diff --git a/CREDITS b/CREDITS
index 513aaa3..8373676 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1864,10 +1864,11 @@
 
 N: Martin Kepplinger
 E: martink@posteo.de
-E: martin.kepplinger@theobroma-systems.com
+E: martin.kepplinger@ginzinger.com
 W: http://www.martinkepplinger.com
 D: mma8452 accelerators iio driver
-D: Kernel cleanups
+D: pegasus_notetaker input driver
+D: Kernel fixes and cleanups
 S: Garnisonstraße 26
 S: 4020 Linz
 S: Austria
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index e5b6497..c75b64a 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -309,3 +309,4 @@
 	with a reshape in progress.
 1.9.0   Add support for RAID level takeover/reshape/region size
 	and set size reduction.
+1.9.1   Fix activation of existing RAID 4/10 mapped devices
diff --git a/Documentation/devicetree/bindings/net/marvell-orion-net.txt b/Documentation/devicetree/bindings/net/marvell-orion-net.txt
index bce52b2..6fd988c 100644
--- a/Documentation/devicetree/bindings/net/marvell-orion-net.txt
+++ b/Documentation/devicetree/bindings/net/marvell-orion-net.txt
@@ -49,6 +49,7 @@
 and
 
  - phy-handle: See ethernet.txt file in the same directory.
+ - phy-mode: See ethernet.txt file in the same directory.
 
 or
 
diff --git a/Documentation/devicetree/bindings/reset/uniphier-reset.txt b/Documentation/devicetree/bindings/reset/uniphier-reset.txt
index e6bbfcc..5020524 100644
--- a/Documentation/devicetree/bindings/reset/uniphier-reset.txt
+++ b/Documentation/devicetree/bindings/reset/uniphier-reset.txt
@@ -6,25 +6,25 @@
 
 Required properties:
 - compatible: should be one of the following:
-    "socionext,uniphier-sld3-reset" - for PH1-sLD3 SoC.
-    "socionext,uniphier-ld4-reset"  - for PH1-LD4 SoC.
-    "socionext,uniphier-pro4-reset" - for PH1-Pro4 SoC.
-    "socionext,uniphier-sld8-reset" - for PH1-sLD8 SoC.
-    "socionext,uniphier-pro5-reset" - for PH1-Pro5 SoC.
-    "socionext,uniphier-pxs2-reset" - for ProXstream2/PH1-LD6b SoC.
-    "socionext,uniphier-ld11-reset" - for PH1-LD11 SoC.
-    "socionext,uniphier-ld20-reset" - for PH1-LD20 SoC.
+    "socionext,uniphier-sld3-reset" - for sLD3 SoC.
+    "socionext,uniphier-ld4-reset"  - for LD4 SoC.
+    "socionext,uniphier-pro4-reset" - for Pro4 SoC.
+    "socionext,uniphier-sld8-reset" - for sLD8 SoC.
+    "socionext,uniphier-pro5-reset" - for Pro5 SoC.
+    "socionext,uniphier-pxs2-reset" - for PXs2/LD6b SoC.
+    "socionext,uniphier-ld11-reset" - for LD11 SoC.
+    "socionext,uniphier-ld20-reset" - for LD20 SoC.
 - #reset-cells: should be 1.
 
 Example:
 
 	sysctrl@61840000 {
-		compatible = "socionext,uniphier-ld20-sysctrl",
+		compatible = "socionext,uniphier-ld11-sysctrl",
 			     "simple-mfd", "syscon";
 		reg = <0x61840000 0x4000>;
 
 		reset {
-			compatible = "socionext,uniphier-ld20-reset";
+			compatible = "socionext,uniphier-ld11-reset";
 			#reset-cells = <1>;
 		};
 
@@ -32,30 +32,30 @@
 	};
 
 
-Media I/O (MIO) reset
----------------------
+Media I/O (MIO) reset, SD reset
+-------------------------------
 
 Required properties:
 - compatible: should be one of the following:
-    "socionext,uniphier-sld3-mio-reset" - for PH1-sLD3 SoC.
-    "socionext,uniphier-ld4-mio-reset"  - for PH1-LD4 SoC.
-    "socionext,uniphier-pro4-mio-reset" - for PH1-Pro4 SoC.
-    "socionext,uniphier-sld8-mio-reset" - for PH1-sLD8 SoC.
-    "socionext,uniphier-pro5-mio-reset" - for PH1-Pro5 SoC.
-    "socionext,uniphier-pxs2-mio-reset" - for ProXstream2/PH1-LD6b SoC.
-    "socionext,uniphier-ld11-mio-reset" - for PH1-LD11 SoC.
-    "socionext,uniphier-ld20-mio-reset" - for PH1-LD20 SoC.
+    "socionext,uniphier-sld3-mio-reset" - for sLD3 SoC.
+    "socionext,uniphier-ld4-mio-reset"  - for LD4 SoC.
+    "socionext,uniphier-pro4-mio-reset" - for Pro4 SoC.
+    "socionext,uniphier-sld8-mio-reset" - for sLD8 SoC.
+    "socionext,uniphier-pro5-sd-reset"  - for Pro5 SoC.
+    "socionext,uniphier-pxs2-sd-reset"  - for PXs2/LD6b SoC.
+    "socionext,uniphier-ld11-mio-reset" - for LD11 SoC.
+    "socionext,uniphier-ld20-sd-reset"  - for LD20 SoC.
 - #reset-cells: should be 1.
 
 Example:
 
 	mioctrl@59810000 {
-		compatible = "socionext,uniphier-ld20-mioctrl",
+		compatible = "socionext,uniphier-ld11-mioctrl",
 			     "simple-mfd", "syscon";
 		reg = <0x59810000 0x800>;
 
 		reset {
-			compatible = "socionext,uniphier-ld20-mio-reset";
+			compatible = "socionext,uniphier-ld11-mio-reset";
 			#reset-cells = <1>;
 		};
 
@@ -68,24 +68,24 @@
 
 Required properties:
 - compatible: should be one of the following:
-    "socionext,uniphier-ld4-peri-reset"  - for PH1-LD4 SoC.
-    "socionext,uniphier-pro4-peri-reset" - for PH1-Pro4 SoC.
-    "socionext,uniphier-sld8-peri-reset" - for PH1-sLD8 SoC.
-    "socionext,uniphier-pro5-peri-reset" - for PH1-Pro5 SoC.
-    "socionext,uniphier-pxs2-peri-reset" - for ProXstream2/PH1-LD6b SoC.
-    "socionext,uniphier-ld11-peri-reset" - for PH1-LD11 SoC.
-    "socionext,uniphier-ld20-peri-reset" - for PH1-LD20 SoC.
+    "socionext,uniphier-ld4-peri-reset"  - for LD4 SoC.
+    "socionext,uniphier-pro4-peri-reset" - for Pro4 SoC.
+    "socionext,uniphier-sld8-peri-reset" - for sLD8 SoC.
+    "socionext,uniphier-pro5-peri-reset" - for Pro5 SoC.
+    "socionext,uniphier-pxs2-peri-reset" - for PXs2/LD6b SoC.
+    "socionext,uniphier-ld11-peri-reset" - for LD11 SoC.
+    "socionext,uniphier-ld20-peri-reset" - for LD20 SoC.
 - #reset-cells: should be 1.
 
 Example:
 
 	perictrl@59820000 {
-		compatible = "socionext,uniphier-ld20-perictrl",
+		compatible = "socionext,uniphier-ld11-perictrl",
 			     "simple-mfd", "syscon";
 		reg = <0x59820000 0x200>;
 
 		reset {
-			compatible = "socionext,uniphier-ld20-peri-reset";
+			compatible = "socionext,uniphier-ld11-peri-reset";
 			#reset-cells = <1>;
 		};
 
diff --git a/Documentation/devicetree/bindings/serial/cdns,uart.txt b/Documentation/devicetree/bindings/serial/cdns,uart.txt
index a3eb154..227bb77 100644
--- a/Documentation/devicetree/bindings/serial/cdns,uart.txt
+++ b/Documentation/devicetree/bindings/serial/cdns,uart.txt
@@ -1,7 +1,9 @@
 Binding for Cadence UART Controller
 
 Required properties:
-- compatible : should be "cdns,uart-r1p8", or "xlnx,xuartps"
+- compatible :
+  Use "xlnx,xuartps","cdns,uart-r1p8" for Zynq-7xxx SoC.
+  Use "xlnx,zynqmp-uart","cdns,uart-r1p12" for Zynq Ultrascale+ MPSoC.
 - reg: Should contain UART controller registers location and length.
 - interrupts: Should contain UART controller interrupts.
 - clocks: Must contain phandles to the UART clocks
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index 1e4000d..8d27d1a 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -9,6 +9,14 @@
     - "renesas,scifb-r8a73a4" for R8A73A4 (R-Mobile APE6) SCIFB compatible UART.
     - "renesas,scifa-r8a7740" for R8A7740 (R-Mobile A1) SCIFA compatible UART.
     - "renesas,scifb-r8a7740" for R8A7740 (R-Mobile A1) SCIFB compatible UART.
+    - "renesas,scif-r8a7743" for R8A7743 (RZ/G1M) SCIF compatible UART.
+    - "renesas,scifa-r8a7743" for R8A7743 (RZ/G1M) SCIFA compatible UART.
+    - "renesas,scifb-r8a7743" for R8A7743 (RZ/G1M) SCIFB compatible UART.
+    - "renesas,hscif-r8a7743" for R8A7743 (RZ/G1M) HSCIF compatible UART.
+    - "renesas,scif-r8a7745" for R8A7745 (RZ/G1E) SCIF compatible UART.
+    - "renesas,scifa-r8a7745" for R8A7745 (RZ/G1E) SCIFA compatible UART.
+    - "renesas,scifb-r8a7745" for R8A7745 (RZ/G1E) SCIFB compatible UART.
+    - "renesas,hscif-r8a7745" for R8A7745 (RZ/G1E) HSCIF compatible UART.
     - "renesas,scif-r8a7778" for R8A7778 (R-Car M1) SCIF compatible UART.
     - "renesas,scif-r8a7779" for R8A7779 (R-Car H1) SCIF compatible UART.
     - "renesas,scif-r8a7790" for R8A7790 (R-Car H2) SCIF compatible UART.
diff --git a/Documentation/devicetree/bindings/usb/dwc2.txt b/Documentation/devicetree/bindings/usb/dwc2.txt
index 455f2c3..2c30a54 100644
--- a/Documentation/devicetree/bindings/usb/dwc2.txt
+++ b/Documentation/devicetree/bindings/usb/dwc2.txt
@@ -28,10 +28,7 @@
 - g-use-dma: enable dma usage in gadget driver.
 - g-rx-fifo-size: size of rx fifo size in gadget mode.
 - g-np-tx-fifo-size: size of non-periodic tx fifo size in gadget mode.
-
-Deprecated properties:
-- g-tx-fifo-size: size of periodic tx fifo per endpoint (except ep0)
-  in gadget mode.
+- g-tx-fifo-size: size of periodic tx fifo per endpoint (except ep0) in gadget mode.
 
 Example:
 
diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt
index 0fe1c6e..a20b2fa 100644
--- a/Documentation/networking/netdev-FAQ.txt
+++ b/Documentation/networking/netdev-FAQ.txt
@@ -29,8 +29,8 @@
    Linus, and net-next is where the new code goes for the future release.
    You can find the trees here:
 
-	http://git.kernel.org/?p=linux/kernel/git/davem/net.git
-	http://git.kernel.org/?p=linux/kernel/git/davem/net-next.git
+        https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
+        https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
 
 Q: How often do changes from these trees make it to the mainline Linus tree?
 
@@ -76,7 +76,7 @@
 
 A: Load the mainline (Linus) page here:
 
-	http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git
+	https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
 
    and note the top of the "tags" section.  If it is rc1, it is early
    in the dev cycle.  If it was tagged rc7 a week ago, then a release
@@ -123,7 +123,7 @@
 
    It contains the patches which Dave has selected, but not yet handed
    off to Greg.  If Greg already has the patch, then it will be here:
-	http://git.kernel.org/cgit/linux/kernel/git/stable/stable-queue.git
+	https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git
 
    A quick way to find whether the patch is in this stable-queue is
    to simply clone the repo, and then git grep the mainline commit ID, e.g.
diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt
index 4fb51d3..399e4e8 100644
--- a/Documentation/networking/nf_conntrack-sysctl.txt
+++ b/Documentation/networking/nf_conntrack-sysctl.txt
@@ -33,24 +33,6 @@
 	If this option is enabled, the connection tracking code will
 	provide userspace with connection tracking events via ctnetlink.
 
-nf_conntrack_events_retry_timeout - INTEGER (seconds)
-	default 15
-
-	This option is only relevant when "reliable connection tracking
-	events" are used.  Normally, ctnetlink is "lossy", that is,
-	events are normally dropped when userspace listeners can't keep up.
-
-	Userspace can request "reliable event mode".  When this mode is
-	active, the conntrack will only be destroyed after the event was
-	delivered.  If event delivery fails, the kernel periodically
-	re-tries to send the event to userspace.
-
-	This is the maximum interval the kernel should use when re-trying
-	to deliver the destroy event.
-
-	A higher number means there will be fewer delivery retries and it
-	will take longer for a backlog to be processed.
-
 nf_conntrack_expect_max - INTEGER
 	Maximum size of expectation table.  Default value is
 	nf_conntrack_buckets / 256. Minimum is 1.
diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index f2491a8..e5dd9f4 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -4,7 +4,17 @@
 1. Acquisition Orders
 ---------------------
 
-(to be written)
+The acquisition orders for mutexes are as follows:
+
+- kvm->lock is taken outside vcpu->mutex
+
+- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
+
+- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
+  them together is quite rare.
+
+For spinlocks, kvm_lock is taken outside kvm->mmu_lock.  Everything
+else is a leaf: no other lock is taken inside the critical sections.
 
 2: Exception
 ------------
diff --git a/MAINTAINERS b/MAINTAINERS
index c447953..411e3b8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1442,6 +1442,7 @@
 F:	arch/arm/configs/mvebu_*_defconfig
 
 ARM/Marvell Berlin SoC support
+M:	Jisheng Zhang <jszhang@marvell.com>
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -2551,15 +2552,18 @@
 F:	drivers/net/ethernet/broadcom/genet/
 
 BROADCOM BNX2 GIGABIT ETHERNET DRIVER
-M:	Sony Chacko <sony.chacko@qlogic.com>
-M:	Dept-HSGLinuxNICDev@qlogic.com
+M:	Rasesh Mody <rasesh.mody@cavium.com>
+M:	Harish Patil <harish.patil@cavium.com>
+M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2.*
 F:	drivers/net/ethernet/broadcom/bnx2_*
 
 BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M:	Ariel Elior <ariel.elior@qlogic.com>
+M:	Yuval Mintz <Yuval.Mintz@cavium.com>
+M:	Ariel Elior <ariel.elior@cavium.com>
+M:	everest-linux-l2@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
@@ -2766,7 +2770,9 @@
 F:	drivers/scsi/bfa/
 
 BROCADE BNA 10 GIGABIT ETHERNET DRIVER
-M:	Rasesh Mody <rasesh.mody@qlogic.com>
+M:	Rasesh Mody <rasesh.mody@cavium.com>
+M:	Sudarsana Kalluru <sudarsana.kalluru@cavium.com>
+M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/brocade/bna/
@@ -5287,6 +5293,12 @@
 S:	Maintained
 F:	scripts/get_maintainer.pl
 
+GENWQE (IBM Generic Workqueue Card)
+M:	Frank Haverkamp <haver@linux.vnet.ibm.com>
+M:	Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
+S:	Supported
+F:	drivers/misc/genwqe/
+
 GFS2 FILE SYSTEM
 M:	Steven Whitehouse <swhiteho@redhat.com>
 M:	Bob Peterson <rpeterso@redhat.com>
@@ -7913,6 +7925,10 @@
 MEMORY TECHNOLOGY DEVICES (MTD)
 M:	David Woodhouse <dwmw2@infradead.org>
 M:	Brian Norris <computersforpeace@gmail.com>
+M:	Boris Brezillon <boris.brezillon@free-electrons.com>
+M:	Marek Vasut <marek.vasut@gmail.com>
+M:	Richard Weinberger <richard@nod.at>
+M:	Cyrille Pitchen <cyrille.pitchen@atmel.com>
 L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
 Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
@@ -8100,6 +8116,7 @@
 F:	drivers/media/dvb-frontends/mn88473*
 
 MODULE SUPPORT
+M:	Jessica Yu <jeyu@redhat.com>
 M:	Rusty Russell <rusty@rustcorp.com.au>
 S:	Maintained
 F:	include/linux/module.h
@@ -8509,11 +8526,10 @@
 F:	drivers/net/wireless/
 
 NETXEN (1/10) GbE SUPPORT
-M:	Manish Chopra <manish.chopra@qlogic.com>
-M:	Sony Chacko <sony.chacko@qlogic.com>
-M:	Rajesh Borundia <rajesh.borundia@qlogic.com>
+M:	Manish Chopra <manish.chopra@cavium.com>
+M:	Rahul Verma <rahul.verma@cavium.com>
+M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
-W:	http://www.qlogic.com
 S:	Supported
 F:	drivers/net/ethernet/qlogic/netxen/
 
@@ -9889,33 +9905,32 @@
 F:	drivers/scsi/qla4xxx/
 
 QLOGIC QLA3XXX NETWORK DRIVER
-M:	Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
-M:	Ron Mercer <ron.mercer@qlogic.com>
-M:	linux-driver@qlogic.com
+M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/LICENSE.qla3xxx
 F:	drivers/net/ethernet/qlogic/qla3xxx.*
 
 QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M:	Dept-GELinuxNICDev@qlogic.com
+M:	Harish Patil <harish.patil@cavium.com>
+M:	Manish Chopra <manish.chopra@cavium.com>
+M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/qlcnic/
 
 QLOGIC QLGE 10Gb ETHERNET DRIVER
-M:	Harish Patil <harish.patil@qlogic.com>
-M:	Sudarsana Kalluru <sudarsana.kalluru@qlogic.com>
-M:	Dept-GELinuxNICDev@qlogic.com
-M:	linux-driver@qlogic.com
+M:	Harish Patil <harish.patil@cavium.com>
+M:	Manish Chopra <manish.chopra@cavium.com>
+M:	Dept-GELinuxNICDev@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/qlge/
 
 QLOGIC QL4xxx ETHERNET DRIVER
-M:	Yuval Mintz <Yuval.Mintz@qlogic.com>
-M:	Ariel Elior <Ariel.Elior@qlogic.com>
-M:	everest-linux-l2@qlogic.com
+M:	Yuval Mintz <Yuval.Mintz@cavium.com>
+M:	Ariel Elior <Ariel.Elior@cavium.com>
+M:	everest-linux-l2@cavium.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/qed/
@@ -11393,6 +11408,17 @@
 S:	Maintained
 F:	drivers/clk/spear/
 
+SPI NOR SUBSYSTEM
+M:	Cyrille Pitchen <cyrille.pitchen@atmel.com>
+M:	Marek Vasut <marek.vasut@gmail.com>
+L:	linux-mtd@lists.infradead.org
+W:	http://www.linux-mtd.infradead.org/
+Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
+T:	git git://github.com/spi-nor/linux.git
+S:	Maintained
+F:	drivers/mtd/spi-nor/
+F:	include/linux/mtd/spi-nor.h
+
 SPI SUBSYSTEM
 M:	Mark Brown <broonie@kernel.org>
 L:	linux-spi@vger.kernel.org
@@ -12772,6 +12798,7 @@
 
 VIRTIO CORE, NET AND BLOCK DRIVERS
 M:	"Michael S. Tsirkin" <mst@redhat.com>
+M:	Jason Wang <jasowang@redhat.com>
 L:	virtualization@lists.linux-foundation.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/virtio/
@@ -12802,6 +12829,7 @@
 
 VIRTIO HOST (VHOST)
 M:	"Michael S. Tsirkin" <mst@redhat.com>
+M:	Jason Wang <jasowang@redhat.com>
 L:	kvm@vger.kernel.org
 L:	virtualization@lists.linux-foundation.org
 L:	netdev@vger.kernel.org
diff --git a/Makefile b/Makefile
index 93beca4..f97f786 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index ecd1237..bd204bf 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -41,6 +41,8 @@
 	select PERF_USE_VMALLOC
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_GENERIC_DMA_COHERENT
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZMA
 
 config MIGHT_HAVE_PCI
 	bool
@@ -186,14 +188,6 @@
 config ARC_HAS_COH_CACHES
 	def_bool n
 
-config ARC_MCIP
-	bool "ARConnect Multicore IP (MCIP) Support "
-	depends on ISA_ARCV2
-	help
-	  This IP block enables SMP in ARC-HS38 cores.
-	  It provides for cross-core interrupts, multi-core debug
-	  hardware semaphores, shared memory,....
-
 config NR_CPUS
 	int "Maximum number of CPUs (2-4096)"
 	range 2 4096
@@ -211,6 +205,15 @@
 
 endif	#SMP
 
+config ARC_MCIP
+	bool "ARConnect Multicore IP (MCIP) Support "
+	depends on ISA_ARCV2
+	default y if SMP
+	help
+	  This IP block enables SMP in ARC-HS38 cores.
+	  It provides for cross-core interrupts, multi-core debug
+	  hardware semaphores, shared memory,....
+
 menuconfig ARC_CACHE
 	bool "Enable Cache Support"
 	default y
@@ -537,14 +540,6 @@
 	bool "Paranoia Checks in Low Level TLB Handlers"
 	default n
 
-config ARC_DBG_TLB_MISS_COUNT
-	bool "Profile TLB Misses"
-	default n
-	select DEBUG_FS
-	help
-	  Counts number of I and D TLB Misses and exports them via Debugfs
-	  The counters can be cleared via Debugfs as well
-
 endif
 
 config ARC_UBOOT_SUPPORT
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index aa82d13..864adad 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -50,9 +50,6 @@
 
 cflags-$(atleast_gcc44)			+= -fsection-anchors
 
-cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
-cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
-
 ifdef CONFIG_ISA_ARCV2
 
 ifndef CONFIG_ARC_HAS_LL64
diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile
index e597cb34..f94cf15 100644
--- a/arch/arc/boot/Makefile
+++ b/arch/arc/boot/Makefile
@@ -14,9 +14,15 @@
 
 suffix-y := bin
 suffix-$(CONFIG_KERNEL_GZIP)	:= gz
+suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
 
-targets += uImage uImage.bin uImage.gz
-extra-y += vmlinux.bin vmlinux.bin.gz
+targets += uImage
+targets += uImage.bin
+targets += uImage.gz
+targets += uImage.lzma
+extra-y += vmlinux.bin
+extra-y += vmlinux.bin.gz
+extra-y += vmlinux.bin.lzma
 
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
@@ -24,12 +30,18 @@
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
 
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,lzma)
+
 $(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,uimage,none)
 
 $(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
 	$(call if_changed,uimage,gzip)
 
+$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
+	$(call if_changed,uimage,lzma)
+
 $(obj)/uImage: $(obj)/uImage.$(suffix-y)
 	@ln -sf $(notdir $<) $@
 	@echo '  Image $@ is ready'
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index db25c65..7f3f9f6 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -349,10 +349,11 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
+	const char *details, *name;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
-		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
+		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
 			     fpu_sp:1, fpu_dp:1, pad2:6,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
 			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index fb781e3..b3410ff 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -53,7 +53,7 @@ extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
 extern void read_decode_cache_bcr(void);
 
-extern int ioc_exists;
+extern int ioc_enable;
 extern unsigned long perip_base, perip_end;
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index 7096f97..aa2d6da 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -54,7 +54,7 @@ extern int elf_check_arch(const struct elf32_hdr *);
  * the loader.  We need to make sure that it is out of the way of the program
  * that it will "exec", and that there is sufficient room for the brk.
  */
-#define ELF_ET_DYN_BASE		(2 * TASK_SIZE / 3)
+#define ELF_ET_DYN_BASE		(2UL * TASK_SIZE / 3)
 
 /*
  * When the program starts, a1 contains a pointer to a function to be
diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h
index 847e3bb..c8fbe41 100644
--- a/arch/arc/include/asm/mcip.h
+++ b/arch/arc/include/asm/mcip.h
@@ -55,6 +55,22 @@ struct mcip_cmd {
 #define IDU_M_DISTRI_DEST		0x2
 };
 
+struct mcip_bcr {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad3:8,
+			     idu:1, llm:1, num_cores:6,
+			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
+			     msg:1, sem:1, ipi:1, pad:1,
+			     ver:8;
+#else
+		unsigned int ver:8,
+			     pad:1, ipi:1, sem:1, msg:1,
+			     pad2:1, dbg:1, gfrc:1, iocoh:1,
+			     num_cores:6, llm:1, idu:1,
+			     pad3:8;
+#endif
+};
+
 /*
  * MCIP programming model
  *
diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h
index 518222b..6e91d8b 100644
--- a/arch/arc/include/asm/module.h
+++ b/arch/arc/include/asm/module.h
@@ -18,6 +18,7 @@
 struct mod_arch_specific {
 	void *unw_info;
 	int unw_sec_idx;
+	const char *secstr;
 };
 #endif
 
diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h
index 48b37c6..cb954cd 100644
--- a/arch/arc/include/asm/setup.h
+++ b/arch/arc/include/asm/setup.h
@@ -27,11 +27,6 @@ struct id_to_str {
 	const char *str;
 };
 
-struct cpuinfo_data {
-	struct id_to_str info;
-	int up_range;
-};
-
 extern int root_mountflags, end_mem;
 
 void setup_processor(void);
@@ -43,5 +38,6 @@ void __init setup_arch_memory(void);
 #define IS_USED_RUN(v)		((v) ? "" : "(not used) ")
 #define IS_USED_CFG(cfg)	IS_USED_RUN(IS_ENABLED(cfg))
 #define IS_AVAIL2(v, s, cfg)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg))
+#define IS_AVAIL3(v, v2, s)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_DISABLED_RUN(v2))
 
 #endif /* __ASMARC_SETUP_H */
diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h
index e56f9fc..772b67c 100644
--- a/arch/arc/include/asm/syscalls.h
+++ b/arch/arc/include/asm/syscalls.h
@@ -17,6 +17,7 @@ int sys_clone_wrapper(int, int, int, int, int);
 int sys_cacheflush(uint32_t, uint32_t uint32_t);
 int sys_arc_settls(void *);
 int sys_arc_gettls(void);
+int sys_arc_usr_cmpxchg(int *, int, int);
 
 #include <asm-generic/syscalls.h>
 
diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 41fa2ec..9a34136 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -27,18 +27,19 @@
 
 #define NR_syscalls	__NR_syscalls
 
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+
 /* ARC specific syscall */
 #define __NR_cacheflush		(__NR_arch_specific_syscall + 0)
 #define __NR_arc_settls		(__NR_arch_specific_syscall + 1)
 #define __NR_arc_gettls		(__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg	(__NR_arch_specific_syscall + 4)
 
 __SYSCALL(__NR_cacheflush, sys_cacheflush)
 __SYSCALL(__NR_arc_settls, sys_arc_settls)
 __SYSCALL(__NR_arc_gettls, sys_arc_gettls)
-
-
-/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
-#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
 __SYSCALL(__NR_sysfs, sys_sysfs)
 
 #undef __SYSCALL
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 72f9179..c424d5a 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -15,11 +15,12 @@
 #include <asm/mcip.h>
 #include <asm/setup.h>
 
-static char smp_cpuinfo_buf[128];
-static int idu_detected;
-
 static DEFINE_RAW_SPINLOCK(mcip_lock);
 
+#ifdef CONFIG_SMP
+
+static char smp_cpuinfo_buf[128];
+
 static void mcip_setup_per_cpu(int cpu)
 {
 	smp_ipi_irq_setup(cpu, IPI_IRQ);
@@ -86,21 +87,7 @@ static void mcip_ipi_clear(int irq)
 
 static void mcip_probe_n_setup(void)
 {
-	struct mcip_bcr {
-#ifdef CONFIG_CPU_BIG_ENDIAN
-		unsigned int pad3:8,
-			     idu:1, llm:1, num_cores:6,
-			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
-			     msg:1, sem:1, ipi:1, pad:1,
-			     ver:8;
-#else
-		unsigned int ver:8,
-			     pad:1, ipi:1, sem:1, msg:1,
-			     pad2:1, dbg:1, gfrc:1, iocoh:1,
-			     num_cores:6, llm:1, idu:1,
-			     pad3:8;
-#endif
-	} mp;
+	struct mcip_bcr mp;
 
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
@@ -114,7 +101,6 @@ static void mcip_probe_n_setup(void)
 		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	cpuinfo_arc700[0].extn.gfrc = mp.gfrc;
-	idu_detected = mp.idu;
 
 	if (mp.dbg) {
 		__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf);
@@ -130,6 +116,8 @@ struct plat_smp_ops plat_smp_ops = {
 	.ipi_clear	= mcip_ipi_clear,
 };
 
+#endif
+
 /***************************************************************************
  * ARCv2 Interrupt Distribution Unit (IDU)
  *
@@ -295,8 +283,11 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 	/* Read IDU BCR to confirm nr_irqs */
 	int nr_irqs = of_irq_count(intc);
 	int i, irq;
+	struct mcip_bcr mp;
 
-	if (!idu_detected)
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+
+	if (!mp.idu)
 		panic("IDU not detected, but DeviceTree using it");
 
 	pr_info("MCIP: IDU referenced from Devicetree %d irqs\n", nr_irqs);
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
index 9a28497..42e964d 100644
--- a/arch/arc/kernel/module.c
+++ b/arch/arc/kernel/module.c
@@ -30,17 +30,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 			      char *secstr, struct module *mod)
 {
 #ifdef CONFIG_ARC_DW2_UNWIND
-	int i;
-
 	mod->arch.unw_sec_idx = 0;
 	mod->arch.unw_info = NULL;
-
-	for (i = 1; i < hdr->e_shnum; i++) {
-		if (strcmp(secstr+sechdrs[i].sh_name, ".eh_frame") == 0) {
-			mod->arch.unw_sec_idx = i;
-			break;
-		}
-	}
+	mod->arch.secstr = secstr;
 #endif
 	return 0;
 }
@@ -59,29 +51,33 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 		       unsigned int relsec,	/* sec index for relo sec */
 		       struct module *module)
 {
-	int i, n;
+	int i, n, relo_type;
 	Elf32_Rela *rel_entry = (void *)sechdrs[relsec].sh_addr;
 	Elf32_Sym *sym_entry, *sym_sec;
-	Elf32_Addr relocation;
-	Elf32_Addr location;
-	Elf32_Addr sec_to_patch;
-	int relo_type;
+	Elf32_Addr relocation, location, tgt_addr;
+	unsigned int tgtsec;
 
-	sec_to_patch = sechdrs[sechdrs[relsec].sh_info].sh_addr;
+	/*
+	 * @relsec has relocations e.g. .rela.init.text
+	 * @tgtsec is section to patch e.g. .init.text
+	 */
+	tgtsec = sechdrs[relsec].sh_info;
+	tgt_addr = sechdrs[tgtsec].sh_addr;
 	sym_sec = (Elf32_Sym *) sechdrs[symindex].sh_addr;
 	n = sechdrs[relsec].sh_size / sizeof(*rel_entry);
 
-	pr_debug("\n========== Module Sym reloc ===========================\n");
-	pr_debug("Section to fixup %x\n", sec_to_patch);
+	pr_debug("\nSection to fixup %s @%x\n",
+		 module->arch.secstr + sechdrs[tgtsec].sh_name, tgt_addr);
 	pr_debug("=========================================================\n");
-	pr_debug("rela->r_off | rela->addend | sym->st_value | ADDR | VALUE\n");
+	pr_debug("r_off\tr_add\tst_value ADDRESS  VALUE\n");
 	pr_debug("=========================================================\n");
 
 	/* Loop thru entries in relocation section */
 	for (i = 0; i < n; i++) {
+		const char *s;
 
 		/* This is where to make the change */
-		location = sec_to_patch + rel_entry[i].r_offset;
+		location = tgt_addr + rel_entry[i].r_offset;
 
 		/* This is the symbol it is referring to.  Note that all
 		   undefined symbols have been resolved.  */
@@ -89,10 +85,15 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 
 		relocation = sym_entry->st_value + rel_entry[i].r_addend;
 
-		pr_debug("\t%x\t\t%x\t\t%x  %x %x [%s]\n",
-			rel_entry[i].r_offset, rel_entry[i].r_addend,
-			sym_entry->st_value, location, relocation,
-			strtab + sym_entry->st_name);
+		if (sym_entry->st_name == 0 && ELF_ST_TYPE (sym_entry->st_info) == STT_SECTION) {
+			s = module->arch.secstr + sechdrs[sym_entry->st_shndx].sh_name;
+		} else {
+			s = strtab + sym_entry->st_name;
+		}
+
+		pr_debug("   %x\t%x\t%x %x %x [%s]\n",
+			 rel_entry[i].r_offset, rel_entry[i].r_addend,
+			 sym_entry->st_value, location, relocation, s);
 
 		/* This assumes modules are built with -mlong-calls
 		 * so any branches/jumps are absolute 32 bit jmps
@@ -111,6 +112,10 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			goto relo_err;
 
 	}
+
+	if (strcmp(module->arch.secstr+sechdrs[tgtsec].sh_name, ".eh_frame") == 0)
+		module->arch.unw_sec_idx = tgtsec;
+
 	return 0;
 
 relo_err:
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index be1972b..59aa43c 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -41,6 +41,39 @@ SYSCALL_DEFINE0(arc_gettls)
 	return task_thread_info(current)->thr_ptr;
 }
 
+SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
+{
+	int uval;
+	int ret;
+
+	/*
+	 * This is only for old cores lacking LLOCK/SCOND, which by defintion
+	 * can't possibly be SMP. Thus doesn't need to be SMP safe.
+	 * And this also helps reduce the overhead for serializing in
+	 * the UP case
+	 */
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP));
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	preempt_disable();
+
+	ret = __get_user(uval, uaddr);
+	if (ret)
+		goto done;
+
+	if (uval != expected)
+		ret = -EAGAIN;
+	else
+		ret = __put_user(new, uaddr);
+
+done:
+	preempt_enable();
+
+	return ret;
+}
+
 void arch_cpu_idle(void)
 {
 	/* sleep, but enable all interrupts before committing */
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 3df7f9c..0385df7 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -40,6 +40,29 @@ struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 
 struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 
+static const struct id_to_str arc_cpu_rel[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
+	{ 0x34, "R4.10"},
+	{ 0x35, "R4.11"},
+#else
+	{ 0x51, "R2.0" },
+	{ 0x52, "R2.1" },
+	{ 0x53, "R3.0" },
+#endif
+	{ 0x00, NULL   }
+};
+
+static const struct id_to_str arc_cpu_nm[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
+	{ 0x20, "ARC 600"   },
+	{ 0x30, "ARC 770"   },  /* 750 identified seperately */
+#else
+	{ 0x40, "ARC EM"  },
+	{ 0x50, "ARC HS38"  },
+#endif
+	{ 0x00, "Unknown"   }
+};
+
 static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
 {
 	if (is_isa_arcompact()) {
@@ -92,11 +115,26 @@ static void read_arc_build_cfg_regs(void)
 	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+	const struct id_to_str *tbl;
+
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
 	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
+	for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) {
+		if (cpu->core.family == tbl->id) {
+			cpu->details = tbl->str;
+			break;
+		}
+	}
+
+	for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) {
+		if ((cpu->core.family & 0xF0) == tbl->id)
+			break;
+	}
+	cpu->name = tbl->str;
+
 	READ_BCR(ARC_REG_TIMERS_BCR, timer);
 	cpu->extn.timer0 = timer.t0;
 	cpu->extn.timer1 = timer.t1;
@@ -111,6 +149,9 @@ static void read_arc_build_cfg_regs(void)
 	cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0;        /* 1,3 */
 	cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0;
 	cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */
+	cpu->extn.swape = (cpu->core.family >= 0x34) ? 1 :
+				IS_ENABLED(CONFIG_ARC_HAS_SWAPE);
+
 	READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
 
 	/* Read CCM BCRs for boot reporting even if not enabled in Kconfig */
@@ -160,64 +201,38 @@ static void read_arc_build_cfg_regs(void)
 	cpu->extn.rtt = bcr.ver ? 1 : 0;
 
 	cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
+
+	/* some hacks for lack of feature BCR info in old ARC700 cores */
+	if (is_isa_arcompact()) {
+		if (!cpu->isa.ver)	/* ISA BCR absent, use Kconfig info */
+			cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
+		else
+			cpu->isa.atomic = cpu->isa.atomic1;
+
+		cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+
+		 /* there's no direct way to distinguish 750 vs. 770 */
+		if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3))
+			cpu->name = "ARC750";
+	}
 }
 
