diff --git a/CREDITS b/CREDITS
index 10a9eee..c585607 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3949,8 +3949,6 @@
 D: Ralink rt2x00 WLAN driver
 D: Minix V2 file-system
 D: Misc fixes
-S: Geessinkweg 177
-S: 7544 TX Enschede
 S: The Netherlands
 
 N: Lars Wirzenius
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 4987417..2a4a423 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -272,6 +272,22 @@
 				     the modified cache line is written to main
 				     memory only when it is replaced
 
+
+What:		/sys/devices/system/cpu/cpu*/cache/index*/id
+Date:		September 2016
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Cache id
+
+		The id provides a unique number for a specific instance of
+		a cache of a particular type. E.g. there may be a level
+		3 unified cache on each socket in a server and we may
+		assign them ids 0, 1, 2, ...
+
+		Note that id value can be non-contiguous. E.g. level 1
+		caches typically exist per core, but there may not be a
+		power of two cores on a socket, so these caches may be
+		numbered 0, 1, 2, 3, 4, 5, 8, 9, 10, ...
+
 What:		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats
 		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat
 		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index c75e5d6..a6eb7dc 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -12,7 +12,7 @@
 	    kernel-api.xml filesystems.xml lsm.xml kgdb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
 	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
-	    80211.xml sh.xml regulator.xml w1.xml \
+	    sh.xml regulator.xml w1.xml \
 	    writing_musb_glue_layer.xml iio.xml
 
 ifeq ($(DOCBOOKS),)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index be2d6d0..21e2d88 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1441,6 +1441,10 @@
 			The builtin appraise policy appraises all files
 			owned by uid=0.
 
+	ima_canonical_fmt [IMA]
+			Use the canonical format for the binary runtime
+			measurements, instead of host native format.
+
 	ima_hash=	[IMA]
 			Format: { md5 | sha1 | rmd160 | sha256 | sha384
 				   | sha512 | ... }
diff --git a/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt b/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt
index 750374f..c0f37cb 100644
--- a/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt
+++ b/Documentation/devicetree/bindings/mmc/sdhci-cadence.txt
@@ -1,7 +1,9 @@
 * Cadence SD/SDIO/eMMC Host Controller
 
 Required properties:
-- compatible: should be "cdns,sd4hc".
+- compatible: should be one of the following:
+    "cdns,sd4hc"               - default of the IP
+    "socionext,uniphier-sd4hc" - for Socionext UniPhier SoCs
 - reg: offset and length of the register set for the device.
 - interrupts: a single interrupt specifier.
 - clocks: phandle to the input clock.
@@ -19,7 +21,7 @@
 
 Example:
 	emmc: sdhci@5a000000 {
-		compatible = "cdns,sd4hc";
+		compatible = "socionext,uniphier-sd4hc", "cdns,sd4hc";
 		reg = <0x5a000000 0x400>;
 		interrupts = <0 78 4>;
 		clocks = <&clk 4>;
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt b/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt
index 063c02d..eea73ad 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt
@@ -2,11 +2,14 @@
 
 Required properties:
 - compatible: should contain one of the following SoC strings:
-	* "hisilicon,hix5hd2-gemac"
-	* "hisilicon,hi3798cv200-gemac"
+	* "hisilicon,hix5hd2-gmac"
+	* "hisilicon,hi3798cv200-gmac"
+	* "hisilicon,hi3516a-gmac"
 	and one of the following version string:
-	* "hisilicon,hisi-gemac-v1"
-	* "hisilicon,hisi-gemac-v2"
+	* "hisilicon,hisi-gmac-v1"
+	* "hisilicon,hisi-gmac-v2"
+  The version v1 includes SoCs hix5hd2.
+  The version v2 includes SoCs hi3798cv200, hi3516a.
 - reg: specifies base physical address(s) and size of the device registers.
   The first region is the MAC register base and size.
   The second region is external interface control register.
@@ -35,7 +38,7 @@
 
 Example:
 	gmac0: ethernet@f9840000 {
-		compatible = "hisilicon,hi3798cv200-gemac", "hisilicon,hisi-gemac-v2";
+		compatible = "hisilicon,hi3798cv200-gmac", "hisilicon,hisi-gmac-v2";
 		reg = <0xf9840000 0x1000>,<0xf984300c 0x4>;
 		interrupts = <0 71 4>;
 		#address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index 54749b6..ff1bc4b 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -38,8 +38,14 @@
 - enet-phy-lane-swap: If set, indicates the PHY will swap the TX/RX lanes to
   compensate for the board being designed with the lanes swapped.
 
-- eee-broken-modes: Bits to clear in the MDIO_AN_EEE_ADV register to
-  disable EEE broken modes.
+- eee-broken-100tx:
+- eee-broken-1000t:
+- eee-broken-10gt:
+- eee-broken-1000kx:
+- eee-broken-10gkx4:
+- eee-broken-10gkr:
+  Mark the corresponding energy efficient ethernet mode as broken and
+  request the ethernet to stop advertising it.
 
 Example:
 
diff --git a/Documentation/features/io/dma-api-debug/arch-support.txt b/Documentation/features/io/dma-api-debug/arch-support.txt
index 4f4a344..ffa522a 100644
--- a/Documentation/features/io/dma-api-debug/arch-support.txt
+++ b/Documentation/features/io/dma-api-debug/arch-support.txt
@@ -36,5 +36,5 @@
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  |
-    |      xtensa: | TODO |
+    |      xtensa: |  ok  |
     -----------------------
diff --git a/Documentation/features/io/dma-contiguous/arch-support.txt b/Documentation/features/io/dma-contiguous/arch-support.txt
index a97e8e3..83d2cf9 100644
--- a/Documentation/features/io/dma-contiguous/arch-support.txt
+++ b/Documentation/features/io/dma-contiguous/arch-support.txt
@@ -36,5 +36,5 @@
     |          um: | TODO |
     |   unicore32: | TODO |
     |         x86: |  ok  |
-    |      xtensa: | TODO |
+    |      xtensa: |  ok  |
     -----------------------
diff --git a/Documentation/features/io/sg-chain/arch-support.txt b/Documentation/features/io/sg-chain/arch-support.txt
index b9b6755..6ca98f9 100644
--- a/Documentation/features/io/sg-chain/arch-support.txt
+++ b/Documentation/features/io/sg-chain/arch-support.txt
@@ -7,7 +7,7 @@
     |         arch |status|
     -----------------------
     |       alpha: | TODO |
-    |         arc: | TODO |
+    |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
     |       avr32: | TODO |
diff --git a/Documentation/scsi/g_NCR5380.txt b/Documentation/scsi/g_NCR5380.txt
index e2c1879..37b1967 100644
--- a/Documentation/scsi/g_NCR5380.txt
+++ b/Documentation/scsi/g_NCR5380.txt
@@ -6,17 +6,15 @@
 This file documents the NCR53c400 extensions by Kevin Lentin and some
 enhancements to the NCR5380 core.
 
-This driver supports both NCR5380 and NCR53c400 cards in port or memory
-mapped modes. Currently this driver can only support one of those mapping
-modes at a time but it does support both of these chips at the same time.
-The next release of this driver will support port & memory mapped cards at
-the same time. It should be able to handle multiple different cards in the
-same machine.
+This driver supports NCR5380 and NCR53c400 and compatible cards in port or
+memory mapped modes.
 
-The drivers/scsi/Makefile has an override in it for the most common
-NCR53c400 card, the Trantor T130B in its default configuration:
-	Port: 0x350
-	IRQ : 5
+Use of an interrupt is recommended, if supported by the board, as this will
+allow targets to disconnect and thereby improve SCSI bus utilization.
+
+If the irq parameter is 254 or is omitted entirely, the driver will probe
+for the correct IRQ line automatically. If the irq parameter is 0 or 255
+then no IRQ will be used.
 
 The NCR53c400 does not support DMA but it does have Pseudo-DMA which is
 supported by the driver.
@@ -47,22 +45,24 @@
   dtc_3181e=1  to set up for a Domex Technology Corp 3181E board
   hp_c2502=1   to set up for a Hewlett Packard C2502 board
 
-e.g.
-OLD: modprobe g_NCR5380 ncr_irq=5 ncr_addr=0x350 ncr_5380=1
-NEW: modprobe g_NCR5380 irq=5 base=0x350 card=0
-  for a port mapped NCR5380 board or
+E.g. Trantor T130B in its default configuration:
+modprobe g_NCR5380 irq=5 base=0x350 card=1
+or alternatively, using the old syntax,
+modprobe g_NCR5380 ncr_irq=5 ncr_addr=0x350 ncr_53c400=1
 
-OLD: modprobe g_NCR5380 ncr_irq=255 ncr_addr=0xc8000 ncr_53c400=1
-NEW: modprobe g_NCR5380 irq=255 base=0xc8000 card=1
-  for a memory mapped NCR53C400 board with interrupts disabled or
+E.g. a port mapped NCR5380 board, driver to probe for IRQ:
+modprobe g_NCR5380 base=0x350 card=0
+or alternatively,
+modprobe g_NCR5380 ncr_addr=0x350 ncr_5380=1
 
-NEW: modprobe g_NCR5380 irq=0,7 base=0x240,0x300 card=3,4
-  for two cards: DTC3181 (in non-PnP mode) at 0x240 with no IRQ
-             and HP C2502 at 0x300 with IRQ 7
+E.g. a memory mapped NCR53C400 board with no IRQ:
+modprobe g_NCR5380 irq=255 base=0xc8000 card=1
+or alternatively,
+modprobe g_NCR5380 ncr_irq=255 ncr_addr=0xc8000 ncr_53c400=1
 
-(255 should be specified for no or DMA interrupt, 254 to autoprobe for an 
-     IRQ line if overridden on the command line.)
-
+E.g. two cards, DTC3181 (in non-PnP mode) at 0x240 with no IRQ
+and HP C2502 at 0x300 with IRQ 7:
+modprobe g_NCR5380 irq=0,7 base=0x240,0x300 card=3,4
 
 Kevin Lentin
 K.Lentin@cs.monash.edu.au
diff --git a/Documentation/sphinx/rstFlatTable.py b/Documentation/sphinx/rstFlatTable.py
index 55f2757..25feb0d 100755
--- a/Documentation/sphinx/rstFlatTable.py
+++ b/Documentation/sphinx/rstFlatTable.py
@@ -157,6 +157,11 @@
     def buildTableNode(self):
 
         colwidths    = self.directive.get_column_widths(self.max_cols)
+        if isinstance(colwidths, tuple):
+            # Since docutils 0.13, get_column_widths returns a (widths,
+            # colwidths) tuple, where widths is a string (i.e. 'auto').
+            # See https://sourceforge.net/p/docutils/patches/120/.
+            colwidths = colwidths[1]
         stub_columns = self.directive.options.get('stub-columns', 0)
         header_rows  = self.directive.options.get('header-rows', 0)
 
diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt
index a445da0..3f76c0c 100644
--- a/Documentation/unaligned-memory-access.txt
+++ b/Documentation/unaligned-memory-access.txt
@@ -151,7 +151,7 @@
 #else
 	const u16 *a = (const u16 *)addr1;
 	const u16 *b = (const u16 *)addr2;
-	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0;
+	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0;
 #endif
 }
 
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
new file mode 100644
index 0000000..d918d26
--- /dev/null
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -0,0 +1,214 @@
+User Interface for Resource Allocation in Intel Resource Director Technology
+
+Copyright (C) 2016 Intel Corporation
+
+Fenghua Yu <fenghua.yu@intel.com>
+Tony Luck <tony.luck@intel.com>
+
+This feature is enabled by the CONFIG_INTEL_RDT_A Kconfig and the
+X86 /proc/cpuinfo flag bits "rdt", "cat_l3" and "cdp_l3".
+
+To use the feature mount the file system:
+
+ # mount -t resctrl resctrl [-o cdp] /sys/fs/resctrl
+
+mount options are:
+
+"cdp": Enable code/data prioritization in L3 cache allocations.
+
+
+Info directory
+--------------
+
+The 'info' directory contains information about the enabled
+resources. Each resource has its own subdirectory. The subdirectory
+names reflect the resource names. Each subdirectory contains the
+following files:
+
+"num_closids":  The number of CLOSIDs which are valid for this
+	        resource. The kernel uses the smallest number of
+		CLOSIDs of all enabled resources as limit.
+
+"cbm_mask":     The bitmask which is valid for this resource. This
+		mask is equivalent to 100%.
+
+"min_cbm_bits": The minimum number of consecutive bits which must be
+		set when writing a mask.
+
+
+Resource groups
+---------------
+Resource groups are represented as directories in the resctrl file
+system. The default group is the root directory. Other groups may be
+created as desired by the system administrator using the "mkdir(1)"
+command, and removed using "rmdir(1)".
+
+There are three files associated with each group:
+
+"tasks": A list of tasks that belongs to this group. Tasks can be
+	added to a group by writing the task ID to the "tasks" file
+	(which will automatically remove them from the previous
+	group to which they belonged). New tasks created by fork(2)
+	and clone(2) are added to the same group as their parent.
+	If a pid is not in any sub partition, it is in root partition
+	(i.e. default partition).
+
+"cpus": A bitmask of logical CPUs assigned to this group. Writing
+	a new mask can add/remove CPUs from this group. Added CPUs
+	are removed from their previous group. Removed ones are
+	given to the default (root) group. You cannot remove CPUs
+	from the default group.
+
+"schemata": A list of all the resources available to this group.
+	Each resource has its own line and format - see below for
+	details.
+
+When a task is running the following rules define which resources
+are available to it:
+
+1) If the task is a member of a non-default group, then the schemata
+for that group is used.
+
+2) Else if the task belongs to the default group, but is running on a
+CPU that is assigned to some specific group, then the schemata for
+the CPU's group is used.
+
+3) Otherwise the schemata for the default group is used.
+
+
+Schemata files - general concepts
+---------------------------------
+Each line in the file describes one resource. The line starts with
+the name of the resource, followed by specific values to be applied
+in each of the instances of that resource on the system.
+
+Cache IDs
+---------
+On current generation systems there is one L3 cache per socket and L2
+caches are generally just shared by the hyperthreads on a core, but this
+isn't an architectural requirement. We could have multiple separate L3
+caches on a socket, multiple cores could share an L2 cache. So instead
+of using "socket" or "core" to define the set of logical cpus sharing
+a resource we use a "Cache ID". At a given cache level this will be a
+unique number across the whole system (but it isn't guaranteed to be a
+contiguous sequence, there may be gaps).  To find the ID for each logical
+CPU look in /sys/devices/system/cpu/cpu*/cache/index*/id
+
+Cache Bit Masks (CBM)
+---------------------
+For cache resources we describe the portion of the cache that is available
+for allocation using a bitmask. The maximum value of the mask is defined
+by each cpu model (and may be different for different cache levels). It
+is found using CPUID, but is also provided in the "info" directory of
+the resctrl file system in "info/{resource}/cbm_mask". X86 hardware
+requires that these masks have all the '1' bits in a contiguous block. So
+0x3, 0x6 and 0xC are legal 4-bit masks with two bits set, but 0x5, 0x9
+and 0xA are not.  On a system with a 20-bit mask each bit represents 5%
+of the capacity of the cache. You could partition the cache into four
+equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000.
+
+
+L3 details (code and data prioritization disabled)
+--------------------------------------------------
+With CDP disabled the L3 schemata format is:
+
+	L3:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+L3 details (CDP enabled via mount option to resctrl)
+----------------------------------------------------
+When CDP is enabled L3 control is split into two separate resources
+so you can specify independent masks for code and data like this:
+
+	L3data:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+	L3code:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+L2 details
+----------
+L2 cache does not support code and data prioritization, so the
+schemata format is always:
+
+	L2:<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+Example 1
+---------
+On a two socket machine (one L3 cache per socket) with just four bits
+for cache bit masks
+
+# mount -t resctrl resctrl /sys/fs/resctrl
+# cd /sys/fs/resctrl
+# mkdir p0 p1
+# echo "L3:0=3;1=c" > /sys/fs/resctrl/p0/schemata
+# echo "L3:0=3;1=3" > /sys/fs/resctrl/p1/schemata
+
+The default resource group is unmodified, so we have access to all parts
+of all caches (its schemata file reads "L3:0=f;1=f").
+
+Tasks that are under the control of group "p0" may only allocate from the
+"lower" 50% on cache ID 0, and the "upper" 50% of cache ID 1.
+Tasks in group "p1" use the "lower" 50% of cache on both sockets.
+
+Example 2
+---------
+Again two sockets, but this time with a more realistic 20-bit mask.
+
+Two real time tasks pid=1234 running on processor 0 and pid=5678 running on
+processor 1 on socket 0 on a 2-socket and dual core machine. To avoid noisy
+neighbors, each of the two real-time tasks exclusively occupies one quarter
+of L3 cache on socket 0.
+
+# mount -t resctrl resctrl /sys/fs/resctrl
+# cd /sys/fs/resctrl
+
+First we reset the schemata for the default group so that the "upper"
+50% of the L3 cache on socket 0 cannot be used by ordinary tasks:
+
+# echo "L3:0=3ff;1=fffff" > schemata
+
+Next we make a resource group for our first real time task and give
+it access to the "top" 25% of the cache on socket 0.
+
+# mkdir p0
+# echo "L3:0=f8000;1=fffff" > p0/schemata
+
+Finally we move our first real time task into this resource group. We
+also use taskset(1) to ensure the task always runs on a dedicated CPU
+on socket 0. Most uses of resource groups will also constrain which
+processors tasks run on.
+
+# echo 1234 > p0/tasks
+# taskset -cp 1 1234
+
+Ditto for the second real time task (with the remaining 25% of cache):
+
+# mkdir p1
+# echo "L3:0=7c00;1=fffff" > p1/schemata
+# echo 5678 > p1/tasks
+# taskset -cp 2 5678
+
+Example 3
+---------
+
+A single socket system which has real-time tasks running on core 4-7 and
+non real-time workload assigned to core 0-3. The real-time tasks share text
+and data, so a per task association is not required and due to interaction
+with the kernel it's desired that the kernel on these cores shares L3 with
+the tasks.
+
+# mount -t resctrl resctrl /sys/fs/resctrl
+# cd /sys/fs/resctrl
+
+First we reset the schemata for the default group so that the "upper"
+50% of the L3 cache on socket 0 cannot be used by ordinary tasks:
+
+# echo "L3:0=3ff" > schemata
+
+Next we make a resource group for our real time cores and give
+it access to the "top" 50% of the cache on socket 0.
+
+# mkdir p0
+# echo "L3:0=ffc00;" > p0/schemata
+
+Finally we move core 4-7 over to the new group and make sure that the
+kernel and the tasks running there get 50% of the cache.
+
+# echo C0 > p0/cpus
diff --git a/Documentation/x86/topology.txt b/Documentation/x86/topology.txt
index 06afac2..f3e9d7e 100644
--- a/Documentation/x86/topology.txt
+++ b/Documentation/x86/topology.txt
@@ -63,6 +63,15 @@
     The maximum possible number of packages in the system. Helpful for per
     package facilities to preallocate per package information.
 
+  - cpu_llc_id:
+
+    A per-CPU variable containing:
+    - On Intel, the first APIC ID of the list of CPUs sharing the Last Level
+    Cache
+
+    - On AMD, the Node ID or Core Complex ID containing the Last Level
+    Cache. In general, it is a number identifying an LLC uniquely on the
+    system.
 
 * Cores:
 
diff --git a/MAINTAINERS b/MAINTAINERS
index f6eb97b..cfff2c9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -143,7 +143,7 @@
 F:	drivers/net/ethernet/3com/typhoon*
 
 3WARE SAS/SATA-RAID SCSI DRIVERS (3W-XXXX, 3W-9XXX, 3W-SAS)
-M:	Adam Radford <linuxraid@lsi.com>
+M:	Adam Radford <aradford@gmail.com>
 L:	linux-scsi@vger.kernel.org
 W:	http://www.lsi.com
 S:	Supported
@@ -1747,7 +1747,7 @@
 
 ARM/SAMSUNG S5P SERIES JPEG CODEC SUPPORT
 M:	Andrzej Pietrasiewicz <andrzej.p@samsung.com>
-M:	Jacek Anaszewski <j.anaszewski@samsung.com>
+M:	Jacek Anaszewski <jacek.anaszewski@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org
 L:	linux-media@vger.kernel.org
 S:	Maintained
@@ -5735,7 +5735,7 @@
 F:	drivers/media/dvb-frontends/hd29l2*
 
 HEWLETT PACKARD ENTERPRISE ILO NMI WATCHDOG DRIVER
-M:	Brian Boylston <brian.boylston@hpe.com>
+M:	Jimmy Vance <jimmy.vance@hpe.com>
 S:	Supported
 F:	Documentation/watchdog/hpwdt.txt
 F:	drivers/watchdog/hpwdt.c
@@ -7229,7 +7229,7 @@
 
 LED SUBSYSTEM
 M:	Richard Purdie <rpurdie@rpsys.net>
-M:	Jacek Anaszewski <j.anaszewski@samsung.com>
+M:	Jacek Anaszewski <jacek.anaszewski@gmail.com>
 M:	Pavel Machek <pavel@ucw.cz>
 L:	linux-leds@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git
@@ -8828,7 +8828,7 @@
 F:	drivers/ntb/hw/intel/
 
 NTB AMD DRIVER
-M:	Xiangliang Yu <Xiangliang.Yu@amd.com>
+M:	Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
 L:	linux-ntb@googlegroups.com
 S:	Supported
 F:	drivers/ntb/hw/amd/
@@ -10136,6 +10136,12 @@
 F:	include/linux/qed/
 F:	drivers/net/ethernet/qlogic/qede/
 
+QLOGIC QL41xxx ISCSI DRIVER
+M:	QLogic-Storage-Upstream@cavium.com
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/scsi/qedi/
+
 QNX4 FILESYSTEM
 M:	Anders Larsen <al@alarsen.net>
 W:	http://www.alarsen.net/linux/qnx4fs/
@@ -10327,6 +10333,14 @@
 S:	Supported
 F:	drivers/infiniband/sw/rdmavt
 
+RDT - RESOURCE ALLOCATION
+M:	Fenghua Yu <fenghua.yu@intel.com>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+F:	arch/x86/kernel/cpu/intel_rdt*
+F:	arch/x86/include/asm/intel_rdt*
+F:	Documentation/x86/intel_rdt*
+
 READ-COPY UPDATE (RCU)
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
diff --git a/Makefile b/Makefile
index b103777..5470d59 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
-PATCHLEVEL = 9
+PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc2
 NAME = Roaring Lionus
 
 # *DOCUMENTATION*
diff --git a/arch/Kconfig b/arch/Kconfig
index 19483ae..99839c2 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -5,6 +5,9 @@
 config KEXEC_CORE
 	bool
 
+config HAVE_IMA_KEXEC
+	bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING
diff --git a/arch/alpha/boot/misc.c b/arch/alpha/boot/misc.c
index 3ff9a95..1b568ed 100644
--- a/arch/alpha/boot/misc.c
+++ b/arch/alpha/boot/misc.c
@@ -21,7 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define memzero(s,n)	memset ((s),0,(n))
 #define puts		srm_printk
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 2d6efcf..2f26ae7 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -26,7 +26,7 @@
 #include <linux/bitops.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 volatile unsigned long irq_err_count;
 DEFINE_PER_CPU(unsigned long, irq_pmi_count);
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 56e427c..54d8616 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -39,7 +39,7 @@
 
 #include <asm/fpu.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sysinfo.h>
 #include <asm/thread_info.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index b483156..bca963a 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -31,7 +31,7 @@
 #include <linux/rcupdate.h>
 
 #include <asm/reg.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c
index 04abdec..bc4d2cd 100644
--- a/arch/alpha/kernel/ptrace.c
+++ b/arch/alpha/kernel/ptrace.c
@@ -16,7 +16,7 @@
 #include <linux/tracehook.h>
 #include <linux/audit.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/fpu.h>
 
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index 4811e54..491e6a6 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -53,7 +53,7 @@ static struct notifier_block alpha_panic_block = {
         INT_MAX /* try to do it first */
 };
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/hwrpb.h>
 #include <asm/dma.h>
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 8dbfb15..17308f9 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -22,7 +22,7 @@
 #include <linux/syscalls.h>
 #include <linux/tracehook.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sigcontext.h>
 #include <asm/ucontext.h>
 
diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c
index ffe996a..705ae12 100644
--- a/arch/alpha/kernel/srm_env.c
+++ b/arch/alpha/kernel/srm_env.c
@@ -35,7 +35,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <asm/console.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/machvec.h>
 
 #define BASE_DIR	"srm_environment"	/* Subdir in /proc/		*/
diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 72b5951..e9c45b6 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -18,7 +18,7 @@
 #include <linux/tty_flip.h>
 
 #include <asm/console.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 static DEFINE_SPINLOCK(srmcons_callback_lock);
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index 5b6202a..3bfe058 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -34,7 +34,7 @@
 #include <linux/profile.h>
 #include <linux/irq_work.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/hwrpb.h>
 
@@ -133,7 +133,7 @@ init_rtc_clockevent(void)
  * The QEMU clock as a clocksource primitive.
  */
 
-static cycle_t
+static u64
 qemu_cs_read(struct clocksource *cs)
 {
 	return qemu_get_vmtime();
@@ -260,7 +260,7 @@ common_init_rtc(void)
  * use this method when WTINT is in use.
  */
 
-static cycle_t read_rpcc(struct clocksource *cs)
+static u64 read_rpcc(struct clocksource *cs)
 {
 	return rpcc();
 }
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 74aceea..3328af7 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -18,7 +18,7 @@
 #include <linux/ratelimit.h>
 
 #include <asm/gentrap.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 #include <asm/sysinfo.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index b4ff3b6..5dfb797 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -11,7 +11,7 @@
 
 #include <linux/types.h>
 #include <linux/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 #define ldq_u(x,y) \
diff --git a/arch/alpha/math-emu/math.c b/arch/alpha/math-emu/math.c
index 58c2669..fa5ae0a 100644
--- a/arch/alpha/math-emu/math.c
+++ b/arch/alpha/math-emu/math.c
@@ -3,7 +3,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "sfp-util.h"
 #include <math-emu/soft-fp.h>
diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index a1bea91..0542e97 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -22,7 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/gfp.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/hwrpb.h>
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index ab12723..c75d290 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -9,6 +9,7 @@
 config ARC
 	def_bool y
 	select ARC_TIMERS
+	select ARCH_HAS_SG_CHAIN
 	select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index da41a54..f659942 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -244,7 +244,7 @@ struct cpuinfo_arc_mmu {
 };
 
 struct cpuinfo_arc_cache {
-	unsigned int sz_k:14, line_len:8, assoc:4, ver:4, alias:1, vipt:1;
+	unsigned int sz_k:14, line_len:8, assoc:4, alias:1, vipt:1, pad:4;
 };
 
 struct cpuinfo_arc_bpu {
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index a093adb..fc662f4 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -85,6 +85,10 @@ void flush_anon_page(struct vm_area_struct *vma,
  */
 #define PG_dc_clean	PG_arch_1
 
+#define CACHE_COLORS_NUM	4
+#define CACHE_COLORS_MSK	(CACHE_COLORS_NUM - 1)
+#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & CACHE_COLORS_MSK)
+
 /*
  * Simple wrapper over config option
  * Bootup code ensures that hardware matches kernel configuration
@@ -94,8 +98,6 @@ static inline int cache_is_vipt_aliasing(void)
 	return IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
 }
 
-#define CACHE_COLOR(addr)	(((unsigned long)(addr) >> (PAGE_SHIFT)) & 1)
-
 /*
  * checks if two addresses (after page aligning) index into same cache set
  */
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index e880dfa..a64c447 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -38,10 +38,10 @@
 #define AUX_IRQ_ACT_BIT_U	31
 
 /*
- * User space should be interruptable even by lowest prio interrupt
- * Safe even if actual interrupt priorities is fewer or even one
+ * Hardware supports 16 priorities (0 highest, 15 lowest)
+ * Linux by default runs at 1, priority 0 reserved for NMI style interrupts
  */
-#define ARCV2_IRQ_DEF_PRIO	15
+#define ARCV2_IRQ_DEF_PRIO	1
 
 /* seed value for status register */
 #define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index 7a1c124..0b6388a 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -67,12 +67,23 @@
 
 	INTERRUPT_PROLOGUE  irq
 
-	clri		; To make status32.IE agree with CPU internal state
+	# irq control APIs local_irq_save/restore/disable/enable fiddle with
+	# global interrupt enable bits in STATUS32 (.IE for 1 prio, .E[] for 2 prio)
+	# However a taken interrupt doesn't clear these bits. Thus irqs_disabled()
+	# query in hard ISR path would return false (since .IE is set) which would
+	# trips genirq interrupt handling asserts.
+	#
+	# So do a "soft" disable of interrutps here.
+	#
+	# Note this disable is only for consistent book-keeping as further interrupts
+	# will be disabled anyways even w/o this. Hardware tracks active interrupts
+	# seperately in AUX_IRQ_ACTIVE.active and will not take new interrupts
+	# unless this one returns (or higher prio becomes pending in 2-prio scheme)
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	TRACE_ASM_IRQ_DISABLE
-#endif
+	IRQ_DISABLE
 
+	; icause is banked: one per priority level
+	; so a higher prio interrupt taken here won't clobber prev prio icause
 	lr  r0, [ICAUSE]
 	mov   blink, ret_from_exception
 
@@ -171,6 +182,7 @@
 ; All 2 entry points to here already disable interrupts
 
 .Lrestore_regs:
+restore_regs:
 
 	# Interrpts are actually disabled from this point on, but will get
 	# reenabled after we return from interrupt/exception.
diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S
index 98812c1..9211707 100644
--- a/arch/arc/kernel/entry-compact.S
+++ b/arch/arc/kernel/entry-compact.S
@@ -259,7 +259,7 @@
 
 	EXCEPTION_PROLOGUE
 
-	lr  r2, [ecr]
+	mov r2, r9	; ECR set into r9 already
 	lr  r0, [efa]	; Faulting Data address (not part of pt_regs saved above)
 
 	; Exception auto-disables further Intr/exceptions.
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 62b59409..994dca7 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -14,8 +14,6 @@
 #include <linux/irqchip.h>
 #include <asm/irq.h>
 
-static int irq_prio;
-
 /*
  * Early Hardware specific Interrupt setup
  * -Called very early (start_kernel -> setup_arch -> setup_processor)
@@ -24,7 +22,7 @@ static int irq_prio;
  */
 void arc_init_IRQ(void)
 {
-	unsigned int tmp;
+	unsigned int tmp, irq_prio;
 
 	struct irq_build {
 #ifdef CONFIG_CPU_BIG_ENDIAN
@@ -67,12 +65,12 @@ void arc_init_IRQ(void)
 
 	irq_prio = irq_bcr.prio;	/* Encoded as N-1 for N levels */
 	pr_info("archs-intc\t: %d priority levels (default %d)%s\n",
-		irq_prio + 1, irq_prio,
+		irq_prio + 1, ARCV2_IRQ_DEF_PRIO,
 		irq_bcr.firq ? " FIRQ (not used)":"");
 
 	/* setup status32, don't enable intr yet as kernel doesn't want */
 	tmp = read_aux_reg(0xa);
-	tmp |= STATUS_AD_MASK | (irq_prio << 1);
+	tmp |= STATUS_AD_MASK | (ARCV2_IRQ_DEF_PRIO << 1);
 	tmp &= ~STATUS_IE_MASK;
 	asm volatile("kflag %0	\n"::"r"(tmp));
 }
@@ -93,7 +91,7 @@ void arcv2_irq_enable(struct irq_data *data)
 {
 	/* set default priority */
 	write_aux_reg(AUX_IRQ_SELECT, data->irq);
-	write_aux_reg(AUX_IRQ_PRIORITY, irq_prio);
+	write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
 
 	/*
 	 * hw auto enables (linux unmask) all by default
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 50d7169..ec86ac0 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -40,7 +40,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 	struct cpuinfo_arc_cache *p;
 
 #define PR_CACHE(p, cfg, str)						\
-	if (!(p)->ver)							\
+	if (!(p)->line_len)						\
 		n += scnprintf(buf + n, len - n, str"\t\t: N/A\n");	\
 	else								\
 		n += scnprintf(buf + n, len - n,			\
@@ -54,7 +54,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 	PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache");
 
 	p = &cpuinfo_arc700[c].slc;
-	if (p->ver)
+	if (p->line_len)
 		n += scnprintf(buf + n, len - n,
 			       "SLC\t\t: %uK, %uB Line%s\n",
 			       p->sz_k, p->line_len, IS_USED_RUN(slc_enable));
@@ -104,7 +104,6 @@ static void read_decode_cache_bcr_arcv2(int cpu)
 	READ_BCR(ARC_REG_SLC_BCR, sbcr);
 	if (sbcr.ver) {
 		READ_BCR(ARC_REG_SLC_CFG, slc_cfg);
-		p_slc->ver = sbcr.ver;
 		p_slc->sz_k = 128 << slc_cfg.sz;
 		l2_line_sz = p_slc->line_len = (slc_cfg.lsz == 0) ? 128 : 64;
 	}
@@ -152,7 +151,6 @@ void read_decode_cache_bcr(void)
 
 	p_ic->line_len = 8 << ibcr.line_len;
 	p_ic->sz_k = 1 << (ibcr.sz - 1);
-	p_ic->ver = ibcr.ver;
 	p_ic->vipt = 1;
 	p_ic->alias = p_ic->sz_k/p_ic->assoc/TO_KB(PAGE_SIZE) > 1;
 
@@ -176,7 +174,6 @@ void read_decode_cache_bcr(void)
 
 	p_dc->line_len = 16 << dbcr.line_len;
 	p_dc->sz_k = 1 << (dbcr.sz - 1);
-	p_dc->ver = dbcr.ver;
 
 slc_chk:
 	if (is_isa_arcv2())
@@ -945,17 +942,13 @@ void arc_cache_init(void)
 	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
 		struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
 
-		if (!ic->ver)
+		if (!ic->line_len)
 			panic("cache support enabled but non-existent cache\n");
 
 		if (ic->line_len != L1_CACHE_BYTES)
 			panic("ICache line [%d] != kernel Config [%d]",
 			      ic->line_len, L1_CACHE_BYTES);
 
-		if (ic->ver != CONFIG_ARC_MMU_VER)
-			panic("Cache ver [%d] doesn't match MMU ver [%d]\n",
-			      ic->ver, CONFIG_ARC_MMU_VER);
-
 		/*
 		 * In MMU v4 (HS38x) the aliasing icache config uses IVIL/PTAG
 		 * pair to provide vaddr/paddr respectively, just as in MMU v3
@@ -969,7 +962,7 @@ void arc_cache_init(void)
 	if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE)) {
 		struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache;
 
-		if (!dc->ver)
+		if (!dc->line_len)
 			panic("cache support enabled but non-existent cache\n");
 
 		if (dc->line_len != L1_CACHE_BYTES)
@@ -979,11 +972,16 @@ void arc_cache_init(void)
 		/* check for D-Cache aliasing on ARCompact: ARCv2 has PIPT */
 		if (is_isa_arcompact()) {
 			int handled = IS_ENABLED(CONFIG_ARC_CACHE_VIPT_ALIASING);
+			int num_colors = dc->sz_k/dc->assoc/TO_KB(PAGE_SIZE);
 
-			if (dc->alias && !handled)
-				panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-			else if (!dc->alias && handled)
+			if (dc->alias) {
+				if (!handled)
+					panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+				if (CACHE_COLORS_NUM != num_colors)
+					panic("CACHE_COLORS_NUM not optimized for config\n");
+			} else if (!dc->alias && handled) {
 				panic("Disable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+			}
 		}
 	}
 
diff --git a/arch/arm/boot/dts/hisi-x5hd2.dtsi b/arch/arm/boot/dts/hisi-x5hd2.dtsi
index c02e092..6c712a9 100644
--- a/arch/arm/boot/dts/hisi-x5hd2.dtsi
+++ b/arch/arm/boot/dts/hisi-x5hd2.dtsi
@@ -438,7 +438,7 @@
 		};
 
 		gmac0: ethernet@1840000 {
-			compatible = "hisilicon,hix5hd2-gemac", "hisilicon,hisi-gemac-v1";
+			compatible = "hisilicon,hix5hd2-gmac", "hisilicon,hisi-gmac-v1";
 			reg = <0x1840000 0x1000>,<0x184300c 0x4>;
 			interrupts = <0 71 4>;
 			clocks = <&clock HIX5HD2_MAC0_CLK>;
@@ -447,7 +447,7 @@
 		};
 
 		gmac1: ethernet@1841000 {
-			compatible = "hisilicon,hix5hd2-gemac", "hisilicon,hisi-gemac-v1";
+			compatible = "hisilicon,hix5hd2-gmac", "hisilicon,hisi-gmac-v1";
 			reg = <0x1841000 0x1000>,<0x1843010 0x4>;
 			interrupts = <0 72 4>;
 			clocks = <&clock HIX5HD2_MAC1_CLK>;
diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c
index 6053f64..4c10c64 100644
--- a/arch/arm/common/bL_switcher_dummy_if.c
+++ b/arch/arm/common/bL_switcher_dummy_if.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/miscdevice.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/bL_switcher.h>
 
 static ssize_t bL_switcher_write(struct file *file, const char __user *buf,
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 02d5e5e..895ae51 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -339,7 +339,7 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING,
-				  "AP_ARM_TWD_STARTING",
+				  "arm/timer/twd:starting",
 				  twd_timer_starting_cpu, twd_timer_dying_cpu);
 
 	twd_get_clock(np);
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index c3fe769d..853221f 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -29,7 +29,7 @@
 #include <asm/opcodes.h>
 #include <asm/system_info.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Error-checking SWP macros implemented using ldrex{b}/strex{b}
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 8f92efa..1167678 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -33,7 +33,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/mman.h>
 #include <asm/tlbflush.h>
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 9aca920..fa6182a 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -23,7 +23,7 @@
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <asm/cputype.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/kvm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c
index 6c18445..034f865 100644
--- a/arch/arm/mach-davinci/time.c
+++ b/arch/arm/mach-davinci/time.c
@@ -268,7 +268,7 @@ static void __init timer_init(void)
 /*
  * clocksource
  */
-static cycle_t read_cycles(struct clocksource *cs)
+static u64 read_cycles(struct clocksource *cs)
 {
 	struct timer_s *t = &timers[TID_CLOCKSOURCE];
 
diff --git a/arch/arm/mach-ep93xx/timer-ep93xx.c b/arch/arm/mach-ep93xx/timer-ep93xx.c
index e5f7911..874cbc9 100644
--- a/arch/arm/mach-ep93xx/timer-ep93xx.c
+++ b/arch/arm/mach-ep93xx/timer-ep93xx.c
@@ -59,13 +59,13 @@ static u64 notrace ep93xx_read_sched_clock(void)
 	return ret;
 }
 
-cycle_t ep93xx_clocksource_read(struct clocksource *c)
+u64 ep93xx_clocksource_read(struct clocksource *c)
 {
 	u64 ret;
 
 	ret = readl(EP93XX_TIMER4_VALUE_LOW);
 	ret |= ((u64) (readl(EP93XX_TIMER4_VALUE_HIGH) & 0xff) << 32);
-	return (cycle_t) ret;
+	return (u64) ret;
 }
 
 static int ep93xx_clkevt_set_next_event(unsigned long next,
diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index 810edc7..75395a7 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -19,7 +19,7 @@
 
 #include "common.h"
 
-static cycle_t cksrc_dc21285_read(struct clocksource *cs)
+static u64 cksrc_dc21285_read(struct clocksource *cs)
 {
 	return cs->mask - *CSR_TIMER2_VALUE;
 }
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index ba96bf9..6991577 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -60,6 +60,7 @@
 
 #define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu)
 
+static enum cpuhp_state cpuhp_mmdc_state;
 static int ddr_type;
 
 struct fsl_mmdc_devtype_data {
@@ -451,8 +452,8 @@ static int imx_mmdc_remove(struct platform_device *pdev)
 {
 	struct mmdc_pmu *pmu_mmdc = platform_get_drvdata(pdev);
 
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	perf_pmu_unregister(&pmu_mmdc->pmu);
-	cpuhp_remove_state_nocalls(CPUHP_ONLINE);
 	kfree(pmu_mmdc);
 	return 0;
 }
@@ -472,6 +473,18 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 		return -ENOMEM;
 	}
 
+	/* The first instance registers the hotplug state */
+	if (!cpuhp_mmdc_state) {
+		ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					      "perf/arm/mmdc:online", NULL,
+					      mmdc_pmu_offline_cpu);
+		if (ret < 0) {
+			pr_err("cpuhp_setup_state_multi failed\n");
+			goto pmu_free;
+		}
+		cpuhp_mmdc_state = ret;
+	}
+
 	mmdc_num = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev);
 	if (mmdc_num == 0)
 		name = "mmdc";
@@ -485,26 +498,23 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 			HRTIMER_MODE_REL);
 	pmu_mmdc->hrtimer.function = mmdc_pmu_timer_handler;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_ONLINE,
-					 &pmu_mmdc->node);
-	cpumask_set_cpu(smp_processor_id(), &pmu_mmdc->cpu);
-	ret = cpuhp_setup_state_multi(CPUHP_AP_NOTIFY_ONLINE,
-				      "MMDC_ONLINE", NULL,
-				      mmdc_pmu_offline_cpu);
-	if (ret) {
-		pr_err("cpuhp_setup_state_multi failure\n");
-		goto pmu_register_err;
-	}
+	cpumask_set_cpu(raw_smp_processor_id(), &pmu_mmdc->cpu);
+
+	/* Register the pmu instance for cpu hotplug */
+	cpuhp_state_add_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 
 	ret = perf_pmu_register(&(pmu_mmdc->pmu), name, -1);
-	platform_set_drvdata(pdev, pmu_mmdc);
 	if (ret)
 		goto pmu_register_err;
+
+	platform_set_drvdata(pdev, pmu_mmdc);
 	return 0;
 
 pmu_register_err:
 	pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret);
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	hrtimer_cancel(&pmu_mmdc->hrtimer);
+pmu_free:
 	kfree(pmu_mmdc);
 	return ret;
 }
diff --git a/arch/arm/mach-iop13xx/irq.c b/arch/arm/mach-iop13xx/irq.c
index c702cc4..bd9b43c 100644
--- a/arch/arm/mach-iop13xx/irq.c
+++ b/arch/arm/mach-iop13xx/irq.c
@@ -20,7 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/sysctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mach/irq.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 26874f6..846e033 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -34,7 +34,7 @@
 #include <mach/udc.h>
 #include <mach/hardware.h>
 #include <mach/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/irq.h>
@@ -493,7 +493,7 @@ static u64 notrace ixp4xx_read_sched_clock(void)
  * clocksource
  */
 
-static cycle_t ixp4xx_clocksource_read(struct clocksource *c)
+static u64 ixp4xx_clocksource_read(struct clocksource *c)
 {
 	return *IXP4XX_OSTS;
 }
diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c
index 3c2c92a..96ad1db 100644
--- a/arch/arm/mach-mmp/time.c
+++ b/arch/arm/mach-mmp/time.c
@@ -144,7 +144,7 @@ static struct clock_event_device ckevt = {
 	.set_state_oneshot	= timer_set_shutdown,
 };
 
-static cycle_t clksrc_read(struct clocksource *cs)
+static u64 clksrc_read(struct clocksource *cs)
 {
 	return timer_read();
 }
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index ae2a018..8f8748a 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -148,7 +148,7 @@ static void __init armada_370_coherency_init(struct device_node *np)
 	of_node_put(cpu_config_np);
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_MVEBU_COHERENCY,
-				  "AP_ARM_MVEBU_COHERENCY",
+				  "arm/mvebu/coherency:starting",
 				  armada_xp_clear_l2_starting, NULL);
 exit:
 	set_cpu_coherent();
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 5e2e221..56128da 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -369,9 +369,9 @@ static bool use_gptimer_clksrc __initdata;
 /*
  * clocksource
  */
-static cycle_t clocksource_read_cycles(struct clocksource *cs)
+static u64 clocksource_read_cycles(struct clocksource *cs)
 {
-	return (cycle_t)__omap_dm_timer_read_counter(&clksrc,
+	return (u64)__omap_dm_timer_read_counter(&clksrc,
 						     OMAP_TIMER_NONPOSTED);
 }
 
diff --git a/arch/arm/mach-rpc/dma.c b/arch/arm/mach-rpc/dma.c
index 6d3517d..fb48f31 100644
--- a/arch/arm/mach-rpc/dma.c
+++ b/arch/arm/mach-rpc/dma.c
@@ -20,7 +20,7 @@
 #include <asm/fiq.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/mach/dma.h>
 #include <asm/hardware/iomd.h>
diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c
index 976d305..0a1e228 100644
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -563,7 +563,7 @@ static __init int l2x0_pmu_init(void)
 
 	cpumask_set_cpu(0, &pmu_cpu);
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE,
-					"AP_PERF_ARM_L2X0_ONLINE", NULL,
+					"perf/arm/l2x0:online", NULL,
 					l2x0_pmu_offline_cpu);
 	if (ret)
 		goto out_pmu;
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index d1870c7..2290be3 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -683,7 +683,7 @@ static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
 
 	if (aux & L310_AUX_CTRL_FULL_LINE_ZERO)
 		cpuhp_setup_state(CPUHP_AP_ARM_L2X0_STARTING,
-				  "AP_ARM_L2X0_STARTING", l2c310_starting_cpu,
+				  "arm/l2x0:starting", l2c310_starting_cpu,
 				  l2c310_dying_cpu);
 }
 
diff --git a/arch/arm/plat-iop/time.c b/arch/arm/plat-iop/time.c
index 101e8f2..2cff001 100644
--- a/arch/arm/plat-iop/time.c
+++ b/arch/arm/plat-iop/time.c
@@ -25,7 +25,7 @@
 #include <linux/sched_clock.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 #include <mach/time.h>
@@ -38,7 +38,7 @@
 /*
  * IOP clocksource (free-running timer 1).
  */
-static cycle_t notrace iop_clocksource_read(struct clocksource *unused)
+static u64 notrace iop_clocksource_read(struct clocksource *unused)
 {
 	return 0xffffffffu - read_tcr1();
 }
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 0351f56..569d5a6 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -799,7 +799,7 @@ static int __init vfp_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_VFP_STARTING,
-				  "AP_ARM_VFP_STARTING", vfp_starting_cpu,
+				  "arm/vfp:starting", vfp_starting_cpu,
 				  vfp_dying_cpu);
 
 	vfp_vector = vfp_support_entry;
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 4986dc0..11d9f28 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -412,7 +412,7 @@ static int __init xen_guest_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 
 	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
-				 "AP_ARM_XEN_STARTING", xen_starting_cpu,
+				 "arm/xen:starting", xen_starting_cpu,
 				 xen_dying_cpu);
 }
 early_initcall(xen_guest_init);
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index d0de0e0..c1976c0 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -29,7 +29,7 @@
 
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
-/* ACPI table mapping after acpi_gbl_permanent_mmap is set */
+/* ACPI table mapping after acpi_permanent_mmap is set */
 static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
 					    acpi_size size)
 {
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
new file mode 100644
index 0000000..df411f3
--- /dev/null
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -0,0 +1,65 @@
+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sysreg.h>
+#include <asm/assembler.h>
+
+/*
+ * User access enabling/disabling macros.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	.macro	__uaccess_ttbr0_disable, tmp1
+	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
+	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
+	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
+	isb
+	.endm
+
+	.macro	__uaccess_ttbr0_enable, tmp1
+	get_thread_info \tmp1
+	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
+	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
+	isb
+	.endm
+
+	.macro	uaccess_ttbr0_disable, tmp1
+alternative_if_not ARM64_HAS_PAN
+	__uaccess_ttbr0_disable \tmp1
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1
+	restore_irq \tmp2
+alternative_else_nop_endif
+	.endm
+#else
+	.macro	uaccess_ttbr0_disable, tmp1
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.endm
+#endif
+
+/*
+ * These macros are no-ops when UAO is present.
+ */
+	.macro	uaccess_disable_not_uao, tmp1
+	uaccess_ttbr0_disable \tmp1
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(1)
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_enable_not_uao, tmp1, tmp2
+	uaccess_ttbr0_enable \tmp1, \tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(0)
+alternative_else_nop_endif
+	.endm
+
+#endif
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index b71086d..bfe6328 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -165,6 +165,11 @@ extern u64			kimage_vaddr;
 /* the offset between the kernel virtual and physical mappings */
 extern u64			kimage_voffset;
 
+static inline unsigned long kaslr_offset(void)
+{
+	return kimage_vaddr - KIMAGE_VADDR;
+}
+
 /*
  * Allow all memory at the discovery stage. We will clip it later.
  */
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index d26750c..46da3ea 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -22,8 +22,6 @@
 #include <asm/kernel-pgtable.h>
 #include <asm/sysreg.h>
 
-#ifndef __ASSEMBLY__
-
 /*
  * User space memory access functions
  */
@@ -424,66 +422,4 @@ extern long strncpy_from_user(char *dest, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
-#else	/* __ASSEMBLY__ */
-
-#include <asm/assembler.h>
-
-/*
- * User access enabling/disabling macros.
- */
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
-	.macro	__uaccess_ttbr0_disable, tmp1
-	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
-	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
-	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
-	isb
-	.endm
-
-	.macro	__uaccess_ttbr0_enable, tmp1
-	get_thread_info \tmp1
-	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
-	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
-	isb
-	.endm
-
-	.macro	uaccess_ttbr0_disable, tmp1
-alternative_if_not ARM64_HAS_PAN
-	__uaccess_ttbr0_disable \tmp1
-alternative_else_nop_endif
-	.endm
-
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
-alternative_if_not ARM64_HAS_PAN
-	save_and_disable_irq \tmp2		// avoid preemption
-	__uaccess_ttbr0_enable \tmp1
-	restore_irq \tmp2
-alternative_else_nop_endif
-	.endm
-#else
-	.macro	uaccess_ttbr0_disable, tmp1
-	.endm
-
-	.macro	uaccess_ttbr0_enable, tmp1, tmp2
-	.endm
-#endif
-
-/*
- * These macros are no-ops when UAO is present.
- */
-	.macro	uaccess_disable_not_uao, tmp1
-	uaccess_ttbr0_disable \tmp1
-alternative_if ARM64_ALT_PAN_NOT_UAO
-	SET_PSTATE_PAN(1)
-alternative_else_nop_endif
-	.endm
-
-	.macro	uaccess_enable_not_uao, tmp1, tmp2
-	uaccess_ttbr0_enable \tmp1, \tmp2
-alternative_if ARM64_ALT_PAN_NOT_UAO
-	SET_PSTATE_PAN(0)
-alternative_else_nop_endif
-	.endm
-
-#endif	/* __ASSEMBLY__ */
-
 #endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h
index 2b79b8a..b0d708f 100644
--- a/arch/arm64/include/asm/word-at-a-time.h
+++ b/arch/arm64/include/asm/word-at-a-time.h
@@ -16,7 +16,7 @@
 #ifndef __ASM_WORD_AT_A_TIME_H
 #define __ASM_WORD_AT_A_TIME_H
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifndef __AARCH64EB__
 
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 252a6d9..64d9cbd6 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -132,14 +132,13 @@ static int __init acpi_fadt_sanity_check(void)
 	struct acpi_table_header *table;
 	struct acpi_table_fadt *fadt;
 	acpi_status status;
-	acpi_size tbl_size;
 	int ret = 0;
 
 	/*
 	 * FADT is required on arm64; retrieve it to check its presence
 	 * and carry out revision and ACPI HW reduced compliancy tests
 	 */
-	status = acpi_get_table_with_size(ACPI_SIG_FADT, 0, &table, &tbl_size);
+	status = acpi_get_table(ACPI_SIG_FADT, 0, &table);
 	if (ACPI_FAILURE(status)) {
 		const char *msg = acpi_format_exception(status);
 
@@ -170,10 +169,10 @@ static int __init acpi_fadt_sanity_check(void)
 
 out:
 	/*
-	 * acpi_get_table_with_size() creates FADT table mapping that
+	 * acpi_get_table() creates FADT table mapping that
 	 * should be released after parsing and before resuming boot
 	 */
-	early_acpi_os_unmap_memory(table, tbl_size);
+	acpi_put_table(table);
 	return ret;
 }
 
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 04de188..ecf9298 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -19,7 +19,7 @@
 #include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cpufeature.h>
 
 #define CREATE_TRACE_POINTS
@@ -640,7 +640,7 @@ static int __init armv8_deprecated_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
-				  "AP_ARM64_ISNDEP_STARTING",
+				  "arm64/isndep:starting",
 				  run_all_insn_set_hw_mode, NULL);
 	register_insn_emulation_sysctl(ctl_abi);
 
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 605df76..2bd4264 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -140,7 +140,7 @@ static int clear_os_lock(unsigned int cpu)
 static int debug_monitors_init(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
-				 "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING",
+				 "arm64/debug_monitors:starting",
 				 clear_os_lock, NULL);
 }
 postcore_initcall(debug_monitors_init);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 4f0d763..923841f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -31,7 +31,7 @@
 #include <asm/memory.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
-#include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
 
 /*
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 1b3c747..0296e79 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -1001,7 +1001,7 @@ static int __init arch_hw_breakpoint_init(void)
 	 * debugger will leave the world in a nice state for us.
 	 */
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
-			  "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING",
+			  "perf/arm64/hw_breakpoint:starting",
 			  hw_breakpoint_reset, NULL);
 	if (ret)
 		pr_err("failed to register CPU hotplug notifier: %d\n", ret);
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 1decd2b..f0593c9 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -29,7 +29,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/system_misc.h>
 #include <asm/insn.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 #include <asm/sections.h>
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index a53f52a..b051367 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -338,11 +338,11 @@ subsys_initcall(topology_init);
 static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
 			      void *p)
 {
-	u64 const kaslr_offset = kimage_vaddr - KIMAGE_VADDR;
+	const unsigned long offset = kaslr_offset();
 
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset > 0) {
-		pr_emerg("Kernel Offset: 0x%llx from 0x%lx\n",
-			 kaslr_offset, KIMAGE_VADDR);
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && offset > 0) {
+		pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
+			 offset, KIMAGE_VADDR);
 	} else {
 		pr_emerg("Kernel Offset: disabled\n");
 	}
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index b7063de..c747a0f 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -26,7 +26,7 @@
 #include <asm/esr.h>
 #include <asm/fpsimd.h>
 #include <asm/signal32.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 struct compat_sigcontext {
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 3f9e157..b37446a 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -26,7 +26,7 @@
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <asm/cputype.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/kvm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index d7150e3..e88fb99 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -17,7 +17,7 @@
  */
 #include <linux/linkage.h>
 
-#include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 	.text
 
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index cfe1339..4b5d826 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -17,7 +17,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy from user space to a kernel buffer (alignment handled by the hardware)
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 718b1c4..47184c3 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -19,7 +19,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy from user space to user space (alignment handled by the hardware)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index e99e31c..351f076 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -17,7 +17,7 @@
 #include <linux/linkage.h>
 
 #include <asm/cache.h>
-#include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  * Copy to user space from a kernel buffer (alignment handled by the hardware)
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index da95769..83c27b6e 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -23,7 +23,7 @@
 #include <asm/assembler.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
-#include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 
 /*
  *	flush_icache_range(start,end)
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index b41aff2..947830a 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -49,7 +49,7 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <asm/uaccess.h>
+#include <asm/asm-uaccess.h>
 #include <xen/interface/xen.h>
 
 
diff --git a/arch/avr32/kernel/avr32_ksyms.c b/arch/avr32/kernel/avr32_ksyms.c
index 7c6cf14..0d05fd0 100644
--- a/arch/avr32/kernel/avr32_ksyms.c
+++ b/arch/avr32/kernel/avr32_ksyms.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 
 #include <asm/checksum.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * GCC functions
diff --git a/arch/avr32/kernel/ptrace.c b/arch/avr32/kernel/ptrace.c
index 4aedcab..a89b893 100644
--- a/arch/avr32/kernel/ptrace.c
+++ b/arch/avr32/kernel/ptrace.c
@@ -17,7 +17,7 @@
 #include <linux/notifier.h>
 
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ocd.h>
 #include <asm/mmu_context.h>
 #include <linux/kdebug.h>
diff --git a/arch/avr32/kernel/signal.c b/arch/avr32/kernel/signal.c
index 8f1c63b..b5fcc49 100644
--- a/arch/avr32/kernel/signal.c
+++ b/arch/avr32/kernel/signal.c
@@ -17,7 +17,7 @@
 #include <linux/unistd.h>
 #include <linux/tracehook.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ucontext.h>
 #include <asm/syscalls.h>
 
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index a124c55..4d9b696 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -20,9 +20,9 @@
 
 static bool disable_cpu_idle_poll;
 
-static cycle_t read_cycle_count(struct clocksource *cs)
+static u64 read_cycle_count(struct clocksource *cs)
 {
-	return (cycle_t)sysreg_read(COUNT);
+	return (u64)sysreg_read(COUNT);
 }
 
 /*
diff --git a/arch/avr32/mm/cache.c b/arch/avr32/mm/cache.c
index 85d635c..d947682 100644
--- a/arch/avr32/mm/cache.c
+++ b/arch/avr32/mm/cache.c
@@ -12,7 +12,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cachectl.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/syscalls.h>
 
 /*
diff --git a/arch/blackfin/kernel/bfin_dma.c b/arch/blackfin/kernel/bfin_dma.c
index 4a32f2d..9d3eb0c 100644
--- a/arch/blackfin/kernel/bfin_dma.c
+++ b/arch/blackfin/kernel/bfin_dma.c
@@ -19,7 +19,7 @@
 #include <asm/blackfin.h>
 #include <asm/cacheflush.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/early_printk.h>
 
 /*
diff --git a/arch/blackfin/kernel/kgdb_test.c b/arch/blackfin/kernel/kgdb_test.c
index 18ab004..b8b785d 100644
--- a/arch/blackfin/kernel/kgdb_test.c
+++ b/arch/blackfin/kernel/kgdb_test.c
@@ -12,7 +12,7 @@
 #include <linux/proc_fs.h>
 
 #include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/blackfin.h>
 
diff --git a/arch/blackfin/kernel/module.c b/arch/blackfin/kernel/module.c
index 4489efc..0188c93 100644
--- a/arch/blackfin/kernel/module.c
+++ b/arch/blackfin/kernel/module.c
@@ -14,7 +14,7 @@
 #include <linux/kernel.h>
 #include <asm/dma.h>
 #include <asm/cacheflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Transfer the section to the L1 memory */
 int
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 6355e97..6a9524a 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -475,7 +475,7 @@ static int __init bfin_pmu_init(void)
 
 	ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	if (!ret)
-		cpuhp_setup_state(CPUHP_PERF_BFIN, "PERF_BFIN",
+		cpuhp_setup_state(CPUHP_PERF_BFIN,"perf/bfin:starting",
 				  bfin_pmu_prepare_cpu, NULL);
 	return ret;
 }
diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c
index fb9e95f..0e9fcf8 100644
--- a/arch/blackfin/kernel/time-ts.c
+++ b/arch/blackfin/kernel/time-ts.c
@@ -26,7 +26,7 @@
 
 #if defined(CONFIG_CYCLES_CLOCKSOURCE)
 
-static notrace cycle_t bfin_read_cycles(struct clocksource *cs)
+static notrace u64 bfin_read_cycles(struct clocksource *cs)
 {
 #ifdef CONFIG_CPU_FREQ
 	return __bfin_cycles_off + (get_cycles() << __bfin_cycles_mod);
@@ -80,7 +80,7 @@ void __init setup_gptimer0(void)
 	enable_gptimers(TIMER0bit);
 }
 
-static cycle_t bfin_read_gptimer0(struct clocksource *cs)
+static u64 bfin_read_gptimer0(struct clocksource *cs)
 {
 	return bfin_read_TIMER0_COUNTER();
 }
diff --git a/arch/c6x/kernel/time.c b/arch/c6x/kernel/time.c
index 04845aa..6a8e00a 100644
--- a/arch/c6x/kernel/time.c
+++ b/arch/c6x/kernel/time.c
@@ -26,7 +26,7 @@
 static u32 sched_clock_multiplier;
 #define SCHED_CLOCK_SHIFT 16
 
-static cycle_t tsc_read(struct clocksource *cs)
+static u64 tsc_read(struct clocksource *cs)
 {
 	return get_cycles();
 }
diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c
index 63f5560..4cc72b0 100644
--- a/arch/c6x/mm/init.c
+++ b/arch/c6x/mm/init.c
@@ -18,7 +18,7 @@
 #include <linux/initrd.h>
 
 #include <asm/sections.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * ZERO_PAGE is a special page that is used for zero-initialized
diff --git a/arch/cris/arch-v10/drivers/eeprom.c b/arch/cris/arch-v10/drivers/eeprom.c
index c903a9e..33558d2 100644
--- a/arch/cris/arch-v10/drivers/eeprom.c
+++ b/arch/cris/arch-v10/drivers/eeprom.c
@@ -29,7 +29,7 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "i2c.h"
 
 #define D(x)
diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c
index 0f39832..9ac75d6 100644
--- a/arch/cris/arch-v10/drivers/sync_serial.c
+++ b/arch/cris/arch-v10/drivers/sync_serial.c
@@ -27,7 +27,7 @@
 #include <asm/dma.h>
 #include <asm/io.h>
 #include <arch/svinto.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sync_serial.h>
 #include <arch/io_interface_mux.h>
 
diff --git a/arch/cris/arch-v10/kernel/ptrace.c b/arch/cris/arch-v10/kernel/ptrace.c
index bfddfb9..eca94c7 100644
--- a/arch/cris/arch-v10/kernel/ptrace.c
+++ b/arch/cris/arch-v10/kernel/ptrace.c
@@ -12,7 +12,7 @@
 #include <linux/signal.h>
 #include <linux/security.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
diff --git a/arch/cris/arch-v10/kernel/signal.c b/arch/cris/arch-v10/kernel/signal.c
index 7122d97..db30c98e 100644
--- a/arch/cris/arch-v10/kernel/signal.c
+++ b/arch/cris/arch-v10/kernel/signal.c
@@ -26,7 +26,7 @@
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <arch/system.h>
 
 #define DEBUG_SIG 0
diff --git a/arch/cris/arch-v10/kernel/traps.c b/arch/cris/arch-v10/kernel/traps.c
index 7001bed..96d004f 100644
--- a/arch/cris/arch-v10/kernel/traps.c
+++ b/arch/cris/arch-v10/kernel/traps.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <arch/sv_addr_ag.h>
 #include <arch/system.h>
 
diff --git a/arch/cris/arch-v10/lib/usercopy.c b/arch/cris/arch-v10/lib/usercopy.c
index b964c66..1ba7cc0 100644
--- a/arch/cris/arch-v10/lib/usercopy.c
+++ b/arch/cris/arch-v10/lib/usercopy.c
@@ -8,7 +8,7 @@
  * Pieces used from memcpy, originally by Kenny Ranerup long time ago.
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Asm:s have been tweaked (within the domain of correctness) to give
    satisfactory results for "gcc version 2.96 20000427 (experimental)".
diff --git a/arch/cris/arch-v10/mm/fault.c b/arch/cris/arch-v10/mm/fault.c
index ed60588..75210cb 100644
--- a/arch/cris/arch-v10/mm/fault.c
+++ b/arch/cris/arch-v10/mm/fault.c
@@ -11,7 +11,7 @@
  */
 
 #include <linux/mm.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <arch/svinto.h>
 #include <asm/mmu_context.h>
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index 0068fd4..ae6903d 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -14,7 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/stddef.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
 
diff --git a/arch/cris/arch-v32/kernel/ptrace.c b/arch/cris/arch-v32/kernel/ptrace.c
index fe1f9cf7b..c366bc0 100644
--- a/arch/cris/arch-v32/kernel/ptrace.c
+++ b/arch/cris/arch-v32/kernel/ptrace.c
@@ -12,7 +12,7 @@
 #include <linux/signal.h>
 #include <linux/security.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
diff --git a/arch/cris/arch-v32/kernel/signal.c b/arch/cris/arch-v32/kernel/signal.c
index 150d1d7..816bf2c 100644
--- a/arch/cris/arch-v32/kernel/signal.c
+++ b/arch/cris/arch-v32/kernel/signal.c
@@ -18,7 +18,7 @@
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <arch/hwregs/cpu_vect.h>
 
 extern unsigned long cris_signal_return_page;
diff --git a/arch/cris/arch-v32/kernel/traps.c b/arch/cris/arch-v32/kernel/traps.c
index 8bbe09c..d79666a 100644
--- a/arch/cris/arch-v32/kernel/traps.c
+++ b/arch/cris/arch-v32/kernel/traps.c
@@ -4,7 +4,7 @@
 
 #include <linux/ptrace.h>
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <hwregs/supp_reg.h>
 #include <hwregs/intr_vect_defs.h>
 #include <asm/irq.h>
diff --git a/arch/cris/arch-v32/lib/usercopy.c b/arch/cris/arch-v32/lib/usercopy.c
index f0f335d..05e58da 100644
--- a/arch/cris/arch-v32/lib/usercopy.c
+++ b/arch/cris/arch-v32/lib/usercopy.c
@@ -8,7 +8,7 @@
  * Pieces used from memcpy, originally by Kenny Ranerup long time ago.
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Asm:s have been tweaked (within the domain of correctness) to give
    satisfactory results for "gcc version 3.2.1 Axis release R53/1.53-v32".
diff --git a/arch/cris/kernel/crisksyms.c b/arch/cris/kernel/crisksyms.c
index 31b4bd2..3166d1c 100644
--- a/arch/cris/kernel/crisksyms.c
+++ b/arch/cris/kernel/crisksyms.c
@@ -10,7 +10,7 @@
 #include <linux/tty.h>
 
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/checksum.h>
 #include <asm/io.h>
 #include <asm/delay.h>
diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c
index b78498e..50a7dd4 100644
--- a/arch/cris/kernel/process.c
+++ b/arch/cris/kernel/process.c
@@ -14,7 +14,7 @@
 
 #include <linux/atomic.h>
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
diff --git a/arch/cris/kernel/profile.c b/arch/cris/kernel/profile.c
index cd9f15b..ad56b37 100644
--- a/arch/cris/kernel/profile.c
+++ b/arch/cris/kernel/profile.c
@@ -5,7 +5,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define SAMPLE_BUFFER_SIZE 8192
 
diff --git a/arch/cris/kernel/ptrace.c b/arch/cris/kernel/ptrace.c
index fd3427e..806b7640 100644
--- a/arch/cris/kernel/ptrace.c
+++ b/arch/cris/kernel/ptrace.c
@@ -18,7 +18,7 @@
 #include <linux/user.h>
 #include <linux/tracehook.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
diff --git a/arch/cris/kernel/sys_cris.c b/arch/cris/kernel/sys_cris.c
index 7aa036e..8febb03 100644
--- a/arch/cris/kernel/sys_cris.c
+++ b/arch/cris/kernel/sys_cris.c
@@ -23,7 +23,7 @@
 #include <linux/file.h>
 #include <linux/ipc.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/segment.h>
 
 asmlinkage long
diff --git a/arch/cris/kernel/traps.c b/arch/cris/kernel/traps.c
index da4c724..b2a312a 100644
--- a/arch/cris/kernel/traps.c
+++ b/arch/cris/kernel/traps.c
@@ -20,7 +20,7 @@
 #endif
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <arch/system.h>
 
 extern void arch_enable_nmi(void);
diff --git a/arch/frv/include/asm/futex.h b/arch/frv/include/asm/futex.h
index 4bea27f..2e1da71 100644
--- a/arch/frv/include/asm/futex.h
+++ b/arch/frv/include/asm/futex.h
@@ -5,7 +5,7 @@
 
 #include <linux/futex.h>
 #include <asm/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr);
 
diff --git a/arch/frv/kernel/irq.c b/arch/frv/kernel/irq.c
index 2239346..93513e4 100644
--- a/arch/frv/kernel/irq.c
+++ b/arch/frv/kernel/irq.c
@@ -28,7 +28,7 @@
 #include <linux/atomic.h>
 #include <asm/io.h>
 #include <asm/smp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/delay.h>
 #include <asm/irq.h>
diff --git a/arch/frv/kernel/pm-mb93093.c b/arch/frv/kernel/pm-mb93093.c
index eaa7b58..8358e34 100644
--- a/arch/frv/kernel/pm-mb93093.c
+++ b/arch/frv/kernel/pm-mb93093.c
@@ -17,7 +17,7 @@
 #include <linux/sysctl.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/mb86943a.h>
 
diff --git a/arch/frv/kernel/pm.c b/arch/frv/kernel/pm.c
index ac767d9..051ccec 100644
--- a/arch/frv/kernel/pm.c
+++ b/arch/frv/kernel/pm.c
@@ -19,7 +19,7 @@
 #include <linux/sysctl.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/mb86943a.h>
 
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 5d40aeb77..b306241 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -28,7 +28,7 @@
 #include <linux/rcupdate.h>
 
 #include <asm/asm-offsets.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
diff --git a/arch/frv/kernel/ptrace.c b/arch/frv/kernel/ptrace.c
index 3987ff8..4976840 100644
--- a/arch/frv/kernel/ptrace.c
+++ b/arch/frv/kernel/ptrace.c
@@ -23,7 +23,7 @@
 #include <linux/elf.h>
 #include <linux/tracehook.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c
index 82d5e91..bf6e07a 100644
--- a/arch/frv/kernel/signal.c
+++ b/arch/frv/kernel/signal.c
@@ -22,7 +22,7 @@
 #include <linux/personality.h>
 #include <linux/tracehook.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 
 #define DEBUG_SIG 0
diff --git a/arch/frv/kernel/sys_frv.c b/arch/frv/kernel/sys_frv.c
index 9c49808..f80cc8b 100644
--- a/arch/frv/kernel/sys_frv.c
+++ b/arch/frv/kernel/sys_frv.c
@@ -25,7 +25,7 @@
 #include <linux/ipc.h>
 
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
 			  unsigned long prot, unsigned long flags,
diff --git a/arch/frv/kernel/sysctl.c b/arch/frv/kernel/sysctl.c
index f4dfae2..b54a649 100644
--- a/arch/frv/kernel/sysctl.c
+++ b/arch/frv/kernel/sysctl.c
@@ -12,7 +12,7 @@
 #include <linux/sysctl.h>
 #include <linux/proc_fs.h>
 #include <linux/init.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static const char frv_cache_wback[] = "wback";
 static const char frv_cache_wthru[] = "wthru";
diff --git a/arch/frv/kernel/traps.c b/arch/frv/kernel/traps.c
index a6d105d..31221fb 100644
--- a/arch/frv/kernel/traps.c
+++ b/arch/frv/kernel/traps.c
@@ -23,7 +23,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/setup.h>
 #include <asm/fpu.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/siginfo.h>
 #include <asm/unaligned.h>
diff --git a/arch/frv/kernel/uaccess.c b/arch/frv/kernel/uaccess.c
index 374f88d..8b360b4 100644
--- a/arch/frv/kernel/uaccess.c
+++ b/arch/frv/kernel/uaccess.c
@@ -11,7 +11,7 @@
 
 #include <linux/mm.h>
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*****************************************************************************/
 /*
diff --git a/arch/frv/mm/dma-alloc.c b/arch/frv/mm/dma-alloc.c
index 7a73aae..e701aa9 100644
--- a/arch/frv/mm/dma-alloc.c
+++ b/arch/frv/mm/dma-alloc.c
@@ -44,7 +44,7 @@
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/smp.h>
 
 static int map_page(unsigned long va, unsigned long pa, pgprot_t prot)
diff --git a/arch/frv/mm/extable.c b/arch/frv/mm/extable.c
index 8863d6c..9a641c1 100644
--- a/arch/frv/mm/extable.c
+++ b/arch/frv/mm/extable.c
@@ -4,7 +4,7 @@
 
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern const void __memset_end, __memset_user_error_lr, __memset_user_error_handler;
 extern const void __memcpy_end, __memcpy_user_error_lr, __memcpy_user_error_handler;
diff --git a/arch/h8300/boot/compressed/misc.c b/arch/h8300/boot/compressed/misc.c
index 9f64fe8..a947dbb 100644
--- a/arch/h8300/boot/compressed/misc.c
+++ b/arch/h8300/boot/compressed/misc.c
@@ -9,7 +9,7 @@
  * Adapted for h8300 by Yoshinori Sato 2006
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * gzip declarations
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index dee4125..891974a 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -38,7 +38,7 @@
 #include <linux/slab.h>
 #include <linux/rcupdate.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/traps.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
index 7138303..d784f71 100644
--- a/arch/h8300/kernel/signal.c
+++ b/arch/h8300/kernel/signal.c
@@ -41,7 +41,7 @@
 #include <linux/tracehook.h>
 
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/traps.h>
 #include <asm/ucontext.h>
diff --git a/arch/hexagon/kernel/hexagon_ksyms.c b/arch/hexagon/kernel/hexagon_ksyms.c
index c041d8e..af9dec4 100644
--- a/arch/hexagon/kernel/hexagon_ksyms.c
+++ b/arch/hexagon/kernel/hexagon_ksyms.c
@@ -21,7 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <asm/hexagon_vm.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Additional functions */
 EXPORT_SYMBOL(__clear_user_hexagon);
diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c
index b039a62..c6b22b9 100644
--- a/arch/hexagon/kernel/signal.c
+++ b/arch/hexagon/kernel/signal.c
@@ -24,7 +24,7 @@
 #include <asm/registers.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ucontext.h>
 #include <asm/cacheflush.h>
 #include <asm/signal.h>
diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c
index a6a1d1f..ff4e9bf 100644
--- a/arch/hexagon/kernel/time.c
+++ b/arch/hexagon/kernel/time.c
@@ -72,9 +72,9 @@ struct adsp_hw_timer_struct {
 /*  Look for "TCX0" for related constants.  */
 static __iomem struct adsp_hw_timer_struct *rtos_timer;
 
-static cycle_t timer_get_cycles(struct clocksource *cs)
+static u64 timer_get_cycles(struct clocksource *cs)
 {
-	return (cycle_t) __vmgettime();
+	return (u64) __vmgettime();
 }
 
 static struct clocksource hexagon_clocksource = {
diff --git a/arch/hexagon/mm/uaccess.c b/arch/hexagon/mm/uaccess.c
index 3412726..ec90afd 100644
--- a/arch/hexagon/mm/uaccess.c
+++ b/arch/hexagon/mm/uaccess.c
@@ -23,7 +23,7 @@
  * we implement here as subroutines.
  */
 #include <linux/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 
 /*
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index bd7c251..de863d6 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -26,7 +26,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mm.h>
 #include <linux/signal.h>
 #include <linux/module.h>
diff --git a/arch/ia64/kernel/brl_emu.c b/arch/ia64/kernel/brl_emu.c
index 0b286ca..8682df6 100644
--- a/arch/ia64/kernel/brl_emu.c
+++ b/arch/ia64/kernel/brl_emu.c
@@ -9,7 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>
 
 extern char ia64_set_b1, ia64_set_b2, ia64_set_b3, ia64_set_b4, ia64_set_b5;
diff --git a/arch/ia64/kernel/crash_dump.c b/arch/ia64/kernel/crash_dump.c
index c8c9298..9c12b79 100644
--- a/arch/ia64/kernel/crash_dump.c
+++ b/arch/ia64/kernel/crash_dump.c
@@ -11,7 +11,7 @@
 #include <linux/crash_dump.h>
 
 #include <asm/page.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /**
  * copy_oldmem_page - copy one page from "oldmem"
diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c
index 5fa3848..ee1a4af 100644
--- a/arch/ia64/kernel/cyclone.c
+++ b/arch/ia64/kernel/cyclone.c
@@ -21,9 +21,9 @@ void __init cyclone_setup(void)
 
 static void __iomem *cyclone_mc;
 
-static cycle_t read_cyclone(struct clocksource *cs)
+static u64 read_cyclone(struct clocksource *cs)
 {
-	return (cycle_t)readq((void __iomem *)cyclone_mc);
+	return (u64)readq((void __iomem *)cyclone_mc);
 }
 
 static struct clocksource clocksource_cyclone = {
diff --git a/arch/ia64/kernel/fsyscall_gtod_data.h b/arch/ia64/kernel/fsyscall_gtod_data.h
index 146b15b..dcc5149 100644
--- a/arch/ia64/kernel/fsyscall_gtod_data.h
+++ b/arch/ia64/kernel/fsyscall_gtod_data.h
@@ -9,15 +9,15 @@ struct fsyscall_gtod_data_t {
 	seqcount_t	seq;
 	struct timespec	wall_time;
 	struct timespec monotonic_time;
-	cycle_t		clk_mask;
+	u64		clk_mask;
 	u32		clk_mult;
 	u32		clk_shift;
 	void		*clk_fsys_mmio;
-	cycle_t		clk_cycle_last;
+	u64		clk_cycle_last;
 } ____cacheline_aligned;
 
 struct itc_jitter_data_t {
 	int		itc_jitter;
-	cycle_t		itc_lastcycle;
+	u64		itc_lastcycle;
 } ____cacheline_aligned;
 
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
index 0eaa89f..fa8ee64 100644
--- a/arch/ia64/kernel/init_task.c
+++ b/arch/ia64/kernel/init_task.c
@@ -14,7 +14,7 @@
 #include <linux/init_task.h>
 #include <linux/mqueue.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index de4fc00..2ff1df7 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -17,7 +17,7 @@
  */
 
 #include <asm/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index c7c5144..45ff27e 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -33,7 +33,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/sections.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern void jprobe_inst_return(void);
 
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 2436ad5..677a868 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -50,7 +50,7 @@
 #include <asm/perfmon.h>
 #include <asm/processor.h>
 #include <asm/signal.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/delay.h>
 
 #ifdef CONFIG_PERFMON
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index aae6c4d..52deab6 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -41,7 +41,7 @@
 #include <asm/sal.h>
 #include <asm/switch_to.h>
 #include <asm/tlbflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unwind.h>
 #include <asm/user.h>
 
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 36f660d..0b1153e 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -26,7 +26,7 @@
 #include <asm/processor.h>
 #include <asm/ptrace_offsets.h>
 #include <asm/rse.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unwind.h>
 #ifdef CONFIG_PERFMON
 #include <asm/perfmon.h>
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index aaf74f3..d194d5c 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -48,7 +48,7 @@
 #include <linux/semaphore.h>
 
 #include <asm/sal.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 MODULE_AUTHOR("Jesse Barnes <jbarnes@sgi.com>");
 MODULE_DESCRIPTION("/proc interface to IA-64 SAL features");
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index b3a124d..5db52c6 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -22,7 +22,7 @@
 #include <linux/wait.h>
 
 #include <asm/intrinsics.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/rse.h>
 #include <asm/sigcontext.h>
 
diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c
index 41e33f8..a09c122 100644
--- a/arch/ia64/kernel/sys_ia64.c
+++ b/arch/ia64/kernel/sys_ia64.c
@@ -18,7 +18,7 @@
 #include <linux/hugetlb.h>
 
 #include <asm/shmparam.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 unsigned long
 arch_get_unmapped_area (struct file *filp, unsigned long addr, unsigned long len,
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 021f44a..71775b95 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -31,7 +31,7 @@
 
 #include "fsyscall_gtod_data.h"
 
-static cycle_t itc_get_cycles(struct clocksource *cs);
+static u64 itc_get_cycles(struct clocksource *cs);
 
 struct fsyscall_gtod_data_t fsyscall_gtod_data;
 
@@ -323,7 +323,7 @@ void ia64_init_itm(void)
 	}
 }
 
-static cycle_t itc_get_cycles(struct clocksource *cs)
+static u64 itc_get_cycles(struct clocksource *cs)
 {
 	unsigned long lcycle, now, ret;
 
@@ -397,7 +397,7 @@ void update_vsyscall_tz(void)
 }
 
 void update_vsyscall_old(struct timespec *wall, struct timespec *wtm,
-			 struct clocksource *c, u32 mult, cycle_t cycle_last)
+			 struct clocksource *c, u32 mult, u64 cycle_last)
 {
 	write_seqcount_begin(&fsyscall_gtod_data.seq);
 
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index 77edd68..095bfaf 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -21,7 +21,7 @@
 #include <asm/fpswa.h>
 #include <asm/intrinsics.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/setup.h>
 
 fpswa_interface_t *fpswa_interface;
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 7f0d316..9cd01c2 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -22,7 +22,7 @@
 #include <asm/intrinsics.h>
 #include <asm/processor.h>
 #include <asm/rse.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
 extern int die_if_kernel(char *str, struct pt_regs *regs, long err);
diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c
index 8f66195..9704e2c 100644
--- a/arch/ia64/kernel/unwind.c
+++ b/arch/ia64/kernel/unwind.c
@@ -41,7 +41,7 @@
 #include <asm/ptrace_offsets.h>
 #include <asm/rse.h>
 #include <asm/sections.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "entry.h"
 #include "unwind_i.h"
diff --git a/arch/ia64/lib/csum_partial_copy.c b/arch/ia64/lib/csum_partial_copy.c
index 118daf5..42f7678 100644
--- a/arch/ia64/lib/csum_partial_copy.c
+++ b/arch/ia64/lib/csum_partial_copy.c
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/string.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * XXX Fixme: those 2 inlines are meant for debugging and will go away
diff --git a/arch/ia64/mm/extable.c b/arch/ia64/mm/extable.c
index 8f70bb2..4edb816 100644
--- a/arch/ia64/mm/extable.c
+++ b/arch/ia64/mm/extable.c
@@ -5,7 +5,7 @@
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 void
 ia64_handle_exception (struct pt_regs *regs, const struct exception_table_entry *e)
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 1841ef6..bb4610f 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -31,7 +31,7 @@
 #include <asm/sal.h>
 #include <asm/sections.h>
 #include <asm/tlb.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/mca.h>
 
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index b999257..4c3b84d 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -37,7 +37,7 @@
 
 #include <asm/processor.h>
 #include <asm/topology.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sal.h>
 #include <asm/sn/io.h>
 #include <asm/sn/sn_sal.h>
diff --git a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
index 7aab87f..29cf8f8 100644
--- a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
+++ b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
@@ -9,7 +9,7 @@
 #ifdef CONFIG_PROC_FS
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sn/sn_sal.h>
 
 static int partition_id_show(struct seq_file *s, void *p)
diff --git a/arch/ia64/sn/kernel/sn2/timer.c b/arch/ia64/sn/kernel/sn2/timer.c
index abab8f9..66edc36 100644
--- a/arch/ia64/sn/kernel/sn2/timer.c
+++ b/arch/ia64/sn/kernel/sn2/timer.c
@@ -22,9 +22,9 @@
 
 extern unsigned long sn_rtc_cycles_per_second;
 
-static cycle_t read_sn2(struct clocksource *cs)
+static u64 read_sn2(struct clocksource *cs)
 {
-	return (cycle_t)readq(RTC_COUNTER_ADDR);
+	return (u64)readq(RTC_COUNTER_ADDR);
 }
 
 static struct clocksource clocksource_sn2 = {
diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c
index e35f648..32d0380 100644
--- a/arch/ia64/sn/kernel/tiocx.c
+++ b/arch/ia64/sn/kernel/tiocx.c
@@ -14,7 +14,7 @@
 #include <linux/capability.h>
 #include <linux/device.h>
 #include <linux/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sn/sn_sal.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/io.h>
diff --git a/arch/m32r/kernel/align.c b/arch/m32r/kernel/align.c
index ab871cc..ec51e5b 100644
--- a/arch/m32r/kernel/align.c
+++ b/arch/m32r/kernel/align.c
@@ -5,7 +5,7 @@
  */
 
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int get_reg(struct pt_regs *regs, int nr)
 {
diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c
index c7272b8..5537f73 100644
--- a/arch/m32r/kernel/irq.c
+++ b/arch/m32r/kernel/irq.c
@@ -19,7 +19,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * do_IRQ handles all normal device IRQs (the special
diff --git a/arch/m32r/kernel/m32r_ksyms.c b/arch/m32r/kernel/m32r_ksyms.c
index 23f26f4a..d763f0b 100644
--- a/arch/m32r/kernel/m32r_ksyms.c
+++ b/arch/m32r/kernel/m32r_ksyms.c
@@ -8,7 +8,7 @@
 #include <linux/string.h>
 
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/checksum.h>
 #include <asm/io.h>
 #include <asm/delay.h>
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index a88b1f0..e0568be 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -29,7 +29,7 @@
 #include <linux/rcupdate.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/elf.h>
 #include <asm/m32r.h>
diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c
index c145605..a68acb9 100644
--- a/arch/m32r/kernel/ptrace.c
+++ b/arch/m32r/kernel/ptrace.c
@@ -27,7 +27,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c
index 1c81e24..1ed5970 100644
--- a/arch/m32r/kernel/signal.c
+++ b/arch/m32r/kernel/signal.c
@@ -23,7 +23,7 @@
 #include <linux/tracehook.h>
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define DEBUG_SIG 0
 
diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c
index c3fdd63..f349570 100644
--- a/arch/m32r/kernel/sys_m32r.c
+++ b/arch/m32r/kernel/sys_m32r.c
@@ -22,7 +22,7 @@
 #include <linux/utsname.h>
 #include <linux/ipc.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cachectl.h>
 #include <asm/cacheflush.h>
 #include <asm/syscall.h>
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index a7a424f..c3c5fdf 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -18,7 +18,7 @@
 #include <asm/page.h>
 #include <asm/processor.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
 
diff --git a/arch/m32r/lib/csum_partial_copy.c b/arch/m32r/lib/csum_partial_copy.c
index 5596f3d..b3cd59c 100644
--- a/arch/m32r/lib/csum_partial_copy.c
+++ b/arch/m32r/lib/csum_partial_copy.c
@@ -22,7 +22,7 @@
 
 #include <net/checksum.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Copy while checksumming, otherwise like csum_partial
diff --git a/arch/m32r/lib/usercopy.c b/arch/m32r/lib/usercopy.c
index 82abd15..fd03f27 100644
--- a/arch/m32r/lib/usercopy.c
+++ b/arch/m32r/lib/usercopy.c
@@ -9,7 +9,7 @@
 #include <linux/prefetch.h>
 #include <linux/string.h>
 #include <linux/thread_info.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 unsigned long
 __generic_copy_to_user(void __user *to, const void *from, unsigned long n)
diff --git a/arch/m32r/mm/extable.c b/arch/m32r/mm/extable.c
index 1743f23..40ccf80 100644
--- a/arch/m32r/mm/extable.c
+++ b/arch/m32r/mm/extable.c
@@ -3,7 +3,7 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int fixup_exception(struct pt_regs *regs)
 {
diff --git a/arch/m32r/mm/fault-nommu.c b/arch/m32r/mm/fault-nommu.c
index 80f18cc..e22d5dd 100644
--- a/arch/m32r/mm/fault-nommu.c
+++ b/arch/m32r/mm/fault-nommu.c
@@ -22,7 +22,7 @@
 #include <linux/vt_kern.h>              /* For unblank_screen() */
 
 #include <asm/m32r.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/hardirq.h>
diff --git a/arch/m68k/68000/timers.c b/arch/m68k/68000/timers.c
index 99a9869..252455b 100644
--- a/arch/m68k/68000/timers.c
+++ b/arch/m68k/68000/timers.c
@@ -76,7 +76,7 @@ static struct irqaction m68328_timer_irq = {
 
 /***************************************************************************/
 
-static cycle_t m68328_read_clk(struct clocksource *cs)
+static u64 m68328_read_clk(struct clocksource *cs)
 {
 	unsigned long flags;
 	u32 cycles;
diff --git a/arch/m68k/bvme6000/rtc.c b/arch/m68k/bvme6000/rtc.c
index f7984f4..d53c9b3 100644
--- a/arch/m68k/bvme6000/rtc.c
+++ b/arch/m68k/bvme6000/rtc.c
@@ -20,7 +20,7 @@
 #include <asm/bvme6000hw.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/setup.h>
 
 /*
diff --git a/arch/m68k/coldfire/dma_timer.c b/arch/m68k/coldfire/dma_timer.c
index 235ad57..8273eea 100644
--- a/arch/m68k/coldfire/dma_timer.c
+++ b/arch/m68k/coldfire/dma_timer.c
@@ -34,7 +34,7 @@
 #define DMA_DTMR_CLK_DIV_16	(2 << 1)
 #define DMA_DTMR_ENABLE		(1 << 0)
 
-static cycle_t cf_dt_get_cycles(struct clocksource *cs)
+static u64 cf_dt_get_cycles(struct clocksource *cs)
 {
 	return __raw_readl(DTCN0);
 }
diff --git a/arch/m68k/coldfire/pit.c b/arch/m68k/coldfire/pit.c
index d86a9ff..175553d 100644
--- a/arch/m68k/coldfire/pit.c
+++ b/arch/m68k/coldfire/pit.c
@@ -118,7 +118,7 @@ static struct irqaction pit_irq = {
 
 /***************************************************************************/
 
-static cycle_t pit_read_clk(struct clocksource *cs)
+static u64 pit_read_clk(struct clocksource *cs)
 {
 	unsigned long flags;
 	u32 cycles;
diff --git a/arch/m68k/coldfire/sltimers.c b/arch/m68k/coldfire/sltimers.c
index 831a08c..3292c0d 100644
--- a/arch/m68k/coldfire/sltimers.c
+++ b/arch/m68k/coldfire/sltimers.c
@@ -97,7 +97,7 @@ static struct irqaction mcfslt_timer_irq = {
 	.handler = mcfslt_tick,
 };
 
-static cycle_t mcfslt_read_clk(struct clocksource *cs)
+static u64 mcfslt_read_clk(struct clocksource *cs)
 {
 	unsigned long flags;
 	u32 cycles, scnt;
diff --git a/arch/m68k/coldfire/timers.c b/arch/m68k/coldfire/timers.c
index cd496a2..2dc7a58 100644
--- a/arch/m68k/coldfire/timers.c
+++ b/arch/m68k/coldfire/timers.c
@@ -89,7 +89,7 @@ static struct irqaction mcftmr_timer_irq = {
 
 /***************************************************************************/
 
-static cycle_t mcftmr_read_clk(struct clocksource *cs)
+static u64 mcftmr_read_clk(struct clocksource *cs)
 {
 	unsigned long flags;
 	u32 cycles;
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 4ba1ae7..aaf28f8 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -27,7 +27,7 @@
 #include <linux/mqueue.h>
 #include <linux/rcupdate.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/traps.h>
 #include <asm/machdep.h>
 #include <asm/setup.h>
diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c
index 1bc10e6..9cd86d7 100644
--- a/arch/m68k/kernel/ptrace.c
+++ b/arch/m68k/kernel/ptrace.c
@@ -20,7 +20,7 @@
 #include <linux/signal.h>
 #include <linux/tracehook.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 58507ed..8ead291 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -46,7 +46,7 @@
 #include <linux/tracehook.h>
 
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/traps.h>
 #include <asm/ucontext.h>
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index 9aa01ad..98a2daa 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -22,7 +22,7 @@
 #include <linux/ipc.h>
 
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cachectl.h>
 #include <asm/traps.h>
 #include <asm/page.h>
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index 6c9ca24..558f384 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -32,7 +32,7 @@
 
 #include <asm/setup.h>
 #include <asm/fpu.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/traps.h>
 #include <asm/pgalloc.h>
 #include <asm/machdep.h>
diff --git a/arch/m68k/lib/uaccess.c b/arch/m68k/lib/uaccess.c
index 35d1442..a76b73a 100644
--- a/arch/m68k/lib/uaccess.c
+++ b/arch/m68k/lib/uaccess.c
@@ -5,7 +5,7 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 unsigned long __generic_copy_from_user(void *to, const void __user *from,
 				       unsigned long n)
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index 0fb54a9..c6d351f 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -16,7 +16,7 @@
 #include <linux/cuda.h>
 #include <linux/pmu.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/segment.h>
 #include <asm/setup.h>
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index b09a3cb..9c1e656 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -20,7 +20,7 @@
 #include <linux/gfp.h>
 
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/traps.h>
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index 8f37fdd..7cb72db 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -21,7 +21,7 @@
 #include <linux/gfp.h>
 
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/machdep.h>
diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c
index 269f811..b5b7d53 100644
--- a/arch/m68k/mm/sun3mmu.c
+++ b/arch/m68k/mm/sun3mmu.c
@@ -18,7 +18,7 @@
 #include <linux/bootmem.h>
 
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/machdep.h>
diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c
index 1cdc732..8f00847 100644
--- a/arch/m68k/mvme16x/rtc.c
+++ b/arch/m68k/mvme16x/rtc.c
@@ -19,7 +19,7 @@
 #include <asm/mvme16xhw.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/setup.h>
 
 /*
diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c
index 3f258e2..0f95134 100644
--- a/arch/m68k/sun3/mmu_emu.c
+++ b/arch/m68k/sun3/mmu_emu.c
@@ -18,7 +18,7 @@
 
 #include <asm/setup.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/sun3mmu.h>
diff --git a/arch/metag/kernel/irq.c b/arch/metag/kernel/irq.c
index 3074b64..c993960 100644
--- a/arch/metag/kernel/irq.c
+++ b/arch/metag/kernel/irq.c
@@ -13,7 +13,7 @@
 
 #include <asm/core_reg.h>
 #include <asm/mach/arch.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_4KSTACKS
 union irq_ctx {
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 052cba2..7e793eb 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -868,7 +868,7 @@ static int __init init_hw_perf_events(void)
 	metag_out32(0, PERF_COUNT(1));
 
 	cpuhp_setup_state(CPUHP_AP_PERF_METAG_STARTING,
-			  "AP_PERF_METAG_STARTING", metag_pmu_starting_cpu,
+			  "perf/metag:starting", metag_pmu_starting_cpu,
 			  NULL);
 
 	ret = perf_pmu_register(&pmu, metag_pmu->name, PERF_TYPE_RAW);
diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index 805ae5d..032fed7 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -38,6 +38,6 @@
 
 #endif /* __ASSEMBLY__ */
 
-#define __NR_syscalls         392
+#define __NR_syscalls         398
 
 #endif /* _ASM_MICROBLAZE_UNISTD_H */
diff --git a/arch/microblaze/include/uapi/asm/unistd.h b/arch/microblaze/include/uapi/asm/unistd.h
index a8bd3fa..d808615 100644
--- a/arch/microblaze/include/uapi/asm/unistd.h
+++ b/arch/microblaze/include/uapi/asm/unistd.h
@@ -407,5 +407,11 @@
 #define __NR_userfaultfd	389
 #define __NR_membarrier		390
 #define __NR_mlock2		391
+#define __NR_copy_file_range	392
+#define __NR_preadv2		393
+#define __NR_pwritev2		394
+#define __NR_pkey_mprotect	395
+#define __NR_pkey_alloc		396
+#define __NR_pkey_free		397
 
 #endif /* _UAPI_ASM_MICROBLAZE_UNISTD_H */
diff --git a/arch/microblaze/kernel/cpu/cpuinfo.c b/arch/microblaze/kernel/cpu/cpuinfo.c
index b70bb53..96b3f26 100644
--- a/arch/microblaze/kernel/cpu/cpuinfo.c
+++ b/arch/microblaze/kernel/cpu/cpuinfo.c
@@ -49,6 +49,8 @@ const struct cpu_ver_key cpu_ver_lookup[] = {
 	{"9.3", 0x20},
 	{"9.4", 0x21},
 	{"9.5", 0x22},
+	{"9.6", 0x23},
+	{"10.0", 0x24},
 	{NULL, 0},
 };
 
@@ -75,6 +77,10 @@ const struct family_string_key family_string_lookup[] = {
 	{"zynq7000", 0x12},
 	{"UltraScale Virtex", 0x13},
 	{"UltraScale Kintex", 0x14},
+	{"UltraScale+ Zynq", 0x15},
+	{"UltraScale+ Virtex", 0x16},
+	{"UltraScale+ Kintex", 0x17},
+	{"Spartan7", 0x18},
 	{NULL, 0},
 };
 
diff --git a/arch/microblaze/kernel/syscall_table.S b/arch/microblaze/kernel/syscall_table.S
index 6b3dd99..6841c2d 100644
--- a/arch/microblaze/kernel/syscall_table.S
+++ b/arch/microblaze/kernel/syscall_table.S
@@ -392,3 +392,9 @@
 	.long sys_userfaultfd
 	.long sys_membarrier		/* 390 */
 	.long sys_mlock2
+	.long sys_copy_file_range
+	.long sys_preadv2
+	.long sys_pwritev2
+	.long sys_pkey_mprotect		/* 395 */
+	.long sys_pkey_alloc
+	.long sys_pkey_free
diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index 5bbf38b..1d6fad5 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -190,17 +190,17 @@ static u64 xilinx_clock_read(void)
 	return read_fn(timer_baseaddr + TCR1);
 }
 
-static cycle_t xilinx_read(struct clocksource *cs)
+static u64 xilinx_read(struct clocksource *cs)
 {
 	/* reading actual value of timer 1 */
-	return (cycle_t)xilinx_clock_read();
+	return (u64)xilinx_clock_read();
 }
 
 static struct timecounter xilinx_tc = {
 	.cc = NULL,
 };
 
-static cycle_t xilinx_cc_read(const struct cyclecounter *cc)
+static u64 xilinx_cc_read(const struct cyclecounter *cc)
 {
 	return xilinx_read(NULL);
 }
@@ -259,7 +259,7 @@ static int __init xilinx_timer_init(struct device_node *timer)
 	int ret;
 
 	if (initialized)
-		return;
+		return -EINVAL;
 
 	initialized = 1;
 
diff --git a/arch/mips/alchemy/common/power.c b/arch/mips/alchemy/common/power.c
index 921ed30..303257b 100644
--- a/arch/mips/alchemy/common/power.c
+++ b/arch/mips/alchemy/common/power.c
@@ -33,7 +33,7 @@
 #include <linux/sysctl.h>
 #include <linux/jiffies.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mach-au1x00/au1000.h>
 
 /*
diff --git a/arch/mips/alchemy/common/time.c b/arch/mips/alchemy/common/time.c
index f99d3ec..e1bec5a 100644
--- a/arch/mips/alchemy/common/time.c
+++ b/arch/mips/alchemy/common/time.c
@@ -44,7 +44,7 @@
 /* 32kHz clock enabled and detected */
 #define CNTR_OK (SYS_CNTRL_E0 | SYS_CNTRL_32S)
 
-static cycle_t au1x_counter1_read(struct clocksource *cs)
+static u64 au1x_counter1_read(struct clocksource *cs)
 {
 	return alchemy_rdsys(AU1000_SYS_RTCREAD);
 }
diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c
index 23c2344..39f153f 100644
--- a/arch/mips/cavium-octeon/csrc-octeon.c
+++ b/arch/mips/cavium-octeon/csrc-octeon.c
@@ -98,7 +98,7 @@ void octeon_init_cvmcount(void)
 	local_irq_restore(flags);
 }
 
-static cycle_t octeon_cvmcount_read(struct clocksource *cs)
+static u64 octeon_cvmcount_read(struct clocksource *cs)
 {
 	return read_c0_cvmcount();
 }
diff --git a/arch/mips/dec/kn01-berr.c b/arch/mips/dec/kn01-berr.c
index 44d8a87..e9d2db4 100644
--- a/arch/mips/dec/kn01-berr.c
+++ b/arch/mips/dec/kn01-berr.c
@@ -23,7 +23,7 @@
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/dec/kn01.h>
 
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index bce1ce5..7749daf 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -18,7 +18,7 @@
 
 #include <linux/in6.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * computes the checksum of a memory block at buff, length len,
diff --git a/arch/mips/include/asm/compat-signal.h b/arch/mips/include/asm/compat-signal.h
index 64e0b934..4c61764 100644
--- a/arch/mips/include/asm/compat-signal.h
+++ b/arch/mips/include/asm/compat-signal.h
@@ -8,7 +8,7 @@
 #include <asm/signal.h>
 #include <asm/siginfo.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static inline int __copy_conv_sigset_to_user(compat_sigset_t __user *d,
 	const sigset_t *s)
diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index 667ca3c..b42b513 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -20,7 +20,7 @@
 #include <asm/cpu-features.h>
 #include <asm/cpu-type.h>
 #include <asm/mipsmtregs.h>
-#include <asm/uaccess.h> /* for segment_eq() */
+#include <linux/uaccess.h> /* for segment_eq() */
 
 extern void (*r4k_blast_dcache)(void);
 extern void (*r4k_blast_icache)(void);
diff --git a/arch/mips/include/asm/termios.h b/arch/mips/include/asm/termios.h
index 6245b68..ce2d72e 100644
--- a/arch/mips/include/asm/termios.h
+++ b/arch/mips/include/asm/termios.h
@@ -9,7 +9,7 @@
 #ifndef _ASM_TERMIOS_H
 #define _ASM_TERMIOS_H
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <uapi/asm/termios.h>
 
 /*
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index db6f5af..1900f39 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -18,7 +18,7 @@
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dma.h>
 #include <asm/jazzdma.h>
 #include <asm/pgtable.h>
diff --git a/arch/mips/jz4740/time.c b/arch/mips/jz4740/time.c
index 1f7ca2c..bcf8f8c 100644
--- a/arch/mips/jz4740/time.c
+++ b/arch/mips/jz4740/time.c
@@ -34,7 +34,7 @@
 
 static uint16_t jz4740_jiffies_per_tick;
 
-static cycle_t jz4740_clocksource_read(struct clocksource *cs)
+static u64 jz4740_clocksource_read(struct clocksource *cs)
 {
 	return jz4740_timer_get_count(TIMER_CLOCKSOURCE);
 }
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 12c7181..ae037a3 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -18,7 +18,7 @@
 #include <asm/inst.h>
 #include <asm/mips-r2-to-r6-emul.h>
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Calculate and return exception PC in case of branch delay slot
diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c
index 537eefd..aaca60d 100644
--- a/arch/mips/kernel/cevt-txx9.c
+++ b/arch/mips/kernel/cevt-txx9.c
@@ -27,7 +27,7 @@ struct txx9_clocksource {
 	struct txx9_tmr_reg __iomem *tmrptr;
 };
 
-static cycle_t txx9_cs_read(struct clocksource *cs)
+static u64 txx9_cs_read(struct clocksource *cs)
 {
 	struct txx9_clocksource *txx9_cs =
 		container_of(cs, struct txx9_clocksource, cs);
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index dd31754..07718bb 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -30,7 +30,7 @@
 #include <asm/elf.h>
 #include <asm/pgtable-bits.h>
 #include <asm/spram.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Hardware capabilities */
 unsigned int elf_hwcap __read_mostly;
diff --git a/arch/mips/kernel/crash_dump.c b/arch/mips/kernel/crash_dump.c
index 6fe7790..77ee99a 100644
--- a/arch/mips/kernel/crash_dump.c
+++ b/arch/mips/kernel/crash_dump.c
@@ -1,7 +1,7 @@
 #include <linux/highmem.h>
 #include <linux/bootmem.h>
 #include <linux/crash_dump.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/slab.h>
 
 static void *kdump_buf_page;
diff --git a/arch/mips/kernel/csrc-bcm1480.c b/arch/mips/kernel/csrc-bcm1480.c
index 7f65b53..f011261 100644
--- a/arch/mips/kernel/csrc-bcm1480.c
+++ b/arch/mips/kernel/csrc-bcm1480.c
@@ -25,9 +25,9 @@
 
 #include <asm/sibyte/sb1250.h>
 
-static cycle_t bcm1480_hpt_read(struct clocksource *cs)
+static u64 bcm1480_hpt_read(struct clocksource *cs)
 {
-	return (cycle_t) __raw_readq(IOADDR(A_SCD_ZBBUS_CYCLE_COUNT));
+	return (u64) __raw_readq(IOADDR(A_SCD_ZBBUS_CYCLE_COUNT));
 }
 
 struct clocksource bcm1480_clocksource = {
diff --git a/arch/mips/kernel/csrc-ioasic.c b/arch/mips/kernel/csrc-ioasic.c
index 722f558..f6acd1e 100644
--- a/arch/mips/kernel/csrc-ioasic.c
+++ b/arch/mips/kernel/csrc-ioasic.c
@@ -22,7 +22,7 @@
 #include <asm/dec/ioasic.h>
 #include <asm/dec/ioasic_addrs.h>
 
-static cycle_t dec_ioasic_hpt_read(struct clocksource *cs)
+static u64 dec_ioasic_hpt_read(struct clocksource *cs)
 {
 	return ioasic_read(IO_REG_FCTR);
 }
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index d76275d..eed099f 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -11,7 +11,7 @@
 
 #include <asm/time.h>
 
-static cycle_t c0_hpt_read(struct clocksource *cs)
+static u64 c0_hpt_read(struct clocksource *cs)
 {
 	return read_c0_count();
 }
diff --git a/arch/mips/kernel/csrc-sb1250.c b/arch/mips/kernel/csrc-sb1250.c
index d915652..b07b731 100644
--- a/arch/mips/kernel/csrc-sb1250.c
+++ b/arch/mips/kernel/csrc-sb1250.c
@@ -30,7 +30,7 @@
  * The HPT is free running from SB1250_HPT_VALUE down to 0 then starts over
  * again.
  */
-static inline cycle_t sb1250_hpt_get_cycles(void)
+static inline u64 sb1250_hpt_get_cycles(void)
 {
 	unsigned int count;
 	void __iomem *addr;
@@ -41,7 +41,7 @@ static inline cycle_t sb1250_hpt_get_cycles(void)
 	return SB1250_HPT_VALUE - count;
 }
 
-static cycle_t sb1250_hpt_read(struct clocksource *cs)
+static u64 sb1250_hpt_read(struct clocksource *cs)
 {
 	return sb1250_hpt_get_cycles();
 }
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index f25f7ea..f8f5836 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -23,7 +23,7 @@
 #include <linux/ftrace.h>
 
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c
index de63d36..1f4bd22 100644
--- a/arch/mips/kernel/kgdb.c
+++ b/arch/mips/kernel/kgdb.c
@@ -32,7 +32,7 @@
 #include <asm/cacheflush.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static struct hard_trap_info {
 	unsigned char tt;	/* Trap type code for MIPS R3xxx and R4xxx */
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 50fb625..0352f74 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -38,7 +38,7 @@
 
 #include <asm/compat-signal.h>
 #include <asm/sim.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/mman.h>
 
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 789d7bf..a12904e 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -11,7 +11,7 @@
 #include <linux/sched.h>
 #include <linux/security.h>
 #include <linux/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * CPU mask used to set process affinity for MT VPEs/TCs with FPUs
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index bd09853..ef2ca28 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -29,7 +29,7 @@
 #include <asm/local.h>
 #include <asm/mipsregs.h>
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_64BIT
 #define ADDIU	"daddiu "
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index e2b6ab7..93aeec7 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -12,7 +12,7 @@
 #include <linux/export.h>
 #include <asm/checksum.h>
 #include <linux/mm.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ftrace.h>
 #include <asm/fpu.h>
 #include <asm/msa.h>
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index 7cf653e..5f928c3 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -713,7 +713,7 @@ static int __init cps_pm_init(void)
 		pr_warn("pm-cps: no CPC, clock & power gating unavailable\n");
 	}
 
-	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PM_CPS_CPU_ONLINE",
+	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mips/cps_pm:online",
 				 cps_pm_online_cpu, NULL);
 }
 arch_initcall(cps_pm_init);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 9514e5f..5142b1d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -38,7 +38,7 @@
 #include <asm/mipsregs.h>
 #include <asm/processor.h>
 #include <asm/reg.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/elf.h>
 #include <asm/isadep.h>
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index a92994d..c8ba260 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -41,7 +41,7 @@
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/syscall.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/bootinfo.h>
 #include <asm/reg.h>
 
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 5fcbdcd..4f09985 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -32,7 +32,7 @@
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/reg.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/bootinfo.h>
 
 /*
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 97b7c51..84165f2 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -16,7 +16,7 @@
 
 #include <asm/compat.h>
 #include <asm/compat-signal.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 #include "signal-common.h"
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index a7bc384..b672ceb 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -33,7 +33,7 @@
 #include <asm/cacheflush.h>
 #include <asm/compat-signal.h>
 #include <asm/sim.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ucontext.h>
 #include <asm/fpu.h>
 #include <asm/cpu-features.h>
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 53a7ef9..833f822 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -36,7 +36,7 @@
 #include <asm/sim.h>
 #include <asm/shmparam.h>
 #include <asm/sysmips.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/switch_to.h>
 
 /*
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 3905003..6c7f9d7 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -61,7 +61,7 @@
 #include <asm/siginfo.h>
 #include <asm/tlbdebug.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/watch.h>
 #include <asm/mmu_context.h>
 #include <asm/types.h>
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index f1c308d..7ed9835 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -89,7 +89,7 @@
 #include <asm/fpu.h>
 #include <asm/fpu_emulator.h>
 #include <asm/inst.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define STR(x)	__STR(x)
 #define __STR(x)  #x
diff --git a/arch/mips/loongson32/common/time.c b/arch/mips/loongson32/common/time.c
index ff224f0..e6f972d 100644
--- a/arch/mips/loongson32/common/time.c
+++ b/arch/mips/loongson32/common/time.c
@@ -63,7 +63,7 @@ void __init ls1x_pwmtimer_init(void)
 	ls1x_pwmtimer_restart();
 }
 
-static cycle_t ls1x_clocksource_read(struct clocksource *cs)
+static u64 ls1x_clocksource_read(struct clocksource *cs)
 {
 	unsigned long flags;
 	int count;
@@ -107,7 +107,7 @@ static cycle_t ls1x_clocksource_read(struct clocksource *cs)
 
 	raw_spin_unlock_irqrestore(&ls1x_timer_lock, flags);
 
-	return (cycle_t) (jifs * ls1x_jiffies_per_tick) + count;
+	return (u64) (jifs * ls1x_jiffies_per_tick) + count;
 }
 
 static struct clocksource ls1x_clocksource = {
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
index da77d41..9edfa55 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
@@ -144,7 +144,7 @@ void __init setup_mfgpt0_timer(void)
  * to just read by itself. So use jiffies to emulate a free
  * running counter:
  */
-static cycle_t mfgpt_read(struct clocksource *cs)
+static u64 mfgpt_read(struct clocksource *cs)
 {
 	unsigned long flags;
 	int count;
@@ -188,7 +188,7 @@ static cycle_t mfgpt_read(struct clocksource *cs)
 
 	raw_spin_unlock_irqrestore(&mfgpt_lock, flags);
 
-	return (cycle_t) (jifs * COMPARE) + count;
+	return (u64) (jifs * COMPARE) + count;
 }
 
 static struct clocksource clocksource_mfgpt = {
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c
index 4788bea..24afe36 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/loongson-3/hpet.c
@@ -248,9 +248,9 @@ void __init setup_hpet_timer(void)
 	pr_info("hpet clock event device register\n");
 }
 
-static cycle_t hpet_read_counter(struct clocksource *cs)
+static u64 hpet_read_counter(struct clocksource *cs)
 {
-	return (cycle_t)hpet_read(HPET_COUNTER);
+	return (u64)hpet_read(HPET_COUNTER);
 }
 
 static void hpet_suspend(struct clocksource *cs)
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index f8b7bf8..a298ac9 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -42,7 +42,7 @@
 #include <asm/inst.h>
 #include <asm/ptrace.h>
 #include <asm/signal.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/cpu-info.h>
 #include <asm/processor.h>
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index 4a094f7..c4469ff 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -6,7 +6,7 @@
 #include <asm/fpu_emulator.h>
 #include <asm/inst.h>
 #include <asm/mipsregs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /**
  * struct emuframe - The 'emulation' frame structure
diff --git a/arch/mips/mm/extable.c b/arch/mips/mm/extable.c
index e474fa2..81bc8a3 100644
--- a/arch/mips/mm/extable.c
+++ b/arch/mips/mm/extable.c
@@ -8,7 +8,7 @@
 #include <linux/extable.h>
 #include <linux/spinlock.h>
 #include <asm/branch.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int fixup_exception(struct pt_regs *regs)
 {
diff --git a/arch/mips/mm/sc-debugfs.c b/arch/mips/mm/sc-debugfs.c
index 01f1154..7e945e3 100644
--- a/arch/mips/mm/sc-debugfs.c
+++ b/arch/mips/mm/sc-debugfs.c
@@ -10,7 +10,7 @@
 
 #include <asm/bcache.h>
 #include <asm/debug.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/debugfs.h>
 #include <linux/init.h>
 
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 7407da0..1829a90 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -75,7 +75,7 @@ static void __init estimate_frequencies(void)
 	unsigned int count, start;
 	unsigned char secs1, secs2, ctrl;
 	int secs;
-	cycle_t giccount = 0, gicstart = 0;
+	u64 giccount = 0, gicstart = 0;
 
 #if defined(CONFIG_KVM_GUEST) && CONFIG_KVM_GUEST_TIMER_FREQ
 	mips_hpt_frequency = CONFIG_KVM_GUEST_TIMER_FREQ * 1000000;
diff --git a/arch/mips/netlogic/common/time.c b/arch/mips/netlogic/common/time.c
index 5873c83..cbbf0d4 100644
--- a/arch/mips/netlogic/common/time.c
+++ b/arch/mips/netlogic/common/time.c
@@ -59,14 +59,14 @@ unsigned int get_c0_compare_int(void)
 	return IRQ_TIMER;
 }
 
-static cycle_t nlm_get_pic_timer(struct clocksource *cs)
+static u64 nlm_get_pic_timer(struct clocksource *cs)
 {
 	uint64_t picbase = nlm_get_node(0)->picbase;
 
 	return ~nlm_pic_read_timer(picbase, PIC_CLOCK_TIMER);
 }
 
-static cycle_t nlm_get_pic_timer32(struct clocksource *cs)
+static u64 nlm_get_pic_timer32(struct clocksource *cs)
 {
 	uint64_t picbase = nlm_get_node(0)->picbase;
 
diff --git a/arch/mips/oprofile/op_model_loongson3.c b/arch/mips/oprofile/op_model_loongson3.c
index 85f3ee4..436b1fc 100644
--- a/arch/mips/oprofile/op_model_loongson3.c
+++ b/arch/mips/oprofile/op_model_loongson3.c
@@ -11,7 +11,7 @@
 #include <linux/oprofile.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <irq.h>
 #include <loongson.h>
 #include "op_impl.h"
@@ -186,7 +186,7 @@ static int __init loongson3_init(void)
 {
 	on_each_cpu(reset_counters, NULL, 1);
 	cpuhp_setup_state_nocalls(CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
-				  "AP_MIPS_OP_LOONGSON3_STARTING",
+				  "mips/oprofile/loongson3:starting",
 				  loongson3_starting_cpu, loongson3_dying_cpu);
 	save_perf_irq = perf_irq;
 	perf_irq = loongson3_perfcount_handler;
diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index 712cc0f..9960a83 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -19,7 +19,7 @@
 #include <asm/sgi/ioc.h>
 #include <asm/sgi/ip22.h>
 #include <asm/r4kcache.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/bootinfo.h>
 
 static unsigned int count_be_is_fixup;
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index 692778d..2e0edb3 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -19,7 +19,7 @@
 #include <asm/sn/sn0/hub.h>
 #include <asm/tlbdebug.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static void dump_hub_information(unsigned long errst0, unsigned long errst1)
 {
diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c
index 42d6cb9..695c51b 100644
--- a/arch/mips/sgi-ip27/ip27-timer.c
+++ b/arch/mips/sgi-ip27/ip27-timer.c
@@ -140,7 +140,7 @@ static void __init hub_rt_clock_event_global_init(void)
 	setup_irq(irq, &hub_rt_irqaction);
 }
 
-static cycle_t hub_rt_read(struct clocksource *cs)
+static u64 hub_rt_read(struct clocksource *cs)
 {
 	return REMOTE_HUB_L(cputonasid(0), PI_RT_COUNT);
 }
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index afc1cad..ba8f46d 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -11,7 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/addrspace.h>
 #include <asm/ptrace.h>
 #include <asm/tlbdebug.h>
diff --git a/arch/mips/sibyte/common/sb_tbprof.c b/arch/mips/sibyte/common/sb_tbprof.c
index 059e28c..99c720b 100644
--- a/arch/mips/sibyte/common/sb_tbprof.c
+++ b/arch/mips/sibyte/common/sb_tbprof.c
@@ -54,7 +54,7 @@
 #define K_INT_PERF_CNT K_BCM1480_INT_PERF_CNT
 #endif
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define SBPROF_TB_MAJOR 240
 
diff --git a/arch/mn10300/kernel/csrc-mn10300.c b/arch/mn10300/kernel/csrc-mn10300.c
index 45644cf..6b74df3 100644
--- a/arch/mn10300/kernel/csrc-mn10300.c
+++ b/arch/mn10300/kernel/csrc-mn10300.c
@@ -13,7 +13,7 @@
 #include <asm/timex.h>
 #include "internal.h"
 
-static cycle_t mn10300_read(struct clocksource *cs)
+static u64 mn10300_read(struct clocksource *cs)
 {
 	return read_timestamp_counter();
 }
diff --git a/arch/mn10300/kernel/fpu.c b/arch/mn10300/kernel/fpu.c
index 064fa19..2578b7a 100644
--- a/arch/mn10300/kernel/fpu.c
+++ b/arch/mn10300/kernel/fpu.c
@@ -8,7 +8,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the Licence, or (at your option) any later version.
  */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fpu.h>
 #include <asm/elf.h>
 #include <asm/exceptions.h>
diff --git a/arch/mn10300/kernel/mn10300_ksyms.c b/arch/mn10300/kernel/mn10300_ksyms.c
index f9eb975..ec6c4f8 100644
--- a/arch/mn10300/kernel/mn10300_ksyms.c
+++ b/arch/mn10300/kernel/mn10300_ksyms.c
@@ -9,7 +9,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 
 
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index cbede4e..e5def22 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -26,7 +26,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/rcupdate.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/processor.h>
diff --git a/arch/mn10300/kernel/ptrace.c b/arch/mn10300/kernel/ptrace.c
index 5bd5851..976020f 100644
--- a/arch/mn10300/kernel/ptrace.c
+++ b/arch/mn10300/kernel/ptrace.c
@@ -19,7 +19,7 @@
 #include <linux/regset.h>
 #include <linux/elf.h>
 #include <linux/tracehook.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/cacheflush.h>
diff --git a/arch/mn10300/kernel/setup.c b/arch/mn10300/kernel/setup.c
index 2ad7f32..1b3d80d 100644
--- a/arch/mn10300/kernel/setup.c
+++ b/arch/mn10300/kernel/setup.c
@@ -25,7 +25,7 @@
 #include <linux/cpu.h>
 #include <asm/processor.h>
 #include <linux/console.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/setup.h>
 #include <asm/io.h>
 #include <asm/smp.h>
diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c
index cd8cb1d..2f3cb57 100644
--- a/arch/mn10300/kernel/signal.c
+++ b/arch/mn10300/kernel/signal.c
@@ -25,7 +25,7 @@
 #include <linux/tracehook.h>
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fpu.h>
 #include "sigframe.h"
 
diff --git a/arch/mn10300/kernel/sys_mn10300.c b/arch/mn10300/kernel/sys_mn10300.c
index 815f135..f999981 100644
--- a/arch/mn10300/kernel/sys_mn10300.c
+++ b/arch/mn10300/kernel/sys_mn10300.c
@@ -21,7 +21,7 @@
 #include <linux/file.h>
 #include <linux/tty.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 asmlinkage long old_mmap(unsigned long addr, unsigned long len,
 			 unsigned long prot, unsigned long flags,
diff --git a/arch/mn10300/lib/checksum.c b/arch/mn10300/lib/checksum.c
index b6580f5..0f56915 100644
--- a/arch/mn10300/lib/checksum.c
+++ b/arch/mn10300/lib/checksum.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/checksum.h>
 #include "internal.h"
 
diff --git a/arch/mn10300/mm/cache-smp.c b/arch/mn10300/mm/cache-smp.c
index 2d23b9e..e809960 100644
--- a/arch/mn10300/mm/cache-smp.c
+++ b/arch/mn10300/mm/cache-smp.c
@@ -18,7 +18,7 @@
 #include <asm/processor.h>
 #include <asm/cacheflush.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/smp.h>
 #include "cache-smp.h"
 
diff --git a/arch/mn10300/mm/cache.c b/arch/mn10300/mm/cache.c
index 0a1f0aa..0b925cc 100644
--- a/arch/mn10300/mm/cache.c
+++ b/arch/mn10300/mm/cache.c
@@ -17,7 +17,7 @@
 #include <asm/processor.h>
 #include <asm/cacheflush.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/smp.h>
 #include "cache-smp.h"
 
diff --git a/arch/mn10300/mm/extable.c b/arch/mn10300/mm/extable.c
index 25e5485..305de46 100644
--- a/arch/mn10300/mm/extable.c
+++ b/arch/mn10300/mm/extable.c
@@ -10,7 +10,7 @@
  */
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int fixup_exception(struct pt_regs *regs)
 {
diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c
index 97a1ec0..8ce677d 100644
--- a/arch/mn10300/mm/init.c
+++ b/arch/mn10300/mm/init.c
@@ -29,7 +29,7 @@
 #include <linux/gfp.h>
 
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/dma.h>
diff --git a/arch/mn10300/mm/misalignment.c b/arch/mn10300/mm/misalignment.c
index b9920b1..31d04da 100644
--- a/arch/mn10300/mm/misalignment.c
+++ b/arch/mn10300/mm/misalignment.c
@@ -23,7 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
 #include <asm/smp.h>
diff --git a/arch/mn10300/proc-mn2ws0050/proc-init.c b/arch/mn10300/proc-mn2ws0050/proc-init.c
index 950cc8d..25b1b45 100644
--- a/arch/mn10300/proc-mn2ws0050/proc-init.c
+++ b/arch/mn10300/proc-mn2ws0050/proc-init.c
@@ -16,7 +16,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
 #include <asm/smp.h>
diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c
index 746bf5c..6e2bdc9 100644
--- a/arch/nios2/kernel/time.c
+++ b/arch/nios2/kernel/time.c
@@ -81,7 +81,7 @@ static inline unsigned long read_timersnapshot(struct nios2_timer *timer)
 	return count;
 }
 
-static cycle_t nios2_timer_read(struct clocksource *cs)
+static u64 nios2_timer_read(struct clocksource *cs)
 {
 	struct nios2_clocksource *nios2_cs = to_nios2_clksource(cs);
 	unsigned long flags;
diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c
index 81f7da7..72ed30a 100644
--- a/arch/nios2/kernel/traps.c
+++ b/arch/nios2/kernel/traps.c
@@ -19,7 +19,7 @@
 
 #include <asm/traps.h>
 #include <asm/sections.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static DEFINE_SPINLOCK(die_lock);
 
diff --git a/arch/openrisc/kernel/or32_ksyms.c b/arch/openrisc/kernel/or32_ksyms.c
index 83ccf7c..86e31cf 100644
--- a/arch/openrisc/kernel/or32_ksyms.c
+++ b/arch/openrisc/kernel/or32_ksyms.c
@@ -24,7 +24,7 @@
 #include <linux/semaphore.h>
 
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/checksum.h>
 #include <asm/io.h>
 #include <asm/hardirq.h>
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 277123b..d7990df 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -36,7 +36,7 @@
 #include <linux/mqueue.h>
 #include <linux/fs.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/processor.h>
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index c82be69..265f10f 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -30,7 +30,7 @@
 #include <asm/processor.h>
 #include <asm/syscall.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define DEBUG_SIG 0
 
diff --git a/arch/openrisc/kernel/time.c b/arch/openrisc/kernel/time.c
index 50e9701..687c11d 100644
--- a/arch/openrisc/kernel/time.c
+++ b/arch/openrisc/kernel/time.c
@@ -117,9 +117,9 @@ static __init void openrisc_clockevent_init(void)
  * is 32 bits wide and runs at the CPU clock frequency.
  */
 
-static cycle_t openrisc_timer_read(struct clocksource *cs)
+static u64 openrisc_timer_read(struct clocksource *cs)
 {
-	return (cycle_t) mfspr(SPR_TTCR);
+	return (u64) mfspr(SPR_TTCR);
 }
 
 static struct clocksource openrisc_timer = {
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 3d3f606..a4574cb 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -31,7 +31,7 @@
 #include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/kallsyms.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/segment.h>
 #include <asm/io.h>
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index ef31fc2..5525446 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -44,6 +44,8 @@
         /* Read-only sections, merged into text segment: */
         . = LOAD_BASE ;
 
+	_text = .;
+
 	/* _s_kernel_ro must be page aligned */
 	. = ALIGN(PAGE_SIZE);
 	_s_kernel_ro = .;
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index e94cd22..b1a7435 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -20,7 +20,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/siginfo.h>
 #include <asm/signal.h>
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index a14b865..3a71f38 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -7,6 +7,7 @@
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_SYSCALL_TRACEPOINTS
 	select ARCH_WANT_FRAME_POINTERS
+	select ARCH_HAS_ELF_RANDOMIZE
 	select RTC_CLASS
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index 78c9fd3..a6b2a42 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -348,9 +348,10 @@ struct pt_regs;	/* forward declaration... */
 
 #define ELF_HWCAP	0
 
-#define STACK_RND_MASK	(is_32bit_task() ? \
-				0x7ff >> (PAGE_SHIFT - 12) : \
-				0x3ffff >> (PAGE_SHIFT - 12))
+/* Masks for stack and mmap randomization */
+#define BRK_RND_MASK	(is_32bit_task() ? 0x07ffUL : 0x3ffffUL)
+#define MMAP_RND_MASK	(is_32bit_task() ? 0x1fffUL : 0x3ffffUL)
+#define STACK_RND_MASK	MMAP_RND_MASK
 
 struct mm_struct;
 extern unsigned long arch_randomize_brk(struct mm_struct *);
diff --git a/arch/parisc/include/asm/pdcpat.h b/arch/parisc/include/asm/pdcpat.h
index 47539f1..e1d2890 100644
--- a/arch/parisc/include/asm/pdcpat.h
+++ b/arch/parisc/include/asm/pdcpat.h
@@ -289,7 +289,7 @@ extern int pdc_pat_cell_get_number(struct pdc_pat_cell_num *cell_info);
 extern int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsigned long mod, unsigned long view_type, void *mem_addr);
 extern int pdc_pat_cell_num_to_loc(void *, unsigned long);
 
-extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, void *hpa);
+extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, unsigned long hpa);
 
 extern int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr, unsigned long count, unsigned long offset);
 
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index ca40741..a3661ee 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -93,9 +93,7 @@ struct system_cpuinfo_parisc {
 /* Per CPU data structure - ie varies per CPU.  */
 struct cpuinfo_parisc {
 	unsigned long it_value;     /* Interval Timer at last timer Intr */
-	unsigned long it_delta;     /* Interval delta (tic_10ms / HZ * 100) */
 	unsigned long irq_count;    /* number of IRQ's since boot */
-	unsigned long irq_max_cr16; /* longest time to handle a single IRQ */
 	unsigned long cpuid;        /* aka slot_number or set to NO_PROC_ID */
 	unsigned long hpa;          /* Host Physical address */
 	unsigned long txn_addr;     /* MMIO addr of EIR or id_eid */
@@ -103,8 +101,6 @@ struct cpuinfo_parisc {
 	unsigned long pending_ipi;  /* bitmap of type ipi_message_type */
 #endif
 	unsigned long bh_count;     /* number of times bh was invoked */
-	unsigned long prof_counter; /* per CPU profiling support */
-	unsigned long prof_multiplier;	/* per CPU profiling support */
 	unsigned long fp_rev;
 	unsigned long fp_model;
 	unsigned int state;
diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index 78d30d2..1c4fe61 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -38,7 +38,7 @@
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/pdc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_64BIT
 #define FRAME_SIZE	128
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 4fcff2d..ad4cb16 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -878,6 +878,9 @@
 	STREG   %r19,PT_SR7(%r16)
 
 intr_return:
+	/* NOTE: Need to enable interrupts incase we schedule. */
+	ssm     PSW_SM_I, %r0
+
 	/* check for reschedule */
 	mfctl   %cr30,%r1
 	LDREG   TI_FLAGS(%r1),%r19	/* sched.h: TIF_NEED_RESCHED */
@@ -904,11 +907,6 @@
 	LDREG	PT_IASQ1(%r16), %r20
 	cmpib,COND(=),n 0,%r20,intr_restore /* backward */
 
-	/* NOTE: We need to enable interrupts if we have to deliver
-	 * signals. We used to do this earlier but it caused kernel
-	 * stack overflows. */
-	ssm     PSW_SM_I, %r0
-
 	copy	%r0, %r25			/* long in_syscall = 0 */
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29			/* Reference param save area */
@@ -960,10 +958,6 @@
 	cmpib,COND(=)	0, %r20, intr_do_preempt
 	nop
 
-	/* NOTE: We need to enable interrupts if we schedule.  We used
-	 * to do this earlier but it caused kernel stack overflows. */
-	ssm     PSW_SM_I, %r0
-
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29		/* Reference param save area */
 #endif
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index e5d7190..9d797ae 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -1258,7 +1258,7 @@ int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsigned long
  *
  * Retrieve the cpu number for the cpu at the specified HPA.
  */
-int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, void *hpa)
+int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, unsigned long hpa)
 {
 	int retval;
 	unsigned long flags;
diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c
index c05d187..c9789d9 100644
--- a/arch/parisc/kernel/inventory.c
+++ b/arch/parisc/kernel/inventory.c
@@ -216,9 +216,9 @@ pat_query_module(ulong pcell_loc, ulong mod_index)
 	register_parisc_device(dev);	/* advertise device */
 
 #ifdef DEBUG_PAT
-	pdc_pat_cell_mod_maddr_block_t io_pdc_cell;
 	/* dump what we see so far... */
 	switch (PAT_GET_ENTITY(dev->mod_info)) {
+		pdc_pat_cell_mod_maddr_block_t io_pdc_cell;
 		unsigned long i;
 
 	case PAT_ENTITY_PROC:
@@ -259,9 +259,9 @@ pat_query_module(ulong pcell_loc, ulong mod_index)
 				pa_pdc_cell->mod[4 + i * 3]);	/* finish (ie end) */
 			printk(KERN_DEBUG 
 				"  IO_VIEW %ld: 0x%016lx 0x%016lx 0x%016lx\n", 
-				i, io_pdc_cell->mod[2 + i * 3],	/* type */
-				io_pdc_cell->mod[3 + i * 3],	/* start */
-				io_pdc_cell->mod[4 + i * 3]);	/* finish (ie end) */
+				i, io_pdc_cell.mod[2 + i * 3],	/* type */
+				io_pdc_cell.mod[3 + i * 3],	/* start */
+				io_pdc_cell.mod[4 + i * 3]);	/* finish (ie end) */
 		}
 		printk(KERN_DEBUG "\n");
 		break;
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index 3cad8aa..7484b3d 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -43,7 +43,7 @@ EXPORT_SYMBOL(__xchg64);
 EXPORT_SYMBOL(__cmpxchg_u64);
 #endif
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 EXPORT_SYMBOL(lclear_user);
 EXPORT_SYMBOL(lstrnlen_user);
 
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index b6298a8..697c535 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -33,7 +33,7 @@
 #include <asm/io.h>
 #include <asm/page.h>	/* get_order */
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/tlbflush.h>	/* for purge_tlb_*() macros */
 
 static struct proc_dir_entry * proc_gsc_root __read_mostly = NULL;
diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index 518f4f5..e282a51 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -48,7 +48,7 @@
 #include <linux/miscdevice.h>
 #include <linux/spinlock.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/perf.h>
 #include <asm/parisc-device.h>
 #include <asm/processor.h>
@@ -301,7 +301,6 @@ static ssize_t perf_read(struct file *file, char __user *buf, size_t cnt, loff_t
 static ssize_t perf_write(struct file *file, const char __user *buf, size_t count, 
 	loff_t *ppos)
 {
-	int err;
 	size_t image_size;
 	uint32_t image_type;
 	uint32_t interface_type;
@@ -320,8 +319,8 @@ static ssize_t perf_write(struct file *file, const char __user *buf, size_t coun
 	if (count != sizeof(uint32_t))
 		return -EIO;
 
-	if ((err = copy_from_user(&image_type, buf, sizeof(uint32_t))) != 0) 
-		return err;
+	if (copy_from_user(&image_type, buf, sizeof(uint32_t)))
+		return -EFAULT;
 
 	/* Get the interface type and test type */
    	interface_type = (image_type >> 16) & 0xffff;
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 4063943..ea6603e 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -276,11 +276,7 @@ void *dereference_function_descriptor(void *ptr)
 
 static inline unsigned long brk_rnd(void)
 {
-	/* 8MB for 32bit, 1GB for 64bit */
-	if (is_32bit_task())
-		return (get_random_int() & 0x7ffUL) << PAGE_SHIFT;
-	else
-		return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT;
+	return (get_random_int() & BRK_RND_MASK) << PAGE_SHIFT;
 }
 
 unsigned long arch_randomize_brk(struct mm_struct *mm)
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index 0c2a94a..85de47f 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -78,11 +78,6 @@ DEFINE_PER_CPU(struct cpuinfo_parisc, cpu_data);
 static void
 init_percpu_prof(unsigned long cpunum)
 {
-	struct cpuinfo_parisc *p;
-
-	p = &per_cpu(cpu_data, cpunum);
-	p->prof_counter = 1;
-	p->prof_multiplier = 1;
 }
 
 
@@ -99,6 +94,7 @@ static int processor_probe(struct parisc_device *dev)
 	unsigned long txn_addr;
 	unsigned long cpuid;
 	struct cpuinfo_parisc *p;
+	struct pdc_pat_cpu_num cpu_info __maybe_unused;
 
 #ifdef CONFIG_SMP
 	if (num_online_cpus() >= nr_cpu_ids) {
@@ -123,10 +119,6 @@ static int processor_probe(struct parisc_device *dev)
 		ulong status;
 		unsigned long bytecnt;
 	        pdc_pat_cell_mod_maddr_block_t *pa_pdc_cell;
-#undef USE_PAT_CPUID
-#ifdef USE_PAT_CPUID
-		struct pdc_pat_cpu_num cpu_info;
-#endif
 
 		pa_pdc_cell = kmalloc(sizeof (*pa_pdc_cell), GFP_KERNEL);
 		if (!pa_pdc_cell)
@@ -145,22 +137,27 @@ static int processor_probe(struct parisc_device *dev)
 
 		kfree(pa_pdc_cell);
 
+		/* get the cpu number */
+		status = pdc_pat_cpu_get_number(&cpu_info, dev->hpa.start);
+		BUG_ON(PDC_OK != status);
+
+		pr_info("Logical CPU #%lu is physical cpu #%lu at location "
+			"0x%lx with hpa %pa\n",
+			cpuid, cpu_info.cpu_num, cpu_info.cpu_loc,
+			&dev->hpa.start);
+
+#undef USE_PAT_CPUID
 #ifdef USE_PAT_CPUID
 /* We need contiguous numbers for cpuid. Firmware's notion
  * of cpuid is for physical CPUs and we just don't care yet.
  * We'll care when we need to query PAT PDC about a CPU *after*
  * boot time (ie shutdown a CPU from an OS perspective).
  */
-		/* get the cpu number */
-		status = pdc_pat_cpu_get_number(&cpu_info, dev->hpa.start);
-
-		BUG_ON(PDC_OK != status);
-
 		if (cpu_info.cpu_num >= NR_CPUS) {
-			printk(KERN_WARNING "IGNORING CPU at 0x%x,"
+			printk(KERN_WARNING "IGNORING CPU at %pa,"
 				" cpu_slot_id > NR_CPUS"
 				" (%ld > %d)\n",
-				dev->hpa.start, cpu_info.cpu_num, NR_CPUS);
+				&dev->hpa.start, cpu_info.cpu_num, NR_CPUS);
 			/* Ignore CPU since it will only crash */
 			boot_cpu_data.cpu_count--;
 			return 1;
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index e02d7b4..f8b6959 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -24,7 +24,7 @@
 #include <linux/signal.h>
 #include <linux/audit.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 2264f68..e58925a 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -27,7 +27,7 @@
 #include <linux/elf.h>
 #include <asm/ucontext.h>
 #include <asm/rt_sigframe.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c
index c342b2e..70aaabb 100644
--- a/arch/parisc/kernel/signal32.c
+++ b/arch/parisc/kernel/signal32.c
@@ -31,7 +31,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "signal32.h"
 
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 0a393a0..bf32941 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -23,7 +23,7 @@
  *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/elf.h>
 #include <linux/file.h>
 #include <linux/fs.h>
@@ -225,19 +225,17 @@ static unsigned long mmap_rnd(void)
 {
 	unsigned long rnd = 0;
 
-	/*
-	*  8 bits of randomness in 32bit mmaps, 20 address space bits
-	* 28 bits of randomness in 64bit mmaps, 40 address space bits
-	*/
-	if (current->flags & PF_RANDOMIZE) {
-		if (is_32bit_task())
-			rnd = get_random_int() % (1<<8);
-		else
-			rnd = get_random_int() % (1<<28);
-	}
+	if (current->flags & PF_RANDOMIZE)
+		rnd = get_random_int() & MMAP_RND_MASK;
+
 	return rnd << PAGE_SHIFT;
 }
 
+unsigned long arch_mmap_rnd(void)
+{
+	return (get_random_int() & MMAP_RND_MASK) << PAGE_SHIFT;
+}
+
 static unsigned long mmap_legacy_base(void)
 {
 	return TASK_UNMAPPED_BASE + mmap_rnd();
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 325f30d..da0d9cb 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -28,7 +28,7 @@
 #include <linux/platform_device.h>
 #include <linux/ftrace.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/page.h>
@@ -59,10 +59,9 @@ static unsigned long clocktick __read_mostly;	/* timer cycles per tick */
  */
 irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 {
-	unsigned long now, now2;
+	unsigned long now;
 	unsigned long next_tick;
-	unsigned long cycles_elapsed, ticks_elapsed = 1;
-	unsigned long cycles_remainder;
+	unsigned long ticks_elapsed = 0;
 	unsigned int cpu = smp_processor_id();
 	struct cpuinfo_parisc *cpuinfo = &per_cpu(cpu_data, cpu);
 
@@ -71,102 +70,49 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 
 	profile_tick(CPU_PROFILING);
 
-	/* Initialize next_tick to the expected tick time. */
+	/* Initialize next_tick to the old expected tick time. */
 	next_tick = cpuinfo->it_value;
 
-	/* Get current cycle counter (Control Register 16). */
-	now = mfctl(16);
+	/* Calculate how many ticks have elapsed. */
+	do {
+		++ticks_elapsed;
+		next_tick += cpt;
+		now = mfctl(16);
+	} while (next_tick - now > cpt);
 
-	cycles_elapsed = now - next_tick;
-
-	if ((cycles_elapsed >> 6) < cpt) {
-		/* use "cheap" math (add/subtract) instead
-		 * of the more expensive div/mul method
-		 */
-		cycles_remainder = cycles_elapsed;
-		while (cycles_remainder > cpt) {
-			cycles_remainder -= cpt;
-			ticks_elapsed++;
-		}
-	} else {
-		/* TODO: Reduce this to one fdiv op */
-		cycles_remainder = cycles_elapsed % cpt;
-		ticks_elapsed += cycles_elapsed / cpt;
-	}
-
-	/* convert from "division remainder" to "remainder of clock tick" */
-	cycles_remainder = cpt - cycles_remainder;
-
-	/* Determine when (in CR16 cycles) next IT interrupt will fire.
-	 * We want IT to fire modulo clocktick even if we miss/skip some.
-	 * But those interrupts don't in fact get delivered that regularly.
-	 */
-	next_tick = now + cycles_remainder;
-
+	/* Store (in CR16 cycles) up to when we are accounting right now. */
 	cpuinfo->it_value = next_tick;
 
-	/* Program the IT when to deliver the next interrupt.
-	 * Only bottom 32-bits of next_tick are writable in CR16!
-	 */
-	mtctl(next_tick, 16);
+	/* Go do system house keeping. */
+	if (cpu == 0)
+		xtime_update(ticks_elapsed);
 
-	/* Skip one clocktick on purpose if we missed next_tick.
+	update_process_times(user_mode(get_irq_regs()));
+
+	/* Skip clockticks on purpose if we know we would miss those.
 	 * The new CR16 must be "later" than current CR16 otherwise
 	 * itimer would not fire until CR16 wrapped - e.g 4 seconds
 	 * later on a 1Ghz processor. We'll account for the missed
-	 * tick on the next timer interrupt.
+	 * ticks on the next timer interrupt.
+	 * We want IT to fire modulo clocktick even if we miss/skip some.
+	 * But those interrupts don't in fact get delivered that regularly.
 	 *
 	 * "next_tick - now" will always give the difference regardless
 	 * if one or the other wrapped. If "now" is "bigger" we'll end up
 	 * with a very large unsigned number.
 	 */
-	now2 = mfctl(16);
-	if (next_tick - now2 > cpt)
-		mtctl(next_tick+cpt, 16);
+	while (next_tick - mfctl(16) > cpt)
+		next_tick += cpt;
 
-#if 1
-/*
- * GGG: DEBUG code for how many cycles programming CR16 used.
- */
-	if (unlikely(now2 - now > 0x3000)) 	/* 12K cycles */
-		printk (KERN_CRIT "timer_interrupt(CPU %d): SLOW! 0x%lx cycles!"
-			" cyc %lX rem %lX "
-			" next/now %lX/%lX\n",
-			cpu, now2 - now, cycles_elapsed, cycles_remainder,
-			next_tick, now );
-#endif
-
-	/* Can we differentiate between "early CR16" (aka Scenario 1) and
-	 * "long delay" (aka Scenario 3)? I don't think so.
-	 *
-	 * Timer_interrupt will be delivered at least a few hundred cycles
-	 * after the IT fires. But it's arbitrary how much time passes
-	 * before we call it "late". I've picked one second.
-	 *
-	 * It's important NO printk's are between reading CR16 and
-	 * setting up the next value. May introduce huge variance.
+	/* Program the IT when to deliver the next interrupt.
+	 * Only bottom 32-bits of next_tick are writable in CR16!
+	 * Timer interrupt will be delivered at least a few hundred cycles
+	 * after the IT fires, so if we are too close (<= 500 cycles) to the
+	 * next cycle, simply skip it.
 	 */
-	if (unlikely(ticks_elapsed > HZ)) {
-		/* Scenario 3: very long delay?  bad in any case */
-		printk (KERN_CRIT "timer_interrupt(CPU %d): delayed!"
-			" cycles %lX rem %lX "
-			" next/now %lX/%lX\n",
-			cpu,
-			cycles_elapsed, cycles_remainder,
-			next_tick, now );
-	}
-
-	/* Done mucking with unreliable delivery of interrupts.
-	 * Go do system house keeping.
-	 */
-
-	if (!--cpuinfo->prof_counter) {
-		cpuinfo->prof_counter = cpuinfo->prof_multiplier;
-		update_process_times(user_mode(get_irq_regs()));
-	}
-
-	if (cpu == 0)
-		xtime_update(ticks_elapsed);
+	if (next_tick - mfctl(16) <= 500)
+		next_tick += cpt;
+	mtctl(next_tick, 16);
 
 	return IRQ_HANDLED;
 }
@@ -191,7 +137,7 @@ EXPORT_SYMBOL(profile_pc);
 
 /* clock source code */
 
-static cycle_t notrace read_cr16(struct clocksource *cs)
+static u64 notrace read_cr16(struct clocksource *cs)
 {
 	return get_cycles();
 }
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index 2b65c01..0a21067a 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -26,7 +26,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/ratelimit.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/hardirq.h>
 #include <asm/traps.h>
 
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index e278a87..1b73690 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -15,7 +15,7 @@
 #include <linux/kallsyms.h>
 #include <linux/sort.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/assembly.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
diff --git a/arch/parisc/lib/checksum.c b/arch/parisc/lib/checksum.c
index ae66d31..ba6384d 100644
--- a/arch/parisc/lib/checksum.c
+++ b/arch/parisc/lib/checksum.c
@@ -20,7 +20,7 @@
 #include <net/checksum.h>
 #include <asm/byteorder.h>
 #include <asm/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define addc(_t,_r)                     \
 	__asm__ __volatile__ (          \
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3da87e1..a8ee573 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -469,6 +469,7 @@
 config KEXEC_FILE
 	bool "kexec file based system call"
 	select KEXEC_CORE
+	select HAVE_IMA_KEXEC
 	select BUILD_BIN2C
 	depends on PPC64
 	depends on CRYPTO=y
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 8159256..ba47c70 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -15,7 +15,7 @@
 #include <linux/threads.h>
 #include <asm/cacheflush.h>
 #include <asm/checksum.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/epapr_hcalls.h>
 
 #include <uapi/asm/ucontext.h>
diff --git a/arch/powerpc/include/asm/ima.h b/arch/powerpc/include/asm/ima.h
new file mode 100644
index 0000000..2313bdf
--- /dev/null
+++ b/arch/powerpc/include/asm/ima.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_POWERPC_IMA_H
+#define _ASM_POWERPC_IMA_H
+
+struct kimage;
+
+int ima_get_kexec_buffer(void **addr, size_t *size);
+int ima_free_kexec_buffer(void);
+
+#ifdef CONFIG_IMA
+void remove_ima_buffer(void *fdt, int chosen_node);
+#else
+static inline void remove_ima_buffer(void *fdt, int chosen_node) {}
+#endif
+
+#ifdef CONFIG_IMA_KEXEC
+int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
+			      size_t size);
+
+int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node);
+#else
+static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
+				   int chosen_node)
+{
+	remove_ima_buffer(fdt, chosen_node);
+	return 0;
+}
+#endif /* CONFIG_IMA_KEXEC */
+
+#endif /* _ASM_POWERPC_IMA_H */
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 6c3b715..25668bc 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -94,11 +94,22 @@ static inline bool kdump_in_progress(void)
 #ifdef CONFIG_KEXEC_FILE
 extern struct kexec_file_ops kexec_elf64_ops;
 
+#ifdef CONFIG_IMA_KEXEC
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	phys_addr_t ima_buffer_addr;
+	size_t ima_buffer_size;
+};
+#endif
+
 int setup_purgatory(struct kimage *image, const void *slave_code,
 		    const void *fdt, unsigned long kernel_load_addr,
 		    unsigned long fdt_load_addr);
-int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
-		  unsigned long initrd_len, const char *cmdline);
+int setup_new_fdt(const struct kimage *image, void *fdt,
+		  unsigned long initrd_load_addr, unsigned long initrd_len,
+		  const char *cmdline);
+int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size);
 #endif /* CONFIG_KEXEC_FILE */
 
 #else /* !CONFIG_KEXEC_CORE */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index a3a6047..23f8082 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -112,6 +112,10 @@
 obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o crash.o \
 				   machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC_FILE)	+= machine_kexec_file_$(BITS).o kexec_elf_$(BITS).o
+ifeq ($(CONFIG_HAVE_IMA_KEXEC)$(CONFIG_IMA),yy)
+obj-y				+= ima_kexec.o
+endif
+
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 033f338..8d58c61 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -20,7 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cache.h>
 #include <asm/cputable.h>
 #include <asm/emulated_ops.h>
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index cfa0f81..d10ad25 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -18,7 +18,7 @@
 #include <asm/kdump.h>
 #include <asm/prom.h>
 #include <asm/firmware.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/rtas.h>
 
 #ifdef DEBUG
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 03d089b..4d3aa05 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -33,7 +33,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/processor.h>
 #include <asm/sstep.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Stores the breakpoints currently in use on each breakpoint address
diff --git a/arch/powerpc/kernel/ima_kexec.c b/arch/powerpc/kernel/ima_kexec.c
new file mode 100644
index 0000000..5ea42c9
--- /dev/null
+++ b/arch/powerpc/kernel/ima_kexec.c
@@ -0,0 +1,223 @@
+/*
+ * Copyright (C) 2016 IBM Corporation
+ *
+ * Authors:
+ * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.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.
+ */
+
+#include <linux/slab.h>
+#include <linux/kexec.h>
+#include <linux/of.h>
+#include <linux/memblock.h>
+#include <linux/libfdt.h>
+
+static int get_addr_size_cells(int *addr_cells, int *size_cells)
+{
+	struct device_node *root;
+
+	root = of_find_node_by_path("/");
+	if (!root)
+		return -EINVAL;
+
+	*addr_cells = of_n_addr_cells(root);
+	*size_cells = of_n_size_cells(root);
+
+	of_node_put(root);
+
+	return 0;
+}
+
+static int do_get_kexec_buffer(const void *prop, int len, unsigned long *addr,
+			       size_t *size)
+{
+	int ret, addr_cells, size_cells;
+
+	ret = get_addr_size_cells(&addr_cells, &size_cells);
+	if (ret)
+		return ret;
+
+	if (len < 4 * (addr_cells + size_cells))
+		return -ENOENT;
+
+	*addr = of_read_number(prop, addr_cells);
+	*size = of_read_number(prop + 4 * addr_cells, size_cells);
+
+	return 0;
+}
+
+/**
+ * ima_get_kexec_buffer - get IMA buffer from the previous kernel
+ * @addr:	On successful return, set to point to the buffer contents.
+ * @size:	On successful return, set to the buffer size.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int ima_get_kexec_buffer(void **addr, size_t *size)
+{
+	int ret, len;
+	unsigned long tmp_addr;
+	size_t tmp_size;
+	const void *prop;
+
+	prop = of_get_property(of_chosen, "linux,ima-kexec-buffer", &len);
+	if (!prop)
+		return -ENOENT;
+
+	ret = do_get_kexec_buffer(prop, len, &tmp_addr, &tmp_size);
+	if (ret)
+		return ret;
+
+	*addr = __va(tmp_addr);
+	*size = tmp_size;
+
+	return 0;
+}
+
+/**
+ * ima_free_kexec_buffer - free memory used by the IMA buffer
+ */
+int ima_free_kexec_buffer(void)
+{
+	int ret;
+	unsigned long addr;
+	size_t size;
+	struct property *prop;
+
+	prop = of_find_property(of_chosen, "linux,ima-kexec-buffer", NULL);
+	if (!prop)
+		return -ENOENT;
+
+	ret = do_get_kexec_buffer(prop->value, prop->length, &addr, &size);
+	if (ret)
+		return ret;
+
+	ret = of_remove_property(of_chosen, prop);
+	if (ret)
+		return ret;
+
+	return memblock_free(addr, size);
+
+}
+
+/**
+ * remove_ima_buffer - remove the IMA buffer property and reservation from @fdt
+ *
+ * The IMA measurement buffer is of no use to a subsequent kernel, so we always
+ * remove it from the device tree.
+ */
+void remove_ima_buffer(void *fdt, int chosen_node)
+{
+	int ret, len;
+	unsigned long addr;
+	size_t size;
+	const void *prop;
+
+	prop = fdt_getprop(fdt, chosen_node, "linux,ima-kexec-buffer", &len);
+	if (!prop)
+		return;
+
+	ret = do_get_kexec_buffer(prop, len, &addr, &size);
+	fdt_delprop(fdt, chosen_node, "linux,ima-kexec-buffer");
+	if (ret)
+		return;
+
+	ret = delete_fdt_mem_rsv(fdt, addr, size);
+	if (!ret)
+		pr_debug("Removed old IMA buffer reservation.\n");
+}
+
+#ifdef CONFIG_IMA_KEXEC
+/**
+ * arch_ima_add_kexec_buffer - do arch-specific steps to add the IMA buffer
+ *
+ * Architectures should use this function to pass on the IMA buffer
+ * information to the next kernel.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
+			      size_t size)
+{
+	image->arch.ima_buffer_addr = load_addr;
+	image->arch.ima_buffer_size = size;
+
+	return 0;
+}
+
+static int write_number(void *p, u64 value, int cells)
+{
+	if (cells == 1) {
+		u32 tmp;
+
+		if (value > U32_MAX)
+			return -EINVAL;
+
+		tmp = cpu_to_be32(value);
+		memcpy(p, &tmp, sizeof(tmp));
+	} else if (cells == 2) {
+		u64 tmp;
+
+		tmp = cpu_to_be64(value);
+		memcpy(p, &tmp, sizeof(tmp));
+	} else
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * setup_ima_buffer - add IMA buffer information to the fdt
+ * @image:		kexec image being loaded.
+ * @fdt:		Flattened device tree for the next kernel.
+ * @chosen_node:	Offset to the chosen node.
+ *
+ * Return: 0 on success, or negative errno on error.
+ */
+int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node)
+{
+	int ret, addr_cells, size_cells, entry_size;
+	u8 value[16];
+
+	remove_ima_buffer(fdt, chosen_node);
+	if (!image->arch.ima_buffer_size)
+		return 0;
+
+	ret = get_addr_size_cells(&addr_cells, &size_cells);
+	if (ret)
+		return ret;
+
+	entry_size = 4 * (addr_cells + size_cells);
+
+	if (entry_size > sizeof(value))
+		return -EINVAL;
+
+	ret = write_number(value, image->arch.ima_buffer_addr, addr_cells);
+	if (ret)
+		return ret;
+
+	ret = write_number(value + 4 * addr_cells, image->arch.ima_buffer_size,
+			   size_cells);
+	if (ret)
+		return ret;
+
+	ret = fdt_setprop(fdt, chosen_node, "linux,ima-kexec-buffer", value,
+			  entry_size);
+	if (ret < 0)
+		return -EINVAL;
+
+	ret = fdt_add_mem_rsv(fdt, image->arch.ima_buffer_addr,
+			      image->arch.ima_buffer_size);
+	if (ret)
+		return -EINVAL;
+
+	pr_debug("IMA buffer at 0x%llx, size = 0x%zx\n",
+		 image->arch.ima_buffer_addr, image->arch.ima_buffer_size);
+
+	return 0;
+}
+#endif /* CONFIG_IMA_KEXEC */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 3c05c31..a018f5c 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -55,7 +55,7 @@
 #include <linux/of.h>
 #include <linux/of_irq.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/irq.h>
diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c
index 6acffd3..9a42309 100644
--- a/arch/powerpc/kernel/kexec_elf_64.c
+++ b/arch/powerpc/kernel/kexec_elf_64.c
@@ -627,7 +627,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 		goto out;
 	}
 
-	ret = setup_new_fdt(fdt, initrd_load_addr, initrd_len, cmdline);
+	ret = setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline);
 	if (ret)
 		goto out;
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index ad108b8..735ff3d 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -35,7 +35,7 @@
 #include <asm/code-patching.h>
 #include <asm/cacheflush.h>
 #include <asm/sstep.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c
index 7abc8a7..992c0d2 100644
--- a/arch/powerpc/kernel/machine_kexec_file_64.c
+++ b/arch/powerpc/kernel/machine_kexec_file_64.c
@@ -27,6 +27,7 @@
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
+#include <asm/ima.h>
 
 #define SLAVE_CODE_SIZE		256
 
@@ -180,7 +181,7 @@ int setup_purgatory(struct kimage *image, const void *slave_code,
  *
  * Return: 0 on success, or negative errno on error.
  */
-static int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size)
+int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size)
 {
 	int i, ret, num_rsvs = fdt_num_mem_rsv(fdt);
 
@@ -209,6 +210,7 @@ static int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size
 
 /*
  * setup_new_fdt - modify /chosen and memory reservation for the next kernel
+ * @image:		kexec image being loaded.
  * @fdt:		Flattened device tree for the next kernel.
  * @initrd_load_addr:	Address where the next initrd will be loaded.
  * @initrd_len:		Size of the next initrd, or 0 if there will be none.
@@ -217,8 +219,9 @@ static int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size
  *
  * Return: 0 on success, or negative errno on error.
  */
-int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
-		  unsigned long initrd_len, const char *cmdline)
+int setup_new_fdt(const struct kimage *image, void *fdt,
+		  unsigned long initrd_load_addr, unsigned long initrd_len,
+		  const char *cmdline)
 {
 	int ret, chosen_node;
 	const void *prop;
@@ -328,6 +331,12 @@ int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
 		}
 	}
 
+	ret = setup_ima_buffer(image, fdt, chosen_node);
+	if (ret) {
+		pr_err("Error setting up the new device tree.\n");
+		return ret;
+	}
+
 	ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0);
 	if (ret) {
 		pr_err("Error setting up the new device tree.\n");
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 1863324..84db14e 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -296,7 +296,7 @@
 	lis	r3, KERNELBASE@h
 	iccci	0,r3
 #endif
-#elif CONFIG_FSL_BOOKE
+#elif defined(CONFIG_FSL_BOOKE)
 BEGIN_FTR_SECTION
 	mfspr   r3,SPRN_L1CSR0
 	ori     r3,r3,L1CSR0_CFI|L1CSR0_CLFC
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 30b89d5..3f7ba0f 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -22,7 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/bug.h>
 #include <asm/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/firmware.h>
 #include <linux/sort.h>
 #include <asm/setup.h>
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 34d2c59..d5e2b83 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -28,7 +28,7 @@
 #include <linux/pagemap.h>
 #include <linux/pstore.h>
 #include <linux/zlib.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/nvram.h>
 #include <asm/rtas.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 678f87a..41c86c6 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -24,7 +24,7 @@
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/machdep.h>
 
 #undef DEBUG
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index c30612a..56548bf 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -24,7 +24,7 @@
 #include <asm/machdep.h>
 #include <asm/vdso_datapage.h>
 #include <asm/rtas.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/prom.h>
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index b1ec62f..e4744ff 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -34,7 +34,7 @@
 #include <linux/perf_event.h>
 #include <linux/context_tracking.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/switch_to.h>
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c
index 1e887f3..f37eb53 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace32.c
@@ -29,7 +29,7 @@
 #include <linux/signal.h>
 #include <linux/compat.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/switch_to.h>
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index c82eed9..df56dfc 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -24,7 +24,7 @@
 #include <linux/bitops.h>
 #include <linux/rtc.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <asm/io.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 6a3e5de..112cc3b 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -35,7 +35,7 @@
 #include <asm/page.h>
 #include <asm/param.h>
 #include <asm/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/udbg.h>
 #include <asm/syscalls.h>
 #include <asm/smp.h>
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index db2b482..f6f6a8a 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -19,7 +19,7 @@
 #include <linux/proc_fs.h>
 #include <linux/reboot.h>
 #include <asm/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/rtas.h>
 
 #define MODULE_VERS "1.0"
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index a26a020..2bf1f9b 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -22,7 +22,7 @@
 #include <linux/workqueue.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/rtas.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 5fe7918..7fcf1f7 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -29,7 +29,7 @@
 #include <asm/bootx.h>
 #include <asm/btext.h>
 #include <asm/machdep.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pmac_feature.h>
 #include <asm/sections.h>
 #include <asm/nvram.h>
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index bbe77ae..3a36711 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -15,7 +15,7 @@
 #include <linux/key.h>
 #include <linux/context_tracking.h>
 #include <asm/hw_breakpoint.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/debug.h>
 #include <asm/tm.h>
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 27aa913..97bb138 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -37,7 +37,7 @@
 #include <linux/binfmts.h>
 #endif
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/syscalls.h>
 #include <asm/sigcontext.h>
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 96698fd..c83c115 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -27,7 +27,7 @@
 
 #include <asm/sigcontext.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/unistd.h>
 #include <asm/cacheflush.h>
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 8a28587..15f216d 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -44,7 +44,7 @@
 
 #include <asm/ptrace.h>
 #include <asm/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/time.h>
 #include <asm/mmu_context.h>
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index 644cce3..de04c9f 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -36,7 +36,7 @@
 #include <linux/file.h>
 #include <linux/personality.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/syscalls.h>
 #include <asm/time.h>
 #include <asm/unistd.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index be9751f..bc2e08d 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -64,7 +64,7 @@
 #include <asm/nvram.h>
 #include <asm/cache.h>
 #include <asm/machdep.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/time.h>
 #include <asm/prom.h>
 #include <asm/irq.h>
@@ -80,7 +80,7 @@
 #include <linux/clockchips.h>
 #include <linux/timekeeper_internal.h>
 
-static cycle_t rtc_read(struct clocksource *);
+static u64 rtc_read(struct clocksource *);
 static struct clocksource clocksource_rtc = {
 	.name         = "rtc",
 	.rating       = 400,
@@ -89,7 +89,7 @@ static struct clocksource clocksource_rtc = {
 	.read         = rtc_read,
 };
 
-static cycle_t timebase_read(struct clocksource *);
+static u64 timebase_read(struct clocksource *);
 static struct clocksource clocksource_timebase = {
 	.name         = "timebase",
 	.rating       = 400,
@@ -802,18 +802,18 @@ void read_persistent_clock(struct timespec *ts)
 }
 
 /* clocksource code */
-static cycle_t rtc_read(struct clocksource *cs)
+static u64 rtc_read(struct clocksource *cs)
 {
-	return (cycle_t)get_rtc();
+	return (u64)get_rtc();
 }
 
-static cycle_t timebase_read(struct clocksource *cs)
+static u64 timebase_read(struct clocksource *cs)
 {
-	return (cycle_t)get_tb();
+	return (u64)get_tb();
 }
 
 void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
-			 struct clocksource *clock, u32 mult, cycle_t cycle_last)
+			 struct clocksource *clock, u32 mult, u64 cycle_last)
 {
 	u64 new_tb_to_xs, new_stamp_xsec;
 	u32 frac_sec;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4239aaf..e6cc56b 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -40,7 +40,7 @@
 
 #include <asm/emulated_ops.h>
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/machdep.h>
 #include <asm/rtas.h>
diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c
index c4bfadb..2d8f6d8 100644
--- a/arch/powerpc/kernel/vecemu.c
+++ b/arch/powerpc/kernel/vecemu.c
@@ -7,7 +7,7 @@
 #include <linux/sched.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Functions in vector.S */
 extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index b6952dd..019f008 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -25,7 +25,7 @@
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8dcbe37..ec34e39 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -39,7 +39,7 @@
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -1872,8 +1872,7 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
 	}
 	dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
 		   / tb_ticks_per_sec;
-	hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
-		      HRTIMER_MODE_REL);
+	hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL);
 	vcpu->arch.timer_running = 1;
 }
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 826c541..1482961 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -28,7 +28,7 @@
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index 02176fd..f102616 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -17,7 +17,7 @@
 
 #include <linux/anon_inodes.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index ef27fbd..20528701 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -11,7 +11,7 @@
 #include <linux/kvm.h>
 #include <linux/err.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/kvm_book3s.h>
 #include <asm/kvm_ppc.h>
 #include <asm/hvcall.h>
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 3bdc639..20dff10 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -14,7 +14,7 @@
 #include <linux/anon_inodes.h>
 #include <linux/spinlock.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/kvm_book3s.h>
 #include <asm/kvm_ppc.h>
 #include <asm/hvcall.h>
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index df3f270..0514cbd 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -30,7 +30,7 @@
 #include <linux/fs.h>
 
 #include <asm/cputable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/kvm_ppc.h>
 #include <asm/cacheflush.h>
 #include <asm/dbell.h>
diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c
index ed38f81..fe312c1 100644
--- a/arch/powerpc/kvm/mpic.c
+++ b/arch/powerpc/kvm/mpic.c
@@ -29,7 +29,7 @@
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/anon_inodes.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mpic.h>
 #include <asm/kvm_para.h>
 #include <asm/kvm_host.h>
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index efd1183..cd892de 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -30,7 +30,7 @@
 #include <linux/irqbypass.h>
 #include <linux/kvm_irqfd.h>
 #include <asm/cputable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/kvm_ppc.h>
 #include <asm/tlbflush.h>
 #include <asm/cputhreads.h>
diff --git a/arch/powerpc/lib/checksum_wrappers.c b/arch/powerpc/lib/checksum_wrappers.c
index 08e3a33..a0cb63f 100644
--- a/arch/powerpc/lib/checksum_wrappers.c
+++ b/arch/powerpc/lib/checksum_wrappers.c
@@ -21,7 +21,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/checksum.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 			       int len, __wsum sum, int *err_ptr)
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index d5edbeb..c1746df 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -13,7 +13,7 @@
 #include <linux/mm.h>
 #include <asm/page.h>
 #include <asm/code-patching.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 int patch_instruction(unsigned int *addr, unsigned int instr)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 9c78a9c..06c7e9b 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -14,7 +14,7 @@
 #include <linux/prefetch.h>
 #include <asm/sstep.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cpu_has_feature.h>
 #include <asm/cputable.h>
 
diff --git a/arch/powerpc/lib/usercopy_64.c b/arch/powerpc/lib/usercopy_64.c
index 5eea6f3..9bd3a3d 100644
--- a/arch/powerpc/lib/usercopy_64.c
+++ b/arch/powerpc/lib/usercopy_64.c
@@ -7,7 +7,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
 {
diff --git a/arch/powerpc/math-emu/fabs.c b/arch/powerpc/math-emu/fabs.c
index 549baba..a5e7ad1 100644
--- a/arch/powerpc/math-emu/fabs.c
+++ b/arch/powerpc/math-emu/fabs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int
 fabs(u32 *frD, u32 *frB)
diff --git a/arch/powerpc/math-emu/fadd.c b/arch/powerpc/math-emu/fadd.c
index 0158a16..29de37e 100644
--- a/arch/powerpc/math-emu/fadd.c
+++ b/arch/powerpc/math-emu/fadd.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fadds.c b/arch/powerpc/math-emu/fadds.c
index 5930f40..7093c5b 100644
--- a/arch/powerpc/math-emu/fadds.c
+++ b/arch/powerpc/math-emu/fadds.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fcmpo.c b/arch/powerpc/math-emu/fcmpo.c
index 5bce011..5d64446 100644
--- a/arch/powerpc/math-emu/fcmpo.c
+++ b/arch/powerpc/math-emu/fcmpo.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fcmpu.c b/arch/powerpc/math-emu/fcmpu.c
index d4fb1ba..0f9bf48 100644
--- a/arch/powerpc/math-emu/fcmpu.c
+++ b/arch/powerpc/math-emu/fcmpu.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fctiw.c b/arch/powerpc/math-emu/fctiw.c
index f694440..716d6da 100644
--- a/arch/powerpc/math-emu/fctiw.c
+++ b/arch/powerpc/math-emu/fctiw.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fctiwz.c b/arch/powerpc/math-emu/fctiwz.c
index 71e782f..7212fa7 100644
--- a/arch/powerpc/math-emu/fctiwz.c
+++ b/arch/powerpc/math-emu/fctiwz.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fdiv.c b/arch/powerpc/math-emu/fdiv.c
index a29239c..e1e4520 100644
--- a/arch/powerpc/math-emu/fdiv.c
+++ b/arch/powerpc/math-emu/fdiv.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fdivs.c b/arch/powerpc/math-emu/fdivs.c
index 526bc26..5511e2d1 100644
--- a/arch/powerpc/math-emu/fdivs.c
+++ b/arch/powerpc/math-emu/fdivs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fmadd.c b/arch/powerpc/math-emu/fmadd.c
index 8c3f20a..2b6fae0 100644
--- a/arch/powerpc/math-emu/fmadd.c
+++ b/arch/powerpc/math-emu/fmadd.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fmadds.c b/arch/powerpc/math-emu/fmadds.c
index 794fb31..aff35f2 100644
--- a/arch/powerpc/math-emu/fmadds.c
+++ b/arch/powerpc/math-emu/fmadds.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fmr.c b/arch/powerpc/math-emu/fmr.c
index bd55384..f634791 100644
--- a/arch/powerpc/math-emu/fmr.c
+++ b/arch/powerpc/math-emu/fmr.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int
 fmr(u32 *frD, u32 *frB)
diff --git a/arch/powerpc/math-emu/fmsub.c b/arch/powerpc/math-emu/fmsub.c
index 626f6fe..1fb26ce 100644
--- a/arch/powerpc/math-emu/fmsub.c
+++ b/arch/powerpc/math-emu/fmsub.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fmsubs.c b/arch/powerpc/math-emu/fmsubs.c
index 3425bc8..f739654 100644
--- a/arch/powerpc/math-emu/fmsubs.c
+++ b/arch/powerpc/math-emu/fmsubs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fmul.c b/arch/powerpc/math-emu/fmul.c
index 2c19297..ffd31b5 100644
--- a/arch/powerpc/math-emu/fmul.c
+++ b/arch/powerpc/math-emu/fmul.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fmuls.c b/arch/powerpc/math-emu/fmuls.c
index f5ad5c9..21aee43 100644
--- a/arch/powerpc/math-emu/fmuls.c
+++ b/arch/powerpc/math-emu/fmuls.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fnabs.c b/arch/powerpc/math-emu/fnabs.c
index a7d34f3..af877a5 100644
--- a/arch/powerpc/math-emu/fnabs.c
+++ b/arch/powerpc/math-emu/fnabs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int
 fnabs(u32 *frD, u32 *frB)
diff --git a/arch/powerpc/math-emu/fneg.c b/arch/powerpc/math-emu/fneg.c
index 1e988cd..8417d17 100644
--- a/arch/powerpc/math-emu/fneg.c
+++ b/arch/powerpc/math-emu/fneg.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int
 fneg(u32 *frD, u32 *frB)
diff --git a/arch/powerpc/math-emu/fnmadd.c b/arch/powerpc/math-emu/fnmadd.c
index e817bc5..6316ef0 100644
--- a/arch/powerpc/math-emu/fnmadd.c
+++ b/arch/powerpc/math-emu/fnmadd.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fnmadds.c b/arch/powerpc/math-emu/fnmadds.c
index 4db4b7d..9ffe037 100644
--- a/arch/powerpc/math-emu/fnmadds.c
+++ b/arch/powerpc/math-emu/fnmadds.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fnmsub.c b/arch/powerpc/math-emu/fnmsub.c
index f65979f..f97a9cf 100644
--- a/arch/powerpc/math-emu/fnmsub.c
+++ b/arch/powerpc/math-emu/fnmsub.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fnmsubs.c b/arch/powerpc/math-emu/fnmsubs.c
index 9021dac..7fa1217 100644
--- a/arch/powerpc/math-emu/fnmsubs.c
+++ b/arch/powerpc/math-emu/fnmsubs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fre.c b/arch/powerpc/math-emu/fre.c
index 49ccf2c..b621a79 100644
--- a/arch/powerpc/math-emu/fre.c
+++ b/arch/powerpc/math-emu/fre.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int fre(void *frD, void *frB)
 {
diff --git a/arch/powerpc/math-emu/fres.c b/arch/powerpc/math-emu/fres.c
index 10ecbd0..211c30d 100644
--- a/arch/powerpc/math-emu/fres.c
+++ b/arch/powerpc/math-emu/fres.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int
 fres(void *frD, void *frB)
diff --git a/arch/powerpc/math-emu/frsp.c b/arch/powerpc/math-emu/frsp.c
index ddcc146..3e3bc73 100644
--- a/arch/powerpc/math-emu/frsp.c
+++ b/arch/powerpc/math-emu/frsp.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/frsqrte.c b/arch/powerpc/math-emu/frsqrte.c
index 1d0a3a0..7c2ce43 100644
--- a/arch/powerpc/math-emu/frsqrte.c
+++ b/arch/powerpc/math-emu/frsqrte.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int
 frsqrte(void *frD, void *frB)
diff --git a/arch/powerpc/math-emu/frsqrtes.c b/arch/powerpc/math-emu/frsqrtes.c
index 7e838e3..269951a 100644
--- a/arch/powerpc/math-emu/frsqrtes.c
+++ b/arch/powerpc/math-emu/frsqrtes.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int frsqrtes(void *frD, void *frB)
 {
diff --git a/arch/powerpc/math-emu/fsel.c b/arch/powerpc/math-emu/fsel.c
index 1b0c144..32b62c6 100644
--- a/arch/powerpc/math-emu/fsel.c
+++ b/arch/powerpc/math-emu/fsel.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fsqrt.c b/arch/powerpc/math-emu/fsqrt.c
index a55fc7d..0e2a34b 100644
--- a/arch/powerpc/math-emu/fsqrt.c
+++ b/arch/powerpc/math-emu/fsqrt.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fsqrts.c b/arch/powerpc/math-emu/fsqrts.c
index 31dccbf..420cf19 100644
--- a/arch/powerpc/math-emu/fsqrts.c
+++ b/arch/powerpc/math-emu/fsqrts.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fsub.c b/arch/powerpc/math-emu/fsub.c
index 02c5dff4..feedd70 100644
--- a/arch/powerpc/math-emu/fsub.c
+++ b/arch/powerpc/math-emu/fsub.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/fsubs.c b/arch/powerpc/math-emu/fsubs.c
index 5d9b18c..7419051 100644
--- a/arch/powerpc/math-emu/fsubs.c
+++ b/arch/powerpc/math-emu/fsubs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/lfd.c b/arch/powerpc/math-emu/lfd.c
index 79ac76d..d998a50 100644
--- a/arch/powerpc/math-emu/lfd.c
+++ b/arch/powerpc/math-emu/lfd.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/double.h>
diff --git a/arch/powerpc/math-emu/lfs.c b/arch/powerpc/math-emu/lfs.c
index 434ed27..1ee10b8 100644
--- a/arch/powerpc/math-emu/lfs.c
+++ b/arch/powerpc/math-emu/lfs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/math.c b/arch/powerpc/math-emu/math.c
index ab151f0..76ee2e5 100644
--- a/arch/powerpc/math-emu/math.c
+++ b/arch/powerpc/math-emu/math.c
@@ -5,7 +5,7 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/reg.h>
 #include <asm/switch_to.h>
 
diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c
index 28337c9..581f404 100644
--- a/arch/powerpc/math-emu/math_efp.c
+++ b/arch/powerpc/math-emu/math_efp.c
@@ -22,7 +22,7 @@
 #include <linux/types.h>
 #include <linux/prctl.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/reg.h>
 
 #define FP_EX_BOOKE_E500_SPE
diff --git a/arch/powerpc/math-emu/mcrfs.c b/arch/powerpc/math-emu/mcrfs.c
index e948d57..8e8e723 100644
--- a/arch/powerpc/math-emu/mcrfs.c
+++ b/arch/powerpc/math-emu/mcrfs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/mffs.c b/arch/powerpc/math-emu/mffs.c
index 5526cf9..e00fdc2 100644
--- a/arch/powerpc/math-emu/mffs.c
+++ b/arch/powerpc/math-emu/mffs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/mtfsb0.c b/arch/powerpc/math-emu/mtfsb0.c
index bc98558..5ed3e7d 100644
--- a/arch/powerpc/math-emu/mtfsb0.c
+++ b/arch/powerpc/math-emu/mtfsb0.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/mtfsb1.c b/arch/powerpc/math-emu/mtfsb1.c
index fe6ed5a..602aa16 100644
--- a/arch/powerpc/math-emu/mtfsb1.c
+++ b/arch/powerpc/math-emu/mtfsb1.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/mtfsf.c b/arch/powerpc/math-emu/mtfsf.c
index 44b0fc8..b0d5593 100644
--- a/arch/powerpc/math-emu/mtfsf.c
+++ b/arch/powerpc/math-emu/mtfsf.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/mtfsfi.c b/arch/powerpc/math-emu/mtfsfi.c
index fd2acc2..5df3054 100644
--- a/arch/powerpc/math-emu/mtfsfi.c
+++ b/arch/powerpc/math-emu/mtfsfi.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/math-emu/stfd.c b/arch/powerpc/math-emu/stfd.c
index 33a165c..6baeaec 100644
--- a/arch/powerpc/math-emu/stfd.c
+++ b/arch/powerpc/math-emu/stfd.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int
 stfd(void *frS, void *ea)
diff --git a/arch/powerpc/math-emu/stfiwx.c b/arch/powerpc/math-emu/stfiwx.c
index f15a35f..9da7c5d 100644
--- a/arch/powerpc/math-emu/stfiwx.c
+++ b/arch/powerpc/math-emu/stfiwx.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int
 stfiwx(u32 *frS, void *ea)
diff --git a/arch/powerpc/math-emu/stfs.c b/arch/powerpc/math-emu/stfs.c
index 6122147..62bd252 100644
--- a/arch/powerpc/math-emu/stfs.c
+++ b/arch/powerpc/math-emu/stfs.c
@@ -1,6 +1,6 @@
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sfp-machine.h>
 #include <math-emu/soft-fp.h>
diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c
index 31a5d42..61ac468 100644
--- a/arch/powerpc/mm/40x_mmu.c
+++ b/arch/powerpc/mm/40x_mmu.c
@@ -43,7 +43,7 @@
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/smp.h>
 #include <asm/bootx.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 139dec4..080d49b 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -48,7 +48,7 @@
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/smp.h>
 #include <asm/machdep.h>
 #include <asm/setup.h>
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 8410b4b..8033493 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -42,7 +42,7 @@
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/tlbflush.h>
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index a000c35..93abf8a 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -51,7 +51,7 @@
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/smp.h>
 #include <asm/machdep.h>
 #include <asm/tlb.h>
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 0cb6bd8..b1099cb 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -944,7 +944,7 @@ void __init initmem_init(void)
 	 * _nocalls() + manual invocation is used because cpuhp is not yet
 	 * initialized for the boot CPU.
 	 */
-	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "POWER_NUMA_PREPARE",
+	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "powerpc/numa:prepare",
 				  ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
 	for_each_present_cpu(cpu)
 		numa_setup_cpu(cpu);
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index d554351..5c096c0 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -15,7 +15,7 @@
 #include <linux/hugetlb.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/tlbflush.h>
 
 /*
diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c
index b19265d..5182f29 100644
--- a/arch/powerpc/oprofile/cell/spu_profiler.c
+++ b/arch/powerpc/oprofile/cell/spu_profiler.c
@@ -180,7 +180,7 @@ static enum hrtimer_restart profile_spus(struct hrtimer *timer)
 	smp_wmb();	/* insure spu event buffer updates are written */
 			/* don't want events intermingled... */
 
-	kt = ktime_set(0, profiling_interval);
+	kt = profiling_interval;
 	if (!spu_prof_running)
 		goto stop;
 	hrtimer_forward(timer, timer->base->get_time(), kt);
@@ -204,7 +204,7 @@ int start_spu_profiling_cycles(unsigned int cycles_reset)
 	ktime_t kt;
 
 	pr_debug("timer resolution: %lu\n", TICK_NSEC);
-	kt = ktime_set(0, profiling_interval);
+	kt = profiling_interval;
 	hrtimer_init(&timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer_set_expires(&timer, kt);
 	timer.function = profile_spus;
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 72c27b8..fd3e403 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2189,7 +2189,7 @@ int register_power_pmu(struct power_pmu *pmu)
 #endif /* CONFIG_PPC64 */
 
 	perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW);
-	cpuhp_setup_state(CPUHP_PERF_POWER, "PERF_POWER",
+	cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare",
 			  power_pmu_prepare_cpu, NULL);
 	return 0;
 }
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index 3803b0a..6c0ba75 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -117,9 +117,6 @@ static const struct of_device_id of_device_ids[] = {
 	{
 		.compatible	= "fsl,qe",
 	},
-	{
-		.compatible    = "fsl,fman",
-	},
 	/* The following two are for the Freescale hypervisor */
 	{
 		.name		= "hypervisor",
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 85c85eb..e5a891a 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -30,7 +30,7 @@
 #include <linux/coredump.h>
 #include <linux/binfmts.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "spufs.h"
 
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 3a14712..a35e2c2 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -35,7 +35,7 @@
 #include <asm/time.h>
 #include <asm/spu.h>
 #include <asm/spu_info.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "spufs.h"
 #include "sputrace.h"
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 5364d4a..d8af9bc0 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -38,7 +38,7 @@
 #include <asm/prom.h>
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "spufs.h"
 
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index a87200a..0d290ea 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -5,7 +5,7 @@
 #include <linux/namei.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "spufs.h"
 
diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c
index 9ef8cc3..c3ede2c 100644
--- a/arch/powerpc/platforms/chrp/nvram.c
+++ b/arch/powerpc/platforms/chrp/nvram.c
@@ -13,7 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/rtas.h>
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index f2344cb..ecd6d91 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -18,7 +18,7 @@
 #include <linux/vmalloc.h>
 #include <linux/fcntl.h>
 #include <linux/kobject.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/opal.h>
 
 struct elog_obj {
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index e4169d6..4886eb8 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -21,7 +21,7 @@
 #include <asm/xics.h>
 #include <asm/opal.h>
 #include <asm/prom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/debug.h>
 
 static int opal_lpc_chip_id = -1;
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index e315e70..2d6ee1c 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -29,7 +29,7 @@
 #include <asm/opal-prd.h>
 #include <asm/opal.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 /**
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 9723288..4839db3 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -37,7 +37,7 @@
 #include <asm/hvcall.h>
 #include <asm/mmu.h>
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/memory.h>
 #include <asm/plpar_wrappers.h>
 
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 76caa4a..5cb2e4b 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -24,7 +24,7 @@
 
 #include <asm/prom.h>
 #include <asm/machdep.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/rtas.h>
 
 static struct workqueue_struct *pseries_hp_wq;
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 39049e4..6b04e3f 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -24,7 +24,7 @@
 #include <linux/debugfs.h>
 #include <linux/spinlock.h>
 #include <asm/smp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/firmware.h>
 #include <asm/lppaca.h>
 #include <asm/debug.h>
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e639797..779fc2a 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -25,7 +25,7 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/lppaca.h>
 #include <asm/hvcall.h>
 #include <asm/firmware.h>
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 79aef8c..69cedc1 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -18,7 +18,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/ctype.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/nvram.h>
 #include <asm/rtas.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index cc66c49..e5bf1e8 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -19,7 +19,7 @@
 
 #include <asm/prom.h>
 #include <asm/machdep.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu.h>
 
 #include "of_helpers.h"
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index 7d28cab..c47585a 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -27,7 +27,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/rtas.h>
 #include <asm/prom.h>
 
diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c
index 6f5a8d1..d0e9f17 100644
--- a/arch/powerpc/sysdev/scom.c
+++ b/arch/powerpc/sysdev/scom.c
@@ -25,7 +25,7 @@
 #include <asm/debug.h>
 #include <asm/prom.h>
 #include <asm/scom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 const struct scom_controller *scom_controller;
 EXPORT_SYMBOL_GPL(scom_controller);
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 53a16aa..5692dd5 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -30,7 +30,7 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
 #include <asm/tsi108.h>
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index f587c48..5a8dfa2 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -28,7 +28,7 @@
 #include <linux/platform_device.h>
 #include <asm/appldata.h>
 #include <asm/vtimer.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/smp.h>
 
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index 4da604e..8515dd5 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -6,7 +6,7 @@
  * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/sclp.h>
 #include <asm/ipl.h>
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 1113389..daf9bb0 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -21,7 +21,7 @@
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <asm/debug.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/timex.h>
 #include <asm/cpacf.h>
 
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index d7f100c..12bf4fe 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -11,7 +11,7 @@
 #ifndef _S390_CHECKSUM_H
 #define _S390_CHECKSUM_H
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * computes the checksum of a memory block at buff, length len,
diff --git a/arch/s390/include/asm/idals.h b/arch/s390/include/asm/idals.h
index a7b2d75..280b60a 100644
--- a/arch/s390/include/asm/idals.h
+++ b/arch/s390/include/asm/idals.h
@@ -17,7 +17,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <asm/cio.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define IDA_SIZE_LOG 12 /* 11 for 2k , 12 for 4k */
 #define IDA_BLOCK_SIZE (1L<<IDA_SIZE_LOG)
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 515fea5..67f7a99 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -8,7 +8,7 @@
 #define __S390_MMU_CONTEXT_H
 
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/ctl_reg.h>
 
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 0f9cd90..96df454 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -51,7 +51,7 @@
 #include <linux/slab.h>
 
 #include <asm/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/scm.h>
 #include <net/sock.h>
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 6f2a6ab..362350cc 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -23,7 +23,7 @@
 #include <linux/personality.h>
 #include <linux/binfmts.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/lowcore.h>
 #include <asm/switch_to.h>
 #include "compat_linux.h"
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index aa12de7..79f8ae9 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -19,7 +19,7 @@
 #include <linux/ctype.h>
 #include <linux/string.h>
 #include <linux/sysctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/fs.h>
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index c74c592..9f017cf 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -22,7 +22,7 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dis.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index fdb4042..84e0557 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -33,7 +33,7 @@
 #include <linux/ftrace.h>
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dis.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe);
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 037c2a2..1aba10e 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -711,7 +711,7 @@ static int __init cpumf_pmu_init(void)
 		return rc;
 	}
 	return cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE,
-				 "AP_PERF_S390_CF_ONLINE",
+				 "perf/s390/cf:online",
 				 s390_pmu_online_cpu, s390_pmu_offline_cpu);
 }
 early_initcall(cpumf_pmu_init);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 763dec1..1c0b585 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1623,7 +1623,7 @@ static int __init init_cpum_sampling_pmu(void)
 		goto out;
 	}
 
-	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "AP_PERF_S390_SF_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "perf/s390/sf:online",
 			  s390_pmu_sf_online_cpu, s390_pmu_sf_offline_cpu);
 out:
 	return err;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index b81ab88..7447ba5 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -26,7 +26,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/switch_to.h>
 #include "entry.h"
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 9f241d1e..62a4c26 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -26,7 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/compat.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/lowcore.h>
 #include <asm/switch_to.h>
 #include "entry.h"
diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c
index f145490..b7af452 100644
--- a/arch/s390/kernel/sys_s390.c
+++ b/arch/s390/kernel/sys_s390.c
@@ -27,7 +27,7 @@
 #include <linux/personality.h>
 #include <linux/unistd.h>
 #include <linux/ipc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "entry.h"
 
 /*
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 867d0a0..52949df 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -38,7 +38,7 @@
 #include <linux/clockchips.h>
 #include <linux/gfp.h>
 #include <linux/kprobes.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/facility.h>
 #include <asm/delay.h>
 #include <asm/div64.h>
@@ -209,7 +209,7 @@ void read_boot_clock64(struct timespec64 *ts)
 	tod_to_timeval(clock - TOD_UNIX_EPOCH, ts);
 }
 
-static cycle_t read_tod_clock(struct clocksource *cs)
+static u64 read_tod_clock(struct clocksource *cs)
 {
 	unsigned long long now, adj;
 
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index d0539f7..283ad78 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -19,7 +19,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fpu/api.h>
 #include "entry.h"
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index af13f1a..0f8f141 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -20,7 +20,7 @@
 #include <linux/vmalloc.h>
 #include <asm/asm-offsets.h>
 #include <asm/dis.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sclp.h>
 #include <asm/isc.h>
 #include <asm/gmap.h>
@@ -1019,7 +1019,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 		return 0;
 
 	__set_cpu_idle(vcpu);
-	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
+	hrtimer_start(&vcpu->arch.ckc_timer, sltime, HRTIMER_MODE_REL);
 	VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
 no_timer:
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index b3e9d18..b67454a 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -29,7 +29,7 @@
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/dma.h>
diff --git a/arch/score/include/asm/checksum.h b/arch/score/include/asm/checksum.h
index 539d9fd..0338927f 100644
--- a/arch/score/include/asm/checksum.h
+++ b/arch/score/include/asm/checksum.h
@@ -2,7 +2,7 @@
 #define _ASM_SCORE_CHECKSUM_H
 
 #include <linux/in6.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * computes the checksum of a memory block at buff, length len,
diff --git a/arch/score/kernel/ptrace.c b/arch/score/kernel/ptrace.c
index 4f7314d..8b75e54 100644
--- a/arch/score/kernel/ptrace.c
+++ b/arch/score/kernel/ptrace.c
@@ -29,7 +29,7 @@
 #include <linux/ptrace.h>
 #include <linux/regset.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * retrieve the contents of SCORE userspace general registers
diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index 5cea1e7..d948a68 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -29,7 +29,7 @@
 #include <asm/cacheflush.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 unsigned long exception_handlers[32];
 
diff --git a/arch/score/lib/checksum_copy.c b/arch/score/lib/checksum_copy.c
index 9b770b3..39b99ef 100644
--- a/arch/score/lib/checksum_copy.c
+++ b/arch/score/lib/checksum_copy.c
@@ -25,7 +25,7 @@
 
 #include <net/checksum.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 unsigned int csum_partial_copy(const char *src, char *dst,
 				int len, unsigned int sum)
diff --git a/arch/sh/boards/mach-landisk/gio.c b/arch/sh/boards/mach-landisk/gio.c
index 8132dff..32c317f 100644
--- a/arch/sh/boards/mach-landisk/gio.c
+++ b/arch/sh/boards/mach-landisk/gio.c
@@ -18,7 +18,7 @@
 #include <linux/cdev.h>
 #include <linux/fs.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <mach-landisk/mach/gio.h>
 #include <mach-landisk/mach/iodata_landisk.h>
 
diff --git a/arch/sh/boot/compressed/misc.c b/arch/sh/boot/compressed/misc.c
index 208a975..ae1dfdb 100644
--- a/arch/sh/boot/compressed/misc.c
+++ b/arch/sh/boot/compressed/misc.c
@@ -11,7 +11,7 @@
  * Modified to use standard LinuxSH BIOS by Greg Banks 7Jul2000
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/addrspace.h>
 #include <asm/page.h>
 
diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h
index 9f417fe..35ffdd0 100644
--- a/arch/sh/include/asm/mmu_context.h
+++ b/arch/sh/include/asm/mmu_context.h
@@ -10,7 +10,7 @@
 #ifdef __KERNEL__
 #include <cpu/mmu_context.h>
 #include <asm/tlbflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm-generic/mm_hooks.h>
 
diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c
index c8b3be1..c4f01c5 100644
--- a/arch/sh/kernel/cpu/init.c
+++ b/arch/sh/kernel/cpu/init.c
@@ -16,7 +16,7 @@
 #include <linux/log2.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 #include <asm/cache.h>
diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c
index 53b8eeb..c32e660 100644
--- a/arch/sh/kernel/cpu/shmobile/cpuidle.c
+++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c
@@ -16,7 +16,7 @@
 #include <linux/cpuidle.h>
 #include <linux/export.h>
 #include <asm/suspend.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static unsigned long cpuidle_mode[] = {
 	SUSP_SH_SLEEP, /* regular sleep mode */
diff --git a/arch/sh/kernel/cpu/shmobile/pm.c b/arch/sh/kernel/cpu/shmobile/pm.c
index ac37b72..fba2be5 100644
--- a/arch/sh/kernel/cpu/shmobile/pm.c
+++ b/arch/sh/kernel/cpu/shmobile/pm.c
@@ -14,7 +14,7 @@
 #include <linux/io.h>
 #include <linux/suspend.h>
 #include <asm/suspend.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/bl_bit.h>
 
diff --git a/arch/sh/kernel/crash_dump.c b/arch/sh/kernel/crash_dump.c
index 569e7b1..b33be50 100644
--- a/arch/sh/kernel/crash_dump.c
+++ b/arch/sh/kernel/crash_dump.c
@@ -7,7 +7,7 @@
 #include <linux/errno.h>
 #include <linux/crash_dump.h>
 #include <linux/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /**
  * copy_oldmem_page - copy one page from "oldmem"
diff --git a/arch/sh/kernel/io_trapped.c b/arch/sh/kernel/io_trapped.c
index f8ce362..4d4e7a2 100644
--- a/arch/sh/kernel/io_trapped.c
+++ b/arch/sh/kernel/io_trapped.c
@@ -16,7 +16,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/io_trapped.h>
 
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 6c0378c..bc35911 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -16,7 +16,7 @@
 #include <linux/ratelimit.h>
 #include <asm/processor.h>
 #include <asm/machvec.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/thread_info.h>
 #include <cpu/mmu_context.h>
 
diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 83acbf3..1653ff6 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -15,7 +15,7 @@
 #include <linux/kdebug.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index ee12e94..5174185 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -23,7 +23,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/prefetch.h>
 #include <linux/stackprotector.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/fpu.h>
 #include <asm/syscalls.h>
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index 9d3e991..e0b271b 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -26,7 +26,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <asm/syscalls.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 #include <asm/fpu.h>
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index c1a6b89..1aabfd35 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -26,7 +26,7 @@
 #include <linux/elf.h>
 #include <linux/regset.h>
 #include <linux/hw_breakpoint.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
diff --git a/arch/sh/kernel/ptrace_64.c b/arch/sh/kernel/ptrace_64.c
index 5cea973..c49d0d0 100644
--- a/arch/sh/kernel/ptrace_64.c
+++ b/arch/sh/kernel/ptrace_64.c
@@ -32,7 +32,7 @@
 #include <linux/elf.h>
 #include <linux/regset.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index e7b49d8..3a44c75 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -31,7 +31,7 @@
 #include <linux/memblock.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/page.h>
 #include <asm/elf.h>
diff --git a/arch/sh/kernel/sh_ksyms_64.c b/arch/sh/kernel/sh_ksyms_64.c
index 26a0774..6ee3740 100644
--- a/arch/sh/kernel/sh_ksyms_64.c
+++ b/arch/sh/kernel/sh_ksyms_64.c
@@ -18,7 +18,7 @@
 #include <linux/screen_info.h>
 #include <asm/cacheflush.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/checksum.h>
 #include <asm/io.h>
 #include <asm/delay.h>
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index f7c3d5c..5128d30 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -25,7 +25,7 @@
 #include <linux/io.h>
 #include <linux/tracehook.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/syscalls.h>
diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c
index d8a3f0d..7b77f18 100644
--- a/arch/sh/kernel/signal_64.c
+++ b/arch/sh/kernel/signal_64.c
@@ -23,7 +23,7 @@
 #include <linux/stddef.h>
 #include <linux/tracehook.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/fpu.h>
diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c
index 8c6a350..6576e5e 100644
--- a/arch/sh/kernel/sys_sh.c
+++ b/arch/sh/kernel/sys_sh.c
@@ -23,7 +23,7 @@
 #include <linux/fs.h>
 #include <linux/ipc.h>
 #include <asm/syscalls.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/cacheflush.h>
 #include <asm/cachectl.h>
diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c
index b66d1c6..d5287d7 100644
--- a/arch/sh/kernel/sys_sh32.c
+++ b/arch/sh/kernel/sys_sh32.c
@@ -13,7 +13,7 @@
 #include <linux/fs.h>
 #include <linux/ipc.h>
 #include <asm/cacheflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/syscalls.h>
 
diff --git a/arch/sh/kernel/traps_64.c b/arch/sh/kernel/traps_64.c
index d208c27..00835ed 100644
--- a/arch/sh/kernel/traps_64.c
+++ b/arch/sh/kernel/traps_64.c
@@ -25,7 +25,7 @@
 #include <linux/sysctl.h>
 #include <linux/module.h>
 #include <linux/perf_event.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/alignment.h>
 #include <asm/processor.h>
diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c
index 04aa55f..5078cb8 100644
--- a/arch/sh/math-emu/math.c
+++ b/arch/sh/math-emu/math.c
@@ -14,7 +14,7 @@
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <asm/io.h>
 
diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c
index 777e50f..4eb9d43 100644
--- a/arch/sh/mm/cache-debugfs.c
+++ b/arch/sh/mm/cache-debugfs.c
@@ -12,7 +12,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cache.h>
 #include <asm/io.h>
 
diff --git a/arch/sh/mm/cache-sh3.c b/arch/sh/mm/cache-sh3.c
index e37523f..031634f 100644
--- a/arch/sh/mm/cache-sh3.c
+++ b/arch/sh/mm/cache-sh3.c
@@ -17,7 +17,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
diff --git a/arch/sh/mm/cache-sh5.c b/arch/sh/mm/cache-sh5.c
index d1bffbc..d94dade 100644
--- a/arch/sh/mm/cache-sh5.c
+++ b/arch/sh/mm/cache-sh5.c
@@ -17,7 +17,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 
 extern void __weak sh4__flush_region_init(void);
diff --git a/arch/sh/mm/cache-sh7705.c b/arch/sh/mm/cache-sh7705.c
index 7729cca..6cd2aa3 100644
--- a/arch/sh/mm/cache-sh7705.c
+++ b/arch/sh/mm/cache-sh7705.c
@@ -20,7 +20,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
diff --git a/arch/sh/mm/extable_32.c b/arch/sh/mm/extable_32.c
index c1cf446..9cfcbb5 100644
--- a/arch/sh/mm/extable_32.c
+++ b/arch/sh/mm/extable_32.c
@@ -5,7 +5,7 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int fixup_exception(struct pt_regs *regs)
 {
diff --git a/arch/sh/mm/extable_64.c b/arch/sh/mm/extable_64.c
index f054996..96edaff 100644
--- a/arch/sh/mm/extable_64.c
+++ b/arch/sh/mm/extable_64.c
@@ -12,7 +12,7 @@
  */
 #include <linux/rwsem.h>
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern unsigned long copy_user_memcpy, copy_user_memcpy_end;
 extern void __copy_user_fixup(void);
diff --git a/arch/sh/mm/nommu.c b/arch/sh/mm/nommu.c
index 36312d2..82f8197 100644
--- a/arch/sh/mm/nommu.c
+++ b/arch/sh/mm/nommu.c
@@ -14,7 +14,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/page.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Nothing too terribly exciting here ..
diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c
index 7160c9f..7b2cc49 100644
--- a/arch/sh/mm/pmb.c
+++ b/arch/sh/mm/pmb.c
@@ -25,7 +25,7 @@
 #include <linux/vmalloc.h>
 #include <asm/cacheflush.h>
 #include <asm/sizes.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
diff --git a/arch/sh/mm/tlb-sh3.c b/arch/sh/mm/tlb-sh3.c
index 6554fb4..5c66665 100644
--- a/arch/sh/mm/tlb-sh3.c
+++ b/arch/sh/mm/tlb-sh3.c
@@ -21,7 +21,7 @@
 #include <linux/interrupt.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
diff --git a/arch/sh/mm/tlbex_64.c b/arch/sh/mm/tlbex_64.c
index 8557548..8ff966d 100644
--- a/arch/sh/mm/tlbex_64.c
+++ b/arch/sh/mm/tlbex_64.c
@@ -36,7 +36,7 @@
 #include <linux/kprobes.h>
 #include <asm/tlb.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 
diff --git a/arch/sh/mm/tlbflush_64.c b/arch/sh/mm/tlbflush_64.c
index f33fdd2..bd0715d 100644
--- a/arch/sh/mm/tlbflush_64.c
+++ b/arch/sh/mm/tlbflush_64.c
@@ -24,7 +24,7 @@
 #include <linux/interrupt.h>
 #include <asm/io.h>
 #include <asm/tlb.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 
diff --git a/arch/sh/oprofile/backtrace.c b/arch/sh/oprofile/backtrace.c
index 9c88dcd..c7695f9 100644
--- a/arch/sh/oprofile/backtrace.c
+++ b/arch/sh/oprofile/backtrace.c
@@ -19,7 +19,7 @@
 #include <linux/mm.h>
 #include <asm/unwinder.h>
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sections.h>
 #include <asm/stacktrace.h>
 
diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h
index eff748c..e25af5f 100644
--- a/arch/sparc/include/asm/checksum_32.h
+++ b/arch/sparc/include/asm/checksum_32.h
@@ -16,7 +16,7 @@
  */
 
 #include <linux/in6.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h
index 0395d75..96a5ed5 100644
--- a/arch/sparc/include/asm/checksum_64.h
+++ b/arch/sparc/include/asm/checksum_64.h
@@ -16,7 +16,7 @@
  */
 
 #include <linux/in6.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c
index 742f6c4..9ebc37e 100644
--- a/arch/sparc/kernel/apc.c
+++ b/arch/sparc/kernel/apc.c
@@ -17,7 +17,7 @@
 
 #include <asm/io.h>
 #include <asm/oplib.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/auxio.h>
 #include <asm/apc.h>
 #include <asm/processor.h>
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 34a7930..3bebf39 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -35,7 +35,7 @@
 #include <asm/timer.h>
 #include <asm/smp.h>
 #include <asm/starfire.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cache.h>
 #include <asm/cpudata.h>
 #include <asm/auxio.h>
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index b0377db..2d13a4f 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -11,7 +11,7 @@
 #include <linux/context_tracking.h>
 #include <asm/signal.h>
 #include <asm/cacheflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* We do not have hardware single-stepping on sparc64.
  * So we implement software single-stepping with breakpoint
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 8a6982d..c0765bb 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -17,7 +17,7 @@
 #include <asm/hypervisor.h>
 #include <asm/mdesc.h>
 #include <asm/prom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/oplib.h>
 #include <asm/smp.h>
 
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 9c1878f..015e55a 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -21,7 +21,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/prom.h>
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index 24384e1..a38787b 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -33,7 +33,7 @@
 #include <asm/pcic.h>
 #include <asm/timex.h>
 #include <asm/timer.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq_regs.h>
 
 #include "kernel.h"
diff --git a/arch/sparc/kernel/pmc.c b/arch/sparc/kernel/pmc.c
index 97d1231..f12b23f 100644
--- a/arch/sparc/kernel/pmc.c
+++ b/arch/sparc/kernel/pmc.c
@@ -15,7 +15,7 @@
 
 #include <asm/io.h>
 #include <asm/oplib.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/auxio.h>
 #include <asm/processor.h>
 
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index b7780a5..48ffc3e 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -28,7 +28,7 @@
 
 #include <asm/auxio.h>
 #include <asm/oplib.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 47ff558..d249ca1 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -33,7 +33,7 @@
 #include <linux/nmi.h>
 #include <linux/context_tracking.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index a331fdc..eca3dc7 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -23,7 +23,7 @@
 #include <linux/tracehook.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 
 #include "kernel.h"
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 96494b2..901063c1 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -31,7 +31,7 @@
 
 #include <asm/asi.h>
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/psrcompat.h>
 #include <asm/visasm.h>
 #include <asm/spitfire.h>
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 91cc2f4..b4096bb 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -21,7 +21,7 @@
 #include <linux/bitops.h>
 #include <linux/tracehook.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/pgtable.h>
 #include <asm/psrcompat.h>
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 9c0c8fd..62c3e25 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -20,7 +20,7 @@
 #include <linux/bitops.h>
 #include <linux/tracehook.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index c782c9b..965d50e 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -25,7 +25,7 @@
 #include <linux/bitops.h>
 #include <linux/context_tracking.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/pgtable.h>
 #include <asm/fpumacro.h>
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 8182f7c..0ce347f 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -43,7 +43,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/oplib.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/starfire.h>
 #include <asm/tlb.h>
 #include <asm/sections.h>
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 022c30c..bca44f3 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -44,7 +44,7 @@
 #include <linux/slab.h>
 
 #include <asm/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fpumacro.h>
 #include <asm/mmu_context.h>
 #include <asm/compat_signal.h>
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index 646988d..fb7b185 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -21,7 +21,7 @@
 #include <linux/smp.h>
 #include <linux/ipc.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 #include "systbls.h"
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index fe8b8ee..884c703 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -26,7 +26,7 @@
 #include <linux/export.h>
 #include <linux/context_tracking.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/utrap.h>
 #include <asm/unistd.h>
 
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index 1affabc..244062b 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -148,7 +148,7 @@ static unsigned int sbus_cycles_offset(void)
 	return offset;
 }
 
-static cycle_t timer_cs_read(struct clocksource *cs)
+static u64 timer_cs_read(struct clocksource *cs)
 {
 	unsigned int seq, offset;
 	u64 cycles;
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index c69b21e..12a6d35 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -45,7 +45,7 @@
 #include <asm/smp.h>
 #include <asm/sections.h>
 #include <asm/cpudata.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq_regs.h>
 
 #include "entry.h"
@@ -770,7 +770,7 @@ void udelay(unsigned long usecs)
 }
 EXPORT_SYMBOL(udelay);
 
-static cycle_t clocksource_tick_read(struct clocksource *cs)
+static u64 clocksource_tick_read(struct clocksource *cs)
 {
 	return tick_ops->get_tick();
 }
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 496fa92..4bc10e4 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -29,7 +29,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/unistd.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fpumacro.h>
 #include <asm/lsu.h>
 #include <asm/dcu.h>
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 32b61d1..d20d4e3 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -12,7 +12,7 @@
 #include <linux/mm.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <linux/perf_event.h>
 
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 52c00d9..cda7fd3 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -16,7 +16,7 @@
 #include <asm/ptrace.h>
 #include <asm/pstate.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <linux/bitops.h>
 #include <linux/perf_event.h>
diff --git a/arch/sparc/kernel/uprobes.c b/arch/sparc/kernel/uprobes.c
index b683140..d852ae5 100644
--- a/arch/sparc/kernel/uprobes.c
+++ b/arch/sparc/kernel/uprobes.c
@@ -29,7 +29,7 @@
 #include <linux/kdebug.h>
 
 #include <asm/cacheflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Compute the address of the breakpoint instruction and return it.
  *
diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c
index c096c62..c4ac58e 100644
--- a/arch/sparc/kernel/visemul.c
+++ b/arch/sparc/kernel/visemul.c
@@ -10,7 +10,7 @@
 #include <asm/ptrace.h>
 #include <asm/pstate.h>
 #include <asm/fpumacro.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 
 /* OPF field of various VIS instructions.  */
diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c
index 87bab0a..435a467 100644
--- a/arch/sparc/kernel/windows.c
+++ b/arch/sparc/kernel/windows.c
@@ -11,7 +11,7 @@
 #include <linux/smp.h>
 
 #include <asm/cacheflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "kernel.h"
 
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index 5ce8f2f..4d7e0ff 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -68,7 +68,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/perf_event.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "sfp-util_32.h"
 #include <math-emu/soft-fp.h>
diff --git a/arch/sparc/math-emu/math_64.c b/arch/sparc/math-emu/math_64.c
index 034aadb..9647051 100644
--- a/arch/sparc/math-emu/math_64.c
+++ b/arch/sparc/math-emu/math_64.c
@@ -15,7 +15,7 @@
 
 #include <asm/fpumacro.h>
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 
 #include "sfp-util_64.h"
diff --git a/arch/sparc/mm/extable.c b/arch/sparc/mm/extable.c
index a61c349..768a11e 100644
--- a/arch/sparc/mm/extable.c
+++ b/arch/sparc/mm/extable.c
@@ -3,7 +3,7 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 void sort_extable(struct exception_table_entry *start,
 		  struct exception_table_entry *finish)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 37aa537..5d2f915 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -35,7 +35,7 @@
 #include <asm/oplib.h>
 #include <asm/iommu.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 #include <asm/dma.h>
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 9f37106..c84c54a 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -35,7 +35,7 @@
 #include <asm/syscalls.h>
 #include <asm/traps.h>
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #ifdef CONFIG_HARDWALL
 #include <asm/hardwall.h>
 #endif
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index 8629730..de3eae8 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -25,7 +25,7 @@
 #include <linux/prctl.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 #include <arch/abi.h>
 #include <arch/spr_def.h>
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index 4fe78c5..f229e97 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -27,7 +27,7 @@
 #include <linux/prctl.h>
 #include <asm/cacheflush.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 #include <arch/abi.h>
 #include <arch/spr_def.h>
diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c
index 3282787..6d38127 100644
--- a/arch/um/drivers/harddog_kern.c
+++ b/arch/um/drivers/harddog_kern.c
@@ -45,7 +45,7 @@
 #include <linux/mutex.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "mconsole.h"
 
 MODULE_LICENSE("GPL");
diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c
index 3a4b587..12bdb59 100644
--- a/arch/um/drivers/hostaudio_kern.c
+++ b/arch/um/drivers/hostaudio_kern.c
@@ -9,7 +9,7 @@
 #include <linux/sound.h>
 #include <linux/soundcard.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <init.h>
 #include <os.h>
 
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 8a6b571..8a4c72a 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -24,7 +24,7 @@
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/switch_to.h>
 
 #include <init.h>
diff --git a/arch/um/drivers/mmapper_kern.c b/arch/um/drivers/mmapper_kern.c
index 62145c2..3645fcb 100644
--- a/arch/um/drivers/mmapper_kern.c
+++ b/arch/um/drivers/mmapper_kern.c
@@ -17,7 +17,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <mem_user.h>
 
 /* These are set in mmapper_init, which is called at boot time */
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index dd16c90..05523f1 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -12,7 +12,7 @@
 #include <linux/interrupt.h>
 #include <linux/miscdevice.h>
 #include <linux/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <irq_kern.h>
 #include <os.h>
 
diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c
index 0d7103c..770ec07 100644
--- a/arch/um/kernel/exec.c
+++ b/arch/um/kernel/exec.c
@@ -11,7 +11,7 @@
 #include <linux/slab.h>
 #include <asm/current.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <as-layout.h>
 #include <mem_user.h>
 #include <skas.h>
diff --git a/arch/um/kernel/exitcode.c b/arch/um/kernel/exitcode.c
index 41ebbfe..546302e 100644
--- a/arch/um/kernel/exitcode.c
+++ b/arch/um/kernel/exitcode.c
@@ -10,7 +10,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * If read and write race, the read will still atomically read a valid
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 034b42c7..078630d 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -24,7 +24,7 @@
 #include <asm/current.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <as-layout.h>
 #include <kern_util.h>
 #include <os.h>
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index 6a826cb..bc2a516 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -7,7 +7,7 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/tracehook.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ptrace-abi.h>
 
 void user_enable_single_step(struct task_struct *child)
diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c
index c1d0ae0..6258676 100644
--- a/arch/um/kernel/syscall.c
+++ b/arch/um/kernel/syscall.c
@@ -11,7 +11,7 @@
 #include <linux/syscalls.h>
 #include <asm/current.h>
 #include <asm/mman.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 long old_mmap(unsigned long addr, unsigned long len,
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index 25c2366..ba87a27 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -83,7 +83,7 @@ static irqreturn_t um_timer(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static cycle_t timer_read(struct clocksource *cs)
+static u64 timer_read(struct clocksource *cs)
 {
 	return os_nsecs() / TIMER_MULTIPLIER;
 }
diff --git a/arch/unicore32/kernel/time.c b/arch/unicore32/kernel/time.c
index ac4c544..fceaa67 100644
--- a/arch/unicore32/kernel/time.c
+++ b/arch/unicore32/kernel/time.c
@@ -62,7 +62,7 @@ static struct clock_event_device ckevt_puv3_osmr0 = {
 	.set_state_oneshot	= puv3_osmr0_shutdown,
 };
 
-static cycle_t puv3_read_oscr(struct clocksource *cs)
+static u64 puv3_read_oscr(struct clocksource *cs)
 {
 	return readl(OST_OSCR);
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 64024c9..e487493 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -412,6 +412,19 @@
        def_bool y
        depends on X86_GOLDFISH
 
+config INTEL_RDT_A
+	bool "Intel Resource Director Technology Allocation support"
+	default n
+	depends on X86 && CPU_SUP_INTEL
+	select KERNFS
+	help
+	  Select to enable resource allocation which is a sub-feature of
+	  Intel Resource Director Technology(RDT). More information about
+	  RDT can be found in the Intel x86 Architecture Software
+	  Developer Manual.
+
+	  Say N if unsure.
+
 if X86_32
 config X86_EXTENDED_PLATFORM
 	bool "Support for extended (non-PC) x86 platforms"
diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
index 4224ede..26240dd 100644
--- a/arch/x86/boot/cpu.c
+++ b/arch/x86/boot/cpu.c
@@ -87,12 +87,6 @@ int validate_cpu(void)
 		return -1;
 	}
 
-	if (CONFIG_X86_MINIMUM_CPU_FAMILY <= 4 && !IS_ENABLED(CONFIG_M486) &&
-	    !has_eflag(X86_EFLAGS_ID)) {
-		printf("This kernel requires a CPU with the CPUID instruction.  Build with CONFIG_M486=y to run on this CPU.\n");
-		return -1;
-	}
-
 	if (err_flags) {
 		puts("This kernel requires the following features "
 		     "not present on the CPU:\n");
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index bdd9cc5..b83c61c 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -25,7 +25,7 @@
 #include <asm/desc.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cpufeature.h>
 
 #define CREATE_TRACE_POINTS
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 02223cb..9d4d6e1 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -92,10 +92,10 @@ static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
 	return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
 }
 
-static notrace cycle_t vread_pvclock(int *mode)
+static notrace u64 vread_pvclock(int *mode)
 {
 	const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
-	cycle_t ret;
+	u64 ret;
 	u64 last;
 	u32 version;
 
@@ -142,9 +142,9 @@ static notrace cycle_t vread_pvclock(int *mode)
 }
 #endif
 
-notrace static cycle_t vread_tsc(void)
+notrace static u64 vread_tsc(void)
 {
-	cycle_t ret = (cycle_t)rdtsc_ordered();
+	u64 ret = (u64)rdtsc_ordered();
 	u64 last = gtod->cycle_last;
 
 	if (likely(ret >= last))
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 40121d1..10820f6 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -371,7 +371,7 @@ static int __init init_vdso(void)
 
 	/* notifier priority > KVM */
 	return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
-				 "AP_X86_VDSO_VMA_ONLINE", vgetcpu_online, NULL);
+				 "x86/vdso/vma:online", vgetcpu_online, NULL);
 }
 subsys_initcall(init_vdso);
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index b26ee32..05612a2 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1010,7 +1010,7 @@ static __init int amd_ibs_init(void)
 	 * all online cpus.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-			  "AP_PERF_X86_AMD_IBS_STARTING",
+			  "perf/x86/amd/ibs:STARTING",
 			  x86_pmu_amd_ibs_starting_cpu,
 			  x86_pmu_amd_ibs_dying_cpu);
 
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 9842270..a6eee5a 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -291,7 +291,7 @@ static int __init amd_power_pmu_init(void)
 
 
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
-			  "AP_PERF_X86_AMD_POWER_ONLINE",
+			  "perf/x86/amd/power:online",
 			  power_cpu_init, power_cpu_exit);
 
 	ret = perf_pmu_register(&pmu_class, "power", -1);
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 65577f0..a0b1bdb 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -527,16 +527,16 @@ static int __init amd_uncore_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 	if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
-			      "PERF_X86_AMD_UNCORE_PREP",
+			      "perf/x86/amd/uncore:prepare",
 			      amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
 		goto fail_l2;
 
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
-			      "AP_PERF_X86_AMD_UNCORE_STARTING",
+			      "perf/x86/amd/uncore:starting",
 			      amd_uncore_cpu_starting, NULL))
 		goto fail_prep;
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
-			      "AP_PERF_X86_AMD_UNCORE_ONLINE",
+			      "perf/x86/amd/uncore:online",
 			      amd_uncore_cpu_online,
 			      amd_uncore_cpu_down_prepare))
 		goto fail_start;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f1c2258..019c588 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1820,18 +1820,18 @@ static int __init init_hw_perf_events(void)
 	 * Install callbacks. Core will call them for each online
 	 * cpu.
 	 */
-	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "PERF_X86_PREPARE",
+	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "perf/x86:prepare",
 				x86_pmu_prepare_cpu, x86_pmu_dead_cpu);
 	if (err)
 		return err;
 
 	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING,
-				"AP_PERF_X86_STARTING", x86_pmu_starting_cpu,
+				"perf/x86:starting", x86_pmu_starting_cpu,
 				x86_pmu_dying_cpu);
 	if (err)
 		goto out;
 
-	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "AP_PERF_X86_ONLINE",
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "perf/x86:online",
 				x86_pmu_online_cpu, NULL);
 	if (err)
 		goto out1;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cb85222..8613826 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2110,6 +2110,27 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 		    GLOBAL_STATUS_LBRS_FROZEN);
 	if (!status)
 		goto done;
+	/*
+	 * In case multiple PEBS events are sampled at the same time,
+	 * it is possible to have GLOBAL_STATUS bit 62 set indicating
+	 * PEBS buffer overflow and also seeing at most 3 PEBS counters
+	 * having their bits set in the status register. This is a sign
+	 * that there was at least one PEBS record pending at the time
+	 * of the PMU interrupt. PEBS counters must only be processed
+	 * via the drain_pebs() calls and not via the regular sample
+	 * processing loop coming after that the function, otherwise
+	 * phony regular samples may be generated in the sampling buffer
+	 * not marked with the EXACT tag. Another possibility is to have
+	 * one PEBS event and at least one non-PEBS event whic hoverflows
+	 * while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will
+	 * not be set, yet the overflow status bit for the PEBS counter will
+	 * be on Skylake.
+	 *
+	 * To avoid this problem, we systematically ignore the PEBS-enabled
+	 * counters from the GLOBAL_STATUS mask and we always process PEBS
+	 * events via drain_pebs().
+	 */
+	status &= ~cpuc->pebs_enabled;
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -2117,15 +2138,6 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
 		handled++;
 		x86_pmu.drain_pebs(regs);
-		/*
-		 * There are cases where, even though, the PEBS ovfl bit is set
-		 * in GLOBAL_OVF_STATUS, the PEBS events may also have their
-		 * overflow bits set for their counters. We must clear them
-		 * here because they have been processed as exact samples in
-		 * the drain_pebs() routine. They must not be processed again
-		 * in the for_each_bit_set() loop for regular samples below.
-		 */
-		status &= ~cpuc->pebs_enabled;
 		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 	}
 
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 8f82b02..8c00dc0 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -7,9 +7,9 @@
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel_rdt_common.h>
 #include "../perf_event.h"
 
-#define MSR_IA32_PQR_ASSOC	0x0c8f
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
@@ -24,32 +24,13 @@ static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 static bool cqm_enabled, mbm_enabled;
 unsigned int mbm_socket_max;
 
-/**
- * struct intel_pqr_state - State cache for the PQR MSR
- * @rmid:		The cached Resource Monitoring ID
- * @closid:		The cached Class Of Service ID
- * @rmid_usecnt:	The usage counter for rmid
- *
- * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
- * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
- * contains both parts, so we need to cache them.
- *
- * The cache also helps to avoid pointless updates if the value does
- * not change.
- */
-struct intel_pqr_state {
-	u32			rmid;
-	u32			closid;
-	int			rmid_usecnt;
-};
-
 /*
  * The cached intel_pqr_state is strictly per CPU and can never be
  * updated from a remote CPU. Both functions which modify the state
  * (intel_cqm_event_start and intel_cqm_event_stop) are called with
  * interrupts disabled, which is sufficient for the protection.
  */
-static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
 static struct hrtimer *mbm_timers;
 /**
  * struct sample - mbm event's (local or total) data
@@ -1766,9 +1747,9 @@ static int __init intel_cqm_init(void)
 	 * is enabled to avoid notifier leak.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
-			  "AP_PERF_X86_CQM_STARTING",
+			  "perf/x86/cqm:starting",
 			  intel_cqm_cpu_starting, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "AP_PERF_X86_CQM_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online",
 			  NULL, intel_cqm_cpu_exit);
 
 out:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index da51e5a..fec8a461 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -594,6 +594,9 @@ static int __init cstate_probe(const struct cstate_model *cm)
 
 static inline void cstate_cleanup(void)
 {
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING);
+
 	if (has_cstate_core)
 		perf_pmu_unregister(&cstate_core_pmu);
 
@@ -606,16 +609,16 @@ static int __init cstate_init(void)
 	int err;
 
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING,
-			  "AP_PERF_X86_CSTATE_STARTING", cstate_cpu_init,
-			  NULL);
+			  "perf/x86/cstate:starting", cstate_cpu_init, NULL);
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE,
-			  "AP_PERF_X86_CSTATE_ONLINE", NULL, cstate_cpu_exit);
+			  "perf/x86/cstate:online", NULL, cstate_cpu_exit);
 
 	if (has_cstate_core) {
 		err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
 		if (err) {
 			has_cstate_core = false;
 			pr_info("Failed to register cstate core pmu\n");
+			cstate_cleanup();
 			return err;
 		}
 	}
@@ -629,8 +632,7 @@ static int __init cstate_init(void)
 			return err;
 		}
 	}
-
-	return err;
+	return 0;
 }
 
 static int __init cstate_pmu_init(void)
@@ -655,8 +657,6 @@ module_init(cstate_pmu_init);
 
 static void __exit cstate_pmu_exit(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING);
 	cstate_cleanup();
 }
 module_exit(cstate_pmu_exit);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 0a535ce..bd34124 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -803,13 +803,13 @@ static int __init rapl_pmu_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP",
+	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
 				rapl_cpu_prepare, NULL);
 	if (ret)
 		goto out;
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
-				"AP_PERF_X86_RAPL_ONLINE",
+				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
 		goto out1;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index dbaaf7dc..97c246f 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1398,22 +1398,22 @@ static int __init intel_uncore_init(void)
 	 */
 	if (!cret) {
 	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
-					"PERF_X86_UNCORE_PREP",
-					uncore_cpu_prepare, NULL);
+				       "perf/x86/intel/uncore:prepare",
+				       uncore_cpu_prepare, NULL);
 		if (ret)
 			goto err;
 	} else {
 		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
-					  "PERF_X86_UNCORE_PREP",
+					  "perf/x86/intel/uncore:prepare",
 					  uncore_cpu_prepare, NULL);
 	}
 	first_init = 1;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
-			  "AP_PERF_X86_UNCORE_STARTING",
+			  "perf/x86/uncore:starting",
 			  uncore_cpu_starting, uncore_cpu_dying);
 	first_init = 0;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
-			  "AP_PERF_X86_UNCORE_ONLINE",
+			  "perf/x86/uncore:online",
 			  uncore_event_cpu_online, uncore_event_cpu_offline);
 	return 0;
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 2724277..e6832be 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -669,7 +669,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
-	EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
+	UNCORE_EVENT_CONSTRAINT(0x1f, 0xe),
 	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index cb26f18..7c0a711 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -27,7 +27,7 @@
 #include <linux/jiffies.h>
 #include <linux/perf_event.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
 #include <asm/user32.h>
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index cb13c05..95c0b4a 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -20,7 +20,7 @@
 #include <linux/compat.h>
 #include <linux/binfmts.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fpu/internal.h>
 #include <asm/fpu/signal.h>
 #include <asm/ptrace.h>
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 719cd70..47956c6 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -42,7 +42,7 @@
 #include <linux/slab.h>
 #include <asm/mman.h>
 #include <asm/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <asm/vgtod.h>
 #include <asm/sys_ia32.h>
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 44b8762..830b19d 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -1,5 +1,5 @@
 #include <asm/ftrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/string.h>
 #include <asm/page.h>
 #include <asm/checksum.h>
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 68557f52..8540227 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -139,6 +139,19 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
 
+static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+{
+	bool negative;
+	asm volatile(LOCK_PREFIX "andb %2,%1\n\t"
+		CC_SET(s)
+		: CC_OUT(s) (negative), ADDR
+		: "ir" ((char) ~(1 << nr)) : "memory");
+	return negative;
+}
+
+// Let everybody know we have it
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+
 /*
  * __clear_bit_unlock - Clears a bit in memory
  * @nr: Bit to clear
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index c020ee7..08e7efb 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -8,7 +8,7 @@
  */
 
 #include <linux/compiler.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 /**
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 6ccbf1a..eafee31 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -189,6 +189,9 @@
 
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2	( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3	( 7*32+ 6) /* Code and Data Prioritization L3 */
 
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
@@ -222,6 +225,7 @@
 #define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
 #define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A	( 9*32+15) /* Resource Director Technology Allocation */
 #define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
 #define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
 #define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
new file mode 100644
index 0000000..95ce5c8
--- /dev/null
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -0,0 +1,224 @@
+#ifndef _ASM_X86_INTEL_RDT_H
+#define _ASM_X86_INTEL_RDT_H
+
+#ifdef CONFIG_INTEL_RDT_A
+
+#include <linux/kernfs.h>
+#include <linux/jump_label.h>
+
+#include <asm/intel_rdt_common.h>
+
+#define IA32_L3_QOS_CFG		0xc81
+#define IA32_L3_CBM_BASE	0xc90
+#define IA32_L2_CBM_BASE	0xd10
+
+#define L3_QOS_CDP_ENABLE	0x01ULL
+
+/**
+ * struct rdtgroup - store rdtgroup's data in resctrl file system.
+ * @kn:				kernfs node
+ * @rdtgroup_list:		linked list for all rdtgroups
+ * @closid:			closid for this rdtgroup
+ * @cpu_mask:			CPUs assigned to this rdtgroup
+ * @flags:			status bits
+ * @waitcount:			how many cpus expect to find this
+ *				group when they acquire rdtgroup_mutex
+ */
+struct rdtgroup {
+	struct kernfs_node	*kn;
+	struct list_head	rdtgroup_list;
+	int			closid;
+	struct cpumask		cpu_mask;
+	int			flags;
+	atomic_t		waitcount;
+};
+
+/* rdtgroup.flags */
+#define	RDT_DELETED		1
+
+/* List of all resource groups */
+extern struct list_head rdt_all_groups;
+
+int __init rdtgroup_init(void);
+
+/**
+ * struct rftype - describe each file in the resctrl file system
+ * @name: file name
+ * @mode: access mode
+ * @kf_ops: operations
+ * @seq_show: show content of the file
+ * @write: write to the file
+ */
+struct rftype {
+	char			*name;
+	umode_t			mode;
+	struct kernfs_ops	*kf_ops;
+
+	int (*seq_show)(struct kernfs_open_file *of,
+			struct seq_file *sf, void *v);
+	/*
+	 * write() is the generic write callback which maps directly to
+	 * kernfs write operation and overrides all other operations.
+	 * Maximum write size is determined by ->max_write_len.
+	 */
+	ssize_t (*write)(struct kernfs_open_file *of,
+			 char *buf, size_t nbytes, loff_t off);
+};
+
+/**
+ * struct rdt_resource - attributes of an RDT resource
+ * @enabled:			Is this feature enabled on this machine
+ * @capable:			Is this feature available on this machine
+ * @name:			Name to use in "schemata" file
+ * @num_closid:			Number of CLOSIDs available
+ * @max_cbm:			Largest Cache Bit Mask allowed
+ * @min_cbm_bits:		Minimum number of consecutive bits to be set
+ *				in a cache bit mask
+ * @domains:			All domains for this resource
+ * @num_domains:		Number of domains active
+ * @msr_base:			Base MSR address for CBMs
+ * @tmp_cbms:			Scratch space when updating schemata
+ * @num_tmp_cbms:		Number of CBMs in tmp_cbms
+ * @cache_level:		Which cache level defines scope of this domain
+ * @cbm_idx_multi:		Multiplier of CBM index
+ * @cbm_idx_offset:		Offset of CBM index. CBM index is computed by:
+ *				closid * cbm_idx_multi + cbm_idx_offset
+ */
+struct rdt_resource {
+	bool			enabled;
+	bool			capable;
+	char			*name;
+	int			num_closid;
+	int			cbm_len;
+	int			min_cbm_bits;
+	u32			max_cbm;
+	struct list_head	domains;
+	int			num_domains;
+	int			msr_base;
+	u32			*tmp_cbms;
+	int			num_tmp_cbms;
+	int			cache_level;
+	int			cbm_idx_multi;
+	int			cbm_idx_offset;
+};
+
+/**
+ * struct rdt_domain - group of cpus sharing an RDT resource
+ * @list:	all instances of this resource
+ * @id:		unique id for this instance
+ * @cpu_mask:	which cpus share this resource
+ * @cbm:	array of cache bit masks (indexed by CLOSID)
+ */
+struct rdt_domain {
+	struct list_head	list;
+	int			id;
+	struct cpumask		cpu_mask;
+	u32			*cbm;
+};
+
+/**
+ * struct msr_param - set a range of MSRs from a domain
+ * @res:       The resource to use
+ * @low:       Beginning index from base MSR
+ * @high:      End index
+ */
+struct msr_param {
+	struct rdt_resource	*res;
+	int			low;
+	int			high;
+};
+
+extern struct mutex rdtgroup_mutex;
+
+extern struct rdt_resource rdt_resources_all[];
+extern struct rdtgroup rdtgroup_default;
+DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
+
+int __init rdtgroup_init(void);
+
+enum {
+	RDT_RESOURCE_L3,
+	RDT_RESOURCE_L3DATA,
+	RDT_RESOURCE_L3CODE,
+	RDT_RESOURCE_L2,
+
+	/* Must be the last */
+	RDT_NUM_RESOURCES,
+};
+
+#define for_each_capable_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++) 							      \
+		if (r->capable)
+
+#define for_each_enabled_rdt_resource(r)				      \
+	for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\
+	     r++)							      \
+		if (r->enabled)
+
+/* CPUID.(EAX=10H, ECX=ResID=1).EAX */
+union cpuid_0x10_1_eax {
+	struct {
+		unsigned int cbm_len:5;
+	} split;
+	unsigned int full;
+};
+
+/* CPUID.(EAX=10H, ECX=ResID=1).EDX */
+union cpuid_0x10_1_edx {
+	struct {
+		unsigned int cos_max:16;
+	} split;
+	unsigned int full;
+};
+
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_closid);
+
+void rdt_cbm_update(void *arg);
+struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
+void rdtgroup_kn_unlock(struct kernfs_node *kn);
+ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off);
+int rdtgroup_schemata_show(struct kernfs_open_file *of,
+			   struct seq_file *s, void *v);
+
+/*
+ * intel_rdt_sched_in() - Writes the task's CLOSid to IA32_PQR_MSR
+ *
+ * Following considerations are made so that this has minimal impact
+ * on scheduler hot path:
+ * - This will stay as no-op unless we are running on an Intel SKU
+ *   which supports resource control and we enable by mounting the
+ *   resctrl file system.
+ * - Caches the per cpu CLOSid values and does the MSR write only
+ *   when a task with a different CLOSid is scheduled in.
+ *
+ * Must be called with preemption disabled.
+ */
+static inline void intel_rdt_sched_in(void)
+{
+	if (static_branch_likely(&rdt_enable_key)) {
+		struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+		int closid;
+
+		/*
+		 * If this task has a closid assigned, use it.
+		 * Else use the closid assigned to this cpu.
+		 */
+		closid = current->closid;
+		if (closid == 0)
+			closid = this_cpu_read(cpu_closid);
+
+		if (closid != state->closid) {
+			state->closid = closid;
+			wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, closid);
+		}
+	}
+}
+
+#else
+
+static inline void intel_rdt_sched_in(void) {}
+
+#endif /* CONFIG_INTEL_RDT_A */
+#endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/include/asm/intel_rdt_common.h b/arch/x86/include/asm/intel_rdt_common.h
new file mode 100644
index 0000000..b31081b
--- /dev/null
+++ b/arch/x86/include/asm/intel_rdt_common.h
@@ -0,0 +1,27 @@
+#ifndef _ASM_X86_INTEL_RDT_COMMON_H
+#define _ASM_X86_INTEL_RDT_COMMON_H
+
+#define MSR_IA32_PQR_ASSOC	0x0c8f
+
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid:		The cached Resource Monitoring ID
+ * @closid:		The cached Class Of Service ID
+ * @rmid_usecnt:	The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+	u32			rmid;
+	u32			closid;
+	int			rmid_usecnt;
+};
+
+DECLARE_PER_CPU(struct intel_pqr_state, pqr_state);
+
+#endif /* _ASM_X86_INTEL_RDT_COMMON_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2e25038..a7066dc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -768,7 +768,7 @@ struct kvm_arch {
 	spinlock_t pvclock_gtod_sync_lock;
 	bool use_master_clock;
 	u64 master_kernel_ns;
-	cycle_t master_cycle_now;
+	u64 master_cycle_now;
 	struct delayed_work kvmclock_update_work;
 	struct delayed_work kvmclock_sync_work;
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6aa741f..eaf1005 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -602,33 +602,69 @@ static __always_inline void cpu_relax(void)
 	rep_nop();
 }
 
