
+};
+
+static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
+int __init early_irq_init(void)
+{
+	int count, i, node = first_online_node;
+	struct irq_desc *desc;
+
+	init_irq_default_affinity();
+
+	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+
+	desc = irq_desc;
+	count = ARRAY_SIZE(irq_desc);
+
+	for (i = 0; i < count; i++) {
+		desc[i].irq_data.irq = i;
+		desc[i].irq_data.chip = &no_irq_chip;
+		desc[i].kstat_irqs = kstat_irqs_all[i];
+		alloc_masks(desc + i, GFP_KERNEL, node);
+		desc_smp_init(desc + i, node);
+		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+	}
+	return arch_early_irq_init();
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
+}
+
+struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
+{
+	return irq_to_desc(irq);
+}
+
+static void free_desc(unsigned int irq)
+{
+	dynamic_irq_cleanup(irq);
+}
+
+static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
+{
+	return start;
+}
+#endif /* !CONFIG_SPARSE_IRQ */
+
+/* Dynamic interrupt handling */
+
+/**
+ * irq_free_descs - free irq descriptors
+ * @from:	Start of descriptor range
+ * @cnt:	Number of consecutive irqs to free
+ */
+void irq_free_descs(unsigned int from, unsigned int cnt)
+{
+	int i;
+
+	if (from >= nr_irqs || (from + cnt) > nr_irqs)
+		return;
+
+	for (i = 0; i < cnt; i++)
+		free_desc(from + i);
+
+	mutex_lock(&sparse_irq_lock);
+	bitmap_clear(allocated_irqs, from, cnt);
+	mutex_unlock(&sparse_irq_lock);
+}
+
+/**
+ * irq_alloc_descs - allocate and initialize a range of irq descriptors
+ * @irq:	Allocate for specific irq number if irq >= 0
+ * @from:	Start the search from this irq number
+ * @cnt:	Number of consecutive irqs to allocate.
+ * @node:	Preferred node on which the irq descriptor should be allocated
+ *
+ * Returns the first irq number or error code
+ */
+int __ref
+irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
+{
+	int start, ret;
+
+	if (!cnt)
+		return -EINVAL;
+
+	mutex_lock(&sparse_irq_lock);
+
+	start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+	ret = -EEXIST;
+	if (irq >=0 && start != irq)
+		goto err;
+
+	ret = -ENOMEM;
+	if (start >= nr_irqs)
+		goto err;
+
+	bitmap_set(allocated_irqs, start, cnt);
+	mutex_unlock(&sparse_irq_lock);
+	return alloc_descs(start, cnt, node);
+
+err:
+	mutex_unlock(&sparse_irq_lock);
+	return ret;
+}
+
+/**
+ * irq_reserve_irqs - mark irqs allocated
+ * @from:	mark from irq number
+ * @cnt:	number of irqs to mark
+ *
+ * Returns 0 on success or an appropriate error code
+ */
+int irq_reserve_irqs(unsigned int from, unsigned int cnt)
+{
+	unsigned int start;
+	int ret = 0;
+
+	if (!cnt || (from + cnt) > nr_irqs)
+		return -EINVAL;
+
+	mutex_lock(&sparse_irq_lock);
+	start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+	if (start == from)
+		bitmap_set(allocated_irqs, start, cnt);
+	else
+		ret = -EEXIST;
+	mutex_unlock(&sparse_irq_lock);
+	return ret;
+}
+
+/**
+ * irq_get_next_irq - get next allocated irq number
+ * @offset:	where to start the search
+ *
+ * Returns next irq number after offset or nr_irqs if none is found.
+ */
+unsigned int irq_get_next_irq(unsigned int offset)
+{
+	return find_next_bit(allocated_irqs, nr_irqs, offset);
+}
+
+/**
+ * dynamic_irq_cleanup - cleanup a dynamically allocated irq
+ * @irq:	irq number to initialize
+ */
+void dynamic_irq_cleanup(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	desc_set_defaults(irq, desc, desc_node(desc));
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	return desc ? desc->kstat_irqs[cpu] : 0;
+}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c3003e9..644e8d5 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -73,8 +73,8 @@
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
-	    !desc->chip->set_affinity)
+	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->irq_data.chip ||
+	    !desc->irq_data.chip->irq_set_affinity)
 		return 0;
 
 	return 1;
@@ -109,17 +109,18 @@
 int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_chip *chip = desc->irq_data.chip;
 	unsigned long flags;
 
-	if (!desc->chip->set_affinity)
+	if (!chip->irq_set_affinity)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PCNTXT) {
-		if (!desc->chip->set_affinity(irq, cpumask)) {
-			cpumask_copy(desc->affinity, cpumask);
+		if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
+			cpumask_copy(desc->irq_data.affinity, cpumask);
 			irq_set_thread_affinity(desc);
 		}
 	}
@@ -128,8 +129,8 @@
 		cpumask_copy(desc->pending_mask, cpumask);
 	}
 #else
-	if (!desc->chip->set_affinity(irq, cpumask)) {
-		cpumask_copy(desc->affinity, cpumask);
+	if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
+		cpumask_copy(desc->irq_data.affinity, cpumask);
 		irq_set_thread_affinity(desc);
 	}
 #endif
@@ -168,16 +169,16 @@
 	 * one of the targets is online.
 	 */
 	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpumask_any_and(desc->affinity, cpu_online_mask)
+		if (cpumask_any_and(desc->irq_data.affinity, cpu_online_mask)
 		    < nr_cpu_ids)
 			goto set_affinity;
 		else
 			desc->status &= ~IRQ_AFFINITY_SET;
 	}
 
-	cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
+	cpumask_and(desc->irq_data.affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-	desc->chip->set_affinity(irq, desc->affinity);
+	desc->irq_data.chip->irq_set_affinity(&desc->irq_data, desc->irq_data.affinity, false);
 
 	return 0;
 }
@@ -223,7 +224,7 @@
 
 	if (!desc->depth++) {
 		desc->status |= IRQ_DISABLED;
-		desc->chip->disable(irq);
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
 	}
 }
 
@@ -246,11 +247,11 @@
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	__disable_irq(desc, irq, false);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
 
@@ -313,7 +314,7 @@
  *	IRQ line is re-enabled.
  *
  *	This function may be called from IRQ context only when
- *	desc->chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
+ *	desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
  */
 void enable_irq(unsigned int irq)
 {
@@ -323,11 +324,11 @@
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	__enable_irq(desc, irq, false);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(enable_irq);
 
@@ -336,8 +337,8 @@
 	struct irq_desc *desc = irq_to_desc(irq);
 	int ret = -ENXIO;
 
-	if (desc->chip->set_wake)
-		ret = desc->chip->set_wake(irq, on);
+	if (desc->irq_data.chip->irq_set_wake)
+		ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on);
 
 	return ret;
 }
@@ -429,12 +430,12 @@
 }
 
 int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
-		unsigned long flags)
+		      unsigned long flags)
 {
 	int ret;
-	struct irq_chip *chip = desc->chip;
+	struct irq_chip *chip = desc->irq_data.chip;
 
-	if (!chip || !chip->set_type) {
+	if (!chip || !chip->irq_set_type) {
 		/*
 		 * IRQF_TRIGGER_* but the PIC does not support multiple
 		 * flow-types?
@@ -445,11 +446,11 @@
 	}
 
 	/* caller masked out all except trigger mode flags */
-	ret = chip->set_type(irq, flags);
+	ret = chip->irq_set_type(&desc->irq_data, flags);
 
 	if (ret)
-		pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
-				(int)flags, irq, chip->set_type);
+		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+		       flags, irq, chip->irq_set_type);
 	else {
 		if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 			flags |= IRQ_LEVEL;
@@ -457,8 +458,8 @@
 		desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
 		desc->status |= flags;
 
-		if (chip != desc->chip)
-			irq_chip_set_defaults(desc->chip);
+		if (chip != desc->irq_data.chip)
+			irq_chip_set_defaults(desc->irq_data.chip);
 	}
 
 	return ret;
@@ -507,7 +508,7 @@
 static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
 {
 again:
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irq(&desc->lock);
 
 	/*
@@ -521,17 +522,17 @@
 	 */
 	if (unlikely(desc->status & IRQ_INPROGRESS)) {
 		raw_spin_unlock_irq(&desc->lock);
-		chip_bus_sync_unlock(irq, desc);
+		chip_bus_sync_unlock(desc);
 		cpu_relax();
 		goto again;
 	}
 
 	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
 		desc->status &= ~IRQ_MASKED;
-		desc->chip->unmask(irq);
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
 	raw_spin_unlock_irq(&desc->lock);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 
 #ifdef CONFIG_SMP
@@ -556,7 +557,7 @@
 	}
 
 	raw_spin_lock_irq(&desc->lock);
-	cpumask_copy(mask, desc->affinity);
+	cpumask_copy(mask, desc->irq_data.affinity);
 	raw_spin_unlock_irq(&desc->lock);
 
 	set_cpus_allowed_ptr(current, mask);
@@ -657,7 +658,7 @@
 	if (!desc)
 		return -EINVAL;
 
-	if (desc->chip == &no_irq_chip)
+	if (desc->irq_data.chip == &no_irq_chip)
 		return -ENOSYS;
 	/*
 	 * Some drivers like serial.c use request_irq() heavily,
@@ -752,7 +753,7 @@
 	}
 
 	if (!shared) {
-		irq_chip_set_defaults(desc->chip);
+		irq_chip_set_defaults(desc->irq_data.chip);
 
 		init_waitqueue_head(&desc->wait_for_threads);
 
@@ -779,7 +780,7 @@
 		if (!(desc->status & IRQ_NOAUTOEN)) {
 			desc->depth = 0;
 			desc->status &= ~IRQ_DISABLED;
-			desc->chip->startup(irq);
+			desc->irq_data.chip->irq_startup(&desc->irq_data);
 		} else
 			/* Undo nested disables: */
 			desc->depth = 1;
@@ -912,17 +913,17 @@
 
 	/* Currently used only by UML, might disappear one day: */
 #ifdef CONFIG_IRQ_RELEASE_METHOD
-	if (desc->chip->release)
-		desc->chip->release(irq, dev_id);
+	if (desc->irq_data.chip->release)
+		desc->irq_data.chip->release(irq, dev_id);
 #endif
 
 	/* If this was the last handler, shut down the IRQ line: */
 	if (!desc->action) {
 		desc->status |= IRQ_DISABLED;
-		if (desc->chip->shutdown)
-			desc->chip->shutdown(irq);
+		if (desc->irq_data.chip->irq_shutdown)
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		else
-			desc->chip->disable(irq);
+			desc->irq_data.chip->irq_disable(&desc->irq_data);
 	}
 
 #ifdef CONFIG_SMP
@@ -997,9 +998,9 @@
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	kfree(__free_irq(irq, dev_id));
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(free_irq);
 
@@ -1086,9 +1087,9 @@
 	action->name = devname;
 	action->dev_id = dev_id;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 
 	if (retval)
 		kfree(action);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 2419622..1d25419 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,6 +7,7 @@
 void move_masked_irq(int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_chip *chip = desc->irq_data.chip;
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
@@ -24,7 +25,7 @@
 	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
 
-	if (!desc->chip->set_affinity)
+	if (!chip->irq_set_affinity)
 		return;
 
 	assert_raw_spin_locked(&desc->lock);
@@ -43,8 +44,9 @@
 	 */
 	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
 		   < nr_cpu_ids))
-		if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
-			cpumask_copy(desc->affinity, desc->pending_mask);
+		if (!chip->irq_set_affinity(&desc->irq_data,
+					    desc->pending_mask, false)) {
+			cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
 			irq_set_thread_affinity(desc);
 		}
 
@@ -61,8 +63,8 @@
 	if (unlikely(desc->status & IRQ_DISABLED))
 		return;
 
-	desc->chip->mask(irq);
+	desc->irq_data.chip->irq_mask(&desc->irq_data);
 	move_masked_irq(irq);
-	desc->chip->unmask(irq);
+	desc->irq_data.chip->irq_unmask(&desc->irq_data);
 }
 
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
deleted file mode 100644
index 65d3845..0000000
--- a/kernel/irq/numa_migrate.c
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * NUMA irq-desc migration code
- *
- * Migrate IRQ data structures (irq_desc, chip_data, etc.) over to
- * the new "home node" of the IRQ.
- */
-
-#include <linux/irq.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/random.h>
-#include <linux/interrupt.h>
-#include <linux/kernel_stat.h>
-
-#include "internals.h"
-
-static void init_copy_kstat_irqs(struct irq_desc *old_desc,
-				 struct irq_desc *desc,
-				 int node, int nr)
-{
-	init_kstat_irqs(desc, node, nr);
-
-	if (desc->kstat_irqs != old_desc->kstat_irqs)
-		memcpy(desc->kstat_irqs, old_desc->kstat_irqs,
-			 nr * sizeof(*desc->kstat_irqs));
-}
-
-static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
-{
-	if (old_desc->kstat_irqs == desc->kstat_irqs)
-		return;
-
-	kfree(old_desc->kstat_irqs);
-	old_desc->kstat_irqs = NULL;
-}
-
-static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
-		 struct irq_desc *desc, int node)
-{
-	memcpy(desc, old_desc, sizeof(struct irq_desc));
-	if (!alloc_desc_masks(desc, node, false)) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
-				"for migration.\n", irq);
-		return false;
-	}
-	raw_spin_lock_init(&desc->lock);
-	desc->node = node;
-	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids);
-	init_copy_desc_masks(old_desc, desc);
-	arch_init_copy_chip_data(old_desc, desc, node);
-	return true;
-}
-
-static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
-{
-	free_kstat_irqs(old_desc, desc);
-	free_desc_masks(old_desc, desc);
-	arch_free_chip_data(old_desc, desc);
-}
-
-static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
-						int node)
-{
-	struct irq_desc *desc;
-	unsigned int irq;
-	unsigned long flags;
-
-	irq = old_desc->irq;
-
-	raw_spin_lock_irqsave(&sparse_irq_lock, flags);
-
-	/* We have to check it to avoid races with another CPU */
-	desc = irq_to_desc(irq);
-
-	if (desc && old_desc != desc)
-		goto out_unlock;
-
-	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-	if (!desc) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc "
-				"for migration.\n", irq);
-		/* still use old one */
-		desc = old_desc;
-		goto out_unlock;
-	}
-	if (!init_copy_one_irq_desc(irq, old_desc, desc, node)) {
-		/* still use old one */
-		kfree(desc);
-		desc = old_desc;
-		goto out_unlock;
-	}
-
-	replace_irq_desc(irq, desc);
-	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-	/* free the old one */
-	free_one_irq_desc(old_desc, desc);
-	kfree(old_desc);
-
-	return desc;
-
-out_unlock:
-	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-	return desc;
-}
-
-struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
-{
-	/* those static or target node is -1, do not move them */
-	if (desc->irq < NR_IRQS_LEGACY || node == -1)
-		return desc;
-
-	if (desc->node != node)
-		desc = __real_move_irq_desc(desc, node);
-
-	return desc;
-}
-
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 09a2ee5..01b1d3a 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -21,7 +21,7 @@
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	const struct cpumask *mask = desc->affinity;
+	const struct cpumask *mask = desc->irq_data.affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PENDING)
@@ -65,7 +65,7 @@
 	cpumask_var_t new_value;
 	int err;
 
-	if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
+	if (!irq_to_desc(irq)->irq_data.chip->irq_set_affinity || no_irq_affinity ||
 	    irq_balancing_disabled(irq))
 		return -EIO;
 
@@ -185,7 +185,7 @@
 {
 	struct irq_desc *desc = irq_to_desc((long) m->private);
 
-	seq_printf(m, "%d\n", desc->node);
+	seq_printf(m, "%d\n", desc->irq_data.node);
 	return 0;
 }
 
@@ -269,7 +269,7 @@
 {
 	char name [MAX_NAMELEN];
 
-	if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
+	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
 		return;
 
 	memset(name, 0, MAX_NAMELEN);
@@ -297,6 +297,24 @@
 			 &irq_spurious_proc_fops, (void *)(long)irq);
 }
 
+void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
+{
+	char name [MAX_NAMELEN];
+
+	if (!root_irq_dir || !desc->dir)
+		return;
+#ifdef CONFIG_SMP
+	remove_proc_entry("smp_affinity", desc->dir);
+	remove_proc_entry("affinity_hint", desc->dir);
+	remove_proc_entry("node", desc->dir);
+#endif
+	remove_proc_entry("spurious", desc->dir);
+
+	memset(name, 0, MAX_NAMELEN);
+	sprintf(name, "%u", irq);
+	remove_proc_entry(name, root_irq_dir);
+}
+
 #undef MAX_NAMELEN
 
 void unregister_handler_proc(unsigned int irq, struct irqaction *action)
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 090c376..891115a 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -60,7 +60,7 @@
 	/*
 	 * Make sure the interrupt is enabled, before resending it:
 	 */
-	desc->chip->enable(irq);
+	desc->irq_data.chip->irq_enable(&desc->irq_data);
 
 	/*
 	 * We do not resend level type interrupts. Level type
@@ -70,7 +70,8 @@
 	if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
 		desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
 
-		if (!desc->chip->retrigger || !desc->chip->retrigger(irq)) {
+		if (!desc->irq_data.chip->irq_retrigger ||
+		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 89fb90a..3089d3b9 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -14,6 +14,8 @@
 #include <linux/moduleparam.h>
 #include <linux/timer.h>
 
+#include "internals.h"
+
 static int irqfixup __read_mostly;
 
 #define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
@@ -78,8 +80,8 @@
 	 * If we did actual work for the real IRQ line we must let the
 	 * IRQ controller clean up too
 	 */
-	if (work && desc->chip && desc->chip->end)
-		desc->chip->end(irq);
+	if (work)
+		irq_end(irq, desc);
 	raw_spin_unlock(&desc->lock);
 
 	return ok;
@@ -254,7 +256,7 @@
 		printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
 		desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
 		desc->depth++;
-		desc->chip->disable(irq);
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
 
 		mod_timer(&poll_spurious_irq_timer,
 			  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
new file mode 100644
index 0000000..f16763f
--- /dev/null
+++ b/kernel/irq_work.c
@@ -0,0 +1,164 @@
+/*
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ * Provides a framework for enqueueing and running callbacks from hardirq
+ * context. The enqueueing is NMI-safe.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/irq_work.h>
+#include <linux/hardirq.h>
+
+/*
+ * An entry can be in one of four states:
+ *
+ * free	     NULL, 0 -> {claimed}       : free to be used
+ * claimed   NULL, 3 -> {pending}       : claimed to be enqueued
+ * pending   next, 3 -> {busy}          : queued, pending callback
+ * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
+ *
+ * We use the lower two bits of the next pointer to keep PENDING and BUSY
+ * flags.
+ */
+
+#define IRQ_WORK_PENDING	1UL
+#define IRQ_WORK_BUSY		2UL
+#define IRQ_WORK_FLAGS		3UL
+
+static inline bool irq_work_is_set(struct irq_work *entry, int flags)
+{
+	return (unsigned long)entry->next & flags;
+}
+
+static inline struct irq_work *irq_work_next(struct irq_work *entry)
+{
+	unsigned long next = (unsigned long)entry->next;
+	next &= ~IRQ_WORK_FLAGS;
+	return (struct irq_work *)next;
+}
+
+static inline struct irq_work *next_flags(struct irq_work *entry, int flags)
+{
+	unsigned long next = (unsigned long)entry;
+	next |= flags;
+	return (struct irq_work *)next;
+}
+
+static DEFINE_PER_CPU(struct irq_work *, irq_work_list);
+
+/*
+ * Claim the entry so that no one else will poke at it.
+ */
+static bool irq_work_claim(struct irq_work *entry)
+{
+	struct irq_work *next, *nflags;
+
+	do {
+		next = entry->next;
+		if ((unsigned long)next & IRQ_WORK_PENDING)
+			return false;
+		nflags = next_flags(next, IRQ_WORK_FLAGS);
+	} while (cmpxchg(&entry->next, next, nflags) != next);
+
+	return true;
+}
+
+
+void __weak arch_irq_work_raise(void)
+{
+	/*
+	 * Lame architectures will get the timer tick callback
+	 */
+}
+
+/*
+ * Queue the entry and raise the IPI if needed.
+ */
+static void __irq_work_queue(struct irq_work *entry)
+{
+	struct irq_work **head, *next;
+
+	head = &get_cpu_var(irq_work_list);
+
+	do {
+		next = *head;
+		/* Can assign non-atomic because we keep the flags set. */
+		entry->next = next_flags(next, IRQ_WORK_FLAGS);
+	} while (cmpxchg(head, next, entry) != next);
+
+	/* The list was empty, raise self-interrupt to start processing. */
+	if (!irq_work_next(entry))
+		arch_irq_work_raise();
+
+	put_cpu_var(irq_work_list);
+}
+
+/*
+ * Enqueue the irq_work @entry, returns true on success, failure when the
+ * @entry was already enqueued by someone else.
+ *
+ * Can be re-enqueued while the callback is still in progress.
+ */
+bool irq_work_queue(struct irq_work *entry)
+{
+	if (!irq_work_claim(entry)) {
+		/*
+		 * Already enqueued, can't do!
+		 */
+		return false;
+	}
+
+	__irq_work_queue(entry);
+	return true;
+}
+EXPORT_SYMBOL_GPL(irq_work_queue);
+
+/*
+ * Run the irq_work entries on this cpu. Requires to be ran from hardirq
+ * context with local IRQs disabled.
+ */
+void irq_work_run(void)
+{
+	struct irq_work *list, **head;
+
+	head = &__get_cpu_var(irq_work_list);
+	if (*head == NULL)
+		return;
+
+	BUG_ON(!in_irq());
+	BUG_ON(!irqs_disabled());
+
+	list = xchg(head, NULL);
+	while (list != NULL) {
+		struct irq_work *entry = list;
+
+		list = irq_work_next(list);
+
+		/*
+		 * Clear the PENDING bit, after this point the @entry
+		 * can be re-used.
+		 */
+		entry->next = next_flags(NULL, IRQ_WORK_BUSY);
+		entry->func(entry);
+		/*
+		 * Clear the BUSY bit and return to the free state if
+		 * no-one else claimed it meanwhile.
+		 */
+		cmpxchg(&entry->next, next_flags(NULL, IRQ_WORK_BUSY), NULL);
+	}
+}
+EXPORT_SYMBOL_GPL(irq_work_run);
+
+/*
+ * Synchronize against the irq_work @entry, ensures the entry is not
+ * currently in use.
+ */
+void irq_work_sync(struct irq_work *entry)
+{
+	WARN_ON_ONCE(irqs_disabled());
+
+	while (irq_work_is_set(entry, IRQ_WORK_BUSY))
+		cpu_relax();
+}
+EXPORT_SYMBOL_GPL(irq_work_sync);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
new file mode 100644
index 0000000..7be868b
--- /dev/null
+++ b/kernel/jump_label.c
@@ -0,0 +1,429 @@
+/*
+ * jump label support
+ *
+ * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
+ *
+ */
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/err.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+#define JUMP_LABEL_HASH_BITS 6
+#define JUMP_LABEL_TABLE_SIZE (1 << JUMP_LABEL_HASH_BITS)
+static struct hlist_head jump_label_table[JUMP_LABEL_TABLE_SIZE];
+
+/* mutex to protect coming/going of the the jump_label table */
+static DEFINE_MUTEX(jump_label_mutex);
+
+struct jump_label_entry {
+	struct hlist_node hlist;
+	struct jump_entry *table;
+	int nr_entries;
+	/* hang modules off here */
+	struct hlist_head modules;
+	unsigned long key;
+};
+
+struct jump_label_module_entry {
+	struct hlist_node hlist;
+	struct jump_entry *table;
+	int nr_entries;
+	struct module *mod;
+};
+
+static int jump_label_cmp(const void *a, const void *b)
+{
+	const struct jump_entry *jea = a;
+	const struct jump_entry *jeb = b;
+
+	if (jea->key < jeb->key)
+		return -1;
+
+	if (jea->key > jeb->key)
+		return 1;
+
+	return 0;
+}
+
+static void
+sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop)
+{
+	unsigned long size;
+
+	size = (((unsigned long)stop - (unsigned long)start)
+					/ sizeof(struct jump_entry));
+	sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
+}
+
+static struct jump_label_entry *get_jump_label_entry(jump_label_t key)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct jump_label_entry *e;
+	u32 hash = jhash((void *)&key, sizeof(jump_label_t), 0);
+
+	head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)];
+	hlist_for_each_entry(e, node, head, hlist) {
+		if (key == e->key)
+			return e;
+	}
+	return NULL;
+}
+
+static struct jump_label_entry *
+add_jump_label_entry(jump_label_t key, int nr_entries, struct jump_entry *table)
+{
+	struct hlist_head *head;
+	struct jump_label_entry *e;
+	u32 hash;
+
+	e = get_jump_label_entry(key);
+	if (e)
+		return ERR_PTR(-EEXIST);
+
+	e = kmalloc(sizeof(struct jump_label_entry), GFP_KERNEL);
+	if (!e)
+		return ERR_PTR(-ENOMEM);
+
+	hash = jhash((void *)&key, sizeof(jump_label_t), 0);
+	head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)];
+	e->key = key;
+	e->table = table;
+	e->nr_entries = nr_entries;
+	INIT_HLIST_HEAD(&(e->modules));
+	hlist_add_head(&e->hlist, head);
+	return e;
+}
+
+static int
+build_jump_label_hashtable(struct jump_entry *start, struct jump_entry *stop)
+{
+	struct jump_entry *iter, *iter_begin;
+	struct jump_label_entry *entry;
+	int count;
+
+	sort_jump_label_entries(start, stop);
+	iter = start;
+	while (iter < stop) {
+		entry = get_jump_label_entry(iter->key);
+		if (!entry) {
+			iter_begin = iter;
+			count = 0;
+			while ((iter < stop) &&
+				(iter->key == iter_begin->key)) {
+				iter++;
+				count++;
+			}
+			entry = add_jump_label_entry(iter_begin->key,
+							count, iter_begin);
+			if (IS_ERR(entry))
+				return PTR_ERR(entry);
+		 } else {
+			WARN_ONCE(1, KERN_ERR "build_jump_hashtable: unexpected entry!\n");
+			return -1;
+		}
+	}
+	return 0;
+}
+
+/***
+ * jump_label_update - update jump label text
+ * @key -  key value associated with a a jump label
+ * @type - enum set to JUMP_LABEL_ENABLE or JUMP_LABEL_DISABLE
+ *
+ * Will enable/disable the jump for jump label @key, depending on the
+ * value of @type.
+ *
+ */
+
+void jump_label_update(unsigned long key, enum jump_label_type type)
+{
+	struct jump_entry *iter;
+	struct jump_label_entry *entry;
+	struct hlist_node *module_node;
+	struct jump_label_module_entry *e_module;
+	int count;
+
+	mutex_lock(&jump_label_mutex);
+	entry = get_jump_label_entry((jump_label_t)key);
+	if (entry) {
+		count = entry->nr_entries;
+		iter = entry->table;
+		while (count--) {
+			if (kernel_text_address(iter->code))
+				arch_jump_label_transform(iter, type);
+			iter++;
+		}
+		/* eanble/disable jump labels in modules */
+		hlist_for_each_entry(e_module, module_node, &(entry->modules),
+							hlist) {
+			count = e_module->nr_entries;
+			iter = e_module->table;
+			while (count--) {
+				if (kernel_text_address(iter->code))
+					arch_jump_label_transform(iter, type);
+				iter++;
+			}
+		}
+	}
+	mutex_unlock(&jump_label_mutex);
+}
+
+static int addr_conflict(struct jump_entry *entry, void *start, void *end)
+{
+	if (entry->code <= (unsigned long)end &&
+		entry->code + JUMP_LABEL_NOP_SIZE > (unsigned long)start)
+		return 1;
+
+	return 0;
+}
+
+#ifdef CONFIG_MODULES
+
+static int module_conflict(void *start, void *end)
+{
+	struct hlist_head *head;
+	struct hlist_node *node, *node_next, *module_node, *module_node_next;
+	struct jump_label_entry *e;
+	struct jump_label_module_entry *e_module;
+	struct jump_entry *iter;
+	int i, count;
+	int conflict = 0;
+
+	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
+		head = &jump_label_table[i];
+		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
+			hlist_for_each_entry_safe(e_module, module_node,
+							module_node_next,
+							&(e->modules), hlist) {
+				count = e_module->nr_entries;
+				iter = e_module->table;
+				while (count--) {
+					if (addr_conflict(iter, start, end)) {
+						conflict = 1;
+						goto out;
+					}
+					iter++;
+				}
+			}
+		}
+	}
+out:
+	return conflict;
+}
+
+#endif
+
+/***
+ * jump_label_text_reserved - check if addr range is reserved
+ * @start: start text addr
+ * @end: end text addr
+ *
+ * checks if the text addr located between @start and @end
+ * overlaps with any of the jump label patch addresses. Code
+ * that wants to modify kernel text should first verify that
+ * it does not overlap with any of the jump label addresses.
+ *
+ * returns 1 if there is an overlap, 0 otherwise
+ */
+int jump_label_text_reserved(void *start, void *end)
+{
+	struct jump_entry *iter;
+	struct jump_entry *iter_start = __start___jump_table;
+	struct jump_entry *iter_stop = __start___jump_table;
+	int conflict = 0;
+
+	mutex_lock(&jump_label_mutex);
+	iter = iter_start;
+	while (iter < iter_stop) {
+		if (addr_conflict(iter, start, end)) {
+			conflict = 1;
+			goto out;
+		}
+		iter++;
+	}
+
+	/* now check modules */
+#ifdef CONFIG_MODULES
+	conflict = module_conflict(start, end);
+#endif
+out:
+	mutex_unlock(&jump_label_mutex);
+	return conflict;
+}
+
+static __init int init_jump_label(void)
+{
+	int ret;
+	struct jump_entry *iter_start = __start___jump_table;
+	struct jump_entry *iter_stop = __stop___jump_table;
+	struct jump_entry *iter;
+
+	mutex_lock(&jump_label_mutex);
+	ret = build_jump_label_hashtable(__start___jump_table,
+					 __stop___jump_table);
+	iter = iter_start;
+	while (iter < iter_stop) {
+		arch_jump_label_text_poke_early(iter->code);
+		iter++;
+	}
+	mutex_unlock(&jump_label_mutex);
+	return ret;
+}
+early_initcall(init_jump_label);
+
+#ifdef CONFIG_MODULES
+
+static struct jump_label_module_entry *
+add_jump_label_module_entry(struct jump_label_entry *entry,
+			    struct jump_entry *iter_begin,
+			    int count, struct module *mod)
+{
+	struct jump_label_module_entry *e;
+
+	e = kmalloc(sizeof(struct jump_label_module_entry), GFP_KERNEL);
+	if (!e)
+		return ERR_PTR(-ENOMEM);
+	e->mod = mod;
+	e->nr_entries = count;
+	e->table = iter_begin;
+	hlist_add_head(&e->hlist, &entry->modules);
+	return e;
+}
+
+static int add_jump_label_module(struct module *mod)
+{
+	struct jump_entry *iter, *iter_begin;
+	struct jump_label_entry *entry;
+	struct jump_label_module_entry *module_entry;
+	int count;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return 0;
+
+	sort_jump_label_entries(mod->jump_entries,
+				mod->jump_entries + mod->num_jump_entries);
+	iter = mod->jump_entries;
+	while (iter < mod->jump_entries + mod->num_jump_entries) {
+		entry = get_jump_label_entry(iter->key);
+		iter_begin = iter;
+		count = 0;
+		while ((iter < mod->jump_entries + mod->num_jump_entries) &&
+			(iter->key == iter_begin->key)) {
+				iter++;
+				count++;
+		}
+		if (!entry) {
+			entry = add_jump_label_entry(iter_begin->key, 0, NULL);
+			if (IS_ERR(entry))
+				return PTR_ERR(entry);
+		}
+		module_entry = add_jump_label_module_entry(entry, iter_begin,
+							   count, mod);
+		if (IS_ERR(module_entry))
+			return PTR_ERR(module_entry);
+	}
+	return 0;
+}
+
+static void remove_jump_label_module(struct module *mod)
+{
+	struct hlist_head *head;
+	struct hlist_node *node, *node_next, *module_node, *module_node_next;
+	struct jump_label_entry *e;
+	struct jump_label_module_entry *e_module;
+	int i;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return;
+
+	for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) {
+		head = &jump_label_table[i];
+		hlist_for_each_entry_safe(e, node, node_next, head, hlist) {
+			hlist_for_each_entry_safe(e_module, module_node,
+						  module_node_next,
+						  &(e->modules), hlist) {
+				if (e_module->mod == mod) {
+					hlist_del(&e_module->hlist);
+					kfree(e_module);
+				}
+			}
+			if (hlist_empty(&e->modules) && (e->nr_entries == 0)) {
+				hlist_del(&e->hlist);
+				kfree(e);
+			}
+		}
+	}
+}
+
+static int
+jump_label_module_notify(struct notifier_block *self, unsigned long val,
+			 void *data)
+{
+	struct module *mod = data;
+	int ret = 0;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		mutex_lock(&jump_label_mutex);
+		ret = add_jump_label_module(mod);
+		if (ret)
+			remove_jump_label_module(mod);
+		mutex_unlock(&jump_label_mutex);
+		break;
+	case MODULE_STATE_GOING:
+		mutex_lock(&jump_label_mutex);
+		remove_jump_label_module(mod);
+		mutex_unlock(&jump_label_mutex);
+		break;
+	}
+	return ret;
+}
+
+/***
+ * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop()
+ * @mod: module to patch
+ *
+ * Allow for run-time selection of the optimal nops. Before the module
+ * loads patch these with arch_get_jump_label_nop(), which is specified by
+ * the arch specific jump label code.
+ */
+void jump_label_apply_nops(struct module *mod)
+{
+	struct jump_entry *iter;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (!mod->num_jump_entries)
+		return;
+
+	iter = mod->jump_entries;
+	while (iter < mod->jump_entries + mod->num_jump_entries) {
+		arch_jump_label_text_poke_early(iter->code);
+		iter++;
+	}
+}
+
+struct notifier_block jump_label_module_nb = {
+	.notifier_call = jump_label_module_notify,
+	.priority = 0,
+};
+
+static __init int init_jump_label_module(void)
+{
+	return register_module_notifier(&jump_label_module_nb);
+}
+early_initcall(init_jump_label_module);
+
+#endif /* CONFIG_MODULES */
+
+#endif
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 282035f..56a8919 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -47,6 +47,7 @@
 #include <linux/memory.h>
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
+#include <linux/jump_label.h>
 
 #include <asm-generic/sections.h>
 #include <asm/cacheflush.h>
@@ -399,7 +400,7 @@
  * Return an optimized kprobe whose optimizing code replaces
  * instructions including addr (exclude breakpoint).
  */
-struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
+static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
 {
 	int i;
 	struct kprobe *p = NULL;
@@ -831,6 +832,7 @@
 
 void __kprobes kretprobe_hash_lock(struct task_struct *tsk,
 			 struct hlist_head **head, unsigned long *flags)
+__acquires(hlist_lock)
 {
 	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
 	spinlock_t *hlist_lock;
@@ -842,6 +844,7 @@
 
 static void __kprobes kretprobe_table_lock(unsigned long hash,
 	unsigned long *flags)
+__acquires(hlist_lock)
 {
 	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	spin_lock_irqsave(hlist_lock, *flags);
@@ -849,6 +852,7 @@
 
 void __kprobes kretprobe_hash_unlock(struct task_struct *tsk,
 	unsigned long *flags)
+__releases(hlist_lock)
 {
 	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
 	spinlock_t *hlist_lock;
@@ -857,7 +861,9 @@
 	spin_unlock_irqrestore(hlist_lock, *flags);
 }
 
-void __kprobes kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
+static void __kprobes kretprobe_table_unlock(unsigned long hash,
+       unsigned long *flags)
+__releases(hlist_lock)
 {
 	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	spin_unlock_irqrestore(hlist_lock, *flags);
@@ -1141,7 +1147,8 @@
 	preempt_disable();
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr) ||
-	    ftrace_text_reserved(p->addr, p->addr)) {
+	    ftrace_text_reserved(p->addr, p->addr) ||
+	    jump_label_text_reserved(p->addr, p->addr)) {
 		preempt_enable();
 		return -EINVAL;
 	}
@@ -1339,18 +1346,19 @@
 	if (num <= 0)
 		return -EINVAL;
 	for (i = 0; i < num; i++) {
-		unsigned long addr;
+		unsigned long addr, offset;
 		jp = jps[i];
 		addr = arch_deref_entry_point(jp->entry);
 
-		if (!kernel_text_address(addr))
-			ret = -EINVAL;
-		else {
-			/* Todo: Verify probepoint is a function entry point */
+		/* Verify probepoint is a function entry point */
+		if (kallsyms_lookup_size_offset(addr, NULL, &offset) &&
+		    offset == 0) {
 			jp->kp.pre_handler = setjmp_pre_handler;
 			jp->kp.break_handler = longjmp_break_handler;
 			ret = register_kprobe(&jp->kp);
-		}
+		} else
+			ret = -EINVAL;
+
 		if (ret < 0) {
 			if (i > 0)
 				unregister_jprobes(jps, i);
@@ -1992,6 +2000,7 @@
 static const struct file_operations fops_kp = {
 	.read =         read_enabled_file_bool,
 	.write =        write_enabled_file_bool,
+	.llseek =	default_llseek,
 };
 
 static int __kprobes debugfs_kprobe_init(void)
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index f2852a5..42ba65d 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -639,6 +639,16 @@
 	}
 #endif
 
+	if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
+		debug_locks_off();
+		printk(KERN_ERR
+			"BUG: looking up invalid subclass: %u\n", subclass);
+		printk(KERN_ERR
+			"turning off the locking correctness validator.\n");
+		dump_stack();
+		return NULL;
+	}
+
 	/*
 	 * Static locks do not have their class-keys yet - for them the key
 	 * is the lock object itself:
@@ -774,7 +784,9 @@
 	raw_local_irq_restore(flags);
 
 	if (!subclass || force)
-		lock->class_cache = class;
+		lock->class_cache[0] = class;
+	else if (subclass < NR_LOCKDEP_CACHING_CLASSES)
+		lock->class_cache[subclass] = class;
 
 	if (DEBUG_LOCKS_WARN_ON(class->subclass != subclass))
 		return NULL;
@@ -2679,7 +2691,11 @@
 void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		      struct lock_class_key *key, int subclass)
 {
-	lock->class_cache = NULL;
+	int i;
+
+	for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
+		lock->class_cache[i] = NULL;
+
 #ifdef CONFIG_LOCK_STAT
 	lock->cpu = raw_smp_processor_id();
 #endif
@@ -2739,21 +2755,13 @@
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return 0;
 
-	if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
-		debug_locks_off();
-		printk("BUG: MAX_LOCKDEP_SUBCLASSES too low!\n");
-		printk("turning off the locking correctness validator.\n");
-		dump_stack();
-		return 0;
-	}
-
 	if (lock->key == &__lockdep_no_validate__)
 		check = 1;
 
-	if (!subclass)
-		class = lock->class_cache;
+	if (subclass < NR_LOCKDEP_CACHING_CLASSES)
+		class = lock->class_cache[subclass];
 	/*
-	 * Not cached yet or subclass?
+	 * Not cached?
 	 */
 	if (unlikely(!class)) {
 		class = register_lock_class(lock, subclass, 0);
@@ -2918,7 +2926,7 @@
 		return 1;
 
 	if (hlock->references) {
-		struct lock_class *class = lock->class_cache;
+		struct lock_class *class = lock->class_cache[0];
 
 		if (!class)
 			class = look_up_lock_class(lock, 0);
@@ -3559,7 +3567,12 @@
 		if (list_empty(head))
 			continue;
 		list_for_each_entry_safe(class, next, head, hash_entry) {
-			if (unlikely(class == lock->class_cache)) {
+			int match = 0;
+
+			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
+				match |= class == lock->class_cache[j];
+
+			if (unlikely(match)) {
 				if (debug_locks_off_graph_unlock())
 					WARN_ON(1);
 				goto out_restore;
@@ -3775,7 +3788,7 @@
  * Careful: only use this function if you are sure that
  * the task cannot run in parallel!
  */
-void __debug_show_held_locks(struct task_struct *task)
+void debug_show_held_locks(struct task_struct *task)
 {
 	if (unlikely(!debug_locks)) {
 		printk("INFO: lockdep is turned off.\n");
@@ -3783,12 +3796,6 @@
 	}
 	lockdep_print_held_locks(task);
 }
-EXPORT_SYMBOL_GPL(__debug_show_held_locks);
-
-void debug_show_held_locks(struct task_struct *task)
-{
-		__debug_show_held_locks(task);
-}
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
 void lockdep_sys_exit(void)
diff --git a/kernel/module.c b/kernel/module.c
index ccd6419..2df4630 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -55,6 +55,7 @@
 #include <linux/async.h>
 #include <linux/percpu.h>
 #include <linux/kmemleak.h>
+#include <linux/jump_label.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
@@ -2309,6 +2310,11 @@
 					sizeof(*mod->tracepoints),
 					&mod->num_tracepoints);
 #endif
+#ifdef HAVE_JUMP_LABEL
+	mod->jump_entries = section_objs(info, "__jump_table",
+					sizeof(*mod->jump_entries),
+					&mod->num_jump_entries);
+#endif
 #ifdef CONFIG_EVENT_TRACING
 	mod->trace_events = section_objs(info, "_ftrace_events",
 					 sizeof(*mod->trace_events),
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index b98bed3..f309e80 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -31,24 +31,18 @@
 #include <linux/kernel_stat.h>
 #include <linux/perf_event.h>
 #include <linux/ftrace_event.h>
-#include <linux/hw_breakpoint.h>
 
 #include <asm/irq_regs.h>
 
-/*
- * Each CPU has a list of per CPU events:
- */
-static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
-
-int perf_max_events __read_mostly = 1;
-static int perf_reserved_percpu __read_mostly;
-static int perf_overcommit __read_mostly = 1;
-
-static atomic_t nr_events __read_mostly;
+atomic_t perf_task_events __read_mostly;
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
 static atomic_t nr_task_events __read_mostly;
 
+static LIST_HEAD(pmus);
+static DEFINE_MUTEX(pmus_lock);
+static struct srcu_struct pmus_srcu;
+
 /*
  * perf event paranoia level:
  *  -1 - not paranoid at all
@@ -67,36 +61,43 @@
 
 static atomic64_t perf_event_id;
 
-/*
- * Lock for (sysadmin-configurable) event reservations:
- */
-static DEFINE_SPINLOCK(perf_resource_lock);
-
-/*
- * Architecture provided APIs - weak aliases:
- */
-extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
-{
-	return NULL;
-}
-
-void __weak hw_perf_disable(void)		{ barrier(); }
-void __weak hw_perf_enable(void)		{ barrier(); }
-
 void __weak perf_event_print_debug(void)	{ }
 
-static DEFINE_PER_CPU(int, perf_disable_count);
-
-void perf_disable(void)
+extern __weak const char *perf_pmu_name(void)
 {
-	if (!__get_cpu_var(perf_disable_count)++)
-		hw_perf_disable();
+	return "pmu";
 }
 
-void perf_enable(void)
+void perf_pmu_disable(struct pmu *pmu)
 {
-	if (!--__get_cpu_var(perf_disable_count))
-		hw_perf_enable();
+	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+	if (!(*count)++)
+		pmu->pmu_disable(pmu);
+}
+
+void perf_pmu_enable(struct pmu *pmu)
+{
+	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+	if (!--(*count))
+		pmu->pmu_enable(pmu);
+}
+
+static DEFINE_PER_CPU(struct list_head, rotation_list);
+
+/*
+ * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
+ * because they're strictly cpu affine and rotate_start is called with IRQs
+ * disabled, while rotate_context is called from IRQ context.
+ */
+static void perf_pmu_rotate_start(struct pmu *pmu)
+{
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+	struct list_head *head = &__get_cpu_var(rotation_list);
+
+	WARN_ON(!irqs_disabled());
+
+	if (list_empty(&cpuctx->rotation_list))
+		list_add(&cpuctx->rotation_list, head);
 }
 
 static void get_ctx(struct perf_event_context *ctx)
@@ -151,13 +152,13 @@
  * the context could get moved to another task.
  */
 static struct perf_event_context *
-perf_lock_task_context(struct task_struct *task, unsigned long *flags)
+perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
 {
 	struct perf_event_context *ctx;
 
 	rcu_read_lock();
- retry:
-	ctx = rcu_dereference(task->perf_event_ctxp);
+retry:
+	ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
 	if (ctx) {
 		/*
 		 * If this context is a clone of another, it might
@@ -170,7 +171,7 @@
 		 * can't get swapped on us any more.
 		 */
 		raw_spin_lock_irqsave(&ctx->lock, *flags);
-		if (ctx != rcu_dereference(task->perf_event_ctxp)) {
+		if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {
 			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
 			goto retry;
 		}
@@ -189,12 +190,13 @@
  * can't get swapped to another task.  This also increments its
  * reference count so that the context can't get freed.
  */
-static struct perf_event_context *perf_pin_task_context(struct task_struct *task)
+static struct perf_event_context *
+perf_pin_task_context(struct task_struct *task, int ctxn)
 {
 	struct perf_event_context *ctx;
 	unsigned long flags;
 
-	ctx = perf_lock_task_context(task, &flags);
+	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		++ctx->pin_count;
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
@@ -302,6 +304,8 @@
 	}
 
 	list_add_rcu(&event->event_entry, &ctx->event_list);
+	if (!ctx->nr_events)
+		perf_pmu_rotate_start(ctx->pmu);
 	ctx->nr_events++;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat++;
@@ -311,7 +315,12 @@
 {
 	struct perf_event *group_leader = event->group_leader;
 
-	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_GROUP);
+	/*
+	 * We can have double attach due to group movement in perf_event_open.
+	 */
+	if (event->attach_state & PERF_ATTACH_GROUP)
+		return;
+
 	event->attach_state |= PERF_ATTACH_GROUP;
 
 	if (group_leader == event)
@@ -408,8 +417,8 @@
 	return event->cpu == -1 || event->cpu == smp_processor_id();
 }
 
-static void
-event_sched_out(struct perf_event *event,
+static int
+__event_sched_out(struct perf_event *event,
 		  struct perf_cpu_context *cpuctx,
 		  struct perf_event_context *ctx)
 {
@@ -428,15 +437,14 @@
 	}
 
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
-		return;
+		return 0;
 
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-	event->tstamp_stopped = ctx->time;
-	event->pmu->disable(event);
+	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
 	if (!is_software_event(event))
@@ -444,6 +452,19 @@
 	ctx->nr_active--;
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
+	return 1;
+}
+
+static void
+event_sched_out(struct perf_event *event,
+		  struct perf_cpu_context *cpuctx,
+		  struct perf_event_context *ctx)
+{
+	int ret;
+
+	ret = __event_sched_out(event, cpuctx, ctx);
+	if (ret)
+		event->tstamp_stopped = ctx->time;
 }
 
 static void
@@ -466,6 +487,12 @@
 		cpuctx->exclusive = 0;
 }
 
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+	return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -474,9 +501,9 @@
  */
 static void __perf_event_remove_from_context(void *info)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -487,27 +514,11 @@
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	/*
-	 * Protect the list operation against NMI by disabling the
-	 * events on a global level.
-	 */
-	perf_disable();
 
 	event_sched_out(event, cpuctx, ctx);
 
 	list_del_event(event, ctx);
 
-	if (!ctx->task) {
-		/*
-		 * Allow more per task events with respect to the
-		 * reservation:
-		 */
-		cpuctx->max_pertask =
-			min(perf_max_events - ctx->nr_events,
-			    perf_max_events - perf_reserved_percpu);
-	}
-
-	perf_enable();
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -572,8 +583,8 @@
 static void __perf_event_disable(void *info)
 {
 	struct perf_event *event = info;
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	/*
 	 * If this is a per-task event, need to check whether this
@@ -628,7 +639,7 @@
 		return;
 	}
 
- retry:
+retry:
 	task_oncpu_function_call(task, __perf_event_disable, event);
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -653,7 +664,7 @@
 }
 
 static int
-event_sched_in(struct perf_event *event,
+__event_sched_in(struct perf_event *event,
 		 struct perf_cpu_context *cpuctx,
 		 struct perf_event_context *ctx)
 {
@@ -667,14 +678,12 @@
 	 */
 	smp_wmb();
 
-	if (event->pmu->enable(event)) {
+	if (event->pmu->add(event, PERF_EF_START)) {
 		event->state = PERF_EVENT_STATE_INACTIVE;
 		event->oncpu = -1;
 		return -EAGAIN;
 	}
 
-	event->tstamp_running += ctx->time - event->tstamp_stopped;
-
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	ctx->nr_active++;
@@ -685,28 +694,56 @@
 	return 0;
 }
 
+static inline int
+event_sched_in(struct perf_event *event,
+		 struct perf_cpu_context *cpuctx,
+		 struct perf_event_context *ctx)
+{
+	int ret = __event_sched_in(event, cpuctx, ctx);
+	if (ret)
+		return ret;
+	event->tstamp_running += ctx->time - event->tstamp_stopped;
+	return 0;
+}
+
+static void
+group_commit_event_sched_in(struct perf_event *group_event,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_event_context *ctx)
+{
+	struct perf_event *event;
+	u64 now = ctx->time;
+
+	group_event->tstamp_running += now - group_event->tstamp_stopped;
+	/*
+	 * Schedule in siblings as one group (if any):
+	 */
+	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
+		event->tstamp_running += now - event->tstamp_stopped;
+	}
+}
+
 static int
 group_sched_in(struct perf_event *group_event,
 	       struct perf_cpu_context *cpuctx,
 	       struct perf_event_context *ctx)
 {
 	struct perf_event *event, *partial_group = NULL;
-	const struct pmu *pmu = group_event->pmu;
-	bool txn = false;
+	struct pmu *pmu = group_event->pmu;
 
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
 
-	/* Check if group transaction availabe */
-	if (pmu->start_txn)
-		txn = true;
+	pmu->start_txn(pmu);
 
-	if (txn)
-		pmu->start_txn(pmu);
-
-	if (event_sched_in(group_event, cpuctx, ctx)) {
-		if (txn)
-			pmu->cancel_txn(pmu);
+	/*
+	 * use __event_sched_in() to delay updating tstamp_running
+	 * until the transaction is committed. In case of failure
+	 * we will keep an unmodified tstamp_running which is a
+	 * requirement to get correct timing information
+	 */
+	if (__event_sched_in(group_event, cpuctx, ctx)) {
+		pmu->cancel_txn(pmu);
 		return -EAGAIN;
 	}
 
@@ -714,29 +751,33 @@
 	 * Schedule in siblings as one group (if any):
 	 */
 	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
-		if (event_sched_in(event, cpuctx, ctx)) {
+		if (__event_sched_in(event, cpuctx, ctx)) {
 			partial_group = event;
 			goto group_error;
 		}
 	}
 
-	if (!txn || !pmu->commit_txn(pmu))
+	if (!pmu->commit_txn(pmu)) {
+		/* commit tstamp_running */
+		group_commit_event_sched_in(group_event, cpuctx, ctx);
 		return 0;
-
+	}
 group_error:
 	/*
 	 * Groups can be scheduled in as one unit only, so undo any
 	 * partial group before returning:
+	 *
+	 * use __event_sched_out() to avoid updating tstamp_stopped
+	 * because the event never actually ran
 	 */
 	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
 		if (event == partial_group)
 			break;
-		event_sched_out(event, cpuctx, ctx);
+		__event_sched_out(event, cpuctx, ctx);
 	}
-	event_sched_out(group_event, cpuctx, ctx);
+	__event_sched_out(group_event, cpuctx, ctx);
 
-	if (txn)
-		pmu->cancel_txn(pmu);
+	pmu->cancel_txn(pmu);
 
 	return -EAGAIN;
 }
@@ -789,10 +830,10 @@
  */
 static void __perf_install_in_context(void *info)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *leader = event->group_leader;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
 	/*
@@ -812,12 +853,6 @@
 	ctx->is_active = 1;
 	update_context_time(ctx);
 
-	/*
-	 * Protect the list operation against NMI by disabling the
-	 * events on a global level. NOP for non NMI based events.
-	 */
-	perf_disable();
-
 	add_event_to_ctx(event, ctx);
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
@@ -855,12 +890,7 @@
 		}
 	}
 
-	if (!err && !ctx->task && cpuctx->max_pertask)
-		cpuctx->max_pertask--;
-
- unlock:
-	perf_enable();
-
+unlock:
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -883,6 +913,8 @@
 {
 	struct task_struct *task = ctx->task;
 
+	event->ctx = ctx;
+
 	if (!task) {
 		/*
 		 * Per cpu events are installed via an smp call and
@@ -931,10 +963,12 @@
 
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	event->tstamp_enabled = ctx->time - event->total_time_enabled;
-	list_for_each_entry(sub, &event->sibling_list, group_entry)
-		if (sub->state >= PERF_EVENT_STATE_INACTIVE)
+	list_for_each_entry(sub, &event->sibling_list, group_entry) {
+		if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
 			sub->tstamp_enabled =
 				ctx->time - sub->total_time_enabled;
+		}
+	}
 }
 
 /*
@@ -943,9 +977,9 @@
 static void __perf_event_enable(void *info)
 {
 	struct perf_event *event = info;
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *leader = event->group_leader;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	int err;
 
 	/*
@@ -979,12 +1013,10 @@
 	if (!group_can_go_on(event, cpuctx, 1)) {
 		err = -EEXIST;
 	} else {
-		perf_disable();
 		if (event == leader)
 			err = group_sched_in(event, cpuctx, ctx);
 		else
 			err = event_sched_in(event, cpuctx, ctx);
-		perf_enable();
 	}
 
 	if (err) {
@@ -1000,7 +1032,7 @@
 		}
 	}
 
- unlock:
+unlock:
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -1041,7 +1073,7 @@
 	if (event->state == PERF_EVENT_STATE_ERROR)
 		event->state = PERF_EVENT_STATE_OFF;
 
- retry:
+retry:
 	raw_spin_unlock_irq(&ctx->lock);
 	task_oncpu_function_call(task, __perf_event_enable, event);
 
@@ -1061,7 +1093,7 @@
 	if (event->state == PERF_EVENT_STATE_OFF)
 		__perf_event_mark_enabled(event, ctx);
 
- out:
+out:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -1092,26 +1124,26 @@
 	struct perf_event *event;
 
 	raw_spin_lock(&ctx->lock);
+	perf_pmu_disable(ctx->pmu);
 	ctx->is_active = 0;
 	if (likely(!ctx->nr_events))
 		goto out;
 	update_context_time(ctx);
 
-	perf_disable();
 	if (!ctx->nr_active)
-		goto out_enable;
+		goto out;
 
-	if (event_type & EVENT_PINNED)
+	if (event_type & EVENT_PINNED) {
 		list_for_each_entry(event, &ctx->pinned_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
+	}
 
-	if (event_type & EVENT_FLEXIBLE)
+	if (event_type & EVENT_FLEXIBLE) {
 		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
-
- out_enable:
-	perf_enable();
- out:
+	}
+out:
+	perf_pmu_enable(ctx->pmu);
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -1209,34 +1241,25 @@
 	}
 }
 
-/*
- * Called from scheduler to remove the events of the current task,
- * with interrupts disabled.
- *
- * We stop each event and update the event value in event->count.
- *
- * This does not protect us against NMI, but disable()
- * sets the disabled bit in the control field of event _before_
- * accessing the event control register. If a NMI hits, then it will
- * not restart the event.
- */
-void perf_event_task_sched_out(struct task_struct *task,
-				 struct task_struct *next)
+void perf_event_context_sched_out(struct task_struct *task, int ctxn,
+				  struct task_struct *next)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_event_context *ctx = task->perf_event_ctxp[ctxn];
 	struct perf_event_context *next_ctx;
 	struct perf_event_context *parent;
+	struct perf_cpu_context *cpuctx;
 	int do_switch = 1;
 
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+	if (likely(!ctx))
+		return;
 
-	if (likely(!ctx || !cpuctx->task_ctx))
+	cpuctx = __get_cpu_context(ctx);
+	if (!cpuctx->task_ctx)
 		return;
 
 	rcu_read_lock();
 	parent = rcu_dereference(ctx->parent_ctx);
-	next_ctx = next->perf_event_ctxp;
+	next_ctx = next->perf_event_ctxp[ctxn];
 	if (parent && next_ctx &&
 	    rcu_dereference(next_ctx->parent_ctx) == parent) {
 		/*
@@ -1255,8 +1278,8 @@
 			 * XXX do we need a memory barrier of sorts
 			 * wrt to rcu_dereference() of perf_event_ctxp
 			 */
-			task->perf_event_ctxp = next_ctx;
-			next->perf_event_ctxp = ctx;
+			task->perf_event_ctxp[ctxn] = next_ctx;
+			next->perf_event_ctxp[ctxn] = ctx;
 			ctx->task = next;
 			next_ctx->task = task;
 			do_switch = 0;
@@ -1274,10 +1297,35 @@
 	}
 }
 
+#define for_each_task_context_nr(ctxn)					\
+	for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++)
+
+/*
+ * Called from scheduler to remove the events of the current task,
+ * with interrupts disabled.
+ *
+ * We stop each event and update the event value in event->count.
+ *
+ * This does not protect us against NMI, but disable()
+ * sets the disabled bit in the control field of event _before_
+ * accessing the event control register. If a NMI hits, then it will
+ * not restart the event.
+ */
+void __perf_event_task_sched_out(struct task_struct *task,
+				 struct task_struct *next)
+{
+	int ctxn;
+
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+
+	for_each_task_context_nr(ctxn)
+		perf_event_context_sched_out(task, ctxn, next);
+}
+
 static void task_ctx_sched_out(struct perf_event_context *ctx,
 			       enum event_type_t event_type)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	if (!cpuctx->task_ctx)
 		return;
@@ -1292,14 +1340,6 @@
 /*
  * Called with IRQs disabled
  */
-static void __perf_event_task_sched_out(struct perf_event_context *ctx)
-{
-	task_ctx_sched_out(ctx, EVENT_ALL);
-}
-
-/*
- * Called with IRQs disabled
- */
 static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 			      enum event_type_t event_type)
 {
@@ -1350,9 +1390,10 @@
 		if (event->cpu != -1 && event->cpu != smp_processor_id())
 			continue;
 
-		if (group_can_go_on(event, cpuctx, can_add_hw))
+		if (group_can_go_on(event, cpuctx, can_add_hw)) {
 			if (group_sched_in(event, cpuctx, ctx))
 				can_add_hw = 0;
+		}
 	}
 }
 
@@ -1368,8 +1409,6 @@
 
 	ctx->timestamp = perf_clock();
 
-	perf_disable();
-
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.
@@ -1381,8 +1420,7 @@
 	if (event_type & EVENT_FLEXIBLE)
 		ctx_flexible_sched_in(ctx, cpuctx);
 
-	perf_enable();
- out:
+out:
 	raw_spin_unlock(&ctx->lock);
 }
 
@@ -1394,43 +1432,28 @@
 	ctx_sched_in(ctx, cpuctx, event_type);
 }
 
-static void task_ctx_sched_in(struct task_struct *task,
+static void task_ctx_sched_in(struct perf_event_context *ctx,
 			      enum event_type_t event_type)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_cpu_context *cpuctx;
 
-	if (likely(!ctx))
-		return;
+       	cpuctx = __get_cpu_context(ctx);
 	if (cpuctx->task_ctx == ctx)
 		return;
+
 	ctx_sched_in(ctx, cpuctx, event_type);
 	cpuctx->task_ctx = ctx;
 }
-/*
- * Called from scheduler to add the events of the current task
- * with interrupts disabled.
- *
- * We restore the event value and then enable it.
- *
- * This does not protect us against NMI, but enable()
- * sets the enabled bit in the control field of event _before_
- * accessing the event control register. If a NMI hits, then it will
- * keep the event running.
- */
-void perf_event_task_sched_in(struct task_struct *task)
+
+void perf_event_context_sched_in(struct perf_event_context *ctx)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_cpu_context *cpuctx;
 
-	if (likely(!ctx))
-		return;
-
+	cpuctx = __get_cpu_context(ctx);
 	if (cpuctx->task_ctx == ctx)
 		return;
 
-	perf_disable();
-
+	perf_pmu_disable(ctx->pmu);
 	/*
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,
@@ -1444,7 +1467,37 @@
 
 	cpuctx->task_ctx = ctx;
 
-	perf_enable();
+	/*
+	 * Since these rotations are per-cpu, we need to ensure the
+	 * cpu-context we got scheduled on is actually rotating.
+	 */
+	perf_pmu_rotate_start(ctx->pmu);
+	perf_pmu_enable(ctx->pmu);
+}
+
+/*
+ * Called from scheduler to add the events of the current task
+ * with interrupts disabled.
+ *
+ * We restore the event value and then enable it.
+ *
+ * This does not protect us against NMI, but enable()
+ * sets the enabled bit in the control field of event _before_
+ * accessing the event control register. If a NMI hits, then it will
+ * keep the event running.
+ */
+void __perf_event_task_sched_in(struct task_struct *task)
+{
+	struct perf_event_context *ctx;
+	int ctxn;
+
+	for_each_task_context_nr(ctxn) {
+		ctx = task->perf_event_ctxp[ctxn];
+		if (likely(!ctx))
+			continue;
+
+		perf_event_context_sched_in(ctx);
+	}
 }
 
 #define MAX_INTERRUPTS (~0ULL)
@@ -1524,22 +1577,6 @@
 	return div64_u64(dividend, divisor);
 }
 
-static void perf_event_stop(struct perf_event *event)
-{
-	if (!event->pmu->stop)
-		return event->pmu->disable(event);
-
-	return event->pmu->stop(event);
-}
-
-static int perf_event_start(struct perf_event *event)
-{
-	if (!event->pmu->start)
-		return event->pmu->enable(event);
-
-	return event->pmu->start(event);
-}
-
 static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -1559,15 +1596,13 @@
 	hwc->sample_period = sample_period;
 
 	if (local64_read(&hwc->period_left) > 8*sample_period) {
-		perf_disable();
-		perf_event_stop(event);
+		event->pmu->stop(event, PERF_EF_UPDATE);
 		local64_set(&hwc->period_left, 0);
-		perf_event_start(event);
-		perf_enable();
+		event->pmu->start(event, PERF_EF_RELOAD);
 	}
 }
 
-static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
+static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
 {
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
@@ -1592,23 +1627,19 @@
 		 */
 		if (interrupts == MAX_INTERRUPTS) {
 			perf_log_throttle(event, 1);
-			perf_disable();
-			event->pmu->unthrottle(event);
-			perf_enable();
+			event->pmu->start(event, 0);
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
 			continue;
 
-		perf_disable();
 		event->pmu->read(event);
 		now = local64_read(&event->count);
 		delta = now - hwc->freq_count_stamp;
 		hwc->freq_count_stamp = now;
 
 		if (delta > 0)
-			perf_adjust_period(event, TICK_NSEC, delta);
-		perf_enable();
+			perf_adjust_period(event, period, delta);
 	}
 	raw_spin_unlock(&ctx->lock);
 }
@@ -1626,32 +1657,38 @@
 	raw_spin_unlock(&ctx->lock);
 }
 
-void perf_event_task_tick(struct task_struct *curr)
+/*
+ * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
+ * because they're strictly cpu affine and rotate_start is called with IRQs
+ * disabled, while rotate_context is called from IRQ context.
+ */
+static void perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
-	int rotate = 0;
+	u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC;
+	struct perf_event_context *ctx = NULL;
+	int rotate = 0, remove = 1;
 
-	if (!atomic_read(&nr_events))
-		return;
+	if (cpuctx->ctx.nr_events) {
+		remove = 0;
+		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
+			rotate = 1;
+	}
 
-	cpuctx = &__get_cpu_var(perf_cpu_context);
-	if (cpuctx->ctx.nr_events &&
-	    cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
-		rotate = 1;
+	ctx = cpuctx->task_ctx;
+	if (ctx && ctx->nr_events) {
+		remove = 0;
+		if (ctx->nr_events != ctx->nr_active)
+			rotate = 1;
+	}
 
-	ctx = curr->perf_event_ctxp;
-	if (ctx && ctx->nr_events && ctx->nr_events != ctx->nr_active)
-		rotate = 1;
-
-	perf_ctx_adjust_freq(&cpuctx->ctx);
+	perf_pmu_disable(cpuctx->ctx.pmu);
+	perf_ctx_adjust_freq(&cpuctx->ctx, interval);
 	if (ctx)
-		perf_ctx_adjust_freq(ctx);
+		perf_ctx_adjust_freq(ctx, interval);
 
 	if (!rotate)
-		return;
+		goto done;
 
-	perf_disable();
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
 		task_ctx_sched_out(ctx, EVENT_FLEXIBLE);
@@ -1662,8 +1699,27 @@
 
 	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
-		task_ctx_sched_in(curr, EVENT_FLEXIBLE);
-	perf_enable();
+		task_ctx_sched_in(ctx, EVENT_FLEXIBLE);
+
+done:
+	if (remove)
+		list_del_init(&cpuctx->rotation_list);
+
+	perf_pmu_enable(cpuctx->ctx.pmu);
+}
+
+void perf_event_task_tick(void)
+{
+	struct list_head *head = &__get_cpu_var(rotation_list);
+	struct perf_cpu_context *cpuctx, *tmp;
+
+	WARN_ON(!irqs_disabled());
+
+	list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) {
+		if (cpuctx->jiffies_interval == 1 ||
+				!(jiffies % cpuctx->jiffies_interval))
+			perf_rotate_context(cpuctx);
+	}
 }
 
 static int event_enable_on_exec(struct perf_event *event,
@@ -1685,20 +1741,18 @@
  * Enable all of a task's events that have been marked enable-on-exec.
  * This expects task == current.
  */
-static void perf_event_enable_on_exec(struct task_struct *task)
+static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 {
-	struct perf_event_context *ctx;
 	struct perf_event *event;
 	unsigned long flags;
 	int enabled = 0;
 	int ret;
 
 	local_irq_save(flags);
-	ctx = task->perf_event_ctxp;
 	if (!ctx || !ctx->nr_events)
 		goto out;
 
-	__perf_event_task_sched_out(ctx);
+	task_ctx_sched_out(ctx, EVENT_ALL);
 
 	raw_spin_lock(&ctx->lock);
 
@@ -1722,8 +1776,8 @@
 
 	raw_spin_unlock(&ctx->lock);
 
-	perf_event_task_sched_in(task);
- out:
+	perf_event_context_sched_in(ctx);
+out:
 	local_irq_restore(flags);
 }
 
@@ -1732,9 +1786,9 @@
  */
 static void __perf_event_read(void *info)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -1773,7 +1827,13 @@
 		unsigned long flags;
 
 		raw_spin_lock_irqsave(&ctx->lock, flags);
-		update_context_time(ctx);
+		/*
+		 * may read while context is not active
+		 * (e.g., thread is blocked), in that case
+		 * we cannot update context time
+		 */
+		if (ctx->is_active)
+			update_context_time(ctx);
 		update_event_times(event);
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
@@ -1782,11 +1842,219 @@
 }
 
 /*
+ * Callchain support
+ */
+
+struct callchain_cpus_entries {
+	struct rcu_head			rcu_head;
+	struct perf_callchain_entry	*cpu_entries[0];
+};
+
+static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
+static atomic_t nr_callchain_events;
+static DEFINE_MUTEX(callchain_mutex);
+struct callchain_cpus_entries *callchain_cpus_entries;
+
+
+__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs)
+{
+}
+
+__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs)
+{
+}
+
+static void release_callchain_buffers_rcu(struct rcu_head *head)
+{
+	struct callchain_cpus_entries *entries;
+	int cpu;
+
+	entries = container_of(head, struct callchain_cpus_entries, rcu_head);
+
+	for_each_possible_cpu(cpu)
+		kfree(entries->cpu_entries[cpu]);
+
+	kfree(entries);
+}
+
+static void release_callchain_buffers(void)
+{
+	struct callchain_cpus_entries *entries;
+
+	entries = callchain_cpus_entries;
+	rcu_assign_pointer(callchain_cpus_entries, NULL);
+	call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
+}
+
+static int alloc_callchain_buffers(void)
+{
+	int cpu;
+	int size;
+	struct callchain_cpus_entries *entries;
+
+	/*
+	 * We can't use the percpu allocation API for data that can be
+	 * accessed from NMI. Use a temporary manual per cpu allocation
+	 * until that gets sorted out.
+	 */
+	size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) *
+		num_possible_cpus();
+
+	entries = kzalloc(size, GFP_KERNEL);
+	if (!entries)
+		return -ENOMEM;
+
+	size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
+
+	for_each_possible_cpu(cpu) {
+		entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
+							 cpu_to_node(cpu));
+		if (!entries->cpu_entries[cpu])
+			goto fail;
+	}
+
+	rcu_assign_pointer(callchain_cpus_entries, entries);
+
+	return 0;
+
+fail:
+	for_each_possible_cpu(cpu)
+		kfree(entries->cpu_entries[cpu]);
+	kfree(entries);
+
+	return -ENOMEM;
+}
+
+static int get_callchain_buffers(void)
+{
+	int err = 0;
+	int count;
+
+	mutex_lock(&callchain_mutex);
+
+	count = atomic_inc_return(&nr_callchain_events);
+	if (WARN_ON_ONCE(count < 1)) {
+		err = -EINVAL;
+		goto exit;
+	}
+
+	if (count > 1) {
+		/* If the allocation failed, give up */
+		if (!callchain_cpus_entries)
+			err = -ENOMEM;
+		goto exit;
+	}
+
+	err = alloc_callchain_buffers();
+	if (err)
+		release_callchain_buffers();
+exit:
+	mutex_unlock(&callchain_mutex);
+
+	return err;
+}
+
+static void put_callchain_buffers(void)
+{
+	if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
+		release_callchain_buffers();
+		mutex_unlock(&callchain_mutex);
+	}
+}
+
+static int get_recursion_context(int *recursion)
+{
+	int rctx;
+
+	if (in_nmi())
+		rctx = 3;
+	else if (in_irq())
+		rctx = 2;
+	else if (in_softirq())
+		rctx = 1;
+	else
+		rctx = 0;
+
+	if (recursion[rctx])
+		return -1;
+
+	recursion[rctx]++;
+	barrier();
+
+	return rctx;
+}
+
+static inline void put_recursion_context(int *recursion, int rctx)
+{
+	barrier();
+	recursion[rctx]--;
+}
+
+static struct perf_callchain_entry *get_callchain_entry(int *rctx)
+{
+	int cpu;
+	struct callchain_cpus_entries *entries;
+
+	*rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
+	if (*rctx == -1)
+		return NULL;
+
+	entries = rcu_dereference(callchain_cpus_entries);
+	if (!entries)
+		return NULL;
+
+	cpu = smp_processor_id();
+
+	return &entries->cpu_entries[cpu][*rctx];
+}
+
+static void
+put_callchain_entry(int rctx)
+{
+	put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
+}
+
+static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	int rctx;
+	struct perf_callchain_entry *entry;
+
+
+	entry = get_callchain_entry(&rctx);
+	if (rctx == -1)
+		return NULL;
+
+	if (!entry)
+		goto exit_put;
+
+	entry->nr = 0;
+
+	if (!user_mode(regs)) {
+		perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
+		perf_callchain_kernel(entry, regs);
+		if (current->mm)
+			regs = task_pt_regs(current);
+		else
+			regs = NULL;
+	}
+
+	if (regs) {
+		perf_callchain_store(entry, PERF_CONTEXT_USER);
+		perf_callchain_user(entry, regs);
+	}
+
+exit_put:
+	put_callchain_entry(rctx);
+
+	return entry;
+}
+
+/*
  * Initialize the perf_event context in a task_struct:
  */
-static void
-__perf_event_init_context(struct perf_event_context *ctx,
-			    struct task_struct *task)
+static void __perf_event_init_context(struct perf_event_context *ctx)
 {
 	raw_spin_lock_init(&ctx->lock);
 	mutex_init(&ctx->mutex);
@@ -1794,45 +2062,38 @@
 	INIT_LIST_HEAD(&ctx->flexible_groups);
 	INIT_LIST_HEAD(&ctx->event_list);
 	atomic_set(&ctx->refcount, 1);
-	ctx->task = task;
 }
 
-static struct perf_event_context *find_get_context(pid_t pid, int cpu)
+static struct perf_event_context *
+alloc_perf_context(struct pmu *pmu, struct task_struct *task)
 {
 	struct perf_event_context *ctx;
-	struct perf_cpu_context *cpuctx;
+
+	ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+	if (!ctx)
+		return NULL;
+
+	__perf_event_init_context(ctx);
+	if (task) {
+		ctx->task = task;
+		get_task_struct(task);
+	}
+	ctx->pmu = pmu;
+
+	return ctx;
+}
+
+static struct task_struct *
+find_lively_task_by_vpid(pid_t vpid)
+{
 	struct task_struct *task;
-	unsigned long flags;
 	int err;
 
-	if (pid == -1 && cpu != -1) {
-		/* Must be root to operate on a CPU event: */
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return ERR_PTR(-EACCES);
-
-		if (cpu < 0 || cpu >= nr_cpumask_bits)
-			return ERR_PTR(-EINVAL);
-
-		/*
-		 * We could be clever and allow to attach a event to an
-		 * offline CPU and activate it when the CPU comes up, but
-		 * that's for later.
-		 */
-		if (!cpu_online(cpu))
-			return ERR_PTR(-ENODEV);
-
-		cpuctx = &per_cpu(perf_cpu_context, cpu);
-		ctx = &cpuctx->ctx;
-		get_ctx(ctx);
-
-		return ctx;
-	}
-
 	rcu_read_lock();
-	if (!pid)
+	if (!vpid)
 		task = current;
 	else
-		task = find_task_by_vpid(pid);
+		task = find_task_by_vpid(vpid);
 	if (task)
 		get_task_struct(task);
 	rcu_read_unlock();
@@ -1852,36 +2113,78 @@
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto errout;
 
- retry:
-	ctx = perf_lock_task_context(task, &flags);
+	return task;
+errout:
+	put_task_struct(task);
+	return ERR_PTR(err);
+
+}
+
+static struct perf_event_context *
+find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
+{
+	struct perf_event_context *ctx;
+	struct perf_cpu_context *cpuctx;
+	unsigned long flags;
+	int ctxn, err;
+
+	if (!task && cpu != -1) {
+		/* Must be root to operate on a CPU event: */
+		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return ERR_PTR(-EACCES);
+
+		if (cpu < 0 || cpu >= nr_cpumask_bits)
+			return ERR_PTR(-EINVAL);
+
+		/*
+		 * We could be clever and allow to attach a event to an
+		 * offline CPU and activate it when the CPU comes up, but
+		 * that's for later.
+		 */
+		if (!cpu_online(cpu))
+			return ERR_PTR(-ENODEV);
+
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+		ctx = &cpuctx->ctx;
+		get_ctx(ctx);
+
+		return ctx;
+	}
+
+	err = -EINVAL;
+	ctxn = pmu->task_ctx_nr;
+	if (ctxn < 0)
+		goto errout;
+
+retry:
+	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
 		unclone_ctx(ctx);
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	}
 
 	if (!ctx) {
-		ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+		ctx = alloc_perf_context(pmu, task);
 		err = -ENOMEM;
 		if (!ctx)
 			goto errout;
-		__perf_event_init_context(ctx, task);
+
 		get_ctx(ctx);
-		if (cmpxchg(&task->perf_event_ctxp, NULL, ctx)) {
+
+		if (cmpxchg(&task->perf_event_ctxp[ctxn], NULL, ctx)) {
 			/*
 			 * We raced with some other task; use
 			 * the context they set.
 			 */
+			put_task_struct(task);
 			kfree(ctx);
 			goto retry;
 		}
-		get_task_struct(task);
 	}
 
-	put_task_struct(task);
 	return ctx;
 
- errout:
-	put_task_struct(task);
+errout:
 	return ERR_PTR(err);
 }
 
@@ -1898,21 +2201,23 @@
 	kfree(event);
 }
 
-static void perf_pending_sync(struct perf_event *event);
 static void perf_buffer_put(struct perf_buffer *buffer);
 
 static void free_event(struct perf_event *event)
 {
-	perf_pending_sync(event);
+	irq_work_sync(&event->pending);
 
 	if (!event->parent) {
-		atomic_dec(&nr_events);
+		if (event->attach_state & PERF_ATTACH_TASK)
+			jump_label_dec(&perf_task_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_dec(&nr_mmap_events);
 		if (event->attr.comm)
 			atomic_dec(&nr_comm_events);
 		if (event->attr.task)
 			atomic_dec(&nr_task_events);
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			put_callchain_buffers();
 	}
 
 	if (event->buffer) {
@@ -1923,7 +2228,9 @@
 	if (event->destroy)
 		event->destroy(event);
 
-	put_ctx(event->ctx);
+	if (event->ctx)
+		put_ctx(event->ctx);
+
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
 
@@ -2342,6 +2649,9 @@
 
 static int perf_event_index(struct perf_event *event)
 {
+	if (event->hw.state & PERF_HES_STOPPED)
+		return 0;
+
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
 		return 0;
 
@@ -2845,16 +3155,7 @@
 	}
 }
 
-/*
- * Pending wakeups
- *
- * Handle the case where we need to wakeup up from NMI (or rq->lock) context.
- *
- * The NMI bit means we cannot possibly take locks. Therefore, maintain a
- * single linked list and use cmpxchg() to add entries lockless.
- */
-
-static void perf_pending_event(struct perf_pending_entry *entry)
+static void perf_pending_event(struct irq_work *entry)
 {
 	struct perf_event *event = container_of(entry,
 			struct perf_event, pending);
@@ -2870,99 +3171,6 @@
 	}
 }
 
-#define PENDING_TAIL ((struct perf_pending_entry *)-1UL)
-
-static DEFINE_PER_CPU(struct perf_pending_entry *, perf_pending_head) = {
-	PENDING_TAIL,
-};
-
-static void perf_pending_queue(struct perf_pending_entry *entry,
-			       void (*func)(struct perf_pending_entry *))
-{
-	struct perf_pending_entry **head;
-
-	if (cmpxchg(&entry->next, NULL, PENDING_TAIL) != NULL)
-		return;
-
-	entry->func = func;
-
-	head = &get_cpu_var(perf_pending_head);
-
-	do {
-		entry->next = *head;
-	} while (cmpxchg(head, entry->next, entry) != entry->next);
-
-	set_perf_event_pending();
-
-	put_cpu_var(perf_pending_head);
-}
-
-static int __perf_pending_run(void)
-{
-	struct perf_pending_entry *list;
-	int nr = 0;
-
-	list = xchg(&__get_cpu_var(perf_pending_head), PENDING_TAIL);
-	while (list != PENDING_TAIL) {
-		void (*func)(struct perf_pending_entry *);
-		struct perf_pending_entry *entry = list;
-
-		list = list->next;
-
-		func = entry->func;
-		entry->next = NULL;
-		/*
-		 * Ensure we observe the unqueue before we issue the wakeup,
-		 * so that we won't be waiting forever.
-		 * -- see perf_not_pending().
-		 */
-		smp_wmb();
-
-		func(entry);
-		nr++;
-	}
-
-	return nr;
-}
-
-static inline int perf_not_pending(struct perf_event *event)
-{
-	/*
-	 * If we flush on whatever cpu we run, there is a chance we don't
-	 * need to wait.
-	 */
-	get_cpu();
-	__perf_pending_run();
-	put_cpu();
-
-	/*
-	 * Ensure we see the proper queue state before going to sleep
-	 * so that we do not miss the wakeup. -- see perf_pending_handle()
-	 */
-	smp_rmb();
-	return event->pending.next == NULL;
-}
-
-static void perf_pending_sync(struct perf_event *event)
-{
-	wait_event(event->waitq, perf_not_pending(event));
-}
-
-void perf_event_do_pending(void)
-{
-	__perf_pending_run();
-}
-
-/*
- * Callchain support -- arch specific
- */
-
-__weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	return NULL;
-}
-
-
 /*
  * We assume there is only KVM supporting the callbacks.
  * Later on, we might change it to a list if there is
@@ -3012,8 +3220,7 @@
 
 	if (handle->nmi) {
 		handle->event->pending_wakeup = 1;
-		perf_pending_queue(&handle->event->pending,
-				   perf_pending_event);
+		irq_work_queue(&handle->event->pending);
 	} else
 		perf_event_wakeup(handle->event);
 }
@@ -3069,7 +3276,7 @@
 	if (handle->wakeup != local_read(&buffer->wakeup))
 		perf_output_wakeup(handle);
 
- out:
+out:
 	preempt_enable();
 }
 
@@ -3457,14 +3664,20 @@
 	struct perf_output_handle handle;
 	struct perf_event_header header;
 
+	/* protect the callchain buffers */
+	rcu_read_lock();
+
 	perf_prepare_sample(&header, data, event, regs);
 
 	if (perf_output_begin(&handle, event, header.size, nmi, 1))
-		return;
+		goto exit;
 
 	perf_output_sample(&handle, &header, data, event);
 
 	perf_output_end(&handle);
+
+exit:
+	rcu_read_unlock();
 }
 
 /*
@@ -3578,16 +3791,27 @@
 static void perf_event_task_event(struct perf_task_event *task_event)
 {
 	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx = task_event->task_ctx;
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+	int ctxn;
 
 	rcu_read_lock();
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_event_task_ctx(&cpuctx->ctx, task_event);
-	if (!ctx)
-		ctx = rcu_dereference(current->perf_event_ctxp);
-	if (ctx)
-		perf_event_task_ctx(ctx, task_event);
-	put_cpu_var(perf_cpu_context);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		perf_event_task_ctx(&cpuctx->ctx, task_event);
+
+		ctx = task_event->task_ctx;
+		if (!ctx) {
+			ctxn = pmu->task_ctx_nr;
+			if (ctxn < 0)
+				goto next;
+			ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		}
+		if (ctx)
+			perf_event_task_ctx(ctx, task_event);
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
+	}
 	rcu_read_unlock();
 }
 
@@ -3692,8 +3916,10 @@
 {
 	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx;
-	unsigned int size;
 	char comm[TASK_COMM_LEN];
+	unsigned int size;
+	struct pmu *pmu;
+	int ctxn;
 
 	memset(comm, 0, sizeof(comm));
 	strlcpy(comm, comm_event->task->comm, sizeof(comm));
@@ -3705,21 +3931,36 @@
 	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
 
 	rcu_read_lock();
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_event_comm_ctx(&cpuctx->ctx, comm_event);
-	ctx = rcu_dereference(current->perf_event_ctxp);
-	if (ctx)
-		perf_event_comm_ctx(ctx, comm_event);
-	put_cpu_var(perf_cpu_context);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
+
+		ctxn = pmu->task_ctx_nr;
+		if (ctxn < 0)
+			goto next;
+
+		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		if (ctx)
+			perf_event_comm_ctx(ctx, comm_event);
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
+	}
 	rcu_read_unlock();
 }
 
 void perf_event_comm(struct task_struct *task)
 {
 	struct perf_comm_event comm_event;
+	struct perf_event_context *ctx;
+	int ctxn;
 
-	if (task->perf_event_ctxp)
-		perf_event_enable_on_exec(task);
+	for_each_task_context_nr(ctxn) {
+		ctx = task->perf_event_ctxp[ctxn];
+		if (!ctx)
+			continue;
+
+		perf_event_enable_on_exec(ctx);
+	}
 
 	if (!atomic_read(&nr_comm_events))
 		return;
@@ -3821,6 +4062,8 @@
 	char tmp[16];
 	char *buf = NULL;
 	const char *name;
+	struct pmu *pmu;
+	int ctxn;
 
 	memset(tmp, 0, sizeof(tmp));
 
@@ -3873,12 +4116,23 @@
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
 	rcu_read_lock();
-	cpuctx = &get_cpu_var(perf_cpu_context);
-	perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, vma->vm_flags & VM_EXEC);
-	ctx = rcu_dereference(current->perf_event_ctxp);
-	if (ctx)
-		perf_event_mmap_ctx(ctx, mmap_event, vma->vm_flags & VM_EXEC);
-	put_cpu_var(perf_cpu_context);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
+					vma->vm_flags & VM_EXEC);
+
+		ctxn = pmu->task_ctx_nr;
+		if (ctxn < 0)
+			goto next;
+
+		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		if (ctx) {
+			perf_event_mmap_ctx(ctx, mmap_event,
+					vma->vm_flags & VM_EXEC);
+		}
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
+	}
 	rcu_read_unlock();
 
 	kfree(buf);
@@ -3960,8 +4214,6 @@
 	struct hw_perf_event *hwc = &event->hw;
 	int ret = 0;
 