-static const struct cpuinfo_data arc_cpu_tbl[] = {
-#ifdef CONFIG_ISA_ARCOMPACT
-	{ {0x20, "ARC 600"      }, 0x2F},
-	{ {0x30, "ARC 700"      }, 0x33},
-	{ {0x34, "ARC 700 R4.10"}, 0x34},
-	{ {0x35, "ARC 700 R4.11"}, 0x35},
-#else
-	{ {0x50, "ARC HS38 R2.0"}, 0x51},
-	{ {0x52, "ARC HS38 R2.1"}, 0x52},
-	{ {0x53, "ARC HS38 R3.0"}, 0x53},
-#endif
-	{ {0x00, NULL		} }
-};
-
-
 static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
 	struct bcr_identity *core = &cpu->core;
-	const struct cpuinfo_data *tbl;
-	char *isa_nm;
-	int i, be, atomic;
-	int n = 0;
+	int i, n = 0;
 
 	FIX_PTR(cpu);
 
-	if (is_isa_arcompact()) {
-		isa_nm = "ARCompact";
-		be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
-
-		atomic = cpu->isa.atomic1;
-		if (!cpu->isa.ver)	/* ISA BCR absent, use Kconfig info */
-			atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
-	} else {
-		isa_nm = "ARCv2";
-		be = cpu->isa.be;
-		atomic = cpu->isa.atomic;
-	}
-
 	n += scnprintf(buf + n, len - n,
 		       "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n",
 		       core->family, core->cpu_id, core->chip_id);
 
-	for (tbl = &arc_cpu_tbl[0]; tbl->info.id != 0; tbl++) {
-		if ((core->family >= tbl->info.id) &&
-		    (core->family <= tbl->up_range)) {
-			n += scnprintf(buf + n, len - n,
-				       "processor [%d]\t: %s (%s ISA) %s\n",
-				       cpu_id, tbl->info.str, isa_nm,
-				       IS_AVAIL1(be, "[Big-Endian]"));
-			break;
-		}
-	}
-
-	if (tbl->info.id == 0)
-		n += scnprintf(buf + n, len - n, "UNKNOWN ARC Processor\n");
+	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n",
+		       cpu_id, cpu->name, cpu->details,
+		       is_isa_arcompact() ? "ARCompact" : "ARCv2",
+		       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"));
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
 		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
@@ -226,7 +241,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 				 CONFIG_ARC_HAS_RTC));
 
 	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
-			   IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
+			   IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
 			   IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
 			   IS_AVAIL1(cpu->isa.unalign, "unalign (not used)"));
 
@@ -253,7 +268,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       IS_AVAIL1(cpu->extn.swap, "swap "),
 		       IS_AVAIL1(cpu->extn.minmax, "minmax "),
 		       IS_AVAIL1(cpu->extn.crc, "crc "),
-		       IS_AVAIL2(1, "swape", CONFIG_ARC_HAS_SWAPE));
+		       IS_AVAIL2(cpu->extn.swape, "swape", CONFIG_ARC_HAS_SWAPE));
 
 	if (cpu->bpu.ver)
 		n += scnprintf(buf + n, len - n,
@@ -272,9 +287,7 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 
 	FIX_PTR(cpu);
 
-	n += scnprintf(buf + n, len - n,
-		       "Vector Table\t: %#x\nPeripherals\t: %#lx:%#lx\n",
-		       cpu->vec_base, perip_base, perip_end);
+	n += scnprintf(buf + n, len - n, "Vector Table\t: %#x\n", cpu->vec_base);
 
 	if (cpu->extn.fpu_sp || cpu->extn.fpu_dp)
 		n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
@@ -507,7 +520,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 	 * way to pass it w/o having to kmalloc/free a 2 byte string.
 	 * Encode cpu-id as 0xFFcccc, which is decoded by show routine.
 	 */
-	return *pos < num_possible_cpus() ? cpu_to_ptr(*pos) : NULL;
+	return *pos < nr_cpu_ids ? cpu_to_ptr(*pos) : NULL;
 }
 
 static void *c_next(struct seq_file *m, void *v, loff_t *pos)
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 934150e..82f9bc8 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -237,113 +237,3 @@ void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
 	if (!user_mode(regs))
 		show_stacktrace(current, regs);
 }
-
-#ifdef CONFIG_DEBUG_FS
-
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/mount.h>
-#include <linux/pagemap.h>
-#include <linux/init.h>
-#include <linux/namei.h>
-#include <linux/debugfs.h>
-
-static struct dentry *test_dentry;
-static struct dentry *test_dir;
-static struct dentry *test_u32_dentry;
-
-static u32 clr_on_read = 1;
-
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-u32 numitlb, numdtlb, num_pte_not_present;
-
-static int fill_display_data(char *kbuf)
-{
-	size_t num = 0;
-	num += sprintf(kbuf + num, "I-TLB Miss %x\n", numitlb);
-	num += sprintf(kbuf + num, "D-TLB Miss %x\n", numdtlb);
-	num += sprintf(kbuf + num, "PTE not present %x\n", num_pte_not_present);
-
-	if (clr_on_read)
-		numitlb = numdtlb = num_pte_not_present = 0;
-
-	return num;
-}
-
-static int tlb_stats_open(struct inode *inode, struct file *file)
-{
-	file->private_data = (void *)__get_free_page(GFP_KERNEL);
-	return 0;
-}
-
-/* called on user read(): display the counters */
-static ssize_t tlb_stats_output(struct file *file,	/* file descriptor */
-				char __user *user_buf,	/* user buffer */
-				size_t len,		/* length of buffer */
-				loff_t *offset)		/* offset in the file */
-{
-	size_t num;
-	char *kbuf = (char *)file->private_data;
-
-	/* All of the data can he shoved in one iteration */
-	if (*offset != 0)
-		return 0;
-
-	num = fill_display_data(kbuf);
-
-	/* simple_read_from_buffer() is helper for copy to user space
-	   It copies up to @2 (num) bytes from kernel buffer @4 (kbuf) at offset
-	   @3 (offset) into the user space address starting at @1 (user_buf).
-	   @5 (len) is max size of user buffer
-	 */
-	return simple_read_from_buffer(user_buf, num, offset, kbuf, len);
-}
-
-/* called on user write : clears the counters */
-static ssize_t tlb_stats_clear(struct file *file, const char __user *user_buf,
-			       size_t length, loff_t *offset)
-{
-	numitlb = numdtlb = num_pte_not_present = 0;
-	return length;
-}
-
-static int tlb_stats_close(struct inode *inode, struct file *file)
-{
-	free_page((unsigned long)(file->private_data));
-	return 0;
-}
-
-static const struct file_operations tlb_stats_file_ops = {
-	.read = tlb_stats_output,
-	.write = tlb_stats_clear,
-	.open = tlb_stats_open,
-	.release = tlb_stats_close
-};
-#endif
-
-static int __init arc_debugfs_init(void)
-{
-	test_dir = debugfs_create_dir("arc", NULL);
-
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	test_dentry = debugfs_create_file("tlb_stats", 0444, test_dir, NULL,
-					  &tlb_stats_file_ops);
-#endif
-
-	test_u32_dentry =
-	    debugfs_create_u32("clr_on_read", 0444, test_dir, &clr_on_read);
-
-	return 0;
-}
-
-module_init(arc_debugfs_init);
-
-static void __exit arc_debugfs_exit(void)
-{
-	debugfs_remove(test_u32_dentry);
-	debugfs_remove(test_dentry);
-	debugfs_remove(test_dir);
-}
-module_exit(arc_debugfs_exit);
-
-#endif
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 97dddbe..2b96cfc 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -22,8 +22,8 @@
 #include <asm/setup.h>
 
 static int l2_line_sz;
-int ioc_exists;
-volatile int slc_enable = 1, ioc_enable = 1;
+static int ioc_exists;
+int slc_enable = 1, ioc_enable = 1;
 unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
 unsigned long perip_end = 0xFFFFFFFF; /* legacy value */
 
@@ -53,18 +53,15 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 	PR_CACHE(&cpuinfo_arc700[c].icache, CONFIG_ARC_HAS_ICACHE, "I-Cache");
 	PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache");
 
-	if (!is_isa_arcv2())
-                return buf;
-
 	p = &cpuinfo_arc700[c].slc;
 	if (p->ver)
 		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));
 
-	if (ioc_exists)
-		n += scnprintf(buf + n, len - n, "IOC\t\t:%s\n",
-				IS_DISABLED_RUN(ioc_enable));
+	n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n",
+		       perip_base,
+		       IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency "));
 
 	return buf;
 }
@@ -113,8 +110,10 @@ static void read_decode_cache_bcr_arcv2(int cpu)
 	}
 
 	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
-	if (cbcr.c && ioc_enable)
+	if (cbcr.c)
 		ioc_exists = 1;
+	else
+		ioc_enable = 0;
 
 	/* HS 2.0 didn't have AUX_VOL */
 	if (cpuinfo_arc700[cpu].core.family > 0x51) {
@@ -1002,7 +1001,7 @@ void arc_cache_init(void)
 			read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_DISABLE);
 	}
 
-	if (is_isa_arcv2() && ioc_exists) {
+	if (is_isa_arcv2() && ioc_enable) {
 		/* IO coherency base - 0x8z */
 		write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000);
 		/* IO coherency aperture size - 512Mb: 0x8z-0xAz */
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 20afc65..60aab5a 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -45,7 +45,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 	 *   -For coherent data, Read/Write to buffers terminate early in cache
 	 *   (vs. always going to memory - thus are faster)
 	 */
-	if ((is_isa_arcv2() && ioc_exists) ||
+	if ((is_isa_arcv2() && ioc_enable) ||
 	    (attrs & DMA_ATTR_NON_CONSISTENT))
 		need_coh = 0;
 
@@ -97,7 +97,7 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
 	int is_non_coh = 1;
 
 	is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) ||
-			(is_isa_arcv2() && ioc_exists);
+			(is_isa_arcv2() && ioc_enable);
 
 	if (PageHighMem(page) || !is_non_coh)
 		iounmap((void __force __iomem *)vaddr);
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index ec868a9..bdb295e 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -793,16 +793,16 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len)
 	char super_pg[64] = "";
 
 	if (p_mmu->s_pg_sz_m)
-		scnprintf(super_pg, 64, "%dM Super Page%s, ",
+		scnprintf(super_pg, 64, "%dM Super Page %s",
 			  p_mmu->s_pg_sz_m,
 			  IS_USED_CFG(CONFIG_TRANSPARENT_HUGEPAGE));
 
 	n += scnprintf(buf + n, len - n,
-		      "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d %s%s\n",
+		      "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d%s%s\n",
 		       p_mmu->ver, p_mmu->pg_sz_k, super_pg,
 		       p_mmu->sets * p_mmu->ways, p_mmu->sets, p_mmu->ways,
 		       p_mmu->u_dtlb, p_mmu->u_itlb,
-		       IS_AVAIL2(p_mmu->pae, "PAE40 ", CONFIG_ARC_HAS_PAE40));
+		       IS_AVAIL2(p_mmu->pae, ", PAE40 ", CONFIG_ARC_HAS_PAE40));
 
 	return buf;
 }
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index f1967ee..b30e4e3 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -237,15 +237,6 @@
 
 2:
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	and.f 0, r0, _PAGE_PRESENT
-	bz   1f
-	ld   r3, [num_pte_not_present]
-	add  r3, r3, 1
-	st   r3, [num_pte_not_present]
-1:
-#endif
-
 .endm
 
 ;-----------------------------------------------------------------
@@ -309,12 +300,6 @@
 
 	TLBMISS_FREEUP_REGS
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	ld  r0, [@numitlb]
-	add r0, r0, 1
-	st  r0, [@numitlb]
-#endif
-
 	;----------------------------------------------------------------
 	; Get the PTE corresponding to V-addr accessed, r2 is setup with EFA
 	LOAD_FAULT_PTE
@@ -349,12 +334,6 @@
 
 	TLBMISS_FREEUP_REGS
 
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-	ld  r0, [@numdtlb]
-	add r0, r0, 1
-	st  r0, [@numdtlb]
-#endif
-
 	;----------------------------------------------------------------
 	; Get the PTE corresponding to V-addr accessed
 	; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE, r2 = EFA
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index b3df1c6..386eee6 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -239,14 +239,25 @@
 			arm,primecell-periphid = <0x10480180>;
 			max-frequency = <100000000>;
 			bus-width = <4>;
+			cap-sd-highspeed;
 			cap-mmc-highspeed;
+			sd-uhs-sdr12;
+			sd-uhs-sdr25;
+			/* All direction control is used */
+			st,sig-dir-cmd;
+			st,sig-dir-dat0;
+			st,sig-dir-dat2;
+			st,sig-dir-dat31;
+			st,sig-pin-fbclk;
+			full-pwr-cycle;
 			vmmc-supply = <&ab8500_ldo_aux3_reg>;
 			vqmmc-supply = <&vmmci>;
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&sdi0_default_mode>;
 			pinctrl-1 = <&sdi0_sleep_mode>;
 
-			cd-gpios  = <&gpio6 26 GPIO_ACTIVE_LOW>; // 218
+			/* GPIO218 MMC_CD */
+			cd-gpios  = <&gpio6 26 GPIO_ACTIVE_LOW>;
 
 			status = "okay";
 		};
@@ -549,7 +560,7 @@
 					/* VMMCI level-shifter enable */
 					snowball_cfg3 {
 						pins = "GPIO217_AH12";
-						ste,config = <&gpio_out_lo>;
+						ste,config = <&gpio_out_hi>;
 					};
 					/* VMMCI level-shifter voltage select */
 					snowball_cfg4 {
diff --git a/arch/arm/boot/dts/uniphier-pro5.dtsi b/arch/arm/boot/dts/uniphier-pro5.dtsi
index 2c49c36..5357ea9 100644
--- a/arch/arm/boot/dts/uniphier-pro5.dtsi
+++ b/arch/arm/boot/dts/uniphier-pro5.dtsi
@@ -184,11 +184,11 @@
 };
 
 &mio_clk {
-	compatible = "socionext,uniphier-pro5-mio-clock";
+	compatible = "socionext,uniphier-pro5-sd-clock";
 };
 
 &mio_rst {
-	compatible = "socionext,uniphier-pro5-mio-reset";
+	compatible = "socionext,uniphier-pro5-sd-reset";
 };
 
 &peri_clk {
diff --git a/arch/arm/boot/dts/uniphier-pxs2.dtsi b/arch/arm/boot/dts/uniphier-pxs2.dtsi
index 8789cd5..950f07b 100644
--- a/arch/arm/boot/dts/uniphier-pxs2.dtsi
+++ b/arch/arm/boot/dts/uniphier-pxs2.dtsi
@@ -197,11 +197,11 @@
 };
 
 &mio_clk {
-	compatible = "socionext,uniphier-pxs2-mio-clock";
+	compatible = "socionext,uniphier-pxs2-sd-clock";
 };
 
 &mio_rst {
-	compatible = "socionext,uniphier-pxs2-mio-reset";
+	compatible = "socionext,uniphier-pxs2-sd-reset";
 };
 
 &peri_clk {
diff --git a/arch/arm/boot/dts/vf500.dtsi b/arch/arm/boot/dts/vf500.dtsi
index a3824e6..d7fdb2a 100644
--- a/arch/arm/boot/dts/vf500.dtsi
+++ b/arch/arm/boot/dts/vf500.dtsi
@@ -70,7 +70,7 @@
 			global_timer: timer@40002200 {
 				compatible = "arm,cortex-a9-global-timer";
 				reg = <0x40002200 0x20>;
-				interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 				interrupt-parent = <&intc>;
 				clocks = <&clks VF610_CLK_PLATFORM_BUS>;
 			};
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 437d074..11f37ed 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -850,6 +850,7 @@
 CONFIG_PWM_TEGRA=y
 CONFIG_PWM_VT8500=y
 CONFIG_PHY_HIX5HD2_SATA=y
+CONFIG_E1000E=y
 CONFIG_PWM_STI=y
 CONFIG_PWM_BCM2835=y
 CONFIG_PWM_BRCMSTB=m
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 194b699..ada0d29 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -19,7 +19,7 @@
  * This may need to be greater than __NR_last_syscall+1 in order to
  * account for the padding in the syscall table
  */
-#define __NR_syscalls  (396)
+#define __NR_syscalls  (400)
 
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 2cb9dc7..314100a 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -420,6 +420,9 @@
 #define __NR_copy_file_range		(__NR_SYSCALL_BASE+391)
 #define __NR_preadv2			(__NR_SYSCALL_BASE+392)
 #define __NR_pwritev2			(__NR_SYSCALL_BASE+393)
+#define __NR_pkey_mprotect		(__NR_SYSCALL_BASE+394)
+#define __NR_pkey_alloc			(__NR_SYSCALL_BASE+395)
+#define __NR_pkey_free			(__NR_SYSCALL_BASE+396)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 703fa0f..08030b1 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -403,6 +403,9 @@
 		CALL(sys_copy_file_range)
 		CALL(sys_preadv2)
 		CALL(sys_pwritev2)
+		CALL(sys_pkey_mprotect)
+/* 395 */	CALL(sys_pkey_alloc)
+		CALL(sys_pkey_free)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 0df062d..b54db47 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -408,7 +408,7 @@ static struct genpd_onecell_data imx_gpc_onecell_data = {
 static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
 {
 	struct clk *clk;
-	int i;
+	int i, ret;
 
 	imx6q_pu_domain.reg = pu_reg;
 
@@ -430,13 +430,22 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
 	if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS))
 		return 0;
 
-	pm_genpd_init(&imx6q_pu_domain.base, NULL, false);
-	return of_genpd_add_provider_onecell(dev->of_node,
-					     &imx_gpc_onecell_data);
+	for (i = 0; i < ARRAY_SIZE(imx_gpc_domains); i++)
+		pm_genpd_init(imx_gpc_domains[i], NULL, false);
 
+	ret =  of_genpd_add_provider_onecell(dev->of_node,
+					     &imx_gpc_onecell_data);
+	if (ret)
+		goto power_off;
+
+	return 0;
+
+power_off:
+	imx6q_pm_pu_power_off(&imx6q_pu_domain.base);
 clk_err:
 	while (i--)
 		clk_put(imx6q_pu_domain.clk[i]);
+	imx6q_pu_domain.reg = NULL;
 	return -EINVAL;
 }
 
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 97fd251..45801b2 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -173,7 +173,7 @@ static void __init imx6q_enet_phy_init(void)
 				ksz9021rn_phy_fixup);
 		phy_register_fixup_for_uid(PHY_ID_KSZ9031, MICREL_PHY_ID_MASK,
 				ksz9031rn_phy_fixup);
-		phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffff,
+		phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffef,
 				ar8031_phy_fixup);
 		phy_register_fixup_for_uid(PHY_ID_AR8035, 0xffffffef,
 				ar8035_phy_fixup);
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index f9b6bd3..541647f 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -23,6 +23,7 @@
 	select CACHE_L2X0
 	select ARM_CPU_SUSPEND
 	select MACH_MVEBU_ANY
+	select MVEBU_CLK_COREDIV
 
 config MACH_ARMADA_370
 	bool "Marvell Armada 370 boards"
@@ -32,7 +33,6 @@
 	select CPU_PJ4B
 	select MACH_MVEBU_V7
 	select PINCTRL_ARMADA_370
-	select MVEBU_CLK_COREDIV
 	help
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Armada 370 SoC with device tree.
@@ -50,7 +50,6 @@
 	select HAVE_SMP
 	select MACH_MVEBU_V7
 	select PINCTRL_ARMADA_375
-	select MVEBU_CLK_COREDIV
 	help
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Armada 375 SoC with device tree.
@@ -68,7 +67,6 @@
 	select HAVE_SMP
 	select MACH_MVEBU_V7
 	select PINCTRL_ARMADA_38X
-	select MVEBU_CLK_COREDIV
 	help
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Armada 380/385 SoC with device tree.
diff --git a/arch/arm/mach-uniphier/Kconfig b/arch/arm/mach-uniphier/Kconfig
index 82dddee..3930fbb 100644
--- a/arch/arm/mach-uniphier/Kconfig
+++ b/arch/arm/mach-uniphier/Kconfig
@@ -1,6 +1,7 @@
 config ARCH_UNIPHIER
 	bool "Socionext UniPhier SoCs"
 	depends on ARCH_MULTI_V7
+	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_AMBA
 	select ARM_GLOBAL_TIMER
 	select ARM_GIC
diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S
index 6d8e8e3..4cdfab3 100644
--- a/arch/arm/mm/abort-lv4t.S
+++ b/arch/arm/mm/abort-lv4t.S
@@ -7,7 +7,7 @@
  *	   : r4 = aborted context pc
  *	   : r5 = aborted context psr
  *
- * Returns : r4-r5, r10-r11, r13 preserved
+ * Returns : r4-r5, r9-r11, r13 preserved
  *
  * Purpose : obtain information about current aborted instruction.
  * Note: we read user space.  This means we might cause a data
@@ -48,7 +48,10 @@
 /* c */	b	do_DataAbort			@ ldc	rd, [rn], #m	@ Same as ldr	rd, [rn], #m
 /* d */	b	do_DataAbort			@ ldc	rd, [rn, #m]
 /* e */	b	.data_unknown
-/* f */
+/* f */	b	.data_unknown
+
+.data_unknown_r9:
+	ldr	r9, [sp], #4
 .data_unknown:	@ Part of jumptable
 	mov	r0, r4
 	mov	r1, r8
@@ -57,6 +60,7 @@
 .data_arm_ldmstm:
 	tst	r8, #1 << 21			@ check writeback bit
 	beq	do_DataAbort			@ no writeback -> no fixup
+	str	r9, [sp, #-4]!
 	mov	r7, #0x11
 	orr	r7, r7, #0x1100
 	and	r6, r8, r7
@@ -75,12 +79,14 @@
 	subne	r7, r7, r6, lsl #2		@ Undo increment
 	addeq	r7, r7, r6, lsl #2		@ Undo decrement
 	str	r7, [r2, r9, lsr #14]		@ Put register 'Rn'
+	ldr	r9, [sp], #4
 	b	do_DataAbort
 
 .data_arm_lateldrhpre:
 	tst	r8, #1 << 21			@ Check writeback bit
 	beq	do_DataAbort			@ No writeback -> no fixup
 .data_arm_lateldrhpost:
+	str	r9, [sp, #-4]!
 	and	r9, r8, #0x00f			@ get Rm / low nibble of immediate value
 	tst	r8, #1 << 22			@ if (immediate offset)
 	andne	r6, r8, #0xf00			@ { immediate high nibble
@@ -93,6 +99,7 @@
 	subne	r7, r7, r6			@ Undo incrmenet
 	addeq	r7, r7, r6			@ Undo decrement
 	str	r7, [r2, r9, lsr #14]		@ Put register 'Rn'
+	ldr	r9, [sp], #4
 	b	do_DataAbort
 
 .data_arm_lateldrpreconst:
@@ -101,12 +108,14 @@
 .data_arm_lateldrpostconst:
 	movs	r6, r8, lsl #20			@ Get offset
 	beq	do_DataAbort			@ zero -> no fixup
+	str	r9, [sp, #-4]!
 	and	r9, r8, #15 << 16		@ Extract 'n' from instruction
 	ldr	r7, [r2, r9, lsr #14]		@ Get register 'Rn'
 	tst	r8, #1 << 23			@ Check U bit
 	subne	r7, r7, r6, lsr #20		@ Undo increment
 	addeq	r7, r7, r6, lsr #20		@ Undo decrement
 	str	r7, [r2, r9, lsr #14]		@ Put register 'Rn'
+	ldr	r9, [sp], #4
 	b	do_DataAbort
 
 .data_arm_lateldrprereg:
@@ -115,6 +124,7 @@
 .data_arm_lateldrpostreg:
 	and	r7, r8, #15			@ Extract 'm' from instruction
 	ldr	r6, [r2, r7, lsl #2]		@ Get register 'Rm'
+	str	r9, [sp, #-4]!
 	mov	r9, r8, lsr #7			@ get shift count
 	ands	r9, r9, #31
 	and	r7, r8, #0x70			@ get shift type
@@ -126,33 +136,33 @@
 	b	.data_arm_apply_r6_and_rn
 	b	.data_arm_apply_r6_and_rn	@ 1: LSL #0
 	nop
-	b	.data_unknown			@ 2: MUL?
+	b	.data_unknown_r9		@ 2: MUL?
 	nop
-	b	.data_unknown			@ 3: MUL?
+	b	.data_unknown_r9		@ 3: MUL?
 	nop
 	mov	r6, r6, lsr r9			@ 4: LSR #!0
 	b	.data_arm_apply_r6_and_rn
 	mov	r6, r6, lsr #32			@ 5: LSR #32
 	b	.data_arm_apply_r6_and_rn
-	b	.data_unknown			@ 6: MUL?
+	b	.data_unknown_r9		@ 6: MUL?
 	nop
-	b	.data_unknown			@ 7: MUL?
+	b	.data_unknown_r9		@ 7: MUL?
 	nop
 	mov	r6, r6, asr r9			@ 8: ASR #!0
 	b	.data_arm_apply_r6_and_rn
 	mov	r6, r6, asr #32			@ 9: ASR #32
 	b	.data_arm_apply_r6_and_rn
-	b	.data_unknown			@ A: MUL?
+	b	.data_unknown_r9		@ A: MUL?
 	nop
-	b	.data_unknown			@ B: MUL?
+	b	.data_unknown_r9		@ B: MUL?
 	nop
 	mov	r6, r6, ror r9			@ C: ROR #!0
 	b	.data_arm_apply_r6_and_rn
 	mov	r6, r6, rrx			@ D: RRX
 	b	.data_arm_apply_r6_and_rn
-	b	.data_unknown			@ E: MUL?
+	b	.data_unknown_r9		@ E: MUL?
 	nop
-	b	.data_unknown			@ F: MUL?
+	b	.data_unknown_r9		@ F: MUL?
 
 .data_thumb_abort:
 	ldrh	r8, [r4]			@ read instruction
@@ -190,6 +200,7 @@
 .data_thumb_pushpop:
 	tst	r8, #1 << 10
 	beq	.data_unknown
+	str	r9, [sp, #-4]!
 	and	r6, r8, #0x55			@ hweight8(r8) + R bit
 	and	r9, r8, #0xaa
 	add	r6, r6, r9, lsr #1
@@ -204,9 +215,11 @@
 	addeq	r7, r7, r6, lsl #2		@ increment SP if PUSH
 	subne	r7, r7, r6, lsl #2		@ decrement SP if POP
 	str	r7, [r2, #13 << 2]
+	ldr	r9, [sp], #4
 	b	do_DataAbort
 
 .data_thumb_ldmstm:
+	str	r9, [sp, #-4]!
 	and	r6, r8, #0x55			@ hweight8(r8)
 	and	r9, r8, #0xaa
 	add	r6, r6, r9, lsr #1
@@ -219,4 +232,5 @@
 	and	r6, r6, #15			@ number of regs to transfer
 	sub	r7, r7, r6, lsl #2		@ always decrement
 	str	r7, [r2, r9, lsr #6]
+	ldr	r9, [sp], #4
 	b	do_DataAbort
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index cfbdf02..101794f 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -190,6 +190,7 @@
 
 config ARCH_UNIPHIER
 	bool "Socionext UniPhier SoC Family"
+	select ARCH_HAS_RESET_CONTROLLER
 	select PINCTRL
 	help
 	  This enables support for Socionext UniPhier SoC family.
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
index 2d7872a..b09f3bc 100644
--- a/arch/arm64/boot/dts/broadcom/ns2-svk.dts
+++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
@@ -164,6 +164,8 @@
 		nand-ecc-mode = "hw";
 		nand-ecc-strength = <8>;
 		nand-ecc-step-size = <512>;
+		nand-bus-width = <16>;
+		brcm,nand-oob-sector-size = <16>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 220ac70..97d331e 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -123,6 +123,7 @@
 			     <1 14 0xf08>, /* Physical Non-Secure PPI */
 			     <1 11 0xf08>, /* Virtual PPI */
 			     <1 10 0xf08>; /* Hypervisor PPI */
+		fsl,erratum-a008585;
 	};
 
 	pmu {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index 337da90..7f0dc13 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -195,6 +195,7 @@
 			     <1 14 4>, /* Physical Non-Secure PPI, active-low */
 			     <1 11 4>, /* Virtual PPI, active-low */
 			     <1 10 4>; /* Hypervisor PPI, active-low */
+		fsl,erratum-a008585;
 	};
 
 	pmu {
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index e5e3ed6..602e2c2 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -131,7 +131,7 @@
 				#address-cells = <0x1>;
 				#size-cells = <0x0>;
 				cell-index = <1>;
-				clocks = <&cpm_syscon0 0 3>;
+				clocks = <&cpm_syscon0 1 21>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts b/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
index 46cdddf..e5eeca2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
@@ -116,7 +116,6 @@
 	cap-mmc-highspeed;
 	clock-frequency = <150000000>;
 	disable-wp;
-	keep-power-in-suspend;
 	non-removable;
 	num-slots = <1>;
 	vmmc-supply = <&vcc_io>;
@@ -258,8 +257,6 @@
 			};
 
 			vcc_sd: SWITCH_REG1 {
-				regulator-always-on;
-				regulator-boot-on;
 				regulator-name = "vcc_sd";
 			};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
index 5797933..ea0a8ec 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
@@ -152,8 +152,6 @@
 		gpio = <&gpio3 11 GPIO_ACTIVE_LOW>;
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <3300000>;
-		regulator-always-on;
-		regulator-boot-on;
 		vin-supply = <&vcc_io>;
 	};
 
@@ -201,7 +199,6 @@
 	bus-width = <8>;
 	cap-mmc-highspeed;
 	disable-wp;
-	keep-power-in-suspend;
 	mmc-pwrseq = <&emmc_pwrseq>;
 	mmc-hs200-1_2v;
 	mmc-hs200-1_8v;
@@ -350,7 +347,6 @@
 	clock-freq-min-max = <400000 50000000>;
 	cap-sd-highspeed;
 	card-detect-delay = <200>;
-	keep-power-in-suspend;
 	num-slots = <1>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>;
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
index 08fd7cf..56a1b2e 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
@@ -257,18 +257,18 @@
 			reg = <0x59801000 0x400>;
 		};
 
-		mioctrl@59810000 {
-			compatible = "socionext,uniphier-mioctrl",
+		sdctrl@59810000 {
+			compatible = "socionext,uniphier-ld20-sdctrl",
 				     "simple-mfd", "syscon";
 			reg = <0x59810000 0x800>;
 
-			mio_clk: clock {
-				compatible = "socionext,uniphier-ld20-mio-clock";
+			sd_clk: clock {
+				compatible = "socionext,uniphier-ld20-sd-clock";
 				#clock-cells = <1>;
 			};
 
-			mio_rst: reset {
-				compatible = "socionext,uniphier-ld20-mio-reset";
+			sd_rst: reset {
+				compatible = "socionext,uniphier-ld20-sd-reset";
 				#reset-cells = <1>;
 			};
 		};
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 39feb85..6e1cb8c 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_ALTERNATIVE_H
 #define __ASM_ALTERNATIVE_H
 
-#include <asm/cpufeature.h>
+#include <asm/cpucaps.h>
 #include <asm/insn.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
new file mode 100644
index 0000000..87b4465
--- /dev/null
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -0,0 +1,40 @@
+/*
+ * arch/arm64/include/asm/cpucaps.h
+ *
+ * Copyright (C) 2016 ARM Ltd.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_CPUCAPS_H
+#define __ASM_CPUCAPS_H
+
+#define ARM64_WORKAROUND_CLEAN_CACHE		0
+#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
+#define ARM64_WORKAROUND_845719			2
+#define ARM64_HAS_SYSREG_GIC_CPUIF		3
+#define ARM64_HAS_PAN				4
+#define ARM64_HAS_LSE_ATOMICS			5
+#define ARM64_WORKAROUND_CAVIUM_23154		6
+#define ARM64_WORKAROUND_834220			7
+#define ARM64_HAS_NO_HW_PREFETCH		8
+#define ARM64_HAS_UAO				9
+#define ARM64_ALT_PAN_NOT_UAO			10
+#define ARM64_HAS_VIRT_HOST_EXTN		11
+#define ARM64_WORKAROUND_CAVIUM_27456		12
+#define ARM64_HAS_32BIT_EL0			13
+#define ARM64_HYP_OFFSET_LOW			14
+#define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
+
+#define ARM64_NCAPS				16
+
+#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index a27c324..0bc0b1d 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -11,6 +11,7 @@
 
 #include <linux/jump_label.h>
 
+#include <asm/cpucaps.h>
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
@@ -24,25 +25,6 @@
 #define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
 #define cpu_feature(x)		ilog2(HWCAP_ ## x)
 
-#define ARM64_WORKAROUND_CLEAN_CACHE		0
-#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
-#define ARM64_WORKAROUND_845719			2
-#define ARM64_HAS_SYSREG_GIC_CPUIF		3
-#define ARM64_HAS_PAN				4
-#define ARM64_HAS_LSE_ATOMICS			5
-#define ARM64_WORKAROUND_CAVIUM_23154		6
-#define ARM64_WORKAROUND_834220			7
-#define ARM64_HAS_NO_HW_PREFETCH		8
-#define ARM64_HAS_UAO				9
-#define ARM64_ALT_PAN_NOT_UAO			10
-#define ARM64_HAS_VIRT_HOST_EXTN		11
-#define ARM64_WORKAROUND_CAVIUM_27456		12
-#define ARM64_HAS_32BIT_EL0			13
-#define ARM64_HYP_OFFSET_LOW			14
-#define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
-
-#define ARM64_NCAPS				16
-
 #ifndef __ASSEMBLY__
 
 #include <linux/kernel.h>
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
index 23acc00..fc756e2 100644
--- a/arch/arm64/include/asm/lse.h
+++ b/arch/arm64/include/asm/lse.h
@@ -5,7 +5,6 @@
 
 #include <linux/stringify.h>
 #include <asm/alternative.h>
-#include <asm/cpufeature.h>
 
 #ifdef __ASSEMBLER__
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ba62df8..b71086d 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -217,7 +217,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
 #define __virt_to_pgoff(kaddr)	(((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
-#define __page_to_voff(kaddr)	(((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
+#define __page_to_voff(page)	(((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
 
 #define page_to_virt(page)	((void *)((__page_to_voff(page)) | PAGE_OFFSET))
 #define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 778a985..4b32168 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -147,7 +147,7 @@ static int __init early_cpu_to_node(int cpu)
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	return node_distance(from, to);
+	return node_distance(early_cpu_to_node(from), early_cpu_to_node(to));
 }
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
@@ -223,8 +223,11 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	void *nd;
 	int tnid;
 
-	pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
-		nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
+	if (start_pfn < end_pfn)
+		pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
+			start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
+	else
+		pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
 
 	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
 	nd = __va(nd_pa);
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index 099e170..0068fd4 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -3149,7 +3149,7 @@ static void print_dma_descriptors(struct cryptocop_int_operation *iop)
 	printk("print_dma_descriptors start\n");
 
 	printk("iop:\n");
-	printk("\tsid: 0x%lld\n", iop->sid);
+	printk("\tsid: 0x%llx\n", iop->sid);
 
 	printk("\tcdesc_out: 0x%p\n", iop->cdesc_out);
 	printk("\tcdesc_in: 0x%p\n", iop->cdesc_in);
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
index b408fe6..3cef068 100644
--- a/arch/h8300/include/asm/thread_info.h
+++ b/arch/h8300/include/asm/thread_info.h
@@ -31,7 +31,6 @@ struct thread_info {
 	int		   cpu;			/* cpu we're on */
 	int		   preempt_count;	/* 0 => preemptable, <0 => BUG */
 	mm_segment_t		addr_limit;
-	struct restart_block restart_block;
 };
 