-/* Stop speculative execution and prefetching of modified code. */
+/*
+ * This function forces the icache and prefetched instruction stream to
+ * catch up with reality in two very specific cases:
+ *
+ *  a) Text was modified using one virtual address and is about to be executed
+ *     from the same physical page at a different virtual address.
+ *
+ *  b) Text was modified on a different CPU, may subsequently be
+ *     executed on this CPU, and you want to make sure the new version
+ *     gets executed.  This generally means you're calling this in a IPI.
+ *
+ * If you're calling this for a different reason, you're probably doing
+ * it wrong.
+ */
 static inline void sync_core(void)
 {
-	int tmp;
+	/*
+	 * There are quite a few ways to do this.  IRET-to-self is nice
+	 * because it works on every CPU, at any CPL (so it's compatible
+	 * with paravirtualization), and it never exits to a hypervisor.
+	 * The only down sides are that it's a bit slow (it seems to be
+	 * a bit more than 2x slower than the fastest options) and that
+	 * it unmasks NMIs.  The "push %cs" is needed because, in
+	 * paravirtual environments, __KERNEL_CS may not be a valid CS
+	 * value when we do IRET directly.
+	 *
+	 * In case NMI unmasking or performance ever becomes a problem,
+	 * the next best option appears to be MOV-to-CR2 and an
+	 * unconditional jump.  That sequence also works on all CPUs,
+	 * but it will fault at CPL3 (i.e. Xen PV and lguest).
+	 *
+	 * CPUID is the conventional way, but it's nasty: it doesn't
+	 * exist on some 486-like CPUs, and it usually exits to a
+	 * hypervisor.
+	 *
+	 * Like all of Linux's memory ordering operations, this is a
+	 * compiler barrier as well.
+	 */
+	register void *__sp asm(_ASM_SP);
 
-#ifdef CONFIG_M486
-	/*
-	 * Do a CPUID if available, otherwise do a jump.  The jump
-	 * can conveniently enough be the jump around CPUID.
-	 */
-	asm volatile("cmpl %2,%1\n\t"
-		     "jl 1f\n\t"
-		     "cpuid\n"
-		     "1:"
-		     : "=a" (tmp)
-		     : "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+#ifdef CONFIG_X86_32
+	asm volatile (
+		"pushfl\n\t"
+		"pushl %%cs\n\t"
+		"pushl $1f\n\t"
+		"iret\n\t"
+		"1:"
+		: "+r" (__sp) : : "memory");
 #else
-	/*
-	 * CPUID is a barrier to speculative execution.
-	 * Prefetched instructions are automatically
-	 * invalidated when modified.
-	 */
-	asm volatile("cpuid"
-		     : "=a" (tmp)
-		     : "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+	unsigned int tmp;
+
+	asm volatile (
+		"mov %%ss, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq %%rsp\n\t"
+		"addq $8, (%%rsp)\n\t"
+		"pushfq\n\t"
+		"mov %%cs, %0\n\t"
+		"pushq %q0\n\t"
+		"pushq $1f\n\t"
+		"iretq\n\t"
+		"1:"
+		: "=&r" (tmp), "+r" (__sp) : : "cc", "memory");
 #endif
 }
 
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 3ad741b..448cfe1 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -14,7 +14,7 @@ static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
 #endif
 
 /* some helper functions for xen and kvm pv clock sources */
-cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
 void pvclock_set_flags(u8 flags);
 unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
@@ -87,11 +87,10 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 }
 
 static __always_inline
-cycle_t __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
-			      u64 tsc)
+u64 __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, u64 tsc)
 {
 	u64 delta = tsc - src->tsc_timestamp;
-	cycle_t offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
+	u64 offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
 					     src->tsc_shift);
 	return src->system_time + offset;
 }
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index abb1fdc..f5e6f1c 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -29,7 +29,7 @@ static inline cycles_t get_cycles(void)
 	return rdtsc();
 }
 
-extern struct system_counterval_t convert_art_to_tsc(cycle_t art);
+extern struct system_counterval_t convert_art_to_tsc(u64 art);
 
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index c5a7f3a..6fa75b1 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -12,7 +12,7 @@ struct unwind_state {
 	struct task_struct *task;
 	int graph_idx;
 #ifdef CONFIG_FRAME_POINTER
-	unsigned long *bp;
+	unsigned long *bp, *orig_sp;
 	struct pt_regs *regs;
 #else
 	unsigned long *sp;
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 3a01996..022e597 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -17,8 +17,8 @@ struct vsyscall_gtod_data {
 	unsigned seq;
 
 	int vclock_mode;
-	cycle_t	cycle_last;
-	cycle_t	mask;
+	u64	cycle_last;
+	u64	mask;
 	u32	mult;
 	u32	shift;
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 6ba7931..7ba7e90 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -59,7 +59,7 @@ struct x86_init_irqs {
 
 /**
  * struct x86_init_oem - oem platform specific customizing functions
- * @arch_setup:			platform specific architecure setup
+ * @arch_setup:			platform specific architecture setup
  * @banner:			print a platform specific banner
  */
 struct x86_init_oem {
@@ -165,8 +165,25 @@ struct x86_legacy_devices {
 };
 
 /**
+ * enum x86_legacy_i8042_state - i8042 keyboard controller state
+ * @X86_LEGACY_I8042_PLATFORM_ABSENT: the controller is always absent on
+ *	given platform/subarch.
+ * @X86_LEGACY_I8042_FIRMWARE_ABSENT: firmware reports that the controller
+ *	is absent.
+ * @X86_LEGACY_i8042_EXPECTED_PRESENT: the controller is likely to be
+ *	present, the i8042 driver should probe for controller existence.
+ */
+enum x86_legacy_i8042_state {
+	X86_LEGACY_I8042_PLATFORM_ABSENT,
+	X86_LEGACY_I8042_FIRMWARE_ABSENT,
+	X86_LEGACY_I8042_EXPECTED_PRESENT,
+};
+
+/**
  * struct x86_legacy_features - legacy x86 features
  *
+ * @i8042: indicated if we expect the device to have i8042 controller
+ *	present.
  * @rtc: this device has a CMOS real-time clock present
  * @reserve_bios_regions: boot code will search for the EBDA address and the
  * 	start of the 640k - 1M BIOS region.  If false, the platform must
@@ -175,6 +192,7 @@ struct x86_legacy_devices {
  * 	documentation for further details.
  */
 struct x86_legacy_features {
+	enum x86_legacy_i8042_state i8042;
 	int rtc;
 	int reserve_bios_regions;
 	struct x86_legacy_devices devices;
@@ -188,15 +206,14 @@ struct x86_legacy_features {
  * @set_wallclock:		set time back to HW clock
  * @is_untracked_pat_range	exclude from PAT logic
  * @nmi_init			enable NMI on cpus
- * @i8042_detect		pre-detect if i8042 controller exists
  * @save_sched_clock_state:	save state for sched_clock() on suspend
  * @restore_sched_clock_state:	restore state for sched_clock() on resume
- * @apic_post_init:		adjust apic if neeeded
+ * @apic_post_init:		adjust apic if needed
  * @legacy:			legacy features
  * @set_legacy_features:	override legacy features. Use of this callback
  * 				is highly discouraged. You should only need
  * 				this if your hardware platform requires further
- * 				custom fine tuning far beyong what may be
+ * 				custom fine tuning far beyond what may be
  * 				possible in x86_early_init_platform_quirks() by
  * 				only using the current x86_hardware_subarch
  * 				semantics.
@@ -210,7 +227,6 @@ struct x86_platform_ops {
 	bool (*is_untracked_pat_range)(u64 start, u64 end);
 	void (*nmi_init)(void);
 	unsigned char (*get_nmi_reason)(void);
-	int (*i8042_detect)(void);
 	void (*save_sched_clock_state)(void);
 	void (*restore_sched_clock_state)(void);
 	void (*apic_post_init)(void);
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index f5fb840..33cbd3d 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -7,7 +7,7 @@
 #include <linux/pfn.h>
 #include <linux/mm.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 6f65b0e..64422f8 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -930,6 +930,13 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
 		x86_platform.legacy.devices.pnpbios = 0;
 	}
 
+	if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
+	    !(acpi_gbl_FADT.boot_flags & ACPI_FADT_8042) &&
+	    x86_platform.legacy.i8042 != X86_LEGACY_I8042_PLATFORM_ABSENT) {
+		pr_debug("ACPI: i8042 controller is absent\n");
+		x86_platform.legacy.i8042 = X86_LEGACY_I8042_FIRMWARE_ABSENT;
+	}
+
 	if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) {
 		pr_debug("ACPI: not registering RTC platform device\n");
 		x86_platform.legacy.rtc = 0;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5cb272a..c5b8f76 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -337,7 +337,11 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
 		n_dspl, (unsigned long)orig_insn + n_dspl + repl_len);
 }
 
-static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
+/*
+ * "noinline" to cause control flow change and thus invalidate I$ and
+ * cause refetch after modification.
+ */
+static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
 {
 	unsigned long flags;
 
@@ -346,7 +350,6 @@ static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
 
 	local_irq_save(flags);
 	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
-	sync_core();
 	local_irq_restore(flags);
 
 	DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
@@ -359,9 +362,12 @@ static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
  * This implies that asymmetric systems where APs have less capabilities than
  * the boot processor are not handled. Tough. Make sure you disable such
  * features by hand.
+ *
+ * Marked "noinline" to cause control flow change and thus insn cache
+ * to refetch changed I$ lines.
  */
-void __init_or_module apply_alternatives(struct alt_instr *start,
-					 struct alt_instr *end)
+void __init_or_module noinline apply_alternatives(struct alt_instr *start,
+						  struct alt_instr *end)
 {
 	struct alt_instr *a;
 	u8 *instr, *replacement;
@@ -667,7 +673,6 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	unsigned long flags;
 	local_irq_save(flags);
 	memcpy(addr, opcode, len);
-	sync_core();
 	local_irq_restore(flags);
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 456316f..65721dc 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -234,7 +234,7 @@ static __init int apbt_late_init(void)
 	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
 		!apb_timer_block_enabled)
 		return 0;
-	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "X86_APB_DEAD", NULL,
+	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "x86/apb:dead", NULL,
 				 apbt_cpu_dead);
 }
 fs_initcall(apbt_late_init);
@@ -247,7 +247,7 @@ void apbt_setup_secondary_clock(void) {}
 static int apbt_clocksource_register(void)
 {
 	u64 start, now;
-	cycle_t t1;
+	u64 t1;
 
 	/* Start the counter, use timer 2 as source, timer 0/1 for event */
 	dw_apb_clocksource_start(clocksource_apbt);
@@ -355,7 +355,7 @@ unsigned long apbt_quick_calibrate(void)
 {
 	int i, scale;
 	u64 old, new;
-	cycle_t t1, t2;
+	u64 t1, t2;
 	unsigned long khz = 0;
 	u32 loop, shift;
 
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 200af5a..5a35f20 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -191,7 +191,7 @@ static int x2apic_cluster_probe(void)
 	if (!x2apic_mode)
 		return 0;
 
-	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare",
 				x2apic_prepare_cpu, x2apic_dead_cpu);
 	if (ret < 0) {
 		pr_err("Failed to register X2APIC_PREPARE\n");
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 643818a7..45d44c173c 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -234,7 +234,7 @@
 #include <linux/i8253.h>
 #include <linux/cpuidle.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/desc.h>
 #include <asm/olpc.h>
 #include <asm/paravirt.h>
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 33b6367..5200001 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -32,6 +32,8 @@
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
+obj-$(CONFIG_INTEL_RDT_A)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_schemata.o
+
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
 obj-$(CONFIG_MICROCODE)			+= microcode/
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1f6b50a..dc1697c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -667,13 +667,14 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_1_EDX] = edx;
 	}
 
+	/* Thermal and Power Management Leaf: level 0x00000006 (eax) */
+	if (c->cpuid_level >= 0x00000006)
+		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
+
 	/* Additional Intel-defined flags: level 0x00000007 */
 	if (c->cpuid_level >= 0x00000007) {
 		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
-
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
-
-		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
 		c->x86_capability[CPUID_7_ECX] = ecx;
 	}
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index be63371..0282b0d 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -153,6 +153,7 @@ struct _cpuid4_info_regs {
 	union _cpuid4_leaf_eax eax;
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
+	unsigned int id;
 	unsigned long size;
 	struct amd_northbridge *nb;
 };
@@ -894,6 +895,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
 static void ci_leaf_init(struct cacheinfo *this_leaf,
 			 struct _cpuid4_info_regs *base)
 {
+	this_leaf->id = base->id;
+	this_leaf->attributes = CACHE_ID;
 	this_leaf->level = base->eax.split.level;
 	this_leaf->type = cache_type_map[base->eax.split.type];
 	this_leaf->coherency_line_size =
@@ -920,6 +923,22 @@ static int __init_cache_level(unsigned int cpu)
 	return 0;
 }
 
+/*
+ * The max shared threads number comes from CPUID.4:EAX[25-14] with input
+ * ECX as cache index. Then right shift apicid by the number's order to get
+ * cache id for this cache node.
+ */
+static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	unsigned long num_threads_sharing;
+	int index_msb;
+
+	num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing;
+	index_msb = get_count_order(num_threads_sharing);
+	id4_regs->id = c->apicid >> index_msb;
+}
+
 static int __populate_cache_leaves(unsigned int cpu)
 {
 	unsigned int idx, ret;
@@ -931,6 +950,7 @@ static int __populate_cache_leaves(unsigned int cpu)
 		ret = cpuid4_cache_lookup_regs(idx, &id4_regs);
 		if (ret)
 			return ret;
+		get_cache_id(cpu, &id4_regs);
 		ci_leaf_init(this_leaf++, &id4_regs);
 		__cache_cpumap_setup(cpu, idx, &id4_regs);
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
new file mode 100644
index 0000000..5a533fe
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -0,0 +1,403 @@
+/*
+ * Resource Director Technology(RDT)
+ * - Cache Allocation code.
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Authors:
+ *    Fenghua Yu <fenghua.yu@intel.com>
+ *    Tony Luck <tony.luck@intel.com>
+ *    Vikas Shivappa <vikas.shivappa@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual June 2016, volume 3, section 17.17.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/cacheinfo.h>
+#include <linux/cpuhotplug.h>
+
+#include <asm/intel-family.h>
+#include <asm/intel_rdt.h>
+
+/* Mutex to protect rdtgroup access. */
+DEFINE_MUTEX(rdtgroup_mutex);
+
+DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
+
+#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
+
+struct rdt_resource rdt_resources_all[] = {
+	{
+		.name		= "L3",
+		.domains	= domain_init(RDT_RESOURCE_L3),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 1,
+		.cbm_idx_offset	= 0
+	},
+	{
+		.name		= "L3DATA",
+		.domains	= domain_init(RDT_RESOURCE_L3DATA),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 2,
+		.cbm_idx_offset	= 0
+	},
+	{
+		.name		= "L3CODE",
+		.domains	= domain_init(RDT_RESOURCE_L3CODE),
+		.msr_base	= IA32_L3_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 3,
+		.cbm_idx_multi	= 2,
+		.cbm_idx_offset	= 1
+	},
+	{
+		.name		= "L2",
+		.domains	= domain_init(RDT_RESOURCE_L2),
+		.msr_base	= IA32_L2_CBM_BASE,
+		.min_cbm_bits	= 1,
+		.cache_level	= 2,
+		.cbm_idx_multi	= 1,
+		.cbm_idx_offset	= 0
+	},
+};
+
+static int cbm_idx(struct rdt_resource *r, int closid)
+{
+	return closid * r->cbm_idx_multi + r->cbm_idx_offset;
+}
+
+/*
+ * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
+ * as they do not have CPUID enumeration support for Cache allocation.
+ * The check for Vendor/Family/Model is not enough to guarantee that
+ * the MSRs won't #GP fault because only the following SKUs support
+ * CAT:
+ *	Intel(R) Xeon(R)  CPU E5-2658  v3  @  2.20GHz
+ *	Intel(R) Xeon(R)  CPU E5-2648L v3  @  1.80GHz
+ *	Intel(R) Xeon(R)  CPU E5-2628L v3  @  2.00GHz
+ *	Intel(R) Xeon(R)  CPU E5-2618L v3  @  2.30GHz
+ *	Intel(R) Xeon(R)  CPU E5-2608L v3  @  2.00GHz
+ *	Intel(R) Xeon(R)  CPU E5-2658A v3  @  2.20GHz
+ *
+ * Probe by trying to write the first of the L3 cach mask registers
+ * and checking that the bits stick. Max CLOSids is always 4 and max cbm length
+ * is always 20 on hsw server parts. The minimum cache bitmask length
+ * allowed for HSW server is always 2 bits. Hardcode all of them.
+ */
+static inline bool cache_alloc_hsw_probe(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86 == 6 &&
+	    boot_cpu_data.x86_model == INTEL_FAM6_HASWELL_X) {
+		struct rdt_resource *r  = &rdt_resources_all[RDT_RESOURCE_L3];
+		u32 l, h, max_cbm = BIT_MASK(20) - 1;
+
+		if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
+			return false;
+		rdmsr(IA32_L3_CBM_BASE, l, h);
+
+		/* If all the bits were set in MSR, return success */
+		if (l != max_cbm)
+			return false;
+
+		r->num_closid = 4;
+		r->cbm_len = 20;
+		r->max_cbm = max_cbm;
+		r->min_cbm_bits = 2;
+		r->capable = true;
+		r->enabled = true;
+
+		return true;
+	}
+
+	return false;
+}
+
+static void rdt_get_config(int idx, struct rdt_resource *r)
+{
+	union cpuid_0x10_1_eax eax;
+	union cpuid_0x10_1_edx edx;
+	u32 ebx, ecx;
+
+	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
+	r->num_closid = edx.split.cos_max + 1;
+	r->cbm_len = eax.split.cbm_len + 1;
+	r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->capable = true;
+	r->enabled = true;
+}
+
+static void rdt_get_cdp_l3_config(int type)
+{
+	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	struct rdt_resource *r = &rdt_resources_all[type];
+
+	r->num_closid = r_l3->num_closid / 2;
+	r->cbm_len = r_l3->cbm_len;
+	r->max_cbm = r_l3->max_cbm;
+	r->capable = true;
+	/*
+	 * By default, CDP is disabled. CDP can be enabled by mount parameter
+	 * "cdp" during resctrl file system mount time.
+	 */
+	r->enabled = false;
+}
+
+static inline bool get_rdt_resources(void)
+{
+	bool ret = false;
+
+	if (cache_alloc_hsw_probe())
+		return true;
+
+	if (!boot_cpu_has(X86_FEATURE_RDT_A))
+		return false;
+
+	if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
+		rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
+		if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
+			rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
+			rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
+		}
+		ret = true;
+	}
+	if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
+		/* CPUID 0x10.2 fields are same format at 0x10.1 */
+		rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+		ret = true;
+	}
+
+	return ret;
+}
+
+static int get_cache_id(int cpu, int level)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
+	int i;
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == level)
+			return ci->info_list[i].id;
+	}
+
+	return -1;
+}
+
+void rdt_cbm_update(void *arg)
+{
+	struct msr_param *m = (struct msr_param *)arg;
+	struct rdt_resource *r = m->res;
+	int i, cpu = smp_processor_id();
+	struct rdt_domain *d;
+
+	list_for_each_entry(d, &r->domains, list) {
+		/* Find the domain that contains this CPU */
+		if (cpumask_test_cpu(cpu, &d->cpu_mask))
+			goto found;
+	}
+	pr_info_once("cpu %d not found in any domain for resource %s\n",
+		     cpu, r->name);
+
+	return;
+
+found:
+	for (i = m->low; i < m->high; i++) {
+		int idx = cbm_idx(r, i);
+
+		wrmsrl(r->msr_base + idx, d->cbm[i]);
+	}
+}
+
+/*
+ * rdt_find_domain - Find a domain in a resource that matches input resource id
+ *
+ * Search resource r's domain list to find the resource id. If the resource
+ * id is found in a domain, return the domain. Otherwise, if requested by
+ * caller, return the first domain whose id is bigger than the input id.
+ * The domain list is sorted by id in ascending order.
+ */
+static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
+					  struct list_head **pos)
+{
+	struct rdt_domain *d;
+	struct list_head *l;
+
+	if (id < 0)
+		return ERR_PTR(id);
+
+	list_for_each(l, &r->domains) {
+		d = list_entry(l, struct rdt_domain, list);
+		/* When id is found, return its domain. */
+		if (id == d->id)
+			return d;
+		/* Stop searching when finding id's position in sorted list. */
+		if (id < d->id)
+			break;
+	}
+
+	if (pos)
+		*pos = l;
+
+	return NULL;
+}
+
+/*
+ * domain_add_cpu - Add a cpu to a resource's domain list.
+ *
+ * If an existing domain in the resource r's domain list matches the cpu's
+ * resource id, add the cpu in the domain.
+ *
+ * Otherwise, a new domain is allocated and inserted into the right position
+ * in the domain list sorted by id in ascending order.
+ *
+ * The order in the domain list is visible to users when we print entries
+ * in the schemata file and schemata input is validated to have the same order
+ * as this list.
+ */
+static void domain_add_cpu(int cpu, struct rdt_resource *r)
+{
+	int i, id = get_cache_id(cpu, r->cache_level);
+	struct list_head *add_pos = NULL;
+	struct rdt_domain *d;
+
+	d = rdt_find_domain(r, id, &add_pos);
+	if (IS_ERR(d)) {
+		pr_warn("Could't find cache id for cpu %d\n", cpu);
+		return;
+	}
+
+	if (d) {
+		cpumask_set_cpu(cpu, &d->cpu_mask);
+		return;
+	}
+
+	d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu));
+	if (!d)
+		return;
+
+	d->id = id;
+
+	d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL);
+	if (!d->cbm) {
+		kfree(d);
+		return;
+	}
+
+	for (i = 0; i < r->num_closid; i++) {
+		int idx = cbm_idx(r, i);
+
+		d->cbm[i] = r->max_cbm;
+		wrmsrl(r->msr_base + idx, d->cbm[i]);
+	}
+
+	cpumask_set_cpu(cpu, &d->cpu_mask);
+	list_add_tail(&d->list, add_pos);
+	r->num_domains++;
+}
+
+static void domain_remove_cpu(int cpu, struct rdt_resource *r)
+{
+	int id = get_cache_id(cpu, r->cache_level);
+	struct rdt_domain *d;
+
+	d = rdt_find_domain(r, id, NULL);
+	if (IS_ERR_OR_NULL(d)) {
+		pr_warn("Could't find cache id for cpu %d\n", cpu);
+		return;
+	}
+
+	cpumask_clear_cpu(cpu, &d->cpu_mask);
+	if (cpumask_empty(&d->cpu_mask)) {
+		r->num_domains--;
+		kfree(d->cbm);
+		list_del(&d->list);
+		kfree(d);
+	}
+}
+
+static void clear_closid(int cpu)
+{
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+
+	per_cpu(cpu_closid, cpu) = 0;
+	state->closid = 0;
+	wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0);
+}
+
+static int intel_rdt_online_cpu(unsigned int cpu)
+{
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+	for_each_capable_rdt_resource(r)
+		domain_add_cpu(cpu, r);
+	/* The cpu is set in default rdtgroup after online. */
+	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
+	clear_closid(cpu);
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int intel_rdt_offline_cpu(unsigned int cpu)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+	for_each_capable_rdt_resource(r)
+		domain_remove_cpu(cpu, r);
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask))
+			break;
+	}
+	clear_closid(cpu);
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int __init intel_rdt_late_init(void)
+{
+	struct rdt_resource *r;
+	int state, ret;
+
+	if (!get_rdt_resources())
+		return -ENODEV;
+
+	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				  "x86/rdt/cat:online:",
+				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
+	if (state < 0)
+		return state;
+
+	ret = rdtgroup_init();
+	if (ret) {
+		cpuhp_remove_state(state);
+		return ret;
+	}
+
+	for_each_capable_rdt_resource(r)
+		pr_info("Intel RDT %s allocation detected\n", r->name);
+
+	return 0;
+}
+
+late_initcall(intel_rdt_late_init);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
new file mode 100644
index 0000000..8af04afd
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -0,0 +1,1115 @@
+/*
+ * User interface for Resource Alloction in Resource Director Technology(RDT)
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Fenghua Yu <fenghua.yu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/kernfs.h>
+#include <linux/seq_file.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/task_work.h>
+
+#include <uapi/linux/magic.h>
+
+#include <asm/intel_rdt.h>
+#include <asm/intel_rdt_common.h>
+
+DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
+struct kernfs_root *rdt_root;
+struct rdtgroup rdtgroup_default;
+LIST_HEAD(rdt_all_groups);
+
+/* Kernel fs node for "info" directory under root */
+static struct kernfs_node *kn_info;
+
+/*
+ * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
+ * we can keep a bitmap of free CLOSIDs in a single integer.
+ *
+ * Using a global CLOSID across all resources has some advantages and
+ * some drawbacks:
+ * + We can simply set "current->closid" to assign a task to a resource
+ *   group.
+ * + Context switch code can avoid extra memory references deciding which
+ *   CLOSID to load into the PQR_ASSOC MSR
+ * - We give up some options in configuring resource groups across multi-socket
+ *   systems.
+ * - Our choices on how to configure each resource become progressively more
+ *   limited as the number of resources grows.
+ */
+static int closid_free_map;
+
+static void closid_init(void)
+{
+	struct rdt_resource *r;
+	int rdt_min_closid = 32;
+
+	/* Compute rdt_min_closid across all resources */
+	for_each_enabled_rdt_resource(r)
+		rdt_min_closid = min(rdt_min_closid, r->num_closid);
+
+	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
+
+	/* CLOSID 0 is always reserved for the default group */
+	closid_free_map &= ~1;
+}
+
+int closid_alloc(void)
+{
+	int closid = ffs(closid_free_map);
+
+	if (closid == 0)
+		return -ENOSPC;
+	closid--;
+	closid_free_map &= ~(1 << closid);
+
+	return closid;
+}
+
+static void closid_free(int closid)
+{
+	closid_free_map |= 1 << closid;
+}
+
+/* set uid and gid of rdtgroup dirs and files to that of the creator */
+static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
+{
+	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
+				.ia_uid = current_fsuid(),
+				.ia_gid = current_fsgid(), };
+
+	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
+	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
+		return 0;
+
+	return kernfs_setattr(kn, &iattr);
+}
+
+static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
+{
+	struct kernfs_node *kn;
+	int ret;
+
+	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
+				  0, rft->kf_ops, rft, NULL, NULL);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret) {
+		kernfs_remove(kn);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int rdtgroup_add_files(struct kernfs_node *kn, struct rftype *rfts,
+			      int len)
+{
+	struct rftype *rft;
+	int ret;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		ret = rdtgroup_add_file(kn, rft);
+		if (ret)
+			goto error;
+	}
+
+	return 0;
+error:
+	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
+	while (--rft >= rfts)
+		kernfs_remove_by_name(kn, rft->name);
+	return ret;
+}
+
+static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
+{
+	struct kernfs_open_file *of = m->private;
+	struct rftype *rft = of->kn->priv;
+
+	if (rft->seq_show)
+		return rft->seq_show(of, m, arg);
+	return 0;
+}
+
+static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
+				   size_t nbytes, loff_t off)
+{
+	struct rftype *rft = of->kn->priv;
+
+	if (rft->write)
+		return rft->write(of, buf, nbytes, off);
+
+	return -EINVAL;
+}
+
+static struct kernfs_ops rdtgroup_kf_single_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.write			= rdtgroup_file_write,
+	.seq_show		= rdtgroup_seqfile_show,
+};
+
+static int rdtgroup_cpus_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp)
+		seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask));
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+/*
+ * This is safe against intel_rdt_sched_in() called from __switch_to()
+ * because __switch_to() is executed with interrupts disabled. A local call
+ * from rdt_update_closid() is proteced against __switch_to() because
+ * preemption is disabled.
+ */
+static void rdt_update_cpu_closid(void *closid)
+{
+	if (closid)
+		this_cpu_write(cpu_closid, *(int *)closid);
+	/*
+	 * We cannot unconditionally write the MSR because the current
+	 * executing task might have its own closid selected. Just reuse
+	 * the context switch code.
+	 */
+	intel_rdt_sched_in();
+}
+
+/*
+ * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
+ *
+ * Per task closids must have been set up before calling this function.
+ *
+ * The per cpu closids are updated with the smp function call, when @closid
+ * is not NULL. If @closid is NULL then all affected percpu closids must
+ * have been set up before calling this function.
+ */
+static void
+rdt_update_closid(const struct cpumask *cpu_mask, int *closid)
+{
+	int cpu = get_cpu();
+
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		rdt_update_cpu_closid(closid);
+	smp_call_function_many(cpu_mask, rdt_update_cpu_closid, closid, 1);
+	put_cpu();
+}
+
+static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	cpumask_var_t tmpmask, newmask;
+	struct rdtgroup *rdtgrp, *r;
+	int ret;
+
+	if (!buf)
+		return -EINVAL;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
+		free_cpumask_var(tmpmask);
+		return -ENOMEM;
+	}
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	ret = cpumask_parse(buf, newmask);
+	if (ret)
+		goto unlock;
+
+	/* check that user didn't specify any offline cpus */
+	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
+	if (cpumask_weight(tmpmask)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	/* Check whether cpus are dropped from this group */
+	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
+	if (cpumask_weight(tmpmask)) {
+		/* Can't drop from default group */
+		if (rdtgrp == &rdtgroup_default) {
+			ret = -EINVAL;
+			goto unlock;
+		}
+		/* Give any dropped cpus to rdtgroup_default */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, tmpmask);
+		rdt_update_closid(tmpmask, &rdtgroup_default.closid);
+	}
+
+	/*
+	 * If we added cpus, remove them from previous group that owned them
+	 * and update per-cpu closid
+	 */
+	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
+	if (cpumask_weight(tmpmask)) {
+		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
+			if (r == rdtgrp)
+				continue;
+			cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask);
+		}
+		rdt_update_closid(tmpmask, &rdtgrp->closid);
+	}
+
+	/* Done pushing/pulling - update this group with new mask */
+	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+
+unlock:
+	rdtgroup_kn_unlock(of->kn);
+	free_cpumask_var(tmpmask);
+	free_cpumask_var(newmask);
+
+	return ret ?: nbytes;
+}
+
+struct task_move_callback {
+	struct callback_head	work;
+	struct rdtgroup		*rdtgrp;
+};
+
+static void move_myself(struct callback_head *head)
+{
+	struct task_move_callback *callback;
+	struct rdtgroup *rdtgrp;
+
+	callback = container_of(head, struct task_move_callback, work);
+	rdtgrp = callback->rdtgrp;
+
+	/*
+	 * If resource group was deleted before this task work callback
+	 * was invoked, then assign the task to root group and free the
+	 * resource group.
+	 */
+	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
+	    (rdtgrp->flags & RDT_DELETED)) {
+		current->closid = 0;
+		kfree(rdtgrp);
+	}
+
+	preempt_disable();
+	/* update PQR_ASSOC MSR to make resource group go into effect */
+	intel_rdt_sched_in();
+	preempt_enable();
+
+	kfree(callback);
+}
+
+static int __rdtgroup_move_task(struct task_struct *tsk,
+				struct rdtgroup *rdtgrp)
+{
+	struct task_move_callback *callback;
+	int ret;
+
+	callback = kzalloc(sizeof(*callback), GFP_KERNEL);
+	if (!callback)
+		return -ENOMEM;
+	callback->work.func = move_myself;
+	callback->rdtgrp = rdtgrp;
+
+	/*
+	 * Take a refcount, so rdtgrp cannot be freed before the
+	 * callback has been invoked.
+	 */
+	atomic_inc(&rdtgrp->waitcount);
+	ret = task_work_add(tsk, &callback->work, true);
+	if (ret) {
+		/*
+		 * Task is exiting. Drop the refcount and free the callback.
+		 * No need to check the refcount as the group cannot be
+		 * deleted before the write function unlocks rdtgroup_mutex.
+		 */
+		atomic_dec(&rdtgrp->waitcount);
+		kfree(callback);
+	} else {
+		tsk->closid = rdtgrp->closid;
+	}
+	return ret;
+}
+
+static int rdtgroup_task_write_permission(struct task_struct *task,
+					  struct kernfs_open_file *of)
+{
+	const struct cred *tcred = get_task_cred(task);
+	const struct cred *cred = current_cred();
+	int ret = 0;
+
+	/*
+	 * Even if we're attaching all tasks in the thread group, we only
+	 * need to check permissions on one of them.
+	 */
+	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
+	    !uid_eq(cred->euid, tcred->uid) &&
+	    !uid_eq(cred->euid, tcred->suid))
+		ret = -EPERM;
+
+	put_cred(tcred);
+	return ret;
+}
+
+static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
+			      struct kernfs_open_file *of)
+{
+	struct task_struct *tsk;
+	int ret;
+
+	rcu_read_lock();
+	if (pid) {
+		tsk = find_task_by_vpid(pid);
+		if (!tsk) {
+			rcu_read_unlock();
+			return -ESRCH;
+		}
+	} else {
+		tsk = current;
+	}
+
+	get_task_struct(tsk);
+	rcu_read_unlock();
+
+	ret = rdtgroup_task_write_permission(tsk, of);
+	if (!ret)
+		ret = __rdtgroup_move_task(tsk, rdtgrp);
+
+	put_task_struct(tsk);
+	return ret;
+}
+
+static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+	pid_t pid;
+
+	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
+		return -EINVAL;
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp)
+		ret = rdtgroup_move_task(pid, rdtgrp, of);
+	else
+		ret = -ENOENT;
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret ?: nbytes;
+}
+
+static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
+{
+	struct task_struct *p, *t;
+
+	rcu_read_lock();
+	for_each_process_thread(p, t) {
+		if (t->closid == r->closid)
+			seq_printf(s, "%d\n", t->pid);
+	}
+	rcu_read_unlock();
+}
+
+static int rdtgroup_tasks_show(struct kernfs_open_file *of,
+			       struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp)
+		show_rdt_tasks(rdtgrp, s);
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+/* Files in each rdtgroup */
+static struct rftype rdtgroup_base_files[] = {
+	{
+		.name		= "cpus",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+	},
+	{
+		.name		= "tasks",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_tasks_write,
+		.seq_show	= rdtgroup_tasks_show,
+	},
+	{
+		.name		= "schemata",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_schemata_write,
+		.seq_show	= rdtgroup_schemata_show,
+	},
+};
+
+static int rdt_num_closids_show(struct kernfs_open_file *of,
+				struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%d\n", r->num_closid);
+
+	return 0;
+}
+
+static int rdt_cbm_mask_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%x\n", r->max_cbm);
+
+	return 0;
+}
+
+static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+
+	seq_printf(seq, "%d\n", r->min_cbm_bits);
+
+	return 0;
+}
+
+/* rdtgroup information files for one cache resource. */
+static struct rftype res_info_files[] = {
+	{
+		.name		= "num_closids",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_num_closids_show,
+	},
+	{
+		.name		= "cbm_mask",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_cbm_mask_show,
+	},
+	{
+		.name		= "min_cbm_bits",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_min_cbm_bits_show,
+	},
+};
+
+static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
+{
+	struct kernfs_node *kn_subdir;
+	struct rdt_resource *r;
+	int ret;
+
+	/* create the directory */
+	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
+	if (IS_ERR(kn_info))
+		return PTR_ERR(kn_info);
+	kernfs_get(kn_info);
+
+	for_each_enabled_rdt_resource(r) {
+		kn_subdir = kernfs_create_dir(kn_info, r->name,
+					      kn_info->mode, r);
+		if (IS_ERR(kn_subdir)) {
+			ret = PTR_ERR(kn_subdir);
+			goto out_destroy;
+		}
+		kernfs_get(kn_subdir);
+		ret = rdtgroup_kn_set_ugid(kn_subdir);
+		if (ret)
+			goto out_destroy;
+		ret = rdtgroup_add_files(kn_subdir, res_info_files,
+					 ARRAY_SIZE(res_info_files));
+		if (ret)
+			goto out_destroy;
+		kernfs_activate(kn_subdir);
+	}
+
+	/*
+	 * This extra ref will be put in kernfs_remove() and guarantees
+	 * that @rdtgrp->kn is always accessible.
+	 */
+	kernfs_get(kn_info);
+
+	ret = rdtgroup_kn_set_ugid(kn_info);
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn_info);
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn_info);
+	return ret;
+}
+
+static void l3_qos_cfg_update(void *arg)
+{
+	bool *enable = arg;
+
+	wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
+}
+
+static int set_l3_qos_cfg(struct rdt_resource *r, bool enable)
+{
+	cpumask_var_t cpu_mask;
+	struct rdt_domain *d;
+	int cpu;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	list_for_each_entry(d, &r->domains, list) {
+		/* Pick one CPU from each domain instance to update MSR */
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+	}
+	cpu = get_cpu();
+	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		l3_qos_cfg_update(&enable);
+	/* Update QOS_CFG MSR on all other cpus in cpu_mask. */
+	smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+static int cdp_enable(void)
+{
+	struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA];
+	struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE];
+	struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3];
+	int ret;
+
+	if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable)
+		return -EINVAL;
+
+	ret = set_l3_qos_cfg(r_l3, true);
+	if (!ret) {
+		r_l3->enabled = false;
+		r_l3data->enabled = true;
+		r_l3code->enabled = true;
+	}
+	return ret;
+}
+
+static void cdp_disable(void)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	r->enabled = r->capable;
+
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) {
+		rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false;
+		rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false;
+		set_l3_qos_cfg(r, false);
+	}
+}
+
+static int parse_rdtgroupfs_options(char *data)
+{
+	char *token, *o = data;
+	int ret = 0;
+
+	while ((token = strsep(&o, ",")) != NULL) {
+		if (!*token)
+			return -EINVAL;
+
+		if (!strcmp(token, "cdp"))
+			ret = cdp_enable();
+	}
+
+	return ret;
+}
+
+/*
+ * We don't allow rdtgroup directories to be created anywhere
+ * except the root directory. Thus when looking for the rdtgroup
+ * structure for a kernfs node we are either looking at a directory,
+ * in which case the rdtgroup structure is pointed at by the "priv"
+ * field, otherwise we have a file, and need only look to the parent
+ * to find the rdtgroup.
+ */
+static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
+{
+	if (kernfs_type(kn) == KERNFS_DIR) {
+		/*
+		 * All the resource directories use "kn->priv"
+		 * to point to the "struct rdtgroup" for the
+		 * resource. "info" and its subdirectories don't
+		 * have rdtgroup structures, so return NULL here.
+		 */
+		if (kn == kn_info || kn->parent == kn_info)
+			return NULL;
+		else
+			return kn->priv;
+	} else {
+		return kn->parent->priv;
+	}
+}
+
+struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
+{
+	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
+
+	if (!rdtgrp)
+		return NULL;
+
+	atomic_inc(&rdtgrp->waitcount);
+	kernfs_break_active_protection(kn);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	/* Was this group deleted while we waited? */
+	if (rdtgrp->flags & RDT_DELETED)
+		return NULL;
+
+	return rdtgrp;
+}
+
+void rdtgroup_kn_unlock(struct kernfs_node *kn)
+{
+	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
+
+	if (!rdtgrp)
+		return;
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
+	    (rdtgrp->flags & RDT_DELETED)) {
+		kernfs_unbreak_active_protection(kn);
+		kernfs_put(kn);
+		kfree(rdtgrp);
+	} else {
+		kernfs_unbreak_active_protection(kn);
+	}
+}
+
+static struct dentry *rdt_mount(struct file_system_type *fs_type,
+				int flags, const char *unused_dev_name,
+				void *data)
+{
+	struct dentry *dentry;
+	int ret;
+
+	mutex_lock(&rdtgroup_mutex);
+	/*
+	 * resctrl file system can only be mounted once.
+	 */
+	if (static_branch_unlikely(&rdt_enable_key)) {
+		dentry = ERR_PTR(-EBUSY);
+		goto out;
+	}
+
+	ret = parse_rdtgroupfs_options(data);
+	if (ret) {
+		dentry = ERR_PTR(ret);
+		goto out_cdp;
+	}
+
+	closid_init();
+
+	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
+	if (ret) {
+		dentry = ERR_PTR(ret);
+		goto out_cdp;
+	}
+
+	dentry = kernfs_mount(fs_type, flags, rdt_root,
+			      RDTGROUP_SUPER_MAGIC, NULL);
+	if (IS_ERR(dentry))
+		goto out_cdp;
+
+	static_branch_enable(&rdt_enable_key);
+	goto out;
+
+out_cdp:
+	cdp_disable();
+out:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return dentry;
+}
+
+static int reset_all_cbms(struct rdt_resource *r)
+{
+	struct msr_param msr_param;
+	cpumask_var_t cpu_mask;
+	struct rdt_domain *d;
+	int i, cpu;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	msr_param.res = r;
+	msr_param.low = 0;
+	msr_param.high = r->num_closid;
+
+	/*
+	 * Disable resource control for this resource by setting all
+	 * CBMs in all domains to the maximum mask value. Pick one CPU
+	 * from each domain to update the MSRs below.
+	 */
+	list_for_each_entry(d, &r->domains, list) {
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+
+		for (i = 0; i < r->num_closid; i++)
+			d->cbm[i] = r->max_cbm;
+	}
+	cpu = get_cpu();
+	/* Update CBM on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		rdt_cbm_update(&msr_param);
+	/* Update CBM on all other cpus in cpu_mask. */
+	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+/*
+ * Move tasks from one to the other group. If @from is NULL, then all tasks
+ * in the systems are moved unconditionally (used for teardown).
+ *
+ * If @mask is not NULL the cpus on which moved tasks are running are set
+ * in that mask so the update smp function call is restricted to affected
+ * cpus.
+ */
+static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
+				 struct cpumask *mask)
+{
+	struct task_struct *p, *t;
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(p, t) {
+		if (!from || t->closid == from->closid) {
+			t->closid = to->closid;
+#ifdef CONFIG_SMP
+			/*
+			 * This is safe on x86 w/o barriers as the ordering
+			 * of writing to task_cpu() and t->on_cpu is
+			 * reverse to the reading here. The detection is
+			 * inaccurate as tasks might move or schedule
+			 * before the smp function call takes place. In
+			 * such a case the function call is pointless, but
+			 * there is no other side effect.
+			 */
+			if (mask && t->on_cpu)
+				cpumask_set_cpu(task_cpu(t), mask);
+#endif
+		}
+	}
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * Forcibly remove all of subdirectories under root.
+ */
+static void rmdir_all_sub(void)
+{
+	struct rdtgroup *rdtgrp, *tmp;
+
+	/* Move all tasks to the default resource group */
+	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
+
+	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
+		/* Remove each rdtgroup other than root */
+		if (rdtgrp == &rdtgroup_default)
+			continue;
+
+		/*
+		 * Give any CPUs back to the default group. We cannot copy
+		 * cpu_online_mask because a CPU might have executed the
+		 * offline callback already, but is still marked online.
+		 */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
+
+		kernfs_remove(rdtgrp->kn);
+		list_del(&rdtgrp->rdtgroup_list);
+		kfree(rdtgrp);
+	}
+	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
+	get_online_cpus();
+	rdt_update_closid(cpu_online_mask, &rdtgroup_default.closid);
+	put_online_cpus();
+
+	kernfs_remove(kn_info);
+}
+
+static void rdt_kill_sb(struct super_block *sb)
+{
+	struct rdt_resource *r;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	/*Put everything back to default values. */
+	for_each_enabled_rdt_resource(r)
+		reset_all_cbms(r);
+	cdp_disable();
+	rmdir_all_sub();
+	static_branch_disable(&rdt_enable_key);
+	kernfs_kill_sb(sb);
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static struct file_system_type rdt_fs_type = {
+	.name    = "resctrl",
+	.mount   = rdt_mount,
+	.kill_sb = rdt_kill_sb,
+};
+
+static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+			  umode_t mode)
+{
+	struct rdtgroup *parent, *rdtgrp;
+	struct kernfs_node *kn;
+	int ret, closid;
+
+	/* Only allow mkdir in the root directory */
+	if (parent_kn != rdtgroup_default.kn)
+		return -EPERM;
+
+	/* Do not accept '\n' to avoid unparsable situation. */
+	if (strchr(name, '\n'))
+		return -EINVAL;
+
+	parent = rdtgroup_kn_lock_live(parent_kn);
+	if (!parent) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	ret = closid_alloc();
+	if (ret < 0)
+		goto out_unlock;
+	closid = ret;
+
+	/* allocate the rdtgroup. */
+	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
+	if (!rdtgrp) {
+		ret = -ENOSPC;
+		goto out_closid_free;
+	}
+	rdtgrp->closid = closid;
+	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
+
+	/* kernfs creates the directory for rdtgrp */
+	kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp);
+	if (IS_ERR(kn)) {
+		ret = PTR_ERR(kn);
+		goto out_cancel_ref;
+	}
+	rdtgrp->kn = kn;
+
+	/*
+	 * kernfs_remove() will drop the reference count on "kn" which
+	 * will free it. But we still need it to stick around for the
+	 * rdtgroup_kn_unlock(kn} call below. Take one extra reference
+	 * here, which will be dropped inside rdtgroup_kn_unlock().
+	 */
+	kernfs_get(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
+
+	ret = rdtgroup_add_files(kn, rdtgroup_base_files,
+				 ARRAY_SIZE(rdtgroup_base_files));
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn);
+
+	ret = 0;
+	goto out_unlock;
+
+out_destroy:
+	kernfs_remove(rdtgrp->kn);
+out_cancel_ref:
+	list_del(&rdtgrp->rdtgroup_list);
+	kfree(rdtgrp);
+out_closid_free:
+	closid_free(closid);
+out_unlock:
+	rdtgroup_kn_unlock(parent_kn);
+	return ret;
+}
+
+static int rdtgroup_rmdir(struct kernfs_node *kn)
+{
+	int ret, cpu, closid = rdtgroup_default.closid;
+	struct rdtgroup *rdtgrp;
+	cpumask_var_t tmpmask;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+
+	rdtgrp = rdtgroup_kn_lock_live(kn);
+	if (!rdtgrp) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	/* Give any tasks back to the default group */
+	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);
+
+	/* Give any CPUs back to the default group */
+	cpumask_or(&rdtgroup_default.cpu_mask,
+		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
+
+	/* Update per cpu closid of the moved CPUs first */
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		per_cpu(cpu_closid, cpu) = closid;
+	/*
+	 * Update the MSR on moved CPUs and CPUs which have moved
+	 * task running on them.
+	 */
+	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
+	rdt_update_closid(tmpmask, NULL);
+
+	rdtgrp->flags = RDT_DELETED;
+	closid_free(rdtgrp->closid);
+	list_del(&rdtgrp->rdtgroup_list);
+
+	/*
+	 * one extra hold on this, will drop when we kfree(rdtgrp)
+	 * in rdtgroup_kn_unlock()
+	 */
+	kernfs_get(kn);
+	kernfs_remove(rdtgrp->kn);
+	ret = 0;
+out:
+	rdtgroup_kn_unlock(kn);
+	free_cpumask_var(tmpmask);
+	return ret;
+}
+
+static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
+{
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled)
+		seq_puts(seq, ",cdp");
+	return 0;
+}
+
+static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
+	.mkdir		= rdtgroup_mkdir,
+	.rmdir		= rdtgroup_rmdir,
+	.show_options	= rdtgroup_show_options,
+};
+
+static int __init rdtgroup_setup_root(void)
+{
+	int ret;
+
+	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
+				      KERNFS_ROOT_CREATE_DEACTIVATED,
+				      &rdtgroup_default);
+	if (IS_ERR(rdt_root))
+		return PTR_ERR(rdt_root);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgroup_default.closid = 0;
+	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
+
+	ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files,
+				 ARRAY_SIZE(rdtgroup_base_files));
+	if (ret) {
+		kernfs_destroy_root(rdt_root);
+		goto out;
+	}
+
+	rdtgroup_default.kn = rdt_root->kn;
+	kernfs_activate(rdtgroup_default.kn);
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return ret;
+}
+
+/*
+ * rdtgroup_init - rdtgroup initialization
+ *
+ * Setup resctrl file system including set up root, create mount point,
+ * register rdtgroup filesystem, and initialize files under root directory.
+ *
+ * Return: 0 on success or -errno
+ */
+int __init rdtgroup_init(void)
+{
+	int ret = 0;
+
+	ret = rdtgroup_setup_root();
+	if (ret)
+		return ret;
+
+	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
+	if (ret)
+		goto cleanup_root;
+
+	ret = register_filesystem(&rdt_fs_type);
+	if (ret)
+		goto cleanup_mountpoint;
+
+	return 0;
+
+cleanup_mountpoint:
+	sysfs_remove_mount_point(fs_kobj, "resctrl");
+cleanup_root:
+	kernfs_destroy_root(rdt_root);
+
+	return ret;
+}
diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c
new file mode 100644
index 0000000..f369cb8
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c
@@ -0,0 +1,245 @@
+/*
+ * Resource Director Technology(RDT)
+ * - Cache Allocation code.
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Authors:
+ *    Fenghua Yu <fenghua.yu@intel.com>
+ *    Tony Luck <tony.luck@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual June 2016, volume 3, section 17.17.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/kernfs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <asm/intel_rdt.h>
+
+/*
+ * Check whether a cache bit mask is valid. The SDM says:
+ *	Please note that all (and only) contiguous '1' combinations
+ *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
+ * Additionally Haswell requires at least two bits set.
+ */
+static bool cbm_validate(unsigned long var, struct rdt_resource *r)
+{
+	unsigned long first_bit, zero_bit;
+
+	if (var == 0 || var > r->max_cbm)
+		return false;
+
+	first_bit = find_first_bit(&var, r->cbm_len);
+	zero_bit = find_next_zero_bit(&var, r->cbm_len, first_bit);
+
+	if (find_next_bit(&var, r->cbm_len, zero_bit) < r->cbm_len)
+		return false;
+
+	if ((zero_bit - first_bit) < r->min_cbm_bits)
+		return false;
+	return true;
+}
+
+/*
+ * Read one cache bit mask (hex). Check that it is valid for the current
+ * resource type.
+ */
+static int parse_cbm(char *buf, struct rdt_resource *r)
+{
+	unsigned long data;
+	int ret;
+
+	ret = kstrtoul(buf, 16, &data);
+	if (ret)
+		return ret;
+	if (!cbm_validate(data, r))
+		return -EINVAL;
+	r->tmp_cbms[r->num_tmp_cbms++] = data;
+
+	return 0;
+}
+
+/*
+ * For each domain in this resource we expect to find a series of:
+ *	id=mask
+ * separated by ";". The "id" is in decimal, and must appear in the
+ * right order.
+ */
+static int parse_line(char *line, struct rdt_resource *r)
+{
+	char *dom = NULL, *id;
+	struct rdt_domain *d;
+	unsigned long dom_id;
+
+	list_for_each_entry(d, &r->domains, list) {
+		dom = strsep(&line, ";");
+		if (!dom)
+			return -EINVAL;
+		id = strsep(&dom, "=");
+		if (kstrtoul(id, 10, &dom_id) || dom_id != d->id)
+			return -EINVAL;
+		if (parse_cbm(dom, r))
+			return -EINVAL;
+	}
+
+	/* Any garbage at the end of the line? */
+	if (line && line[0])
+		return -EINVAL;
+	return 0;
+}
+
+static int update_domains(struct rdt_resource *r, int closid)
+{
+	struct msr_param msr_param;
+	cpumask_var_t cpu_mask;
+	struct rdt_domain *d;
+	int cpu, idx = 0;
+
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	msr_param.low = closid;
+	msr_param.high = msr_param.low + 1;
+	msr_param.res = r;
+
+	list_for_each_entry(d, &r->domains, list) {
+		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+		d->cbm[msr_param.low] = r->tmp_cbms[idx++];
+	}
+	cpu = get_cpu();
+	/* Update CBM on this cpu if it's in cpu_mask. */
+	if (cpumask_test_cpu(cpu, cpu_mask))
+		rdt_cbm_update(&msr_param);
+	/* Update CBM on other cpus. */
+	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	put_cpu();
+
+	free_cpumask_var(cpu_mask);
+
+	return 0;
+}
+
+ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	char *tok, *resname;
+	int closid, ret = 0;
+	u32 *l3_cbms = NULL;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	closid = rdtgrp->closid;
+
+	/* get scratch space to save all the masks while we validate input */
+	for_each_enabled_rdt_resource(r) {
+		r->tmp_cbms = kcalloc(r->num_domains, sizeof(*l3_cbms),
+				      GFP_KERNEL);
+		if (!r->tmp_cbms) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		r->num_tmp_cbms = 0;
+	}
+
+	while ((tok = strsep(&buf, "\n")) != NULL) {
+		resname = strsep(&tok, ":");
+		if (!tok) {
+			ret = -EINVAL;
+			goto out;
+		}
+		for_each_enabled_rdt_resource(r) {
+			if (!strcmp(resname, r->name) &&
+			    closid < r->num_closid) {
+				ret = parse_line(tok, r);
+				if (ret)
+					goto out;
+				break;
+			}
+		}
+		if (!r->name) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	/* Did the parser find all the masks we need? */
+	for_each_enabled_rdt_resource(r) {
+		if (r->num_tmp_cbms != r->num_domains) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	for_each_enabled_rdt_resource(r) {
+		ret = update_domains(r, closid);
+		if (ret)
+			goto out;
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	for_each_enabled_rdt_resource(r) {
+		kfree(r->tmp_cbms);
+		r->tmp_cbms = NULL;
+	}
+	return ret ?: nbytes;
+}
+
+static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
+{
+	struct rdt_domain *dom;
+	bool sep = false;
+
+	seq_printf(s, "%s:", r->name);
+	list_for_each_entry(dom, &r->domains, list) {
+		if (sep)
+			seq_puts(s, ";");
+		seq_printf(s, "%d=%x", dom->id, dom->cbm[closid]);
+		sep = true;
+	}
+	seq_puts(s, "\n");
+}
+
+int rdtgroup_schemata_show(struct kernfs_open_file *of,
+			   struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	int closid, ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp) {
+		closid = rdtgrp->closid;
+		for_each_enabled_rdt_resource(r) {
+			if (closid < r->num_closid)
+				show_doms(s, r, closid);
+		}
+	} else {
+		ret = -ENOENT;
+	}
+	rdtgroup_kn_unlock(of->kn);
+	return ret;
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index c7efbcf..87cc9ab 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -14,7 +14,7 @@
 #include <linux/init.h>
 #include <linux/debugfs.h>
 #include <asm/mce.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "mce-internal.h"
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index ffacfdc..a5fd137 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1182,6 +1182,9 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	const char *name = get_name(bank, NULL);
 	int err = 0;
 
+	if (!dev)
+		return -ENODEV;
+
 	if (is_shared_bank(bank)) {
 		nb = node_to_amd_nb(amd_get_nb_id(cpu));
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 6f353bd..6a31e26 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -116,10 +116,11 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
 
 /*
  * This scans the ucode blob for the proper container as we can have multiple
- * containers glued together.
+ * containers glued together. Returns the equivalence ID from the equivalence
+ * table or 0 if none found.
  */
-static struct container
-find_proper_container(u8 *ucode, size_t size, u16 *ret_id)
+static u16
+find_proper_container(u8 *ucode, size_t size, struct container *ret_cont)
 {
 	struct container ret = { NULL, 0 };
 	u32 eax, ebx, ecx, edx;
@@ -138,7 +139,7 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id)
 	if (header[0] != UCODE_MAGIC ||
 	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
 	    header[2] == 0)                            /* size */
-		return ret;
+		return eq_id;
 
 	eax = 0x00000001;
 	ecx = 0;
@@ -163,8 +164,9 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id)
 			 * ucode update loop below
 			 */
 			left = ret.size - offset;
-			*ret_id = eq_id;
-			return ret;
+
+			*ret_cont = ret;
+			return eq_id;
 		}
 
 		/*
@@ -189,7 +191,7 @@ find_proper_container(u8 *ucode, size_t size, u16 *ret_id)
 		ucode     = data;
 	}
 
-	return ret;
+	return eq_id;
 }
 
 static int __apply_microcode_amd(struct microcode_amd *mc_amd)
@@ -214,17 +216,18 @@ static int __apply_microcode_amd(struct microcode_amd *mc_amd)
  * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
  * load_microcode_amd() to save equivalent cpu table and microcode patches in
  * kernel heap memory.
+ *
+ * Returns true if container found (sets @ret_cont), false otherwise.
  */
-static struct container
-apply_microcode_early_amd(void *ucode, size_t size, bool save_patch)
+static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch,
+				      struct container *ret_cont)
 {
-	struct container ret = { NULL, 0 };
 	u8 (*patch)[PATCH_MAX_SIZE];
+	u32 rev, *header, *new_rev;
+	struct container ret;
 	int offset, left;
-	u32 rev, *header;
-	u8  *data;
 	u16 eq_id = 0;
-	u32 *new_rev;
+	u8  *data;
 
 #ifdef CONFIG_X86_32
 	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
@@ -235,11 +238,11 @@ apply_microcode_early_amd(void *ucode, size_t size, bool save_patch)
 #endif
 
 	if (check_current_patch_level(&rev, true))
-		return (struct container){ NULL, 0 };
+		return false;
 
-	ret = find_proper_container(ucode, size, &eq_id);
+	eq_id = find_proper_container(ucode, size, &ret);
 	if (!eq_id)
-		return (struct container){ NULL, 0 };
+		return false;
 
 	this_equiv_id = eq_id;
 	header = (u32 *)ret.data;
@@ -273,7 +276,11 @@ apply_microcode_early_amd(void *ucode, size_t size, bool save_patch)
 		data   += offset;
 		left   -= offset;
 	}
-	return ret;
+
+	if (ret_cont)
+		*ret_cont = ret;
+
+	return true;
 }
 
 static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
@@ -294,6 +301,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
 void __init load_ucode_amd_bsp(unsigned int family)
 {
 	struct ucode_cpu_info *uci;
+	u32 eax, ebx, ecx, edx;
 	struct cpio_data cp;
 	const char *path;
 	bool use_pa;
@@ -315,9 +323,12 @@ void __init load_ucode_amd_bsp(unsigned int family)
 		return;
 
 	/* Get BSP's CPUID.EAX(1), needed in load_microcode_amd() */
-	uci->cpu_sig.sig = cpuid_eax(1);
+	eax = 1;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+	uci->cpu_sig.sig = eax;
 
-	apply_microcode_early_amd(cp.data, cp.size, true);
+	apply_microcode_early_amd(cp.data, cp.size, true, NULL);
 }
 
 #ifdef CONFIG_X86_32
@@ -349,7 +360,7 @@ void load_ucode_amd_ap(unsigned int family)
 	 * This would set amd_ucode_patch above so that the following APs can
 	 * use it directly instead of going down this path again.
 	 */
-	apply_microcode_early_amd(cp.data, cp.size, true);
+	apply_microcode_early_amd(cp.data, cp.size, true, NULL);
 }
 #else
 void load_ucode_amd_ap(unsigned int family)
@@ -387,8 +398,7 @@ void load_ucode_amd_ap(unsigned int family)
 			}
 		}
 
-		cont = apply_microcode_early_amd(cp.data, cp.size, false);
-		if (!(cont.data && cont.size)) {
+		if (!apply_microcode_early_amd(cp.data, cp.size, false, &cont)) {
 			cont.size = -1;
 			return;
 		}
@@ -443,7 +453,7 @@ int __init save_microcode_in_initrd_amd(unsigned int fam)
 				return -EINVAL;
 			}
 
-			cont = find_proper_container(cp.data, cp.size, &eq_id);
+			eq_id = find_proper_container(cp.data, cp.size, &cont);
 			if (!eq_id) {
 				cont.size = -1;
 				return -EINVAL;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 6996413..2af69d2 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -44,7 +44,7 @@
 #define DRIVER_VERSION	"2.2"
 
 static struct microcode_ops	*microcode_ops;
-static bool dis_ucode_ldr;
+static bool dis_ucode_ldr = true;
 
 LIST_HEAD(microcode_cache);
 
@@ -76,6 +76,7 @@ struct cpu_info_ctx {
 static bool __init check_loader_disabled_bsp(void)
 {
 	static const char *__dis_opt_str = "dis_ucode_ldr";
+	u32 a, b, c, d;
 
 #ifdef CONFIG_X86_32
 	const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
@@ -88,8 +89,23 @@ static bool __init check_loader_disabled_bsp(void)
 	bool *res = &dis_ucode_ldr;
 #endif
 
-	if (cmdline_find_option_bool(cmdline, option))
-		*res = true;
+	if (!have_cpuid_p())
+		return *res;
+
+	a = 1;
+	c = 0;
+	native_cpuid(&a, &b, &c, &d);
+
+	/*
+	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
+	 * completely accurate as xen pv guests don't see that CPUID bit set but
+	 * that's good enough as they don't land on the BSP path anyway.
+	 */
+	if (c & BIT(31))
+		return *res;
+
+	if (cmdline_find_option_bool(cmdline, option) <= 0)
+		*res = false;
 
 	return *res;
 }
@@ -121,9 +137,6 @@ void __init load_ucode_bsp(void)
 	if (check_loader_disabled_bsp())
 		return;
 
-	if (!have_cpuid_p())
-		return;
-
 	vendor = x86_cpuid_vendor();
 	family = x86_cpuid_family();
 
@@ -157,9 +170,6 @@ void load_ucode_ap(void)
 	if (check_loader_disabled_ap())
 		return;
 
-	if (!have_cpuid_p())
-		return;
-
 	vendor = x86_cpuid_vendor();
 	family = x86_cpuid_family();
 
@@ -233,14 +243,12 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
 # endif
 
 	/*
-	 * Did we relocate the ramdisk?
-	 *
-	 * So we possibly relocate the ramdisk *after* applying microcode on the
-	 * BSP so we rely on use_pa (use physical addresses) - even if it is not
-	 * absolutely correct - to determine whether we've done the ramdisk
-	 * relocation already.
+	 * Fixup the start address: after reserve_initrd() runs, initrd_start
+	 * has the virtual address of the beginning of the initrd. It also
+	 * possibly relocates the ramdisk. In either case, initrd_start contains
+	 * the updated address so use that instead.
 	 */
-	if (!use_pa && relocated_ramdisk)
+	if (!use_pa && initrd_start)
 		start = initrd_start;
 
 	return find_cpio_data(path, (void *)start, size, NULL);
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 54d50c3..b624b54 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -368,6 +368,26 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save)
 	return patch;
 }
 
+static void cpuid_1(void)
+{
+	/*
+	 * According to the Intel SDM, Volume 3, 9.11.7:
+	 *
+	 *   CPUID returns a value in a model specific register in
+	 *   addition to its usual register return values. The
+	 *   semantics of CPUID cause it to deposit an update ID value
+	 *   in the 64-bit model-specific register at address 08BH
+	 *   (IA32_BIOS_SIGN_ID). If no update is present in the
+	 *   processor, the value in the MSR remains unmodified.
+	 *
+	 * Use native_cpuid -- this code runs very early and we don't
+	 * want to mess with paravirt.
+	 */
+	unsigned int eax = 1, ebx, ecx = 0, edx;
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+}
+
 static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 {
 	unsigned int val[2];
@@ -393,7 +413,7 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
+	cpuid_1();
 
 	/* get the current revision from MSR 0x8B */
 	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
@@ -593,7 +613,7 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
+	cpuid_1();
 
 	/* get the current revision from MSR 0x8B */
 	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
@@ -805,7 +825,7 @@ static int apply_microcode_intel(int cpu)
 	wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
+	cpuid_1();
 
 	/* get the current revision from MSR 0x8B */
 	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 6c04454..65e20c9 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -30,6 +30,7 @@
 #include <asm/apic.h>
 #include <asm/timer.h>
 #include <asm/reboot.h>
+#include <asm/nmi.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -132,9 +133,9 @@ static uint32_t  __init ms_hyperv_platform(void)
 	return 0;
 }
 
-static cycle_t read_hv_clock(struct clocksource *arg)
+static u64 read_hv_clock(struct clocksource *arg)
 {
-	cycle_t current_tick;
+	u64 current_tick;
 	/*
 	 * Read the partition counter to get the current tick count. This count
 	 * is set to 0 when the partition is created and is incremented in
@@ -157,6 +158,26 @@ static unsigned char hv_get_nmi_reason(void)
 	return 0;
 }
 
+#ifdef CONFIG_X86_LOCAL_APIC
+/*
+ * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes
+ * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle
+ * unknown NMI on the first CPU which gets it.
+ */
+static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
+{
+	static atomic_t nmi_cpu = ATOMIC_INIT(-1);
+
+	if (!unknown_nmi_panic)
+		return NMI_DONE;
+
+	if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1)
+		return NMI_HANDLED;
+
+	return NMI_DONE;
+}
+#endif
+
 static void __init ms_hyperv_init_platform(void)
 {
 	/*
@@ -182,6 +203,9 @@ static void __init ms_hyperv_init_platform(void)
 		pr_info("HyperV: LAPIC Timer Frequency: %#x\n",
 			lapic_timer_frequency);
 	}
+
+	register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST,
+			     "hv_nmi_unknown");
 #endif
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index d1316f9..d979406 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -20,12 +20,15 @@ struct cpuid_bit {
 /* Please keep the leaf sorted by cpuid_bit.level for faster search. */
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
-	{ X86_FEATURE_EPB,              CPUID_ECX,  3, 0x00000006, 0 },
-	{ X86_FEATURE_INTEL_PT,         CPUID_EBX, 25, 0x00000007, 0 },
+	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_INTEL_PT,		CPUID_EBX, 25, 0x00000007, 0 },
 	{ X86_FEATURE_AVX512_4VNNIW,    CPUID_EDX,  2, 0x00000007, 0 },
 	{ X86_FEATURE_AVX512_4FMAPS,    CPUID_EDX,  3, 0x00000007, 0 },
-	{ X86_FEATURE_HW_PSTATE,        CPUID_EDX,  7, 0x80000007, 0 },
-	{ X86_FEATURE_CPB,              CPUID_EDX,  9, 0x80000007, 0 },
+	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
+	{ X86_FEATURE_CAT_L2,		CPUID_EBX,  2, 0x00000010, 0 },
+	{ X86_FEATURE_CDP_L3,		CPUID_ECX,  2, 0x00000010, 1 },
+	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
+	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index 11891ca..538fede 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -10,7 +10,7 @@
 #include <linux/highmem.h>
 #include <linux/crash_dump.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static void *kdump_buf_page;
 
diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c
index f6dfd93..b2f7207 100644
--- a/arch/x86/kernel/doublefault.c
+++ b/arch/x86/kernel/doublefault.c
@@ -3,7 +3,7 @@
 #include <linux/init_task.h>
 #include <linux/fs.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 274fab9..85e87b4 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -791,7 +791,7 @@ static union hpet_lock hpet __cacheline_aligned = {
 	{ .lock = __ARCH_SPIN_LOCK_UNLOCKED, },
 };
 
-static cycle_t read_hpet(struct clocksource *cs)
+static u64 read_hpet(struct clocksource *cs)
 {
 	unsigned long flags;
 	union hpet_lock old, new;
@@ -802,7 +802,7 @@ static cycle_t read_hpet(struct clocksource *cs)
 	 * Read HPET directly if in NMI.
 	 */
 	if (in_nmi())
-		return (cycle_t)hpet_readl(HPET_COUNTER);
+		return (u64)hpet_readl(HPET_COUNTER);
 
 	/*
 	 * Read the current state of the lock and HPET value atomically.
@@ -821,7 +821,7 @@ static cycle_t read_hpet(struct clocksource *cs)
 		WRITE_ONCE(hpet.value, new.value);
 		arch_spin_unlock(&hpet.lock);
 		local_irq_restore(flags);
-		return (cycle_t)new.value;
+		return (u64)new.value;
 	}
 	local_irq_restore(flags);
 
@@ -843,15 +843,15 @@ static cycle_t read_hpet(struct clocksource *cs)
 		new.lockval = READ_ONCE(hpet.lockval);
 	} while ((new.value == old.value) && arch_spin_is_locked(&new.lock));
 
-	return (cycle_t)new.value;
+	return (u64)new.value;
 }
 #else
 /*
  * For UP or 32-bit.
  */
-static cycle_t read_hpet(struct clocksource *cs)
+static u64 read_hpet(struct clocksource *cs)
 {
-	return (cycle_t)hpet_readl(HPET_COUNTER);
+	return (u64)hpet_readl(HPET_COUNTER);
 }
 #endif
 
@@ -867,7 +867,7 @@ static struct clocksource clocksource_hpet = {
 static int hpet_clocksource_register(void)
 {
 	u64 start, now;
-	cycle_t t1;
+	u64 t1;
 
 	/* Start the counter */
 	hpet_restart_counter();
@@ -1051,11 +1051,11 @@ static __init int hpet_late_init(void)
 		return 0;
 
 	/* This notifier should be called after workqueue is ready */
-	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE",
+	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "x86/hpet:online",
 				hpet_cpuhp_online, NULL);
 	if (ret)
 		return ret;
-	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL,
+	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "x86/hpet:dead", NULL,
 				hpet_cpuhp_dead);
 	if (ret)
 		goto err_cpuhp;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index d9d8d16..eb35093 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -56,7 +56,7 @@
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/alternative.h>
 #include <asm/insn.h>
 #include <asm/debugreg.h>
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3bb4c5f..3d1bee9 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -33,7 +33,7 @@
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/alternative.h>
 #include <asm/insn.h>
 #include <asm/debugreg.h>
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 60b9949..2a5cafd 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -32,7 +32,7 @@
 static int kvmclock __ro_after_init = 1;
 static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
 static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
-static cycle_t kvm_sched_clock_offset;
+static u64 kvm_sched_clock_offset;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -79,10 +79,10 @@ static int kvm_set_wallclock(const struct timespec *now)
 	return -1;
 }
 
-static cycle_t kvm_clock_read(void)
+static u64 kvm_clock_read(void)
 {
 	struct pvclock_vcpu_time_info *src;
-	cycle_t ret;
+	u64 ret;
 	int cpu;
 
 	preempt_disable_notrace();
@@ -93,12 +93,12 @@ static cycle_t kvm_clock_read(void)
 	return ret;
 }
 
-static cycle_t kvm_clock_get_cycles(struct clocksource *cs)
+static u64 kvm_clock_get_cycles(struct clocksource *cs)
 {
 	return kvm_clock_read();
 }
 
-static cycle_t kvm_sched_clock_read(void)
+static u64 kvm_sched_clock_read(void)
 {
 	return kvm_clock_read() - kvm_sched_clock_offset;
 }
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index f5e3ff8..ef68880 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -224,7 +224,6 @@ static int __init msr_init(void)
 	return 0;
 
 out_class:
-	cpuhp_remove_state(cpuhp_msr_state);
 	class_destroy(msr_class);
 out_chrdev:
 	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index d33ef16..553acbb 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -68,7 +68,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 #endif
 
 	default:
-patch_default:
+patch_default: __maybe_unused
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
 
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index f4fcf26..11aaf1e 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -80,7 +80,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 #endif
 
 	default:
-patch_default:
+patch_default: __maybe_unused
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
 
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
index 24a5030..9127112 100644
--- a/arch/x86/kernel/platform-quirks.c
+++ b/arch/x86/kernel/platform-quirks.c
@@ -6,6 +6,7 @@
 
 void __init x86_early_init_platform_quirks(void)
 {
+	x86_platform.legacy.i8042 = X86_LEGACY_I8042_EXPECTED_PRESENT;
 	x86_platform.legacy.rtc = 1;
 	x86_platform.legacy.reserve_bios_regions = 0;
 	x86_platform.legacy.devices.pnpbios = 1;
@@ -16,10 +17,14 @@ void __init x86_early_init_platform_quirks(void)
 		break;
 	case X86_SUBARCH_XEN:
 	case X86_SUBARCH_LGUEST:
+		x86_platform.legacy.devices.pnpbios = 0;
+		x86_platform.legacy.rtc = 0;
+		break;
 	case X86_SUBARCH_INTEL_MID:
 	case X86_SUBARCH_CE4100:
 		x86_platform.legacy.devices.pnpbios = 0;
 		x86_platform.legacy.rtc = 0;
+		x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT;
 		break;
 	}
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 37363e4..b615a11 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -23,7 +23,7 @@
 #include <asm/cpu.h>
 #include <asm/apic.h>
 #include <asm/syscalls.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mwait.h>
 #include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index d0d7441..a0ac3e8 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -53,6 +53,7 @@
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>
 #include <asm/vm86.h>
+#include <asm/intel_rdt.h>
 
 void __show_regs(struct pt_regs *regs, int all)
 {
@@ -296,5 +297,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	this_cpu_write(current_task, next_p);
 
+	/* Load the Intel cache allocation PQR MSR. */
+	intel_rdt_sched_in();
+
 	return prev_p;
 }
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index a76b65e..a61e141 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -49,6 +49,7 @@
 #include <asm/switch_to.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/vdso.h>
+#include <asm/intel_rdt.h>
 
 __visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
 
@@ -476,6 +477,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 			loadsegment(ss, __KERNEL_DS);
 	}
 
+	/* Load the Intel cache allocation PQR MSR. */
+	intel_rdt_sched_in();
+
 	return prev_p;
 }
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 0e63c02..9cc7d5a 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -24,7 +24,7 @@
 #include <linux/export.h>
 #include <linux/context_tracking.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/fpu/internal.h>
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 5b2cc88..9e93fe5 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -71,10 +71,10 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
 	return flags & valid_flags;
 }
 
-cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 {
 	unsigned version;
-	cycle_t ret;
+	u64 ret;
 	u64 last;
 	u8 flags;
 
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 8402907..b868fa1 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -408,7 +408,7 @@ static __init int tboot_late_init(void)
 	tboot_create_trampoline();
 
 	atomic_set(&ap_wfs_count, 0);
-	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "AP_X86_TBOOT_DYING", NULL,
+	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "x86/tboot:dying", NULL,
 			  tboot_dying_cpu);
 #ifdef CONFIG_DEBUG_FS
 	debugfs_create_file("tboot_log", S_IRUSR,
diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c
index 27538f1..a3b875c 100644
--- a/arch/x86/kernel/test_nx.c
+++ b/arch/x86/kernel/test_nx.c
@@ -13,7 +13,7 @@
 #include <linux/sort.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/asm.h>
 
 extern int rodata_test_data;
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 9692a5e..6c89344 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -5,7 +5,7 @@
 #include <linux/regset.h>
 #include <linux/syscalls.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/desc.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 0aed75a..be3a49e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1101,9 +1101,9 @@ static void tsc_resume(struct clocksource *cs)
  * checking the result of read_tsc() - cycle_last for being negative.
  * That works because CLOCKSOURCE_MASK(64) does not mask out any bit.
  */
-static cycle_t read_tsc(struct clocksource *cs)
+static u64 read_tsc(struct clocksource *cs)
 {
-	return (cycle_t)rdtsc_ordered();
+	return (u64)rdtsc_ordered();
 }
 
 /*
@@ -1192,7 +1192,7 @@ int unsynchronized_tsc(void)
 /*
  * Convert ART to TSC given numerator/denominator found in detect_art()
  */
-struct system_counterval_t convert_art_to_tsc(cycle_t art)
+struct system_counterval_t convert_art_to_tsc(u64 art)
 {
 	u64 tmp, res, rem;
 
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index ea7b7f9..4443e499 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -6,6 +6,37 @@
 
 #define FRAME_HEADER_SIZE (sizeof(long) * 2)
 
+static void unwind_dump(struct unwind_state *state, unsigned long *sp)
+{
+	static bool dumped_before = false;
+	bool prev_zero, zero = false;
+	unsigned long word;
+
+	if (dumped_before)
+		return;
+
+	dumped_before = true;
+
+	printk_deferred("unwind stack type:%d next_sp:%p mask:%lx graph_idx:%d\n",
+			state->stack_info.type, state->stack_info.next_sp,
+			state->stack_mask, state->graph_idx);
+
+	for (sp = state->orig_sp; sp < state->stack_info.end; sp++) {
+		word = READ_ONCE_NOCHECK(*sp);
+
+		prev_zero = zero;
+		zero = word == 0;
+
+		if (zero) {
+			if (!prev_zero)
+				printk_deferred("%p: %016x ...\n", sp, 0);
+			continue;
+		}
+
+		printk_deferred("%p: %016lx (%pB)\n", sp, word, (void *)word);
+	}
+}
+
 unsigned long unwind_get_return_address(struct unwind_state *state)
 {
 	unsigned long addr;
@@ -20,15 +51,7 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
 	addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
 				     addr_p);
 
-	if (!__kernel_text_address(addr)) {
-		printk_deferred_once(KERN_WARNING
-			"WARNING: unrecognized kernel stack return address %p at %p in %s:%d\n",
-			(void *)addr, addr_p, state->task->comm,
-			state->task->pid);
-		return 0;
-	}
-
-	return addr;
+	return __kernel_text_address(addr) ? addr : 0;
 }
 EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
@@ -46,7 +69,14 @@ static bool is_last_task_frame(struct unwind_state *state)
 	unsigned long bp = (unsigned long)state->bp;
 	unsigned long regs = (unsigned long)task_pt_regs(state->task);
 
-	return bp == regs - FRAME_HEADER_SIZE;
+	/*
+	 * We have to check for the last task frame at two different locations
+	 * because gcc can occasionally decide to realign the stack pointer and
+	 * change the offset of the stack frame by a word in the prologue of a
+	 * function called by head/entry code.
+	 */
+	return bp == regs - FRAME_HEADER_SIZE ||
+	       bp == regs - FRAME_HEADER_SIZE - sizeof(long);
 }
 
 /*
@@ -67,6 +97,7 @@ static bool update_stack_state(struct unwind_state *state, void *addr,
 			       size_t len)
 {
 	struct stack_info *info = &state->stack_info;
+	enum stack_type orig_type = info->type;
 
 	/*
 	 * If addr isn't on the current stack, switch to the next one.
@@ -80,6 +111,9 @@ static bool update_stack_state(struct unwind_state *state, void *addr,
 				   &state->stack_mask))
 			return false;
 
+	if (!state->orig_sp || info->type != orig_type)
+		state->orig_sp = addr;
+
 	return true;
 }
 
@@ -178,11 +212,13 @@ bool unwind_next_frame(struct unwind_state *state)
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
 			state->regs, state->task->comm,
 			state->task->pid, next_frame);
+		unwind_dump(state, (unsigned long *)state->regs);
 	} else {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack frame pointer at %p in %s:%d has bad value %p\n",
 			state->bp, state->task->comm,
 			state->task->pid, next_frame);
+		unwind_dump(state, state->bp);
 	}
 the_end:
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 01f30e5..ec5d754 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -47,7 +47,7 @@
 #include <linux/slab.h>
 #include <linux/security.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/tlbflush.h>
 #include <asm/irq.h>
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 0bd9f12..11a93f0 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -89,7 +89,6 @@ struct x86_cpuinit_ops x86_cpuinit = {
 };
 
 static void default_nmi_init(void) { };
-static int default_i8042_detect(void) { return 1; };
 
 struct x86_platform_ops x86_platform __ro_after_init = {
 	.calibrate_cpu			= native_calibrate_cpu,
@@ -100,7 +99,6 @@ struct x86_platform_ops x86_platform __ro_after_init = {
 	.is_untracked_pat_range		= is_ISA_range,
 	.nmi_init			= default_nmi_init,
 	.get_nmi_reason			= default_get_nmi_reason,
-	.i8042_detect			= default_i8042_detect,
 	.save_sched_clock_state 	= tsc_save_sched_clock_state,
 	.restore_sched_clock_state 	= tsc_restore_sched_clock_state,
 };
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 34a66b2..5fe290c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1106,7 +1106,7 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	now = ktime_get();
 	remaining = ktime_sub(apic->lapic_timer.target_expiration, now);
 	if (ktime_to_ns(remaining) < 0)
-		remaining = ktime_set(0, 0);
+		remaining = 0;
 
 	ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period);
 	tmcct = div64_u64(ns,
@@ -2057,7 +2057,7 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 			apic->lapic_timer.tscdeadline = 0;
 		if (apic_lvtt_oneshot(apic)) {
 			apic->lapic_timer.tscdeadline = 0;
-			apic->lapic_timer.target_expiration = ktime_set(0, 0);
+			apic->lapic_timer.target_expiration = 0;
 		}
 		atomic_set(&apic->lapic_timer.pending, 0);
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 445c51b..51ccfe0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1131,8 +1131,8 @@ struct pvclock_gtod_data {
 
 	struct { /* extract of a clocksource struct */
 		int vclock_mode;
-		cycle_t	cycle_last;
-		cycle_t	mask;
+		u64	cycle_last;
+		u64	mask;
 		u32	mult;
 		u32	shift;
 	} clock;
@@ -1572,9 +1572,9 @@ static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
 
 #ifdef CONFIG_X86_64
 
-static cycle_t read_tsc(void)
+static u64 read_tsc(void)
 {
-	cycle_t ret = (cycle_t)rdtsc_ordered();
+	u64 ret = (u64)rdtsc_ordered();
 	u64 last = pvclock_gtod_data.clock.cycle_last;
 
 	if (likely(ret >= last))
@@ -1592,7 +1592,7 @@ static cycle_t read_tsc(void)
 	return last;
 }
 
-static inline u64 vgettsc(cycle_t *cycle_now)
+static inline u64 vgettsc(u64 *cycle_now)
 {
 	long v;
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
@@ -1603,7 +1603,7 @@ static inline u64 vgettsc(cycle_t *cycle_now)
 	return v * gtod->clock.mult;
 }
 
-static int do_monotonic_boot(s64 *t, cycle_t *cycle_now)
+static int do_monotonic_boot(s64 *t, u64 *cycle_now)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
@@ -1624,7 +1624,7 @@ static int do_monotonic_boot(s64 *t, cycle_t *cycle_now)
 }
 
 /* returns true if host is using tsc clocksource */
-static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now)
+static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now)
 {
 	/* checked again under seqlock below */
 	if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
@@ -5855,7 +5855,7 @@ static void kvm_timer_init(void)
 	}
 	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 
-	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 4ca0d78..d3289d7 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -916,7 +916,7 @@ static unsigned long lguest_tsc_khz(void)
  * If we can't use the TSC, the kernel falls back to our lower-priority
  * "lguest_clock", where we read the time value given to us by the Host.
  */
-static cycle_t lguest_clock_read(struct clocksource *cs)
+static u64 lguest_clock_read(struct clocksource *cs)
 {
 	unsigned long sec, nsec;
 
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 0b28121..1f65ff65 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -11,7 +11,7 @@
 #include <linux/export.h>
 #include <linux/backing-dev.h>
 #include <linux/interrupt.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmx.h>
 #include <asm/asm.h>
 
diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c
index 9e6545f..2ccc424 100644
--- a/arch/x86/math-emu/errors.c
+++ b/arch/x86/math-emu/errors.c
@@ -19,7 +19,7 @@
 
 #include <linux/signal.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "fpu_emu.h"
 #include "fpu_system.h"
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index e945fed..0203bae 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -27,7 +27,7 @@
 #include <linux/signal.h>
 #include <linux/regset.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/traps.h>
 #include <asm/user.h>
 #include <asm/fpu/internal.h>
diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c
index 8db2659..b8ef9f9d2 100644
--- a/arch/x86/math-emu/get_address.c
+++ b/arch/x86/math-emu/get_address.c
@@ -19,7 +19,7 @@
 
 #include <linux/stddef.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/vm86.h>
 
 #include "fpu_system.h"
diff --git a/arch/x86/math-emu/load_store.c b/arch/x86/math-emu/load_store.c
index 95228ff..1643054 100644
--- a/arch/x86/math-emu/load_store.c
+++ b/arch/x86/math-emu/load_store.c
@@ -18,7 +18,7 @@
  |    other processes using the emulator while swapping is in progress.      |
  +---------------------------------------------------------------------------*/
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "fpu_system.h"
 #include "exception.h"
diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c
index d597fe7..2c98965 100644
--- a/arch/x86/math-emu/reg_ld_str.c
+++ b/arch/x86/math-emu/reg_ld_str.c
@@ -19,7 +19,7 @@
 
 #include "fpu_emu.h"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "fpu_system.h"
 #include "exception.h"
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index fcd06f7..61a7e9e 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,5 +1,5 @@
 #include <linux/extable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index cf80590..928d657 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -34,7 +34,7 @@
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/dma.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 963895f..af85b68 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -36,7 +36,7 @@
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/dma.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e3353c9..5a287e5 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -20,7 +20,7 @@
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #include <asm/pat.h>
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 821cb41..ce4b067 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -23,11 +23,6 @@
 #include <asm/io_apic.h>
 #include <asm/emergency-restart.h>
 
-static int ce4100_i8042_detect(void)
-{
-	return 0;
-}
-
 /*
  * The CE4100 platform has an internal 8051 Microcontroller which is
  * responsible for signaling to the external Power Management Unit the
@@ -145,7 +140,6 @@ static void sdv_pci_init(void)
 void __init x86_ce4100_early_setup(void)
 {
 	x86_init.oem.arch_setup = sdv_arch_setup;
-	x86_platform.i8042_detect = ce4100_i8042_detect;
 	x86_init.resources.probe_roms = x86_init_noop;
 	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
 	x86_init.mpparse.find_smp_config = x86_init_noop;
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index dd6cfa4..61b5ed2 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -19,7 +19,7 @@
 # I2C Devices
 obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o
 obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o
-obj-$(subst m,y,$(CONFIG_INPUT_MPU3050)) += platform_mpu3050.o
+obj-$(subst m,y,$(CONFIG_MPU3050_I2C)) += platform_mpu3050.o
 obj-$(subst m,y,$(CONFIG_INPUT_BMA150)) += platform_bma023.o
 obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o
 # I2C GPIO Expanders
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 7850128..12a2725 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -161,12 +161,6 @@ static void intel_mid_arch_setup(void)
 	regulator_has_full_constraints();
 }
 
-/* MID systems don't have i8042 controller */
-static int intel_mid_i8042_detect(void)
-{
-	return 0;
-}
-
 /*
  * Moorestown does not have external NMI source nor port 0x61 to report
  * NMI status. The possible NMI sources are from pmu as a result of NMI
@@ -197,7 +191,6 @@ void __init x86_intel_mid_early_setup(void)
 	x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
 
 	x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
-	x86_platform.i8042_detect = intel_mid_i8042_detect;
 	x86_init.timers.wallclock_init = intel_mid_rtc_init;
 	x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
 
diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c
index f5bad40..b8f5620 100644
--- a/arch/x86/platform/intel-quark/imr_selftest.c
+++ b/arch/x86/platform/intel-quark/imr_selftest.c
@@ -25,7 +25,8 @@
  * @fmt:	format string.
  * ...		variadic argument list.
  */
-static void __init imr_self_test_result(int res, const char *fmt, ...)
+static __printf(2, 3)
+void __init imr_self_test_result(int res, const char *fmt, ...)
 {
 	va_list vlist;
 
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index b333fc4..2ee7632 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -30,7 +30,7 @@
 
 #define RTC_NAME		"sgi_rtc"
 
-static cycle_t uv_read_rtc(struct clocksource *cs);
+static u64 uv_read_rtc(struct clocksource *cs);
 static int uv_rtc_next_event(unsigned long, struct clock_event_device *);
 static int uv_rtc_shutdown(struct clock_event_device *evt);
 
@@ -38,7 +38,7 @@ static struct clocksource clocksource_uv = {
 	.name		= RTC_NAME,
 	.rating		= 299,
 	.read		= uv_read_rtc,
-	.mask		= (cycle_t)UVH_RTC_REAL_TIME_CLOCK_MASK,
+	.mask		= (u64)UVH_RTC_REAL_TIME_CLOCK_MASK,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -296,7 +296,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
  * cachelines of it's own page.  This allows faster simultaneous reads
  * from a given socket.
  */
-static cycle_t uv_read_rtc(struct clocksource *cs)
+static u64 uv_read_rtc(struct clocksource *cs)
 {
 	unsigned long offset;
 
@@ -305,7 +305,7 @@ static cycle_t uv_read_rtc(struct clocksource *cs)
 	else
 		offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
 
-	return (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
+	return (u64)uv_read_local_mmr(UVH_RTC | offset);
 }
 
 /*
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 0c2fae8..73eb7fd 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -992,11 +992,12 @@ static void emit_relocs(int as_text, int use_real_mode)
 		die("Segment relocations found but --realmode not specified\n");
 
 	/* Order the relocations for more efficient processing */
-	sort_relocs(&relocs16);
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
 	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
+#else
+	sort_relocs(&relocs16);
 #endif
 
 	/* Print the relocations */
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index 60a5a5a..2497bac 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -5,7 +5,7 @@
 
 #include <linux/mm.h>
 #include <linux/sched.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ptrace-abi.h>
 #include <skas.h>
 
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index e30202b..a5c9910 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -10,7 +10,7 @@
 #include <linux/errno.h>
 #define __FRAME_OFFSETS
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ptrace-abi.h>
 
 /*
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 49e5036..727ed44 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -9,7 +9,7 @@
 #include <linux/ptrace.h>
 #include <linux/kernel.h>
 #include <asm/unistd.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ucontext.h>
 #include <frame_kern.h>
 #include <skas.h>
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index 48e3858..5bd949d 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -6,7 +6,7 @@
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/syscalls.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ptrace-abi.h>
 #include <os.h>
 #include <skas.h>
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ced7027..51ef952 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1529,11 +1529,11 @@ static int xen_cpuhp_setup(void)
 	int rc;
 
 	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
-				       "XEN_HVM_GUEST_PREPARE",
+				       "x86/xen/hvm_guest:prepare",
 				       xen_cpu_up_prepare, xen_cpu_dead);
 	if (rc >= 0) {
 		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					       "XEN_HVM_GUEST_ONLINE",
+					       "x86/xen/hvm_guest:online",
 					       xen_cpu_up_online, NULL);
 		if (rc < 0)
 			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 37129db..276da63 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -71,7 +71,7 @@
 
 #include <asm/cache.h>
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 33d8f6a..1e69956 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -39,10 +39,10 @@ static unsigned long xen_tsc_khz(void)
 	return pvclock_tsc_khz(info);
 }
 
-cycle_t xen_clocksource_read(void)
+u64 xen_clocksource_read(void)
 {
         struct pvclock_vcpu_time_info *src;
-	cycle_t ret;
+	u64 ret;
 
 	preempt_disable_notrace();
 	src = &__this_cpu_read(xen_vcpu)->time;
@@ -51,7 +51,7 @@ cycle_t xen_clocksource_read(void)
 	return ret;
 }
 
-static cycle_t xen_clocksource_get_cycles(struct clocksource *cs)
+static u64 xen_clocksource_get_cycles(struct clocksource *cs)
 {
 	return xen_clocksource_read();
 }
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 3cbce3b..ac0a2b0 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -67,7 +67,7 @@ void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);
 void xen_setup_runstate_info(int cpu);
 void xen_teardown_timer(int cpu);
-cycle_t xen_clocksource_read(void);
+u64 xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);
 void __init xen_init_time_ops(void);
 void __init xen_hvm_init_time_ops(void);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index f610586..f4126cf 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -15,6 +15,7 @@
 	select GENERIC_SCHED_CLOCK
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_EXIT_THREAD
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if !MMU
diff --git a/arch/xtensa/boot/dts/kc705.dts b/arch/xtensa/boot/dts/kc705.dts
index b1f4ee8..6106bdc 100644
--- a/arch/xtensa/boot/dts/kc705.dts
+++ b/arch/xtensa/boot/dts/kc705.dts
@@ -11,4 +11,20 @@
 		device_type = "memory";
 		reg = <0x00000000 0x38000000>;
 	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		/* global autoconfigured region for contiguous allocations */
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0x04000000>;
+			alignment = <0x2000>;
+			alloc-ranges = <0x00000000 0x20000000>;
+			linux,cma-default;
+		};
+	};
 };
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 28cf4c5..b7fbaa5 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -3,6 +3,7 @@
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += div64.h
+generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index ec35074..3ae74d7 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -12,7 +12,7 @@
 #define _XTENSA_CHECKSUM_H
 
 #include <linux/in6.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <variant/core.h>
 
 /*
diff --git a/arch/xtensa/include/asm/segment.h b/arch/xtensa/include/asm/segment.h
index a2eb547..98964ad 100644
--- a/arch/xtensa/include/asm/segment.h
+++ b/arch/xtensa/include/asm/segment.h
@@ -11,6 +11,6 @@
 #ifndef _XTENSA_SEGMENT_H
 #define _XTENSA_SEGMENT_H
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #endif	/* _XTENSA_SEGEMENT_H */
diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile
index c31f5d5..264fb89 100644
--- a/arch/xtensa/kernel/Makefile
+++ b/arch/xtensa/kernel/Makefile
@@ -14,6 +14,7 @@
 obj-$(CONFIG_SMP) += smp.o mxhead.o
 obj-$(CONFIG_XTENSA_VARIANT_HAVE_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
+obj-$(CONFIG_S32C1I_SELFTEST) += s32c1i_selftest.o
 
 AFLAGS_head.o += -mtext-section-literals
 AFLAGS_mxhead.o += -mtext-section-literals
diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c
index 8e10e35..bcb5beb 100644
--- a/arch/xtensa/kernel/asm-offsets.c
+++ b/arch/xtensa/kernel/asm-offsets.c
@@ -24,7 +24,7 @@
 
 #include <asm/ptrace.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int main(void)
 {
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 4ac3d23..a265edd 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -25,7 +25,7 @@
 #include <linux/of.h>
 
 #include <asm/mxregs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/platform.h>
 
 DECLARE_PER_CPU(unsigned long, nmi_count);
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 6a16dec..70e362e 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -15,6 +15,7 @@
  * Joe Taylor <joe@tensilica.com, joetylr@yahoo.com>
  */
 
+#include <linux/dma-contiguous.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
@@ -146,6 +147,8 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size,
 {
 	unsigned long ret;
 	unsigned long uncached = 0;
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page *page = NULL;
 
 	/* ignore region speicifiers */
 
@@ -153,11 +156,18 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size,
 
 	if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
 		flag |= GFP_DMA;
-	ret = (unsigned long)__get_free_pages(flag, get_order(size));
 
-	if (ret == 0)
+	if (gfpflags_allow_blocking(flag))
+		page = dma_alloc_from_contiguous(dev, count, get_order(size));
+
+	if (!page)
+		page = alloc_pages(flag, get_order(size));
+
+	if (!page)
 		return NULL;
 
+	ret = (unsigned long)page_address(page);
+
 	/* We currently don't support coherent memory outside KSEG */
 
 	BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR ||
@@ -170,16 +180,19 @@ static void *xtensa_dma_alloc(struct device *dev, size_t size,
 	return (void *)uncached;
 }
 
-static void xtensa_dma_free(struct device *hwdev, size_t size, void *vaddr,
+static void xtensa_dma_free(struct device *dev, size_t size, void *vaddr,
 			    dma_addr_t dma_handle, unsigned long attrs)
 {
 	unsigned long addr = (unsigned long)vaddr +
 		XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
+	struct page *page = virt_to_page(addr);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
 	BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR ||
 	       addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
-	free_pages(addr, get_order(size));
+	if (!dma_release_from_contiguous(dev, page, count))
+		__free_pages(page, get_order(size));
 }
 
 static dma_addr_t xtensa_map_page(struct device *dev, struct page *page,
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 0fecc8a..ff1d813 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -422,7 +422,7 @@ static int __init xtensa_pmu_init(void)
 	int irq = irq_create_mapping(NULL, XCHAL_PROFILING_INTERRUPT);
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_XTENSA_STARTING,
-				"AP_PERF_XTENSA_STARTING", xtensa_pmu_setup,
+				"perf/xtensa:starting", xtensa_pmu_setup,
 				NULL);
 	if (ret) {
 		pr_err("xtensa_pmu: failed to register CPU-hotplug.\n");
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index e0ded48..826d251 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -35,7 +35,7 @@
 #include <linux/rcupdate.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/platform.h>
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index a651f3a..32519b7 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -29,7 +29,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/ptrace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 void user_enable_single_step(struct task_struct *child)
diff --git a/arch/xtensa/kernel/s32c1i_selftest.c b/arch/xtensa/kernel/s32c1i_selftest.c
new file mode 100644
index 0000000..07e56e3
--- /dev/null
+++ b/arch/xtensa/kernel/s32c1i_selftest.c
@@ -0,0 +1,128 @@
+/*
+ * S32C1I selftest.
+ *
+ * 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) 2016 Cadence Design Systems Inc.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+#include <asm/traps.h>
+
+#if XCHAL_HAVE_S32C1I
+
+static int __initdata rcw_word, rcw_probe_pc, rcw_exc;
+
+/*
+ * Basic atomic compare-and-swap, that records PC of S32C1I for probing.
+ *
+ * If *v == cmp, set *v = set.  Return previous *v.
+ */
+static inline int probed_compare_swap(int *v, int cmp, int set)
+{
+	int tmp;
+
+	__asm__ __volatile__(
+			"	movi	%1, 1f\n"
+			"	s32i	%1, %4, 0\n"
+			"	wsr	%2, scompare1\n"
+			"1:	s32c1i	%0, %3, 0\n"
+			: "=a" (set), "=&a" (tmp)
+			: "a" (cmp), "a" (v), "a" (&rcw_probe_pc), "0" (set)
+			: "memory"
+			);
+	return set;
+}
+
+/* Handle probed exception */
+
+static void __init do_probed_exception(struct pt_regs *regs,
+				       unsigned long exccause)
+{
+	if (regs->pc == rcw_probe_pc) {	/* exception on s32c1i ? */
+		regs->pc += 3;		/* skip the s32c1i instruction */
+		rcw_exc = exccause;
+	} else {
+		do_unhandled(regs, exccause);
+	}
+}
+
+/* Simple test of S32C1I (soc bringup assist) */
+
+static int __init check_s32c1i(void)
+{
+	int n, cause1, cause2;
+	void *handbus, *handdata, *handaddr; /* temporarily saved handlers */
+
+	rcw_probe_pc = 0;
+	handbus  = trap_set_handler(EXCCAUSE_LOAD_STORE_ERROR,
+			do_probed_exception);
+	handdata = trap_set_handler(EXCCAUSE_LOAD_STORE_DATA_ERROR,
+			do_probed_exception);
+	handaddr = trap_set_handler(EXCCAUSE_LOAD_STORE_ADDR_ERROR,
+			do_probed_exception);
+
+	/* First try an S32C1I that does not store: */
+	rcw_exc = 0;
+	rcw_word = 1;
+	n = probed_compare_swap(&rcw_word, 0, 2);
+	cause1 = rcw_exc;
+
+	/* took exception? */
+	if (cause1 != 0) {
+		/* unclean exception? */
+		if (n != 2 || rcw_word != 1)
+			panic("S32C1I exception error");
+	} else if (rcw_word != 1 || n != 1) {
+		panic("S32C1I compare error");
+	}
+
+	/* Then an S32C1I that stores: */
+	rcw_exc = 0;
+	rcw_word = 0x1234567;
+	n = probed_compare_swap(&rcw_word, 0x1234567, 0xabcde);
+	cause2 = rcw_exc;
+
+	if (cause2 != 0) {
+		/* unclean exception? */
+		if (n != 0xabcde || rcw_word != 0x1234567)
+			panic("S32C1I exception error (b)");
+	} else if (rcw_word != 0xabcde || n != 0x1234567) {
+		panic("S32C1I store error");
+	}
+
+	/* Verify consistency of exceptions: */
+	if (cause1 || cause2) {
+		pr_warn("S32C1I took exception %d, %d\n", cause1, cause2);
+		/* If emulation of S32C1I upon bus error gets implemented,
+		 * we can get rid of this panic for single core (not SMP)
+		 */
+		panic("S32C1I exceptions not currently supported");
+	}
+	if (cause1 != cause2)
+		panic("inconsistent S32C1I exceptions");
+
+	trap_set_handler(EXCCAUSE_LOAD_STORE_ERROR, handbus);
+	trap_set_handler(EXCCAUSE_LOAD_STORE_DATA_ERROR, handdata);
+	trap_set_handler(EXCCAUSE_LOAD_STORE_ADDR_ERROR, handaddr);
+	return 0;
+}
+
+#else /* XCHAL_HAVE_S32C1I */
+
+/* This condition should not occur with a commercially deployed processor.
+ * Display reminder for early engr test or demo chips / FPGA bitstreams
+ */
+static int __init check_s32c1i(void)
+{
+	pr_warn("Processor configuration lacks atomic compare-and-swap support!\n");
+	return 0;
+}
+
+#endif /* XCHAL_HAVE_S32C1I */
+
+early_initcall(check_s32c1i);
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 88a044a..848e856 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -31,10 +31,6 @@
 # include <linux/console.h>
 #endif
 
-#ifdef CONFIG_RTC
-# include <linux/timex.h>
-#endif
-
 #ifdef CONFIG_PROC_FS
 # include <linux/seq_file.h>
 #endif
@@ -48,24 +44,22 @@
 #include <asm/page.h>
 #include <asm/setup.h>
 #include <asm/param.h>
-#include <asm/traps.h>
 #include <asm/smp.h>
 #include <asm/sysmem.h>
 
 #include <platform/hardware.h>
 
 #if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE)
-struct screen_info screen_info = { 0, 24, 0, 0, 0, 80, 0, 0, 0, 24, 1, 16};
+struct screen_info screen_info = {
+	.orig_x = 0,
+	.orig_y = 24,
+	.orig_video_cols = 80,
+	.orig_video_lines = 24,
+	.orig_video_isVGA = 1,
+	.orig_video_points = 16,
+};
 #endif
 
-#ifdef CONFIG_BLK_DEV_FD
-extern struct fd_ops no_fd_ops;
-struct fd_ops *fd_ops;
-#endif
-
-extern struct rtc_ops no_rtc_ops;
-struct rtc_ops *rtc_ops;
-
 #ifdef CONFIG_BLK_DEV_INITRD
 extern unsigned long initrd_start;
 extern unsigned long initrd_end;
@@ -77,7 +71,6 @@ extern int initrd_below_start_ok;
 void *dtb_start = __dtb_start;
 #endif
 
-unsigned char aux_device_present;
 extern unsigned long loops_per_jiffy;
 
 /* Command line specified as configuration option. */
@@ -317,120 +310,6 @@ extern char _SecondaryResetVector_text_start;
 extern char _SecondaryResetVector_text_end;
 #endif
 
-
-#ifdef CONFIG_S32C1I_SELFTEST
-#if XCHAL_HAVE_S32C1I
-
-static int __initdata rcw_word, rcw_probe_pc, rcw_exc;
-
-/*
- * Basic atomic compare-and-swap, that records PC of S32C1I for probing.
- *
- * If *v == cmp, set *v = set.  Return previous *v.
- */
-static inline int probed_compare_swap(int *v, int cmp, int set)
-{
-	int tmp;
-
-	__asm__ __volatile__(
-			"	movi	%1, 1f\n"
-			"	s32i	%1, %4, 0\n"
-			"	wsr	%2, scompare1\n"
-			"1:	s32c1i	%0, %3, 0\n"
-			: "=a" (set), "=&a" (tmp)
-			: "a" (cmp), "a" (v), "a" (&rcw_probe_pc), "0" (set)
-			: "memory"
-			);
-	return set;
-}
-
-/* Handle probed exception */
-
-static void __init do_probed_exception(struct pt_regs *regs,
-		unsigned long exccause)
-{
-	if (regs->pc == rcw_probe_pc) {	/* exception on s32c1i ? */
-		regs->pc += 3;		/* skip the s32c1i instruction */
-		rcw_exc = exccause;
-	} else {
-		do_unhandled(regs, exccause);
-	}
-}
-
-/* Simple test of S32C1I (soc bringup assist) */
-
-static int __init check_s32c1i(void)
-{
-	int n, cause1, cause2;
-	void *handbus, *handdata, *handaddr; /* temporarily saved handlers */
-
-	rcw_probe_pc = 0;
-	handbus  = trap_set_handler(EXCCAUSE_LOAD_STORE_ERROR,
-			do_probed_exception);
-	handdata = trap_set_handler(EXCCAUSE_LOAD_STORE_DATA_ERROR,
-			do_probed_exception);
-	handaddr = trap_set_handler(EXCCAUSE_LOAD_STORE_ADDR_ERROR,
-			do_probed_exception);
-
-	/* First try an S32C1I that does not store: */
-	rcw_exc = 0;
-	rcw_word = 1;
-	n = probed_compare_swap(&rcw_word, 0, 2);
-	cause1 = rcw_exc;
-
-	/* took exception? */
-	if (cause1 != 0) {
-		/* unclean exception? */
-		if (n != 2 || rcw_word != 1)
-			panic("S32C1I exception error");
-	} else if (rcw_word != 1 || n != 1) {
-		panic("S32C1I compare error");
-	}
-
-	/* Then an S32C1I that stores: */
-	rcw_exc = 0;
-	rcw_word = 0x1234567;
-	n = probed_compare_swap(&rcw_word, 0x1234567, 0xabcde);
-	cause2 = rcw_exc;
-
-	if (cause2 != 0) {
-		/* unclean exception? */
-		if (n != 0xabcde || rcw_word != 0x1234567)
-			panic("S32C1I exception error (b)");
-	} else if (rcw_word != 0xabcde || n != 0x1234567) {
-		panic("S32C1I store error");
-	}
-
-	/* Verify consistency of exceptions: */
-	if (cause1 || cause2) {
-		pr_warn("S32C1I took exception %d, %d\n", cause1, cause2);
-		/* If emulation of S32C1I upon bus error gets implemented,
-		   we can get rid of this panic for single core (not SMP) */
-		panic("S32C1I exceptions not currently supported");
-	}
-	if (cause1 != cause2)
-		panic("inconsistent S32C1I exceptions");
-
-	trap_set_handler(EXCCAUSE_LOAD_STORE_ERROR, handbus);
-	trap_set_handler(EXCCAUSE_LOAD_STORE_DATA_ERROR, handdata);
-	trap_set_handler(EXCCAUSE_LOAD_STORE_ADDR_ERROR, handaddr);
-	return 0;
-}
-
-#else /* XCHAL_HAVE_S32C1I */
-
-/* This condition should not occur with a commercially deployed processor.
-   Display reminder for early engr test or demo chips / FPGA bitstreams */
-static int __init check_s32c1i(void)
-{
-	pr_warn("Processor configuration lacks atomic compare-and-swap support!\n");
-	return 0;
-}
-
-#endif /* XCHAL_HAVE_S32C1I */
-early_initcall(check_s32c1i);
-#endif /* CONFIG_S32C1I_SELFTEST */
-
 static inline int mem_reserve(unsigned long start, unsigned long end)
 {
 	return memblock_reserve(start, end - start);
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index e87adaa..c412947 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -22,7 +22,7 @@
 #include <linux/tracehook.h>
 
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/coprocessor.h>
 #include <asm/unistd.h>
diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c
index 7538d80..e7d30ee 100644
--- a/arch/xtensa/kernel/stacktrace.c
+++ b/arch/xtensa/kernel/stacktrace.c
@@ -14,7 +14,7 @@
 
 #include <asm/stacktrace.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #if IS_ENABLED(CONFIG_OPROFILE) || IS_ENABLED(CONFIG_PERF_EVENTS)
 
diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
index 83cf496..d3fd100 100644
--- a/arch/xtensa/kernel/syscall.c
+++ b/arch/xtensa/kernel/syscall.c
@@ -15,7 +15,7 @@
  * Kevin Chea
  *
  */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/syscall.h>
 #include <asm/unistd.h>
 #include <linux/linkage.h>
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index be81e69..668c105 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -34,9 +34,9 @@
 unsigned long ccount_freq;		/* ccount Hz */
 EXPORT_SYMBOL(ccount_freq);
 
-static cycle_t ccount_read(struct clocksource *cs)
+static u64 ccount_read(struct clocksource *cs)
 {
-	return (cycle_t)get_ccount();
+	return (u64)get_ccount();
 }
 
 static u64 notrace ccount_sched_clock_read(void)
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index ce37d5b..282bf72 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -35,7 +35,7 @@
 #include <asm/stacktrace.h>
 #include <asm/ptrace.h>
 #include <asm/timex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/traps.h>
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 4d2872f..d159e9b 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -19,7 +19,7 @@
 #include <asm/irq.h>
 #include <linux/in6.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/checksum.h>
 #include <asm/dma.h>
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 80e4cfb..720fe4e 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -26,6 +26,7 @@
 #include <linux/nodemask.h>
 #include <linux/mm.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/bootparam.h>
 #include <asm/page.h>
@@ -60,6 +61,7 @@ void __init bootmem_init(void)
 	max_low_pfn = min(max_pfn, MAX_LOW_PFN);
 
 	memblock_set_current_limit(PFN_PHYS(max_low_pfn));
+	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
 
 	memblock_dump_all();
 }
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index c68f1e6..0140a22 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -20,7 +20,7 @@
 #include <linux/seq_file.h>
 #include <linux/serial.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 
 #include <platform/simcall.h>
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index ede04cc..02e94bb 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -17,7 +17,7 @@
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/proc_fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <platform/simcall.h>
 
 #define SIMDISK_MAJOR 240
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4bf850e..a8e67a1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2569,7 +2569,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
 	 * This will be replaced with the stats tracking code, using
 	 * 'avg_completion_time / 2' as the pre-sleep target.
 	 */
-	kt = ktime_set(0, nsecs);
+	kt = nsecs;
 
 	mode = HRTIMER_MODE_REL;
 	hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
diff --git a/block/bsg.c b/block/bsg.c
index 8a05a40..a57046d 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -655,6 +655,9 @@ bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 
 	dprintk("%s: write %Zd bytes\n", bd->name, count);
 
+	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+		return -EINVAL;
+
 	bsg_set_block(bd, file);
 
 	bytes_written = 0;
diff --git a/block/ioctl.c b/block/ioctl.c
index f856963..be7f4de 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -8,7 +8,7 @@
 #include <linux/fs.h>
 #include <linux/blktrace_api.h>
 #include <linux/pr.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
 {
@@ -45,6 +45,9 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 				    || pstart < 0 || plength < 0 || partno > 65535)
 					return -EINVAL;
 			}
+			/* check if partition is aligned to blocksize */
+			if (p.start & (bdev_logical_block_size(bdev) - 1))
+				return -EINVAL;
 
 			mutex_lock(&bdev->bd_mutex);
 
diff --git a/block/partitions/ibm.c b/block/partitions/ibm.c
index 47a6147..14b081a 100644
--- a/block/partitions/ibm.c
+++ b/block/partitions/ibm.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <asm/dasd.h>
 #include <asm/ebcdic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/vtoc.h>
 
 #include "check.h"
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 0774799..c2b6492 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -28,7 +28,7 @@
 #include <linux/slab.h>
 #include <linux/times.h>
 #include <linux/uio.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_ioctl.h>
@@ -182,6 +182,9 @@ static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 	__set_bit(WRITE_16, filter->write_ok);
 	__set_bit(WRITE_LONG, filter->write_ok);
 	__set_bit(WRITE_LONG_2, filter->write_ok);
+	__set_bit(WRITE_SAME, filter->write_ok);
+	__set_bit(WRITE_SAME_16, filter->write_ok);
+	__set_bit(WRITE_SAME_32, filter->write_ok);
 	__set_bit(ERASE, filter->write_ok);
 	__set_bit(GPCMD_MODE_SELECT_10, filter->write_ok);
 	__set_bit(MODE_SELECT, filter->write_ok);
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index f616ad7..44e888b 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1461,16 +1461,25 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 	for (i = 0; i < ctcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = ctemplate[i].inlen;
+		void *input_vec;
 
+		input_vec = kmalloc(ilen, GFP_KERNEL);
+		if (!input_vec) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		memcpy(input_vec, ctemplate[i].input, ilen);
 		memset(output, 0, dlen);
 		init_completion(&result.completion);
-		sg_init_one(&src, ctemplate[i].input, ilen);
+		sg_init_one(&src, input_vec, ilen);
 		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
 			pr_err("alg: acomp: request alloc failed for %s\n",
 			       algo);
+			kfree(input_vec);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1483,6 +1492,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 		if (ret) {
 			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1491,6 +1501,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1500,26 +1511,37 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			       i + 1, algo);
 			hexdump(output, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
 
+		kfree(input_vec);
 		acomp_request_free(req);
 	}
 
 	for (i = 0; i < dtcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = dtemplate[i].inlen;
+		void *input_vec;
 
+		input_vec = kmalloc(ilen, GFP_KERNEL);
+		if (!input_vec) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		memcpy(input_vec, dtemplate[i].input, ilen);
 		memset(output, 0, dlen);
 		init_completion(&result.completion);
-		sg_init_one(&src, dtemplate[i].input, ilen);
+		sg_init_one(&src, input_vec, ilen);
 		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
 			pr_err("alg: acomp: request alloc failed for %s\n",
 			       algo);
+			kfree(input_vec);
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -1532,6 +1554,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 		if (ret) {
 			pr_err("alg: acomp: decompression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1540,6 +1563,7 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			pr_err("alg: acomp: Decompression test %d failed for %s: output len = %d\n",
 			       i + 1, algo, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
@@ -1549,10 +1573,12 @@ static int test_acomp(struct crypto_acomp *tfm, struct comp_testvec *ctemplate,
 			       i + 1, algo);
 			hexdump(output, req->dlen);
 			ret = -EINVAL;
+			kfree(input_vec);
 			acomp_request_free(req);
 			goto out;
 		}
 
+		kfree(input_vec);
 		acomp_request_free(req);
 	}
 
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 201292e..d00bc0e 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -37,7 +37,7 @@
 #include <linux/suspend.h>
 #include <linux/acpi.h>
 #include <acpi/video.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define PREFIX "ACPI: "
 
diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h
index 7dd527f..94be8a8 100644
--- a/drivers/acpi/acpica/actables.h
+++ b/drivers/acpi/acpica/actables.h
@@ -166,6 +166,12 @@ acpi_tb_install_table_with_override(struct acpi_table_desc *new_table_desc,
 
 acpi_status acpi_tb_parse_root_table(acpi_physical_address rsdp_address);
 
+acpi_status
+acpi_tb_get_table(struct acpi_table_desc *table_desc,
+		  struct acpi_table_header **out_table);
+
+void acpi_tb_put_table(struct acpi_table_desc *table_desc);
+
 /*
  * tbxfload
  */
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 5fb838e..81473a4 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -311,6 +311,8 @@ void acpi_tb_parse_fadt(void)
 {
 	u32 length;
 	struct acpi_table_header *table;
+	struct acpi_table_desc *fadt_desc;
+	acpi_status status;
 
 	/*
 	 * The FADT has multiple versions with different lengths,
@@ -319,14 +321,12 @@ void acpi_tb_parse_fadt(void)
 	 * Get a local copy of the FADT and convert it to a common format
 	 * Map entire FADT, assumed to be smaller than one page.
 	 */
-	length = acpi_gbl_root_table_list.tables[acpi_gbl_fadt_index].length;
-
-	table =
-	    acpi_os_map_memory(acpi_gbl_root_table_list.
-			       tables[acpi_gbl_fadt_index].address, length);
-	if (!table) {
+	fadt_desc = &acpi_gbl_root_table_list.tables[acpi_gbl_fadt_index];
+	status = acpi_tb_get_table(fadt_desc, &table);
+	if (ACPI_FAILURE(status)) {
 		return;
 	}
+	length = fadt_desc->length;
 
 	/*
 	 * Validate the FADT checksum before we copy the table. Ignore
@@ -340,7 +340,7 @@ void acpi_tb_parse_fadt(void)
 
 	/* All done with the real FADT, unmap it */
 
-	acpi_os_unmap_memory(table, length);
+	acpi_tb_put_table(fadt_desc);
 
 	/* Obtain the DSDT and FACS tables via their addresses within the FADT */
 
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 51eb07c..86854e8 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -381,3 +381,88 @@ acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 	acpi_os_unmap_memory(table, length);
 	return_ACPI_STATUS(AE_OK);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_tb_get_table
+ *
+ * PARAMETERS:  table_desc          - Table descriptor
+ *              out_table           - Where the pointer to the table is returned
+ *
+ * RETURN:      Status and pointer to the requested table
+ *
+ * DESCRIPTION: Increase a reference to a table descriptor and return the
+ *              validated table pointer.
+ *              If the table descriptor is an entry of the root table list,
+ *              this API must be invoked with ACPI_MTX_TABLES acquired.
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_tb_get_table(struct acpi_table_desc *table_desc,
+		  struct acpi_table_header **out_table)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_tb_get_table);
+
+	if (table_desc->validation_count == 0) {
+
+		/* Table need to be "VALIDATED" */
+
+		status = acpi_tb_validate_table(table_desc);
+		if (ACPI_FAILURE(status)) {
+			return_ACPI_STATUS(status);
+		}
+	}
+
+	table_desc->validation_count++;
+	if (table_desc->validation_count == 0) {
+		ACPI_ERROR((AE_INFO,
+			    "Table %p, Validation count is zero after increment\n",
+			    table_desc));
+		table_desc->validation_count--;
+		return_ACPI_STATUS(AE_LIMIT);
+	}
+
+	*out_table = table_desc->pointer;
+	return_ACPI_STATUS(AE_OK);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_tb_put_table
+ *
+ * PARAMETERS:  table_desc          - Table descriptor
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Decrease a reference to a table descriptor and release the
+ *              validated table pointer if no references.
+ *              If the table descriptor is an entry of the root table list,
+ *              this API must be invoked with ACPI_MTX_TABLES acquired.
+ *
+ ******************************************************************************/
+
+void acpi_tb_put_table(struct acpi_table_desc *table_desc)
+{
+
+	ACPI_FUNCTION_TRACE(acpi_tb_put_table);
+
+	if (table_desc->validation_count == 0) {
+		ACPI_WARNING((AE_INFO,
+			      "Table %p, Validation count is zero before decrement\n",
+			      table_desc));
+		return_VOID;
+	}
+	table_desc->validation_count--;
+
+	if (table_desc->validation_count == 0) {
+
+		/* Table need to be "INVALIDATED" */
+
+		acpi_tb_invalidate_table(table_desc);
+	}
+
+	return_VOID;
+}
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index d5adb7a..7684707 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -282,7 +282,7 @@ ACPI_EXPORT_SYMBOL(acpi_get_table_header)
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_get_table_with_size
+ * FUNCTION:    acpi_get_table
  *
  * PARAMETERS:  signature           - ACPI signature of needed table
  *              instance            - Which instance (for SSDTs)
@@ -292,16 +292,21 @@ ACPI_EXPORT_SYMBOL(acpi_get_table_header)
  *
  * DESCRIPTION: Finds and verifies an ACPI table. Table must be in the
  *              RSDT/XSDT.
+ *              Note that an early stage acpi_get_table() call must be paired
+ *              with an early stage acpi_put_table() call. otherwise the table
+ *              pointer mapped by the early stage mapping implementation may be
+ *              erroneously unmapped by the late stage unmapping implementation
+ *              in an acpi_put_table() invoked during the late stage.
  *
  ******************************************************************************/
 acpi_status
-acpi_get_table_with_size(char *signature,
-	       u32 instance, struct acpi_table_header **out_table,
-	       acpi_size *tbl_size)
+acpi_get_table(char *signature,
+	       u32 instance, struct acpi_table_header ** out_table)
 {
 	u32 i;
 	u32 j;
-	acpi_status status;
+	acpi_status status = AE_NOT_FOUND;
+	struct acpi_table_desc *table_desc;
 
 	/* Parameter validation */
 
@@ -309,13 +314,22 @@ acpi_get_table_with_size(char *signature,
 		return (AE_BAD_PARAMETER);
 	}
 
+	/*
+	 * Note that the following line is required by some OSPMs, they only
+	 * check if the returned table is NULL instead of the returned status
+	 * to determined if this function is succeeded.
+	 */
+	*out_table = NULL;
+
+	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
+
 	/* Walk the root table list */
 
 	for (i = 0, j = 0; i < acpi_gbl_root_table_list.current_table_count;
 	     i++) {
-		if (!ACPI_COMPARE_NAME
-		    (&(acpi_gbl_root_table_list.tables[i].signature),
-		     signature)) {
+		table_desc = &acpi_gbl_root_table_list.tables[i];
+
+		if (!ACPI_COMPARE_NAME(&table_desc->signature, signature)) {
 			continue;
 		}
 
@@ -323,43 +337,65 @@ acpi_get_table_with_size(char *signature,
 			continue;
 		}
 
-		status =
-		    acpi_tb_validate_table(&acpi_gbl_root_table_list.tables[i]);
-		if (ACPI_SUCCESS(status)) {
-			*out_table = acpi_gbl_root_table_list.tables[i].pointer;
-			*tbl_size = acpi_gbl_root_table_list.tables[i].length;
-		}
-
-		if (!acpi_gbl_permanent_mmap) {
-			acpi_gbl_root_table_list.tables[i].pointer = NULL;
-		}
-
-		return (status);
+		status = acpi_tb_get_table(table_desc, out_table);
+		break;
 	}
 
-	return (AE_NOT_FOUND);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_get_table_with_size)
-
-acpi_status
-acpi_get_table(char *signature,
-	       u32 instance, struct acpi_table_header **out_table)
-{
-	acpi_size tbl_size;
-
-	return acpi_get_table_with_size(signature,
-		       instance, out_table, &tbl_size);
+	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
+	return (status);
 }
 
 ACPI_EXPORT_SYMBOL(acpi_get_table)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_put_table
+ *
+ * PARAMETERS:  table               - The pointer to the table
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Release a table returned by acpi_get_table() and its clones.
+ *              Note that it is not safe if this function was invoked after an
+ *              uninstallation happened to the original table descriptor.
+ *              Currently there is no OSPMs' requirement to handle such
+ *              situations.
+ *
+ ******************************************************************************/
+void acpi_put_table(struct acpi_table_header *table)
+{
+	u32 i;
+	struct acpi_table_desc *table_desc;
+
+	ACPI_FUNCTION_TRACE(acpi_put_table);
+
+	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
+
+	/* Walk the root table list */
+
+	for (i = 0; i < acpi_gbl_root_table_list.current_table_count; i++) {
+		table_desc = &acpi_gbl_root_table_list.tables[i];
+
+		if (table_desc->pointer != table) {
+			continue;
+		}
+
+		acpi_tb_put_table(table_desc);
+		break;
+	}
+
+	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
+	return_VOID;
+}
+
+ACPI_EXPORT_SYMBOL(acpi_put_table)
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_get_table_by_index
  *
  * PARAMETERS:  table_index         - Table index
- *              table               - Where the pointer to the table is returned
+ *              out_table           - Where the pointer to the table is returned
  *
  * RETURN:      Status and pointer to the requested table
  *
@@ -368,7 +404,7 @@ ACPI_EXPORT_SYMBOL(acpi_get_table)
  *
  ******************************************************************************/
 acpi_status
-acpi_get_table_by_index(u32 table_index, struct acpi_table_header **table)
+acpi_get_table_by_index(u32 table_index, struct acpi_table_header **out_table)
 {
 	acpi_status status;
 
@@ -376,35 +412,33 @@ acpi_get_table_by_index(u32 table_index, struct acpi_table_header **table)
 
 	/* Parameter validation */
 
-	if (!table) {
+	if (!out_table) {
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
+	/*
+	 * Note that the following line is required by some OSPMs, they only
+	 * check if the returned table is NULL instead of the returned status
+	 * to determined if this function is succeeded.
+	 */
+	*out_table = NULL;
+
 	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 
 	/* Validate index */
 
 	if (table_index >= acpi_gbl_root_table_list.current_table_count) {
-		(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
-		return_ACPI_STATUS(AE_BAD_PARAMETER);
+		status = AE_BAD_PARAMETER;
+		goto unlock_and_exit;
 	}
 
-	if (!acpi_gbl_root_table_list.tables[table_index].pointer) {
+	status =
+	    acpi_tb_get_table(&acpi_gbl_root_table_list.tables[table_index],
+			      out_table);
 
-		/* Table is not mapped, map it */
-
-		status =
-		    acpi_tb_validate_table(&acpi_gbl_root_table_list.
-					   tables[table_index]);
-		if (ACPI_FAILURE(status)) {
-			(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
-			return_ACPI_STATUS(status);
-		}
-	}
-
-	*table = acpi_gbl_root_table_list.tables[table_index].pointer;
+unlock_and_exit:
 	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
-	return_ACPI_STATUS(AE_OK);
+	return_ACPI_STATUS(status);
 }
 
 ACPI_EXPORT_SYMBOL(acpi_get_table_by_index)
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 05fe9eb..4ef1e46 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -36,7 +36,7 @@
 #ifdef CONFIG_ACPI_PROCFS_POWER
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #endif
 
 #include <linux/acpi.h>
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 5cbefd7..95855cb 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -974,7 +974,7 @@ void __init acpi_early_init(void)
 	if (!acpi_strict)
 		acpi_gbl_enable_interpreter_slack = TRUE;
 
-	acpi_gbl_permanent_mmap = 1;
+	acpi_permanent_mmap = true;
 
 	/*
 	 * If the machine falls into the DMI check table,
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 312c4b4..2f82b8e 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -2806,12 +2806,13 @@ static int acpi_nfit_add(struct acpi_device *adev)
 	acpi_size sz;
 	int rc = 0;
 
-	status = acpi_get_table_with_size(ACPI_SIG_NFIT, 0, &tbl, &sz);
+	status = acpi_get_table(ACPI_SIG_NFIT, 0, &tbl);
 	if (ACPI_FAILURE(status)) {
 		/* This is ok, we could have an nvdimm hotplugged later */
 		dev_dbg(dev, "failed to find NFIT at startup\n");
 		return 0;
 	}
+	sz = tbl->length;
 
 	acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
 	if (!acpi_desc)
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 9a4c6ab..57fb5f4 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -42,7 +42,7 @@
 #include <linux/semaphore.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "internal.h"
@@ -76,6 +76,7 @@ static struct workqueue_struct *kacpi_notify_wq;
 static struct workqueue_struct *kacpi_hotplug_wq;
 static bool acpi_os_initialized;
 unsigned int acpi_sci_irq = INVALID_ACPI_IRQ;
+bool acpi_permanent_mmap = false;
 
 /*
  * This list of permanent mappings is for memory that may be accessed from
@@ -306,7 +307,7 @@ static void acpi_unmap(acpi_physical_address pg_off, void __iomem *vaddr)
  * virtual address).  If not found, map it, add it to that list and return a
  * pointer to it.
  *
- * During early init (when acpi_gbl_permanent_mmap has not been set yet) this
+ * During early init (when acpi_permanent_mmap has not been set yet) this
  * routine simply calls __acpi_map_table() to get the job done.
  */
 void __iomem *__ref
@@ -322,7 +323,7 @@ acpi_os_map_iomem(acpi_physical_address phys, acpi_size size)
 		return NULL;
 	}
 
-	if (!acpi_gbl_permanent_mmap)
+	if (!acpi_permanent_mmap)
 		return __acpi_map_table((unsigned long)phys, size);
 
 	mutex_lock(&acpi_ioremap_lock);
@@ -392,7 +393,7 @@ static void acpi_os_map_cleanup(struct acpi_ioremap *map)
  * mappings, drop a reference to it and unmap it if there are no more active
  * references to it.
  *
- * During early init (when acpi_gbl_permanent_mmap has not been set yet) this
+ * During early init (when acpi_permanent_mmap has not been set yet) this
  * routine simply calls __acpi_unmap_table() to get the job done.  Since
  * __acpi_unmap_table() is an __init function, the __ref annotation is needed
  * here.
@@ -401,7 +402,7 @@ void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size)
 {
 	struct acpi_ioremap *map;
 
-	if (!acpi_gbl_permanent_mmap) {
+	if (!acpi_permanent_mmap) {
 		__acpi_unmap_table(virt, size);
 		return;
 	}
@@ -426,12 +427,6 @@ void __ref acpi_os_unmap_memory(void *virt, acpi_size size)
 }
 EXPORT_SYMBOL_GPL(acpi_os_unmap_memory);
 
-void __init early_acpi_os_unmap_memory(void __iomem *virt, acpi_size size)
-{
-	if (!acpi_gbl_permanent_mmap)
-		__acpi_unmap_table(virt, size);
-}
-
 int acpi_os_map_generic_address(struct acpi_generic_address *gas)
 {
 	u64 addr;
diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c
index 2a35815..a34669c 100644
--- a/drivers/acpi/proc.c
+++ b/drivers/acpi/proc.c
@@ -4,7 +4,7 @@
 #include <linux/suspend.h>
 #include <linux/bcd.h>
 #include <linux/acpi.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "sleep.h"
 #include "internal.h"
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 5c78ee1..611a558 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -154,18 +154,16 @@ static phys_cpuid_t map_madt_entry(struct acpi_table_madt *madt,
 phys_cpuid_t __init acpi_map_madt_entry(u32 acpi_id)
 {
 	struct acpi_table_madt *madt = NULL;
-	acpi_size tbl_size;
 	phys_cpuid_t rv;
 
-	acpi_get_table_with_size(ACPI_SIG_MADT, 0,
-				 (struct acpi_table_header **)&madt,
-				 &tbl_size);
+	acpi_get_table(ACPI_SIG_MADT, 0,
+		       (struct acpi_table_header **)&madt);
 	if (!madt)
 		return PHYS_CPUID_INVALID;
 
 	rv = map_madt_entry(madt, 1, acpi_id, true);
 
-	early_acpi_os_unmap_memory(madt, tbl_size);
+	acpi_put_table((struct acpi_table_header *)madt);
 
 	return rv;
 }
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index 1fed84a..59c3a5d 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -28,7 +28,7 @@
 #include <linux/cpufreq.h>
 #include <linux/acpi.h>
 #include <acpi/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define PREFIX "ACPI: "
 
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index d51ca1c..a12f96c 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -31,7 +31,7 @@
 #include <linux/acpi.h>
 #include <acpi/processor.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define PREFIX "ACPI: "
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 93b00cf..45dec87 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1120,9 +1120,6 @@ acpi_backlight_cap_match(acpi_handle handle, u32 level, void *context,
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found generic backlight "
 				  "support\n"));
 		*cap |= ACPI_VIDEO_BACKLIGHT;
-		if (!acpi_has_method(handle, "_BQC"))
-			printk(KERN_WARNING FW_BUG PREFIX "No _BQC method, "
-				"cannot determine initial brightness\n");
 		/* We have backlight support, no need to scan further */
 		return AE_CTRL_TERMINATE;
 	}
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index e8d7bc7..b8019c4 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -33,7 +33,6 @@ int __init parse_spcr(bool earlycon)
 {
 	static char opts[64];
 	struct acpi_table_spcr *table;
-	acpi_size table_size;
 	acpi_status status;
 	char *uart;
 	char *iotype;
@@ -43,9 +42,8 @@ int __init parse_spcr(bool earlycon)
 	if (acpi_disabled)
 		return -ENODEV;
 
-	status = acpi_get_table_with_size(ACPI_SIG_SPCR, 0,
-					  (struct acpi_table_header **)&table,
-					  &table_size);
+	status = acpi_get_table(ACPI_SIG_SPCR, 0,
+				(struct acpi_table_header **)&table);
 
 	if (ACPI_FAILURE(status))
 		return -ENOENT;
@@ -106,6 +104,6 @@ int __init parse_spcr(bool earlycon)
 	err = add_preferred_console(uart, 0, opts + strlen(uart) + 1);
 
 done:
-	early_acpi_os_unmap_memory((void __iomem *)table, table_size);
+	acpi_put_table((struct acpi_table_header *)table);
 	return err;
 }
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index cdd56c4..2604189d 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -333,7 +333,6 @@ acpi_table_parse_entries_array(char *id,
 			 unsigned int max_entries)
 {
 	struct acpi_table_header *table_header = NULL;
-	acpi_size tbl_size;
 	int count;
 	u32 instance = 0;
 
@@ -346,7 +345,7 @@ acpi_table_parse_entries_array(char *id,
 	if (!strncmp(id, ACPI_SIG_MADT, 4))
 		instance = acpi_apic_instance;
 
-	acpi_get_table_with_size(id, instance, &table_header, &tbl_size);
+	acpi_get_table(id, instance, &table_header);
 	if (!table_header) {
 		pr_warn("%4.4s not present\n", id);
 		return -ENODEV;
@@ -355,7 +354,7 @@ acpi_table_parse_entries_array(char *id,
 	count = acpi_parse_entries_array(id, table_size, table_header,
 			proc, proc_num, max_entries);
 
-	early_acpi_os_unmap_memory((char *)table_header, tbl_size);
+	acpi_put_table(table_header);
 	return count;
 }
 
@@ -397,7 +396,6 @@ acpi_table_parse_madt(enum acpi_madt_type id,
 int __init acpi_table_parse(char *id, acpi_tbl_table_handler handler)
 {
 	struct acpi_table_header *table = NULL;
-	acpi_size tbl_size;
 
 	if (acpi_disabled)
 		return -ENODEV;
@@ -406,13 +404,13 @@ int __init acpi_table_parse(char *id, acpi_tbl_table_handler handler)
 		return -EINVAL;
 
 	if (strncmp(id, ACPI_SIG_MADT, 4) == 0)
-		acpi_get_table_with_size(id, acpi_apic_instance, &table, &tbl_size);
+		acpi_get_table(id, acpi_apic_instance, &table);
 	else
-		acpi_get_table_with_size(id, 0, &table, &tbl_size);
+		acpi_get_table(id, 0, &table);
 
 	if (table) {
 		handler(table);
-		early_acpi_os_unmap_memory(table, tbl_size);
+		acpi_put_table(table);
 		return 0;
 	} else
 		return -ENODEV;
@@ -426,16 +424,15 @@ int __init acpi_table_parse(char *id, acpi_tbl_table_handler handler)
 static void __init check_multiple_madt(void)
 {
 	struct acpi_table_header *table = NULL;
-	acpi_size tbl_size;
 
-	acpi_get_table_with_size(ACPI_SIG_MADT, 2, &table, &tbl_size);
+	acpi_get_table(ACPI_SIG_MADT, 2, &table);
 	if (table) {
 		pr_warn("BIOS bug: multiple APIC/MADT found, using %d\n",
 			acpi_apic_instance);
 		pr_warn("If \"acpi_apic_instance=%d\" works better, "
 			"notify linux-acpi@vger.kernel.org\n",
 			acpi_apic_instance ? 0 : 2);
-		early_acpi_os_unmap_memory(table, tbl_size);
+		acpi_put_table(table);
 
 	} else
 		acpi_apic_instance = 0;
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 35e8fbc..1d0417b 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -40,7 +40,7 @@
 #include <linux/thermal.h>
 #include <linux/acpi.h>
 #include <linux/workqueue.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define PREFIX "ACPI: "
 
diff --git a/drivers/atm/adummy.c b/drivers/atm/adummy.c
index f9b983a..1fd25e8 100644
--- a/drivers/atm/adummy.c
+++ b/drivers/atm/adummy.c
@@ -16,7 +16,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/atmdev.h>
 #include <linux/atm.h>
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index 480fa6f..3ef6253e1 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -10,7 +10,7 @@
 #include <linux/bitops.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 
 
diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c
index 40c2d56..c53a9dd 100644
--- a/drivers/atm/eni.c
+++ b/drivers/atm/eni.c
@@ -21,7 +21,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/string.h>
 #include <asm/byteorder.h>
 
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 85aaf22..80c2ddc 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -52,7 +52,7 @@
 #include <asm/string.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/wait.h>
 
 #include "firestream.h"
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index 81aaa50..637c3e6 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -43,7 +43,7 @@
 #include <asm/irq.h>
 #include <asm/dma.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 
 #ifdef CONFIG_SBUS
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index 31b513a..3617659 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -71,7 +71,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/atmdev.h>
 #include <linux/atm.h>
diff --git a/drivers/atm/horizon.c b/drivers/atm/horizon.c
index 5fc81e2..584aa88 100644
--- a/drivers/atm/horizon.c
+++ b/drivers/atm/horizon.c
@@ -45,7 +45,7 @@
 
 #include <asm/io.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/string.h>
 #include <asm/byteorder.h>
 
diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index feb023d..082aa02 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -17,7 +17,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <asm/param.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "idt77105.h"
 
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 074616b..471ddfd 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -45,7 +45,7 @@
 #include <linux/slab.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <asm/byteorder.h>
 
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index b275676..8640baf 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -58,7 +58,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>  
 #include <linux/atomic.h>
-#include <asm/uaccess.h>  
+#include <linux/uaccess.h>  
 #include <asm/string.h>  
 #include <asm/byteorder.h>  
 #include <linux/vmalloc.h>
diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index c7296b5..cb28579 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -50,7 +50,7 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/etherdevice.h>
 #include "nicstar.h"
diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c
index 0215934..b036314 100644
--- a/drivers/atm/suni.c
+++ b/drivers/atm/suni.c
@@ -23,7 +23,7 @@
 #include <linux/atm_suni.h>
 #include <linux/slab.h>
 #include <asm/param.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 
 #include "suni.h"
diff --git a/drivers/atm/uPD98402.c b/drivers/atm/uPD98402.c
index 5120a96..4fa13a8 100644
--- a/drivers/atm/uPD98402.c
+++ b/drivers/atm/uPD98402.c
@@ -10,7 +10,7 @@
 #include <linux/sonet.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 
 #include "uPD98402.h"
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index d3dc954..292dec1 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -27,7 +27,7 @@
 #include <asm/string.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "uPD98401.h"
 #include "uPD98402.h"
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index 1e3903d..eb3af27 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -363,6 +363,7 @@ static ssize_t file_name##_show(struct device *dev,		\
 	return sprintf(buf, "%u\n", this_leaf->object);		\
 }
 
+show_one(id, id);
 show_one(level, level);
 show_one(coherency_line_size, coherency_line_size);
 show_one(number_of_sets, number_of_sets);
@@ -444,6 +445,7 @@ static ssize_t write_policy_show(struct device *dev,
 	return n;
 }
 
+static DEVICE_ATTR_RO(id);
 static DEVICE_ATTR_RO(level);
 static DEVICE_ATTR_RO(type);
 static DEVICE_ATTR_RO(coherency_line_size);
@@ -457,6 +459,7 @@ static DEVICE_ATTR_RO(shared_cpu_list);
 static DEVICE_ATTR_RO(physical_line_partition);
 
 static struct attribute *cache_default_attrs[] = {
+	&dev_attr_id.attr,
 	&dev_attr_type.attr,
 	&dev_attr_level.attr,
 	&dev_attr_shared_cpu_map.attr,
@@ -480,6 +483,8 @@ cache_default_attrs_is_visible(struct kobject *kobj,
 	const struct cpumask *mask = &this_leaf->shared_cpu_map;
 	umode_t mode = attr->mode;
 
+	if ((attr == &dev_attr_id.attr) && (this_leaf->attributes & CACHE_ID))
+		return mode;
 	if ((attr == &dev_attr_type.attr) && this_leaf->type)
 		return mode;
 	if ((attr == &dev_attr_level.attr) && this_leaf->level)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index bb69e58..8ab8ea1 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -23,7 +23,7 @@
 #include <linux/slab.h>
 
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static DEFINE_MUTEX(mem_sysfs_mutex);
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 5711708..a5e1262 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -544,6 +544,7 @@ static int genpd_runtime_suspend(struct device *dev)
 		return -EBUSY;
 
 	/* Measure suspend latency. */
+	time_start = 0;
 	if (runtime_pm)
 		time_start = ktime_get();
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 48c6294..249e030 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -194,7 +194,7 @@ void device_pm_move_last(struct device *dev)
 
 static ktime_t initcall_debug_start(struct device *dev)
 {
-	ktime_t calltime = ktime_set(0, 0);
+	ktime_t calltime = 0;
 
 	if (pm_print_times_enabled) {
 		pr_info("calling  %s+ @ %i, parent: %s\n",
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index bf9ba26..f546f8f 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -998,14 +998,14 @@ static int print_wakeup_source_stats(struct seq_file *m,
 
 		active_time = ktime_sub(now, ws->last_time);
 		total_time = ktime_add(total_time, active_time);
-		if (active_time.tv64 > max_time.tv64)
+		if (active_time > max_time)
 			max_time = active_time;
 
 		if (ws->autosleep_enabled)
 			prevent_sleep_time = ktime_add(prevent_sleep_time,
 				ktime_sub(now, ws->start_prevent_time));
 	} else {
-		active_time = ktime_set(0, 0);
+		active_time = 0;
 	}
 
 	seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n",
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 0809cda..26a51be 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -48,7 +48,7 @@
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "DAC960.h"
 
 #define DAC960_GAM_MINOR	252
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 5fd50a2..a328f67 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -70,7 +70,7 @@
 #include <linux/platform_device.h>
 
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
 #include <asm/irq.h>
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index ad793f3..3adc32a 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -23,7 +23,7 @@
 #include <linux/pfn_t.h>
 #endif
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define SECTOR_SHIFT		9
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index db9d6bb..e5c5b8e 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -43,7 +43,7 @@
 #include <linux/mutex.h>
 #include <linux/bitmap.h>
 #include <linux/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/dma-mapping.h>
 #include <linux/blkdev.h>
diff --git a/drivers/block/cryptoloop.c b/drivers/block/cryptoloop.c
index 3d31761..74e03aa 100644
--- a/drivers/block/cryptoloop.c
+++ b/drivers/block/cryptoloop.c
@@ -26,7 +26,7 @@
 #include <linux/string.h>
 #include <linux/blkdev.h>
 #include <linux/scatterlist.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "loop.h"
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index 3abb121..a9b48ed 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -45,7 +45,7 @@
 
 #define REALLY_SLOW_IO
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef __arm__
 #undef  HD_IRQ
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 4af8187..f347285 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -78,7 +78,7 @@
 #include <linux/uio.h>
 #include "loop.h"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static DEFINE_IDR(loop_index_idr);
 static DEFINE_MUTEX(loop_index_mutex);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 99c8446..38c576f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -36,7 +36,7 @@
 #include <linux/debugfs.h>
 #include <linux/blk-mq.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/types.h>
 
 #include <linux/nbd.h>
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 4943ee2..c0e14e5 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -257,7 +257,7 @@ static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 
 static void null_cmd_end_timer(struct nullb_cmd *cmd)
 {
-	ktime_t kt = ktime_set(0, completion_nsec);
+	ktime_t kt = completion_nsec;
 
 	hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL);
 }
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 9336236..5fd2d0e 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -139,7 +139,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_SLV, D_DLY};
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static DEFINE_MUTEX(pcd_mutex);
 static DEFINE_SPINLOCK(pcd_lock);
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 78a39f7..c3ed2fc 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -155,7 +155,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_GEO, D_SBY, D_DLY, D_SLV};
 #include <linux/blkpg.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/workqueue.h>
 
 static DEFINE_MUTEX(pd_mutex);
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index 7a7d977..ed93e8b 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -155,7 +155,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_SLV, D_LUN, D_DLY};
 #include <linux/blkdev.h>
 #include <linux/blkpg.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static DEFINE_MUTEX(pf_mutex);
 static DEFINE_SPINLOCK(pf_spin_lock);
diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c
index bfbd4c8..5db955f 100644
--- a/drivers/block/paride/pg.c
+++ b/drivers/block/paride/pg.c
@@ -166,7 +166,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_SLV, D_DLY};
 #include <linux/mutex.h>
 #include <linux/jiffies.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 module_param(verbose, int, 0644);
 module_param(major, int, 0);
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 216a94f..61fc6824 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -150,7 +150,7 @@ static int (*drives[4])[6] = {&drive0, &drive1, &drive2, &drive3};
 #include <linux/sched.h>	/* current, TASK_*, schedule_timeout() */
 #include <linux/mutex.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 module_param(verbose, int, 0);
 module_param(major, int, 0);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 95c98de..1b94c1c 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -68,7 +68,7 @@
 #include <linux/debugfs.h>
 #include <linux/device.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define DRIVER_NAME	"pktcdvd"
 
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index c264f2d..aabd8e9 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -34,7 +34,7 @@
 #include <asm/io.h>
 #include <asm/dbdma.h>
 #include <asm/prom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mediabay.h>
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index ba4bfe9..0e93ad7 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -29,7 +29,7 @@
 #include <linux/completion.h>
 #include <linux/scatterlist.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #if 0
 #define CARM_DEBUG
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 46f4c71..c141cc3 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -54,7 +54,7 @@
 
 #include "umem.h"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #define MM_MAXCARDS 4
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 2316333..c49da15 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -1796,7 +1796,7 @@ static int __init cci_platform_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCI_ONLINE,
-				      "AP_PERF_ARM_CCI_ONLINE", NULL,
+				      "perf/arm/cci:online", NULL,
 				      cci_pmu_offline_cpu);
 	if (ret)
 		return ret;
diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c
index d1074d9..4d6a2b7 100644
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -1562,7 +1562,7 @@ static int __init arm_ccn_init(void)
 	int i, ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-				      "AP_PERF_ARM_CCN_ONLINE", NULL,
+				      "perf/arm/ccn:online", NULL,
 				      arm_ccn_pmu_offline_cpu);
 	if (ret)
 		return ret;
@@ -1570,7 +1570,10 @@ static int __init arm_ccn_init(void)
 	for (i = 0; i < ARRAY_SIZE(arm_ccn_pmu_events); i++)
 		arm_ccn_pmu_events_attrs[i] = &arm_ccn_pmu_events[i].attr.attr;
 
-	return platform_driver_register(&arm_ccn_driver);
+	ret = platform_driver_register(&arm_ccn_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_CCN_ONLINE);
+	return ret;
 }
 
 static void __exit arm_ccn_exit(void)
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 5d475b3..59cca72 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -282,7 +282,7 @@
 #include <linux/blkdev.h>
 #include <linux/times.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* used to tell the module to turn on full debugging messages */
 static bool debug;
diff --git a/drivers/char/agp/compat_ioctl.c b/drivers/char/agp/compat_ioctl.c
index a48e05b..2053f70 100644
--- a/drivers/char/agp/compat_ioctl.c
+++ b/drivers/char/agp/compat_ioctl.c
@@ -31,7 +31,7 @@
 #include <linux/fs.h>
 #include <linux/agpgart.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "agp.h"
 #include "compat_ioctl.h"
 
diff --git a/drivers/char/agp/frontend.c b/drivers/char/agp/frontend.c
index 0f64d14..f695588 100644
--- a/drivers/char/agp/frontend.c
+++ b/drivers/char/agp/frontend.c
@@ -38,7 +38,7 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include "agp.h"
 
diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c
index 1479030..e5c62dc 100644
--- a/drivers/char/applicom.c
+++ b/drivers/char/applicom.c
@@ -34,7 +34,7 @@
 #include <linux/fs.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "applicom.h"
 
diff --git a/drivers/char/bfin-otp.c b/drivers/char/bfin-otp.c
index 35d46da..0584025 100644
--- a/drivers/char/bfin-otp.c
+++ b/drivers/char/bfin-otp.c
@@ -20,7 +20,7 @@
 
 #include <asm/blackfin.h>
 #include <asm/bfrom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define stamp(fmt, args...) pr_debug("%s:%i: " fmt "\n", __func__, __LINE__, ## args)
 #define stampit() stamp("here i am")
diff --git a/drivers/char/ds1620.c b/drivers/char/ds1620.c
index 0fae529..eb53cba 100644
--- a/drivers/char/ds1620.c
+++ b/drivers/char/ds1620.c
@@ -13,7 +13,7 @@
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/therm.h>
 
 #ifdef CONFIG_PROC_FS
diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c
index 65a8d96..5847139 100644
--- a/drivers/char/dtlk.c
+++ b/drivers/char/dtlk.c
@@ -59,7 +59,7 @@
 #include <linux/sched.h>
 #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/uaccess.h>	/* for get_user, etc. */
 #include <linux/wait.h>		/* for wait_queue */
 #include <linux/init.h>		/* for __init, module_{init,exit} */
 #include <linux/poll.h>		/* for POLLIN, etc. */
diff --git a/drivers/char/generic_nvram.c b/drivers/char/generic_nvram.c
index 073db95..14e728f 100644
--- a/drivers/char/generic_nvram.c
+++ b/drivers/char/generic_nvram.c
@@ -21,7 +21,7 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/nvram.h>
 #ifdef CONFIG_PPC_PMAC
 #include <asm/machdep.h>
diff --git a/drivers/char/hangcheck-timer.c b/drivers/char/hangcheck-timer.c
index a7c5c59..4f33737 100644
--- a/drivers/char/hangcheck-timer.c
+++ b/drivers/char/hangcheck-timer.c
@@ -46,7 +46,7 @@
 #include <linux/reboot.h>
 #include <linux/init.h>
 #include <linux/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/sysrq.h>
 #include <linux/timer.h>
 #include <linux/hrtimer.h>
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index be54e53..20b32bb 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -69,9 +69,9 @@ static u32 hpet_nhpet, hpet_max_freq = HPET_USER_FREQ;
 #ifdef CONFIG_IA64
 static void __iomem *hpet_mctr;
 
-static cycle_t read_hpet(struct clocksource *cs)
+static u64 read_hpet(struct clocksource *cs)
 {
-	return (cycle_t)read_counter((void __iomem *)hpet_mctr);
+	return (u64)read_counter((void __iomem *)hpet_mctr);
 }
 
 static struct clocksource clocksource_hpet = {
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index f976641..6ce5ce8 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -43,7 +43,7 @@
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/err.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 #define RNG_MODULE_NAME		"hw_random"
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 4facc75..4035495 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -43,7 +43,7 @@
 #include <linux/kdebug.h>
 #include <linux/rwsem.h>
 #include <linux/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/notifier.h>
 #include <linux/nmi.h>
 #include <linux/reboot.h>
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index c4094c4..5b67427 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -134,7 +134,7 @@
 #include <linux/lp.h>
 
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* if you have more than 8 printers, remember to increase LP_NO */
 #define LP_NO 8
diff --git a/drivers/char/mbcs.c b/drivers/char/mbcs.c
index 67d4264..8c9216a 100644
--- a/drivers/char/mbcs.c
+++ b/drivers/char/mbcs.c
@@ -28,7 +28,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/intr.h>
diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
index 3d6c067..f786b18 100644
--- a/drivers/char/mmtimer.c
+++ b/drivers/char/mmtimer.c
@@ -35,7 +35,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/intr.h>
 #include <asm/sn/shub_mmr.h>
diff --git a/drivers/char/mwave/3780i.c b/drivers/char/mwave/3780i.c
index 972c40a..4a8937f 100644
--- a/drivers/char/mwave/3780i.c
+++ b/drivers/char/mwave/3780i.c
@@ -54,7 +54,7 @@
 #include <linux/sched.h>	/* cond_resched() */
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 #include "smapi.h"
 #include "mwavedd.h"
diff --git a/drivers/char/mwave/mwavedd.h b/drivers/char/mwave/mwavedd.h
index 37e0a49..21cb09c 100644
--- a/drivers/char/mwave/mwavedd.h
+++ b/drivers/char/mwave/mwavedd.h
@@ -53,7 +53,7 @@
 #include "smapi.h"
 #include "mwavepub.h"
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/wait.h>
 
 extern int mwave_debug;
diff --git a/drivers/char/nsc_gpio.c b/drivers/char/nsc_gpio.c
index b07b119..2a91bf0 100644
--- a/drivers/char/nsc_gpio.c
+++ b/drivers/char/nsc_gpio.c
@@ -14,7 +14,7 @@
 #include <linux/init.h>
 #include <linux/nsc_gpio.h>
 #include <linux/platform_device.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #define NAME "nsc_gpio"
diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c
index 0e18442..a5b1eb2 100644
--- a/drivers/char/nwbutton.c
+++ b/drivers/char/nwbutton.c
@@ -16,7 +16,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 #include <asm/mach-types.h>
 
diff --git a/drivers/char/nwflash.c b/drivers/char/nwflash.c
index dbe598d..a284ae2 100644
--- a/drivers/char/nwflash.c
+++ b/drivers/char/nwflash.c
@@ -31,7 +31,7 @@
 #include <asm/hardware/dec21285.h>
 #include <asm/io.h>
 #include <asm/mach-types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*****************************************************************************/
 #include <asm/nwflash.h>
diff --git a/drivers/char/pc8736x_gpio.c b/drivers/char/pc8736x_gpio.c
index 3f79a9f..5f4be88 100644
--- a/drivers/char/pc8736x_gpio.c
+++ b/drivers/char/pc8736x_gpio.c
@@ -20,7 +20,7 @@
 #include <linux/mutex.h>
 #include <linux/nsc_gpio.h>
 #include <linux/platform_device.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define DEVNAME "pc8736x_gpio"
 
diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c
index fc061f7..d712325 100644
--- a/drivers/char/pcmcia/cm4040_cs.c
+++ b/drivers/char/pcmcia/cm4040_cs.c
@@ -26,7 +26,7 @@
 #include <linux/poll.h>
 #include <linux/mutex.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #include <pcmcia/cistpl.h>
diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c
index a7dd5f4..d136db1 100644
--- a/drivers/char/pcmcia/synclink_cs.c
+++ b/drivers/char/pcmcia/synclink_cs.c
@@ -84,7 +84,7 @@
 #define PUT_USER(error,value,addr) error = put_user(value,addr)
 #define COPY_TO_USER(error,dest,src,size) error = copy_to_user(dest,src,size) ? -EFAULT : 0
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static MGSL_PARAMS default_params = {
 	MGSL_MODE_HDLC,			/* unsigned long mode */
diff --git a/drivers/char/random.c b/drivers/char/random.c
index d6876d5..1ef2640 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -265,7 +265,7 @@
 #include <crypto/chacha20.h>
 
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
 #include <asm/io.h>
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index e83b2ad..293167c 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -24,7 +24,7 @@
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 struct raw_device_data {
 	struct block_device *binding;
diff --git a/drivers/char/scx200_gpio.c b/drivers/char/scx200_gpio.c
index 0bc135b..903761b 100644
--- a/drivers/char/scx200_gpio.c
+++ b/drivers/char/scx200_gpio.c
@@ -12,7 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #include <linux/types.h>
diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c
index 719c5b4..4fa7fcd 100644
--- a/drivers/char/sonypi.c
+++ b/drivers/char/sonypi.c
@@ -52,7 +52,7 @@
 #include <linux/platform_device.h>
 #include <linux/gfp.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #include <linux/sonypi.h>
diff --git a/drivers/char/tlclk.c b/drivers/char/tlclk.c
index 100cd1d..572a517 100644
--- a/drivers/char/tlclk.c
+++ b/drivers/char/tlclk.c
@@ -44,7 +44,7 @@
 #include <linux/miscdevice.h>
 #include <linux/platform_device.h>
 #include <asm/io.h>		/* inb/outb */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 MODULE_AUTHOR("Sebastien Bouchard <sebastien.bouchard@ca.kontron.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/char/toshiba.c b/drivers/char/toshiba.c
index f5a45d8..5488516 100644
--- a/drivers/char/toshiba.c
+++ b/drivers/char/toshiba.c
@@ -63,7 +63,7 @@
 #include <linux/miscdevice.h>
 #include <linux/ioport.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/init.h>
 #include <linux/stat.h>
 #include <linux/proc_fs.h>
diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c
index c07dfe5..3e6b23c 100644
--- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c
+++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c
@@ -88,7 +88,7 @@
 #include <linux/slab.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_OF
 /* For open firmware. */
diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c
index 28037d0..1961e35 100644
--- a/drivers/clocksource/acpi_pm.c
+++ b/drivers/clocksource/acpi_pm.c
@@ -58,16 +58,16 @@ u32 acpi_pm_read_verified(void)
 	return v2;
 }
 
-static cycle_t acpi_pm_read(struct clocksource *cs)
+static u64 acpi_pm_read(struct clocksource *cs)
 {
-	return (cycle_t)read_pmtmr();
+	return (u64)read_pmtmr();
 }
 
 static struct clocksource clocksource_acpi_pm = {
 	.name		= "acpi_pm",
 	.rating		= 200,
 	.read		= acpi_pm_read,
-	.mask		= (cycle_t)ACPI_PM_MASK,
+	.mask		= (u64)ACPI_PM_MASK,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
@@ -81,9 +81,9 @@ static int __init acpi_pm_good_setup(char *__str)
 }
 __setup("acpi_pm_good", acpi_pm_good_setup);
 
-static cycle_t acpi_pm_read_slow(struct clocksource *cs)
+static u64 acpi_pm_read_slow(struct clocksource *cs)
 {
-	return (cycle_t)acpi_pm_read_verified();
+	return (u64)acpi_pm_read_verified();
 }
 
 static inline void acpi_pm_need_workaround(void)
@@ -145,7 +145,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_LE,
  */
 static int verify_pmtmr_rate(void)
 {
-	cycle_t value1, value2;
+	u64 value1, value2;
 	unsigned long count, delta;
 
 	mach_prepare_counter();
@@ -175,7 +175,7 @@ static int verify_pmtmr_rate(void)
 
 static int __init init_acpi_pm_clocksource(void)
 {
-	cycle_t value1, value2;
+	u64 value1, value2;
 	unsigned int i, j = 0;
 
 	if (!pmtmr_ioport)
diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c
index a49748d..7517f95 100644
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -56,7 +56,7 @@ static int noinline arc_get_timer_clk(struct device_node *node)
 
 #ifdef CONFIG_ARC_TIMERS_64BIT
 
-static cycle_t arc_read_gfrc(struct clocksource *cs)
+static u64 arc_read_gfrc(struct clocksource *cs)
 {
 	unsigned long flags;
 	u32 l, h;
@@ -71,7 +71,7 @@ static cycle_t arc_read_gfrc(struct clocksource *cs)
 
 	local_irq_restore(flags);
 
-	return (((cycle_t)h) << 32) | l;
+	return (((u64)h) << 32) | l;
 }
 
 static struct clocksource arc_counter_gfrc = {
@@ -105,7 +105,7 @@ CLOCKSOURCE_OF_DECLARE(arc_gfrc, "snps,archs-timer-gfrc", arc_cs_setup_gfrc);
 #define AUX_RTC_LOW	0x104
 #define AUX_RTC_HIGH	0x105
 
-static cycle_t arc_read_rtc(struct clocksource *cs)
+static u64 arc_read_rtc(struct clocksource *cs)
 {
 	unsigned long status;
 	u32 l, h;
@@ -122,7 +122,7 @@ static cycle_t arc_read_rtc(struct clocksource *cs)
 		status = read_aux_reg(AUX_RTC_CTRL);
 	} while (!(status & _BITUL(31)));
 
-	return (((cycle_t)h) << 32) | l;
+	return (((u64)h) << 32) | l;
 }
 
 static struct clocksource arc_counter_rtc = {
@@ -166,9 +166,9 @@ CLOCKSOURCE_OF_DECLARE(arc_rtc, "snps,archs-timer-rtc", arc_cs_setup_rtc);
  * 32bit TIMER1 to keep counting monotonically and wraparound
  */
 
-static cycle_t arc_read_timer1(struct clocksource *cs)
+static u64 arc_read_timer1(struct clocksource *cs)
 {
-	return (cycle_t) read_aux_reg(ARC_REG_TIMER1_CNT);
+	return (u64) read_aux_reg(ARC_REG_TIMER1_CNT);
 }
 
 static struct clocksource arc_counter_timer1 = {
@@ -309,7 +309,7 @@ static int __init arc_clockevent_setup(struct device_node *node)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_ARC_TIMER_STARTING,
-				"AP_ARC_TIMER_STARTING",
+				"clockevents/arc/timer:starting",
 				arc_timer_starting_cpu,
 				arc_timer_dying_cpu);
 	if (ret) {
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 02fef68..4c8c3fb 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -562,12 +562,12 @@ static u64 arch_counter_get_cntvct_mem(void)
  */
 u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
 
-static cycle_t arch_counter_read(struct clocksource *cs)
+static u64 arch_counter_read(struct clocksource *cs)
 {
 	return arch_timer_read_counter();
 }
 
-static cycle_t arch_counter_read_cc(const struct cyclecounter *cc)
+static u64 arch_counter_read_cc(const struct cyclecounter *cc)
 {
 	return arch_timer_read_counter();
 }
@@ -738,7 +738,7 @@ static int __init arch_timer_register(void)
 
 	/* Register and immediately configure the timer on the boot CPU */
 	err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING,
-				"AP_ARM_ARCH_TIMER_STARTING",
+				"clockevents/arm/arch_timer:starting",
 				arch_timer_starting_cpu, arch_timer_dying_cpu);
 	if (err)
 		goto out_unreg_cpupm;
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index 8da0329..123ed20 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -195,7 +195,7 @@ static int gt_dying_cpu(unsigned int cpu)
 	return 0;
 }
 
-static cycle_t gt_clocksource_read(struct clocksource *cs)
+static u64 gt_clocksource_read(struct clocksource *cs)
 {
 	return gt_counter_read();
 }
@@ -316,7 +316,7 @@ static int __init global_timer_of_register(struct device_node *np)
 		goto out_irq;
 	
 	err = cpuhp_setup_state(CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
-				"AP_ARM_GLOBAL_TIMER_STARTING",
+				"clockevents/arm/global_timer:starting",
 				gt_starting_cpu, gt_dying_cpu);
 	if (err)
 		goto out_irq;
diff --git a/drivers/clocksource/cadence_ttc_timer.c b/drivers/clocksource/cadence_ttc_timer.c
index fbfbdec..44e5e95 100644
--- a/drivers/clocksource/cadence_ttc_timer.c
+++ b/drivers/clocksource/cadence_ttc_timer.c
@@ -158,11 +158,11 @@ static irqreturn_t ttc_clock_event_interrupt(int irq, void *dev_id)
  *
  * returns: Current timer counter register value
  **/
-static cycle_t __ttc_clocksource_read(struct clocksource *cs)
+static u64 __ttc_clocksource_read(struct clocksource *cs)
 {
 	struct ttc_timer *timer = &to_ttc_timer_clksrc(cs)->ttc;
 
-	return (cycle_t)readl_relaxed(timer->base_addr +
+	return (u64)readl_relaxed(timer->base_addr +
 				TTC_COUNT_VAL_OFFSET);
 }
 
diff --git a/drivers/clocksource/clksrc-dbx500-prcmu.c b/drivers/clocksource/clksrc-dbx500-prcmu.c
index 77a365f..c69e277 100644
--- a/drivers/clocksource/clksrc-dbx500-prcmu.c
+++ b/drivers/clocksource/clksrc-dbx500-prcmu.c
@@ -30,7 +30,7 @@
 
 static void __iomem *clksrc_dbx500_timer_base;
 
-static cycle_t notrace clksrc_dbx500_prcmu_read(struct clocksource *cs)
+static u64 notrace clksrc_dbx500_prcmu_read(struct clocksource *cs)
 {
 	void __iomem *base = clksrc_dbx500_timer_base;
 	u32 count, count2;
diff --git a/drivers/clocksource/dummy_timer.c b/drivers/clocksource/dummy_timer.c
index 89f1c2e..01f3f5a 100644
--- a/drivers/clocksource/dummy_timer.c
+++ b/drivers/clocksource/dummy_timer.c
@@ -34,7 +34,7 @@ static int dummy_timer_starting_cpu(unsigned int cpu)
 static int __init dummy_timer_register(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_DUMMY_TIMER_STARTING,
-				 "AP_DUMMY_TIMER_STARTING",
+				 "clockevents/dummy_timer:starting",
 				 dummy_timer_starting_cpu, NULL);
 }
 early_initcall(dummy_timer_register);
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index 797505a..63e4f55 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -348,7 +348,7 @@ void dw_apb_clocksource_start(struct dw_apb_clocksource *dw_cs)
 	dw_apb_clocksource_read(dw_cs);
 }
 
-static cycle_t __apbt_read_clocksource(struct clocksource *cs)
+static u64 __apbt_read_clocksource(struct clocksource *cs)
 {
 	u32 current_count;
 	struct dw_apb_clocksource *dw_cs =
@@ -357,7 +357,7 @@ static cycle_t __apbt_read_clocksource(struct clocksource *cs)
 	current_count = apbt_readl_relaxed(&dw_cs->timer,
 					APBTMR_N_CURRENT_VALUE);
 
-	return (cycle_t)~current_count;
+	return (u64)~current_count;
 }
 
 static void apbt_restart_clocksource(struct clocksource *cs)
@@ -416,7 +416,7 @@ void dw_apb_clocksource_register(struct dw_apb_clocksource *dw_cs)
  *
  * @dw_cs:	The clocksource to read.
  */
-cycle_t dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs)
+u64 dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs)
 {
-	return (cycle_t)~apbt_readl(&dw_cs->timer, APBTMR_N_CURRENT_VALUE);
+	return (u64)~apbt_readl(&dw_cs->timer, APBTMR_N_CURRENT_VALUE);
 }
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index 19bb179..aff87df 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -110,9 +110,9 @@ static void em_sti_disable(struct em_sti_priv *p)
 	clk_disable_unprepare(p->clk);
 }
 
-static cycle_t em_sti_count(struct em_sti_priv *p)
+static u64 em_sti_count(struct em_sti_priv *p)
 {
-	cycle_t ticks;
+	u64 ticks;
 	unsigned long flags;
 
 	/* the STI hardware buffers the 48-bit count, but to
@@ -121,14 +121,14 @@ static cycle_t em_sti_count(struct em_sti_priv *p)
 	 * Always read STI_COUNT_H before STI_COUNT_L.
 	 */
 	raw_spin_lock_irqsave(&p->lock, flags);
-	ticks = (cycle_t)(em_sti_read(p, STI_COUNT_H) & 0xffff) << 32;
+	ticks = (u64)(em_sti_read(p, STI_COUNT_H) & 0xffff) << 32;
 	ticks |= em_sti_read(p, STI_COUNT_L);
 	raw_spin_unlock_irqrestore(&p->lock, flags);
 
 	return ticks;
 }
 
-static cycle_t em_sti_set_next(struct em_sti_priv *p, cycle_t next)
+static u64 em_sti_set_next(struct em_sti_priv *p, u64 next)
 {
 	unsigned long flags;
 
@@ -198,7 +198,7 @@ static struct em_sti_priv *cs_to_em_sti(struct clocksource *cs)
 	return container_of(cs, struct em_sti_priv, cs);
 }
 
-static cycle_t em_sti_clocksource_read(struct clocksource *cs)
+static u64 em_sti_clocksource_read(struct clocksource *cs)
 {
 	return em_sti_count(cs_to_em_sti(cs));
 }
@@ -271,7 +271,7 @@ static int em_sti_clock_event_next(unsigned long delta,
 				   struct clock_event_device *ced)
 {
 	struct em_sti_priv *p = ced_to_em_sti(ced);
-	cycle_t next;
+	u64 next;
 	int safe;
 
 	next = em_sti_set_next(p, em_sti_count(p) + delta);
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 8f3488b..4da1dc2 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -183,7 +183,7 @@ static u64 exynos4_read_count_64(void)
 		hi2 = readl_relaxed(reg_base + EXYNOS4_MCT_G_CNT_U);
 	} while (hi != hi2);
 
-	return ((cycle_t)hi << 32) | lo;
+	return ((u64)hi << 32) | lo;
 }
 
 /**
@@ -199,7 +199,7 @@ static u32 notrace exynos4_read_count_32(void)
 	return readl_relaxed(reg_base + EXYNOS4_MCT_G_CNT_L);
 }
 
-static cycle_t exynos4_frc_read(struct clocksource *cs)
+static u64 exynos4_frc_read(struct clocksource *cs)
 {
 	return exynos4_read_count_32();
 }
@@ -266,7 +266,7 @@ static void exynos4_mct_comp0_stop(void)
 static void exynos4_mct_comp0_start(bool periodic, unsigned long cycles)
 {
 	unsigned int tcon;
-	cycle_t comp_cycle;
+	u64 comp_cycle;
 
 	tcon = readl_relaxed(reg_base + EXYNOS4_MCT_G_TCON);
 
@@ -552,7 +552,7 @@ static int __init exynos4_timer_resources(struct device_node *np, void __iomem *
 
 	/* Install hotplug callbacks which configure the timer on this CPU */
 	err = cpuhp_setup_state(CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
-				"AP_EXYNOS4_MCT_TIMER_STARTING",
+				"clockevents/exynos4/mct_timer:starting",
 				exynos4_mct_starting_cpu,
 				exynos4_mct_dying_cpu);
 	if (err)
diff --git a/drivers/clocksource/h8300_timer16.c b/drivers/clocksource/h8300_timer16.c
index 07d9d5b..5b27fb9 100644
--- a/drivers/clocksource/h8300_timer16.c
+++ b/drivers/clocksource/h8300_timer16.c
@@ -72,7 +72,7 @@ static inline struct timer16_priv *cs_to_priv(struct clocksource *cs)
 	return container_of(cs, struct timer16_priv, cs);
 }
 
-static cycle_t timer16_clocksource_read(struct clocksource *cs)
+static u64 timer16_clocksource_read(struct clocksource *cs)
 {
 	struct timer16_priv *p = cs_to_priv(cs);
 	unsigned long raw, value;
diff --git a/drivers/clocksource/h8300_tpu.c b/drivers/clocksource/h8300_tpu.c
index 7bdf199..72e1cf2 100644
--- a/drivers/clocksource/h8300_tpu.c
+++ b/drivers/clocksource/h8300_tpu.c
@@ -64,7 +64,7 @@ static inline struct tpu_priv *cs_to_priv(struct clocksource *cs)
 	return container_of(cs, struct tpu_priv, cs);
 }
 
-static cycle_t tpu_clocksource_read(struct clocksource *cs)
+static u64 tpu_clocksource_read(struct clocksource *cs)
 {
 	struct tpu_priv *p = cs_to_priv(cs);
 	unsigned long flags;
diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c
index 0efd36e..64f6490 100644
--- a/drivers/clocksource/i8253.c
+++ b/drivers/clocksource/i8253.c
@@ -25,7 +25,7 @@ EXPORT_SYMBOL(i8253_lock);
  * to just read by itself. So use jiffies to emulate a free
  * running counter:
  */
-static cycle_t i8253_read(struct clocksource *cs)
+static u64 i8253_read(struct clocksource *cs)
 {
 	static int old_count;
 	static u32 old_jifs;
@@ -83,7 +83,7 @@ static cycle_t i8253_read(struct clocksource *cs)
 
 	count = (PIT_LATCH - 1) - count;
 
-	return (cycle_t)(jifs * PIT_LATCH) + count;
+	return (u64)(jifs * PIT_LATCH) + count;
 }
 
 static struct clocksource i8253_cs = {
diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
index 54e1665..7c61226 100644
--- a/drivers/clocksource/jcore-pit.c
+++ b/drivers/clocksource/jcore-pit.c
@@ -57,7 +57,7 @@ static notrace u64 jcore_sched_clock_read(void)
 	return seclo * NSEC_PER_SEC + nsec;
 }
 
-static cycle_t jcore_clocksource_read(struct clocksource *cs)
+static u64 jcore_clocksource_read(struct clocksource *cs)
 {
 	return jcore_sched_clock_read();
 }
@@ -240,7 +240,7 @@ static int __init jcore_pit_init(struct device_node *node)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
-			  "AP_JCORE_TIMER_STARTING",
+			  "clockevents/jcore:starting",
 			  jcore_pit_local_init, NULL);
 
 	return 0;
diff --git a/drivers/clocksource/metag_generic.c b/drivers/clocksource/metag_generic.c
index a80ab3e..6fcf965 100644
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -56,7 +56,7 @@ static int metag_timer_set_next_event(unsigned long delta,
 	return 0;
 }
 
-static cycle_t metag_clocksource_read(struct clocksource *cs)
+static u64 metag_clocksource_read(struct clocksource *cs)
 {
 	return __core_reg_get(TXTIMER);
 }
@@ -154,6 +154,6 @@ int __init metag_generic_timer_init(void)
 
 	/* Hook cpu boot to configure the CPU's timers */
 	return cpuhp_setup_state(CPUHP_AP_METAG_TIMER_STARTING,
-				 "AP_METAG_TIMER_STARTING",
+				 "clockevents/metag:starting",
 				 arch_timer_starting_cpu, NULL);
 }
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 7a960cd..d9ef7a6 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -120,12 +120,12 @@ static int gic_clockevent_init(void)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_MIPS_GIC_TIMER_STARTING,
-			  "AP_MIPS_GIC_TIMER_STARTING", gic_starting_cpu,
-			  gic_dying_cpu);
+			  "clockevents/mips/gic/timer:starting",
+			  gic_starting_cpu, gic_dying_cpu);
 	return 0;
 }
 
-static cycle_t gic_hpt_read(struct clocksource *cs)
+static u64 gic_hpt_read(struct clocksource *cs)
 {
 	return gic_read_count();
 }
diff --git a/drivers/clocksource/mmio.c b/drivers/clocksource/mmio.c
index c4f7d7a..4c4df98 100644
--- a/drivers/clocksource/mmio.c
+++ b/drivers/clocksource/mmio.c
@@ -20,24 +20,24 @@ static inline struct clocksource_mmio *to_mmio_clksrc(struct clocksource *c)
 	return container_of(c, struct clocksource_mmio, clksrc);
 }
 
-cycle_t clocksource_mmio_readl_up(struct clocksource *c)
+u64 clocksource_mmio_readl_up(struct clocksource *c)
 {
-	return (cycle_t)readl_relaxed(to_mmio_clksrc(c)->reg);
+	return (u64)readl_relaxed(to_mmio_clksrc(c)->reg);
 }
 
-cycle_t clocksource_mmio_readl_down(struct clocksource *c)
+u64 clocksource_mmio_readl_down(struct clocksource *c)
 {
-	return ~(cycle_t)readl_relaxed(to_mmio_clksrc(c)->reg) & c->mask;
+	return ~(u64)readl_relaxed(to_mmio_clksrc(c)->reg) & c->mask;
 }
 
-cycle_t clocksource_mmio_readw_up(struct clocksource *c)
+u64 clocksource_mmio_readw_up(struct clocksource *c)
 {
-	return (cycle_t)readw_relaxed(to_mmio_clksrc(c)->reg);
+	return (u64)readw_relaxed(to_mmio_clksrc(c)->reg);
 }
 
-cycle_t clocksource_mmio_readw_down(struct clocksource *c)
+u64 clocksource_mmio_readw_down(struct clocksource *c)
 {
-	return ~(cycle_t)readw_relaxed(to_mmio_clksrc(c)->reg) & c->mask;
+	return ~(u64)readw_relaxed(to_mmio_clksrc(c)->reg) & c->mask;
 }
 
 /**
@@ -51,7 +51,7 @@ cycle_t clocksource_mmio_readw_down(struct clocksource *c)
  */
 int __init clocksource_mmio_init(void __iomem *base, const char *name,
 	unsigned long hz, int rating, unsigned bits,
-	cycle_t (*read)(struct clocksource *))
+	u64 (*read)(struct clocksource *))
 {
 	struct clocksource_mmio *cs;
 
diff --git a/drivers/clocksource/moxart_timer.c b/drivers/clocksource/moxart_timer.c
index 2a8f470..7f34306 100644
--- a/drivers/clocksource/moxart_timer.c
+++ b/drivers/clocksource/moxart_timer.c
@@ -161,19 +161,22 @@ static int __init moxart_timer_init(struct device_node *node)
 	timer->base = of_iomap(node, 0);
 	if (!timer->base) {
 		pr_err("%s: of_iomap failed\n", node->full_name);
-		return -ENXIO;
+		ret = -ENXIO;
+		goto out_free;
 	}
 
 	irq = irq_of_parse_and_map(node, 0);
 	if (irq <= 0) {
 		pr_err("%s: irq_of_parse_and_map failed\n", node->full_name);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out_unmap;
 	}
 
 	clk = of_clk_get(node, 0);
 	if (IS_ERR(clk))  {
 		pr_err("%s: of_clk_get failed\n", node->full_name);
-		return PTR_ERR(clk);
+		ret = PTR_ERR(clk);
+		goto out_unmap;
 	}
 
 	pclk = clk_get_rate(clk);
@@ -186,7 +189,8 @@ static int __init moxart_timer_init(struct device_node *node)
 		timer->t1_disable_val = ASPEED_TIMER1_DISABLE;
 	} else {
 		pr_err("%s: unknown platform\n", node->full_name);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out_unmap;
 	}
 
 	timer->count_per_tick = DIV_ROUND_CLOSEST(pclk, HZ);
@@ -208,14 +212,14 @@ static int __init moxart_timer_init(struct device_node *node)
 				    clocksource_mmio_readl_down);
 	if (ret) {
 		pr_err("%s: clocksource_mmio_init failed\n", node->full_name);
-		return ret;
+		goto out_unmap;
 	}
 
 	ret = request_irq(irq, moxart_timer_interrupt, IRQF_TIMER,
 			  node->name, &timer->clkevt);
 	if (ret) {
 		pr_err("%s: setup_irq failed\n", node->full_name);
-		return ret;
+		goto out_unmap;
 	}
 
 	/* Clear match registers */
@@ -241,6 +245,12 @@ static int __init moxart_timer_init(struct device_node *node)
 	clockevents_config_and_register(&timer->clkevt, pclk, 0x4, 0xfffffffe);
 
 	return 0;
+
+out_unmap:
+	iounmap(timer->base);
+out_free:
+	kfree(timer);
+	return ret;
 }
 CLOCKSOURCE_OF_DECLARE(moxart, "moxa,moxart-timer", moxart_timer_init);
 CLOCKSOURCE_OF_DECLARE(aspeed, "aspeed,ast2400-timer", moxart_timer_init);
diff --git a/drivers/clocksource/mxs_timer.c b/drivers/clocksource/mxs_timer.c
index 0ba0a91..99b77af 100644
--- a/drivers/clocksource/mxs_timer.c
+++ b/drivers/clocksource/mxs_timer.c
@@ -97,7 +97,7 @@ static void timrot_irq_acknowledge(void)
 		     HW_TIMROT_TIMCTRLn(0) + STMP_OFFSET_REG_CLR);
 }
 
-static cycle_t timrotv1_get_cycles(struct clocksource *cs)
+static u64 timrotv1_get_cycles(struct clocksource *cs)
 {
 	return ~((__raw_readl(mxs_timrot_base + HW_TIMROT_TIMCOUNTn(1))
 			& 0xffff0000) >> 16);
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index 3283cfa..ee358cd 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -89,7 +89,7 @@ static struct clock_event_device __percpu *msm_evt;
 
 static void __iomem *source_base;
 
-static notrace cycle_t msm_read_timer_count(struct clocksource *cs)
+static notrace u64 msm_read_timer_count(struct clocksource *cs)
 {
 	return readl_relaxed(source_base + TIMER_COUNT_VAL);
 }
@@ -182,7 +182,7 @@ static int __init msm_timer_init(u32 dgt_hz, int sched_bits, int irq,
 	} else {
 		/* Install and invoke hotplug callbacks */
 		res = cpuhp_setup_state(CPUHP_AP_QCOM_TIMER_STARTING,
-					"AP_QCOM_TIMER_STARTING",
+					"clockevents/qcom/timer:starting",
 					msm_local_timer_starting_cpu,
 					msm_local_timer_dying_cpu);
 		if (res) {
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 54565bd..0093ece 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -307,7 +307,7 @@ static void samsung_clocksource_resume(struct clocksource *cs)
 	samsung_time_start(pwm.source_id, true);
 }
 
-static cycle_t notrace samsung_clocksource_read(struct clocksource *c)
+static u64 notrace samsung_clocksource_read(struct clocksource *c)
 {
 	return ~readl_relaxed(pwm.source_reg);
 }
diff --git a/drivers/clocksource/scx200_hrt.c b/drivers/clocksource/scx200_hrt.c
index 64f9e82..a46660b 100644
--- a/drivers/clocksource/scx200_hrt.c
+++ b/drivers/clocksource/scx200_hrt.c
@@ -43,10 +43,10 @@ MODULE_PARM_DESC(ppm, "+-adjust to actual XO freq (ppm)");
 /* The base timer frequency, * 27 if selected */
 #define HRT_FREQ   1000000
 
-static cycle_t read_hrt(struct clocksource *cs)
+static u64 read_hrt(struct clocksource *cs)
 {
 	/* Read the timer value */
-	return (cycle_t) inl(scx200_cb_base + SCx200_TIMER_OFFSET);
+	return (u64) inl(scx200_cb_base + SCx200_TIMER_OFFSET);
 }
 
 static struct clocksource cs_hrt = {
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 103c493..28757ed 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -612,7 +612,7 @@ static struct sh_cmt_channel *cs_to_sh_cmt(struct clocksource *cs)
 	return container_of(cs, struct sh_cmt_channel, cs);
 }
 
-static cycle_t sh_cmt_clocksource_read(struct clocksource *cs)
+static u64 sh_cmt_clocksource_read(struct clocksource *cs)
 {
 	struct sh_cmt_channel *ch = cs_to_sh_cmt(cs);
 	unsigned long flags, raw;
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 469e776..1fbf2aa 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -255,7 +255,7 @@ static struct sh_tmu_channel *cs_to_sh_tmu(struct clocksource *cs)
 	return container_of(cs, struct sh_tmu_channel, cs);
 }
 
-static cycle_t sh_tmu_clocksource_read(struct clocksource *cs)
+static u64 sh_tmu_clocksource_read(struct clocksource *cs)
 {
 	struct sh_tmu_channel *ch = cs_to_sh_tmu(cs);
 
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 4da2af9..d4ca996 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -41,7 +41,7 @@
 
 static void __iomem *tcaddr;
 
-static cycle_t tc_get_cycles(struct clocksource *cs)
+static u64 tc_get_cycles(struct clocksource *cs)
 {
 	unsigned long	flags;
 	u32		lower, upper;
@@ -56,7 +56,7 @@ static cycle_t tc_get_cycles(struct clocksource *cs)
 	return (upper << 16) | lower;
 }
 
-static cycle_t tc_get_cycles32(struct clocksource *cs)
+static u64 tc_get_cycles32(struct clocksource *cs)
 {
 	return __raw_readl(tcaddr + ATMEL_TC_REG(0, CV));
 }
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 3c39e6f..4440aef 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -320,7 +320,7 @@ static int __init armada_370_xp_timer_common_init(struct device_node *np)
 	}
 
 	res = cpuhp_setup_state(CPUHP_AP_ARMADA_TIMER_STARTING,
-				"AP_ARMADA_TIMER_STARTING",
+				"clockevents/armada:starting",
 				armada_370_xp_timer_starting_cpu,
 				armada_370_xp_timer_dying_cpu);
 	if (res) {
diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c
index a8e6c7d..3710e4d 100644
--- a/drivers/clocksource/time-pistachio.c
+++ b/drivers/clocksource/time-pistachio.c
@@ -67,7 +67,7 @@ static inline void gpt_writel(void __iomem *base, u32 value, u32 offset,
 	writel(value, base + 0x20 * gpt_id + offset);
 }
 
-static cycle_t notrace
+static u64 notrace
 pistachio_clocksource_read_cycles(struct clocksource *cs)
 {
 	struct pistachio_clocksource *pcs = to_pistachio_clocksource(cs);
@@ -84,7 +84,7 @@ pistachio_clocksource_read_cycles(struct clocksource *cs)
 	counter = gpt_readl(pcs->base, TIMER_CURRENT_VALUE, 0);
 	raw_spin_unlock_irqrestore(&pcs->lock, flags);
 
-	return (cycle_t)~counter;
+	return (u64)~counter;
 }
 
 static u64 notrace pistachio_read_sched_clock(void)
diff --git a/drivers/clocksource/timer-atlas7.c b/drivers/clocksource/timer-atlas7.c
index 4334e03..3d8a181 100644
--- a/drivers/clocksource/timer-atlas7.c
+++ b/drivers/clocksource/timer-atlas7.c
@@ -85,7 +85,7 @@ static irqreturn_t sirfsoc_timer_interrupt(int irq, void *dev_id)
 }
 
 /* read 64-bit timer counter */
-static cycle_t sirfsoc_timer_read(struct clocksource *cs)
+static u64 sirfsoc_timer_read(struct clocksource *cs)
 {
 	u64 cycles;
 
@@ -221,7 +221,7 @@ static int __init sirfsoc_clockevent_init(void)
 
 	/* Install and invoke hotplug callbacks */
 	return cpuhp_setup_state(CPUHP_AP_MARCO_TIMER_STARTING,
-				 "AP_MARCO_TIMER_STARTING",
+				 "clockevents/marco:starting",
 				 sirfsoc_local_timer_starting_cpu,
 				 sirfsoc_local_timer_dying_cpu);
 }
diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c
index 6555821..c0b5df3 100644
--- a/drivers/clocksource/timer-atmel-pit.c
+++ b/drivers/clocksource/timer-atmel-pit.c
@@ -73,7 +73,7 @@ static inline void pit_write(void __iomem *base, unsigned int reg_offset, unsign
  * Clocksource:  just a monotonic counter of MCK/16 cycles.
  * We don't care whether or not PIT irqs are enabled.
  */
-static cycle_t read_pit_clk(struct clocksource *cs)
+static u64 read_pit_clk(struct clocksource *cs)
 {
 	struct pit_data *data = clksrc_to_pit_data(cs);
 	unsigned long flags;
diff --git a/drivers/clocksource/timer-atmel-st.c b/drivers/clocksource/timer-atmel-st.c
index e90ab5b..be4ac76 100644
--- a/drivers/clocksource/timer-atmel-st.c
+++ b/drivers/clocksource/timer-atmel-st.c
@@ -92,7 +92,7 @@ static irqreturn_t at91rm9200_timer_interrupt(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
-static cycle_t read_clk32k(struct clocksource *cs)
+static u64 read_clk32k(struct clocksource *cs)
 {
 	return read_CRTR();
 }
diff --git a/drivers/clocksource/timer-nps.c b/drivers/clocksource/timer-nps.c
index 8da5e93..da1f798 100644
--- a/drivers/clocksource/timer-nps.c
+++ b/drivers/clocksource/timer-nps.c
@@ -77,11 +77,11 @@ static int __init nps_get_timer_clk(struct device_node *node,
 	return 0;
 }
 
-static cycle_t nps_clksrc_read(struct clocksource *clksrc)
+static u64 nps_clksrc_read(struct clocksource *clksrc)
 {
 	int cluster = raw_smp_processor_id() >> NPS_CLUSTER_OFFSET;
 
-	return (cycle_t)ioread32be(nps_msu_reg_low_addr[cluster]);
+	return (u64)ioread32be(nps_msu_reg_low_addr[cluster]);
 }
 
 static int __init nps_setup_clocksource(struct device_node *node)
diff --git a/drivers/clocksource/timer-prima2.c b/drivers/clocksource/timer-prima2.c
index c32148e..bfa981a 100644
--- a/drivers/clocksource/timer-prima2.c
+++ b/drivers/clocksource/timer-prima2.c
@@ -72,7 +72,7 @@ static irqreturn_t sirfsoc_timer_interrupt(int irq, void *dev_id)
 }
 
 /* read 64-bit timer counter */
-static cycle_t notrace sirfsoc_timer_read(struct clocksource *cs)
+static u64 notrace sirfsoc_timer_read(struct clocksource *cs)
 {
 	u64 cycles;
 
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 4f87f3e..a3e662b 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -152,7 +152,7 @@ static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static cycle_t sun5i_clksrc_read(struct clocksource *clksrc)
+static u64 sun5i_clksrc_read(struct clocksource *clksrc)
 {
 	struct sun5i_timer_clksrc *cs = to_sun5i_timer_clksrc(clksrc);
 
diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c
index cf5b14e..6240677 100644
--- a/drivers/clocksource/timer-ti-32k.c
+++ b/drivers/clocksource/timer-ti-32k.c
@@ -65,11 +65,11 @@ static inline struct ti_32k *to_ti_32k(struct clocksource *cs)
 	return container_of(cs, struct ti_32k, cs);
 }
 
-static cycle_t notrace ti_32k_read_cycles(struct clocksource *cs)
+static u64 notrace ti_32k_read_cycles(struct clocksource *cs)
 {
 	struct ti_32k *ti = to_ti_32k(cs);
 
-	return (cycle_t)readl_relaxed(ti->counter);
+	return (u64)readl_relaxed(ti->counter);
 }
 
 static struct ti_32k ti_32k_timer = {
diff --git a/drivers/clocksource/vt8500_timer.c b/drivers/clocksource/vt8500_timer.c
index b150694..d02b510 100644
--- a/drivers/clocksource/vt8500_timer.c
+++ b/drivers/clocksource/vt8500_timer.c
@@ -53,7 +53,7 @@
 
 static void __iomem *regbase;
 
-static cycle_t vt8500_timer_read(struct clocksource *cs)
+static u64 vt8500_timer_read(struct clocksource *cs)
 {
 	int loops = msecs_to_loops(10);
 	writel(3, regbase + TIMER_CTRL_VAL);
@@ -75,7 +75,7 @@ static int vt8500_timer_set_next_event(unsigned long cycles,
 				    struct clock_event_device *evt)
 {
 	int loops = msecs_to_loops(10);
-	cycle_t alarm = clocksource.read(&clocksource) + cycles;
+	u64 alarm = clocksource.read(&clocksource) + cycles;
 	while ((readl(regbase + TIMER_AS_VAL) & TIMER_MATCH_W_ACTIVE)
 						&& --loops)
 		cpu_relax();
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 3a98702..3a2ca0f 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -930,7 +930,7 @@ static void __init acpi_cpufreq_boost_init(void)
 
 static void acpi_cpufreq_boost_exit(void)
 {
-	if (acpi_cpufreq_online >= 0)
+	if (acpi_cpufreq_online > 0)
 		cpuhp_remove_state_nocalls(acpi_cpufreq_online);
 }
 
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index 759612d..e28a31a 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -18,7 +18,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pal.h>
 
 #include <linux/acpi.h>
diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c
index 176e84c..0cb9040 100644
--- a/drivers/cpufreq/s3c64xx-cpufreq.c
+++ b/drivers/cpufreq/s3c64xx-cpufreq.c
@@ -107,7 +107,7 @@ static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy,
 }
 
 #ifdef CONFIG_REGULATOR
-static void __init s3c64xx_cpufreq_config_regulator(void)
+static void s3c64xx_cpufreq_config_regulator(void)
 {
 	int count, v, i, found;
 	struct cpufreq_frequency_table *freq;
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index fe8f089..ac321f0 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -19,7 +19,7 @@
 #include <linux/tick.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define PROMOTION_COUNT 4
 #define DEMOTION_COUNT 1
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index a768da7..b7872f6 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -273,7 +273,8 @@ struct mv_cesa_op_ctx {
 #define CESA_TDMA_SRC_IN_SRAM			BIT(30)
 #define CESA_TDMA_END_OF_REQ			BIT(29)
 #define CESA_TDMA_BREAK_CHAIN			BIT(28)
-#define CESA_TDMA_TYPE_MSK			GENMASK(27, 0)
+#define CESA_TDMA_SET_STATE			BIT(27)
+#define CESA_TDMA_TYPE_MSK			GENMASK(26, 0)
 #define CESA_TDMA_DUMMY				0
 #define CESA_TDMA_DATA				1
 #define CESA_TDMA_OP				2
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 317cf02..77c0fb9 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -280,13 +280,32 @@ static void mv_cesa_ahash_std_prepare(struct ahash_request *req)
 	sreq->offset = 0;
 }
 
+static void mv_cesa_ahash_dma_step(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_req *base = &creq->base;
+
+	/* We must explicitly set the digest state. */
+	if (base->chain.first->flags & CESA_TDMA_SET_STATE) {
+		struct mv_cesa_engine *engine = base->engine;
+		int i;
+
+		/* Set the hash state in the IVDIG regs. */
+		for (i = 0; i < ARRAY_SIZE(creq->state); i++)
+			writel_relaxed(creq->state[i], engine->regs +
+				       CESA_IVDIG(i));
+	}
+
+	mv_cesa_dma_step(base);
+}
+
 static void mv_cesa_ahash_step(struct crypto_async_request *req)
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
 
 	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->base);
+		mv_cesa_ahash_dma_step(ahashreq);
 	else
 		mv_cesa_ahash_std_step(ahashreq);
 }
@@ -584,12 +603,16 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	struct mv_cesa_ahash_dma_iter iter;
 	struct mv_cesa_op_ctx *op = NULL;
 	unsigned int frag_len;
+	bool set_state = false;
 	int ret;
 	u32 type;
 
 	basereq->chain.first = NULL;
 	basereq->chain.last = NULL;
 
+	if (!mv_cesa_mac_op_is_first_frag(&creq->op_tmpl))
+		set_state = true;
+
 	if (creq->src_nents) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
 				 DMA_TO_DEVICE);
@@ -683,6 +706,15 @@ static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
 	if (type != CESA_TDMA_RESULT)
 		basereq->chain.last->flags |= CESA_TDMA_BREAK_CHAIN;
 
+	if (set_state) {
+		/*
+		 * Put the CESA_TDMA_SET_STATE flag on the first tdma desc to
+		 * let the step logic know that the IVDIG registers should be
+		 * explicitly set before launching a TDMA chain.
+		 */
+		basereq->chain.first->flags |= CESA_TDMA_SET_STATE;
+	}
+
 	return 0;
 
 err_free_tdma:
diff --git a/drivers/crypto/marvell/tdma.c b/drivers/crypto/marvell/tdma.c
index 4416b88..c76375f 100644
--- a/drivers/crypto/marvell/tdma.c
+++ b/drivers/crypto/marvell/tdma.c
@@ -109,7 +109,14 @@ void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
 		last->next = dreq->chain.first;
 		engine->chain.last = dreq->chain.last;
 
-		if (!(last->flags & CESA_TDMA_BREAK_CHAIN))
+		/*
+		 * Break the DMA chain if the CESA_TDMA_BREAK_CHAIN is set on
+		 * the last element of the current chain, or if the request
+		 * being queued needs the IV regs to be set before lauching
+		 * the request.
+		 */
+		if (!(last->flags & CESA_TDMA_BREAK_CHAIN) &&
+		    !(dreq->chain.first->flags & CESA_TDMA_SET_STATE))
 			last->next_dma = dreq->chain.first->cur_dma;
 	}
 }
diff --git a/drivers/dio/dio.c b/drivers/dio/dio.c
index 55dd88d..8301845 100644
--- a/drivers/dio/dio.c
+++ b/drivers/dio/dio.c
@@ -31,7 +31,7 @@
 #include <linux/init.h>
 #include <linux/dio.h>
 #include <linux/slab.h>                         /* kmalloc() */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>                             /* readb() */
 
 struct dio_bus dio_bus = {
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 451f899..c929760 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -429,8 +429,8 @@ static int dmatest_func(void *data)
 	int			dst_cnt;
 	int			i;
 	ktime_t			ktime, start, diff;
-	ktime_t			filltime = ktime_set(0, 0);
-	ktime_t			comparetime = ktime_set(0, 0);
+	ktime_t			filltime = 0;
+	ktime_t			comparetime = 0;
 	s64			runtime = 0;
 	unsigned long long	total_len = 0;
 	u8			align = 0;
diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c
index de4d5d0..65cf2b9 100644
--- a/drivers/edac/edac_device.c
+++ b/drivers/edac/edac_device.c
@@ -13,7 +13,7 @@
  */
 
 #include <asm/page.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/highmem.h>
 #include <linux/init.h>
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 5f2c717..750891e 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -28,7 +28,7 @@
 #include <linux/ctype.h>
 #include <linux/edac.h>
 #include <linux/bitops.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include "edac_mc.h"
 #include "edac_module.h"
diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c
index 4e9d563..48c844a 100644
--- a/drivers/edac/edac_pci.c
+++ b/drivers/edac/edac_pci.c
@@ -10,7 +10,7 @@
  *
  */
 #include <asm/page.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/ctype.h>
 #include <linux/highmem.h>
 #include <linux/init.h>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 4f973a9..8ec1967 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -305,8 +305,9 @@ static bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev)
 	GOP_VBIOS_CONTENT *vbios;
 	VFCT_IMAGE_HEADER *vhdr;
 
-	if (!ACPI_SUCCESS(acpi_get_table_with_size("VFCT", 1, &hdr, &tbl_size)))
+	if (!ACPI_SUCCESS(acpi_get_table("VFCT", 1, &hdr)))
 		return false;
+	tbl_size = hdr->length;
 	if (tbl_size < sizeof(UEFI_ACPI_VFCT)) {
 		DRM_ERROR("ACPI VFCT table present but broken (too short #1)\n");
 		goto out_unmap;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index e564442..b4e4ec6 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1944,9 +1944,7 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 	dce_v6_0_lock_cursor(crtc, true);
 
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height ||
-	    hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -1955,8 +1953,6 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 		dce_v6_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_width = width;
-		amdgpu_crtc->cursor_height = height;
 		amdgpu_crtc->cursor_hot_x = hot_x;
 		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 6ce7fb4..584abe8 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2438,8 +2438,6 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 		dce_v8_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_width = width;
-		amdgpu_crtc->cursor_height = height;
 		amdgpu_crtc->cursor_hot_x = hot_x;
 		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index e4a5a5a..762f8e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -752,7 +752,7 @@ static enum hrtimer_restart dce_virtual_vblank_timer_handle(struct hrtimer *vbla
 
 	drm_handle_vblank(ddev, amdgpu_crtc->crtc_id);
 	dce_virtual_pageflip(adev, amdgpu_crtc->crtc_id);
-	hrtimer_start(vblank_timer, ktime_set(0, DCE_VIRTUAL_VBLANK_PERIOD),
+	hrtimer_start(vblank_timer, DCE_VIRTUAL_VBLANK_PERIOD,
 		      HRTIMER_MODE_REL);
 
 	return HRTIMER_NORESTART;
@@ -772,11 +772,11 @@ static void dce_virtual_set_crtc_vblank_interrupt_state(struct amdgpu_device *ad
 		hrtimer_init(&adev->mode_info.crtcs[crtc]->vblank_timer,
 			     CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		hrtimer_set_expires(&adev->mode_info.crtcs[crtc]->vblank_timer,
-				    ktime_set(0, DCE_VIRTUAL_VBLANK_PERIOD));
+				    DCE_VIRTUAL_VBLANK_PERIOD);
 		adev->mode_info.crtcs[crtc]->vblank_timer.function =
 			dce_virtual_vblank_timer_handle;
 		hrtimer_start(&adev->mode_info.crtcs[crtc]->vblank_timer,
-			      ktime_set(0, DCE_VIRTUAL_VBLANK_PERIOD), HRTIMER_MODE_REL);
+			      DCE_VIRTUAL_VBLANK_PERIOD, HRTIMER_MODE_REL);
 	} else if (!state && adev->mode_info.crtcs[crtc]->vsync_timer_enabled) {
 		DRM_DEBUG("Disable software vsync timer\n");
 		hrtimer_cancel(&adev->mode_info.crtcs[crtc]->vblank_timer);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 558640a..b323f5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -411,244 +411,587 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev)
 		break;
 	}
 
-	if (adev->asic_type == CHIP_VERDE ||
-	    adev->asic_type == CHIP_OLAND ||
+	if (adev->asic_type == CHIP_VERDE) {
+		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 1:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 2:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 3:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 4:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16));
+				break;
+			case 5:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 6:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 7:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 8:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED));
+				break;
+			case 9:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16));
+				break;
+			case 10:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 11:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 12:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 13:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16));
+				break;
+			case 14:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 15:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 16:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 17:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 18:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16));
+				break;
+			case 19:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_XTHICK) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 20:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 21:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 22:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 23:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 24:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 25:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 26:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 27:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 28:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 29:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 30:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			default:
+				continue;
+			}
+			adev->gfx.config.tile_mode_array[reg_offset] = gb_tile_moden;
+			WREG32(mmGB_TILE_MODE0 + reg_offset, gb_tile_moden);
+		}
+	} else if (adev->asic_type == CHIP_OLAND ||
 	    adev->asic_type == CHIP_HAINAN) {
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
 			switch (reg_offset) {
 			case 0:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 1:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 2:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 3:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4));
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
 				break;
 			case 4:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2));
 				break;
 			case 5:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(split_equal_to_row_size) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
 				break;
 			case 6:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(split_equal_to_row_size) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
 				break;
 			case 7:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(split_equal_to_row_size) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4));
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
 				break;
 			case 8:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED));
 				break;
 			case 9:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2));
 				break;
 			case 10:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 11:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 12:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 13:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2));
 				break;
 			case 14:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 15:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 16:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
 			case 17:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
-						 TILE_SPLIT(split_equal_to_row_size) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 18:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						 PIPE_CONFIG(ADDR_SURF_P2));
+				break;
+			case 19:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_XTHICK) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 20:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
 				break;
 			case 21:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
 				break;
 			case 22:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4));
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
 				break;
 			case 23:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
 				break;
 			case 24:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_8_BANK));
 				break;
 			case 25:
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
-						 NUM_BANKS(ADDR_SURF_8_BANK) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 26:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 27:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 28:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 29:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 30:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P2) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
 				break;
 			default:
-				gb_tile_moden = 0;
-				break;
+				continue;
 			}
 			adev->gfx.config.tile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(mmGB_TILE_MODE0 + reg_offset, gb_tile_moden);
@@ -656,239 +999,291 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev)
 	} else if ((adev->asic_type == CHIP_TAHITI) || (adev->asic_type == CHIP_PITCAIRN)) {
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
 			switch (reg_offset) {
-			case 0:  /* non-AA compressed depth or any compressed stencil */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+			case 0:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
-			case 1:  /* 2xAA/4xAA compressed depth only */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+			case 1:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
-			case 2:  /* 8xAA compressed depth only */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+			case 2:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
 				break;
-			case 3:  /* 2xAA/4xAA compressed depth with stencil (for depth buffer) */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+			case 3:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
 				break;
-			case 4:  /* Maps w/ a dimension less than the 2D macro-tile dimensions (for mipmapped depth textures) */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
+			case 4:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16));
 				break;
-			case 5:  /* Uncompressed 16bpp depth - and stencil buffer allocated with it */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(split_equal_to_row_size) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 6:  /* Uncompressed 32bpp depth - and stencil buffer allocated with it */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(split_equal_to_row_size) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1));
-				break;
-			case 7:  /* Uncompressed 8bpp stencil without depth (drivers typically do not use) */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(split_equal_to_row_size) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 8:  /* 1D and 1D Array Surfaces */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 9:  /* Displayable maps. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 10:  /* Display 8bpp. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 11:  /* Display 16bpp. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 12:  /* Display 32bpp. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+			case 5:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1));
-				break;
-			case 13:  /* Thin. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 14:  /* Thin 8 bpp. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
 				break;
-			case 15:  /* Thin 16 bpp. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+			case 6:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
 						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1));
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
 				break;
-			case 16:  /* Thin 32 bpp. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1));
-				break;
-			case 17:  /* Thin 64 bpp. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(split_equal_to_row_size) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1));
-				break;
-			case 21:  /* 8 bpp PRT. */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 22:  /* 16 bpp PRT */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4));
-				break;
-			case 23:  /* 32 bpp PRT */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 24:  /* 64 bpp PRT */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
-						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
-						 NUM_BANKS(ADDR_SURF_16_BANK) |
-						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
-						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2));
-				break;
-			case 25:  /* 128 bpp PRT */
-				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
-						 MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
-						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+			case 7:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
 						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
-						 NUM_BANKS(ADDR_SURF_8_BANK) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 8:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED));
+				break;
+			case 9:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16));
+				break;
+			case 10:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 11:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 12:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
 						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
 						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
-						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1));
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 13:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16));
+				break;
+			case 14:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 15:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 16:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK));
+				break;
+			case 17:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 18:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16));
+				break;
+			case 19:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_XTHICK) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 20:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_16_BANK) |
+						 TILE_SPLIT(split_equal_to_row_size));
+				break;
+			case 21:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 22:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 23:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 24:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 25:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 26:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 27:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 28:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 29:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
+				break;
+			case 30:
+				gb_tile_moden = (MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+						 ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						 PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+						 TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						 BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						 BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						 MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						 NUM_BANKS(ADDR_SURF_2_BANK));
 				break;
 			default:
-				gb_tile_moden = 0;
-				break;
+				continue;
 			}
 			adev->gfx.config.tile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(mmGB_TILE_MODE0 + reg_offset, gb_tile_moden);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 6324f67..d0ec009 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -3949,8 +3949,12 @@ static int gfx_v8_0_init_save_restore_list(struct amdgpu_device *adev)
 	temp = mmRLC_SRM_INDEX_CNTL_ADDR_0;
 	data = mmRLC_SRM_INDEX_CNTL_DATA_0;
 	for (i = 0; i < sizeof(unique_indices) / sizeof(int); i++) {
-		amdgpu_mm_wreg(adev, temp + i, unique_indices[i] & 0x3FFFF, false);
-		amdgpu_mm_wreg(adev, data + i, unique_indices[i] >> 20, false);
+		if (unique_indices[i] != 0) {
+			amdgpu_mm_wreg(adev, temp + i,
+					unique_indices[i] & 0x3FFFF, false);
+			amdgpu_mm_wreg(adev, data + i,
+					unique_indices[i] >> 20, false);
+		}
 	}
 	kfree(register_list_format);
 
@@ -3966,20 +3970,17 @@ static void gfx_v8_0_init_power_gating(struct amdgpu_device *adev)
 {
 	uint32_t data;
 
-	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
-			      AMD_PG_SUPPORT_GFX_SMG |
-			      AMD_PG_SUPPORT_GFX_DMG)) {
-		WREG32_FIELD(CP_RB_WPTR_POLL_CNTL, IDLE_POLL_COUNT, 0x60);
+	WREG32_FIELD(CP_RB_WPTR_POLL_CNTL, IDLE_POLL_COUNT, 0x60);
 
-		data = REG_SET_FIELD(0, RLC_PG_DELAY, POWER_UP_DELAY, 0x10);
-		data = REG_SET_FIELD(data, RLC_PG_DELAY, POWER_DOWN_DELAY, 0x10);
-		data = REG_SET_FIELD(data, RLC_PG_DELAY, CMD_PROPAGATE_DELAY, 0x10);
-		data = REG_SET_FIELD(data, RLC_PG_DELAY, MEM_SLEEP_DELAY, 0x10);
-		WREG32(mmRLC_PG_DELAY, data);
+	data = REG_SET_FIELD(0, RLC_PG_DELAY, POWER_UP_DELAY, 0x10);
+	data = REG_SET_FIELD(data, RLC_PG_DELAY, POWER_DOWN_DELAY, 0x10);
+	data = REG_SET_FIELD(data, RLC_PG_DELAY, CMD_PROPAGATE_DELAY, 0x10);
+	data = REG_SET_FIELD(data, RLC_PG_DELAY, MEM_SLEEP_DELAY, 0x10);
+	WREG32(mmRLC_PG_DELAY, data);
 
-		WREG32_FIELD(RLC_PG_DELAY_2, SERDES_CMD_DELAY, 0x3);
-		WREG32_FIELD(RLC_AUTO_PG_CTRL, GRBM_REG_SAVE_GFX_IDLE_THRESHOLD, 0x55f0);
-	}
+	WREG32_FIELD(RLC_PG_DELAY_2, SERDES_CMD_DELAY, 0x3);
+	WREG32_FIELD(RLC_AUTO_PG_CTRL, GRBM_REG_SAVE_GFX_IDLE_THRESHOLD, 0x55f0);
+
 }
 
 static void cz_enable_sck_slow_down_on_power_up(struct amdgpu_device *adev,
@@ -3996,41 +3997,37 @@ static void cz_enable_sck_slow_down_on_power_down(struct amdgpu_device *adev,
 
 static void cz_enable_cp_power_gating(struct amdgpu_device *adev, bool enable)
 {
-	WREG32_FIELD(RLC_PG_CNTL, CP_PG_DISABLE, enable ? 1 : 0);
+	WREG32_FIELD(RLC_PG_CNTL, CP_PG_DISABLE, enable ? 0 : 1);
 }
 
 static void gfx_v8_0_init_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
-			      AMD_PG_SUPPORT_GFX_SMG |
-			      AMD_PG_SUPPORT_GFX_DMG |
-			      AMD_PG_SUPPORT_CP |
-			      AMD_PG_SUPPORT_GDS |
-			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
+	if ((adev->asic_type == CHIP_CARRIZO) ||
+	    (adev->asic_type == CHIP_STONEY)) {
 		gfx_v8_0_init_csb(adev);
 		gfx_v8_0_init_save_restore_list(adev);
 		gfx_v8_0_enable_save_restore_machine(adev);
-
-		if ((adev->asic_type == CHIP_CARRIZO) ||
-		    (adev->asic_type == CHIP_STONEY)) {
-			WREG32(mmRLC_JUMP_TABLE_RESTORE, adev->gfx.rlc.cp_table_gpu_addr >> 8);
-			gfx_v8_0_init_power_gating(adev);
-			WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, adev->gfx.cu_info.ao_cu_mask);
-			if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
-				cz_enable_sck_slow_down_on_power_up(adev, true);
-				cz_enable_sck_slow_down_on_power_down(adev, true);
-			} else {
-				cz_enable_sck_slow_down_on_power_up(adev, false);
-				cz_enable_sck_slow_down_on_power_down(adev, false);
-			}
-			if (adev->pg_flags & AMD_PG_SUPPORT_CP)
-				cz_enable_cp_power_gating(adev, true);
-			else
-				cz_enable_cp_power_gating(adev, false);
-		} else if (adev->asic_type == CHIP_POLARIS11) {
-			gfx_v8_0_init_power_gating(adev);
+		WREG32(mmRLC_JUMP_TABLE_RESTORE, adev->gfx.rlc.cp_table_gpu_addr >> 8);
+		gfx_v8_0_init_power_gating(adev);
+		WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, adev->gfx.cu_info.ao_cu_mask);
+		if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
+			cz_enable_sck_slow_down_on_power_up(adev, true);
+			cz_enable_sck_slow_down_on_power_down(adev, true);
+		} else {
+			cz_enable_sck_slow_down_on_power_up(adev, false);
+			cz_enable_sck_slow_down_on_power_down(adev, false);
 		}
+		if (adev->pg_flags & AMD_PG_SUPPORT_CP)
+			cz_enable_cp_power_gating(adev, true);
+		else
+			cz_enable_cp_power_gating(adev, false);
+	} else if (adev->asic_type == CHIP_POLARIS11) {
+		gfx_v8_0_init_csb(adev);
+		gfx_v8_0_init_save_restore_list(adev);
+		gfx_v8_0_enable_save_restore_machine(adev);
+		gfx_v8_0_init_power_gating(adev);
 	}
+
 }
 
 static void gfx_v8_0_rlc_stop(struct amdgpu_device *adev)
@@ -5339,14 +5336,11 @@ static int gfx_v8_0_set_powergating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_PG_STATE_GATE) ? true : false;
 
-	if (!(adev->pg_flags & AMD_PG_SUPPORT_GFX_PG))
-		return 0;
-
 	switch (adev->asic_type) {
 	case CHIP_CARRIZO:
 	case CHIP_STONEY:
-		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)
-			cz_update_gfx_cg_power_gating(adev, enable);
+
+		cz_update_gfx_cg_power_gating(adev, enable);
 
 		if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) && enable)
 			gfx_v8_0_enable_gfx_static_mg_power_gating(adev, true);
@@ -5791,25 +5785,49 @@ static int gfx_v8_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 static int gfx_v8_0_tonga_update_gfx_clock_gating(struct amdgpu_device *adev,
 					  enum amd_clockgating_state state)
 {
-	uint32_t msg_id, pp_state;
+	uint32_t msg_id, pp_state = 0;
+	uint32_t pp_support_state = 0;
 	void *pp_handle = adev->powerplay.pp_handle;
 
-	if (state == AMD_CG_STATE_UNGATE)
-		pp_state = 0;
-	else
-		pp_state = PP_STATE_CG | PP_STATE_LS;
+	if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS) {
+			pp_support_state = PP_STATE_SUPPORT_LS;
+			pp_state = PP_STATE_LS;
+		}
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG) {
+			pp_support_state |= PP_STATE_SUPPORT_CG;
+			pp_state |= PP_STATE_CG;
+		}
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
-			PP_BLOCK_GFX_CG,
-			PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-			pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+		msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
+				PP_BLOCK_GFX_CG,
+				pp_support_state,
+				pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
-			PP_BLOCK_GFX_MG,
-			PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-			pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+	if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) {
+			pp_support_state = PP_STATE_SUPPORT_LS;
+			pp_state = PP_STATE_LS;
+		}
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG) {
+			pp_support_state |= PP_STATE_SUPPORT_CG;
+			pp_state |= PP_STATE_CG;
+		}
+
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+
+		msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
+				PP_BLOCK_GFX_MG,
+				pp_support_state,
+				pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
 	return 0;
 }
@@ -5817,43 +5835,98 @@ static int gfx_v8_0_tonga_update_gfx_clock_gating(struct amdgpu_device *adev,
 static int gfx_v8_0_polaris_update_gfx_clock_gating(struct amdgpu_device *adev,
 					  enum amd_clockgating_state state)
 {
-	uint32_t msg_id, pp_state;
+
+	uint32_t msg_id, pp_state = 0;
+	uint32_t pp_support_state = 0;
 	void *pp_handle = adev->powerplay.pp_handle;
 
-	if (state == AMD_CG_STATE_UNGATE)
-		pp_state = 0;
-	else
-		pp_state = PP_STATE_CG | PP_STATE_LS;
+	if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS) {
+			pp_support_state = PP_STATE_SUPPORT_LS;
+			pp_state = PP_STATE_LS;
+		}
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG) {
+			pp_support_state |= PP_STATE_SUPPORT_CG;
+			pp_state |= PP_STATE_CG;
+		}
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
-			PP_BLOCK_GFX_CG,
-			PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-			pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+		msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
+				PP_BLOCK_GFX_CG,
+				pp_support_state,
+				pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
-			PP_BLOCK_GFX_3D,
-			PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-			pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+	if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_3D_CGCG | AMD_CG_SUPPORT_GFX_3D_CGLS)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS) {
+			pp_support_state = PP_STATE_SUPPORT_LS;
+			pp_state = PP_STATE_LS;
+		}
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG) {
+			pp_support_state |= PP_STATE_SUPPORT_CG;
+			pp_state |= PP_STATE_CG;
+		}
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
-			PP_BLOCK_GFX_MG,
-			PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-			pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+		msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
+				PP_BLOCK_GFX_3D,
+				pp_support_state,
+				pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
-			PP_BLOCK_GFX_RLC,
-			PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-			pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+	if (adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) {
+			pp_support_state = PP_STATE_SUPPORT_LS;
+			pp_state = PP_STATE_LS;
+		}
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG) {
+			pp_support_state |= PP_STATE_SUPPORT_CG;
+			pp_state |= PP_STATE_CG;
+		}
+
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+
+		msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
+				PP_BLOCK_GFX_MG,
+				pp_support_state,
+				pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
+
+	if (adev->cg_flags & AMD_CG_SUPPORT_GFX_RLC_LS) {
+		pp_support_state = PP_STATE_SUPPORT_LS;
+
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		else
+			pp_state = PP_STATE_LS;
+
+		msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
+				PP_BLOCK_GFX_RLC,
+				pp_support_state,
+				pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
+
+	if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CP_LS) {
+		pp_support_state = PP_STATE_SUPPORT_LS;
+
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		else
+			pp_state = PP_STATE_LS;
+		msg_id = PP_CG_MSG_ID(PP_GROUP_GFX,
 			PP_BLOCK_GFX_CP,
-			PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
+			pp_support_state,
 			pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 3ed8ad8..c46b015 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -43,13 +43,14 @@
 
 static const u32 tahiti_golden_registers[] =
 {
+	0x17bc, 0x00000030, 0x00000011,
 	0x2684, 0x00010000, 0x00018208,
 	0x260c, 0xffffffff, 0x00000000,
 	0x260d, 0xf00fffff, 0x00000400,
 	0x260e, 0x0002021c, 0x00020200,
 	0x031e, 0x00000080, 0x00000000,
-	0x340c, 0x000300c0, 0x00800040,
-	0x360c, 0x000300c0, 0x00800040,
+	0x340c, 0x000000c0, 0x00800040,
+	0x360c, 0x000000c0, 0x00800040,
 	0x16ec, 0x000000f0, 0x00000070,
 	0x16f0, 0x00200000, 0x50100000,
 	0x1c0c, 0x31000311, 0x00000011,
@@ -60,7 +61,7 @@ static const u32 tahiti_golden_registers[] =
 	0x22c4, 0x0000ff0f, 0x00000000,
 	0xa293, 0x07ffffff, 0x4e000000,
 	0xa0d4, 0x3f3f3fff, 0x2a00126a,
-	0x000c, 0x000000ff, 0x0040,
+	0x000c, 0xffffffff, 0x0040,
 	0x000d, 0x00000040, 0x00004040,
 	0x2440, 0x07ffffff, 0x03000000,
 	0x23a2, 0x01ff1f3f, 0x00000000,
@@ -73,7 +74,11 @@ static const u32 tahiti_golden_registers[] =
 	0x2234, 0xffffffff, 0x000fff40,
 	0x2235, 0x0000001f, 0x00000010,
 	0x0504, 0x20000000, 0x20fffed8,
-	0x0570, 0x000c0fc0, 0x000c0400
+	0x0570, 0x000c0fc0, 0x000c0400,
+	0x052c, 0x0fffffff, 0xffffffff,
+	0x052d, 0x0fffffff, 0x0fffffff,
+	0x052e, 0x0fffffff, 0x0fffffff,
+	0x052f, 0x0fffffff, 0x0fffffff
 };
 
 static const u32 tahiti_golden_registers2[] =
@@ -83,16 +88,18 @@ static const u32 tahiti_golden_registers2[] =
 
 static const u32 tahiti_golden_rlc_registers[] =
 {
+	0x263e, 0xffffffff, 0x12011003,
 	0x3109, 0xffffffff, 0x00601005,
 	0x311f, 0xffffffff, 0x10104040,
 	0x3122, 0xffffffff, 0x0100000a,
 	0x30c5, 0xffffffff, 0x00000800,
 	0x30c3, 0xffffffff, 0x800000f4,
-	0x3d2a, 0xffffffff, 0x00000000
+	0x3d2a, 0x00000008, 0x00000000
 };
 
 static const u32 pitcairn_golden_registers[] =
 {
+	0x17bc, 0x00000030, 0x00000011,
 	0x2684, 0x00010000, 0x00018208,
 	0x260c, 0xffffffff, 0x00000000,
 	0x260d, 0xf00fffff, 0x00000400,
@@ -110,7 +117,7 @@ static const u32 pitcairn_golden_registers[] =
 	0x22c4, 0x0000ff0f, 0x00000000,
 	0xa293, 0x07ffffff, 0x4e000000,
 	0xa0d4, 0x3f3f3fff, 0x2a00126a,
-	0x000c, 0x000000ff, 0x0040,
+	0x000c, 0xffffffff, 0x0040,
 	0x000d, 0x00000040, 0x00004040,
 	0x2440, 0x07ffffff, 0x03000000,
 	0x2418, 0x0000007f, 0x00000020,
@@ -119,11 +126,16 @@ static const u32 pitcairn_golden_registers[] =
 	0x2b04, 0xffffffff, 0x00000000,
 	0x2b03, 0xffffffff, 0x32761054,
 	0x2235, 0x0000001f, 0x00000010,
-	0x0570, 0x000c0fc0, 0x000c0400
+	0x0570, 0x000c0fc0, 0x000c0400,
+	0x052c, 0x0fffffff, 0xffffffff,
+	0x052d, 0x0fffffff, 0x0fffffff,
+	0x052e, 0x0fffffff, 0x0fffffff,
+	0x052f, 0x0fffffff, 0x0fffffff
 };
 
 static const u32 pitcairn_golden_rlc_registers[] =
 {
+	0x263e, 0xffffffff, 0x12011003,
 	0x3109, 0xffffffff, 0x00601004,
 	0x311f, 0xffffffff, 0x10102020,
 	0x3122, 0xffffffff, 0x01000020,
@@ -133,133 +145,134 @@ static const u32 pitcairn_golden_rlc_registers[] =
 
 static const u32 verde_pg_init[] =
 {
-	0xd4f, 0xffffffff, 0x40000,
-	0xd4e, 0xffffffff, 0x200010ff,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x7007,
-	0xd4e, 0xffffffff, 0x300010ff,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x400000,
-	0xd4e, 0xffffffff, 0x100010ff,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x120200,
-	0xd4e, 0xffffffff, 0x500010ff,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x1e1e16,
-	0xd4e, 0xffffffff, 0x600010ff,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x171f1e,
-	0xd4e, 0xffffffff, 0x700010ff,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4f, 0xffffffff, 0x0,
-	0xd4e, 0xffffffff, 0x9ff,
-	0xd40, 0xffffffff, 0x0,
-	0xd41, 0xffffffff, 0x10000800,
-	0xd41, 0xffffffff, 0xf,
-	0xd41, 0xffffffff, 0xf,
-	0xd40, 0xffffffff, 0x4,
-	0xd41, 0xffffffff, 0x1000051e,
-	0xd41, 0xffffffff, 0xffff,
-	0xd41, 0xffffffff, 0xffff,
-	0xd40, 0xffffffff, 0x8,
-	0xd41, 0xffffffff, 0x80500,
-	0xd40, 0xffffffff, 0x12,
-	0xd41, 0xffffffff, 0x9050c,
-	0xd40, 0xffffffff, 0x1d,
-	0xd41, 0xffffffff, 0xb052c,
-	0xd40, 0xffffffff, 0x2a,
-	0xd41, 0xffffffff, 0x1053e,
-	0xd40, 0xffffffff, 0x2d,
-	0xd41, 0xffffffff, 0x10546,
-	0xd40, 0xffffffff, 0x30,
-	0xd41, 0xffffffff, 0xa054e,
-	0xd40, 0xffffffff, 0x3c,
-	0xd41, 0xffffffff, 0x1055f,
-	0xd40, 0xffffffff, 0x3f,
-	0xd41, 0xffffffff, 0x10567,
-	0xd40, 0xffffffff, 0x42,
-	0xd41, 0xffffffff, 0x1056f,
-	0xd40, 0xffffffff, 0x45,
-	0xd41, 0xffffffff, 0x10572,
-	0xd40, 0xffffffff, 0x48,
-	0xd41, 0xffffffff, 0x20575,
-	0xd40, 0xffffffff, 0x4c,
-	0xd41, 0xffffffff, 0x190801,
-	0xd40, 0xffffffff, 0x67,
-	0xd41, 0xffffffff, 0x1082a,
-	0xd40, 0xffffffff, 0x6a,
-	0xd41, 0xffffffff, 0x1b082d,
-	0xd40, 0xffffffff, 0x87,
-	0xd41, 0xffffffff, 0x310851,
-	0xd40, 0xffffffff, 0xba,
-	0xd41, 0xffffffff, 0x891,
-	0xd40, 0xffffffff, 0xbc,
-	0xd41, 0xffffffff, 0x893,
-	0xd40, 0xffffffff, 0xbe,
-	0xd41, 0xffffffff, 0x20895,
-	0xd40, 0xffffffff, 0xc2,
-	0xd41, 0xffffffff, 0x20899,
-	0xd40, 0xffffffff, 0xc6,
-	0xd41, 0xffffffff, 0x2089d,
-	0xd40, 0xffffffff, 0xca,
-	0xd41, 0xffffffff, 0x8a1,
-	0xd40, 0xffffffff, 0xcc,
-	0xd41, 0xffffffff, 0x8a3,
-	0xd40, 0xffffffff, 0xce,
-	0xd41, 0xffffffff, 0x308a5,
-	0xd40, 0xffffffff, 0xd3,
-	0xd41, 0xffffffff, 0x6d08cd,
-	0xd40, 0xffffffff, 0x142,
-	0xd41, 0xffffffff, 0x2000095a,
-	0xd41, 0xffffffff, 0x1,
-	0xd40, 0xffffffff, 0x144,
-	0xd41, 0xffffffff, 0x301f095b,
-	0xd40, 0xffffffff, 0x165,
-	0xd41, 0xffffffff, 0xc094d,
-	0xd40, 0xffffffff, 0x173,
-	0xd41, 0xffffffff, 0xf096d,
-	0xd40, 0xffffffff, 0x184,
-	0xd41, 0xffffffff, 0x15097f,
-	0xd40, 0xffffffff, 0x19b,
-	0xd41, 0xffffffff, 0xc0998,
-	0xd40, 0xffffffff, 0x1a9,
-	0xd41, 0xffffffff, 0x409a7,
-	0xd40, 0xffffffff, 0x1af,
-	0xd41, 0xffffffff, 0xcdc,
-	0xd40, 0xffffffff, 0x1b1,
-	0xd41, 0xffffffff, 0x800,
-	0xd42, 0xffffffff, 0x6c9b2000,
-	0xd44, 0xfc00, 0x2000,
-	0xd51, 0xffffffff, 0xfc0,
-	0xa35, 0x00000100, 0x100
+	0x0d4f, 0xffffffff, 0x40000,
+	0x0d4e, 0xffffffff, 0x200010ff,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x7007,
+	0x0d4e, 0xffffffff, 0x300010ff,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x400000,
+	0x0d4e, 0xffffffff, 0x100010ff,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x120200,
+	0x0d4e, 0xffffffff, 0x500010ff,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x1e1e16,
+	0x0d4e, 0xffffffff, 0x600010ff,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x171f1e,
+	0x0d4e, 0xffffffff, 0x700010ff,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4f, 0xffffffff, 0x0,
+	0x0d4e, 0xffffffff, 0x9ff,
+	0x0d40, 0xffffffff, 0x0,
+	0x0d41, 0xffffffff, 0x10000800,
+	0x0d41, 0xffffffff, 0xf,
+	0x0d41, 0xffffffff, 0xf,
+	0x0d40, 0xffffffff, 0x4,
+	0x0d41, 0xffffffff, 0x1000051e,
+	0x0d41, 0xffffffff, 0xffff,
+	0x0d41, 0xffffffff, 0xffff,
+	0x0d40, 0xffffffff, 0x8,
+	0x0d41, 0xffffffff, 0x80500,
+	0x0d40, 0xffffffff, 0x12,
+	0x0d41, 0xffffffff, 0x9050c,
+	0x0d40, 0xffffffff, 0x1d,
+	0x0d41, 0xffffffff, 0xb052c,
+	0x0d40, 0xffffffff, 0x2a,
+	0x0d41, 0xffffffff, 0x1053e,
+	0x0d40, 0xffffffff, 0x2d,
+	0x0d41, 0xffffffff, 0x10546,
+	0x0d40, 0xffffffff, 0x30,
+	0x0d41, 0xffffffff, 0xa054e,
+	0x0d40, 0xffffffff, 0x3c,
+	0x0d41, 0xffffffff, 0x1055f,
+	0x0d40, 0xffffffff, 0x3f,
+	0x0d41, 0xffffffff, 0x10567,
+	0x0d40, 0xffffffff, 0x42,
+	0x0d41, 0xffffffff, 0x1056f,
+	0x0d40, 0xffffffff, 0x45,
+	0x0d41, 0xffffffff, 0x10572,
+	0x0d40, 0xffffffff, 0x48,
+	0x0d41, 0xffffffff, 0x20575,
+	0x0d40, 0xffffffff, 0x4c,
+	0x0d41, 0xffffffff, 0x190801,
+	0x0d40, 0xffffffff, 0x67,
+	0x0d41, 0xffffffff, 0x1082a,
+	0x0d40, 0xffffffff, 0x6a,
+	0x0d41, 0xffffffff, 0x1b082d,
+	0x0d40, 0xffffffff, 0x87,
+	0x0d41, 0xffffffff, 0x310851,
+	0x0d40, 0xffffffff, 0xba,
+	0x0d41, 0xffffffff, 0x891,
+	0x0d40, 0xffffffff, 0xbc,
+	0x0d41, 0xffffffff, 0x893,
+	0x0d40, 0xffffffff, 0xbe,
+	0x0d41, 0xffffffff, 0x20895,
+	0x0d40, 0xffffffff, 0xc2,
+	0x0d41, 0xffffffff, 0x20899,
+	0x0d40, 0xffffffff, 0xc6,
+	0x0d41, 0xffffffff, 0x2089d,
+	0x0d40, 0xffffffff, 0xca,
+	0x0d41, 0xffffffff, 0x8a1,
+	0x0d40, 0xffffffff, 0xcc,
+	0x0d41, 0xffffffff, 0x8a3,
+	0x0d40, 0xffffffff, 0xce,
+	0x0d41, 0xffffffff, 0x308a5,
+	0x0d40, 0xffffffff, 0xd3,
+	0x0d41, 0xffffffff, 0x6d08cd,
+	0x0d40, 0xffffffff, 0x142,
+	0x0d41, 0xffffffff, 0x2000095a,
+	0x0d41, 0xffffffff, 0x1,
+	0x0d40, 0xffffffff, 0x144,
+	0x0d41, 0xffffffff, 0x301f095b,
+	0x0d40, 0xffffffff, 0x165,
+	0x0d41, 0xffffffff, 0xc094d,
+	0x0d40, 0xffffffff, 0x173,
+	0x0d41, 0xffffffff, 0xf096d,
+	0x0d40, 0xffffffff, 0x184,
+	0x0d41, 0xffffffff, 0x15097f,
+	0x0d40, 0xffffffff, 0x19b,
+	0x0d41, 0xffffffff, 0xc0998,
+	0x0d40, 0xffffffff, 0x1a9,
+	0x0d41, 0xffffffff, 0x409a7,
+	0x0d40, 0xffffffff, 0x1af,
+	0x0d41, 0xffffffff, 0xcdc,
+	0x0d40, 0xffffffff, 0x1b1,
+	0x0d41, 0xffffffff, 0x800,
+	0x0d42, 0xffffffff, 0x6c9b2000,
+	0x0d44, 0xfc00, 0x2000,
+	0x0d51, 0xffffffff, 0xfc0,
+	0x0a35, 0x00000100, 0x100
 };
 
 static const u32 verde_golden_rlc_registers[] =
 {
+	0x263e, 0xffffffff, 0x02010002,
 	0x3109, 0xffffffff, 0x033f1005,
 	0x311f, 0xffffffff, 0x10808020,
 	0x3122, 0xffffffff, 0x00800008,
@@ -269,65 +282,45 @@ static const u32 verde_golden_rlc_registers[] =
 
 static const u32 verde_golden_registers[] =
 {
+	0x17bc, 0x00000030, 0x00000011,
 	0x2684, 0x00010000, 0x00018208,
 	0x260c, 0xffffffff, 0x00000000,
 	0x260d, 0xf00fffff, 0x00000400,
 	0x260e, 0x0002021c, 0x00020200,
 	0x031e, 0x00000080, 0x00000000,
 	0x340c, 0x000300c0, 0x00800040,
-	0x340c, 0x000300c0, 0x00800040,
-	0x360c, 0x000300c0, 0x00800040,
 	0x360c, 0x000300c0, 0x00800040,
 	0x16ec, 0x000000f0, 0x00000070,
 	0x16f0, 0x00200000, 0x50100000,
-
 	0x1c0c, 0x31000311, 0x00000011,
 	0x0ab9, 0x00073ffe, 0x000022a2,
-	0x0ab9, 0x00073ffe, 0x000022a2,
-	0x0ab9, 0x00073ffe, 0x000022a2,
-	0x0903, 0x000007ff, 0x00000000,
-	0x0903, 0x000007ff, 0x00000000,
 	0x0903, 0x000007ff, 0x00000000,
 	0x2285, 0xf000001f, 0x00000007,
-	0x2285, 0xf000001f, 0x00000007,
-	0x2285, 0xf000001f, 0x00000007,
-	0x2285, 0xffffffff, 0x00ffffff,
+	0x22c9, 0xffffffff, 0x00ffffff,
 	0x22c4, 0x0000ff0f, 0x00000000,
-
 	0xa293, 0x07ffffff, 0x4e000000,
 	0xa0d4, 0x3f3f3fff, 0x0000124a,
-	0xa0d4, 0x3f3f3fff, 0x0000124a,
-	0xa0d4, 0x3f3f3fff, 0x0000124a,
-	0x000c, 0x000000ff, 0x0040,
+	0x000c, 0xffffffff, 0x0040,
 	0x000d, 0x00000040, 0x00004040,
 	0x2440, 0x07ffffff, 0x03000000,
-	0x2440, 0x07ffffff, 0x03000000,
 	0x23a2, 0x01ff1f3f, 0x00000000,
-	0x23a3, 0x01ff1f3f, 0x00000000,
-	0x23a2, 0x01ff1f3f, 0x00000000,
-	0x23a1, 0x01ff1f3f, 0x00000000,
-	0x23a1, 0x01ff1f3f, 0x00000000,
-
 	0x23a1, 0x01ff1f3f, 0x00000000,
 	0x2418, 0x0000007f, 0x00000020,
 	0x2542, 0x00010000, 0x00010000,
-	0x2b01, 0x000003ff, 0x00000003,
-	0x2b05, 0x000003ff, 0x00000003,
 	0x2b05, 0x000003ff, 0x00000003,
 	0x2b04, 0xffffffff, 0x00000000,
-	0x2b04, 0xffffffff, 0x00000000,
-	0x2b04, 0xffffffff, 0x00000000,
-	0x2b03, 0xffffffff, 0x00001032,
-	0x2b03, 0xffffffff, 0x00001032,
 	0x2b03, 0xffffffff, 0x00001032,
 	0x2235, 0x0000001f, 0x00000010,
-	0x2235, 0x0000001f, 0x00000010,
-	0x2235, 0x0000001f, 0x00000010,
-	0x0570, 0x000c0fc0, 0x000c0400
+	0x0570, 0x000c0fc0, 0x000c0400,
+	0x052c, 0x0fffffff, 0xffffffff,
+	0x052d, 0x0fffffff, 0x0fffffff,
+	0x052e, 0x0fffffff, 0x0fffffff,
+	0x052f, 0x0fffffff, 0x0fffffff
 };
 
 static const u32 oland_golden_registers[] =
 {
+	0x17bc, 0x00000030, 0x00000011,
 	0x2684, 0x00010000, 0x00018208,
 	0x260c, 0xffffffff, 0x00000000,
 	0x260d, 0xf00fffff, 0x00000400,
@@ -336,7 +329,7 @@ static const u32 oland_golden_registers[] =
 	0x340c, 0x000300c0, 0x00800040,
 	0x360c, 0x000300c0, 0x00800040,
 	0x16ec, 0x000000f0, 0x00000070,
-	0x16f9, 0x00200000, 0x50100000,
+	0x16f0, 0x00200000, 0x50100000,
 	0x1c0c, 0x31000311, 0x00000011,
 	0x0ab9, 0x00073ffe, 0x000022a2,
 	0x0903, 0x000007ff, 0x00000000,
@@ -345,7 +338,7 @@ static const u32 oland_golden_registers[] =
 	0x22c4, 0x0000ff0f, 0x00000000,
 	0xa293, 0x07ffffff, 0x4e000000,
 	0xa0d4, 0x3f3f3fff, 0x00000082,
-	0x000c, 0x000000ff, 0x0040,
+	0x000c, 0xffffffff, 0x0040,
 	0x000d, 0x00000040, 0x00004040,
 	0x2440, 0x07ffffff, 0x03000000,
 	0x2418, 0x0000007f, 0x00000020,
@@ -354,11 +347,16 @@ static const u32 oland_golden_registers[] =
 	0x2b04, 0xffffffff, 0x00000000,
 	0x2b03, 0xffffffff, 0x00003210,
 	0x2235, 0x0000001f, 0x00000010,
-	0x0570, 0x000c0fc0, 0x000c0400
+	0x0570, 0x000c0fc0, 0x000c0400,
+	0x052c, 0x0fffffff, 0xffffffff,
+	0x052d, 0x0fffffff, 0x0fffffff,
+	0x052e, 0x0fffffff, 0x0fffffff,
+	0x052f, 0x0fffffff, 0x0fffffff
 };
 
 static const u32 oland_golden_rlc_registers[] =
 {
+	0x263e, 0xffffffff, 0x02010002,
 	0x3109, 0xffffffff, 0x00601005,
 	0x311f, 0xffffffff, 0x10104040,
 	0x3122, 0xffffffff, 0x0100000a,
@@ -368,22 +366,27 @@ static const u32 oland_golden_rlc_registers[] =
 
 static const u32 hainan_golden_registers[] =
 {
+	0x17bc, 0x00000030, 0x00000011,
 	0x2684, 0x00010000, 0x00018208,
 	0x260c, 0xffffffff, 0x00000000,
 	0x260d, 0xf00fffff, 0x00000400,
 	0x260e, 0x0002021c, 0x00020200,
-	0x4595, 0xff000fff, 0x00000100,
+	0x031e, 0x00000080, 0x00000000,
+	0x3430, 0xff000fff, 0x00000100,
 	0x340c, 0x000300c0, 0x00800040,
 	0x3630, 0xff000fff, 0x00000100,
 	0x360c, 0x000300c0, 0x00800040,
+	0x16ec, 0x000000f0, 0x00000070,
+	0x16f0, 0x00200000, 0x50100000,
+	0x1c0c, 0x31000311, 0x00000011,
 	0x0ab9, 0x00073ffe, 0x000022a2,
 	0x0903, 0x000007ff, 0x00000000,
 	0x2285, 0xf000001f, 0x00000007,
 	0x22c9, 0xffffffff, 0x00ffffff,
 	0x22c4, 0x0000ff0f, 0x00000000,
-	0xa393, 0x07ffffff, 0x4e000000,
+	0xa293, 0x07ffffff, 0x4e000000,
 	0xa0d4, 0x3f3f3fff, 0x00000000,
-	0x000c, 0x000000ff, 0x0040,
+	0x000c, 0xffffffff, 0x0040,
 	0x000d, 0x00000040, 0x00004040,
 	0x2440, 0x03e00000, 0x03600000,
 	0x2418, 0x0000007f, 0x00000020,
@@ -392,12 +395,16 @@ static const u32 hainan_golden_registers[] =
 	0x2b04, 0xffffffff, 0x00000000,
 	0x2b03, 0xffffffff, 0x00003210,
 	0x2235, 0x0000001f, 0x00000010,
-	0x0570, 0x000c0fc0, 0x000c0400
+	0x0570, 0x000c0fc0, 0x000c0400,
+	0x052c, 0x0fffffff, 0xffffffff,
+	0x052d, 0x0fffffff, 0x0fffffff,
+	0x052e, 0x0fffffff, 0x0fffffff,
+	0x052f, 0x0fffffff, 0x0fffffff
 };
 
 static const u32 hainan_golden_registers2[] =
 {
-	0x263e, 0xffffffff, 0x02010001
+	0x263e, 0xffffffff, 0x2011003
 };
 
 static const u32 tahiti_mgcg_cgcg_init[] =
@@ -513,18 +520,18 @@ static const u32 tahiti_mgcg_cgcg_init[] =
 	0x21c2, 0xffffffff, 0x00900100,
 	0x311e, 0xffffffff, 0x00000080,
 	0x3101, 0xffffffff, 0x0020003f,
-	0xc, 0xffffffff, 0x0000001c,
-	0xd, 0x000f0000, 0x000f0000,
-	0x583, 0xffffffff, 0x00000100,
-	0x409, 0xffffffff, 0x00000100,
-	0x40b, 0x00000101, 0x00000000,
-	0x82a, 0xffffffff, 0x00000104,
-	0x993, 0x000c0000, 0x000c0000,
-	0x992, 0x000c0000, 0x000c0000,
+	0x000c, 0xffffffff, 0x0000001c,
+	0x000d, 0x000f0000, 0x000f0000,
+	0x0583, 0xffffffff, 0x00000100,
+	0x0409, 0xffffffff, 0x00000100,
+	0x040b, 0x00000101, 0x00000000,
+	0x082a, 0xffffffff, 0x00000104,
+	0x0993, 0x000c0000, 0x000c0000,
+	0x0992, 0x000c0000, 0x000c0000,
 	0x1579, 0xff000fff, 0x00000100,
 	0x157a, 0x00000001, 0x00000001,
-	0xbd4, 0x00000001, 0x00000001,
-	0xc33, 0xc0000fff, 0x00000104,
+	0x0bd4, 0x00000001, 0x00000001,
+	0x0c33, 0xc0000fff, 0x00000104,
 	0x3079, 0x00000001, 0x00000001,
 	0x3430, 0xfffffff0, 0x00000100,
 	0x3630, 0xfffffff0, 0x00000100
@@ -612,16 +619,16 @@ static const u32 pitcairn_mgcg_cgcg_init[] =
 	0x21c2, 0xffffffff, 0x00900100,
 	0x311e, 0xffffffff, 0x00000080,
 	0x3101, 0xffffffff, 0x0020003f,
-	0xc, 0xffffffff, 0x0000001c,
-	0xd, 0x000f0000, 0x000f0000,
-	0x583, 0xffffffff, 0x00000100,
-	0x409, 0xffffffff, 0x00000100,
-	0x40b, 0x00000101, 0x00000000,
-	0x82a, 0xffffffff, 0x00000104,
+	0x000c, 0xffffffff, 0x0000001c,
+	0x000d, 0x000f0000, 0x000f0000,
+	0x0583, 0xffffffff, 0x00000100,
+	0x0409, 0xffffffff, 0x00000100,
+	0x040b, 0x00000101, 0x00000000,
+	0x082a, 0xffffffff, 0x00000104,
 	0x1579, 0xff000fff, 0x00000100,
 	0x157a, 0x00000001, 0x00000001,
-	0xbd4, 0x00000001, 0x00000001,
-	0xc33, 0xc0000fff, 0x00000104,
+	0x0bd4, 0x00000001, 0x00000001,
+	0x0c33, 0xc0000fff, 0x00000104,
 	0x3079, 0x00000001, 0x00000001,
 	0x3430, 0xfffffff0, 0x00000100,
 	0x3630, 0xfffffff0, 0x00000100
@@ -709,18 +716,18 @@ static const u32 verde_mgcg_cgcg_init[] =
 	0x21c2, 0xffffffff, 0x00900100,
 	0x311e, 0xffffffff, 0x00000080,
 	0x3101, 0xffffffff, 0x0020003f,
-	0xc, 0xffffffff, 0x0000001c,
-	0xd, 0x000f0000, 0x000f0000,
-	0x583, 0xffffffff, 0x00000100,
-	0x409, 0xffffffff, 0x00000100,
-	0x40b, 0x00000101, 0x00000000,
-	0x82a, 0xffffffff, 0x00000104,
-	0x993, 0x000c0000, 0x000c0000,
-	0x992, 0x000c0000, 0x000c0000,
+	0x000c, 0xffffffff, 0x0000001c,
+	0x000d, 0x000f0000, 0x000f0000,
+	0x0583, 0xffffffff, 0x00000100,
+	0x0409, 0xffffffff, 0x00000100,
+	0x040b, 0x00000101, 0x00000000,
+	0x082a, 0xffffffff, 0x00000104,
+	0x0993, 0x000c0000, 0x000c0000,
+	0x0992, 0x000c0000, 0x000c0000,
 	0x1579, 0xff000fff, 0x00000100,
 	0x157a, 0x00000001, 0x00000001,
-	0xbd4, 0x00000001, 0x00000001,
-	0xc33, 0xc0000fff, 0x00000104,
+	0x0bd4, 0x00000001, 0x00000001,
+	0x0c33, 0xc0000fff, 0x00000104,
 	0x3079, 0x00000001, 0x00000001,
 	0x3430, 0xfffffff0, 0x00000100,
 	0x3630, 0xfffffff0, 0x00000100
@@ -788,18 +795,18 @@ static const u32 oland_mgcg_cgcg_init[] =
 	0x21c2, 0xffffffff, 0x00900100,
 	0x311e, 0xffffffff, 0x00000080,
 	0x3101, 0xffffffff, 0x0020003f,
-	0xc, 0xffffffff, 0x0000001c,
-	0xd, 0x000f0000, 0x000f0000,
-	0x583, 0xffffffff, 0x00000100,
-	0x409, 0xffffffff, 0x00000100,
-	0x40b, 0x00000101, 0x00000000,
-	0x82a, 0xffffffff, 0x00000104,
-	0x993, 0x000c0000, 0x000c0000,
-	0x992, 0x000c0000, 0x000c0000,
+	0x000c, 0xffffffff, 0x0000001c,
+	0x000d, 0x000f0000, 0x000f0000,
+	0x0583, 0xffffffff, 0x00000100,
+	0x0409, 0xffffffff, 0x00000100,
+	0x040b, 0x00000101, 0x00000000,
+	0x082a, 0xffffffff, 0x00000104,
+	0x0993, 0x000c0000, 0x000c0000,
+	0x0992, 0x000c0000, 0x000c0000,
 	0x1579, 0xff000fff, 0x00000100,
 	0x157a, 0x00000001, 0x00000001,
-	0xbd4, 0x00000001, 0x00000001,
-	0xc33, 0xc0000fff, 0x00000104,
+	0x0bd4, 0x00000001, 0x00000001,
+	0x0c33, 0xc0000fff, 0x00000104,
 	0x3079, 0x00000001, 0x00000001,
 	0x3430, 0xfffffff0, 0x00000100,
 	0x3630, 0xfffffff0, 0x00000100
@@ -867,15 +874,15 @@ static const u32 hainan_mgcg_cgcg_init[] =
 	0x21c2, 0xffffffff, 0x00900100,
 	0x311e, 0xffffffff, 0x00000080,
 	0x3101, 0xffffffff, 0x0020003f,
-	0xc, 0xffffffff, 0x0000001c,
-	0xd, 0x000f0000, 0x000f0000,
-	0x583, 0xffffffff, 0x00000100,
-	0x409, 0xffffffff, 0x00000100,
-	0x82a, 0xffffffff, 0x00000104,
-	0x993, 0x000c0000, 0x000c0000,
-	0x992, 0x000c0000, 0x000c0000,
-	0xbd4, 0x00000001, 0x00000001,
-	0xc33, 0xc0000fff, 0x00000104,
+	0x000c, 0xffffffff, 0x0000001c,
+	0x000d, 0x000f0000, 0x000f0000,
+	0x0583, 0xffffffff, 0x00000100,
+	0x0409, 0xffffffff, 0x00000100,
+	0x082a, 0xffffffff, 0x00000104,
+	0x0993, 0x000c0000, 0x000c0000,
+	0x0992, 0x000c0000, 0x000c0000,
+	0x0bd4, 0x00000001, 0x00000001,
+	0x0c33, 0xc0000fff, 0x00000104,
 	0x3079, 0x00000001, 0x00000001,
 	0x3430, 0xfffffff0, 0x00000100,
 	0x3630, 0xfffffff0, 0x00000100
@@ -1179,6 +1186,8 @@ static int si_common_early_init(void *handle)
 			AMD_CG_SUPPORT_HDP_LS |
 			AMD_CG_SUPPORT_HDP_MGCG;
 			adev->pg_flags = 0;
+		adev->external_rev_id = (adev->rev_id == 0) ? 1 :
+					(adev->rev_id == 1) ? 5 : 6;
 		break;
 	case CHIP_PITCAIRN:
 		adev->cg_flags =
@@ -1198,6 +1207,7 @@ static int si_common_early_init(void *handle)
 			AMD_CG_SUPPORT_HDP_LS |
 			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
+		adev->external_rev_id = adev->rev_id + 20;
 		break;
 
 	case CHIP_VERDE:
@@ -1219,7 +1229,7 @@ static int si_common_early_init(void *handle)
 			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		//???
-		adev->external_rev_id = adev->rev_id + 0x14;
+		adev->external_rev_id = adev->rev_id + 40;
 		break;
 	case CHIP_OLAND:
 		adev->cg_flags =
@@ -1238,6 +1248,7 @@ static int si_common_early_init(void *handle)
 			AMD_CG_SUPPORT_HDP_LS |
 			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
+		adev->external_rev_id = 60;
 		break;
 	case CHIP_HAINAN:
 		adev->cg_flags =
@@ -1255,6 +1266,7 @@ static int si_common_early_init(void *handle)
 			AMD_CG_SUPPORT_HDP_LS |
 			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
+		adev->external_rev_id = 70;
 		break;
 