-	throttle = (throttle && event->pmu->unthrottle != NULL);
-
 	if (!throttle) {
 		hwc->interrupts++;
 	} else {
@@ -4004,8 +4256,7 @@
 		event->pending_kill = POLL_HUP;
 		if (nmi) {
 			event->pending_disable = 1;
-			perf_pending_queue(&event->pending,
-					   perf_pending_event);
+			irq_work_queue(&event->pending);
 		} else
 			perf_event_disable(event);
 	}
@@ -4029,6 +4280,17 @@
  * Generic software event infrastructure
  */
 
+struct swevent_htable {
+	struct swevent_hlist		*swevent_hlist;
+	struct mutex			hlist_mutex;
+	int				hlist_refcount;
+
+	/* Recursion avoidance in each contexts */
+	int				recursion[PERF_NR_CONTEXTS];
+};
+
+static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
+
 /*
  * We directly increment event->count and keep a second value in
  * event->hw.period_left to count intervals. This period event
@@ -4086,7 +4348,7 @@
 	}
 }
 
-static void perf_swevent_add(struct perf_event *event, u64 nr,
+static void perf_swevent_event(struct perf_event *event, u64 nr,
 			       int nmi, struct perf_sample_data *data,
 			       struct pt_regs *regs)
 {
@@ -4112,6 +4374,9 @@
 static int perf_exclude_event(struct perf_event *event,
 			      struct pt_regs *regs)
 {
+	if (event->hw.state & PERF_HES_STOPPED)
+		return 0;
+
 	if (regs) {
 		if (event->attr.exclude_user && user_mode(regs))
 			return 1;
@@ -4158,11 +4423,11 @@
 
 /* For the read side: events when they trigger */
 static inline struct hlist_head *
-find_swevent_head_rcu(struct perf_cpu_context *ctx, u64 type, u32 event_id)
+find_swevent_head_rcu(struct swevent_htable *swhash, u64 type, u32 event_id)
 {
 	struct swevent_hlist *hlist;
 
-	hlist = rcu_dereference(ctx->swevent_hlist);
+	hlist = rcu_dereference(swhash->swevent_hlist);
 	if (!hlist)
 		return NULL;
 
@@ -4171,7 +4436,7 @@
 
 /* For the event head insertion and removal in the hlist */
 static inline struct hlist_head *
-find_swevent_head(struct perf_cpu_context *ctx, struct perf_event *event)
+find_swevent_head(struct swevent_htable *swhash, struct perf_event *event)
 {
 	struct swevent_hlist *hlist;
 	u32 event_id = event->attr.config;
@@ -4182,7 +4447,7 @@
 	 * and release. Which makes the protected version suitable here.
 	 * The context lock guarantees that.
 	 */
-	hlist = rcu_dereference_protected(ctx->swevent_hlist,
+	hlist = rcu_dereference_protected(swhash->swevent_hlist,
 					  lockdep_is_held(&event->ctx->lock));
 	if (!hlist)
 		return NULL;
@@ -4195,23 +4460,19 @@
 				    struct perf_sample_data *data,
 				    struct pt_regs *regs)
 {
-	struct perf_cpu_context *cpuctx;
+	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
 	struct perf_event *event;
 	struct hlist_node *node;
 	struct hlist_head *head;
 
-	cpuctx = &__get_cpu_var(perf_cpu_context);
-
 	rcu_read_lock();
-
-	head = find_swevent_head_rcu(cpuctx, type, event_id);
-
+	head = find_swevent_head_rcu(swhash, type, event_id);
 	if (!head)
 		goto end;
 
 	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_swevent_match(event, type, event_id, data, regs))
-			perf_swevent_add(event, nr, nmi, data, regs);
+			perf_swevent_event(event, nr, nmi, data, regs);
 	}
 end:
 	rcu_read_unlock();
@@ -4219,33 +4480,17 @@
 
 int perf_swevent_get_recursion_context(void)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	int rctx;
+	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
 
-	if (in_nmi())
-		rctx = 3;
-	else if (in_irq())
-		rctx = 2;
-	else if (in_softirq())
-		rctx = 1;
-	else
-		rctx = 0;
-
-	if (cpuctx->recursion[rctx])
-		return -1;
-
-	cpuctx->recursion[rctx]++;
-	barrier();
-
-	return rctx;
+	return get_recursion_context(swhash->recursion);
 }
 EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
 void inline perf_swevent_put_recursion_context(int rctx)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	barrier();
-	cpuctx->recursion[rctx]--;
+	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+
+	put_recursion_context(swhash->recursion, rctx);
 }
 
 void __perf_sw_event(u32 event_id, u64 nr, int nmi,
@@ -4271,20 +4516,20 @@
 {
 }
 
-static int perf_swevent_enable(struct perf_event *event)
+static int perf_swevent_add(struct perf_event *event, int flags)
 {
+	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
 	struct hw_perf_event *hwc = &event->hw;
-	struct perf_cpu_context *cpuctx;
 	struct hlist_head *head;
 
-	cpuctx = &__get_cpu_var(perf_cpu_context);
-
 	if (hwc->sample_period) {
 		hwc->last_period = hwc->sample_period;
 		perf_swevent_set_period(event);
 	}
 
-	head = find_swevent_head(cpuctx, event);
+	hwc->state = !(flags & PERF_EF_START);
+
+	head = find_swevent_head(swhash, event);
 	if (WARN_ON_ONCE(!head))
 		return -EINVAL;
 
@@ -4293,202 +4538,27 @@
 	return 0;
 }
 
-static void perf_swevent_disable(struct perf_event *event)
+static void perf_swevent_del(struct perf_event *event, int flags)
 {
 	hlist_del_rcu(&event->hlist_entry);
 }
 
-static void perf_swevent_void(struct perf_event *event)
+static void perf_swevent_start(struct perf_event *event, int flags)
 {
+	event->hw.state = 0;
 }
 
-static int perf_swevent_int(struct perf_event *event)
+static void perf_swevent_stop(struct perf_event *event, int flags)
 {
-	return 0;
+	event->hw.state = PERF_HES_STOPPED;
 }
 
-static const struct pmu perf_ops_generic = {
-	.enable		= perf_swevent_enable,
-	.disable	= perf_swevent_disable,
-	.start		= perf_swevent_int,
-	.stop		= perf_swevent_void,
-	.read		= perf_swevent_read,
-	.unthrottle	= perf_swevent_void, /* hwc->interrupts already reset */
-};
-
-/*
- * hrtimer based swevent callback
- */
-
-static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
-{
-	enum hrtimer_restart ret = HRTIMER_RESTART;
-	struct perf_sample_data data;
-	struct pt_regs *regs;
-	struct perf_event *event;
-	u64 period;
-
-	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
-	event->pmu->read(event);
-
-	perf_sample_data_init(&data, 0);
-	data.period = event->hw.last_period;
-	regs = get_irq_regs();
-
-	if (regs && !perf_exclude_event(event, regs)) {
-		if (!(event->attr.exclude_idle && current->pid == 0))
-			if (perf_event_overflow(event, 0, &data, regs))
-				ret = HRTIMER_NORESTART;
-	}
-
-	period = max_t(u64, 10000, event->hw.sample_period);
-	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
-
-	return ret;
-}
-
-static void perf_swevent_start_hrtimer(struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hwc->hrtimer.function = perf_swevent_hrtimer;
-	if (hwc->sample_period) {
-		u64 period;
-
-		if (hwc->remaining) {
-			if (hwc->remaining < 0)
-				period = 10000;
-			else
-				period = hwc->remaining;
-			hwc->remaining = 0;
-		} else {
-			period = max_t(u64, 10000, hwc->sample_period);
-		}
-		__hrtimer_start_range_ns(&hwc->hrtimer,
-				ns_to_ktime(period), 0,
-				HRTIMER_MODE_REL, 0);
-	}
-}
-
-static void perf_swevent_cancel_hrtimer(struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (hwc->sample_period) {
-		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
-		hwc->remaining = ktime_to_ns(remaining);
-
-		hrtimer_cancel(&hwc->hrtimer);
-	}
-}
-
-/*
- * Software event: cpu wall time clock
- */
-
-static void cpu_clock_perf_event_update(struct perf_event *event)
-{
-	int cpu = raw_smp_processor_id();
-	s64 prev;
-	u64 now;
-
-	now = cpu_clock(cpu);
-	prev = local64_xchg(&event->hw.prev_count, now);
-	local64_add(now - prev, &event->count);
-}
-
-static int cpu_clock_perf_event_enable(struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	int cpu = raw_smp_processor_id();
-
-	local64_set(&hwc->prev_count, cpu_clock(cpu));
-	perf_swevent_start_hrtimer(event);
-
-	return 0;
-}
-
-static void cpu_clock_perf_event_disable(struct perf_event *event)
-{
-	perf_swevent_cancel_hrtimer(event);
-	cpu_clock_perf_event_update(event);
-}
-
-static void cpu_clock_perf_event_read(struct perf_event *event)
-{
-	cpu_clock_perf_event_update(event);
-}
-
-static const struct pmu perf_ops_cpu_clock = {
-	.enable		= cpu_clock_perf_event_enable,
-	.disable	= cpu_clock_perf_event_disable,
-	.read		= cpu_clock_perf_event_read,
-};
-
-/*
- * Software event: task time clock
- */
-
-static void task_clock_perf_event_update(struct perf_event *event, u64 now)
-{
-	u64 prev;
-	s64 delta;
-
-	prev = local64_xchg(&event->hw.prev_count, now);
-	delta = now - prev;
-	local64_add(delta, &event->count);
-}
-
-static int task_clock_perf_event_enable(struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	u64 now;
-
-	now = event->ctx->time;
-
-	local64_set(&hwc->prev_count, now);
-
-	perf_swevent_start_hrtimer(event);
-
-	return 0;
-}
-
-static void task_clock_perf_event_disable(struct perf_event *event)
-{
-	perf_swevent_cancel_hrtimer(event);
-	task_clock_perf_event_update(event, event->ctx->time);
-
-}
-
-static void task_clock_perf_event_read(struct perf_event *event)
-{
-	u64 time;
-
-	if (!in_nmi()) {
-		update_context_time(event->ctx);
-		time = event->ctx->time;
-	} else {
-		u64 now = perf_clock();
-		u64 delta = now - event->ctx->timestamp;
-		time = event->ctx->time + delta;
-	}
-
-	task_clock_perf_event_update(event, time);
-}
-
-static const struct pmu perf_ops_task_clock = {
-	.enable		= task_clock_perf_event_enable,
-	.disable	= task_clock_perf_event_disable,
-	.read		= task_clock_perf_event_read,
-};
-
 /* Deref the hlist from the update side */
 static inline struct swevent_hlist *
-swevent_hlist_deref(struct perf_cpu_context *cpuctx)
+swevent_hlist_deref(struct swevent_htable *swhash)
 {
-	return rcu_dereference_protected(cpuctx->swevent_hlist,
-					 lockdep_is_held(&cpuctx->hlist_mutex));
+	return rcu_dereference_protected(swhash->swevent_hlist,
+					 lockdep_is_held(&swhash->hlist_mutex));
 }
 
 static void swevent_hlist_release_rcu(struct rcu_head *rcu_head)
@@ -4499,27 +4569,27 @@
 	kfree(hlist);
 }
 
-static void swevent_hlist_release(struct perf_cpu_context *cpuctx)
+static void swevent_hlist_release(struct swevent_htable *swhash)
 {
-	struct swevent_hlist *hlist = swevent_hlist_deref(cpuctx);
+	struct swevent_hlist *hlist = swevent_hlist_deref(swhash);
 
 	if (!hlist)
 		return;
 
-	rcu_assign_pointer(cpuctx->swevent_hlist, NULL);
+	rcu_assign_pointer(swhash->swevent_hlist, NULL);
 	call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu);
 }
 
 static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
 {
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
-	mutex_lock(&cpuctx->hlist_mutex);
+	mutex_lock(&swhash->hlist_mutex);
 
-	if (!--cpuctx->hlist_refcount)
-		swevent_hlist_release(cpuctx);
+	if (!--swhash->hlist_refcount)
+		swevent_hlist_release(swhash);
 
-	mutex_unlock(&cpuctx->hlist_mutex);
+	mutex_unlock(&swhash->hlist_mutex);
 }
 
 static void swevent_hlist_put(struct perf_event *event)
@@ -4537,12 +4607,12 @@
 
 static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
 {
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
+	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 	int err = 0;
 
-	mutex_lock(&cpuctx->hlist_mutex);
+	mutex_lock(&swhash->hlist_mutex);
 
-	if (!swevent_hlist_deref(cpuctx) && cpu_online(cpu)) {
+	if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
@@ -4550,11 +4620,11 @@
 			err = -ENOMEM;
 			goto exit;
 		}
-		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
+		rcu_assign_pointer(swhash->swevent_hlist, hlist);
 	}
-	cpuctx->hlist_refcount++;
- exit:
-	mutex_unlock(&cpuctx->hlist_mutex);
+	swhash->hlist_refcount++;
+exit:
+	mutex_unlock(&swhash->hlist_mutex);
 
 	return err;
 }
@@ -4578,7 +4648,7 @@
 	put_online_cpus();
 
 	return 0;
- fail:
+fail:
 	for_each_possible_cpu(cpu) {
 		if (cpu == failed_cpu)
 			break;
@@ -4589,17 +4659,64 @@
 	return err;
 }
 
-#ifdef CONFIG_EVENT_TRACING
+atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
-static const struct pmu perf_ops_tracepoint = {
-	.enable		= perf_trace_enable,
-	.disable	= perf_trace_disable,
-	.start		= perf_swevent_int,
-	.stop		= perf_swevent_void,
+static void sw_perf_event_destroy(struct perf_event *event)
+{
+	u64 event_id = event->attr.config;
+
+	WARN_ON(event->parent);
+
+	jump_label_dec(&perf_swevent_enabled[event_id]);
+	swevent_hlist_put(event);
+}
+
+static int perf_swevent_init(struct perf_event *event)
+{
+	int event_id = event->attr.config;
+
+	if (event->attr.type != PERF_TYPE_SOFTWARE)
+		return -ENOENT;
+
+	switch (event_id) {
+	case PERF_COUNT_SW_CPU_CLOCK:
+	case PERF_COUNT_SW_TASK_CLOCK:
+		return -ENOENT;
+
+	default:
+		break;
+	}
+
+	if (event_id > PERF_COUNT_SW_MAX)
+		return -ENOENT;
+
+	if (!event->parent) {
+		int err;
+
+		err = swevent_hlist_get(event);
+		if (err)
+			return err;
+
+		jump_label_inc(&perf_swevent_enabled[event_id]);
+		event->destroy = sw_perf_event_destroy;
+	}
+
+	return 0;
+}
+
+static struct pmu perf_swevent = {
+	.task_ctx_nr	= perf_sw_context,
+
+	.event_init	= perf_swevent_init,
+	.add		= perf_swevent_add,
+	.del		= perf_swevent_del,
+	.start		= perf_swevent_start,
+	.stop		= perf_swevent_stop,
 	.read		= perf_swevent_read,
-	.unthrottle	= perf_swevent_void,
 };
 
+#ifdef CONFIG_EVENT_TRACING
+
 static int perf_tp_filter_match(struct perf_event *event,
 				struct perf_sample_data *data)
 {
@@ -4643,7 +4760,7 @@
 
 	hlist_for_each_entry_rcu(event, node, head, hlist_entry) {
 		if (perf_tp_event_match(event, &data, regs))
-			perf_swevent_add(event, count, 1, &data, regs);
+			perf_swevent_event(event, count, 1, &data, regs);
 	}
 
 	perf_swevent_put_recursion_context(rctx);
@@ -4655,10 +4772,13 @@
 	perf_trace_destroy(event);
 }
 
-static const struct pmu *tp_perf_event_init(struct perf_event *event)
+static int perf_tp_event_init(struct perf_event *event)
 {
 	int err;
 
+	if (event->attr.type != PERF_TYPE_TRACEPOINT)
+		return -ENOENT;
+
 	/*
 	 * Raw tracepoint data is a severe data leak, only allow root to
 	 * have these.
@@ -4666,15 +4786,31 @@
 	if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
 			perf_paranoid_tracepoint_raw() &&
 			!capable(CAP_SYS_ADMIN))
-		return ERR_PTR(-EPERM);
+		return -EPERM;
 
 	err = perf_trace_init(event);
 	if (err)
-		return NULL;
+		return err;
 
 	event->destroy = tp_perf_event_destroy;
 
-	return &perf_ops_tracepoint;
+	return 0;
+}
+
+static struct pmu perf_tracepoint = {
+	.task_ctx_nr	= perf_sw_context,
+
+	.event_init	= perf_tp_event_init,
+	.add		= perf_trace_add,
+	.del		= perf_trace_del,
+	.start		= perf_swevent_start,
+	.stop		= perf_swevent_stop,
+	.read		= perf_swevent_read,
+};
+
+static inline void perf_tp_register(void)
+{
+	perf_pmu_register(&perf_tracepoint);
 }
 
 static int perf_event_set_filter(struct perf_event *event, void __user *arg)
@@ -4702,9 +4838,8 @@
 
 #else
 
-static const struct pmu *tp_perf_event_init(struct perf_event *event)
+static inline void perf_tp_register(void)
 {
-	return NULL;
 }
 
 static int perf_event_set_filter(struct perf_event *event, void __user *arg)
@@ -4719,24 +4854,6 @@
 #endif /* CONFIG_EVENT_TRACING */
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
-static void bp_perf_event_destroy(struct perf_event *event)
-{
-	release_bp_slot(event);
-}
-
-static const struct pmu *bp_perf_event_init(struct perf_event *bp)
-{
-	int err;
-
-	err = register_perf_hw_breakpoint(bp);
-	if (err)
-		return ERR_PTR(err);
-
-	bp->destroy = bp_perf_event_destroy;
-
-	return &perf_ops_bp;
-}
-
 void perf_bp_event(struct perf_event *bp, void *data)
 {
 	struct perf_sample_data sample;
@@ -4744,80 +4861,382 @@
 
 	perf_sample_data_init(&sample, bp->attr.bp_addr);
 
-	if (!perf_exclude_event(bp, regs))
-		perf_swevent_add(bp, 1, 1, &sample, regs);
-}
-#else
-static const struct pmu *bp_perf_event_init(struct perf_event *bp)
-{
-	return NULL;
-}
-
-void perf_bp_event(struct perf_event *bp, void *regs)
-{
+	if (!bp->hw.state && !perf_exclude_event(bp, regs))
+		perf_swevent_event(bp, 1, 1, &sample, regs);
 }
 #endif
 
-atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
+/*
+ * hrtimer based swevent callback
+ */
 
-static void sw_perf_event_destroy(struct perf_event *event)
+static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 {
-	u64 event_id = event->attr.config;
+	enum hrtimer_restart ret = HRTIMER_RESTART;
+	struct perf_sample_data data;
+	struct pt_regs *regs;
+	struct perf_event *event;
+	u64 period;
 
-	WARN_ON(event->parent);
+	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
+	event->pmu->read(event);
 
-	atomic_dec(&perf_swevent_enabled[event_id]);
-	swevent_hlist_put(event);
+	perf_sample_data_init(&data, 0);
+	data.period = event->hw.last_period;
+	regs = get_irq_regs();
+
+	if (regs && !perf_exclude_event(event, regs)) {
+		if (!(event->attr.exclude_idle && current->pid == 0))
+			if (perf_event_overflow(event, 0, &data, regs))
+				ret = HRTIMER_NORESTART;
+	}
+
+	period = max_t(u64, 10000, event->hw.sample_period);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
+
+	return ret;
 }
 
-static const struct pmu *sw_perf_event_init(struct perf_event *event)
+static void perf_swevent_start_hrtimer(struct perf_event *event)
 {
-	const struct pmu *pmu = NULL;
-	u64 event_id = event->attr.config;
+	struct hw_perf_event *hwc = &event->hw;
+
+	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hwc->hrtimer.function = perf_swevent_hrtimer;
+	if (hwc->sample_period) {
+		s64 period = local64_read(&hwc->period_left);
+
+		if (period) {
+			if (period < 0)
+				period = 10000;
+
+			local64_set(&hwc->period_left, 0);
+		} else {
+			period = max_t(u64, 10000, hwc->sample_period);
+		}
+		__hrtimer_start_range_ns(&hwc->hrtimer,
+				ns_to_ktime(period), 0,
+				HRTIMER_MODE_REL_PINNED, 0);
+	}
+}
+
+static void perf_swevent_cancel_hrtimer(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->sample_period) {
+		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
+		local64_set(&hwc->period_left, ktime_to_ns(remaining));
+
+		hrtimer_cancel(&hwc->hrtimer);
+	}
+}
+
+/*
+ * Software event: cpu wall time clock
+ */
+
+static void cpu_clock_event_update(struct perf_event *event)
+{
+	s64 prev;
+	u64 now;
+
+	now = local_clock();
+	prev = local64_xchg(&event->hw.prev_count, now);
+	local64_add(now - prev, &event->count);
+}
+
+static void cpu_clock_event_start(struct perf_event *event, int flags)
+{
+	local64_set(&event->hw.prev_count, local_clock());
+	perf_swevent_start_hrtimer(event);
+}
+
+static void cpu_clock_event_stop(struct perf_event *event, int flags)
+{
+	perf_swevent_cancel_hrtimer(event);
+	cpu_clock_event_update(event);
+}
+
+static int cpu_clock_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		cpu_clock_event_start(event, flags);
+
+	return 0;
+}
+
+static void cpu_clock_event_del(struct perf_event *event, int flags)
+{
+	cpu_clock_event_stop(event, flags);
+}
+
+static void cpu_clock_event_read(struct perf_event *event)
+{
+	cpu_clock_event_update(event);
+}
+
+static int cpu_clock_event_init(struct perf_event *event)
+{
+	if (event->attr.type != PERF_TYPE_SOFTWARE)
+		return -ENOENT;
+
+	if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
+		return -ENOENT;
+
+	return 0;
+}
+
+static struct pmu perf_cpu_clock = {
+	.task_ctx_nr	= perf_sw_context,
+
+	.event_init	= cpu_clock_event_init,
+	.add		= cpu_clock_event_add,
+	.del		= cpu_clock_event_del,
+	.start		= cpu_clock_event_start,
+	.stop		= cpu_clock_event_stop,
+	.read		= cpu_clock_event_read,
+};
+
+/*
+ * Software event: task time clock
+ */
+
+static void task_clock_event_update(struct perf_event *event, u64 now)
+{
+	u64 prev;
+	s64 delta;
+
+	prev = local64_xchg(&event->hw.prev_count, now);
+	delta = now - prev;
+	local64_add(delta, &event->count);
+}
+
+static void task_clock_event_start(struct perf_event *event, int flags)
+{
+	local64_set(&event->hw.prev_count, event->ctx->time);
+	perf_swevent_start_hrtimer(event);
+}
+
+static void task_clock_event_stop(struct perf_event *event, int flags)
+{
+	perf_swevent_cancel_hrtimer(event);
+	task_clock_event_update(event, event->ctx->time);
+}
+
+static int task_clock_event_add(struct perf_event *event, int flags)
+{
+	if (flags & PERF_EF_START)
+		task_clock_event_start(event, flags);
+
+	return 0;
+}
+
+static void task_clock_event_del(struct perf_event *event, int flags)
+{
+	task_clock_event_stop(event, PERF_EF_UPDATE);
+}
+
+static void task_clock_event_read(struct perf_event *event)
+{
+	u64 time;
+
+	if (!in_nmi()) {
+		update_context_time(event->ctx);
+		time = event->ctx->time;
+	} else {
+		u64 now = perf_clock();
+		u64 delta = now - event->ctx->timestamp;
+		time = event->ctx->time + delta;
+	}
+
+	task_clock_event_update(event, time);
+}
+
+static int task_clock_event_init(struct perf_event *event)
+{
+	if (event->attr.type != PERF_TYPE_SOFTWARE)
+		return -ENOENT;
+
+	if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
+		return -ENOENT;
+
+	return 0;
+}
+
+static struct pmu perf_task_clock = {
+	.task_ctx_nr	= perf_sw_context,
+
+	.event_init	= task_clock_event_init,
+	.add		= task_clock_event_add,
+	.del		= task_clock_event_del,
+	.start		= task_clock_event_start,
+	.stop		= task_clock_event_stop,
+	.read		= task_clock_event_read,
+};
+
+static void perf_pmu_nop_void(struct pmu *pmu)
+{
+}
+
+static int perf_pmu_nop_int(struct pmu *pmu)
+{
+	return 0;
+}
+
+static void perf_pmu_start_txn(struct pmu *pmu)
+{
+	perf_pmu_disable(pmu);
+}
+
+static int perf_pmu_commit_txn(struct pmu *pmu)
+{
+	perf_pmu_enable(pmu);
+	return 0;
+}
+
+static void perf_pmu_cancel_txn(struct pmu *pmu)
+{
+	perf_pmu_enable(pmu);
+}
+
+/*
+ * Ensures all contexts with the same task_ctx_nr have the same
+ * pmu_cpu_context too.
+ */
+static void *find_pmu_context(int ctxn)
+{
+	struct pmu *pmu;
+
+	if (ctxn < 0)
+		return NULL;
+
+	list_for_each_entry(pmu, &pmus, entry) {
+		if (pmu->task_ctx_nr == ctxn)
+			return pmu->pmu_cpu_context;
+	}
+
+	return NULL;
+}
+
+static void free_pmu_context(void * __percpu cpu_context)
+{
+	struct pmu *pmu;
+
+	mutex_lock(&pmus_lock);
+	/*
+	 * Like a real lame refcount.
+	 */
+	list_for_each_entry(pmu, &pmus, entry) {
+		if (pmu->pmu_cpu_context == cpu_context)
+			goto out;
+	}
+
+	free_percpu(cpu_context);
+out:
+	mutex_unlock(&pmus_lock);
+}
+
+int perf_pmu_register(struct pmu *pmu)
+{
+	int cpu, ret;
+
+	mutex_lock(&pmus_lock);
+	ret = -ENOMEM;
+	pmu->pmu_disable_count = alloc_percpu(int);
+	if (!pmu->pmu_disable_count)
+		goto unlock;
+
+	pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr);
+	if (pmu->pmu_cpu_context)
+		goto got_cpu_context;
+
+	pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context);
+	if (!pmu->pmu_cpu_context)
+		goto free_pdc;
+
+	for_each_possible_cpu(cpu) {
+		struct perf_cpu_context *cpuctx;
+
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+		__perf_event_init_context(&cpuctx->ctx);
+		cpuctx->ctx.type = cpu_context;
+		cpuctx->ctx.pmu = pmu;
+		cpuctx->jiffies_interval = 1;
+		INIT_LIST_HEAD(&cpuctx->rotation_list);
+	}
+
+got_cpu_context:
+	if (!pmu->start_txn) {
+		if (pmu->pmu_enable) {
+			/*
+			 * If we have pmu_enable/pmu_disable calls, install
+			 * transaction stubs that use that to try and batch
+			 * hardware accesses.
+			 */
+			pmu->start_txn  = perf_pmu_start_txn;
+			pmu->commit_txn = perf_pmu_commit_txn;
+			pmu->cancel_txn = perf_pmu_cancel_txn;
+		} else {
+			pmu->start_txn  = perf_pmu_nop_void;
+			pmu->commit_txn = perf_pmu_nop_int;
+			pmu->cancel_txn = perf_pmu_nop_void;
+		}
+	}
+
+	if (!pmu->pmu_enable) {
+		pmu->pmu_enable  = perf_pmu_nop_void;
+		pmu->pmu_disable = perf_pmu_nop_void;
+	}
+
+	list_add_rcu(&pmu->entry, &pmus);
+	ret = 0;
+unlock:
+	mutex_unlock(&pmus_lock);
+
+	return ret;
+
+free_pdc:
+	free_percpu(pmu->pmu_disable_count);
+	goto unlock;
+}
+
+void perf_pmu_unregister(struct pmu *pmu)
+{
+	mutex_lock(&pmus_lock);
+	list_del_rcu(&pmu->entry);
+	mutex_unlock(&pmus_lock);
 
 	/*
-	 * Software events (currently) can't in general distinguish
-	 * between user, kernel and hypervisor events.
-	 * However, context switches and cpu migrations are considered
-	 * to be kernel events, and page faults are never hypervisor
-	 * events.
+	 * We dereference the pmu list under both SRCU and regular RCU, so
+	 * synchronize against both of those.
 	 */
-	switch (event_id) {
-	case PERF_COUNT_SW_CPU_CLOCK:
-		pmu = &perf_ops_cpu_clock;
+	synchronize_srcu(&pmus_srcu);
+	synchronize_rcu();
 
-		break;
-	case PERF_COUNT_SW_TASK_CLOCK:
-		/*
-		 * If the user instantiates this as a per-cpu event,
-		 * use the cpu_clock event instead.
-		 */
-		if (event->ctx->task)
-			pmu = &perf_ops_task_clock;
-		else
-			pmu = &perf_ops_cpu_clock;
+	free_percpu(pmu->pmu_disable_count);
+	free_pmu_context(pmu->pmu_cpu_context);
+}
 
-		break;
-	case PERF_COUNT_SW_PAGE_FAULTS:
-	case PERF_COUNT_SW_PAGE_FAULTS_MIN:
-	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
-	case PERF_COUNT_SW_CONTEXT_SWITCHES:
-	case PERF_COUNT_SW_CPU_MIGRATIONS:
-	case PERF_COUNT_SW_ALIGNMENT_FAULTS:
-	case PERF_COUNT_SW_EMULATION_FAULTS:
-		if (!event->parent) {
-			int err;
+struct pmu *perf_init_event(struct perf_event *event)
+{
+	struct pmu *pmu = NULL;
+	int idx;
 
-			err = swevent_hlist_get(event);
-			if (err)
-				return ERR_PTR(err);
+	idx = srcu_read_lock(&pmus_srcu);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		int ret = pmu->event_init(event);
+		if (!ret)
+			goto unlock;
 
-			atomic_inc(&perf_swevent_enabled[event_id]);
-			event->destroy = sw_perf_event_destroy;
+		if (ret != -ENOENT) {
+			pmu = ERR_PTR(ret);
+			goto unlock;
 		}
-		pmu = &perf_ops_generic;
-		break;
 	}
+	pmu = ERR_PTR(-ENOENT);
+unlock:
+	srcu_read_unlock(&pmus_srcu, idx);
 
 	return pmu;
 }
@@ -4826,20 +5245,18 @@
  * Allocate and initialize a event structure
  */
 static struct perf_event *
-perf_event_alloc(struct perf_event_attr *attr,
-		   int cpu,
-		   struct perf_event_context *ctx,
-		   struct perf_event *group_leader,
-		   struct perf_event *parent_event,
-		   perf_overflow_handler_t overflow_handler,
-		   gfp_t gfpflags)
+perf_event_alloc(struct perf_event_attr *attr, int cpu,
+		 struct task_struct *task,
+		 struct perf_event *group_leader,
+		 struct perf_event *parent_event,
+		 perf_overflow_handler_t overflow_handler)
 {
-	const struct pmu *pmu;
+	struct pmu *pmu;
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	long err;
 
-	event = kzalloc(sizeof(*event), gfpflags);
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
 	if (!event)
 		return ERR_PTR(-ENOMEM);
 
@@ -4857,6 +5274,7 @@
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
 	init_waitqueue_head(&event->waitq);
+	init_irq_work(&event->pending, perf_pending_event);
 
 	mutex_init(&event->mmap_mutex);
 
@@ -4864,7 +5282,6 @@
 	event->attr		= *attr;
 	event->group_leader	= group_leader;
 	event->pmu		= NULL;
-	event->ctx		= ctx;
 	event->oncpu		= -1;
 
 	event->parent		= parent_event;
@@ -4874,6 +5291,17 @@
 
 	event->state		= PERF_EVENT_STATE_INACTIVE;
 
+	if (task) {
+		event->attach_state = PERF_ATTACH_TASK;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+		/*
+		 * hw_breakpoint is a bit difficult here..
+		 */
+		if (attr->type == PERF_TYPE_BREAKPOINT)
+			event->hw.bp_target = task;
+#endif
+	}
+
 	if (!overflow_handler && parent_event)
 		overflow_handler = parent_event->overflow_handler;
 	
@@ -4898,29 +5326,8 @@
 	if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
 		goto done;
 
-	switch (attr->type) {
-	case PERF_TYPE_RAW:
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-		pmu = hw_perf_event_init(event);
-		break;
+	pmu = perf_init_event(event);
 
-	case PERF_TYPE_SOFTWARE:
-		pmu = sw_perf_event_init(event);
-		break;
-
-	case PERF_TYPE_TRACEPOINT:
-		pmu = tp_perf_event_init(event);
-		break;
-
-	case PERF_TYPE_BREAKPOINT:
-		pmu = bp_perf_event_init(event);
-		break;
-
-
-	default:
-		break;
-	}
 done:
 	err = 0;
 	if (!pmu)
@@ -4938,13 +5345,21 @@
 	event->pmu = pmu;
 
 	if (!event->parent) {
-		atomic_inc(&nr_events);
+		if (event->attach_state & PERF_ATTACH_TASK)
+			jump_label_inc(&perf_task_events);
 		if (event->attr.mmap || event->attr.mmap_data)
 			atomic_inc(&nr_mmap_events);
 		if (event->attr.comm)
 			atomic_inc(&nr_comm_events);
 		if (event->attr.task)
 			atomic_inc(&nr_task_events);
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+			err = get_callchain_buffers();
+			if (err) {
+				free_event(event);
+				return ERR_PTR(err);
+			}
+		}
 	}
 
 	return event;
@@ -5092,12 +5507,16 @@
 		struct perf_event_attr __user *, attr_uptr,
 		pid_t, pid, int, cpu, int, group_fd, unsigned long, flags)
 {
-	struct perf_event *event, *group_leader = NULL, *output_event = NULL;
+	struct perf_event *group_leader = NULL, *output_event = NULL;
+	struct perf_event *event, *sibling;
 	struct perf_event_attr attr;
 	struct perf_event_context *ctx;
 	struct file *event_file = NULL;
 	struct file *group_file = NULL;
+	struct task_struct *task = NULL;
+	struct pmu *pmu;
 	int event_fd;
+	int move_group = 0;
 	int fput_needed = 0;
 	int err;
 
@@ -5123,20 +5542,11 @@
 	if (event_fd < 0)
 		return event_fd;
 
-	/*
-	 * Get the target context (task or percpu):
-	 */
-	ctx = find_get_context(pid, cpu);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto err_fd;
-	}
-
 	if (group_fd != -1) {
 		group_leader = perf_fget_light(group_fd, &fput_needed);
 		if (IS_ERR(group_leader)) {
 			err = PTR_ERR(group_leader);
-			goto err_put_context;
+			goto err_fd;
 		}
 		group_file = group_leader->filp;
 		if (flags & PERF_FLAG_FD_OUTPUT)
@@ -5145,6 +5555,58 @@
 			group_leader = NULL;
 	}
 
+	if (pid != -1) {
+		task = find_lively_task_by_vpid(pid);
+		if (IS_ERR(task)) {
+			err = PTR_ERR(task);
+			goto err_group_fd;
+		}
+	}
+
+	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, NULL);
+	if (IS_ERR(event)) {
+		err = PTR_ERR(event);
+		goto err_task;
+	}
+
+	/*
+	 * Special case software events and allow them to be part of
+	 * any hardware group.
+	 */
+	pmu = event->pmu;
+
+	if (group_leader &&
+	    (is_software_event(event) != is_software_event(group_leader))) {
+		if (is_software_event(event)) {
+			/*
+			 * If event and group_leader are not both a software
+			 * event, and event is, then group leader is not.
+			 *
+			 * Allow the addition of software events to !software
+			 * groups, this is safe because software events never
+			 * fail to schedule.
+			 */
+			pmu = group_leader->pmu;
+		} else if (is_software_event(group_leader) &&
+			   (group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+			/*
+			 * In case the group is a pure software group, and we
+			 * try to add a hardware event, move the whole group to
+			 * the hardware context.
+			 */
+			move_group = 1;
+		}
+	}
+
+	/*
+	 * Get the target context (task or percpu):
+	 */
+	ctx = find_get_context(pmu, task, cpu);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto err_alloc;
+	}
+
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
@@ -5156,42 +5618,66 @@
 		 * becoming part of another group-sibling):
 		 */
 		if (group_leader->group_leader != group_leader)
-			goto err_put_context;
+			goto err_context;
 		/*
 		 * Do not allow to attach to a group in a different
 		 * task or CPU context:
 		 */
-		if (group_leader->ctx != ctx)
-			goto err_put_context;
+		if (move_group) {
+			if (group_leader->ctx->type != ctx->type)
+				goto err_context;
+		} else {
+			if (group_leader->ctx != ctx)
+				goto err_context;
+		}
+
 		/*
 		 * Only a group leader can be exclusive or pinned
 		 */
 		if (attr.exclusive || attr.pinned)
-			goto err_put_context;
-	}
-
-	event = perf_event_alloc(&attr, cpu, ctx, group_leader,
-				     NULL, NULL, GFP_KERNEL);
-	if (IS_ERR(event)) {
-		err = PTR_ERR(event);
-		goto err_put_context;
+			goto err_context;
 	}
 
 	if (output_event) {
 		err = perf_event_set_output(event, output_event);
 		if (err)
-			goto err_free_put_context;
+			goto err_context;
 	}
 
 	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
-		goto err_free_put_context;
+		goto err_context;
+	}
+
+	if (move_group) {
+		struct perf_event_context *gctx = group_leader->ctx;
+
+		mutex_lock(&gctx->mutex);
+		perf_event_remove_from_context(group_leader);
+		list_for_each_entry(sibling, &group_leader->sibling_list,
+				    group_entry) {
+			perf_event_remove_from_context(sibling);
+			put_ctx(gctx);
+		}
+		mutex_unlock(&gctx->mutex);
+		put_ctx(gctx);
 	}
 
 	event->filp = event_file;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
+
+	if (move_group) {
+		perf_install_in_context(ctx, group_leader, cpu);
+		get_ctx(ctx);
+		list_for_each_entry(sibling, &group_leader->sibling_list,
+				    group_entry) {
+			perf_install_in_context(ctx, sibling, cpu);
+			get_ctx(ctx);
+		}
+	}
+
 	perf_install_in_context(ctx, event, cpu);
 	++ctx->generation;
 	mutex_unlock(&ctx->mutex);
@@ -5212,11 +5698,15 @@
 	fd_install(event_fd, event_file);
 	return event_fd;
 
-err_free_put_context:
-	free_event(event);
-err_put_context:
-	fput_light(group_file, fput_needed);
+err_context:
 	put_ctx(ctx);
+err_alloc:
+	free_event(event);
+err_task:
+	if (task)
+		put_task_struct(task);
+err_group_fd:
+	fput_light(group_file, fput_needed);
 err_fd:
 	put_unused_fd(event_fd);
 	return err;
@@ -5227,32 +5717,31 @@
  *
  * @attr: attributes of the counter to create
  * @cpu: cpu in which the counter is bound
- * @pid: task to profile
+ * @task: task to profile (NULL for percpu)
  */
 struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
-				 pid_t pid,
+				 struct task_struct *task,
 				 perf_overflow_handler_t overflow_handler)
 {
-	struct perf_event *event;
 	struct perf_event_context *ctx;
+	struct perf_event *event;
 	int err;
 
 	/*
 	 * Get the target context (task or percpu):
 	 */
 
-	ctx = find_get_context(pid, cpu);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto err_exit;
-	}
-
-	event = perf_event_alloc(attr, cpu, ctx, NULL,
-				 NULL, overflow_handler, GFP_KERNEL);
+	event = perf_event_alloc(attr, cpu, task, NULL, NULL, overflow_handler);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_put_context;
+		goto err;
+	}
+
+	ctx = find_get_context(event->pmu, task, cpu);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto err_free;
 	}
 
 	event->filp = NULL;
@@ -5270,112 +5759,13 @@
 
 	return event;
 
- err_put_context:
-	put_ctx(ctx);
- err_exit:
+err_free:
+	free_event(event);
+err:
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
 
-/*
- * inherit a event from parent task to child task:
- */
-static struct perf_event *
-inherit_event(struct perf_event *parent_event,
-	      struct task_struct *parent,
-	      struct perf_event_context *parent_ctx,
-	      struct task_struct *child,
-	      struct perf_event *group_leader,
-	      struct perf_event_context *child_ctx)
-{
-	struct perf_event *child_event;
-
-	/*
-	 * Instead of creating recursive hierarchies of events,
-	 * we link inherited events back to the original parent,
-	 * which has a filp for sure, which we use as the reference
-	 * count:
-	 */
-	if (parent_event->parent)
-		parent_event = parent_event->parent;
-
-	child_event = perf_event_alloc(&parent_event->attr,
-					   parent_event->cpu, child_ctx,
-					   group_leader, parent_event,
-					   NULL, GFP_KERNEL);
-	if (IS_ERR(child_event))
-		return child_event;
-	get_ctx(child_ctx);
-
-	/*
-	 * Make the child state follow the state of the parent event,
-	 * not its attr.disabled bit.  We hold the parent's mutex,
-	 * so we won't race with perf_event_{en, dis}able_family.
-	 */
-	if (parent_event->state >= PERF_EVENT_STATE_INACTIVE)
-		child_event->state = PERF_EVENT_STATE_INACTIVE;
-	else
-		child_event->state = PERF_EVENT_STATE_OFF;
-
-	if (parent_event->attr.freq) {
-		u64 sample_period = parent_event->hw.sample_period;
-		struct hw_perf_event *hwc = &child_event->hw;
-
-		hwc->sample_period = sample_period;
-		hwc->last_period   = sample_period;
-
-		local64_set(&hwc->period_left, sample_period);
-	}
-
-	child_event->overflow_handler = parent_event->overflow_handler;
-
-	/*
-	 * Link it up in the child's context:
-	 */
-	add_event_to_ctx(child_event, child_ctx);
-
-	/*
-	 * Get a reference to the parent filp - we will fput it
-	 * when the child event exits. This is safe to do because
-	 * we are in the parent and we know that the filp still
-	 * exists and has a nonzero count:
-	 */
-	atomic_long_inc(&parent_event->filp->f_count);
-
-	/*
-	 * Link this into the parent event's child list
-	 */
-	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
-	mutex_lock(&parent_event->child_mutex);
-	list_add_tail(&child_event->child_list, &parent_event->child_list);
-	mutex_unlock(&parent_event->child_mutex);
-
-	return child_event;
-}
-
-static int inherit_group(struct perf_event *parent_event,
-	      struct task_struct *parent,
-	      struct perf_event_context *parent_ctx,
-	      struct task_struct *child,
-	      struct perf_event_context *child_ctx)
-{
-	struct perf_event *leader;
-	struct perf_event *sub;
-	struct perf_event *child_ctr;
-
-	leader = inherit_event(parent_event, parent, parent_ctx,
-				 child, NULL, child_ctx);
-	if (IS_ERR(leader))
-		return PTR_ERR(leader);
-	list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
-		child_ctr = inherit_event(sub, parent, parent_ctx,
-					    child, leader, child_ctx);
-		if (IS_ERR(child_ctr))
-			return PTR_ERR(child_ctr);
-	}
-	return 0;
-}
-
 static void sync_child_event(struct perf_event *child_event,
 			       struct task_struct *child)
 {
@@ -5432,16 +5822,13 @@
 	}
 }
 
-/*
- * When a child task exits, feed back event values to parent events.
- */
-void perf_event_exit_task(struct task_struct *child)
+static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 {
 	struct perf_event *child_event, *tmp;
 	struct perf_event_context *child_ctx;
 	unsigned long flags;
 
-	if (likely(!child->perf_event_ctxp)) {
+	if (likely(!child->perf_event_ctxp[ctxn])) {
 		perf_event_task(child, NULL, 0);
 		return;
 	}
@@ -5453,8 +5840,8 @@
 	 * scheduled, so we are now safe from rescheduling changing
 	 * our context.
 	 */
-	child_ctx = child->perf_event_ctxp;
-	__perf_event_task_sched_out(child_ctx);
+	child_ctx = child->perf_event_ctxp[ctxn];
+	task_ctx_sched_out(child_ctx, EVENT_ALL);
 
 	/*
 	 * Take the context lock here so that if find_get_context is
@@ -5462,7 +5849,7 @@
 	 * incremented the context's refcount before we do put_ctx below.
 	 */
 	raw_spin_lock(&child_ctx->lock);
-	child->perf_event_ctxp = NULL;
+	child->perf_event_ctxp[ctxn] = NULL;
 	/*
 	 * If this context is a clone; unclone it so it can't get
 	 * swapped to another process while we're removing all
@@ -5515,6 +5902,17 @@
 	put_ctx(child_ctx);
 }
 
+/*
+ * When a child task exits, feed back event values to parent events.
+ */
+void perf_event_exit_task(struct task_struct *child)
+{
+	int ctxn;
+
+	for_each_task_context_nr(ctxn)
+		perf_event_exit_task_context(child, ctxn);
+}
+
 static void perf_free_event(struct perf_event *event,
 			    struct perf_event_context *ctx)
 {
@@ -5536,48 +5934,166 @@
 
 /*
  * free an unexposed, unused context as created by inheritance by
- * init_task below, used by fork() in case of fail.
+ * perf_event_init_task below, used by fork() in case of fail.
  */
 void perf_event_free_task(struct task_struct *task)
 {
-	struct perf_event_context *ctx = task->perf_event_ctxp;
+	struct perf_event_context *ctx;
 	struct perf_event *event, *tmp;
+	int ctxn;
 
-	if (!ctx)
-		return;
+	for_each_task_context_nr(ctxn) {
+		ctx = task->perf_event_ctxp[ctxn];
+		if (!ctx)
+			continue;
 
-	mutex_lock(&ctx->mutex);
+		mutex_lock(&ctx->mutex);
 again:
-	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
-		perf_free_event(event, ctx);
+		list_for_each_entry_safe(event, tmp, &ctx->pinned_groups,
+				group_entry)
+			perf_free_event(event, ctx);
 
-	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups,
-				 group_entry)
-		perf_free_event(event, ctx);
+		list_for_each_entry_safe(event, tmp, &ctx->flexible_groups,
+				group_entry)
+			perf_free_event(event, ctx);
 
-	if (!list_empty(&ctx->pinned_groups) ||
-	    !list_empty(&ctx->flexible_groups))
-		goto again;
+		if (!list_empty(&ctx->pinned_groups) ||
+				!list_empty(&ctx->flexible_groups))
+			goto again;
 
-	mutex_unlock(&ctx->mutex);
+		mutex_unlock(&ctx->mutex);
 
-	put_ctx(ctx);
+		put_ctx(ctx);
+	}
+}
+
+void perf_event_delayed_put(struct task_struct *task)
+{
+	int ctxn;
+
+	for_each_task_context_nr(ctxn)
+		WARN_ON_ONCE(task->perf_event_ctxp[ctxn]);
+}
+
+/*
+ * inherit a event from parent task to child task:
+ */
+static struct perf_event *
+inherit_event(struct perf_event *parent_event,
+	      struct task_struct *parent,
+	      struct perf_event_context *parent_ctx,
+	      struct task_struct *child,
+	      struct perf_event *group_leader,
+	      struct perf_event_context *child_ctx)
+{
+	struct perf_event *child_event;
+	unsigned long flags;
+
+	/*
+	 * Instead of creating recursive hierarchies of events,
+	 * we link inherited events back to the original parent,
+	 * which has a filp for sure, which we use as the reference
+	 * count:
+	 */
+	if (parent_event->parent)
+		parent_event = parent_event->parent;
+
+	child_event = perf_event_alloc(&parent_event->attr,
+					   parent_event->cpu,
+					   child,
+					   group_leader, parent_event,
+					   NULL);
+	if (IS_ERR(child_event))
+		return child_event;
+	get_ctx(child_ctx);
+
+	/*
+	 * Make the child state follow the state of the parent event,
+	 * not its attr.disabled bit.  We hold the parent's mutex,
+	 * so we won't race with perf_event_{en, dis}able_family.
+	 */
+	if (parent_event->state >= PERF_EVENT_STATE_INACTIVE)
+		child_event->state = PERF_EVENT_STATE_INACTIVE;
+	else
+		child_event->state = PERF_EVENT_STATE_OFF;
+
+	if (parent_event->attr.freq) {
+		u64 sample_period = parent_event->hw.sample_period;
+		struct hw_perf_event *hwc = &child_event->hw;
+
+		hwc->sample_period = sample_period;
+		hwc->last_period   = sample_period;
+
+		local64_set(&hwc->period_left, sample_period);
+	}
+
+	child_event->ctx = child_ctx;
+	child_event->overflow_handler = parent_event->overflow_handler;
+
+	/*
+	 * Link it up in the child's context:
+	 */
+	raw_spin_lock_irqsave(&child_ctx->lock, flags);
+	add_event_to_ctx(child_event, child_ctx);
+	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
+
+	/*
+	 * Get a reference to the parent filp - we will fput it
+	 * when the child event exits. This is safe to do because
+	 * we are in the parent and we know that the filp still
+	 * exists and has a nonzero count:
+	 */
+	atomic_long_inc(&parent_event->filp->f_count);
+
+	/*
+	 * Link this into the parent event's child list
+	 */
+	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
+	mutex_lock(&parent_event->child_mutex);
+	list_add_tail(&child_event->child_list, &parent_event->child_list);
+	mutex_unlock(&parent_event->child_mutex);
+
+	return child_event;
+}
+
+static int inherit_group(struct perf_event *parent_event,
+	      struct task_struct *parent,
+	      struct perf_event_context *parent_ctx,
+	      struct task_struct *child,
+	      struct perf_event_context *child_ctx)
+{
+	struct perf_event *leader;
+	struct perf_event *sub;
+	struct perf_event *child_ctr;
+
+	leader = inherit_event(parent_event, parent, parent_ctx,
+				 child, NULL, child_ctx);
+	if (IS_ERR(leader))
+		return PTR_ERR(leader);
+	list_for_each_entry(sub, &parent_event->sibling_list, group_entry) {
+		child_ctr = inherit_event(sub, parent, parent_ctx,
+					    child, leader, child_ctx);
+		if (IS_ERR(child_ctr))
+			return PTR_ERR(child_ctr);
+	}
+	return 0;
 }
 
 static int
 inherit_task_group(struct perf_event *event, struct task_struct *parent,
 		   struct perf_event_context *parent_ctx,
-		   struct task_struct *child,
+		   struct task_struct *child, int ctxn,
 		   int *inherited_all)
 {
 	int ret;
-	struct perf_event_context *child_ctx = child->perf_event_ctxp;
+	struct perf_event_context *child_ctx;
 
 	if (!event->attr.inherit) {
 		*inherited_all = 0;
 		return 0;
 	}
 
+       	child_ctx = child->perf_event_ctxp[ctxn];
 	if (!child_ctx) {
 		/*
 		 * This is executed from the parent task context, so
@@ -5586,14 +6102,11 @@
 		 * child.
 		 */
 
-		child_ctx = kzalloc(sizeof(struct perf_event_context),
-				    GFP_KERNEL);
+		child_ctx = alloc_perf_context(event->pmu, child);
 		if (!child_ctx)
 			return -ENOMEM;
 
-		__perf_event_init_context(child_ctx, child);
-		child->perf_event_ctxp = child_ctx;
-		get_task_struct(child);
+		child->perf_event_ctxp[ctxn] = child_ctx;
 	}
 
 	ret = inherit_group(event, parent, parent_ctx,
@@ -5605,11 +6118,10 @@
 	return ret;
 }
 
-
 /*
  * Initialize the perf_event context in task_struct
  */
-int perf_event_init_task(struct task_struct *child)
+int perf_event_init_context(struct task_struct *child, int ctxn)
 {
 	struct perf_event_context *child_ctx, *parent_ctx;
 	struct perf_event_context *cloned_ctx;
@@ -5618,19 +6130,19 @@
 	int inherited_all = 1;
 	int ret = 0;
 
-	child->perf_event_ctxp = NULL;
+	child->perf_event_ctxp[ctxn] = NULL;
 
 	mutex_init(&child->perf_event_mutex);
 	INIT_LIST_HEAD(&child->perf_event_list);
 
-	if (likely(!parent->perf_event_ctxp))
+	if (likely(!parent->perf_event_ctxp[ctxn]))
 		return 0;
 
 	/*
 	 * If the parent's context is a clone, pin it so it won't get
 	 * swapped under us.
 	 */
-	parent_ctx = perf_pin_task_context(parent);
+	parent_ctx = perf_pin_task_context(parent, ctxn);
 
 	/*
 	 * No need to check if parent_ctx != NULL here; since we saw
@@ -5650,20 +6162,20 @@
 	 * the list, not manipulating it:
 	 */
 	list_for_each_entry(event, &parent_ctx->pinned_groups, group_entry) {
-		ret = inherit_task_group(event, parent, parent_ctx, child,
-					 &inherited_all);
+		ret = inherit_task_group(event, parent, parent_ctx,
+					 child, ctxn, &inherited_all);
 		if (ret)
 			break;
 	}
 
 	list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
-		ret = inherit_task_group(event, parent, parent_ctx, child,
-					 &inherited_all);
+		ret = inherit_task_group(event, parent, parent_ctx,
+					 child, ctxn, &inherited_all);
 		if (ret)
 			break;
 	}
 
-	child_ctx = child->perf_event_ctxp;
+	child_ctx = child->perf_event_ctxp[ctxn];
 
 	if (child_ctx && inherited_all) {
 		/*
@@ -5692,63 +6204,98 @@
 	return ret;
 }
 
+/*
+ * Initialize the perf_event context in task_struct
+ */
+int perf_event_init_task(struct task_struct *child)
+{
+	int ctxn, ret;
+
+	for_each_task_context_nr(ctxn) {
+		ret = perf_event_init_context(child, ctxn);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static void __init perf_event_init_all_cpus(void)
 {
+	struct swevent_htable *swhash;
 	int cpu;
-	struct perf_cpu_context *cpuctx;
 
 	for_each_possible_cpu(cpu) {
-		cpuctx = &per_cpu(perf_cpu_context, cpu);
-		mutex_init(&cpuctx->hlist_mutex);
-		__perf_event_init_context(&cpuctx->ctx, NULL);
+		swhash = &per_cpu(swevent_htable, cpu);
+		mutex_init(&swhash->hlist_mutex);
+		INIT_LIST_HEAD(&per_cpu(rotation_list, cpu));
 	}
 }
 
 static void __cpuinit perf_event_init_cpu(int cpu)
 {
-	struct perf_cpu_context *cpuctx;
+	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
-	cpuctx = &per_cpu(perf_cpu_context, cpu);
-
-	spin_lock(&perf_resource_lock);
-	cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
-	spin_unlock(&perf_resource_lock);
-
-	mutex_lock(&cpuctx->hlist_mutex);
-	if (cpuctx->hlist_refcount > 0) {
+	mutex_lock(&swhash->hlist_mutex);
+	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
-		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
-		WARN_ON_ONCE(!hlist);
-		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
+		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
+		WARN_ON(!hlist);
+		rcu_assign_pointer(swhash->swevent_hlist, hlist);
 	}
-	mutex_unlock(&cpuctx->hlist_mutex);
+	mutex_unlock(&swhash->hlist_mutex);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void __perf_event_exit_cpu(void *info)
+static void perf_pmu_rotate_stop(struct pmu *pmu)
 {
-	struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
-	struct perf_event_context *ctx = &cpuctx->ctx;
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+	WARN_ON(!irqs_disabled());
+
+	list_del_init(&cpuctx->rotation_list);
+}
+
+static void __perf_event_exit_context(void *__info)
+{
+	struct perf_event_context *ctx = __info;
 	struct perf_event *event, *tmp;
 
+	perf_pmu_rotate_stop(ctx->pmu);
+
 	list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
 		__perf_event_remove_from_context(event);
 	list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
 		__perf_event_remove_from_context(event);
 }
+
+static void perf_event_exit_cpu_context(int cpu)
+{
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+	int idx;
+
+	idx = srcu_read_lock(&pmus_srcu);
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		ctx = &per_cpu_ptr(pmu->pmu_cpu_context, cpu)->ctx;
+
+		mutex_lock(&ctx->mutex);
+		smp_call_function_single(cpu, __perf_event_exit_context, ctx, 1);
+		mutex_unlock(&ctx->mutex);
+	}
+	srcu_read_unlock(&pmus_srcu, idx);
+}
+
 static void perf_event_exit_cpu(int cpu)
 {
-	struct perf_cpu_context *cpuctx = &per_cpu(perf_cpu_context, cpu);
-	struct perf_event_context *ctx = &cpuctx->ctx;
+	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
-	mutex_lock(&cpuctx->hlist_mutex);
-	swevent_hlist_release(cpuctx);
-	mutex_unlock(&cpuctx->hlist_mutex);
+	mutex_lock(&swhash->hlist_mutex);
+	swevent_hlist_release(swhash);
+	mutex_unlock(&swhash->hlist_mutex);
 
-	mutex_lock(&ctx->mutex);
-	smp_call_function_single(cpu, __perf_event_exit_cpu, NULL, 1);
-	mutex_unlock(&ctx->mutex);
+	perf_event_exit_cpu_context(cpu);
 }
 #else
 static inline void perf_event_exit_cpu(int cpu) { }
@@ -5778,118 +6325,13 @@
 	return NOTIFY_OK;
 }
 
-/*
- * This has to have a higher priority than migration_notifier in sched.c.
- */
-static struct notifier_block __cpuinitdata perf_cpu_nb = {
-	.notifier_call		= perf_cpu_notify,
-	.priority		= 20,
-};
-
 void __init perf_event_init(void)
 {
 	perf_event_init_all_cpus();
-	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
-			(void *)(long)smp_processor_id());
-	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE,
-			(void *)(long)smp_processor_id());
-	register_cpu_notifier(&perf_cpu_nb);
+	init_srcu_struct(&pmus_srcu);
+	perf_pmu_register(&perf_swevent);
+	perf_pmu_register(&perf_cpu_clock);
+	perf_pmu_register(&perf_task_clock);
+	perf_tp_register();
+	perf_cpu_notifier(perf_cpu_notify);
 }
-
-static ssize_t perf_show_reserve_percpu(struct sysdev_class *class,
-					struct sysdev_class_attribute *attr,
-					char *buf)
-{
-	return sprintf(buf, "%d\n", perf_reserved_percpu);
-}
-
-static ssize_t
-perf_set_reserve_percpu(struct sysdev_class *class,
-			struct sysdev_class_attribute *attr,
-			const char *buf,
-			size_t count)
-{
-	struct perf_cpu_context *cpuctx;
-	unsigned long val;
-	int err, cpu, mpt;
-
-	err = strict_strtoul(buf, 10, &val);
-	if (err)
-		return err;
-	if (val > perf_max_events)
-		return -EINVAL;
-
-	spin_lock(&perf_resource_lock);
-	perf_reserved_percpu = val;
-	for_each_online_cpu(cpu) {
-		cpuctx = &per_cpu(perf_cpu_context, cpu);
-		raw_spin_lock_irq(&cpuctx->ctx.lock);
-		mpt = min(perf_max_events - cpuctx->ctx.nr_events,
-			  perf_max_events - perf_reserved_percpu);
-		cpuctx->max_pertask = mpt;
-		raw_spin_unlock_irq(&cpuctx->ctx.lock);
-	}
-	spin_unlock(&perf_resource_lock);
-
-	return count;
-}
-
-static ssize_t perf_show_overcommit(struct sysdev_class *class,
-				    struct sysdev_class_attribute *attr,
-				    char *buf)
-{
-	return sprintf(buf, "%d\n", perf_overcommit);
-}
-
-static ssize_t
-perf_set_overcommit(struct sysdev_class *class,
-		    struct sysdev_class_attribute *attr,
-		    const char *buf, size_t count)
-{
-	unsigned long val;
-	int err;
-
-	err = strict_strtoul(buf, 10, &val);
-	if (err)
-		return err;
-	if (val > 1)
-		return -EINVAL;
-
-	spin_lock(&perf_resource_lock);
-	perf_overcommit = val;
-	spin_unlock(&perf_resource_lock);
-
-	return count;
-}
-
-static SYSDEV_CLASS_ATTR(
-				reserve_percpu,
-				0644,
-				perf_show_reserve_percpu,
-				perf_set_reserve_percpu
-			);
-
-static SYSDEV_CLASS_ATTR(
-				overcommit,
-				0644,
-				perf_show_overcommit,
-				perf_set_overcommit
-			);
-
-static struct attribute *perfclass_attrs[] = {
-	&attr_reserve_percpu.attr,
-	&attr_overcommit.attr,
-	NULL
-};
-
-static struct attribute_group perfclass_attr_group = {
-	.attrs			= perfclass_attrs,
-	.name			= "perf_events",
-};
-
-static int __init perf_event_sysfs_init(void)
-{
-	return sysfs_create_group(&cpu_sysdev_class.kset.kobj,
-				  &perfclass_attr_group);
-}
-device_initcall(perf_event_sysfs_init);
diff --git a/kernel/pid.c b/kernel/pid.c
index d55c6fb..39b65b6 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -401,7 +401,7 @@
 	struct task_struct *result = NULL;
 	if (pid) {
 		struct hlist_node *first;
-		first = rcu_dereference_check(pid->tasks[type].first,
+		first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]),
 					      rcu_read_lock_held() ||
 					      lockdep_tasklist_lock_is_held());
 		if (first)
@@ -416,6 +416,7 @@
  */
 struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
 {
+	rcu_lockdep_assert(rcu_read_lock_held());
 	return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
 }
 
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index 645e541..a96b850 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -110,6 +110,7 @@
 	.write = pm_qos_power_write,
 	.open = pm_qos_power_open,
 	.release = pm_qos_power_release,
+	.llseek = noop_llseek,
 };
 
 /* unlocked internal variant */
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index ca6066a..29bff61 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -86,6 +86,7 @@
 	depends on SMP
 	depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE
 	depends on PM_SLEEP
+	select HOTPLUG
 	select HOTPLUG_CPU
 	default y
 
@@ -137,6 +138,8 @@
 config HIBERNATION
 	bool "Hibernation (aka 'suspend to disk')"
 	depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
 	select SUSPEND_NVS if HAS_IOMEM
 	---help---
 	  Enable the suspend to disk (STD) functionality, which is usually
@@ -242,3 +245,17 @@
 	bool
 	depends on PM_SLEEP || PM_RUNTIME
 	default y
+
+config PM_OPP
+	bool "Operating Performance Point (OPP) Layer library"
+	depends on PM
+	---help---
+	  SOCs have a standard set of tuples consisting of frequency and
+	  voltage pairs that the device will support per voltage domain. This
+	  is called Operating Performance Point or OPP. The actual definitions
+	  of OPP varies over silicon within the same family of devices.
+
+	  OPP layer organizes the data internally using device pointers
+	  representing individual voltage domains and provides SOC
+	  implementations a ready to use framework to manage OPPs.
+	  For more information, read <file:Documentation/power/opp.txt>
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 8dc31e0..657272e 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -29,6 +29,7 @@
 #include "power.h"
 
 
+static int nocompress = 0;
 static int noresume = 0;
 static char resume_file[256] = CONFIG_PM_STD_PARTITION;
 dev_t swsusp_resume_device;
@@ -638,6 +639,8 @@
 
 		if (hibernation_mode == HIBERNATION_PLATFORM)
 			flags |= SF_PLATFORM_MODE;
+		if (nocompress)
+			flags |= SF_NOCOMPRESS_MODE;
 		pr_debug("PM: writing image.\n");
 		error = swsusp_write(flags);
 		swsusp_free();
@@ -705,7 +708,7 @@
 		goto Unlock;
 	}
 
-	pr_debug("PM: Checking image partition %s\n", resume_file);
+	pr_debug("PM: Checking hibernation image partition %s\n", resume_file);
 
 	/* Check if the device is there */
 	swsusp_resume_device = name_to_dev_t(resume_file);
@@ -730,10 +733,10 @@
 	}
 
  Check_image:
-	pr_debug("PM: Resume from partition %d:%d\n",
+	pr_debug("PM: Hibernation image partition %d:%d present\n",
 		MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device));
 
-	pr_debug("PM: Checking hibernation image.\n");
+	pr_debug("PM: Looking for hibernation image.\n");
 	error = swsusp_check();
 	if (error)
 		goto Unlock;
@@ -765,14 +768,14 @@
 		goto Done;
 	}
 
-	pr_debug("PM: Reading hibernation image.\n");
+	pr_debug("PM: Loading hibernation image.\n");
 
 	error = swsusp_read(&flags);
 	swsusp_close(FMODE_READ);
 	if (!error)
 		hibernation_restore(flags & SF_PLATFORM_MODE);
 
-	printk(KERN_ERR "PM: Restore failed, recovering.\n");
+	printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n");
 	swsusp_free();
 	thaw_processes();
  Done:
@@ -785,7 +788,7 @@
 	/* For success case, the suspend path will release the lock */
  Unlock:
 	mutex_unlock(&pm_mutex);
-	pr_debug("PM: Resume from disk failed.\n");
+	pr_debug("PM: Hibernation image not present or could not be loaded.\n");
 	return error;
 close_finish:
 	swsusp_close(FMODE_READ);
@@ -1004,6 +1007,15 @@
 	return 1;
 }
 
+static int __init hibernate_setup(char *str)
+{
+	if (!strncmp(str, "noresume", 8))
+		noresume = 1;
+	else if (!strncmp(str, "nocompress", 10))
+		nocompress = 1;
+	return 1;
+}
+
 static int __init noresume_setup(char *str)
 {
 	noresume = 1;
@@ -1013,3 +1025,4 @@
 __setup("noresume", noresume_setup);
 __setup("resume_offset=", resume_offset_setup);
 __setup("resume=", resume_setup);
+__setup("hibernate=", hibernate_setup);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 62b0bc6..7b5db6a 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -237,18 +237,18 @@
 				struct kobj_attribute *attr,
 				char *buf)
 {
-	unsigned long val;
+	unsigned int val;
 
-	return pm_get_wakeup_count(&val) ? sprintf(buf, "%lu\n", val) : -EINTR;
+	return pm_get_wakeup_count(&val) ? sprintf(buf, "%u\n", val) : -EINTR;
 }
 
 static ssize_t wakeup_count_store(struct kobject *kobj,
 				struct kobj_attribute *attr,
 				const char *buf, size_t n)
 {
-	unsigned long val;
+	unsigned int val;
 
-	if (sscanf(buf, "%lu", &val) == 1) {
+	if (sscanf(buf, "%u", &val) == 1) {
 		if (pm_save_wakeup_count(val))
 			return n;
 	}
@@ -281,12 +281,30 @@
 }
 
 power_attr(pm_trace);
+
+static ssize_t pm_trace_dev_match_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *buf)
+{
+	return show_trace_dev_match(buf, PAGE_SIZE);
+}
+
+static ssize_t
+pm_trace_dev_match_store(struct kobject *kobj, struct kobj_attribute *attr,
+			 const char *buf, size_t n)
+{
+	return -EINVAL;
+}
+
+power_attr(pm_trace_dev_match);
+
 #endif /* CONFIG_PM_TRACE */
 
 static struct attribute * g[] = {
 	&state_attr.attr,
 #ifdef CONFIG_PM_TRACE
 	&pm_trace_attr.attr,
+	&pm_trace_dev_match_attr.attr,
 #endif
 #ifdef CONFIG_PM_SLEEP
 	&pm_async_attr.attr,
@@ -308,7 +326,7 @@
 
 static int __init pm_start_workqueue(void)
 {
-	pm_wq = create_freezeable_workqueue("pm");
+	pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0);
 
 	return pm_wq ? 0 : -ENOMEM;
 }
@@ -321,6 +339,7 @@
 	int error = pm_start_workqueue();
 	if (error)
 		return error;
+	hibernate_image_size_init();
 	power_kobj = kobject_create_and_add("power", NULL);
 	if (!power_kobj)
 		return -ENOMEM;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 006270f..03634be 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -14,6 +14,9 @@
 } __attribute__((aligned(PAGE_SIZE)));
 
 #ifdef CONFIG_HIBERNATION
+/* kernel/power/snapshot.c */
+extern void __init hibernate_image_size_init(void);
+
 #ifdef CONFIG_ARCH_HIBERNATION_HEADER
 /* Maximum size of architecture specific data in a hibernation header */
 #define MAX_ARCH_HEADER_SIZE	(sizeof(struct new_utsname) + 4)
@@ -49,7 +52,11 @@
 extern int hibernation_snapshot(int platform_mode);
 extern int hibernation_restore(int platform_mode);
 extern int hibernation_platform_enter(void);
-#endif
+
+#else /* !CONFIG_HIBERNATION */
+
+static inline void hibernate_image_size_init(void) {}
+#endif /* !CONFIG_HIBERNATION */
 
 extern int pfn_is_nosave(unsigned long);
 
@@ -134,6 +141,7 @@
  * the image header.
  */
 #define SF_PLATFORM_MODE	1
+#define SF_NOCOMPRESS_MODE	2
 
 /* kernel/power/hibernate.c */
 extern int swsusp_check(void);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 028a995..e50b4c1 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -40,6 +40,7 @@
 	struct timeval start, end;
 	u64 elapsed_csecs64;
 	unsigned int elapsed_csecs;
+	bool wakeup = false;
 
 	do_gettimeofday(&start);
 
@@ -78,6 +79,11 @@
 		if (!todo || time_after(jiffies, end_time))
 			break;
 
+		if (!pm_check_wakeup_events()) {
+			wakeup = true;
+			break;
+		}
+
 		/*
 		 * We need to retry, but first give the freezing tasks some
 		 * time to enter the regrigerator.
@@ -97,8 +103,9 @@
 		 * but it cleans up leftover PF_FREEZE requests.
 		 */
 		printk("\n");
-		printk(KERN_ERR "Freezing of tasks failed after %d.%02d seconds "
+		printk(KERN_ERR "Freezing of tasks %s after %d.%02d seconds "
 		       "(%d tasks refusing to freeze, wq_busy=%d):\n",
+		       wakeup ? "aborted" : "failed",
 		       elapsed_csecs / 100, elapsed_csecs % 100,
 		       todo - wq_busy, wq_busy);
 
@@ -107,7 +114,7 @@
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
 			task_lock(p);
-			if (freezing(p) && !freezer_should_skip(p))
+			if (!wakeup && freezing(p) && !freezer_should_skip(p))
 				sched_show_task(p);
 			cancel_freezing(p);
 			task_unlock(p);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index d3f795f..ac7eb10 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -46,7 +46,12 @@
  * size will not exceed N bytes, but if that is impossible, it will
  * try to create the smallest image possible.
  */
-unsigned long image_size = 500 * 1024 * 1024;
+unsigned long image_size;
+
+void __init hibernate_image_size_init(void)
+{
+	image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE;
+}
 
 /* List of PBEs needed for restoring the pages that were allocated before
  * the suspend and included in the suspend image, but have also been
@@ -1318,12 +1323,14 @@
 
 	/* Compute the maximum number of saveable pages to leave in memory. */
 	max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES;
+	/* Compute the desired number of image pages specified by image_size. */
 	size = DIV_ROUND_UP(image_size, PAGE_SIZE);
 	if (size > max_size)
 		size = max_size;
 	/*
-	 * If the maximum is not less than the current number of saveable pages
-	 * in memory, allocate page frames for the image and we're done.
+	 * If the desired number of image pages is at least as large as the
+	 * current number of saveable pages in memory, allocate page frames for
+	 * the image and we're done.
 	 */
 	if (size >= saveable) {
 		pages = preallocate_image_highmem(save_highmem);
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index e6a5bdf..916eaa7 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -24,10 +24,12 @@
 #include <linux/swapops.h>
 #include <linux/pm.h>
 #include <linux/slab.h>
+#include <linux/lzo.h>
+#include <linux/vmalloc.h>
 
 #include "power.h"
 
-#define SWSUSP_SIG	"S1SUSPEND"
+#define HIBERNATE_SIG	"LINHIB0001"
 
 /*
  *	The swap map is a data structure used for keeping track of each page
@@ -193,7 +195,7 @@
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
-		memcpy(swsusp_header->sig,SWSUSP_SIG, 10);
+		memcpy(swsusp_header->sig, HIBERNATE_SIG, 10);
 		swsusp_header->image = handle->first_sector;
 		swsusp_header->flags = flags;
 		error = hib_bio_write_page(swsusp_resume_block,
@@ -357,6 +359,18 @@
 	return error;
 }
 
+/* We need to remember how much compressed data we need to read. */
+#define LZO_HEADER	sizeof(size_t)
+
+/* Number of pages/bytes we'll compress at one time. */
+#define LZO_UNC_PAGES	32
+#define LZO_UNC_SIZE	(LZO_UNC_PAGES * PAGE_SIZE)
+
+/* Number of pages/bytes we need for compressed data (worst case). */
+#define LZO_CMP_PAGES	DIV_ROUND_UP(lzo1x_worst_compress(LZO_UNC_SIZE) + \
+			             LZO_HEADER, PAGE_SIZE)
+#define LZO_CMP_SIZE	(LZO_CMP_PAGES * PAGE_SIZE)
+
 /**
  *	save_image - save the suspend image data
  */
@@ -404,6 +418,137 @@
 	return ret;
 }
 
+
+/**
+ * save_image_lzo - Save the suspend image data compressed with LZO.
+ * @handle: Swap mam handle to use for saving the image.
+ * @snapshot: Image to read data from.
+ * @nr_to_write: Number of pages to save.
+ */
+static int save_image_lzo(struct swap_map_handle *handle,
+                          struct snapshot_handle *snapshot,
+                          unsigned int nr_to_write)
+{
+	unsigned int m;
+	int ret = 0;
+	int nr_pages;
+	int err2;
+	struct bio *bio;
+	struct timeval start;
+	struct timeval stop;
+	size_t off, unc_len, cmp_len;
+	unsigned char *unc, *cmp, *wrk, *page;
+
+	page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+	if (!page) {
+		printk(KERN_ERR "PM: Failed to allocate LZO page\n");
+		return -ENOMEM;
+	}
+
+	wrk = vmalloc(LZO1X_1_MEM_COMPRESS);
+	if (!wrk) {
+		printk(KERN_ERR "PM: Failed to allocate LZO workspace\n");
+		free_page((unsigned long)page);
+		return -ENOMEM;
+	}
+
+	unc = vmalloc(LZO_UNC_SIZE);
+	if (!unc) {
+		printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n");
+		vfree(wrk);
+		free_page((unsigned long)page);
+		return -ENOMEM;
+	}
+
+	cmp = vmalloc(LZO_CMP_SIZE);
+	if (!cmp) {
+		printk(KERN_ERR "PM: Failed to allocate LZO compressed\n");
+		vfree(unc);
+		vfree(wrk);
+		free_page((unsigned long)page);
+		return -ENOMEM;
+	}
+
+	printk(KERN_INFO
+		"PM: Compressing and saving image data (%u pages) ...     ",
+		nr_to_write);
+	m = nr_to_write / 100;
+	if (!m)
+		m = 1;
+	nr_pages = 0;
+	bio = NULL;
+	do_gettimeofday(&start);
+	for (;;) {
+		for (off = 0; off < LZO_UNC_SIZE; off += PAGE_SIZE) {
+			ret = snapshot_read_next(snapshot);
+			if (ret < 0)
+				goto out_finish;
+
+			if (!ret)
+				break;
+
+			memcpy(unc + off, data_of(*snapshot), PAGE_SIZE);
+
+			if (!(nr_pages % m))
+				printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m);
+			nr_pages++;
+		}
+
+		if (!off)
+			break;
+
+		unc_len = off;
+		ret = lzo1x_1_compress(unc, unc_len,
+		                       cmp + LZO_HEADER, &cmp_len, wrk);
+		if (ret < 0) {
+			printk(KERN_ERR "PM: LZO compression failed\n");
+			break;
+		}
+
+		if (unlikely(!cmp_len ||
+		             cmp_len > lzo1x_worst_compress(unc_len))) {
+			printk(KERN_ERR "PM: Invalid LZO compressed length\n");
+			ret = -1;
+			break;
+		}
+
+		*(size_t *)cmp = cmp_len;
+
+		/*
+		 * Given we are writing one page at a time to disk, we copy
+		 * that much from the buffer, although the last bit will likely
+		 * be smaller than full page. This is OK - we saved the length
+		 * of the compressed data, so any garbage at the end will be
+		 * discarded when we read it.
+		 */
+		for (off = 0; off < LZO_HEADER + cmp_len; off += PAGE_SIZE) {
+			memcpy(page, cmp + off, PAGE_SIZE);
+
+			ret = swap_write_page(handle, page, &bio);
+			if (ret)
+				goto out_finish;
+		}
+	}
+
+out_finish:
+	err2 = hib_wait_on_bio_chain(&bio);
+	do_gettimeofday(&stop);
+	if (!ret)
+		ret = err2;
+	if (!ret)
+		printk(KERN_CONT "\b\b\b\bdone\n");
+	else
+		printk(KERN_CONT "\n");
+	swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
+
+	vfree(cmp);
+	vfree(unc);
+	vfree(wrk);
+	free_page((unsigned long)page);
+
+	return ret;
+}
+
 /**
  *	enough_swap - Make sure we have enough swap to save the image.
  *
@@ -411,12 +556,16 @@
  *	space avaiable from the resume partition.
  */
 
-static int enough_swap(unsigned int nr_pages)
+static int enough_swap(unsigned int nr_pages, unsigned int flags)
 {
 	unsigned int free_swap = count_swap_pages(root_swap, 1);
+	unsigned int required;
 
 	pr_debug("PM: Free swap pages: %u\n", free_swap);
-	return free_swap > nr_pages + PAGES_FOR_IO;
+
+	required = PAGES_FOR_IO + ((flags & SF_NOCOMPRESS_MODE) ?
+		nr_pages : (nr_pages * LZO_CMP_PAGES) / LZO_UNC_PAGES + 1);
+	return free_swap > required;
 }
 
 /**
@@ -443,7 +592,7 @@
 		printk(KERN_ERR "PM: Cannot get swap writer\n");
 		return error;
 	}
-	if (!enough_swap(pages)) {
+	if (!enough_swap(pages, flags)) {
 		printk(KERN_ERR "PM: Not enough free swap\n");
 		error = -ENOSPC;
 		goto out_finish;
@@ -458,8 +607,11 @@
 	}
 	header = (struct swsusp_info *)data_of(snapshot);
 	error = swap_write_page(&handle, header, NULL);
-	if (!error)
-		error = save_image(&handle, &snapshot, pages - 1);
+	if (!error) {
+		error = (flags & SF_NOCOMPRESS_MODE) ?
+			save_image(&handle, &snapshot, pages - 1) :
+			save_image_lzo(&handle, &snapshot, pages - 1);
+	}
 out_finish:
 	error = swap_writer_finish(&handle, flags, error);
 	return error;
@@ -590,6 +742,127 @@
 }
 
 /**
+ * load_image_lzo - Load compressed image data and decompress them with LZO.
+ * @handle: Swap map handle to use for loading data.
+ * @snapshot: Image to copy uncompressed data into.
+ * @nr_to_read: Number of pages to load.
+ */
+static int load_image_lzo(struct swap_map_handle *handle,
+                          struct snapshot_handle *snapshot,
+                          unsigned int nr_to_read)
+{
+	unsigned int m;
+	int error = 0;
+	struct timeval start;
+	struct timeval stop;
+	unsigned nr_pages;
+	size_t off, unc_len, cmp_len;
+	unsigned char *unc, *cmp, *page;
+
+	page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+	if (!page) {
+		printk(KERN_ERR "PM: Failed to allocate LZO page\n");
+		return -ENOMEM;
+	}
+
+	unc = vmalloc(LZO_UNC_SIZE);
+	if (!unc) {
+		printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n");
+		free_page((unsigned long)page);
+		return -ENOMEM;
+	}
+
+	cmp = vmalloc(LZO_CMP_SIZE);
+	if (!cmp) {
+		printk(KERN_ERR "PM: Failed to allocate LZO compressed\n");
+		vfree(unc);
+		free_page((unsigned long)page);
+		return -ENOMEM;
+	}
+
+	printk(KERN_INFO
+		"PM: Loading and decompressing image data (%u pages) ...     ",
+		nr_to_read);
+	m = nr_to_read / 100;
+	if (!m)
+		m = 1;
+	nr_pages = 0;
+	do_gettimeofday(&start);
+
+	error = snapshot_write_next(snapshot);
+	if (error <= 0)
+		goto out_finish;
+
+	for (;;) {
+		error = swap_read_page(handle, page, NULL); /* sync */
+		if (error)
+			break;
+
+		cmp_len = *(size_t *)page;
+		if (unlikely(!cmp_len ||
+		             cmp_len > lzo1x_worst_compress(LZO_UNC_SIZE))) {
+			printk(KERN_ERR "PM: Invalid LZO compressed length\n");
+			error = -1;
+			break;
+		}
+
+		memcpy(cmp, page, PAGE_SIZE);
+		for (off = PAGE_SIZE; off < LZO_HEADER + cmp_len; off += PAGE_SIZE) {
+			error = swap_read_page(handle, page, NULL); /* sync */
+			if (error)
+				goto out_finish;
+
+			memcpy(cmp + off, page, PAGE_SIZE);
+		}
+
+		unc_len = LZO_UNC_SIZE;
+		error = lzo1x_decompress_safe(cmp + LZO_HEADER, cmp_len,
+		                              unc, &unc_len);
+		if (error < 0) {
+			printk(KERN_ERR "PM: LZO decompression failed\n");
+			break;
+		}
+
+		if (unlikely(!unc_len ||
+		             unc_len > LZO_UNC_SIZE ||
+		             unc_len & (PAGE_SIZE - 1))) {
+			printk(KERN_ERR "PM: Invalid LZO uncompressed length\n");
+			error = -1;
+			break;
+		}
+
+		for (off = 0; off < unc_len; off += PAGE_SIZE) {
+			memcpy(data_of(*snapshot), unc + off, PAGE_SIZE);
+
+			if (!(nr_pages % m))
+				printk("\b\b\b\b%3d%%", nr_pages / m);
+			nr_pages++;
+
+			error = snapshot_write_next(snapshot);
+			if (error <= 0)
+				goto out_finish;
+		}
+	}
+
+out_finish:
+	do_gettimeofday(&stop);
+	if (!error) {
+		printk("\b\b\b\bdone\n");
+		snapshot_write_finalize(snapshot);
+		if (!snapshot_image_loaded(snapshot))
+			error = -ENODATA;
+	} else
+		printk("\n");
+	swsusp_show_speed(&start, &stop, nr_to_read, "Read");
+
+	vfree(cmp);
+	vfree(unc);
+	free_page((unsigned long)page);
+
+	return error;
+}
+
+/**
  *	swsusp_read - read the hibernation image.
  *	@flags_p: flags passed by the "frozen" kernel in the image header should
  *		  be written into this memeory location
@@ -612,8 +885,11 @@
 		goto end;
 	if (!error)
 		error = swap_read_page(&handle, header, NULL);
-	if (!error)
-		error = load_image(&handle, &snapshot, header->pages - 1);
+	if (!error) {
+		error = (*flags_p & SF_NOCOMPRESS_MODE) ?
+			load_image(&handle, &snapshot, header->pages - 1) :
+			load_image_lzo(&handle, &snapshot, header->pages - 1);
+	}
 	swap_reader_finish(&handle);
 end:
 	if (!error)
@@ -640,7 +916,7 @@
 		if (error)
 			goto put;
 
-		if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
+		if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
 			error = hib_bio_write_page(swsusp_resume_block,
@@ -653,13 +929,13 @@
 		if (error)
 			blkdev_put(hib_resume_bdev, FMODE_READ);
 		else
-			pr_debug("PM: Signature found, resuming\n");
+			pr_debug("PM: Image signature found, resuming\n");
 	} else {
 		error = PTR_ERR(hib_resume_bdev);
 	}
 
 	if (error)
-		pr_debug("PM: Error %d checking image file\n", error);
+		pr_debug("PM: Image not found (code %d)\n", error);
 
 	return error;
 }
diff --git a/kernel/printk.c b/kernel/printk.c
index 8fe465a..2531017 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -85,7 +85,7 @@
  * provides serialisation for access to the entire console
  * driver system.
  */
-static DECLARE_MUTEX(console_sem);
+static DEFINE_SEMAPHORE(console_sem);
 struct console *console_drivers;
 EXPORT_SYMBOL_GPL(console_drivers);
 