 /*
@@ -44,9 +43,6 @@ struct thread_info {
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
index ad1f81f..7138303 100644
--- a/arch/h8300/kernel/signal.c
+++ b/arch/h8300/kernel/signal.c
@@ -79,7 +79,7 @@ restore_sigcontext(struct sigcontext *usc, int *pd0)
 	unsigned int er0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore passed registers */
 #define COPY(r)  do { err |= get_user(regs->r, &usc->sc_##r); } while (0)
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index fbf40d3..1a6bac7 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -263,7 +263,7 @@
 
 bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y) \
 		  VMLINUX_ENTRY_ADDRESS=$(entry-y) \
-		  PLATFORM=$(platform-y)
+		  PLATFORM="$(platform-y)"
 ifdef CONFIG_32BIT
 bootvars-y	+= ADDR_BITS=32
 endif
diff --git a/arch/mips/boot/dts/mti/malta.dts b/arch/mips/boot/dts/mti/malta.dts
index f604a27..ffe3a15 100644
--- a/arch/mips/boot/dts/mti/malta.dts
+++ b/arch/mips/boot/dts/mti/malta.dts
@@ -84,12 +84,13 @@
 	fpga_regs: system-controller@1f000000 {
 		compatible = "mti,malta-fpga", "syscon", "simple-mfd";
 		reg = <0x1f000000 0x1000>;
+		native-endian;
 
 		reboot {
 			compatible = "syscon-reboot";
 			regmap = <&fpga_regs>;
 			offset = <0x500>;
-			mask = <0x4d>;
+			mask = <0x42>;
 		};
 	};
 
diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c
index 0ea73e8..d493ccb 100644
--- a/arch/mips/generic/init.c
+++ b/arch/mips/generic/init.c
@@ -30,9 +30,19 @@ static __initdata const void *mach_match_data;
 
 void __init prom_init(void)
 {
+	plat_get_fdt();
+	BUG_ON(!fdt);
+}
+
+void __init *plat_get_fdt(void)
+{
 	const struct mips_machine *check_mach;
 	const struct of_device_id *match;
 
+	if (fdt)
+		/* Already set up */
+		return (void *)fdt;
+
 	if ((fw_arg0 == -2) && !fdt_check_header((void *)fw_arg1)) {
 		/*
 		 * We booted using the UHI boot protocol, so we have been
@@ -75,12 +85,6 @@ void __init prom_init(void)
 		/* Retrieve the machine's FDT */
 		fdt = mach->fdt;
 	}
-
-	BUG_ON(!fdt);
-}
-
-void __init *plat_get_fdt(void)
-{
 	return (void *)fdt;
 }
 
diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h
index 355dc25..c05369e 100644
--- a/arch/mips/include/asm/fpu_emulator.h
+++ b/arch/mips/include/asm/fpu_emulator.h
@@ -63,6 +63,8 @@ do {									\
 extern int fpu_emulator_cop1Handler(struct pt_regs *xcp,
 				    struct mips_fpu_struct *ctx, int has_fpu,
 				    void *__user *fault_addr);
+void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
+		     struct task_struct *tsk);
 int process_fpemu_return(int sig, void __user *fault_addr,
 			 unsigned long fcr31);
 int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
@@ -81,4 +83,15 @@ static inline void fpu_emulator_init_fpu(void)
 		set_fpr64(&t->thread.fpu.fpr[i], 0, SIGNALLING_NAN);
 }
 
+/*
+ * Mask the FCSR Cause bits according to the Enable bits, observing
+ * that Unimplemented is always enabled.
+ */
+static inline unsigned long mask_fcr31_x(unsigned long fcr31)
+{
+	return fcr31 & (FPU_CSR_UNI_X |
+			((fcr31 & FPU_CSR_ALL_E) <<
+			 (ffs(FPU_CSR_ALL_X) - ffs(FPU_CSR_ALL_E))));
+}
+
 #endif /* _ASM_FPU_EMULATOR_H */
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 07f58cf..bebec37 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -293,7 +293,10 @@ struct kvm_vcpu_arch {
 	/* Host KSEG0 address of the EI/DI offset */
 	void *kseg0_commpage;
 
-	u32 io_gpr;		/* GPR used as IO source/target */
+	/* Resume PC after MMIO completion */
+	unsigned long io_pc;
+	/* GPR used as IO source/target */
+	u32 io_gpr;
 
 	struct hrtimer comparecount_timer;
 	/* Count timer control KVM register */
@@ -315,8 +318,6 @@ struct kvm_vcpu_arch {
 	/* Bitmask of pending exceptions to be cleared */
 	unsigned long pending_exceptions_clr;
 
-	u32 pending_load_cause;
-
 	/* Save/Restore the entryhi register when are are preempted/scheduled back in */
 	unsigned long preempt_entryhi;
 
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index ebb5c0f..c0ae279 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -76,6 +76,22 @@ do {	if (cpu_has_rw_llb) {						\
 } while (0)
 
 /*
+ * Check FCSR for any unmasked exceptions pending set with `ptrace',
+ * clear them and send a signal.
+ */
+#define __sanitize_fcr31(next)						\
+do {									\
+	unsigned long fcr31 = mask_fcr31_x(next->thread.fpu.fcr31);	\
+	void __user *pc;						\
+									\
+	if (unlikely(fcr31)) {						\
+		pc = (void __user *)task_pt_regs(next)->cp0_epc;	\
+		next->thread.fpu.fcr31 &= ~fcr31;			\
+		force_fcr31_sig(fcr31, pc, next);			\
+	}								\
+} while (0)
+
+/*
  * For newly created kernel threads switch_to() will return to
  * ret_from_kernel_thread, newly created user threads to ret_from_fork.
  * That is, everything following resume() will be skipped for new threads.
@@ -85,6 +101,8 @@ do {	if (cpu_has_rw_llb) {						\
 do {									\
 	__mips_mt_fpaff_switch_to(prev);				\
 	lose_fpu_inatomic(1, prev);					\
+	if (tsk_used_math(next))					\
+		__sanitize_fcr31(next);					\
 	if (cpu_has_dsp) {						\
 		__save_dsp(prev);					\
 		__restore_dsp(next);					\
diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c
index 2a45867..a4964c3 100644
--- a/arch/mips/kernel/mips-cpc.c
+++ b/arch/mips/kernel/mips-cpc.c
@@ -21,6 +21,11 @@ static DEFINE_PER_CPU_ALIGNED(spinlock_t, cpc_core_lock);
 
 static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags);
 
+phys_addr_t __weak mips_cpc_default_phys_base(void)
+{
+	return 0;
+}
+
 /**
  * mips_cpc_phys_base - retrieve the physical base address of the CPC
  *
@@ -43,8 +48,12 @@ static phys_addr_t mips_cpc_phys_base(void)
 	if (cpc_base & CM_GCR_CPC_BASE_CPCEN_MSK)
 		return cpc_base & CM_GCR_CPC_BASE_CPCBASE_MSK;
 
-	/* Otherwise, give it the default address & enable it */
+	/* Otherwise, use the default address */
 	cpc_base = mips_cpc_default_phys_base();
+	if (!cpc_base)
+		return cpc_base;
+
+	/* Enable the CPC, mapped at the default address */
 	write_gcr_cpc_base(cpc_base | CM_GCR_CPC_BASE_CPCEN_MSK);
 	return cpc_base;
 }
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index 22dedd6..bd09853 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -899,7 +899,7 @@ static inline int mipsr2_find_op_func(struct pt_regs *regs, u32 inst,
  * mipsr2_decoder: Decode and emulate a MIPS R2 instruction
  * @regs: Process register set
  * @inst: Instruction to decode and emulate
- * @fcr31: Floating Point Control and Status Register returned
+ * @fcr31: Floating Point Control and Status Register Cause bits returned
  */
 int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 {
@@ -1172,13 +1172,13 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 
 		err = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 0,
 					       &fault_addr);
-		*fcr31 = current->thread.fpu.fcr31;
 
 		/*
-		 * We can't allow the emulated instruction to leave any of
-		 * the cause bits set in $fcr31.
+		 * We can't allow the emulated instruction to leave any
+		 * enabled Cause bits set in $fcr31.
 		 */
-		current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
+		*fcr31 = res = mask_fcr31_x(current->thread.fpu.fcr31);
+		current->thread.fpu.fcr31 &= ~res;
 
 		/*
 		 * this is a tricky issue - lose_fpu() uses LL/SC atomics
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 6103b24..a92994d 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -79,16 +79,15 @@ void ptrace_disable(struct task_struct *child)
 }
 
 /*
- * Poke at FCSR according to its mask.  Don't set the cause bits as
- * this is currently not handled correctly in FP context restoration
- * and will cause an oops if a corresponding enable bit is set.
+ * Poke at FCSR according to its mask.  Set the Cause bits even
+ * if a corresponding Enable bit is set.  This will be noticed at
+ * the time the thread is switched to and SIGFPE thrown accordingly.
  */
 static void ptrace_setfcr31(struct task_struct *child, u32 value)
 {
 	u32 fcr31;
 	u32 mask;
 
-	value &= ~FPU_CSR_ALL_X;
 	fcr31 = child->thread.fpu.fcr31;
 	mask = boot_cpu_data.fpu_msk31;
 	child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
@@ -817,6 +816,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			break;
 #endif
 		case FPC_CSR:
+			init_fp_ctx(child);
 			ptrace_setfcr31(child, data);
 			break;
 		case DSP_BASE ... DSP_BASE + 5: {
diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S
index b4ac637..918f2f6 100644
--- a/arch/mips/kernel/r2300_fpu.S
+++ b/arch/mips/kernel/r2300_fpu.S
@@ -21,106 +21,84 @@
 #define EX(a,b)							\
 9:	a,##b;							\
 	.section __ex_table,"a";				\
+	PTR	9b,fault;					\
+	.previous
+
+#define EX2(a,b)						\
+9:	a,##b;							\
+	.section __ex_table,"a";				\
 	PTR	9b,bad_stack;					\
+	PTR	9b+4,bad_stack;					\
 	.previous
 
 	.set	noreorder
 	.set	mips1
-	/* Save floating point context */
+
+/**
+ * _save_fp_context() - save FP context from the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
+ *
+ * Save FP context, including the 32 FP data registers and the FP
+ * control & status register, from the FPU to signal context.
+ */
 LEAF(_save_fp_context)
 	.set	push
 	SET_HARDFLOAT
 	li	v0, 0					# assume success
-	cfc1	t1,fcr31
-	EX(swc1 $f0,(SC_FPREGS+0)(a0))
-	EX(swc1 $f1,(SC_FPREGS+8)(a0))
-	EX(swc1 $f2,(SC_FPREGS+16)(a0))
-	EX(swc1 $f3,(SC_FPREGS+24)(a0))
-	EX(swc1 $f4,(SC_FPREGS+32)(a0))
-	EX(swc1 $f5,(SC_FPREGS+40)(a0))
-	EX(swc1 $f6,(SC_FPREGS+48)(a0))
-	EX(swc1 $f7,(SC_FPREGS+56)(a0))
-	EX(swc1 $f8,(SC_FPREGS+64)(a0))
-	EX(swc1 $f9,(SC_FPREGS+72)(a0))
-	EX(swc1 $f10,(SC_FPREGS+80)(a0))
-	EX(swc1 $f11,(SC_FPREGS+88)(a0))
-	EX(swc1 $f12,(SC_FPREGS+96)(a0))
-	EX(swc1 $f13,(SC_FPREGS+104)(a0))
-	EX(swc1 $f14,(SC_FPREGS+112)(a0))
-	EX(swc1 $f15,(SC_FPREGS+120)(a0))
-	EX(swc1 $f16,(SC_FPREGS+128)(a0))
-	EX(swc1 $f17,(SC_FPREGS+136)(a0))
-	EX(swc1 $f18,(SC_FPREGS+144)(a0))
-	EX(swc1 $f19,(SC_FPREGS+152)(a0))
-	EX(swc1 $f20,(SC_FPREGS+160)(a0))
-	EX(swc1 $f21,(SC_FPREGS+168)(a0))
-	EX(swc1 $f22,(SC_FPREGS+176)(a0))
-	EX(swc1 $f23,(SC_FPREGS+184)(a0))
-	EX(swc1 $f24,(SC_FPREGS+192)(a0))
-	EX(swc1 $f25,(SC_FPREGS+200)(a0))
-	EX(swc1 $f26,(SC_FPREGS+208)(a0))
-	EX(swc1 $f27,(SC_FPREGS+216)(a0))
-	EX(swc1 $f28,(SC_FPREGS+224)(a0))
-	EX(swc1 $f29,(SC_FPREGS+232)(a0))
-	EX(swc1 $f30,(SC_FPREGS+240)(a0))
-	EX(swc1 $f31,(SC_FPREGS+248)(a0))
-	EX(sw	t1,(SC_FPC_CSR)(a0))
-	cfc1	t0,$0				# implementation/version
+	cfc1	t1, fcr31
+	EX2(s.d $f0, 0(a0))
+	EX2(s.d $f2, 16(a0))
+	EX2(s.d $f4, 32(a0))
+	EX2(s.d $f6, 48(a0))
+	EX2(s.d $f8, 64(a0))
+	EX2(s.d $f10, 80(a0))
+	EX2(s.d $f12, 96(a0))
+	EX2(s.d $f14, 112(a0))
+	EX2(s.d $f16, 128(a0))
+	EX2(s.d $f18, 144(a0))
+	EX2(s.d $f20, 160(a0))
+	EX2(s.d $f22, 176(a0))
+	EX2(s.d $f24, 192(a0))
+	EX2(s.d $f26, 208(a0))
+	EX2(s.d $f28, 224(a0))
+	EX2(s.d $f30, 240(a0))
 	jr	ra
+	 EX(sw	t1, (a1))
 	.set	pop
-	.set	nomacro
-	 EX(sw	t0,(SC_FPC_EIR)(a0))
-	.set	macro
 	END(_save_fp_context)
 
-/*
- * Restore FPU state:
- *  - fp gp registers
- *  - cp1 status/control register
+/**
+ * _restore_fp_context() - restore FP context to the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
  *
- * We base the decision which registers to restore from the signal stack
- * frame on the current content of c0_status, not on the content of the
- * stack frame which might have been changed by the user.
+ * Restore FP context, including the 32 FP data registers and the FP
+ * control & status register, from signal context to the FPU.
  */
 LEAF(_restore_fp_context)
 	.set	push
 	SET_HARDFLOAT
 	li	v0, 0					# assume success
-	EX(lw t0,(SC_FPC_CSR)(a0))
-	EX(lwc1 $f0,(SC_FPREGS+0)(a0))
-	EX(lwc1 $f1,(SC_FPREGS+8)(a0))
-	EX(lwc1 $f2,(SC_FPREGS+16)(a0))
-	EX(lwc1 $f3,(SC_FPREGS+24)(a0))
-	EX(lwc1 $f4,(SC_FPREGS+32)(a0))
-	EX(lwc1 $f5,(SC_FPREGS+40)(a0))
-	EX(lwc1 $f6,(SC_FPREGS+48)(a0))
-	EX(lwc1 $f7,(SC_FPREGS+56)(a0))
-	EX(lwc1 $f8,(SC_FPREGS+64)(a0))
-	EX(lwc1 $f9,(SC_FPREGS+72)(a0))
-	EX(lwc1 $f10,(SC_FPREGS+80)(a0))
-	EX(lwc1 $f11,(SC_FPREGS+88)(a0))
-	EX(lwc1 $f12,(SC_FPREGS+96)(a0))
-	EX(lwc1 $f13,(SC_FPREGS+104)(a0))
-	EX(lwc1 $f14,(SC_FPREGS+112)(a0))
-	EX(lwc1 $f15,(SC_FPREGS+120)(a0))
-	EX(lwc1 $f16,(SC_FPREGS+128)(a0))
-	EX(lwc1 $f17,(SC_FPREGS+136)(a0))
-	EX(lwc1 $f18,(SC_FPREGS+144)(a0))
-	EX(lwc1 $f19,(SC_FPREGS+152)(a0))
-	EX(lwc1 $f20,(SC_FPREGS+160)(a0))
-	EX(lwc1 $f21,(SC_FPREGS+168)(a0))
-	EX(lwc1 $f22,(SC_FPREGS+176)(a0))
-	EX(lwc1 $f23,(SC_FPREGS+184)(a0))
-	EX(lwc1 $f24,(SC_FPREGS+192)(a0))
-	EX(lwc1 $f25,(SC_FPREGS+200)(a0))
-	EX(lwc1 $f26,(SC_FPREGS+208)(a0))
-	EX(lwc1 $f27,(SC_FPREGS+216)(a0))
-	EX(lwc1 $f28,(SC_FPREGS+224)(a0))
-	EX(lwc1 $f29,(SC_FPREGS+232)(a0))
-	EX(lwc1 $f30,(SC_FPREGS+240)(a0))
-	EX(lwc1 $f31,(SC_FPREGS+248)(a0))
+	EX(lw t0, (a1))
+	EX2(l.d $f0, 0(a0))
+	EX2(l.d $f2, 16(a0))
+	EX2(l.d $f4, 32(a0))
+	EX2(l.d $f6, 48(a0))
+	EX2(l.d $f8, 64(a0))
+	EX2(l.d $f10, 80(a0))
+	EX2(l.d $f12, 96(a0))
+	EX2(l.d $f14, 112(a0))
+	EX2(l.d $f16, 128(a0))
+	EX2(l.d $f18, 144(a0))
+	EX2(l.d $f20, 160(a0))
+	EX2(l.d $f22, 176(a0))
+	EX2(l.d $f24, 192(a0))
+	EX2(l.d $f26, 208(a0))
+	EX2(l.d $f28, 224(a0))
+	EX2(l.d $f30, 240(a0))
 	jr	ra
-	 ctc1	t0,fcr31
+	 ctc1	t0, fcr31
 	.set	pop
 	END(_restore_fp_context)
 	.set	reorder
diff --git a/arch/mips/kernel/r6000_fpu.S b/arch/mips/kernel/r6000_fpu.S
index 4707738..9cc7bfa 100644
--- a/arch/mips/kernel/r6000_fpu.S
+++ b/arch/mips/kernel/r6000_fpu.S
@@ -21,7 +21,14 @@
 	.set	push
 	SET_HARDFLOAT
 
-	/* Save floating point context */
+/**
+ * _save_fp_context() - save FP context from the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
+ *
+ * Save FP context, including the 32 FP data registers and the FP
+ * control & status register, from the FPU to signal context.
+ */
 	LEAF(_save_fp_context)
 	mfc0	t0,CP0_STATUS
 	sll	t0,t0,2
@@ -30,59 +37,59 @@
 
 	cfc1	t1,fcr31
 	/* Store the 16 double precision registers */
-	sdc1	$f0,(SC_FPREGS+0)(a0)
-	sdc1	$f2,(SC_FPREGS+16)(a0)
-	sdc1	$f4,(SC_FPREGS+32)(a0)
-	sdc1	$f6,(SC_FPREGS+48)(a0)
-	sdc1	$f8,(SC_FPREGS+64)(a0)
-	sdc1	$f10,(SC_FPREGS+80)(a0)
-	sdc1	$f12,(SC_FPREGS+96)(a0)
-	sdc1	$f14,(SC_FPREGS+112)(a0)
-	sdc1	$f16,(SC_FPREGS+128)(a0)
-	sdc1	$f18,(SC_FPREGS+144)(a0)
-	sdc1	$f20,(SC_FPREGS+160)(a0)
-	sdc1	$f22,(SC_FPREGS+176)(a0)
-	sdc1	$f24,(SC_FPREGS+192)(a0)
-	sdc1	$f26,(SC_FPREGS+208)(a0)
-	sdc1	$f28,(SC_FPREGS+224)(a0)
-	sdc1	$f30,(SC_FPREGS+240)(a0)
+	sdc1	$f0,0(a0)
+	sdc1	$f2,16(a0)
+	sdc1	$f4,32(a0)
+	sdc1	$f6,48(a0)
+	sdc1	$f8,64(a0)
+	sdc1	$f10,80(a0)
+	sdc1	$f12,96(a0)
+	sdc1	$f14,112(a0)
+	sdc1	$f16,128(a0)
+	sdc1	$f18,144(a0)
+	sdc1	$f20,160(a0)
+	sdc1	$f22,176(a0)
+	sdc1	$f24,192(a0)
+	sdc1	$f26,208(a0)
+	sdc1	$f28,224(a0)
+	sdc1	$f30,240(a0)
 	jr	ra
-	 sw	t0,SC_FPC_CSR(a0)
+	 sw	t0,(a1)
 1:	jr	ra
 	 nop
 	END(_save_fp_context)
 
-/* Restore FPU state:
- *  - fp gp registers
- *  - cp1 status/control register
+/**
+ * _restore_fp_context() - restore FP context to the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
  *
- * We base the decision which registers to restore from the signal stack
- * frame on the current content of c0_status, not on the content of the
- * stack frame which might have been changed by the user.
+ * Restore FP context, including the 32 FP data registers and the FP
+ * control & status register, from signal context to the FPU.
  */
 	LEAF(_restore_fp_context)
 	mfc0	t0,CP0_STATUS
 	sll	t0,t0,2
 
 	bgez	t0,1f
-	 lw	t0,SC_FPC_CSR(a0)
+	 lw	t0,(a1)
 	/* Restore the 16 double precision registers */
-	ldc1	$f0,(SC_FPREGS+0)(a0)
-	ldc1	$f2,(SC_FPREGS+16)(a0)
-	ldc1	$f4,(SC_FPREGS+32)(a0)
-	ldc1	$f6,(SC_FPREGS+48)(a0)
-	ldc1	$f8,(SC_FPREGS+64)(a0)
-	ldc1	$f10,(SC_FPREGS+80)(a0)
-	ldc1	$f12,(SC_FPREGS+96)(a0)
-	ldc1	$f14,(SC_FPREGS+112)(a0)
-	ldc1	$f16,(SC_FPREGS+128)(a0)
-	ldc1	$f18,(SC_FPREGS+144)(a0)
-	ldc1	$f20,(SC_FPREGS+160)(a0)
-	ldc1	$f22,(SC_FPREGS+176)(a0)
-	ldc1	$f24,(SC_FPREGS+192)(a0)
-	ldc1	$f26,(SC_FPREGS+208)(a0)
-	ldc1	$f28,(SC_FPREGS+224)(a0)
-	ldc1	$f30,(SC_FPREGS+240)(a0)
+	ldc1	$f0,0(a0)
+	ldc1	$f2,16(a0)
+	ldc1	$f4,32(a0)
+	ldc1	$f6,48(a0)
+	ldc1	$f8,64(a0)
+	ldc1	$f10,80(a0)
+	ldc1	$f12,96(a0)
+	ldc1	$f14,112(a0)
+	ldc1	$f16,128(a0)
+	ldc1	$f18,144(a0)
+	ldc1	$f20,160(a0)
+	ldc1	$f22,176(a0)
+	ldc1	$f24,192(a0)
+	ldc1	$f26,208(a0)
+	ldc1	$f28,224(a0)
+	ldc1	$f30,240(a0)
 	jr	ra
 	 ctc1	t0,fcr31
 1:	jr	ra
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index ca1cc30..1958910 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -200,7 +200,7 @@ static inline __init unsigned long get_random_boot(void)
 
 #if defined(CONFIG_USE_OF)
 	/* Get any additional entropy passed in device tree */
-	{
+	if (initial_boot_params) {
 		int node, len;
 		u64 *prop;
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 0d57909..f66e5ce 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -368,6 +368,19 @@ static void __init bootmem_init(void)
 		end = PFN_DOWN(boot_mem_map.map[i].addr
 				+ boot_mem_map.map[i].size);
 
+#ifndef CONFIG_HIGHMEM
+		/*
+		 * Skip highmem here so we get an accurate max_low_pfn if low
+		 * memory stops short of high memory.
+		 * If the region overlaps HIGHMEM_START, end is clipped so
+		 * max_pfn excludes the highmem portion.
+		 */
+		if (start >= PFN_DOWN(HIGHMEM_START))
+			continue;
+		if (end > PFN_DOWN(HIGHMEM_START))
+			end = PFN_DOWN(HIGHMEM_START);
+#endif
+
 		if (end > max_low_pfn)
 			max_low_pfn = end;
 		if (start < min_low_pfn)
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 1f5fdee..3905003 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -156,7 +156,7 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs)
 		print_ip_sym(pc);
 		pc = unwind_stack(task, &sp, pc, &ra);
 	} while (pc);
-	printk("\n");
+	pr_cont("\n");
 }
 
 /*
@@ -174,22 +174,24 @@ static void show_stacktrace(struct task_struct *task,
 	printk("Stack :");
 	i = 0;
 	while ((unsigned long) sp & (PAGE_SIZE - 1)) {
-		if (i && ((i % (64 / field)) == 0))
-			printk("\n	 ");
+		if (i && ((i % (64 / field)) == 0)) {
+			pr_cont("\n");
+			printk("       ");
+		}
 		if (i > 39) {
-			printk(" ...");
+			pr_cont(" ...");
 			break;
 		}
 
 		if (__get_user(stackdata, sp++)) {
-			printk(" (Bad stack address)");
+			pr_cont(" (Bad stack address)");
 			break;
 		}
 
-		printk(" %0*lx", field, stackdata);
+		pr_cont(" %0*lx", field, stackdata);
 		i++;
 	}
-	printk("\n");
+	pr_cont("\n");
 	show_backtrace(task, regs);
 }
 
@@ -229,18 +231,19 @@ static void show_code(unsigned int __user *pc)
 	long i;
 	unsigned short __user *pc16 = NULL;
 
-	printk("\nCode:");
+	printk("Code:");
 
 	if ((unsigned long)pc & 1)
 		pc16 = (unsigned short __user *)((unsigned long)pc & ~1);
 	for(i = -3 ; i < 6 ; i++) {
 		unsigned int insn;
 		if (pc16 ? __get_user(insn, pc16 + i) : __get_user(insn, pc + i)) {
-			printk(" (Bad address in epc)\n");
+			pr_cont(" (Bad address in epc)\n");
 			break;
 		}
-		printk("%c%0*x%c", (i?' ':'<'), pc16 ? 4 : 8, insn, (i?' ':'>'));
+		pr_cont("%c%0*x%c", (i?' ':'<'), pc16 ? 4 : 8, insn, (i?' ':'>'));
 	}
+	pr_cont("\n");
 }
 
 static void __show_regs(const struct pt_regs *regs)
@@ -259,15 +262,15 @@ static void __show_regs(const struct pt_regs *regs)
 		if ((i % 4) == 0)
 			printk("$%2d   :", i);
 		if (i == 0)
-			printk(" %0*lx", field, 0UL);
+			pr_cont(" %0*lx", field, 0UL);
 		else if (i == 26 || i == 27)
-			printk(" %*s", field, "");
+			pr_cont(" %*s", field, "");
 		else
-			printk(" %0*lx", field, regs->regs[i]);
+			pr_cont(" %0*lx", field, regs->regs[i]);
 
 		i++;
 		if ((i % 4) == 0)
-			printk("\n");
+			pr_cont("\n");
 	}
 
 #ifdef CONFIG_CPU_HAS_SMARTMIPS
@@ -288,46 +291,46 @@ static void __show_regs(const struct pt_regs *regs)
 
 	if (cpu_has_3kex) {
 		if (regs->cp0_status & ST0_KUO)
-			printk("KUo ");
+			pr_cont("KUo ");
 		if (regs->cp0_status & ST0_IEO)
-			printk("IEo ");
+			pr_cont("IEo ");
 		if (regs->cp0_status & ST0_KUP)
-			printk("KUp ");
+			pr_cont("KUp ");
 		if (regs->cp0_status & ST0_IEP)
-			printk("IEp ");
+			pr_cont("IEp ");
 		if (regs->cp0_status & ST0_KUC)
-			printk("KUc ");
+			pr_cont("KUc ");
 		if (regs->cp0_status & ST0_IEC)
-			printk("IEc ");
+			pr_cont("IEc ");
 	} else if (cpu_has_4kex) {
 		if (regs->cp0_status & ST0_KX)
-			printk("KX ");
+			pr_cont("KX ");
 		if (regs->cp0_status & ST0_SX)
-			printk("SX ");
+			pr_cont("SX ");
 		if (regs->cp0_status & ST0_UX)
-			printk("UX ");
+			pr_cont("UX ");
 		switch (regs->cp0_status & ST0_KSU) {
 		case KSU_USER:
-			printk("USER ");
+			pr_cont("USER ");
 			break;
 		case KSU_SUPERVISOR:
-			printk("SUPERVISOR ");
+			pr_cont("SUPERVISOR ");
 			break;
 		case KSU_KERNEL:
-			printk("KERNEL ");
+			pr_cont("KERNEL ");
 			break;
 		default:
-			printk("BAD_MODE ");
+			pr_cont("BAD_MODE ");
 			break;
 		}
 		if (regs->cp0_status & ST0_ERL)
-			printk("ERL ");
+			pr_cont("ERL ");
 		if (regs->cp0_status & ST0_EXL)
-			printk("EXL ");
+			pr_cont("EXL ");
 		if (regs->cp0_status & ST0_IE)
-			printk("IE ");
+			pr_cont("IE ");
 	}
-	printk("\n");
+	pr_cont("\n");
 
 	exccode = (cause & CAUSEF_EXCCODE) >> CAUSEB_EXCCODE;
 	printk("Cause : %08x (ExcCode %02x)\n", cause, exccode);
@@ -705,6 +708,32 @@ asmlinkage void do_ov(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
+/*
+ * Send SIGFPE according to FCSR Cause bits, which must have already
+ * been masked against Enable bits.  This is impotant as Inexact can
+ * happen together with Overflow or Underflow, and `ptrace' can set
+ * any bits.
+ */
+void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
+		     struct task_struct *tsk)
+{
+	struct siginfo si = { .si_addr = fault_addr, .si_signo = SIGFPE };
+
+	if (fcr31 & FPU_CSR_INV_X)
+		si.si_code = FPE_FLTINV;
+	else if (fcr31 & FPU_CSR_DIV_X)
+		si.si_code = FPE_FLTDIV;
+	else if (fcr31 & FPU_CSR_OVF_X)
+		si.si_code = FPE_FLTOVF;
+	else if (fcr31 & FPU_CSR_UDF_X)
+		si.si_code = FPE_FLTUND;
+	else if (fcr31 & FPU_CSR_INE_X)
+		si.si_code = FPE_FLTRES;
+	else
+		si.si_code = __SI_FAULT;
+	force_sig_info(SIGFPE, &si, tsk);
+}
+
 int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 {
 	struct siginfo si = { 0 };
@@ -715,27 +744,7 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 		return 0;
 
 	case SIGFPE:
-		si.si_addr = fault_addr;
-		si.si_signo = sig;
-		/*
-		 * Inexact can happen together with Overflow or Underflow.
-		 * Respect the mask to deliver the correct exception.
-		 */
-		fcr31 &= (fcr31 & FPU_CSR_ALL_E) <<
-			 (ffs(FPU_CSR_ALL_X) - ffs(FPU_CSR_ALL_E));
-		if (fcr31 & FPU_CSR_INV_X)
-			si.si_code = FPE_FLTINV;
-		else if (fcr31 & FPU_CSR_DIV_X)
-			si.si_code = FPE_FLTDIV;
-		else if (fcr31 & FPU_CSR_OVF_X)
-			si.si_code = FPE_FLTOVF;
-		else if (fcr31 & FPU_CSR_UDF_X)
-			si.si_code = FPE_FLTUND;
-		else if (fcr31 & FPU_CSR_INE_X)
-			si.si_code = FPE_FLTRES;
-		else
-			si.si_code = __SI_FAULT;
-		force_sig_info(sig, &si, current);
+		force_fcr31_sig(fcr31, fault_addr, current);
 		return 1;
 
 	case SIGBUS:
@@ -799,13 +808,13 @@ static int simulate_fp(struct pt_regs *regs, unsigned int opcode,
 	/* Run the emulator */
 	sig = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
 				       &fault_addr);
-	fcr31 = current->thread.fpu.fcr31;
 
 	/*
-	 * We can't allow the emulated instruction to leave any of
-	 * the cause bits set in $fcr31.
+	 * We can't allow the emulated instruction to leave any
+	 * enabled Cause bits set in $fcr31.
 	 */
-	current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
+	fcr31 = mask_fcr31_x(current->thread.fpu.fcr31);
+	current->thread.fpu.fcr31 &= ~fcr31;
 
 	/* Restore the hardware register state */
 	own_fpu(1);
@@ -831,7 +840,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 		goto out;
 
 	/* Clear FCSR.Cause before enabling interrupts */
-	write_32bit_cp1_register(CP1_STATUS, fcr31 & ~FPU_CSR_ALL_X);
+	write_32bit_cp1_register(CP1_STATUS, fcr31 & ~mask_fcr31_x(fcr31));
 	local_irq_enable();
 
 	die_if_kernel("FP exception in kernel code", regs);
@@ -853,13 +862,13 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 		/* Run the emulator */
 		sig = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
 					       &fault_addr);
-		fcr31 = current->thread.fpu.fcr31;
 
 		/*
-		 * We can't allow the emulated instruction to leave any of
-		 * the cause bits set in $fcr31.
+		 * We can't allow the emulated instruction to leave any
+		 * enabled Cause bits set in $fcr31.
 		 */
-		current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
+		fcr31 = mask_fcr31_x(current->thread.fpu.fcr31);
+		current->thread.fpu.fcr31 &= ~fcr31;
 
 		/* Restore the hardware register state */
 		own_fpu(1);	/* Using the FPU again.	 */
@@ -1424,13 +1433,13 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 
 		sig = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 0,
 					       &fault_addr);
-		fcr31 = current->thread.fpu.fcr31;
 
 		/*
 		 * We can't allow the emulated instruction to leave
-		 * any of the cause bits set in $fcr31.
+		 * any enabled Cause bits set in $fcr31.
 		 */
-		current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
+		fcr31 = mask_fcr31_x(current->thread.fpu.fcr31);
+		current->thread.fpu.fcr31 &= ~fcr31;
 
 		/* Send a signal if required.  */
 		if (!process_fpemu_return(sig, fault_addr, fcr31) && !err)
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 8770f32..aa09374 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -790,15 +790,15 @@ enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	enum emulation_result er = EMULATE_DONE;
 
-	if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
+	if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
+		kvm_clear_c0_guest_status(cop0, ST0_ERL);
+		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
+	} else if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
 		kvm_debug("[%#lx] ERET to %#lx\n", vcpu->arch.pc,
 			  kvm_read_c0_guest_epc(cop0));
 		kvm_clear_c0_guest_status(cop0, ST0_EXL);
 		vcpu->arch.pc = kvm_read_c0_guest_epc(cop0);
 
-	} else if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
-		kvm_clear_c0_guest_status(cop0, ST0_ERL);
-		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
 	} else {
 		kvm_err("[%#lx] ERET when MIPS_SR_EXL|MIPS_SR_ERL == 0\n",
 			vcpu->arch.pc);
@@ -1528,13 +1528,25 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
 					    struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DO_MMIO;
+	unsigned long curr_pc;
 	u32 op, rt;
 	u32 bytes;
 
 	rt = inst.i_format.rt;
 	op = inst.i_format.opcode;
 
-	vcpu->arch.pending_load_cause = cause;
+	/*
+	 * Find the resume PC now while we have safe and easy access to the
+	 * prior branch instruction, and save it for
+	 * kvm_mips_complete_mmio_load() to restore later.
+	 */
+	curr_pc = vcpu->arch.pc;
+	er = update_pc(vcpu, cause);
+	if (er == EMULATE_FAIL)
+		return er;
+	vcpu->arch.io_pc = vcpu->arch.pc;
+	vcpu->arch.pc = curr_pc;
+
 	vcpu->arch.io_gpr = rt;
 
 	switch (op) {
@@ -2494,9 +2506,8 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 		goto done;
 	}
 
-	er = update_pc(vcpu, vcpu->arch.pending_load_cause);
-	if (er == EMULATE_FAIL)
-		return er;
+	/* Restore saved resume PC */
+	vcpu->arch.pc = vcpu->arch.io_pc;
 
 	switch (run->mmio.len) {
 	case 4:
@@ -2518,11 +2529,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	if (vcpu->arch.pending_load_cause & CAUSEF_BD)
-		kvm_debug("[%#lx] Completing %d byte BD Load to gpr %d (0x%08lx) type %d\n",
-			  vcpu->arch.pc, run->mmio.len, vcpu->arch.io_gpr, *gpr,
-			  vcpu->mmio_needed);
-
 done:
 	return er;
 }
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 622037d..06a60b1 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -426,7 +426,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 static void kvm_mips_check_asids(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	int cpu = smp_processor_id();
+	int i, cpu = smp_processor_id();
 	unsigned int gasid;
 