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 9f771f4..bf088d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -932,18 +932,64 @@ static int vi_common_early_init(void *handle)
 		adev->external_rev_id = adev->rev_id + 0x3c;
 		break;
 	case CHIP_TONGA:
-		adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG;
-		adev->pg_flags = AMD_PG_SUPPORT_UVD;
+		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_ROM_MGCG |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_DRM_LS |
+			AMD_CG_SUPPORT_UVD_MGCG;
+		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x14;
 		break;
 	case CHIP_POLARIS11:
-		adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG |
+		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_RLC_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_3D_CGCG |
+			AMD_CG_SUPPORT_GFX_3D_CGLS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_MGCG |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_ROM_MGCG |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_DRM_LS |
+			AMD_CG_SUPPORT_UVD_MGCG |
 			AMD_CG_SUPPORT_VCE_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x5A;
 		break;
 	case CHIP_POLARIS10:
-		adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG |
+		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_RLC_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_GFX_CGCG |
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_3D_CGCG |
+			AMD_CG_SUPPORT_GFX_3D_CGLS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_MGCG |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_HDP_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_ROM_MGCG |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_DRM_LS |
+			AMD_CG_SUPPORT_UVD_MGCG |
 			AMD_CG_SUPPORT_VCE_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x50;
@@ -971,6 +1017,7 @@ static int vi_common_early_init(void *handle)
 			adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
 				AMD_PG_SUPPORT_GFX_SMG |
 				AMD_PG_SUPPORT_GFX_PIPELINE |
+				AMD_PG_SUPPORT_CP |
 				AMD_PG_SUPPORT_UVD |
 				AMD_PG_SUPPORT_VCE;
 		}
@@ -996,6 +1043,7 @@ static int vi_common_early_init(void *handle)
 		adev->pg_flags = AMD_PG_SUPPORT_GFX_PG |
 			AMD_PG_SUPPORT_GFX_SMG |
 			AMD_PG_SUPPORT_GFX_PIPELINE |
+			AMD_PG_SUPPORT_CP |
 			AMD_PG_SUPPORT_UVD |
 			AMD_PG_SUPPORT_VCE;
 		adev->external_rev_id = adev->rev_id + 0x61;
@@ -1155,57 +1203,118 @@ static void vi_update_rom_medium_grain_clock_gating(struct amdgpu_device *adev,
 static int vi_common_set_clockgating_state_by_smu(void *handle,
 					   enum amd_clockgating_state state)
 {
-	uint32_t msg_id, pp_state;
+	uint32_t msg_id, pp_state = 0;
+	uint32_t pp_support_state = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	void *pp_handle = adev->powerplay.pp_handle;
 
-	if (state == AMD_CG_STATE_UNGATE)
-		pp_state = 0;
-	else
-		pp_state = PP_STATE_CG | PP_STATE_LS;
+	if (adev->cg_flags & (AMD_CG_SUPPORT_MC_LS | AMD_CG_SUPPORT_MC_MGCG)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_MC_LS) {
+			pp_support_state = AMD_CG_SUPPORT_MC_LS;
+			pp_state = PP_STATE_LS;
+		}
+		if (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG) {
+			pp_support_state |= AMD_CG_SUPPORT_MC_MGCG;
+			pp_state |= PP_STATE_CG;
+		}
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
+			       PP_BLOCK_SYS_MC,
+			       pp_support_state,
+			       pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
-		       PP_BLOCK_SYS_MC,
-		       PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-		       pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+	if (adev->cg_flags & (AMD_CG_SUPPORT_SDMA_LS | AMD_CG_SUPPORT_SDMA_MGCG)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_SDMA_LS) {
+			pp_support_state = AMD_CG_SUPPORT_SDMA_LS;
+			pp_state = PP_STATE_LS;
+		}
+		if (adev->cg_flags & AMD_CG_SUPPORT_SDMA_MGCG) {
+			pp_support_state |= AMD_CG_SUPPORT_SDMA_MGCG;
+			pp_state |= PP_STATE_CG;
+		}
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
+			       PP_BLOCK_SYS_SDMA,
+			       pp_support_state,
+			       pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
-		       PP_BLOCK_SYS_SDMA,
-		       PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-		       pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+	if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_MGCG)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
+			pp_support_state = AMD_CG_SUPPORT_HDP_LS;
+			pp_state = PP_STATE_LS;
+		}
+		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG) {
+			pp_support_state |= AMD_CG_SUPPORT_HDP_MGCG;
+			pp_state |= PP_STATE_CG;
+		}
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
+			       PP_BLOCK_SYS_HDP,
+			       pp_support_state,
+			       pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
-		       PP_BLOCK_SYS_HDP,
-		       PP_STATE_SUPPORT_CG | PP_STATE_SUPPORT_LS,
-		       pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
-		       PP_BLOCK_SYS_BIF,
-		       PP_STATE_SUPPORT_LS,
-		       pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+	if (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS) {
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		else
+			pp_state = PP_STATE_LS;
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
-		       PP_BLOCK_SYS_BIF,
-		       PP_STATE_SUPPORT_CG,
-		       pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+		msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
+			       PP_BLOCK_SYS_BIF,
+			       PP_STATE_SUPPORT_LS,
+			        pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
+	if (adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG) {
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		else
+			pp_state = PP_STATE_CG;
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
-		       PP_BLOCK_SYS_DRM,
-		       PP_STATE_SUPPORT_LS,
-		       pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+		msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
+			       PP_BLOCK_SYS_BIF,
+			       PP_STATE_SUPPORT_CG,
+			       pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 
-	msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
-		       PP_BLOCK_SYS_ROM,
-		       PP_STATE_SUPPORT_CG,
-		       pp_state);
-	amd_set_clockgating_by_smu(pp_handle, msg_id);
+	if (adev->cg_flags & AMD_CG_SUPPORT_DRM_LS) {
 
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		else
+			pp_state = PP_STATE_LS;
+
+		msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
+			       PP_BLOCK_SYS_DRM,
+			       PP_STATE_SUPPORT_LS,
+			       pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
+
+	if (adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG) {
+
+		if (state == AMD_CG_STATE_UNGATE)
+			pp_state = 0;
+		else
+			pp_state = PP_STATE_CG;
+
+		msg_id = PP_CG_MSG_ID(PP_GROUP_SYS,
+			       PP_BLOCK_SYS_ROM,
+			       PP_STATE_SUPPORT_CG,
+			       pp_state);
+		amd_set_clockgating_by_smu(pp_handle, msg_id);
+	}
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index d198627..c02469a 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -126,6 +126,10 @@ enum amd_vce_level {
 #define AMD_CG_SUPPORT_HDP_LS			(1 << 15)
 #define AMD_CG_SUPPORT_HDP_MGCG			(1 << 16)
 #define AMD_CG_SUPPORT_ROM_MGCG			(1 << 17)
+#define AMD_CG_SUPPORT_DRM_LS			(1 << 18)
+#define AMD_CG_SUPPORT_BIF_MGCG			(1 << 19)
+#define AMD_CG_SUPPORT_GFX_3D_CGCG		(1 << 20)
+#define AMD_CG_SUPPORT_GFX_3D_CGLS		(1 << 21)
 
 /* PG flags */
 #define AMD_PG_SUPPORT_GFX_PG			(1 << 0)
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 904beaa..f75c642 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -223,7 +223,8 @@ static int ast_get_dram_info(struct drm_device *dev)
 	ast_write32(ast, 0x10000, 0xfc600309);
 
 	do {
-		;
+		if (pci_channel_offline(dev->pdev))
+			return -EIO;
 	} while (ast_read32(ast, 0x10000) != 0x01);
 	data = ast_read32(ast, 0x10004);
 
@@ -428,7 +429,9 @@ int ast_driver_load(struct drm_device *dev, unsigned long flags)
 	ast_detect_chip(dev, &need_post);
 
 	if (ast->chip != AST1180) {
-		ast_get_dram_info(dev);
+		ret = ast_get_dram_info(dev);
+		if (ret)
+			goto out_free;
 		ast->vram_size = ast_get_vram_info(dev);
 		DRM_INFO("dram %d %d %d %08x\n", ast->mclk, ast->dram_type, ast->dram_bus_width, ast->vram_size);
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 56002a5..243224a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3509,6 +3509,8 @@ extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val);
 int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u32 mbox, u32 val);
+int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
+		      u32 reply_mask, u32 reply, int timeout_base_ms);
 
 /* intel_sideband.c */
 u32 vlv_punit_read(struct drm_i915_private *dev_priv, u32 addr);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 412f351..4a31b7a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -174,21 +174,35 @@ static struct sg_table *
 i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 {
 	struct address_space *mapping = obj->base.filp->f_mapping;
-	char *vaddr = obj->phys_handle->vaddr;
+	drm_dma_handle_t *phys;
 	struct sg_table *st;
 	struct scatterlist *sg;
+	char *vaddr;
 	int i;
 
 	if (WARN_ON(i915_gem_object_needs_bit17_swizzle(obj)))
 		return ERR_PTR(-EINVAL);
 
+	/* Always aligning to the object size, allows a single allocation
+	 * to handle all possible callers, and given typical object sizes,
+	 * the alignment of the buddy allocation will naturally match.
+	 */
+	phys = drm_pci_alloc(obj->base.dev,
+			     obj->base.size,
+			     roundup_pow_of_two(obj->base.size));
+	if (!phys)
+		return ERR_PTR(-ENOMEM);
+
+	vaddr = phys->vaddr;
 	for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
 		struct page *page;
 		char *src;
 
 		page = shmem_read_mapping_page(mapping, i);
-		if (IS_ERR(page))
-			return ERR_CAST(page);
+		if (IS_ERR(page)) {
+			st = ERR_CAST(page);
+			goto err_phys;
+		}
 
 		src = kmap_atomic(page);
 		memcpy(vaddr, src, PAGE_SIZE);
@@ -202,21 +216,29 @@ i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
 	i915_gem_chipset_flush(to_i915(obj->base.dev));
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (st == NULL)
-		return ERR_PTR(-ENOMEM);
+	if (!st) {
+		st = ERR_PTR(-ENOMEM);
+		goto err_phys;
+	}
 
 	if (sg_alloc_table(st, 1, GFP_KERNEL)) {
 		kfree(st);
-		return ERR_PTR(-ENOMEM);
+		st = ERR_PTR(-ENOMEM);
+		goto err_phys;
 	}
 
 	sg = st->sgl;
 	sg->offset = 0;
 	sg->length = obj->base.size;
 
-	sg_dma_address(sg) = obj->phys_handle->busaddr;
+	sg_dma_address(sg) = phys->busaddr;
 	sg_dma_len(sg) = obj->base.size;
 
+	obj->phys_handle = phys;
+	return st;
+
+err_phys:
+	drm_pci_free(obj->base.dev, phys);
 	return st;
 }
 
@@ -272,12 +294,13 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj,
 
 	sg_free_table(pages);
 	kfree(pages);
+
+	drm_pci_free(obj->base.dev, obj->phys_handle);
 }
 
 static void
 i915_gem_object_release_phys(struct drm_i915_gem_object *obj)
 {
-	drm_pci_free(obj->base.dev, obj->phys_handle);
 	i915_gem_object_unpin_pages(obj);
 }
 
@@ -538,15 +561,13 @@ int
 i915_gem_object_attach_phys(struct drm_i915_gem_object *obj,
 			    int align)
 {
-	drm_dma_handle_t *phys;
 	int ret;
 
-	if (obj->phys_handle) {
-		if ((unsigned long)obj->phys_handle->vaddr & (align -1))
-			return -EBUSY;
+	if (align > obj->base.size)
+		return -EINVAL;
 
+	if (obj->ops == &i915_gem_phys_ops)
 		return 0;
-	}
 
 	if (obj->mm.madv != I915_MADV_WILLNEED)
 		return -EFAULT;
@@ -562,12 +583,6 @@ i915_gem_object_attach_phys(struct drm_i915_gem_object *obj,
 	if (obj->mm.pages)
 		return -EBUSY;
 
-	/* create a new object */
-	phys = drm_pci_alloc(obj->base.dev, obj->base.size, align);
-	if (!phys)
-		return -ENOMEM;
-
-	obj->phys_handle = phys;
 	obj->ops = &i915_gem_phys_ops;
 
 	return i915_gem_object_pin_pages(obj);
@@ -2326,7 +2341,8 @@ static struct sg_table *
 i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-	int page_count, i;
+	const unsigned long page_count = obj->base.size / PAGE_SIZE;
+	unsigned long i;
 	struct address_space *mapping;
 	struct sg_table *st;
 	struct scatterlist *sg;
@@ -2352,7 +2368,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	if (st == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	page_count = obj->base.size / PAGE_SIZE;
+rebuild_st:
 	if (sg_alloc_table(st, page_count, GFP_KERNEL)) {
 		kfree(st);
 		return ERR_PTR(-ENOMEM);
@@ -2411,8 +2427,25 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	i915_sg_trim(st);
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);
-	if (ret)
-		goto err_pages;
+	if (ret) {
+		/* DMA remapping failed? One possible cause is that
+		 * it could not reserve enough large entries, asking
+		 * for PAGE_SIZE chunks instead may be helpful.
+		 */
+		if (max_segment > PAGE_SIZE) {
+			for_each_sgt_page(page, sgt_iter, st)
+				put_page(page);
+			sg_free_table(st);
+
+			max_segment = PAGE_SIZE;
+			goto rebuild_st;
+		} else {
+			dev_warn(&dev_priv->drm.pdev->dev,
+				 "Failed to DMA remap %lu pages\n",
+				 page_count);
+			goto err_pages;
+		}
+	}
 
 	if (i915_gem_object_needs_bit17_swizzle(obj))
 		i915_gem_object_do_bit_17_swizzle(obj, st);
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index ebaa941..abc78bb 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -55,10 +55,9 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
 		return -ENODEV;
 
 	/* See the comment at the drm_mm_init() call for more about this check.
-	 * WaSkipStolenMemoryFirstPage:bdw,chv,kbl (incomplete)
+	 * WaSkipStolenMemoryFirstPage:bdw+ (incomplete)
 	 */
-	if (start < 4096 && (IS_GEN8(dev_priv) ||
-			     IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)))
+	if (start < 4096 && INTEL_GEN(dev_priv) >= 8)
 		start = 4096;
 
 	mutex_lock(&dev_priv->mm.stolen_lock);
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 47590ab..3df8d3d 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -460,7 +460,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 
 static DEVICE_ATTR(gt_act_freq_mhz, S_IRUGO, gt_act_freq_mhz_show, NULL);
 static DEVICE_ATTR(gt_cur_freq_mhz, S_IRUGO, gt_cur_freq_mhz_show, NULL);
-static DEVICE_ATTR(gt_boost_freq_mhz, S_IRUGO, gt_boost_freq_mhz_show, gt_boost_freq_mhz_store);
+static DEVICE_ATTR(gt_boost_freq_mhz, S_IRUGO | S_IWUSR, gt_boost_freq_mhz_show, gt_boost_freq_mhz_store);
 static DEVICE_ATTR(gt_max_freq_mhz, S_IRUGO | S_IWUSR, gt_max_freq_mhz_show, gt_max_freq_mhz_store);
 static DEVICE_ATTR(gt_min_freq_mhz, S_IRUGO | S_IWUSR, gt_min_freq_mhz_show, gt_min_freq_mhz_store);
 
diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h
index 8405b5a..7e3545f 100644
--- a/drivers/gpu/drm/i915/intel_bios.h
+++ b/drivers/gpu/drm/i915/intel_bios.h
@@ -46,14 +46,20 @@ struct edp_power_seq {
 	u16 t11_t12;
 } __packed;
 
-/* MIPI Sequence Block definitions */
+/*
+ * MIPI Sequence Block definitions
+ *
+ * Note the VBT spec has AssertReset / DeassertReset swapped from their
+ * usual naming, we use the proper names here to avoid confusion when
+ * reading the code.
+ */
 enum mipi_seq {
 	MIPI_SEQ_END = 0,
-	MIPI_SEQ_ASSERT_RESET,
+	MIPI_SEQ_DEASSERT_RESET,	/* Spec says MipiAssertResetPin */
 	MIPI_SEQ_INIT_OTP,
 	MIPI_SEQ_DISPLAY_ON,
 	MIPI_SEQ_DISPLAY_OFF,
-	MIPI_SEQ_DEASSERT_RESET,
+	MIPI_SEQ_ASSERT_RESET,		/* Spec says MipiDeassertResetPin */
 	MIPI_SEQ_BACKLIGHT_ON,		/* sequence block v2+ */
 	MIPI_SEQ_BACKLIGHT_OFF,		/* sequence block v2+ */
 	MIPI_SEQ_TEAR_ON,		/* sequence block v2+ */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index cf5cff7..6daad86 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6244,35 +6244,24 @@ skl_dpll0_disable(struct drm_i915_private *dev_priv)
 	dev_priv->cdclk_pll.vco = 0;
 }
 
-static bool skl_cdclk_pcu_ready(struct drm_i915_private *dev_priv)
-{
-	int ret;
-	u32 val;
-
-	/* inform PCU we want to change CDCLK */
-	val = SKL_CDCLK_PREPARE_FOR_CHANGE;
-	mutex_lock(&dev_priv->rps.hw_lock);
-	ret = sandybridge_pcode_read(dev_priv, SKL_PCODE_CDCLK_CONTROL, &val);
-	mutex_unlock(&dev_priv->rps.hw_lock);
-
-	return ret == 0 && (val & SKL_CDCLK_READY_FOR_CHANGE);
-}
-
-static bool skl_cdclk_wait_for_pcu_ready(struct drm_i915_private *dev_priv)
-{
-	return _wait_for(skl_cdclk_pcu_ready(dev_priv), 3000, 10) == 0;
-}
-
 static void skl_set_cdclk(struct drm_i915_private *dev_priv, int cdclk, int vco)
 {
 	u32 freq_select, pcu_ack;
+	int ret;
 
 	WARN_ON((cdclk == 24000) != (vco == 0));
 
 	DRM_DEBUG_DRIVER("Changing CDCLK to %d kHz (VCO %d kHz)\n", cdclk, vco);
 
-	if (!skl_cdclk_wait_for_pcu_ready(dev_priv)) {
-		DRM_ERROR("failed to inform PCU about cdclk change\n");
+	mutex_lock(&dev_priv->rps.hw_lock);
+	ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
+				SKL_CDCLK_PREPARE_FOR_CHANGE,
+				SKL_CDCLK_READY_FOR_CHANGE,
+				SKL_CDCLK_READY_FOR_CHANGE, 3);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+	if (ret) {
+		DRM_ERROR("Failed to inform PCU about cdclk change (%d)\n",
+			  ret);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 90283ed..d9bc19b 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -4014,8 +4014,8 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 		return;
 
 	/* FIXME: we need to synchronize this sort of stuff with hardware
-	 * readout */
-	if (WARN_ON_ONCE(!intel_dp->lane_count))
+	 * readout. Currently fast link training doesn't work on boot-up. */
+	if (!intel_dp->lane_count)
 		return;
 
 	/* if link training is requested we should perform it always */
diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index 0d8ff00..47cd1b2 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -300,7 +300,8 @@ static void chv_exec_gpio(struct drm_i915_private *dev_priv,
 	mutex_lock(&dev_priv->sb_lock);
 	vlv_iosf_sb_write(dev_priv, port, cfg1, 0);
 	vlv_iosf_sb_write(dev_priv, port, cfg0,
-			  CHV_GPIO_GPIOCFG_GPO | CHV_GPIO_GPIOTXSTATE(value));
+			  CHV_GPIO_GPIOEN | CHV_GPIO_GPIOCFG_GPO |
+			  CHV_GPIO_GPIOTXSTATE(value));
 	mutex_unlock(&dev_priv->sb_lock);
 }
 
@@ -376,11 +377,11 @@ static const fn_mipi_elem_exec exec_elem[] = {
  */
 
 static const char * const seq_name[] = {
-	[MIPI_SEQ_ASSERT_RESET] = "MIPI_SEQ_ASSERT_RESET",
+	[MIPI_SEQ_DEASSERT_RESET] = "MIPI_SEQ_DEASSERT_RESET",
 	[MIPI_SEQ_INIT_OTP] = "MIPI_SEQ_INIT_OTP",
 	[MIPI_SEQ_DISPLAY_ON] = "MIPI_SEQ_DISPLAY_ON",
 	[MIPI_SEQ_DISPLAY_OFF]  = "MIPI_SEQ_DISPLAY_OFF",
-	[MIPI_SEQ_DEASSERT_RESET] = "MIPI_SEQ_DEASSERT_RESET",
+	[MIPI_SEQ_ASSERT_RESET] = "MIPI_SEQ_ASSERT_RESET",
 	[MIPI_SEQ_BACKLIGHT_ON] = "MIPI_SEQ_BACKLIGHT_ON",
 	[MIPI_SEQ_BACKLIGHT_OFF] = "MIPI_SEQ_BACKLIGHT_OFF",
 	[MIPI_SEQ_TEAR_ON] = "MIPI_SEQ_TEAR_ON",
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0a09024..d4961fa 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1968,12 +1968,7 @@ int logical_render_ring_init(struct intel_engine_cs *engine)
 			  ret);
 	}
 
-	ret = logical_ring_init(engine);
-	if (ret) {
-		lrc_destroy_wa_ctx_obj(engine);
-	}
-
-	return ret;
+	return logical_ring_init(engine);
 }
 
 int logical_xcs_ring_init(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d67974e..ae2c0bb 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2964,24 +2964,10 @@ intel_enable_sagv(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-static int
-intel_do_sagv_disable(struct drm_i915_private *dev_priv)
-{
-	int ret;
-	uint32_t temp = GEN9_SAGV_DISABLE;
-
-	ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL,
-				     &temp);
-	if (ret)
-		return ret;
-	else
-		return temp & GEN9_SAGV_IS_DISABLED;
-}
-
 int
 intel_disable_sagv(struct drm_i915_private *dev_priv)
 {
-	int ret, result;
+	int ret;
 
 	if (!intel_has_sagv(dev_priv))
 		return 0;
@@ -2993,25 +2979,23 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 	mutex_lock(&dev_priv->rps.hw_lock);
 
 	/* bspec says to keep retrying for at least 1 ms */
-	ret = wait_for(result = intel_do_sagv_disable(dev_priv), 1);
+	ret = skl_pcode_request(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+				GEN9_SAGV_DISABLE,
+				GEN9_SAGV_IS_DISABLED, GEN9_SAGV_IS_DISABLED,
+				1);
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
-	if (ret == -ETIMEDOUT) {
-		DRM_ERROR("Request to disable SAGV timed out\n");
-		return -ETIMEDOUT;
-	}
-
 	/*
 	 * Some skl systems, pre-release machines in particular,
 	 * don't actually have an SAGV.
 	 */
-	if (IS_SKYLAKE(dev_priv) && result == -ENXIO) {
+	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
 		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
 		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
 		return 0;
-	} else if (result < 0) {
-		DRM_ERROR("Failed to disable the SAGV\n");
-		return result;
+	} else if (ret < 0) {
+		DRM_ERROR("Failed to disable the SAGV (%d)\n", ret);
+		return ret;
 	}
 
 	dev_priv->sagv_status = I915_SAGV_DISABLED;
@@ -7890,6 +7874,81 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
+static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
+				  u32 request, u32 reply_mask, u32 reply,
+				  u32 *status)
+{
+	u32 val = request;
+
+	*status = sandybridge_pcode_read(dev_priv, mbox, &val);
+
+	return *status || ((val & reply_mask) == reply);
+}
+
+/**
+ * skl_pcode_request - send PCODE request until acknowledgment
+ * @dev_priv: device private
+ * @mbox: PCODE mailbox ID the request is targeted for
+ * @request: request ID
+ * @reply_mask: mask used to check for request acknowledgment
+ * @reply: value used to check for request acknowledgment
+ * @timeout_base_ms: timeout for polling with preemption enabled
+ *
+ * Keep resending the @request to @mbox until PCODE acknowledges it, PCODE
+ * reports an error or an overall timeout of @timeout_base_ms+10 ms expires.
+ * The request is acknowledged once the PCODE reply dword equals @reply after
+ * applying @reply_mask. Polling is first attempted with preemption enabled
+ * for @timeout_base_ms and if this times out for another 10 ms with
+ * preemption disabled.
+ *
+ * Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some
+ * other error as reported by PCODE.
+ */
+int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
+		      u32 reply_mask, u32 reply, int timeout_base_ms)
+{
+	u32 status;
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+#define COND skl_pcode_try_request(dev_priv, mbox, request, reply_mask, reply, \
+				   &status)
+
+	/*
+	 * Prime the PCODE by doing a request first. Normally it guarantees
+	 * that a subsequent request, at most @timeout_base_ms later, succeeds.
+	 * _wait_for() doesn't guarantee when its passed condition is evaluated
+	 * first, so send the first request explicitly.
+	 */
+	if (COND) {
+		ret = 0;
+		goto out;
+	}
+	ret = _wait_for(COND, timeout_base_ms * 1000, 10);
+	if (!ret)
+		goto out;
+
+	/*
+	 * The above can time out if the number of requests was low (2 in the
+	 * worst case) _and_ PCODE was busy for some reason even after a
+	 * (queued) request and @timeout_base_ms delay. As a workaround retry
+	 * the poll with preemption disabled to maximize the number of
+	 * requests. Increase the timeout from @timeout_base_ms to 10ms to
+	 * account for interrupts that could reduce the number of these
+	 * requests.
+	 */
+	DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
+	WARN_ON_ONCE(timeout_base_ms > 3);
+	preempt_disable();
+	ret = wait_for_atomic(COND, 10);
+	preempt_enable();
+
+out:
+	return ret ? ret : status;
+#undef COND
+}
+
 static int byt_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
 	/*
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 7b488e2..c6be706 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -825,13 +825,9 @@ void intel_psr_init(struct drm_device *dev)
 	dev_priv->psr_mmio_base = IS_HASWELL(dev_priv) ?
 		HSW_EDP_PSR_BASE : BDW_EDP_PSR_BASE;
 
-	/* Per platform default */
-	if (i915.enable_psr == -1) {
-		if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-			i915.enable_psr = 1;
-		else
-			i915.enable_psr = 0;
-	}
+	/* Per platform default: all disabled. */
+	if (i915.enable_psr == -1)
+		i915.enable_psr = 0;
 
 	/* Set link_standby x link_off defaults */
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 356c662..87b4af0 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -1039,7 +1039,18 @@ static bool vlv_power_well_enabled(struct drm_i915_private *dev_priv,
 
 static void vlv_init_display_clock_gating(struct drm_i915_private *dev_priv)
 {
-	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
+	u32 val;
+
+	/*
+	 * On driver load, a pipe may be active and driving a DSI display.
+	 * Preserve DPOUNIT_CLOCK_GATE_DISABLE to avoid the pipe getting stuck
+	 * (and never recovering) in this case. intel_dsi_post_disable() will
+	 * clear it when we turn off the display.
+	 */
+	val = I915_READ(DSPCLK_GATE_D);
+	val &= DPOUNIT_CLOCK_GATE_DISABLE;
+	val |= VRHUNIT_CLOCK_GATE_DISABLE;
+	I915_WRITE(DSPCLK_GATE_D, val);
 
 	/*
 	 * Disable trickle feed and enable pnd deadline calculation
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index d7be0d9..0bffd3f 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -62,7 +62,7 @@ fw_domain_arm_timer(struct intel_uncore_forcewake_domain *d)
 {
 	d->wake_count++;
 	hrtimer_start_range_ns(&d->timer,
-			       ktime_set(0, NSEC_PER_MSEC),
+			       NSEC_PER_MSEC,
 			       NSEC_PER_MSEC,
 			       HRTIMER_MODE_REL);
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index f2f348f..a6126c9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -330,7 +330,7 @@ nouveau_fence_wait_legacy(struct dma_fence *f, bool intr, long wait)
 		__set_current_state(intr ? TASK_INTERRUPTIBLE :
 					   TASK_UNINTERRUPTIBLE);
 
-		kt = ktime_set(0, sleep_time);
+		kt = sleep_time;
 		schedule_hrtimeout(&kt, HRTIMER_MODE_REL);
 		sleep_time *= 2;
 		if (sleep_time > NSEC_PER_MSEC)
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 21b6732..c829cfb 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -603,8 +603,9 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev)
 	GOP_VBIOS_CONTENT *vbios;
 	VFCT_IMAGE_HEADER *vhdr;
 
-	if (!ACPI_SUCCESS(acpi_get_table_with_size("VFCT", 1, &hdr, &tbl_size)))
+	if (!ACPI_SUCCESS(acpi_get_table("VFCT", 1, &hdr)))
 		return false;
+	tbl_size = hdr->length;
 	if (tbl_size < sizeof(UEFI_ACPI_VFCT)) {
 		DRM_ERROR("ACPI VFCT table present but broken (too short #1)\n");
 		goto out_unmap;
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index 9942b05..725dffa 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -539,7 +539,7 @@ static void tilcdc_crtc_off(struct drm_crtc *crtc, bool shutdown)
 	}
 
 	drm_flip_work_commit(&tilcdc_crtc->unref_work, priv->wq);
-	tilcdc_crtc->last_vblank = ktime_set(0, 0);
+	tilcdc_crtc->last_vblank = 0;
 
 	tilcdc_crtc->enabled = false;
 	mutex_unlock(&tilcdc_crtc->enable_lock);
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 446802a..b44b32f 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -135,9 +135,9 @@ u64 hv_do_hypercall(u64 control, void *input, void *output)
 EXPORT_SYMBOL_GPL(hv_do_hypercall);
 
 #ifdef CONFIG_X86_64
-static cycle_t read_hv_clock_tsc(struct clocksource *arg)
+static u64 read_hv_clock_tsc(struct clocksource *arg)
 {
-	cycle_t current_tick;
+	u64 current_tick;
 	struct ms_hyperv_tsc_page *tsc_pg = hv_context.tsc_page;
 
 	if (tsc_pg->tsc_sequence != 0) {
@@ -146,7 +146,7 @@ static cycle_t read_hv_clock_tsc(struct clocksource *arg)
 		 */
 
 		while (1) {
-			cycle_t tmp;
+			u64 tmp;
 			u32 sequence = tsc_pg->tsc_sequence;
 			u64 cur_tsc;
 			u64 scale = tsc_pg->tsc_scale;
@@ -350,7 +350,7 @@ int hv_post_message(union hv_connection_id connection_id,
 static int hv_ce_set_next_event(unsigned long delta,
 				struct clock_event_device *evt)
 {
-	cycle_t current_tick;
+	u64 current_tick;
 
 	WARN_ON(!clockevent_state_oneshot(evt));
 
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index 3fe368b..a51b6b6 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -804,10 +804,10 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	if (!etm_count++) {
 		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "AP_ARM_CORESIGHT_STARTING",
+					  "arm/coresight:starting",
 					  etm_starting_cpu, etm_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT_ONLINE",
+						"arm/coresight:online",
 						etm_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 4db8d6a..031480f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -986,11 +986,11 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm4_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
-					  "AP_ARM_CORESIGHT4_STARTING",
+		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
+					  "arm/coresight4:starting",
 					  etm4_starting_cpu, etm4_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT4_ONLINE",
+						"arm/coresight4:online",
 						etm4_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
@@ -1037,7 +1037,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 err_arch_supported:
 	if (--etm4_count == 0) {
-		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING);
+		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)
 			cpuhp_remove_state_nocalls(hp_online);
 	}
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 08153ea..6ce4313 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -150,6 +150,29 @@ static int i2c_dw_plat_prepare_clk(struct dw_i2c_dev *i_dev, bool prepare)
 	return 0;
 }
 
+static void dw_i2c_set_fifo_size(struct dw_i2c_dev *dev, int id)
+{
+	u32 param, tx_fifo_depth, rx_fifo_depth;
+
+	/*
+	 * Try to detect the FIFO depth if not set by interface driver,
+	 * the depth could be from 2 to 256 from HW spec.
+	 */
+	param = i2c_dw_read_comp_param(dev);
+	tx_fifo_depth = ((param >> 16) & 0xff) + 1;
+	rx_fifo_depth = ((param >> 8)  & 0xff) + 1;
+	if (!dev->tx_fifo_depth) {
+		dev->tx_fifo_depth = tx_fifo_depth;
+		dev->rx_fifo_depth = rx_fifo_depth;
+		dev->adapter.nr = id;
+	} else if (tx_fifo_depth >= 2) {
+		dev->tx_fifo_depth = min_t(u32, dev->tx_fifo_depth,
+				tx_fifo_depth);
+		dev->rx_fifo_depth = min_t(u32, dev->rx_fifo_depth,
+				rx_fifo_depth);
+	}
+}
+
 static int dw_i2c_plat_probe(struct platform_device *pdev)
 {
 	struct dw_i2c_platform_data *pdata = dev_get_platdata(&pdev->dev);
@@ -245,13 +268,7 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 				1000000);
 	}
 
-	if (!dev->tx_fifo_depth) {
-		u32 param1 = i2c_dw_read_comp_param(dev);
-
-		dev->tx_fifo_depth = ((param1 >> 16) & 0xff) + 1;
-		dev->rx_fifo_depth = ((param1 >> 8)  & 0xff) + 1;
-		dev->adapter.nr = pdev->id;
-	}
+	dw_i2c_set_fifo_size(dev, pdev->id);
 
 	adap = &dev->adapter;
 	adap->owner = THIS_MODULE;
diff --git a/drivers/i2c/busses/i2c-octeon-core.c b/drivers/i2c/busses/i2c-octeon-core.c
index 3d10f1a..1d8775799 100644
--- a/drivers/i2c/busses/i2c-octeon-core.c
+++ b/drivers/i2c/busses/i2c-octeon-core.c
@@ -342,7 +342,9 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target,
 		if (result)
 			return result;
 
-		data[i] = octeon_i2c_data_read(i2c);
+		data[i] = octeon_i2c_data_read(i2c, &result);
+		if (result)
+			return result;
 		if (recv_len && i == 0) {
 			if (data[i] > I2C_SMBUS_BLOCK_MAX + 1)
 				return -EPROTO;
diff --git a/drivers/i2c/busses/i2c-octeon-core.h b/drivers/i2c/busses/i2c-octeon-core.h
index 87151ea..e160f83 100644
--- a/drivers/i2c/busses/i2c-octeon-core.h
+++ b/drivers/i2c/busses/i2c-octeon-core.h
@@ -141,11 +141,14 @@ static inline void octeon_i2c_writeq_flush(u64 val, void __iomem *addr)
  */
 static inline void octeon_i2c_reg_write(struct octeon_i2c *i2c, u64 eop_reg, u8 data)
 {
+	int tries = 1000;
 	u64 tmp;
 
 	__raw_writeq(SW_TWSI_V | eop_reg | data, i2c->twsi_base + SW_TWSI(i2c));
 	do {
 		tmp = __raw_readq(i2c->twsi_base + SW_TWSI(i2c));
+		if (--tries < 0)
+			return;
 	} while ((tmp & SW_TWSI_V) != 0);
 }
 
@@ -163,24 +166,32 @@ static inline void octeon_i2c_reg_write(struct octeon_i2c *i2c, u64 eop_reg, u8
  *
  * The I2C core registers are accessed indirectly via the SW_TWSI CSR.
  */
-static inline u8 octeon_i2c_reg_read(struct octeon_i2c *i2c, u64 eop_reg)
+static inline int octeon_i2c_reg_read(struct octeon_i2c *i2c, u64 eop_reg,
+				      int *error)
 {
+	int tries = 1000;
 	u64 tmp;
 
 	__raw_writeq(SW_TWSI_V | eop_reg | SW_TWSI_R, i2c->twsi_base + SW_TWSI(i2c));
 	do {
 		tmp = __raw_readq(i2c->twsi_base + SW_TWSI(i2c));
+		if (--tries < 0) {
+			/* signal that the returned data is invalid */
+			if (error)
+				*error = -EIO;
+			return 0;
+		}
 	} while ((tmp & SW_TWSI_V) != 0);
 
 	return tmp & 0xFF;
 }
 
 #define octeon_i2c_ctl_read(i2c)					\
-	octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_CTL)
-#define octeon_i2c_data_read(i2c)					\
-	octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_DATA)
+	octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_CTL, NULL)
+#define octeon_i2c_data_read(i2c, error)				\
+	octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_DATA, error)
 #define octeon_i2c_stat_read(i2c)					\
-	octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_STAT)
+	octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_STAT, NULL)
 
 /**
  * octeon_i2c_read_int - read the TWSI_INT register
diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c
index 05cf192..0ab1e55 100644
--- a/drivers/i2c/busses/i2c-xgene-slimpro.c
+++ b/drivers/i2c/busses/i2c-xgene-slimpro.c
@@ -415,6 +415,7 @@ static int xgene_slimpro_i2c_probe(struct platform_device *pdev)
 	adapter->algo = &xgene_slimpro_i2c_algorithm;
 	adapter->class = I2C_CLASS_HWMON;
 	adapter->dev.parent = &pdev->dev;
+	adapter->dev.of_node = pdev->dev.of_node;
 	i2c_set_adapdata(adapter, ctx);
 	rc = i2c_add_adapter(adapter);
 	if (rc) {
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 3de95a2..cf9e396 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -30,7 +30,7 @@
 #define pr_fmt(fmt) "i2c-core: " fmt
 
 #include <dt-bindings/i2c/i2c.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/acpi.h>
 #include <linux/clk/clk-conf.h>
 #include <linux/completion.h>
diff --git a/drivers/i2c/muxes/i2c-mux-mlxcpld.c b/drivers/i2c/muxes/i2c-mux-mlxcpld.c
index 3ab654b..b7ca249 100644
--- a/drivers/i2c/muxes/i2c-mux-mlxcpld.c
+++ b/drivers/i2c/muxes/i2c-mux-mlxcpld.c
@@ -95,6 +95,7 @@ static int mlxcpld_mux_reg_write(struct i2c_adapter *adap,
 				 struct i2c_client *client, u8 val)
 {
 	struct mlxcpld_mux_plat_data *pdata = dev_get_platdata(&client->dev);
+	int ret = -ENODEV;
 
 	if (adap->algo->master_xfer) {
 		struct i2c_msg msg;
@@ -104,17 +105,21 @@ static int mlxcpld_mux_reg_write(struct i2c_adapter *adap,
 		msg.flags = 0;
 		msg.len = 2;
 		msg.buf = msgbuf;
-		return __i2c_transfer(adap, &msg, 1);
+		ret = __i2c_transfer(adap, &msg, 1);
+
+		if (ret >= 0 && ret != 1)
+			ret = -EREMOTEIO;
 	} else if (adap->algo->smbus_xfer) {
 		union i2c_smbus_data data;
 
 		data.byte = val;
-		return adap->algo->smbus_xfer(adap, client->addr,
-					      client->flags, I2C_SMBUS_WRITE,
-					      pdata->sel_reg_addr,
-					      I2C_SMBUS_BYTE_DATA, &data);
-	} else
-		return -ENODEV;
+		ret = adap->algo->smbus_xfer(adap, client->addr,
+					     client->flags, I2C_SMBUS_WRITE,
+					     pdata->sel_reg_addr,
+					     I2C_SMBUS_BYTE_DATA, &data);
+	}
+
+	return ret;
 }
 
 static int mlxcpld_mux_select_chan(struct i2c_mux_core *muxc, u32 chan)
@@ -127,10 +132,7 @@ static int mlxcpld_mux_select_chan(struct i2c_mux_core *muxc, u32 chan)
 	/* Only select the channel if its different from the last channel */
 	if (data->last_chan != regval) {
 		err = mlxcpld_mux_reg_write(muxc->parent, client, regval);
-		if (err)
-			data->last_chan = 0;
-		else
-			data->last_chan = regval;
+		data->last_chan = err < 0 ? 0 : regval;
 	}
 
 	return err;
diff --git a/drivers/i2c/muxes/i2c-mux-pca954x.c b/drivers/i2c/muxes/i2c-mux-pca954x.c
index 9a348ee..dd18b9c 100644
--- a/drivers/i2c/muxes/i2c-mux-pca954x.c
+++ b/drivers/i2c/muxes/i2c-mux-pca954x.c
@@ -167,6 +167,9 @@ static int pca954x_reg_write(struct i2c_adapter *adap,
 		buf[0] = val;
 		msg.buf = buf;
 		ret = __i2c_transfer(adap, &msg, 1);
+
+		if (ret >= 0 && ret != 1)
+			ret = -EREMOTEIO;
 	} else {
 		union i2c_smbus_data data;
 		ret = adap->algo->smbus_xfer(adap, client->addr,
@@ -195,7 +198,7 @@ static int pca954x_select_chan(struct i2c_mux_core *muxc, u32 chan)
 	/* Only select the channel if its different from the last channel */
 	if (data->last_chan != regval) {
 		ret = pca954x_reg_write(muxc->parent, client, regval);
-		data->last_chan = ret ? 0 : regval;
+		data->last_chan = ret < 0 ? 0 : regval;
 	}
 
 	return ret;
diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c
index 0ceae5c..4b5dc01 100644
--- a/drivers/ide/hpt366.c
+++ b/drivers/ide/hpt366.c
@@ -130,7 +130,7 @@
 #include <linux/ide.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #define DRV_NAME "hpt366"
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 83679da..5ceace5 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -31,7 +31,7 @@
 
 #include <asm/byteorder.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/div64.h>
 
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 6360bbd..201e43f 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -51,7 +51,7 @@
 
 #include <asm/byteorder.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 int ide_end_rq(ide_drive_t *drive, struct request *rq, int error,
diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c
index 376f2dc..210a088 100644
--- a/drivers/ide/ide-iops.c
+++ b/drivers/ide/ide-iops.c
@@ -24,7 +24,7 @@
 
 #include <asm/byteorder.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 void SELECT_MASK(ide_drive_t *drive, int mask)
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 0b63fac..330e319 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -36,7 +36,7 @@
 
 #include <asm/byteorder.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 /**
diff --git a/drivers/ide/ide-proc.c b/drivers/ide/ide-proc.c
index 97c0700..863db44 100644
--- a/drivers/ide/ide-proc.c
+++ b/drivers/ide/ide-proc.c
@@ -16,7 +16,7 @@
 
 #include <linux/module.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/errno.h>
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
diff --git a/drivers/iio/trigger/iio-trig-hrtimer.c b/drivers/iio/trigger/iio-trig-hrtimer.c
index 5e6d451..a1cad6c 100644
--- a/drivers/iio/trigger/iio-trig-hrtimer.c
+++ b/drivers/iio/trigger/iio-trig-hrtimer.c
@@ -63,7 +63,7 @@ ssize_t iio_hrtimer_store_sampling_frequency(struct device *dev,
 		return -EINVAL;
 
 	info->sampling_frequency = val;
-	info->period = ktime_set(0, NSEC_PER_SEC / val);
+	info->period = NSEC_PER_SEC / val;
 
 	return len;
 }
@@ -141,8 +141,7 @@ static struct iio_sw_trigger *iio_trig_hrtimer_probe(const char *name)
 	trig_info->timer.function = iio_hrtimer_trig_handler;
 
 	trig_info->sampling_frequency = HRTIMER_DEFAULT_SAMPLING_FREQUENCY;
-	trig_info->period = ktime_set(0, NSEC_PER_SEC /
-				      trig_info->sampling_frequency);
+	trig_info->period = NSEC_PER_SEC / trig_info->sampling_frequency;
 
 	ret = iio_trigger_register(trig_info->swt.trigger);
 	if (ret)
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index 579f9a7..e0a995b 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -46,7 +46,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <rdma/ib.h>
 #include <rdma/ib_cm.h>
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 415a318..249b403 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -50,7 +50,7 @@
 #include <linux/semaphore.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <rdma/ib_mad.h>
 #include <rdma/ib_user_mad.h>
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 09b6491..7007822 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -38,7 +38,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "uverbs.h"
 #include "core_priv.h"
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 8135935..b3f95d4 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -46,7 +46,7 @@
 #include <linux/anon_inodes.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <rdma/ib.h>
 
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index b7ac97b..cda5542 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -321,7 +321,8 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		FW_RI_RES_WR_DCAEN_V(0) |
 		FW_RI_RES_WR_DCACPU_V(0) |
 		FW_RI_RES_WR_FBMIN_V(2) |
-		FW_RI_RES_WR_FBMAX_V(2) |
+		(t4_sq_onchip(&wq->sq) ? FW_RI_RES_WR_FBMAX_V(2) :
+					 FW_RI_RES_WR_FBMAX_V(3)) |
 		FW_RI_RES_WR_CIDXFTHRESHO_V(0) |
 		FW_RI_RES_WR_CIDXFTHRESH_V(0) |
 		FW_RI_RES_WR_EQSIZE_V(eqsize));
@@ -345,7 +346,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		FW_RI_RES_WR_DCAEN_V(0) |
 		FW_RI_RES_WR_DCACPU_V(0) |
 		FW_RI_RES_WR_FBMIN_V(2) |
-		FW_RI_RES_WR_FBMAX_V(2) |
+		FW_RI_RES_WR_FBMAX_V(3) |
 		FW_RI_RES_WR_CIDXFTHRESHO_V(0) |
 		FW_RI_RES_WR_CIDXFTHRESH_V(0) |
 		FW_RI_RES_WR_EQSIZE_V(eqsize));
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index 392f783..98923a8 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -358,13 +358,16 @@ void i40iw_qp_add_qos(struct i40iw_sc_qp *qp)
  * @dev: sc device struct
  * @pd: sc pd ptr
  * @pd_id: pd_id for allocated pd
+ * @abi_ver: ABI version from user context, -1 if not valid
  */
 static void i40iw_sc_pd_init(struct i40iw_sc_dev *dev,
 			     struct i40iw_sc_pd *pd,
-			     u16 pd_id)
+			     u16 pd_id,
+			     int abi_ver)
 {
 	pd->size = sizeof(*pd);
 	pd->pd_id = pd_id;
+	pd->abi_ver = abi_ver;
 	pd->dev = dev;
 }
 
@@ -2252,6 +2255,7 @@ static enum i40iw_status_code i40iw_sc_qp_init(struct i40iw_sc_qp *qp,
 					      offset);
 
 	info->qp_uk_init_info.wqe_alloc_reg = wqe_alloc_reg;
+	info->qp_uk_init_info.abi_ver = qp->pd->abi_ver;
 	ret_code = i40iw_qp_uk_init(&qp->qp_uk, &info->qp_uk_init_info);
 	if (ret_code)
 		return ret_code;
@@ -2270,10 +2274,21 @@ static enum i40iw_status_code i40iw_sc_qp_init(struct i40iw_sc_qp *qp,
 						    false);
 	i40iw_debug(qp->dev, I40IW_DEBUG_WQE, "%s: hw_sq_size[%04d] sq_ring.size[%04d]\n",
 		    __func__, qp->hw_sq_size, qp->qp_uk.sq_ring.size);
-	ret_code = i40iw_fragcnt_to_wqesize_rq(qp->qp_uk.max_rq_frag_cnt,
-					       &wqe_size);
-	if (ret_code)
-		return ret_code;
+
+	switch (qp->pd->abi_ver) {
+	case 4:
+		ret_code = i40iw_fragcnt_to_wqesize_rq(qp->qp_uk.max_rq_frag_cnt,
+						       &wqe_size);
+		if (ret_code)
+			return ret_code;
+		break;
+	case 5: /* fallthrough until next ABI version */
+	default:
+		if (qp->qp_uk.max_rq_frag_cnt > I40IW_MAX_WQ_FRAGMENT_COUNT)
+			return I40IW_ERR_INVALID_FRAG_COUNT;
+		wqe_size = I40IW_MAX_WQE_SIZE_RQ;
+		break;
+	}
 	qp->hw_rq_size = i40iw_get_encoded_wqe_size(qp->qp_uk.rq_size *
 				(wqe_size / I40IW_QP_WQE_MIN_SIZE), false);
 	i40iw_debug(qp->dev, I40IW_DEBUG_WQE,
diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c
index 449ba8c..db41ab4 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_puda.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c
@@ -930,7 +930,7 @@ enum i40iw_status_code i40iw_puda_create_rsrc(struct i40iw_sc_vsi *vsi,
 	INIT_LIST_HEAD(&rsrc->txpend);
 
 	rsrc->tx_wqe_avail_cnt = info->sq_size - 1;
-	dev->iw_pd_ops->pd_init(dev, &rsrc->sc_pd, info->pd_id);
+	dev->iw_pd_ops->pd_init(dev, &rsrc->sc_pd, info->pd_id, -1);
 	rsrc->qp_id = info->qp_id;
 	rsrc->cq_id = info->cq_id;
 	rsrc->sq_size = info->sq_size;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_type.h b/drivers/infiniband/hw/i40iw/i40iw_type.h
index f3f8e9c..7b76259 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_type.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_type.h
@@ -280,6 +280,7 @@ struct i40iw_sc_pd {
 	u32 size;
 	struct i40iw_sc_dev *dev;
 	u16 pd_id;
+	int abi_ver;
 };
 
 struct i40iw_cqp_quanta {
@@ -852,6 +853,7 @@ struct i40iw_qp_init_info {
 	u64 host_ctx_pa;
 	u64 q2_pa;
 	u64 shadow_area_pa;
+	int abi_ver;
 	u8 sq_tph_val;
 	u8 rq_tph_val;
 	u8 type;
@@ -1051,7 +1053,7 @@ struct i40iw_aeq_ops {
 };
 
 struct i40iw_pd_ops {
-	void (*pd_init)(struct i40iw_sc_dev *, struct i40iw_sc_pd *, u16);
+	void (*pd_init)(struct i40iw_sc_dev *, struct i40iw_sc_pd *, u16, int);
 };
 
 struct i40iw_priv_qp_ops {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ucontext.h b/drivers/infiniband/hw/i40iw/i40iw_ucontext.h
index 12acd68..57d3f1d 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ucontext.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_ucontext.h
@@ -39,8 +39,8 @@
 
 #include <linux/types.h>
 
-#define I40IW_ABI_USERSPACE_VER 4
-#define I40IW_ABI_KERNEL_VER    4
+#define I40IW_ABI_VER 5
+
 struct i40iw_alloc_ucontext_req {
 	__u32 reserved32;
 	__u8 userspace_ver;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_uk.c b/drivers/infiniband/hw/i40iw/i40iw_uk.c
index 4376cd6..2800f79 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_uk.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_uk.c
@@ -966,10 +966,6 @@ enum i40iw_status_code i40iw_qp_uk_init(struct i40iw_qp_uk *qp,
 	if (ret_code)
 		return ret_code;
 
-	ret_code = i40iw_get_wqe_shift(info->rq_size, info->max_rq_frag_cnt, 0, &rqshift);
-	if (ret_code)
-		return ret_code;
-
 	qp->sq_base = info->sq;
 	qp->rq_base = info->rq;
 	qp->shadow_area = info->shadow_area;
@@ -998,8 +994,19 @@ enum i40iw_status_code i40iw_qp_uk_init(struct i40iw_qp_uk *qp,
 	if (!qp->use_srq) {
 		qp->rq_size = info->rq_size;
 		qp->max_rq_frag_cnt = info->max_rq_frag_cnt;
-		qp->rq_wqe_size = rqshift;
 		I40IW_RING_INIT(qp->rq_ring, qp->rq_size);
+		switch (info->abi_ver) {
+		case 4:
+			ret_code = i40iw_get_wqe_shift(info->rq_size, info->max_rq_frag_cnt, 0, &rqshift);
+			if (ret_code)
+				return ret_code;
+			break;
+		case 5: /* fallthrough until next ABI version */
+		default:
+			rqshift = I40IW_MAX_RQ_WQE_SHIFT;
+			break;
+		}
+		qp->rq_wqe_size = rqshift;
 		qp->rq_wqe_size_multiplier = 4 << rqshift;
 	}
 	qp->ops = iw_qp_uk_ops;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_user.h b/drivers/infiniband/hw/i40iw/i40iw_user.h
index 80d9f46..84be6f1 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_user.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_user.h
@@ -76,6 +76,7 @@ enum i40iw_device_capabilities_const {
 	I40IW_MAX_ORD_SIZE =			127,
 	I40IW_MAX_WQ_ENTRIES =			2048,
 	I40IW_Q2_BUFFER_SIZE =			(248 + 100),
+	I40IW_MAX_WQE_SIZE_RQ =			128,
 	I40IW_QP_CTX_SIZE =			248,
 	I40IW_MAX_PDS = 			32768
 };
@@ -97,6 +98,7 @@ enum i40iw_device_capabilities_const {
 #define i40iw_address_list u64 *
 
 #define	I40IW_MAX_MR_SIZE	0x10000000000L
+#define	I40IW_MAX_RQ_WQE_SHIFT	2
 
 struct i40iw_qp_uk;
 struct i40iw_cq_uk;
@@ -405,7 +407,7 @@ struct i40iw_qp_uk_init_info {
 	u32 max_sq_frag_cnt;
 	u32 max_rq_frag_cnt;
 	u32 max_inline_data;
-
+	int abi_ver;
 };
 
 struct i40iw_cq_uk_init_info {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 7368a50..29e97df 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -145,9 +145,8 @@ static struct ib_ucontext *i40iw_alloc_ucontext(struct ib_device *ibdev,
 	if (ib_copy_from_udata(&req, udata, sizeof(req)))
 		return ERR_PTR(-EINVAL);
 
-	if (req.userspace_ver != I40IW_ABI_USERSPACE_VER) {
-		i40iw_pr_err("Invalid userspace driver version detected. Detected version %d, should be %d\n",
-			     req.userspace_ver, I40IW_ABI_USERSPACE_VER);
+	if (req.userspace_ver < 4 || req.userspace_ver > I40IW_ABI_VER) {
+		i40iw_pr_err("Unsupported provider library version %u.\n", req.userspace_ver);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -155,13 +154,14 @@ static struct ib_ucontext *i40iw_alloc_ucontext(struct ib_device *ibdev,
 	uresp.max_qps = iwdev->max_qp;
 	uresp.max_pds = iwdev->max_pd;
 	uresp.wq_size = iwdev->max_qp_wr * 2;
-	uresp.kernel_ver = I40IW_ABI_KERNEL_VER;
+	uresp.kernel_ver = req.userspace_ver;
 
 	ucontext = kzalloc(sizeof(*ucontext), GFP_KERNEL);
 	if (!ucontext)
 		return ERR_PTR(-ENOMEM);
 
 	ucontext->iwdev = iwdev;
+	ucontext->abi_ver = req.userspace_ver;
 
 	if (ib_copy_to_udata(udata, &uresp, sizeof(uresp))) {
 		kfree(ucontext);
@@ -333,6 +333,7 @@ static struct ib_pd *i40iw_alloc_pd(struct ib_device *ibdev,
 	struct i40iw_sc_dev *dev = &iwdev->sc_dev;
 	struct i40iw_alloc_pd_resp uresp;
 	struct i40iw_sc_pd *sc_pd;
+	struct i40iw_ucontext *ucontext;
 	u32 pd_id = 0;
 	int err;
 
@@ -353,15 +354,18 @@ static struct ib_pd *i40iw_alloc_pd(struct ib_device *ibdev,
 	}
 
 	sc_pd = &iwpd->sc_pd;
-	dev->iw_pd_ops->pd_init(dev, sc_pd, pd_id);
 
 	if (context) {
+		ucontext = to_ucontext(context);
+		dev->iw_pd_ops->pd_init(dev, sc_pd, pd_id, ucontext->abi_ver);
 		memset(&uresp, 0, sizeof(uresp));
 		uresp.pd_id = pd_id;
 		if (ib_copy_to_udata(udata, &uresp, sizeof(uresp))) {
 			err = -EFAULT;
 			goto error;
 		}
+	} else {
+		dev->iw_pd_ops->pd_init(dev, sc_pd, pd_id, -1);
 	}
 
 	i40iw_add_pdusecount(iwpd);
@@ -518,7 +522,7 @@ static int i40iw_setup_kmode_qp(struct i40iw_device *iwdev,
 	struct i40iw_dma_mem *mem = &iwqp->kqp.dma_mem;
 	u32 sqdepth, rqdepth;
 	u32 sq_size, rq_size;
-	u8 sqshift, rqshift;
+	u8 sqshift;
 	u32 size;
 	enum i40iw_status_code status;
 	struct i40iw_qp_uk_init_info *ukinfo = &info->qp_uk_init_info;
@@ -527,14 +531,11 @@ static int i40iw_setup_kmode_qp(struct i40iw_device *iwdev,
 	rq_size = i40iw_qp_roundup(ukinfo->rq_size + 1);
 
 	status = i40iw_get_wqe_shift(sq_size, ukinfo->max_sq_frag_cnt, ukinfo->max_inline_data, &sqshift);
-	if (!status)
-		status = i40iw_get_wqe_shift(rq_size, ukinfo->max_rq_frag_cnt, 0, &rqshift);
-
 	if (status)
 		return -ENOMEM;
 
 	sqdepth = sq_size << sqshift;
-	rqdepth = rq_size << rqshift;
+	rqdepth = rq_size << I40IW_MAX_RQ_WQE_SHIFT;
 
 	size = sqdepth * sizeof(struct i40iw_sq_uk_wr_trk_info) + (rqdepth << 3);
 	iwqp->kqp.wrid_mem = kzalloc(size, GFP_KERNEL);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.h b/drivers/infiniband/hw/i40iw/i40iw_verbs.h
index 6549c93..07c3fec 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.h
@@ -42,6 +42,7 @@ struct i40iw_ucontext {
 	spinlock_t cq_reg_mem_list_lock; /* memory list for cq's */
 	struct list_head qp_reg_mem_list;
 	spinlock_t qp_reg_mem_list_lock; /* memory list for qp's */
+	int abi_ver;
 };
 
 struct i40iw_pd {
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 302fb05..57c8de2 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -890,6 +890,8 @@ struct ib_cq *qedr_create_cq(struct ib_device *ibdev,
 
 		pbl_ptr = cq->q.pbl_tbl->pa;
 		page_cnt = cq->q.pbl_info.num_pbes;
+
+		cq->ibcq.cqe = chain_entries;
 	} else {
 		cq->cq_type = QEDR_CQ_TYPE_KERNEL;
 
@@ -905,6 +907,7 @@ struct ib_cq *qedr_create_cq(struct ib_device *ibdev,
 
 		page_cnt = qed_chain_get_page_cnt(&cq->pbl);
 		pbl_ptr = qed_chain_get_pbl_phys(&cq->pbl);
+		cq->ibcq.cqe = cq->pbl.capacity;
 	}
 
 	qedr_init_cq_params(cq, ctx, dev, vector, chain_entries, page_cnt,
@@ -982,8 +985,13 @@ int qedr_destroy_cq(struct ib_cq *ibcq)
 
 	/* GSIs CQs are handled by driver, so they don't exist in the FW */
 	if (cq->cq_type != QEDR_CQ_TYPE_GSI) {
+		int rc;
+
 		iparams.icid = cq->icid;
-		dev->ops->rdma_destroy_cq(dev->rdma_ctx, &iparams, &oparams);
+		rc = dev->ops->rdma_destroy_cq(dev->rdma_ctx, &iparams,
+					       &oparams);
+		if (rc)
+			return rc;
 		dev->ops->common->chain_free(dev->cdev, &cq->pbl);
 	}
 
@@ -1966,7 +1974,7 @@ int qedr_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 	if (attr_mask & IB_QP_STATE) {
 		if ((qp->qp_type != IB_QPT_GSI) && (!udata))
-			qedr_update_qp_state(dev, qp, qp_params.new_state);
+			rc = qedr_update_qp_state(dev, qp, qp_params.new_state);
 		qp->state = qp_params.new_state;
 	}
 
@@ -2070,8 +2078,10 @@ int qedr_destroy_qp(struct ib_qp *ibqp)
 	DP_DEBUG(dev, QEDR_MSG_QP, "destroy qp: destroying %p, qp type=%d\n",
 		 qp, qp->qp_type);
 
-	if (qp->state != (QED_ROCE_QP_STATE_RESET | QED_ROCE_QP_STATE_ERR |
-			  QED_ROCE_QP_STATE_INIT)) {
+	if ((qp->state != QED_ROCE_QP_STATE_RESET) &&
+	    (qp->state != QED_ROCE_QP_STATE_ERR) &&
+	    (qp->state != QED_ROCE_QP_STATE_INIT)) {
+
 		attr.qp_state = IB_QPS_ERR;
 		attr_mask |= IB_QP_STATE;
 
@@ -2626,7 +2636,9 @@ static u32 qedr_prepare_sq_rdma_data(struct qedr_dev *dev,
 	rwqe2->r_key = cpu_to_le32(rdma_wr(wr)->rkey);
 	DMA_REGPAIR_LE(rwqe2->remote_va, rdma_wr(wr)->remote_addr);
 
-	if (wr->send_flags & IB_SEND_INLINE) {
+	if (wr->send_flags & IB_SEND_INLINE &&
+	    (wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM ||
+	     wr->opcode == IB_WR_RDMA_WRITE)) {
 		u8 flags = 0;
 
 		SET_FIELD2(flags, RDMA_SQ_RDMA_WQE_1ST_INLINE_FLG, 1);
@@ -2977,8 +2989,9 @@ int qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 
 	spin_lock_irqsave(&qp->q_lock, flags);
 
-	if ((qp->state == QED_ROCE_QP_STATE_RESET) ||
-	    (qp->state == QED_ROCE_QP_STATE_ERR)) {
+	if ((qp->state != QED_ROCE_QP_STATE_RTS) &&
+	    (qp->state != QED_ROCE_QP_STATE_ERR) &&
+	    (qp->state != QED_ROCE_QP_STATE_SQD)) {
 		spin_unlock_irqrestore(&qp->q_lock, flags);
 		*bad_wr = wr;
 		DP_DEBUG(dev, QEDR_MSG_CQ,
@@ -3031,8 +3044,7 @@ int qedr_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 
 	spin_lock_irqsave(&qp->q_lock, flags);
 
-	if ((qp->state == QED_ROCE_QP_STATE_RESET) ||
-	    (qp->state == QED_ROCE_QP_STATE_ERR)) {
+	if (qp->state == QED_ROCE_QP_STATE_RESET) {
 		spin_unlock_irqrestore(&qp->q_lock, flags);
 		*bad_wr = wr;
 		return -EINVAL;
@@ -3174,6 +3186,7 @@ static int process_req(struct qedr_dev *dev, struct qedr_qp *qp,
 
 		/* fill WC */
 		wc->status = status;
+		wc->vendor_err = 0;
 		wc->wc_flags = 0;
 		wc->src_qp = qp->id;
 		wc->qp = &qp->ibqp;
@@ -3225,7 +3238,7 @@ static int qedr_poll_cq_req(struct qedr_dev *dev,
 		       "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n",
 		       cq->icid, qp->icid);
 		cnt = process_req(dev, qp, cq, num_entries, wc, req->sq_cons,
-				  IB_WC_WR_FLUSH_ERR, 0);
+				  IB_WC_WR_FLUSH_ERR, 1);
 		break;
 	default:
 		/* process all WQE before the cosumer */
@@ -3363,6 +3376,7 @@ static void __process_resp_one(struct qedr_dev *dev, struct qedr_qp *qp,
 
 	/* fill WC */
 	wc->status = wc_status;
+	wc->vendor_err = 0;
 	wc->src_qp = qp->id;
 	wc->qp = &qp->ibqp;
 	wc->wr_id = wr_id;
@@ -3391,6 +3405,7 @@ static int process_resp_flush(struct qedr_qp *qp, struct qedr_cq *cq,
 	while (num_entries && qp->rq.wqe_cons != hw_cons) {
 		/* fill WC */
 		wc->status = IB_WC_WR_FLUSH_ERR;
+		wc->vendor_err = 0;
 		wc->wc_flags = 0;
 		wc->src_qp = qp->id;
 		wc->byte_len = 0;
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index cd27cbd..d369f24 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -224,7 +224,7 @@ static inline enum comp_state check_psn(struct rxe_qp *qp,
 		else
 			return COMPST_DONE;
 	} else if ((diff > 0) && (wqe->mask & WR_ATOMIC_OR_READ_MASK)) {
-		return COMPST_ERROR_RETRY;
+		return COMPST_DONE;
 	} else {
 		return COMPST_CHECK_ACK;
 	}
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 16967cd..342e781 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -455,8 +455,7 @@ static int send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
 		return -EAGAIN;
 	}
 
-	if (pkt->qp)
-		atomic_inc(&pkt->qp->skb_out);
+	atomic_inc(&pkt->qp->skb_out);
 	kfree_skb(skb);
 
 	return 0;
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index c3e60e4..486d576 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -855,4 +855,5 @@ void rxe_qp_cleanup(void *arg)
 	free_rd_atomic_resources(qp);
 
 	kernel_sock_shutdown(qp->sk, SHUT_RDWR);
+	sock_release(qp->sk);
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 7a36ec9..3435eff 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -1070,12 +1070,13 @@ static enum resp_states duplicate_request(struct rxe_qp *qp,
 					  struct rxe_pkt_info *pkt)
 {
 	enum resp_states rc;
+	u32 prev_psn = (qp->resp.psn - 1) & BTH_PSN_MASK;
 
 	if (pkt->mask & RXE_SEND_MASK ||
 	    pkt->mask & RXE_WRITE_MASK) {
 		/* SEND. Ack again and cleanup. C9-105. */
 		if (bth_ack(pkt))
-			send_ack(qp, pkt, AETH_ACK_UNLIMITED, qp->resp.psn - 1);
+			send_ack(qp, pkt, AETH_ACK_UNLIMITED, prev_psn);
 		rc = RESPST_CLEANUP;
 		goto out;
 	} else if (pkt->mask & RXE_READ_MASK) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index a2f9f29..fd81111 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -35,7 +35,7 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "ipoib.h"
 
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 64b3d11..9104e6b 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -62,7 +62,7 @@
 
 #include <net/sock.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
diff --git a/drivers/input/input-compat.c b/drivers/input/input-compat.c
index d84d20b..2186f71 100644
--- a/drivers/input/input-compat.c
+++ b/drivers/input/input-compat.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/export.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "input-compat.h"
 
 #ifdef CONFIG_COMPAT
diff --git a/drivers/input/joystick/walkera0701.c b/drivers/input/joystick/walkera0701.c
index 70a893a..36a5b93 100644
--- a/drivers/input/joystick/walkera0701.c
+++ b/drivers/input/joystick/walkera0701.c
@@ -165,7 +165,7 @@ static void walkera0701_irq_handler(void *handler_data)
 				RESERVE + BIN1_PULSE - BIN0_PULSE)	/* frame sync .. */
 		w->counter = 0;
 
-	hrtimer_start(&w->timer, ktime_set(0, BIN_SAMPLE), HRTIMER_MODE_REL);
+	hrtimer_start(&w->timer, BIN_SAMPLE, HRTIMER_MODE_REL);
 }
 
 static enum hrtimer_restart timer_handler(struct hrtimer
diff --git a/drivers/input/misc/atlas_btns.c b/drivers/input/misc/atlas_btns.c
index 638165c..6423aac 100644
--- a/drivers/input/misc/atlas_btns.c
+++ b/drivers/input/misc/atlas_btns.c
@@ -28,7 +28,7 @@
 #include <linux/input.h>
 #include <linux/types.h>
 #include <linux/acpi.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define ACPI_ATLAS_NAME		"Atlas ACPI"
 #define ACPI_ATLAS_CLASS	"Atlas"
diff --git a/drivers/input/mouse/amimouse.c b/drivers/input/mouse/amimouse.c
index a7fd8f2..a33437c 100644
--- a/drivers/input/mouse/amimouse.c
+++ b/drivers/input/mouse/amimouse.c
@@ -25,7 +25,7 @@
 
 #include <asm/irq.h>
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
 
diff --git a/drivers/input/mouse/atarimouse.c b/drivers/input/mouse/atarimouse.c
index d1c4323..96f2f51 100644
--- a/drivers/input/mouse/atarimouse.c
+++ b/drivers/input/mouse/atarimouse.c
@@ -47,7 +47,7 @@
 
 #include <asm/irq.h>
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/atarihw.h>
 #include <asm/atarikb.h>
 #include <asm/atariints.h>
diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c
index 354d47e..7331084 100644
--- a/drivers/input/mouse/trackpoint.c
+++ b/drivers/input/mouse/trackpoint.c
@@ -15,7 +15,7 @@
 #include <linux/input.h>
 #include <linux/libps2.h>
 #include <linux/proc_fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "psmouse.h"
 #include "trackpoint.h"
 
diff --git a/drivers/input/serio/hp_sdc.c b/drivers/input/serio/hp_sdc.c
index 852858e..559c99c 100644
--- a/drivers/input/serio/hp_sdc.c
+++ b/drivers/input/serio/hp_sdc.c
@@ -79,7 +79,7 @@
 # define sdc_readb(p)		gsc_readb(p)
 # define sdc_writeb(v,p)	gsc_writeb((v),(p))
 #elif defined(__mc68000__)
-# include <asm/uaccess.h>
+#include <linux/uaccess.h>
 # define sdc_readb(p)		in_8(p)
 # define sdc_writeb(v,p)	out_8((p),(v))
 #else
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 73a4e68..77551f5 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -983,7 +983,11 @@ static int __init i8042_pnp_init(void)
 #if defined(__ia64__)
 		return -ENODEV;
 #else
-		pr_info("PNP: No PS/2 controller found. Probing ports directly.\n");
+		pr_info("PNP: No PS/2 controller found.\n");
+		if (x86_platform.legacy.i8042 !=
+				X86_LEGACY_I8042_EXPECTED_PRESENT)
+			return -ENODEV;
+		pr_info("Probing ports directly.\n");
 		return 0;
 #endif
 	}
@@ -1070,8 +1074,8 @@ static int __init i8042_platform_init(void)
 
 #ifdef CONFIG_X86
 	u8 a20_on = 0xdf;
-	/* Just return if pre-detection shows no i8042 controller exist */
-	if (!x86_platform.i8042_detect())
+	/* Just return if platform does not have i8042 controller */
+	if (x86_platform.legacy.i8042 == X86_LEGACY_I8042_PLATFORM_ABSENT)
 		return -ENODEV;
 #endif
 
diff --git a/drivers/input/serio/q40kbd.c b/drivers/input/serio/q40kbd.c
index 5a9d521..d0fccc8 100644
--- a/drivers/input/serio/q40kbd.c
+++ b/drivers/input/serio/q40kbd.c
@@ -38,7 +38,7 @@
 #include <linux/slab.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/q40_master.h>
 #include <asm/irq.h>
 #include <asm/q40ints.h>
diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c
index d189843..f8ead9f 100644
--- a/drivers/input/serio/serport.c
+++ b/drivers/input/serio/serport.c
@@ -13,7 +13,7 @@
  * the Free Software Foundation.
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c
index 4613f0a..d67547b 100644
--- a/drivers/input/tablet/aiptek.c
+++ b/drivers/input/tablet/aiptek.c
@@ -75,7 +75,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/usb/input.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
 /*
diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c
index abf09ac..b796e89 100644
--- a/drivers/input/tablet/gtco.c
+++ b/drivers/input/tablet/gtco.c
@@ -56,7 +56,7 @@ Scott Hill shill@gtcocalcomp.com
 #include <linux/slab.h>
 #include <linux/input.h>
 #include <linux/usb.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
 #include <linux/bitops.h>
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 971154c..6799cf9 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -2209,14 +2209,13 @@ static void __init free_dma_resources(void)
 static int __init early_amd_iommu_init(void)
 {
 	struct acpi_table_header *ivrs_base;
-	acpi_size ivrs_size;
 	acpi_status status;
 	int i, remap_cache_sz, ret = 0;
 
 	if (!amd_iommu_detected)
 		return -ENODEV;
 
-	status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size);
+	status = acpi_get_table("IVRS", 0, &ivrs_base);
 	if (status == AE_NOT_FOUND)
 		return -ENODEV;
 	else if (ACPI_FAILURE(status)) {
@@ -2338,7 +2337,7 @@ static int __init early_amd_iommu_init(void)
 
 out:
 	/* Don't leak any ACPI memory */
-	early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size);
+	acpi_put_table(ivrs_base);
 	ivrs_base = NULL;
 
 	return ret;
@@ -2362,10 +2361,9 @@ static int amd_iommu_enable_interrupts(void)
 static bool detect_ivrs(void)
 {
 	struct acpi_table_header *ivrs_base;
-	acpi_size ivrs_size;
 	acpi_status status;
 
-	status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size);
+	status = acpi_get_table("IVRS", 0, &ivrs_base);
 	if (status == AE_NOT_FOUND)
 		return false;
 	else if (ACPI_FAILURE(status)) {
@@ -2374,7 +2372,7 @@ static bool detect_ivrs(void)
 		return false;
 	}
 
-	early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size);
+	acpi_put_table(ivrs_base);
 
 	/* Make sure ACS will be enabled during PCI probe */
 	pci_request_acs();
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 8c53748..a88576d 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -68,7 +68,6 @@ DECLARE_RWSEM(dmar_global_lock);
 LIST_HEAD(dmar_drhd_units);
 
 struct acpi_table_header * __initdata dmar_tbl;
-static acpi_size dmar_tbl_size;
 static int dmar_dev_scope_status = 1;
 static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 
@@ -543,9 +542,7 @@ static int __init dmar_table_detect(void)
 	acpi_status status = AE_OK;
 
 	/* if we could find DMAR table, then there are DMAR devices */
-	status = acpi_get_table_with_size(ACPI_SIG_DMAR, 0,
-				(struct acpi_table_header **)&dmar_tbl,
-				&dmar_tbl_size);
+	status = acpi_get_table(ACPI_SIG_DMAR, 0, &dmar_tbl);
 
 	if (ACPI_SUCCESS(status) && !dmar_tbl) {
 		pr_warn("Unable to map DMAR\n");
@@ -906,7 +903,7 @@ int __init detect_intel_iommu(void)
 		x86_init.iommu.iommu_init = intel_iommu_init;
 #endif
 
-	early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size);
+	acpi_put_table(dmar_tbl);
 	dmar_tbl = NULL;
 	up_write(&dmar_global_lock);
 
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 8bcee65..eb0d4d4 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -578,13 +578,13 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 #ifdef CONFIG_SMP
 		set_smp_cross_call(armada_mpic_send_doorbell);
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-					  "AP_IRQ_ARMADA_XP_STARTING",
+					  "irqchip/armada/ipi:starting",
 					  armada_xp_mpic_starting_cpu, NULL);
 #endif
 	} else {
 #ifdef CONFIG_SMP
-		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
-					  "AP_IRQ_ARMADA_CASC_STARTING",
+		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
+					  "irqchip/armada/cascade:starting",
 					  mpic_cascaded_starting_cpu, NULL);
 #endif
 		irq_set_chained_handler(parent_irq,
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index d96b2c9..e7463e3 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -245,7 +245,7 @@ bcm2836_arm_irqchip_smp_init(void)
 #ifdef CONFIG_SMP
 	/* Unmask IPIs to the boot CPU. */
 	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
-			  "AP_IRQ_BCM2836_STARTING", bcm2836_cpu_starting,
+			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
 			  bcm2836_cpu_dying);
 
 	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 26e1d7f..c132f29 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -632,9 +632,9 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 static void gic_smp_init(void)
 {
 	set_smp_cross_call(gic_raise_softirq);
-	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GICV3_STARTING,
-				  "AP_IRQ_GICV3_STARTING", gic_starting_cpu,
-				  NULL);
+	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
+				  "irqchip/arm/gicv3:starting",
+				  gic_starting_cpu, NULL);
 }
 
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index d6c404b..1b1df4f 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1191,7 +1191,7 @@ static int __init __gic_init_bases(struct gic_chip_data *gic,
 		set_smp_cross_call(gic_raise_softirq);
 #endif
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
-					  "AP_IRQ_GIC_STARTING",
+					  "irqchip/arm/gic:starting",
 					  gic_starting_cpu, NULL);
 		set_handle_irq(gic_handle_irq);
 		if (static_key_true(&supports_deactivate))
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index 021b0e0..c1b4ee9 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -407,7 +407,7 @@ hip04_of_init(struct device_node *node, struct device_node *parent)
 	set_handle_irq(hip04_handle_irq);
 
 	hip04_irq_dist_init(&hip04_data);
-	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "AP_IRQ_HIP04_STARTING",
+	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "irqchip/hip04:starting",
 			  hip04_irq_starting_cpu, NULL);
 	return 0;
 }
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index c0178a1..c01c09e 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -152,12 +152,12 @@ static inline void gic_map_to_vpe(unsigned int intr, unsigned int vpe)
 }
 
 #ifdef CONFIG_CLKSRC_MIPS_GIC
-cycle_t gic_read_count(void)
+u64 gic_read_count(void)
 {
 	unsigned int hi, hi2, lo;
 
 	if (mips_cm_is64)
-		return (cycle_t)gic_read(GIC_REG(SHARED, GIC_SH_COUNTER));
+		return (u64)gic_read(GIC_REG(SHARED, GIC_SH_COUNTER));
 
 	do {
 		hi = gic_read32(GIC_REG(SHARED, GIC_SH_COUNTER_63_32));
@@ -165,7 +165,7 @@ cycle_t gic_read_count(void)
 		hi2 = gic_read32(GIC_REG(SHARED, GIC_SH_COUNTER_63_32));
 	} while (hi2 != hi);
 
-	return (((cycle_t) hi) << 32) + lo;
+	return (((u64) hi) << 32) + lo;
 }
 
 unsigned int gic_get_count_width(void)
@@ -179,7 +179,7 @@ unsigned int gic_get_count_width(void)
 	return bits;
 }
 
-void gic_write_compare(cycle_t cnt)
+void gic_write_compare(u64 cnt)
 {
 	if (mips_cm_is64) {
 		gic_write(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE), cnt);
@@ -191,7 +191,7 @@ void gic_write_compare(cycle_t cnt)
 	}
 }
 
-void gic_write_cpu_compare(cycle_t cnt, int cpu)
+void gic_write_cpu_compare(u64 cnt, int cpu)
 {
 	unsigned long flags;
 
@@ -211,17 +211,17 @@ void gic_write_cpu_compare(cycle_t cnt, int cpu)
 	local_irq_restore(flags);
 }
 
-cycle_t gic_read_compare(void)
+u64 gic_read_compare(void)
 {
 	unsigned int hi, lo;
 
 	if (mips_cm_is64)
-		return (cycle_t)gic_read(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE));
+		return (u64)gic_read(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE));
 
 	hi = gic_read32(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE_HI));
 	lo = gic_read32(GIC_REG(VPE_LOCAL, GIC_VPE_COMPARE_LO));
 
-	return (((cycle_t) hi) << 32) + lo;
+	return (((u64) hi) << 32) + lo;
 }
 
 void gic_start_count(void)
diff --git a/drivers/irqchip/irq-st.c b/drivers/irqchip/irq-st.c
index 9af48a8..5e0e250 100644
--- a/drivers/irqchip/irq-st.c
+++ b/drivers/irqchip/irq-st.c
@@ -180,7 +180,7 @@ static int st_irq_syscfg_probe(struct platform_device *pdev)
 	return st_irq_syscfg_enable(pdev);
 }
 
-static int st_irq_syscfg_resume(struct device *dev)
+static int __maybe_unused st_irq_syscfg_resume(struct device *dev)
 {
 	struct st_irq_syscfg *ddata = dev_get_drvdata(dev);
 
diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 823f698..49d0f70 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -28,7 +28,7 @@
 #include <linux/moduleparam.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/isdn/capicmd.h>
 #include <linux/isdn/capiutil.h>
 #ifdef AVMB1_COMPAT
diff --git a/drivers/isdn/hardware/avm/b1.c b/drivers/isdn/hardware/avm/b1.c
index 4d9b195..9fdbd99 100644
--- a/drivers/isdn/hardware/avm/b1.c
+++ b/drivers/isdn/hardware/avm/b1.c
@@ -24,7 +24,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <linux/init.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/netdevice.h>
 #include <linux/isdn/capilli.h>
 #include "avmcard.h"
diff --git a/drivers/isdn/hardware/avm/b1dma.c b/drivers/isdn/hardware/avm/b1dma.c
index 19b113f..818bd8f 100644
--- a/drivers/isdn/hardware/avm/b1dma.c
+++ b/drivers/isdn/hardware/avm/b1dma.c
@@ -23,7 +23,7 @@
 #include <linux/gfp.h>
 #include <asm/io.h>
 #include <linux/init.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/netdevice.h>
 #include <linux/isdn/capilli.h>
 #include "avmcard.h"
diff --git a/drivers/isdn/hardware/avm/c4.c b/drivers/isdn/hardware/avm/c4.c
index 5d00d72..17beb28 100644
--- a/drivers/isdn/hardware/avm/c4.c
+++ b/drivers/isdn/hardware/avm/c4.c
@@ -24,7 +24,7 @@
 #include <linux/init.h>
 #include <linux/gfp.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/netdevice.h>
 #include <linux/isdn/capicmd.h>
 #include <linux/isdn/capiutil.h>
diff --git a/drivers/isdn/hardware/eicon/capimain.c b/drivers/isdn/hardware/eicon/capimain.c
index 997d46a..be36d82 100644
--- a/drivers/isdn/hardware/eicon/capimain.c
+++ b/drivers/isdn/hardware/eicon/capimain.c
@@ -13,7 +13,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/skbuff.h>
 
diff --git a/drivers/isdn/hardware/eicon/divamnt.c b/drivers/isdn/hardware/eicon/divamnt.c
index 0de29b7b..72e58bf 100644
--- a/drivers/isdn/hardware/eicon/divamnt.c
+++ b/drivers/isdn/hardware/eicon/divamnt.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/poll.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "platform.h"
 #include "di_defs.h"
diff --git a/drivers/isdn/hardware/eicon/divasi.c b/drivers/isdn/hardware/eicon/divasi.c
index 4103a8c..cb88090 100644
--- a/drivers/isdn/hardware/eicon/divasi.c
+++ b/drivers/isdn/hardware/eicon/divasi.c
@@ -18,7 +18,7 @@
 #include <linux/proc_fs.h>
 #include <linux/skbuff.h>
 #include <linux/seq_file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "platform.h"
 #include "di_defs.h"
diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c
index 32f3451..8b7ad4f 100644
--- a/drivers/isdn/hardware/eicon/divasmain.c
+++ b/drivers/isdn/hardware/eicon/divasmain.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/ioport.h>
 #include <linux/pci.h>
diff --git a/drivers/isdn/hardware/eicon/divasproc.c b/drivers/isdn/hardware/eicon/divasproc.c
index 56ce98a..b57efd6 100644
--- a/drivers/isdn/hardware/eicon/divasproc.c
+++ b/drivers/isdn/hardware/eicon/divasproc.c
@@ -16,7 +16,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/list.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "platform.h"
 #include "debuglib.h"
diff --git a/drivers/isdn/hysdn/hysdn_boot.c b/drivers/isdn/hysdn/hysdn_boot.c
index eda4741..4a04253 100644
--- a/drivers/isdn/hysdn/hysdn_boot.c
+++ b/drivers/isdn/hysdn/hysdn_boot.c
@@ -13,7 +13,7 @@
 
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "hysdn_defs.h"
 #include "hysdn_pof.h"
diff --git a/drivers/leds/trigger/ledtrig-cpu.c b/drivers/leds/trigger/ledtrig-cpu.c
index 9719caf..a418964 100644
--- a/drivers/leds/trigger/ledtrig-cpu.c
+++ b/drivers/leds/trigger/ledtrig-cpu.c
@@ -127,7 +127,7 @@ static int __init ledtrig_cpu_init(void)
 
 	register_syscore_ops(&ledtrig_cpu_syscore_ops);
 
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_LEDTRIG_STARTING",
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "leds/trigger:starting",
 				ledtrig_online_cpu, ledtrig_prepare_down_cpu);
 	if (ret < 0)
 		pr_err("CPU hotplug notifier for ledtrig-cpu could not be registered: %d\n",
diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c
index 9e385b3..ac21904 100644
--- a/drivers/lguest/core.c
+++ b/drivers/lguest/core.c
@@ -15,7 +15,7 @@
 #include <linux/slab.h>
 #include <asm/paravirt.h>
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/poll.h>
 #include <asm/asm-offsets.h>
 #include "lg.h"
diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c
index e3abebc9..0bc127e 100644
--- a/drivers/lguest/page_tables.c
+++ b/drivers/lguest/page_tables.c
@@ -16,7 +16,7 @@
 #include <linux/random.h>
 #include <linux/percpu.h>
 #include <asm/tlbflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "lg.h"
 
 /*M:008
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 743253f..d71f632 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -45,7 +45,7 @@
 #include <asm/desc.h>
 #include <asm/setup.h>
 #include <asm/lguest.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 #include "../lg.h"
diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c
index cd35079..281fa9e 100644
--- a/drivers/macintosh/ans-lcd.c
+++ b/drivers/macintosh/ans-lcd.c
@@ -11,7 +11,7 @@
 #include <linux/delay.h>
 #include <linux/fs.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sections.h>
 #include <asm/prom.h>
 #include <asm/io.h>
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index 08edb2c..2278691 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -47,7 +47,7 @@
 #include <asm/pmac_feature.h>
 #include <asm/smu.h>
 #include <asm/sections.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define VERSION "0.7"
 #define AUTHOR  "(c) 2005 Benjamin Herrenschmidt, IBM Corp."
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 91081dc..43b8db2 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -57,7 +57,7 @@
 #include <asm/pmac_feature.h>
 #include <asm/pmac_pfunc.h>
 #include <asm/pmac_low_i2c.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/cputable.h>
 #include <asm/time.h>
diff --git a/drivers/macintosh/via-pmu68k.c b/drivers/macintosh/via-pmu68k.c
index a00ee41..a411c5c 100644
--- a/drivers/macintosh/via-pmu68k.c
+++ b/drivers/macintosh/via-pmu68k.c
@@ -38,7 +38,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Misc minor number allocated for /dev/pmu */
 #define PMU_MINOR	154
diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c
index c19dd82..2aeb034 100644
--- a/drivers/mailbox/bcm-pdc-mailbox.c
+++ b/drivers/mailbox/bcm-pdc-mailbox.c
@@ -60,7 +60,13 @@
 #define RING_ENTRY_SIZE   sizeof(struct dma64dd)
 
 /* # entries in PDC dma ring */
-#define PDC_RING_ENTRIES  128
+#define PDC_RING_ENTRIES  512
+/*
+ * Minimum number of ring descriptor entries that must be free to tell mailbox
+ * framework that it can submit another request
+ */
+#define PDC_RING_SPACE_MIN  15
+
 #define PDC_RING_SIZE    (PDC_RING_ENTRIES * RING_ENTRY_SIZE)
 /* Rings are 8k aligned */
 #define RING_ALIGN_ORDER  13
@@ -93,11 +99,9 @@
  * Interrupt mask and status definitions. Enable interrupts for tx and rx on
  * ring 0
  */
-#define PDC_XMTINT_0         (24 + PDC_RINGSET)
 #define PDC_RCVINT_0         (16 + PDC_RINGSET)
-#define PDC_XMTINTEN_0       BIT(PDC_XMTINT_0)
 #define PDC_RCVINTEN_0       BIT(PDC_RCVINT_0)
-#define PDC_INTMASK  (PDC_XMTINTEN_0 | PDC_RCVINTEN_0)
+#define PDC_INTMASK	     (PDC_RCVINTEN_0)
 #define PDC_LAZY_FRAMECOUNT  1
 #define PDC_LAZY_TIMEOUT     10000
 #define PDC_LAZY_INT  (PDC_LAZY_TIMEOUT | (PDC_LAZY_FRAMECOUNT << 24))
@@ -117,15 +121,16 @@
 
 /*
  * Sets the following bits for write to transmit control reg:
- *  0    - XmtEn - enable activity on the tx channel
  * 11    - PtyChkDisable - parity check is disabled
  * 20:18 - BurstLen = 3 -> 2^7 = 128 byte data reads from memory
  */
-#define PDC_TX_CTL              0x000C0801
+#define PDC_TX_CTL		0x000C0800
+
+/* Bit in tx control reg to enable tx channel */
+#define PDC_TX_ENABLE		0x1
 
 /*
  * Sets the following bits for write to receive control reg:
- * 0     - RcvEn - enable activity on the rx channel
  * 7:1   - RcvOffset - size in bytes of status region at start of rx frame buf
  * 9     - SepRxHdrDescEn - place start of new frames only in descriptors
  *                          that have StartOfFrame set
@@ -135,7 +140,10 @@
  * 11    - PtyChkDisable - parity check is disabled
  * 20:18 - BurstLen = 3 -> 2^7 = 128 byte data reads from memory
  */
-#define PDC_RX_CTL              0x000C0E01
+#define PDC_RX_CTL		0x000C0E00
+
+/* Bit in rx control reg to enable rx channel */
+#define PDC_RX_ENABLE		0x1
 
 #define CRYPTO_D64_RS0_CD_MASK   ((PDC_RING_ENTRIES * RING_ENTRY_SIZE) - 1)
 
@@ -252,11 +260,29 @@ struct pdc_ring_alloc {
 	u32	    size;    /* ring allocation size in bytes */
 };
 
+/*
+ * context associated with a receive descriptor.
+ * @rxp_ctx: opaque context associated with frame that starts at each
+ *           rx ring index.
+ * @dst_sg:  Scatterlist used to form reply frames beginning at a given ring
+ *           index. Retained in order to unmap each sg after reply is processed.
+ * @rxin_numd: Number of rx descriptors associated with the message that starts
+ *             at a descriptor index. Not set for every index. For example,
+ *             if descriptor index i points to a scatterlist with 4 entries,
+ *             then the next three descriptor indexes don't have a value set.
+ * @resp_hdr: Virtual address of buffer used to catch DMA rx status
+ * @resp_hdr_daddr: physical address of DMA rx status buffer
+ */
+struct pdc_rx_ctx {
+	void *rxp_ctx;
+	struct scatterlist *dst_sg;
+	u32  rxin_numd;
+	void *resp_hdr;
+	dma_addr_t resp_hdr_daddr;
+};
+
 /* PDC state structure */
 struct pdc_state {
-	/* synchronize access to this PDC state structure */
-	spinlock_t pdc_lock;
-
 	/* Index of the PDC whose state is in this structure instance */
 	u8 pdc_idx;
 
@@ -272,13 +298,8 @@ struct pdc_state {
 
 	unsigned int pdc_irq;
 
-	/*
-	 * Last interrupt status read from PDC device. Saved in interrupt
-	 * handler so the handler can clear the interrupt in the device,
-	 * and the interrupt thread called later can know which interrupt
-	 * bits are active.
-	 */
-	unsigned long intstatus;
+	/* tasklet for deferred processing after DMA rx interrupt */
+	struct tasklet_struct rx_tasklet;
 
 	/* Number of bytes of receive status prior to each rx frame */
 	u32 rx_status_len;
@@ -369,11 +390,7 @@ struct pdc_state {
 	/* Index of next rx descriptor to post. */
 	u32  rxout;
 
-	/*
-	 * opaque context associated with frame that starts at each
-	 * rx ring index.
-	 */
-	void *rxp_ctx[PDC_RING_ENTRIES];
+	struct pdc_rx_ctx rx_ctx[PDC_RING_ENTRIES];
 
 	/*
 	 * Scatterlists used to form request and reply frames beginning at a
@@ -381,27 +398,18 @@ struct pdc_state {
 	 * is processed
 	 */
 	struct scatterlist *src_sg[PDC_RING_ENTRIES];
-	struct scatterlist *dst_sg[PDC_RING_ENTRIES];
-
-	/*
-	 * Number of rx descriptors associated with the message that starts
-	 * at this descriptor index. Not set for every index. For example,
-	 * if descriptor index i points to a scatterlist with 4 entries, then
-	 * the next three descriptor indexes don't have a value set.
-	 */
-	u32  rxin_numd[PDC_RING_ENTRIES];
-
-	void *resp_hdr[PDC_RING_ENTRIES];
-	dma_addr_t resp_hdr_daddr[PDC_RING_ENTRIES];
 
 	struct dentry *debugfs_stats;  /* debug FS stats file for this PDC */
 
 	/* counters */
-	u32  pdc_requests;    /* number of request messages submitted */
-	u32  pdc_replies;     /* number of reply messages received */
-	u32  txnobuf;         /* count of tx ring full */
-	u32  rxnobuf;         /* count of rx ring full */
-	u32  rx_oflow;        /* count of rx overflows */
+	u32  pdc_requests;     /* number of request messages submitted */
+	u32  pdc_replies;      /* number of reply messages received */
+	u32  last_tx_not_done; /* too few tx descriptors to indicate done */
+	u32  tx_ring_full;     /* unable to accept msg because tx ring full */
+	u32  rx_ring_full;     /* unable to accept msg because rx ring full */
+	u32  txnobuf;          /* unable to create tx descriptor */
+	u32  rxnobuf;          /* unable to create rx descriptor */
+	u32  rx_oflow;         /* count of rx overflows */
 };
 
 /* Global variables */
@@ -434,20 +442,33 @@ static ssize_t pdc_debugfs_read(struct file *filp, char __user *ubuf,
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "SPU %u stats:\n", pdcs->pdc_idx);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "PDC requests............%u\n",
+			       "PDC requests....................%u\n",
 			       pdcs->pdc_requests);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "PDC responses...........%u\n",
+			       "PDC responses...................%u\n",
 			       pdcs->pdc_replies);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "Tx err ring full........%u\n",
+			       "Tx not done.....................%u\n",
+			       pdcs->last_tx_not_done);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Tx ring full....................%u\n",
+			       pdcs->tx_ring_full);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Rx ring full....................%u\n",
+			       pdcs->rx_ring_full);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Tx desc write fail. Ring full...%u\n",
 			       pdcs->txnobuf);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "Rx err ring full........%u\n",
+			       "Rx desc write fail. Ring full...%u\n",
 			       pdcs->rxnobuf);
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
-			       "Receive overflow........%u\n",
+			       "Receive overflow................%u\n",
 			       pdcs->rx_oflow);
+	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+			       "Num frags in rx ring............%u\n",
+			       NRXDACTIVE(pdcs->rxin, pdcs->last_rx_curr,
+					  pdcs->nrxpost));
 
 	if (out_offset > out_count)
 		out_offset = out_count;
@@ -480,17 +501,16 @@ static void pdc_setup_debugfs(struct pdc_state *pdcs)
 	if (!debugfs_dir)
 		debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
 
-	pdcs->debugfs_stats = debugfs_create_file(spu_stats_name, S_IRUSR,
+	/* S_IRUSR == 0400 */
+	pdcs->debugfs_stats = debugfs_create_file(spu_stats_name, 0400,
 						  debugfs_dir, pdcs,
 						  &pdc_debugfs_stats);
 }
 
 static void pdc_free_debugfs(void)
 {
-	if (debugfs_dir && simple_empty(debugfs_dir)) {
-		debugfs_remove_recursive(debugfs_dir);
-		debugfs_dir = NULL;
-	}
+	debugfs_remove_recursive(debugfs_dir);
+	debugfs_dir = NULL;
 }
 
 /**
@@ -505,17 +525,17 @@ pdc_build_rxd(struct pdc_state *pdcs, dma_addr_t dma_addr,
 	      u32 buf_len, u32 flags)
 {
 	struct device *dev = &pdcs->pdev->dev;
+	struct dma64dd *rxd = &pdcs->rxd_64[pdcs->rxout];
 
 	dev_dbg(dev,
 		"Writing rx descriptor for PDC %u at index %u with length %u. flags %#x\n",
 		pdcs->pdc_idx, pdcs->rxout, buf_len, flags);
 
-	iowrite32(lower_32_bits(dma_addr),
-		  (void *)&pdcs->rxd_64[pdcs->rxout].addrlow);
-	iowrite32(upper_32_bits(dma_addr),
-		  (void *)&pdcs->rxd_64[pdcs->rxout].addrhigh);
-	iowrite32(flags, (void *)&pdcs->rxd_64[pdcs->rxout].ctrl1);
-	iowrite32(buf_len, (void *)&pdcs->rxd_64[pdcs->rxout].ctrl2);
+	rxd->addrlow = cpu_to_le32(lower_32_bits(dma_addr));
+	rxd->addrhigh = cpu_to_le32(upper_32_bits(dma_addr));
+	rxd->ctrl1 = cpu_to_le32(flags);
+	rxd->ctrl2 = cpu_to_le32(buf_len);
+
 	/* bump ring index and return */
 	pdcs->rxout = NEXTRXD(pdcs->rxout, pdcs->nrxpost);
 }
@@ -533,53 +553,50 @@ pdc_build_txd(struct pdc_state *pdcs, dma_addr_t dma_addr, u32 buf_len,
 	      u32 flags)
 {
 	struct device *dev = &pdcs->pdev->dev;
+	struct dma64dd *txd = &pdcs->txd_64[pdcs->txout];
 
 	dev_dbg(dev,
 		"Writing tx descriptor for PDC %u at index %u with length %u, flags %#x\n",
 		pdcs->pdc_idx, pdcs->txout, buf_len, flags);
 
-	iowrite32(lower_32_bits(dma_addr),
-		  (void *)&pdcs->txd_64[pdcs->txout].addrlow);
-	iowrite32(upper_32_bits(dma_addr),
-		  (void *)&pdcs->txd_64[pdcs->txout].addrhigh);
-	iowrite32(flags, (void *)&pdcs->txd_64[pdcs->txout].ctrl1);
-	iowrite32(buf_len, (void *)&pdcs->txd_64[pdcs->txout].ctrl2);
+	txd->addrlow = cpu_to_le32(lower_32_bits(dma_addr));
+	txd->addrhigh = cpu_to_le32(upper_32_bits(dma_addr));
+	txd->ctrl1 = cpu_to_le32(flags);
+	txd->ctrl2 = cpu_to_le32(buf_len);
 
 	/* bump ring index and return */
 	pdcs->txout = NEXTTXD(pdcs->txout, pdcs->ntxpost);
 }
 
 /**
- * pdc_receive() - Receive a response message from a given SPU.
+ * pdc_receive_one() - Receive a response message from a given SPU.
  * @pdcs:    PDC state for the SPU to receive from
- * @mssg:    mailbox message to be returned to client
  *
  * When the return code indicates success, the response message is available in
  * the receive buffers provided prior to submission of the request.
  *
- * Input:
- *   pdcs - PDC state structure for the SPU to be polled
- *   mssg - mailbox message to be returned to client. This function sets the
- *	    context pointer on the message to help the client associate the
- *	    response with a request.
- *
  * Return:  PDC_SUCCESS if one or more receive descriptors was processed
  *          -EAGAIN indicates that no response message is available
  *          -EIO an error occurred
  */
 static int
-pdc_receive(struct pdc_state *pdcs, struct brcm_message *mssg)
+pdc_receive_one(struct pdc_state *pdcs)
 {
 	struct device *dev = &pdcs->pdev->dev;
+	struct mbox_controller *mbc;
+	struct mbox_chan *chan;
+	struct brcm_message mssg;
 	u32 len, rx_status;
 	u32 num_frags;
-	int i;
 	u8 *resp_hdr;    /* virtual addr of start of resp message DMA header */
 	u32 frags_rdy;   /* number of fragments ready to read */
 	u32 rx_idx;      /* ring index of start of receive frame */
 	dma_addr_t resp_hdr_daddr;
+	struct pdc_rx_ctx *rx_ctx;
 
-	spin_lock(&pdcs->pdc_lock);
+	mbc = &pdcs->mbc;
+	chan = &mbc->chans[0];
+	mssg.type = BRCM_MESSAGE_SPU;
 
 	/*
 	 * return if a complete response message is not yet ready.
@@ -587,47 +604,34 @@ pdc_receive(struct pdc_state *pdcs, struct brcm_message *mssg)
 	 * to read.
 	 */
 	frags_rdy = NRXDACTIVE(pdcs->rxin, pdcs->last_rx_curr, pdcs->nrxpost);
-	if ((frags_rdy == 0) || (frags_rdy < pdcs->rxin_numd[pdcs->rxin])) {
-		/* See if the hw has written more fragments than we know */
-		pdcs->last_rx_curr =
-		    (ioread32((void *)&pdcs->rxregs_64->status0) &
-		     CRYPTO_D64_RS0_CD_MASK) / RING_ENTRY_SIZE;
-		frags_rdy = NRXDACTIVE(pdcs->rxin, pdcs->last_rx_curr,
-				       pdcs->nrxpost);
-		if ((frags_rdy == 0) ||
-		    (frags_rdy < pdcs->rxin_numd[pdcs->rxin])) {
-			/* No response ready */
-			spin_unlock(&pdcs->pdc_lock);
-			return -EAGAIN;
-		}
-		/* can't read descriptors/data until write index is read */
-		rmb();
-	}
+	if ((frags_rdy == 0) ||
+	    (frags_rdy < pdcs->rx_ctx[pdcs->rxin].rxin_numd))
+		/* No response ready */
+		return -EAGAIN;
 
 	num_frags = pdcs->txin_numd[pdcs->txin];
+	WARN_ON(num_frags == 0);
+
 	dma_unmap_sg(dev, pdcs->src_sg[pdcs->txin],
 		     sg_nents(pdcs->src_sg[pdcs->txin]), DMA_TO_DEVICE);
 
-	for (i = 0; i < num_frags; i++)
-		pdcs->txin = NEXTTXD(pdcs->txin, pdcs->ntxpost);
+	pdcs->txin = (pdcs->txin + num_frags) & pdcs->ntxpost;
 
 	dev_dbg(dev, "PDC %u reclaimed %d tx descriptors",
 		pdcs->pdc_idx, num_frags);
 
 	rx_idx = pdcs->rxin;
-	num_frags = pdcs->rxin_numd[rx_idx];
+	rx_ctx = &pdcs->rx_ctx[rx_idx];
+	num_frags = rx_ctx->rxin_numd;
 	/* Return opaque context with result */
-	mssg->ctx = pdcs->rxp_ctx[rx_idx];
-	pdcs->rxp_ctx[rx_idx] = NULL;
-	resp_hdr = pdcs->resp_hdr[rx_idx];
-	resp_hdr_daddr = pdcs->resp_hdr_daddr[rx_idx];
-	dma_unmap_sg(dev, pdcs->dst_sg[rx_idx],
-		     sg_nents(pdcs->dst_sg[rx_idx]), DMA_FROM_DEVICE);
+	mssg.ctx = rx_ctx->rxp_ctx;
+	rx_ctx->rxp_ctx = NULL;
+	resp_hdr = rx_ctx->resp_hdr;
+	resp_hdr_daddr = rx_ctx->resp_hdr_daddr;
+	dma_unmap_sg(dev, rx_ctx->dst_sg, sg_nents(rx_ctx->dst_sg),
+		     DMA_FROM_DEVICE);
 
-	for (i = 0; i < num_frags; i++)
-		pdcs->rxin = NEXTRXD(pdcs->rxin, pdcs->nrxpost);
-
-	spin_unlock(&pdcs->pdc_lock);
+	pdcs->rxin = (pdcs->rxin + num_frags) & pdcs->nrxpost;
 
 	dev_dbg(dev, "PDC %u reclaimed %d rx descriptors",
 		pdcs->pdc_idx, num_frags);
@@ -659,12 +663,35 @@ pdc_receive(struct pdc_state *pdcs, struct brcm_message *mssg)
 
 	dma_pool_free(pdcs->rx_buf_pool, resp_hdr, resp_hdr_daddr);
 
+	mbox_chan_received_data(chan, &mssg);
+
 	pdcs->pdc_replies++;
-	/* if we read one or more rx descriptors, claim success */
-	if (num_frags > 0)
-		return PDC_SUCCESS;
-	else
-		return -EIO;
+	return PDC_SUCCESS;
+}
+
+/**
+ * pdc_receive() - Process as many responses as are available in the rx ring.
+ * @pdcs:  PDC state
+ *
+ * Called within the hard IRQ.
+ * Return:
+ */
+static int
+pdc_receive(struct pdc_state *pdcs)
+{
+	int rx_status;
+
+	/* read last_rx_curr from register once */
+	pdcs->last_rx_curr =
+	    (ioread32(&pdcs->rxregs_64->status0) &
+	     CRYPTO_D64_RS0_CD_MASK) / RING_ENTRY_SIZE;
+
+	do {
+		/* Could be many frames ready */
+		rx_status = pdc_receive_one(pdcs);
+	} while (rx_status == PDC_SUCCESS);
+
+	return 0;
 }
 
 /**
@@ -766,8 +793,8 @@ static int pdc_tx_list_final(struct pdc_state *pdcs)
 	 * before chip starts to process new request
 	 */
 	wmb();
-	iowrite32(pdcs->rxout << 4, (void *)&pdcs->rxregs_64->ptr);
-	iowrite32(pdcs->txout << 4, (void *)&pdcs->txregs_64->ptr);
+	iowrite32(pdcs->rxout << 4, &pdcs->rxregs_64->ptr);
+	iowrite32(pdcs->txout << 4, &pdcs->txregs_64->ptr);
 	pdcs->pdc_requests++;
 
 	return PDC_SUCCESS;
@@ -796,6 +823,7 @@ static int pdc_rx_list_init(struct pdc_state *pdcs, struct scatterlist *dst_sg,
 	u32 rx_pkt_cnt = 1;	/* Adding a single rx buffer */
 	dma_addr_t daddr;
 	void *vaddr;
+	struct pdc_rx_ctx *rx_ctx;
 
 	rx_avail = pdcs->nrxpost - NRXDACTIVE(pdcs->rxin, pdcs->rxout,
 					      pdcs->nrxpost);
@@ -806,7 +834,7 @@ static int pdc_rx_list_init(struct pdc_state *pdcs, struct scatterlist *dst_sg,
 
 	/* allocate a buffer for the dma rx status */
 	vaddr = dma_pool_zalloc(pdcs->rx_buf_pool, GFP_ATOMIC, &daddr);
-	if (!vaddr)
+	if (unlikely(!vaddr))
 		return -ENOMEM;
 
 	/*
@@ -819,15 +847,16 @@ static int pdc_rx_list_init(struct pdc_state *pdcs, struct scatterlist *dst_sg,
 
 	/* This is always the first descriptor in the receive sequence */
 	flags = D64_CTRL1_SOF;
-	pdcs->rxin_numd[pdcs->rx_msg_start] = 1;
+	pdcs->rx_ctx[pdcs->rx_msg_start].rxin_numd = 1;
 
 	if (unlikely(pdcs->rxout == (pdcs->nrxd - 1)))
 		flags |= D64_CTRL1_EOT;
 
-	pdcs->rxp_ctx[pdcs->rxout] = ctx;
-	pdcs->dst_sg[pdcs->rxout] = dst_sg;
-	pdcs->resp_hdr[pdcs->rxout] = vaddr;
-	pdcs->resp_hdr_daddr[pdcs->rxout] = daddr;
+	rx_ctx = &pdcs->rx_ctx[pdcs->rxout];
+	rx_ctx->rxp_ctx = ctx;
+	rx_ctx->dst_sg = dst_sg;
+	rx_ctx->resp_hdr = vaddr;
+	rx_ctx->resp_hdr_daddr = daddr;
 	pdc_build_rxd(pdcs, daddr, pdcs->pdc_resp_hdr_len, flags);
 	return PDC_SUCCESS;
 }
@@ -895,7 +924,7 @@ static int pdc_rx_list_sg_add(struct pdc_state *pdcs, struct scatterlist *sg)
 		desc_w++;
 		sg = sg_next(sg);
 	}
-	pdcs->rxin_numd[pdcs->rx_msg_start] += desc_w;
+	pdcs->rx_ctx[pdcs->rx_msg_start].rxin_numd += desc_w;
 
 	return PDC_SUCCESS;
 }
@@ -903,7 +932,7 @@ static int pdc_rx_list_sg_add(struct pdc_state *pdcs, struct scatterlist *sg)
 /**
  * pdc_irq_handler() - Interrupt handler called in interrupt context.
  * @irq:      Interrupt number that has fired
- * @cookie:   PDC state for DMA engine that generated the interrupt
+ * @data:     device struct for DMA engine that generated the interrupt
  *
  * We have to clear the device interrupt status flags here. So cache the
  * status for later use in the thread function. Other than that, just return
@@ -912,88 +941,39 @@ static int pdc_rx_list_sg_add(struct pdc_state *pdcs, struct scatterlist *sg)
  * Return: IRQ_WAKE_THREAD if interrupt is ours
  *         IRQ_NONE otherwise
  */
-static irqreturn_t pdc_irq_handler(int irq, void *cookie)
+static irqreturn_t pdc_irq_handler(int irq, void *data)
 {
-	struct pdc_state *pdcs = cookie;
+	struct device *dev = (struct device *)data;
+	struct pdc_state *pdcs = dev_get_drvdata(dev);
 	u32 intstatus = ioread32(pdcs->pdc_reg_vbase + PDC_INTSTATUS_OFFSET);
 
-	if (intstatus & PDC_XMTINTEN_0)
-		set_bit(PDC_XMTINT_0, &pdcs->intstatus);
-	if (intstatus & PDC_RCVINTEN_0)
-		set_bit(PDC_RCVINT_0, &pdcs->intstatus);
+	if (unlikely(intstatus == 0))
+		return IRQ_NONE;
+
+	/* Disable interrupts until soft handler runs */
+	iowrite32(0, pdcs->pdc_reg_vbase + PDC_INTMASK_OFFSET);
 
 	/* Clear interrupt flags in device */
 	iowrite32(intstatus, pdcs->pdc_reg_vbase + PDC_INTSTATUS_OFFSET);
 
 	/* Wakeup IRQ thread */
-	if (pdcs && (irq == pdcs->pdc_irq) && (intstatus & PDC_INTMASK))
-		return IRQ_WAKE_THREAD;
-
-	return IRQ_NONE;
+	tasklet_schedule(&pdcs->rx_tasklet);
+	return IRQ_HANDLED;
 }
 
 /**
- * pdc_irq_thread() - Function invoked on deferred thread when a DMA tx has
- * completed or data is available to receive.
- * @irq:    Interrupt number
- * @cookie: PDC state for PDC that generated the interrupt
- *
- * On DMA tx complete, notify the mailbox client. On DMA rx complete, process
- * as many SPU response messages as are available and send each to the mailbox
- * client.
- *
- * Return: IRQ_HANDLED if we recognized and handled the interrupt
- *         IRQ_NONE otherwise
+ * pdc_tasklet_cb() - Tasklet callback that runs the deferred processing after
+ * a DMA receive interrupt. Reenables the receive interrupt.
+ * @data: PDC state structure
  */
-static irqreturn_t pdc_irq_thread(int irq, void *cookie)
+static void pdc_tasklet_cb(unsigned long data)
 {
-	struct pdc_state *pdcs = cookie;
-	struct mbox_controller *mbc;
-	struct mbox_chan *chan;
-	bool tx_int;
-	bool rx_int;
-	int rx_status;
-	struct brcm_message mssg;
+	struct pdc_state *pdcs = (struct pdc_state *)data;
 
-	tx_int = test_and_clear_bit(PDC_XMTINT_0, &pdcs->intstatus);
-	rx_int = test_and_clear_bit(PDC_RCVINT_0, &pdcs->intstatus);
+	pdc_receive(pdcs);
 
-	if (pdcs && (tx_int || rx_int)) {
-		dev_dbg(&pdcs->pdev->dev,
-			"%s() got irq %d with tx_int %s, rx_int %s",
-			__func__, irq,
-			tx_int ? "set" : "clear", rx_int ? "set" : "clear");
-
-		mbc = &pdcs->mbc;
-		chan = &mbc->chans[0];
-
-		if (tx_int) {
-			dev_dbg(&pdcs->pdev->dev, "%s(): tx done", __func__);
-			/* only one frame in flight at a time */
-			mbox_chan_txdone(chan, PDC_SUCCESS);
-		}
-		if (rx_int) {
-			while (1) {
-				/* Could be many frames ready */
-				memset(&mssg, 0, sizeof(mssg));
-				mssg.type = BRCM_MESSAGE_SPU;
-				rx_status = pdc_receive(pdcs, &mssg);
-				if (rx_status >= 0) {
-					dev_dbg(&pdcs->pdev->dev,
-						"%s(): invoking client rx cb",
-						__func__);
-					mbox_chan_received_data(chan, &mssg);
-				} else {
-					dev_dbg(&pdcs->pdev->dev,
-						"%s(): no SPU response available",
-						__func__);
-					break;
-				}
-			}
-		}
-		return IRQ_HANDLED;
-	}
-	return IRQ_NONE;
+	/* reenable interrupts */
+	iowrite32(PDC_INTMASK, pdcs->pdc_reg_vbase + PDC_INTMASK_OFFSET);
 }
 
 /**
@@ -1016,14 +996,14 @@ static int pdc_ring_init(struct pdc_state *pdcs, int ringset)
 
 	/* Allocate tx ring */
 	tx.vbase = dma_pool_zalloc(pdcs->ring_pool, GFP_KERNEL, &tx.dmabase);
-	if (!tx.vbase) {
+	if (unlikely(!tx.vbase)) {
 		err = -ENOMEM;
 		goto done;
 	}
 
 	/* Allocate rx ring */
 	rx.vbase = dma_pool_zalloc(pdcs->ring_pool, GFP_KERNEL, &rx.dmabase);
-	if (!rx.vbase) {
+	if (unlikely(!rx.vbase)) {
 		err = -ENOMEM;
 		goto fail_dealloc;
 	}
@@ -1033,9 +1013,6 @@ static int pdc_ring_init(struct pdc_state *pdcs, int ringset)
 	dev_dbg(dev, " - base DMA addr of rx ring      %pad", &rx.dmabase);
 	dev_dbg(dev, " - base virtual addr of rx ring  %p", rx.vbase);
 
-	/* lock after ring allocation to avoid scheduling while atomic */
-	spin_lock(&pdcs->pdc_lock);
-
 	memcpy(&pdcs->tx_ring_alloc, &tx, sizeof(tx));
 	memcpy(&pdcs->rx_ring_alloc, &rx, sizeof(rx));
 
@@ -1053,40 +1030,52 @@ static int pdc_ring_init(struct pdc_state *pdcs, int ringset)
 
 	/* Tell device the base DMA address of each ring */
 	dma_reg = &pdcs->regs->dmaregs[ringset];
+
+	/* But first disable DMA and set curptr to 0 for both TX & RX */
+	iowrite32(PDC_TX_CTL, &dma_reg->dmaxmt.control);
+	iowrite32((PDC_RX_CTL + (pdcs->rx_status_len << 1)),
+		  &dma_reg->dmarcv.control);
+	iowrite32(0, &dma_reg->dmaxmt.ptr);
+	iowrite32(0, &dma_reg->dmarcv.ptr);
+
+	/* Set base DMA addresses */
 	iowrite32(lower_32_bits(pdcs->tx_ring_alloc.dmabase),
-		  (void *)&dma_reg->dmaxmt.addrlow);
+		  &dma_reg->dmaxmt.addrlow);
 	iowrite32(upper_32_bits(pdcs->tx_ring_alloc.dmabase),
-		  (void *)&dma_reg->dmaxmt.addrhigh);
+		  &dma_reg->dmaxmt.addrhigh);
 
 	iowrite32(lower_32_bits(pdcs->rx_ring_alloc.dmabase),
-		  (void *)&dma_reg->dmarcv.addrlow);
+		  &dma_reg->dmarcv.addrlow);
 	iowrite32(upper_32_bits(pdcs->rx_ring_alloc.dmabase),
-		  (void *)&dma_reg->dmarcv.addrhigh);
+		  &dma_reg->dmarcv.addrhigh);
+
+	/* Re-enable DMA */
+	iowrite32(PDC_TX_CTL | PDC_TX_ENABLE, &dma_reg->dmaxmt.control);
+	iowrite32((PDC_RX_CTL | PDC_RX_ENABLE | (pdcs->rx_status_len << 1)),
+		  &dma_reg->dmarcv.control);
 
 	/* Initialize descriptors */
 	for (i = 0; i < PDC_RING_ENTRIES; i++) {
 		/* Every tx descriptor can be used for start of frame. */
 		if (i != pdcs->ntxpost) {
 			iowrite32(D64_CTRL1_SOF | D64_CTRL1_EOF,
-				  (void *)&pdcs->txd_64[i].ctrl1);
+				  &pdcs->txd_64[i].ctrl1);
 		} else {
 			/* Last descriptor in ringset. Set End of Table. */
 			iowrite32(D64_CTRL1_SOF | D64_CTRL1_EOF |
-				  D64_CTRL1_EOT,
-				  (void *)&pdcs->txd_64[i].ctrl1);
+				  D64_CTRL1_EOT, &pdcs->txd_64[i].ctrl1);
 		}
 
 		/* Every rx descriptor can be used for start of frame */
 		if (i != pdcs->nrxpost) {
 			iowrite32(D64_CTRL1_SOF,
-				  (void *)&pdcs->rxd_64[i].ctrl1);
+				  &pdcs->rxd_64[i].ctrl1);
 		} else {
 			/* Last descriptor in ringset. Set End of Table. */
 			iowrite32(D64_CTRL1_SOF | D64_CTRL1_EOT,
-				  (void *)&pdcs->rxd_64[i].ctrl1);
+				  &pdcs->rxd_64[i].ctrl1);
 		}
 	}
-	spin_unlock(&pdcs->pdc_lock);
 	return PDC_SUCCESS;
 
 fail_dealloc:
@@ -1111,6 +1100,80 @@ static void pdc_ring_free(struct pdc_state *pdcs)
 }
 
 /**
+ * pdc_desc_count() - Count the number of DMA descriptors that will be required
+ * for a given scatterlist. Account for the max length of a DMA buffer.
+ * @sg:    Scatterlist to be DMA'd
+ * Return: Number of descriptors required
+ */
+static u32 pdc_desc_count(struct scatterlist *sg)
+{
+	u32 cnt = 0;
+
+	while (sg) {
+		cnt += ((sg->length / PDC_DMA_BUF_MAX) + 1);
+		sg = sg_next(sg);
+	}
+	return cnt;
+}
+
+/**
+ * pdc_rings_full() - Check whether the tx ring has room for tx_cnt descriptors
+ * and the rx ring has room for rx_cnt descriptors.
+ * @pdcs:  PDC state
+ * @tx_cnt: The number of descriptors required in the tx ring
+ * @rx_cnt: The number of descriptors required i the rx ring
+ *
+ * Return: true if one of the rings does not have enough space
+ *         false if sufficient space is available in both rings
+ */
+static bool pdc_rings_full(struct pdc_state *pdcs, int tx_cnt, int rx_cnt)
+{
+	u32 rx_avail;
+	u32 tx_avail;
+	bool full = false;
+
+	/* Check if the tx and rx rings are likely to have enough space */
+	rx_avail = pdcs->nrxpost - NRXDACTIVE(pdcs->rxin, pdcs->rxout,
+					      pdcs->nrxpost);
+	if (unlikely(rx_cnt > rx_avail)) {
+		pdcs->rx_ring_full++;
+		full = true;
+	}
+
+	if (likely(!full)) {
+		tx_avail = pdcs->ntxpost - NTXDACTIVE(pdcs->txin, pdcs->txout,
+						      pdcs->ntxpost);
+		if (unlikely(tx_cnt > tx_avail)) {
+			pdcs->tx_ring_full++;
+			full = true;
+		}
+	}
+	return full;
+}
+
+/**
+ * pdc_last_tx_done() - If both the tx and rx rings have at least
+ * PDC_RING_SPACE_MIN descriptors available, then indicate that the mailbox
+ * framework can submit another message.
+ * @chan:  mailbox channel to check
+ * Return: true if PDC can accept another message on this channel
+ */
+static bool pdc_last_tx_done(struct mbox_chan *chan)
+{
+	struct pdc_state *pdcs = chan->con_priv;
+	bool ret;
+
+	if (unlikely(pdc_rings_full(pdcs, PDC_RING_SPACE_MIN,
+				    PDC_RING_SPACE_MIN))) {
+		pdcs->last_tx_not_done++;
+		ret = false;
+	} else {
+		ret = true;
+	}
+	return ret;
+}
+
+/**
  * pdc_send_data() - mailbox send_data function
  * @chan:	The mailbox channel on which the data is sent. The channel
  *              corresponds to a DMA ringset.
@@ -1141,29 +1204,43 @@ static int pdc_send_data(struct mbox_chan *chan, void *data)
 	int src_nent;
 	int dst_nent;
 	int nent;
+	u32 tx_desc_req;
+	u32 rx_desc_req;
 
-	if (mssg->type != BRCM_MESSAGE_SPU)
+	if (unlikely(mssg->type != BRCM_MESSAGE_SPU))
 		return -ENOTSUPP;
 
 	src_nent = sg_nents(mssg->spu.src);
-	if (src_nent) {
+	if (likely(src_nent)) {
 		nent = dma_map_sg(dev, mssg->spu.src, src_nent, DMA_TO_DEVICE);
-		if (nent == 0)
+		if (unlikely(nent == 0))
 			return -EIO;
 	}
 
 	dst_nent = sg_nents(mssg->spu.dst);
-	if (dst_nent) {
+	if (likely(dst_nent)) {
 		nent = dma_map_sg(dev, mssg->spu.dst, dst_nent,
 				  DMA_FROM_DEVICE);
-		if (nent == 0) {
+		if (unlikely(nent == 0)) {
 			dma_unmap_sg(dev, mssg->spu.src, src_nent,
 				     DMA_TO_DEVICE);
 			return -EIO;
 		}
 	}
 
-	spin_lock(&pdcs->pdc_lock);
+	/*
+	 * Check if the tx and rx rings have enough space. Do this prior to
+	 * writing any tx or rx descriptors. Need to ensure that we do not write
+	 * a partial set of descriptors, or write just rx descriptors but
+	 * corresponding tx descriptors don't fit. Note that we want this check
+	 * and the entire sequence of descriptor to happen without another
+	 * thread getting in. The channel spin lock in the mailbox framework
+	 * ensures this.
+	 */
+	tx_desc_req = pdc_desc_count(mssg->spu.src);
+	rx_desc_req = pdc_desc_count(mssg->spu.dst);
+	if (unlikely(pdc_rings_full(pdcs, tx_desc_req, rx_desc_req + 1)))
+		return -ENOSPC;
 
 	/* Create rx descriptors to SPU catch response */
 	err = pdc_rx_list_init(pdcs, mssg->spu.dst, mssg->ctx);
@@ -1173,9 +1250,7 @@ static int pdc_send_data(struct mbox_chan *chan, void *data)
 	err |= pdc_tx_list_sg_add(pdcs, mssg->spu.src);
 	err |= pdc_tx_list_final(pdcs);	/* initiate transfer */
 
-	spin_unlock(&pdcs->pdc_lock);
-
-	if (err)
+	if (unlikely(err))
 		dev_err(&pdcs->pdev->dev,
 			"%s failed with error %d", __func__, err);
 
@@ -1224,26 +1299,29 @@ void pdc_hw_init(struct pdc_state *pdcs)
 	/* initialize data structures */
 	pdcs->regs = (struct pdc_regs *)pdcs->pdc_reg_vbase;
 	pdcs->txregs_64 = (struct dma64_regs *)
-	    (void *)(((u8 *)pdcs->pdc_reg_vbase) +
+	    (((u8 *)pdcs->pdc_reg_vbase) +
 		     PDC_TXREGS_OFFSET + (sizeof(struct dma64) * ringset));
 	pdcs->rxregs_64 = (struct dma64_regs *)
-	    (void *)(((u8 *)pdcs->pdc_reg_vbase) +
+	    (((u8 *)pdcs->pdc_reg_vbase) +
 		     PDC_RXREGS_OFFSET + (sizeof(struct dma64) * ringset));
 
 	pdcs->ntxd = PDC_RING_ENTRIES;
 	pdcs->nrxd = PDC_RING_ENTRIES;
 	pdcs->ntxpost = PDC_RING_ENTRIES - 1;
 	pdcs->nrxpost = PDC_RING_ENTRIES - 1;
-	pdcs->regs->intmask = 0;
+	iowrite32(0, &pdcs->regs->intmask);
 
 	dma_reg = &pdcs->regs->dmaregs[ringset];
-	iowrite32(0, (void *)&dma_reg->dmaxmt.ptr);
-	iowrite32(0, (void *)&dma_reg->dmarcv.ptr);
 
-	iowrite32(PDC_TX_CTL, (void *)&dma_reg->dmaxmt.control);
+	/* Configure DMA but will enable later in pdc_ring_init() */
+	iowrite32(PDC_TX_CTL, &dma_reg->dmaxmt.control);
 
 	iowrite32(PDC_RX_CTL + (pdcs->rx_status_len << 1),
-		  (void *)&dma_reg->dmarcv.control);
+		  &dma_reg->dmarcv.control);
+
+	/* Reset current index pointers after making sure DMA is disabled */
+	iowrite32(0, &dma_reg->dmaxmt.ptr);
+	iowrite32(0, &dma_reg->dmarcv.ptr);
 
 	if (pdcs->pdc_resp_hdr_len == PDC_SPU2_RESP_HDR_LEN)
 		iowrite32(PDC_CKSUM_CTRL,
@@ -1251,6 +1329,21 @@ void pdc_hw_init(struct pdc_state *pdcs)
 }
 
 /**
+ * pdc_hw_disable() - Disable the tx and rx control in the hw.
+ * @pdcs: PDC state structure
+ *
+ */
+static void pdc_hw_disable(struct pdc_state *pdcs)
+{
+	struct dma64 *dma_reg;
+
+	dma_reg = &pdcs->regs->dmaregs[PDC_RINGSET];
+	iowrite32(PDC_TX_CTL, &dma_reg->dmaxmt.control);
+	iowrite32(PDC_RX_CTL + (pdcs->rx_status_len << 1),
+		  &dma_reg->dmarcv.control);
+}
+
+/**
  * pdc_rx_buf_pool_create() - Pool of receive buffers used to catch the metadata
  * header returned with each response message.
  * @pdcs: PDC state structure
@@ -1301,8 +1394,6 @@ static int pdc_interrupts_init(struct pdc_state *pdcs)
 	struct device_node *dn = pdev->dev.of_node;
 	int err;
 
-	pdcs->intstatus = 0;
-
 	/* interrupt configuration */
 	iowrite32(PDC_INTMASK, pdcs->pdc_reg_vbase + PDC_INTMASK_OFFSET);
 	iowrite32(PDC_LAZY_INT, pdcs->pdc_reg_vbase + PDC_RCVLAZY0_OFFSET);
@@ -1311,11 +1402,11 @@ static int pdc_interrupts_init(struct pdc_state *pdcs)
 	pdcs->pdc_irq = irq_of_parse_and_map(dn, 0);
 	dev_dbg(dev, "pdc device %s irq %u for pdcs %p",
 		dev_name(dev), pdcs->pdc_irq, pdcs);
-	err = devm_request_threaded_irq(dev, pdcs->pdc_irq,
-					pdc_irq_handler,
-					pdc_irq_thread, 0, dev_name(dev), pdcs);
+
+	err = devm_request_irq(dev, pdcs->pdc_irq, pdc_irq_handler, 0,
+			       dev_name(dev), dev);
 	if (err) {
-		dev_err(dev, "threaded tx IRQ %u request failed with err %d\n",
+		dev_err(dev, "IRQ %u request failed with err %d\n",
 			pdcs->pdc_irq, err);
 		return err;
 	}
@@ -1324,6 +1415,7 @@ static int pdc_interrupts_init(struct pdc_state *pdcs)
 
 static const struct mbox_chan_ops pdc_mbox_chan_ops = {
 	.send_data = pdc_send_data,
+	.last_tx_done = pdc_last_tx_done,
 	.startup = pdc_startup,
 	.shutdown = pdc_shutdown
 };
@@ -1356,8 +1448,9 @@ static int pdc_mb_init(struct pdc_state *pdcs)
 	if (!mbc->chans)
 		return -ENOMEM;
 
-	mbc->txdone_irq = true;
-	mbc->txdone_poll = false;
+	mbc->txdone_irq = false;
+	mbc->txdone_poll = true;
+	mbc->txpoll_period = 1;
 	for (chan_index = 0; chan_index < mbc->num_chans; chan_index++)
 		mbc->chans[chan_index].con_priv = pdcs;
 
@@ -1427,7 +1520,6 @@ static int pdc_probe(struct platform_device *pdev)
 		goto cleanup;
 	}
 
-	spin_lock_init(&pdcs->pdc_lock);
 	pdcs->pdev = pdev;
 	platform_set_drvdata(pdev, pdcs);
 	pdcs->pdc_idx = pdcg.num_spu;
@@ -1473,6 +1565,9 @@ static int pdc_probe(struct platform_device *pdev)
 
 	pdc_hw_init(pdcs);
 
+	/* Init tasklet for deferred DMA rx processing */
+	tasklet_init(&pdcs->rx_tasklet, pdc_tasklet_cb, (unsigned long)pdcs);
+
 	err = pdc_interrupts_init(pdcs);
 	if (err)
 		goto cleanup_buf_pool;
@@ -1489,6 +1584,7 @@ static int pdc_probe(struct platform_device *pdev)
 	return PDC_SUCCESS;
 
 cleanup_buf_pool:
+	tasklet_kill(&pdcs->rx_tasklet);
 	dma_pool_destroy(pdcs->rx_buf_pool);
 
 cleanup_ring_pool:
@@ -1504,6 +1600,10 @@ static int pdc_remove(struct platform_device *pdev)
 
 	pdc_free_debugfs();
 
+	tasklet_kill(&pdcs->rx_tasklet);
+
+	pdc_hw_disable(pdcs);
+
 	mbox_controller_unregister(&pdcs->mbc);
 
 	dma_pool_destroy(pdcs->rx_buf_pool);
diff --git a/drivers/mailbox/mailbox-sti.c b/drivers/mailbox/mailbox-sti.c
index a334db5..41bcd33 100644
--- a/drivers/mailbox/mailbox-sti.c
+++ b/drivers/mailbox/mailbox-sti.c
@@ -403,6 +403,7 @@ static const struct of_device_id sti_mailbox_match[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(of, sti_mailbox_match);
 
 static int sti_mbox_probe(struct platform_device *pdev)
 {
diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c
index 9ca96e9..9c79f80 100644
--- a/drivers/mailbox/mailbox-test.c
+++ b/drivers/mailbox/mailbox-test.c
@@ -11,12 +11,14 @@
 
 #include <linux/debugfs.h>
 #include <linux/err.h>
+#include <linux/fs.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/mailbox_client.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
@@ -39,6 +41,8 @@ struct mbox_test_device {
 	char			*signal;
 	char			*message;
 	spinlock_t		lock;
+	wait_queue_head_t	waitq;
+	struct fasync_struct	*async_queue;
 };
 
 static ssize_t mbox_test_signal_write(struct file *filp,
@@ -81,6 +85,13 @@ static const struct file_operations mbox_test_signal_ops = {
 	.llseek	= generic_file_llseek,
 };
 
+static int mbox_test_message_fasync(int fd, struct file *filp, int on)
+{
+	struct mbox_test_device *tdev = filp->private_data;
+
+	return fasync_helper(fd, filp, on, &tdev->async_queue);
+}
+
 static ssize_t mbox_test_message_write(struct file *filp,
 				       const char __user *userbuf,
 				       size_t count, loff_t *ppos)
@@ -138,6 +149,20 @@ static ssize_t mbox_test_message_write(struct file *filp,
 	return ret < 0 ? ret : count;
 }
 
+static bool mbox_test_message_data_ready(struct mbox_test_device *tdev)
+{
+	unsigned char data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tdev->lock, flags);
+	data = tdev->rx_buffer[0];
+	spin_unlock_irqrestore(&tdev->lock, flags);
+
+	if (data != '\0')
+		return true;
+	return false;
+}
+
 static ssize_t mbox_test_message_read(struct file *filp, char __user *userbuf,
 				      size_t count, loff_t *ppos)
 {
@@ -147,6 +172,8 @@ static ssize_t mbox_test_message_read(struct file *filp, char __user *userbuf,
 	int l = 0;
 	int ret;
 
+	DECLARE_WAITQUEUE(wait, current);
+
 	touser = kzalloc(MBOX_HEXDUMP_MAX_LEN + 1, GFP_KERNEL);
 	if (!touser)
 		return -ENOMEM;
@@ -155,15 +182,29 @@ static ssize_t mbox_test_message_read(struct file *filp, char __user *userbuf,
 		ret = snprintf(touser, 20, "<NO RX CAPABILITY>\n");
 		ret = simple_read_from_buffer(userbuf, count, ppos,
 					      touser, ret);
-		goto out;
+		goto kfree_err;
 	}
 
-	if (tdev->rx_buffer[0] == '\0') {
-		ret = snprintf(touser, 9, "<EMPTY>\n");
-		ret = simple_read_from_buffer(userbuf, count, ppos,
-					      touser, ret);
-		goto out;
-	}
+	add_wait_queue(&tdev->waitq, &wait);
+
+	do {
+		__set_current_state(TASK_INTERRUPTIBLE);
+
+		if (mbox_test_message_data_ready(tdev))
+			break;
+
+		if (filp->f_flags & O_NONBLOCK) {
+			ret = -EAGAIN;
+			goto waitq_err;
+		}
+
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			goto waitq_err;
+		}
+		schedule();
+
+	} while (1);
 
 	spin_lock_irqsave(&tdev->lock, flags);
 
@@ -185,14 +226,31 @@ static ssize_t mbox_test_message_read(struct file *filp, char __user *userbuf,
 	spin_unlock_irqrestore(&tdev->lock, flags);
 
 	ret = simple_read_from_buffer(userbuf, count, ppos, touser, MBOX_HEXDUMP_MAX_LEN);
-out:
+waitq_err:
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&tdev->waitq, &wait);
+kfree_err:
 	kfree(touser);
 	return ret;
 }
 
+static unsigned int
+mbox_test_message_poll(struct file *filp, struct poll_table_struct *wait)
+{
+	struct mbox_test_device *tdev = filp->private_data;
+
+	poll_wait(filp, &tdev->waitq, wait);
+
+	if (mbox_test_message_data_ready(tdev))
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
 static const struct file_operations mbox_test_message_ops = {
 	.write	= mbox_test_message_write,
 	.read	= mbox_test_message_read,
+	.fasync	= mbox_test_message_fasync,
+	.poll	= mbox_test_message_poll,
 	.open	= simple_open,
 	.llseek	= generic_file_llseek,
 };
@@ -234,6 +292,10 @@ static void mbox_test_receive_message(struct mbox_client *client, void *message)
 		memcpy(tdev->rx_buffer, message, MBOX_MAX_MSG_LEN);
 	}
 	spin_unlock_irqrestore(&tdev->lock, flags);
+
+	wake_up_interruptible(&tdev->waitq);
+
+	kill_fasync(&tdev->async_queue, SIGIO, POLL_IN);
 }
 
 static void mbox_test_prepare_message(struct mbox_client *client, void *message)
@@ -290,6 +352,7 @@ static int mbox_test_probe(struct platform_device *pdev)
 {
 	struct mbox_test_device *tdev;
 	struct resource *res;
+	resource_size_t size;
 	int ret;
 
 	tdev = devm_kzalloc(&pdev->dev, sizeof(*tdev), GFP_KERNEL);
@@ -298,14 +361,21 @@ static int mbox_test_probe(struct platform_device *pdev)
 
 	/* It's okay for MMIO to be NULL */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	size = resource_size(res);
 	tdev->tx_mmio = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(tdev->tx_mmio))
+	if (PTR_ERR(tdev->tx_mmio) == -EBUSY)
+		/* if reserved area in SRAM, try just ioremap */
+		tdev->tx_mmio = devm_ioremap(&pdev->dev, res->start, size);
+	else if (IS_ERR(tdev->tx_mmio))
 		tdev->tx_mmio = NULL;
 
 	/* If specified, second reg entry is Rx MMIO */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	size = resource_size(res);
 	tdev->rx_mmio = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(tdev->rx_mmio))
+	if (PTR_ERR(tdev->rx_mmio) == -EBUSY)
+		tdev->rx_mmio = devm_ioremap(&pdev->dev, res->start, size);
+	else if (IS_ERR(tdev->rx_mmio))
 		tdev->rx_mmio = tdev->tx_mmio;
 
 	tdev->tx_channel = mbox_test_request_channel(pdev, "tx");
@@ -334,6 +404,7 @@ static int mbox_test_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	init_waitqueue_head(&tdev->waitq);
 	dev_info(&pdev->dev, "Successfully registered\n");
 
 	return 0;
@@ -357,6 +428,7 @@ static const struct of_device_id mbox_test_match[] = {
 	{ .compatible = "mailbox-test" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, mbox_test_match);
 
 static struct platform_driver mbox_test_driver = {
 	.driver = {
diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index 4a36632..4671f8a 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -87,8 +87,7 @@ static void msg_submit(struct mbox_chan *chan)
 
 	if (!err && (chan->txdone_method & TXDONE_BY_POLL))
 		/* kick start the timer immediately to avoid delays */
-		hrtimer_start(&chan->mbox->poll_hrt, ktime_set(0, 0),
-			      HRTIMER_MODE_REL);
+		hrtimer_start(&chan->mbox->poll_hrt, 0, HRTIMER_MODE_REL);
 }
 
 static void tx_tick(struct mbox_chan *chan, int r)
diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
index 1f32688..dd9ecd35 100644
--- a/drivers/mailbox/pcc.c
+++ b/drivers/mailbox/pcc.c
@@ -447,7 +447,6 @@ static int pcc_parse_subspace_irq(int id,
  */
 static int __init acpi_pcc_probe(void)
 {
-	acpi_size pcct_tbl_header_size;
 	struct acpi_table_header *pcct_tbl;
 	struct acpi_subtable_header *pcct_entry;
 	struct acpi_table_pcct *acpi_pcct_tbl;
@@ -456,9 +455,7 @@ static int __init acpi_pcc_probe(void)
 	acpi_status status = AE_OK;
 
 	/* Search for PCCT */
-	status = acpi_get_table_with_size(ACPI_SIG_PCCT, 0,
-			&pcct_tbl,
-			&pcct_tbl_header_size);
+	status = acpi_get_table(ACPI_SIG_PCCT, 0, &pcct_tbl);
 
 	if (ACPI_FAILURE(status) || !pcct_tbl) {
 		pr_warn("PCCT header not found.\n");
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 6b420a5..c3ea03c 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -425,7 +425,7 @@ struct cache {
 	 * until a gc finishes - otherwise we could pointlessly burn a ton of
 	 * cpu
 	 */
-	unsigned		invalidate_needs_gc:1;
+	unsigned		invalidate_needs_gc;
 
 	bool			discard; /* Get rid of? */
 
@@ -593,8 +593,8 @@ struct cache_set {
 
 	/* Counts how many sectors bio_insert has added to the cache */
 	atomic_t		sectors_to_gc;
+	wait_queue_head_t	gc_wait;
 
-	wait_queue_head_t	moving_gc_wait;
 	struct keybuf		moving_gc_keys;
 	/* Number of moving GC bios in flight */
 	struct semaphore	moving_in_flight;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 6fdd8e2..a43eedd 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1757,32 +1757,34 @@ static void bch_btree_gc(struct cache_set *c)
 	bch_moving_gc(c);
 }
 
-static int bch_gc_thread(void *arg)
+static bool gc_should_run(struct cache_set *c)
 {
-	struct cache_set *c = arg;
 	struct cache *ca;
 	unsigned i;
 
-	while (1) {
-again:
-		bch_btree_gc(c);
+	for_each_cache(ca, c, i)
+		if (ca->invalidate_needs_gc)
+			return true;
 
-		set_current_state(TASK_INTERRUPTIBLE);
+	if (atomic_read(&c->sectors_to_gc) < 0)
+		return true;
+
+	return false;
+}
+
+static int bch_gc_thread(void *arg)
+{
+	struct cache_set *c = arg;
+
+	while (1) {
+		wait_event_interruptible(c->gc_wait,
+			   kthread_should_stop() || gc_should_run(c));
+
 		if (kthread_should_stop())
 			break;
 
-		mutex_lock(&c->bucket_lock);
-
-		for_each_cache(ca, c, i)
-			if (ca->invalidate_needs_gc) {
-				mutex_unlock(&c->bucket_lock);
-				set_current_state(TASK_RUNNING);
-				goto again;
-			}
-
-		mutex_unlock(&c->bucket_lock);
-
-		schedule();
+		set_gc_sectors(c);
+		bch_btree_gc(c);
 	}
 
 	return 0;
@@ -1790,11 +1792,10 @@ static int bch_gc_thread(void *arg)
 
 int bch_gc_thread_start(struct cache_set *c)
 {
-	c->gc_thread = kthread_create(bch_gc_thread, c, "bcache_gc");
+	c->gc_thread = kthread_run(bch_gc_thread, c, "bcache_gc");
 	if (IS_ERR(c->gc_thread))
 		return PTR_ERR(c->gc_thread);
 
-	set_task_state(c->gc_thread, TASK_INTERRUPTIBLE);
 	return 0;
 }
 
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index 5c391fa..9b80417 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -260,8 +260,7 @@ void bch_initial_mark_key(struct cache_set *, int, struct bkey *);
 
 static inline void wake_up_gc(struct cache_set *c)
 {
-	if (c->gc_thread)
-		wake_up_process(c->gc_thread);
+	wake_up(&c->gc_wait);
 }
 
 #define MAP_DONE	0
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index f49c541..76d2087 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -196,10 +196,8 @@ static void bch_data_insert_start(struct closure *cl)
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
-	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) {
-		set_gc_sectors(op->c);
+	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0)
 		wake_up_gc(op->c);
-	}
 
 	if (op->bypass)
 		return bch_data_invalidate(cl);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2fb5bfe..3a19cbc 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -58,6 +58,7 @@ static wait_queue_head_t unregister_wait;
 struct workqueue_struct *bcache_wq;
 
 #define BTREE_MAX_PAGES		(256 * 1024 / PAGE_SIZE)
+#define BCACHE_MINORS		16 /* partition support */
 
 /* Superblock */
 
@@ -783,8 +784,10 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	if (minor < 0)
 		return minor;
 
+	minor *= BCACHE_MINORS;
+
 	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
-	    !(d->disk = alloc_disk(1))) {
+	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
 		ida_simple_remove(&bcache_minor, minor);
 		return -ENOMEM;
 	}
@@ -1489,6 +1492,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	mutex_init(&c->bucket_lock);
 	init_waitqueue_head(&c->btree_cache_wait);
 	init_waitqueue_head(&c->bucket_wait);
+	init_waitqueue_head(&c->gc_wait);
 	sema_init(&c->uuid_write_mutex, 1);
 
 	spin_lock_init(&c->btree_gc_time.lock);
@@ -1548,6 +1552,7 @@ static void run_cache_set(struct cache_set *c)
 
 	for_each_cache(ca, c, i)
 		c->nbuckets += ca->sb.nbuckets;
+	set_gc_sectors(c);
 
 	if (CACHE_SYNC(&c->sb)) {
 		LIST_HEAD(journal);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index c72a770..a5a9b17 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -17,7 +17,7 @@
 #include <linux/hdreg.h>
 #include <linux/compat.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define DM_MSG_PREFIX "ioctl"
 #define DM_DRIVER_EMAIL "dm-devel@redhat.com"
diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c
index efe55a3..0c16bb2 100644
--- a/drivers/media/dvb-core/dmxdev.c
+++ b/drivers/media/dvb-core/dmxdev.c
@@ -30,7 +30,7 @@
 #include <linux/poll.h>
 #include <linux/ioctl.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "dmxdev.h"
 
 static int debug;
@@ -562,7 +562,7 @@ static int dvb_dmxdev_start_feed(struct dmxdev *dmxdev,
 				 struct dmxdev_filter *filter,
 				 struct dmxdev_feed *feed)
 {
-	ktime_t timeout = ktime_set(0, 0);
+	ktime_t timeout = 0;
 	struct dmx_pes_filter_params *para = &filter->params.pes;
 	dmx_output_t otype;
 	int ret;
diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c
index 3ad0b2c..bbbff72 100644
--- a/drivers/media/dvb-core/dvb_demux.c
+++ b/drivers/media/dvb-core/dvb_demux.c
@@ -31,7 +31,7 @@
 #include <linux/poll.h>
 #include <linux/string.h>
 #include <linux/crc32.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/div64.h>
 
 #include "dvb_demux.h"
diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c
index dfc03a9..bc5e8cf 100644
--- a/drivers/media/dvb-core/dvb_net.c
+++ b/drivers/media/dvb-core/dvb_net.c
@@ -62,7 +62,7 @@
 #include <linux/etherdevice.h>
 #include <linux/dvb/net.h>
 #include <linux/uio.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/crc32.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
diff --git a/drivers/media/dvb-core/dvb_ringbuffer.c b/drivers/media/dvb-core/dvb_ringbuffer.c
index 7df7fb3..5c4b5a1 100644
--- a/drivers/media/dvb-core/dvb_ringbuffer.c
+++ b/drivers/media/dvb-core/dvb_ringbuffer.c
@@ -31,7 +31,7 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "dvb_ringbuffer.h"
 
diff --git a/drivers/media/i2c/adv7170.c b/drivers/media/i2c/adv7170.c
index 05f1dc6..fc9ec0f 100644
--- a/drivers/media/i2c/adv7170.c
+++ b/drivers/media/i2c/adv7170.c
@@ -32,7 +32,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/adv7175.c b/drivers/media/i2c/adv7175.c
index f554809..72139bd 100644
--- a/drivers/media/i2c/adv7175.c
+++ b/drivers/media/i2c/adv7175.c
@@ -28,7 +28,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/bt856.c b/drivers/media/i2c/bt856.c
index 4817659..54c6278 100644
--- a/drivers/media/i2c/bt856.c
+++ b/drivers/media/i2c/bt856.c
@@ -32,7 +32,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/bt866.c b/drivers/media/i2c/bt866.c
index bbec70c..0d3f46a 100644
--- a/drivers/media/i2c/bt866.c
+++ b/drivers/media/i2c/bt866.c
@@ -32,7 +32,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/cs53l32a.c b/drivers/media/i2c/cs53l32a.c
index e4b3cf4..59c1a98 100644
--- a/drivers/media/i2c/cs53l32a.c
+++ b/drivers/media/i2c/cs53l32a.c
@@ -24,7 +24,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/m52790.c b/drivers/media/i2c/m52790.c
index 81171d8..89c28c3 100644
--- a/drivers/media/i2c/m52790.c
+++ b/drivers/media/i2c/m52790.c
@@ -24,7 +24,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/i2c/m52790.h>
diff --git a/drivers/media/i2c/saa6588.c b/drivers/media/i2c/saa6588.c
index 89e458c..0064023 100644
--- a/drivers/media/i2c/saa6588.c
+++ b/drivers/media/i2c/saa6588.c
@@ -29,7 +29,7 @@
 #include <linux/slab.h>
 #include <linux/poll.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <media/i2c/saa6588.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/saa7110.c b/drivers/media/i2c/saa7110.c
index 6f49886..ad456ce 100644
--- a/drivers/media/i2c/saa7110.c
+++ b/drivers/media/i2c/saa7110.c
@@ -31,7 +31,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/saa7185.c b/drivers/media/i2c/saa7185.c
index eecad2d..119050e 100644
--- a/drivers/media/i2c/saa7185.c
+++ b/drivers/media/i2c/saa7185.c
@@ -28,7 +28,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/tlv320aic23b.c b/drivers/media/i2c/tlv320aic23b.c
index 2e06c06..cc6104d 100644
--- a/drivers/media/i2c/tlv320aic23b.c
+++ b/drivers/media/i2c/tlv320aic23b.c
@@ -27,7 +27,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/vp27smpx.c b/drivers/media/i2c/vp27smpx.c
index d6c23bd..ef0d8b8 100644
--- a/drivers/media/i2c/vp27smpx.c
+++ b/drivers/media/i2c/vp27smpx.c
@@ -25,7 +25,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/vpx3220.c b/drivers/media/i2c/vpx3220.c
index 90b693f..ce9f093 100644
--- a/drivers/media/i2c/vpx3220.c
+++ b/drivers/media/i2c/vpx3220.c
@@ -23,7 +23,7 @@
 #include <linux/delay.h>
 #include <linux/types.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/wm8739.c b/drivers/media/i2c/wm8739.c
index f086e5e..c885def 100644
--- a/drivers/media/i2c/wm8739.c
+++ b/drivers/media/i2c/wm8739.c
@@ -25,7 +25,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/i2c/wm8775.c b/drivers/media/i2c/wm8775.c
index 5581f4d..45039d7 100644
--- a/drivers/media/i2c/wm8775.c
+++ b/drivers/media/i2c/wm8775.c
@@ -29,7 +29,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/i2c.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/pci/cx88/cx88-input.c b/drivers/media/pci/cx88/cx88-input.c
index dcfea35..c7b3cb4 100644
--- a/drivers/media/pci/cx88/cx88-input.c
+++ b/drivers/media/pci/cx88/cx88-input.c
@@ -178,8 +178,7 @@ static enum hrtimer_restart cx88_ir_work(struct hrtimer *timer)
 	struct cx88_IR *ir = container_of(timer, struct cx88_IR, timer);
 
 	cx88_ir_handle_key(ir);
-	missed = hrtimer_forward_now(&ir->timer,
-				     ktime_set(0, ir->polling * 1000000));
+	missed = hrtimer_forward_now(&ir->timer, ir->polling * 1000000);
 	if (missed > 1)
 		ir_dprintk("Missed ticks %ld\n", missed - 1);
 
@@ -199,8 +198,7 @@ static int __cx88_ir_start(void *priv)
 	if (ir->polling) {
 		hrtimer_init(&ir->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		ir->timer.function = cx88_ir_work;
-		hrtimer_start(&ir->timer,
-			      ktime_set(0, ir->polling * 1000000),
+		hrtimer_start(&ir->timer, ir->polling * 1000000,
 			      HRTIMER_MODE_REL);
 	}
 	if (ir->sampling) {
diff --git a/drivers/media/pci/ivtv/ivtv-driver.h b/drivers/media/pci/ivtv/ivtv-driver.h
index 10cba305..6b09a95 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.h
+++ b/drivers/media/pci/ivtv/ivtv-driver.h
@@ -53,7 +53,7 @@
 #include <linux/kthread.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 #include <linux/dvb/video.h>
diff --git a/drivers/media/pci/meye/meye.c b/drivers/media/pci/meye/meye.c
index e825bc9..24fba63 100644
--- a/drivers/media/pci/meye/meye.c
+++ b/drivers/media/pci/meye/meye.c
@@ -37,7 +37,7 @@
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-fh.h>
 #include <media/v4l2-event.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
diff --git a/drivers/media/pci/pt3/pt3.c b/drivers/media/pci/pt3/pt3.c
index 7fb649e..77f4d15 100644
--- a/drivers/media/pci/pt3/pt3.c
+++ b/drivers/media/pci/pt3/pt3.c
@@ -463,7 +463,7 @@ static int pt3_fetch_thread(void *data)
 
 		pt3_proc_dma(adap);
 
-		delay = ktime_set(0, PT3_FETCH_DELAY * NSEC_PER_MSEC);
+		delay = PT3_FETCH_DELAY * NSEC_PER_MSEC;
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		freezable_schedule_hrtimeout_range(&delay,
 					PT3_FETCH_DELAY_DELTA * NSEC_PER_MSEC,
diff --git a/drivers/media/pci/zoran/videocodec.c b/drivers/media/pci/zoran/videocodec.c
index 13a3c07..3c3cbce 100644
--- a/drivers/media/pci/zoran/videocodec.c
+++ b/drivers/media/pci/zoran/videocodec.c
@@ -40,7 +40,7 @@
 #ifdef CONFIG_PROC_FS
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #endif
 
 #include "videocodec.h"
diff --git a/drivers/media/pci/zoran/zoran_driver.c b/drivers/media/pci/zoran/zoran_driver.c
index 2170e17..94b9b61 100644
--- a/drivers/media/pci/zoran/zoran_driver.c
+++ b/drivers/media/pci/zoran/zoran_driver.c
@@ -66,7 +66,7 @@
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/proc_fs.h>
 
 #include <linux/mutex.h>
diff --git a/drivers/media/platform/arv.c b/drivers/media/platform/arv.c
index 03c5098..8fe59bf 100644
--- a/drivers/media/platform/arv.c
+++ b/drivers/media/platform/arv.c
@@ -34,7 +34,7 @@
 #include <media/v4l2-fh.h>
 #include <linux/mutex.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/m32r.h>
 #include <asm/io.h>
 #include <asm/dma.h>
diff --git a/drivers/media/rc/ir-rx51.c b/drivers/media/rc/ir-rx51.c
index 82fb6f2..e6efa8c 100644
--- a/drivers/media/rc/ir-rx51.c
+++ b/drivers/media/rc/ir-rx51.c
@@ -109,7 +109,7 @@ static enum hrtimer_restart lirc_rx51_timer_cb(struct hrtimer *timer)
 
 		now = timer->base->get_time();
 
-	} while (hrtimer_get_expires_tv64(timer) < now.tv64);
+	} while (hrtimer_get_expires_tv64(timer) < now);
 
 	return HRTIMER_RESTART;
 end:
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-ioread.c b/drivers/media/usb/pvrusb2/pvrusb2-ioread.c
index 70b8a05..3c7ca2c 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-ioread.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-ioread.c
@@ -25,7 +25,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define BUFFER_COUNT 32
 #define BUFFER_SIZE PAGE_ALIGN(0x4000)
diff --git a/drivers/media/usb/pwc/pwc-ctrl.c b/drivers/media/usb/pwc/pwc-ctrl.c
index 3a16185..655cef3 100644
--- a/drivers/media/usb/pwc/pwc-ctrl.c
+++ b/drivers/media/usb/pwc/pwc-ctrl.c
@@ -39,7 +39,7 @@
 /* Control functions for the cam; brightness, contrast, video mode, etc. */
 
 #ifdef __KERNEL__
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #endif
 #include <asm/errno.h>
 
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 57cfe26a..a5ea1f5 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -54,7 +54,7 @@
 #if defined(CONFIG_SPI)
 #include <linux/spi/spi.h>
 #endif
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/div64.h>
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 8be561a..fa2124c 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -25,7 +25,7 @@
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index 02b5f69..7b3b413 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -58,7 +58,7 @@
 #include <linux/compat.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/message/fusion/mptlan.h b/drivers/message/fusion/mptlan.h
index 69e9d54..8946e19 100644
--- a/drivers/message/fusion/mptlan.h
+++ b/drivers/message/fusion/mptlan.h
@@ -70,7 +70,7 @@
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
     /* Override mptbase.h by pre-defining these! */
diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c
index 520f584..e05c324 100644
--- a/drivers/misc/ibmasm/ibmasmfs.c
+++ b/drivers/misc/ibmasm/ibmasmfs.c
@@ -76,7 +76,7 @@
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include "ibmasm.h"
 #include "remote.h"
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index bab3f07..cb1698f 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -43,7 +43,7 @@
 #include <linux/mmc/mmc.h>
 #include <linux/mmc/sd.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "queue.h"
 #include "block.h"
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 543eadd..1076b9d 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -496,8 +496,7 @@ static int __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq)
  * Returns enum mmc_blk_status after checking errors.
  */
 static enum mmc_blk_status mmc_wait_for_data_req_done(struct mmc_host *host,
-				      struct mmc_request *mrq,
-				      struct mmc_async_req *next_req)
+						      struct mmc_request *mrq)
 {
 	struct mmc_command *cmd;
 	struct mmc_context_info *context_info = &host->context_info;
@@ -507,7 +506,7 @@ static enum mmc_blk_status mmc_wait_for_data_req_done(struct mmc_host *host,
 		wait_event_interruptible(context_info->wait,
 				(context_info->is_done_rcv ||
 				 context_info->is_new_req));
-		context_info->is_waiting_last_req = false;
+
 		if (context_info->is_done_rcv) {
 			context_info->is_done_rcv = false;
 			cmd = mrq->cmd;
@@ -527,10 +526,9 @@ static enum mmc_blk_status mmc_wait_for_data_req_done(struct mmc_host *host,
 				__mmc_start_request(host, mrq);
 				continue; /* wait for done/new event again */
 			}
-		} else if (context_info->is_new_req) {
-			if (!next_req)
-				return MMC_BLK_NEW_REQUEST;
 		}
+
+		return MMC_BLK_NEW_REQUEST;
 	}
 	mmc_retune_release(host);
 	return status;
@@ -660,7 +658,7 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host,
 		mmc_pre_req(host, areq->mrq);
 
 	if (host->areq) {
-		status = mmc_wait_for_data_req_done(host, host->areq->mrq, areq);
+		status = mmc_wait_for_data_req_done(host, host->areq->mrq);
 		if (status == MMC_BLK_NEW_REQUEST) {
 			if (ret_stat)
 				*ret_stat = status;
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index deb90c2..a614f37 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -223,6 +223,7 @@ static int mmc_decode_scr(struct mmc_card *card)
 static int mmc_read_ssr(struct mmc_card *card)
 {
 	unsigned int au, es, et, eo;
+	u32 *raw_ssr;
 	int i;
 
 	if (!(card->csd.cmdclass & CCC_APP_SPEC)) {
@@ -231,14 +232,21 @@ static int mmc_read_ssr(struct mmc_card *card)
 		return 0;
 	}
 
-	if (mmc_app_sd_status(card, card->raw_ssr)) {
+	raw_ssr = kmalloc(sizeof(card->raw_ssr), GFP_KERNEL);
+	if (!raw_ssr)
+		return -ENOMEM;
+
+	if (mmc_app_sd_status(card, raw_ssr)) {
 		pr_warn("%s: problem reading SD Status register\n",
 			mmc_hostname(card->host));
+		kfree(raw_ssr);
 		return 0;
 	}
 
 	for (i = 0; i < 16; i++)
-		card->raw_ssr[i] = be32_to_cpu(card->raw_ssr[i]);
+		card->raw_ssr[i] = be32_to_cpu(raw_ssr[i]);
+
+	kfree(raw_ssr);
 
 	/*
 	 * UNSTUFF_BITS only works with four u32s so we have to offset the
diff --git a/drivers/mmc/host/android-goldfish.c b/drivers/mmc/host/android-goldfish.c
index dca5518..590a8a4 100644
--- a/drivers/mmc/host/android-goldfish.c
+++ b/drivers/mmc/host/android-goldfish.c
@@ -49,7 +49,7 @@
 
 #include <asm/types.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define DRIVER_NAME "goldfish_mmc"
 
diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c
index 1501cfd..4b0ecb9 100644
--- a/drivers/mmc/host/sdhci-cadence.c
+++ b/drivers/mmc/host/sdhci-cadence.c
@@ -262,6 +262,7 @@ static int sdhci_cdns_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id sdhci_cdns_match[] = {
+	{ .compatible = "socionext,uniphier-sd4hc" },
 	{ .compatible = "cdns,sd4hc" },
 	{ /* sentinel */ }
 };
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 111991e..2390980 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1576,6 +1576,9 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	unsigned long flags;
 	u8 ctrl;
 
+	if (ios->power_mode == MMC_POWER_UNDEFINED)
+		return;
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	if (host->flags & SDHCI_DEVICE_DEAD) {
@@ -2938,23 +2941,25 @@ int sdhci_runtime_resume_host(struct sdhci_host *host)
 
 	sdhci_init(host, 0);
 
-	/* Force clock and power re-program */
-	host->pwr = 0;
-	host->clock = 0;
-	mmc->ops->start_signal_voltage_switch(mmc, &mmc->ios);
-	mmc->ops->set_ios(mmc, &mmc->ios);
+	if (mmc->ios.power_mode != MMC_POWER_UNDEFINED) {
+		/* Force clock and power re-program */
+		host->pwr = 0;
+		host->clock = 0;
+		mmc->ops->start_signal_voltage_switch(mmc, &mmc->ios);
+		mmc->ops->set_ios(mmc, &mmc->ios);
 
-	if ((host_flags & SDHCI_PV_ENABLED) &&
-		!(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN)) {
-		spin_lock_irqsave(&host->lock, flags);
-		sdhci_enable_preset_value(host, true);
-		spin_unlock_irqrestore(&host->lock, flags);
+		if ((host_flags & SDHCI_PV_ENABLED) &&
+		    !(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN)) {
+			spin_lock_irqsave(&host->lock, flags);
+			sdhci_enable_preset_value(host, true);
+			spin_unlock_irqrestore(&host->lock, flags);
+		}
+
+		if ((mmc->caps2 & MMC_CAP2_HS400_ES) &&
+		    mmc->ops->hs400_enhanced_strobe)
+			mmc->ops->hs400_enhanced_strobe(mmc, &mmc->ios);
 	}
 
-	if ((mmc->caps2 & MMC_CAP2_HS400_ES) &&
-	    mmc->ops->hs400_enhanced_strobe)
-		mmc->ops->hs400_enhanced_strobe(mmc, &mmc->ios);
-
 	spin_lock_irqsave(&host->lock, flags);
 
 	host->runtime_suspended = false;
diff --git a/drivers/mtd/devices/pmc551.c b/drivers/mtd/devices/pmc551.c
index 220f920..cadea06 100644
--- a/drivers/mtd/devices/pmc551.c
+++ b/drivers/mtd/devices/pmc551.c
@@ -82,7 +82,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/ptrace.h>
diff --git a/drivers/mtd/devices/slram.c b/drivers/mtd/devices/slram.c
index a70eb83..8087c36 100644
--- a/drivers/mtd/devices/slram.c
+++ b/drivers/mtd/devices/slram.c
@@ -30,7 +30,7 @@
 
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c
index 9fb3b0d..664d206 100644
--- a/drivers/mtd/ftl.c
+++ b/drivers/mtd/ftl.c
@@ -70,7 +70,7 @@
 #include <linux/hdreg.h>
 #include <linux/vmalloc.h>
 #include <linux/blkpg.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/mtd/ftl.h>
 
diff --git a/drivers/mtd/inftlcore.c b/drivers/mtd/inftlcore.c
index b66b541..8db740d 100644
--- a/drivers/mtd/inftlcore.c
+++ b/drivers/mtd/inftlcore.c
@@ -34,7 +34,7 @@
 #include <linux/mtd/nftl.h>
 #include <linux/mtd/inftl.h>
 #include <linux/mtd/nand.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/errno.h>
 #include <asm/io.h>
 
diff --git a/drivers/mtd/inftlmount.c b/drivers/mtd/inftlmount.c
index 1388c8d..8d6bb189 100644
--- a/drivers/mtd/inftlmount.c
+++ b/drivers/mtd/inftlmount.c
@@ -27,7 +27,7 @@
 #include <linux/module.h>
 #include <asm/errno.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/mtd/mtd.h>
diff --git a/drivers/mtd/maps/sun_uflash.c b/drivers/mtd/maps/sun_uflash.c
index d459aca..414956e 100644
--- a/drivers/mtd/maps/sun_uflash.c
+++ b/drivers/mtd/maps/sun_uflash.c
@@ -16,7 +16,7 @@
 #include <linux/of_device.h>
 #include <linux/slab.h>
 #include <asm/prom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #include <linux/mtd/mtd.h>
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 8d58acf..df8a5ef 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -31,7 +31,7 @@
 #include <linux/spinlock.h>
 #include <linux/hdreg.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "mtdcore.h"
 
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 2a47a3f..ce5ccc5 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -37,7 +37,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/map.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "mtdcore.h"
 
diff --git a/drivers/mtd/nftlcore.c b/drivers/mtd/nftlcore.c
index 46f27de..e211613 100644
--- a/drivers/mtd/nftlcore.c
+++ b/drivers/mtd/nftlcore.c
@@ -25,7 +25,7 @@
 #include <linux/module.h>
 #include <asm/errno.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/init.h>
diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
index 31f89f1..b8c2933 100644
--- a/drivers/net/appletalk/ipddp.c
+++ b/drivers/net/appletalk/ipddp.c
@@ -33,7 +33,7 @@
 #include <linux/if_arp.h>
 #include <linux/slab.h>
 #include <net/route.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "ipddp.h"		/* Our stuff */
 
diff --git a/drivers/net/can/softing/softing_fw.c b/drivers/net/can/softing/softing_fw.c
index 52fe507..4063215 100644
--- a/drivers/net/can/softing/softing_fw.c
+++ b/drivers/net/can/softing/softing_fw.c
@@ -390,7 +390,7 @@ static void softing_initialize_timestamp(struct softing *card)
 	ovf = 0x100000000ULL * 16;
 	do_div(ovf, card->pdat->freq ?: 16);
 
-	card->ts_overflow = ktime_add_us(ktime_set(0, 0), ovf);
+	card->ts_overflow = ktime_add_us(0, ovf);
 }
 
 ktime_t softing_raw2ktime(struct softing *card, u32 raw)
@@ -647,7 +647,7 @@ int softing_startstop(struct net_device *dev, int up)
 		open_candev(netdev);
 		if (dev != netdev) {
 			/* notify other busses on the restart */
-			softing_netdev_rx(netdev, &msg, ktime_set(0, 0));
+			softing_netdev_rx(netdev, &msg, 0);
 			++priv->can.can_stats.restarts;
 		}
 		netif_wake_queue(netdev);
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index 7621f91..5f64dee 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -192,7 +192,7 @@ static int softing_handle_1(struct softing *card)
 				/* a dead bus has no overflows */
 				continue;
 			++netdev->stats.rx_over_errors;
-			softing_netdev_rx(netdev, &msg, ktime_set(0, 0));
+			softing_netdev_rx(netdev, &msg, 0);
 		}
 		/* prepare for other use */
 		memset(&msg, 0, sizeof(msg));
diff --git a/drivers/net/eql.c b/drivers/net/eql.c
index a10ad74..fe13bfe 100644
--- a/drivers/net/eql.c
+++ b/drivers/net/eql.c
@@ -127,7 +127,7 @@
 #include <linux/if_eql.h>
 #include <linux/pkt_sched.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int eql_open(struct net_device *dev);
 static int eql_close(struct net_device *dev);
diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index a753378..c7f9f2c 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -88,7 +88,7 @@
 #include <linux/eisa.h>
 #include <linux/bitops.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index be5b801..e7b1fa5 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -72,7 +72,7 @@ static int max_interrupt_work = 20;
 #include <linux/ethtool.h>
 #include <linux/bitops.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/dma.h>
 
diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c
index 9359a37..47c844c 100644
--- a/drivers/net/ethernet/3com/3c574_cs.c
+++ b/drivers/net/ethernet/3com/3c574_cs.c
@@ -92,7 +92,7 @@ earlier 3Com products.
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 /*====================================================================*/
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index b3560a3..40196f4 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -92,7 +92,7 @@ static int vortex_debug = 1;
 #include <linux/gfp.h>
 #include <asm/irq.h>			/* For nr_irqs only. */
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Kernel compatibility defines, some common to David Hinds' PCMCIA package.
    This is only in the support-all-kernels source code. */
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c
index a0cacbe..9fe3990 100644
--- a/drivers/net/ethernet/3com/typhoon.c
+++ b/drivers/net/ethernet/3com/typhoon.c
@@ -119,7 +119,7 @@ static const int multicast_filter_limit = 32;
 #include <linux/bitops.h>
 #include <asm/processor.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/in6.h>
 #include <linux/dma-mapping.h>
 #include <linux/firmware.h>
diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index 1d84a05..3da1fc5 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -46,7 +46,7 @@
 
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define AXNET_CMD	0x00
 #define AXNET_DATAPORT	0x10	/* NatSemi-defined port window offset. */
diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c
index 0735530..1bdea74 100644
--- a/drivers/net/ethernet/8390/ne2k-pci.c
+++ b/drivers/net/ethernet/8390/ne2k-pci.c
@@ -54,7 +54,7 @@ static int options[MAX_UNITS];
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "8390.h"
 
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 63079a6..bd0a2a1 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -49,7 +49,7 @@
 
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define PCNET_CMD	0x00
 #define PCNET_DATAPORT	0x10	/* NatSemi-defined port window offset. */
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 6e16e44..e4c28fe 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -166,7 +166,6 @@
 source "drivers/net/ethernet/silan/Kconfig"
 source "drivers/net/ethernet/sis/Kconfig"
 source "drivers/net/ethernet/sfc/Kconfig"
-source "drivers/net/ethernet/sfc/falcon/Kconfig"
 source "drivers/net/ethernet/sgi/Kconfig"
 source "drivers/net/ethernet/smsc/Kconfig"
 source "drivers/net/ethernet/stmicro/Kconfig"
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 3aaad33..c12d261 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -45,7 +45,7 @@
 #include <linux/mm.h>
 #include <linux/firmware.h>
 #include <asm/processor.h>		/* Processor type for cache alignment. */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 /*
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 16f0c70..a1a52eb 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -80,7 +80,7 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 #define DRV_NAME "acenic"
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 11cf1e3..9595f1b 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -87,7 +87,7 @@ Revision History:
 
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 #define AMD8111E_VLAN_TAG_USED 1
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index 113a3b3..b556c92 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -151,7 +151,7 @@ Include Files
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 /* ----------------------------------------------------------------------------
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
index b03e4f5..a533a6c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
@@ -122,7 +122,7 @@
 #include "xgbe.h"
 #include "xgbe-common.h"
 
-static cycle_t xgbe_cc_read(const struct cyclecounter *cc)
+static u64 xgbe_cc_read(const struct cyclecounter *cc)
 {
 	struct xgbe_prv_data *pdata = container_of(cc,
 						   struct xgbe_prv_data,
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 1df3048..48707ed 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -32,7 +32,7 @@
 #include <linux/slab.h>
 #include <linux/phy.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 688617a..d8d06fd 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -15223,7 +15223,7 @@ void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb)
 }
 
 /* Read the PHC */
-static cycle_t bnx2x_cyclecounter_read(const struct cyclecounter *cc)
+static u64 bnx2x_cyclecounter_read(const struct cyclecounter *cc)
 {
 	struct bnx2x *bp = container_of(cc, struct bnx2x, cyclecounter);
 	int port = BP_PORT(bp);
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 16e12c4..21f80f5 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1469,6 +1469,12 @@ static int octeon_mgmt_probe(struct platform_device *pdev)
 	p->agl = (u64)devm_ioremap(&pdev->dev, p->agl_phys, p->agl_size);
 	p->agl_prt_ctl = (u64)devm_ioremap(&pdev->dev, p->agl_prt_ctl_phys,
 					   p->agl_prt_ctl_size);
+	if (!p->mix || !p->agl || !p->agl_prt_ctl) {
+		dev_err(&pdev->dev, "failed to map I/O memory\n");
+		result = -ENOMEM;
+		goto err;
+	}
+
 	spin_lock_init(&p->lock);
 
 	skb_queue_head_init(&p->tx_list);
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 3a05f90..d8aff7a 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -44,7 +44,7 @@
 #include <linux/mii.h>
 #include <linux/sockios.h>
 #include <linux/dma-mapping.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "cpl5_cmd.h"
 #include "regs.h"
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 7b2224a..d764916 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -50,7 +50,7 @@
 #include <linux/stringify.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "common.h"
 #include "cxgb3_ioctl.h"
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 66c37fa..6f95187 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -63,7 +63,7 @@
 #include <net/addrconf.h>
 #include <net/bonding.h>
 #include <net/addrconf.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/crash_dump.h>
 
 #include "cxgb4.h"
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index fba3b2a..a267173 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -76,6 +76,7 @@ enum {
 	CPL_PASS_ESTABLISH    = 0x41,
 	CPL_RX_DATA_DDP       = 0x42,
 	CPL_PASS_ACCEPT_REQ   = 0x44,
+	CPL_RX_ISCSI_CMP      = 0x45,
 	CPL_TRACE_PKT_T5      = 0x48,
 	CPL_RX_ISCSI_DDP      = 0x49,
 
@@ -934,6 +935,18 @@ struct cpl_iscsi_data {
 	__u8 status;
 };
 
+struct cpl_rx_iscsi_cmp {
+	union opcode_tid ot;
+	__be16 pdu_len_ddp;
+	__be16 len;
+	__be32 seq;
+	__be16 urg;
+	__u8 rsvd;
+	__u8 status;
+	__be32 ulp_crc;
+	__be32 ddpvld;
+};
+
 struct cpl_tx_data_iso {
 	__be32 op_to_scsi;
 	__u8   reserved1;
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index 90c573b..57c17e7 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -49,7 +49,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
 /* These identify the driver base version and may not be removed. */
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 51fda3a..df4a871 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -472,7 +472,7 @@
 #include <asm/dma.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #ifdef CONFIG_PPC_PMAC
 #include <asm/machdep.h>
 #endif /* CONFIG_PPC_PMAC */
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index df49949..07e10a4 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -90,7 +90,7 @@
 #include <asm/processor.h>
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 
 #ifdef CONFIG_TULIP_DM910X
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 5f13774..17e566a8 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -31,7 +31,7 @@
 #include <linux/mii.h>
 #include <linux/crc32.h>
 #include <asm/unaligned.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_SPARC
 #include <asm/prom.h>
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index e1c4133..f82ebe5 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -40,7 +40,7 @@
 #include <asm/processor.h>
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define uw32(reg, val)	iowrite32(val, ioaddr + (reg))
 #define ur32(reg)	ioread32(ioaddr + (reg))
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index feda96d..bc9bf88 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -129,7 +129,7 @@ static int full_duplex[MAX_UNITS] = {-1, -1, -1, -1, -1, -1, -1, -1};
 #include <linux/rtnetlink.h>
 #include <linux/crc32.h>
 #include <linux/bitops.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>		/* Processor type for cache alignment. */
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/drivers/net/ethernet/dec/tulip/xircom_cb.c b/drivers/net/ethernet/dec/tulip/xircom_cb.c
index 19e4ea1..a8de793 100644
--- a/drivers/net/ethernet/dec/tulip/xircom_cb.c
+++ b/drivers/net/ethernet/dec/tulip/xircom_cb.c
@@ -30,7 +30,7 @@
 #include <linux/delay.h>
 #include <linux/bitops.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #ifdef CONFIG_NET_POLL_CONTROLLER
 #include <asm/irq.h>
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 8f4f612..5d8ae53 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -31,7 +31,7 @@
 #include <linux/bitops.h>
 #include <asm/processor.h>	/* Processor type for cache alignment. */
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/time.h>
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index eab36ac..2e5b667 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -91,7 +91,7 @@ static char *media[MAX_UNITS];
 #include <linux/skbuff.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>		/* Processor type for cache alignment. */
 #include <asm/io.h>
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index 5765095..7bf78a0 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -253,7 +253,7 @@ static enum hrtimer_restart ec_bhf_timer_fun(struct hrtimer *timer)
 	if (!netif_running(priv->net_dev))
 		return HRTIMER_NORESTART;
 
-	hrtimer_forward_now(timer, ktime_set(0, polling_frequency));
+	hrtimer_forward_now(timer, polling_frequency);
 	return HRTIMER_RESTART;
 }
 
@@ -427,8 +427,7 @@ static int ec_bhf_open(struct net_device *net_dev)
 
 	hrtimer_init(&priv->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	priv->hrtimer.function = ec_bhf_timer_fun;
-	hrtimer_start(&priv->hrtimer, ktime_set(0, polling_frequency),
-		      HRTIMER_MODE_REL);
+	hrtimer_start(&priv->hrtimer, polling_frequency, HRTIMER_MODE_REL);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 6cfa63a..4c30c44 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -65,7 +65,7 @@
 /* Number of bytes of an RX frame that are copied to skb->data */
 #define BE_HDR_LEN		((u16) 64)
 /* allocate extra space to allow tunneling decapsulation without head reallocation */
-#define BE_RX_SKB_ALLOC_SIZE (BE_HDR_LEN + 64)
+#define BE_RX_SKB_ALLOC_SIZE	256
 
 #define BE_MAX_JUMBO_FRAME_SIZE	9018
 #define BE_MIN_MTU		256
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index 6967b28..9cb436c 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -88,7 +88,7 @@ static int full_duplex[MAX_UNITS] = { -1, -1, -1, -1, -1, -1, -1, -1 };
 
 #include <asm/processor.h>	/* Processor type for cache alignment. */
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 /* These identify the driver base version and may not be removed. */
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index f9e7446..6ebad3f 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -230,7 +230,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
  * cyclecounter structure used to construct a ns counter from the
  * arbitrary fixed point registers
  */
-static cycle_t fec_ptp_read(const struct cyclecounter *cc)
+static u64 fec_ptp_read(const struct cyclecounter *cc)
 {
 	struct fec_enet_private *fep =
 		container_of(cc, struct fec_enet_private, cc);
diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig
index 79b7c84..dc0850b 100644
--- a/drivers/net/ethernet/freescale/fman/Kconfig
+++ b/drivers/net/ethernet/freescale/fman/Kconfig
@@ -1,6 +1,6 @@
 config FSL_FMAN
 	tristate "FMan support"
-	depends on FSL_SOC || COMPILE_TEST
+	depends on FSL_SOC || ARCH_LAYERSCAPE || COMPILE_TEST
 	select GENERIC_ALLOCATOR
 	select PHYLIB
 	default n
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index dafd9e1..f60845f 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -1890,6 +1890,7 @@ static int fman_reset(struct fman *fman)
 
 		goto _return;
 	} else {
+#ifdef CONFIG_PPC
 		struct device_node *guts_node;
 		struct ccsr_guts __iomem *guts_regs;
 		u32 devdisr2, reg;
@@ -1921,6 +1922,7 @@ static int fman_reset(struct fman *fman)
 
 		/* Enable all MACs */
 		iowrite32be(reg, &guts_regs->devdisr2);
+#endif
 
 		/* Perform FMan reset */
 		iowrite32be(FPM_RSTC_FM_RESET, &fman->fpm_regs->fm_rstc);
@@ -1932,25 +1934,31 @@ static int fman_reset(struct fman *fman)
 		} while (((ioread32be(&fman->fpm_regs->fm_rstc)) &
 			 FPM_RSTC_FM_RESET) && --count);
 		if (count == 0) {
+#ifdef CONFIG_PPC
 			iounmap(guts_regs);
 			of_node_put(guts_node);
+#endif
 			err = -EBUSY;
 			goto _return;
 		}
+#ifdef CONFIG_PPC
 
 		/* Restore devdisr2 value */
 		iowrite32be(devdisr2, &guts_regs->devdisr2);
 
 		iounmap(guts_regs);
 		of_node_put(guts_node);
+#endif
 
 		goto _return;
 
+#ifdef CONFIG_PPC
 guts_regs:
 		of_node_put(guts_node);
 guts_node:
 		dev_dbg(fman->dev, "%s: Didn't perform FManV3 reset due to Errata A007273!\n",
 			__func__);
+#endif
 	}
 _return:
 	return err;
@@ -2868,6 +2876,13 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 
 	fman->dev = &of_dev->dev;
 
+	err = of_platform_populate(fm_node, NULL, NULL, &of_dev->dev);
+	if (err) {
+		dev_err(&of_dev->dev, "%s: of_platform_populate() failed\n",
+			__func__);
+		goto fman_free;
+	}
+
 	return fman;
 
 fman_node_put:
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 69ca42c..0b31f85 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -594,6 +594,7 @@ static const u16 phy2speed[] = {
 	[PHY_INTERFACE_MODE_RGMII_RXID]	= SPEED_1000,
 	[PHY_INTERFACE_MODE_RGMII_TXID]	= SPEED_1000,
 	[PHY_INTERFACE_MODE_RTBI]		= SPEED_1000,
+	[PHY_INTERFACE_MODE_QSGMII]		= SPEED_1000,
 	[PHY_INTERFACE_MODE_XGMII]		= SPEED_10000
 };
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index d9f3a48..1f98838 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -44,7 +44,7 @@
 #include <linux/vmalloc.h>
 #include <asm/pgtable.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "fs_enet.h"
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index 120c758..6e64989 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -42,7 +42,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "fs_enet.h"
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index 777beff..db9c0bc 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -36,7 +36,7 @@
 #include <linux/gfp.h>
 
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_8xx
 #include <asm/8xx_immap.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 15abd37..96d44cf 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -35,7 +35,7 @@
 #include <linux/of_platform.h>
 
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_8xx
 #include <asm/8xx_immap.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index a89267b..1582d82 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -35,7 +35,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mpc5xxx.h>
 
 #include "fs_enet.h"
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 756f7e7..a6e7afa 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -93,7 +93,7 @@
 #include <asm/mpc85xx.h>
 #endif
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
 #include <linux/crc32.h>
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 6e8a9c8..5aa8147 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -40,7 +40,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/crc32.h>
 #include <linux/workqueue.h>
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 56588f2..a93e019 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -32,7 +32,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/crc32.h>
 #include <asm/types.h>
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 53c5fcf..9d66088 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -37,7 +37,7 @@
 #include <linux/of_net.h>
 #include <linux/of_platform.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 #include <asm/io.h>
 #include <soc/fsl/qe/immap_qe.h>
diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 8ba636f..b642990 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -32,7 +32,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/types.h>
 
 #include "ucc_geth.h"
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index 51c4abc..a69cd19 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -54,7 +54,7 @@
 #include <pcmcia/ciscode.h>
 #include <pcmcia/ds.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 /*====================================================================*/
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index ee7e9ce..418ca1f3 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -1316,10 +1316,11 @@ static int hix5hd2_dev_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id hix5hd2_of_match[] = {
-	{ .compatible = "hisilicon,hisi-gemac-v1", .data = (void *)GEMAC_V1 },
-	{ .compatible = "hisilicon,hisi-gemac-v2", .data = (void *)GEMAC_V2 },
-	{ .compatible = "hisilicon,hix5hd2-gemac", .data = (void *)GEMAC_V1 },
-	{ .compatible = "hisilicon,hi3798cv200-gemac", .data = (void *)GEMAC_V2 },
+	{ .compatible = "hisilicon,hisi-gmac-v1", .data = (void *)GEMAC_V1 },
+	{ .compatible = "hisilicon,hisi-gmac-v2", .data = (void *)GEMAC_V2 },
+	{ .compatible = "hisilicon,hix5hd2-gmac", .data = (void *)GEMAC_V1 },
+	{ .compatible = "hisilicon,hi3798cv200-gmac", .data = (void *)GEMAC_V2 },
+	{ .compatible = "hisilicon,hi3516a-gmac", .data = (void *)GEMAC_V2 },
 	{},
 };
 
@@ -1327,7 +1328,7 @@ MODULE_DEVICE_TABLE(of, hix5hd2_of_match);
 
 static struct platform_driver hix5hd2_dev_driver = {
 	.driver = {
-		.name = "hisi-gemac",
+		.name = "hisi-gmac",
 		.of_match_table = hix5hd2_of_match,
 	},
 	.probe = hix5hd2_dev_probe,
@@ -1338,4 +1339,4 @@ module_platform_driver(hix5hd2_dev_driver);
 
 MODULE_DESCRIPTION("HISILICON Gigabit Ethernet MAC driver");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:hisi-gemac");
+MODULE_ALIAS("platform:hisi-gmac");
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 52a69c9..5909615 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -47,7 +47,7 @@
 #include <asm/processor.h>
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dcr.h>
 #include <asm/dcr-regs.h>
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index ffcf35a..eccf1da 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -4305,24 +4305,24 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter)
 /**
  * e1000e_sanitize_systim - sanitize raw cycle counter reads
  * @hw: pointer to the HW structure
- * @systim: cycle_t value read, sanitized and returned
+ * @systim: time value read, sanitized and returned
  *
  * Errata for 82574/82583 possible bad bits read from SYSTIMH/L:
  * check to see that the time is incrementing at a reasonable
  * rate and is a multiple of incvalue.
  **/
-static cycle_t e1000e_sanitize_systim(struct e1000_hw *hw, cycle_t systim)
+static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim)
 {
 	u64 time_delta, rem, temp;
-	cycle_t systim_next;
+	u64 systim_next;
 	u32 incvalue;
 	int i;
 
 	incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK;
 	for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) {
 		/* latch SYSTIMH on read of SYSTIML */
-		systim_next = (cycle_t)er32(SYSTIML);
-		systim_next |= (cycle_t)er32(SYSTIMH) << 32;
+		systim_next = (u64)er32(SYSTIML);
+		systim_next |= (u64)er32(SYSTIMH) << 32;
 
 		time_delta = systim_next - systim;
 		temp = time_delta;
@@ -4342,13 +4342,13 @@ static cycle_t e1000e_sanitize_systim(struct e1000_hw *hw, cycle_t systim)
  * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
  * @cc: cyclecounter structure
  **/
-static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc)
+static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
 {
 	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
 						     cc);
 	struct e1000_hw *hw = &adapter->hw;
 	u32 systimel, systimeh;
-	cycle_t systim;
+	u64 systim;
 	/* SYSTIMH latching upon SYSTIML read does not work well.
 	 * This means that if SYSTIML overflows after we read it but before
 	 * we read SYSTIMH, the value of SYSTIMH has been incremented and we
@@ -4368,8 +4368,8 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc)
 			systimel = systimel_2;
 		}
 	}
-	systim = (cycle_t)systimel;
-	systim |= (cycle_t)systimeh << 32;
+	systim = (u64)systimel;
+	systim |= (u64)systimeh << 32;
 
 	if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW)
 		systim = e1000e_sanitize_systim(hw, systim);
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index ad03763..34cc3be 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -127,8 +127,8 @@ static int e1000e_phc_get_syncdevicetime(ktime_t *device,
 	unsigned long flags;
 	int i;
 	u32 tsync_ctrl;
-	cycle_t dev_cycles;
-	cycle_t sys_cycles;
+	u64 dev_cycles;
+	u64 sys_cycles;
 
 	tsync_ctrl = er32(TSYNCTXCTL);
 	tsync_ctrl |= E1000_TSYNCTXCTL_START_SYNC |
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index c30eea8..c447755 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -77,7 +77,7 @@
 static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter);
 
 /* SYSTIM read access for the 82576 */
-static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc)
+static u64 igb_ptp_read_82576(const struct cyclecounter *cc)
 {
 	struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc);
 	struct e1000_hw *hw = &igb->hw;
@@ -94,7 +94,7 @@ static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc)
 }
 
 /* SYSTIM read access for the 82580 */
-static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc)
+static u64 igb_ptp_read_82580(const struct cyclecounter *cc)
 {
 	struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc);
 	struct e1000_hw *hw = &igb->hw;
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
index d2b29b4..e5d7255 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
@@ -30,7 +30,7 @@
 
 #include "ixgb.h"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define IXGB_ALL_RAR_ENTRIES 16
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index a922776..1efb404 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -245,7 +245,7 @@ static void ixgbe_ptp_setup_sdp_x540(struct ixgbe_adapter *adapter)
  * result of SYSTIME is 32bits of "billions of cycles" and 32 bits of
  * "cycles", rather than seconds and nanoseconds.
  */
-static cycle_t ixgbe_ptp_read_X550(const struct cyclecounter *hw_cc)
+static u64 ixgbe_ptp_read_X550(const struct cyclecounter *hw_cc)
 {
 	struct ixgbe_adapter *adapter =
 			container_of(hw_cc, struct ixgbe_adapter, hw_cc);
@@ -282,7 +282,7 @@ static cycle_t ixgbe_ptp_read_X550(const struct cyclecounter *hw_cc)
  * cyclecounter structure used to construct a ns counter from the
  * arbitrary fixed point registers
  */
-static cycle_t ixgbe_ptp_read_82599(const struct cyclecounter *cc)
+static u64 ixgbe_ptp_read_82599(const struct cyclecounter *cc)
 {
 	struct ixgbe_adapter *adapter =
 		container_of(cc, struct ixgbe_adapter, hw_cc);
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index cbeea91..8037426 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -900,10 +900,10 @@ static void korina_restart_task(struct work_struct *work)
 				DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR,
 				&lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
+	korina_free_ring(dev);
+
 	if (korina_init(dev) < 0) {
 		printk(KERN_ERR "%s: cannot restart device\n", dev->name);
 		return;
@@ -1064,12 +1064,12 @@ static int korina_close(struct net_device *dev)
 	tmp = tmp | DMA_STAT_DONE | DMA_STAT_HALT | DMA_STAT_ERR;
 	writel(tmp, &lp->rx_dma_regs->dmasm);
 
-	korina_free_ring(dev);
-
 	napi_disable(&lp->napi);
 
 	cancel_work_sync(&lp->restart_task);
 
+	korina_free_ring(dev);
+
 	free_irq(lp->rx_irq, dev);
 	free_irq(lp->tx_irq, dev);
 	free_irq(lp->ovr_irq, dev);
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index dabc541..4fe430c 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -770,6 +770,17 @@ struct mvpp2_rx_desc {
 	u32 reserved8;
 };
 
+struct mvpp2_txq_pcpu_buf {
+	/* Transmitted SKB */
+	struct sk_buff *skb;
+
+	/* Physical address of transmitted buffer */
+	dma_addr_t phys;
+
+	/* Size transmitted */
+	size_t size;
+};
+
 /* Per-CPU Tx queue control */
 struct mvpp2_txq_pcpu {
 	int cpu;
@@ -785,11 +796,8 @@ struct mvpp2_txq_pcpu {
 	/* Number of Tx DMA descriptors reserved for each CPU */
 	int reserved_num;
 
-	/* Array of transmitted skb */
-	struct sk_buff **tx_skb;
-
-	/* Array of transmitted buffers' physical addresses */
-	dma_addr_t *tx_buffs;
+	/* Infos about transmitted buffers */
+	struct mvpp2_txq_pcpu_buf *buffs;
 
 	/* Index of last TX DMA descriptor that was inserted */
 	int txq_put_index;
@@ -979,10 +987,11 @@ static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu,
 			      struct sk_buff *skb,
 			      struct mvpp2_tx_desc *tx_desc)
 {
-	txq_pcpu->tx_skb[txq_pcpu->txq_put_index] = skb;
-	if (skb)
-		txq_pcpu->tx_buffs[txq_pcpu->txq_put_index] =
-							 tx_desc->buf_phys_addr;
+	struct mvpp2_txq_pcpu_buf *tx_buf =
+		txq_pcpu->buffs + txq_pcpu->txq_put_index;
+	tx_buf->skb = skb;
+	tx_buf->size = tx_desc->data_size;
+	tx_buf->phys = tx_desc->buf_phys_addr;
 	txq_pcpu->txq_put_index++;
 	if (txq_pcpu->txq_put_index == txq_pcpu->size)
 		txq_pcpu->txq_put_index = 0;
@@ -4401,17 +4410,16 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 	int i;
 
 	for (i = 0; i < num; i++) {
-		dma_addr_t buf_phys_addr =
-				    txq_pcpu->tx_buffs[txq_pcpu->txq_get_index];
-		struct sk_buff *skb = txq_pcpu->tx_skb[txq_pcpu->txq_get_index];
+		struct mvpp2_txq_pcpu_buf *tx_buf =
+			txq_pcpu->buffs + txq_pcpu->txq_get_index;
 
 		mvpp2_txq_inc_get(txq_pcpu);
 
-		dma_unmap_single(port->dev->dev.parent, buf_phys_addr,
-				 skb_headlen(skb), DMA_TO_DEVICE);
-		if (!skb)
+		dma_unmap_single(port->dev->dev.parent, tx_buf->phys,
+				 tx_buf->size, DMA_TO_DEVICE);
+		if (!tx_buf->skb)
 			continue;
-		dev_kfree_skb_any(skb);
+		dev_kfree_skb_any(tx_buf->skb);
 	}
 }
 
@@ -4651,15 +4659,10 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
 		txq_pcpu->size = txq->size;
-		txq_pcpu->tx_skb = kmalloc(txq_pcpu->size *
-					   sizeof(*txq_pcpu->tx_skb),
-					   GFP_KERNEL);
-		if (!txq_pcpu->tx_skb)
-			goto error;
-
-		txq_pcpu->tx_buffs = kmalloc(txq_pcpu->size *
-					     sizeof(dma_addr_t), GFP_KERNEL);
-		if (!txq_pcpu->tx_buffs)
+		txq_pcpu->buffs = kmalloc(txq_pcpu->size *
+					  sizeof(struct mvpp2_txq_pcpu_buf),
+					  GFP_KERNEL);
+		if (!txq_pcpu->buffs)
 			goto error;
 
 		txq_pcpu->count = 0;
@@ -4673,8 +4676,7 @@ static int mvpp2_txq_init(struct mvpp2_port *port,
 error:
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
-		kfree(txq_pcpu->tx_skb);
-		kfree(txq_pcpu->tx_buffs);
+		kfree(txq_pcpu->buffs);
 	}
 
 	dma_free_coherent(port->dev->dev.parent,
@@ -4693,8 +4695,7 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port,
 
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
-		kfree(txq_pcpu->tx_skb);
-		kfree(txq_pcpu->tx_buffs);
+		kfree(txq_pcpu->buffs);
 	}
 
 	if (txq->descs)
@@ -4912,7 +4913,7 @@ static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu)
 
 	if (!port_pcpu->timer_scheduled) {
 		port_pcpu->timer_scheduled = true;
-		interval = ktime_set(0, MVPP2_TXDONE_HRTIMER_PERIOD_NS);
+		interval = MVPP2_TXDONE_HRTIMER_PERIOD_NS;
 		hrtimer_start(&port_pcpu->tx_done_timer, interval,
 			      HRTIMER_MODE_REL_PINNED);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index a5fc46b..015198c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -38,7 +38,7 @@
 
 /* mlx4_en_read_clock - read raw cycle counter (to be used by time counter)
  */
-static cycle_t mlx4_en_read_clock(const struct cyclecounter *tc)
+static u64 mlx4_en_read_clock(const struct cyclecounter *tc)
 {
 	struct mlx4_en_dev *mdev =
 		container_of(tc, struct mlx4_en_dev, cycles);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index bcd9553..edbe200 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1638,7 +1638,8 @@ int mlx4_en_start_port(struct net_device *dev)
 
 	/* Configure tx cq's and rings */
 	for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
-		u8 num_tx_rings_p_up = t == TX ? priv->num_tx_rings_p_up : 1;
+		u8 num_tx_rings_p_up = t == TX ?
+			priv->num_tx_rings_p_up : priv->tx_ring_num[t];
 
 		for (i = 0; i < priv->tx_ring_num[t]; i++) {
 			/* Configure cq */
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index b2ca8a6..5e7840a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1823,10 +1823,10 @@ static void unmap_bf_area(struct mlx4_dev *dev)
 		io_mapping_free(mlx4_priv(dev)->bf_mapping);
 }
 
-cycle_t mlx4_read_clock(struct mlx4_dev *dev)
+u64 mlx4_read_clock(struct mlx4_dev *dev)
 {
 	u32 clockhi, clocklo, clockhi1;
-	cycle_t cycles;
+	u64 cycles;
 	int i;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 2cd8e56..746a92c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -49,7 +49,7 @@ void mlx5e_fill_hwstamp(struct mlx5e_tstamp *tstamp, u64 timestamp,
 	hwts->hwtstamp = ns_to_ktime(nsec);
 }
 
-static cycle_t mlx5e_read_internal_timer(const struct cyclecounter *cc)
+static u64 mlx5e_read_internal_timer(const struct cyclecounter *cc)
 {
 	struct mlx5e_tstamp *tstamp = container_of(cc, struct mlx5e_tstamp,
 						   cycles);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 3b026c1..7431f63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -75,7 +75,7 @@ static void mlx5_fc_stats_insert(struct rb_root *root, struct mlx5_fc *counter)
 	struct rb_node *parent = NULL;
 
 	while (*new) {
-		struct mlx5_fc *this = container_of(*new, struct mlx5_fc, node);
+		struct mlx5_fc *this = rb_entry(*new, struct mlx5_fc, node);
 		int result = counter->id - this->id;
 
 		parent = *new;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7b4c339..54e5a78 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -557,7 +557,7 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id)
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev)
+u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 {
 	u32 timer_h, timer_h1, timer_l;
 
@@ -567,7 +567,7 @@ cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 	if (timer_h != timer_h1) /* wrap around */
 		timer_l = ioread32be(&dev->iseg->internal_timer_l);
 
-	return (cycle_t)timer_l | (cycle_t)timer_h1 << 32;
+	return (u64)timer_l | (u64)timer_h1 << 32;
 }
 
 static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index e0a8fbd..d4a99c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -106,7 +106,7 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
-cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev);
+u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
 u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx);
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
 void mlx5_cq_tasklet_cb(unsigned long data);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 53126bf..01d0efa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -942,7 +942,7 @@ static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work)
 	char rauht_pl[MLXSW_REG_RAUHT_LEN];
 	struct net_device *dev;
 	bool entry_connected;
-	u8 nud_state;
+	u8 nud_state, dead;
 	bool updating;
 	bool removing;
 	bool adding;
@@ -953,10 +953,11 @@ static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work)
 	dip = ntohl(*((__be32 *) n->primary_key));
 	memcpy(neigh_entry->ha, n->ha, sizeof(neigh_entry->ha));
 	nud_state = n->nud_state;
+	dead = n->dead;
 	dev = n->dev;
 	read_unlock_bh(&n->lock);
 
-	entry_connected = nud_state & NUD_VALID;
+	entry_connected = nud_state & NUD_VALID && !dead;
 	adding = (!neigh_entry->offloaded) && entry_connected;
 	updating = neigh_entry->offloaded && entry_connected;
 	removing = neigh_entry->offloaded && !entry_connected;
@@ -1351,7 +1352,7 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_neigh_entry *neigh_entry;
 	struct net_device *dev = fib_nh->nh_dev;
 	struct neighbour *n;
-	u8 nud_state;
+	u8 nud_state, dead;
 
 	/* Take a reference of neigh here ensuring that neigh would
 	 * not be detructed before the nexthop entry is finished.
@@ -1383,8 +1384,9 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
 	list_add_tail(&nh->neigh_list_node, &neigh_entry->nexthop_list);
 	read_lock_bh(&n->lock);
 	nud_state = n->nud_state;
+	dead = n->dead;
 	read_unlock_bh(&n->lock);
-	__mlxsw_sp_nexthop_neigh_update(nh, !(nud_state & NUD_VALID));
+	__mlxsw_sp_nexthop_neigh_update(nh, !(nud_state & NUD_VALID && !dead));
 
 	return 0;
 }
@@ -1394,6 +1396,7 @@ static void mlxsw_sp_nexthop_fini(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry;
 
+	__mlxsw_sp_nexthop_neigh_update(nh, true);
 	list_del(&nh->neigh_list_node);
 
 	/* If that is the last nexthop connected to that neigh, remove from
@@ -1452,6 +1455,8 @@ mlxsw_sp_nexthop_group_destroy(struct mlxsw_sp *mlxsw_sp,
 		nh = &nh_grp->nexthops[i];
 		mlxsw_sp_nexthop_fini(mlxsw_sp, nh);
 	}
+	mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
+	WARN_ON_ONCE(nh_grp->adj_index_valid);
 	kfree(nh_grp);
 }
 
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index 22b0821..90eac63 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -51,7 +51,7 @@
 #include <asm/processor.h>	/* Processor type for cache alignment. */
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define DRV_NAME	"natsemi"
 #define DRV_VERSION	"2.1"
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index 93c4bdc..f9d2eb9 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -119,7 +119,7 @@
 #include <linux/slab.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define DRV_NAME "ns83820"
 
diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c
index 2d04679..baff744 100644
--- a/drivers/net/ethernet/packetengines/hamachi.c
+++ b/drivers/net/ethernet/packetengines/hamachi.c
@@ -160,7 +160,7 @@ static int tx_params[MAX_UNITS] = {-1, -1, -1, -1, -1, -1, -1, -1};
 #include <linux/delay.h>
 #include <linux/bitops.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>	/* Processor type for cache alignment. */
 #include <asm/io.h>
 #include <asm/unaligned.h>
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index 2a2ca5f..fa7770d 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -100,7 +100,7 @@ static int gx_fix;
 #include <linux/ethtool.h>
 #include <linux/crc32.h>
 #include <linux/bitops.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>		/* Processor type for cache alignment. */
 #include <asm/unaligned.h>
 #include <asm/io.h>
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index b7c89eb..0b3cd58 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -76,7 +76,7 @@
 #include <linux/cache.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* These identify the driver base version and may not be removed. */
 static char version[] =
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f9b97f5..44389c9 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -326,6 +326,7 @@ enum cfg_version {
 static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
+	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 46f7be8..2c03262 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -1,3 +1,20 @@
+#
+# Solarflare device configuration
+#
+
+config NET_VENDOR_SOLARFLARE
+	bool "Solarflare devices"
+	default y
+	---help---
+	  If you have a network (Ethernet) card belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about Solarflare devices. If you say Y, you will be asked
+	  for your specific card in the following questions.
+
+if NET_VENDOR_SOLARFLARE
+
 config SFC
 	tristate "Solarflare SFC9000/SFC9100-family support"
 	depends on PCI
@@ -44,3 +61,7 @@
 	  Driver-Interface) commands and responses, allowing debugging of
 	  driver/firmware interaction.  The tracing is actually enabled by
 	  a sysfs file 'mcdi_logging' under the PCI device.
+
+source "drivers/net/ethernet/sfc/falcon/Kconfig"
+
+endif # NET_VENDOR_SOLARFLARE
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 42051ab..d390b96 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -60,7 +60,7 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sn/types.h>
 #include <asm/sn/ioc3.h>
 #include <asm/pci/bridge.h>
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 39fca6c..19a4587 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -74,7 +74,7 @@
 #include <asm/processor.h>      /* Processor type for cache alignment. */
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>	/* User space memory access functions */
+#include <linux/uaccess.h>	/* User space memory access functions */
 
 #include "sis900.h"
 
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index fe9760f..55a95e1 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -86,7 +86,7 @@ static int rx_copybreak;
 #include <linux/crc32.h>
 #include <linux/bitops.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 /* These identify the driver base version and may not be removed. */
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index f1c75e2..6715462 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -52,7 +52,7 @@
 #include <pcmcia/ss.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*====================================================================*/
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 77ab0a8..fa6e970 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -864,6 +864,10 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 	int ret;
 	struct device *dev = &bsp_priv->pdev->dev;
 
+	ret = gmac_clk_enable(bsp_priv, true);
+	if (ret)
+		return ret;
+
 	/*rmii or rgmii*/
 	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII) {
 		dev_info(dev, "init for RGMII\n");
@@ -880,10 +884,6 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 	if (ret)
 		return ret;
 
-	ret = gmac_clk_enable(bsp_priv, true);
-	if (ret)
-		return ret;
-
 	pm_runtime_enable(dev);
 	pm_runtime_get_sync(dev);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index b21d03f..be3c91c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -539,7 +539,7 @@ struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
 	mac->mii.reg_shift = 6;
 	mac->mii.reg_mask = 0x000007C0;
 	mac->mii.clk_csr_shift = 2;
-	mac->mii.clk_csr_mask = 0xF;
+	mac->mii.clk_csr_mask = GENMASK(5, 2);
 
 	/* Get and dump the chip ID */
 	*synopsys_id = stmmac_get_synopsys_id(hwid);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index a1d582f..9dd2987 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -197,7 +197,7 @@ struct mac_device_info *dwmac100_setup(void __iomem *ioaddr, int *synopsys_id)
 	mac->mii.reg_shift = 6;
 	mac->mii.reg_mask = 0x000007C0;
 	mac->mii.clk_csr_shift = 2;
-	mac->mii.clk_csr_mask = 0xF;
+	mac->mii.clk_csr_mask = GENMASK(5, 2);
 
 	/* Synopsys Id is not available on old chips */
 	*synopsys_id = 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index a340fc8..8816515 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -334,7 +334,7 @@ static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 		 * descriptors for the same frame has to be set before, to
 		 * avoid race condition.
 		 */
-		wmb();
+		dma_wmb();
 
 	p->des3 = cpu_to_le32(tdes3);
 }
@@ -377,7 +377,7 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
 		 * descriptors for the same frame has to be set before, to
 		 * avoid race condition.
 		 */
-		wmb();
+		dma_wmb();
 
 	p->des3 = cpu_to_le32(tdes3);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index ce97e52..f0d8632 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -350,7 +350,7 @@ static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 		 * descriptors for the same frame has to be set before, to
 		 * avoid race condition.
 		 */
-		wmb();
+		dma_wmb();
 
 	p->des0 = cpu_to_le32(tdes0);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3e40578..bb40382 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2125,7 +2125,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * descriptor and then barrier is needed to make sure that
 	 * all is coherent before granting the DMA engine.
 	 */
-	smp_wmb();
+	dma_wmb();
 
 	if (netif_msg_pktdata(priv)) {
 		pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n",
@@ -2338,7 +2338,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * descriptor and then barrier is needed to make sure that
 		 * all is coherent before granting the DMA engine.
 		 */
-		smp_wmb();
+		dma_wmb();
 	}
 
 	netdev_sent_queue(dev, skb->len);
@@ -2443,14 +2443,14 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv)
 			netif_dbg(priv, rx_status, priv->dev,
 				  "refill entry #%d\n", entry);
 		}
-		wmb();
+		dma_wmb();
 
 		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
 			priv->hw->desc->init_rx_desc(p, priv->use_riwt, 0, 0);
 		else
 			priv->hw->desc->set_rx_owner(p);
 
-		wmb();
+		dma_wmb();
 
 		entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE);
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 23322fd..b0344c2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -81,8 +81,8 @@ static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
 	value |= (phyaddr << priv->hw->mii.addr_shift)
 		& priv->hw->mii.addr_mask;
 	value |= (phyreg << priv->hw->mii.reg_shift) & priv->hw->mii.reg_mask;
-	value |= (priv->clk_csr & priv->hw->mii.clk_csr_mask)
-		<< priv->hw->mii.clk_csr_shift;
+	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
+		& priv->hw->mii.clk_csr_mask;
 	if (priv->plat->has_gmac4)
 		value |= MII_GMAC4_READ;
 
@@ -116,16 +116,18 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
 	unsigned int mii_address = priv->hw->mii.addr;
 	unsigned int mii_data = priv->hw->mii.data;
 
-	u32 value = MII_WRITE | MII_BUSY;
+	u32 value = MII_BUSY;
 
 	value |= (phyaddr << priv->hw->mii.addr_shift)
 		& priv->hw->mii.addr_mask;
 	value |= (phyreg << priv->hw->mii.reg_shift) & priv->hw->mii.reg_mask;
 
-	value |= ((priv->clk_csr & priv->hw->mii.clk_csr_mask)
-		<< priv->hw->mii.clk_csr_shift);
+	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
+		& priv->hw->mii.clk_csr_mask;
 	if (priv->plat->has_gmac4)
 		value |= MII_GMAC4_WRITE;
+	else
+		value |= MII_WRITE;
 
 	/* Wait until any existing MII operation is complete */
 	if (stmmac_mdio_busy_wait(priv->ioaddr, mii_address))
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index e9e5ef2..0e8e89f 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -99,7 +99,7 @@
 #include <linux/atomic.h>
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define cas_page_map(x)      kmap_atomic((x))
 #define cas_page_unmap(x)    kunmap_atomic((x))
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 66ecf0f..d277e41 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -42,7 +42,7 @@
 
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/irq.h>
 
 #ifdef CONFIG_SPARC
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index ca96408..72ff05c 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -49,7 +49,7 @@
 #include <asm/prom.h>
 #include <asm/auxio.h>
 #endif
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
 #include <asm/irq.h>
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 0c0d48e..32279d2 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -121,7 +121,7 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 	return type == match ? 0 : -1;
 }
 
-static cycle_t cpts_systim_read(const struct cyclecounter *cc)
+static u64 cpts_systim_read(const struct cyclecounter *cc)
 {
 	u64 val = 0;
 	struct cpts_event *event;
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index c7e547e..7d9e36f 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -94,6 +94,7 @@
 
 /* offset relative to base of XGBE_SS_REG_INDEX */
 #define XGBE10_SGMII_MODULE_OFFSET	0x100
+#define IS_SS_ID_XGBE(d)		((d)->ss_version == XGBE_SS_VERSION_10)
 /* offset relative to base of XGBE_SM_REG_INDEX */
 #define XGBE10_HOST_PORT_OFFSET		0x34
 #define XGBE10_SLAVE_PORT_OFFSET	0x64
@@ -1746,6 +1747,17 @@ static void keystone_set_msglevel(struct net_device *ndev, u32 value)
 	netcp->msg_enable = value;
 }
 
+static struct gbe_intf *keystone_get_intf_data(struct netcp_intf *netcp)
+{
+	struct gbe_intf *gbe_intf;
+
+	gbe_intf = netcp_module_get_intf_data(&gbe_module, netcp);
+	if (!gbe_intf)
+		gbe_intf = netcp_module_get_intf_data(&xgbe_module, netcp);
+
+	return gbe_intf;
+}
+
 static void keystone_get_stat_strings(struct net_device *ndev,
 				      uint32_t stringset, uint8_t *data)
 {
@@ -1754,7 +1766,7 @@ static void keystone_get_stat_strings(struct net_device *ndev,
 	struct gbe_priv *gbe_dev;
 	int i;
 
-	gbe_intf = netcp_module_get_intf_data(&gbe_module, netcp);
+	gbe_intf = keystone_get_intf_data(netcp);
 	if (!gbe_intf)
 		return;
 	gbe_dev = gbe_intf->gbe_dev;
@@ -1778,7 +1790,7 @@ static int keystone_get_sset_count(struct net_device *ndev, int stringset)
 	struct gbe_intf *gbe_intf;
 	struct gbe_priv *gbe_dev;
 
-	gbe_intf = netcp_module_get_intf_data(&gbe_module, netcp);
+	gbe_intf = keystone_get_intf_data(netcp);
 	if (!gbe_intf)
 		return -EINVAL;
 	gbe_dev = gbe_intf->gbe_dev;
@@ -1896,7 +1908,7 @@ static void keystone_get_ethtool_stats(struct net_device *ndev,
 	struct gbe_intf *gbe_intf;
 	struct gbe_priv *gbe_dev;
 
-	gbe_intf = netcp_module_get_intf_data(&gbe_module, netcp);
+	gbe_intf = keystone_get_intf_data(netcp);
 	if (!gbe_intf)
 		return;
 
@@ -1920,7 +1932,7 @@ static int keystone_get_link_ksettings(struct net_device *ndev,
 	if (!phy)
 		return -EINVAL;
 
-	gbe_intf = netcp_module_get_intf_data(&gbe_module, netcp);
+	gbe_intf = keystone_get_intf_data(netcp);
 	if (!gbe_intf)
 		return -EINVAL;
 
@@ -1953,7 +1965,7 @@ static int keystone_set_link_ksettings(struct net_device *ndev,
 	if (!phy)
 		return -EINVAL;
 
-	gbe_intf = netcp_module_get_intf_data(&gbe_module, netcp);
+	gbe_intf = keystone_get_intf_data(netcp);
 	if (!gbe_intf)
 		return -EINVAL;
 
@@ -2311,7 +2323,7 @@ static void gbe_init_host_port(struct gbe_priv *priv)
 	int bypass_en = 1;
 
 	/* Host Tx Pri */
-	if (IS_SS_ID_NU(priv))
+	if (IS_SS_ID_NU(priv) || IS_SS_ID_XGBE(priv))
 		writel(HOST_TX_PRI_MAP_DEFAULT,
 		       GBE_REG_ADDR(priv, host_port_regs, tx_pri_map));
 
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 0aaf975..2255f9a 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -751,7 +751,7 @@ static void tile_net_schedule_tx_wake_timer(struct net_device *dev,
 		&info->mpipe[instance].tx_wake[priv->echannel];
 
 	hrtimer_start(&tx_wake->timer,
-		      ktime_set(0, TX_TIMER_DELAY_USEC * 1000UL),
+		      TX_TIMER_DELAY_USEC * 1000UL,
 		      HRTIMER_MODE_REL_PINNED);
 }
 
@@ -770,7 +770,7 @@ static void tile_net_schedule_egress_timer(void)
 
 	if (!info->egress_timer_scheduled) {
 		hrtimer_start(&info->egress_timer,
-			      ktime_set(0, EGRESS_TIMER_DELAY_USEC * 1000UL),
+			      EGRESS_TIMER_DELAY_USEC * 1000UL,
 			      HRTIMER_MODE_REL_PINNED);
 		info->egress_timer_scheduled = true;
 	}
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index ba5c542..0a6c4e8 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -114,7 +114,7 @@ static const int multicast_filter_limit = 32;
 #include <asm/processor.h>	/* Processor type for cache alignment. */
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/dmi.h>
 
 /* These identify the driver base version and may not be removed. */
diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index 3b08ec7..f718832 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -88,7 +88,7 @@
 #include <pcmcia/ciscode.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifndef MANFID_COMPAQ
   #define MANFID_COMPAQ 	   0x0138
diff --git a/drivers/net/fddi/skfp/hwmtm.c b/drivers/net/fddi/skfp/hwmtm.c
index e26398b..d0a68bd 100644
--- a/drivers/net/fddi/skfp/hwmtm.c
+++ b/drivers/net/fddi/skfp/hwmtm.c
@@ -1483,7 +1483,7 @@ void mac_drv_clear_rx_queue(struct s_smc *smc)
 	r = queue->rx_curr_get ;
 	while (queue->rx_used) {
 		DRV_BUF_FLUSH(r,DDI_DMA_SYNC_FORCPU) ;
-		DB_RX("switch OWN bit of RxD 0x%x ",r,0,5) ;
+		DB_RX("switch OWN bit of RxD 0x%p ",r,0,5) ;
 		r->rxd_rbctrl &= ~cpu_to_le32(BMU_OWN) ;
 		frag_count = 1 ;
 		DRV_BUF_FLUSH(r,DDI_DMA_SYNC_FORDEV) ;
@@ -1645,7 +1645,7 @@ void hwm_tx_frag(struct s_smc *smc, char far *virt, u_long phys, int len,
 	DB_TX("hwm_tx_frag: len = %d, frame_status = %x ",len,frame_status,2) ;
 	if (frame_status & LAN_TX) {
 		/* '*t' is already defined */
-		DB_TX("LAN_TX: TxD = %x, virt = %x ",t,virt,3) ;
+		DB_TX("LAN_TX: TxD = %p, virt = %p ",t,virt,3) ;
 		t->txd_virt = virt ;
 		t->txd_txdscr = cpu_to_le32(smc->os.hwm.tx_descr) ;
 		t->txd_tbadr = cpu_to_le32(phys) ;
@@ -1819,7 +1819,7 @@ void smt_send_mbuf(struct s_smc *smc, SMbuf *mb, int fc)
 	__le32	tbctrl;
 