@@ -556,7 +556,7 @@
 	/* If a crash is occurring, make sure we can't deadlock */
 	spin_lock_init(&logbuf_lock);
 	/* And make sure that we print immediately */
-	init_MUTEX(&console_sem);
+	sema_init(&console_sem, 1);
 }
 
 #if defined(CONFIG_PRINTK_TIME)
diff --git a/kernel/profile.c b/kernel/profile.c
index b22a899..66f841b 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -555,6 +555,7 @@
 static const struct file_operations proc_profile_operations = {
 	.read		= read_profile,
 	.write		= write_profile,
+	.llseek		= default_llseek,
 };
 
 #ifdef CONFIG_SMP
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 4d16983..a23a57a 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -73,12 +73,14 @@
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
 
 /**
- * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section?
+ * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
  *
  * Check for bottom half being disabled, which covers both the
  * CONFIG_PROVE_RCU and not cases.  Note that if someone uses
  * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled)
- * will show the situation.
+ * will show the situation.  This is useful for debug checks in functions
+ * that require that they be called within an RCU read-side critical
+ * section.
  *
  * Check debug_lockdep_rcu_enabled() to prevent false positives during boot.
  */
@@ -86,7 +88,7 @@
 {
 	if (!debug_lockdep_rcu_enabled())
 		return 1;
-	return in_softirq();
+	return in_softirq() || irqs_disabled();
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
 
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 196ec02..d806735 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -59,6 +59,14 @@
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+/* Forward declarations for rcutiny_plugin.h. */
+static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
+static void __call_rcu(struct rcu_head *head,
+		       void (*func)(struct rcu_head *rcu),
+		       struct rcu_ctrlblk *rcp);
+
+#include "rcutiny_plugin.h"
+
 #ifdef CONFIG_NO_HZ
 
 static long rcu_dynticks_nesting = 1;
@@ -140,6 +148,7 @@
 		rcu_sched_qs(cpu);
 	else if (!in_softirq())
 		rcu_bh_qs(cpu);
+	rcu_preempt_check_callbacks();
 }
 
 /*
@@ -162,6 +171,7 @@
 	*rcp->donetail = NULL;
 	if (rcp->curtail == rcp->donetail)
 		rcp->curtail = &rcp->rcucblist;
+	rcu_preempt_remove_callbacks(rcp);
 	rcp->donetail = &rcp->rcucblist;
 	local_irq_restore(flags);
 
@@ -182,6 +192,7 @@
 {
 	__rcu_process_callbacks(&rcu_sched_ctrlblk);
 	__rcu_process_callbacks(&rcu_bh_ctrlblk);
+	rcu_preempt_process_callbacks();
 }
 
 /*
@@ -223,15 +234,15 @@
 }
 
 /*
- * Post an RCU callback to be invoked after the end of an RCU grace
+ * Post an RCU callback to be invoked after the end of an RCU-sched grace
  * period.  But since we have but one CPU, that would be after any
  * quiescent state.
  */
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
 	__call_rcu(head, func, &rcu_sched_ctrlblk);
 }
-EXPORT_SYMBOL_GPL(call_rcu);
+EXPORT_SYMBOL_GPL(call_rcu_sched);
 
 /*
  * Post an RCU bottom-half callback to be invoked after any subsequent
@@ -243,20 +254,6 @@
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
 
-void rcu_barrier(void)
-{
-	struct rcu_synchronize rcu;
-
-	init_rcu_head_on_stack(&rcu.head);
-	init_completion(&rcu.completion);
-	/* Will wake me after RCU finished. */
-	call_rcu(&rcu.head, wakeme_after_rcu);
-	/* Wait for it. */
-	wait_for_completion(&rcu.completion);
-	destroy_rcu_head_on_stack(&rcu.head);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier);
-
 void rcu_barrier_bh(void)
 {
 	struct rcu_synchronize rcu;
@@ -289,5 +286,3 @@
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 }
-
-#include "rcutiny_plugin.h"
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index d223a92bc..6ceca4f 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -1,7 +1,7 @@
 /*
- * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition
  * Internal non-public definitions that provide either classic
- * or preemptable semantics.
+ * or preemptible semantics.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -17,11 +17,587 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
- * Copyright IBM Corporation, 2009
+ * Copyright (c) 2010 Linaro
  *
  * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
  */
 
+#ifdef CONFIG_TINY_PREEMPT_RCU
+
+#include <linux/delay.h>
+
+/* Global control variables for preemptible RCU. */
+struct rcu_preempt_ctrlblk {
+	struct rcu_ctrlblk rcb;	/* curtail: ->next ptr of last CB for GP. */
+	struct rcu_head **nexttail;
+				/* Tasks blocked in a preemptible RCU */
+				/*  read-side critical section while an */
+				/*  preemptible-RCU grace period is in */
+				/*  progress must wait for a later grace */
+				/*  period.  This pointer points to the */
+				/*  ->next pointer of the last task that */
+				/*  must wait for a later grace period, or */
+				/*  to &->rcb.rcucblist if there is no */
+				/*  such task. */
+	struct list_head blkd_tasks;
+				/* Tasks blocked in RCU read-side critical */
+				/*  section.  Tasks are placed at the head */
+				/*  of this list and age towards the tail. */
+	struct list_head *gp_tasks;
+				/* Pointer to the first task blocking the */
+				/*  current grace period, or NULL if there */
+				/*  is not such task. */
+	struct list_head *exp_tasks;
+				/* Pointer to first task blocking the */
+				/*  current expedited grace period, or NULL */
+				/*  if there is no such task.  If there */
+				/*  is no current expedited grace period, */
+				/*  then there cannot be any such task. */
+	u8 gpnum;		/* Current grace period. */
+	u8 gpcpu;		/* Last grace period blocked by the CPU. */
+	u8 completed;		/* Last grace period completed. */
+				/*  If all three are equal, RCU is idle. */
+};
+
+static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = {
+	.rcb.donetail = &rcu_preempt_ctrlblk.rcb.rcucblist,
+	.rcb.curtail = &rcu_preempt_ctrlblk.rcb.rcucblist,
+	.nexttail = &rcu_preempt_ctrlblk.rcb.rcucblist,
+	.blkd_tasks = LIST_HEAD_INIT(rcu_preempt_ctrlblk.blkd_tasks),
+};
+
+static int rcu_preempted_readers_exp(void);
+static void rcu_report_exp_done(void);
+
+/*
+ * Return true if the CPU has not yet responded to the current grace period.
+ */
+static int rcu_cpu_blocking_cur_gp(void)
+{
+	return rcu_preempt_ctrlblk.gpcpu != rcu_preempt_ctrlblk.gpnum;
+}
+
+/*
+ * Check for a running RCU reader.  Because there is only one CPU,
+ * there can be but one running RCU reader at a time.  ;-)
+ */
+static int rcu_preempt_running_reader(void)
+{
+	return current->rcu_read_lock_nesting;
+}
+
+/*
+ * Check for preempted RCU readers blocking any grace period.
+ * If the caller needs a reliable answer, it must disable hard irqs.
+ */
+static int rcu_preempt_blocked_readers_any(void)
+{
+	return !list_empty(&rcu_preempt_ctrlblk.blkd_tasks);
+}
+
+/*
+ * Check for preempted RCU readers blocking the current grace period.
+ * If the caller needs a reliable answer, it must disable hard irqs.
+ */
+static int rcu_preempt_blocked_readers_cgp(void)
+{
+	return rcu_preempt_ctrlblk.gp_tasks != NULL;
+}
+
+/*
+ * Return true if another preemptible-RCU grace period is needed.
+ */
+static int rcu_preempt_needs_another_gp(void)
+{
+	return *rcu_preempt_ctrlblk.rcb.curtail != NULL;
+}
+
+/*
+ * Return true if a preemptible-RCU grace period is in progress.
+ * The caller must disable hardirqs.
+ */
+static int rcu_preempt_gp_in_progress(void)
+{
+	return rcu_preempt_ctrlblk.completed != rcu_preempt_ctrlblk.gpnum;
+}
+
+/*
+ * Record a preemptible-RCU quiescent state for the specified CPU.  Note
+ * that this just means that the task currently running on the CPU is
+ * in a quiescent state.  There might be any number of tasks blocked
+ * while in an RCU read-side critical section.
+ *
+ * Unlike the other rcu_*_qs() functions, callers to this function
+ * must disable irqs in order to protect the assignment to
+ * ->rcu_read_unlock_special.
+ *
+ * Because this is a single-CPU implementation, the only way a grace
+ * period can end is if the CPU is in a quiescent state.  The reason is
+ * that a blocked preemptible-RCU reader can exit its critical section
+ * only if the CPU is running it at the time.  Therefore, when the
+ * last task blocking the current grace period exits its RCU read-side
+ * critical section, neither the CPU nor blocked tasks will be stopping
+ * the current grace period.  (In contrast, SMP implementations
+ * might have CPUs running in RCU read-side critical sections that
+ * block later grace periods -- but this is not possible given only
+ * one CPU.)
+ */
+static void rcu_preempt_cpu_qs(void)
+{
+	/* Record both CPU and task as having responded to current GP. */
+	rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum;
+	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+
+	/*
+	 * If there is no GP, or if blocked readers are still blocking GP,
+	 * then there is nothing more to do.
+	 */
+	if (!rcu_preempt_gp_in_progress() || rcu_preempt_blocked_readers_cgp())
+		return;
+
+	/* Advance callbacks. */
+	rcu_preempt_ctrlblk.completed = rcu_preempt_ctrlblk.gpnum;
+	rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.rcb.curtail;
+	rcu_preempt_ctrlblk.rcb.curtail = rcu_preempt_ctrlblk.nexttail;
+
+	/* If there are no blocked readers, next GP is done instantly. */
+	if (!rcu_preempt_blocked_readers_any())
+		rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail;
+
+	/* If there are done callbacks, make RCU_SOFTIRQ process them. */
+	if (*rcu_preempt_ctrlblk.rcb.donetail != NULL)
+		raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Start a new RCU grace period if warranted.  Hard irqs must be disabled.
+ */
+static void rcu_preempt_start_gp(void)
+{
+	if (!rcu_preempt_gp_in_progress() && rcu_preempt_needs_another_gp()) {
+
+		/* Official start of GP. */
+		rcu_preempt_ctrlblk.gpnum++;
+
+		/* Any blocked RCU readers block new GP. */
+		if (rcu_preempt_blocked_readers_any())
+			rcu_preempt_ctrlblk.gp_tasks =
+				rcu_preempt_ctrlblk.blkd_tasks.next;
+
+		/* If there is no running reader, CPU is done with GP. */
+		if (!rcu_preempt_running_reader())
+			rcu_preempt_cpu_qs();
+	}
+}
+
+/*
+ * We have entered the scheduler, and the current task might soon be
+ * context-switched away from.  If this task is in an RCU read-side
+ * critical section, we will no longer be able to rely on the CPU to
+ * record that fact, so we enqueue the task on the blkd_tasks list.
+ * If the task started after the current grace period began, as recorded
+ * by ->gpcpu, we enqueue at the beginning of the list.  Otherwise
+ * before the element referenced by ->gp_tasks (or at the tail if
+ * ->gp_tasks is NULL) and point ->gp_tasks at the newly added element.
+ * The task will dequeue itself when it exits the outermost enclosing
+ * RCU read-side critical section.  Therefore, the current grace period
+ * cannot be permitted to complete until the ->gp_tasks pointer becomes
+ * NULL.
+ *
+ * Caller must disable preemption.
+ */
+void rcu_preempt_note_context_switch(void)
+{
+	struct task_struct *t = current;
+	unsigned long flags;
+
+	local_irq_save(flags); /* must exclude scheduler_tick(). */
+	if (rcu_preempt_running_reader() &&
+	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
+
+		/* Possibly blocking in an RCU read-side critical section. */
+		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
+
+		/*
+		 * If this CPU has already checked in, then this task
+		 * will hold up the next grace period rather than the
+		 * current grace period.  Queue the task accordingly.
+		 * If the task is queued for the current grace period
+		 * (i.e., this CPU has not yet passed through a quiescent
+		 * state for the current grace period), then as long
+		 * as that task remains queued, the current grace period
+		 * cannot end.
+		 */
+		list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks);
+		if (rcu_cpu_blocking_cur_gp())
+			rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry;
+	}
+
+	/*
+	 * Either we were not in an RCU read-side critical section to
+	 * begin with, or we have now recorded that critical section
+	 * globally.  Either way, we can now note a quiescent state
+	 * for this CPU.  Again, if we were in an RCU read-side critical
+	 * section, and if that critical section was blocking the current
+	 * grace period, then the fact that the task has been enqueued
+	 * means that current grace period continues to be blocked.
+	 */
+	rcu_preempt_cpu_qs();
+	local_irq_restore(flags);
+}
+
+/*
+ * Tiny-preemptible RCU implementation for rcu_read_lock().
+ * Just increment ->rcu_read_lock_nesting, shared state will be updated
+ * if we block.
+ */
+void __rcu_read_lock(void)
+{
+	current->rcu_read_lock_nesting++;
+	barrier();  /* needed if we ever invoke rcu_read_lock in rcutiny.c */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_lock);
+
+/*
+ * Handle special cases during rcu_read_unlock(), such as needing to
+ * notify RCU core processing or task having blocked during the RCU
+ * read-side critical section.
+ */
+static void rcu_read_unlock_special(struct task_struct *t)
+{
+	int empty;
+	int empty_exp;
+	unsigned long flags;
+	struct list_head *np;
+	int special;
+
+	/*
+	 * NMI handlers cannot block and cannot safely manipulate state.
+	 * They therefore cannot possibly be special, so just leave.
+	 */
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+
+	/*
+	 * If RCU core is waiting for this CPU to exit critical section,
+	 * let it know that we have done so.
+	 */
+	special = t->rcu_read_unlock_special;
+	if (special & RCU_READ_UNLOCK_NEED_QS)
+		rcu_preempt_cpu_qs();
+
+	/* Hardware IRQ handlers cannot block. */
+	if (in_irq()) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	/* Clean up if blocked during RCU read-side critical section. */
+	if (special & RCU_READ_UNLOCK_BLOCKED) {
+		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
+
+		/*
+		 * Remove this task from the ->blkd_tasks list and adjust
+		 * any pointers that might have been referencing it.
+		 */
+		empty = !rcu_preempt_blocked_readers_cgp();
+		empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL;
+		np = t->rcu_node_entry.next;
+		if (np == &rcu_preempt_ctrlblk.blkd_tasks)
+			np = NULL;
+		list_del(&t->rcu_node_entry);
+		if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks)
+			rcu_preempt_ctrlblk.gp_tasks = np;
+		if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks)
+			rcu_preempt_ctrlblk.exp_tasks = np;
+		INIT_LIST_HEAD(&t->rcu_node_entry);
+
+		/*
+		 * If this was the last task on the current list, and if
+		 * we aren't waiting on the CPU, report the quiescent state
+		 * and start a new grace period if needed.
+		 */
+		if (!empty && !rcu_preempt_blocked_readers_cgp()) {
+			rcu_preempt_cpu_qs();
+			rcu_preempt_start_gp();
+		}
+
+		/*
+		 * If this was the last task on the expedited lists,
+		 * then we need wake up the waiting task.
+		 */
+		if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL)
+			rcu_report_exp_done();
+	}
+	local_irq_restore(flags);
+}
+
+/*
+ * Tiny-preemptible RCU implementation for rcu_read_unlock().
+ * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
+ * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
+ * invoke rcu_read_unlock_special() to clean up after a context switch
+ * in an RCU read-side critical section and other special cases.
+ */
+void __rcu_read_unlock(void)
+{
+	struct task_struct *t = current;
+
+	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutiny.c */
+	--t->rcu_read_lock_nesting;
+	barrier();  /* decrement before load of ->rcu_read_unlock_special */
+	if (t->rcu_read_lock_nesting == 0 &&
+	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+		rcu_read_unlock_special(t);
+#ifdef CONFIG_PROVE_LOCKING
+	WARN_ON_ONCE(t->rcu_read_lock_nesting < 0);
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_unlock);
+
+/*
+ * Check for a quiescent state from the current CPU.  When a task blocks,
+ * the task is recorded in the rcu_preempt_ctrlblk structure, which is
+ * checked elsewhere.  This is called from the scheduling-clock interrupt.
+ *
+ * Caller must disable hard irqs.
+ */
+static void rcu_preempt_check_callbacks(void)
+{
+	struct task_struct *t = current;
+
+	if (rcu_preempt_gp_in_progress() &&
+	    (!rcu_preempt_running_reader() ||
+	     !rcu_cpu_blocking_cur_gp()))
+		rcu_preempt_cpu_qs();
+	if (&rcu_preempt_ctrlblk.rcb.rcucblist !=
+	    rcu_preempt_ctrlblk.rcb.donetail)
+		raise_softirq(RCU_SOFTIRQ);
+	if (rcu_preempt_gp_in_progress() &&
+	    rcu_cpu_blocking_cur_gp() &&
+	    rcu_preempt_running_reader())
+		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
+}
+
+/*
+ * TINY_PREEMPT_RCU has an extra callback-list tail pointer to
+ * update, so this is invoked from __rcu_process_callbacks() to
+ * handle that case.  Of course, it is invoked for all flavors of
+ * RCU, but RCU callbacks can appear only on one of the lists, and
+ * neither ->nexttail nor ->donetail can possibly be NULL, so there
+ * is no need for an explicit check.
+ */
+static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
+{
+	if (rcu_preempt_ctrlblk.nexttail == rcp->donetail)
+		rcu_preempt_ctrlblk.nexttail = &rcp->rcucblist;
+}
+
+/*
+ * Process callbacks for preemptible RCU.
+ */
+static void rcu_preempt_process_callbacks(void)
+{
+	__rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
+}
+
+/*
+ * Queue a preemptible -RCU callback for invocation after a grace period.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	unsigned long flags;
+
+	debug_rcu_head_queue(head);
+	head->func = func;
+	head->next = NULL;
+
+	local_irq_save(flags);
+	*rcu_preempt_ctrlblk.nexttail = head;
+	rcu_preempt_ctrlblk.nexttail = &head->next;
+	rcu_preempt_start_gp();  /* checks to see if GP needed. */
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+void rcu_barrier(void)
+{
+	struct rcu_synchronize rcu;
+
+	init_rcu_head_on_stack(&rcu.head);
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
+	destroy_rcu_head_on_stack(&rcu.head);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+/*
+ * synchronize_rcu - wait until a grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full grace
+ * period has elapsed, in other words after all currently executing RCU
+ * read-side critical sections have completed.  RCU read-side critical
+ * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
+ * and may be nested.
+ */
+void synchronize_rcu(void)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (!rcu_scheduler_active)
+		return;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+	WARN_ON_ONCE(rcu_preempt_running_reader());
+	if (!rcu_preempt_blocked_readers_any())
+		return;
+
+	/* Once we get past the fastpath checks, same code as rcu_barrier(). */
+	rcu_barrier();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu);
+
+static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
+static unsigned long sync_rcu_preempt_exp_count;
+static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
+
+/*
+ * Return non-zero if there are any tasks in RCU read-side critical
+ * sections blocking the current preemptible-RCU expedited grace period.
+ * If there is no preemptible-RCU expedited grace period currently in
+ * progress, returns zero unconditionally.
+ */
+static int rcu_preempted_readers_exp(void)
+{
+	return rcu_preempt_ctrlblk.exp_tasks != NULL;
+}
+
+/*
+ * Report the exit from RCU read-side critical section for the last task
+ * that queued itself during or before the current expedited preemptible-RCU
+ * grace period.
+ */
+static void rcu_report_exp_done(void)
+{
+	wake_up(&sync_rcu_preempt_exp_wq);
+}
+
+/*
+ * Wait for an rcu-preempt grace period, but expedite it.  The basic idea
+ * is to rely in the fact that there is but one CPU, and that it is
+ * illegal for a task to invoke synchronize_rcu_expedited() while in a
+ * preemptible-RCU read-side critical section.  Therefore, any such
+ * critical sections must correspond to blocked tasks, which must therefore
+ * be on the ->blkd_tasks list.  So just record the current head of the
+ * list in the ->exp_tasks pointer, and wait for all tasks including and
+ * after the task pointed to by ->exp_tasks to drain.
+ */
+void synchronize_rcu_expedited(void)
+{
+	unsigned long flags;
+	struct rcu_preempt_ctrlblk *rpcp = &rcu_preempt_ctrlblk;
+	unsigned long snap;
+
+	barrier(); /* ensure prior action seen before grace period. */
+
+	WARN_ON_ONCE(rcu_preempt_running_reader());
+
+	/*
+	 * Acquire lock so that there is only one preemptible RCU grace
+	 * period in flight.  Of course, if someone does the expedited
+	 * grace period for us while we are acquiring the lock, just leave.
+	 */
+	snap = sync_rcu_preempt_exp_count + 1;
+	mutex_lock(&sync_rcu_preempt_exp_mutex);
+	if (ULONG_CMP_LT(snap, sync_rcu_preempt_exp_count))
+		goto unlock_mb_ret; /* Others did our work for us. */
+
+	local_irq_save(flags);
+
+	/*
+	 * All RCU readers have to already be on blkd_tasks because
+	 * we cannot legally be executing in an RCU read-side critical
+	 * section.
+	 */
+
+	/* Snapshot current head of ->blkd_tasks list. */
+	rpcp->exp_tasks = rpcp->blkd_tasks.next;
+	if (rpcp->exp_tasks == &rpcp->blkd_tasks)
+		rpcp->exp_tasks = NULL;
+	local_irq_restore(flags);
+
+	/* Wait for tail of ->blkd_tasks list to drain. */
+	if (rcu_preempted_readers_exp())
+		wait_event(sync_rcu_preempt_exp_wq,
+			   !rcu_preempted_readers_exp());
+
+	/* Clean up and exit. */
+	barrier(); /* ensure expedited GP seen before counter increment. */
+	sync_rcu_preempt_exp_count++;
+unlock_mb_ret:
+	mutex_unlock(&sync_rcu_preempt_exp_mutex);
+	barrier(); /* ensure subsequent action seen after grace period. */
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
+ * Does preemptible RCU need the CPU to stay out of dynticks mode?
+ */
+int rcu_preempt_needs_cpu(void)
+{
+	if (!rcu_preempt_running_reader())
+		rcu_preempt_cpu_qs();
+	return rcu_preempt_ctrlblk.rcb.rcucblist != NULL;
+}
+
+/*
+ * Check for a task exiting while in a preemptible -RCU read-side
+ * critical section, clean up if so.  No need to issue warnings,
+ * as debug_check_no_locks_held() already does this if lockdep
+ * is enabled.
+ */
+void exit_rcu(void)
+{
+	struct task_struct *t = current;
+
+	if (t->rcu_read_lock_nesting == 0)
+		return;
+	t->rcu_read_lock_nesting = 1;
+	rcu_read_unlock();
+}
+
+#else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
+
+/*
+ * Because preemptible RCU does not exist, it never has any callbacks
+ * to check.
+ */
+static void rcu_preempt_check_callbacks(void)
+{
+}
+
+/*
+ * Because preemptible RCU does not exist, it never has any callbacks
+ * to remove.
+ */
+static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
+{
+}
+
+/*
+ * Because preemptible RCU does not exist, it never has any callbacks
+ * to process.
+ */
+static void rcu_preempt_process_callbacks(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 #include <linux/kernel_stat.h>
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 2e2726d..9d8e8fb 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -120,7 +120,7 @@
 };
 
 static LIST_HEAD(rcu_torture_freelist);
-static struct rcu_torture *rcu_torture_current;
+static struct rcu_torture __rcu *rcu_torture_current;
 static long rcu_torture_current_version;
 static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
 static DEFINE_SPINLOCK(rcu_torture_lock);
@@ -153,8 +153,10 @@
 #define FULLSTOP_SHUTDOWN 1	/* System shutdown with rcutorture running. */
 #define FULLSTOP_RMMOD    2	/* Normal rmmod of rcutorture. */
 static int fullstop = FULLSTOP_RMMOD;
-DEFINE_MUTEX(fullstop_mutex);	/* Protect fullstop transitions and spawning */
-				/*  of kthreads. */
+/*
+ * Protect fullstop transitions and spawning of kthreads.
+ */
+static DEFINE_MUTEX(fullstop_mutex);
 
 /*
  * Detect and respond to a system shutdown.
@@ -303,6 +305,10 @@
 		mdelay(longdelay_ms);
 	if (!(rcu_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
+#ifdef CONFIG_PREEMPT
+	if (!preempt_count() && !(rcu_random(rrsp) % (nrealreaders * 20000)))
+		preempt_schedule();  /* No QS if preempt_disable() in effect */
+#endif
 }
 
 static void rcu_torture_read_unlock(int idx) __releases(RCU)
@@ -536,6 +542,8 @@
 	delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay * uspertick);
 	if (!delay)
 		schedule_timeout_interruptible(longdelay);
+	else
+		rcu_read_delay(rrsp);
 }
 
 static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
@@ -731,7 +739,8 @@
 			continue;
 		rp->rtort_pipe_count = 0;
 		udelay(rcu_random(&rand) & 0x3ff);
-		old_rp = rcu_torture_current;
+		old_rp = rcu_dereference_check(rcu_torture_current,
+					       current == writer_task);
 		rp->rtort_mbtest = 1;
 		rcu_assign_pointer(rcu_torture_current, rp);
 		smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index d5bc439..ccdc04c 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -143,6 +143,11 @@
 module_param(qhimark, int, 0);
 module_param(qlowmark, int, 0);
 
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+int rcu_cpu_stall_suppress __read_mostly = RCU_CPU_STALL_SUPPRESS_INIT;
+module_param(rcu_cpu_stall_suppress, int, 0644);
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
 static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
 static int rcu_pending(int cpu);
 
@@ -450,7 +455,7 @@
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
-int rcu_cpu_stall_panicking __read_mostly;
+int rcu_cpu_stall_suppress __read_mostly;
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
@@ -482,8 +487,11 @@
 	rcu_print_task_stall(rnp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
-	/* OK, time to rat on our buddy... */
-
+	/*
+	 * OK, time to rat on our buddy...
+	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * RCU CPU stall warnings.
+	 */
 	printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks: {",
 	       rsp->name);
 	rcu_for_each_leaf_node(rsp, rnp) {
@@ -512,6 +520,11 @@
 	unsigned long flags;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	/*
+	 * OK, time to rat on ourselves...
+	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * RCU CPU stall warnings.
+	 */
 	printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n",
 	       rsp->name, smp_processor_id(), jiffies - rsp->gp_start);
 	trigger_all_cpu_backtrace();
@@ -530,11 +543,11 @@
 	long delta;
 	struct rcu_node *rnp;
 
-	if (rcu_cpu_stall_panicking)
+	if (rcu_cpu_stall_suppress)
 		return;
-	delta = jiffies - rsp->jiffies_stall;
+	delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall);
 	rnp = rdp->mynode;
-	if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
+	if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && delta >= 0) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
@@ -548,10 +561,26 @@
 
 static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
 {
-	rcu_cpu_stall_panicking = 1;
+	rcu_cpu_stall_suppress = 1;
 	return NOTIFY_DONE;
 }
 
+/**
+ * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
+ *
+ * Set the stall-warning timeout way off into the future, thus preventing
+ * any RCU CPU stall-warning messages from appearing in the current set of
+ * RCU grace periods.
+ *
+ * The caller must disable hard irqs.
+ */
+void rcu_cpu_stall_reset(void)
+{
+	rcu_sched_state.jiffies_stall = jiffies + ULONG_MAX / 2;
+	rcu_bh_state.jiffies_stall = jiffies + ULONG_MAX / 2;
+	rcu_preempt_stall_reset();
+}
+
 static struct notifier_block rcu_panic_block = {
 	.notifier_call = rcu_panic,
 };
@@ -571,6 +600,10 @@
 {
 }
 
+void rcu_cpu_stall_reset(void)
+{
+}
+
 static void __init check_cpu_stall_init(void)
 {
 }
@@ -712,7 +745,7 @@
 rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
-	struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	if (!cpu_needs_another_gp(rsp, rdp) || rsp->fqs_active) {
@@ -960,7 +993,7 @@
 static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
 {
 	int i;
-	struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
 	if (rdp->nxtlist == NULL)
 		return;  /* irqs disabled, so comparison is stable. */
@@ -971,6 +1004,7 @@
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
 		rdp->nxttail[i] = &rdp->nxtlist;
 	rsp->orphan_qlen += rdp->qlen;
+	rdp->n_cbs_orphaned += rdp->qlen;
 	rdp->qlen = 0;
 	raw_spin_unlock(&rsp->onofflock);  /* irqs remain disabled. */
 }
@@ -984,7 +1018,7 @@
 	struct rcu_data *rdp;
 
 	raw_spin_lock_irqsave(&rsp->onofflock, flags);
-	rdp = rsp->rda[smp_processor_id()];
+	rdp = this_cpu_ptr(rsp->rda);
 	if (rsp->orphan_cbs_list == NULL) {
 		raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 		return;
@@ -992,6 +1026,7 @@
 	*rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
 	rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail;
 	rdp->qlen += rsp->orphan_qlen;
+	rdp->n_cbs_adopted += rsp->orphan_qlen;
 	rsp->orphan_cbs_list = NULL;
 	rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
 	rsp->orphan_qlen = 0;
@@ -1007,7 +1042,7 @@
 	unsigned long flags;
 	unsigned long mask;
 	int need_report = 0;
-	struct rcu_data *rdp = rsp->rda[cpu];
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp;
 
 	/* Exclude any attempts to start a new grace period. */
@@ -1123,6 +1158,7 @@
 
 	/* Update count, and requeue any remaining callbacks. */
 	rdp->qlen -= count;
+	rdp->n_cbs_invoked += count;
 	if (list != NULL) {
 		*tail = rdp->nxtlist;
 		rdp->nxtlist = list;
@@ -1226,7 +1262,8 @@
 		cpu = rnp->grplo;
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
-			if ((rnp->qsmask & bit) != 0 && f(rsp->rda[cpu]))
+			if ((rnp->qsmask & bit) != 0 &&
+			    f(per_cpu_ptr(rsp->rda, cpu)))
 				mask |= bit;
 		}
 		if (mask != 0) {
@@ -1402,7 +1439,7 @@
 	 * a quiescent state betweentimes.
 	 */
 	local_irq_save(flags);
-	rdp = rsp->rda[smp_processor_id()];
+	rdp = this_cpu_ptr(rsp->rda);
 	rcu_process_gp_end(rsp, rdp);
 	check_for_new_grace_period(rsp, rdp);
 
@@ -1701,7 +1738,7 @@
 {
 	unsigned long flags;
 	int i;
-	struct rcu_data *rdp = rsp->rda[cpu];
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
@@ -1729,7 +1766,7 @@
 {
 	unsigned long flags;
 	unsigned long mask;
-	struct rcu_data *rdp = rsp->rda[cpu];
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
@@ -1865,7 +1902,8 @@
 /*
  * Helper function for rcu_init() that initializes one rcu_state structure.
  */
-static void __init rcu_init_one(struct rcu_state *rsp)
+static void __init rcu_init_one(struct rcu_state *rsp,
+		struct rcu_data __percpu *rda)
 {
 	static char *buf[] = { "rcu_node_level_0",
 			       "rcu_node_level_1",
@@ -1918,37 +1956,23 @@
 		}
 	}
 
+	rsp->rda = rda;
 	rnp = rsp->level[NUM_RCU_LVLS - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
 			rnp++;
-		rsp->rda[i]->mynode = rnp;
+		per_cpu_ptr(rsp->rda, i)->mynode = rnp;
 		rcu_boot_init_percpu_data(i, rsp);
 	}
 }
 
-/*
- * Helper macro for __rcu_init() and __rcu_init_preempt().  To be used
- * nowhere else!  Assigns leaf node pointers into each CPU's rcu_data
- * structure.
- */
-#define RCU_INIT_FLAVOR(rsp, rcu_data) \
-do { \
-	int i; \
-	\
-	for_each_possible_cpu(i) { \
-		(rsp)->rda[i] = &per_cpu(rcu_data, i); \
-	} \
-	rcu_init_one(rsp); \
-} while (0)
-
 void __init rcu_init(void)
 {
 	int cpu;
 
 	rcu_bootup_announce();
-	RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
-	RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
+	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	__rcu_init_preempt();
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 14c040b..91d4170 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -202,6 +202,9 @@
 	long		qlen;		/* # of queued callbacks */
 	long		qlen_last_fqs_check;
 					/* qlen at last check for QS forcing */
+	unsigned long	n_cbs_invoked;	/* count of RCU cbs invoked. */
+	unsigned long	n_cbs_orphaned;	/* RCU cbs sent to orphanage. */
+	unsigned long	n_cbs_adopted;	/* RCU cbs adopted from orphanage. */
 	unsigned long	n_force_qs_snap;
 					/* did other CPU force QS recently? */
 	long		blimit;		/* Upper limit on a processed batch */
@@ -254,19 +257,23 @@
 #define RCU_STALL_DELAY_DELTA	       0
 #endif
 
-#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ + RCU_STALL_DELAY_DELTA)
+#define RCU_SECONDS_TILL_STALL_CHECK   (CONFIG_RCU_CPU_STALL_TIMEOUT * HZ + \
+					RCU_STALL_DELAY_DELTA)
 						/* for rsp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ + RCU_STALL_DELAY_DELTA)
+#define RCU_SECONDS_TILL_STALL_RECHECK (3 * RCU_SECONDS_TILL_STALL_CHECK + 30)
 						/* for rsp->jiffies_stall */
 #define RCU_STALL_RAT_DELAY		2	/* Allow other CPUs time */
 						/*  to take at least one */
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR_RUNNABLE
+#define RCU_CPU_STALL_SUPPRESS_INIT 0
+#else
+#define RCU_CPU_STALL_SUPPRESS_INIT 1
+#endif
 
-#define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
-#define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -283,7 +290,7 @@
 	struct rcu_node *level[NUM_RCU_LVLS];	/* Hierarchy levels. */
 	u32 levelcnt[MAX_RCU_LVLS + 1];		/* # nodes in each level. */
 	u8 levelspread[NUM_RCU_LVLS];		/* kids/node in each level. */
-	struct rcu_data *rda[NR_CPUS];		/* array of rdp pointers. */
+	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 
@@ -365,6 +372,7 @@
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
+static void rcu_preempt_stall_reset(void);
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 0e4f420..71a4147 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -57,7 +57,7 @@
 	printk(KERN_INFO
 	       "\tRCU-based detection of stalled CPUs is disabled.\n");
 #endif
-#ifndef CONFIG_RCU_CPU_STALL_VERBOSE
+#if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
 	printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
 #endif
 #if NUM_RCU_LVL_4 != 0
@@ -154,7 +154,7 @@
 	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = rcu_preempt_state.rda[cpu];
+		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -201,7 +201,7 @@
  */
 void __rcu_read_lock(void)
 {
-	ACCESS_ONCE(current->rcu_read_lock_nesting)++;
+	current->rcu_read_lock_nesting++;
 	barrier();  /* needed if we ever invoke rcu_read_lock in rcutree.c */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -344,7 +344,9 @@
 	struct task_struct *t = current;
 
 	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
-	if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
+	--t->rcu_read_lock_nesting;
+	barrier();  /* decrement before load of ->rcu_read_unlock_special */
+	if (t->rcu_read_lock_nesting == 0 &&
 	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
 		rcu_read_unlock_special(t);
 #ifdef CONFIG_PROVE_LOCKING
@@ -417,6 +419,16 @@
 	}
 }
 
+/*
+ * Suppress preemptible RCU's CPU stall warnings by pushing the
+ * time of the next stall-warning message comfortably far into the
+ * future.
+ */
+static void rcu_preempt_stall_reset(void)
+{
+	rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2;
+}
+
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
@@ -546,9 +558,11 @@
  *
  * Control will return to the caller some time after a full grace
  * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed.  RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
+ * read-side critical sections have completed.  Note, however, that
+ * upon return from synchronize_rcu(), the caller might well be executing
+ * concurrently with new RCU read-side critical sections that began while
+ * synchronize_rcu() was waiting.  RCU read-side critical sections are
+ * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
  */
 void synchronize_rcu(void)
 {
@@ -771,7 +785,7 @@
  */
 static void __init __rcu_init_preempt(void)
 {
-	RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
+	rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
 }
 
 /*
@@ -865,6 +879,14 @@
 {
 }
 
+/*
+ * Because preemptible RCU does not exist, there is no need to suppress
+ * its CPU stall warnings.
+ */
+static void rcu_preempt_stall_reset(void)
+{
+}
+
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
@@ -919,15 +941,6 @@
 }
 
 /*
- * In classic RCU, call_rcu() is just call_rcu_sched().
- */
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
-{
-	call_rcu_sched(head, func);
-}
-EXPORT_SYMBOL_GPL(call_rcu);
-
-/*
  * Wait for an rcu-preempt grace period, but make it happen quickly.
  * But because preemptable RCU does not exist, map to rcu-sched.
  */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 36c95b4..d15430b 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -64,7 +64,9 @@
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
-	seq_printf(m, " ql=%ld b=%ld\n", rdp->qlen, rdp->blimit);
+	seq_printf(m, " ql=%ld b=%ld", rdp->qlen, rdp->blimit);
+	seq_printf(m, " ci=%lu co=%lu ca=%lu\n",
+		   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
 
 #define PRINT_RCU_DATA(name, func, m) \
@@ -119,7 +121,9 @@
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
-	seq_printf(m, ",%ld,%ld\n", rdp->qlen, rdp->blimit);
+	seq_printf(m, ",%ld,%ld", rdp->qlen, rdp->blimit);
+	seq_printf(m, ",%lu,%lu,%lu\n",
+		   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
 
 static int show_rcudata_csv(struct seq_file *m, void *unused)
@@ -128,7 +132,7 @@
 #ifdef CONFIG_NO_HZ
 	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
-	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n");
+	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	seq_puts(m, "\"rcu_preempt:\"\n");
 	PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m);
@@ -262,7 +266,7 @@
 	struct rcu_data *rdp;
 
 	for_each_possible_cpu(cpu) {
-		rdp = rsp->rda[cpu];
+		rdp = per_cpu_ptr(rsp->rda, cpu);
 		if (rdp->beenonline)
 			print_one_rcu_pending(m, rdp);
 	}
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index a56f629..66cb89b 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -76,7 +76,9 @@
 		}
 
 		if (!lockwakeup && td->bkl == 4) {
+#ifdef CONFIG_LOCK_KERNEL
 			unlock_kernel();
+#endif
 			td->bkl = 0;
 		}
 		return 0;
@@ -133,14 +135,18 @@
 		if (td->bkl)
 			return 0;
 		td->bkl = 1;
+#ifdef CONFIG_LOCK_KERNEL
 		lock_kernel();
+#endif
 		td->bkl = 4;
 		return 0;
 
 	case RTTEST_UNLOCKBKL:
 		if (td->bkl != 4)
 			break;
+#ifdef CONFIG_LOCK_KERNEL
 		unlock_kernel();
+#endif
 		td->bkl = 0;
 		return 0;
 
diff --git a/kernel/sched.c b/kernel/sched.c
index dc85ceb..d42992b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -426,9 +426,7 @@
 	 */
 	cpumask_var_t rto_mask;
 	atomic_t rto_count;
-#ifdef CONFIG_SMP
 	struct cpupri cpupri;
-#endif
 };
 
 /*
@@ -437,7 +435,7 @@
  */
 static struct root_domain def_root_domain;
 
-#endif
+#endif /* CONFIG_SMP */
 
 /*
  * This is the main, per-CPU runqueue data structure.
@@ -488,11 +486,12 @@
 	 */
 	unsigned long nr_uninterruptible;
 
-	struct task_struct *curr, *idle;
+	struct task_struct *curr, *idle, *stop;
 	unsigned long next_balance;
 	struct mm_struct *prev_mm;
 
 	u64 clock;
+	u64 clock_task;
 
 	atomic_t nr_iowait;
 
@@ -520,6 +519,10 @@
 	u64 avg_idle;
 #endif
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	u64 prev_irq_time;
+#endif
+
 	/* calc_load related fields */
 	unsigned long calc_load_update;
 	long calc_load_active;
@@ -643,10 +646,22 @@
 
 #endif /* CONFIG_CGROUP_SCHED */
 
+static u64 irq_time_cpu(int cpu);
+static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+
 inline void update_rq_clock(struct rq *rq)
 {
-	if (!rq->skip_clock_update)
-		rq->clock = sched_clock_cpu(cpu_of(rq));
+	if (!rq->skip_clock_update) {
+		int cpu = cpu_of(rq);
+		u64 irq_time;
+
+		rq->clock = sched_clock_cpu(cpu);
+		irq_time = irq_time_cpu(cpu);
+		if (rq->clock - irq_time > rq->clock_task)
+			rq->clock_task = rq->clock - irq_time;
+
+		sched_irq_time_avg_update(rq, irq_time);
+	}
 }
 
 /*
@@ -723,7 +738,7 @@
 		size_t cnt, loff_t *ppos)
 {
 	char buf[64];
-	char *cmp = buf;
+	char *cmp;
 	int neg = 0;
 	int i;
 
@@ -734,6 +749,7 @@
 		return -EFAULT;
 
 	buf[cnt] = 0;
+	cmp = strstrip(buf);
 
 	if (strncmp(buf, "NO_", 3) == 0) {
 		neg = 1;
@@ -741,9 +757,7 @@
 	}
 
 	for (i = 0; sched_feat_names[i]; i++) {
-		int len = strlen(sched_feat_names[i]);
-
-		if (strncmp(cmp, sched_feat_names[i], len) == 0) {
+		if (strcmp(cmp, sched_feat_names[i]) == 0) {
 			if (neg)
 				sysctl_sched_features &= ~(1UL << i);
 			else
@@ -1840,7 +1854,7 @@
 
 static const struct sched_class rt_sched_class;
 
-#define sched_class_highest (&rt_sched_class)
+#define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
@@ -1858,12 +1872,6 @@
 
 static void set_load_weight(struct task_struct *p)
 {
-	if (task_has_rt_policy(p)) {
-		p->se.load.weight = 0;
-		p->se.load.inv_weight = WMULT_CONST;
-		return;
-	}
-
 	/*
 	 * SCHED_IDLE tasks get minimal weight:
 	 */
@@ -1917,13 +1925,132 @@
 	dec_nr_running(rq);
 }
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+/*
+ * There are no locks covering percpu hardirq/softirq time.
+ * They are only modified in account_system_vtime, on corresponding CPU
+ * with interrupts disabled. So, writes are safe.
+ * They are read and saved off onto struct rq in update_rq_clock().
+ * This may result in other CPU reading this CPU's irq time and can
+ * race with irq/account_system_vtime on this CPU. We would either get old
+ * or new value (or semi updated value on 32 bit) with a side effect of
+ * accounting a slice of irq time to wrong task when irq is in progress
+ * while we read rq->clock. That is a worthy compromise in place of having
+ * locks on each irq in account_system_time.
+ */
+static DEFINE_PER_CPU(u64, cpu_hardirq_time);
+static DEFINE_PER_CPU(u64, cpu_softirq_time);
+
+static DEFINE_PER_CPU(u64, irq_start_time);
+static int sched_clock_irqtime;
+
+void enable_sched_clock_irqtime(void)
+{
+	sched_clock_irqtime = 1;
+}
+
+void disable_sched_clock_irqtime(void)
+{
+	sched_clock_irqtime = 0;
+}
+
+static u64 irq_time_cpu(int cpu)
+{
+	if (!sched_clock_irqtime)
+		return 0;
+
+	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+}
+
+void account_system_vtime(struct task_struct *curr)
+{
+	unsigned long flags;
+	int cpu;
+	u64 now, delta;
+
+	if (!sched_clock_irqtime)
+		return;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+	now = sched_clock_cpu(cpu);
+	delta = now - per_cpu(irq_start_time, cpu);
+	per_cpu(irq_start_time, cpu) = now;
+	/*
+	 * We do not account for softirq time from ksoftirqd here.
+	 * We want to continue accounting softirq time to ksoftirqd thread
+	 * in that case, so as not to confuse scheduler with a special task
+	 * that do not consume any time, but still wants to run.
+	 */
+	if (hardirq_count())
+		per_cpu(cpu_hardirq_time, cpu) += delta;
+	else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+		per_cpu(cpu_softirq_time, cpu) += delta;
+
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(account_system_vtime);
+
+static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+{
+	if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
+		u64 delta_irq = curr_irq_time - rq->prev_irq_time;
+		rq->prev_irq_time = curr_irq_time;
+		sched_rt_avg_update(rq, delta_irq);
+	}
+}
+
+#else
+
+static u64 irq_time_cpu(int cpu)
+{
+	return 0;
+}
+
+static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
+
+#endif
+
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
 #endif
 
+void sched_set_stop_task(int cpu, struct task_struct *stop)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+	struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+	if (stop) {
+		/*
+		 * Make it appear like a SCHED_FIFO task, its something
+		 * userspace knows about and won't get confused about.
+		 *
+		 * Also, it will make PI more or less work without too
+		 * much confusion -- but then, stop work should not
+		 * rely on PI working anyway.
+		 */
+		sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
+
+		stop->sched_class = &stop_sched_class;
+	}
+
+	cpu_rq(cpu)->stop = stop;
+
+	if (old_stop) {
+		/*
+		 * Reset it back to a normal scheduling class so that
+		 * it can die in pieces.
+		 */
+		old_stop->sched_class = &rt_sched_class;
+	}
+}
+
 /*
  * __normal_prio - return the priority that is based on the static prio
  */
@@ -2003,6 +2130,9 @@
 	if (p->sched_class != &fair_sched_class)
 		return 0;
 
+	if (unlikely(p->policy == SCHED_IDLE))
+		return 0;
+
 	/*
 	 * Buddy candidates are cache hot:
 	 */
@@ -2852,14 +2982,14 @@
 	 */
 	arch_start_context_switch(prev);
 
-	if (likely(!mm)) {
+	if (!mm) {
 		next->active_mm = oldmm;
 		atomic_inc(&oldmm->mm_count);
 		enter_lazy_tlb(oldmm, next);
 	} else
 		switch_mm(oldmm, mm, next);
 
-	if (likely(!prev->mm)) {
+	if (!prev->mm) {
 		prev->active_mm = NULL;
 		rq->prev_mm = oldmm;
 	}
@@ -3248,7 +3378,7 @@
 
 	if (task_current(rq, p)) {
 		update_rq_clock(rq);
-		ns = rq->clock - p->se.exec_start;
+		ns = rq->clock_task - p->se.exec_start;
 		if ((s64)ns < 0)
 			ns = 0;
 	}
@@ -3397,7 +3527,7 @@
 	tmp = cputime_to_cputime64(cputime);
 	if (hardirq_count() - hardirq_offset)
 		cpustat->irq = cputime64_add(cpustat->irq, tmp);
-	else if (softirq_count())
+	else if (in_serving_softirq())
 		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
 	else
 		cpustat->system = cputime64_add(cpustat->system, tmp);
@@ -3584,7 +3714,7 @@
 	curr->sched_class->task_tick(rq, curr, 0);
 	raw_spin_unlock(&rq->lock);
 
-	perf_event_task_tick(curr);
+	perf_event_task_tick();
 
 #ifdef CONFIG_SMP
 	rq->idle_at_tick = idle_cpu(cpu);
@@ -3723,17 +3853,13 @@
 			return p;
 	}
 
-	class = sched_class_highest;
-	for ( ; ; ) {
+	for_each_class(class) {
 		p = class->pick_next_task(rq);
 		if (p)
 			return p;
-		/*
-		 * Will never be NULL as the idle class always
-		 * returns a non-NULL p:
-		 */
-		class = class->next;
 	}
+
+	BUG(); /* the idle class will always have a runnable task */
 }
 
 /*
@@ -4358,6 +4484,7 @@
 
 	rq = task_rq_lock(p, &flags);
 
+	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
 	on_rq = p->se.on_rq;
@@ -4645,7 +4772,7 @@
 	}
 
 	if (user) {
-		retval = security_task_setscheduler(p, policy, param);
+		retval = security_task_setscheduler(p);
 		if (retval)
 			return retval;
 	}
@@ -4661,6 +4788,15 @@
 	 */
 	rq = __task_rq_lock(p);
 
+	/*
+	 * Changing the policy of the stop threads its a very bad idea
+	 */
+	if (p == rq->stop) {
+		__task_rq_unlock(rq);
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		return -EINVAL;
+	}
+
 #ifdef CONFIG_RT_GROUP_SCHED
 	if (user) {
 		/*
@@ -4887,13 +5023,13 @@
 	if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
 		goto out_unlock;
 
-	retval = security_task_setscheduler(p, 0, NULL);
+	retval = security_task_setscheduler(p);
 	if (retval)
 		goto out_unlock;
 
 	cpuset_cpus_allowed(p, cpus_allowed);
 	cpumask_and(new_mask, in_mask, cpus_allowed);
- again:
+again:
 	retval = set_cpus_allowed_ptr(p, new_mask);
 
 	if (!retval) {
@@ -5337,7 +5473,19 @@
 	idle->se.exec_start = sched_clock();
 
 	cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
+	/*
+	 * We're having a chicken and egg problem, even though we are
+	 * holding rq->lock, the cpu isn't yet set to this cpu so the
+	 * lockdep check in task_group() will fail.
+	 *
+	 * Similar case to sched_fork(). / Alternatively we could
+	 * use task_rq_lock() here and obtain the other rq->lock.
+	 *
+	 * Silence PROVE_RCU
+	 */
+	rcu_read_lock();
 	__set_task_cpu(idle, cpu);
+	rcu_read_unlock();
 
 	rq->curr = rq->idle = idle;
 #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
@@ -6514,6 +6662,7 @@
 	cpumask_var_t		nodemask;
 	cpumask_var_t		this_sibling_map;
 	cpumask_var_t		this_core_map;
+	cpumask_var_t		this_book_map;
 	cpumask_var_t		send_covered;
 	cpumask_var_t		tmpmask;
 	struct sched_group	**sched_group_nodes;
@@ -6525,6 +6674,7 @@
 	sa_rootdomain,
 	sa_tmpmask,
 	sa_send_covered,
+	sa_this_book_map,
 	sa_this_core_map,
 	sa_this_sibling_map,
 	sa_nodemask,
@@ -6560,31 +6710,48 @@
 #ifdef CONFIG_SCHED_MC
 static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
-#endif /* CONFIG_SCHED_MC */
 
-#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
 static int
 cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
-
+#ifdef CONFIG_SCHED_SMT
 	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
+#else
+	group = cpu;
+#endif
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
 	return group;
 }
-#elif defined(CONFIG_SCHED_MC)
+#endif /* CONFIG_SCHED_MC */
+
+/*
+ * book sched-domains:
+ */
+#ifdef CONFIG_SCHED_BOOK
+static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
+
 static int
-cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *unused)
+cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *mask)
 {
-	if (sg)
-		*sg = &per_cpu(sched_group_core, cpu).sg;
-	return cpu;
-}
+	int group = cpu;
+#ifdef CONFIG_SCHED_MC
+	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_SMT)
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
+	group = cpumask_first(mask);
 #endif
+	if (sg)
+		*sg = &per_cpu(sched_group_book, group).sg;
+	return group;
+}
+#endif /* CONFIG_SCHED_BOOK */
 
 static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
@@ -6594,7 +6761,10 @@
 		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
-#ifdef CONFIG_SCHED_MC
+#ifdef CONFIG_SCHED_BOOK
+	cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
+	group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_MC)
 	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
@@ -6855,6 +7025,9 @@
 #ifdef CONFIG_SCHED_MC
  SD_INIT_FUNC(MC)
 #endif
+#ifdef CONFIG_SCHED_BOOK
+ SD_INIT_FUNC(BOOK)
+#endif
 
 static int default_relax_domain_level = -1;
 
@@ -6904,6 +7077,8 @@
 		free_cpumask_var(d->tmpmask); /* fall through */
 	case sa_send_covered:
 		free_cpumask_var(d->send_covered); /* fall through */
+	case sa_this_book_map:
+		free_cpumask_var(d->this_book_map); /* fall through */
 	case sa_this_core_map:
 		free_cpumask_var(d->this_core_map); /* fall through */
 	case sa_this_sibling_map:
@@ -6950,8 +7125,10 @@
 		return sa_nodemask;
 	if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
 		return sa_this_sibling_map;
-	if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+	if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
 		return sa_this_core_map;
+	if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+		return sa_this_book_map;
 	if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
 		return sa_send_covered;
 	d->rd = alloc_rootdomain();
@@ -7009,6 +7186,23 @@
 	return sd;
 }
 
+static struct sched_domain *__build_book_sched_domain(struct s_data *d,
+	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+	struct sched_domain *parent, int i)
+{
+	struct sched_domain *sd = parent;
+#ifdef CONFIG_SCHED_BOOK
+	sd = &per_cpu(book_domains, i).sd;
+	SD_INIT(sd, BOOK);
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
+	sd->parent = parent;
+	parent->child = sd;
+	cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
+#endif
+	return sd;
+}
+
 static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
 	const struct cpumask *cpu_map, struct sched_domain_attr *attr,
 	struct sched_domain *parent, int i)
@@ -7066,6 +7260,15 @@
 						d->send_covered, d->tmpmask);
 		break;
 #endif
+#ifdef CONFIG_SCHED_BOOK
+	case SD_LV_BOOK: /* set up book groups */
+		cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
+		if (cpu == cpumask_first(d->this_book_map))
+			init_sched_build_groups(d->this_book_map, cpu_map,
+						&cpu_to_book_group,
+						d->send_covered, d->tmpmask);
+		break;
+#endif
 	case SD_LV_CPU: /* set up physical groups */
 		cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
 		if (!cpumask_empty(d->nodemask))
@@ -7113,12 +7316,14 @@
 
 		sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
 		sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+		sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
 		sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
 		sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
 	}
 
 	for_each_cpu(i, cpu_map) {
 		build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+		build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
 		build_sched_groups(&d, SD_LV_MC, cpu_map, i);
 	}
 
@@ -7149,6 +7354,12 @@
 		init_sched_groups_power(i, sd);
 	}
 #endif
+#ifdef CONFIG_SCHED_BOOK
+	for_each_cpu(i, cpu_map) {
+		sd = &per_cpu(book_domains, i).sd;
+		init_sched_groups_power(i, sd);
+	}
+#endif
 
 	for_each_cpu(i, cpu_map) {
 		sd = &per_cpu(phys_domains, i).sd;
@@ -7174,6 +7385,8 @@
 		sd = &per_cpu(cpu_domains, i).sd;
 #elif defined(CONFIG_SCHED_MC)
 		sd = &per_cpu(core_domains, i).sd;
+#elif defined(CONFIG_SCHED_BOOK)
+		sd = &per_cpu(book_domains, i).sd;
 #else
 		sd = &per_cpu(phys_domains, i).sd;
 #endif
@@ -8078,9 +8291,9 @@
 
 	return 1;
 
- err_free_rq:
+err_free_rq:
 	kfree(cfs_rq);
- err:
+err:
 	return 0;
 }
 
@@ -8168,9 +8381,9 @@
 
 	return 1;
 
- err_free_rq:
+err_free_rq:
 	kfree(rt_rq);
- err:
+err:
 	return 0;
 }
 
@@ -8528,7 +8741,7 @@
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
 	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
- unlock:
+unlock:
 	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index db3f674..933f3d1 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -25,7 +25,7 @@
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
- * (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
  * 'timeslice length' - timeslices in CFS are of variable length
@@ -52,7 +52,7 @@
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
 unsigned int sysctl_sched_min_granularity = 750000ULL;
 unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
@@ -519,7 +519,7 @@
 static void update_curr(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
-	u64 now = rq_of(cfs_rq)->clock;
+	u64 now = rq_of(cfs_rq)->clock_task;
 	unsigned long delta_exec;
 
 	if (unlikely(!curr))
@@ -602,7 +602,7 @@
 	/*
 	 * We are starting a new run period:
 	 */
-	se->exec_start = rq_of(cfs_rq)->clock;
+	se->exec_start = rq_of(cfs_rq)->clock_task;
 }
 
 /**************************************************
@@ -1764,6 +1764,10 @@
 	set_task_cpu(p, this_cpu);
 	activate_task(this_rq, p, 0);
 	check_preempt_curr(this_rq, p, 0);
+
+	/* re-arm NEWIDLE balancing when moving tasks */
+	src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
+	this_rq->idle_stamp = 0;
 }
 
 /*
@@ -1798,7 +1802,7 @@
 	 * 2) too many balance attempts have failed.
 	 */
 
-	tsk_cache_hot = task_hot(p, rq->clock, sd);
+	tsk_cache_hot = task_hot(p, rq->clock_task, sd);
 	if (!tsk_cache_hot ||
 		sd->nr_balance_failed > sd->cache_nice_tries) {
 #ifdef CONFIG_SCHEDSTATS
@@ -2030,12 +2034,14 @@
 	unsigned long this_load;
 	unsigned long this_load_per_task;
 	unsigned long this_nr_running;
+	unsigned long this_has_capacity;
 
 	/* Statistics of the busiest group */
 	unsigned long max_load;
 	unsigned long busiest_load_per_task;
 	unsigned long busiest_nr_running;
 	unsigned long busiest_group_capacity;
+	unsigned long busiest_has_capacity;
 
 	int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2058,6 +2064,7 @@
 	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
 	unsigned long group_capacity;
 	int group_imb; /* Is there an imbalance in the group ? */
+	int group_has_capacity; /* Is there extra capacity in the group? */
 };
 
 /**
@@ -2268,7 +2275,13 @@
 	u64 total, available;
 
 	total = sched_avg_period() + (rq->clock - rq->age_stamp);
-	available = total - rq->rt_avg;
+
+	if (unlikely(total < rq->rt_avg)) {
+		/* Ensures that power won't end up being negative */
+		available = 0;
+	} else {
+		available = total - rq->rt_avg;
+	}
 
 	if (unlikely((s64)total < SCHED_LOAD_SCALE))
 		total = SCHED_LOAD_SCALE;
@@ -2378,7 +2391,7 @@
 			int local_group, const struct cpumask *cpus,
 			int *balance, struct sg_lb_stats *sgs)
 {
-	unsigned long load, max_cpu_load, min_cpu_load;
+	unsigned long load, max_cpu_load, min_cpu_load, max_nr_running;
 	int i;
 	unsigned int balance_cpu = -1, first_idle_cpu = 0;
 	unsigned long avg_load_per_task = 0;
@@ -2389,6 +2402,7 @@
 	/* Tally up the load of all CPUs in the group */
 	max_cpu_load = 0;
 	min_cpu_load = ~0UL;
+	max_nr_running = 0;
 
 	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
 		struct rq *rq = cpu_rq(i);
@@ -2406,8 +2420,10 @@
 			load = target_load(i, load_idx);
 		} else {
 			load = source_load(i, load_idx);
-			if (load > max_cpu_load)
+			if (load > max_cpu_load) {
 				max_cpu_load = load;
+				max_nr_running = rq->nr_running;
+			}
 			if (min_cpu_load > load)
 				min_cpu_load = load;
 		}
@@ -2447,13 +2463,15 @@
 	if (sgs->sum_nr_running)
 		avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
 		sgs->group_imb = 1;
 
-	sgs->group_capacity =
-		DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+	sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
 	if (!sgs->group_capacity)
 		sgs->group_capacity = fix_small_capacity(sd, group);
+
+	if (sgs->group_capacity > sgs->sum_nr_running)
+		sgs->group_has_capacity = 1;
 }
 
 /**
@@ -2542,9 +2560,14 @@
 		/*
 		 * In case the child domain prefers tasks go to siblings
 		 * first, lower the sg capacity to one so that we'll try
-		 * and move all the excess tasks away.
+		 * and move all the excess tasks away. We lower the capacity
+		 * of a group only if the local group has the capacity to fit
+		 * these excess tasks, i.e. nr_running < group_capacity. The
+		 * extra check prevents the case where you always pull from the
+		 * heaviest group when it is already under-utilized (possible
+		 * with a large weight task outweighs the tasks on the system).
 		 */
-		if (prefer_sibling)
+		if (prefer_sibling && !local_group && sds->this_has_capacity)
 			sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
 		if (local_group) {
@@ -2552,12 +2575,14 @@
 			sds->this = sg;
 			sds->this_nr_running = sgs.sum_nr_running;
 			sds->this_load_per_task = sgs.sum_weighted_load;
+			sds->this_has_capacity = sgs.group_has_capacity;
 		} else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
 			sds->max_load = sgs.avg_load;
 			sds->busiest = sg;
 			sds->busiest_nr_running = sgs.sum_nr_running;
 			sds->busiest_group_capacity = sgs.group_capacity;
 			sds->busiest_load_per_task = sgs.sum_weighted_load;
+			sds->busiest_has_capacity = sgs.group_has_capacity;
 			sds->group_imb = sgs.group_imb;
 		}
 
@@ -2754,6 +2779,7 @@
 		return fix_small_imbalance(sds, this_cpu, imbalance);
 
 }
+
 /******* find_busiest_group() helpers end here *********************/
 
 /**
@@ -2805,6 +2831,11 @@
 	 * 4) This group is more busy than the avg busieness at this
 	 *    sched_domain.
 	 * 5) The imbalance is within the specified limit.
+	 *
+	 * Note: when doing newidle balance, if the local group has excess
+	 * capacity (i.e. nr_running < group_capacity) and the busiest group
+	 * does not have any capacity, we force a load balance to pull tasks
+	 * to the local group. In this case, we skip past checks 3, 4 and 5.
 	 */
 	if (!(*balance))
 		goto ret;
@@ -2816,6 +2847,11 @@
 	if (!sds.busiest || sds.busiest_nr_running == 0)
 		goto out_balanced;
 
+	/*  SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+	if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
+			!sds.busiest_has_capacity)
+		goto force_balance;
+
 	if (sds.this_load >= sds.max_load)
 		goto out_balanced;
 
@@ -2827,6 +2863,7 @@
 	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
 		goto out_balanced;
 
+force_balance:
 	/* Looks like there is an imbalance. Compute it */
 	calculate_imbalance(&sds, this_cpu, imbalance);
 	return sds.busiest;
@@ -3031,7 +3068,14 @@
 
 	if (!ld_moved) {
 		schedstat_inc(sd, lb_failed[idle]);
-		sd->nr_balance_failed++;
+		/*
+		 * Increment the failure counter only on periodic balance.
+		 * We do not want newidle balance, which can be very
+		 * frequent, pollute the failure counter causing
+		 * excessive cache_hot migrations and active balances.
+		 */
+		if (idle != CPU_NEWLY_IDLE)
+			sd->nr_balance_failed++;
 
 		if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
 					this_cpu)) {
@@ -3153,10 +3197,8 @@
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
 			next_balance = sd->last_balance + interval;
-		if (pulled_task) {
-			this_rq->idle_stamp = 0;
+		if (pulled_task)
 			break;
-		}
 	}
 
 	raw_spin_lock(&this_rq->lock);
@@ -3751,8 +3793,11 @@
 
 	update_rq_clock(rq);
 
-	if (unlikely(task_cpu(p) != this_cpu))
+	if (unlikely(task_cpu(p) != this_cpu)) {
+		rcu_read_lock();
 		__set_task_cpu(p, this_cpu);
+		rcu_read_unlock();
+	}
 
 	update_curr(cfs_rq);
 
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 83c66e8..185f920 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -61,3 +61,8 @@
  * release the lock. Decreases scheduling overhead.
  */
 SCHED_FEAT(OWNER_SPIN, 1)
+
+/*
+ * Decrement CPU power based on irq activity
+ */
+SCHED_FEAT(NONIRQ_POWER, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index d10c80e..bea7d79 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -609,7 +609,7 @@
 	if (!task_has_rt_policy(curr))
 		return;
 
-	delta_exec = rq->clock - curr->se.exec_start;
+	delta_exec = rq->clock_task - curr->se.exec_start;
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
 
@@ -618,7 +618,7 @@
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
 
-	curr->se.exec_start = rq->clock;
+	curr->se.exec_start = rq->clock_task;
 	cpuacct_charge(curr, delta_exec);
 
 	sched_rt_avg_update(rq, delta_exec);
@@ -960,18 +960,19 @@
 	 * runqueue. Otherwise simply start this RT task
 	 * on its current runqueue.
 	 *
-	 * We want to avoid overloading runqueues. Even if
-	 * the RT task is of higher priority than the current RT task.
-	 * RT tasks behave differently than other tasks. If
-	 * one gets preempted, we try to push it off to another queue.
-	 * So trying to keep a preempting RT task on the same
-	 * cache hot CPU will force the running RT task to
-	 * a cold CPU. So we waste all the cache for the lower
-	 * RT task in hopes of saving some of a RT task
-	 * that is just being woken and probably will have
-	 * cold cache anyway.
+	 * We want to avoid overloading runqueues. If the woken
+	 * task is a higher priority, then it will stay on this CPU
+	 * and the lower prio task should be moved to another CPU.
+	 * Even though this will probably make the lower prio task
+	 * lose its cache, we do not want to bounce a higher task
+	 * around just because it gave up its CPU, perhaps for a
+	 * lock?
+	 *
+	 * For equal prio tasks, we just let the scheduler sort it out.
 	 */
 	if (unlikely(rt_task(rq->curr)) &&
+	    (rq->curr->rt.nr_cpus_allowed < 2 ||
+	     rq->curr->prio < p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
 		int cpu = find_lowest_rq(p);
 
@@ -1074,7 +1075,7 @@
 	} while (rt_rq);
 
 	p = rt_task_of(rt_se);
-	p->se.exec_start = rq->clock;
+	p->se.exec_start = rq->clock_task;
 
 	return p;
 }
@@ -1139,7 +1140,7 @@
 	for_each_leaf_rt_rq(rt_rq, rq) {
 		array = &rt_rq->active;
 		idx = sched_find_first_bit(array->bitmap);
- next_idx:
+next_idx:
 		if (idx >= MAX_RT_PRIO)
 			continue;
 		if (next && next->prio < idx)
@@ -1315,7 +1316,7 @@
 	if (!next_task)
 		return 0;
 
- retry:
+retry:
 	if (unlikely(next_task == rq->curr)) {
 		WARN_ON(1);
 		return 0;
@@ -1463,7 +1464,7 @@
 			 * but possible)
 			 */
 		}
- skip:
+skip:
 		double_unlock_balance(this_rq, src_rq);
 	}
 
@@ -1491,7 +1492,10 @@
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
 	    has_pushable_tasks(rq) &&
-	    p->rt.nr_cpus_allowed > 1)
+	    p->rt.nr_cpus_allowed > 1 &&
+	    rt_task(rq->curr) &&
+	    (rq->curr->rt.nr_cpus_allowed < 2 ||
+	     rq->curr->prio < p->prio))
 		push_rt_tasks(rq);
 }
 
@@ -1709,7 +1713,7 @@
 {
 	struct task_struct *p = rq->curr;
 
-	p->se.exec_start = rq->clock;
+	p->se.exec_start = rq->clock_task;
 
 	/* The running task is never eligible for pushing */
 	dequeue_pushable_task(rq, p);
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
new file mode 100644
index 0000000..45bddc0
--- /dev/null
+++ b/kernel/sched_stoptask.c
@@ -0,0 +1,108 @@
+/*
+ * stop-task scheduling class.
+ *
+ * The stop task is the highest priority task in the system, it preempts
+ * everything and will be preempted by nothing.
+ *
+ * See kernel/stop_machine.c
+ */
+
+#ifdef CONFIG_SMP
+static int
+select_task_rq_stop(struct rq *rq, struct task_struct *p,
+		    int sd_flag, int flags)
+{
+	return task_cpu(p); /* stop tasks as never migrate */
+}
+#endif /* CONFIG_SMP */
+
+static void
+check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+	resched_task(rq->curr); /* we preempt everything */
+}
+
+static struct task_struct *pick_next_task_stop(struct rq *rq)
+{
+	struct task_struct *stop = rq->stop;
+
+	if (stop && stop->state == TASK_RUNNING)
+		return stop;
+
+	return NULL;
+}
+
+static void
+enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+}
+
+static void
+dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+}
+
+static void yield_task_stop(struct rq *rq)
+{
+	BUG(); /* the stop task should never yield, its pointless. */
+}
+
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+{
+}
+
+static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
+{
+}
+
+static void set_curr_task_stop(struct rq *rq)
+{
+}
+
+static void switched_to_stop(struct rq *rq, struct task_struct *p,
+			     int running)
+{
+	BUG(); /* its impossible to change to this class */
+}
+
+static void prio_changed_stop(struct rq *rq, struct task_struct *p,
+			      int oldprio, int running)
+{
+	BUG(); /* how!?, what priority? */
+}
+
+static unsigned int
+get_rr_interval_stop(struct rq *rq, struct task_struct *task)
+{
+	return 0;
+}
+
+/*
+ * Simple, special scheduling class for the per-CPU stop tasks:
+ */
+static const struct sched_class stop_sched_class = {
+	.next			= &rt_sched_class,
+
+	.enqueue_task		= enqueue_task_stop,
+	.dequeue_task		= dequeue_task_stop,
+	.yield_task		= yield_task_stop,
+
+	.check_preempt_curr	= check_preempt_curr_stop,
+
+	.pick_next_task		= pick_next_task_stop,
+	.put_prev_task		= put_prev_task_stop,
+
+#ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_stop,
+#endif
+
+	.set_curr_task          = set_curr_task_stop,
+	.task_tick		= task_tick_stop,
+
+	.get_rr_interval	= get_rr_interval_stop,
+
+	.prio_changed		= prio_changed_stop,
+	.switched_to		= switched_to_stop,
+
+	/* no .task_new for stop tasks */
+};
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 07b4f1b..fc97888 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -77,11 +77,21 @@
 }
 
 /*
+ * preempt_count and SOFTIRQ_OFFSET usage:
+ * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
+ *   softirq processing.
+ * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ *   on local_bh_disable or local_bh_enable.
+ * This lets us distinguish between whether we are currently processing
+ * softirq and whether we just have bh disabled.
+ */
+
+/*
  * This one is for softirq.c-internal use,
  * where hardirqs are disabled legitimately:
  */
 #ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip)
+static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 {
 	unsigned long flags;
 
@@ -95,32 +105,43 @@
 	 * We must manually increment preempt_count here and manually
 	 * call the trace_preempt_off later.
 	 */
-	preempt_count() += SOFTIRQ_OFFSET;
+	preempt_count() += cnt;
 	/*
 	 * Were softirqs turned off above:
 	 */
-	if (softirq_count() == SOFTIRQ_OFFSET)
+	if (softirq_count() == cnt)
 		trace_softirqs_off(ip);
 	raw_local_irq_restore(flags);
 
-	if (preempt_count() == SOFTIRQ_OFFSET)
+	if (preempt_count() == cnt)
 		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
 #else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip)
+static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
 {
-	add_preempt_count(SOFTIRQ_OFFSET);
+	add_preempt_count(cnt);
 	barrier();
 }
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
 void local_bh_disable(void)
 {
-	__local_bh_disable((unsigned long)__builtin_return_address(0));
+	__local_bh_disable((unsigned long)__builtin_return_address(0),
+				SOFTIRQ_DISABLE_OFFSET);
 }
 
 EXPORT_SYMBOL(local_bh_disable);
 
+static void __local_bh_enable(unsigned int cnt)
+{
+	WARN_ON_ONCE(in_irq());
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (softirq_count() == cnt)
+		trace_softirqs_on((unsigned long)__builtin_return_address(0));
+	sub_preempt_count(cnt);
+}
+
 /*
  * Special-case - softirqs can safely be enabled in
  * cond_resched_softirq(), or by __do_softirq(),
@@ -128,12 +149,7 @@
  */
 void _local_bh_enable(void)
 {
-	WARN_ON_ONCE(in_irq());
-	WARN_ON_ONCE(!irqs_disabled());
-
-	if (softirq_count() == SOFTIRQ_OFFSET)
-		trace_softirqs_on((unsigned long)__builtin_return_address(0));
-	sub_preempt_count(SOFTIRQ_OFFSET);
+	__local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
 }
 
 EXPORT_SYMBOL(_local_bh_enable);
@@ -147,13 +163,13 @@
 	/*
 	 * Are softirqs going to be turned on now:
 	 */
-	if (softirq_count() == SOFTIRQ_OFFSET)
+	if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
 		trace_softirqs_on(ip);
 	/*
 	 * Keep preemption disabled until we are done with
 	 * softirq processing:
  	 */
- 	sub_preempt_count(SOFTIRQ_OFFSET - 1);
+	sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);
 
 	if (unlikely(!in_interrupt() && local_softirq_pending()))
 		do_softirq();
@@ -198,7 +214,8 @@
 	pending = local_softirq_pending();
 	account_system_vtime(current);
 
-	__local_bh_disable((unsigned long)__builtin_return_address(0));
+	__local_bh_disable((unsigned long)__builtin_return_address(0),
+				SOFTIRQ_OFFSET);
 	lockdep_softirq_enter();
 
 	cpu = smp_processor_id();
@@ -245,7 +262,7 @@
 	lockdep_softirq_exit();
 
 	account_system_vtime(current);
-	_local_bh_enable();
+	__local_bh_enable(SOFTIRQ_OFFSET);
 }
 
 #ifndef __ARCH_HAS_DO_SOFTIRQ
@@ -279,10 +296,16 @@
 
 	rcu_irq_enter();
 	if (idle_cpu(cpu) && !in_interrupt()) {
-		__irq_enter();
+		/*
+		 * Prevent raise_softirq from needlessly waking up ksoftirqd
+		 * here, as softirq will be serviced on return from interrupt.
+		 */
+		local_bh_disable();
 		tick_check_idle(cpu);
-	} else
-		__irq_enter();
+		_local_bh_enable();
+	}
+
+	__irq_enter();
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
@@ -696,6 +719,7 @@
 {
 	set_current_state(TASK_INTERRUPTIBLE);
 
+	current->flags |= PF_KSOFTIRQD;
 	while (!kthread_should_stop()) {
 		preempt_disable();
 		if (!local_softirq_pending()) {
@@ -886,17 +910,14 @@
 	return 0;
 }
 
+#ifdef CONFIG_GENERIC_HARDIRQS
 int __init __weak arch_probe_nr_irqs(void)
 {
-	return 0;
+	return NR_IRQS_LEGACY;
 }
 
 int __init __weak arch_early_irq_init(void)
 {
 	return 0;
 }
-
-int __weak arch_init_chip_data(struct irq_desc *desc, int node)
-{
-	return 0;
-}
+#endif
diff --git a/kernel/srcu.c b/kernel/srcu.c
index 2980da3..c71e075 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -46,11 +46,9 @@
 int __init_srcu_struct(struct srcu_struct *sp, const char *name,
 		       struct lock_class_key *key)
 {
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
 	/* Don't re-initialize a lock while it is held. */
 	debug_check_no_locks_freed((void *)sp, sizeof(*sp));
 	lockdep_init_map(&sp->dep_map, name, key, 0);
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 	return init_srcu_struct_fields(sp);
 }
 EXPORT_SYMBOL_GPL(__init_srcu_struct);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 4372ccb..090c288 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -287,11 +287,12 @@
 	goto repeat;
 }
 
+extern void sched_set_stop_task(int cpu, struct task_struct *stop);
+
 /* manage stopper for a cpu, mostly lifted from sched migration thread mgmt */
 static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
 					   unsigned long action, void *hcpu)
 {
-	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
 	unsigned int cpu = (unsigned long)hcpu;
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 	struct task_struct *p;
@@ -304,13 +305,13 @@
 				   cpu);
 		if (IS_ERR(p))
 			return NOTIFY_BAD;
-		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
 		get_task_struct(p);
+		kthread_bind(p, cpu);
+		sched_set_stop_task(cpu, p);
 		stopper->thread = p;
 		break;
 
 	case CPU_ONLINE:
-		kthread_bind(stopper->thread, cpu);
 		/* strictly unnecessary, as first user will wake it */
 		wake_up_process(stopper->thread);
 		/* mark enabled */
@@ -325,6 +326,7 @@
 	{
 		struct cpu_stop_work *work;
 
+		sched_set_stop_task(cpu, NULL);
 		/* kill the stopper */
 		kthread_stop(stopper->thread);
 		/* drain remaining works */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index bad369e..c782fe9 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -50,6 +50,7 @@
 cond_syscall(sys_recvmsg);
 cond_syscall(sys_recvmmsg);
 cond_syscall(compat_sys_recvmsg);
+cond_syscall(compat_sys_recv);
 cond_syscall(compat_sys_recvfrom);
 cond_syscall(compat_sys_recvmmsg);
 cond_syscall(sys_socketcall);
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index 4f10451..f8b11a2 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -115,7 +115,9 @@
 	int ret;
 	struct kprobe *kps[2] = {&kp, &kp2};
 
-	kp.addr = 0; /* addr should be cleard for reusing kprobe. */
+	/* addr and flags should be cleard for reusing kprobe. */
+	kp.addr = NULL;
+	kp.flags = 0;
 	ret = register_kprobes(kps, 2);
 	if (ret < 0) {
 		printk(KERN_ERR "Kprobe smoke test failed: "
@@ -210,7 +212,9 @@
 	int ret;
 	struct jprobe *jps[2] = {&jp, &jp2};
 
-	jp.kp.addr = 0; /* addr should be cleard for reusing kprobe. */
+	/* addr and flags should be cleard for reusing kprobe. */
+	jp.kp.addr = NULL;
+	jp.kp.flags = 0;
 	ret = register_jprobes(jps, 2);
 	if (ret < 0) {
 		printk(KERN_ERR "Kprobe smoke test failed: "
@@ -323,7 +327,9 @@
 	int ret;
 	struct kretprobe *rps[2] = {&rp, &rp2};
 
-	rp.kp.addr = 0; /* addr should be cleard for reusing kprobe. */
+	/* addr and flags should be cleard for reusing kprobe. */
+	rp.kp.addr = NULL;
+	rp.kp.flags = 0;
 	ret = register_kretprobes(rps, 2);
 	if (ret < 0) {
 		printk(KERN_ERR "Kprobe smoke test failed: "
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index c631168..d232189 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -149,10 +149,18 @@
 	time_reftime = get_seconds();
 
 	offset64    = offset;
-	freq_adj    = (offset64 * secs) <<
-			(NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
+	freq_adj    = ntp_update_offset_fll(offset64, secs);
 
-	freq_adj    += ntp_update_offset_fll(offset64, secs);
+	/*
+	 * Clamp update interval to reduce PLL gain with low
+	 * sampling rate (e.g. intermittent network connection)
+	 * to avoid instability.
+	 */
+	if (unlikely(secs > 1 << (SHIFT_PLL + 1 + time_constant)))
+		secs = 1 << (SHIFT_PLL + 1 + time_constant);
+
+	freq_adj    += (offset64 * secs) <<
+			(NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
 
 	freq_adj    = min(freq_adj + time_freq, MAXFREQ_SCALED);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 97bf05b..68a9ae7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -37,7 +37,7 @@
 #include <linux/delay.h>
 #include <linux/tick.h>
 #include <linux/kallsyms.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 
@@ -1279,7 +1279,10 @@
 	run_local_timers();
 	rcu_check_callbacks(cpu, user_tick);
 	printk_tick();
-	perf_event_do_pending();
+#ifdef CONFIG_IRQ_WORK
+	if (in_irq())
+		irq_work_run();
+#endif
 	scheduler_tick();
 	run_posix_cpu_timers(p);
 }
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 538501c..e04b8bc 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -49,6 +49,11 @@
 	help
 	  See Documentation/trace/ftrace-design.txt
 
+config HAVE_C_RECORDMCOUNT
+	bool
+	help
+	  C version of recordmcount available?
+
 config TRACER_MAX_TRACE
 	bool
 
@@ -121,7 +126,7 @@
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	select FRAME_POINTER
+	select FRAME_POINTER if (!ARM_UNWIND)
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 959f8d6..bc251ed 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -23,7 +23,6 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/debugfs.h>
-#include <linux/smp_lock.h>
 #include <linux/time.h>
 #include <linux/uaccess.h>
 
@@ -326,6 +325,7 @@
 	.owner =	THIS_MODULE,
 	.open =		blk_dropped_open,
 	.read =		blk_dropped_read,
+	.llseek =	default_llseek,
 };
 
 static int blk_msg_open(struct inode *inode, struct file *filp)
@@ -365,6 +365,7 @@
 	.owner =	THIS_MODULE,
 	.open =		blk_msg_open,
 	.write =	blk_msg_write,
+	.llseek =	noop_llseek,
 };
 
 /*
@@ -639,7 +640,6 @@
 	if (!q)
 		return -ENXIO;
 
-	lock_kernel();
 	mutex_lock(&bdev->bd_mutex);
 
 	switch (cmd) {
@@ -667,7 +667,6 @@
 	}
 
 	mutex_unlock(&bdev->bd_mutex);
-	unlock_kernel();
 	return ret;
 }
 
@@ -1652,10 +1651,9 @@
 	struct block_device *bdev;
 	ssize_t ret = -ENXIO;
 
-	lock_kernel();
 	bdev = bdget(part_devt(p));
 	if (bdev == NULL)
-		goto out_unlock_kernel;
+		goto out;
 
 	q = blk_trace_get_queue(bdev);
 	if (q == NULL)
@@ -1683,8 +1681,7 @@
 	mutex_unlock(&bdev->bd_mutex);
 out_bdput:
 	bdput(bdev);
-out_unlock_kernel:
-	unlock_kernel();
+out:
 	return ret;
 }
 
@@ -1714,11 +1711,10 @@
 
 	ret = -ENXIO;
 
-	lock_kernel();
 	p = dev_to_part(dev);
 	bdev = bdget(part_devt(p));
 	if (bdev == NULL)
-		goto out_unlock_kernel;
+		goto out;
 
 	q = blk_trace_get_queue(bdev);
 	if (q == NULL)
@@ -1753,8 +1749,6 @@
 	mutex_unlock(&bdev->bd_mutex);
 out_bdput:
 	bdput(bdev);
-out_unlock_kernel:
-	unlock_kernel();
 out:
 	return ret ? ret : count;
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fa7ece6..f3dadae 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -800,6 +800,7 @@
 	.open		= tracing_open_generic,
 	.read		= ftrace_profile_read,
 	.write		= ftrace_profile_write,
+	.llseek		= default_llseek,
 };
 
 /* used to initialize the real stat files */
@@ -884,10 +885,8 @@
 	FTRACE_ENABLE_CALLS		= (1 << 0),
 	FTRACE_DISABLE_CALLS		= (1 << 1),
 	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
-	FTRACE_ENABLE_MCOUNT		= (1 << 3),
-	FTRACE_DISABLE_MCOUNT		= (1 << 4),
-	FTRACE_START_FUNC_RET		= (1 << 5),
-	FTRACE_STOP_FUNC_RET		= (1 << 6),
+	FTRACE_START_FUNC_RET		= (1 << 3),
+	FTRACE_STOP_FUNC_RET		= (1 << 4),
 };
 
 static int ftrace_filtered;
@@ -1226,8 +1225,6 @@
 
 static void ftrace_startup_sysctl(void)
 {
-	int command = FTRACE_ENABLE_MCOUNT;
-
 	if (unlikely(ftrace_disabled))
 		return;
 
@@ -1235,23 +1232,17 @@
 	saved_ftrace_func = NULL;
 	/* ftrace_start_up is true if we want ftrace running */
 	if (ftrace_start_up)
-		command |= FTRACE_ENABLE_CALLS;
-
-	ftrace_run_update_code(command);
+		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
 }
 
 static void ftrace_shutdown_sysctl(void)
 {
-	int command = FTRACE_DISABLE_MCOUNT;
-
 	if (unlikely(ftrace_disabled))
 		return;
 
 	/* ftrace_start_up is true if ftrace is running */
 	if (ftrace_start_up)
-		command |= FTRACE_DISABLE_CALLS;
-
-	ftrace_run_update_code(command);
+		ftrace_run_update_code(FTRACE_DISABLE_CALLS);
 }
 
 static cycle_t		ftrace_update_time;
@@ -1368,24 +1359,29 @@
 #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
 
 struct ftrace_iterator {
-	struct ftrace_page	*pg;
-	int			hidx;
-	int			idx;
-	unsigned		flags;
-	struct trace_parser	parser;
+	loff_t				pos;
+	loff_t				func_pos;
+	struct ftrace_page		*pg;
+	struct dyn_ftrace		*func;
+	struct ftrace_func_probe	*probe;
+	struct trace_parser		parser;
+	int				hidx;
+	int				idx;
+	unsigned			flags;
 };
 
 static void *
-t_hash_next(struct seq_file *m, void *v, loff_t *pos)
+t_hash_next(struct seq_file *m, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
-	struct hlist_node *hnd = v;
+	struct hlist_node *hnd = NULL;
 	struct hlist_head *hhd;
 