 	/*
@@ -442,6 +442,9 @@ static void kvm_mips_check_asids(struct kvm_vcpu *vcpu)
 						vcpu);
 			vcpu->arch.guest_user_asid[cpu] =
 				vcpu->arch.guest_user_mm.context.asid[cpu];
+			for_each_possible_cpu(i)
+				if (i != cpu)
+					vcpu->arch.guest_user_asid[cpu] = 0;
 			vcpu->arch.last_user_gasid = gasid;
 		}
 	}
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index 03883ba..3b677c8 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -260,13 +260,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	if ((vcpu->arch.guest_user_asid[cpu] ^ asid_cache(cpu)) &
 						asid_version_mask(cpu)) {
-		u32 gasid = kvm_read_c0_guest_entryhi(vcpu->arch.cop0) &
-				KVM_ENTRYHI_ASID;
-
 		kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, vcpu);
 		vcpu->arch.guest_user_asid[cpu] =
 		    vcpu->arch.guest_user_mm.context.asid[cpu];
-		vcpu->arch.last_user_gasid = gasid;
 		newasid++;
 
 		kvm_debug("[%d]: cpu_context: %#lx\n", cpu,
diff --git a/arch/mips/lib/dump_tlb.c b/arch/mips/lib/dump_tlb.c
index 0f80b93..6eb50a7 100644
--- a/arch/mips/lib/dump_tlb.c
+++ b/arch/mips/lib/dump_tlb.c
@@ -135,42 +135,42 @@ static void dump_tlb(int first, int last)
 		c0 = (entrylo0 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
 		c1 = (entrylo1 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
 
-		printk("va=%0*lx asid=%0*lx",
-		       vwidth, (entryhi & ~0x1fffUL),
-		       asidwidth, entryhi & asidmask);
+		pr_cont("va=%0*lx asid=%0*lx",
+			vwidth, (entryhi & ~0x1fffUL),
+			asidwidth, entryhi & asidmask);
 		if (cpu_has_guestid)
-			printk(" gid=%02lx",
-			       (guestctl1 & MIPS_GCTL1_RID)
+			pr_cont(" gid=%02lx",
+				(guestctl1 & MIPS_GCTL1_RID)
 					>> MIPS_GCTL1_RID_SHIFT);
 		/* RI/XI are in awkward places, so mask them off separately */
 		pa = entrylo0 & ~(MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI);
 		if (xpa)
 			pa |= (unsigned long long)readx_c0_entrylo0() << 30;
 		pa = (pa << 6) & PAGE_MASK;
-		printk("\n\t[");
+		pr_cont("\n\t[");
 		if (cpu_has_rixi)
-			printk("ri=%d xi=%d ",
-			       (entrylo0 & MIPS_ENTRYLO_RI) ? 1 : 0,
-			       (entrylo0 & MIPS_ENTRYLO_XI) ? 1 : 0);
-		printk("pa=%0*llx c=%d d=%d v=%d g=%d] [",
-		       pwidth, pa, c0,
-		       (entrylo0 & ENTRYLO_D) ? 1 : 0,
-		       (entrylo0 & ENTRYLO_V) ? 1 : 0,
-		       (entrylo0 & ENTRYLO_G) ? 1 : 0);
+			pr_cont("ri=%d xi=%d ",
+				(entrylo0 & MIPS_ENTRYLO_RI) ? 1 : 0,
+				(entrylo0 & MIPS_ENTRYLO_XI) ? 1 : 0);
+		pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d] [",
+			pwidth, pa, c0,
+			(entrylo0 & ENTRYLO_D) ? 1 : 0,
+			(entrylo0 & ENTRYLO_V) ? 1 : 0,
+			(entrylo0 & ENTRYLO_G) ? 1 : 0);
 		/* RI/XI are in awkward places, so mask them off separately */
 		pa = entrylo1 & ~(MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI);
 		if (xpa)
 			pa |= (unsigned long long)readx_c0_entrylo1() << 30;
 		pa = (pa << 6) & PAGE_MASK;
 		if (cpu_has_rixi)
-			printk("ri=%d xi=%d ",
-			       (entrylo1 & MIPS_ENTRYLO_RI) ? 1 : 0,
-			       (entrylo1 & MIPS_ENTRYLO_XI) ? 1 : 0);
-		printk("pa=%0*llx c=%d d=%d v=%d g=%d]\n",
-		       pwidth, pa, c1,
-		       (entrylo1 & ENTRYLO_D) ? 1 : 0,
-		       (entrylo1 & ENTRYLO_V) ? 1 : 0,
-		       (entrylo1 & ENTRYLO_G) ? 1 : 0);
+			pr_cont("ri=%d xi=%d ",
+				(entrylo1 & MIPS_ENTRYLO_RI) ? 1 : 0,
+				(entrylo1 & MIPS_ENTRYLO_XI) ? 1 : 0);
+		pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d]\n",
+			pwidth, pa, c1,
+			(entrylo1 & ENTRYLO_D) ? 1 : 0,
+			(entrylo1 & ENTRYLO_V) ? 1 : 0,
+			(entrylo1 & ENTRYLO_G) ? 1 : 0);
 	}
 	printk("\n");
 
diff --git a/arch/mips/lib/r3k_dump_tlb.c b/arch/mips/lib/r3k_dump_tlb.c
index 744f4a7..85b4086 100644
--- a/arch/mips/lib/r3k_dump_tlb.c
+++ b/arch/mips/lib/r3k_dump_tlb.c
@@ -53,15 +53,15 @@ static void dump_tlb(int first, int last)
 			 */
 			printk("Index: %2d ", i);
 
-			printk("va=%08lx asid=%08lx"
-			       "  [pa=%06lx n=%d d=%d v=%d g=%d]",
-			       entryhi & PAGE_MASK,
-			       entryhi & asid_mask,
-			       entrylo0 & PAGE_MASK,
-			       (entrylo0 & R3K_ENTRYLO_N) ? 1 : 0,
-			       (entrylo0 & R3K_ENTRYLO_D) ? 1 : 0,
-			       (entrylo0 & R3K_ENTRYLO_V) ? 1 : 0,
-			       (entrylo0 & R3K_ENTRYLO_G) ? 1 : 0);
+			pr_cont("va=%08lx asid=%08lx"
+				"  [pa=%06lx n=%d d=%d v=%d g=%d]",
+				entryhi & PAGE_MASK,
+				entryhi & asid_mask,
+				entrylo0 & PAGE_MASK,
+				(entrylo0 & R3K_ENTRYLO_N) ? 1 : 0,
+				(entrylo0 & R3K_ENTRYLO_D) ? 1 : 0,
+				(entrylo0 & R3K_ENTRYLO_V) ? 1 : 0,
+				(entrylo0 & R3K_ENTRYLO_G) ? 1 : 0);
 		}
 	}
 	printk("\n");
diff --git a/arch/openrisc/include/asm/cache.h b/arch/openrisc/include/asm/cache.h
index 4ce7a01..5f55da9 100644
--- a/arch/openrisc/include/asm/cache.h
+++ b/arch/openrisc/include/asm/cache.h
@@ -23,6 +23,8 @@
  * they shouldn't be hard-coded!
  */
 
+#define __ro_after_init __read_mostly
+
 #define L1_CACHE_BYTES 16
 #define L1_CACHE_SHIFT 4
 
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index a9b9407..6b0741e 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -368,7 +368,9 @@
 
 #define __IGNORE_select		/* newselect */
 #define __IGNORE_fadvise64	/* fadvise64_64 */
-
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
 
 #define LINUX_GATEWAY_ADDR      0x100
 
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index f815066..700e2d2 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -873,11 +873,11 @@ static void print_parisc_device(struct parisc_device *dev)
 
 	if (dev->num_addrs) {
 		int k;
-		printk(", additional addresses: ");
+		pr_cont(", additional addresses: ");
 		for (k = 0; k < dev->num_addrs; k++)
-			printk("0x%lx ", dev->addr[k]);
+			pr_cont("0x%lx ", dev->addr[k]);
 	}
-	printk("\n");
+	pr_cont("\n");
 }
 
 /**
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index d03422e..23de307 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -100,14 +100,12 @@
 	.endr
 
 /* This address must remain fixed at 0x100 for glibc's syscalls to work */
-	.align 256
+	.align LINUX_GATEWAY_ADDR
 linux_gateway_entry:
 	gate	.+8, %r0			/* become privileged */
 	mtsp	%r0,%sr4			/* get kernel space into sr4 */
 	mtsp	%r0,%sr5			/* get kernel space into sr5 */
 	mtsp	%r0,%sr6			/* get kernel space into sr6 */
-	mfsp    %sr7,%r1                        /* save user sr7 */
-	mtsp    %r1,%sr3                        /* and store it in sr3 */
 
 #ifdef CONFIG_64BIT
 	/* for now we can *always* set the W bit on entry to the syscall
@@ -133,6 +131,14 @@
 	depdi	0, 31, 32, %r21
 1:	
 #endif
+
+	/* We use a rsm/ssm pair to prevent sr3 from being clobbered
+	 * by external interrupts.
+	 */
+	mfsp    %sr7,%r1                        /* save user sr7 */
+	rsm	PSW_SM_I, %r0			/* disable interrupts */
+	mtsp    %r1,%sr3                        /* and store it in sr3 */
+
 	mfctl   %cr30,%r1
 	xor     %r1,%r30,%r30                   /* ye olde xor trick */
 	xor     %r1,%r30,%r1
@@ -147,6 +153,7 @@
 	 */
 
 	mtsp	%r0,%sr7			/* get kernel space into sr7 */
+	ssm	PSW_SM_I, %r0			/* enable interrupts */
 	STREGM	%r1,FRAME_SIZE(%r30)		/* save r1 (usp) here for now */
 	mfctl	%cr30,%r1			/* get task ptr in %r1 */
 	LDREG	TI_TASK(%r1),%r1
@@ -474,11 +481,6 @@
 	comiclr,>>	__NR_lws_entries, %r20, %r0
 	b,n	lws_exit_nosys
 
-	/* WARNING: Trashing sr2 and sr3 */
-	mfsp	%sr7,%r1			/* get userspace into sr3 */
-	mtsp	%r1,%sr3
-	mtsp	%r0,%sr2			/* get kernel space into sr2 */
-
 	/* Load table start */
 	ldil	L%lws_table, %r1
 	ldo	R%lws_table(%r1), %r28	/* Scratch use of r28 */
@@ -627,9 +629,9 @@
 	stw	%r1, 4(%sr2,%r20)
 #endif
 	/* The load and store could fail */
-1:	ldw,ma	0(%sr3,%r26), %r28
+1:	ldw,ma	0(%r26), %r28
 	sub,<>	%r28, %r25, %r0
-2:	stw,ma	%r24, 0(%sr3,%r26)
+2:	stw,ma	%r24, 0(%r26)
 	/* Free lock */
 	stw,ma	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
@@ -706,9 +708,9 @@
 	nop
 
 	/* 8bit load */
-4:	ldb	0(%sr3,%r25), %r25
+4:	ldb	0(%r25), %r25
 	b	cas2_lock_start
-5:	ldb	0(%sr3,%r24), %r24
+5:	ldb	0(%r24), %r24
 	nop
 	nop
 	nop
@@ -716,9 +718,9 @@
 	nop
 
 	/* 16bit load */
-6:	ldh	0(%sr3,%r25), %r25
+6:	ldh	0(%r25), %r25
 	b	cas2_lock_start
-7:	ldh	0(%sr3,%r24), %r24
+7:	ldh	0(%r24), %r24
 	nop
 	nop
 	nop
@@ -726,9 +728,9 @@
 	nop
 
 	/* 32bit load */
-8:	ldw	0(%sr3,%r25), %r25
+8:	ldw	0(%r25), %r25
 	b	cas2_lock_start
-9:	ldw	0(%sr3,%r24), %r24
+9:	ldw	0(%r24), %r24
 	nop
 	nop
 	nop
@@ -737,14 +739,14 @@
 
 	/* 64bit load */
 #ifdef CONFIG_64BIT
-10:	ldd	0(%sr3,%r25), %r25
-11:	ldd	0(%sr3,%r24), %r24
+10:	ldd	0(%r25), %r25
+11:	ldd	0(%r24), %r24
 #else
 	/* Load new value into r22/r23 - high/low */
-10:	ldw	0(%sr3,%r25), %r22
-11:	ldw	4(%sr3,%r25), %r23
+10:	ldw	0(%r25), %r22
+11:	ldw	4(%r25), %r23
 	/* Load new value into fr4 for atomic store later */
-12:	flddx	0(%sr3,%r24), %fr4
+12:	flddx	0(%r24), %fr4
 #endif
 
 cas2_lock_start:
@@ -794,30 +796,30 @@
 	ldo	1(%r0),%r28
 
 	/* 8bit CAS */
-13:	ldb,ma	0(%sr3,%r26), %r29
+13:	ldb,ma	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-14:	stb,ma	%r24, 0(%sr3,%r26)
+14:	stb,ma	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop
 
 	/* 16bit CAS */
-15:	ldh,ma	0(%sr3,%r26), %r29
+15:	ldh,ma	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-16:	sth,ma	%r24, 0(%sr3,%r26)
+16:	sth,ma	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop
 
 	/* 32bit CAS */
-17:	ldw,ma	0(%sr3,%r26), %r29
+17:	ldw,ma	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-18:	stw,ma	%r24, 0(%sr3,%r26)
+18:	stw,ma	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
@@ -825,22 +827,22 @@
 
 	/* 64bit CAS */
 #ifdef CONFIG_64BIT
-19:	ldd,ma	0(%sr3,%r26), %r29
+19:	ldd,ma	0(%r26), %r29
 	sub,*=	%r29, %r25, %r0
 	b,n	cas2_end
-20:	std,ma	%r24, 0(%sr3,%r26)
+20:	std,ma	%r24, 0(%r26)
 	copy	%r0, %r28
 #else
 	/* Compare first word */
-19:	ldw,ma	0(%sr3,%r26), %r29
+19:	ldw,ma	0(%r26), %r29
 	sub,=	%r29, %r22, %r0
 	b,n	cas2_end
 	/* Compare second word */
-20:	ldw,ma	4(%sr3,%r26), %r29
+20:	ldw,ma	4(%r26), %r29
 	sub,=	%r29, %r23, %r0
 	b,n	cas2_end
 	/* Perform the store */
-21:	fstdx	%fr4, 0(%sr3,%r26)
+21:	fstdx	%fr4, 0(%r26)
 	copy	%r0, %r28
 #endif
 
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index ee655ed..1e8fceb 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -53,10 +53,8 @@ static inline __sum16 csum_fold(__wsum sum)
 	return (__force __sum16)(~((__force u32)sum + tmp) >> 16);
 }
 
-static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-                                     unsigned short len,
-                                     unsigned short proto,
-                                     __wsum sum)
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
 {
 #ifdef __powerpc64__
 	unsigned long s = (__force u32)sum;
@@ -83,10 +81,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * computes the checksum of the TCP/UDP pseudo-header
  * returns a 16-bit checksum, already complemented
  */
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
-					__wsum sum)
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index 01b8a13..3919332 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -26,7 +26,7 @@ extern u64 pnv_first_deep_stop_state;
 	std	r0,0(r1);					\
 	ptesync;						\
 	ld	r0,0(r1);					\
-1:	cmp	cr0,r0,r0;					\
+1:	cmpd	cr0,r0,r0;					\
 	bne	1b;						\
 	IDLE_INST;						\
 	b	.
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 2e4e7d8..84d49b1 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -93,6 +93,10 @@
 	ld	reg,PACAKBASE(r13);	/* get high part of &label */	\
 	ori	reg,reg,(FIXED_SYMBOL_ABS_ADDR(label))@l;
 
+#define __LOAD_HANDLER(reg, label)					\
+	ld	reg,PACAKBASE(r13);					\
+	ori	reg,reg,(ABS_ADDR(label))@l;
+
 /* Exception register prefixes */
 #define EXC_HV	H
 #define EXC_STD
@@ -208,6 +212,18 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define kvmppc_interrupt kvmppc_interrupt_pr
 #endif
 
+#ifdef CONFIG_RELOCATABLE
+#define BRANCH_TO_COMMON(reg, label)					\
+	__LOAD_HANDLER(reg, label);					\
+	mtctr	reg;							\
+	bctr
+
+#else
+#define BRANCH_TO_COMMON(reg, label)					\
+	b	label
+
+#endif
+
 #define __KVM_HANDLER_PROLOG(area, n)					\
 	BEGIN_FTR_SECTION_NESTED(947)					\
 	ld	r10,area+EX_CFAR(r13);					\
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index f6f68f7..99e1397 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -52,11 +52,23 @@ static inline int mm_is_core_local(struct mm_struct *mm)
 	return cpumask_subset(mm_cpumask(mm),
 			      topology_sibling_cpumask(smp_processor_id()));
 }
+
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+	return cpumask_equal(mm_cpumask(mm),
+			      cpumask_of(smp_processor_id()));
+}
+
 #else
 static inline int mm_is_core_local(struct mm_struct *mm)
 {
 	return 1;
 }
+
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+	return 1;
+}
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f129408..08ba447 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -95,19 +95,35 @@
 /* No virt vectors corresponding with 0x0..0x100 */
 EXC_VIRT_NONE(0x4000, 0x4100)
 
+
+#ifdef CONFIG_PPC_P7_NAP
+	/*
+	 * If running native on arch 2.06 or later, check if we are waking up
+	 * from nap/sleep/winkle, and branch to idle handler.
+	 */
+#define IDLETEST(n)							\
+	BEGIN_FTR_SECTION ;						\
+	mfspr	r10,SPRN_SRR1 ;						\
+	rlwinm.	r10,r10,47-31,30,31 ;					\
+	beq-	1f ;							\
+	cmpwi	cr3,r10,2 ;						\
+	BRANCH_TO_COMMON(r10, system_reset_idle_common) ;		\
+1:									\
+	END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+#else
+#define IDLETEST NOTEST
+#endif
+
 EXC_REAL_BEGIN(system_reset, 0x100, 0x200)
 	SET_SCRATCH0(r13)
-#ifdef CONFIG_PPC_P7_NAP
-BEGIN_FTR_SECTION
-	/* Running native on arch 2.06 or later, check if we are
-	 * waking up from nap/sleep/winkle.
-	 */
-	mfspr	r13,SPRN_SRR1
-	rlwinm.	r13,r13,47-31,30,31
-	beq	9f
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+				 IDLETEST, 0x100)
 
-	cmpwi	cr3,r13,2
-	GET_PACA(r13)
+EXC_REAL_END(system_reset, 0x100, 0x200)
+EXC_VIRT_NONE(0x4100, 0x4200)
+
+#ifdef CONFIG_PPC_P7_NAP
+EXC_COMMON_BEGIN(system_reset_idle_common)
 	bl	pnv_restore_hyp_resource
 
 	li	r0,PNV_THREAD_RUNNING
@@ -130,14 +146,8 @@
 	blt	cr3,2f
 	b	pnv_wakeup_loss
 2:	b	pnv_wakeup_noloss
+#endif
 
-9:
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-#endif /* CONFIG_PPC_P7_NAP */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
-				 NOTEST, 0x100)
-EXC_REAL_END(system_reset, 0x100, 0x200)
-EXC_VIRT_NONE(0x4100, 0x4200)
 EXC_COMMON(system_reset_common, 0x100, system_reset_exception)
 
 #ifdef CONFIG_PPC_PSERIES
@@ -817,10 +827,8 @@
 TRAMP_KVM(PACA_EXGEN, 0xb00)
 EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
 
-
-#define LOAD_SYSCALL_HANDLER(reg)				\
-	ld	reg,PACAKBASE(r13);				\
-	ori	reg,reg,(ABS_ADDR(system_call_common))@l;
+#define LOAD_SYSCALL_HANDLER(reg)					\
+	__LOAD_HANDLER(reg, system_call_common)
 
 /* Syscall routine is used twice, in reloc-off and reloc-on paths */
 #define SYSCALL_PSERIES_1 					\
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 9781c69..03d089b 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -275,7 +275,7 @@ int hw_breakpoint_handler(struct die_args *args)
 	if (!stepped) {
 		WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
 			"0x%lx will be disabled.", info->address);
-		perf_event_disable(bp);
+		perf_event_disable_inatomic(bp);
 		goto out;
 	}
 	/*
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index bd739fe..72dac0b 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -90,6 +90,7 @@
  * Threads will spin in HMT_LOW until the lock bit is cleared.
  * r14 - pointer to core_idle_state
  * r15 - used to load contents of core_idle_state
+ * r9  - used as a temporary variable
  */
 
 core_idle_lock_held:
@@ -99,6 +100,8 @@
 	bne	3b
 	HMT_MEDIUM
 	lwarx	r15,0,r14
+	andi.	r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	bne	core_idle_lock_held
 	blr
 
 /*
@@ -163,12 +166,6 @@
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	/* Tell KVM we're entering idle */
-	li	r4,KVM_HWTHREAD_IN_IDLE
-	stb	r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-
 	/*
 	 * Go to real mode to do the nap, as required by the architecture.
 	 * Also, we need to be in real mode before setting hwthread_state,
@@ -185,6 +182,26 @@
 
 	.globl pnv_enter_arch207_idle_mode
 pnv_enter_arch207_idle_mode:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* Tell KVM we're entering idle */
+	li	r4,KVM_HWTHREAD_IN_IDLE
+	/******************************************************/
+	/*  N O T E   W E L L    ! ! !    N O T E   W E L L   */
+	/* The following store to HSTATE_HWTHREAD_STATE(r13)  */
+	/* MUST occur in real mode, i.e. with the MMU off,    */
+	/* and the MMU must stay off until we clear this flag */
+	/* and test HSTATE_HWTHREAD_REQ(r13) in the system    */
+	/* reset interrupt vector in exceptions-64s.S.        */
+	/* The reason is that another thread can switch the   */
+	/* MMU to a guest context whenever this flag is set   */
+	/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on,    */
+	/* that would potentially cause this thread to start  */
+	/* executing instructions from guest memory in        */
+	/* hypervisor mode, leading to a host crash or data   */
+	/* corruption, or worse.                              */
+	/******************************************************/
+	stb	r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
 	stb	r3,PACA_THREAD_IDLE_STATE(r13)
 	cmpwi	cr3,r3,PNV_THREAD_SLEEP
 	bge	cr3,2f
@@ -250,6 +267,12 @@
  * r3 - requested stop state
  */
 power_enter_stop:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* Tell KVM we're entering idle */
+	li	r4,KVM_HWTHREAD_IN_IDLE
+	/* DO THIS IN REAL MODE!  See comment above. */
+	stb	r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
 /*
  * Check if the requested state is a deep idle state.
  */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9e7c10f..ce6dc61 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1012,7 +1012,7 @@ void restore_tm_state(struct pt_regs *regs)
 	/* Ensure that restore_math() will restore */
 	if (msr_diff & MSR_FP)
 		current->thread.load_fp = 1;
-#ifdef CONFIG_ALIVEC
+#ifdef CONFIG_ALTIVEC
 	if (cpu_has_feature(CPU_FTR_ALTIVEC) && msr_diff & MSR_VEC)
 		current->thread.load_vec = 1;
 #endif
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 82ff5de..a0ea63a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -23,6 +23,7 @@
 #include <asm/ppc-opcode.h>
 #include <asm/pnv-pci.h>
 #include <asm/opal.h>
+#include <asm/smp.h>
 
 #include "book3s_xics.h"
 
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 0e49ec5..bda8c43 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -175,7 +175,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		goto no_context;
 
-	if (!mm_is_core_local(mm)) {
+	if (!mm_is_thread_local(mm)) {
 		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 		if (lock_tlbie)
@@ -201,7 +201,7 @@ void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		goto no_context;
 
-	if (!mm_is_core_local(mm)) {
+	if (!mm_is_thread_local(mm)) {
 		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 		if (lock_tlbie)
@@ -226,7 +226,7 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 	pid = mm ? mm->context.id : 0;
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		goto bail;
-	if (!mm_is_core_local(mm)) {
+	if (!mm_is_thread_local(mm)) {
 		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 		if (lock_tlbie)
@@ -321,7 +321,7 @@ void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
 {
 	unsigned long pid;
 	unsigned long addr;
-	int local = mm_is_core_local(mm);
+	int local = mm_is_thread_local(mm);
 	unsigned long ap = mmu_get_ap(psize);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 	unsigned long page_size = 1UL << mmu_psize_defs[psize].shift;
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 28f03ca..794bebb 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -363,11 +363,11 @@ static void *diag204_store(void)
 static int diag224_get_name_table(void)
 {
 	/* memory must be below 2GB */
-	diag224_cpu_names = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA);
+	diag224_cpu_names = (char *) __get_free_page(GFP_KERNEL | GFP_DMA);
 	if (!diag224_cpu_names)
 		return -ENOMEM;
 	if (diag224(diag224_cpu_names)) {
-		kfree(diag224_cpu_names);
+		free_page((unsigned long) diag224_cpu_names);
 		return -EOPNOTSUPP;
 	}
 	EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16);
@@ -376,7 +376,7 @@ static int diag224_get_name_table(void)
 
 static void diag224_delete_name_table(void)
 {
-	kfree(diag224_cpu_names);
+	free_page((unsigned long) diag224_cpu_names);
 }
 
 static int diag224_idx2name(int index, char *name)
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 64053d9..836c562 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -12,9 +12,7 @@
 
 #ifndef __ASSEMBLY__
 
-unsigned long return_address(int depth);
-
-#define ftrace_return_address(n) return_address(n)
+#define ftrace_return_address(n) __builtin_return_address(n)
 
 void _mcount(void);
 void ftrace_caller(void);
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 0332317..602af69 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -192,7 +192,7 @@ struct task_struct;
 struct mm_struct;
 struct seq_file;
 
-typedef int (*dump_trace_func_t)(void *data, unsigned long address);
+typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable);
 void dump_trace(dump_trace_func_t func, void *data,
 		struct task_struct *task, unsigned long sp);
 
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 02613ba..3066031 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -9,6 +9,9 @@
 #include <uapi/asm/unistd.h>
 
 #define __IGNORE_time
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 43446fa..c74c592 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -2014,12 +2014,12 @@ void show_code(struct pt_regs *regs)
 			*ptr++ = '\t';
 		ptr += print_insn(ptr, code + start, addr);
 		start += opsize;
-		printk("%s", buffer);
+		pr_cont("%s", buffer);
 		ptr = buffer;
 		ptr += sprintf(ptr, "\n          ");
 		hops++;
 	}
-	printk("\n");
+	pr_cont("\n");
 }
 
 void print_fn_code(unsigned char *code, unsigned long len)
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 6693383..55d4fe1 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -38,10 +38,10 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
+		if (func(data, sf->gprs[8], 0))
+			return sp;
 		/* Follow the backchain. */
 		while (1) {
-			if (func(data, sf->gprs[8]))
-				return sp;
 			low = sp;
 			sp = sf->back_chain;
 			if (!sp)
@@ -49,6 +49,8 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
+			if (func(data, sf->gprs[8], 1))
+				return sp;
 		}
 		/* Zero backchain detected, check for interrupt frame. */
 		sp = (unsigned long) (sf + 1);
@@ -56,7 +58,7 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
 			return sp;
 		regs = (struct pt_regs *) sp;
 		if (!user_mode(regs)) {
-			if (func(data, regs->psw.addr))
+			if (func(data, regs->psw.addr, 1))
 				return sp;
 		}
 		low = sp;
@@ -85,33 +87,12 @@ void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task,
 }
 EXPORT_SYMBOL_GPL(dump_trace);
 
-struct return_address_data {
-	unsigned long address;
-	int depth;
-};
-
-static int __return_address(void *data, unsigned long address)
+static int show_address(void *data, unsigned long address, int reliable)
 {
-	struct return_address_data *rd = data;
-
-	if (rd->depth--)
-		return 0;
-	rd->address = address;
-	return 1;
-}
-
-unsigned long return_address(int depth)
-{
-	struct return_address_data rd = { .depth = depth + 2 };
-
-	dump_trace(__return_address, &rd, NULL, current_stack_pointer());
-	return rd.address;
-}
-EXPORT_SYMBOL_GPL(return_address);
-
-static int show_address(void *data, unsigned long address)
-{
-	printk("([<%016lx>] %pSR)\n", address, (void *)address);
+	if (reliable)
+		printk(" [<%016lx>] %pSR \n", address, (void *)address);
+	else
+		printk("([<%016lx>] %pSR)\n", address, (void *)address);
 	return 0;
 }
 
@@ -138,14 +119,14 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 		else
 			stack = (unsigned long *)task->thread.ksp;
 	}
+	printk(KERN_DEFAULT "Stack:\n");
 	for (i = 0; i < 20; i++) {
 		if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
 			break;
-		if ((i * sizeof(long) % 32) == 0)
-			printk("%s       ", i == 0 ? "" : "\n");
-		printk("%016lx ", *stack++);
+		if (i % 4 == 0)
+			printk(KERN_DEFAULT "       ");
+		pr_cont("%016lx%c", *stack++, i % 4 == 3 ? '\n' : ' ');
 	}
-	printk("\n");
 	show_trace(task, (unsigned long)sp);
 }
 
@@ -163,13 +144,13 @@ void show_registers(struct pt_regs *regs)
 	mode = user_mode(regs) ? "User" : "Krnl";
 	printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr);
 	if (!user_mode(regs))
-		printk(" (%pSR)", (void *)regs->psw.addr);
-	printk("\n");
+		pr_cont(" (%pSR)", (void *)regs->psw.addr);
+	pr_cont("\n");
 	printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
 	       "P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e,
 	       psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm);
-	printk(" RI:%x EA:%x", psw->ri, psw->eaba);
-	printk("\n%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
+	pr_cont(" RI:%x EA:%x\n", psw->ri, psw->eaba);
+	printk("%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
 	       regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
 	printk("           %016lx %016lx %016lx %016lx\n",
 	       regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]);
@@ -205,14 +186,14 @@ void die(struct pt_regs *regs, const char *str)
 	printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff,
 	       regs->int_code >> 17, ++die_counter);
 #ifdef CONFIG_PREEMPT
-	printk("PREEMPT ");
+	pr_cont("PREEMPT ");
 #endif
 #ifdef CONFIG_SMP
-	printk("SMP ");
+	pr_cont("SMP ");
 #endif
 	if (debug_pagealloc_enabled())
-		printk("DEBUG_PAGEALLOC");
-	printk("\n");
+		pr_cont("DEBUG_PAGEALLOC");
+	pr_cont("\n");
 	notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV);
 	print_modules();
 	show_regs(regs);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 17431f6..955a7b6 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -222,7 +222,7 @@ static int __init service_level_perf_register(void)
 }
 arch_initcall(service_level_perf_register);
 
-static int __perf_callchain_kernel(void *data, unsigned long address)
+static int __perf_callchain_kernel(void *data, unsigned long address, int reliable)
 {
 	struct perf_callchain_entry_ctx *entry = data;
 
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 44f84b2..355db9d 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -27,12 +27,12 @@ static int __save_address(void *data, unsigned long address, int nosched)
 	return 1;
 }
 
-static int save_address(void *data, unsigned long address)
+static int save_address(void *data, unsigned long address, int reliable)
 {
 	return __save_address(data, address, 0);
 }
 
-static int save_address_nosched(void *data, unsigned long address)
+static int save_address_nosched(void *data, unsigned long address, int reliable)
 {
 	return __save_address(data, address, 1);
 }
diff --git a/arch/s390/kvm/sthyi.c b/arch/s390/kvm/sthyi.c
index bd98b7d..05c98bb 100644
--- a/arch/s390/kvm/sthyi.c
+++ b/arch/s390/kvm/sthyi.c
@@ -315,7 +315,7 @@ static void fill_diag(struct sthyi_sctns *sctns)
 	if (r < 0)
 		goto out;
 
-	diag224_buf = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA);
+	diag224_buf = (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
 	if (!diag224_buf || diag224(diag224_buf))
 		goto out;
 
@@ -378,7 +378,7 @@ static void fill_diag(struct sthyi_sctns *sctns)
 	sctns->par.infpval1 |= PAR_WGHT_VLD;
 
 out:
-	kfree(diag224_buf);
+	free_page((unsigned long)diag224_buf);
 	vfree(diag204_buf);
 }
 
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index cd404aa..4a0c5bc 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -217,6 +217,7 @@ static __init int setup_hugepagesz(char *opt)
 	} else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 	} else {
+		hugetlb_bad_size();
 		pr_err("hugepagesz= specifies an unsupported page size %s\n",
 			string);
 		return 0;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f56a39b..b3e9d18 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -151,36 +151,40 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
-	unsigned long normal_end_pfn = PFN_DOWN(memblock_end_of_DRAM());
-	unsigned long dma_end_pfn = PFN_DOWN(MAX_DMA_ADDRESS);
+	unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long size_pages = PFN_DOWN(size);
-	unsigned long nr_pages;
-	int rc, zone_enum;
+	pg_data_t *pgdat = NODE_DATA(nid);
+	struct zone *zone;
+	int rc, i;
 
 	rc = vmem_add_mapping(start, size);
 	if (rc)
 		return rc;
 
-	while (size_pages > 0) {
-		if (start_pfn < dma_end_pfn) {
-			nr_pages = (start_pfn + size_pages > dma_end_pfn) ?
-				   dma_end_pfn - start_pfn : size_pages;
-			zone_enum = ZONE_DMA;
-		} else if (start_pfn < normal_end_pfn) {
-			nr_pages = (start_pfn + size_pages > normal_end_pfn) ?
-				   normal_end_pfn - start_pfn : size_pages;
-			zone_enum = ZONE_NORMAL;
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		zone = pgdat->node_zones + i;
+		if (zone_idx(zone) != ZONE_MOVABLE) {
+			/* Add range within existing zone limits, if possible */
+			zone_start_pfn = zone->zone_start_pfn;
+			zone_end_pfn = zone->zone_start_pfn +
+				       zone->spanned_pages;
 		} else {
-			nr_pages = size_pages;
-			zone_enum = ZONE_MOVABLE;
+			/* Add remaining range to ZONE_MOVABLE */
+			zone_start_pfn = start_pfn;
+			zone_end_pfn = start_pfn + size_pages;
 		}
-		rc = __add_pages(nid, NODE_DATA(nid)->node_zones + zone_enum,
-				 start_pfn, size_pages);
+		if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
+			continue;
+		nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
+			   zone_end_pfn - start_pfn : size_pages;
+		rc = __add_pages(nid, zone, start_pfn, nr_pages);
 		if (rc)
 			break;
 		start_pfn += nr_pages;
 		size_pages -= nr_pages;
+		if (!size_pages)
+			break;
 	}
 	if (rc)
 		vmem_remove_mapping(start, size);
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 16f4c39..9a4de45 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <asm/processor.h>
 
-static int __s390_backtrace(void *data, unsigned long address)
+static int __s390_backtrace(void *data, unsigned long address, int reliable)
 {
 	unsigned int *depth = data;
 
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index a6cfdab..5b0ed48 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -24,9 +24,10 @@ typedef struct {
 	unsigned int	icache_line_size;
 	unsigned int	ecache_size;
 	unsigned int	ecache_line_size;
-	unsigned short	sock_id;
+	unsigned short	sock_id;	/* physical package */
 	unsigned short	core_id;
-	int		proc_id;
+	unsigned short  max_cache_id;	/* groupings of highest shared cache */
+	unsigned short	proc_id;	/* strand (aka HW thread) id */
 } cpuinfo_sparc;
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index d9c5876..8011e79 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -134,7 +134,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	*(volatile __u32 *)&lp->lock = ~0U;
 }
 
-static void inline arch_write_unlock(arch_rwlock_t *lock)
+static inline void arch_write_unlock(arch_rwlock_t *lock)
 {
 	__asm__ __volatile__(
 "	st		%%g0, [%0]"
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index 87990b7..07c9f2e 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -96,7 +96,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long fla
 
 /* Multi-reader locks, these are much saner than the 32-bit Sparc ones... */
 
-static void inline arch_read_lock(arch_rwlock_t *lock)
+static inline void arch_read_lock(arch_rwlock_t *lock)
 {
 	unsigned long tmp1, tmp2;
 
@@ -119,7 +119,7 @@ static void inline arch_read_lock(arch_rwlock_t *lock)
 	: "memory");
 }
 
-static int inline arch_read_trylock(arch_rwlock_t *lock)
+static inline int arch_read_trylock(arch_rwlock_t *lock)
 {
 	int tmp1, tmp2;
 
@@ -140,7 +140,7 @@ static int inline arch_read_trylock(arch_rwlock_t *lock)
 	return tmp1;
 }
 