 	NDD_TRACE("THSB",mb,fc,0) ;
-	DB_TX("smt_send_mbuf: mb = 0x%x, fc = 0x%x",mb,fc,4) ;
+	DB_TX("smt_send_mbuf: mb = 0x%p, fc = 0x%x",mb,fc,4) ;
 
 	mb->sm_off-- ;	/* set to fc */
 	mb->sm_len++ ;	/* + fc */
@@ -1960,7 +1960,7 @@ static void mac_drv_clear_txd(struct s_smc *smc)
 
 			do {
 				DRV_BUF_FLUSH(t1,DDI_DMA_SYNC_FORCPU) ;
-				DB_TX("check OWN/EOF bit of TxD 0x%x",t1,0,5) ;
+				DB_TX("check OWN/EOF bit of TxD 0x%p",t1,0,5) ;
 				tbctrl = le32_to_cpu(CR_READ(t1->txd_tbctrl));
 
 				if (tbctrl & BMU_OWN || !queue->tx_used){
@@ -1988,7 +1988,7 @@ static void mac_drv_clear_txd(struct s_smc *smc)
 			}
 			else {
 #ifndef PASS_1ST_TXD_2_TX_COMP
-				DB_TX("mac_drv_tx_comp for TxD 0x%x",t2,0,4) ;
+				DB_TX("mac_drv_tx_comp for TxD 0x%p",t2,0,4) ;
 				mac_drv_tx_complete(smc,t2) ;
 #else
 				DB_TX("mac_drv_tx_comp for TxD 0x%x",
@@ -2052,7 +2052,7 @@ void mac_drv_clear_tx_queue(struct s_smc *smc)
 		tx_used = queue->tx_used ;
 		while (tx_used) {
 			DRV_BUF_FLUSH(t,DDI_DMA_SYNC_FORCPU) ;
-			DB_TX("switch OWN bit of TxD 0x%x ",t,0,5) ;
+			DB_TX("switch OWN bit of TxD 0x%p ",t,0,5) ;
 			t->txd_tbctrl &= ~cpu_to_le32(BMU_OWN) ;
 			DRV_BUF_FLUSH(t,DDI_DMA_SYNC_FORDEV) ;
 			t = t->txd_next ;
diff --git a/drivers/net/fddi/skfp/pmf.c b/drivers/net/fddi/skfp/pmf.c
index 441b4dc..52fa162 100644
--- a/drivers/net/fddi/skfp/pmf.c
+++ b/drivers/net/fddi/skfp/pmf.c
@@ -284,7 +284,7 @@ void smt_pmf_received_pack(struct s_smc *smc, SMbuf *mb, int local)
 	SMbuf		*reply ;
 
 	sm = smtod(mb,struct smt_header *) ;
-	DB_SMT("SMT: processing PMF frame at %x len %d\n",sm,mb->sm_len) ;
+	DB_SMT("SMT: processing PMF frame at %p len %d\n",sm,mb->sm_len) ;
 #ifdef	DEBUG
 	dump_smt(smc,sm,"PMF Received") ;
 #endif
diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c
index 3a63918..2414f1d 100644
--- a/drivers/net/fddi/skfp/skfddi.c
+++ b/drivers/net/fddi/skfp/skfddi.c
@@ -88,7 +88,7 @@ static const char * const boot_msg =
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include	"h/types.h"
 #undef ADDR			// undo Linux definition
diff --git a/drivers/net/fddi/skfp/smt.c b/drivers/net/fddi/skfp/smt.c
index cd78b7c..e80a089 100644
--- a/drivers/net/fddi/skfp/smt.c
+++ b/drivers/net/fddi/skfp/smt.c
@@ -504,7 +504,7 @@ void smt_received_pack(struct s_smc *smc, SMbuf *mb, int fs)
 #endif
 
 	smt_swap_para(sm,(int) mb->sm_len,1) ;
-	DB_SMT("SMT : received packet [%s] at 0x%x\n",
+	DB_SMT("SMT : received packet [%s] at 0x%p\n",
 		smt_type_name[m_fc(mb) & 0xf],sm) ;
 	DB_SMT("SMT : version %d, class %s\n",sm->smt_version,
 		smt_class_name[(sm->smt_class>LAST_CLASS)?0 : sm->smt_class]) ;
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 470b3dc..922bf44 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -13,7 +13,7 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
 #include <linux/mm.h>
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 78dbc44..7d05469 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -55,7 +55,7 @@
 #include <linux/jiffies.h>
 #include <linux/random.h>
 #include <net/ax25.h> 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* --------------------------------------------------------------------- */
 
diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c
index 072cddc..809dc25 100644
--- a/drivers/net/hamradio/baycom_par.c
+++ b/drivers/net/hamradio/baycom_par.c
@@ -86,7 +86,7 @@
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* --------------------------------------------------------------------- */
 
diff --git a/drivers/net/hamradio/baycom_ser_fdx.c b/drivers/net/hamradio/baycom_ser_fdx.c
index 7b916d5..ebc0682 100644
--- a/drivers/net/hamradio/baycom_ser_fdx.c
+++ b/drivers/net/hamradio/baycom_ser_fdx.c
@@ -82,7 +82,7 @@
 #include <linux/jiffies.h>
 #include <linux/time64.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/hamradio/baycom_ser_hdx.c b/drivers/net/hamradio/baycom_ser_hdx.c
index f9a8976..60fcf51 100644
--- a/drivers/net/hamradio/baycom_ser_hdx.c
+++ b/drivers/net/hamradio/baycom_ser_hdx.c
@@ -67,7 +67,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/hdlcdrv.h>
 #include <linux/baycom.h>
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 622ab3a..f62e7f3 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -69,7 +69,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
diff --git a/drivers/net/hamradio/dmascc.c b/drivers/net/hamradio/dmascc.c
index e4137c1..2479072 100644
--- a/drivers/net/hamradio/dmascc.c
+++ b/drivers/net/hamradio/dmascc.c
@@ -40,7 +40,7 @@
 #include <asm/dma.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/ax25.h>
 #include "z8530.h"
 
diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index 4bad0b8..8c3633c 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -58,7 +58,7 @@
 #include <linux/hdlcdrv.h>
 #include <linux/random.h>
 #include <net/ax25.h> 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/crc-ccitt.h>
 
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 1dfe230..ece59c5 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -17,7 +17,7 @@
  */
 #include <linux/module.h>
 #include <linux/bitops.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/crc16.h>
 #include <linux/string.h>
 #include <linux/mm.h>
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index b808316..6754cd0 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -178,7 +178,7 @@
 
 #include <asm/irq.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "z8530.h"
 
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index aaff07c..b6891ad 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -68,7 +68,7 @@
 #include <linux/seq_file.h>
 #include <net/net_namespace.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/init.h>
 
 #include <linux/yam.h>
diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index f5a9728..dd7fc665 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -46,7 +46,7 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define rr_if_busy(dev)     netif_queue_stopped(dev)
 #define rr_if_running(dev)  netif_running(dev)
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 0570257..46d53a6 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -510,7 +510,7 @@ at86rf230_async_state_delay(void *context)
 	case STATE_TRX_OFF:
 		switch (ctx->to_state) {
 		case STATE_RX_AACK_ON:
-			tim = ktime_set(0, c->t_off_to_aack * NSEC_PER_USEC);
+			tim = c->t_off_to_aack * NSEC_PER_USEC;
 			/* state change from TRX_OFF to RX_AACK_ON to do a
 			 * calibration, we need to reset the timeout for the
 			 * next one.
@@ -519,7 +519,7 @@ at86rf230_async_state_delay(void *context)
 			goto change;
 		case STATE_TX_ARET_ON:
 		case STATE_TX_ON:
-			tim = ktime_set(0, c->t_off_to_tx_on * NSEC_PER_USEC);
+			tim = c->t_off_to_tx_on * NSEC_PER_USEC;
 			/* state change from TRX_OFF to TX_ON or ARET_ON to do
 			 * a calibration, we need to reset the timeout for the
 			 * next one.
@@ -539,8 +539,7 @@ at86rf230_async_state_delay(void *context)
 			 * to TX_ON or TRX_OFF.
 			 */
 			if (!force) {
-				tim = ktime_set(0, (c->t_frame + c->t_p_ack) *
-						   NSEC_PER_USEC);
+				tim = (c->t_frame + c->t_p_ack) * NSEC_PER_USEC;
 				goto change;
 			}
 			break;
@@ -552,7 +551,7 @@ at86rf230_async_state_delay(void *context)
 	case STATE_P_ON:
 		switch (ctx->to_state) {
 		case STATE_TRX_OFF:
-			tim = ktime_set(0, c->t_reset_to_off * NSEC_PER_USEC);
+			tim = c->t_reset_to_off * NSEC_PER_USEC;
 			goto change;
 		default:
 			break;
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 031093e..dbfbb33 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -99,6 +99,11 @@ struct ipvl_port {
 	int			count;
 };
 
+struct ipvl_skb_cb {
+	bool tx_pkt;
+};
+#define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0]))
+
 static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)
 {
 	return rcu_dereference(d->rx_handler_data);
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index b4e9907..83ce74a 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -198,7 +198,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 	unsigned int mac_hash;
 	int ret;
 	u8 pkt_type;
-	bool hlocal, dlocal;
+	bool tx_pkt;
 
 	__skb_queue_head_init(&list);
 
@@ -207,8 +207,11 @@ void ipvlan_process_multicast(struct work_struct *work)
 	spin_unlock_bh(&port->backlog.lock);
 
 	while ((skb = __skb_dequeue(&list)) != NULL) {
+		struct net_device *dev = skb->dev;
+		bool consumed = false;
+
 		ethh = eth_hdr(skb);
-		hlocal = ether_addr_equal(ethh->h_source, port->dev->dev_addr);
+		tx_pkt = IPVL_SKB_CB(skb)->tx_pkt;
 		mac_hash = ipvlan_mac_hash(ethh->h_dest);
 
 		if (ether_addr_equal(ethh->h_dest, port->dev->broadcast))
@@ -216,41 +219,45 @@ void ipvlan_process_multicast(struct work_struct *work)
 		else
 			pkt_type = PACKET_MULTICAST;
 
-		dlocal = false;
 		rcu_read_lock();
 		list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
-			if (hlocal && (ipvlan->dev == skb->dev)) {
-				dlocal = true;
+			if (tx_pkt && (ipvlan->dev == skb->dev))
 				continue;
-			}
 			if (!test_bit(mac_hash, ipvlan->mac_filters))
 				continue;
-
+			if (!(ipvlan->dev->flags & IFF_UP))
+				continue;
 			ret = NET_RX_DROP;
 			len = skb->len + ETH_HLEN;
 			nskb = skb_clone(skb, GFP_ATOMIC);
-			if (!nskb)
-				goto acct;
-
-			nskb->pkt_type = pkt_type;
-			nskb->dev = ipvlan->dev;
-			if (hlocal)
-				ret = dev_forward_skb(ipvlan->dev, nskb);
-			else
-				ret = netif_rx(nskb);
-acct:
+			local_bh_disable();
+			if (nskb) {
+				consumed = true;
+				nskb->pkt_type = pkt_type;
+				nskb->dev = ipvlan->dev;
+				if (tx_pkt)
+					ret = dev_forward_skb(ipvlan->dev, nskb);
+				else
+					ret = netif_rx(nskb);
+			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+			local_bh_enable();
 		}
 		rcu_read_unlock();
 
-		if (dlocal) {
+		if (tx_pkt) {
 			/* If the packet originated here, send it out. */
 			skb->dev = port->dev;
 			skb->pkt_type = pkt_type;
 			dev_queue_xmit(skb);
 		} else {
-			kfree_skb(skb);
+			if (consumed)
+				consume_skb(skb);
+			else
+				kfree_skb(skb);
 		}
+		if (dev)
+			dev_put(dev);
 	}
 }
 
@@ -470,15 +477,24 @@ static int ipvlan_process_outbound(struct sk_buff *skb)
 }
 
 static void ipvlan_multicast_enqueue(struct ipvl_port *port,
-				     struct sk_buff *skb)
+				     struct sk_buff *skb, bool tx_pkt)
 {
 	if (skb->protocol == htons(ETH_P_PAUSE)) {
 		kfree_skb(skb);
 		return;
 	}
 
+	/* Record that the deferred packet is from TX or RX path. By
+	 * looking at mac-addresses on packet will lead to erronus decisions.
+	 * (This would be true for a loopback-mode on master device or a
+	 * hair-pin mode of the switch.)
+	 */
+	IPVL_SKB_CB(skb)->tx_pkt = tx_pkt;
+
 	spin_lock(&port->backlog.lock);
 	if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
+		if (skb->dev)
+			dev_hold(skb->dev);
 		__skb_queue_tail(&port->backlog, skb);
 		spin_unlock(&port->backlog.lock);
 		schedule_work(&port->wq);
@@ -537,7 +553,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 
 	} else if (is_multicast_ether_addr(eth->h_dest)) {
 		ipvlan_skb_crossing_ns(skb, NULL);
-		ipvlan_multicast_enqueue(ipvlan->port, skb);
+		ipvlan_multicast_enqueue(ipvlan->port, skb, true);
 		return NET_XMIT_SUCCESS;
 	}
 
@@ -634,7 +650,7 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb,
 			 */
 			if (nskb) {
 				ipvlan_skb_crossing_ns(nskb, NULL);
-				ipvlan_multicast_enqueue(port, nskb);
+				ipvlan_multicast_enqueue(port, nskb, false);
 			}
 		}
 	} else {
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 693ec5b..8b0f993 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -135,6 +135,7 @@ static int ipvlan_port_create(struct net_device *dev)
 static void ipvlan_port_destroy(struct net_device *dev)
 {
 	struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+	struct sk_buff *skb;
 
 	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
 	if (port->mode == IPVLAN_MODE_L3S) {
@@ -144,7 +145,11 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	}
 	netdev_rx_handler_unregister(dev);
 	cancel_work_sync(&port->wq);
-	__skb_queue_purge(&port->backlog);
+	while ((skb = __skb_dequeue(&port->backlog)) != NULL) {
+		if (skb->dev)
+			dev_put(skb->dev);
+		kfree_skb(skb);
+	}
 	kfree(port);
 }
 
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index 7a3f990..7a20a9a 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -31,7 +31,7 @@
 #include <linux/slab.h>
 #include <linux/tty.h>
 #include <linux/init.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
 
diff --git a/drivers/net/irda/kingsun-sir.c b/drivers/net/irda/kingsun-sir.c
index fb5d162..24c0f16 100644
--- a/drivers/net/irda/kingsun-sir.c
+++ b/drivers/net/irda/kingsun-sir.c
@@ -71,7 +71,7 @@
 
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/irda/irda.h>
 #include <net/irda/wrapper.h>
diff --git a/drivers/net/irda/ks959-sir.c b/drivers/net/irda/ks959-sir.c
index 8e6e0ed..3affded 100644
--- a/drivers/net/irda/ks959-sir.c
+++ b/drivers/net/irda/ks959-sir.c
@@ -123,7 +123,7 @@
 
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/irda/irda.h>
 #include <net/irda/wrapper.h>
diff --git a/drivers/net/irda/ksdazzle-sir.c b/drivers/net/irda/ksdazzle-sir.c
index 37f23a1..741452c 100644
--- a/drivers/net/irda/ksdazzle-sir.c
+++ b/drivers/net/irda/ksdazzle-sir.c
@@ -87,7 +87,7 @@
 
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/irda/irda.h>
 #include <net/irda/wrapper.h>
diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c
index bca6a1e..6f6ed75 100644
--- a/drivers/net/irda/mcs7780.c
+++ b/drivers/net/irda/mcs7780.c
@@ -55,7 +55,7 @@
 
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/irda/irda.h>
 #include <net/irda/wrapper.h>
diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c
index a0849f4..ffedad2 100644
--- a/drivers/net/irda/vlsi_ir.c
+++ b/drivers/net/irda/vlsi_ir.c
@@ -45,7 +45,7 @@ MODULE_LICENSE("GPL");
 #include <linux/seq_file.h>
 #include <linux/math64.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 #include <net/irda/irda.h>
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 6255973..1e05b7c 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -40,7 +40,7 @@
 #include <linux/fcntl.h>
 #include <linux/in.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #include <linux/inet.h>
diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c
index 36e3e20..e28913d 100644
--- a/drivers/net/phy/davicom.c
+++ b/drivers/net/phy/davicom.c
@@ -32,7 +32,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define MII_DM9161_SCR		0x10
 #define MII_DM9161_SCR_INIT	0x0610
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 22b51f0..567280a 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -28,7 +28,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 MODULE_DESCRIPTION("ICPlus IP175C/IP101A/IP101G/IC1001 PHY drivers");
 MODULE_AUTHOR("Michael Barkowski");
diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c
index b9fde1b..8d198a1f 100644
--- a/drivers/net/phy/lxt.c
+++ b/drivers/net/phy/lxt.c
@@ -32,7 +32,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* The Level one LXT970 is used by many boards				     */
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 9c06f80..92b0838 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1187,8 +1187,8 @@ static int genphy_config_advert(struct phy_device *phydev)
  */
 static int genphy_config_eee_advert(struct phy_device *phydev)
 {
-	u32 broken = phydev->eee_broken_modes;
-	u32 old_adv, adv;
+	int broken = phydev->eee_broken_modes;
+	int old_adv, adv;
 
 	/* Nothing to disable */
 	if (!broken)
@@ -1665,7 +1665,7 @@ static void of_set_phy_supported(struct phy_device *phydev)
 static void of_set_phy_eee_broken(struct phy_device *phydev)
 {
 	struct device_node *node = phydev->mdio.dev.of_node;
-	u32 broken;
+	u32 broken = 0;
 
 	if (!IS_ENABLED(CONFIG_OF_MDIO))
 		return;
@@ -1673,8 +1673,20 @@ static void of_set_phy_eee_broken(struct phy_device *phydev)
 	if (!node)
 		return;
 
-	if (!of_property_read_u32(node, "eee-broken-modes", &broken))
-		phydev->eee_broken_modes = broken;
+	if (of_property_read_bool(node, "eee-broken-100tx"))
+		broken |= MDIO_EEE_100TX;
+	if (of_property_read_bool(node, "eee-broken-1000t"))
+		broken |= MDIO_EEE_1000T;
+	if (of_property_read_bool(node, "eee-broken-10gt"))
+		broken |= MDIO_EEE_10GT;
+	if (of_property_read_bool(node, "eee-broken-1000kx"))
+		broken |= MDIO_EEE_1000KX;
+	if (of_property_read_bool(node, "eee-broken-10gkx4"))
+		broken |= MDIO_EEE_10GKX4;
+	if (of_property_read_bool(node, "eee-broken-10gkr"))
+		broken |= MDIO_EEE_10GKR;
+
+	phydev->eee_broken_modes = broken;
 }
 
 /**
diff --git a/drivers/net/phy/qsemi.c b/drivers/net/phy/qsemi.c
index d470db8..dbef800 100644
--- a/drivers/net/phy/qsemi.c
+++ b/drivers/net/phy/qsemi.c
@@ -32,7 +32,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* ------------------------------------------------------------------------- */
 /* The Quality Semiconductor QS6612 is used on the RPX CLLF                  */
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 9c889e0..feb9569 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -34,7 +34,7 @@
 #include <linux/jiffies.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/string.h>
 
 #define PPP_VERSION	"2.4.2"
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 925d3e2..9ae5398 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -47,7 +47,7 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define PPP_VERSION	"2.4.2"
 
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index f017c72..d7e4052 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -83,7 +83,7 @@
 #include <net/netns/generic.h>
 #include <net/sock.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define PPPOE_HASH_BITS 4
 #define PPPOE_HASH_SIZE (1 << PPPOE_HASH_BITS)
diff --git a/drivers/net/ppp/pppox.c b/drivers/net/ppp/pppox.c
index b9c8be6..c0599b3 100644
--- a/drivers/net/ppp/pppox.c
+++ b/drivers/net/ppp/pppox.c
@@ -34,7 +34,7 @@
 
 #include <net/sock.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static const struct pppox_proto *pppox_protos[PX_MAX_PROTO + 1];
 
diff --git a/drivers/net/sb1000.c b/drivers/net/sb1000.c
index 8b8b532..7820fce 100644
--- a/drivers/net/sb1000.c
+++ b/drivers/net/sb1000.c
@@ -55,7 +55,7 @@ static char version[] = "sb1000.c:v1.1.2 6/01/98 (fventuri@mediaone.net)\n";
 
 #include <asm/io.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef SB1000_DEBUG
 static int sb1000_debug = SB1000_DEBUG;
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 27ed252..5782733 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -75,7 +75,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <linux/timer.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/checksum.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 7e933d8..9841f3d 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -64,7 +64,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/sched.h>
 #include <linux/string.h>
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 57e88b8..cd8e02c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -73,7 +73,7 @@
 #include <linux/uio.h>
 #include <linux/skb_array.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Uncomment to enable debugging */
 /* #define TUN_DEBUG 1 */
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index a1f2f6f..3daa41b 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -42,7 +42,7 @@
 #include <linux/crc32.h>
 #include <linux/bitops.h>
 #include <linux/gfp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #undef DEBUG
 
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 2d1a6f2..f317984 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1282,7 +1282,7 @@ static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx)
 	/* start timer, if not already started */
 	if (!(hrtimer_active(&ctx->tx_timer) || atomic_read(&ctx->stop)))
 		hrtimer_start(&ctx->tx_timer,
-				ktime_set(0, ctx->timer_interval),
+				ctx->timer_interval,
 				HRTIMER_MODE_REL);
 }
 
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index 338aed5..876f02f 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -54,7 +54,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/wait.h>
 #include <linux/firmware.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 #undef DEBUG
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 399f7ee..24e803f 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -42,7 +42,7 @@
 #include <linux/usb.h>
 #include <linux/module.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "pegasus.h"
 
 /*
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 93a1bda..95b7bd0 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -14,7 +14,7 @@
 #include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/usb.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Version Information */
 #define DRIVER_VERSION "v0.6.2 (2004/08/27)"
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 08327e0..4a10500 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -333,9 +333,9 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 static void virtnet_xdp_xmit(struct virtnet_info *vi,
 			     struct receive_queue *rq,
 			     struct send_queue *sq,
-			     struct xdp_buff *xdp)
+			     struct xdp_buff *xdp,
+			     void *data)
 {
-	struct page *page = virt_to_head_page(xdp->data);
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	unsigned int num_sg, len;
 	void *xdp_sent;
@@ -343,32 +343,46 @@ static void virtnet_xdp_xmit(struct virtnet_info *vi,
 
 	/* Free up any pending old buffers before queueing new ones. */
 	while ((xdp_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		struct page *sent_page = virt_to_head_page(xdp_sent);
+		if (vi->mergeable_rx_bufs) {
+			struct page *sent_page = virt_to_head_page(xdp_sent);
 
-		if (vi->mergeable_rx_bufs)
 			put_page(sent_page);
-		else
-			give_pages(rq, sent_page);
+		} else { /* small buffer */
+			struct sk_buff *skb = xdp_sent;
+
+			kfree_skb(skb);
+		}
 	}
 
-	/* Zero header and leave csum up to XDP layers */
-	hdr = xdp->data;
-	memset(hdr, 0, vi->hdr_len);
+	if (vi->mergeable_rx_bufs) {
+		/* Zero header and leave csum up to XDP layers */
+		hdr = xdp->data;
+		memset(hdr, 0, vi->hdr_len);
 
-	num_sg = 1;
-	sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data);
+		num_sg = 1;
+		sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data);
+	} else { /* small buffer */
+		struct sk_buff *skb = data;
+
+		/* Zero header and leave csum up to XDP layers */
+		hdr = skb_vnet_hdr(skb);
+		memset(hdr, 0, vi->hdr_len);
+
+		num_sg = 2;
+		sg_init_table(sq->sg, 2);
+		sg_set_buf(sq->sg, hdr, vi->hdr_len);
+		skb_to_sgvec(skb, sq->sg + 1, 0, skb->len);
+	}
 	err = virtqueue_add_outbuf(sq->vq, sq->sg, num_sg,
-				   xdp->data, GFP_ATOMIC);
+				   data, GFP_ATOMIC);
 	if (unlikely(err)) {
-		if (vi->mergeable_rx_bufs)
+		if (vi->mergeable_rx_bufs) {
+			struct page *page = virt_to_head_page(xdp->data);
+
 			put_page(page);
-		else
-			give_pages(rq, page);
+		} else /* small buffer */
+			kfree_skb(data);
 		return; // On error abort to avoid unnecessary kick
-	} else if (!vi->mergeable_rx_bufs) {
-		/* If not mergeable bufs must be big packets so cleanup pages */
-		give_pages(rq, (struct page *)page->private);
-		page->private = 0;
 	}
 
 	virtqueue_kick(sq->vq);
@@ -377,23 +391,26 @@ static void virtnet_xdp_xmit(struct virtnet_info *vi,
 static u32 do_xdp_prog(struct virtnet_info *vi,
 		       struct receive_queue *rq,
 		       struct bpf_prog *xdp_prog,
-		       struct page *page, int offset, int len)
+		       void *data, int len)
 {
 	int hdr_padded_len;
 	struct xdp_buff xdp;
+	void *buf;
 	unsigned int qp;
 	u32 act;
-	u8 *buf;
 
-	buf = page_address(page) + offset;
-
-	if (vi->mergeable_rx_bufs)
+	if (vi->mergeable_rx_bufs) {
 		hdr_padded_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
-	else
-		hdr_padded_len = sizeof(struct padded_vnet_hdr);
+		xdp.data = data + hdr_padded_len;
+		xdp.data_end = xdp.data + (len - vi->hdr_len);
+		buf = data;
+	} else { /* small buffers */
+		struct sk_buff *skb = data;
 
-	xdp.data = buf + hdr_padded_len;
-	xdp.data_end = xdp.data + (len - vi->hdr_len);
+		xdp.data = skb->data;
+		xdp.data_end = xdp.data + len;
+		buf = skb->data;
+	}
 
 	act = bpf_prog_run_xdp(xdp_prog, &xdp);
 	switch (act) {
@@ -403,8 +420,8 @@ static u32 do_xdp_prog(struct virtnet_info *vi,
 		qp = vi->curr_queue_pairs -
 			vi->xdp_queue_pairs +
 			smp_processor_id();
-		xdp.data = buf + (vi->mergeable_rx_bufs ? 0 : 4);
-		virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp);
+		xdp.data = buf;
+		virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp, data);
 		return XDP_TX;
 	default:
 		bpf_warn_invalid_xdp_action(act);
@@ -414,26 +431,17 @@ static u32 do_xdp_prog(struct virtnet_info *vi,
 	}
 }
 
-static struct sk_buff *receive_small(struct virtnet_info *vi, void *buf, unsigned int len)
+static struct sk_buff *receive_small(struct net_device *dev,
+				     struct virtnet_info *vi,
+				     struct receive_queue *rq,
+				     void *buf, unsigned int len)
 {
 	struct sk_buff * skb = buf;
+	struct bpf_prog *xdp_prog;
 
 	len -= vi->hdr_len;
 	skb_trim(skb, len);
 
-	return skb;
-}
-
-static struct sk_buff *receive_big(struct net_device *dev,
-				   struct virtnet_info *vi,
-				   struct receive_queue *rq,
-				   void *buf,
-				   unsigned int len)
-{
-	struct bpf_prog *xdp_prog;
-	struct page *page = buf;
-	struct sk_buff *skb;
-
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -442,7 +450,7 @@ static struct sk_buff *receive_big(struct net_device *dev,
 
 		if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
 			goto err_xdp;
-		act = do_xdp_prog(vi, rq, xdp_prog, page, 0, len);
+		act = do_xdp_prog(vi, rq, xdp_prog, skb, len);
 		switch (act) {
 		case XDP_PASS:
 			break;
@@ -456,18 +464,33 @@ static struct sk_buff *receive_big(struct net_device *dev,
 	}
 	rcu_read_unlock();
 
-	skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+	return skb;
+
+err_xdp:
+	rcu_read_unlock();
+	dev->stats.rx_dropped++;
+	kfree_skb(skb);
+xdp_xmit:
+	return NULL;
+}
+
+static struct sk_buff *receive_big(struct net_device *dev,
+				   struct virtnet_info *vi,
+				   struct receive_queue *rq,
+				   void *buf,
+				   unsigned int len)
+{
+	struct page *page = buf;
+	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+
 	if (unlikely(!skb))
 		goto err;
 
 	return skb;
 
-err_xdp:
-	rcu_read_unlock();
 err:
 	dev->stats.rx_dropped++;
 	give_pages(rq, page);
-xdp_xmit:
 	return NULL;
 }
 
@@ -483,7 +506,7 @@ static struct sk_buff *receive_big(struct net_device *dev,
  * anymore.
  */
 static struct page *xdp_linearize_page(struct receive_queue *rq,
-				       u16 num_buf,
+				       u16 *num_buf,
 				       struct page *p,
 				       int offset,
 				       unsigned int *len)
@@ -497,7 +520,7 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 	memcpy(page_address(page) + page_off, page_address(p) + offset, *len);
 	page_off += *len;
 
-	while (--num_buf) {
+	while (--*num_buf) {
 		unsigned int buflen;
 		unsigned long ctx;
 		void *buf;
@@ -507,19 +530,22 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 		if (unlikely(!ctx))
 			goto err_buf;
 
-		/* guard against a misconfigured or uncooperative backend that
-		 * is sending packet larger than the MTU.
-		 */
-		if ((page_off + buflen) > PAGE_SIZE)
-			goto err_buf;
-
 		buf = mergeable_ctx_to_buf_address(ctx);
 		p = virt_to_head_page(buf);
 		off = buf - page_address(p);
 
+		/* guard against a misconfigured or uncooperative backend that
+		 * is sending packet larger than the MTU.
+		 */
+		if ((page_off + buflen) > PAGE_SIZE) {
+			put_page(p);
+			goto err_buf;
+		}
+
 		memcpy(page_address(page) + page_off,
 		       page_address(p) + off, buflen);
 		page_off += buflen;
+		put_page(p);
 	}
 
 	*len = page_off;
@@ -552,16 +578,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		struct page *xdp_page;
 		u32 act;
 
-		/* No known backend devices should send packets with
-		 * more than a single buffer when XDP conditions are
-		 * met. However it is not strictly illegal so the case
-		 * is handled as an exception and a warning is thrown.
-		 */
+		/* This happens when rx buffer size is underestimated */
 		if (unlikely(num_buf > 1)) {
-			bpf_warn_invalid_xdp_buffer();
-
 			/* linearize data for XDP */
-			xdp_page = xdp_linearize_page(rq, num_buf,
+			xdp_page = xdp_linearize_page(rq, &num_buf,
 						      page, offset, &len);
 			if (!xdp_page)
 				goto err_xdp;
@@ -575,16 +595,25 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		 * the receive path after XDP is loaded. In practice I
 		 * was not able to create this condition.
 		 */
-		if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
+		if (unlikely(hdr->hdr.gso_type))
 			goto err_xdp;
 
-		act = do_xdp_prog(vi, rq, xdp_prog, page, offset, len);
+		act = do_xdp_prog(vi, rq, xdp_prog,
+				  page_address(xdp_page) + offset, len);
 		switch (act) {
 		case XDP_PASS:
-			if (unlikely(xdp_page != page))
-				__free_pages(xdp_page, 0);
+			/* We can only create skb based on xdp_page. */
+			if (unlikely(xdp_page != page)) {
+				rcu_read_unlock();
+				put_page(page);
+				head_skb = page_to_skb(vi, rq, xdp_page,
+						       0, len, PAGE_SIZE);
+				ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+				return head_skb;
+			}
 			break;
 		case XDP_TX:
+			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
 			if (unlikely(xdp_page != page))
 				goto err_xdp;
 			rcu_read_unlock();
@@ -593,6 +622,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		default:
 			if (unlikely(xdp_page != page))
 				__free_pages(xdp_page, 0);
+			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
 			goto err_xdp;
 		}
 	}
@@ -704,7 +734,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	else if (vi->big_packets)
 		skb = receive_big(dev, vi, rq, buf, len);
 	else
-		skb = receive_small(vi, buf, len);
+		skb = receive_small(dev, vi, rq, buf, len);
 
 	if (unlikely(!skb))
 		return;
@@ -1678,7 +1708,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 	int i, err;
 
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
-	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6)) {
+	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
+	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
+	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO)) {
 		netdev_warn(dev, "can't set XDP while host is implementing LRO, disable LRO first\n");
 		return -EOPNOTSUPP;
 	}
@@ -2452,13 +2484,13 @@ static __init int virtio_net_driver_init(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "AP_VIRT_NET_ONLINE",
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "virtio/net:online",
 				      virtnet_cpu_online,
 				      virtnet_cpu_down_prep);
 	if (ret < 0)
 		goto out;
 	virtionet_online = ret;
-	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "VIRT_NET_DEAD",
+	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "virtio/net:dead",
 				      NULL, virtnet_cpu_dead);
 	if (ret)
 		goto err_dead;
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index ae6ecf4..65ee2a6 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -52,7 +52,7 @@
 
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static const char version[] = "DLCI driver v0.35, 4 Jan 1997, mike.mclagan@linux.org";
 
diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c
index 7351e54..799830f 100644
--- a/drivers/net/wan/dscc4.c
+++ b/drivers/net/wan/dscc4.c
@@ -95,7 +95,7 @@
 
 #include <asm/cache.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 03696d3..33265eb 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -30,7 +30,7 @@
 #include <linux/if.h>
 #include <linux/hdlc.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "farsync.h"
 
diff --git a/drivers/net/wan/hd64570.c b/drivers/net/wan/hd64570.c
index dc334c8..166696d 100644
--- a/drivers/net/wan/hd64570.c
+++ b/drivers/net/wan/hd64570.c
@@ -39,7 +39,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "hd64570.h"
 
 #define get_msci(port)	  (phy_node(port) ?   MSCI1_OFFSET :   MSCI0_OFFSET)
diff --git a/drivers/net/wan/hd64572.c b/drivers/net/wan/hd64572.c
index e92ecf1..7ef49da 100644
--- a/drivers/net/wan/hd64572.c
+++ b/drivers/net/wan/hd64572.c
@@ -39,7 +39,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "hd64572.h"
 
 #define NAPI_WEIGHT		16
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 6676607..9df9ed6 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -35,7 +35,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index 001b779..4698450 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -59,7 +59,7 @@
 #include <asm/processor.h>             /* Processor type for cache alignment. */
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 //#include <asm/spinlock.h>
 
 #define DRIVER_MAJOR_VERSION     1
diff --git a/drivers/net/wan/lmc/lmc_media.c b/drivers/net/wan/lmc/lmc_media.c
index ff2e4a5..cffe23b 100644
--- a/drivers/net/wan/lmc/lmc_media.c
+++ b/drivers/net/wan/lmc/lmc_media.c
@@ -19,7 +19,7 @@
 #include <asm/io.h>
 #include <asm/dma.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "lmc.h"
 #include "lmc_var.h"
diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c
index 3f83be9..3ca3419 100644
--- a/drivers/net/wan/sbni.c
+++ b/drivers/net/wan/sbni.c
@@ -63,7 +63,7 @@
 #include <asm/types.h>
 #include <asm/byteorder.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "sbni.h"
 
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index 421ac5f..236c625 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -56,7 +56,7 @@
 
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static const char* version = "SDLA driver v0.30, 12 Sep 1996, mike.mclagan@linux.org";
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index c893314..50d6ee6 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -8271,7 +8271,7 @@ void ath10k_wmi_free_host_mem(struct ath10k *ar)
 		dma_unmap_single(ar->dev,
 				 ar->wmi.mem_chunks[i].paddr,
 				 ar->wmi.mem_chunks[i].len,
-				 DMA_TO_DEVICE);
+				 DMA_BIDIRECTIONAL);
 		kfree(ar->wmi.mem_chunks[i].vaddr);
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 486afa9..4e2f3ac 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -2713,7 +2713,7 @@ void ath_tx_edma_tasklet(struct ath_softc *sc)
 		fifo_list = &txq->txq_fifo[txq->txq_tailidx];
 		if (list_empty(fifo_list)) {
 			ath_txq_unlock(sc, txq);
-			return;
+			break;
 		}
 
 		bf = list_first_entry(fifo_list, struct ath_buf, list);
diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index eb92d5a..e12f623 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -48,7 +48,7 @@
 #include <linux/timer.h>
 #include <asm/byteorder.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index ccae3bb..7ffc4ab 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -6868,7 +6868,7 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr,
 
 	err = brcmf_p2p_attach(cfg, p2pdev_forced);
 	if (err) {
-		brcmf_err("P2P initilisation failed (%d)\n", err);
+		brcmf_err("P2P initialisation failed (%d)\n", err);
 		goto wiphy_unreg_out;
 	}
 	err = brcmf_btcoex_attach(cfg);
@@ -6893,7 +6893,7 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr,
 	err = brcmf_fweh_activate_events(ifp);
 	if (err) {
 		brcmf_err("FWEH activation failed (%d)\n", err);
-		goto wiphy_unreg_out;
+		goto detach;
 	}
 
 	/* Fill in some of the advertised nl80211 supported features */
@@ -6908,6 +6908,9 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr,
 
 	return cfg;
 
+detach:
+	brcmf_btcoex_detach(cfg);
+	brcmf_p2p_detach(&cfg->p2p);
 wiphy_unreg_out:
 	wiphy_unregister(cfg->wiphy);
 priv_out:
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c
index f273cab..9a25e79 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c
@@ -137,6 +137,7 @@ static int brcmf_pno_add_ssid(struct brcmf_if *ifp, struct cfg80211_ssid *ssid,
 	pfn.wpa_auth = cpu_to_le32(BRCMF_PNO_WPA_AUTH_ANY);
 	pfn.wsec = cpu_to_le32(0);
 	pfn.infra = cpu_to_le32(1);
+	pfn.flags = 0;
 	if (active)
 		pfn.flags = cpu_to_le32(1 << BRCMF_PNO_HIDDEN_BIT);
 	pfn.ssid.SSID_len = cpu_to_le32(ssid->ssid_len);
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index 6417609..356aba9 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -148,7 +148,7 @@ that only one external action is invoked at a time.
 #include <linux/dma-mapping.h>
 #include <linux/proc_fs.h>
 #include <linux/skbuff.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_geo.c b/drivers/net/wireless/intel/ipw2x00/libipw_geo.c
index 218f2a3..ce7eda2 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_geo.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_geo.c
@@ -38,7 +38,7 @@
 #include <linux/types.h>
 #include <linux/wireless.h>
 #include <linux/etherdevice.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "libipw.h"
 
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_module.c b/drivers/net/wireless/intel/ipw2x00/libipw_module.c
index 2332075..c58c5b2 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_module.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_module.c
@@ -46,7 +46,7 @@
 #include <linux/types.h>
 #include <linux/wireless.h>
 #include <linux/etherdevice.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/net_namespace.h>
 #include <net/arp.h>
 
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_rx.c b/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
index 1c1ec7b..6df19f0 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
@@ -29,7 +29,7 @@
 #include <linux/types.h>
 #include <linux/wireless.h>
 #include <linux/etherdevice.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/ctype.h>
 
 #include <net/lib80211.h>
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_tx.c b/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
index e8c0398..048f1e3 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_tx.c
@@ -39,7 +39,7 @@
 #include <linux/types.h>
 #include <linux/wireless.h>
 #include <linux/etherdevice.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "libipw.h"
 
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index a8a9bd8..544ef7a 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -32,7 +32,7 @@
 
 
 #include <asm/delay.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/slab.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/wireless/intersil/hostap/hostap_main.c b/drivers/net/wireless/intersil/hostap/hostap_main.c
index 1a16b8c..544fc09 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_main.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_main.c
@@ -27,7 +27,7 @@
 #include <net/net_namespace.h>
 #include <net/iw_handler.h>
 #include <net/lib80211.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "hostap_wlan.h"
 #include "hostap_80211.h"
diff --git a/drivers/net/wireless/intersil/prism54/isl_38xx.c b/drivers/net/wireless/intersil/prism54/isl_38xx.c
index 6700387..ce9d4db 100644
--- a/drivers/net/wireless/intersil/prism54/isl_38xx.c
+++ b/drivers/net/wireless/intersil/prism54/isl_38xx.c
@@ -21,7 +21,7 @@
 #include <linux/delay.h>
 #include <linux/ktime.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 #include "prismcompat.h"
diff --git a/drivers/net/wireless/intersil/prism54/isl_ioctl.c b/drivers/net/wireless/intersil/prism54/isl_ioctl.c
index 48e8a97..334717b0 100644
--- a/drivers/net/wireless/intersil/prism54/isl_ioctl.c
+++ b/drivers/net/wireless/intersil/prism54/isl_ioctl.c
@@ -26,7 +26,7 @@
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "prismcompat.h"
 #include "isl_ioctl.h"
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
index 9f61293..f38c440 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c
@@ -177,7 +177,7 @@ static bool rt2800usb_tx_sta_fifo_read_completed(struct rt2x00_dev *rt2x00dev,
 	if (rt2800usb_txstatus_pending(rt2x00dev)) {
 		/* Read register after 1 ms */
 		hrtimer_start(&rt2x00dev->txstatus_timer,
-			      ktime_set(0, TXSTATUS_READ_INTERVAL),
+			      TXSTATUS_READ_INTERVAL,
 			      HRTIMER_MODE_REL);
 		return false;
 	}
@@ -204,7 +204,7 @@ static void rt2800usb_async_read_tx_status(struct rt2x00_dev *rt2x00dev)
 
 	/* Read TX_STA_FIFO register after 2 ms */
 	hrtimer_start(&rt2x00dev->txstatus_timer,
-		      ktime_set(0, 2*TXSTATUS_READ_INTERVAL),
+		      2 * TXSTATUS_READ_INTERVAL,
 		      HRTIMER_MODE_REL);
 }
 
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 4fdc722..b944794 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -53,7 +53,7 @@
 
 #include <asm/io.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Warning : these stuff will slow down the driver... */
 #define WIRELESS_SPY		/* Enable spying addresses */
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index 2caa4ad..ded1493 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -1829,7 +1829,8 @@ bool rtl_cmd_send_packet(struct ieee80211_hw *hw, struct sk_buff *skb)
 
 	spin_lock_irqsave(&rtlpriv->locks.irq_th_lock, flags);
 	pskb = __skb_dequeue(&ring->queue);
-	dev_kfree_skb_irq(pskb);
+	if (pskb)
+		dev_kfree_skb_irq(pskb);
 
 	/*this is wrong, fill_tx_cmddesc needs update*/
 	pdesc = &ring->desc[0];
diff --git a/drivers/net/wireless/wl3501_cs.c b/drivers/net/wireless/wl3501_cs.c
index d9d29ab..acec0d9 100644
--- a/drivers/net/wireless/wl3501_cs.c
+++ b/drivers/net/wireless/wl3501_cs.c
@@ -51,7 +51,7 @@
 #include <pcmcia/ds.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "wl3501.h"
 
diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c
index 6ccba0d..019a158 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.c
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.c
@@ -138,11 +138,11 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
 	base_addr = pci_resource_start(ndev->ntb.pdev, bar);
 
 	if (bar != 1) {
-		xlat_reg = AMD_BAR23XLAT_OFFSET + ((bar - 2) << 3);
-		limit_reg = AMD_BAR23LMT_OFFSET + ((bar - 2) << 3);
+		xlat_reg = AMD_BAR23XLAT_OFFSET + ((bar - 2) << 2);
+		limit_reg = AMD_BAR23LMT_OFFSET + ((bar - 2) << 2);
 
 		/* Set the limit if supported */
-		limit = base_addr + size;
+		limit = size;
 
 		/* set and verify setting the translation address */
 		write64(addr, peer_mmio + xlat_reg);
@@ -164,14 +164,8 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx,
 		xlat_reg = AMD_BAR1XLAT_OFFSET;
 		limit_reg = AMD_BAR1LMT_OFFSET;
 
-		/* split bar addr range must all be 32 bit */
-		if (addr & (~0ull << 32))
-			return -EINVAL;
-		if ((addr + size) & (~0ull << 32))
-			return -EINVAL;
-
 		/* Set the limit if supported */
-		limit = base_addr + size;
+		limit = size;
 
 		/* set and verify setting the translation address */
 		write64(addr, peer_mmio + xlat_reg);
@@ -199,6 +193,11 @@ static int amd_link_is_up(struct amd_ntb_dev *ndev)
 	if (!ndev->peer_sta)
 		return NTB_LNK_STA_ACTIVE(ndev->cntl_sta);
 
+	if (ndev->peer_sta & AMD_LINK_UP_EVENT) {
+		ndev->peer_sta = 0;
+		return 1;
+	}
+
 	/* If peer_sta is reset or D0 event, the ISR has
 	 * started a timer to check link status of hardware.
 	 * So here just clear status bit. And if peer_sta is
@@ -207,7 +206,7 @@ static int amd_link_is_up(struct amd_ntb_dev *ndev)
 	 */
 	if (ndev->peer_sta & AMD_PEER_RESET_EVENT)
 		ndev->peer_sta &= ~AMD_PEER_RESET_EVENT;
-	else if (ndev->peer_sta & AMD_PEER_D0_EVENT)
+	else if (ndev->peer_sta & (AMD_PEER_D0_EVENT | AMD_LINK_DOWN_EVENT))
 		ndev->peer_sta = 0;
 
 	return 0;
@@ -491,6 +490,8 @@ static void amd_handle_event(struct amd_ntb_dev *ndev, int vec)
 		break;
 	case AMD_PEER_D3_EVENT:
 	case AMD_PEER_PMETO_EVENT:
+	case AMD_LINK_UP_EVENT:
+	case AMD_LINK_DOWN_EVENT:
 		amd_ack_smu(ndev, status);
 
 		/* link down */
@@ -598,7 +599,7 @@ static int ndev_init_isr(struct amd_ntb_dev *ndev,
 
 err_msix_request:
 	while (i-- > 0)
-		free_irq(ndev->msix[i].vector, ndev);
+		free_irq(ndev->msix[i].vector, &ndev->vec[i]);
 	pci_disable_msix(pdev);
 err_msix_enable:
 	kfree(ndev->msix);
diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.h b/drivers/ntb/hw/amd/ntb_hw_amd.h
index 2eac3cd..13d73ed 100644
--- a/drivers/ntb/hw/amd/ntb_hw_amd.h
+++ b/drivers/ntb/hw/amd/ntb_hw_amd.h
@@ -148,9 +148,12 @@ enum {
 	AMD_PEER_D3_EVENT	= BIT(2),
 	AMD_PEER_PMETO_EVENT	= BIT(3),
 	AMD_PEER_D0_EVENT	= BIT(4),
+	AMD_LINK_UP_EVENT	= BIT(5),
+	AMD_LINK_DOWN_EVENT	= BIT(6),
 	AMD_EVENT_INTMASK	= (AMD_PEER_FLUSH_EVENT |
 				AMD_PEER_RESET_EVENT | AMD_PEER_D3_EVENT |
-				AMD_PEER_PMETO_EVENT | AMD_PEER_D0_EVENT),
+				AMD_PEER_PMETO_EVENT | AMD_PEER_D0_EVENT |
+				AMD_LINK_UP_EVENT | AMD_LINK_DOWN_EVENT),
 
 	AMD_PMESTAT_OFFSET	= 0x480,
 	AMD_PMSGTRIG_OFFSET	= 0x490,
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
index 7310a26..eca9688 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.c
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -86,7 +86,12 @@ static const struct intel_ntb_xlat_reg xeon_pri_xlat;
 static const struct intel_ntb_xlat_reg xeon_sec_xlat;
 static struct intel_b2b_addr xeon_b2b_usd_addr;
 static struct intel_b2b_addr xeon_b2b_dsd_addr;
+static const struct intel_ntb_reg skx_reg;
+static const struct intel_ntb_alt_reg skx_pri_reg;
+static const struct intel_ntb_alt_reg skx_b2b_reg;
+static const struct intel_ntb_xlat_reg skx_sec_xlat;
 static const struct ntb_dev_ops intel_ntb_ops;
+static const struct ntb_dev_ops intel_ntb3_ops;
 
 static const struct file_operations intel_ntb_debugfs_info;
 static struct dentry *debugfs_dir;
@@ -145,6 +150,9 @@ module_param_named(xeon_b2b_dsd_bar5_addr32,
 MODULE_PARM_DESC(xeon_b2b_dsd_bar5_addr32,
 		 "XEON B2B DSD split-BAR 5 32-bit address");
 
+static inline enum ntb_topo xeon_ppd_topo(struct intel_ntb_dev *ndev, u8 ppd);
+static int xeon_init_isr(struct intel_ntb_dev *ndev);
+
 #ifndef ioread64
 #ifdef readq
 #define ioread64 readq
@@ -206,6 +214,14 @@ static inline int pdev_is_xeon(struct pci_dev *pdev)
 	return 0;
 }
 
+static inline int pdev_is_skx_xeon(struct pci_dev *pdev)
+{
+	if (pdev->device == PCI_DEVICE_ID_INTEL_NTB_B2B_SKX)
+		return 1;
+
+	return 0;
+}
+
 static inline void ndev_reset_unsafe_flags(struct intel_ntb_dev *ndev)
 {
 	ndev->unsafe_flags = 0;
@@ -390,6 +406,9 @@ static irqreturn_t ndev_interrupt(struct intel_ntb_dev *ndev, int vec)
 
 	vec_mask = ndev_vec_mask(ndev, vec);
 
+	if ((ndev->hwerr_flags & NTB_HWERR_MSIX_VECTOR32_BAD) && (vec == 31))
+		vec_mask |= ndev->db_link_mask;
+
 	dev_dbg(ndev_dev(ndev), "vec %d vec_mask %llx\n", vec, vec_mask);
 
 	ndev->last_ts = jiffies;
@@ -409,6 +428,9 @@ static irqreturn_t ndev_vec_isr(int irq, void *dev)
 {
 	struct intel_ntb_vec *nvec = dev;
 
+	dev_dbg(ndev_dev(nvec->ndev), "irq: %d  nvec->num: %d\n",
+		irq, nvec->num);
+
 	return ndev_interrupt(nvec->ndev, nvec->num);
 }
 
@@ -465,14 +487,14 @@ static int ndev_init_isr(struct intel_ntb_dev *ndev,
 			goto err_msix_request;
 	}
 
-	dev_dbg(ndev_dev(ndev), "Using msix interrupts\n");
+	dev_dbg(ndev_dev(ndev), "Using %d msix interrupts\n", msix_count);
 	ndev->db_vec_count = msix_count;
 	ndev->db_vec_shift = msix_shift;
 	return 0;
 
 err_msix_request:
 	while (i-- > 0)
-		free_irq(ndev->msix[i].vector, ndev);
+		free_irq(ndev->msix[i].vector, &ndev->vec[i]);
 	pci_disable_msix(pdev);
 err_msix_enable:
 	kfree(ndev->msix);
@@ -547,8 +569,171 @@ static void ndev_deinit_isr(struct intel_ntb_dev *ndev)
 	}
 }
 
-static ssize_t ndev_debugfs_read(struct file *filp, char __user *ubuf,
-				 size_t count, loff_t *offp)
+static ssize_t ndev_ntb3_debugfs_read(struct file *filp, char __user *ubuf,
+				      size_t count, loff_t *offp)
+{
+	struct intel_ntb_dev *ndev;
+	void __iomem *mmio;
+	char *buf;
+	size_t buf_size;
+	ssize_t ret, off;
+	union { u64 v64; u32 v32; u16 v16; } u;
+
+	ndev = filp->private_data;
+	mmio = ndev->self_mmio;
+
+	buf_size = min(count, 0x800ul);
+
+	buf = kmalloc(buf_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	off = 0;
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "NTB Device Information:\n");
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "Connection Topology -\t%s\n",
+			 ntb_topo_string(ndev->ntb.topo));
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "NTB CTL -\t\t%#06x\n", ndev->ntb_ctl);
+	off += scnprintf(buf + off, buf_size - off,
+			 "LNK STA -\t\t%#06x\n", ndev->lnk_sta);
+
+	if (!ndev->reg->link_is_up(ndev))
+		off += scnprintf(buf + off, buf_size - off,
+				 "Link Status -\t\tDown\n");
+	else {
+		off += scnprintf(buf + off, buf_size - off,
+				 "Link Status -\t\tUp\n");
+		off += scnprintf(buf + off, buf_size - off,
+				 "Link Speed -\t\tPCI-E Gen %u\n",
+				 NTB_LNK_STA_SPEED(ndev->lnk_sta));
+		off += scnprintf(buf + off, buf_size - off,
+				 "Link Width -\t\tx%u\n",
+				 NTB_LNK_STA_WIDTH(ndev->lnk_sta));
+	}
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "Memory Window Count -\t%u\n", ndev->mw_count);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Scratchpad Count -\t%u\n", ndev->spad_count);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Count -\t%u\n", ndev->db_count);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Vector Count -\t%u\n", ndev->db_vec_count);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Vector Shift -\t%u\n", ndev->db_vec_shift);
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Valid Mask -\t%#llx\n", ndev->db_valid_mask);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Link Mask -\t%#llx\n", ndev->db_link_mask);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Mask Cached -\t%#llx\n", ndev->db_mask);
+
+	u.v64 = ndev_db_read(ndev, mmio + ndev->self_reg->db_mask);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Mask -\t\t%#llx\n", u.v64);
+
+	u.v64 = ndev_db_read(ndev, mmio + ndev->self_reg->db_bell);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Doorbell Bell -\t\t%#llx\n", u.v64);
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "\nNTB Incoming XLAT:\n");
+
+	u.v64 = ioread64(mmio + SKX_IMBAR1XBASE_OFFSET);
+	off += scnprintf(buf + off, buf_size - off,
+			 "IMBAR1XBASE -\t\t%#018llx\n", u.v64);
+
+	u.v64 = ioread64(mmio + SKX_IMBAR2XBASE_OFFSET);
+	off += scnprintf(buf + off, buf_size - off,
+			 "IMBAR2XBASE -\t\t%#018llx\n", u.v64);
+
+	u.v64 = ioread64(mmio + SKX_IMBAR1XLMT_OFFSET);
+	off += scnprintf(buf + off, buf_size - off,
+			 "IMBAR1XLMT -\t\t\t%#018llx\n", u.v64);
+
+	u.v64 = ioread64(mmio + SKX_IMBAR2XLMT_OFFSET);
+	off += scnprintf(buf + off, buf_size - off,
+			 "IMBAR2XLMT -\t\t\t%#018llx\n", u.v64);
+
+	if (ntb_topo_is_b2b(ndev->ntb.topo)) {
+		off += scnprintf(buf + off, buf_size - off,
+				 "\nNTB Outgoing B2B XLAT:\n");
+
+		u.v64 = ioread64(mmio + SKX_EMBAR1XBASE_OFFSET);
+		off += scnprintf(buf + off, buf_size - off,
+				 "EMBAR1XBASE -\t\t%#018llx\n", u.v64);
+
+		u.v64 = ioread64(mmio + SKX_EMBAR2XBASE_OFFSET);
+		off += scnprintf(buf + off, buf_size - off,
+				 "EMBAR2XBASE -\t\t%#018llx\n", u.v64);
+
+		u.v64 = ioread64(mmio + SKX_EMBAR1XLMT_OFFSET);
+		off += scnprintf(buf + off, buf_size - off,
+				 "EMBAR1XLMT -\t\t%#018llx\n", u.v64);
+
+		u.v64 = ioread64(mmio + SKX_EMBAR2XLMT_OFFSET);
+		off += scnprintf(buf + off, buf_size - off,
+				 "EMBAR2XLMT -\t\t%#018llx\n", u.v64);
+
+		off += scnprintf(buf + off, buf_size - off,
+				 "\nNTB Secondary BAR:\n");
+
+		u.v64 = ioread64(mmio + SKX_EMBAR0_OFFSET);
+		off += scnprintf(buf + off, buf_size - off,
+				 "EMBAR0 -\t\t%#018llx\n", u.v64);
+
+		u.v64 = ioread64(mmio + SKX_EMBAR1_OFFSET);
+		off += scnprintf(buf + off, buf_size - off,
+				 "EMBAR1 -\t\t%#018llx\n", u.v64);
+
+		u.v64 = ioread64(mmio + SKX_EMBAR2_OFFSET);
+		off += scnprintf(buf + off, buf_size - off,
+				 "EMBAR2 -\t\t%#018llx\n", u.v64);
+	}
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "\nNTB Statistics:\n");
+
+	u.v16 = ioread16(mmio + SKX_USMEMMISS_OFFSET);
+	off += scnprintf(buf + off, buf_size - off,
+			 "Upstream Memory Miss -\t%u\n", u.v16);
+
+	off += scnprintf(buf + off, buf_size - off,
+			 "\nNTB Hardware Errors:\n");
+
+	if (!pci_read_config_word(ndev->ntb.pdev,
+				  SKX_DEVSTS_OFFSET, &u.v16))
+		off += scnprintf(buf + off, buf_size - off,
+				 "DEVSTS -\t\t%#06x\n", u.v16);
+
+	if (!pci_read_config_word(ndev->ntb.pdev,
+				  SKX_LINK_STATUS_OFFSET, &u.v16))
+		off += scnprintf(buf + off, buf_size - off,
+				 "LNKSTS -\t\t%#06x\n", u.v16);
+
+	if (!pci_read_config_dword(ndev->ntb.pdev,
+				   SKX_UNCERRSTS_OFFSET, &u.v32))
+		off += scnprintf(buf + off, buf_size - off,
+				 "UNCERRSTS -\t\t%#06x\n", u.v32);
+
+	if (!pci_read_config_dword(ndev->ntb.pdev,
+				   SKX_CORERRSTS_OFFSET, &u.v32))
+		off += scnprintf(buf + off, buf_size - off,
+				 "CORERRSTS -\t\t%#06x\n", u.v32);
+
+	ret = simple_read_from_buffer(ubuf, count, offp, buf, off);
+	kfree(buf);
+	return ret;
+}
+
+static ssize_t ndev_ntb_debugfs_read(struct file *filp, char __user *ubuf,
+				     size_t count, loff_t *offp)
 {
 	struct intel_ntb_dev *ndev;
 	struct pci_dev *pdev;
@@ -813,6 +998,20 @@ static ssize_t ndev_debugfs_read(struct file *filp, char __user *ubuf,
 	return ret;
 }
 
+static ssize_t ndev_debugfs_read(struct file *filp, char __user *ubuf,
+				 size_t count, loff_t *offp)
+{
+	struct intel_ntb_dev *ndev = filp->private_data;
+
+	if (pdev_is_xeon(ndev->ntb.pdev) ||
+	    pdev_is_atom(ndev->ntb.pdev))
+		return ndev_ntb_debugfs_read(filp, ubuf, count, offp);
+	else if (pdev_is_skx_xeon(ndev->ntb.pdev))
+		return ndev_ntb3_debugfs_read(filp, ubuf, count, offp);
+
+	return -ENXIO;
+}
+
 static void ndev_init_debugfs(struct intel_ntb_dev *ndev)
 {
 	if (!debugfs_dir) {
@@ -1428,6 +1627,383 @@ static void atom_deinit_dev(struct intel_ntb_dev *ndev)
 	atom_deinit_isr(ndev);
 }
 
+/* Skylake Xeon NTB */
+
+static u64 skx_db_ioread(void __iomem *mmio)
+{
+	return ioread64(mmio);
+}
+
+static void skx_db_iowrite(u64 bits, void __iomem *mmio)
+{
+	iowrite64(bits, mmio);
+}
+
+static int skx_init_isr(struct intel_ntb_dev *ndev)
+{
+	int i;
+
+	/*
+	 * The MSIX vectors and the interrupt status bits are not lined up
+	 * on Skylake. By default the link status bit is bit 32, however it
+	 * is by default MSIX vector0. We need to fixup to line them up.
+	 * The vectors at reset is 1-32,0. We need to reprogram to 0-32.
+	 */
+
+	for (i = 0; i < SKX_DB_MSIX_VECTOR_COUNT; i++)
+		iowrite8(i, ndev->self_mmio + SKX_INTVEC_OFFSET + i);
+
+	/* move link status down one as workaround */
+	if (ndev->hwerr_flags & NTB_HWERR_MSIX_VECTOR32_BAD) {
+		iowrite8(SKX_DB_MSIX_VECTOR_COUNT - 2,
+			 ndev->self_mmio + SKX_INTVEC_OFFSET +
+			 (SKX_DB_MSIX_VECTOR_COUNT - 1));
+	}
+
+	return ndev_init_isr(ndev, SKX_DB_MSIX_VECTOR_COUNT,
+			     SKX_DB_MSIX_VECTOR_COUNT,
+			     SKX_DB_MSIX_VECTOR_SHIFT,
+			     SKX_DB_TOTAL_SHIFT);
+}
+
+static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev,
+			    const struct intel_b2b_addr *addr,
+			    const struct intel_b2b_addr *peer_addr)
+{
+	struct pci_dev *pdev;
+	void __iomem *mmio;
+	resource_size_t bar_size;
+	phys_addr_t bar_addr;
+	int b2b_bar;
+	u8 bar_sz;
+
+	pdev = ndev_pdev(ndev);
+	mmio = ndev->self_mmio;
+
+	if (ndev->b2b_idx == UINT_MAX) {
+		dev_dbg(ndev_dev(ndev), "not using b2b mw\n");
+		b2b_bar = 0;
+		ndev->b2b_off = 0;
+	} else {
+		b2b_bar = ndev_mw_to_bar(ndev, ndev->b2b_idx);
+		if (b2b_bar < 0)
+			return -EIO;
+
+		dev_dbg(ndev_dev(ndev), "using b2b mw bar %d\n", b2b_bar);
+
+		bar_size = pci_resource_len(ndev->ntb.pdev, b2b_bar);
+
+		dev_dbg(ndev_dev(ndev), "b2b bar size %#llx\n", bar_size);
+
+		if (b2b_mw_share && ((bar_size >> 1) >= XEON_B2B_MIN_SIZE)) {
+			dev_dbg(ndev_dev(ndev),
+				"b2b using first half of bar\n");
+			ndev->b2b_off = bar_size >> 1;
+		} else if (bar_size >= XEON_B2B_MIN_SIZE) {
+			dev_dbg(ndev_dev(ndev),
+				"b2b using whole bar\n");
+			ndev->b2b_off = 0;
+			--ndev->mw_count;
+		} else {
+			dev_dbg(ndev_dev(ndev),
+				"b2b bar size is too small\n");
+			return -EIO;
+		}
+	}
+
+	/*
+	 * Reset the secondary bar sizes to match the primary bar sizes,
+	 * except disable or halve the size of the b2b secondary bar.
+	 */
+	pci_read_config_byte(pdev, SKX_IMBAR1SZ_OFFSET, &bar_sz);
+	dev_dbg(ndev_dev(ndev), "IMBAR1SZ %#x\n", bar_sz);
+	if (b2b_bar == 1) {
+		if (ndev->b2b_off)
+			bar_sz -= 1;
+		else
+			bar_sz = 0;
+	}
+
+	pci_write_config_byte(pdev, SKX_EMBAR1SZ_OFFSET, bar_sz);
+	pci_read_config_byte(pdev, SKX_EMBAR1SZ_OFFSET, &bar_sz);
+	dev_dbg(ndev_dev(ndev), "EMBAR1SZ %#x\n", bar_sz);
+
+	pci_read_config_byte(pdev, SKX_IMBAR2SZ_OFFSET, &bar_sz);
+	dev_dbg(ndev_dev(ndev), "IMBAR2SZ %#x\n", bar_sz);
+	if (b2b_bar == 2) {
+		if (ndev->b2b_off)
+			bar_sz -= 1;
+		else
+			bar_sz = 0;
+	}
+
+	pci_write_config_byte(pdev, SKX_EMBAR2SZ_OFFSET, bar_sz);
+	pci_read_config_byte(pdev, SKX_EMBAR2SZ_OFFSET, &bar_sz);
+	dev_dbg(ndev_dev(ndev), "EMBAR2SZ %#x\n", bar_sz);
+
+	/* SBAR01 hit by first part of the b2b bar */
+	if (b2b_bar == 0)
+		bar_addr = addr->bar0_addr;
+	else if (b2b_bar == 1)
+		bar_addr = addr->bar2_addr64;
+	else if (b2b_bar == 2)
+		bar_addr = addr->bar4_addr64;
+	else
+		return -EIO;
+
+	/* setup incoming bar limits == base addrs (zero length windows) */
+	bar_addr = addr->bar2_addr64 + (b2b_bar == 1 ? ndev->b2b_off : 0);
+	iowrite64(bar_addr, mmio + SKX_IMBAR1XLMT_OFFSET);
+	bar_addr = ioread64(mmio + SKX_IMBAR1XLMT_OFFSET);
+	dev_dbg(ndev_dev(ndev), "IMBAR1XLMT %#018llx\n", bar_addr);
+
+	bar_addr = addr->bar4_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0);
+	iowrite64(bar_addr, mmio + SKX_IMBAR2XLMT_OFFSET);
+	bar_addr = ioread64(mmio + SKX_IMBAR2XLMT_OFFSET);
+	dev_dbg(ndev_dev(ndev), "IMBAR2XLMT %#018llx\n", bar_addr);
+
+	/* zero incoming translation addrs */
+	iowrite64(0, mmio + SKX_IMBAR1XBASE_OFFSET);
+	iowrite64(0, mmio + SKX_IMBAR2XBASE_OFFSET);
+
+	ndev->peer_mmio = ndev->self_mmio;
+
+	return 0;
+}
+
+static int skx_init_ntb(struct intel_ntb_dev *ndev)
+{
+	int rc;
+
+
+	ndev->mw_count = XEON_MW_COUNT;
+	ndev->spad_count = SKX_SPAD_COUNT;
+	ndev->db_count = SKX_DB_COUNT;
+	ndev->db_link_mask = SKX_DB_LINK_BIT;
+
+	/* DB fixup for using 31 right now */
+	if (ndev->hwerr_flags & NTB_HWERR_MSIX_VECTOR32_BAD)
+		ndev->db_link_mask |= BIT_ULL(31);
+
+	switch (ndev->ntb.topo) {
+	case NTB_TOPO_B2B_USD:
+	case NTB_TOPO_B2B_DSD:
+		ndev->self_reg = &skx_pri_reg;
+		ndev->peer_reg = &skx_b2b_reg;
+		ndev->xlat_reg = &skx_sec_xlat;
+
+		if (ndev->ntb.topo == NTB_TOPO_B2B_USD) {
+			rc = skx_setup_b2b_mw(ndev,
+					      &xeon_b2b_dsd_addr,
+					      &xeon_b2b_usd_addr);
+		} else {
+			rc = skx_setup_b2b_mw(ndev,
+					      &xeon_b2b_usd_addr,
+					      &xeon_b2b_dsd_addr);
+		}
+
+		if (rc)
+			return rc;
+
+		/* Enable Bus Master and Memory Space on the secondary side */
+		iowrite16(PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER,
+			  ndev->self_mmio + SKX_SPCICMD_OFFSET);
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	ndev->db_valid_mask = BIT_ULL(ndev->db_count) - 1;
+
+	ndev->reg->db_iowrite(ndev->db_valid_mask,
+			      ndev->self_mmio +
+			      ndev->self_reg->db_mask);
+
+	return 0;
+}
+
+static int skx_init_dev(struct intel_ntb_dev *ndev)
+{
+	struct pci_dev *pdev;
+	u8 ppd;
+	int rc;
+
+	pdev = ndev_pdev(ndev);
+
+	ndev->reg = &skx_reg;
+
+	rc = pci_read_config_byte(pdev, XEON_PPD_OFFSET, &ppd);
+	if (rc)
+		return -EIO;
+
+	ndev->ntb.topo = xeon_ppd_topo(ndev, ppd);
+	dev_dbg(ndev_dev(ndev), "ppd %#x topo %s\n", ppd,
+		ntb_topo_string(ndev->ntb.topo));
+	if (ndev->ntb.topo == NTB_TOPO_NONE)
+		return -EINVAL;
+
+	if (pdev_is_skx_xeon(pdev))
+		ndev->hwerr_flags |= NTB_HWERR_MSIX_VECTOR32_BAD;
+
+	rc = skx_init_ntb(ndev);
+	if (rc)
+		return rc;
+
+	return skx_init_isr(ndev);
+}
+
+static int intel_ntb3_link_enable(struct ntb_dev *ntb,
+				  enum ntb_speed max_speed,
+				  enum ntb_width max_width)
+{
+	struct intel_ntb_dev *ndev;
+	u32 ntb_ctl;
+
+	ndev = container_of(ntb, struct intel_ntb_dev, ntb);
+
+	dev_dbg(ndev_dev(ndev),
+		"Enabling link with max_speed %d max_width %d\n",
+		max_speed, max_width);
+
+	if (max_speed != NTB_SPEED_AUTO)
+		dev_dbg(ndev_dev(ndev), "ignoring max_speed %d\n", max_speed);
+	if (max_width != NTB_WIDTH_AUTO)
+		dev_dbg(ndev_dev(ndev), "ignoring max_width %d\n", max_width);
+
+	ntb_ctl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl);
+	ntb_ctl &= ~(NTB_CTL_DISABLE | NTB_CTL_CFG_LOCK);
+	ntb_ctl |= NTB_CTL_P2S_BAR2_SNOOP | NTB_CTL_S2P_BAR2_SNOOP;
+	ntb_ctl |= NTB_CTL_P2S_BAR4_SNOOP | NTB_CTL_S2P_BAR4_SNOOP;
+	iowrite32(ntb_ctl, ndev->self_mmio + ndev->reg->ntb_ctl);
+
+	return 0;
+}
+static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx,
+				   dma_addr_t addr, resource_size_t size)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+	unsigned long xlat_reg, limit_reg;
+	resource_size_t bar_size, mw_size;
+	void __iomem *mmio;
+	u64 base, limit, reg_val;
+	int bar;
+
+	if (idx >= ndev->b2b_idx && !ndev->b2b_off)
+		idx += 1;
+
+	bar = ndev_mw_to_bar(ndev, idx);
+	if (bar < 0)
+		return bar;
+
+	bar_size = pci_resource_len(ndev->ntb.pdev, bar);
+
+	if (idx == ndev->b2b_idx)
+		mw_size = bar_size - ndev->b2b_off;
+	else
+		mw_size = bar_size;
+
+	/* hardware requires that addr is aligned to bar size */
+	if (addr & (bar_size - 1))
+		return -EINVAL;
+
+	/* make sure the range fits in the usable mw size */
+	if (size > mw_size)
+		return -EINVAL;
+
+	mmio = ndev->self_mmio;
+	xlat_reg = ndev->xlat_reg->bar2_xlat + (idx * 0x10);
+	limit_reg = ndev->xlat_reg->bar2_limit + (idx * 0x10);
+	base = pci_resource_start(ndev->ntb.pdev, bar);
+
+	/* Set the limit if supported, if size is not mw_size */
+	if (limit_reg && size != mw_size)
+		limit = base + size;
+	else
+		limit = base + mw_size;
+
+	/* set and verify setting the translation address */
+	iowrite64(addr, mmio + xlat_reg);
+	reg_val = ioread64(mmio + xlat_reg);
+	if (reg_val != addr) {
+		iowrite64(0, mmio + xlat_reg);
+		return -EIO;
+	}
+
+	dev_dbg(ndev_dev(ndev), "BAR %d IMBARXBASE: %#Lx\n", bar, reg_val);
+
+	/* set and verify setting the limit */
+	iowrite64(limit, mmio + limit_reg);
+	reg_val = ioread64(mmio + limit_reg);
+	if (reg_val != limit) {
+		iowrite64(base, mmio + limit_reg);
+		iowrite64(0, mmio + xlat_reg);
+		return -EIO;
+	}
+
+	dev_dbg(ndev_dev(ndev), "BAR %d IMBARXLMT: %#Lx\n", bar, reg_val);
+
+	/* setup the EP */
+	limit_reg = ndev->xlat_reg->bar2_limit + (idx * 0x10) + 0x4000;
+	base = ioread64(mmio + SKX_EMBAR1_OFFSET + (8 * idx));
+	base &= ~0xf;
+
+	if (limit_reg && size != mw_size)
+		limit = base + size;
+	else
+		limit = base + mw_size;
+
+	/* set and verify setting the limit */
+	iowrite64(limit, mmio + limit_reg);
+	reg_val = ioread64(mmio + limit_reg);
+	if (reg_val != limit) {
+		iowrite64(base, mmio + limit_reg);
+		iowrite64(0, mmio + xlat_reg);
+		return -EIO;
+	}
+
+	dev_dbg(ndev_dev(ndev), "BAR %d EMBARXLMT: %#Lx\n", bar, reg_val);
+
+	return 0;
+}
+
+static int intel_ntb3_peer_db_set(struct ntb_dev *ntb, u64 db_bits)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+	int bit;
+
+	if (db_bits & ~ndev->db_valid_mask)
+		return -EINVAL;
+
+	while (db_bits) {
+		bit = __ffs(db_bits);
+		iowrite32(1, ndev->peer_mmio +
+				ndev->peer_reg->db_bell + (bit * 4));
+		db_bits &= db_bits - 1;
+	}
+
+	return 0;
+}
+
+static u64 intel_ntb3_db_read(struct ntb_dev *ntb)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_db_read(ndev,
+			    ndev->self_mmio +
+			    ndev->self_reg->db_clear);
+}
+
+static int intel_ntb3_db_clear(struct ntb_dev *ntb, u64 db_bits)
+{
+	struct intel_ntb_dev *ndev = ntb_ndev(ntb);
+
+	return ndev_db_write(ndev, db_bits,
+			     ndev->self_mmio +
+			     ndev->self_reg->db_clear);
+}
+
 /* XEON */
 
 static u64 xeon_db_ioread(void __iomem *mmio)
@@ -2120,6 +2696,24 @@ static int intel_ntb_pci_probe(struct pci_dev *pdev,
 		if (rc)
 			goto err_init_dev;
 
+	} else if (pdev_is_skx_xeon(pdev)) {
+		ndev = kzalloc_node(sizeof(*ndev), GFP_KERNEL, node);
+		if (!ndev) {
+			rc = -ENOMEM;
+			goto err_ndev;
+		}
+
+		ndev_init_struct(ndev, pdev);
+		ndev->ntb.ops = &intel_ntb3_ops;
+
+		rc = intel_ntb_init_pci(ndev, pdev);
+		if (rc)
+			goto err_init_pci;
+
+		rc = skx_init_dev(ndev);
+		if (rc)
+			goto err_init_dev;
+
 	} else {
 		rc = -EINVAL;
 		goto err_ndev;
@@ -2143,7 +2737,7 @@ static int intel_ntb_pci_probe(struct pci_dev *pdev,
 	ndev_deinit_debugfs(ndev);
 	if (pdev_is_atom(pdev))
 		atom_deinit_dev(ndev);
-	else if (pdev_is_xeon(pdev))
+	else if (pdev_is_xeon(pdev) || pdev_is_skx_xeon(pdev))
 		xeon_deinit_dev(ndev);
 err_init_dev:
 	intel_ntb_deinit_pci(ndev);
@@ -2161,7 +2755,7 @@ static void intel_ntb_pci_remove(struct pci_dev *pdev)
 	ndev_deinit_debugfs(ndev);
 	if (pdev_is_atom(pdev))
 		atom_deinit_dev(ndev);
-	else if (pdev_is_xeon(pdev))
+	else if (pdev_is_xeon(pdev) || pdev_is_skx_xeon(pdev))
 		xeon_deinit_dev(ndev);
 	intel_ntb_deinit_pci(ndev);
 	kfree(ndev);
@@ -2257,6 +2851,36 @@ static struct intel_b2b_addr xeon_b2b_dsd_addr = {
 	.bar5_addr32		= XEON_B2B_BAR5_ADDR32,
 };
 
+static const struct intel_ntb_reg skx_reg = {
+	.poll_link		= xeon_poll_link,
+	.link_is_up		= xeon_link_is_up,
+	.db_ioread		= skx_db_ioread,
+	.db_iowrite		= skx_db_iowrite,
+	.db_size		= sizeof(u64),
+	.ntb_ctl		= SKX_NTBCNTL_OFFSET,
+	.mw_bar			= {2, 4},
+};
+
+static const struct intel_ntb_alt_reg skx_pri_reg = {
+	.db_bell		= SKX_EM_DOORBELL_OFFSET,
+	.db_clear		= SKX_IM_INT_STATUS_OFFSET,
+	.db_mask		= SKX_IM_INT_DISABLE_OFFSET,
+	.spad			= SKX_IM_SPAD_OFFSET,
+};
+
+static const struct intel_ntb_alt_reg skx_b2b_reg = {
+	.db_bell		= SKX_IM_DOORBELL_OFFSET,
+	.db_clear		= SKX_EM_INT_STATUS_OFFSET,
+	.db_mask		= SKX_EM_INT_DISABLE_OFFSET,
+	.spad			= SKX_B2B_SPAD_OFFSET,
+};
+
+static const struct intel_ntb_xlat_reg skx_sec_xlat = {
+/*	.bar0_base		= SKX_EMBAR0_OFFSET, */
+	.bar2_limit		= SKX_IMBAR1XLMT_OFFSET,
+	.bar2_xlat		= SKX_IMBAR1XBASE_OFFSET,
+};
+
 /* operations for primary side of local ntb */
 static const struct ntb_dev_ops intel_ntb_ops = {
 	.mw_count		= intel_ntb_mw_count,
@@ -2284,6 +2908,31 @@ static const struct ntb_dev_ops intel_ntb_ops = {
 	.peer_spad_write	= intel_ntb_peer_spad_write,
 };
 
+static const struct ntb_dev_ops intel_ntb3_ops = {
+	.mw_count		= intel_ntb_mw_count,
+	.mw_get_range		= intel_ntb_mw_get_range,
+	.mw_set_trans		= intel_ntb3_mw_set_trans,
+	.link_is_up		= intel_ntb_link_is_up,
+	.link_enable		= intel_ntb3_link_enable,
+	.link_disable		= intel_ntb_link_disable,
+	.db_valid_mask		= intel_ntb_db_valid_mask,
+	.db_vector_count	= intel_ntb_db_vector_count,
+	.db_vector_mask		= intel_ntb_db_vector_mask,
+	.db_read		= intel_ntb3_db_read,
+	.db_clear		= intel_ntb3_db_clear,
+	.db_set_mask		= intel_ntb_db_set_mask,
+	.db_clear_mask		= intel_ntb_db_clear_mask,
+	.peer_db_addr		= intel_ntb_peer_db_addr,
+	.peer_db_set		= intel_ntb3_peer_db_set,
+	.spad_is_unsafe		= intel_ntb_spad_is_unsafe,
+	.spad_count		= intel_ntb_spad_count,
+	.spad_read		= intel_ntb_spad_read,
+	.spad_write		= intel_ntb_spad_write,
+	.peer_spad_addr		= intel_ntb_peer_spad_addr,
+	.peer_spad_read		= intel_ntb_peer_spad_read,
+	.peer_spad_write	= intel_ntb_peer_spad_write,
+};
+
 static const struct file_operations intel_ntb_debugfs_info = {
 	.owner = THIS_MODULE,
 	.open = simple_open,
@@ -2307,6 +2956,7 @@ static const struct pci_device_id intel_ntb_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_IVT)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_HSX)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_SS_BDX)},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_SKX)},
 	{0}
 };
 MODULE_DEVICE_TABLE(pci, intel_ntb_pci_tbl);
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.h b/drivers/ntb/hw/intel/ntb_hw_intel.h
index 3ec149c..f2cf8a7 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.h
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.h
@@ -70,6 +70,7 @@
 #define PCI_DEVICE_ID_INTEL_NTB_B2B_BDX	0x6F0D
 #define PCI_DEVICE_ID_INTEL_NTB_PS_BDX	0x6F0E
 #define PCI_DEVICE_ID_INTEL_NTB_SS_BDX	0x6F0F
+#define PCI_DEVICE_ID_INTEL_NTB_B2B_SKX	0x201C
 
 /* Intel Xeon hardware */
 
@@ -150,6 +151,51 @@
 #define XEON_DB_TOTAL_SHIFT		16
 #define XEON_SPAD_COUNT			16
 
+/* Intel Skylake Xeon hardware */
+#define SKX_IMBAR1SZ_OFFSET		0x00d0
+#define SKX_IMBAR2SZ_OFFSET		0x00d1
+#define SKX_EMBAR1SZ_OFFSET		0x00d2
+#define SKX_EMBAR2SZ_OFFSET		0x00d3
+#define SKX_DEVCTRL_OFFSET		0x0098
+#define SKX_DEVSTS_OFFSET		0x009a
+#define SKX_UNCERRSTS_OFFSET		0x014c
+#define SKX_CORERRSTS_OFFSET		0x0158
+#define SKX_LINK_STATUS_OFFSET		0x01a2
+
+#define SKX_NTBCNTL_OFFSET		0x0000
+#define SKX_IMBAR1XBASE_OFFSET		0x0010		/* SBAR2XLAT */
+#define SKX_IMBAR1XLMT_OFFSET		0x0018		/* SBAR2LMT */
+#define SKX_IMBAR2XBASE_OFFSET		0x0020		/* SBAR4XLAT */
+#define SKX_IMBAR2XLMT_OFFSET		0x0028		/* SBAR4LMT */
+#define SKX_IM_INT_STATUS_OFFSET	0x0040
+#define SKX_IM_INT_DISABLE_OFFSET	0x0048
+#define SKX_IM_SPAD_OFFSET		0x0080		/* SPAD */
+#define SKX_USMEMMISS_OFFSET		0x0070
+#define SKX_INTVEC_OFFSET		0x00d0
+#define SKX_IM_DOORBELL_OFFSET		0x0100		/* SDOORBELL0 */
+#define SKX_B2B_SPAD_OFFSET		0x0180		/* B2B SPAD */
+#define SKX_EMBAR0XBASE_OFFSET		0x4008		/* B2B_XLAT */
+#define SKX_EMBAR1XBASE_OFFSET		0x4010		/* PBAR2XLAT */
+#define SKX_EMBAR1XLMT_OFFSET		0x4018		/* PBAR2LMT */
+#define SKX_EMBAR2XBASE_OFFSET		0x4020		/* PBAR4XLAT */
+#define SKX_EMBAR2XLMT_OFFSET		0x4028		/* PBAR4LMT */
+#define SKX_EM_INT_STATUS_OFFSET	0x4040
+#define SKX_EM_INT_DISABLE_OFFSET	0x4048
+#define SKX_EM_SPAD_OFFSET		0x4080		/* remote SPAD */
+#define SKX_EM_DOORBELL_OFFSET		0x4100		/* PDOORBELL0 */
+#define SKX_SPCICMD_OFFSET		0x4504		/* SPCICMD */
+#define SKX_EMBAR0_OFFSET		0x4510		/* SBAR0BASE */
+#define SKX_EMBAR1_OFFSET		0x4518		/* SBAR23BASE */
+#define SKX_EMBAR2_OFFSET		0x4520		/* SBAR45BASE */
+
+#define SKX_DB_COUNT			32
+#define SKX_DB_LINK			32
+#define SKX_DB_LINK_BIT			BIT_ULL(SKX_DB_LINK)
+#define SKX_DB_MSIX_VECTOR_COUNT	33
+#define SKX_DB_MSIX_VECTOR_SHIFT	1
+#define SKX_DB_TOTAL_SHIFT		33
+#define SKX_SPAD_COUNT			16
+
 /* Intel Atom hardware */
 
 #define ATOM_SBAR2XLAT_OFFSET		0x0008
@@ -240,6 +286,7 @@
 #define NTB_HWERR_SDOORBELL_LOCKUP	BIT_ULL(0)
 #define NTB_HWERR_SB01BASE_LOCKUP	BIT_ULL(1)
 #define NTB_HWERR_B2BDOORBELL_BIT14	BIT_ULL(2)
+#define NTB_HWERR_MSIX_VECTOR32_BAD	BIT_ULL(3)
 
 /* flags to indicate unsafe api */
 #define NTB_UNSAFE_DB			BIT_ULL(0)
@@ -263,6 +310,7 @@ struct intel_ntb_reg {
 struct intel_ntb_alt_reg {
 	unsigned long			db_bell;
 	unsigned long			db_mask;
+	unsigned long			db_clear;
 	unsigned long			spad;
 };
 
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 4eb8adb..f81aa4b 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -66,6 +66,7 @@
 #define NTB_TRANSPORT_VER	"4"
 #define NTB_TRANSPORT_NAME	"ntb_transport"
 #define NTB_TRANSPORT_DESC	"Software Queue-Pair Transport over NTB"
+#define NTB_TRANSPORT_MIN_SPADS (MW0_SZ_HIGH + 2)
 
 MODULE_DESCRIPTION(NTB_TRANSPORT_DESC);
 MODULE_VERSION(NTB_TRANSPORT_VER);
@@ -242,9 +243,6 @@ enum {
 	NUM_MWS,
 	MW0_SZ_HIGH,
 	MW0_SZ_LOW,
-	MW1_SZ_HIGH,
-	MW1_SZ_LOW,
-	MAX_SPAD,
 };
 
 #define dev_client_dev(__dev) \
@@ -811,7 +809,7 @@ static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)
 {
 	struct ntb_transport_qp *qp;
 	u64 qp_bitmap_alloc;
-	int i;
+	unsigned int i, count;
 
 	qp_bitmap_alloc = nt->qp_bitmap & ~nt->qp_bitmap_free;
 
@@ -831,7 +829,8 @@ static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)
 	 * goes down, blast them now to give them a sane value the next
 	 * time they are accessed
 	 */
-	for (i = 0; i < MAX_SPAD; i++)
+	count = ntb_spad_count(nt->ndev);
+	for (i = 0; i < count; i++)
 		ntb_spad_write(nt->ndev, i, 0);
 }
 
@@ -960,7 +959,6 @@ static void ntb_qp_link_work(struct work_struct *work)
 	ntb_peer_spad_write(nt->ndev, QP_LINKS, val | BIT(qp->qp_num));
 
 	/* query remote spad for qp ready bits */
-	ntb_peer_spad_read(nt->ndev, QP_LINKS);
 	dev_dbg_ratelimited(&pdev->dev, "Remote QP link status = %x\n", val);
 
 	/* See if the remote side is up */
@@ -1064,17 +1062,12 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
 {
 	struct ntb_transport_ctx *nt;
 	struct ntb_transport_mw *mw;
-	unsigned int mw_count, qp_count;
+	unsigned int mw_count, qp_count, spad_count, max_mw_count_for_spads;
 	u64 qp_bitmap;
 	int node;
 	int rc, i;
 
 	mw_count = ntb_mw_count(ndev);
-	if (ntb_spad_count(ndev) < (NUM_MWS + 1 + mw_count * 2)) {
-		dev_err(&ndev->dev, "Not enough scratch pad registers for %s",
-			NTB_TRANSPORT_NAME);
-		return -EIO;
-	}
 
 	if (ntb_db_is_unsafe(ndev))
 		dev_dbg(&ndev->dev,
@@ -1090,8 +1083,18 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
 		return -ENOMEM;
 
 	nt->ndev = ndev;
+	spad_count = ntb_spad_count(ndev);
 
-	nt->mw_count = mw_count;
+	/* Limit the MW's based on the availability of scratchpads */
+
+	if (spad_count < NTB_TRANSPORT_MIN_SPADS) {
+		nt->mw_count = 0;
+		rc = -EINVAL;
+		goto err;
+	}
+
+	max_mw_count_for_spads = (spad_count - MW0_SZ_HIGH) / 2;
+	nt->mw_count = min(mw_count, max_mw_count_for_spads);
 
 	nt->mw_vec = kzalloc_node(mw_count * sizeof(*nt->mw_vec),
 				  GFP_KERNEL, node);
diff --git a/drivers/nubus/proc.c b/drivers/nubus/proc.c
index 5371b37..e8f68f5 100644
--- a/drivers/nubus/proc.c
+++ b/drivers/nubus/proc.c
@@ -25,7 +25,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 static int
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 2fd7dc2..3d21a15 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -50,7 +50,7 @@
 #define NVME_AQ_DEPTH		256
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
-		
+
 /*
  * We handle AEN commands ourselves and don't even let the
  * block layer know about them.
@@ -1349,7 +1349,7 @@ static ssize_t nvme_cmb_show(struct device *dev,
 {
 	struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
 
-	return snprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
+	return scnprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
 		       ndev->cmbloc, ndev->cmbsz);
 }
 static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
diff --git a/drivers/oprofile/event_buffer.c b/drivers/oprofile/event_buffer.c
index c0cc4e7..67935fb 100644
--- a/drivers/oprofile/event_buffer.c
+++ b/drivers/oprofile/event_buffer.c
@@ -18,7 +18,7 @@
 #include <linux/capability.h>
 #include <linux/dcookies.h>
 #include <linux/fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "oprof.h"
 #include "event_buffer.h"
diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c
index 134398e..d77ebbf 100644
--- a/drivers/oprofile/oprofilefs.c
+++ b/drivers/oprofile/oprofilefs.c
@@ -15,7 +15,7 @@
 #include <linux/oprofile.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "oprof.h"
 
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 3ed6238..553ef8a 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -48,7 +48,7 @@
 
 #include <asm/byteorder.h>
 #include <asm/cache.h>		/* for L1_CACHE_BYTES */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/dma.h>
 #include <asm/io.h>
diff --git a/drivers/parisc/ccio-rm-dma.c b/drivers/parisc/ccio-rm-dma.c
index f78f6f1..1bf9880 100644
--- a/drivers/parisc/ccio-rm-dma.c
+++ b/drivers/parisc/ccio-rm-dma.c
@@ -40,7 +40,7 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/io.h>
 #include <asm/hardware.h>
diff --git a/drivers/parisc/eisa_eeprom.c b/drivers/parisc/eisa_eeprom.c
index 783906f..4dd9b13 100644
--- a/drivers/parisc/eisa_eeprom.c
+++ b/drivers/parisc/eisa_eeprom.c
@@ -26,7 +26,7 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/eisa_eeprom.h>
 
 #define 	EISA_EEPROM_MINOR 241
diff --git a/drivers/parisc/eisa_enumerator.c b/drivers/parisc/eisa_enumerator.c
index 21905fe..d9bffe8 100644
--- a/drivers/parisc/eisa_enumerator.c
+++ b/drivers/parisc/eisa_enumerator.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 #include <asm/eisa_bus.h>
diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c
index b482431..ff1a332 100644
--- a/drivers/parisc/led.c
+++ b/drivers/parisc/led.c
@@ -49,7 +49,7 @@
 #include <asm/param.h>		/* HZ */
 #include <asm/led.h>
 #include <asm/pdc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* The control of the LEDs and LCDs on PARISC-machines have to be done 
    completely in software. The necessary calculations are done in a work queue
diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c
index 3651c38..055f83f 100644
--- a/drivers/parisc/pdc_stable.c
+++ b/drivers/parisc/pdc_stable.c
@@ -68,7 +68,7 @@
 
 #include <asm/pdc.h>
 #include <asm/page.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/hardware.h>
 
 #define PDCS_VERSION	"0.30"
diff --git a/drivers/parport/daisy.c b/drivers/parport/daisy.c
index 5bed17f..d998d0e 100644
--- a/drivers/parport/daisy.c
+++ b/drivers/parport/daisy.c
@@ -26,7 +26,7 @@
 #include <linux/sched.h>
 
 #include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #undef DEBUG
 
diff --git a/drivers/parport/ieee1284_ops.c b/drivers/parport/ieee1284_ops.c
index 2e21af4..c0e7d21 100644
--- a/drivers/parport/ieee1284_ops.c
+++ b/drivers/parport/ieee1284_ops.c
@@ -18,7 +18,7 @@
 #include <linux/parport.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #undef DEBUG /* undef me for production */
 
diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c
index 6e3a60c..dd6d4cc 100644
--- a/drivers/parport/parport_gsc.c
+++ b/drivers/parport/parport_gsc.c
@@ -34,7 +34,7 @@
 
 #include <asm/io.h>
 #include <asm/dma.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/superio.h>
 
 #include <linux/parport.h>
diff --git a/drivers/parport/probe.c b/drivers/parport/probe.c
index d763bc9..4d1d6ea 100644
--- a/drivers/parport/probe.c
+++ b/drivers/parport/probe.c
@@ -10,7 +10,7 @@
 #include <linux/ctype.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static const struct {
 	const char *token;
diff --git a/drivers/parport/procfs.c b/drivers/parport/procfs.c
index 74ed3e4..8ee44a104 100644
--- a/drivers/parport/procfs.c
+++ b/drivers/parport/procfs.c
@@ -23,7 +23,7 @@
 #include <linux/sysctl.h>
 #include <linux/device.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
 
diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c
index f6221d7..68d105a 100644
--- a/drivers/pci/hotplug/acpiphp_ibm.c
+++ b/drivers/pci/hotplug/acpiphp_ibm.c
@@ -35,7 +35,7 @@
 #include <linux/kobject.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "acpiphp.h"
 #include "../pci.h"
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
index ec009a7..33d300d 100644
--- a/drivers/pci/hotplug/cpqphp_core.c
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -40,7 +40,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "cpqphp.h"
 #include "cpqphp_nvram.h"
diff --git a/drivers/pci/hotplug/cpqphp_nvram.c b/drivers/pci/hotplug/cpqphp_nvram.c
index c25fc90..daae807 100644
--- a/drivers/pci/hotplug/cpqphp_nvram.c
+++ b/drivers/pci/hotplug/cpqphp_nvram.c
@@ -34,7 +34,7 @@
 #include <linux/workqueue.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "cpqphp.h"
 #include "cpqphp_nvram.h"
 
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index 56013d0..7b0e97b 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -42,7 +42,7 @@
 #include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "../pci.h"
 #include "cpci_hotplug.h"
 
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 2408abe..f82710a 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -11,7 +11,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/capability.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 #include "pci.h"
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 9236e40..1800bef 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3044,7 +3044,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0e0d, quirk_intel_ntb);
 static ktime_t fixup_debug_start(struct pci_dev *dev,
 				 void (*fn)(struct pci_dev *dev))
 {
-	ktime_t calltime = ktime_set(0, 0);
+	ktime_t calltime = 0;
 
 	dev_dbg(&dev->dev, "calling %pF\n", fn);
 	if (initcall_debug) {
diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c
index b91c4da..9bf993e 100644
--- a/drivers/pci/syscall.c
+++ b/drivers/pci/syscall.c
@@ -10,7 +10,7 @@
 #include <linux/errno.h>
 #include <linux/pci.h>
 #include <linux/syscalls.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "pci.h"
 
 SYSCALL_DEFINE5(pciconfig_read, unsigned long, bus, unsigned long, dfn,
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index b37b572..6d93358 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -1084,7 +1084,7 @@ static int arm_pmu_hp_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_STARTING,
-				      "AP_PERF_ARM_STARTING",
+				      "perf/arm/pmu:starting",
 				      arm_perf_starting_cpu, NULL);
 	if (ret)
 		pr_err("CPU hotplug notifier for ARM PMU could not be registered: %d\n",
diff --git a/drivers/platform/x86/msi-wmi.c b/drivers/platform/x86/msi-wmi.c
index 978e6d6..9a32f86 100644
--- a/drivers/platform/x86/msi-wmi.c
+++ b/drivers/platform/x86/msi-wmi.c
@@ -283,7 +283,7 @@ static int __init msi_wmi_input_setup(void)
 	if (err)
 		goto err_free_keymap;
 
-	last_pressed = ktime_set(0, 0);
+	last_pressed = 0;
 
 	return 0;
 
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index c890a49..aa2ee51 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -68,7 +68,7 @@
 #include <linux/poll.h>
 #include <linux/miscdevice.h>
 #endif
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <acpi/video.h>
 
 #define dprintk(fmt, ...)			\
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index aa65a85..cacb43f 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -82,7 +82,7 @@
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/initval.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <acpi/video.h>
 
 /* ThinkPad CMOS commands */
diff --git a/drivers/pnp/interface.c b/drivers/pnp/interface.c
index 4b6808f..5c5b3d4 100644
--- a/drivers/pnp/interface.c
+++ b/drivers/pnp/interface.c
@@ -17,7 +17,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "base.h"
 
diff --git a/drivers/pnp/pnpbios/proc.c b/drivers/pnp/pnpbios/proc.c
index c212db0..5ee6b2a 100644
--- a/drivers/pnp/pnpbios/proc.c
+++ b/drivers/pnp/pnpbios/proc.c
@@ -26,7 +26,7 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "pnpbios.h"
 
diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c
index 15fed9d..bfcd6fb 100644
--- a/drivers/power/reset/ltc2952-poweroff.c
+++ b/drivers/power/reset/ltc2952-poweroff.c
@@ -169,7 +169,7 @@ static void ltc2952_poweroff_kill(void)
 
 static void ltc2952_poweroff_default(struct ltc2952_poweroff *data)
 {
-	data->wde_interval = ktime_set(0, 300L*1E6L);
+	data->wde_interval = 300L * 1E6L;
 	data->trigger_delay = ktime_set(2, 500L*1E6L);
 
 	hrtimer_init(&data->timer_trigger, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 84a52db..fc0fa75 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -363,7 +363,7 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 		rtc_timer_remove(rtc, &rtc->aie_timer);
 
 	rtc->aie_timer.node.expires = rtc_tm_to_ktime(alarm->time);
-	rtc->aie_timer.period = ktime_set(0, 0);
+	rtc->aie_timer.period = 0;
 	if (alarm->enabled)
 		err = rtc_timer_enqueue(rtc, &rtc->aie_timer);
 
@@ -391,11 +391,11 @@ int rtc_initialize_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 		return err;
 
 	rtc->aie_timer.node.expires = rtc_tm_to_ktime(alarm->time);
-	rtc->aie_timer.period = ktime_set(0, 0);
+	rtc->aie_timer.period = 0;
 
 	/* Alarm has to be enabled & in the future for us to enqueue it */
-	if (alarm->enabled && (rtc_tm_to_ktime(now).tv64 <
-			 rtc->aie_timer.node.expires.tv64)) {
+	if (alarm->enabled && (rtc_tm_to_ktime(now) <
+			 rtc->aie_timer.node.expires)) {
 
 		rtc->aie_timer.enabled = 1;
 		timerqueue_add(&rtc->timerqueue, &rtc->aie_timer.node);
@@ -554,7 +554,7 @@ enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer)
 	int count;
 	rtc = container_of(timer, struct rtc_device, pie_timer);
 
-	period = ktime_set(0, NSEC_PER_SEC/rtc->irq_freq);
+	period = NSEC_PER_SEC / rtc->irq_freq;
 	count = hrtimer_forward_now(timer, period);
 
 	rtc_handle_legacy_irq(rtc, count, RTC_PF);
@@ -665,7 +665,7 @@ static int rtc_update_hrtimer(struct rtc_device *rtc, int enabled)
 		return -1;
 
 	if (enabled) {
-		ktime_t period = ktime_set(0, NSEC_PER_SEC / rtc->irq_freq);
+		ktime_t period = NSEC_PER_SEC / rtc->irq_freq;
 
 		hrtimer_start(&rtc->pie_timer, period, HRTIMER_MODE_REL);
 	}
@@ -766,7 +766,7 @@ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer)
 
 	/* Skip over expired timers */
 	while (next) {
-		if (next->expires.tv64 >= now.tv64)
+		if (next->expires >= now)
 			break;
 		next = timerqueue_iterate_next(next);
 	}
@@ -858,7 +858,7 @@ void rtc_timer_do_work(struct work_struct *work)
 	__rtc_read_time(rtc, &tm);
 	now = rtc_tm_to_ktime(tm);
 	while ((next = timerqueue_getnext(&rtc->timerqueue))) {
-		if (next->expires.tv64 > now.tv64)
+		if (next->expires > now)
 			break;
 
 		/* expire timer */
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 84ca314..dd46e96 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -20,7 +20,7 @@
 #include <linux/slab.h>
 
 #include <asm/debug.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ipl.h>
 
 /* This is ugly... */
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 67bf50c..ade0421 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -26,7 +26,7 @@
 #include <asm/idals.h>
 #include <asm/ebcdic.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cio.h>
 #include <asm/ccwdev.h>
 #include <asm/itcw.h>
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index 6c5d671..8713fef 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -20,7 +20,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <asm/ebcdic.h>
 
diff --git a/drivers/s390/block/dasd_erp.c b/drivers/s390/block/dasd_erp.c
index 113c1c1..9e34191 100644
--- a/drivers/s390/block/dasd_erp.c
+++ b/drivers/s390/block/dasd_erp.c
@@ -15,7 +15,7 @@
 
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* This is ugly... */
 #define PRINTK_HEADER "dasd_erp:"
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index e2fa759..8b1341f 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -16,7 +16,7 @@
 #include <linux/fs.h>
 #include <linux/blkpg.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* This is ugly... */
 #define PRINTK_HEADER "dasd_gendisk:"
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 9dfbd97..ec65c1e 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -21,7 +21,7 @@
 #include <asm/ccwdev.h>
 #include <asm/schid.h>
 #include <asm/cmb.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* This is ugly... */
 #define PRINTK_HEADER "dasd_ioctl:"
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index bad7a19..70dc2c4 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -20,7 +20,7 @@
 #include <linux/proc_fs.h>
 
 #include <asm/debug.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* This is ugly... */
 #define PRINTK_HEADER "dasd_proc:"
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 288f59a..b9d7e75 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -41,7 +41,7 @@
 #include <linux/suspend.h>
 #include <linux/platform_device.h>
 #include <linux/gfp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define XPRAM_NAME	"xpram"
 #define XPRAM_DEVS	1	/* one partition */
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index 1b8d825..9ec4ae0 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -25,7 +25,7 @@
 #include <asm/cio.h>
 #include <asm/io.h>
 #include <asm/ebcdic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/delay.h>
 #include <asm/cpcmd.h>
 #include <asm/setup.h>
diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c
index 7b9c50a..82c9133 100644
--- a/drivers/s390/char/keyboard.c
+++ b/drivers/s390/char/keyboard.c
@@ -14,7 +14,7 @@
 #include <linux/consolemap.h>
 #include <linux/kbd_kern.h>
 #include <linux/kbd_diacr.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "keyboard.h"
 
diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c
index ebdeaa5..027ac6a 100644
--- a/drivers/s390/char/monreader.c
+++ b/drivers/s390/char/monreader.c
@@ -23,7 +23,7 @@
 #include <linux/device.h>
 #include <linux/slab.h>
 #include <net/iucv/iucv.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ebcdic.h>
 #include <asm/extmem.h>
 
diff --git a/drivers/s390/char/monwriter.c b/drivers/s390/char/monwriter.c
index 9b5d113..571a7e3 100644
--- a/drivers/s390/char/monwriter.c
+++ b/drivers/s390/char/monwriter.c
@@ -21,7 +21,7 @@
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ebcdic.h>
 #include <asm/io.h>
 #include <asm/appldata.h>
diff --git a/drivers/s390/char/sclp_rw.c b/drivers/s390/char/sclp_rw.c
index 6010cd3..91b26df 100644
--- a/drivers/s390/char/sclp_rw.c
+++ b/drivers/s390/char/sclp_rw.c
@@ -13,7 +13,7 @@
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/ctype.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "sclp.h"
 #include "sclp_rw.h"
diff --git a/drivers/s390/char/sclp_tty.c b/drivers/s390/char/sclp_tty.c
index 9259017..236b736 100644
--- a/drivers/s390/char/sclp_tty.c
+++ b/drivers/s390/char/sclp_tty.c
@@ -15,7 +15,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/gfp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "ctrlchar.h"
 #include "sclp.h"
diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c
index 68d6ee7..095481d 100644
--- a/drivers/s390/char/sclp_vt220.c
+++ b/drivers/s390/char/sclp_vt220.c
@@ -26,7 +26,7 @@
 #include <linux/reboot.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "sclp.h"
 #include "ctrlchar.h"
 
diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c
index 77f9b9c..46ac116 100644
--- a/drivers/s390/char/tape_char.c
+++ b/drivers/s390/char/tape_char.c
@@ -18,7 +18,7 @@
 #include <linux/mtio.h>
 #include <linux/compat.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define TAPE_DBF_AREA	tape_core_dbf
 
diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index 272cb6c..e5ebe2f 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -24,7 +24,7 @@
 #include <asm/ccwdev.h>
 #include <asm/cio.h>
 #include <asm/ebcdic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "raw3270.h"
 #include "tty3270.h"
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 2a67b49..65f5a79 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -21,7 +21,7 @@
 #include <asm/compat.h>
 #include <asm/cpcmd.h>
 #include <asm/debug.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "vmcp.h"
 
 static debug_info_t *vmcp_debug;
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index 3167e85..57974a1 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -21,7 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cpcmd.h>
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c
index ff18f37..04aceb6 100644
--- a/drivers/s390/char/vmur.c
+++ b/drivers/s390/char/vmur.c
@@ -15,7 +15,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cio.h>
 #include <asm/ccwdev.h>
 #include <asm/debug.h>
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index f771e5e..d3b51ed 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -23,7 +23,7 @@
 #include <asm/ipl.h>
 #include <asm/sclp.h>
 #include <asm/setup.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/debug.h>
 #include <asm/processor.h>
 #include <asm/irqflags.h>
diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c
index 9082476..bf7f5d4 100644
--- a/drivers/s390/cio/blacklist.c
+++ b/drivers/s390/cio/blacklist.c
@@ -17,7 +17,7 @@
 #include <linux/ctype.h>
 #include <linux/device.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cio.h>
 #include <asm/ipl.h>
 
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 6d75984..5fa6991 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -333,7 +333,7 @@ void ap_wait(enum ap_wait wait)
 	case AP_WAIT_TIMEOUT:
 		spin_lock_bh(&ap_poll_timer_lock);
 		if (!hrtimer_is_queued(&ap_poll_timer)) {
-			hr_time = ktime_set(0, poll_timeout);
+			hr_time = poll_timeout;
 			hrtimer_forward_now(&ap_poll_timer, hr_time);
 			hrtimer_restart(&ap_poll_timer);
 		}
@@ -860,7 +860,7 @@ static ssize_t poll_timeout_store(struct bus_type *bus, const char *buf,
 	    time > 120000000000ULL)
 		return -EINVAL;
 	poll_timeout = time;
-	hr_time = ktime_set(0, poll_timeout);
+	hr_time = poll_timeout;
 
 	spin_lock_bh(&ap_poll_timer_lock);
 	hrtimer_cancel(&ap_poll_timer);
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 854a6e5..51eece9 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -36,7 +36,7 @@
 #include <linux/compat.h>
 #include <linux/slab.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/hw_random.h>
 #include <linux/debugfs.h>
 #include <asm/debug.h>
diff --git a/drivers/s390/crypto/zcrypt_cex2a.c b/drivers/s390/crypto/zcrypt_cex2a.c
index c7d48a1..b97c5d5 100644
--- a/drivers/s390/crypto/zcrypt_cex2a.c
+++ b/drivers/s390/crypto/zcrypt_cex2a.c
@@ -30,7 +30,7 @@
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mod_devicetable.h>
 
 #include "ap_bus.h"
diff --git a/drivers/s390/crypto/zcrypt_pcixcc.c b/drivers/s390/crypto/zcrypt_pcixcc.c
index 26ceaa6..6006047 100644
--- a/drivers/s390/crypto/zcrypt_pcixcc.c
+++ b/drivers/s390/crypto/zcrypt_pcixcc.c
@@ -31,7 +31,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mod_devicetable.h>
 
 #include "ap_bus.h"
diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index 2981024..3f85b97 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -62,7 +62,7 @@
 #include <net/dst.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ebcdic.h>
 
 #include <net/iucv/iucv.h>
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index 5810019..d5bf36e 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -289,11 +289,12 @@ void zfcp_dbf_rec_trig(char *tag, struct zfcp_adapter *adapter,
 
 
 /**
- * zfcp_dbf_rec_run - trace event related to running recovery
+ * zfcp_dbf_rec_run_lvl - trace event related to running recovery
+ * @level: trace level to be used for event
  * @tag: identifier for event
  * @erp: erp_action running
  */
-void zfcp_dbf_rec_run(char *tag, struct zfcp_erp_action *erp)
+void zfcp_dbf_rec_run_lvl(int level, char *tag, struct zfcp_erp_action *erp)
 {
 	struct zfcp_dbf *dbf = erp->adapter->dbf;
 	struct zfcp_dbf_rec *rec = &dbf->rec_buf;
@@ -319,11 +320,21 @@ void zfcp_dbf_rec_run(char *tag, struct zfcp_erp_action *erp)
 	else
 		rec->u.run.rec_count = atomic_read(&erp->adapter->erp_counter);
 
-	debug_event(dbf->rec, 1, rec, sizeof(*rec));
+	debug_event(dbf->rec, level, rec, sizeof(*rec));
 	spin_unlock_irqrestore(&dbf->rec_lock, flags);
 }
 
 /**
+ * zfcp_dbf_rec_run - trace event related to running recovery
+ * @tag: identifier for event
+ * @erp: erp_action running
+ */
+void zfcp_dbf_rec_run(char *tag, struct zfcp_erp_action *erp)
+{
+	zfcp_dbf_rec_run_lvl(1, tag, erp);
+}
+
+/**
  * zfcp_dbf_rec_run_wka - trace wka port event with info like running recovery
  * @tag: identifier for event
  * @wka_port: well known address port
diff --git a/drivers/s390/scsi/zfcp_dbf.h b/drivers/s390/scsi/zfcp_dbf.h
index 36d0758..db186d4 100644
--- a/drivers/s390/scsi/zfcp_dbf.h
+++ b/drivers/s390/scsi/zfcp_dbf.h
@@ -2,7 +2,7 @@
  * zfcp device driver
  * debug feature declarations
  *
- * Copyright IBM Corp. 2008, 2015
+ * Copyright IBM Corp. 2008, 2016
  */
 
 #ifndef ZFCP_DBF_H
@@ -283,6 +283,30 @@ struct zfcp_dbf {
 	struct zfcp_dbf_scsi		scsi_buf;
 };
 
+/**
+ * zfcp_dbf_hba_fsf_resp_suppress - true if we should not trace by default
+ * @req: request that has been completed
+ *
+ * Returns true if FCP response with only benign residual under count.
+ */
+static inline
+bool zfcp_dbf_hba_fsf_resp_suppress(struct zfcp_fsf_req *req)
+{
+	struct fsf_qtcb *qtcb = req->qtcb;
+	u32 fsf_stat = qtcb->header.fsf_status;
+	struct fcp_resp *fcp_rsp;
+	u8 rsp_flags, fr_status;
+
+	if (qtcb->prefix.qtcb_type != FSF_IO_COMMAND)
+		return false; /* not an FCP response */
+	fcp_rsp = (struct fcp_resp *)&qtcb->bottom.io.fcp_rsp;
+	rsp_flags = fcp_rsp->fr_flags;
+	fr_status = fcp_rsp->fr_status;
+	return (fsf_stat == FSF_FCP_RSP_AVAILABLE) &&
+		(rsp_flags == FCP_RESID_UNDER) &&
+		(fr_status == SAM_STAT_GOOD);
+}
+
 static inline
 void zfcp_dbf_hba_fsf_resp(char *tag, int level, struct zfcp_fsf_req *req)
 {
@@ -304,7 +328,9 @@ void zfcp_dbf_hba_fsf_response(struct zfcp_fsf_req *req)
 		zfcp_dbf_hba_fsf_resp("fs_perr", 1, req);
 
 	} else if (qtcb->header.fsf_status != FSF_GOOD) {
-		zfcp_dbf_hba_fsf_resp("fs_ferr", 1, req);
+		zfcp_dbf_hba_fsf_resp("fs_ferr",
+				      zfcp_dbf_hba_fsf_resp_suppress(req)
+				      ? 5 : 1, req);
 
 	} else if ((req->fsf_command == FSF_QTCB_OPEN_PORT_WITH_DID) ||
 		   (req->fsf_command == FSF_QTCB_OPEN_LUN)) {
@@ -388,4 +414,15 @@ void zfcp_dbf_scsi_devreset(char *tag, struct scsi_cmnd *scmnd, u8 flag)
 	_zfcp_dbf_scsi(tmp_tag, 1, scmnd, NULL);
 }
 
+/**
+ * zfcp_dbf_scsi_nullcmnd() - trace NULLify of SCSI command in dev/tgt-reset.
+ * @scmnd: SCSI command that was NULLified.
+ * @fsf_req: request that owned @scmnd.
+ */
+static inline void zfcp_dbf_scsi_nullcmnd(struct scsi_cmnd *scmnd,
+					  struct zfcp_fsf_req *fsf_req)
+{
+	_zfcp_dbf_scsi("scfc__1", 3, scmnd, fsf_req);
+}
+
 #endif /* ZFCP_DBF_H */
diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c
index a59d678..7ccfce5 100644
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -3,7 +3,7 @@
  *
  * Error Recovery Procedures (ERP).
  *
- * Copyright IBM Corp. 2002, 2015
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -1204,6 +1204,62 @@ static void zfcp_erp_action_dequeue(struct zfcp_erp_action *erp_action)
 	}
 }
 
+/**
+ * zfcp_erp_try_rport_unblock - unblock rport if no more/new recovery
+ * @port: zfcp_port whose fc_rport we should try to unblock
+ */
+static void zfcp_erp_try_rport_unblock(struct zfcp_port *port)
+{
+	unsigned long flags;
+	struct zfcp_adapter *adapter = port->adapter;
+	int port_status;
+	struct Scsi_Host *shost = adapter->scsi_host;
+	struct scsi_device *sdev;
+
+	write_lock_irqsave(&adapter->erp_lock, flags);
+	port_status = atomic_read(&port->status);
+	if ((port_status & ZFCP_STATUS_COMMON_UNBLOCKED)    == 0 ||
+	    (port_status & (ZFCP_STATUS_COMMON_ERP_INUSE |
+			    ZFCP_STATUS_COMMON_ERP_FAILED)) != 0) {
+		/* new ERP of severity >= port triggered elsewhere meanwhile or
+		 * local link down (adapter erp_failed but not clear unblock)
+		 */
+		zfcp_dbf_rec_run_lvl(4, "ertru_p", &port->erp_action);
+		write_unlock_irqrestore(&adapter->erp_lock, flags);
+		return;
+	}
+	spin_lock(shost->host_lock);
+	__shost_for_each_device(sdev, shost) {
+		struct zfcp_scsi_dev *zsdev = sdev_to_zfcp(sdev);
+		int lun_status;
+
+		if (zsdev->port != port)
+			continue;
+		/* LUN under port of interest */
+		lun_status = atomic_read(&zsdev->status);
+		if ((lun_status & ZFCP_STATUS_COMMON_ERP_FAILED) != 0)
+			continue; /* unblock rport despite failed LUNs */
+		/* LUN recovery not given up yet [maybe follow-up pending] */
+		if ((lun_status & ZFCP_STATUS_COMMON_UNBLOCKED) == 0 ||
+		    (lun_status & ZFCP_STATUS_COMMON_ERP_INUSE) != 0) {
+			/* LUN blocked:
+			 * not yet unblocked [LUN recovery pending]
+			 * or meanwhile blocked [new LUN recovery triggered]
+			 */
+			zfcp_dbf_rec_run_lvl(4, "ertru_l", &zsdev->erp_action);
+			spin_unlock(shost->host_lock);
+			write_unlock_irqrestore(&adapter->erp_lock, flags);
+			return;
+		}
+	}
+	/* now port has no child or all children have completed recovery,
+	 * and no ERP of severity >= port was meanwhile triggered elsewhere
+	 */
+	zfcp_scsi_schedule_rport_register(port);
+	spin_unlock(shost->host_lock);
+	write_unlock_irqrestore(&adapter->erp_lock, flags);
+}
+
 static void zfcp_erp_action_cleanup(struct zfcp_erp_action *act, int result)
 {
 	struct zfcp_adapter *adapter = act->adapter;
@@ -1214,6 +1270,7 @@ static void zfcp_erp_action_cleanup(struct zfcp_erp_action *act, int result)
 	case ZFCP_ERP_ACTION_REOPEN_LUN:
 		if (!(act->status & ZFCP_STATUS_ERP_NO_REF))
 			scsi_device_put(sdev);
+		zfcp_erp_try_rport_unblock(port);
 		break;
 
 	case ZFCP_ERP_ACTION_REOPEN_PORT:
@@ -1224,7 +1281,7 @@ static void zfcp_erp_action_cleanup(struct zfcp_erp_action *act, int result)
 		 */
 		if (act->step != ZFCP_ERP_STEP_UNINITIALIZED)
 			if (result == ZFCP_ERP_SUCCEEDED)
-				zfcp_scsi_schedule_rport_register(port);
+				zfcp_erp_try_rport_unblock(port);
 		/* fall through */
 	case ZFCP_ERP_ACTION_REOPEN_PORT_FORCED:
 		put_device(&port->dev);
diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h
index 968a0ab..9afdbc3 100644
--- a/drivers/s390/scsi/zfcp_ext.h
+++ b/drivers/s390/scsi/zfcp_ext.h
@@ -3,7 +3,7 @@
  *
  * External function declarations.
  *
- * Copyright IBM Corp. 2002, 2015
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #ifndef ZFCP_EXT_H
@@ -35,6 +35,8 @@ extern void zfcp_dbf_adapter_unregister(struct zfcp_adapter *);
 extern void zfcp_dbf_rec_trig(char *, struct zfcp_adapter *,
 			      struct zfcp_port *, struct scsi_device *, u8, u8);
 extern void zfcp_dbf_rec_run(char *, struct zfcp_erp_action *);
+extern void zfcp_dbf_rec_run_lvl(int level, char *tag,
+				 struct zfcp_erp_action *erp);
 extern void zfcp_dbf_rec_run_wka(char *, struct zfcp_fc_wka_port *, u64);
 extern void zfcp_dbf_hba_fsf_uss(char *, struct zfcp_fsf_req *);
 extern void zfcp_dbf_hba_fsf_res(char *, int, struct zfcp_fsf_req *);
diff --git a/drivers/s390/scsi/zfcp_fsf.h b/drivers/s390/scsi/zfcp_fsf.h
index be1c04b..ea3c76a 100644
--- a/drivers/s390/scsi/zfcp_fsf.h
+++ b/drivers/s390/scsi/zfcp_fsf.h
@@ -3,7 +3,7 @@
  *
  * Interface to the FSF support functions.
  *
- * Copyright IBM Corp. 2002, 2015
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #ifndef FSF_H
@@ -78,6 +78,7 @@
 #define FSF_APP_TAG_CHECK_FAILURE		0x00000082
 #define FSF_REF_TAG_CHECK_FAILURE		0x00000083
 #define FSF_ADAPTER_STATUS_AVAILABLE		0x000000AD
+#define FSF_FCP_RSP_AVAILABLE			0x000000AF
 #define FSF_UNKNOWN_COMMAND			0x000000E2
 #define FSF_UNKNOWN_OP_SUBTYPE                  0x000000E3
 #define FSF_INVALID_COMMAND_OPTION              0x000000E5
diff --git a/drivers/s390/scsi/zfcp_reqlist.h b/drivers/s390/scsi/zfcp_reqlist.h
index 7c2c619..703fce5 100644
--- a/drivers/s390/scsi/zfcp_reqlist.h
+++ b/drivers/s390/scsi/zfcp_reqlist.h
@@ -4,7 +4,7 @@
  * Data structure and helper functions for tracking pending FSF
  * requests.
  *
- * Copyright IBM Corp. 2009
+ * Copyright IBM Corp. 2009, 2016
  */
 
 #ifndef ZFCP_REQLIST_H
@@ -180,4 +180,32 @@ static inline void zfcp_reqlist_move(struct zfcp_reqlist *rl,
 	spin_unlock_irqrestore(&rl->lock, flags);
 }
 
+/**
+ * zfcp_reqlist_apply_for_all() - apply a function to every request.
+ * @rl: the requestlist that contains the target requests.
+ * @f: the function to apply to each request; the first parameter of the
+ *     function will be the target-request; the second parameter is the same
+ *     pointer as given with the argument @data.
+ * @data: freely chosen argument; passed through to @f as second parameter.
+ *
+ * Uses :c:macro:`list_for_each_entry` to iterate over the lists in the hash-
+ * table (not a 'safe' variant, so don't modify the list).
+ *
+ * Holds @rl->lock over the entire request-iteration.
+ */
+static inline void
+zfcp_reqlist_apply_for_all(struct zfcp_reqlist *rl,
+			   void (*f)(struct zfcp_fsf_req *, void *), void *data)
+{
+	struct zfcp_fsf_req *req;
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&rl->lock, flags);
+	for (i = 0; i < ZFCP_REQ_LIST_BUCKETS; i++)
+		list_for_each_entry(req, &rl->buckets[i], list)
+			f(req, data);
+	spin_unlock_irqrestore(&rl->lock, flags);
+}
+
 #endif /* ZFCP_REQLIST_H */
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 9069f98..07ffdbb 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -3,7 +3,7 @@
  *
  * Interface to Linux SCSI midlayer.
  *
- * Copyright IBM Corp. 2002, 2015
+ * Copyright IBM Corp. 2002, 2016
  */
 
 #define KMSG_COMPONENT "zfcp"
@@ -88,9 +88,7 @@ int zfcp_scsi_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scpnt)
 	}
 
 	if (unlikely(!(status & ZFCP_STATUS_COMMON_UNBLOCKED))) {
-		/* This could be either
-		 * open LUN pending: this is temporary, will result in
-		 *	open LUN or ERP_FAILED, so retry command
+		/* This could be
 		 * call to rport_delete pending: mimic retry from
 		 * 	fc_remote_port_chkready until rport is BLOCKED
 		 */
@@ -209,6 +207,57 @@ static int zfcp_scsi_eh_abort_handler(struct scsi_cmnd *scpnt)
 	return retval;
 }
 
+struct zfcp_scsi_req_filter {
+	u8 tmf_scope;
+	u32 lun_handle;
+	u32 port_handle;
+};
+
+static void zfcp_scsi_forget_cmnd(struct zfcp_fsf_req *old_req, void *data)
+{
+	struct zfcp_scsi_req_filter *filter =
+		(struct zfcp_scsi_req_filter *)data;
+
+	/* already aborted - prevent side-effects - or not a SCSI command */
+	if (old_req->data == NULL || old_req->fsf_command != FSF_QTCB_FCP_CMND)
+		return;
+
+	/* (tmf_scope == FCP_TMF_TGT_RESET || tmf_scope == FCP_TMF_LUN_RESET) */
+	if (old_req->qtcb->header.port_handle != filter->port_handle)
+		return;
+
+	if (filter->tmf_scope == FCP_TMF_LUN_RESET &&
+	    old_req->qtcb->header.lun_handle != filter->lun_handle)
+		return;
+
+	zfcp_dbf_scsi_nullcmnd((struct scsi_cmnd *)old_req->data, old_req);
+	old_req->data = NULL;
+}
+
+static void zfcp_scsi_forget_cmnds(struct zfcp_scsi_dev *zsdev, u8 tm_flags)
+{
+	struct zfcp_adapter *adapter = zsdev->port->adapter;
+	struct zfcp_scsi_req_filter filter = {
+		.tmf_scope = FCP_TMF_TGT_RESET,
+		.port_handle = zsdev->port->handle,
+	};
+	unsigned long flags;
+
+	if (tm_flags == FCP_TMF_LUN_RESET) {
+		filter.tmf_scope = FCP_TMF_LUN_RESET;
+		filter.lun_handle = zsdev->lun_handle;
+	}
+
+	/*
+	 * abort_lock secures against other processings - in the abort-function
+	 * and normal cmnd-handler - of (struct zfcp_fsf_req *)->data
+	 */
+	write_lock_irqsave(&adapter->abort_lock, flags);
+	zfcp_reqlist_apply_for_all(adapter->req_list, zfcp_scsi_forget_cmnd,
+				   &filter);
+	write_unlock_irqrestore(&adapter->abort_lock, flags);
+}
+
 static int zfcp_task_mgmt_function(struct scsi_cmnd *scpnt, u8 tm_flags)
 {
 	struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(scpnt->device);
@@ -241,8 +290,10 @@ static int zfcp_task_mgmt_function(struct scsi_cmnd *scpnt, u8 tm_flags)
 	if (fsf_req->status & ZFCP_STATUS_FSFREQ_TMFUNCFAILED) {
 		zfcp_dbf_scsi_devreset("fail", scpnt, tm_flags);
 		retval = FAILED;
-	} else
+	} else {
 		zfcp_dbf_scsi_devreset("okay", scpnt, tm_flags);
+		zfcp_scsi_forget_cmnds(zfcp_sdev, tm_flags);
+	}
 
 	zfcp_fsf_req_free(fsf_req);
 	return retval;
diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c
index 33fbe82..04efed1 100644
--- a/drivers/sbus/char/display7seg.c
+++ b/drivers/sbus/char/display7seg.c
@@ -17,7 +17,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>		/* put_/get_user			*/
+#include <linux/uaccess.h>		/* put_/get_user			*/
 #include <asm/io.h>
 
 #include <asm/display7seg.h>
diff --git a/drivers/sbus/char/envctrl.c b/drivers/sbus/char/envctrl.c
index 5609b60..56e962a 100644
--- a/drivers/sbus/char/envctrl.c
+++ b/drivers/sbus/char/envctrl.c
@@ -29,7 +29,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/envctrl.h>
 #include <asm/io.h>
 
diff --git a/drivers/sbus/char/flash.c b/drivers/sbus/char/flash.c
index 206ef42..216f923 100644
--- a/drivers/sbus/char/flash.c
+++ b/drivers/sbus/char/flash.c
@@ -15,7 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/upa.h>
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
index a40ee1e..6ff61da 100644
--- a/drivers/sbus/char/jsflash.c
+++ b/drivers/sbus/char/jsflash.c
@@ -37,7 +37,7 @@
 #include <linux/string.h>
 #include <linux/genhd.h>
 #include <linux/blkdev.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/pcic.h>
diff --git a/drivers/sbus/char/openprom.c b/drivers/sbus/char/openprom.c
index 4612691..2c2e6a3 100644
--- a/drivers/sbus/char/openprom.c
+++ b/drivers/sbus/char/openprom.c
@@ -40,7 +40,7 @@
 #include <linux/fs.h>
 #include <asm/oplib.h>
 #include <asm/prom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/openpromio.h>
 #ifdef CONFIG_PCI
 #include <linux/pci.h>
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index a56a7b2..00e7968 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -1,8 +1,8 @@
 /*
    3w-9xxx.c -- 3ware 9000 Storage Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
-   Modifications By: Tom Couch <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
+   Modifications By: Tom Couch
 
    Copyright (C) 2004-2009 Applied Micro Circuits Corporation.
    Copyright (C) 2010 LSI Corporation.
@@ -41,10 +41,7 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
    Bugs/Comments/Suggestions should be mailed to:
-   linuxraid@lsi.com
-
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
 
    Note: This version of the driver does not contain a bundled firmware
          image.
@@ -95,7 +92,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/scsi/3w-9xxx.h b/drivers/scsi/3w-9xxx.h
index 0fdc83c..b6c208c 100644
--- a/drivers/scsi/3w-9xxx.h
+++ b/drivers/scsi/3w-9xxx.h
@@ -1,8 +1,8 @@
 /*
    3w-9xxx.h -- 3ware 9000 Storage Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
-   Modifications By: Tom Couch <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
+   Modifications By: Tom Couch
 
    Copyright (C) 2004-2009 Applied Micro Circuits Corporation.
    Copyright (C) 2010 LSI Corporation.
@@ -41,10 +41,7 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
    Bugs/Comments/Suggestions should be mailed to:
-   linuxraid@lsi.com
-
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
 */
 
 #ifndef _3W_9XXX_H
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index f837485..b150e13 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1,7 +1,7 @@
 /*
    3w-sas.c -- LSI 3ware SAS/SATA-RAID Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
 
    Copyright (C) 2009 LSI Corporation.
 
@@ -43,10 +43,7 @@
    LSI 3ware 9750 6Gb/s SAS/SATA-RAID
 
    Bugs/Comments/Suggestions should be mailed to:
-   linuxraid@lsi.com
-
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
 
    History
    -------
@@ -67,7 +64,7 @@
 #include <linux/slab.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/scsi/3w-sas.h b/drivers/scsi/3w-sas.h
index fec6449..05e77d8 100644
--- a/drivers/scsi/3w-sas.h
+++ b/drivers/scsi/3w-sas.h
@@ -1,7 +1,7 @@
 /*
    3w-sas.h -- LSI 3ware SAS/SATA-RAID Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
 
    Copyright (C) 2009 LSI Corporation.
 
@@ -39,10 +39,7 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
    Bugs/Comments/Suggestions should be mailed to:
-   linuxraid@lsi.com
-
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
 */
 
 #ifndef _3W_SAS_H
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 25aba16..33261b6 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -1,7 +1,7 @@
 /* 
    3w-xxxx.c -- 3ware Storage Controller device driver for Linux.
 
-   Written By: Adam Radford <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
    Modifications By: Joel Jacobson <linux@3ware.com>
    		     Arnaldo Carvalho de Melo <acme@conectiva.com.br>
                      Brad Strand <linux@3ware.com>
@@ -47,10 +47,9 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA 
 
    Bugs/Comments/Suggestions should be mailed to:                            
-   linuxraid@lsi.com
 
-   For more information, goto:
-   http://www.lsi.com
+   aradford@gmail.com
+
 
    History
    -------
@@ -211,7 +210,7 @@
 #include <linux/mutex.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/scsi/3w-xxxx.h b/drivers/scsi/3w-xxxx.h
index 6f65e66..69e80c1 100644
--- a/drivers/scsi/3w-xxxx.h
+++ b/drivers/scsi/3w-xxxx.h
@@ -1,7 +1,7 @@
 /* 
    3w-xxxx.h -- 3ware Storage Controller device driver for Linux.
    
-   Written By: Adam Radford <linuxraid@lsi.com>
+   Written By: Adam Radford <aradford@gmail.com>
    Modifications By: Joel Jacobson <linux@3ware.com>
    		     Arnaldo Carvalho de Melo <acme@conectiva.com.br>
                      Brad Strand <linux@3ware.com>
@@ -45,7 +45,8 @@
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA 
 
    Bugs/Comments/Suggestions should be mailed to:                            
-   linuxraid@lsi.com
+
+   aradford@gmail.com
    
    For more information, goto:
    http://www.lsi.com
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index dfa9334..a4f6b0d 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1233,6 +1233,7 @@
 
 source "drivers/scsi/qla2xxx/Kconfig"
 source "drivers/scsi/qla4xxx/Kconfig"
+source "drivers/scsi/qedi/Kconfig"
 
 config SCSI_LPFC
 	tristate "Emulex LightPulse Fibre Channel Support"
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index a2d0395..736b774 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -131,6 +131,7 @@
 obj-$(CONFIG_SCSI_CXGB3_ISCSI)	+= libiscsi.o libiscsi_tcp.o cxgbi/
 obj-$(CONFIG_SCSI_CXGB4_ISCSI)	+= libiscsi.o libiscsi_tcp.o cxgbi/
 obj-$(CONFIG_SCSI_BNX2_ISCSI)	+= libiscsi.o bnx2i/
+obj-$(CONFIG_QEDI)          += libiscsi.o qedi/
 obj-$(CONFIG_BE2ISCSI)		+= libiscsi.o be2iscsi/
 obj-$(CONFIG_SCSI_ESAS2R)	+= esas2r/
 obj-$(CONFIG_SCSI_PMCRAID)	+= pmcraid.o
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index d849ffa..4f5ca79 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -97,9 +97,6 @@
  * and macros and include this file in your driver.
  *
  * These macros control options :
- * AUTOPROBE_IRQ - if defined, the NCR5380_probe_irq() function will be
- * defined.
- *
  * AUTOSENSE - if defined, REQUEST SENSE will be performed automatically
  * for commands that return with a CHECK CONDITION status.
  *
@@ -127,9 +124,7 @@
  * NCR5380_dma_residual   - residual byte count
  *
  * The generic driver is initialized by calling NCR5380_init(instance),
- * after setting the appropriate host specific fields and ID.  If the
- * driver wishes to autoprobe for an IRQ line, the NCR5380_probe_irq(instance,
- * possible) function may be used.
+ * after setting the appropriate host specific fields and ID.
  */
 
 #ifndef NCR5380_io_delay
@@ -351,76 +346,6 @@ static void NCR5380_print_phase(struct Scsi_Host *instance)
 }
 #endif
 
-
-static int probe_irq;
-
-/**
- * probe_intr	-	helper for IRQ autoprobe
- * @irq: interrupt number
- * @dev_id: unused
- * @regs: unused
- *
- * Set a flag to indicate the IRQ in question was received. This is
- * used by the IRQ probe code.
- */
-
-static irqreturn_t probe_intr(int irq, void *dev_id)
-{
-	probe_irq = irq;
-	return IRQ_HANDLED;
-}
-
-/**
- * NCR5380_probe_irq	-	find the IRQ of an NCR5380
- * @instance: NCR5380 controller
- * @possible: bitmask of ISA IRQ lines
- *
- * Autoprobe for the IRQ line used by the NCR5380 by triggering an IRQ
- * and then looking to see what interrupt actually turned up.
- */
-
-static int __maybe_unused NCR5380_probe_irq(struct Scsi_Host *instance,
-						int possible)
-{
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
-	unsigned long timeout;
-	int trying_irqs, i, mask;
-
-	for (trying_irqs = 0, i = 1, mask = 2; i < 16; ++i, mask <<= 1)
-		if ((mask & possible) && (request_irq(i, &probe_intr, 0, "NCR-probe", NULL) == 0))
-			trying_irqs |= mask;
-
-	timeout = jiffies + msecs_to_jiffies(250);
-	probe_irq = NO_IRQ;
-
-	/*
-	 * A interrupt is triggered whenever BSY = false, SEL = true
-	 * and a bit set in the SELECT_ENABLE_REG is asserted on the
-	 * SCSI bus.
-	 *
-	 * Note that the bus is only driven when the phase control signals
-	 * (I/O, C/D, and MSG) match those in the TCR, so we must reset that
-	 * to zero.
-	 */
-
-	NCR5380_write(TARGET_COMMAND_REG, 0);
-	NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
-	NCR5380_write(OUTPUT_DATA_REG, hostdata->id_mask);
-	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_DATA | ICR_ASSERT_SEL);
-
-	while (probe_irq == NO_IRQ && time_before(jiffies, timeout))
-		schedule_timeout_uninterruptible(1);
-
-	NCR5380_write(SELECT_ENABLE_REG, 0);
-	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
-
-	for (i = 1, mask = 2; i < 16; ++i, mask <<= 1)
-		if (trying_irqs & mask)
-			free_irq(i, NULL);
-
-	return probe_irq;
-}
-
 /**
  * NCR58380_info - report driver and host information
  * @instance: relevant scsi host instance
diff --git a/drivers/scsi/NCR5380.h b/drivers/scsi/NCR5380.h
index 3c6ce54..51a3567 100644
--- a/drivers/scsi/NCR5380.h
+++ b/drivers/scsi/NCR5380.h
@@ -199,16 +199,6 @@
 
 #define PHASE_SR_TO_TCR(phase) ((phase) >> 2)
 
-/*
- * These are "special" values for the irq and dma_channel fields of the 
- * Scsi_Host structure
- */
-
-#define DMA_NONE	255
-#define IRQ_AUTO	254
-#define DMA_AUTO	254
-#define PORT_AUTO	0xffff	/* autoprobe io port for 53c400a */
-
 #ifndef NO_IRQ
 #define NO_IRQ		0
 #endif
@@ -290,7 +280,6 @@ static void NCR5380_print(struct Scsi_Host *instance);
 #define NCR5380_dprint_phase(flg, arg) do {} while (0)
 #endif
 
-static int NCR5380_probe_irq(struct Scsi_Host *instance, int possible);
 static int NCR5380_init(struct Scsi_Host *instance, int flags);
 static int NCR5380_maybe_reset_bus(struct Scsi_Host *);
 static void NCR5380_exit(struct Scsi_Host *instance);
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 6678d1f..1ee7c65 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -32,7 +32,7 @@
 #include <linux/slab.h>
 #include <linux/completion.h>
 #include <linux/blkdev.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/highmem.h> /* For flush_kernel_dcache_page */
 #include <linux/module.h>
 
diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index 5648b71..e1daff2 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -41,7 +41,7 @@
 #include <linux/delay.h> /* ssleep prototype */
 #include <linux/kthread.h>
 #include <linux/semaphore.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi_host.h>
 
 #include "aacraid.h"
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index e4f3e22..3ecbf20 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -160,7 +160,6 @@ static const struct pci_device_id aac_pci_tbl[] = {
 	{ 0x9005, 0x028b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 62 }, /* Adaptec PMC Series 6 (Tupelo) */
 	{ 0x9005, 0x028c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 63 }, /* Adaptec PMC Series 7 (Denali) */
 	{ 0x9005, 0x028d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 64 }, /* Adaptec PMC Series 8 */
-	{ 0x9005, 0x028f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 65 }, /* Adaptec PMC Series 9 */
 	{ 0,}
 };
 MODULE_DEVICE_TABLE(pci, aac_pci_tbl);
@@ -239,7 +238,6 @@ static struct aac_driver_ident aac_drivers[] = {
 	{ aac_src_init, "aacraid", "ADAPTEC ", "RAID            ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 6 (Tupelo) */
 	{ aac_srcv_init, "aacraid", "ADAPTEC ", "RAID            ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 7 (Denali) */
 	{ aac_srcv_init, "aacraid", "ADAPTEC ", "RAID            ", 2, AAC_QUIRK_SRC }, /* Adaptec PMC Series 8 */
-	{ aac_srcv_init, "aacraid", "ADAPTEC ", "RAID            ", 2, AAC_QUIRK_SRC } /* Adaptec PMC Series 9 */
 };
 
 /**
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 9e45749..af032c4 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -61,7 +61,7 @@
 #include <linux/circ_buf.h>
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index 9d253cb..d9e1521 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -27,7 +27,7 @@
 #include <linux/fs.h>
 #include <linux/pci.h>
 #include <linux/firmware.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/fcntl.h>
 
 #include "bfad_drv.h"
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 0990130..c639d5a 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -127,13 +127,6 @@ module_param_named(log_fka, bnx2fc_log_fka, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(log_fka, " Print message to kernel log when fcoe is "
 	"initiating a FIP keep alive when debug logging is enabled.");
 
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2fc_cpu_notifier = {
-	.notifier_call = bnx2fc_cpu_callback,
-};
-
 static inline struct net_device *bnx2fc_netdev(const struct fc_lport *lport)
 {
 	return ((struct bnx2fc_interface *)
@@ -2622,37 +2615,19 @@ static void bnx2fc_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-/**
- * bnx2fc_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:    The callback data block
- * @action: The event triggering the callback
- * @hcpu:   The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for fcoe
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu)
-{
-	unsigned cpu = (unsigned long)hcpu;
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(PFX "CPU %x online: Create Rx thread\n", cpu);
-		bnx2fc_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2fc_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2fc_cpu_online(unsigned int cpu)
+{
+	printk(PFX "CPU %x online: Create Rx thread\n", cpu);
+	bnx2fc_percpu_thread_create(cpu);
+	return 0;
+}
+
+static int bnx2fc_cpu_dead(unsigned int cpu)
+{
+	printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2fc_percpu_thread_destroy(cpu);
+	return 0;
 }
 
 static int bnx2fc_slave_configure(struct scsi_device *sdev)
@@ -2664,6 +2639,8 @@ static int bnx2fc_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
+static enum cpuhp_state bnx2fc_online_state;
+
 /**
  * bnx2fc_mod_init - module init entry point
  *
@@ -2724,21 +2701,31 @@ static int __init bnx2fc_mod_init(void)
 		spin_lock_init(&p->fp_work_lock);
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
-	for_each_online_cpu(cpu) {
+	for_each_online_cpu(cpu)
 		bnx2fc_percpu_thread_create(cpu);
-	}
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2fc:online",
+				       bnx2fc_cpu_online, NULL);
+	if (rc < 0)
+		goto stop_threads;
+	bnx2fc_online_state = rc;
 
-	cpu_notifier_register_done();
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD, "scsi/bnx2fc:dead",
+				  NULL, bnx2fc_cpu_dead);
+	put_online_cpus();
 
 	cnic_register_driver(CNIC_ULP_FCOE, &bnx2fc_cnic_cb);
 
 	return 0;
 
+stop_threads:
+	for_each_online_cpu(cpu)
+		bnx2fc_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	kthread_stop(l2_thread);
 free_wq:
 	destroy_workqueue(bnx2fc_wq);
 release_bt:
@@ -2797,16 +2784,16 @@ static void __exit bnx2fc_mod_exit(void)
 	if (l2_thread)
 		kthread_stop(l2_thread);
 
-	cpu_notifier_register_begin();
-
+	get_online_cpus();
 	/* Destroy per cpu threads */
 	for_each_online_cpu(cpu) {
 		bnx2fc_percpu_thread_destroy(cpu);
 	}
 
-	__unregister_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	cpuhp_remove_state_nocalls(bnx2fc_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD);
 
-	cpu_notifier_register_done();
+	put_online_cpus();
 
 	destroy_workqueue(bnx2fc_wq);
 	/*
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index c8b410c..86afc00 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
+++ b/drivers/scsi/bnx2i/bnx2i_init.c
@@ -70,14 +70,6 @@ u64 iscsi_error_mask = 0x00;
 
 DEFINE_PER_CPU(struct bnx2i_percpu_s, bnx2i_percpu);
 
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2i_cpu_notifier = {
-	.notifier_call = bnx2i_cpu_callback,
-};
-
-
 /**
  * bnx2i_identify_device - identifies NetXtreme II device type
  * @hba: 		Adapter structure pointer
@@ -461,41 +453,21 @@ static void bnx2i_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-
-/**
- * bnx2i_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:	The callback data block
- * @action:	The event triggering the callback
- * @hcpu:	The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for iSCSI
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu)
+static int bnx2i_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(KERN_INFO "bnx2i: CPU %x online: Create Rx thread\n",
-			cpu);
-		bnx2i_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(KERN_INFO "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2i_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+	pr_info("bnx2i: CPU %x online: Create Rx thread\n", cpu);
+	bnx2i_percpu_thread_create(cpu);
+	return 0;
 }
 
+static int bnx2i_cpu_dead(unsigned int cpu)
+{
+	pr_info("CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2i_percpu_thread_destroy(cpu);
+	return 0;
+}
+
+static enum cpuhp_state bnx2i_online_state;
 
 /**
  * bnx2i_mod_init - module init entry point
@@ -539,18 +511,28 @@ static int __init bnx2i_mod_init(void)
 		p->iothread = NULL;
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_create(cpu);
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2i_cpu_notifier);
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2i:online",
+				       bnx2i_cpu_online, NULL);
+	if (err < 0)
+		goto remove_threads;
+	bnx2i_online_state = err;
 
-	cpu_notifier_register_done();
-
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2I_DEAD, "scsi/bnx2i:dead",
+				  NULL, bnx2i_cpu_dead);
+	put_online_cpus();
 	return 0;
 
+remove_threads:
+	for_each_online_cpu(cpu)
+		bnx2i_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	cnic_unregister_driver(CNIC_ULP_ISCSI);
 unreg_xport:
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 out:
@@ -587,14 +569,14 @@ static void __exit bnx2i_mod_exit(void)
 	}
 	mutex_unlock(&bnx2i_dev_lock);
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_destroy(cpu);
 
-	__unregister_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	cpuhp_remove_state_nocalls(bnx2i_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2I_DEAD);
+	put_online_cpus();
 
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 	cnic_unregister_driver(CNIC_ULP_ISCSI);
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 9e6f647..9a2fdc3 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -189,7 +189,6 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
 				struct l2t_entry *e)
 {
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);
-	int t4 = is_t4(lldi->adapter_type);
 	int wscale = cxgbi_sock_compute_wscale(csk->mss_idx);
 	unsigned long long opt0;
 	unsigned int opt2;
@@ -232,7 +231,7 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
 			csk, &req->local_ip, ntohs(req->local_port),
 			&req->peer_ip, ntohs(req->peer_port),
 			csk->atid, csk->rss_qid);
-	} else {
+	} else if (is_t5(lldi->adapter_type)) {
 		struct cpl_t5_act_open_req *req =
 				(struct cpl_t5_act_open_req *)skb->head;
 		u32 isn = (prandom_u32() & ~7UL) - 1;
@@ -260,12 +259,45 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb,
 			csk, &req->local_ip, ntohs(req->local_port),
 			&req->peer_ip, ntohs(req->peer_port),
 			csk->atid, csk->rss_qid);
+	} else {
+		struct cpl_t6_act_open_req *req =
+				(struct cpl_t6_act_open_req *)skb->head;
+		u32 isn = (prandom_u32() & ~7UL) - 1;
+
+		INIT_TP_WR(req, 0);
+		OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ,
+							    qid_atid));
+		req->local_port = csk->saddr.sin_port;
+		req->peer_port = csk->daddr.sin_port;
+		req->local_ip = csk->saddr.sin_addr.s_addr;
+		req->peer_ip = csk->daddr.sin_addr.s_addr;
+		req->opt0 = cpu_to_be64(opt0);
+		req->params = cpu_to_be64(FILTER_TUPLE_V(
+				cxgb4_select_ntuple(
+					csk->cdev->ports[csk->port_id],
+					csk->l2t)));
+		req->rsvd = cpu_to_be32(isn);
+
+		opt2 |= T5_ISS_VALID;
+		opt2 |= RX_FC_DISABLE_F;
+		opt2 |= T5_OPT_2_VALID_F;
+
+		req->opt2 = cpu_to_be32(opt2);
+		req->rsvd2 = cpu_to_be32(0);
+		req->opt3 = cpu_to_be32(0);
+
+		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
+			  "csk t6 0x%p, %pI4:%u-%pI4:%u, atid %d, qid %u.\n",
+			  csk, &req->local_ip, ntohs(req->local_port),
+			  &req->peer_ip, ntohs(req->peer_port),
+			  csk->atid, csk->rss_qid);
 	}
 
 	set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id);
 
 	pr_info_ipaddr("t%d csk 0x%p,%u,0x%lx,%u, rss_qid %u.\n",
-		       (&csk->saddr), (&csk->daddr), t4 ? 4 : 5, csk,
+		       (&csk->saddr), (&csk->daddr),
+		       CHELSIO_CHIP_VERSION(lldi->adapter_type), csk,
 		       csk->state, csk->flags, csk->atid, csk->rss_qid);
 
 	cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
@@ -276,7 +308,6 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 			       struct l2t_entry *e)
 {
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev);
-	int t4 = is_t4(lldi->adapter_type);
 	int wscale = cxgbi_sock_compute_wscale(csk->mss_idx);
 	unsigned long long opt0;
 	unsigned int opt2;
@@ -294,10 +325,9 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 
 	opt2 = RX_CHANNEL_V(0) |
 		RSS_QUEUE_VALID_F |
-		RX_FC_DISABLE_F |
 		RSS_QUEUE_V(csk->rss_qid);
 
-	if (t4) {
+	if (is_t4(lldi->adapter_type)) {
 		struct cpl_act_open_req6 *req =
 			    (struct cpl_act_open_req6 *)skb->head;
 
@@ -322,7 +352,7 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 		req->params = cpu_to_be32(cxgb4_select_ntuple(
 					  csk->cdev->ports[csk->port_id],
 					  csk->l2t));
-	} else {
+	} else if (is_t5(lldi->adapter_type)) {
 		struct cpl_t5_act_open_req6 *req =
 				(struct cpl_t5_act_open_req6 *)skb->head;
 
@@ -345,12 +375,41 @@ static void send_act_open_req6(struct cxgbi_sock *csk, struct sk_buff *skb,
 		req->params = cpu_to_be64(FILTER_TUPLE_V(cxgb4_select_ntuple(
 					  csk->cdev->ports[csk->port_id],
 					  csk->l2t)));
+	} else {
+		struct cpl_t6_act_open_req6 *req =
+				(struct cpl_t6_act_open_req6 *)skb->head;
+
+		INIT_TP_WR(req, 0);
+		OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ6,
+							    qid_atid));
+		req->local_port = csk->saddr6.sin6_port;
+		req->peer_port = csk->daddr6.sin6_port;
+		req->local_ip_hi = *(__be64 *)(csk->saddr6.sin6_addr.s6_addr);
+		req->local_ip_lo = *(__be64 *)(csk->saddr6.sin6_addr.s6_addr +
+									8);
+		req->peer_ip_hi = *(__be64 *)(csk->daddr6.sin6_addr.s6_addr);
+		req->peer_ip_lo = *(__be64 *)(csk->daddr6.sin6_addr.s6_addr +
+									8);
+		req->opt0 = cpu_to_be64(opt0);
+
+		opt2 |= RX_FC_DISABLE_F;
+		opt2 |= T5_OPT_2_VALID_F;
+
+		req->opt2 = cpu_to_be32(opt2);
+
+		req->params = cpu_to_be64(FILTER_TUPLE_V(cxgb4_select_ntuple(
+					  csk->cdev->ports[csk->port_id],
+					  csk->l2t)));
+
+		req->rsvd2 = cpu_to_be32(0);
+		req->opt3 = cpu_to_be32(0);
 	}
 
 	set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id);
 
 	pr_info("t%d csk 0x%p,%u,0x%lx,%u, [%pI6]:%u-[%pI6]:%u, rss_qid %u.\n",
-		t4 ? 4 : 5, csk, csk->state, csk->flags, csk->atid,
+		CHELSIO_CHIP_VERSION(lldi->adapter_type), csk, csk->state,
+		csk->flags, csk->atid,
 		&csk->saddr6.sin6_addr, ntohs(csk->saddr.sin_port),
 		&csk->daddr6.sin6_addr, ntohs(csk->daddr.sin_port),
 		csk->rss_qid);
@@ -742,7 +801,7 @@ static void do_act_establish(struct cxgbi_device *cdev, struct sk_buff *skb)
 		       (&csk->saddr), (&csk->daddr),
 		       atid, tid, csk, csk->state, csk->flags, rcv_isn);
 
-	module_put(THIS_MODULE);
+	module_put(cdev->owner);
 
 	cxgbi_sock_get(csk);
 	csk->tid = tid;
@@ -891,7 +950,7 @@ static void do_act_open_rpl(struct cxgbi_device *cdev, struct sk_buff *skb)
 	if (is_neg_adv(status))
 		goto rel_skb;
 
-	module_put(THIS_MODULE);
+	module_put(cdev->owner);
 
 	if (status && status != CPL_ERR_TCAM_FULL &&
 	    status != CPL_ERR_CONN_EXIST &&
@@ -1173,6 +1232,101 @@ static void do_rx_iscsi_hdr(struct cxgbi_device *cdev, struct sk_buff *skb)
 	__kfree_skb(skb);
 }
 
+static void do_rx_iscsi_data(struct cxgbi_device *cdev, struct sk_buff *skb)
+{
+	struct cxgbi_sock *csk;
+	struct cpl_iscsi_hdr *cpl = (struct cpl_iscsi_hdr *)skb->data;
+	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
+	struct tid_info *t = lldi->tids;
+	struct sk_buff *lskb;
+	u32 tid = GET_TID(cpl);
+	u16 pdu_len_ddp = be16_to_cpu(cpl->pdu_len_ddp);
+
+	csk = lookup_tid(t, tid);
+	if (unlikely(!csk)) {
+		pr_err("can't find conn. for tid %u.\n", tid);
+		goto rel_skb;
+	}
+
+	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
+		  "csk 0x%p,%u,0x%lx, tid %u, skb 0x%p,%u, 0x%x.\n",
+		  csk, csk->state, csk->flags, csk->tid, skb,
+		  skb->len, pdu_len_ddp);
+
+	spin_lock_bh(&csk->lock);
+
+	if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) {
+		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
+			  "csk 0x%p,%u,0x%lx,%u, bad state.\n",
+			  csk, csk->state, csk->flags, csk->tid);
+
+		if (csk->state != CTP_ABORTING)
+			goto abort_conn;
+		else
+			goto discard;
+	}
+
+	cxgbi_skcb_tcp_seq(skb) = be32_to_cpu(cpl->seq);
+	cxgbi_skcb_flags(skb) = 0;
+
+	skb_reset_transport_header(skb);
+	__skb_pull(skb, sizeof(*cpl));
+	__pskb_trim(skb, ntohs(cpl->len));
+
+	if (!csk->skb_ulp_lhdr)
+		csk->skb_ulp_lhdr = skb;
+
+	lskb = csk->skb_ulp_lhdr;
+	cxgbi_skcb_set_flag(lskb, SKCBF_RX_DATA);
+
+	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
+		  "csk 0x%p,%u,0x%lx, skb 0x%p data, 0x%p.\n",
+		  csk, csk->state, csk->flags, skb, lskb);
+
+	__skb_queue_tail(&csk->receive_queue, skb);
+	spin_unlock_bh(&csk->lock);
+	return;
+
+abort_conn:
+	send_abort_req(csk);
+discard:
+	spin_unlock_bh(&csk->lock);
+rel_skb:
+	__kfree_skb(skb);
+}
+
+static void
+cxgb4i_process_ddpvld(struct cxgbi_sock *csk,
+		      struct sk_buff *skb, u32 ddpvld)
+{
+	if (ddpvld & (1 << CPL_RX_DDP_STATUS_HCRC_SHIFT)) {
+		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, hcrc bad 0x%lx.\n",
+			csk, skb, ddpvld, cxgbi_skcb_flags(skb));
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_HCRC_ERR);
+	}
+
+	if (ddpvld & (1 << CPL_RX_DDP_STATUS_DCRC_SHIFT)) {
+		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, dcrc bad 0x%lx.\n",
+			csk, skb, ddpvld, cxgbi_skcb_flags(skb));
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_DCRC_ERR);
+	}
+
+	if (ddpvld & (1 << CPL_RX_DDP_STATUS_PAD_SHIFT)) {
+		log_debug(1 << CXGBI_DBG_PDU_RX,
+			  "csk 0x%p, lhdr 0x%p, status 0x%x, pad bad.\n",
+			  csk, skb, ddpvld);
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_PAD_ERR);
+	}
+
+	if ((ddpvld & (1 << CPL_RX_DDP_STATUS_DDP_SHIFT)) &&
+	    !cxgbi_skcb_test_flag(skb, SKCBF_RX_DATA)) {
+		log_debug(1 << CXGBI_DBG_PDU_RX,
+			  "csk 0x%p, lhdr 0x%p, 0x%x, data ddp'ed.\n",
+			  csk, skb, ddpvld);
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_DATA_DDPD);
+	}
+}
+
 static void do_rx_data_ddp(struct cxgbi_device *cdev,
 				  struct sk_buff *skb)
 {
@@ -1182,7 +1336,7 @@ static void do_rx_data_ddp(struct cxgbi_device *cdev,
 	unsigned int tid = GET_TID(rpl);
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
 	struct tid_info *t = lldi->tids;
-	unsigned int status = ntohl(rpl->ddpvld);
+	u32 ddpvld = be32_to_cpu(rpl->ddpvld);
 
 	csk = lookup_tid(t, tid);
 	if (unlikely(!csk)) {
@@ -1192,7 +1346,7 @@ static void do_rx_data_ddp(struct cxgbi_device *cdev,
 
 	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
 		"csk 0x%p,%u,0x%lx, skb 0x%p,0x%x, lhdr 0x%p.\n",
-		csk, csk->state, csk->flags, skb, status, csk->skb_ulp_lhdr);
+		csk, csk->state, csk->flags, skb, ddpvld, csk->skb_ulp_lhdr);
 
 	spin_lock_bh(&csk->lock);
 
@@ -1220,29 +1374,8 @@ static void do_rx_data_ddp(struct cxgbi_device *cdev,
 		pr_info("tid 0x%x, RX_DATA_DDP pdulen %u != %u.\n",
 			csk->tid, ntohs(rpl->len), cxgbi_skcb_rx_pdulen(lskb));
 
-	if (status & (1 << CPL_RX_DDP_STATUS_HCRC_SHIFT)) {
-		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, hcrc bad 0x%lx.\n",
-			csk, lskb, status, cxgbi_skcb_flags(lskb));
-		cxgbi_skcb_set_flag(lskb, SKCBF_RX_HCRC_ERR);
-	}
-	if (status & (1 << CPL_RX_DDP_STATUS_DCRC_SHIFT)) {
-		pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, dcrc bad 0x%lx.\n",
-			csk, lskb, status, cxgbi_skcb_flags(lskb));
-		cxgbi_skcb_set_flag(lskb, SKCBF_RX_DCRC_ERR);
-	}
-	if (status & (1 << CPL_RX_DDP_STATUS_PAD_SHIFT)) {
-		log_debug(1 << CXGBI_DBG_PDU_RX,
-			"csk 0x%p, lhdr 0x%p, status 0x%x, pad bad.\n",
-			csk, lskb, status);
-		cxgbi_skcb_set_flag(lskb, SKCBF_RX_PAD_ERR);
-	}
-	if ((status & (1 << CPL_RX_DDP_STATUS_DDP_SHIFT)) &&
-		!cxgbi_skcb_test_flag(lskb, SKCBF_RX_DATA)) {
-		log_debug(1 << CXGBI_DBG_PDU_RX,
-			"csk 0x%p, lhdr 0x%p, 0x%x, data ddp'ed.\n",
-			csk, lskb, status);
-		cxgbi_skcb_set_flag(lskb, SKCBF_RX_DATA_DDPD);
-	}
+	cxgb4i_process_ddpvld(csk, lskb, ddpvld);
+
 	log_debug(1 << CXGBI_DBG_PDU_RX,
 		"csk 0x%p, lskb 0x%p, f 0x%lx.\n",
 		csk, lskb, cxgbi_skcb_flags(lskb));
@@ -1260,6 +1393,98 @@ static void do_rx_data_ddp(struct cxgbi_device *cdev,
 	__kfree_skb(skb);
 }
 
+static void
+do_rx_iscsi_cmp(struct cxgbi_device *cdev, struct sk_buff *skb)
+{
+	struct cxgbi_sock *csk;
+	struct cpl_rx_iscsi_cmp *rpl = (struct cpl_rx_iscsi_cmp *)skb->data;
+	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
+	struct tid_info *t = lldi->tids;
+	struct sk_buff *data_skb = NULL;
+	u32 tid = GET_TID(rpl);
+	u32 ddpvld = be32_to_cpu(rpl->ddpvld);
+	u32 seq = be32_to_cpu(rpl->seq);
+	u16 pdu_len_ddp = be16_to_cpu(rpl->pdu_len_ddp);
+
+	csk = lookup_tid(t, tid);
+	if (unlikely(!csk)) {
+		pr_err("can't find connection for tid %u.\n", tid);
+		goto rel_skb;
+	}
+
+	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX,
+		  "csk 0x%p,%u,0x%lx, skb 0x%p,0x%x, lhdr 0x%p, len %u, "
+		  "pdu_len_ddp %u, status %u.\n",
+		  csk, csk->state, csk->flags, skb, ddpvld, csk->skb_ulp_lhdr,
+		  ntohs(rpl->len), pdu_len_ddp,  rpl->status);
+
+	spin_lock_bh(&csk->lock);
+
+	if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) {
+		log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
+			  "csk 0x%p,%u,0x%lx,%u, bad state.\n",
+			  csk, csk->state, csk->flags, csk->tid);
+
+		if (csk->state != CTP_ABORTING)
+			goto abort_conn;
+		else
+			goto discard;
+	}
+
+	cxgbi_skcb_tcp_seq(skb) = seq;
+	cxgbi_skcb_flags(skb) = 0;
+	cxgbi_skcb_rx_pdulen(skb) = 0;
+
+	skb_reset_transport_header(skb);
+	__skb_pull(skb, sizeof(*rpl));
+	__pskb_trim(skb, be16_to_cpu(rpl->len));
+
+	csk->rcv_nxt = seq + pdu_len_ddp;
+
+	if (csk->skb_ulp_lhdr) {
+		data_skb = skb_peek(&csk->receive_queue);
+		if (!data_skb ||
+		    !cxgbi_skcb_test_flag(data_skb, SKCBF_RX_DATA)) {
+			pr_err("Error! freelist data not found 0x%p, tid %u\n",
+			       data_skb, tid);
+
+			goto abort_conn;
+		}
+		__skb_unlink(data_skb, &csk->receive_queue);
+
+		cxgbi_skcb_set_flag(skb, SKCBF_RX_DATA);
+
+		__skb_queue_tail(&csk->receive_queue, skb);
+		__skb_queue_tail(&csk->receive_queue, data_skb);
+	} else {
+		 __skb_queue_tail(&csk->receive_queue, skb);
+	}
+
+	csk->skb_ulp_lhdr = NULL;
+
+	cxgbi_skcb_set_flag(skb, SKCBF_RX_HDR);
+	cxgbi_skcb_set_flag(skb, SKCBF_RX_STATUS);
+	cxgbi_skcb_set_flag(skb, SKCBF_RX_ISCSI_COMPL);
+	cxgbi_skcb_rx_ddigest(skb) = be32_to_cpu(rpl->ulp_crc);
+
+	cxgb4i_process_ddpvld(csk, skb, ddpvld);
+
+	log_debug(1 << CXGBI_DBG_PDU_RX, "csk 0x%p, skb 0x%p, f 0x%lx.\n",
+		  csk, skb, cxgbi_skcb_flags(skb));
+
+	cxgbi_conn_pdu_ready(csk);
+	spin_unlock_bh(&csk->lock);
+
+	return;
+
+abort_conn:
+	send_abort_req(csk);
+discard:
+	spin_unlock_bh(&csk->lock);
+rel_skb:
+	__kfree_skb(skb);
+}
+
 static void do_fw4_ack(struct cxgbi_device *cdev, struct sk_buff *skb)
 {
 	struct cxgbi_sock *csk;
@@ -1382,7 +1607,6 @@ static int init_act_open(struct cxgbi_sock *csk)
 	void *daddr;
 	unsigned int step;
 	unsigned int size, size6;
-	int t4 = is_t4(lldi->adapter_type);
 	unsigned int linkspeed;
 	unsigned int rcv_winf, snd_winf;
 
@@ -1428,12 +1652,15 @@ static int init_act_open(struct cxgbi_sock *csk)
 		cxgb4_clip_get(ndev, (const u32 *)&csk->saddr6.sin6_addr, 1);
 #endif
 
-	if (t4) {
+	if (is_t4(lldi->adapter_type)) {
 		size = sizeof(struct cpl_act_open_req);
 		size6 = sizeof(struct cpl_act_open_req6);
-	} else {
+	} else if (is_t5(lldi->adapter_type)) {
 		size = sizeof(struct cpl_t5_act_open_req);
 		size6 = sizeof(struct cpl_t5_act_open_req6);
+	} else {
+		size = sizeof(struct cpl_t6_act_open_req);
+		size6 = sizeof(struct cpl_t6_act_open_req6);
 	}
 
 	if (csk->csk_family == AF_INET)
@@ -1452,8 +1679,8 @@ static int init_act_open(struct cxgbi_sock *csk)
 		csk->mtu = dst_mtu(csk->dst);
 	cxgb4_best_mtu(lldi->mtus, csk->mtu, &csk->mss_idx);
 	csk->tx_chan = cxgb4_port_chan(ndev);
-	/* SMT two entries per row */
-	csk->smac_idx = ((cxgb4_port_viid(ndev) & 0x7F)) << 1;
+	csk->smac_idx = cxgb4_tp_smt_idx(lldi->adapter_type,
+					 cxgb4_port_viid(ndev));
 	step = lldi->ntxq / lldi->nchan;
 	csk->txq_idx = cxgb4_port_idx(ndev) * step;
 	step = lldi->nrxq / lldi->nchan;
@@ -1486,7 +1713,11 @@ static int init_act_open(struct cxgbi_sock *csk)
 		       csk->mtu, csk->mss_idx, csk->smac_idx);
 
 	/* must wait for either a act_open_rpl or act_open_establish */
-	try_module_get(THIS_MODULE);
+	if (!try_module_get(cdev->owner)) {
+		pr_err("%s, try_module_get failed.\n", ndev->name);
+		goto rel_resource;
+	}
+
 	cxgbi_sock_set_state(csk, CTP_ACTIVE_OPEN);
 	if (csk->csk_family == AF_INET)
 		send_act_open_req(csk, skb, csk->l2t);
@@ -1521,10 +1752,11 @@ static cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
 	[CPL_CLOSE_CON_RPL] = do_close_con_rpl,
 	[CPL_FW4_ACK] = do_fw4_ack,
 	[CPL_ISCSI_HDR] = do_rx_iscsi_hdr,
-	[CPL_ISCSI_DATA] = do_rx_iscsi_hdr,
+	[CPL_ISCSI_DATA] = do_rx_iscsi_data,
 	[CPL_SET_TCB_RPL] = do_set_tcb_rpl,
 	[CPL_RX_DATA_DDP] = do_rx_data_ddp,
 	[CPL_RX_ISCSI_DDP] = do_rx_data_ddp,
+	[CPL_RX_ISCSI_CMP] = do_rx_iscsi_cmp,
 	[CPL_RX_DATA] = do_rx_data,
 };
 
@@ -1794,10 +2026,12 @@ static void *t4_uld_add(const struct cxgb4_lld_info *lldi)
 	cdev->nports = lldi->nports;
 	cdev->mtus = lldi->mtus;
 	cdev->nmtus = NMTUS;
-	cdev->rx_credit_thres = cxgb4i_rx_credit_thres;
+	cdev->rx_credit_thres = (CHELSIO_CHIP_VERSION(lldi->adapter_type) <=
+				 CHELSIO_T5) ? cxgb4i_rx_credit_thres : 0;
 	cdev->skb_tx_rsvd = CXGB4I_TX_HEADER_LEN;
 	cdev->skb_rx_extra = sizeof(struct cpl_iscsi_hdr);
 	cdev->itp = &cxgb4i_iscsi_transport;
+	cdev->owner = THIS_MODULE;
 
 	cdev->pfvf = FW_VIID_PFN_G(cxgb4_port_viid(lldi->ports[0]))
 			<< FW_VIID_PFN_S;
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 2ffe029..9167bcd 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -642,6 +642,12 @@ static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr)
 			n->dev->name, ndev->name, mtu);
 	}
 
+	if (!(ndev->flags & IFF_UP) || !netif_carrier_ok(ndev)) {
+		pr_info("%s interface not up.\n", ndev->name);
+		err = -ENETDOWN;
+		goto rel_neigh;
+	}
+
 	cdev = cxgbi_device_find_by_netdev(ndev, &port);
 	if (!cdev) {
 		pr_info("dst %pI4, %s, NOT cxgbi device.\n",
@@ -736,6 +742,12 @@ static struct cxgbi_sock *cxgbi_check_route6(struct sockaddr *dst_addr)
 	}
 	ndev = n->dev;
 
+	if (!(ndev->flags & IFF_UP) || !netif_carrier_ok(ndev)) {
+		pr_info("%s interface not up.\n", ndev->name);
+		err = -ENETDOWN;
+		goto rel_rt;
+	}
+
 	if (ipv6_addr_is_multicast(&daddr6->sin6_addr)) {
 		pr_info("multi-cast route %pI6 port %u, dev %s.\n",
 			daddr6->sin6_addr.s6_addr,
@@ -896,6 +908,7 @@ EXPORT_SYMBOL_GPL(cxgbi_sock_fail_act_open);
 void cxgbi_sock_act_open_req_arp_failure(void *handle, struct sk_buff *skb)
 {
 	struct cxgbi_sock *csk = (struct cxgbi_sock *)skb->sk;
+	struct module *owner = csk->cdev->owner;
 
 	log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
 		csk, (csk)->state, (csk)->flags, (csk)->tid);
@@ -906,6 +919,8 @@ void cxgbi_sock_act_open_req_arp_failure(void *handle, struct sk_buff *skb)
 	spin_unlock_bh(&csk->lock);
 	cxgbi_sock_put(csk);
 	__kfree_skb(skb);
+
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(cxgbi_sock_act_open_req_arp_failure);
 
@@ -1574,6 +1589,25 @@ static int skb_read_pdu_bhs(struct iscsi_conn *conn, struct sk_buff *skb)
 		return -EIO;
 	}
 
+	if (cxgbi_skcb_test_flag(skb, SKCBF_RX_ISCSI_COMPL) &&
+	    cxgbi_skcb_test_flag(skb, SKCBF_RX_DATA_DDPD)) {
+		/* If completion flag is set and data is directly
+		 * placed in to the host memory then update
+		 * task->exp_datasn to the datasn in completion
+		 * iSCSI hdr as T6 adapter generates completion only
+		 * for the last pdu of a sequence.
+		 */
+		itt_t itt = ((struct iscsi_data *)skb->data)->itt;
+		struct iscsi_task *task = iscsi_itt_to_ctask(conn, itt);
+		u32 data_sn = be32_to_cpu(((struct iscsi_data *)
+							skb->data)->datasn);
+		if (task && task->sc) {
+			struct iscsi_tcp_task *tcp_task = task->dd_data;
+
+			tcp_task->exp_datasn = data_sn;
+		}
+	}
+
 	return read_pdu_skb(conn, skb, 0, 0);
 }
 
@@ -1627,15 +1661,15 @@ static void csk_return_rx_credits(struct cxgbi_sock *csk, int copied)
 		csk->rcv_wup, cdev->rx_credit_thres,
 		csk->rcv_win);
 
+	if (!cdev->rx_credit_thres)
+		return;
+
 	if (csk->state != CTP_ESTABLISHED)
 		return;
 
 	credits = csk->copied_seq - csk->rcv_wup;
 	if (unlikely(!credits))
 		return;
-	if (unlikely(cdev->rx_credit_thres == 0))
-		return;
-
 	must_send = credits + 16384 >= csk->rcv_win;
 	if (must_send || credits >= cdev->rx_credit_thres)
 		csk->rcv_wup += cdev->csk_send_rx_credits(csk, credits);
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
index e780273..95ba990 100644
--- a/drivers/scsi/cxgbi/libcxgbi.h
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -207,6 +207,7 @@ enum cxgbi_skcb_flags {
 	SKCBF_RX_HDR,		/* received pdu header */
 	SKCBF_RX_DATA,		/* received pdu payload */
 	SKCBF_RX_STATUS,	/* received ddp status */
+	SKCBF_RX_ISCSI_COMPL,   /* received iscsi completion */
 	SKCBF_RX_DATA_DDPD,	/* pdu payload ddp'd */
 	SKCBF_RX_HCRC_ERR,	/* header digest error */
 	SKCBF_RX_DCRC_ERR,	/* data digest error */
@@ -467,6 +468,7 @@ struct cxgbi_device {
 	struct pci_dev *pdev;
 	struct dentry *debugfs_root;
 	struct iscsi_transport *itp;
+	struct module *owner;
 
 	unsigned int pfvf;
 	unsigned int rx_credit_thres;
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 27c0dce..5f75e63 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -37,7 +37,7 @@ MODULE_DESCRIPTION("Adaptec I2O RAID Driver");
 ////////////////////////////////////////////////////////////////
 
 #include <linux/ioctl.h>	/* For SCSI-Passthrough */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/stat.h>
 #include <linux/slab.h>		/* for kmalloc() */
diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c
index de5147a..6f9665d 100644
--- a/drivers/scsi/g_NCR5380.c
+++ b/drivers/scsi/g_NCR5380.c
@@ -37,7 +37,7 @@
 #define MAX_CARDS 8
 
 /* old-style parameters for compatibility */
-static int ncr_irq;
+static int ncr_irq = -1;
 static int ncr_addr;
 static int ncr_5380;
 static int ncr_53c400;
@@ -52,9 +52,9 @@ module_param(ncr_53c400a, int, 0);
 module_param(dtc_3181e, int, 0);
 module_param(hp_c2502, int, 0);
 
-static int irq[] = { 0, 0, 0, 0, 0, 0, 0, 0 };
+static int irq[] = { -1, -1, -1, -1, -1, -1, -1, -1 };
 module_param_array(irq, int, NULL, 0);
-MODULE_PARM_DESC(irq, "IRQ number(s)");
+MODULE_PARM_DESC(irq, "IRQ number(s) (0=none, 254=auto [default])");
 
 static int base[] = { 0, 0, 0, 0, 0, 0, 0, 0 };
 module_param_array(base, int, NULL, 0);
@@ -67,6 +67,56 @@ MODULE_PARM_DESC(card, "card type (0=NCR5380, 1=NCR53C400, 2=NCR53C400A, 3=DTC31
 MODULE_ALIAS("g_NCR5380_mmio");
 MODULE_LICENSE("GPL");
 
+static void g_NCR5380_trigger_irq(struct Scsi_Host *instance)
+{
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
+
+	/*
+	 * An interrupt is triggered whenever BSY = false, SEL = true
+	 * and a bit set in the SELECT_ENABLE_REG is asserted on the
+	 * SCSI bus.
+	 *
+	 * Note that the bus is only driven when the phase control signals
+	 * (I/O, C/D, and MSG) match those in the TCR.
+	 */
+	NCR5380_write(TARGET_COMMAND_REG,
+	              PHASE_SR_TO_TCR(NCR5380_read(STATUS_REG) & PHASE_MASK));
+	NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
+	NCR5380_write(OUTPUT_DATA_REG, hostdata->id_mask);
+	NCR5380_write(INITIATOR_COMMAND_REG,
+	              ICR_BASE | ICR_ASSERT_DATA | ICR_ASSERT_SEL);
+
+	msleep(1);
+
+	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
+	NCR5380_write(SELECT_ENABLE_REG, 0);
+	NCR5380_write(TARGET_COMMAND_REG, 0);
+}
+
+/**
+ * g_NCR5380_probe_irq - find the IRQ of a NCR5380 or equivalent
+ * @instance: SCSI host instance
+ *
+ * Autoprobe for the IRQ line used by the card by triggering an IRQ
+ * and then looking to see what interrupt actually turned up.
+ */
+
+static int g_NCR5380_probe_irq(struct Scsi_Host *instance)
+{
+	struct NCR5380_hostdata *hostdata = shost_priv(instance);
+	int irq_mask, irq;
+
+	NCR5380_read(RESET_PARITY_INTERRUPT_REG);
+	irq_mask = probe_irq_on();
+	g_NCR5380_trigger_irq(instance);
+	irq = probe_irq_off(irq_mask);
+	NCR5380_read(RESET_PARITY_INTERRUPT_REG);
+
+	if (irq <= 0)
+		return NO_IRQ;
+	return irq;
+}
+
 /*
  * Configure I/O address of 53C400A or DTC436 by writing magic numbers
  * to ports 0x779 and 0x379.
@@ -81,14 +131,33 @@ static void magic_configure(int idx, u8 irq, u8 magic[])
 	outb(magic[3], 0x379);
 	outb(magic[4], 0x379);
 
-	/* allowed IRQs for HP C2502 */
-	if (irq != 2 && irq != 3 && irq != 4 && irq != 5 && irq != 7)
-		irq = 0;
+	if (irq == 9)
+		irq = 2;
+
 	if (idx >= 0 && idx <= 7)
 		cfg = 0x80 | idx | (irq << 4);
 	outb(cfg, 0x379);
 }
 
+static irqreturn_t legacy_empty_irq_handler(int irq, void *dev_id)
+{
+	return IRQ_HANDLED;
+}
+
+static int legacy_find_free_irq(int *irq_table)
+{
+	while (*irq_table != -1) {
+		if (!request_irq(*irq_table, legacy_empty_irq_handler,
+		                 IRQF_PROBE_SHARED, "Test IRQ",
+		                 (void *)irq_table)) {
+			free_irq(*irq_table, (void *) irq_table);
+			return *irq_table;
+		}
+		irq_table++;
+	}
+	return -1;
+}
+
 static unsigned int ncr_53c400a_ports[] = {
 	0x280, 0x290, 0x300, 0x310, 0x330, 0x340, 0x348, 0x350, 0
 };
@@ -101,6 +170,9 @@ static u8 ncr_53c400a_magic[] = {	/* 53C400A & DTC436 */
 static u8 hp_c2502_magic[] = {	/* HP C2502 */
 	0x0f, 0x22, 0xf0, 0x20, 0x80
 };
+static int hp_c2502_irqs[] = {
+	9, 5, 7, 3, 4, -1
+};
 
 static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
 			struct device *pdev, int base, int irq, int board)
@@ -248,6 +320,13 @@ static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
 		}
 	}
 
+	/* Check for vacant slot */
+	NCR5380_write(MODE_REG, 0);
+	if (NCR5380_read(MODE_REG) != 0) {
+		ret = -ENODEV;
+		goto out_unregister;
+	}
+
 	ret = NCR5380_init(instance, flags | FLAG_LATE_DMA_SETUP);
 	if (ret)
 		goto out_unregister;
@@ -262,29 +341,57 @@ static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
 
 	NCR5380_maybe_reset_bus(instance);
 
-	if (irq != IRQ_AUTO)
-		instance->irq = irq;
-	else
-		instance->irq = NCR5380_probe_irq(instance, 0xffff);
-
 	/* Compatibility with documented NCR5380 kernel parameters */
-	if (instance->irq == 255)
-		instance->irq = NO_IRQ;
+	if (irq == 255 || irq == 0)
+		irq = NO_IRQ;
+	else if (irq == -1)
+		irq = IRQ_AUTO;
 
-	if (instance->irq != NO_IRQ) {
-		/* set IRQ for HP C2502 */
-		if (board == BOARD_HP_C2502)
-			magic_configure(port_idx, instance->irq, magic);
-		if (request_irq(instance->irq, generic_NCR5380_intr,
-				0, "NCR5380", instance)) {
-			printk(KERN_WARNING "scsi%d : IRQ%d not free, interrupts disabled\n", instance->host_no, instance->irq);
-			instance->irq = NO_IRQ;
+	if (board == BOARD_HP_C2502) {
+		int *irq_table = hp_c2502_irqs;
+		int board_irq = -1;
+
+		switch (irq) {
+		case NO_IRQ:
+			board_irq = 0;
+			break;
+		case IRQ_AUTO:
+			board_irq = legacy_find_free_irq(irq_table);
+			break;
+		default:
+			while (*irq_table != -1)
+				if (*irq_table++ == irq)
+					board_irq = irq;
 		}
+
+		if (board_irq <= 0) {
+			board_irq = 0;
+			irq = NO_IRQ;
+		}
+
+		magic_configure(port_idx, board_irq, magic);
 	}
 
-	if (instance->irq == NO_IRQ) {
-		printk(KERN_INFO "scsi%d : interrupts not enabled. for better interactive performance,\n", instance->host_no);
-		printk(KERN_INFO "scsi%d : please jumper the board for a free IRQ.\n", instance->host_no);
+	if (irq == IRQ_AUTO) {
+		instance->irq = g_NCR5380_probe_irq(instance);
+		if (instance->irq == NO_IRQ)
+			shost_printk(KERN_INFO, instance, "no irq detected\n");
+	} else {
+		instance->irq = irq;
+		if (instance->irq == NO_IRQ)
+			shost_printk(KERN_INFO, instance, "no irq provided\n");
+	}
+
+	if (instance->irq != NO_IRQ) {
+		if (request_irq(instance->irq, generic_NCR5380_intr,
+				0, "NCR5380", instance)) {
+			instance->irq = NO_IRQ;
+			shost_printk(KERN_INFO, instance,
+			             "irq %d denied\n", instance->irq);
+		} else {
+			shost_printk(KERN_INFO, instance,
+			             "irq %d acquired\n", instance->irq);
+		}
 	}
 
 	ret = scsi_add_host(instance, pdev);
@@ -597,7 +704,7 @@ static int __init generic_NCR5380_init(void)
 	int ret = 0;
 
 	/* compatibility with old-style parameters */
-	if (irq[0] == 0 && base[0] == 0 && card[0] == -1) {
+	if (irq[0] == -1 && base[0] == 0 && card[0] == -1) {
 		irq[0] = ncr_irq;
 		base[0] = ncr_addr;
 		if (ncr_5380)
diff --git a/drivers/scsi/g_NCR5380.h b/drivers/scsi/g_NCR5380.h
index 3ce5b65..81b22d9 100644
--- a/drivers/scsi/g_NCR5380.h
+++ b/drivers/scsi/g_NCR5380.h
@@ -51,4 +51,6 @@
 #define BOARD_DTC3181E	3
 #define BOARD_HP_C2502	4
 
+#define IRQ_AUTO	254
+
 #endif /* GENERIC_NCR5380_H */
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 0a76774..d020a13 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -130,7 +130,7 @@
 
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>
 #include <linux/scatterlist.h>
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 691a093..cbc0c5f 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -1557,10 +1557,9 @@ static void hpsa_monitor_offline_device(struct ctlr_info *h,
 
 	/* Device is not on the list, add it. */
 	device = kmalloc(sizeof(*device), GFP_KERNEL);
-	if (!device) {
-		dev_warn(&h->pdev->dev, "out of memory in %s\n", __func__);
+	if (!device)
 		return;
-	}
+
 	memcpy(device->scsi3addr, scsi3addr, sizeof(device->scsi3addr));
 	spin_lock_irqsave(&h->offline_device_lock, flags);
 	list_add_tail(&device->offline_list, &h->offline_device_list);
@@ -2142,17 +2141,15 @@ static int hpsa_alloc_sg_chain_blocks(struct ctlr_info *h)
 
 	h->cmd_sg_list = kzalloc(sizeof(*h->cmd_sg_list) * h->nr_cmds,
 				GFP_KERNEL);
-	if (!h->cmd_sg_list) {
-		dev_err(&h->pdev->dev, "Failed to allocate SG list\n");
+	if (!h->cmd_sg_list)
 		return -ENOMEM;
-	}
+
 	for (i = 0; i < h->nr_cmds; i++) {
 		h->cmd_sg_list[i] = kmalloc(sizeof(*h->cmd_sg_list[i]) *
 						h->chainsize, GFP_KERNEL);
-		if (!h->cmd_sg_list[i]) {
-			dev_err(&h->pdev->dev, "Failed to allocate cmd SG\n");
+		if (!h->cmd_sg_list[i])
 			goto clean;
-		}
+
 	}
 	return 0;
 
@@ -3454,11 +3451,8 @@ static void hpsa_get_sas_address(struct ctlr_info *h, unsigned char *scsi3addr,
 		struct bmic_sense_subsystem_info *ssi;
 
 		ssi = kzalloc(sizeof(*ssi), GFP_KERNEL);
-		if (ssi == NULL) {
-			dev_warn(&h->pdev->dev,
-				"%s: out of memory\n", __func__);
+		if (!ssi)
 			return;
-		}
 
 		rc = hpsa_bmic_sense_subsystem_information(h,
 					scsi3addr, 0, ssi, sizeof(*ssi));
@@ -4335,8 +4329,6 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
 
 		currentsd[i] = kzalloc(sizeof(*currentsd[i]), GFP_KERNEL);
 		if (!currentsd[i]) {
-			dev_warn(&h->pdev->dev, "out of memory at %s:%d\n",
-				__FILE__, __LINE__);
 			h->drv_req_rescan = 1;
 			goto out;
 		}
@@ -8597,14 +8589,12 @@ static int hpsa_luns_changed(struct ctlr_info *h)
 	 */
 
 	if (!h->lastlogicals)
-		goto out;
+		return rc;
 
 	logdev = kzalloc(sizeof(*logdev), GFP_KERNEL);
-	if (!logdev) {
-		dev_warn(&h->pdev->dev,
-			"Out of memory, can't track lun changes.\n");
-		goto out;
-	}
+	if (!logdev)
+		return rc;
+
 	if (hpsa_scsi_do_report_luns(h, 1, logdev, sizeof(*logdev), 0)) {
 		dev_warn(&h->pdev->dev,
 			"report luns failed, can't track lun changes.\n");
@@ -8998,11 +8988,8 @@ static void hpsa_disable_rld_caching(struct ctlr_info *h)
 		return;
 
 	options = kzalloc(sizeof(*options), GFP_KERNEL);
-	if (!options) {
-		dev_err(&h->pdev->dev,
-			"Error: failed to disable rld caching, during alloc.\n");
+	if (!options)
 		return;
-	}
 
 	c = cmd_alloc(h);
 
diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c
index a83f705..db17ad1 100644
--- a/drivers/scsi/hptiop.c
+++ b/drivers/scsi/hptiop.c
@@ -26,7 +26,7 @@
 #include <linux/timer.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/div64.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index d9534ee..50cd011 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -95,6 +95,7 @@ static int fast_fail = 1;
 static int client_reserve = 1;
 static char partition_name[97] = "UNKNOWN";
 static unsigned int partition_number = -1;
+static LIST_HEAD(ibmvscsi_head);
 
 static struct scsi_transport_template *ibmvscsi_transport_template;
 
@@ -232,6 +233,7 @@ static void ibmvscsi_task(void *data)
 		while ((crq = crq_queue_next_crq(&hostdata->queue)) != NULL) {
 			ibmvscsi_handle_crq(crq, hostdata);
 			crq->valid = VIOSRP_CRQ_FREE;
+			wmb();
 		}
 
 		vio_enable_interrupts(vdev);
@@ -240,6 +242,7 @@ static void ibmvscsi_task(void *data)
 			vio_disable_interrupts(vdev);
 			ibmvscsi_handle_crq(crq, hostdata);
 			crq->valid = VIOSRP_CRQ_FREE;
+			wmb();
 		} else {
 			done = 1;
 		}
@@ -992,7 +995,7 @@ static void handle_cmd_rsp(struct srp_event_struct *evt_struct)
 	if (unlikely(rsp->opcode != SRP_RSP)) {
 		if (printk_ratelimit())
 			dev_warn(evt_struct->hostdata->dev,
-				 "bad SRP RSP type %d\n", rsp->opcode);
+				 "bad SRP RSP type %#02x\n", rsp->opcode);
 	}
 	
 	if (cmnd) {
@@ -2270,6 +2273,7 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	}
 
 	dev_set_drvdata(&vdev->dev, hostdata);
+	list_add_tail(&hostdata->host_list, &ibmvscsi_head);
 	return 0;
 
       add_srp_port_failed:
@@ -2291,6 +2295,7 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 static int ibmvscsi_remove(struct vio_dev *vdev)
 {
 	struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev);
+	list_del(&hostdata->host_list);
 	unmap_persist_bufs(hostdata);
 	release_event_pool(&hostdata->pool, hostdata);
 	ibmvscsi_release_crq_queue(&hostdata->queue, hostdata,
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.h b/drivers/scsi/ibmvscsi/ibmvscsi.h
index e0f6c3a..3a78755 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.h
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.h
@@ -90,6 +90,7 @@ struct event_pool {
 
 /* all driver data associated with a host adapter */
 struct ibmvscsi_host_data {
+	struct list_head host_list;
 	atomic_t request_limit;
 	int client_migrated;
 	int reset_crq;
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index c9fa356..3d3768a 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -30,6 +30,7 @@
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/string.h>
+#include <linux/delay.h>
 
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
@@ -1693,7 +1694,7 @@ static void srp_snd_msg_failed(struct scsi_info *vscsi, long rc)
 		if (!vscsi->rsp_q_timer.started) {
 			if (vscsi->rsp_q_timer.timer_pops <
 			    MAX_TIMER_POPS) {
-				kt = ktime_set(0, WAIT_NANO_SECONDS);
+				kt = WAIT_NANO_SECONDS;
 			} else {
 				/*
 				 * slide the timeslice if the maximum
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
index 98b0ca7..65c6189 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
@@ -26,6 +26,7 @@
 #ifndef __H_IBMVSCSI_TGT
 #define __H_IBMVSCSI_TGT
 
+#include <linux/interrupt.h>
 #include "libsrp.h"
 
 #define SYS_ID_NAME_LEN		64
diff --git a/drivers/scsi/ips.h b/drivers/scsi/ips.h
index 45b9566..b782bb6 100644
--- a/drivers/scsi/ips.h
+++ b/drivers/scsi/ips.h
@@ -51,7 +51,7 @@
    #define _IPS_H_
 
 #include <linux/nmi.h>
-   #include <asm/uaccess.h>
+#include <linux/uaccess.h>
    #include <asm/io.h>
 
    /*
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 9d05302..3c63c29 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -34,7 +34,7 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/blkdev.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
diff --git a/drivers/scsi/megaraid/megaraid_mm.h b/drivers/scsi/megaraid/megaraid_mm.h
index 55b425c..a30e725 100644
--- a/drivers/scsi/megaraid/megaraid_mm.h
+++ b/drivers/scsi/megaraid/megaraid_mm.h
@@ -17,7 +17,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 6484c38..d5cf15e 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -42,7 +42,7 @@
 #include <linux/delay.h>
 #include <linux/uio.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fs.h>
 #include <linux/compat.h>
 #include <linux/blkdev.h>
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 8de0eda..394fe13 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -402,6 +402,9 @@ struct MPT3SAS_DEVICE {
 	u8	block;
 	u8	tlr_snoop_check;
 	u8	ignore_delay_remove;
+	/* Iopriority Command Handling */
+	u8	ncq_prio_enable;
+
 };
 
 #define MPT3_CMD_NOT_USED	0x8000	/* free */
@@ -1458,4 +1461,7 @@ mpt3sas_setup_direct_io(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 	struct _raid_device *raid_device, Mpi2SCSIIORequest_t *mpi_request,
 	u16 smid);
 
+/* NCQ Prio Handling Check */
+bool scsih_ncq_prio_supp(struct scsi_device *sdev);
+
 #endif /* MPT3SAS_BASE_H_INCLUDED */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 050bd78..95f0f24 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -3325,8 +3325,6 @@ static DEVICE_ATTR(diag_trigger_mpi, S_IRUGO | S_IWUSR,
 
 /*********** diagnostic trigger suppport *** END ****************************/
 
-
-
 /*****************************************/
 
 struct device_attribute *mpt3sas_host_attrs[] = {
@@ -3402,9 +3400,50 @@ _ctl_device_handle_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR(sas_device_handle, S_IRUGO, _ctl_device_handle_show, NULL);
 
+/**
+ * _ctl_device_ncq_io_prio_show - send prioritized io commands to device
+ * @dev - pointer to embedded device
+ * @buf - the buffer returned
+ *
+ * A sysfs 'read/write' sdev attribute, only works with SATA
+ */
+static ssize_t
+_ctl_device_ncq_prio_enable_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	struct MPT3SAS_DEVICE *sas_device_priv_data = sdev->hostdata;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			sas_device_priv_data->ncq_prio_enable);
+}
+
+static ssize_t
+_ctl_device_ncq_prio_enable_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	struct MPT3SAS_DEVICE *sas_device_priv_data = sdev->hostdata;
+	bool ncq_prio_enable = 0;
+
+	if (kstrtobool(buf, &ncq_prio_enable))
+		return -EINVAL;
+
+	if (!scsih_ncq_prio_supp(sdev))
+		return -EINVAL;
+
+	sas_device_priv_data->ncq_prio_enable = ncq_prio_enable;
+	return strlen(buf);
+}
+static DEVICE_ATTR(sas_ncq_prio_enable, S_IRUGO | S_IWUSR,
+		   _ctl_device_ncq_prio_enable_show,
+		   _ctl_device_ncq_prio_enable_store);
+
 struct device_attribute *mpt3sas_dev_attrs[] = {
 	&dev_attr_sas_address,
 	&dev_attr_sas_device_handle,
+	&dev_attr_sas_ncq_prio_enable,
 	NULL,
 };
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 5c8f752..b5c966e 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -4053,6 +4053,8 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	struct MPT3SAS_TARGET *sas_target_priv_data;
 	struct _raid_device *raid_device;
+	struct request *rq = scmd->request;
+	int class;
 	Mpi2SCSIIORequest_t *mpi_request;
 	u32 mpi_control;
 	u16 smid;
@@ -4115,7 +4117,12 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 
 	/* set tags */
 	mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
-
+	/* NCQ Prio supported, make sure control indicated high priority */
+	if (sas_device_priv_data->ncq_prio_enable) {
+		class = IOPRIO_PRIO_CLASS(req_get_ioprio(rq));
+		if (class == IOPRIO_CLASS_RT)
+			mpi_control |= 1 << MPI2_SCSIIO_CONTROL_CMDPRI_SHIFT;
+	}
 	/* Make sure Device is not raid volume.
 	 * We do not expose raid functionality to upper layer for warpdrive.
 	 */
@@ -9099,6 +9106,31 @@ scsih_pci_mmio_enabled(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
+/**
+ * scsih__ncq_prio_supp - Check for NCQ command priority support
+ * @sdev: scsi device struct
+ *
+ * This is called when a user indicates they would like to enable
+ * ncq command priorities. This works only on SATA devices.
+ */
+bool scsih_ncq_prio_supp(struct scsi_device *sdev)
+{
+	unsigned char *buf;
+	bool ncq_prio_supp = false;
+
+	if (!scsi_device_supports_vpd(sdev))
+		return ncq_prio_supp;
+
+	buf = kmalloc(SCSI_VPD_PG_LEN, GFP_KERNEL);
+	if (!buf)
+		return ncq_prio_supp;
+
+	if (!scsi_get_vpd_page(sdev, 0x89, buf, SCSI_VPD_PG_LEN))
+		ncq_prio_supp = (buf[213] >> 4) & 1;
+
+	kfree(buf);
+	return ncq_prio_supp;
+}
 /*
  * The pci device ids are defined in mpi/mpi2_cnfg.h.
  */
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index a2960f5..e8196c5 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -52,7 +52,7 @@ static const char * osst_version = "0.99.4";
 #include <linux/delay.h>
 #include <linux/jiffies.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dma.h>
 