-	WARN_ON(!(iter->flags & FTRACE_ITER_HASH));
-
 	(*pos)++;
+	iter->pos = *pos;
 
+	if (iter->probe)
+		hnd = &iter->probe->node;
  retry:
 	if (iter->hidx >= FTRACE_FUNC_HASHSIZE)
 		return NULL;
@@ -1408,7 +1404,12 @@
 		}
 	}
 
-	return hnd;
+	if (WARN_ON_ONCE(!hnd))
+		return NULL;
+
+	iter->probe = hlist_entry(hnd, struct ftrace_func_probe, node);
+
+	return iter;
 }
 
 static void *t_hash_start(struct seq_file *m, loff_t *pos)
@@ -1417,26 +1418,32 @@
 	void *p = NULL;
 	loff_t l;
 
-	if (!(iter->flags & FTRACE_ITER_HASH))
-		*pos = 0;
-
-	iter->flags |= FTRACE_ITER_HASH;
+	if (iter->func_pos > *pos)
+		return NULL;
 
 	iter->hidx = 0;
-	for (l = 0; l <= *pos; ) {
-		p = t_hash_next(m, p, &l);
+	for (l = 0; l <= (*pos - iter->func_pos); ) {
+		p = t_hash_next(m, &l);
 		if (!p)
 			break;
 	}
-	return p;
+	if (!p)
+		return NULL;
+
+	/* Only set this if we have an item */
+	iter->flags |= FTRACE_ITER_HASH;
+
+	return iter;
 }
 
-static int t_hash_show(struct seq_file *m, void *v)
+static int
+t_hash_show(struct seq_file *m, struct ftrace_iterator *iter)
 {
 	struct ftrace_func_probe *rec;
-	struct hlist_node *hnd = v;
 
-	rec = hlist_entry(hnd, struct ftrace_func_probe, node);
+	rec = iter->probe;
+	if (WARN_ON_ONCE(!rec))
+		return -EIO;
 
 	if (rec->ops->print)
 		return rec->ops->print(m, rec->ip, rec->ops, rec->data);
@@ -1457,12 +1464,13 @@
 	struct dyn_ftrace *rec = NULL;
 
 	if (iter->flags & FTRACE_ITER_HASH)
-		return t_hash_next(m, v, pos);
+		return t_hash_next(m, pos);
 
 	(*pos)++;
+	iter->pos = *pos;
 
 	if (iter->flags & FTRACE_ITER_PRINTALL)
-		return NULL;
+		return t_hash_start(m, pos);
 
  retry:
 	if (iter->idx >= iter->pg->index) {
@@ -1491,7 +1499,20 @@
 		}
 	}
 
-	return rec;
+	if (!rec)
+		return t_hash_start(m, pos);
+
+	iter->func_pos = *pos;
+	iter->func = rec;
+
+	return iter;
+}
+
+static void reset_iter_read(struct ftrace_iterator *iter)
+{
+	iter->pos = 0;
+	iter->func_pos = 0;
+	iter->flags &= ~(FTRACE_ITER_PRINTALL & FTRACE_ITER_HASH);
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
@@ -1502,6 +1523,12 @@
 
 	mutex_lock(&ftrace_lock);
 	/*
+	 * If an lseek was done, then reset and start from beginning.
+	 */
+	if (*pos < iter->pos)
+		reset_iter_read(iter);
+
+	/*
 	 * For set_ftrace_filter reading, if we have the filter
 	 * off, we can short cut and just print out that all
 	 * functions are enabled.
@@ -1518,6 +1545,11 @@
 	if (iter->flags & FTRACE_ITER_HASH)
 		return t_hash_start(m, pos);
 
+	/*
+	 * Unfortunately, we need to restart at ftrace_pages_start
+	 * every time we let go of the ftrace_mutex. This is because
+	 * those pointers can change without the lock.
+	 */
 	iter->pg = ftrace_pages_start;
 	iter->idx = 0;
 	for (l = 0; l <= *pos; ) {
@@ -1526,10 +1558,14 @@
 			break;
 	}
 
-	if (!p && iter->flags & FTRACE_ITER_FILTER)
-		return t_hash_start(m, pos);
+	if (!p) {
+		if (iter->flags & FTRACE_ITER_FILTER)
+			return t_hash_start(m, pos);
 
-	return p;
+		return NULL;
+	}
+
+	return iter;
 }
 
 static void t_stop(struct seq_file *m, void *p)
@@ -1540,16 +1576,18 @@
 static int t_show(struct seq_file *m, void *v)
 {
 	struct ftrace_iterator *iter = m->private;
-	struct dyn_ftrace *rec = v;
+	struct dyn_ftrace *rec;
 
 	if (iter->flags & FTRACE_ITER_HASH)
-		return t_hash_show(m, v);
+		return t_hash_show(m, iter);
 
 	if (iter->flags & FTRACE_ITER_PRINTALL) {
 		seq_printf(m, "#### all functions enabled ####\n");
 		return 0;
 	}
 
+	rec = iter->func;
+
 	if (!rec)
 		return 0;
 
@@ -1601,8 +1639,8 @@
 
 	ret = ftrace_avail_open(inode, file);
 	if (!ret) {
-		m = (struct seq_file *)file->private_data;
-		iter = (struct ftrace_iterator *)m->private;
+		m = file->private_data;
+		iter = m->private;
 		iter->flags = FTRACE_ITER_FAILURES;
 	}
 
@@ -2418,7 +2456,7 @@
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = no_llseek,
+	.llseek = ftrace_regex_lseek,
 	.release = ftrace_filter_release,
 };
 
@@ -2632,6 +2670,7 @@
 	.read		= seq_read,
 	.write		= ftrace_graph_write,
 	.release	= ftrace_graph_release,
+	.llseek		= seq_lseek,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bca9637..c3dab05 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2606,6 +2606,19 @@
 }
 EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
 
+/*
+ * The total entries in the ring buffer is the running counter
+ * of entries entered into the ring buffer, minus the sum of
+ * the entries read from the ring buffer and the number of
+ * entries that were overwritten.
+ */
+static inline unsigned long
+rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	return local_read(&cpu_buffer->entries) -
+		(local_read(&cpu_buffer->overrun) + cpu_buffer->read);
+}
+
 /**
  * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
  * @buffer: The ring buffer
@@ -2614,16 +2627,13 @@
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned long ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = (local_read(&cpu_buffer->entries) - local_read(&cpu_buffer->overrun))
-		- cpu_buffer->read;
 
-	return ret;
+	return rb_num_of_entries(cpu_buffer);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
 
@@ -2684,8 +2694,7 @@
 	/* if you care about this being correct, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		entries += (local_read(&cpu_buffer->entries) -
-			    local_read(&cpu_buffer->overrun)) - cpu_buffer->read;
+		entries += rb_num_of_entries(cpu_buffer);
 	}
 
 	return entries;
@@ -3965,6 +3974,7 @@
 	.open		= tracing_open_generic,
 	.read		= rb_simple_read,
 	.write		= rb_simple_write,
+	.llseek		= default_llseek,
 };
 
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9ec59f5..001bcd2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2196,7 +2196,7 @@
 
 static int tracing_release(struct inode *inode, struct file *file)
 {
-	struct seq_file *m = (struct seq_file *)file->private_data;
+	struct seq_file *m = file->private_data;
 	struct trace_iterator *iter;
 	int cpu;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d39b3c5..9021f8c 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -343,6 +343,10 @@
 		    unsigned long ip,
 		    unsigned long parent_ip,
 		    unsigned long flags, int pc);
+void trace_graph_function(struct trace_array *tr,
+		    unsigned long ip,
+		    unsigned long parent_ip,
+		    unsigned long flags, int pc);
 void trace_default_header(struct seq_file *m);
 void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
 int trace_empty(struct trace_iterator *iter);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 31cc4cb..39c059c 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -9,7 +9,7 @@
 #include <linux/kprobes.h>
 #include "trace.h"
 
-static char *perf_trace_buf[4];
+static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];
 
 /*
  * Force it to be aligned to unsigned long to avoid misaligned accesses
@@ -24,7 +24,7 @@
 static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
-	struct hlist_head *list;
+	struct hlist_head __percpu *list;
 	int ret = -ENOMEM;
 	int cpu;
 
@@ -42,11 +42,11 @@
 	tp_event->perf_events = list;
 
 	if (!total_ref_count) {
-		char *buf;
+		char __percpu *buf;
 		int i;
 
-		for (i = 0; i < 4; i++) {
-			buf = (char *)alloc_percpu(perf_trace_t);
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+			buf = (char __percpu *)alloc_percpu(perf_trace_t);
 			if (!buf)
 				goto fail;
 
@@ -65,7 +65,7 @@
 	if (!total_ref_count) {
 		int i;
 
-		for (i = 0; i < 4; i++) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 			free_percpu(perf_trace_buf[i]);
 			perf_trace_buf[i] = NULL;
 		}
@@ -101,22 +101,26 @@
 	return ret;
 }
 
-int perf_trace_enable(struct perf_event *p_event)
+int perf_trace_add(struct perf_event *p_event, int flags)
 {
 	struct ftrace_event_call *tp_event = p_event->tp_event;
+	struct hlist_head __percpu *pcpu_list;
 	struct hlist_head *list;
 
-	list = tp_event->perf_events;
-	if (WARN_ON_ONCE(!list))
+	pcpu_list = tp_event->perf_events;
+	if (WARN_ON_ONCE(!pcpu_list))
 		return -EINVAL;
 
-	list = this_cpu_ptr(list);
+	if (!(flags & PERF_EF_START))
+		p_event->hw.state = PERF_HES_STOPPED;
+
+	list = this_cpu_ptr(pcpu_list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
 	return 0;
 }
 
-void perf_trace_disable(struct perf_event *p_event)
+void perf_trace_del(struct perf_event *p_event, int flags)
 {
 	hlist_del_rcu(&p_event->hlist_entry);
 }
@@ -142,7 +146,7 @@
 	tp_event->perf_events = NULL;
 
 	if (!--total_ref_count) {
-		for (i = 0; i < 4; i++) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
 			free_percpu(perf_trace_buf[i]);
 			perf_trace_buf[i] = NULL;
 		}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4c758f1..0725eea 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -600,21 +600,29 @@
 
 enum {
 	FORMAT_HEADER		= 1,
-	FORMAT_PRINTFMT		= 2,
+	FORMAT_FIELD_SEPERATOR	= 2,
+	FORMAT_PRINTFMT		= 3,
 };
 
 static void *f_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct ftrace_event_call *call = m->private;
 	struct ftrace_event_field *field;
-	struct list_head *head;
+	struct list_head *common_head = &ftrace_common_fields;
+	struct list_head *head = trace_get_fields(call);
 
 	(*pos)++;
 
 	switch ((unsigned long)v) {
 	case FORMAT_HEADER:
-		head = &ftrace_common_fields;
+		if (unlikely(list_empty(common_head)))
+			return NULL;
 
+		field = list_entry(common_head->prev,
+				   struct ftrace_event_field, link);
+		return field;
+
+	case FORMAT_FIELD_SEPERATOR:
 		if (unlikely(list_empty(head)))
 			return NULL;
 
@@ -626,31 +634,10 @@
 		return NULL;
 	}
 
-	head = trace_get_fields(call);
-
-	/*
-	 * To separate common fields from event fields, the
-	 * LSB is set on the first event field. Clear it in case.
-	 */
-	v = (void *)((unsigned long)v & ~1L);
-
 	field = v;
-	/*
-	 * If this is a common field, and at the end of the list, then
-	 * continue with main list.
-	 */
-	if (field->link.prev == &ftrace_common_fields) {
-		if (unlikely(list_empty(head)))
-			return NULL;
-		field = list_entry(head->prev, struct ftrace_event_field, link);
-		/* Set the LSB to notify f_show to print an extra newline */
-		field = (struct ftrace_event_field *)
-			((unsigned long)field | 1);
-		return field;
-	}
-
-	/* If we are done tell f_show to print the format */
-	if (field->link.prev == head)
+	if (field->link.prev == common_head)
+		return (void *)FORMAT_FIELD_SEPERATOR;
+	else if (field->link.prev == head)
 		return (void *)FORMAT_PRINTFMT;
 
 	field = list_entry(field->link.prev, struct ftrace_event_field, link);
@@ -688,22 +675,16 @@
 		seq_printf(m, "format:\n");
 		return 0;
 
+	case FORMAT_FIELD_SEPERATOR:
+		seq_putc(m, '\n');
+		return 0;
+
 	case FORMAT_PRINTFMT:
 		seq_printf(m, "\nprint fmt: %s\n",
 			   call->print_fmt);
 		return 0;
 	}
 
-	/*
-	 * To separate common fields from event fields, the
-	 * LSB is set on the first event field. Clear it and
-	 * print a newline if it is set.
-	 */
-	if ((unsigned long)v & 1) {
-		seq_putc(m, '\n');
-		v = (void *)((unsigned long)v & ~1L);
-	}
-
 	field = v;
 
 	/*
@@ -951,6 +932,7 @@
 	.open = tracing_open_generic,
 	.read = event_enable_read,
 	.write = event_enable_write,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_event_format_fops = {
@@ -963,29 +945,34 @@
 static const struct file_operations ftrace_event_id_fops = {
 	.open = tracing_open_generic,
 	.read = event_id_read,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_event_filter_fops = {
 	.open = tracing_open_generic,
 	.read = event_filter_read,
 	.write = event_filter_write,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_subsystem_filter_fops = {
 	.open = tracing_open_generic,
 	.read = subsystem_filter_read,
 	.write = subsystem_filter_write,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_system_enable_fops = {
 	.open = tracing_open_generic,
 	.read = system_enable_read,
 	.write = system_enable_write,
+	.llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_show_header_fops = {
 	.open = tracing_open_generic,
 	.read = show_header,
+	.llseek = default_llseek,
 };
 
 static struct dentry *event_trace_events_dir(void)
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 6f23369..76b0598 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -15,15 +15,19 @@
 #include "trace.h"
 #include "trace_output.h"
 
+/* When set, irq functions will be ignored */
+static int ftrace_graph_skip_irqs;
+
 struct fgraph_cpu_data {
 	pid_t		last_pid;
 	int		depth;
+	int		depth_irq;
 	int		ignore;
 	unsigned long	enter_funcs[FTRACE_RETFUNC_DEPTH];
 };
 
 struct fgraph_data {
-	struct fgraph_cpu_data		*cpu_data;
+	struct fgraph_cpu_data __percpu *cpu_data;
 
 	/* Place to preserve last processed entry. */
 	struct ftrace_graph_ent_entry	ent;
@@ -41,6 +45,7 @@
 #define TRACE_GRAPH_PRINT_PROC		0x8
 #define TRACE_GRAPH_PRINT_DURATION	0x10
 #define TRACE_GRAPH_PRINT_ABS_TIME	0x20
+#define TRACE_GRAPH_PRINT_IRQS		0x40
 
 static struct tracer_opt trace_opts[] = {
 	/* Display overruns? (for self-debug purpose) */
@@ -55,13 +60,15 @@
 	{ TRACER_OPT(funcgraph-duration, TRACE_GRAPH_PRINT_DURATION) },
 	/* Display absolute time of an entry */
 	{ TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) },
+	/* Display interrupts */
+	{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
 	{ } /* Empty entry */
 };
 
 static struct tracer_flags tracer_flags = {
 	/* Don't display overruns and proc by default */
 	.val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD |
-	       TRACE_GRAPH_PRINT_DURATION,
+	       TRACE_GRAPH_PRINT_DURATION | TRACE_GRAPH_PRINT_IRQS,
 	.opts = trace_opts
 };
 
@@ -204,6 +211,14 @@
 	return 1;
 }
 
+static inline int ftrace_graph_ignore_irqs(void)
+{
+	if (!ftrace_graph_skip_irqs)
+		return 0;
+
+	return in_irq();
+}
+
 int trace_graph_entry(struct ftrace_graph_ent *trace)
 {
 	struct trace_array *tr = graph_array;
@@ -218,7 +233,8 @@
 		return 0;
 
 	/* trace it when it is-nested-in or is a function enabled. */
-	if (!(trace->depth || ftrace_graph_addr(trace->func)))
+	if (!(trace->depth || ftrace_graph_addr(trace->func)) ||
+	      ftrace_graph_ignore_irqs())
 		return 0;
 
 	local_irq_save(flags);
@@ -246,6 +262,34 @@
 		return trace_graph_entry(trace);
 }
 
+static void
+__trace_graph_function(struct trace_array *tr,
+		unsigned long ip, unsigned long flags, int pc)
+{
+	u64 time = trace_clock_local();
+	struct ftrace_graph_ent ent = {
+		.func  = ip,
+		.depth = 0,
+	};
+	struct ftrace_graph_ret ret = {
+		.func     = ip,
+		.depth    = 0,
+		.calltime = time,
+		.rettime  = time,
+	};
+
+	__trace_graph_entry(tr, &ent, flags, pc);
+	__trace_graph_return(tr, &ret, flags, pc);
+}
+
+void
+trace_graph_function(struct trace_array *tr,
+		unsigned long ip, unsigned long parent_ip,
+		unsigned long flags, int pc)
+{
+	__trace_graph_function(tr, ip, flags, pc);
+}
+
 void __trace_graph_return(struct trace_array *tr,
 				struct ftrace_graph_ret *trace,
 				unsigned long flags,
@@ -649,8 +693,9 @@
 
 	/* Print nsecs (we don't want to exceed 7 numbers) */
 	if (len < 7) {
-		snprintf(nsecs_str, min(sizeof(nsecs_str), 8UL - len), "%03lu",
-			 nsecs_rem);
+		size_t slen = min_t(size_t, sizeof(nsecs_str), 8UL - len);
+
+		snprintf(nsecs_str, slen, "%03lu", nsecs_rem);
 		ret = trace_seq_printf(s, ".%s", nsecs_str);
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
@@ -855,6 +900,108 @@
 	return 0;
 }
 
+/*
+ * Entry check for irq code
+ *
+ * returns 1 if
+ *  - we are inside irq code
+ *  - we just extered irq code
+ *
+ * retunns 0 if
+ *  - funcgraph-interrupts option is set
+ *  - we are not inside irq code
+ */
+static int
+check_irq_entry(struct trace_iterator *iter, u32 flags,
+		unsigned long addr, int depth)
+{
+	int cpu = iter->cpu;
+	int *depth_irq;
+	struct fgraph_data *data = iter->private;
+
+	/*
+	 * If we are either displaying irqs, or we got called as
+	 * a graph event and private data does not exist,
+	 * then we bypass the irq check.
+	 */
+	if ((flags & TRACE_GRAPH_PRINT_IRQS) ||
+	    (!data))
+		return 0;
+
+	depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
+	/*
+	 * We are inside the irq code
+	 */
+	if (*depth_irq >= 0)
+		return 1;
+
+	if ((addr < (unsigned long)__irqentry_text_start) ||
+	    (addr >= (unsigned long)__irqentry_text_end))
+		return 0;
+
+	/*
+	 * We are entering irq code.
+	 */
+	*depth_irq = depth;
+	return 1;
+}
+
+/*
+ * Return check for irq code
+ *
+ * returns 1 if
+ *  - we are inside irq code
+ *  - we just left irq code
+ *
+ * returns 0 if
+ *  - funcgraph-interrupts option is set
+ *  - we are not inside irq code
+ */
+static int
+check_irq_return(struct trace_iterator *iter, u32 flags, int depth)
+{
+	int cpu = iter->cpu;
+	int *depth_irq;
+	struct fgraph_data *data = iter->private;
+
+	/*
+	 * If we are either displaying irqs, or we got called as
+	 * a graph event and private data does not exist,
+	 * then we bypass the irq check.
+	 */
+	if ((flags & TRACE_GRAPH_PRINT_IRQS) ||
+	    (!data))
+		return 0;
+
+	depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
+	/*
+	 * We are not inside the irq code.
+	 */
+	if (*depth_irq == -1)
+		return 0;
+
+	/*
+	 * We are inside the irq code, and this is returning entry.
+	 * Let's not trace it and clear the entry depth, since
+	 * we are out of irq code.
+	 *
+	 * This condition ensures that we 'leave the irq code' once
+	 * we are out of the entry depth. Thus protecting us from
+	 * the RETURN entry loss.
+	 */
+	if (*depth_irq >= depth) {
+		*depth_irq = -1;
+		return 1;
+	}
+
+	/*
+	 * We are inside the irq code, and this is not the entry.
+	 */
+	return 1;
+}
+
 static enum print_line_t
 print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 			struct trace_iterator *iter, u32 flags)
@@ -865,6 +1012,9 @@
 	static enum print_line_t ret;
 	int cpu = iter->cpu;
 
+	if (check_irq_entry(iter, flags, call->func, call->depth))
+		return TRACE_TYPE_HANDLED;
+
 	if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func, flags))
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -902,6 +1052,9 @@
 	int ret;
 	int i;
 
+	if (check_irq_return(iter, flags, trace->depth))
+		return TRACE_TYPE_HANDLED;
+
 	if (data) {
 		struct fgraph_cpu_data *cpu_data;
 		int cpu = iter->cpu;
@@ -1054,7 +1207,7 @@
 
 
 enum print_line_t
-print_graph_function_flags(struct trace_iterator *iter, u32 flags)
+__print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
 	struct ftrace_graph_ent_entry *field;
 	struct fgraph_data *data = iter->private;
@@ -1117,7 +1270,18 @@
 static enum print_line_t
 print_graph_function(struct trace_iterator *iter)
 {
-	return print_graph_function_flags(iter, tracer_flags.val);
+	return __print_graph_function_flags(iter, tracer_flags.val);
+}
+
+enum print_line_t print_graph_function_flags(struct trace_iterator *iter,
+					     u32 flags)
+{
+	if (trace_flags & TRACE_ITER_LATENCY_FMT)
+		flags |= TRACE_GRAPH_PRINT_DURATION;
+	else
+		flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+	return __print_graph_function_flags(iter, flags);
 }
 
 static enum print_line_t
@@ -1149,7 +1313,7 @@
 	seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
 }
 
-void print_graph_headers_flags(struct seq_file *s, u32 flags)
+static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
 	int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
 
@@ -1190,6 +1354,23 @@
 	print_graph_headers_flags(s, tracer_flags.val);
 }
 
+void print_graph_headers_flags(struct seq_file *s, u32 flags)
+{
+	struct trace_iterator *iter = s->private;
+
+	if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+		/* print nothing if the buffers are empty */
+		if (trace_empty(iter))
+			return;
+
+		print_trace_header(s, iter);
+		flags |= TRACE_GRAPH_PRINT_DURATION;
+	} else
+		flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+	__print_graph_headers_flags(s, flags);
+}
+
 void graph_trace_open(struct trace_iterator *iter)
 {
 	/* pid and depth on the last trace processed */
@@ -1210,9 +1391,12 @@
 		pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
 		int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
 		int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore);
+		int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
 		*pid = -1;
 		*depth = 0;
 		*ignore = 0;
+		*depth_irq = -1;
 	}
 
 	iter->private = data;
@@ -1235,6 +1419,14 @@
 	}
 }
 
+static int func_graph_set_flag(u32 old_flags, u32 bit, int set)
+{
+	if (bit == TRACE_GRAPH_PRINT_IRQS)
+		ftrace_graph_skip_irqs = !set;
+
+	return 0;
+}
+
 static struct trace_event_functions graph_functions = {
 	.trace		= print_graph_function_event,
 };
@@ -1261,6 +1453,7 @@
 	.print_line	= print_graph_function,
 	.print_header	= print_graph_headers,
 	.flags		= &tracer_flags,
+	.set_flag	= func_graph_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_function_graph,
 #endif
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 73a6b06..5cf8c60 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -87,14 +87,22 @@
 
 #ifdef CONFIG_FUNCTION_TRACER
 /*
- * irqsoff uses its own tracer function to keep the overhead down:
+ * Prologue for the preempt and irqs off function tracers.
+ *
+ * Returns 1 if it is OK to continue, and data->disabled is
+ *            incremented.
+ *         0 if the trace is to be ignored, and data->disabled
+ *            is kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
  */
-static void
-irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+static int func_prolog_dec(struct trace_array *tr,
+			   struct trace_array_cpu **data,
+			   unsigned long *flags)
 {
-	struct trace_array *tr = irqsoff_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
 	long disabled;
 	int cpu;
 
@@ -106,18 +114,38 @@
 	 */
 	cpu = raw_smp_processor_id();
 	if (likely(!per_cpu(tracing_cpu, cpu)))
-		return;
+		return 0;
 
-	local_save_flags(flags);
+	local_save_flags(*flags);
 	/* slight chance to get a false positive on tracing_cpu */
-	if (!irqs_disabled_flags(flags))
-		return;
+	if (!irqs_disabled_flags(*flags))
+		return 0;
 
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
+	*data = tr->data[cpu];
+	disabled = atomic_inc_return(&(*data)->disabled);
 
 	if (likely(disabled == 1))
-		trace_function(tr, ip, parent_ip, flags, preempt_count());
+		return 1;
+
+	atomic_dec(&(*data)->disabled);
+
+	return 0;
+}
+
+/*
+ * irqsoff uses its own tracer function to keep the overhead down:
+ */
+static void
+irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct trace_array *tr = irqsoff_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+
+	if (!func_prolog_dec(tr, &data, &flags))
+		return;
+
+	trace_function(tr, ip, parent_ip, flags, preempt_count());
 
 	atomic_dec(&data->disabled);
 }
@@ -155,30 +183,16 @@
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
 	unsigned long flags;
-	long disabled;
 	int ret;
-	int cpu;
 	int pc;
 
-	cpu = raw_smp_processor_id();
-	if (likely(!per_cpu(tracing_cpu, cpu)))
+	if (!func_prolog_dec(tr, &data, &flags))
 		return 0;
 
-	local_save_flags(flags);
-	/* slight chance to get a false positive on tracing_cpu */
-	if (!irqs_disabled_flags(flags))
-		return 0;
-
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
-		ret = __trace_graph_entry(tr, trace, flags, pc);
-	} else
-		ret = 0;
-
+	pc = preempt_count();
+	ret = __trace_graph_entry(tr, trace, flags, pc);
 	atomic_dec(&data->disabled);
+
 	return ret;
 }
 
@@ -187,27 +201,13 @@
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
 	unsigned long flags;
-	long disabled;
-	int cpu;
 	int pc;
 
-	cpu = raw_smp_processor_id();
-	if (likely(!per_cpu(tracing_cpu, cpu)))
+	if (!func_prolog_dec(tr, &data, &flags))
 		return;
 
-	local_save_flags(flags);
-	/* slight chance to get a false positive on tracing_cpu */
-	if (!irqs_disabled_flags(flags))
-		return;
-
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
-		__trace_graph_return(tr, trace, flags, pc);
-	}
-
+	pc = preempt_count();
+	__trace_graph_return(tr, trace, flags, pc);
 	atomic_dec(&data->disabled);
 }
 
@@ -229,75 +229,33 @@
 
 static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 {
-	u32 flags = GRAPH_TRACER_FLAGS;
-
-	if (trace_flags & TRACE_ITER_LATENCY_FMT)
-		flags |= TRACE_GRAPH_PRINT_DURATION;
-	else
-		flags |= TRACE_GRAPH_PRINT_ABS_TIME;
-
 	/*
 	 * In graph mode call the graph tracer output function,
 	 * otherwise go with the TRACE_FN event handler
 	 */
 	if (is_graph())
-		return print_graph_function_flags(iter, flags);
+		return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
 
 	return TRACE_TYPE_UNHANDLED;
 }
 
 static void irqsoff_print_header(struct seq_file *s)
 {
-	if (is_graph()) {
-		struct trace_iterator *iter = s->private;
-		u32 flags = GRAPH_TRACER_FLAGS;
-
-		if (trace_flags & TRACE_ITER_LATENCY_FMT) {
-			/* print nothing if the buffers are empty */
-			if (trace_empty(iter))
-				return;
-
-			print_trace_header(s, iter);
-			flags |= TRACE_GRAPH_PRINT_DURATION;
-		} else
-			flags |= TRACE_GRAPH_PRINT_ABS_TIME;
-
-		print_graph_headers_flags(s, flags);
-	} else
+	if (is_graph())
+		print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+	else
 		trace_default_header(s);
 }
 
 static void
-trace_graph_function(struct trace_array *tr,
-		 unsigned long ip, unsigned long flags, int pc)
-{
-	u64 time = trace_clock_local();
-	struct ftrace_graph_ent ent = {
-		.func  = ip,
-		.depth = 0,
-	};
-	struct ftrace_graph_ret ret = {
-		.func     = ip,
-		.depth    = 0,
-		.calltime = time,
-		.rettime  = time,
-	};
-
-	__trace_graph_entry(tr, &ent, flags, pc);
-	__trace_graph_return(tr, &ret, flags, pc);
-}
-
-static void
 __trace_function(struct trace_array *tr,
 		 unsigned long ip, unsigned long parent_ip,
 		 unsigned long flags, int pc)
 {
-	if (!is_graph())
+	if (is_graph())
+		trace_graph_function(tr, ip, parent_ip, flags, pc);
+	else
 		trace_function(tr, ip, parent_ip, flags, pc);
-	else {
-		trace_graph_function(tr, parent_ip, flags, pc);
-		trace_graph_function(tr, ip, flags, pc);
-	}
 }
 
 #else
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 4086eae6..7319559 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -31,13 +31,81 @@
 static arch_spinlock_t wakeup_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
+static void wakeup_reset(struct trace_array *tr);
 static void __wakeup_reset(struct trace_array *tr);
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
+static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
 static int save_lat_flag;
 
+#define TRACE_DISPLAY_GRAPH     1
+
+static struct tracer_opt trace_opts[] = {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* display latency trace as call graph */
+	{ TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+#endif
+	{ } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+	.val  = 0,
+	.opts = trace_opts,
+};
+
+#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
+
 #ifdef CONFIG_FUNCTION_TRACER
+
 /*
- * irqsoff uses its own tracer function to keep the overhead down:
+ * Prologue for the wakeup function tracers.
+ *
+ * Returns 1 if it is OK to continue, and preemption
+ *            is disabled and data->disabled is incremented.
+ *         0 if the trace is to be ignored, and preemption
+ *            is not disabled and data->disabled is
+ *            kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
+ */
+static int
+func_prolog_preempt_disable(struct trace_array *tr,
+			    struct trace_array_cpu **data,
+			    int *pc)
+{
+	long disabled;
+	int cpu;
+
+	if (likely(!wakeup_task))
+		return 0;
+
+	*pc = preempt_count();
+	preempt_disable_notrace();
+
+	cpu = raw_smp_processor_id();
+	if (cpu != wakeup_current_cpu)
+		goto out_enable;
+
+	*data = tr->data[cpu];
+	disabled = atomic_inc_return(&(*data)->disabled);
+	if (unlikely(disabled != 1))
+		goto out;
+
+	return 1;
+
+out:
+	atomic_dec(&(*data)->disabled);
+
+out_enable:
+	preempt_enable_notrace();
+	return 0;
+}
+
+/*
+ * wakeup uses its own tracer function to keep the overhead down:
  */
 static void
 wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
@@ -45,34 +113,16 @@
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
 	unsigned long flags;
-	long disabled;
-	int cpu;
 	int pc;
 
-	if (likely(!wakeup_task))
+	if (!func_prolog_preempt_disable(tr, &data, &pc))
 		return;
 
-	pc = preempt_count();
-	preempt_disable_notrace();
-
-	cpu = raw_smp_processor_id();
-	if (cpu != wakeup_current_cpu)
-		goto out_enable;
-
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-	if (unlikely(disabled != 1))
-		goto out;
-
 	local_irq_save(flags);
-
 	trace_function(tr, ip, parent_ip, flags, pc);
-
 	local_irq_restore(flags);
 
- out:
 	atomic_dec(&data->disabled);
- out_enable:
 	preempt_enable_notrace();
 }
 
@@ -82,6 +132,156 @@
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
+static int start_func_tracer(int graph)
+{
+	int ret;
+
+	if (!graph)
+		ret = register_ftrace_function(&trace_ops);
+	else
+		ret = register_ftrace_graph(&wakeup_graph_return,
+					    &wakeup_graph_entry);
+
+	if (!ret && tracing_is_enabled())
+		tracer_enabled = 1;
+	else
+		tracer_enabled = 0;
+
+	return ret;
+}
+
+static void stop_func_tracer(int graph)
+{
+	tracer_enabled = 0;
+
+	if (!graph)
+		unregister_ftrace_function(&trace_ops);
+	else
+		unregister_ftrace_graph();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+{
+
+	if (!(bit & TRACE_DISPLAY_GRAPH))
+		return -EINVAL;
+
+	if (!(is_graph() ^ set))
+		return 0;
+
+	stop_func_tracer(!set);
+
+	wakeup_reset(wakeup_trace);
+	tracing_max_latency = 0;
+
+	return start_func_tracer(set);
+}
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = wakeup_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	int pc, ret = 0;
+
+	if (!func_prolog_preempt_disable(tr, &data, &pc))
+		return 0;
+
+	local_save_flags(flags);
+	ret = __trace_graph_entry(tr, trace, flags, pc);
+	atomic_dec(&data->disabled);
+	preempt_enable_notrace();
+
+	return ret;
+}
+
+static void wakeup_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct trace_array *tr = wakeup_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	int pc;
+
+	if (!func_prolog_preempt_disable(tr, &data, &pc))
+		return;
+
+	local_save_flags(flags);
+	__trace_graph_return(tr, trace, flags, pc);
+	atomic_dec(&data->disabled);
+
+	preempt_enable_notrace();
+	return;
+}
+
+static void wakeup_trace_open(struct trace_iterator *iter)
+{
+	if (is_graph())
+		graph_trace_open(iter);
+}
+
+static void wakeup_trace_close(struct trace_iterator *iter)
+{
+	if (iter->private)
+		graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC)
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+	/*
+	 * In graph mode call the graph tracer output function,
+	 * otherwise go with the TRACE_FN event handler
+	 */
+	if (is_graph())
+		return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
+
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_print_header(struct seq_file *s)
+{
+	if (is_graph())
+		print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+	else
+		trace_default_header(s);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+		 unsigned long ip, unsigned long parent_ip,
+		 unsigned long flags, int pc)
+{
+	if (is_graph())
+		trace_graph_function(tr, ip, parent_ip, flags, pc);
+	else
+		trace_function(tr, ip, parent_ip, flags, pc);
+}
+#else
+#define __trace_function trace_function
+
+static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+{
+	return -EINVAL;
+}
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+	return -1;
+}
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
+static void wakeup_print_header(struct seq_file *s) { }
+static void wakeup_trace_open(struct trace_iterator *iter) { }
+static void wakeup_trace_close(struct trace_iterator *iter) { }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /*
  * Should this new latency be reported/recorded?
  */
@@ -152,7 +352,7 @@
 	/* The task we are waiting for is waking up */
 	data = wakeup_trace->data[wakeup_cpu];
 
-	trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
+	__trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
 	tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
 	T0 = data->preempt_timestamp;
@@ -252,7 +452,7 @@
 	 * is not called by an assembly function  (where as schedule is)
 	 * it should be safe to use it here.
 	 */
-	trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
+	__trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
 
 out_locked:
 	arch_spin_unlock(&wakeup_lock);
@@ -303,12 +503,8 @@
 	 */
 	smp_wmb();
 
-	register_ftrace_function(&trace_ops);
-
-	if (tracing_is_enabled())
-		tracer_enabled = 1;
-	else
-		tracer_enabled = 0;
+	if (start_func_tracer(is_graph()))
+		printk(KERN_ERR "failed to start wakeup tracer\n");
 
 	return;
 fail_deprobe_wake_new:
@@ -320,7 +516,7 @@
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
 	tracer_enabled = 0;
-	unregister_ftrace_function(&trace_ops);
+	stop_func_tracer(is_graph());
 	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
 	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
 	unregister_trace_sched_wakeup(probe_wakeup, NULL);
@@ -379,9 +575,15 @@
 	.start		= wakeup_tracer_start,
 	.stop		= wakeup_tracer_stop,
 	.print_max	= 1,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flags		= &tracer_flags,
+	.set_flag	= wakeup_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
 	.use_max_tr	= 1,
 };
 
@@ -394,9 +596,15 @@
 	.stop		= wakeup_tracer_stop,
 	.wait_pipe	= poll_wait_pipe,
 	.print_max	= 1,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flags		= &tracer_flags,
+	.set_flag	= wakeup_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
 #endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
 	.use_max_tr	= 1,
 };
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index a6b7e0e..4c5dead 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -195,6 +195,7 @@
 	.open		= tracing_open_generic,
 	.read		= stack_max_size_read,
 	.write		= stack_max_size_write,
+	.llseek		= default_llseek,
 };
 
 static void *
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index a7cc379..209b379 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -263,6 +263,11 @@
 {
 	int ret, cpu;
 
+	for_each_possible_cpu(cpu) {
+		spin_lock_init(&workqueue_cpu_stat(cpu)->lock);
+		INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list);
+	}
+
 	ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
 	if (ret)
 		goto out;
@@ -279,11 +284,6 @@
 	if (ret)
 		goto no_creation;
 
-	for_each_possible_cpu(cpu) {
-		spin_lock_init(&workqueue_cpu_stat(cpu)->lock);
-		INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list);
-	}
-
 	return 0;
 
 no_creation:
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index c77f3ec..e95ee7f 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/jump_label.h>
 
 extern struct tracepoint __start___tracepoints[];
 extern struct tracepoint __stop___tracepoints[];
@@ -263,7 +264,13 @@
 	 * is used.
 	 */
 	rcu_assign_pointer(elem->funcs, (*entry)->funcs);
-	elem->state = active;
+	if (!elem->state && active) {
+		jump_label_enable(&elem->state);
+		elem->state = active;
+	} else if (elem->state && !active) {
+		jump_label_disable(&elem->state);
+		elem->state = active;
+	}
 }
 
 /*
@@ -277,7 +284,10 @@
 	if (elem->unregfunc && elem->state)
 		elem->unregfunc();
 
-	elem->state = 0;
+	if (elem->state) {
+		jump_label_disable(&elem->state);
+		elem->state = 0;
+	}
 	rcu_assign_pointer(elem->funcs, NULL);
 }
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7f9c3c5..bafba68 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -43,7 +43,6 @@
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
 
-static int __read_mostly did_panic;
 static int __initdata no_watchdog;
 
 
@@ -187,18 +186,6 @@
 	return 0;
 }
 
-static int
-watchdog_panic(struct notifier_block *this, unsigned long event, void *ptr)
-{
-	did_panic = 1;
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block panic_block = {
-	.notifier_call = watchdog_panic,
-};
-
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static struct perf_event_attr wd_hw_attr = {
 	.type		= PERF_TYPE_HARDWARE,
@@ -209,7 +196,7 @@
 };
 
 /* Callback function for perf event subsystem */
-void watchdog_overflow_callback(struct perf_event *event, int nmi,
+static void watchdog_overflow_callback(struct perf_event *event, int nmi,
 		 struct perf_sample_data *data,
 		 struct pt_regs *regs)
 {
@@ -371,14 +358,14 @@
 	/* Try to register using hardware perf events */
 	wd_attr = &wd_hw_attr;
 	wd_attr->sample_period = hw_nmi_get_sample_period();
-	event = perf_event_create_kernel_counter(wd_attr, cpu, -1, watchdog_overflow_callback);
+	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback);
 	if (!IS_ERR(event)) {
 		printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");
 		goto out_save;
 	}
 
 	printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event);
-	return -1;
+	return PTR_ERR(event);
 
 	/* success path */
 out_save:
@@ -422,17 +409,19 @@
 static int watchdog_enable(int cpu)
 {
 	struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
+	int err;
 
 	/* enable the perf event */
-	if (watchdog_nmi_enable(cpu) != 0)
-		return -1;
+	err = watchdog_nmi_enable(cpu);
+	if (err)
+		return err;
 
 	/* create the watchdog thread */
 	if (!p) {
 		p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu);
 		if (IS_ERR(p)) {
 			printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu);
-			return -1;
+			return PTR_ERR(p);
 		}
 		kthread_bind(p, cpu);
 		per_cpu(watchdog_touch_ts, cpu) = 0;
@@ -484,6 +473,9 @@
 {
 	int cpu;
 
+	if (no_watchdog)
+		return;
+
 	for_each_online_cpu(cpu)
 		watchdog_disable(cpu);
 
@@ -526,17 +518,16 @@
 cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
 	int hotcpu = (unsigned long)hcpu;
+	int err = 0;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		if (watchdog_prepare_cpu(hotcpu))
-			return NOTIFY_BAD;
+		err = watchdog_prepare_cpu(hotcpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		if (watchdog_enable(hotcpu))
-			return NOTIFY_BAD;
+		err = watchdog_enable(hotcpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
@@ -549,7 +540,7 @@
 		break;
 #endif /* CONFIG_HOTPLUG_CPU */
 	}
-	return NOTIFY_OK;
+	return notifier_from_errno(err);
 }
 
 static struct notifier_block __cpuinitdata cpu_nfb = {
@@ -565,13 +556,11 @@
 		return 0;
 
 	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
-	WARN_ON(err == NOTIFY_BAD);
+	WARN_ON(notifier_to_errno(err));
 
 	cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
 	register_cpu_notifier(&cpu_nfb);
 
-	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
-
 	return 0;
 }
 early_initcall(spawn_watchdog_task);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f77afd9..30acdb7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -42,9 +42,6 @@
 #include <linux/lockdep.h>
 #include <linux/idr.h>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/workqueue.h>
-
 #include "workqueue_sched.h"
 
 enum {
@@ -257,6 +254,9 @@
 EXPORT_SYMBOL_GPL(system_nrt_wq);
 EXPORT_SYMBOL_GPL(system_unbound_wq);
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
+
 #define for_each_busy_worker(worker, i, pos, gcwq)			\
 	for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)			\
 		hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)
@@ -310,21 +310,6 @@
 	     (cpu) < WORK_CPU_NONE;					\
 	     (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq)))
 
-#ifdef CONFIG_LOCKDEP
-/**
- * in_workqueue_context() - in context of specified workqueue?
- * @wq: the workqueue of interest
- *
- * Checks lockdep state to see if the current task is executing from
- * within a workqueue item.  This function exists only if lockdep is
- * enabled.
- */
-int in_workqueue_context(struct workqueue_struct *wq)
-{
-	return lock_is_held(&wq->lockdep_map);
-}
-#endif
-
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 
 static struct debug_obj_descr work_debug_descr;
@@ -604,7 +589,9 @@
 {
 	atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu);
 
-	return !list_empty(&gcwq->worklist) && atomic_read(nr_running) <= 1;
+	return !list_empty(&gcwq->worklist) &&
+		(atomic_read(nr_running) <= 1 ||
+		 gcwq->flags & GCWQ_HIGHPRI_PENDING);
 }
 
 /* Do we need a new worker?  Called from manager. */
@@ -997,6 +984,7 @@
 
 	/* gcwq determined, get cwq and queue */
 	cwq = get_cwq(gcwq->cpu, wq);
+	trace_workqueue_queue_work(cpu, cwq, work);
 
 	BUG_ON(!list_empty(&work->entry));
 
@@ -1004,6 +992,7 @@
 	work_flags = work_color_to_flags(cwq->work_color);
 
 	if (likely(cwq->nr_active < cwq->max_active)) {
+		trace_workqueue_activate_work(work);
 		cwq->nr_active++;
 		worklist = gcwq_determine_ins_pos(gcwq, cwq);
 	} else {
@@ -1679,6 +1668,7 @@
 						    struct work_struct, entry);
 	struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq);
 
+	trace_workqueue_activate_work(work);
 	move_linked_works(work, pos, NULL);
 	__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
 	cwq->nr_active++;
@@ -2326,27 +2316,17 @@
 }
 EXPORT_SYMBOL_GPL(flush_workqueue);
 
-/**
- * flush_work - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * Returns false if @work has already terminated.
- *
- * It is expected that, prior to calling flush_work(), the caller has
- * arranged for the work to not be requeued, otherwise it doesn't make
- * sense to use this function.
- */
-int flush_work(struct work_struct *work)
+static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
+			     bool wait_executing)
 {
 	struct worker *worker = NULL;
 	struct global_cwq *gcwq;
 	struct cpu_workqueue_struct *cwq;
-	struct wq_barrier barr;
 
 	might_sleep();
 	gcwq = get_work_gcwq(work);
 	if (!gcwq)
-		return 0;
+		return false;
 
 	spin_lock_irq(&gcwq->lock);
 	if (!list_empty(&work->entry)) {
@@ -2359,28 +2339,127 @@
 		cwq = get_work_cwq(work);
 		if (unlikely(!cwq || gcwq != cwq->gcwq))
 			goto already_gone;
-	} else {
+	} else if (wait_executing) {
 		worker = find_worker_executing_work(gcwq, work);
 		if (!worker)
 			goto already_gone;
 		cwq = worker->current_cwq;
-	}
+	} else
+		goto already_gone;
 
-	insert_wq_barrier(cwq, &barr, work, worker);
+	insert_wq_barrier(cwq, barr, work, worker);
 	spin_unlock_irq(&gcwq->lock);
 
 	lock_map_acquire(&cwq->wq->lockdep_map);
 	lock_map_release(&cwq->wq->lockdep_map);
-
-	wait_for_completion(&barr.done);
-	destroy_work_on_stack(&barr.work);
-	return 1;
+	return true;
 already_gone:
 	spin_unlock_irq(&gcwq->lock);
-	return 0;
+	return false;
+}
+
+/**
+ * flush_work - wait for a work to finish executing the last queueing instance
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution.  This function considers
+ * only the last queueing instance of @work.  If @work has been
+ * enqueued across different CPUs on a non-reentrant workqueue or on
+ * multiple workqueues, @work might still be executing on return on
+ * some of the CPUs from earlier queueing.
+ *
+ * If @work was queued only on a non-reentrant, ordered or unbound
+ * workqueue, @work is guaranteed to be idle on return if it hasn't
+ * been requeued since flush started.
+ *
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work(struct work_struct *work)
+{
+	struct wq_barrier barr;
+
+	if (start_flush_work(work, &barr, true)) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+		return true;
+	} else
+		return false;
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
+static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
+{
+	struct wq_barrier barr;
+	struct worker *worker;
+
+	spin_lock_irq(&gcwq->lock);
+
+	worker = find_worker_executing_work(gcwq, work);
+	if (unlikely(worker))
+		insert_wq_barrier(worker->current_cwq, &barr, work, worker);
+
+	spin_unlock_irq(&gcwq->lock);
+
+	if (unlikely(worker)) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+		return true;
+	} else
+		return false;
+}
+
+static bool wait_on_work(struct work_struct *work)
+{
+	bool ret = false;
+	int cpu;
+
+	might_sleep();
+
+	lock_map_acquire(&work->lockdep_map);
+	lock_map_release(&work->lockdep_map);
+
+	for_each_gcwq_cpu(cpu)
+		ret |= wait_on_cpu_work(get_gcwq(cpu), work);
+	return ret;
+}
+
+/**
+ * flush_work_sync - wait until a work has finished execution
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution.  On return, it's
+ * guaranteed that all queueing instances of @work which happened
+ * before this function is called are finished.  In other words, if
+ * @work hasn't been requeued since this function was called, @work is
+ * guaranteed to be idle on return.
+ *
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work_sync(struct work_struct *work)
+{
+	struct wq_barrier barr;
+	bool pending, waited;
+
+	/* we'll wait for executions separately, queue barr only if pending */
+	pending = start_flush_work(work, &barr, false);
+
+	/* wait for executions to finish */
+	waited = wait_on_work(work);
+
+	/* wait for the pending one */
+	if (pending) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+	}
+
+	return pending || waited;
+}
+EXPORT_SYMBOL_GPL(flush_work_sync);
+
 /*
  * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
  * so this work can't be re-armed in any way.
@@ -2423,39 +2502,7 @@
 	return ret;
 }
 
-static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
-{
-	struct wq_barrier barr;
-	struct worker *worker;
-
-	spin_lock_irq(&gcwq->lock);
-
-	worker = find_worker_executing_work(gcwq, work);
-	if (unlikely(worker))
-		insert_wq_barrier(worker->current_cwq, &barr, work, worker);
-
-	spin_unlock_irq(&gcwq->lock);
-
-	if (unlikely(worker)) {
-		wait_for_completion(&barr.done);
-		destroy_work_on_stack(&barr.work);
-	}
-}
-
-static void wait_on_work(struct work_struct *work)
-{
-	int cpu;
-
-	might_sleep();
-
-	lock_map_acquire(&work->lockdep_map);
-	lock_map_release(&work->lockdep_map);
-
-	for_each_gcwq_cpu(cpu)
-		wait_on_cpu_work(get_gcwq(cpu), work);
-}
-
-static int __cancel_work_timer(struct work_struct *work,
+static bool __cancel_work_timer(struct work_struct *work,
 				struct timer_list* timer)
 {
 	int ret;
@@ -2472,42 +2519,81 @@
 }
 
 /**
- * cancel_work_sync - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
+ * cancel_work_sync - cancel a work and wait for it to finish
+ * @work: the work to cancel
  *
- * Returns true if @work was pending.
+ * Cancel @work and wait for its execution to finish.  This function
+ * can be used even if the work re-queues itself or migrates to
+ * another workqueue.  On return from this function, @work is
+ * guaranteed to be not pending or executing on any CPU.
  *
- * cancel_work_sync() will cancel the work if it is queued. If the work's
- * callback appears to be running, cancel_work_sync() will block until it
- * has completed.
+ * cancel_work_sync(&delayed_work->work) must not be used for
+ * delayed_work's.  Use cancel_delayed_work_sync() instead.
  *
- * It is possible to use this function if the work re-queues itself. It can
- * cancel the work even if it migrates to another workqueue, however in that
- * case it only guarantees that work->func() has completed on the last queued
- * workqueue.
- *
- * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
- * pending, otherwise it goes into a busy-wait loop until the timer expires.
- *
- * The caller must ensure that workqueue_struct on which this work was last
+ * The caller must ensure that the workqueue on which @work was last
  * queued can't be destroyed before this function returns.
+ *
+ * RETURNS:
+ * %true if @work was pending, %false otherwise.
  */
-int cancel_work_sync(struct work_struct *work)
+bool cancel_work_sync(struct work_struct *work)
 {
 	return __cancel_work_timer(work, NULL);
 }
 EXPORT_SYMBOL_GPL(cancel_work_sync);
 
 /**
- * cancel_delayed_work_sync - reliably kill off a delayed work.
- * @dwork: the delayed work struct
+ * flush_delayed_work - wait for a dwork to finish executing the last queueing
+ * @dwork: the delayed work to flush
  *
- * Returns true if @dwork was pending.
+ * Delayed timer is cancelled and the pending work is queued for
+ * immediate execution.  Like flush_work(), this function only
+ * considers the last queueing instance of @dwork.
  *
- * It is possible to use this function if @dwork rearms itself via queue_work()
- * or queue_delayed_work(). See also the comment for cancel_work_sync().
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
  */
-int cancel_delayed_work_sync(struct delayed_work *dwork)
+bool flush_delayed_work(struct delayed_work *dwork)
+{
+	if (del_timer_sync(&dwork->timer))
+		__queue_work(raw_smp_processor_id(),
+			     get_work_cwq(&dwork->work)->wq, &dwork->work);
+	return flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
+ * flush_delayed_work_sync - wait for a dwork to finish
+ * @dwork: the delayed work to flush
+ *
+ * Delayed timer is cancelled and the pending work is queued for
+ * execution immediately.  Other than timer handling, its behavior
+ * is identical to flush_work_sync().
+ *
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_delayed_work_sync(struct delayed_work *dwork)
+{
+	if (del_timer_sync(&dwork->timer))
+		__queue_work(raw_smp_processor_id(),
+			     get_work_cwq(&dwork->work)->wq, &dwork->work);
+	return flush_work_sync(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work_sync);
+
+/**
+ * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish
+ * @dwork: the delayed work cancel
+ *
+ * This is cancel_work_sync() for delayed works.
+ *
+ * RETURNS:
+ * %true if @dwork was pending, %false otherwise.
+ */
+bool cancel_delayed_work_sync(struct delayed_work *dwork)
 {
 	return __cancel_work_timer(&dwork->work, &dwork->timer);
 }
@@ -2559,23 +2645,6 @@
 EXPORT_SYMBOL(schedule_delayed_work);
 
 /**
- * flush_delayed_work - block until a dwork_struct's callback has terminated
- * @dwork: the delayed work which is to be flushed
- *
- * Any timeout is cancelled, and any pending work is run immediately.
- */
-void flush_delayed_work(struct delayed_work *dwork)
-{
-	if (del_timer_sync(&dwork->timer)) {
-		__queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq,
-			     &dwork->work);
-		put_cpu();
-	}
-	flush_work(&dwork->work);
-}
-EXPORT_SYMBOL(flush_delayed_work);
-
-/**
  * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
  * @cpu: cpu to use
  * @dwork: job to be done
@@ -2592,13 +2661,15 @@
 EXPORT_SYMBOL(schedule_delayed_work_on);
 
 /**
- * schedule_on_each_cpu - call a function on each online CPU from keventd
+ * schedule_on_each_cpu - execute a function synchronously on each online CPU
  * @func: the function to call
  *
- * Returns zero on success.
- * Returns -ve errno on failure.
- *
+ * schedule_on_each_cpu() executes @func on each online CPU using the
+ * system workqueue and blocks until all CPUs have completed.
  * schedule_on_each_cpu() is very slow.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
  */
 int schedule_on_each_cpu(work_func_t func)
 {
@@ -2764,6 +2835,13 @@
 	unsigned int cpu;
 
 	/*
+	 * Workqueues which may be used during memory reclaim should
+	 * have a rescuer to guarantee forward progress.
+	 */
+	if (flags & WQ_MEM_RECLAIM)
+		flags |= WQ_RESCUER;
+
+	/*
 	 * Unbound workqueues aren't concurrency managed and should be
 	 * dispatched to workers immediately.
 	 */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 1b4afd2..7b2a8ca9 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -461,6 +461,15 @@
 	 This feature allows mutex semantics violations to be detected and
 	 reported.
 
+config BKL
+	bool "Big Kernel Lock" if (SMP || PREEMPT)
+	default y
+	help
+	  This is the traditional lock that is used in old code instead
+	  of proper locking. All drivers that use the BKL should depend
+	  on this symbol.
+	  Say Y here unless you are working on removing the BKL.
+
 config DEBUG_LOCK_ALLOC
 	bool "Lock debugging: detect incorrect freeing of live locks"
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
@@ -482,6 +491,7 @@
 	select DEBUG_SPINLOCK
 	select DEBUG_MUTEXES
 	select DEBUG_LOCK_ALLOC
+	select TRACE_IRQFLAGS
 	default n
 	help
 	 This feature enables the kernel to prove that all locking
@@ -539,6 +549,23 @@
 	 disabling, allowing multiple RCU-lockdep warnings to be printed
 	 on a single reboot.
 
+	 Say Y to allow multiple RCU-lockdep warnings per boot.
+
+	 Say N if you are unsure.
+
+config SPARSE_RCU_POINTER
+	bool "RCU debugging: sparse-based checks for pointer usage"
+	default n
+	help
+	 This feature enables the __rcu sparse annotation for
+	 RCU-protected pointers.  This annotation will cause sparse
+	 to flag any non-RCU used of annotated pointers.  This can be
+	 helpful when debugging RCU usage.  Please note that this feature
+	 is not intended to enforce code cleanliness; it is instead merely
+	 a debugging aid.
+
+	 Say Y to make sparse flag questionable use of RCU-protected pointers
+
 	 Say N if you are unsure.
 
 config LOCKDEP
@@ -579,11 +606,10 @@
 	  of more runtime overhead.
 
 config TRACE_IRQFLAGS
-	depends on DEBUG_KERNEL
 	bool
-	default y
-	depends on TRACE_IRQFLAGS_SUPPORT
-	depends on PROVE_LOCKING
+	help
+	  Enables hooks to interrupt enabling and disabling for
+	  either tracing or lock debugging.
 
 config DEBUG_SPINLOCK_SLEEP
 	bool "Spinlock debugging: sleep-inside-spinlock checking"
@@ -832,6 +858,30 @@
 
 	  Say Y if you are unsure.
 
+config RCU_CPU_STALL_TIMEOUT
+	int "RCU CPU stall timeout in seconds"
+	depends on RCU_CPU_STALL_DETECTOR
+	range 3 300
+	default 60
+	help
+	  If a given RCU grace period extends more than the specified
+	  number of seconds, a CPU stall warning is printed.  If the
+	  RCU grace period persists, additional CPU stall warnings are
+	  printed at more widely spaced intervals.
+
+config RCU_CPU_STALL_DETECTOR_RUNNABLE
+	bool "RCU CPU stall checking starts automatically at boot"
+	depends on RCU_CPU_STALL_DETECTOR
+	default y
+	help
+	  If set, start checking for RCU CPU stalls immediately on
+	  boot.  Otherwise, RCU CPU stall checking must be manually
+	  enabled.
+
+	  Say Y if you are unsure.
+
+	  Say N if you wish to suppress RCU CPU stall checking during boot.
+
 config RCU_CPU_STALL_VERBOSE
 	bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR"
 	depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 01e6427..4bfb047 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -590,6 +590,7 @@
 static const struct file_operations filter_fops = {
 	.read  = filter_read,
 	.write = filter_write,
+	.llseek = default_llseek,
 };
 
 static int dma_debug_fs_init(void)
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 02afc25..7bd6df7 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -26,19 +26,11 @@
 #include <linux/dynamic_debug.h>
 #include <linux/debugfs.h>
 #include <linux/slab.h>
+#include <linux/jump_label.h>
 
 extern struct _ddebug __start___verbose[];
 extern struct _ddebug __stop___verbose[];
 
-/* dynamic_debug_enabled, and dynamic_debug_enabled2 are bitmasks in which
- * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They
- * use independent hash functions, to reduce the chance of false positives.
- */
-long long dynamic_debug_enabled;
-EXPORT_SYMBOL_GPL(dynamic_debug_enabled);
-long long dynamic_debug_enabled2;
-EXPORT_SYMBOL_GPL(dynamic_debug_enabled2);
-
 struct ddebug_table {
 	struct list_head link;
 	char *mod_name;
@@ -88,26 +80,6 @@
 }
 
 /*
- * must be called with ddebug_lock held
- */
-
-static int disabled_hash(char hash, bool first_table)
-{
-	struct ddebug_table *dt;
-	char table_hash_value;
-
-	list_for_each_entry(dt, &ddebug_tables, link) {
-		if (first_table)
-			table_hash_value = dt->ddebugs->primary_hash;
-		else
-			table_hash_value = dt->ddebugs->secondary_hash;
-		if (dt->num_enabled && (hash == table_hash_value))
-			return 0;
-	}
-	return 1;
-}
-
-/*
  * Search the tables for _ddebug's which match the given
  * `query' and apply the `flags' and `mask' to them.  Tells
  * the user which ddebug's were changed, or whether none
@@ -170,17 +142,9 @@
 				dt->num_enabled++;
 			dp->flags = newflags;
 			if (newflags) {
-				dynamic_debug_enabled |=
-						(1LL << dp->primary_hash);
-				dynamic_debug_enabled2 |=
-						(1LL << dp->secondary_hash);
+				jump_label_enable(&dp->enabled);
 			} else {
-				if (disabled_hash(dp->primary_hash, true))
-					dynamic_debug_enabled &=
-						~(1LL << dp->primary_hash);
-				if (disabled_hash(dp->secondary_hash, false))
-					dynamic_debug_enabled2 &=
-						~(1LL << dp->secondary_hash);
+				jump_label_disable(&dp->enabled);
 			}
 			if (verbose)
 				printk(KERN_INFO
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index efd16fa..6f412ab4 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -49,7 +49,7 @@
 	unsigned int	height;		/* Height from the bottom */
 	unsigned int	count;
 	struct rcu_head	rcu_head;
-	void		*slots[RADIX_TREE_MAP_SIZE];
+	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
 	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 34e3082..7c06ee5 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -70,7 +70,7 @@
  */
 static unsigned long io_tlb_overflow = 32*1024;
 
-void *io_tlb_overflow_buffer;
+static void *io_tlb_overflow_buffer;
 
 /*
  * This is a free list describing the number of free entries available from
@@ -147,16 +147,16 @@
 	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
 	 * between io_tlb_start and io_tlb_end.
 	 */
-	io_tlb_list = alloc_bootmem(io_tlb_nslabs * sizeof(int));
+	io_tlb_list = alloc_bootmem_pages(PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
 	for (i = 0; i < io_tlb_nslabs; i++)
  		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
 	io_tlb_index = 0;
-	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(phys_addr_t));
+	io_tlb_orig_addr = alloc_bootmem_pages(PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
 
 	/*
 	 * Get the overflow emergency buffer
 	 */
-	io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
+	io_tlb_overflow_buffer = alloc_bootmem_low_pages(PAGE_ALIGN(io_tlb_overflow));
 	if (!io_tlb_overflow_buffer)
 		panic("Cannot allocate SWIOTLB overflow buffer!\n");
 	if (verbose)
@@ -182,7 +182,7 @@
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
-	io_tlb_start = alloc_bootmem_low_pages(bytes);
+	io_tlb_start = alloc_bootmem_low_pages(PAGE_ALIGN(bytes));
 	if (!io_tlb_start)
 		panic("Cannot allocate SWIOTLB buffer");
 
@@ -308,13 +308,13 @@
 			   get_order(io_tlb_nslabs << IO_TLB_SHIFT));
 	} else {
 		free_bootmem_late(__pa(io_tlb_overflow_buffer),
-				  io_tlb_overflow);
+				  PAGE_ALIGN(io_tlb_overflow));
 		free_bootmem_late(__pa(io_tlb_orig_addr),
-				  io_tlb_nslabs * sizeof(phys_addr_t));
+				  PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
 		free_bootmem_late(__pa(io_tlb_list),
-				  io_tlb_nslabs * sizeof(int));
+				  PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
 		free_bootmem_late(__pa(io_tlb_start),
-				  io_tlb_nslabs << IO_TLB_SHIFT);
+				  PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
 	}
 }
 
diff --git a/mm/Kconfig b/mm/Kconfig
index f0fb912..c2c8a4a 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -301,3 +301,11 @@
 	  of 1 says that all excess pages should be trimmed.
 
 	  See Documentation/nommu-mmap.txt for more information.
+
+#
+# UP and nommu archs use km based percpu allocator
+#
+config NEED_PER_CPU_KM
+	depends on !SMP
+	bool
+	default y
diff --git a/mm/Makefile b/mm/Makefile
index 34b2546..f73f75a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -11,7 +11,7 @@
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
-			   page_isolation.o mm_init.o mmu_context.o \
+			   page_isolation.o mm_init.o mmu_context.o percpu.o \
 			   $(mmu-y)
 obj-y += init-mm.o
 
@@ -36,11 +36,6 @@
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifdef CONFIG_SMP
-obj-y += percpu.o
-else
-obj-y += percpu_up.o
-endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 142c84a..13b0caa 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/kmemleak.h>
 #include <linux/range.h>
+#include <linux/memblock.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -434,7 +435,8 @@
 			      unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(physaddr, physaddr + size);
+	kmemleak_free_part(__va(physaddr), size);
+	memblock_x86_free_range(physaddr, physaddr + size);
 #else
 	unsigned long start, end;
 
@@ -459,7 +461,8 @@
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(addr, addr + size);
+	kmemleak_free_part(__va(addr), size);
+	memblock_x86_free_range(addr, addr + size);
 #else
 	unsigned long start, end;
 
@@ -526,6 +529,12 @@
 }
 
 #ifndef CONFIG_NO_BOOTMEM
+int __weak __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
+				   int flags)
+{
+	return reserve_bootmem(phys, len, flags);
+}
+
 static unsigned long __init align_idx(struct bootmem_data *bdata,
 				      unsigned long idx, unsigned long step)
 {
diff --git a/mm/memblock.c b/mm/memblock.c
index 43840b3..400dc62 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -11,60 +11,55 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
+#include <linux/poison.h>
+#include <linux/pfn.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 #include <linux/memblock.h>
 
-#define MEMBLOCK_ALLOC_ANYWHERE	0
+struct memblock memblock __initdata_memblock;
 
-struct memblock memblock;
+int memblock_debug __initdata_memblock;
+int memblock_can_resize __initdata_memblock;
+static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock;
+static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock;
 
-static int memblock_debug;
-
-static int __init early_memblock(char *p)
+/* inline so we don't get a warning when pr_debug is compiled out */
+static inline const char *memblock_type_name(struct memblock_type *type)
 {
-	if (p && strstr(p, "debug"))
-		memblock_debug = 1;
-	return 0;
-}
-early_param("memblock", early_memblock);
-
-static void memblock_dump(struct memblock_region *region, char *name)
-{
-	unsigned long long base, size;
-	int i;
-
-	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
-
-	for (i = 0; i < region->cnt; i++) {
-		base = region->region[i].base;
-		size = region->region[i].size;
-
-		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
-		    name, i, base, base + size - 1, size);
-	}
+	if (type == &memblock.memory)
+		return "memory";
+	else if (type == &memblock.reserved)
+		return "reserved";
+	else
+		return "unknown";
 }
 
-void memblock_dump_all(void)
+/*
+ * Address comparison utilities
+ */
+
+static phys_addr_t __init_memblock memblock_align_down(phys_addr_t addr, phys_addr_t size)
 {
-	if (!memblock_debug)
-		return;
-
-	pr_info("MEMBLOCK configuration:\n");
-	pr_info(" rmo_size    = 0x%llx\n", (unsigned long long)memblock.rmo_size);
-	pr_info(" memory.size = 0x%llx\n", (unsigned long long)memblock.memory.size);
-
-	memblock_dump(&memblock.memory, "memory");
-	memblock_dump(&memblock.reserved, "reserved");
+	return addr & ~(size - 1);
 }
 
-static unsigned long memblock_addrs_overlap(u64 base1, u64 size1, u64 base2,
-					u64 size2)
+static phys_addr_t __init_memblock memblock_align_up(phys_addr_t addr, phys_addr_t size)
+{
+	return (addr + (size - 1)) & ~(size - 1);
+}
+
+static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
+				       phys_addr_t base2, phys_addr_t size2)
 {
 	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
 }
 
-static long memblock_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2)
+static long __init_memblock memblock_addrs_adjacent(phys_addr_t base1, phys_addr_t size1,
+			       phys_addr_t base2, phys_addr_t size2)
 {
 	if (base2 == base1 + size1)
 		return 1;
@@ -74,174 +69,365 @@
 	return 0;
 }
 
-static long memblock_regions_adjacent(struct memblock_region *rgn,
-		unsigned long r1, unsigned long r2)
+static long __init_memblock memblock_regions_adjacent(struct memblock_type *type,
+				 unsigned long r1, unsigned long r2)
 {
-	u64 base1 = rgn->region[r1].base;
-	u64 size1 = rgn->region[r1].size;
-	u64 base2 = rgn->region[r2].base;
-	u64 size2 = rgn->region[r2].size;
+	phys_addr_t base1 = type->regions[r1].base;
+	phys_addr_t size1 = type->regions[r1].size;
+	phys_addr_t base2 = type->regions[r2].base;
+	phys_addr_t size2 = type->regions[r2].size;
 
 	return memblock_addrs_adjacent(base1, size1, base2, size2);
 }
 
-static void memblock_remove_region(struct memblock_region *rgn, unsigned long r)
+long __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
 	unsigned long i;
 
-	for (i = r; i < rgn->cnt - 1; i++) {
-		rgn->region[i].base = rgn->region[i + 1].base;
-		rgn->region[i].size = rgn->region[i + 1].size;
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
+		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
+			break;
 	}
-	rgn->cnt--;
+
+	return (i < type->cnt) ? i : -1;
+}
+
+/*
+ * Find, allocate, deallocate or reserve unreserved regions. All allocations
+ * are top-down.
+ */
+
+static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_addr_t end,
+					  phys_addr_t size, phys_addr_t align)
+{
+	phys_addr_t base, res_base;
+	long j;
+
+	/* In case, huge size is requested */
+	if (end < size)
+		return MEMBLOCK_ERROR;
+
+	base = memblock_align_down((end - size), align);
+
+	/* Prevent allocations returning 0 as it's also used to
+	 * indicate an allocation failure
+	 */
+	if (start == 0)
+		start = PAGE_SIZE;
+
+	while (start <= base) {
+		j = memblock_overlaps_region(&memblock.reserved, base, size);
+		if (j < 0)
+			return base;
+		res_base = memblock.reserved.regions[j].base;
+		if (res_base < size)
+			break;
+		base = memblock_align_down(res_base - size, align);
+	}
+
+	return MEMBLOCK_ERROR;
+}
+
+static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size,
+			phys_addr_t align, phys_addr_t start, phys_addr_t end)
+{
+	long i;
+
+	BUG_ON(0 == size);
+
+	size = memblock_align_up(size, align);
+
+	/* Pump up max_addr */
+	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+		end = memblock.current_limit;
+
+	/* We do a top-down search, this tends to limit memory
+	 * fragmentation by keeping early boot allocs near the
+	 * top of memory
+	 */
+	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
+		phys_addr_t memblockbase = memblock.memory.regions[i].base;
+		phys_addr_t memblocksize = memblock.memory.regions[i].size;
+		phys_addr_t bottom, top, found;
+
+		if (memblocksize < size)
+			continue;
+		if ((memblockbase + memblocksize) <= start)
+			break;
+		bottom = max(memblockbase, start);
+		top = min(memblockbase + memblocksize, end);
+		if (bottom >= top)
+			continue;
+		found = memblock_find_region(bottom, top, size, align);
+		if (found != MEMBLOCK_ERROR)
+			return found;
+	}
+	return MEMBLOCK_ERROR;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64 size, u64 align)
+{
+	return memblock_find_base(size, align, start, end);
+}
+
+/*
+ * Free memblock.reserved.regions
+ */
+int __init_memblock memblock_free_reserved_regions(void)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	return memblock_free(__pa(memblock.reserved.regions),
+		 sizeof(struct memblock_region) * memblock.reserved.max);
+}
+
+/*
+ * Reserve memblock.reserved.regions
+ */
+int __init_memblock memblock_reserve_reserved_regions(void)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	return memblock_reserve(__pa(memblock.reserved.regions),
+		 sizeof(struct memblock_region) * memblock.reserved.max);
+}
+
+static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
+{
+	unsigned long i;
+
+	for (i = r; i < type->cnt - 1; i++) {
+		type->regions[i].base = type->regions[i + 1].base;
+		type->regions[i].size = type->regions[i + 1].size;
+	}
+	type->cnt--;
 }
 
 /* Assumption: base addr of region 1 < base addr of region 2 */
-static void memblock_coalesce_regions(struct memblock_region *rgn,
+static void __init_memblock memblock_coalesce_regions(struct memblock_type *type,
 		unsigned long r1, unsigned long r2)
 {
-	rgn->region[r1].size += rgn->region[r2].size;
-	memblock_remove_region(rgn, r2);
+	type->regions[r1].size += type->regions[r2].size;
+	memblock_remove_region(type, r2);
 }
 
-void __init memblock_init(void)
+/* Defined below but needed now */
+static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size);
+
+static int __init_memblock memblock_double_array(struct memblock_type *type)
 {
-	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
-	 * This simplifies the memblock_add() code below...
+	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_size, new_size, addr;
+	int use_slab = slab_is_available();
+
+	/* We don't allow resizing until we know about the reserved regions
+	 * of memory that aren't suitable for allocation
 	 */
-	memblock.memory.region[0].base = 0;
-	memblock.memory.region[0].size = 0;
-	memblock.memory.cnt = 1;
+	if (!memblock_can_resize)
+		return -1;
 
-	/* Ditto. */
-	memblock.reserved.region[0].base = 0;
-	memblock.reserved.region[0].size = 0;
-	memblock.reserved.cnt = 1;
+	/* Calculate new doubled size */
+	old_size = type->max * sizeof(struct memblock_region);
+	new_size = old_size << 1;
+
+	/* Try to find some space for it.
+	 *
+	 * WARNING: We assume that either slab_is_available() and we use it or
+	 * we use MEMBLOCK for allocations. That means that this is unsafe to use
+	 * when bootmem is currently active (unless bootmem itself is implemented
+	 * on top of MEMBLOCK which isn't the case yet)
+	 *
+	 * This should however not be an issue for now, as we currently only
+	 * call into MEMBLOCK while it's still active, or much later when slab is
+	 * active for memory hotplug operations
+	 */
+	if (use_slab) {
+		new_array = kmalloc(new_size, GFP_KERNEL);
+		addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array);
+	} else
+		addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE);
+	if (addr == MEMBLOCK_ERROR) {
+		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
+		       memblock_type_name(type), type->max, type->max * 2);
+		return -1;
+	}
+	new_array = __va(addr);
+
+	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
+		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
+
+	/* Found space, we now need to move the array over before
+	 * we add the reserved region since it may be our reserved
+	 * array itself that is full.
+	 */
+	memcpy(new_array, type->regions, old_size);
+	memset(new_array + type->max, 0, old_size);
+	old_array = type->regions;
+	type->regions = new_array;
+	type->max <<= 1;
+
+	/* If we use SLAB that's it, we are done */
+	if (use_slab)
+		return 0;
+
+	/* Add the new reserved region now. Should not fail ! */
+	BUG_ON(memblock_add_region(&memblock.reserved, addr, new_size) < 0);
+
+	/* If the array wasn't our static init one, then free it. We only do
+	 * that before SLAB is available as later on, we don't know whether
+	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
+	 * anyways
+	 */
+	if (old_array != memblock_memory_init_regions &&
+	    old_array != memblock_reserved_init_regions)
+		memblock_free(__pa(old_array), old_size);
+
+	return 0;
 }
 
-void __init memblock_analyze(void)
+extern int __init_memblock __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+					  phys_addr_t addr2, phys_addr_t size2)
 {
-	int i;
-
-	memblock.memory.size = 0;
-
-	for (i = 0; i < memblock.memory.cnt; i++)
-		memblock.memory.size += memblock.memory.region[i].size;
+	return 1;
 }
 
-static long memblock_add_region(struct memblock_region *rgn, u64 base, u64 size)
+static long __init_memblock memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
 	unsigned long coalesced = 0;
 	long adjacent, i;
 
-	if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
+	if ((type->cnt == 1) && (type->regions[0].size == 0)) {
+		type->regions[0].base = base;
+		type->regions[0].size = size;
 		return 0;
 	}
 
 	/* First try and coalesce this MEMBLOCK with another. */
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
 
 		if ((rgnbase == base) && (rgnsize == size))
 			/* Already have this region, so we're done */
 			return 0;
 
 		adjacent = memblock_addrs_adjacent(base, size, rgnbase, rgnsize);
+		/* Check if arch allows coalescing */
+		if (adjacent != 0 && type == &memblock.memory &&
+		    !memblock_memory_can_coalesce(base, size, rgnbase, rgnsize))
+			break;
 		if (adjacent > 0) {
-			rgn->region[i].base -= size;
-			rgn->region[i].size += size;
+			type->regions[i].base -= size;
+			type->regions[i].size += size;
 			coalesced++;
 			break;
 		} else if (adjacent < 0) {
-			rgn->region[i].size += size;
+			type->regions[i].size += size;
 			coalesced++;
 			break;
 		}
 	}
 
-	if ((i < rgn->cnt - 1) && memblock_regions_adjacent(rgn, i, i+1)) {
-		memblock_coalesce_regions(rgn, i, i+1);
+	/* If we plugged a hole, we may want to also coalesce with the
+	 * next region
+	 */
+	if ((i < type->cnt - 1) && memblock_regions_adjacent(type, i, i+1) &&
+	    ((type != &memblock.memory || memblock_memory_can_coalesce(type->regions[i].base,
+							     type->regions[i].size,
+							     type->regions[i+1].base,
+							     type->regions[i+1].size)))) {
+		memblock_coalesce_regions(type, i, i+1);
 		coalesced++;
 	}
 
 	if (coalesced)
 		return coalesced;
-	if (rgn->cnt >= MAX_MEMBLOCK_REGIONS)
+
+	/* If we are out of space, we fail. It's too late to resize the array
+	 * but then this shouldn't have happened in the first place.
+	 */
+	if (WARN_ON(type->cnt >= type->max))
 		return -1;
 
 	/* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */
-	for (i = rgn->cnt - 1; i >= 0; i--) {
-		if (base < rgn->region[i].base) {
-			rgn->region[i+1].base = rgn->region[i].base;
-			rgn->region[i+1].size = rgn->region[i].size;
+	for (i = type->cnt - 1; i >= 0; i--) {
+		if (base < type->regions[i].base) {
+			type->regions[i+1].base = type->regions[i].base;
+			type->regions[i+1].size = type->regions[i].size;
 		} else {
-			rgn->region[i+1].base = base;
-			rgn->region[i+1].size = size;
+			type->regions[i+1].base = base;
+			type->regions[i+1].size = size;
 			break;
 		}
 	}
 
-	if (base < rgn->region[0].base) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
+	if (base < type->regions[0].base) {
+		type->regions[0].base = base;
+		type->regions[0].size = size;
 	}
-	rgn->cnt++;
+	type->cnt++;
+
+	/* The array is full ? Try to resize it. If that fails, we undo
+	 * our allocation and return an error
+	 */
+	if (type->cnt == type->max && memblock_double_array(type)) {
+		type->cnt--;
+		return -1;
+	}
 
 	return 0;
 }
 
-long memblock_add(u64 base, u64 size)
+long __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_region *_rgn = &memblock.memory;
-
-	/* On pSeries LPAR systems, the first MEMBLOCK is our RMO region. */
-	if (base == 0)
-		memblock.rmo_size = size;
-
-	return memblock_add_region(_rgn, base, size);
+	return memblock_add_region(&memblock.memory, base, size);
 
 }
 
-static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size)
+static long __init_memblock __memblock_remove(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
-	u64 rgnbegin, rgnend;
-	u64 end = base + size;
+	phys_addr_t rgnbegin, rgnend;
+	phys_addr_t end = base + size;
 	int i;
 
 	rgnbegin = rgnend = 0; /* supress gcc warnings */
 
 	/* Find the region where (base, size) belongs to */
-	for (i=0; i < rgn->cnt; i++) {
-		rgnbegin = rgn->region[i].base;
-		rgnend = rgnbegin + rgn->region[i].size;
+	for (i=0; i < type->cnt; i++) {
+		rgnbegin = type->regions[i].base;
+		rgnend = rgnbegin + type->regions[i].size;
 
 		if ((rgnbegin <= base) && (end <= rgnend))
 			break;
 	}
 
 	/* Didn't find the region */
-	if (i == rgn->cnt)
+	if (i == type->cnt)
 		return -1;
 
 	/* Check to see if we are removing entire region */
 	if ((rgnbegin == base) && (rgnend == end)) {
-		memblock_remove_region(rgn, i);
+		memblock_remove_region(type, i);
 		return 0;
 	}
 
 	/* Check to see if region is matching at the front */
 	if (rgnbegin == base) {
-		rgn->region[i].base = end;
-		rgn->region[i].size -= size;
+		type->regions[i].base = end;
+		type->regions[i].size -= size;
 		return 0;
 	}
 
 	/* Check to see if the region is matching at the end */
 	if (rgnend == end) {
-		rgn->region[i].size -= size;
+		type->regions[i].size -= size;
 		return 0;
 	}
 
@@ -249,133 +435,49 @@
 	 * We need to split the entry -  adjust the current one to the
 	 * beginging of the hole and add the region after hole.
 	 */
-	rgn->region[i].size = base - rgn->region[i].base;
-	return memblock_add_region(rgn, end, rgnend - end);
+	type->regions[i].size = base - type->regions[i].base;
+	return memblock_add_region(type, end, rgnend - end);
 }
 
-long memblock_remove(u64 base, u64 size)
+long __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 {
 	return __memblock_remove(&memblock.memory, base, size);
 }
 
-long __init memblock_free(u64 base, u64 size)
+long __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
 {
 	return __memblock_remove(&memblock.reserved, base, size);
 }
 
-long __init memblock_reserve(u64 base, u64 size)
+long __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_region *_rgn = &memblock.reserved;
+	struct memblock_type *_rgn = &memblock.reserved;
 
 	BUG_ON(0 == size);
 
 	return memblock_add_region(_rgn, base, size);
 }
 
-long memblock_overlaps_region(struct memblock_region *rgn, u64 base, u64 size)
+phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	unsigned long i;
+	phys_addr_t found;
 
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
-		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
-			break;
-	}
-
-	return (i < rgn->cnt) ? i : -1;
-}
-
-static u64 memblock_align_down(u64 addr, u64 size)
-{
-	return addr & ~(size - 1);
-}
-
-static u64 memblock_align_up(u64 addr, u64 size)
-{
-	return (addr + (size - 1)) & ~(size - 1);
-}
-
-static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end,
-					   u64 size, u64 align)
-{
-	u64 base, res_base;
-	long j;
-
-	base = memblock_align_down((end - size), align);
-	while (start <= base) {
-		j = memblock_overlaps_region(&memblock.reserved, base, size);
-		if (j < 0) {
-			/* this area isn't reserved, take it */
-			if (memblock_add_region(&memblock.reserved, base, size) < 0)
-				base = ~(u64)0;
-			return base;
-		}
-		res_base = memblock.reserved.region[j].base;
-		if (res_base < size)
-			break;
-		base = memblock_align_down(res_base - size, align);
-	}
-
-	return ~(u64)0;
-}
-
-static u64 __init memblock_alloc_nid_region(struct memblock_property *mp,
-				       u64 (*nid_range)(u64, u64, int *),
-				       u64 size, u64 align, int nid)
-{
-	u64 start, end;
-
-	start = mp->base;
-	end = start + mp->size;
-
-	start = memblock_align_up(start, align);
-	while (start < end) {
-		u64 this_end;
-		int this_nid;
-
-		this_end = nid_range(start, end, &this_nid);
-		if (this_nid == nid) {
-			u64 ret = memblock_alloc_nid_unreserved(start, this_end,
-							   size, align);
-			if (ret != ~(u64)0)
-				return ret;
-		}
-		start = this_end;
-	}
-
-	return ~(u64)0;
-}
-
-u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-			 u64 (*nid_range)(u64 start, u64 end, int *nid))
-{
-	struct memblock_region *mem = &memblock.memory;
-	int i;
-
-	BUG_ON(0 == size);
-
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
 	size = memblock_align_up(size, align);
 
-	for (i = 0; i < mem->cnt; i++) {
-		u64 ret = memblock_alloc_nid_region(&mem->region[i],
-					       nid_range,
-					       size, align, nid);
-		if (ret != ~(u64)0)
-			return ret;
-	}
+	found = memblock_find_base(size, align, 0, max_addr);
+	if (found != MEMBLOCK_ERROR &&
+	    memblock_add_region(&memblock.reserved, found, size) >= 0)
+		return found;
 
-	return memblock_alloc(size, align);
+	return 0;
 }
 
-u64 __init memblock_alloc(u64 size, u64 align)
+phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
-}
-
-u64 __init memblock_alloc_base(u64 size, u64 align, u64 max_addr)
-{
-	u64 alloc;
+	phys_addr_t alloc;
 
 	alloc = __memblock_alloc_base(size, align, max_addr);
 
@@ -386,71 +488,136 @@
 	return alloc;
 }
 
-u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr)
+phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
-	long i, j;
-	u64 base = 0;
-	u64 res_base;
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
+}
+
+
+/*
+ * Additional node-local allocators. Search for node memory is bottom up
+ * and walks memblock regions within that node bottom-up as well, but allocation
+ * within an memblock region is top-down. XXX I plan to fix that at some stage
+ *
+ * WARNING: Only available after early_node_map[] has been populated,
+ * on some architectures, that is after all the calls to add_active_range()
+ * have been done to populate it.
+ */
+
+phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
+{
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+	/*
+	 * This code originates from sparc which really wants use to walk by addresses
+	 * and returns the nid. This is not very convenient for early_pfn_map[] users
+	 * as the map isn't sorted yet, and it really wants to be walked by nid.
+	 *
+	 * For now, I implement the inefficient method below which walks the early
+	 * map multiple times. Eventually we may want to use an ARCH config option
+	 * to implement a completely different method for both case.
+	 */
+	unsigned long start_pfn, end_pfn;
+	int i;
+
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		get_pfn_range_for_nid(i, &start_pfn, &end_pfn);
+		if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn))
+			continue;
+		*nid = i;
+		return min(end, PFN_PHYS(end_pfn));
+	}
+#endif
+	*nid = 0;
+
+	return end;
+}
+
+static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
+					       phys_addr_t size,
+					       phys_addr_t align, int nid)
+{
+	phys_addr_t start, end;
+
+	start = mp->base;
+	end = start + mp->size;
+
+	start = memblock_align_up(start, align);
+	while (start < end) {
+		phys_addr_t this_end;
+		int this_nid;
+
+		this_end = memblock_nid_range(start, end, &this_nid);
+		if (this_nid == nid) {
+			phys_addr_t ret = memblock_find_region(start, this_end, size, align);
+			if (ret != MEMBLOCK_ERROR &&
+			    memblock_add_region(&memblock.reserved, ret, size) >= 0)
+				return ret;
+		}
+		start = this_end;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+
+phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
+{
+	struct memblock_type *mem = &memblock.memory;
+	int i;
 