-static void inline arch_read_unlock(arch_rwlock_t *lock)
+static inline void arch_read_unlock(arch_rwlock_t *lock)
 {
 	unsigned long tmp1, tmp2;
 
@@ -156,7 +156,7 @@ static void inline arch_read_unlock(arch_rwlock_t *lock)
 	: "memory");
 }
 
-static void inline arch_write_lock(arch_rwlock_t *lock)
+static inline void arch_write_lock(arch_rwlock_t *lock)
 {
 	unsigned long mask, tmp1, tmp2;
 
@@ -181,7 +181,7 @@ static void inline arch_write_lock(arch_rwlock_t *lock)
 	: "memory");
 }
 
-static void inline arch_write_unlock(arch_rwlock_t *lock)
+static inline void arch_write_unlock(arch_rwlock_t *lock)
 {
 	__asm__ __volatile__(
 "	stw		%%g0, [%0]"
@@ -190,7 +190,7 @@ static void inline arch_write_unlock(arch_rwlock_t *lock)
 	: "memory");
 }
 
-static int inline arch_write_trylock(arch_rwlock_t *lock)
+static inline int arch_write_trylock(arch_rwlock_t *lock)
 {
 	unsigned long mask, tmp1, tmp2, result;
 
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index bec481a..7b4898a 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -44,14 +44,20 @@ int __node_distance(int, int);
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_sib_map[cpu])
+#define topology_core_cache_cpumask(cpu)	(&cpu_core_sib_cache_map[cpu])
 #define topology_sibling_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
 #endif /* CONFIG_SMP */
 
 extern cpumask_t cpu_core_map[NR_CPUS];
 extern cpumask_t cpu_core_sib_map[NR_CPUS];
+extern cpumask_t cpu_core_sib_cache_map[NR_CPUS];
+
+/**
+ * Return cores that shares the last level cache.
+ */
 static inline const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-        return &cpu_core_map[cpu];
+	return &cpu_core_sib_cache_map[cpu];
 }
 
 #endif /* _ASM_SPARC64_TOPOLOGY_H */
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index b68acc5..5373136 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -82,7 +82,6 @@ static inline int access_ok(int type, const void __user * addr, unsigned long si
 	return 1;
 }
 
-void __ret_efault(void);
 void __retl_efault(void);
 
 /* Uh, these should become the main single-value transfer routines..
@@ -189,55 +188,34 @@ int __get_user_bad(void);
 unsigned long __must_check ___copy_from_user(void *to,
 					     const void __user *from,
 					     unsigned long size);
-unsigned long copy_from_user_fixup(void *to, const void __user *from,
-				   unsigned long size);
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long size)
 {
-	unsigned long ret;
-
 	check_object_size(to, size, false);
 
-	ret = ___copy_from_user(to, from, size);
-	if (unlikely(ret))
-		ret = copy_from_user_fixup(to, from, size);
-
-	return ret;
+	return ___copy_from_user(to, from, size);
 }
 #define __copy_from_user copy_from_user
 
 unsigned long __must_check ___copy_to_user(void __user *to,
 					   const void *from,
 					   unsigned long size);
-unsigned long copy_to_user_fixup(void __user *to, const void *from,
-				 unsigned long size);
 static inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long size)
 {
-	unsigned long ret;
-
 	check_object_size(from, size, true);
 
-	ret = ___copy_to_user(to, from, size);
-	if (unlikely(ret))
-		ret = copy_to_user_fixup(to, from, size);
-	return ret;
+	return ___copy_to_user(to, from, size);
 }
 #define __copy_to_user copy_to_user
 
 unsigned long __must_check ___copy_in_user(void __user *to,
 					   const void __user *from,
 					   unsigned long size);
-unsigned long copy_in_user_fixup(void __user *to, void __user *from,
-				 unsigned long size);
 static inline unsigned long __must_check
 copy_in_user(void __user *to, void __user *from, unsigned long size)
 {
-	unsigned long ret = ___copy_in_user(to, from, size);
-
-	if (unlikely(ret))
-		ret = copy_in_user_fixup(to, from, size);
-	return ret;
+	return ___copy_in_user(to, from, size);
 }
 #define __copy_in_user copy_in_user
 
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index beba6c1..6aa3da1 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -926,48 +926,11 @@
 EXPORT_SYMBOL(tlb_type)
 	.section	".fixup",#alloc,#execinstr
 
-	.globl	__ret_efault, __retl_efault, __ret_one, __retl_one
-ENTRY(__ret_efault)
-	ret
-	 restore %g0, -EFAULT, %o0
-ENDPROC(__ret_efault)
-EXPORT_SYMBOL(__ret_efault)
-
 ENTRY(__retl_efault)
 	retl
 	 mov	-EFAULT, %o0
 ENDPROC(__retl_efault)
 
-ENTRY(__retl_one)
-	retl
-	 mov	1, %o0
-ENDPROC(__retl_one)
-
-ENTRY(__retl_one_fp)
-	VISExitHalf
-	retl
-	 mov	1, %o0
-ENDPROC(__retl_one_fp)
-
-ENTRY(__ret_one_asi)
-	wr	%g0, ASI_AIUS, %asi
-	ret
-	 restore %g0, 1, %o0
-ENDPROC(__ret_one_asi)
-
-ENTRY(__retl_one_asi)
-	wr	%g0, ASI_AIUS, %asi
-	retl
-	 mov	1, %o0
-ENDPROC(__retl_one_asi)
-
-ENTRY(__retl_one_asi_fp)
-	wr	%g0, ASI_AIUS, %asi
-	VISExitHalf
-	retl
-	 mov	1, %o0
-ENDPROC(__retl_one_asi_fp)
-
 ENTRY(__retl_o1)
 	retl
 	 mov	%o1, %o0
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
index 59bbeff..07933b9 100644
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -13,19 +13,30 @@
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
-	u32 val;
 	u32 *insn = (u32 *) (unsigned long) entry->code;
+	u32 val;
 
 	if (type == JUMP_LABEL_JMP) {
 		s32 off = (s32)entry->target - (s32)entry->code;
+		bool use_v9_branch = false;
+
+		BUG_ON(off & 3);
 
 #ifdef CONFIG_SPARC64
-		/* ba,pt %xcc, . + (off << 2) */
-		val = 0x10680000 | ((u32) off >> 2);
-#else
-		/* ba . + (off << 2) */
-		val = 0x10800000 | ((u32) off >> 2);
+		if (off <= 0xfffff && off >= -0x100000)
+			use_v9_branch = true;
 #endif
+		if (use_v9_branch) {
+			/* WDISP19 - target is . + immed << 2 */
+			/* ba,pt %xcc, . + off */
+			val = 0x10680000 | (((u32) off >> 2) & 0x7ffff);
+		} else {
+			/* WDISP22 - target is . + immed << 2 */
+			BUG_ON(off > 0x7fffff);
+			BUG_ON(off < -0x800000);
+			/* ba . + off */
+			val = 0x10800000 | (((u32) off >> 2) & 0x3fffff);
+		}
 	} else {
 		val = 0x01000000;
 	}
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 1122886..8a6982d 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -645,13 +645,20 @@ static void __mark_core_id(struct mdesc_handle *hp, u64 node,
 		cpu_data(*id).core_id = core_id;
 }
 
-static void __mark_sock_id(struct mdesc_handle *hp, u64 node,
-			   int sock_id)
+static void __mark_max_cache_id(struct mdesc_handle *hp, u64 node,
+				int max_cache_id)
 {
 	const u64 *id = mdesc_get_property(hp, node, "id", NULL);
 
-	if (*id < num_possible_cpus())
-		cpu_data(*id).sock_id = sock_id;
+	if (*id < num_possible_cpus()) {
+		cpu_data(*id).max_cache_id = max_cache_id;
+
+		/**
+		 * On systems without explicit socket descriptions socket
+		 * is max_cache_id
+		 */
+		cpu_data(*id).sock_id = max_cache_id;
+	}
 }
 
 static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
@@ -660,10 +667,11 @@ static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
 	find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10);
 }
 
-static void mark_sock_ids(struct mdesc_handle *hp, u64 mp,
-			  int sock_id)
+static void mark_max_cache_ids(struct mdesc_handle *hp, u64 mp,
+			       int max_cache_id)
 {
-	find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10);
+	find_back_node_value(hp, mp, "cpu", __mark_max_cache_id,
+			     max_cache_id, 10);
 }
 
 static void set_core_ids(struct mdesc_handle *hp)
@@ -694,14 +702,15 @@ static void set_core_ids(struct mdesc_handle *hp)
 	}
 }
 
-static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
+static int set_max_cache_ids_by_cache(struct mdesc_handle *hp, int level)
 {
 	u64 mp;
 	int idx = 1;
 	int fnd = 0;
 
-	/* Identify unique sockets by looking for cpus backpointed to by
-	 * shared level n caches.
+	/**
+	 * Identify unique highest level of shared cache by looking for cpus
+	 * backpointed to by shared level N caches.
 	 */
 	mdesc_for_each_node_by_name(hp, mp, "cache") {
 		const u64 *cur_lvl;
@@ -709,8 +718,7 @@ static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
 		cur_lvl = mdesc_get_property(hp, mp, "level", NULL);
 		if (*cur_lvl != level)
 			continue;
-
-		mark_sock_ids(hp, mp, idx);
+		mark_max_cache_ids(hp, mp, idx);
 		idx++;
 		fnd = 1;
 	}
@@ -745,15 +753,17 @@ static void set_sock_ids(struct mdesc_handle *hp)
 {
 	u64 mp;
 
-	/* If machine description exposes sockets data use it.
-	 * Otherwise fallback to use shared L3 or L2 caches.
+	/**
+	 * Find the highest level of shared cache which pre-T7 is also
+	 * the socket.
 	 */
+	if (!set_max_cache_ids_by_cache(hp, 3))
+		set_max_cache_ids_by_cache(hp, 2);
+
+	/* If machine description exposes sockets data use it.*/
 	mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets");
 	if (mp != MDESC_NODE_NULL)
-		return set_sock_ids_by_socket(hp, mp);
-
-	if (!set_sock_ids_by_cache(hp, 3))
-		set_sock_ids_by_cache(hp, 2);
+		set_sock_ids_by_socket(hp, mp);
 }
 
 static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index d3035ba..8182f7c 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -63,9 +63,13 @@ cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
 cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = {
 	[0 ... NR_CPUS-1] = CPU_MASK_NONE };
 
+cpumask_t cpu_core_sib_cache_map[NR_CPUS] __read_mostly = {
+	[0 ... NR_CPUS - 1] = CPU_MASK_NONE };
+
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_SYMBOL(cpu_core_map);
 EXPORT_SYMBOL(cpu_core_sib_map);
+EXPORT_SYMBOL(cpu_core_sib_cache_map);
 
 static cpumask_t smp_commenced_mask;
 
@@ -1265,6 +1269,10 @@ void smp_fill_in_sib_core_maps(void)
 		unsigned int j;
 
 		for_each_present_cpu(j)  {
+			if (cpu_data(i).max_cache_id ==
+			    cpu_data(j).max_cache_id)
+				cpumask_set_cpu(j, &cpu_core_sib_cache_map[i]);
+
 			if (cpu_data(i).sock_id == cpu_data(j).sock_id)
 				cpumask_set_cpu(j, &cpu_core_sib_map[i]);
 		}
diff --git a/arch/sparc/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S
index b7d0bd6..69a439f 100644
--- a/arch/sparc/lib/GENcopy_from_user.S
+++ b/arch/sparc/lib/GENcopy_from_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S
index 780550e..9947427 100644
--- a/arch/sparc/lib/GENcopy_to_user.S
+++ b/arch/sparc/lib/GENcopy_to_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/GENmemcpy.S b/arch/sparc/lib/GENmemcpy.S
index 89358ee..059ea24 100644
--- a/arch/sparc/lib/GENmemcpy.S
+++ b/arch/sparc/lib/GENmemcpy.S
@@ -4,21 +4,18 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #define GLOBAL_SPARE	%g7
 #else
 #define GLOBAL_SPARE	%g5
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -45,6 +42,29 @@
 	.register	%g3,#scratch
 
 	.text
+
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+ENTRY(GEN_retl_o4_1)
+	add	%o4, %o2, %o4
+	retl
+	 add	%o4, 1, %o0
+ENDPROC(GEN_retl_o4_1)
+ENTRY(GEN_retl_g1_8)
+	add	%g1, %o2, %g1
+	retl
+	 add	%g1, 8, %o0
+ENDPROC(GEN_retl_g1_8)
+ENTRY(GEN_retl_o2_4)
+	retl
+	 add	%o2, 4, %o0
+ENDPROC(GEN_retl_o2_4)
+ENTRY(GEN_retl_o2_1)
+	retl
+	 add	%o2, 1, %o0
+ENDPROC(GEN_retl_o2_1)
+#endif
+
 	.align		64
 
 	.globl	FUNC_NAME
@@ -73,8 +93,8 @@
 	sub		%g0, %o4, %o4
 	sub		%o2, %o4, %o2
 1:	subcc		%o4, 1, %o4
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o0))
+	EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o4_1)
+	EX_ST(STORE(stb, %g1, %o0),GEN_retl_o4_1)
 	add		%o1, 1, %o1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
@@ -82,8 +102,8 @@
 	andn		%o2, 0x7, %g1
 	sub		%o2, %g1, %o2
 1:	subcc		%g1, 0x8, %g1
-	EX_LD(LOAD(ldx, %o1, %g2))
-	EX_ST(STORE(stx, %g2, %o0))
+	EX_LD(LOAD(ldx, %o1, %g2),GEN_retl_g1_8)
+	EX_ST(STORE(stx, %g2, %o0),GEN_retl_g1_8)
 	add		%o1, 0x8, %o1
 	bne,pt		%XCC, 1b
 	 add		%o0, 0x8, %o0
@@ -100,8 +120,8 @@
 
 1:
 	subcc		%o2, 4, %o2
-	EX_LD(LOAD(lduw, %o1, %g1))
-	EX_ST(STORE(stw, %g1, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %g1),GEN_retl_o2_4)
+	EX_ST(STORE(stw, %g1, %o1 + %o3),GEN_retl_o2_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -111,8 +131,8 @@
 	.align		32
 90:
 	subcc		%o2, 1, %o2
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o1 + %o3))
+	EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o2_1)
+	EX_ST(STORE(stb, %g1, %o1 + %o3),GEN_retl_o2_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 885f00e..69912d2 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -38,7 +38,7 @@
 lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
 lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
 
-lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
+lib-$(CONFIG_SPARC64) += copy_in_user.o memmove.o
 lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
 
 obj-$(CONFIG_SPARC64) += iomap.o
diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S
index d5242b8..b79a699 100644
--- a/arch/sparc/lib/NG2copy_from_user.S
+++ b/arch/sparc/lib/NG2copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S
index 4e962d9..dcec55f 100644
--- a/arch/sparc/lib/NG2copy_to_user.S
+++ b/arch/sparc/lib/NG2copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index d5f585d..c629dbd 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #define GLOBAL_SPARE	%g7
@@ -32,21 +33,17 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -140,45 +137,110 @@
 	fsrc2		%x6, %f12; \
 	fsrc2		%x7, %f14;
 #define FREG_LOAD_1(base, x0) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0))
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1)
 #define FREG_LOAD_2(base, x0, x1) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_3(base, x0, x1, x2) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_4(base, x0, x1, x2, x3) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD_FP(LOAD(ldd, base + 0x18, %x3));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD_FP(LOAD(ldd, base + 0x20, %x4));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
-	EX_LD_FP(LOAD(ldd, base + 0x28, %x5));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1);
 #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \
-	EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
-	EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
-	EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
-	EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
-	EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
-	EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \
-	EX_LD_FP(LOAD(ldd, base + 0x30, %x6));
+	EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); \
+	EX_LD_FP(LOAD(ldd, base + 0x30, %x6), NG2_retl_o2_plus_g1);
 
 	.register	%g2,#scratch
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_fp:
+	VISExitHalf
+__restore_asi:
+	retl
+	 wr	%g0, ASI_AIUS, %asi
+ENTRY(NG2_retl_o2)
+	ba,pt	%xcc, __restore_asi
+	 mov	%o2, %o0
+ENDPROC(NG2_retl_o2)
+ENTRY(NG2_retl_o2_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 1, %o0
+ENDPROC(NG2_retl_o2_plus_1)
+ENTRY(NG2_retl_o2_plus_4)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 4, %o0
+ENDPROC(NG2_retl_o2_plus_4)
+ENTRY(NG2_retl_o2_plus_8)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 8, %o0
+ENDPROC(NG2_retl_o2_plus_8)
+ENTRY(NG2_retl_o2_plus_o4_plus_1)
+	add	%o4, 1, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_1)
+ENTRY(NG2_retl_o2_plus_o4_plus_8)
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_8)
+ENTRY(NG2_retl_o2_plus_o4_plus_16)
+	add	%o4, 16, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_16)
+ENTRY(NG2_retl_o2_plus_g1_fp)
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_fp)
+ENTRY(NG2_retl_o2_plus_g1_plus_64_fp)
+	add	%g1, 64, %g1
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_plus_64_fp)
+ENTRY(NG2_retl_o2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_plus_1)
+ENTRY(NG2_retl_o2_and_7_plus_o4)
+	and	%o2, 7, %o2
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_and_7_plus_o4)
+ENTRY(NG2_retl_o2_and_7_plus_o4_plus_8)
+	and	%o2, 7, %o2
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG2_retl_o2_and_7_plus_o4_plus_8)
+#endif
+
 	.align		64
 
 	.globl	FUNC_NAME
@@ -230,8 +292,8 @@
 	sub		%g0, %o4, %o4	! bytes to align dst
 	sub		%o2, %o4, %o2
 1:	subcc		%o4, 1, %o4
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o0))
+	EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_o4_plus_1)
+	EX_ST(STORE(stb, %g1, %o0), NG2_retl_o2_plus_o4_plus_1)
 	add		%o1, 1, %o1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
@@ -281,11 +343,11 @@
 	 nop
 	/* fall through for 0 < low bits < 8 */
 110:	sub		%o4, 64, %g2
-	EX_LD_FP(LOAD_BLK(%g2, %f0))
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+	EX_LD_FP(LOAD_BLK(%g2, %f0), NG2_retl_o2_plus_g1)
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -296,10 +358,10 @@
 
 120:	sub		%o4, 56, %g2
 	FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -310,10 +372,10 @@
 
 130:	sub		%o4, 48, %g2
 	FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_6(f20, f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -324,10 +386,10 @@
 
 140:	sub		%o4, 40, %g2
 	FREG_LOAD_5(%g2, f0, f2, f4, f6, f8)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_5(f22, f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -338,10 +400,10 @@
 
 150:	sub		%o4, 32, %g2
 	FREG_LOAD_4(%g2, f0, f2, f4, f6)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_4(f24, f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -352,10 +414,10 @@
 
 160:	sub		%o4, 24, %g2
 	FREG_LOAD_3(%g2, f0, f2, f4)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_3(f26, f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -366,10 +428,10 @@
 
 170:	sub		%o4, 16, %g2
 	FREG_LOAD_2(%g2, f0, f2)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_2(f28, f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -380,10 +442,10 @@
 
 180:	sub		%o4, 8, %g2
 	FREG_LOAD_1(%g2, f0)
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
-	EX_LD_FP(LOAD_BLK(%o4, %f16))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+	EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
 	FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30)
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	FREG_MOVE_1(f30)
 	subcc		%g1, 64, %g1
 	add		%o4, 64, %o4
@@ -393,10 +455,10 @@
 	 nop
 
 190:
-1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+1:	EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
 	subcc		%g1, 64, %g1
-	EX_LD_FP(LOAD_BLK(%o4, %f0))
-	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+	EX_LD_FP(LOAD_BLK(%o4, %f0), NG2_retl_o2_plus_g1_plus_64)
+	EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1_plus_64)
 	add		%o4, 64, %o4
 	bne,pt		%xcc, 1b
 	 LOAD(prefetch, %o4 + 64, #one_read)
@@ -423,28 +485,28 @@
 	andn		%o2, 0xf, %o4
 	and		%o2, 0xf, %o2
 1:	subcc		%o4, 0x10, %o4
-	EX_LD(LOAD(ldx, %o1, %o5))
+	EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_o4_plus_16)
 	add		%o1, 0x08, %o1
-	EX_LD(LOAD(ldx, %o1, %g1))
+	EX_LD(LOAD(ldx, %o1, %g1), NG2_retl_o2_plus_o4_plus_16)
 	sub		%o1, 0x08, %o1
-	EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE))
+	EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_16)
 	add		%o1, 0x8, %o1
-	EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE))
+	EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_8)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x8, %o1
 73:	andcc		%o2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x8, %o2
-	EX_LD(LOAD(ldx, %o1, %o5))
-	EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_8)
+	EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_8)
 	add		%o1, 0x8, %o1
 1:	andcc		%o2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x4, %o2
-	EX_LD(LOAD(lduw, %o1, %o5))
-	EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(lduw, %o1, %o5), NG2_retl_o2_plus_4)
+	EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4)
 	add		%o1, 0x4, %o1
 1:	cmp		%o2, 0
 	be,pt		%XCC, 85f
@@ -460,8 +522,8 @@
 	sub		%o2, %g1, %o2
 
 1:	subcc		%g1, 1, %g1
-	EX_LD(LOAD(ldub, %o1, %o5))
-	EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(ldub, %o1, %o5), NG2_retl_o2_plus_g1_plus_1)
+	EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_g1_plus_1)
 	bgu,pt		%icc, 1b
 	 add		%o1, 1, %o1
 
@@ -477,16 +539,16 @@
 
 8:	mov		64, GLOBAL_SPARE
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1, %g2))
+	EX_LD(LOAD(ldx, %o1, %g2), NG2_retl_o2)
 	sub		GLOBAL_SPARE, %g1, GLOBAL_SPARE
 	andn		%o2, 0x7, %o4
 	sllx		%g2, %g1, %g2
 1:	add		%o1, 0x8, %o1
-	EX_LD(LOAD(ldx, %o1, %g3))
+	EX_LD(LOAD(ldx, %o1, %g3), NG2_retl_o2_and_7_plus_o4)
 	subcc		%o4, 0x8, %o4
 	srlx		%g3, GLOBAL_SPARE, %o5
 	or		%o5, %g2, %o5
-	EX_ST(STORE(stx, %o5, %o0))
+	EX_ST(STORE(stx, %o5, %o0), NG2_retl_o2_and_7_plus_o4_plus_8)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -506,8 +568,8 @@
 
 1:
 	subcc		%o2, 4, %o2
-	EX_LD(LOAD(lduw, %o1, %g1))
-	EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(lduw, %o1, %g1), NG2_retl_o2_plus_4)
+	EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -517,8 +579,8 @@
 	.align		32
 90:
 	subcc		%o2, 1, %o2
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE))
+	EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_1)
+	EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl
diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S
index 2e8ee7a..16a286c 100644
--- a/arch/sparc/lib/NG4copy_from_user.S
+++ b/arch/sparc/lib/NG4copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2012 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x, y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S
index be0bf45..6b0276f 100644
--- a/arch/sparc/lib/NG4copy_to_user.S
+++ b/arch/sparc/lib/NG4copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 2012 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_asi_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 8e13ee1..75bb93b 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #define GLOBAL_SPARE	%g7
@@ -46,22 +47,19 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
-#endif
 
 #ifndef LOAD
 #define LOAD(type,addr,dest)	type [addr], dest
@@ -94,6 +92,158 @@
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_asi_fp:
+	VISExitHalf
+__restore_asi:
+	retl
+	 wr	%g0, ASI_AIUS, %asi
+
+ENTRY(NG4_retl_o2)
+	ba,pt	%xcc, __restore_asi
+	 mov	%o2, %o0
+ENDPROC(NG4_retl_o2)
+ENTRY(NG4_retl_o2_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 1, %o0
+ENDPROC(NG4_retl_o2_plus_1)
+ENTRY(NG4_retl_o2_plus_4)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, 4, %o0
+ENDPROC(NG4_retl_o2_plus_4)
+ENTRY(NG4_retl_o2_plus_o5)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5)
+ENTRY(NG4_retl_o2_plus_o5_plus_4)
+	add	%o5, 4, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_4)
+ENTRY(NG4_retl_o2_plus_o5_plus_8)
+	add	%o5, 8, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_8)
+ENTRY(NG4_retl_o2_plus_o5_plus_16)
+	add	%o5, 16, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_16)
+ENTRY(NG4_retl_o2_plus_o5_plus_24)
+	add	%o5, 24, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_24)
+ENTRY(NG4_retl_o2_plus_o5_plus_32)
+	add	%o5, 32, %o5
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_32)
+ENTRY(NG4_retl_o2_plus_g1)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1)
+ENTRY(NG4_retl_o2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_1)
+ENTRY(NG4_retl_o2_plus_g1_plus_8)
+	add	%g1, 8, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_8)
+ENTRY(NG4_retl_o2_plus_o4)
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4)
+ENTRY(NG4_retl_o2_plus_o4_plus_8)
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8)
+ENTRY(NG4_retl_o2_plus_o4_plus_16)
+	add	%o4, 16, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16)
+ENTRY(NG4_retl_o2_plus_o4_plus_24)
+	add	%o4, 24, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24)
+ENTRY(NG4_retl_o2_plus_o4_plus_32)
+	add	%o4, 32, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32)
+ENTRY(NG4_retl_o2_plus_o4_plus_40)
+	add	%o4, 40, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40)
+ENTRY(NG4_retl_o2_plus_o4_plus_48)
+	add	%o4, 48, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48)
+ENTRY(NG4_retl_o2_plus_o4_plus_56)
+	add	%o4, 56, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56)
+ENTRY(NG4_retl_o2_plus_o4_plus_64)
+	add	%o4, 64, %o4
+	ba,pt	%xcc, __restore_asi
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64)
+ENTRY(NG4_retl_o2_plus_o4_fp)
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_8_fp)
+	add	%o4, 8, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_16_fp)
+	add	%o4, 16, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_24_fp)
+	add	%o4, 24, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_32_fp)
+	add	%o4, 32, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_40_fp)
+	add	%o4, 40, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_48_fp)
+	add	%o4, 48, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_56_fp)
+	add	%o4, 56, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_64_fp)
+	add	%o4, 64, %o4
+	ba,pt	%xcc, __restore_asi_fp
+	 add	%o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64_fp)
+#endif
 	.align		64
 
 	.globl	FUNC_NAME
@@ -124,12 +274,13 @@
 	brz,pt		%g1, 51f
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 1, %o1
 	subcc		%g1, 1, %g1
 	add		%o0, 1, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g2, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
 
 51:	LOAD(prefetch, %o1 + 0x040, #n_reads_strong)
 	LOAD(prefetch, %o1 + 0x080, #n_reads_strong)
@@ -154,43 +305,43 @@
 	brz,pt		%g1, .Llarge_aligned
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g2))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 8, %o1
 	subcc		%g1, 8, %g1
 	add		%o0, 8, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stx, %g2, %o0 - 0x08))
+	 EX_ST(STORE(stx, %g2, %o0 - 0x08), NG4_retl_o2_plus_g1_plus_8)
 
 .Llarge_aligned:
 	/* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */
 	andn		%o2, 0x3f, %o4
 	sub		%o2, %o4, %o2
 
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o4)
 	add		%o1, 0x40, %o1
-	EX_LD(LOAD(ldx, %o1 - 0x38, %g2))
+	EX_LD(LOAD(ldx, %o1 - 0x38, %g2), NG4_retl_o2_plus_o4)
 	subcc		%o4, 0x40, %o4
-	EX_LD(LOAD(ldx, %o1 - 0x30, %g3))
-	EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE))
-	EX_LD(LOAD(ldx, %o1 - 0x20, %o5))
-	EX_ST(STORE_INIT(%g1, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x30, %g3), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD(LOAD(ldx, %o1 - 0x20, %o5), NG4_retl_o2_plus_o4_plus_64)
+	EX_ST(STORE_INIT(%g1, %o0), NG4_retl_o2_plus_o4_plus_64)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g2, %o0))
+	EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_56)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x18, %g2))
-	EX_ST(STORE_INIT(%g3, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x18, %g2), NG4_retl_o2_plus_o4_plus_48)
+	EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_48)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x10, %g3))
-	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x10, %g3), NG4_retl_o2_plus_o4_plus_40)
+	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_40)
 	add		%o0, 0x08, %o0
-	EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE))
-	EX_ST(STORE_INIT(%o5, %o0))
+	EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_32)
+	EX_ST(STORE_INIT(%o5, %o0), NG4_retl_o2_plus_o4_plus_32)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g2, %o0))
+	EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_24)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(%g3, %o0))
+	EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_16)
 	add		%o0, 0x08, %o0
-	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+	EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_8)
 	add		%o0, 0x08, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %o1 + 0x200, #n_reads_strong)
@@ -216,17 +367,17 @@
 	sub		%o2, %o4, %o2
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
-	EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0))
-1:	EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0), NG4_retl_o2_plus_o4)
+1:	EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2), NG4_retl_o2_plus_o4)
 	subcc		%o4, 0x40, %o4
-	EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12))
-	EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12), NG4_retl_o2_plus_o4_plus_64)
+	EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14), NG4_retl_o2_plus_o4_plus_64)
 	faligndata	%f0, %f2, %f16
-	EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0))
+	EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0), NG4_retl_o2_plus_o4_plus_64)
 	faligndata	%f2, %f4, %f18
 	add		%g1, 0x40, %g1
 	faligndata	%f4, %f6, %f20
@@ -235,14 +386,14 @@
 	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE(std, %f16, %o0 + 0x00))
-	EX_ST_FP(STORE(std, %f18, %o0 + 0x08))
-	EX_ST_FP(STORE(std, %f20, %o0 + 0x10))
-	EX_ST_FP(STORE(std, %f22, %o0 + 0x18))
-	EX_ST_FP(STORE(std, %f24, %o0 + 0x20))
-	EX_ST_FP(STORE(std, %f26, %o0 + 0x28))
-	EX_ST_FP(STORE(std, %f28, %o0 + 0x30))
-	EX_ST_FP(STORE(std, %f30, %o0 + 0x38))
+	EX_ST_FP(STORE(std, %f16, %o0 + 0x00), NG4_retl_o2_plus_o4_plus_64)
+	EX_ST_FP(STORE(std, %f18, %o0 + 0x08), NG4_retl_o2_plus_o4_plus_56)
+	EX_ST_FP(STORE(std, %f20, %o0 + 0x10), NG4_retl_o2_plus_o4_plus_48)
+	EX_ST_FP(STORE(std, %f22, %o0 + 0x18), NG4_retl_o2_plus_o4_plus_40)
+	EX_ST_FP(STORE(std, %f24, %o0 + 0x20), NG4_retl_o2_plus_o4_plus_32)
+	EX_ST_FP(STORE(std, %f26, %o0 + 0x28), NG4_retl_o2_plus_o4_plus_24)
+	EX_ST_FP(STORE(std, %f28, %o0 + 0x30), NG4_retl_o2_plus_o4_plus_16)
+	EX_ST_FP(STORE(std, %f30, %o0 + 0x38), NG4_retl_o2_plus_o4_plus_8)
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
@@ -270,37 +421,38 @@
 	andncc		%o2, 0x20 - 1, %o5
 	be,pn		%icc, 2f
 	 sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
-	EX_LD(LOAD(ldx, %o1 + 0x08, %g2))
-	EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE))
-	EX_LD(LOAD(ldx, %o1 + 0x18, %o4))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x08, %g2), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE), NG4_retl_o2_plus_o5)
+	EX_LD(LOAD(ldx, %o1 + 0x18, %o4), NG4_retl_o2_plus_o5)
 	add		%o1, 0x20, %o1
 	subcc		%o5, 0x20, %o5
-	EX_ST(STORE(stx, %g1, %o0 + 0x00))
-	EX_ST(STORE(stx, %g2, %o0 + 0x08))
-	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10))
-	EX_ST(STORE(stx, %o4, %o0 + 0x18))
+	EX_ST(STORE(stx, %g1, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_32)
+	EX_ST(STORE(stx, %g2, %o0 + 0x08), NG4_retl_o2_plus_o5_plus_24)
+	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), NG4_retl_o2_plus_o5_plus_24)
+	EX_ST(STORE(stx, %o4, %o0 + 0x18), NG4_retl_o2_plus_o5_plus_8)
 	bne,pt		%icc, 1b
 	 add		%o0, 0x20, %o0
 2:	andcc		%o2, 0x18, %o5
 	be,pt		%icc, 3f
 	 sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
 	add		%o1, 0x08, %o1
 	add		%o0, 0x08, %o0
 	subcc		%o5, 0x08, %o5
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stx, %g1, %o0 - 0x08))
+	 EX_ST(STORE(stx, %g1, %o0 - 0x08), NG4_retl_o2_plus_o5_plus_8)
 3:	brz,pt		%o2, .Lexit
 	 cmp		%o2, 0x04
 	bl,pn		%icc, .Ltiny
 	 nop
-	EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+	EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2)
 	add		%o1, 0x04, %o1
 	add		%o0, 0x04, %o0
 	subcc		%o2, 0x04, %o2
 	bne,pn		%icc, .Ltiny
-	 EX_ST(STORE(stw, %g1, %o0 - 0x04))
+	 EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_4)
 	ba,a,pt		%icc, .Lexit
 .Lmedium_unaligned:
 	/* First get dest 8 byte aligned.  */
@@ -309,12 +461,12 @@
 	brz,pt		%g1, 2f
 	 sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
 	add		%o1, 1, %o1
 	subcc		%g1, 1, %g1
 	add		%o0, 1, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g2, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
 2:
 	and		%o1, 0x7, %g1
 	brz,pn		%g1, .Lmedium_noprefetch
@@ -322,16 +474,16 @@
 	mov		64, %g2
 	sub		%g2, %g1, %g2
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1 + 0x00, %o4))
+	EX_LD(LOAD(ldx, %o1 + 0x00, %o4), NG4_retl_o2)
 	sllx		%o4, %g1, %o4
 	andn		%o2, 0x08 - 1, %o5
 	sub		%o2, %o5, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x08, %g3))
+1:	EX_LD(LOAD(ldx, %o1 + 0x08, %g3), NG4_retl_o2_plus_o5)
 	add		%o1, 0x08, %o1
 	subcc		%o5, 0x08, %o5
 	srlx		%g3, %g2, GLOBAL_SPARE
 	or		GLOBAL_SPARE, %o4, GLOBAL_SPARE
-	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00))
+	EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_8)
 	add		%o0, 0x08, %o0
 	bne,pt		%icc, 1b
 	 sllx		%g3, %g1, %o4
@@ -342,17 +494,17 @@
 	ba,pt		%icc, .Lsmall_unaligned
 
 .Ltiny:
-	EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+	EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
 	subcc		%o2, 1, %o2
 	be,pn		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x00))
-	EX_LD(LOAD(ldub, %o1 + 0x01, %g1))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x00), NG4_retl_o2_plus_1)
+	EX_LD(LOAD(ldub, %o1 + 0x01, %g1), NG4_retl_o2)
 	subcc		%o2, 1, %o2
 	be,pn		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x01))
-	EX_LD(LOAD(ldub, %o1 + 0x02, %g1))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x01), NG4_retl_o2_plus_1)
+	EX_LD(LOAD(ldub, %o1 + 0x02, %g1), NG4_retl_o2)
 	ba,pt		%icc, .Lexit
-	 EX_ST(STORE(stb, %g1, %o0 + 0x02))
+	 EX_ST(STORE(stb, %g1, %o0 + 0x02), NG4_retl_o2)
 
 .Lsmall:
 	andcc		%g2, 0x3, %g0
@@ -360,22 +512,22 @@
 	 andn		%o2, 0x4 - 1, %o5
 	sub		%o2, %o5, %o2
 1:
-	EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+	EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
 	add		%o1, 0x04, %o1
 	subcc		%o5, 0x04, %o5
 	add		%o0, 0x04, %o0
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stw, %g1, %o0 - 0x04))
+	 EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_o5_plus_4)
 	brz,pt		%o2, .Lexit
 	 nop
 	ba,a,pt		%icc, .Ltiny
 