 /* The driver prints some debugging information on the console if DEBUG
diff --git a/drivers/scsi/qedi/Kconfig b/drivers/scsi/qedi/Kconfig
new file mode 100644
index 0000000..23ca8a2
--- /dev/null
+++ b/drivers/scsi/qedi/Kconfig
@@ -0,0 +1,10 @@
+config QEDI
+	tristate "QLogic QEDI 25/40/100Gb iSCSI Initiator Driver Support"
+	depends on PCI && SCSI
+	depends on QED
+	select SCSI_ISCSI_ATTRS
+	select QED_LL2
+	select QED_ISCSI
+	---help---
+	This driver supports iSCSI offload for the QLogic FastLinQ
+	41000 Series Converged Network Adapters.
diff --git a/drivers/scsi/qedi/Makefile b/drivers/scsi/qedi/Makefile
new file mode 100644
index 0000000..2b3e16b
--- /dev/null
+++ b/drivers/scsi/qedi/Makefile
@@ -0,0 +1,5 @@
+obj-$(CONFIG_QEDI) := qedi.o
+qedi-y := qedi_main.o qedi_iscsi.o qedi_fw.o qedi_sysfs.o \
+	    qedi_dbg.o
+
+qedi-$(CONFIG_DEBUG_FS) += qedi_debugfs.o
diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h
new file mode 100644
index 0000000..5ca3e8c
--- /dev/null
+++ b/drivers/scsi/qedi/qedi.h
@@ -0,0 +1,364 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_H_
+#define _QEDI_H_
+
+#define __PREVENT_QED_HSI__
+
+#include <scsi/scsi_transport_iscsi.h>
+#include <scsi/libiscsi.h>
+#include <scsi/scsi_host.h>
+#include <linux/uio_driver.h>
+
+#include "qedi_hsi.h"
+#include <linux/qed/qed_if.h>
+#include "qedi_dbg.h"
+#include <linux/qed/qed_iscsi_if.h>
+#include <linux/qed/qed_ll2_if.h>
+#include "qedi_version.h"
+
+#define QEDI_MODULE_NAME		"qedi"
+
+struct qedi_endpoint;
+
+/*
+ * PCI function probe defines
+ */
+#define QEDI_MODE_NORMAL	0
+#define QEDI_MODE_RECOVERY	1
+
+#define ISCSI_WQE_SET_PTU_INVALIDATE	1
+#define QEDI_MAX_ISCSI_TASK		4096
+#define QEDI_MAX_TASK_NUM		0x0FFF
+#define QEDI_MAX_ISCSI_CONNS_PER_HBA	1024
+#define QEDI_ISCSI_MAX_BDS_PER_CMD	256	/* Firmware max BDs is 256 */
+#define MAX_OUSTANDING_TASKS_PER_CON	1024
+
+#define QEDI_MAX_BD_LEN		0xffff
+#define QEDI_BD_SPLIT_SZ	0x1000
+#define QEDI_PAGE_SIZE		4096
+#define QEDI_FAST_SGE_COUNT	4
+/* MAX Length for cached SGL */
+#define MAX_SGLEN_FOR_CACHESGL	((1U << 16) - 1)
+
+#define MAX_NUM_MSIX_PF         8
+#define MIN_NUM_CPUS_MSIX(x)	min((x)->msix_count, num_online_cpus())
+
+#define QEDI_LOCAL_PORT_MIN     60000
+#define QEDI_LOCAL_PORT_MAX     61024
+#define QEDI_LOCAL_PORT_RANGE   (QEDI_LOCAL_PORT_MAX - QEDI_LOCAL_PORT_MIN)
+#define QEDI_LOCAL_PORT_INVALID	0xffff
+#define TX_RX_RING		16
+#define RX_RING			(TX_RX_RING - 1)
+#define LL2_SINGLE_BUF_SIZE	0x400
+#define QEDI_PAGE_SIZE		4096
+#define QEDI_PAGE_ALIGN(addr)	ALIGN(addr, QEDI_PAGE_SIZE)
+#define QEDI_PAGE_MASK		(~((QEDI_PAGE_SIZE) - 1))
+
+#define QEDI_PAGE_SIZE		4096
+#define QEDI_PATH_HANDLE	0xFE0000000UL
+
+struct qedi_uio_ctrl {
+	/* meta data */
+	u32 uio_hsi_version;
+
+	/* user writes */
+	u32 host_tx_prod;
+	u32 host_rx_cons;
+	u32 host_rx_bd_cons;
+	u32 host_tx_pkt_len;
+	u32 host_rx_cons_cnt;
+
+	/* driver writes */
+	u32 hw_tx_cons;
+	u32 hw_rx_prod;
+	u32 hw_rx_bd_prod;
+	u32 hw_rx_prod_cnt;
+
+	/* other */
+	u8 mac_addr[6];
+	u8 reserve[2];
+};
+
+struct qedi_rx_bd {
+	u32 rx_pkt_index;
+	u32 rx_pkt_len;
+	u16 vlan_id;
+};
+
+#define QEDI_RX_DESC_CNT	(QEDI_PAGE_SIZE / sizeof(struct qedi_rx_bd))
+#define QEDI_MAX_RX_DESC_CNT	(QEDI_RX_DESC_CNT - 1)
+#define QEDI_NUM_RX_BD		(QEDI_RX_DESC_CNT * 1)
+#define QEDI_MAX_RX_BD		(QEDI_NUM_RX_BD - 1)
+
+#define QEDI_NEXT_RX_IDX(x)	((((x) & (QEDI_MAX_RX_DESC_CNT)) ==	\
+				  (QEDI_MAX_RX_DESC_CNT - 1)) ?		\
+				 (x) + 2 : (x) + 1)
+
+struct qedi_uio_dev {
+	struct uio_info		qedi_uinfo;
+	u32			uio_dev;
+	struct list_head	list;
+
+	u32			ll2_ring_size;
+	void			*ll2_ring;
+
+	u32			ll2_buf_size;
+	void			*ll2_buf;
+
+	void			*rx_pkt;
+	void			*tx_pkt;
+
+	struct qedi_ctx		*qedi;
+	struct pci_dev		*pdev;
+	void			*uctrl;
+};
+
+/* List to maintain the skb pointers */
+struct skb_work_list {
+	struct list_head list;
+	struct sk_buff *skb;
+	u16 vlan_id;
+};
+
+/* Queue sizes in number of elements */
+#define QEDI_SQ_SIZE		MAX_OUSTANDING_TASKS_PER_CON
+#define QEDI_CQ_SIZE		2048
+#define QEDI_CMDQ_SIZE		QEDI_MAX_ISCSI_TASK
+#define QEDI_PROTO_CQ_PROD_IDX	0
+
+struct qedi_glbl_q_params {
+	u64 hw_p_cq;	/* Completion queue PBL */
+	u64 hw_p_rq;	/* Request queue PBL */
+	u64 hw_p_cmdq;	/* Command queue PBL */
+};
+
+struct global_queue {
+	union iscsi_cqe *cq;
+	dma_addr_t cq_dma;
+	u32 cq_mem_size;
+	u32 cq_cons_idx; /* Completion queue consumer index */
+
+	void *cq_pbl;
+	dma_addr_t cq_pbl_dma;
+	u32 cq_pbl_size;
+
+};
+
+struct qedi_fastpath {
+	struct qed_sb_info	*sb_info;
+	u16			sb_id;
+#define QEDI_NAME_SIZE		16
+	char			name[QEDI_NAME_SIZE];
+	struct qedi_ctx         *qedi;
+};
+
+/* Used to pass fastpath information needed to process CQEs */
+struct qedi_io_work {
+	struct list_head list;
+	struct iscsi_cqe_solicited cqe;
+	u16	que_idx;
+};
+
+/**
+ * struct iscsi_cid_queue - Per adapter iscsi cid queue
+ *
+ * @cid_que_base:           queue base memory
+ * @cid_que:                queue memory pointer
+ * @cid_q_prod_idx:         produce index
+ * @cid_q_cons_idx:         consumer index
+ * @cid_q_max_idx:          max index. used to detect wrap around condition
+ * @cid_free_cnt:           queue size
+ * @conn_cid_tbl:           iscsi cid to conn structure mapping table
+ *
+ * Per adapter iSCSI CID Queue
+ */
+struct iscsi_cid_queue {
+	void *cid_que_base;
+	u32 *cid_que;
+	u32 cid_q_prod_idx;
+	u32 cid_q_cons_idx;
+	u32 cid_q_max_idx;
+	u32 cid_free_cnt;
+	struct qedi_conn **conn_cid_tbl;
+};
+
+struct qedi_portid_tbl {
+	spinlock_t      lock;	/* Port id lock */
+	u16             start;
+	u16             max;
+	u16             next;
+	unsigned long   *table;
+};
+
+struct qedi_itt_map {
+	__le32	itt;
+	struct qedi_cmd *p_cmd;
+};
+
+/* I/O tracing entry */
+#define QEDI_IO_TRACE_SIZE             2048
+struct qedi_io_log {
+#define QEDI_IO_TRACE_REQ              0
+#define QEDI_IO_TRACE_RSP              1
+	u8 direction;
+	u16 task_id;
+	u32 cid;
+	u32 port_id;	/* Remote port fabric ID */
+	int lun;
+	u8 op;		/* SCSI CDB */
+	u8 lba[4];
+	unsigned int bufflen;	/* SCSI buffer length */
+	unsigned int sg_count;	/* Number of SG elements */
+	u8 fast_sgs;		/* number of fast sgls */
+	u8 slow_sgs;		/* number of slow sgls */
+	u8 cached_sgs;		/* number of cached sgls */
+	int result;		/* Result passed back to mid-layer */
+	unsigned long jiffies;	/* Time stamp when I/O logged */
+	int refcount;		/* Reference count for task id */
+	unsigned int blk_req_cpu; /* CPU that the task is queued on by
+				   * blk layer
+				   */
+	unsigned int req_cpu;	/* CPU that the task is queued on */
+	unsigned int intr_cpu;	/* Interrupt CPU that the task is received on */
+	unsigned int blk_rsp_cpu;/* CPU that task is actually processed and
+				  * returned to blk layer
+				  */
+	bool cached_sge;
+	bool slow_sge;
+	bool fast_sge;
+};
+
+/* Number of entries in BDQ */
+#define QEDI_BDQ_NUM		256
+#define QEDI_BDQ_BUF_SIZE	256
+
+/* DMA coherent buffers for BDQ */
+struct qedi_bdq_buf {
+	void *buf_addr;
+	dma_addr_t buf_dma;
+};
+
+/* Main port level struct */
+struct qedi_ctx {
+	struct qedi_dbg_ctx dbg_ctx;
+	struct Scsi_Host *shost;
+	struct pci_dev *pdev;
+	struct qed_dev *cdev;
+	struct qed_dev_iscsi_info dev_info;
+	struct qed_int_info int_info;
+	struct qedi_glbl_q_params *p_cpuq;
+	struct global_queue **global_queues;
+	/* uio declaration */
+	struct qedi_uio_dev *udev;
+	struct list_head ll2_skb_list;
+	spinlock_t ll2_lock;	/* Light L2 lock */
+	spinlock_t hba_lock;	/* per port lock */
+	struct task_struct *ll2_recv_thread;
+	unsigned long flags;
+#define UIO_DEV_OPENED		1
+#define QEDI_IOTHREAD_WAKE	2
+#define QEDI_IN_RECOVERY	5
+#define QEDI_IN_OFFLINE		6
+
+	u8 mac[ETH_ALEN];
+	u32 src_ip[4];
+	u8 ip_type;
+
+	/* Physical address of above array */
+	dma_addr_t hw_p_cpuq;
+
+	struct qedi_bdq_buf bdq[QEDI_BDQ_NUM];
+	void *bdq_pbl;
+	dma_addr_t bdq_pbl_dma;
+	size_t bdq_pbl_mem_size;
+	void *bdq_pbl_list;
+	dma_addr_t bdq_pbl_list_dma;
+	u8 bdq_pbl_list_num_entries;
+	void __iomem *bdq_primary_prod;
+	void __iomem *bdq_secondary_prod;
+	u16 bdq_prod_idx;
+	u16 rq_num_entries;
+
+	u32 msix_count;
+	u32 max_sqes;
+	u8 num_queues;
+	u32 max_active_conns;
+
+	struct iscsi_cid_queue cid_que;
+	struct qedi_endpoint **ep_tbl;
+	struct qedi_portid_tbl lcl_port_tbl;
+
+	/* Rx fast path intr context */
+	struct qed_sb_info	*sb_array;
+	struct qedi_fastpath	*fp_array;
+	struct qed_iscsi_tid	tasks;
+
+#define QEDI_LINK_DOWN		0
+#define QEDI_LINK_UP		1
+	atomic_t link_state;
+
+#define QEDI_RESERVE_TASK_ID	0
+#define MAX_ISCSI_TASK_ENTRIES	4096
+#define QEDI_INVALID_TASK_ID	(MAX_ISCSI_TASK_ENTRIES + 1)
+	unsigned long task_idx_map[MAX_ISCSI_TASK_ENTRIES / BITS_PER_LONG];
+	struct qedi_itt_map *itt_map;
+	u16 tid_reuse_count[QEDI_MAX_ISCSI_TASK];
+	struct qed_pf_params pf_params;
+
+	struct workqueue_struct *tmf_thread;
+	struct workqueue_struct *offload_thread;
+
+	u16 ll2_mtu;
+
+	struct workqueue_struct *dpc_wq;
+
+	spinlock_t task_idx_lock;	/* To protect gbl context */
+	s32 last_tidx_alloc;
+	s32 last_tidx_clear;
+
+	struct qedi_io_log io_trace_buf[QEDI_IO_TRACE_SIZE];
+	spinlock_t io_trace_lock;	/* prtect trace Log buf */
+	u16 io_trace_idx;
+	unsigned int intr_cpu;
+	u32 cached_sgls;
+	bool use_cached_sge;
+	u32 slow_sgls;
+	bool use_slow_sge;
+	u32 fast_sgls;
+	bool use_fast_sge;
+
+	atomic_t num_offloads;
+};
+
+struct qedi_work {
+	struct list_head list;
+	struct qedi_ctx *qedi;
+	union iscsi_cqe cqe;
+	u16     que_idx;
+	bool is_solicited;
+};
+
+struct qedi_percpu_s {
+	struct task_struct *iothread;
+	struct list_head work_list;
+	spinlock_t p_work_lock;		/* Per cpu worker lock */
+};
+
+static inline void *qedi_get_task_mem(struct qed_iscsi_tid *info, u32 tid)
+{
+	return (info->blocks[tid / info->num_tids_per_block] +
+		(tid % info->num_tids_per_block) * info->size);
+}
+
+#define QEDI_U64_HI(val) ((u32)(((u64)(val)) >> 32))
+#define QEDI_U64_LO(val) ((u32)(((u64)(val)) & 0xffffffff))
+
+#endif /* _QEDI_H_ */
diff --git a/drivers/scsi/qedi/qedi_dbg.c b/drivers/scsi/qedi/qedi_dbg.c
new file mode 100644
index 0000000..2bdedb9
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_dbg.c
@@ -0,0 +1,143 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include "qedi_dbg.h"
+#include <linux/vmalloc.h>
+
+void
+qedi_dbg_err(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+	     const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (likely(qedi) && likely(qedi->pdev))
+		pr_err("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
+		       nfunc, line, qedi->host_no, &vaf);
+	else
+		pr_err("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+void
+qedi_dbg_warn(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+	      const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedi_dbg_log & QEDI_LOG_WARN))
+		return;
+
+	if (likely(qedi) && likely(qedi->pdev))
+		pr_warn("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
+			nfunc, line, qedi->host_no, &vaf);
+	else
+		pr_warn("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+void
+qedi_dbg_notice(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedi_dbg_log & QEDI_LOG_NOTICE))
+		return;
+
+	if (likely(qedi) && likely(qedi->pdev))
+		pr_notice("[%s]:[%s:%d]:%d: %pV",
+			  dev_name(&qedi->pdev->dev), nfunc, line,
+			  qedi->host_no, &vaf);
+	else
+		pr_notice("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+void
+qedi_dbg_info(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+	      u32 level, const char *fmt, ...)
+{
+	va_list va;
+	struct va_format vaf;
+	char nfunc[32];
+
+	memset(nfunc, 0, sizeof(nfunc));
+	memcpy(nfunc, func, sizeof(nfunc) - 1);
+
+	va_start(va, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &va;
+
+	if (!(qedi_dbg_log & level))
+		return;
+
+	if (likely(qedi) && likely(qedi->pdev))
+		pr_info("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
+			nfunc, line, qedi->host_no, &vaf);
+	else
+		pr_info("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
+
+	va_end(va);
+}
+
+int
+qedi_create_sysfs_attr(struct Scsi_Host *shost, struct sysfs_bin_attrs *iter)
+{
+	int ret = 0;
+
+	for (; iter->name; iter++) {
+		ret = sysfs_create_bin_file(&shost->shost_gendev.kobj,
+					    iter->attr);
+		if (ret)
+			pr_err("Unable to create sysfs %s attr, err(%d).\n",
+			       iter->name, ret);
+	}
+	return ret;
+}
+
+void
+qedi_remove_sysfs_attr(struct Scsi_Host *shost, struct sysfs_bin_attrs *iter)
+{
+	for (; iter->name; iter++)
+		sysfs_remove_bin_file(&shost->shost_gendev.kobj, iter->attr);
+}
diff --git a/drivers/scsi/qedi/qedi_dbg.h b/drivers/scsi/qedi/qedi_dbg.h
new file mode 100644
index 0000000..c55572b
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_dbg.h
@@ -0,0 +1,144 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_DBG_H_
+#define _QEDI_DBG_H_
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include <linux/version.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <scsi/scsi_transport.h>
+#include <scsi/scsi_transport_iscsi.h>
+#include <linux/fs.h>
+
+#define __PREVENT_QED_HSI__
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/qed_if.h>
+
+extern uint qedi_dbg_log;
+
+/* Debug print level definitions */
+#define QEDI_LOG_DEFAULT	0x1		/* Set default logging mask */
+#define QEDI_LOG_INFO		0x2		/* Informational logs,
+						 * MAC address, WWPN, WWNN
+						 */
+#define QEDI_LOG_DISC		0x4		/* Init, discovery, rport */
+#define QEDI_LOG_LL2		0x8		/* LL2, VLAN logs */
+#define QEDI_LOG_CONN		0x10		/* Connection setup, cleanup */
+#define QEDI_LOG_EVT		0x20		/* Events, link, mtu */
+#define QEDI_LOG_TIMER		0x40		/* Timer events */
+#define QEDI_LOG_MP_REQ		0x80		/* Middle Path (MP) logs */
+#define QEDI_LOG_SCSI_TM	0x100		/* SCSI Aborts, Task Mgmt */
+#define QEDI_LOG_UNSOL		0x200		/* unsolicited event logs */
+#define QEDI_LOG_IO		0x400		/* scsi cmd, completion */
+#define QEDI_LOG_MQ		0x800		/* Multi Queue logs */
+#define QEDI_LOG_BSG		0x1000		/* BSG logs */
+#define QEDI_LOG_DEBUGFS	0x2000		/* debugFS logs */
+#define QEDI_LOG_LPORT		0x4000		/* lport logs */
+#define QEDI_LOG_ELS		0x8000		/* ELS logs */
+#define QEDI_LOG_NPIV		0x10000		/* NPIV logs */
+#define QEDI_LOG_SESS		0x20000		/* Conection setup, cleanup */
+#define QEDI_LOG_UIO		0x40000		/* iSCSI UIO logs */
+#define QEDI_LOG_TID		0x80000         /* FW TID context acquire,
+						 * free
+						 */
+#define QEDI_TRACK_TID		0x100000        /* Track TID state. To be
+						 * enabled only at module load
+						 * and not run-time.
+						 */
+#define QEDI_TRACK_CMD_LIST    0x300000        /* Track active cmd list nodes,
+						* done with reference to TID,
+						* hence TRACK_TID also enabled.
+						*/
+#define QEDI_LOG_NOTICE		0x40000000	/* Notice logs */
+#define QEDI_LOG_WARN		0x80000000	/* Warning logs */
+
+/* Debug context structure */
+struct qedi_dbg_ctx {
+	unsigned int host_no;
+	struct pci_dev *pdev;
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *bdf_dentry;
+#endif
+};
+
+#define QEDI_ERR(pdev, fmt, ...)	\
+		qedi_dbg_err(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDI_WARN(pdev, fmt, ...)	\
+		qedi_dbg_warn(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDI_NOTICE(pdev, fmt, ...)	\
+		qedi_dbg_notice(pdev, __func__, __LINE__, fmt, ## __VA_ARGS__)
+#define QEDI_INFO(pdev, level, fmt, ...)	\
+		qedi_dbg_info(pdev, __func__, __LINE__, level, fmt,	\
+			      ## __VA_ARGS__)
+
+void qedi_dbg_err(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		  const char *fmt, ...);
+void qedi_dbg_warn(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		   const char *fmt, ...);
+void qedi_dbg_notice(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		     const char *fmt, ...);
+void qedi_dbg_info(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
+		   u32 info, const char *fmt, ...);
+
+struct Scsi_Host;
+
+struct sysfs_bin_attrs {
+	char *name;
+	struct bin_attribute *attr;
+};
+
+int qedi_create_sysfs_attr(struct Scsi_Host *shost,
+			   struct sysfs_bin_attrs *iter);
+void qedi_remove_sysfs_attr(struct Scsi_Host *shost,
+			    struct sysfs_bin_attrs *iter);
+
+#ifdef CONFIG_DEBUG_FS
+/* DebugFS related code */
+struct qedi_list_of_funcs {
+	char *oper_str;
+	ssize_t (*oper_func)(struct qedi_dbg_ctx *qedi);
+};
+
+struct qedi_debugfs_ops {
+	char *name;
+	struct qedi_list_of_funcs *qedi_funcs;
+};
+
+#define qedi_dbg_fileops(drv, ops) \
+{ \
+	.owner  = THIS_MODULE, \
+	.open   = simple_open, \
+	.read   = drv##_dbg_##ops##_cmd_read, \
+	.write  = drv##_dbg_##ops##_cmd_write \
+}
+
+/* Used for debugfs sequential files */
+#define qedi_dbg_fileops_seq(drv, ops) \
+{ \
+	.owner = THIS_MODULE, \
+	.open = drv##_dbg_##ops##_open, \
+	.read = seq_read, \
+	.llseek = seq_lseek, \
+	.release = single_release, \
+}
+
+void qedi_dbg_host_init(struct qedi_dbg_ctx *qedi,
+			struct qedi_debugfs_ops *dops,
+			const struct file_operations *fops);
+void qedi_dbg_host_exit(struct qedi_dbg_ctx *qedi);
+void qedi_dbg_init(char *drv_name);
+void qedi_dbg_exit(void);
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* _QEDI_DBG_H_ */
diff --git a/drivers/scsi/qedi/qedi_debugfs.c b/drivers/scsi/qedi/qedi_debugfs.c
new file mode 100644
index 0000000..9559362
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_debugfs.c
@@ -0,0 +1,244 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include "qedi.h"
+#include "qedi_dbg.h"
+
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+
+int do_not_recover;
+static struct dentry *qedi_dbg_root;
+
+void
+qedi_dbg_host_init(struct qedi_dbg_ctx *qedi,
+		   struct qedi_debugfs_ops *dops,
+		   const struct file_operations *fops)
+{
+	char host_dirname[32];
+	struct dentry *file_dentry = NULL;
+
+	sprintf(host_dirname, "host%u", qedi->host_no);
+	qedi->bdf_dentry = debugfs_create_dir(host_dirname, qedi_dbg_root);
+	if (!qedi->bdf_dentry)
+		return;
+
+	while (dops) {
+		if (!(dops->name))
+			break;
+
+		file_dentry = debugfs_create_file(dops->name, 0600,
+						  qedi->bdf_dentry, qedi,
+						  fops);
+		if (!file_dentry) {
+			QEDI_INFO(qedi, QEDI_LOG_DEBUGFS,
+				  "Debugfs entry %s creation failed\n",
+				  dops->name);
+			debugfs_remove_recursive(qedi->bdf_dentry);
+			return;
+		}
+		dops++;
+		fops++;
+	}
+}
+
+void
+qedi_dbg_host_exit(struct qedi_dbg_ctx *qedi)
+{
+	debugfs_remove_recursive(qedi->bdf_dentry);
+	qedi->bdf_dentry = NULL;
+}
+
+void
+qedi_dbg_init(char *drv_name)
+{
+	qedi_dbg_root = debugfs_create_dir(drv_name, NULL);
+	if (!qedi_dbg_root)
+		QEDI_INFO(NULL, QEDI_LOG_DEBUGFS, "Init of debugfs failed\n");
+}
+
+void
+qedi_dbg_exit(void)
+{
+	debugfs_remove_recursive(qedi_dbg_root);
+	qedi_dbg_root = NULL;
+}
+
+static ssize_t
+qedi_dbg_do_not_recover_enable(struct qedi_dbg_ctx *qedi_dbg)
+{
+	if (!do_not_recover)
+		do_not_recover = 1;
+
+	QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
+		  do_not_recover);
+	return 0;
+}
+
+static ssize_t
+qedi_dbg_do_not_recover_disable(struct qedi_dbg_ctx *qedi_dbg)
+{
+	if (do_not_recover)
+		do_not_recover = 0;
+
+	QEDI_INFO(qedi_dbg, QEDI_LOG_DEBUGFS, "do_not_recover=%d\n",
+		  do_not_recover);
+	return 0;
+}
+
+static struct qedi_list_of_funcs qedi_dbg_do_not_recover_ops[] = {
+	{ "enable", qedi_dbg_do_not_recover_enable },
+	{ "disable", qedi_dbg_do_not_recover_disable },
+	{ NULL, NULL }
+};
+
+struct qedi_debugfs_ops qedi_debugfs_ops[] = {
+	{ "gbl_ctx", NULL },
+	{ "do_not_recover", qedi_dbg_do_not_recover_ops},
+	{ "io_trace", NULL },
+	{ NULL, NULL }
+};
+
+static ssize_t
+qedi_dbg_do_not_recover_cmd_write(struct file *filp, const char __user *buffer,
+				  size_t count, loff_t *ppos)
+{
+	size_t cnt = 0;
+	struct qedi_dbg_ctx *qedi_dbg =
+			(struct qedi_dbg_ctx *)filp->private_data;
+	struct qedi_list_of_funcs *lof = qedi_dbg_do_not_recover_ops;
+
+	if (*ppos)
+		return 0;
+
+	while (lof) {
+		if (!(lof->oper_str))
+			break;
+
+		if (!strncmp(lof->oper_str, buffer, strlen(lof->oper_str))) {
+			cnt = lof->oper_func(qedi_dbg);
+			break;
+		}
+
+		lof++;
+	}
+	return (count - cnt);
+}
+
+static ssize_t
+qedi_dbg_do_not_recover_cmd_read(struct file *filp, char __user *buffer,
+				 size_t count, loff_t *ppos)
+{
+	size_t cnt = 0;
+
+	if (*ppos)
+		return 0;
+
+	cnt = sprintf(buffer, "do_not_recover=%d\n", do_not_recover);
+	cnt = min_t(int, count, cnt - *ppos);
+	*ppos += cnt;
+	return cnt;
+}
+
+static int
+qedi_gbl_ctx_show(struct seq_file *s, void *unused)
+{
+	struct qedi_fastpath *fp = NULL;
+	struct qed_sb_info *sb_info = NULL;
+	struct status_block *sb = NULL;
+	struct global_queue *que = NULL;
+	int id;
+	u16 prod_idx;
+	struct qedi_ctx *qedi = s->private;
+	unsigned long flags;
+
+	seq_puts(s, " DUMP CQ CONTEXT:\n");
+
+	for (id = 0; id < MIN_NUM_CPUS_MSIX(qedi); id++) {
+		spin_lock_irqsave(&qedi->hba_lock, flags);
+		seq_printf(s, "=========FAST CQ PATH [%d] ==========\n", id);
+		fp = &qedi->fp_array[id];
+		sb_info = fp->sb_info;
+		sb = sb_info->sb_virt;
+		prod_idx = (sb->pi_array[QEDI_PROTO_CQ_PROD_IDX] &
+			    STATUS_BLOCK_PROD_INDEX_MASK);
+		seq_printf(s, "SB PROD IDX: %d\n", prod_idx);
+		que = qedi->global_queues[fp->sb_id];
+		seq_printf(s, "DRV CONS IDX: %d\n", que->cq_cons_idx);
+		seq_printf(s, "CQ complete host memory: %d\n", fp->sb_id);
+		seq_puts(s, "=========== END ==================\n\n\n");
+		spin_unlock_irqrestore(&qedi->hba_lock, flags);
+	}
+	return 0;
+}
+
+static int
+qedi_dbg_gbl_ctx_open(struct inode *inode, struct file *file)
+{
+	struct qedi_dbg_ctx *qedi_dbg = inode->i_private;
+	struct qedi_ctx *qedi = container_of(qedi_dbg, struct qedi_ctx,
+					     dbg_ctx);
+
+	return single_open(file, qedi_gbl_ctx_show, qedi);
+}
+
+static int
+qedi_io_trace_show(struct seq_file *s, void *unused)
+{
+	int id, idx = 0;
+	struct qedi_ctx *qedi = s->private;
+	struct qedi_io_log *io_log;
+	unsigned long flags;
+
+	seq_puts(s, " DUMP IO LOGS:\n");
+	spin_lock_irqsave(&qedi->io_trace_lock, flags);
+	idx = qedi->io_trace_idx;
+	for (id = 0; id < QEDI_IO_TRACE_SIZE; id++) {
+		io_log = &qedi->io_trace_buf[idx];
+		seq_printf(s, "iodir-%d:", io_log->direction);
+		seq_printf(s, "tid-0x%x:", io_log->task_id);
+		seq_printf(s, "cid-0x%x:", io_log->cid);
+		seq_printf(s, "lun-%d:", io_log->lun);
+		seq_printf(s, "op-0x%02x:", io_log->op);
+		seq_printf(s, "0x%02x%02x%02x%02x:", io_log->lba[0],
+			   io_log->lba[1], io_log->lba[2], io_log->lba[3]);
+		seq_printf(s, "buflen-%d:", io_log->bufflen);
+		seq_printf(s, "sgcnt-%d:", io_log->sg_count);
+		seq_printf(s, "res-0x%08x:", io_log->result);
+		seq_printf(s, "jif-%lu:", io_log->jiffies);
+		seq_printf(s, "blk_req_cpu-%d:", io_log->blk_req_cpu);
+		seq_printf(s, "req_cpu-%d:", io_log->req_cpu);
+		seq_printf(s, "intr_cpu-%d:", io_log->intr_cpu);
+		seq_printf(s, "blk_rsp_cpu-%d\n", io_log->blk_rsp_cpu);
+
+		idx++;
+		if (idx == QEDI_IO_TRACE_SIZE)
+			idx = 0;
+	}
+	spin_unlock_irqrestore(&qedi->io_trace_lock, flags);
+	return 0;
+}
+
+static int
+qedi_dbg_io_trace_open(struct inode *inode, struct file *file)
+{
+	struct qedi_dbg_ctx *qedi_dbg = inode->i_private;
+	struct qedi_ctx *qedi = container_of(qedi_dbg, struct qedi_ctx,
+					     dbg_ctx);
+
+	return single_open(file, qedi_io_trace_show, qedi);
+}
+
+const struct file_operations qedi_dbg_fops[] = {
+	qedi_dbg_fileops_seq(qedi, gbl_ctx),
+	qedi_dbg_fileops(qedi, do_not_recover),
+	qedi_dbg_fileops_seq(qedi, io_trace),
+	{ NULL, NULL },
+};
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
new file mode 100644
index 0000000..b1d3904
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -0,0 +1,2378 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include <linux/blkdev.h>
+#include <scsi/scsi_tcq.h>
+#include <linux/delay.h>
+
+#include "qedi.h"
+#include "qedi_iscsi.h"
+#include "qedi_gbl.h"
+
+static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
+			       struct iscsi_task *mtask);
+
+void qedi_iscsi_unmap_sg_list(struct qedi_cmd *cmd)
+{
+	struct scsi_cmnd *sc = cmd->scsi_cmd;
+
+	if (cmd->io_tbl.sge_valid && sc) {
+		cmd->io_tbl.sge_valid = 0;
+		scsi_dma_unmap(sc);
+	}
+}
+
+static void qedi_process_logout_resp(struct qedi_ctx *qedi,
+				     union iscsi_cqe *cqe,
+				     struct iscsi_task *task,
+				     struct qedi_conn *qedi_conn)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_logout_rsp *resp_hdr;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_logout_response_hdr *cqe_logout_response;
+	struct qedi_cmd *cmd;
+
+	cmd = (struct qedi_cmd *)task->dd_data;
+	cqe_logout_response = &cqe->cqe_common.iscsi_hdr.logout_response;
+	spin_lock(&session->back_lock);
+	resp_hdr = (struct iscsi_logout_rsp *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(resp_hdr, 0, sizeof(struct iscsi_hdr));
+	resp_hdr->opcode = cqe_logout_response->opcode;
+	resp_hdr->flags = cqe_logout_response->flags;
+	resp_hdr->hlength = 0;
+
+	resp_hdr->itt = build_itt(cqe->cqe_solicited.itid, conn->session->age);
+	resp_hdr->statsn = cpu_to_be32(cqe_logout_response->stat_sn);
+	resp_hdr->exp_cmdsn = cpu_to_be32(cqe_logout_response->exp_cmd_sn);
+	resp_hdr->max_cmdsn = cpu_to_be32(cqe_logout_response->max_cmd_sn);
+
+	resp_hdr->t2wait = cpu_to_be32(cqe_logout_response->time2wait);
+	resp_hdr->t2retain = cpu_to_be32(cqe_logout_response->time2retain);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+		  "Freeing tid=0x%x for cid=0x%x\n",
+		  cmd->task_id, qedi_conn->iscsi_conn_id);
+
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	} else {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Active cmd list node already deleted, tid=0x%x, cid=0x%x, io_cmd_node=%p\n",
+			  cmd->task_id, qedi_conn->iscsi_conn_id,
+			  &cmd->io_cmd);
+	}
+
+	cmd->state = RESPONSE_RECEIVED;
+	qedi_clear_task_idx(qedi, cmd->task_id);
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr, NULL, 0);
+
+	spin_unlock(&session->back_lock);
+}
+
+static void qedi_process_text_resp(struct qedi_ctx *qedi,
+				   union iscsi_cqe *cqe,
+				   struct iscsi_task *task,
+				   struct qedi_conn *qedi_conn)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_task_context *task_ctx;
+	struct iscsi_text_rsp *resp_hdr_ptr;
+	struct iscsi_text_response_hdr *cqe_text_response;
+	struct qedi_cmd *cmd;
+	int pld_len;
+	u32 *tmp;
+
+	cmd = (struct qedi_cmd *)task->dd_data;
+	task_ctx = qedi_get_task_mem(&qedi->tasks, cmd->task_id);
+
+	cqe_text_response = &cqe->cqe_common.iscsi_hdr.text_response;
+	spin_lock(&session->back_lock);
+	resp_hdr_ptr =  (struct iscsi_text_rsp *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(resp_hdr_ptr, 0, sizeof(struct iscsi_hdr));
+	resp_hdr_ptr->opcode = cqe_text_response->opcode;
+	resp_hdr_ptr->flags = cqe_text_response->flags;
+	resp_hdr_ptr->hlength = 0;
+
+	hton24(resp_hdr_ptr->dlength,
+	       (cqe_text_response->hdr_second_dword &
+		ISCSI_TEXT_RESPONSE_HDR_DATA_SEG_LEN_MASK));
+	tmp = (u32 *)resp_hdr_ptr->dlength;
+
+	resp_hdr_ptr->itt = build_itt(cqe->cqe_solicited.itid,
+				      conn->session->age);
+	resp_hdr_ptr->ttt = cqe_text_response->ttt;
+	resp_hdr_ptr->statsn = cpu_to_be32(cqe_text_response->stat_sn);
+	resp_hdr_ptr->exp_cmdsn = cpu_to_be32(cqe_text_response->exp_cmd_sn);
+	resp_hdr_ptr->max_cmdsn = cpu_to_be32(cqe_text_response->max_cmd_sn);
+
+	pld_len = cqe_text_response->hdr_second_dword &
+		  ISCSI_TEXT_RESPONSE_HDR_DATA_SEG_LEN_MASK;
+	qedi_conn->gen_pdu.resp_wr_ptr = qedi_conn->gen_pdu.resp_buf + pld_len;
+
+	memset(task_ctx, '\0', sizeof(*task_ctx));
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+		  "Freeing tid=0x%x for cid=0x%x\n",
+		  cmd->task_id, qedi_conn->iscsi_conn_id);
+
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	} else {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Active cmd list node already deleted, tid=0x%x, cid=0x%x, io_cmd_node=%p\n",
+			  cmd->task_id, qedi_conn->iscsi_conn_id,
+			  &cmd->io_cmd);
+	}
+
+	cmd->state = RESPONSE_RECEIVED;
+	qedi_clear_task_idx(qedi, cmd->task_id);
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr,
+			     qedi_conn->gen_pdu.resp_buf,
+			     (qedi_conn->gen_pdu.resp_wr_ptr -
+			      qedi_conn->gen_pdu.resp_buf));
+	spin_unlock(&session->back_lock);
+}
+
+static void qedi_tmf_resp_work(struct work_struct *work)
+{
+	struct qedi_cmd *qedi_cmd =
+				container_of(work, struct qedi_cmd, tmf_work);
+	struct qedi_conn *qedi_conn = qedi_cmd->conn;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_tm_rsp *resp_hdr_ptr;
+	struct iscsi_cls_session *cls_sess;
+	int rval = 0;
+
+	set_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+	resp_hdr_ptr =  (struct iscsi_tm_rsp *)qedi_cmd->tmf_resp_buf;
+	cls_sess = iscsi_conn_to_session(qedi_conn->cls_conn);
+
+	iscsi_block_session(session->cls_session);
+	rval = qedi_cleanup_all_io(qedi, qedi_conn, qedi_cmd->task, true);
+	if (rval) {
+		clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+		qedi_clear_task_idx(qedi, qedi_cmd->task_id);
+		iscsi_unblock_session(session->cls_session);
+		return;
+	}
+
+	iscsi_unblock_session(session->cls_session);
+	qedi_clear_task_idx(qedi, qedi_cmd->task_id);
+
+	spin_lock(&session->back_lock);
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr, NULL, 0);
+	spin_unlock(&session->back_lock);
+	kfree(resp_hdr_ptr);
+	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+}
+
+static void qedi_process_tmf_resp(struct qedi_ctx *qedi,
+				  union iscsi_cqe *cqe,
+				  struct iscsi_task *task,
+				  struct qedi_conn *qedi_conn)
+
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_tmf_response_hdr *cqe_tmp_response;
+	struct iscsi_tm_rsp *resp_hdr_ptr;
+	struct iscsi_tm *tmf_hdr;
+	struct qedi_cmd *qedi_cmd = NULL;
+	u32 *tmp;
+
+	cqe_tmp_response = &cqe->cqe_common.iscsi_hdr.tmf_response;
+
+	qedi_cmd = task->dd_data;
+	qedi_cmd->tmf_resp_buf = kzalloc(sizeof(*resp_hdr_ptr), GFP_KERNEL);
+	if (!qedi_cmd->tmf_resp_buf) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failed to allocate resp buf, cid=0x%x\n",
+			  qedi_conn->iscsi_conn_id);
+		return;
+	}
+
+	spin_lock(&session->back_lock);
+	resp_hdr_ptr =  (struct iscsi_tm_rsp *)qedi_cmd->tmf_resp_buf;
+	memset(resp_hdr_ptr, 0, sizeof(struct iscsi_tm_rsp));
+
+	/* Fill up the header */
+	resp_hdr_ptr->opcode = cqe_tmp_response->opcode;
+	resp_hdr_ptr->flags = cqe_tmp_response->hdr_flags;
+	resp_hdr_ptr->response = cqe_tmp_response->hdr_response;
+	resp_hdr_ptr->hlength = 0;
+
+	hton24(resp_hdr_ptr->dlength,
+	       (cqe_tmp_response->hdr_second_dword &
+		ISCSI_TMF_RESPONSE_HDR_DATA_SEG_LEN_MASK));
+	tmp = (u32 *)resp_hdr_ptr->dlength;
+	resp_hdr_ptr->itt = build_itt(cqe->cqe_solicited.itid,
+				      conn->session->age);
+	resp_hdr_ptr->statsn = cpu_to_be32(cqe_tmp_response->stat_sn);
+	resp_hdr_ptr->exp_cmdsn  = cpu_to_be32(cqe_tmp_response->exp_cmd_sn);
+	resp_hdr_ptr->max_cmdsn = cpu_to_be32(cqe_tmp_response->max_cmd_sn);
+
+	tmf_hdr = (struct iscsi_tm *)qedi_cmd->task->hdr;
+
+	if (likely(qedi_cmd->io_cmd_in_list)) {
+		qedi_cmd->io_cmd_in_list = false;
+		list_del_init(&qedi_cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	}
+
+	if (((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	      ISCSI_TM_FUNC_LOGICAL_UNIT_RESET) ||
+	    ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	      ISCSI_TM_FUNC_TARGET_WARM_RESET) ||
+	    ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	      ISCSI_TM_FUNC_TARGET_COLD_RESET)) {
+		INIT_WORK(&qedi_cmd->tmf_work, qedi_tmf_resp_work);
+		queue_work(qedi->tmf_thread, &qedi_cmd->tmf_work);
+		goto unblock_sess;
+	}
+
+	qedi_clear_task_idx(qedi, qedi_cmd->task_id);
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr, NULL, 0);
+	kfree(resp_hdr_ptr);
+
+unblock_sess:
+	spin_unlock(&session->back_lock);
+}
+
+static void qedi_process_login_resp(struct qedi_ctx *qedi,
+				    union iscsi_cqe *cqe,
+				    struct iscsi_task *task,
+				    struct qedi_conn *qedi_conn)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_task_context *task_ctx;
+	struct iscsi_login_rsp *resp_hdr_ptr;
+	struct iscsi_login_response_hdr *cqe_login_response;
+	struct qedi_cmd *cmd;
+	int pld_len;
+	u32 *tmp;
+
+	cmd = (struct qedi_cmd *)task->dd_data;
+
+	cqe_login_response = &cqe->cqe_common.iscsi_hdr.login_response;
+	task_ctx = qedi_get_task_mem(&qedi->tasks, cmd->task_id);
+
+	spin_lock(&session->back_lock);
+	resp_hdr_ptr =  (struct iscsi_login_rsp *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(resp_hdr_ptr, 0, sizeof(struct iscsi_login_rsp));
+	resp_hdr_ptr->opcode = cqe_login_response->opcode;
+	resp_hdr_ptr->flags = cqe_login_response->flags_attr;
+	resp_hdr_ptr->hlength = 0;
+
+	hton24(resp_hdr_ptr->dlength,
+	       (cqe_login_response->hdr_second_dword &
+		ISCSI_LOGIN_RESPONSE_HDR_DATA_SEG_LEN_MASK));
+	tmp = (u32 *)resp_hdr_ptr->dlength;
+	resp_hdr_ptr->itt = build_itt(cqe->cqe_solicited.itid,
+				      conn->session->age);
+	resp_hdr_ptr->tsih = cqe_login_response->tsih;
+	resp_hdr_ptr->statsn = cpu_to_be32(cqe_login_response->stat_sn);
+	resp_hdr_ptr->exp_cmdsn = cpu_to_be32(cqe_login_response->exp_cmd_sn);
+	resp_hdr_ptr->max_cmdsn = cpu_to_be32(cqe_login_response->max_cmd_sn);
+	resp_hdr_ptr->status_class = cqe_login_response->status_class;
+	resp_hdr_ptr->status_detail = cqe_login_response->status_detail;
+	pld_len = cqe_login_response->hdr_second_dword &
+		  ISCSI_LOGIN_RESPONSE_HDR_DATA_SEG_LEN_MASK;
+	qedi_conn->gen_pdu.resp_wr_ptr = qedi_conn->gen_pdu.resp_buf + pld_len;
+
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	}
+
+	memset(task_ctx, '\0', sizeof(*task_ctx));
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr_ptr,
+			     qedi_conn->gen_pdu.resp_buf,
+			     (qedi_conn->gen_pdu.resp_wr_ptr -
+			     qedi_conn->gen_pdu.resp_buf));
+
+	spin_unlock(&session->back_lock);
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+		  "Freeing tid=0x%x for cid=0x%x\n",
+		  cmd->task_id, qedi_conn->iscsi_conn_id);
+	cmd->state = RESPONSE_RECEIVED;
+	qedi_clear_task_idx(qedi, cmd->task_id);
+}
+
+static void qedi_get_rq_bdq_buf(struct qedi_ctx *qedi,
+				struct iscsi_cqe_unsolicited *cqe,
+				char *ptr, int len)
+{
+	u16 idx = 0;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "pld_len [%d], bdq_prod_idx [%d], idx [%d]\n",
+		  len, qedi->bdq_prod_idx,
+		  (qedi->bdq_prod_idx % qedi->rq_num_entries));
+
+	/* Obtain buffer address from rqe_opaque */
+	idx = cqe->rqe_opaque.lo;
+	if ((idx < 0) || (idx > (QEDI_BDQ_NUM - 1))) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "wrong idx %d returned by FW, dropping the unsolicited pkt\n",
+			  idx);
+		return;
+	}
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "rqe_opaque.lo [0x%p], rqe_opaque.hi [0x%p], idx [%d]\n",
+		  cqe->rqe_opaque.lo, cqe->rqe_opaque.hi, idx);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "unsol_cqe_type = %d\n", cqe->unsol_cqe_type);
+	switch (cqe->unsol_cqe_type) {
+	case ISCSI_CQE_UNSOLICITED_SINGLE:
+	case ISCSI_CQE_UNSOLICITED_FIRST:
+		if (len)
+			memcpy(ptr, (void *)qedi->bdq[idx].buf_addr, len);
+		break;
+	case ISCSI_CQE_UNSOLICITED_MIDDLE:
+	case ISCSI_CQE_UNSOLICITED_LAST:
+		break;
+	default:
+		break;
+	}
+}
+
+static void qedi_put_rq_bdq_buf(struct qedi_ctx *qedi,
+				struct iscsi_cqe_unsolicited *cqe,
+				int count)
+{
+	u16 tmp;
+	u16 idx = 0;
+	struct scsi_bd *pbl;
+
+	/* Obtain buffer address from rqe_opaque */
+	idx = cqe->rqe_opaque.lo;
+	if ((idx < 0) || (idx > (QEDI_BDQ_NUM - 1))) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "wrong idx %d returned by FW, dropping the unsolicited pkt\n",
+			  idx);
+		return;
+	}
+
+	pbl = (struct scsi_bd *)qedi->bdq_pbl;
+	pbl += (qedi->bdq_prod_idx % qedi->rq_num_entries);
+	pbl->address.hi = cpu_to_le32(QEDI_U64_HI(qedi->bdq[idx].buf_dma));
+	pbl->address.lo = cpu_to_le32(QEDI_U64_LO(qedi->bdq[idx].buf_dma));
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "pbl [0x%p] pbl->address hi [0x%llx] lo [0x%llx] idx [%d]\n",
+		  pbl, pbl->address.hi, pbl->address.lo, idx);
+	pbl->opaque.hi = 0;
+	pbl->opaque.lo = cpu_to_le32(QEDI_U64_LO(idx));
+
+	/* Increment producer to let f/w know we've handled the frame */
+	qedi->bdq_prod_idx += count;
+
+	writew(qedi->bdq_prod_idx, qedi->bdq_primary_prod);
+	tmp = readw(qedi->bdq_primary_prod);
+
+	writew(qedi->bdq_prod_idx, qedi->bdq_secondary_prod);
+	tmp = readw(qedi->bdq_secondary_prod);
+}
+
+static void qedi_unsol_pdu_adjust_bdq(struct qedi_ctx *qedi,
+				      struct iscsi_cqe_unsolicited *cqe,
+				      u32 pdu_len, u32 num_bdqs,
+				      char *bdq_data)
+{
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "num_bdqs [%d]\n", num_bdqs);
+
+	qedi_get_rq_bdq_buf(qedi, cqe, bdq_data, pdu_len);
+	qedi_put_rq_bdq_buf(qedi, cqe, (num_bdqs + 1));
+}
+
+static int qedi_process_nopin_mesg(struct qedi_ctx *qedi,
+				   union iscsi_cqe *cqe,
+				   struct iscsi_task *task,
+				   struct qedi_conn *qedi_conn, u16 que_idx)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_nop_in_hdr *cqe_nop_in;
+	struct iscsi_nopin *hdr;
+	struct qedi_cmd *cmd;
+	int tgt_async_nop = 0;
+	u32 lun[2];
+	u32 pdu_len, num_bdqs;
+	char bdq_data[QEDI_BDQ_BUF_SIZE];
+	unsigned long flags;
+
+	spin_lock_bh(&session->back_lock);
+	cqe_nop_in = &cqe->cqe_common.iscsi_hdr.nop_in;
+
+	pdu_len = cqe_nop_in->hdr_second_dword &
+		  ISCSI_NOP_IN_HDR_DATA_SEG_LEN_MASK;
+	num_bdqs = pdu_len / QEDI_BDQ_BUF_SIZE;
+
+	hdr = (struct iscsi_nopin *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(hdr, 0, sizeof(struct iscsi_hdr));
+	hdr->opcode = cqe_nop_in->opcode;
+	hdr->max_cmdsn = cpu_to_be32(cqe_nop_in->max_cmd_sn);
+	hdr->exp_cmdsn = cpu_to_be32(cqe_nop_in->exp_cmd_sn);
+	hdr->statsn = cpu_to_be32(cqe_nop_in->stat_sn);
+	hdr->ttt = cpu_to_be32(cqe_nop_in->ttt);
+
+	if (cqe->cqe_common.cqe_type == ISCSI_CQE_TYPE_UNSOLICITED) {
+		spin_lock_irqsave(&qedi->hba_lock, flags);
+		qedi_unsol_pdu_adjust_bdq(qedi, &cqe->cqe_unsolicited,
+					  pdu_len, num_bdqs, bdq_data);
+		hdr->itt = RESERVED_ITT;
+		tgt_async_nop = 1;
+		spin_unlock_irqrestore(&qedi->hba_lock, flags);
+		goto done;
+	}
+
+	/* Response to one of our nop-outs */
+	if (task) {
+		cmd = task->dd_data;
+		hdr->flags = ISCSI_FLAG_CMD_FINAL;
+		hdr->itt = build_itt(cqe->cqe_solicited.itid,
+				     conn->session->age);
+		lun[0] = 0xffffffff;
+		lun[1] = 0xffffffff;
+		memcpy(&hdr->lun, lun, sizeof(struct scsi_lun));
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+			  "Freeing tid=0x%x for cid=0x%x\n",
+			  cmd->task_id, qedi_conn->iscsi_conn_id);
+		cmd->state = RESPONSE_RECEIVED;
+		spin_lock(&qedi_conn->list_lock);
+		if (likely(cmd->io_cmd_in_list)) {
+			cmd->io_cmd_in_list = false;
+			list_del_init(&cmd->io_cmd);
+			qedi_conn->active_cmd_count--;
+		}
+
+		spin_unlock(&qedi_conn->list_lock);
+		qedi_clear_task_idx(qedi, cmd->task_id);
+	}
+
+done:
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)hdr, bdq_data, pdu_len);
+
+	spin_unlock_bh(&session->back_lock);
+	return tgt_async_nop;
+}
+
+static void qedi_process_async_mesg(struct qedi_ctx *qedi,
+				    union iscsi_cqe *cqe,
+				    struct iscsi_task *task,
+				    struct qedi_conn *qedi_conn,
+				    u16 que_idx)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_async_msg_hdr *cqe_async_msg;
+	struct iscsi_async *resp_hdr;
+	u32 lun[2];
+	u32 pdu_len, num_bdqs;
+	char bdq_data[QEDI_BDQ_BUF_SIZE];
+	unsigned long flags;
+
+	spin_lock_bh(&session->back_lock);
+
+	cqe_async_msg = &cqe->cqe_common.iscsi_hdr.async_msg;
+	pdu_len = cqe_async_msg->hdr_second_dword &
+		ISCSI_ASYNC_MSG_HDR_DATA_SEG_LEN_MASK;
+	num_bdqs = pdu_len / QEDI_BDQ_BUF_SIZE;
+
+	if (cqe->cqe_common.cqe_type == ISCSI_CQE_TYPE_UNSOLICITED) {
+		spin_lock_irqsave(&qedi->hba_lock, flags);
+		qedi_unsol_pdu_adjust_bdq(qedi, &cqe->cqe_unsolicited,
+					  pdu_len, num_bdqs, bdq_data);
+		spin_unlock_irqrestore(&qedi->hba_lock, flags);
+	}
+
+	resp_hdr = (struct iscsi_async *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(resp_hdr, 0, sizeof(struct iscsi_hdr));
+	resp_hdr->opcode = cqe_async_msg->opcode;
+	resp_hdr->flags = 0x80;
+
+	lun[0] = cpu_to_be32(cqe_async_msg->lun.lo);
+	lun[1] = cpu_to_be32(cqe_async_msg->lun.hi);
+	memcpy(&resp_hdr->lun, lun, sizeof(struct scsi_lun));
+	resp_hdr->exp_cmdsn = cpu_to_be32(cqe_async_msg->exp_cmd_sn);
+	resp_hdr->max_cmdsn = cpu_to_be32(cqe_async_msg->max_cmd_sn);
+	resp_hdr->statsn = cpu_to_be32(cqe_async_msg->stat_sn);
+
+	resp_hdr->async_event = cqe_async_msg->async_event;
+	resp_hdr->async_vcode = cqe_async_msg->async_vcode;
+
+	resp_hdr->param1 = cpu_to_be16(cqe_async_msg->param1_rsrv);
+	resp_hdr->param2 = cpu_to_be16(cqe_async_msg->param2_rsrv);
+	resp_hdr->param3 = cpu_to_be16(cqe_async_msg->param3_rsrv);
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)resp_hdr, bdq_data,
+			     pdu_len);
+
+	spin_unlock_bh(&session->back_lock);
+}
+
+static void qedi_process_reject_mesg(struct qedi_ctx *qedi,
+				     union iscsi_cqe *cqe,
+				     struct iscsi_task *task,
+				     struct qedi_conn *qedi_conn,
+				     uint16_t que_idx)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_reject_hdr *cqe_reject;
+	struct iscsi_reject *hdr;
+	u32 pld_len, num_bdqs;
+	unsigned long flags;
+
+	spin_lock_bh(&session->back_lock);
+	cqe_reject = &cqe->cqe_common.iscsi_hdr.reject;
+	pld_len = cqe_reject->hdr_second_dword &
+		  ISCSI_REJECT_HDR_DATA_SEG_LEN_MASK;
+	num_bdqs = pld_len / QEDI_BDQ_BUF_SIZE;
+
+	if (cqe->cqe_common.cqe_type == ISCSI_CQE_TYPE_UNSOLICITED) {
+		spin_lock_irqsave(&qedi->hba_lock, flags);
+		qedi_unsol_pdu_adjust_bdq(qedi, &cqe->cqe_unsolicited,
+					  pld_len, num_bdqs, conn->data);
+		spin_unlock_irqrestore(&qedi->hba_lock, flags);
+	}
+	hdr = (struct iscsi_reject *)&qedi_conn->gen_pdu.resp_hdr;
+	memset(hdr, 0, sizeof(struct iscsi_hdr));
+	hdr->opcode = cqe_reject->opcode;
+	hdr->reason = cqe_reject->hdr_reason;
+	hdr->flags = cqe_reject->hdr_flags;
+	hton24(hdr->dlength, (cqe_reject->hdr_second_dword &
+			      ISCSI_REJECT_HDR_DATA_SEG_LEN_MASK));
+	hdr->max_cmdsn = cpu_to_be32(cqe_reject->max_cmd_sn);
+	hdr->exp_cmdsn = cpu_to_be32(cqe_reject->exp_cmd_sn);
+	hdr->statsn = cpu_to_be32(cqe_reject->stat_sn);
+	hdr->ffffffff = cpu_to_be32(0xffffffff);
+
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)hdr,
+			     conn->data, pld_len);
+	spin_unlock_bh(&session->back_lock);
+}
+
+static void qedi_scsi_completion(struct qedi_ctx *qedi,
+				 union iscsi_cqe *cqe,
+				 struct iscsi_task *task,
+				 struct iscsi_conn *conn)
+{
+	struct scsi_cmnd *sc_cmd;
+	struct qedi_cmd *cmd = task->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct iscsi_scsi_rsp *hdr;
+	struct iscsi_data_in_hdr *cqe_data_in;
+	int datalen = 0;
+	struct qedi_conn *qedi_conn;
+	u32 iscsi_cid;
+	bool mark_cmd_node_deleted = false;
+	u8 cqe_err_bits = 0;
+
+	iscsi_cid  = cqe->cqe_common.conn_id;
+	qedi_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+
+	cqe_data_in = &cqe->cqe_common.iscsi_hdr.data_in;
+	cqe_err_bits =
+		cqe->cqe_common.error_bitmap.error_bits.cqe_error_status_bits;
+
+	spin_lock_bh(&session->back_lock);
+	/* get the scsi command */
+	sc_cmd = cmd->scsi_cmd;
+
+	if (!sc_cmd) {
+		QEDI_WARN(&qedi->dbg_ctx, "sc_cmd is NULL!\n");
+		goto error;
+	}
+
+	if (!sc_cmd->SCp.ptr) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "SCp.ptr is NULL, returned in another context.\n");
+		goto error;
+	}
+
+	if (!sc_cmd->request) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "sc_cmd->request is NULL, sc_cmd=%p.\n",
+			  sc_cmd);
+		goto error;
+	}
+
+	if (!sc_cmd->request->special) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "request->special is NULL so request not valid, sc_cmd=%p.\n",
+			  sc_cmd);
+		goto error;
+	}
+
+	if (!sc_cmd->request->q) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "request->q is NULL so request is not valid, sc_cmd=%p.\n",
+			  sc_cmd);
+		goto error;
+	}
+
+	qedi_iscsi_unmap_sg_list(cmd);
+
+	hdr = (struct iscsi_scsi_rsp *)task->hdr;
+	hdr->opcode = cqe_data_in->opcode;
+	hdr->max_cmdsn = cpu_to_be32(cqe_data_in->max_cmd_sn);
+	hdr->exp_cmdsn = cpu_to_be32(cqe_data_in->exp_cmd_sn);
+	hdr->itt = build_itt(cqe->cqe_solicited.itid, conn->session->age);
+	hdr->response = cqe_data_in->reserved1;
+	hdr->cmd_status = cqe_data_in->status_rsvd;
+	hdr->flags = cqe_data_in->flags;
+	hdr->residual_count = cpu_to_be32(cqe_data_in->residual_count);
+
+	if (hdr->cmd_status == SAM_STAT_CHECK_CONDITION) {
+		datalen = cqe_data_in->reserved2 &
+			  ISCSI_COMMON_HDR_DATA_SEG_LEN_MASK;
+		memcpy((char *)conn->data, (char *)cmd->sense_buffer, datalen);
+	}
+
+	/* If f/w reports data underrun err then set residual to IO transfer
+	 * length, set Underrun flag and clear Overrun flag explicitly
+	 */
+	if (unlikely(cqe_err_bits &&
+		     GET_FIELD(cqe_err_bits, CQE_ERROR_BITMAP_UNDER_RUN_ERR))) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Under flow itt=0x%x proto flags=0x%x tid=0x%x cid 0x%x fw resid 0x%x sc dlen 0x%x\n",
+			  hdr->itt, cqe_data_in->flags, cmd->task_id,
+			  qedi_conn->iscsi_conn_id, hdr->residual_count,
+			  scsi_bufflen(sc_cmd));
+		hdr->residual_count = cpu_to_be32(scsi_bufflen(sc_cmd));
+		hdr->flags |= ISCSI_FLAG_CMD_UNDERFLOW;
+		hdr->flags &= (~ISCSI_FLAG_CMD_OVERFLOW);
+	}
+
+	spin_lock(&qedi_conn->list_lock);
+	if (likely(cmd->io_cmd_in_list)) {
+		cmd->io_cmd_in_list = false;
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+		mark_cmd_node_deleted = true;
+	}
+	spin_unlock(&qedi_conn->list_lock);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+		  "Freeing tid=0x%x for cid=0x%x\n",
+		  cmd->task_id, qedi_conn->iscsi_conn_id);
+	cmd->state = RESPONSE_RECEIVED;
+	if (qedi_io_tracing)
+		qedi_trace_io(qedi, task, cmd->task_id, QEDI_IO_TRACE_RSP);
+
+	qedi_clear_task_idx(qedi, cmd->task_id);
+	__iscsi_complete_pdu(conn, (struct iscsi_hdr *)hdr,
+			     conn->data, datalen);
+error:
+	spin_unlock_bh(&session->back_lock);
+}
+
+static void qedi_mtask_completion(struct qedi_ctx *qedi,
+				  union iscsi_cqe *cqe,
+				  struct iscsi_task *task,
+				  struct qedi_conn *conn, uint16_t que_idx)
+{
+	struct iscsi_conn *iscsi_conn;
+	u32 hdr_opcode;
+
+	hdr_opcode = cqe->cqe_common.iscsi_hdr.common.hdr_first_byte;
+	iscsi_conn = conn->cls_conn->dd_data;
+
+	switch (hdr_opcode) {
+	case ISCSI_OPCODE_SCSI_RESPONSE:
+	case ISCSI_OPCODE_DATA_IN:
+		qedi_scsi_completion(qedi, cqe, task, iscsi_conn);
+		break;
+	case ISCSI_OPCODE_LOGIN_RESPONSE:
+		qedi_process_login_resp(qedi, cqe, task, conn);
+		break;
+	case ISCSI_OPCODE_TMF_RESPONSE:
+		qedi_process_tmf_resp(qedi, cqe, task, conn);
+		break;
+	case ISCSI_OPCODE_TEXT_RESPONSE:
+		qedi_process_text_resp(qedi, cqe, task, conn);
+		break;
+	case ISCSI_OPCODE_LOGOUT_RESPONSE:
+		qedi_process_logout_resp(qedi, cqe, task, conn);
+		break;
+	case ISCSI_OPCODE_NOP_IN:
+		qedi_process_nopin_mesg(qedi, cqe, task, conn, que_idx);
+		break;
+	default:
+		QEDI_ERR(&qedi->dbg_ctx, "unknown opcode\n");
+	}
+}
+
+static void qedi_process_nopin_local_cmpl(struct qedi_ctx *qedi,
+					  struct iscsi_cqe_solicited *cqe,
+					  struct iscsi_task *task,
+					  struct qedi_conn *qedi_conn)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+	struct qedi_cmd *cmd = task->dd_data;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_UNSOL,
+		  "itid=0x%x, cmd task id=0x%x\n",
+		  cqe->itid, cmd->task_id);
+
+	cmd->state = RESPONSE_RECEIVED;
+	qedi_clear_task_idx(qedi, cmd->task_id);
+
+	spin_lock_bh(&session->back_lock);
+	__iscsi_put_task(task);
+	spin_unlock_bh(&session->back_lock);
+}
+
+static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi,
+					  struct iscsi_cqe_solicited *cqe,
+					  struct iscsi_task *task,
+					  struct iscsi_conn *conn)
+{
+	struct qedi_work_map *work, *work_tmp;
+	u32 proto_itt = cqe->itid;
+	u32 ptmp_itt = 0;
+	itt_t protoitt = 0;
+	int found = 0;
+	struct qedi_cmd *qedi_cmd = NULL;
+	u32 rtid = 0;
+	u32 iscsi_cid;
+	struct qedi_conn *qedi_conn;
+	struct qedi_cmd *cmd_new, *dbg_cmd;
+	struct iscsi_task *mtask;
+	struct iscsi_tm *tmf_hdr = NULL;
+
+	iscsi_cid = cqe->conn_id;
+	qedi_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+
+	/* Based on this itt get the corresponding qedi_cmd */
+	spin_lock_bh(&qedi_conn->tmf_work_lock);
+	list_for_each_entry_safe(work, work_tmp, &qedi_conn->tmf_work_list,
+				 list) {
+		if (work->rtid == proto_itt) {
+			/* We found the command */
+			qedi_cmd = work->qedi_cmd;
+			if (!qedi_cmd->list_tmf_work) {
+				QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+					  "TMF work not found, cqe->tid=0x%x, cid=0x%x\n",
+					  proto_itt, qedi_conn->iscsi_conn_id);
+				WARN_ON(1);
+			}
+			found = 1;
+			mtask = qedi_cmd->task;
+			tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+			rtid = work->rtid;
+
+			list_del_init(&work->list);
+			kfree(work);
+			qedi_cmd->list_tmf_work = NULL;
+		}
+	}
+	spin_unlock_bh(&qedi_conn->tmf_work_lock);
+
+	if (found) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+			  "TMF work, cqe->tid=0x%x, tmf flags=0x%x, cid=0x%x\n",
+			  proto_itt, tmf_hdr->flags, qedi_conn->iscsi_conn_id);
+
+		if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+		    ISCSI_TM_FUNC_ABORT_TASK) {
+			spin_lock_bh(&conn->session->back_lock);
+
+			protoitt = build_itt(get_itt(tmf_hdr->rtt),
+					     conn->session->age);
+			task = iscsi_itt_to_task(conn, protoitt);
+
+			spin_unlock_bh(&conn->session->back_lock);
+
+			if (!task) {
+				QEDI_NOTICE(&qedi->dbg_ctx,
+					    "IO task completed, tmf rtt=0x%x, cid=0x%x\n",
+					    get_itt(tmf_hdr->rtt),
+					    qedi_conn->iscsi_conn_id);
+				return;
+			}
+
+			dbg_cmd = task->dd_data;
+
+			QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+				  "Abort tmf rtt=0x%x, i/o itt=0x%x, i/o tid=0x%x, cid=0x%x\n",
+				  get_itt(tmf_hdr->rtt), get_itt(task->itt),
+				  dbg_cmd->task_id, qedi_conn->iscsi_conn_id);
+
+			if (qedi_cmd->state == CLEANUP_WAIT_FAILED)
+				qedi_cmd->state = CLEANUP_RECV;
+
+			qedi_clear_task_idx(qedi_conn->qedi, rtid);
+
+			spin_lock(&qedi_conn->list_lock);
+			list_del_init(&dbg_cmd->io_cmd);
+			qedi_conn->active_cmd_count--;
+			spin_unlock(&qedi_conn->list_lock);
+			qedi_cmd->state = CLEANUP_RECV;
+			wake_up_interruptible(&qedi_conn->wait_queue);
+		}
+	} else if (qedi_conn->cmd_cleanup_req > 0) {
+		spin_lock_bh(&conn->session->back_lock);
+		qedi_get_proto_itt(qedi, cqe->itid, &ptmp_itt);
+		protoitt = build_itt(ptmp_itt, conn->session->age);
+		task = iscsi_itt_to_task(conn, protoitt);
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+			  "cleanup io itid=0x%x, protoitt=0x%x, cmd_cleanup_cmpl=%d, cid=0x%x\n",
+			  cqe->itid, protoitt, qedi_conn->cmd_cleanup_cmpl,
+			  qedi_conn->iscsi_conn_id);
+
+		spin_unlock_bh(&conn->session->back_lock);
+		if (!task) {
+			QEDI_NOTICE(&qedi->dbg_ctx,
+				    "task is null, itid=0x%x, cid=0x%x\n",
+				    cqe->itid, qedi_conn->iscsi_conn_id);
+			return;
+		}
+		qedi_conn->cmd_cleanup_cmpl++;
+		wake_up(&qedi_conn->wait_queue);
+		cmd_new = task->dd_data;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+			  "Freeing tid=0x%x for cid=0x%x\n",
+			  cqe->itid, qedi_conn->iscsi_conn_id);
+		qedi_clear_task_idx(qedi_conn->qedi, cqe->itid);
+
+	} else {
+		qedi_get_proto_itt(qedi, cqe->itid, &ptmp_itt);
+		protoitt = build_itt(ptmp_itt, conn->session->age);
+		task = iscsi_itt_to_task(conn, protoitt);
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Delayed or untracked cleanup response, itt=0x%x, tid=0x%x, cid=0x%x, task=%p\n",
+			 protoitt, cqe->itid, qedi_conn->iscsi_conn_id, task);
+		WARN_ON(1);
+	}
+}
+
+void qedi_fp_process_cqes(struct qedi_work *work)
+{
+	struct qedi_ctx *qedi = work->qedi;
+	union iscsi_cqe *cqe = &work->cqe;
+	struct iscsi_task *task = NULL;
+	struct iscsi_nopout *nopout_hdr;
+	struct qedi_conn *q_conn;
+	struct iscsi_conn *conn;
+	struct qedi_cmd *qedi_cmd;
+	u32 comp_type;
+	u32 iscsi_cid;
+	u32 hdr_opcode;
+	u16 que_idx = work->que_idx;
+	u8 cqe_err_bits = 0;
+
+	comp_type = cqe->cqe_common.cqe_type;
+	hdr_opcode = cqe->cqe_common.iscsi_hdr.common.hdr_first_byte;
+	cqe_err_bits =
+		cqe->cqe_common.error_bitmap.error_bits.cqe_error_status_bits;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "fw_cid=0x%x, cqe type=0x%x, opcode=0x%x\n",
+		  cqe->cqe_common.conn_id, comp_type, hdr_opcode);
+
+	if (comp_type >= MAX_ISCSI_CQES_TYPE) {
+		QEDI_WARN(&qedi->dbg_ctx, "Invalid CqE type\n");
+		return;
+	}
+
+	iscsi_cid  = cqe->cqe_common.conn_id;
+	q_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+	if (!q_conn) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Session no longer exists for cid=0x%x!!\n",
+			  iscsi_cid);
+		return;
+	}
+
+	conn = q_conn->cls_conn->dd_data;
+
+	if (unlikely(cqe_err_bits &&
+		     GET_FIELD(cqe_err_bits,
+			       CQE_ERROR_BITMAP_DATA_DIGEST_ERR))) {
+		iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST);
+		return;
+	}
+
+	switch (comp_type) {
+	case ISCSI_CQE_TYPE_SOLICITED:
+	case ISCSI_CQE_TYPE_SOLICITED_WITH_SENSE:
+		qedi_cmd = container_of(work, struct qedi_cmd, cqe_work);
+		task = qedi_cmd->task;
+		if (!task) {
+			QEDI_WARN(&qedi->dbg_ctx, "task is NULL\n");
+			return;
+		}
+
+		/* Process NOPIN local completion */
+		nopout_hdr = (struct iscsi_nopout *)task->hdr;
+		if ((nopout_hdr->itt == RESERVED_ITT) &&
+		    (cqe->cqe_solicited.itid != (u16)RESERVED_ITT)) {
+			qedi_process_nopin_local_cmpl(qedi, &cqe->cqe_solicited,
+						      task, q_conn);
+		} else {
+			cqe->cqe_solicited.itid =
+					       qedi_get_itt(cqe->cqe_solicited);
+			/* Process other solicited responses */
+			qedi_mtask_completion(qedi, cqe, task, q_conn, que_idx);
+		}
+		break;
+	case ISCSI_CQE_TYPE_UNSOLICITED:
+		switch (hdr_opcode) {
+		case ISCSI_OPCODE_NOP_IN:
+			qedi_process_nopin_mesg(qedi, cqe, task, q_conn,
+						que_idx);
+			break;
+		case ISCSI_OPCODE_ASYNC_MSG:
+			qedi_process_async_mesg(qedi, cqe, task, q_conn,
+						que_idx);
+			break;
+		case ISCSI_OPCODE_REJECT:
+			qedi_process_reject_mesg(qedi, cqe, task, q_conn,
+						 que_idx);
+			break;
+		}
+		goto exit_fp_process;
+	case ISCSI_CQE_TYPE_DUMMY:
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "Dummy CqE\n");
+		goto exit_fp_process;
+	case ISCSI_CQE_TYPE_TASK_CLEANUP:
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "CleanUp CqE\n");
+		qedi_process_cmd_cleanup_resp(qedi, &cqe->cqe_solicited, task,
+					      conn);
+		goto exit_fp_process;
+	default:
+		QEDI_ERR(&qedi->dbg_ctx, "Error cqe.\n");
+		break;
+	}
+
+exit_fp_process:
+	return;
+}
+
+static void qedi_add_to_sq(struct qedi_conn *qedi_conn, struct iscsi_task *task,
+			   u16 tid, uint16_t ptu_invalidate, int is_cleanup)
+{
+	struct iscsi_wqe *wqe;
+	struct iscsi_wqe_field *cont_field;
+	struct qedi_endpoint *ep;
+	struct scsi_cmnd *sc = task->sc;
+	struct iscsi_login_req *login_hdr;
+	struct qedi_cmd *cmd = task->dd_data;
+
+	login_hdr = (struct iscsi_login_req *)task->hdr;
+	ep = qedi_conn->ep;
+	wqe = &ep->sq[ep->sq_prod_idx];
+
+	memset(wqe, 0, sizeof(*wqe));
+
+	ep->sq_prod_idx++;
+	ep->fw_sq_prod_idx++;
+	if (ep->sq_prod_idx == QEDI_SQ_SIZE)
+		ep->sq_prod_idx = 0;
+
+	if (is_cleanup) {
+		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_TASK_CLEANUP);
+		wqe->task_id = tid;
+		return;
+	}
+
+	if (ptu_invalidate) {
+		SET_FIELD(wqe->flags, ISCSI_WQE_PTU_INVALIDATE,
+			  ISCSI_WQE_SET_PTU_INVALIDATE);
+	}
+
+	cont_field = &wqe->cont_prevtid_union.cont_field;
+
+	switch (task->hdr->opcode & ISCSI_OPCODE_MASK) {
+	case ISCSI_OP_LOGIN:
+	case ISCSI_OP_TEXT:
+		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_MIDDLE_PATH);
+		SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
+			  1);
+		cont_field->contlen_cdbsize_field = ntoh24(login_hdr->dlength);
+		break;
+	case ISCSI_OP_LOGOUT:
+	case ISCSI_OP_NOOP_OUT:
+	case ISCSI_OP_SCSI_TMFUNC:
+		 SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
+			   ISCSI_WQE_TYPE_NORMAL);
+		break;
+	default:
+		if (!sc)
+			break;
+
+		SET_FIELD(wqe->flags, ISCSI_WQE_WQE_TYPE,
+			  ISCSI_WQE_TYPE_NORMAL);
+		cont_field->contlen_cdbsize_field =
+				(sc->sc_data_direction == DMA_TO_DEVICE) ?
+				scsi_bufflen(sc) : 0;
+		if (cmd->use_slowpath)
+			SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES, 0);
+		else
+			SET_FIELD(wqe->flags, ISCSI_WQE_NUM_FAST_SGES,
+				  (sc->sc_data_direction ==
+				   DMA_TO_DEVICE) ?
+				  min((u16)QEDI_FAST_SGE_COUNT,
+				      (u16)cmd->io_tbl.sge_valid) : 0);
+		break;
+	}
+
+	wqe->task_id = tid;
+	/* Make sure SQ data is coherent */
+	wmb();
+}
+
+static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
+{
+	struct iscsi_db_data dbell = { 0 };
+
+	dbell.agg_flags = 0;
+
+	dbell.params |= DB_DEST_XCM << ISCSI_DB_DATA_DEST_SHIFT;
+	dbell.params |= DB_AGG_CMD_SET << ISCSI_DB_DATA_AGG_CMD_SHIFT;
+	dbell.params |=
+		   DQ_XCM_ISCSI_SQ_PROD_CMD << ISCSI_DB_DATA_AGG_VAL_SEL_SHIFT;
+
+	dbell.sq_prod = qedi_conn->ep->fw_sq_prod_idx;
+	writel(*(u32 *)&dbell, qedi_conn->ep->p_doorbell);
+
+	/* Make sure fw write idx is coherent, and include both memory barriers
+	 * as a failsafe as for some architectures the call is the same but on
+	 * others they are two different assembly operations.
+	 */
+	wmb();
+	mmiowb();
+	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_MP_REQ,
+		  "prod_idx=0x%x, fw_prod_idx=0x%x, cid=0x%x\n",
+		  qedi_conn->ep->sq_prod_idx, qedi_conn->ep->fw_sq_prod_idx,
+		  qedi_conn->iscsi_conn_id);
+}
+
+int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
+			  struct iscsi_task *task)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_login_req *login_hdr;
+	struct iscsi_login_req_hdr *fw_login_req = NULL;
+	struct iscsi_cached_sge_ctx *cached_sge = NULL;
+	struct iscsi_sge *single_sge = NULL;
+	struct iscsi_sge *req_sge = NULL;
+	struct iscsi_sge *resp_sge = NULL;
+	struct qedi_cmd *qedi_cmd;
+	s16 ptu_invalidate = 0;
+	s16 tid = 0;
+
+	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	login_hdr = (struct iscsi_login_req *)task->hdr;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
+	qedi_cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_login_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.login_req;
+	fw_login_req->opcode = login_hdr->opcode;
+	fw_login_req->version_min = login_hdr->min_version;
+	fw_login_req->version_max = login_hdr->max_version;
+	fw_login_req->flags_attr = login_hdr->flags;
+	fw_login_req->isid_tabc = *((u16 *)login_hdr->isid + 2);
+	fw_login_req->isid_d = *((u32 *)login_hdr->isid);
+	fw_login_req->tsih = login_hdr->tsih;
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	fw_login_req->itt = qedi_set_itt(tid, get_itt(task->itt));
+	fw_login_req->cid = qedi_conn->iscsi_conn_id;
+	fw_login_req->cmd_sn = be32_to_cpu(login_hdr->cmdsn);
+	fw_login_req->exp_stat_sn = be32_to_cpu(login_hdr->exp_statsn);
+	fw_login_req->exp_stat_sn = 0;
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						qedi->tid_reuse_count[tid]++;
+	cached_sge =
+	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
+	cached_sge->sge.sge_len = req_sge->sge_len;
+	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	cached_sge->sge.sge_addr.hi =
+			     (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+
+	/* Mstorm context */
+	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
+	fw_task_ctx->mstorm_st_context.task_type = 0x2;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
+	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
+	single_sge->sge_len = resp_sge->sge_len;
+
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SINGLE_SGE, 1);
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SLOW_IO, 0);
+	fw_task_ctx->mstorm_st_context.sgl_size = 1;
+	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
+						ntoh24(login_hdr->dlength);
+	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+	fw_task_ctx->ustorm_st_context.task_type = 0x2;
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	fw_task_ctx->ustorm_ag_context.exp_data_acked =
+						 ntoh24(login_hdr->dlength);
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+	qedi_cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+	return 0;
+}
+
+int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
+			   struct iscsi_task *task)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_logout_req_hdr *fw_logout_req = NULL;
+	struct iscsi_task_context *fw_task_ctx = NULL;
+	struct iscsi_logout *logout_hdr = NULL;
+	struct qedi_cmd *qedi_cmd = NULL;
+	s16  tid = 0;
+	s16 ptu_invalidate = 0;
+
+	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	logout_hdr = (struct iscsi_logout *)task->hdr;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+	qedi_cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_logout_req = &fw_task_ctx->ystorm_st_context.pdu_hdr.logout_req;
+	fw_logout_req->opcode = ISCSI_OPCODE_LOGOUT_REQUEST;
+	fw_logout_req->reason_code = 0x80 | logout_hdr->flags;
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	fw_logout_req->itt = qedi_set_itt(tid, get_itt(task->itt));
+	fw_logout_req->exp_stat_sn = be32_to_cpu(logout_hdr->exp_statsn);
+	fw_logout_req->cmd_sn = be32_to_cpu(logout_hdr->cmdsn);
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						  qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						qedi->tid_reuse_count[tid]++;
+	fw_logout_req->cid = qedi_conn->iscsi_conn_id;
+	fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+
+	/* Mstorm context */
+	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
+	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
+	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+
+	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+		  ISCSI_REG1_NUM_FAST_SGES, 0);
+
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+	qedi_cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+
+	return 0;
+}
+
+int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
+			struct iscsi_task *task, bool in_recovery)
+{
+	int rval;
+	struct iscsi_task *ctask;
+	struct qedi_cmd *cmd, *cmd_tmp;
+	struct iscsi_tm *tmf_hdr;
+	unsigned int lun = 0;
+	bool lun_reset = false;
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_session *session = conn->session;
+
+	/* From recovery, task is NULL or from tmf resp valid task */
+	if (task) {
+		tmf_hdr = (struct iscsi_tm *)task->hdr;
+
+		if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+			ISCSI_TM_FUNC_LOGICAL_UNIT_RESET) {
+			lun_reset = true;
+			lun = scsilun_to_int(&tmf_hdr->lun);
+		}
+	}
+
+	qedi_conn->cmd_cleanup_req = 0;
+	qedi_conn->cmd_cleanup_cmpl = 0;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "active_cmd_count=%d, cid=0x%x, in_recovery=%d, lun_reset=%d\n",
+		  qedi_conn->active_cmd_count, qedi_conn->iscsi_conn_id,
+		  in_recovery, lun_reset);
+
+	if (lun_reset)
+		spin_lock_bh(&session->back_lock);
+
+	spin_lock(&qedi_conn->list_lock);
+
+	list_for_each_entry_safe(cmd, cmd_tmp, &qedi_conn->active_cmd_list,
+				 io_cmd) {
+		ctask = cmd->task;
+		if (ctask == task)
+			continue;
+
+		if (lun_reset) {
+			if (cmd->scsi_cmd && cmd->scsi_cmd->device) {
+				QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+					  "tid=0x%x itt=0x%x scsi_cmd_ptr=%p device=%p task_state=%d cmd_state=0%x cid=0x%x\n",
+					  cmd->task_id, get_itt(ctask->itt),
+					  cmd->scsi_cmd, cmd->scsi_cmd->device,
+					  ctask->state, cmd->state,
+					  qedi_conn->iscsi_conn_id);
+				if (cmd->scsi_cmd->device->lun != lun)
+					continue;
+			}
+		}
+		qedi_conn->cmd_cleanup_req++;
+		qedi_iscsi_cleanup_task(ctask, true);
+
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Deleted active cmd list node io_cmd=%p, cid=0x%x\n",
+			  &cmd->io_cmd, qedi_conn->iscsi_conn_id);
+	}
+
+	spin_unlock(&qedi_conn->list_lock);
+
+	if (lun_reset)
+		spin_unlock_bh(&session->back_lock);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "cmd_cleanup_req=%d, cid=0x%x\n",
+		  qedi_conn->cmd_cleanup_req,
+		  qedi_conn->iscsi_conn_id);
+
+	rval  = wait_event_interruptible_timeout(qedi_conn->wait_queue,
+						 ((qedi_conn->cmd_cleanup_req ==
+						 qedi_conn->cmd_cleanup_cmpl) ||
+						 qedi_conn->ep),
+						 5 * HZ);
+	if (rval) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+			  "i/o cmd_cleanup_req=%d, equal to cmd_cleanup_cmpl=%d, cid=0x%x\n",
+			  qedi_conn->cmd_cleanup_req,
+			  qedi_conn->cmd_cleanup_cmpl,
+			  qedi_conn->iscsi_conn_id);
+
+		return 0;
+	}
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "i/o cmd_cleanup_req=%d, not equal to cmd_cleanup_cmpl=%d, cid=0x%x\n",
+		  qedi_conn->cmd_cleanup_req,
+		  qedi_conn->cmd_cleanup_cmpl,
+		  qedi_conn->iscsi_conn_id);
+
+	iscsi_host_for_each_session(qedi->shost,
+				    qedi_mark_device_missing);
+	qedi_ops->common->drain(qedi->cdev);
+
+	/* Enable IOs for all other sessions except current.*/
+	if (!wait_event_interruptible_timeout(qedi_conn->wait_queue,
+					      (qedi_conn->cmd_cleanup_req ==
+					       qedi_conn->cmd_cleanup_cmpl),
+					      5 * HZ)) {
+		iscsi_host_for_each_session(qedi->shost,
+					    qedi_mark_device_available);
+		return -1;
+	}
+
+	iscsi_host_for_each_session(qedi->shost,
+				    qedi_mark_device_available);
+
+	return 0;
+}
+
+void qedi_clearsq(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
+		  struct iscsi_task *task)
+{
+	struct qedi_endpoint *qedi_ep;
+	int rval;
+
+	qedi_ep = qedi_conn->ep;
+	qedi_conn->cmd_cleanup_req = 0;
+	qedi_conn->cmd_cleanup_cmpl = 0;
+
+	if (!qedi_ep) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Cannot proceed, ep already disconnected, cid=0x%x\n",
+			  qedi_conn->iscsi_conn_id);
+		return;
+	}
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "Clearing SQ for cid=0x%x, conn=%p, ep=%p\n",
+		  qedi_conn->iscsi_conn_id, qedi_conn, qedi_ep);
+
+	qedi_ops->clear_sq(qedi->cdev, qedi_ep->handle);
+
+	rval = qedi_cleanup_all_io(qedi, qedi_conn, task, true);
+	if (rval) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "fatal error, need hard reset, cid=0x%x\n",
+			 qedi_conn->iscsi_conn_id);
+		WARN_ON(1);
+	}
+}
+
+static int qedi_wait_for_cleanup_request(struct qedi_ctx *qedi,
+					 struct qedi_conn *qedi_conn,
+					 struct iscsi_task *task,
+					 struct qedi_cmd *qedi_cmd,
+					 struct qedi_work_map *list_work)
+{
+	struct qedi_cmd *cmd = (struct qedi_cmd *)task->dd_data;
+	int wait;
+
+	wait  = wait_event_interruptible_timeout(qedi_conn->wait_queue,
+						 ((qedi_cmd->state ==
+						   CLEANUP_RECV) ||
+						 ((qedi_cmd->type == TYPEIO) &&
+						  (cmd->state ==
+						   RESPONSE_RECEIVED))),
+						 5 * HZ);
+	if (!wait) {
+		qedi_cmd->state = CLEANUP_WAIT_FAILED;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+			  "Cleanup timedout tid=0x%x, issue connection recovery, cid=0x%x\n",
+			  cmd->task_id, qedi_conn->iscsi_conn_id);
+
+		return -1;
+	}
+	return 0;
+}
+
+static void qedi_tmf_work(struct work_struct *work)
+{
+	struct qedi_cmd *qedi_cmd =
+		container_of(work, struct qedi_cmd, tmf_work);
+	struct qedi_conn *qedi_conn = qedi_cmd->conn;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct iscsi_cls_session *cls_sess;
+	struct qedi_work_map *list_work = NULL;
+	struct iscsi_task *mtask;
+	struct qedi_cmd *cmd;
+	struct iscsi_task *ctask;
+	struct iscsi_tm *tmf_hdr;
+	s16 rval = 0;
+	s16 tid = 0;
+
+	mtask = qedi_cmd->task;
+	tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+	cls_sess = iscsi_conn_to_session(qedi_conn->cls_conn);
+	set_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+
+	ctask = iscsi_itt_to_task(conn, tmf_hdr->rtt);
+	if (!ctask || !ctask->sc) {
+		QEDI_ERR(&qedi->dbg_ctx, "Task already completed\n");
+		goto abort_ret;
+	}
+
+	cmd = (struct qedi_cmd *)ctask->dd_data;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "Abort tmf rtt=0x%x, cmd itt=0x%x, cmd tid=0x%x, cid=0x%x\n",
+		  get_itt(tmf_hdr->rtt), get_itt(ctask->itt), cmd->task_id,
+		  qedi_conn->iscsi_conn_id);
+
+	if (do_not_recover) {
+		QEDI_ERR(&qedi->dbg_ctx, "DONT SEND CLEANUP/ABORT %d\n",
+			 do_not_recover);
+		goto abort_ret;
+	}
+
+	list_work = kzalloc(sizeof(*list_work), GFP_ATOMIC);
+	if (!list_work) {
+		QEDI_ERR(&qedi->dbg_ctx, "Memory alloction failed\n");
+		goto abort_ret;
+	}
+
+	qedi_cmd->type = TYPEIO;
+	list_work->qedi_cmd = qedi_cmd;
+	list_work->rtid = cmd->task_id;
+	list_work->state = QEDI_WORK_SCHEDULED;
+	qedi_cmd->list_tmf_work = list_work;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "Queue tmf work=%p, list node=%p, cid=0x%x, tmf flags=0x%x\n",
+		  list_work->ptr_tmf_work, list_work, qedi_conn->iscsi_conn_id,
+		  tmf_hdr->flags);
+
+	spin_lock_bh(&qedi_conn->tmf_work_lock);
+	list_add_tail(&list_work->list, &qedi_conn->tmf_work_list);
+	spin_unlock_bh(&qedi_conn->tmf_work_lock);
+
+	qedi_iscsi_cleanup_task(ctask, false);
+
+	rval = qedi_wait_for_cleanup_request(qedi, qedi_conn, ctask, qedi_cmd,
+					     list_work);
+	if (rval == -1) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "FW cleanup got escalated, cid=0x%x\n",
+			  qedi_conn->iscsi_conn_id);
+		goto ldel_exit;
+	}
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1) {
+		QEDI_ERR(&qedi->dbg_ctx, "Invalid tid, cid=0x%x\n",
+			 qedi_conn->iscsi_conn_id);
+		goto ldel_exit;
+	}
+
+	qedi_cmd->task_id = tid;
+	qedi_send_iscsi_tmf(qedi_conn, qedi_cmd->task);
+
+abort_ret:
+	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+	return;
+
+ldel_exit:
+	spin_lock_bh(&qedi_conn->tmf_work_lock);
+	if (!qedi_cmd->list_tmf_work) {
+		list_del_init(&list_work->list);
+		qedi_cmd->list_tmf_work = NULL;
+		kfree(list_work);
+	}
+	spin_unlock_bh(&qedi_conn->tmf_work_lock);
+
+	spin_lock(&qedi_conn->list_lock);
+	list_del_init(&cmd->io_cmd);
+	qedi_conn->active_cmd_count--;
+	spin_unlock(&qedi_conn->list_lock);
+
+	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+}
+
+static int qedi_send_iscsi_tmf(struct qedi_conn *qedi_conn,
+			       struct iscsi_task *mtask)
+{
+	struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data;
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_tmf_request_hdr *fw_tmf_request;
+	struct iscsi_sge *single_sge;
+	struct qedi_cmd *qedi_cmd;
+	struct qedi_cmd *cmd;
+	struct iscsi_task *ctask;
+	struct iscsi_tm *tmf_hdr;
+	struct iscsi_sge *req_sge;
+	struct iscsi_sge *resp_sge;
+	u32 lun[2];
+	s16 tid = 0, ptu_invalidate = 0;
+
+	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
+	tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+
+	tid = qedi_cmd->task_id;
+	qedi_update_itt_map(qedi, tid, mtask->itt, qedi_cmd);
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
+	fw_tmf_request = &fw_task_ctx->ystorm_st_context.pdu_hdr.tmf_request;
+	fw_tmf_request->itt = qedi_set_itt(tid, get_itt(mtask->itt));
+	fw_tmf_request->cmd_sn = be32_to_cpu(tmf_hdr->cmdsn);
+
+	memcpy(lun, &tmf_hdr->lun, sizeof(struct scsi_lun));
+	fw_tmf_request->lun.lo = be32_to_cpu(lun[0]);
+	fw_tmf_request->lun.hi = be32_to_cpu(lun[1]);
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						qedi->tid_reuse_count[tid]++;
+
+	if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	     ISCSI_TM_FUNC_ABORT_TASK) {
+		ctask = iscsi_itt_to_task(conn, tmf_hdr->rtt);
+		if (!ctask || !ctask->sc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not get reference task\n");
+			return 0;
+		}
+		cmd = (struct qedi_cmd *)ctask->dd_data;
+		fw_tmf_request->rtt =
+				qedi_set_itt(cmd->task_id,
+					     get_itt(tmf_hdr->rtt));
+	} else {
+		fw_tmf_request->rtt = ISCSI_RESERVED_TAG;
+	}
+
+	fw_tmf_request->opcode = tmf_hdr->opcode;
+	fw_tmf_request->function = tmf_hdr->flags;
+	fw_tmf_request->hdr_second_dword = ntoh24(tmf_hdr->dlength);
+	fw_tmf_request->ref_cmd_sn = be32_to_cpu(tmf_hdr->refcmdsn);
+
+	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
+	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
+	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
+	single_sge->sge_len = resp_sge->sge_len;
+
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SINGLE_SGE, 1);
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SLOW_IO, 0);
+	fw_task_ctx->mstorm_st_context.sgl_size = 1;
+	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = 0;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = 0;
+	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
+	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+
+	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+		  ISCSI_REG1_NUM_FAST_SGES, 0);
+
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
+	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "Add TMF to SQ, tmf tid=0x%x, itt=0x%x, cid=0x%x\n",
+		  tid,  mtask->itt, qedi_conn->iscsi_conn_id);
+
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+	qedi_cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, mtask, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+	return 0;
+}
+
+int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn,
+			  struct iscsi_task *mtask)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_tm *tmf_hdr;
+	struct qedi_cmd *qedi_cmd = (struct qedi_cmd *)mtask->dd_data;
+	s16 tid = 0;
+
+	tmf_hdr = (struct iscsi_tm *)mtask->hdr;
+	qedi_cmd->task = mtask;
+
+	/* If abort task then schedule the work and return */
+	if ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+	    ISCSI_TM_FUNC_ABORT_TASK) {
+		qedi_cmd->state = CLEANUP_WAIT;
+		INIT_WORK(&qedi_cmd->tmf_work, qedi_tmf_work);
+		queue_work(qedi->tmf_thread, &qedi_cmd->tmf_work);
+
+	} else if (((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+		    ISCSI_TM_FUNC_LOGICAL_UNIT_RESET) ||
+		   ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+		    ISCSI_TM_FUNC_TARGET_WARM_RESET) ||
+		   ((tmf_hdr->flags & ISCSI_FLAG_TM_FUNC_MASK) ==
+		    ISCSI_TM_FUNC_TARGET_COLD_RESET)) {
+		tid = qedi_get_task_idx(qedi);
+		if (tid == -1) {
+			QEDI_ERR(&qedi->dbg_ctx, "Invalid tid, cid=0x%x\n",
+				 qedi_conn->iscsi_conn_id);
+			return -1;
+		}
+		qedi_cmd->task_id = tid;
+
+		qedi_send_iscsi_tmf(qedi_conn, qedi_cmd->task);
+
+	} else {
+		QEDI_ERR(&qedi->dbg_ctx, "Invalid tmf, cid=0x%x\n",
+			 qedi_conn->iscsi_conn_id);
+		return -1;
+	}
+
+	return 0;
+}
+
+int qedi_send_iscsi_text(struct qedi_conn *qedi_conn,
+			 struct iscsi_task *task)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_text_request_hdr *fw_text_request;
+	struct iscsi_cached_sge_ctx *cached_sge;
+	struct iscsi_sge *single_sge;
+	struct qedi_cmd *qedi_cmd;
+	/* For 6.5 hdr iscsi_hdr */
+	struct iscsi_text *text_hdr;
+	struct iscsi_sge *req_sge;
+	struct iscsi_sge *resp_sge;
+	s16 ptu_invalidate = 0;
+	s16 tid = 0;
+
+	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	text_hdr = (struct iscsi_text *)task->hdr;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+
+	qedi_cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_text_request =
+			&fw_task_ctx->ystorm_st_context.pdu_hdr.text_request;
+	fw_text_request->opcode = text_hdr->opcode;
+	fw_text_request->flags_attr = text_hdr->flags;
+
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+	fw_text_request->itt = qedi_set_itt(tid, get_itt(task->itt));
+	fw_text_request->ttt = text_hdr->ttt;
+	fw_text_request->cmd_sn = be32_to_cpu(text_hdr->cmdsn);
+	fw_text_request->exp_stat_sn = be32_to_cpu(text_hdr->exp_statsn);
+	fw_text_request->hdr_second_dword = ntoh24(text_hdr->dlength);
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						     qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						   qedi->tid_reuse_count[tid]++;
+
+	cached_sge =
+	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
+	cached_sge->sge.sge_len = req_sge->sge_len;
+	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	cached_sge->sge.sge_addr.hi =
+			      (u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+
+	/* Mstorm context */
+	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
+	fw_task_ctx->mstorm_st_context.task_type = 0x2;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
+	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
+	single_sge->sge_len = resp_sge->sge_len;
+
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SINGLE_SGE, 1);
+	SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+		  ISCSI_MFLAGS_SLOW_IO, 0);
+	fw_task_ctx->mstorm_st_context.sgl_size = 1;
+	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_ag_context.exp_data_acked =
+						      ntoh24(text_hdr->dlength);
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len =
+						      ntoh24(text_hdr->dlength);
+	fw_task_ctx->ustorm_st_context.exp_data_sn =
+					      be32_to_cpu(text_hdr->exp_statsn);
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+	fw_task_ctx->ustorm_st_context.task_type = 0x2;
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+	/*  Add command in active command list */
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+	qedi_cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+
+	return 0;
+}
+
+int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
+			   struct iscsi_task *task,
+			   char *datap, int data_len, int unsol)
+{
+	struct qedi_ctx *qedi = qedi_conn->qedi;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_nop_out_hdr *fw_nop_out;
+	struct qedi_cmd *qedi_cmd;
+	/* For 6.5 hdr iscsi_hdr */
+	struct iscsi_nopout *nopout_hdr;
+	struct iscsi_cached_sge_ctx *cached_sge;
+	struct iscsi_sge *single_sge;
+	struct iscsi_sge *req_sge;
+	struct iscsi_sge *resp_sge;
+	u32 lun[2];
+	s16 ptu_invalidate = 0;
+	s16 tid = 0;
+
+	req_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+	resp_sge = (struct iscsi_sge *)qedi_conn->gen_pdu.resp_bd_tbl;
+	qedi_cmd = (struct qedi_cmd *)task->dd_data;
+	nopout_hdr = (struct iscsi_nopout *)task->hdr;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1) {
+		QEDI_WARN(&qedi->dbg_ctx, "Invalid tid\n");
+		return -ENOMEM;
+	}
+
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+	qedi_cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_nop_out = &fw_task_ctx->ystorm_st_context.pdu_hdr.nop_out;
+	SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_CONST1, 1);
+	SET_FIELD(fw_nop_out->flags_attr, ISCSI_NOP_OUT_HDR_RSRV, 0);
+
+	memcpy(lun, &nopout_hdr->lun, sizeof(struct scsi_lun));
+	fw_nop_out->lun.lo = be32_to_cpu(lun[0]);
+	fw_nop_out->lun.hi = be32_to_cpu(lun[1]);
+
+	qedi_update_itt_map(qedi, tid, task->itt, qedi_cmd);
+
+	if (nopout_hdr->ttt != ISCSI_TTT_ALL_ONES) {
+		fw_nop_out->itt = be32_to_cpu(nopout_hdr->itt);
+		fw_nop_out->ttt = be32_to_cpu(nopout_hdr->ttt);
+		fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+		fw_task_ctx->ystorm_st_context.state.local_comp = 1;
+		SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+			  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 1);
+	} else {
+		fw_nop_out->itt = qedi_set_itt(tid, get_itt(task->itt));
+		fw_nop_out->ttt = ISCSI_TTT_ALL_ONES;
+		fw_task_ctx->ystorm_st_context.state.buffer_offset[0] = 0;
+
+		spin_lock(&qedi_conn->list_lock);
+		list_add_tail(&qedi_cmd->io_cmd, &qedi_conn->active_cmd_list);
+		qedi_cmd->io_cmd_in_list = true;
+		qedi_conn->active_cmd_count++;
+		spin_unlock(&qedi_conn->list_lock);
+	}
+
+	fw_nop_out->opcode = ISCSI_OPCODE_NOP_OUT;
+	fw_nop_out->cmd_sn = be32_to_cpu(nopout_hdr->cmdsn);
+	fw_nop_out->exp_stat_sn = be32_to_cpu(nopout_hdr->exp_statsn);
+
+	cached_sge =
+	       &fw_task_ctx->ystorm_st_context.state.sgl_ctx_union.cached_sge;
+	cached_sge->sge.sge_len = req_sge->sge_len;
+	cached_sge->sge.sge_addr.lo = (u32)(qedi_conn->gen_pdu.req_dma_addr);
+	cached_sge->sge.sge_addr.hi =
+			(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+
+	/* Mstorm context */
+	fw_task_ctx->mstorm_st_context.task_type = ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->mstorm_ag_context.task_cid = (u16)qedi_conn->iscsi_conn_id;
+
+	single_sge = &fw_task_ctx->mstorm_st_context.sgl_union.single_sge;
+	single_sge->sge_addr.lo = resp_sge->sge_addr.lo;
+	single_sge->sge_addr.hi = resp_sge->sge_addr.hi;
+	single_sge->sge_len = resp_sge->sge_len;
+	fw_task_ctx->mstorm_st_context.rem_task_size = resp_sge->sge_len;
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						qedi->tid_reuse_count[tid]++;
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = resp_sge->sge_len;
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = data_len;
+	fw_task_ctx->ustorm_st_context.exp_data_sn = 0;
+	fw_task_ctx->ustorm_st_context.task_type =  ISCSI_TASK_TYPE_MIDPATH;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = 0;
+
+	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+		  ISCSI_REG1_NUM_FAST_SGES, 0);
+
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+
+	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
+	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+	return 0;
+}
+
+static int qedi_split_bd(struct qedi_cmd *cmd, u64 addr, int sg_len,
+			 int bd_index)
+{
+	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	int frag_size, sg_frags;
+
+	sg_frags = 0;
+
+	while (sg_len) {
+		if (addr % QEDI_PAGE_SIZE)
+			frag_size =
+				   (QEDI_PAGE_SIZE - (addr % QEDI_PAGE_SIZE));
+		else
+			frag_size = (sg_len > QEDI_BD_SPLIT_SZ) ? 0 :
+				    (sg_len % QEDI_BD_SPLIT_SZ);
+
+		if (frag_size == 0)
+			frag_size = QEDI_BD_SPLIT_SZ;
+
+		bd[bd_index + sg_frags].sge_addr.lo = (addr & 0xffffffff);
+		bd[bd_index + sg_frags].sge_addr.hi = (addr >> 32);
+		bd[bd_index + sg_frags].sge_len = (u16)frag_size;
+		QEDI_INFO(&cmd->conn->qedi->dbg_ctx, QEDI_LOG_IO,
+			  "split sge %d: addr=%llx, len=%x",
+			  (bd_index + sg_frags), addr, frag_size);
+
+		addr += (u64)frag_size;
+		sg_frags++;
+		sg_len -= frag_size;
+	}
+	return sg_frags;
+}
+
+static int qedi_map_scsi_sg(struct qedi_ctx *qedi, struct qedi_cmd *cmd)
+{
+	struct scsi_cmnd *sc = cmd->scsi_cmd;
+	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	struct scatterlist *sg;
+	int byte_count = 0;
+	int bd_count = 0;
+	int sg_count;
+	int sg_len;
+	int sg_frags;
+	u64 addr, end_addr;
+	int i;
+
+	WARN_ON(scsi_sg_count(sc) > QEDI_ISCSI_MAX_BDS_PER_CMD);
+
+	sg_count = dma_map_sg(&qedi->pdev->dev, scsi_sglist(sc),
+			      scsi_sg_count(sc), sc->sc_data_direction);
+
+	/*
+	 * New condition to send single SGE as cached-SGL.
+	 * Single SGE with length less than 64K.
+	 */
+	sg = scsi_sglist(sc);
+	if ((sg_count == 1) && (sg_dma_len(sg) <= MAX_SGLEN_FOR_CACHESGL)) {
+		sg_len = sg_dma_len(sg);
+		addr = (u64)sg_dma_address(sg);
+
+		bd[bd_count].sge_addr.lo = (addr & 0xffffffff);
+		bd[bd_count].sge_addr.hi = (addr >> 32);
+		bd[bd_count].sge_len = (u16)sg_len;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
+			  "single-cashed-sgl: bd_count:%d addr=%llx, len=%x",
+			  sg_count, addr, sg_len);
+
+		return ++bd_count;
+	}
+
+	scsi_for_each_sg(sc, sg, sg_count, i) {
+		sg_len = sg_dma_len(sg);
+		addr = (u64)sg_dma_address(sg);
+		end_addr = (addr + sg_len);
+
+		/*
+		 * first sg elem in the 'list',
+		 * check if end addr is page-aligned.
+		 */
+		if ((i == 0) && (sg_count > 1) && (end_addr % QEDI_PAGE_SIZE))
+			cmd->use_slowpath = true;
+
+		/*
+		 * last sg elem in the 'list',
+		 * check if start addr is page-aligned.
+		 */
+		else if ((i == (sg_count - 1)) &&
+			 (sg_count > 1) && (addr % QEDI_PAGE_SIZE))
+			cmd->use_slowpath = true;
+
+		/*
+		 * middle sg elements in list,
+		 * check if start and end addr is page-aligned
+		 */
+		else if ((i != 0) && (i != (sg_count - 1)) &&
+			 ((addr % QEDI_PAGE_SIZE) ||
+			 (end_addr % QEDI_PAGE_SIZE)))
+			cmd->use_slowpath = true;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "sg[%d] size=0x%x",
+			  i, sg_len);
+
+		if (sg_len > QEDI_BD_SPLIT_SZ) {
+			sg_frags = qedi_split_bd(cmd, addr, sg_len, bd_count);
+		} else {
+			sg_frags = 1;
+			bd[bd_count].sge_addr.lo = addr & 0xffffffff;
+			bd[bd_count].sge_addr.hi = addr >> 32;
+			bd[bd_count].sge_len = sg_len;
+		}
+		byte_count += sg_len;
+		bd_count += sg_frags;
+	}
+
+	if (byte_count != scsi_bufflen(sc))
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "byte_count = %d != scsi_bufflen = %d\n", byte_count,
+			 scsi_bufflen(sc));
+	else
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "byte_count = %d\n",
+			  byte_count);
+
+	WARN_ON(byte_count != scsi_bufflen(sc));
+
+	return bd_count;
+}
+
+static void qedi_iscsi_map_sg_list(struct qedi_cmd *cmd)
+{
+	int bd_count;
+	struct scsi_cmnd *sc = cmd->scsi_cmd;
+
+	if (scsi_sg_count(sc)) {
+		bd_count  = qedi_map_scsi_sg(cmd->conn->qedi, cmd);
+		if (bd_count == 0)
+			return;
+	} else {
+		struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+
+		bd[0].sge_addr.lo = 0;
+		bd[0].sge_addr.hi = 0;
+		bd[0].sge_len = 0;
+		bd_count = 0;
+	}
+	cmd->io_tbl.sge_valid = bd_count;
+}
+
+static void qedi_cpy_scsi_cdb(struct scsi_cmnd *sc, u32 *dstp)
+{
+	u32 dword;
+	int lpcnt;
+	u8 *srcp;
+
+	lpcnt = sc->cmd_len / sizeof(dword);
+	srcp = (u8 *)sc->cmnd;
+	while (lpcnt--) {
+		memcpy(&dword, (const void *)srcp, 4);
+		*dstp = cpu_to_be32(dword);
+		srcp += 4;
+		dstp++;
+	}
+	if (sc->cmd_len & 0x3) {
+		dword = (u32)srcp[0] | ((u32)srcp[1] << 8);
+		*dstp = cpu_to_be32(dword);
+	}
+}
+
+void qedi_trace_io(struct qedi_ctx *qedi, struct iscsi_task *task,
+		   u16 tid, int8_t direction)
+{
+	struct qedi_io_log *io_log;
+	struct iscsi_conn *conn = task->conn;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct scsi_cmnd *sc_cmd = task->sc;
+	unsigned long flags;
+	u8 op;
+
+	spin_lock_irqsave(&qedi->io_trace_lock, flags);
+
+	io_log = &qedi->io_trace_buf[qedi->io_trace_idx];
+	io_log->direction = direction;
+	io_log->task_id = tid;
+	io_log->cid = qedi_conn->iscsi_conn_id;
+	io_log->lun = sc_cmd->device->lun;
+	io_log->op = sc_cmd->cmnd[0];
+	op = sc_cmd->cmnd[0];
+	io_log->lba[0] = sc_cmd->cmnd[2];
+	io_log->lba[1] = sc_cmd->cmnd[3];
+	io_log->lba[2] = sc_cmd->cmnd[4];
+	io_log->lba[3] = sc_cmd->cmnd[5];
+	io_log->bufflen = scsi_bufflen(sc_cmd);
+	io_log->sg_count = scsi_sg_count(sc_cmd);
+	io_log->fast_sgs = qedi->fast_sgls;
+	io_log->cached_sgs = qedi->cached_sgls;
+	io_log->slow_sgs = qedi->slow_sgls;
+	io_log->cached_sge = qedi->use_cached_sge;
+	io_log->slow_sge = qedi->use_slow_sge;
+	io_log->fast_sge = qedi->use_fast_sge;
+	io_log->result = sc_cmd->result;
+	io_log->jiffies = jiffies;
+	io_log->blk_req_cpu = smp_processor_id();
+
+	if (direction == QEDI_IO_TRACE_REQ) {
+		/* For requests we only care about the submission CPU */
+		io_log->req_cpu = smp_processor_id() % qedi->num_queues;
+		io_log->intr_cpu = 0;
+		io_log->blk_rsp_cpu = 0;
+	} else if (direction == QEDI_IO_TRACE_RSP) {
+		io_log->req_cpu = smp_processor_id() % qedi->num_queues;
+		io_log->intr_cpu = qedi->intr_cpu;
+		io_log->blk_rsp_cpu = smp_processor_id();
+	}
+
+	qedi->io_trace_idx++;
+	if (qedi->io_trace_idx == QEDI_IO_TRACE_SIZE)
+		qedi->io_trace_idx = 0;
+
+	qedi->use_cached_sge = false;
+	qedi->use_slow_sge = false;
+	qedi->use_fast_sge = false;
+
+	spin_unlock_irqrestore(&qedi->io_trace_lock, flags);
+}
+
+int qedi_iscsi_send_ioreq(struct iscsi_task *task)
+{
+	struct iscsi_conn *conn = task->conn;
+	struct iscsi_session *session = conn->session;
+	struct Scsi_Host *shost = iscsi_session_to_shost(session->cls_session);
+	struct qedi_ctx *qedi = iscsi_host_priv(shost);
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_cmd *cmd = task->dd_data;
+	struct scsi_cmnd *sc = task->sc;
+	struct iscsi_task_context *fw_task_ctx;
+	struct iscsi_cached_sge_ctx *cached_sge;
+	struct iscsi_phys_sgl_ctx *phys_sgl;
+	struct iscsi_virt_sgl_ctx *virt_sgl;
+	struct ystorm_iscsi_task_st_ctx *yst_cxt;
+	struct mstorm_iscsi_task_st_ctx *mst_cxt;
+	struct iscsi_sgl *sgl_struct;
+	struct iscsi_sge *single_sge;
+	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr;
+	struct iscsi_sge *bd = cmd->io_tbl.sge_tbl;
+	enum iscsi_task_type task_type;
+	struct iscsi_cmd_hdr *fw_cmd;
+	u32 lun[2];
+	u32 exp_data;
+	u16 cq_idx = smp_processor_id() % qedi->num_queues;
+	s16 ptu_invalidate = 0;
+	s16 tid = 0;
+	u8 num_fast_sgs;
+
+	tid = qedi_get_task_idx(qedi);
+	if (tid == -1)
+		return -ENOMEM;
+
+	qedi_iscsi_map_sg_list(cmd);
+
+	int_to_scsilun(sc->device->lun, (struct scsi_lun *)lun);
+	fw_task_ctx = qedi_get_task_mem(&qedi->tasks, tid);
+
+	memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context));
+	cmd->task_id = tid;
+
+	/* Ystorm context */
+	fw_cmd = &fw_task_ctx->ystorm_st_context.pdu_hdr.cmd;
+	SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_ATTR, ISCSI_ATTR_SIMPLE);
+
+	if (sc->sc_data_direction == DMA_TO_DEVICE) {
+		if (conn->session->initial_r2t_en) {
+			exp_data = min((conn->session->imm_data_en *
+					conn->max_xmit_dlength),
+				       conn->session->first_burst);
+			exp_data = min(exp_data, scsi_bufflen(sc));
+			fw_task_ctx->ustorm_ag_context.exp_data_acked =
+							  cpu_to_le32(exp_data);
+		} else {
+			fw_task_ctx->ustorm_ag_context.exp_data_acked =
+			      min(conn->session->first_burst, scsi_bufflen(sc));
+		}
+
+		SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_WRITE, 1);
+		task_type = ISCSI_TASK_TYPE_INITIATOR_WRITE;
+	} else {
+		if (scsi_bufflen(sc))
+			SET_FIELD(fw_cmd->flags_attr, ISCSI_CMD_HDR_READ, 1);
+		task_type = ISCSI_TASK_TYPE_INITIATOR_READ;
+	}
+
+	fw_cmd->lun.lo = be32_to_cpu(lun[0]);
+	fw_cmd->lun.hi = be32_to_cpu(lun[1]);
+
+	qedi_update_itt_map(qedi, tid, task->itt, cmd);
+	fw_cmd->itt = qedi_set_itt(tid, get_itt(task->itt));
+	fw_cmd->expected_transfer_length = scsi_bufflen(sc);
+	fw_cmd->cmd_sn = be32_to_cpu(hdr->cmdsn);
+	fw_cmd->opcode = hdr->opcode;
+	qedi_cpy_scsi_cdb(sc, (u32 *)fw_cmd->cdb);
+
+	/* Mstorm context */
+	fw_task_ctx->mstorm_st_context.sense_db.lo = (u32)cmd->sense_buffer_dma;
+	fw_task_ctx->mstorm_st_context.sense_db.hi =
+					(u32)((u64)cmd->sense_buffer_dma >> 32);
+	fw_task_ctx->mstorm_ag_context.task_cid = qedi_conn->iscsi_conn_id;
+	fw_task_ctx->mstorm_st_context.task_type = task_type;
+
+	if (qedi->tid_reuse_count[tid] == QEDI_MAX_TASK_NUM) {
+		ptu_invalidate = 1;
+		qedi->tid_reuse_count[tid] = 0;
+	}
+	fw_task_ctx->ystorm_st_context.state.reuse_count =
+						     qedi->tid_reuse_count[tid];
+	fw_task_ctx->mstorm_st_context.reuse_count =
+						   qedi->tid_reuse_count[tid]++;
+
+	/* Ustorm context */
+	fw_task_ctx->ustorm_st_context.rem_rcv_len = scsi_bufflen(sc);
+	fw_task_ctx->ustorm_st_context.exp_data_transfer_len = scsi_bufflen(sc);
+	fw_task_ctx->ustorm_st_context.exp_data_sn =
+						   be32_to_cpu(hdr->exp_statsn);
+	fw_task_ctx->ustorm_st_context.task_type = task_type;
+	fw_task_ctx->ustorm_st_context.cq_rss_number = cq_idx;
+	fw_task_ctx->ustorm_ag_context.icid = (u16)qedi_conn->iscsi_conn_id;
+
+	SET_FIELD(fw_task_ctx->ustorm_ag_context.flags1,
+		  USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.flags,
+		  USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP, 0);
+
+	num_fast_sgs = (cmd->io_tbl.sge_valid ?
+			min((u16)QEDI_FAST_SGE_COUNT,
+			    (u16)cmd->io_tbl.sge_valid) : 0);
+	SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+		  ISCSI_REG1_NUM_FAST_SGES, num_fast_sgs);
+
+	fw_task_ctx->ustorm_st_context.lun.lo = be32_to_cpu(lun[0]);
+	fw_task_ctx->ustorm_st_context.lun.hi = be32_to_cpu(lun[1]);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO, "Total sge count [%d]\n",
+		  cmd->io_tbl.sge_valid);
+
+	yst_cxt = &fw_task_ctx->ystorm_st_context;
+	mst_cxt = &fw_task_ctx->mstorm_st_context;
+	/* Tx path */
+	if (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) {
+		/* not considering  superIO or FastIO */
+		if (cmd->io_tbl.sge_valid == 1) {
+			cached_sge = &yst_cxt->state.sgl_ctx_union.cached_sge;
+			cached_sge->sge.sge_addr.lo = bd[0].sge_addr.lo;
+			cached_sge->sge.sge_addr.hi = bd[0].sge_addr.hi;
+			cached_sge->sge.sge_len = bd[0].sge_len;
+			qedi->cached_sgls++;
+		} else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 1);
+			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+				  ISCSI_REG1_NUM_FAST_SGES, 0);
+			phys_sgl = &yst_cxt->state.sgl_ctx_union.phys_sgl;
+			phys_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
+			phys_sgl->sgl_base.hi =
+				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+			phys_sgl->sgl_size = cmd->io_tbl.sge_valid;
+			qedi->slow_sgls++;
+		} else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 0);
+			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+				  ISCSI_REG1_NUM_FAST_SGES,
+				  min((u16)QEDI_FAST_SGE_COUNT,
+				      (u16)cmd->io_tbl.sge_valid));
+			virt_sgl = &yst_cxt->state.sgl_ctx_union.virt_sgl;
+			virt_sgl->sgl_base.lo = (u32)(cmd->io_tbl.sge_tbl_dma);
+			virt_sgl->sgl_base.hi =
+				      (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+			virt_sgl->sgl_initial_offset =
+				 (u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
+			qedi->fast_sgls++;
+		}
+		fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
+		fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
+	} else {
+	/* Rx path */
+		if (cmd->io_tbl.sge_valid == 1) {
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 0);
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SINGLE_SGE, 1);
+			single_sge = &mst_cxt->sgl_union.single_sge;
+			single_sge->sge_addr.lo = bd[0].sge_addr.lo;
+			single_sge->sge_addr.hi = bd[0].sge_addr.hi;
+			single_sge->sge_len = bd[0].sge_len;
+			qedi->cached_sgls++;
+		} else if ((cmd->io_tbl.sge_valid != 1) && cmd->use_slowpath) {
+			sgl_struct = &mst_cxt->sgl_union.sgl_struct;
+			sgl_struct->sgl_addr.lo =
+						(u32)(cmd->io_tbl.sge_tbl_dma);
+			sgl_struct->sgl_addr.hi =
+				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 1);
+			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+				  ISCSI_REG1_NUM_FAST_SGES, 0);
+			sgl_struct->updated_sge_size = 0;
+			sgl_struct->updated_sge_offset = 0;
+			qedi->slow_sgls++;
+		} else if ((cmd->io_tbl.sge_valid != 1) && !cmd->use_slowpath) {
+			sgl_struct = &mst_cxt->sgl_union.sgl_struct;
+			sgl_struct->sgl_addr.lo =
+						(u32)(cmd->io_tbl.sge_tbl_dma);
+			sgl_struct->sgl_addr.hi =
+				     (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32);
+			sgl_struct->byte_offset =
+				(u32)bd[0].sge_addr.lo & (QEDI_PAGE_SIZE - 1);
+			SET_FIELD(fw_task_ctx->mstorm_st_context.flags.mflags,
+				  ISCSI_MFLAGS_SLOW_IO, 0);
+			SET_FIELD(fw_task_ctx->ustorm_st_context.reg1.reg1_map,
+				  ISCSI_REG1_NUM_FAST_SGES, 0);
+			sgl_struct->updated_sge_size = 0;
+			sgl_struct->updated_sge_offset = 0;
+			qedi->fast_sgls++;
+		}
+		fw_task_ctx->mstorm_st_context.sgl_size = cmd->io_tbl.sge_valid;
+		fw_task_ctx->mstorm_st_context.rem_task_size = scsi_bufflen(sc);
+	}
+
+	if (cmd->io_tbl.sge_valid == 1)
+		/* Singel-SGL */
+		qedi->use_cached_sge = true;
+	else {
+		if (cmd->use_slowpath)
+			qedi->use_slow_sge = true;
+		else
+			qedi->use_fast_sge = true;
+	}
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
+		  "%s: %s-SGL: num_sges=0x%x first-sge-lo=0x%x first-sge-hi=0x%x",
+		  (task_type == ISCSI_TASK_TYPE_INITIATOR_WRITE) ?
+		  "Write " : "Read ", (cmd->io_tbl.sge_valid == 1) ?
+		  "Single" : (cmd->use_slowpath ? "SLOW" : "FAST"),
+		  (u16)cmd->io_tbl.sge_valid, (u32)(cmd->io_tbl.sge_tbl_dma),
+		  (u32)((u64)cmd->io_tbl.sge_tbl_dma >> 32));
+
+	/*  Add command in active command list */
+	spin_lock(&qedi_conn->list_lock);
+	list_add_tail(&cmd->io_cmd, &qedi_conn->active_cmd_list);
+	cmd->io_cmd_in_list = true;
+	qedi_conn->active_cmd_count++;
+	spin_unlock(&qedi_conn->list_lock);
+
+	qedi_add_to_sq(qedi_conn, task, tid, ptu_invalidate, false);
+	qedi_ring_doorbell(qedi_conn);
+	if (qedi_io_tracing)
+		qedi_trace_io(qedi, task, tid, QEDI_IO_TRACE_REQ);
+
+	return 0;
+}
+
+int qedi_iscsi_cleanup_task(struct iscsi_task *task, bool mark_cmd_node_deleted)
+{
+	struct iscsi_conn *conn = task->conn;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_cmd *cmd = task->dd_data;
+	s16 ptu_invalidate = 0;
+
+	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
+		  "issue cleanup tid=0x%x itt=0x%x task_state=%d cmd_state=0%x cid=0x%x\n",
+		  cmd->task_id, get_itt(task->itt), task->state,
+		  cmd->state, qedi_conn->iscsi_conn_id);
+
+	qedi_add_to_sq(qedi_conn, task, cmd->task_id, ptu_invalidate, true);
+	qedi_ring_doorbell(qedi_conn);
+
+	return 0;
+}
diff --git a/drivers/scsi/qedi/qedi_gbl.h b/drivers/scsi/qedi/qedi_gbl.h
new file mode 100644
index 0000000..8e488de
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_gbl.h
@@ -0,0 +1,73 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_GBL_H_
+#define _QEDI_GBL_H_
+
+#include "qedi_iscsi.h"
+
+extern uint qedi_io_tracing;
+extern int do_not_recover;
+extern struct scsi_host_template qedi_host_template;
+extern struct iscsi_transport qedi_iscsi_transport;
+extern const struct qed_iscsi_ops *qedi_ops;
+extern struct qedi_debugfs_ops qedi_debugfs_ops;
+extern const struct file_operations qedi_dbg_fops;
+extern struct device_attribute *qedi_shost_attrs[];
+
+int qedi_alloc_sq(struct qedi_ctx *qedi, struct qedi_endpoint *ep);
+void qedi_free_sq(struct qedi_ctx *qedi, struct qedi_endpoint *ep);
+
+int qedi_send_iscsi_login(struct qedi_conn *qedi_conn,
+			  struct iscsi_task *task);
+int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn,
+			   struct iscsi_task *task);
+int qedi_iscsi_abort_work(struct qedi_conn *qedi_conn,
+			  struct iscsi_task *mtask);
+int qedi_send_iscsi_text(struct qedi_conn *qedi_conn,
+			 struct iscsi_task *task);
+int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn,
+			   struct iscsi_task *task,
+			   char *datap, int data_len, int unsol);
+int qedi_iscsi_send_ioreq(struct iscsi_task *task);
+int qedi_get_task_idx(struct qedi_ctx *qedi);
+void qedi_clear_task_idx(struct qedi_ctx *qedi, int idx);
+int qedi_iscsi_cleanup_task(struct iscsi_task *task,
+			    bool mark_cmd_node_deleted);
+void qedi_iscsi_unmap_sg_list(struct qedi_cmd *cmd);
+void qedi_update_itt_map(struct qedi_ctx *qedi, u32 tid, u32 proto_itt,
+			 struct qedi_cmd *qedi_cmd);
+void qedi_get_proto_itt(struct qedi_ctx *qedi, u32 tid, u32 *proto_itt);
+void qedi_get_task_tid(struct qedi_ctx *qedi, u32 itt, int16_t *tid);
+void qedi_process_iscsi_error(struct qedi_endpoint *ep,
+			      struct async_data *data);
+void qedi_start_conn_recovery(struct qedi_ctx *qedi,
+			      struct qedi_conn *qedi_conn);
+struct qedi_conn *qedi_get_conn_from_id(struct qedi_ctx *qedi, u32 iscsi_cid);
+void qedi_process_tcp_error(struct qedi_endpoint *ep, struct async_data *data);
+void qedi_mark_device_missing(struct iscsi_cls_session *cls_session);
+void qedi_mark_device_available(struct iscsi_cls_session *cls_session);
+void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu);
+int qedi_recover_all_conns(struct qedi_ctx *qedi);
+void qedi_fp_process_cqes(struct qedi_work *work);
+int qedi_cleanup_all_io(struct qedi_ctx *qedi,
+			struct qedi_conn *qedi_conn,
+			struct iscsi_task *task, bool in_recovery);
+void qedi_trace_io(struct qedi_ctx *qedi, struct iscsi_task *task,
+		   u16 tid, int8_t direction);
+int qedi_alloc_id(struct qedi_portid_tbl *id_tbl, u16 id);
+u16 qedi_alloc_new_id(struct qedi_portid_tbl *id_tbl);
+void qedi_free_id(struct qedi_portid_tbl *id_tbl, u16 id);
+int qedi_create_sysfs_ctx_attr(struct qedi_ctx *qedi);
+void qedi_remove_sysfs_ctx_attr(struct qedi_ctx *qedi);
+void qedi_clearsq(struct qedi_ctx *qedi,
+		  struct qedi_conn *qedi_conn,
+		  struct iscsi_task *task);
+
+#endif
diff --git a/drivers/scsi/qedi/qedi_hsi.h b/drivers/scsi/qedi/qedi_hsi.h
new file mode 100644
index 0000000..8ca44c7
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_hsi.h
@@ -0,0 +1,52 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+#ifndef __QEDI_HSI__
+#define __QEDI_HSI__
+/*
+ * Add include to common target
+ */
+#include <linux/qed/common_hsi.h>
+
+/*
+ * Add include to common storage target
+ */
+#include <linux/qed/storage_common.h>
+
+/*
+ * Add include to common TCP target
+ */
+#include <linux/qed/tcp_common.h>
+
+/*
+ * Add include to common iSCSI target for both eCore and protocol driver
+ */
+#include <linux/qed/iscsi_common.h>
+
+/*
+ * iSCSI CMDQ element
+ */
+struct iscsi_cmdqe {
+	__le16 conn_id;
+	u8 invalid_command;
+	u8 cmd_hdr_type;
+	__le32 reserved1[2];
+	__le32 cmd_payload[13];
+};
+
+/*
+ * iSCSI CMD header type
+ */
+enum iscsi_cmd_hdr_type {
+	ISCSI_CMD_HDR_TYPE_BHS_ONLY /* iSCSI BHS with no expected AHS */,
+	ISCSI_CMD_HDR_TYPE_BHS_W_AHS /* iSCSI BHS with expected AHS */,
+	ISCSI_CMD_HDR_TYPE_AHS /* iSCSI AHS */,
+	MAX_ISCSI_CMD_HDR_TYPE
+};
+
+#endif /* __QEDI_HSI__ */
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
new file mode 100644
index 0000000..d6a2054
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -0,0 +1,1624 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include <linux/blkdev.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <scsi/scsi_tcq.h>
+
+#include "qedi.h"
+#include "qedi_iscsi.h"
+#include "qedi_gbl.h"
+
+int qedi_recover_all_conns(struct qedi_ctx *qedi)
+{
+	struct qedi_conn *qedi_conn;
+	int i;
+
+	for (i = 0; i < qedi->max_active_conns; i++) {
+		qedi_conn = qedi_get_conn_from_id(qedi, i);
+		if (!qedi_conn)
+			continue;
+
+		qedi_start_conn_recovery(qedi, qedi_conn);
+	}
+
+	return SUCCESS;
+}
+
+static int qedi_eh_host_reset(struct scsi_cmnd *cmd)
+{
+	struct Scsi_Host *shost = cmd->device->host;
+	struct qedi_ctx *qedi;
+
+	qedi = iscsi_host_priv(shost);
+
+	return qedi_recover_all_conns(qedi);
+}
+
+struct scsi_host_template qedi_host_template = {
+	.module = THIS_MODULE,
+	.name = "QLogic QEDI 25/40/100Gb iSCSI Initiator Driver",
+	.proc_name = QEDI_MODULE_NAME,
+	.queuecommand = iscsi_queuecommand,
+	.eh_abort_handler = iscsi_eh_abort,
+	.eh_device_reset_handler = iscsi_eh_device_reset,
+	.eh_target_reset_handler = iscsi_eh_recover_target,
+	.eh_host_reset_handler = qedi_eh_host_reset,
+	.target_alloc = iscsi_target_alloc,
+	.change_queue_depth = scsi_change_queue_depth,
+	.can_queue = QEDI_MAX_ISCSI_TASK,
+	.this_id = -1,
+	.sg_tablesize = QEDI_ISCSI_MAX_BDS_PER_CMD,
+	.max_sectors = 0xffff,
+	.cmd_per_lun = 128,
+	.use_clustering = ENABLE_CLUSTERING,
+	.shost_attrs = qedi_shost_attrs,
+};
+
+static void qedi_conn_free_login_resources(struct qedi_ctx *qedi,
+					   struct qedi_conn *qedi_conn)
+{
+	if (qedi_conn->gen_pdu.resp_bd_tbl) {
+		dma_free_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+				  qedi_conn->gen_pdu.resp_bd_tbl,
+				  qedi_conn->gen_pdu.resp_bd_dma);
+		qedi_conn->gen_pdu.resp_bd_tbl = NULL;
+	}
+
+	if (qedi_conn->gen_pdu.req_bd_tbl) {
+		dma_free_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+				  qedi_conn->gen_pdu.req_bd_tbl,
+				  qedi_conn->gen_pdu.req_bd_dma);
+		qedi_conn->gen_pdu.req_bd_tbl = NULL;
+	}
+
+	if (qedi_conn->gen_pdu.resp_buf) {
+		dma_free_coherent(&qedi->pdev->dev,
+				  ISCSI_DEF_MAX_RECV_SEG_LEN,
+				  qedi_conn->gen_pdu.resp_buf,
+				  qedi_conn->gen_pdu.resp_dma_addr);
+		qedi_conn->gen_pdu.resp_buf = NULL;
+	}
+
+	if (qedi_conn->gen_pdu.req_buf) {
+		dma_free_coherent(&qedi->pdev->dev,
+				  ISCSI_DEF_MAX_RECV_SEG_LEN,
+				  qedi_conn->gen_pdu.req_buf,
+				  qedi_conn->gen_pdu.req_dma_addr);
+		qedi_conn->gen_pdu.req_buf = NULL;
+	}
+}
+
+static int qedi_conn_alloc_login_resources(struct qedi_ctx *qedi,
+					   struct qedi_conn *qedi_conn)
+{
+	qedi_conn->gen_pdu.req_buf =
+		dma_alloc_coherent(&qedi->pdev->dev,
+				   ISCSI_DEF_MAX_RECV_SEG_LEN,
+				   &qedi_conn->gen_pdu.req_dma_addr,
+				   GFP_KERNEL);
+	if (!qedi_conn->gen_pdu.req_buf)
+		goto login_req_buf_failure;
+
+	qedi_conn->gen_pdu.req_buf_size = 0;
+	qedi_conn->gen_pdu.req_wr_ptr = qedi_conn->gen_pdu.req_buf;
+
+	qedi_conn->gen_pdu.resp_buf =
+		dma_alloc_coherent(&qedi->pdev->dev,
+				   ISCSI_DEF_MAX_RECV_SEG_LEN,
+				   &qedi_conn->gen_pdu.resp_dma_addr,
+				   GFP_KERNEL);
+	if (!qedi_conn->gen_pdu.resp_buf)
+		goto login_resp_buf_failure;
+
+	qedi_conn->gen_pdu.resp_buf_size = ISCSI_DEF_MAX_RECV_SEG_LEN;
+	qedi_conn->gen_pdu.resp_wr_ptr = qedi_conn->gen_pdu.resp_buf;
+
+	qedi_conn->gen_pdu.req_bd_tbl =
+		dma_alloc_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+				   &qedi_conn->gen_pdu.req_bd_dma, GFP_KERNEL);
+	if (!qedi_conn->gen_pdu.req_bd_tbl)
+		goto login_req_bd_tbl_failure;
+
+	qedi_conn->gen_pdu.resp_bd_tbl =
+		dma_alloc_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+				   &qedi_conn->gen_pdu.resp_bd_dma,
+				   GFP_KERNEL);
+	if (!qedi_conn->gen_pdu.resp_bd_tbl)
+		goto login_resp_bd_tbl_failure;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SESS,
+		  "Allocation successful, cid=0x%x\n",
+		  qedi_conn->iscsi_conn_id);
+	return 0;
+
+login_resp_bd_tbl_failure:
+	dma_free_coherent(&qedi->pdev->dev, QEDI_PAGE_SIZE,
+			  qedi_conn->gen_pdu.req_bd_tbl,
+			  qedi_conn->gen_pdu.req_bd_dma);
+	qedi_conn->gen_pdu.req_bd_tbl = NULL;
+
+login_req_bd_tbl_failure:
+	dma_free_coherent(&qedi->pdev->dev, ISCSI_DEF_MAX_RECV_SEG_LEN,
+			  qedi_conn->gen_pdu.resp_buf,
+			  qedi_conn->gen_pdu.resp_dma_addr);
+	qedi_conn->gen_pdu.resp_buf = NULL;
+login_resp_buf_failure:
+	dma_free_coherent(&qedi->pdev->dev, ISCSI_DEF_MAX_RECV_SEG_LEN,
+			  qedi_conn->gen_pdu.req_buf,
+			  qedi_conn->gen_pdu.req_dma_addr);
+	qedi_conn->gen_pdu.req_buf = NULL;
+login_req_buf_failure:
+	iscsi_conn_printk(KERN_ERR, qedi_conn->cls_conn->dd_data,
+			  "login resource alloc failed!!\n");
+	return -ENOMEM;
+}
+
+static void qedi_destroy_cmd_pool(struct qedi_ctx *qedi,
+				  struct iscsi_session *session)
+{
+	int i;
+
+	for (i = 0; i < session->cmds_max; i++) {
+		struct iscsi_task *task = session->cmds[i];
+		struct qedi_cmd *cmd = task->dd_data;
+
+		if (cmd->io_tbl.sge_tbl)
+			dma_free_coherent(&qedi->pdev->dev,
+					  QEDI_ISCSI_MAX_BDS_PER_CMD *
+					  sizeof(struct iscsi_sge),
+					  cmd->io_tbl.sge_tbl,
+					  cmd->io_tbl.sge_tbl_dma);
+
+		if (cmd->sense_buffer)
+			dma_free_coherent(&qedi->pdev->dev,
+					  SCSI_SENSE_BUFFERSIZE,
+					  cmd->sense_buffer,
+					  cmd->sense_buffer_dma);
+	}
+}
+
+static int qedi_alloc_sget(struct qedi_ctx *qedi, struct iscsi_session *session,
+			   struct qedi_cmd *cmd)
+{
+	struct qedi_io_bdt *io = &cmd->io_tbl;
+	struct iscsi_sge *sge;
+
+	io->sge_tbl = dma_alloc_coherent(&qedi->pdev->dev,
+					 QEDI_ISCSI_MAX_BDS_PER_CMD *
+					 sizeof(*sge),
+					 &io->sge_tbl_dma, GFP_KERNEL);
+	if (!io->sge_tbl) {
+		iscsi_session_printk(KERN_ERR, session,
+				     "Could not allocate BD table.\n");
+		return -ENOMEM;
+	}
+
+	io->sge_valid = 0;
+	return 0;
+}
+
+static int qedi_setup_cmd_pool(struct qedi_ctx *qedi,
+			       struct iscsi_session *session)
+{
+	int i;
+
+	for (i = 0; i < session->cmds_max; i++) {
+		struct iscsi_task *task = session->cmds[i];
+		struct qedi_cmd *cmd = task->dd_data;
+
+		task->hdr = &cmd->hdr;
+		task->hdr_max = sizeof(struct iscsi_hdr);
+
+		if (qedi_alloc_sget(qedi, session, cmd))
+			goto free_sgets;
+
+		cmd->sense_buffer = dma_alloc_coherent(&qedi->pdev->dev,
+						       SCSI_SENSE_BUFFERSIZE,
+						       &cmd->sense_buffer_dma,
+						       GFP_KERNEL);
+		if (!cmd->sense_buffer)
+			goto free_sgets;
+	}
+
+	return 0;
+
+free_sgets:
+	qedi_destroy_cmd_pool(qedi, session);
+	return -ENOMEM;
+}
+
+static struct iscsi_cls_session *
+qedi_session_create(struct iscsi_endpoint *ep, u16 cmds_max,
+		    u16 qdepth, uint32_t initial_cmdsn)
+{
+	struct Scsi_Host *shost;
+	struct iscsi_cls_session *cls_session;
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *qedi_ep;
+
+	if (!ep)
+		return NULL;
+
+	qedi_ep = ep->dd_data;
+	shost = qedi_ep->qedi->shost;
+	qedi = iscsi_host_priv(shost);
+
+	if (cmds_max > qedi->max_sqes)
+		cmds_max = qedi->max_sqes;
+	else if (cmds_max < QEDI_SQ_WQES_MIN)
+		cmds_max = QEDI_SQ_WQES_MIN;
+
+	cls_session = iscsi_session_setup(&qedi_iscsi_transport, shost,
+					  cmds_max, 0, sizeof(struct qedi_cmd),
+					  initial_cmdsn, ISCSI_MAX_TARGET);
+	if (!cls_session) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failed to setup session for ep=%p\n", qedi_ep);
+		return NULL;
+	}
+
+	if (qedi_setup_cmd_pool(qedi, cls_session->dd_data)) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failed to setup cmd pool for ep=%p\n", qedi_ep);
+		goto session_teardown;
+	}
+
+	return cls_session;
+
+session_teardown:
+	iscsi_session_teardown(cls_session);
+	return NULL;
+}
+
+static void qedi_session_destroy(struct iscsi_cls_session *cls_session)
+{
+	struct iscsi_session *session = cls_session->dd_data;
+	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
+	struct qedi_ctx *qedi = iscsi_host_priv(shost);
+
+	qedi_destroy_cmd_pool(qedi, session);
+	iscsi_session_teardown(cls_session);
+}
+
+static struct iscsi_cls_conn *
+qedi_conn_create(struct iscsi_cls_session *cls_session, uint32_t cid)
+{
+	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
+	struct qedi_ctx *qedi = iscsi_host_priv(shost);
+	struct iscsi_cls_conn *cls_conn;
+	struct qedi_conn *qedi_conn;
+	struct iscsi_conn *conn;
+
+	cls_conn = iscsi_conn_setup(cls_session, sizeof(*qedi_conn),
+				    cid);
+	if (!cls_conn) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "conn_new: iscsi conn setup failed, cid=0x%x, cls_sess=%p!\n",
+			 cid, cls_session);
+		return NULL;
+	}
+
+	conn = cls_conn->dd_data;
+	qedi_conn = conn->dd_data;
+	qedi_conn->cls_conn = cls_conn;
+	qedi_conn->qedi = qedi;
+	qedi_conn->ep = NULL;
+	qedi_conn->active_cmd_count = 0;
+	INIT_LIST_HEAD(&qedi_conn->active_cmd_list);
+	spin_lock_init(&qedi_conn->list_lock);
+
+	if (qedi_conn_alloc_login_resources(qedi, qedi_conn)) {
+		iscsi_conn_printk(KERN_ALERT, conn,
+				  "conn_new: login resc alloc failed, cid=0x%x, cls_sess=%p!!\n",
+				   cid, cls_session);
+		goto free_conn;
+	}
+
+	return cls_conn;
+
+free_conn:
+	iscsi_conn_teardown(cls_conn);
+	return NULL;
+}
+
+void qedi_mark_device_missing(struct iscsi_cls_session *cls_session)
+{
+	iscsi_block_session(cls_session);
+}
+
+void qedi_mark_device_available(struct iscsi_cls_session *cls_session)
+{
+	iscsi_unblock_session(cls_session);
+}
+
+static int qedi_bind_conn_to_iscsi_cid(struct qedi_ctx *qedi,
+				       struct qedi_conn *qedi_conn)
+{
+	u32 iscsi_cid = qedi_conn->iscsi_conn_id;
+
+	if (qedi->cid_que.conn_cid_tbl[iscsi_cid]) {
+		iscsi_conn_printk(KERN_ALERT, qedi_conn->cls_conn->dd_data,
+				  "conn bind - entry #%d not free\n",
+				  iscsi_cid);
+		return -EBUSY;
+	}
+
+	qedi->cid_que.conn_cid_tbl[iscsi_cid] = qedi_conn;
+	return 0;
+}
+
+struct qedi_conn *qedi_get_conn_from_id(struct qedi_ctx *qedi, u32 iscsi_cid)
+{
+	if (!qedi->cid_que.conn_cid_tbl) {
+		QEDI_ERR(&qedi->dbg_ctx, "missing conn<->cid table\n");
+		return NULL;
+
+	} else if (iscsi_cid >= qedi->max_active_conns) {
+		QEDI_ERR(&qedi->dbg_ctx, "wrong cid #%d\n", iscsi_cid);
+		return NULL;
+	}
+	return qedi->cid_que.conn_cid_tbl[iscsi_cid];
+}
+
+static int qedi_conn_bind(struct iscsi_cls_session *cls_session,
+			  struct iscsi_cls_conn *cls_conn,
+			  u64 transport_fd, int is_leading)
+{
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
+	struct qedi_ctx *qedi = iscsi_host_priv(shost);
+	struct qedi_endpoint *qedi_ep;
+	struct iscsi_endpoint *ep;
+
+	ep = iscsi_lookup_endpoint(transport_fd);
+	if (!ep)
+		return -EINVAL;
+
+	qedi_ep = ep->dd_data;
+	if ((qedi_ep->state == EP_STATE_TCP_FIN_RCVD) ||
+	    (qedi_ep->state == EP_STATE_TCP_RST_RCVD))
+		return -EINVAL;
+
+	if (iscsi_conn_bind(cls_session, cls_conn, is_leading))
+		return -EINVAL;
+
+	qedi_ep->conn = qedi_conn;
+	qedi_conn->ep = qedi_ep;
+	qedi_conn->iscsi_conn_id = qedi_ep->iscsi_cid;
+	qedi_conn->fw_cid = qedi_ep->fw_cid;
+	qedi_conn->cmd_cleanup_req = 0;
+	qedi_conn->cmd_cleanup_cmpl = 0;
+
+	if (qedi_bind_conn_to_iscsi_cid(qedi, qedi_conn))
+		return -EINVAL;
+
+	spin_lock_init(&qedi_conn->tmf_work_lock);
+	INIT_LIST_HEAD(&qedi_conn->tmf_work_list);
+	init_waitqueue_head(&qedi_conn->wait_queue);
+	return 0;
+}
+
+static int qedi_iscsi_update_conn(struct qedi_ctx *qedi,
+				  struct qedi_conn *qedi_conn)
+{
+	struct qed_iscsi_params_update *conn_info;
+	struct iscsi_cls_conn *cls_conn = qedi_conn->cls_conn;
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qedi_endpoint *qedi_ep;
+	int rval;
+
+	qedi_ep = qedi_conn->ep;
+
+	conn_info = kzalloc(sizeof(*conn_info), GFP_KERNEL);
+	if (!conn_info) {
+		QEDI_ERR(&qedi->dbg_ctx, "memory alloc failed\n");
+		return -ENOMEM;
+	}
+
+	conn_info->update_flag = 0;
+
+	if (conn->hdrdgst_en)
+		SET_FIELD(conn_info->update_flag,
+			  ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN, true);
+	if (conn->datadgst_en)
+		SET_FIELD(conn_info->update_flag,
+			  ISCSI_CONN_UPDATE_RAMROD_PARAMS_DD_EN, true);
+	if (conn->session->initial_r2t_en)
+		SET_FIELD(conn_info->update_flag,
+			  ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T,
+			  true);
+	if (conn->session->imm_data_en)
+		SET_FIELD(conn_info->update_flag,
+			  ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA,
+			  true);
+
+	conn_info->max_seq_size = conn->session->max_burst;
+	conn_info->max_recv_pdu_length = conn->max_recv_dlength;
+	conn_info->max_send_pdu_length = conn->max_xmit_dlength;
+	conn_info->first_seq_length = conn->session->first_burst;
+	conn_info->exp_stat_sn = conn->exp_statsn;
+
+	rval = qedi_ops->update_conn(qedi->cdev, qedi_ep->handle,
+				     conn_info);
+	if (rval) {
+		rval = -ENXIO;
+		QEDI_ERR(&qedi->dbg_ctx, "Could not update connection\n");
+		goto update_conn_err;
+	}
+
+	kfree(conn_info);
+	rval = 0;
+
+update_conn_err:
+	return rval;
+}
+
+static u16 qedi_calc_mss(u16 pmtu, u8 is_ipv6, u8 tcp_ts_en, u8 vlan_en)
+{
+	u16 mss = 0;
+	u16 hdrs = TCP_HDR_LEN;
+
+	if (is_ipv6)
+		hdrs += IPV6_HDR_LEN;
+	else
+		hdrs += IPV4_HDR_LEN;
+
+	if (vlan_en)
+		hdrs += VLAN_LEN;
+
+	mss = pmtu - hdrs;
+
+	if (tcp_ts_en)
+		mss -= TCP_OPTION_LEN;
+
+	if (!mss)
+		mss = DEF_MSS;
+
+	return mss;
+}
+
+static int qedi_iscsi_offload_conn(struct qedi_endpoint *qedi_ep)
+{
+	struct qedi_ctx *qedi = qedi_ep->qedi;
+	struct qed_iscsi_params_offload *conn_info;
+	int rval;
+	int i;
+
+	conn_info = kzalloc(sizeof(*conn_info), GFP_KERNEL);
+	if (!conn_info) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failed to allocate memory ep=%p\n", qedi_ep);
+		return -ENOMEM;
+	}
+
+	ether_addr_copy(conn_info->src.mac, qedi_ep->src_mac);
+	ether_addr_copy(conn_info->dst.mac, qedi_ep->dst_mac);
+
+	conn_info->src.ip[0] = ntohl(qedi_ep->src_addr[0]);
+	conn_info->dst.ip[0] = ntohl(qedi_ep->dst_addr[0]);
+
+	if (qedi_ep->ip_type == TCP_IPV4) {
+		conn_info->ip_version = 0;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "After ntohl: src_addr=%pI4, dst_addr=%pI4\n",
+			  qedi_ep->src_addr, qedi_ep->dst_addr);
+	} else {
+		for (i = 1; i < 4; i++) {
+			conn_info->src.ip[i] = ntohl(qedi_ep->src_addr[i]);
+			conn_info->dst.ip[i] = ntohl(qedi_ep->dst_addr[i]);
+		}
+
+		conn_info->ip_version = 1;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "After ntohl: src_addr=%pI6, dst_addr=%pI6\n",
+			  qedi_ep->src_addr, qedi_ep->dst_addr);
+	}
+
+	conn_info->src.port = qedi_ep->src_port;
+	conn_info->dst.port = qedi_ep->dst_port;
+
+	conn_info->layer_code = ISCSI_SLOW_PATH_LAYER_CODE;
+	conn_info->sq_pbl_addr = qedi_ep->sq_pbl_dma;
+	conn_info->vlan_id = qedi_ep->vlan_id;
+
+	SET_FIELD(conn_info->tcp_flags, TCP_OFFLOAD_PARAMS_TS_EN, 1);
+	SET_FIELD(conn_info->tcp_flags, TCP_OFFLOAD_PARAMS_DA_EN, 1);
+	SET_FIELD(conn_info->tcp_flags, TCP_OFFLOAD_PARAMS_DA_CNT_EN, 1);
+	SET_FIELD(conn_info->tcp_flags, TCP_OFFLOAD_PARAMS_KA_EN, 1);
+
+	conn_info->default_cq = (qedi_ep->fw_cid % 8);
+
+	conn_info->ka_max_probe_cnt = DEF_KA_MAX_PROBE_COUNT;
+	conn_info->dup_ack_theshold = 3;
+	conn_info->rcv_wnd = 65535;
+	conn_info->cwnd = DEF_MAX_CWND;
+
+	conn_info->ss_thresh = 65535;
+	conn_info->srtt = 300;
+	conn_info->rtt_var = 150;
+	conn_info->flow_label = 0;
+	conn_info->ka_timeout = DEF_KA_TIMEOUT;
+	conn_info->ka_interval = DEF_KA_INTERVAL;
+	conn_info->max_rt_time = DEF_MAX_RT_TIME;
+	conn_info->ttl = DEF_TTL;
+	conn_info->tos_or_tc = DEF_TOS;
+	conn_info->remote_port = qedi_ep->dst_port;
+	conn_info->local_port = qedi_ep->src_port;
+
+	conn_info->mss = qedi_calc_mss(qedi_ep->pmtu,
+				       (qedi_ep->ip_type == TCP_IPV6),
+				       1, (qedi_ep->vlan_id != 0));
+
+	conn_info->rcv_wnd_scale = 4;
+	conn_info->ts_ticks_per_second = 1000;
+	conn_info->da_timeout_value = 200;
+	conn_info->ack_frequency = 2;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "Default cq index [%d], mss [%d]\n",
+		  conn_info->default_cq, conn_info->mss);
+
+	rval = qedi_ops->offload_conn(qedi->cdev, qedi_ep->handle, conn_info);
+	if (rval)
+		QEDI_ERR(&qedi->dbg_ctx, "offload_conn returned %d, ep=%p\n",
+			 rval, qedi_ep);
+
+	kfree(conn_info);
+	return rval;
+}
+
+static int qedi_conn_start(struct iscsi_cls_conn *cls_conn)
+{
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_ctx *qedi;
+	int rval;
+
+	qedi = qedi_conn->qedi;
+
+	rval = qedi_iscsi_update_conn(qedi, qedi_conn);
+	if (rval) {
+		iscsi_conn_printk(KERN_ALERT, conn,
+				  "conn_start: FW oflload conn failed.\n");
+		rval = -EINVAL;
+		goto start_err;
+	}
+
+	clear_bit(QEDI_CONN_FW_CLEANUP, &qedi_conn->flags);
+	qedi_conn->abrt_conn = 0;
+
+	rval = iscsi_conn_start(cls_conn);
+	if (rval) {
+		iscsi_conn_printk(KERN_ALERT, conn,
+				  "iscsi_conn_start: FW oflload conn failed!!\n");
+	}
+
+start_err:
+	return rval;
+}
+
+static void qedi_conn_destroy(struct iscsi_cls_conn *cls_conn)
+{
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct Scsi_Host *shost;
+	struct qedi_ctx *qedi;
+
+	shost = iscsi_session_to_shost(iscsi_conn_to_session(cls_conn));
+	qedi = iscsi_host_priv(shost);
+
+	qedi_conn_free_login_resources(qedi, qedi_conn);
+	iscsi_conn_teardown(cls_conn);
+}
+
+static int qedi_ep_get_param(struct iscsi_endpoint *ep,
+			     enum iscsi_param param, char *buf)
+{
+	struct qedi_endpoint *qedi_ep = ep->dd_data;
+	int len;
+
+	if (!qedi_ep)
+		return -ENOTCONN;
+
+	switch (param) {
+	case ISCSI_PARAM_CONN_PORT:
+		len = sprintf(buf, "%hu\n", qedi_ep->dst_port);
+		break;
+	case ISCSI_PARAM_CONN_ADDRESS:
+		if (qedi_ep->ip_type == TCP_IPV4)
+			len = sprintf(buf, "%pI4\n", qedi_ep->dst_addr);
+		else
+			len = sprintf(buf, "%pI6\n", qedi_ep->dst_addr);
+		break;
+	default:
+		return -ENOTCONN;
+	}
+
+	return len;
+}
+
+static int qedi_host_get_param(struct Scsi_Host *shost,
+			       enum iscsi_host_param param, char *buf)
+{
+	struct qedi_ctx *qedi;
+	int len;
+
+	qedi = iscsi_host_priv(shost);
+
+	switch (param) {
+	case ISCSI_HOST_PARAM_HWADDRESS:
+		len = sysfs_format_mac(buf, qedi->mac, 6);
+		break;
+	case ISCSI_HOST_PARAM_NETDEV_NAME:
+		len = sprintf(buf, "host%d\n", shost->host_no);
+		break;
+	case ISCSI_HOST_PARAM_IPADDRESS:
+		if (qedi->ip_type == TCP_IPV4)
+			len = sprintf(buf, "%pI4\n", qedi->src_ip);
+		else
+			len = sprintf(buf, "%pI6\n", qedi->src_ip);
+		break;
+	default:
+		return iscsi_host_get_param(shost, param, buf);
+	}
+
+	return len;
+}
+
+static void qedi_conn_get_stats(struct iscsi_cls_conn *cls_conn,
+				struct iscsi_stats *stats)
+{
+	struct iscsi_conn *conn = cls_conn->dd_data;
+	struct qed_iscsi_stats iscsi_stats;
+	struct Scsi_Host *shost;
+	struct qedi_ctx *qedi;
+
+	shost = iscsi_session_to_shost(iscsi_conn_to_session(cls_conn));
+	qedi = iscsi_host_priv(shost);
+	qedi_ops->get_stats(qedi->cdev, &iscsi_stats);
+
+	conn->txdata_octets = iscsi_stats.iscsi_tx_bytes_cnt;
+	conn->rxdata_octets = iscsi_stats.iscsi_rx_bytes_cnt;
+	conn->dataout_pdus_cnt = (uint32_t)iscsi_stats.iscsi_tx_data_pdu_cnt;
+	conn->datain_pdus_cnt = (uint32_t)iscsi_stats.iscsi_rx_data_pdu_cnt;
+	conn->r2t_pdus_cnt = (uint32_t)iscsi_stats.iscsi_rx_r2t_pdu_cnt;
+
+	stats->txdata_octets = conn->txdata_octets;
+	stats->rxdata_octets = conn->rxdata_octets;
+	stats->scsicmd_pdus = conn->scsicmd_pdus_cnt;
+	stats->dataout_pdus = conn->dataout_pdus_cnt;
+	stats->scsirsp_pdus = conn->scsirsp_pdus_cnt;
+	stats->datain_pdus = conn->datain_pdus_cnt;
+	stats->r2t_pdus = conn->r2t_pdus_cnt;
+	stats->tmfcmd_pdus = conn->tmfcmd_pdus_cnt;
+	stats->tmfrsp_pdus = conn->tmfrsp_pdus_cnt;
+	stats->digest_err = 0;
+	stats->timeout_err = 0;
+	strcpy(stats->custom[0].desc, "eh_abort_cnt");
+	stats->custom[0].value = conn->eh_abort_cnt;
+	stats->custom_length = 1;
+}
+
+static void qedi_iscsi_prep_generic_pdu_bd(struct qedi_conn *qedi_conn)
+{
+	struct iscsi_sge *bd_tbl;
+
+	bd_tbl = (struct iscsi_sge *)qedi_conn->gen_pdu.req_bd_tbl;
+
+	bd_tbl->sge_addr.hi =
+		(u32)((u64)qedi_conn->gen_pdu.req_dma_addr >> 32);
+	bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.req_dma_addr;
+	bd_tbl->sge_len = qedi_conn->gen_pdu.req_wr_ptr -
+				qedi_conn->gen_pdu.req_buf;
+	bd_tbl->reserved0 = 0;
+	bd_tbl = (struct iscsi_sge  *)qedi_conn->gen_pdu.resp_bd_tbl;
+	bd_tbl->sge_addr.hi =
+			(u32)((u64)qedi_conn->gen_pdu.resp_dma_addr >> 32);
+	bd_tbl->sge_addr.lo = (u32)qedi_conn->gen_pdu.resp_dma_addr;
+	bd_tbl->sge_len = ISCSI_DEF_MAX_RECV_SEG_LEN;
+	bd_tbl->reserved0 = 0;
+}
+
+static int qedi_iscsi_send_generic_request(struct iscsi_task *task)
+{
+	struct qedi_cmd *cmd = task->dd_data;
+	struct qedi_conn *qedi_conn = cmd->conn;
+	char *buf;
+	int data_len;
+	int rc = 0;
+
+	qedi_iscsi_prep_generic_pdu_bd(qedi_conn);
+	switch (task->hdr->opcode & ISCSI_OPCODE_MASK) {
+	case ISCSI_OP_LOGIN:
+		qedi_send_iscsi_login(qedi_conn, task);
+		break;
+	case ISCSI_OP_NOOP_OUT:
+		data_len = qedi_conn->gen_pdu.req_buf_size;
+		buf = qedi_conn->gen_pdu.req_buf;
+		if (data_len)
+			rc = qedi_send_iscsi_nopout(qedi_conn, task,
+						    buf, data_len, 1);
+		else
+			rc = qedi_send_iscsi_nopout(qedi_conn, task,
+						    NULL, 0, 1);
+		break;
+	case ISCSI_OP_LOGOUT:
+		rc = qedi_send_iscsi_logout(qedi_conn, task);
+		break;
+	case ISCSI_OP_SCSI_TMFUNC:
+		rc = qedi_iscsi_abort_work(qedi_conn, task);
+		break;
+	case ISCSI_OP_TEXT:
+		rc = qedi_send_iscsi_text(qedi_conn, task);
+		break;
+	default:
+		iscsi_conn_printk(KERN_ALERT, qedi_conn->cls_conn->dd_data,
+				  "unsupported op 0x%x\n", task->hdr->opcode);
+	}
+
+	return rc;
+}
+
+static int qedi_mtask_xmit(struct iscsi_conn *conn, struct iscsi_task *task)
+{
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_cmd *cmd = task->dd_data;
+
+	memset(qedi_conn->gen_pdu.req_buf, 0, ISCSI_DEF_MAX_RECV_SEG_LEN);
+
+	qedi_conn->gen_pdu.req_buf_size = task->data_count;
+
+	if (task->data_count) {
+		memcpy(qedi_conn->gen_pdu.req_buf, task->data,
+		       task->data_count);
+		qedi_conn->gen_pdu.req_wr_ptr =
+			qedi_conn->gen_pdu.req_buf + task->data_count;
+	}
+
+	cmd->conn = conn->dd_data;
+	cmd->scsi_cmd = NULL;
+	return qedi_iscsi_send_generic_request(task);
+}
+
+static int qedi_task_xmit(struct iscsi_task *task)
+{
+	struct iscsi_conn *conn = task->conn;
+	struct qedi_conn *qedi_conn = conn->dd_data;
+	struct qedi_cmd *cmd = task->dd_data;
+	struct scsi_cmnd *sc = task->sc;
+
+	cmd->state = 0;
+	cmd->task = NULL;
+	cmd->use_slowpath = false;
+	cmd->conn = qedi_conn;
+	cmd->task = task;
+	cmd->io_cmd_in_list = false;
+	INIT_LIST_HEAD(&cmd->io_cmd);
+
+	if (!sc)
+		return qedi_mtask_xmit(conn, task);
+
+	cmd->scsi_cmd = sc;
+	return qedi_iscsi_send_ioreq(task);
+}
+
+static struct iscsi_endpoint *
+qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr,
+		int non_blocking)
+{
+	struct qedi_ctx *qedi;
+	struct iscsi_endpoint *ep;
+	struct qedi_endpoint *qedi_ep;
+	struct sockaddr_in *addr;
+	struct sockaddr_in6 *addr6;
+	struct qed_dev *cdev  =  NULL;
+	struct qedi_uio_dev *udev = NULL;
+	struct iscsi_path path_req;
+	u32 msg_type = ISCSI_KEVENT_IF_DOWN;
+	u32 iscsi_cid = QEDI_CID_RESERVED;
+	u16 len = 0;
+	char *buf = NULL;
+	int ret;
+
+	if (!shost) {
+		ret = -ENXIO;
+		QEDI_ERR(NULL, "shost is NULL\n");
+		return ERR_PTR(ret);
+	}
+
+	if (do_not_recover) {
+		ret = -ENOMEM;
+		return ERR_PTR(ret);
+	}
+
+	qedi = iscsi_host_priv(shost);
+	cdev = qedi->cdev;
+	udev = qedi->udev;
+
+	if (test_bit(QEDI_IN_OFFLINE, &qedi->flags) ||
+	    test_bit(QEDI_IN_RECOVERY, &qedi->flags)) {
+		ret = -ENOMEM;
+		return ERR_PTR(ret);
+	}
+
+	ep = iscsi_create_endpoint(sizeof(struct qedi_endpoint));
+	if (!ep) {
+		QEDI_ERR(&qedi->dbg_ctx, "endpoint create fail\n");
+		ret = -ENOMEM;
+		return ERR_PTR(ret);
+	}
+	qedi_ep = ep->dd_data;
+	memset(qedi_ep, 0, sizeof(struct qedi_endpoint));
+	qedi_ep->state = EP_STATE_IDLE;
+	qedi_ep->iscsi_cid = (u32)-1;
+	qedi_ep->qedi = qedi;
+
+	if (dst_addr->sa_family == AF_INET) {
+		addr = (struct sockaddr_in *)dst_addr;
+		memcpy(qedi_ep->dst_addr, &addr->sin_addr.s_addr,
+		       sizeof(struct in_addr));
+		qedi_ep->dst_port = ntohs(addr->sin_port);
+		qedi_ep->ip_type = TCP_IPV4;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "dst_addr=%pI4, dst_port=%u\n",
+			  qedi_ep->dst_addr, qedi_ep->dst_port);
+	} else if (dst_addr->sa_family == AF_INET6) {
+		addr6 = (struct sockaddr_in6 *)dst_addr;
+		memcpy(qedi_ep->dst_addr, &addr6->sin6_addr,
+		       sizeof(struct in6_addr));
+		qedi_ep->dst_port = ntohs(addr6->sin6_port);
+		qedi_ep->ip_type = TCP_IPV6;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "dst_addr=%pI6, dst_port=%u\n",
+			  qedi_ep->dst_addr, qedi_ep->dst_port);
+	} else {
+		QEDI_ERR(&qedi->dbg_ctx, "Invalid endpoint\n");
+	}
+
+	if (atomic_read(&qedi->link_state) != QEDI_LINK_UP) {
+		QEDI_WARN(&qedi->dbg_ctx, "qedi link down\n");
+		ret = -ENXIO;
+		goto ep_conn_exit;
+	}
+
+	ret = qedi_alloc_sq(qedi, qedi_ep);
+	if (ret)
+		goto ep_conn_exit;
+
+	ret = qedi_ops->acquire_conn(qedi->cdev, &qedi_ep->handle,
+				     &qedi_ep->fw_cid, &qedi_ep->p_doorbell);
+
+	if (ret) {
+		QEDI_ERR(&qedi->dbg_ctx, "Could not acquire connection\n");
+		ret = -ENXIO;
+		goto ep_free_sq;
+	}
+
+	iscsi_cid = qedi_ep->handle;
+	qedi_ep->iscsi_cid = iscsi_cid;
+
+	init_waitqueue_head(&qedi_ep->ofld_wait);
+	init_waitqueue_head(&qedi_ep->tcp_ofld_wait);
+	qedi_ep->state = EP_STATE_OFLDCONN_START;
+	qedi->ep_tbl[iscsi_cid] = qedi_ep;
+
+	buf = (char *)&path_req;
+	len = sizeof(path_req);
+	memset(&path_req, 0, len);
+
+	msg_type = ISCSI_KEVENT_PATH_REQ;
+	path_req.handle = (u64)qedi_ep->iscsi_cid;
+	path_req.pmtu = qedi->ll2_mtu;
+	qedi_ep->pmtu = qedi->ll2_mtu;
+	if (qedi_ep->ip_type == TCP_IPV4) {
+		memcpy(&path_req.dst.v4_addr, &qedi_ep->dst_addr,
+		       sizeof(struct in_addr));
+		path_req.ip_addr_len = 4;
+	} else {
+		memcpy(&path_req.dst.v6_addr, &qedi_ep->dst_addr,
+		       sizeof(struct in6_addr));
+		path_req.ip_addr_len = 16;
+	}
+
+	ret = iscsi_offload_mesg(shost, &qedi_iscsi_transport, msg_type, buf,
+				 len);
+	if (ret) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "iscsi_offload_mesg() failed for cid=0x%x ret=%d\n",
+			 iscsi_cid, ret);
+		goto ep_rel_conn;
+	}
+
+	atomic_inc(&qedi->num_offloads);
+	return ep;
+
+ep_rel_conn:
+	qedi->ep_tbl[iscsi_cid] = NULL;
+	ret = qedi_ops->release_conn(qedi->cdev, qedi_ep->handle);
+	if (ret)
+		QEDI_WARN(&qedi->dbg_ctx, "release_conn returned %d\n",
+			  ret);
+ep_free_sq:
+	qedi_free_sq(qedi, qedi_ep);
+ep_conn_exit:
+	iscsi_destroy_endpoint(ep);
+	return ERR_PTR(ret);
+}
+
+static int qedi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms)
+{
+	struct qedi_endpoint *qedi_ep;
+	int ret = 0;
+
+	if (do_not_recover)
+		return 1;
+
+	qedi_ep = ep->dd_data;
+	if (qedi_ep->state == EP_STATE_IDLE ||
+	    qedi_ep->state == EP_STATE_OFLDCONN_FAILED)
+		return -1;
+
+	if (qedi_ep->state == EP_STATE_OFLDCONN_COMPL)
+		ret = 1;
+
+	ret = wait_event_interruptible_timeout(qedi_ep->ofld_wait,
+					       QEDI_OFLD_WAIT_STATE(qedi_ep),
+					       msecs_to_jiffies(timeout_ms));
+
+	if (qedi_ep->state == EP_STATE_OFLDCONN_FAILED)
+		ret = -1;
+
+	if (ret > 0)
+		return 1;
+	else if (!ret)
+		return 0;
+	else
+		return ret;
+}
+
+static void qedi_cleanup_active_cmd_list(struct qedi_conn *qedi_conn)
+{
+	struct qedi_cmd *cmd, *cmd_tmp;
+
+	list_for_each_entry_safe(cmd, cmd_tmp, &qedi_conn->active_cmd_list,
+				 io_cmd) {
+		list_del_init(&cmd->io_cmd);
+		qedi_conn->active_cmd_count--;
+	}
+}
+
+static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
+{
+	struct qedi_endpoint *qedi_ep;
+	struct qedi_conn *qedi_conn = NULL;
+	struct iscsi_conn *conn = NULL;
+	struct qedi_ctx *qedi;
+	int ret = 0;
+	int wait_delay = 20 * HZ;
+	int abrt_conn = 0;
+	int count = 10;
+
+	qedi_ep = ep->dd_data;
+	qedi = qedi_ep->qedi;
+
+	flush_work(&qedi_ep->offload_work);
+
+	if (qedi_ep->conn) {
+		qedi_conn = qedi_ep->conn;
+		conn = qedi_conn->cls_conn->dd_data;
+		iscsi_suspend_queue(conn);
+		abrt_conn = qedi_conn->abrt_conn;
+
+		while (count--)	{
+			if (!test_bit(QEDI_CONN_FW_CLEANUP,
+				      &qedi_conn->flags)) {
+				break;
+			}
+			msleep(1000);
+		}
+
+		if (test_bit(QEDI_IN_RECOVERY, &qedi->flags)) {
+			if (do_not_recover) {
+				QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+					  "Do not recover cid=0x%x\n",
+					  qedi_ep->iscsi_cid);
+				goto ep_exit_recover;
+			}
+			QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+				  "Reset recovery cid=0x%x, qedi_ep=%p, state=0x%x\n",
+				  qedi_ep->iscsi_cid, qedi_ep, qedi_ep->state);
+			qedi_cleanup_active_cmd_list(qedi_conn);
+			goto ep_release_conn;
+		}
+	}
+
+	if (do_not_recover)
+		goto ep_exit_recover;
+
+	switch (qedi_ep->state) {
+	case EP_STATE_OFLDCONN_START:
+		goto ep_release_conn;
+	case EP_STATE_OFLDCONN_FAILED:
+			break;
+	case EP_STATE_OFLDCONN_COMPL:
+		if (unlikely(!qedi_conn))
+			break;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Active cmd count=%d, abrt_conn=%d, ep state=0x%x, cid=0x%x, qedi_conn=%p\n",
+			  qedi_conn->active_cmd_count, abrt_conn,
+			  qedi_ep->state,
+			  qedi_ep->iscsi_cid,
+			  qedi_ep->conn
+			  );
+
+		if (!qedi_conn->active_cmd_count)
+			abrt_conn = 0;
+		else
+			abrt_conn = 1;
+
+		if (abrt_conn)
+			qedi_clearsq(qedi, qedi_conn, NULL);
+		break;
+	default:
+		break;
+	}
+
+	qedi_ep->state = EP_STATE_DISCONN_START;
+	ret = qedi_ops->destroy_conn(qedi->cdev, qedi_ep->handle, abrt_conn);
+	if (ret) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "destroy_conn failed returned %d\n", ret);
+	} else {
+		ret = wait_event_interruptible_timeout(
+					qedi_ep->tcp_ofld_wait,
+					(qedi_ep->state !=
+					 EP_STATE_DISCONN_START),
+					wait_delay);
+		if ((ret <= 0) || (qedi_ep->state == EP_STATE_DISCONN_START)) {
+			QEDI_WARN(&qedi->dbg_ctx,
+				  "Destroy conn timedout or interrupted, ret=%d, delay=%d, cid=0x%x\n",
+				  ret, wait_delay, qedi_ep->iscsi_cid);
+		}
+	}
+
+ep_release_conn:
+	ret = qedi_ops->release_conn(qedi->cdev, qedi_ep->handle);
+	if (ret)
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "release_conn returned %d, cid=0x%x\n",
+			  ret, qedi_ep->iscsi_cid);
+ep_exit_recover:
+	qedi_ep->state = EP_STATE_IDLE;
+	qedi->ep_tbl[qedi_ep->iscsi_cid] = NULL;
+	qedi->cid_que.conn_cid_tbl[qedi_ep->iscsi_cid] = NULL;
+	qedi_free_id(&qedi->lcl_port_tbl, qedi_ep->src_port);
+	qedi_free_sq(qedi, qedi_ep);
+
+	if (qedi_conn)
+		qedi_conn->ep = NULL;
+
+	qedi_ep->conn = NULL;
+	qedi_ep->qedi = NULL;
+	atomic_dec(&qedi->num_offloads);
+
+	iscsi_destroy_endpoint(ep);
+}
+
+static int qedi_data_avail(struct qedi_ctx *qedi, u16 vlanid)
+{
+	struct qed_dev *cdev = qedi->cdev;
+	struct qedi_uio_dev *udev;
+	struct qedi_uio_ctrl *uctrl;
+	struct sk_buff *skb;
+	u32 len;
+	int rc = 0;
+
+	udev = qedi->udev;
+	if (!udev) {
+		QEDI_ERR(&qedi->dbg_ctx, "udev is NULL.\n");
+		return -EINVAL;
+	}
+
+	uctrl = (struct qedi_uio_ctrl *)udev->uctrl;
+	if (!uctrl) {
+		QEDI_ERR(&qedi->dbg_ctx, "uctlr is NULL.\n");
+		return -EINVAL;
+	}
+
+	len = uctrl->host_tx_pkt_len;
+	if (!len) {
+		QEDI_ERR(&qedi->dbg_ctx, "Invalid len %u\n", len);
+		return -EINVAL;
+	}
+
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (!skb) {
+		QEDI_ERR(&qedi->dbg_ctx, "alloc_skb failed\n");
+		return -EINVAL;
+	}
+
+	skb_put(skb, len);
+	memcpy(skb->data, udev->tx_pkt, len);
+	skb->ip_summed = CHECKSUM_NONE;
+
+	if (vlanid)
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlanid);
+
+	rc = qedi_ops->ll2->start_xmit(cdev, skb);
+	if (rc) {
+		QEDI_ERR(&qedi->dbg_ctx, "ll2 start_xmit returned %d\n",
+			 rc);
+		kfree_skb(skb);
+	}
+
+	uctrl->host_tx_pkt_len = 0;
+	uctrl->hw_tx_cons++;
+
+	return rc;
+}
+
+static void qedi_offload_work(struct work_struct *work)
+{
+	struct qedi_endpoint *qedi_ep =
+		container_of(work, struct qedi_endpoint, offload_work);
+	struct qedi_ctx *qedi;
+	int wait_delay = 20 * HZ;
+	int ret;
+
+	qedi = qedi_ep->qedi;
+
+	ret = qedi_iscsi_offload_conn(qedi_ep);
+	if (ret) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n",
+			 qedi_ep->iscsi_cid, qedi_ep, ret);
+		qedi_ep->state = EP_STATE_OFLDCONN_FAILED;
+		return;
+	}
+
+	ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait,
+					       (qedi_ep->state ==
+					       EP_STATE_OFLDCONN_COMPL),
+					       wait_delay);
+	if ((ret <= 0) || (qedi_ep->state != EP_STATE_OFLDCONN_COMPL)) {
+		qedi_ep->state = EP_STATE_OFLDCONN_FAILED;
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n",
+			 qedi_ep->iscsi_cid, qedi_ep);
+	}
+}
+
+static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data)
+{
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *qedi_ep;
+	int ret = 0;
+	u32 iscsi_cid;
+	u16 port_id = 0;
+
+	if (!shost) {
+		ret = -ENXIO;
+		QEDI_ERR(NULL, "shost is NULL\n");
+		return ret;
+	}
+
+	if (strcmp(shost->hostt->proc_name, "qedi")) {
+		ret = -ENXIO;
+		QEDI_ERR(NULL, "shost %s is invalid\n",
+			 shost->hostt->proc_name);
+		return ret;
+	}
+
+	qedi = iscsi_host_priv(shost);
+	if (path_data->handle == QEDI_PATH_HANDLE) {
+		ret = qedi_data_avail(qedi, path_data->vlan_id);
+		goto set_path_exit;
+	}
+
+	iscsi_cid = (u32)path_data->handle;
+	qedi_ep = qedi->ep_tbl[iscsi_cid];
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "iscsi_cid=0x%x, qedi_ep=%p\n", iscsi_cid, qedi_ep);
+
+	if (!is_valid_ether_addr(&path_data->mac_addr[0])) {
+		QEDI_NOTICE(&qedi->dbg_ctx, "dst mac NOT VALID\n");
+		ret = -EIO;
+		goto set_path_exit;
+	}
+
+	ether_addr_copy(&qedi_ep->src_mac[0], &qedi->mac[0]);
+	ether_addr_copy(&qedi_ep->dst_mac[0], &path_data->mac_addr[0]);
+
+	qedi_ep->vlan_id = path_data->vlan_id;
+	if (path_data->pmtu < DEF_PATH_MTU) {
+		qedi_ep->pmtu = qedi->ll2_mtu;
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "MTU cannot be %u, using default MTU %u\n",
+			   path_data->pmtu, qedi_ep->pmtu);
+	}
+
+	if (path_data->pmtu != qedi->ll2_mtu) {
+		if (path_data->pmtu > JUMBO_MTU) {
+			ret = -EINVAL;
+			QEDI_ERR(NULL, "Invalid MTU %u\n", path_data->pmtu);
+			goto set_path_exit;
+		}
+
+		qedi_reset_host_mtu(qedi, path_data->pmtu);
+		qedi_ep->pmtu = qedi->ll2_mtu;
+	}
+
+	port_id = qedi_ep->src_port;
+	if (port_id >= QEDI_LOCAL_PORT_MIN &&
+	    port_id < QEDI_LOCAL_PORT_MAX) {
+		if (qedi_alloc_id(&qedi->lcl_port_tbl, port_id))
+			port_id = 0;
+	} else {
+		port_id = 0;
+	}
+
+	if (!port_id) {
+		port_id = qedi_alloc_new_id(&qedi->lcl_port_tbl);
+		if (port_id == QEDI_LOCAL_PORT_INVALID) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Failed to allocate port id for iscsi_cid=0x%x\n",
+				 iscsi_cid);
+			ret = -ENOMEM;
+			goto set_path_exit;
+		}
+	}
+
+	qedi_ep->src_port = port_id;
+
+	if (qedi_ep->ip_type == TCP_IPV4) {
+		memcpy(&qedi_ep->src_addr[0], &path_data->src.v4_addr,
+		       sizeof(struct in_addr));
+		memcpy(&qedi->src_ip[0], &path_data->src.v4_addr,
+		       sizeof(struct in_addr));
+		qedi->ip_type = TCP_IPV4;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "src addr:port=%pI4:%u, dst addr:port=%pI4:%u\n",
+			  qedi_ep->src_addr, qedi_ep->src_port,
+			  qedi_ep->dst_addr, qedi_ep->dst_port);
+	} else {
+		memcpy(&qedi_ep->src_addr[0], &path_data->src.v6_addr,
+		       sizeof(struct in6_addr));
+		memcpy(&qedi->src_ip[0], &path_data->src.v6_addr,
+		       sizeof(struct in6_addr));
+		qedi->ip_type = TCP_IPV6;
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "src addr:port=%pI6:%u, dst addr:port=%pI6:%u\n",
+			  qedi_ep->src_addr, qedi_ep->src_port,
+			  qedi_ep->dst_addr, qedi_ep->dst_port);
+	}
+
+	INIT_WORK(&qedi_ep->offload_work, qedi_offload_work);
+	queue_work(qedi->offload_thread, &qedi_ep->offload_work);
+
+	ret = 0;
+
+set_path_exit:
+	return ret;
+}
+
+static umode_t qedi_attr_is_visible(int param_type, int param)
+{
+	switch (param_type) {
+	case ISCSI_HOST_PARAM:
+		switch (param) {
+		case ISCSI_HOST_PARAM_NETDEV_NAME:
+		case ISCSI_HOST_PARAM_HWADDRESS:
+		case ISCSI_HOST_PARAM_IPADDRESS:
+			return 0444;
+		default:
+			return 0;
+		}
+	case ISCSI_PARAM:
+		switch (param) {
+		case ISCSI_PARAM_MAX_RECV_DLENGTH:
+		case ISCSI_PARAM_MAX_XMIT_DLENGTH:
+		case ISCSI_PARAM_HDRDGST_EN:
+		case ISCSI_PARAM_DATADGST_EN:
+		case ISCSI_PARAM_CONN_ADDRESS:
+		case ISCSI_PARAM_CONN_PORT:
+		case ISCSI_PARAM_EXP_STATSN:
+		case ISCSI_PARAM_PERSISTENT_ADDRESS:
+		case ISCSI_PARAM_PERSISTENT_PORT:
+		case ISCSI_PARAM_PING_TMO:
+		case ISCSI_PARAM_RECV_TMO:
+		case ISCSI_PARAM_INITIAL_R2T_EN:
+		case ISCSI_PARAM_MAX_R2T:
+		case ISCSI_PARAM_IMM_DATA_EN:
+		case ISCSI_PARAM_FIRST_BURST:
+		case ISCSI_PARAM_MAX_BURST:
+		case ISCSI_PARAM_PDU_INORDER_EN:
+		case ISCSI_PARAM_DATASEQ_INORDER_EN:
+		case ISCSI_PARAM_ERL:
+		case ISCSI_PARAM_TARGET_NAME:
+		case ISCSI_PARAM_TPGT:
+		case ISCSI_PARAM_USERNAME:
+		case ISCSI_PARAM_PASSWORD:
+		case ISCSI_PARAM_USERNAME_IN:
+		case ISCSI_PARAM_PASSWORD_IN:
+		case ISCSI_PARAM_FAST_ABORT:
+		case ISCSI_PARAM_ABORT_TMO:
+		case ISCSI_PARAM_LU_RESET_TMO:
+		case ISCSI_PARAM_TGT_RESET_TMO:
+		case ISCSI_PARAM_IFACE_NAME:
+		case ISCSI_PARAM_INITIATOR_NAME:
+		case ISCSI_PARAM_BOOT_ROOT:
+		case ISCSI_PARAM_BOOT_NIC:
+		case ISCSI_PARAM_BOOT_TARGET:
+			return 0444;
+		default:
+			return 0;
+		}
+	}
+
+	return 0;
+}
+
+static void qedi_cleanup_task(struct iscsi_task *task)
+{
+	if (!task->sc || task->state == ISCSI_TASK_PENDING) {
+		QEDI_INFO(NULL, QEDI_LOG_IO, "Returning ref_cnt=%d\n",
+			  atomic_read(&task->refcount));
+		return;
+	}
+
+	qedi_iscsi_unmap_sg_list(task->dd_data);
+}
+
+struct iscsi_transport qedi_iscsi_transport = {
+	.owner = THIS_MODULE,
+	.name = QEDI_MODULE_NAME,
+	.caps = CAP_RECOVERY_L0 | CAP_HDRDGST | CAP_MULTI_R2T | CAP_DATADGST |
+		CAP_DATA_PATH_OFFLOAD | CAP_TEXT_NEGO,
+	.create_session = qedi_session_create,
+	.destroy_session = qedi_session_destroy,
+	.create_conn = qedi_conn_create,
+	.bind_conn = qedi_conn_bind,
+	.start_conn = qedi_conn_start,
+	.stop_conn = iscsi_conn_stop,
+	.destroy_conn = qedi_conn_destroy,
+	.set_param = iscsi_set_param,
+	.get_ep_param = qedi_ep_get_param,
+	.get_conn_param = iscsi_conn_get_param,
+	.get_session_param = iscsi_session_get_param,
+	.get_host_param = qedi_host_get_param,
+	.send_pdu = iscsi_conn_send_pdu,
+	.get_stats = qedi_conn_get_stats,
+	.xmit_task = qedi_task_xmit,
+	.cleanup_task = qedi_cleanup_task,
+	.session_recovery_timedout = iscsi_session_recovery_timedout,
+	.ep_connect = qedi_ep_connect,
+	.ep_poll = qedi_ep_poll,
+	.ep_disconnect = qedi_ep_disconnect,
+	.set_path = qedi_set_path,
+	.attr_is_visible = qedi_attr_is_visible,
+};
+
+void qedi_start_conn_recovery(struct qedi_ctx *qedi,
+			      struct qedi_conn *qedi_conn)
+{
+	struct iscsi_cls_session *cls_sess;
+	struct iscsi_cls_conn *cls_conn;
+	struct iscsi_conn *conn;
+
+	cls_conn = qedi_conn->cls_conn;
+	conn = cls_conn->dd_data;
+	cls_sess = iscsi_conn_to_session(cls_conn);
+
+	if (iscsi_is_session_online(cls_sess)) {
+		qedi_conn->abrt_conn = 1;
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Failing connection, state=0x%x, cid=0x%x\n",
+			 conn->session->state, qedi_conn->iscsi_conn_id);
+		iscsi_conn_failure(qedi_conn->cls_conn->dd_data,
+				   ISCSI_ERR_CONN_FAILED);
+	}
+}
+
+static const struct {
+	enum iscsi_error_types error_code;
+	char *err_string;
+} qedi_iscsi_error[] = {
+	{ ISCSI_STATUS_NONE,
+	  "tcp_error none"
+	},
+	{ ISCSI_CONN_ERROR_TASK_CID_MISMATCH,
+	  "task cid mismatch"
+	},
+	{ ISCSI_CONN_ERROR_TASK_NOT_VALID,
+	  "invalid task"
+	},
+	{ ISCSI_CONN_ERROR_RQ_RING_IS_FULL,
+	  "rq ring full"
+	},
+	{ ISCSI_CONN_ERROR_CMDQ_RING_IS_FULL,
+	  "cmdq ring full"
+	},
+	{ ISCSI_CONN_ERROR_HQE_CACHING_FAILED,
+	  "sge caching failed"
+	},
+	{ ISCSI_CONN_ERROR_HEADER_DIGEST_ERROR,
+	  "hdr digest error"
+	},
+	{ ISCSI_CONN_ERROR_LOCAL_COMPLETION_ERROR,
+	  "local cmpl error"
+	},
+	{ ISCSI_CONN_ERROR_DATA_OVERRUN,
+	  "invalid task"
+	},
+	{ ISCSI_CONN_ERROR_OUT_OF_SGES_ERROR,
+	  "out of sge error"
+	},
+	{ ISCSI_CONN_ERROR_TCP_SEG_PROC_IP_OPTIONS_ERROR,
+	  "tcp seg ip options error"
+	},
+	{ ISCSI_CONN_ERROR_TCP_IP_FRAGMENT_ERROR,
+	  "tcp ip fragment error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_AHS_LEN,
+	  "AHS len protocol error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_ITT_OUT_OF_RANGE,
+	  "itt out of range error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SEG_LEN_EXCEEDS_PDU_SIZE,
+	  "data seg more than pdu size"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_OPCODE,
+	  "invalid opcode"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_OPCODE_BEFORE_UPDATE,
+	  "invalid opcode before update"
+	},
+	{ ISCSI_CONN_ERROR_UNVALID_NOPIN_DSL,
+	  "unexpected opcode"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_CARRIES_NO_DATA,
+	  "r2t carries no data"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SN,
+	  "data sn error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_IN_TTT,
+	  "data TTT error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_TTT,
+	  "r2t TTT error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_BUFFER_OFFSET,
+	  "buffer offset error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_BUFFER_OFFSET_OOO,
+	  "buffer offset ooo"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_SN,
+	  "data seg len 0"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_0,
+	  "data xer len error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_1,
+	  "data xer len1 error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_2,
+	  "data xer len2 error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_LUN,
+	  "protocol lun error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_F_BIT_ZERO,
+	  "f bit zero error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_EXP_STAT_SN,
+	  "exp stat sn error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DSL_NOT_ZERO,
+	  "dsl not zero error"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_DSL,
+	  "invalid dsl"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SEG_LEN_TOO_BIG,
+	  "data seg len too big"
+	},
+	{ ISCSI_CONN_ERROR_PROTOCOL_ERR_OUTSTANDING_R2T_COUNT,
+	  "outstanding r2t count error"
+	},
+	{ ISCSI_CONN_ERROR_SENSE_DATA_LENGTH,
+	  "sense datalen error"
+	},
+};
+
+char *qedi_get_iscsi_error(enum iscsi_error_types err_code)
+{
+	int i;
+	char *msg = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(qedi_iscsi_error); i++) {
+		if (qedi_iscsi_error[i].error_code == err_code) {
+			msg = qedi_iscsi_error[i].err_string;
+			break;
+		}
+	}
+	return msg;
+}
+
+void qedi_process_iscsi_error(struct qedi_endpoint *ep, struct async_data *data)
+{
+	struct qedi_conn *qedi_conn;
+	struct qedi_ctx *qedi;
+	char warn_notice[] = "iscsi_warning";
+	char error_notice[] = "iscsi_error";
+	char unknown_msg[] = "Unknown error";
+	char *message;
+	int need_recovery = 0;
+	u32 err_mask = 0;
+	char *msg;
+
+	if (!ep)
+		return;
+
+	qedi_conn = ep->conn;
+	if (!qedi_conn)
+		return;
+
+	qedi = ep->qedi;
+
+	QEDI_ERR(&qedi->dbg_ctx, "async event iscsi error:0x%x\n",
+		 data->error_code);
+
+	if (err_mask) {
+		need_recovery = 0;
+		message = warn_notice;
+	} else {
+		need_recovery = 1;
+		message = error_notice;
+	}
+
+	msg = qedi_get_iscsi_error(data->error_code);
+	if (!msg) {
+		need_recovery = 0;
+		msg = unknown_msg;
+	}
+
+	iscsi_conn_printk(KERN_ALERT,
+			  qedi_conn->cls_conn->dd_data,
+			  "qedi: %s - %s\n", message, msg);
+
+	if (need_recovery)
+		qedi_start_conn_recovery(qedi_conn->qedi, qedi_conn);
+}
+
+void qedi_process_tcp_error(struct qedi_endpoint *ep, struct async_data *data)
+{
+	struct qedi_conn *qedi_conn;
+
+	if (!ep)
+		return;
+
+	qedi_conn = ep->conn;
+	if (!qedi_conn)
+		return;
+
+	QEDI_ERR(&ep->qedi->dbg_ctx, "async event TCP error:0x%x\n",
+		 data->error_code);
+
+	qedi_start_conn_recovery(qedi_conn->qedi, qedi_conn);
+}
diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h
new file mode 100644
index 0000000..d3c06bb
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_iscsi.h
@@ -0,0 +1,232 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#ifndef _QEDI_ISCSI_H_
+#define _QEDI_ISCSI_H_
+
+#include <linux/socket.h>
+#include <linux/completion.h>
+#include "qedi.h"
+
+#define ISCSI_MAX_SESS_PER_HBA	4096
+
+#define DEF_KA_TIMEOUT		7200000
+#define DEF_KA_INTERVAL		10000
+#define DEF_KA_MAX_PROBE_COUNT	10
+#define DEF_TOS			0
+#define DEF_TTL			0xfe
+#define DEF_SND_SEQ_SCALE	0
+#define DEF_RCV_BUF		0xffff
+#define DEF_SND_BUF		0xffff
+#define DEF_SEED		0
+#define DEF_MAX_RT_TIME		8000
+#define DEF_MAX_DA_COUNT        2
+#define DEF_SWS_TIMER		1000
+#define DEF_MAX_CWND		2
+#define DEF_PATH_MTU		1500
+#define DEF_MSS			1460
+#define DEF_LL2_MTU		1560
+#define JUMBO_MTU		9000
+
+#define MIN_MTU         576 /* rfc 793 */
+#define IPV4_HDR_LEN    20
+#define IPV6_HDR_LEN    40
+#define TCP_HDR_LEN     20
+#define TCP_OPTION_LEN  12
+#define VLAN_LEN         4
+
+enum {
+	EP_STATE_IDLE                   = 0x0,
+	EP_STATE_ACQRCONN_START         = 0x1,
+	EP_STATE_ACQRCONN_COMPL         = 0x2,
+	EP_STATE_OFLDCONN_START         = 0x4,
+	EP_STATE_OFLDCONN_COMPL         = 0x8,
+	EP_STATE_DISCONN_START          = 0x10,
+	EP_STATE_DISCONN_COMPL          = 0x20,
+	EP_STATE_CLEANUP_START          = 0x40,
+	EP_STATE_CLEANUP_CMPL           = 0x80,
+	EP_STATE_TCP_FIN_RCVD           = 0x100,
+	EP_STATE_TCP_RST_RCVD           = 0x200,
+	EP_STATE_LOGOUT_SENT            = 0x400,
+	EP_STATE_LOGOUT_RESP_RCVD       = 0x800,
+	EP_STATE_CLEANUP_FAILED         = 0x1000,
+	EP_STATE_OFLDCONN_FAILED        = 0x2000,
+	EP_STATE_CONNECT_FAILED         = 0x4000,
+	EP_STATE_DISCONN_TIMEDOUT       = 0x8000,
+};
+
+struct qedi_conn;
+
+struct qedi_endpoint {
+	struct qedi_ctx *qedi;
+	u32 dst_addr[4];
+	u32 src_addr[4];
+	u16 src_port;
+	u16 dst_port;
+	u16 vlan_id;
+	u16 pmtu;
+	u8 src_mac[ETH_ALEN];
+	u8 dst_mac[ETH_ALEN];
+	u8 ip_type;
+	int state;
+	wait_queue_head_t ofld_wait;
+	wait_queue_head_t tcp_ofld_wait;
+	u32 iscsi_cid;
+	/* identifier of the connection from qed */
+	u32 handle;
+	u32 fw_cid;
+	void __iomem *p_doorbell;
+
+	/* Send queue management */
+	struct iscsi_wqe *sq;
+	dma_addr_t sq_dma;
+
+	u16 sq_prod_idx;
+	u16 fw_sq_prod_idx;
+	u16 sq_con_idx;
+	u32 sq_mem_size;
+
+	void *sq_pbl;
+	dma_addr_t sq_pbl_dma;
+	u32 sq_pbl_size;
+	struct qedi_conn *conn;
+	struct work_struct offload_work;
+};
+
+#define QEDI_SQ_WQES_MIN	16
+
+struct qedi_io_bdt {
+	struct iscsi_sge *sge_tbl;
+	dma_addr_t sge_tbl_dma;
+	u16 sge_valid;
+};
+
+/**
+ * struct generic_pdu_resc - login pdu resource structure
+ *
+ * @req_buf:            driver buffer used to stage payload associated with
+ *                      the login request
+ * @req_dma_addr:       dma address for iscsi login request payload buffer
+ * @req_buf_size:       actual login request payload length
+ * @req_wr_ptr:         pointer into login request buffer when next data is
+ *                      to be written
+ * @resp_hdr:           iscsi header where iscsi login response header is to
+ *                      be recreated
+ * @resp_buf:           buffer to stage login response payload
+ * @resp_dma_addr:      login response payload buffer dma address
+ * @resp_buf_size:      login response paylod length
+ * @resp_wr_ptr:        pointer into login response buffer when next data is
+ *                      to be written
+ * @req_bd_tbl:         iscsi login request payload BD table
+ * @req_bd_dma:         login request BD table dma address
+ * @resp_bd_tbl:        iscsi login response payload BD table
+ * @resp_bd_dma:        login request BD table dma address
+ *
+ * following structure defines buffer info for generic pdus such as iSCSI Login,
+ *      Logout and NOP
+ */
+struct generic_pdu_resc {
+	char *req_buf;
+	dma_addr_t req_dma_addr;
+	u32 req_buf_size;
+	char *req_wr_ptr;
+	struct iscsi_hdr resp_hdr;
+	char *resp_buf;
+	dma_addr_t resp_dma_addr;
+	u32 resp_buf_size;
+	char *resp_wr_ptr;
+	char *req_bd_tbl;
+	dma_addr_t req_bd_dma;
+	char *resp_bd_tbl;
+	dma_addr_t resp_bd_dma;
+};
+
+struct qedi_conn {
+	struct iscsi_cls_conn *cls_conn;
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *ep;
+	struct list_head active_cmd_list;
+	spinlock_t list_lock;		/* internal conn lock */
+	u32 active_cmd_count;
+	u32 cmd_cleanup_req;
+	u32 cmd_cleanup_cmpl;
+
+	u32 iscsi_conn_id;
+	int itt;
+	int abrt_conn;
+#define QEDI_CID_RESERVED	0x5AFF
+	u32 fw_cid;
+	/*
+	 * Buffer for login negotiation process
+	 */
+	struct generic_pdu_resc gen_pdu;
+
+	struct list_head tmf_work_list;
+	wait_queue_head_t wait_queue;
+	spinlock_t tmf_work_lock;	/* tmf work lock */
+	unsigned long flags;
+#define QEDI_CONN_FW_CLEANUP	1
+};
+
+struct qedi_cmd {
+	struct list_head io_cmd;
+	bool io_cmd_in_list;
+	struct iscsi_hdr hdr;
+	struct qedi_conn *conn;
+	struct scsi_cmnd *scsi_cmd;
+	struct scatterlist *sg;
+	struct qedi_io_bdt io_tbl;
+	struct iscsi_task_context request;
+	unsigned char *sense_buffer;
+	dma_addr_t sense_buffer_dma;
+	u16 task_id;
+
+	/* field populated for tmf work queue */
+	struct iscsi_task *task;
+	struct work_struct tmf_work;
+	int state;
+#define CLEANUP_WAIT	1
+#define CLEANUP_RECV	2
+#define CLEANUP_WAIT_FAILED	3
+#define CLEANUP_NOT_REQUIRED	4
+#define LUN_RESET_RESPONSE_RECEIVED	5
+#define RESPONSE_RECEIVED	6
+
+	int type;
+#define TYPEIO		1
+#define TYPERESET	2
+
+	struct qedi_work_map *list_tmf_work;
+	/* slowpath management */
+	bool use_slowpath;
+
+	struct iscsi_tm_rsp *tmf_resp_buf;
+	struct qedi_work cqe_work;
+};
+
+struct qedi_work_map {
+	struct list_head list;
+	struct qedi_cmd *qedi_cmd;
+	int rtid;
+
+	int state;
+#define QEDI_WORK_QUEUED	1
+#define QEDI_WORK_SCHEDULED	2
+#define QEDI_WORK_EXIT		3
+
+	struct work_struct *ptr_tmf_work;
+};
+
+#define qedi_set_itt(task_id, itt) ((u32)(((task_id) & 0xffff) | ((itt) << 16)))
+#define qedi_get_itt(cqe) (cqe.iscsi_hdr.cmd.itt >> 16)
+
+#define QEDI_OFLD_WAIT_STATE(q) ((q)->state == EP_STATE_OFLDCONN_FAILED || \
+				(q)->state == EP_STATE_OFLDCONN_COMPL)
+
+#endif /* _QEDI_ISCSI_H_ */
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
new file mode 100644
index 0000000..5eda21d
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -0,0 +1,2095 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/if_arp.h>
+#include <scsi/iscsi_if.h>
+#include <linux/inet.h>
+#include <net/arp.h>
+#include <linux/list.h>
+#include <linux/kthread.h>
+#include <linux/mm.h>
+#include <linux/if_vlan.h>
+#include <linux/cpu.h>
+
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi.h>
+
+#include "qedi.h"
+#include "qedi_gbl.h"
+#include "qedi_iscsi.h"
+
+static uint qedi_fw_debug;
+module_param(qedi_fw_debug, uint, 0644);
+MODULE_PARM_DESC(qedi_fw_debug, " Firmware debug level 0(default) to 3");
+
+uint qedi_dbg_log = QEDI_LOG_WARN | QEDI_LOG_SCSI_TM;
+module_param(qedi_dbg_log, uint, 0644);
+MODULE_PARM_DESC(qedi_dbg_log, " Default debug level");
+
+uint qedi_io_tracing;
+module_param(qedi_io_tracing, uint, 0644);
+MODULE_PARM_DESC(qedi_io_tracing,
+		 " Enable logging of SCSI requests/completions into trace buffer. (default off).");
+
+const struct qed_iscsi_ops *qedi_ops;
+static struct scsi_transport_template *qedi_scsi_transport;
+static struct pci_driver qedi_pci_driver;
+static DEFINE_PER_CPU(struct qedi_percpu_s, qedi_percpu);
+static LIST_HEAD(qedi_udev_list);
+/* Static function declaration */
+static int qedi_alloc_global_queues(struct qedi_ctx *qedi);
+static void qedi_free_global_queues(struct qedi_ctx *qedi);
+static struct qedi_cmd *qedi_get_cmd_from_tid(struct qedi_ctx *qedi, u32 tid);
+static void qedi_reset_uio_rings(struct qedi_uio_dev *udev);
+static void qedi_ll2_free_skbs(struct qedi_ctx *qedi);
+
+static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle)
+{
+	struct qedi_ctx *qedi;
+	struct qedi_endpoint *qedi_ep;
+	struct async_data *data;
+	int rval = 0;
+
+	if (!context || !fw_handle) {
+		QEDI_ERR(NULL, "Recv event with ctx NULL\n");
+		return -EINVAL;
+	}
+
+	qedi = (struct qedi_ctx *)context;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "Recv Event %d fw_handle %p\n", fw_event_code, fw_handle);
+
+	data = (struct async_data *)fw_handle;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "cid=0x%x tid=0x%x err-code=0x%x fw-dbg-param=0x%x\n",
+		   data->cid, data->itid, data->error_code,
+		   data->fw_debug_param);
+
+	qedi_ep = qedi->ep_tbl[data->cid];
+
+	if (!qedi_ep) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Cannot process event, ep already disconnected, cid=0x%x\n",
+			   data->cid);
+		WARN_ON(1);
+		return -ENODEV;
+	}
+
+	switch (fw_event_code) {
+	case ISCSI_EVENT_TYPE_ASYN_CONNECT_COMPLETE:
+		if (qedi_ep->state == EP_STATE_OFLDCONN_START)
+			qedi_ep->state = EP_STATE_OFLDCONN_COMPL;
+
+		wake_up_interruptible(&qedi_ep->tcp_ofld_wait);
+		break;
+	case ISCSI_EVENT_TYPE_ASYN_TERMINATE_DONE:
+		qedi_ep->state = EP_STATE_DISCONN_COMPL;
+		wake_up_interruptible(&qedi_ep->tcp_ofld_wait);
+		break;
+	case ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR:
+		qedi_process_iscsi_error(qedi_ep, data);
+		break;
+	case ISCSI_EVENT_TYPE_ASYN_ABORT_RCVD:
+	case ISCSI_EVENT_TYPE_ASYN_SYN_RCVD:
+	case ISCSI_EVENT_TYPE_ASYN_MAX_RT_TIME:
+	case ISCSI_EVENT_TYPE_ASYN_MAX_RT_CNT:
+	case ISCSI_EVENT_TYPE_ASYN_MAX_KA_PROBES_CNT:
+	case ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2:
+	case ISCSI_EVENT_TYPE_TCP_CONN_ERROR:
+		qedi_process_tcp_error(qedi_ep, data);
+		break;
+	default:
+		QEDI_ERR(&qedi->dbg_ctx, "Recv Unknown Event %u\n",
+			 fw_event_code);
+	}
+
+	return rval;
+}
+
+static int qedi_uio_open(struct uio_info *uinfo, struct inode *inode)
+{
+	struct qedi_uio_dev *udev = uinfo->priv;
+	struct qedi_ctx *qedi = udev->qedi;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (udev->uio_dev != -1)
+		return -EBUSY;
+
+	rtnl_lock();
+	udev->uio_dev = iminor(inode);
+	qedi_reset_uio_rings(udev);
+	set_bit(UIO_DEV_OPENED, &qedi->flags);
+	rtnl_unlock();
+
+	return 0;
+}
+
+static int qedi_uio_close(struct uio_info *uinfo, struct inode *inode)
+{
+	struct qedi_uio_dev *udev = uinfo->priv;
+	struct qedi_ctx *qedi = udev->qedi;
+
+	udev->uio_dev = -1;
+	clear_bit(UIO_DEV_OPENED, &qedi->flags);
+	qedi_ll2_free_skbs(qedi);
+	return 0;
+}
+
+static void __qedi_free_uio_rings(struct qedi_uio_dev *udev)
+{
+	if (udev->ll2_ring) {
+		free_page((unsigned long)udev->ll2_ring);
+		udev->ll2_ring = NULL;
+	}
+
+	if (udev->ll2_buf) {
+		free_pages((unsigned long)udev->ll2_buf, 2);
+		udev->ll2_buf = NULL;
+	}
+}
+
+static void __qedi_free_uio(struct qedi_uio_dev *udev)
+{
+	uio_unregister_device(&udev->qedi_uinfo);
+
+	__qedi_free_uio_rings(udev);
+
+	pci_dev_put(udev->pdev);
+	kfree(udev->uctrl);
+	kfree(udev);
+}
+
+static void qedi_free_uio(struct qedi_uio_dev *udev)
+{
+	if (!udev)
+		return;
+
+	list_del_init(&udev->list);
+	__qedi_free_uio(udev);
+}
+
+static void qedi_reset_uio_rings(struct qedi_uio_dev *udev)
+{
+	struct qedi_ctx *qedi = NULL;
+	struct qedi_uio_ctrl *uctrl = NULL;
+
+	qedi = udev->qedi;
+	uctrl = udev->uctrl;
+
+	spin_lock_bh(&qedi->ll2_lock);
+	uctrl->host_rx_cons = 0;
+	uctrl->hw_rx_prod = 0;
+	uctrl->hw_rx_bd_prod = 0;
+	uctrl->host_rx_bd_cons = 0;
+
+	memset(udev->ll2_ring, 0, udev->ll2_ring_size);
+	memset(udev->ll2_buf, 0, udev->ll2_buf_size);
+	spin_unlock_bh(&qedi->ll2_lock);
+}
+
+static int __qedi_alloc_uio_rings(struct qedi_uio_dev *udev)
+{
+	int rc = 0;
+
+	if (udev->ll2_ring || udev->ll2_buf)
+		return rc;
+
+	/* Allocating memory for LL2 ring  */
+	udev->ll2_ring_size = QEDI_PAGE_SIZE;
+	udev->ll2_ring = (void *)get_zeroed_page(GFP_KERNEL | __GFP_COMP);
+	if (!udev->ll2_ring) {
+		rc = -ENOMEM;
+		goto exit_alloc_ring;
+	}
+
+	/* Allocating memory for Tx/Rx pkt buffer */
+	udev->ll2_buf_size = TX_RX_RING * LL2_SINGLE_BUF_SIZE;
+	udev->ll2_buf_size = QEDI_PAGE_ALIGN(udev->ll2_buf_size);
+	udev->ll2_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_COMP |
+						 __GFP_ZERO, 2);
+	if (!udev->ll2_buf) {
+		rc = -ENOMEM;
+		goto exit_alloc_buf;
+	}
+	return rc;
+
+exit_alloc_buf:
+	free_page((unsigned long)udev->ll2_ring);
+	udev->ll2_ring = NULL;
+exit_alloc_ring:
+	return rc;
+}
+
+static int qedi_alloc_uio_rings(struct qedi_ctx *qedi)
+{
+	struct qedi_uio_dev *udev = NULL;
+	struct qedi_uio_ctrl *uctrl = NULL;
+	int rc = 0;
+
+	list_for_each_entry(udev, &qedi_udev_list, list) {
+		if (udev->pdev == qedi->pdev) {
+			udev->qedi = qedi;
+			if (__qedi_alloc_uio_rings(udev)) {
+				udev->qedi = NULL;
+				return -ENOMEM;
+			}
+			qedi->udev = udev;
+			return 0;
+		}
+	}
+
+	udev = kzalloc(sizeof(*udev), GFP_KERNEL);
+	if (!udev) {
+		rc = -ENOMEM;
+		goto err_udev;
+	}
+
+	uctrl = kzalloc(sizeof(*uctrl), GFP_KERNEL);
+	if (!uctrl) {
+		rc = -ENOMEM;
+		goto err_uctrl;
+	}
+
+	udev->uio_dev = -1;
+
+	udev->qedi = qedi;
+	udev->pdev = qedi->pdev;
+	udev->uctrl = uctrl;
+
+	rc = __qedi_alloc_uio_rings(udev);
+	if (rc)
+		goto err_uio_rings;
+
+	list_add(&udev->list, &qedi_udev_list);
+
+	pci_dev_get(udev->pdev);
+	qedi->udev = udev;
+
+	udev->tx_pkt = udev->ll2_buf;
+	udev->rx_pkt = udev->ll2_buf + LL2_SINGLE_BUF_SIZE;
+	return 0;
+
+ err_uio_rings:
+	kfree(uctrl);
+ err_uctrl:
+	kfree(udev);
+ err_udev:
+	return -ENOMEM;
+}
+
+static int qedi_init_uio(struct qedi_ctx *qedi)
+{
+	struct qedi_uio_dev *udev = qedi->udev;
+	struct uio_info *uinfo;
+	int ret = 0;
+
+	if (!udev)
+		return -ENOMEM;
+
+	uinfo = &udev->qedi_uinfo;
+
+	uinfo->mem[0].addr = (unsigned long)udev->uctrl;
+	uinfo->mem[0].size = sizeof(struct qedi_uio_ctrl);
+	uinfo->mem[0].memtype = UIO_MEM_LOGICAL;
+
+	uinfo->mem[1].addr = (unsigned long)udev->ll2_ring;
+	uinfo->mem[1].size = udev->ll2_ring_size;
+	uinfo->mem[1].memtype = UIO_MEM_LOGICAL;
+
+	uinfo->mem[2].addr = (unsigned long)udev->ll2_buf;
+	uinfo->mem[2].size = udev->ll2_buf_size;
+	uinfo->mem[2].memtype = UIO_MEM_LOGICAL;
+
+	uinfo->name = "qedi_uio";
+	uinfo->version = QEDI_MODULE_VERSION;
+	uinfo->irq = UIO_IRQ_CUSTOM;
+
+	uinfo->open = qedi_uio_open;
+	uinfo->release = qedi_uio_close;
+
+	if (udev->uio_dev == -1) {
+		if (!uinfo->priv) {
+			uinfo->priv = udev;
+
+			ret = uio_register_device(&udev->pdev->dev, uinfo);
+			if (ret) {
+				QEDI_ERR(&qedi->dbg_ctx,
+					 "UIO registration failed\n");
+			}
+		}
+	}
+
+	return ret;
+}
+
+static int qedi_alloc_and_init_sb(struct qedi_ctx *qedi,
+				  struct qed_sb_info *sb_info, u16 sb_id)
+{
+	struct status_block *sb_virt;
+	dma_addr_t sb_phys;
+	int ret;
+
+	sb_virt = dma_alloc_coherent(&qedi->pdev->dev,
+				     sizeof(struct status_block), &sb_phys,
+				     GFP_KERNEL);
+	if (!sb_virt) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Status block allocation failed for id = %d.\n",
+			  sb_id);
+		return -ENOMEM;
+	}
+
+	ret = qedi_ops->common->sb_init(qedi->cdev, sb_info, sb_virt, sb_phys,
+				       sb_id, QED_SB_TYPE_STORAGE);
+	if (ret) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Status block initialization failed for id = %d.\n",
+			  sb_id);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void qedi_free_sb(struct qedi_ctx *qedi)
+{
+	struct qed_sb_info *sb_info;
+	int id;
+
+	for (id = 0; id < MIN_NUM_CPUS_MSIX(qedi); id++) {
+		sb_info = &qedi->sb_array[id];
+		if (sb_info->sb_virt)
+			dma_free_coherent(&qedi->pdev->dev,
+					  sizeof(*sb_info->sb_virt),
+					  (void *)sb_info->sb_virt,
+					  sb_info->sb_phys);
+	}
+}
+
+static void qedi_free_fp(struct qedi_ctx *qedi)
+{
+	kfree(qedi->fp_array);
+	kfree(qedi->sb_array);
+}
+
+static void qedi_destroy_fp(struct qedi_ctx *qedi)
+{
+	qedi_free_sb(qedi);
+	qedi_free_fp(qedi);
+}
+
+static int qedi_alloc_fp(struct qedi_ctx *qedi)
+{
+	int ret = 0;
+
+	qedi->fp_array = kcalloc(MIN_NUM_CPUS_MSIX(qedi),
+				 sizeof(struct qedi_fastpath), GFP_KERNEL);
+	if (!qedi->fp_array) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "fastpath fp array allocation failed.\n");
+		return -ENOMEM;
+	}
+
+	qedi->sb_array = kcalloc(MIN_NUM_CPUS_MSIX(qedi),
+				 sizeof(struct qed_sb_info), GFP_KERNEL);
+	if (!qedi->sb_array) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "fastpath sb array allocation failed.\n");
+		ret = -ENOMEM;
+		goto free_fp;
+	}
+
+	return ret;
+
+free_fp:
+	qedi_free_fp(qedi);
+	return ret;
+}
+
+static void qedi_int_fp(struct qedi_ctx *qedi)
+{
+	struct qedi_fastpath *fp;
+	int id;
+
+	memset(qedi->fp_array, 0, MIN_NUM_CPUS_MSIX(qedi) *
+	       sizeof(*qedi->fp_array));
+	memset(qedi->sb_array, 0, MIN_NUM_CPUS_MSIX(qedi) *
+	       sizeof(*qedi->sb_array));
+
+	for (id = 0; id < MIN_NUM_CPUS_MSIX(qedi); id++) {
+		fp = &qedi->fp_array[id];
+		fp->sb_info = &qedi->sb_array[id];
+		fp->sb_id = id;
+		fp->qedi = qedi;
+		snprintf(fp->name, sizeof(fp->name), "%s-fp-%d",
+			 "qedi", id);
+
+		/* fp_array[i] ---- irq cookie
+		 * So init data which is needed in int ctx
+		 */
+	}
+}
+
+static int qedi_prepare_fp(struct qedi_ctx *qedi)
+{
+	struct qedi_fastpath *fp;
+	int id, ret = 0;
+
+	ret = qedi_alloc_fp(qedi);
+	if (ret)
+		goto err;
+
+	qedi_int_fp(qedi);
+
+	for (id = 0; id < MIN_NUM_CPUS_MSIX(qedi); id++) {
+		fp = &qedi->fp_array[id];
+		ret = qedi_alloc_and_init_sb(qedi, fp->sb_info, fp->sb_id);
+		if (ret) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "SB allocation and initialization failed.\n");
+			ret = -EIO;
+			goto err_init;
+		}
+	}
+
+	return 0;
+
+err_init:
+	qedi_free_sb(qedi);
+	qedi_free_fp(qedi);
+err:
+	return ret;
+}
+
+static int qedi_setup_cid_que(struct qedi_ctx *qedi)
+{
+	int i;
+
+	qedi->cid_que.cid_que_base = kmalloc_array(qedi->max_active_conns,
+						   sizeof(u32), GFP_KERNEL);
+	if (!qedi->cid_que.cid_que_base)
+		return -ENOMEM;
+
+	qedi->cid_que.conn_cid_tbl = kmalloc_array(qedi->max_active_conns,
+						   sizeof(struct qedi_conn *),
+						   GFP_KERNEL);
+	if (!qedi->cid_que.conn_cid_tbl) {
+		kfree(qedi->cid_que.cid_que_base);
+		qedi->cid_que.cid_que_base = NULL;
+		return -ENOMEM;
+	}
+
+	qedi->cid_que.cid_que = (u32 *)qedi->cid_que.cid_que_base;
+	qedi->cid_que.cid_q_prod_idx = 0;
+	qedi->cid_que.cid_q_cons_idx = 0;
+	qedi->cid_que.cid_q_max_idx = qedi->max_active_conns;
+	qedi->cid_que.cid_free_cnt = qedi->max_active_conns;
+
+	for (i = 0; i < qedi->max_active_conns; i++) {
+		qedi->cid_que.cid_que[i] = i;
+		qedi->cid_que.conn_cid_tbl[i] = NULL;
+	}
+
+	return 0;
+}
+
+static void qedi_release_cid_que(struct qedi_ctx *qedi)
+{
+	kfree(qedi->cid_que.cid_que_base);
+	qedi->cid_que.cid_que_base = NULL;
+
+	kfree(qedi->cid_que.conn_cid_tbl);
+	qedi->cid_que.conn_cid_tbl = NULL;
+}
+
+static int qedi_init_id_tbl(struct qedi_portid_tbl *id_tbl, u16 size,
+			    u16 start_id, u16 next)
+{
+	id_tbl->start = start_id;
+	id_tbl->max = size;
+	id_tbl->next = next;
+	spin_lock_init(&id_tbl->lock);
+	id_tbl->table = kzalloc(DIV_ROUND_UP(size, 32) * 4, GFP_KERNEL);
+	if (!id_tbl->table)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void qedi_free_id_tbl(struct qedi_portid_tbl *id_tbl)
+{
+	kfree(id_tbl->table);
+	id_tbl->table = NULL;
+}
+
+int qedi_alloc_id(struct qedi_portid_tbl *id_tbl, u16 id)
+{
+	int ret = -1;
+
+	id -= id_tbl->start;
+	if (id >= id_tbl->max)
+		return ret;
+
+	spin_lock(&id_tbl->lock);
+	if (!test_bit(id, id_tbl->table)) {
+		set_bit(id, id_tbl->table);
+		ret = 0;
+	}
+	spin_unlock(&id_tbl->lock);
+	return ret;
+}
+
+u16 qedi_alloc_new_id(struct qedi_portid_tbl *id_tbl)
+{
+	u16 id;
+
+	spin_lock(&id_tbl->lock);
+	id = find_next_zero_bit(id_tbl->table, id_tbl->max, id_tbl->next);
+	if (id >= id_tbl->max) {
+		id = QEDI_LOCAL_PORT_INVALID;
+		if (id_tbl->next != 0) {
+			id = find_first_zero_bit(id_tbl->table, id_tbl->next);
+			if (id >= id_tbl->next)
+				id = QEDI_LOCAL_PORT_INVALID;
+		}
+	}
+
+	if (id < id_tbl->max) {
+		set_bit(id, id_tbl->table);
+		id_tbl->next = (id + 1) & (id_tbl->max - 1);
+		id += id_tbl->start;
+	}
+
+	spin_unlock(&id_tbl->lock);
+
+	return id;
+}
+
+void qedi_free_id(struct qedi_portid_tbl *id_tbl, u16 id)
+{
+	if (id == QEDI_LOCAL_PORT_INVALID)
+		return;
+
+	id -= id_tbl->start;
+	if (id >= id_tbl->max)
+		return;
+
+	clear_bit(id, id_tbl->table);
+}
+
+static void qedi_cm_free_mem(struct qedi_ctx *qedi)
+{
+	kfree(qedi->ep_tbl);
+	qedi->ep_tbl = NULL;
+	qedi_free_id_tbl(&qedi->lcl_port_tbl);
+}
+
+static int qedi_cm_alloc_mem(struct qedi_ctx *qedi)
+{
+	u16 port_id;
+
+	qedi->ep_tbl = kzalloc((qedi->max_active_conns *
+				sizeof(struct qedi_endpoint *)), GFP_KERNEL);
+	if (!qedi->ep_tbl)
+		return -ENOMEM;
+	port_id = prandom_u32() % QEDI_LOCAL_PORT_RANGE;
+	if (qedi_init_id_tbl(&qedi->lcl_port_tbl, QEDI_LOCAL_PORT_RANGE,
+			     QEDI_LOCAL_PORT_MIN, port_id)) {
+		qedi_cm_free_mem(qedi);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static struct qedi_ctx *qedi_host_alloc(struct pci_dev *pdev)
+{
+	struct Scsi_Host *shost;
+	struct qedi_ctx *qedi = NULL;
+
+	shost = iscsi_host_alloc(&qedi_host_template,
+				 sizeof(struct qedi_ctx), 0);
+	if (!shost) {
+		QEDI_ERR(NULL, "Could not allocate shost\n");
+		goto exit_setup_shost;
+	}
+
+	shost->max_id = QEDI_MAX_ISCSI_CONNS_PER_HBA;
+	shost->max_channel = 0;
+	shost->max_lun = ~0;
+	shost->max_cmd_len = 16;
+	shost->transportt = qedi_scsi_transport;
+
+	qedi = iscsi_host_priv(shost);
+	memset(qedi, 0, sizeof(*qedi));
+	qedi->shost = shost;
+	qedi->dbg_ctx.host_no = shost->host_no;
+	qedi->pdev = pdev;
+	qedi->dbg_ctx.pdev = pdev;
+	qedi->max_active_conns = ISCSI_MAX_SESS_PER_HBA;
+	qedi->max_sqes = QEDI_SQ_SIZE;
+
+	if (shost_use_blk_mq(shost))
+		shost->nr_hw_queues = MIN_NUM_CPUS_MSIX(qedi);
+
+	pci_set_drvdata(pdev, qedi);
+
+exit_setup_shost:
+	return qedi;
+}
+
+static int qedi_ll2_rx(void *cookie, struct sk_buff *skb, u32 arg1, u32 arg2)
+{
+	struct qedi_ctx *qedi = (struct qedi_ctx *)cookie;
+	struct qedi_uio_dev *udev;
+	struct qedi_uio_ctrl *uctrl;
+	struct skb_work_list *work;
+	u32 prod;
+
+	if (!qedi) {
+		QEDI_ERR(NULL, "qedi is NULL\n");
+		return -1;
+	}
+
+	if (!test_bit(UIO_DEV_OPENED, &qedi->flags)) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_UIO,
+			  "UIO DEV is not opened\n");
+		kfree_skb(skb);
+		return 0;
+	}
+
+	udev = qedi->udev;
+	uctrl = udev->uctrl;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Could not allocate work so dropping frame.\n");
+		kfree_skb(skb);
+		return 0;
+	}
+
+	INIT_LIST_HEAD(&work->list);
+	work->skb = skb;
+
+	if (skb_vlan_tag_present(skb))
+		work->vlan_id = skb_vlan_tag_get(skb);
+
+	if (work->vlan_id)
+		__vlan_insert_tag(work->skb, htons(ETH_P_8021Q), work->vlan_id);
+
+	spin_lock_bh(&qedi->ll2_lock);
+	list_add_tail(&work->list, &qedi->ll2_skb_list);
+
+	++uctrl->hw_rx_prod_cnt;
+	prod = (uctrl->hw_rx_prod + 1) % RX_RING;
+	if (prod != uctrl->host_rx_cons) {
+		uctrl->hw_rx_prod = prod;
+		spin_unlock_bh(&qedi->ll2_lock);
+		wake_up_process(qedi->ll2_recv_thread);
+		return 0;
+	}
+
+	spin_unlock_bh(&qedi->ll2_lock);
+	return 0;
+}
+
+/* map this skb to iscsiuio mmaped region */
+static int qedi_ll2_process_skb(struct qedi_ctx *qedi, struct sk_buff *skb,
+				u16 vlan_id)
+{
+	struct qedi_uio_dev *udev = NULL;
+	struct qedi_uio_ctrl *uctrl = NULL;
+	struct qedi_rx_bd rxbd;
+	struct qedi_rx_bd *p_rxbd;
+	u32 rx_bd_prod;
+	void *pkt;
+	int len = 0;
+
+	if (!qedi) {
+		QEDI_ERR(NULL, "qedi is NULL\n");
+		return -1;
+	}
+
+	udev = qedi->udev;
+	uctrl = udev->uctrl;
+	pkt = udev->rx_pkt + (uctrl->hw_rx_prod * LL2_SINGLE_BUF_SIZE);
+	len = min_t(u32, skb->len, (u32)LL2_SINGLE_BUF_SIZE);
+	memcpy(pkt, skb->data, len);
+
+	memset(&rxbd, 0, sizeof(rxbd));
+	rxbd.rx_pkt_index = uctrl->hw_rx_prod;
+	rxbd.rx_pkt_len = len;
+	rxbd.vlan_id = vlan_id;
+
+	uctrl->hw_rx_bd_prod = (uctrl->hw_rx_bd_prod + 1) % QEDI_NUM_RX_BD;
+	rx_bd_prod = uctrl->hw_rx_bd_prod;
+	p_rxbd = (struct qedi_rx_bd *)udev->ll2_ring;
+	p_rxbd += rx_bd_prod;
+
+	memcpy(p_rxbd, &rxbd, sizeof(rxbd));
+
+	/* notify the iscsiuio about new packet */
+	uio_event_notify(&udev->qedi_uinfo);
+
+	return 0;
+}
+
+static void qedi_ll2_free_skbs(struct qedi_ctx *qedi)
+{
+	struct skb_work_list *work, *work_tmp;
+
+	spin_lock_bh(&qedi->ll2_lock);
+	list_for_each_entry_safe(work, work_tmp, &qedi->ll2_skb_list, list) {
+		list_del(&work->list);
+		if (work->skb)
+			kfree_skb(work->skb);
+		kfree(work);
+	}
+	spin_unlock_bh(&qedi->ll2_lock);
+}
+
+static int qedi_ll2_recv_thread(void *arg)
+{
+	struct qedi_ctx *qedi = (struct qedi_ctx *)arg;
+	struct skb_work_list *work, *work_tmp;
+
+	set_user_nice(current, -20);
+
+	while (!kthread_should_stop()) {
+		spin_lock_bh(&qedi->ll2_lock);
+		list_for_each_entry_safe(work, work_tmp, &qedi->ll2_skb_list,
+					 list) {
+			list_del(&work->list);
+			qedi_ll2_process_skb(qedi, work->skb, work->vlan_id);
+			kfree_skb(work->skb);
+			kfree(work);
+		}
+		set_current_state(TASK_INTERRUPTIBLE);
+		spin_unlock_bh(&qedi->ll2_lock);
+		schedule();
+	}
+
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
+static int qedi_set_iscsi_pf_param(struct qedi_ctx *qedi)
+{
+	u8 num_sq_pages;
+	u32 log_page_size;
+	int rval = 0;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC, "Min number of MSIX %d\n",
+		  MIN_NUM_CPUS_MSIX(qedi));
+
+	num_sq_pages = (MAX_OUSTANDING_TASKS_PER_CON * 8) / PAGE_SIZE;
+
+	qedi->num_queues = MIN_NUM_CPUS_MSIX(qedi);
+
+	memset(&qedi->pf_params.iscsi_pf_params, 0,
+	       sizeof(qedi->pf_params.iscsi_pf_params));
+
+	qedi->p_cpuq = pci_alloc_consistent(qedi->pdev,
+			qedi->num_queues * sizeof(struct qedi_glbl_q_params),
+			&qedi->hw_p_cpuq);
+	if (!qedi->p_cpuq) {
+		QEDI_ERR(&qedi->dbg_ctx, "pci_alloc_consistent fail\n");
+		rval = -1;
+		goto err_alloc_mem;
+	}
+
+	rval = qedi_alloc_global_queues(qedi);
+	if (rval) {
+		QEDI_ERR(&qedi->dbg_ctx, "Global queue allocation failed.\n");
+		rval = -1;
+		goto err_alloc_mem;
+	}
+
+	qedi->pf_params.iscsi_pf_params.num_cons = QEDI_MAX_ISCSI_CONNS_PER_HBA;
+	qedi->pf_params.iscsi_pf_params.num_tasks = QEDI_MAX_ISCSI_TASK;
+	qedi->pf_params.iscsi_pf_params.half_way_close_timeout = 10;
+	qedi->pf_params.iscsi_pf_params.num_sq_pages_in_ring = num_sq_pages;
+	qedi->pf_params.iscsi_pf_params.num_r2tq_pages_in_ring = num_sq_pages;
+	qedi->pf_params.iscsi_pf_params.num_uhq_pages_in_ring = num_sq_pages;
+	qedi->pf_params.iscsi_pf_params.num_queues = qedi->num_queues;
+	qedi->pf_params.iscsi_pf_params.debug_mode = qedi_fw_debug;
+
+	for (log_page_size = 0 ; log_page_size < 32 ; log_page_size++) {
+		if ((1 << log_page_size) == PAGE_SIZE)
+			break;
+	}
+	qedi->pf_params.iscsi_pf_params.log_page_size = log_page_size;
+
+	qedi->pf_params.iscsi_pf_params.glbl_q_params_addr =
+							   (u64)qedi->hw_p_cpuq;
+
+	/* RQ BDQ initializations.
+	 * rq_num_entries: suggested value for Initiator is 16 (4KB RQ)
+	 * rqe_log_size: 8 for 256B RQE
+	 */
+	qedi->pf_params.iscsi_pf_params.rqe_log_size = 8;
+	/* BDQ address and size */
+	qedi->pf_params.iscsi_pf_params.bdq_pbl_base_addr[BDQ_ID_RQ] =
+							qedi->bdq_pbl_list_dma;
+	qedi->pf_params.iscsi_pf_params.bdq_pbl_num_entries[BDQ_ID_RQ] =
+						qedi->bdq_pbl_list_num_entries;
+	qedi->pf_params.iscsi_pf_params.rq_buffer_size = QEDI_BDQ_BUF_SIZE;
+
+	/* cq_num_entries: num_tasks + rq_num_entries */
+	qedi->pf_params.iscsi_pf_params.cq_num_entries = 2048;
+
+	qedi->pf_params.iscsi_pf_params.gl_rq_pi = QEDI_PROTO_CQ_PROD_IDX;
+	qedi->pf_params.iscsi_pf_params.gl_cmd_pi = 1;
+	qedi->pf_params.iscsi_pf_params.ooo_enable = 1;
+
+err_alloc_mem:
+	return rval;
+}
+
+/* Free DMA coherent memory for array of queue pointers we pass to qed */
+static void qedi_free_iscsi_pf_param(struct qedi_ctx *qedi)
+{
+	size_t size = 0;
+
+	if (qedi->p_cpuq) {
+		size = qedi->num_queues * sizeof(struct qedi_glbl_q_params);
+		pci_free_consistent(qedi->pdev, size, qedi->p_cpuq,
+				    qedi->hw_p_cpuq);
+	}
+
+	qedi_free_global_queues(qedi);
+
+	kfree(qedi->global_queues);
+}
+
+static void qedi_link_update(void *dev, struct qed_link_output *link)
+{
+	struct qedi_ctx *qedi = (struct qedi_ctx *)dev;
+
+	if (link->link_up) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Link Up event.\n");
+		atomic_set(&qedi->link_state, QEDI_LINK_UP);
+	} else {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+			  "Link Down event.\n");
+		atomic_set(&qedi->link_state, QEDI_LINK_DOWN);
+	}
+}
+
+static struct qed_iscsi_cb_ops qedi_cb_ops = {
+	{
+		.link_update =		qedi_link_update,
+	}
+};
+
+static int qedi_queue_cqe(struct qedi_ctx *qedi, union iscsi_cqe *cqe,
+			  u16 que_idx, struct qedi_percpu_s *p)
+{
+	struct qedi_work *qedi_work;
+	struct qedi_conn *q_conn;
+	struct iscsi_conn *conn;
+	struct qedi_cmd *qedi_cmd;
+	u32 iscsi_cid;
+	int rc = 0;
+
+	iscsi_cid  = cqe->cqe_common.conn_id;
+	q_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid];
+	if (!q_conn) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Session no longer exists for cid=0x%x!!\n",
+			  iscsi_cid);
+		return -1;
+	}
+	conn = q_conn->cls_conn->dd_data;
+
+	switch (cqe->cqe_common.cqe_type) {
+	case ISCSI_CQE_TYPE_SOLICITED:
+	case ISCSI_CQE_TYPE_SOLICITED_WITH_SENSE:
+		qedi_cmd = qedi_get_cmd_from_tid(qedi, cqe->cqe_solicited.itid);
+		if (!qedi_cmd) {
+			rc = -1;
+			break;
+		}
+		INIT_LIST_HEAD(&qedi_cmd->cqe_work.list);
+		qedi_cmd->cqe_work.qedi = qedi;
+		memcpy(&qedi_cmd->cqe_work.cqe, cqe, sizeof(union iscsi_cqe));
+		qedi_cmd->cqe_work.que_idx = que_idx;
+		qedi_cmd->cqe_work.is_solicited = true;
+		list_add_tail(&qedi_cmd->cqe_work.list, &p->work_list);
+		break;
+	case ISCSI_CQE_TYPE_UNSOLICITED:
+	case ISCSI_CQE_TYPE_DUMMY:
+	case ISCSI_CQE_TYPE_TASK_CLEANUP:
+		qedi_work = kzalloc(sizeof(*qedi_work), GFP_ATOMIC);
+		if (!qedi_work) {
+			rc = -1;
+			break;
+		}
+		INIT_LIST_HEAD(&qedi_work->list);
+		qedi_work->qedi = qedi;
+		memcpy(&qedi_work->cqe, cqe, sizeof(union iscsi_cqe));
+		qedi_work->que_idx = que_idx;
+		qedi_work->is_solicited = false;
+		list_add_tail(&qedi_work->list, &p->work_list);
+		break;
+	default:
+		rc = -1;
+		QEDI_ERR(&qedi->dbg_ctx, "FW Error cqe.\n");
+	}
+	return rc;
+}
+
+static bool qedi_process_completions(struct qedi_fastpath *fp)
+{
+	struct qedi_ctx *qedi = fp->qedi;
+	struct qed_sb_info *sb_info = fp->sb_info;
+	struct status_block *sb = sb_info->sb_virt;
+	struct qedi_percpu_s *p = NULL;
+	struct global_queue *que;
+	u16 prod_idx;
+	unsigned long flags;
+	union iscsi_cqe *cqe;
+	int cpu;
+	int ret;
+
+	/* Get the current firmware producer index */
+	prod_idx = sb->pi_array[QEDI_PROTO_CQ_PROD_IDX];
+
+	if (prod_idx >= QEDI_CQ_SIZE)
+		prod_idx = prod_idx % QEDI_CQ_SIZE;
+
+	que = qedi->global_queues[fp->sb_id];
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
+		  "Before: global queue=%p prod_idx=%d cons_idx=%d, sb_id=%d\n",
+		  que, prod_idx, que->cq_cons_idx, fp->sb_id);
+
+	qedi->intr_cpu = fp->sb_id;
+	cpu = smp_processor_id();
+	p = &per_cpu(qedi_percpu, cpu);
+
+	if (unlikely(!p->iothread))
+		WARN_ON(1);
+
+	spin_lock_irqsave(&p->p_work_lock, flags);
+	while (que->cq_cons_idx != prod_idx) {
+		cqe = &que->cq[que->cq_cons_idx];
+
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_IO,
+			  "cqe=%p prod_idx=%d cons_idx=%d.\n",
+			  cqe, prod_idx, que->cq_cons_idx);
+
+		ret = qedi_queue_cqe(qedi, cqe, fp->sb_id, p);
+		if (ret)
+			continue;
+
+		que->cq_cons_idx++;
+		if (que->cq_cons_idx == QEDI_CQ_SIZE)
+			que->cq_cons_idx = 0;
+	}
+	wake_up_process(p->iothread);
+	spin_unlock_irqrestore(&p->p_work_lock, flags);
+
+	return true;
+}
+
+static bool qedi_fp_has_work(struct qedi_fastpath *fp)
+{
+	struct qedi_ctx *qedi = fp->qedi;
+	struct global_queue *que;
+	struct qed_sb_info *sb_info = fp->sb_info;
+	struct status_block *sb = sb_info->sb_virt;
+	u16 prod_idx;
+
+	barrier();
+
+	/* Get the current firmware producer index */
+	prod_idx = sb->pi_array[QEDI_PROTO_CQ_PROD_IDX];
+
+	/* Get the pointer to the global CQ this completion is on */
+	que = qedi->global_queues[fp->sb_id];
+
+	/* prod idx wrap around uint16 */
+	if (prod_idx >= QEDI_CQ_SIZE)
+		prod_idx = prod_idx % QEDI_CQ_SIZE;
+
+	return (que->cq_cons_idx != prod_idx);
+}
+
+/* MSI-X fastpath handler code */
+static irqreturn_t qedi_msix_handler(int irq, void *dev_id)
+{
+	struct qedi_fastpath *fp = dev_id;
+	struct qedi_ctx *qedi = fp->qedi;
+	bool wake_io_thread = true;
+
+	qed_sb_ack(fp->sb_info, IGU_INT_DISABLE, 0);
+
+process_again:
+	wake_io_thread = qedi_process_completions(fp);
+	if (wake_io_thread) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+			  "process already running\n");
+	}
+
+	if (qedi_fp_has_work(fp) == 0)
+		qed_sb_update_sb_idx(fp->sb_info);
+
+	/* Check for more work */
+	rmb();
+
+	if (qedi_fp_has_work(fp) == 0)
+		qed_sb_ack(fp->sb_info, IGU_INT_ENABLE, 1);
+	else
+		goto process_again;
+
+	return IRQ_HANDLED;
+}
+
+/* simd handler for MSI/INTa */
+static void qedi_simd_int_handler(void *cookie)
+{
+	/* Cookie is qedi_ctx struct */
+	struct qedi_ctx *qedi = (struct qedi_ctx *)cookie;
+
+	QEDI_WARN(&qedi->dbg_ctx, "qedi=%p.\n", qedi);
+}
+
+#define QEDI_SIMD_HANDLER_NUM		0
+static void qedi_sync_free_irqs(struct qedi_ctx *qedi)
+{
+	int i;
+
+	if (qedi->int_info.msix_cnt) {
+		for (i = 0; i < qedi->int_info.used_cnt; i++) {
+			synchronize_irq(qedi->int_info.msix[i].vector);
+			irq_set_affinity_hint(qedi->int_info.msix[i].vector,
+					      NULL);
+			free_irq(qedi->int_info.msix[i].vector,
+				 &qedi->fp_array[i]);
+		}
+	} else {
+		qedi_ops->common->simd_handler_clean(qedi->cdev,
+						     QEDI_SIMD_HANDLER_NUM);
+	}
+
+	qedi->int_info.used_cnt = 0;
+	qedi_ops->common->set_fp_int(qedi->cdev, 0);
+}
+
+static int qedi_request_msix_irq(struct qedi_ctx *qedi)
+{
+	int i, rc, cpu;
+
+	cpu = cpumask_first(cpu_online_mask);
+	for (i = 0; i < MIN_NUM_CPUS_MSIX(qedi); i++) {
+		rc = request_irq(qedi->int_info.msix[i].vector,
+				 qedi_msix_handler, 0, "qedi",
+				 &qedi->fp_array[i]);
+
+		if (rc) {
+			QEDI_WARN(&qedi->dbg_ctx, "request_irq failed.\n");
+			qedi_sync_free_irqs(qedi);
+			return rc;
+		}
+		qedi->int_info.used_cnt++;
+		rc = irq_set_affinity_hint(qedi->int_info.msix[i].vector,
+					   get_cpu_mask(cpu));
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	}
+
+	return 0;
+}
+
+static int qedi_setup_int(struct qedi_ctx *qedi)
+{
+	int rc = 0;
+
+	rc = qedi_ops->common->set_fp_int(qedi->cdev, num_online_cpus());
+	rc = qedi_ops->common->get_fp_int(qedi->cdev, &qedi->int_info);
+	if (rc)
+		goto exit_setup_int;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "Number of msix_cnt = 0x%x num of cpus = 0x%x\n",
+		   qedi->int_info.msix_cnt, num_online_cpus());
+
+	if (qedi->int_info.msix_cnt) {
+		rc = qedi_request_msix_irq(qedi);
+		goto exit_setup_int;
+	} else {
+		qedi_ops->common->simd_handler_config(qedi->cdev, &qedi,
+						      QEDI_SIMD_HANDLER_NUM,
+						      qedi_simd_int_handler);
+		qedi->int_info.used_cnt = 1;
+	}
+
+exit_setup_int:
+	return rc;
+}
+
+static void qedi_free_bdq(struct qedi_ctx *qedi)
+{
+	int i;
+
+	if (qedi->bdq_pbl_list)
+		dma_free_coherent(&qedi->pdev->dev, PAGE_SIZE,
+				  qedi->bdq_pbl_list, qedi->bdq_pbl_list_dma);
+
+	if (qedi->bdq_pbl)
+		dma_free_coherent(&qedi->pdev->dev, qedi->bdq_pbl_mem_size,
+				  qedi->bdq_pbl, qedi->bdq_pbl_dma);
+
+	for (i = 0; i < QEDI_BDQ_NUM; i++) {
+		if (qedi->bdq[i].buf_addr) {
+			dma_free_coherent(&qedi->pdev->dev, QEDI_BDQ_BUF_SIZE,
+					  qedi->bdq[i].buf_addr,
+					  qedi->bdq[i].buf_dma);
+		}
+	}
+}
+
+static void qedi_free_global_queues(struct qedi_ctx *qedi)
+{
+	int i;
+	struct global_queue **gl = qedi->global_queues;
+
+	for (i = 0; i < qedi->num_queues; i++) {
+		if (!gl[i])
+			continue;
+
+		if (gl[i]->cq)
+			dma_free_coherent(&qedi->pdev->dev, gl[i]->cq_mem_size,
+					  gl[i]->cq, gl[i]->cq_dma);
+		if (gl[i]->cq_pbl)
+			dma_free_coherent(&qedi->pdev->dev, gl[i]->cq_pbl_size,
+					  gl[i]->cq_pbl, gl[i]->cq_pbl_dma);
+
+		kfree(gl[i]);
+	}
+	qedi_free_bdq(qedi);
+}
+
+static int qedi_alloc_bdq(struct qedi_ctx *qedi)
+{
+	int i;
+	struct scsi_bd *pbl;
+	u64 *list;
+	dma_addr_t page;
+
+	/* Alloc dma memory for BDQ buffers */
+	for (i = 0; i < QEDI_BDQ_NUM; i++) {
+		qedi->bdq[i].buf_addr =
+				dma_alloc_coherent(&qedi->pdev->dev,
+						   QEDI_BDQ_BUF_SIZE,
+						   &qedi->bdq[i].buf_dma,
+						   GFP_KERNEL);
+		if (!qedi->bdq[i].buf_addr) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not allocate BDQ buffer %d.\n", i);
+			return -ENOMEM;
+		}
+	}
+
+	/* Alloc dma memory for BDQ page buffer list */
+	qedi->bdq_pbl_mem_size = QEDI_BDQ_NUM * sizeof(struct scsi_bd);
+	qedi->bdq_pbl_mem_size = ALIGN(qedi->bdq_pbl_mem_size, PAGE_SIZE);
+	qedi->rq_num_entries = qedi->bdq_pbl_mem_size / sizeof(struct scsi_bd);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN, "rq_num_entries = %d.\n",
+		  qedi->rq_num_entries);
+
+	qedi->bdq_pbl = dma_alloc_coherent(&qedi->pdev->dev,
+					   qedi->bdq_pbl_mem_size,
+					   &qedi->bdq_pbl_dma, GFP_KERNEL);
+	if (!qedi->bdq_pbl) {
+		QEDI_ERR(&qedi->dbg_ctx, "Could not allocate BDQ PBL.\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * Populate BDQ PBL with physical and virtual address of individual
+	 * BDQ buffers
+	 */
+	pbl = (struct scsi_bd  *)qedi->bdq_pbl;
+	for (i = 0; i < QEDI_BDQ_NUM; i++) {
+		pbl->address.hi =
+				cpu_to_le32(QEDI_U64_HI(qedi->bdq[i].buf_dma));
+		pbl->address.lo =
+				cpu_to_le32(QEDI_U64_LO(qedi->bdq[i].buf_dma));
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+			  "pbl [0x%p] pbl->address hi [0x%llx] lo [0x%llx], idx [%d]\n",
+			  pbl, pbl->address.hi, pbl->address.lo, i);
+		pbl->opaque.hi = 0;
+		pbl->opaque.lo = cpu_to_le32(QEDI_U64_LO(i));
+		pbl++;
+	}
+
+	/* Allocate list of PBL pages */
+	qedi->bdq_pbl_list = dma_alloc_coherent(&qedi->pdev->dev,
+						PAGE_SIZE,
+						&qedi->bdq_pbl_list_dma,
+						GFP_KERNEL);
+	if (!qedi->bdq_pbl_list) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Could not allocate list of PBL pages.\n");
+		return -ENOMEM;
+	}
+	memset(qedi->bdq_pbl_list, 0, PAGE_SIZE);
+
+	/*
+	 * Now populate PBL list with pages that contain pointers to the
+	 * individual buffers.
+	 */
+	qedi->bdq_pbl_list_num_entries = qedi->bdq_pbl_mem_size / PAGE_SIZE;
+	list = (u64 *)qedi->bdq_pbl_list;
+	page = qedi->bdq_pbl_list_dma;
+	for (i = 0; i < qedi->bdq_pbl_list_num_entries; i++) {
+		*list = qedi->bdq_pbl_dma;
+		list++;
+		page += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+static int qedi_alloc_global_queues(struct qedi_ctx *qedi)
+{
+	u32 *list;
+	int i;
+	int status = 0, rc;
+	u32 *pbl;
+	dma_addr_t page;
+	int num_pages;
+
+	/*
+	 * Number of global queues (CQ / RQ). This should
+	 * be <= number of available MSIX vectors for the PF
+	 */
+	if (!qedi->num_queues) {
+		QEDI_ERR(&qedi->dbg_ctx, "No MSI-X vectors available!\n");
+		return 1;
+	}
+
+	/* Make sure we allocated the PBL that will contain the physical
+	 * addresses of our queues
+	 */
+	if (!qedi->p_cpuq) {
+		status = 1;
+		goto mem_alloc_failure;
+	}
+
+	qedi->global_queues = kzalloc((sizeof(struct global_queue *) *
+				       qedi->num_queues), GFP_KERNEL);
+	if (!qedi->global_queues) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Unable to allocate global queues array ptr memory\n");
+		return -ENOMEM;
+	}
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "qedi->global_queues=%p.\n", qedi->global_queues);
+
+	/* Allocate DMA coherent buffers for BDQ */
+	rc = qedi_alloc_bdq(qedi);
+	if (rc)
+		goto mem_alloc_failure;
+
+	/* Allocate a CQ and an associated PBL for each MSI-X
+	 * vector.
+	 */
+	for (i = 0; i < qedi->num_queues; i++) {
+		qedi->global_queues[i] =
+					kzalloc(sizeof(*qedi->global_queues[0]),
+						GFP_KERNEL);
+		if (!qedi->global_queues[i]) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Unable to allocation global queue %d.\n", i);
+			goto mem_alloc_failure;
+		}
+
+		qedi->global_queues[i]->cq_mem_size =
+		    (QEDI_CQ_SIZE + 8) * sizeof(union iscsi_cqe);
+		qedi->global_queues[i]->cq_mem_size =
+		    (qedi->global_queues[i]->cq_mem_size +
+		    (QEDI_PAGE_SIZE - 1));
+
+		qedi->global_queues[i]->cq_pbl_size =
+		    (qedi->global_queues[i]->cq_mem_size /
+		    QEDI_PAGE_SIZE) * sizeof(void *);
+		qedi->global_queues[i]->cq_pbl_size =
+		    (qedi->global_queues[i]->cq_pbl_size +
+		    (QEDI_PAGE_SIZE - 1));
+
+		qedi->global_queues[i]->cq =
+		    dma_alloc_coherent(&qedi->pdev->dev,
+				       qedi->global_queues[i]->cq_mem_size,
+				       &qedi->global_queues[i]->cq_dma,
+				       GFP_KERNEL);
+
+		if (!qedi->global_queues[i]->cq) {
+			QEDI_WARN(&qedi->dbg_ctx,
+				  "Could not allocate cq.\n");
+			status = -ENOMEM;
+			goto mem_alloc_failure;
+		}
+		memset(qedi->global_queues[i]->cq, 0,
+		       qedi->global_queues[i]->cq_mem_size);
+
+		qedi->global_queues[i]->cq_pbl =
+		    dma_alloc_coherent(&qedi->pdev->dev,
+				       qedi->global_queues[i]->cq_pbl_size,
+				       &qedi->global_queues[i]->cq_pbl_dma,
+				       GFP_KERNEL);
+
+		if (!qedi->global_queues[i]->cq_pbl) {
+			QEDI_WARN(&qedi->dbg_ctx,
+				  "Could not allocate cq PBL.\n");
+			status = -ENOMEM;
+			goto mem_alloc_failure;
+		}
+		memset(qedi->global_queues[i]->cq_pbl, 0,
+		       qedi->global_queues[i]->cq_pbl_size);
+
+		/* Create PBL */
+		num_pages = qedi->global_queues[i]->cq_mem_size /
+		    QEDI_PAGE_SIZE;
+		page = qedi->global_queues[i]->cq_dma;
+		pbl = (u32 *)qedi->global_queues[i]->cq_pbl;
+
+		while (num_pages--) {
+			*pbl = (u32)page;
+			pbl++;
+			*pbl = (u32)((u64)page >> 32);
+			pbl++;
+			page += QEDI_PAGE_SIZE;
+		}
+	}
+
+	list = (u32 *)qedi->p_cpuq;
+
+	/*
+	 * The list is built as follows: CQ#0 PBL pointer, RQ#0 PBL pointer,
+	 * CQ#1 PBL pointer, RQ#1 PBL pointer, etc.  Each PBL pointer points
+	 * to the physical address which contains an array of pointers to the
+	 * physical addresses of the specific queue pages.
+	 */
+	for (i = 0; i < qedi->num_queues; i++) {
+		*list = (u32)qedi->global_queues[i]->cq_pbl_dma;
+		list++;
+		*list = (u32)((u64)qedi->global_queues[i]->cq_pbl_dma >> 32);
+		list++;
+
+		*list = (u32)0;
+		list++;
+		*list = (u32)((u64)0 >> 32);
+		list++;
+	}
+
+	return 0;
+
+mem_alloc_failure:
+	qedi_free_global_queues(qedi);
+	return status;
+}
+
+int qedi_alloc_sq(struct qedi_ctx *qedi, struct qedi_endpoint *ep)
+{
+	int rval = 0;
+	u32 *pbl;
+	dma_addr_t page;
+	int num_pages;
+
+	if (!ep)
+		return -EIO;
+
+	/* Calculate appropriate queue and PBL sizes */
+	ep->sq_mem_size = QEDI_SQ_SIZE * sizeof(struct iscsi_wqe);
+	ep->sq_mem_size += QEDI_PAGE_SIZE - 1;
+
+	ep->sq_pbl_size = (ep->sq_mem_size / QEDI_PAGE_SIZE) * sizeof(void *);
+	ep->sq_pbl_size = ep->sq_pbl_size + QEDI_PAGE_SIZE;
+
+	ep->sq = dma_alloc_coherent(&qedi->pdev->dev, ep->sq_mem_size,
+				    &ep->sq_dma, GFP_KERNEL);
+	if (!ep->sq) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Could not allocate send queue.\n");
+		rval = -ENOMEM;
+		goto out;
+	}
+	memset(ep->sq, 0, ep->sq_mem_size);
+
+	ep->sq_pbl = dma_alloc_coherent(&qedi->pdev->dev, ep->sq_pbl_size,
+					&ep->sq_pbl_dma, GFP_KERNEL);
+	if (!ep->sq_pbl) {
+		QEDI_WARN(&qedi->dbg_ctx,
+			  "Could not allocate send queue PBL.\n");
+		rval = -ENOMEM;
+		goto out_free_sq;
+	}
+	memset(ep->sq_pbl, 0, ep->sq_pbl_size);
+
+	/* Create PBL */
+	num_pages = ep->sq_mem_size / QEDI_PAGE_SIZE;
+	page = ep->sq_dma;
+	pbl = (u32 *)ep->sq_pbl;
+
+	while (num_pages--) {
+		*pbl = (u32)page;
+		pbl++;
+		*pbl = (u32)((u64)page >> 32);
+		pbl++;
+		page += QEDI_PAGE_SIZE;
+	}
+
+	return rval;
+
+out_free_sq:
+	dma_free_coherent(&qedi->pdev->dev, ep->sq_mem_size, ep->sq,
+			  ep->sq_dma);
+out:
+	return rval;
+}
+
+void qedi_free_sq(struct qedi_ctx *qedi, struct qedi_endpoint *ep)
+{
+	if (ep->sq_pbl)
+		dma_free_coherent(&qedi->pdev->dev, ep->sq_pbl_size, ep->sq_pbl,
+				  ep->sq_pbl_dma);
+	if (ep->sq)
+		dma_free_coherent(&qedi->pdev->dev, ep->sq_mem_size, ep->sq,
+				  ep->sq_dma);
+}
+
+int qedi_get_task_idx(struct qedi_ctx *qedi)
+{
+	s16 tmp_idx;
+
+again:
+	tmp_idx = find_first_zero_bit(qedi->task_idx_map,
+				      MAX_ISCSI_TASK_ENTRIES);
+
+	if (tmp_idx >= MAX_ISCSI_TASK_ENTRIES) {
+		QEDI_ERR(&qedi->dbg_ctx, "FW task context pool is full.\n");
+		tmp_idx = -1;
+		goto err_idx;
+	}
+
+	if (test_and_set_bit(tmp_idx, qedi->task_idx_map))
+		goto again;
+
+err_idx:
+	return tmp_idx;
+}
+
+void qedi_clear_task_idx(struct qedi_ctx *qedi, int idx)
+{
+	if (!test_and_clear_bit(idx, qedi->task_idx_map)) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "FW task context, already cleared, tid=0x%x\n", idx);
+		WARN_ON(1);
+	}
+}
+
+void qedi_update_itt_map(struct qedi_ctx *qedi, u32 tid, u32 proto_itt,
+			 struct qedi_cmd *cmd)
+{
+	qedi->itt_map[tid].itt = proto_itt;
+	qedi->itt_map[tid].p_cmd = cmd;
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "update itt map tid=0x%x, with proto itt=0x%x\n", tid,
+		  qedi->itt_map[tid].itt);
+}
+
+void qedi_get_task_tid(struct qedi_ctx *qedi, u32 itt, s16 *tid)
+{
+	u16 i;
+
+	for (i = 0; i < MAX_ISCSI_TASK_ENTRIES; i++) {
+		if (qedi->itt_map[i].itt == itt) {
+			*tid = i;
+			QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+				  "Ref itt=0x%x, found at tid=0x%x\n",
+				  itt, *tid);
+			return;
+		}
+	}
+
+	WARN_ON(1);
+}
+
+void qedi_get_proto_itt(struct qedi_ctx *qedi, u32 tid, u32 *proto_itt)
+{
+	*proto_itt = qedi->itt_map[tid].itt;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_CONN,
+		  "Get itt map tid [0x%x with proto itt[0x%x]",
+		  tid, *proto_itt);
+}
+
+struct qedi_cmd *qedi_get_cmd_from_tid(struct qedi_ctx *qedi, u32 tid)
+{
+	struct qedi_cmd *cmd = NULL;
+
+	if (tid > MAX_ISCSI_TASK_ENTRIES)
+		return NULL;
+
+	cmd = qedi->itt_map[tid].p_cmd;
+	if (cmd->task_id != tid)
+		return NULL;
+
+	qedi->itt_map[tid].p_cmd = NULL;
+
+	return cmd;
+}
+
+static int qedi_alloc_itt(struct qedi_ctx *qedi)
+{
+	qedi->itt_map = kcalloc(MAX_ISCSI_TASK_ENTRIES,
+				sizeof(struct qedi_itt_map), GFP_KERNEL);
+	if (!qedi->itt_map) {
+		QEDI_ERR(&qedi->dbg_ctx,
+			 "Unable to allocate itt map array memory\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void qedi_free_itt(struct qedi_ctx *qedi)
+{
+	kfree(qedi->itt_map);
+}
+
+static struct qed_ll2_cb_ops qedi_ll2_cb_ops = {
+	.rx_cb = qedi_ll2_rx,
+	.tx_cb = NULL,
+};
+
+static int qedi_percpu_io_thread(void *arg)
+{
+	struct qedi_percpu_s *p = arg;
+	struct qedi_work *work, *tmp;
+	unsigned long flags;
+	LIST_HEAD(work_list);
+
+	set_user_nice(current, -20);
+
+	while (!kthread_should_stop()) {
+		spin_lock_irqsave(&p->p_work_lock, flags);
+		while (!list_empty(&p->work_list)) {
+			list_splice_init(&p->work_list, &work_list);
+			spin_unlock_irqrestore(&p->p_work_lock, flags);
+
+			list_for_each_entry_safe(work, tmp, &work_list, list) {
+				list_del_init(&work->list);
+				qedi_fp_process_cqes(work);
+				if (!work->is_solicited)
+					kfree(work);
+			}
+			cond_resched();
+			spin_lock_irqsave(&p->p_work_lock, flags);
+		}
+		set_current_state(TASK_INTERRUPTIBLE);
+		spin_unlock_irqrestore(&p->p_work_lock, flags);
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	return 0;
+}
+
+static int qedi_cpu_online(unsigned int cpu)
+{
+	struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
+	struct task_struct *thread;
+
+	thread = kthread_create_on_node(qedi_percpu_io_thread, (void *)p,
+					cpu_to_node(cpu),
+					"qedi_thread/%d", cpu);
+	if (IS_ERR(thread))
+		return PTR_ERR(thread);
+
+	kthread_bind(thread, cpu);
+	p->iothread = thread;
+	wake_up_process(thread);
+	return 0;
+}
+
+static int qedi_cpu_offline(unsigned int cpu)
+{
+	struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
+	struct qedi_work *work, *tmp;
+	struct task_struct *thread;
+
+	spin_lock_bh(&p->p_work_lock);
+	thread = p->iothread;
+	p->iothread = NULL;
+
+	list_for_each_entry_safe(work, tmp, &p->work_list, list) {
+		list_del_init(&work->list);
+		qedi_fp_process_cqes(work);
+		if (!work->is_solicited)
+			kfree(work);
+	}
+
+	spin_unlock_bh(&p->p_work_lock);
+	if (thread)
+		kthread_stop(thread);
+	return 0;
+}
+
+void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu)
+{
+	struct qed_ll2_params params;
+
+	qedi_recover_all_conns(qedi);
+
+	qedi_ops->ll2->stop(qedi->cdev);
+	qedi_ll2_free_skbs(qedi);
+
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "old MTU %u, new MTU %u\n",
+		  qedi->ll2_mtu, mtu);
+	memset(&params, 0, sizeof(params));
+	qedi->ll2_mtu = mtu;
+	params.mtu = qedi->ll2_mtu + IPV6_HDR_LEN + TCP_HDR_LEN;
+	params.drop_ttl0_packets = 0;
+	params.rx_vlan_stripping = 1;
+	ether_addr_copy(params.ll2_mac_address, qedi->dev_info.common.hw_mac);
+	qedi_ops->ll2->start(qedi->cdev, &params);
+}
+
+static void __qedi_remove(struct pci_dev *pdev, int mode)
+{
+	struct qedi_ctx *qedi = pci_get_drvdata(pdev);
+
+	if (qedi->tmf_thread) {
+		flush_workqueue(qedi->tmf_thread);
+		destroy_workqueue(qedi->tmf_thread);
+		qedi->tmf_thread = NULL;
+	}
+
+	if (qedi->offload_thread) {
+		flush_workqueue(qedi->offload_thread);
+		destroy_workqueue(qedi->offload_thread);
+		qedi->offload_thread = NULL;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_host_exit(&qedi->dbg_ctx);
+#endif
+	if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags))
+		qedi_ops->common->set_power_state(qedi->cdev, PCI_D0);
+
+	qedi_sync_free_irqs(qedi);
+
+	if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) {
+		qedi_ops->stop(qedi->cdev);
+		qedi_ops->ll2->stop(qedi->cdev);
+	}
+
+	if (mode == QEDI_MODE_NORMAL)
+		qedi_free_iscsi_pf_param(qedi);
+
+	if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) {
+		qedi_ops->common->slowpath_stop(qedi->cdev);
+		qedi_ops->common->remove(qedi->cdev);
+	}
+
+	qedi_destroy_fp(qedi);
+
+	if (mode == QEDI_MODE_NORMAL) {
+		qedi_release_cid_que(qedi);
+		qedi_cm_free_mem(qedi);
+		qedi_free_uio(qedi->udev);
+		qedi_free_itt(qedi);
+
+		iscsi_host_remove(qedi->shost);
+		iscsi_host_free(qedi->shost);
+
+		if (qedi->ll2_recv_thread) {
+			kthread_stop(qedi->ll2_recv_thread);
+			qedi->ll2_recv_thread = NULL;
+		}
+		qedi_ll2_free_skbs(qedi);
+	}
+}
+
+static int __qedi_probe(struct pci_dev *pdev, int mode)
+{
+	struct qedi_ctx *qedi;
+	struct qed_ll2_params params;
+	u32 dp_module = 0;
+	u8 dp_level = 0;
+	bool is_vf = false;
+	char host_buf[16];
+	struct qed_link_params link_params;
+	struct qed_slowpath_params sp_params;
+	struct qed_probe_params qed_params;
+	void *task_start, *task_end;
+	int rc;
+	u16 tmp;
+
+	if (mode != QEDI_MODE_RECOVERY) {
+		qedi = qedi_host_alloc(pdev);
+		if (!qedi) {
+			rc = -ENOMEM;
+			goto exit_probe;
+		}
+	} else {
+		qedi = pci_get_drvdata(pdev);
+	}
+
+	memset(&qed_params, 0, sizeof(qed_params));
+	qed_params.protocol = QED_PROTOCOL_ISCSI;
+	qed_params.dp_module = dp_module;
+	qed_params.dp_level = dp_level;
+	qed_params.is_vf = is_vf;
+	qedi->cdev = qedi_ops->common->probe(pdev, &qed_params);
+	if (!qedi->cdev) {
+		rc = -ENODEV;
+		QEDI_ERR(&qedi->dbg_ctx, "Cannot initialize hardware\n");
+		goto free_host;
+	}
+
+	qedi->msix_count = MAX_NUM_MSIX_PF;
+	atomic_set(&qedi->link_state, QEDI_LINK_DOWN);
+
+	if (mode != QEDI_MODE_RECOVERY) {
+		rc = qedi_set_iscsi_pf_param(qedi);
+		if (rc) {
+			rc = -ENOMEM;
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Set iSCSI pf param fail\n");
+			goto free_host;
+		}
+	}
+
+	qedi_ops->common->update_pf_params(qedi->cdev, &qedi->pf_params);
+
+	rc = qedi_prepare_fp(qedi);
+	if (rc) {
+		QEDI_ERR(&qedi->dbg_ctx, "Cannot start slowpath.\n");
+		goto free_pf_params;
+	}
+
+	/* Start the Slowpath-process */
+	memset(&sp_params, 0, sizeof(struct qed_slowpath_params));
+	sp_params.int_mode = QED_INT_MODE_MSIX;
+	sp_params.drv_major = QEDI_DRIVER_MAJOR_VER;
+	sp_params.drv_minor = QEDI_DRIVER_MINOR_VER;
+	sp_params.drv_rev = QEDI_DRIVER_REV_VER;
+	sp_params.drv_eng = QEDI_DRIVER_ENG_VER;
+	strlcpy(sp_params.name, "qedi iSCSI", QED_DRV_VER_STR_SIZE);
+	rc = qedi_ops->common->slowpath_start(qedi->cdev, &sp_params);
+	if (rc) {
+		QEDI_ERR(&qedi->dbg_ctx, "Cannot start slowpath\n");
+		goto stop_hw;
+	}
+
+	/* update_pf_params needs to be called before and after slowpath
+	 * start
+	 */
+	qedi_ops->common->update_pf_params(qedi->cdev, &qedi->pf_params);
+
+	qedi_setup_int(qedi);
+	if (rc)
+		goto stop_iscsi_func;
+
+	qedi_ops->common->set_power_state(qedi->cdev, PCI_D0);
+
+	/* Learn information crucial for qedi to progress */
+	rc = qedi_ops->fill_dev_info(qedi->cdev, &qedi->dev_info);
+	if (rc)
+		goto stop_iscsi_func;
+
+	/* Record BDQ producer doorbell addresses */
+	qedi->bdq_primary_prod = qedi->dev_info.primary_dbq_rq_addr;
+	qedi->bdq_secondary_prod = qedi->dev_info.secondary_bdq_rq_addr;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "BDQ primary_prod=%p secondary_prod=%p.\n",
+		  qedi->bdq_primary_prod,
+		  qedi->bdq_secondary_prod);
+
+	/*
+	 * We need to write the number of BDs in the BDQ we've preallocated so
+	 * the f/w will do a prefetch and we'll get an unsolicited CQE when a
+	 * packet arrives.
+	 */
+	qedi->bdq_prod_idx = QEDI_BDQ_NUM;
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "Writing %d to primary and secondary BDQ doorbell registers.\n",
+		  qedi->bdq_prod_idx);
+	writew(qedi->bdq_prod_idx, qedi->bdq_primary_prod);
+	tmp = readw(qedi->bdq_primary_prod);
+	writew(qedi->bdq_prod_idx, qedi->bdq_secondary_prod);
+	tmp = readw(qedi->bdq_secondary_prod);
+
+	ether_addr_copy(qedi->mac, qedi->dev_info.common.hw_mac);
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC, "MAC address is %pM.\n",
+		  qedi->mac);
+
+	sprintf(host_buf, "host_%d", qedi->shost->host_no);
+	qedi_ops->common->set_id(qedi->cdev, host_buf, QEDI_MODULE_VERSION);
+
+	qedi_ops->register_ops(qedi->cdev, &qedi_cb_ops, qedi);
+
+	memset(&params, 0, sizeof(params));
+	params.mtu = DEF_PATH_MTU + IPV6_HDR_LEN + TCP_HDR_LEN;
+	qedi->ll2_mtu = DEF_PATH_MTU;
+	params.drop_ttl0_packets = 0;
+	params.rx_vlan_stripping = 1;
+	ether_addr_copy(params.ll2_mac_address, qedi->dev_info.common.hw_mac);
+
+	if (mode != QEDI_MODE_RECOVERY) {
+		/* set up rx path */
+		INIT_LIST_HEAD(&qedi->ll2_skb_list);
+		spin_lock_init(&qedi->ll2_lock);
+		/* start qedi context */
+		spin_lock_init(&qedi->hba_lock);
+		spin_lock_init(&qedi->task_idx_lock);
+	}
+	qedi_ops->ll2->register_cb_ops(qedi->cdev, &qedi_ll2_cb_ops, qedi);
+	qedi_ops->ll2->start(qedi->cdev, &params);
+
+	if (mode != QEDI_MODE_RECOVERY) {
+		qedi->ll2_recv_thread = kthread_run(qedi_ll2_recv_thread,
+						    (void *)qedi,
+						    "qedi_ll2_thread");
+	}
+
+	rc = qedi_ops->start(qedi->cdev, &qedi->tasks,
+			     qedi, qedi_iscsi_event_cb);
+	if (rc) {
+		rc = -ENODEV;
+		QEDI_ERR(&qedi->dbg_ctx, "Cannot start iSCSI function\n");
+		goto stop_slowpath;
+	}
+
+	task_start = qedi_get_task_mem(&qedi->tasks, 0);
+	task_end = qedi_get_task_mem(&qedi->tasks, MAX_TID_BLOCKS_ISCSI - 1);
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_DISC,
+		  "Task context start=%p, end=%p block_size=%u.\n",
+		   task_start, task_end, qedi->tasks.size);
+
+	memset(&link_params, 0, sizeof(link_params));
+	link_params.link_up = true;
+	rc = qedi_ops->common->set_link(qedi->cdev, &link_params);
+	if (rc) {
+		QEDI_WARN(&qedi->dbg_ctx, "Link set up failed.\n");
+		atomic_set(&qedi->link_state, QEDI_LINK_DOWN);
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_host_init(&qedi->dbg_ctx, &qedi_debugfs_ops,
+			   &qedi_dbg_fops);
+#endif
+	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
+		  "QLogic FastLinQ iSCSI Module qedi %s, FW %d.%d.%d.%d\n",
+		  QEDI_MODULE_VERSION, FW_MAJOR_VERSION, FW_MINOR_VERSION,
+		  FW_REVISION_VERSION, FW_ENGINEERING_VERSION);
+
+	if (mode == QEDI_MODE_NORMAL) {
+		if (iscsi_host_add(qedi->shost, &pdev->dev)) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not add iscsi host\n");
+			rc = -ENOMEM;
+			goto remove_host;
+		}
+
+		/* Allocate uio buffers */
+		rc = qedi_alloc_uio_rings(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "UIO alloc ring failed err=%d\n", rc);
+			goto remove_host;
+		}
+
+		rc = qedi_init_uio(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "UIO init failed, err=%d\n", rc);
+			goto free_uio;
+		}
+
+		/* host the array on iscsi_conn */
+		rc = qedi_setup_cid_que(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not setup cid que\n");
+			goto free_uio;
+		}
+
+		rc = qedi_cm_alloc_mem(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not alloc cm memory\n");
+			goto free_cid_que;
+		}
+
+		rc = qedi_alloc_itt(qedi);
+		if (rc) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Could not alloc itt memory\n");
+			goto free_cid_que;
+		}
+
+		sprintf(host_buf, "host_%d", qedi->shost->host_no);
+		qedi->tmf_thread = create_singlethread_workqueue(host_buf);
+		if (!qedi->tmf_thread) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Unable to start tmf thread!\n");
+			rc = -ENODEV;
+			goto free_cid_que;
+		}
+
+		sprintf(host_buf, "qedi_ofld%d", qedi->shost->host_no);
+		qedi->offload_thread = create_workqueue(host_buf);
+		if (!qedi->offload_thread) {
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Unable to start offload thread!\n");
+			rc = -ENODEV;
+			goto free_cid_que;
+		}
+
+		/* F/w needs 1st task context memory entry for performance */
+		set_bit(QEDI_RESERVE_TASK_ID, qedi->task_idx_map);
+		atomic_set(&qedi->num_offloads, 0);
+	}
+
+	return 0;
+
+free_cid_que:
+	qedi_release_cid_que(qedi);
+free_uio:
+	qedi_free_uio(qedi->udev);
+remove_host:
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_host_exit(&qedi->dbg_ctx);
+#endif
+	iscsi_host_remove(qedi->shost);
+stop_iscsi_func:
+	qedi_ops->stop(qedi->cdev);
+stop_slowpath:
+	qedi_ops->common->slowpath_stop(qedi->cdev);
+stop_hw:
+	qedi_ops->common->remove(qedi->cdev);
+free_pf_params:
+	qedi_free_iscsi_pf_param(qedi);
+free_host:
+	iscsi_host_free(qedi->shost);
+exit_probe:
+	return rc;
+}
+
+static int qedi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	return __qedi_probe(pdev, QEDI_MODE_NORMAL);
+}
+
+static void qedi_remove(struct pci_dev *pdev)
+{
+	__qedi_remove(pdev, QEDI_MODE_NORMAL);
+}
+
+static struct pci_device_id qedi_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x165E) },
+	{ 0 },
+};
+MODULE_DEVICE_TABLE(pci, qedi_pci_tbl);
+
+static enum cpuhp_state qedi_cpuhp_state;
+
+static struct pci_driver qedi_pci_driver = {
+	.name = QEDI_MODULE_NAME,
+	.id_table = qedi_pci_tbl,
+	.probe = qedi_probe,
+	.remove = qedi_remove,
+};
+
+static int __init qedi_init(void)
+{
+	struct qedi_percpu_s *p;
+	int cpu, rc = 0;
+
+	qedi_ops = qed_get_iscsi_ops();
+	if (!qedi_ops) {
+		QEDI_ERR(NULL, "Failed to get qed iSCSI operations\n");
+		return -EINVAL;
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_init("qedi");
+#endif
+
+	qedi_scsi_transport = iscsi_register_transport(&qedi_iscsi_transport);
+	if (!qedi_scsi_transport) {
+		QEDI_ERR(NULL, "Could not register qedi transport");
+		rc = -ENOMEM;
+		goto exit_qedi_init_1;
+	}
+
+	for_each_possible_cpu(cpu) {
+		p = &per_cpu(qedi_percpu, cpu);
+		INIT_LIST_HEAD(&p->work_list);
+		spin_lock_init(&p->p_work_lock);
+		p->iothread = NULL;
+	}
+
+	rc = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "scsi/qedi:online",
+			       qedi_cpu_online, qedi_cpu_offline);
+	if (rc < 0)
+		goto exit_qedi_init_2;
+	qedi_cpuhp_state = rc;
+
+	rc = pci_register_driver(&qedi_pci_driver);
+	if (rc) {
+		QEDI_ERR(NULL, "Failed to register driver\n");
+		goto exit_qedi_hp;
+	}
+
+	return 0;
+
+exit_qedi_hp:
+	cpuhp_remove_state(qedi_cpuhp_state);
+exit_qedi_init_2:
+	iscsi_unregister_transport(&qedi_iscsi_transport);
+exit_qedi_init_1:
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_exit();
+#endif
+	qed_put_iscsi_ops();
+	return rc;
+}
+
+static void __exit qedi_cleanup(void)
+{
+	pci_unregister_driver(&qedi_pci_driver);
+	cpuhp_remove_state(qedi_cpuhp_state);
+	iscsi_unregister_transport(&qedi_iscsi_transport);
+
+#ifdef CONFIG_DEBUG_FS
+	qedi_dbg_exit();
+#endif
+	qed_put_iscsi_ops();
+}
+
+MODULE_DESCRIPTION("QLogic FastLinQ 4xxxx iSCSI Module");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("QLogic Corporation");
+MODULE_VERSION(QEDI_MODULE_VERSION);
+module_init(qedi_init);
+module_exit(qedi_cleanup);
diff --git a/drivers/scsi/qedi/qedi_sysfs.c b/drivers/scsi/qedi/qedi_sysfs.c
new file mode 100644
index 0000000..b10c48b
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_sysfs.c
@@ -0,0 +1,52 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#include "qedi.h"
+#include "qedi_gbl.h"
+#include "qedi_iscsi.h"
+#include "qedi_dbg.h"
+
+static inline struct qedi_ctx *qedi_dev_to_hba(struct device *dev)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+
+	return iscsi_host_priv(shost);
+}
+
+static ssize_t qedi_show_port_state(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct qedi_ctx *qedi = qedi_dev_to_hba(dev);
+
+	if (atomic_read(&qedi->link_state) == QEDI_LINK_UP)
+		return sprintf(buf, "Online\n");
+	else
+		return sprintf(buf, "Linkdown\n");
+}
+
+static ssize_t qedi_show_speed(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct qedi_ctx *qedi = qedi_dev_to_hba(dev);
+	struct qed_link_output if_link;
+
+	qedi_ops->common->get_link(qedi->cdev, &if_link);
+
+	return sprintf(buf, "%d Gbit\n", if_link.speed / 1000);
+}
+
+static DEVICE_ATTR(port_state, 0444, qedi_show_port_state, NULL);
+static DEVICE_ATTR(speed, 0444, qedi_show_speed, NULL);
+
+struct device_attribute *qedi_shost_attrs[] = {
+	&dev_attr_port_state,
+	&dev_attr_speed,
+	NULL
+};
diff --git a/drivers/scsi/qedi/qedi_version.h b/drivers/scsi/qedi/qedi_version.h
new file mode 100644
index 0000000..9543a1b
--- /dev/null
+++ b/drivers/scsi/qedi/qedi_version.h
@@ -0,0 +1,14 @@
+/*
+ * QLogic iSCSI Offload Driver
+ * Copyright (c) 2016 Cavium Inc.
+ *
+ * This software is available under the terms of the GNU General Public License
+ * (GPL) Version 2, available from the file COPYING in the main directory of
+ * this source tree.
+ */
+
+#define QEDI_MODULE_VERSION	"8.10.3.0"
+#define QEDI_DRIVER_MAJOR_VER		8
+#define QEDI_DRIVER_MINOR_VER		10
+#define QEDI_DRIVER_REV_VER		3
+#define QEDI_DRIVER_ENG_VER		0
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index fe7469c..47eb4d5 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -1988,9 +1988,9 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 	scsi_qla_host_t *base_vha = shost_priv(fc_vport->shost);
 	scsi_qla_host_t *vha = NULL;
 	struct qla_hw_data *ha = base_vha->hw;
-	uint16_t options = 0;
 	int	cnt;
 	struct req_que *req = ha->req_q_map[0];
+	struct qla_qpair *qpair;
 
 	ret = qla24xx_vport_create_req_sanity_check(fc_vport);
 	if (ret) {
@@ -2075,15 +2075,9 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 	qlt_vport_create(vha, ha);
 	qla24xx_vport_disable(fc_vport, disable);
 