 	BUG_ON(0 == size);
 
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
 	size = memblock_align_up(size, align);
 
-	/* On some platforms, make sure we allocate lowmem */
-	/* Note that MEMBLOCK_REAL_LIMIT may be MEMBLOCK_ALLOC_ANYWHERE */
-	if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-		max_addr = MEMBLOCK_REAL_LIMIT;
-
-	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
-		u64 memblockbase = memblock.memory.region[i].base;
-		u64 memblocksize = memblock.memory.region[i].size;
-
-		if (memblocksize < size)
-			continue;
-		if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-			base = memblock_align_down(memblockbase + memblocksize - size, align);
-		else if (memblockbase < max_addr) {
-			base = min(memblockbase + memblocksize, max_addr);
-			base = memblock_align_down(base - size, align);
-		} else
-			continue;
-
-		while (base && memblockbase <= base) {
-			j = memblock_overlaps_region(&memblock.reserved, base, size);
-			if (j < 0) {
-				/* this area isn't reserved, take it */
-				if (memblock_add_region(&memblock.reserved, base, size) < 0)
-					return 0;
-				return base;
-			}
-			res_base = memblock.reserved.region[j].base;
-			if (res_base < size)
-				break;
-			base = memblock_align_down(res_base - size, align);
-		}
+	/* We do a bottom-up search for a region with the right
+	 * nid since that's easier considering how memblock_nid_range()
+	 * works
+	 */
+	for (i = 0; i < mem->cnt; i++) {
+		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
+					       size, align, nid);
+		if (ret != MEMBLOCK_ERROR)
+			return ret;
 	}
+
 	return 0;
 }
 
-/* You must call memblock_analyze() before this. */
-u64 __init memblock_phys_mem_size(void)
+phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	return memblock.memory.size;
+	phys_addr_t res = memblock_alloc_nid(size, align, nid);
+
+	if (res)
+		return res;
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
 }
 
-u64 memblock_end_of_DRAM(void)
+
+/*
+ * Remaining API functions
+ */
+
+/* You must call memblock_analyze() before this. */
+phys_addr_t __init memblock_phys_mem_size(void)
+{
+	return memblock.memory_size;
+}
+
+phys_addr_t __init_memblock memblock_end_of_DRAM(void)
 {
 	int idx = memblock.memory.cnt - 1;
 
-	return (memblock.memory.region[idx].base + memblock.memory.region[idx].size);
+	return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
 }
 
 /* You must call memblock_analyze() after this. */
-void __init memblock_enforce_memory_limit(u64 memory_limit)
+void __init memblock_enforce_memory_limit(phys_addr_t memory_limit)
 {
 	unsigned long i;
-	u64 limit;
-	struct memblock_property *p;
+	phys_addr_t limit;
+	struct memblock_region *p;
 
 	if (!memory_limit)
 		return;
@@ -458,24 +625,21 @@
 	/* Truncate the memblock regions to satisfy the memory limit. */
 	limit = memory_limit;
 	for (i = 0; i < memblock.memory.cnt; i++) {
-		if (limit > memblock.memory.region[i].size) {
-			limit -= memblock.memory.region[i].size;
+		if (limit > memblock.memory.regions[i].size) {
+			limit -= memblock.memory.regions[i].size;
 			continue;
 		}
 
-		memblock.memory.region[i].size = limit;
+		memblock.memory.regions[i].size = limit;
 		memblock.memory.cnt = i + 1;
 		break;
 	}
 
-	if (memblock.memory.region[0].size < memblock.rmo_size)
-		memblock.rmo_size = memblock.memory.region[0].size;
-
 	memory_limit = memblock_end_of_DRAM();
 
 	/* And truncate any reserves above the limit also. */
 	for (i = 0; i < memblock.reserved.cnt; i++) {
-		p = &memblock.reserved.region[i];
+		p = &memblock.reserved.regions[i];
 
 		if (p->base > memory_limit)
 			p->size = 0;
@@ -489,53 +653,190 @@
 	}
 }
 
-int __init memblock_is_reserved(u64 addr)
+static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
 {
-	int i;
+	unsigned int left = 0, right = type->cnt;
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		u64 upper = memblock.reserved.region[i].base +
-			memblock.reserved.region[i].size - 1;
-		if ((addr >= memblock.reserved.region[i].base) && (addr <= upper))
-			return 1;
-	}
-	return 0;
+	do {
+		unsigned int mid = (right + left) / 2;
+
+		if (addr < type->regions[mid].base)
+			right = mid;
+		else if (addr >= (type->regions[mid].base +
+				  type->regions[mid].size))
+			left = mid + 1;
+		else
+			return mid;
+	} while (left < right);
+	return -1;
 }
 
-int memblock_is_region_reserved(u64 base, u64 size)
+int __init memblock_is_reserved(phys_addr_t addr)
+{
+	return memblock_search(&memblock.reserved, addr) != -1;
+}
+
+int __init_memblock memblock_is_memory(phys_addr_t addr)
+{
+	return memblock_search(&memblock.memory, addr) != -1;
+}
+
+int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
+{
+	int idx = memblock_search(&memblock.reserved, base);
+
+	if (idx == -1)
+		return 0;
+	return memblock.reserved.regions[idx].base <= base &&
+		(memblock.reserved.regions[idx].base +
+		 memblock.reserved.regions[idx].size) >= (base + size);
+}
+
+int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
 {
 	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
 }
 
-/*
- * Given a <base, len>, find which memory regions belong to this range.
- * Adjust the request and return a contiguous chunk.
- */
-int memblock_find(struct memblock_property *res)
+
+void __init_memblock memblock_set_current_limit(phys_addr_t limit)
+{
+	memblock.current_limit = limit;
+}
+
+static void __init_memblock memblock_dump(struct memblock_type *region, char *name)
+{
+	unsigned long long base, size;
+	int i;
+
+	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
+
+	for (i = 0; i < region->cnt; i++) {
+		base = region->regions[i].base;
+		size = region->regions[i].size;
+
+		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes\n",
+		    name, i, base, base + size - 1, size);
+	}
+}
+
+void __init_memblock memblock_dump_all(void)
+{
+	if (!memblock_debug)
+		return;
+
+	pr_info("MEMBLOCK configuration:\n");
+	pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
+
+	memblock_dump(&memblock.memory, "memory");
+	memblock_dump(&memblock.reserved, "reserved");
+}
+
+void __init memblock_analyze(void)
 {
 	int i;
-	u64 rstart, rend;
 
-	rstart = res->base;
-	rend = rstart + res->size - 1;
+	/* Check marker in the unused last array entry */
+	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		u64 start = memblock.memory.region[i].base;
-		u64 end = start + memblock.memory.region[i].size - 1;
+	memblock.memory_size = 0;
 
-		if (start > rend)
-			return -1;
+	for (i = 0; i < memblock.memory.cnt; i++)
+		memblock.memory_size += memblock.memory.regions[i].size;
 
-		if ((end >= rstart) && (start < rend)) {
-			/* adjust the request */
-			if (rstart < start)
-				rstart = start;
-			if (rend > end)
-				rend = end;
-			res->base = rstart;
-			res->size = rend - rstart + 1;
-			return 0;
-		}
-	}
-	return -1;
+	/* We allow resizing from there */
+	memblock_can_resize = 1;
 }
+
+void __init memblock_init(void)
+{
+	static int init_done __initdata = 0;
+
+	if (init_done)
+		return;
+	init_done = 1;
+
+	/* Hookup the initial arrays */
+	memblock.memory.regions	= memblock_memory_init_regions;
+	memblock.memory.max		= INIT_MEMBLOCK_REGIONS;
+	memblock.reserved.regions	= memblock_reserved_init_regions;
+	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
+
+	/* Write a marker in the unused last array entry */
+	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+
+	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
+	 * This simplifies the memblock_add() code below...
+	 */
+	memblock.memory.regions[0].base = 0;
+	memblock.memory.regions[0].size = 0;
+	memblock.memory.cnt = 1;
+
+	/* Ditto. */
+	memblock.reserved.regions[0].base = 0;
+	memblock.reserved.regions[0].size = 0;
+	memblock.reserved.cnt = 1;
+
+	memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
+}
+
+static int __init early_memblock(char *p)
+{
+	if (p && strstr(p, "debug"))
+		memblock_debug = 1;
+	return 0;
+}
+early_param("memblock", early_memblock);
+
+#if defined(CONFIG_DEBUG_FS) && !defined(ARCH_DISCARD_MEMBLOCK)
+
+static int memblock_debug_show(struct seq_file *m, void *private)
+{
+	struct memblock_type *type = m->private;
+	struct memblock_region *reg;
+	int i;
+
+	for (i = 0; i < type->cnt; i++) {
+		reg = &type->regions[i];
+		seq_printf(m, "%4d: ", i);
+		if (sizeof(phys_addr_t) == 4)
+			seq_printf(m, "0x%08lx..0x%08lx\n",
+				   (unsigned long)reg->base,
+				   (unsigned long)(reg->base + reg->size - 1));
+		else
+			seq_printf(m, "0x%016llx..0x%016llx\n",
+				   (unsigned long long)reg->base,
+				   (unsigned long long)(reg->base + reg->size - 1));
+
+	}
+	return 0;
+}
+
+static int memblock_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, memblock_debug_show, inode->i_private);
+}
+
+static const struct file_operations memblock_debug_fops = {
+	.open = memblock_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init memblock_init_debugfs(void)
+{
+	struct dentry *root = debugfs_create_dir("memblock", NULL);
+	if (!root)
+		return -ENXIO;
+	debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
+	debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
+
+	return 0;
+}
+__initcall(memblock_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/mm/memory.c b/mm/memory.c
index 0e18b4d..98b58fe 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3185,7 +3185,7 @@
 		 * with threads.
 		 */
 		if (flags & FAULT_FLAG_WRITE)
-			flush_tlb_page(vma, address);
+			flush_tlb_fix_spurious_fault(vma, address);
 	}
 unlock:
 	pte_unmap_unlock(pte, ptl);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index dd186c1..d4e940a 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -840,7 +840,6 @@
 	ret = 0;
 	if (drain) {
 		lru_add_drain_all();
-		flush_scheduled_work();
 		cond_resched();
 		drain_all_pages();
 	}
@@ -862,7 +861,6 @@
 	}
 	/* drain all zone's lru pagevec, this is asyncronous... */
 	lru_add_drain_all();
-	flush_scheduled_work();
 	yield();
 	/* drain pcp pages , this is synchrouns. */
 	drain_all_pages();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f12ad18..2a362c5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -21,6 +21,7 @@
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/kmemcheck.h>
@@ -3636,6 +3637,41 @@
 	}
 }
 
+#ifdef CONFIG_HAVE_MEMBLOCK
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	int i;
+
+	/* Need to go over early_node_map to find out good range for node */
+	for_each_active_range_index_in_nid(i, nid) {
+		u64 addr;
+		u64 ei_start, ei_last;
+		u64 final_start, final_end;
+
+		ei_last = early_node_map[i].end_pfn;
+		ei_last <<= PAGE_SHIFT;
+		ei_start = early_node_map[i].start_pfn;
+		ei_start <<= PAGE_SHIFT;
+
+		final_start = max(ei_start, goal);
+		final_end = min(ei_last, limit);
+
+		if (final_start >= final_end)
+			continue;
+
+		addr = memblock_find_in_range(final_start, final_end, size, align);
+
+		if (addr == MEMBLOCK_ERROR)
+			continue;
+
+		return addr;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+#endif
+
 int __init add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid)
 {
@@ -3655,46 +3691,26 @@
 void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)
 {
-	int i;
 	void *ptr;
+	u64 addr;
 
-	if (limit > get_max_mapped())
-		limit = get_max_mapped();
+	if (limit > memblock.current_limit)
+		limit = memblock.current_limit;
 
-	/* need to go over early_node_map to find out good range for node */
-	for_each_active_range_index_in_nid(i, nid) {
-		u64 addr;
-		u64 ei_start, ei_last;
+	addr = find_memory_core_early(nid, size, align, goal, limit);
 
-		ei_last = early_node_map[i].end_pfn;
-		ei_last <<= PAGE_SHIFT;
-		ei_start = early_node_map[i].start_pfn;
-		ei_start <<= PAGE_SHIFT;
-		addr = find_early_area(ei_start, ei_last,
-					 goal, limit, size, align);
+	if (addr == MEMBLOCK_ERROR)
+		return NULL;
 
-		if (addr == -1ULL)
-			continue;
-
-#if 0
-		printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
-				nid,
-				ei_start, ei_last, goal, limit, size,
-				align, addr);
-#endif
-
-		ptr = phys_to_virt(addr);
-		memset(ptr, 0, size);
-		reserve_early_without_check(addr, addr + size, "BOOTMEM");
-		/*
-		 * The min_count is set to 0 so that bootmem allocated blocks
-		 * are never reported as leaks.
-		 */
-		kmemleak_alloc(ptr, size, 0, 0);
-		return ptr;
-	}
-
-	return NULL;
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+	return ptr;
 }
 #endif
 
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index df68085..89633fe 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -27,7 +27,7 @@
  *   chunk size is not aligned.  percpu-km code will whine about it.
  */
 
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#if defined(CONFIG_SMP) && defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
 #error "contiguous percpu allocation is incompatible with paged first chunk"
 #endif
 
@@ -35,7 +35,11 @@
 
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
 {
-	/* noop */
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
+
 	return 0;
 }
 
diff --git a/mm/percpu.c b/mm/percpu.c
index c76ef38..6fc9015 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -76,6 +76,7 @@
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
 #define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
 
+#ifdef CONFIG_SMP
 /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
 #ifndef __addr_to_pcpu_ptr
 #define __addr_to_pcpu_ptr(addr)					\
@@ -89,6 +90,11 @@
 			 (unsigned long)pcpu_base_addr -		\
 			 (unsigned long)__per_cpu_start)
 #endif
+#else	/* CONFIG_SMP */
+/* on UP, it's always identity mapped */
+#define __addr_to_pcpu_ptr(addr)	(void __percpu *)(addr)
+#define __pcpu_ptr_to_addr(ptr)		(void __force *)(ptr)
+#endif	/* CONFIG_SMP */
 
 struct pcpu_chunk {
 	struct list_head	list;		/* linked to pcpu_slot lists */
@@ -820,8 +826,8 @@
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  *
- * Allocate percpu area of @size bytes aligned at @align.  Might
- * sleep.  Might trigger writeouts.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align.
+ * Might sleep.  Might trigger writeouts.
  *
  * CONTEXT:
  * Does GFP_KERNEL allocation.
@@ -840,9 +846,10 @@
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  *
- * Allocate percpu area of @size bytes aligned at @align from reserved
- * percpu area if arch has set it up; otherwise, allocation is served
- * from the same dynamic area.  Might sleep.  Might trigger writeouts.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align
+ * from reserved percpu area if arch has set it up; otherwise,
+ * allocation is served from the same dynamic area.  Might sleep.
+ * Might trigger writeouts.
  *
  * CONTEXT:
  * Does GFP_KERNEL allocation.
@@ -949,6 +956,7 @@
  */
 bool is_kernel_percpu_address(unsigned long addr)
 {
+#ifdef CONFIG_SMP
 	const size_t static_size = __per_cpu_end - __per_cpu_start;
 	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
 	unsigned int cpu;
@@ -959,6 +967,8 @@
 		if ((void *)addr >= start && (void *)addr < start + static_size)
 			return true;
         }
+#endif
+	/* on UP, can't distinguish from other static vars, always false */
 	return false;
 }
 
@@ -1067,6 +1077,321 @@
 }
 
 /**
+ * pcpu_dump_alloc_info - print out information about pcpu_alloc_info
+ * @lvl: loglevel
+ * @ai: allocation info to dump
+ *
+ * Print out information about @ai using loglevel @lvl.
+ */
+static void pcpu_dump_alloc_info(const char *lvl,
+				 const struct pcpu_alloc_info *ai)
+{
+	int group_width = 1, cpu_width = 1, width;
+	char empty_str[] = "--------";
+	int alloc = 0, alloc_end = 0;
+	int group, v;
+	int upa, apl;	/* units per alloc, allocs per line */
+
+	v = ai->nr_groups;
+	while (v /= 10)
+		group_width++;
+
+	v = num_possible_cpus();
+	while (v /= 10)
+		cpu_width++;
+	empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0';
+
+	upa = ai->alloc_size / ai->unit_size;
+	width = upa * (cpu_width + 1) + group_width + 3;
+	apl = rounddown_pow_of_two(max(60 / width, 1));
+
+	printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu",
+	       lvl, ai->static_size, ai->reserved_size, ai->dyn_size,
+	       ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size);
+
+	for (group = 0; group < ai->nr_groups; group++) {
+		const struct pcpu_group_info *gi = &ai->groups[group];
+		int unit = 0, unit_end = 0;
+
+		BUG_ON(gi->nr_units % upa);
+		for (alloc_end += gi->nr_units / upa;
+		     alloc < alloc_end; alloc++) {
+			if (!(alloc % apl)) {
+				printk("\n");
+				printk("%spcpu-alloc: ", lvl);
+			}
+			printk("[%0*d] ", group_width, group);
+
+			for (unit_end += upa; unit < unit_end; unit++)
+				if (gi->cpu_map[unit] != NR_CPUS)
+					printk("%0*d ", cpu_width,
+					       gi->cpu_map[unit]);
+				else
+					printk("%s ", empty_str);
+		}
+	}
+	printk("\n");
+}
+
+/**
+ * pcpu_setup_first_chunk - initialize the first percpu chunk
+ * @ai: pcpu_alloc_info describing how to percpu area is shaped
+ * @base_addr: mapped address
+ *
+ * Initialize the first percpu chunk which contains the kernel static
+ * perpcu area.  This function is to be called from arch percpu area
+ * setup path.
+ *
+ * @ai contains all information necessary to initialize the first
+ * chunk and prime the dynamic percpu allocator.
+ *
+ * @ai->static_size is the size of static percpu area.
+ *
+ * @ai->reserved_size, if non-zero, specifies the amount of bytes to
+ * reserve after the static area in the first chunk.  This reserves
+ * the first chunk such that it's available only through reserved
+ * percpu allocation.  This is primarily used to serve module percpu
+ * static areas on architectures where the addressing model has
+ * limited offset range for symbol relocations to guarantee module
+ * percpu symbols fall inside the relocatable range.
+ *
+ * @ai->dyn_size determines the number of bytes available for dynamic
+ * allocation in the first chunk.  The area between @ai->static_size +
+ * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused.
+ *
+ * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE
+ * and equal to or larger than @ai->static_size + @ai->reserved_size +
+ * @ai->dyn_size.
+ *
+ * @ai->atom_size is the allocation atom size and used as alignment
+ * for vm areas.
+ *
+ * @ai->alloc_size is the allocation size and always multiple of
+ * @ai->atom_size.  This is larger than @ai->atom_size if
+ * @ai->unit_size is larger than @ai->atom_size.
+ *
+ * @ai->nr_groups and @ai->groups describe virtual memory layout of
+ * percpu areas.  Units which should be colocated are put into the
+ * same group.  Dynamic VM areas will be allocated according to these
+ * groupings.  If @ai->nr_groups is zero, a single group containing
+ * all units is assumed.
+ *
+ * The caller should have mapped the first chunk at @base_addr and
+ * copied static data to each unit.
+ *
+ * If the first chunk ends up with both reserved and dynamic areas, it
+ * is served by two chunks - one to serve the core static and reserved
+ * areas and the other for the dynamic area.  They share the same vm
+ * and page map but uses different area allocation map to stay away
+ * from each other.  The latter chunk is circulated in the chunk slots
+ * and available for dynamic allocation like any other chunks.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
+				  void *base_addr)
+{
+	static char cpus_buf[4096] __initdata;
+	static int smap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
+	static int dmap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
+	size_t dyn_size = ai->dyn_size;
+	size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
+	struct pcpu_chunk *schunk, *dchunk = NULL;
+	unsigned long *group_offsets;
+	size_t *group_sizes;
+	unsigned long *unit_off;
+	unsigned int cpu;
+	int *unit_map;
+	int group, unit, i;
+
+	cpumask_scnprintf(cpus_buf, sizeof(cpus_buf), cpu_possible_mask);
+
+#define PCPU_SETUP_BUG_ON(cond)	do {					\
+	if (unlikely(cond)) {						\
+		pr_emerg("PERCPU: failed to initialize, %s", #cond);	\
+		pr_emerg("PERCPU: cpu_possible_mask=%s\n", cpus_buf);	\
+		pcpu_dump_alloc_info(KERN_EMERG, ai);			\
+		BUG();							\
+	}								\
+} while (0)
+
+	/* sanity checks */
+	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
+#ifdef CONFIG_SMP
+	PCPU_SETUP_BUG_ON(!ai->static_size);
+#endif
+	PCPU_SETUP_BUG_ON(!base_addr);
+	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
+	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
+	PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
+	PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
+	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
+
+	/* process group information and build config tables accordingly */
+	group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));
+	group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0]));
+	unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0]));
+	unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0]));
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		unit_map[cpu] = UINT_MAX;
+	pcpu_first_unit_cpu = NR_CPUS;
+
+	for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
+		const struct pcpu_group_info *gi = &ai->groups[group];
+
+		group_offsets[group] = gi->base_offset;
+		group_sizes[group] = gi->nr_units * ai->unit_size;
+
+		for (i = 0; i < gi->nr_units; i++) {
+			cpu = gi->cpu_map[i];
+			if (cpu == NR_CPUS)
+				continue;
+
+			PCPU_SETUP_BUG_ON(cpu > nr_cpu_ids);
+			PCPU_SETUP_BUG_ON(!cpu_possible(cpu));
+			PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX);
+
+			unit_map[cpu] = unit + i;
+			unit_off[cpu] = gi->base_offset + i * ai->unit_size;
+
+			if (pcpu_first_unit_cpu == NR_CPUS)
+				pcpu_first_unit_cpu = cpu;
+			pcpu_last_unit_cpu = cpu;
+		}
+	}
+	pcpu_nr_units = unit;
+
+	for_each_possible_cpu(cpu)
+		PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX);
+
+	/* we're done parsing the input, undefine BUG macro and dump config */
+#undef PCPU_SETUP_BUG_ON
+	pcpu_dump_alloc_info(KERN_INFO, ai);
+
+	pcpu_nr_groups = ai->nr_groups;
+	pcpu_group_offsets = group_offsets;
+	pcpu_group_sizes = group_sizes;
+	pcpu_unit_map = unit_map;
+	pcpu_unit_offsets = unit_off;
+
+	/* determine basic parameters */
+	pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
+	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
+	pcpu_atom_size = ai->atom_size;
+	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
+		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
+
+	/*
+	 * Allocate chunk slots.  The additional last slot is for
+	 * empty chunks.
+	 */
+	pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
+	pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0]));
+	for (i = 0; i < pcpu_nr_slots; i++)
+		INIT_LIST_HEAD(&pcpu_slot[i]);
+
+	/*
+	 * Initialize static chunk.  If reserved_size is zero, the
+	 * static chunk covers static area + dynamic allocation area
+	 * in the first chunk.  If reserved_size is not zero, it
+	 * covers static area + reserved area (mostly used for module
+	 * static percpu allocation).
+	 */
+	schunk = alloc_bootmem(pcpu_chunk_struct_size);
+	INIT_LIST_HEAD(&schunk->list);
+	schunk->base_addr = base_addr;
+	schunk->map = smap;
+	schunk->map_alloc = ARRAY_SIZE(smap);
+	schunk->immutable = true;
+	bitmap_fill(schunk->populated, pcpu_unit_pages);
+
+	if (ai->reserved_size) {
+		schunk->free_size = ai->reserved_size;
+		pcpu_reserved_chunk = schunk;
+		pcpu_reserved_chunk_limit = ai->static_size + ai->reserved_size;
+	} else {
+		schunk->free_size = dyn_size;
+		dyn_size = 0;			/* dynamic area covered */
+	}
+	schunk->contig_hint = schunk->free_size;
+
+	schunk->map[schunk->map_used++] = -ai->static_size;
+	if (schunk->free_size)
+		schunk->map[schunk->map_used++] = schunk->free_size;
+
+	/* init dynamic chunk if necessary */
+	if (dyn_size) {
+		dchunk = alloc_bootmem(pcpu_chunk_struct_size);
+		INIT_LIST_HEAD(&dchunk->list);
+		dchunk->base_addr = base_addr;
+		dchunk->map = dmap;
+		dchunk->map_alloc = ARRAY_SIZE(dmap);
+		dchunk->immutable = true;
+		bitmap_fill(dchunk->populated, pcpu_unit_pages);
+
+		dchunk->contig_hint = dchunk->free_size = dyn_size;
+		dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit;
+		dchunk->map[dchunk->map_used++] = dchunk->free_size;
+	}
+
+	/* link the first chunk in */
+	pcpu_first_chunk = dchunk ?: schunk;
+	pcpu_chunk_relocate(pcpu_first_chunk, -1);
+
+	/* we're done */
+	pcpu_base_addr = base_addr;
+	return 0;
+}
+
+#ifdef CONFIG_SMP
+
+const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
+	[PCPU_FC_AUTO]	= "auto",
+	[PCPU_FC_EMBED]	= "embed",
+	[PCPU_FC_PAGE]	= "page",
+};
+
+enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;
+
+static int __init percpu_alloc_setup(char *str)
+{
+	if (0)
+		/* nada */;
+#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
+	else if (!strcmp(str, "embed"))
+		pcpu_chosen_fc = PCPU_FC_EMBED;
+#endif
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+	else if (!strcmp(str, "page"))
+		pcpu_chosen_fc = PCPU_FC_PAGE;
+#endif
+	else
+		pr_warning("PERCPU: unknown allocator %s specified\n", str);
+
+	return 0;
+}
+early_param("percpu_alloc", percpu_alloc_setup);
+
+/*
+ * pcpu_embed_first_chunk() is used by the generic percpu setup.
+ * Build it if needed by the arch config or the generic setup is going
+ * to be used.
+ */
+#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
+	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
+#define BUILD_EMBED_FIRST_CHUNK
+#endif
+
+/* build pcpu_page_first_chunk() iff needed by the arch config */
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
+#define BUILD_PAGE_FIRST_CHUNK
+#endif
+
+/* pcpu_build_alloc_info() is used by both embed and page first chunk */
+#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK)
+/**
  * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
  * @reserved_size: the size of reserved percpu area in bytes
  * @dyn_size: minimum free size for dynamic allocation in bytes
@@ -1220,303 +1545,9 @@
 
 	return ai;
 }
+#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */
 
-/**
- * pcpu_dump_alloc_info - print out information about pcpu_alloc_info
- * @lvl: loglevel
- * @ai: allocation info to dump
- *
- * Print out information about @ai using loglevel @lvl.
- */
-static void pcpu_dump_alloc_info(const char *lvl,
-				 const struct pcpu_alloc_info *ai)
-{
-	int group_width = 1, cpu_width = 1, width;
-	char empty_str[] = "--------";
-	int alloc = 0, alloc_end = 0;
-	int group, v;
-	int upa, apl;	/* units per alloc, allocs per line */
-
-	v = ai->nr_groups;
-	while (v /= 10)
-		group_width++;
-
-	v = num_possible_cpus();
-	while (v /= 10)
-		cpu_width++;
-	empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0';
-
-	upa = ai->alloc_size / ai->unit_size;
-	width = upa * (cpu_width + 1) + group_width + 3;
-	apl = rounddown_pow_of_two(max(60 / width, 1));
-
-	printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu",
-	       lvl, ai->static_size, ai->reserved_size, ai->dyn_size,
-	       ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size);
-
-	for (group = 0; group < ai->nr_groups; group++) {
-		const struct pcpu_group_info *gi = &ai->groups[group];
-		int unit = 0, unit_end = 0;
-
-		BUG_ON(gi->nr_units % upa);
-		for (alloc_end += gi->nr_units / upa;
-		     alloc < alloc_end; alloc++) {
-			if (!(alloc % apl)) {
-				printk("\n");
-				printk("%spcpu-alloc: ", lvl);
-			}
-			printk("[%0*d] ", group_width, group);
-
-			for (unit_end += upa; unit < unit_end; unit++)
-				if (gi->cpu_map[unit] != NR_CPUS)
-					printk("%0*d ", cpu_width,
-					       gi->cpu_map[unit]);
-				else
-					printk("%s ", empty_str);
-		}
-	}
-	printk("\n");
-}
-
-/**
- * pcpu_setup_first_chunk - initialize the first percpu chunk
- * @ai: pcpu_alloc_info describing how to percpu area is shaped
- * @base_addr: mapped address
- *
- * Initialize the first percpu chunk which contains the kernel static
- * perpcu area.  This function is to be called from arch percpu area
- * setup path.
- *
- * @ai contains all information necessary to initialize the first
- * chunk and prime the dynamic percpu allocator.
- *
- * @ai->static_size is the size of static percpu area.
- *
- * @ai->reserved_size, if non-zero, specifies the amount of bytes to
- * reserve after the static area in the first chunk.  This reserves
- * the first chunk such that it's available only through reserved
- * percpu allocation.  This is primarily used to serve module percpu
- * static areas on architectures where the addressing model has
- * limited offset range for symbol relocations to guarantee module
- * percpu symbols fall inside the relocatable range.
- *
- * @ai->dyn_size determines the number of bytes available for dynamic
- * allocation in the first chunk.  The area between @ai->static_size +
- * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused.
- *
- * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE
- * and equal to or larger than @ai->static_size + @ai->reserved_size +
- * @ai->dyn_size.
- *
- * @ai->atom_size is the allocation atom size and used as alignment
- * for vm areas.
- *
- * @ai->alloc_size is the allocation size and always multiple of
- * @ai->atom_size.  This is larger than @ai->atom_size if
- * @ai->unit_size is larger than @ai->atom_size.
- *
- * @ai->nr_groups and @ai->groups describe virtual memory layout of
- * percpu areas.  Units which should be colocated are put into the
- * same group.  Dynamic VM areas will be allocated according to these
- * groupings.  If @ai->nr_groups is zero, a single group containing
- * all units is assumed.
- *
- * The caller should have mapped the first chunk at @base_addr and
- * copied static data to each unit.
- *
- * If the first chunk ends up with both reserved and dynamic areas, it
- * is served by two chunks - one to serve the core static and reserved
- * areas and the other for the dynamic area.  They share the same vm
- * and page map but uses different area allocation map to stay away
- * from each other.  The latter chunk is circulated in the chunk slots
- * and available for dynamic allocation like any other chunks.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
-				  void *base_addr)
-{
-	static char cpus_buf[4096] __initdata;
-	static int smap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
-	static int dmap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
-	size_t dyn_size = ai->dyn_size;
-	size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
-	struct pcpu_chunk *schunk, *dchunk = NULL;
-	unsigned long *group_offsets;
-	size_t *group_sizes;
-	unsigned long *unit_off;
-	unsigned int cpu;
-	int *unit_map;
-	int group, unit, i;
-
-	cpumask_scnprintf(cpus_buf, sizeof(cpus_buf), cpu_possible_mask);
-
-#define PCPU_SETUP_BUG_ON(cond)	do {					\
-	if (unlikely(cond)) {						\
-		pr_emerg("PERCPU: failed to initialize, %s", #cond);	\
-		pr_emerg("PERCPU: cpu_possible_mask=%s\n", cpus_buf);	\
-		pcpu_dump_alloc_info(KERN_EMERG, ai);			\
-		BUG();							\
-	}								\
-} while (0)
-
-	/* sanity checks */
-	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
-	PCPU_SETUP_BUG_ON(!ai->static_size);
-	PCPU_SETUP_BUG_ON(!base_addr);
-	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
-	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
-	PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
-	PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
-	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
-
-	/* process group information and build config tables accordingly */
-	group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));
-	group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0]));
-	unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0]));
-	unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0]));
-
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
-		unit_map[cpu] = UINT_MAX;
-	pcpu_first_unit_cpu = NR_CPUS;
-
-	for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
-		const struct pcpu_group_info *gi = &ai->groups[group];
-
-		group_offsets[group] = gi->base_offset;
-		group_sizes[group] = gi->nr_units * ai->unit_size;
-
-		for (i = 0; i < gi->nr_units; i++) {
-			cpu = gi->cpu_map[i];
-			if (cpu == NR_CPUS)
-				continue;
-
-			PCPU_SETUP_BUG_ON(cpu > nr_cpu_ids);
-			PCPU_SETUP_BUG_ON(!cpu_possible(cpu));
-			PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX);
-
-			unit_map[cpu] = unit + i;
-			unit_off[cpu] = gi->base_offset + i * ai->unit_size;
-
-			if (pcpu_first_unit_cpu == NR_CPUS)
-				pcpu_first_unit_cpu = cpu;
-			pcpu_last_unit_cpu = cpu;
-		}
-	}
-	pcpu_nr_units = unit;
-
-	for_each_possible_cpu(cpu)
-		PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX);
-
-	/* we're done parsing the input, undefine BUG macro and dump config */
-#undef PCPU_SETUP_BUG_ON
-	pcpu_dump_alloc_info(KERN_INFO, ai);
-
-	pcpu_nr_groups = ai->nr_groups;
-	pcpu_group_offsets = group_offsets;
-	pcpu_group_sizes = group_sizes;
-	pcpu_unit_map = unit_map;
-	pcpu_unit_offsets = unit_off;
-
-	/* determine basic parameters */
-	pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
-	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
-	pcpu_atom_size = ai->atom_size;
-	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
-		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
-
-	/*
-	 * Allocate chunk slots.  The additional last slot is for
-	 * empty chunks.
-	 */
-	pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
-	pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0]));
-	for (i = 0; i < pcpu_nr_slots; i++)
-		INIT_LIST_HEAD(&pcpu_slot[i]);
-
-	/*
-	 * Initialize static chunk.  If reserved_size is zero, the
-	 * static chunk covers static area + dynamic allocation area
-	 * in the first chunk.  If reserved_size is not zero, it
-	 * covers static area + reserved area (mostly used for module
-	 * static percpu allocation).
-	 */
-	schunk = alloc_bootmem(pcpu_chunk_struct_size);
-	INIT_LIST_HEAD(&schunk->list);
-	schunk->base_addr = base_addr;
-	schunk->map = smap;
-	schunk->map_alloc = ARRAY_SIZE(smap);
-	schunk->immutable = true;
-	bitmap_fill(schunk->populated, pcpu_unit_pages);
-
-	if (ai->reserved_size) {
-		schunk->free_size = ai->reserved_size;
-		pcpu_reserved_chunk = schunk;
-		pcpu_reserved_chunk_limit = ai->static_size + ai->reserved_size;
-	} else {
-		schunk->free_size = dyn_size;
-		dyn_size = 0;			/* dynamic area covered */
-	}
-	schunk->contig_hint = schunk->free_size;
-
-	schunk->map[schunk->map_used++] = -ai->static_size;
-	if (schunk->free_size)
-		schunk->map[schunk->map_used++] = schunk->free_size;
-
-	/* init dynamic chunk if necessary */
-	if (dyn_size) {
-		dchunk = alloc_bootmem(pcpu_chunk_struct_size);
-		INIT_LIST_HEAD(&dchunk->list);
-		dchunk->base_addr = base_addr;
-		dchunk->map = dmap;
-		dchunk->map_alloc = ARRAY_SIZE(dmap);
-		dchunk->immutable = true;
-		bitmap_fill(dchunk->populated, pcpu_unit_pages);
-
-		dchunk->contig_hint = dchunk->free_size = dyn_size;
-		dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit;
-		dchunk->map[dchunk->map_used++] = dchunk->free_size;
-	}
-
-	/* link the first chunk in */
-	pcpu_first_chunk = dchunk ?: schunk;
-	pcpu_chunk_relocate(pcpu_first_chunk, -1);
-
-	/* we're done */
-	pcpu_base_addr = base_addr;
-	return 0;
-}
-
-const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
-	[PCPU_FC_AUTO]	= "auto",
-	[PCPU_FC_EMBED]	= "embed",
-	[PCPU_FC_PAGE]	= "page",
-};
-
-enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;
-
-static int __init percpu_alloc_setup(char *str)
-{
-	if (0)
-		/* nada */;
-#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
-	else if (!strcmp(str, "embed"))
-		pcpu_chosen_fc = PCPU_FC_EMBED;
-#endif
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
-	else if (!strcmp(str, "page"))
-		pcpu_chosen_fc = PCPU_FC_PAGE;
-#endif
-	else
-		pr_warning("PERCPU: unknown allocator %s specified\n", str);
-
-	return 0;
-}
-early_param("percpu_alloc", percpu_alloc_setup);
-
-#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
-	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
+#if defined(BUILD_EMBED_FIRST_CHUNK)
 /**
  * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
  * @reserved_size: the size of reserved percpu area in bytes
@@ -1645,10 +1676,9 @@
 		free_bootmem(__pa(areas), areas_size);
 	return rc;
 }
-#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
-	  !CONFIG_HAVE_SETUP_PER_CPU_AREA */
+#endif /* BUILD_EMBED_FIRST_CHUNK */
 
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#ifdef BUILD_PAGE_FIRST_CHUNK
 /**
  * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
  * @reserved_size: the size of reserved percpu area in bytes
@@ -1756,10 +1786,11 @@
 	pcpu_free_alloc_info(ai);
 	return rc;
 }
-#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */
+#endif /* BUILD_PAGE_FIRST_CHUNK */
 
+#ifndef	CONFIG_HAVE_SETUP_PER_CPU_AREA
 /*
- * Generic percpu area setup.
+ * Generic SMP percpu area setup.
  *
  * The embedding helper is used because its behavior closely resembles
  * the original non-dynamic generic percpu area setup.  This is
@@ -1770,7 +1801,6 @@
  * on the physical linear memory mapping which uses large page
  * mappings on applicable archs.
  */
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
@@ -1799,13 +1829,48 @@
 				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
 				    pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
 	if (rc < 0)
-		panic("Failed to initialized percpu areas.");
+		panic("Failed to initialize percpu areas.");
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu)
 		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
 }
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
+#endif	/* CONFIG_HAVE_SETUP_PER_CPU_AREA */
+
+#else	/* CONFIG_SMP */
+
+/*
+ * UP percpu area setup.
+ *
+ * UP always uses km-based percpu allocator with identity mapping.
+ * Static percpu variables are indistinguishable from the usual static
+ * variables and don't require any special preparation.
+ */
+void __init setup_per_cpu_areas(void)
+{
+	const size_t unit_size =
+		roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE,
+					 PERCPU_DYNAMIC_RESERVE));
+	struct pcpu_alloc_info *ai;
+	void *fc;
+
+	ai = pcpu_alloc_alloc_info(1, 1);
+	fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	if (!ai || !fc)
+		panic("Failed to allocate memory for percpu areas.");
+
+	ai->dyn_size = unit_size;
+	ai->unit_size = unit_size;
+	ai->atom_size = unit_size;
+	ai->alloc_size = unit_size;
+	ai->groups[0].nr_units = 1;
+	ai->groups[0].cpu_map[0] = 0;
+
+	if (pcpu_setup_first_chunk(ai, fc) < 0)
+		panic("Failed to initialize percpu areas.");
+}
+
+#endif	/* CONFIG_SMP */
 
 /*
  * First and reserved chunks are initialized with temporary allocation
diff --git a/mm/percpu_up.c b/mm/percpu_up.c
deleted file mode 100644
index db884fa..0000000
--- a/mm/percpu_up.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * mm/percpu_up.c - dummy percpu memory allocator implementation for UP
- */
-
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/slab.h>
-
-void __percpu *__alloc_percpu(size_t size, size_t align)
-{
-	/*
-	 * Can't easily make larger alignment work with kmalloc.  WARN
-	 * on it.  Larger alignment should only be used for module
-	 * percpu sections on SMP for which this path isn't used.
-	 */
-	WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-	return (void __percpu __force *)kzalloc(size, GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-void free_percpu(void __percpu *p)
-{
-	kfree(this_cpu_ptr(p));
-}
-EXPORT_SYMBOL_GPL(free_percpu);
-
-phys_addr_t per_cpu_ptr_to_phys(void *addr)
-{
-	return __pa(addr);
-}
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index aa33fd6..29d6cbf 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -220,18 +220,7 @@
 
 	if (vmemmap_buf_start) {
 		/* need to free left buf */
-#ifdef CONFIG_NO_BOOTMEM
-		free_early(__pa(vmemmap_buf_start), __pa(vmemmap_buf_end));
-		if (vmemmap_buf_start < vmemmap_buf) {
-			char name[15];
-
-			snprintf(name, sizeof(name), "MEMMAP %d", nodeid);
-			reserve_early_without_check(__pa(vmemmap_buf_start),
-						    __pa(vmemmap_buf), name);
-		}
-#else
 		free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf);
-#endif
 		vmemmap_buf = NULL;
 		vmemmap_buf_end = NULL;
 	}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 7c703ff..9fc7bac 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -139,7 +139,7 @@
 	nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
 	if (nr_blocks) {
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT);
+				nr_blocks, GFP_KERNEL, 0);
 		if (err)
 			return err;
 		cond_resched();
@@ -150,7 +150,7 @@
 		nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
 
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT);
+				nr_blocks, GFP_KERNEL, 0);
 		if (err)
 			break;
 
@@ -189,7 +189,7 @@
 			start_block <<= PAGE_SHIFT - 9;
 			nr_blocks <<= PAGE_SHIFT - 9;
 			if (blkdev_issue_discard(si->bdev, start_block,
-				    nr_blocks, GFP_NOIO, BLKDEV_IFL_WAIT))
+				    nr_blocks, GFP_NOIO, 0))
 				break;
 		}
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6b8889d..9f90962 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -517,6 +517,15 @@
 static void purge_fragmented_blocks_allcpus(void);
 
 /*
+ * called before a call to iounmap() if the caller wants vm_area_struct's
+ * immediately freed.
+ */
+void set_iounmap_nonlazy(void)
+{
+	atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
+}
+
+/*
  * Purges all lazily-freed vmap areas.
  *
  * If sync is 0 then don't purge if there is already a purge in progress.
@@ -2056,6 +2065,7 @@
 }
 EXPORT_SYMBOL_GPL(free_vm_area);
 
+#ifdef CONFIG_SMP
 static struct vmap_area *node_to_va(struct rb_node *n)
 {
 	return n ? rb_entry(n, struct vmap_area, rb_node) : NULL;
@@ -2336,6 +2346,7 @@
 		free_vm_area(vms[i]);
 	kfree(vms);
 }
+#endif	/* CONFIG_SMP */
 
 #ifdef CONFIG_PROC_FS
 static void *s_start(struct seq_file *m, loff_t *pos)
diff --git a/net/Kconfig b/net/Kconfig
index e926884..55fd82e 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -293,6 +293,7 @@
 source "net/rfkill/Kconfig"
 source "net/9p/Kconfig"
 source "net/caif/Kconfig"
+source "net/ceph/Kconfig"
 
 
 endif   # if NET
diff --git a/net/Makefile b/net/Makefile
index ea60fbc..6b7bfd7 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -68,3 +68,4 @@
 endif
 obj-$(CONFIG_WIMAX)		+= wimax/
 obj-$(CONFIG_DNS_RESOLVER)	+= dns_resolver/
+obj-$(CONFIG_CEPH_LIB)		+= ceph/
diff --git a/net/atm/proc.c b/net/atm/proc.c
index 6262aea..f85da077 100644
--- a/net/atm/proc.c
+++ b/net/atm/proc.c
@@ -38,6 +38,7 @@
 static const struct file_operations proc_atm_dev_ops = {
 	.owner =	THIS_MODULE,
 	.read =		proc_dev_atm_read,
+	.llseek =	noop_llseek,
 };
 
 static void add_stats(struct seq_file *seq, const char *aal,
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
new file mode 100644
index 0000000..ad42404
--- /dev/null
+++ b/net/ceph/Kconfig
@@ -0,0 +1,28 @@
+config CEPH_LIB
+        tristate "Ceph core library (EXPERIMENTAL)"
+	depends on INET && EXPERIMENTAL
+	select LIBCRC32C
+	select CRYPTO_AES
+	select CRYPTO
+	default n
+	help
+	  Choose Y or M here to include cephlib, which provides the
+	  common functionality to both the Ceph filesystem and
+	  to the rados block device (rbd).
+
+	  More information at http://ceph.newdream.net/.
+
+	  If unsure, say N.
+
+config CEPH_LIB_PRETTYDEBUG
+	bool "Include file:line in ceph debug output"
+	depends on CEPH_LIB
+	default n
+	help
+	  If you say Y here, debug output will include a filename and
+	  line to aid debugging.  This increases kernel size and slows
+	  execution slightly when debug call sites are enabled (e.g.,
+	  via CONFIG_DYNAMIC_DEBUG).
+
+	  If unsure, say N.
+
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
new file mode 100644
index 0000000..aab1cab
--- /dev/null
+++ b/net/ceph/Makefile
@@ -0,0 +1,37 @@
+#
+# Makefile for CEPH filesystem.
+#
+
+ifneq ($(KERNELRELEASE),)
+
+obj-$(CONFIG_CEPH_LIB) += libceph.o
+
+libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
+	mon_client.o \
+	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
+	debugfs.o \
+	auth.o auth_none.o \
+	crypto.o armor.o \
+	auth_x.o \
+	ceph_fs.o ceph_strings.o ceph_hash.o \
+	pagevec.o
+
+else
+#Otherwise we were called directly from the command
+# line; invoke the kernel build system.
+
+KERNELDIR ?= /lib/modules/$(shell uname -r)/build
+PWD := $(shell pwd)
+
+default: all
+
+all:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules
+
+modules_install:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules_install
+
+clean:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) clean
+
+endif
diff --git a/fs/ceph/armor.c b/net/ceph/armor.c
similarity index 100%
rename from fs/ceph/armor.c
rename to net/ceph/armor.c
diff --git a/fs/ceph/auth.c b/net/ceph/auth.c
similarity index 96%
rename from fs/ceph/auth.c
rename to net/ceph/auth.c
index 6d2e306..549c1f4 100644
--- a/fs/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -1,16 +1,16 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include "types.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
 #include "auth_none.h"
 #include "auth_x.h"
-#include "decode.h"
-#include "super.h"
 
-#include "messenger.h"
 
 /*
  * get protocol handler
diff --git a/fs/ceph/auth_none.c b/net/ceph/auth_none.c
similarity index 96%
rename from fs/ceph/auth_none.c
rename to net/ceph/auth_none.c
index ad1dc21..214c2bb 100644
--- a/fs/ceph/auth_none.c
+++ b/net/ceph/auth_none.c
@@ -1,14 +1,15 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+
 #include "auth_none.h"
-#include "auth.h"
-#include "decode.h"
 
 static void reset(struct ceph_auth_client *ac)
 {
diff --git a/fs/ceph/auth_none.h b/net/ceph/auth_none.h
similarity index 94%
rename from fs/ceph/auth_none.h
rename to net/ceph/auth_none.h
index 8164df1..ed7d088 100644
--- a/fs/ceph/auth_none.h
+++ b/net/ceph/auth_none.h
@@ -2,8 +2,7 @@
 #define _FS_CEPH_AUTH_NONE_H
 
 #include <linux/slab.h>
-
-#include "auth.h"
+#include <linux/ceph/auth.h>
 
 /*
  * null security mode.
diff --git a/fs/ceph/auth_x.c b/net/ceph/auth_x.c
similarity index 99%
rename from fs/ceph/auth_x.c
rename to net/ceph/auth_x.c
index a2d002c..7fd5dfc 100644
--- a/fs/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -1,16 +1,17 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+
+#include "crypto.h"
 #include "auth_x.h"
 #include "auth_x_protocol.h"
-#include "crypto.h"
-#include "auth.h"
-#include "decode.h"
 
 #define TEMP_TICKET_BUF_LEN	256
 
diff --git a/fs/ceph/auth_x.h b/net/ceph/auth_x.h
similarity index 96%
rename from fs/ceph/auth_x.h
rename to net/ceph/auth_x.h
index ff6f818..e02da7a 100644
--- a/fs/ceph/auth_x.h
+++ b/net/ceph/auth_x.h
@@ -3,8 +3,9 @@
 
 #include <linux/rbtree.h>
 
+#include <linux/ceph/auth.h>
+
 #include "crypto.h"
-#include "auth.h"
 #include "auth_x_protocol.h"
 
 /*
diff --git a/fs/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h
similarity index 100%
rename from fs/ceph/auth_x_protocol.h
rename to net/ceph/auth_x_protocol.h
diff --git a/fs/ceph/buffer.c b/net/ceph/buffer.c
similarity index 85%
rename from fs/ceph/buffer.c
rename to net/ceph/buffer.c
index cd39f17..53d8abf 100644
--- a/fs/ceph/buffer.c
+++ b/net/ceph/buffer.c
@@ -1,10 +1,11 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/slab.h>
 
-#include "buffer.h"
-#include "decode.h"
+#include <linux/ceph/buffer.h>
+#include <linux/ceph/decode.h>
 
 struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 {
@@ -32,6 +33,7 @@
 	dout("buffer_new %p\n", b);
 	return b;
 }
+EXPORT_SYMBOL(ceph_buffer_new);
 
 void ceph_buffer_release(struct kref *kref)
 {
@@ -46,6 +48,7 @@
 	}
 	kfree(b);
 }
+EXPORT_SYMBOL(ceph_buffer_release);
 
 int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end)
 {
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
new file mode 100644
index 0000000..f3e4a13
--- /dev/null
+++ b/net/ceph/ceph_common.c
@@ -0,0 +1,529 @@
+
+#include <linux/ceph/ceph_debug.h>
+#include <linux/backing-dev.h>
+#include <linux/ctype.h>
+#include <linux/fs.h>
+#include <linux/inet.h>
+#include <linux/in6.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/parser.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/statfs.h>
+#include <linux/string.h>
+
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/debugfs.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+
+
+
+/*
+ * find filename portion of a path (/foo/bar/baz -> baz)
+ */
+const char *ceph_file_part(const char *s, int len)
+{
+	const char *e = s + len;
+
+	while (e != s && *(e-1) != '/')
+		e--;
+	return e;
+}
+EXPORT_SYMBOL(ceph_file_part);
+
+const char *ceph_msg_type_name(int type)
+{
+	switch (type) {
+	case CEPH_MSG_SHUTDOWN: return "shutdown";
+	case CEPH_MSG_PING: return "ping";
+	case CEPH_MSG_AUTH: return "auth";
+	case CEPH_MSG_AUTH_REPLY: return "auth_reply";
+	case CEPH_MSG_MON_MAP: return "mon_map";
+	case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
+	case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
+	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
+	case CEPH_MSG_STATFS: return "statfs";
+	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+	case CEPH_MSG_MDS_MAP: return "mds_map";
+	case CEPH_MSG_CLIENT_SESSION: return "client_session";
+	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
+	case CEPH_MSG_CLIENT_REQUEST: return "client_request";
+	case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
+	case CEPH_MSG_CLIENT_REPLY: return "client_reply";
+	case CEPH_MSG_CLIENT_CAPS: return "client_caps";
+	case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
+	case CEPH_MSG_CLIENT_SNAP: return "client_snap";
+	case CEPH_MSG_CLIENT_LEASE: return "client_lease";
+	case CEPH_MSG_OSD_MAP: return "osd_map";
+	case CEPH_MSG_OSD_OP: return "osd_op";
+	case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
+	default: return "unknown";
+	}
+}
+EXPORT_SYMBOL(ceph_msg_type_name);
+
+/*
+ * Initially learn our fsid, or verify an fsid matches.
+ */
+int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
+{
+	if (client->have_fsid) {
+		if (ceph_fsid_compare(&client->fsid, fsid)) {
+			pr_err("bad fsid, had %pU got %pU",
+			       &client->fsid, fsid);
+			return -1;
+		}
+	} else {
+		pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid);
+		memcpy(&client->fsid, fsid, sizeof(*fsid));
+		ceph_debugfs_client_init(client);
+		client->have_fsid = true;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_check_fsid);
+
+static int strcmp_null(const char *s1, const char *s2)
+{
+	if (!s1 && !s2)
+		return 0;
+	if (s1 && !s2)
+		return -1;
+	if (!s1 && s2)
+		return 1;
+	return strcmp(s1, s2);
+}
+
+int ceph_compare_options(struct ceph_options *new_opt,
+			 struct ceph_client *client)
+{
+	struct ceph_options *opt1 = new_opt;
+	struct ceph_options *opt2 = client->options;
+	int ofs = offsetof(struct ceph_options, mon_addr);
+	int i;
+	int ret;
+
+	ret = memcmp(opt1, opt2, ofs);
+	if (ret)
+		return ret;
+
+	ret = strcmp_null(opt1->name, opt2->name);
+	if (ret)
+		return ret;
+
+	ret = strcmp_null(opt1->secret, opt2->secret);
+	if (ret)
+		return ret;
+
+	/* any matching mon ip implies a match */
+	for (i = 0; i < opt1->num_mon; i++) {
+		if (ceph_monmap_contains(client->monc.monmap,
+				 &opt1->mon_addr[i]))
+			return 0;
+	}
+	return -1;
+}
+EXPORT_SYMBOL(ceph_compare_options);
+
+
+static int parse_fsid(const char *str, struct ceph_fsid *fsid)
+{
+	int i = 0;
+	char tmp[3];
+	int err = -EINVAL;
+	int d;
+
+	dout("parse_fsid '%s'\n", str);
+	tmp[2] = 0;
+	while (*str && i < 16) {
+		if (ispunct(*str)) {
+			str++;
+			continue;
+		}
+		if (!isxdigit(str[0]) || !isxdigit(str[1]))
+			break;
+		tmp[0] = str[0];
+		tmp[1] = str[1];
+		if (sscanf(tmp, "%x", &d) < 1)
+			break;
+		fsid->fsid[i] = d & 0xff;
+		i++;
+		str += 2;
+	}
+
+	if (i == 16)
+		err = 0;
+	dout("parse_fsid ret %d got fsid %pU", err, fsid);
+	return err;
+}
+
+/*
+ * ceph options
+ */
+enum {
+	Opt_osdtimeout,
+	Opt_osdkeepalivetimeout,
+	Opt_mount_timeout,
+	Opt_osd_idle_ttl,
+	Opt_last_int,
+	/* int args above */
+	Opt_fsid,
+	Opt_name,
+	Opt_secret,
+	Opt_ip,
+	Opt_last_string,
+	/* string args above */
+	Opt_noshare,
+	Opt_nocrc,
+};
+
+static match_table_t opt_tokens = {
+	{Opt_osdtimeout, "osdtimeout=%d"},
+	{Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
+	{Opt_mount_timeout, "mount_timeout=%d"},
+	{Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+	/* int args above */
+	{Opt_fsid, "fsid=%s"},
+	{Opt_name, "name=%s"},
+	{Opt_secret, "secret=%s"},
+	{Opt_ip, "ip=%s"},
+	/* string args above */
+	{Opt_noshare, "noshare"},
+	{Opt_nocrc, "nocrc"},
+	{-1, NULL}
+};
+
+void ceph_destroy_options(struct ceph_options *opt)
+{
+	dout("destroy_options %p\n", opt);
+	kfree(opt->name);
+	kfree(opt->secret);
+	kfree(opt);
+}
+EXPORT_SYMBOL(ceph_destroy_options);
+
+int ceph_parse_options(struct ceph_options **popt, char *options,
+		       const char *dev_name, const char *dev_name_end,
+		       int (*parse_extra_token)(char *c, void *private),
+		       void *private)
+{
+	struct ceph_options *opt;
+	const char *c;
+	int err = -ENOMEM;
+	substring_t argstr[MAX_OPT_ARGS];
+
+	opt = kzalloc(sizeof(*opt), GFP_KERNEL);
+	if (!opt)
+		return err;
+	opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr),
+				GFP_KERNEL);
+	if (!opt->mon_addr)
+		goto out;
+
+	dout("parse_options %p options '%s' dev_name '%s'\n", opt, options,
+	     dev_name);
+
+	/* start with defaults */
+	opt->flags = CEPH_OPT_DEFAULT;
+	opt->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
+	opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
+	opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
+	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
+
+	/* get mon ip(s) */
+	/* ip1[:port1][,ip2[:port2]...] */
+	err = ceph_parse_ips(dev_name, dev_name_end, opt->mon_addr,
+			     CEPH_MAX_MON, &opt->num_mon);
+	if (err < 0)
+		goto out;
+
+	/* parse mount options */
+	while ((c = strsep(&options, ",")) != NULL) {
+		int token, intval, ret;
+		if (!*c)
+			continue;
+		err = -EINVAL;
+		token = match_token((char *)c, opt_tokens, argstr);
+		if (token < 0 && parse_extra_token) {
+			/* extra? */
+			err = parse_extra_token((char *)c, private);
+			if (err < 0) {
+				pr_err("bad option at '%s'\n", c);
+				goto out;
+			}
+			continue;
+		}
+		if (token < Opt_last_int) {
+			ret = match_int(&argstr[0], &intval);
+			if (ret < 0) {
+				pr_err("bad mount option arg (not int) "
+				       "at '%s'\n", c);
+				continue;
+			}
+			dout("got int token %d val %d\n", token, intval);
+		} else if (token > Opt_last_int && token < Opt_last_string) {
+			dout("got string token %d val %s\n", token,
+			     argstr[0].from);
+		} else {
+			dout("got token %d\n", token);
+		}
+		switch (token) {
+		case Opt_ip:
+			err = ceph_parse_ips(argstr[0].from,
+					     argstr[0].to,
+					     &opt->my_addr,
+					     1, NULL);
+			if (err < 0)
+				goto out;
+			opt->flags |= CEPH_OPT_MYIP;
+			break;
+
+		case Opt_fsid:
+			err = parse_fsid(argstr[0].from, &opt->fsid);
+			if (err == 0)
+				opt->flags |= CEPH_OPT_FSID;
+			break;
+		case Opt_name:
+			opt->name = kstrndup(argstr[0].from,
+					      argstr[0].to-argstr[0].from,
+					      GFP_KERNEL);
+			break;
+		case Opt_secret:
+			opt->secret = kstrndup(argstr[0].from,
+						argstr[0].to-argstr[0].from,
+						GFP_KERNEL);
+			break;
+
+			/* misc */
+		case Opt_osdtimeout:
+			opt->osd_timeout = intval;
+			break;
+		case Opt_osdkeepalivetimeout:
+			opt->osd_keepalive_timeout = intval;
+			break;
+		case Opt_osd_idle_ttl:
+			opt->osd_idle_ttl = intval;
+			break;
+		case Opt_mount_timeout:
+			opt->mount_timeout = intval;
+			break;
+
+		case Opt_noshare:
+			opt->flags |= CEPH_OPT_NOSHARE;
+			break;
+
+		case Opt_nocrc:
+			opt->flags |= CEPH_OPT_NOCRC;
+			break;
+
+		default:
+			BUG_ON(token);
+		}
+	}
+
+	/* success */
+	*popt = opt;
+	return 0;
+
+out:
+	ceph_destroy_options(opt);
+	return err;
+}
+EXPORT_SYMBOL(ceph_parse_options);
+
+u64 ceph_client_id(struct ceph_client *client)
+{
+	return client->monc.auth->global_id;
+}
+EXPORT_SYMBOL(ceph_client_id);
+
+/*
+ * create a fresh client instance
+ */
+struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private)
+{
+	struct ceph_client *client;
+	int err = -ENOMEM;
+
+	client = kzalloc(sizeof(*client), GFP_KERNEL);
+	if (client == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	client->private = private;
+	client->options = opt;
+
+	mutex_init(&client->mount_mutex);
+	init_waitqueue_head(&client->auth_wq);
+	client->auth_err = 0;
+
+	client->extra_mon_dispatch = NULL;
+	client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT;
+	client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT;
+
+	client->msgr = NULL;
+
+	/* subsystems */
+	err = ceph_monc_init(&client->monc, client);
+	if (err < 0)
+		goto fail;
+	err = ceph_osdc_init(&client->osdc, client);
+	if (err < 0)
+		goto fail_monc;
+
+	return client;
+
+fail_monc:
+	ceph_monc_stop(&client->monc);
+fail:
+	kfree(client);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(ceph_create_client);
+
+void ceph_destroy_client(struct ceph_client *client)
+{
+	dout("destroy_client %p\n", client);
+
+	/* unmount */
+	ceph_osdc_stop(&client->osdc);
+
+	/*
+	 * make sure mds and osd connections close out before destroying
+	 * the auth module, which is needed to free those connections'
+	 * ceph_authorizers.
+	 */
+	ceph_msgr_flush();
+
+	ceph_monc_stop(&client->monc);
+
+	ceph_debugfs_client_cleanup(client);
+
+	if (client->msgr)
+		ceph_messenger_destroy(client->msgr);
+
+	ceph_destroy_options(client->options);
+
+	kfree(client);
+	dout("destroy_client %p done\n", client);
+}
+EXPORT_SYMBOL(ceph_destroy_client);
+
+/*
+ * true if we have the mon map (and have thus joined the cluster)
+ */
+static int have_mon_and_osd_map(struct ceph_client *client)
+{
+	return client->monc.monmap && client->monc.monmap->epoch &&
+	       client->osdc.osdmap && client->osdc.osdmap->epoch;
+}
+
+/*
+ * mount: join the ceph cluster, and open root directory.
+ */
+int __ceph_open_session(struct ceph_client *client, unsigned long started)
+{
+	struct ceph_entity_addr *myaddr = NULL;
+	int err;
+	unsigned long timeout = client->options->mount_timeout * HZ;
+
+	/* initialize the messenger */
+	if (client->msgr == NULL) {
+		if (ceph_test_opt(client, MYIP))
+			myaddr = &client->options->my_addr;
+		client->msgr = ceph_messenger_create(myaddr,
+					client->supported_features,
+					client->required_features);
+		if (IS_ERR(client->msgr)) {
+			client->msgr = NULL;
+			return PTR_ERR(client->msgr);
+		}
+		client->msgr->nocrc = ceph_test_opt(client, NOCRC);
+	}
+
+	/* open session, and wait for mon and osd maps */
+	err = ceph_monc_open_session(&client->monc);
+	if (err < 0)
+		return err;
+
+	while (!have_mon_and_osd_map(client)) {
+		err = -EIO;
+		if (timeout && time_after_eq(jiffies, started + timeout))
+			return err;
+
+		/* wait */
+		dout("mount waiting for mon_map\n");
+		err = wait_event_interruptible_timeout(client->auth_wq,
+			have_mon_and_osd_map(client) || (client->auth_err < 0),
+			timeout);
+		if (err == -EINTR || err == -ERESTARTSYS)
+			return err;
+		if (client->auth_err < 0)
+			return client->auth_err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__ceph_open_session);
+
+
+int ceph_open_session(struct ceph_client *client)
+{
+	int ret;
+	unsigned long started = jiffies;  /* note the start time */
+
+	dout("open_session start\n");
+	mutex_lock(&client->mount_mutex);
+
+	ret = __ceph_open_session(client, started);
+
+	mutex_unlock(&client->mount_mutex);
+	return ret;
+}
+EXPORT_SYMBOL(ceph_open_session);
+
+
+static int __init init_ceph_lib(void)
+{
+	int ret = 0;
+
+	ret = ceph_debugfs_init();
+	if (ret < 0)
+		goto out;
+
+	ret = ceph_msgr_init();
+	if (ret < 0)
+		goto out_debugfs;
+
+	pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n",
+		CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL,
+		CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
+		CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
+
+	return 0;
+
+out_debugfs:
+	ceph_debugfs_cleanup();
+out:
+	return ret;
+}
+
+static void __exit exit_ceph_lib(void)
+{
+	dout("exit_ceph_lib\n");
+	ceph_msgr_exit();
+	ceph_debugfs_cleanup();
+}
+
+module_init(init_ceph_lib);
+module_exit(exit_ceph_lib);
+
+MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
+MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
+MODULE_AUTHOR("Patience Warnick <patience@newdream.net>");
+MODULE_DESCRIPTION("Ceph filesystem for Linux");
+MODULE_LICENSE("GPL");
diff --git a/fs/ceph/ceph_fs.c b/net/ceph/ceph_fs.c
similarity index 92%
rename from fs/ceph/ceph_fs.c
rename to net/ceph/ceph_fs.c
index 3ac6cc7..a3a3a31 100644
--- a/fs/ceph/ceph_fs.c
+++ b/net/ceph/ceph_fs.c
@@ -1,7 +1,8 @@
 /*
  * Some non-inline ceph helpers
  */
-#include "types.h"
+#include <linux/module.h>
+#include <linux/ceph/types.h>
 
 /*
  * return true if @layout appears to be valid
@@ -52,6 +53,7 @@
 
 	return mode;
 }
+EXPORT_SYMBOL(ceph_flags_to_mode);
 
 int ceph_caps_for_mode(int mode)
 {
@@ -70,3 +72,4 @@
 
 	return caps;
 }
+EXPORT_SYMBOL(ceph_caps_for_mode);
diff --git a/fs/ceph/ceph_hash.c b/net/ceph/ceph_hash.c
similarity index 98%
rename from fs/ceph/ceph_hash.c
rename to net/ceph/ceph_hash.c
index bd57001..815ef88 100644
--- a/fs/ceph/ceph_hash.c
+++ b/net/ceph/ceph_hash.c
@@ -1,5 +1,5 @@
 
-#include "types.h"
+#include <linux/ceph/types.h>
 
 /*
  * Robert Jenkin's hash function.
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
new file mode 100644
index 0000000..3fbda04
--- /dev/null
+++ b/net/ceph/ceph_strings.c
@@ -0,0 +1,84 @@
+/*
+ * Ceph string constants
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+const char *ceph_entity_type_name(int type)
+{
+	switch (type) {
+	case CEPH_ENTITY_TYPE_MDS: return "mds";
+	case CEPH_ENTITY_TYPE_OSD: return "osd";
+	case CEPH_ENTITY_TYPE_MON: return "mon";
+	case CEPH_ENTITY_TYPE_CLIENT: return "client";
+	case CEPH_ENTITY_TYPE_AUTH: return "auth";
+	default: return "unknown";
+	}
+}
+
+const char *ceph_osd_op_name(int op)
+{
+	switch (op) {
+	case CEPH_OSD_OP_READ: return "read";
+	case CEPH_OSD_OP_STAT: return "stat";
+
+	case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
+
+	case CEPH_OSD_OP_WRITE: return "write";
+	case CEPH_OSD_OP_DELETE: return "delete";
+	case CEPH_OSD_OP_TRUNCATE: return "truncate";
+	case CEPH_OSD_OP_ZERO: return "zero";
+	case CEPH_OSD_OP_WRITEFULL: return "writefull";
+	case CEPH_OSD_OP_ROLLBACK: return "rollback";
+
+	case CEPH_OSD_OP_APPEND: return "append";
+	case CEPH_OSD_OP_STARTSYNC: return "startsync";
+	case CEPH_OSD_OP_SETTRUNC: return "settrunc";
+	case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
+
+	case CEPH_OSD_OP_TMAPUP: return "tmapup";
+	case CEPH_OSD_OP_TMAPGET: return "tmapget";
+	case CEPH_OSD_OP_TMAPPUT: return "tmapput";
+
+	case CEPH_OSD_OP_GETXATTR: return "getxattr";
+	case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
+	case CEPH_OSD_OP_SETXATTR: return "setxattr";
+	case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
+	case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
+	case CEPH_OSD_OP_RMXATTR: return "rmxattr";
+	case CEPH_OSD_OP_CMPXATTR: return "cmpxattr";
+
+	case CEPH_OSD_OP_PULL: return "pull";
+	case CEPH_OSD_OP_PUSH: return "push";
+	case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
+	case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
+	case CEPH_OSD_OP_SCRUB: return "scrub";
+
+	case CEPH_OSD_OP_WRLOCK: return "wrlock";
+	case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
+	case CEPH_OSD_OP_RDLOCK: return "rdlock";
+	case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
+	case CEPH_OSD_OP_UPLOCK: return "uplock";
+	case CEPH_OSD_OP_DNLOCK: return "dnlock";
+
+	case CEPH_OSD_OP_CALL: return "call";
+
+	case CEPH_OSD_OP_PGLS: return "pgls";
+	}
+	return "???";
+}
+
+
+const char *ceph_pool_op_name(int op)
+{
+	switch (op) {
+	case POOL_OP_CREATE: return "create";
+	case POOL_OP_DELETE: return "delete";
+	case POOL_OP_AUID_CHANGE: return "auid change";
+	case POOL_OP_CREATE_SNAP: return "create snap";
+	case POOL_OP_DELETE_SNAP: return "delete snap";
+	case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
+	case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
+	}
+	return "???";
+}
diff --git a/fs/ceph/crush/crush.c b/net/ceph/crush/crush.c
similarity index 98%
rename from fs/ceph/crush/crush.c
rename to net/ceph/crush/crush.c
index fabd302..d6ebb13 100644
--- a/fs/ceph/crush/crush.c
+++ b/net/ceph/crush/crush.c
@@ -8,7 +8,7 @@
 # define BUG_ON(x) assert(!(x))
 #endif
 
-#include "crush.h"
+#include <linux/crush/crush.h>
 
 const char *crush_bucket_alg_name(int alg)
 {
diff --git a/fs/ceph/crush/hash.c b/net/ceph/crush/hash.c
similarity index 98%
rename from fs/ceph/crush/hash.c
rename to net/ceph/crush/hash.c
index 5873aed..5bb63e3 100644
--- a/fs/ceph/crush/hash.c
+++ b/net/ceph/crush/hash.c
@@ -1,6 +1,6 @@
 
 #include <linux/types.h>
-#include "hash.h"
+#include <linux/crush/hash.h>
 
 /*
  * Robert Jenkins' function for mixing 32-bit values
diff --git a/fs/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
similarity index 99%
rename from fs/ceph/crush/mapper.c
rename to net/ceph/crush/mapper.c
index a4eec13..42599e3 100644
--- a/fs/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -18,8 +18,8 @@
 # define kfree(x) free(x)
 #endif
 
-#include "crush.h"
-#include "hash.h"
+#include <linux/crush/crush.h>
+#include <linux/crush/hash.h>
 
 /*
  * Implement the core CRUSH mapping algorithm.
diff --git a/fs/ceph/crypto.c b/net/ceph/crypto.c
similarity index 99%
rename from fs/ceph/crypto.c
rename to net/ceph/crypto.c
index a3e627f..7b505b0 100644
--- a/fs/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -1,13 +1,13 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <crypto/hash.h>
 
+#include <linux/ceph/decode.h>
 #include "crypto.h"
-#include "decode.h"
 
 int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end)
 {
diff --git a/fs/ceph/crypto.h b/net/ceph/crypto.h
similarity index 95%
rename from fs/ceph/crypto.h
rename to net/ceph/crypto.h
index bdf3860..f9eccac 100644
--- a/fs/ceph/crypto.h
+++ b/net/ceph/crypto.h
@@ -1,8 +1,8 @@
 #ifndef _FS_CEPH_CRYPTO_H
 #define _FS_CEPH_CRYPTO_H
 
-#include "types.h"
-#include "buffer.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/buffer.h>
 
 /*
  * cryptographic secret
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
new file mode 100644
index 0000000..27d4ea31
--- /dev/null
+++ b/net/ceph/debugfs.c
@@ -0,0 +1,267 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+
+#ifdef CONFIG_DEBUG_FS
+
+/*
+ * Implement /sys/kernel/debug/ceph fun
+ *
+ * /sys/kernel/debug/ceph/client*  - an instance of the ceph client
+ *      .../osdmap      - current osdmap
+ *      .../monmap      - current monmap
+ *      .../osdc        - active osd requests
+ *      .../monc        - mon client state
+ *      .../dentry_lru  - dump contents of dentry lru
+ *      .../caps        - expose cap (reservation) stats
+ *      .../bdi         - symlink to ../../bdi/something
+ */
+
+static struct dentry *ceph_debugfs_dir;
+
+static int monmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_client *client = s->private;
+
+	if (client->monc.monmap == NULL)
+		return 0;
+
+	seq_printf(s, "epoch %d\n", client->monc.monmap->epoch);
+	for (i = 0; i < client->monc.monmap->num_mon; i++) {
+		struct ceph_entity_inst *inst =
+			&client->monc.monmap->mon_inst[i];
+
+		seq_printf(s, "\t%s%lld\t%s\n",
+			   ENTITY_NAME(inst->name),
+			   ceph_pr_addr(&inst->addr.in_addr));
+	}
+	return 0;
+}
+
+static int osdmap_show(struct seq_file *s, void *p)
+{
+	int i;
+	struct ceph_client *client = s->private;
+	struct rb_node *n;
+
+	if (client->osdc.osdmap == NULL)
+		return 0;
+	seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
+	seq_printf(s, "flags%s%s\n",
+		   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
+		   " NEARFULL" : "",
+		   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
+		   " FULL" : "");
+	for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
+		struct ceph_pg_pool_info *pool =
+			rb_entry(n, struct ceph_pg_pool_info, node);
+		seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n",
+			   pool->id, pool->v.pg_num, pool->pg_num_mask,
+			   pool->v.lpg_num, pool->lpg_num_mask);
+	}
+	for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
+		struct ceph_entity_addr *addr =
+			&client->osdc.osdmap->osd_addr[i];
+		int state = client->osdc.osdmap->osd_state[i];
+		char sb[64];
+
+		seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
+			   i, ceph_pr_addr(&addr->in_addr),
+			   ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
+			   ceph_osdmap_state_str(sb, sizeof(sb), state));
+	}
+	return 0;
+}
+
+static int monc_show(struct seq_file *s, void *p)
+{
+	struct ceph_client *client = s->private;
+	struct ceph_mon_generic_request *req;
+	struct ceph_mon_client *monc = &client->monc;
+	struct rb_node *rp;
+
+	mutex_lock(&monc->mutex);
+
+	if (monc->have_mdsmap)
+		seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap);
+	if (monc->have_osdmap)
+		seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap);
+	if (monc->want_next_osdmap)
+		seq_printf(s, "want next osdmap\n");
+
+	for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) {
+		__u16 op;
+		req = rb_entry(rp, struct ceph_mon_generic_request, node);
+		op = le16_to_cpu(req->request->hdr.type);
+		if (op == CEPH_MSG_STATFS)
+			seq_printf(s, "%lld statfs\n", req->tid);
+		else
+			seq_printf(s, "%lld unknown\n", req->tid);
+	}
+
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
+static int osdc_show(struct seq_file *s, void *pp)
+{
+	struct ceph_client *client = s->private;
+	struct ceph_osd_client *osdc = &client->osdc;
+	struct rb_node *p;
+
+	mutex_lock(&osdc->request_mutex);
+	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+		struct ceph_osd_request *req;
+		struct ceph_osd_request_head *head;
+		struct ceph_osd_op *op;
+		int num_ops;
+		int opcode, olen;
+		int i;
+
+		req = rb_entry(p, struct ceph_osd_request, r_node);
+
+		seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid,
+			   req->r_osd ? req->r_osd->o_osd : -1,
+			   le32_to_cpu(req->r_pgid.pool),
+			   le16_to_cpu(req->r_pgid.ps));
+
+		head = req->r_request->front.iov_base;
+		op = (void *)(head + 1);
+
+		num_ops = le16_to_cpu(head->num_ops);
+		olen = le32_to_cpu(head->object_len);
+		seq_printf(s, "%.*s", olen,
+			   (const char *)(head->ops + num_ops));
+
+		if (req->r_reassert_version.epoch)
+			seq_printf(s, "\t%u'%llu",
+			   (unsigned)le32_to_cpu(req->r_reassert_version.epoch),
+			   le64_to_cpu(req->r_reassert_version.version));
+		else
+			seq_printf(s, "\t");
+
+		for (i = 0; i < num_ops; i++) {
+			opcode = le16_to_cpu(op->op);
+			seq_printf(s, "\t%s", ceph_osd_op_name(opcode));
+			op++;
+		}
+
+		seq_printf(s, "\n");
+	}
+	mutex_unlock(&osdc->request_mutex);
+	return 0;
+}
+
+CEPH_DEFINE_SHOW_FUNC(monmap_show)
+CEPH_DEFINE_SHOW_FUNC(osdmap_show)
+CEPH_DEFINE_SHOW_FUNC(monc_show)
+CEPH_DEFINE_SHOW_FUNC(osdc_show)
+
+int ceph_debugfs_init(void)
+{
+	ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
+	if (!ceph_debugfs_dir)
+		return -ENOMEM;
+	return 0;
+}
+
+void ceph_debugfs_cleanup(void)
+{
+	debugfs_remove(ceph_debugfs_dir);
+}
+
+int ceph_debugfs_client_init(struct ceph_client *client)
+{
+	int ret = -ENOMEM;
+	char name[80];
+
+	snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
+		 client->monc.auth->global_id);
+
+	client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
+	if (!client->debugfs_dir)
+		goto out;
+
+	client->monc.debugfs_file = debugfs_create_file("monc",
+						      0600,
+						      client->debugfs_dir,
+						      client,
+						      &monc_show_fops);
+	if (!client->monc.debugfs_file)
+		goto out;
+
+	client->osdc.debugfs_file = debugfs_create_file("osdc",
+						      0600,
+						      client->debugfs_dir,
+						      client,
+						      &osdc_show_fops);
+	if (!client->osdc.debugfs_file)
+		goto out;
+
+	client->debugfs_monmap = debugfs_create_file("monmap",
+					0600,
+					client->debugfs_dir,
+					client,
+					&monmap_show_fops);
+	if (!client->debugfs_monmap)
+		goto out;
+
+	client->debugfs_osdmap = debugfs_create_file("osdmap",
+					0600,
+					client->debugfs_dir,
+					client,
+					&osdmap_show_fops);
+	if (!client->debugfs_osdmap)
+		goto out;
+
+	return 0;
+
+out:
+	ceph_debugfs_client_cleanup(client);
+	return ret;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+	debugfs_remove(client->debugfs_osdmap);
+	debugfs_remove(client->debugfs_monmap);
+	debugfs_remove(client->osdc.debugfs_file);
+	debugfs_remove(client->monc.debugfs_file);
+	debugfs_remove(client->debugfs_dir);
+}
+
+#else  /* CONFIG_DEBUG_FS */
+
+int ceph_debugfs_init(void)
+{
+	return 0;
+}
+
+void ceph_debugfs_cleanup(void)
+{
+}
+
+int ceph_debugfs_client_init(struct ceph_client *client)
+{
+	return 0;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+}
+
+#endif  /* CONFIG_DEBUG_FS */
+
+EXPORT_SYMBOL(ceph_debugfs_init);
+EXPORT_SYMBOL(ceph_debugfs_cleanup);
diff --git a/fs/ceph/messenger.c b/net/ceph/messenger.c
similarity index 89%
rename from fs/ceph/messenger.c
rename to net/ceph/messenger.c
index 2502d76..0e8157e 100644
--- a/fs/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/crc32c.h>
 #include <linux/ctype.h>
@@ -9,12 +9,14 @@
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
 #include <net/tcp.h>
 
-#include "super.h"
-#include "messenger.h"
-#include "decode.h"
-#include "pagelist.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/pagelist.h>
 
 /*
  * Ceph uses the messenger to exchange ceph_msg messages with other
@@ -48,7 +50,7 @@
 static DEFINE_SPINLOCK(addr_str_lock);
 static int last_addr_str;
 
-const char *pr_addr(const struct sockaddr_storage *ss)
+const char *ceph_pr_addr(const struct sockaddr_storage *ss)
 {
 	int i;
 	char *s;
@@ -79,6 +81,7 @@
 
 	return s;
 }
+EXPORT_SYMBOL(ceph_pr_addr);
 
 static void encode_my_addr(struct ceph_messenger *msgr)
 {
@@ -91,7 +94,7 @@
  */
 struct workqueue_struct *ceph_msgr_wq;
 
-int __init ceph_msgr_init(void)
+int ceph_msgr_init(void)
 {
 	ceph_msgr_wq = create_workqueue("ceph-msgr");
 	if (IS_ERR(ceph_msgr_wq)) {
@@ -102,16 +105,19 @@
 	}
 	return 0;
 }
+EXPORT_SYMBOL(ceph_msgr_init);
 
 void ceph_msgr_exit(void)
 {
 	destroy_workqueue(ceph_msgr_wq);
 }
+EXPORT_SYMBOL(ceph_msgr_exit);
 
 void ceph_msgr_flush(void)
 {
 	flush_workqueue(ceph_msgr_wq);
 }
+EXPORT_SYMBOL(ceph_msgr_flush);
 
 
 /*
@@ -221,19 +227,19 @@
 
 	set_sock_callbacks(sock, con);
 
-	dout("connect %s\n", pr_addr(&con->peer_addr.in_addr));
+	dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
 
 	ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
 				 O_NONBLOCK);
 	if (ret == -EINPROGRESS) {
 		dout("connect %s EINPROGRESS sk_state = %u\n",
-		     pr_addr(&con->peer_addr.in_addr),
+		     ceph_pr_addr(&con->peer_addr.in_addr),
 		     sock->sk->sk_state);
 		ret = 0;
 	}
 	if (ret < 0) {
 		pr_err("connect %s error %d\n",
-		       pr_addr(&con->peer_addr.in_addr), ret);
+		       ceph_pr_addr(&con->peer_addr.in_addr), ret);
 		sock_release(sock);
 		con->sock = NULL;
 		con->error_msg = "connect error";
@@ -334,7 +340,8 @@
  */
 void ceph_con_close(struct ceph_connection *con)
 {
-	dout("con_close %p peer %s\n", con, pr_addr(&con->peer_addr.in_addr));
+	dout("con_close %p peer %s\n", con,
+	     ceph_pr_addr(&con->peer_addr.in_addr));
 	set_bit(CLOSED, &con->state);  /* in case there's queued work */
 	clear_bit(STANDBY, &con->state);  /* avoid connect_seq bump */
 	clear_bit(LOSSYTX, &con->state);  /* so we retry next connect */
@@ -347,19 +354,21 @@
 	mutex_unlock(&con->mutex);
 	queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_close);
 
 /*
  * Reopen a closed connection, with a new peer address.
  */
 void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
 {
-	dout("con_open %p %s\n", con, pr_addr(&addr->in_addr));
+	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
 	set_bit(OPENING, &con->state);
 	clear_bit(CLOSED, &con->state);
 	memcpy(&con->peer_addr, addr, sizeof(*addr));
 	con->delay = 0;      /* reset backoff memory */
 	queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_open);
 
 /*
  * return true if this connection ever successfully opened
@@ -406,6 +415,7 @@
 	INIT_LIST_HEAD(&con->out_sent);
 	INIT_DELAYED_WORK(&con->work, con_work);
 }
+EXPORT_SYMBOL(ceph_con_init);
 
 
 /*
@@ -529,8 +539,11 @@
 	if (le32_to_cpu(m->hdr.data_len) > 0) {
 		/* initialize page iterator */
 		con->out_msg_pos.page = 0;
-		con->out_msg_pos.page_pos =
-			le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+		if (m->pages)
+			con->out_msg_pos.page_pos =
+				le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+		else
+			con->out_msg_pos.page_pos = 0;
 		con->out_msg_pos.data_pos = 0;
 		con->out_msg_pos.did_page_crc = 0;
 		con->out_more = 1;  /* data + footer will follow */
@@ -647,7 +660,7 @@
 	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
 	     con->connect_seq, global_seq, proto);
 
-	con->out_connect.features = cpu_to_le64(CEPH_FEATURE_SUPPORTED);
+	con->out_connect.features = cpu_to_le64(msgr->supported_features);
 	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
 	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
 	con->out_connect.global_seq = cpu_to_le32(global_seq);
@@ -712,6 +725,31 @@
 	return ret;  /* done! */
 }
 