 .Lsmall_unaligned:
-1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+1:	EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
 	add		%o1, 1, %o1
 	add		%o0, 1, %o0
 	subcc		%o2, 1, %o2
 	bne,pt		%icc, 1b
-	 EX_ST(STORE(stb, %g1, %o0 - 0x01))
+	 EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
 	ba,a,pt		%icc, .Lexit
 	.size		FUNC_NAME, .-FUNC_NAME
diff --git a/arch/sparc/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S
index 5d1e4d1..9cd42fc 100644
--- a/arch/sparc/lib/NGcopy_from_user.S
+++ b/arch/sparc/lib/NGcopy_from_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __ret_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S
index ff630dc..5c358af 100644
--- a/arch/sparc/lib/NGcopy_to_user.S
+++ b/arch/sparc/lib/NGcopy_to_user.S
@@ -3,11 +3,11 @@
  * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __ret_one_asi;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S
index 96a14ca..d88c4ed 100644
--- a/arch/sparc/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/asi.h>
 #include <asm/thread_info.h>
 #define GLOBAL_SPARE	%g7
@@ -27,15 +28,11 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -79,6 +76,92 @@
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_asi:
+	ret
+	wr	%g0, ASI_AIUS, %asi
+	 restore
+ENTRY(NG_ret_i2_plus_i4_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i5, %i0
+ENDPROC(NG_ret_i2_plus_i4_plus_1)
+ENTRY(NG_ret_i2_plus_g1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1)
+ENTRY(NG_ret_i2_plus_g1_minus_8)
+	sub	%g1, 8, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_8)
+ENTRY(NG_ret_i2_plus_g1_minus_16)
+	sub	%g1, 16, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_16)
+ENTRY(NG_ret_i2_plus_g1_minus_24)
+	sub	%g1, 24, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_24)
+ENTRY(NG_ret_i2_plus_g1_minus_32)
+	sub	%g1, 32, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_32)
+ENTRY(NG_ret_i2_plus_g1_minus_40)
+	sub	%g1, 40, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_40)
+ENTRY(NG_ret_i2_plus_g1_minus_48)
+	sub	%g1, 48, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_48)
+ENTRY(NG_ret_i2_plus_g1_minus_56)
+	sub	%g1, 56, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_56)
+ENTRY(NG_ret_i2_plus_i4)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4)
+ENTRY(NG_ret_i2_plus_i4_minus_8)
+	sub	%i4, 8, %i4
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4_minus_8)
+ENTRY(NG_ret_i2_plus_8)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 8, %i0
+ENDPROC(NG_ret_i2_plus_8)
+ENTRY(NG_ret_i2_plus_4)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 4, %i0
+ENDPROC(NG_ret_i2_plus_4)
+ENTRY(NG_ret_i2_plus_1)
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, 1, %i0
+ENDPROC(NG_ret_i2_plus_1)
+ENTRY(NG_ret_i2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_plus_1)
+ENTRY(NG_ret_i2)
+	ba,pt	%xcc, __restore_asi
+	 mov	%i2, %i0
+ENDPROC(NG_ret_i2)
+ENTRY(NG_ret_i2_and_7_plus_i4)
+	and	%i2, 7, %i2
+	ba,pt	%xcc, __restore_asi
+	 add	%i2, %i4, %i0
+ENDPROC(NG_ret_i2_and_7_plus_i4)
+#endif
+
 	.align		64
 
 	.globl	FUNC_NAME
@@ -126,8 +209,8 @@
 	sub		%g0, %i4, %i4	! bytes to align dst
 	sub		%i2, %i4, %i2
 1:	subcc		%i4, 1, %i4
-	EX_LD(LOAD(ldub, %i1, %g1))
-	EX_ST(STORE(stb, %g1, %o0))
+	EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_i4_plus_1)
+	EX_ST(STORE(stb, %g1, %o0), NG_ret_i2_plus_i4_plus_1)
 	add		%i1, 1, %i1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
@@ -160,7 +243,7 @@
 	and		%i4, 0x7, GLOBAL_SPARE
 	sll		GLOBAL_SPARE, 3, GLOBAL_SPARE
 	mov		64, %i5
-	EX_LD(LOAD_TWIN(%i1, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1, %g2, %g3), NG_ret_i2_plus_g1)
 	sub		%i5, GLOBAL_SPARE, %i5
 	mov		16, %o4
 	mov		32, %o5
@@ -178,31 +261,31 @@
 	srlx		WORD3, PRE_SHIFT, TMP; \
 	or		WORD2, TMP, WORD2;
 
-8:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+8:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
 	MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
 	LOAD(prefetch, %i1 + %i3, #one_read)
 
-	EX_ST(STORE_INIT(%g2, %o0 + 0x00))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x08))
+	EX_ST(STORE_INIT(%g2, %o0 + 0x00), NG_ret_i2_plus_g1)
+	EX_ST(STORE_INIT(%g3, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
 
-	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
 	MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o2, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x18))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
 
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%g2, %o0 + 0x20))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x28))
+	EX_ST(STORE_INIT(%g2, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%g3, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
 
-	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
 	MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o2, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 8b
@@ -211,31 +294,31 @@
 	ba,pt		%XCC, 60f
 	 add		%i1, %i4, %i1
 
-9:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+9:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
 	MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
 	LOAD(prefetch, %i1 + %i3, #one_read)
 
-	EX_ST(STORE_INIT(%g3, %o0 + 0x00))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x08))
+	EX_ST(STORE_INIT(%g3, %o0 + 0x00), NG_ret_i2_plus_g1)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
 
-	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
 	MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o3, %o0 + 0x10))
-	EX_ST(STORE_INIT(%g2, %o0 + 0x18))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%g2, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
 
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%g3, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x28))
+	EX_ST(STORE_INIT(%g3, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
 
-	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
 	MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
 
-	EX_ST(STORE_INIT(%o3, %o0 + 0x30))
-	EX_ST(STORE_INIT(%g2, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%g2, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 9b
@@ -249,25 +332,25 @@
 	 * one twin load ahead, then add 8 back into source when
 	 * we finish the loop.
 	 */
-	EX_LD(LOAD_TWIN(%i1, %o4, %o5))
+	EX_LD(LOAD_TWIN(%i1, %o4, %o5), NG_ret_i2_plus_g1)
 	mov	16, %o7
 	mov	32, %g2
 	mov	48, %g3
 	mov	64, %o1
-1:	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1:	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
 	LOAD(prefetch, %i1 + %o1, #one_read)
-	EX_ST(STORE_INIT(%o5, %o0 + 0x00))	! initializes cache line
-	EX_ST(STORE_INIT(%o2, %o0 + 0x08))
-	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o4, %o0 + 0x18))
-	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
-	EX_ST(STORE_INIT(%o5, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x28))
-	EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5))
+	EX_ST(STORE_INIT(%o5, %o0 + 0x00), NG_ret_i2_plus_g1)	! initializes cache line
+	EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o4, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o5, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+	EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5), NG_ret_i2_plus_g1_minus_48)
 	add		%i1, 64, %i1
-	EX_ST(STORE_INIT(%o3, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o4, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o4, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 1b
 	 add		%o0, 64, %o0
@@ -282,20 +365,20 @@
 	mov	32, %g2
 	mov	48, %g3
 	mov	64, %o1
-1:	EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5))
-	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1:	EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5), NG_ret_i2_plus_g1)
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
 	LOAD(prefetch, %i1 + %o1, #one_read)
-	EX_ST(STORE_INIT(%o4, %o0 + 0x00))	! initializes cache line
-	EX_ST(STORE_INIT(%o5, %o0 + 0x08))
-	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x10))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x18))
-	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
+	EX_ST(STORE_INIT(%o4, %o0 + 0x00), NG_ret_i2_plus_g1)	! initializes cache line
+	EX_ST(STORE_INIT(%o5, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
 	add	%i1, 64, %i1
-	EX_ST(STORE_INIT(%o4, %o0 + 0x20))
-	EX_ST(STORE_INIT(%o5, %o0 + 0x28))
-	EX_ST(STORE_INIT(%o2, %o0 + 0x30))
-	EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o4, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+	EX_ST(STORE_INIT(%o5, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+	EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+	EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
 	subcc	%g1, 64, %g1
 	bne,pt	%XCC, 1b
 	 add	%o0, 64, %o0
@@ -321,28 +404,28 @@
 	andn		%i2, 0xf, %i4
 	and		%i2, 0xf, %i2
 1:	subcc		%i4, 0x10, %i4
-	EX_LD(LOAD(ldx, %i1, %o4))
+	EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4)
 	add		%i1, 0x08, %i1
-	EX_LD(LOAD(ldx, %i1, %g1))
+	EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4)
 	sub		%i1, 0x08, %i1
-	EX_ST(STORE(stx, %o4, %i1 + %i3))
+	EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4)
 	add		%i1, 0x8, %i1
-	EX_ST(STORE(stx, %g1, %i1 + %i3))
+	EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8)
 	bgu,pt		%XCC, 1b
 	 add		%i1, 0x8, %i1
 73:	andcc		%i2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%i2, 0x8, %i2
-	EX_LD(LOAD(ldx, %i1, %o4))
-	EX_ST(STORE(stx, %o4, %i1 + %i3))
+	EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_8)
+	EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_8)
 	add		%i1, 0x8, %i1
 1:	andcc		%i2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%i2, 0x4, %i2
-	EX_LD(LOAD(lduw, %i1, %i5))
-	EX_ST(STORE(stw, %i5, %i1 + %i3))
+	EX_LD(LOAD(lduw, %i1, %i5), NG_ret_i2_plus_4)
+	EX_ST(STORE(stw, %i5, %i1 + %i3), NG_ret_i2_plus_4)
 	add		%i1, 0x4, %i1
 1:	cmp		%i2, 0
 	be,pt		%XCC, 85f
@@ -358,8 +441,8 @@
 	sub		%i2, %g1, %i2
 
 1:	subcc		%g1, 1, %g1
-	EX_LD(LOAD(ldub, %i1, %i5))
-	EX_ST(STORE(stb, %i5, %i1 + %i3))
+	EX_LD(LOAD(ldub, %i1, %i5), NG_ret_i2_plus_g1_plus_1)
+	EX_ST(STORE(stb, %i5, %i1 + %i3), NG_ret_i2_plus_g1_plus_1)
 	bgu,pt		%icc, 1b
 	 add		%i1, 1, %i1
 
@@ -375,16 +458,16 @@
 
 8:	mov		64, %i3
 	andn		%i1, 0x7, %i1
-	EX_LD(LOAD(ldx, %i1, %g2))
+	EX_LD(LOAD(ldx, %i1, %g2), NG_ret_i2)
 	sub		%i3, %g1, %i3
 	andn		%i2, 0x7, %i4
 	sllx		%g2, %g1, %g2
 1:	add		%i1, 0x8, %i1
-	EX_LD(LOAD(ldx, %i1, %g3))
+	EX_LD(LOAD(ldx, %i1, %g3), NG_ret_i2_and_7_plus_i4)
 	subcc		%i4, 0x8, %i4
 	srlx		%g3, %i3, %i5
 	or		%i5, %g2, %i5
-	EX_ST(STORE(stx, %i5, %o0))
+	EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -404,8 +487,8 @@
 
 1:
 	subcc		%i2, 4, %i2
-	EX_LD(LOAD(lduw, %i1, %g1))
-	EX_ST(STORE(stw, %g1, %i1 + %i3))
+	EX_LD(LOAD(lduw, %i1, %g1), NG_ret_i2_plus_4)
+	EX_ST(STORE(stw, %g1, %i1 + %i3), NG_ret_i2_plus_4)
 	bgu,pt		%XCC, 1b
 	 add		%i1, 4, %i1
 
@@ -415,8 +498,8 @@
 	.align		32
 90:
 	subcc		%i2, 1, %i2
-	EX_LD(LOAD(ldub, %i1, %g1))
-	EX_ST(STORE(stb, %g1, %i1 + %i3))
+	EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_1)
+	EX_ST(STORE(stb, %g1, %i1 + %i3), NG_ret_i2_plus_1)
 	bgu,pt		%XCC, 90b
 	 add		%i1, 1, %i1
 	ret
diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S
index ecc5692..bb6ff73 100644
--- a/arch/sparc/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S
index 9eea392..ed92ce73 100644
--- a/arch/sparc/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index 97e1b21..4f0d50b 100644
--- a/arch/sparc/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
@@ -5,6 +5,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #include <asm/export.h>
@@ -24,21 +25,17 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -79,53 +76,169 @@
 	faligndata		%f7, %f8, %f60;			\
 	faligndata		%f8, %f9, %f62;
 
-#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt)	\
-	EX_LD_FP(LOAD_BLK(%src, %fdest));				\
-	EX_ST_FP(STORE_BLK(%fsrc, %dest));				\
-	add			%src, 0x40, %src;		\
-	subcc			%len, 0x40, %len;		\
-	be,pn			%xcc, jmptgt;			\
-	 add			%dest, 0x40, %dest;		\
+#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, jmptgt)			\
+	EX_LD_FP(LOAD_BLK(%src, %fdest), U1_gs_80_fp);			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp);			\
+	add			%src, 0x40, %src;			\
+	subcc			%GLOBAL_SPARE, 0x40, %GLOBAL_SPARE;	\
+	be,pn			%xcc, jmptgt;				\
+	 add			%dest, 0x40, %dest;			\
 
-#define LOOP_CHUNK1(src, dest, len, branch_dest)		\
-	MAIN_LOOP_CHUNK(src, dest, f0,  f48, len, branch_dest)
-#define LOOP_CHUNK2(src, dest, len, branch_dest)		\
-	MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest)
-#define LOOP_CHUNK3(src, dest, len, branch_dest)		\
-	MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)
+#define LOOP_CHUNK1(src, dest, branch_dest)		\
+	MAIN_LOOP_CHUNK(src, dest, f0,  f48, branch_dest)
+#define LOOP_CHUNK2(src, dest, branch_dest)		\
+	MAIN_LOOP_CHUNK(src, dest, f16, f48, branch_dest)
+#define LOOP_CHUNK3(src, dest, branch_dest)		\
+	MAIN_LOOP_CHUNK(src, dest, f32, f48, branch_dest)
 
 #define DO_SYNC			membar	#Sync;
 #define STORE_SYNC(dest, fsrc)				\
-	EX_ST_FP(STORE_BLK(%fsrc, %dest));			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp);	\
 	add			%dest, 0x40, %dest;	\
 	DO_SYNC
 
 #define STORE_JUMP(dest, fsrc, target)			\
-	EX_ST_FP(STORE_BLK(%fsrc, %dest));			\
+	EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_40_fp);	\
 	add			%dest, 0x40, %dest;	\
 	ba,pt			%xcc, target;		\
 	 nop;
 
-#define FINISH_VISCHUNK(dest, f0, f1, left)	\
-	subcc			%left, 8, %left;\
-	bl,pn			%xcc, 95f;	\
-	 faligndata		%f0, %f1, %f48;	\
-	EX_ST_FP(STORE(std, %f48, %dest));		\
+#define FINISH_VISCHUNK(dest, f0, f1)			\
+	subcc			%g3, 8, %g3;		\
+	bl,pn			%xcc, 95f;		\
+	 faligndata		%f0, %f1, %f48;		\
+	EX_ST_FP(STORE(std, %f48, %dest), U1_g3_8_fp);	\
 	add			%dest, 8, %dest;
 
-#define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)	\
-	subcc			%left, 8, %left;	\
-	bl,pn			%xcc, 95f;		\
+#define UNEVEN_VISCHUNK_LAST(dest, f0, f1)	\
+	subcc			%g3, 8, %g3;	\
+	bl,pn			%xcc, 95f;	\
 	 fsrc2			%f0, %f1;
 
-#define UNEVEN_VISCHUNK(dest, f0, f1, left)		\
-	UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)	\
+#define UNEVEN_VISCHUNK(dest, f0, f1)		\
+	UNEVEN_VISCHUNK_LAST(dest, f0, f1)	\
 	ba,a,pt			%xcc, 93f;
 
 	.register	%g2,#scratch
 	.register	%g3,#scratch
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+ENTRY(U1_g1_1_fp)
+	VISExitHalf
+	add		%g1, 1, %g1
+	add		%g1, %g2, %g1
+	retl
+	 add		%g1, %o2, %o0
+ENDPROC(U1_g1_1_fp)
+ENTRY(U1_g2_0_fp)
+	VISExitHalf
+	retl
+	 add		%g2, %o2, %o0
+ENDPROC(U1_g2_0_fp)
+ENTRY(U1_g2_8_fp)
+	VISExitHalf
+	add		%g2, 8, %g2
+	retl
+	 add		%g2, %o2, %o0
+ENDPROC(U1_g2_8_fp)
+ENTRY(U1_gs_0_fp)
+	VISExitHalf
+	add		%GLOBAL_SPARE, %g3, %o0
+	retl
+	 add		%o0, %o2, %o0
+ENDPROC(U1_gs_0_fp)
+ENTRY(U1_gs_80_fp)
+	VISExitHalf
+	add		%GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
+	add		%GLOBAL_SPARE, %g3, %o0
+	retl
+	 add		%o0, %o2, %o0
+ENDPROC(U1_gs_80_fp)
+ENTRY(U1_gs_40_fp)
+	VISExitHalf
+	add		%GLOBAL_SPARE, 0x40, %GLOBAL_SPARE
+	add		%GLOBAL_SPARE, %g3, %o0
+	retl
+	 add		%o0, %o2, %o0
+ENDPROC(U1_gs_40_fp)
+ENTRY(U1_g3_0_fp)
+	VISExitHalf
+	retl
+	 add		%g3, %o2, %o0
+ENDPROC(U1_g3_0_fp)
+ENTRY(U1_g3_8_fp)
+	VISExitHalf
+	add		%g3, 8, %g3
+	retl
+	 add		%g3, %o2, %o0
+ENDPROC(U1_g3_8_fp)
+ENTRY(U1_o2_0_fp)
+	VISExitHalf
+	retl
+	 mov		%o2, %o0
+ENDPROC(U1_o2_0_fp)
+ENTRY(U1_o2_1_fp)
+	VISExitHalf
+	retl
+	 add		%o2, 1, %o0
+ENDPROC(U1_o2_1_fp)
+ENTRY(U1_gs_0)
+	VISExitHalf
+	retl
+	 add		%GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0)
+ENTRY(U1_gs_8)
+	VISExitHalf
+	add		%GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+	retl
+	 add		%GLOBAL_SPARE, 0x8, %o0
+ENDPROC(U1_gs_8)
+ENTRY(U1_gs_10)
+	VISExitHalf
+	add		%GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+	retl
+	 add		%GLOBAL_SPARE, 0x10, %o0
+ENDPROC(U1_gs_10)
+ENTRY(U1_o2_0)
+	retl
+	 mov		%o2, %o0
+ENDPROC(U1_o2_0)
+ENTRY(U1_o2_8)
+	retl
+	 add		%o2, 8, %o0
+ENDPROC(U1_o2_8)
+ENTRY(U1_o2_4)
+	retl
+	 add		%o2, 4, %o0
+ENDPROC(U1_o2_4)
+ENTRY(U1_o2_1)
+	retl
+	 add		%o2, 1, %o0
+ENDPROC(U1_o2_1)
+ENTRY(U1_g1_0)
+	retl
+	 add		%g1, %o2, %o0
+ENDPROC(U1_g1_0)
+ENTRY(U1_g1_1)
+	add		%g1, 1, %g1
+	retl
+	 add		%g1, %o2, %o0
+ENDPROC(U1_g1_1)
+ENTRY(U1_gs_0_o2_adj)
+	and		%o2, 7, %o2
+	retl
+	 add		%GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0_o2_adj)
+ENTRY(U1_gs_8_o2_adj)
+	and		%o2, 7, %o2
+	add		%GLOBAL_SPARE, 8, %GLOBAL_SPARE
+	retl
+	 add		%GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_8_o2_adj)
+#endif
+
 	.align		64
 
 	.globl		FUNC_NAME
@@ -167,8 +280,8 @@
 	 and		%g2, 0x38, %g2
 
 1:	subcc		%g1, 0x1, %g1
-	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
-	EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
+	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U1_g1_1_fp)
+	EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE), U1_g1_1_fp)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x1, %o1
 
@@ -179,20 +292,20 @@
 	be,pt		%icc, 3f
 	 alignaddr	%o1, %g0, %o1
 
-	EX_LD_FP(LOAD(ldd, %o1, %f4))
-1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+	EX_LD_FP(LOAD(ldd, %o1, %f4), U1_g2_0_fp)
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U1_g2_0_fp)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f4, %f6, %f0
-	EX_ST_FP(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
 	be,pn		%icc, 3f
 	 add		%o0, 0x8, %o0
 
-	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U1_g2_0_fp)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f6, %f4, %f0
-	EX_ST_FP(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
 	bne,pt		%icc, 1b
 	 add		%o0, 0x8, %o0
 
@@ -215,13 +328,13 @@
 	add		%g1, %GLOBAL_SPARE, %g1
 	subcc		%o2, %g3, %o2
 
-	EX_LD_FP(LOAD_BLK(%o1, %f0))
+	EX_LD_FP(LOAD_BLK(%o1, %f0), U1_gs_0_fp)
 	add		%o1, 0x40, %o1
 	add		%g1, %g3, %g1
-	EX_LD_FP(LOAD_BLK(%o1, %f16))
+	EX_LD_FP(LOAD_BLK(%o1, %f16), U1_gs_0_fp)
 	add		%o1, 0x40, %o1
 	sub		%GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
-	EX_LD_FP(LOAD_BLK(%o1, %f32))
+	EX_LD_FP(LOAD_BLK(%o1, %f32), U1_gs_80_fp)
 	add		%o1, 0x40, %o1
 
 	/* There are 8 instances of the unrolled loop,
@@ -241,11 +354,11 @@
 
 	.align		64
 1:	FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f0, %f2, %f48
 1:	FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
@@ -262,11 +375,11 @@
 	STORE_JUMP(o0, f48, 56f)
 
 1:	FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f2, %f4, %f48
 1:	FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
@@ -283,11 +396,11 @@
 	STORE_JUMP(o0, f48, 57f)
 
 1:	FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f4, %f6, %f48
 1:	FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
@@ -304,11 +417,11 @@
 	STORE_JUMP(o0, f48, 58f)
 
 1:	FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6) 
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f6, %f8, %f48
 1:	FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
@@ -325,11 +438,11 @@
 	STORE_JUMP(o0, f48, 59f)
 
 1:	FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f8, %f10, %f48
 1:	FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
@@ -346,11 +459,11 @@
 	STORE_JUMP(o0, f48, 60f)
 
 1:	FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f10, %f12, %f48
 1:	FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
@@ -367,11 +480,11 @@
 	STORE_JUMP(o0, f48, 61f)
 
 1:	FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f12, %f14, %f48
 1:	FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
@@ -388,11 +501,11 @@
 	STORE_JUMP(o0, f48, 62f)
 
 1:	FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
-	LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+	LOOP_CHUNK1(o1, o0, 1f)
 	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
-	LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+	LOOP_CHUNK2(o1, o0, 2f)
 	FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
-	LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+	LOOP_CHUNK3(o1, o0, 3f)
 	ba,pt		%xcc, 1b+4
 	 faligndata	%f14, %f16, %f48
 1:	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
@@ -408,53 +521,53 @@
 	FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
 	STORE_JUMP(o0, f48, 63f)
 
-40:	FINISH_VISCHUNK(o0, f0,  f2,  g3)
-41:	FINISH_VISCHUNK(o0, f2,  f4,  g3)
-42:	FINISH_VISCHUNK(o0, f4,  f6,  g3)
-43:	FINISH_VISCHUNK(o0, f6,  f8,  g3)
-44:	FINISH_VISCHUNK(o0, f8,  f10, g3)
-45:	FINISH_VISCHUNK(o0, f10, f12, g3)
-46:	FINISH_VISCHUNK(o0, f12, f14, g3)
-47:	UNEVEN_VISCHUNK(o0, f14, f0,  g3)
-48:	FINISH_VISCHUNK(o0, f16, f18, g3)
-49:	FINISH_VISCHUNK(o0, f18, f20, g3)
-50:	FINISH_VISCHUNK(o0, f20, f22, g3)
-51:	FINISH_VISCHUNK(o0, f22, f24, g3)
-52:	FINISH_VISCHUNK(o0, f24, f26, g3)
-53:	FINISH_VISCHUNK(o0, f26, f28, g3)
-54:	FINISH_VISCHUNK(o0, f28, f30, g3)
-55:	UNEVEN_VISCHUNK(o0, f30, f0,  g3)
-56:	FINISH_VISCHUNK(o0, f32, f34, g3)
-57:	FINISH_VISCHUNK(o0, f34, f36, g3)
-58:	FINISH_VISCHUNK(o0, f36, f38, g3)
-59:	FINISH_VISCHUNK(o0, f38, f40, g3)
-60:	FINISH_VISCHUNK(o0, f40, f42, g3)
-61:	FINISH_VISCHUNK(o0, f42, f44, g3)
-62:	FINISH_VISCHUNK(o0, f44, f46, g3)
-63:	UNEVEN_VISCHUNK_LAST(o0, f46, f0,  g3)
+40:	FINISH_VISCHUNK(o0, f0,  f2)
+41:	FINISH_VISCHUNK(o0, f2,  f4)
+42:	FINISH_VISCHUNK(o0, f4,  f6)
+43:	FINISH_VISCHUNK(o0, f6,  f8)
+44:	FINISH_VISCHUNK(o0, f8,  f10)
+45:	FINISH_VISCHUNK(o0, f10, f12)
+46:	FINISH_VISCHUNK(o0, f12, f14)
+47:	UNEVEN_VISCHUNK(o0, f14, f0)
+48:	FINISH_VISCHUNK(o0, f16, f18)
+49:	FINISH_VISCHUNK(o0, f18, f20)
+50:	FINISH_VISCHUNK(o0, f20, f22)
+51:	FINISH_VISCHUNK(o0, f22, f24)
+52:	FINISH_VISCHUNK(o0, f24, f26)
+53:	FINISH_VISCHUNK(o0, f26, f28)
+54:	FINISH_VISCHUNK(o0, f28, f30)
+55:	UNEVEN_VISCHUNK(o0, f30, f0)
+56:	FINISH_VISCHUNK(o0, f32, f34)
+57:	FINISH_VISCHUNK(o0, f34, f36)
+58:	FINISH_VISCHUNK(o0, f36, f38)
+59:	FINISH_VISCHUNK(o0, f38, f40)
+60:	FINISH_VISCHUNK(o0, f40, f42)
+61:	FINISH_VISCHUNK(o0, f42, f44)
+62:	FINISH_VISCHUNK(o0, f44, f46)
+63:	UNEVEN_VISCHUNK_LAST(o0, f46, f0)
 
-93:	EX_LD_FP(LOAD(ldd, %o1, %f2))
+93:	EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp)
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f0, %f2, %f8
-	EX_ST_FP(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
 	bl,pn		%xcc, 95f
 	 add		%o0, 8, %o0
-	EX_LD_FP(LOAD(ldd, %o1, %f0))
+	EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp)
 	add		%o1, 8, %o1
 	subcc		%g3, 8, %g3
 	faligndata	%f2, %f0, %f8
-	EX_ST_FP(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
 	bge,pt		%xcc, 93b
 	 add		%o0, 8, %o0
 
 95:	brz,pt		%o2, 2f
 	 mov		%g1, %o1
 
-1:	EX_LD_FP(LOAD(ldub, %o1, %o3))
+1:	EX_LD_FP(LOAD(ldub, %o1, %o3), U1_o2_0_fp)
 	add		%o1, 1, %o1
 	subcc		%o2, 1, %o2
-	EX_ST_FP(STORE(stb, %o3, %o0))
+	EX_ST_FP(STORE(stb, %o3, %o0), U1_o2_1_fp)
 	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 
@@ -470,27 +583,27 @@
 
 72:	andn		%o2, 0xf, %GLOBAL_SPARE
 	and		%o2, 0xf, %o2
-1:	EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
-	EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
+1:	EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U1_gs_0)
+	EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U1_gs_0)
 	subcc		%GLOBAL_SPARE, 0x10, %GLOBAL_SPARE
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U1_gs_10)
 	add		%o1, 0x8, %o1
-	EX_ST(STORE(stx, %g1, %o1 + %o3))
+	EX_ST(STORE(stx, %g1, %o1 + %o3), U1_gs_8)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x8, %o1
 73:	andcc		%o2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
-	EX_LD(LOAD(ldx, %o1, %o5))
+	EX_LD(LOAD(ldx, %o1, %o5), U1_o2_0)
 	sub		%o2, 0x8, %o2
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U1_o2_8)
 	add		%o1, 0x8, %o1
 1:	andcc		%o2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
-	EX_LD(LOAD(lduw, %o1, %o5))
+	EX_LD(LOAD(lduw, %o1, %o5), U1_o2_0)
 	sub		%o2, 0x4, %o2
-	EX_ST(STORE(stw, %o5, %o1 + %o3))
+	EX_ST(STORE(stw, %o5, %o1 + %o3), U1_o2_4)
 	add		%o1, 0x4, %o1
 1:	cmp		%o2, 0
 	be,pt		%XCC, 85f
@@ -504,9 +617,9 @@
 	 sub		%g0, %g1, %g1
 	sub		%o2, %g1, %o2
 
-1:	EX_LD(LOAD(ldub, %o1, %o5))
+1:	EX_LD(LOAD(ldub, %o1, %o5), U1_g1_0)
 	subcc		%g1, 1, %g1
-	EX_ST(STORE(stb, %o5, %o1 + %o3))
+	EX_ST(STORE(stb, %o5, %o1 + %o3), U1_g1_1)
 	bgu,pt		%icc, 1b
 	 add		%o1, 1, %o1
 
@@ -522,16 +635,16 @@
 
 8:	mov		64, %o3
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1, %g2))
+	EX_LD(LOAD(ldx, %o1, %g2), U1_o2_0)
 	sub		%o3, %g1, %o3
 	andn		%o2, 0x7, %GLOBAL_SPARE
 	sllx		%g2, %g1, %g2
-1:	EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1:	EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U1_gs_0_o2_adj)
 	subcc		%GLOBAL_SPARE, 0x8, %GLOBAL_SPARE
 	add		%o1, 0x8, %o1
 	srlx		%g3, %o3, %o5
 	or		%o5, %g2, %o5
-	EX_ST(STORE(stx, %o5, %o0))
+	EX_ST(STORE(stx, %o5, %o0), U1_gs_8_o2_adj)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -549,9 +662,9 @@
 	bne,pn		%XCC, 90f
 	 sub		%o0, %o1, %o3
 
-1:	EX_LD(LOAD(lduw, %o1, %g1))
+1:	EX_LD(LOAD(lduw, %o1, %g1), U1_o2_0)
 	subcc		%o2, 4, %o2
-	EX_ST(STORE(stw, %g1, %o1 + %o3))
+	EX_ST(STORE(stw, %g1, %o1 + %o3), U1_o2_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -559,9 +672,9 @@
 	 mov		EX_RETVAL(%o4), %o0
 
 	.align		32
-90:	EX_LD(LOAD(ldub, %o1, %g1))
+90:	EX_LD(LOAD(ldub, %o1, %g1), U1_o2_0)
 	subcc		%o2, 1, %o2
-	EX_ST(STORE(stb, %g1, %o1 + %o3))
+	EX_ST(STORE(stb, %g1, %o1 + %o3), U1_o2_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl
diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S
index 88ad73d..db73010 100644
--- a/arch/sparc/lib/U3copy_from_user.S
+++ b/arch/sparc/lib/U3copy_from_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_LD(x)		\
+#define EX_LD(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_LD_FP(x)		\
+#define EX_LD_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S
index 845139d..c4ee858 100644
--- a/arch/sparc/lib/U3copy_to_user.S
+++ b/arch/sparc/lib/U3copy_to_user.S
@@ -3,19 +3,19 @@
  * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
  */
 
-#define EX_ST(x)		\
+#define EX_ST(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, y;		\
 	.text;			\
 	.align 4;
 
-#define EX_ST_FP(x)		\
+#define EX_ST_FP(x,y)		\
 98:	x;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one_fp;\
+	.word 98b, y##_fp;	\
 	.text;			\
 	.align 4;
 
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 491ee69..54f9870 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -4,6 +4,7 @@
  */
 
 #ifdef __KERNEL__
+#include <linux/linkage.h>
 #include <asm/visasm.h>
 #include <asm/asi.h>
 #define GLOBAL_SPARE	%g7
@@ -22,21 +23,17 @@
 #endif
 
 #ifndef EX_LD
-#define EX_LD(x)	x
+#define EX_LD(x,y)	x
 #endif
 #ifndef EX_LD_FP
-#define EX_LD_FP(x)	x
+#define EX_LD_FP(x,y)	x
 #endif
 
 #ifndef EX_ST
-#define EX_ST(x)	x
+#define EX_ST(x,y)	x
 #endif
 #ifndef EX_ST_FP
-#define EX_ST_FP(x)	x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x)	x
+#define EX_ST_FP(x,y)	x
 #endif
 
 #ifndef LOAD
@@ -77,6 +74,87 @@
 	 */
 
 	.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x)	x
+__restore_fp:
+	VISExitHalf
+	retl
+	 nop
+ENTRY(U3_retl_o2_plus_g2_plus_g1_plus_1_fp)
+	add	%g1, 1, %g1
+	add	%g2, %g1, %g2
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_plus_g1_plus_1_fp)
+ENTRY(U3_retl_o2_plus_g2_fp)
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_fp)
+ENTRY(U3_retl_o2_plus_g2_plus_8_fp)
+	add	%g2, 8, %g2
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_plus_8_fp)
+ENTRY(U3_retl_o2)
+	retl
+	 mov	%o2, %o0
+ENDPROC(U3_retl_o2)
+ENTRY(U3_retl_o2_plus_1)
+	retl
+	 add	%o2, 1, %o0
+ENDPROC(U3_retl_o2_plus_1)
+ENTRY(U3_retl_o2_plus_4)
+	retl
+	 add	%o2, 4, %o0
+ENDPROC(U3_retl_o2_plus_4)
+ENTRY(U3_retl_o2_plus_8)
+	retl
+	 add	%o2, 8, %o0
+ENDPROC(U3_retl_o2_plus_8)
+ENTRY(U3_retl_o2_plus_g1_plus_1)
+	add	%g1, 1, %g1
+	retl
+	 add	%o2, %g1, %o0
+ENDPROC(U3_retl_o2_plus_g1_plus_1)
+ENTRY(U3_retl_o2_fp)
+	ba,pt	%xcc, __restore_fp
+	 mov	%o2, %o0
+ENDPROC(U3_retl_o2_fp)
+ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp)
+	sll	%o3, 6, %o3
+	add	%o3, 0x80, %o3
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %o3, %o0
+ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp)
+ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp)
+	sll	%o3, 6, %o3
+	add	%o3, 0x40, %o3
+	ba,pt	%xcc, __restore_fp
+	 add	%o2, %o3, %o0
+ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp)
+ENTRY(U3_retl_o2_plus_GS_plus_0x10)
+	add	GLOBAL_SPARE, 0x10, GLOBAL_SPARE
+	retl
+	 add	%o2, GLOBAL_SPARE, %o0
+ENDPROC(U3_retl_o2_plus_GS_plus_0x10)
+ENTRY(U3_retl_o2_plus_GS_plus_0x08)
+	add	GLOBAL_SPARE, 0x08, GLOBAL_SPARE
+	retl
+	 add	%o2, GLOBAL_SPARE, %o0
+ENDPROC(U3_retl_o2_plus_GS_plus_0x08)
+ENTRY(U3_retl_o2_and_7_plus_GS)
+	and	%o2, 7, %o2
+	retl
+	 add	%o2, GLOBAL_SPARE, %o2
+ENDPROC(U3_retl_o2_and_7_plus_GS)
+ENTRY(U3_retl_o2_and_7_plus_GS_plus_8)
+	add	GLOBAL_SPARE, 8, GLOBAL_SPARE
+	and	%o2, 7, %o2
+	retl
+	 add	%o2, GLOBAL_SPARE, %o2
+ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8)
+#endif
+
 	.align		64
 
 	/* The cheetah's flexible spine, oversized liver, enlarged heart,
@@ -126,8 +204,8 @@
 	 and		%g2, 0x38, %g2
 
 1:	subcc		%g1, 0x1, %g1
-	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
-	EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE))
+	EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U3_retl_o2_plus_g2_plus_g1_plus_1)
+	EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE), U3_retl_o2_plus_g2_plus_g1_plus_1)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x1, %o1
 