-	if (ha->flags.cpu_affinity_enabled) {
-		req = ha->req_q_map[1];
-		ql_dbg(ql_dbg_multiq, vha, 0xc000,
-		    "Request queue %p attached with "
-		    "VP[%d], cpu affinity =%d\n",
-		    req, vha->vp_idx, ha->flags.cpu_affinity_enabled);
+	if (!ql2xmqsupport || !ha->npiv_info)
 		goto vport_queue;
-	} else if (ql2xmaxqueues == 1 || !ha->npiv_info)
-		goto vport_queue;
+
 	/* Create a request queue in QoS mode for the vport */
 	for (cnt = 0; cnt < ha->nvram_npiv_size; cnt++) {
 		if (memcmp(ha->npiv_info[cnt].port_name, vha->port_name, 8) == 0
@@ -2095,20 +2089,20 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 	}
 
 	if (qos) {
-		ret = qla25xx_create_req_que(ha, options, vha->vp_idx, 0, 0,
-			qos);
-		if (!ret)
+		qpair = qla2xxx_create_qpair(vha, qos, vha->vp_idx);
+		if (!qpair)
 			ql_log(ql_log_warn, vha, 0x7084,
-			    "Can't create request queue for VP[%d]\n",
+			    "Can't create qpair for VP[%d]\n",
 			    vha->vp_idx);
 		else {
 			ql_dbg(ql_dbg_multiq, vha, 0xc001,
-			    "Request Que:%d Q0s: %d) created for VP[%d]\n",
-			    ret, qos, vha->vp_idx);
+			    "Queue pair: %d Qos: %d) created for VP[%d]\n",
+			    qpair->id, qos, vha->vp_idx);
 			ql_dbg(ql_dbg_user, vha, 0x7085,
-			    "Request Que:%d Q0s: %d) created for VP[%d]\n",
-			    ret, qos, vha->vp_idx);
-			req = ha->req_q_map[ret];
+			    "Queue Pair: %d Qos: %d) created for VP[%d]\n",
+			    qpair->id, qos, vha->vp_idx);
+			req = qpair->req;
+			vha->qpair = qpair;
 		}
 	}
 
@@ -2162,10 +2156,10 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 	clear_bit(vha->vp_idx, ha->vp_idx_map);
 	mutex_unlock(&ha->vport_lock);
 
-	if (vha->req->id && !ha->flags.cpu_affinity_enabled) {
-		if (qla25xx_delete_req_que(vha, vha->req) != QLA_SUCCESS)
+	if (vha->qpair->vp_idx == vha->vp_idx) {
+		if (qla2xxx_delete_qpair(vha, vha->qpair) != QLA_SUCCESS)
 			ql_log(ql_log_warn, vha, 0x7087,
-			    "Queue delete failed.\n");
+			    "Queue Pair delete failed.\n");
 	}
 
 	ql_log(ql_log_info, vha, 0x7088, "VP[%d] deleted.\n", id);
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 45af34d..21d9fb7 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -11,7 +11,7 @@
  * ----------------------------------------------------------------------
  * |             Level            |   Last Value Used  |     Holes	|
  * ----------------------------------------------------------------------
- * | Module Init and Probe        |       0x0191       | 0x0146         |
+ * | Module Init and Probe        |       0x0193       | 0x0146         |
  * |                              |                    | 0x015b-0x0160	|
  * |                              |                    | 0x016e		|
  * | Mailbox commands             |       0x1199       | 0x1193		|
@@ -58,7 +58,7 @@
  * |                              |                    | 0xb13a,0xb142  |
  * |                              |                    | 0xb13c-0xb140  |
  * |                              |                    | 0xb149		|
- * | MultiQ                       |       0xc00c       |		|
+ * | MultiQ                       |       0xc010       |		|
  * | Misc                         |       0xd301       | 0xd031-0xd0ff	|
  * |                              |                    | 0xd101-0xd1fe	|
  * |                              |                    | 0xd214-0xd2fe	|
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 5236e3f..f7df01b 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -401,6 +401,7 @@ typedef struct srb {
 	uint16_t type;
 	char *name;
 	int iocbs;
+	struct qla_qpair *qpair;
 	union {
 		struct srb_iocb iocb_cmd;
 		struct bsg_job *bsg_job;
@@ -2719,6 +2720,7 @@ struct isp_operations {
 
 	int (*get_flash_version) (struct scsi_qla_host *, void *);
 	int (*start_scsi) (srb_t *);
+	int (*start_scsi_mq) (srb_t *);
 	int (*abort_isp) (struct scsi_qla_host *);
 	int (*iospace_config)(struct qla_hw_data*);
 	int (*initialize_adapter)(struct scsi_qla_host *);
@@ -2730,8 +2732,10 @@ struct isp_operations {
 #define QLA_MSIX_FW_MODE(m)	(((m) & (BIT_7|BIT_8|BIT_9)) >> 7)
 #define QLA_MSIX_FW_MODE_1(m)	(QLA_MSIX_FW_MODE(m) == 1)
 
-#define QLA_MSIX_DEFAULT	0x00
-#define QLA_MSIX_RSP_Q		0x01
+#define QLA_MSIX_DEFAULT		0x00
+#define QLA_MSIX_RSP_Q			0x01
+#define QLA_ATIO_VECTOR		0x02
+#define QLA_MSIX_QPAIR_MULTIQ_RSP_Q	0x03
 
 #define QLA_MIDX_DEFAULT	0
 #define QLA_MIDX_RSP_Q		1
@@ -2745,9 +2749,11 @@ struct scsi_qla_host;
 
 struct qla_msix_entry {
 	int have_irq;
+	int in_use;
 	uint32_t vector;
 	uint16_t entry;
-	struct rsp_que *rsp;
+	char name[30];
+	void *handle;
 	struct irq_affinity_notify irq_notify;
 	int cpuid;
 };
@@ -2872,7 +2878,6 @@ struct rsp_que {
 	struct qla_msix_entry *msix;
 	struct req_que *req;
 	srb_t *status_srb; /* status continuation entry */
-	struct work_struct q_work;
 
 	dma_addr_t  dma_fx00;
 	response_t *ring_fx00;
@@ -2909,6 +2914,37 @@ struct req_que {
 	uint8_t req_pkt[REQUEST_ENTRY_SIZE];
 };
 
+/*Queue pair data structure */
+struct qla_qpair {
+	spinlock_t qp_lock;
+	atomic_t ref_count;
+	/* distill these fields down to 'online=0/1'
+	 * ha->flags.eeh_busy
+	 * ha->flags.pci_channel_io_perm_failure
+	 * base_vha->loop_state
+	 */
+	uint32_t online:1;
+	/* move vha->flags.difdix_supported here */
+	uint32_t difdix_supported:1;
+	uint32_t delete_in_progress:1;
+
+	uint16_t id;			/* qp number used with FW */
+	uint16_t num_active_cmd;	/* cmds down at firmware */
+	cpumask_t cpu_mask; /* CPU mask for cpu affinity operation */
+	uint16_t vp_idx;		/* vport ID */
+
+	mempool_t *srb_mempool;
+
+	/* to do: New driver: move queues to here instead of pointers */
+	struct req_que *req;
+	struct rsp_que *rsp;
+	struct atio_que *atio;
+	struct qla_msix_entry *msix; /* point to &ha->msix_entries[x] */
+	struct qla_hw_data *hw;
+	struct work_struct q_work;
+	struct list_head qp_list_elem; /* vha->qp_list */
+};
+
 /* Place holder for FW buffer parameters */
 struct qlfc_fw {
 	void *fw_buf;
@@ -3004,7 +3040,6 @@ struct qla_hw_data {
 		uint32_t	chip_reset_done		:1;
 		uint32_t	running_gold_fw		:1;
 		uint32_t	eeh_busy		:1;
-		uint32_t	cpu_affinity_enabled	:1;
 		uint32_t	disable_msix_handshake	:1;
 		uint32_t	fcp_prio_enabled	:1;
 		uint32_t	isp82xx_fw_hung:1;
@@ -3061,10 +3096,15 @@ struct qla_hw_data {
 	uint8_t         mqenable;
 	struct req_que **req_q_map;
 	struct rsp_que **rsp_q_map;
+	struct qla_qpair **queue_pair_map;
 	unsigned long req_qid_map[(QLA_MAX_QUEUES / 8) / sizeof(unsigned long)];
 	unsigned long rsp_qid_map[(QLA_MAX_QUEUES / 8) / sizeof(unsigned long)];
+	unsigned long qpair_qid_map[(QLA_MAX_QUEUES / 8)
+		/ sizeof(unsigned long)];
 	uint8_t 	max_req_queues;
 	uint8_t 	max_rsp_queues;
+	uint8_t		max_qpairs;
+	struct qla_qpair *base_qpair;
 	struct qla_npiv_entry *npiv_info;
 	uint16_t	nvram_npiv_size;
 
@@ -3328,6 +3368,7 @@ struct qla_hw_data {
 
 	struct mutex vport_lock;        /* Virtual port synchronization */
 	spinlock_t vport_slock; /* order is hardware_lock, then vport_slock */
+	struct mutex mq_lock;        /* multi-queue synchronization */
 	struct completion mbx_cmd_comp; /* Serialize mbx access */
 	struct completion mbx_intr_comp;  /* Used for completion notification */
 	struct completion dcbx_comp;	/* For set port config notification */
@@ -3608,6 +3649,7 @@ typedef struct scsi_qla_host {
 
 		uint32_t	fw_tgt_reported:1;
 		uint32_t	bbcr_enable:1;
+		uint32_t	qpairs_available:1;
 	} flags;
 
 	atomic_t	loop_state;
@@ -3646,6 +3688,7 @@ typedef struct scsi_qla_host {
 #define FX00_TARGET_SCAN	24
 #define FX00_CRITEMP_RECOVERY	25
 #define FX00_HOST_INFO_RESEND	26
+#define QPAIR_ONLINE_CHECK_NEEDED	27
 
 	unsigned long	pci_flags;
 #define PFLG_DISCONNECTED	0	/* PCI device removed */
@@ -3704,10 +3747,13 @@ typedef struct scsi_qla_host {
 	/* List of pending PLOGI acks, protected by hw lock */
 	struct list_head	plogi_ack_list;
 
+	struct list_head	qp_list;
+
 	uint32_t	vp_abort_cnt;
 
 	struct fc_vport	*fc_vport;	/* holds fc_vport * for each vport */
 	uint16_t        vp_idx;		/* vport ID */
+	struct qla_qpair *qpair;	/* base qpair */
 
 	unsigned long		vp_flags;
 #define VP_IDX_ACQUIRED		0	/* bit no 0 */
@@ -3763,6 +3809,23 @@ struct qla_tgt_vp_map {
 	scsi_qla_host_t *vha;
 };
 
+struct qla2_sgx {
+	dma_addr_t		dma_addr;	/* OUT */
+	uint32_t		dma_len;	/* OUT */
+
+	uint32_t		tot_bytes;	/* IN */
+	struct scatterlist	*cur_sg;	/* IN */
+
+	/* for book keeping, bzero on initial invocation */
+	uint32_t		bytes_consumed;
+	uint32_t		num_bytes;
+	uint32_t		tot_partial;
+
+	/* for debugging */
+	uint32_t		num_sg;
+	srb_t			*sp;
+};
+
 /*
  * Macros to help code, maintain, etc.
  */
@@ -3775,21 +3838,34 @@ struct qla_tgt_vp_map {
 		(test_bit(ISP_ABORT_NEEDED, &ha->dpc_flags) || \
 			 test_bit(LOOP_RESYNC_NEEDED, &ha->dpc_flags))
 
-#define QLA_VHA_MARK_BUSY(__vha, __bail) do {		     \
-	atomic_inc(&__vha->vref_count);			     \
-	mb();						     \
-	if (__vha->flags.delete_progress) {		     \
-		atomic_dec(&__vha->vref_count);		     \
-		__bail = 1;				     \
-	} else {					     \
-		__bail = 0;				     \
-	}						     \
+#define QLA_VHA_MARK_BUSY(__vha, __bail) do {		\
+	atomic_inc(&__vha->vref_count);			\
+	mb();						\
+	if (__vha->flags.delete_progress) {		\
+		atomic_dec(&__vha->vref_count);		\
+		__bail = 1;				\
+	} else {					\
+		__bail = 0;				\
+	}						\
 } while (0)
 
-#define QLA_VHA_MARK_NOT_BUSY(__vha) do {		     \
-	atomic_dec(&__vha->vref_count);			     \
+#define QLA_VHA_MARK_NOT_BUSY(__vha)			\
+	atomic_dec(&__vha->vref_count);			\
+
+#define QLA_QPAIR_MARK_BUSY(__qpair, __bail) do {	\
+	atomic_inc(&__qpair->ref_count);		\
+	mb();						\
+	if (__qpair->delete_in_progress) {		\
+		atomic_dec(&__qpair->ref_count);	\
+		__bail = 1;				\
+	} else {					\
+	       __bail = 0;				\
+	}						\
 } while (0)
 
+#define QLA_QPAIR_MARK_NOT_BUSY(__qpair)		\
+	atomic_dec(&__qpair->ref_count);		\
+
 /*
  * qla2x00 local function return status codes
  */
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index c51d9f3..afa0116 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -91,12 +91,17 @@ extern int
 qla2x00_alloc_outstanding_cmds(struct qla_hw_data *, struct req_que *);
 extern int qla2x00_init_rings(scsi_qla_host_t *);
 extern uint8_t qla27xx_find_valid_image(struct scsi_qla_host *);
+extern struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *,
+	int, int);
+extern int qla2xxx_delete_qpair(struct scsi_qla_host *, struct qla_qpair *);
 
 /*
  * Global Data in qla_os.c source file.
  */
 extern char qla2x00_version_str[];
 
+extern struct kmem_cache *srb_cachep;
+
 extern int ql2xlogintimeout;
 extern int qlport_down_retry;
 extern int ql2xplogiabsentdevice;
@@ -105,8 +110,7 @@ extern int ql2xfdmienable;
 extern int ql2xallocfwdump;
 extern int ql2xextended_error_logging;
 extern int ql2xiidmaenable;
-extern int ql2xmaxqueues;
-extern int ql2xmultique_tag;
+extern int ql2xmqsupport;
 extern int ql2xfwloadbin;
 extern int ql2xetsenable;
 extern int ql2xshiftctondsd;
@@ -172,6 +176,9 @@ extern int qla2x00_post_uevent_work(struct scsi_qla_host *, u32);
 
 extern int qla2x00_post_uevent_work(struct scsi_qla_host *, u32);
 extern void qla2x00_disable_board_on_pci_error(struct work_struct *);
+extern void qla2x00_sp_compl(void *, void *, int);
+extern void qla2xxx_qpair_sp_free_dma(void *, void *);
+extern void qla2xxx_qpair_sp_compl(void *, void *, int);
 
 /*
  * Global Functions in qla_mid.c source file.
@@ -220,6 +227,8 @@ extern uint16_t qla2x00_calc_iocbs_32(uint16_t);
 extern uint16_t qla2x00_calc_iocbs_64(uint16_t);
 extern void qla2x00_build_scsi_iocbs_32(srb_t *, cmd_entry_t *, uint16_t);
 extern void qla2x00_build_scsi_iocbs_64(srb_t *, cmd_entry_t *, uint16_t);
+extern void qla24xx_build_scsi_iocbs(srb_t *, struct cmd_type_7 *,
+	uint16_t, struct req_que *);
 extern int qla2x00_start_scsi(srb_t *sp);
 extern int qla24xx_start_scsi(srb_t *sp);
 int qla2x00_marker(struct scsi_qla_host *, struct req_que *, struct rsp_que *,
@@ -227,6 +236,7 @@ int qla2x00_marker(struct scsi_qla_host *, struct req_que *, struct rsp_que *,
 extern int qla2x00_start_sp(srb_t *);
 extern int qla24xx_dif_start_scsi(srb_t *);
 extern int qla2x00_start_bidir(srb_t *, struct scsi_qla_host *, uint32_t);
+extern int qla2xxx_dif_start_scsi_mq(srb_t *);
 extern unsigned long qla2x00_get_async_timeout(struct scsi_qla_host *);
 
 extern void *qla2x00_alloc_iocbs(scsi_qla_host_t *, srb_t *);
@@ -237,7 +247,10 @@ extern int qla24xx_walk_and_build_sglist(struct qla_hw_data *, srb_t *,
 	uint32_t *, uint16_t, struct qla_tgt_cmd *);
 extern int qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *, srb_t *,
 	uint32_t *, uint16_t, struct qla_tgt_cmd *);
-
+extern int qla24xx_get_one_block_sg(uint32_t, struct qla2_sgx *, uint32_t *);
+extern int qla24xx_configure_prot_mode(srb_t *, uint16_t *);
+extern int qla24xx_build_scsi_crc_2_iocbs(srb_t *,
+	struct cmd_type_crc_2 *, uint16_t, uint16_t, uint16_t);
 
 /*
  * Global Function Prototypes in qla_mbx.c source file.
@@ -468,6 +481,8 @@ qla2x00_get_sp_from_handle(scsi_qla_host_t *, const char *, struct req_que *,
 extern void
 qla2x00_process_completed_request(struct scsi_qla_host *, struct req_que *,
 	uint32_t);
+extern irqreturn_t
+qla2xxx_msix_rsp_q(int irq, void *dev_id);
 
 /*
  * Global Function Prototypes in qla_sup.c source file.
@@ -603,15 +618,18 @@ extern int qla2x00_dfs_setup(scsi_qla_host_t *);
 extern int qla2x00_dfs_remove(scsi_qla_host_t *);
 
 /* Globa function prototypes for multi-q */
-extern int qla25xx_request_irq(struct rsp_que *);
+extern int qla25xx_request_irq(struct qla_hw_data *, struct qla_qpair *,
+	struct qla_msix_entry *, int);
 extern int qla25xx_init_req_que(struct scsi_qla_host *, struct req_que *);
 extern int qla25xx_init_rsp_que(struct scsi_qla_host *, struct rsp_que *);
 extern int qla25xx_create_req_que(struct qla_hw_data *, uint16_t, uint8_t,
 	uint16_t, int, uint8_t);
 extern int qla25xx_create_rsp_que(struct qla_hw_data *, uint16_t, uint8_t,
-	uint16_t, int);
+	uint16_t, struct qla_qpair *);
+
 extern void qla2x00_init_response_q_entries(struct rsp_que *);
 extern int qla25xx_delete_req_que(struct scsi_qla_host *, struct req_que *);
+extern int qla25xx_delete_rsp_que(struct scsi_qla_host *, struct rsp_que *);
 extern int qla25xx_delete_queues(struct scsi_qla_host *);
 extern uint16_t qla24xx_rd_req_reg(struct qla_hw_data *, uint16_t);
 extern uint16_t qla25xx_rd_req_reg(struct qla_hw_data *, uint16_t);
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 5b09296..632d5f3 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1769,8 +1769,7 @@ qla2x00_alloc_outstanding_cmds(struct qla_hw_data *ha, struct req_que *req)
 	if (req->outstanding_cmds)
 		return QLA_SUCCESS;
 
-	if (!IS_FWI2_CAPABLE(ha) || (ha->mqiobase &&
-	    (ql2xmultique_tag || ql2xmaxqueues > 1)))
+	if (!IS_FWI2_CAPABLE(ha))
 		req->num_outstanding_cmds = DEFAULT_OUTSTANDING_COMMANDS;
 	else {
 		if (ha->cur_fw_xcb_count <= ha->cur_fw_iocb_count)
@@ -4248,10 +4247,7 @@ qla2x00_loop_resync(scsi_qla_host_t *vha)
 	struct req_que *req;
 	struct rsp_que *rsp;
 
-	if (vha->hw->flags.cpu_affinity_enabled)
-		req = vha->hw->req_q_map[0];
-	else
-		req = vha->req;
+	req = vha->req;
 	rsp = req->rsp;
 
 	clear_bit(ISP_ABORT_RETRY, &vha->dpc_flags);
@@ -6040,10 +6036,10 @@ qla24xx_configure_vhba(scsi_qla_host_t *vha)
 		return -EINVAL;
 
 	rval = qla2x00_fw_ready(base_vha);
-	if (ha->flags.cpu_affinity_enabled)
-		req = ha->req_q_map[0];
+	if (vha->qpair)
+		req = vha->qpair->req;
 	else
-		req = vha->req;
+		req = ha->req_q_map[0];
 	rsp = req->rsp;
 
 	if (rval == QLA_SUCCESS) {
@@ -6725,3 +6721,162 @@ qla24xx_update_all_fcp_prio(scsi_qla_host_t *vha)
 
 	return ret;
 }
+
+struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos, int vp_idx)
+{
+	int rsp_id = 0;
+	int  req_id = 0;
+	int i;
+	struct qla_hw_data *ha = vha->hw;
+	uint16_t qpair_id = 0;
+	struct qla_qpair *qpair = NULL;
+	struct qla_msix_entry *msix;
+
+	if (!(ha->fw_attributes & BIT_6) || !ha->flags.msix_enabled) {
+		ql_log(ql_log_warn, vha, 0x00181,
+		    "FW/Driver is not multi-queue capable.\n");
+		return NULL;
+	}
+
+	if (ql2xmqsupport) {
+		qpair = kzalloc(sizeof(struct qla_qpair), GFP_KERNEL);
+		if (qpair == NULL) {
+			ql_log(ql_log_warn, vha, 0x0182,
+			    "Failed to allocate memory for queue pair.\n");
+			return NULL;
+		}
+		memset(qpair, 0, sizeof(struct qla_qpair));
+
+		qpair->hw = vha->hw;
+
+		/* Assign available que pair id */
+		mutex_lock(&ha->mq_lock);
+		qpair_id = find_first_zero_bit(ha->qpair_qid_map, ha->max_qpairs);
+		if (qpair_id >= ha->max_qpairs) {
+			mutex_unlock(&ha->mq_lock);
+			ql_log(ql_log_warn, vha, 0x0183,
+			    "No resources to create additional q pair.\n");
+			goto fail_qid_map;
+		}
+		set_bit(qpair_id, ha->qpair_qid_map);
+		ha->queue_pair_map[qpair_id] = qpair;
+		qpair->id = qpair_id;
+		qpair->vp_idx = vp_idx;
+
+		for (i = 0; i < ha->msix_count; i++) {
+			msix = &ha->msix_entries[i];
+			if (msix->in_use)
+				continue;
+			qpair->msix = msix;
+			ql_log(ql_dbg_multiq, vha, 0xc00f,
+			    "Vector %x selected for qpair\n", msix->vector);
+			break;
+		}
+		if (!qpair->msix) {
+			ql_log(ql_log_warn, vha, 0x0184,
+			    "Out of MSI-X vectors!.\n");
+			goto fail_msix;
+		}
+
+		qpair->msix->in_use = 1;
+		list_add_tail(&qpair->qp_list_elem, &vha->qp_list);
+
+		mutex_unlock(&ha->mq_lock);
+
+		/* Create response queue first */
+		rsp_id = qla25xx_create_rsp_que(ha, 0, 0, 0, qpair);
+		if (!rsp_id) {
+			ql_log(ql_log_warn, vha, 0x0185,
+			    "Failed to create response queue.\n");
+			goto fail_rsp;
+		}
+
+		qpair->rsp = ha->rsp_q_map[rsp_id];
+
+		/* Create request queue */
+		req_id = qla25xx_create_req_que(ha, 0, vp_idx, 0, rsp_id, qos);
+		if (!req_id) {
+			ql_log(ql_log_warn, vha, 0x0186,
+			    "Failed to create request queue.\n");
+			goto fail_req;
+		}
+
+		qpair->req = ha->req_q_map[req_id];
+		qpair->rsp->req = qpair->req;
+
+		if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif) {
+			if (ha->fw_attributes & BIT_4)
+				qpair->difdix_supported = 1;
+		}
+
+		qpair->srb_mempool = mempool_create_slab_pool(SRB_MIN_REQ, srb_cachep);
+		if (!qpair->srb_mempool) {
+			ql_log(ql_log_warn, vha, 0x0191,
+			    "Failed to create srb mempool for qpair %d\n",
+			    qpair->id);
+			goto fail_mempool;
+		}
+
+		/* Mark as online */
+		qpair->online = 1;
+
+		if (!vha->flags.qpairs_available)
+			vha->flags.qpairs_available = 1;
+
+		ql_dbg(ql_dbg_multiq, vha, 0xc00d,
+		    "Request/Response queue pair created, id %d\n",
+		    qpair->id);
+		ql_dbg(ql_dbg_init, vha, 0x0187,
+		    "Request/Response queue pair created, id %d\n",
+		    qpair->id);
+	}
+	return qpair;
+
+fail_mempool:
+fail_req:
+	qla25xx_delete_rsp_que(vha, qpair->rsp);
+fail_rsp:
+	mutex_lock(&ha->mq_lock);
+	qpair->msix->in_use = 0;
+	list_del(&qpair->qp_list_elem);
+	if (list_empty(&vha->qp_list))
+		vha->flags.qpairs_available = 0;
+fail_msix:
+	ha->queue_pair_map[qpair_id] = NULL;
+	clear_bit(qpair_id, ha->qpair_qid_map);
+	mutex_unlock(&ha->mq_lock);
+fail_qid_map:
+	kfree(qpair);
+	return NULL;
+}
+
+int qla2xxx_delete_qpair(struct scsi_qla_host *vha, struct qla_qpair *qpair)
+{
+	int ret;
+	struct qla_hw_data *ha = qpair->hw;
+
+	qpair->delete_in_progress = 1;
+	while (atomic_read(&qpair->ref_count))
+		msleep(500);
+
+	ret = qla25xx_delete_req_que(vha, qpair->req);
+	if (ret != QLA_SUCCESS)
+		goto fail;
+	ret = qla25xx_delete_rsp_que(vha, qpair->rsp);
+	if (ret != QLA_SUCCESS)
+		goto fail;
+
+	mutex_lock(&ha->mq_lock);
+	ha->queue_pair_map[qpair->id] = NULL;
+	clear_bit(qpair->id, ha->qpair_qid_map);
+	list_del(&qpair->qp_list_elem);
+	if (list_empty(&vha->qp_list))
+		vha->flags.qpairs_available = 0;
+	mempool_destroy(qpair->srb_mempool);
+	kfree(qpair);
+	mutex_unlock(&ha->mq_lock);
+
+	return QLA_SUCCESS;
+fail:
+	return ret;
+}
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index edc48f3..44e4045 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -216,6 +216,36 @@ qla2x00_reset_active(scsi_qla_host_t *vha)
 }
 
 static inline srb_t *
+qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag)
+{
+	srb_t *sp = NULL;
+	uint8_t bail;
+
+	QLA_QPAIR_MARK_BUSY(qpair, bail);
+	if (unlikely(bail))
+		return NULL;
+
+	sp = mempool_alloc(qpair->srb_mempool, flag);
+	if (!sp)
+		goto done;
+
+	memset(sp, 0, sizeof(*sp));
+	sp->fcport = fcport;
+	sp->iocbs = 1;
+done:
+	if (!sp)
+		QLA_QPAIR_MARK_NOT_BUSY(qpair);
+	return sp;
+}
+
+static inline void
+qla2xxx_rel_qpair_sp(struct qla_qpair *qpair, srb_t *sp)
+{
+	mempool_free(sp, qpair->srb_mempool);
+	QLA_QPAIR_MARK_NOT_BUSY(qpair);
+}
+
+static inline srb_t *
 qla2x00_get_sp(scsi_qla_host_t *vha, fc_port_t *fcport, gfp_t flag)
 {
 	srb_t *sp = NULL;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 221ad89..58e49a3 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -12,7 +12,6 @@
 
 #include <scsi/scsi_tcq.h>
 
-static void qla25xx_set_que(srb_t *, struct rsp_que **);
 /**
  * qla2x00_get_cmd_direction() - Determine control_flag data direction.
  * @cmd: SCSI command
@@ -143,7 +142,7 @@ qla2x00_prep_cont_type1_iocb(scsi_qla_host_t *vha, struct req_que *req)
 	return (cont_pkt);
 }
 
-static inline int
+inline int
 qla24xx_configure_prot_mode(srb_t *sp, uint16_t *fw_prot_opts)
 {
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
@@ -693,10 +692,11 @@ qla24xx_calc_dsd_lists(uint16_t dsds)
  * @sp: SRB command to process
  * @cmd_pkt: Command type 3 IOCB
  * @tot_dsds: Total number of segments to transfer
+ * @req: pointer to request queue
  */
-static inline void
+inline void
 qla24xx_build_scsi_iocbs(srb_t *sp, struct cmd_type_7 *cmd_pkt,
-    uint16_t tot_dsds)
+	uint16_t tot_dsds, struct req_que *req)
 {
 	uint16_t	avail_dsds;
 	uint32_t	*cur_dsd;
@@ -745,7 +745,7 @@ qla24xx_build_scsi_iocbs(srb_t *sp, struct cmd_type_7 *cmd_pkt,
 			 * Five DSDs are available in the Continuation
 			 * Type 1 IOCB.
 			 */
-			cont_pkt = qla2x00_prep_cont_type1_iocb(vha, vha->req);
+			cont_pkt = qla2x00_prep_cont_type1_iocb(vha, req);
 			cur_dsd = (uint32_t *)cont_pkt->dseg_0_address;
 			avail_dsds = 5;
 		}
@@ -845,24 +845,7 @@ qla24xx_set_t10dif_tags(srb_t *sp, struct fw_dif_context *pkt,
 	}
 }
 
-struct qla2_sgx {
-	dma_addr_t		dma_addr;	/* OUT */
-	uint32_t		dma_len;	/* OUT */
-
-	uint32_t		tot_bytes;	/* IN */
-	struct scatterlist	*cur_sg;	/* IN */
-
-	/* for book keeping, bzero on initial invocation */
-	uint32_t		bytes_consumed;
-	uint32_t		num_bytes;
-	uint32_t		tot_partial;
-
-	/* for debugging */
-	uint32_t		num_sg;
-	srb_t			*sp;
-};
-
-static int
+int
 qla24xx_get_one_block_sg(uint32_t blk_sz, struct qla2_sgx *sgx,
 	uint32_t *partial)
 {
@@ -1207,7 +1190,7 @@ qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
  * @cmd_pkt: Command type 3 IOCB
  * @tot_dsds: Total number of segments to transfer
  */
-static inline int
+inline int
 qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
     uint16_t tot_dsds, uint16_t tot_prot_dsds, uint16_t fw_prot_opts)
 {
@@ -1436,8 +1419,8 @@ qla24xx_start_scsi(srb_t *sp)
 	struct qla_hw_data *ha = vha->hw;
 
 	/* Setup device pointers. */
-	qla25xx_set_que(sp, &rsp);
 	req = vha->req;
+	rsp = req->rsp;
 
 	/* So we know we haven't pci_map'ed anything yet */
 	tot_dsds = 0;
@@ -1523,12 +1506,10 @@ qla24xx_start_scsi(srb_t *sp)
 	cmd_pkt->byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd));
 
 	/* Build IOCB segments */
-	qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds);
+	qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds, req);
 
 	/* Set total data segment count. */
 	cmd_pkt->entry_count = (uint8_t)req_cnt;
-	/* Specify response queue number where completion should happen */
-	cmd_pkt->entry_status = (uint8_t) rsp->id;
 	wmb();
 	/* Adjust ring index. */
 	req->ring_index++;
@@ -1597,9 +1578,8 @@ qla24xx_dif_start_scsi(srb_t *sp)
 	}
 
 	/* Setup device pointers. */
-
-	qla25xx_set_que(sp, &rsp);
 	req = vha->req;
+	rsp = req->rsp;
 
 	/* So we know we haven't pci_map'ed anything yet */
 	tot_dsds = 0;
@@ -1764,18 +1744,365 @@ qla24xx_dif_start_scsi(srb_t *sp)
 	return QLA_FUNCTION_FAILED;
 }
 
-
-static void qla25xx_set_que(srb_t *sp, struct rsp_que **rsp)
+/**
+ * qla2xxx_start_scsi_mq() - Send a SCSI command to the ISP
+ * @sp: command to send to the ISP
+ *
+ * Returns non-zero if a failure occurred, else zero.
+ */
+static int
+qla2xxx_start_scsi_mq(srb_t *sp)
 {
+	int		nseg;
+	unsigned long   flags;
+	uint32_t	*clr_ptr;
+	uint32_t        index;
+	uint32_t	handle;
+	struct cmd_type_7 *cmd_pkt;
+	uint16_t	cnt;
+	uint16_t	req_cnt;
+	uint16_t	tot_dsds;
+	struct req_que *req = NULL;
+	struct rsp_que *rsp = NULL;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
-	struct qla_hw_data *ha = sp->fcport->vha->hw;
-	int affinity = cmd->request->cpu;
+	struct scsi_qla_host *vha = sp->fcport->vha;
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_qpair *qpair = sp->qpair;
 
-	if (ha->flags.cpu_affinity_enabled && affinity >= 0 &&
-		affinity < ha->max_rsp_queues - 1)
-		*rsp = ha->rsp_q_map[affinity + 1];
-	 else
-		*rsp = ha->rsp_q_map[0];
+	/* Setup qpair pointers */
+	rsp = qpair->rsp;
+	req = qpair->req;
+
+	/* So we know we haven't pci_map'ed anything yet */
+	tot_dsds = 0;
+
+	/* Send marker if required */
+	if (vha->marker_needed != 0) {
+		if (qla2x00_marker(vha, req, rsp, 0, 0, MK_SYNC_ALL) !=
+		    QLA_SUCCESS)
+			return QLA_FUNCTION_FAILED;
+		vha->marker_needed = 0;
+	}
+
+	/* Acquire qpair specific lock */
+	spin_lock_irqsave(&qpair->qp_lock, flags);
+
+	/* Check for room in outstanding command list. */
+	handle = req->current_outstanding_cmd;
+	for (index = 1; index < req->num_outstanding_cmds; index++) {
+		handle++;
+		if (handle == req->num_outstanding_cmds)
+			handle = 1;
+		if (!req->outstanding_cmds[handle])
+			break;
+	}
+	if (index == req->num_outstanding_cmds)
+		goto queuing_error;
+
+	/* Map the sg table so we have an accurate count of sg entries needed */
+	if (scsi_sg_count(cmd)) {
+		nseg = dma_map_sg(&ha->pdev->dev, scsi_sglist(cmd),
+		    scsi_sg_count(cmd), cmd->sc_data_direction);
+		if (unlikely(!nseg))
+			goto queuing_error;
+	} else
+		nseg = 0;
+
+	tot_dsds = nseg;
+	req_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
+	if (req->cnt < (req_cnt + 2)) {
+		cnt = IS_SHADOW_REG_CAPABLE(ha) ? *req->out_ptr :
+		    RD_REG_DWORD_RELAXED(req->req_q_out);
+		if (req->ring_index < cnt)
+			req->cnt = cnt - req->ring_index;
+		else
+			req->cnt = req->length -
+				(req->ring_index - cnt);
+		if (req->cnt < (req_cnt + 2))
+			goto queuing_error;
+	}
+
+	/* Build command packet. */
+	req->current_outstanding_cmd = handle;
+	req->outstanding_cmds[handle] = sp;
+	sp->handle = handle;
+	cmd->host_scribble = (unsigned char *)(unsigned long)handle;
+	req->cnt -= req_cnt;
+
+	cmd_pkt = (struct cmd_type_7 *)req->ring_ptr;
+	cmd_pkt->handle = MAKE_HANDLE(req->id, handle);
+
+	/* Zero out remaining portion of packet. */
+	/*    tagged queuing modifier -- default is TSK_SIMPLE (0). */
+	clr_ptr = (uint32_t *)cmd_pkt + 2;
+	memset(clr_ptr, 0, REQUEST_ENTRY_SIZE - 8);
+	cmd_pkt->dseg_count = cpu_to_le16(tot_dsds);
+
+	/* Set NPORT-ID and LUN number*/
+	cmd_pkt->nport_handle = cpu_to_le16(sp->fcport->loop_id);
+	cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa;
+	cmd_pkt->port_id[1] = sp->fcport->d_id.b.area;
+	cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain;
+	cmd_pkt->vp_index = sp->fcport->vha->vp_idx;
+
+	int_to_scsilun(cmd->device->lun, &cmd_pkt->lun);
+	host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun));
+
+	cmd_pkt->task = TSK_SIMPLE;
+
+	/* Load SCSI command packet. */
+	memcpy(cmd_pkt->fcp_cdb, cmd->cmnd, cmd->cmd_len);
+	host_to_fcp_swap(cmd_pkt->fcp_cdb, sizeof(cmd_pkt->fcp_cdb));
+
+	cmd_pkt->byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd));
+
+	/* Build IOCB segments */
+	qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds, req);
+
+	/* Set total data segment count. */
+	cmd_pkt->entry_count = (uint8_t)req_cnt;
+	wmb();
+	/* Adjust ring index. */
+	req->ring_index++;
+	if (req->ring_index == req->length) {
+		req->ring_index = 0;
+		req->ring_ptr = req->ring;
+	} else
+		req->ring_ptr++;
+
+	sp->flags |= SRB_DMA_VALID;
+
+	/* Set chip new ring index. */
+	WRT_REG_DWORD(req->req_q_in, req->ring_index);
+
+	/* Manage unprocessed RIO/ZIO commands in response queue. */
+	if (vha->flags.process_response_queue &&
+		rsp->ring_ptr->signature != RESPONSE_PROCESSED)
+		qla24xx_process_response_queue(vha, rsp);
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+	return QLA_SUCCESS;
+
+queuing_error:
+	if (tot_dsds)
+		scsi_dma_unmap(cmd);
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+
+	return QLA_FUNCTION_FAILED;
+}
+
+
+/**
+ * qla2xxx_dif_start_scsi_mq() - Send a SCSI command to the ISP
+ * @sp: command to send to the ISP
+ *
+ * Returns non-zero if a failure occurred, else zero.
+ */
+int
+qla2xxx_dif_start_scsi_mq(srb_t *sp)
+{
+	int			nseg;
+	unsigned long		flags;
+	uint32_t		*clr_ptr;
+	uint32_t		index;
+	uint32_t		handle;
+	uint16_t		cnt;
+	uint16_t		req_cnt = 0;
+	uint16_t		tot_dsds;
+	uint16_t		tot_prot_dsds;
+	uint16_t		fw_prot_opts = 0;
+	struct req_que		*req = NULL;
+	struct rsp_que		*rsp = NULL;
+	struct scsi_cmnd	*cmd = GET_CMD_SP(sp);
+	struct scsi_qla_host	*vha = sp->fcport->vha;
+	struct qla_hw_data	*ha = vha->hw;
+	struct cmd_type_crc_2	*cmd_pkt;
+	uint32_t		status = 0;
+	struct qla_qpair	*qpair = sp->qpair;
+
+#define QDSS_GOT_Q_SPACE	BIT_0
+
+	/* Check for host side state */
+	if (!qpair->online) {
+		cmd->result = DID_NO_CONNECT << 16;
+		return QLA_INTERFACE_ERROR;
+	}
+
+	if (!qpair->difdix_supported &&
+		scsi_get_prot_op(cmd) != SCSI_PROT_NORMAL) {
+		cmd->result = DID_NO_CONNECT << 16;
+		return QLA_INTERFACE_ERROR;
+	}
+
+	/* Only process protection or >16 cdb in this routine */
+	if (scsi_get_prot_op(cmd) == SCSI_PROT_NORMAL) {
+		if (cmd->cmd_len <= 16)
+			return qla2xxx_start_scsi_mq(sp);
+	}
+
+	/* Setup qpair pointers */
+	rsp = qpair->rsp;
+	req = qpair->req;
+
+	/* So we know we haven't pci_map'ed anything yet */
+	tot_dsds = 0;
+
+	/* Send marker if required */
+	if (vha->marker_needed != 0) {
+		if (qla2x00_marker(vha, req, rsp, 0, 0, MK_SYNC_ALL) !=
+		    QLA_SUCCESS)
+			return QLA_FUNCTION_FAILED;
+		vha->marker_needed = 0;
+	}
+
+	/* Acquire ring specific lock */
+	spin_lock_irqsave(&qpair->qp_lock, flags);
+
+	/* Check for room in outstanding command list. */
+	handle = req->current_outstanding_cmd;
+	for (index = 1; index < req->num_outstanding_cmds; index++) {
+		handle++;
+		if (handle == req->num_outstanding_cmds)
+			handle = 1;
+		if (!req->outstanding_cmds[handle])
+			break;
+	}
+
+	if (index == req->num_outstanding_cmds)
+		goto queuing_error;
+
+	/* Compute number of required data segments */
+	/* Map the sg table so we have an accurate count of sg entries needed */
+	if (scsi_sg_count(cmd)) {
+		nseg = dma_map_sg(&ha->pdev->dev, scsi_sglist(cmd),
+		    scsi_sg_count(cmd), cmd->sc_data_direction);
+		if (unlikely(!nseg))
+			goto queuing_error;
+		else
+			sp->flags |= SRB_DMA_VALID;
+
+		if ((scsi_get_prot_op(cmd) == SCSI_PROT_READ_INSERT) ||
+		    (scsi_get_prot_op(cmd) == SCSI_PROT_WRITE_STRIP)) {
+			struct qla2_sgx sgx;
+			uint32_t	partial;
+
+			memset(&sgx, 0, sizeof(struct qla2_sgx));
+			sgx.tot_bytes = scsi_bufflen(cmd);
+			sgx.cur_sg = scsi_sglist(cmd);
+			sgx.sp = sp;
+
+			nseg = 0;
+			while (qla24xx_get_one_block_sg(
+			    cmd->device->sector_size, &sgx, &partial))
+				nseg++;
+		}
+	} else
+		nseg = 0;
+
+	/* number of required data segments */
+	tot_dsds = nseg;
+
+	/* Compute number of required protection segments */
+	if (qla24xx_configure_prot_mode(sp, &fw_prot_opts)) {
+		nseg = dma_map_sg(&ha->pdev->dev, scsi_prot_sglist(cmd),
+		    scsi_prot_sg_count(cmd), cmd->sc_data_direction);
+		if (unlikely(!nseg))
+			goto queuing_error;
+		else
+			sp->flags |= SRB_CRC_PROT_DMA_VALID;
+
+		if ((scsi_get_prot_op(cmd) == SCSI_PROT_READ_INSERT) ||
+		    (scsi_get_prot_op(cmd) == SCSI_PROT_WRITE_STRIP)) {
+			nseg = scsi_bufflen(cmd) / cmd->device->sector_size;
+		}
+	} else {
+		nseg = 0;
+	}
+
+	req_cnt = 1;
+	/* Total Data and protection sg segment(s) */
+	tot_prot_dsds = nseg;
+	tot_dsds += nseg;
+	if (req->cnt < (req_cnt + 2)) {
+		cnt = IS_SHADOW_REG_CAPABLE(ha) ? *req->out_ptr :
+		    RD_REG_DWORD_RELAXED(req->req_q_out);
+		if (req->ring_index < cnt)
+			req->cnt = cnt - req->ring_index;
+		else
+			req->cnt = req->length -
+				(req->ring_index - cnt);
+		if (req->cnt < (req_cnt + 2))
+			goto queuing_error;
+	}
+
+	status |= QDSS_GOT_Q_SPACE;
+
+	/* Build header part of command packet (excluding the OPCODE). */
+	req->current_outstanding_cmd = handle;
+	req->outstanding_cmds[handle] = sp;
+	sp->handle = handle;
+	cmd->host_scribble = (unsigned char *)(unsigned long)handle;
+	req->cnt -= req_cnt;
+
+	/* Fill-in common area */
+	cmd_pkt = (struct cmd_type_crc_2 *)req->ring_ptr;
+	cmd_pkt->handle = MAKE_HANDLE(req->id, handle);
+
+	clr_ptr = (uint32_t *)cmd_pkt + 2;
+	memset(clr_ptr, 0, REQUEST_ENTRY_SIZE - 8);
+
+	/* Set NPORT-ID and LUN number*/
+	cmd_pkt->nport_handle = cpu_to_le16(sp->fcport->loop_id);
+	cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa;
+	cmd_pkt->port_id[1] = sp->fcport->d_id.b.area;
+	cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain;
+
+	int_to_scsilun(cmd->device->lun, &cmd_pkt->lun);
+	host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun));
+
+	/* Total Data and protection segment(s) */
+	cmd_pkt->dseg_count = cpu_to_le16(tot_dsds);
+
+	/* Build IOCB segments and adjust for data protection segments */
+	if (qla24xx_build_scsi_crc_2_iocbs(sp, (struct cmd_type_crc_2 *)
+	    req->ring_ptr, tot_dsds, tot_prot_dsds, fw_prot_opts) !=
+		QLA_SUCCESS)
+		goto queuing_error;
+
+	cmd_pkt->entry_count = (uint8_t)req_cnt;
+	cmd_pkt->timeout = cpu_to_le16(0);
+	wmb();
+
+	/* Adjust ring index. */
+	req->ring_index++;
+	if (req->ring_index == req->length) {
+		req->ring_index = 0;
+		req->ring_ptr = req->ring;
+	} else
+		req->ring_ptr++;
+
+	/* Set chip new ring index. */
+	WRT_REG_DWORD(req->req_q_in, req->ring_index);
+
+	/* Manage unprocessed RIO/ZIO commands in response queue. */
+	if (vha->flags.process_response_queue &&
+	    rsp->ring_ptr->signature != RESPONSE_PROCESSED)
+		qla24xx_process_response_queue(vha, rsp);
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+
+	return QLA_SUCCESS;
+
+queuing_error:
+	if (status & QDSS_GOT_Q_SPACE) {
+		req->outstanding_cmds[handle] = NULL;
+		req->cnt += req_cnt;
+	}
+	/* Cleanup will be performed by the caller (queuecommand) */
+
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
+	return QLA_FUNCTION_FAILED;
 }
 
 /* Generic Control-SRB manipulation functions. */
@@ -2664,7 +2991,7 @@ qla82xx_start_scsi(srb_t *sp)
 		cmd_pkt->byte_count = cpu_to_le32((uint32_t)scsi_bufflen(cmd));
 
 		/* Build IOCB segments */
-		qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds);
+		qla24xx_build_scsi_iocbs(sp, cmd_pkt, tot_dsds, req);
 
 		/* Set total data segment count. */
 		cmd_pkt->entry_count = (uint8_t)req_cnt;
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 19f1848..5093ca9 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -9,6 +9,7 @@
 
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/t10-pi.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/scsi_bsg_fc.h>
 #include <scsi/scsi_eh.h>
@@ -2871,41 +2872,6 @@ qla24xx_msix_rsp_q(int irq, void *dev_id)
 }
 
 static irqreturn_t
-qla25xx_msix_rsp_q(int irq, void *dev_id)
-{
-	struct qla_hw_data *ha;
-	scsi_qla_host_t *vha;
-	struct rsp_que *rsp;
-	struct device_reg_24xx __iomem *reg;
-	unsigned long flags;
-	uint32_t hccr = 0;
-
-	rsp = (struct rsp_que *) dev_id;
-	if (!rsp) {
-		ql_log(ql_log_info, NULL, 0x505b,
-		    "%s: NULL response queue pointer.\n", __func__);
-		return IRQ_NONE;
-	}
-	ha = rsp->hw;
-	vha = pci_get_drvdata(ha->pdev);
-
-	/* Clear the interrupt, if enabled, for this response queue */
-	if (!ha->flags.disable_msix_handshake) {
-		reg = &ha->iobase->isp24;
-		spin_lock_irqsave(&ha->hardware_lock, flags);
-		WRT_REG_DWORD(&reg->hccr, HCCRX_CLR_RISC_INT);
-		hccr = RD_REG_DWORD_RELAXED(&reg->hccr);
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
-	}
-	if (qla2x00_check_reg32_for_disconnect(vha, hccr))
-		goto out;
-	queue_work_on((int) (rsp->id - 1), ha->wq, &rsp->q_work);
-
-out:
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t
 qla24xx_msix_default(int irq, void *dev_id)
 {
 	scsi_qla_host_t	*vha;
@@ -3001,6 +2967,35 @@ qla24xx_msix_default(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+irqreturn_t
+qla2xxx_msix_rsp_q(int irq, void *dev_id)
+{
+	struct qla_hw_data *ha;
+	struct qla_qpair *qpair;
+	struct device_reg_24xx __iomem *reg;
+	unsigned long flags;
+
+	qpair = dev_id;
+	if (!qpair) {
+		ql_log(ql_log_info, NULL, 0x505b,
+		    "%s: NULL response queue pointer.\n", __func__);
+		return IRQ_NONE;
+	}
+	ha = qpair->hw;
+
+	/* Clear the interrupt, if enabled, for this response queue */
+	if (unlikely(!ha->flags.disable_msix_handshake)) {
+		reg = &ha->iobase->isp24;
+		spin_lock_irqsave(&ha->hardware_lock, flags);
+		WRT_REG_DWORD(&reg->hccr, HCCRX_CLR_RISC_INT);
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+	}
+
+	queue_work(ha->wq, &qpair->q_work);
+
+	return IRQ_HANDLED;
+}
+
 /* Interrupt handling helpers. */
 
 struct qla_init_msix_entry {
@@ -3008,69 +3003,28 @@ struct qla_init_msix_entry {
 	irq_handler_t handler;
 };
 
-static struct qla_init_msix_entry msix_entries[3] = {
-	{ "qla2xxx (default)", qla24xx_msix_default },
-	{ "qla2xxx (rsp_q)", qla24xx_msix_rsp_q },
-	{ "qla2xxx (multiq)", qla25xx_msix_rsp_q },
-};
-
-static struct qla_init_msix_entry qla82xx_msix_entries[2] = {
-	{ "qla2xxx (default)", qla82xx_msix_default },
-	{ "qla2xxx (rsp_q)", qla82xx_msix_rsp_q },
-};
-
-static struct qla_init_msix_entry qla83xx_msix_entries[3] = {
+static struct qla_init_msix_entry msix_entries[] = {
 	{ "qla2xxx (default)", qla24xx_msix_default },
 	{ "qla2xxx (rsp_q)", qla24xx_msix_rsp_q },
 	{ "qla2xxx (atio_q)", qla83xx_msix_atio_q },
+	{ "qla2xxx (qpair_multiq)", qla2xxx_msix_rsp_q },
 };
 
-static void
-qla24xx_disable_msix(struct qla_hw_data *ha)
-{
-	int i;
-	struct qla_msix_entry *qentry;
-	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
-
-	for (i = 0; i < ha->msix_count; i++) {
-		qentry = &ha->msix_entries[i];
-		if (qentry->have_irq) {
-			/* un-register irq cpu affinity notification */
-			irq_set_affinity_notifier(qentry->vector, NULL);
-			free_irq(qentry->vector, qentry->rsp);
-		}
-	}
-	pci_disable_msix(ha->pdev);
-	kfree(ha->msix_entries);
-	ha->msix_entries = NULL;
-	ha->flags.msix_enabled = 0;
-	ql_dbg(ql_dbg_init, vha, 0x0042,
-	    "Disabled the MSI.\n");
-}
+static struct qla_init_msix_entry qla82xx_msix_entries[] = {
+	{ "qla2xxx (default)", qla82xx_msix_default },
+	{ "qla2xxx (rsp_q)", qla82xx_msix_rsp_q },
+};
 
 static int
 qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 {
 #define MIN_MSIX_COUNT	2
-#define ATIO_VECTOR	2
 	int i, ret;
-	struct msix_entry *entries;
 	struct qla_msix_entry *qentry;
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 
-	entries = kzalloc(sizeof(struct msix_entry) * ha->msix_count,
-			GFP_KERNEL);
-	if (!entries) {
-		ql_log(ql_log_warn, vha, 0x00bc,
-		    "Failed to allocate memory for msix_entry.\n");
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < ha->msix_count; i++)
-		entries[i].entry = i;
-
-	ret = pci_enable_msix_range(ha->pdev,
-				    entries, MIN_MSIX_COUNT, ha->msix_count);
+	ret = pci_alloc_irq_vectors(ha->pdev, MIN_MSIX_COUNT, ha->msix_count,
+				    PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
 	if (ret < 0) {
 		ql_log(ql_log_fatal, vha, 0x00c7,
 		    "MSI-X: Failed to enable support, "
@@ -3080,10 +3034,23 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	} else if (ret < ha->msix_count) {
 		ql_log(ql_log_warn, vha, 0x00c6,
 		    "MSI-X: Failed to enable support "
-		    "-- %d/%d\n Retry with %d vectors.\n",
-		    ha->msix_count, ret, ret);
+		     "with %d vectors, using %d vectors.\n",
+		    ha->msix_count, ret);
 		ha->msix_count = ret;
-		ha->max_rsp_queues = ha->msix_count - 1;
+		/* Recalculate queue values */
+		if (ha->mqiobase && ql2xmqsupport) {
+			ha->max_req_queues = ha->msix_count - 1;
+
+			/* ATIOQ needs 1 vector. That's 1 less QPair */
+			if (QLA_TGT_MODE_ENABLED())
+				ha->max_req_queues--;
+
+			ha->max_rsp_queues = ha->max_req_queues;
+
+			ha->max_qpairs = ha->max_req_queues - 1;
+			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0190,
+			    "Adjusted Max no of queues pairs: %d.\n", ha->max_qpairs);
+		}
 	}
 	ha->msix_entries = kzalloc(sizeof(struct qla_msix_entry) *
 				ha->msix_count, GFP_KERNEL);
@@ -3097,20 +3064,23 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 
 	for (i = 0; i < ha->msix_count; i++) {
 		qentry = &ha->msix_entries[i];
-		qentry->vector = entries[i].vector;
-		qentry->entry = entries[i].entry;
+		qentry->vector = pci_irq_vector(ha->pdev, i);
+		qentry->entry = i;
 		qentry->have_irq = 0;
-		qentry->rsp = NULL;
+		qentry->in_use = 0;
+		qentry->handle = NULL;
 		qentry->irq_notify.notify  = qla_irq_affinity_notify;
 		qentry->irq_notify.release = qla_irq_affinity_release;
 		qentry->cpuid = -1;
 	}
 
 	/* Enable MSI-X vectors for the base queue */
-	for (i = 0; i < 2; i++) {
+	for (i = 0; i < (QLA_MSIX_RSP_Q + 1); i++) {
 		qentry = &ha->msix_entries[i];
-		qentry->rsp = rsp;
+		qentry->handle = rsp;
 		rsp->msix = qentry;
+		scnprintf(qentry->name, sizeof(qentry->name),
+		    msix_entries[i].name);
 		if (IS_P3P_TYPE(ha))
 			ret = request_irq(qentry->vector,
 				qla82xx_msix_entries[i].handler,
@@ -3122,6 +3092,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		if (ret)
 			goto msix_register_fail;
 		qentry->have_irq = 1;
+		qentry->in_use = 1;
 
 		/* Register for CPU affinity notification. */
 		irq_set_affinity_notifier(qentry->vector, &qentry->irq_notify);
@@ -3141,12 +3112,15 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	 * queue.
 	 */
 	if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
-		qentry = &ha->msix_entries[ATIO_VECTOR];
-		qentry->rsp = rsp;
+		qentry = &ha->msix_entries[QLA_ATIO_VECTOR];
 		rsp->msix = qentry;
+		qentry->handle = rsp;
+		scnprintf(qentry->name, sizeof(qentry->name),
+		    msix_entries[QLA_ATIO_VECTOR].name);
+		qentry->in_use = 1;
 		ret = request_irq(qentry->vector,
-			qla83xx_msix_entries[ATIO_VECTOR].handler,
-			0, qla83xx_msix_entries[ATIO_VECTOR].name, rsp);
+			msix_entries[QLA_ATIO_VECTOR].handler,
+			0, msix_entries[QLA_ATIO_VECTOR].name, rsp);
 		qentry->have_irq = 1;
 	}
 
@@ -3155,7 +3129,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		ql_log(ql_log_fatal, vha, 0x00cb,
 		    "MSI-X: unable to register handler -- %x/%d.\n",
 		    qentry->vector, ret);
-		qla24xx_disable_msix(ha);
+		qla2x00_free_irqs(vha);
 		ha->mqenable = 0;
 		goto msix_out;
 	}
@@ -3163,11 +3137,13 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	/* Enable MSI-X vector for response queue update for queue 0 */
 	if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 		if (ha->msixbase && ha->mqiobase &&
-		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1))
+		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1 ||
+		     ql2xmqsupport))
 			ha->mqenable = 1;
 	} else
-		if (ha->mqiobase
-		    && (ha->max_rsp_queues > 1 || ha->max_req_queues > 1))
+		if (ha->mqiobase &&
+		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1 ||
+		     ql2xmqsupport))
 			ha->mqenable = 1;
 	ql_dbg(ql_dbg_multiq, vha, 0xc005,
 	    "mqiobase=%p, max_rsp_queues=%d, max_req_queues=%d.\n",
@@ -3177,7 +3153,6 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 	    ha->mqiobase, ha->max_rsp_queues, ha->max_req_queues);
 
 msix_out:
-	kfree(entries);
 	return ret;
 }
 
@@ -3230,7 +3205,7 @@ qla2x00_request_irqs(struct qla_hw_data *ha, struct rsp_que *rsp)
 	    !IS_QLA27XX(ha))
 		goto skip_msi;
 
-	ret = pci_enable_msi(ha->pdev);
+	ret = pci_alloc_irq_vectors(ha->pdev, 1, 1, PCI_IRQ_MSI);
 	if (!ret) {
 		ql_dbg(ql_dbg_init, vha, 0x0038,
 		    "MSI: Enabled.\n");
@@ -3275,6 +3250,8 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
 	struct rsp_que *rsp;
+	struct qla_msix_entry *qentry;
+	int i;
 
 	/*
 	 * We need to check that ha->rsp_q_map is valid in case we are called
@@ -3284,25 +3261,36 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 		return;
 	rsp = ha->rsp_q_map[0];
 
-	if (ha->flags.msix_enabled)
-		qla24xx_disable_msix(ha);
-	else if (ha->flags.msi_enabled) {
-		free_irq(ha->pdev->irq, rsp);
-		pci_disable_msi(ha->pdev);
-	} else
-		free_irq(ha->pdev->irq, rsp);
+	if (ha->flags.msix_enabled) {
+		for (i = 0; i < ha->msix_count; i++) {
+			qentry = &ha->msix_entries[i];
+			if (qentry->have_irq) {
+				irq_set_affinity_notifier(qentry->vector, NULL);
+				free_irq(pci_irq_vector(ha->pdev, i), qentry->handle);
+			}
+		}
+		kfree(ha->msix_entries);
+		ha->msix_entries = NULL;
+		ha->flags.msix_enabled = 0;
+		ql_dbg(ql_dbg_init, vha, 0x0042,
+			"Disabled MSI-X.\n");
+	} else {
+		free_irq(pci_irq_vector(ha->pdev, 0), rsp);
+	}
+
+	pci_free_irq_vectors(ha->pdev);
 }
 
-
-int qla25xx_request_irq(struct rsp_que *rsp)
+int qla25xx_request_irq(struct qla_hw_data *ha, struct qla_qpair *qpair,
+	struct qla_msix_entry *msix, int vector_type)
 {
-	struct qla_hw_data *ha = rsp->hw;
-	struct qla_init_msix_entry *intr = &msix_entries[2];
-	struct qla_msix_entry *msix = rsp->msix;
+	struct qla_init_msix_entry *intr = &msix_entries[vector_type];
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 	int ret;
 
-	ret = request_irq(msix->vector, intr->handler, 0, intr->name, rsp);
+	scnprintf(msix->name, sizeof(msix->name),
+	    "qla2xxx%lu_qpair%d", vha->host_no, qpair->id);
+	ret = request_irq(msix->vector, intr->handler, 0, msix->name, qpair);
 	if (ret) {
 		ql_log(ql_log_fatal, vha, 0x00e6,
 		    "MSI-X: Unable to register handler -- %x/%d.\n",
@@ -3310,7 +3298,7 @@ int qla25xx_request_irq(struct rsp_que *rsp)
 		return ret;
 	}
 	msix->have_irq = 1;
-	msix->rsp = rsp;
+	msix->handle = qpair;
 	return ret;
 }
 
@@ -3323,11 +3311,12 @@ static void qla_irq_affinity_notify(struct irq_affinity_notify *notify,
 		container_of(notify, struct qla_msix_entry, irq_notify);
 	struct qla_hw_data *ha;
 	struct scsi_qla_host *base_vha;
+	struct rsp_que *rsp = e->handle;
 
 	/* user is recommended to set mask to just 1 cpu */
 	e->cpuid = cpumask_first(mask);
 
-	ha = e->rsp->hw;
+	ha = rsp->hw;
 	base_vha = pci_get_drvdata(ha->pdev);
 
 	ql_dbg(ql_dbg_init, base_vha, 0xffff,
@@ -3351,9 +3340,10 @@ static void qla_irq_affinity_release(struct kref *ref)
 		container_of(ref, struct irq_affinity_notify, kref);
 	struct qla_msix_entry *e =
 		container_of(notify, struct qla_msix_entry, irq_notify);
-	struct scsi_qla_host *base_vha = pci_get_drvdata(e->rsp->hw->pdev);
+	struct rsp_que *rsp = e->handle;
+	struct scsi_qla_host *base_vha = pci_get_drvdata(rsp->hw->pdev);
 
 	ql_dbg(ql_dbg_init, base_vha, 0xffff,
-	    "%s: host%ld: vector %d cpu %d \n", __func__,
+		"%s: host%ld: vector %d cpu %d\n", __func__,
 	    base_vha->host_no, e->vector, e->cpuid);
 }
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 23698c9..2819ceb 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -10,6 +10,43 @@
 #include <linux/delay.h>
 #include <linux/gfp.h>
 
+struct rom_cmd {
+	uint16_t cmd;
+} rom_cmds[] = {
+	{ MBC_LOAD_RAM },
+	{ MBC_EXECUTE_FIRMWARE },
+	{ MBC_READ_RAM_WORD },
+	{ MBC_MAILBOX_REGISTER_TEST },
+	{ MBC_VERIFY_CHECKSUM },
+	{ MBC_GET_FIRMWARE_VERSION },
+	{ MBC_LOAD_RISC_RAM },
+	{ MBC_DUMP_RISC_RAM },
+	{ MBC_LOAD_RISC_RAM_EXTENDED },
+	{ MBC_DUMP_RISC_RAM_EXTENDED },
+	{ MBC_WRITE_RAM_WORD_EXTENDED },
+	{ MBC_READ_RAM_EXTENDED },
+	{ MBC_GET_RESOURCE_COUNTS },
+	{ MBC_SET_FIRMWARE_OPTION },
+	{ MBC_MID_INITIALIZE_FIRMWARE },
+	{ MBC_GET_FIRMWARE_STATE },
+	{ MBC_GET_MEM_OFFLOAD_CNTRL_STAT },
+	{ MBC_GET_RETRY_COUNT },
+	{ MBC_TRACE_CONTROL },
+};
+
+static int is_rom_cmd(uint16_t cmd)
+{
+	int i;
+	struct  rom_cmd *wc;
+
+	for (i = 0; i < ARRAY_SIZE(rom_cmds); i++) {
+		wc = rom_cmds + i;
+		if (wc->cmd == cmd)
+			return 1;
+	}
+
+	return 0;
+}
 
 /*
  * qla2x00_mailbox_command
@@ -92,6 +129,17 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		return QLA_FUNCTION_TIMEOUT;
 	}
 
+	/* check if ISP abort is active and return cmd with timeout */
+	if ((test_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags) ||
+	    test_bit(ISP_ABORT_RETRY, &base_vha->dpc_flags) ||
+	    test_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags)) &&
+	    !is_rom_cmd(mcp->mb[0])) {
+		ql_log(ql_log_info, vha, 0x1005,
+		    "Cmd 0x%x aborted with timeout since ISP Abort is pending\n",
+		    mcp->mb[0]);
+		return QLA_FUNCTION_TIMEOUT;
+	}
+
 	/*
 	 * Wait for active mailbox commands to finish by waiting at most tov
 	 * seconds. This is to serialize actual issuing of mailbox cmds during
@@ -178,6 +226,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			WRT_REG_WORD(&reg->isp.hccr, HCCR_SET_HOST_INT);
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
+		wait_time = jiffies;
 		if (!wait_for_completion_timeout(&ha->mbx_intr_comp,
 		    mcp->tov * HZ)) {
 			ql_dbg(ql_dbg_mbx, vha, 0x117a,
@@ -186,6 +235,9 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		}
+		if (time_after(jiffies, wait_time + 5 * HZ))
+			ql_log(ql_log_warn, vha, 0x1015, "cmd=0x%x, waited %d msecs\n",
+			    command, jiffies_to_msecs(jiffies - wait_time));
 	} else {
 		ql_dbg(ql_dbg_mbx, vha, 0x1011,
 		    "Cmd=%x Polling Mode.\n", command);
@@ -1194,12 +1246,17 @@ qla2x00_abort_command(srb_t *sp)
 	fc_port_t	*fcport = sp->fcport;
 	scsi_qla_host_t *vha = fcport->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct req_que *req = vha->req;
+	struct req_que *req;
 	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
 
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x103b,
 	    "Entered %s.\n", __func__);
 
+	if (vha->flags.qpairs_available && sp->qpair)
+		req = sp->qpair->req;
+	else
+		req = vha->req;
+
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (handle = 1; handle < req->num_outstanding_cmds; handle++) {
 		if (req->outstanding_cmds[handle] == sp)
@@ -2152,10 +2209,10 @@ qla24xx_login_fabric(scsi_qla_host_t *vha, uint16_t loop_id, uint8_t domain,
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1061,
 	    "Entered %s.\n", __func__);
 
-	if (ha->flags.cpu_affinity_enabled)
-		req = ha->req_q_map[0];
+	if (vha->vp_idx && vha->qpair)
+		req = vha->qpair->req;
 	else
-		req = vha->req;
+		req = ha->req_q_map[0];
 
 	lg = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &lg_dma);
 	if (lg == NULL) {
@@ -2435,10 +2492,7 @@ qla24xx_fabric_logout(scsi_qla_host_t *vha, uint16_t loop_id, uint8_t domain,
 	}
 	memset(lg, 0, sizeof(struct logio_entry_24xx));
 
-	if (ql2xmaxqueues > 1)
-		req = ha->req_q_map[0];
-	else
-		req = vha->req;
+	req = vha->req;
 	lg->entry_type = LOGINOUT_PORT_IOCB_TYPE;
 	lg->entry_count = 1;
 	lg->handle = MAKE_HANDLE(req->id, lg->handle);
@@ -2904,6 +2958,9 @@ qla24xx_abort_command(srb_t *sp)
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x108c,
 	    "Entered %s.\n", __func__);
 
+	if (vha->flags.qpairs_available && sp->qpair)
+		req = sp->qpair->req;
+
 	if (ql2xasynctmfenable)
 		return qla24xx_async_abort_command(sp);
 
@@ -2984,6 +3041,7 @@ __qla24xx_issue_tmf(char *name, uint32_t type, struct fc_port *fcport,
 	struct qla_hw_data *ha;
 	struct req_que *req;
 	struct rsp_que *rsp;
+	struct qla_qpair *qpair;
 
 	vha = fcport->vha;
 	ha = vha->hw;
@@ -2992,10 +3050,15 @@ __qla24xx_issue_tmf(char *name, uint32_t type, struct fc_port *fcport,
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1092,
 	    "Entered %s.\n", __func__);
 
-	if (ha->flags.cpu_affinity_enabled)
-		rsp = ha->rsp_q_map[tag + 1];
-	else
+	if (vha->vp_idx && vha->qpair) {
+		/* NPIV port */
+		qpair = vha->qpair;
+		rsp = qpair->rsp;
+		req = qpair->req;
+	} else {
 		rsp = req->rsp;
+	}
+
 	tsk = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &tsk_dma);
 	if (tsk == NULL) {
 		ql_log(ql_log_warn, vha, 0x1093,
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index cf7ba52..c6d6f0d 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -540,9 +540,10 @@ qla25xx_free_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp)
 	uint16_t que_id = rsp->id;
 
 	if (rsp->msix && rsp->msix->have_irq) {
-		free_irq(rsp->msix->vector, rsp);
+		free_irq(rsp->msix->vector, rsp->msix->handle);
 		rsp->msix->have_irq = 0;
-		rsp->msix->rsp = NULL;
+		rsp->msix->in_use = 0;
+		rsp->msix->handle = NULL;
 	}
 	dma_free_coherent(&ha->pdev->dev, (rsp->length + 1) *
 		sizeof(response_t), rsp->ring, rsp->dma);
@@ -573,7 +574,7 @@ qla25xx_delete_req_que(struct scsi_qla_host *vha, struct req_que *req)
 	return ret;
 }
 
-static int
+int
 qla25xx_delete_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp)
 {
 	int ret = -1;
@@ -596,34 +597,42 @@ qla25xx_delete_queues(struct scsi_qla_host *vha)
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
 	struct qla_hw_data *ha = vha->hw;
+	struct qla_qpair *qpair, *tqpair;
 
-	/* Delete request queues */
-	for (cnt = 1; cnt < ha->max_req_queues; cnt++) {
-		req = ha->req_q_map[cnt];
-		if (req && test_bit(cnt, ha->req_qid_map)) {
-			ret = qla25xx_delete_req_que(vha, req);
-			if (ret != QLA_SUCCESS) {
-				ql_log(ql_log_warn, vha, 0x00ea,
-				    "Couldn't delete req que %d.\n",
-				    req->id);
-				return ret;
+	if (ql2xmqsupport) {
+		list_for_each_entry_safe(qpair, tqpair, &vha->qp_list,
+		    qp_list_elem)
+			qla2xxx_delete_qpair(vha, qpair);
+	} else {
+		/* Delete request queues */
+		for (cnt = 1; cnt < ha->max_req_queues; cnt++) {
+			req = ha->req_q_map[cnt];
+			if (req && test_bit(cnt, ha->req_qid_map)) {
+				ret = qla25xx_delete_req_que(vha, req);
+				if (ret != QLA_SUCCESS) {
+					ql_log(ql_log_warn, vha, 0x00ea,
+					    "Couldn't delete req que %d.\n",
+					    req->id);
+					return ret;
+				}
+			}
+		}
+
+		/* Delete response queues */
+		for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) {
+			rsp = ha->rsp_q_map[cnt];
+			if (rsp && test_bit(cnt, ha->rsp_qid_map)) {
+				ret = qla25xx_delete_rsp_que(vha, rsp);
+				if (ret != QLA_SUCCESS) {
+					ql_log(ql_log_warn, vha, 0x00eb,
+					    "Couldn't delete rsp que %d.\n",
+					    rsp->id);
+					return ret;
+				}
 			}
 		}
 	}
 
-	/* Delete response queues */
-	for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) {
-		rsp = ha->rsp_q_map[cnt];
-		if (rsp && test_bit(cnt, ha->rsp_qid_map)) {
-			ret = qla25xx_delete_rsp_que(vha, rsp);
-			if (ret != QLA_SUCCESS) {
-				ql_log(ql_log_warn, vha, 0x00eb,
-				    "Couldn't delete rsp que %d.\n",
-				    rsp->id);
-				return ret;
-			}
-		}
-	}
 	return ret;
 }
 
@@ -659,10 +668,10 @@ qla25xx_create_req_que(struct qla_hw_data *ha, uint16_t options,
 	if (ret != QLA_SUCCESS)
 		goto que_failed;
 
-	mutex_lock(&ha->vport_lock);
+	mutex_lock(&ha->mq_lock);
 	que_id = find_first_zero_bit(ha->req_qid_map, ha->max_req_queues);
 	if (que_id >= ha->max_req_queues) {
-		mutex_unlock(&ha->vport_lock);
+		mutex_unlock(&ha->mq_lock);
 		ql_log(ql_log_warn, base_vha, 0x00db,
 		    "No resources to create additional request queue.\n");
 		goto que_failed;
@@ -708,7 +717,7 @@ qla25xx_create_req_que(struct qla_hw_data *ha, uint16_t options,
 	req->req_q_out = &reg->isp25mq.req_q_out;
 	req->max_q_depth = ha->req_q_map[0]->max_q_depth;
 	req->out_ptr = (void *)(req->ring + req->length);
-	mutex_unlock(&ha->vport_lock);
+	mutex_unlock(&ha->mq_lock);
 	ql_dbg(ql_dbg_multiq, base_vha, 0xc004,
 	    "ring_ptr=%p ring_index=%d, "
 	    "cnt=%d id=%d max_q_depth=%d.\n",
@@ -724,9 +733,9 @@ qla25xx_create_req_que(struct qla_hw_data *ha, uint16_t options,
 	if (ret != QLA_SUCCESS) {
 		ql_log(ql_log_fatal, base_vha, 0x00df,
 		    "%s failed.\n", __func__);
-		mutex_lock(&ha->vport_lock);
+		mutex_lock(&ha->mq_lock);
 		clear_bit(que_id, ha->req_qid_map);
-		mutex_unlock(&ha->vport_lock);
+		mutex_unlock(&ha->mq_lock);
 		goto que_failed;
 	}
 
@@ -741,20 +750,20 @@ qla25xx_create_req_que(struct qla_hw_data *ha, uint16_t options,
 static void qla_do_work(struct work_struct *work)
 {
 	unsigned long flags;
-	struct rsp_que *rsp = container_of(work, struct rsp_que, q_work);
+	struct qla_qpair *qpair = container_of(work, struct qla_qpair, q_work);
 	struct scsi_qla_host *vha;
-	struct qla_hw_data *ha = rsp->hw;
+	struct qla_hw_data *ha = qpair->hw;
 
-	spin_lock_irqsave(&rsp->hw->hardware_lock, flags);
+	spin_lock_irqsave(&qpair->qp_lock, flags);
 	vha = pci_get_drvdata(ha->pdev);
-	qla24xx_process_response_queue(vha, rsp);
-	spin_unlock_irqrestore(&rsp->hw->hardware_lock, flags);
+	qla24xx_process_response_queue(vha, qpair->rsp);
+	spin_unlock_irqrestore(&qpair->qp_lock, flags);
 }
 
 /* create response queue */
 int
 qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options,
-	uint8_t vp_idx, uint16_t rid, int req)
+	uint8_t vp_idx, uint16_t rid, struct qla_qpair *qpair)
 {
 	int ret = 0;
 	struct rsp_que *rsp = NULL;
@@ -779,28 +788,24 @@ qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options,
 		goto que_failed;
 	}
 
-	mutex_lock(&ha->vport_lock);
+	mutex_lock(&ha->mq_lock);
 	que_id = find_first_zero_bit(ha->rsp_qid_map, ha->max_rsp_queues);
 	if (que_id >= ha->max_rsp_queues) {
-		mutex_unlock(&ha->vport_lock);
+		mutex_unlock(&ha->mq_lock);
 		ql_log(ql_log_warn, base_vha, 0x00e2,
 		    "No resources to create additional request queue.\n");
 		goto que_failed;
 	}
 	set_bit(que_id, ha->rsp_qid_map);
 
-	if (ha->flags.msix_enabled)
-		rsp->msix = &ha->msix_entries[que_id + 1];
-	else
-		ql_log(ql_log_warn, base_vha, 0x00e3,
-		    "MSIX not enabled.\n");
+	rsp->msix = qpair->msix;
 
 	ha->rsp_q_map[que_id] = rsp;
 	rsp->rid = rid;
 	rsp->vp_idx = vp_idx;
 	rsp->hw = ha;
 	ql_dbg(ql_dbg_init, base_vha, 0x00e4,
-	    "queue_id=%d rid=%d vp_idx=%d hw=%p.\n",
+	    "rsp queue_id=%d rid=%d vp_idx=%d hw=%p.\n",
 	    que_id, rsp->rid, rsp->vp_idx, rsp->hw);
 	/* Use alternate PCI bus number */
 	if (MSB(rsp->rid))
@@ -812,23 +817,27 @@ qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options,
 	if (!IS_MSIX_NACK_CAPABLE(ha))
 		options |= BIT_6;
 
+	/* Set option to indicate response queue creation */
+	options |= BIT_1;
+
 	rsp->options = options;
 	rsp->id = que_id;
 	reg = ISP_QUE_REG(ha, que_id);
 	rsp->rsp_q_in = &reg->isp25mq.rsp_q_in;
 	rsp->rsp_q_out = &reg->isp25mq.rsp_q_out;
 	rsp->in_ptr = (void *)(rsp->ring + rsp->length);
-	mutex_unlock(&ha->vport_lock);
+	mutex_unlock(&ha->mq_lock);
 	ql_dbg(ql_dbg_multiq, base_vha, 0xc00b,
-	    "options=%x id=%d rsp_q_in=%p rsp_q_out=%p",
+	    "options=%x id=%d rsp_q_in=%p rsp_q_out=%p\n",
 	    rsp->options, rsp->id, rsp->rsp_q_in,
 	    rsp->rsp_q_out);
 	ql_dbg(ql_dbg_init, base_vha, 0x00e5,
-	    "options=%x id=%d rsp_q_in=%p rsp_q_out=%p",
+	    "options=%x id=%d rsp_q_in=%p rsp_q_out=%p\n",
 	    rsp->options, rsp->id, rsp->rsp_q_in,
 	    rsp->rsp_q_out);
 
-	ret = qla25xx_request_irq(rsp);
+	ret = qla25xx_request_irq(ha, qpair, qpair->msix,
+	    QLA_MSIX_QPAIR_MULTIQ_RSP_Q);
 	if (ret)
 		goto que_failed;
 
@@ -836,19 +845,16 @@ qla25xx_create_rsp_que(struct qla_hw_data *ha, uint16_t options,
 	if (ret != QLA_SUCCESS) {
 		ql_log(ql_log_fatal, base_vha, 0x00e7,
 		    "%s failed.\n", __func__);
-		mutex_lock(&ha->vport_lock);
+		mutex_lock(&ha->mq_lock);
 		clear_bit(que_id, ha->rsp_qid_map);
-		mutex_unlock(&ha->vport_lock);
+		mutex_unlock(&ha->mq_lock);
 		goto que_failed;
 	}
-	if (req >= 0)
-		rsp->req = ha->req_q_map[req];
-	else
-		rsp->req = NULL;
+	rsp->req = NULL;
 
 	qla2x00_init_response_q_entries(rsp);
-	if (rsp->hw->wq)
-		INIT_WORK(&rsp->q_work, qla_do_work);
+	if (qpair->hw->wq)
+		INIT_WORK(&qpair->q_work, qla_do_work);
 	return rsp->id;
 
 que_failed:
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 56d6142..8521cfe 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -13,6 +13,7 @@
 #include <linux/mutex.h>
 #include <linux/kobject.h>
 #include <linux/slab.h>
+#include <linux/blk-mq-pci.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/scsicam.h>
 #include <scsi/scsi_transport.h>
@@ -30,7 +31,7 @@ static int apidev_major;
 /*
  * SRB allocation cache
  */
-static struct kmem_cache *srb_cachep;
+struct kmem_cache *srb_cachep;
 
 /*
  * CT6 CTX allocation cache
@@ -143,19 +144,12 @@ MODULE_PARM_DESC(ql2xiidmaenable,
 		"Enables iIDMA settings "
 		"Default is 1 - perform iIDMA. 0 - no iIDMA.");
 
-int ql2xmaxqueues = 1;
-module_param(ql2xmaxqueues, int, S_IRUGO);
-MODULE_PARM_DESC(ql2xmaxqueues,
-		"Enables MQ settings "
-		"Default is 1 for single queue. Set it to number "
-		"of queues in MQ mode.");
-
-int ql2xmultique_tag;
-module_param(ql2xmultique_tag, int, S_IRUGO);
-MODULE_PARM_DESC(ql2xmultique_tag,
-		"Enables CPU affinity settings for the driver "
-		"Default is 0 for no affinity of request and response IO. "
-		"Set it to 1 to turn on the cpu affinity.");
+int ql2xmqsupport = 1;
+module_param(ql2xmqsupport, int, S_IRUGO);
+MODULE_PARM_DESC(ql2xmqsupport,
+		"Enable on demand multiple queue pairs support "
+		"Default is 1 for supported. "
+		"Set it to 0 to turn off mq qpair support.");
 
 int ql2xfwloadbin;
 module_param(ql2xfwloadbin, int, S_IRUGO|S_IWUSR);
@@ -261,6 +255,7 @@ static int qla2xxx_eh_host_reset(struct scsi_cmnd *);
 static void qla2x00_clear_drv_active(struct qla_hw_data *);
 static void qla2x00_free_device(scsi_qla_host_t *);
 static void qla83xx_disable_laser(scsi_qla_host_t *vha);
+static int qla2xxx_map_queues(struct Scsi_Host *shost);
 
 struct scsi_host_template qla2xxx_driver_template = {
 	.module			= THIS_MODULE,
@@ -280,6 +275,7 @@ struct scsi_host_template qla2xxx_driver_template = {
 	.scan_finished		= qla2xxx_scan_finished,
 	.scan_start		= qla2xxx_scan_start,
 	.change_queue_depth	= scsi_change_queue_depth,
+	.map_queues             = qla2xxx_map_queues,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
 	.use_clustering		= ENABLE_CLUSTERING,
@@ -339,6 +335,8 @@ static int qla2x00_mem_alloc(struct qla_hw_data *, uint16_t, uint16_t,
 	struct req_que **, struct rsp_que **);
 static void qla2x00_free_fw_dump(struct qla_hw_data *);
 static void qla2x00_mem_free(struct qla_hw_data *);
+int qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd,
+	struct qla_qpair *qpair);
 
 /* -------------------------------------------------------------------------- */
 static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req,
@@ -360,6 +358,25 @@ static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req,
 		    "Unable to allocate memory for response queue ptrs.\n");
 		goto fail_rsp_map;
 	}
+
+	if (ql2xmqsupport && ha->max_qpairs) {
+		ha->queue_pair_map = kcalloc(ha->max_qpairs, sizeof(struct qla_qpair *),
+			GFP_KERNEL);
+		if (!ha->queue_pair_map) {
+			ql_log(ql_log_fatal, vha, 0x0180,
+			    "Unable to allocate memory for queue pair ptrs.\n");
+			goto fail_qpair_map;
+		}
+		ha->base_qpair = kzalloc(sizeof(struct qla_qpair), GFP_KERNEL);
+		if (ha->base_qpair == NULL) {
+			ql_log(ql_log_warn, vha, 0x0182,
+			    "Failed to allocate base queue pair memory.\n");
+			goto fail_base_qpair;
+		}
+		ha->base_qpair->req = req;
+		ha->base_qpair->rsp = rsp;
+	}
+
 	/*
 	 * Make sure we record at least the request and response queue zero in
 	 * case we need to free them if part of the probe fails.
@@ -370,6 +387,11 @@ static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req,
 	set_bit(0, ha->req_qid_map);
 	return 1;
 
+fail_base_qpair:
+	kfree(ha->queue_pair_map);
+fail_qpair_map:
+	kfree(ha->rsp_q_map);
+	ha->rsp_q_map = NULL;
 fail_rsp_map:
 	kfree(ha->req_q_map);
 	ha->req_q_map = NULL;
@@ -417,84 +439,45 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	struct req_que *req;
 	struct rsp_que *rsp;
 	int cnt;
+	unsigned long flags;
 
+	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (cnt = 0; cnt < ha->max_req_queues; cnt++) {
 		if (!test_bit(cnt, ha->req_qid_map))
 			continue;
 
 		req = ha->req_q_map[cnt];
+		clear_bit(cnt, ha->req_qid_map);
+		ha->req_q_map[cnt] = NULL;
+
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		qla2x00_free_req_que(ha, req);
+		spin_lock_irqsave(&ha->hardware_lock, flags);
 	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	kfree(ha->req_q_map);
 	ha->req_q_map = NULL;
 
+
+	spin_lock_irqsave(&ha->hardware_lock, flags);
 	for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) {
 		if (!test_bit(cnt, ha->rsp_qid_map))
 			continue;
 
 		rsp = ha->rsp_q_map[cnt];
+		clear_bit(cnt, ha->req_qid_map);
+		ha->rsp_q_map[cnt] =  NULL;
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		qla2x00_free_rsp_que(ha, rsp);
+		spin_lock_irqsave(&ha->hardware_lock, flags);
 	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	kfree(ha->rsp_q_map);
 	ha->rsp_q_map = NULL;
 }
 
-static int qla25xx_setup_mode(struct scsi_qla_host *vha)
-{
-	uint16_t options = 0;
-	int ques, req, ret;
-	struct qla_hw_data *ha = vha->hw;
-
-	if (!(ha->fw_attributes & BIT_6)) {
-		ql_log(ql_log_warn, vha, 0x00d8,
-		    "Firmware is not multi-queue capable.\n");
-		goto fail;
-	}
-	if (ql2xmultique_tag) {
-		/* create a request queue for IO */
-		options |= BIT_7;
-		req = qla25xx_create_req_que(ha, options, 0, 0, -1,
-			QLA_DEFAULT_QUE_QOS);
-		if (!req) {
-			ql_log(ql_log_warn, vha, 0x00e0,
-			    "Failed to create request queue.\n");
-			goto fail;
-		}
-		ha->wq = alloc_workqueue("qla2xxx_wq", WQ_MEM_RECLAIM, 1);
-		vha->req = ha->req_q_map[req];
-		options |= BIT_1;
-		for (ques = 1; ques < ha->max_rsp_queues; ques++) {
-			ret = qla25xx_create_rsp_que(ha, options, 0, 0, req);
-			if (!ret) {
-				ql_log(ql_log_warn, vha, 0x00e8,
-				    "Failed to create response queue.\n");
-				goto fail2;
-			}
-		}
-		ha->flags.cpu_affinity_enabled = 1;
-		ql_dbg(ql_dbg_multiq, vha, 0xc007,
-		    "CPU affinity mode enabled, "
-		    "no. of response queues:%d no. of request queues:%d.\n",
-		    ha->max_rsp_queues, ha->max_req_queues);
-		ql_dbg(ql_dbg_init, vha, 0x00e9,
-		    "CPU affinity mode enabled, "
-		    "no. of response queues:%d no. of request queues:%d.\n",
-		    ha->max_rsp_queues, ha->max_req_queues);
-	}
-	return 0;
-fail2:
-	qla25xx_delete_queues(vha);
-	destroy_workqueue(ha->wq);
-	ha->wq = NULL;
-	vha->req = ha->req_q_map[0];
-fail:
-	ha->mqenable = 0;
-	kfree(ha->req_q_map);
-	kfree(ha->rsp_q_map);
-	ha->max_req_queues = ha->max_rsp_queues = 1;
-	return 1;
-}
-
 static char *
 qla2x00_pci_info_str(struct scsi_qla_host *vha, char *str)
 {
@@ -669,7 +652,7 @@ qla2x00_sp_free_dma(void *vha, void *ptr)
 	qla2x00_rel_sp(sp->fcport->vha, sp);
 }
 
-static void
+void
 qla2x00_sp_compl(void *data, void *ptr, int res)
 {
 	struct qla_hw_data *ha = (struct qla_hw_data *)data;
@@ -693,6 +676,75 @@ qla2x00_sp_compl(void *data, void *ptr, int res)
 	cmd->scsi_done(cmd);
 }
 
+void
+qla2xxx_qpair_sp_free_dma(void *vha, void *ptr)
+{
+	srb_t *sp = (srb_t *)ptr;
+	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
+	struct qla_hw_data *ha = sp->fcport->vha->hw;
+	void *ctx = GET_CMD_CTX_SP(sp);
+
+	if (sp->flags & SRB_DMA_VALID) {
+		scsi_dma_unmap(cmd);
+		sp->flags &= ~SRB_DMA_VALID;
+	}
+
+	if (sp->flags & SRB_CRC_PROT_DMA_VALID) {
+		dma_unmap_sg(&ha->pdev->dev, scsi_prot_sglist(cmd),
+		    scsi_prot_sg_count(cmd), cmd->sc_data_direction);
+		sp->flags &= ~SRB_CRC_PROT_DMA_VALID;
+	}
+
+	if (sp->flags & SRB_CRC_CTX_DSD_VALID) {
+		/* List assured to be having elements */
+		qla2x00_clean_dsd_pool(ha, sp, NULL);
+		sp->flags &= ~SRB_CRC_CTX_DSD_VALID;
+	}
+
+	if (sp->flags & SRB_CRC_CTX_DMA_VALID) {
+		dma_pool_free(ha->dl_dma_pool, ctx,
+		    ((struct crc_context *)ctx)->crc_ctx_dma);
+		sp->flags &= ~SRB_CRC_CTX_DMA_VALID;
+	}
+
+	if (sp->flags & SRB_FCP_CMND_DMA_VALID) {
+		struct ct6_dsd *ctx1 = (struct ct6_dsd *)ctx;
+
+		dma_pool_free(ha->fcp_cmnd_dma_pool, ctx1->fcp_cmnd,
+		    ctx1->fcp_cmnd_dma);
+		list_splice(&ctx1->dsd_list, &ha->gbl_dsd_list);
+		ha->gbl_dsd_inuse -= ctx1->dsd_use_cnt;
+		ha->gbl_dsd_avail += ctx1->dsd_use_cnt;
+		mempool_free(ctx1, ha->ctx_mempool);
+	}
+
+	CMD_SP(cmd) = NULL;
+	qla2xxx_rel_qpair_sp(sp->qpair, sp);
+}
+
+void
+qla2xxx_qpair_sp_compl(void *data, void *ptr, int res)
+{
+	srb_t *sp = (srb_t *)ptr;
+	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
+
+	cmd->result = res;
+
+	if (atomic_read(&sp->ref_count) == 0) {
+		ql_dbg(ql_dbg_io, sp->fcport->vha, 0x3079,
+		    "SP reference-count to ZERO -- sp=%p cmd=%p.\n",
+		    sp, GET_CMD_SP(sp));
+		if (ql2xextended_error_logging & ql_dbg_io)
+			WARN_ON(atomic_read(&sp->ref_count) == 0);
+		return;
+	}
+	if (!atomic_dec_and_test(&sp->ref_count))
+		return;
+
+	qla2xxx_qpair_sp_free_dma(sp->fcport->vha, sp);
+	cmd->scsi_done(cmd);
+}
+
 /* If we are SP1 here, we need to still take and release the host_lock as SP1
  * does not have the changes necessary to avoid taking host->host_lock.
  */
@@ -706,12 +758,28 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
 	srb_t *sp;
 	int rval;
+	struct qla_qpair *qpair = NULL;
+	uint32_t tag;
+	uint16_t hwq;
 
 	if (unlikely(test_bit(UNLOADING, &base_vha->dpc_flags))) {
 		cmd->result = DID_NO_CONNECT << 16;
 		goto qc24_fail_command;
 	}
 
+	if (ha->mqenable) {
+		if (shost_use_blk_mq(vha->host)) {
+			tag = blk_mq_unique_tag(cmd->request);
+			hwq = blk_mq_unique_tag_to_hwq(tag);
+			qpair = ha->queue_pair_map[hwq];
+		} else if (vha->vp_idx && vha->qpair) {
+			qpair = vha->qpair;
+		}
+
+		if (qpair)
+			return qla2xxx_mqueuecommand(host, cmd, qpair);
+	}
+
 	if (ha->flags.eeh_busy) {
 		if (ha->flags.pci_channel_io_perm_failure) {
 			ql_dbg(ql_dbg_aer, vha, 0x9010,
@@ -808,6 +876,95 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	return 0;
 }
 
+/* For MQ supported I/O */
+int
+qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd,
+    struct qla_qpair *qpair)
+{
+	scsi_qla_host_t *vha = shost_priv(host);
+	fc_port_t *fcport = (struct fc_port *) cmd->device->hostdata;
+	struct fc_rport *rport = starget_to_rport(scsi_target(cmd->device));
+	struct qla_hw_data *ha = vha->hw;
+	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+	srb_t *sp;
+	int rval;
+
+	rval = fc_remote_port_chkready(rport);
+	if (rval) {
+		cmd->result = rval;
+		ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x3076,
+		    "fc_remote_port_chkready failed for cmd=%p, rval=0x%x.\n",
+		    cmd, rval);
+		goto qc24_fail_command;
+	}
+
+	if (!fcport) {
+		cmd->result = DID_NO_CONNECT << 16;
+		goto qc24_fail_command;
+	}
+
+	if (atomic_read(&fcport->state) != FCS_ONLINE) {
+		if (atomic_read(&fcport->state) == FCS_DEVICE_DEAD ||
+			atomic_read(&base_vha->loop_state) == LOOP_DEAD) {
+			ql_dbg(ql_dbg_io, vha, 0x3077,
+			    "Returning DNC, fcport_state=%d loop_state=%d.\n",
+			    atomic_read(&fcport->state),
+			    atomic_read(&base_vha->loop_state));
+			cmd->result = DID_NO_CONNECT << 16;
+			goto qc24_fail_command;
+		}
+		goto qc24_target_busy;
+	}
+
+	/*
+	 * Return target busy if we've received a non-zero retry_delay_timer
+	 * in a FCP_RSP.
+	 */
+	if (fcport->retry_delay_timestamp == 0) {
+		/* retry delay not set */
+	} else if (time_after(jiffies, fcport->retry_delay_timestamp))
+		fcport->retry_delay_timestamp = 0;
+	else
+		goto qc24_target_busy;
+
+	sp = qla2xxx_get_qpair_sp(qpair, fcport, GFP_ATOMIC);
+	if (!sp)
+		goto qc24_host_busy;
+
+	sp->u.scmd.cmd = cmd;
+	sp->type = SRB_SCSI_CMD;
+	atomic_set(&sp->ref_count, 1);
+	CMD_SP(cmd) = (void *)sp;
+	sp->free = qla2xxx_qpair_sp_free_dma;
+	sp->done = qla2xxx_qpair_sp_compl;
+	sp->qpair = qpair;
+
+	rval = ha->isp_ops->start_scsi_mq(sp);
+	if (rval != QLA_SUCCESS) {
+		ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x3078,
+		    "Start scsi failed rval=%d for cmd=%p.\n", rval, cmd);
+		if (rval == QLA_INTERFACE_ERROR)
+			goto qc24_fail_command;
+		goto qc24_host_busy_free_sp;
+	}
+
+	return 0;
+
+qc24_host_busy_free_sp:
+	qla2xxx_qpair_sp_free_dma(vha, sp);
+
+qc24_host_busy:
+	return SCSI_MLQUEUE_HOST_BUSY;
+
+qc24_target_busy:
+	return SCSI_MLQUEUE_TARGET_BUSY;
+
+qc24_fail_command:
+	cmd->scsi_done(cmd);
+
+	return 0;
+}
+
 /*
  * qla2x00_eh_wait_on_command
  *    Waits for the command to be returned by the Firmware for some
@@ -1601,7 +1758,6 @@ qla2x00_iospace_config(struct qla_hw_data *ha)
 {
 	resource_size_t pio;
 	uint16_t msix;
-	int cpus;
 
 	if (pci_request_selected_regions(ha->pdev, ha->bars,
 	    QLA2XXX_DRIVER_NAME)) {
@@ -1658,9 +1814,7 @@ qla2x00_iospace_config(struct qla_hw_data *ha)
 
 	/* Determine queue resources */
 	ha->max_req_queues = ha->max_rsp_queues = 1;
-	if ((ql2xmaxqueues <= 1 && !ql2xmultique_tag) ||
-		(ql2xmaxqueues > 1 && ql2xmultique_tag) ||
-		(!IS_QLA25XX(ha) && !IS_QLA81XX(ha)))
+	if (!ql2xmqsupport || (!IS_QLA25XX(ha) && !IS_QLA81XX(ha)))
 		goto mqiobase_exit;
 
 	ha->mqiobase = ioremap(pci_resource_start(ha->pdev, 3),
@@ -1670,26 +1824,18 @@ qla2x00_iospace_config(struct qla_hw_data *ha)
 		    "MQIO Base=%p.\n", ha->mqiobase);
 		/* Read MSIX vector size of the board */
 		pci_read_config_word(ha->pdev, QLA_PCI_MSIX_CONTROL, &msix);
-		ha->msix_count = msix;
+		ha->msix_count = msix + 1;
 		/* Max queues are bounded by available msix vectors */
-		/* queue 0 uses two msix vectors */
-		if (ql2xmultique_tag) {
-			cpus = num_online_cpus();
-			ha->max_rsp_queues = (ha->msix_count - 1 > cpus) ?
-				(cpus + 1) : (ha->msix_count - 1);
-			ha->max_req_queues = 2;
-		} else if (ql2xmaxqueues > 1) {
-			ha->max_req_queues = ql2xmaxqueues > QLA_MQ_SIZE ?
-			    QLA_MQ_SIZE : ql2xmaxqueues;
-			ql_dbg_pci(ql_dbg_multiq, ha->pdev, 0xc008,
-			    "QoS mode set, max no of request queues:%d.\n",
-			    ha->max_req_queues);
-			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0019,
-			    "QoS mode set, max no of request queues:%d.\n",
-			    ha->max_req_queues);
-		}
+		/* MB interrupt uses 1 vector */
+		ha->max_req_queues = ha->msix_count - 1;
+		ha->max_rsp_queues = ha->max_req_queues;
+		/* Queue pairs is the max value minus the base queue pair */
+		ha->max_qpairs = ha->max_rsp_queues - 1;
+		ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0188,
+		    "Max no of queues pairs: %d.\n", ha->max_qpairs);
+
 		ql_log_pci(ql_log_info, ha->pdev, 0x001a,
-		    "MSI-X vector count: %d.\n", msix);
+		    "MSI-X vector count: %d.\n", ha->msix_count);
 	} else
 		ql_log_pci(ql_log_info, ha->pdev, 0x001b,
 		    "BAR 3 not enabled.\n");
@@ -1709,7 +1855,6 @@ static int
 qla83xx_iospace_config(struct qla_hw_data *ha)
 {
 	uint16_t msix;
-	int cpus;
 
 	if (pci_request_selected_regions(ha->pdev, ha->bars,
 	    QLA2XXX_DRIVER_NAME)) {
@@ -1761,32 +1906,36 @@ qla83xx_iospace_config(struct qla_hw_data *ha)
 		/* Read MSIX vector size of the board */
 		pci_read_config_word(ha->pdev,
 		    QLA_83XX_PCI_MSIX_CONTROL, &msix);
-		ha->msix_count = msix;
-		/* Max queues are bounded by available msix vectors */
-		/* queue 0 uses two msix vectors */
-		if (ql2xmultique_tag) {
-			cpus = num_online_cpus();
-			ha->max_rsp_queues = (ha->msix_count - 1 > cpus) ?
-				(cpus + 1) : (ha->msix_count - 1);
-			ha->max_req_queues = 2;
-		} else if (ql2xmaxqueues > 1) {
-			ha->max_req_queues = ql2xmaxqueues > QLA_MQ_SIZE ?
-						QLA_MQ_SIZE : ql2xmaxqueues;
-			ql_dbg_pci(ql_dbg_multiq, ha->pdev, 0xc00c,
-			    "QoS mode set, max no of request queues:%d.\n",
-			    ha->max_req_queues);
-			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x011b,
-			    "QoS mode set, max no of request queues:%d.\n",
-			    ha->max_req_queues);
+		ha->msix_count = msix + 1;
+		/*
+		 * By default, driver uses at least two msix vectors
+		 * (default & rspq)
+		 */
+		if (ql2xmqsupport) {
+			/* MB interrupt uses 1 vector */
+			ha->max_req_queues = ha->msix_count - 1;
+			ha->max_rsp_queues = ha->max_req_queues;
+
+			/* ATIOQ needs 1 vector. That's 1 less QPair */
+			if (QLA_TGT_MODE_ENABLED())
+				ha->max_req_queues--;
+
+			/* Queue pairs is the max value minus
+			 * the base queue pair */
+			ha->max_qpairs = ha->max_req_queues - 1;
+			ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0190,
+			    "Max no of queues pairs: %d.\n", ha->max_qpairs);
 		}
 		ql_log_pci(ql_log_info, ha->pdev, 0x011c,
-		    "MSI-X vector count: %d.\n", msix);
+		    "MSI-X vector count: %d.\n", ha->msix_count);
 	} else
 		ql_log_pci(ql_log_info, ha->pdev, 0x011e,
 		    "BAR 1 not enabled.\n");
 
 mqiobase_exit:
 	ha->msix_count = ha->max_rsp_queues + 1;
+	if (QLA_TGT_MODE_ENABLED())
+		ha->msix_count++;
 
 	qlt_83xx_iospace_config(ha);
 
@@ -1831,6 +1980,7 @@ static struct isp_operations qla2100_isp_ops = {
 	.write_optrom		= qla2x00_write_optrom_data,
 	.get_flash_version	= qla2x00_get_flash_version,
 	.start_scsi		= qla2x00_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config     	= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -1869,6 +2019,7 @@ static struct isp_operations qla2300_isp_ops = {
 	.write_optrom		= qla2x00_write_optrom_data,
 	.get_flash_version	= qla2x00_get_flash_version,
 	.start_scsi		= qla2x00_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -1907,6 +2058,7 @@ static struct isp_operations qla24xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -1945,6 +2097,7 @@ static struct isp_operations qla25xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_dif_start_scsi,
+	.start_scsi_mq          = qla2xxx_dif_start_scsi_mq,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -1983,6 +2136,7 @@ static struct isp_operations qla81xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_dif_start_scsi,
+	.start_scsi_mq          = qla2xxx_dif_start_scsi_mq,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla2x00_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2021,6 +2175,7 @@ static struct isp_operations qla82xx_isp_ops = {
 	.write_optrom		= qla82xx_write_optrom_data,
 	.get_flash_version	= qla82xx_get_flash_version,
 	.start_scsi             = qla82xx_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla82xx_abort_isp,
 	.iospace_config     	= qla82xx_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2059,6 +2214,7 @@ static struct isp_operations qla8044_isp_ops = {
 	.write_optrom		= qla8044_write_optrom_data,
 	.get_flash_version	= qla82xx_get_flash_version,
 	.start_scsi             = qla82xx_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qla8044_abort_isp,
 	.iospace_config		= qla82xx_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2097,6 +2253,7 @@ static struct isp_operations qla83xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_dif_start_scsi,
+	.start_scsi_mq          = qla2xxx_dif_start_scsi_mq,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla83xx_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2135,6 +2292,7 @@ static struct isp_operations qlafx00_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qlafx00_start_scsi,
+	.start_scsi_mq          = NULL,
 	.abort_isp		= qlafx00_abort_isp,
 	.iospace_config		= qlafx00_iospace_config,
 	.initialize_adapter	= qlafx00_initialize_adapter,
@@ -2173,6 +2331,7 @@ static struct isp_operations qla27xx_isp_ops = {
 	.write_optrom		= qla24xx_write_optrom_data,
 	.get_flash_version	= qla24xx_get_flash_version,
 	.start_scsi		= qla24xx_dif_start_scsi,
+	.start_scsi_mq          = qla2xxx_dif_start_scsi_mq,
 	.abort_isp		= qla2x00_abort_isp,
 	.iospace_config		= qla83xx_iospace_config,
 	.initialize_adapter	= qla2x00_initialize_adapter,
@@ -2387,6 +2546,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	uint16_t req_length = 0, rsp_length = 0;
 	struct req_que *req = NULL;
 	struct rsp_que *rsp = NULL;
+	int i;
+
 	bars = pci_select_bars(pdev, IORESOURCE_MEM | IORESOURCE_IO);
 	sht = &qla2xxx_driver_template;
 	if (pdev->device == PCI_DEVICE_ID_QLOGIC_ISP2422 ||
@@ -2650,6 +2811,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    "Found an ISP%04X irq %d iobase 0x%p.\n",
 	    pdev->device, pdev->irq, ha->iobase);
 	mutex_init(&ha->vport_lock);
+	mutex_init(&ha->mq_lock);
 	init_completion(&ha->mbx_cmd_comp);
 	complete(&ha->mbx_cmd_comp);
 	init_completion(&ha->mbx_intr_comp);
@@ -2737,7 +2899,11 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    host->max_cmd_len, host->max_channel, host->max_lun,
 	    host->transportt, sht->vendor_id);
 
-que_init:
+	/* Set up the irqs */
+	ret = qla2x00_request_irqs(ha, rsp);
+	if (ret)
+		goto probe_init_failed;
+
 	/* Alloc arrays of request and response ring ptrs */
 	if (!qla2x00_alloc_queues(ha, req, rsp)) {
 		ql_log(ql_log_fatal, base_vha, 0x003d,
@@ -2746,12 +2912,17 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto probe_init_failed;
 	}
 
-	qlt_probe_one_stage1(base_vha, ha);
+	if (ha->mqenable && shost_use_blk_mq(host)) {
+		/* number of hardware queues supported by blk/scsi-mq*/
+		host->nr_hw_queues = ha->max_qpairs;
 
-	/* Set up the irqs */
-	ret = qla2x00_request_irqs(ha, rsp);
-	if (ret)
-		goto probe_init_failed;
+		ql_dbg(ql_dbg_init, base_vha, 0x0192,
+			"blk/scsi-mq enabled, HW queues = %d.\n", host->nr_hw_queues);
+	} else
+		ql_dbg(ql_dbg_init, base_vha, 0x0193,
+			"blk/scsi-mq disabled.\n");
+
+	qlt_probe_one_stage1(base_vha, ha);
 
 	pci_save_state(pdev);
 
@@ -2842,11 +3013,12 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    host->can_queue, base_vha->req,
 	    base_vha->mgmt_svr_loop_id, host->sg_tablesize);
 
-	if (ha->mqenable) {
-		if (qla25xx_setup_mode(base_vha)) {
-			ql_log(ql_log_warn, base_vha, 0x00ec,
-			    "Failed to create queues, falling back to single queue mode.\n");
-			goto que_init;
+	if (ha->mqenable && qla_ini_mode_enabled(base_vha)) {
+		ha->wq = alloc_workqueue("qla2xxx_wq", WQ_MEM_RECLAIM, 1);
+		/* Create start of day qpairs for Block MQ */
+		if (shost_use_blk_mq(host)) {
+			for (i = 0; i < ha->max_qpairs; i++)
+				qla2xxx_create_qpair(base_vha, 5, 0);
 		}
 	}
 
@@ -3115,13 +3287,6 @@ qla2x00_delete_all_vps(struct qla_hw_data *ha, scsi_qla_host_t *base_vha)
 static void
 qla2x00_destroy_deferred_work(struct qla_hw_data *ha)
 {
-	/* Flush the work queue and remove it */
-	if (ha->wq) {
-		flush_workqueue(ha->wq);
-		destroy_workqueue(ha->wq);
-		ha->wq = NULL;
-	}
-
 	/* Cancel all work and destroy DPC workqueues */
 	if (ha->dpc_lp_wq) {
 		cancel_work_sync(&ha->idc_aen);
@@ -3317,9 +3482,17 @@ qla2x00_free_device(scsi_qla_host_t *vha)
 		ha->isp_ops->disable_intrs(ha);
 	}
 
+	qla2x00_free_fcports(vha);
+
 	qla2x00_free_irqs(vha);
 
-	qla2x00_free_fcports(vha);
+	/* Flush the work queue and remove it */
+	if (ha->wq) {
+		flush_workqueue(ha->wq);
+		destroy_workqueue(ha->wq);
+		ha->wq = NULL;
+	}
+
 
 	qla2x00_mem_free(ha);
 
@@ -4034,6 +4207,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	INIT_LIST_HEAD(&vha->qla_sess_op_cmd_list);
 	INIT_LIST_HEAD(&vha->logo_list);
 	INIT_LIST_HEAD(&vha->plogi_ack_list);
+	INIT_LIST_HEAD(&vha->qp_list);
 
 	spin_lock_init(&vha->work_lock);
 	spin_lock_init(&vha->cmd_list_lock);
@@ -5038,8 +5212,8 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 
 	base_vha->flags.init_done = 0;
 	qla25xx_delete_queues(base_vha);
-	qla2x00_free_irqs(base_vha);
 	qla2x00_free_fcports(base_vha);
+	qla2x00_free_irqs(base_vha);
 	qla2x00_mem_free(ha);
 	qla82xx_md_free(base_vha);
 	qla2x00_free_queues(ha);
@@ -5073,6 +5247,8 @@ qla2x00_do_dpc(void *data)
 {
 	scsi_qla_host_t *base_vha;
 	struct qla_hw_data *ha;
+	uint32_t online;
+	struct qla_qpair *qpair;
 
 	ha = (struct qla_hw_data *)data;
 	base_vha = pci_get_drvdata(ha->pdev);
@@ -5334,6 +5510,22 @@ qla2x00_do_dpc(void *data)
 				ha->isp_ops->beacon_blink(base_vha);
 		}
 
+		/* qpair online check */
+		if (test_and_clear_bit(QPAIR_ONLINE_CHECK_NEEDED,
+		    &base_vha->dpc_flags)) {
+			if (ha->flags.eeh_busy ||
+			    ha->flags.pci_channel_io_perm_failure)
+				online = 0;
+			else
+				online = 1;
+
+			mutex_lock(&ha->mq_lock);
+			list_for_each_entry(qpair, &base_vha->qp_list,
+			    qp_list_elem)
+			qpair->online = online;
+			mutex_unlock(&ha->mq_lock);
+		}
+
 		if (!IS_QLAFX00(ha))
 			qla2x00_do_dpc_all_vps(base_vha);
 
@@ -5676,6 +5868,10 @@ qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
 	switch (state) {
 	case pci_channel_io_normal:
 		ha->flags.eeh_busy = 0;
+		if (ql2xmqsupport) {
+			set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		}
 		return PCI_ERS_RESULT_CAN_RECOVER;
 	case pci_channel_io_frozen:
 		ha->flags.eeh_busy = 1;
@@ -5689,10 +5885,18 @@ qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
 		pci_disable_device(pdev);
 		/* Return back all IOs */
 		qla2x00_abort_all_cmds(vha, DID_RESET << 16);
+		if (ql2xmqsupport) {
+			set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		}
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
 		ha->flags.pci_channel_io_perm_failure = 1;
 		qla2x00_abort_all_cmds(vha, DID_NO_CONNECT << 16);
+		if (ql2xmqsupport) {
+			set_bit(QPAIR_ONLINE_CHECK_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		}
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -5960,6 +6164,13 @@ qla83xx_disable_laser(scsi_qla_host_t *vha)
 	qla83xx_wr_reg(vha, reg, data);
 }
 
+static int qla2xxx_map_queues(struct Scsi_Host *shost)
+{
+	scsi_qla_host_t *vha = (scsi_qla_host_t *)shost->hostdata;
+
+	return blk_mq_pci_map_queues(&shost->tag_set, vha->hw->pdev);
+}
+
 static const struct pci_error_handlers qla2xxx_err_handler = {
 	.error_detected = qla2xxx_pci_error_detected,
 	.mmio_enabled = qla2xxx_pci_mmio_enabled,
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index 9f6012b..b4336e0 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -9,7 +9,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * NVRAM support routines
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index cf04a36..03051e1 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -4085,7 +4085,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 			jiffies_to_timespec(delta_jiff, &ts);
 			kt = ktime_set(ts.tv_sec, ts.tv_nsec);
 		} else
-			kt = ktime_set(0, sdebug_ndelay);
+			kt = sdebug_ndelay;
 		if (NULL == sd_dp) {
 			sd_dp = kzalloc(sizeof(*sd_dp), GFP_ATOMIC);
 			if (NULL == sd_dp)
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index c4f7b56..8b8c814 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -12,7 +12,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c
index 7a74b82..480a597 100644
--- a/drivers/scsi/scsi_proc.c
+++ b/drivers/scsi/scsi_proc.c
@@ -26,7 +26,7 @@
 #include <linux/seq_file.h>
 #include <linux/mutex.h>
 #include <linux/gfp.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 0734927..82dfe07 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1204,10 +1204,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 	struct request_queue *rq = sdev->request_queue;
 	struct scsi_target *starget = sdev->sdev_target;
 
-	error = scsi_device_set_state(sdev, SDEV_RUNNING);
-	if (error)
-		return error;
-
 	error = scsi_target_add(starget);
 	if (error)
 		return error;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 1622e23..b193304 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -53,7 +53,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/pr.h>
 #include <linux/t10-pi.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 070332e..dbe5b4b 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -581,6 +581,9 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	sg_io_hdr_t *hp;
 	unsigned char cmnd[SG_MAX_CDB_SIZE];
 
+	if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+		return -EINVAL;
+
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index bed2bbd..94352e4 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -46,7 +46,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_dbg.h>
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 03054c0..dfffdf6 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -10,7 +10,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_dbg.h>
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 605887d..5f35b86 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -41,7 +41,7 @@ static const char *verstr = "20160209";
 #include <linux/delay.h>
 #include <linux/mutex.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dma.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index aa43bfe..abe6173 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -23,6 +23,7 @@
 #include "unipro.h"
 #include "ufs-qcom.h"
 #include "ufshci.h"
+#include "ufs_quirks.h"
 #define UFS_QCOM_DEFAULT_DBG_PRINT_EN	\
 	(UFS_QCOM_DBG_PRINT_REGS_EN | UFS_QCOM_DBG_PRINT_TEST_BUS_EN)
 
@@ -1031,6 +1032,34 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
 	return ret;
 }
 
+static int ufs_qcom_quirk_host_pa_saveconfigtime(struct ufs_hba *hba)
+{
+	int err;
+	u32 pa_vs_config_reg1;
+
+	err = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_VS_CONFIG_REG1),
+			     &pa_vs_config_reg1);
+	if (err)
+		goto out;
+
+	/* Allow extension of MSB bits of PA_SaveConfigTime attribute */
+	err = ufshcd_dme_set(hba, UIC_ARG_MIB(PA_VS_CONFIG_REG1),
+			    (pa_vs_config_reg1 | (1 << 12)));
+
+out:
+	return err;
+}
+
+static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
+{
+	int err = 0;
+
+	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME)
+		err = ufs_qcom_quirk_host_pa_saveconfigtime(hba);
+
+	return err;
+}
+
 static u32 ufs_qcom_get_ufs_hci_version(struct ufs_hba *hba)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
@@ -1194,7 +1223,16 @@ static int ufs_qcom_init(struct ufs_hba *hba)
 	 */
 	host->generic_phy = devm_phy_get(dev, "ufsphy");
 
-	if (IS_ERR(host->generic_phy)) {
+	if (host->generic_phy == ERR_PTR(-EPROBE_DEFER)) {
+		/*
+		 * UFS driver might be probed before the phy driver does.
+		 * In that case we would like to return EPROBE_DEFER code.
+		 */
+		err = -EPROBE_DEFER;
+		dev_warn(dev, "%s: required phy device. hasn't probed yet. err = %d\n",
+			__func__, err);
+		goto out_variant_clear;
+	} else if (IS_ERR(host->generic_phy)) {
 		err = PTR_ERR(host->generic_phy);
 		dev_err(dev, "%s: PHY get failed %d\n", __func__, err);
 		goto out_variant_clear;
@@ -1432,7 +1470,8 @@ static void ufs_qcom_print_hw_debug_reg_all(struct ufs_hba *hba,
 	reg = ufs_qcom_get_debug_reg_offset(host, UFS_UFS_DBG_RD_PRDT_RAM);
 	print_fn(hba, reg, 64, "UFS_UFS_DBG_RD_PRDT_RAM ", priv);
 
-	ufshcd_writel(hba, (reg & ~UFS_BIT(17)), REG_UFS_CFG1);
+	/* clear bit 17 - UTP_DBG_RAMS_EN */
+	ufshcd_rmwl(hba, UFS_BIT(17), 0, REG_UFS_CFG1);
 
 	reg = ufs_qcom_get_debug_reg_offset(host, UFS_DBG_RD_REG_UAWM);
 	print_fn(hba, reg, 4, "UFS_DBG_RD_REG_UAWM ", priv);
@@ -1609,6 +1648,7 @@ static struct ufs_hba_variant_ops ufs_hba_qcom_vops = {
 	.hce_enable_notify      = ufs_qcom_hce_enable_notify,
 	.link_startup_notify    = ufs_qcom_link_startup_notify,
 	.pwr_change_notify	= ufs_qcom_pwr_change_notify,
+	.apply_dev_quirks	= ufs_qcom_apply_dev_quirks,
 	.suspend		= ufs_qcom_suspend,
 	.resume			= ufs_qcom_resume,
 	.dbg_register_dump	= ufs_qcom_dump_dbg_regs,
diff --git a/drivers/scsi/ufs/ufs-qcom.h b/drivers/scsi/ufs/ufs-qcom.h
index a19307a..fe517cd 100644
--- a/drivers/scsi/ufs/ufs-qcom.h
+++ b/drivers/scsi/ufs/ufs-qcom.h
@@ -142,6 +142,7 @@ enum ufs_qcom_phy_init_type {
 	 UFS_QCOM_DBG_PRINT_TEST_BUS_EN)
 
 /* QUniPro Vendor specific attributes */
+#define PA_VS_CONFIG_REG1	0x9000
 #define DME_VS_CORE_CLK_CTRL	0xD002
 /* bit and mask definitions for DME_VS_CORE_CLK_CTRL attribute */
 #define DME_VS_CORE_CLK_CTRL_CORE_CLK_DIV_EN_BIT		BIT(8)
diff --git a/drivers/scsi/ufs/ufs_quirks.h b/drivers/scsi/ufs/ufs_quirks.h
index f798305..08b799d 100644
--- a/drivers/scsi/ufs/ufs_quirks.h
+++ b/drivers/scsi/ufs/ufs_quirks.h
@@ -134,29 +134,17 @@ struct ufs_dev_fix {
  */
 #define UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE	(1 << 7)
 
+/*
+ * The max. value PA_SaveConfigTime is 250 (10us) but this is not enough for
+ * some vendors.
+ * Gear switch from PWM to HS may fail even with this max. PA_SaveConfigTime.
+ * Gear switch can be issued by host controller as an error recovery and any
+ * software delay will not help on this case so we need to increase
+ * PA_SaveConfigTime to >32us as per vendor recommendation.
+ */
+#define UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME	(1 << 8)
 
 struct ufs_hba;
 void ufs_advertise_fixup_device(struct ufs_hba *hba);
 
-static struct ufs_dev_fix ufs_fixups[] = {
-	/* UFS cards deviations table */
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
-		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
-		UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS),
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
-		UFS_DEVICE_NO_FASTAUTO),
-	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
-		UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE),
-	UFS_FIX(UFS_VENDOR_TOSHIBA, UFS_ANY_MODEL,
-		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
-	UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9C8KBADG",
-		UFS_DEVICE_QUIRK_PA_TACTIVATE),
-	UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9D8KBADG",
-		UFS_DEVICE_QUIRK_PA_TACTIVATE),
-	UFS_FIX(UFS_VENDOR_SKHYNIX, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
-
-	END_FIX
-};
 #endif /* UFS_QUIRKS_H_ */
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index ef8548c..20e5e5f 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -185,6 +185,30 @@ ufs_get_pm_lvl_to_link_pwr_state(enum ufs_pm_level lvl)
 	return ufs_pm_lvl_states[lvl].link_state;
 }
 
+static struct ufs_dev_fix ufs_fixups[] = {
+	/* UFS cards deviations table */
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS),
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
+		UFS_DEVICE_NO_FASTAUTO),
+	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE),
+	UFS_FIX(UFS_VENDOR_TOSHIBA, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM),
+	UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9C8KBADG",
+		UFS_DEVICE_QUIRK_PA_TACTIVATE),
+	UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9D8KBADG",
+		UFS_DEVICE_QUIRK_PA_TACTIVATE),
+	UFS_FIX(UFS_VENDOR_SKHYNIX, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
+	UFS_FIX(UFS_VENDOR_SKHYNIX, UFS_ANY_MODEL,
+		UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME),
+
+	END_FIX
+};
+
 static void ufshcd_tmc_handler(struct ufs_hba *hba);
 static void ufshcd_async_scan(void *data, async_cookie_t cookie);
 static int ufshcd_reset_and_restore(struct ufs_hba *hba);
@@ -288,10 +312,24 @@ int ufshcd_wait_for_register(struct ufs_hba *hba, u32 reg, u32 mask,
  */
 static inline u32 ufshcd_get_intr_mask(struct ufs_hba *hba)
 {
-	if (hba->ufs_version == UFSHCI_VERSION_10)
-		return INTERRUPT_MASK_ALL_VER_10;
-	else
-		return INTERRUPT_MASK_ALL_VER_11;
+	u32 intr_mask = 0;
+
+	switch (hba->ufs_version) {
+	case UFSHCI_VERSION_10:
+		intr_mask = INTERRUPT_MASK_ALL_VER_10;
+		break;
+	/* allow fall through */
+	case UFSHCI_VERSION_11:
+	case UFSHCI_VERSION_20:
+		intr_mask = INTERRUPT_MASK_ALL_VER_11;
+		break;
+	/* allow fall through */
+	case UFSHCI_VERSION_21:
+	default:
+		intr_mask = INTERRUPT_MASK_ALL_VER_21;
+	}
+
+	return intr_mask;
 }
 
 /**
@@ -892,7 +930,7 @@ static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba)
 	if (!hba->outstanding_reqs && scaling->is_busy_started) {
 		scaling->tot_busy_t += ktime_to_us(ktime_sub(ktime_get(),
 					scaling->busy_start_t));
-		scaling->busy_start_t = ktime_set(0, 0);
+		scaling->busy_start_t = 0;
 		scaling->is_busy_started = false;
 	}
 }
@@ -5199,6 +5237,8 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE)
 		ufshcd_quirk_tune_host_pa_tactivate(hba);
+
+	ufshcd_vops_apply_dev_quirks(hba);
 }
 
 /**
@@ -6621,7 +6661,7 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev,
 		scaling->busy_start_t = ktime_get();
 		scaling->is_busy_started = true;
 	} else {
-		scaling->busy_start_t = ktime_set(0, 0);
+		scaling->busy_start_t = 0;
 		scaling->is_busy_started = false;
 	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
@@ -6667,6 +6707,13 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	/* Get UFS version supported by the controller */
 	hba->ufs_version = ufshcd_get_ufs_version(hba);
 
+	if ((hba->ufs_version != UFSHCI_VERSION_10) &&
+	    (hba->ufs_version != UFSHCI_VERSION_11) &&
+	    (hba->ufs_version != UFSHCI_VERSION_20) &&
+	    (hba->ufs_version != UFSHCI_VERSION_21))
+		dev_err(hba->dev, "invalid UFS version 0x%x\n",
+			hba->ufs_version);
+
 	/* Get Interrupt bit mask per version */
 	hba->intr_mask = ufshcd_get_intr_mask(hba);
 
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 7d9ff22..08cd26ed 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -266,7 +266,7 @@ struct ufs_pwr_mode_info {
  * @setup_task_mgmt: called before any task management request is issued
  *                  to set some things
  * @hibern8_notify: called around hibern8 enter/exit
- *		    to configure some things
+ * @apply_dev_quirks: called to apply device specific quirks
  * @suspend: called during host controller PM callback
  * @resume: called during host controller PM callback
  * @dbg_register_dump: used to dump controller debug information
@@ -293,7 +293,8 @@ struct ufs_hba_variant_ops {
 	void	(*setup_xfer_req)(struct ufs_hba *, int, bool);
 	void	(*setup_task_mgmt)(struct ufs_hba *, int, u8);
 	void    (*hibern8_notify)(struct ufs_hba *, enum uic_cmd_dme,
-				       enum ufs_notify_change_status);
+					enum ufs_notify_change_status);
+	int	(*apply_dev_quirks)(struct ufs_hba *);
 	int     (*suspend)(struct ufs_hba *, enum ufs_pm_op);
 	int     (*resume)(struct ufs_hba *, enum ufs_pm_op);
 	void	(*dbg_register_dump)(struct ufs_hba *hba);
@@ -839,6 +840,13 @@ static inline void ufshcd_vops_hibern8_notify(struct ufs_hba *hba,
 		return hba->vops->hibern8_notify(hba, cmd, status);
 }
 
+static inline int ufshcd_vops_apply_dev_quirks(struct ufs_hba *hba)
+{
+	if (hba->vops && hba->vops->apply_dev_quirks)
+		return hba->vops->apply_dev_quirks(hba);
+	return 0;
+}
+
 static inline int ufshcd_vops_suspend(struct ufs_hba *hba, enum ufs_pm_op op)
 {
 	if (hba->vops && hba->vops->suspend)
diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h
index 5d97886..8c5190e 100644
--- a/drivers/scsi/ufs/ufshci.h
+++ b/drivers/scsi/ufs/ufshci.h
@@ -72,6 +72,10 @@ enum {
 	REG_UIC_COMMAND_ARG_1			= 0x94,
 	REG_UIC_COMMAND_ARG_2			= 0x98,
 	REG_UIC_COMMAND_ARG_3			= 0x9C,
+	REG_UFS_CCAP				= 0x100,
+	REG_UFS_CRYPTOCAP			= 0x104,
+
+	UFSHCI_CRYPTO_REG_SPACE_SIZE		= 0x400,
 };
 
 /* Controller capability masks */
@@ -275,6 +279,9 @@ enum {
 
 	/* Interrupt disable mask for UFSHCI v1.1 */
 	INTERRUPT_MASK_ALL_VER_11	= 0x31FFF,
+
+	/* Interrupt disable mask for UFSHCI v2.1 */
+	INTERRUPT_MASK_ALL_VER_21	= 0x71FFF,
 };
 
 /*
diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 6b9cf06..427e219 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -967,48 +967,38 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+static enum cpuhp_state lustre_cpu_online;
+
+static void cfs_cpu_incr_cpt_version(void)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
-
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
-
-	return NOTIFY_OK;
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
+}
 
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
+
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask, topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1008,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online > 0)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1019,8 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+	int ret = 0;
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,8 +1035,19 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
+	ret = -EINVAL;
 
 	if (*cpu_pattern) {
 		cfs_cpt_table = cfs_cpt_table_create_pattern(cpu_pattern);
@@ -1075,7 +1080,7 @@ cfs_cpu_init(void)
 
  failed:
 	cfs_cpu_fini();
-	return -1;
+	return ret;
 }
 
 #endif
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c
index d02bf58..8bcb9b7 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_target.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c
@@ -9,6 +9,7 @@
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <asm/unaligned.h>
+#include <net/tcp.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include "cxgbit.h"
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index b7d747e..da2c73a 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -23,7 +23,9 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/idr.h>
+#include <linux/delay.h>
 #include <asm/unaligned.h>
+#include <net/ipv6.h>
 #include <scsi/scsi_proto.h>
 #include <scsi/iscsi_proto.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h
index 4cf2c0f..e0db2ce 100644
--- a/drivers/target/iscsi/iscsi_target.h
+++ b/drivers/target/iscsi/iscsi_target.h
@@ -1,6 +1,18 @@
 #ifndef ISCSI_TARGET_H
 #define ISCSI_TARGET_H
 
+#include <linux/types.h>
+#include <linux/spinlock.h>
+
+struct iscsi_cmd;
+struct iscsi_conn;
+struct iscsi_np;
+struct iscsi_portal_group;
+struct iscsi_session;
+struct iscsi_tpg_np;
+struct kref;
+struct sockaddr_storage;
+
 extern struct iscsi_tiqn *iscsit_get_tiqn_for_login(unsigned char *);
 extern struct iscsi_tiqn *iscsit_get_tiqn(unsigned char *, int);
 extern void iscsit_put_tiqn_for_login(struct iscsi_tiqn *);
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index e116f0e..903b667 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -20,8 +20,8 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/err.h>
+#include <linux/random.h>
 #include <linux/scatterlist.h>
-
 #include <target/iscsi/iscsi_target_core.h>
 #include "iscsi_target_nego.h"
 #include "iscsi_target_auth.h"
diff --git a/drivers/target/iscsi/iscsi_target_auth.h b/drivers/target/iscsi/iscsi_target_auth.h
index d22f7b96..1b91c13 100644
--- a/drivers/target/iscsi/iscsi_target_auth.h
+++ b/drivers/target/iscsi/iscsi_target_auth.h
@@ -1,6 +1,8 @@
 #ifndef _ISCSI_CHAP_H_
 #define _ISCSI_CHAP_H_
 
+#include <linux/types.h>
+
 #define CHAP_DIGEST_UNKNOWN	0
 #define CHAP_DIGEST_MD5		5
 #define CHAP_DIGEST_SHA		6
@@ -18,6 +20,9 @@
 #define CHAP_STAGE_CLIENT_NRIC	4
 #define CHAP_STAGE_SERVER_NR	5
 
+struct iscsi_node_auth;
+struct iscsi_conn;
+
 extern u32 chap_main_loop(struct iscsi_conn *, struct iscsi_node_auth *, char *, char *,
 				int *, int *);
 
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 923c032..bf40f03 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -21,10 +21,11 @@
 #include <linux/ctype.h>
 #include <linux/export.h>
 #include <linux/inet.h>
+#include <linux/module.h>
+#include <net/ipv6.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/iscsi/iscsi_transport.h>
-
 #include <target/iscsi/iscsi_target_core.h>
 #include "iscsi_target_parameters.h"
 #include "iscsi_target_device.h"
@@ -100,8 +101,10 @@ static ssize_t lio_target_np_driver_store(struct config_item *item,
 
 		tpg_np_new = iscsit_tpg_add_network_portal(tpg,
 					&np->np_sockaddr, tpg_np, type);
-		if (IS_ERR(tpg_np_new))
+		if (IS_ERR(tpg_np_new)) {
+			rc = PTR_ERR(tpg_np_new);
 			goto out;
+		}
 	} else {
 		tpg_np_new = iscsit_tpg_locate_child_np(tpg_np, type);
 		if (tpg_np_new) {
diff --git a/drivers/target/iscsi/iscsi_target_datain_values.c b/drivers/target/iscsi/iscsi_target_datain_values.c
index 647d4a5..173ddd9 100644
--- a/drivers/target/iscsi/iscsi_target_datain_values.c
+++ b/drivers/target/iscsi/iscsi_target_datain_values.c
@@ -16,8 +16,8 @@
  * GNU General Public License for more details.
  ******************************************************************************/
 
+#include <linux/slab.h>
 #include <scsi/iscsi_proto.h>
-
 #include <target/iscsi/iscsi_target_core.h>
 #include "iscsi_target_seq_pdu_list.h"
 #include "iscsi_target_erl1.h"
diff --git a/drivers/target/iscsi/iscsi_target_datain_values.h b/drivers/target/iscsi/iscsi_target_datain_values.h
index 646429a..16edeee 100644
--- a/drivers/target/iscsi/iscsi_target_datain_values.h
+++ b/drivers/target/iscsi/iscsi_target_datain_values.h
@@ -1,6 +1,9 @@
 #ifndef ISCSI_TARGET_DATAIN_VALUES_H
 #define ISCSI_TARGET_DATAIN_VALUES_H
 
+struct iscsi_cmd;
+struct iscsi_datain;
+
 extern struct iscsi_datain_req *iscsit_allocate_datain_req(void);
 extern void iscsit_attach_datain_req(struct iscsi_cmd *, struct iscsi_datain_req *);
 extern void iscsit_free_datain_req(struct iscsi_cmd *, struct iscsi_datain_req *);
diff --git a/drivers/target/iscsi/iscsi_target_device.h b/drivers/target/iscsi/iscsi_target_device.h
index a0e2df9..06dbff5 100644
--- a/drivers/target/iscsi/iscsi_target_device.h
+++ b/drivers/target/iscsi/iscsi_target_device.h
@@ -1,6 +1,9 @@
 #ifndef ISCSI_TARGET_DEVICE_H
 #define ISCSI_TARGET_DEVICE_H
 
+struct iscsi_cmd;
+struct iscsi_session;
+
 extern void iscsit_determine_maxcmdsn(struct iscsi_session *);
 extern void iscsit_increment_maxcmdsn(struct iscsi_cmd *, struct iscsi_session *);
 
diff --git a/drivers/target/iscsi/iscsi_target_erl0.h b/drivers/target/iscsi/iscsi_target_erl0.h
index a9e2f94..60e69e2 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.h
+++ b/drivers/target/iscsi/iscsi_target_erl0.h
@@ -1,6 +1,12 @@
 #ifndef ISCSI_TARGET_ERL0_H
 #define ISCSI_TARGET_ERL0_H
 
+#include <linux/types.h>
+
+struct iscsi_cmd;
+struct iscsi_conn;
+struct iscsi_session;
+
 extern void iscsit_set_dataout_sequence_values(struct iscsi_cmd *);
 extern int iscsit_check_pre_dataout(struct iscsi_cmd *, unsigned char *);
 extern int iscsit_check_post_dataout(struct iscsi_cmd *, unsigned char *, u8);
diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c
index 9214c9da..fe9b7f1 100644
--- a/drivers/target/iscsi/iscsi_target_erl1.c
+++ b/drivers/target/iscsi/iscsi_target_erl1.c
@@ -17,6 +17,7 @@
  ******************************************************************************/
 
 #include <linux/list.h>
+#include <linux/slab.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
diff --git a/drivers/target/iscsi/iscsi_target_erl1.h b/drivers/target/iscsi/iscsi_target_erl1.h
index 2a3ebf1..54d36bd 100644
--- a/drivers/target/iscsi/iscsi_target_erl1.h
+++ b/drivers/target/iscsi/iscsi_target_erl1.h
@@ -1,6 +1,16 @@
 #ifndef ISCSI_TARGET_ERL1_H
 #define ISCSI_TARGET_ERL1_H
 
+#include <linux/types.h>
+#include <scsi/iscsi_proto.h> /* itt_t */
+
+struct iscsi_cmd;
+struct iscsi_conn;
+struct iscsi_datain_req;
+struct iscsi_ooo_cmdsn;
+struct iscsi_pdu;
+struct iscsi_session;
+
 extern int iscsit_dump_data_payload(struct iscsi_conn *, u32, int);
 extern int iscsit_create_recovery_datain_values_datasequenceinorder_yes(
 			struct iscsi_cmd *, struct iscsi_datain_req *);
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index e24f1c7..faf9ae0 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -17,6 +17,7 @@
  * GNU General Public License for more details.
  ******************************************************************************/
 
+#include <linux/slab.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
diff --git a/drivers/target/iscsi/iscsi_target_erl2.h b/drivers/target/iscsi/iscsi_target_erl2.h
index 63f2501..7965f1e 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.h
+++ b/drivers/target/iscsi/iscsi_target_erl2.h
@@ -1,6 +1,13 @@
 #ifndef ISCSI_TARGET_ERL2_H
 #define ISCSI_TARGET_ERL2_H
 
+#include <linux/types.h>
+
+struct iscsi_cmd;
+struct iscsi_conn;
+struct iscsi_conn_recovery;
+struct iscsi_session;
+
 extern void iscsit_create_conn_recovery_datain_values(struct iscsi_cmd *, __be32);
 extern void iscsit_create_conn_recovery_dataout_values(struct iscsi_cmd *);
 extern struct iscsi_conn_recovery *iscsit_get_inactive_connection_recovery_entry(
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 15f79a2..450f51d 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -20,6 +20,8 @@
 #include <linux/string.h>
 #include <linux/kthread.h>
 #include <linux/idr.h>
+#include <linux/tcp.h>        /* TCP_NODELAY */
+#include <net/ipv6.h>         /* ipv6_addr_v4mapped() */
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index b597aa2..0e1fd6c 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -1,6 +1,13 @@
 #ifndef ISCSI_TARGET_LOGIN_H
 #define ISCSI_TARGET_LOGIN_H
 
+#include <linux/types.h>
+
+struct iscsi_conn;
+struct iscsi_login;
+struct iscsi_np;
+struct sockaddr_storage;
+
 extern int iscsi_login_setup_crypto(struct iscsi_conn *);
 extern int iscsi_check_for_session_reinstatement(struct iscsi_conn *);
 extern int iscsi_login_post_auth_non_zero_tsih(struct iscsi_conn *, u16, u32);
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 89d34bd..46388c9 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -18,6 +18,8 @@
 
 #include <linux/ctype.h>
 #include <linux/kthread.h>
+#include <linux/slab.h>
+#include <net/sock.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
diff --git a/drivers/target/iscsi/iscsi_target_nego.h b/drivers/target/iscsi/iscsi_target_nego.h
index f021cbd..53438bf 100644
--- a/drivers/target/iscsi/iscsi_target_nego.h
+++ b/drivers/target/iscsi/iscsi_target_nego.h
@@ -4,6 +4,10 @@
 #define DECIMAL         0
 #define HEX             1
 
+struct iscsi_conn;
+struct iscsi_login;
+struct iscsi_np;
+
 extern void convert_null_to_semi(char *, int);
 extern int extract_param(const char *, const char *, unsigned int, char *,
 		unsigned char *);
diff --git a/drivers/target/iscsi/iscsi_target_nodeattrib.h b/drivers/target/iscsi/iscsi_target_nodeattrib.h
index 0c69a46..79cdf06 100644
--- a/drivers/target/iscsi/iscsi_target_nodeattrib.h
+++ b/drivers/target/iscsi/iscsi_target_nodeattrib.h
@@ -1,6 +1,11 @@
 #ifndef ISCSI_TARGET_NODEATTRIB_H
 #define ISCSI_TARGET_NODEATTRIB_H
 
+#include <linux/types.h>
+
+struct iscsi_node_acl;
+struct iscsi_portal_group;
+
 extern void iscsit_set_default_node_attribues(struct iscsi_node_acl *,
 					      struct iscsi_portal_group *);
 extern int iscsit_na_dataout_timeout(struct iscsi_node_acl *, u32);
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 0efa80b..e65bf78 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -17,7 +17,7 @@
  ******************************************************************************/
 
 #include <linux/slab.h>
-
+#include <linux/uio.h> /* struct kvec */
 #include <target/iscsi/iscsi_target_core.h>
 #include "iscsi_target_util.h"
 #include "iscsi_target_parameters.h"
diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h
index a0751e3..9962ccf 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.h
+++ b/drivers/target/iscsi/iscsi_target_parameters.h
@@ -1,6 +1,7 @@
 #ifndef ISCSI_PARAMETERS_H
 #define ISCSI_PARAMETERS_H
 
+#include <linux/types.h>
 #include <scsi/iscsi_proto.h>
 
 struct iscsi_extra_response {
@@ -23,6 +24,11 @@ struct iscsi_param {
 	struct list_head p_list;
 } ____cacheline_aligned;
 
+struct iscsi_conn;
+struct iscsi_conn_ops;
+struct iscsi_param_list;
+struct iscsi_sess_ops;
+
 extern int iscsi_login_rx_data(struct iscsi_conn *, char *, int);
 extern int iscsi_login_tx_data(struct iscsi_conn *, char *, char *, int);
 extern void iscsi_dump_conn_ops(struct iscsi_conn_ops *);
diff --git a/drivers/target/iscsi/iscsi_target_seq_pdu_list.h b/drivers/target/iscsi/iscsi_target_seq_pdu_list.h
index d5b1537..be12343 100644
--- a/drivers/target/iscsi/iscsi_target_seq_pdu_list.h
+++ b/drivers/target/iscsi/iscsi_target_seq_pdu_list.h
@@ -1,6 +1,9 @@
 #ifndef ISCSI_SEQ_AND_PDU_LIST_H
 #define ISCSI_SEQ_AND_PDU_LIST_H
 
+#include <linux/types.h>
+#include <linux/cache.h>
+
 /* struct iscsi_pdu->status */
 #define DATAOUT_PDU_SENT			1
 
@@ -78,6 +81,8 @@ struct iscsi_seq {
 	u32		xfer_len;
 } ____cacheline_aligned;
 
+struct iscsi_cmd;
+
 extern int iscsit_build_pdu_and_seq_lists(struct iscsi_cmd *, u32);
 extern struct iscsi_pdu *iscsit_get_pdu_holder(struct iscsi_cmd *, u32, u32);
 extern struct iscsi_pdu *iscsit_get_pdu_holder_for_seq(struct iscsi_cmd *, struct iscsi_seq *);
diff --git a/drivers/target/iscsi/iscsi_target_tmr.h b/drivers/target/iscsi/iscsi_target_tmr.h
index 142e992..64cc5c0 100644
--- a/drivers/target/iscsi/iscsi_target_tmr.h
+++ b/drivers/target/iscsi/iscsi_target_tmr.h
@@ -1,6 +1,12 @@
 #ifndef ISCSI_TARGET_TMR_H
 #define ISCSI_TARGET_TMR_H
 
+#include <linux/types.h>
+
+struct iscsi_cmd;
+struct iscsi_conn;
+struct iscsi_tmr_req;
+
 extern u8 iscsit_tmr_abort_task(struct iscsi_cmd *, unsigned char *);
 extern int iscsit_tmr_task_warm_reset(struct iscsi_conn *, struct iscsi_tmr_req *,
 			unsigned char *);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 0814e58..2e7e08d 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -16,9 +16,9 @@
  * GNU General Public License for more details.
  ******************************************************************************/
 
+#include <linux/slab.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
-
 #include <target/iscsi/iscsi_target_core.h>
 #include "iscsi_target_erl0.h"
 #include "iscsi_target_login.h"
@@ -260,7 +260,6 @@ int iscsit_tpg_add_portal_group(struct iscsi_tiqn *tiqn, struct iscsi_portal_gro
 		iscsi_release_param_list(tpg->param_list);
 		tpg->param_list = NULL;
 	}
-	kfree(tpg);
 	return -ENOMEM;
 }
 
diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h
index 2da2119..ceba298 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.h
+++ b/drivers/target/iscsi/iscsi_target_tpg.h
@@ -1,6 +1,15 @@
 #ifndef ISCSI_TARGET_TPG_H
 #define ISCSI_TARGET_TPG_H
 
+#include <linux/types.h>
+
+struct iscsi_np;
+struct iscsi_session;
+struct iscsi_tiqn;
+struct iscsi_tpg_np;
+struct se_node_acl;
+struct sockaddr_storage;
+
 extern struct iscsi_portal_group *iscsit_alloc_portal_group(struct iscsi_tiqn *, u16);
 extern int iscsit_load_discovery_tpg(void);
 extern void iscsit_release_discovery_tpg(void);
diff --git a/drivers/target/iscsi/iscsi_target_transport.c b/drivers/target/iscsi/iscsi_target_transport.c
index 08217d6..c4eb141 100644
--- a/drivers/target/iscsi/iscsi_target_transport.c
+++ b/drivers/target/iscsi/iscsi_target_transport.c
@@ -1,5 +1,6 @@
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/module.h>
 #include <target/iscsi/iscsi_transport.h>
 
 static LIST_HEAD(g_transport_list);
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 1f38177..b5a1b4c 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -18,6 +18,7 @@
 
 #include <linux/list.h>
 #include <linux/percpu_ida.h>
+#include <net/ipv6.h>         /* ipv6_addr_equal() */
 #include <scsi/scsi_tcq.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h
index 995f1cb..8ff0885 100644
--- a/drivers/target/iscsi/iscsi_target_util.h
+++ b/drivers/target/iscsi/iscsi_target_util.h
@@ -1,8 +1,16 @@
 #ifndef ISCSI_TARGET_UTIL_H
 #define ISCSI_TARGET_UTIL_H
 
+#include <linux/types.h>
+#include <scsi/iscsi_proto.h>        /* itt_t */
+
 #define MARKER_SIZE	8
 
+struct iscsi_cmd;
+struct iscsi_conn;
+struct iscsi_conn_recovery;
+struct iscsi_session;
+
 extern int iscsit_add_r2t_to_list(struct iscsi_cmd *, u32, u32, int, u32);
 extern struct iscsi_r2t *iscsit_get_r2t_for_eos(struct iscsi_cmd *, u32, u32);
 extern struct iscsi_r2t *iscsit_get_r2t_from_list(struct iscsi_cmd *);
diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h
index 4346462..a8a230b 100644
--- a/drivers/target/loopback/tcm_loop.h
+++ b/drivers/target/loopback/tcm_loop.h
@@ -1,3 +1,7 @@
+#include <linux/types.h>
+#include <linux/device.h>
+#include <target/target_core_base.h> /* struct se_cmd */
+
 #define TCM_LOOP_VERSION		"v2.1-rc2"
 #define TL_WWN_ADDR_LEN			256
 #define TL_TPGS_PER_HBA			32
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index 58bb6ed..e5c3e5f 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -28,6 +28,7 @@
 #include <linux/string.h>
 #include <linux/configfs.h>
 #include <linux/ctype.h>
+#include <linux/delay.h>
 #include <linux/firewire.h>
 #include <linux/firewire-constants.h>
 #include <scsi/scsi_proto.h>
@@ -928,7 +929,7 @@ static struct sbp_target_request *sbp_mgt_get_req(struct sbp_session *sess,
 	struct sbp_target_request *req;
 	int tag;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
 	if (tag < 0)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 4c82bbe..f5e3300 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -26,8 +26,11 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/configfs.h>
+#include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/fcntl.h>
 #include <linux/file.h>
+#include <linux/fs.h>
 #include <scsi/scsi_proto.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h
index 9b250f9..c69c11b 100644
--- a/drivers/target/target_core_alua.h
+++ b/drivers/target/target_core_alua.h
@@ -1,6 +1,8 @@
 #ifndef TARGET_CORE_ALUA_H
 #define TARGET_CORE_ALUA_H
 
+#include <target/target_core_base.h>
+
 /*
  * INQUIRY response data, TPGS Field
  *
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index a35a347..54b36c9 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -144,12 +144,12 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item,
 		return -EINVAL;
 	}
 	if (!S_ISDIR(file_inode(fp)->i_mode)) {
-		filp_close(fp, 0);
+		filp_close(fp, NULL);
 		mutex_unlock(&g_tf_lock);
 		pr_err("db_root: not a directory: %s\n", db_root_stage);
 		return -EINVAL;
 	}
-	filp_close(fp, 0);
+	filp_close(fp, NULL);
 
 	strncpy(db_root, db_root_stage, read_bytes);
 
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 6b42348..1ebd13e 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -33,6 +33,7 @@
 #include <linux/kthread.h>
 #include <linux/in.h>
 #include <linux/export.h>
+#include <linux/t10-pi.h>
 #include <asm/unaligned.h>
 #include <net/sock.h>
 #include <net/tcp.h>
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index d545993..87aa376 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -32,6 +32,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/falloc.h>
+#include <linux/uio.h>
 #include <scsi/scsi_proto.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h
index 068966f..526595a 100644
--- a/drivers/target/target_core_file.h
+++ b/drivers/target/target_core_file.h
@@ -1,6 +1,8 @@
 #ifndef TARGET_CORE_FILE_H
 #define TARGET_CORE_FILE_H
 
+#include <target/target_core_base.h>
+
 #define FD_VERSION		"4.0"
 
 #define FD_MAX_DEV_NAME		256
diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h
index 01c2afd..718d3fc 100644
--- a/drivers/target/target_core_iblock.h
+++ b/drivers/target/target_core_iblock.h
@@ -1,6 +1,9 @@
 #ifndef TARGET_CORE_IBLOCK_H
 #define TARGET_CORE_IBLOCK_H
 
+#include <linux/atomic.h>
+#include <target/target_core_base.h>
+
 #define IBLOCK_VERSION		"4.0"
 
 #define IBLOCK_MAX_CDBS		16
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index e2c970a..9ab7090 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -1,6 +1,11 @@
 #ifndef TARGET_CORE_INTERNAL_H
 #define TARGET_CORE_INTERNAL_H
 
+#include <linux/configfs.h>
+#include <linux/list.h>
+#include <linux/types.h>
+#include <target/target_core_base.h>
+
 #define TARGET_CORE_NAME_MAX_LEN	64
 #define TARGET_FABRIC_NAME_SIZE		32
 
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 47463c9..d761025 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -29,6 +29,8 @@
 #include <linux/list.h>
 #include <linux/vmalloc.h>
 #include <linux/file.h>
+#include <linux/fcntl.h>
+#include <linux/fs.h>
 #include <scsi/scsi_proto.h>
 #include <asm/unaligned.h>
 
@@ -253,8 +255,7 @@ target_scsi2_reservation_reserve(struct se_cmd *cmd)
 
 	if ((cmd->t_task_cdb[1] & 0x01) &&
 	    (cmd->t_task_cdb[1] & 0x02)) {
-		pr_err("LongIO and Obselete Bits set, returning"
-				" ILLEGAL_REQUEST\n");
+		pr_err("LongIO and Obsolete Bits set, returning ILLEGAL_REQUEST\n");
 		return TCM_UNSUPPORTED_SCSI_OPCODE;
 	}
 	/*
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index e3d26e9..847bd47 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -1,5 +1,9 @@
 #ifndef TARGET_CORE_PR_H
 #define TARGET_CORE_PR_H
+
+#include <linux/types.h>
+#include <target/target_core_base.h>
+
 /*
  * PERSISTENT_RESERVE_OUT service action codes
  *
diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h
index 6d2007e..8a02fa4 100644
--- a/drivers/target/target_core_pscsi.h
+++ b/drivers/target/target_core_pscsi.h
@@ -15,11 +15,12 @@
 #define PS_TIMEOUT_DISK		(15*HZ)
 #define PS_TIMEOUT_OTHER	(500*HZ)
 
-#include <linux/device.h>
-#include <linux/kref.h>
-#include <linux/kobject.h>
+#include <linux/cache.h>             /* ___cacheline_aligned */
+#include <target/target_core_base.h> /* struct se_device */
 
+struct block_device;
 struct scsi_device;
+struct Scsi_Host;
 
 struct pscsi_plugin_task {
 	unsigned char pscsi_sense[TRANSPORT_SENSE_BUFFER];
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 24b36fd..ddc216c 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -26,7 +26,9 @@
 
 #include <linux/string.h>
 #include <linux/parser.h>
+#include <linux/highmem.h>
 #include <linux/timer.h>
+#include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <scsi/scsi_proto.h>
diff --git a/drivers/target/target_core_rd.h b/drivers/target/target_core_rd.h
index cc46a6a..91fc1a3 100644
--- a/drivers/target/target_core_rd.h
+++ b/drivers/target/target_core_rd.h
@@ -1,6 +1,10 @@
 #ifndef TARGET_CORE_RD_H
 #define TARGET_CORE_RD_H
 
+#include <linux/module.h>
+#include <linux/types.h>
+#include <target/target_core_base.h>
+
 #define RD_HBA_VERSION		"v4.0"
 #define RD_MCP_VERSION		"4.0"
 
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 04f616b..4879e70 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/ratelimit.h>
 #include <linux/crc-t10dif.h>
+#include <linux/t10-pi.h>
 #include <asm/unaligned.h>
 #include <scsi/scsi_proto.h>
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/target/target_core_ua.h b/drivers/target/target_core_ua.h
index bd6e78b..9740285 100644
--- a/drivers/target/target_core_ua.h
+++ b/drivers/target/target_core_ua.h
@@ -1,6 +1,8 @@
 #ifndef TARGET_CORE_UA_H
 #define TARGET_CORE_UA_H
 
+#include <target/target_core_base.h>
+
 /*
  * From spc4r17, Table D.1: ASC and ASCQ Assignement
  */
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 2b3c856..8041710 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -27,6 +27,7 @@
 #include <linux/uio_driver.h>
 #include <linux/stringify.h>
 #include <linux/bitops.h>
+#include <linux/highmem.h>
 #include <net/genetlink.h>
 #include <scsi/scsi_common.h>
 #include <scsi/scsi_proto.h>
@@ -537,7 +538,7 @@ tcmu_queue_cmd(struct se_cmd *se_cmd)
 	struct se_device *se_dev = se_cmd->se_dev;
 	struct tcmu_dev *udev = TCMU_DEV(se_dev);
 	struct tcmu_cmd *tcmu_cmd;
-	int ret;
+	sense_reason_t ret;
 
 	tcmu_cmd = tcmu_alloc_cmd(se_cmd);
 	if (!tcmu_cmd)
@@ -685,8 +686,6 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data)
 	target_complete_cmd(cmd->se_cmd, SAM_STAT_CHECK_CONDITION);
 	cmd->se_cmd = NULL;
 
-	kmem_cache_free(tcmu_cmd_cache, cmd);
-
 	return 0;
 }
 
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 094a144..37d5cae 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -25,6 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <linux/configfs.h>
+#include <linux/ratelimit.h>
 #include <scsi/scsi_proto.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/target/target_core_xcopy.h b/drivers/target/target_core_xcopy.h
index 700a981..4d3d4dd 100644
--- a/drivers/target/target_core_xcopy.h
+++ b/drivers/target/target_core_xcopy.h
@@ -1,3 +1,5 @@
+#include <target/target_core_base.h>
+
 #define XCOPY_TARGET_DESC_LEN		32
 #define XCOPY_SEGMENT_DESC_LEN		28
 #define XCOPY_NAA_IEEE_REGEX_LEN	16
diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h
index e28209b..11d27b9 100644
--- a/drivers/target/tcm_fc/tcm_fc.h
+++ b/drivers/target/tcm_fc/tcm_fc.h
@@ -17,6 +17,9 @@
 #ifndef __TCM_FC_H__
 #define __TCM_FC_H__
 
+#include <linux/types.h>
+#include <target/target_core_base.h>
+
 #define FT_VERSION "0.4"
 
 #define FT_NAMELEN 32		/* length of ASCII WWPNs including pad */
diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index dfbb974..dea16bb 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -127,7 +127,7 @@ static struct serial_state rs_table[1];
 
 #define NR_PORTS ARRAY_SIZE(rs_table)
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define serial_isroot()	(capable(CAP_SYS_ADMIN))
 
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index ce86487..9b5c0fb 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -42,7 +42,7 @@
 #include <linux/slab.h>
 #include <linux/serial_core.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "hvc_console.h"
 
diff --git a/drivers/tty/hvc/hvcs.c b/drivers/tty/hvc/hvcs.c
index 3c4d7c2..7823d6d 100644
--- a/drivers/tty/hvc/hvcs.c
+++ b/drivers/tty/hvc/hvcs.c
@@ -81,7 +81,7 @@
 #include <linux/tty_flip.h>
 #include <asm/hvconsole.h>
 #include <asm/hvcserver.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/vio.h>
 
 /*
diff --git a/drivers/tty/hvc/hvsi.c b/drivers/tty/hvc/hvsi.c
index 96ce6bd..2e578d6 100644
--- a/drivers/tty/hvc/hvsi.c
+++ b/drivers/tty/hvc/hvsi.c
@@ -46,7 +46,7 @@
 #include <asm/hvcall.h>
 #include <asm/hvconsole.h>
 #include <asm/prom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/vio.h>
 #include <asm/param.h>
 #include <asm/hvsi.h>
diff --git a/drivers/tty/moxa.c b/drivers/tty/moxa.c
index 60d37b2..4caf0c3 100644
--- a/drivers/tty/moxa.c
+++ b/drivers/tty/moxa.c
@@ -47,7 +47,7 @@
 #include <linux/ratelimit.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "moxa.h"
 
diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c
index 69294ae..7b8f383 100644
--- a/drivers/tty/mxser.c
+++ b/drivers/tty/mxser.c
@@ -43,7 +43,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "mxser.h"
 
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index a7fa016..eb27883 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -103,7 +103,7 @@
 #include <linux/bitops.h>
 
 #include <asm/termios.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Buffers for individual HDLC frames
diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c
index 3451114..305b649 100644
--- a/drivers/tty/n_r3964.c
+++ b/drivers/tty/n_r3964.c
@@ -65,7 +65,7 @@
 #include <linux/n_r3964.h>
 #include <linux/poll.h>
 #include <linux/init.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*#define DEBUG_QUEUE*/
 
diff --git a/drivers/tty/serial/icom.c b/drivers/tty/serial/icom.c
index c60a8d5e..d83783c 100644
--- a/drivers/tty/serial/icom.c
+++ b/drivers/tty/serial/icom.c
@@ -53,7 +53,7 @@
 
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "icom.h"
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index d084737..9939c3d 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -36,7 +36,7 @@
 #include <linux/mutex.h>
 
 #include <asm/irq.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * This is used to lock changes in serial line configuration.
diff --git a/drivers/tty/synclink.c b/drivers/tty/synclink.c
index 415885c..657eed8 100644
--- a/drivers/tty/synclink.c
+++ b/drivers/tty/synclink.c
@@ -107,7 +107,7 @@
 #define PUT_USER(error,value,addr) error = put_user(value,addr)
 #define COPY_TO_USER(error,dest,src,size) error = copy_to_user(dest,src,size) ? -EFAULT : 0
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define RCLRVALUE 0xffff
 
diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c
index 8267bcf..31885f2 100644
--- a/drivers/tty/synclink_gt.c
+++ b/drivers/tty/synclink_gt.c
@@ -77,7 +77,7 @@
 #include <asm/irq.h>
 #include <asm/dma.h>
 #include <asm/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #if defined(CONFIG_HDLC) || (defined(CONFIG_HDLC_MODULE) && defined(CONFIG_SYNCLINK_GT_MODULE))
 #define SYNCLINK_GENERIC_HDLC 1
diff --git a/drivers/tty/synclinkmp.c b/drivers/tty/synclinkmp.c
index d66620f..51e8846 100644
--- a/drivers/tty/synclinkmp.c
+++ b/drivers/tty/synclinkmp.c
@@ -79,7 +79,7 @@
 #define PUT_USER(error,value,addr) error = put_user(value,addr)
 #define COPY_TO_USER(error,dest,src,size) error = copy_to_user(dest,src,size) ? -EFAULT : 0
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static MGSL_PARAMS default_params = {
 	MGSL_MODE_HDLC,			/* unsigned long mode */
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index bf36ac9..f27fc0f 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -22,7 +22,7 @@
 #include <linux/compat.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #undef TTY_DEBUG_WAIT_UNTIL_SENT
 
diff --git a/drivers/tty/vt/consolemap.c b/drivers/tty/vt/consolemap.c
index 71e8140..1f6e17f 100644
--- a/drivers/tty/vt/consolemap.c
+++ b/drivers/tty/vt/consolemap.c
@@ -29,7 +29,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/tty.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/console.h>
 #include <linux/consolemap.h>
 #include <linux/vt_kern.h>
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 368ce18..36e1b8c 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -16,7 +16,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/kbd_kern.h>
 #include <linux/vt_kern.h>
diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c
index 14a2b5f..56dcff6 100644
--- a/drivers/tty/vt/vc_screen.c
+++ b/drivers/tty/vt/vc_screen.c
@@ -39,7 +39,7 @@
 #include <linux/slab.h>
 #include <linux/notifier.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index f62c598..a56edf2 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -29,7 +29,7 @@
 #include <linux/timex.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/kbd_kern.h>
 #include <linux/vt_kern.h>
diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c
index 4dec9df..5a59da0 100644
--- a/drivers/usb/atm/usbatm.c
+++ b/drivers/usb/atm/usbatm.c
@@ -64,7 +64,7 @@
 
 #include "usbatm.h"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/crc32.h>
 #include <linux/errno.h>
 #include <linux/init.h>
diff --git a/drivers/usb/chipidea/otg_fsm.c b/drivers/usb/chipidea/otg_fsm.c
index de8e22e..93e24ce 100644
--- a/drivers/usb/chipidea/otg_fsm.c
+++ b/drivers/usb/chipidea/otg_fsm.c
@@ -234,8 +234,8 @@ static void ci_otg_add_timer(struct ci_hdrc *ci, enum otg_fsm_timer t)
 				ktime_set(timer_sec, timer_nsec));
 	ci->enabled_otg_timer_bits |= (1 << t);
 	if ((ci->next_otg_timer == NUM_OTG_FSM_TIMERS) ||
-			(ci->hr_timeouts[ci->next_otg_timer].tv64 >
-						ci->hr_timeouts[t].tv64)) {
+			(ci->hr_timeouts[ci->next_otg_timer] >
+						ci->hr_timeouts[t])) {
 			ci->next_otg_timer = t;
 			hrtimer_start_range_ns(&ci->otg_fsm_hrtimer,
 					ci->hr_timeouts[t], NSEC_PER_MSEC,
@@ -269,8 +269,8 @@ static void ci_otg_del_timer(struct ci_hdrc *ci, enum otg_fsm_timer t)
 			for_each_set_bit(cur_timer, &enabled_timer_bits,
 							NUM_OTG_FSM_TIMERS) {
 				if ((next_timer == NUM_OTG_FSM_TIMERS) ||
-					(ci->hr_timeouts[next_timer].tv64 <
-					ci->hr_timeouts[cur_timer].tv64))
+					(ci->hr_timeouts[next_timer] <
+					 ci->hr_timeouts[cur_timer]))
 					next_timer = cur_timer;
 			}
 		}
@@ -397,14 +397,14 @@ static enum hrtimer_restart ci_otg_hrtimer_func(struct hrtimer *t)
 
 	now = ktime_get();
 	for_each_set_bit(cur_timer, &enabled_timer_bits, NUM_OTG_FSM_TIMERS) {
-		if (now.tv64 >= ci->hr_timeouts[cur_timer].tv64) {
+		if (now >= ci->hr_timeouts[cur_timer]) {
 			ci->enabled_otg_timer_bits &= ~(1 << cur_timer);
 			if (otg_timer_handlers[cur_timer])
 				ret = otg_timer_handlers[cur_timer](ci);
 		} else {
 			if ((next_timer == NUM_OTG_FSM_TIMERS) ||
-				(ci->hr_timeouts[cur_timer].tv64 <
-					ci->hr_timeouts[next_timer].tv64))
+				(ci->hr_timeouts[cur_timer] <
+					ci->hr_timeouts[next_timer]))
 				next_timer = cur_timer;
 		}
 	}
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 143454e..1fa5c0f 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -29,7 +29,7 @@
 #include <linux/random.h>
 #include <linux/pm_qos.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 #include "hub.h"
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index e8008fa..224717e6 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -1113,8 +1113,7 @@ static struct sk_buff *ncm_wrap_ntb(struct gether *port,
 		}
 
 		/* Delay the timer. */
-		hrtimer_start(&ncm->task_timer,
-			      ktime_set(0, TX_TIMEOUT_NSECS),
+		hrtimer_start(&ncm->task_timer, TX_TIMEOUT_NSECS,
 			      HRTIMER_MODE_REL);
 
 		/* Add the datagram position entries */
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index 197f733..d235113 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1073,7 +1073,7 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu,
 	struct usbg_cmd *cmd;
 	int tag;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
 	if (tag < 0)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 10b2576..e8f4102 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -20,7 +20,7 @@
 #include <linux/uts.h>
 #include <linux/wait.h>
 #include <linux/compiler.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/poll.h>
diff --git a/drivers/usb/host/ehci-timer.c b/drivers/usb/host/ehci-timer.c
index 69f50e6..3893b5b 100644
--- a/drivers/usb/host/ehci-timer.c
+++ b/drivers/usb/host/ehci-timer.c
@@ -88,8 +88,7 @@ static void ehci_enable_event(struct ehci_hcd *ehci, unsigned event,
 	ktime_t		*timeout = &ehci->hr_timeouts[event];
 
 	if (resched)
-		*timeout = ktime_add(ktime_get(),
-				ktime_set(0, event_delays_ns[event]));
+		*timeout = ktime_add(ktime_get(), event_delays_ns[event]);
 	ehci->enabled_hrtimer_events |= (1 << event);
 
 	/* Track only the lowest-numbered pending event */
@@ -425,7 +424,7 @@ static enum hrtimer_restart ehci_hrtimer_func(struct hrtimer *t)
 	 */
 	now = ktime_get();
 	for_each_set_bit(e, &events, EHCI_HRTIMER_NUM_EVENTS) {
-		if (now.tv64 >= ehci->hr_timeouts[e].tv64)
+		if (now >= ehci->hr_timeouts[e])
 			event_handlers[e](ehci);
 		else
 			ehci_enable_event(ehci, e, false);
diff --git a/drivers/usb/host/fotg210-hcd.c b/drivers/usb/host/fotg210-hcd.c
index 66efa9a..9d0b051 100644
--- a/drivers/usb/host/fotg210-hcd.c
+++ b/drivers/usb/host/fotg210-hcd.c
@@ -1080,8 +1080,7 @@ static void fotg210_enable_event(struct fotg210_hcd *fotg210, unsigned event,
 	ktime_t *timeout = &fotg210->hr_timeouts[event];
 
 	if (resched)
-		*timeout = ktime_add(ktime_get(),
-				ktime_set(0, event_delays_ns[event]));
+		*timeout = ktime_add(ktime_get(), event_delays_ns[event]);
 	fotg210->enabled_hrtimer_events |= (1 << event);
 
 	/* Track only the lowest-numbered pending event */
@@ -1381,7 +1380,7 @@ static enum hrtimer_restart fotg210_hrtimer_func(struct hrtimer *t)
 	 */
 	now = ktime_get();
 	for_each_set_bit(e, &events, FOTG210_HRTIMER_NUM_EVENTS) {
-		if (now.tv64 >= fotg210->hr_timeouts[e].tv64)
+		if (now >= fotg210->hr_timeouts[e])
 			event_handlers[e](fotg210);
 		else
 			fotg210_enable_event(fotg210, e, false);
diff --git a/drivers/usb/host/uhci-hcd.c b/drivers/usb/host/uhci-hcd.c
index 5d3d914..683098a 100644
--- a/drivers/usb/host/uhci-hcd.c
+++ b/drivers/usb/host/uhci-hcd.c
@@ -42,7 +42,7 @@
 #include <linux/bitops.h>
 #include <linux/dmi.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 
diff --git a/drivers/usb/misc/ftdi-elan.c b/drivers/usb/misc/ftdi-elan.c
index 9a82f83..01a9373 100644
--- a/drivers/usb/misc/ftdi-elan.c
+++ b/drivers/usb/misc/ftdi-elan.c
@@ -48,7 +48,7 @@
 #include <linux/module.h>
 #include <linux/kref.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/usb.h>
 #include <linux/workqueue.h>
 #include <linux/platform_device.h>
diff --git a/drivers/usb/misc/idmouse.c b/drivers/usb/misc/idmouse.c
index 2975e80..debc1fd 100644
--- a/drivers/usb/misc/idmouse.c
+++ b/drivers/usb/misc/idmouse.c
@@ -23,7 +23,7 @@
 #include <linux/module.h>
 #include <linux/completion.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/usb.h>
 
 /* image constants */
diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c
index 9ca5956..3bc5356 100644
--- a/drivers/usb/misc/ldusb.c
+++ b/drivers/usb/misc/ldusb.c
@@ -28,7 +28,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/input.h>
 #include <linux/usb.h>
 #include <linux/poll.h>
diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c
index c8fbe7b..b10e26c 100644
--- a/drivers/usb/misc/legousbtower.c
+++ b/drivers/usb/misc/legousbtower.c
@@ -83,7 +83,7 @@
 #include <linux/module.h>
 #include <linux/completion.h>
 #include <linux/mutex.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/usb.h>
 #include <linux/poll.h>
 
diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c
index 1a874a1..91c2227 100644
--- a/drivers/usb/mon/mon_bin.c
+++ b/drivers/usb/mon/mon_bin.c
@@ -20,7 +20,7 @@
 #include <linux/slab.h>
 #include <linux/time64.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "usb_mon.h"
 
diff --git a/drivers/usb/mon/mon_stat.c b/drivers/usb/mon/mon_stat.c
index 5388a33..5bdf73a 100644
--- a/drivers/usb/mon/mon_stat.c
+++ b/drivers/usb/mon/mon_stat.c
@@ -12,7 +12,7 @@
 #include <linux/export.h>
 #include <linux/usb.h>
 #include <linux/fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "usb_mon.h"
 
diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c
index e59334b..db1a4ab 100644
--- a/drivers/usb/mon/mon_text.c
+++ b/drivers/usb/mon/mon_text.c
@@ -14,7 +14,7 @@
 #include <linux/mutex.h>
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "usb_mon.h"
 
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index d4d7c56..1636385 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -197,8 +197,7 @@ static enum hrtimer_restart cppi41_recheck_tx_req(struct hrtimer *timer)
 	if (!list_empty(&controller->early_tx_list) &&
 	    !hrtimer_is_queued(&controller->early_tx)) {
 		ret = HRTIMER_RESTART;
-		hrtimer_forward_now(&controller->early_tx,
-				ktime_set(0, 20 * NSEC_PER_USEC));
+		hrtimer_forward_now(&controller->early_tx, 20 * NSEC_PER_USEC);
 	}
 
 	spin_unlock_irqrestore(&musb->lock, flags);
@@ -280,9 +279,9 @@ static void cppi41_dma_callback(void *private_data)
 		unsigned long usecs = cppi41_channel->total_len / 10;
 
 		hrtimer_start_range_ns(&controller->early_tx,
-				ktime_set(0, usecs * NSEC_PER_USEC),
-				20 * NSEC_PER_USEC,
-				HRTIMER_MODE_REL);
+				       usecs * NSEC_PER_USEC,
+				       20 * NSEC_PER_USEC,
+				       HRTIMER_MODE_REL);
 	}
 
 out:
diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c
index 9b22d94..4fef50e 100644
--- a/drivers/usb/musb/musb_debugfs.c
+++ b/drivers/usb/musb/musb_debugfs.c
@@ -37,7 +37,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "musb_core.h"
 #include "musb_debug.h"
diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c
index 1e11614..42d02a2 100644
--- a/drivers/video/console/newport_con.c
+++ b/drivers/video/console/newport_con.c
@@ -21,7 +21,7 @@
 #include <linux/slab.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/gio_device.h>
diff --git a/drivers/video/fbdev/68328fb.c b/drivers/video/fbdev/68328fb.c
index 17f21ce..c0c6b88 100644
--- a/drivers/video/fbdev/68328fb.c
+++ b/drivers/video/fbdev/68328fb.c
@@ -35,7 +35,7 @@
 #include <linux/vmalloc.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fb.h>
 #include <linux/init.h>
 
diff --git a/drivers/video/fbdev/hitfb.c b/drivers/video/fbdev/hitfb.c
index 9d68dc9..abe3e54 100644
--- a/drivers/video/fbdev/hitfb.c
+++ b/drivers/video/fbdev/hitfb.c
@@ -22,7 +22,7 @@
 #include <linux/fb.h>
 
 #include <asm/machvec.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/hd64461.h>
diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c
index 9476d19..16f16f5 100644
--- a/drivers/video/fbdev/hpfb.c
+++ b/drivers/video/fbdev/hpfb.c
@@ -16,7 +16,7 @@
 #include <linux/dio.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static struct fb_info fb_info = {
 	.fix = {
diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c
index 8778e01..1c3c7ab 100644
--- a/drivers/video/fbdev/mx3fb.c
+++ b/drivers/video/fbdev/mx3fb.c
@@ -33,7 +33,7 @@
 #include <linux/platform_data/video-mx3fb.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define MX3FB_NAME		"mx3_sdc_fb"
 
diff --git a/drivers/video/fbdev/q40fb.c b/drivers/video/fbdev/q40fb.c
index 7487f76..04ea330 100644
--- a/drivers/video/fbdev/q40fb.c
+++ b/drivers/video/fbdev/q40fb.c
@@ -18,7 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/setup.h>
 #include <asm/q40_master.h>
 #include <linux/fb.h>
diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c
index d0a4e2f..d80bc8a 100644
--- a/drivers/video/fbdev/sm501fb.c
+++ b/drivers/video/fbdev/sm501fb.c
@@ -31,7 +31,7 @@
 #include <linux/console.h>
 #include <linux/io.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/div64.h>
 
 #ifdef CONFIG_PM
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 7df4228..accfef7 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -67,7 +67,7 @@
 #include <linux/io.h>
 
 #include <asm/grfioctl.h>	/* for HP-UX compatibility */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "sticore.h"
 
diff --git a/drivers/video/fbdev/w100fb.c b/drivers/video/fbdev/w100fb.c
index 10951c8..d570e19 100644
--- a/drivers/video/fbdev/w100fb.c
+++ b/drivers/video/fbdev/w100fb.c
@@ -35,7 +35,7 @@
 #include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <video/w100fb.h>
 #include "w100fb.h"
 
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 3eb58cb..acb00b5 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -72,16 +72,16 @@
 	  module will be called softdog.
 
 config DA9052_WATCHDOG
-        tristate "Dialog DA9052 Watchdog"
-        depends on PMIC_DA9052
-        select WATCHDOG_CORE
-        help
-          Support for the watchdog in the DA9052 PMIC. Watchdog trigger
-          cause system reset.
+	tristate "Dialog DA9052 Watchdog"
+	depends on PMIC_DA9052
+	select WATCHDOG_CORE
+	help
+	  Support for the watchdog in the DA9052 PMIC. Watchdog trigger
+	  cause system reset.
 
-          Say Y here to include support for the DA9052 watchdog.
-          Alternatively say M to compile the driver as a module,
-          which will be called da9052_wdt.
+	  Say Y here to include support for the DA9052 watchdog.
+	  Alternatively say M to compile the driver as a module,
+	  which will be called da9052_wdt.
 
 config DA9055_WATCHDOG
 	tristate "Dialog Semiconductor DA9055 Watchdog"
@@ -104,11 +104,11 @@
 	  This driver can be built as a module. The module name is da9063_wdt.
 
 config DA9062_WATCHDOG
-	tristate "Dialog DA9062 Watchdog"
+	tristate "Dialog DA9062/61 Watchdog"
 	depends on MFD_DA9062
 	select WATCHDOG_CORE
 	help
-	  Support for the watchdog in the DA9062 PMIC.
+	  Support for the watchdog in the DA9062 and DA9061 PMICs.
 
 	  This driver can be built as a module. The module name is da9062_wdt.
 
@@ -1008,8 +1008,8 @@
 	tristate "IT87 Watchdog Timer"
 	depends on X86
 	---help---
-	  This is the driver for the hardware watchdog on the ITE IT8702,
-	  IT8712, IT8716, IT8718, IT8720, IT8721, IT8726 and IT8728
+	  This is the driver for the hardware watchdog on the ITE IT8620,
+	  IT8702, IT8712, IT8716, IT8718, IT8720, IT8721, IT8726 and IT8728
 	  Super I/O chips.
 
 	  If the driver does not work, then make sure that the game port in
@@ -1514,6 +1514,13 @@
 	help
 	  Hardware driver for the Lantiq SoC Watchdog Timer.
 
+config LOONGSON1_WDT
+	tristate "Loongson1 SoC hardware watchdog"
+	depends on MACH_LOONGSON32
+	select WATCHDOG_CORE
+	help
+	  Hardware driver for the Loongson1 SoC Watchdog Timer.
+
 config RALINK_WDT
 	tristate "Ralink SoC watchdog"
 	select WATCHDOG_CORE
@@ -1624,16 +1631,16 @@
 	  The value can be overridden by the wdt_period command-line parameter.
 
 config MEN_A21_WDT
-       tristate "MEN A21 VME CPU Carrier Board Watchdog Timer"
-       select WATCHDOG_CORE
-       depends on GPIOLIB || COMPILE_TEST
-       help
-        Watchdog driver for MEN A21 VMEbus CPU Carrier Boards.
+	tristate "MEN A21 VME CPU Carrier Board Watchdog Timer"
+	select WATCHDOG_CORE
+	depends on GPIOLIB || COMPILE_TEST
+	help
+	  Watchdog driver for MEN A21 VMEbus CPU Carrier Boards.
 
-	The driver can also be built as a module. If so, the module will be
-	called mena21_wdt.
+	  The driver can also be built as a module. If so, the module will be
+	  called mena21_wdt.
 
-	If unsure select N here.
+	  If unsure select N here.
 
 # PPC64 Architecture
 
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index caa9f4a..0c3d35e 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -163,6 +163,7 @@
 obj-$(CONFIG_OCTEON_WDT) += octeon-wdt.o
 octeon-wdt-y := octeon-wdt-main.o octeon-wdt-nmi.o
 obj-$(CONFIG_LANTIQ_WDT) += lantiq_wdt.o
+obj-$(CONFIG_LOONGSON1_WDT) += loongson1_wdt.o
 obj-$(CONFIG_RALINK_WDT) += rt2880_wdt.o
 obj-$(CONFIG_IMGPDC_WDT) += imgpdc_wdt.o
 obj-$(CONFIG_MT7621_WDT) += mt7621_wdt.o
diff --git a/drivers/watchdog/bcm2835_wdt.c b/drivers/watchdog/bcm2835_wdt.c
index 4dddd82..c32c45b 100644
--- a/drivers/watchdog/bcm2835_wdt.c
+++ b/drivers/watchdog/bcm2835_wdt.c
@@ -55,6 +55,15 @@ struct bcm2835_wdt {
 static unsigned int heartbeat;
 static bool nowayout = WATCHDOG_NOWAYOUT;
 
+static bool bcm2835_wdt_is_running(struct bcm2835_wdt *wdt)
+{
+	uint32_t cur;
+
+	cur = readl(wdt->base + PM_RSTC);
+
+	return !!(cur & PM_RSTC_WRCFG_FULL_RESET);
+}
+
 static int bcm2835_wdt_start(struct watchdog_device *wdog)
 {
 	struct bcm2835_wdt *wdt = watchdog_get_drvdata(wdog);
@@ -181,6 +190,17 @@ static int bcm2835_wdt_probe(struct platform_device *pdev)
 	watchdog_init_timeout(&bcm2835_wdt_wdd, heartbeat, dev);
 	watchdog_set_nowayout(&bcm2835_wdt_wdd, nowayout);
 	bcm2835_wdt_wdd.parent = &pdev->dev;
+	if (bcm2835_wdt_is_running(wdt)) {
+		/*
+		 * The currently active timeout value (set by the
+		 * bootloader) may be different from the module
+		 * heartbeat parameter or the value in device
+		 * tree. But we just need to set WDOG_HW_RUNNING,
+		 * because then the framework will "immediately" ping
+		 * the device, updating the timeout.
+		 */
+		set_bit(WDOG_HW_RUNNING, &bcm2835_wdt_wdd.status);
+	}
 	err = watchdog_register_device(&bcm2835_wdt_wdd);
 	if (err) {
 		dev_err(dev, "Failed to register watchdog device");
diff --git a/drivers/watchdog/bcm7038_wdt.c b/drivers/watchdog/bcm7038_wdt.c
index e238df4..4814c00 100644
--- a/drivers/watchdog/bcm7038_wdt.c
+++ b/drivers/watchdog/bcm7038_wdt.c
@@ -216,6 +216,7 @@ static const struct of_device_id bcm7038_wdt_match[] = {
 	{ .compatible = "brcm,bcm7038-wdt" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, bcm7038_wdt_match);
 
 static struct platform_driver bcm7038_wdt_driver = {
 	.probe		= bcm7038_wdt_probe,
diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c
index 71ee079..3d43775 100644
--- a/drivers/watchdog/cpwd.c
+++ b/drivers/watchdog/cpwd.c
@@ -538,12 +538,9 @@ static int cpwd_probe(struct platform_device *op)
 	if (cpwd_device)
 		return -EINVAL;
 
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
-	err = -ENOMEM;
-	if (!p) {
-		pr_err("Unable to allocate struct cpwd\n");
-		goto out;
-	}
+	p = devm_kzalloc(&op->dev, sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
 
 	p->irq = op->archdata.irqs[0];
 
@@ -553,12 +550,12 @@ static int cpwd_probe(struct platform_device *op)
 			     4 * WD_TIMER_REGSZ, DRIVER_NAME);
 	if (!p->regs) {
 		pr_err("Unable to map registers\n");
-		goto out_free;
+		return -ENOMEM;
 	}
 
 	options = of_find_node_by_path("/options");
-	err = -ENODEV;
 	if (!options) {
+		err = -ENODEV;
 		pr_err("Unable to find /options node\n");
 		goto out_iounmap;
 	}
@@ -620,10 +617,7 @@ static int cpwd_probe(struct platform_device *op)
 
 	platform_set_drvdata(op, p);
 	cpwd_device = p;
-	err = 0;
-
-out:
-	return err;
+	return 0;
 
 out_unregister:
 	for (i--; i >= 0; i--)
@@ -632,9 +626,7 @@ static int cpwd_probe(struct platform_device *op)
 out_iounmap:
 	of_iounmap(&op->resource[0], p->regs, 4 * WD_TIMER_REGSZ);
 
-out_free:
-	kfree(p);
-	goto out;
+	return err;
 }
 
 static int cpwd_remove(struct platform_device *op)
@@ -659,7 +651,6 @@ static int cpwd_remove(struct platform_device *op)
 		free_irq(p->irq, p);
 
 	of_iounmap(&op->resource[0], p->regs, 4 * WD_TIMER_REGSZ);
-	kfree(p);
 
 	cpwd_device = NULL;
 
diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c
index 7386111..a02cee6 100644
--- a/drivers/watchdog/da9062_wdt.c
+++ b/drivers/watchdog/da9062_wdt.c
@@ -1,5 +1,5 @@
 /*
- * da9062_wdt.c - WDT device driver for DA9062
+ * Watchdog device driver for DA9062 and DA9061 PMICs
  * Copyright (C) 2015  Dialog Semiconductor Ltd.
  *
  * This program is free software; you can redistribute it and/or
@@ -188,6 +188,13 @@ static const struct watchdog_ops da9062_watchdog_ops = {
 	.set_timeout = da9062_wdt_set_timeout,
 };
 
+static const struct of_device_id da9062_compatible_id_table[] = {
+	{ .compatible = "dlg,da9062-watchdog", },
+	{ },
+};
+
+MODULE_DEVICE_TABLE(of, da9062_compatible_id_table);
+
 static int da9062_wdt_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -244,11 +251,12 @@ static struct platform_driver da9062_wdt_driver = {
 	.remove = da9062_wdt_remove,
 	.driver = {
 		.name = "da9062-watchdog",
+		.of_match_table = da9062_compatible_id_table,
 	},
 };
 module_platform_driver(da9062_wdt_driver);
 
 MODULE_AUTHOR("S Twiss <stwiss.opensource@diasemi.com>");
-MODULE_DESCRIPTION("WDT device driver for Dialog DA9062");
+MODULE_DESCRIPTION("WDT device driver for Dialog DA9062 and DA9061");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:da9062-watchdog");
diff --git a/drivers/watchdog/davinci_wdt.c b/drivers/watchdog/davinci_wdt.c
index 17454ca..0e731d7 100644
--- a/drivers/watchdog/davinci_wdt.c
+++ b/drivers/watchdog/davinci_wdt.c
@@ -166,8 +166,12 @@ static int davinci_wdt_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	davinci_wdt->clk = devm_clk_get(dev, NULL);
-	if (WARN_ON(IS_ERR(davinci_wdt->clk)))
+
+	if (IS_ERR(davinci_wdt->clk)) {
+		if (PTR_ERR(davinci_wdt->clk) != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "failed to get clock node\n");
 		return PTR_ERR(davinci_wdt->clk);
+	}
 
 	clk_prepare_enable(davinci_wdt->clk);
 
diff --git a/drivers/watchdog/intel-mid_wdt.c b/drivers/watchdog/intel-mid_wdt.c
index db36d12..a4b7292 100644
--- a/drivers/watchdog/intel-mid_wdt.c
+++ b/drivers/watchdog/intel-mid_wdt.c
@@ -43,6 +43,7 @@ static inline int wdt_command(int sub, u32 *in, int inlen)
 
 static int wdt_start(struct watchdog_device *wd)
 {
+	struct device *dev = watchdog_get_drvdata(wd);
 	int ret, in_size;
 	int timeout = wd->timeout;
 	struct ipc_wd_start {
@@ -57,36 +58,32 @@ static int wdt_start(struct watchdog_device *wd)
 	in_size = DIV_ROUND_UP(sizeof(ipc_wd_start), 4);
 
 	ret = wdt_command(SCU_WATCHDOG_START, (u32 *)&ipc_wd_start, in_size);
-	if (ret) {
-		struct device *dev = watchdog_get_drvdata(wd);
+	if (ret)
 		dev_crit(dev, "error starting watchdog: %d\n", ret);
-	}
 
 	return ret;
 }
 
 static int wdt_ping(struct watchdog_device *wd)
 {
+	struct device *dev = watchdog_get_drvdata(wd);
 	int ret;
 
 	ret = wdt_command(SCU_WATCHDOG_KEEPALIVE, NULL, 0);
-	if (ret) {
-		struct device *dev = watchdog_get_drvdata(wd);
-		dev_crit(dev, "Error executing keepalive: 0x%x\n", ret);
-	}
+	if (ret)
+		dev_crit(dev, "Error executing keepalive: %d\n", ret);
 
 	return ret;
 }
 
 static int wdt_stop(struct watchdog_device *wd)
 {
+	struct device *dev = watchdog_get_drvdata(wd);
 	int ret;
 
 	ret = wdt_command(SCU_WATCHDOG_STOP, NULL, 0);
-	if (ret) {
-		struct device *dev = watchdog_get_drvdata(wd);
-		dev_crit(dev, "Error stopping watchdog: 0x%x\n", ret);
-	}
+	if (ret)
+		dev_crit(dev, "Error stopping watchdog: %d\n", ret);
 
 	return ret;
 }
@@ -151,6 +148,9 @@ static int mid_wdt_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* Make sure the watchdog is not running */
+	wdt_stop(wdt_dev);
+
 	ret = watchdog_register_device(wdt_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "error registering watchdog device\n");
diff --git a/drivers/watchdog/it87_wdt.c b/drivers/watchdog/it87_wdt.c
index e54839b..b9878c4 100644
--- a/drivers/watchdog/it87_wdt.c
+++ b/drivers/watchdog/it87_wdt.c
@@ -12,7 +12,7 @@
  *		    http://www.ite.com.tw/
  *
  *	Support of the watchdog timers, which are available on
- *	IT8702, IT8712, IT8716, IT8718, IT8720, IT8721, IT8726,
+ *	IT8620, IT8702, IT8712, IT8716, IT8718, IT8720, IT8721, IT8726,
  *	IT8728 and IT8783.
  *
  *	This program is free software; you can redistribute it and/or
@@ -78,6 +78,7 @@
 
 /* Chip Id numbers */
 #define NO_DEV_ID	0xffff
+#define IT8620_ID	0x8620
 #define IT8702_ID	0x8702
 #define IT8705_ID	0x8705
 #define IT8712_ID	0x8712
@@ -630,6 +631,7 @@ static int __init it87_wdt_init(void)
 	case IT8726_ID:
 		max_units = 65535;
 		break;
+	case IT8620_ID:
 	case IT8718_ID:
 	case IT8720_ID:
 	case IT8721_ID:
diff --git a/drivers/watchdog/jz4740_wdt.c b/drivers/watchdog/jz4740_wdt.c
index c8d51dd..20627f2 100644
--- a/drivers/watchdog/jz4740_wdt.c
+++ b/drivers/watchdog/jz4740_wdt.c
@@ -148,7 +148,7 @@ static const struct of_device_id jz4740_wdt_of_matches[] = {
 	{ .compatible = "ingenic,jz4740-watchdog", },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, jz4740_wdt_of_matches)
+MODULE_DEVICE_TABLE(of, jz4740_wdt_of_matches);
 #endif
 
 static int jz4740_wdt_probe(struct platform_device *pdev)
diff --git a/drivers/watchdog/loongson1_wdt.c b/drivers/watchdog/loongson1_wdt.c
new file mode 100644
index 0000000..3aee50c
--- /dev/null
+++ b/drivers/watchdog/loongson1_wdt.c
@@ -0,0 +1,170 @@
+/*
+ * Copyright (c) 2016 Yang Ling <gnaygnil@gmail.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.
+ */
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/watchdog.h>
+#include <loongson1.h>
+
+#define DEFAULT_HEARTBEAT	30
+
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0444);
+
+static unsigned int heartbeat;
+module_param(heartbeat, uint, 0444);
+
+struct ls1x_wdt_drvdata {
+	void __iomem *base;
+	struct clk *clk;
+	unsigned long clk_rate;
+	struct watchdog_device wdt;
+};
+
+static int ls1x_wdt_ping(struct watchdog_device *wdt_dev)
+{
+	struct ls1x_wdt_drvdata *drvdata = watchdog_get_drvdata(wdt_dev);
+
+	writel(0x1, drvdata->base + WDT_SET);
+
+	return 0;
+}
+
+static int ls1x_wdt_set_timeout(struct watchdog_device *wdt_dev,
+				unsigned int timeout)
+{
+	struct ls1x_wdt_drvdata *drvdata = watchdog_get_drvdata(wdt_dev);
+	unsigned int max_hw_heartbeat = wdt_dev->max_hw_heartbeat_ms / 1000;
+	unsigned int counts;
+
+	wdt_dev->timeout = timeout;
+
+	counts = drvdata->clk_rate * min(timeout, max_hw_heartbeat);
+	writel(counts, drvdata->base + WDT_TIMER);
+
+	return 0;
+}
+
+static int ls1x_wdt_start(struct watchdog_device *wdt_dev)
+{
+	struct ls1x_wdt_drvdata *drvdata = watchdog_get_drvdata(wdt_dev);
+
+	writel(0x1, drvdata->base + WDT_EN);
+
+	return 0;
+}
+
+static int ls1x_wdt_stop(struct watchdog_device *wdt_dev)
+{
+	struct ls1x_wdt_drvdata *drvdata = watchdog_get_drvdata(wdt_dev);
+
+	writel(0x0, drvdata->base + WDT_EN);
+
+	return 0;
+}
+
+static const struct watchdog_info ls1x_wdt_info = {
+	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
+	.identity = "Loongson1 Watchdog",
+};
+
+static const struct watchdog_ops ls1x_wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = ls1x_wdt_start,
+	.stop = ls1x_wdt_stop,
+	.ping = ls1x_wdt_ping,
+	.set_timeout = ls1x_wdt_set_timeout,
+};
+
+static int ls1x_wdt_probe(struct platform_device *pdev)
+{
+	struct ls1x_wdt_drvdata *drvdata;
+	struct watchdog_device *ls1x_wdt;
+	unsigned long clk_rate;
+	struct resource *res;
+	int err;
+
+	drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	drvdata->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(drvdata->base))
+		return PTR_ERR(drvdata->base);
+
+	drvdata->clk = devm_clk_get(&pdev->dev, pdev->name);
+	if (IS_ERR(drvdata->clk))
+		return PTR_ERR(drvdata->clk);
+
+	err = clk_prepare_enable(drvdata->clk);
+	if (err) {
+		dev_err(&pdev->dev, "clk enable failed\n");
+		return err;
+	}
+
+	clk_rate = clk_get_rate(drvdata->clk);
+	if (!clk_rate) {
+		err = -EINVAL;
+		goto err0;
+	}
+	drvdata->clk_rate = clk_rate;
+
+	ls1x_wdt = &drvdata->wdt;
+	ls1x_wdt->info = &ls1x_wdt_info;
+	ls1x_wdt->ops = &ls1x_wdt_ops;
+	ls1x_wdt->timeout = DEFAULT_HEARTBEAT;
+	ls1x_wdt->min_timeout = 1;
+	ls1x_wdt->max_hw_heartbeat_ms = U32_MAX / clk_rate * 1000;
+	ls1x_wdt->parent = &pdev->dev;
+
+	watchdog_init_timeout(ls1x_wdt, heartbeat, &pdev->dev);
+	watchdog_set_nowayout(ls1x_wdt, nowayout);
+	watchdog_set_drvdata(ls1x_wdt, drvdata);
+
+	err = watchdog_register_device(&drvdata->wdt);
+	if (err) {
+		dev_err(&pdev->dev, "failed to register watchdog device\n");
+		goto err0;
+	}
+
+	platform_set_drvdata(pdev, drvdata);
+
+	dev_info(&pdev->dev, "Loongson1 Watchdog driver registered\n");
+
+	return 0;
+err0:
+	clk_disable_unprepare(drvdata->clk);
+	return err;
+}
+
+static int ls1x_wdt_remove(struct platform_device *pdev)
+{
+	struct ls1x_wdt_drvdata *drvdata = platform_get_drvdata(pdev);
+
+	watchdog_unregister_device(&drvdata->wdt);
+	clk_disable_unprepare(drvdata->clk);
+
+	return 0;
+}
+
+static struct platform_driver ls1x_wdt_driver = {
+	.probe = ls1x_wdt_probe,
+	.remove = ls1x_wdt_remove,
+	.driver = {
+		.name = "ls1x-wdt",
+	},
+};
+
+module_platform_driver(ls1x_wdt_driver);
+
+MODULE_AUTHOR("Yang Ling <gnaygnil@gmail.com>");
+MODULE_DESCRIPTION("Loongson1 Watchdog Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/max77620_wdt.c b/drivers/watchdog/max77620_wdt.c
index 48b84df..68c41fa 100644
--- a/drivers/watchdog/max77620_wdt.c
+++ b/drivers/watchdog/max77620_wdt.c
@@ -205,6 +205,7 @@ static struct platform_device_id max77620_wdt_devtype[] = {
 	{ .name = "max77620-watchdog", },
 	{ },
 };
+MODULE_DEVICE_TABLE(platform, max77620_wdt_devtype);
 
 static struct platform_driver max77620_wdt_driver = {
 	.driver	= {
diff --git a/drivers/watchdog/mei_wdt.c b/drivers/watchdog/mei_wdt.c
index 79b3551..b29c6fd 100644
--- a/drivers/watchdog/mei_wdt.c
+++ b/drivers/watchdog/mei_wdt.c
@@ -389,6 +389,8 @@ static int mei_wdt_register(struct mei_wdt *wdt)
 	wdt->wdd.max_timeout = MEI_WDT_MAX_TIMEOUT;
 
 	watchdog_set_drvdata(&wdt->wdd, wdt);
+	watchdog_stop_on_reboot(&wdt->wdd);
+
 	ret = watchdog_register_device(&wdt->wdd);
 	if (ret) {
 		dev_err(dev, "unable to register watchdog device = %d.\n", ret);
diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c
index 44d180a..45d4766 100644
--- a/drivers/watchdog/meson_gxbb_wdt.c
+++ b/drivers/watchdog/meson_gxbb_wdt.c
@@ -264,7 +264,6 @@ static struct platform_driver meson_gxbb_wdt_driver = {
 
 module_platform_driver(meson_gxbb_wdt_driver);
 
-MODULE_ALIAS("platform:meson-gxbb-wdt");
 MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
 MODULE_DESCRIPTION("Amlogic Meson GXBB Watchdog timer driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/watchdog/mpc8xxx_wdt.c b/drivers/watchdog/mpc8xxx_wdt.c
index 5f2273a..366e5c7 100644
--- a/drivers/watchdog/mpc8xxx_wdt.c
+++ b/drivers/watchdog/mpc8xxx_wdt.c
@@ -23,7 +23,6 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/timer.h>
-#include <linux/miscdevice.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/module.h>
diff --git a/drivers/watchdog/octeon-wdt-main.c b/drivers/watchdog/octeon-wdt-main.c
index 529182d..b5cdceb 100644
--- a/drivers/watchdog/octeon-wdt-main.c
+++ b/drivers/watchdog/octeon-wdt-main.c
@@ -56,7 +56,6 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/miscdevice.h>
 #include <linux/interrupt.h>
 #include <linux/watchdog.h>
 #include <linux/cpumask.h>
diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c
index 5796b5d..4f47b5e 100644
--- a/drivers/watchdog/qcom-wdt.c
+++ b/drivers/watchdog/qcom-wdt.c
@@ -209,7 +209,7 @@ static int qcom_wdt_probe(struct platform_device *pdev)
 	wdt->wdd.parent = &pdev->dev;
 	wdt->layout = regs;
 
-	if (readl(wdt->base + WDT_STS) & 1)
+	if (readl(wdt_addr(wdt, WDT_STS)) & 1)
 		wdt->wdd.bootstatus = WDIOF_CARDRESET;
 
 	/*
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 7ef27c6..c03f9c8 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -445,7 +445,7 @@ int __init xen_evtchn_fifo_init(void)
 	evtchn_ops = &evtchn_ops_fifo;
 
 	cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE,
-				  "CPUHP_XEN_EVTCHN_PREPARE",
+				  "xen/evtchn:prepare",
 				  xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead);
 out:
 	put_cpu();
diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c
index 6ac2579..0539730 100644
--- a/drivers/zorro/proc.c
+++ b/drivers/zorro/proc.c
@@ -16,7 +16,7 @@
 #include <linux/export.h>
 
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/amigahw.h>
 #include <asm/setup.h>
 
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index d7b78d5..6a0f3fa 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -34,7 +34,7 @@
 #include <linux/list.h>
 #include <linux/pagemap.h>
 #include <linux/utsname.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/idr.h>
 #include <linux/uio.h>
 #include <linux/slab.h>
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 2853b40..35efb9a 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -14,7 +14,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/sched.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 
 static struct proc_dir_entry *proc_afs;
diff --git a/fs/aio.c b/fs/aio.c
index 8edf253..4ab67e8 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -42,7 +42,7 @@
 #include <linux/mount.h>
 
 #include <asm/kmap_types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 
@@ -1285,7 +1285,7 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
 			struct io_event __user *event,
 			struct timespec __user *timeout)
 {
-	ktime_t until = { .tv64 = KTIME_MAX };
+	ktime_t until = KTIME_MAX;
 	long ret = 0;
 
 	if (timeout) {
@@ -1311,7 +1311,7 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
 	 * the ringbuffer empty. So in practice we should be ok, but it's
 	 * something to be aware of when touching this code.
 	 */
-	if (until.tv64 == 0)
+	if (until == 0)
 		aio_read_events(ctx, min_nr, nr, event, &ret);
 	else
 		wait_event_interruptible_hrtimeout(ctx->wait,
@@ -1367,6 +1367,39 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	return ret;
 }
 
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_events, u32 __user *, ctx32p)
+{
+	struct kioctx *ioctx = NULL;
+	unsigned long ctx;
+	long ret;
+
+	ret = get_user(ctx, ctx32p);
+	if (unlikely(ret))
+		goto out;
+
+	ret = -EINVAL;
+	if (unlikely(ctx || nr_events == 0)) {
+		pr_debug("EINVAL: ctx %lu nr_events %u\n",
+		         ctx, nr_events);
+		goto out;
+	}
+
+	ioctx = ioctx_alloc(nr_events);
+	ret = PTR_ERR(ioctx);
+	if (!IS_ERR(ioctx)) {
+		/* truncating is ok because it's a user address */
+		ret = put_user((u32)ioctx->user_id, ctx32p);
+		if (ret)
+			kill_ioctx(current->mm, ioctx, NULL);
+		percpu_ref_put(&ioctx->users);
+	}
+
+out:
+	return ret;
+}
+#endif
+
 /* sys_io_destroy:
  *	Destroy the aio_context specified.  May cancel any outstanding 
  *	AIOs and block on completion.  Will fail with -ENOSYS if not
@@ -1591,8 +1624,8 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	return ret;
 }
 
-long do_io_submit(aio_context_t ctx_id, long nr,
-		  struct iocb __user *__user *iocbpp, bool compat)
+static long do_io_submit(aio_context_t ctx_id, long nr,
+			  struct iocb __user *__user *iocbpp, bool compat)
 {
 	struct kioctx *ctx;
 	long ret = 0;
@@ -1662,6 +1695,44 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 	return do_io_submit(ctx_id, nr, iocbpp, 0);
 }
 
+#ifdef CONFIG_COMPAT
+static inline long
+copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
+{
+	compat_uptr_t uptr;
+	int i;
+
+	for (i = 0; i < nr; ++i) {
+		if (get_user(uptr, ptr32 + i))
+			return -EFAULT;
+		if (put_user(compat_ptr(uptr), ptr64 + i))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+#define MAX_AIO_SUBMITS 	(PAGE_SIZE/sizeof(struct iocb *))
+
+COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
+		       int, nr, u32 __user *, iocb)
+{
+	struct iocb __user * __user *iocb64;
+	long ret;
+
+	if (unlikely(nr < 0))
+		return -EINVAL;
+
+	if (nr > MAX_AIO_SUBMITS)
+		nr = MAX_AIO_SUBMITS;
+
+	iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64));
+	ret = copy_iocb(nr, iocb, iocb64);
+	if (!ret)
+		ret = do_io_submit(ctx_id, nr, iocb64, 1);
+	return ret;
+}
+#endif
+
 /* lookup_kiocb
  *	Finds a given iocb for cancellation.
  */
@@ -1761,3 +1832,25 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
 	}
 	return ret;
 }
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
+		       compat_long_t, min_nr,
+		       compat_long_t, nr,
+		       struct io_event __user *, events,
+		       struct compat_timespec __user *, timeout)
+{
+	struct timespec t;
+	struct timespec __user *ut = NULL;
+
+	if (timeout) {
+		if (compat_get_timespec(&t, timeout))
+			return -EFAULT;
+
+		ut = compat_alloc_user_space(sizeof(*ut));
+		if (copy_to_user(ut, &t, sizeof(t)))
+			return -EFAULT;
+	}
+	return sys_io_getevents(ctx_id, min_nr, nr, events, ut);
+}
+#endif
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 80ef38c..3168ee4 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -20,7 +20,7 @@
 #include <linux/magic.h>
 #include <linux/anon_inodes.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static struct vfsmount *anon_inode_mnt __read_mostly;
 static struct inode *anon_inode_inode;
diff --git a/fs/befs/befs.h b/fs/befs/befs.h
index c6bad51..b914cfb 100644
--- a/fs/befs/befs.h
+++ b/fs/befs/befs.h
@@ -129,6 +129,7 @@ static inline befs_inode_addr
 blockno2iaddr(struct super_block *sb, befs_blocknr_t blockno)
 {
 	befs_inode_addr iaddr;
+
 	iaddr.allocation_group = blockno >> BEFS_SB(sb)->ag_shift;
 	iaddr.start =
 	    blockno - (iaddr.allocation_group << BEFS_SB(sb)->ag_shift);
@@ -140,7 +141,7 @@ blockno2iaddr(struct super_block *sb, befs_blocknr_t blockno)
 static inline unsigned int
 befs_iaddrs_per_block(struct super_block *sb)
 {
-	return BEFS_SB(sb)->block_size / sizeof (befs_disk_inode_addr);
+	return BEFS_SB(sb)->block_size / sizeof(befs_disk_inode_addr);
 }
 
 #include "endian.h"
diff --git a/fs/befs/befs_fs_types.h b/fs/befs/befs_fs_types.h
index eb557d9..69c9d8c 100644
--- a/fs/befs/befs_fs_types.h
+++ b/fs/befs/befs_fs_types.h
@@ -55,12 +55,12 @@ enum super_flags {
 };
 
 #define BEFS_BYTEORDER_NATIVE 0x42494745
-#define BEFS_BYTEORDER_NATIVE_LE (__force fs32)cpu_to_le32(BEFS_BYTEORDER_NATIVE)
-#define BEFS_BYTEORDER_NATIVE_BE (__force fs32)cpu_to_be32(BEFS_BYTEORDER_NATIVE)
+#define BEFS_BYTEORDER_NATIVE_LE ((__force fs32)cpu_to_le32(BEFS_BYTEORDER_NATIVE))
+#define BEFS_BYTEORDER_NATIVE_BE ((__force fs32)cpu_to_be32(BEFS_BYTEORDER_NATIVE))
 
 #define BEFS_SUPER_MAGIC BEFS_SUPER_MAGIC1
-#define BEFS_SUPER_MAGIC1_LE (__force fs32)cpu_to_le32(BEFS_SUPER_MAGIC1)
-#define BEFS_SUPER_MAGIC1_BE (__force fs32)cpu_to_be32(BEFS_SUPER_MAGIC1)
+#define BEFS_SUPER_MAGIC1_LE ((__force fs32)cpu_to_le32(BEFS_SUPER_MAGIC1))
+#define BEFS_SUPER_MAGIC1_BE ((__force fs32)cpu_to_be32(BEFS_SUPER_MAGIC1))
 
 /*
  * Flags of inode
@@ -79,7 +79,7 @@ enum inode_flags {
 	BEFS_INODE_WAS_WRITTEN = 0x00020000,
 	BEFS_NO_TRANSACTION = 0x00040000,
 };
-/* 
+/*
  * On-Disk datastructures of BeFS
  */
 
@@ -139,7 +139,7 @@ typedef struct {
 
 } PACKED befs_super_block;
 
-/* 
+/*
  * Note: the indirect and dbl_indir block_runs may
  * be longer than one block!
  */
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index 7e135ea..d509887 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -12,8 +12,8 @@
  *
  * Dominic Giampaolo, author of "Practical File System
  * Design with the Be File System", for such a helpful book.
- * 
- * Marcus J. Ranum, author of the b+tree package in 
+ *
+ * Marcus J. Ranum, author of the b+tree package in
  * comp.sources.misc volume 10. This code is not copied from that
  * work, but it is partially based on it.
  *
@@ -38,38 +38,38 @@
  */
 
 /* Befs B+tree structure:
- * 
+ *
  * The first thing in the tree is the tree superblock. It tells you
  * all kinds of useful things about the tree, like where the rootnode
  * is located, and the size of the nodes (always 1024 with current version
  * of BeOS).
  *
  * The rest of the tree consists of a series of nodes. Nodes contain a header
- * (struct befs_btree_nodehead), the packed key data, an array of shorts 
+ * (struct befs_btree_nodehead), the packed key data, an array of shorts
  * containing the ending offsets for each of the keys, and an array of
- * befs_off_t values. In interior nodes, the keys are the ending keys for 
- * the childnode they point to, and the values are offsets into the 
- * datastream containing the tree. 
+ * befs_off_t values. In interior nodes, the keys are the ending keys for
+ * the childnode they point to, and the values are offsets into the
+ * datastream containing the tree.
  */
 
 /* Note:
- * 
- * The book states 2 confusing things about befs b+trees. First, 
+ *
+ * The book states 2 confusing things about befs b+trees. First,
  * it states that the overflow field of node headers is used by internal nodes
  * to point to another node that "effectively continues this one". Here is what
  * I believe that means. Each key in internal nodes points to another node that
- * contains key values less than itself. Inspection reveals that the last key 
- * in the internal node is not the last key in the index. Keys that are 
- * greater than the last key in the internal node go into the overflow node. 
+ * contains key values less than itself. Inspection reveals that the last key
+ * in the internal node is not the last key in the index. Keys that are
+ * greater than the last key in the internal node go into the overflow node.
  * I imagine there is a performance reason for this.
  *
- * Second, it states that the header of a btree node is sufficient to 
- * distinguish internal nodes from leaf nodes. Without saying exactly how. 
+ * Second, it states that the header of a btree node is sufficient to
+ * distinguish internal nodes from leaf nodes. Without saying exactly how.
  * After figuring out the first, it becomes obvious that internal nodes have
  * overflow nodes and leafnodes do not.
  */
 
-/* 
+/*
  * Currently, this code is only good for directory B+trees.
  * In order to be used for other BFS indexes, it needs to be extended to handle
  * duplicate keys and non-string keytypes (int32, int64, float, double).
@@ -237,8 +237,8 @@ befs_bt_read_node(struct super_block *sb, const befs_data_stream *ds,
  * with @key (usually the disk block number of an inode).
  *
  * On failure, returns BEFS_ERR or BEFS_BT_NOT_FOUND.
- * 
- * Algorithm: 
+ *
+ * Algorithm:
  *   Read the superblock and rootnode of the b+tree.
  *   Drill down through the interior nodes using befs_find_key().
  *   Once at the correct leaf node, use befs_find_key() again to get the
@@ -402,12 +402,12 @@ befs_find_key(struct super_block *sb, struct befs_btree_node *node,
  *
  * Here's how it works: Key_no is the index of the key/value pair to
  * return in keybuf/value.
- * Bufsize is the size of keybuf (BEFS_NAME_LEN+1 is a good size). Keysize is 
+ * Bufsize is the size of keybuf (BEFS_NAME_LEN+1 is a good size). Keysize is
  * the number of characters in the key (just a convenience).
  *
  * Algorithm:
  *   Get the first leafnode of the tree. See if the requested key is in that
- *   node. If not, follow the node->right link to the next leafnode. Repeat 
+ *   node. If not, follow the node->right link to the next leafnode. Repeat
  *   until the (key_no)th key is found or the tree is out of keys.
  */
 int
@@ -536,7 +536,7 @@ befs_btree_read(struct super_block *sb, const befs_data_stream *ds,
  * @node_off: Pointer to offset of current node within datastream. Modified
  * 		by the function.
  *
- * Helper function for btree traverse. Moves the current position to the 
+ * Helper function for btree traverse. Moves the current position to the
  * start of the first leaf node.
  *
  * Also checks for an empty tree. If there are no keys, returns BEFS_BT_EMPTY.
@@ -592,10 +592,10 @@ befs_btree_seekleaf(struct super_block *sb, const befs_data_stream *ds,
 }
 
 /**
- * befs_leafnode - Determine if the btree node is a leaf node or an 
+ * befs_leafnode - Determine if the btree node is a leaf node or an
  * interior node
  * @node: Pointer to node structure to test
- * 
+ *
  * Return 1 if leaf, 0 if interior
  */
 static int
@@ -656,7 +656,7 @@ befs_bt_valarray(struct befs_btree_node *node)
  * @node: Pointer to the node structure to find the keydata array within
  *
  * Returns a pointer to the start of the keydata array
- * of the node pointed to by the node header 
+ * of the node pointed to by the node header
  */
 static char *
 befs_bt_keydata(struct befs_btree_node *node)
@@ -702,7 +702,7 @@ befs_bt_get_key(struct super_block *sb, struct befs_btree_node *node,
 
 /**
  * befs_compare_strings - compare two strings
- * @key1: pointer to the first key to be compared 
+ * @key1: pointer to the first key to be compared
  * @keylen1: length in bytes of key1
  * @key2: pointer to the second key to be compared
  * @keylen2: length in bytes of key2
diff --git a/fs/befs/btree.h b/fs/befs/btree.h
index f2a8f63..60c6c72 100644
--- a/fs/befs/btree.h
+++ b/fs/befs/btree.h
@@ -1,13 +1,11 @@
 /*
  * btree.h
- * 
+ *
  */
 
-
 int befs_btree_find(struct super_block *sb, const befs_data_stream *ds,
-		    const char *key, befs_off_t * value);
+		    const char *key, befs_off_t *value);
 
 int befs_btree_read(struct super_block *sb, const befs_data_stream *ds,
 		    loff_t key_no, size_t bufsize, char *keybuf,
-		    size_t * keysize, befs_off_t * value);
-
+		    size_t *keysize, befs_off_t *value);
diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c
index b4c7ba0..720b3bc 100644
--- a/fs/befs/datastream.c
+++ b/fs/befs/datastream.c
@@ -84,13 +84,11 @@ befs_read_datastream(struct super_block *sb, const befs_data_stream *ds,
  *
  * Takes a file position and gives back a brun who's starting block
  * is block number fblock of the file.
- * 
+ *
  * Returns BEFS_OK or BEFS_ERR.
- * 
+ *
  * Calls specialized functions for each of the three possible
  * datastream regions.
- *
- * 2001-11-15 Will Dyson
  */
 int
 befs_fblock2brun(struct super_block *sb, const befs_data_stream *data,
@@ -120,7 +118,7 @@ befs_fblock2brun(struct super_block *sb, const befs_data_stream *data,
 
 /**
  * befs_read_lsmylink - read long symlink from datastream.
- * @sb: Filesystem superblock 
+ * @sb: Filesystem superblock
  * @ds: Datastream to read from
  * @buff: Buffer in which to place long symlink data
  * @len: Length of the long symlink in bytes
diff --git a/fs/befs/datastream.h b/fs/befs/datastream.h
index 91ba820..7ff9ff0 100644
--- a/fs/befs/datastream.h
+++ b/fs/befs/datastream.h
@@ -5,10 +5,10 @@
 
 struct buffer_head *befs_read_datastream(struct super_block *sb,
 					 const befs_data_stream *ds,
-					 befs_off_t pos, uint * off);
+					 befs_off_t pos, uint *off);
 
 int befs_fblock2brun(struct super_block *sb, const befs_data_stream *data,
-		     befs_blocknr_t fblock, befs_block_run * run);
+		     befs_blocknr_t fblock, befs_block_run *run);
 
 size_t befs_read_lsymlink(struct super_block *sb, const befs_data_stream *data,
 			  void *buff, befs_off_t len);
@@ -17,4 +17,3 @@ befs_blocknr_t befs_count_blocks(struct super_block *sb,
 			  const befs_data_stream *ds);
 
 extern const befs_inode_addr BAD_IADDR;
-
diff --git a/fs/befs/debug.c b/fs/befs/debug.c
index 85c1339..36656c8 100644
--- a/fs/befs/debug.c
+++ b/fs/befs/debug.c
@@ -1,6 +1,6 @@
 /*
  *  linux/fs/befs/debug.c
- * 
+ *
  * Copyright (C) 2001 Will Dyson (will_dyson at pobox.com)
  *
  * With help from the ntfs-tng driver by Anton Altparmakov
@@ -57,6 +57,7 @@ befs_debug(const struct super_block *sb, const char *fmt, ...)
 
 	struct va_format vaf;
 	va_list args;
+
 	va_start(args, fmt);
 	vaf.fmt = fmt;
 	vaf.va = &args;
@@ -67,7 +68,7 @@ befs_debug(const struct super_block *sb, const char *fmt, ...)
 }
 
 void
-befs_dump_inode(const struct super_block *sb, befs_inode * inode)
+befs_dump_inode(const struct super_block *sb, befs_inode *inode)
 {
 #ifdef CONFIG_BEFS_DEBUG
 
@@ -151,7 +152,7 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode)
  */
 
 void
-befs_dump_super_block(const struct super_block *sb, befs_super_block * sup)
+befs_dump_super_block(const struct super_block *sb, befs_super_block *sup)
 {
 #ifdef CONFIG_BEFS_DEBUG
 
@@ -202,7 +203,7 @@ befs_dump_super_block(const struct super_block *sb, befs_super_block * sup)
 #if 0
 /* unused */
 void
-befs_dump_small_data(const struct super_block *sb, befs_small_data * sd)
+befs_dump_small_data(const struct super_block *sb, befs_small_data *sd)
 {
 }
 
@@ -221,7 +222,8 @@ befs_dump_run(const struct super_block *sb, befs_disk_block_run run)
 #endif  /*  0  */
 
 void
-befs_dump_index_entry(const struct super_block *sb, befs_disk_btree_super * super)
+befs_dump_index_entry(const struct super_block *sb,
+		      befs_disk_btree_super *super)
 {
 #ifdef CONFIG_BEFS_DEBUG
 
@@ -242,7 +244,7 @@ befs_dump_index_entry(const struct super_block *sb, befs_disk_btree_super * supe
 }
 
 void
-befs_dump_index_node(const struct super_block *sb, befs_btree_nodehead * node)
+befs_dump_index_node(const struct super_block *sb, befs_btree_nodehead *node)
 {
 #ifdef CONFIG_BEFS_DEBUG
 
diff --git a/fs/befs/inode.c b/fs/befs/inode.c
index fa4b718..5367a64 100644
--- a/fs/befs/inode.c
+++ b/fs/befs/inode.c
@@ -1,6 +1,6 @@
 /*
  * inode.c
- * 
+ *
  * Copyright (C) 2001 Will Dyson <will_dyson@pobox.com>
  */
 
@@ -10,12 +10,12 @@
 #include "inode.h"
 
 /*
-	Validates the correctness of the befs inode
-	Returns BEFS_OK if the inode should be used, otherwise
-	returns BEFS_BAD_INODE
-*/
+ * Validates the correctness of the befs inode
+ * Returns BEFS_OK if the inode should be used, otherwise
+ * returns BEFS_BAD_INODE
+ */
 int
-befs_check_inode(struct super_block *sb, befs_inode * raw_inode,
+befs_check_inode(struct super_block *sb, befs_inode *raw_inode,
 		 befs_blocknr_t inode)
 {
 	u32 magic1 = fs32_to_cpu(sb, raw_inode->magic1);
diff --git a/fs/befs/inode.h b/fs/befs/inode.h
index 9dc7fd9..2219e41 100644
--- a/fs/befs/inode.h
+++ b/fs/befs/inode.h
@@ -1,8 +1,7 @@
 /*
  * inode.h
- * 
+ *
  */
 
-int befs_check_inode(struct super_block *sb, befs_inode * raw_inode,
+int befs_check_inode(struct super_block *sb, befs_inode *raw_inode,
 		     befs_blocknr_t inode);
-
diff --git a/fs/befs/io.c b/fs/befs/io.c
index b4a5581..227cb86 100644
--- a/fs/befs/io.c
+++ b/fs/befs/io.c
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2001 Will Dyson <will_dyson@pobox.com
  *
- * Based on portions of file.c and inode.c 
+ * Based on portions of file.c and inode.c
  * by Makoto Kato (m_kato@ga2.so-net.ne.jp)
  *
  * Many thanks to Dominic Giampaolo, author of Practical File System
@@ -19,8 +19,7 @@
 /*
  * Converts befs notion of disk addr to a disk offset and uses
  * linux kernel function sb_bread() to get the buffer containing
- * the offset. -Will Dyson
- *
+ * the offset.
  */
 
 struct buffer_head *
@@ -55,7 +54,7 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
 	befs_debug(sb, "<--- %s", __func__);
 	return bh;
 
-      error:
+error:
 	befs_debug(sb, "<--- %s ERROR", __func__);
 	return NULL;
 }
diff --git a/fs/befs/io.h b/fs/befs/io.h
index 78d7bc6..9b3e196 100644
--- a/fs/befs/io.h
+++ b/fs/befs/io.h
@@ -4,4 +4,3 @@
 
 struct buffer_head *befs_bread_iaddr(struct super_block *sb,
 				     befs_inode_addr iaddr);
-
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 647a276..1940716 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -18,6 +18,7 @@
 #include <linux/parser.h>
 #include <linux/namei.h>
 #include <linux/sched.h>
+#include <linux/exportfs.h>
 
 #include "befs.h"
 #include "btree.h"
@@ -37,7 +38,8 @@ static int befs_readdir(struct file *, struct dir_context *);
 static int befs_get_block(struct inode *, sector_t, struct buffer_head *, int);
 static int befs_readpage(struct file *file, struct page *page);
 static sector_t befs_bmap(struct address_space *mapping, sector_t block);
-static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int);
+static struct dentry *befs_lookup(struct inode *, struct dentry *,
+				  unsigned int);
 static struct inode *befs_iget(struct super_block *, unsigned long);
 static struct inode *befs_alloc_inode(struct super_block *sb);
 static void befs_destroy_inode(struct inode *inode);
@@ -51,6 +53,10 @@ static void befs_put_super(struct super_block *);
 static int befs_remount(struct super_block *, int *, char *);
 static int befs_statfs(struct dentry *, struct kstatfs *);
 static int parse_options(char *, struct befs_mount_options *);
+static struct dentry *befs_fh_to_dentry(struct super_block *sb,
+				struct fid *fid, int fh_len, int fh_type);
+static struct dentry *befs_fh_to_parent(struct super_block *sb,
+				struct fid *fid, int fh_len, int fh_type);
 
 static const struct super_operations befs_sops = {
 	.alloc_inode	= befs_alloc_inode,	/* allocate a new inode */
@@ -83,9 +89,14 @@ static const struct address_space_operations befs_symlink_aops = {
 	.readpage	= befs_symlink_readpage,
 };
 
-/* 
+static const struct export_operations befs_export_operations = {
+	.fh_to_dentry	= befs_fh_to_dentry,
+	.fh_to_parent	= befs_fh_to_parent,
+};
+
+/*
  * Called by generic_file_read() to read a page of data
- * 
+ *
  * In turn, simply calls a generic block read function and
  * passes it the address of befs_get_block, for mapping file
  * positions to disk blocks.
@@ -102,15 +113,13 @@ befs_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping, block, befs_get_block);
 }
 
-/* 
- * Generic function to map a file position (block) to a 
+/*
+ * Generic function to map a file position (block) to a
  * disk offset (passed back in bh_result).
  *
  * Used by many higher level functions.
  *
  * Calls befs_fblock2brun() in datastream.c to do the real work.
- *
- * -WD 10-26-01
  */
 
 static int
@@ -269,15 +278,15 @@ befs_alloc_inode(struct super_block *sb)
 	struct befs_inode_info *bi;
 
 	bi = kmem_cache_alloc(befs_inode_cachep, GFP_KERNEL);
-        if (!bi)
-                return NULL;
-        return &bi->vfs_inode;
+	if (!bi)
+		return NULL;
+	return &bi->vfs_inode;
 }
 
 static void befs_i_callback(struct rcu_head *head)
 {
 	struct inode *inode = container_of(head, struct inode, i_rcu);
-        kmem_cache_free(befs_inode_cachep, BEFS_I(inode));
+	kmem_cache_free(befs_inode_cachep, BEFS_I(inode));
 }
 
 static void befs_destroy_inode(struct inode *inode)
@@ -287,7 +296,7 @@ static void befs_destroy_inode(struct inode *inode)
 
 static void init_once(void *foo)
 {
-        struct befs_inode_info *bi = (struct befs_inode_info *) foo;
+	struct befs_inode_info *bi = (struct befs_inode_info *) foo;
 
 	inode_init_once(&bi->vfs_inode);
 }
@@ -338,7 +347,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 	/*
 	 * set uid and gid.  But since current BeOS is single user OS, so
 	 * you can change by "uid" or "gid" options.
-	 */   
+	 */
 
 	inode->i_uid = befs_sb->mount_opts.use_uid ?
 		befs_sb->mount_opts.uid :
@@ -353,14 +362,14 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 	 * BEFS's time is 64 bits, but current VFS is 32 bits...
 	 * BEFS don't have access time. Nor inode change time. VFS
 	 * doesn't have creation time.
-	 * Also, the lower 16 bits of the last_modified_time and 
+	 * Also, the lower 16 bits of the last_modified_time and
 	 * create_time are just a counter to help ensure uniqueness
 	 * for indexing purposes. (PFD, page 54)
 	 */
 
 	inode->i_mtime.tv_sec =
 	    fs64_to_cpu(sb, raw_inode->last_modified_time) >> 16;
-	inode->i_mtime.tv_nsec = 0;   /* lower 16 bits are not a time */	
+	inode->i_mtime.tv_nsec = 0;   /* lower 16 bits are not a time */
 	inode->i_ctime = inode->i_mtime;
 	inode->i_atime = inode->i_mtime;
 
@@ -414,10 +423,10 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 	unlock_new_inode(inode);
 	return inode;
 
-      unacquire_bh:
+unacquire_bh:
 	brelse(bh);
 
-      unacquire_none:
+unacquire_none:
 	iget_failed(inode);
 	befs_debug(sb, "<--- %s - Bad inode", __func__);
 	return ERR_PTR(-EIO);
@@ -442,7 +451,7 @@ befs_init_inodecache(void)
 }
 
 /* Called at fs teardown.
- * 
+ *
  * Taken from NFS implementation by Al Viro.
  */
 static void
@@ -491,13 +500,10 @@ static int befs_symlink_readpage(struct file *unused, struct page *page)
 }
 
 /*
- * UTF-8 to NLS charset  convert routine
- * 
+ * UTF-8 to NLS charset convert routine
  *
- * Changed 8/10/01 by Will Dyson. Now use uni2char() / char2uni() rather than
- * the nls tables directly
+ * Uses uni2char() / char2uni() rather than the nls tables directly
  */
-
 static int
 befs_utf2nls(struct super_block *sb, const char *in,
 	     int in_len, char **out, int *out_len)
@@ -521,9 +527,8 @@ befs_utf2nls(struct super_block *sb, const char *in,
 	}
 
 	*out = result = kmalloc(maxlen, GFP_NOFS);
-	if (!*out) {
+	if (!*out)
 		return -ENOMEM;
-	}
 
 	for (i = o = 0; i < in_len; i += utflen, o += unilen) {
 
@@ -546,7 +551,7 @@ befs_utf2nls(struct super_block *sb, const char *in,
 
 	return o;
 
-      conv_err:
+conv_err:
 	befs_error(sb, "Name using character set %s contains a character that "
 		   "cannot be converted to unicode.", nls->charset);
 	befs_debug(sb, "<--- %s", __func__);
@@ -561,18 +566,18 @@ befs_utf2nls(struct super_block *sb, const char *in,
  * @in_len: Length of input string in bytes
  * @out: The output string in UTF-8 format
  * @out_len: Length of the output buffer
- * 
+ *
  * Converts input string @in, which is in the format of the loaded NLS map,
  * into a utf8 string.
- * 
+ *
  * The destination string @out is allocated by this function and the caller is
  * responsible for freeing it with kfree()
- * 
+ *
  * On return, *@out_len is the length of @out in bytes.
  *
  * On success, the return value is the number of utf8 characters written to
  * the output buffer @out.
- *  
+ *
  * On Failure, a negative number coresponding to the error code is returned.
  */
 
@@ -585,9 +590,11 @@ befs_nls2utf(struct super_block *sb, const char *in,
 	wchar_t uni;
 	int unilen, utflen;
 	char *result;
-	/* There're nls characters that will translate to 3-chars-wide UTF-8
-	 * characters, a additional byte is needed to save the final \0
-	 * in special cases */
+	/*
+	 * There are nls characters that will translate to 3-chars-wide UTF-8
+	 * characters, an additional byte is needed to save the final \0
+	 * in special cases
+	 */
 	int maxlen = (3 * in_len) + 1;
 
 	befs_debug(sb, "---> %s\n", __func__);
@@ -624,14 +631,41 @@ befs_nls2utf(struct super_block *sb, const char *in,
 
 	return i;
 
-      conv_err:
-	befs_error(sb, "Name using charecter set %s contains a charecter that "
+conv_err:
+	befs_error(sb, "Name using character set %s contains a character that "
 		   "cannot be converted to unicode.", nls->charset);
 	befs_debug(sb, "<--- %s", __func__);
 	kfree(result);
 	return -EILSEQ;
 }
 
+static struct inode *befs_nfs_get_inode(struct super_block *sb, uint64_t ino,
+					 uint32_t generation)
+{
+	/* No need to handle i_generation */
+	return befs_iget(sb, ino);
+}
+
+/*
+ * Map a NFS file handle to a corresponding dentry
+ */
+static struct dentry *befs_fh_to_dentry(struct super_block *sb,
+				struct fid *fid, int fh_len, int fh_type)
+{
+	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+				    befs_nfs_get_inode);
+}
+
+/*
+ * Find the parent for a file specified by NFS handle
+ */
+static struct dentry *befs_fh_to_parent(struct super_block *sb,
+				struct fid *fid, int fh_len, int fh_type)
+{
+	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+				    befs_nfs_get_inode);
+}
+
 enum {
 	Opt_uid, Opt_gid, Opt_charset, Opt_debug, Opt_err,
 };
@@ -666,6 +700,7 @@ parse_options(char *options, struct befs_mount_options *opts)
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
+
 		if (!*p)
 			continue;
 
@@ -721,7 +756,7 @@ parse_options(char *options, struct befs_mount_options *opts)
 }
 
 /* This function has the responsibiltiy of getting the
- * filesystem ready for unmounting. 
+ * filesystem ready for unmounting.
  * Basically, we free everything that we allocated in
  * befs_read_inode
  */
@@ -782,8 +817,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 	 * Linux 2.4.10 and later refuse to read blocks smaller than
 	 * the logical block size for the device. But we also need to read at
 	 * least 1k to get the second 512 bytes of the volume.
-	 * -WD 10-26-01
-	 */ 
+	 */
 	blocksize = sb_min_blocksize(sb, 1024);
 	if (!blocksize) {
 		if (!silent)
@@ -791,7 +825,8 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 		goto unacquire_priv_sbp;
 	}
 
-	if (!(bh = sb_bread(sb, sb_block))) {
+	bh = sb_bread(sb, sb_block);
+	if (!bh) {
 		if (!silent)
 			befs_error(sb, "unable to read superblock");
 		goto unacquire_priv_sbp;
@@ -816,7 +851,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 
 	brelse(bh);
 
-	if( befs_sb->num_blocks > ~((sector_t)0) ) {
+	if (befs_sb->num_blocks > ~((sector_t)0)) {
 		if (!silent)
 			befs_error(sb, "blocks count: %llu is larger than the host can use",
 					befs_sb->num_blocks);
@@ -831,6 +866,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 	/* Set real blocksize of fs */
 	sb_set_blocksize(sb, (ulong) befs_sb->block_size);
 	sb->s_op = &befs_sops;
+	sb->s_export_op = &befs_export_operations;
 	root = befs_iget(sb, iaddr2blockno(sb, &(befs_sb->root_dir)));
 	if (IS_ERR(root)) {
 		ret = PTR_ERR(root);
@@ -861,16 +897,16 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	return 0;
-/*****************/
-      unacquire_bh:
+
+unacquire_bh:
 	brelse(bh);
 
-      unacquire_priv_sbp:
+unacquire_priv_sbp:
 	kfree(befs_sb->mount_opts.iocharset);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
 
-      unacquire_none:
+unacquire_none:
 	return ret;
 }
 
@@ -919,7 +955,7 @@ static struct file_system_type befs_fs_type = {
 	.name		= "befs",
 	.mount		= befs_mount,
 	.kill_sb	= kill_block_super,
-	.fs_flags	= FS_REQUIRES_DEV,	
+	.fs_flags	= FS_REQUIRES_DEV,
 };
 MODULE_ALIAS_FS("befs");
 
@@ -956,9 +992,9 @@ exit_befs_fs(void)
 }
 
 /*
-Macros that typecheck the init and exit functions,
-ensures that they are called at init and cleanup,
-and eliminates warnings about unused functions.
-*/
+ * Macros that typecheck the init and exit functions,
+ * ensures that they are called at init and cleanup,
+ * and eliminates warnings about unused functions.
+ */
 module_init(init_befs_fs)
 module_exit(exit_befs_fs)
diff --git a/fs/befs/super.h b/fs/befs/super.h
index dc45563..ec1df30 100644
--- a/fs/befs/super.h
+++ b/fs/befs/super.h
@@ -2,7 +2,5 @@
  * super.h
  */
 
-int befs_load_sb(struct super_block *sb, befs_super_block * disk_sb);
-
+int befs_load_sb(struct super_block *sb, befs_super_block *disk_sb);
 int befs_check_sb(struct super_block *sb);
-
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 1e5c896..f2deec0 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -16,7 +16,7 @@
 #include <linux/vfs.h>
 #include <linux/writeback.h>
 #include <linux/uio.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "bfs.h"
 
 MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index ae1b540..2a59139 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -26,7 +26,7 @@
 #include <linux/coredump.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/a.out-core.h>
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index e6c1bd4..29a02da 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -36,7 +36,7 @@
 #include <linux/coredump.h>
 #include <linux/sched.h>
 #include <linux/dax.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/param.h>
 #include <asm/page.h>
 