+#ifdef CONFIG_BLOCK
+static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
+{
+	if (!bio) {
+		*iter = NULL;
+		*seg = 0;
+		return;
+	}
+	*iter = bio;
+	*seg = bio->bi_idx;
+}
+
+static void iter_bio_next(struct bio **bio_iter, int *seg)
+{
+	if (*bio_iter == NULL)
+		return;
+
+	BUG_ON(*seg >= (*bio_iter)->bi_vcnt);
+
+	(*seg)++;
+	if (*seg == (*bio_iter)->bi_vcnt)
+		init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
+}
+#endif
+
 /*
  * Write as much message data payload as we can.  If we finish, queue
  * up the footer.
@@ -726,21 +764,46 @@
 	size_t len;
 	int crc = con->msgr->nocrc;
 	int ret;
+	int total_max_write;
+	int in_trail = 0;
+	size_t trail_len = (msg->trail ? msg->trail->length : 0);
 
 	dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n",
 	     con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages,
 	     con->out_msg_pos.page_pos);
 
-	while (con->out_msg_pos.page < con->out_msg->nr_pages) {
+#ifdef CONFIG_BLOCK
+	if (msg->bio && !msg->bio_iter)
+		init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
+#endif
+
+	while (data_len > con->out_msg_pos.data_pos) {
 		struct page *page = NULL;
 		void *kaddr = NULL;
+		int max_write = PAGE_SIZE;
+		int page_shift = 0;
+
+		total_max_write = data_len - trail_len -
+			con->out_msg_pos.data_pos;
 
 		/*
 		 * if we are calculating the data crc (the default), we need
 		 * to map the page.  if our pages[] has been revoked, use the
 		 * zero page.
 		 */
-		if (msg->pages) {
+
+		/* have we reached the trail part of the data? */
+		if (con->out_msg_pos.data_pos >= data_len - trail_len) {
+			in_trail = 1;
+
+			total_max_write = data_len - con->out_msg_pos.data_pos;
+
+			page = list_first_entry(&msg->trail->head,
+						struct page, lru);
+			if (crc)
+				kaddr = kmap(page);
+			max_write = PAGE_SIZE;
+		} else if (msg->pages) {
 			page = msg->pages[con->out_msg_pos.page];
 			if (crc)
 				kaddr = kmap(page);
@@ -749,13 +812,25 @@
 						struct page, lru);
 			if (crc)
 				kaddr = kmap(page);
+#ifdef CONFIG_BLOCK
+		} else if (msg->bio) {
+			struct bio_vec *bv;
+
+			bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg);
+			page = bv->bv_page;
+			page_shift = bv->bv_offset;
+			if (crc)
+				kaddr = kmap(page) + page_shift;
+			max_write = bv->bv_len;
+#endif
 		} else {
 			page = con->msgr->zero_page;
 			if (crc)
 				kaddr = page_address(con->msgr->zero_page);
 		}
-		len = min((int)(PAGE_SIZE - con->out_msg_pos.page_pos),
-			  (int)(data_len - con->out_msg_pos.data_pos));
+		len = min_t(int, max_write - con->out_msg_pos.page_pos,
+			    total_max_write);
+
 		if (crc && !con->out_msg_pos.did_page_crc) {
 			void *base = kaddr + con->out_msg_pos.page_pos;
 			u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
@@ -765,13 +840,14 @@
 				cpu_to_le32(crc32c(tmpcrc, base, len));
 			con->out_msg_pos.did_page_crc = 1;
 		}
-
 		ret = kernel_sendpage(con->sock, page,
-				      con->out_msg_pos.page_pos, len,
+				      con->out_msg_pos.page_pos + page_shift,
+				      len,
 				      MSG_DONTWAIT | MSG_NOSIGNAL |
 				      MSG_MORE);
 
-		if (crc && (msg->pages || msg->pagelist))
+		if (crc &&
+		    (msg->pages || msg->pagelist || msg->bio || in_trail))
 			kunmap(page);
 
 		if (ret <= 0)
@@ -783,9 +859,16 @@
 			con->out_msg_pos.page_pos = 0;
 			con->out_msg_pos.page++;
 			con->out_msg_pos.did_page_crc = 0;
-			if (msg->pagelist)
+			if (in_trail)
+				list_move_tail(&page->lru,
+					       &msg->trail->head);
+			else if (msg->pagelist)
 				list_move_tail(&page->lru,
 					       &msg->pagelist->head);
+#ifdef CONFIG_BLOCK
+			else if (msg->bio)
+				iter_bio_next(&msg->bio_iter, &msg->bio_seg);
+#endif
 		}
 	}
 
@@ -938,7 +1021,7 @@
 {
 	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
 		pr_err("connect to %s got bad banner\n",
-		       pr_addr(&con->peer_addr.in_addr));
+		       ceph_pr_addr(&con->peer_addr.in_addr));
 		con->error_msg = "protocol error, bad banner";
 		return -1;
 	}
@@ -1041,7 +1124,7 @@
 
 		addr_set_port(ss, port);
 
-		dout("parse_ips got %s\n", pr_addr(ss));
+		dout("parse_ips got %s\n", ceph_pr_addr(ss));
 
 		if (p == end)
 			break;
@@ -1061,6 +1144,7 @@
 	pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c);
 	return -EINVAL;
 }
+EXPORT_SYMBOL(ceph_parse_ips);
 
 static int process_banner(struct ceph_connection *con)
 {
@@ -1082,9 +1166,9 @@
 	    !(addr_is_blank(&con->actual_peer_addr.in_addr) &&
 	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
 		pr_warning("wrong peer, want %s/%d, got %s/%d\n",
-			   pr_addr(&con->peer_addr.in_addr),
+			   ceph_pr_addr(&con->peer_addr.in_addr),
 			   (int)le32_to_cpu(con->peer_addr.nonce),
-			   pr_addr(&con->actual_peer_addr.in_addr),
+			   ceph_pr_addr(&con->actual_peer_addr.in_addr),
 			   (int)le32_to_cpu(con->actual_peer_addr.nonce));
 		con->error_msg = "wrong peer at address";
 		return -1;
@@ -1102,7 +1186,7 @@
 		addr_set_port(&con->msgr->inst.addr.in_addr, port);
 		encode_my_addr(con->msgr);
 		dout("process_banner learned my addr is %s\n",
-		     pr_addr(&con->msgr->inst.addr.in_addr));
+		     ceph_pr_addr(&con->msgr->inst.addr.in_addr));
 	}
 
 	set_bit(NEGOTIATING, &con->state);
@@ -1123,8 +1207,8 @@
 
 static int process_connect(struct ceph_connection *con)
 {
-	u64 sup_feat = CEPH_FEATURE_SUPPORTED;
-	u64 req_feat = CEPH_FEATURE_REQUIRED;
+	u64 sup_feat = con->msgr->supported_features;
+	u64 req_feat = con->msgr->required_features;
 	u64 server_feat = le64_to_cpu(con->in_reply.features);
 
 	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
@@ -1134,7 +1218,7 @@
 		pr_err("%s%lld %s feature set mismatch,"
 		       " my %llx < server's %llx, missing %llx\n",
 		       ENTITY_NAME(con->peer_name),
-		       pr_addr(&con->peer_addr.in_addr),
+		       ceph_pr_addr(&con->peer_addr.in_addr),
 		       sup_feat, server_feat, server_feat & ~sup_feat);
 		con->error_msg = "missing required protocol features";
 		fail_protocol(con);
@@ -1144,7 +1228,7 @@
 		pr_err("%s%lld %s protocol version mismatch,"
 		       " my %d != server's %d\n",
 		       ENTITY_NAME(con->peer_name),
-		       pr_addr(&con->peer_addr.in_addr),
+		       ceph_pr_addr(&con->peer_addr.in_addr),
 		       le32_to_cpu(con->out_connect.protocol_version),
 		       le32_to_cpu(con->in_reply.protocol_version));
 		con->error_msg = "protocol version mismatch";
@@ -1178,7 +1262,7 @@
 		     le32_to_cpu(con->in_connect.connect_seq));
 		pr_err("%s%lld %s connection reset\n",
 		       ENTITY_NAME(con->peer_name),
-		       pr_addr(&con->peer_addr.in_addr));
+		       ceph_pr_addr(&con->peer_addr.in_addr));
 		reset_connection(con);
 		prepare_write_connect(con->msgr, con, 0);
 		prepare_read_connect(con);
@@ -1223,7 +1307,7 @@
 			pr_err("%s%lld %s protocol feature mismatch,"
 			       " my required %llx > server's %llx, need %llx\n",
 			       ENTITY_NAME(con->peer_name),
-			       pr_addr(&con->peer_addr.in_addr),
+			       ceph_pr_addr(&con->peer_addr.in_addr),
 			       req_feat, server_feat, req_feat & ~server_feat);
 			con->error_msg = "missing required protocol features";
 			fail_protocol(con);
@@ -1305,8 +1389,7 @@
 					struct kvec *section,
 					unsigned int sec_len, u32 *crc)
 {
-	int left;
-	int ret;
+	int ret, left;
 
 	BUG_ON(!section);
 
@@ -1329,13 +1412,83 @@
 static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
 				struct ceph_msg_header *hdr,
 				int *skip);
+
+
+static int read_partial_message_pages(struct ceph_connection *con,
+				      struct page **pages,
+				      unsigned data_len, int datacrc)
+{
+	void *p;
+	int ret;
+	int left;
+
+	left = min((int)(data_len - con->in_msg_pos.data_pos),
+		   (int)(PAGE_SIZE - con->in_msg_pos.page_pos));
+	/* (page) data */
+	BUG_ON(pages == NULL);
+	p = kmap(pages[con->in_msg_pos.page]);
+	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
+			       left);
+	if (ret > 0 && datacrc)
+		con->in_data_crc =
+			crc32c(con->in_data_crc,
+				  p + con->in_msg_pos.page_pos, ret);
+	kunmap(pages[con->in_msg_pos.page]);
+	if (ret <= 0)
+		return ret;
+	con->in_msg_pos.data_pos += ret;
+	con->in_msg_pos.page_pos += ret;
+	if (con->in_msg_pos.page_pos == PAGE_SIZE) {
+		con->in_msg_pos.page_pos = 0;
+		con->in_msg_pos.page++;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_BLOCK
+static int read_partial_message_bio(struct ceph_connection *con,
+				    struct bio **bio_iter, int *bio_seg,
+				    unsigned data_len, int datacrc)
+{
+	struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg);
+	void *p;
+	int ret, left;
+
+	if (IS_ERR(bv))
+		return PTR_ERR(bv);
+
+	left = min((int)(data_len - con->in_msg_pos.data_pos),
+		   (int)(bv->bv_len - con->in_msg_pos.page_pos));
+
+	p = kmap(bv->bv_page) + bv->bv_offset;
+
+	ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
+			       left);
+	if (ret > 0 && datacrc)
+		con->in_data_crc =
+			crc32c(con->in_data_crc,
+				  p + con->in_msg_pos.page_pos, ret);
+	kunmap(bv->bv_page);
+	if (ret <= 0)
+		return ret;
+	con->in_msg_pos.data_pos += ret;
+	con->in_msg_pos.page_pos += ret;
+	if (con->in_msg_pos.page_pos == bv->bv_len) {
+		con->in_msg_pos.page_pos = 0;
+		iter_bio_next(bio_iter, bio_seg);
+	}
+
+	return ret;
+}
+#endif
+
 /*
  * read (part of) a message.
  */
 static int read_partial_message(struct ceph_connection *con)
 {
 	struct ceph_msg *m = con->in_msg;
-	void *p;
 	int ret;
 	int to, left;
 	unsigned front_len, middle_len, data_len, data_off;
@@ -1381,7 +1534,7 @@
 	if ((s64)seq - (s64)con->in_seq < 1) {
 		pr_info("skipping %s%lld %s seq %lld, expected %lld\n",
 			ENTITY_NAME(con->peer_name),
-			pr_addr(&con->peer_addr.in_addr),
+			ceph_pr_addr(&con->peer_addr.in_addr),
 			seq, con->in_seq + 1);
 		con->in_base_pos = -front_len - middle_len - data_len -
 			sizeof(m->footer);
@@ -1422,7 +1575,10 @@
 			m->middle->vec.iov_len = 0;
 
 		con->in_msg_pos.page = 0;
-		con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+		if (m->pages)
+			con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+		else
+			con->in_msg_pos.page_pos = 0;
 		con->in_msg_pos.data_pos = 0;
 	}
 
@@ -1440,27 +1596,29 @@
 		if (ret <= 0)
 			return ret;
 	}
+#ifdef CONFIG_BLOCK
+	if (m->bio && !m->bio_iter)
+		init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
+#endif
 
 	/* (page) data */
 	while (con->in_msg_pos.data_pos < data_len) {
-		left = min((int)(data_len - con->in_msg_pos.data_pos),
-			   (int)(PAGE_SIZE - con->in_msg_pos.page_pos));
-		BUG_ON(m->pages == NULL);
-		p = kmap(m->pages[con->in_msg_pos.page]);
-		ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
-				       left);
-		if (ret > 0 && datacrc)
-			con->in_data_crc =
-				crc32c(con->in_data_crc,
-					  p + con->in_msg_pos.page_pos, ret);
-		kunmap(m->pages[con->in_msg_pos.page]);
-		if (ret <= 0)
-			return ret;
-		con->in_msg_pos.data_pos += ret;
-		con->in_msg_pos.page_pos += ret;
-		if (con->in_msg_pos.page_pos == PAGE_SIZE) {
-			con->in_msg_pos.page_pos = 0;
-			con->in_msg_pos.page++;
+		if (m->pages) {
+			ret = read_partial_message_pages(con, m->pages,
+						 data_len, datacrc);
+			if (ret <= 0)
+				return ret;
+#ifdef CONFIG_BLOCK
+		} else if (m->bio) {
+
+			ret = read_partial_message_bio(con,
+						 &m->bio_iter, &m->bio_seg,
+						 data_len, datacrc);
+			if (ret <= 0)
+				return ret;
+#endif
+		} else {
+			BUG_ON(1);
 		}
 	}
 
@@ -1874,9 +2032,9 @@
 static void ceph_fault(struct ceph_connection *con)
 {
 	pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
-	       pr_addr(&con->peer_addr.in_addr), con->error_msg);
+	       ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
 	dout("fault %p state %lu to peer %s\n",
-	     con, con->state, pr_addr(&con->peer_addr.in_addr));
+	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
 	if (test_bit(LOSSYTX, &con->state)) {
 		dout("fault on LOSSYTX channel\n");
@@ -1936,7 +2094,9 @@
 /*
  * create a new messenger instance
  */
-struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr)
+struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
+					     u32 supported_features,
+					     u32 required_features)
 {
 	struct ceph_messenger *msgr;
 
@@ -1944,6 +2104,9 @@
 	if (msgr == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	msgr->supported_features = supported_features;
+	msgr->required_features = required_features;
+
 	spin_lock_init(&msgr->global_seq_lock);
 
 	/* the zero page is needed if a request is "canceled" while the message
@@ -1966,6 +2129,7 @@
 	dout("messenger_create %p\n", msgr);
 	return msgr;
 }
+EXPORT_SYMBOL(ceph_messenger_create);
 
 void ceph_messenger_destroy(struct ceph_messenger *msgr)
 {
@@ -1975,6 +2139,7 @@
 	kfree(msgr);
 	dout("destroyed messenger %p\n", msgr);
 }
+EXPORT_SYMBOL(ceph_messenger_destroy);
 
 /*
  * Queue up an outgoing message on the given connection.
@@ -2011,6 +2176,7 @@
 	if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
 		queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_send);
 
 /*
  * Revoke a message that was previously queued for send
@@ -2076,6 +2242,7 @@
 	    test_and_set_bit(WRITE_PENDING, &con->state) == 0)
 		queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_keepalive);
 
 
 /*
@@ -2136,6 +2303,10 @@
 	m->nr_pages = 0;
 	m->pages = NULL;
 	m->pagelist = NULL;
+	m->bio = NULL;
+	m->bio_iter = NULL;
+	m->bio_seg = 0;
+	m->trail = NULL;
 
 	dout("ceph_msg_new %p front %d\n", m, front_len);
 	return m;
@@ -2146,6 +2317,7 @@
 	pr_err("msg_new can't create type %d front %d\n", type, front_len);
 	return NULL;
 }
+EXPORT_SYMBOL(ceph_msg_new);
 
 /*
  * Allocate "middle" portion of a message, if it is needed and wasn't
@@ -2250,11 +2422,14 @@
 		m->pagelist = NULL;
 	}
 
+	m->trail = NULL;
+
 	if (m->pool)
 		ceph_msgpool_put(m->pool, m);
 	else
 		ceph_msg_kfree(m);
 }
+EXPORT_SYMBOL(ceph_msg_last_put);
 
 void ceph_msg_dump(struct ceph_msg *msg)
 {
@@ -2275,3 +2450,4 @@
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       &msg->footer, sizeof(msg->footer), true);
 }
+EXPORT_SYMBOL(ceph_msg_dump);
diff --git a/fs/ceph/mon_client.c b/net/ceph/mon_client.c
similarity index 94%
rename from fs/ceph/mon_client.c
rename to net/ceph/mon_client.c
index b2a5a3e..8a07939 100644
--- a/fs/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1,14 +1,16 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/sched.h>
 
-#include "mon_client.h"
-#include "super.h"
-#include "auth.h"
-#include "decode.h"
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/decode.h>
+
+#include <linux/ceph/auth.h>
 
 /*
  * Interact with Ceph monitor cluster.  Handle requests for new map
@@ -74,7 +76,7 @@
 	     m->num_mon);
 	for (i = 0; i < m->num_mon; i++)
 		dout("monmap_decode  mon%d is %s\n", i,
-		     pr_addr(&m->mon_inst[i].addr.in_addr));
+		     ceph_pr_addr(&m->mon_inst[i].addr.in_addr));
 	return m;
 
 bad:
@@ -191,30 +193,33 @@
 		struct ceph_msg *msg = monc->m_subscribe;
 		struct ceph_mon_subscribe_item *i;
 		void *p, *end;
+		int num;
 
 		p = msg->front.iov_base;
 		end = p + msg->front_max;
 
-		dout("__send_subscribe to 'mdsmap' %u+\n",
-		     (unsigned)monc->have_mdsmap);
+		num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap;
+		ceph_encode_32(&p, num);
+
 		if (monc->want_next_osdmap) {
 			dout("__send_subscribe to 'osdmap' %u\n",
 			     (unsigned)monc->have_osdmap);
-			ceph_encode_32(&p, 3);
 			ceph_encode_string(&p, end, "osdmap", 6);
 			i = p;
 			i->have = cpu_to_le64(monc->have_osdmap);
 			i->onetime = 1;
 			p += sizeof(*i);
 			monc->want_next_osdmap = 2;  /* requested */
-		} else {
-			ceph_encode_32(&p, 2);
 		}
-		ceph_encode_string(&p, end, "mdsmap", 6);
-		i = p;
-		i->have = cpu_to_le64(monc->have_mdsmap);
-		i->onetime = 0;
-		p += sizeof(*i);
+		if (monc->want_mdsmap) {
+			dout("__send_subscribe to 'mdsmap' %u+\n",
+			     (unsigned)monc->have_mdsmap);
+			ceph_encode_string(&p, end, "mdsmap", 6);
+			i = p;
+			i->have = cpu_to_le64(monc->have_mdsmap);
+			i->onetime = 0;
+			p += sizeof(*i);
+		}
 		ceph_encode_string(&p, end, "monmap", 6);
 		i = p;
 		i->have = 0;
@@ -243,7 +248,8 @@
 	mutex_lock(&monc->mutex);
 	if (monc->hunting) {
 		pr_info("mon%d %s session established\n",
-			monc->cur_mon, pr_addr(&monc->con->peer_addr.in_addr));
+			monc->cur_mon,
+			ceph_pr_addr(&monc->con->peer_addr.in_addr));
 		monc->hunting = false;
 	}
 	dout("handle_subscribe_ack after %d seconds\n", seconds);
@@ -266,6 +272,7 @@
 	mutex_unlock(&monc->mutex);
 	return 0;
 }
+EXPORT_SYMBOL(ceph_monc_got_mdsmap);
 
 int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 got)
 {
@@ -310,6 +317,7 @@
 	mutex_unlock(&monc->mutex);
 	return 0;
 }
+EXPORT_SYMBOL(ceph_monc_open_session);
 
 /*
  * The monitor responds with mount ack indicate mount success.  The
@@ -540,6 +548,7 @@
 	kref_put(&req->kref, release_generic_request);
 	return err;
 }
+EXPORT_SYMBOL(ceph_monc_do_statfs);
 
 /*
  * pool ops
@@ -651,6 +660,7 @@
 				   pool, 0, (char *)snapid, sizeof(*snapid));
 
 }
+EXPORT_SYMBOL(ceph_monc_create_snapid);
 
 int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
 			    u32 pool, u64 snapid)
@@ -708,9 +718,9 @@
  */
 static int build_initial_monmap(struct ceph_mon_client *monc)
 {
-	struct ceph_mount_args *args = monc->client->mount_args;
-	struct ceph_entity_addr *mon_addr = args->mon_addr;
-	int num_mon = args->num_mon;
+	struct ceph_options *opt = monc->client->options;
+	struct ceph_entity_addr *mon_addr = opt->mon_addr;
+	int num_mon = opt->num_mon;
 	int i;
 
 	/* build initial monmap */
@@ -728,11 +738,6 @@
 	}
 	monc->monmap->num_mon = num_mon;
 	monc->have_fsid = false;
-
-	/* release addr memory */
-	kfree(args->mon_addr);
-	args->mon_addr = NULL;
-	args->num_mon = 0;
 	return 0;
 }
 
@@ -753,8 +758,8 @@
 	monc->con = NULL;
 
 	/* authentication */
-	monc->auth = ceph_auth_init(cl->mount_args->name,
-				    cl->mount_args->secret);
+	monc->auth = ceph_auth_init(cl->options->name,
+				    cl->options->secret);
 	if (IS_ERR(monc->auth))
 		return PTR_ERR(monc->auth);
 	monc->auth->want_keys =
@@ -808,6 +813,7 @@
 out:
 	return err;
 }
+EXPORT_SYMBOL(ceph_monc_init);
 
 void ceph_monc_stop(struct ceph_mon_client *monc)
 {
@@ -832,6 +838,7 @@
 
 	kfree(monc->monmap);
 }
+EXPORT_SYMBOL(ceph_monc_stop);
 
 static void handle_auth_reply(struct ceph_mon_client *monc,
 			      struct ceph_msg *msg)
@@ -889,6 +896,7 @@
 	mutex_unlock(&monc->mutex);
 	return ret;
 }
+EXPORT_SYMBOL(ceph_monc_validate_auth);
 
 /*
  * handle incoming message
@@ -922,15 +930,16 @@
 		ceph_monc_handle_map(monc, msg);
 		break;
 
-	case CEPH_MSG_MDS_MAP:
-		ceph_mdsc_handle_map(&monc->client->mdsc, msg);
-		break;
-
 	case CEPH_MSG_OSD_MAP:
 		ceph_osdc_handle_map(&monc->client->osdc, msg);
 		break;
 
 	default:
+		/* can the chained handler handle it? */
+		if (monc->client->extra_mon_dispatch &&
+		    monc->client->extra_mon_dispatch(monc->client, msg) == 0)
+			break;
+			
 		pr_err("received unknown message type %d %s\n", type,
 		       ceph_msg_type_name(type));
 	}
@@ -994,7 +1003,7 @@
 	if (monc->con && !monc->hunting)
 		pr_info("mon%d %s session lost, "
 			"hunting for new mon\n", monc->cur_mon,
-			pr_addr(&monc->con->peer_addr.in_addr));
+			ceph_pr_addr(&monc->con->peer_addr.in_addr));
 
 	__close_session(monc);
 	if (!monc->hunting) {
diff --git a/fs/ceph/msgpool.c b/net/ceph/msgpool.c
similarity index 95%
rename from fs/ceph/msgpool.c
rename to net/ceph/msgpool.c
index dd65a64..d5f2d97 100644
--- a/fs/ceph/msgpool.c
+++ b/net/ceph/msgpool.c
@@ -1,11 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
-#include "msgpool.h"
+#include <linux/ceph/msgpool.h>
 
 static void *alloc_fn(gfp_t gfp_mask, void *arg)
 {
diff --git a/fs/ceph/osd_client.c b/net/ceph/osd_client.c
similarity index 84%
rename from fs/ceph/osd_client.c
rename to net/ceph/osd_client.c
index 3b5571b..7939199 100644
--- a/fs/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1,17 +1,22 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/err.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#ifdef CONFIG_BLOCK
+#include <linux/bio.h>
+#endif
 
-#include "super.h"
-#include "osd_client.h"
-#include "messenger.h"
-#include "decode.h"
-#include "auth.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osd_client.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/pagelist.h>
 
 #define OSD_OP_FRONT_LEN	4096
 #define OSD_OPREPLY_FRONT_LEN	512
@@ -22,6 +27,59 @@
 
 static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd);
 
+static int op_needs_trail(int op)
+{
+	switch (op) {
+	case CEPH_OSD_OP_GETXATTR:
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+	case CEPH_OSD_OP_CALL:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static int op_has_extent(int op)
+{
+	return (op == CEPH_OSD_OP_READ ||
+		op == CEPH_OSD_OP_WRITE);
+}
+
+void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+			struct ceph_file_layout *layout,
+			u64 snapid,
+			u64 off, u64 *plen, u64 *bno,
+			struct ceph_osd_request *req,
+			struct ceph_osd_req_op *op)
+{
+	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
+	u64 orig_len = *plen;
+	u64 objoff, objlen;    /* extent in object */
+
+	reqhead->snapid = cpu_to_le64(snapid);
+
+	/* object extent? */
+	ceph_calc_file_object_mapping(layout, off, plen, bno,
+				      &objoff, &objlen);
+	if (*plen < orig_len)
+		dout(" skipping last %llu, final file extent %llu~%llu\n",
+		     orig_len - *plen, off, *plen);
+
+	if (op_has_extent(op->op)) {
+		op->extent.offset = objoff;
+		op->extent.length = objlen;
+	}
+	req->r_num_pages = calc_pages_for(off, *plen);
+	if (op->op == CEPH_OSD_OP_WRITE)
+		op->payload_len = *plen;
+
+	dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
+	     *bno, objoff, objlen, req->r_num_pages);
+
+}
+EXPORT_SYMBOL(ceph_calc_raw_layout);
+
 /*
  * Implement client access to distributed object storage cluster.
  *
@@ -48,34 +106,19 @@
  * fill osd op in request message.
  */
 static void calc_layout(struct ceph_osd_client *osdc,
-			struct ceph_vino vino, struct ceph_file_layout *layout,
+			struct ceph_vino vino,
+			struct ceph_file_layout *layout,
 			u64 off, u64 *plen,
-			struct ceph_osd_request *req)
+			struct ceph_osd_request *req,
+			struct ceph_osd_req_op *op)
 {
-	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
-	struct ceph_osd_op *op = (void *)(reqhead + 1);
-	u64 orig_len = *plen;
-	u64 objoff, objlen;    /* extent in object */
 	u64 bno;
 
-	reqhead->snapid = cpu_to_le64(vino.snap);
-
-	/* object extent? */
-	ceph_calc_file_object_mapping(layout, off, plen, &bno,
-				      &objoff, &objlen);
-	if (*plen < orig_len)
-		dout(" skipping last %llu, final file extent %llu~%llu\n",
-		     orig_len - *plen, off, *plen);
+	ceph_calc_raw_layout(osdc, layout, vino.snap, off,
+			     plen, &bno, req, op);
 
 	sprintf(req->r_oid, "%llx.%08llx", vino.ino, bno);
 	req->r_oid_len = strlen(req->r_oid);
-
-	op->extent.offset = cpu_to_le64(objoff);
-	op->extent.length = cpu_to_le64(objlen);
-	req->r_num_pages = calc_pages_for(off, *plen);
-
-	dout("calc_layout %s (%d) %llu~%llu (%d pages)\n",
-	     req->r_oid, req->r_oid_len, objoff, objlen, req->r_num_pages);
 }
 
 /*
@@ -101,12 +144,259 @@
 	if (req->r_own_pages)
 		ceph_release_page_vector(req->r_pages,
 					 req->r_num_pages);
+#ifdef CONFIG_BLOCK
+	if (req->r_bio)
+		bio_put(req->r_bio);
+#endif
 	ceph_put_snap_context(req->r_snapc);
+	if (req->r_trail) {
+		ceph_pagelist_release(req->r_trail);
+		kfree(req->r_trail);
+	}
 	if (req->r_mempool)
 		mempool_free(req, req->r_osdc->req_mempool);
 	else
 		kfree(req);
 }
+EXPORT_SYMBOL(ceph_osdc_release_request);
+
+static int get_num_ops(struct ceph_osd_req_op *ops, int *needs_trail)
+{
+	int i = 0;
+
+	if (needs_trail)
+		*needs_trail = 0;
+	while (ops[i].op) {
+		if (needs_trail && op_needs_trail(ops[i].op))
+			*needs_trail = 1;
+		i++;
+	}
+
+	return i;
+}
+
+struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+					       int flags,
+					       struct ceph_snap_context *snapc,
+					       struct ceph_osd_req_op *ops,
+					       bool use_mempool,
+					       gfp_t gfp_flags,
+					       struct page **pages,
+					       struct bio *bio)
+{
+	struct ceph_osd_request *req;
+	struct ceph_msg *msg;
+	int needs_trail;
+	int num_op = get_num_ops(ops, &needs_trail);
+	size_t msg_size = sizeof(struct ceph_osd_request_head);
+
+	msg_size += num_op*sizeof(struct ceph_osd_op);
+
+	if (use_mempool) {
+		req = mempool_alloc(osdc->req_mempool, gfp_flags);
+		memset(req, 0, sizeof(*req));
+	} else {
+		req = kzalloc(sizeof(*req), gfp_flags);
+	}
+	if (req == NULL)
+		return NULL;
+
+	req->r_osdc = osdc;
+	req->r_mempool = use_mempool;
+
+	kref_init(&req->r_kref);
+	init_completion(&req->r_completion);
+	init_completion(&req->r_safe_completion);
+	INIT_LIST_HEAD(&req->r_unsafe_item);
+	req->r_flags = flags;
+
+	WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
+
+	/* create reply message */
+	if (use_mempool)
+		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
+	else
+		msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY,
+				   OSD_OPREPLY_FRONT_LEN, gfp_flags);
+	if (!msg) {
+		ceph_osdc_put_request(req);
+		return NULL;
+	}
+	req->r_reply = msg;
+
+	/* allocate space for the trailing data */
+	if (needs_trail) {
+		req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags);
+		if (!req->r_trail) {
+			ceph_osdc_put_request(req);
+			return NULL;
+		}
+		ceph_pagelist_init(req->r_trail);
+	}
+	/* create request message; allow space for oid */
+	msg_size += 40;
+	if (snapc)
+		msg_size += sizeof(u64) * snapc->num_snaps;
+	if (use_mempool)
+		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
+	else
+		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags);
+	if (!msg) {
+		ceph_osdc_put_request(req);
+		return NULL;
+	}
+
+	msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
+	memset(msg->front.iov_base, 0, msg->front.iov_len);
+
+	req->r_request = msg;
+	req->r_pages = pages;
+#ifdef CONFIG_BLOCK
+	if (bio) {
+		req->r_bio = bio;
+		bio_get(req->r_bio);
+	}
+#endif
+
+	return req;
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_request);
+
+static void osd_req_encode_op(struct ceph_osd_request *req,
+			      struct ceph_osd_op *dst,
+			      struct ceph_osd_req_op *src)
+{
+	dst->op = cpu_to_le16(src->op);
+
+	switch (dst->op) {
+	case CEPH_OSD_OP_READ:
+	case CEPH_OSD_OP_WRITE:
+		dst->extent.offset =
+			cpu_to_le64(src->extent.offset);
+		dst->extent.length =
+			cpu_to_le64(src->extent.length);
+		dst->extent.truncate_size =
+			cpu_to_le64(src->extent.truncate_size);
+		dst->extent.truncate_seq =
+			cpu_to_le32(src->extent.truncate_seq);
+		break;
+
+	case CEPH_OSD_OP_GETXATTR:
+	case CEPH_OSD_OP_SETXATTR:
+	case CEPH_OSD_OP_CMPXATTR:
+		BUG_ON(!req->r_trail);
+
+		dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
+		dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
+		dst->xattr.cmp_op = src->xattr.cmp_op;
+		dst->xattr.cmp_mode = src->xattr.cmp_mode;
+		ceph_pagelist_append(req->r_trail, src->xattr.name,
+				     src->xattr.name_len);
+		ceph_pagelist_append(req->r_trail, src->xattr.val,
+				     src->xattr.value_len);
+		break;
+	case CEPH_OSD_OP_CALL:
+		BUG_ON(!req->r_trail);
+
+		dst->cls.class_len = src->cls.class_len;
+		dst->cls.method_len = src->cls.method_len;
+		dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
+
+		ceph_pagelist_append(req->r_trail, src->cls.class_name,
+				     src->cls.class_len);
+		ceph_pagelist_append(req->r_trail, src->cls.method_name,
+				     src->cls.method_len);
+		ceph_pagelist_append(req->r_trail, src->cls.indata,
+				     src->cls.indata_len);
+		break;
+	case CEPH_OSD_OP_ROLLBACK:
+		dst->snap.snapid = cpu_to_le64(src->snap.snapid);
+		break;
+	case CEPH_OSD_OP_STARTSYNC:
+		break;
+	default:
+		pr_err("unrecognized osd opcode %d\n", dst->op);
+		WARN_ON(1);
+		break;
+	}
+	dst->payload_len = cpu_to_le32(src->payload_len);
+}
+
+/*
+ * build new request AND message
+ *
+ */
+void ceph_osdc_build_request(struct ceph_osd_request *req,
+			     u64 off, u64 *plen,
+			     struct ceph_osd_req_op *src_ops,
+			     struct ceph_snap_context *snapc,
+			     struct timespec *mtime,
+			     const char *oid,
+			     int oid_len)
+{
+	struct ceph_msg *msg = req->r_request;
+	struct ceph_osd_request_head *head;
+	struct ceph_osd_req_op *src_op;
+	struct ceph_osd_op *op;
+	void *p;
+	int num_op = get_num_ops(src_ops, NULL);
+	size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
+	int flags = req->r_flags;
+	u64 data_len = 0;
+	int i;
+
+	head = msg->front.iov_base;
+	op = (void *)(head + 1);
+	p = (void *)(op + num_op);
+
+	req->r_snapc = ceph_get_snap_context(snapc);
+
+	head->client_inc = cpu_to_le32(1); /* always, for now. */
+	head->flags = cpu_to_le32(flags);
+	if (flags & CEPH_OSD_FLAG_WRITE)
+		ceph_encode_timespec(&head->mtime, mtime);
+	head->num_ops = cpu_to_le16(num_op);
+
+
+	/* fill in oid */
+	head->object_len = cpu_to_le32(oid_len);
+	memcpy(p, oid, oid_len);
+	p += oid_len;
+
+	src_op = src_ops;
+	while (src_op->op) {
+		osd_req_encode_op(req, op, src_op);
+		src_op++;
+		op++;
+	}
+
+	if (req->r_trail)
+		data_len += req->r_trail->length;
+
+	if (snapc) {
+		head->snap_seq = cpu_to_le64(snapc->seq);
+		head->num_snaps = cpu_to_le32(snapc->num_snaps);
+		for (i = 0; i < snapc->num_snaps; i++) {
+			put_unaligned_le64(snapc->snaps[i], p);
+			p += sizeof(u64);
+		}
+	}
+
+	if (flags & CEPH_OSD_FLAG_WRITE) {
+		req->r_request->hdr.data_off = cpu_to_le16(off);
+		req->r_request->hdr.data_len = cpu_to_le32(*plen + data_len);
+	} else if (data_len) {
+		req->r_request->hdr.data_off = 0;
+		req->r_request->hdr.data_len = cpu_to_le32(data_len);
+	}
+
+	BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
+	msg_size = p - msg->front.iov_base;
+	msg->front.iov_len = msg_size;
+	msg->hdr.front_len = cpu_to_le32(msg_size);
+	return;
+}
+EXPORT_SYMBOL(ceph_osdc_build_request);
 
 /*
  * build new request AND message, calculate layout, and adjust file
@@ -131,110 +421,40 @@
 					       struct timespec *mtime,
 					       bool use_mempool, int num_reply)
 {
+	struct ceph_osd_req_op ops[3];
 	struct ceph_osd_request *req;
-	struct ceph_msg *msg;
-	struct ceph_osd_request_head *head;
-	struct ceph_osd_op *op;
-	void *p;
-	int num_op = 1 + do_sync;
-	size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
-	int i;
 
-	if (use_mempool) {
-		req = mempool_alloc(osdc->req_mempool, GFP_NOFS);
-		memset(req, 0, sizeof(*req));
-	} else {
-		req = kzalloc(sizeof(*req), GFP_NOFS);
-	}
-	if (req == NULL)
-		return NULL;
-
-	req->r_osdc = osdc;
-	req->r_mempool = use_mempool;
-	kref_init(&req->r_kref);
-	init_completion(&req->r_completion);
-	init_completion(&req->r_safe_completion);
-	INIT_LIST_HEAD(&req->r_unsafe_item);
-	req->r_flags = flags;
-
-	WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
-
-	/* create reply message */
-	if (use_mempool)
-		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
-	else
-		msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY,
-				   OSD_OPREPLY_FRONT_LEN, GFP_NOFS);
-	if (!msg) {
-		ceph_osdc_put_request(req);
-		return NULL;
-	}
-	req->r_reply = msg;
-
-	/* create request message; allow space for oid */
-	msg_size += 40;
-	if (snapc)
-		msg_size += sizeof(u64) * snapc->num_snaps;
-	if (use_mempool)
-		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
-	else
-		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, GFP_NOFS);
-	if (!msg) {
-		ceph_osdc_put_request(req);
-		return NULL;
-	}
-	msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
-	memset(msg->front.iov_base, 0, msg->front.iov_len);
-	head = msg->front.iov_base;
-	op = (void *)(head + 1);
-	p = (void *)(op + num_op);
-
-	req->r_request = msg;
-	req->r_snapc = ceph_get_snap_context(snapc);
-
-	head->client_inc = cpu_to_le32(1); /* always, for now. */
-	head->flags = cpu_to_le32(flags);
-	if (flags & CEPH_OSD_FLAG_WRITE)
-		ceph_encode_timespec(&head->mtime, mtime);
-	head->num_ops = cpu_to_le16(num_op);
-	op->op = cpu_to_le16(opcode);
-
-	/* calculate max write size */
-	calc_layout(osdc, vino, layout, off, plen, req);
-	req->r_file_layout = *layout;  /* keep a copy */
-
-	if (flags & CEPH_OSD_FLAG_WRITE) {
-		req->r_request->hdr.data_off = cpu_to_le16(off);
-		req->r_request->hdr.data_len = cpu_to_le32(*plen);
-		op->payload_len = cpu_to_le32(*plen);
-	}
-	op->extent.truncate_size = cpu_to_le64(truncate_size);
-	op->extent.truncate_seq = cpu_to_le32(truncate_seq);
-
-	/* fill in oid */
-	head->object_len = cpu_to_le32(req->r_oid_len);
-	memcpy(p, req->r_oid, req->r_oid_len);
-	p += req->r_oid_len;
+	ops[0].op = opcode;
+	ops[0].extent.truncate_seq = truncate_seq;
+	ops[0].extent.truncate_size = truncate_size;
+	ops[0].payload_len = 0;
 
 	if (do_sync) {
-		op++;
-		op->op = cpu_to_le16(CEPH_OSD_OP_STARTSYNC);
-	}
-	if (snapc) {
-		head->snap_seq = cpu_to_le64(snapc->seq);
-		head->num_snaps = cpu_to_le32(snapc->num_snaps);
-		for (i = 0; i < snapc->num_snaps; i++) {
-			put_unaligned_le64(snapc->snaps[i], p);
-			p += sizeof(u64);
-		}
-	}
+		ops[1].op = CEPH_OSD_OP_STARTSYNC;
+		ops[1].payload_len = 0;
+		ops[2].op = 0;
+	} else
+		ops[1].op = 0;
 
-	BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
-	msg_size = p - msg->front.iov_base;
-	msg->front.iov_len = msg_size;
-	msg->hdr.front_len = cpu_to_le32(msg_size);
+	req = ceph_osdc_alloc_request(osdc, flags,
+					 snapc, ops,
+					 use_mempool,
+					 GFP_NOFS, NULL, NULL);
+	if (IS_ERR(req))
+		return req;
+
+	/* calculate max write size */
+	calc_layout(osdc, vino, layout, off, plen, req, ops);
+	req->r_file_layout = *layout;  /* keep a copy */
+
+	ceph_osdc_build_request(req, off, plen, ops,
+				snapc,
+				mtime,
+				req->r_oid, req->r_oid_len);
+
 	return req;
 }
+EXPORT_SYMBOL(ceph_osdc_new_request);
 
 /*
  * We keep osd requests in an rbtree, sorted by ->r_tid.
@@ -389,7 +609,7 @@
 	dout("__move_osd_to_lru %p\n", osd);
 	BUG_ON(!list_empty(&osd->o_osd_lru));
 	list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
-	osd->lru_ttl = jiffies + osdc->client->mount_args->osd_idle_ttl * HZ;
+	osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl * HZ;
 }
 
 static void __remove_osd_from_lru(struct ceph_osd *osd)
@@ -483,7 +703,7 @@
 static void __schedule_osd_timeout(struct ceph_osd_client *osdc)
 {
 	schedule_delayed_work(&osdc->timeout_work,
-			osdc->client->mount_args->osd_keepalive_timeout * HZ);
+			osdc->client->options->osd_keepalive_timeout * HZ);
 }
 
 static void __cancel_osd_timeout(struct ceph_osd_client *osdc)
@@ -684,9 +904,9 @@
 		container_of(work, struct ceph_osd_client, timeout_work.work);
 	struct ceph_osd_request *req, *last_req = NULL;
 	struct ceph_osd *osd;
-	unsigned long timeout = osdc->client->mount_args->osd_timeout * HZ;
+	unsigned long timeout = osdc->client->options->osd_timeout * HZ;
 	unsigned long keepalive =
-		osdc->client->mount_args->osd_keepalive_timeout * HZ;
+		osdc->client->options->osd_keepalive_timeout * HZ;
 	unsigned long last_stamp = 0;
 	struct rb_node *p;
 	struct list_head slow_osds;
@@ -773,7 +993,7 @@
 		container_of(work, struct ceph_osd_client,
 			     osds_timeout_work.work);
 	unsigned long delay =
-		osdc->client->mount_args->osd_idle_ttl * HZ >> 2;
+		osdc->client->options->osd_idle_ttl * HZ >> 2;
 
 	dout("osds timeout\n");
 	down_read(&osdc->map_sem);
@@ -1104,6 +1324,10 @@
 
 	req->r_request->pages = req->r_pages;
 	req->r_request->nr_pages = req->r_num_pages;
+#ifdef CONFIG_BLOCK
+	req->r_request->bio = req->r_bio;
+#endif
+	req->r_request->trail = req->r_trail;
 
 	register_request(osdc, req);
 
@@ -1131,6 +1355,7 @@
 	up_read(&osdc->map_sem);
 	return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_start_request);
 
 /*
  * wait for a request to complete
@@ -1153,6 +1378,7 @@
 	dout("wait_request tid %llu result %d\n", req->r_tid, req->r_result);
 	return req->r_result;
 }
+EXPORT_SYMBOL(ceph_osdc_wait_request);
 
 /*
  * sync - wait for all in-flight requests to flush.  avoid starvation.
@@ -1186,6 +1412,7 @@
 	mutex_unlock(&osdc->request_mutex);
 	dout("sync done (thru tid %llu)\n", last_tid);
 }
+EXPORT_SYMBOL(ceph_osdc_sync);
 
 /*
  * init, shutdown
@@ -1211,7 +1438,7 @@
 	INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout);
 
 	schedule_delayed_work(&osdc->osds_timeout_work,
-	   round_jiffies_relative(osdc->client->mount_args->osd_idle_ttl * HZ));
+	   round_jiffies_relative(osdc->client->options->osd_idle_ttl * HZ));
 
 	err = -ENOMEM;
 	osdc->req_mempool = mempool_create_kmalloc_pool(10,
@@ -1237,6 +1464,7 @@
 out:
 	return err;
 }
+EXPORT_SYMBOL(ceph_osdc_init);
 
 void ceph_osdc_stop(struct ceph_osd_client *osdc)
 {
@@ -1251,6 +1479,7 @@
 	ceph_msgpool_destroy(&osdc->msgpool_op);
 	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
 }
+EXPORT_SYMBOL(ceph_osdc_stop);
 
 /*
  * Read some contiguous pages.  If we cross a stripe boundary, shorten
@@ -1288,6 +1517,7 @@
 	dout("readpages result %d\n", rc);
 	return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_readpages);
 
 /*
  * do a synchronous write on N pages
@@ -1330,6 +1560,7 @@
 	dout("writepages result %d\n", rc);
 	return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_writepages);
 
 /*
  * handle incoming message
@@ -1420,6 +1651,9 @@
 		}
 		m->pages = req->r_pages;
 		m->nr_pages = req->r_num_pages;
+#ifdef CONFIG_BLOCK
+		m->bio = req->r_bio;
+#endif
 	}
 	*skip = 0;
 	req->r_con_filling_msg = ceph_con_get(con);
diff --git a/fs/ceph/osdmap.c b/net/ceph/osdmap.c
similarity index 97%
rename from fs/ceph/osdmap.c
rename to net/ceph/osdmap.c
index e31f118..d73f3f6 100644
--- a/fs/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1,14 +1,15 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <asm/div64.h>
 
-#include "super.h"
-#include "osdmap.h"
-#include "crush/hash.h"
-#include "crush/mapper.h"
-#include "decode.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osdmap.h>
+#include <linux/ceph/decode.h>
+#include <linux/crush/hash.h>
+#include <linux/crush/mapper.h>
 
 char *ceph_osdmap_state_str(char *str, int len, int state)
 {
@@ -417,6 +418,20 @@
 	return NULL;
 }
 
+int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name)
+{
+	struct rb_node *rbp;
+
+	for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) {
+		struct ceph_pg_pool_info *pi =
+			rb_entry(rbp, struct ceph_pg_pool_info, node);
+		if (pi->name && strcmp(pi->name, name) == 0)
+			return pi->id;
+	}
+	return -ENOENT;
+}
+EXPORT_SYMBOL(ceph_pg_poolid_by_name);
+
 static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
 {
 	rb_erase(&pi->node, root);
@@ -966,6 +981,7 @@
 
 	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
 }
+EXPORT_SYMBOL(ceph_calc_file_object_mapping);
 
 /*
  * calculate an object layout (i.e. pgid) from an oid,
@@ -1011,6 +1027,7 @@
 	ol->ol_stripe_unit = fl->fl_object_stripe_unit;
 	return 0;
 }
+EXPORT_SYMBOL(ceph_calc_object_layout);
 
 /*
  * Calculate raw osd vector for the given pgid.  Return pointer to osd
@@ -1108,3 +1125,4 @@
 			return osds[i];
 	return -1;
 }
+EXPORT_SYMBOL(ceph_calc_pg_primary);
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
new file mode 100644
index 0000000..13cb409
--- /dev/null
+++ b/net/ceph/pagelist.c
@@ -0,0 +1,154 @@
+
+#include <linux/module.h>
+#include <linux/gfp.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/ceph/pagelist.h>
+
+static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
+{
+	if (pl->mapped_tail) {
+		struct page *page = list_entry(pl->head.prev, struct page, lru);
+		kunmap(page);
+		pl->mapped_tail = NULL;
+	}
+}
+
+int ceph_pagelist_release(struct ceph_pagelist *pl)
+{
+	ceph_pagelist_unmap_tail(pl);
+	while (!list_empty(&pl->head)) {
+		struct page *page = list_first_entry(&pl->head, struct page,
+						     lru);
+		list_del(&page->lru);
+		__free_page(page);
+	}
+	ceph_pagelist_free_reserve(pl);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_release);
+
+static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
+{
+	struct page *page;
+
+	if (!pl->num_pages_free) {
+		page = __page_cache_alloc(GFP_NOFS);
+	} else {
+		page = list_first_entry(&pl->free_list, struct page, lru);
+		list_del(&page->lru);
+		--pl->num_pages_free;
+	}
+	if (!page)
+		return -ENOMEM;
+	pl->room += PAGE_SIZE;
+	ceph_pagelist_unmap_tail(pl);
+	list_add_tail(&page->lru, &pl->head);
+	pl->mapped_tail = kmap(page);
+	return 0;
+}
+
+int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len)
+{
+	while (pl->room < len) {
+		size_t bit = pl->room;
+		int ret;
+
+		memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK),
+		       buf, bit);
+		pl->length += bit;
+		pl->room -= bit;
+		buf += bit;
+		len -= bit;
+		ret = ceph_pagelist_addpage(pl);
+		if (ret)
+			return ret;
+	}
+
+	memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len);
+	pl->length += len;
+	pl->room -= len;
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_append);
+
+/**
+ * Allocate enough pages for a pagelist to append the given amount
+ * of data without without allocating.
+ * Returns: 0 on success, -ENOMEM on error.
+ */
+int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space)
+{
+	if (space <= pl->room)
+		return 0;
+	space -= pl->room;
+	space = (space + PAGE_SIZE - 1) >> PAGE_SHIFT;   /* conv to num pages */
+
+	while (space > pl->num_pages_free) {
+		struct page *page = __page_cache_alloc(GFP_NOFS);
+		if (!page)
+			return -ENOMEM;
+		list_add_tail(&page->lru, &pl->free_list);
+		++pl->num_pages_free;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_reserve);
+
+/**
+ * Free any pages that have been preallocated.
+ */
+int ceph_pagelist_free_reserve(struct ceph_pagelist *pl)
+{
+	while (!list_empty(&pl->free_list)) {
+		struct page *page = list_first_entry(&pl->free_list,
+						     struct page, lru);
+		list_del(&page->lru);
+		__free_page(page);
+		--pl->num_pages_free;
+	}
+	BUG_ON(pl->num_pages_free);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_free_reserve);
+
+/**
+ * Create a truncation point.
+ */
+void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
+			      struct ceph_pagelist_cursor *c)
+{
+	c->pl = pl;
+	c->page_lru = pl->head.prev;
+	c->room = pl->room;
+}
+EXPORT_SYMBOL(ceph_pagelist_set_cursor);
+
+/**
+ * Truncate a pagelist to the given point. Move extra pages to reserve.
+ * This won't sleep.
+ * Returns: 0 on success,
+ *          -EINVAL if the pagelist doesn't match the trunc point pagelist
+ */
+int ceph_pagelist_truncate(struct ceph_pagelist *pl,
+			   struct ceph_pagelist_cursor *c)
+{
+	struct page *page;
+
+	if (pl != c->pl)
+		return -EINVAL;
+	ceph_pagelist_unmap_tail(pl);
+	while (pl->head.prev != c->page_lru) {
+		page = list_entry(pl->head.prev, struct page, lru);
+		list_del(&page->lru);                /* remove from pagelist */
+		list_add_tail(&page->lru, &pl->free_list); /* add to reserve */
+		++pl->num_pages_free;
+	}
+	pl->room = c->room;
+	if (!list_empty(&pl->head)) {
+		page = list_entry(pl->head.prev, struct page, lru);
+		pl->mapped_tail = kmap(page);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_truncate);
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
new file mode 100644
index 0000000..54caf06
--- /dev/null
+++ b/net/ceph/pagevec.c
@@ -0,0 +1,223 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/writeback.h>
+
+#include <linux/ceph/libceph.h>
+
+/*
+ * build a vector of user pages
+ */
+struct page **ceph_get_direct_page_vector(const char __user *data,
+						 int num_pages,
+						 loff_t off, size_t len)
+{
+	struct page **pages;
+	int rc;
+
+	pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+
+	down_read(&current->mm->mmap_sem);
+	rc = get_user_pages(current, current->mm, (unsigned long)data,
+			    num_pages, 0, 0, pages, NULL);
+	up_read(&current->mm->mmap_sem);
+	if (rc < 0)
+		goto fail;
+	return pages;
+
+fail:
+	kfree(pages);
+	return ERR_PTR(rc);
+}
+EXPORT_SYMBOL(ceph_get_direct_page_vector);
+
+void ceph_put_page_vector(struct page **pages, int num_pages)
+{
+	int i;
+
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+	kfree(pages);
+}
+EXPORT_SYMBOL(ceph_put_page_vector);
+
+void ceph_release_page_vector(struct page **pages, int num_pages)
+{
+	int i;
+
+	for (i = 0; i < num_pages; i++)
+		__free_pages(pages[i], 0);
+	kfree(pages);
+}
+EXPORT_SYMBOL(ceph_release_page_vector);
+
+/*
+ * allocate a vector new pages
+ */
+struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags)
+{
+	struct page **pages;
+	int i;
+
+	pages = kmalloc(sizeof(*pages) * num_pages, flags);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+	for (i = 0; i < num_pages; i++) {
+		pages[i] = __page_cache_alloc(flags);
+		if (pages[i] == NULL) {
+			ceph_release_page_vector(pages, i);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+	return pages;
+}
+EXPORT_SYMBOL(ceph_alloc_page_vector);
+
+/*
+ * copy user data into a page vector
+ */
+int ceph_copy_user_to_page_vector(struct page **pages,
+					 const char __user *data,
+					 loff_t off, size_t len)
+{
+	int i = 0;
+	int po = off & ~PAGE_CACHE_MASK;
+	int left = len;
+	int l, bad;
+
+	while (left > 0) {
+		l = min_t(int, PAGE_CACHE_SIZE-po, left);
+		bad = copy_from_user(page_address(pages[i]) + po, data, l);
+		if (bad == l)
+			return -EFAULT;
+		data += l - bad;
+		left -= l - bad;
+		po += l - bad;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_user_to_page_vector);
+
+int ceph_copy_to_page_vector(struct page **pages,
+				    const char *data,
+				    loff_t off, size_t len)
+{
+	int i = 0;
+	size_t po = off & ~PAGE_CACHE_MASK;
+	size_t left = len;
+	size_t l;
+
+	while (left > 0) {
+		l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+		memcpy(page_address(pages[i]) + po, data, l);
+		data += l;
+		left -= l;
+		po += l;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_to_page_vector);
+
+int ceph_copy_from_page_vector(struct page **pages,
+				    char *data,
+				    loff_t off, size_t len)
+{
+	int i = 0;
+	size_t po = off & ~PAGE_CACHE_MASK;
+	size_t left = len;
+	size_t l;
+
+	while (left > 0) {
+		l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+		memcpy(data, page_address(pages[i]) + po, l);
+		data += l;
+		left -= l;
+		po += l;
+		if (po == PAGE_CACHE_SIZE) {
+			po = 0;
+			i++;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_from_page_vector);
+
+/*
+ * copy user data from a page vector into a user pointer
+ */
+int ceph_copy_page_vector_to_user(struct page **pages,
+					 char __user *data,
+					 loff_t off, size_t len)
+{
+	int i = 0;
+	int po = off & ~PAGE_CACHE_MASK;
+	int left = len;
+	int l, bad;
+
+	while (left > 0) {
+		l = min_t(int, left, PAGE_CACHE_SIZE-po);
+		bad = copy_to_user(data, page_address(pages[i]) + po, l);
+		if (bad == l)
+			return -EFAULT;
+		data += l - bad;
+		left -= l - bad;
+		if (po) {
+			po += l - bad;
+			if (po == PAGE_CACHE_SIZE)
+				po = 0;
+		}
+		i++;
+	}
+	return len;
+}
+EXPORT_SYMBOL(ceph_copy_page_vector_to_user);
+
+/*
+ * Zero an extent within a page vector.  Offset is relative to the
+ * start of the first page.
+ */
+void ceph_zero_page_vector_range(int off, int len, struct page **pages)
+{
+	int i = off >> PAGE_CACHE_SHIFT;
+
+	off &= ~PAGE_CACHE_MASK;
+
+	dout("zero_page_vector_page %u~%u\n", off, len);
+
+	/* leading partial page? */
+	if (off) {
+		int end = min((int)PAGE_CACHE_SIZE, off + len);
+		dout("zeroing %d %p head from %d\n", i, pages[i],
+		     (int)off);
+		zero_user_segment(pages[i], off, end);
+		len -= (end - off);
+		i++;
+	}
+	while (len >= PAGE_CACHE_SIZE) {
+		dout("zeroing %d %p len=%d\n", i, pages[i], len);
+		zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
+		len -= PAGE_CACHE_SIZE;
+		i++;
+	}
+	/* trailing partial page? */
+	if (len) {
+		dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len);
+		zero_user_segment(pages[i], 0, len);
+	}
+}
+EXPORT_SYMBOL(ceph_zero_page_vector_range);
+
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 251997a..282806b 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -243,6 +243,7 @@
 	unlock_sock_fast(sk, slow);
 
 	/* skb is now orphaned, can be freed outside of locked section */
+	trace_kfree_skb(skb, skb_free_datagram_locked);
 	__kfree_skb(skb);
 }
 EXPORT_SYMBOL(skb_free_datagram_locked);
diff --git a/net/core/dev.c b/net/core/dev.c
index 660dd41..7ec85e2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -128,6 +128,8 @@
 #include <linux/jhash.h>
 #include <linux/random.h>
 #include <trace/events/napi.h>
+#include <trace/events/net.h>
+#include <trace/events/skb.h>
 #include <linux/pci.h>
 
 #include "net-sysfs.h"
@@ -1978,6 +1980,7 @@
 		}
 
 		rc = ops->ndo_start_xmit(skb, dev);
+		trace_net_dev_xmit(skb, rc);
 		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
 		return rc;
@@ -1998,6 +2001,7 @@
 			skb_dst_drop(nskb);
 
 		rc = ops->ndo_start_xmit(nskb, dev);
+		trace_net_dev_xmit(nskb, rc);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
 				goto out_kfree_gso_skb;
@@ -2186,6 +2190,7 @@
 #ifdef CONFIG_NET_CLS_ACT
 	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
 #endif
+	trace_net_dev_queue(skb);
 	if (q->enqueue) {
 		rc = __dev_xmit_skb(skb, q, dev, txq);
 		goto out;
@@ -2512,6 +2517,7 @@
 	if (netdev_tstamp_prequeue)
 		net_timestamp_check(skb);
 
+	trace_netif_rx(skb);
 #ifdef CONFIG_RPS
 	{
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
@@ -2571,6 +2577,7 @@
 			clist = clist->next;
 
 			WARN_ON(atomic_read(&skb->users));
+			trace_kfree_skb(skb, net_tx_action);
 			__kfree_skb(skb);
 		}
 	}
@@ -2828,6 +2835,7 @@
 	if (!netdev_tstamp_prequeue)
 		net_timestamp_check(skb);
 
+	trace_netif_receive_skb(skb);
 	if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
 		return NET_RX_SUCCESS;
 
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index afa6380..7f1bb2a 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -26,6 +26,7 @@
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/skb.h>
+#include <trace/events/net.h>
 #include <trace/events/napi.h>
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c83b421..56ba3c4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -466,6 +466,7 @@
 		smp_rmb();
 	else if (likely(!atomic_dec_and_test(&skb->users)))
 		return;
+	trace_consume_skb(skb);
 	__kfree_skb(skb);
 }
 EXPORT_SYMBOL(consume_skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index ef30e9d..7d99e13 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1078,8 +1078,11 @@
 #ifdef CONFIG_CGROUPS
 void sock_update_classid(struct sock *sk)
 {
-	u32 classid = task_cls_classid(current);
+	u32 classid;
 
+	rcu_read_lock();  /* doing current task, which cannot vanish. */
+	classid = task_cls_classid(current);
+	rcu_read_unlock();
 	if (classid && classid != sk->sk_classid)
 		sk->sk_classid = classid;
 }
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 078e48d..33d0e62 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -149,6 +149,7 @@
 	.owner	 = THIS_MODULE,
 	.open	 = dccpprobe_open,
 	.read    = dccpprobe_read,
+	.llseek  = noop_llseek,
 };
 
 static __init int dccpprobe_init(void)
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 244f7cb..37f8adb 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -11,6 +11,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/percpu.h>
+#include <linux/security.h>
 #include <net/net_namespace.h>
 
 #include <linux/netfilter.h>
@@ -87,6 +88,29 @@
 	rcu_read_unlock();
 }
 
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+{
+	int ret;
+	u32 len;
+	char *secctx;
+
+	ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
+	if (ret)
+		return ret;
+
+	ret = seq_printf(s, "secctx=%s ", secctx);
+
+	security_release_secctx(secctx, len);
+	return ret;
+}
+#else
+static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+{
+	return 0;
+}
+#endif
+
 static int ct_seq_show(struct seq_file *s, void *v)
 {
 	struct nf_conntrack_tuple_hash *hash = v;
@@ -148,10 +172,8 @@
 		goto release;
 #endif
 
-#ifdef CONFIG_NF_CONNTRACK_SECMARK
-	if (seq_printf(s, "secmark=%u ", ct->secmark))
+	if (ct_show_secctx(s, ct))
 		goto release;
-#endif
 
 	if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
 		goto release;
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 8c8632d..957c924 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -38,7 +38,7 @@
 static struct nf_conntrack_l3proto *l3proto __read_mostly;
 
 #define MAX_IP_NAT_PROTO 256
-static const struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO]
+static const struct nf_nat_protocol __rcu *nf_nat_protos[MAX_IP_NAT_PROTO]
 						__read_mostly;
 
 static inline const struct nf_nat_protocol *
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index f8efada..6211e21 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -214,6 +214,7 @@
 	.owner	 = THIS_MODULE,
 	.open	 = tcpprobe_open,
 	.read    = tcpprobe_read,
+	.llseek  = noop_llseek,
 };
 
 static __init int tcpprobe_init(void)
diff --git a/net/ipx/Kconfig b/net/ipx/Kconfig
index e9ad006..02549cb 100644
--- a/net/ipx/Kconfig
+++ b/net/ipx/Kconfig
@@ -3,6 +3,7 @@
 #
 config IPX
 	tristate "The IPX protocol"
+	depends on BKL # should be fixable
 	select LLC
 	---help---
 	  This is support for the Novell networking protocol, IPX, commonly
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index a694c59..b8b0ae7 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -36,6 +36,7 @@
 static const struct file_operations name## _ops = {			\
 	.read = name## _read,						\
 	.open = mac80211_open_file_generic,				\
+	.llseek = generic_file_llseek,					\
 };
 
 #define DEBUGFS_ADD(name)						\
@@ -101,7 +102,8 @@
 static const struct file_operations tsf_ops = {
 	.read = tsf_read,
 	.write = tsf_write,
-	.open = mac80211_open_file_generic
+	.open = mac80211_open_file_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t reset_write(struct file *file, const char __user *user_buf,
@@ -120,6 +122,7 @@
 static const struct file_operations reset_ops = {
 	.write = reset_write,
 	.open = mac80211_open_file_generic,
+	.llseek = noop_llseek,
 };
 
 static ssize_t noack_read(struct file *file, char __user *user_buf,
@@ -155,7 +158,8 @@
 static const struct file_operations noack_ops = {
 	.read = noack_read,
 	.write = noack_write,
-	.open = mac80211_open_file_generic
+	.open = mac80211_open_file_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t uapsd_queues_read(struct file *file, char __user *user_buf,
@@ -201,7 +205,8 @@
 static const struct file_operations uapsd_queues_ops = {
 	.read = uapsd_queues_read,
 	.write = uapsd_queues_write,
-	.open = mac80211_open_file_generic
+	.open = mac80211_open_file_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t uapsd_max_sp_len_read(struct file *file, char __user *user_buf,
@@ -247,7 +252,8 @@
 static const struct file_operations uapsd_max_sp_len_ops = {
 	.read = uapsd_max_sp_len_read,
 	.write = uapsd_max_sp_len_write,
-	.open = mac80211_open_file_generic
+	.open = mac80211_open_file_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t channel_type_read(struct file *file, char __user *user_buf,
@@ -279,7 +285,8 @@
 
 static const struct file_operations channel_type_ops = {
 	.read = channel_type_read,
-	.open = mac80211_open_file_generic
+	.open = mac80211_open_file_generic,
+	.llseek = default_llseek,
 };
 
 static ssize_t queues_read(struct file *file, char __user *user_buf,
@@ -302,7 +309,8 @@
 
 static const struct file_operations queues_ops = {
 	.read = queues_read,
-	.open = mac80211_open_file_generic
+	.open = mac80211_open_file_generic,
+	.llseek = default_llseek,
 };
 
 /* statistics stuff */
@@ -346,6 +354,7 @@
 static const struct file_operations stats_ ##name## _ops = {		\
 	.read = stats_ ##name## _read,					\
 	.open = mac80211_open_file_generic,				\
+	.llseek = generic_file_llseek,					\
 };
 
 #define DEBUGFS_STATS_ADD(name, field)					\
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index fa5e76e..7cd8dd9 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -32,6 +32,7 @@
 static const struct file_operations key_ ##name## _ops = {		\
 	.read = key_##name##_read,					\
 	.open = mac80211_open_file_generic,				\
+	.llseek = generic_file_llseek,					\
 }
 
 #define KEY_FILE(name, format)						\
@@ -46,6 +47,7 @@
 static const struct file_operations key_ ##name## _ops = {		\
 	.read = key_conf_##name##_read,					\
 	.open = mac80211_open_file_generic,				\
+	.llseek = generic_file_llseek,					\
 }
 
 #define KEY_CONF_FILE(name, format)					\
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 20b2998..8ad33ee 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -121,6 +121,7 @@
 	.read = ieee80211_if_read_##name,				\
 	.write = (_write),						\
 	.open = mac80211_open_file_generic,				\
+	.llseek = generic_file_llseek,					\
 }
 
 #define __IEEE80211_IF_FILE_W(name)					\
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 76839d4..6a8fdc3 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -36,6 +36,7 @@
 static const struct file_operations sta_ ##name## _ops = {		\
 	.read = sta_##name##_read,					\
 	.open = mac80211_open_file_generic,				\
+	.llseek = generic_file_llseek,					\
 }
 
 #define STA_OPS_RW(name)						\
@@ -43,6 +44,7 @@
 	.read = sta_##name##_read,					\
 	.write = sta_##name##_write,					\
 	.open = mac80211_open_file_generic,				\
+	.llseek = generic_file_llseek,					\
 }
 
 #define STA_FILE(name, field, format)					\
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index be04d461..334cbd3 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -145,6 +145,7 @@
 static const struct file_operations rcname_ops = {
 	.read = rcname_read,
 	.open = mac80211_open_file_generic,
+	.llseek = default_llseek,
 };
 #endif
 
diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c
index 241e76f..a290ad23 100644
--- a/net/mac80211/rc80211_minstrel_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_debugfs.c
@@ -122,6 +122,7 @@
 	.open = minstrel_stats_open,
 	.read = minstrel_stats_read,
 	.release = minstrel_stats_release,
+	.llseek = default_llseek,
 };
 
 void
diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c
index 4a5a4b3..cefcb5d 100644
--- a/net/mac80211/rc80211_minstrel_ht_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c
@@ -90,7 +90,7 @@
 		MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10);
 	ms->len = p - ms->buf;
 
-	return 0;
+	return nonseekable_open(inode, file);
 }
 
 static const struct file_operations minstrel_ht_stat_fops = {
@@ -98,6 +98,7 @@
 	.open = minstrel_ht_stats_open,
 	.read = minstrel_stats_read,
 	.release = minstrel_stats_release,
+	.llseek = no_llseek,
 };
 
 void
diff --git a/net/mac80211/rc80211_pid_debugfs.c b/net/mac80211/rc80211_pid_debugfs.c
index 47438b4..7905f79 100644
--- a/net/mac80211/rc80211_pid_debugfs.c
+++ b/net/mac80211/rc80211_pid_debugfs.c
@@ -206,6 +206,7 @@
 	.poll = rate_control_pid_events_poll,
 	.open = rate_control_pid_events_open,
 	.release = rate_control_pid_events_release,
+	.llseek = noop_llseek,
 };
 
 void rate_control_pid_add_sta_debugfs(void *priv, void *priv_sta,
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 78b505d..fdaec7d 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -27,7 +27,7 @@
 
 static DEFINE_MUTEX(afinfo_mutex);
 
-const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
+const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
 EXPORT_SYMBOL(nf_afinfo);
 
 int nf_register_afinfo(const struct nf_afinfo *afinfo)
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index cdcc764..5702de3 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -26,10 +26,10 @@
 
 static DEFINE_MUTEX(nf_ct_ecache_mutex);
 
-struct nf_ct_event_notifier *nf_conntrack_event_cb __read_mostly;
+struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_event_cb);
 
-struct nf_exp_event_notifier *nf_expect_event_cb __read_mostly;
+struct nf_exp_event_notifier __rcu *nf_expect_event_cb __read_mostly;
 EXPORT_SYMBOL_GPL(nf_expect_event_cb);
 
 /* deliver cached events and clear cache entry - must be called with locally
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 8d9e4c94..bd82450 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -16,7 +16,7 @@
 #include <linux/skbuff.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 
-static struct nf_ct_ext_type *nf_ct_ext_types[NF_CT_EXT_NUM];
+static struct nf_ct_ext_type __rcu *nf_ct_ext_types[NF_CT_EXT_NUM];
 static DEFINE_MUTEX(nf_ct_ext_type_mutex);
 
 void __nf_ct_ext_destroy(struct nf_conn *ct)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 5bae1cd..146476c 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -22,6 +22,7 @@
 #include <linux/rculist_nulls.h>
 #include <linux/types.h>
 #include <linux/timer.h>
+#include <linux/security.h>
 #include <linux/skbuff.h>
 #include <linux/errno.h>
 #include <linux/netlink.h>
@@ -245,16 +246,31 @@
 
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
 static inline int
-ctnetlink_dump_secmark(struct sk_buff *skb, const struct nf_conn *ct)
+ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct)
 {
-	NLA_PUT_BE32(skb, CTA_SECMARK, htonl(ct->secmark));
-	return 0;
+	struct nlattr *nest_secctx;
+	int len, ret;
+	char *secctx;
 
+	ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
+	if (ret)
+		return ret;
+
+	ret = -1;
+	nest_secctx = nla_nest_start(skb, CTA_SECCTX | NLA_F_NESTED);
+	if (!nest_secctx)
+		goto nla_put_failure;
+
+	NLA_PUT_STRING(skb, CTA_SECCTX_NAME, secctx);
+	nla_nest_end(skb, nest_secctx);
+
+	ret = 0;
 nla_put_failure:
-	return -1;
+	security_release_secctx(secctx, len);
+	return ret;
 }
 #else
-#define ctnetlink_dump_secmark(a, b) (0)
+#define ctnetlink_dump_secctx(a, b) (0)
 #endif
 
 #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple)
@@ -391,7 +407,7 @@
 	    ctnetlink_dump_protoinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_helpinfo(skb, ct) < 0 ||
 	    ctnetlink_dump_mark(skb, ct) < 0 ||
-	    ctnetlink_dump_secmark(skb, ct) < 0 ||
+	    ctnetlink_dump_secctx(skb, ct) < 0 ||
 	    ctnetlink_dump_id(skb, ct) < 0 ||
 	    ctnetlink_dump_use(skb, ct) < 0 ||
 	    ctnetlink_dump_master(skb, ct) < 0 ||
@@ -437,6 +453,17 @@
 	       ;
 }
 
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+static int ctnetlink_nlmsg_secctx_size(const struct nf_conn *ct)
+{
+	int len;
+
+	security_secid_to_secctx(ct->secmark, NULL, &len);
+
+	return sizeof(char) * len;
+}
+#endif
+
 static inline size_t
 ctnetlink_nlmsg_size(const struct nf_conn *ct)
 {
@@ -453,7 +480,8 @@
 	       + nla_total_size(0) /* CTA_HELP */
 	       + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
-	       + nla_total_size(sizeof(u_int32_t)) /* CTA_SECMARK */
+	       + nla_total_size(0) /* CTA_SECCTX */
+	       + nla_total_size(ctnetlink_nlmsg_secctx_size(ct)) /* CTA_SECCTX_NAME */
 #endif
 #ifdef CONFIG_NF_NAT_NEEDED
 	       + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
@@ -556,7 +584,7 @@
 
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
 		if ((events & (1 << IPCT_SECMARK) || ct->secmark)
-		    && ctnetlink_dump_secmark(skb, ct) < 0)
+		    && ctnetlink_dump_secctx(skb, ct) < 0)
 			goto nla_put_failure;
 #endif
 
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 5886ba1..ed6d929 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -28,8 +28,8 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
 
-static struct nf_conntrack_l4proto **nf_ct_protos[PF_MAX] __read_mostly;
-struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX] __read_mostly;
+static struct nf_conntrack_l4proto __rcu **nf_ct_protos[PF_MAX] __read_mostly;
+struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX] __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_l3protos);
 
 static DEFINE_MUTEX(nf_ct_proto_mutex);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index eb973fc..0fb6570 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/percpu.h>
 #include <linux/netdevice.h>
+#include <linux/security.h>
 #include <net/net_namespace.h>
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
@@ -108,6 +109,29 @@
 	rcu_read_unlock();
 }
 
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+{
+	int ret;
+	u32 len;
+	char *secctx;
+
+	ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
+	if (ret)
+		return ret;
+
+	ret = seq_printf(s, "secctx=%s ", secctx);
+
+	security_release_secctx(secctx, len);
+	return ret;
+}
+#else
+static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+{
+	return 0;
+}
+#endif
+
 /* return 0 on success, 1 in case of error */
 static int ct_seq_show(struct seq_file *s, void *v)
 {
@@ -168,10 +192,8 @@
 		goto release;
 #endif
 
-#ifdef CONFIG_NF_CONNTRACK_SECMARK
-	if (seq_printf(s, "secmark=%u ", ct->secmark))
+	if (ct_show_secctx(s, ct))
 		goto release;
-#endif
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	if (seq_printf(s, "zone=%u ", nf_ct_zone(ct)))
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 7df37fd..b07393e 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -16,7 +16,7 @@
 #define NF_LOG_PREFIXLEN		128
 #define NFLOGGER_NAME_LEN		64
 
-static const struct nf_logger *nf_loggers[NFPROTO_NUMPROTO] __read_mostly;
+static const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO] __read_mostly;
 static struct list_head nf_loggers_l[NFPROTO_NUMPROTO] __read_mostly;
 static DEFINE_MUTEX(nf_log_mutex);
 
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 78b3cf9c..74aebed5 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -18,7 +18,7 @@
  * long term mutex.  The handler must provide an an outfn() to accept packets
  * for queueing and must reinject all packets it receives, no matter what.
  */
-static const struct nf_queue_handler *queue_handler[NFPROTO_NUMPROTO] __read_mostly;
+static const struct nf_queue_handler __rcu *queue_handler[NFPROTO_NUMPROTO] __read_mostly;
 
 static DEFINE_MUTEX(queue_handler_mutex);
 
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 0cb6053..782e5198 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/skbuff.h>
-#include <linux/selinux.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <linux/netfilter/x_tables.h>
diff --git a/net/netfilter/xt_SECMARK.c b/net/netfilter/xt_SECMARK.c
index 23b2d6c..9faf5e0 100644
--- a/net/netfilter/xt_SECMARK.c
+++ b/net/netfilter/xt_SECMARK.c
@@ -14,8 +14,8 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/module.h>
+#include <linux/security.h>
 #include <linux/skbuff.h>
-#include <linux/selinux.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_SECMARK.h>
 
@@ -39,9 +39,8 @@
 
 	switch (mode) {
 	case SECMARK_MODE_SEL:
-		secmark = info->u.sel.selsid;
+		secmark = info->secid;
 		break;
-
 	default:
 		BUG();
 	}
@@ -50,33 +49,33 @@
 	return XT_CONTINUE;
 }
 
-static int checkentry_selinux(struct xt_secmark_target_info *info)
+static int checkentry_lsm(struct xt_secmark_target_info *info)
 {
 	int err;
-	struct xt_secmark_target_selinux_info *sel = &info->u.sel;
 
-	sel->selctx[SECMARK_SELCTX_MAX - 1] = '\0';
+	info->secctx[SECMARK_SECCTX_MAX - 1] = '\0';
+	info->secid = 0;
 
-	err = selinux_string_to_sid(sel->selctx, &sel->selsid);
+	err = security_secctx_to_secid(info->secctx, strlen(info->secctx),
+				       &info->secid);
 	if (err) {
 		if (err == -EINVAL)
-			pr_info("invalid SELinux context \'%s\'\n",
-				sel->selctx);
+			pr_info("invalid security context \'%s\'\n", info->secctx);
 		return err;
 	}
 
-	if (!sel->selsid) {
-		pr_info("unable to map SELinux context \'%s\'\n", sel->selctx);
+	if (!info->secid) {
+		pr_info("unable to map security context \'%s\'\n", info->secctx);
 		return -ENOENT;
 	}
 
-	err = selinux_secmark_relabel_packet_permission(sel->selsid);
+	err = security_secmark_relabel_packet(info->secid);
 	if (err) {
 		pr_info("unable to obtain relabeling permission\n");
 		return err;
 	}
 
-	selinux_secmark_refcount_inc();
+	security_secmark_refcount_inc();
 	return 0;
 }
 
@@ -100,16 +99,16 @@
 
 	switch (info->mode) {
 	case SECMARK_MODE_SEL:
-		err = checkentry_selinux(info);
-		if (err <= 0)
-			return err;
 		break;
-
 	default:
 		pr_info("invalid mode: %hu\n", info->mode);
 		return -EINVAL;
 	}
 
+	err = checkentry_lsm(info);
+	if (err)
+		return err;
+
 	if (!mode)
 		mode = info->mode;
 	return 0;
@@ -119,7 +118,7 @@
 {
 	switch (mode) {
 	case SECMARK_MODE_SEL:
-		selinux_secmark_refcount_dec();
+		security_secmark_refcount_dec();
 	}
 }
 
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 76aec6a..d2ff15a 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -567,6 +567,7 @@
 	.write   = recent_mt_proc_write,
 	.release = seq_release_private,
 	.owner   = THIS_MODULE,
+	.llseek = seq_lseek,
 };
 
 static int __net_init recent_proc_net_init(struct net *net)
diff --git a/net/nonet.c b/net/nonet.c
index 92e7664..b1a73fd 100644
--- a/net/nonet.c
+++ b/net/nonet.c
@@ -22,4 +22,5 @@
 const struct file_operations bad_sock_fops = {
 	.owner = THIS_MODULE,
 	.open = sock_no_open,
+	.llseek = noop_llseek,
 };
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 51875a0..04f5990 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -1241,6 +1241,7 @@
 	.unlocked_ioctl	= rfkill_fop_ioctl,
 	.compat_ioctl	= rfkill_fop_ioctl,
 #endif
+	.llseek		= no_llseek,
 };
 
 static struct miscdevice rfkill_miscdev = {
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 78ef2c5..37dff78 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -123,7 +123,7 @@
 	 * calls by looking at the number of nested bh disable calls because
 	 * softirqs always disables bh.
 	 */
-	if (softirq_count() != SOFTIRQ_OFFSET) {
+	if (in_serving_softirq()) {
 		/* If there is an sk_classid we'll use that. */
 		if (!skb->sk)
 			return -1;
diff --git a/net/sctp/probe.c b/net/sctp/probe.c
index db3a42b..289b1ba 100644
--- a/net/sctp/probe.c
+++ b/net/sctp/probe.c
@@ -117,6 +117,7 @@
 	.owner	= THIS_MODULE,
 	.open	= sctpprobe_open,
 	.read	= sctpprobe_read,
+	.llseek = noop_llseek,
 };
 
 sctp_disposition_t jsctp_sf_eat_sack(const struct sctp_endpoint *ep,
diff --git a/net/socket.c b/net/socket.c
index 2270b94..9eac5c3 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -502,6 +502,7 @@
 const struct file_operations bad_sock_fops = {
 	.owner = THIS_MODULE,
 	.open = sock_no_open,
+	.llseek = noop_llseek,
 };
 
 /**
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 2b06410..7dce81a 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -28,7 +28,6 @@
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <asm/ioctls.h>
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/cache.h>
@@ -1348,15 +1347,10 @@
 static long cache_ioctl_procfs(struct file *filp,
 			       unsigned int cmd, unsigned long arg)
 {
-	long ret;
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct cache_detail *cd = PDE(inode)->data;
 
-	lock_kernel();
-	ret = cache_ioctl(inode, filp, cmd, arg, cd);
-	unlock_kernel();
-
-	return ret;
+	return cache_ioctl(inode, filp, cmd, arg, cd);
 }
 
 static int cache_open_procfs(struct inode *inode, struct file *filp)
@@ -1441,6 +1435,7 @@
 	.read		= read_flush_procfs,
 	.write		= write_flush_procfs,
 	.release	= release_flush_procfs,
+	.llseek		= no_llseek,
 };
 
 static void remove_cache_proc_entries(struct cache_detail *cd)
@@ -1555,13 +1550,8 @@
 {
 	struct inode *inode = filp->f_dentry->d_inode;
 	struct cache_detail *cd = RPC_I(inode)->private;
-	long ret;
 
-	lock_kernel();
-	ret = cache_ioctl(inode, filp, cmd, arg, cd);
-	unlock_kernel();
-
-	return ret;
+	return cache_ioctl(inode, filp, cmd, arg, cd);
 }
 
 static int cache_open_pipefs(struct inode *inode, struct file *filp)
@@ -1646,6 +1636,7 @@
 	.read		= read_flush_pipefs,
 	.write		= write_flush_pipefs,
 	.release	= release_flush_pipefs,
+	.llseek		= no_llseek,
 };
 
 int sunrpc_cache_register_pipefs(struct dentry *parent,
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 8c8eef2..28bcd52 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -27,7 +27,6 @@
 #include <linux/workqueue.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/sunrpc/cache.h>
-#include <linux/smp_lock.h>
 
 static struct vfsmount *rpc_mount __read_mostly;
 static int rpc_mount_count;
@@ -309,40 +308,33 @@
 	return mask;
 }
 
-static int
-rpc_pipe_ioctl_unlocked(struct file *filp, unsigned int cmd, unsigned long arg)
+static long
+rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
-	struct rpc_inode *rpci = RPC_I(filp->f_path.dentry->d_inode);
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct rpc_inode *rpci = RPC_I(inode);
 	int len;
 
 	switch (cmd) {
 	case FIONREAD:
-		if (rpci->ops == NULL)
+		spin_lock(&inode->i_lock);
+		if (rpci->ops == NULL) {
+			spin_unlock(&inode->i_lock);
 			return -EPIPE;
+		}
 		len = rpci->pipelen;
 		if (filp->private_data) {
 			struct rpc_pipe_msg *msg;
 			msg = (struct rpc_pipe_msg *)filp->private_data;
 			len += msg->len - msg->copied;
 		}
+		spin_unlock(&inode->i_lock);
 		return put_user(len, (int __user *)arg);
 	default:
 		return -EINVAL;
 	}
 }
 
-static long
-rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
-{
-	long ret;
-
-	lock_kernel();
-	ret = rpc_pipe_ioctl_unlocked(filp, cmd, arg);
-	unlock_kernel();
-
-	return ret;
-}
-
 static const struct file_operations rpc_pipe_fops = {
 	.owner		= THIS_MODULE,
 	.llseek		= no_llseek,
diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
index a4991a3..39765bc 100644
--- a/net/wireless/debugfs.c
+++ b/net/wireless/debugfs.c
@@ -34,6 +34,7 @@
 static const struct file_operations name## _ops = {			\
 	.read = name## _read,						\
 	.open = cfg80211_open_file_generic,				\
+	.llseek = generic_file_llseek,					\
 };
 
 DEBUGFS_READONLY_FILE(rts_threshold, 20, "%d",
@@ -102,6 +103,7 @@
 static const struct file_operations ht40allow_map_ops = {
 	.read = ht40allow_map_read,
 	.open = cfg80211_open_file_generic,
+	.llseek = default_llseek,
 };
 