@@ -138,20 +216,20 @@
 	be,pt		%icc, 3f
 	 alignaddr	%o1, %g0, %o1
 
-	EX_LD_FP(LOAD(ldd, %o1, %f4))
-1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+	EX_LD_FP(LOAD(ldd, %o1, %f4), U3_retl_o2_plus_g2)
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U3_retl_o2_plus_g2)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f4, %f6, %f0
-	EX_ST_FP(STORE(std, %f0, %o0))
+	EX_ST_FP(STORE(std, %f0, %o0), U3_retl_o2_plus_g2_plus_8)
 	be,pn		%icc, 3f
 	 add		%o0, 0x8, %o0
 
-	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U3_retl_o2_plus_g2)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f6, %f4, %f2
-	EX_ST_FP(STORE(std, %f2, %o0))
+	EX_ST_FP(STORE(std, %f2, %o0), U3_retl_o2_plus_g2_plus_8)
 	bne,pt		%icc, 1b
 	 add		%o0, 0x8, %o0
 
@@ -161,25 +239,25 @@
 	LOAD(prefetch, %o1 + 0x080, #one_read)
 	LOAD(prefetch, %o1 + 0x0c0, #one_read)
 	LOAD(prefetch, %o1 + 0x100, #one_read)
-	EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0), U3_retl_o2)
 	LOAD(prefetch, %o1 + 0x140, #one_read)
-	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2)
 	LOAD(prefetch, %o1 + 0x180, #one_read)
-	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2)
 	LOAD(prefetch, %o1 + 0x1c0, #one_read)
 	faligndata	%f0, %f2, %f16
-	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2)
 	faligndata	%f2, %f4, %f18
-	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2)
 	faligndata	%f4, %f6, %f20
-	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2)
 	faligndata	%f6, %f8, %f22
 
-	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2)
 	faligndata	%f8, %f10, %f24
-	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2)
 	faligndata	%f10, %f12, %f26
-	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2)
 
 	subcc		GLOBAL_SPARE, 0x80, GLOBAL_SPARE
 	add		%o1, 0x40, %o1
@@ -190,26 +268,26 @@
 
 	.align		64
 1:
-	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	faligndata	%f12, %f14, %f28
-	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE_BLK(%f16, %o0))
-	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f0, %f2, %f16
 	add		%o0, 0x40, %o0
 
-	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f2, %f4, %f18
-	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f4, %f6, %f20
-	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	subcc		%o3, 0x01, %o3
 	faligndata	%f6, %f8, %f22
-	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 
 	faligndata	%f8, %f10, %f24
-	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	LOAD(prefetch, %o1 + 0x1c0, #one_read)
 	faligndata	%f10, %f12, %f26
 	bg,pt		%XCC, 1b
@@ -217,29 +295,29 @@
 
 	/* Finally we copy the last full 64-byte block. */
 2:
-	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	faligndata	%f12, %f14, %f28
-	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80)
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE_BLK(%f16, %o0))
-	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+	EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
+	EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f0, %f2, %f16
-	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f2, %f4, %f18
-	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f4, %f6, %f20
-	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f6, %f8, %f22
-	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	faligndata	%f8, %f10, %f24
 	cmp		%g1, 0
 	be,pt		%XCC, 1f
 	 add		%o0, 0x40, %o0
-	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 1:	faligndata	%f10, %f12, %f26
 	faligndata	%f12, %f14, %f28
 	faligndata	%f14, %f0, %f30
-	EX_ST_FP(STORE_BLK(%f16, %o0))
+	EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x40)
 	add		%o0, 0x40, %o0
 	add		%o1, 0x40, %o1
 	membar		#Sync
@@ -259,20 +337,20 @@
 
 	sub		%o2, %g2, %o2
 	be,a,pt		%XCC, 1f
-	 EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0))
+	 EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0), U3_retl_o2_plus_g2)
 
-1:	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2))
+1:	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2), U3_retl_o2_plus_g2)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f0, %f2, %f8
-	EX_ST_FP(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8)
 	be,pn		%XCC, 2f
 	 add		%o0, 0x8, %o0
-	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0))
+	EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0), U3_retl_o2_plus_g2)
 	add		%o1, 0x8, %o1
 	subcc		%g2, 0x8, %g2
 	faligndata	%f2, %f0, %f8
-	EX_ST_FP(STORE(std, %f8, %o0))
+	EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8)
 	bne,pn		%XCC, 1b
 	 add		%o0, 0x8, %o0
 
@@ -292,30 +370,33 @@
 	 andcc		%o2, 0x8, %g0
 	be,pt		%icc, 1f
 	 nop
-	EX_LD(LOAD(ldx, %o1, %o5))
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2)
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2)
 	add		%o1, 0x8, %o1
+	sub		%o2, 8, %o2
 
 1:	andcc		%o2, 0x4, %g0
 	be,pt		%icc, 1f
 	 nop
-	EX_LD(LOAD(lduw, %o1, %o5))
-	EX_ST(STORE(stw, %o5, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2)
+	EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2)
 	add		%o1, 0x4, %o1
+	sub		%o2, 4, %o2
 
 1:	andcc		%o2, 0x2, %g0
 	be,pt		%icc, 1f
 	 nop
-	EX_LD(LOAD(lduh, %o1, %o5))
-	EX_ST(STORE(sth, %o5, %o1 + %o3))
+	EX_LD(LOAD(lduh, %o1, %o5), U3_retl_o2)
+	EX_ST(STORE(sth, %o5, %o1 + %o3), U3_retl_o2)
 	add		%o1, 0x2, %o1
+	sub		%o2, 2, %o2
 
 1:	andcc		%o2, 0x1, %g0
 	be,pt		%icc, 85f
 	 nop
-	EX_LD(LOAD(ldub, %o1, %o5))
+	EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2)
 	ba,pt		%xcc, 85f
-	 EX_ST(STORE(stb, %o5, %o1 + %o3))
+	 EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2)
 
 	.align		64
 70: /* 16 < len <= 64 */
@@ -326,26 +407,26 @@
 	andn		%o2, 0xf, GLOBAL_SPARE
 	and		%o2, 0xf, %o2
 1:	subcc		GLOBAL_SPARE, 0x10, GLOBAL_SPARE
-	EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
-	EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U3_retl_o2_plus_GS_plus_0x10)
+	EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U3_retl_o2_plus_GS_plus_0x10)
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x10)
 	add		%o1, 0x8, %o1
-	EX_ST(STORE(stx, %g1, %o1 + %o3))
+	EX_ST(STORE(stx, %g1, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x08)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 0x8, %o1
 73:	andcc		%o2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x8, %o2
-	EX_LD(LOAD(ldx, %o1, %o5))
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2_plus_8)
+	EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_8)
 	add		%o1, 0x8, %o1
 1:	andcc		%o2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x4, %o2
-	EX_LD(LOAD(lduw, %o1, %o5))
-	EX_ST(STORE(stw, %o5, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2_plus_4)
+	EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2_plus_4)
 	add		%o1, 0x4, %o1
 1:	cmp		%o2, 0
 	be,pt		%XCC, 85f
@@ -361,8 +442,8 @@
 	sub		%o2, %g1, %o2
 
 1:	subcc		%g1, 1, %g1
-	EX_LD(LOAD(ldub, %o1, %o5))
-	EX_ST(STORE(stb, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2_plus_g1_plus_1)
+	EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2_plus_g1_plus_1)
 	bgu,pt		%icc, 1b
 	 add		%o1, 1, %o1
 
@@ -378,16 +459,16 @@
 
 8:	mov		64, %o3
 	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1, %g2))
+	EX_LD(LOAD(ldx, %o1, %g2), U3_retl_o2)
 	sub		%o3, %g1, %o3
 	andn		%o2, 0x7, GLOBAL_SPARE
 	sllx		%g2, %g1, %g2
-1:	EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1:	EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U3_retl_o2_and_7_plus_GS)
 	subcc		GLOBAL_SPARE, 0x8, GLOBAL_SPARE
 	add		%o1, 0x8, %o1
 	srlx		%g3, %o3, %o5
 	or		%o5, %g2, %o5
-	EX_ST(STORE(stx, %o5, %o0))
+	EX_ST(STORE(stx, %o5, %o0), U3_retl_o2_and_7_plus_GS_plus_8)
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
@@ -407,8 +488,8 @@
 
 1:
 	subcc		%o2, 4, %o2
-	EX_LD(LOAD(lduw, %o1, %g1))
-	EX_ST(STORE(stw, %g1, %o1 + %o3))
+	EX_LD(LOAD(lduw, %o1, %g1), U3_retl_o2_plus_4)
+	EX_ST(STORE(stw, %g1, %o1 + %o3), U3_retl_o2_plus_4)
 	bgu,pt		%XCC, 1b
 	 add		%o1, 4, %o1
 
@@ -418,8 +499,8 @@
 	.align		32
 90:
 	subcc		%o2, 1, %o2
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o1 + %o3))
+	EX_LD(LOAD(ldub, %o1, %g1), U3_retl_o2_plus_1)
+	EX_ST(STORE(stb, %g1, %o1 + %o3), U3_retl_o2_plus_1)
 	bgu,pt		%XCC, 90b
 	 add		%o1, 1, %o1
 	retl
diff --git a/arch/sparc/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S
index 482de09..0252b21 100644
--- a/arch/sparc/lib/copy_in_user.S
+++ b/arch/sparc/lib/copy_in_user.S
@@ -9,18 +9,33 @@
 
 #define XCC xcc
 
-#define EX(x,y)			\
+#define EX(x,y,z)		\
 98:	x,y;			\
 	.section __ex_table,"a";\
 	.align 4;		\
-	.word 98b, __retl_one;	\
+	.word 98b, z;		\
 	.text;			\
 	.align 4;
 
+#define EX_O4(x,y) EX(x,y,__retl_o4_plus_8)
+#define EX_O2_4(x,y) EX(x,y,__retl_o2_plus_4)
+#define EX_O2_1(x,y) EX(x,y,__retl_o2_plus_1)
+
 	.register	%g2,#scratch
 	.register	%g3,#scratch
 
 	.text
+__retl_o4_plus_8:
+	add	%o4, %o2, %o4
+	retl
+	 add	%o4, 8, %o0
+__retl_o2_plus_4:
+	retl
+	 add	%o2, 4, %o0
+__retl_o2_plus_1:
+	retl
+	 add	%o2, 1, %o0
+
 	.align	32
 
 	/* Don't try to get too fancy here, just nice and
@@ -45,8 +60,8 @@
 	andn		%o2, 0x7, %o4
 	and		%o2, 0x7, %o2
 1:	subcc		%o4, 0x8, %o4
-	EX(ldxa [%o1] %asi, %o5)
-	EX(stxa %o5, [%o0] %asi)
+	EX_O4(ldxa [%o1] %asi, %o5)
+	EX_O4(stxa %o5, [%o0] %asi)
 	add		%o1, 0x8, %o1
 	bgu,pt		%XCC, 1b
 	 add		%o0, 0x8, %o0
@@ -54,8 +69,8 @@
 	be,pt		%XCC, 1f
 	 nop
 	sub		%o2, 0x4, %o2
-	EX(lduwa [%o1] %asi, %o5)
-	EX(stwa %o5, [%o0] %asi)
+	EX_O2_4(lduwa [%o1] %asi, %o5)
+	EX_O2_4(stwa %o5, [%o0] %asi)
 	add		%o1, 0x4, %o1
 	add		%o0, 0x4, %o0
 1:	cmp		%o2, 0
@@ -71,8 +86,8 @@
 
 82:
 	subcc		%o2, 4, %o2
-	EX(lduwa [%o1] %asi, %g1)
-	EX(stwa %g1, [%o0] %asi)
+	EX_O2_4(lduwa [%o1] %asi, %g1)
+	EX_O2_4(stwa %g1, [%o0] %asi)
 	add		%o1, 4, %o1
 	bgu,pt		%XCC, 82b
 	 add		%o0, 4, %o0
@@ -83,8 +98,8 @@
 	.align	32
 90:
 	subcc		%o2, 1, %o2
-	EX(lduba [%o1] %asi, %g1)
-	EX(stba %g1, [%o0] %asi)
+	EX_O2_1(lduba [%o1] %asi, %g1)
+	EX_O2_1(stba %g1, [%o0] %asi)
 	add		%o1, 1, %o1
 	bgu,pt		%XCC, 90b
 	 add		%o0, 1, %o0
diff --git a/arch/sparc/lib/user_fixup.c b/arch/sparc/lib/user_fixup.c
deleted file mode 100644
index ac96ae2..0000000
--- a/arch/sparc/lib/user_fixup.c
+++ /dev/null
@@ -1,71 +0,0 @@
-/* user_fixup.c: Fix up user copy faults.
- *
- * Copyright (C) 2004 David S. Miller <davem@redhat.com>
- */
-
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/module.h>
-
-#include <asm/uaccess.h>
-
-/* Calculating the exact fault address when using
- * block loads and stores can be very complicated.
- *
- * Instead of trying to be clever and handling all
- * of the cases, just fix things up simply here.
- */
-
-static unsigned long compute_size(unsigned long start, unsigned long size, unsigned long *offset)
-{
-	unsigned long fault_addr = current_thread_info()->fault_address;
-	unsigned long end = start + size;
-
-	if (fault_addr < start || fault_addr >= end) {
-		*offset = 0;
-	} else {
-		*offset = fault_addr - start;
-		size = end - fault_addr;
-	}
-	return size;
-}
-
-unsigned long copy_from_user_fixup(void *to, const void __user *from, unsigned long size)
-{
-	unsigned long offset;
-
-	size = compute_size((unsigned long) from, size, &offset);
-	if (likely(size))
-		memset(to + offset, 0, size);
-
-	return size;
-}
-EXPORT_SYMBOL(copy_from_user_fixup);
-
-unsigned long copy_to_user_fixup(void __user *to, const void *from, unsigned long size)
-{
-	unsigned long offset;
-
-	return compute_size((unsigned long) to, size, &offset);
-}
-EXPORT_SYMBOL(copy_to_user_fixup);
-
-unsigned long copy_in_user_fixup(void __user *to, void __user *from, unsigned long size)
-{
-	unsigned long fault_addr = current_thread_info()->fault_address;
-	unsigned long start = (unsigned long) to;
-	unsigned long end = start + size;
-
-	if (fault_addr >= start && fault_addr < end)
-		return end - fault_addr;
-
-	start = (unsigned long) from;
-	end = start + size;
-	if (fault_addr >= start && fault_addr < end)
-		return end - fault_addr;
-
-	return size;
-}
-EXPORT_SYMBOL(copy_in_user_fixup);
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index f2b7711..e20fbba 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -27,6 +27,20 @@ static inline int tag_compare(unsigned long tag, unsigned long vaddr)
 	return (tag == (vaddr >> 22));
 }
 
+static void flush_tsb_kernel_range_scan(unsigned long start, unsigned long end)
+{
+	unsigned long idx;
+
+	for (idx = 0; idx < KERNEL_TSB_NENTRIES; idx++) {
+		struct tsb *ent = &swapper_tsb[idx];
+		unsigned long match = idx << 13;
+
+		match |= (ent->tag << 22);
+		if (match >= start && match < end)
+			ent->tag = (1UL << TSB_TAG_INVALID_BIT);
+	}
+}
+
 /* TSB flushes need only occur on the processor initiating the address
  * space modification, not on each cpu the address space has run on.
  * Only the TLB flush needs that treatment.
@@ -36,6 +50,9 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
 {
 	unsigned long v;
 
+	if ((end - start) >> PAGE_SHIFT >= 2 * KERNEL_TSB_NENTRIES)
+		return flush_tsb_kernel_range_scan(start, end);
+
 	for (v = start; v < end; v += PAGE_SIZE) {
 		unsigned long hash = tsb_hash(v, PAGE_SHIFT,
 					      KERNEL_TSB_NENTRIES);
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index b4f4733..5d2fd6c 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -30,7 +30,7 @@
 	.text
 	.align		32
 	.globl		__flush_tlb_mm
-__flush_tlb_mm:		/* 18 insns */
+__flush_tlb_mm:		/* 19 insns */
 	/* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */
 	ldxa		[%o1] ASI_DMMU, %g2
 	cmp		%g2, %o0
@@ -81,7 +81,7 @@
 
 	.align		32
 	.globl		__flush_tlb_pending
-__flush_tlb_pending:	/* 26 insns */
+__flush_tlb_pending:	/* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	rdpr		%pstate, %g7
 	sllx		%o1, 3, %o1
@@ -113,12 +113,14 @@
 
 	.align		32
 	.globl		__flush_tlb_kernel_range
-__flush_tlb_kernel_range:	/* 16 insns */
+__flush_tlb_kernel_range:	/* 31 insns */
 	/* %o0=start, %o1=end */
 	cmp		%o0, %o1
 	be,pn		%xcc, 2f
+	 sub		%o1, %o0, %o3
+	srlx		%o3, 18, %o4
+	brnz,pn		%o4, __spitfire_flush_tlb_kernel_range_slow
 	 sethi		%hi(PAGE_SIZE), %o4
-	sub		%o1, %o0, %o3
 	sub		%o3, %o4, %o3
 	or		%o0, 0x20, %o0		! Nucleus
 1:	stxa		%g0, [%o0 + %o3] ASI_DMMU_DEMAP
@@ -131,6 +133,41 @@
 	retl
 	 nop
 	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+__spitfire_flush_tlb_kernel_range_slow:
+	mov		63 * 8, %o4
+1:	ldxa		[%o4] ASI_ITLB_DATA_ACCESS, %o3
+	andcc		%o3, 0x40, %g0			/* _PAGE_L_4U */
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %o3
+	stxa		%g0, [%o3] ASI_IMMU
+	stxa		%g0, [%o4] ASI_ITLB_DATA_ACCESS
+	membar		#Sync
+2:	ldxa		[%o4] ASI_DTLB_DATA_ACCESS, %o3
+	andcc		%o3, 0x40, %g0
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %o3
+	stxa		%g0, [%o3] ASI_DMMU
+	stxa		%g0, [%o4] ASI_DTLB_DATA_ACCESS
+	membar		#Sync
+2:	sub		%o4, 8, %o4
+	brgez,pt	%o4, 1b
+	 nop
+	retl
+	 nop
 
 __spitfire_flush_tlb_mm_slow:
 	rdpr		%pstate, %g1
@@ -285,6 +322,40 @@
 	retl
 	 wrpr		%g7, 0x0, %pstate
 
+__cheetah_flush_tlb_kernel_range:	/* 31 insns */
+	/* %o0=start, %o1=end */
+	cmp		%o0, %o1
+	be,pn		%xcc, 2f
+	 sub		%o1, %o0, %o3
+	srlx		%o3, 18, %o4
+	brnz,pn		%o4, 3f
+	 sethi		%hi(PAGE_SIZE), %o4
+	sub		%o3, %o4, %o3
+	or		%o0, 0x20, %o0		! Nucleus
+1:	stxa		%g0, [%o0 + %o3] ASI_DMMU_DEMAP
+	stxa		%g0, [%o0 + %o3] ASI_IMMU_DEMAP
+	membar		#Sync
+	brnz,pt		%o3, 1b
+	 sub		%o3, %o4, %o3
+2:	sethi		%hi(KERNBASE), %o3
+	flush		%o3
+	retl
+	 nop
+3:	mov		0x80, %o4
+	stxa		%g0, [%o4] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g0, [%o4] ASI_IMMU_DEMAP
+	membar		#Sync
+	retl
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
 #ifdef DCACHE_ALIASING_POSSIBLE
 __cheetah_flush_dcache_page: /* 11 insns */
 	sethi		%hi(PAGE_OFFSET), %g1
@@ -309,19 +380,28 @@
 	ret
 	 restore
 
-__hypervisor_flush_tlb_mm: /* 10 insns */
+__hypervisor_flush_tlb_mm: /* 19 insns */
 	mov		%o0, %o2	/* ARG2: mmu context */
 	mov		0, %o0		/* ARG0: CPU lists unimplemented */
 	mov		0, %o1		/* ARG1: CPU lists unimplemented */
 	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
 	mov		HV_FAST_MMU_DEMAP_CTX, %o5
 	ta		HV_FAST_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_FAST_MMU_DEMAP_CTX, %o1
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o5
+	jmpl		%o5 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
-__hypervisor_flush_tlb_page: /* 11 insns */
+__hypervisor_flush_tlb_page: /* 22 insns */
 	/* %o0 = context, %o1 = vaddr */
 	mov		%o0, %g2
 	mov		%o1, %o0              /* ARG0: vaddr + IMMU-bit */
@@ -330,12 +410,23 @@
 	srlx		%o0, PAGE_SHIFT, %o0
 	sllx		%o0, PAGE_SHIFT, %o0
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
-__hypervisor_flush_tlb_pending: /* 16 insns */
+__hypervisor_flush_tlb_pending: /* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	sllx		%o1, 3, %g1
 	mov		%o2, %g2
@@ -347,31 +438,57 @@
 	srlx		%o0, PAGE_SHIFT, %o0
 	sllx		%o0, PAGE_SHIFT, %o0
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 1f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	brnz,pt		%g1, 1b
 	 nop
 	retl
 	 nop
+1:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
 
-__hypervisor_flush_tlb_kernel_range: /* 16 insns */
+__hypervisor_flush_tlb_kernel_range: /* 31 insns */
 	/* %o0=start, %o1=end */
 	cmp		%o0, %o1
 	be,pn		%xcc, 2f
-	 sethi		%hi(PAGE_SIZE), %g3
-	mov		%o0, %g1
-	sub		%o1, %g1, %g2
+	 sub		%o1, %o0, %g2
+	srlx		%g2, 18, %g3
+	brnz,pn		%g3, 4f
+	 mov		%o0, %g1
+	sethi		%hi(PAGE_SIZE), %g3
 	sub		%g2, %g3, %g2
 1:	add		%g1, %g2, %o0	/* ARG0: virtual address */
 	mov		0, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2	/* ARG2: flags */
 	ta		HV_MMU_UNMAP_ADDR_TRAP
-	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	brnz,pn		%o0, 3f
 	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
 	brnz,pt		%g2, 1b
 	 sub		%g2, %g3, %g2
 2:	retl
 	 nop
+3:	sethi		%hi(__hypervisor_tlb_tl0_error), %o2
+	jmpl		%o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+	 nop
+4:	mov		0, %o0		/* ARG0: CPU lists unimplemented */
+	mov		0, %o1		/* ARG1: CPU lists unimplemented */
+	mov		0, %o2		/* ARG2: mmu context == nucleus */
+	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
+	mov		HV_FAST_MMU_DEMAP_CTX, %o5
+	ta		HV_FAST_TRAP
+	brnz,pn		%o0, 3b
+	 mov		HV_FAST_MMU_DEMAP_CTX, %o1
+	retl
+	 nop
 
 #ifdef DCACHE_ALIASING_POSSIBLE
 	/* XXX Niagara and friends have an 8K cache, so no aliasing is
@@ -394,43 +511,6 @@
 	retl
 	 nop
 
-	.globl		cheetah_patch_cachetlbops
-cheetah_patch_cachetlbops:
-	save		%sp, -128, %sp
-
-	sethi		%hi(__flush_tlb_mm), %o0
-	or		%o0, %lo(__flush_tlb_mm), %o0
-	sethi		%hi(__cheetah_flush_tlb_mm), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_mm), %o1
-	call		tlb_patch_one
-	 mov		19, %o2
-
-	sethi		%hi(__flush_tlb_page), %o0
-	or		%o0, %lo(__flush_tlb_page), %o0
-	sethi		%hi(__cheetah_flush_tlb_page), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
-	call		tlb_patch_one
-	 mov		22, %o2
-
-	sethi		%hi(__flush_tlb_pending), %o0
-	or		%o0, %lo(__flush_tlb_pending), %o0
-	sethi		%hi(__cheetah_flush_tlb_pending), %o1
-	or		%o1, %lo(__cheetah_flush_tlb_pending), %o1
-	call		tlb_patch_one
-	 mov		27, %o2
-
-#ifdef DCACHE_ALIASING_POSSIBLE
-	sethi		%hi(__flush_dcache_page), %o0
-	or		%o0, %lo(__flush_dcache_page), %o0
-	sethi		%hi(__cheetah_flush_dcache_page), %o1
-	or		%o1, %lo(__cheetah_flush_dcache_page), %o1
-	call		tlb_patch_one
-	 mov		11, %o2
-#endif /* DCACHE_ALIASING_POSSIBLE */
-
-	ret
-	 restore
-
 #ifdef CONFIG_SMP
 	/* These are all called by the slaves of a cross call, at
 	 * trap level 1, with interrupts fully disabled.
@@ -447,7 +527,7 @@
 	 */
 	.align		32
 	.globl		xcall_flush_tlb_mm
-xcall_flush_tlb_mm:	/* 21 insns */
+xcall_flush_tlb_mm:	/* 24 insns */
 	mov		PRIMARY_CONTEXT, %g2
 	ldxa		[%g2] ASI_DMMU, %g3
 	srlx		%g3, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -469,9 +549,12 @@
 	nop
 	nop
 	nop
+	nop
+	nop
+	nop
 
 	.globl		xcall_flush_tlb_page
-xcall_flush_tlb_page:	/* 17 insns */
+xcall_flush_tlb_page:	/* 20 insns */
 	/* %g5=context, %g1=vaddr */
 	mov		PRIMARY_CONTEXT, %g4
 	ldxa		[%g4] ASI_DMMU, %g2
@@ -490,15 +573,20 @@
 	retry
 	nop
 	nop
+	nop
+	nop
+	nop
 
 	.globl		xcall_flush_tlb_kernel_range
-xcall_flush_tlb_kernel_range:	/* 25 insns */
+xcall_flush_tlb_kernel_range:	/* 44 insns */
 	sethi		%hi(PAGE_SIZE - 1), %g2
 	or		%g2, %lo(PAGE_SIZE - 1), %g2
 	andn		%g1, %g2, %g1
 	andn		%g7, %g2, %g7
 	sub		%g7, %g1, %g3
-	add		%g2, 1, %g2
+	srlx		%g3, 18, %g2
+	brnz,pn		%g2, 2f
+	 add		%g2, 1, %g2
 	sub		%g3, %g2, %g3
 	or		%g1, 0x20, %g1		! Nucleus
 1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
@@ -507,8 +595,25 @@
 	brnz,pt		%g3, 1b
 	 sub		%g3, %g2, %g3
 	retry
-	nop
-	nop
+2:	mov		63 * 8, %g1
+1:	ldxa		[%g1] ASI_ITLB_DATA_ACCESS, %g2
+	andcc		%g2, 0x40, %g0			/* _PAGE_L_4U */
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %g2
+	stxa		%g0, [%g2] ASI_IMMU
+	stxa		%g0, [%g1] ASI_ITLB_DATA_ACCESS
+	membar		#Sync
+2:	ldxa		[%g1] ASI_DTLB_DATA_ACCESS, %g2
+	andcc		%g2, 0x40, %g0
+	bne,pn		%xcc, 2f
+	 mov		TLB_TAG_ACCESS, %g2
+	stxa		%g0, [%g2] ASI_DMMU
+	stxa		%g0, [%g1] ASI_DTLB_DATA_ACCESS
+	membar		#Sync
+2:	sub		%g1, 8, %g1
+	brgez,pt	%g1, 1b
+	 nop
+	retry
 	nop
 	nop
 	nop
@@ -637,6 +742,52 @@
 
 	retry
 
+__cheetah_xcall_flush_tlb_kernel_range:	/* 44 insns */
+	sethi		%hi(PAGE_SIZE - 1), %g2
+	or		%g2, %lo(PAGE_SIZE - 1), %g2
+	andn		%g1, %g2, %g1
+	andn		%g7, %g2, %g7
+	sub		%g7, %g1, %g3
+	srlx		%g3, 18, %g2
+	brnz,pn		%g2, 2f
+	 add		%g2, 1, %g2
+	sub		%g3, %g2, %g3
+	or		%g1, 0x20, %g1		! Nucleus
+1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
+	stxa		%g0, [%g1 + %g3] ASI_IMMU_DEMAP
+	membar		#Sync
+	brnz,pt		%g3, 1b
+	 sub		%g3, %g2, %g3
+	retry
+2:	mov		0x80, %g2
+	stxa		%g0, [%g2] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g0, [%g2] ASI_IMMU_DEMAP
+	membar		#Sync
+	retry
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
 #ifdef DCACHE_ALIASING_POSSIBLE
 	.align		32
 	.globl		xcall_flush_dcache_page_cheetah
@@ -700,7 +851,7 @@
 	ba,a,pt	%xcc, rtrap
 
 	.globl		__hypervisor_xcall_flush_tlb_mm
-__hypervisor_xcall_flush_tlb_mm: /* 21 insns */
+__hypervisor_xcall_flush_tlb_mm: /* 24 insns */
 	/* %g5=ctx, g1,g2,g3,g4,g7=scratch, %g6=unusable */
 	mov		%o0, %g2
 	mov		%o1, %g3
@@ -714,7 +865,7 @@
 	mov		HV_FAST_MMU_DEMAP_CTX, %o5
 	ta		HV_FAST_TRAP
 	mov		HV_FAST_MMU_DEMAP_CTX, %g6
-	brnz,pn		%o0, __hypervisor_tlb_xcall_error
+	brnz,pn		%o0, 1f
 	 mov		%o0, %g5
 	mov		%g2, %o0
 	mov		%g3, %o1
@@ -723,9 +874,12 @@
 	mov		%g7, %o5
 	membar		#Sync
 	retry
+1:	sethi		%hi(__hypervisor_tlb_xcall_error), %g4
+	jmpl		%g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+	 nop
 
 	.globl		__hypervisor_xcall_flush_tlb_page
-__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+__hypervisor_xcall_flush_tlb_page: /* 20 insns */
 	/* %g5=ctx, %g1=vaddr */
 	mov		%o0, %g2
 	mov		%o1, %g3
@@ -737,42 +891,64 @@
 	sllx		%o0, PAGE_SHIFT, %o0
 	ta		HV_MMU_UNMAP_ADDR_TRAP
 	mov		HV_MMU_UNMAP_ADDR_TRAP, %g6
-	brnz,a,pn	%o0, __hypervisor_tlb_xcall_error
+	brnz,a,pn	%o0, 1f
 	 mov		%o0, %g5
 	mov		%g2, %o0
 	mov		%g3, %o1
 	mov		%g4, %o2
 	membar		#Sync
 	retry
+1:	sethi		%hi(__hypervisor_tlb_xcall_error), %g4
+	jmpl		%g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+	 nop
 
 	.globl		__hypervisor_xcall_flush_tlb_kernel_range
-__hypervisor_xcall_flush_tlb_kernel_range: /* 25 insns */
+__hypervisor_xcall_flush_tlb_kernel_range: /* 44 insns */
 	/* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */
 	sethi		%hi(PAGE_SIZE - 1), %g2
 	or		%g2, %lo(PAGE_SIZE - 1), %g2
 	andn		%g1, %g2, %g1
 	andn		%g7, %g2, %g7
 	sub		%g7, %g1, %g3
+	srlx		%g3, 18, %g7
 	add		%g2, 1, %g2
 	sub		%g3, %g2, %g3
 	mov		%o0, %g2
 	mov		%o1, %g4
-	mov		%o2, %g7
+	brnz,pn		%g7, 2f
+	 mov		%o2, %g7
 1:	add		%g1, %g3, %o0	/* ARG0: virtual address */
 	mov		0, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2	/* ARG2: flags */
 	ta		HV_MMU_UNMAP_ADDR_TRAP
 	mov		HV_MMU_UNMAP_ADDR_TRAP, %g6
-	brnz,pn		%o0, __hypervisor_tlb_xcall_error
+	brnz,pn		%o0, 1f
 	 mov		%o0, %g5
 	sethi		%hi(PAGE_SIZE), %o2
 	brnz,pt		%g3, 1b
 	 sub		%g3, %o2, %g3
-	mov		%g2, %o0
+5:	mov		%g2, %o0
 	mov		%g4, %o1
 	mov		%g7, %o2
 	membar		#Sync
 	retry
+1:	sethi		%hi(__hypervisor_tlb_xcall_error), %g4
+	jmpl		%g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+	 nop
+2:	mov		%o3, %g1
+	mov		%o5, %g3
+	mov		0, %o0		/* ARG0: CPU lists unimplemented */
+	mov		0, %o1		/* ARG1: CPU lists unimplemented */
+	mov		0, %o2		/* ARG2: mmu context == nucleus */
+	mov		HV_MMU_ALL, %o3	/* ARG3: flags */
+	mov		HV_FAST_MMU_DEMAP_CTX, %o5
+	ta		HV_FAST_TRAP
+	mov		%g1, %o3
+	brz,pt		%o0, 5b
+	 mov		%g3, %o5
+	mov		HV_FAST_MMU_DEMAP_CTX, %g6
+	ba,pt		%xcc, 1b
+	 clr		%g5
 
 	/* These just get rescheduled to PIL vectors. */
 	.globl		xcall_call_function
@@ -809,6 +985,58 @@
 
 #endif /* CONFIG_SMP */
 
+	.globl		cheetah_patch_cachetlbops
+cheetah_patch_cachetlbops:
+	save		%sp, -128, %sp
+
+	sethi		%hi(__flush_tlb_mm), %o0
+	or		%o0, %lo(__flush_tlb_mm), %o0
+	sethi		%hi(__cheetah_flush_tlb_mm), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_mm), %o1
+	call		tlb_patch_one
+	 mov		19, %o2
+
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__cheetah_flush_tlb_page), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		22, %o2
+
+	sethi		%hi(__flush_tlb_pending), %o0
+	or		%o0, %lo(__flush_tlb_pending), %o0
+	sethi		%hi(__cheetah_flush_tlb_pending), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_pending), %o1
+	call		tlb_patch_one
+	 mov		27, %o2
+
+	sethi		%hi(__flush_tlb_kernel_range), %o0
+	or		%o0, %lo(__flush_tlb_kernel_range), %o0
+	sethi		%hi(__cheetah_flush_tlb_kernel_range), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_kernel_range), %o1
+	call		tlb_patch_one
+	 mov		31, %o2
+
+#ifdef DCACHE_ALIASING_POSSIBLE
+	sethi		%hi(__flush_dcache_page), %o0
+	or		%o0, %lo(__flush_dcache_page), %o0
+	sethi		%hi(__cheetah_flush_dcache_page), %o1
+	or		%o1, %lo(__cheetah_flush_dcache_page), %o1
+	call		tlb_patch_one
+	 mov		11, %o2
+#endif /* DCACHE_ALIASING_POSSIBLE */
+
+#ifdef CONFIG_SMP
+	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
+	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0
+	sethi		%hi(__cheetah_xcall_flush_tlb_kernel_range), %o1
+	or		%o1, %lo(__cheetah_xcall_flush_tlb_kernel_range), %o1
+	call		tlb_patch_one
+	 mov		44, %o2
+#endif /* CONFIG_SMP */
+
+	ret
+	 restore
 
 	.globl		hypervisor_patch_cachetlbops
 hypervisor_patch_cachetlbops:
@@ -819,28 +1047,28 @@
 	sethi		%hi(__hypervisor_flush_tlb_mm), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_mm), %o1
 	call		tlb_patch_one
-	 mov		10, %o2
+	 mov		19, %o2
 
 	sethi		%hi(__flush_tlb_page), %o0
 	or		%o0, %lo(__flush_tlb_page), %o0
 	sethi		%hi(__hypervisor_flush_tlb_page), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		11, %o2
+	 mov		22, %o2
 
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__hypervisor_flush_tlb_pending), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_pending), %o1
 	call		tlb_patch_one
-	 mov		16, %o2
+	 mov		27, %o2
 
 	sethi		%hi(__flush_tlb_kernel_range), %o0
 	or		%o0, %lo(__flush_tlb_kernel_range), %o0
 	sethi		%hi(__hypervisor_flush_tlb_kernel_range), %o1
 	or		%o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1
 	call		tlb_patch_one
-	 mov		16, %o2
+	 mov		31, %o2
 
 #ifdef DCACHE_ALIASING_POSSIBLE
 	sethi		%hi(__flush_dcache_page), %o0
@@ -857,21 +1085,21 @@
 	sethi		%hi(__hypervisor_xcall_flush_tlb_mm), %o1
 	or		%o1, %lo(__hypervisor_xcall_flush_tlb_mm), %o1
 	call		tlb_patch_one
-	 mov		21, %o2
+	 mov		24, %o2
 
 	sethi		%hi(xcall_flush_tlb_page), %o0
 	or		%o0, %lo(xcall_flush_tlb_page), %o0
 	sethi		%hi(__hypervisor_xcall_flush_tlb_page), %o1
 	or		%o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		17, %o2
+	 mov		20, %o2
 