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 464a972..d2e36f8 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -37,7 +37,7 @@
 #include <linux/coredump.h>
 #include <linux/dax.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/param.h>
 #include <asm/pgalloc.h>
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7c45072..6254cee 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -32,7 +32,7 @@
 #include <linux/badblocks.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/falloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 
 struct bdev_inode {
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 3d03e48..9727e1d 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -24,7 +24,7 @@
 #include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifsproto.h"
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 5eb0412..66bd7fa 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -699,11 +699,15 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 
 	if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) {
 		if (!ses->domainName) {
-			rc = find_domain_name(ses, nls_cp);
-			if (rc) {
-				cifs_dbg(VFS, "error %d finding domain name\n",
-					 rc);
-				goto setup_ntlmv2_rsp_ret;
+			if (ses->domainAuto) {
+				rc = find_domain_name(ses, nls_cp);
+				if (rc) {
+					cifs_dbg(VFS, "error %d finding domain name\n",
+						 rc);
+					goto setup_ntlmv2_rsp_ret;
+				}
+			} else {
+				ses->domainName = kstrdup("", GFP_KERNEL);
 			}
 		}
 	} else {
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index e6efb9a..70f4e65 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -615,7 +615,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 		return dget(sb->s_root);
 
 	full_path = cifs_build_path_to_root(vol, cifs_sb,
-					    cifs_sb_master_tcon(cifs_sb));
+				cifs_sb_master_tcon(cifs_sb), 0);
 	if (full_path == NULL)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 1f17f6b..7ea8a33 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -514,6 +514,7 @@ struct smb_vol {
 	bool persistent:1;
 	bool nopersistent:1;
 	bool resilient:1; /* noresilient not required since not fored for CA */
+	bool domainauto:1;
 	unsigned int rsize;
 	unsigned int wsize;
 	bool sockopt_tcp_nodelay:1;
@@ -525,6 +526,7 @@ struct smb_vol {
 	struct sockaddr_storage srcaddr; /* allow binding to a local IP */
 	struct nls_table *local_nls;
 	unsigned int echo_interval; /* echo interval in secs */
+	__u64 snapshot_time; /* needed for timewarp tokens */
 	unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */
 };
 
@@ -646,6 +648,8 @@ struct TCP_Server_Info {
 	unsigned int	max_read;
 	unsigned int	max_write;
 	__u8		preauth_hash[512];
+	struct delayed_work reconnect; /* reconnect workqueue job */
+	struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
 #endif /* CONFIG_CIFS_SMB2 */
 	unsigned long echo_interval;
 };
@@ -827,6 +831,7 @@ struct cifs_ses {
 	enum securityEnum sectype; /* what security flavor was specified? */
 	bool sign;		/* is signing required? */
 	bool need_reconnect:1; /* connection reset, uid now invalid */
+	bool domainAuto:1;
 #ifdef CONFIG_CIFS_SMB2
 	__u16 session_flags;
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
@@ -849,6 +854,7 @@ cap_unix(struct cifs_ses *ses)
 struct cifs_tcon {
 	struct list_head tcon_list;
 	int tc_count;
+	struct list_head rlist; /* reconnect list */
 	struct list_head openFileList;
 	spinlock_t open_file_lock; /* protects list above */
 	struct cifs_ses *ses;	/* pointer to session associated with */
@@ -922,6 +928,7 @@ struct cifs_tcon {
 	bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */
 	bool broken_sparse_sup; /* if server or share does not support sparse */
 	bool need_reconnect:1; /* connection reset, tid now invalid */
+	bool need_reopen_files:1; /* need to reopen tcon file handles */
 	bool use_resilient:1; /* use resilient instead of durable handles */
 	bool use_persistent:1; /* use persistent instead of durable handles */
 #ifdef CONFIG_CIFS_SMB2
@@ -932,6 +939,7 @@ struct cifs_tcon {
 	__u32 maximal_access;
 	__u32 vol_serial_number;
 	__le64 vol_create_time;
+	__u64 snapshot_time; /* for timewarp tokens - timestamp of snapshot */
 	__u32 ss_flags;		/* sector size flags */
 	__u32 perf_sector_size; /* best sector size for perf */
 	__u32 max_chunks;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index ced0e42..c7b3c84 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -63,7 +63,8 @@ extern void exit_cifs_spnego(void);
 extern char *build_path_from_dentry(struct dentry *);
 extern char *cifs_build_path_to_root(struct smb_vol *vol,
 				     struct cifs_sb_info *cifs_sb,
-				     struct cifs_tcon *tcon);
+				     struct cifs_tcon *tcon,
+				     int add_treename);
 extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
 extern char *cifs_compose_mount_options(const char *sb_mountdata,
 		const char *fullpath, const struct dfs_info3_param *ref,
@@ -206,6 +207,9 @@ extern void cifs_add_pending_open_locked(struct cifs_fid *fid,
 					 struct tcon_link *tlink,
 					 struct cifs_pending_open *open);
 extern void cifs_del_pending_open(struct cifs_pending_open *open);
+extern void cifs_put_tcp_session(struct TCP_Server_Info *server,
+				 int from_reconnect);
+extern void cifs_put_tcon(struct cifs_tcon *tcon);
 
 #if IS_ENABLED(CONFIG_CIFS_DFS_UPCALL)
 extern void cifs_dfs_release_automount_timer(void);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index e3fed92..b472618 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -35,7 +35,7 @@
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 #include <linux/task_io_accounting_ops.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifsacl.h"
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index f7563c8..35ae49e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -34,7 +34,7 @@
 #include <linux/pagevec.h>
 #include <linux/freezer.h>
 #include <linux/namei.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <linux/inet.h>
 #include <linux/module.h>
@@ -53,6 +53,9 @@
 #include "nterr.h"
 #include "rfc1002pdu.h"
 #include "fscache.h"
+#ifdef CONFIG_CIFS_SMB2
+#include "smb2proto.h"
+#endif
 
 #define CIFS_PORT 445
 #define RFC1001_PORT 139
@@ -89,6 +92,7 @@ enum {
 	Opt_multiuser, Opt_sloppy, Opt_nosharesock,
 	Opt_persistent, Opt_nopersistent,
 	Opt_resilient, Opt_noresilient,
+	Opt_domainauto,
 
 	/* Mount options which take numeric value */
 	Opt_backupuid, Opt_backupgid, Opt_uid,
@@ -96,6 +100,7 @@ enum {
 	Opt_dirmode, Opt_port,
 	Opt_rsize, Opt_wsize, Opt_actimeo,
 	Opt_echo_interval, Opt_max_credits,
+	Opt_snapshot,
 
 	/* Mount options which take string value */
 	Opt_user, Opt_pass, Opt_ip,
@@ -177,6 +182,7 @@ static const match_table_t cifs_mount_option_tokens = {
 	{ Opt_nopersistent, "nopersistenthandles"},
 	{ Opt_resilient, "resilienthandles"},
 	{ Opt_noresilient, "noresilienthandles"},
+	{ Opt_domainauto, "domainauto"},
 
 	{ Opt_backupuid, "backupuid=%s" },
 	{ Opt_backupgid, "backupgid=%s" },
@@ -192,6 +198,7 @@ static const match_table_t cifs_mount_option_tokens = {
 	{ Opt_actimeo, "actimeo=%s" },
 	{ Opt_echo_interval, "echo_interval=%s" },
 	{ Opt_max_credits, "max_credits=%s" },
+	{ Opt_snapshot, "snapshot=%s" },
 
 	{ Opt_blank_user, "user=" },
 	{ Opt_blank_user, "username=" },
@@ -1500,6 +1507,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 		case Opt_noresilient:
 			vol->resilient = false; /* already the default */
 			break;
+		case Opt_domainauto:
+			vol->domainauto = true;
+			break;
 
 		/* Numeric Values */
 		case Opt_backupuid:
@@ -1602,6 +1612,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			}
 			vol->echo_interval = option;
 			break;
+		case Opt_snapshot:
+			if (get_option_ul(args, &option)) {
+				cifs_dbg(VFS, "%s: Invalid snapshot time\n",
+					 __func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->snapshot_time = option;
+			break;
 		case Opt_max_credits:
 			if (get_option_ul(args, &option) || (option < 20) ||
 			    (option > 60000)) {
@@ -2101,8 +2119,8 @@ cifs_find_tcp_session(struct smb_vol *vol)
 	return NULL;
 }
 
-static void
-cifs_put_tcp_session(struct TCP_Server_Info *server)
+void
+cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 {
 	struct task_struct *task;
 
@@ -2119,6 +2137,19 @@ cifs_put_tcp_session(struct TCP_Server_Info *server)
 
 	cancel_delayed_work_sync(&server->echo);
 
+#ifdef CONFIG_CIFS_SMB2
+	if (from_reconnect)
+		/*
+		 * Avoid deadlock here: reconnect work calls
+		 * cifs_put_tcp_session() at its end. Need to be sure
+		 * that reconnect work does nothing with server pointer after
+		 * that step.
+		 */
+		cancel_delayed_work(&server->reconnect);
+	else
+		cancel_delayed_work_sync(&server->reconnect);
+#endif
+
 	spin_lock(&GlobalMid_Lock);
 	server->tcpStatus = CifsExiting;
 	spin_unlock(&GlobalMid_Lock);
@@ -2183,6 +2214,10 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	INIT_LIST_HEAD(&tcp_ses->tcp_ses_list);
 	INIT_LIST_HEAD(&tcp_ses->smb_ses_list);
 	INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request);
+#ifdef CONFIG_CIFS_SMB2
+	INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server);
+	mutex_init(&tcp_ses->reconnect_mutex);
+#endif
 	memcpy(&tcp_ses->srcaddr, &volume_info->srcaddr,
 	       sizeof(tcp_ses->srcaddr));
 	memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr,
@@ -2341,7 +2376,7 @@ cifs_put_smb_ses(struct cifs_ses *ses)
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	sesInfoFree(ses);
-	cifs_put_tcp_session(server);
+	cifs_put_tcp_session(server, 0);
 }
 
 #ifdef CONFIG_KEYS
@@ -2515,7 +2550,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 		mutex_unlock(&ses->session_mutex);
 
 		/* existing SMB ses has a server reference already */
-		cifs_put_tcp_session(server);
+		cifs_put_tcp_session(server, 0);
 		free_xid(xid);
 		return ses;
 	}
@@ -2549,6 +2584,8 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 		if (!ses->domainName)
 			goto get_ses_fail;
 	}
+	if (volume_info->domainauto)
+		ses->domainAuto = volume_info->domainauto;
 	ses->cred_uid = volume_info->cred_uid;
 	ses->linux_uid = volume_info->linux_uid;
 
@@ -2587,7 +2624,7 @@ static int match_tcon(struct cifs_tcon *tcon, const char *unc)
 }
 
 static struct cifs_tcon *
-cifs_find_tcon(struct cifs_ses *ses, const char *unc)
+cifs_find_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 {
 	struct list_head *tmp;
 	struct cifs_tcon *tcon;
@@ -2595,8 +2632,14 @@ cifs_find_tcon(struct cifs_ses *ses, const char *unc)
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &ses->tcon_list) {
 		tcon = list_entry(tmp, struct cifs_tcon, tcon_list);
-		if (!match_tcon(tcon, unc))
+		if (!match_tcon(tcon, volume_info->UNC))
 			continue;
+
+#ifdef CONFIG_CIFS_SMB2
+		if (tcon->snapshot_time != volume_info->snapshot_time)
+			continue;
+#endif /* CONFIG_CIFS_SMB2 */
+
 		++tcon->tc_count;
 		spin_unlock(&cifs_tcp_ses_lock);
 		return tcon;
@@ -2605,7 +2648,7 @@ cifs_find_tcon(struct cifs_ses *ses, const char *unc)
 	return NULL;
 }
 
-static void
+void
 cifs_put_tcon(struct cifs_tcon *tcon)
 {
 	unsigned int xid;
@@ -2637,7 +2680,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	int rc, xid;
 	struct cifs_tcon *tcon;
 
-	tcon = cifs_find_tcon(ses, volume_info->UNC);
+	tcon = cifs_find_tcon(ses, volume_info);
 	if (tcon) {
 		cifs_dbg(FYI, "Found match on UNC path\n");
 		/* existing tcon already has a reference */
@@ -2658,6 +2701,22 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		goto out_fail;
 	}
 
+	if (volume_info->snapshot_time) {
+#ifdef CONFIG_CIFS_SMB2
+		if (ses->server->vals->protocol_id == 0) {
+			cifs_dbg(VFS,
+			     "Use SMB2 or later for snapshot mount option\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+		} else
+			tcon->snapshot_time = volume_info->snapshot_time;
+#else
+		cifs_dbg(VFS, "Snapshot mount option requires SMB2 support\n");
+		rc = -EOPNOTSUPP;
+		goto out_fail;
+#endif /* CONFIG_CIFS_SMB2 */
+	}
+
 	tcon->ses = ses;
 	if (volume_info->password) {
 		tcon->password = kstrdup(volume_info->password, GFP_KERNEL);
@@ -3707,7 +3766,8 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 		/*
 		 * cifs_build_path_to_root works only when we have a valid tcon
 		 */
-		full_path = cifs_build_path_to_root(volume_info, cifs_sb, tcon);
+		full_path = cifs_build_path_to_root(volume_info, cifs_sb, tcon,
+					tcon->Flags & SMB_SHARE_IS_IN_DFS);
 		if (full_path == NULL) {
 			rc = -ENOMEM;
 			goto mount_fail_check;
@@ -3793,7 +3853,7 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 		else if (ses)
 			cifs_put_smb_ses(ses);
 		else
-			cifs_put_tcp_session(server);
+			cifs_put_tcp_session(server, 0);
 		bdi_destroy(&cifs_sb->bdi);
 	}
 
@@ -4104,7 +4164,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 	ses = cifs_get_smb_ses(master_tcon->ses->server, vol_info);
 	if (IS_ERR(ses)) {
 		tcon = (struct cifs_tcon *)ses;
-		cifs_put_tcp_session(master_tcon->ses->server);
+		cifs_put_tcp_session(master_tcon->ses->server, 0);
 		goto out;
 	}
 
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 789ff1d..2c227a9 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -47,7 +47,7 @@ renew_parental_timestamps(struct dentry *direntry)
 
 char *
 cifs_build_path_to_root(struct smb_vol *vol, struct cifs_sb_info *cifs_sb,
-			struct cifs_tcon *tcon)
+			struct cifs_tcon *tcon, int add_treename)
 {
 	int pplen = vol->prepath ? strlen(vol->prepath) + 1 : 0;
 	int dfsplen;
@@ -59,7 +59,7 @@ cifs_build_path_to_root(struct smb_vol *vol, struct cifs_sb_info *cifs_sb,
 		return full_path;
 	}
 
-	if (tcon->Flags & SMB_SHARE_IS_IN_DFS)
+	if (add_treename)
 		dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1);
 	else
 		dfsplen = 0;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 7f5f617..18a1e1d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -777,6 +777,11 @@ cifs_reopen_persistent_handles(struct cifs_tcon *tcon)
 	struct list_head *tmp1;
 	struct list_head tmp_list;
 
+	if (!tcon->use_persistent || !tcon->need_reopen_files)
+		return;
+
+	tcon->need_reopen_files = false;
+
 	cifs_dbg(FYI, "Reopen persistent handles");
 	INIT_LIST_HEAD(&tmp_list);
 
@@ -793,7 +798,8 @@ cifs_reopen_persistent_handles(struct cifs_tcon *tcon)
 
 	list_for_each_safe(tmp, tmp1, &tmp_list) {
 		open_file = list_entry(tmp, struct cifsFileInfo, rlist);
-		cifs_reopen_file(open_file, false /* do not flush */);
+		if (cifs_reopen_file(open_file, false /* do not flush */))
+			tcon->need_reopen_files = true;
 		list_del_init(&open_file->rlist);
 		cifsFileInfo_put(open_file);
 	}
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 9f51b81..0015287 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -189,7 +189,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 	xid = get_xid();
 
 	cifs_sb = CIFS_SB(inode->i_sb);
-	cifs_dbg(VFS, "cifs ioctl 0x%x\n", command);
+	cifs_dbg(FYI, "cifs ioctl 0x%x\n", command);
 	switch (command) {
 		case FS_IOC_GETFLAGS:
 			if (pSMBFile == NULL)
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index d031af8..c4d996f 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -45,13 +45,8 @@
 	(CIFS_MF_SYMLINK_LINK_OFFSET + CIFS_MF_SYMLINK_LINK_MAXLEN)
 
 #define CIFS_MF_SYMLINK_LEN_FORMAT "XSym\n%04u\n"
-#define CIFS_MF_SYMLINK_MD5_FORMAT \
-	"%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n"
-#define CIFS_MF_SYMLINK_MD5_ARGS(md5_hash) \
-	md5_hash[0],  md5_hash[1],  md5_hash[2],  md5_hash[3], \
-	md5_hash[4],  md5_hash[5],  md5_hash[6],  md5_hash[7], \
-	md5_hash[8],  md5_hash[9],  md5_hash[10], md5_hash[11],\
-	md5_hash[12], md5_hash[13], md5_hash[14], md5_hash[15]
+#define CIFS_MF_SYMLINK_MD5_FORMAT "%16phN\n"
+#define CIFS_MF_SYMLINK_MD5_ARGS(md5_hash) md5_hash
 
 static int
 symlink_hash(unsigned int link_len, const char *link_str, u8 *md5_hash)
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index f9e766f..b2aff0c 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -260,7 +260,7 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
 	 * and check it for zero before using.
 	 */
 	max_buf = tlink_tcon(cfile->tlink)->ses->server->maxBuf;
-	if (!max_buf) {
+	if (max_buf < sizeof(struct smb2_lock_element)) {
 		free_xid(xid);
 		return -EINVAL;
 	}
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 5ca5ea46..8745722 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -250,16 +250,19 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	}
 
 	cifs_mark_open_files_invalid(tcon);
+	if (tcon->use_persistent)
+		tcon->need_reopen_files = true;
 
 	rc = SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nls_codepage);
 	mutex_unlock(&tcon->ses->session_mutex);
 
-	if (tcon->use_persistent)
-		cifs_reopen_persistent_handles(tcon);
-
 	cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc);
 	if (rc)
 		goto out;
+
+	if (smb2_command != SMB2_INTERNAL_CMD)
+		queue_delayed_work(cifsiod_wq, &server->reconnect, 0);
+
 	atomic_inc(&tconInfoReconnectCount);
 out:
 	/*
@@ -280,7 +283,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	case SMB2_CHANGE_NOTIFY:
 	case SMB2_QUERY_INFO:
 	case SMB2_SET_INFO:
-		return -EAGAIN;
+		rc = -EAGAIN;
 	}
 	unload_nls(nls_codepage);
 	return rc;
@@ -1972,6 +1975,55 @@ smb2_echo_callback(struct mid_q_entry *mid)
 	add_credits(server, credits_received, CIFS_ECHO_OP);
 }
 
+void smb2_reconnect_server(struct work_struct *work)
+{
+	struct TCP_Server_Info *server = container_of(work,
+					struct TCP_Server_Info, reconnect.work);
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon, *tcon2;
+	struct list_head tmp_list;
+	int tcon_exist = false;
+
+	/* Prevent simultaneous reconnects that can corrupt tcon->rlist list */
+	mutex_lock(&server->reconnect_mutex);
+
+	INIT_LIST_HEAD(&tmp_list);
+	cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n");
+
+	spin_lock(&cifs_tcp_ses_lock);
+	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+		list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+			if (tcon->need_reconnect || tcon->need_reopen_files) {
+				tcon->tc_count++;
+				list_add_tail(&tcon->rlist, &tmp_list);
+				tcon_exist = true;
+			}
+		}
+	}
+	/*
+	 * Get the reference to server struct to be sure that the last call of
+	 * cifs_put_tcon() in the loop below won't release the server pointer.
+	 */
+	if (tcon_exist)
+		server->srv_count++;
+
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
+		if (!smb2_reconnect(SMB2_INTERNAL_CMD, tcon))
+			cifs_reopen_persistent_handles(tcon);
+		list_del_init(&tcon->rlist);
+		cifs_put_tcon(tcon);
+	}
+
+	cifs_dbg(FYI, "Reconnecting tcons finished\n");
+	mutex_unlock(&server->reconnect_mutex);
+
+	/* now we can safely release srv struct */
+	if (tcon_exist)
+		cifs_put_tcp_session(server, 1);
+}
+
 int
 SMB2_echo(struct TCP_Server_Info *server)
 {
@@ -1984,32 +2036,11 @@ SMB2_echo(struct TCP_Server_Info *server)
 	cifs_dbg(FYI, "In echo request\n");
 
 	if (server->tcpStatus == CifsNeedNegotiate) {
-		struct list_head *tmp, *tmp2;
-		struct cifs_ses *ses;
-		struct cifs_tcon *tcon;
-
-		cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n");
-		spin_lock(&cifs_tcp_ses_lock);
-		list_for_each(tmp, &server->smb_ses_list) {
-			ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
-			list_for_each(tmp2, &ses->tcon_list) {
-				tcon = list_entry(tmp2, struct cifs_tcon,
-						  tcon_list);
-				/* add check for persistent handle reconnect */
-				if (tcon && tcon->need_reconnect) {
-					spin_unlock(&cifs_tcp_ses_lock);
-					rc = smb2_reconnect(SMB2_ECHO, tcon);
-					spin_lock(&cifs_tcp_ses_lock);
-				}
-			}
-		}
-		spin_unlock(&cifs_tcp_ses_lock);
+		/* No need to send echo on newly established connections */
+		queue_delayed_work(cifsiod_wq, &server->reconnect, 0);
+		return rc;
 	}
 
-	/* if no session, renegotiate failed above */
-	if (server->tcpStatus == CifsNeedNegotiate)
-		return -EIO;
-
 	rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req);
 	if (rc)
 		return rc;
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index fd3709e..dc0d141 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -80,6 +80,8 @@
 #define SMB2_SET_INFO		cpu_to_le16(SMB2_SET_INFO_HE)
 #define SMB2_OPLOCK_BREAK	cpu_to_le16(SMB2_OPLOCK_BREAK_HE)
 
+#define SMB2_INTERNAL_CMD	cpu_to_le16(0xFFFF)
+
 #define NUMBER_OF_SMB2_COMMANDS	0x0013
 
 /* BB FIXME - analyze following length BB */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index eb2cde2..f2d511a 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -96,6 +96,7 @@ extern int smb2_open_file(const unsigned int xid,
 extern int smb2_unlock_range(struct cifsFileInfo *cfile,
 			     struct file_lock *flock, const unsigned int xid);
 extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
+extern void smb2_reconnect_server(struct work_struct *work);
 
 /*
  * SMB2 Worker functions - most of protocol specific implementation details
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 699b786..c12bffe 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -23,7 +23,7 @@
    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
-#include <crypto/skcipher.h>
+#include <linux/crypto.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
@@ -69,46 +69,22 @@ str_to_key(unsigned char *str, unsigned char *key)
 static int
 smbhash(unsigned char *out, const unsigned char *in, unsigned char *key)
 {
-	int rc;
 	unsigned char key2[8];
-	struct crypto_skcipher *tfm_des;
-	struct scatterlist sgin, sgout;
-	struct skcipher_request *req;
+	struct crypto_cipher *tfm_des;
 
 	str_to_key(key, key2);
 
-	tfm_des = crypto_alloc_skcipher("ecb(des)", 0, CRYPTO_ALG_ASYNC);
+	tfm_des = crypto_alloc_cipher("des", 0, 0);
 	if (IS_ERR(tfm_des)) {
-		rc = PTR_ERR(tfm_des);
 		cifs_dbg(VFS, "could not allocate des crypto API\n");
-		goto smbhash_err;
+		return PTR_ERR(tfm_des);
 	}
 
-	req = skcipher_request_alloc(tfm_des, GFP_KERNEL);
-	if (!req) {
-		rc = -ENOMEM;
-		cifs_dbg(VFS, "could not allocate des crypto API\n");
-		goto smbhash_free_skcipher;
-	}
+	crypto_cipher_setkey(tfm_des, key2, 8);
+	crypto_cipher_encrypt_one(tfm_des, out, in);
+	crypto_free_cipher(tfm_des);
 
-	crypto_skcipher_setkey(tfm_des, key2, 8);
-
-	sg_init_one(&sgin, in, 8);
-	sg_init_one(&sgout, out, 8);
-
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, &sgin, &sgout, 8, NULL);
-
-	rc = crypto_skcipher_encrypt(req);
-	if (rc)
-		cifs_dbg(VFS, "could not encrypt crypt key rc: %d\n", rc);
-
-	skcipher_request_free(req);
-
-smbhash_free_skcipher:
-	crypto_free_skcipher(tfm_des);
-smbhash_err:
-	return rc;
+	return 0;
 }
 
 static int
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 5f02edc..fbb84c0 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -30,7 +30,7 @@
 #include <linux/tcp.h>
 #include <linux/bvec.h>
 #include <linux/highmem.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <linux/mempool.h>
 #include "cifspdu.h"
diff --git a/fs/compat.c b/fs/compat.c
index 543b48c..e50a211 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -49,7 +49,7 @@
 #include <linux/pagemap.h>
 #include <linux/aio.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/ioctls.h>
 #include "internal.h"
@@ -487,45 +487,6 @@ COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
 	return compat_sys_fcntl64(fd, cmd, arg);
 }
 
-COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_reqs, u32 __user *, ctx32p)
-{
-	long ret;
-	aio_context_t ctx64;
-
-	mm_segment_t oldfs = get_fs();
-	if (unlikely(get_user(ctx64, ctx32p)))
-		return -EFAULT;
-
-	set_fs(KERNEL_DS);
-	/* The __user pointer cast is valid because of the set_fs() */
-	ret = sys_io_setup(nr_reqs, (aio_context_t __user *) &ctx64);
-	set_fs(oldfs);
-	/* truncating is ok because it's a user address */
-	if (!ret)
-		ret = put_user((u32) ctx64, ctx32p);
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
-		       compat_long_t, min_nr,
-		       compat_long_t, nr,
-		       struct io_event __user *, events,
-		       struct compat_timespec __user *, timeout)
-{
-	struct timespec t;
-	struct timespec __user *ut = NULL;
-
-	if (timeout) {
-		if (compat_get_timespec(&t, timeout))
-			return -EFAULT;
-
-		ut = compat_alloc_user_space(sizeof(*ut));
-		if (copy_to_user(ut, &t, sizeof(t)) )
-			return -EFAULT;
-	} 
-	return sys_io_getevents(ctx_id, min_nr, nr, events, ut);
-}
-
 /* A write operation does a read from user space and vice versa */
 #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
 
@@ -602,42 +563,6 @@ ssize_t compat_rw_copy_check_uvector(int type,
 	return ret;
 }
 
-static inline long
-copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
-{
-	compat_uptr_t uptr;
-	int i;
-
-	for (i = 0; i < nr; ++i) {
-		if (get_user(uptr, ptr32 + i))
-			return -EFAULT;
-		if (put_user(compat_ptr(uptr), ptr64 + i))
-			return -EFAULT;
-	}
-	return 0;
-}
-
-#define MAX_AIO_SUBMITS 	(PAGE_SIZE/sizeof(struct iocb *))
-
-COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
-		       int, nr, u32 __user *, iocb)
-{
-	struct iocb __user * __user *iocb64; 
-	long ret;
-
-	if (unlikely(nr < 0))
-		return -EINVAL;
-
-	if (nr > MAX_AIO_SUBMITS)
-		nr = MAX_AIO_SUBMITS;
-	
-	iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64));
-	ret = copy_iocb(nr, iocb, iocb64);
-	if (!ret)
-		ret = do_io_submit(ctx_id, nr, iocb64, 1);
-	return ret;
-}
-
 struct compat_ncp_mount_data {
 	compat_int_t version;
 	compat_uint_t ncp_fd;
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index f2d7402..11d087b 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -76,7 +76,7 @@
 #include <scsi/sg.h>
 #endif
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/ethtool.h>
 #include <linux/mii.h>
 #include <linux/if_bonding.h>
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index 2c6312d..39da110 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -29,7 +29,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/vmalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/configfs.h>
 #include "configfs_internal.h"
diff --git a/fs/coredump.c b/fs/coredump.c
index eb9c92c..e525b60 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -38,7 +38,7 @@
 #include <linux/path.h>
 #include <linux/timekeeping.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
 #include <asm/exec.h>
diff --git a/fs/dax.c b/fs/dax.c
index a8732fb..5c74f60 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -451,16 +451,37 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
 }
 
+static int __dax_invalidate_mapping_entry(struct address_space *mapping,
+					  pgoff_t index, bool trunc)
+{
+	int ret = 0;
+	void *entry;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = get_unlocked_mapping_entry(mapping, index, NULL);
+	if (!entry || !radix_tree_exceptional_entry(entry))
+		goto out;
+	if (!trunc &&
+	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	     radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
+		goto out;
+	radix_tree_delete(page_tree, index);
+	mapping->nrexceptional--;
+	ret = 1;
+out:
+	put_unlocked_mapping_entry(mapping, index, entry);
+	spin_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
 /*
  * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
  * entry to get unlocked before deleting it.
  */
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
-	void *entry;
+	int ret = __dax_invalidate_mapping_entry(mapping, index, true);
 
-	spin_lock_irq(&mapping->tree_lock);
-	entry = get_unlocked_mapping_entry(mapping, index, NULL);
 	/*
 	 * This gets called from truncate / punch_hole path. As such, the caller
 	 * must hold locks protecting against concurrent modifications of the
@@ -468,16 +489,46 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	 * caller has seen exceptional entry for this index, we better find it
 	 * at that index as well...
 	 */
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
-		spin_unlock_irq(&mapping->tree_lock);
-		return 0;
-	}
-	radix_tree_delete(&mapping->page_tree, index);
-	mapping->nrexceptional--;
-	spin_unlock_irq(&mapping->tree_lock);
-	dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	WARN_ON_ONCE(!ret);
+	return ret;
+}
 
-	return 1;
+/*
+ * Invalidate exceptional DAX entry if easily possible. This handles DAX
+ * entries for invalidate_inode_pages() so we evict the entry only if we can
+ * do so without blocking.
+ */
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+	int ret = 0;
+	void *entry, **slot;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
+	if (!entry || !radix_tree_exceptional_entry(entry) ||
+	    slot_locked(mapping, slot))
+		goto out;
+	if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	    radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+		goto out;
+	radix_tree_delete(page_tree, index);
+	mapping->nrexceptional--;
+	ret = 1;
+out:
+	spin_unlock_irq(&mapping->tree_lock);
+	if (ret)
+		dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	return ret;
+}
+
+/*
+ * Invalidate exceptional DAX entry if it is clean.
+ */
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index)
+{
+	return __dax_invalidate_mapping_entry(mapping, index, false);
 }
 
 /*
@@ -488,15 +539,16 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
  * otherwise it will simply fall out of the page cache under memory
  * pressure without ever having been dirtied.
  */
-static int dax_load_hole(struct address_space *mapping, void *entry,
+static int dax_load_hole(struct address_space *mapping, void **entry,
 			 struct vm_fault *vmf)
 {
 	struct page *page;
+	int ret;
 
 	/* Hole page already exists? Return it...  */
-	if (!radix_tree_exceptional_entry(entry)) {
-		vmf->page = entry;
-		return VM_FAULT_LOCKED;
+	if (!radix_tree_exceptional_entry(*entry)) {
+		page = *entry;
+		goto out;
 	}
 
 	/* This will replace locked radix tree entry with a hole page */
@@ -504,8 +556,17 @@ static int dax_load_hole(struct address_space *mapping, void *entry,
 				   vmf->gfp_mask | __GFP_ZERO);
 	if (!page)
 		return VM_FAULT_OOM;
+ out:
 	vmf->page = page;
-	return VM_FAULT_LOCKED;
+	ret = finish_fault(vmf);
+	vmf->page = NULL;
+	*entry = page;
+	if (!ret) {
+		/* Grab reference for PTE that is now referencing the page */
+		get_page(page);
+		return VM_FAULT_NOPAGE;
+	}
+	return ret;
 }
 
 static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size,
@@ -934,6 +995,17 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED))
 		return -EIO;
 
+	/*
+	 * Write can allocate block for an area which has a hole page mapped
+	 * into page tables. We have to tear down these mappings so that data
+	 * written by write(2) is visible in mmap.
+	 */
+	if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+		invalidate_inode_pages2_range(inode->i_mapping,
+					      pos >> PAGE_SHIFT,
+					      (end - 1) >> PAGE_SHIFT);
+	}
+
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
 		struct blk_dax_ctl dax = { 0 };
@@ -992,23 +1064,6 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == WRITE)
 		flags |= IOMAP_WRITE;
 
-	/*
-	 * Yes, even DAX files can have page cache attached to them:  A zeroed
-	 * page is inserted into the pagecache when we have to serve a write
-	 * fault on a hole.  It should never be dirtied and can simply be
-	 * dropped from the pagecache once we get real data for the page.
-	 *
-	 * XXX: This is racy against mmap, and there's nothing we can do about
-	 * it. We'll eventually need to shift this down even further so that
-	 * we can check if we allocated blocks over a hole first.
-	 */
-	if (mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
-				pos >> PAGE_SHIFT,
-				(pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
-	}
-
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
 				iter, dax_iomap_actor);
@@ -1023,6 +1078,15 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(dax_iomap_rw);
 
+static int dax_fault_return(int error)
+{
+	if (error == 0)
+		return VM_FAULT_NOPAGE;
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
+}
+
 /**
  * dax_iomap_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
@@ -1055,12 +1119,6 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (pos >= i_size_read(inode))
 		return VM_FAULT_SIGBUS;
 
-	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
-	if (IS_ERR(entry)) {
-		error = PTR_ERR(entry);
-		goto out;
-	}
-
 	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
 		flags |= IOMAP_WRITE;
 
@@ -1071,9 +1129,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	 */
 	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		return dax_fault_return(error);
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		error = -EIO;		/* fs corruption? */
+		vmf_ret = dax_fault_return(-EIO);	/* fs corruption? */
+		goto finish_iomap;
+	}
+
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+	if (IS_ERR(entry)) {
+		vmf_ret = dax_fault_return(PTR_ERR(entry));
 		goto finish_iomap;
 	}
 
@@ -1096,13 +1160,13 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 
 		if (error)
-			goto finish_iomap;
+			goto error_unlock_entry;
 
 		__SetPageUptodate(vmf->cow_page);
 		vmf_ret = finish_fault(vmf);
 		if (!vmf_ret)
 			vmf_ret = VM_FAULT_DONE_COW;
-		goto finish_iomap;
+		goto unlock_entry;
 	}
 
 	switch (iomap.type) {
@@ -1114,12 +1178,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, sector,
 				PAGE_SIZE, &entry, vma, vmf);
+		/* -EBUSY is fine, somebody else faulted on the same PTE */
+		if (error == -EBUSY)
+			error = 0;
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
-			vmf_ret = dax_load_hole(mapping, entry, vmf);
-			break;
+			vmf_ret = dax_load_hole(mapping, &entry, vmf);
+			goto unlock_entry;
 		}
 		/*FALLTHRU*/
 	default:
@@ -1128,31 +1195,25 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		break;
 	}
 
+ error_unlock_entry:
+	vmf_ret = dax_fault_return(error) | major;
+ unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
-		if (error || (vmf_ret & VM_FAULT_ERROR)) {
-			/* keep previous error */
-			ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PAGE_SIZE,
-					PAGE_SIZE, flags, &iomap);
-		}
+		int copied = PAGE_SIZE;
+
+		if (vmf_ret & VM_FAULT_ERROR)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PTE we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
- unlock_entry:
-	if (vmf_ret != VM_FAULT_LOCKED || error)
-		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
- out:
-	if (error == -ENOMEM)
-		return VM_FAULT_OOM | major;
-	/* -EBUSY is fine, somebody else faulted on the same PTE */
-	if (error < 0 && error != -EBUSY)
-		return VM_FAULT_SIGBUS | major;
-	if (vmf_ret) {
-		WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */
-		return vmf_ret;
-	}
-	return VM_FAULT_NOPAGE | major;
+	return vmf_ret;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_fault);
 
@@ -1277,16 +1338,6 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		goto fallback;
 
 	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
-	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
-	if (IS_ERR(entry))
-		goto fallback;
-
-	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way
 	 * to look up our filesystem block.
@@ -1294,10 +1345,21 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	pos = (loff_t)pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		goto fallback;
+
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
+	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto finish_iomap;
+
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
@@ -1310,7 +1372,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
-			goto finish_iomap;
+			goto unlock_entry;
 		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
 				&entry);
 		break;
@@ -1319,20 +1381,23 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		break;
 	}
 
- finish_iomap:
-	if (ops->iomap_end) {
-		if (result == VM_FAULT_FALLBACK) {
-			ops->iomap_end(inode, pos, PMD_SIZE, 0, iomap_flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PMD_SIZE, PMD_SIZE,
-					iomap_flags, &iomap);
-			if (error)
-				result = VM_FAULT_FALLBACK;
-		}
-	}
  unlock_entry:
 	put_locked_mapping_entry(mapping, pgoff, entry);
+ finish_iomap:
+	if (ops->iomap_end) {
+		int copied = PMD_SIZE;
+
+		if (result == VM_FAULT_FALLBACK)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PMD we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
+				&iomap);
+	}
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, pmd, address);
diff --git a/fs/dcache.c b/fs/dcache.c
index 2523783..769903d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -26,7 +26,7 @@
 #include <linux/export.h>
 #include <linux/mount.h>
 #include <linux/file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/security.h>
 #include <linux/seqlock.h>
 #include <linux/swap.h>
diff --git a/fs/dcookies.c b/fs/dcookies.c
index a26a701..0d0461c 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -26,7 +26,7 @@
 #include <linux/mutex.h>
 #include <linux/path.h>
 #include <linux/compat.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* The dcookies are allocated from a kmem_cache and
  * hashed onto a small number of lists. None of the
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index b670f56..748e8d5 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -38,7 +38,7 @@
 #include <linux/mutex.h>
 #include <linux/idr.h>
 #include <linux/ratelimit.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/dlm.h>
 #include "config.h"
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 35502d4..6df3322 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1395,7 +1395,6 @@ static int nodeid_warned(int nodeid, int num_nodes, int *warned)
 void dlm_scan_waiters(struct dlm_ls *ls)
 {
 	struct dlm_lkb *lkb;
-	ktime_t zero = ktime_set(0, 0);
 	s64 us;
 	s64 debug_maxus = 0;
 	u32 debug_scanned = 0;
@@ -1409,7 +1408,7 @@ void dlm_scan_waiters(struct dlm_ls *ls)
 	mutex_lock(&ls->ls_waiters_mutex);
 
 	list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
-		if (ktime_equal(lkb->lkb_wait_time, zero))
+		if (!lkb->lkb_wait_time)
 			continue;
 
 		debug_scanned++;
@@ -1419,7 +1418,7 @@ void dlm_scan_waiters(struct dlm_ls *ls)
 		if (us < dlm_config.ci_waitwarn_us)
 			continue;
 
-		lkb->lkb_wait_time = zero;
+		lkb->lkb_wait_time = 0;
 
 		debug_expired++;
 		if (us > debug_maxus)
diff --git a/fs/efs/efs.h b/fs/efs/efs.h
index 5bbf961..70f5d4f 100644
--- a/fs/efs/efs.h
+++ b/fs/efs/efs.h
@@ -14,7 +14,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/fs.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define EFS_VERSION "1.0a"
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 10db912..bcb68fc 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -34,7 +34,7 @@
 #include <linux/mutex.h>
 #include <linux/anon_inodes.h>
 #include <linux/device.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/mman.h>
 #include <linux/atomic.h>
diff --git a/fs/exec.c b/fs/exec.c
index 8112eac..e579466 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -19,7 +19,7 @@
  * current->executable is only used by the procfs.  This allows a dispatch
  * table to check for several different types  of binary formats.  We keep
  * trying until we recognize the file or we run out of supported binary
- * formats. 
+ * formats.
  */
 
 #include <linux/slab.h>
@@ -58,7 +58,7 @@
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
 
@@ -1268,6 +1268,13 @@ int flush_old_exec(struct linux_binprm * bprm)
 	flush_thread();
 	current->personality &= ~bprm->per_clear;
 
+	/*
+	 * We have to apply CLOEXEC before we change whether the process is
+	 * dumpable (in setup_new_exec) to avoid a race with a process in userspace
+	 * trying to access the should-be-closed file descriptors of a process
+	 * undergoing exec(2).
+	 */
+	do_close_on_exec(current->files);
 	return 0;
 
 out:
@@ -1330,7 +1337,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 	   group */
 	current->self_exec_id++;
 	flush_signal_handlers(current, 0);
-	do_close_on_exec(current->files);
 }
 EXPORT_SYMBOL(setup_new_exec);
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0093ea2..f073bfc 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -751,9 +751,8 @@ static int ext2_get_blocks(struct inode *inode,
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
 		}
-	} else {
-		*new = true;
 	}
+	*new = true;
 
 	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
 	mutex_unlock(&ei->truncate_mutex);
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 9d61742..191e02b 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -14,7 +14,7 @@
 #include <linux/compat.h>
 #include <linux/mount.h>
 #include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 6cb042b..9e25a71 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -31,7 +31,7 @@
 #include <linux/mount.h>
 #include <linux/log2.h>
 #include <linux/quotaops.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index b1f8416..3e295d3 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -37,7 +37,7 @@
 #include <linux/quotaops.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fiemap.h>
 #include <linux/backing-dev.h>
 #include "ext4_jbd2.h"
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b5f1844..d663d3d 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -258,7 +258,6 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int result;
-	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -266,24 +265,12 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-						EXT4_DATA_TRANS_BLOCKS(sb));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else
-		result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+	}
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	if (write)
 		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
@@ -292,7 +279,6 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 						pmd_t *pmd, unsigned int flags)
 {
 	int result;
-	handle_t *handle = NULL;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = flags & FAULT_FLAG_WRITE;
@@ -300,27 +286,13 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-				ext4_chunk_trans_blocks(inode,
-							PMD_SIZE / PAGE_SIZE));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else {
-		result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
-					     &ext4_iomap_ops);
 	}
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
+				     &ext4_iomap_ops);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+	if (write)
 		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return result;
 }
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 49fd137..d534399 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -15,7 +15,7 @@
 #include <linux/file.h>
 #include <linux/quotaops.h>
 #include <linux/uuid.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 63a6b63..66845a0 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -38,7 +38,7 @@
 #include <linux/log2.h>
 #include <linux/crc16.h>
 #include <linux/cleancache.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/kthread.h>
 #include <linux/freezer.h>
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 6e2771c..e1c54f2 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -25,7 +25,7 @@
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
 
diff --git a/fs/fhandle.c b/fs/fhandle.c
index ca3c3dd..5559168 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -8,7 +8,7 @@
 #include <linux/fs_struct.h>
 #include <linux/fsnotify.h>
 #include <linux/personality.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 #include "mount.h"
 
diff --git a/fs/filesystems.c b/fs/filesystems.c
index c5618db..cac7554 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -14,7 +14,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Handling of filesystem drivers list.
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index e23ff70..016c11e 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -22,7 +22,7 @@
 #include <linux/swap.h>
 #include <linux/crc32.h>
 #include <linux/writeback.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/dlm.h>
 #include <linux/dlm_plock.h>
 #include <linux/delay.h>
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 14cbf60..94f50ca 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -21,7 +21,7 @@
 #include <linux/list.h>
 #include <linux/wait.h>
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/kthread.h>
@@ -695,7 +695,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_target = LM_ST_UNLOCKED;
 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
 	gl->gl_ops = glops;
-	gl->gl_dstamp = ktime_set(0, 0);
+	gl->gl_dstamp = 0;
 	preempt_disable();
 	/* We use the global stats to estimate the initial per-glock stats */
 	gl->gl_stats = this_cpu_ptr(sdp->sd_lkstats)->lkstats[glops->go_type];
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6cd9f84..eb7724b 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -19,7 +19,7 @@
 #include <linux/crc32.h>
 #include <linux/fiemap.h>
 #include <linux/security.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "gfs2.h"
 #include "incore.h"
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index c9ff1cf..f8d30e4 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -15,7 +15,7 @@
 #include <linux/buffer_head.h>
 #include <linux/module.h>
 #include <linux/kobject.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/genhd.h>
 
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index aee4485..763d659 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -14,7 +14,7 @@
 #include <linux/buffer_head.h>
 #include <linux/crc32.h>
 #include <linux/gfs2_ondisk.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "gfs2.h"
 #include "incore.h"
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index a4a5770..d87721a 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -14,7 +14,7 @@
 #include <linux/xattr.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/posix_acl_xattr.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "gfs2.h"
 #include "incore.h"
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index 4cdec5a..6d0783e 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -23,7 +23,7 @@
 #include <linux/workqueue.h>
 
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "hfs.h"
 
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index 99627f8..0a156d8 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -16,7 +16,7 @@
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/sched.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "hfsplus_fs.h"
 
 /*
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 4fb7b10..54de77e 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -37,7 +37,7 @@
 #include <linux/migrate.h>
 #include <linux/uio.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static const struct super_operations hugetlbfs_ops;
 static const struct address_space_operations hugetlbfs_aops;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 8ed971e..a097048 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -47,7 +47,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/jbd2.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 
 #ifdef CONFIG_JBD2_DEBUG
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index b6fd1ff..fc89f94 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -13,7 +13,7 @@
 #include <linux/sched.h>
 #include <linux/blkdev.h>
 #include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "jfs_filsys.h"
 #include "jfs_debug.h"
diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c
index a37eb5f..a709076 100644
--- a/fs/jfs/jfs_debug.c
+++ b/fs/jfs/jfs_debug.c
@@ -22,7 +22,7 @@
 #include <linux/module.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "jfs_incore.h"
 #include "jfs_filsys.h"
 #include "jfs_debug.h"
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 85671f7..2be7c9c 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -31,7 +31,7 @@
 #include <linux/exportfs.h>
 #include <linux/crc32.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/blkdev.h>
 
diff --git a/fs/libfs.c b/fs/libfs.c
index 6637aa6..e973cd5 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -16,7 +16,7 @@
 #include <linux/writeback.h>
 #include <linux/buffer_head.h> /* sync_mapping_buffers */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 
diff --git a/fs/locks.c b/fs/locks.c
index 22c5b4a..2681132 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -131,7 +131,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/filelock.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
diff --git a/fs/namei.c b/fs/namei.c
index d9fc761..ad74877 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -37,7 +37,7 @@
 #include <linux/hash.h>
 #include <linux/bitops.h>
 #include <linux/init_task.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 #include "mount.h"
diff --git a/fs/namespace.c b/fs/namespace.c
index f7e28f8..b5b1259 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -96,10 +96,6 @@ static inline struct hlist_head *mp_hash(struct dentry *dentry)
 	return &mountpoint_hashtable[tmp & mp_hash_mask];
 }
 
-/*
- * allocation is serialized by namespace_sem, but we need the spinlock to
- * serialize with freeing.
- */
 static int mnt_alloc_id(struct mount *mnt)
 {
 	int res;
@@ -1034,6 +1030,8 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 		if (IS_MNT_SLAVE(old))
 			list_add(&mnt->mnt_slave, &old->mnt_slave);
 		mnt->mnt_master = old->mnt_master;
+	} else {
+		CLEAR_MNT_SHARED(mnt);
 	}
 	if (flag & CL_MAKE_SHARED)
 		set_mnt_shared(mnt);
@@ -1828,9 +1826,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	if (IS_MNT_UNBINDABLE(old_mnt))
 		return ERR_PTR(-EINVAL);
 
-	down_read(&namespace_sem);
 	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
-	up_read(&namespace_sem);
 	if (IS_ERR(new_mnt))
 		return ERR_CAST(new_mnt);
 
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 6df2a38..088f524 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -18,7 +18,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <linux/namei.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 #include "ncp_fs.h"
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 83ca772..76965e7 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -8,7 +8,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/time.h>
 #include <linux/kernel.h>
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index ba611bf..7eb89c2 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -13,7 +13,7 @@
 
 #include <linux/module.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 
 #include <linux/time.h>
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 0a3f9b5..4434e49 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -20,7 +20,7 @@
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "ncp_fs.h"
 
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 33b873b..39f57be 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -18,7 +18,7 @@
 #include <linux/fcntl.h>
 #include <linux/memcontrol.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "ncp_fs.h"
 
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 17cfb74..b4c87cf 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -21,7 +21,7 @@
 #include <linux/fcntl.h>
 #include <linux/pagemap.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 #include <asm/string.h>
diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index 471bc3d..f32f272 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -16,7 +16,7 @@
 #include <linux/fcntl.h>
 #include <linux/stat.h>
 #include <linux/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/in.h>
 #include <linux/net.h>
 #include <linux/mm.h>
diff --git a/fs/ncpfs/symlink.c b/fs/ncpfs/symlink.c
index 421b6f9..a6d26b4 100644
--- a/fs/ncpfs/symlink.c
+++ b/fs/ncpfs/symlink.c
@@ -21,7 +21,7 @@
  */
 
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/errno.h>
 #include <linux/fs.h>
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index cb22a9f..fad8104 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1273,8 +1273,8 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
  */
 static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	int error;
 	struct inode *inode = d_inode(dentry);
+	int error = 0;
 
 	/*
 	 * I believe we can only get a negative dentry here in the case of a
@@ -1293,7 +1293,8 @@ static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags)
 		return 0;
 	}
 
-	error = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	if (nfs_mapping_need_revalidate_inode(inode))
+		error = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
 	dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n",
 			__func__, inode->i_ino, error ? "invalid" : "valid");
 	return !error;
@@ -2285,8 +2286,7 @@ static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, str
 		if (cache == NULL)
 			goto out;
 		/* Found an entry, is our attribute cache valid? */
-		if (!nfs_attribute_cache_expired(inode) &&
-		    !(nfsi->cache_validity & NFS_INO_INVALID_ATTR))
+		if (!nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
 			break;
 		err = -ECHILD;
 		if (!may_block)
@@ -2334,12 +2334,12 @@ static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred,
 		cache = NULL;
 	if (cache == NULL)
 		goto out;
-	err = nfs_revalidate_inode_rcu(NFS_SERVER(inode), inode);
-	if (err)
+	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
 		goto out;
 	res->jiffies = cache->jiffies;
 	res->cred = cache->cred;
 	res->mask = cache->mask;
+	err = 0;
 out:
 	rcu_read_unlock();
 	return err;
@@ -2491,12 +2491,13 @@ EXPORT_SYMBOL_GPL(nfs_may_open);
 static int nfs_execute_ok(struct inode *inode, int mask)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
-	int ret;
+	int ret = 0;
 
-	if (mask & MAY_NOT_BLOCK)
-		ret = nfs_revalidate_inode_rcu(server, inode);
-	else
-		ret = nfs_revalidate_inode(server, inode);
+	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) {
+		if (mask & MAY_NOT_BLOCK)
+			return -ECHILD;
+		ret = __nfs_revalidate_inode(server, inode);
+	}
 	if (ret == 0 && !execute_ok(inode))
 		ret = -EACCES;
 	return ret;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index be88bcd..aab32fc 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -52,7 +52,7 @@
 #include <linux/nfs_page.h>
 #include <linux/sunrpc/clnt.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 
 #include "internal.h"
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 55208b9..26dbe8b 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -29,7 +29,7 @@
 #include <linux/gfp.h>
 #include <linux/swap.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "delegation.h"
 #include "internal.h"
@@ -101,21 +101,11 @@ EXPORT_SYMBOL_GPL(nfs_file_release);
 static int nfs_revalidate_file_size(struct inode *inode, struct file *filp)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
-	struct nfs_inode *nfsi = NFS_I(inode);
-	const unsigned long force_reval = NFS_INO_REVAL_PAGECACHE|NFS_INO_REVAL_FORCED;
-	unsigned long cache_validity = nfsi->cache_validity;
-
-	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) &&
-	    (cache_validity & force_reval) != force_reval)
-		goto out_noreval;
 
 	if (filp->f_flags & O_DIRECT)
 		goto force_reval;
-	if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
+	if (nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE))
 		goto force_reval;
-	if (nfs_attribute_timeout(inode))
-		goto force_reval;
-out_noreval:
 	return 0;
 force_reval:
 	return __nfs_revalidate_inode(server, inode);
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index a5589b7..f956ca2 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -282,7 +282,8 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 			     s->nfs_client->cl_minorversion);
 
 out_test_devid:
-	if (filelayout_test_devid_unavailable(devid))
+	if (ret->ds_clp == NULL ||
+	    filelayout_test_devid_unavailable(devid))
 		ret = NULL;
 out:
 	return ret;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 9e111d0..0ca4af8 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -619,12 +619,11 @@ nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror,
 			    struct nfs4_ff_layoutstat *layoutstat,
 			    ktime_t now)
 {
-	static const ktime_t notime = {0};
 	s64 report_interval = FF_LAYOUTSTATS_REPORT_INTERVAL;
 	struct nfs4_flexfile_layout *ffl = FF_LAYOUT_FROM_HDR(mirror->layout);
 
 	nfs4_ff_start_busy_timer(&layoutstat->busy_timer, now);
-	if (ktime_equal(mirror->start_time, notime))
+	if (!mirror->start_time)
 		mirror->start_time = now;
 	if (mirror->report_interval != 0)
 		report_interval = (s64)mirror->report_interval * 1000LL;
@@ -1126,7 +1125,8 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 	case -EPIPE:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
-		nfs4_mark_deviceid_unavailable(devid);
+		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
+				&devid->deviceid);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		/* fall through */
 	default:
@@ -1175,7 +1175,8 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 	default:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
-		nfs4_mark_deviceid_unavailable(devid);
+		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
+				&devid->deviceid);
 	}
 	/* FIXME: Need to prevent infinite looping here. */
 	return -NFS4ERR_RESET_TO_PNFS;
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 3cc39d1..e5a6f24 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -177,7 +177,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 static void ff_layout_mark_devid_invalid(struct pnfs_layout_segment *lseg,
 		struct nfs4_deviceid_node *devid)
 {
-	nfs4_mark_deviceid_unavailable(devid);
+	nfs4_delete_deviceid(devid->ld, devid->nfs_client, &devid->deviceid);
 	if (!ff_layout_has_available_ds(lseg))
 		pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode,
 				lseg);
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index a608ffd..391dafa 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -30,7 +30,7 @@
 #include <linux/namei.h>
 #include <linux/security.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5864146..5ca4d96 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -39,7 +39,7 @@
 #include <linux/compat.h>
 #include <linux/freezer.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
@@ -160,6 +160,43 @@ int nfs_sync_mapping(struct address_space *mapping)
 	return ret;
 }
 
+static int nfs_attribute_timeout(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
+}
+
+static bool nfs_check_cache_invalid_delegated(struct inode *inode, unsigned long flags)
+{
+	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+
+	/* Special case for the pagecache or access cache */
+	if (flags == NFS_INO_REVAL_PAGECACHE &&
+	    !(cache_validity & NFS_INO_REVAL_FORCED))
+		return false;
+	return (cache_validity & flags) != 0;
+}
+
+static bool nfs_check_cache_invalid_not_delegated(struct inode *inode, unsigned long flags)
+{
+	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+
+	if ((cache_validity & flags) != 0)
+		return true;
+	if (nfs_attribute_timeout(inode))
+		return true;
+	return false;
+}
+
+bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags)
+{
+	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
+		return nfs_check_cache_invalid_delegated(inode, flags);
+
+	return nfs_check_cache_invalid_not_delegated(inode, flags);
+}
+
 static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -795,6 +832,8 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
 	if (!is_sync)
 		return;
 	inode = d_inode(ctx->dentry);
+	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
+		return;
 	nfsi = NFS_I(inode);
 	if (inode->i_mapping->nrpages == 0)
 		return;
@@ -1044,13 +1083,6 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 	return status;
 }
 
-int nfs_attribute_timeout(struct inode *inode)
-{
-	struct nfs_inode *nfsi = NFS_I(inode);
-
-	return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
-}
-
 int nfs_attribute_cache_expired(struct inode *inode)
 {
 	if (nfs_have_delegated_attributes(inode))
@@ -1073,15 +1105,6 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 }
 EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
 
-int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode)
-{
-	if (!(NFS_I(inode)->cache_validity &
-			(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
-			&& !nfs_attribute_cache_expired(inode))
-		return NFS_STALE(inode) ? -ESTALE : 0;
-	return -ECHILD;
-}
-
 static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -1114,17 +1137,8 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 
 bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 {
-	unsigned long cache_validity = NFS_I(inode)->cache_validity;
-
-	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) {
-		const unsigned long force_reval =
-			NFS_INO_REVAL_PAGECACHE|NFS_INO_REVAL_FORCED;
-		return (cache_validity & force_reval) == force_reval;
-	}
-
-	return (cache_validity & NFS_INO_REVAL_PAGECACHE)
-		|| nfs_attribute_timeout(inode)
-		|| NFS_STALE(inode);
+	return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) ||
+		NFS_STALE(inode);
 }
 
 int nfs_revalidate_mapping_rcu(struct inode *inode)
@@ -1536,13 +1550,6 @@ static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr
 {
 	unsigned long invalid = NFS_INO_INVALID_ATTR;
 
-	/*
-	 * Don't revalidate the pagecache if we hold a delegation, but do
-	 * force an attribute update
-	 */
-	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
-		invalid = NFS_INO_INVALID_ATTR|NFS_INO_REVAL_FORCED;
-
 	if (S_ISDIR(inode->i_mode))
 		invalid |= NFS_INO_INVALID_DATA;
 	nfs_set_cache_invalid(inode, invalid);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 6b79c2c..09ca5095 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -381,6 +381,7 @@ extern int nfs_drop_inode(struct inode *);
 extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
 void nfs_zap_acl_cache(struct inode *inode);
+extern bool nfs_check_cache_invalid(struct inode *, unsigned long);
 extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
 extern int nfs_wait_atomic_killable(atomic_t *p);
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d33242c..6dcbc5d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1089,8 +1089,15 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 
 	spin_lock(&dir->i_lock);
 	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
-	if (!cinfo->atomic || cinfo->before != dir->i_version)
+	if (cinfo->atomic && cinfo->before == dir->i_version) {
+		nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE;
+		nfsi->attrtimeo_timestamp = jiffies;
+	} else {
 		nfs_force_lookup_revalidate(dir);
+		if (cinfo->before != dir->i_version)
+			nfsi->cache_validity |= NFS_INO_INVALID_ACCESS |
+				NFS_INO_INVALID_ACL;
+	}
 	dir->i_version = cinfo->after;
 	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	nfs_fscache_invalidate(dir);
@@ -3115,6 +3122,16 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			res_stateid = &calldata->res.stateid;
 			renew_lease(server, calldata->timestamp);
 			break;
+		case -NFS4ERR_ACCESS:
+			if (calldata->arg.bitmask != NULL) {
+				calldata->arg.bitmask = NULL;
+				calldata->res.fattr = NULL;
+				task->tk_status = 0;
+				rpc_restart_call_prepare(task);
+				goto out_release;
+
+			}
+			break;
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_EXPIRED:
@@ -3140,7 +3157,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			res_stateid, calldata->arg.fmode);
 out_release:
 	nfs_release_seqid(calldata->arg.seqid);
-	nfs_refresh_inode(calldata->inode, calldata->res.fattr);
+	nfs_refresh_inode(calldata->inode, &calldata->fattr);
 	dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
 }
 
@@ -3193,9 +3210,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		goto out_wait;
 	}
 
-	if (calldata->arg.fmode == 0) {
+	if (calldata->arg.fmode == 0)
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
 
+	if (calldata->arg.fmode == 0 || calldata->arg.fmode == FMODE_READ) {
 		/* Close-to-open cache consistency revalidation */
 		if (!nfs4_have_delegation(inode, FMODE_READ))
 			calldata->arg.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
@@ -3207,7 +3225,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		nfs4_map_atomic_open_share(NFS_SERVER(inode),
 				calldata->arg.fmode, 0);
 
-	nfs_fattr_init(calldata->res.fattr);
+	if (calldata->res.fattr == NULL)
+		calldata->arg.bitmask = NULL;
+	else if (calldata->arg.bitmask == NULL)
+		calldata->res.fattr = NULL;
 	calldata->timestamp = jiffies;
 	if (nfs4_setup_sequence(NFS_SERVER(inode),
 				&calldata->arg.seq_args,
@@ -3274,6 +3295,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
 	calldata->arg.seqid = alloc_seqid(&state->owner->so_seqid, gfp_mask);
 	if (IS_ERR(calldata->arg.seqid))
 		goto out_free_calldata;
+	nfs_fattr_init(&calldata->fattr);
 	calldata->arg.fmode = 0;
 	calldata->lr.arg.ld_private = &calldata->lr.ld_private;
 	calldata->res.fattr = &calldata->fattr;
@@ -5673,6 +5695,14 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 	case -NFS4ERR_STALE_STATEID:
 		task->tk_status = 0;
 		break;
+	case -NFS4ERR_ACCESS:
+		if (data->args.bitmask) {
+			data->args.bitmask = NULL;
+			data->res.fattr = NULL;
+			task->tk_status = 0;
+			rpc_restart_call_prepare(task);
+			return;
+		}
 	default:
 		if (nfs4_async_handle_error(task, data->res.server,
 					    NULL, NULL) == -EAGAIN) {
@@ -5692,6 +5722,7 @@ static void nfs4_delegreturn_release(void *calldata)
 		if (data->lr.roc)
 			pnfs_roc_release(&data->lr.arg, &data->lr.res,
 					data->res.lr_ret);
+		nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
 		nfs_iput_and_deactive(inode);
 	}
 	kfree(calldata);
@@ -5780,10 +5811,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	if (status != 0)
 		goto out;
 	status = data->rpc_status;
-	if (status == 0)
-		nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
-	else
-		nfs_refresh_inode(inode, &data->fattr);
 out:
 	rpc_put_task(task);
 	return status;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 95baf7d..1d152f4 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -494,21 +494,18 @@ nfs4_alloc_state_owner(struct nfs_server *server,
 }
 
 static void
-nfs4_drop_state_owner(struct nfs4_state_owner *sp)
+nfs4_reset_state_owner(struct nfs4_state_owner *sp)
 {
-	struct rb_node *rb_node = &sp->so_server_node;
-
-	if (!RB_EMPTY_NODE(rb_node)) {
-		struct nfs_server *server = sp->so_server;
-		struct nfs_client *clp = server->nfs_client;
-
-		spin_lock(&clp->cl_lock);
-		if (!RB_EMPTY_NODE(rb_node)) {
-			rb_erase(rb_node, &server->state_owners);
-			RB_CLEAR_NODE(rb_node);
-		}
-		spin_unlock(&clp->cl_lock);
-	}
+	/* This state_owner is no longer usable, but must
+	 * remain in place so that state recovery can find it
+	 * and the opens associated with it.
+	 * It may also be used for new 'open' request to
+	 * return a delegation to the server.
+	 * So update the 'create_time' so that it looks like
+	 * a new state_owner.  This will cause the server to
+	 * request an OPEN_CONFIRM to start a new sequence.
+	 */
+	sp->so_seqid.create_time = ktime_get();
 }
 
 static void nfs4_free_state_owner(struct nfs4_state_owner *sp)
@@ -797,21 +794,33 @@ void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode)
 
 /*
  * Search the state->lock_states for an existing lock_owner
- * that is compatible with current->files
+ * that is compatible with either of the given owners.
+ * If the second is non-zero, then the first refers to a Posix-lock
+ * owner (current->files) and the second refers to a flock/OFD
+ * owner (struct file*).  In that case, prefer a match for the first
+ * owner.
+ * If both sorts of locks are held on the one file we cannot know
+ * which stateid was intended to be used, so a "correct" choice cannot
+ * be made.  Failing that, a "consistent" choice is preferable.  The
+ * consistent choice we make is to prefer the first owner, that of a
+ * Posix lock.
  */
 static struct nfs4_lock_state *
 __nfs4_find_lock_state(struct nfs4_state *state,
 		       fl_owner_t fl_owner, fl_owner_t fl_owner2)
 {
-	struct nfs4_lock_state *pos;
+	struct nfs4_lock_state *pos, *ret = NULL;
 	list_for_each_entry(pos, &state->lock_states, ls_locks) {
-		if (pos->ls_owner != fl_owner &&
-		    pos->ls_owner != fl_owner2)
-			continue;
-		atomic_inc(&pos->ls_count);
-		return pos;
+		if (pos->ls_owner == fl_owner) {
+			ret = pos;
+			break;
+		}
+		if (pos->ls_owner == fl_owner2)
+			ret = pos;
 	}
-	return NULL;
+	if (ret)
+		atomic_inc(&ret->ls_count);
+	return ret;
 }
 
 /*
@@ -1101,7 +1110,7 @@ void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
 
 	sp = container_of(seqid->sequence, struct nfs4_state_owner, so_seqid);
 	if (status == -NFS4ERR_BAD_SEQID)
-		nfs4_drop_state_owner(sp);
+		nfs4_reset_state_owner(sp);
 	if (!nfs4_has_session(sp->so_server->nfs_client))
 		nfs_increment_seqid(status, seqid);
 }
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1af6268..e9255cb 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -502,11 +502,13 @@ static int nfs4_stat_to_errno(int);
 				(compound_encode_hdr_maxsz + \
 				 encode_sequence_maxsz + \
 				 encode_putfh_maxsz + \
+				 encode_layoutreturn_maxsz + \
 				 encode_open_downgrade_maxsz)
 #define NFS4_dec_open_downgrade_sz \
 				(compound_decode_hdr_maxsz + \
 				 decode_sequence_maxsz + \
 				 decode_putfh_maxsz + \
+				 decode_layoutreturn_maxsz + \
 				 decode_open_downgrade_maxsz)
 #define NFS4_enc_close_sz	(compound_encode_hdr_maxsz + \
 				 encode_sequence_maxsz + \
@@ -2277,9 +2279,9 @@ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_putfh(xdr, args->fh, &hdr);
 	if (args->lr_args)
 		encode_layoutreturn(xdr, args->lr_args, &hdr);
-	encode_close(xdr, args, &hdr);
 	if (args->bitmask != NULL)
 		encode_getfattr(xdr, args->bitmask, &hdr);
+	encode_close(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -2356,6 +2358,8 @@ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
+	if (args->lr_args)
+		encode_layoutreturn(xdr, args->lr_args, &hdr);
 	encode_open_downgrade(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
@@ -2701,7 +2705,8 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req,
 	encode_putfh(xdr, args->fhandle, &hdr);
 	if (args->lr_args)
 		encode_layoutreturn(xdr, args->lr_args, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
+	if (args->bitmask)
+		encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_delegreturn(xdr, args->stateid, &hdr);
 	encode_nops(&hdr);
 }
@@ -6151,6 +6156,12 @@ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
+	if (res->lr_res) {
+		status = decode_layoutreturn(xdr, res->lr_res);
+		res->lr_ret = status;
+		if (status)
+			goto out;
+	}
 	status = decode_open_downgrade(xdr, res);
 out:
 	return status;
@@ -6484,16 +6495,12 @@ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 		if (status)
 			goto out;
 	}
+	if (res->fattr != NULL) {
+		status = decode_getfattr(xdr, res->fattr, res->server);
+		if (status != 0)
+			goto out;
+	}
 	status = decode_close(xdr, res);
-	if (status != 0)
-		goto out;
-	/*
-	 * Note: Server may do delete on close for this file
-	 * 	in which case the getattr call will fail with
-	 * 	an ESTALE error. Shouldn't be a problem,
-	 * 	though, since fattr->valid will remain unset.
-	 */
-	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6966,9 +6973,11 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp,
 		if (status)
 			goto out;
 	}
-	status = decode_getfattr(xdr, res->fattr, res->server);
-	if (status != 0)
-		goto out;
+	if (res->fattr) {
+		status = decode_getfattr(xdr, res->fattr, res->server);
+		if (status != 0)
+			goto out;
+	}
 	status = decode_delegreturn(xdr);
 out:
 	return status;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 896df7b..59554f3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1251,6 +1251,7 @@ bool pnfs_roc(struct inode *ino,
 	nfs4_stateid stateid;
 	enum pnfs_iomode iomode = 0;
 	bool layoutreturn = false, roc = false;
+	bool skip_read = false;
 
 	if (!nfs_have_layout(ino))
 		return false;
@@ -1270,18 +1271,27 @@ bool pnfs_roc(struct inode *ino,
 	}
 
 	/* no roc if we hold a delegation */
-	if (nfs4_check_delegation(ino, FMODE_READ))
-		goto out_noroc;
+	if (nfs4_check_delegation(ino, FMODE_READ)) {
+		if (nfs4_check_delegation(ino, FMODE_WRITE))
+			goto out_noroc;
+		skip_read = true;
+	}
 
 	list_for_each_entry(ctx, &nfsi->open_files, list) {
 		state = ctx->state;
+		if (state == NULL)
+			continue;
 		/* Don't return layout if there is open file state */
-		if (state != NULL && state->state != 0)
+		if (state->state & FMODE_WRITE)
 			goto out_noroc;
+		if (state->state & FMODE_READ)
+			skip_read = true;
 	}
 
 
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) {
+		if (skip_read && lseg->pls_range.iomode == IOMODE_READ)
+			continue;
 		/* If we are sending layoutreturn, invalidate all valid lsegs */
 		if (!test_and_clear_bit(NFS_LSEG_ROC, &lseg->pls_flags))
 			continue;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ddce94ce..6bca178 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -55,7 +55,7 @@
 #include <linux/nsproxy.h>
 #include <linux/rcupdate.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 6e761f3..b00d53d 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -24,7 +24,7 @@
 #include <linux/freezer.h>
 #include <linux/wait.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "delegation.h"
 #include "internal.h"
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index c16bf5a..34c1c44 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/nsproxy.h>
 #include <linux/sunrpc/addr.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "state.h"
 #include "netns.h"
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7a21abe..26c6fdb 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -26,7 +26,7 @@
 #include <linux/jhash.h>
 #include <linux/ima.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/exportfs.h>
 #include <linux/writeback.h>
 #include <linux/security.h>
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 99510d8..358ed7e 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -30,7 +30,7 @@
 #include <linux/writeback.h>
 
 #include <asm/page.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "attrib.h"
 #include "bitmap.h"
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 96a155a..f6e8717 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1250,7 +1250,7 @@ static int o2hb_thread(void *data)
 
 		mlog(ML_HEARTBEAT,
 		     "start = %lld, end = %lld, msec = %u, ret = %d\n",
-		     before_hb.tv64, after_hb.tv64, elapsed_msec, ret);
+		     before_hb, after_hb, elapsed_msec, ret);
 
 		if (!kthread_should_stop() &&
 		    elapsed_msec < reg->hr_timeout_ms) {
diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c
index dfe162f..d331c23 100644
--- a/fs/ocfs2/cluster/masklog.c
+++ b/fs/ocfs2/cluster/masklog.c
@@ -24,7 +24,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "masklog.h"
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 8abab16..d4b5c81 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -62,7 +62,7 @@
 #include <linux/export.h>
 #include <net/tcp.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "heartbeat.h"
 #include "tcp.h"
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 1079fae..9ab9e18 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -45,7 +45,7 @@
 #include <linux/backing-dev.h>
 #include <linux/poll.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "stackglue.h"
 #include "userdlm.h"
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index d171d2c..f8933cb 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4834,7 +4834,7 @@ int ocfs2_reflink_remap_range(struct file *file_in,
 
 	ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
 			&len, is_dedupe);
-	if (ret || len == 0)
+	if (ret <= 0)
 		goto out_unlock;
 
 	/* Lock out changes to the allocation maps and remap. */
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index c9e828e..dae9eb7 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -24,7 +24,7 @@
 #include <linux/slab.h>
 #include <linux/reboot.h>
 #include <linux/sched.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "stackglue.h"
 
diff --git a/fs/open.c b/fs/open.c
index d3ed817..9921f70 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -19,7 +19,7 @@
 #include <linux/mount.h>
 #include <linux/fcntl.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fs.h>
 #include <linux/personality.h>
 #include <linux/pagemap.h>
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index c003a66..13215f2 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -16,7 +16,7 @@
 #include <asm/openprom.h>
 #include <asm/oplib.h>
 #include <asm/prom.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static DEFINE_MUTEX(op_mutex);
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 8e0d9f2..73b84ba 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -23,7 +23,7 @@
 #include <linux/fcntl.h>
 #include <linux/memcontrol.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
 
 #include "internal.h"
diff --git a/fs/pnode.c b/fs/pnode.c
index 234a9ac..06a793f 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -67,49 +67,47 @@ int get_dominating_id(struct mount *mnt, const struct path *root)
 
 static int do_make_slave(struct mount *mnt)
 {
-	struct mount *peer_mnt = mnt, *master = mnt->mnt_master;
-	struct mount *slave_mnt;
+	struct mount *master, *slave_mnt;
 
-	/*
-	 * slave 'mnt' to a peer mount that has the
-	 * same root dentry. If none is available then
-	 * slave it to anything that is available.
-	 */
-	while ((peer_mnt = next_peer(peer_mnt)) != mnt &&
-	       peer_mnt->mnt.mnt_root != mnt->mnt.mnt_root) ;
-
-	if (peer_mnt == mnt) {
-		peer_mnt = next_peer(mnt);
-		if (peer_mnt == mnt)
-			peer_mnt = NULL;
-	}
-	if (mnt->mnt_group_id && IS_MNT_SHARED(mnt) &&
-	    list_empty(&mnt->mnt_share))
-		mnt_release_group_id(mnt);
-
-	list_del_init(&mnt->mnt_share);
-	mnt->mnt_group_id = 0;
-
-	if (peer_mnt)
-		master = peer_mnt;
-
-	if (master) {
-		list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)
-			slave_mnt->mnt_master = master;
-		list_move(&mnt->mnt_slave, &master->mnt_slave_list);
-		list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);
-		INIT_LIST_HEAD(&mnt->mnt_slave_list);
-	} else {
-		struct list_head *p = &mnt->mnt_slave_list;
-		while (!list_empty(p)) {
-                        slave_mnt = list_first_entry(p,
-					struct mount, mnt_slave);
-			list_del_init(&slave_mnt->mnt_slave);
-			slave_mnt->mnt_master = NULL;
+	if (list_empty(&mnt->mnt_share)) {
+		if (IS_MNT_SHARED(mnt)) {
+			mnt_release_group_id(mnt);
+			CLEAR_MNT_SHARED(mnt);
 		}
+		master = mnt->mnt_master;
+		if (!master) {
+			struct list_head *p = &mnt->mnt_slave_list;
+			while (!list_empty(p)) {
+				slave_mnt = list_first_entry(p,
+						struct mount, mnt_slave);
+				list_del_init(&slave_mnt->mnt_slave);
+				slave_mnt->mnt_master = NULL;
+			}
+			return 0;
+		}
+	} else {
+		struct mount *m;
+		/*
+		 * slave 'mnt' to a peer mount that has the
+		 * same root dentry. If none is available then
+		 * slave it to anything that is available.
+		 */
+		for (m = master = next_peer(mnt); m != mnt; m = next_peer(m)) {
+			if (m->mnt.mnt_root == mnt->mnt.mnt_root) {
+				master = m;
+				break;
+			}
+		}
+		list_del_init(&mnt->mnt_share);
+		mnt->mnt_group_id = 0;
+		CLEAR_MNT_SHARED(mnt);
 	}
+	list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)
+		slave_mnt->mnt_master = master;
+	list_move(&mnt->mnt_slave, &master->mnt_slave_list);
+	list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);
+	INIT_LIST_HEAD(&mnt->mnt_slave_list);
 	mnt->mnt_master = master;
-	CLEAR_MNT_SHARED(mnt);
 	return 0;
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5ea8363..8e7e61b 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -47,7 +47,7 @@
  *  Overall revision about smaps.
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/errno.h>
 #include <linux/time.h>
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 7eb3cef..f6a01f0 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -22,7 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 8733001..842a5ff 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -24,7 +24,7 @@
 #include <linux/mount.h>
 #include <linux/magic.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 5c89a07..0b80ad8 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -23,7 +23,7 @@
 #include <linux/bootmem.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <linux/list.h>
 #include <linux/ioport.h>
diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c
index 05f8dcd..f9387bb 100644
--- a/fs/proc/kmsg.c
+++ b/fs/proc/kmsg.c
@@ -14,7 +14,7 @@
 #include <linux/fs.h>
 #include <linux/syslog.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 
 extern wait_queue_head_t log_wait;
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index f8595e8..7563437 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -25,7 +25,7 @@
 #include <linux/seq_file.h>
 #include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
 #include <asm/div64.h>
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 3ecd445..a2066e6 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -13,7 +13,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
 #include <linux/kernel-page-flags.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 
 #define KPMSIZE sizeof(u64)
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 7ae6b1d..ffd72a6 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -8,7 +8,7 @@
  *  proc net directory handling functions
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/errno.h>
 #include <linux/time.h>
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index 15f327b..901bd06 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -4,7 +4,7 @@
  * Copyright 1997, Theodore Ts'o
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/errno.h>
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 4bd0373..1988440 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -6,7 +6,7 @@
  *  proc root directory handling functions
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/errno.h>
 #include <linux/time.h>
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 958f325..8f96a49 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -17,7 +17,7 @@
 #include <linux/shmem_fs.h>
 
 #include <asm/elf.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
 
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 8ab782d..5105b15 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -22,7 +22,7 @@
 #include <linux/list.h>
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include "internal.h"
 
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 2bcbf4e..2ef7ce7 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -23,7 +23,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 
 static int ramfs_nommu_setattr(struct dentry *, struct iattr *);
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 8621c03..26e4586 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -35,7 +35,7 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 
 #define RAMFS_DEFAULT_MODE	0755
diff --git a/fs/read_write.c b/fs/read_write.c
index da6de12..5816d4c 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -20,7 +20,7 @@
 #include <linux/fs.h>
 #include "internal.h"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
@@ -1669,6 +1669,9 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
  * Check that the two inodes are eligible for cloning, the ranges make
  * sense, and then flush all dirty data.  Caller must ensure that the
  * inodes have been locked against any other modifications.
+ *
+ * Returns: 0 for "nothing to clone", 1 for "something to clone", or
+ * the usual negative error code.
  */
 int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
 			       struct inode *inode_out, loff_t pos_out,
@@ -1695,17 +1698,15 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
 
 	/* Are we going all the way to the end? */
 	isize = i_size_read(inode_in);
-	if (isize == 0) {
-		*len = 0;
+	if (isize == 0)
 		return 0;
-	}
 
 	/* Zero length dedupe exits immediately; reflink goes to EOF. */
 	if (*len == 0) {
-		if (is_dedupe) {
-			*len = 0;
+		if (is_dedupe || pos_in == isize)
 			return 0;
-		}
+		if (pos_in > isize)
+			return -EINVAL;
 		*len = isize - pos_in;
 	}
 
@@ -1769,7 +1770,7 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
 			return -EBADE;
 	}
 
-	return 0;
+	return 1;
 }
 EXPORT_SYMBOL(vfs_clone_file_prep_inodes);
 
@@ -1955,6 +1956,9 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 		goto out;
 	ret = 0;
 
+	if (off + len > i_size_read(src))
+		return -EINVAL;
+
 	/* pre-format output fields to sane values */
 	for (i = 0; i < count; i++) {
 		same->info[i].bytes_deduped = 0ULL;
diff --git a/fs/readdir.c b/fs/readdir.c
index 9d0212c..0e8a7f3 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -19,7 +19,7 @@
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 int iterate_dir(struct file *file, struct dir_context *ctx)
 {
diff --git a/fs/select.c b/fs/select.c
index 3d4f85d..305c0da 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -31,7 +31,7 @@
 #include <net/busy_poll.h>
 #include <linux/vmalloc.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 /*
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 368bfb9..ca69fb9 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -15,7 +15,7 @@
 #include <linux/printk.h>
 #include <linux/string_helpers.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 
 static void seq_set_overflow(struct seq_file *m)
@@ -190,6 +190,13 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 	 */
 	m->version = file->f_version;
 
+	/*
+	 * if request is to read from zero offset, reset iterator to first
+	 * record as it might have been already advanced by previous requests
+	 */
+	if (*ppos == 0)
+		m->index = 0;
+
 	/* Don't assume *ppos is where we left it */
 	if (unlikely(*ppos != m->read_pos)) {
 		while ((err = traverse(m, *ppos)) == -EAGAIN)
diff --git a/fs/splice.c b/fs/splice.c
index 8ed7c9d..873d831 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1087,7 +1087,13 @@ EXPORT_SYMBOL(do_splice_direct);
 
 static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags)
 {
-	while (pipe->nrbufs == pipe->buffers) {
+	for (;;) {
+		if (unlikely(!pipe->readers)) {
+			send_sig(SIGPIPE, current, 0);
+			return -EPIPE;
+		}
+		if (pipe->nrbufs != pipe->buffers)
+			return 0;
 		if (flags & SPLICE_F_NONBLOCK)
 			return -EAGAIN;
 		if (signal_pending(current))
@@ -1096,7 +1102,6 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags)
 		pipe_wait(pipe);
 		pipe->waiting_writers--;
 	}
-	return 0;
 }
 
 static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
diff --git a/fs/stat.c b/fs/stat.c
index 0b210c3..a268b7f 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -15,7 +15,7 @@
 #include <linux/syscalls.h>
 #include <linux/pagemap.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 void generic_fillattr(struct inode *inode, struct kstat *stat)
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 9ae4abb..c173cc1 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -55,7 +55,7 @@ static inline bool isalarm(struct timerfd_ctx *ctx)
 /*
  * This gets called when the timer event triggers. We set the "expired"
  * flag, but we do not re-arm the timer (in case it's necessary,
- * tintv.tv64 != 0) until the timer is accessed.
+ * tintv != 0) until the timer is accessed.
  */
 static void timerfd_triggered(struct timerfd_ctx *ctx)
 {
@@ -93,7 +93,7 @@ static enum alarmtimer_restart timerfd_alarmproc(struct alarm *alarm,
  */
 void timerfd_clock_was_set(void)
 {
-	ktime_t moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 });
+	ktime_t moffs = ktime_mono_to_real(0);
 	struct timerfd_ctx *ctx;
 	unsigned long flags;
 
@@ -102,8 +102,8 @@ void timerfd_clock_was_set(void)
 		if (!ctx->might_cancel)
 			continue;
 		spin_lock_irqsave(&ctx->wqh.lock, flags);
-		if (ctx->moffs.tv64 != moffs.tv64) {
-			ctx->moffs.tv64 = KTIME_MAX;
+		if (ctx->moffs != moffs) {
+			ctx->moffs = KTIME_MAX;
 			ctx->ticks++;
 			wake_up_locked(&ctx->wqh);
 		}
@@ -124,9 +124,9 @@ static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
 
 static bool timerfd_canceled(struct timerfd_ctx *ctx)
 {
-	if (!ctx->might_cancel || ctx->moffs.tv64 != KTIME_MAX)
+	if (!ctx->might_cancel || ctx->moffs != KTIME_MAX)
 		return false;
-	ctx->moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 });
+	ctx->moffs = ktime_mono_to_real(0);
 	return true;
 }
 
@@ -155,7 +155,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
 	else
 		remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr);
 
-	return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
+	return remaining < 0 ? 0: remaining;
 }
 
 static int timerfd_setup(struct timerfd_ctx *ctx, int flags,
@@ -184,7 +184,7 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags,
 		ctx->t.tmr.function = timerfd_tmrproc;
 	}
 
-	if (texp.tv64 != 0) {
+	if (texp != 0) {
 		if (isalarm(ctx)) {
 			if (flags & TFD_TIMER_ABSTIME)
 				alarm_start(&ctx->t.alarm, texp);
@@ -261,9 +261,9 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
 	if (ctx->ticks) {
 		ticks = ctx->ticks;
 
-		if (ctx->expired && ctx->tintv.tv64) {
+		if (ctx->expired && ctx->tintv) {
 			/*
-			 * If tintv.tv64 != 0, this is a periodic timer that
+			 * If tintv != 0, this is a periodic timer that
 			 * needs to be re-armed. We avoid doing it in the timer
 			 * callback to avoid DoS attacks specifying a very
 			 * short timer period.
@@ -410,7 +410,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 	else
 		hrtimer_init(&ctx->t.tmr, clockid, HRTIMER_MODE_ABS);
 
-	ctx->moffs = ktime_mono_to_real((ktime_t){ .tv64 = 0 });
+	ctx->moffs = ktime_mono_to_real(0);
 
 	ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx,
 			       O_RDWR | (flags & TFD_SHARED_FCNTL_FLAGS));
@@ -469,7 +469,7 @@ static int do_timerfd_settime(int ufd, int flags,
 	 * We do not update "ticks" and "expired" since the timer will be
 	 * re-programmed again in the following timerfd_setup() call.
 	 */
-	if (ctx->expired && ctx->tintv.tv64) {
+	if (ctx->expired && ctx->tintv) {
 		if (isalarm(ctx))
 			alarm_forward_now(&ctx->t.alarm, ctx->tintv);
 		else
@@ -499,7 +499,7 @@ static int do_timerfd_gettime(int ufd, struct itimerspec *t)
 	ctx = f.file->private_data;
 
 	spin_lock_irq(&ctx->wqh.lock);
-	if (ctx->expired && ctx->tintv.tv64) {
+	if (ctx->expired && ctx->tintv) {
 		ctx->expired = 0;
 
 		if (isalarm(ctx)) {
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 45ceb94..7e41aee 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -25,7 +25,7 @@
  *        David S. Miller (davem@caip.rutgers.edu), 1995
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -1191,7 +1191,7 @@ static int ufs_truncate(struct inode *inode, loff_t size)
 	return err;
 }
 
-void ufs_truncate_blocks(struct inode *inode)
+static void ufs_truncate_blocks(struct inode *inode)
 {
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 	      S_ISLNK(inode->i_mode)))
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index f04ab23..131b2b7 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -71,7 +71,7 @@
 
 #include <stdarg.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/errno.h>
 #include <linux/fs.h>
diff --git a/fs/utimes.c b/fs/utimes.c
index 5fdb505..32b15b3 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -8,7 +8,7 @@
 #include <linux/stat.h>
 #include <linux/utime.h>
 #include <linux/syscalls.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 #ifdef __ARCH_WANT_SYS_UTIME
diff --git a/fs/xattr.c b/fs/xattr.c
index 2d13b4e..7e3317c 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -22,7 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/posix_acl_xattr.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static const char *
 strcmp_prefix(const char *a, const char *a_prefix)
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 321f577..7c49938 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -19,7 +19,7 @@
 #include <linux/ioctl.h>
 #include <linux/mount.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_format.h"
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index a415f82..e467218 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -83,7 +83,7 @@ typedef __u32			xfs_nlink_t;
 #include <asm/page.h>
 #include <asm/div64.h>
 #include <asm/param.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index aca2d4b..07593a3 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1161,7 +1161,7 @@ xfs_reflink_remap_range(
 
 	ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
 			&len, is_dedupe);
-	if (ret || len == 0)
+	if (ret <= 0)
 		goto out_unlock;
 
 	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h
index d7d0f49..303315b 100644
--- a/include/acpi/acpi_io.h
+++ b/include/acpi/acpi_io.h
@@ -13,6 +13,8 @@ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
 }
 #endif
 
+extern bool acpi_permanent_mmap;
+
 void __iomem *__ref
 acpi_os_map_iomem(acpi_physical_address phys, acpi_size size);
 void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size);
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 5c7356a..f5e10dd 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -513,10 +513,12 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status
 			     acpi_get_table(acpi_string signature, u32 instance,
 					    struct acpi_table_header
 					    **out_table))
+ACPI_EXTERNAL_RETURN_VOID(void acpi_put_table(struct acpi_table_header *table))
+
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status
-			     acpi_get_table_by_index(u32 table_index,
-						     struct acpi_table_header
-						     **out_table))
+			    acpi_get_table_by_index(u32 table_index,
+						    struct acpi_table_header
+						    **out_table))
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status
 			     acpi_install_table_handler(acpi_table_handler
 							handler, void *context))
@@ -965,15 +967,6 @@ void acpi_terminate_debugger(void);
 /*
  * Divergences
  */
-ACPI_GLOBAL(u8, acpi_gbl_permanent_mmap);
-
-ACPI_EXTERNAL_RETURN_STATUS(acpi_status
-			    acpi_get_table_with_size(acpi_string signature,
-						     u32 instance,
-						     struct acpi_table_header
-						     **out_table,
-						     acpi_size *tbl_size))
-
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status
 			    acpi_get_data_full(acpi_handle object,
 					       acpi_object_handler handler,
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index c19700e..da5708c 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -371,6 +371,7 @@ struct acpi_table_desc {
 	union acpi_name_union signature;
 	acpi_owner_id owner_id;
 	u8 flags;
+	u16 validation_count;
 };
 
 /* Masks for Flags field above */
diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h
index a5509d8..7dbb114 100644
--- a/include/acpi/platform/aclinuxex.h
+++ b/include/acpi/platform/aclinuxex.h
@@ -142,7 +142,6 @@ static inline void acpi_os_terminate_command_signals(void)
 /*
  * OSL interfaces added by Linux
  */
-void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size);
 
 #endif				/* __KERNEL__ */
 
diff --git a/include/asm-generic/termios-base.h b/include/asm-generic/termios-base.h
index 0a769fe..157bbf6 100644
--- a/include/asm-generic/termios-base.h
+++ b/include/asm-generic/termios-base.h
@@ -4,7 +4,7 @@
 #ifndef _ASM_GENERIC_TERMIOS_BASE_H
 #define _ASM_GENERIC_TERMIOS_BASE_H
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifndef __ARCH_TERMIO_GETPUT
 
diff --git a/include/asm-generic/termios.h b/include/asm-generic/termios.h
index 4fa6fe0..8c13a16 100644
--- a/include/asm-generic/termios.h
+++ b/include/asm-generic/termios.h
@@ -2,7 +2,7 @@
 #define _ASM_GENERIC_TERMIOS_H
 
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <uapi/asm-generic/termios.h>
 
 /*	intr=^C		quit=^\		erase=del	kill=^U
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index a9cfd33..192016e 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -61,7 +61,7 @@
 
 #include <asm/mman.h>
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <uapi/drm/drm.h>
 #include <uapi/drm/drm_mode.h>
diff --git a/include/dt-bindings/net/mdio.h b/include/dt-bindings/net/mdio.h
deleted file mode 100644
index 99c6d90..0000000
--- a/include/dt-bindings/net/mdio.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * This header provides generic constants for ethernet MDIO bindings
- */
-
-#ifndef _DT_BINDINGS_NET_MDIO_H
-#define _DT_BINDINGS_NET_MDIO_H
-
-/*
- * EEE capability Advertisement
- */
-
-#define MDIO_EEE_100TX		0x0002	/* 100TX EEE cap */
-#define MDIO_EEE_1000T		0x0004	/* 1000T EEE cap */
-#define MDIO_EEE_10GT		0x0008	/* 10GT EEE cap */
-#define MDIO_EEE_1000KX		0x0010	/* 1000KX EEE cap */
-#define MDIO_EEE_10GKX4		0x0020	/* 10G KX4 EEE cap */
-#define MDIO_EEE_10GKR		0x0040	/* 10G KR EEE cap */
-
-#endif
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index dda39d8..b717ed9 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -25,13 +25,13 @@
 
 struct arch_timer_kvm {
 	/* Virtual offset */
-	cycle_t			cntvoff;
+	u64			cntvoff;
 };
 
 struct arch_timer_cpu {
 	/* Registers: control register, timer value */
 	u32				cntv_ctl;	/* Saved/restored */
-	cycle_t				cntv_cval;	/* Saved/restored */
+	u64				cntv_cval;	/* Saved/restored */
 
 	/*
 	 * Anything that is not used directly from assembly code goes
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 9eb42db..fdd0a34 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -14,14 +14,9 @@ typedef int (kiocb_cancel_fn)(struct kiocb *);
 /* prototypes */
 #ifdef CONFIG_AIO
 extern void exit_aio(struct mm_struct *mm);
-extern long do_io_submit(aio_context_t ctx_id, long nr,
-			 struct iocb __user *__user *iocbpp, bool compat);
 void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
 #else
 static inline void exit_aio(struct mm_struct *mm) { }
-static inline long do_io_submit(aio_context_t ctx_id, long nr,
-				struct iocb __user * __user *iocbpp,
-				bool compat) { return 0; }
 static inline void kiocb_set_cancel_fn(struct kiocb *req,
 				       kiocb_cancel_fn *cancel) { }
 #endif /* CONFIG_AIO */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 286b2a2..8369564 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -288,7 +288,6 @@ enum blk_queue_state {
 struct blk_queue_tag {
 	struct request **tag_index;	/* map of busy tags */
 	unsigned long *tag_map;		/* bit map of free/busy tags */
-	int busy;			/* current depth */
 	int max_depth;			/* what we will send to device */
 	int real_max_depth;		/* what the array can hold */
 	atomic_t refcnt;		/* map can be shared */
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index a951fd1..6a524bf 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -18,6 +18,7 @@ enum cache_type {
 
 /**
  * struct cacheinfo - represent a cache leaf node
+ * @id: This cache's id. It is unique among caches with the same (type, level).
  * @type: type of the cache - data, inst or unified
  * @level: represents the hierarchy in the multi-level cache
  * @coherency_line_size: size of each cache line usually representing
@@ -44,6 +45,7 @@ enum cache_type {
  * keeping, the remaining members form the core properties of the cache
  */
 struct cacheinfo {
+	unsigned int id;
 	enum cache_type type;
 	unsigned int level;
 	unsigned int coherency_line_size;
@@ -61,6 +63,7 @@ struct cacheinfo {
 #define CACHE_WRITE_ALLOCATE	BIT(3)
 #define CACHE_ALLOCATE_POLICY_MASK	\
 	(CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE)
+#define CACHE_ID		BIT(4)
 
 	struct device_node *of_node;
 	bool disable_sysfs;
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 65602d3..e315d04 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -75,8 +75,8 @@ struct module;
  * structure.
  */
 struct clocksource {
-	cycle_t (*read)(struct clocksource *cs);
-	cycle_t mask;
+	u64 (*read)(struct clocksource *cs);
+	u64 mask;
 	u32 mult;
 	u32 shift;
 	u64 max_idle_ns;
@@ -98,8 +98,8 @@ struct clocksource {
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
 	struct list_head wd_list;
-	cycle_t cs_last;
-	cycle_t wd_last;
+	u64 cs_last;
+	u64 wd_last;
 #endif
 	struct module *owner;
 };
@@ -117,7 +117,7 @@ struct clocksource {
 #define CLOCK_SOURCE_RESELECT			0x100
 
 /* simplify initialization of mask field */
-#define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
+#define CLOCKSOURCE_MASK(bits) (u64)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
 
 static inline u32 clocksource_freq2mult(u32 freq, u32 shift_constant, u64 from)
 {
@@ -176,7 +176,7 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant)
  *
  * XXX - This could use some mult_lxl_ll() asm optimization
  */
-static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift)
+static inline s64 clocksource_cyc2ns(u64 cycles, u32 mult, u32 shift)
 {
 	return ((u64) cycles * mult) >> shift;
 }
@@ -236,13 +236,13 @@ static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz
 
 extern int timekeeping_notify(struct clocksource *clock);
 
-extern cycle_t clocksource_mmio_readl_up(struct clocksource *);
-extern cycle_t clocksource_mmio_readl_down(struct clocksource *);
-extern cycle_t clocksource_mmio_readw_up(struct clocksource *);
-extern cycle_t clocksource_mmio_readw_down(struct clocksource *);
+extern u64 clocksource_mmio_readl_up(struct clocksource *);
+extern u64 clocksource_mmio_readl_down(struct clocksource *);
+extern u64 clocksource_mmio_readw_up(struct clocksource *);
+extern u64 clocksource_mmio_readw_down(struct clocksource *);
 
 extern int clocksource_mmio_init(void __iomem *, const char *,
-	unsigned long, int, unsigned, cycle_t (*)(struct clocksource *));
+	unsigned long, int, unsigned, u64 (*)(struct clocksource *));
 
 extern int clocksource_i8253_init(void);
 
diff --git a/include/linux/configfs.h b/include/linux/configfs.h
index 9a30b92..2319b8c 100644
--- a/include/linux/configfs.h
+++ b/include/linux/configfs.h
@@ -35,14 +35,11 @@
 #ifndef _CONFIGFS_H_
 #define _CONFIGFS_H_
 
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/kref.h>
-#include <linux/mutex.h>
-#include <linux/err.h>
-
-#include <linux/atomic.h>
+#include <linux/stat.h>   /* S_IRUGO */
+#include <linux/types.h>  /* ssize_t */
+#include <linux/list.h>   /* struct list_head */
+#include <linux/kref.h>   /* struct kref */
+#include <linux/mutex.h>  /* struct mutex */
 
 #define CONFIGFS_ITEM_NAME_LEN	20
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 09807c2..21f9c74 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -57,9 +57,6 @@ struct notifier_block;
 
 #define CPU_ONLINE		0x0002 /* CPU (unsigned)v is up */
 #define CPU_UP_PREPARE		0x0003 /* CPU (unsigned)v coming up */
-#define CPU_UP_CANCELED		0x0004 /* CPU (unsigned)v NOT coming up */
-#define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
-#define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
@@ -80,80 +77,14 @@ struct notifier_block;
 
 #ifdef CONFIG_SMP
 extern bool cpuhp_tasks_frozen;
-/* Need to know about CPUs going up/down? */
-#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
-#define cpu_notifier(fn, pri) {					\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	register_cpu_notifier(&fn##_nb);			\
-}
-
-#define __cpu_notifier(fn, pri) {				\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	__register_cpu_notifier(&fn##_nb);			\
-}
-
-extern int register_cpu_notifier(struct notifier_block *nb);
-extern int __register_cpu_notifier(struct notifier_block *nb);
-extern void unregister_cpu_notifier(struct notifier_block *nb);
-extern void __unregister_cpu_notifier(struct notifier_block *nb);
-
-#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-#endif
-
 int cpu_up(unsigned int cpu);
 void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 
-#define cpu_notifier_register_begin	cpu_maps_update_begin
-#define cpu_notifier_register_done	cpu_maps_update_done
-
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
 
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
 static inline void cpu_maps_update_begin(void)
 {
 }
@@ -162,14 +93,6 @@ static inline void cpu_maps_update_done(void)
 {
 }
 
-static inline void cpu_notifier_register_begin(void)
-{
-}
-
-static inline void cpu_notifier_register_done(void)
-{
-}
-
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -182,12 +105,6 @@ extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
-#define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
-#define __hotcpu_notifier(fn, pri)	__cpu_notifier(fn, pri)
-#define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
-#define __register_hotcpu_notifier(nb)	__register_cpu_notifier(nb)
-#define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
-#define __unregister_hotcpu_notifier(nb)	__unregister_cpu_notifier(nb)
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
@@ -199,13 +116,6 @@ static inline void cpu_hotplug_done(void) {}
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
-#define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-/* These aren't inline functions due to a GCC bug. */
-#define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define __register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define unregister_hotcpu_notifier(nb)	({ (void)(nb); })
-#define __unregister_hotcpu_notifier(nb)	({ (void)(nb); })
 #endif		/* CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM_SLEEP_SMP
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 2ab7bf5..20bfefb 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,9 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
+	CPUHP_SCSI_BNX2FC_DEAD,
+	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
@@ -56,7 +59,6 @@ enum cpuhp_state {
 	CPUHP_POWERPC_MMU_CTX_PREPARE,
 	CPUHP_XEN_PREPARE,
 	CPUHP_XEN_EVTCHN_PREPARE,
-	CPUHP_NOTIFY_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
 	CPUHP_BLK_MQ_PREPARE,
@@ -71,7 +73,6 @@ enum cpuhp_state {
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_DEAD,
-	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BRINGUP_CPU,
 	CPUHP_AP_IDLE_DEAD,
@@ -79,10 +80,8 @@ enum cpuhp_state {
 	CPUHP_AP_SCHED_STARTING,
 	CPUHP_AP_RCUTREE_DYING,
 	CPUHP_AP_IRQ_GIC_STARTING,
-	CPUHP_AP_IRQ_GICV3_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_PERF_X86_UNCORE_STARTING,
@@ -118,7 +117,6 @@ enum cpuhp_state {
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
-	CPUHP_AP_ARM_CORESIGHT4_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,
@@ -142,7 +140,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-	CPUHP_AP_NOTIFY_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
 	CPUHP_AP_X86_HPET_ONLINE,
diff --git a/include/linux/dax.h b/include/linux/dax.h
index f97bcfe..24ad711 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -41,6 +41,9 @@ ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index);
 void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		pgoff_t index, void *entry, bool wake_all);
 
diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h
index 1f79b20..4334106 100644
--- a/include/linux/dw_apb_timer.h
+++ b/include/linux/dw_apb_timer.h
@@ -50,6 +50,6 @@ dw_apb_clocksource_init(unsigned rating, const char *name, void __iomem *base,
 			unsigned long freq);
 void dw_apb_clocksource_register(struct dw_apb_clocksource *dw_cs);
 void dw_apb_clocksource_start(struct dw_apb_clocksource *dw_cs);
-cycle_t dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs);
+u64 dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs);
 
 #endif /* __DW_APB_TIMER_H__ */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 7023142..a0934e6 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -610,7 +610,6 @@ bool bpf_helper_changes_pkt_data(void *func);
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 void bpf_warn_invalid_xdp_action(u32 act);
-void bpf_warn_invalid_xdp_buffer(void);
 
 #ifdef CONFIG_BPF_JIT
 extern int bpf_jit_enable;
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 6435f46..7c5b694 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -1,14 +1,14 @@
 #ifndef _LINUX_FUTEX_H
 #define _LINUX_FUTEX_H
 
+#include <linux/ktime.h>
 #include <uapi/linux/futex.h>
 
 struct inode;
 struct mm_struct;
 struct task_struct;
-union ktime;
 
-long do_futex(u32 __user *uaddr, int op, u32 val, union ktime *timeout,
+long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 	      u32 __user *uaddr2, u32 val2, u32 val3);
 
 extern int
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 5e00f80..cdab81b 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -228,8 +228,8 @@ static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t t
 
 static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64)
 {
-	timer->node.expires.tv64 = tv64;
-	timer->_softexpires.tv64 = tv64;
+	timer->node.expires = tv64;
+	timer->_softexpires = tv64;
 }
 
 static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
@@ -256,11 +256,11 @@ static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer)
 
 static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
 {
-	return timer->node.expires.tv64;
+	return timer->node.expires;
 }
 static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer)
 {
-	return timer->_softexpires.tv64;
+	return timer->_softexpires;
 }
 
 static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
@@ -297,7 +297,7 @@ extern void hrtimer_peek_ahead_timers(void);
  * this resolution values.
  */
 # define HIGH_RES_NSEC		1
-# define KTIME_HIGH_RES		(ktime_t) { .tv64 = HIGH_RES_NSEC }
+# define KTIME_HIGH_RES		(HIGH_RES_NSEC)
 # define MONOTONIC_RES_NSEC	HIGH_RES_NSEC
 # define KTIME_MONOTONIC_RES	KTIME_HIGH_RES
 
@@ -333,7 +333,7 @@ __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now)
 	 * hrtimer_start_range_ns() to prevent short timeouts.
 	 */
 	if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel)
-		rem.tv64 -= hrtimer_resolution;
+		rem -= hrtimer_resolution;
 	return rem;
 }
 
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 0eb7c2e..7f6952f 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -11,6 +11,7 @@
 #define _LINUX_IMA_H
 
 #include <linux/fs.h>
+#include <linux/kexec.h>
 struct linux_binprm;
 
 #ifdef CONFIG_IMA
@@ -23,6 +24,10 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
 extern void ima_post_path_mknod(struct dentry *dentry);
 
+#ifdef CONFIG_IMA_KEXEC
+extern void ima_add_kexec_buffer(struct kimage *image);
+#endif
+
 #else
 static inline int ima_bprm_check(struct linux_binprm *bprm)
 {
@@ -62,6 +67,13 @@ static inline void ima_post_path_mknod(struct dentry *dentry)
 
 #endif /* CONFIG_IMA */
 
+#ifndef CONFIG_IMA_KEXEC
+struct kimage;
+
+static inline void ima_add_kexec_buffer(struct kimage *image)
+{}
+#endif
+
 #ifdef CONFIG_IMA_APPRAISE
 extern void ima_inode_post_setattr(struct dentry *dentry);
 extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,
diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h
index 81f930b..7b49c71 100644
--- a/include/linux/irqchip/mips-gic.h
+++ b/include/linux/irqchip/mips-gic.h
@@ -259,11 +259,11 @@ extern void gic_init(unsigned long gic_base_addr,
 	unsigned long gic_addrspace_size, unsigned int cpu_vec,
 	unsigned int irqbase);
 extern void gic_clocksource_init(unsigned int);
-extern cycle_t gic_read_count(void);
+extern u64 gic_read_count(void);
 extern unsigned int gic_get_count_width(void);
-extern cycle_t gic_read_compare(void);
-extern void gic_write_compare(cycle_t cnt);
-extern void gic_write_cpu_compare(cycle_t cnt, int cpu);
+extern u64 gic_read_compare(void);
+extern void gic_write_compare(u64 cnt);
+extern void gic_write_cpu_compare(u64 cnt, int cpu);
 extern void gic_start_count(void);
 extern void gic_stop_count(void);
 extern int gic_get_c0_compare_int(void);
diff --git a/include/linux/isdnif.h b/include/linux/isdnif.h
index 0fc6ff2..8d80fdc 100644
--- a/include/linux/isdnif.h
+++ b/include/linux/isdnif.h
@@ -500,6 +500,6 @@ typedef struct {
  *
  */
 extern int register_isdn(isdn_if*);
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #endif /* __ISDNIF_H__ */
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 0fb7ffb..0c8bd45 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -24,21 +24,8 @@
 #include <linux/time.h>
 #include <linux/jiffies.h>
 
-/*
- * ktime_t:
- *
- * A single 64-bit variable is used to store the hrtimers
- * internal representation of time values in scalar nanoseconds. The
- * design plays out best on 64-bit CPUs, where most conversions are
- * NOPs and most arithmetic ktime_t operations are plain arithmetic
- * operations.
- *
- */
-union ktime {
-	s64	tv64;
-};
-
-typedef union ktime ktime_t;		/* Kill this */
+/* Nanosecond scalar representation for kernel time values */
+typedef s64	ktime_t;
 
 /**
  * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value
@@ -50,39 +37,34 @@ typedef union ktime ktime_t;		/* Kill this */
 static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs)
 {
 	if (unlikely(secs >= KTIME_SEC_MAX))
-		return (ktime_t){ .tv64 = KTIME_MAX };
+		return KTIME_MAX;
 
-	return (ktime_t) { .tv64 = secs * NSEC_PER_SEC + (s64)nsecs };
+	return secs * NSEC_PER_SEC + (s64)nsecs;
 }
 
 /* Subtract two ktime_t variables. rem = lhs -rhs: */
-#define ktime_sub(lhs, rhs) \
-		({ (ktime_t){ .tv64 = (lhs).tv64 - (rhs).tv64 }; })
+#define ktime_sub(lhs, rhs)	((lhs) - (rhs))
 
 /* Add two ktime_t variables. res = lhs + rhs: */
-#define ktime_add(lhs, rhs) \
-		({ (ktime_t){ .tv64 = (lhs).tv64 + (rhs).tv64 }; })
+#define ktime_add(lhs, rhs)	((lhs) + (rhs))
 
 /*
  * Same as ktime_add(), but avoids undefined behaviour on overflow; however,
  * this means that you must check the result for overflow yourself.
  */
-#define ktime_add_unsafe(lhs, rhs) \
-		({ (ktime_t){ .tv64 = (u64) (lhs).tv64 + (rhs).tv64 }; })
+#define ktime_add_unsafe(lhs, rhs)	((u64) (lhs) + (rhs))
 
 /*
  * Add a ktime_t variable and a scalar nanosecond value.
  * res = kt + nsval:
  */
-#define ktime_add_ns(kt, nsval) \
-		({ (ktime_t){ .tv64 = (kt).tv64 + (nsval) }; })
+#define ktime_add_ns(kt, nsval)		((kt) + (nsval))
 
 /*
  * Subtract a scalar nanosecod from a ktime_t variable
  * res = kt - nsval:
  */
-#define ktime_sub_ns(kt, nsval) \
-		({ (ktime_t){ .tv64 = (kt).tv64 - (nsval) }; })
+#define ktime_sub_ns(kt, nsval)		((kt) - (nsval))
 
 /* convert a timespec to ktime_t format: */
 static inline ktime_t timespec_to_ktime(struct timespec ts)
@@ -103,31 +85,16 @@ static inline ktime_t timeval_to_ktime(struct timeval tv)
 }
 
 /* Map the ktime_t to timespec conversion to ns_to_timespec function */
-#define ktime_to_timespec(kt)		ns_to_timespec((kt).tv64)
+#define ktime_to_timespec(kt)		ns_to_timespec((kt))
 
 /* Map the ktime_t to timespec conversion to ns_to_timespec function */
-#define ktime_to_timespec64(kt)		ns_to_timespec64((kt).tv64)
+#define ktime_to_timespec64(kt)		ns_to_timespec64((kt))
 
 /* Map the ktime_t to timeval conversion to ns_to_timeval function */
-#define ktime_to_timeval(kt)		ns_to_timeval((kt).tv64)
+#define ktime_to_timeval(kt)		ns_to_timeval((kt))
 
 /* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */
-#define ktime_to_ns(kt)			((kt).tv64)
-
-
-/**
- * ktime_equal - Compares two ktime_t variables to see if they are equal
- * @cmp1:	comparable1
- * @cmp2:	comparable2
- *
- * Compare two ktime_t variables.
- *
- * Return: 1 if equal.
- */
-static inline int ktime_equal(const ktime_t cmp1, const ktime_t cmp2)
-{
-	return cmp1.tv64 == cmp2.tv64;
-}
+#define ktime_to_ns(kt)			(kt)
 
 /**
  * ktime_compare - Compares two ktime_t variables for less, greater or equal
@@ -141,9 +108,9 @@ static inline int ktime_equal(const ktime_t cmp1, const ktime_t cmp2)
  */
 static inline int ktime_compare(const ktime_t cmp1, const ktime_t cmp2)
 {
-	if (cmp1.tv64 < cmp2.tv64)
+	if (cmp1 < cmp2)
 		return -1;
-	if (cmp1.tv64 > cmp2.tv64)
+	if (cmp1 > cmp2)
 		return 1;
 	return 0;
 }
@@ -182,7 +149,7 @@ static inline s64 ktime_divns(const ktime_t kt, s64 div)
 	 */
 	BUG_ON(div < 0);
 	if (__builtin_constant_p(div) && !(div >> 32)) {
-		s64 ns = kt.tv64;
+		s64 ns = kt;
 		u64 tmp = ns < 0 ? -ns : ns;
 
 		do_div(tmp, div);
@@ -199,7 +166,7 @@ static inline s64 ktime_divns(const ktime_t kt, s64 div)
 	 * so catch them on 64bit as well.
 	 */
 	WARN_ON(div < 0);
-	return kt.tv64 / div;
+	return kt / div;
 }
 #endif
 
@@ -256,7 +223,7 @@ extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs);
 static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt,
 						       struct timespec *ts)
 {
-	if (kt.tv64) {
+	if (kt) {
 		*ts = ktime_to_timespec(kt);
 		return true;
 	} else {
@@ -275,7 +242,7 @@ static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt,
 static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt,
 						       struct timespec64 *ts)
 {
-	if (kt.tv64) {
+	if (kt) {
 		*ts = ktime_to_timespec64(kt);
 		return true;
 	} else {
@@ -290,20 +257,16 @@ static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt,
  * this resolution values.
  */
 #define LOW_RES_NSEC		TICK_NSEC
-#define KTIME_LOW_RES		(ktime_t){ .tv64 = LOW_RES_NSEC }
+#define KTIME_LOW_RES		(LOW_RES_NSEC)
 
 static inline ktime_t ns_to_ktime(u64 ns)
 {
-	static const ktime_t ktime_zero = { .tv64 = 0 };
-
-	return ktime_add_ns(ktime_zero, ns);
+	return ns;
 }
 
 static inline ktime_t ms_to_ktime(u64 ms)
 {
-	static const ktime_t ktime_zero = { .tv64 = 0 };
-
-	return ktime_add_ms(ktime_zero, ms);
+	return ms * NSEC_PER_MSEC;
 }
 
 # include <linux/timekeeping.h>
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index c9f3796..93bdb34 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1460,7 +1460,7 @@ int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id,
 int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
 				      u32 max_range_qpn);
 
-cycle_t mlx4_read_clock(struct mlx4_dev *dev);
+u64 mlx4_read_clock(struct mlx4_dev *dev);
 
 struct mlx4_active_ports {
 	DECLARE_BITMAP(ports, MLX4_MAX_PORTS);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4424784..fe6b403 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1758,6 +1758,8 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 	return ptl;
 }
 
+extern void __init pagecache_init(void);
+
 extern void free_area_init(unsigned long * zones_size);
 extern void free_area_init_node(int nid, unsigned long * zones_size,
 		unsigned long zone_start_pfn, unsigned long *zholes_size);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index cb63197..f1da8c8 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -340,10 +340,8 @@ extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
 extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
 extern int nfs_permission(struct inode *, int);
 extern int nfs_open(struct inode *, struct file *);
-extern int nfs_attribute_timeout(struct inode *inode);
 extern int nfs_attribute_cache_expired(struct inode *inode);
 extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
-extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
 extern bool nfs_mapping_need_revalidate_inode(struct inode *inode);
 extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index 50a7dbe..de87cea 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -968,6 +968,9 @@ static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx,
  */
 static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx)
 {
+	if (!ntb->ops->peer_spad_read)
+		return 0;
+
 	return ntb->ops->peer_spad_read(ntb, idx);
 }
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 74e4dda..6b5818d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -79,6 +79,7 @@ enum pageflags {
 	PG_dirty,
 	PG_lru,
 	PG_active,
+	PG_waiters,		/* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
 	PG_slab,
 	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
 	PG_arch_1,
@@ -87,7 +88,6 @@ enum pageflags {
 	PG_private_2,		/* If pagecache, has fs aux data */
 	PG_writeback,		/* Page is under writeback */
 	PG_head,		/* A head page */
-	PG_swapcache,		/* Swap page: swp_entry_t in private */
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
@@ -110,6 +110,9 @@ enum pageflags {
 	/* Filesystems */
 	PG_checked = PG_owner_priv_1,
 
+	/* SwapBacked */
+	PG_swapcache = PG_owner_priv_1,	/* Swap page: swp_entry_t in private */
+
 	/* Two page bits are conscripted by FS-Cache to maintain local caching
 	 * state.  These bits are set on pages belonging to the netfs's inodes
 	 * when those inodes are being locally cached.
@@ -167,6 +170,9 @@ static __always_inline int PageCompound(struct page *page)
  *     for compound page all operations related to the page flag applied to
  *     head page.
  *
+ * PF_ONLY_HEAD:
+ *     for compound page, callers only ever operate on the head page.
+ *
  * PF_NO_TAIL:
  *     modifications of the page flag must be done on small or head pages,
  *     checks can be done on tail pages too.
@@ -176,6 +182,9 @@ static __always_inline int PageCompound(struct page *page)
  */
 #define PF_ANY(page, enforce)	page
 #define PF_HEAD(page, enforce)	compound_head(page)
+#define PF_ONLY_HEAD(page, enforce) ({					\
+		VM_BUG_ON_PGFLAGS(PageTail(page), page);		\
+		page;})
 #define PF_NO_TAIL(page, enforce) ({					\
 		VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page);	\
 		compound_head(page);})
@@ -253,6 +262,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
 	TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
 
 __PAGEFLAG(Locked, locked, PF_NO_TAIL)
+PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
 PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND)
 PAGEFLAG(Referenced, referenced, PF_HEAD)
 	TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
@@ -314,7 +324,13 @@ PAGEFLAG_FALSE(HighMem)
 #endif
 
 #ifdef CONFIG_SWAP
-PAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
+static __always_inline int PageSwapCache(struct page *page)
+{
+	return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags);
+
+}
+SETPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
+CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
@@ -701,12 +717,12 @@ static inline void ClearPageSlabPfmemalloc(struct page *page)
  * Flags checked when a page is freed.  Pages being freed should not have
  * these flags set.  It they are, there is a problem.
  */
-#define PAGE_FLAGS_CHECK_AT_FREE \
-	(1UL << PG_lru	 | 1UL << PG_locked    | \
-	 1UL << PG_private | 1UL << PG_private_2 | \
-	 1UL << PG_writeback | 1UL << PG_reserved | \
-	 1UL << PG_slab	 | 1UL << PG_swapcache | 1UL << PG_active | \
-	 1UL << PG_unevictable | __PG_MLOCKED)
+#define PAGE_FLAGS_CHECK_AT_FREE				\
+	(1UL << PG_lru		| 1UL << PG_locked	|	\
+	 1UL << PG_private	| 1UL << PG_private_2	|	\
+	 1UL << PG_writeback	| 1UL << PG_reserved	|	\
+	 1UL << PG_slab		| 1UL << PG_active 	|	\
+	 1UL << PG_unevictable	| __PG_MLOCKED)
 
 /*
  * Flags checked when a page is prepped for return by the page allocator.
@@ -735,6 +751,7 @@ static inline int page_has_private(struct page *page)
 
 #undef PF_ANY
 #undef PF_HEAD
+#undef PF_ONLY_HEAD
 #undef PF_NO_TAIL
 #undef PF_NO_COMPOUND
 #endif /* !__GENERATING_BOUNDS_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7dbe914..324c8dba 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -9,7 +9,7 @@
 #include <linux/list.h>
 #include <linux/highmem.h>
 #include <linux/compiler.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/gfp.h>
 #include <linux/bitops.h>
 #include <linux/hardirq.h> /* for in_interrupt() */
@@ -486,22 +486,14 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
  * and for filesystems which need to wait on PG_private.
  */
 extern void wait_on_page_bit(struct page *page, int bit_nr);
-
 extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
-extern int wait_on_page_bit_killable_timeout(struct page *page,
-					     int bit_nr, unsigned long timeout);
+extern void wake_up_page_bit(struct page *page, int bit_nr);
 
-static inline int wait_on_page_locked_killable(struct page *page)
-{
-	if (!PageLocked(page))
-		return 0;
-	return wait_on_page_bit_killable(compound_head(page), PG_locked);
-}
-
-extern wait_queue_head_t *page_waitqueue(struct page *page);
 static inline void wake_up_page(struct page *page, int bit)
 {
-	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
+	if (!PageWaiters(page))
+		return;
+	wake_up_page_bit(page, bit);
 }
 
 /* 
@@ -517,6 +509,13 @@ static inline void wait_on_page_locked(struct page *page)
 		wait_on_page_bit(compound_head(page), PG_locked);
 }
 
+static inline int wait_on_page_locked_killable(struct page *page)
+{
+	if (!PageLocked(page))
+		return 0;
+	return wait_on_page_bit_killable(compound_head(page), PG_locked);
+}
+
 /* 
  * Wait for a page to complete writeback
  */
diff --git a/include/linux/poll.h b/include/linux/poll.h
index 37b057b..a46d675 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -8,7 +8,7 @@
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/sysctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <uapi/linux/poll.h>
 
 extern struct ctl_table epoll_table[]; /* for sysctl */
diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h
index 57c9e06..56375ed 100644
--- a/include/linux/ratelimit.h
+++ b/include/linux/ratelimit.h
@@ -77,8 +77,11 @@ extern int ___ratelimit(struct ratelimit_state *rs, const char *func);
 
 #ifdef CONFIG_PRINTK
 
-#define WARN_ON_RATELIMIT(condition, state)			\
-		WARN_ON((condition) && __ratelimit(state))
+#define WARN_ON_RATELIMIT(condition, state)	({		\
+	bool __rtn_cond = !!(condition);			\
+	WARN_ON(__rtn_cond && __ratelimit(state));		\
+	__rtn_cond;						\
+})
 
 #define WARN_RATELIMIT(condition, format, ...)			\
 ({								\
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a440cf1..4d19052 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1821,6 +1821,9 @@ struct task_struct {
 	/* cg_list protected by css_set_lock and tsk->alloc_lock */
 	struct list_head cg_list;
 #endif
+#ifdef CONFIG_INTEL_RDT_A
+	int closid;
+#endif
 #ifdef CONFIG_FUTEX
 	struct robust_list_head __user *robust_list;
 #ifdef CONFIG_COMPAT
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ac7fa34..b53c0cf 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3227,7 +3227,7 @@ static inline ktime_t net_timedelta(ktime_t t)
 
 static inline ktime_t net_invalid_timestamp(void)
 {
-	return ktime_set(0, 0);
+	return 0;
 }
 
 struct sk_buff *skb_clone_sk(struct sk_buff *skb);
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 62be0786..a04fea1 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -127,9 +127,7 @@ static inline void tick_nohz_idle_exit(void) { }
 
 static inline ktime_t tick_nohz_get_sleep_length(void)
 {
-	ktime_t len = { .tv64 = NSEC_PER_SEC/HZ };
-
-	return len;
+	return NSEC_PER_SEC / HZ;
 }
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h
index 4382035..2496ad4 100644
--- a/include/linux/timecounter.h
+++ b/include/linux/timecounter.h
@@ -20,7 +20,7 @@
 #include <linux/types.h>
 
 /* simplify initialization of mask field */
-#define CYCLECOUNTER_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
+#define CYCLECOUNTER_MASK(bits) (u64)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
 
 /**
  * struct cyclecounter - hardware abstraction for a free running counter
@@ -37,8 +37,8 @@
  * @shift:		cycle to nanosecond divisor (power of two)
  */
 struct cyclecounter {
-	cycle_t (*read)(const struct cyclecounter *cc);
-	cycle_t mask;
+	u64 (*read)(const struct cyclecounter *cc);
+	u64 mask;
 	u32 mult;
 	u32 shift;
 };
@@ -63,7 +63,7 @@ struct cyclecounter {
  */
 struct timecounter {
 	const struct cyclecounter *cc;
-	cycle_t cycle_last;
+	u64 cycle_last;
 	u64 nsec;
 	u64 mask;
 	u64 frac;
@@ -77,7 +77,7 @@ struct timecounter {
  * @frac:	pointer to storage for the fractional nanoseconds.
  */
 static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
-				      cycle_t cycles, u64 mask, u64 *frac)
+				      u64 cycles, u64 mask, u64 *frac)
 {
 	u64 ns = (u64) cycles;
 
@@ -134,6 +134,6 @@ extern u64 timecounter_read(struct timecounter *tc);
  * in the past.
  */
 extern u64 timecounter_cyc2time(struct timecounter *tc,
-				cycle_t cycle_tstamp);
+				u64 cycle_tstamp);
 
 #endif
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index e880054..110f453 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -29,9 +29,9 @@
  */
 struct tk_read_base {
 	struct clocksource	*clock;
-	cycle_t			(*read)(struct clocksource *cs);
-	cycle_t			mask;
-	cycle_t			cycle_last;
+	u64			(*read)(struct clocksource *cs);
+	u64			mask;
+	u64			cycle_last;
 	u32			mult;
 	u32			shift;
 	u64			xtime_nsec;
@@ -97,7 +97,7 @@ struct timekeeper {
 	struct timespec64	raw_time;
 
 	/* The following members are for timekeeping internal use */
-	cycle_t			cycle_interval;
+	u64			cycle_interval;
 	u64			xtime_interval;
 	s64			xtime_remainder;
 	u32			raw_interval;
@@ -136,7 +136,7 @@ extern void update_vsyscall_tz(void);
 
 extern void update_vsyscall_old(struct timespec *ts, struct timespec *wtm,
 				struct clocksource *c, u32 mult,
-				cycle_t cycle_last);
+				u64 cycle_last);
 extern void update_vsyscall_tz(void);
 
 #else
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 361f8bf..d2e804e 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -293,7 +293,7 @@ extern void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw,
  * @cs_was_changed_seq:	The sequence number of clocksource change events
  */
 struct system_time_snapshot {
-	cycle_t		cycles;
+	u64		cycles;
 	ktime_t		real;
 	ktime_t		raw;
 	unsigned int	clock_was_set_seq;
@@ -321,7 +321,7 @@ struct system_device_crosststamp {
  *	timekeeping code to verify comparibility of two cycle values
  */
 struct system_counterval_t {
-	cycle_t			cycles;
+	u64			cycles;
 	struct clocksource	*cs;
 };
 
diff --git a/include/linux/types.h b/include/linux/types.h
index d501ad3..1e7bd24 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -228,8 +228,5 @@ struct callback_head {
 typedef void (*rcu_callback_t)(struct rcu_head *head);
 typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func);
 
-/* clocksource cycle base type */
-typedef u64 cycle_t;
-
 #endif /*  __ASSEMBLY__ */
 #endif /* _LINUX_TYPES_H */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2408e8d5..1421132 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -510,7 +510,7 @@ do {									\
 	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC,		\
 			      HRTIMER_MODE_REL);			\
 	hrtimer_init_sleeper(&__t, current);				\
-	if ((timeout).tv64 != KTIME_MAX)				\
+	if ((timeout) != KTIME_MAX)				\
 		hrtimer_start_range_ns(&__t.timer, timeout,		\
 				       current->timer_slack_ns,		\
 				       HRTIMER_MODE_REL);		\
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index c78f9f0..5527d91 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -375,7 +375,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
 unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
 
 void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time);
-void page_writeback_init(void);
 void balance_dirty_pages_ratelimited(struct address_space *mapping);
 bool wb_over_bg_thresh(struct bdi_writeback *wb);
 
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 5c30891..35d0fab 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -22,7 +22,7 @@
 #include <linux/errno.h>
 #include <asm/types.h>
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/checksum.h>
 
 #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index f0cf5a1..0378e88 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -110,6 +110,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_orphan_retries;
 	int sysctl_tcp_fin_timeout;
 	unsigned int sysctl_tcp_notsent_lowat;
+	int sysctl_tcp_tw_reuse;
 
 	int sysctl_igmp_max_memberships;
 	int sysctl_igmp_max_msf;
diff --git a/include/net/red.h b/include/net/red.h
index 76e0b5f..208e718 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -207,7 +207,7 @@ static inline void red_set_parms(struct red_parms *p,
 
 static inline int red_is_idling(const struct red_vars *v)
 {
-	return v->qidlestart.tv64 != 0;
+	return v->qidlestart != 0;
 }
 
 static inline void red_start_of_idle_period(struct red_vars *v)
@@ -217,7 +217,7 @@ static inline void red_start_of_idle_period(struct red_vars *v)
 
 static inline void red_end_of_idle_period(struct red_vars *v)
 {
-	v->qidlestart.tv64 = 0;
+	v->qidlestart = 0;
 }
 
 static inline void red_restart(struct red_vars *v)
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index f0dcaeb..d8833a8 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -69,7 +69,7 @@
 #include <net/ip6_route.h>
 #endif
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/page.h>
 #include <net/sock.h>
 #include <net/snmp.h>
diff --git a/include/net/sock.h b/include/net/sock.h
index 282d065..f0e867f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2193,8 +2193,8 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 	 */
 	if (sock_flag(sk, SOCK_RCVTSTAMP) ||
 	    (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
-	    (kt.tv64 && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
-	    (hwtstamps->hwtstamp.tv64 &&
+	    (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
+	    (hwtstamps->hwtstamp &&
 	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
 	else
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 207147b..6061963 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -252,7 +252,6 @@ extern int sysctl_tcp_wmem[3];
 extern int sysctl_tcp_rmem[3];
 extern int sysctl_tcp_app_win;
 extern int sysctl_tcp_adv_win_scale;
-extern int sysctl_tcp_tw_reuse;
 extern int sysctl_tcp_frto;
 extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_nometrics_save;
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index 931a47b..1beab55 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -205,10 +205,12 @@ static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
 
 	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
 	if (dev) {
-		ip4 = (struct in_device *)dev->ip_ptr;
-		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address)
+		ip4 = in_dev_get(dev);
+		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address) {
 			ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address,
 					       (struct in6_addr *)gid);
+			in_dev_put(ip4);
+		}
 		dev_put(dev);
 	}
 }
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 8029d2a..958a24d 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -59,7 +59,7 @@
 #include <linux/if_link.h>
 #include <linux/atomic.h>
 #include <linux/mmu_notifier.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 4ac24f5..275581d 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -1,12 +1,14 @@
 #ifndef ISCSI_TARGET_CORE_H
 #define ISCSI_TARGET_CORE_H
 
-#include <linux/in.h>
-#include <linux/configfs.h>
-#include <net/sock.h>
-#include <net/tcp.h>
-#include <scsi/iscsi_proto.h>
-#include <target/target_core_base.h>
+#include <linux/dma-direction.h>     /* enum dma_data_direction */
+#include <linux/list.h>              /* struct list_head */
+#include <linux/socket.h>            /* struct sockaddr_storage */
+#include <linux/types.h>             /* u8 */
+#include <scsi/iscsi_proto.h>        /* itt_t */
+#include <target/target_core_base.h> /* struct se_cmd */
+
+struct sock;
 
 #define ISCSIT_VERSION			"v4.1.0"
 #define ISCSI_MAX_DATASN_MISSING_COUNT	16
diff --git a/include/target/iscsi/iscsi_target_stat.h b/include/target/iscsi/iscsi_target_stat.h
index e615bb4..c27dd47 100644
--- a/include/target/iscsi/iscsi_target_stat.h
+++ b/include/target/iscsi/iscsi_target_stat.h
@@ -1,6 +1,10 @@
 #ifndef ISCSI_TARGET_STAT_H
 #define ISCSI_TARGET_STAT_H
 
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/socket.h>
+
 /*
  * For struct iscsi_tiqn->tiqn_wwn default groups
  */
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index 40ac7cd..1277e9b 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -1,6 +1,6 @@
-#include <linux/module.h>
-#include <linux/list.h>
-#include "iscsi_target_core.h"
+#include "iscsi_target_core.h" /* struct iscsi_cmd */
+
+struct sockaddr_storage;
 
 struct iscsit_transport {
 #define ISCSIT_TRANSPORT_NAME	16
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index f6f3bc5..b54b98d 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -1,8 +1,14 @@
 #ifndef TARGET_CORE_BACKEND_H
 #define TARGET_CORE_BACKEND_H
 
+#include <linux/types.h>
+#include <target/target_core_base.h>
+
 #define TRANSPORT_FLAG_PASSTHROUGH		1
 
+struct request_queue;
+struct scatterlist;
+
 struct target_backend_ops {
 	char name[16];
 	char inquiry_prod[16];
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 0055828..29e6858 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -1,14 +1,10 @@
 #ifndef TARGET_CORE_BASE_H
 #define TARGET_CORE_BASE_H
 
-#include <linux/in.h>
-#include <linux/configfs.h>
-#include <linux/dma-mapping.h>
-#include <linux/blkdev.h>
-#include <linux/percpu_ida.h>
-#include <linux/t10-pi.h>
-#include <net/sock.h>
-#include <net/tcp.h>
+#include <linux/configfs.h>      /* struct config_group */
+#include <linux/dma-direction.h> /* enum dma_data_direction */
+#include <linux/percpu_ida.h>    /* struct percpu_ida */
+#include <linux/semaphore.h>     /* struct semaphore */
 
 #define TARGET_CORE_VERSION		"v5.0"
 
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 5cd6faa..358041b 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -1,6 +1,10 @@
 #ifndef TARGET_CORE_FABRIC_H
 #define TARGET_CORE_FABRIC_H
 
+#include <linux/configfs.h>
+#include <linux/types.h>
+#include <target/target_core_base.h>
+
 struct target_core_fabric_ops {
 	struct module *module;
 	const char *name;
diff --git a/include/trace/events/alarmtimer.h b/include/trace/events/alarmtimer.h
index a1c108c..ae4f358 100644
--- a/include/trace/events/alarmtimer.h
+++ b/include/trace/events/alarmtimer.h
@@ -31,7 +31,7 @@ TRACE_EVENT(alarmtimer_suspend,
 	),
 
 	TP_fast_assign(
-		__entry->expires = expires.tv64;
+		__entry->expires = expires;
 		__entry->alarm_type = flag;
 	),
 
@@ -57,8 +57,8 @@ DECLARE_EVENT_CLASS(alarm_class,
 	TP_fast_assign(
 		__entry->alarm = alarm;
 		__entry->alarm_type = alarm->type;
-		__entry->expires = alarm->node.expires.tv64;
-		__entry->now = now.tv64;
+		__entry->expires = alarm->node.expires;
+		__entry->now = now;
 	),
 
 	TP_printk("alarmtimer:%p type:%s expires:%llu now:%llu",
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 5a81ab4..9e687ca 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -81,6 +81,7 @@
 
 #define __def_pageflag_names						\
 	{1UL << PG_locked,		"locked"	},		\
+	{1UL << PG_waiters,		"waiters"	},		\
 	{1UL << PG_error,		"error"		},		\
 	{1UL << PG_referenced,		"referenced"	},		\
 	{1UL << PG_uptodate,		"uptodate"	},		\
@@ -95,7 +96,6 @@
 	{1UL << PG_private_2,		"private_2"	},		\
 	{1UL << PG_writeback,		"writeback"	},		\
 	{1UL << PG_head,		"head"		},		\
-	{1UL << PG_swapcache,		"swapcache"	},		\
 	{1UL << PG_mappedtodisk,	"mappedtodisk"	},		\
 	{1UL << PG_reclaim,		"reclaim"	},		\
 	{1UL << PG_swapbacked,		"swapbacked"	},		\
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 28c5da6..1448637 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -177,16 +177,14 @@ TRACE_EVENT(hrtimer_start,
 	TP_fast_assign(
 		__entry->hrtimer	= hrtimer;
 		__entry->function	= hrtimer->function;
-		__entry->expires	= hrtimer_get_expires(hrtimer).tv64;
-		__entry->softexpires	= hrtimer_get_softexpires(hrtimer).tv64;
+		__entry->expires	= hrtimer_get_expires(hrtimer);
+		__entry->softexpires	= hrtimer_get_softexpires(hrtimer);
 	),
 
 	TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu",
 		  __entry->hrtimer, __entry->function,
-		  (unsigned long long)ktime_to_ns((ktime_t) {
-				  .tv64 = __entry->expires }),
-		  (unsigned long long)ktime_to_ns((ktime_t) {
-				  .tv64 = __entry->softexpires }))
+		  (unsigned long long) __entry->expires,
+		  (unsigned long long) __entry->softexpires)
 );
 
 /**
@@ -211,13 +209,13 @@ TRACE_EVENT(hrtimer_expire_entry,
 
 	TP_fast_assign(
 		__entry->hrtimer	= hrtimer;
-		__entry->now		= now->tv64;
+		__entry->now		= *now;
 		__entry->function	= hrtimer->function;
 	),
 
 	TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function,
-		  (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now }))
- );
+		  (unsigned long long) __entry->now)
+);
 
 DECLARE_EVENT_CLASS(hrtimer_class,
 
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 9bd5594..e230af2 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -57,6 +57,7 @@
 #define CGROUP_SUPER_MAGIC	0x27e0eb
 #define CGROUP2_SUPER_MAGIC	0x63677270
 
+#define RDTGROUP_SUPER_MAGIC	0x7655821
 
 #define STACK_END_MAGIC		0x57AC6E9D
 
diff --git a/init/init_task.c b/init/init_task.c
index 11f83be1..53d4ce9 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -9,7 +9,7 @@
 #include <linux/mm.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
diff --git a/init/main.c b/init/main.c
index c81c9fa..b0c9d6f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -647,9 +647,8 @@ asmlinkage __visible void __init start_kernel(void)
 	security_init();
 	dbg_late_init();
 	vfs_caches_init();
+	pagecache_init();
 	signals_init();
-	/* rootfs populating might need page-writeback */
-	page_writeback_init();
 	proc_root_init();
 	nsfs_init();
 	cpuset_init();
diff --git a/kernel/capability.c b/kernel/capability.c
index 4984e1f..a98e814 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -17,7 +17,7 @@
 #include <linux/syscalls.h>
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Leveraged for setting/resetting capabilities
diff --git a/kernel/compat.c b/kernel/compat.c
index b3a047f..19aec5d 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -28,7 +28,7 @@
 #include <linux/ptrace.h>
 #include <linux/gfp.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp)
 {
diff --git a/kernel/configs.c b/kernel/configs.c
index c18b1f1..2df132b 100644
--- a/kernel/configs.c
+++ b/kernel/configs.c
@@ -28,7 +28,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /**************************************************/
 /* the actual current config file                 */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5339aca..f75c4d0 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -183,23 +183,16 @@ EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
 /*
  * The following two APIs (cpu_maps_update_begin/done) must be used when
  * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
- * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
- * hotplug callback (un)registration performed using __register_cpu_notifier()
- * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_done);
-
-static RAW_NOTIFIER_HEAD(cpu_chain);
 
 /* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
@@ -349,66 +342,7 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-/* Need to know about CPUs going up/down? */
-int register_cpu_notifier(struct notifier_block *nb)
-{
-	int ret;
-	cpu_maps_update_begin();
-	ret = raw_notifier_chain_register(&cpu_chain, nb);
-	cpu_maps_update_done();
-	return ret;
-}
-
-int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return raw_notifier_chain_register(&cpu_chain, nb);
-}
-
-static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
-			int *nr_calls)
-{
-	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
-	void *hcpu = (void *)(long)cpu;
-
-	int ret;
-
-	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
-					nr_calls);
-
-	return notifier_to_errno(ret);
-}
-
-static int cpu_notify(unsigned long val, unsigned int cpu)
-{
-	return __cpu_notify(val, cpu, -1, NULL);
-}
-
-static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
-{
-	BUG_ON(cpu_notify(val, cpu));
-}
-
 /* Notifier wrappers for transitioning to state machine */
-static int notify_prepare(unsigned int cpu)
-{
-	int nr_calls = 0;
-	int ret;
-
-	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
-	if (ret) {
-		nr_calls--;
-		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
-				__func__, cpu);
-		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
-	}
-	return ret;
-}
-
-static int notify_online(unsigned int cpu)
-{
-	cpu_notify(CPU_ONLINE, cpu);
-	return 0;
-}
 
 static int bringup_wait_for_ap(unsigned int cpu)
 {
@@ -433,10 +367,8 @@ static int bringup_cpu(unsigned int cpu)
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
 	irq_unlock_sparse();
-	if (ret) {
-		cpu_notify(CPU_UP_CANCELED, cpu);
+	if (ret)
 		return ret;
-	}
 	ret = bringup_wait_for_ap(cpu);
 	BUG_ON(!cpu_online(cpu));
 	return ret;
@@ -565,11 +497,6 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
 
 		undo_cpu_down(cpu, st);
-		/*
-		 * This is a momentary workaround to keep the notifier users
-		 * happy. Will go away once we got rid of the notifiers.
-		 */
-		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
 		st->rollback = false;
 	} else {
 		/* Cannot happen .... */
@@ -659,22 +586,6 @@ void __init cpuhp_threads_init(void)
 	kthread_unpark(this_cpu_read(cpuhp_state.thread));
 }
 
-EXPORT_SYMBOL(register_cpu_notifier);
-EXPORT_SYMBOL(__register_cpu_notifier);
-void unregister_cpu_notifier(struct notifier_block *nb)
-{
-	cpu_maps_update_begin();
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-	cpu_maps_update_done();
-}
-EXPORT_SYMBOL(unregister_cpu_notifier);
-
-void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-}
-EXPORT_SYMBOL(__unregister_cpu_notifier);
-
 #ifdef CONFIG_HOTPLUG_CPU
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
@@ -741,20 +652,6 @@ static inline void check_for_tasks(int dead_cpu)
 	read_unlock(&tasklist_lock);
 }
 
-static int notify_down_prepare(unsigned int cpu)
-{
-	int err, nr_calls = 0;
-
-	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
-	if (err) {
-		nr_calls--;
-		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
-		pr_warn("%s: attempt to take down CPU %u failed\n",
-				__func__, cpu);
-	}
-	return err;
-}
-
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
@@ -833,13 +730,6 @@ static int takedown_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int notify_dead(unsigned int cpu)
-{
-	cpu_notify_nofail(CPU_DEAD, cpu);
-	check_for_tasks(cpu);
-	return 0;
-}
-
 static void cpuhp_complete_idle_dead(void *arg)
 {
 	struct cpuhp_cpu_state *st = arg;
@@ -863,9 +753,7 @@ void cpuhp_report_idle_dead(void)
 }
 
 #else
-#define notify_down_prepare	NULL
 #define takedown_cpu		NULL
-#define notify_dead		NULL
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -924,9 +812,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
 	cpu_hotplug_done();
-	/* This post dead nonsense must die */
-	if (!ret && hasdied)
-		cpu_notify_nofail(CPU_POST_DEAD, cpu);
 	return ret;
 }
 
@@ -1292,17 +1177,6 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 		.teardown.single	= rcutree_dead_cpu,
 	},
 	/*
-	 * Preparatory and dead notifiers. Will be replaced once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_NOTIFY_PREPARE] = {
-		.name			= "notify:prepare",
-		.startup.single		= notify_prepare,
-		.teardown.single	= notify_dead,
-		.skip_onerr		= true,
-		.cant_stop		= true,
-	},
-	/*
 	 * On the tear-down path, timers_dead_cpu() must be invoked
 	 * before blk_mq_queue_reinit_notify() from notify_dead(),
 	 * otherwise a RCU stall occurs.
@@ -1391,17 +1265,6 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.startup.single		= rcutree_online_cpu,
 		.teardown.single	= rcutree_offline_cpu,
 	},
-
-	/*
-	 * Online/down_prepare notifiers. Will be removed once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_AP_NOTIFY_ONLINE] = {
-		.name			= "notify:online",
-		.startup.single		= notify_online,
-		.teardown.single	= notify_down_prepare,
-		.skip_onerr		= true,
-	},
 #endif
 	/*
 	 * The dynamically registered state space is here
@@ -1432,23 +1295,53 @@ static int cpuhp_cb_check(enum cpuhp_state state)
 	return 0;
 }
 
-static void cpuhp_store_callbacks(enum cpuhp_state state,
-				  const char *name,
-				  int (*startup)(unsigned int cpu),
-				  int (*teardown)(unsigned int cpu),
-				  bool multi_instance)
+/*
+ * Returns a free for dynamic slot assignment of the Online state. The states
+ * are protected by the cpuhp_slot_states mutex and an empty slot is identified
+ * by having no name assigned.
+ */
+static int cpuhp_reserve_state(enum cpuhp_state state)
+{
+	enum cpuhp_state i;
+
+	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
+		if (!cpuhp_ap_states[i].name)
+			return i;
+	}
+	WARN(1, "No more dynamic states available for CPU hotplug\n");
+	return -ENOSPC;
+}
+
+static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
+				 int (*startup)(unsigned int cpu),
+				 int (*teardown)(unsigned int cpu),
+				 bool multi_instance)
 {
 	/* (Un)Install the callbacks for further cpu hotplug operations */
 	struct cpuhp_step *sp;
+	int ret = 0;
 
 	mutex_lock(&cpuhp_state_mutex);
+
+	if (state == CPUHP_AP_ONLINE_DYN) {
+		ret = cpuhp_reserve_state(state);
+		if (ret < 0)
+			goto out;
+		state = ret;
+	}
 	sp = cpuhp_get_step(state);
+	if (name && sp->name) {
+		ret = -EBUSY;
+		goto out;
+	}
 	sp->startup.single = startup;
 	sp->teardown.single = teardown;
 	sp->name = name;
 	sp->multi_instance = multi_instance;
 	INIT_HLIST_HEAD(&sp->list);
+out:
 	mutex_unlock(&cpuhp_state_mutex);
+	return ret;
 }
 
 static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
@@ -1509,29 +1402,6 @@ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
 	}
 }
 
-/*
- * Returns a free for dynamic slot assignment of the Online state. The states
- * are protected by the cpuhp_slot_states mutex and an empty slot is identified
- * by having no name assigned.
- */
-static int cpuhp_reserve_state(enum cpuhp_state state)
-{
-	enum cpuhp_state i;
-
-	mutex_lock(&cpuhp_state_mutex);
-	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
-		if (cpuhp_ap_states[i].name)
-			continue;
-
-		cpuhp_ap_states[i].name = "Reserved";
-		mutex_unlock(&cpuhp_state_mutex);
-		return i;
-	}
-	mutex_unlock(&cpuhp_state_mutex);
-	WARN(1, "No more dynamic states available for CPU hotplug\n");
-	return -ENOSPC;
-}
-
 int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 			       bool invoke)
 {
@@ -1580,11 +1450,13 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
 
 /**
  * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
- * @state:	The state to setup
- * @invoke:	If true, the startup function is invoked for cpus where
- *		cpu state >= @state
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @state:		The state to setup
+ * @invoke:		If true, the startup function is invoked for cpus where
+ *			cpu state >= @state
+ * @startup:		startup callback function
+ * @teardown:		teardown callback function
+ * @multi_instance:	State is set up for multiple instances which get
+ *			added afterwards.
  *
  * Returns:
  *   On success:
@@ -1599,25 +1471,23 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 			bool multi_instance)
 {
 	int cpu, ret = 0;
-	int dyn_state = 0;
+	bool dynstate;
 
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
 
 	get_online_cpus();
 
-	/* currently assignments for the ONLINE state are possible */
-	if (state == CPUHP_AP_ONLINE_DYN) {
-		dyn_state = 1;
-		ret = cpuhp_reserve_state(state);
-		if (ret < 0)
-			goto out;
+	ret = cpuhp_store_callbacks(state, name, startup, teardown,
+				    multi_instance);
+
+	dynstate = state == CPUHP_AP_ONLINE_DYN;
+	if (ret > 0 && dynstate) {
 		state = ret;
+		ret = 0;
 	}
 
-	cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
-
-	if (!invoke || !startup)
+	if (ret || !invoke || !startup)
 		goto out;
 
 	/*
@@ -1641,7 +1511,11 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 	}
 out:
 	put_online_cpus();
-	if (!ret && dyn_state)
+	/*
+	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
+	 * dynamically allocated state in case of success.
+	 */
+	if (!ret && dynstate)
 		return state;
 	return ret;
 }
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 29f815d..b308888 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -55,7 +55,7 @@
 #include <linux/backing-dev.h>
 #include <linux/sort.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/mutex.h>
 #include <linux/cgroup.h>
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 215871b..d416f3b 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1194,7 +1194,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
 	/* Reserve the 1st slot for get_trampoline_vaddr() */
 	set_bit(0, area->bitmap);
 	atomic_set(&area->slot_count, 1);
-	copy_to_page(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE);
+	arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE);
 
 	if (!xol_add_vma(mm, area))
 		return area;
diff --git a/kernel/exit.c b/kernel/exit.c
index aacff8e..8f14b86 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -56,7 +56,7 @@
 #include <linux/kcov.h>
 #include <linux/random.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
diff --git a/kernel/extable.c b/kernel/extable.c
index e820cce..e3beec4 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -22,7 +22,7 @@
 #include <linux/init.h>
 
 #include <asm/sections.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * mutex protecting text section modification (dynamic code patching).
diff --git a/kernel/fork.c b/kernel/fork.c
index 869b8cc..11c5c8a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -79,7 +79,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
diff --git a/kernel/futex.c b/kernel/futex.c
index 9246d9f..0842c8ca 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2459,7 +2459,7 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
-	restart->futex.time = abs_time->tv64;
+	restart->futex.time = *abs_time;
 	restart->futex.bitset = bitset;
 	restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
@@ -2480,7 +2480,7 @@ static long futex_wait_restart(struct restart_block *restart)
 	ktime_t t, *tp = NULL;
 
 	if (restart->futex.flags & FLAGS_HAS_TIMEOUT) {
-		t.tv64 = restart->futex.time;
+		t = restart->futex.time;
 		tp = &t;
 	}
 	restart->fn = do_no_restart_syscall;
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 4ae3232..3f40996 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -13,7 +13,7 @@
 #include <linux/ptrace.h>
 #include <linux/syscalls.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 /*
diff --git a/kernel/groups.c b/kernel/groups.c
index 2fcadd6..8dd7a61 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -8,7 +8,7 @@
 #include <linux/syscalls.h>
 #include <linux/user_namespace.h>
 #include <linux/vmalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 struct group_info *groups_alloc(int gidsetsize)
 {
diff --git a/kernel/kcov.c b/kernel/kcov.c
index cc2fa35ca..85e5546 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -19,6 +19,7 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/kcov.h>
+#include <asm/setup.h>
 
 /*
  * kcov descriptor (one per opened debugfs file).
@@ -73,6 +74,11 @@ void notrace __sanitizer_cov_trace_pc(void)
 	if (mode == KCOV_MODE_TRACE) {
 		unsigned long *area;
 		unsigned long pos;
+		unsigned long ip = _RET_IP_;
+
+#ifdef CONFIG_RANDOMIZE_BASE
+		ip -= kaslr_offset();
+#endif
 
 		/*
 		 * There is some code that runs in interrupts but for which
@@ -86,7 +92,7 @@ void notrace __sanitizer_cov_trace_pc(void)
 		/* The first word is number of subsequent PCs. */
 		pos = READ_ONCE(area[0]) + 1;
 		if (likely(pos < t->kcov_size)) {
-			area[pos] = _RET_IP_;
+			area[pos] = ip;
 			WRITE_ONCE(area[0], pos);
 		}
 	}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 0c2df7f..b56a558 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/fs.h>
+#include <linux/ima.h>
 #include <crypto/hash.h>
 #include <crypto/sha.h>
 #include <linux/syscalls.h>
@@ -132,6 +133,9 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 		return ret;
 	image->kernel_buf_len = size;
 
+	/* IMA needs to pass the measurement list to the next kernel. */
+	ima_add_kexec_buffer(image);
+
 	/* Call arch image probe handlers */
 	ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
 					    image->kernel_buf_len);
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 0277d12..d45c960 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -39,7 +39,7 @@
 #include <linux/rwsem.h>
 #include <linux/ptrace.h>
 #include <linux/async.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <trace/events/module.h>
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d630954..4346010 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -52,7 +52,7 @@
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
 #include <asm/errno.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define KPROBE_HASH_BITS 6
 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index a0f61ef..6d1fcc7 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -18,7 +18,7 @@
 #include <linux/debug_locks.h>
 #include <linux/vmalloc.h>
 #include <linux/sort.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/div64.h>
 
 #include "lockdep_internals.h"
diff --git a/kernel/module.c b/kernel/module.c
index f7482db..5088784c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -46,7 +46,7 @@
 #include <linux/string.h>
 #include <linux/mutex.h>
 #include <linux/rculist.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 #include <linux/license.h>
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 4f0f060..2d8e2b2 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -30,7 +30,7 @@
 #include <linux/compiler.h>
 #include <linux/ktime.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 35310b6..22df9f7 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -25,7 +25,7 @@
 #include <linux/cpu.h>
 #include <linux/freezer.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "power.h"
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index e2cdd87..8b26964 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -46,7 +46,7 @@
 #include <linux/ctype.h>
 #include <linux/uio.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/sections.h>
 
 #define CREATE_TRACE_POINTS
diff --git a/kernel/profile.c b/kernel/profile.c
index 2dbccf2..f67ce0a 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -408,7 +408,7 @@ void profile_tick(int type)
 #ifdef CONFIG_PROC_FS
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static int prof_cpu_mask_proc_show(struct seq_file *m, void *v)
 {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 966556e..c56fb57 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1456,7 +1456,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * yield - it could be a while.
 		 */
 		if (unlikely(queued)) {
-			ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
+			ktime_t to = NSEC_PER_SEC / HZ;
 
 			set_current_state(TASK_UNINTERRUPTIBLE);
 			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
diff --git a/kernel/signal.c b/kernel/signal.c
index ae60996..ff046b7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -39,7 +39,7 @@
 #include <trace/events/signal.h>
 
 #include <asm/param.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/siginfo.h>
 #include <asm/cacheflush.h>
@@ -587,7 +587,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 			struct hrtimer *tmr = &tsk->signal->real_timer;
 
 			if (!hrtimer_is_queued(tmr) &&
-			    tsk->signal->it_real_incr.tv64 != 0) {
+			    tsk->signal->it_real_incr != 0) {
 				hrtimer_forward(tmr, tmr->base->get_time(),
 						tsk->signal->it_real_incr);
 				hrtimer_restart(tmr);
@@ -2766,7 +2766,7 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 int do_sigtimedwait(const sigset_t *which, siginfo_t *info,
 		    const struct timespec *ts)
 {
-	ktime_t *to = NULL, timeout = { .tv64 = KTIME_MAX };
+	ktime_t *to = NULL, timeout = KTIME_MAX;
 	struct task_struct *tsk = current;
 	sigset_t mask = *which;
 	int sig, ret = 0;
@@ -2786,7 +2786,7 @@ int do_sigtimedwait(const sigset_t *which, siginfo_t *info,
 
 	spin_lock_irq(&tsk->sighand->siglock);
 	sig = dequeue_signal(tsk, &mask, info);
-	if (!sig && timeout.tv64) {
+	if (!sig && timeout) {
 		/*
 		 * None ready, temporarily unblock those we're interested
 		 * while we are sleeping in so that we'll be awakened when
diff --git a/kernel/sys.c b/kernel/sys.c
index 9758892..842914e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -57,7 +57,7 @@
 /* Move somewhere else to avoid recompiling? */
 #include <generated/utsrelease.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/unistd.h>
 
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 635482e..8acef85 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -150,6 +150,9 @@ cond_syscall(sys_io_destroy);
 cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
+cond_syscall(compat_sys_io_setup);
+cond_syscall(compat_sys_io_submit);
+cond_syscall(compat_sys_io_getevents);
 cond_syscall(sys_sysfs);
 cond_syscall(sys_syslog);
 cond_syscall(sys_process_vm_readv);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 1a292eb..8dbaec0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -67,7 +67,7 @@
 #include <linux/bpf.h>
 #include <linux/mount.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/processor.h>
 
 #ifdef CONFIG_X86
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 3921cf7..e6dc9a5 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -234,7 +234,7 @@ static int alarmtimer_suspend(struct device *dev)
 	min = freezer_delta;
 	expires = freezer_expires;
 	type = freezer_alarmtype;
-	freezer_delta = ktime_set(0, 0);
+	freezer_delta = 0;
 	spin_unlock_irqrestore(&freezer_delta_lock, flags);
 
 	rtc = alarmtimer_get_rtcdev();
@@ -254,13 +254,13 @@ static int alarmtimer_suspend(struct device *dev)
 		if (!next)
 			continue;
 		delta = ktime_sub(next->expires, base->gettime());
-		if (!min.tv64 || (delta.tv64 < min.tv64)) {
+		if (!min || (delta < min)) {
 			expires = next->expires;
 			min = delta;
 			type = i;
 		}
 	}
-	if (min.tv64 == 0)
+	if (min == 0)
 		return 0;
 
 	if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) {
@@ -277,7 +277,7 @@ static int alarmtimer_suspend(struct device *dev)
 	now = ktime_add(now, min);
 
 	/* Set alarm, if in the past reject suspend briefly to handle */
-	ret = rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0));
+	ret = rtc_timer_start(rtc, &rtctimer, now, 0);
 	if (ret < 0)
 		__pm_wakeup_event(ws, MSEC_PER_SEC);
 	return ret;
@@ -328,7 +328,7 @@ static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
 	delta = ktime_sub(absexp, base->gettime());
 
 	spin_lock_irqsave(&freezer_delta_lock, flags);
-	if (!freezer_delta.tv64 || (delta.tv64 < freezer_delta.tv64)) {
+	if (!freezer_delta || (delta < freezer_delta)) {
 		freezer_delta = delta;
 		freezer_expires = absexp;
 		freezer_alarmtype = type;
@@ -453,10 +453,10 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
 
 	delta = ktime_sub(now, alarm->node.expires);
 
-	if (delta.tv64 < 0)
+	if (delta < 0)
 		return 0;
 
-	if (unlikely(delta.tv64 >= interval.tv64)) {
+	if (unlikely(delta >= interval)) {
 		s64 incr = ktime_to_ns(interval);
 
 		overrun = ktime_divns(delta, incr);
@@ -464,7 +464,7 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
 		alarm->node.expires = ktime_add_ns(alarm->node.expires,
 							incr*overrun);
 
-		if (alarm->node.expires.tv64 > now.tv64)
+		if (alarm->node.expires > now)
 			return overrun;
 		/*
 		 * This (and the ktime_add() below) is the
@@ -522,7 +522,7 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 	}
 
 	/* Re-add periodic timers */
-	if (ptr->it.alarm.interval.tv64) {
+	if (ptr->it.alarm.interval) {
 		ptr->it_overrun += alarm_forward(alarm, now,
 						ptr->it.alarm.interval);
 		result = ALARMTIMER_RESTART;
@@ -730,7 +730,7 @@ static int update_rmtp(ktime_t exp, enum  alarmtimer_type type,
 
 	rem = ktime_sub(exp, alarm_bases[type].gettime());
 
-	if (rem.tv64 <= 0)
+	if (rem <= 0)
 		return 0;
 	rmt = ktime_to_timespec(rem);
 
@@ -755,7 +755,7 @@ static long __sched alarm_timer_nsleep_restart(struct restart_block *restart)
 	struct alarm alarm;
 	int ret = 0;
 
-	exp.tv64 = restart->nanosleep.expires;
+	exp = restart->nanosleep.expires;
 	alarm_init(&alarm, type, alarmtimer_nsleep_wakeup);
 
 	if (alarmtimer_do_nsleep(&alarm, exp))
@@ -835,7 +835,7 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	restart = &current->restart_block;
 	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
-	restart->nanosleep.expires = exp.tv64;
+	restart->nanosleep.expires = exp;
 	restart->nanosleep.rmtp = rmtp;
 	ret = -ERESTART_RESTARTBLOCK;
 
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 2c5bc77..97ac095 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -179,7 +179,7 @@ void clockevents_switch_state(struct clock_event_device *dev,
 void clockevents_shutdown(struct clock_event_device *dev)
 {
 	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
-	dev->next_event.tv64 = KTIME_MAX;
+	dev->next_event = KTIME_MAX;
 }
 
 /**
@@ -213,7 +213,7 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 	if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
 		printk_deferred(KERN_WARNING
 				"CE: Reprogramming failure. Giving up\n");
-		dev->next_event.tv64 = KTIME_MAX;
+		dev->next_event = KTIME_MAX;
 		return -ETIME;
 	}
 
@@ -310,7 +310,7 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 	int64_t delta;
 	int rc;
 
-	if (unlikely(expires.tv64 < 0)) {
+	if (unlikely(expires < 0)) {
 		WARN_ON_ONCE(1);
 		return -ETIME;
 	}
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 150242c..665985b 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -170,7 +170,7 @@ void clocksource_mark_unstable(struct clocksource *cs)
 static void clocksource_watchdog(unsigned long data)
 {
 	struct clocksource *cs;
-	cycle_t csnow, wdnow, cslast, wdlast, delta;
+	u64 csnow, wdnow, cslast, wdlast, delta;
 	int64_t wd_nsec, cs_nsec;
 	int next_cpu, reset_pending;
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 08be5c9..c6ecedd 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -50,7 +50,7 @@
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <trace/events/timer.h>
 
@@ -171,7 +171,7 @@ hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
 		return 0;
 
 	expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
-	return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
+	return expires <= new_base->cpu_base->expires_next;
 #else
 	return 0;
 #endif
@@ -313,7 +313,7 @@ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
 	 * We use KTIME_SEC_MAX here, the maximum timeout which we can
 	 * return to user space in a timespec:
 	 */
-	if (res.tv64 < 0 || res.tv64 < lhs.tv64 || res.tv64 < rhs.tv64)
+	if (res < 0 || res < lhs || res < rhs)
 		res = ktime_set(KTIME_SEC_MAX, 0);
 
 	return res;
@@ -465,8 +465,8 @@ static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base,
 static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 {
 	struct hrtimer_clock_base *base = cpu_base->clock_base;
-	ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
 	unsigned int active = cpu_base->active_bases;
+	ktime_t expires, expires_next = KTIME_MAX;
 
 	hrtimer_update_next_timer(cpu_base, NULL);
 	for (; active; base++, active >>= 1) {
@@ -479,7 +479,7 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 		next = timerqueue_getnext(&base->active);
 		timer = container_of(next, struct hrtimer, node);
 		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-		if (expires.tv64 < expires_next.tv64) {
+		if (expires < expires_next) {
 			expires_next = expires;
 			hrtimer_update_next_timer(cpu_base, timer);
 		}
@@ -489,8 +489,8 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
 	 * the clock bases so the result might be negative. Fix it up
 	 * to prevent a false positive in clockevents_program_event().
 	 */
-	if (expires_next.tv64 < 0)
-		expires_next.tv64 = 0;
+	if (expires_next < 0)
+		expires_next = 0;
 	return expires_next;
 }
 #endif
@@ -561,10 +561,10 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
 	expires_next = __hrtimer_get_next_event(cpu_base);
 
-	if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
+	if (skip_equal && expires_next == cpu_base->expires_next)
 		return;
 
-	cpu_base->expires_next.tv64 = expires_next.tv64;
+	cpu_base->expires_next = expires_next;
 
 	/*
 	 * If a hang was detected in the last timer interrupt then we
@@ -622,10 +622,10 @@ static void hrtimer_reprogram(struct hrtimer *timer,
 	 * CLOCK_REALTIME timer might be requested with an absolute
 	 * expiry time which is less than base->offset. Set it to 0.
 	 */
-	if (expires.tv64 < 0)
-		expires.tv64 = 0;
+	if (expires < 0)
+		expires = 0;
 
-	if (expires.tv64 >= cpu_base->expires_next.tv64)
+	if (expires >= cpu_base->expires_next)
 		return;
 
 	/* Update the pointer to the next expiring timer */
@@ -653,7 +653,7 @@ static void hrtimer_reprogram(struct hrtimer *timer,
  */
 static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
 {
-	base->expires_next.tv64 = KTIME_MAX;
+	base->expires_next = KTIME_MAX;
 	base->hres_active = 0;
 }
 
@@ -827,21 +827,21 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 
 	delta = ktime_sub(now, hrtimer_get_expires(timer));
 
-	if (delta.tv64 < 0)
+	if (delta < 0)
 		return 0;
 
 	if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED))
 		return 0;
 
-	if (interval.tv64 < hrtimer_resolution)
-		interval.tv64 = hrtimer_resolution;
+	if (interval < hrtimer_resolution)
+		interval = hrtimer_resolution;
 
-	if (unlikely(delta.tv64 >= interval.tv64)) {
+	if (unlikely(delta >= interval)) {
 		s64 incr = ktime_to_ns(interval);
 
 		orun = ktime_divns(delta, incr);
 		hrtimer_add_expires_ns(timer, incr * orun);
-		if (hrtimer_get_expires_tv64(timer) > now.tv64)
+		if (hrtimer_get_expires_tv64(timer) > now)
 			return orun;
 		/*
 		 * This (and the ktime_add() below) is the
@@ -955,7 +955,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
 	 */
 	timer->is_rel = mode & HRTIMER_MODE_REL;
 	if (timer->is_rel)
-		tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution));
+		tim = ktime_add_safe(tim, hrtimer_resolution);
 #endif
 	return tim;
 }
@@ -1104,7 +1104,7 @@ u64 hrtimer_get_next_event(void)
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
 	if (!__hrtimer_hres_active(cpu_base))
-		expires = __hrtimer_get_next_event(cpu_base).tv64;
+		expires = __hrtimer_get_next_event(cpu_base);
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
@@ -1296,7 +1296,7 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now)
 			 * are right-of a not yet expired timer, because that
 			 * timer will have to trigger a wakeup anyway.
 			 */
-			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
+			if (basenow < hrtimer_get_softexpires_tv64(timer))
 				break;
 
 			__run_hrtimer(cpu_base, base, timer, &basenow);
@@ -1318,7 +1318,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 	BUG_ON(!cpu_base->hres_active);
 	cpu_base->nr_events++;
-	dev->next_event.tv64 = KTIME_MAX;
+	dev->next_event = KTIME_MAX;
 
 	raw_spin_lock(&cpu_base->lock);
 	entry_time = now = hrtimer_update_base(cpu_base);
@@ -1331,7 +1331,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	 * timers which run their callback and need to be requeued on
 	 * this CPU.
 	 */
-	cpu_base->expires_next.tv64 = KTIME_MAX;
+	cpu_base->expires_next = KTIME_MAX;
 
 	__hrtimer_run_queues(cpu_base, now);
 
@@ -1379,13 +1379,13 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	cpu_base->hang_detected = 1;
 	raw_spin_unlock(&cpu_base->lock);
 	delta = ktime_sub(now, entry_time);
-	if ((unsigned int)delta.tv64 > cpu_base->max_hang_time)
-		cpu_base->max_hang_time = (unsigned int) delta.tv64;
+	if ((unsigned int)delta > cpu_base->max_hang_time)
+		cpu_base->max_hang_time = (unsigned int) delta;
 	/*
 	 * Limit it to a sensible value as we enforce a longer
 	 * delay. Give the CPU at least 100ms to catch up.
 	 */
-	if (delta.tv64 > 100 * NSEC_PER_MSEC)
+	if (delta > 100 * NSEC_PER_MSEC)
 		expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
 	else
 		expires_next = ktime_add(now, delta);
@@ -1495,7 +1495,7 @@ static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp)
 	ktime_t rem;
 
 	rem = hrtimer_expires_remaining(timer);
-	if (rem.tv64 <= 0)
+	if (rem <= 0)
 		return 0;
 	rmt = ktime_to_timespec(rem);
 
@@ -1693,7 +1693,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 	 * Optimize when a zero timeout value is given. It does not
 	 * matter whether this is an absolute or a relative time.
 	 */
-	if (expires && !expires->tv64) {
+	if (expires && *expires == 0) {
 		__set_current_state(TASK_RUNNING);
 		return 0;
 	}
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 2b9f45b..8c89143 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -14,7 +14,7 @@
 #include <linux/hrtimer.h>
 #include <trace/events/timer.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /**
  * itimer_get_remtime - get remaining time for the timer
@@ -34,10 +34,10 @@ static struct timeval itimer_get_remtime(struct hrtimer *timer)
 	 * then we return 0 - which is correct.
 	 */
 	if (hrtimer_active(timer)) {
-		if (rem.tv64 <= 0)
-			rem.tv64 = NSEC_PER_USEC;
+		if (rem <= 0)
+			rem = NSEC_PER_USEC;
 	} else
-		rem.tv64 = 0;
+		rem = 0;
 
 	return ktime_to_timeval(rem);
 }
@@ -216,12 +216,12 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 			goto again;
 		}
 		expires = timeval_to_ktime(value->it_value);
-		if (expires.tv64 != 0) {
+		if (expires != 0) {
 			tsk->signal->it_real_incr =
 				timeval_to_ktime(value->it_interval);
 			hrtimer_start(timer, expires, HRTIMER_MODE_REL);
 		} else
-			tsk->signal->it_real_incr.tv64 = 0;
+			tsk->signal->it_real_incr = 0;
 
 		trace_itimer_state(ITIMER_REAL, value, 0);
 		spin_unlock_irq(&tsk->sighand->siglock);
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 555e21f..a4a0e47 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -59,9 +59,9 @@
 #define JIFFIES_SHIFT	8
 #endif
 
-static cycle_t jiffies_read(struct clocksource *cs)
+static u64 jiffies_read(struct clocksource *cs)
 {
-	return (cycle_t) jiffies;
+	return (u64) jiffies;
 }
 
 static struct clocksource clocksource_jiffies = {
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 6df8927..edf19cc 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -381,7 +381,7 @@ ktime_t ntp_get_next_leap(void)
 
 	if ((time_state == TIME_INS) && (time_status & STA_INS))
 		return ktime_set(ntp_next_leap_sec, 0);
-	ret.tv64 = KTIME_MAX;
+	ret = KTIME_MAX;
 	return ret;
 }
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index f246763..e9e8c10 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -6,7 +6,7 @@
 #include <linux/posix-timers.h>
 #include <linux/errno.h>
 #include <linux/math64.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/kernel_stat.h>
 #include <trace/events/timer.h>
 #include <linux/tick.h>
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index f2826c3..1e6623d 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -36,7 +36,7 @@
 #include <linux/time.h>
 #include <linux/mutex.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/compiler.h>
@@ -359,7 +359,7 @@ static void schedule_next_timer(struct k_itimer *timr)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
 
-	if (timr->it.real.interval.tv64 == 0)
+	if (timr->it.real.interval == 0)
 		return;
 
 	timr->it_overrun += (unsigned int) hrtimer_forward(timer,
@@ -449,7 +449,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 	timr = container_of(timer, struct k_itimer, it.real.timer);
 	spin_lock_irqsave(&timr->it_lock, flags);
 
-	if (timr->it.real.interval.tv64 != 0)
+	if (timr->it.real.interval != 0)
 		si_private = ++timr->it_requeue_pending;
 
 	if (posix_timer_event(timr, si_private)) {
@@ -458,7 +458,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 		 * we will not get a call back to restart it AND
 		 * it should be restarted.
 		 */
-		if (timr->it.real.interval.tv64 != 0) {
+		if (timr->it.real.interval != 0) {
 			ktime_t now = hrtimer_cb_get_time(timer);
 
 			/*
@@ -485,9 +485,9 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 			 */
 #ifdef CONFIG_HIGH_RES_TIMERS
 			{
-				ktime_t kj = ktime_set(0, NSEC_PER_SEC / HZ);
+				ktime_t kj = NSEC_PER_SEC / HZ;
 
-				if (timr->it.real.interval.tv64 < kj.tv64)
+				if (timr->it.real.interval < kj)
 					now = ktime_add(now, kj);
 			}
 #endif
@@ -743,7 +743,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 	iv = timr->it.real.interval;
 
 	/* interval timer ? */
-	if (iv.tv64)
+	if (iv)
 		cur_setting->it_interval = ktime_to_timespec(iv);
 	else if (!hrtimer_active(timer) &&
 		 (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
@@ -756,13 +756,13 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 	 * timer move the expiry time forward by intervals, so
 	 * expiry is > now.
 	 */
-	if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
-	    (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
+	if (iv && (timr->it_requeue_pending & REQUEUE_PENDING ||
+		   (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
 		timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
 
 	remaining = __hrtimer_expires_remaining_adjusted(timer, now);
 	/* Return 0 only, when the timer is expired and not pending */
-	if (remaining.tv64 <= 0) {
+	if (remaining <= 0) {
 		/*
 		 * A single shot SIGEV_NONE timer must return 0, when
 		 * it is expired !
@@ -839,7 +839,7 @@ common_timer_set(struct k_itimer *timr, int flags,
 		common_timer_get(timr, old_setting);
 
 	/* disable the timer */
-	timr->it.real.interval.tv64 = 0;
+	timr->it.real.interval = 0;
 	/*
 	 * careful here.  If smp we could be in the "fire" routine which will
 	 * be spinning as we hold the lock.  But this is ONLY an SMP issue.
@@ -924,7 +924,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 
 static int common_timer_del(struct k_itimer *timer)
 {
-	timer->it.real.interval.tv64 = 0;
+	timer->it.real.interval = 0;
 
 	if (hrtimer_try_to_cancel(&timer->it.real.timer) < 0)
 		return TIMER_RETRY;
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 690b797..a7bb8f3 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -97,7 +97,7 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
 
 	if (clockevent_state_oneshot(&ce_broadcast_hrtimer))
-		if (ce_broadcast_hrtimer.next_event.tv64 != KTIME_MAX)
+		if (ce_broadcast_hrtimer.next_event != KTIME_MAX)
 			return HRTIMER_RESTART;
 
 	return HRTIMER_NORESTART;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index d2a20e8..3109204 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -604,14 +604,14 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
-	dev->next_event.tv64 = KTIME_MAX;
-	next_event.tv64 = KTIME_MAX;
+	dev->next_event = KTIME_MAX;
+	next_event = KTIME_MAX;
 	cpumask_clear(tmpmask);
 	now = ktime_get();
 	/* Find all expired events */
 	for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
 		td = &per_cpu(tick_cpu_device, cpu);
-		if (td->evtdev->next_event.tv64 <= now.tv64) {
+		if (td->evtdev->next_event <= now) {
 			cpumask_set_cpu(cpu, tmpmask);
 			/*
 			 * Mark the remote cpu in the pending mask, so
@@ -619,8 +619,8 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 			 * timer in tick_broadcast_oneshot_control().
 			 */
 			cpumask_set_cpu(cpu, tick_broadcast_pending_mask);
-		} else if (td->evtdev->next_event.tv64 < next_event.tv64) {
-			next_event.tv64 = td->evtdev->next_event.tv64;
+		} else if (td->evtdev->next_event < next_event) {
+			next_event = td->evtdev->next_event;
 			next_cpu = cpu;
 		}
 	}
@@ -657,7 +657,7 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 	 * - There are pending events on sleeping CPUs which were not
 	 * in the event mask
 	 */
-	if (next_event.tv64 != KTIME_MAX)
+	if (next_event != KTIME_MAX)
 		tick_broadcast_set_event(dev, next_cpu, next_event);
 
 	raw_spin_unlock(&tick_broadcast_lock);
@@ -672,7 +672,7 @@ static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
 {
 	if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
 		return 0;
-	if (bc->next_event.tv64 == KTIME_MAX)
+	if (bc->next_event == KTIME_MAX)
 		return 0;
 	return bc->bound_on == cpu ? -EBUSY : 0;
 }
@@ -688,7 +688,7 @@ static void broadcast_shutdown_local(struct clock_event_device *bc,
 	if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
 		if (broadcast_needs_cpu(bc, smp_processor_id()))
 			return;
-		if (dev->next_event.tv64 < bc->next_event.tv64)
+		if (dev->next_event < bc->next_event)
 			return;
 	}
 	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
@@ -754,7 +754,7 @@ int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			 */
 			if (cpumask_test_cpu(cpu, tick_broadcast_force_mask)) {
 				ret = -EBUSY;
-			} else if (dev->next_event.tv64 < bc->next_event.tv64) {
+			} else if (dev->next_event < bc->next_event) {
 				tick_broadcast_set_event(bc, cpu, dev->next_event);
 				/*
 				 * In case of hrtimer broadcasts the
@@ -789,7 +789,7 @@ int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			/*
 			 * Bail out if there is no next event.
 			 */
-			if (dev->next_event.tv64 == KTIME_MAX)
+			if (dev->next_event == KTIME_MAX)
 				goto out;
 			/*
 			 * If the pending bit is not set, then we are
@@ -824,7 +824,7 @@ int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			 * nohz fixups.
 			 */
 			now = ktime_get();
-			if (dev->next_event.tv64 <= now.tv64) {
+			if (dev->next_event <= now) {
 				cpumask_set_cpu(cpu, tick_broadcast_force_mask);
 				goto out;
 			}
@@ -897,7 +897,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 						       tick_next_period);
 			tick_broadcast_set_event(bc, cpu, tick_next_period);
 		} else
-			bc->next_event.tv64 = KTIME_MAX;
+			bc->next_event = KTIME_MAX;
 	} else {
 		/*
 		 * The first cpu which switches to oneshot mode sets
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 4fcd99e..49edc1c 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -178,8 +178,8 @@ static void tick_setup_device(struct tick_device *td,
 			      struct clock_event_device *newdev, int cpu,
 			      const struct cpumask *cpumask)
 {
-	ktime_t next_event;
 	void (*handler)(struct clock_event_device *) = NULL;
+	ktime_t next_event = 0;
 
 	/*
 	 * First device setup ?
@@ -195,7 +195,7 @@ static void tick_setup_device(struct tick_device *td,
 			else
 				tick_do_timer_cpu = TICK_DO_TIMER_NONE;
 			tick_next_period = ktime_get();
-			tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
+			tick_period = NSEC_PER_SEC / HZ;
 		}
 
 		/*
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index b513446..6b009c2 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -28,7 +28,7 @@ int tick_program_event(ktime_t expires, int force)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 
-	if (unlikely(expires.tv64 == KTIME_MAX)) {
+	if (unlikely(expires == KTIME_MAX)) {
 		/*
 		 * We don't need the clock event device any more, stop it.
 		 */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 71496a2..2c115fd 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -58,21 +58,21 @@ static void tick_do_update_jiffies64(ktime_t now)
 	 * Do a quick check without holding jiffies_lock:
 	 */
 	delta = ktime_sub(now, last_jiffies_update);
-	if (delta.tv64 < tick_period.tv64)
+	if (delta < tick_period)
 		return;
 
 	/* Reevaluate with jiffies_lock held */
 	write_seqlock(&jiffies_lock);
 
 	delta = ktime_sub(now, last_jiffies_update);
-	if (delta.tv64 >= tick_period.tv64) {
+	if (delta >= tick_period) {
 
 		delta = ktime_sub(delta, tick_period);
 		last_jiffies_update = ktime_add(last_jiffies_update,
 						tick_period);
 
 		/* Slow path for long timeouts */
-		if (unlikely(delta.tv64 >= tick_period.tv64)) {
+		if (unlikely(delta >= tick_period)) {
 			s64 incr = ktime_to_ns(tick_period);
 
 			ticks = ktime_divns(delta, incr);
@@ -101,7 +101,7 @@ static ktime_t tick_init_jiffy_update(void)
 
 	write_seqlock(&jiffies_lock);
 	/* Did we start the jiffies update yet ? */
-	if (last_jiffies_update.tv64 == 0)
+	if (last_jiffies_update == 0)
 		last_jiffies_update = tick_next_period;
 	period = last_jiffies_update;
 	write_sequnlock(&jiffies_lock);
@@ -669,7 +669,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&jiffies_lock);
-		basemono = last_jiffies_update.tv64;
+		basemono = last_jiffies_update;
 		basejiff = jiffies;
 	} while (read_seqretry(&jiffies_lock, seq));
 	ts->last_jiffies = basejiff;
@@ -697,7 +697,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	 */
 	delta = next_tick - basemono;
 	if (delta <= (u64)TICK_NSEC) {
-		tick.tv64 = 0;
+		tick = 0;
 
 		/*
 		 * Tell the timer code that the base is not idle, i.e. undo
@@ -764,10 +764,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		expires = KTIME_MAX;
 
 	expires = min_t(u64, expires, next_tick);
-	tick.tv64 = expires;
+	tick = expires;
 
 	/* Skip reprogram of event if its not changed */
-	if (ts->tick_stopped && (expires == dev->next_event.tv64))
+	if (ts->tick_stopped && (expires == dev->next_event))
 		goto out;
 
 	/*
@@ -864,7 +864,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	}
 
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
-		ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
+		ts->sleep_length = NSEC_PER_SEC / HZ;
 		return false;
 	}
 
@@ -914,7 +914,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
 		ts->idle_calls++;
 
 		expires = tick_nohz_stop_sched_tick(ts, now, cpu);
-		if (expires.tv64 > 0LL) {
+		if (expires > 0LL) {
 			ts->idle_sleeps++;
 			ts->idle_expires = expires;
 		}
@@ -1051,7 +1051,7 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	struct pt_regs *regs = get_irq_regs();
 	ktime_t now = ktime_get();
 
-	dev->next_event.tv64 = KTIME_MAX;
+	dev->next_event = KTIME_MAX;
 
 	tick_sched_do_timer(now);
 	tick_sched_handle(ts, regs);
diff --git a/kernel/time/time.c b/kernel/time/time.c
index bd62fb8..a3a9a8a 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -38,7 +38,7 @@
 #include <linux/math64.h>
 #include <linux/ptrace.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 #include <generated/timeconst.h>
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
index 4687b31..8afd789 100644
--- a/kernel/time/timecounter.c
+++ b/kernel/time/timecounter.c
@@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(timecounter_init);
  */
 static u64 timecounter_read_delta(struct timecounter *tc)
 {
-	cycle_t cycle_now, cycle_delta;
+	u64 cycle_now, cycle_delta;
 	u64 ns_offset;
 
 	/* read cycle counter: */
@@ -80,7 +80,7 @@ EXPORT_SYMBOL_GPL(timecounter_read);
  * time previous to the time stored in the cycle counter.
  */
 static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc,
-			       cycle_t cycles, u64 mask, u64 frac)
+			       u64 cycles, u64 mask, u64 frac)
 {
 	u64 ns = (u64) cycles;
 
@@ -90,7 +90,7 @@ static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc,
 }
 
 u64 timecounter_cyc2time(struct timecounter *tc,
-			 cycle_t cycle_tstamp)
+			 u64 cycle_tstamp)
 {
 	u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
 	u64 nsec = tc->nsec, frac = tc->frac;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index da233cd..db087d7e1 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -104,7 +104,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
 	 */
 	set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec,
 					-tk->wall_to_monotonic.tv_nsec);
-	WARN_ON_ONCE(tk->offs_real.tv64 != timespec64_to_ktime(tmp).tv64);
+	WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp));
 	tk->wall_to_monotonic = wtm;
 	set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
 	tk->offs_real = timespec64_to_ktime(tmp);
@@ -119,10 +119,10 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 #ifdef CONFIG_DEBUG_TIMEKEEPING
 #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
 
-static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
+static void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 {
 
-	cycle_t max_cycles = tk->tkr_mono.clock->max_cycles;
+	u64 max_cycles = tk->tkr_mono.clock->max_cycles;
 	const char *name = tk->tkr_mono.clock->name;
 
 	if (offset > max_cycles) {
@@ -158,10 +158,10 @@ static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
 	}
 }
 
-static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	cycle_t now, last, mask, max, delta;
+	u64 now, last, mask, max, delta;
 	unsigned int seq;
 
 	/*
@@ -199,12 +199,12 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
 	return delta;
 }
 #else
-static inline void timekeeping_check_update(struct timekeeper *tk, cycle_t offset)
+static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 {
 }
-static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
 {
-	cycle_t cycle_now, delta;
+	u64 cycle_now, delta;
 
 	/* read clocksource */
 	cycle_now = tkr->read(tkr->clock);
@@ -229,7 +229,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
  */
 static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 {
-	cycle_t interval;
+	u64 interval;
 	u64 tmp, ntpinterval;
 	struct clocksource *old_clock;
 
@@ -254,7 +254,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	if (tmp == 0)
 		tmp = 1;
 
-	interval = (cycle_t) tmp;
+	interval = (u64) tmp;
 	tk->cycle_interval = interval;
 
 	/* Go back from cycles -> shifted ns */
@@ -298,8 +298,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
-static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
-					  cycle_t delta)
+static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
 {
 	u64 nsec;
 
@@ -312,16 +311,15 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
 
 static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
 {
-	cycle_t delta;
+	u64 delta;
 
 	delta = timekeeping_get_delta(tkr);
 	return timekeeping_delta_to_ns(tkr, delta);
 }
 
-static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr,
-					   cycle_t cycles)
+static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
 {
-	cycle_t delta;
+	u64 delta;
 
 	/* calculate the delta since the last update_wall_time */
 	delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask);
@@ -454,9 +452,9 @@ u64 notrace ktime_get_boot_fast_ns(void)
 EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
 
 /* Suspend-time cycles value for halted fast timekeeper. */
-static cycle_t cycles_at_suspend;
+static u64 cycles_at_suspend;
 
-static cycle_t dummy_clock_read(struct clocksource *cs)
+static u64 dummy_clock_read(struct clocksource *cs)
 {
 	return cycles_at_suspend;
 }
@@ -573,7 +571,7 @@ EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
 static inline void tk_update_leap_state(struct timekeeper *tk)
 {
 	tk->next_leap_ktime = ntp_get_next_leap();
-	if (tk->next_leap_ktime.tv64 != KTIME_MAX)
+	if (tk->next_leap_ktime != KTIME_MAX)
 		/* Convert to monotonic time */
 		tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real);
 }
@@ -650,7 +648,7 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 static void timekeeping_forward_now(struct timekeeper *tk)
 {
 	struct clocksource *clock = tk->tkr_mono.clock;
-	cycle_t cycle_now, delta;
+	u64 cycle_now, delta;
 	u64 nsec;
 
 	cycle_now = tk->tkr_mono.read(clock);
@@ -923,7 +921,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
 	ktime_t base_real;
 	u64 nsec_raw;
 	u64 nsec_real;
-	cycle_t now;
+	u64 now;
 
 	WARN_ON_ONCE(timekeeping_suspended);
 
@@ -982,8 +980,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
  * interval is partial_history_cycles.
  */
 static int adjust_historical_crosststamp(struct system_time_snapshot *history,
-					 cycle_t partial_history_cycles,
-					 cycle_t total_history_cycles,
+					 u64 partial_history_cycles,
+					 u64 total_history_cycles,
 					 bool discontinuity,
 					 struct system_device_crosststamp *ts)
 {
@@ -1047,7 +1045,7 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history,
 /*
  * cycle_between - true if test occurs chronologically between before and after
  */
-static bool cycle_between(cycle_t before, cycle_t test, cycle_t after)
+static bool cycle_between(u64 before, u64 test, u64 after)
 {
 	if (test > before && test < after)
 		return true;
@@ -1077,7 +1075,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 {
 	struct system_counterval_t system_counterval;
 	struct timekeeper *tk = &tk_core.timekeeper;
-	cycle_t cycles, now, interval_start;
+	u64 cycles, now, interval_start;
 	unsigned int clock_was_set_seq = 0;
 	ktime_t base_real, base_raw;
 	u64 nsec_real, nsec_raw;
@@ -1138,7 +1136,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 	 * current interval
 	 */
 	if (do_interp) {
-		cycle_t partial_history_cycles, total_history_cycles;
+		u64 partial_history_cycles, total_history_cycles;
 		bool discontinuity;
 
 		/*
@@ -1644,7 +1642,7 @@ void timekeeping_resume(void)
 	struct clocksource *clock = tk->tkr_mono.clock;
 	unsigned long flags;
 	struct timespec64 ts_new, ts_delta;
-	cycle_t cycle_now;
+	u64 cycle_now;
 
 	sleeptime_injected = false;
 	read_persistent_clock64(&ts_new);
@@ -2010,11 +2008,10 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
  *
  * Returns the unconsumed cycles.
  */
-static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
-						u32 shift,
-						unsigned int *clock_set)
+static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
+				    u32 shift, unsigned int *clock_set)
 {
-	cycle_t interval = tk->cycle_interval << shift;
+	u64 interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
 
 	/* If the offset is smaller than a shifted interval, do nothing */
@@ -2055,7 +2052,7 @@ void update_wall_time(void)
 {
 	struct timekeeper *real_tk = &tk_core.timekeeper;
 	struct timekeeper *tk = &shadow_timekeeper;
-	cycle_t offset;
+	u64 offset;
 	int shift = 0, maxshift;
 	unsigned int clock_set = 0;
 	unsigned long flags;
@@ -2253,7 +2250,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
 		}
 
 		/* Handle leapsecond insertion adjustments */
-		if (unlikely(base.tv64 >= tk->next_leap_ktime.tv64))
+		if (unlikely(base >= tk->next_leap_ktime))
 			*offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0));
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index 5be7627..9a18f12 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -13,9 +13,9 @@ extern void tk_debug_account_sleep_time(struct timespec64 *t);
 #endif
 
 #ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE
-static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask)
+static inline u64 clocksource_delta(u64 now, u64 last, u64 mask)
 {
-	cycle_t ret = (now - last) & mask;
+	u64 ret = (now - last) & mask;
 
 	/*
 	 * Prevent time going backwards by checking the MSB of mask in
@@ -24,7 +24,7 @@ static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask)
 	return ret & ~(mask >> 1) ? 0 : ret;
 }
 #else
-static inline cycle_t clocksource_delta(cycle_t now, cycle_t last, cycle_t mask)
+static inline u64 clocksource_delta(u64 now, u64 last, u64 mask)
 {
 	return (now - last) & mask;
 }
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ea4fbf8..ec33a69 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -43,7 +43,7 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/div64.h>
 #include <asm/timex.h>
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ba7d8b2..afe6cd1 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -17,7 +17,7 @@
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "tick-internal.h"
 
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index 087204c..afddded 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -43,7 +43,7 @@
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * This is our basic unit of interest: a timer expiry event identified
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1f0f547..eb230f0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2847,7 +2847,7 @@ static void ftrace_shutdown_sysctl(void)
 	}
 }
 
-static cycle_t		ftrace_update_time;
+static u64		ftrace_update_time;
 unsigned long		ftrace_update_tot_cnt;
 
 static inline int ops_traces_mod(struct ftrace_ops *ops)
@@ -2894,7 +2894,7 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 {
 	struct ftrace_page *pg;
 	struct dyn_ftrace *p;
-	cycle_t start, stop;
+	u64 start, stop;
 	unsigned long update_cnt = 0;
 	unsigned long rec_flags = 0;
 	int i;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 66f829c..d744978 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -236,7 +236,7 @@ static int __init set_tracepoint_printk(char *str)
 }
 __setup("tp_printk", set_tracepoint_printk);
 
-unsigned long long ns2usecs(cycle_t nsec)
+unsigned long long ns2usecs(u64 nsec)
 {
 	nsec += 500;
 	do_div(nsec, 1000);
@@ -573,7 +573,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	return read;
 }
 
-static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
+static u64 buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
 	u64 ts;
 
@@ -587,7 +587,7 @@ static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 	return ts;
 }
 
-cycle_t ftrace_now(int cpu)
+u64 ftrace_now(int cpu)
 {
 	return buffer_ftrace_now(&global_trace.trace_buffer, cpu);
 }
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c223449..1ea51ab 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -159,7 +159,7 @@ struct trace_array_cpu {
 	unsigned long		policy;
 	unsigned long		rt_priority;
 	unsigned long		skipped_entries;
-	cycle_t			preempt_timestamp;
+	u64			preempt_timestamp;
 	pid_t			pid;
 	kuid_t			uid;
 	char			comm[TASK_COMM_LEN];
@@ -177,7 +177,7 @@ struct trace_buffer {
 	struct trace_array		*tr;
 	struct ring_buffer		*buffer;
 	struct trace_array_cpu __percpu	*data;
-	cycle_t				time_start;
+	u64				time_start;
 	int				cpu;
 };
 
@@ -689,7 +689,7 @@ static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
 }
 #endif /* CONFIG_STACKTRACE */
 
-extern cycle_t ftrace_now(int cpu);
+extern u64 ftrace_now(int cpu);
 
 extern void trace_find_cmdline(int pid, char comm[]);
 extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
@@ -736,7 +736,7 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
-extern unsigned long long ns2usecs(cycle_t nsec);
+extern unsigned long long ns2usecs(u64 nsec);
 extern int
 trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 86654d7..7758bc0 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -298,7 +298,7 @@ static void irqsoff_print_header(struct seq_file *s)
 /*
  * Should this new latency be reported/recorded?
  */
-static bool report_latency(struct trace_array *tr, cycle_t delta)
+static bool report_latency(struct trace_array *tr, u64 delta)
 {
 	if (tracing_thresh) {
 		if (delta < tracing_thresh)
@@ -316,7 +316,7 @@ check_critical_timing(struct trace_array *tr,
 		      unsigned long parent_ip,
 		      int cpu)
 {
-	cycle_t T0, T1, delta;
+	u64 T0, T1, delta;
 	unsigned long flags;
 	int pc;
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 5d0bb02..ddec53b 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -358,7 +358,7 @@ static void wakeup_print_header(struct seq_file *s)
 /*
  * Should this new latency be reported/recorded?
  */
-static bool report_latency(struct trace_array *tr, cycle_t delta)
+static bool report_latency(struct trace_array *tr, u64 delta)
 {
 	if (tracing_thresh) {
 		if (delta < tracing_thresh)
@@ -440,7 +440,7 @@ probe_wakeup_sched_switch(void *ignore, bool preempt,
 			  struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
-	cycle_t T0, T1, delta;
+	u64 T0, T1, delta;
 	unsigned long flags;
 	long disabled;
 	int cpu;
diff --git a/kernel/uid16.c b/kernel/uid16.c
index cc40793..71645ae 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -14,7 +14,7 @@
 #include <linux/security.h>
 #include <linux/syscalls.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 SYSCALL_DEFINE3(chown16, const char __user *, filename, old_uid_t, user, old_gid_t, group)
 {
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7446097..b06848a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -26,7 +26,7 @@
 	  the kernel bootargs. loglevel=<x> continues to override whatever
 	  value is specified here as well.
 
-	  Note: This does not affect the log level of un-prefixed prink()
+	  Note: This does not affect the log level of un-prefixed printk()
 	  usage in the kernel. That is controlled by the MESSAGE_LOGLEVEL_DEFAULT
 	  option.
 
@@ -1538,30 +1538,6 @@
 
 	  Say N if unsure.
 
-config CPU_NOTIFIER_ERROR_INJECT
-	tristate "CPU notifier error injection module"
-	depends on HOTPLUG_CPU && NOTIFIER_ERROR_INJECTION
-	help
-	  This option provides a kernel module that can be used to test
-	  the error handling of the cpu notifiers by injecting artificial
-	  errors to CPU notifier chain callbacks.  It is controlled through
-	  debugfs interface under /sys/kernel/debug/notifier-error-inject/cpu
-
-	  If the notifier call chain should be failed with some events
-	  notified, write the error code to "actions/<notifier event>/error".
-
-	  Example: Inject CPU offline error (-1 == -EPERM)
-
-	  # cd /sys/kernel/debug/notifier-error-inject/cpu
-	  # echo -1 > actions/CPU_DOWN_PREPARE/error
-	  # echo 0 > /sys/devices/system/cpu/cpu1/online
-	  bash: echo: write error: Operation not permitted
-
-	  To compile this code as a module, choose M here: the module will
-	  be called cpu-notifier-error-inject.
-
-	  If unsure, say N.
-
 config PM_NOTIFIER_ERROR_INJECT
 	tristate "PM notifier error injection module"
 	depends on PM && NOTIFIER_ERROR_INJECTION
diff --git a/lib/Makefile b/lib/Makefile
index 50144a3..bc4073a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -128,7 +128,6 @@
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
-obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
 obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
 obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
 obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o
diff --git a/lib/cpu-notifier-error-inject.c b/lib/cpu-notifier-error-inject.c
deleted file mode 100644
index 0e2c9a1..0000000
--- a/lib/cpu-notifier-error-inject.c
+++ /dev/null
@@ -1,84 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-
-#include "notifier-error-inject.h"
-
-static int priority;
-module_param(priority, int, 0);
-MODULE_PARM_DESC(priority, "specify cpu notifier priority");
-
-#define UP_PREPARE 0
-#define UP_PREPARE_FROZEN 0
-#define DOWN_PREPARE 0
-#define DOWN_PREPARE_FROZEN 0
-
-static struct notifier_err_inject cpu_notifier_err_inject = {
-	.actions = {
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE_FROZEN) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE_FROZEN) },
-		{}
-	}
-};
-
-static int notf_err_handle(struct notifier_err_inject_action *action)
-{
-	int ret;
-
-	ret = action->error;
-	if (ret)
-		pr_info("Injecting error (%d) to %s\n", ret, action->name);
-	return ret;
-}
-
-static int notf_err_inj_up_prepare(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[0]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[1]);
-}
-
-static int notf_err_inj_dead(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[2]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[3]);
-}
-
-static struct dentry *dir;
-
-static int err_inject_init(void)
-{
-	int err;
-
-	dir = notifier_err_inject_init("cpu", notifier_err_inject_dir,
-					&cpu_notifier_err_inject, priority);
-	if (IS_ERR(dir))
-		return PTR_ERR(dir);
-
-	err = cpuhp_setup_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE,
-					"cpu-err-notif:prepare",
-					notf_err_inj_up_prepare,
-					notf_err_inj_dead);
-	if (err)
-		debugfs_remove_recursive(dir);
-
-	return err;
-}
-
-static void err_inject_exit(void)
-{
-	cpuhp_remove_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE);
-	debugfs_remove_recursive(dir);
-}
-
-module_init(err_inject_init);
-module_exit(err_inject_exit);
-
-MODULE_DESCRIPTION("CPU notifier error injection module");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");
diff --git a/lib/extable.c b/lib/extable.c
index 0be02ad..62968da 100644
--- a/lib/extable.c
+++ b/lib/extable.c
@@ -12,7 +12,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/sort.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifndef ARCH_HAS_RELATIVE_EXTABLE
 #define ex_to_insn(x)	((x)->insn)
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 228892d..25f5723 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -73,19 +73,21 @@
 }
 
 #define iterate_all_kinds(i, n, v, I, B, K) {			\
-	size_t skip = i->iov_offset;				\
-	if (unlikely(i->type & ITER_BVEC)) {			\
-		struct bio_vec v;				\
-		struct bvec_iter __bi;				\
-		iterate_bvec(i, n, v, __bi, skip, (B))		\
-	} else if (unlikely(i->type & ITER_KVEC)) {		\
-		const struct kvec *kvec;			\
-		struct kvec v;					\
-		iterate_kvec(i, n, v, kvec, skip, (K))		\
-	} else {						\
-		const struct iovec *iov;			\
-		struct iovec v;					\
-		iterate_iovec(i, n, v, iov, skip, (I))		\
+	if (likely(n)) {					\
+		size_t skip = i->iov_offset;			\
+		if (unlikely(i->type & ITER_BVEC)) {		\
+			struct bio_vec v;			\
+			struct bvec_iter __bi;			\
+			iterate_bvec(i, n, v, __bi, skip, (B))	\
+		} else if (unlikely(i->type & ITER_KVEC)) {	\
+			const struct kvec *kvec;		\
+			struct kvec v;				\
+			iterate_kvec(i, n, v, kvec, skip, (K))	\
+		} else {					\
+			const struct iovec *iov;		\
+			struct iovec v;				\
+			iterate_iovec(i, n, v, iov, skip, (I))	\
+		}						\
 	}							\
 }
 
@@ -576,7 +578,7 @@ bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i)
 		WARN_ON(1);
 		return false;
 	}
-	if (unlikely(i->count < bytes))				\
+	if (unlikely(i->count < bytes))
 		return false;
 
 	iterate_all_kinds(i, bytes, v, ({
@@ -620,7 +622,7 @@ bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i)
 		WARN_ON(1);
 		return false;
 	}
-	if (unlikely(i->count < bytes))				\
+	if (unlikely(i->count < bytes))
 		return false;
 	iterate_all_kinds(i, bytes, v, ({
 		if (__copy_from_user_nocache((to += v.iov_len) - v.iov_len,
@@ -837,11 +839,8 @@ unsigned long iov_iter_alignment(const struct iov_iter *i)
 	unsigned long res = 0;
 	size_t size = i->count;
 
-	if (!size)
-		return 0;
-
 	if (unlikely(i->type & ITER_PIPE)) {
-		if (i->iov_offset && allocated(&i->pipe->bufs[i->idx]))
+		if (size && i->iov_offset && allocated(&i->pipe->bufs[i->idx]))
 			return size | i->iov_offset;
 		return size;
 	}
@@ -856,10 +855,8 @@ EXPORT_SYMBOL(iov_iter_alignment);
 
 unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
 {
-        unsigned long res = 0;
+	unsigned long res = 0;
 	size_t size = i->count;
-	if (!size)
-		return 0;
 
 	if (unlikely(i->type & ITER_PIPE)) {
 		WARN_ON(1);
@@ -874,7 +871,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
 		(res |= (!res ? 0 : (unsigned long)v.iov_base) |
 			(size != v.iov_len ? size : 0))
 		);
-		return res;
+	return res;
 }
 EXPORT_SYMBOL(iov_iter_gap_alignment);
 
@@ -908,6 +905,9 @@ static ssize_t pipe_get_pages(struct iov_iter *i,
 	size_t capacity;
 	int idx;
 
+	if (!maxsize)
+		return 0;
+
 	if (!sanity(i))
 		return -EFAULT;
 
@@ -926,9 +926,6 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 	if (maxsize > i->count)
 		maxsize = i->count;
 
-	if (!maxsize)
-		return 0;
-
 	if (unlikely(i->type & ITER_PIPE))
 		return pipe_get_pages(i, pages, maxsize, maxpages, start);
 	iterate_all_kinds(i, maxsize, v, ({
@@ -975,6 +972,9 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
 	int idx;
 	int npages;
 
+	if (!maxsize)
+		return 0;
+
 	if (!sanity(i))
 		return -EFAULT;
 
@@ -1006,9 +1006,6 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 	if (maxsize > i->count)
 		maxsize = i->count;
 
-	if (!maxsize)
-		return 0;
-
 	if (unlikely(i->type & ITER_PIPE))
 		return pipe_get_pages_alloc(i, pages, maxsize, start);
 	iterate_all_kinds(i, maxsize, v, ({
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index b8e2080..bf85e05 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -17,7 +17,7 @@
 #include <linux/math64.h>
 #include <linux/export.h>
 #include <linux/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "kstrtox.h"
 
 const char *_parse_integer_fixup_radix(const char *s, unsigned int *base)
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index 782ae8c..adc6ee0 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -48,7 +48,7 @@ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 	while (*p) {
 		parent = *p;
 		ptr = rb_entry(parent, struct timerqueue_node, node);
-		if (node->expires.tv64 < ptr->expires.tv64)
+		if (node->expires < ptr->expires)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -56,7 +56,7 @@ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node)
 	rb_link_node(&node->node, parent, p);
 	rb_insert_color(&node->node, &head->head);
 
-	if (!head->next || node->expires.tv64 < head->next->expires.tv64) {
+	if (!head->next || node->expires < head->next->expires) {
 		head->next = node;
 		return true;
 	}
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 6c707bf..a430131 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -139,7 +139,20 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 		}
 
 		if (end_index >= start_index) {
-			unsigned long count = invalidate_mapping_pages(mapping,
+			unsigned long count;
+
+			/*
+			 * It's common to FADV_DONTNEED right after
+			 * the read or write that instantiates the
+			 * pages, in which case there will be some
+			 * sitting on the local LRU cache. Try to
+			 * avoid the expensive remote drain and the
+			 * second cache tree walk below by flushing
+			 * them out right away.
+			 */
+			lru_add_drain();
+
+			count = invalidate_mapping_pages(mapping,
 						start_index, end_index);
 
 			/*
diff --git a/mm/filemap.c b/mm/filemap.c
index 32be3c8..d0e4d10 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -739,46 +739,160 @@ EXPORT_SYMBOL(__page_cache_alloc);
  * at a cost of "thundering herd" phenomena during rare hash
  * collisions.
  */
-wait_queue_head_t *page_waitqueue(struct page *page)
+#define PAGE_WAIT_TABLE_BITS 8
+#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
+static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
+
+static wait_queue_head_t *page_waitqueue(struct page *page)
 {
-	return bit_waitqueue(page, 0);
+	return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
 }
-EXPORT_SYMBOL(page_waitqueue);
+
+void __init pagecache_init(void)
+{
+	int i;
+
+	for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(&page_wait_table[i]);
+
+	page_writeback_init();
+}
+
+struct wait_page_key {
+	struct page *page;
+	int bit_nr;
+	int page_match;
+};
+
+struct wait_page_queue {
+	struct page *page;
+	int bit_nr;
+	wait_queue_t wait;
+};
+
+static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
+{
+	struct wait_page_key *key = arg;
+	struct wait_page_queue *wait_page
+		= container_of(wait, struct wait_page_queue, wait);
+
+	if (wait_page->page != key->page)
+	       return 0;
+	key->page_match = 1;
+
+	if (wait_page->bit_nr != key->bit_nr)
+		return 0;
+	if (test_bit(key->bit_nr, &key->page->flags))
+		return 0;
+
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
+void wake_up_page_bit(struct page *page, int bit_nr)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	struct wait_page_key key;
+	unsigned long flags;
+
+	key.page = page;
+	key.bit_nr = bit_nr;
+	key.page_match = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_locked_key(q, TASK_NORMAL, &key);
+	/*
+	 * It is possible for other pages to have collided on the waitqueue
+	 * hash, so in that case check for a page match. That prevents a long-
+	 * term waiter
+	 *
+	 * It is still possible to miss a case here, when we woke page waiters
+	 * and removed them from the waitqueue, but there are still other
+	 * page waiters.
+	 */
+	if (!waitqueue_active(q) || !key.page_match) {
+		ClearPageWaiters(page);
+		/*
+		 * It's possible to miss clearing Waiters here, when we woke
+		 * our page waiters, but the hashed waitqueue has waiters for
+		 * other pages on it.
+		 *
+		 * That's okay, it's a rare case. The next waker will clear it.
+		 */
+	}
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(wake_up_page_bit);
+
+static inline int wait_on_page_bit_common(wait_queue_head_t *q,
+		struct page *page, int bit_nr, int state, bool lock)
+{
+	struct wait_page_queue wait_page;
+	wait_queue_t *wait = &wait_page.wait;
+	int ret = 0;
+
+	init_wait(wait);
+	wait->func = wake_page_function;
+	wait_page.page = page;
+	wait_page.bit_nr = bit_nr;
+
+	for (;;) {
+		spin_lock_irq(&q->lock);
+
+		if (likely(list_empty(&wait->task_list))) {
+			if (lock)
+				__add_wait_queue_tail_exclusive(q, wait);
+			else
+				__add_wait_queue(q, wait);
+			SetPageWaiters(page);
+		}
+
+		set_current_state(state);
+
+		spin_unlock_irq(&q->lock);
+
+		if (likely(test_bit(bit_nr, &page->flags))) {
+			io_schedule();
+			if (unlikely(signal_pending_state(state, current))) {
+				ret = -EINTR;
+				break;
+			}
+		}
+
+		if (lock) {
+			if (!test_and_set_bit_lock(bit_nr, &page->flags))
+				break;
+		} else {
+			if (!test_bit(bit_nr, &page->flags))
+				break;
+		}
+	}
+
+	finish_wait(q, wait);
+
+	/*
+	 * A signal could leave PageWaiters set. Clearing it here if
+	 * !waitqueue_active would be possible (by open-coding finish_wait),
+	 * but still fail to catch it in the case of wait hash collision. We
+	 * already can fail to clear wait hash collision cases, so don't
+	 * bother with signals either.
+	 */
+
+	return ret;
+}
 
 void wait_on_page_bit(struct page *page, int bit_nr)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
-	if (test_bit(bit_nr, &page->flags))
-		__wait_on_bit(page_waitqueue(page), &wait, bit_wait_io,
-							TASK_UNINTERRUPTIBLE);
+	wait_queue_head_t *q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
 }
 EXPORT_SYMBOL(wait_on_page_bit);
 
 int wait_on_page_bit_killable(struct page *page, int bit_nr)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
-	if (!test_bit(bit_nr, &page->flags))
-		return 0;
-
-	return __wait_on_bit(page_waitqueue(page), &wait,
-			     bit_wait_io, TASK_KILLABLE);
+	wait_queue_head_t *q = page_waitqueue(page);
+	return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);
 }
 
-int wait_on_page_bit_killable_timeout(struct page *page,
-				       int bit_nr, unsigned long timeout)
-{
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
-	wait.key.timeout = jiffies + timeout;
-	if (!test_bit(bit_nr, &page->flags))
-		return 0;
-	return __wait_on_bit(page_waitqueue(page), &wait,
-			     bit_wait_io_timeout, TASK_KILLABLE);
-}
-EXPORT_SYMBOL_GPL(wait_on_page_bit_killable_timeout);
-
 /**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
  * @page: Page defining the wait queue of interest
@@ -793,10 +907,34 @@ void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
 
 	spin_lock_irqsave(&q->lock, flags);
 	__add_wait_queue(q, waiter);
+	SetPageWaiters(page);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL_GPL(add_page_wait_queue);
 
+#ifndef clear_bit_unlock_is_negative_byte
+
+/*
+ * PG_waiters is the high bit in the same byte as PG_lock.
+ *
+ * On x86 (and on many other architectures), we can clear PG_lock and
+ * test the sign bit at the same time. But if the architecture does
+ * not support that special operation, we just do this all by hand
+ * instead.
+ *
+ * The read of PG_waiters has to be after (or concurrently with) PG_locked
+ * being cleared, but a memory barrier should be unneccssary since it is
+ * in the same byte as PG_locked.
+ */
+static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
+{
+	clear_bit_unlock(nr, mem);
+	/* smp_mb__after_atomic(); */
+	return test_bit(PG_waiters, mem);
+}
+
+#endif
+
 /**
  * unlock_page - unlock a locked page
  * @page: the page
@@ -806,16 +944,19 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  * mechanism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
- * The mb is necessary to enforce ordering between the clear_bit and the read
- * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
+ * Note that this depends on PG_waiters being the sign bit in the byte
+ * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
+ * clear the PG_locked bit and test PG_waiters at the same time fairly
+ * portably (architectures that do LL/SC can test any bit, while x86 can
+ * test the sign bit).
  */
 void unlock_page(struct page *page)
 {
+	BUILD_BUG_ON(PG_waiters != 7);
 	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	clear_bit_unlock(PG_locked, &page->flags);
-	smp_mb__after_atomic();
-	wake_up_page(page, PG_locked);
+	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
+		wake_up_page_bit(page, PG_locked);
 }
 EXPORT_SYMBOL(unlock_page);
 
@@ -874,23 +1015,19 @@ EXPORT_SYMBOL_GPL(page_endio);
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock
  */
-void __lock_page(struct page *page)
+void __lock_page(struct page *__page)
 {
-	struct page *page_head = compound_head(page);
-	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
-
-	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
-							TASK_UNINTERRUPTIBLE);
+	struct page *page = compound_head(__page);
+	wait_queue_head_t *q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);
 }
 EXPORT_SYMBOL(__lock_page);
 
-int __lock_page_killable(struct page *page)
+int __lock_page_killable(struct page *__page)
 {
-	struct page *page_head = compound_head(page);
-	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
-
-	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
-					bit_wait_io, TASK_KILLABLE);
+	struct page *page = compound_head(__page);
+	wait_queue_head_t *q = page_waitqueue(page);
+	return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
diff --git a/mm/internal.h b/mm/internal.h
index 44d6889..7aa2ea0 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -36,6 +36,8 @@
 /* Do not use these with a slab allocator */
 #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
 
+void page_writeback_init(void);
+
 int do_swap_page(struct vm_fault *vmf);
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 175ec51..4048897 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -68,7 +68,7 @@
 #include <net/ip.h>
 #include "slab.h"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <trace/events/vmscan.h>
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 19e796d..f283c7e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -764,12 +764,11 @@ static int me_huge_page(struct page *p, unsigned long pfn)
  */
 
 #define dirty		(1UL << PG_dirty)
-#define sc		(1UL << PG_swapcache)
+#define sc		((1UL << PG_swapcache) | (1UL << PG_swapbacked))
 #define unevict		(1UL << PG_unevictable)
 #define mlock		(1UL << PG_mlocked)
 #define writeback	(1UL << PG_writeback)
 #define lru		(1UL << PG_lru)
-#define swapbacked	(1UL << PG_swapbacked)
 #define head		(1UL << PG_head)
 #define slab		(1UL << PG_slab)
 #define reserved	(1UL << PG_reserved)
@@ -819,7 +818,6 @@ static struct page_state {
 #undef mlock
 #undef writeback
 #undef lru
-#undef swapbacked
 #undef head
 #undef slab
 #undef reserved
diff --git a/mm/memory.c b/mm/memory.c
index 455c3e6..7d23b50 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -68,7 +68,7 @@
 #include <asm/io.h>
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/pgtable.h>
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 6d3639e..2e34664 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -96,7 +96,7 @@
 #include <linux/printk.h>
 
 #include <asm/tlbflush.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 0ed24b1..87f4d0f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -466,13 +466,15 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 */
 	newpage->index = page->index;
 	newpage->mapping = page->mapping;
-	if (PageSwapBacked(page))
-		__SetPageSwapBacked(newpage);
-
 	get_page(newpage);	/* add cache reference */
-	if (PageSwapCache(page)) {
-		SetPageSwapCache(newpage);
-		set_page_private(newpage, page_private(page));
+	if (PageSwapBacked(page)) {
+		__SetPageSwapBacked(newpage);
+		if (PageSwapCache(page)) {
+			SetPageSwapCache(newpage);
+			set_page_private(newpage, page_private(page));
+		}
+	} else {
+		VM_BUG_ON_PAGE(PageSwapCache(page), page);
 	}
 
 	/* Move dirty while page refs frozen and newpage not yet exposed */
diff --git a/mm/mincore.c b/mm/mincore.c
index bfb8664..ddb872d 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -16,7 +16,7 @@
 #include <linux/swapops.h>
 #include <linux/hugetlb.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 
 static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
diff --git a/mm/mmap.c b/mm/mmap.c
index 1af87c1..dc4291d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -45,7 +45,7 @@
 #include <linux/moduleparam.h>
 #include <linux/pkeys.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/tlb.h>
 #include <asm/mmu_context.h>
diff --git a/mm/mprotect.c b/mm/mprotect.c
index cc2459c..f9c07f5 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -25,7 +25,7 @@
 #include <linux/perf_event.h>
 #include <linux/pkeys.h>
 #include <linux/ksm.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
diff --git a/mm/nommu.c b/mm/nommu.c
index 210d7ec..24f9f5f 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -35,7 +35,7 @@
 #include <linux/audit.h>
 #include <linux/printk.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
diff --git a/mm/shmem.c b/mm/shmem.c
index b1b20dc..bb53285 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -71,7 +71,7 @@ static struct vfsmount *shm_mnt;
 #include <linux/fcntl.h>
 #include <uapi/linux/memfd.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 
 #include "internal.h"
diff --git a/mm/swap.c b/mm/swap.c
index 4dcf852..844baed 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -69,6 +69,7 @@ static void __page_cache_release(struct page *page)
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
 		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 	}
+	__ClearPageWaiters(page);
 	mem_cgroup_uncharge(page);
 }
 
@@ -784,6 +785,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 
 		/* Clear Active bit in case of parallel mark_page_accessed */
 		__ClearPageActive(page);
+		__ClearPageWaiters(page);
 
 		list_add(&page->lru, &pages_to_free);
 	}
diff --git a/mm/truncate.c b/mm/truncate.c
index fd97f1d..dd7b24e 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -24,20 +24,12 @@
 #include <linux/rmap.h>
 #include "internal.h"
 
-static void clear_exceptional_entry(struct address_space *mapping,
-				    pgoff_t index, void *entry)
+static void clear_shadow_entry(struct address_space *mapping, pgoff_t index,
+			       void *entry)
 {
 	struct radix_tree_node *node;
 	void **slot;
 
-	/* Handled by shmem itself */
-	if (shmem_mapping(mapping))
-		return;
-
-	if (dax_mapping(mapping)) {
-		dax_delete_mapping_entry(mapping, index);
-		return;
-	}
 	spin_lock_irq(&mapping->tree_lock);
 	/*
 	 * Regular page slots are stabilized by the page lock even
@@ -55,6 +47,56 @@ static void clear_exceptional_entry(struct address_space *mapping,
 	spin_unlock_irq(&mapping->tree_lock);
 }
 
+/*
+ * Unconditionally remove exceptional entry. Usually called from truncate path.
+ */
+static void truncate_exceptional_entry(struct address_space *mapping,
+				       pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	if (dax_mapping(mapping)) {
+		dax_delete_mapping_entry(mapping, index);
+		return;
+	}
+	clear_shadow_entry(mapping, index, entry);
+}
+
+/*
+ * Invalidate exceptional entry if easily possible. This handles exceptional
+ * entries for invalidate_inode_pages() so for DAX it evicts only unlocked and
+ * clean entries.
+ */
+static int invalidate_exceptional_entry(struct address_space *mapping,
+					pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return 1;
+	if (dax_mapping(mapping))
+		return dax_invalidate_mapping_entry(mapping, index);
+	clear_shadow_entry(mapping, index, entry);
+	return 1;
+}
+
+/*
+ * Invalidate exceptional entry if clean. This handles exceptional entries for
+ * invalidate_inode_pages2() so for DAX it evicts only clean entries.
+ */
+static int invalidate_exceptional_entry2(struct address_space *mapping,
+					 pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return 1;
+	if (dax_mapping(mapping))
+		return dax_invalidate_mapping_entry_sync(mapping, index);
+	clear_shadow_entry(mapping, index, entry);
+	return 1;
+}
+
 /**
  * do_invalidatepage - invalidate part or all of a page
  * @page: the page which is affected
@@ -262,7 +304,8 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				truncate_exceptional_entry(mapping, index,
+							   page);
 				continue;
 			}
 
@@ -351,7 +394,8 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			}
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				truncate_exceptional_entry(mapping, index,
+							   page);
 				continue;
 			}
 
@@ -470,7 +514,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				invalidate_exceptional_entry(mapping, index,
+							     page);
 				continue;
 			}
 
@@ -592,7 +637,9 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
-				clear_exceptional_entry(mapping, index, page);
+				if (!invalidate_exceptional_entry2(mapping,
+								   index, page))
+					ret = -EBUSY;
 				continue;
 			}
 
diff --git a/mm/util.c b/mm/util.c
index 1a41553..3cb2164 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -13,7 +13,7 @@
 #include <linux/vmalloc.h>
 
 #include <asm/sections.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "internal.h"
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a558438..3ca82d4 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -32,7 +32,7 @@
 #include <linux/llist.h>
 #include <linux/bitops.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
diff --git a/net/802/fc.c b/net/802/fc.c
index 7b92190..1bb496e 100644
--- a/net/802/fc.c
+++ b/net/802/fc.c
@@ -10,7 +10,7 @@
  *		v 1.0 03/22/99
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
diff --git a/net/802/hippi.c b/net/802/hippi.c
index 5e4427b..4460606 100644
--- a/net/802/hippi.c
+++ b/net/802/hippi.c
@@ -34,7 +34,7 @@
 #include <linux/errno.h>
 #include <net/arp.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * Create the HIPPI MAC header for an arbitrary protocol layer
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 691f0ad..467069b 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -34,7 +34,7 @@
 #include <net/rtnetlink.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/if_vlan.h>
 #include "vlan.h"
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 2fdebab..90fcf5f 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -32,7 +32,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>
diff --git a/net/ax25/ax25_addr.c b/net/ax25/ax25_addr.c
index e7c9b0e..ac2542b 100644
--- a/net/ax25/ax25_addr.c
+++ b/net/ax25/ax25_addr.c
@@ -21,7 +21,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index 3d10676..9a3a301 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -23,7 +23,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_ds_in.c b/net/ax25/ax25_ds_in.c
index 9bd31e8..891596e 100644
--- a/net/ax25/ax25_ds_in.c
+++ b/net/ax25/ax25_ds_in.c
@@ -22,7 +22,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_ds_subr.c b/net/ax25/ax25_ds_subr.c
index e05bd57..28827e8 100644
--- a/net/ax25/ax25_ds_subr.c
+++ b/net/ax25/ax25_ds_subr.c
@@ -23,7 +23,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 5237dff..5fb2104b 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -24,7 +24,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_iface.c b/net/ax25/ax25_iface.c
index 7f16e8a..8c07c28 100644
--- a/net/ax25/ax25_iface.c
+++ b/net/ax25/ax25_iface.c
@@ -23,7 +23,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c
index bb5a0e4..8607526 100644
--- a/net/ax25/ax25_in.c
+++ b/net/ax25/ax25_in.c
@@ -25,7 +25,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index 2fa3be9..183b1c5 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -23,7 +23,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>
diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c
index 8ddd41b..b11a5f4 100644
--- a/net/ax25/ax25_out.c
+++ b/net/ax25/ax25_out.c
@@ -25,7 +25,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index d390977..e1fda27 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -31,7 +31,7 @@
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_std_in.c b/net/ax25/ax25_std_in.c
index 3fbf8f7..8632b86 100644
--- a/net/ax25/ax25_std_in.c
+++ b/net/ax25/ax25_std_in.c
@@ -29,7 +29,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_std_subr.c b/net/ax25/ax25_std_subr.c
index 8b66a41..94bd063 100644
--- a/net/ax25/ax25_std_subr.c
+++ b/net/ax25/ax25_std_subr.c
@@ -20,7 +20,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_std_timer.c b/net/ax25/ax25_std_timer.c
index 2c0d6ef..30bbc67 100644
--- a/net/ax25/ax25_std_timer.c
+++ b/net/ax25/ax25_std_timer.c
@@ -24,7 +24,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 655a7d4..4855d18 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -25,7 +25,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_timer.c b/net/ax25/ax25_timer.c
index c3cffa7..23a6f38 100644
--- a/net/ax25/ax25_timer.c
+++ b/net/ax25/ax25_timer.c
@@ -28,7 +28,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c
index 4ad2fb7..0403b0d 100644
--- a/net/ax25/ax25_uid.c
+++ b/net/ax25/ax25_uid.c
@@ -25,7 +25,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index bca5ead..ed3b319 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -19,7 +19,7 @@
 #include <linux/list.h>
 #include <linux/netfilter_bridge.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "br_private.h"
 
 #define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index d99b200..da8157c 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/times.h>
 #include <net/net_namespace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "br_private.h"
 
 static int get_bridge_ifindices(struct net *net, int *indices, int num)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index b12501a..8ca6a92 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -40,7 +40,7 @@
 #include <net/netfilter/br_netfilter.h>
 #include <net/netns/generic.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "br_private.h"
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 5989661..96c072e 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -38,7 +38,7 @@
 #include <net/route.h>
 #include <net/netfilter/br_netfilter.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "br_private.h"
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 1ab6014..537e3d5 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -23,7 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <linux/cpumask.h>
 #include <linux/audit.h>
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 436a753..21ac753 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -199,11 +199,11 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 
 		seq_printf(m, "%c ", (op->flags & RX_CHECK_DLC) ? 'd' : ' ');
 
-		if (op->kt_ival1.tv64)
+		if (op->kt_ival1)
 			seq_printf(m, "timeo=%lld ",
 				   (long long)ktime_to_us(op->kt_ival1));
 
-		if (op->kt_ival2.tv64)
+		if (op->kt_ival2)
 			seq_printf(m, "thr=%lld ",
 				   (long long)ktime_to_us(op->kt_ival2));
 
@@ -226,11 +226,11 @@ static int bcm_proc_show(struct seq_file *m, void *v)
 		else
 			seq_printf(m, "[%u] ", op->nframes);
 
-		if (op->kt_ival1.tv64)
+		if (op->kt_ival1)
 			seq_printf(m, "t1=%lld ",
 				   (long long)ktime_to_us(op->kt_ival1));
 
-		if (op->kt_ival2.tv64)
+		if (op->kt_ival2)
 			seq_printf(m, "t2=%lld ",
 				   (long long)ktime_to_us(op->kt_ival2));
 
@@ -365,11 +365,11 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
 
 static void bcm_tx_start_timer(struct bcm_op *op)
 {
-	if (op->kt_ival1.tv64 && op->count)
+	if (op->kt_ival1 && op->count)
 		hrtimer_start(&op->timer,
 			      ktime_add(ktime_get(), op->kt_ival1),
 			      HRTIMER_MODE_ABS);
-	else if (op->kt_ival2.tv64)
+	else if (op->kt_ival2)
 		hrtimer_start(&op->timer,
 			      ktime_add(ktime_get(), op->kt_ival2),
 			      HRTIMER_MODE_ABS);
@@ -380,7 +380,7 @@ static void bcm_tx_timeout_tsklet(unsigned long data)
 	struct bcm_op *op = (struct bcm_op *)data;
 	struct bcm_msg_head msg_head;
 
-	if (op->kt_ival1.tv64 && (op->count > 0)) {
+	if (op->kt_ival1 && (op->count > 0)) {
 
 		op->count--;
 		if (!op->count && (op->flags & TX_COUNTEVT)) {
@@ -398,7 +398,7 @@ static void bcm_tx_timeout_tsklet(unsigned long data)
 		}
 		bcm_can_tx(op);
 
-	} else if (op->kt_ival2.tv64)
+	} else if (op->kt_ival2)
 		bcm_can_tx(op);
 
 	bcm_tx_start_timer(op);
@@ -459,7 +459,7 @@ static void bcm_rx_update_and_send(struct bcm_op *op,
 	lastdata->flags |= (RX_RECV|RX_THR);
 
 	/* throttling mode inactive ? */
-	if (!op->kt_ival2.tv64) {
+	if (!op->kt_ival2) {
 		/* send RX_CHANGED to the user immediately */
 		bcm_rx_changed(op, lastdata);
 		return;
@@ -470,7 +470,7 @@ static void bcm_rx_update_and_send(struct bcm_op *op,
 		return;
 
 	/* first reception with enabled throttling mode */
-	if (!op->kt_lastmsg.tv64)
+	if (!op->kt_lastmsg)
 		goto rx_changed_settime;
 
 	/* got a second frame inside a potential throttle period? */
@@ -537,7 +537,7 @@ static void bcm_rx_starttimer(struct bcm_op *op)
 	if (op->flags & RX_NO_AUTOTIMER)
 		return;
 
-	if (op->kt_ival1.tv64)
+	if (op->kt_ival1)
 		hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL);
 }
 
@@ -643,7 +643,7 @@ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer)
 		return HRTIMER_RESTART;
 	} else {
 		/* rearm throttle handling */
-		op->kt_lastmsg = ktime_set(0, 0);
+		op->kt_lastmsg = 0;
 		return HRTIMER_NORESTART;
 	}
 }
@@ -1005,7 +1005,7 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
 
 		/* disable an active timer due to zero values? */
-		if (!op->kt_ival1.tv64 && !op->kt_ival2.tv64)
+		if (!op->kt_ival1 && !op->kt_ival2)
 			hrtimer_cancel(&op->timer);
 	}
 
@@ -1189,19 +1189,19 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
 
 			/* disable an active timer due to zero value? */
-			if (!op->kt_ival1.tv64)
+			if (!op->kt_ival1)
 				hrtimer_cancel(&op->timer);
 
 			/*
 			 * In any case cancel the throttle timer, flush
 			 * potentially blocked msgs and reset throttle handling
 			 */
-			op->kt_lastmsg = ktime_set(0, 0);
+			op->kt_lastmsg = 0;
 			hrtimer_cancel(&op->thrtimer);
 			bcm_rx_thr_flush(op, 1);
 		}
 
-		if ((op->flags & STARTTIMER) && op->kt_ival1.tv64)
+		if ((op->flags & STARTTIMER) && op->kt_ival1)
 			hrtimer_start(&op->timer, op->kt_ival1,
 				      HRTIMER_MODE_REL);
 	}
diff --git a/net/can/gw.c b/net/can/gw.c
index 4551687..a54ab0c 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -429,7 +429,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
 
 	/* clear the skb timestamp if not configured the other way */
 	if (!(gwj->flags & CGW_FLAGS_CAN_SRC_TSTAMP))
-		nskb->tstamp.tv64 = 0;
+		nskb->tstamp = 0;
 
 	/* send to netdevice */
 	if (can_send(nskb, gwj->flags & CGW_FLAGS_CAN_ECHO))
diff --git a/net/compat.c b/net/compat.c
index 1cd2ec0..96c544b 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -28,7 +28,7 @@
 #include <net/sock.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/compat.h>
 
 int get_compat_msghdr(struct msghdr *kmsg,
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9482037..662bea5 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -36,7 +36,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/errno.h>
diff --git a/net/core/dev.c b/net/core/dev.c
index 6372117..8db5a0b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -72,7 +72,7 @@
  *				        - netif_rx() feedback
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -1731,14 +1731,14 @@ EXPORT_SYMBOL(net_disable_timestamp);
 
 static inline void net_timestamp_set(struct sk_buff *skb)
 {
-	skb->tstamp.tv64 = 0;
+	skb->tstamp = 0;
 	if (static_key_false(&netstamp_needed))
 		__net_timestamp(skb);
 }
 
 #define net_timestamp_check(COND, SKB)			\
 	if (static_key_false(&netstamp_needed)) {		\
-		if ((COND) && !(SKB)->tstamp.tv64)	\
+		if ((COND) && !(SKB)->tstamp)	\
 			__net_timestamp(SKB);		\
 	}						\
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 7190bd6..1969b3f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -40,7 +40,7 @@
 #include <net/flow_dissector.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/filter.h>
 #include <linux/ratelimit.h>
@@ -2972,12 +2972,6 @@ void bpf_warn_invalid_xdp_action(u32 act)
 }
 EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
 
-void bpf_warn_invalid_xdp_buffer(void)
-{
-	WARN_ONCE(1, "Illegal XDP buffer encountered, expect throughput degradation\n");
-}
-EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_buffer);
-
 static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg,
 					int src_reg, int ctx_off,
 					struct bpf_insn *insn_buf,
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 101b5d0..0385dec 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -14,7 +14,7 @@
  *              names to make it usable in general net subsystem.
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/types.h>
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 782dd86..7bb12e0 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -100,6 +100,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh)
 		neigh->parms->neigh_cleanup(neigh);
 
 	__neigh_notify(neigh, RTM_DELNEIGH, 0);
+	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
 	neigh_release(neigh);
 }
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c482491..18b5aae 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -40,7 +40,7 @@
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/inet.h>
 #include <linux/netdevice.h>
diff --git a/net/core/scm.c b/net/core/scm.c
index 2696aef..d882043 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -29,7 +29,7 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 65a74e1..5a03730 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -72,7 +72,7 @@
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <trace/events/skb.h>
 #include <linux/highmem.h>
 #include <linux/capability.h>
@@ -4368,7 +4368,7 @@ EXPORT_SYMBOL(skb_try_coalesce);
  */
 void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 {
-	skb->tstamp.tv64 = 0;
+	skb->tstamp = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
 	skb->ignore_df = 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 9fa46b9..f560e08 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -118,7 +118,7 @@
 #include <linux/memcontrol.h>
 #include <linux/prefetch.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/netdevice.h>
 #include <net/protocol.h>
diff --git a/net/core/utils.c b/net/core/utils.c
index cf5622b..6592d7b 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -31,7 +31,7 @@
 #include <net/net_ratelimit.h>
 
 #include <asm/byteorder.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10);
 /*
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 41f803e..8fdd9f4 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -42,7 +42,7 @@
 #include <linux/notifier.h>
 #include <linux/slab.h>
 #include <linux/jiffies.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/net_namespace.h>
 #include <net/neighbour.h>
 #include <net/dst.h>
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index a796fc7..7af0ba61 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -31,7 +31,7 @@
 #include <linux/timer.h>
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/neighbour.h>
 #include <net/dst.h>
 #include <net/flow.h>
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 1540b50..2326754 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -25,7 +25,7 @@
 #include <linux/timer.h>
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/route.h> /* RTF_xxx */
 #include <net/neighbour.h>
 #include <net/netlink.h>
diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c
index 5325b54..6c7da6c 100644
--- a/net/decnet/sysctl_net_decnet.c
+++ b/net/decnet/sysctl_net_decnet.c
@@ -22,7 +22,7 @@
 #include <net/dst.h>
 #include <net/flow.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/dn.h>
 #include <net/dn_dev.h>
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1830e6f..f750698 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -90,7 +90,7 @@
 #include <linux/random.h>
 #include <linux/slab.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/inet.h>
 #include <linux/igmp.h>
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 062a67c..4cd2ee8 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -26,7 +26,7 @@
  */
 
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/capability.h>
 #include <linux/module.h>
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index dbad5a1..3ff8938 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -14,7 +14,7 @@
  */
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/capability.h>
 #include <linux/types.h>
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c1bc1e9..7a5b4c7 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -13,7 +13,7 @@
  *		2 of the License, or (at your option) any later version.
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1b0e7d1..2919d1a 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -50,7 +50,7 @@
 
 #define VERSION "0.409"
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index f79d7a8..0777ea9 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -91,7 +91,7 @@
 #include <linux/errno.h>
 #include <linux/timer.h>
 #include <linux/init.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
 #include <net/inet_common.h>
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 15db786..68d6221 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -72,7 +72,7 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/jiffies.h>
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 78fd620..c9c1cb6 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -17,7 +17,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/in.h>
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 4d158ff..93157f2 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/skbuff.h>
 #include <linux/ip.h>
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6c9615c..fac275c4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -42,7 +42,7 @@
  *		Hirokazu Takahashi:	sendfile() on UDP works now.
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -958,7 +958,7 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+	if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
 	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8b13881..57e1405 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -44,7 +44,7 @@
 #include <net/ip_fib.h>
 
 #include <linux/errqueue.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  *	SOL_IP control messages.
@@ -148,7 +148,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 	__be16 *ports = (__be16 *)skb_transport_header(skb);
 
-	if (skb_transport_offset(skb) + 4 > skb->len)
+	if (skb_transport_offset(skb) + 4 > (int)skb->len)
 		return;
 
 	/* All current transport protocols have the port numbers in the
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 071a785..fd9f34b 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -61,7 +61,7 @@
 #include <net/ipconfig.h>
 #include <net/route.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/checksum.h>
 #include <asm/processor.h>
 