 #define DEBUGFS_ADD(name)						\
diff --git a/net/x25/Kconfig b/net/x25/Kconfig
index e6759c9..2196e55 100644
--- a/net/x25/Kconfig
+++ b/net/x25/Kconfig
@@ -5,6 +5,7 @@
 config X25
 	tristate "CCITT X.25 Packet Layer (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
+	depends on BKL # should be fixable
 	---help---
 	  X.25 is a set of standardized network protocols, similar in scope to
 	  frame relay; the one physical line from your box to the X.25 network
diff --git a/samples/kfifo/bytestream-example.c b/samples/kfifo/bytestream-example.c
index 178061e..cfe40ad 100644
--- a/samples/kfifo/bytestream-example.c
+++ b/samples/kfifo/bytestream-example.c
@@ -148,6 +148,7 @@
 	.owner		= THIS_MODULE,
 	.read		= fifo_read,
 	.write		= fifo_write,
+	.llseek		= noop_llseek,
 };
 
 static int __init example_init(void)
diff --git a/samples/kfifo/inttype-example.c b/samples/kfifo/inttype-example.c
index 71b2aab..6f8e79e 100644
--- a/samples/kfifo/inttype-example.c
+++ b/samples/kfifo/inttype-example.c
@@ -141,6 +141,7 @@
 	.owner		= THIS_MODULE,
 	.read		= fifo_read,
 	.write		= fifo_write,
+	.llseek		= noop_llseek,
 };
 
 static int __init example_init(void)
diff --git a/samples/kfifo/record-example.c b/samples/kfifo/record-example.c
index e68bd16..2d7529e 100644
--- a/samples/kfifo/record-example.c
+++ b/samples/kfifo/record-example.c
@@ -155,6 +155,7 @@
 	.owner		= THIS_MODULE,
 	.read		= fifo_read,
 	.write		= fifo_write,
+	.llseek		= noop_llseek,
 };
 
 static int __init example_init(void)
diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c
index 26fab33..f4d89e0 100644
--- a/samples/tracepoints/tracepoint-sample.c
+++ b/samples/tracepoints/tracepoint-sample.c
@@ -30,6 +30,7 @@
 
 static const struct file_operations mark_ops = {
 	.open = my_open,
+	.llseek = noop_llseek,
 };
 
 static int __init sample_init(void)
diff --git a/scripts/Makefile b/scripts/Makefile
index 842dbc2..2e08810 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -11,6 +11,7 @@
 hostprogs-$(CONFIG_LOGO)         += pnmtologo
 hostprogs-$(CONFIG_VT)           += conmakehash
 hostprogs-$(CONFIG_IKCONFIG)     += bin2c
+hostprogs-$(BUILD_C_RECORDMCOUNT) += recordmcount
 
 always		:= $(hostprogs-y) $(hostprogs-m)
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index a1a5cf9..5ad25e1 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -209,12 +209,23 @@
 endif
 
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
+ifdef BUILD_C_RECORDMCOUNT
+# Due to recursion, we must skip empty.o.
+# The empty.o file is created in the make process in order to determine
+#  the target endianness and word size. It is made before all other C
+#  files, including recordmcount.
+cmd_record_mcount = if [ $(@) != "scripts/mod/empty.o" ]; then			\
+			$(objtree)/scripts/recordmcount "$(@)";			\
+		    fi;
+else
 cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
 	"$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \
 	"$(if $(CONFIG_64BIT),64,32)" \
-	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" \
+	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CFLAGS)" \
+	"$(LD)" "$(NM)" "$(RM)" "$(MV)" \
 	"$(if $(part-of-module),1,0)" "$(@)";
 endif
+endif
 
 define rule_cc_o_c
 	$(call echo-cmd,checksrc) $(cmd_checksrc)			  \
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 54fd1b7..7bfcf1a 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -101,14 +101,6 @@
 modname_flags  = $(if $(filter 1,$(words $(modname))),\
                  -D"KBUILD_MODNAME=KBUILD_STR($(call name-fix,$(modname)))")
 
-#hash values
-ifdef CONFIG_DYNAMIC_DEBUG
-debug_flags = -D"DEBUG_HASH=$(shell ./scripts/basic/hash djb2 $(@D)$(modname))"\
-              -D"DEBUG_HASH2=$(shell ./scripts/basic/hash r5 $(@D)$(modname))"
-else
-debug_flags =
-endif
-
 orig_c_flags   = $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(KBUILD_SUBDIR_CCFLAGS) \
                  $(ccflags-y) $(CFLAGS_$(basetarget).o)
 _c_flags       = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(orig_c_flags))
@@ -152,8 +144,7 @@
 
 c_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(__c_flags) $(modkern_cflags)                           \
-		 -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags) \
-		  $(debug_flags)
+		 -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags)
 
 a_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(__a_flags) $(modkern_aflags)
diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile
index 0955995..4c324a1 100644
--- a/scripts/basic/Makefile
+++ b/scripts/basic/Makefile
@@ -9,7 +9,7 @@
 # fixdep: 	 Used to generate dependency information during build process
 # docproc:	 Used in Documentation/DocBook
 
-hostprogs-y	:= fixdep docproc hash
+hostprogs-y	:= fixdep docproc
 always		:= $(hostprogs-y)
 
 # fixdep is needed to compile other host programs
diff --git a/scripts/basic/hash.c b/scripts/basic/hash.c
deleted file mode 100644
index 2ef5d3f..0000000
--- a/scripts/basic/hash.c
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * Copyright (C) 2008 Red Hat, Inc., Jason Baron <jbaron@redhat.com>
- *
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-#define DYNAMIC_DEBUG_HASH_BITS 6
-
-static const char *program;
-
-static void usage(void)
-{
-	printf("Usage: %s <djb2|r5> <modname>\n", program);
-	exit(1);
-}
-
-/* djb2 hashing algorithm by Dan Bernstein. From:
- * http://www.cse.yorku.ca/~oz/hash.html
- */
-
-static unsigned int djb2_hash(char *str)
-{
-	unsigned long hash = 5381;
-	int c;
-
-	c = *str;
-	while (c) {
-		hash = ((hash << 5) + hash) + c;
-		c = *++str;
-	}
-	return (unsigned int)(hash & ((1 << DYNAMIC_DEBUG_HASH_BITS) - 1));
-}
-
-static unsigned int r5_hash(char *str)
-{
-	unsigned long hash = 0;
-	int c;
-
-	c = *str;
-	while (c) {
-		hash = (hash + (c << 4) + (c >> 4)) * 11;
-		c = *++str;
-	}
-	return (unsigned int)(hash & ((1 << DYNAMIC_DEBUG_HASH_BITS) - 1));
-}
-
-int main(int argc, char *argv[])
-{
-	program = argv[0];
-
-	if (argc != 3)
-		usage();
-	if (!strcmp(argv[1], "djb2"))
-		printf("%d\n", djb2_hash(argv[2]));
-	else if (!strcmp(argv[1], "r5"))
-		printf("%d\n", r5_hash(argv[2]));
-	else
-		usage();
-	exit(0);
-}
-
diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh
new file mode 100644
index 0000000..520d16b
--- /dev/null
+++ b/scripts/gcc-goto.sh
@@ -0,0 +1,5 @@
+#!/bin/sh
+# Test for gcc 'asm goto' suport
+# Copyright (C) 2010, Jason Baron <jbaron@redhat.com>
+
+echo "int main(void) { entry: asm goto (\"\"::::entry); return 0; }" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
new file mode 100644
index 0000000..26e1271
--- /dev/null
+++ b/scripts/recordmcount.c
@@ -0,0 +1,363 @@
+/*
+ * recordmcount.c: construct a table of the locations of calls to 'mcount'
+ * so that ftrace can find them quickly.
+ * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>.  All rights reserved.
+ * Licensed under the GNU General Public License, version 2 (GPLv2).
+ *
+ * Restructured to fit Linux format, as well as other updates:
+ *  Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+ */
+
+/*
+ * Strategy: alter the .o file in-place.
+ *
+ * Append a new STRTAB that has the new section names, followed by a new array
+ * ElfXX_Shdr[] that has the new section headers, followed by the section
+ * contents for __mcount_loc and its relocations.  The old shstrtab strings,
+ * and the old ElfXX_Shdr[] array, remain as "garbage" (commonly, a couple
+ * kilobytes.)  Subsequent processing by /bin/ld (or the kernel module loader)
+ * will ignore the garbage regions, because they are not designated by the
+ * new .e_shoff nor the new ElfXX_Shdr[].  [In order to remove the garbage,
+ * then use "ld -r" to create a new file that omits the garbage.]
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <elf.h>
+#include <fcntl.h>
+#include <setjmp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+static int fd_map;	/* File descriptor for file being modified. */
+static int mmap_failed; /* Boolean flag. */
+static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
+static char gpfx;	/* prefix for global symbol name (sometimes '_') */
+static struct stat sb;	/* Remember .st_size, etc. */
+static jmp_buf jmpenv;	/* setjmp/longjmp per-file error escape */
+
+/* setjmp() return values */
+enum {
+	SJ_SETJMP = 0,  /* hardwired first return */
+	SJ_FAIL,
+	SJ_SUCCEED
+};
+
+/* Per-file resource cleanup when multiple files. */
+static void
+cleanup(void)
+{
+	if (!mmap_failed)
+		munmap(ehdr_curr, sb.st_size);
+	else
+		free(ehdr_curr);
+	close(fd_map);
+}
+
+static void __attribute__((noreturn))
+fail_file(void)
+{
+	cleanup();
+	longjmp(jmpenv, SJ_FAIL);
+}
+
+static void __attribute__((noreturn))
+succeed_file(void)
+{
+	cleanup();
+	longjmp(jmpenv, SJ_SUCCEED);
+}
+
+/* ulseek, uread, ...:  Check return value for errors. */
+
+static off_t
+ulseek(int const fd, off_t const offset, int const whence)
+{
+	off_t const w = lseek(fd, offset, whence);
+	if ((off_t)-1 == w) {
+		perror("lseek");
+		fail_file();
+	}
+	return w;
+}
+
+static size_t
+uread(int const fd, void *const buf, size_t const count)
+{
+	size_t const n = read(fd, buf, count);
+	if (n != count) {
+		perror("read");
+		fail_file();
+	}
+	return n;
+}
+
+static size_t
+uwrite(int const fd, void const *const buf, size_t const count)
+{
+	size_t const n = write(fd, buf, count);
+	if (n != count) {
+		perror("write");
+		fail_file();
+	}
+	return n;
+}
+
+static void *
+umalloc(size_t size)
+{
+	void *const addr = malloc(size);
+	if (0 == addr) {
+		fprintf(stderr, "malloc failed: %zu bytes\n", size);
+		fail_file();
+	}
+	return addr;
+}
+
+/*
+ * Get the whole file as a programming convenience in order to avoid
+ * malloc+lseek+read+free of many pieces.  If successful, then mmap
+ * avoids copying unused pieces; else just read the whole file.
+ * Open for both read and write; new info will be appended to the file.
+ * Use MAP_PRIVATE so that a few changes to the in-memory ElfXX_Ehdr
+ * do not propagate to the file until an explicit overwrite at the last.
+ * This preserves most aspects of consistency (all except .st_size)
+ * for simultaneous readers of the file while we are appending to it.
+ * However, multiple writers still are bad.  We choose not to use
+ * locking because it is expensive and the use case of kernel build
+ * makes multiple writers unlikely.
+ */
+static void *mmap_file(char const *fname)
+{
+	void *addr;
+
+	fd_map = open(fname, O_RDWR);
+	if (0 > fd_map || 0 > fstat(fd_map, &sb)) {
+		perror(fname);
+		fail_file();
+	}
+	if (!S_ISREG(sb.st_mode)) {
+		fprintf(stderr, "not a regular file: %s\n", fname);
+		fail_file();
+	}
+	addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE,
+		    fd_map, 0);
+	mmap_failed = 0;
+	if (MAP_FAILED == addr) {
+		mmap_failed = 1;
+		addr = umalloc(sb.st_size);
+		uread(fd_map, addr, sb.st_size);
+	}
+	return addr;
+}
+
+/* w8rev, w8nat, ...: Handle endianness. */
+
+static uint64_t w8rev(uint64_t const x)
+{
+	return   ((0xff & (x >> (0 * 8))) << (7 * 8))
+	       | ((0xff & (x >> (1 * 8))) << (6 * 8))
+	       | ((0xff & (x >> (2 * 8))) << (5 * 8))
+	       | ((0xff & (x >> (3 * 8))) << (4 * 8))
+	       | ((0xff & (x >> (4 * 8))) << (3 * 8))
+	       | ((0xff & (x >> (5 * 8))) << (2 * 8))
+	       | ((0xff & (x >> (6 * 8))) << (1 * 8))
+	       | ((0xff & (x >> (7 * 8))) << (0 * 8));
+}
+
+static uint32_t w4rev(uint32_t const x)
+{
+	return   ((0xff & (x >> (0 * 8))) << (3 * 8))
+	       | ((0xff & (x >> (1 * 8))) << (2 * 8))
+	       | ((0xff & (x >> (2 * 8))) << (1 * 8))
+	       | ((0xff & (x >> (3 * 8))) << (0 * 8));
+}
+
+static uint32_t w2rev(uint16_t const x)
+{
+	return   ((0xff & (x >> (0 * 8))) << (1 * 8))
+	       | ((0xff & (x >> (1 * 8))) << (0 * 8));
+}
+
+static uint64_t w8nat(uint64_t const x)
+{
+	return x;
+}
+
+static uint32_t w4nat(uint32_t const x)
+{
+	return x;
+}
+
+static uint32_t w2nat(uint16_t const x)
+{
+	return x;
+}
+
+static uint64_t (*w8)(uint64_t);
+static uint32_t (*w)(uint32_t);
+static uint32_t (*w2)(uint16_t);
+
+/* Names of the sections that could contain calls to mcount. */
+static int
+is_mcounted_section_name(char const *const txtname)
+{
+	return 0 == strcmp(".text",          txtname) ||
+		0 == strcmp(".sched.text",    txtname) ||
+		0 == strcmp(".spinlock.text", txtname) ||
+		0 == strcmp(".irqentry.text", txtname) ||
+		0 == strcmp(".text.unlikely", txtname);
+}
+
+/* 32 bit and 64 bit are very similar */
+#include "recordmcount.h"
+#define RECORD_MCOUNT_64
+#include "recordmcount.h"
+
+static void
+do_file(char const *const fname)
+{
+	Elf32_Ehdr *const ehdr = mmap_file(fname);
+	unsigned int reltype = 0;
+
+	ehdr_curr = ehdr;
+	w = w4nat;
+	w2 = w2nat;
+	w8 = w8nat;
+	switch (ehdr->e_ident[EI_DATA]) {
+		static unsigned int const endian = 1;
+	default: {
+		fprintf(stderr, "unrecognized ELF data encoding %d: %s\n",
+			ehdr->e_ident[EI_DATA], fname);
+		fail_file();
+	} break;
+	case ELFDATA2LSB: {
+		if (1 != *(unsigned char const *)&endian) {
+			/* main() is big endian, file.o is little endian. */
+			w = w4rev;
+			w2 = w2rev;
+			w8 = w8rev;
+		}
+	} break;
+	case ELFDATA2MSB: {
+		if (0 != *(unsigned char const *)&endian) {
+			/* main() is little endian, file.o is big endian. */
+			w = w4rev;
+			w2 = w2rev;
+			w8 = w8rev;
+		}
+	} break;
+	}  /* end switch */
+	if (0 != memcmp(ELFMAG, ehdr->e_ident, SELFMAG)
+	||  ET_REL != w2(ehdr->e_type)
+	||  EV_CURRENT != ehdr->e_ident[EI_VERSION]) {
+		fprintf(stderr, "unrecognized ET_REL file %s\n", fname);
+		fail_file();
+	}
+
+	gpfx = 0;
+	switch (w2(ehdr->e_machine)) {
+	default: {
+		fprintf(stderr, "unrecognized e_machine %d %s\n",
+			w2(ehdr->e_machine), fname);
+		fail_file();
+	} break;
+	case EM_386:	 reltype = R_386_32;                   break;
+	case EM_ARM:	 reltype = R_ARM_ABS32;                break;
+	case EM_IA_64:	 reltype = R_IA64_IMM64;   gpfx = '_'; break;
+	case EM_PPC:	 reltype = R_PPC_ADDR32;   gpfx = '_'; break;
+	case EM_PPC64:	 reltype = R_PPC64_ADDR64; gpfx = '_'; break;
+	case EM_S390:    /* reltype: e_class    */ gpfx = '_'; break;
+	case EM_SH:	 reltype = R_SH_DIR32;                 break;
+	case EM_SPARCV9: reltype = R_SPARC_64;     gpfx = '_'; break;
+	case EM_X86_64:	 reltype = R_X86_64_64;                break;
+	}  /* end switch */
+
+	switch (ehdr->e_ident[EI_CLASS]) {
+	default: {
+		fprintf(stderr, "unrecognized ELF class %d %s\n",
+			ehdr->e_ident[EI_CLASS], fname);
+		fail_file();
+	} break;
+	case ELFCLASS32: {
+		if (sizeof(Elf32_Ehdr) != w2(ehdr->e_ehsize)
+		||  sizeof(Elf32_Shdr) != w2(ehdr->e_shentsize)) {
+			fprintf(stderr,
+				"unrecognized ET_REL file: %s\n", fname);
+			fail_file();
+		}
+		if (EM_S390 == w2(ehdr->e_machine))
+			reltype = R_390_32;
+		do32(ehdr, fname, reltype);
+	} break;
+	case ELFCLASS64: {
+		Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr;
+		if (sizeof(Elf64_Ehdr) != w2(ghdr->e_ehsize)
+		||  sizeof(Elf64_Shdr) != w2(ghdr->e_shentsize)) {
+			fprintf(stderr,
+				"unrecognized ET_REL file: %s\n", fname);
+			fail_file();
+		}
+		if (EM_S390 == w2(ghdr->e_machine))
+			reltype = R_390_64;
+		do64(ghdr, fname, reltype);
+	} break;
+	}  /* end switch */
+
+	cleanup();
+}
+
+int
+main(int argc, char const *argv[])
+{
+	const char ftrace[] = "kernel/trace/ftrace.o";
+	int ftrace_size = sizeof(ftrace) - 1;
+	int n_error = 0;  /* gcc-4.3.0 false positive complaint */
+
+	if (argc <= 1) {
+		fprintf(stderr, "usage: recordmcount file.o...\n");
+		return 0;
+	}
+
+	/* Process each file in turn, allowing deep failure. */
+	for (--argc, ++argv; 0 < argc; --argc, ++argv) {
+		int const sjval = setjmp(jmpenv);
+		int len;
+
+		/*
+		 * The file kernel/trace/ftrace.o references the mcount
+		 * function but does not call it. Since ftrace.o should
+		 * not be traced anyway, we just skip it.
+		 */
+		len = strlen(argv[0]);
+		if (len >= ftrace_size &&
+		    strcmp(argv[0] + (len - ftrace_size), ftrace) == 0)
+			continue;
+
+		switch (sjval) {
+		default: {
+			fprintf(stderr, "internal error: %s\n", argv[0]);
+			exit(1);
+		} break;
+		case SJ_SETJMP: {  /* normal sequence */
+			/* Avoid problems if early cleanup() */
+			fd_map = -1;
+			ehdr_curr = NULL;
+			mmap_failed = 1;
+			do_file(argv[0]);
+		} break;
+		case SJ_FAIL: {  /* error in do_file or below */
+			++n_error;
+		} break;
+		case SJ_SUCCEED: {  /* premature success */
+			/* do nothing */
+		} break;
+		}  /* end switch */
+	}
+	return !!n_error;
+}
+
+
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
new file mode 100644
index 0000000..7f39d09
--- /dev/null
+++ b/scripts/recordmcount.h
@@ -0,0 +1,366 @@
+/*
+ * recordmcount.h
+ *
+ * This code was taken out of recordmcount.c written by
+ * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>.  All rights reserved.
+ *
+ * The original code had the same algorithms for both 32bit
+ * and 64bit ELF files, but the code was duplicated to support
+ * the difference in structures that were used. This
+ * file creates a macro of everything that is different between
+ * the 64 and 32 bit code, such that by including this header
+ * twice we can create both sets of functions by including this
+ * header once with RECORD_MCOUNT_64 undefined, and again with
+ * it defined.
+ *
+ * This conversion to macros was done by:
+ * Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc.
+ *
+ * Licensed under the GNU General Public License, version 2 (GPLv2).
+ */
+#undef append_func
+#undef sift_rel_mcount
+#undef find_secsym_ndx
+#undef __has_rel_mcount
+#undef has_rel_mcount
+#undef tot_relsize
+#undef do_func
+#undef Elf_Ehdr
+#undef Elf_Shdr
+#undef Elf_Rel
+#undef Elf_Rela
+#undef Elf_Sym
+#undef ELF_R_SYM
+#undef ELF_R_INFO
+#undef ELF_ST_BIND
+#undef uint_t
+#undef _w
+#undef _align
+#undef _size
+
+#ifdef RECORD_MCOUNT_64
+# define append_func		append64
+# define sift_rel_mcount	sift64_rel_mcount
+# define find_secsym_ndx	find64_secsym_ndx
+# define __has_rel_mcount	__has64_rel_mcount
+# define has_rel_mcount		has64_rel_mcount
+# define tot_relsize		tot64_relsize
+# define do_func		do64
+# define Elf_Ehdr		Elf64_Ehdr
+# define Elf_Shdr		Elf64_Shdr
+# define Elf_Rel		Elf64_Rel
+# define Elf_Rela		Elf64_Rela
+# define Elf_Sym		Elf64_Sym
+# define ELF_R_SYM		ELF64_R_SYM
+# define ELF_R_INFO		ELF64_R_INFO
+# define ELF_ST_BIND		ELF64_ST_BIND
+# define uint_t			uint64_t
+# define _w			w8
+# define _align			7u
+# define _size			8
+#else
+# define append_func		append32
+# define sift_rel_mcount	sift32_rel_mcount
+# define find_secsym_ndx	find32_secsym_ndx
+# define __has_rel_mcount	__has32_rel_mcount
+# define has_rel_mcount		has32_rel_mcount
+# define tot_relsize		tot32_relsize
+# define do_func		do32
+# define Elf_Ehdr		Elf32_Ehdr
+# define Elf_Shdr		Elf32_Shdr
+# define Elf_Rel		Elf32_Rel
+# define Elf_Rela		Elf32_Rela
+# define Elf_Sym		Elf32_Sym
+# define ELF_R_SYM		ELF32_R_SYM
+# define ELF_R_INFO		ELF32_R_INFO
+# define ELF_ST_BIND		ELF32_ST_BIND
+# define uint_t			uint32_t
+# define _w			w
+# define _align			3u
+# define _size			4
+#endif
+
+/* Append the new shstrtab, Elf_Shdr[], __mcount_loc and its relocations. */
+static void append_func(Elf_Ehdr *const ehdr,
+			Elf_Shdr *const shstr,
+			uint_t const *const mloc0,
+			uint_t const *const mlocp,
+			Elf_Rel const *const mrel0,
+			Elf_Rel const *const mrelp,
+			unsigned int const rel_entsize,
+			unsigned int const symsec_sh_link)
+{
+	/* Begin constructing output file */
+	Elf_Shdr mcsec;
+	char const *mc_name = (sizeof(Elf_Rela) == rel_entsize)
+		? ".rela__mcount_loc"
+		:  ".rel__mcount_loc";
+	unsigned const old_shnum = w2(ehdr->e_shnum);
+	uint_t const old_shoff = _w(ehdr->e_shoff);
+	uint_t const old_shstr_sh_size   = _w(shstr->sh_size);
+	uint_t const old_shstr_sh_offset = _w(shstr->sh_offset);
+	uint_t t = 1 + strlen(mc_name) + _w(shstr->sh_size);
+	uint_t new_e_shoff;
+
+	shstr->sh_size = _w(t);
+	shstr->sh_offset = _w(sb.st_size);
+	t += sb.st_size;
+	t += (_align & -t);  /* word-byte align */
+	new_e_shoff = t;
+
+	/* body for new shstrtab */
+	ulseek(fd_map, sb.st_size, SEEK_SET);
+	uwrite(fd_map, old_shstr_sh_offset + (void *)ehdr, old_shstr_sh_size);
+	uwrite(fd_map, mc_name, 1 + strlen(mc_name));
+
+	/* old(modified) Elf_Shdr table, word-byte aligned */
+	ulseek(fd_map, t, SEEK_SET);
+	t += sizeof(Elf_Shdr) * old_shnum;
+	uwrite(fd_map, old_shoff + (void *)ehdr,
+	       sizeof(Elf_Shdr) * old_shnum);
+
+	/* new sections __mcount_loc and .rel__mcount_loc */
+	t += 2*sizeof(mcsec);
+	mcsec.sh_name = w((sizeof(Elf_Rela) == rel_entsize) + strlen(".rel")
+		+ old_shstr_sh_size);
+	mcsec.sh_type = w(SHT_PROGBITS);
+	mcsec.sh_flags = _w(SHF_ALLOC);
+	mcsec.sh_addr = 0;
+	mcsec.sh_offset = _w(t);
+	mcsec.sh_size = _w((void *)mlocp - (void *)mloc0);
+	mcsec.sh_link = 0;
+	mcsec.sh_info = 0;
+	mcsec.sh_addralign = _w(_size);
+	mcsec.sh_entsize = _w(_size);
+	uwrite(fd_map, &mcsec, sizeof(mcsec));
+
+	mcsec.sh_name = w(old_shstr_sh_size);
+	mcsec.sh_type = (sizeof(Elf_Rela) == rel_entsize)
+		? w(SHT_RELA)
+		: w(SHT_REL);
+	mcsec.sh_flags = 0;
+	mcsec.sh_addr = 0;
+	mcsec.sh_offset = _w((void *)mlocp - (void *)mloc0 + t);
+	mcsec.sh_size   = _w((void *)mrelp - (void *)mrel0);
+	mcsec.sh_link = w(symsec_sh_link);
+	mcsec.sh_info = w(old_shnum);
+	mcsec.sh_addralign = _w(_size);
+	mcsec.sh_entsize = _w(rel_entsize);
+	uwrite(fd_map, &mcsec, sizeof(mcsec));
+
+	uwrite(fd_map, mloc0, (void *)mlocp - (void *)mloc0);
+	uwrite(fd_map, mrel0, (void *)mrelp - (void *)mrel0);
+
+	ehdr->e_shoff = _w(new_e_shoff);
+	ehdr->e_shnum = w2(2 + w2(ehdr->e_shnum));  /* {.rel,}__mcount_loc */
+	ulseek(fd_map, 0, SEEK_SET);
+	uwrite(fd_map, ehdr, sizeof(*ehdr));
+}
+
+
+/*
+ * Look at the relocations in order to find the calls to mcount.
+ * Accumulate the section offsets that are found, and their relocation info,
+ * onto the end of the existing arrays.
+ */
+static uint_t *sift_rel_mcount(uint_t *mlocp,
+			       unsigned const offbase,
+			       Elf_Rel **const mrelpp,
+			       Elf_Shdr const *const relhdr,
+			       Elf_Ehdr const *const ehdr,
+			       unsigned const recsym,
+			       uint_t const recval,
+			       unsigned const reltype)
+{
+	uint_t *const mloc0 = mlocp;
+	Elf_Rel *mrelp = *mrelpp;
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	unsigned const symsec_sh_link = w(relhdr->sh_link);
+	Elf_Shdr const *const symsec = &shdr0[symsec_sh_link];
+	Elf_Sym const *const sym0 = (Elf_Sym const *)(_w(symsec->sh_offset)
+		+ (void *)ehdr);
+
+	Elf_Shdr const *const strsec = &shdr0[w(symsec->sh_link)];
+	char const *const str0 = (char const *)(_w(strsec->sh_offset)
+		+ (void *)ehdr);
+
+	Elf_Rel const *const rel0 = (Elf_Rel const *)(_w(relhdr->sh_offset)
+		+ (void *)ehdr);
+	unsigned rel_entsize = _w(relhdr->sh_entsize);
+	unsigned const nrel = _w(relhdr->sh_size) / rel_entsize;
+	Elf_Rel const *relp = rel0;
+
+	unsigned mcountsym = 0;
+	unsigned t;
+
+	for (t = nrel; t; --t) {
+		if (!mcountsym) {
+			Elf_Sym const *const symp =
+				&sym0[ELF_R_SYM(_w(relp->r_info))];
+			char const *symname = &str0[w(symp->st_name)];
+
+			if ('.' == symname[0])
+				++symname;  /* ppc64 hack */
+			if (0 == strcmp((('_' == gpfx) ? "_mcount" : "mcount"),
+					symname))
+				mcountsym = ELF_R_SYM(_w(relp->r_info));
+		}
+
+		if (mcountsym == ELF_R_SYM(_w(relp->r_info))) {
+			uint_t const addend = _w(_w(relp->r_offset) - recval);
+
+			mrelp->r_offset = _w(offbase
+				+ ((void *)mlocp - (void *)mloc0));
+			mrelp->r_info = _w(ELF_R_INFO(recsym, reltype));
+			if (sizeof(Elf_Rela) == rel_entsize) {
+				((Elf_Rela *)mrelp)->r_addend = addend;
+				*mlocp++ = 0;
+			} else
+				*mlocp++ = addend;
+
+			mrelp = (Elf_Rel *)(rel_entsize + (void *)mrelp);
+		}
+		relp = (Elf_Rel const *)(rel_entsize + (void *)relp);
+	}
+	*mrelpp = mrelp;
+	return mlocp;
+}
+
+
+/*
+ * Find a symbol in the given section, to be used as the base for relocating
+ * the table of offsets of calls to mcount.  A local or global symbol suffices,
+ * but avoid a Weak symbol because it may be overridden; the change in value
+ * would invalidate the relocations of the offsets of the calls to mcount.
+ * Often the found symbol will be the unnamed local symbol generated by
+ * GNU 'as' for the start of each section.  For example:
+ *    Num:    Value  Size Type    Bind   Vis      Ndx Name
+ *      2: 00000000     0 SECTION LOCAL  DEFAULT    1
+ */
+static unsigned find_secsym_ndx(unsigned const txtndx,
+				char const *const txtname,
+				uint_t *const recvalp,
+				Elf_Shdr const *const symhdr,
+				Elf_Ehdr const *const ehdr)
+{
+	Elf_Sym const *const sym0 = (Elf_Sym const *)(_w(symhdr->sh_offset)
+		+ (void *)ehdr);
+	unsigned const nsym = _w(symhdr->sh_size) / _w(symhdr->sh_entsize);
+	Elf_Sym const *symp;
+	unsigned t;
+
+	for (symp = sym0, t = nsym; t; --t, ++symp) {
+		unsigned int const st_bind = ELF_ST_BIND(symp->st_info);
+
+		if (txtndx == w2(symp->st_shndx)
+			/* avoid STB_WEAK */
+		    && (STB_LOCAL == st_bind || STB_GLOBAL == st_bind)) {
+			*recvalp = _w(symp->st_value);
+			return symp - sym0;
+		}
+	}
+	fprintf(stderr, "Cannot find symbol for section %d: %s.\n",
+		txtndx, txtname);
+	fail_file();
+}
+
+
+/* Evade ISO C restriction: no declaration after statement in has_rel_mcount. */
+static char const *
+__has_rel_mcount(Elf_Shdr const *const relhdr,  /* is SHT_REL or SHT_RELA */
+		 Elf_Shdr const *const shdr0,
+		 char const *const shstrtab,
+		 char const *const fname)
+{
+	/* .sh_info depends on .sh_type == SHT_REL[,A] */
+	Elf_Shdr const *const txthdr = &shdr0[w(relhdr->sh_info)];
+	char const *const txtname = &shstrtab[w(txthdr->sh_name)];
+
+	if (0 == strcmp("__mcount_loc", txtname)) {
+		fprintf(stderr, "warning: __mcount_loc already exists: %s\n",
+			fname);
+		succeed_file();
+	}
+	if (SHT_PROGBITS != w(txthdr->sh_type) ||
+	    !is_mcounted_section_name(txtname))
+		return NULL;
+	return txtname;
+}
+
+static char const *has_rel_mcount(Elf_Shdr const *const relhdr,
+				  Elf_Shdr const *const shdr0,
+				  char const *const shstrtab,
+				  char const *const fname)
+{
+	if (SHT_REL  != w(relhdr->sh_type) && SHT_RELA != w(relhdr->sh_type))
+		return NULL;
+	return __has_rel_mcount(relhdr, shdr0, shstrtab, fname);
+}
+
+
+static unsigned tot_relsize(Elf_Shdr const *const shdr0,
+			    unsigned nhdr,
+			    const char *const shstrtab,
+			    const char *const fname)
+{
+	unsigned totrelsz = 0;
+	Elf_Shdr const *shdrp = shdr0;
+
+	for (; nhdr; --nhdr, ++shdrp) {
+		if (has_rel_mcount(shdrp, shdr0, shstrtab, fname))
+			totrelsz += _w(shdrp->sh_size);
+	}
+	return totrelsz;
+}
+
+
+/* Overall supervision for Elf32 ET_REL file. */
+static void
+do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
+{
+	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
+		+ (void *)ehdr);
+	unsigned const nhdr = w2(ehdr->e_shnum);
+	Elf_Shdr *const shstr = &shdr0[w2(ehdr->e_shstrndx)];
+	char const *const shstrtab = (char const *)(_w(shstr->sh_offset)
+		+ (void *)ehdr);
+
+	Elf_Shdr const *relhdr;
+	unsigned k;
+
+	/* Upper bound on space: assume all relevant relocs are for mcount. */
+	unsigned const totrelsz = tot_relsize(shdr0, nhdr, shstrtab, fname);
+	Elf_Rel *const mrel0 = umalloc(totrelsz);
+	Elf_Rel *      mrelp = mrel0;
+
+	/* 2*sizeof(address) <= sizeof(Elf_Rel) */
+	uint_t *const mloc0 = umalloc(totrelsz>>1);
+	uint_t *      mlocp = mloc0;
+
+	unsigned rel_entsize = 0;
+	unsigned symsec_sh_link = 0;
+
+	for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) {
+		char const *const txtname = has_rel_mcount(relhdr, shdr0,
+			shstrtab, fname);
+		if (txtname) {
+			uint_t recval = 0;
+			unsigned const recsym = find_secsym_ndx(
+				w(relhdr->sh_info), txtname, &recval,
+				&shdr0[symsec_sh_link = w(relhdr->sh_link)],
+				ehdr);
+
+			rel_entsize = _w(relhdr->sh_entsize);
+			mlocp = sift_rel_mcount(mlocp,
+				(void *)mlocp - (void *)mloc0, &mrelp,
+				relhdr, ehdr, recsym, recval, reltype);
+		}
+	}
+	if (mloc0 != mlocp) {
+		append_func(ehdr, shstr, mloc0, mlocp, mrel0, mrelp,
+			    rel_entsize, symsec_sh_link);
+	}
+	free(mrel0);
+	free(mloc0);
+}
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index e67f054..1d7963f 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -270,6 +270,8 @@
 } elsif ($arch eq "arm") {
     $alignment = 2;
     $section_type = '%progbits';
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_ARM_(CALL|PC24|THM_CALL)" .
+			"\\s+(__gnu_mcount_nc|mcount)\$";
 
 } elsif ($arch eq "ia64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
diff --git a/security/apparmor/.gitignore b/security/apparmor/.gitignore
index 0a0a99f..4d995ae 100644
--- a/security/apparmor/.gitignore
+++ b/security/apparmor/.gitignore
@@ -3,3 +3,4 @@
 #
 af_names.h
 capability_names.h
+rlim_names.h
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 7320331..0848292 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -29,7 +29,7 @@
  * aa_simple_write_to_buffer - common routine for getting policy from user
  * @op: operation doing the user buffer copy
  * @userbuf: user buffer to copy data from  (NOT NULL)
- * @alloc_size: size of user buffer
+ * @alloc_size: size of user buffer (REQUIRES: @alloc_size >= @copy_size)
  * @copy_size: size of data to copy from user buffer
  * @pos: position write is at in the file (NOT NULL)
  *
@@ -42,6 +42,8 @@
 {
 	char *data;
 
+	BUG_ON(copy_size > alloc_size);
+
 	if (*pos != 0)
 		/* only writes from pos 0, that is complete writes */
 		return ERR_PTR(-ESPIPE);
@@ -86,7 +88,8 @@
 }
 
 static const struct file_operations aa_fs_profile_load = {
-	.write = profile_load
+	.write = profile_load,
+	.llseek = default_llseek,
 };
 
 /* .replace file hook fn to load and/or replace policy */
@@ -107,7 +110,8 @@
 }
 
 static const struct file_operations aa_fs_profile_replace = {
-	.write = profile_replace
+	.write = profile_replace,
+	.llseek = default_llseek,
 };
 
 /* .remove file hook fn to remove loaded policy */
@@ -134,7 +138,8 @@
 }
 
 static const struct file_operations aa_fs_profile_remove = {
-	.write = profile_remove
+	.write = profile_remove,
+	.llseek = default_llseek,
 };
 
 /** Base file system setup **/
diff --git a/security/capability.c b/security/capability.c
index 95a6599..30ae00f 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -677,7 +677,18 @@
 {
 }
 
+static int cap_secmark_relabel_packet(u32 secid)
+{
+	return 0;
+}
 
+static void cap_secmark_refcount_inc(void)
+{
+}
+
+static void cap_secmark_refcount_dec(void)
+{
+}
 
 static void cap_req_classify_flow(const struct request_sock *req,
 				  struct flowi *fl)
@@ -777,7 +788,8 @@
 
 static int cap_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
 {
-	return -EOPNOTSUPP;
+	*secid = 0;
+	return 0;
 }
 
 static void cap_release_secctx(char *secdata, u32 seclen)
@@ -1018,6 +1030,9 @@
 	set_to_cap_if_null(ops, inet_conn_request);
 	set_to_cap_if_null(ops, inet_csk_clone);
 	set_to_cap_if_null(ops, inet_conn_established);
+	set_to_cap_if_null(ops, secmark_relabel_packet);
+	set_to_cap_if_null(ops, secmark_refcount_inc);
+	set_to_cap_if_null(ops, secmark_refcount_dec);
 	set_to_cap_if_null(ops, req_classify_flow);
 	set_to_cap_if_null(ops, tun_dev_create);
 	set_to_cap_if_null(ops, tun_dev_post_create);
diff --git a/security/commoncap.c b/security/commoncap.c
index 9d172e6..5e632b4 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -719,14 +719,11 @@
 /**
  * cap_task_setscheduler - Detemine if scheduler policy change is permitted
  * @p: The task to affect
- * @policy: The policy to effect
- * @lp: The parameters to the scheduling policy
  *
  * Detemine if the requested scheduler policy change is permitted for the
  * specified task, returning 0 if permission is granted, -ve if denied.
  */
-int cap_task_setscheduler(struct task_struct *p, int policy,
-			   struct sched_param *lp)
+int cap_task_setscheduler(struct task_struct *p)
 {
 	return cap_safe_nice(p);
 }
diff --git a/security/inode.c b/security/inode.c
index 8c777f0..8883986 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -53,6 +53,7 @@
 	.read =		default_read_file,
 	.write =	default_write_file,
 	.open =		default_open,
+	.llseek =	noop_llseek,
 };
 
 static struct inode *get_inode(struct super_block *sb, int mode, dev_t dev)
diff --git a/security/security.c b/security/security.c
index c53949f..b50f472 100644
--- a/security/security.c
+++ b/security/security.c
@@ -89,20 +89,12 @@
  * Return true if:
  *	-The passed LSM is the one chosen by user at boot time,
  *	-or the passed LSM is configured as the default and the user did not
- *	 choose an alternate LSM at boot time,
- *	-or there is no default LSM set and the user didn't specify a
- *	 specific LSM and we're the first to ask for registration permission,
- *	-or the passed LSM is currently loaded.
+ *	 choose an alternate LSM at boot time.
  * Otherwise, return false.
  */
 int __init security_module_enable(struct security_operations *ops)
 {
-	if (!*chosen_lsm)
-		strncpy(chosen_lsm, ops->name, SECURITY_NAME_MAX);
-	else if (strncmp(ops->name, chosen_lsm, SECURITY_NAME_MAX))
-		return 0;
-
-	return 1;
+	return !strcmp(ops->name, chosen_lsm);
 }
 
 /**
@@ -786,10 +778,9 @@
 	return security_ops->task_setrlimit(p, resource, new_rlim);
 }
 
-int security_task_setscheduler(struct task_struct *p,
-				int policy, struct sched_param *lp)
+int security_task_setscheduler(struct task_struct *p)
 {
-	return security_ops->task_setscheduler(p, policy, lp);
+	return security_ops->task_setscheduler(p);
 }
 
 int security_task_getscheduler(struct task_struct *p)
@@ -1145,6 +1136,24 @@
 	security_ops->inet_conn_established(sk, skb);
 }
 
+int security_secmark_relabel_packet(u32 secid)
+{
+	return security_ops->secmark_relabel_packet(secid);
+}
+EXPORT_SYMBOL(security_secmark_relabel_packet);
+
+void security_secmark_refcount_inc(void)
+{
+	security_ops->secmark_refcount_inc();
+}
+EXPORT_SYMBOL(security_secmark_refcount_inc);
+
+void security_secmark_refcount_dec(void)
+{
+	security_ops->secmark_refcount_dec();
+}
+EXPORT_SYMBOL(security_secmark_refcount_dec);
+
 int security_tun_dev_create(void)
 {
 	return security_ops->tun_dev_create();
diff --git a/security/selinux/Makefile b/security/selinux/Makefile
index 58d80f3..ad5cd76 100644
--- a/security/selinux/Makefile
+++ b/security/selinux/Makefile
@@ -2,25 +2,20 @@
 # Makefile for building the SELinux module as part of the kernel tree.
 #
 
-obj-$(CONFIG_SECURITY_SELINUX) := selinux.o ss/
+obj-$(CONFIG_SECURITY_SELINUX) := selinux.o
 
-selinux-y := avc.o \
-	     hooks.o \
-	     selinuxfs.o \
-	     netlink.o \
-	     nlmsgtab.o \
-	     netif.o \
-	     netnode.o \
-	     netport.o \
-	     exports.o
+selinux-y := avc.o hooks.o selinuxfs.o netlink.o nlmsgtab.o netif.o \
+	     netnode.o netport.o exports.o \
+	     ss/ebitmap.o ss/hashtab.o ss/symtab.o ss/sidtab.o ss/avtab.o \
+	     ss/policydb.o ss/services.o ss/conditional.o ss/mls.o ss/status.o
 
 selinux-$(CONFIG_SECURITY_NETWORK_XFRM) += xfrm.o
 
 selinux-$(CONFIG_NETLABEL) += netlabel.o
 
-EXTRA_CFLAGS += -Isecurity/selinux -Isecurity/selinux/include
+ccflags-y := -Isecurity/selinux -Isecurity/selinux/include
 
-$(obj)/avc.o: $(obj)/flask.h
+$(addprefix $(obj)/,$(selinux-y)): $(obj)/flask.h
 
 quiet_cmd_flask = GEN     $(obj)/flask.h $(obj)/av_permissions.h
       cmd_flask = scripts/selinux/genheaders/genheaders $(obj)/flask.h $(obj)/av_permissions.h
diff --git a/security/selinux/exports.c b/security/selinux/exports.c
index c0a454a..9066438 100644
--- a/security/selinux/exports.c
+++ b/security/selinux/exports.c
@@ -11,58 +11,9 @@
  * it under the terms of the GNU General Public License version 2,
  * as published by the Free Software Foundation.
  */
-#include <linux/types.h>
-#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/selinux.h>
-#include <linux/fs.h>
-#include <linux/ipc.h>
-#include <asm/atomic.h>
 
 #include "security.h"
-#include "objsec.h"
-
-/* SECMARK reference count */
-extern atomic_t selinux_secmark_refcount;
-
-int selinux_string_to_sid(char *str, u32 *sid)
-{
-	if (selinux_enabled)
-		return security_context_to_sid(str, strlen(str), sid);
-	else {
-		*sid = 0;
-		return 0;
-	}
-}
-EXPORT_SYMBOL_GPL(selinux_string_to_sid);
-
-int selinux_secmark_relabel_packet_permission(u32 sid)
-{
-	if (selinux_enabled) {
-		const struct task_security_struct *__tsec;
-		u32 tsid;
-
-		__tsec = current_security();
-		tsid = __tsec->sid;
-
-		return avc_has_perm(tsid, sid, SECCLASS_PACKET,
-				    PACKET__RELABELTO, NULL);
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(selinux_secmark_relabel_packet_permission);
-
-void selinux_secmark_refcount_inc(void)
-{
-	atomic_inc(&selinux_secmark_refcount);
-}
-EXPORT_SYMBOL_GPL(selinux_secmark_refcount_inc);
-
-void selinux_secmark_refcount_dec(void)
-{
-	atomic_dec(&selinux_secmark_refcount);
-}
-EXPORT_SYMBOL_GPL(selinux_secmark_refcount_dec);
 
 bool selinux_is_enabled(void)
 {
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4796ddd..d9154cf 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3354,11 +3354,11 @@
 	return 0;
 }
 
-static int selinux_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp)
+static int selinux_task_setscheduler(struct task_struct *p)
 {
 	int rc;
 
-	rc = cap_task_setscheduler(p, policy, lp);
+	rc = cap_task_setscheduler(p);
 	if (rc)
 		return rc;
 
@@ -4279,6 +4279,27 @@
 	selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid);
 }
 
+static int selinux_secmark_relabel_packet(u32 sid)
+{
+	const struct task_security_struct *__tsec;
+	u32 tsid;
+
+	__tsec = current_security();
+	tsid = __tsec->sid;
+
+	return avc_has_perm(tsid, sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL);
+}
+
+static void selinux_secmark_refcount_inc(void)
+{
+	atomic_inc(&selinux_secmark_refcount);
+}
+
+static void selinux_secmark_refcount_dec(void)
+{
+	atomic_dec(&selinux_secmark_refcount);
+}
+
 static void selinux_req_classify_flow(const struct request_sock *req,
 				      struct flowi *fl)
 {
@@ -5533,6 +5554,9 @@
 	.inet_conn_request =		selinux_inet_conn_request,
 	.inet_csk_clone =		selinux_inet_csk_clone,
 	.inet_conn_established =	selinux_inet_conn_established,
+	.secmark_relabel_packet =	selinux_secmark_relabel_packet,
+	.secmark_refcount_inc =		selinux_secmark_refcount_inc,
+	.secmark_refcount_dec =		selinux_secmark_refcount_dec,
 	.req_classify_flow =		selinux_req_classify_flow,
 	.tun_dev_create =		selinux_tun_dev_create,
 	.tun_dev_post_create = 		selinux_tun_dev_post_create,
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index b4c9eb4..8858d2b 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -17,7 +17,7 @@
 	  { "compute_av", "compute_create", "compute_member",
 	    "check_context", "load_policy", "compute_relabel",
 	    "compute_user", "setenforce", "setbool", "setsecparam",
-	    "setcheckreqprot", NULL } },
+	    "setcheckreqprot", "read_policy", NULL } },
 	{ "process",
 	  { "fork", "transition", "sigchld", "sigkill",
 	    "sigstop", "signull", "signal", "ptrace", "getsched", "setsched",
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 1f7c249..671273e 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -9,6 +9,7 @@
 #define _SELINUX_SECURITY_H_
 
 #include <linux/magic.h>
+#include <linux/types.h>
 #include "flask.h"
 
 #define SECSID_NULL			0x00000000 /* unspecified SID */
@@ -82,6 +83,8 @@
 int security_mls_enabled(void);
 
 int security_load_policy(void *data, size_t len);
+int security_read_policy(void **data, ssize_t *len);
+size_t security_policydb_len(void);
 
 int security_policycap_supported(unsigned int req_cap);
 
@@ -191,5 +194,25 @@
 
 const char *security_get_initial_sid_context(u32 sid);
 
+/*
+ * status notifier using mmap interface
+ */
+extern struct page *selinux_kernel_status_page(void);
+
+#define SELINUX_KERNEL_STATUS_VERSION	1
+struct selinux_kernel_status {
+	u32	version;	/* version number of thie structure */
+	u32	sequence;	/* sequence number of seqlock logic */
+	u32	enforcing;	/* current setting of enforcing mode */
+	u32	policyload;	/* times of policy reloaded */
+	u32	deny_unknown;	/* current setting of deny_unknown */
+	/*
+	 * The version > 0 supports above members.
+	 */
+} __attribute__((packed));
+
+extern void selinux_status_update_setenforce(int enforcing);
+extern void selinux_status_update_policyload(int seqno);
+
 #endif /* _SELINUX_SECURITY_H_ */
 
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 79a1bb6..87e0556 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -68,6 +68,8 @@
 static struct dentry *class_dir;
 static unsigned long last_class_ino;
 
+static char policy_opened;
+
 /* global data for policy capabilities */
 static struct dentry *policycap_dir;
 
@@ -110,6 +112,8 @@
 	SEL_COMPAT_NET,	/* whether to use old compat network packet controls */
 	SEL_REJECT_UNKNOWN, /* export unknown reject handling to userspace */
 	SEL_DENY_UNKNOWN, /* export unknown deny handling to userspace */
+	SEL_STATUS,	/* export current status using mmap() */
+	SEL_POLICY,	/* allow userspace to read the in kernel policy */
 	SEL_INO_NEXT,	/* The next inode number to use */
 };
 
@@ -171,6 +175,7 @@
 		if (selinux_enforcing)
 			avc_ss_reset(0);
 		selnl_notify_setenforce(selinux_enforcing);
+		selinux_status_update_setenforce(selinux_enforcing);
 	}
 	length = count;
 out:
@@ -205,6 +210,59 @@
 	.llseek		= generic_file_llseek,
 };
 
+static int sel_open_handle_status(struct inode *inode, struct file *filp)
+{
+	struct page    *status = selinux_kernel_status_page();
+
+	if (!status)
+		return -ENOMEM;
+
+	filp->private_data = status;
+
+	return 0;
+}
+
+static ssize_t sel_read_handle_status(struct file *filp, char __user *buf,
+				      size_t count, loff_t *ppos)
+{
+	struct page    *status = filp->private_data;
+
+	BUG_ON(!status);
+
+	return simple_read_from_buffer(buf, count, ppos,
+				       page_address(status),
+				       sizeof(struct selinux_kernel_status));
+}
+
+static int sel_mmap_handle_status(struct file *filp,
+				  struct vm_area_struct *vma)
+{
+	struct page    *status = filp->private_data;
+	unsigned long	size = vma->vm_end - vma->vm_start;
+
+	BUG_ON(!status);
+
+	/* only allows one page from the head */
+	if (vma->vm_pgoff > 0 || size != PAGE_SIZE)
+		return -EIO;
+	/* disallow writable mapping */
+	if (vma->vm_flags & VM_WRITE)
+		return -EPERM;
+	/* disallow mprotect() turns it into writable */
+	vma->vm_flags &= ~VM_MAYWRITE;
+
+	return remap_pfn_range(vma, vma->vm_start,
+			       page_to_pfn(status),
+			       size, vma->vm_page_prot);
+}
+
+static const struct file_operations sel_handle_status_ops = {
+	.open		= sel_open_handle_status,
+	.read		= sel_read_handle_status,
+	.mmap		= sel_mmap_handle_status,
+	.llseek		= generic_file_llseek,
+};
+
 #ifdef CONFIG_SECURITY_SELINUX_DISABLE
 static ssize_t sel_write_disable(struct file *file, const char __user *buf,
 				 size_t count, loff_t *ppos)
@@ -296,6 +354,141 @@
 	.llseek		= generic_file_llseek,
 };
 
+struct policy_load_memory {
+	size_t len;
+	void *data;
+};
+
+static int sel_open_policy(struct inode *inode, struct file *filp)
+{
+	struct policy_load_memory *plm = NULL;
+	int rc;
+
+	BUG_ON(filp->private_data);
+
+	mutex_lock(&sel_mutex);
+
+	rc = task_has_security(current, SECURITY__READ_POLICY);
+	if (rc)
+		goto err;
+
+	rc = -EBUSY;
+	if (policy_opened)
+		goto err;
+
+	rc = -ENOMEM;
+	plm = kzalloc(sizeof(*plm), GFP_KERNEL);
+	if (!plm)
+		goto err;
+
+	if (i_size_read(inode) != security_policydb_len()) {
+		mutex_lock(&inode->i_mutex);
+		i_size_write(inode, security_policydb_len());
+		mutex_unlock(&inode->i_mutex);
+	}
+
+	rc = security_read_policy(&plm->data, &plm->len);
+	if (rc)
+		goto err;
+
+	policy_opened = 1;
+
+	filp->private_data = plm;
+
+	mutex_unlock(&sel_mutex);
+
+	return 0;
+err:
+	mutex_unlock(&sel_mutex);
+
+	if (plm)
+		vfree(plm->data);
+	kfree(plm);
+	return rc;
+}
+
+static int sel_release_policy(struct inode *inode, struct file *filp)
+{
+	struct policy_load_memory *plm = filp->private_data;
+
+	BUG_ON(!plm);
+
+	policy_opened = 0;
+
+	vfree(plm->data);
+	kfree(plm);
+
+	return 0;
+}
+
+static ssize_t sel_read_policy(struct file *filp, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct policy_load_memory *plm = filp->private_data;
+	int ret;
+
+	mutex_lock(&sel_mutex);
+
+	ret = task_has_security(current, SECURITY__READ_POLICY);
+	if (ret)
+		goto out;
+
+	ret = simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
+out:
+	mutex_unlock(&sel_mutex);
+	return ret;
+}
+
+static int sel_mmap_policy_fault(struct vm_area_struct *vma,
+				 struct vm_fault *vmf)
+{
+	struct policy_load_memory *plm = vma->vm_file->private_data;
+	unsigned long offset;
+	struct page *page;
+
+	if (vmf->flags & (FAULT_FLAG_MKWRITE | FAULT_FLAG_WRITE))
+		return VM_FAULT_SIGBUS;
+
+	offset = vmf->pgoff << PAGE_SHIFT;
+	if (offset >= roundup(plm->len, PAGE_SIZE))
+		return VM_FAULT_SIGBUS;
+
+	page = vmalloc_to_page(plm->data + offset);
+	get_page(page);
+
+	vmf->page = page;
+
+	return 0;
+}
+
+static struct vm_operations_struct sel_mmap_policy_ops = {
+	.fault = sel_mmap_policy_fault,
+	.page_mkwrite = sel_mmap_policy_fault,
+};
+
+int sel_mmap_policy(struct file *filp, struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_SHARED) {
+		/* do not allow mprotect to make mapping writable */
+		vma->vm_flags &= ~VM_MAYWRITE;
+
+		if (vma->vm_flags & VM_WRITE)
+			return -EACCES;
+	}
+
+	vma->vm_flags |= VM_RESERVED;
+	vma->vm_ops = &sel_mmap_policy_ops;
+
+	return 0;
+}
+
+static const struct file_operations sel_policy_ops = {
+	.open		= sel_open_policy,
+	.read		= sel_read_policy,
+	.mmap		= sel_mmap_policy,
+	.release	= sel_release_policy,
+};
+
 static ssize_t sel_write_load(struct file *file, const char __user *buf,
 			      size_t count, loff_t *ppos)
 
@@ -1612,6 +1805,8 @@
 		[SEL_CHECKREQPROT] = {"checkreqprot", &sel_checkreqprot_ops, S_IRUGO|S_IWUSR},
 		[SEL_REJECT_UNKNOWN] = {"reject_unknown", &sel_handle_unknown_ops, S_IRUGO},
 		[SEL_DENY_UNKNOWN] = {"deny_unknown", &sel_handle_unknown_ops, S_IRUGO},
+		[SEL_STATUS] = {"status", &sel_handle_status_ops, S_IRUGO},
+		[SEL_POLICY] = {"policy", &sel_policy_ops, S_IRUSR},
 		/* last one */ {""}
 	};
 	ret = simple_fill_super(sb, SELINUX_MAGIC, selinux_files);
diff --git a/security/selinux/ss/Makefile b/security/selinux/ss/Makefile
deleted file mode 100644
index 15d4e62..0000000
--- a/security/selinux/ss/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-#
-# Makefile for building the SELinux security server as part of the kernel tree.
-#
-
-EXTRA_CFLAGS += -Isecurity/selinux -Isecurity/selinux/include
-obj-y := ss.o
-
-ss-y := ebitmap.o hashtab.o symtab.o sidtab.o avtab.o policydb.o services.o conditional.o mls.o
-
diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index 929480c..a3dd9fa 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -266,8 +266,8 @@
 	if (shift > 2)
 		shift = shift - 2;
 	nslot = 1 << shift;
-	if (nslot > MAX_AVTAB_SIZE)
-		nslot = MAX_AVTAB_SIZE;
+	if (nslot > MAX_AVTAB_HASH_BUCKETS)
+		nslot = MAX_AVTAB_HASH_BUCKETS;
 	mask = nslot - 1;
 
 	h->htable = kcalloc(nslot, sizeof(*(h->htable)), GFP_KERNEL);
@@ -501,6 +501,48 @@
 	goto out;
 }
 
+int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp)
+{
+	__le16 buf16[4];
+	__le32 buf32[1];
+	int rc;
+
+	buf16[0] = cpu_to_le16(cur->key.source_type);
+	buf16[1] = cpu_to_le16(cur->key.target_type);
+	buf16[2] = cpu_to_le16(cur->key.target_class);
+	buf16[3] = cpu_to_le16(cur->key.specified);
+	rc = put_entry(buf16, sizeof(u16), 4, fp);
+	if (rc)
+		return rc;
+	buf32[0] = cpu_to_le32(cur->datum.data);
+	rc = put_entry(buf32, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+	return 0;
+}
+
+int avtab_write(struct policydb *p, struct avtab *a, void *fp)
+{
+	unsigned int i;
+	int rc = 0;
+	struct avtab_node *cur;
+	__le32 buf[1];
+
+	buf[0] = cpu_to_le32(a->nel);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < a->nslot; i++) {
+		for (cur = a->htable[i]; cur; cur = cur->next) {
+			rc = avtab_write_item(p, cur, fp);
+			if (rc)
+				return rc;
+		}
+	}
+
+	return rc;
+}
 void avtab_cache_init(void)
 {
 	avtab_node_cachep = kmem_cache_create("avtab_node",
diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h
index cd4f734..dff0c75 100644
--- a/security/selinux/ss/avtab.h
+++ b/security/selinux/ss/avtab.h
@@ -71,6 +71,8 @@
 		    void *p);
 
 int avtab_read(struct avtab *a, void *fp, struct policydb *pol);
+int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp);
+int avtab_write(struct policydb *p, struct avtab *a, void *fp);
 
 struct avtab_node *avtab_insert_nonunique(struct avtab *h, struct avtab_key *key,
 					  struct avtab_datum *datum);
@@ -85,7 +87,6 @@
 #define MAX_AVTAB_HASH_BITS 11
 #define MAX_AVTAB_HASH_BUCKETS (1 << MAX_AVTAB_HASH_BITS)
 #define MAX_AVTAB_HASH_MASK (MAX_AVTAB_HASH_BUCKETS-1)
-#define MAX_AVTAB_SIZE MAX_AVTAB_HASH_BUCKETS
 
 #endif	/* _SS_AVTAB_H_ */
 
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index c91e150..655fe1c 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -490,6 +490,129 @@
 	return rc;
 }
 
+int cond_write_bool(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct cond_bool_datum *booldatum = datum;
+	struct policy_data *pd = ptr;
+	void *fp = pd->fp;
+	__le32 buf[3];
+	u32 len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(booldatum->value);
+	buf[1] = cpu_to_le32(booldatum->state);
+	buf[2] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+	return 0;
+}
+
+/*
+ * cond_write_cond_av_list doesn't write out the av_list nodes.
+ * Instead it writes out the key/value pairs from the avtab. This
+ * is necessary because there is no way to uniquely identifying rules
+ * in the avtab so it is not possible to associate individual rules
+ * in the avtab with a conditional without saving them as part of
+ * the conditional. This means that the avtab with the conditional
+ * rules will not be saved but will be rebuilt on policy load.
+ */
+static int cond_write_av_list(struct policydb *p,
+			      struct cond_av_list *list, struct policy_file *fp)
+{
+	__le32 buf[1];
+	struct cond_av_list *cur_list;
+	u32 len;
+	int rc;
+
+	len = 0;
+	for (cur_list = list; cur_list != NULL; cur_list = cur_list->next)
+		len++;
+
+	buf[0] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	if (len == 0)
+		return 0;
+
+	for (cur_list = list; cur_list != NULL; cur_list = cur_list->next) {
+		rc = avtab_write_item(p, cur_list->node, fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+int cond_write_node(struct policydb *p, struct cond_node *node,
+		    struct policy_file *fp)
+{
+	struct cond_expr *cur_expr;
+	__le32 buf[2];
+	int rc;
+	u32 len = 0;
+
+	buf[0] = cpu_to_le32(node->cur_state);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	for (cur_expr = node->expr; cur_expr != NULL; cur_expr = cur_expr->next)
+		len++;
+
+	buf[0] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	for (cur_expr = node->expr; cur_expr != NULL; cur_expr = cur_expr->next) {
+		buf[0] = cpu_to_le32(cur_expr->expr_type);
+		buf[1] = cpu_to_le32(cur_expr->bool);
+		rc = put_entry(buf, sizeof(u32), 2, fp);
+		if (rc)
+			return rc;
+	}
+
+	rc = cond_write_av_list(p, node->true_list, fp);
+	if (rc)
+		return rc;
+	rc = cond_write_av_list(p, node->false_list, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+int cond_write_list(struct policydb *p, struct cond_node *list, void *fp)
+{
+	struct cond_node *cur;
+	u32 len;
+	__le32 buf[1];
+	int rc;
+
+	len = 0;
+	for (cur = list; cur != NULL; cur = cur->next)
+		len++;
+	buf[0] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	for (cur = list; cur != NULL; cur = cur->next) {
+		rc = cond_write_node(p, cur, fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
 /* Determine whether additional permissions are granted by the conditional
  * av table, and if so, add them to the result
  */
diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h
index 53ddb01..3f209c6 100644
--- a/security/selinux/ss/conditional.h
+++ b/security/selinux/ss/conditional.h
@@ -69,6 +69,8 @@
 
 int cond_read_bool(struct policydb *p, struct hashtab *h, void *fp);
 int cond_read_list(struct policydb *p, void *fp);
+int cond_write_bool(void *key, void *datum, void *ptr);
+int cond_write_list(struct policydb *p, struct cond_node *list, void *fp);
 
 void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd);
 
diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
index 04b6145..d42951f 100644
--- a/security/selinux/ss/ebitmap.c
+++ b/security/selinux/ss/ebitmap.c
@@ -22,6 +22,8 @@
 #include "ebitmap.h"
 #include "policydb.h"
 
+#define BITS_PER_U64	(sizeof(u64) * 8)
+
 int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2)
 {
 	struct ebitmap_node *n1, *n2;
@@ -363,10 +365,10 @@
 	e->highbit = le32_to_cpu(buf[1]);
 	count = le32_to_cpu(buf[2]);
 
-	if (mapunit != sizeof(u64) * 8) {
+	if (mapunit != BITS_PER_U64) {
 		printk(KERN_ERR "SELinux: ebitmap: map size %u does not "
 		       "match my size %Zd (high bit was %d)\n",
-		       mapunit, sizeof(u64) * 8, e->highbit);
+		       mapunit, BITS_PER_U64, e->highbit);
 		goto bad;
 	}
 
@@ -446,3 +448,78 @@
 	ebitmap_destroy(e);
 	goto out;
 }
+
+int ebitmap_write(struct ebitmap *e, void *fp)
+{
+	struct ebitmap_node *n;
+	u32 count;
+	__le32 buf[3];
+	u64 map;
+	int bit, last_bit, last_startbit, rc;
+
+	buf[0] = cpu_to_le32(BITS_PER_U64);
+
+	count = 0;
+	last_bit = 0;
+	last_startbit = -1;
+	ebitmap_for_each_positive_bit(e, n, bit) {
+		if (rounddown(bit, (int)BITS_PER_U64) > last_startbit) {
+			count++;
+			last_startbit = rounddown(bit, BITS_PER_U64);
+		}
+		last_bit = roundup(bit + 1, BITS_PER_U64);
+	}
+	buf[1] = cpu_to_le32(last_bit);
+	buf[2] = cpu_to_le32(count);
+
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+
+	map = 0;
+	last_startbit = INT_MIN;
+	ebitmap_for_each_positive_bit(e, n, bit) {
+		if (rounddown(bit, (int)BITS_PER_U64) > last_startbit) {
+			__le64 buf64[1];
+
+			/* this is the very first bit */
+			if (!map) {
+				last_startbit = rounddown(bit, BITS_PER_U64);
+				map = (u64)1 << (bit - last_startbit);
+				continue;
+			}
+
+			/* write the last node */
+			buf[0] = cpu_to_le32(last_startbit);
+			rc = put_entry(buf, sizeof(u32), 1, fp);
+			if (rc)
+				return rc;
+
+			buf64[0] = cpu_to_le64(map);
+			rc = put_entry(buf64, sizeof(u64), 1, fp);
+			if (rc)
+				return rc;
+
+			/* set up for the next node */
+			map = 0;
+			last_startbit = rounddown(bit, BITS_PER_U64);
+		}
+		map |= (u64)1 << (bit - last_startbit);
+	}
+	/* write the last node */
+	if (map) {
+		__le64 buf64[1];
+
+		/* write the last node */
+		buf[0] = cpu_to_le32(last_startbit);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+
+		buf64[0] = cpu_to_le64(map);
+		rc = put_entry(buf64, sizeof(u64), 1, fp);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
diff --git a/security/selinux/ss/ebitmap.h b/security/selinux/ss/ebitmap.h
index f283b43..1f4e93c 100644
--- a/security/selinux/ss/ebitmap.h
+++ b/security/selinux/ss/ebitmap.h
@@ -123,6 +123,7 @@
 int ebitmap_set_bit(struct ebitmap *e, unsigned long bit, int value);
 void ebitmap_destroy(struct ebitmap *e);
 int ebitmap_read(struct ebitmap *e, void *fp);
+int ebitmap_write(struct ebitmap *e, void *fp);
 
 #ifdef CONFIG_NETLABEL
 int ebitmap_netlbl_export(struct ebitmap *ebmap,
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 3a29704..94f630d 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -37,6 +37,7 @@
 #include "policydb.h"
 #include "conditional.h"
 #include "mls.h"
+#include "services.h"
 
 #define _DEBUG_HASHES
 
@@ -185,9 +186,19 @@
 static int rangetr_cmp(struct hashtab *h, const void *k1, const void *k2)
 {
 	const struct range_trans *key1 = k1, *key2 = k2;
-	return (key1->source_type != key2->source_type ||
-		key1->target_type != key2->target_type ||
-		key1->target_class != key2->target_class);
+	int v;
+
+	v = key1->source_type - key2->source_type;
+	if (v)
+		return v;
+
+	v = key1->target_type - key2->target_type;
+	if (v)
+		return v;
+
+	v = key1->target_class - key2->target_class;
+
+	return v;
 }
 
 /*
@@ -1624,11 +1635,11 @@
 
 static int type_bounds_sanity_check(void *key, void *datum, void *datap)
 {
-	struct type_datum *upper, *type;
+	struct type_datum *upper;
 	struct policydb *p = datap;
 	int depth = 0;
 
-	upper = type = datum;
+	upper = datum;
 	while (upper->bounds) {
 		if (++depth == POLICYDB_BOUNDS_MAXDEPTH) {
 			printk(KERN_ERR "SELinux: type %s: "
@@ -2306,3 +2317,843 @@
 	policydb_destroy(p);
 	goto out;
 }
+
+/*
+ * Write a MLS level structure to a policydb binary
+ * representation file.
+ */
+static int mls_write_level(struct mls_level *l, void *fp)
+{
+	__le32 buf[1];
+	int rc;
+
+	buf[0] = cpu_to_le32(l->sens);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&l->cat, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+/*
+ * Write a MLS range structure to a policydb binary
+ * representation file.
+ */
+static int mls_write_range_helper(struct mls_range *r, void *fp)
+{
+	__le32 buf[3];
+	size_t items;
+	int rc, eq;
+
+	eq = mls_level_eq(&r->level[1], &r->level[0]);
+
+	if (eq)
+		items = 2;
+	else
+		items = 3;
+	buf[0] = cpu_to_le32(items-1);
+	buf[1] = cpu_to_le32(r->level[0].sens);
+	if (!eq)
+		buf[2] = cpu_to_le32(r->level[1].sens);
+
+	BUG_ON(items > (sizeof(buf)/sizeof(buf[0])));
+
+	rc = put_entry(buf, sizeof(u32), items, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&r->level[0].cat, fp);
+	if (rc)
+		return rc;
+	if (!eq) {
+		rc = ebitmap_write(&r->level[1].cat, fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int sens_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct level_datum *levdatum = datum;
+	struct policy_data *pd = ptr;
+	void *fp = pd->fp;
+	__le32 buf[2];
+	size_t len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(levdatum->isalias);
+	rc = put_entry(buf, sizeof(u32), 2, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	rc = mls_write_level(levdatum->level, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int cat_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct cat_datum *catdatum = datum;
+	struct policy_data *pd = ptr;
+	void *fp = pd->fp;
+	__le32 buf[3];
+	size_t len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(catdatum->value);
+	buf[2] = cpu_to_le32(catdatum->isalias);
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int role_trans_write(struct role_trans *r, void *fp)
+{
+	struct role_trans *tr;
+	u32 buf[3];
+	size_t nel;
+	int rc;
+
+	nel = 0;
+	for (tr = r; tr; tr = tr->next)
+		nel++;
+	buf[0] = cpu_to_le32(nel);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+	for (tr = r; tr; tr = tr->next) {
+		buf[0] = cpu_to_le32(tr->role);
+		buf[1] = cpu_to_le32(tr->type);
+		buf[2] = cpu_to_le32(tr->new_role);
+		rc = put_entry(buf, sizeof(u32), 3, fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int role_allow_write(struct role_allow *r, void *fp)
+{
+	struct role_allow *ra;
+	u32 buf[2];
+	size_t nel;
+	int rc;
+
+	nel = 0;
+	for (ra = r; ra; ra = ra->next)
+		nel++;
+	buf[0] = cpu_to_le32(nel);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+	for (ra = r; ra; ra = ra->next) {
+		buf[0] = cpu_to_le32(ra->role);
+		buf[1] = cpu_to_le32(ra->new_role);
+		rc = put_entry(buf, sizeof(u32), 2, fp);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+/*
+ * Write a security context structure
+ * to a policydb binary representation file.
+ */
+static int context_write(struct policydb *p, struct context *c,
+			 void *fp)
+{
+	int rc;
+	__le32 buf[3];
+
+	buf[0] = cpu_to_le32(c->user);
+	buf[1] = cpu_to_le32(c->role);
+	buf[2] = cpu_to_le32(c->type);
+
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+
+	rc = mls_write_range_helper(&c->range, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+/*
+ * The following *_write functions are used to
+ * write the symbol data to a policy database
+ * binary representation file.
+ */
+
+static int perm_write(void *vkey, void *datum, void *fp)
+{
+	char *key = vkey;
+	struct perm_datum *perdatum = datum;
+	__le32 buf[2];
+	size_t len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(perdatum->value);
+	rc = put_entry(buf, sizeof(u32), 2, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int common_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct common_datum *comdatum = datum;
+	struct policy_data *pd = ptr;
+	void *fp = pd->fp;
+	__le32 buf[4];
+	size_t len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(comdatum->value);
+	buf[2] = cpu_to_le32(comdatum->permissions.nprim);
+	buf[3] = cpu_to_le32(comdatum->permissions.table->nel);
+	rc = put_entry(buf, sizeof(u32), 4, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	rc = hashtab_map(comdatum->permissions.table, perm_write, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int write_cons_helper(struct policydb *p, struct constraint_node *node,
+			     void *fp)
+{
+	struct constraint_node *c;
+	struct constraint_expr *e;
+	__le32 buf[3];
+	u32 nel;
+	int rc;
+
+	for (c = node; c; c = c->next) {
+		nel = 0;
+		for (e = c->expr; e; e = e->next)
+			nel++;
+		buf[0] = cpu_to_le32(c->permissions);
+		buf[1] = cpu_to_le32(nel);
+		rc = put_entry(buf, sizeof(u32), 2, fp);
+		if (rc)
+			return rc;
+		for (e = c->expr; e; e = e->next) {
+			buf[0] = cpu_to_le32(e->expr_type);
+			buf[1] = cpu_to_le32(e->attr);
+			buf[2] = cpu_to_le32(e->op);
+			rc = put_entry(buf, sizeof(u32), 3, fp);
+			if (rc)
+				return rc;
+
+			switch (e->expr_type) {
+			case CEXPR_NAMES:
+				rc = ebitmap_write(&e->names, fp);
+				if (rc)
+					return rc;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int class_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct class_datum *cladatum = datum;
+	struct policy_data *pd = ptr;
+	void *fp = pd->fp;
+	struct policydb *p = pd->p;
+	struct constraint_node *c;
+	__le32 buf[6];
+	u32 ncons;
+	size_t len, len2;
+	int rc;
+
+	len = strlen(key);
+	if (cladatum->comkey)
+		len2 = strlen(cladatum->comkey);
+	else
+		len2 = 0;
+
+	ncons = 0;
+	for (c = cladatum->constraints; c; c = c->next)
+		ncons++;
+
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(len2);
+	buf[2] = cpu_to_le32(cladatum->value);
+	buf[3] = cpu_to_le32(cladatum->permissions.nprim);
+	if (cladatum->permissions.table)
+		buf[4] = cpu_to_le32(cladatum->permissions.table->nel);
+	else
+		buf[4] = 0;
+	buf[5] = cpu_to_le32(ncons);
+	rc = put_entry(buf, sizeof(u32), 6, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	if (cladatum->comkey) {
+		rc = put_entry(cladatum->comkey, 1, len2, fp);
+		if (rc)
+			return rc;
+	}
+
+	rc = hashtab_map(cladatum->permissions.table, perm_write, fp);
+	if (rc)
+		return rc;
+
+	rc = write_cons_helper(p, cladatum->constraints, fp);
+	if (rc)
+		return rc;
+
+	/* write out the validatetrans rule */
+	ncons = 0;
+	for (c = cladatum->validatetrans; c; c = c->next)
+		ncons++;
+
+	buf[0] = cpu_to_le32(ncons);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	rc = write_cons_helper(p, cladatum->validatetrans, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int role_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct role_datum *role = datum;
+	struct policy_data *pd = ptr;
+	void *fp = pd->fp;
+	struct policydb *p = pd->p;
+	__le32 buf[3];
+	size_t items, len;
+	int rc;
+
+	len = strlen(key);
+	items = 0;
+	buf[items++] = cpu_to_le32(len);
+	buf[items++] = cpu_to_le32(role->value);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		buf[items++] = cpu_to_le32(role->bounds);
+
+	BUG_ON(items > (sizeof(buf)/sizeof(buf[0])));
+
+	rc = put_entry(buf, sizeof(u32), items, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&role->dominates, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&role->types, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int type_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct type_datum *typdatum = datum;
+	struct policy_data *pd = ptr;
+	struct policydb *p = pd->p;
+	void *fp = pd->fp;
+	__le32 buf[4];
+	int rc;
+	size_t items, len;
+
+	len = strlen(key);
+	items = 0;
+	buf[items++] = cpu_to_le32(len);
+	buf[items++] = cpu_to_le32(typdatum->value);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) {
+		u32 properties = 0;
+
+		if (typdatum->primary)
+			properties |= TYPEDATUM_PROPERTY_PRIMARY;
+
+		if (typdatum->attribute)
+			properties |= TYPEDATUM_PROPERTY_ATTRIBUTE;
+
+		buf[items++] = cpu_to_le32(properties);
+		buf[items++] = cpu_to_le32(typdatum->bounds);
+	} else {
+		buf[items++] = cpu_to_le32(typdatum->primary);
+	}
+	BUG_ON(items > (sizeof(buf) / sizeof(buf[0])));
+	rc = put_entry(buf, sizeof(u32), items, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int user_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct user_datum *usrdatum = datum;
+	struct policy_data *pd = ptr;
+	struct policydb *p = pd->p;
+	void *fp = pd->fp;
+	__le32 buf[3];
+	size_t items, len;
+	int rc;
+
+	len = strlen(key);
+	items = 0;
+	buf[items++] = cpu_to_le32(len);
+	buf[items++] = cpu_to_le32(usrdatum->value);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		buf[items++] = cpu_to_le32(usrdatum->bounds);
+	BUG_ON(items > (sizeof(buf) / sizeof(buf[0])));
+	rc = put_entry(buf, sizeof(u32), items, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&usrdatum->roles, fp);
+	if (rc)
+		return rc;
+
+	rc = mls_write_range_helper(&usrdatum->range, fp);
+	if (rc)
+		return rc;
+
+	rc = mls_write_level(&usrdatum->dfltlevel, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int (*write_f[SYM_NUM]) (void *key, void *datum,
+				void *datap) =
+{
+	common_write,
+	class_write,
+	role_write,
+	type_write,
+	user_write,
+	cond_write_bool,
+	sens_write,
+	cat_write,
+};
+
+static int ocontext_write(struct policydb *p, struct policydb_compat_info *info,
+			  void *fp)
+{
+	unsigned int i, j, rc;
+	size_t nel, len;
+	__le32 buf[3];
+	u32 nodebuf[8];
+	struct ocontext *c;
+	for (i = 0; i < info->ocon_num; i++) {
+		nel = 0;
+		for (c = p->ocontexts[i]; c; c = c->next)
+			nel++;
+		buf[0] = cpu_to_le32(nel);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+		for (c = p->ocontexts[i]; c; c = c->next) {
+			switch (i) {
+			case OCON_ISID:
+				buf[0] = cpu_to_le32(c->sid[0]);
+				rc = put_entry(buf, sizeof(u32), 1, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_FS:
+			case OCON_NETIF:
+				len = strlen(c->u.name);
+				buf[0] = cpu_to_le32(len);
+				rc = put_entry(buf, sizeof(u32), 1, fp);
+				if (rc)
+					return rc;
+				rc = put_entry(c->u.name, 1, len, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[1], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_PORT:
+				buf[0] = cpu_to_le32(c->u.port.protocol);
+				buf[1] = cpu_to_le32(c->u.port.low_port);
+				buf[2] = cpu_to_le32(c->u.port.high_port);
+				rc = put_entry(buf, sizeof(u32), 3, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_NODE:
+				nodebuf[0] = c->u.node.addr; /* network order */
+				nodebuf[1] = c->u.node.mask; /* network order */
+				rc = put_entry(nodebuf, sizeof(u32), 2, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_FSUSE:
+				buf[0] = cpu_to_le32(c->v.behavior);
+				len = strlen(c->u.name);
+				buf[1] = cpu_to_le32(len);
+				rc = put_entry(buf, sizeof(u32), 2, fp);
+				if (rc)
+					return rc;
+				rc = put_entry(c->u.name, 1, len, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_NODE6:
+				for (j = 0; j < 4; j++)
+					nodebuf[j] = c->u.node6.addr[j]; /* network order */
+				for (j = 0; j < 4; j++)
+					nodebuf[j + 4] = c->u.node6.mask[j]; /* network order */
+				rc = put_entry(nodebuf, sizeof(u32), 8, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			}
+		}
+	}
+	return 0;
+}
+
+static int genfs_write(struct policydb *p, void *fp)
+{
+	struct genfs *genfs;
+	struct ocontext *c;
+	size_t len;
+	__le32 buf[1];
+	int rc;
+
+	len = 0;
+	for (genfs = p->genfs; genfs; genfs = genfs->next)
+		len++;
+	buf[0] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+	for (genfs = p->genfs; genfs; genfs = genfs->next) {
+		len = strlen(genfs->fstype);
+		buf[0] = cpu_to_le32(len);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+		rc = put_entry(genfs->fstype, 1, len, fp);
+		if (rc)
+			return rc;
+		len = 0;
+		for (c = genfs->head; c; c = c->next)
+			len++;
+		buf[0] = cpu_to_le32(len);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+		for (c = genfs->head; c; c = c->next) {
+			len = strlen(c->u.name);
+			buf[0] = cpu_to_le32(len);
+			rc = put_entry(buf, sizeof(u32), 1, fp);
+			if (rc)
+				return rc;
+			rc = put_entry(c->u.name, 1, len, fp);
+			if (rc)
+				return rc;
+			buf[0] = cpu_to_le32(c->v.sclass);
+			rc = put_entry(buf, sizeof(u32), 1, fp);
+			if (rc)
+				return rc;
+			rc = context_write(p, &c->context[0], fp);
+			if (rc)
+				return rc;
+		}
+	}
+	return 0;
+}
+
+static int range_count(void *key, void *data, void *ptr)
+{
+	int *cnt = ptr;
+	*cnt = *cnt + 1;
+
+	return 0;
+}
+
+static int range_write_helper(void *key, void *data, void *ptr)
+{
+	__le32 buf[2];
+	struct range_trans *rt = key;
+	struct mls_range *r = data;
+	struct policy_data *pd = ptr;
+	void *fp = pd->fp;
+	struct policydb *p = pd->p;
+	int rc;
+
+	buf[0] = cpu_to_le32(rt->source_type);
+	buf[1] = cpu_to_le32(rt->target_type);
+	rc = put_entry(buf, sizeof(u32), 2, fp);
+	if (rc)
+		return rc;
+	if (p->policyvers >= POLICYDB_VERSION_RANGETRANS) {
+		buf[0] = cpu_to_le32(rt->target_class);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+	}
+	rc = mls_write_range_helper(r, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int range_write(struct policydb *p, void *fp)
+{
+	size_t nel;
+	__le32 buf[1];
+	int rc;
+	struct policy_data pd;
+
+	pd.p = p;
+	pd.fp = fp;
+
+	/* count the number of entries in the hashtab */
+	nel = 0;
+	rc = hashtab_map(p->range_tr, range_count, &nel);
+	if (rc)
+		return rc;
+
+	buf[0] = cpu_to_le32(nel);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	/* actually write all of the entries */
+	rc = hashtab_map(p->range_tr, range_write_helper, &pd);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+/*
+ * Write the configuration data in a policy database
+ * structure to a policy database binary representation
+ * file.
+ */
+int policydb_write(struct policydb *p, void *fp)
+{
+	unsigned int i, num_syms;
+	int rc;
+	__le32 buf[4];
+	u32 config;
+	size_t len;
+	struct policydb_compat_info *info;
+
+	/*
+	 * refuse to write policy older than compressed avtab
+	 * to simplify the writer.  There are other tests dropped
+	 * since we assume this throughout the writer code.  Be
+	 * careful if you ever try to remove this restriction
+	 */
+	if (p->policyvers < POLICYDB_VERSION_AVTAB) {
+		printk(KERN_ERR "SELinux: refusing to write policy version %d."
+		       "  Because it is less than version %d\n", p->policyvers,
+		       POLICYDB_VERSION_AVTAB);
+		return -EINVAL;
+	}
+
+	config = 0;
+	if (p->mls_enabled)
+		config |= POLICYDB_CONFIG_MLS;
+
+	if (p->reject_unknown)
+		config |= REJECT_UNKNOWN;
+	if (p->allow_unknown)
+		config |= ALLOW_UNKNOWN;
+
+	/* Write the magic number and string identifiers. */
+	buf[0] = cpu_to_le32(POLICYDB_MAGIC);
+	len = strlen(POLICYDB_STRING);
+	buf[1] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 2, fp);
+	if (rc)
+		return rc;
+	rc = put_entry(POLICYDB_STRING, 1, len, fp);
+	if (rc)
+		return rc;
+
+	/* Write the version, config, and table sizes. */
+	info = policydb_lookup_compat(p->policyvers);
+	if (!info) {
+		printk(KERN_ERR "SELinux: compatibility lookup failed for policy "
+		    "version %d", p->policyvers);
+		return rc;
+	}
+
+	buf[0] = cpu_to_le32(p->policyvers);
+	buf[1] = cpu_to_le32(config);
+	buf[2] = cpu_to_le32(info->sym_num);
+	buf[3] = cpu_to_le32(info->ocon_num);
+
+	rc = put_entry(buf, sizeof(u32), 4, fp);
+	if (rc)
+		return rc;
+
+	if (p->policyvers >= POLICYDB_VERSION_POLCAP) {
+		rc = ebitmap_write(&p->policycaps, fp);
+		if (rc)
+			return rc;
+	}
+
+	if (p->policyvers >= POLICYDB_VERSION_PERMISSIVE) {
+		rc = ebitmap_write(&p->permissive_map, fp);
+		if (rc)
+			return rc;
+	}
+
+	num_syms = info->sym_num;
+	for (i = 0; i < num_syms; i++) {
+		struct policy_data pd;
+
+		pd.fp = fp;
+		pd.p = p;
+
+		buf[0] = cpu_to_le32(p->symtab[i].nprim);
+		buf[1] = cpu_to_le32(p->symtab[i].table->nel);
+
+		rc = put_entry(buf, sizeof(u32), 2, fp);
+		if (rc)
+			return rc;
+		rc = hashtab_map(p->symtab[i].table, write_f[i], &pd);
+		if (rc)
+			return rc;
+	}
+
+	rc = avtab_write(p, &p->te_avtab, fp);
+	if (rc)
+		return rc;
+
+	rc = cond_write_list(p, p->cond_list, fp);
+	if (rc)
+		return rc;
+
+	rc = role_trans_write(p->role_tr, fp);
+	if (rc)
+		return rc;
+
+	rc = role_allow_write(p->role_allow, fp);
+	if (rc)
+		return rc;
+
+	rc = ocontext_write(p, info, fp);
+	if (rc)
+		return rc;
+
+	rc = genfs_write(p, fp);
+	if (rc)
+		return rc;
+
+	rc = range_write(p, fp);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < p->p_types.nprim; i++) {
+		struct ebitmap *e = flex_array_get(p->type_attr_map_array, i);
+
+		BUG_ON(!e);
+		rc = ebitmap_write(e, fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h
index 310e944..95d3d7d 100644
--- a/security/selinux/ss/policydb.h
+++ b/security/selinux/ss/policydb.h
@@ -254,6 +254,9 @@
 
 	struct ebitmap permissive_map;
 