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 79489f0..00d4229 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -96,7 +96,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/in.h>
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 665505d..efc1e76 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -26,7 +26,7 @@
  *
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/types.h>
 #include <linux/capability.h>
 #include <linux/errno.h>
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 1258a9a..a467e12 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -24,7 +24,7 @@
 #include <linux/err.h>
 #include <net/compat.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_arp/arp_tables.h>
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 308b456..91656a1 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -20,7 +20,7 @@
 #include <linux/icmp.h>
 #include <net/ip.h>
 #include <net/compat.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mutex.h>
 #include <linux/proc_fs.h>
 #include <linux/err.h>
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 2300fae..4e49e5c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -41,7 +41,7 @@
 #include <linux/atomic.h>
 #include <asm/byteorder.h>
 #include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
 #include <linux/stddef.h>
 #include <linux/slab.h>
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fa5c037..a82a117 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -65,7 +65,7 @@
 #define pr_fmt(fmt) "IPv4: " fmt
 
 #include <linux/module.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -798,6 +798,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
 	struct rtable *rt;
 	struct flowi4 fl4;
 	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	struct net *net = dev_net(skb->dev);
 	int oif = skb->dev->ifindex;
 	u8 tos = RT_TOS(iph->tos);
 	u8 prot = iph->protocol;
@@ -805,7 +806,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
 
 	rt = (struct rtable *) dst;
 
-	__build_flow_key(sock_net(sk), &fl4, sk, iph, oif, tos, prot, mark, 0);
+	__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
 	__ip_do_redirect(rt, skb, &fl4, true);
 }
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 80bc36b..22cbd61 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -433,13 +433,6 @@ static struct ctl_table ipv4_table[] = {
 		.extra2		= &tcp_adv_win_scale_max,
 	},
 	{
-		.procname	= "tcp_tw_reuse",
-		.data		= &sysctl_tcp_tw_reuse,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "tcp_frto",
 		.data		= &sysctl_tcp_frto,
 		.maxlen		= sizeof(int),
@@ -960,6 +953,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tcp_tw_reuse",
+		.data		= &init_net.ipv4.sysctl_tcp_tw_reuse,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	{
 		.procname	= "fib_multipath_use_neigh",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1ef3165..4a04496 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -277,7 +277,7 @@
 #include <net/ip.h>
 #include <net/sock.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
 #include <net/busy_poll.h>
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30d81f5..fe9da4f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -84,7 +84,6 @@
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
-int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -120,7 +119,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	   and use initial timestamp retrieved from peer table.
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
-	    (!twp || (sysctl_tcp_tw_reuse &&
+	    (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse &&
 			     get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
 		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
 		if (tp->write_seq == 0)
@@ -2456,6 +2455,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_orphan_retries = 0;
 	net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
 	net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+	net->ipv4.sysctl_tcp_tw_reuse = 0;
 
 	return 0;
 fail:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b45101f..1d5331a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -769,6 +769,7 @@ static void tcp_tasklet_func(unsigned long data)
 		list_del(&tp->tsq_node);
 
 		sk = (struct sock *)tp;
+		smp_mb__before_atomic();
 		clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags);
 
 		if (!sk->sk_lock.owned &&
@@ -1037,7 +1038,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	skb_shinfo(skb)->gso_size = tcp_skb_mss(skb);
 
 	/* Our usage of tstamp should remain private */
-	skb->tstamp.tv64 = 0;
+	skb->tstamp = 0;
 
 	/* Cleanup our debris for IP stacks */
 	memset(skb->cb, 0, max(sizeof(struct inet_skb_parm),
@@ -3202,7 +3203,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 #endif
 
 	/* Do not fool tcpdump (if any), clean our debris */
-	skb->tstamp.tv64 = 0;
+	skb->tstamp = 0;
 	return skb;
 }
 EXPORT_SYMBOL(tcp_make_synack);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9ca279b..1307a7c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -79,7 +79,7 @@
 
 #define pr_fmt(fmt) "UDP: " fmt
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
 #include <linux/bootmem.h>
 #include <linux/highmem.h>
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 237e654..aa42123 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -63,7 +63,7 @@
 #include <net/calipso.h>
 #include <net/seg6.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mroute6.h>
 
 #include "ip6_offload.h"
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 0489e19..a3eaafd 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -33,7 +33,7 @@
 #include <net/dsfield.h>
 
 #include <linux/errqueue.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 {
@@ -701,7 +701,7 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 		struct sockaddr_in6 sin6;
 		__be16 *ports = (__be16 *) skb_transport_header(skb);
 
-		if (skb_transport_offset(skb) + 4 <= skb->len) {
+		if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 926818c..e419850 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -232,7 +232,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
 	ipv6h->saddr = hao->addr;
 	hao->addr = tmp_addr;
 
-	if (skb->tstamp.tv64 == 0)
+	if (skb->tstamp == 0)
 		__net_timestamp(skb);
 
 	return true;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 17fa28f..3036f66 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -70,7 +70,7 @@
 #include <net/dsfield.h>
 #include <net/l3mdev.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  *	The ICMP socket(s). This is the most convenient way to flow control
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index b912f0d..8081baf 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -29,7 +29,7 @@
 #include <net/rawv6.h>
 #include <net/transp_v6.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #define FL_MIN_LINGER	6	/* Minimal linger. It is set to 6sec specified
 				   in old IPv6 RFC. Well, it was reasonable value.
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 8b186b5..36d2921 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -42,7 +42,7 @@
 #include <linux/hash.h>
 #include <linux/etherdevice.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 
 #include <net/icmp.h>
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 52101b3..604d8953 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -16,7 +16,7 @@
  *
  */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 3ba5303..ee97c44 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -54,7 +54,7 @@
 #include <net/compat.h>
 #include <net/seg6.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 struct ip6_ra_chain *ip6_ra_chain;
 DEFINE_RWLOCK(ip6_ra_lock);
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 60c79a0..64f0f7b 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -191,7 +191,7 @@ static inline int mip6_report_rl_allow(ktime_t stamp,
 	int allow = 0;
 
 	spin_lock_bh(&mip6_report_rl.lock);
-	if (!ktime_equal(mip6_report_rl.stamp, stamp) ||
+	if (mip6_report_rl.stamp != stamp ||
 	    mip6_report_rl.iif != iif ||
 	    !ipv6_addr_equal(&mip6_report_rl.src, src) ||
 	    !ipv6_addr_equal(&mip6_report_rl.dst, dst)) {
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index d56d8ac..25a022d 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -24,7 +24,7 @@
 #include <linux/icmpv6.h>
 #include <net/ipv6.h>
 #include <net/compat.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/mutex.h>
 #include <linux/proc_fs.h>
 #include <linux/err.h>
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 291ebc2..ea89073 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -591,7 +591,11 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 	}
 
 	offset += skb_transport_offset(skb);
-	BUG_ON(skb_copy_bits(skb, offset, &csum, 2));
+	err = skb_copy_bits(skb, offset, &csum, 2);
+	if (err < 0) {
+		ip6_flush_pending_frames(sk);
+		goto out;
+	}
 
 	/* in case cksum was not initialized */
 	if (unlikely(csum))
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 890acac..8417c41 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -64,7 +64,7 @@
 #include <net/l3mdev.h>
 #include <trace/events/fib6.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0355231..fad992a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -31,7 +31,7 @@
 #include <linux/if_arp.h>
 #include <linux/icmp.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/init.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/if_ether.h>
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 649efc2..4d5c4ee 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -35,7 +35,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/addrconf.h>
 #include <net/ndisc.h>
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 48d0dc89b..8a9219f 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -56,7 +56,7 @@
 #include <net/tcp_states.h>
 #include <net/net_namespace.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* Configuration Variables */
 static unsigned char ipxcfg_max_hops = 16;
@@ -1809,7 +1809,7 @@ static int ipx_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	rc = skb_copy_datagram_msg(skb, sizeof(struct ipxhdr), msg, copied);
 	if (rc)
 		goto out_free;
-	if (skb->tstamp.tv64)
+	if (skb->tstamp)
 		sk->sk_stamp = skb->tstamp;
 
 	if (sipx) {
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 391c3cb..ab25404 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -52,7 +52,7 @@
 #include <linux/poll.h>
 
 #include <asm/ioctls.h>		/* TIOCOUTQ, TIOCINQ */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/sock.h>
 #include <net/tcp_states.h>
diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c
index 873c4b7..817b1b1 100644
--- a/net/irda/ircomm/ircomm_tty.c
+++ b/net/irda/ircomm/ircomm_tty.c
@@ -40,7 +40,7 @@
 #include <linux/interrupt.h>
 #include <linux/device.h>		/* for MODULE_ALIAS_CHARDEV_MAJOR */
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/irda/irda.h>
 #include <net/irda/irmod.h>
diff --git a/net/irda/ircomm/ircomm_tty_ioctl.c b/net/irda/ircomm/ircomm_tty_ioctl.c
index 8f5678c..f180701 100644
--- a/net/irda/ircomm/ircomm_tty_ioctl.c
+++ b/net/irda/ircomm/ircomm_tty_ioctl.c
@@ -32,7 +32,7 @@
 #include <linux/tty.h>
 #include <linux/serial.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/irda/irda.h>
 #include <net/irda/irmod.h>
diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c
index 8567366..890b90d0 100644
--- a/net/irda/irda_device.c
+++ b/net/irda/irda_device.c
@@ -43,7 +43,7 @@
 #include <linux/export.h>
 
 #include <asm/ioctls.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/dma.h>
 #include <asm/io.h>
 
diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h
index c69f0f3..9d451f8 100644
--- a/net/irda/irnet/irnet.h
+++ b/net/irda/irnet/irnet.h
@@ -249,7 +249,7 @@
 #include <linux/capability.h>
 #include <linux/ctype.h>	/* isspace() */
 #include <linux/string.h>	/* skip_spaces() */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/init.h>
 
 #include <linux/ppp_defs.h>
diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index fc60d9d..b50b64a 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -33,7 +33,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/lapb/lapb_in.c b/net/lapb/lapb_in.c
index 1824708..d5d2110 100644
--- a/net/lapb/lapb_in.c
+++ b/net/lapb/lapb_in.c
@@ -31,7 +31,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c
index 482c94d..eda726e 100644
--- a/net/lapb/lapb_out.c
+++ b/net/lapb/lapb_out.c
@@ -29,7 +29,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/lapb/lapb_subr.c b/net/lapb/lapb_subr.c
index 3c1914d..75efde3 100644
--- a/net/lapb/lapb_subr.c
+++ b/net/lapb/lapb_subr.c
@@ -28,7 +28,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c
index 355cc3b..1a5535b 100644
--- a/net/lapb/lapb_timer.c
+++ b/net/lapb/lapb_timer.c
@@ -29,7 +29,7 @@
 #include <linux/inet.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
diff --git a/net/mac802154/util.c b/net/mac802154/util.c
index f9fd095..7c03fb0 100644
--- a/net/mac802154/util.c
+++ b/net/mac802154/util.c
@@ -80,11 +80,11 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb,
 
 		if (skb->len > max_sifs_size)
 			hrtimer_start(&local->ifs_timer,
-				      ktime_set(0, hw->phy->lifs_period * NSEC_PER_USEC),
+				      hw->phy->lifs_period * NSEC_PER_USEC,
 				      HRTIMER_MODE_REL);
 		else
 			hrtimer_start(&local->ifs_timer,
-				      ktime_set(0, hw->phy->sifs_period * NSEC_PER_USEC),
+				      hw->phy->sifs_period * NSEC_PER_USEC,
 				      HRTIMER_MODE_REL);
 	} else {
 		ieee802154_wake_queue(hw);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 3d02b0c..55e0169 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -48,7 +48,7 @@
 #include <net/sock.h>
 #include <net/genetlink.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <net/ip_vs.h>
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 6a0bbfa..3a073cd 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -783,7 +783,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	/* set conntrack timestamp, if enabled. */
 	tstamp = nf_conn_tstamp_find(ct);
 	if (tstamp) {
-		if (skb->tstamp.tv64 == 0)
+		if (skb->tstamp == 0)
 			__net_timestamp(skb);
 
 		tstamp->start = ktime_to_ns(skb->tstamp);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 2278d9a..a09fa9f 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -22,7 +22,7 @@
 #include <linux/sockios.h>
 #include <linux/net.h>
 #include <linux/skbuff.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <net/sock.h>
 #include <linux/init.h>
 
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 200922b..08247bf 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -538,7 +538,7 @@ __build_packet_message(struct nfnl_log_net *log,
 			goto nla_put_failure;
 	}
 
-	if (skb->tstamp.tv64) {
+	if (skb->tstamp) {
 		struct nfulnl_msg_packet_timestamp ts;
 		struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
 		ts.sec = cpu_to_be64(kts.tv_sec);
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index be7627b..3ee0b8a 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -384,7 +384,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		+ nla_total_size(sizeof(u_int32_t))	/* skbinfo */
 		+ nla_total_size(sizeof(u_int32_t));	/* cap_len */
 
-	if (entskb->tstamp.tv64)
+	if (entskb->tstamp)
 		size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp));
 
 	size += nfqnl_get_bridge_size(entry);
@@ -555,7 +555,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	if (nfqnl_put_bridge(entry, skb) < 0)
 		goto nla_put_failure;
 
-	if (entskb->tstamp.tv64) {
+	if (entskb->tstamp) {
 		struct nfqnl_msg_packet_timestamp ts;
 		struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
 
diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c
index 0ae55a3..1b01eec 100644
--- a/net/netfilter/xt_time.c
+++ b/net/netfilter/xt_time.c
@@ -168,7 +168,7 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	 * may happen that the same packet matches both rules if
 	 * it arrived at the right moment before 13:00.
 	 */
-	if (skb->tstamp.tv64 == 0)
+	if (skb->tstamp == 0)
 		__net_timestamp((struct sk_buff *)skb);
 
 	stamp = ktime_to_ns(skb->tstamp);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 801d474..161b628 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -40,7 +40,7 @@
 #include <linux/net.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 2d4c4d3..9c62b63 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -606,7 +606,6 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	rcu_assign_pointer(flow->sf_acts, acts);
 	packet->priority = flow->key.phy.priority;
 	packet->mark = flow->key.phy.skb_mark;
-	packet->protocol = flow->key.eth.type;
 
 	rcu_read_lock();
 	dp = get_dp_rcu(net, ovs_header->dp_ifindex);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 08aa926..2c0a00f 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -312,7 +312,8 @@ static bool icmp6hdr_ok(struct sk_buff *skb)
  * Returns 0 if it encounters a non-vlan or incomplete packet.
  * Returns 1 after successfully parsing vlan tag.
  */
-static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
+static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
+			  bool untag_vlan)
 {
 	struct vlan_head *vh = (struct vlan_head *)skb->data;
 
@@ -330,7 +331,20 @@ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
 	key_vh->tci = vh->tci | htons(VLAN_TAG_PRESENT);
 	key_vh->tpid = vh->tpid;
 
-	__skb_pull(skb, sizeof(struct vlan_head));
+	if (unlikely(untag_vlan)) {
+		int offset = skb->data - skb_mac_header(skb);
+		u16 tci;
+		int err;
+
+		__skb_push(skb, offset);
+		err = __skb_vlan_pop(skb, &tci);
+		__skb_pull(skb, offset);
+		if (err)
+			return err;
+		__vlan_hwaccel_put_tag(skb, key_vh->tpid, tci);
+	} else {
+		__skb_pull(skb, sizeof(struct vlan_head));
+	}
 	return 1;
 }
 
@@ -351,13 +365,13 @@ static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 		key->eth.vlan.tpid = skb->vlan_proto;
 	} else {
 		/* Parse outer vlan tag in the non-accelerated case. */
-		res = parse_vlan_tag(skb, &key->eth.vlan);
+		res = parse_vlan_tag(skb, &key->eth.vlan, true);
 		if (res <= 0)
 			return res;
 	}
 
 	/* Parse inner vlan tag. */
-	res = parse_vlan_tag(skb, &key->eth.cvlan);
+	res = parse_vlan_tag(skb, &key->eth.cvlan, false);
 	if (res <= 0)
 		return res;
 
@@ -800,29 +814,15 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
 	if (err)
 		return err;
 
-	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
-		/* key_extract assumes that skb->protocol is set-up for
-		 * layer 3 packets which is the case for other callers,
-		 * in particular packets recieved from the network stack.
-		 * Here the correct value can be set from the metadata
-		 * extracted above.
-		 */
-		skb->protocol = key->eth.type;
-	} else {
-		struct ethhdr *eth;
+	/* key_extract assumes that skb->protocol is set-up for
+	 * layer 3 packets which is the case for other callers,
+	 * in particular packets received from the network stack.
+	 * Here the correct value can be set from the metadata
+	 * extracted above.
+	 * For L2 packet key eth type would be zero. skb protocol
+	 * would be set to correct value later during key-extact.
+	 */
 
-		skb_reset_mac_header(skb);
-		eth = eth_hdr(skb);
-
-		/* Normally, setting the skb 'protocol' field would be
-		 * handled by a call to eth_type_trans(), but it assumes
-		 * there's a sending device, which we may not have.
-		 */
-		if (eth_proto_is_802_3(eth->h_proto))
-			skb->protocol = eth->h_proto;
-		else
-			skb->protocol = htons(ETH_P_802_2);
-	}
-
+	skb->protocol = key->eth.type;
 	return key_extract(skb, key);
 }
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index d19044f..c87d359 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2195,6 +2195,7 @@ static int validate_set(const struct nlattr *a,
 	case OVS_KEY_ATTR_ETHERNET:
 		if (mac_proto != MAC_PROTO_ETHERNET)
 			return -EINVAL;
+		break;
 
 	case OVS_KEY_ATTR_TUNNEL:
 		if (masked)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 49cd0c7..b9e1a13 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -73,7 +73,7 @@
 #include <net/sock.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 4c93bad..ea96114 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -135,7 +135,7 @@ void rds_rdma_drop_keys(struct rds_sock *rs)
 	/* Release any MRs associated with this socket */
 	spin_lock_irqsave(&rs->rs_rdma_lock, flags);
 	while ((node = rb_first(&rs->rs_rdma_keys))) {
-		mr = container_of(node, struct rds_mr, r_rb_node);
+		mr = rb_entry(node, struct rds_mr, r_rb_node);
 		if (mr->r_trans == rs->rs_transport)
 			mr->r_invalidate = 0;
 		rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys);
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 129d357..9ad301c 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -34,7 +34,7 @@
 #include <linux/if_arp.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>
 #include <linux/mm.h>
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 0fc76d8..452bbb3 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -25,7 +25,7 @@
 #include <linux/skbuff.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/mm.h>
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 7af7125..e3a58e0 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -134,8 +134,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]);
 			daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]);
 
-			metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, 0,
-						      dst_port, TUNNEL_KEY,
+			metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port,
+						      0, TUNNEL_KEY,
 						      key_id, 0);
 		}
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3fbba79..1ecdf80 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -148,13 +148,15 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	unsigned long cl;
 	unsigned long fh;
 	int err;
-	int tp_created = 0;
+	int tp_created;
 
 	if ((n->nlmsg_type != RTM_GETTFILTER) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
+	tp_created = 0;
+
 	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
 	if (err < 0)
 		return err;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 35ac28d..333f8e2 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -442,32 +442,32 @@ static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
 	}
 }
 
-static void fl_set_key_flags(struct nlattr **tb,
-			     u32 *flags_key, u32 *flags_mask)
+static int fl_set_key_flags(struct nlattr **tb,
+			    u32 *flags_key, u32 *flags_mask)
 {
 	u32 key, mask;
 
-	if (!tb[TCA_FLOWER_KEY_FLAGS])
-		return;
+	/* mask is mandatory for flags */
+	if (!tb[TCA_FLOWER_KEY_FLAGS_MASK])
+		return -EINVAL;
 
 	key = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS]));
-
-	if (!tb[TCA_FLOWER_KEY_FLAGS_MASK])
-		mask = ~0;
-	else
-		mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK]));
+	mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK]));
 
 	*flags_key  = 0;
 	*flags_mask = 0;
 
 	fl_set_key_flag(key, mask, flags_key, flags_mask,
 			TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_IS_FRAGMENT);
+
+	return 0;
 }
 
 static int fl_set_key(struct net *net, struct nlattr **tb,
 		      struct fl_flow_key *key, struct fl_flow_key *mask)
 {
 	__be16 ethertype;
+	int ret = 0;
 #ifdef CONFIG_NET_CLS_IND
 	if (tb[TCA_FLOWER_INDEV]) {
 		int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]);
@@ -614,9 +614,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 		       &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
 		       sizeof(key->enc_tp.dst));
 
-	fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
+	if (tb[TCA_FLOWER_KEY_FLAGS])
+		ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
 
-	return 0;
+	return ret;
 }
 
 static bool fl_mask_eq(struct fl_flow_mask *mask1,
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 9ffe1c2..f120758 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -509,7 +509,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer)
 	if (delay) {
 		ktime_t time;
 
-		time = ktime_set(0, 0);
+		time = 0;
 		time = ktime_add_ns(time, PSCHED_TICKS2NS(now + delay));
 		hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS_PINNED);
 	}
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 86309a3..a4f738a 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -136,7 +136,7 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
 		struct fq_flow *aux;
 
 		parent = *p;
-		aux = container_of(parent, struct fq_flow, rate_node);
+		aux = rb_entry(parent, struct fq_flow, rate_node);
 		if (f->time_next_packet >= aux->time_next_packet)
 			p = &parent->rb_right;
 		else
@@ -188,7 +188,7 @@ static void fq_gc(struct fq_sched_data *q,
 	while (*p) {
 		parent = *p;
 
-		f = container_of(parent, struct fq_flow, fq_node);
+		f = rb_entry(parent, struct fq_flow, fq_node);
 		if (f->sk == sk)
 			break;
 
@@ -256,7 +256,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 	while (*p) {
 		parent = *p;
 
-		f = container_of(parent, struct fq_flow, fq_node);
+		f = rb_entry(parent, struct fq_flow, fq_node);
 		if (f->sk == sk) {
 			/* socket might have been reallocated, so check
 			 * if its sk_hash is the same.
@@ -424,7 +424,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
 
 	q->time_next_delayed_flow = ~0ULL;
 	while ((p = rb_first(&q->delayed)) != NULL) {
-		struct fq_flow *f = container_of(p, struct fq_flow, rate_node);
+		struct fq_flow *f = rb_entry(p, struct fq_flow, rate_node);
 
 		if (f->time_next_packet > now) {
 			q->time_next_delayed_flow = f->time_next_packet;
@@ -563,7 +563,7 @@ static void fq_reset(struct Qdisc *sch)
 	for (idx = 0; idx < (1U << q->fq_trees_log); idx++) {
 		root = &q->fq_root[idx];
 		while ((p = rb_first(root)) != NULL) {
-			f = container_of(p, struct fq_flow, fq_node);
+			f = rb_entry(p, struct fq_flow, fq_node);
 			rb_erase(p, root);
 
 			fq_flow_purge(f);
@@ -593,7 +593,7 @@ static void fq_rehash(struct fq_sched_data *q,
 		oroot = &old_array[idx];
 		while ((op = rb_first(oroot)) != NULL) {
 			rb_erase(op, oroot);
-			of = container_of(op, struct fq_flow, fq_node);
+			of = rb_entry(op, struct fq_flow, fq_node);
 			if (fq_gc_candidate(of)) {
 				fcnt++;
 				kmem_cache_free(fq_flow_cachep, of);
@@ -606,7 +606,7 @@ static void fq_rehash(struct fq_sched_data *q,
 			while (*np) {
 				parent = *np;
 
-				nf = container_of(parent, struct fq_flow, fq_node);
+				nf = rb_entry(parent, struct fq_flow, fq_node);
 				BUG_ON(nf->sk == of->sk);
 
 				if (nf->sk > of->sk)
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 9f7b380..bcfadfd 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -152,7 +152,7 @@ struct netem_skb_cb {
 
 static struct sk_buff *netem_rb_to_skb(struct rb_node *rb)
 {
-	return container_of(rb, struct sk_buff, rbnode);
+	return rb_entry(rb, struct sk_buff, rbnode);
 }
 
 static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb)
@@ -627,7 +627,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 			 * from the network (tstamp will be updated).
 			 */
 			if (G_TC_FROM(skb->tc_verd) & AT_INGRESS)
-				skb->tstamp.tv64 = 0;
+				skb->tstamp = 0;
 #endif
 
 			if (q->qdisc) {
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 68428e1..d3cc30c 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1471,7 +1471,7 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
 	 * threshold.  The idea is to recover slowly, but up
 	 * to the initial advertised window.
 	 */
-	if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) {
+	if (asoc->rwnd_press) {
 		int change = min(asoc->pathmtu, asoc->rwnd_press);
 		asoc->rwnd += change;
 		asoc->rwnd_press -= change;
@@ -1539,7 +1539,7 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
 			asoc->rwnd = 0;
 		}
 	} else {
-		asoc->rwnd_over = len - asoc->rwnd;
+		asoc->rwnd_over += len - asoc->rwnd;
 		asoc->rwnd = 0;
 	}
 
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 401c607..1ebc184 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -292,6 +292,8 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list,
 		}
 
 		af->from_addr_param(&addr, rawaddr, htons(port), 0);
+		if (sctp_bind_addr_state(bp, &addr) != -1)
+			goto next;
 		retval = sctp_add_bind_addr(bp, &addr, sizeof(addr),
 					    SCTP_ADDR_SRC, gfp);
 		if (retval) {
@@ -300,6 +302,7 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list,
 			break;
 		}
 
+next:
 		len = ntohs(param->length);
 		addrs_len -= len;
 		raw_addr_list += len;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 176af30..5ed8e79 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -71,7 +71,7 @@
 #include <net/inet_ecn.h>
 #include <net/sctp/sctp.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 static inline int sctp_v6_addr_match_len(union sctp_addr *s1,
 					 union sctp_addr *s2);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 7b523e3..616a942 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -205,26 +205,30 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 	list_for_each_entry_rcu(addr, &net->sctp.local_addr_list, list) {
 		if (!addr->valid)
 			continue;
-		if (sctp_in_scope(net, &addr->a, scope)) {
-			/* Now that the address is in scope, check to see if
-			 * the address type is really supported by the local
-			 * sock as well as the remote peer.
-			 */
-			if ((((AF_INET == addr->a.sa.sa_family) &&
-			      (copy_flags & SCTP_ADDR4_PEERSUPP))) ||
-			    (((AF_INET6 == addr->a.sa.sa_family) &&
-			      (copy_flags & SCTP_ADDR6_ALLOWED) &&
-			      (copy_flags & SCTP_ADDR6_PEERSUPP)))) {
-				error = sctp_add_bind_addr(bp, &addr->a,
-						    sizeof(addr->a),
-						    SCTP_ADDR_SRC, GFP_ATOMIC);
-				if (error)
-					goto end_copy;
-			}
-		}
+		if (!sctp_in_scope(net, &addr->a, scope))
+			continue;
+
+		/* Now that the address is in scope, check to see if
+		 * the address type is really supported by the local
+		 * sock as well as the remote peer.
+		 */
+		if (addr->a.sa.sa_family == AF_INET &&
+		    !(copy_flags & SCTP_ADDR4_PEERSUPP))
+			continue;
+		if (addr->a.sa.sa_family == AF_INET6 &&
+		    (!(copy_flags & SCTP_ADDR6_ALLOWED) ||
+		     !(copy_flags & SCTP_ADDR6_PEERSUPP)))
+			continue;
+
+		if (sctp_bind_addr_state(bp, &addr->a) != -1)
+			continue;
+
+		error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a),
+					   SCTP_ADDR_SRC, GFP_ATOMIC);
+		if (error)
+			break;
 	}
 
-end_copy:
 	rcu_read_unlock();
 	return error;
 }
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index ce54dce..a1652ab 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -72,7 +72,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net,
 	 */
 	peer->rto = msecs_to_jiffies(net->sctp.rto_initial);
 
-	peer->last_time_heard = ktime_set(0, 0);
+	peer->last_time_heard = 0;
 	peer->last_time_ecne_reduced = jiffies;
 
 	peer->param_flags = SPP_HB_DISABLE |
diff --git a/net/socket.c b/net/socket.c
index dc01d7b..8487bf1 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -90,7 +90,7 @@
 #include <linux/slab.h>
 #include <linux/xattr.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/unistd.h>
 
 #include <net/compat.h>
@@ -668,7 +668,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 
 	/* Race occurred between timestamp enabling and packet
 	   receiving.  Fill in the current time for now. */
-	if (need_software_tstamp && skb->tstamp.tv64 == 0)
+	if (need_software_tstamp && skb->tstamp == 0)
 		__net_timestamp(skb);
 
 	if (need_software_tstamp) {
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 16cea00..cdeb1d8 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -50,7 +50,7 @@
 #include <linux/workqueue.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/sunrpc/gss_api.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/hashtable.h>
 
 #include "../netns.h"
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 8aabe12..8147e8d 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -21,7 +21,7 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/string_helpers.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/poll.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 135ec2c..de066ac 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -42,7 +42,7 @@
 #include <net/udp.h>
 #include <net/tcp.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
 #include <trace/events/skb.h>
 
@@ -574,7 +574,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 	}
 	len = svc_addr_len(svc_addr(rqstp));
 	rqstp->rq_addrlen = len;
-	if (skb->tstamp.tv64 == 0) {
+	if (skb->tstamp == 0) {
 		skb->tstamp = ktime_get_real();
 		/* Don't enable netstamp, sunrpc doesn't
 		   need that much accuracy */
diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c
index c88d9bc..8c39364 100644
--- a/net/sunrpc/sysctl.c
+++ b/net/sunrpc/sysctl.c
@@ -14,7 +14,7 @@
 #include <linux/sysctl.h>
 #include <linux/module.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/stats.h>
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 333c5da..800caaa 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -441,15 +441,19 @@ static void __tipc_shutdown(struct socket *sock, int error)
 	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
 		if (TIPC_SKB_CB(skb)->bytes_read) {
 			kfree_skb(skb);
-		} else {
-			if (!tipc_sk_type_connectionless(sk) &&
-			    sk->sk_state != TIPC_DISCONNECTING) {
-				tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-				tipc_node_remove_conn(net, dnode, tsk->portid);
-			}
-			tipc_sk_respond(sk, skb, error);
+			continue;
 		}
+		if (!tipc_sk_type_connectionless(sk) &&
+		    sk->sk_state != TIPC_DISCONNECTING) {
+			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+			tipc_node_remove_conn(net, dnode, tsk->portid);
+		}
+		tipc_sk_respond(sk, skb, error);
 	}
+
+	if (tipc_sk_type_connectionless(sk))
+		return;
+
 	if (sk->sk_state != TIPC_DISCONNECTING) {
 		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
 				      TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
@@ -457,10 +461,8 @@ static void __tipc_shutdown(struct socket *sock, int error)
 				      tsk->portid, error);
 		if (skb)
 			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
-		if (!tipc_sk_type_connectionless(sk)) {
-			tipc_node_remove_conn(net, dnode, tsk->portid);
-			tipc_set_sk_state(sk, TIPC_DISCONNECTING);
-		}
+		tipc_node_remove_conn(net, dnode, tsk->portid);
+		tipc_set_sk_state(sk, TIPC_DISCONNECTING);
 	}
 }
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 310882f..127656e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -100,7 +100,7 @@
 #include <linux/in.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <net/net_namespace.h>
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index f83b74d..079c883 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -51,7 +51,7 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/fcntl.h>
 #include <linux/termios.h>	/* For TIOCINQ/OUTQ */
 #include <linux/notifier.h>
diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c
index fd5ffb2..bcaa180 100644
--- a/net/x25/x25_link.c
+++ b/net/x25/x25_link.c
@@ -29,7 +29,7 @@
 #include <linux/slab.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/init.h>
 #include <net/x25.h>
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 45cb7c6..64e3c82 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -20,7 +20,7 @@
 #include <linux/module.h>
 #include <linux/cache.h>
 #include <linux/audit.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/ktime.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
@@ -1404,7 +1404,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL);
+		tasklet_hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL);
 		return -EINVAL;
 	}
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 671a1d0..9705c27 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -27,7 +27,7 @@
 #include <net/xfrm.h>
 #include <net/netlink.h>
 #include <net/ah.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <linux/in6.h>
 #endif
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 13315ff..09e9d53 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -35,40 +35,43 @@
 hostprogs-y += lwt_len_hist
 hostprogs-y += xdp_tx_iptunnel
 
-test_lru_dist-objs := test_lru_dist.o libbpf.o
-sock_example-objs := sock_example.o libbpf.o
-fds_example-objs := bpf_load.o libbpf.o fds_example.o
-sockex1-objs := bpf_load.o libbpf.o sockex1_user.o
-sockex2-objs := bpf_load.o libbpf.o sockex2_user.o
-sockex3-objs := bpf_load.o libbpf.o sockex3_user.o
-tracex1-objs := bpf_load.o libbpf.o tracex1_user.o
-tracex2-objs := bpf_load.o libbpf.o tracex2_user.o
-tracex3-objs := bpf_load.o libbpf.o tracex3_user.o
-tracex4-objs := bpf_load.o libbpf.o tracex4_user.o
-tracex5-objs := bpf_load.o libbpf.o tracex5_user.o
-tracex6-objs := bpf_load.o libbpf.o tracex6_user.o
-test_probe_write_user-objs := bpf_load.o libbpf.o test_probe_write_user_user.o
-trace_output-objs := bpf_load.o libbpf.o trace_output_user.o
-lathist-objs := bpf_load.o libbpf.o lathist_user.o
-offwaketime-objs := bpf_load.o libbpf.o offwaketime_user.o
-spintest-objs := bpf_load.o libbpf.o spintest_user.o
-map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o
-test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o
-test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
-test_cgrp2_attach-objs := libbpf.o test_cgrp2_attach.o
-test_cgrp2_attach2-objs := libbpf.o test_cgrp2_attach2.o cgroup_helpers.o
-test_cgrp2_sock-objs := libbpf.o test_cgrp2_sock.o
-test_cgrp2_sock2-objs := bpf_load.o libbpf.o test_cgrp2_sock2.o
-xdp1-objs := bpf_load.o libbpf.o xdp1_user.o
+# Libbpf dependencies
+LIBBPF := ../../tools/lib/bpf/bpf.o
+
+test_lru_dist-objs := test_lru_dist.o $(LIBBPF)
+sock_example-objs := sock_example.o $(LIBBPF)
+fds_example-objs := bpf_load.o $(LIBBPF) fds_example.o
+sockex1-objs := bpf_load.o $(LIBBPF) sockex1_user.o
+sockex2-objs := bpf_load.o $(LIBBPF) sockex2_user.o
+sockex3-objs := bpf_load.o $(LIBBPF) sockex3_user.o
+tracex1-objs := bpf_load.o $(LIBBPF) tracex1_user.o
+tracex2-objs := bpf_load.o $(LIBBPF) tracex2_user.o
+tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
+tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
+tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
+tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
+test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
+trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
+lathist-objs := bpf_load.o $(LIBBPF) lathist_user.o
+offwaketime-objs := bpf_load.o $(LIBBPF) offwaketime_user.o
+spintest-objs := bpf_load.o $(LIBBPF) spintest_user.o
+map_perf_test-objs := bpf_load.o $(LIBBPF) map_perf_test_user.o
+test_overhead-objs := bpf_load.o $(LIBBPF) test_overhead_user.o
+test_cgrp2_array_pin-objs := $(LIBBPF) test_cgrp2_array_pin.o
+test_cgrp2_attach-objs := $(LIBBPF) test_cgrp2_attach.o
+test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o cgroup_helpers.o
+test_cgrp2_sock-objs := $(LIBBPF) test_cgrp2_sock.o
+test_cgrp2_sock2-objs := bpf_load.o $(LIBBPF) test_cgrp2_sock2.o
+xdp1-objs := bpf_load.o $(LIBBPF) xdp1_user.o
 # reuse xdp1 source intentionally
-xdp2-objs := bpf_load.o libbpf.o xdp1_user.o
-test_current_task_under_cgroup-objs := bpf_load.o libbpf.o cgroup_helpers.o \
+xdp2-objs := bpf_load.o $(LIBBPF) xdp1_user.o
+test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) cgroup_helpers.o \
 				       test_current_task_under_cgroup_user.o
-trace_event-objs := bpf_load.o libbpf.o trace_event_user.o
-sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
-tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o
-lwt_len_hist-objs := bpf_load.o libbpf.o lwt_len_hist_user.o
-xdp_tx_iptunnel-objs := bpf_load.o libbpf.o xdp_tx_iptunnel_user.o
+trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o
+sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o
+tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o
+lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o
+xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -104,7 +107,10 @@
 always += xdp_tx_iptunnel_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
+HOSTCFLAGS += -I$(srctree)/tools/lib/
 HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
+HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
+HOSTCFLAGS += -I$(srctree)/tools/perf
 
 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
 HOSTLOADLIBES_fds_example += -lelf
diff --git a/samples/bpf/README.rst b/samples/bpf/README.rst
index a43eae3..79f9a58 100644
--- a/samples/bpf/README.rst
+++ b/samples/bpf/README.rst
@@ -1,8 +1,8 @@
 eBPF sample programs
 ====================
 
-This directory contains a mini eBPF library, test stubs, verifier
-test-suite and examples for using eBPF.
+This directory contains a test stubs, verifier test-suite and examples
+for using eBPF. The examples use libbpf from tools/lib/bpf.
 
 Build dependencies
 ==================
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index e30b6de..396e204 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -22,25 +22,34 @@
 #include <poll.h>
 #include <ctype.h>
 #include "libbpf.h"
-#include "bpf_helpers.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 #define DEBUGFS "/sys/kernel/debug/tracing/"
 
 static char license[128];
 static int kern_version;
 static bool processed_sec[128];
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
 int map_fd[MAX_MAPS];
 int prog_fd[MAX_PROGS];
 int event_fd[MAX_PROGS];
 int prog_cnt;
 int prog_array_fd = -1;
 
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+};
+
 static int populate_prog_array(const char *event, int prog_fd)
 {
 	int ind = atoi(event), err;
 
-	err = bpf_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY);
+	err = bpf_map_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY);
 	if (err < 0) {
 		printf("failed to store prog_fd in prog_array\n");
 		return -1;
@@ -58,6 +67,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
 	bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0;
 	bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0;
+	size_t insns_cnt = size / sizeof(struct bpf_insn);
 	enum bpf_prog_type prog_type;
 	char buf[256];
 	int fd, efd, err, id;
@@ -87,9 +97,10 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		return -1;
 	}
 
-	fd = bpf_prog_load(prog_type, prog, size, license, kern_version);
+	fd = bpf_load_program(prog_type, prog, insns_cnt, license, kern_version,
+			      bpf_log_buf, BPF_LOG_BUF_SIZE);
 	if (fd < 0) {
-		printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
+		printf("bpf_load_program() err=%d\n%s", errno, bpf_log_buf);
 		return -1;
 	}
 
@@ -169,7 +180,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	id = atoi(buf);
 	attr.config = id;
 
-	efd = perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
+	efd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
 	if (efd < 0) {
 		printf("event %d fd %d err %s\n", id, efd, strerror(errno));
 		return -1;
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index fb46a42..c827827 100644
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -1,12 +1,15 @@
 #ifndef __BPF_LOAD_H
 #define __BPF_LOAD_H
 
+#include "libbpf.h"
+
 #define MAX_MAPS 32
 #define MAX_PROGS 32
 
 extern int map_fd[MAX_MAPS];
 extern int prog_fd[MAX_PROGS];
 extern int event_fd[MAX_PROGS];
+extern char bpf_log_buf[BPF_LOG_BUF_SIZE];
 extern int prog_cnt;
 
 /* parses elf file compiled by llvm .c->.o
diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c
index 625e797..e29bd52 100644
--- a/samples/bpf/fds_example.c
+++ b/samples/bpf/fds_example.c
@@ -14,6 +14,7 @@
 
 #include "bpf_load.h"
 #include "libbpf.h"
+#include "sock_example.h"
 
 #define BPF_F_PIN	(1 << 0)
 #define BPF_F_GET	(1 << 1)
@@ -49,17 +50,19 @@ static int bpf_map_create(void)
 
 static int bpf_prog_create(const char *object)
 {
-	static const struct bpf_insn insns[] = {
+	static struct bpf_insn insns[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 1),
 		BPF_EXIT_INSN(),
 	};
+	size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn);
 
 	if (object) {
 		assert(!load_bpf_file((char *)object));
 		return prog_fd[0];
 	} else {
-		return bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER,
-				     insns, sizeof(insns), "GPL", 0);
+		return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER,
+					insns, insns_cnt, "GPL", 0,
+					bpf_log_buf, BPF_LOG_BUF_SIZE);
 	}
 }
 
@@ -83,12 +86,12 @@ static int bpf_do_map(const char *file, uint32_t flags, uint32_t key,
 	}
 
 	if ((flags & BPF_F_KEY_VAL) == BPF_F_KEY_VAL) {
-		ret = bpf_update_elem(fd, &key, &value, 0);
+		ret = bpf_map_update_elem(fd, &key, &value, 0);
 		printf("bpf: fd:%d u->(%u:%u) ret:(%d,%s)\n", fd, key, value,
 		       ret, strerror(errno));
 		assert(ret == 0);
 	} else if (flags & BPF_F_KEY) {
-		ret = bpf_lookup_elem(fd, &key, &value);
+		ret = bpf_map_lookup_elem(fd, &key, &value);
 		printf("bpf: fd:%d l->(%u):%u ret:(%d,%s)\n", fd, key, value,
 		       ret, strerror(errno));
 		assert(ret == 0);
diff --git a/samples/bpf/lathist_user.c b/samples/bpf/lathist_user.c
index 65da8c1..6477bad 100644
--- a/samples/bpf/lathist_user.c
+++ b/samples/bpf/lathist_user.c
@@ -73,7 +73,7 @@ static void get_data(int fd)
 	for (c = 0; c < MAX_CPU; c++) {
 		for (i = 0; i < MAX_ENTRIES; i++) {
 			key = c * MAX_ENTRIES + i;
-			bpf_lookup_elem(fd, &key, &value);
+			bpf_map_lookup_elem(fd, &key, &value);
 
 			cpu_hist[c].data[i] = value;
 			if (value > cpu_hist[c].max)
diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c
deleted file mode 100644
index 9ce707b..0000000
--- a/samples/bpf/libbpf.c
+++ /dev/null
@@ -1,176 +0,0 @@
-/* eBPF mini library */
-#include <stdlib.h>
-#include <stdio.h>
-#include <linux/unistd.h>
-#include <unistd.h>
-#include <string.h>
-#include <linux/netlink.h>
-#include <linux/bpf.h>
-#include <errno.h>
-#include <net/ethernet.h>
-#include <net/if.h>
-#include <linux/if_packet.h>
-#include <arpa/inet.h>
-#include "libbpf.h"
-
-static __u64 ptr_to_u64(void *ptr)
-{
-	return (__u64) (unsigned long) ptr;
-}
-
-int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries, int map_flags)
-{
-	union bpf_attr attr = {
-		.map_type = map_type,
-		.key_size = key_size,
-		.value_size = value_size,
-		.max_entries = max_entries,
-		.map_flags = map_flags,
-	};
-
-	return syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
-}
-
-int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags)
-{
-	union bpf_attr attr = {
-		.map_fd = fd,
-		.key = ptr_to_u64(key),
-		.value = ptr_to_u64(value),
-		.flags = flags,
-	};
-
-	return syscall(__NR_bpf, BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
-}
-
-int bpf_lookup_elem(int fd, void *key, void *value)
-{
-	union bpf_attr attr = {
-		.map_fd = fd,
-		.key = ptr_to_u64(key),
-		.value = ptr_to_u64(value),
-	};
-
-	return syscall(__NR_bpf, BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
-}
-
-int bpf_delete_elem(int fd, void *key)
-{
-	union bpf_attr attr = {
-		.map_fd = fd,
-		.key = ptr_to_u64(key),
-	};
-
-	return syscall(__NR_bpf, BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
-}
-
-int bpf_get_next_key(int fd, void *key, void *next_key)
-{
-	union bpf_attr attr = {
-		.map_fd = fd,
-		.key = ptr_to_u64(key),
-		.next_key = ptr_to_u64(next_key),
-	};
-
-	return syscall(__NR_bpf, BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
-}
-
-#define ROUND_UP(x, n) (((x) + (n) - 1u) & ~((n) - 1u))
-
-char bpf_log_buf[LOG_BUF_SIZE];
-
-int bpf_prog_load(enum bpf_prog_type prog_type,
-		  const struct bpf_insn *insns, int prog_len,
-		  const char *license, int kern_version)
-{
-	union bpf_attr attr = {
-		.prog_type = prog_type,
-		.insns = ptr_to_u64((void *) insns),
-		.insn_cnt = prog_len / sizeof(struct bpf_insn),
-		.license = ptr_to_u64((void *) license),
-		.log_buf = ptr_to_u64(bpf_log_buf),
-		.log_size = LOG_BUF_SIZE,
-		.log_level = 1,
-	};
-
-	/* assign one field outside of struct init to make sure any
-	 * padding is zero initialized
-	 */
-	attr.kern_version = kern_version;
-
-	bpf_log_buf[0] = 0;
-
-	return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
-}
-
-int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
-{
-	union bpf_attr attr = {
-		.target_fd = target_fd,
-		.attach_bpf_fd = prog_fd,
-		.attach_type = type,
-	};
-
-	return syscall(__NR_bpf, BPF_PROG_ATTACH, &attr, sizeof(attr));
-}
-
-int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
-{
-	union bpf_attr attr = {
-		.target_fd = target_fd,
-		.attach_type = type,
-	};
-
-	return syscall(__NR_bpf, BPF_PROG_DETACH, &attr, sizeof(attr));
-}
-
-int bpf_obj_pin(int fd, const char *pathname)
-{
-	union bpf_attr attr = {
-		.pathname	= ptr_to_u64((void *)pathname),
-		.bpf_fd		= fd,
-	};
-
-	return syscall(__NR_bpf, BPF_OBJ_PIN, &attr, sizeof(attr));
-}
-
-int bpf_obj_get(const char *pathname)
-{
-	union bpf_attr attr = {
-		.pathname	= ptr_to_u64((void *)pathname),
-	};
-
-	return syscall(__NR_bpf, BPF_OBJ_GET, &attr, sizeof(attr));
-}
-
-int open_raw_sock(const char *name)
-{
-	struct sockaddr_ll sll;
-	int sock;
-
-	sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL));
-	if (sock < 0) {
-		printf("cannot create raw socket\n");
-		return -1;
-	}
-
-	memset(&sll, 0, sizeof(sll));
-	sll.sll_family = AF_PACKET;
-	sll.sll_ifindex = if_nametoindex(name);
-	sll.sll_protocol = htons(ETH_P_ALL);
-	if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) {
-		printf("bind to %s: %s\n", name, strerror(errno));
-		close(sock);
-		return -1;
-	}
-
-	return sock;
-}
-
-int perf_event_open(struct perf_event_attr *attr, int pid, int cpu,
-		    int group_fd, unsigned long flags)
-{
-	return syscall(__NR_perf_event_open, attr, pid, cpu,
-		       group_fd, flags);
-}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index 94a901d..3705fba 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -2,28 +2,10 @@
 #ifndef __LIBBPF_H
 #define __LIBBPF_H
 
+#include <bpf/bpf.h>
+
 struct bpf_insn;
 
-int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries, int map_flags);
-int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags);
-int bpf_lookup_elem(int fd, void *key, void *value);
-int bpf_delete_elem(int fd, void *key);
-int bpf_get_next_key(int fd, void *key, void *next_key);
-
-int bpf_prog_load(enum bpf_prog_type prog_type,
-		  const struct bpf_insn *insns, int insn_len,
-		  const char *license, int kern_version);
-
-int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type);
-int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
-
-int bpf_obj_pin(int fd, const char *pathname);
-int bpf_obj_get(const char *pathname);
-
-#define LOG_BUF_SIZE (256 * 1024)
-extern char bpf_log_buf[LOG_BUF_SIZE];
-
 /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
 
 #define BPF_ALU64_REG(OP, DST, SRC)				\
@@ -203,10 +185,4 @@ extern char bpf_log_buf[LOG_BUF_SIZE];
 		.off   = 0,					\
 		.imm   = 0 })
 
-/* create RAW socket and bind to interface 'name' */
-int open_raw_sock(const char *name);
-
-struct perf_event_attr;
-int perf_event_open(struct perf_event_attr *attr, int pid, int cpu,
-		    int group_fd, unsigned long flags);
 #endif
diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c
index 05d783f..ec8f3bb 100644
--- a/samples/bpf/lwt_len_hist_user.c
+++ b/samples/bpf/lwt_len_hist_user.c
@@ -14,6 +14,8 @@
 #define MAX_INDEX 64
 #define MAX_STARS 38
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static void stars(char *str, long val, long max, int width)
 {
 	int i;
@@ -41,13 +43,13 @@ int main(int argc, char **argv)
 		return -1;
 	}
 
-	while (bpf_get_next_key(map_fd, &key, &next_key) == 0) {
+	while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) {
 		if (next_key >= MAX_INDEX) {
 			fprintf(stderr, "Key %lu out of bounds\n", next_key);
 			continue;
 		}
 
-		bpf_lookup_elem(map_fd, &next_key, values);
+		bpf_map_lookup_elem(map_fd, &next_key, values);
 
 		sum = 0;
 		for (i = 0; i < nr_cpus; i++)
diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
index 6f002a9..9cce2a6 100644
--- a/samples/bpf/offwaketime_user.c
+++ b/samples/bpf/offwaketime_user.c
@@ -49,14 +49,14 @@ static void print_stack(struct key_t *key, __u64 count)
 	int i;
 
 	printf("%s;", key->target);
-	if (bpf_lookup_elem(map_fd[3], &key->tret, ip) != 0) {
+	if (bpf_map_lookup_elem(map_fd[3], &key->tret, ip) != 0) {
 		printf("---;");
 	} else {
 		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
 			print_ksym(ip[i]);
 	}
 	printf("-;");
-	if (bpf_lookup_elem(map_fd[3], &key->wret, ip) != 0) {
+	if (bpf_map_lookup_elem(map_fd[3], &key->wret, ip) != 0) {
 		printf("---;");
 	} else {
 		for (i = 0; i < PERF_MAX_STACK_DEPTH; i++)
@@ -77,8 +77,8 @@ static void print_stacks(int fd)
 	struct key_t key = {}, next_key;
 	__u64 value;
 
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
-		bpf_lookup_elem(fd, &next_key, &value);
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
 		print_stack(&next_key, value);
 		key = next_key;
 	}
diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c
index 260a6bd..be59d7d 100644
--- a/samples/bpf/sampleip_user.c
+++ b/samples/bpf/sampleip_user.c
@@ -21,6 +21,7 @@
 #include <sys/ioctl.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 #define DEFAULT_FREQ	99
 #define DEFAULT_SECS	5
@@ -49,7 +50,7 @@ static int sampling_start(int *pmu_fd, int freq)
 	};
 
 	for (i = 0; i < nr_cpus; i++) {
-		pmu_fd[i] = perf_event_open(&pe_sample_attr, -1 /* pid */, i,
+		pmu_fd[i] = sys_perf_event_open(&pe_sample_attr, -1 /* pid */, i,
 					    -1 /* group_fd */, 0 /* flags */);
 		if (pmu_fd[i] < 0) {
 			fprintf(stderr, "ERROR: Initializing perf sampling\n");
@@ -95,8 +96,8 @@ static void print_ip_map(int fd)
 
 	/* fetch IPs and counts */
 	key = 0, i = 0;
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
-		bpf_lookup_elem(fd, &next_key, &value);
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
 		counts[i].ip = next_key;
 		counts[i++].count = value;
 		key = next_key;
diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c
index 28b60ba..6fc6e19 100644
--- a/samples/bpf/sock_example.c
+++ b/samples/bpf/sock_example.c
@@ -27,6 +27,9 @@
 #include <linux/ip.h>
 #include <stddef.h>
 #include "libbpf.h"
+#include "sock_example.h"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 static int test_sock(void)
 {
@@ -54,9 +57,10 @@ static int test_sock(void)
 		BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */
 		BPF_EXIT_INSN(),
 	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog, sizeof(prog),
-				"GPL", 0);
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, insns_cnt,
+				   "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE);
 	if (prog_fd < 0) {
 		printf("failed to load prog '%s'\n", strerror(errno));
 		goto cleanup;
@@ -72,13 +76,13 @@ static int test_sock(void)
 
 	for (i = 0; i < 10; i++) {
 		key = IPPROTO_TCP;
-		assert(bpf_lookup_elem(map_fd, &key, &tcp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0);
 
 		key = IPPROTO_UDP;
-		assert(bpf_lookup_elem(map_fd, &key, &udp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0);
 
 		key = IPPROTO_ICMP;
-		assert(bpf_lookup_elem(map_fd, &key, &icmp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0);
 
 		printf("TCP %lld UDP %lld ICMP %lld packets\n",
 		       tcp_cnt, udp_cnt, icmp_cnt);
diff --git a/samples/bpf/sock_example.h b/samples/bpf/sock_example.h
new file mode 100644
index 0000000..09f7fe7
--- /dev/null
+++ b/samples/bpf/sock_example.h
@@ -0,0 +1,35 @@
+#include <stdlib.h>
+#include <stdio.h>
+#include <linux/unistd.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <linux/if_packet.h>
+#include <arpa/inet.h>
+#include "libbpf.h"
+
+static inline int open_raw_sock(const char *name)
+{
+	struct sockaddr_ll sll;
+	int sock;
+
+	sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL));
+	if (sock < 0) {
+		printf("cannot create raw socket\n");
+		return -1;
+	}
+
+	memset(&sll, 0, sizeof(sll));
+	sll.sll_family = AF_PACKET;
+	sll.sll_ifindex = if_nametoindex(name);
+	sll.sll_protocol = htons(ETH_P_ALL);
+	if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) {
+		printf("bind to %s: %s\n", name, strerror(errno));
+		close(sock);
+		return -1;
+	}
+
+	return sock;
+}
diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c
index 678ce46..6cd2feb 100644
--- a/samples/bpf/sockex1_user.c
+++ b/samples/bpf/sockex1_user.c
@@ -3,6 +3,7 @@
 #include <linux/bpf.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
 
@@ -32,13 +33,13 @@ int main(int ac, char **argv)
 		int key;
 
 		key = IPPROTO_TCP;
-		assert(bpf_lookup_elem(map_fd[0], &key, &tcp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd[0], &key, &tcp_cnt) == 0);
 
 		key = IPPROTO_UDP;
-		assert(bpf_lookup_elem(map_fd[0], &key, &udp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd[0], &key, &udp_cnt) == 0);
 
 		key = IPPROTO_ICMP;
-		assert(bpf_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0);
 
 		printf("TCP %lld UDP %lld ICMP %lld bytes\n",
 		       tcp_cnt, udp_cnt, icmp_cnt);
diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c
index 8a4085c..0e0207c 100644
--- a/samples/bpf/sockex2_user.c
+++ b/samples/bpf/sockex2_user.c
@@ -3,6 +3,7 @@
 #include <linux/bpf.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
 #include <sys/resource.h>
@@ -39,8 +40,8 @@ int main(int ac, char **argv)
 		int key = 0, next_key;
 		struct pair value;
 
-		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
-			bpf_lookup_elem(map_fd[0], &next_key, &value);
+		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd[0], &next_key, &value);
 			printf("ip %s bytes %lld packets %lld\n",
 			       inet_ntoa((struct in_addr){htonl(next_key)}),
 			       value.bytes, value.packets);
diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
index 3fcfd8c..b5524d4 100644
--- a/samples/bpf/sockex3_user.c
+++ b/samples/bpf/sockex3_user.c
@@ -3,6 +3,7 @@
 #include <linux/bpf.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
 #include <sys/resource.h>
@@ -54,8 +55,8 @@ int main(int argc, char **argv)
 
 		sleep(1);
 		printf("IP     src.port -> dst.port               bytes      packets\n");
-		while (bpf_get_next_key(map_fd[2], &key, &next_key) == 0) {
-			bpf_lookup_elem(map_fd[2], &next_key, &value);
+		while (bpf_map_get_next_key(map_fd[2], &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd[2], &next_key, &value);
 			printf("%s.%05d -> %s.%05d %12lld %12lld\n",
 			       inet_ntoa((struct in_addr){htonl(next_key.src)}),
 			       next_key.port16[0],
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index 311ede5..80676c2 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -31,8 +31,8 @@ int main(int ac, char **argv)
 	for (i = 0; i < 5; i++) {
 		key = 0;
 		printf("kprobing funcs:");
-		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
-			bpf_lookup_elem(map_fd[0], &next_key, &value);
+		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd[0], &next_key, &value);
 			assert(next_key == value);
 			sym = ksym_search(value);
 			printf(" %s", sym->name);
@@ -41,8 +41,8 @@ int main(int ac, char **argv)
 		if (key)
 			printf("\n");
 		key = 0;
-		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0)
-			bpf_delete_elem(map_fd[0], &next_key);
+		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0)
+			bpf_map_delete_elem(map_fd[0], &next_key);
 		sleep(1);
 	}
 
diff --git a/samples/bpf/tc_l2_redirect_user.c b/samples/bpf/tc_l2_redirect_user.c
index 4013c53..28995a7 100644
--- a/samples/bpf/tc_l2_redirect_user.c
+++ b/samples/bpf/tc_l2_redirect_user.c
@@ -60,9 +60,9 @@ int main(int argc, char **argv)
 	}
 
 	/* bpf_tunnel_key.remote_ipv4 expects host byte orders */
-	ret = bpf_update_elem(array_fd, &array_key, &ifindex, 0);
+	ret = bpf_map_update_elem(array_fd, &array_key, &ifindex, 0);
 	if (ret) {
-		perror("bpf_update_elem");
+		perror("bpf_map_update_elem");
 		goto out;
 	}
 
diff --git a/samples/bpf/test_cgrp2_array_pin.c b/samples/bpf/test_cgrp2_array_pin.c
index 70e86f7..8a1b8b5 100644
--- a/samples/bpf/test_cgrp2_array_pin.c
+++ b/samples/bpf/test_cgrp2_array_pin.c
@@ -85,9 +85,9 @@ int main(int argc, char **argv)
 		}
 	}
 
-	ret = bpf_update_elem(array_fd, &array_key, &cg2_fd, 0);
+	ret = bpf_map_update_elem(array_fd, &array_key, &cg2_fd, 0);
 	if (ret) {
-		perror("bpf_update_elem");
+		perror("bpf_map_update_elem");
 		goto out;
 	}
 
diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c
index a19484c..5040586 100644
--- a/samples/bpf/test_cgrp2_attach.c
+++ b/samples/bpf/test_cgrp2_attach.c
@@ -36,6 +36,8 @@ enum {
 	MAP_KEY_BYTES,
 };
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static int prog_load(int map_fd, int verdict)
 {
 	struct bpf_insn prog[] = {
@@ -66,9 +68,11 @@ static int prog_load(int map_fd, int verdict)
 		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
 		BPF_EXIT_INSN(),
 	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 
-	return bpf_prog_load(BPF_PROG_TYPE_CGROUP_SKB,
-			     prog, sizeof(prog), "GPL", 0);
+	return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+				prog, insns_cnt, "GPL", 0,
+				bpf_log_buf, BPF_LOG_BUF_SIZE);
 }
 
 static int usage(const char *argv0)
@@ -108,10 +112,10 @@ static int attach_filter(int cg_fd, int type, int verdict)
 	}
 	while (1) {
 		key = MAP_KEY_PACKETS;
-		assert(bpf_lookup_elem(map_fd, &key, &pkt_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &pkt_cnt) == 0);
 
 		key = MAP_KEY_BYTES;
-		assert(bpf_lookup_elem(map_fd, &key, &byte_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &byte_cnt) == 0);
 
 		printf("cgroup received %lld packets, %lld bytes\n",
 		       pkt_cnt, byte_cnt);
diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c
index ddfac42..6e69be3 100644
--- a/samples/bpf/test_cgrp2_attach2.c
+++ b/samples/bpf/test_cgrp2_attach2.c
@@ -32,6 +32,8 @@
 #define BAR		"/foo/bar/"
 #define PING_CMD	"ping -c1 -w1 127.0.0.1"
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static int prog_load(int verdict)
 {
 	int ret;
@@ -39,9 +41,11 @@ static int prog_load(int verdict)
 		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
 		BPF_EXIT_INSN(),
 	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 
-	ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SKB,
-			     prog, sizeof(prog), "GPL", 0);
+	ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
 
 	if (ret < 0) {
 		log_err("Loading program");
diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c
index d467b3c..0791b94 100644
--- a/samples/bpf/test_cgrp2_sock.c
+++ b/samples/bpf/test_cgrp2_sock.c
@@ -23,6 +23,8 @@
 
 #include "libbpf.h"
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static int prog_load(int idx)
 {
 	struct bpf_insn prog[] = {
@@ -33,9 +35,10 @@ static int prog_load(int idx)
 		BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = verdict */
 		BPF_EXIT_INSN(),
 	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 
-	return bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, prog, sizeof(prog),
-			     "GPL", 0);
+	return bpf_load_program(BPF_PROG_TYPE_CGROUP_SOCK, prog, insns_cnt,
+				"GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE);
 }
 
 static int usage(const char *argv0)
diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c
index 95aaaa8..65b5fb5 100644
--- a/samples/bpf/test_current_task_under_cgroup_user.c
+++ b/samples/bpf/test_current_task_under_cgroup_user.c
@@ -36,7 +36,7 @@ int main(int argc, char **argv)
 	if (!cg2)
 		goto err;
 
-	if (bpf_update_elem(map_fd[0], &idx, &cg2, BPF_ANY)) {
+	if (bpf_map_update_elem(map_fd[0], &idx, &cg2, BPF_ANY)) {
 		log_err("Adding target cgroup to map");
 		goto err;
 	}
@@ -50,7 +50,7 @@ int main(int argc, char **argv)
 	 */
 
 	sync();
-	bpf_lookup_elem(map_fd[1], &idx, &remote_pid);
+	bpf_map_lookup_elem(map_fd[1], &idx, &remote_pid);
 
 	if (local_pid != remote_pid) {
 		fprintf(stderr,
@@ -64,10 +64,10 @@ int main(int argc, char **argv)
 		goto err;
 
 	remote_pid = 0;
-	bpf_update_elem(map_fd[1], &idx, &remote_pid, BPF_ANY);
+	bpf_map_update_elem(map_fd[1], &idx, &remote_pid, BPF_ANY);
 
 	sync();
-	bpf_lookup_elem(map_fd[1], &idx, &remote_pid);
+	bpf_map_lookup_elem(map_fd[1], &idx, &remote_pid);
 
 	if (local_pid == remote_pid) {
 		fprintf(stderr, "BPF cgroup negative test did not work\n");
diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c
index 316230a..d96dc88 100644
--- a/samples/bpf/test_lru_dist.c
+++ b/samples/bpf/test_lru_dist.c
@@ -134,7 +134,7 @@ static int pfect_lru_lookup_or_insert(struct pfect_lru *lru,
 	int seen = 0;
 
 	lru->total++;
-	if (!bpf_lookup_elem(lru->map_fd, &key, &node)) {
+	if (!bpf_map_lookup_elem(lru->map_fd, &key, &node)) {
 		if (node) {
 			list_move(&node->list, &lru->list);
 			return 1;
@@ -151,7 +151,7 @@ static int pfect_lru_lookup_or_insert(struct pfect_lru *lru,
 		node = list_last_entry(&lru->list,
 				       struct pfect_lru_node,
 				       list);
-		bpf_update_elem(lru->map_fd, &node->key, &null_node, BPF_EXIST);
+		bpf_map_update_elem(lru->map_fd, &node->key, &null_node, BPF_EXIST);
 	}
 
 	node->key = key;
@@ -159,10 +159,10 @@ static int pfect_lru_lookup_or_insert(struct pfect_lru *lru,
 
 	lru->nr_misses++;
 	if (seen) {
-		assert(!bpf_update_elem(lru->map_fd, &key, &node, BPF_EXIST));
+		assert(!bpf_map_update_elem(lru->map_fd, &key, &node, BPF_EXIST));
 	} else {
 		lru->nr_unique++;
-		assert(!bpf_update_elem(lru->map_fd, &key, &node, BPF_NOEXIST));
+		assert(!bpf_map_update_elem(lru->map_fd, &key, &node, BPF_NOEXIST));
 	}
 
 	return seen;
@@ -285,11 +285,11 @@ static void do_test_lru_dist(int task, void *data)
 
 		pfect_lru_lookup_or_insert(&pfect_lru, key);
 
-		if (!bpf_lookup_elem(lru_map_fd, &key, &value))
+		if (!bpf_map_lookup_elem(lru_map_fd, &key, &value))
 			continue;
 
-		if (bpf_update_elem(lru_map_fd, &key, &value, BPF_NOEXIST)) {
-			printf("bpf_update_elem(lru_map_fd, %llu): errno:%d\n",
+		if (bpf_map_update_elem(lru_map_fd, &key, &value, BPF_NOEXIST)) {
+			printf("bpf_map_update_elem(lru_map_fd, %llu): errno:%d\n",
 			       key, errno);
 			assert(0);
 		}
@@ -358,19 +358,19 @@ static void test_lru_loss0(int map_type, int map_flags)
 	for (key = 1; key <= 1000; key++) {
 		int start_key, end_key;
 
-		assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == 0);
+		assert(bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST) == 0);
 
 		start_key = 101;
 		end_key = min(key, 900);
 
 		while (start_key <= end_key) {
-			bpf_lookup_elem(map_fd, &start_key, value);
+			bpf_map_lookup_elem(map_fd, &start_key, value);
 			start_key++;
 		}
 	}
 
 	for (key = 1; key <= 1000; key++) {
-		if (bpf_lookup_elem(map_fd, &key, value)) {
+		if (bpf_map_lookup_elem(map_fd, &key, value)) {
 			if (key <= 100)
 				old_unused_losses++;
 			else if (key <= 900)
@@ -408,10 +408,10 @@ static void test_lru_loss1(int map_type, int map_flags)
 	value[0] = 1234;
 
 	for (key = 1; key <= 1000; key++)
-		assert(!bpf_update_elem(map_fd, &key, value, BPF_NOEXIST));
+		assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST));
 
 	for (key = 1; key <= 1000; key++) {
-		if (bpf_lookup_elem(map_fd, &key, value))
+		if (bpf_map_lookup_elem(map_fd, &key, value))
 			nr_losses++;
 	}
 
@@ -436,7 +436,7 @@ static void do_test_parallel_lru_loss(int task, void *data)
 	next_ins_key = stable_base;
 	value[0] = 1234;
 	for (i = 0; i < nr_stable_elems; i++) {
-		assert(bpf_update_elem(map_fd, &next_ins_key, value,
+		assert(bpf_map_update_elem(map_fd, &next_ins_key, value,
 				       BPF_NOEXIST) == 0);
 		next_ins_key++;
 	}
@@ -448,9 +448,9 @@ static void do_test_parallel_lru_loss(int task, void *data)
 
 		if (rn % 10) {
 			key = rn % nr_stable_elems + stable_base;
-			bpf_lookup_elem(map_fd, &key, value);
+			bpf_map_lookup_elem(map_fd, &key, value);
 		} else {
-			bpf_update_elem(map_fd, &next_ins_key, value,
+			bpf_map_update_elem(map_fd, &next_ins_key, value,
 					BPF_NOEXIST);
 			next_ins_key++;
 		}
@@ -458,7 +458,7 @@ static void do_test_parallel_lru_loss(int task, void *data)
 
 	key = stable_base;
 	for (i = 0; i < nr_stable_elems; i++) {
-		if (bpf_lookup_elem(map_fd, &key, value))
+		if (bpf_map_lookup_elem(map_fd, &key, value))
 			nr_losses++;
 		key++;
 	}
diff --git a/samples/bpf/test_probe_write_user_user.c b/samples/bpf/test_probe_write_user_user.c
index a44bf34..b5bf178 100644
--- a/samples/bpf/test_probe_write_user_user.c
+++ b/samples/bpf/test_probe_write_user_user.c
@@ -50,7 +50,7 @@ int main(int ac, char **argv)
 	mapped_addr_in->sin_port = htons(5555);
 	mapped_addr_in->sin_addr.s_addr = inet_addr("255.255.255.255");
 
-	assert(!bpf_update_elem(map_fd[0], &mapped_addr, &serv_addr, BPF_ANY));
+	assert(!bpf_map_update_elem(map_fd[0], &mapped_addr, &serv_addr, BPF_ANY));
 
 	assert(listen(serverfd, 5) == 0);
 
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 9a130d31..0c5561d 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -20,6 +20,7 @@
 #include <sys/resource.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 #define SAMPLE_FREQ 50
 
@@ -61,14 +62,14 @@ static void print_stack(struct key_t *key, __u64 count)
 	int i;
 
 	printf("%3lld %s;", count, key->comm);
-	if (bpf_lookup_elem(map_fd[1], &key->kernstack, ip) != 0) {
+	if (bpf_map_lookup_elem(map_fd[1], &key->kernstack, ip) != 0) {
 		printf("---;");
 	} else {
 		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
 			print_ksym(ip[i]);
 	}
 	printf("-;");
-	if (bpf_lookup_elem(map_fd[1], &key->userstack, ip) != 0) {
+	if (bpf_map_lookup_elem(map_fd[1], &key->userstack, ip) != 0) {
 		printf("---;");
 	} else {
 		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
@@ -98,10 +99,10 @@ static void print_stacks(void)
 	int fd = map_fd[0], stack_map = map_fd[1];
 
 	sys_read_seen = sys_write_seen = false;
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
-		bpf_lookup_elem(fd, &next_key, &value);
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
 		print_stack(&next_key, value);
-		bpf_delete_elem(fd, &next_key);
+		bpf_map_delete_elem(fd, &next_key);
 		key = next_key;
 	}
 
@@ -111,8 +112,8 @@ static void print_stacks(void)
 	}
 
 	/* clear stack map */
-	while (bpf_get_next_key(stack_map, &stackid, &next_id) == 0) {
-		bpf_delete_elem(stack_map, &next_id);
+	while (bpf_map_get_next_key(stack_map, &stackid, &next_id) == 0) {
+		bpf_map_delete_elem(stack_map, &next_id);
 		stackid = next_id;
 	}
 }
@@ -125,9 +126,9 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr)
 
 	/* open perf_event on all cpus */
 	for (i = 0; i < nr_cpus; i++) {
-		pmu_fd[i] = perf_event_open(attr, -1, i, -1, 0);
+		pmu_fd[i] = sys_perf_event_open(attr, -1, i, -1, 0);
 		if (pmu_fd[i] < 0) {
-			printf("perf_event_open failed\n");
+			printf("sys_perf_event_open failed\n");
 			goto all_cpu_err;
 		}
 		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
@@ -146,9 +147,9 @@ static void test_perf_event_task(struct perf_event_attr *attr)
 	int pmu_fd;
 
 	/* open task bound event */
-	pmu_fd = perf_event_open(attr, 0, -1, -1, 0);
+	pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0);
 	if (pmu_fd < 0) {
-		printf("perf_event_open failed\n");
+		printf("sys_perf_event_open failed\n");
 		return;
 	}
 	assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c
index 661a7d0..f4fa6af 100644
--- a/samples/bpf/trace_output_user.c
+++ b/samples/bpf/trace_output_user.c
@@ -21,6 +21,7 @@
 #include <signal.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 static int pmu_fd;
 
@@ -61,7 +62,7 @@ struct perf_event_sample {
 	char data[];
 };
 
-void perf_event_read(print_fn fn)
+static void perf_event_read(print_fn fn)
 {
 	__u64 data_tail = header->data_tail;
 	__u64 data_head = header->data_head;
@@ -159,10 +160,10 @@ static void test_bpf_perf_event(void)
 	};
 	int key = 0;
 
-	pmu_fd = perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
+	pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
 
 	assert(pmu_fd >= 0);
-	assert(bpf_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);
+	assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);
 	ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index 3e225e3..ded9804 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -48,12 +48,12 @@ static void print_hist_for_pid(int fd, void *task)
 	long max_value = 0;
 	int i, ind;
 
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
 		if (memcmp(&next_key, task, SIZE)) {
 			key = next_key;
 			continue;
 		}
-		bpf_lookup_elem(fd, &next_key, values);
+		bpf_map_lookup_elem(fd, &next_key, values);
 		value = 0;
 		for (i = 0; i < nr_cpus; i++)
 			value += values[i];
@@ -83,7 +83,7 @@ static void print_hist(int fd)
 	int task_cnt = 0;
 	int i;
 
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
 		int found = 0;
 
 		for (i = 0; i < task_cnt; i++)
@@ -136,8 +136,8 @@ int main(int ac, char **argv)
 
 	for (i = 0; i < 5; i++) {
 		key = 0;
-		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
-			bpf_lookup_elem(map_fd[0], &next_key, &value);
+		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd[0], &next_key, &value);
 			printf("location 0x%lx count %ld\n", next_key, value);
 			key = next_key;
 		}
diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c
index d0851cb..8f7d199 100644
--- a/samples/bpf/tracex3_user.c
+++ b/samples/bpf/tracex3_user.c
@@ -28,7 +28,7 @@ static void clear_stats(int fd)
 
 	memset(values, 0, sizeof(values));
 	for (key = 0; key < SLOTS; key++)
-		bpf_update_elem(fd, &key, values, BPF_ANY);
+		bpf_map_update_elem(fd, &key, values, BPF_ANY);
 }
 
 const char *color[] = {
@@ -89,7 +89,7 @@ static void print_hist(int fd)
 	int i;
 
 	for (key = 0; key < SLOTS; key++) {
-		bpf_lookup_elem(fd, &key, values);
+		bpf_map_lookup_elem(fd, &key, values);
 		value = 0;
 		for (i = 0; i < nr_cpus; i++)
 			value += values[i];
diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c
index bc4a3bd..03449f77 100644
--- a/samples/bpf/tracex4_user.c
+++ b/samples/bpf/tracex4_user.c
@@ -37,8 +37,8 @@ static void print_old_objects(int fd)
 	key = write(1, "\e[1;1H\e[2J", 12); /* clear screen */
 
 	key = -1;
-	while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
-		bpf_lookup_elem(map_fd[0], &next_key, &v);
+	while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+		bpf_map_lookup_elem(map_fd[0], &next_key, &v);
 		key = next_key;
 		if (val - v.val < 1000000000ll)
 			/* object was allocated more then 1 sec ago */
diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c
index 8ea4976..ca7874e 100644
--- a/samples/bpf/tracex6_user.c
+++ b/samples/bpf/tracex6_user.c
@@ -10,6 +10,7 @@
 #include <linux/bpf.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 #define SAMPLE_PERIOD  0x7fffffffffffffffULL
 
@@ -30,13 +31,13 @@ static void test_bpf_perf_event(void)
 	};
 
 	for (i = 0; i < nr_cpus; i++) {
-		pmu_fd[i] = perf_event_open(&attr_insn_pmu, -1/*pid*/, i/*cpu*/, -1/*group_fd*/, 0);
+		pmu_fd[i] = sys_perf_event_open(&attr_insn_pmu, -1/*pid*/, i/*cpu*/, -1/*group_fd*/, 0);
 		if (pmu_fd[i] < 0) {
 			printf("event syscall failed\n");
 			goto exit;
 		}
 
-		bpf_update_elem(map_fd[0], &i, &pmu_fd[i], BPF_ANY);
+		bpf_map_update_elem(map_fd[0], &i, &pmu_fd[i], BPF_ANY);
 		ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE, 0);
 	}
 
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 5f040a0..d2be65d 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -43,7 +43,7 @@ static void poll_stats(int interval)
 		for (key = 0; key < nr_keys; key++) {
 			__u64 sum = 0;
 
-			assert(bpf_lookup_elem(map_fd[0], &key, values) == 0);
+			assert(bpf_map_lookup_elem(map_fd[0], &key, values) == 0);
 			for (i = 0; i < nr_cpus; i++)
 				sum += (values[i] - prev[key][i]);
 			if (sum)
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 7a71f5c..70e192f 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -51,7 +51,7 @@ static void poll_stats(unsigned int kill_after_s)
 		for (proto = 0; proto < nr_protos; proto++) {
 			__u64 sum = 0;
 
-			assert(bpf_lookup_elem(map_fd[0], &proto, values) == 0);
+			assert(bpf_map_lookup_elem(map_fd[0], &proto, values) == 0);
 			for (i = 0; i < nr_cpus; i++)
 				sum += (values[i] - prev[proto][i]);
 
@@ -237,8 +237,8 @@ int main(int argc, char **argv)
 
 	while (min_port <= max_port) {
 		vip.dport = htons(min_port++);
-		if (bpf_update_elem(map_fd[1], &vip, &tnl, BPF_NOEXIST)) {
-			perror("bpf_update_elem(&vip2tnl)");
+		if (bpf_map_update_elem(map_fd[1], &vip, &tnl, BPF_NOEXIST)) {
+			perror("bpf_map_update_elem(&vip2tnl)");
 			return 1;
 		}
 	}
diff --git a/scripts/selinux/genheaders/Makefile b/scripts/selinux/genheaders/Makefile
index 1d1ac51..6fc2b87 100644
--- a/scripts/selinux/genheaders/Makefile
+++ b/scripts/selinux/genheaders/Makefile
@@ -1,4 +1,6 @@
 hostprogs-y	:= genheaders
-HOST_EXTRACFLAGS += -Isecurity/selinux/include
+HOST_EXTRACFLAGS += \
+	-I$(srctree)/include/uapi -I$(srctree)/include \
+	-I$(srctree)/security/selinux/include
 
 always		:= $(hostprogs-y)
diff --git a/scripts/selinux/genheaders/genheaders.c b/scripts/selinux/genheaders/genheaders.c
index 539855f..f4dd41f 100644
--- a/scripts/selinux/genheaders/genheaders.c
+++ b/scripts/selinux/genheaders/genheaders.c
@@ -1,3 +1,7 @@
+
+/* NOTE: we really do want to use the kernel headers here */
+#define __EXPORTED_HEADERS__
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
diff --git a/scripts/selinux/mdp/Makefile b/scripts/selinux/mdp/Makefile
index dba7eff..d6a83ca 100644
--- a/scripts/selinux/mdp/Makefile
+++ b/scripts/selinux/mdp/Makefile
@@ -1,5 +1,7 @@
 hostprogs-y	:= mdp
-HOST_EXTRACFLAGS += -Isecurity/selinux/include
+HOST_EXTRACFLAGS += \
+	-I$(srctree)/include/uapi -I$(srctree)/include \
+	-I$(srctree)/security/selinux/include
 
 always		:= $(hostprogs-y)
 clean-files	:= policy.* file_contexts
diff --git a/scripts/selinux/mdp/mdp.c b/scripts/selinux/mdp/mdp.c
index e10beb1..c29fa4a 100644
--- a/scripts/selinux/mdp/mdp.c
+++ b/scripts/selinux/mdp/mdp.c
@@ -24,6 +24,10 @@
  * Authors: Serge E. Hallyn <serue@us.ibm.com>
  */
 
+
+/* NOTE: we really do want to use the kernel headers here */
+#define __EXPORTED_HEADERS__
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 5487827..370eb2f 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -27,6 +27,18 @@
 	  to learn more about IMA.
 	  If unsure, say N.
 
+config IMA_KEXEC
+	bool "Enable carrying the IMA measurement list across a soft boot"
+	depends on IMA && TCG_TPM && HAVE_IMA_KEXEC
+	default n
+	help
+	   TPM PCRs are only reset on a hard reboot.  In order to validate
+	   a TPM's quote after a soft boot, the IMA measurement list of the
+	   running kernel must be saved and restored on boot.
+
+	   Depending on the IMA policy, the measurement list can grow to
+	   be very large.
+
 config IMA_MEASURE_PCR_IDX
 	int
 	depends on IMA
diff --git a/security/integrity/ima/Makefile b/security/integrity/ima/Makefile
index 9aeaeda..29f198b 100644
--- a/security/integrity/ima/Makefile
+++ b/security/integrity/ima/Makefile
@@ -8,4 +8,5 @@
 ima-y := ima_fs.o ima_queue.o ima_init.o ima_main.o ima_crypto.o ima_api.o \
 	 ima_policy.o ima_template.o ima_template_lib.o
 ima-$(CONFIG_IMA_APPRAISE) += ima_appraise.o
+ima-$(CONFIG_HAVE_IMA_KEXEC) += ima_kexec.o
 obj-$(CONFIG_IMA_BLACKLIST_KEYRING) += ima_mok.o
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index db25f54..5e6180a 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -28,6 +28,10 @@
 
 #include "../integrity.h"
 
+#ifdef CONFIG_HAVE_IMA_KEXEC
+#include <asm/ima.h>
+#endif
+
 enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN,
 		     IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII };
 enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
@@ -81,6 +85,7 @@ struct ima_template_field {
 
 /* IMA template descriptor definition */
 struct ima_template_desc {
+	struct list_head list;
 	char *name;
 	char *fmt;
 	int num_fields;
@@ -102,6 +107,27 @@ struct ima_queue_entry {
 };
 extern struct list_head ima_measurements;	/* list of all measurements */
 
+/* Some details preceding the binary serialized measurement list */
+struct ima_kexec_hdr {
+	u16 version;
+	u16 _reserved0;
+	u32 _reserved1;
+	u64 buffer_size;
+	u64 count;
+};
+
+#ifdef CONFIG_HAVE_IMA_KEXEC
+void ima_load_kexec_buffer(void);
+#else
+static inline void ima_load_kexec_buffer(void) {}
+#endif /* CONFIG_HAVE_IMA_KEXEC */
+
+/*
+ * The default binary_runtime_measurements list format is defined as the
+ * platform native format.  The canonical format is defined as little-endian.
+ */
+extern bool ima_canonical_fmt;
+
 /* Internal IMA function definitions */
 int ima_init(void);
 int ima_fs_init(void);
@@ -122,7 +148,12 @@ int ima_init_crypto(void);
 void ima_putc(struct seq_file *m, void *data, int datalen);
 void ima_print_digest(struct seq_file *m, u8 *digest, u32 size);
 struct ima_template_desc *ima_template_desc_current(void);
+int ima_restore_measurement_entry(struct ima_template_entry *entry);
+int ima_restore_measurement_list(loff_t bufsize, void *buf);
+int ima_measurements_show(struct seq_file *m, void *v);
+unsigned long ima_get_binary_runtime_size(void);
 int ima_init_template(void);
+void ima_init_template_list(void);
 
 /*
  * used to protect h_table and sha_table
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 38f2ed8..802d5d2 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -477,11 +477,13 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
 		u8 buffer[IMA_EVENT_NAME_LEN_MAX + 1] = { 0 };
 		u8 *data_to_hash = field_data[i].data;
 		u32 datalen = field_data[i].len;
+		u32 datalen_to_hash =
+		    !ima_canonical_fmt ? datalen : cpu_to_le32(datalen);
 
 		if (strcmp(td->name, IMA_TEMPLATE_IMA_NAME) != 0) {
 			rc = crypto_shash_update(shash,
-						(const u8 *) &field_data[i].len,
-						sizeof(field_data[i].len));
+						(const u8 *) &datalen_to_hash,
+						sizeof(datalen_to_hash));
 			if (rc)
 				break;
 		} else if (strcmp(td->fields[i]->field_id, "n") == 0) {
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 3df4690..ca303e5 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -28,6 +28,16 @@
 
 static DEFINE_MUTEX(ima_write_mutex);
 
+bool ima_canonical_fmt;
+static int __init default_canonical_fmt_setup(char *str)
+{
+#ifdef __BIG_ENDIAN
+	ima_canonical_fmt = 1;
+#endif
+	return 1;
+}
+__setup("ima_canonical_fmt", default_canonical_fmt_setup);
+
 static int valid_policy = 1;
 #define TMPBUFLEN 12
 static ssize_t ima_show_htable_value(char __user *buf, size_t count,
@@ -116,13 +126,13 @@ void ima_putc(struct seq_file *m, void *data, int datalen)
  *       [eventdata length]
  *       eventdata[n]=template specific data
  */
-static int ima_measurements_show(struct seq_file *m, void *v)
+int ima_measurements_show(struct seq_file *m, void *v)
 {
 	/* the list never shrinks, so we don't need a lock here */
 	struct ima_queue_entry *qe = v;
 	struct ima_template_entry *e;
 	char *template_name;
-	int namelen;
+	u32 pcr, namelen, template_data_len; /* temporary fields */
 	bool is_ima_template = false;
 	int i;
 
@@ -139,25 +149,29 @@ static int ima_measurements_show(struct seq_file *m, void *v)
 	 * PCR used defaults to the same (config option) in
 	 * little-endian format, unless set in policy
 	 */
-	ima_putc(m, &e->pcr, sizeof(e->pcr));
+	pcr = !ima_canonical_fmt ? e->pcr : cpu_to_le32(e->pcr);
+	ima_putc(m, &pcr, sizeof(e->pcr));
 
 	/* 2nd: template digest */
 	ima_putc(m, e->digest, TPM_DIGEST_SIZE);
 
 	/* 3rd: template name size */
-	namelen = strlen(template_name);
+	namelen = !ima_canonical_fmt ? strlen(template_name) :
+		cpu_to_le32(strlen(template_name));
 	ima_putc(m, &namelen, sizeof(namelen));
 
 	/* 4th:  template name */
-	ima_putc(m, template_name, namelen);
+	ima_putc(m, template_name, strlen(template_name));
 
 	/* 5th:  template length (except for 'ima' template) */
 	if (strcmp(template_name, IMA_TEMPLATE_IMA_NAME) == 0)
 		is_ima_template = true;
 
-	if (!is_ima_template)
-		ima_putc(m, &e->template_data_len,
-			 sizeof(e->template_data_len));
+	if (!is_ima_template) {
+		template_data_len = !ima_canonical_fmt ? e->template_data_len :
+			cpu_to_le32(e->template_data_len);
+		ima_putc(m, &template_data_len, sizeof(e->template_data_len));
+	}
 
 	/* 6th:  template specific data */
 	for (i = 0; i < e->template_desc->num_fields; i++) {
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 2ac1f41..2967d49 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -129,6 +129,8 @@ int __init ima_init(void)
 	if (rc != 0)
 		return rc;
 
+	ima_load_kexec_buffer();
+
 	rc = ima_add_boot_aggregate();	/* boot aggregate must be first entry */
 	if (rc != 0)
 		return rc;
diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c
new file mode 100644
index 0000000..e473eee
--- /dev/null
+++ b/security/integrity/ima/ima_kexec.c
@@ -0,0 +1,168 @@
+/*
+ * Copyright (C) 2016 IBM Corporation
+ *
+ * Authors:
+ * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
+ * Mimi Zohar <zohar@linux.vnet.ibm.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.
+ */
+#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
+#include <linux/kexec.h>
+#include "ima.h"
+
+#ifdef CONFIG_IMA_KEXEC
+static int ima_dump_measurement_list(unsigned long *buffer_size, void **buffer,
+				     unsigned long segment_size)
+{
+	struct ima_queue_entry *qe;
+	struct seq_file file;
+	struct ima_kexec_hdr khdr;
+	int ret = 0;
+
+	/* segment size can't change between kexec load and execute */
+	file.buf = vmalloc(segment_size);
+	if (!file.buf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	file.size = segment_size;
+	file.read_pos = 0;
+	file.count = sizeof(khdr);	/* reserved space */
+
+	memset(&khdr, 0, sizeof(khdr));
+	khdr.version = 1;
+	list_for_each_entry_rcu(qe, &ima_measurements, later) {
+		if (file.count < file.size) {
+			khdr.count++;
+			ima_measurements_show(&file, qe);
+		} else {
+			ret = -EINVAL;
+			break;
+		}
+	}
+
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * fill in reserved space with some buffer details
+	 * (eg. version, buffer size, number of measurements)
+	 */
+	khdr.buffer_size = file.count;
+	if (ima_canonical_fmt) {
+		khdr.version = cpu_to_le16(khdr.version);
+		khdr.count = cpu_to_le64(khdr.count);
+		khdr.buffer_size = cpu_to_le64(khdr.buffer_size);
+	}
+	memcpy(file.buf, &khdr, sizeof(khdr));
+
+	print_hex_dump(KERN_DEBUG, "ima dump: ", DUMP_PREFIX_NONE,
+			16, 1, file.buf,
+			file.count < 100 ? file.count : 100, true);
+
+	*buffer_size = file.count;
+	*buffer = file.buf;
+out:
+	if (ret == -EINVAL)
+		vfree(file.buf);
+	return ret;
+}
+
+/*
+ * Called during kexec_file_load so that IMA can add a segment to the kexec
+ * image for the measurement list for the next kernel.
+ *
+ * This function assumes that kexec_mutex is held.
+ */
+void ima_add_kexec_buffer(struct kimage *image)
+{
+	struct kexec_buf kbuf = { .image = image, .buf_align = PAGE_SIZE,
+				  .buf_min = 0, .buf_max = ULONG_MAX,
+				  .top_down = true };
+	unsigned long binary_runtime_size;
+
+	/* use more understandable variable names than defined in kbuf */
+	void *kexec_buffer = NULL;
+	size_t kexec_buffer_size;
+	size_t kexec_segment_size;
+	int ret;
+
+	/*
+	 * Reserve an extra half page of memory for additional measurements
+	 * added during the kexec load.
+	 */
+	binary_runtime_size = ima_get_binary_runtime_size();
+	if (binary_runtime_size >= ULONG_MAX - PAGE_SIZE)
+		kexec_segment_size = ULONG_MAX;
+	else
+		kexec_segment_size = ALIGN(ima_get_binary_runtime_size() +
+					   PAGE_SIZE / 2, PAGE_SIZE);
+	if ((kexec_segment_size == ULONG_MAX) ||
+	    ((kexec_segment_size >> PAGE_SHIFT) > totalram_pages / 2)) {
+		pr_err("Binary measurement list too large.\n");
+		return;
+	}
+
+	ima_dump_measurement_list(&kexec_buffer_size, &kexec_buffer,
+				  kexec_segment_size);
+	if (!kexec_buffer) {
+		pr_err("Not enough memory for the kexec measurement buffer.\n");
+		return;
+	}
+
+	kbuf.buffer = kexec_buffer;
+	kbuf.bufsz = kexec_buffer_size;
+	kbuf.memsz = kexec_segment_size;
+	ret = kexec_add_buffer(&kbuf);
+	if (ret) {
+		pr_err("Error passing over kexec measurement buffer.\n");
+		return;
+	}
+
+	ret = arch_ima_add_kexec_buffer(image, kbuf.mem, kexec_segment_size);
+	if (ret) {
+		pr_err("Error passing over kexec measurement buffer.\n");
+		return;
+	}
+
+	pr_debug("kexec measurement buffer for the loaded kernel at 0x%lx.\n",
+		 kbuf.mem);
+}
+#endif /* IMA_KEXEC */
+
+/*
+ * Restore the measurement list from the previous kernel.
+ */
+void ima_load_kexec_buffer(void)
+{
+	void *kexec_buffer = NULL;
+	size_t kexec_buffer_size = 0;
+	int rc;
+
+	rc = ima_get_kexec_buffer(&kexec_buffer, &kexec_buffer_size);
+	switch (rc) {
+	case 0:
+		rc = ima_restore_measurement_list(kexec_buffer_size,
+						  kexec_buffer);
+		if (rc != 0)
+			pr_err("Failed to restore the measurement list: %d\n",
+				rc);
+
+		ima_free_kexec_buffer();
+		break;
+	case -ENOTSUPP:
+		pr_debug("Restoring the measurement list not supported\n");
+		break;
+	case -ENOENT:
+		pr_debug("No measurement list to restore\n");
+		break;
+	default:
+		pr_debug("Error restoring the measurement list: %d\n", rc);
+	}
+}
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 423d111..50818c6 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -418,6 +418,7 @@ static int __init init_ima(void)
 {
 	int error;
 
+	ima_init_template_list();
 	hash_setup(CONFIG_IMA_DEFAULT_HASH);
 	error = ima_init();
 	if (!error) {
diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c
index 32f6ac0..d9aa5ab 100644
--- a/security/integrity/ima/ima_queue.c
+++ b/security/integrity/ima/ima_queue.c
@@ -29,6 +29,11 @@
 #define AUDIT_CAUSE_LEN_MAX 32
 
 LIST_HEAD(ima_measurements);	/* list of all measurements */
+#ifdef CONFIG_IMA_KEXEC
+static unsigned long binary_runtime_size;
+#else
+static unsigned long binary_runtime_size = ULONG_MAX;
+#endif
 
 /* key: inode (before secure-hashing a file) */
 struct ima_h_table ima_htable = {
@@ -64,12 +69,32 @@ static struct ima_queue_entry *ima_lookup_digest_entry(u8 *digest_value,
 	return ret;
 }
 
+/*
+ * Calculate the memory required for serializing a single
+ * binary_runtime_measurement list entry, which contains a
+ * couple of variable length fields (e.g template name and data).
+ */
+static int get_binary_runtime_size(struct ima_template_entry *entry)
+{
+	int size = 0;
+
+	size += sizeof(u32);	/* pcr */
+	size += sizeof(entry->digest);
+	size += sizeof(int);	/* template name size field */
+	size += strlen(entry->template_desc->name) + 1;
+	size += sizeof(entry->template_data_len);
+	size += entry->template_data_len;
+	return size;
+}
+
 /* ima_add_template_entry helper function:
- * - Add template entry to measurement list and hash table.
+ * - Add template entry to the measurement list and hash table, for
+ *   all entries except those carried across kexec.
  *
  * (Called with ima_extend_list_mutex held.)
  */
-static int ima_add_digest_entry(struct ima_template_entry *entry)
+static int ima_add_digest_entry(struct ima_template_entry *entry,
+				bool update_htable)
 {
 	struct ima_queue_entry *qe;
 	unsigned int key;
@@ -85,11 +110,34 @@ static int ima_add_digest_entry(struct ima_template_entry *entry)
 	list_add_tail_rcu(&qe->later, &ima_measurements);
 
 	atomic_long_inc(&ima_htable.len);
-	key = ima_hash_key(entry->digest);
-	hlist_add_head_rcu(&qe->hnext, &ima_htable.queue[key]);
+	if (update_htable) {
+		key = ima_hash_key(entry->digest);
+		hlist_add_head_rcu(&qe->hnext, &ima_htable.queue[key]);
+	}
+
+	if (binary_runtime_size != ULONG_MAX) {
+		int size;
+
+		size = get_binary_runtime_size(entry);
+		binary_runtime_size = (binary_runtime_size < ULONG_MAX - size) ?
+		     binary_runtime_size + size : ULONG_MAX;
+	}
 	return 0;
 }
 
+/*
+ * Return the amount of memory required for serializing the
+ * entire binary_runtime_measurement list, including the ima_kexec_hdr
+ * structure.
+ */
+unsigned long ima_get_binary_runtime_size(void)
+{
+	if (binary_runtime_size >= (ULONG_MAX - sizeof(struct ima_kexec_hdr)))
+		return ULONG_MAX;
+	else
+		return binary_runtime_size + sizeof(struct ima_kexec_hdr);
+};
+
 static int ima_pcr_extend(const u8 *hash, int pcr)
 {
 	int result = 0;
@@ -103,8 +151,13 @@ static int ima_pcr_extend(const u8 *hash, int pcr)
 	return result;
 }
 
-/* Add template entry to the measurement list and hash table,
- * and extend the pcr.
+/*
+ * Add template entry to the measurement list and hash table, and
+ * extend the pcr.
+ *
+ * On systems which support carrying the IMA measurement list across
+ * kexec, maintain the total memory size required for serializing the
+ * binary_runtime_measurements.
  */
 int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 			   const char *op, struct inode *inode,
@@ -126,7 +179,7 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 		}
 	}
 
-	result = ima_add_digest_entry(entry);
+	result = ima_add_digest_entry(entry, 1);
 	if (result < 0) {
 		audit_cause = "ENOMEM";
 		audit_info = 0;
@@ -149,3 +202,13 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 			    op, audit_cause, result, audit_info);
 	return result;
 }
+
+int ima_restore_measurement_entry(struct ima_template_entry *entry)
+{
+	int result = 0;
+
+	mutex_lock(&ima_extend_list_mutex);
+	result = ima_add_digest_entry(entry, 0);
+	mutex_unlock(&ima_extend_list_mutex);
+	return result;
+}
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index febd12e..cebb37c 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -15,16 +15,20 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/rculist.h>
 #include "ima.h"
 #include "ima_template_lib.h"
 
-static struct ima_template_desc defined_templates[] = {
+static struct ima_template_desc builtin_templates[] = {
 	{.name = IMA_TEMPLATE_IMA_NAME, .fmt = IMA_TEMPLATE_IMA_FMT},
 	{.name = "ima-ng", .fmt = "d-ng|n-ng"},
 	{.name = "ima-sig", .fmt = "d-ng|n-ng|sig"},
 	{.name = "", .fmt = ""},	/* placeholder for a custom format */
 };
 
+static LIST_HEAD(defined_templates);
+static DEFINE_SPINLOCK(template_list);
+
 static struct ima_template_field supported_fields[] = {
 	{.field_id = "d", .field_init = ima_eventdigest_init,
 	 .field_show = ima_show_template_digest},
@@ -37,6 +41,7 @@ static struct ima_template_field supported_fields[] = {
 	{.field_id = "sig", .field_init = ima_eventsig_init,
 	 .field_show = ima_show_template_sig},
 };
+#define MAX_TEMPLATE_NAME_LEN 15
 
 static struct ima_template_desc *ima_template;
 static struct ima_template_desc *lookup_template_desc(const char *name);
@@ -52,6 +57,8 @@ static int __init ima_template_setup(char *str)
 	if (ima_template)
 		return 1;
 
+	ima_init_template_list();
+
 	/*
 	 * Verify that a template with the supplied name exists.
 	 * If not, use CONFIG_IMA_DEFAULT_TEMPLATE.
@@ -80,7 +87,7 @@ __setup("ima_template=", ima_template_setup);
 
 static int __init ima_template_fmt_setup(char *str)
 {
-	int num_templates = ARRAY_SIZE(defined_templates);
+	int num_templates = ARRAY_SIZE(builtin_templates);
 
 	if (ima_template)
 		return 1;
@@ -91,22 +98,28 @@ static int __init ima_template_fmt_setup(char *str)
 		return 1;
 	}
 
-	defined_templates[num_templates - 1].fmt = str;
-	ima_template = defined_templates + num_templates - 1;
+	builtin_templates[num_templates - 1].fmt = str;
+	ima_template = builtin_templates + num_templates - 1;
+
 	return 1;
 }
 __setup("ima_template_fmt=", ima_template_fmt_setup);
 
 static struct ima_template_desc *lookup_template_desc(const char *name)
 {
-	int i;
+	struct ima_template_desc *template_desc;
+	int found = 0;
 
-	for (i = 0; i < ARRAY_SIZE(defined_templates); i++) {
-		if (strcmp(defined_templates[i].name, name) == 0)
-			return defined_templates + i;
+	rcu_read_lock();
+	list_for_each_entry_rcu(template_desc, &defined_templates, list) {
+		if ((strcmp(template_desc->name, name) == 0) ||
+		    (strcmp(template_desc->fmt, name) == 0)) {
+			found = 1;
+			break;
+		}
 	}
-
-	return NULL;
+	rcu_read_unlock();
+	return found ? template_desc : NULL;
 }
 
 static struct ima_template_field *lookup_template_field(const char *field_id)
@@ -142,9 +155,14 @@ static int template_desc_init_fields(const char *template_fmt,
 {
 	const char *template_fmt_ptr;
 	struct ima_template_field *found_fields[IMA_TEMPLATE_NUM_FIELDS_MAX];
-	int template_num_fields = template_fmt_size(template_fmt);
+	int template_num_fields;
 	int i, len;
 
+	if (num_fields && *num_fields > 0) /* already initialized? */
+		return 0;
+
+	template_num_fields = template_fmt_size(template_fmt);
+
 	if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX) {
 		pr_err("format string '%s' contains too many fields\n",
 		       template_fmt);
@@ -182,11 +200,28 @@ static int template_desc_init_fields(const char *template_fmt,
 	return 0;
 }
 
+void ima_init_template_list(void)
+{
+	int i;
+
+	if (!list_empty(&defined_templates))
+		return;
+
+	spin_lock(&template_list);
+	for (i = 0; i < ARRAY_SIZE(builtin_templates); i++) {
+		list_add_tail_rcu(&builtin_templates[i].list,
+				  &defined_templates);
+	}
+	spin_unlock(&template_list);
+}
+
 struct ima_template_desc *ima_template_desc_current(void)
 {
-	if (!ima_template)
+	if (!ima_template) {
+		ima_init_template_list();
 		ima_template =
 		    lookup_template_desc(CONFIG_IMA_DEFAULT_TEMPLATE);
+	}
 	return ima_template;
 }
 
@@ -205,3 +240,239 @@ int __init ima_init_template(void)
 
 	return result;
 }
+
+static struct ima_template_desc *restore_template_fmt(char *template_name)
+{
+	struct ima_template_desc *template_desc = NULL;
+	int ret;
+
+	ret = template_desc_init_fields(template_name, NULL, NULL);
+	if (ret < 0) {
+		pr_err("attempting to initialize the template \"%s\" failed\n",
+			template_name);
+		goto out;
+	}
+
+	template_desc = kzalloc(sizeof(*template_desc), GFP_KERNEL);
+	if (!template_desc)
+		goto out;
+
+	template_desc->name = "";
+	template_desc->fmt = kstrdup(template_name, GFP_KERNEL);
+	if (!template_desc->fmt)
+		goto out;
+
+	spin_lock(&template_list);
+	list_add_tail_rcu(&template_desc->list, &defined_templates);
+	spin_unlock(&template_list);
+out:
+	return template_desc;
+}
+
+static int ima_restore_template_data(struct ima_template_desc *template_desc,
+				     void *template_data,
+				     int template_data_size,
+				     struct ima_template_entry **entry)
+{
+	struct binary_field_data {
+		u32 len;
+		u8 data[0];
+	} __packed;
+
+	struct binary_field_data *field_data;
+	int offset = 0;
+	int ret = 0;
+	int i;
+
+	*entry = kzalloc(sizeof(**entry) +
+		    template_desc->num_fields * sizeof(struct ima_field_data),
+		    GFP_NOFS);
+	if (!*entry)
+		return -ENOMEM;
+
+	(*entry)->template_desc = template_desc;
+	for (i = 0; i < template_desc->num_fields; i++) {
+		field_data = template_data + offset;
+
+		/* Each field of the template data is prefixed with a length. */
+		if (offset > (template_data_size - sizeof(*field_data))) {
+			pr_err("Restoring the template field failed\n");
+			ret = -EINVAL;
+			break;
+		}
+		offset += sizeof(*field_data);
+
+		if (ima_canonical_fmt)
+			field_data->len = le32_to_cpu(field_data->len);
+
+		if (offset > (template_data_size - field_data->len)) {
+			pr_err("Restoring the template field data failed\n");
+			ret = -EINVAL;
+			break;
+		}
+		offset += field_data->len;
+
+		(*entry)->template_data[i].len = field_data->len;
+		(*entry)->template_data_len += sizeof(field_data->len);
+
+		(*entry)->template_data[i].data =
+			kzalloc(field_data->len + 1, GFP_KERNEL);
+		if (!(*entry)->template_data[i].data) {
+			ret = -ENOMEM;
+			break;
+		}
+		memcpy((*entry)->template_data[i].data, field_data->data,
+			field_data->len);
+		(*entry)->template_data_len += field_data->len;
+	}
+
+	if (ret < 0) {
+		ima_free_template_entry(*entry);
+		*entry = NULL;
+	}
+
+	return ret;
+}
+
+/* Restore the serialized binary measurement list without extending PCRs. */
+int ima_restore_measurement_list(loff_t size, void *buf)
+{
+	struct binary_hdr_v1 {
+		u32 pcr;
+		u8 digest[TPM_DIGEST_SIZE];
+		u32 template_name_len;
+		char template_name[0];
+	} __packed;
+	char template_name[MAX_TEMPLATE_NAME_LEN];
+
+	struct binary_data_v1 {
+		u32 template_data_size;
+		char template_data[0];
+	} __packed;
+
+	struct ima_kexec_hdr *khdr = buf;
+	struct binary_hdr_v1 *hdr_v1;
+	struct binary_data_v1 *data_v1;
+
+	void *bufp = buf + sizeof(*khdr);
+	void *bufendp;
+	struct ima_template_entry *entry;
+	struct ima_template_desc *template_desc;
+	unsigned long count = 0;
+	int ret = 0;
+
+	if (!buf || size < sizeof(*khdr))
+		return 0;
+
+	if (ima_canonical_fmt) {
+		khdr->version = le16_to_cpu(khdr->version);
+		khdr->count = le64_to_cpu(khdr->count);
+		khdr->buffer_size = le64_to_cpu(khdr->buffer_size);
+	}
+
+	if (khdr->version != 1) {
+		pr_err("attempting to restore a incompatible measurement list");
+		return -EINVAL;
+	}
+
+	if (khdr->count > ULONG_MAX - 1) {
+		pr_err("attempting to restore too many measurements");
+		return -EINVAL;
+	}
+
+	/*
+	 * ima kexec buffer prefix: version, buffer size, count
+	 * v1 format: pcr, digest, template-name-len, template-name,
+	 *	      template-data-size, template-data
+	 */
+	bufendp = buf + khdr->buffer_size;
+	while ((bufp < bufendp) && (count++ < khdr->count)) {
+		hdr_v1 = bufp;
+		if (bufp > (bufendp - sizeof(*hdr_v1))) {
+			pr_err("attempting to restore partial measurement\n");
+			ret = -EINVAL;
+			break;
+		}
+		bufp += sizeof(*hdr_v1);
+
+		if (ima_canonical_fmt)
+			hdr_v1->template_name_len =
+			    le32_to_cpu(hdr_v1->template_name_len);
+
+		if ((hdr_v1->template_name_len >= MAX_TEMPLATE_NAME_LEN) ||
+		    (bufp > (bufendp - hdr_v1->template_name_len))) {
+			pr_err("attempting to restore a template name \
+				that is too long\n");
+			ret = -EINVAL;
+			break;
+		}
+		data_v1 = bufp += (u_int8_t)hdr_v1->template_name_len;
+
+		/* template name is not null terminated */
+		memcpy(template_name, hdr_v1->template_name,
+		       hdr_v1->template_name_len);
+		template_name[hdr_v1->template_name_len] = 0;
+
+		if (strcmp(template_name, "ima") == 0) {
+			pr_err("attempting to restore an unsupported \
+				template \"%s\" failed\n", template_name);
+			ret = -EINVAL;
+			break;
+		}
+
+		template_desc = lookup_template_desc(template_name);
+		if (!template_desc) {
+			template_desc = restore_template_fmt(template_name);
+			if (!template_desc)
+				break;
+		}
+
+		/*
+		 * Only the running system's template format is initialized
+		 * on boot.  As needed, initialize the other template formats.
+		 */
+		ret = template_desc_init_fields(template_desc->fmt,
+						&(template_desc->fields),
+						&(template_desc->num_fields));
+		if (ret < 0) {
+			pr_err("attempting to restore the template fmt \"%s\" \
+				failed\n", template_desc->fmt);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (bufp > (bufendp - sizeof(data_v1->template_data_size))) {
+			pr_err("restoring the template data size failed\n");
+			ret = -EINVAL;
+			break;
+		}
+		bufp += (u_int8_t) sizeof(data_v1->template_data_size);
+
+		if (ima_canonical_fmt)
+			data_v1->template_data_size =
+			    le32_to_cpu(data_v1->template_data_size);
+
+		if (bufp > (bufendp - data_v1->template_data_size)) {
+			pr_err("restoring the template data failed\n");
+			ret = -EINVAL;
+			break;
+		}
+		bufp += data_v1->template_data_size;
+
+		ret = ima_restore_template_data(template_desc,
+						data_v1->template_data,
+						data_v1->template_data_size,
+						&entry);
+		if (ret < 0)
+			break;
+
+		memcpy(entry->digest, hdr_v1->digest, TPM_DIGEST_SIZE);
+		entry->pcr =
+		    !ima_canonical_fmt ? hdr_v1->pcr : le32_to_cpu(hdr_v1->pcr);
+		ret = ima_restore_measurement_entry(entry);
+		if (ret < 0)
+			break;
+
+	}
+	return ret;
+}
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index f9bae04..f9ba37b 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -103,8 +103,11 @@ static void ima_show_template_data_binary(struct seq_file *m,
 	u32 len = (show == IMA_SHOW_BINARY_OLD_STRING_FMT) ?
 	    strlen(field_data->data) : field_data->len;
 
-	if (show != IMA_SHOW_BINARY_NO_FIELD_LEN)
-		ima_putc(m, &len, sizeof(len));
+	if (show != IMA_SHOW_BINARY_NO_FIELD_LEN) {
+		u32 field_len = !ima_canonical_fmt ? len : cpu_to_le32(len);
+
+		ima_putc(m, &field_len, sizeof(field_len));
+	}
 
 	if (!len)
 		return;
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index f89f190..04a764f 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -23,7 +23,7 @@
 #include <linux/vmalloc.h>
 #include <linux/security.h>
 #include <linux/uio.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 
 #define KEY_MAX_DESC_SIZE 4096
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 40a8852..918cddc 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -18,7 +18,7 @@
 #include <linux/mutex.h>
 #include <linux/security.h>
 #include <linux/user_namespace.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 
 /* Session keyring create vs join semaphore */
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 9db8b4a..6bbe2f5 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -16,7 +16,7 @@
 #include <linux/err.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 #include <keys/user-type.h>
 
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 66b1840..e187c89 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -15,7 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/err.h>
 #include <keys/user-type.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include "internal.h"
 
 static int logon_vet_description(const char *desc);
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index e2d4ad3..13ae49b 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -1,3 +1,5 @@
+#include <linux/capability.h>
+
 #define COMMON_FILE_SOCK_PERMS "ioctl", "read", "write", "create", \
     "getattr", "setattr", "lock", "relabelfrom", "relabelto", "append"
 
diff --git a/sound/core/hrtimer.c b/sound/core/hrtimer.c
index e2f2702..1ac0c42 100644
--- a/sound/core/hrtimer.c
+++ b/sound/core/hrtimer.c
@@ -58,7 +58,7 @@ static enum hrtimer_restart snd_hrtimer_callback(struct hrtimer *hrt)
 
 	/* calculate the drift */
 	delta = ktime_sub(hrt->base->get_time(), hrtimer_get_expires(hrt));
-	if (delta.tv64 > 0)
+	if (delta > 0)
 		ticks += ktime_divns(delta, ticks * resolution);
 
 	snd_timer_interrupt(stime->timer, ticks);
diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c
index 3689f5f..aca2d7d 100644
--- a/sound/drivers/pcsp/pcsp_lib.c
+++ b/sound/drivers/pcsp/pcsp_lib.c
@@ -166,7 +166,7 @@ static int pcsp_start_playing(struct snd_pcsp *chip)
 	atomic_set(&chip->timer_active, 1);
 	chip->thalf = 0;
 
-	hrtimer_start(&pcsp_chip.timer, ktime_set(0, 0), HRTIMER_MODE_REL);
+	hrtimer_start(&pcsp_chip.timer, 0, HRTIMER_MODE_REL);
 	return 0;
 }
 
diff --git a/sound/firewire/lib.c b/sound/firewire/lib.c
index ca4dfcf..7683238 100644
--- a/sound/firewire/lib.c
+++ b/sound/firewire/lib.c
@@ -114,7 +114,7 @@ static void async_midi_port_callback(struct fw_card *card, int rcode,
 		snd_rawmidi_transmit_ack(substream, port->consume_bytes);
 	else if (!rcode_is_permanent_error(rcode))
 		/* To start next transaction immediately for recovery. */
-		port->next_ktime = ktime_set(0, 0);
+		port->next_ktime = 0;
 	else
 		/* Don't continue processing. */
 		port->error = true;
@@ -156,7 +156,7 @@ static void midi_port_work(struct work_struct *work)
 	if (port->consume_bytes <= 0) {
 		/* Do it in next chance, immediately. */
 		if (port->consume_bytes == 0) {
-			port->next_ktime = ktime_set(0, 0);
+			port->next_ktime = 0;
 			schedule_work(&port->work);
 		} else {
 			/* Fatal error. */
@@ -219,7 +219,7 @@ int snd_fw_async_midi_port_init(struct snd_fw_async_midi_port *port,
 	port->addr = addr;
 	port->fill = fill;
 	port->idling = true;
-	port->next_ktime = ktime_set(0, 0);
+	port->next_ktime = 0;
 	port->error = false;
 
 	INIT_WORK(&port->work, midi_port_work);
diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c
index 38990a7..c6994eb 100644
--- a/sound/hda/hdac_stream.c
+++ b/sound/hda/hdac_stream.c
@@ -465,7 +465,7 @@ int snd_hdac_stream_set_params(struct hdac_stream *azx_dev,
 }
 EXPORT_SYMBOL_GPL(snd_hdac_stream_set_params);
 
-static cycle_t azx_cc_read(const struct cyclecounter *cc)
+static u64 azx_cc_read(const struct cyclecounter *cc)
 {
 	struct hdac_stream *azx_dev = container_of(cc, struct hdac_stream, cc);
 
@@ -473,7 +473,7 @@ static cycle_t azx_cc_read(const struct cyclecounter *cc)
 }
 
 static void azx_timecounter_init(struct hdac_stream *azx_dev,
-				 bool force, cycle_t last)
+				 bool force, u64 last)
 {
 	struct timecounter *tc = &azx_dev->tc;
 	struct cyclecounter *cc = &azx_dev->cc;
@@ -523,7 +523,7 @@ void snd_hdac_stream_timecounter_init(struct hdac_stream *azx_dev,
 	struct snd_pcm_runtime *runtime = azx_dev->substream->runtime;
 	struct hdac_stream *s;
 	bool inited = false;
-	cycle_t cycle_last = 0;
+	u64 cycle_last = 0;
 	int i = 0;
 
 	list_for_each_entry(s, &bus->stream_list, list) {
diff --git a/sound/oss/dmasound/dmasound_atari.c b/sound/oss/dmasound/dmasound_atari.c
index 1c56bf5..a1a2979 100644
--- a/sound/oss/dmasound/dmasound_atari.c
+++ b/sound/oss/dmasound/dmasound_atari.c
@@ -22,7 +22,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/atariints.h>
 #include <asm/atari_stram.h>
 
diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c
index f4ee85a..5f248fb 100644
--- a/sound/oss/dmasound/dmasound_core.c
+++ b/sound/oss/dmasound/dmasound_core.c
@@ -183,7 +183,7 @@
 #include <linux/poll.h>
 #include <linux/mutex.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include "dmasound.h"
 
diff --git a/sound/oss/dmasound/dmasound_paula.c b/sound/oss/dmasound/dmasound_paula.c
index 3f65361..81eb82c 100644
--- a/sound/oss/dmasound/dmasound_paula.c
+++ b/sound/oss/dmasound/dmasound_paula.c
@@ -23,7 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/setup.h>
 #include <asm/amigahw.h>
 #include <asm/amigaints.h>
diff --git a/sound/oss/dmasound/dmasound_q40.c b/sound/oss/dmasound/dmasound_q40.c
index 99bcb21..be4fe15 100644
--- a/sound/oss/dmasound/dmasound_q40.c
+++ b/sound/oss/dmasound/dmasound_q40.c
@@ -20,7 +20,7 @@
 #include <linux/soundcard.h>
 #include <linux/interrupt.h>
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/q40ints.h>
 #include <asm/q40_master.h>
 
diff --git a/sound/oss/msnd.c b/sound/oss/msnd.c
index c0cc951..b63010ad 100644
--- a/sound/oss/msnd.c
+++ b/sound/oss/msnd.c
@@ -32,7 +32,7 @@
 #include <linux/interrupt.h>
 
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/spinlock.h>
 #include <asm/irq.h>
 #include "msnd.h"
diff --git a/sound/oss/os.h b/sound/oss/os.h
index 75ad0cd..0bf89e1 100644
--- a/sound/oss/os.h
+++ b/sound/oss/os.h
@@ -17,7 +17,7 @@
 #include <linux/ioport.h>
 #include <asm/page.h>
 #include <linux/vmalloc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/poll.h>
 #include <linux/pci.h>
 #endif
diff --git a/sound/oss/swarm_cs4297a.c b/sound/oss/swarm_cs4297a.c
index 213a416..f3af63e 100644
--- a/sound/oss/swarm_cs4297a.c
+++ b/sound/oss/swarm_cs4297a.c
@@ -80,7 +80,7 @@
 #include <asm/byteorder.h>
 #include <asm/dma.h>
 #include <asm/io.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 #include <asm/sibyte/sb1250_regs.h>
 #include <asm/sibyte/sb1250_int.h>
diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c
index abf9c0c..461b310 100644
--- a/sound/sh/sh_dac_audio.c
+++ b/sound/sh/sh_dac_audio.c
@@ -87,7 +87,7 @@ static void dac_audio_reset(struct snd_sh_dac *chip)
 
 static void dac_audio_set_rate(struct snd_sh_dac *chip)
 {
-	chip->wakeups_per_second = ktime_set(0, 1000000000 / chip->rate);
+	chip->wakeups_per_second = 1000000000 / chip->rate;
 }
 
 
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index a2cdf33..15d1d5c 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -384,9 +384,6 @@ static void snd_complete_urb(struct urb *urb)
 	if (unlikely(atomic_read(&ep->chip->shutdown)))
 		goto exit_clear;
 
-	if (unlikely(!test_bit(EP_FLAG_RUNNING, &ep->flags)))
-		goto exit_clear;
-
 	if (usb_pipeout(ep->pipe)) {
 		retire_outbound_urb(ep, ctx);
 		/* can be stopped during retire callback */
@@ -537,11 +534,6 @@ static int wait_clear_urbs(struct snd_usb_endpoint *ep)
 			alive, ep->ep_num);
 	clear_bit(EP_FLAG_STOPPING, &ep->flags);
 
-	ep->data_subs = NULL;
-	ep->sync_slave = NULL;
-	ep->retire_data_urb = NULL;
-	ep->prepare_data_urb = NULL;
-
 	return 0;
 }
 
@@ -1028,6 +1020,10 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep)
 
 	if (--ep->use_count == 0) {
 		deactivate_urbs(ep, false);
+		ep->data_subs = NULL;
+		ep->sync_slave = NULL;
+		ep->retire_data_urb = NULL;
+		ep->prepare_data_urb = NULL;
 		set_bit(EP_FLAG_STOPPING, &ep->flags);
 	}
 }
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9e5fc16..0eb0e87 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -73,6 +73,8 @@ enum bpf_cmd {
 	BPF_PROG_LOAD,
 	BPF_OBJ_PIN,
 	BPF_OBJ_GET,
+	BPF_PROG_ATTACH,
+	BPF_PROG_DETACH,
 };
 
 enum bpf_map_type {
@@ -85,6 +87,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_PERCPU_ARRAY,
 	BPF_MAP_TYPE_STACK_TRACE,
 	BPF_MAP_TYPE_CGROUP_ARRAY,
+	BPF_MAP_TYPE_LRU_HASH,
+	BPF_MAP_TYPE_LRU_PERCPU_HASH,
 };
 
 enum bpf_prog_type {
@@ -95,8 +99,23 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SCHED_ACT,
 	BPF_PROG_TYPE_TRACEPOINT,
 	BPF_PROG_TYPE_XDP,
+	BPF_PROG_TYPE_PERF_EVENT,
+	BPF_PROG_TYPE_CGROUP_SKB,
+	BPF_PROG_TYPE_CGROUP_SOCK,
+	BPF_PROG_TYPE_LWT_IN,
+	BPF_PROG_TYPE_LWT_OUT,
+	BPF_PROG_TYPE_LWT_XMIT,
 };
 
+enum bpf_attach_type {
+	BPF_CGROUP_INET_INGRESS,
+	BPF_CGROUP_INET_EGRESS,
+	BPF_CGROUP_INET_SOCK_CREATE,
+	__MAX_BPF_ATTACH_TYPE
+};
+
+#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -105,6 +124,13 @@ enum bpf_prog_type {
 #define BPF_EXIST	2 /* update existing element */
 
 #define BPF_F_NO_PREALLOC	(1U << 0)
+/* Instead of having one common LRU list in the
+ * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
+ * which can scale and perform better.
+ * Note, the LRU nodes (including free nodes) cannot be moved
+ * across different LRU lists.
+ */
+#define BPF_F_NO_COMMON_LRU	(1U << 1)
 
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
@@ -140,243 +166,327 @@ union bpf_attr {
 		__aligned_u64	pathname;
 		__u32		bpf_fd;
 	};
+
+	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
+		__u32		target_fd;	/* container object to attach to */
+		__u32		attach_bpf_fd;	/* eBPF program to attach */
+		__u32		attach_type;
+	};
 } __attribute__((aligned(8)));
 
+/* BPF helper function descriptions:
+ *
+ * void *bpf_map_lookup_elem(&map, &key)
+ *     Return: Map value or NULL
+ *
+ * int bpf_map_update_elem(&map, &key, &value, flags)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_map_delete_elem(&map, &key)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_probe_read(void *dst, int size, void *src)
+ *     Return: 0 on success or negative error
+ *
+ * u64 bpf_ktime_get_ns(void)
+ *     Return: current ktime
+ *
+ * int bpf_trace_printk(const char *fmt, int fmt_size, ...)
+ *     Return: length of buffer written or negative error
+ *
+ * u32 bpf_prandom_u32(void)
+ *     Return: random value
+ *
+ * u32 bpf_raw_smp_processor_id(void)
+ *     Return: SMP processor ID
+ *
+ * int bpf_skb_store_bytes(skb, offset, from, len, flags)
+ *     store bytes into packet
+ *     @skb: pointer to skb
+ *     @offset: offset within packet from skb->mac_header
+ *     @from: pointer where to copy bytes from
+ *     @len: number of bytes to store into packet
+ *     @flags: bit 0 - if true, recompute skb->csum
+ *             other bits - reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_l3_csum_replace(skb, offset, from, to, flags)
+ *     recompute IP checksum
+ *     @skb: pointer to skb
+ *     @offset: offset within packet where IP checksum is located
+ *     @from: old value of header field
+ *     @to: new value of header field
+ *     @flags: bits 0-3 - size of header field
+ *             other bits - reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_l4_csum_replace(skb, offset, from, to, flags)
+ *     recompute TCP/UDP checksum
+ *     @skb: pointer to skb
+ *     @offset: offset within packet where TCP/UDP checksum is located
+ *     @from: old value of header field
+ *     @to: new value of header field
+ *     @flags: bits 0-3 - size of header field
+ *             bit 4 - is pseudo header
+ *             other bits - reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_tail_call(ctx, prog_array_map, index)
+ *     jump into another BPF program
+ *     @ctx: context pointer passed to next program
+ *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
+ *     @index: index inside array that selects specific program to run
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_clone_redirect(skb, ifindex, flags)
+ *     redirect to another netdev
+ *     @skb: pointer to skb
+ *     @ifindex: ifindex of the net device
+ *     @flags: bit 0 - if set, redirect to ingress instead of egress
+ *             other bits - reserved
+ *     Return: 0 on success or negative error
+ *
+ * u64 bpf_get_current_pid_tgid(void)
+ *     Return: current->tgid << 32 | current->pid
+ *
+ * u64 bpf_get_current_uid_gid(void)
+ *     Return: current_gid << 32 | current_uid
+ *
+ * int bpf_get_current_comm(char *buf, int size_of_buf)
+ *     stores current->comm into buf
+ *     Return: 0 on success or negative error
+ *
+ * u32 bpf_get_cgroup_classid(skb)
+ *     retrieve a proc's classid
+ *     @skb: pointer to skb
+ *     Return: classid if != 0
+ *
+ * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_vlan_pop(skb)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_get_tunnel_key(skb, key, size, flags)
+ * int bpf_skb_set_tunnel_key(skb, key, size, flags)
+ *     retrieve or populate tunnel metadata
+ *     @skb: pointer to skb
+ *     @key: pointer to 'struct bpf_tunnel_key'
+ *     @size: size of 'struct bpf_tunnel_key'
+ *     @flags: room for future extensions
+ *     Return: 0 on success or negative error
+ *
+ * u64 bpf_perf_event_read(&map, index)
+ *     Return: Number events read or error code
+ *
+ * int bpf_redirect(ifindex, flags)
+ *     redirect to another netdev
+ *     @ifindex: ifindex of the net device
+ *     @flags: bit 0 - if set, redirect to ingress instead of egress
+ *             other bits - reserved
+ *     Return: TC_ACT_REDIRECT
+ *
+ * u32 bpf_get_route_realm(skb)
+ *     retrieve a dst's tclassid
+ *     @skb: pointer to skb
+ *     Return: realm if != 0
+ *
+ * int bpf_perf_event_output(ctx, map, index, data, size)
+ *     output perf raw sample
+ *     @ctx: struct pt_regs*
+ *     @map: pointer to perf_event_array map
+ *     @index: index of event in the map
+ *     @data: data on stack to be output as raw data
+ *     @size: size of data
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_get_stackid(ctx, map, flags)
+ *     walk user or kernel stack and return id
+ *     @ctx: struct pt_regs*
+ *     @map: pointer to stack_trace map
+ *     @flags: bits 0-7 - numer of stack frames to skip
+ *             bit 8 - collect user stack instead of kernel
+ *             bit 9 - compare stacks by hash only
+ *             bit 10 - if two different stacks hash into the same stackid
+ *                      discard old
+ *             other bits - reserved
+ *     Return: >= 0 stackid on success or negative error
+ *
+ * s64 bpf_csum_diff(from, from_size, to, to_size, seed)
+ *     calculate csum diff
+ *     @from: raw from buffer
+ *     @from_size: length of from buffer
+ *     @to: raw to buffer
+ *     @to_size: length of to buffer
+ *     @seed: optional seed
+ *     Return: csum result or negative error code
+ *
+ * int bpf_skb_get_tunnel_opt(skb, opt, size)
+ *     retrieve tunnel options metadata
+ *     @skb: pointer to skb
+ *     @opt: pointer to raw tunnel option data
+ *     @size: size of @opt
+ *     Return: option size
+ *
+ * int bpf_skb_set_tunnel_opt(skb, opt, size)
+ *     populate tunnel options metadata
+ *     @skb: pointer to skb
+ *     @opt: pointer to raw tunnel option data
+ *     @size: size of @opt
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_change_proto(skb, proto, flags)
+ *     Change protocol of the skb. Currently supported is v4 -> v6,
+ *     v6 -> v4 transitions. The helper will also resize the skb. eBPF
+ *     program is expected to fill the new headers via skb_store_bytes
+ *     and lX_csum_replace.
+ *     @skb: pointer to skb
+ *     @proto: new skb->protocol type
+ *     @flags: reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_change_type(skb, type)
+ *     Change packet type of skb.
+ *     @skb: pointer to skb
+ *     @type: new skb->pkt_type type
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_under_cgroup(skb, map, index)
+ *     Check cgroup2 membership of skb
+ *     @skb: pointer to skb
+ *     @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+ *     @index: index of the cgroup in the bpf_map
+ *     Return:
+ *       == 0 skb failed the cgroup2 descendant test
+ *       == 1 skb succeeded the cgroup2 descendant test
+ *        < 0 error
+ *
+ * u32 bpf_get_hash_recalc(skb)
+ *     Retrieve and possibly recalculate skb->hash.
+ *     @skb: pointer to skb
+ *     Return: hash
+ *
+ * u64 bpf_get_current_task(void)
+ *     Returns current task_struct
+ *     Return: current
+ *
+ * int bpf_probe_write_user(void *dst, void *src, int len)
+ *     safely attempt to write to a location
+ *     @dst: destination address in userspace
+ *     @src: source address on stack
+ *     @len: number of bytes to copy
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_current_task_under_cgroup(map, index)
+ *     Check cgroup2 membership of current task
+ *     @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+ *     @index: index of the cgroup in the bpf_map
+ *     Return:
+ *       == 0 current failed the cgroup2 descendant test
+ *       == 1 current succeeded the cgroup2 descendant test
+ *        < 0 error
+ *
+ * int bpf_skb_change_tail(skb, len, flags)
+ *     The helper will resize the skb to the given new size, to be used f.e.
+ *     with control messages.
+ *     @skb: pointer to skb
+ *     @len: new skb length
+ *     @flags: reserved
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_skb_pull_data(skb, len)
+ *     The helper will pull in non-linear data in case the skb is non-linear
+ *     and not all of len are part of the linear section. Only needed for
+ *     read/write with direct packet access.
+ *     @skb: pointer to skb
+ *     @len: len to make read/writeable
+ *     Return: 0 on success or negative error
+ *
+ * s64 bpf_csum_update(skb, csum)
+ *     Adds csum into skb->csum in case of CHECKSUM_COMPLETE.
+ *     @skb: pointer to skb
+ *     @csum: csum to add
+ *     Return: csum on success or negative error
+ *
+ * void bpf_set_hash_invalid(skb)
+ *     Invalidate current skb->hash.
+ *     @skb: pointer to skb
+ *
+ * int bpf_get_numa_node_id()
+ *     Return: Id of current NUMA node.
+ *
+ * int bpf_skb_change_head()
+ *     Grows headroom of skb and adjusts MAC header offset accordingly.
+ *     Will extends/reallocae as required automatically.
+ *     May change skb data pointer and will thus invalidate any check
+ *     performed for direct packet access.
+ *     @skb: pointer to skb
+ *     @len: length of header to be pushed in front
+ *     @flags: Flags (unused for now)
+ *     Return: 0 on success or negative error
+ *
+ * int bpf_xdp_adjust_head(xdp_md, delta)
+ *     Adjust the xdp_md.data by delta
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: An positive/negative integer to be added to xdp_md.data
+ *     Return: 0 on success or negative on error
+ */
+#define __BPF_FUNC_MAPPER(FN)		\
+	FN(unspec),			\
+	FN(map_lookup_elem),		\
+	FN(map_update_elem),		\
+	FN(map_delete_elem),		\
+	FN(probe_read),			\
+	FN(ktime_get_ns),		\
+	FN(trace_printk),		\
+	FN(get_prandom_u32),		\
+	FN(get_smp_processor_id),	\
+	FN(skb_store_bytes),		\
+	FN(l3_csum_replace),		\
+	FN(l4_csum_replace),		\
+	FN(tail_call),			\
+	FN(clone_redirect),		\
+	FN(get_current_pid_tgid),	\
+	FN(get_current_uid_gid),	\
+	FN(get_current_comm),		\
+	FN(get_cgroup_classid),		\
+	FN(skb_vlan_push),		\
+	FN(skb_vlan_pop),		\
+	FN(skb_get_tunnel_key),		\
+	FN(skb_set_tunnel_key),		\
+	FN(perf_event_read),		\
+	FN(redirect),			\
+	FN(get_route_realm),		\
+	FN(perf_event_output),		\
+	FN(skb_load_bytes),		\
+	FN(get_stackid),		\
+	FN(csum_diff),			\
+	FN(skb_get_tunnel_opt),		\
+	FN(skb_set_tunnel_opt),		\
+	FN(skb_change_proto),		\
+	FN(skb_change_type),		\
+	FN(skb_under_cgroup),		\
+	FN(get_hash_recalc),		\
+	FN(get_current_task),		\
+	FN(probe_write_user),		\
+	FN(current_task_under_cgroup),	\
+	FN(skb_change_tail),		\
+	FN(skb_pull_data),		\
+	FN(csum_update),		\
+	FN(set_hash_invalid),		\
+	FN(get_numa_node_id),		\
+	FN(skb_change_head),		\
+	FN(xdp_adjust_head),
+
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
  */
+#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
 enum bpf_func_id {
-	BPF_FUNC_unspec,
-	BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
-	BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
-	BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
-	BPF_FUNC_probe_read,      /* int bpf_probe_read(void *dst, int size, void *src) */
-	BPF_FUNC_ktime_get_ns,    /* u64 bpf_ktime_get_ns(void) */
-	BPF_FUNC_trace_printk,    /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */
-	BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
-	BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
-
-	/**
-	 * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet
-	 * @skb: pointer to skb
-	 * @offset: offset within packet from skb->mac_header
-	 * @from: pointer where to copy bytes from
-	 * @len: number of bytes to store into packet
-	 * @flags: bit 0 - if true, recompute skb->csum
-	 *         other bits - reserved
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_skb_store_bytes,
-
-	/**
-	 * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum
-	 * @skb: pointer to skb
-	 * @offset: offset within packet where IP checksum is located
-	 * @from: old value of header field
-	 * @to: new value of header field
-	 * @flags: bits 0-3 - size of header field
-	 *         other bits - reserved
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_l3_csum_replace,
-
-	/**
-	 * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum
-	 * @skb: pointer to skb
-	 * @offset: offset within packet where TCP/UDP checksum is located
-	 * @from: old value of header field
-	 * @to: new value of header field
-	 * @flags: bits 0-3 - size of header field
-	 *         bit 4 - is pseudo header
-	 *         other bits - reserved
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_l4_csum_replace,
-
-	/**
-	 * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program
-	 * @ctx: context pointer passed to next program
-	 * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
-	 * @index: index inside array that selects specific program to run
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_tail_call,
-
-	/**
-	 * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev
-	 * @skb: pointer to skb
-	 * @ifindex: ifindex of the net device
-	 * @flags: bit 0 - if set, redirect to ingress instead of egress
-	 *         other bits - reserved
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_clone_redirect,
-
-	/**
-	 * u64 bpf_get_current_pid_tgid(void)
-	 * Return: current->tgid << 32 | current->pid
-	 */
-	BPF_FUNC_get_current_pid_tgid,
-
-	/**
-	 * u64 bpf_get_current_uid_gid(void)
-	 * Return: current_gid << 32 | current_uid
-	 */
-	BPF_FUNC_get_current_uid_gid,
-
-	/**
-	 * bpf_get_current_comm(char *buf, int size_of_buf)
-	 * stores current->comm into buf
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_get_current_comm,
-
-	/**
-	 * bpf_get_cgroup_classid(skb) - retrieve a proc's classid
-	 * @skb: pointer to skb
-	 * Return: classid if != 0
-	 */
-	BPF_FUNC_get_cgroup_classid,
-	BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
-	BPF_FUNC_skb_vlan_pop,  /* bpf_skb_vlan_pop(skb) */
-
-	/**
-	 * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
-	 * retrieve or populate tunnel metadata
-	 * @skb: pointer to skb
-	 * @key: pointer to 'struct bpf_tunnel_key'
-	 * @size: size of 'struct bpf_tunnel_key'
-	 * @flags: room for future extensions
-	 * Retrun: 0 on success
-	 */
-	BPF_FUNC_skb_get_tunnel_key,
-	BPF_FUNC_skb_set_tunnel_key,
-	BPF_FUNC_perf_event_read,	/* u64 bpf_perf_event_read(&map, index) */
-	/**
-	 * bpf_redirect(ifindex, flags) - redirect to another netdev
-	 * @ifindex: ifindex of the net device
-	 * @flags: bit 0 - if set, redirect to ingress instead of egress
-	 *         other bits - reserved
-	 * Return: TC_ACT_REDIRECT
-	 */
-	BPF_FUNC_redirect,
-
-	/**
-	 * bpf_get_route_realm(skb) - retrieve a dst's tclassid
-	 * @skb: pointer to skb
-	 * Return: realm if != 0
-	 */
-	BPF_FUNC_get_route_realm,
-
-	/**
-	 * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample
-	 * @ctx: struct pt_regs*
-	 * @map: pointer to perf_event_array map
-	 * @index: index of event in the map
-	 * @data: data on stack to be output as raw data
-	 * @size: size of data
-	 * Return: 0 on success
-	 */
-	BPF_FUNC_perf_event_output,
-	BPF_FUNC_skb_load_bytes,
-
-	/**
-	 * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id
-	 * @ctx: struct pt_regs*
-	 * @map: pointer to stack_trace map
-	 * @flags: bits 0-7 - numer of stack frames to skip
-	 *         bit 8 - collect user stack instead of kernel
-	 *         bit 9 - compare stacks by hash only
-	 *         bit 10 - if two different stacks hash into the same stackid
-	 *                  discard old
-	 *         other bits - reserved
-	 * Return: >= 0 stackid on success or negative error
-	 */
-	BPF_FUNC_get_stackid,
-
-	/**
-	 * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
-	 * @from: raw from buffer
-	 * @from_size: length of from buffer
-	 * @to: raw to buffer
-	 * @to_size: length of to buffer
-	 * @seed: optional seed
-	 * Return: csum result
-	 */
-	BPF_FUNC_csum_diff,
-
-	/**
-	 * bpf_skb_[gs]et_tunnel_opt(skb, opt, size)
-	 * retrieve or populate tunnel options metadata
-	 * @skb: pointer to skb
-	 * @opt: pointer to raw tunnel option data
-	 * @size: size of @opt
-	 * Return: 0 on success for set, option size for get
-	 */
-	BPF_FUNC_skb_get_tunnel_opt,
-	BPF_FUNC_skb_set_tunnel_opt,
-
-	/**
-	 * bpf_skb_change_proto(skb, proto, flags)
-	 * Change protocol of the skb. Currently supported is
-	 * v4 -> v6, v6 -> v4 transitions. The helper will also
-	 * resize the skb. eBPF program is expected to fill the
-	 * new headers via skb_store_bytes and lX_csum_replace.
-	 * @skb: pointer to skb
-	 * @proto: new skb->protocol type
-	 * @flags: reserved
-	 * Return: 0 on success or negative error
-	 */
-	BPF_FUNC_skb_change_proto,
-
-	/**
-	 * bpf_skb_change_type(skb, type)
-	 * Change packet type of skb.
-	 * @skb: pointer to skb
-	 * @type: new skb->pkt_type type
-	 * Return: 0 on success or negative error
-	 */
-	BPF_FUNC_skb_change_type,
-
-	/**
-	 * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb
-	 * @skb: pointer to skb
-	 * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
-	 * @index: index of the cgroup in the bpf_map
-	 * Return:
-	 *   == 0 skb failed the cgroup2 descendant test
-	 *   == 1 skb succeeded the cgroup2 descendant test
-	 *    < 0 error
-	 */
-	BPF_FUNC_skb_under_cgroup,
-
-	/**
-	 * bpf_get_hash_recalc(skb)
-	 * Retrieve and possibly recalculate skb->hash.
-	 * @skb: pointer to skb
-	 * Return: hash
-	 */
-	BPF_FUNC_get_hash_recalc,
-
-	/**
-	 * u64 bpf_get_current_task(void)
-	 * Returns current task_struct
-	 * Return: current
-	 */
-	BPF_FUNC_get_current_task,
-
-	/**
-	 * bpf_probe_write_user(void *dst, void *src, int len)
-	 * safely attempt to write to a location
-	 * @dst: destination address in userspace
-	 * @src: source address on stack
-	 * @len: number of bytes to copy
-	 * Return: 0 on success or negative error
-	 */
-	BPF_FUNC_probe_write_user,
-
+	__BPF_FUNC_MAPPER(__BPF_ENUM_FN)
 	__BPF_FUNC_MAX_ID,
 };
+#undef __BPF_ENUM_FN
 
 /* All flags used by eBPF helper functions, placed here. */
 
@@ -450,6 +560,31 @@ struct bpf_tunnel_key {
 	__u32 tunnel_label;
 };
 
+/* Generic BPF return codes which all BPF program types may support.
+ * The values are binary compatible with their TC_ACT_* counter-part to
+ * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
+ * programs.
+ *
+ * XDP is handled seprately, see XDP_*.
+ */
+enum bpf_ret_code {
+	BPF_OK = 0,
+	/* 1 reserved */
+	BPF_DROP = 2,
+	/* 3-6 reserved */
+	BPF_REDIRECT = 7,
+	/* >127 are reserved for prog type specific return codes */
+};
+
+struct bpf_sock {
+	__u32 bound_dev_if;
+	__u32 family;
+	__u32 type;
+	__u32 protocol;
+};
+
+#define XDP_PACKET_HEADROOM 256
+
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
  * return codes are reserved for future use. Unknown return codes will result
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 8143536..3ddb58a 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -54,7 +54,7 @@ static int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 }
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size,
-		   int value_size, int max_entries)
+		   int value_size, int max_entries, __u32 map_flags)
 {
 	union bpf_attr attr;
 
@@ -64,13 +64,14 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
 	attr.key_size = key_size;
 	attr.value_size = value_size;
 	attr.max_entries = max_entries;
+	attr.map_flags = map_flags;
 
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
 int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 		     size_t insns_cnt, char *license,
-		     u32 kern_version, char *log_buf, size_t log_buf_sz)
+		     __u32 kern_version, char *log_buf, size_t log_buf_sz)
 {
 	int fd;
 	union bpf_attr attr;
@@ -98,7 +99,7 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 }
 
 int bpf_map_update_elem(int fd, void *key, void *value,
-			u64 flags)
+			__u64 flags)
 {
 	union bpf_attr attr;
 
@@ -166,3 +167,26 @@ int bpf_obj_get(const char *pathname)
 
 	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
 }
+
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.target_fd	   = target_fd;
+	attr.attach_bpf_fd = prog_fd;
+	attr.attach_type   = type;
+
+	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+}
+
+int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.target_fd	 = target_fd;
+	attr.attach_type = type;
+
+	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 253c3db..a2f9853 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -24,22 +24,25 @@
 #include <linux/bpf.h>
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries);
+		   int max_entries, __u32 map_flags);
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536
 int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 		     size_t insns_cnt, char *license,
-		     u32 kern_version, char *log_buf,
+		     __u32 kern_version, char *log_buf,
 		     size_t log_buf_sz);
 
 int bpf_map_update_elem(int fd, void *key, void *value,
-			u64 flags);
+			__u64 flags);
 
 int bpf_map_lookup_elem(int fd, void *key, void *value);
 int bpf_map_delete_elem(int fd, void *key);
 int bpf_map_get_next_key(int fd, void *key, void *next_key);
 int bpf_obj_pin(int fd, const char *pathname);
 int bpf_obj_get(const char *pathname);
+int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+
 
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2e97459..84e6b35 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -854,7 +854,8 @@ bpf_object__create_maps(struct bpf_object *obj)
 		*pfd = bpf_create_map(def->type,
 				      def->key_size,
 				      def->value_size,
-				      def->max_entries);
+				      def->max_entries,
+				      0);
 		if (*pfd < 0) {
 			size_t j;
 			int err = *pfd;
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 7775b1e..7617396 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -132,6 +132,10 @@
 --migrations::
 	Show migration events.
 
+-I::
+--idle-hist::
+	Show idle-related events only.
+
 --time::
 	Only analyze samples within given time window: <start>,<stop>. Times
 	have the format seconds.microseconds. If start is not given (i.e., time
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e5af38e..8fc2482 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -201,6 +201,7 @@
 $(goals) all: sub-make
 
 sub-make: fixdep
+	@./check-headers.sh
 	$(Q)$(MAKE) FIXDEP=1 -f Makefile.perf $(goals)
 
 else # force_fixdep
@@ -404,99 +405,6 @@
 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 $(PERF_IN): prepare FORCE
-	@(test -f ../../include/uapi/linux/perf_event.h && ( \
-        (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
-        || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/linux/hash.h && ( \
-        (diff -B ../include/linux/hash.h ../../include/linux/hash.h >/dev/null) \
-        || echo "Warning: tools/include/linux/hash.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \
-        (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \
-        || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/asm/disabled-features.h && ( \
-        (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/asm/required-features.h && ( \
-        (diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \
-        (diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/lib/memcpy_64.S && ( \
-        (diff -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \
-        || echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/lib/memset_64.S && ( \
-        (diff -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \
-        || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true
-	@(test -f ../../arch/arm/include/uapi/asm/perf_regs.h && ( \
-        (diff -B ../arch/arm/include/uapi/asm/perf_regs.h ../../arch/arm/include/uapi/asm/perf_regs.h >/dev/null) \
-        || echo "Warning: tools/arch/arm/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/arm64/include/uapi/asm/perf_regs.h && ( \
-        (diff -B ../arch/arm64/include/uapi/asm/perf_regs.h ../../arch/arm64/include/uapi/asm/perf_regs.h >/dev/null) \
-        || echo "Warning: tools/arch/arm64/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/powerpc/include/uapi/asm/perf_regs.h && ( \
-        (diff -B ../arch/powerpc/include/uapi/asm/perf_regs.h ../../arch/powerpc/include/uapi/asm/perf_regs.h >/dev/null) \
-        || echo "Warning: tools/arch/powerpc/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/perf_regs.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/perf_regs.h ../../arch/x86/include/uapi/asm/perf_regs.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/kvm.h ../../arch/x86/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/kvm_perf.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/kvm_perf.h ../../arch/x86/include/uapi/asm/kvm_perf.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/svm.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/svm.h ../../arch/x86/include/uapi/asm/svm.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/svm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/x86/include/uapi/asm/vmx.h && ( \
-        (diff -B ../arch/x86/include/uapi/asm/vmx.h ../../arch/x86/include/uapi/asm/vmx.h >/dev/null) \
-        || echo "Warning: tools/arch/x86/include/uapi/asm/vmx.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/powerpc/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/powerpc/include/uapi/asm/kvm.h ../../arch/powerpc/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/powerpc/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/s390/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/s390/include/uapi/asm/kvm.h ../../arch/s390/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/s390/include/uapi/asm/kvm_perf.h && ( \
-        (diff -B ../arch/s390/include/uapi/asm/kvm_perf.h ../../arch/s390/include/uapi/asm/kvm_perf.h >/dev/null) \
-        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/s390/include/uapi/asm/sie.h && ( \
-        (diff -B ../arch/s390/include/uapi/asm/sie.h ../../arch/s390/include/uapi/asm/sie.h >/dev/null) \
-        || echo "Warning: tools/arch/s390/include/uapi/asm/sie.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/arm/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/arm/include/uapi/asm/kvm.h ../../arch/arm/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/arm/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \
-        (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \
-        || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/arch_hweight.h && ( \
-        (diff -B ../include/asm-generic/bitops/arch_hweight.h ../../include/asm-generic/bitops/arch_hweight.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/arch_hweight.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/const_hweight.h && ( \
-        (diff -B ../include/asm-generic/bitops/const_hweight.h ../../include/asm-generic/bitops/const_hweight.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/const_hweight.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/__fls.h && ( \
-        (diff -B ../include/asm-generic/bitops/__fls.h ../../include/asm-generic/bitops/__fls.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/__fls.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/fls.h && ( \
-        (diff -B ../include/asm-generic/bitops/fls.h ../../include/asm-generic/bitops/fls.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/fls.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/asm-generic/bitops/fls64.h && ( \
-        (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \
-        || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/linux/coresight-pmu.h && ( \
-	(diff -B ../include/linux/coresight-pmu.h ../../include/linux/coresight-pmu.h >/dev/null) \
-	|| echo "Warning: tools/include/linux/coresight-pmu.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/uapi/asm-generic/mman-common.h && ( \
-	(diff -B ../include/uapi/asm-generic/mman-common.h ../../include/uapi/asm-generic/mman-common.h >/dev/null) \
-	|| echo "Warning: tools/include/uapi/asm-generic/mman-common.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/uapi/asm-generic/mman.h && ( \
-	(diff -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>$$" ../include/uapi/asm-generic/mman.h ../../include/uapi/asm-generic/mman.h >/dev/null) \
-	|| echo "Warning: tools/include/uapi/asm-generic/mman.h differs from kernel" >&2 )) || true
-	@(test -f ../../include/uapi/linux/mman.h && ( \
-	(diff -B -I "^#include <\(uapi/\)*asm/mman.h>$$" ../include/uapi/linux/mman.h ../../include/uapi/linux/mman.h >/dev/null) \
-	|| echo "Warning: tools/include/uapi/linux/mman.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(JEVENTS_IN): FORCE
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 465012b..6d9d6c4 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -48,7 +48,7 @@ static const struct option options[] = {
 };
 
 static const char * const bench_futex_lock_pi_usage[] = {
-	"perf bench futex requeue <options>",
+	"perf bench futex lock-pi <options>",
 	NULL
 };
 
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 4b41963..f8ca7a4 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -208,7 +208,7 @@ static void compute_stats(struct c2c_hist_entry *c2c_he,
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
 				struct perf_sample *sample,
-				struct perf_evsel *evsel __maybe_unused,
+				struct perf_evsel *evsel,
 				struct machine *machine)
 {
 	struct c2c_hists *c2c_hists = &c2c.hists;
@@ -379,7 +379,7 @@ static int symbol_width(struct hists *hists, struct sort_entry *se)
 
 static int c2c_width(struct perf_hpp_fmt *fmt,
 		     struct perf_hpp *hpp __maybe_unused,
-		     struct hists *hists __maybe_unused)
+		     struct hists *hists)
 {
 	struct c2c_fmt *c2c_fmt;
 	struct c2c_dimension *dim;
@@ -1127,7 +1127,7 @@ MEAN_ENTRY(mean_lcl_entry,  lcl_hitm);
 MEAN_ENTRY(mean_load_entry, load);
 
 static int
-cpucnt_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cpucnt_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he)
 {
 	struct c2c_hist_entry *c2c_he;
@@ -1141,7 +1141,7 @@ cpucnt_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
 }
 
 static int
-cl_idx_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cl_idx_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he)
 {
 	struct c2c_hist_entry *c2c_he;
@@ -1155,7 +1155,7 @@ cl_idx_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
 }
 
 static int
-cl_idx_empty_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		   struct hist_entry *he)
 {
 	int width = c2c_width(fmt, hpp, he->hists);
@@ -1779,7 +1779,6 @@ static int c2c_hists__init(struct c2c_hists *hists,
 	return hpp_list__parse(&hists->list, NULL, sort);
 }
 
-__maybe_unused
 static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
 			     const char *output,
 			     const char *sort)
@@ -2658,7 +2657,7 @@ static int perf_c2c__report(int argc, const char **argv)
 	return err;
 }
 
-static int parse_record_events(const struct option *opt __maybe_unused,
+static int parse_record_events(const struct option *opt,
 			       const char *str, int unset __maybe_unused)
 {
 	bool *event_set = (bool *) opt->value;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index d1ce29b..cd7bc4d 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -70,8 +70,8 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose (show counter open errors, etc)"),
-	OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"),
-	OPT_BOOLEAN('K', "--all-kernel", &all_kernel, "collect only kernel level data"),
+	OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"),
+	OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"),
 	OPT_END()
 	};
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fa26865..74d6a03 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1687,6 +1687,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	/* Enable ignoring missing threads when -u option is defined. */
+	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX;
+
 	err = -ENOMEM;
 	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d2afbe4..06cc759 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -648,7 +648,7 @@ report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
 }
 
 static int
-parse_branch_mode(const struct option *opt __maybe_unused,
+parse_branch_mode(const struct option *opt,
 		  const char *str __maybe_unused, int unset)
 {
 	int *branch_mode = opt->value;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 1a3f1be..d53e706 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -200,6 +200,7 @@ struct perf_sched {
 	/* options for timehist command */
 	bool		summary;
 	bool		summary_only;
+	bool		idle_hist;
 	bool		show_callchain;
 	unsigned int	max_stack;
 	bool		show_cpu_visual;
@@ -230,6 +231,15 @@ struct evsel_runtime {
 	u32 ncpu;       /* highest cpu slot allocated */
 };
 
+/* per cpu idle time data */
+struct idle_thread_runtime {
+	struct thread_runtime	tr;
+	struct thread		*last_thread;
+	struct rb_root		sorted_root;
+	struct callchain_root	callchain;
+	struct callchain_cursor	cursor;
+};
+
 /* track idle times per cpu */
 static struct thread **idle_threads;
 static int idle_max_cpu;
@@ -1765,7 +1775,7 @@ static u64 perf_evsel__get_time(struct perf_evsel *evsel, u32 cpu)
 	return r->last_time[cpu];
 }
 
-static int comm_width = 20;
+static int comm_width = 30;
 
 static char *timehist_get_commstr(struct thread *thread)
 {
@@ -1807,7 +1817,7 @@ static void timehist_header(struct perf_sched *sched)
 		printf(" ");
 	}
 
-	printf(" %-20s  %9s  %9s  %9s",
+	printf(" %-*s  %9s  %9s  %9s", comm_width,
 		"task name", "wait time", "sch delay", "run time");
 
 	printf("\n");
@@ -1820,7 +1830,8 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %*s ", ncpus, "");
 
-	printf(" %-20s  %9s  %9s  %9s\n", "[tid/pid]", "(msec)", "(msec)", "(msec)");
+	printf(" %-*s  %9s  %9s  %9s\n", comm_width,
+	       "[tid/pid]", "(msec)", "(msec)", "(msec)");
 
 	/*
 	 * separator
@@ -1830,7 +1841,7 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %.*s ", ncpus, graph_dotted_line);
 
-	printf(" %.20s  %.9s  %.9s  %.9s",
+	printf(" %.*s  %.9s  %.9s  %.9s", comm_width,
 		graph_dotted_line, graph_dotted_line, graph_dotted_line,
 		graph_dotted_line);
 
@@ -1939,39 +1950,40 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 	r->total_run_time += r->dt_run;
 }
 
-static bool is_idle_sample(struct perf_sched *sched,
-			   struct perf_sample *sample,
-			   struct perf_evsel *evsel,
-			   struct machine *machine)
+static bool is_idle_sample(struct perf_sample *sample,
+			   struct perf_evsel *evsel)
 {
-	struct thread *thread;
-	struct callchain_cursor *cursor = &callchain_cursor;
-
 	/* pid 0 == swapper == idle task */
-	if (sample->pid == 0)
-		return true;
+	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0)
+		return perf_evsel__intval(evsel, sample, "prev_pid") == 0;
 
-	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0) {
-		if (perf_evsel__intval(evsel, sample, "prev_pid") == 0)
-			return true;
-	}
+	return sample->pid == 0;
+}
+
+static void save_task_callchain(struct perf_sched *sched,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct callchain_cursor *cursor = &callchain_cursor;
+	struct thread *thread;
 
 	/* want main thread for process - has maps */
 	thread = machine__findnew_thread(machine, sample->pid, sample->pid);
 	if (thread == NULL) {
 		pr_debug("Failed to get thread for pid %d.\n", sample->pid);
-		return false;
+		return;
 	}
 
 	if (!symbol_conf.use_callchain || sample->callchain == NULL)
-		return false;
+		return;
 
 	if (thread__resolve_callchain(thread, cursor, evsel, sample,
 				      NULL, NULL, sched->max_stack + 2) != 0) {
 		if (verbose)
 			error("Failed to resolve callchain. Skipping\n");
 
-		return false;
+		return;
 	}
 
 	callchain_cursor_commit(cursor);
@@ -1994,8 +2006,24 @@ static bool is_idle_sample(struct perf_sched *sched,
 
 		callchain_cursor_advance(cursor);
 	}
+}
 
-	return false;
+static int init_idle_thread(struct thread *thread)
+{
+	struct idle_thread_runtime *itr;
+
+	thread__set_comm(thread, idle_comm, 0);
+
+	itr = zalloc(sizeof(*itr));
+	if (itr == NULL)
+		return -ENOMEM;
+
+	init_stats(&itr->tr.run_stats);
+	callchain_init(&itr->callchain);
+	callchain_cursor_reset(&itr->cursor);
+	thread__set_priv(thread, itr);
+
+	return 0;
 }
 
 /*
@@ -2004,7 +2032,7 @@ static bool is_idle_sample(struct perf_sched *sched,
  */
 static int init_idle_threads(int ncpu)
 {
-	int i;
+	int i, ret;
 
 	idle_threads = zalloc(ncpu * sizeof(struct thread *));
 	if (!idle_threads)
@@ -2018,7 +2046,9 @@ static int init_idle_threads(int ncpu)
 		if (idle_threads[i] == NULL)
 			return -ENOMEM;
 
-		thread__set_comm(idle_threads[i], idle_comm, 0);
+		ret = init_idle_thread(idle_threads[i]);
+		if (ret < 0)
+			return ret;
 	}
 
 	return 0;
@@ -2065,14 +2095,23 @@ static struct thread *get_idle_thread(int cpu)
 		idle_threads[cpu] = thread__new(0, 0);
 
 		if (idle_threads[cpu]) {
-			idle_threads[cpu]->tid = 0;
-			thread__set_comm(idle_threads[cpu], idle_comm, 0);
+			if (init_idle_thread(idle_threads[cpu]) < 0)
+				return NULL;
 		}
 	}
 
 	return idle_threads[cpu];
 }
 
+static void save_idle_callchain(struct idle_thread_runtime *itr,
+				struct perf_sample *sample)
+{
+	if (!symbol_conf.use_callchain || sample->callchain == NULL)
+		return;
+
+	callchain_cursor__copy(&itr->cursor, &callchain_cursor);
+}
+
 /*
  * handle runtime stats saved per thread
  */
@@ -2111,7 +2150,7 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 {
 	struct thread *thread;
 
-	if (is_idle_sample(sched, sample, evsel, machine)) {
+	if (is_idle_sample(sample, evsel)) {
 		thread = get_idle_thread(sample->cpu);
 		if (thread == NULL)
 			pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
@@ -2124,13 +2163,37 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 			pr_debug("Failed to get thread for tid %d. skipping sample.\n",
 				 sample->tid);
 		}
+
+		save_task_callchain(sched, sample, evsel, machine);
+		if (sched->idle_hist) {
+			struct thread *idle;
+			struct idle_thread_runtime *itr;
+
+			idle = get_idle_thread(sample->cpu);
+			if (idle == NULL) {
+				pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
+				return NULL;
+			}
+
+			itr = thread__priv(idle);
+			if (itr == NULL)
+				return NULL;
+
+			itr->last_thread = thread;
+
+			/* copy task callchain when entering to idle */
+			if (perf_evsel__intval(evsel, sample, "next_pid") == 0)
+				save_idle_callchain(itr, sample);
+		}
 	}
 
 	return thread;
 }
 
 static bool timehist_skip_sample(struct perf_sched *sched,
-				 struct thread *thread)
+				 struct thread *thread,
+				 struct perf_evsel *evsel,
+				 struct perf_sample *sample)
 {
 	bool rc = false;
 
@@ -2139,10 +2202,19 @@ static bool timehist_skip_sample(struct perf_sched *sched,
 		sched->skipped_samples++;
 	}
 
+	if (sched->idle_hist) {
+		if (strcmp(perf_evsel__name(evsel), "sched:sched_switch"))
+			rc = true;
+		else if (perf_evsel__intval(evsel, sample, "prev_pid") != 0 &&
+			 perf_evsel__intval(evsel, sample, "next_pid") != 0)
+			rc = true;
+	}
+
 	return rc;
 }
 
 static void timehist_print_wakeup_event(struct perf_sched *sched,
+					struct perf_evsel *evsel,
 					struct perf_sample *sample,
 					struct machine *machine,
 					struct thread *awakened)
@@ -2155,8 +2227,8 @@ static void timehist_print_wakeup_event(struct perf_sched *sched,
 		return;
 
 	/* show wakeup unless both awakee and awaker are filtered */
-	if (timehist_skip_sample(sched, thread) &&
-	    timehist_skip_sample(sched, awakened)) {
+	if (timehist_skip_sample(sched, thread, evsel, sample) &&
+	    timehist_skip_sample(sched, awakened, evsel, sample)) {
 		return;
 	}
 
@@ -2201,7 +2273,7 @@ static int timehist_sched_wakeup_event(struct perf_tool *tool,
 	/* show wakeups if requested */
 	if (sched->show_wakeups &&
 	    !perf_time__skip_sample(&sched->ptime, sample->time))
-		timehist_print_wakeup_event(sched, sample, machine, thread);
+		timehist_print_wakeup_event(sched, evsel, sample, machine, thread);
 
 	return 0;
 }
@@ -2228,8 +2300,8 @@ static void timehist_print_migration_event(struct perf_sched *sched,
 	if (thread == NULL)
 		return;
 
-	if (timehist_skip_sample(sched, thread) &&
-	    timehist_skip_sample(sched, migrated)) {
+	if (timehist_skip_sample(sched, thread, evsel, sample) &&
+	    timehist_skip_sample(sched, migrated, evsel, sample)) {
 		return;
 	}
 
@@ -2314,7 +2386,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 		goto out;
 	}
 
-	if (timehist_skip_sample(sched, thread))
+	if (timehist_skip_sample(sched, thread, evsel, sample))
 		goto out;
 
 	tr = thread__get_runtime(thread);
@@ -2333,7 +2405,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	if (ptime->start && ptime->start > t)
 		goto out;
 
-	if (ptime->start > tprev)
+	if (tprev && ptime->start > tprev)
 		tprev = ptime->start;
 
 	/*
@@ -2350,7 +2422,39 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 			t = ptime->end;
 	}
 
-	timehist_update_runtime_stats(tr, t, tprev);
+	if (!sched->idle_hist || thread->tid == 0) {
+		timehist_update_runtime_stats(tr, t, tprev);
+
+		if (sched->idle_hist) {
+			struct idle_thread_runtime *itr = (void *)tr;
+			struct thread_runtime *last_tr;
+
+			BUG_ON(thread->tid != 0);
+
+			if (itr->last_thread == NULL)
+				goto out;
+
+			/* add current idle time as last thread's runtime */
+			last_tr = thread__get_runtime(itr->last_thread);
+			if (last_tr == NULL)
+				goto out;
+
+			timehist_update_runtime_stats(last_tr, t, tprev);
+			/*
+			 * remove delta time of last thread as it's not updated
+			 * and otherwise it will show an invalid value next
+			 * time.  we only care total run time and run stat.
+			 */
+			last_tr->dt_run = 0;
+			last_tr->dt_wait = 0;
+			last_tr->dt_delay = 0;
+
+			if (itr->cursor.nr)
+				callchain_append(&itr->callchain, &itr->cursor, t - tprev);
+
+			itr->last_thread = NULL;
+		}
+	}
 
 	if (!sched->summary_only)
 		timehist_print_sample(sched, sample, &al, thread, t);
@@ -2457,6 +2561,60 @@ static int show_deadthread_runtime(struct thread *t, void *priv)
 	return __show_thread_runtime(t, priv);
 }
 
+static size_t callchain__fprintf_folded(FILE *fp, struct callchain_node *node)
+{
+	const char *sep = " <- ";
+	struct callchain_list *chain;
+	size_t ret = 0;
+	char bf[1024];
+	bool first;
+
+	if (node == NULL)
+		return 0;
+
+	ret = callchain__fprintf_folded(fp, node->parent);
+	first = (ret == 0);
+
+	list_for_each_entry(chain, &node->val, list) {
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+		if (chain->ms.sym && chain->ms.sym->ignore)
+			continue;
+		ret += fprintf(fp, "%s%s", first ? "" : sep,
+			       callchain_list__sym_name(chain, bf, sizeof(bf),
+							false));
+		first = false;
+	}
+
+	return ret;
+}
+
+static size_t timehist_print_idlehist_callchain(struct rb_root *root)
+{
+	size_t ret = 0;
+	FILE *fp = stdout;
+	struct callchain_node *chain;
+	struct rb_node *rb_node = rb_first(root);
+
+	printf("  %16s  %8s  %s\n", "Idle time (msec)", "Count", "Callchains");
+	printf("  %.16s  %.8s  %.50s\n", graph_dotted_line, graph_dotted_line,
+	       graph_dotted_line);
+
+	while (rb_node) {
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+		rb_node = rb_next(rb_node);
+
+		ret += fprintf(fp, "  ");
+		print_sched_time(chain->hit, 12);
+		ret += 16;  /* print_sched_time returns 2nd arg + 4 */
+		ret += fprintf(fp, " %8d  ", chain->count);
+		ret += callchain__fprintf_folded(fp, chain);
+		ret += fprintf(fp, "\n");
+	}
+
+	return ret;
+}
+
 static void timehist_print_summary(struct perf_sched *sched,
 				   struct perf_session *session)
 {
@@ -2469,12 +2627,15 @@ static void timehist_print_summary(struct perf_sched *sched,
 
 	memset(&totals, 0, sizeof(totals));
 
-	if (comm_width < 30)
-		comm_width = 30;
-
-	printf("\nRuntime summary\n");
-	printf("%*s  parent   sched-in  ", comm_width, "comm");
-	printf("   run-time    min-run     avg-run     max-run  stddev  migrations\n");
+	if (sched->idle_hist) {
+		printf("\nIdle-time summary\n");
+		printf("%*s  parent  sched-out  ", comm_width, "comm");
+		printf("  idle-time   min-idle    avg-idle    max-idle  stddev  migrations\n");
+	} else {
+		printf("\nRuntime summary\n");
+		printf("%*s  parent   sched-in  ", comm_width, "comm");
+		printf("   run-time    min-run     avg-run     max-run  stddev  migrations\n");
+	}
 	printf("%*s            (count)  ", comm_width, "");
 	printf("     (msec)     (msec)      (msec)      (msec)       %%\n");
 	printf("%.117s\n", graph_dotted_line);
@@ -2490,7 +2651,7 @@ static void timehist_print_summary(struct perf_sched *sched,
 		printf("<no terminated tasks>\n");
 
 	/* CPU idle stats not tracked when samples were skipped */
-	if (sched->skipped_samples)
+	if (sched->skipped_samples && !sched->idle_hist)
 		return;
 
 	printf("\nIdle stats:\n");
@@ -2509,6 +2670,35 @@ static void timehist_print_summary(struct perf_sched *sched,
 			printf("    CPU %2d idle entire time window\n", i);
 	}
 
+	if (sched->idle_hist && symbol_conf.use_callchain) {
+		callchain_param.mode  = CHAIN_FOLDED;
+		callchain_param.value = CCVAL_PERIOD;
+
+		callchain_register_param(&callchain_param);
+
+		printf("\nIdle stats by callchain:\n");
+		for (i = 0; i < idle_max_cpu; ++i) {
+			struct idle_thread_runtime *itr;
+
+			t = idle_threads[i];
+			if (!t)
+				continue;
+
+			itr = thread__priv(t);
+			if (itr == NULL)
+				continue;
+
+			callchain_param.sort(&itr->sorted_root, &itr->callchain,
+					     0, &callchain_param);
+
+			printf("  CPU %2d:", i);
+			print_sched_time(itr->tr.total_run_time, 6);
+			printf(" msec\n");
+			timehist_print_idlehist_callchain(&itr->sorted_root);
+			printf("\n");
+		}
+	}
+
 	printf("\n"
 	       "    Total number of unique tasks: %" PRIu64 "\n"
 	       "Total number of context switches: %" PRIu64 "\n"
@@ -3036,6 +3226,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"),
 	OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"),
 	OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"),
+	OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
 	OPT_STRING(0, "time", &sched.time_str, "str",
 		   "Time span for analysis (start,stop)"),
 	OPT_PARENT(sched_options)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 688dea7..a02f2e9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2195,7 +2195,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+int process_stat_config_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_session *session __maybe_unused)
 {
@@ -2238,7 +2238,7 @@ static int set_maps(struct perf_stat *st)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool __maybe_unused,
+int process_thread_map_event(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_session *session __maybe_unused)
 {
@@ -2257,7 +2257,7 @@ int process_thread_map_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+int process_cpu_map_event(struct perf_tool *tool,
 			  union perf_event *event,
 			  struct perf_session *session __maybe_unused)
 {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
new file mode 100755
index 0000000..c747bfd
--- /dev/null
+++ b/tools/perf/check-headers.sh
@@ -0,0 +1,59 @@
+#!/bin/sh
+
+HEADERS='
+include/uapi/linux/perf_event.h
+include/linux/hash.h
+include/uapi/linux/hw_breakpoint.h
+arch/x86/include/asm/disabled-features.h
+arch/x86/include/asm/required-features.h
+arch/x86/include/asm/cpufeatures.h
+arch/arm/include/uapi/asm/perf_regs.h
+arch/arm64/include/uapi/asm/perf_regs.h
+arch/powerpc/include/uapi/asm/perf_regs.h
+arch/x86/include/uapi/asm/perf_regs.h
+arch/x86/include/uapi/asm/kvm.h
+arch/x86/include/uapi/asm/kvm_perf.h
+arch/x86/include/uapi/asm/svm.h
+arch/x86/include/uapi/asm/vmx.h
+arch/powerpc/include/uapi/asm/kvm.h
+arch/s390/include/uapi/asm/kvm.h
+arch/s390/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/sie.h
+arch/arm/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/kvm.h
+include/asm-generic/bitops/arch_hweight.h
+include/asm-generic/bitops/const_hweight.h
+include/asm-generic/bitops/__fls.h
+include/asm-generic/bitops/fls.h
+include/asm-generic/bitops/fls64.h
+include/linux/coresight-pmu.h
+include/uapi/asm-generic/mman-common.h
+'
+
+check () {
+  file=$1
+  opts=
+
+  shift
+  while [ -n "$*" ]; do
+    opts="$opts \"$1\""
+    shift
+  done
+
+  cmd="diff $opts ../$file ../../$file > /dev/null"
+
+  test -f ../../$file &&
+  eval $cmd || echo "Warning: $file differs from kernel" >&2
+}
+
+
+# simple diff check
+for i in $HEADERS; do
+  check $i -B
+done
+
+# diff with extra ignore lines
+check arch/x86/lib/memcpy_64.S        -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
+check arch/x86/lib/memset_64.S        -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
+check include/uapi/asm-generic/mman.h -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
+check include/uapi/linux/mman.h       -B -I "^#include <\(uapi/\)*asm/mman.h>"
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 9a0236a..1c27d94 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -55,6 +55,7 @@ struct record_opts {
 	bool	     all_user;
 	bool	     tail_synthesize;
 	bool	     overwrite;
+	bool	     ignore_missing_thread;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 2360520..a77dcc0 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -186,6 +186,10 @@ static struct test generic_tests[] = {
 		.func = test__thread_map_synthesize,
 	},
 	{
+		.desc = "Remove thread map",
+		.func = test__thread_map_remove,
+	},
+	{
 		.desc = "Synthesize cpu map",
 		.func = test__cpu_map_synthesize,
 	},
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 0d7b251..a512f0c 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -80,6 +80,7 @@ const char *test__bpf_subtest_get_desc(int subtest);
 int test__bpf_subtest_get_nr(void);
 int test_session_topology(int subtest);
 int test__thread_map_synthesize(int subtest);
+int test__thread_map_remove(int subtest);
 int test__cpu_map_synthesize(int subtest);
 int test__synthesize_stat_config(int subtest);
 int test__synthesize_stat(int subtest);
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index cee2a2c..a4a4b46 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -1,3 +1,4 @@
+#include <stdlib.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <sys/prctl.h>
@@ -93,3 +94,46 @@ int test__thread_map_synthesize(int subtest __maybe_unused)
 
 	return 0;
 }
+
+int test__thread_map_remove(int subtest __maybe_unused)
+{
+	struct thread_map *threads;
+	char *str;
+	int i;
+
+	TEST_ASSERT_VAL("failed to allocate map string",
+			asprintf(&str, "%d,%d", getpid(), getppid()) >= 0);
+
+	threads = thread_map__new_str(str, NULL, 0);
+
+	TEST_ASSERT_VAL("failed to allocate thread_map",
+			threads);
+
+	if (verbose)
+		thread_map__fprintf(threads, stderr);
+
+	TEST_ASSERT_VAL("failed to remove thread",
+			!thread_map__remove(threads, 0));
+
+	TEST_ASSERT_VAL("thread_map count != 1", threads->nr == 1);
+
+	if (verbose)
+		thread_map__fprintf(threads, stderr);
+
+	TEST_ASSERT_VAL("failed to remove thread",
+			!thread_map__remove(threads, 0));
+
+	TEST_ASSERT_VAL("thread_map count != 0", threads->nr == 0);
+
+	if (verbose)
+		thread_map__fprintf(threads, stderr);
+
+	TEST_ASSERT_VAL("failed to not remove thread",
+			thread_map__remove(threads, 0));
+
+	for (i = 0; i < threads->nr; i++)
+		free(threads->map[i].comm);
+
+	free(threads);
+	return 0;
+}
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index fd710ab..af1cfde 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -42,7 +42,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 	P_MMAP_FLAG(SHARED);
 	P_MMAP_FLAG(PRIVATE);
+#ifdef MAP_32BIT
 	P_MMAP_FLAG(32BIT);
+#endif
 	P_MMAP_FLAG(ANONYMOUS);
 	P_MMAP_FLAG(DENYWRITE);
 	P_MMAP_FLAG(EXECUTABLE);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ec7a30f..ba36aac 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -215,7 +215,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 			ui_browser__set_color(browser, color);
 		if (dl->ins.ops && dl->ins.ops->scnprintf) {
 			if (ins__is_jump(&dl->ins)) {
-				bool fwd = dl->ops.target.offset > (u64)dl->offset;
+				bool fwd = dl->ops.target.offset > dl->offset;
 
 				ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
 								    SLSMG_UARROW_CHAR);
@@ -245,7 +245,8 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy
 {
 	if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins)
 	    || !disasm_line__has_offset(dl)
-	    || dl->ops.target.offset >= symbol__size(sym))
+	    || dl->ops.target.offset < 0
+	    || dl->ops.target.offset >= (s64)symbol__size(sym))
 		return false;
 
 	return true;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ea7e0de..06cc04e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -223,13 +223,19 @@ bool ins__is_call(const struct ins *ins)
 static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused)
 {
 	const char *s = strchr(ops->raw, '+');
+	const char *c = strchr(ops->raw, ',');
 
-	ops->target.addr = strtoull(ops->raw, NULL, 16);
-
-	if (s++ != NULL)
-		ops->target.offset = strtoull(s, NULL, 16);
+	if (c++ != NULL)
+		ops->target.addr = strtoull(c, NULL, 16);
 	else
-		ops->target.offset = UINT64_MAX;
+		ops->target.addr = strtoull(ops->raw, NULL, 16);
+
+	if (s++ != NULL) {
+		ops->target.offset = strtoull(s, NULL, 16);
+		ops->target.offset_avail = true;
+	} else {
+		ops->target.offset_avail = false;
+	}
 
 	return 0;
 }
@@ -237,7 +243,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	if (!ops->target.addr)
+	if (!ops->target.addr || ops->target.offset < 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
 	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
@@ -641,7 +647,8 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
-	if (addr < sym->start || addr >= sym->end) {
+	if ((addr < sym->start || addr >= sym->end) &&
+	    (addr != sym->end || sym->start != sym->end)) {
 		pr_debug("%s(%d): ERANGE! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 "\n",
 		       __func__, __LINE__, sym->name, sym->start, addr, sym->end);
 		return -ERANGE;
@@ -1205,9 +1212,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 	if (dl == NULL)
 		return -1;
 
-	if (dl->ops.target.offset == UINT64_MAX)
+	if (!disasm_line__has_offset(dl)) {
 		dl->ops.target.offset = dl->ops.target.addr -
 					map__rip_2objdump(map, sym->start);
+		dl->ops.target.offset_avail = true;
+	}
 
 	/* kcore has no symbols, so add the call target name */
 	if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.name) {
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 87e4cad..09776b5 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -24,7 +24,8 @@ struct ins_operands {
 		char	*raw;
 		char	*name;
 		u64	addr;
-		u64	offset;
+		s64	offset;
+		bool	offset_avail;
 	} target;
 	union {
 		struct {
@@ -68,7 +69,7 @@ struct disasm_line {
 
 static inline bool disasm_line__has_offset(const struct disasm_line *dl)
 {
-	return dl->ops.target.offset != UINT64_MAX;
+	return dl->ops.target.offset_avail;
 }
 
 void disasm_line__free(struct disasm_line *dl);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b2365a63..04e536a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -990,6 +990,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	 * it overloads any global configuration.
 	 */
 	apply_config_terms(evsel, opts);
+
+	evsel->ignore_missing_thread = opts->ignore_missing_thread;
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -1419,6 +1421,33 @@ static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
 	return fprintf(fp, "  %-32s %s\n", name, val);
 }
 
+static bool ignore_missing_thread(struct perf_evsel *evsel,
+				  struct thread_map *threads,
+				  int thread, int err)
+{
+	if (!evsel->ignore_missing_thread)
+		return false;
+
+	/* The system wide setup does not work with threads. */
+	if (evsel->system_wide)
+		return false;
+
+	/* The -ESRCH is perf event syscall errno for pid's not found. */
+	if (err != -ESRCH)
+		return false;
+
+	/* If there's only one thread, let it fail. */
+	if (threads->nr == 1)
+		return false;
+
+	if (thread_map__remove(threads, thread))
+		return false;
+
+	pr_warning("WARNING: Ignored open failure for pid %d\n",
+		   thread_map__pid(threads, thread));
+	return true;
+}
+
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			      struct thread_map *threads)
 {
@@ -1474,7 +1503,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
 		for (thread = 0; thread < nthreads; thread++) {
-			int group_fd;
+			int fd, group_fd;
 
 			if (!evsel->cgrp && !evsel->system_wide)
 				pid = thread_map__pid(threads, thread);
@@ -1484,21 +1513,37 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
 				  pid, cpus->map[cpu], group_fd, flags);
 
-			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
-								     pid,
-								     cpus->map[cpu],
-								     group_fd, flags);
-			if (FD(evsel, cpu, thread) < 0) {
+			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
+						 group_fd, flags);
+
+			FD(evsel, cpu, thread) = fd;
+
+			if (fd < 0) {
 				err = -errno;
+
+				if (ignore_missing_thread(evsel, threads, thread, err)) {
+					/*
+					 * We just removed 1 thread, so take a step
+					 * back on thread index and lower the upper
+					 * nthreads limit.
+					 */
+					nthreads--;
+					thread--;
+
+					/* ... and pretend like nothing have happened. */
+					err = 0;
+					continue;
+				}
+
 				pr_debug2("\nsys_perf_event_open failed, error %d\n",
 					  err);
 				goto try_fallback;
 			}
 
-			pr_debug2(" = %d\n", FD(evsel, cpu, thread));
+			pr_debug2(" = %d\n", fd);
 
 			if (evsel->bpf_fd >= 0) {
-				int evt_fd = FD(evsel, cpu, thread);
+				int evt_fd = fd;
 				int bpf_fd = evsel->bpf_fd;
 
 				err = ioctl(evt_fd,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6abb89c..06ef6f2 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -120,6 +120,7 @@ struct perf_evsel {
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
+	bool			ignore_missing_thread;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index df2482b..dc93940 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1459,7 +1459,8 @@ int dso__load(struct dso *dso, struct map *map)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (is_regular_file(dso->long_name) &&
+	if (!dso->has_build_id &&
+	    is_regular_file(dso->long_name) &&
 	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 40585f5..f9eab20 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -448,3 +448,25 @@ bool thread_map__has(struct thread_map *threads, pid_t pid)
 
 	return false;
 }
+
+int thread_map__remove(struct thread_map *threads, int idx)
+{
+	int i;
+
+	if (threads->nr < 1)
+		return -EINVAL;
+
+	if (idx >= threads->nr)
+		return -EINVAL;
+
+	/*
+	 * Free the 'idx' item and shift the rest up.
+	 */
+	free(threads->map[idx].comm);
+
+	for (i = idx; i < threads->nr - 1; i++)
+		threads->map[i] = threads->map[i + 1];
+
+	threads->nr--;
+	return 0;
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index bd3b971..ea0ef08 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -58,4 +58,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread)
 
 void thread_map__read_comms(struct thread_map *threads);
 bool thread_map__has(struct thread_map *threads, pid_t pid);
+int thread_map__remove(struct thread_map *threads, int idx);
 #endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 8561e7d..8792ad8 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -10,6 +10,7 @@
 turbostat : turbostat.c
 CFLAGS +=	-Wall
 CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
+CFLAGS +=	-DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 492e84f..03cb639 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -25,9 +25,27 @@
 .SS Options
 Options can be specified with a single or double '-', and only as much of the option
 name as necessary to disambiguate it from others is necessary.  Note that options are case-sensitive.
-\fB--Counter MSR#\fP shows the delta of the specified 64-bit MSR counter.
 .PP
-\fB--counter MSR#\fP shows the delta of the specified 32-bit MSR counter.
+\fB--add attributes\fP add column with counter having specified 'attributes'.  The 'location' attribute is required, all others are optional.
+.nf
+	location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP}
+		msrDDD is a decimal offset, eg. msr16
+		msr0xXXX is a hex offset, eg. msr0x10
+
+	scope: {\fBcpu\fP | \fBcore\fP | \fBpackage\fP}
+		sample and print the counter for every cpu, core, or package.
+		default: cpu
+
+	size: {\fBu32\fP | \fBu64\fP }
+		MSRs are read as 64-bits, u32 truncates the displayed value to 32-bits.
+		default: u64
+
+	format: {\fBraw\fP | \fBdelta\fP | \fBpercent\fP}
+		'raw' shows the MSR contents in hex.
+		'delta' shows the difference in values during the measurement interval.
+		'percent' shows the delta as a percentage of the cycles elapsed.
+		default: delta
+.fi
 .PP
 \fB--Dump\fP displays the raw counter values.
 .PP
@@ -43,10 +61,6 @@
 .PP
 \fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts.
 .PP
-\fB--MSR MSR#\fP shows the specified 64-bit MSR value.
-.PP
-\fB--msr MSR#\fP shows the specified 32-bit MSR value.
-.PP
 \fB--Package\fP limits output to the system summary plus the 1st thread in each Package.
 .PP
 \fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package.  Ie. it skips hyper-threaded siblings.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 3e199b5..f13f61b 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -21,6 +21,7 @@
 
 #define _GNU_SOURCE
 #include MSRHEADER
+#include INTEL_FAMILY_HEADER
 #include <stdarg.h>
 #include <stdio.h>
 #include <err.h>
@@ -51,8 +52,6 @@ unsigned int debug;
 unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int dump_only;
-unsigned int skip_c0;
-unsigned int skip_c1;
 unsigned int do_nhm_cstates;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
@@ -72,10 +71,6 @@ unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
 unsigned int do_nhm_platform_info;
-unsigned int extra_msr_offset32;
-unsigned int extra_msr_offset64;
-unsigned int extra_delta_offset32;
-unsigned int extra_delta_offset64;
 unsigned int aperf_mperf_multiplier = 1;
 int do_irq = 1;
 int do_smi;
@@ -131,9 +126,8 @@ unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
 #define RAPL_DRAM_POWER_INFO	(1 << 5)
 					/* 0x61c MSR_DRAM_POWER_INFO */
 
-#define RAPL_CORES		(1 << 6)
+#define RAPL_CORES_POWER_LIMIT	(1 << 6)
 					/* 0x638 MSR_PP0_POWER_LIMIT */
-					/* 0x639 MSR_PP0_ENERGY_STATUS */
 #define RAPL_CORE_POLICY	(1 << 7)
 					/* 0x63a MSR_PP0_POLICY */
 
@@ -141,11 +135,20 @@ unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
 					/* 0x640 MSR_PP1_POWER_LIMIT */
 					/* 0x641 MSR_PP1_ENERGY_STATUS */
 					/* 0x642 MSR_PP1_POLICY */
+
+#define RAPL_CORES_ENERGY_STATUS	(1 << 9)
+					/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
 #define	TJMAX_DEFAULT	100
 
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 
-int aperf_mperf_unstable;
+/*
+ * buffer size used by sscanf() for added column names
+ * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters
+ */
+#define	NAME_BYTES 20
+
 int backwards_count;
 char *progname;
 
@@ -157,16 +160,13 @@ struct thread_data {
 	unsigned long long aperf;
 	unsigned long long mperf;
 	unsigned long long c1;
-	unsigned long long extra_msr64;
-	unsigned long long extra_delta64;
-	unsigned long long extra_msr32;
-	unsigned long long extra_delta32;
 	unsigned int irq_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
 	unsigned int flags;
 #define CPU_IS_FIRST_THREAD_IN_CORE	0x2
 #define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
+	unsigned long long counter[1];
 } *thread_even, *thread_odd;
 
 struct core_data {
@@ -175,6 +175,7 @@ struct core_data {
 	unsigned long long c7;
 	unsigned int core_temp_c;
 	unsigned int core_id;
+	unsigned long long counter[1];
 } *core_even, *core_odd;
 
 struct pkg_data {
@@ -199,7 +200,7 @@ struct pkg_data {
 	unsigned int rapl_pkg_perf_status;	/* MSR_PKG_PERF_STATUS */
 	unsigned int rapl_dram_perf_status;	/* MSR_DRAM_PERF_STATUS */
 	unsigned int pkg_temp_c;
-
+	unsigned long long counter[1];
 } *package_even, *package_odd;
 
 #define ODD_COUNTERS thread_odd, core_odd, package_odd
@@ -213,11 +214,33 @@ struct pkg_data {
 	(core_base + (pkg_no) * topo.num_cores_per_pkg + (core_no))
 #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
 
+enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE};
+enum counter_type {COUNTER_CYCLES, COUNTER_SECONDS};
+enum counter_format {FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT};
+
+struct msr_counter {
+	unsigned int msr_num;
+	char name[NAME_BYTES];
+	unsigned int width;
+	enum counter_type type;
+	enum counter_format format;
+	struct msr_counter *next;
+};
+
+struct sys_counters {
+	unsigned int thread_counter_bytes;
+	unsigned int core_counter_bytes;
+	unsigned int package_counter_bytes;
+	struct msr_counter *tp;
+	struct msr_counter *cp;
+	struct msr_counter *pp;
+} sys;
+
 struct system_summary {
 	struct thread_data threads;
 	struct core_data cores;
 	struct pkg_data packages;
-} sum, average;
+} average;
 
 
 struct topo_params {
@@ -319,120 +342,148 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 /*
  * Example Format w/ field column widths:
  *
- *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     IRQ   SMI   Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp  GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
+ *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     IRQ   SMI   Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 ThreadC CoreTmp  CoreCnt PkgTmp  GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt PkgCnt
  * 12345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
  */
 
 void print_header(void)
 {
-	if (show_pkg)
-		outp += sprintf(outp, " Package");
-	if (show_core)
-		outp += sprintf(outp, "    Core");
-	if (show_cpu)
-		outp += sprintf(outp, "     CPU");
-	if (has_aperf)
-		outp += sprintf(outp, " Avg_MHz");
-	if (has_aperf)
-		outp += sprintf(outp, "   Busy%%");
-	if (has_aperf)
-		outp += sprintf(outp, " Bzy_MHz");
-	outp += sprintf(outp, " TSC_MHz");
+	struct msr_counter *mp;
 
-	if (extra_delta_offset32)
-		outp += sprintf(outp, "  count 0x%03X", extra_delta_offset32);
-	if (extra_delta_offset64)
-		outp += sprintf(outp, "  COUNT 0x%03X", extra_delta_offset64);
-	if (extra_msr_offset32)
-		outp += sprintf(outp, "   MSR 0x%03X", extra_msr_offset32);
-	if (extra_msr_offset64)
-		outp += sprintf(outp, "           MSR 0x%03X", extra_msr_offset64);
+	if (show_pkg)
+		outp += sprintf(outp, "\tPackage");
+	if (show_core)
+		outp += sprintf(outp, "\tCore");
+	if (show_cpu)
+		outp += sprintf(outp, "\tCPU");
+	if (has_aperf)
+		outp += sprintf(outp, "\tAvg_MHz");
+	if (has_aperf)
+		outp += sprintf(outp, "\tBusy%%");
+	if (has_aperf)
+		outp += sprintf(outp, "\tBzy_MHz");
+	outp += sprintf(outp, "\tTSC_MHz");
 
 	if (!debug)
 		goto done;
 
 	if (do_irq)
-		outp += sprintf(outp, "     IRQ");
+		outp += sprintf(outp, "\tIRQ");
 	if (do_smi)
-		outp += sprintf(outp, "     SMI");
+		outp += sprintf(outp, "\tSMI");
 
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "  CPU%%c1");
+		outp += sprintf(outp, "\tCPU%%c1");
 	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "  CPU%%c3");
+		outp += sprintf(outp, "\tCPU%%c3");
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "  CPU%%c6");
+		outp += sprintf(outp, "\tCPU%%c6");
 	if (do_snb_cstates)
-		outp += sprintf(outp, "  CPU%%c7");
+		outp += sprintf(outp, "\tCPU%%c7");
+
+	for (mp = sys.tp; mp; mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 64)
+				outp += sprintf(outp, "\t%18.18s", mp->name);
+			else
+				outp += sprintf(outp, "\t%10.10s", mp->name);
+		} else {
+			outp += sprintf(outp, "\t%-7.7s", mp->name);
+		}
+	}
 
 	if (do_dts)
-		outp += sprintf(outp, " CoreTmp");
+		outp += sprintf(outp, "\tCoreTmp");
+
+	for (mp = sys.cp; mp; mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 64)
+				outp += sprintf(outp, "\t%18.18s", mp->name);
+			else
+				outp += sprintf(outp, "\t%10.10s", mp->name);
+		} else {
+			outp += sprintf(outp, "\t%-7.7s", mp->name);
+		}
+	}
+
 	if (do_ptm)
-		outp += sprintf(outp, "  PkgTmp");
+		outp += sprintf(outp, "\tPkgTmp");
 
 	if (do_gfx_rc6_ms)
-		outp += sprintf(outp, " GFX%%rc6");
+		outp += sprintf(outp, "\tGFX%%rc6");
 
 	if (do_gfx_mhz)
-		outp += sprintf(outp, "  GFXMHz");
+		outp += sprintf(outp, "\tGFXMHz");
 
 	if (do_skl_residency) {
-		outp += sprintf(outp, " Totl%%C0");
-		outp += sprintf(outp, "  Any%%C0");
-		outp += sprintf(outp, "  GFX%%C0");
-		outp += sprintf(outp, " CPUGFX%%");
+		outp += sprintf(outp, "\tTotl%%C0");
+		outp += sprintf(outp, "\tAny%%C0");
+		outp += sprintf(outp, "\tGFX%%C0");
+		outp += sprintf(outp, "\tCPUGFX%%");
 	}
 
 	if (do_pc2)
-		outp += sprintf(outp, " Pkg%%pc2");
+		outp += sprintf(outp, "\tPkg%%pc2");
 	if (do_pc3)
-		outp += sprintf(outp, " Pkg%%pc3");
+		outp += sprintf(outp, "\tPkg%%pc3");
 	if (do_pc6)
-		outp += sprintf(outp, " Pkg%%pc6");
+		outp += sprintf(outp, "\tPkg%%pc6");
 	if (do_pc7)
-		outp += sprintf(outp, " Pkg%%pc7");
+		outp += sprintf(outp, "\tPkg%%pc7");
 	if (do_c8_c9_c10) {
-		outp += sprintf(outp, " Pkg%%pc8");
-		outp += sprintf(outp, " Pkg%%pc9");
-		outp += sprintf(outp, " Pk%%pc10");
+		outp += sprintf(outp, "\tPkg%%pc8");
+		outp += sprintf(outp, "\tPkg%%pc9");
+		outp += sprintf(outp, "\tPk%%pc10");
 	}
 
 	if (do_rapl && !rapl_joules) {
 		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, " PkgWatt");
-		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, " CorWatt");
+			outp += sprintf(outp, "\tPkgWatt");
+		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
+			outp += sprintf(outp, "\tCorWatt");
 		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, " GFXWatt");
+			outp += sprintf(outp, "\tGFXWatt");
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, " RAMWatt");
+			outp += sprintf(outp, "\tRAMWatt");
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, "   PKG_%%");
+			outp += sprintf(outp, "\tPKG_%%");
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, "   RAM_%%");
+			outp += sprintf(outp, "\tRAM_%%");
 	} else if (do_rapl && rapl_joules) {
 		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, "   Pkg_J");
-		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, "   Cor_J");
+			outp += sprintf(outp, "\tPkg_J");
+		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
+			outp += sprintf(outp, "\tCor_J");
 		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, "   GFX_J");
+			outp += sprintf(outp, "\tGFX_J");
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, "   RAM_J");
+			outp += sprintf(outp, "\tRAM_J");
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, "   PKG_%%");
+			outp += sprintf(outp, "\tPKG_%%");
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, "   RAM_%%");
-		outp += sprintf(outp, "   time");
-
+			outp += sprintf(outp, "\tRAM_%%");
 	}
-    done:
+	for (mp = sys.pp; mp; mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 64)
+				outp += sprintf(outp, "\t%18.18s", mp->name);
+			else
+				outp += sprintf(outp, "\t%10.10s", mp->name);
+		} else {
+			outp += sprintf(outp, "\t%-7.7s", mp->name);
+		}
+	}
+
+done:
 	outp += sprintf(outp, "\n");
 }
 
 int dump_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
+	int i;
+	struct msr_counter *mp;
+
 	outp += sprintf(outp, "t %p, c %p, p %p\n", t, c, p);
 
 	if (t) {
@@ -442,18 +493,16 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "aperf: %016llX\n", t->aperf);
 		outp += sprintf(outp, "mperf: %016llX\n", t->mperf);
 		outp += sprintf(outp, "c1: %016llX\n", t->c1);
-		outp += sprintf(outp, "msr0x%x: %08llX\n",
-			extra_delta_offset32, t->extra_delta32);
-		outp += sprintf(outp, "msr0x%x: %016llX\n",
-			extra_delta_offset64, t->extra_delta64);
-		outp += sprintf(outp, "msr0x%x: %08llX\n",
-			extra_msr_offset32, t->extra_msr32);
-		outp += sprintf(outp, "msr0x%x: %016llX\n",
-			extra_msr_offset64, t->extra_msr64);
+
 		if (do_irq)
 			outp += sprintf(outp, "IRQ: %08X\n", t->irq_count);
 		if (do_smi)
 			outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
+
+		for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+			outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n",
+				i, mp->msr_num, t->counter[i]);
+		}
 	}
 
 	if (c) {
@@ -462,6 +511,11 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "c6: %016llX\n", c->c6);
 		outp += sprintf(outp, "c7: %016llX\n", c->c7);
 		outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
+
+		for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+			outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
+				i, mp->msr_num, c->counter[i]);
+		}
 	}
 
 	if (p) {
@@ -491,6 +545,11 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "Throttle RAM: %0X\n",
 			p->rapl_dram_perf_status);
 		outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
+
+		for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+			outp += sprintf(outp, "pADDED [%d] msr0x%x: %08llX\n",
+				i, mp->msr_num, p->counter[i]);
+		}
 	}
 
 	outp += sprintf(outp, "\n");
@@ -506,6 +565,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 {
 	double interval_float;
 	char *fmt8;
+	int i;
+	struct msr_counter *mp;
 
 	 /* if showing only 1st thread in core and this isn't one, bail out */
 	if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
@@ -520,99 +581,103 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	/* topo columns, print blanks on 1st (average) line */
 	if (t == &average.threads) {
 		if (show_pkg)
-			outp += sprintf(outp, "       -");
+			outp += sprintf(outp, "\t-");
 		if (show_core)
-			outp += sprintf(outp, "       -");
+			outp += sprintf(outp, "\t-");
 		if (show_cpu)
-			outp += sprintf(outp, "       -");
+			outp += sprintf(outp, "\t-");
 	} else {
 		if (show_pkg) {
 			if (p)
-				outp += sprintf(outp, "%8d", p->package_id);
+				outp += sprintf(outp, "\t%d", p->package_id);
 			else
-				outp += sprintf(outp, "       -");
+				outp += sprintf(outp, "\t-");
 		}
 		if (show_core) {
 			if (c)
-				outp += sprintf(outp, "%8d", c->core_id);
+				outp += sprintf(outp, "\t%d", c->core_id);
 			else
-				outp += sprintf(outp, "       -");
+				outp += sprintf(outp, "\t-");
 		}
 		if (show_cpu)
-			outp += sprintf(outp, "%8d", t->cpu_id);
+			outp += sprintf(outp, "\t%d", t->cpu_id);
 	}
 
 	/* Avg_MHz */
 	if (has_aperf)
-		outp += sprintf(outp, "%8.0f",
+		outp += sprintf(outp, "\t%.0f",
 			1.0 / units * t->aperf / interval_float);
 
 	/* Busy% */
-	if (has_aperf) {
-		if (!skip_c0)
-			outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
-		else
-			outp += sprintf(outp, "********");
-	}
+	if (has_aperf)
+		outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
 
 	/* Bzy_MHz */
 	if (has_aperf) {
 		if (has_base_hz)
-			outp += sprintf(outp, "%8.0f", base_hz / units * t->aperf / t->mperf);
+			outp += sprintf(outp, "\t%.0f", base_hz / units * t->aperf / t->mperf);
 		else
-			outp += sprintf(outp, "%8.0f",
+			outp += sprintf(outp, "\t%.0f",
 				1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
 	}
 
 	/* TSC_MHz */
-	outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
-
-	/* delta */
-	if (extra_delta_offset32)
-		outp += sprintf(outp, "  %11llu", t->extra_delta32);
-
-	/* DELTA */
-	if (extra_delta_offset64)
-		outp += sprintf(outp, "  %11llu", t->extra_delta64);
-	/* msr */
-	if (extra_msr_offset32)
-		outp += sprintf(outp, "  0x%08llx", t->extra_msr32);
-
-	/* MSR */
-	if (extra_msr_offset64)
-		outp += sprintf(outp, "  0x%016llx", t->extra_msr64);
+	outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float);
 
 	if (!debug)
 		goto done;
 
 	/* IRQ */
 	if (do_irq)
-		outp += sprintf(outp, "%8d", t->irq_count);
+		outp += sprintf(outp, "\t%d", t->irq_count);
 
 	/* SMI */
 	if (do_smi)
-		outp += sprintf(outp, "%8d", t->smi_count);
+		outp += sprintf(outp, "\t%d", t->smi_count);
 
-	if (do_nhm_cstates) {
-		if (!skip_c1)
-			outp += sprintf(outp, "%8.2f", 100.0 * t->c1/t->tsc);
-		else
-			outp += sprintf(outp, "********");
-	}
+	if (do_nhm_cstates)
+		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/t->tsc);
 
 	/* print per-core data only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
 	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "%8.2f", 100.0 * c->c3/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc);
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "%8.2f", 100.0 * c->c6/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc);
 	if (do_snb_cstates)
-		outp += sprintf(outp, "%8.2f", 100.0 * c->c7/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc);
+
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 32)
+				outp += sprintf(outp, "\t0x%08lx", (unsigned long) t->counter[i]);
+			else
+				outp += sprintf(outp, "\t0x%016llx", t->counter[i]);
+		} else if (mp->format == FORMAT_DELTA) {
+			outp += sprintf(outp, "\t%8lld", t->counter[i]);
+		} else if (mp->format == FORMAT_PERCENT) {
+			outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/t->tsc);
+		}
+	}
+
 
 	if (do_dts)
-		outp += sprintf(outp, "%8d", c->core_temp_c);
+		outp += sprintf(outp, "\t%d", c->core_temp_c);
+
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 32)
+				outp += sprintf(outp, "\t0x%08lx", (unsigned long) c->counter[i]);
+			else
+				outp += sprintf(outp, "\t0x%016llx", c->counter[i]);
+		} else if (mp->format == FORMAT_DELTA) {
+			outp += sprintf(outp, "\t%8lld", c->counter[i]);
+		} else if (mp->format == FORMAT_PERCENT) {
+			outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/t->tsc);
+		}
+	}
 
 	/* print per-package data only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
@@ -620,42 +685,42 @@ int format_counters(struct thread_data *t, struct core_data *c,
 
 	/* PkgTmp */
 	if (do_ptm)
-		outp += sprintf(outp, "%8d", p->pkg_temp_c);
+		outp += sprintf(outp, "\t%d", p->pkg_temp_c);
 
 	/* GFXrc6 */
 	if (do_gfx_rc6_ms) {
-		if (p->gfx_rc6_ms == -1) {	/* detect counter reset */
-			outp += sprintf(outp, "  ***.**");
+		if (p->gfx_rc6_ms == -1) {	/* detect GFX counter reset */
+			outp += sprintf(outp, "\t**.**");
 		} else {
-			outp += sprintf(outp, "%8.2f",
+			outp += sprintf(outp, "\t%.2f",
 				p->gfx_rc6_ms / 10.0 / interval_float);
 		}
 	}
 
 	/* GFXMHz */
 	if (do_gfx_mhz)
-		outp += sprintf(outp, "%8d", p->gfx_mhz);
+		outp += sprintf(outp, "\t%d", p->gfx_mhz);
 
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
 	if (do_skl_residency) {
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_any_core_c0/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_core_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc);
 	}
 
 	if (do_pc2)
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc2/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/t->tsc);
 	if (do_pc3)
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc3/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/t->tsc);
 	if (do_pc6)
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc6/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/t->tsc);
 	if (do_pc7)
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc7/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/t->tsc);
 	if (do_c8_c9_c10) {
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc8/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc9/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc10/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/t->tsc);
 	}
 
 	/*
@@ -663,14 +728,14 @@ int format_counters(struct thread_data *t, struct core_data *c,
  	 * indicate that results are suspect by printing "**" in fraction place.
  	 */
 	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "%8.2f";
+		fmt8 = "\t%.2f";
 	else
-		fmt8 = " %6.0f**";
+		fmt8 = "%6.0f**";
 
 	if (do_rapl && !rapl_joules) {
 		if (do_rapl & RAPL_PKG)
 			outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float);
-		if (do_rapl & RAPL_CORES)
+		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
 			outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float);
 		if (do_rapl & RAPL_GFX)
 			outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float);
@@ -697,9 +762,20 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-
-		outp += sprintf(outp, fmt8, interval_float);
 	}
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 32)
+				outp += sprintf(outp, "\t0x%08lx", (unsigned long) p->counter[i]);
+			else
+				outp += sprintf(outp, "\t0x%016llx", p->counter[i]);
+		} else if (mp->format == FORMAT_DELTA) {
+			outp += sprintf(outp, "\t%8lld", p->counter[i]);
+		} else if (mp->format == FORMAT_PERCENT) {
+			outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/t->tsc);
+		}
+	}
+
 done:
 	outp += sprintf(outp, "\n");
 
@@ -752,9 +828,11 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
 		old = 0x100000000 + new - old;	\
 	}
 
-void
+int
 delta_package(struct pkg_data *new, struct pkg_data *old)
 {
+	int i;
+	struct msr_counter *mp;
 
 	if (do_skl_residency) {
 		old->pkg_wtd_core_c0 = new->pkg_wtd_core_c0 - old->pkg_wtd_core_c0;
@@ -788,24 +866,46 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
 	DELTA_WRAP32(new->energy_dram, old->energy_dram);
 	DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status);
 	DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status);
+
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			old->counter[i] = new->counter[i];
+		else
+			old->counter[i] = new->counter[i] - old->counter[i];
+	}
+
+	return 0;
 }
 
 void
 delta_core(struct core_data *new, struct core_data *old)
 {
+	int i;
+	struct msr_counter *mp;
+
 	old->c3 = new->c3 - old->c3;
 	old->c6 = new->c6 - old->c6;
 	old->c7 = new->c7 - old->c7;
 	old->core_temp_c = new->core_temp_c;
+
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			old->counter[i] = new->counter[i];
+		else
+			old->counter[i] = new->counter[i] - old->counter[i];
+	}
 }
 
 /*
  * old = new - old
  */
-void
+int
 delta_thread(struct thread_data *new, struct thread_data *old,
 	struct core_data *core_delta)
 {
+	int i;
+	struct msr_counter *mp;
+
 	old->tsc = new->tsc - old->tsc;
 
 	/* check for TSC < 1 Mcycles over interval */
@@ -821,20 +921,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 			old->aperf = new->aperf - old->aperf;
 			old->mperf = new->mperf - old->mperf;
 		} else {
-
-			if (!aperf_mperf_unstable) {
-				fprintf(outf, "%s: APERF or MPERF went backwards *\n", progname);
-				fprintf(outf, "* Frequency results do not cover entire interval *\n");
-				fprintf(outf, "* fix this by running Linux-2.6.30 or later *\n");
-
-				aperf_mperf_unstable = 1;
-			}
-			/*
-			 * mperf delta is likely a huge "positive" number
-			 * can not use it for calculating c0 time
-			 */
-			skip_c0 = 1;
-			skip_c1 = 1;
+			return -1;
 		}
 	}
 
@@ -865,52 +952,53 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 		old->mperf = 1;	/* divide by 0 protection */
 	}
 
-	old->extra_delta32 = new->extra_delta32 - old->extra_delta32;
-	old->extra_delta32 &= 0xFFFFFFFF;
-
-	old->extra_delta64 = new->extra_delta64 - old->extra_delta64;
-
-	/*
-	 * Extra MSR is just a snapshot, simply copy latest w/o subtracting
-	 */
-	old->extra_msr32 = new->extra_msr32;
-	old->extra_msr64 = new->extra_msr64;
-
 	if (do_irq)
 		old->irq_count = new->irq_count - old->irq_count;
 
 	if (do_smi)
 		old->smi_count = new->smi_count - old->smi_count;
+
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			old->counter[i] = new->counter[i];
+		else
+			old->counter[i] = new->counter[i] - old->counter[i];
+	}
+	return 0;
 }
 
 int delta_cpu(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p, struct thread_data *t2,
 	struct core_data *c2, struct pkg_data *p2)
 {
+	int retval = 0;
+
 	/* calculate core delta only for 1st thread in core */
 	if (t->flags & CPU_IS_FIRST_THREAD_IN_CORE)
 		delta_core(c, c2);
 
 	/* always calculate thread delta */
-	delta_thread(t, t2, c2);	/* c2 is core delta */
+	retval = delta_thread(t, t2, c2);	/* c2 is core delta */
+	if (retval)
+		return retval;
 
 	/* calculate package delta only for 1st core in package */
 	if (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)
-		delta_package(p, p2);
+		retval = delta_package(p, p2);
 
-	return 0;
+	return retval;
 }
 
 void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
+	int i;
+	struct msr_counter  *mp;
+
 	t->tsc = 0;
 	t->aperf = 0;
 	t->mperf = 0;
 	t->c1 = 0;
 
-	t->extra_delta32 = 0;
-	t->extra_delta64 = 0;
-
 	t->irq_count = 0;
 	t->smi_count = 0;
 
@@ -948,21 +1036,36 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	p->gfx_rc6_ms = 0;
 	p->gfx_mhz = 0;
+
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
+		t->counter[i] = 0;
+
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next)
+		c->counter[i] = 0;
+
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next)
+		p->counter[i] = 0;
 }
 int sum_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
+	int i;
+	struct msr_counter *mp;
+
 	average.threads.tsc += t->tsc;
 	average.threads.aperf += t->aperf;
 	average.threads.mperf += t->mperf;
 	average.threads.c1 += t->c1;
 
-	average.threads.extra_delta32 += t->extra_delta32;
-	average.threads.extra_delta64 += t->extra_delta64;
-
 	average.threads.irq_count += t->irq_count;
 	average.threads.smi_count += t->smi_count;
 
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.threads.counter[i] += t->counter[i];
+	}
+
 	/* sum per-core values only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
@@ -973,6 +1076,12 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
 
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.cores.counter[i] += c->counter[i];
+	}
+
 	/* sum per-pkg values only for 1st core in pkg */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		return 0;
@@ -1007,6 +1116,12 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status;
 	average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status;
+
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.packages.counter[i] += p->counter[i];
+	}
 	return 0;
 }
 /*
@@ -1016,6 +1131,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 void compute_average(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
+	int i;
+	struct msr_counter *mp;
+
 	clear_counters(&average.threads, &average.cores, &average.packages);
 
 	for_all_cpus(sum_counters, t, c, p);
@@ -1025,11 +1143,6 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.threads.mperf /= topo.num_cpus;
 	average.threads.c1 /= topo.num_cpus;
 
-	average.threads.extra_delta32 /= topo.num_cpus;
-	average.threads.extra_delta32 &= 0xFFFFFFFF;
-
-	average.threads.extra_delta64 /= topo.num_cpus;
-
 	average.cores.c3 /= topo.num_cores;
 	average.cores.c6 /= topo.num_cores;
 	average.cores.c7 /= topo.num_cores;
@@ -1052,6 +1165,22 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.packages.pc8 /= topo.num_packages;
 	average.packages.pc9 /= topo.num_packages;
 	average.packages.pc10 /= topo.num_packages;
+
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.threads.counter[i] /= topo.num_cpus;
+	}
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.cores.counter[i] /= topo.num_cores;
+	}
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.packages.counter[i] /= topo.num_packages;
+	}
 }
 
 static unsigned long long rdtsc(void)
@@ -1073,6 +1202,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	int cpu = t->cpu_id;
 	unsigned long long msr;
 	int aperf_mperf_retry_count = 0;
+	struct msr_counter *mp;
+	int i;
 
 	if (cpu_migrate(cpu)) {
 		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
@@ -1145,31 +1276,18 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -5;
 		t->smi_count = msr & 0xFFFFFFFF;
 	}
-	if (extra_delta_offset32) {
-		if (get_msr(cpu, extra_delta_offset32, &msr))
-			return -5;
-		t->extra_delta32 = msr & 0xFFFFFFFF;
-	}
-
-	if (extra_delta_offset64)
-		if (get_msr(cpu, extra_delta_offset64, &t->extra_delta64))
-			return -5;
-
-	if (extra_msr_offset32) {
-		if (get_msr(cpu, extra_msr_offset32, &msr))
-			return -5;
-		t->extra_msr32 = msr & 0xFFFFFFFF;
-	}
-
-	if (extra_msr_offset64)
-		if (get_msr(cpu, extra_msr_offset64, &t->extra_msr64))
-			return -5;
 
 	if (use_c1_residency_msr) {
 		if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1))
 			return -6;
 	}
 
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (get_msr(cpu, mp->msr_num, &t->counter[i]))
+			return -10;
+	}
+
+
 	/* collect core counters only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
@@ -1197,6 +1315,10 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
 
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (get_msr(cpu, mp->msr_num, &c->counter[i]))
+			return -10;
+	}
 
 	/* collect package counters only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
@@ -1237,7 +1359,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -13;
 		p->energy_pkg = msr & 0xFFFFFFFF;
 	}
-	if (do_rapl & RAPL_CORES) {
+	if (do_rapl & RAPL_CORES_ENERGY_STATUS) {
 		if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr))
 			return -14;
 		p->energy_cores = msr & 0xFFFFFFFF;
@@ -1274,6 +1396,11 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (do_gfx_mhz)
 		p->gfx_mhz = gfx_cur_mhz;
 
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (get_msr(cpu, mp->msr_num, &p->counter[i]))
+			return -10;
+	}
+
 	return 0;
 }
 
@@ -1310,6 +1437,7 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV,
 int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 
 
 static void
@@ -1638,7 +1766,7 @@ void free_fd_percpu(void)
 {
 	int i;
 
-	for (i = 0; i < topo.max_cpu_num; ++i) {
+	for (i = 0; i < topo.max_cpu_num + 1; ++i) {
 		if (fd_percpu[i] != 0)
 			close(fd_percpu[i]);
 	}
@@ -2071,7 +2199,10 @@ void turbostat_loop()
 		}
 		gettimeofday(&tv_odd, (struct timezone *)NULL);
 		timersub(&tv_odd, &tv_even, &tv_delta);
-		for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
+		if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS)) {
+			re_initialize();
+			goto restart;
+		}
 		compute_average(EVEN_COUNTERS);
 		format_all_counters(EVEN_COUNTERS);
 		flush_output_stdout();
@@ -2087,7 +2218,10 @@ void turbostat_loop()
 		}
 		gettimeofday(&tv_even, (struct timezone *)NULL);
 		timersub(&tv_even, &tv_odd, &tv_delta);
-		for_all_cpus_2(delta_cpu, EVEN_COUNTERS, ODD_COUNTERS);
+		if (for_all_cpus_2(delta_cpu, EVEN_COUNTERS, ODD_COUNTERS)) {
+			re_initialize();
+			goto restart;
+		}
 		compute_average(ODD_COUNTERS);
 		format_all_counters(ODD_COUNTERS);
 		flush_output_stdout();
@@ -2174,47 +2308,51 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	bclk = discover_bclk(family, model);
 
 	switch (model) {
-	case 0x1A:	/* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */
-	case 0x1E:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
+	case INTEL_FAM6_NEHALEM_EP:	/* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */
+	case INTEL_FAM6_NEHALEM:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
 	case 0x1F:	/* Core i7 and i5 Processor - Nehalem */
-	case 0x25:	/* Westmere Client - Clarkdale, Arrandale */
-	case 0x2C:	/* Westmere EP - Gulftown */
-	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
-	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
+	case INTEL_FAM6_WESTMERE:	/* Westmere Client - Clarkdale, Arrandale */
+	case INTEL_FAM6_WESTMERE_EP:	/* Westmere EP - Gulftown */
+	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
+	case INTEL_FAM6_WESTMERE_EX:	/* Westmere-EX Xeon - Eagleton */
 		pkg_cstate_limits = nhm_pkg_cstate_limits;
 		break;
-	case 0x2A:	/* SNB */
-	case 0x2D:	/* SNB Xeon */
-	case 0x3A:	/* IVB */
-	case 0x3E:	/* IVB Xeon */
+	case INTEL_FAM6_SANDYBRIDGE:	/* SNB */
+	case INTEL_FAM6_SANDYBRIDGE_X:	/* SNB Xeon */
+	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
+	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
 		pkg_cstate_limits = snb_pkg_cstate_limits;
 		break;
-	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSX */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x47:	/* BDW */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
-	case 0x55:	/* SKX */
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 		pkg_cstate_limits = hsw_pkg_cstate_limits;
 		break;
-	case 0x37:	/* BYT */
-	case 0x4D:	/* AVN */
+	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
+		pkg_cstate_limits = skx_pkg_cstate_limits;
+		break;
+	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
 		pkg_cstate_limits = slv_pkg_cstate_limits;
 		break;
-	case 0x4C:	/* AMT */
+	case INTEL_FAM6_ATOM_AIRMONT:	/* AMT */
 		pkg_cstate_limits = amt_pkg_cstate_limits;
 		break;
-	case 0x57:	/* PHI */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		pkg_cstate_limits = phi_pkg_cstate_limits;
 		break;
-	case 0x5C:	/* BXT */
+	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 		pkg_cstate_limits = bxt_pkg_cstate_limits;
 		break;
 	default:
@@ -2234,9 +2372,10 @@ int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
 	switch (model) {
 	/* Nehalem compatible, but do not include turbo-ratio limit support */
-	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
-	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
-	case 0x57:	/* PHI - Knights Landing (different MSR definition) */
+	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
+	case INTEL_FAM6_WESTMERE_EX:	/* Westmere-EX Xeon - Eagleton */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI - Knights Landing (different MSR definition) */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return 0;
 	default:
 		return 1;
@@ -2251,8 +2390,8 @@ int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x3E:	/* IVB Xeon */
-	case 0x3F:	/* HSW Xeon */
+	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
+	case INTEL_FAM6_HASWELL_X:	/* HSW Xeon */
 		return 1;
 	default:
 		return 0;
@@ -2267,7 +2406,7 @@ int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x3F:	/* HSW Xeon */
+	case INTEL_FAM6_HASWELL_X:	/* HSW Xeon */
 		return 1;
 	default:
 		return 0;
@@ -2283,7 +2422,8 @@ int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x57:	/* Knights Landing */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return 1;
 	default:
 		return 0;
@@ -2298,22 +2438,23 @@ int has_config_tdp(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x3A:	/* IVB */
-	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSX */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x47:	/* BDW */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
-	case 0x55:	/* SKX */
+	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 
-	case 0x57:	/* Knights Landing */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return 1;
 	default:
 		return 0;
@@ -2593,8 +2734,8 @@ double get_tdp(unsigned int model)
 			return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
 
 	switch (model) {
-	case 0x37:
-	case 0x4D:
+	case INTEL_FAM6_ATOM_SILVERMONT1:
+	case INTEL_FAM6_ATOM_SILVERMONT2:
 		return 30.0;
 	default:
 		return 135.0;
@@ -2611,10 +2752,11 @@ rapl_dram_energy_units_probe(int  model, double rapl_energy_units)
 	/* only called for genuine_intel, family 6 */
 
 	switch (model) {
-	case 0x3F:	/* HSX */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x57:	/* KNL */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return (rapl_dram_energy_units = 15.3 / 1000000);
 	default:
 		return (rapl_energy_units);
@@ -2640,38 +2782,42 @@ void rapl_probe(unsigned int family, unsigned int model)
 		return;
 
 	switch (model) {
-	case 0x2A:
-	case 0x3A:
-	case 0x3C:	/* HSW */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x47:	/* BDW */
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x5C:	/* BXT */
+	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x3F:	/* HSX */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x55:	/* SKX */
-	case 0x57:	/* KNL */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x2D:
-	case 0x3E:
+	case INTEL_FAM6_SANDYBRIDGE_X:
+	case INTEL_FAM6_IVYBRIDGE_X:
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x37:	/* BYT */
-	case 0x4D:	/* AVN */
-		do_rapl = RAPL_PKG | RAPL_CORES ;
+	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
+		do_rapl = RAPL_PKG | RAPL_CORES;
+		break;
+	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS;
 		break;
 	default:
 		return;
@@ -2682,7 +2828,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 		return;
 
 	rapl_power_units = 1.0 / (1 << (msr & 0xF));
-	if (model == 0x37)
+	if (model == INTEL_FAM6_ATOM_SILVERMONT1)
 		rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000;
 	else
 		rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
@@ -2713,11 +2859,11 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 		return;
 
 	switch (model) {
-	case 0x3C:	/* HSW */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
 		do_gfx_perf_limit_reasons = 1;
-	case 0x3F:	/* HSX */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
 		do_core_perf_limit_reasons = 1;
 		do_ring_perf_limit_reasons = 1;
 	default:
@@ -2737,7 +2883,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 	cpu = t->cpu_id;
 
 	/* DTS is per-core, no need to print for each thread */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) 
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
 
 	if (cpu_migrate(cpu)) {
@@ -2886,9 +3032,8 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
 		}
 	}
-	if (do_rapl & RAPL_CORES) {
+	if (do_rapl & RAPL_CORES_POWER_LIMIT) {
 		if (debug) {
-
 			if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
 				return -9;
 			fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
@@ -2927,24 +3072,25 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x2A:
-	case 0x2D:
-	case 0x3A:	/* IVB */
-	case 0x3E:	/* IVB Xeon */
-	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSW */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x47:	/* BDW */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
-	case 0x55:	/* SKX */
-	case 0x5C:	/* BXT */
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_SANDYBRIDGE_X:
+	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
+	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_X:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
+	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 		return 1;
 	}
 	return 0;
@@ -2968,13 +3114,13 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x45:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
-	case 0x5C:	/* BXT */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 		return 1;
 	}
 	return 0;
@@ -2994,10 +3140,10 @@ int has_skl_msrs(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 		return 1;
 	}
 	return 0;
@@ -3010,8 +3156,8 @@ int is_slm(unsigned int family, unsigned int model)
 	if (!genuine_intel)
 		return 0;
 	switch (model) {
-	case 0x37:	/* BYT */
-	case 0x4D:	/* AVN */
+	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
 		return 1;
 	}
 	return 0;
@@ -3022,7 +3168,8 @@ int is_knl(unsigned int family, unsigned int model)
 	if (!genuine_intel)
 		return 0;
 	switch (model) {
-	case 0x57:	/* KNL */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return 1;
 	}
 	return 0;
@@ -3050,7 +3197,7 @@ double slm_bclk(void)
 	i = msr & 0xf;
 	if (i >= SLM_BCLK_FREQS) {
 		fprintf(outf, "SLM BCLK[%d] invalid\n", i);
-		msr = 3;
+		i = 3;
 	}
 	freq = slm_freq_table[i];
 
@@ -3174,10 +3321,11 @@ void decode_misc_pwr_mgmt_msr(void)
 		return;
 
 	if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr))
-		fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB)\n",
+		fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB %sable-OOB)\n",
 			base_cpu, msr,
 			msr & (1 << 0) ? "DIS" : "EN",
-			msr & (1 << 1) ? "EN" : "DIS");
+			msr & (1 << 1) ? "EN" : "DIS",
+			msr & (1 << 8) ? "EN" : "DIS");
 }
 
 void process_cpuid()
@@ -3303,16 +3451,17 @@ void process_cpuid()
 
 			if (crystal_hz == 0)
 				switch(model) {
-				case 0x4E:	/* SKL */
-				case 0x5E:	/* SKL */
-				case 0x8E:	/* KBL */
-				case 0x9E:	/* KBL */
+				case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+				case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+				case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+				case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 					crystal_hz = 24000000;	/* 24.0 MHz */
 					break;
-				case 0x55:	/* SKX */
+				case INTEL_FAM6_SKYLAKE_X:	/* SKX */
+				case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 					crystal_hz = 25000000;	/* 25.0 MHz */
 					break;
-				case 0x5C:	/* BXT */
+				case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 					crystal_hz = 19200000;	/* 19.2 MHz */
 					break;
 				default:
@@ -3385,14 +3534,12 @@ void help()
 	"when COMMAND completes.\n"
 	"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
 	"to print statistics, until interrupted.\n"
+	"--add		add a counter\n"
+	"		eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
 	"--debug	run in \"debug\" mode\n"
 	"--interval sec	Override default 5-second measurement interval\n"
 	"--help		print this help message\n"
-	"--counter msr	print 32-bit counter at address \"msr\"\n"
-	"--Counter msr	print 64-bit Counter at address \"msr\"\n"
 	"--out file	create or truncate \"file\" for all output\n"
-	"--msr msr	print 32-bit value at address \"msr\"\n"
-	"--MSR msr	print 64-bit Value at address \"msr\"\n"
 	"--version	print version information\n"
 	"\n"
 	"For more help, run \"man turbostat\"\n");
@@ -3515,7 +3662,7 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
 	int i;
 
 	*t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg *
-		topo.num_packages, sizeof(struct thread_data));
+		topo.num_packages, sizeof(struct thread_data) + sys.thread_counter_bytes);
 	if (*t == NULL)
 		goto error;
 
@@ -3524,14 +3671,14 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
 		(*t)[i].cpu_id = -1;
 
 	*c = calloc(topo.num_cores_per_pkg * topo.num_packages,
-		sizeof(struct core_data));
+		sizeof(struct core_data) + sys.core_counter_bytes);
 	if (*c == NULL)
 		goto error;
 
 	for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++)
 		(*c)[i].core_id = -1;
 
-	*p = calloc(topo.num_packages, sizeof(struct pkg_data));
+	*p = calloc(topo.num_packages, sizeof(struct pkg_data) + sys.package_counter_bytes);
 	if (*p == NULL)
 		goto error;
 
@@ -3598,7 +3745,7 @@ void allocate_output_buffer()
 }
 void allocate_fd_percpu(void)
 {
-	fd_percpu = calloc(topo.max_cpu_num, sizeof(int));
+	fd_percpu = calloc(topo.max_cpu_num + 1, sizeof(int));
 	if (fd_percpu == NULL)
 		err(-1, "calloc fd_percpu");
 }
@@ -3608,9 +3755,9 @@ void allocate_irq_buffers(void)
 	if (irq_column_2_cpu == NULL)
 		err(-1, "calloc %d", topo.num_cpus);
 
-	irqs_per_cpu = calloc(topo.max_cpu_num, sizeof(int));
+	irqs_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int));
 	if (irqs_per_cpu == NULL)
-		err(-1, "calloc %d", topo.max_cpu_num);
+		err(-1, "calloc %d", topo.max_cpu_num + 1);
 }
 void setup_all_buffers(void)
 {
@@ -3697,9 +3844,12 @@ int fork_it(char **argv)
 	for_all_cpus(get_counters, ODD_COUNTERS);
 	gettimeofday(&tv_odd, (struct timezone *)NULL);
 	timersub(&tv_odd, &tv_even, &tv_delta);
-	for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
-	compute_average(EVEN_COUNTERS);
-	format_all_counters(EVEN_COUNTERS);
+	if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS))
+		fprintf(outf, "%s: Counter reset detected\n", progname);
+	else {
+		compute_average(EVEN_COUNTERS);
+		format_all_counters(EVEN_COUNTERS);
+	}
 
 	fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
 
@@ -3726,24 +3876,170 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 4.12 5 Apr 2016"
+	fprintf(outf, "turbostat version 4.16 24 Dec 2016"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
+int add_counter(unsigned int msr_num, char *name, unsigned int width,
+	enum counter_scope scope, enum counter_type type,
+	enum counter_format format)
+{
+	struct msr_counter *msrp;
+
+	msrp = calloc(1, sizeof(struct msr_counter));
+	if (msrp == NULL) {
+		perror("calloc");
+		exit(1);
+	}
+
+	msrp->msr_num = msr_num;
+	strncpy(msrp->name, name, NAME_BYTES);
+	msrp->width = width;
+	msrp->type = type;
+	msrp->format = format;
+
+	switch (scope) {
+
+	case SCOPE_CPU:
+		sys.thread_counter_bytes += 64;
+		msrp->next = sys.tp;
+		sys.tp = msrp;
+		sys.thread_counter_bytes += sizeof(unsigned long long);
+		break;
+
+	case SCOPE_CORE:
+		sys.core_counter_bytes += 64;
+		msrp->next = sys.cp;
+		sys.cp = msrp;
+		sys.core_counter_bytes += sizeof(unsigned long long);
+		break;
+
+	case SCOPE_PACKAGE:
+		sys.package_counter_bytes += 64;
+		msrp->next = sys.pp;
+		sys.pp = msrp;
+		sys.package_counter_bytes += sizeof(unsigned long long);
+		break;
+	}
+
+	return 0;
+}
+
+void parse_add_command(char *add_command)
+{
+	int msr_num = 0;
+	char name_buffer[NAME_BYTES];
+	int width = 64;
+	int fail = 0;
+	enum counter_scope scope = SCOPE_CPU;
+	enum counter_type type = COUNTER_CYCLES;
+	enum counter_format format = FORMAT_DELTA;
+
+	while (add_command) {
+
+		if (sscanf(add_command, "msr0x%x", &msr_num) == 1)
+			goto next;
+
+		if (sscanf(add_command, "msr%d", &msr_num) == 1)
+			goto next;
+
+		if (sscanf(add_command, "u%d", &width) == 1) {
+			if ((width == 32) || (width == 64))
+				goto next;
+			width = 64;
+		}
+		if (!strncmp(add_command, "cpu", strlen("cpu"))) {
+			scope = SCOPE_CPU;
+			goto next;
+		}
+		if (!strncmp(add_command, "core", strlen("core"))) {
+			scope = SCOPE_CORE;
+			goto next;
+		}
+		if (!strncmp(add_command, "package", strlen("package"))) {
+			scope = SCOPE_PACKAGE;
+			goto next;
+		}
+		if (!strncmp(add_command, "cycles", strlen("cycles"))) {
+			type = COUNTER_CYCLES;
+			goto next;
+		}
+		if (!strncmp(add_command, "seconds", strlen("seconds"))) {
+			type = COUNTER_SECONDS;
+			goto next;
+		}
+		if (!strncmp(add_command, "raw", strlen("raw"))) {
+			format = FORMAT_RAW;
+			goto next;
+		}
+		if (!strncmp(add_command, "delta", strlen("delta"))) {
+			format = FORMAT_DELTA;
+			goto next;
+		}
+		if (!strncmp(add_command, "percent", strlen("percent"))) {
+			format = FORMAT_PERCENT;
+			goto next;
+		}
+
+		if (sscanf(add_command, "%18s,%*s", name_buffer) == 1) {	/* 18 < NAME_BYTES */
+			char *eos;
+
+			eos = strchr(name_buffer, ',');
+			if (eos)
+				*eos = '\0';
+			goto next;
+		}
+
+next:
+		add_command = strchr(add_command, ',');
+		if (add_command)
+			add_command++;
+
+	}
+	if (msr_num == 0) {
+		fprintf(stderr, "--add: (msrDDD | msr0xXXX) required\n");
+		fail++;
+	}
+
+	/* generate default column header */
+	if (*name_buffer == '\0') {
+		if (format == FORMAT_RAW) {
+			if (width == 32)
+				sprintf(name_buffer, "msr%d", msr_num);
+			else
+				sprintf(name_buffer, "MSR%d", msr_num);
+		} else if (format == FORMAT_DELTA) {
+			if (width == 32)
+				sprintf(name_buffer, "cnt%d", msr_num);
+			else
+				sprintf(name_buffer, "CNT%d", msr_num);
+		} else if (format == FORMAT_PERCENT) {
+			if (width == 32)
+				sprintf(name_buffer, "msr%d%%", msr_num);
+			else
+				sprintf(name_buffer, "MSR%d%%", msr_num);
+		}
+	}
+
+	if (add_counter(msr_num, name_buffer, width, scope, type, format))
+		fail++;
+
+	if (fail) {
+		help();
+		exit(1);
+	}
+}
 void cmdline(int argc, char **argv)
 {
 	int opt;
 	int option_index = 0;
 	static struct option long_options[] = {
-		{"Counter",	required_argument,	0, 'C'},
-		{"counter",	required_argument,	0, 'c'},
+		{"add",		required_argument,	0, 'a'},
 		{"Dump",	no_argument,		0, 'D'},
 		{"debug",	no_argument,		0, 'd'},
 		{"interval",	required_argument,	0, 'i'},
 		{"help",	no_argument,		0, 'h'},
 		{"Joules",	no_argument,		0, 'J'},
-		{"MSR",		required_argument,	0, 'M'},
-		{"msr",		required_argument,	0, 'm'},
 		{"out",		required_argument,	0, 'o'},
 		{"Package",	no_argument,		0, 'p'},
 		{"processor",	no_argument,		0, 'p'},
@@ -3758,11 +4054,8 @@ void cmdline(int argc, char **argv)
 	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
-		case 'C':
-			sscanf(optarg, "%x", &extra_delta_offset64);
-			break;
-		case 'c':
-			sscanf(optarg, "%x", &extra_delta_offset32);
+		case 'a':
+			parse_add_command(optarg);
 			break;
 		case 'D':
 			dump_only++;
@@ -3791,12 +4084,6 @@ void cmdline(int argc, char **argv)
 		case 'J':
 			rapl_joules++;
 			break;
-		case 'M':
-			sscanf(optarg, "%x", &extra_msr_offset64);
-			break;
-		case 'm':
-			sscanf(optarg, "%x", &extra_msr_offset32);
-			break;
 		case 'o':
 			outf = fopen_or_die(optarg, "w");
 			break;
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index ae95fc0..a2dbbcc 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -39,7 +39,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->arch.timer_cpu.active_cleared_last = false;
 }
 
-static cycle_t kvm_phys_timer_read(void)
+static u64 kvm_phys_timer_read(void)
 {
 	return timecounter->cc->read(timecounter->cc);
 }
@@ -102,7 +102,7 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 
 static u64 kvm_timer_compute_delta(struct kvm_vcpu *vcpu)
 {
-	cycle_t cval, now;
+	u64 cval, now;
 
 	cval = vcpu->arch.timer_cpu.cntv_cval;
 	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
@@ -155,7 +155,7 @@ static bool kvm_timer_irq_can_fire(struct kvm_vcpu *vcpu)
 bool kvm_timer_should_fire(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-	cycle_t cval, now;
+	u64 cval, now;
 
 	if (!kvm_timer_irq_can_fire(vcpu))
 		return false;
@@ -456,7 +456,7 @@ int kvm_timer_hyp_init(void)
 	kvm_info("virtual timer IRQ%d\n", host_vtimer_irq);
 
 	cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
-			  "AP_KVM_ARM_TIMER_STARTING", kvm_timer_starting_cpu,
+			  "kvm/arm/timer:starting", kvm_timer_starting_cpu,
 			  kvm_timer_dying_cpu);
 	return err;
 }
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 8cebfbc..5114391 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -428,7 +428,7 @@ int kvm_vgic_hyp_init(void)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
-				"AP_KVM_ARM_VGIC_INIT_STARTING",
+				"kvm/arm/vgic:starting",
 				vgic_init_cpu_starting, vgic_init_cpu_dying);
 	if (ret) {
 		kvm_err("Cannot register vgic CPU notifier\n");
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index de102ca..482612b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -53,7 +53,7 @@
 #include <asm/processor.h>
 #include <asm/io.h>
 #include <asm/ioctl.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/pgtable.h>
 
 #include "coalesced_mmio.h"
@@ -3944,7 +3944,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 			goto out_free_1;
 	}
 
-	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "AP_KVM_STARTING",
+	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
 				      kvm_starting_cpu, kvm_dying_cpu);
 	if (r)
 		goto out_free_2;