+	/* length of this policy when it was loaded */
+	size_t len;
+
 	unsigned int policyvers;
 
 	unsigned int reject_unknown : 1;
@@ -270,6 +273,7 @@
 extern int policydb_type_isvalid(struct policydb *p, unsigned int type);
 extern int policydb_role_isvalid(struct policydb *p, unsigned int role);
 extern int policydb_read(struct policydb *p, void *fp);
+extern int policydb_write(struct policydb *p, void *fp);
 
 #define PERM_SYMTAB_SIZE 32
 
@@ -290,6 +294,11 @@
 	size_t len;
 };
 
+struct policy_data {
+	struct policydb *p;
+	void *fp;
+};
+
 static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes)
 {
 	if (bytes > fp->len)
@@ -301,6 +310,17 @@
 	return 0;
 }
 
+static inline int put_entry(void *buf, size_t bytes, int num, struct policy_file *fp)
+{
+	size_t len = bytes * num;
+
+	memcpy(fp->data, buf, len);
+	fp->data += len;
+	fp->len -= len;
+
+	return 0;
+}
+
 extern u16 string_to_security_class(struct policydb *p, const char *name);
 extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name);
 
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 9ea2fec..223c1ff 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -51,6 +51,7 @@
 #include <linux/mutex.h>
 #include <linux/selinux.h>
 #include <linux/flex_array.h>
+#include <linux/vmalloc.h>
 #include <net/netlabel.h>
 
 #include "flask.h"
@@ -991,7 +992,8 @@
 {
 	char *scontextp;
 
-	*scontext = NULL;
+	if (scontext)
+		*scontext = NULL;
 	*scontext_len = 0;
 
 	if (context->len) {
@@ -1008,6 +1010,9 @@
 	*scontext_len += strlen(policydb.p_type_val_to_name[context->type - 1]) + 1;
 	*scontext_len += mls_compute_context_len(context);
 
+	if (!scontext)
+		return 0;
+
 	/* Allocate space for the context; caller must free this space. */
 	scontextp = kmalloc(*scontext_len, GFP_ATOMIC);
 	if (!scontextp)
@@ -1047,7 +1052,8 @@
 	struct context *context;
 	int rc = 0;
 
-	*scontext = NULL;
+	if (scontext)
+		*scontext = NULL;
 	*scontext_len  = 0;
 
 	if (!ss_initialized) {
@@ -1055,6 +1061,8 @@
 			char *scontextp;
 
 			*scontext_len = strlen(initial_sid_to_string[sid]) + 1;
+			if (!scontext)
+				goto out;
 			scontextp = kmalloc(*scontext_len, GFP_ATOMIC);
 			if (!scontextp) {
 				rc = -ENOMEM;
@@ -1769,6 +1777,7 @@
 			return rc;
 		}
 
+		policydb.len = len;
 		rc = selinux_set_mapping(&policydb, secclass_map,
 					 &current_mapping,
 					 &current_mapping_size);
@@ -1791,6 +1800,7 @@
 		selinux_complete_init();
 		avc_ss_reset(seqno);
 		selnl_notify_policyload(seqno);
+		selinux_status_update_policyload(seqno);
 		selinux_netlbl_cache_invalidate();
 		selinux_xfrm_notify_policyload();
 		return 0;
@@ -1804,6 +1814,7 @@
 	if (rc)
 		return rc;
 
+	newpolicydb.len = len;
 	/* If switching between different policy types, log MLS status */
 	if (policydb.mls_enabled && !newpolicydb.mls_enabled)
 		printk(KERN_INFO "SELinux: Disabling MLS support...\n");
@@ -1870,6 +1881,7 @@
 
 	avc_ss_reset(seqno);
 	selnl_notify_policyload(seqno);
+	selinux_status_update_policyload(seqno);
 	selinux_netlbl_cache_invalidate();
 	selinux_xfrm_notify_policyload();
 
@@ -1883,6 +1895,17 @@
 
 }
 
+size_t security_policydb_len(void)
+{
+	size_t len;
+
+	read_lock(&policy_rwlock);
+	len = policydb.len;
+	read_unlock(&policy_rwlock);
+
+	return len;
+}
+
 /**
  * security_port_sid - Obtain the SID for a port.
  * @protocol: protocol number
@@ -2374,6 +2397,7 @@
 	if (!rc) {
 		avc_ss_reset(seqno);
 		selnl_notify_policyload(seqno);
+		selinux_status_update_policyload(seqno);
 		selinux_xfrm_notify_policyload();
 	}
 	return rc;
@@ -3129,3 +3153,38 @@
 	return rc;
 }
 #endif /* CONFIG_NETLABEL */
+
+/**
+ * security_read_policy - read the policy.
+ * @data: binary policy data
+ * @len: length of data in bytes
+ *
+ */
+int security_read_policy(void **data, ssize_t *len)
+{
+	int rc;
+	struct policy_file fp;
+
+	if (!ss_initialized)
+		return -EINVAL;
+
+	*len = security_policydb_len();
+
+	*data = vmalloc_user(*len);
+	if (!*data)
+		return -ENOMEM;
+
+	fp.data = *data;
+	fp.len = *len;
+
+	read_lock(&policy_rwlock);
+	rc = policydb_write(&policydb, &fp);
+	read_unlock(&policy_rwlock);
+
+	if (rc)
+		return rc;
+
+	*len = (unsigned long)fp.data - (unsigned long)*data;
+	return 0;
+
+}
diff --git a/security/selinux/ss/status.c b/security/selinux/ss/status.c
new file mode 100644
index 0000000..d982365
--- /dev/null
+++ b/security/selinux/ss/status.c
@@ -0,0 +1,126 @@
+/*
+ * mmap based event notifications for SELinux
+ *
+ * Author: KaiGai Kohei <kaigai@ak.jp.nec.com>
+ *
+ * Copyright (C) 2010 NEC corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include "avc.h"
+#include "services.h"
+
+/*
+ * The selinux_status_page shall be exposed to userspace applications
+ * using mmap interface on /selinux/status.
+ * It enables to notify applications a few events that will cause reset
+ * of userspace access vector without context switching.
+ *
+ * The selinux_kernel_status structure on the head of status page is
+ * protected from concurrent accesses using seqlock logic, so userspace
+ * application should reference the status page according to the seqlock
+ * logic.
+ *
+ * Typically, application checks status->sequence at the head of access
+ * control routine. If it is odd-number, kernel is updating the status,
+ * so please wait for a moment. If it is changed from the last sequence
+ * number, it means something happen, so application will reset userspace
+ * avc, if needed.
+ * In most cases, application shall confirm the kernel status is not
+ * changed without any system call invocations.
+ */
+static struct page *selinux_status_page;
+static DEFINE_MUTEX(selinux_status_lock);
+
+/*
+ * selinux_kernel_status_page
+ *
+ * It returns a reference to selinux_status_page. If the status page is
+ * not allocated yet, it also tries to allocate it at the first time.
+ */
+struct page *selinux_kernel_status_page(void)
+{
+	struct selinux_kernel_status   *status;
+	struct page		       *result = NULL;
+
+	mutex_lock(&selinux_status_lock);
+	if (!selinux_status_page) {
+		selinux_status_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
+
+		if (selinux_status_page) {
+			status = page_address(selinux_status_page);
+
+			status->version = SELINUX_KERNEL_STATUS_VERSION;
+			status->sequence = 0;
+			status->enforcing = selinux_enforcing;
+			/*
+			 * NOTE: the next policyload event shall set
+			 * a positive value on the status->policyload,
+			 * although it may not be 1, but never zero.
+			 * So, application can know it was updated.
+			 */
+			status->policyload = 0;
+			status->deny_unknown = !security_get_allow_unknown();
+		}
+	}
+	result = selinux_status_page;
+	mutex_unlock(&selinux_status_lock);
+
+	return result;
+}
+
+/*
+ * selinux_status_update_setenforce
+ *
+ * It updates status of the current enforcing/permissive mode.
+ */
+void selinux_status_update_setenforce(int enforcing)
+{
+	struct selinux_kernel_status   *status;
+
+	mutex_lock(&selinux_status_lock);
+	if (selinux_status_page) {
+		status = page_address(selinux_status_page);
+
+		status->sequence++;
+		smp_wmb();
+
+		status->enforcing = enforcing;
+
+		smp_wmb();
+		status->sequence++;
+	}
+	mutex_unlock(&selinux_status_lock);
+}
+
+/*
+ * selinux_status_update_policyload
+ *
+ * It updates status of the times of policy reloaded, and current
+ * setting of deny_unknown.
+ */
+void selinux_status_update_policyload(int seqno)
+{
+	struct selinux_kernel_status   *status;
+
+	mutex_lock(&selinux_status_lock);
+	if (selinux_status_page) {
+		status = page_address(selinux_status_page);
+
+		status->sequence++;
+		smp_wmb();
+
+		status->policyload = seqno;
+		status->deny_unknown = !security_get_allow_unknown();
+
+		smp_wmb();
+		status->sequence++;
+	}
+	mutex_unlock(&selinux_status_lock);
+}
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index c448d57..bc39f40 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1281,12 +1281,11 @@
  *
  * Return 0 if read access is permitted
  */
-static int smack_task_setscheduler(struct task_struct *p, int policy,
-				   struct sched_param *lp)
+static int smack_task_setscheduler(struct task_struct *p)
 {
 	int rc;
 
-	rc = cap_task_setscheduler(p, policy, lp);
+	rc = cap_task_setscheduler(p);
 	if (rc == 0)
 		rc = smk_curacc_on_task(p, MAY_WRITE);
 	return rc;
@@ -3005,7 +3004,8 @@
 {
 	char *sp = smack_from_secid(secid);
 
-	*secdata = sp;
+	if (secdata)
+		*secdata = sp;
 	*seclen = strlen(sp);
 	return 0;
 }
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index a2b72d7..7512502 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -968,6 +968,7 @@
 static const struct file_operations smk_doi_ops = {
 	.read		= smk_read_doi,
 	.write		= smk_write_doi,
+	.llseek		= default_llseek,
 };
 
 /**
@@ -1031,6 +1032,7 @@
 static const struct file_operations smk_direct_ops = {
 	.read		= smk_read_direct,
 	.write		= smk_write_direct,
+	.llseek		= default_llseek,
 };
 
 /**
@@ -1112,6 +1114,7 @@
 static const struct file_operations smk_ambient_ops = {
 	.read		= smk_read_ambient,
 	.write		= smk_write_ambient,
+	.llseek		= default_llseek,
 };
 
 /**
@@ -1191,6 +1194,7 @@
 static const struct file_operations smk_onlycap_ops = {
 	.read		= smk_read_onlycap,
 	.write		= smk_write_onlycap,
+	.llseek		= default_llseek,
 };
 
 /**
@@ -1255,6 +1259,7 @@
 static const struct file_operations smk_logging_ops = {
 	.read		= smk_read_logging,
 	.write		= smk_write_logging,
+	.llseek		= default_llseek,
 };
 /**
  * smk_fill_super - fill the /smackfs superblock
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index c668b44..7556315 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -768,8 +768,10 @@
 		return true; /* Do nothing if open(O_WRONLY). */
 	memset(&head->r, 0, sizeof(head->r));
 	head->r.print_this_domain_only = true;
-	head->r.eof = !domain;
-	head->r.domain = &domain->list;
+	if (domain)
+		head->r.domain = &domain->list;
+	else
+		head->r.eof = 1;
 	tomoyo_io_printf(head, "# select %s\n", data);
 	if (domain && domain->is_deleted)
 		tomoyo_io_printf(head, "# This is a deleted domain.\n");
@@ -2051,13 +2053,22 @@
 		const u8 profile = domain->profile;
 		if (tomoyo_profile_ptr[profile])
 			continue;
+		printk(KERN_ERR "You need to define profile %u before using it.\n",
+		       profile);
+		printk(KERN_ERR "Please see http://tomoyo.sourceforge.jp/2.3/ "
+		       "for more information.\n");
 		panic("Profile %u (used by '%s') not defined.\n",
 		      profile, domain->domainname->name);
 	}
 	tomoyo_read_unlock(idx);
-	if (tomoyo_profile_version != 20090903)
+	if (tomoyo_profile_version != 20090903) {
+		printk(KERN_ERR "You need to install userland programs for "
+		       "TOMOYO 2.3 and initialize policy configuration.\n");
+		printk(KERN_ERR "Please see http://tomoyo.sourceforge.jp/2.3/ "
+		       "for more information.\n");
 		panic("Profile version %u is not supported.\n",
 		      tomoyo_profile_version);
+	}
 	printk(KERN_INFO "TOMOYO: 2.3.0\n");
 	printk(KERN_INFO "Mandatory Access Control activated.\n");
 }
diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c
index f25e3cc..a1f1a2f 100644
--- a/sound/core/seq/oss/seq_oss.c
+++ b/sound/core/seq/oss/seq_oss.c
@@ -220,6 +220,7 @@
 	.poll =		odev_poll,
 	.unlocked_ioctl =	odev_ioctl,
 	.compat_ioctl =	odev_ioctl_compat,
+	.llseek =	noop_llseek,
 };
 
 static int __init
diff --git a/sound/core/sound.c b/sound/core/sound.c
index ac42af4..62a093e 100644
--- a/sound/core/sound.c
+++ b/sound/core/sound.c
@@ -184,7 +184,8 @@
 static const struct file_operations snd_fops =
 {
 	.owner =	THIS_MODULE,
-	.open =		snd_open
+	.open =		snd_open,
+	.llseek =	noop_llseek,
 };
 
 #ifdef CONFIG_SND_DYNAMIC_MINORS
diff --git a/sound/oss/msnd_pinnacle.c b/sound/oss/msnd_pinnacle.c
index 2e48b17..ca942f7 100644
--- a/sound/oss/msnd_pinnacle.c
+++ b/sound/oss/msnd_pinnacle.c
@@ -1117,6 +1117,7 @@
 	.unlocked_ioctl	= dev_ioctl,
 	.open		= dev_open,
 	.release	= dev_release,
+	.llseek		= noop_llseek,
 };
 
 static int reset_dsp(void)
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf.c b/sound/pcmcia/pdaudiocf/pdaudiocf.c
index 7ab9174..8cc4733 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf.c
@@ -142,10 +142,9 @@
 	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 	link->resource[0]->end = 16;
 
-	link->conf.Attributes = CONF_ENABLE_IRQ | CONF_ENABLE_PULSE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-	link->conf.ConfigIndex = 1;
-	link->conf.Present = PRESENT_OPTION;
+	link->config_flags = CONF_ENABLE_IRQ | CONF_ENABLE_PULSE_IRQ;
+	link->config_index = 1;
+	link->config_regs = PRESENT_OPTION;
 
 	return pdacf_config(link);
 }
@@ -217,7 +216,8 @@
 	int ret;
 
 	snd_printdd(KERN_DEBUG "pdacf_config called\n");
-	link->conf.ConfigIndex = 0x5;
+	link->config_index = 0x5;
+	link->config_flags |= CONF_ENABLE_IRQ | CONF_ENABLE_PULSE_IRQ;
 
 	ret = pcmcia_request_io(link);
 	if (ret)
@@ -227,7 +227,7 @@
 	if (ret)
 		goto failed;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -287,9 +287,7 @@
 
 static struct pcmcia_driver pdacf_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "snd-pdaudiocf",
-	},
+	.name		= "snd-pdaudiocf",
 	.probe		= snd_pdacf_probe,
 	.remove		= snd_pdacf_detach,
 	.id_table	= snd_pdacf_ids,
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf.h b/sound/pcmcia/pdaudiocf/pdaudiocf.h
index 5cc3e45..bd26e09 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf.h
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf.h
@@ -24,7 +24,6 @@
 #include <sound/pcm.h>
 #include <asm/io.h>
 #include <linux/interrupt.h>
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
diff --git a/sound/pcmcia/vx/vxpocket.c b/sound/pcmcia/vx/vxpocket.c
index a6edfc3..80000d6 100644
--- a/sound/pcmcia/vx/vxpocket.c
+++ b/sound/pcmcia/vx/vxpocket.c
@@ -2,7 +2,7 @@
  * Driver for Digigram VXpocket V2/440 soundcards
  *
  * Copyright (c) 2002 by Takashi Iwai <tiwai@suse.de>
- *
+
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation; either version 2 of the License, or
@@ -162,10 +162,9 @@
 	link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO;
 	link->resource[0]->end = 16;
 
-	link->conf.Attributes = CONF_ENABLE_IRQ;
-	link->conf.IntType = INT_MEMORY_AND_IO;
-	link->conf.ConfigIndex = 1;
-	link->conf.Present = PRESENT_OPTION;
+	link->config_flags |= CONF_ENABLE_IRQ;
+	link->config_index = 1;
+	link->config_regs = PRESENT_OPTION;
 
 	*chip_ret = vxp;
 	return 0;
@@ -234,7 +233,7 @@
 	if (ret)
 		goto failed;
 
-	ret = pcmcia_request_configuration(link, &link->conf);
+	ret = pcmcia_enable_device(link);
 	if (ret)
 		goto failed;
 
@@ -359,9 +358,7 @@
 
 static struct pcmcia_driver vxp_cs_driver = {
 	.owner		= THIS_MODULE,
-	.drv		= {
-		.name	= "snd-vxpocket",
-	},
+	.name		= "snd-vxpocket",
 	.probe		= vxpocket_probe,
 	.remove		= vxpocket_detach,
 	.id_table	= vxp_ids,
diff --git a/sound/pcmcia/vx/vxpocket.h b/sound/pcmcia/vx/vxpocket.h
index d911066..13d658c 100644
--- a/sound/pcmcia/vx/vxpocket.h
+++ b/sound/pcmcia/vx/vxpocket.h
@@ -23,7 +23,6 @@
 
 #include <sound/vx_core.h>
 
-#include <pcmcia/cs.h>
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index acc91da..4057d35 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -223,6 +223,7 @@
 	.open = codec_reg_open_file,
 	.read = codec_reg_read_file,
 	.write = codec_reg_write_file,
+	.llseek = default_llseek,
 };
 
 static void soc_init_codec_debugfs(struct snd_soc_codec *codec)
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 03cb7c0..72a53d0 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1089,6 +1089,7 @@
 static const struct file_operations dapm_widget_power_fops = {
 	.open = dapm_widget_power_open_file,
 	.read = dapm_widget_power_read_file,
+	.llseek = default_llseek,
 };
 
 void snd_soc_dapm_debugfs_init(struct snd_soc_codec *codec)
diff --git a/sound/sound_core.c b/sound/sound_core.c
index cb61317..c03bbae 100644
--- a/sound/sound_core.c
+++ b/sound/sound_core.c
@@ -165,6 +165,7 @@
 	/* We must have an owner or the module locking fails */
 	.owner	= THIS_MODULE,
 	.open	= soundcore_open,
+	.llseek = noop_llseek,
 };
 
 /*
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 5164a65..b2c6330 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -8,7 +8,7 @@
 SYNOPSIS
 --------
 [verse]
-'perf annotate' [-i <file> | --input=file] symbol_name
+'perf annotate' [-i <file> | --input=file] [symbol_name]
 
 DESCRIPTION
 -----------
@@ -24,6 +24,13 @@
 --input=::
         Input file name. (default: perf.data)
 
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface Use of --tui requires a tty, if one is not
+	present, as when piping to other commands, the stdio interface is
+	used. This interfaces starts by centering on the line with more
+	samples, TAB/UNTAB cycles thru the lines with more samples.
+
 SEE ALSO
 --------
-linkperf:perf-record[1]
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index abfabe9..12052c9 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -65,6 +65,13 @@
 		 the tree is considered as a new profiled object. +
 	Default: fractal,0.5.
 
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface, that is integrated with annotate and allows
+        zooming into DSOs or threads, among other features. Use of --tui
+	requires a tty, if one is not present, as when piping to other
+	commands, the stdio interface is used.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 1950e19..d1db0f6 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -313,6 +313,9 @@
 
 SCRIPT_SH += perf-archive.sh
 
+grep-libs = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+
 #
 # No Perl scripts right now:
 #
@@ -588,14 +591,17 @@
 ifdef NO_LIBPERL
 	BASIC_CFLAGS += -DNO_LIBPERL
 else
-	PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null`
+       PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
+       PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
+       PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
 	PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
 	FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
 	ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED)),y)
 		BASIC_CFLAGS += -DNO_LIBPERL
 	else
-		ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
+               ALL_LDFLAGS += $(PERL_EMBED_LDFLAGS)
+               EXTLIBS += $(PERL_EMBED_LIBADD)
 		LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
 		LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
 	endif
@@ -604,13 +610,16 @@
 ifdef NO_LIBPYTHON
 	BASIC_CFLAGS += -DNO_LIBPYTHON
 else
-	PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null`
+       PYTHON_EMBED_LDOPTS = $(shell python-config --ldflags 2>/dev/null)
+       PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+       PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
 	PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
 	FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 	ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
 		BASIC_CFLAGS += -DNO_LIBPYTHON
 	else
-		ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
+               ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
+               EXTLIBS += $(PYTHON_EMBED_LIBADD)
 		LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
 		LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
 	endif
@@ -653,6 +662,15 @@
 	endif
 endif
 
+
+ifdef NO_STRLCPY
+	BASIC_CFLAGS += -DNO_STRLCPY
+else
+	ifneq ($(call try-cc,$(SOURCE_STRLCPY),),y)
+		BASIC_CFLAGS += -DNO_STRLCPY
+	endif
+endif
+
 ifndef CC_LD_DYNPATH
 	ifdef NO_R_TO_GCC_LINKER
 		# Some gcc does not accept and pass -R to the linker to specify
@@ -910,8 +928,8 @@
 		$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
 
 $(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
-	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(OUTPUT)perf.o \
-		$(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS)
+	$(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \
+               $(BUILTIN_OBJS) $(LIBS) -o $@
 
 $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1478dc6..6d5604d8d 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -28,7 +28,7 @@
 
 static char		const *input_name = "perf.data";
 
-static bool		force;
+static bool		force, use_tui, use_stdio;
 
 static bool		full_paths;
 
@@ -321,7 +321,7 @@
 
 static void hists__find_annotations(struct hists *self)
 {
-	struct rb_node *first = rb_first(&self->entries), *nd = first;
+	struct rb_node *nd = rb_first(&self->entries), *next;
 	int key = KEY_RIGHT;
 
 	while (nd) {
@@ -343,20 +343,19 @@
 
 		if (use_browser > 0) {
 			key = hist_entry__tui_annotate(he);
-			if (is_exit_key(key))
-				break;
 			switch (key) {
 			case KEY_RIGHT:
-			case '\t':
-				nd = rb_next(nd);
+				next = rb_next(nd);
 				break;
 			case KEY_LEFT:
-				if (nd == first)
-					continue;
-				nd = rb_prev(nd);
-			default:
+				next = rb_prev(nd);
 				break;
+			default:
+				return;
 			}
+
+			if (next != NULL)
+				nd = next;
 		} else {
 			hist_entry__tty_annotate(he);
 			nd = rb_next(nd);
@@ -428,6 +427,8 @@
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
+	OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
@@ -443,6 +444,11 @@
 {
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 
+	if (use_stdio)
+		use_browser = 0;
+	else if (use_tui)
+		use_browser = 1;
+
 	setup_browser();
 
 	symbol_conf.priv_size = sizeof(struct sym_priv);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 55fc1f4..5de405d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -32,7 +32,7 @@
 
 static char		const *input_name = "perf.data";
 
-static bool		force;
+static bool		force, use_tui, use_stdio;
 static bool		hide_unresolved;
 static bool		dont_use_callchains;
 
@@ -107,7 +107,8 @@
 		goto out_free_syms;
 	err = 0;
 	if (symbol_conf.use_callchain) {
-		err = append_chain(he->callchain, data->callchain, syms, data->period);
+		err = callchain_append(he->callchain, data->callchain, syms,
+				       data->period);
 		if (err)
 			goto out_free_syms;
 	}
@@ -450,6 +451,8 @@
 		    "Show per-thread event counters"),
 	OPT_STRING(0, "pretty", &pretty_printing_style, "key",
 		   "pretty printing style key: normal raw"),
+	OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+	OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
@@ -482,8 +485,15 @@
 {
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
+	if (use_stdio)
+		use_browser = 0;
+	else if (use_tui)
+		use_browser = 1;
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser();
+	else
+		use_browser = 0;
 	/*
 	 * Only in the newt browser we are doing integrated annotation,
 	 * so don't allocate extra space that won't be used in the stdio
diff --git a/tools/perf/feature-tests.mak b/tools/perf/feature-tests.mak
index 7a7b608..b253db6 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/feature-tests.mak
@@ -110,6 +110,17 @@
 }
 endef
 
+define SOURCE_STRLCPY
+#include <stdlib.h>
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+
+int main(void)
+{
+	strlcpy(NULL, NULL, 0);
+	return 0;
+}
+endef
+
 # try-cc
 # Usage: option = $(call try-cc, source-to-build, cc-options)
 try-cc = $(shell sh -c						  \
diff --git a/tools/perf/scripts/python/bin/netdev-times-record b/tools/perf/scripts/python/bin/netdev-times-record
new file mode 100644
index 0000000..d931a82
--- /dev/null
+++ b/tools/perf/scripts/python/bin/netdev-times-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+perf record -a -e net:net_dev_xmit -e net:net_dev_queue		\
+		-e net:netif_receive_skb -e net:netif_rx		\
+		-e skb:consume_skb -e skb:kfree_skb			\
+		-e skb:skb_copy_datagram_iovec -e napi:napi_poll	\
+		-e irq:irq_handler_entry -e irq:irq_handler_exit	\
+		-e irq:softirq_entry -e irq:softirq_exit		\
+		-e irq:softirq_raise $@
diff --git a/tools/perf/scripts/python/bin/netdev-times-report b/tools/perf/scripts/python/bin/netdev-times-report
new file mode 100644
index 0000000..c3d0a63
--- /dev/null
+++ b/tools/perf/scripts/python/bin/netdev-times-report
@@ -0,0 +1,5 @@
+#!/bin/bash
+# description: display a process of packet and processing time
+# args: [tx] [rx] [dev=] [debug]
+
+perf trace -s ~/libexec/perf-core/scripts/python/netdev-times.py $@
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
new file mode 100644
index 0000000..9aa0a32
--- /dev/null
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -0,0 +1,464 @@
+# Display a process of packets and processed time.
+# It helps us to investigate networking or network device.
+#
+# options
+# tx: show only tx chart
+# rx: show only rx chart
+# dev=: show only thing related to specified device
+# debug: work with debug mode. It shows buffer status.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+all_event_list = []; # insert all tracepoint event related with this script
+irq_dic = {}; # key is cpu and value is a list which stacks irqs
+              # which raise NET_RX softirq
+net_rx_dic = {}; # key is cpu and value include time of NET_RX softirq-entry
+		 # and a list which stacks receive
+receive_hunk_list = []; # a list which include a sequence of receive events
+rx_skb_list = []; # received packet list for matching
+		       # skb_copy_datagram_iovec
+
+buffer_budget = 65536; # the budget of rx_skb_list, tx_queue_list and
+		       # tx_xmit_list
+of_count_rx_skb_list = 0; # overflow count
+
+tx_queue_list = []; # list of packets which pass through dev_queue_xmit
+of_count_tx_queue_list = 0; # overflow count
+
+tx_xmit_list = [];  # list of packets which pass through dev_hard_start_xmit
+of_count_tx_xmit_list = 0; # overflow count
+
+tx_free_list = [];  # list of packets which is freed
+
+# options
+show_tx = 0;
+show_rx = 0;
+dev = 0; # store a name of device specified by option "dev="
+debug = 0;
+
+# indices of event_info tuple
+EINFO_IDX_NAME=   0
+EINFO_IDX_CONTEXT=1
+EINFO_IDX_CPU=    2
+EINFO_IDX_TIME=   3
+EINFO_IDX_PID=    4
+EINFO_IDX_COMM=   5
+
+# Calculate a time interval(msec) from src(nsec) to dst(nsec)
+def diff_msec(src, dst):
+	return (dst - src) / 1000000.0
+
+# Display a process of transmitting a packet
+def print_transmit(hunk):
+	if dev != 0 and hunk['dev'].find(dev) < 0:
+		return
+	print "%7s %5d %6d.%06dsec %12.3fmsec      %12.3fmsec" % \
+		(hunk['dev'], hunk['len'],
+		nsecs_secs(hunk['queue_t']),
+		nsecs_nsecs(hunk['queue_t'])/1000,
+		diff_msec(hunk['queue_t'], hunk['xmit_t']),
+		diff_msec(hunk['xmit_t'], hunk['free_t']))
+
+# Format for displaying rx packet processing
+PF_IRQ_ENTRY= "  irq_entry(+%.3fmsec irq=%d:%s)"
+PF_SOFT_ENTRY="  softirq_entry(+%.3fmsec)"
+PF_NAPI_POLL= "  napi_poll_exit(+%.3fmsec %s)"
+PF_JOINT=     "         |"
+PF_WJOINT=    "         |            |"
+PF_NET_RECV=  "         |---netif_receive_skb(+%.3fmsec skb=%x len=%d)"
+PF_NET_RX=    "         |---netif_rx(+%.3fmsec skb=%x)"
+PF_CPY_DGRAM= "         |      skb_copy_datagram_iovec(+%.3fmsec %d:%s)"
+PF_KFREE_SKB= "         |      kfree_skb(+%.3fmsec location=%x)"
+PF_CONS_SKB=  "         |      consume_skb(+%.3fmsec)"
+
+# Display a process of received packets and interrputs associated with
+# a NET_RX softirq
+def print_receive(hunk):
+	show_hunk = 0
+	irq_list = hunk['irq_list']
+	cpu = irq_list[0]['cpu']
+	base_t = irq_list[0]['irq_ent_t']
+	# check if this hunk should be showed
+	if dev != 0:
+		for i in range(len(irq_list)):
+			if irq_list[i]['name'].find(dev) >= 0:
+				show_hunk = 1
+				break
+	else:
+		show_hunk = 1
+	if show_hunk == 0:
+		return
+
+	print "%d.%06dsec cpu=%d" % \
+		(nsecs_secs(base_t), nsecs_nsecs(base_t)/1000, cpu)
+	for i in range(len(irq_list)):
+		print PF_IRQ_ENTRY % \
+			(diff_msec(base_t, irq_list[i]['irq_ent_t']),
+			irq_list[i]['irq'], irq_list[i]['name'])
+		print PF_JOINT
+		irq_event_list = irq_list[i]['event_list']
+		for j in range(len(irq_event_list)):
+			irq_event = irq_event_list[j]
+			if irq_event['event'] == 'netif_rx':
+				print PF_NET_RX % \
+					(diff_msec(base_t, irq_event['time']),
+					irq_event['skbaddr'])
+				print PF_JOINT
+	print PF_SOFT_ENTRY % \
+		diff_msec(base_t, hunk['sirq_ent_t'])
+	print PF_JOINT
+	event_list = hunk['event_list']
+	for i in range(len(event_list)):
+		event = event_list[i]
+		if event['event_name'] == 'napi_poll':
+			print PF_NAPI_POLL % \
+			    (diff_msec(base_t, event['event_t']), event['dev'])
+			if i == len(event_list) - 1:
+				print ""
+			else:
+				print PF_JOINT
+		else:
+			print PF_NET_RECV % \
+			    (diff_msec(base_t, event['event_t']), event['skbaddr'],
+				event['len'])
+			if 'comm' in event.keys():
+				print PF_WJOINT
+				print PF_CPY_DGRAM % \
+					(diff_msec(base_t, event['comm_t']),
+					event['pid'], event['comm'])
+			elif 'handle' in event.keys():
+				print PF_WJOINT
+				if event['handle'] == "kfree_skb":
+					print PF_KFREE_SKB % \
+						(diff_msec(base_t,
+						event['comm_t']),
+						event['location'])
+				elif event['handle'] == "consume_skb":
+					print PF_CONS_SKB % \
+						diff_msec(base_t,
+							event['comm_t'])
+			print PF_JOINT
+
+def trace_begin():
+	global show_tx
+	global show_rx
+	global dev
+	global debug
+
+	for i in range(len(sys.argv)):
+		if i == 0:
+			continue
+		arg = sys.argv[i]
+		if arg == 'tx':
+			show_tx = 1
+		elif arg =='rx':
+			show_rx = 1
+		elif arg.find('dev=',0, 4) >= 0:
+			dev = arg[4:]
+		elif arg == 'debug':
+			debug = 1
+	if show_tx == 0  and show_rx == 0:
+		show_tx = 1
+		show_rx = 1
+
+def trace_end():
+	# order all events in time
+	all_event_list.sort(lambda a,b :cmp(a[EINFO_IDX_TIME],
+					    b[EINFO_IDX_TIME]))
+	# process all events
+	for i in range(len(all_event_list)):
+		event_info = all_event_list[i]
+		name = event_info[EINFO_IDX_NAME]
+		if name == 'irq__softirq_exit':
+			handle_irq_softirq_exit(event_info)
+		elif name == 'irq__softirq_entry':
+			handle_irq_softirq_entry(event_info)
+		elif name == 'irq__softirq_raise':
+			handle_irq_softirq_raise(event_info)
+		elif name == 'irq__irq_handler_entry':
+			handle_irq_handler_entry(event_info)
+		elif name == 'irq__irq_handler_exit':
+			handle_irq_handler_exit(event_info)
+		elif name == 'napi__napi_poll':
+			handle_napi_poll(event_info)
+		elif name == 'net__netif_receive_skb':
+			handle_netif_receive_skb(event_info)
+		elif name == 'net__netif_rx':
+			handle_netif_rx(event_info)
+		elif name == 'skb__skb_copy_datagram_iovec':
+			handle_skb_copy_datagram_iovec(event_info)
+		elif name == 'net__net_dev_queue':
+			handle_net_dev_queue(event_info)
+		elif name == 'net__net_dev_xmit':
+			handle_net_dev_xmit(event_info)
+		elif name == 'skb__kfree_skb':
+			handle_kfree_skb(event_info)
+		elif name == 'skb__consume_skb':
+			handle_consume_skb(event_info)
+	# display receive hunks
+	if show_rx:
+		for i in range(len(receive_hunk_list)):
+			print_receive(receive_hunk_list[i])
+	# display transmit hunks
+	if show_tx:
+		print "   dev    len      Qdisc        " \
+			"       netdevice             free"
+		for i in range(len(tx_free_list)):
+			print_transmit(tx_free_list[i])
+	if debug:
+		print "debug buffer status"
+		print "----------------------------"
+		print "xmit Qdisc:remain:%d overflow:%d" % \
+			(len(tx_queue_list), of_count_tx_queue_list)
+		print "xmit netdevice:remain:%d overflow:%d" % \
+			(len(tx_xmit_list), of_count_tx_xmit_list)
+		print "receive:remain:%d overflow:%d" % \
+			(len(rx_skb_list), of_count_rx_skb_list)
+
+# called from perf, when it finds a correspoinding event
+def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec):
+	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+		return
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+	all_event_list.append(event_info)
+
+def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm,
+			irq, irq_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			irq, irq_name)
+	all_event_list.append(event_info)
+
+def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
+	all_event_list.append(event_info)
+
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			napi, dev_name)
+	all_event_list.append(event_info)
+
+def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+			skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+			skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, skblen, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, dev_name)
+	all_event_list.append(event_info)
+
+def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, skblen, rc, dev_name):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen, rc ,dev_name)
+	all_event_list.append(event_info)
+
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, protocol, location):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, protocol, location)
+	all_event_list.append(event_info)
+
+def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr)
+	all_event_list.append(event_info)
+
+def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm,
+	skbaddr, skblen):
+	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+			skbaddr, skblen)
+	all_event_list.append(event_info)
+
+def handle_irq_handler_entry(event_info):
+	(name, context, cpu, time, pid, comm, irq, irq_name) = event_info
+	if cpu not in irq_dic.keys():
+		irq_dic[cpu] = []
+	irq_record = {'irq':irq, 'name':irq_name, 'cpu':cpu, 'irq_ent_t':time}
+	irq_dic[cpu].append(irq_record)
+
+def handle_irq_handler_exit(event_info):
+	(name, context, cpu, time, pid, comm, irq, ret) = event_info
+	if cpu not in irq_dic.keys():
+		return
+	irq_record = irq_dic[cpu].pop()
+	if irq != irq_record['irq']:
+		return
+	irq_record.update({'irq_ext_t':time})
+	# if an irq doesn't include NET_RX softirq, drop.
+	if 'event_list' in irq_record.keys():
+		irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_raise(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	if cpu not in irq_dic.keys() \
+	or len(irq_dic[cpu]) == 0:
+		return
+	irq_record = irq_dic[cpu].pop()
+	if 'event_list' in irq_record.keys():
+		irq_event_list = irq_record['event_list']
+	else:
+		irq_event_list = []
+	irq_event_list.append({'time':time, 'event':'sirq_raise'})
+	irq_record.update({'event_list':irq_event_list})
+	irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_entry(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	net_rx_dic[cpu] = {'sirq_ent_t':time, 'event_list':[]}
+
+def handle_irq_softirq_exit(event_info):
+	(name, context, cpu, time, pid, comm, vec) = event_info
+	irq_list = []
+	event_list = 0
+	if cpu in irq_dic.keys():
+		irq_list = irq_dic[cpu]
+		del irq_dic[cpu]
+	if cpu in net_rx_dic.keys():
+		sirq_ent_t = net_rx_dic[cpu]['sirq_ent_t']
+		event_list = net_rx_dic[cpu]['event_list']
+		del net_rx_dic[cpu]
+	if irq_list == [] or event_list == 0:
+		return
+	rec_data = {'sirq_ent_t':sirq_ent_t, 'sirq_ext_t':time,
+		    'irq_list':irq_list, 'event_list':event_list}
+	# merge information realted to a NET_RX softirq
+	receive_hunk_list.append(rec_data)
+
+def handle_napi_poll(event_info):
+	(name, context, cpu, time, pid, comm, napi, dev_name) = event_info
+	if cpu in net_rx_dic.keys():
+		event_list = net_rx_dic[cpu]['event_list']
+		rec_data = {'event_name':'napi_poll',
+				'dev':dev_name, 'event_t':time}
+		event_list.append(rec_data)
+
+def handle_netif_rx(event_info):
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	if cpu not in irq_dic.keys() \
+	or len(irq_dic[cpu]) == 0:
+		return
+	irq_record = irq_dic[cpu].pop()
+	if 'event_list' in irq_record.keys():
+		irq_event_list = irq_record['event_list']
+	else:
+		irq_event_list = []
+	irq_event_list.append({'time':time, 'event':'netif_rx',
+		'skbaddr':skbaddr, 'skblen':skblen, 'dev_name':dev_name})
+	irq_record.update({'event_list':irq_event_list})
+	irq_dic[cpu].append(irq_record)
+
+def handle_netif_receive_skb(event_info):
+	global of_count_rx_skb_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	if cpu in net_rx_dic.keys():
+		rec_data = {'event_name':'netif_receive_skb',
+			    'event_t':time, 'skbaddr':skbaddr, 'len':skblen}
+		event_list = net_rx_dic[cpu]['event_list']
+		event_list.append(rec_data)
+		rx_skb_list.insert(0, rec_data)
+		if len(rx_skb_list) > buffer_budget:
+			rx_skb_list.pop()
+			of_count_rx_skb_list += 1
+
+def handle_net_dev_queue(event_info):
+	global of_count_tx_queue_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, dev_name) = event_info
+	skb = {'dev':dev_name, 'skbaddr':skbaddr, 'len':skblen, 'queue_t':time}
+	tx_queue_list.insert(0, skb)
+	if len(tx_queue_list) > buffer_budget:
+		tx_queue_list.pop()
+		of_count_tx_queue_list += 1
+
+def handle_net_dev_xmit(event_info):
+	global of_count_tx_xmit_list
+
+	(name, context, cpu, time, pid, comm,
+		skbaddr, skblen, rc, dev_name) = event_info
+	if rc == 0: # NETDEV_TX_OK
+		for i in range(len(tx_queue_list)):
+			skb = tx_queue_list[i]
+			if skb['skbaddr'] == skbaddr:
+				skb['xmit_t'] = time
+				tx_xmit_list.insert(0, skb)
+				del tx_queue_list[i]
+				if len(tx_xmit_list) > buffer_budget:
+					tx_xmit_list.pop()
+					of_count_tx_xmit_list += 1
+				return
+
+def handle_kfree_skb(event_info):
+	(name, context, cpu, time, pid, comm,
+		skbaddr, protocol, location) = event_info
+	for i in range(len(tx_queue_list)):
+		skb = tx_queue_list[i]
+		if skb['skbaddr'] == skbaddr:
+			del tx_queue_list[i]
+			return
+	for i in range(len(tx_xmit_list)):
+		skb = tx_xmit_list[i]
+		if skb['skbaddr'] == skbaddr:
+			skb['free_t'] = time
+			tx_free_list.append(skb)
+			del tx_xmit_list[i]
+			return
+	for i in range(len(rx_skb_list)):
+		rec_data = rx_skb_list[i]
+		if rec_data['skbaddr'] == skbaddr:
+			rec_data.update({'handle':"kfree_skb",
+					'comm':comm, 'pid':pid, 'comm_t':time})
+			del rx_skb_list[i]
+			return
+
+def handle_consume_skb(event_info):
+	(name, context, cpu, time, pid, comm, skbaddr) = event_info
+	for i in range(len(tx_xmit_list)):
+		skb = tx_xmit_list[i]
+		if skb['skbaddr'] == skbaddr:
+			skb['free_t'] = time
+			tx_free_list.append(skb)
+			del tx_xmit_list[i]
+			return
+
+def handle_skb_copy_datagram_iovec(event_info):
+	(name, context, cpu, time, pid, comm, skbaddr, skblen) = event_info
+	for i in range(len(rx_skb_list)):
+		rec_data = rx_skb_list[i]
+		if skbaddr == rec_data['skbaddr']:
+			rec_data.update({'handle':"skb_copy_datagram_iovec",
+					'comm':comm, 'pid':pid, 'comm_t':time})
+			del rx_skb_list[i]
+			return
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 27e9ebe..a772979 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -82,6 +82,8 @@
 extern char *perf_pathdup(const char *fmt, ...)
 	__attribute__((format (printf, 1, 2)));
 
+#ifdef NO_STRLCPY
 extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index f231f43..e12d539 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -28,6 +28,9 @@
 #define chain_for_each_child(child, parent)	\
 	list_for_each_entry(child, &parent->children, brothers)
 
+#define chain_for_each_child_safe(child, next, parent)	\
+	list_for_each_entry_safe(child, next, &parent->children, brothers)
+
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 		    enum chain_mode mode)
@@ -86,10 +89,10 @@
  * sort them by hit
  */
 static void
-sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
+sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
 		u64 min_hit, struct callchain_param *param __used)
 {
-	__sort_chain_flat(rb_root, node, min_hit);
+	__sort_chain_flat(rb_root, &root->node, min_hit);
 }
 
 static void __sort_chain_graph_abs(struct callchain_node *node,
@@ -108,11 +111,11 @@
 }
 
 static void
-sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_node *chain_root,
+sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root,
 		     u64 min_hit, struct callchain_param *param __used)
 {
-	__sort_chain_graph_abs(chain_root, min_hit);
-	rb_root->rb_node = chain_root->rb_root.rb_node;
+	__sort_chain_graph_abs(&chain_root->node, min_hit);
+	rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
 static void __sort_chain_graph_rel(struct callchain_node *node,
@@ -133,11 +136,11 @@
 }
 
 static void
-sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root,
+sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root,
 		     u64 min_hit __used, struct callchain_param *param)
 {
-	__sort_chain_graph_rel(chain_root, param->min_percent / 100.0);
-	rb_root->rb_node = chain_root->rb_root.rb_node;
+	__sort_chain_graph_rel(&chain_root->node, param->min_percent / 100.0);
+	rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
 int register_callchain_param(struct callchain_param *param)
@@ -284,19 +287,18 @@
 }
 
 static int
-__append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start, u64 period);
+append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	     unsigned int start, u64 period);
 
 static void
-__append_chain_children(struct callchain_node *root,
-			struct resolved_chain *chain,
-			unsigned int start, u64 period)
+append_chain_children(struct callchain_node *root, struct resolved_chain *chain,
+		      unsigned int start, u64 period)
 {
 	struct callchain_node *rnode;
 
 	/* lookup in childrens */
 	chain_for_each_child(rnode, root) {
-		unsigned int ret = __append_chain(rnode, chain, start, period);
+		unsigned int ret = append_chain(rnode, chain, start, period);
 
 		if (!ret)
 			goto inc_children_hit;
@@ -309,8 +311,8 @@
 }
 
 static int
-__append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start, u64 period)
+append_chain(struct callchain_node *root, struct resolved_chain *chain,
+	     unsigned int start, u64 period)
 {
 	struct callchain_list *cnode;
 	unsigned int i = start;
@@ -357,7 +359,7 @@
 	}
 
 	/* We match the node and still have a part remaining */
-	__append_chain_children(root, chain, i, period);
+	append_chain_children(root, chain, i, period);
 
 	return 0;
 }
@@ -380,8 +382,8 @@
 }
 
 
-int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms, u64 period)
+int callchain_append(struct callchain_root *root, struct ip_callchain *chain,
+		     struct map_symbol *syms, u64 period)
 {
 	struct resolved_chain *filtered;
 
@@ -398,9 +400,65 @@
 	if (!filtered->nr)
 		goto end;
 
-	__append_chain_children(root, filtered, 0, period);
+	append_chain_children(&root->node, filtered, 0, period);
+
+	if (filtered->nr > root->max_depth)
+		root->max_depth = filtered->nr;
 end:
 	free(filtered);
 
 	return 0;
 }
+
+static int
+merge_chain_branch(struct callchain_node *dst, struct callchain_node *src,
+		   struct resolved_chain *chain)
+{
+	struct callchain_node *child, *next_child;
+	struct callchain_list *list, *next_list;
+	int old_pos = chain->nr;
+	int err = 0;
+
+	list_for_each_entry_safe(list, next_list, &src->val, list) {
+		chain->ips[chain->nr].ip = list->ip;
+		chain->ips[chain->nr].ms = list->ms;
+		chain->nr++;
+		list_del(&list->list);
+		free(list);
+	}
+
+	if (src->hit)
+		append_chain_children(dst, chain, 0, src->hit);
+
+	chain_for_each_child_safe(child, next_child, src) {
+		err = merge_chain_branch(dst, child, chain);
+		if (err)
+			break;
+
+		list_del(&child->brothers);
+		free(child);
+	}
+
+	chain->nr = old_pos;
+
+	return err;
+}
+
+int callchain_merge(struct callchain_root *dst, struct callchain_root *src)
+{
+	struct resolved_chain *chain;
+	int err;
+
+	chain = malloc(sizeof(*chain) +
+		       src->max_depth * sizeof(struct resolved_ip));
+	if (!chain)
+		return -ENOMEM;
+
+	chain->nr = 0;
+
+	err = merge_chain_branch(&dst->node, &src->node, chain);
+
+	free(chain);
+
+	return err;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 6de4313..c15fb8c 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -26,9 +26,14 @@
 	u64			children_hit;
 };
 
+struct callchain_root {
+	u64			max_depth;
+	struct callchain_node	node;
+};
+
 struct callchain_param;
 
-typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_node *,
+typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
 				 u64, struct callchain_param *);
 
 struct callchain_param {
@@ -44,15 +49,16 @@
 	struct list_head	list;
 };
 
-static inline void callchain_init(struct callchain_node *node)
+static inline void callchain_init(struct callchain_root *root)
 {
-	INIT_LIST_HEAD(&node->brothers);
-	INIT_LIST_HEAD(&node->children);
-	INIT_LIST_HEAD(&node->val);
+	INIT_LIST_HEAD(&root->node.brothers);
+	INIT_LIST_HEAD(&root->node.children);
+	INIT_LIST_HEAD(&root->node.val);
 
-	node->children_hit = 0;
-	node->parent = NULL;
-	node->hit = 0;
+	root->node.parent = NULL;
+	root->node.hit = 0;
+	root->node.children_hit = 0;
+	root->max_depth = 0;
 }
 
 static inline u64 cumul_hits(struct callchain_node *node)
@@ -61,8 +67,9 @@
 }
 
 int register_callchain_param(struct callchain_param *param);
-int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms, u64 period);
+int callchain_append(struct callchain_root *root, struct ip_callchain *chain,
+		     struct map_symbol *syms, u64 period);
+int callchain_merge(struct callchain_root *dst, struct callchain_root *src);
 
 bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event);
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index be22ae6..2022e87 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -87,7 +87,7 @@
 
 static struct hist_entry *hist_entry__new(struct hist_entry *template)
 {
-	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_node) : 0;
+	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
 	struct hist_entry *self = malloc(sizeof(*self) + callchain_size);
 
 	if (self != NULL) {
@@ -226,6 +226,8 @@
 
 		if (!cmp) {
 			iter->period += he->period;
+			if (symbol_conf.use_callchain)
+				callchain_merge(iter->callchain, he->callchain);
 			hist_entry__free(he);
 			return false;
 		}
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 58a470d..bd74977 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,6 +22,7 @@
 	return ".";
 }
 
+#ifdef NO_STRLCPY
 size_t strlcpy(char *dest, const char *src, size_t size)
 {
 	size_t ret = strlen(src);
@@ -33,7 +34,7 @@
 	}
 	return ret;
 }
-
+#endif
 
 static char *get_pathname(void)
 {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 46e531d..0b91053 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -70,7 +70,7 @@
 		struct hist_entry *pair;
 		struct rb_root	  sorted_chain;
 	};
-	struct callchain_node	callchain[0];
+	struct callchain_root	callchain[0];
 };
 
 enum sort_type {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b2f5ae9..b39f499 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -388,6 +388,20 @@
 	return fprintf(fp, "%s", sbuild_id);
 }
 
+size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp)
+{
+	size_t ret = 0;
+	struct rb_node *nd;
+	struct symbol_name_rb_node *pos;
+
+	for (nd = rb_first(&self->symbol_names[type]); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
+		fprintf(fp, "%s\n", pos->sym.name);
+	}
+
+	return ret;
+}
+
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
 {
 	struct rb_node *nd;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ea95c27..038f220 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -182,6 +182,7 @@
 size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits);
 
 size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp);
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
 
 enum dso_origin {
diff --git a/tools/perf/util/ui/browser.c b/tools/perf/util/ui/browser.c
index 66f2d58..6d0df80 100644
--- a/tools/perf/util/ui/browser.c
+++ b/tools/perf/util/ui/browser.c
@@ -1,16 +1,6 @@
-#define _GNU_SOURCE
-#include <stdio.h>
-#undef _GNU_SOURCE
-/*
- * slang versions <= 2.0.6 have a "#if HAVE_LONG_LONG" that breaks
- * the build if it isn't defined. Use the equivalent one that glibc
- * has on features.h.
- */
-#include <features.h>
-#ifndef HAVE_LONG_LONG
-#define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG
-#endif
 #include <slang.h>
+#include "libslang.h"
+#include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdlib.h>
@@ -19,17 +9,9 @@
 #include "helpline.h"
 #include "../color.h"
 #include "../util.h"
+#include <stdio.h>
 
-#if SLANG_VERSION < 20104
-#define sltt_set_color(obj, name, fg, bg) \
-	SLtt_set_color(obj,(char *)name, (char *)fg, (char *)bg)
-#else
-#define sltt_set_color SLtt_set_color
-#endif
-
-newtComponent newt_form__new(void);
-
-int ui_browser__percent_color(double percent, bool current)
+static int ui_browser__percent_color(double percent, bool current)
 {
 	if (current)
 		return HE_COLORSET_SELECTED;
@@ -40,6 +22,23 @@
 	return HE_COLORSET_NORMAL;
 }
 
+void ui_browser__set_color(struct ui_browser *self __used, int color)
+{
+	SLsmg_set_color(color);
+}
+
+void ui_browser__set_percent_color(struct ui_browser *self,
+				   double percent, bool current)
+{
+	 int color = ui_browser__percent_color(percent, current);
+	 ui_browser__set_color(self, color);
+}
+
+void ui_browser__gotorc(struct ui_browser *self, int y, int x)
+{
+	SLsmg_gotorc(self->y + y, self->x + x);
+}
+
 void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whence)
 {
 	struct list_head *head = self->entries;
@@ -111,7 +110,7 @@
 	nd = self->top;
 
 	while (nd != NULL) {
-		SLsmg_gotorc(self->y + row, self->x);
+		ui_browser__gotorc(self, row, 0);
 		self->write(self, nd, row);
 		if (++row == self->height)
 			break;
@@ -131,13 +130,10 @@
 	int cols, rows;
 	newtGetScreenSize(&cols, &rows);
 
-	if (self->width > cols - 4)
-		self->width = cols - 4;
-	self->height = rows - 5;
-	if (self->height > self->nr_entries)
-		self->height = self->nr_entries;
-	self->y  = (rows - self->height) / 2;
-	self->x = (cols - self->width) / 2;
+	self->width = cols - 1;
+	self->height = rows - 2;
+	self->y = 1;
+	self->x = 0;
 }
 
 void ui_browser__reset_index(struct ui_browser *self)
@@ -146,34 +142,48 @@
 	self->seek(self, 0, SEEK_SET);
 }
 
+void ui_browser__add_exit_key(struct ui_browser *self, int key)
+{
+	newtFormAddHotKey(self->form, key);
+}
+
+void ui_browser__add_exit_keys(struct ui_browser *self, int keys[])
+{
+	int i = 0;
+
+	while (keys[i] && i < 64) {
+		ui_browser__add_exit_key(self, keys[i]);
+		++i;
+	}
+}
+
 int ui_browser__show(struct ui_browser *self, const char *title,
 		     const char *helpline, ...)
 {
 	va_list ap;
+	int keys[] = { NEWT_KEY_UP, NEWT_KEY_DOWN, NEWT_KEY_PGUP,
+		       NEWT_KEY_PGDN, NEWT_KEY_HOME, NEWT_KEY_END, ' ',
+		       NEWT_KEY_LEFT, NEWT_KEY_ESCAPE, 'q', CTRL('c'), 0 };
 
-	if (self->form != NULL) {
+	if (self->form != NULL)
 		newtFormDestroy(self->form);
-		newtPopWindow();
-	}
+
 	ui_browser__refresh_dimensions(self);
-	newtCenteredWindow(self->width, self->height, title);
-	self->form = newt_form__new();
+	self->form = newtForm(NULL, NULL, 0);
 	if (self->form == NULL)
 		return -1;
 
-	self->sb = newtVerticalScrollbar(self->width, 0, self->height,
+	self->sb = newtVerticalScrollbar(self->width, 1, self->height,
 					 HE_COLORSET_NORMAL,
 					 HE_COLORSET_SELECTED);
 	if (self->sb == NULL)
 		return -1;
 
-	newtFormAddHotKey(self->form, NEWT_KEY_UP);
-	newtFormAddHotKey(self->form, NEWT_KEY_DOWN);
-	newtFormAddHotKey(self->form, NEWT_KEY_PGUP);
-	newtFormAddHotKey(self->form, NEWT_KEY_PGDN);
-	newtFormAddHotKey(self->form, NEWT_KEY_HOME);
-	newtFormAddHotKey(self->form, NEWT_KEY_END);
-	newtFormAddHotKey(self->form, ' ');
+	SLsmg_gotorc(0, 0);
+	ui_browser__set_color(self, NEWT_COLORSET_ROOT);
+	slsmg_write_nstring(title, self->width);
+
+	ui_browser__add_exit_keys(self, keys);
 	newtFormAddComponent(self->form, self->sb);
 
 	va_start(ap, helpline);
@@ -185,7 +195,6 @@
 void ui_browser__hide(struct ui_browser *self)
 {
 	newtFormDestroy(self->form);
-	newtPopWindow();
 	self->form = NULL;
 	ui_helpline__pop();
 }
@@ -196,28 +205,28 @@
 
 	newtScrollbarSet(self->sb, self->index, self->nr_entries - 1);
 	row = self->refresh(self);
-	SLsmg_set_color(HE_COLORSET_NORMAL);
+	ui_browser__set_color(self, HE_COLORSET_NORMAL);
 	SLsmg_fill_region(self->y + row, self->x,
 			  self->height - row, self->width, ' ');
 
 	return 0;
 }
 
-int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es)
+int ui_browser__run(struct ui_browser *self)
 {
+	struct newtExitStruct es;
+
 	if (ui_browser__refresh(self) < 0)
 		return -1;
 
 	while (1) {
 		off_t offset;
 
-		newtFormRun(self->form, es);
+		newtFormRun(self->form, &es);
 
-		if (es->reason != NEWT_EXIT_HOTKEY)
+		if (es.reason != NEWT_EXIT_HOTKEY)
 			break;
-		if (is_exit_key(es->u.key))
-			return es->u.key;
-		switch (es->u.key) {
+		switch (es.u.key) {
 		case NEWT_KEY_DOWN:
 			if (self->index == self->nr_entries - 1)
 				break;
@@ -274,12 +283,12 @@
 			self->seek(self, -offset, SEEK_END);
 			break;
 		default:
-			return es->u.key;
+			return es.u.key;
 		}
 		if (ui_browser__refresh(self) < 0)
 			return -1;
 	}
-	return 0;
+	return -1;
 }
 
 unsigned int ui_browser__list_head_refresh(struct ui_browser *self)
@@ -294,7 +303,7 @@
 	pos = self->top;
 
 	list_for_each_from(pos, head) {
-		SLsmg_gotorc(self->y + row, self->x);
+		ui_browser__gotorc(self, row, 0);
 		self->write(self, pos, row);
 		if (++row == self->height)
 			break;
diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h
index 0b9f829..0dc7e4d 100644
--- a/tools/perf/util/ui/browser.h
+++ b/tools/perf/util/ui/browser.h
@@ -25,16 +25,21 @@
 };
 
 
-int ui_browser__percent_color(double percent, bool current);
+void ui_browser__set_color(struct ui_browser *self, int color);
+void ui_browser__set_percent_color(struct ui_browser *self,
+				   double percent, bool current);
 bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row);
 void ui_browser__refresh_dimensions(struct ui_browser *self);
 void ui_browser__reset_index(struct ui_browser *self);
 
+void ui_browser__gotorc(struct ui_browser *self, int y, int x);
+void ui_browser__add_exit_key(struct ui_browser *self, int key);
+void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]);
 int ui_browser__show(struct ui_browser *self, const char *title,
 		     const char *helpline, ...);
 void ui_browser__hide(struct ui_browser *self);
 int ui_browser__refresh(struct ui_browser *self);
-int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es);
+int ui_browser__run(struct ui_browser *self);
 
 void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence);
 unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self);
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index a90273e..82b78f9 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -40,14 +40,12 @@
 
 	if (ol->offset != -1) {
 		struct objdump_line_rb_node *olrb = objdump_line__rb(ol);
-		int color = ui_browser__percent_color(olrb->percent, current_entry);
-		SLsmg_set_color(color);
+		ui_browser__set_percent_color(self, olrb->percent, current_entry);
 		slsmg_printf(" %7.2f ", olrb->percent);
 		if (!current_entry)
-			SLsmg_set_color(HE_COLORSET_CODE);
+			ui_browser__set_color(self, HE_COLORSET_CODE);
 	} else {
-		int color = ui_browser__percent_color(0, current_entry);
-		SLsmg_set_color(color);
+		ui_browser__set_percent_color(self, 0, current_entry);
 		slsmg_write_nstring(" ", 9);
 	}
 
@@ -135,32 +133,31 @@
 	self->curr_hot = nd;
 }
 
-static int annotate_browser__run(struct annotate_browser *self,
-				 struct newtExitStruct *es)
+static int annotate_browser__run(struct annotate_browser *self)
 {
 	struct rb_node *nd;
 	struct hist_entry *he = self->b.priv;
+	int key;
 
 	if (ui_browser__show(&self->b, he->ms.sym->name,
-			     "<- or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0)
+			     "<-, -> or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0)
 		return -1;
-
-	newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-	newtFormAddHotKey(self->b.form, NEWT_KEY_RIGHT);
+	/*
+	 * To allow builtin-annotate to cycle thru multiple symbols by
+	 * examining the exit key for this function.
+	 */
+	ui_browser__add_exit_key(&self->b, NEWT_KEY_RIGHT);
 
 	nd = self->curr_hot;
 	if (nd) {
-		newtFormAddHotKey(self->b.form, NEWT_KEY_TAB);
-		newtFormAddHotKey(self->b.form, NEWT_KEY_UNTAB);
+		int tabs[] = { NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0 };
+		ui_browser__add_exit_keys(&self->b, tabs);
 	}
 
 	while (1) {
-		ui_browser__run(&self->b, es);
+		key = ui_browser__run(&self->b);
 
-		if (es->reason != NEWT_EXIT_HOTKEY)
-			break;
-
-		switch (es->u.key) {
+		switch (key) {
 		case NEWT_KEY_TAB:
 			nd = rb_prev(nd);
 			if (nd == NULL)
@@ -179,12 +176,11 @@
 	}
 out:
 	ui_browser__hide(&self->b);
-	return es->u.key;
+	return key;
 }
 
 int hist_entry__tui_annotate(struct hist_entry *self)
 {
-	struct newtExitStruct es;
 	struct objdump_line *pos, *n;
 	struct objdump_line_rb_node *rbpos;
 	LIST_HEAD(head);
@@ -232,7 +228,7 @@
 		annotate_browser__set_top(&browser, browser.curr_hot);
 
 	browser.b.width += 18; /* Percentage */
-	ret = annotate_browser__run(&browser, &es);
+	ret = annotate_browser__run(&browser);
 	list_for_each_entry_safe(pos, n, &head, node) {
 		list_del(&pos->node);
 		objdump_line__free(pos);
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 6866aa4..ebda8c3 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -58,6 +58,11 @@
 	return map_symbol__folded(&self->ms);
 }
 
+static void map_symbol__set_folding(struct map_symbol *self, bool unfold)
+{
+	self->unfolded = unfold ? self->has_children : false;
+}
+
 static int callchain_node__count_rows_rb_tree(struct callchain_node *self)
 {
 	int n = 0;
@@ -129,16 +134,16 @@
 	for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
 		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
 		struct callchain_list *chain;
-		int first = true;
+		bool first = true;
 
 		list_for_each_entry(chain, &child->val, list) {
 			if (first) {
 				first = false;
 				chain->ms.has_children = chain->list.next != &child->val ||
-							 rb_first(&child->rb_root) != NULL;
+							 !RB_EMPTY_ROOT(&child->rb_root);
 			} else
 				chain->ms.has_children = chain->list.next == &child->val &&
-							 rb_first(&child->rb_root) != NULL;
+							 !RB_EMPTY_ROOT(&child->rb_root);
 		}
 
 		callchain_node__init_have_children_rb_tree(child);
@@ -150,7 +155,7 @@
 	struct callchain_list *chain;
 
 	list_for_each_entry(chain, &self->val, list)
-		chain->ms.has_children = rb_first(&self->rb_root) != NULL;
+		chain->ms.has_children = !RB_EMPTY_ROOT(&self->rb_root);
 
 	callchain_node__init_have_children_rb_tree(self);
 }
@@ -168,6 +173,7 @@
 static void hist_entry__init_have_children(struct hist_entry *self)
 {
 	if (!self->init_have_children) {
+		self->ms.has_children = !RB_EMPTY_ROOT(&self->sorted_chain);
 		callchain__init_have_children(&self->sorted_chain);
 		self->init_have_children = true;
 	}
@@ -195,43 +201,114 @@
 	return false;
 }
 
-static int hist_browser__run(struct hist_browser *self, const char *title,
-			     struct newtExitStruct *es)
+static int callchain_node__set_folding_rb_tree(struct callchain_node *self, bool unfold)
 {
-	char str[256], unit;
-	unsigned long nr_events = self->hists->stats.nr_events[PERF_RECORD_SAMPLE];
+	int n = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
+		struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
+		struct callchain_list *chain;
+		bool has_children = false;
+
+		list_for_each_entry(chain, &child->val, list) {
+			++n;
+			map_symbol__set_folding(&chain->ms, unfold);
+			has_children = chain->ms.has_children;
+		}
+
+		if (has_children)
+			n += callchain_node__set_folding_rb_tree(child, unfold);
+	}
+
+	return n;
+}
+
+static int callchain_node__set_folding(struct callchain_node *node, bool unfold)
+{
+	struct callchain_list *chain;
+	bool has_children = false;
+	int n = 0;
+
+	list_for_each_entry(chain, &node->val, list) {
+		++n;
+		map_symbol__set_folding(&chain->ms, unfold);
+		has_children = chain->ms.has_children;
+	}
+
+	if (has_children)
+		n += callchain_node__set_folding_rb_tree(node, unfold);
+
+	return n;
+}
+
+static int callchain__set_folding(struct rb_root *chain, bool unfold)
+{
+	struct rb_node *nd;
+	int n = 0;
+
+	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+		n += callchain_node__set_folding(node, unfold);
+	}
+
+	return n;
+}
+
+static void hist_entry__set_folding(struct hist_entry *self, bool unfold)
+{
+	hist_entry__init_have_children(self);
+	map_symbol__set_folding(&self->ms, unfold);
+
+	if (self->ms.has_children) {
+		int n = callchain__set_folding(&self->sorted_chain, unfold);
+		self->nr_rows = unfold ? n : 0;
+	} else
+		self->nr_rows = 0;
+}
+
+static void hists__set_folding(struct hists *self, bool unfold)
+{
+	struct rb_node *nd;
+
+	self->nr_entries = 0;
+
+	for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+		hist_entry__set_folding(he, unfold);
+		self->nr_entries += 1 + he->nr_rows;
+	}
+}
+
+static void hist_browser__set_folding(struct hist_browser *self, bool unfold)
+{
+	hists__set_folding(self->hists, unfold);
+	self->b.nr_entries = self->hists->nr_entries;
+	/* Go to the start, we may be way after valid entries after a collapse */
+	ui_browser__reset_index(&self->b);
+}
+
+static int hist_browser__run(struct hist_browser *self, const char *title)
+{
+	int key;
+	int exit_keys[] = { 'a', '?', 'h', 'C', 'd', 'D', 'E', 't',
+			    NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT, 0, };
 
 	self->b.entries = &self->hists->entries;
 	self->b.nr_entries = self->hists->nr_entries;
 
 	hist_browser__refresh_dimensions(self);
 
-	nr_events = convert_unit(nr_events, &unit);
-	snprintf(str, sizeof(str), "Events: %lu%c                            ",
-		 nr_events, unit);
-	newtDrawRootText(0, 0, str);
-
 	if (ui_browser__show(&self->b, title,
 			     "Press '?' for help on key bindings") < 0)
 		return -1;
 
-	newtFormAddHotKey(self->b.form, 'a');
-	newtFormAddHotKey(self->b.form, '?');
-	newtFormAddHotKey(self->b.form, 'h');
-	newtFormAddHotKey(self->b.form, 'd');
-	newtFormAddHotKey(self->b.form, 'D');
-	newtFormAddHotKey(self->b.form, 't');
-
-	newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-	newtFormAddHotKey(self->b.form, NEWT_KEY_RIGHT);
-	newtFormAddHotKey(self->b.form, NEWT_KEY_ENTER);
+	ui_browser__add_exit_keys(&self->b, exit_keys);
 
 	while (1) {
-		ui_browser__run(&self->b, es);
+		key = ui_browser__run(&self->b);
 
-		if (es->reason != NEWT_EXIT_HOTKEY)
-			break;
-		switch (es->u.key) {
+		switch (key) {
 		case 'D': { /* Debug */
 			static int seq;
 			struct hist_entry *h = rb_entry(self->b.top,
@@ -245,18 +322,26 @@
 					   self->b.top_idx,
 					   h->row_offset, h->nr_rows);
 		}
-			continue;
+			break;
+		case 'C':
+			/* Collapse the whole world. */
+			hist_browser__set_folding(self, false);
+			break;
+		case 'E':
+			/* Expand the whole world. */
+			hist_browser__set_folding(self, true);
+			break;
 		case NEWT_KEY_ENTER:
 			if (hist_browser__toggle_fold(self))
 				break;
 			/* fall thru */
 		default:
-			return 0;
+			goto out;
 		}
 	}
-
+out:
 	ui_browser__hide(&self->b);
-	return 0;
+	return key;
 }
 
 static char *callchain_list__sym_name(struct callchain_list *self,
@@ -306,15 +391,10 @@
 			int color;
 			bool was_first = first;
 
-			if (first) {
+			if (first)
 				first = false;
-				chain->ms.has_children = chain->list.next != &child->val ||
-							 rb_first(&child->rb_root) != NULL;
-			} else {
+			else
 				extra_offset = LEVEL_OFFSET_STEP;
-				chain->ms.has_children = chain->list.next == &child->val &&
-							 rb_first(&child->rb_root) != NULL;
-			}
 
 			folded_sign = callchain_list__folded(chain);
 			if (*row_offset != 0) {
@@ -341,8 +421,8 @@
 				*is_current_entry = true;
 			}
 
-			SLsmg_set_color(color);
-			SLsmg_gotorc(self->b.y + row, self->b.x);
+			ui_browser__set_color(&self->b, color);
+			ui_browser__gotorc(&self->b, row, 0);
 			slsmg_write_nstring(" ", offset + extra_offset);
 			slsmg_printf("%c ", folded_sign);
 			slsmg_write_nstring(str, width);
@@ -384,12 +464,7 @@
 	list_for_each_entry(chain, &node->val, list) {
 		char ipstr[BITS_PER_LONG / 4 + 1], *s;
 		int color;
-		/*
-		 * FIXME: This should be moved to somewhere else,
-		 * probably when the callchain is created, so as not to
-		 * traverse it all over again
-		 */
-		chain->ms.has_children = rb_first(&node->rb_root) != NULL;
+
 		folded_sign = callchain_list__folded(chain);
 
 		if (*row_offset != 0) {
@@ -405,8 +480,8 @@
 		}
 
 		s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
-		SLsmg_gotorc(self->b.y + row, self->b.x);
-		SLsmg_set_color(color);
+		ui_browser__gotorc(&self->b, row, 0);
+		ui_browser__set_color(&self->b, color);
 		slsmg_write_nstring(" ", offset);
 		slsmg_printf("%c ", folded_sign);
 		slsmg_write_nstring(s, width - 2);
@@ -465,7 +540,7 @@
 	}
 
 	if (symbol_conf.use_callchain) {
-		entry->ms.has_children = !RB_EMPTY_ROOT(&entry->sorted_chain);
+		hist_entry__init_have_children(entry);
 		folded_sign = hist_entry__folded(entry);
 	}
 
@@ -484,8 +559,8 @@
 				color = HE_COLORSET_NORMAL;
 		}
 
-		SLsmg_set_color(color);
-		SLsmg_gotorc(self->b.y + row, self->b.x);
+		ui_browser__set_color(&self->b, color);
+		ui_browser__gotorc(&self->b, row, 0);
 		if (symbol_conf.use_callchain) {
 			slsmg_printf("%c ", folded_sign);
 			width -= 2;
@@ -687,8 +762,6 @@
 
 static void hist_browser__delete(struct hist_browser *self)
 {
-	newtFormDestroy(self->b.form);
-	newtPopWindow();
 	free(self);
 }
 
@@ -702,21 +775,26 @@
 	return self->he_selection->thread;
 }
 
-static int hist_browser__title(char *bf, size_t size, const char *ev_name,
-			       const struct dso *dso, const struct thread *thread)
+static int hists__browser_title(struct hists *self, char *bf, size_t size,
+				const char *ev_name, const struct dso *dso,
+				const struct thread *thread)
 {
-	int printed = 0;
+	char unit;
+	int printed;
+	unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE];
+
+	nr_events = convert_unit(nr_events, &unit);
+	printed = snprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name);
 
 	if (thread)
 		printed += snprintf(bf + printed, size - printed,
-				    "Thread: %s(%d)",
-				    (thread->comm_set ?  thread->comm : ""),
+				    ", Thread: %s(%d)",
+				    (thread->comm_set ? thread->comm : ""),
 				    thread->pid);
 	if (dso)
 		printed += snprintf(bf + printed, size - printed,
-				    "%sDSO: %s", thread ? " " : "",
-				    dso->short_name);
-	return printed ?: snprintf(bf, size, "Event: %s", ev_name);
+				    ", DSO: %s", dso->short_name);
+	return printed;
 }
 
 int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
@@ -725,7 +803,6 @@
 	struct pstack *fstack;
 	const struct thread *thread_filter = NULL;
 	const struct dso *dso_filter = NULL;
-	struct newtExitStruct es;
 	char msg[160];
 	int key = -1;
 
@@ -738,9 +815,8 @@
 
 	ui_helpline__push(helpline);
 
-	hist_browser__title(msg, sizeof(msg), ev_name,
-			    dso_filter, thread_filter);
-
+	hists__browser_title(self, msg, sizeof(msg), ev_name,
+			     dso_filter, thread_filter);
 	while (1) {
 		const struct thread *thread;
 		const struct dso *dso;
@@ -749,70 +825,63 @@
 		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
 		    browse_map = -2;
 
-		if (hist_browser__run(browser, msg, &es))
-			break;
+		key = hist_browser__run(browser, msg);
 
 		thread = hist_browser__selected_thread(browser);
 		dso = browser->selection->map ? browser->selection->map->dso : NULL;
 
-		if (es.reason == NEWT_EXIT_HOTKEY) {
-			key = es.u.key;
-
-			switch (key) {
-			case NEWT_KEY_F1:
-				goto do_help;
-			case NEWT_KEY_TAB:
-			case NEWT_KEY_UNTAB:
-				/*
-				 * Exit the browser, let hists__browser_tree
-				 * go to the next or previous
-				 */
-				goto out_free_stack;
-			default:;
-			}
-
-			switch (key) {
-			case 'a':
-				if (browser->selection->map == NULL ||
-				    browser->selection->map->dso->annotate_warned)
-					continue;
-				goto do_annotate;
-			case 'd':
-				goto zoom_dso;
-			case 't':
-				goto zoom_thread;
-			case 'h':
-			case '?':
-do_help:
-				ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
-						"<-        Zoom out\n"
-						"a         Annotate current symbol\n"
-						"h/?/F1    Show this window\n"
-						"d         Zoom into current DSO\n"
-						"t         Zoom into current Thread\n"
-						"q/CTRL+C  Exit browser");
+		switch (key) {
+		case NEWT_KEY_TAB:
+		case NEWT_KEY_UNTAB:
+			/*
+			 * Exit the browser, let hists__browser_tree
+			 * go to the next or previous
+			 */
+			goto out_free_stack;
+		case 'a':
+			if (browser->selection->map == NULL &&
+			    browser->selection->map->dso->annotate_warned)
 				continue;
-			default:;
-			}
-			if (is_exit_key(key)) {
-				if (key == NEWT_KEY_ESCAPE &&
-				    !ui__dialog_yesno("Do you really want to exit?"))
-					continue;
-				break;
-			}
+			goto do_annotate;
+		case 'd':
+			goto zoom_dso;
+		case 't':
+			goto zoom_thread;
+		case NEWT_KEY_F1:
+		case 'h':
+		case '?':
+			ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
+					"<-        Zoom out\n"
+					"a         Annotate current symbol\n"
+					"h/?/F1    Show this window\n"
+					"C         Collapse all callchains\n"
+					"E         Expand all callchains\n"
+					"d         Zoom into current DSO\n"
+					"t         Zoom into current Thread\n"
+					"q/CTRL+C  Exit browser");
+			continue;
+		case NEWT_KEY_ENTER:
+		case NEWT_KEY_RIGHT:
+			/* menu */
+			break;
+		case NEWT_KEY_LEFT: {
+			const void *top;
 
-			if (es.u.key == NEWT_KEY_LEFT) {
-				const void *top;
-
-				if (pstack__empty(fstack))
-					continue;
-				top = pstack__pop(fstack);
-				if (top == &dso_filter)
-					goto zoom_out_dso;
-				if (top == &thread_filter)
-					goto zoom_out_thread;
+			if (pstack__empty(fstack))
 				continue;
-			}
+			top = pstack__pop(fstack);
+			if (top == &dso_filter)
+				goto zoom_out_dso;
+			if (top == &thread_filter)
+				goto zoom_out_thread;
+			continue;
+		}
+		case NEWT_KEY_ESCAPE:
+			if (!ui__dialog_yesno("Do you really want to exit?"))
+				continue;
+			/* Fall thru */
+		default:
+			goto out_free_stack;
 		}
 
 		if (browser->selection->sym != NULL &&
@@ -885,8 +954,8 @@
 				pstack__push(fstack, &dso_filter);
 			}
 			hists__filter_by_dso(self, dso_filter);
-			hist_browser__title(msg, sizeof(msg), ev_name,
-					    dso_filter, thread_filter);
+			hists__browser_title(self, msg, sizeof(msg), ev_name,
+					     dso_filter, thread_filter);
 			hist_browser__reset(browser);
 		} else if (choice == zoom_thread) {
 zoom_thread:
@@ -903,8 +972,8 @@
 				pstack__push(fstack, &thread_filter);
 			}
 			hists__filter_by_thread(self, thread_filter);
-			hist_browser__title(msg, sizeof(msg), ev_name,
-					    dso_filter, thread_filter);
+			hists__browser_title(self, msg, sizeof(msg), ev_name,
+					     dso_filter, thread_filter);
 			hist_browser__reset(browser);
 		}
 	}
@@ -925,10 +994,6 @@
 		const char *ev_name = __event_name(hists->type, hists->config);
 
 		key = hists__browse(hists, help, ev_name);
-
-		if (is_exit_key(key))
-			break;
-
 		switch (key) {
 		case NEWT_KEY_TAB:
 			next = rb_next(nd);
@@ -940,7 +1005,7 @@
 				continue;
 			nd = rb_prev(nd);
 		default:
-			break;
+			return key;
 		}
 	}
 
diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c
index 142b825..e35437d 100644
--- a/tools/perf/util/ui/browsers/map.c
+++ b/tools/perf/util/ui/browsers/map.c
@@ -1,6 +1,5 @@
 #include "../libslang.h"
 #include <elf.h>
-#include <newt.h>
 #include <sys/ttydefaults.h>
 #include <ctype.h>
 #include <string.h>
@@ -47,7 +46,6 @@
 struct map_browser {
 	struct ui_browser b;
 	struct map	  *map;
-	u16		  namelen;
 	u8		  addrlen;
 };
 
@@ -56,14 +54,16 @@
 	struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
 	struct map_browser *mb = container_of(self, struct map_browser, b);
 	bool current_entry = ui_browser__is_current_entry(self, row);
-	int color = ui_browser__percent_color(0, current_entry);
+	int width;
 
-	SLsmg_set_color(color);
+	ui_browser__set_percent_color(self, 0, current_entry);
 	slsmg_printf("%*llx %*llx %c ",
 		     mb->addrlen, sym->start, mb->addrlen, sym->end,
 		     sym->binding == STB_GLOBAL ? 'g' :
 		     sym->binding == STB_LOCAL  ? 'l' : 'w');
-	slsmg_write_nstring(sym->name, mb->namelen);
+	width = self->width - ((mb->addrlen * 2) + 4);
+	if (width > 0)
+		slsmg_write_nstring(sym->name, width);
 }
 
 /* FIXME uber-kludgy, see comment on cmd_report... */
@@ -98,31 +98,29 @@
 	return 0;
 }
 
-static int map_browser__run(struct map_browser *self, struct newtExitStruct *es)
+static int map_browser__run(struct map_browser *self)
 {
+	int key;
+
 	if (ui_browser__show(&self->b, self->map->dso->long_name,
 			     "Press <- or ESC to exit, %s / to search",
 			     verbose ? "" : "restart with -v to use") < 0)
 		return -1;
 
-	newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-	newtFormAddHotKey(self->b.form, NEWT_KEY_ENTER);
 	if (verbose)
-		newtFormAddHotKey(self->b.form, '/');
+		ui_browser__add_exit_key(&self->b, '/');
 
 	while (1) {
-		ui_browser__run(&self->b, es);
+		key = ui_browser__run(&self->b);
 
-		if (es->reason != NEWT_EXIT_HOTKEY)
-			break;
-		if (verbose && es->u.key == '/')
+		if (verbose && key == '/')
 			map_browser__search(self);
 		else
 			break;
 	}
 
 	ui_browser__hide(&self->b);
-	return 0;
+	return key;
 }
 
 int map__browse(struct map *self)
@@ -136,7 +134,6 @@
 		},
 		.map = self,
 	};
-	struct newtExitStruct es;
 	struct rb_node *nd;
 	char tmp[BITS_PER_LONG / 4];
 	u64 maxaddr = 0;
@@ -144,8 +141,6 @@
 	for (nd = rb_first(mb.b.entries); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 
-		if (mb.namelen < pos->namelen)
-			mb.namelen = pos->namelen;
 		if (maxaddr < pos->end)
 			maxaddr = pos->end;
 		if (verbose) {
@@ -156,6 +151,5 @@
 	}
 
 	mb.addrlen = snprintf(tmp, sizeof(tmp), "%llx", maxaddr);
-	mb.b.width += mb.addrlen * 2 + 4 + mb.namelen;
-	return map_browser__run(&mb, &es);
+	return map_browser__run(&mb);
 }
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 04600e2..9706d9d 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -11,8 +11,6 @@
 #include "helpline.h"
 #include "util.h"
 
-newtComponent newt_form__new(void);
-
 static void newt_form__set_exit_keys(newtComponent self)
 {
 	newtFormAddHotKey(self, NEWT_KEY_LEFT);
@@ -22,7 +20,7 @@
 	newtFormAddHotKey(self, CTRL('c'));
 }
 
-newtComponent newt_form__new(void)
+static newtComponent newt_form__new(void)
 {
 	newtComponent self = newtForm(NULL, NULL, 0);
 	if (self)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index f380fed..7562707 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -266,19 +266,6 @@
 bool strlazymatch(const char *str, const char *pat);
 unsigned long convert_unit(unsigned long value, char *unit);
 
-#ifndef ESC
-#define ESC 27
-#endif
-
-static inline bool is_exit_key(int key)
-{
-	char up;
-	if (key == CTRL('c') || key == ESC)
-		return true;
-	up = toupper(key);
-	return up == 'Q';
-}
-
 #define _STR(x) #x
 #define STR(x) _STR(x)
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5186e72..60e5e46 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1305,6 +1305,7 @@
 	.unlocked_ioctl = kvm_vcpu_ioctl,
 	.compat_ioctl   = kvm_vcpu_ioctl,
 	.mmap           = kvm_vcpu_mmap,
+	.llseek		= noop_llseek,
 };
 
 /*
@@ -1774,6 +1775,7 @@
 	.compat_ioctl   = kvm_vm_compat_ioctl,
 #endif
 	.mmap           = kvm_vm_mmap,
+	.llseek		= noop_llseek,
 };
 
 static int kvm_dev_ioctl_create_vm(void)
@@ -1867,6 +1869,7 @@
 static struct file_operations kvm_chardev_ops = {
 	.unlocked_ioctl = kvm_dev_ioctl,
 	.compat_ioctl   = kvm_dev_ioctl,
+	.llseek		= noop_llseek,
 };
 
 static struct miscdevice kvm_dev = {