 	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
 	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0
 	sethi		%hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1
 	or		%o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1
 	call		tlb_patch_one
-	 mov		25, %o2
+	 mov		44, %o2
 #endif /* CONFIG_SMP */
 
 	ret
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index 77f28ce..9976fce 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -5,8 +5,8 @@
 OBJECT_FILES_NON_STANDARD_entry_$(BITS).o   := y
 OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
 
-CFLAGS_syscall_64.o		+= -Wno-override-init
-CFLAGS_syscall_32.o		+= -Wno-override-init
+CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_32.o		+= $(call cc-option,-Wno-override-init,)
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index eab0915..a74a2db 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3607,10 +3607,14 @@ __init int intel_pmu_init(void)
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
-	 * assume at least 3 events:
+	 * assume at least 3 events, when not running in a hypervisor:
 	 */
-	if (version > 1)
-		x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
+	if (version > 1) {
+		int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
+
+		x86_pmu.num_counters_fixed =
+			max((int)edx.split.num_counters_fixed, assume);
+	}
 
 	if (boot_cpu_has(X86_FEATURE_PDCM)) {
 		u64 capabilities;
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 3ca87b5..4f5ac72 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -48,7 +48,8 @@
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
+ *						SKL,KNL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -56,15 +57,16 @@
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
+ *						SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -118,6 +120,7 @@ struct cstate_model {
 
 /* Quirk flags */
 #define SLM_PKG_C6_USE_C7_MSR	(1UL << 0)
+#define KNL_CORE_C6_MSR		(1UL << 1)
 
 struct perf_cstate_msr {
 	u64	msr;
@@ -488,6 +491,18 @@ static const struct cstate_model slm_cstates __initconst = {
 	.quirks			= SLM_PKG_C6_USE_C7_MSR,
 };
 
+
+static const struct cstate_model knl_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES),
+	.quirks			= KNL_CORE_C6_MSR,
+};
+
+
+
 #define X86_CSTATES_MODEL(model, states)				\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
 
@@ -523,6 +538,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
@@ -558,6 +575,11 @@ static int __init cstate_probe(const struct cstate_model *cm)
 	if (cm->quirks & SLM_PKG_C6_USE_C7_MSR)
 		pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY;
 
+	/* KNL has different MSR for CORE C6 */
+	if (cm->quirks & KNL_CORE_C6_MSR)
+		pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY;
+
+
 	has_cstate_core = cstate_probe_msr(cm->core_events,
 					   PERF_CSTATE_CORE_EVENT_MAX,
 					   core_msr, core_events_attrs);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index de25aad..d34bd37 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -351,4 +351,10 @@ extern void arch_phys_wc_del(int handle);
 #define arch_phys_wc_add arch_phys_wc_add
 #endif
 
+#ifdef CONFIG_X86_PAT
+extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size);
+extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size);
+#define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc
+#endif
+
 #endif /* _ASM_X86_IO_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4b20f73..bdde807 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -948,7 +948,6 @@ struct kvm_x86_ops {
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
 	bool (*invpcid_supported)(void);
-	void (*adjust_tsc_offset_guest)(struct kvm_vcpu *vcpu, s64 adjustment);
 
 	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
@@ -958,8 +957,6 @@ struct kvm_x86_ops {
 
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
-	u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc);
-
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
 
 	int (*check_intercept)(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8a5abaa..931ced8 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -454,6 +454,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
 		polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
 
 	mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+	acpi_penalize_sci_irq(bus_irq, trigger, polarity);
 
 	/*
 	 * stash over-ride to indicate we've been here
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 620ab06..017bda1 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -429,7 +429,7 @@ int __init save_microcode_in_initrd_amd(void)
 	 * We need the physical address of the container for both bitness since
 	 * boot_params.hdr.ramdisk_image is a physical address.
 	 */
-	cont    = __pa(container);
+	cont    = __pa_nodebug(container);
 	cont_va = container;
 #endif
 
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index efe73aa..7b0d3da 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -18,8 +18,10 @@
 
 #ifdef CC_USING_FENTRY
 # define function_hook	__fentry__
+EXPORT_SYMBOL(__fentry__)
 #else
 # define function_hook	mcount
+EXPORT_SYMBOL(mcount)
 #endif
 
 /* All cases save the original rbp (8 bytes) */
@@ -295,7 +297,6 @@
 	jmp fgraph_trace
 END(function_hook)
 #endif /* CONFIG_DYNAMIC_FTRACE */
-EXPORT_SYMBOL(function_hook)
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 51402a7..0bee04d 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -625,8 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
 			amd_disable_seq_and_redirect_scrub);
 
-#endif
-
 #if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
 #include <linux/jump_label.h>
 #include <asm/string_64.h>
@@ -657,3 +655,4 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap);
 #endif
+#endif
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index bbfbca5..9c337b0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1221,11 +1221,16 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	get_smp_config();
 
+	/*
+	 * Systems w/o ACPI and mptables might not have it mapped the local
+	 * APIC yet, but prefill_possible_map() might need to access it.
+	 */
+	init_apic_mappings();
+
 	prefill_possible_map();
 
 	init_cpu_to_node();
 
-	init_apic_mappings();
 	io_apic_init_mappings();
 
 	kvm_guest_init();
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index 9298993..2d721e5 100644
--- a/arch/x86/kernel/unwind_guess.c
+++ b/arch/x86/kernel/unwind_guess.c
@@ -47,7 +47,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	get_stack_info(first_frame, state->task, &state->stack_info,
 		       &state->stack_mask);
 
-	if (!__kernel_text_address(*first_frame))
+	/*
+	 * The caller can provide the address of the first frame directly
+	 * (first_frame) or indirectly (regs->sp) to indicate which stack frame
+	 * to start unwinding at.  Skip ahead until we reach it.
+	 */
+	if (!unwind_done(state) &&
+	    (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
+	    !__kernel_text_address(*first_frame)))
 		unwind_next_frame(state);
 }
 EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4e95d3e..cbd7b92 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5045,7 +5045,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	/* Decode and fetch the destination operand: register or memory. */
 	rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
 
-	if (ctxt->rip_relative)
+	if (ctxt->rip_relative && likely(ctxt->memopp))
 		ctxt->memopp->addr.mem.ea = address_mask(ctxt,
 					ctxt->memopp->addr.mem.ea + ctxt->_eip);
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f8157a3..8ca1eca 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1138,21 +1138,6 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
-static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	svm->vmcb->control.tsc_offset += adjustment;
-	if (is_guest_mode(vcpu))
-		svm->nested.hsave->control.tsc_offset += adjustment;
-	else
-		trace_kvm_write_tsc_offset(vcpu->vcpu_id,
-				     svm->vmcb->control.tsc_offset - adjustment,
-				     svm->vmcb->control.tsc_offset);
-
-	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
-}
-
 static void avic_init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb;
@@ -3449,12 +3434,6 @@ static int cr8_write_interception(struct vcpu_svm *svm)
 	return 0;
 }
 
-static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
-{
-	struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu));
-	return vmcb->control.tsc_offset + host_tsc;
-}
-
 static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -5422,8 +5401,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
 	.write_tsc_offset = svm_write_tsc_offset,
-	.adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest,
-	.read_l1_tsc = svm_read_l1_tsc,
 
 	.set_tdp_cr3 = set_tdp_cr3,
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index cf1b16d..5382b82 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -187,6 +187,7 @@ struct vmcs {
  */
 struct loaded_vmcs {
 	struct vmcs *vmcs;
+	struct vmcs *shadow_vmcs;
 	int cpu;
 	int launched;
 	struct list_head loaded_vmcss_on_cpu_link;
@@ -411,7 +412,6 @@ struct nested_vmx {
 	 * memory during VMXOFF, VMCLEAR, VMPTRLD.
 	 */
 	struct vmcs12 *cached_vmcs12;
-	struct vmcs *current_shadow_vmcs;
 	/*
 	 * Indicates if the shadow vmcs must be updated with the
 	 * data hold by vmcs12
@@ -421,7 +421,6 @@ struct nested_vmx {
 	/* vmcs02_list cache of VMCSs recently used to run L2 guests */
 	struct list_head vmcs02_pool;
 	int vmcs02_num;
-	u64 vmcs01_tsc_offset;
 	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
@@ -1419,6 +1418,8 @@ static void vmcs_clear(struct vmcs *vmcs)
 static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
 {
 	vmcs_clear(loaded_vmcs->vmcs);
+	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
 	loaded_vmcs->cpu = -1;
 	loaded_vmcs->launched = 0;
 }
@@ -2605,20 +2606,6 @@ static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Like guest_read_tsc, but always returns L1's notion of the timestamp
- * counter, even if a nested guest (L2) is currently running.
- */
-static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
-{
-	u64 tsc_offset;
-
-	tsc_offset = is_guest_mode(vcpu) ?
-		to_vmx(vcpu)->nested.vmcs01_tsc_offset :
-		vmcs_read64(TSC_OFFSET);
-	return host_tsc + tsc_offset;
-}
-
-/*
  * writes 'offset' into guest's timestamp counter offset register
  */
 static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
@@ -2631,7 +2618,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 		 * to the newly set TSC to get L2's TSC.
 		 */
 		struct vmcs12 *vmcs12;
-		to_vmx(vcpu)->nested.vmcs01_tsc_offset = offset;
 		/* recalculate vmcs02.TSC_OFFSET: */
 		vmcs12 = get_vmcs12(vcpu);
 		vmcs_write64(TSC_OFFSET, offset +
@@ -2644,19 +2630,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	}
 }
 
-static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment)
-{
-	u64 offset = vmcs_read64(TSC_OFFSET);
-
-	vmcs_write64(TSC_OFFSET, offset + adjustment);
-	if (is_guest_mode(vcpu)) {
-		/* Even when running L2, the adjustment needs to apply to L1 */
-		to_vmx(vcpu)->nested.vmcs01_tsc_offset += adjustment;
-	} else
-		trace_kvm_write_tsc_offset(vcpu->vcpu_id, offset,
-					   offset + adjustment);
-}
-
 static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0);
@@ -3562,6 +3535,7 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 	loaded_vmcs_clear(loaded_vmcs);
 	free_vmcs(loaded_vmcs->vmcs);
 	loaded_vmcs->vmcs = NULL;
+	WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
 }
 
 static void free_kvm_area(void)
@@ -6696,6 +6670,7 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
 	if (!item)
 		return NULL;
 	item->vmcs02.vmcs = alloc_vmcs();
+	item->vmcs02.shadow_vmcs = NULL;
 	if (!item->vmcs02.vmcs) {
 		kfree(item);
 		return NULL;
@@ -7072,7 +7047,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		shadow_vmcs->revision_id |= (1u << 31);
 		/* init shadow vmcs */
 		vmcs_clear(shadow_vmcs);
-		vmx->nested.current_shadow_vmcs = shadow_vmcs;
+		vmx->vmcs01.shadow_vmcs = shadow_vmcs;
 	}
 
 	INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
@@ -7174,8 +7149,11 @@ static void free_nested(struct vcpu_vmx *vmx)
 		free_page((unsigned long)vmx->nested.msr_bitmap);
 		vmx->nested.msr_bitmap = NULL;
 	}
-	if (enable_shadow_vmcs)
-		free_vmcs(vmx->nested.current_shadow_vmcs);
+	if (enable_shadow_vmcs) {
+		vmcs_clear(vmx->vmcs01.shadow_vmcs);
+		free_vmcs(vmx->vmcs01.shadow_vmcs);
+		vmx->vmcs01.shadow_vmcs = NULL;
+	}
 	kfree(vmx->nested.cached_vmcs12);
 	/* Unpin physical memory we referred to in current vmcs02 */
 	if (vmx->nested.apic_access_page) {
@@ -7352,7 +7330,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
 	int i;
 	unsigned long field;
 	u64 field_value;
-	struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
+	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
 	const unsigned long *fields = shadow_read_write_fields;
 	const int num_fields = max_shadow_read_write_fields;
 
@@ -7401,7 +7379,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 	int i, q;
 	unsigned long field;
 	u64 field_value = 0;
-	struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
+	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
 
 	vmcs_load(shadow_vmcs);
 
@@ -7591,7 +7569,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 				      SECONDARY_EXEC_SHADOW_VMCS);
 			vmcs_write64(VMCS_LINK_POINTER,
-				     __pa(vmx->nested.current_shadow_vmcs));
+				     __pa(vmx->vmcs01.shadow_vmcs));
 			vmx->nested.sync_shadow_vmcs = true;
 		}
 	}
@@ -7659,7 +7637,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 
 	types = (vmx->nested.nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
 
-	if (!(types & (1UL << type))) {
+	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		skip_emulated_instruction(vcpu);
@@ -7722,7 +7700,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 
 	types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7;
 
-	if (!(types & (1UL << type))) {
+	if (type >= 32 || !(types & (1 << type))) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		skip_emulated_instruction(vcpu);
@@ -9156,6 +9134,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
 	vmx->loaded_vmcs->vmcs = alloc_vmcs();
+	vmx->loaded_vmcs->shadow_vmcs = NULL;
 	if (!vmx->loaded_vmcs->vmcs)
 		goto free_msrs;
 	if (!vmm_exclusive)
@@ -10061,9 +10040,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
 		vmcs_write64(TSC_OFFSET,
-			vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
+			vcpu->arch.tsc_offset + vmcs12->tsc_offset);
 	else
-		vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+		vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
 
@@ -10293,8 +10272,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 	enter_guest_mode(vcpu);
 
-	vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
-
 	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
 		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
 
@@ -10818,7 +10795,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	load_vmcs12_host_state(vcpu, vmcs12);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
-	vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (vmx->hv_deadline_tsc == -1)
 		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
 				PIN_BASED_VMX_PREEMPTION_TIMER);
@@ -11339,8 +11316,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
 	.write_tsc_offset = vmx_write_tsc_offset,
-	.adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest,
-	.read_l1_tsc = vmx_read_l1_tsc,
 
 	.set_tdp_cr3 = vmx_set_cr3,
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e375235..3017de0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1409,7 +1409,7 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 
 u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 {
-	return kvm_x86_ops->read_l1_tsc(vcpu, kvm_scale_tsc(vcpu, host_tsc));
+	return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
 }
 EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
 
@@ -1547,7 +1547,7 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc);
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
 					   s64 adjustment)
 {
-	kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment);
+	kvm_vcpu_write_tsc_offset(vcpu, vcpu->arch.tsc_offset + adjustment);
 }
 
 static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
@@ -1555,7 +1555,7 @@ static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
 	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio)
 		WARN_ON(adjustment < 0);
 	adjustment = kvm_scale_tsc(vcpu, (u64) adjustment);
-	kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment);
+	adjust_tsc_offset_guest(vcpu, adjustment);
 }
 
 #ifdef CONFIG_X86_64
@@ -2262,7 +2262,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
 		 */
-		vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data);
+		vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
 		break;
 	case MSR_AMD64_OSVW_ID_LENGTH:
 		if (!guest_cpuid_has_osvw(vcpu))
@@ -2280,11 +2280,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (kvm_pmu_is_valid_msr(vcpu, msr))
 			return kvm_pmu_set_msr(vcpu, msr_info);
 		if (!ignore_msrs) {
-			vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
+			vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n",
 				    msr, data);
 			return 1;
 		} else {
-			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n",
+			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
 				    msr, data);
 			break;
 		}
@@ -7410,10 +7410,12 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+
 	kvmclock_reset(vcpu);
 
-	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
 	kvm_x86_ops->vcpu_free(vcpu);
+	free_cpumask_var(wbinvd_dirty_mask);
 }
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index ddd2661..887e571 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -104,10 +104,10 @@ void __init kernel_randomize_memory(void)
 	 * consistent with the vaddr_start/vaddr_end variables.
 	 */
 	BUILD_BUG_ON(vaddr_start >= vaddr_end);
-	BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) &&
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
 		     vaddr_end >= EFI_VA_START);
-	BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) ||
-		      config_enabled(CONFIG_EFI)) &&
+	BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
+		      IS_ENABLED(CONFIG_EFI)) &&
 		     vaddr_end >= __START_KERNEL_map);
 	BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
 
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 170cc4f..83e701f 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -730,6 +730,20 @@ void io_free_memtype(resource_size_t start, resource_size_t end)
 	free_memtype(start, end);
 }
 
+int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size)
+{
+	enum page_cache_mode type = _PAGE_CACHE_MODE_WC;
+
+	return io_reserve_memtype(start, start + size, &type);
+}
+EXPORT_SYMBOL(arch_io_reserve_memtype_wc);
+
+void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size)
+{
+	io_free_memtype(start, start + size);
+}
+EXPORT_SYMBOL(arch_io_free_memtype_wc);
+
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t vma_prot)
 {
diff --git a/block/badblocks.c b/block/badblocks.c
index 6610e28..6ebcef2 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -133,6 +133,26 @@ int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
 }
 EXPORT_SYMBOL_GPL(badblocks_check);
 
+static void badblocks_update_acked(struct badblocks *bb)
+{
+	u64 *p = bb->page;
+	int i;
+	bool unacked = false;
+
+	if (!bb->unacked_exist)
+		return;
+
+	for (i = 0; i < bb->count ; i++) {
+		if (!BB_ACK(p[i])) {
+			unacked = true;
+			break;
+		}
+	}
+
+	if (!unacked)
+		bb->unacked_exist = 0;
+}
+
 /**
  * badblocks_set() - Add a range of bad blocks to the table.
  * @bb:		the badblocks structure that holds all badblock information
@@ -294,6 +314,8 @@ int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
 	bb->changed = 1;
 	if (!acknowledged)
 		bb->unacked_exist = 1;
+	else
+		badblocks_update_acked(bb);
 	write_sequnlock_irqrestore(&bb->lock, flags);
 
 	return rv;
@@ -401,6 +423,7 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
 		}
 	}
 
+	badblocks_update_acked(bb);
 	bb->changed = 1;
 out:
 	write_sequnlock_irq(&bb->lock);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 6a14b68..3c882cb 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -343,6 +343,34 @@ static void flush_data_end_io(struct request *rq, int error)
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
 
 	/*
+	 * Updating q->in_flight[] here for making this tag usable
+	 * early. Because in blk_queue_start_tag(),
+	 * q->in_flight[BLK_RW_ASYNC] is used to limit async I/O and
+	 * reserve tags for sync I/O.
+	 *
+	 * More importantly this way can avoid the following I/O
+	 * deadlock:
+	 *
+	 * - suppose there are 40 fua requests comming to flush queue
+	 *   and queue depth is 31
+	 * - 30 rqs are scheduled then blk_queue_start_tag() can't alloc
+	 *   tag for async I/O any more
+	 * - all the 30 rqs are completed before FLUSH_PENDING_TIMEOUT
+	 *   and flush_data_end_io() is called
+	 * - the other rqs still can't go ahead if not updating
+	 *   q->in_flight[BLK_RW_ASYNC] here, meantime these rqs
+	 *   are held in flush data queue and make no progress of
+	 *   handling post flush rq
+	 * - only after the post flush rq is handled, all these rqs
+	 *   can be completed
+	 */
+
+	elv_completed_request(q, rq);
+
+	/* for avoiding double accounting */
+	rq->cmd_flags &= ~REQ_STARTED;
+
+	/*
 	 * After populating an empty queue, kick it to avoid stall.  Read
 	 * the comment in flush_end_io().
 	 */
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ddc2eed..f3d27a6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1217,9 +1217,9 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
 	rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
 
-	hctx->queued++;
-	data->hctx = hctx;
-	data->ctx = ctx;
+	data->hctx = alloc_data.hctx;
+	data->ctx = alloc_data.ctx;
+	data->hctx->queued++;
 	return rq;
 }
 
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index f1e6dcc..54d48b9 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -46,6 +46,7 @@
 #include "acdispat.h"
 #include "acnamesp.h"
 #include "actables.h"
+#include "acinterp.h"
 
 #define _COMPONENT          ACPI_DISPATCHER
 ACPI_MODULE_NAME("dsinit")
@@ -214,23 +215,17 @@ acpi_ds_initialize_objects(u32 table_index,
 
 	/* Walk entire namespace from the supplied root */
 
-	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
 	/*
 	 * We don't use acpi_walk_namespace since we do not want to acquire
 	 * the namespace reader lock.
 	 */
 	status =
 	    acpi_ns_walk_namespace(ACPI_TYPE_ANY, start_node, ACPI_UINT32_MAX,
-				   ACPI_NS_WALK_UNLOCK, acpi_ds_init_one_object,
-				   NULL, &info, NULL);
+				   0, acpi_ds_init_one_object, NULL, &info,
+				   NULL);
 	if (ACPI_FAILURE(status)) {
 		ACPI_EXCEPTION((AE_INFO, status, "During WalkNamespace"));
 	}
-	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
 
 	status = acpi_get_table_by_index(table_index, &table);
 	if (ACPI_FAILURE(status)) {
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index 32e9ddc..2b3210f 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -99,14 +99,11 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
 			  "Method auto-serialization parse [%4.4s] %p\n",
 			  acpi_ut_get_node_name(node), node));
 
-	acpi_ex_enter_interpreter();
-
 	/* Create/Init a root op for the method parse tree */
 
 	op = acpi_ps_alloc_op(AML_METHOD_OP, obj_desc->method.aml_start);
 	if (!op) {
-		status = AE_NO_MEMORY;
-		goto unlock;
+		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
 
 	acpi_ps_set_name(op, node->name.integer);
@@ -118,8 +115,7 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
 	    acpi_ds_create_walk_state(node->owner_id, NULL, NULL, NULL);
 	if (!walk_state) {
 		acpi_ps_free_op(op);
-		status = AE_NO_MEMORY;
-		goto unlock;
+		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
 
 	status = acpi_ds_init_aml_walk(walk_state, op, node,
@@ -138,8 +134,6 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
 	status = acpi_ps_parse_aml(walk_state);
 
 	acpi_ps_delete_parse_tree(op);
-unlock:
-	acpi_ex_exit_interpreter();
 	return_ACPI_STATUS(status);
 }
 
@@ -731,26 +725,6 @@ acpi_ds_terminate_control_method(union acpi_operand_object *method_desc,
 		acpi_ds_method_data_delete_all(walk_state);
 
 		/*
-		 * If method is serialized, release the mutex and restore the
-		 * current sync level for this thread
-		 */
-		if (method_desc->method.mutex) {
-
-			/* Acquisition Depth handles recursive calls */
-
-			method_desc->method.mutex->mutex.acquisition_depth--;
-			if (!method_desc->method.mutex->mutex.acquisition_depth) {
-				walk_state->thread->current_sync_level =
-				    method_desc->method.mutex->mutex.
-				    original_sync_level;
-
-				acpi_os_release_mutex(method_desc->method.
-						      mutex->mutex.os_mutex);
-				method_desc->method.mutex->mutex.thread_id = 0;
-			}
-		}
-
-		/*
 		 * Delete any namespace objects created anywhere within the
 		 * namespace by the execution of this method. Unless:
 		 * 1) This method is a module-level executable code method, in which
@@ -786,6 +760,26 @@ acpi_ds_terminate_control_method(union acpi_operand_object *method_desc,
 				    ~ACPI_METHOD_MODIFIED_NAMESPACE;
 			}
 		}
+
+		/*
+		 * If method is serialized, release the mutex and restore the
+		 * current sync level for this thread
+		 */
+		if (method_desc->method.mutex) {
+
+			/* Acquisition Depth handles recursive calls */
+
+			method_desc->method.mutex->mutex.acquisition_depth--;
+			if (!method_desc->method.mutex->mutex.acquisition_depth) {
+				walk_state->thread->current_sync_level =
+				    method_desc->method.mutex->mutex.
+				    original_sync_level;
+
+				acpi_os_release_mutex(method_desc->method.
+						      mutex->mutex.os_mutex);
+				method_desc->method.mutex->mutex.thread_id = 0;
+			}
+		}
 	}
 
 	/* Decrement the thread count on the method */
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 028b22a..e362182 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -607,11 +607,9 @@ acpi_status acpi_ds_load2_end_op(struct acpi_walk_state *walk_state)
 				}
 			}
 
-			acpi_ex_exit_interpreter();
 			status =
 			    acpi_ev_initialize_region
 			    (acpi_ns_get_attached_object(node), FALSE);
-			acpi_ex_enter_interpreter();
 
 			if (ACPI_FAILURE(status)) {
 				/*
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 3843f1f..75ddd16 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -45,6 +45,7 @@
 #include "accommon.h"
 #include "acevents.h"
 #include "acnamesp.h"
+#include "acinterp.h"
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evrgnini")
@@ -597,9 +598,11 @@ acpi_ev_initialize_region(union acpi_operand_object *region_obj,
 					}
 				}
 
+				acpi_ex_exit_interpreter();
 				status =
 				    acpi_ev_execute_reg_method(region_obj,
 							       ACPI_REG_CONNECT);
+				acpi_ex_enter_interpreter();
 
 				if (acpi_ns_locked) {
 					status =
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index 334d3c5..d1f2014 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -137,7 +137,9 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 			  "**** Begin Table Object Initialization\n"));
 
+	acpi_ex_enter_interpreter();
 	status = acpi_ds_initialize_objects(table_index, node);
+	acpi_ex_exit_interpreter();
 
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 			  "**** Completed Table Object Initialization\n"));
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index f0a029e..0d099a2 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -662,7 +662,7 @@ static int ghes_proc(struct ghes *ghes)
 	ghes_do_proc(ghes, ghes->estatus);
 out:
 	ghes_clear_estatus(ghes);
-	return 0;
+	return rc;
 }
 
 static void ghes_add_timer(struct ghes *ghes)
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index c983bf7..bc3d914 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -87,6 +87,7 @@ struct acpi_pci_link {
 
 static LIST_HEAD(acpi_link_list);
 static DEFINE_MUTEX(acpi_link_lock);
+static int sci_irq = -1, sci_penalty;
 
 /* --------------------------------------------------------------------------
                             PCI Link Device Management
@@ -496,25 +497,13 @@ static int acpi_irq_get_penalty(int irq)
 {
 	int penalty = 0;
 
-	/*
-	* Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict
-	* with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be
-	* use for PCI IRQs.
-	*/
-	if (irq == acpi_gbl_FADT.sci_interrupt) {
-		u32 type = irq_get_trigger_type(irq) & IRQ_TYPE_SENSE_MASK;
-
-		if (type != IRQ_TYPE_LEVEL_LOW)
-			penalty += PIRQ_PENALTY_ISA_ALWAYS;
-		else
-			penalty += PIRQ_PENALTY_PCI_USING;
-	}
+	if (irq == sci_irq)
+		penalty += sci_penalty;
 
 	if (irq < ACPI_MAX_ISA_IRQS)
 		return penalty + acpi_isa_irq_penalty[irq];
 
-	penalty += acpi_irq_pci_sharing_penalty(irq);
-	return penalty;
+	return penalty + acpi_irq_pci_sharing_penalty(irq);
 }
 
 int __init acpi_irq_penalty_init(void)
@@ -619,6 +608,10 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link)
 			    acpi_device_bid(link->device));
 		return -ENODEV;
 	} else {
+		if (link->irq.active < ACPI_MAX_ISA_IRQS)
+			acpi_isa_irq_penalty[link->irq.active] +=
+				PIRQ_PENALTY_PCI_USING;
+
 		printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n",
 		       acpi_device_name(link->device),
 		       acpi_device_bid(link->device), link->irq.active);
@@ -849,7 +842,7 @@ static int __init acpi_irq_penalty_update(char *str, int used)
 			continue;
 
 		if (used)
-			new_penalty = acpi_irq_get_penalty(irq) +
+			new_penalty = acpi_isa_irq_penalty[irq] +
 					PIRQ_PENALTY_ISA_USED;
 		else
 			new_penalty = 0;
@@ -871,7 +864,7 @@ static int __init acpi_irq_penalty_update(char *str, int used)
 void acpi_penalize_isa_irq(int irq, int active)
 {
 	if ((irq >= 0) && (irq < ARRAY_SIZE(acpi_isa_irq_penalty)))
-		acpi_isa_irq_penalty[irq] = acpi_irq_get_penalty(irq) +
+		acpi_isa_irq_penalty[irq] +=
 		  (active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING);
 }
 
@@ -881,6 +874,17 @@ bool acpi_isa_irq_available(int irq)
 		    acpi_irq_get_penalty(irq) < PIRQ_PENALTY_ISA_ALWAYS);
 }
 
+void acpi_penalize_sci_irq(int irq, int trigger, int polarity)
+{
+	sci_irq = irq;
+
+	if (trigger == ACPI_MADT_TRIGGER_LEVEL &&
+	    polarity == ACPI_MADT_POLARITY_ACTIVE_LOW)
+		sci_penalty = PIRQ_PENALTY_PCI_USING;
+	else
+		sci_penalty = PIRQ_PENALTY_ISA_ALWAYS;
+}
+
 /*
  * Over-ride default table to reserve additional IRQs for use by ISA
  * e.g. acpi_irq_isa=5
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 562af94..3c71b98 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1002,7 +1002,7 @@ static int binder_dec_node(struct binder_node *node, int strong, int internal)
 
 
 static struct binder_ref *binder_get_ref(struct binder_proc *proc,
-					 uint32_t desc)
+					 u32 desc, bool need_strong_ref)
 {
 	struct rb_node *n = proc->refs_by_desc.rb_node;
 	struct binder_ref *ref;
@@ -1010,12 +1010,16 @@ static struct binder_ref *binder_get_ref(struct binder_proc *proc,
 	while (n) {
 		ref = rb_entry(n, struct binder_ref, rb_node_desc);
 
-		if (desc < ref->desc)
+		if (desc < ref->desc) {
 			n = n->rb_left;
-		else if (desc > ref->desc)
+		} else if (desc > ref->desc) {
 			n = n->rb_right;
-		else
+		} else if (need_strong_ref && !ref->strong) {
+			binder_user_error("tried to use weak ref as strong ref\n");
+			return NULL;
+		} else {
 			return ref;
+		}
 	}
 	return NULL;
 }
@@ -1285,7 +1289,10 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
 		} break;
 		case BINDER_TYPE_HANDLE:
 		case BINDER_TYPE_WEAK_HANDLE: {
-			struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+			struct binder_ref *ref;
+
+			ref = binder_get_ref(proc, fp->handle,
+					     fp->type == BINDER_TYPE_HANDLE);
 
 			if (ref == NULL) {
 				pr_err("transaction release %d bad handle %d\n",
@@ -1380,7 +1387,7 @@ static void binder_transaction(struct binder_proc *proc,
 		if (tr->target.handle) {
 			struct binder_ref *ref;
 
-			ref = binder_get_ref(proc, tr->target.handle);
+			ref = binder_get_ref(proc, tr->target.handle, true);
 			if (ref == NULL) {
 				binder_user_error("%d:%d got transaction to invalid handle\n",
 					proc->pid, thread->pid);
@@ -1577,7 +1584,9 @@ static void binder_transaction(struct binder_proc *proc,
 				fp->type = BINDER_TYPE_HANDLE;
 			else
 				fp->type = BINDER_TYPE_WEAK_HANDLE;
+			fp->binder = 0;
 			fp->handle = ref->desc;
+			fp->cookie = 0;
 			binder_inc_ref(ref, fp->type == BINDER_TYPE_HANDLE,
 				       &thread->todo);
 
@@ -1589,7 +1598,10 @@ static void binder_transaction(struct binder_proc *proc,
 		} break;
 		case BINDER_TYPE_HANDLE:
 		case BINDER_TYPE_WEAK_HANDLE: {
-			struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+			struct binder_ref *ref;
+
+			ref = binder_get_ref(proc, fp->handle,
+					     fp->type == BINDER_TYPE_HANDLE);
 
 			if (ref == NULL) {
 				binder_user_error("%d:%d got transaction with invalid handle, %d\n",
@@ -1624,7 +1636,9 @@ static void binder_transaction(struct binder_proc *proc,
 					return_error = BR_FAILED_REPLY;
 					goto err_binder_get_ref_for_node_failed;
 				}
+				fp->binder = 0;
 				fp->handle = new_ref->desc;
+				fp->cookie = 0;
 				binder_inc_ref(new_ref, fp->type == BINDER_TYPE_HANDLE, NULL);
 				trace_binder_transaction_ref_to_ref(t, ref,
 								    new_ref);
@@ -1678,6 +1692,7 @@ static void binder_transaction(struct binder_proc *proc,
 			binder_debug(BINDER_DEBUG_TRANSACTION,
 				     "        fd %d -> %d\n", fp->handle, target_fd);
 			/* TODO: fput? */
+			fp->binder = 0;
 			fp->handle = target_fd;
 		} break;
 
@@ -1800,7 +1815,9 @@ static int binder_thread_write(struct binder_proc *proc,
 						ref->desc);
 				}
 			} else
-				ref = binder_get_ref(proc, target);
+				ref = binder_get_ref(proc, target,
+						     cmd == BC_ACQUIRE ||
+						     cmd == BC_RELEASE);
 			if (ref == NULL) {
 				binder_user_error("%d:%d refcount change on invalid ref %d\n",
 					proc->pid, thread->pid, target);
@@ -1996,7 +2013,7 @@ static int binder_thread_write(struct binder_proc *proc,
 			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
 				return -EFAULT;
 			ptr += sizeof(binder_uintptr_t);
-			ref = binder_get_ref(proc, target);
+			ref = binder_get_ref(proc, target, false);
 			if (ref == NULL) {
 				binder_user_error("%d:%d %s invalid ref %d\n",
 					proc->pid, thread->pid,
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index ba5f11c..9669fc7 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1418,31 +1418,34 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports,
 	 * Message mode could be enforced. In this case assume that advantage
 	 * of multipe MSIs is negated and use single MSI mode instead.
 	 */
-	nvec = pci_alloc_irq_vectors(pdev, n_ports, INT_MAX,
-			PCI_IRQ_MSIX | PCI_IRQ_MSI);
-	if (nvec > 0) {
-		if (!(readl(hpriv->mmio + HOST_CTL) & HOST_MRSM)) {
-			hpriv->get_irq_vector = ahci_get_irq_vector;
-			hpriv->flags |= AHCI_HFLAG_MULTI_MSI;
-			return nvec;
+	if (n_ports > 1) {
+		nvec = pci_alloc_irq_vectors(pdev, n_ports, INT_MAX,
+				PCI_IRQ_MSIX | PCI_IRQ_MSI);
+		if (nvec > 0) {
+			if (!(readl(hpriv->mmio + HOST_CTL) & HOST_MRSM)) {
+				hpriv->get_irq_vector = ahci_get_irq_vector;
+				hpriv->flags |= AHCI_HFLAG_MULTI_MSI;
+				return nvec;
+			}
+
+			/*
+			 * Fallback to single MSI mode if the controller
+			 * enforced MRSM mode.
+			 */
+			printk(KERN_INFO
+				"ahci: MRSM is on, fallback to single MSI\n");
+			pci_free_irq_vectors(pdev);
 		}
 
 		/*
-		 * Fallback to single MSI mode if the controller enforced MRSM
-		 * mode.
+		 * -ENOSPC indicated we don't have enough vectors.  Don't bother
+		 * trying a single vectors for any other error:
 		 */
-		printk(KERN_INFO "ahci: MRSM is on, fallback to single MSI\n");
-		pci_free_irq_vectors(pdev);
+		if (nvec < 0 && nvec != -ENOSPC)
+			return nvec;
 	}
 
 	/*
-	 * -ENOSPC indicated we don't have enough vectors.  Don't bother trying
-	 * a single vectors for any other error:
-	 */
-	if (nvec < 0 && nvec != -ENOSPC)
-		return nvec;
-
-	/*
 	 * If the host is not capable of supporting per-port vectors, fall
 	 * back to single MSI before finally attempting single MSI-X.
 	 */
@@ -1617,7 +1620,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		/* legacy intx interrupts */
 		pci_intx(pdev, 1);
 	}
-	hpriv->irq = pdev->irq;
+	hpriv->irq = pci_irq_vector(pdev, 0);
 
 	if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss)
 		host->flags |= ATA_HOST_PARALLEL_SCAN;
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index fdf44ca..d02e7c0 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -213,14 +213,16 @@
 	  If you are unsure about this, Say N here.
 
 config DEBUG_TEST_DRIVER_REMOVE
-	bool "Test driver remove calls during probe"
+	bool "Test driver remove calls during probe (UNSTABLE)"
 	depends on DEBUG_KERNEL
 	help
 	  Say Y here if you want the Driver core to test driver remove functions
 	  by calling probe, remove, probe. This tests the remove path without
 	  having to unbind the driver or unload the driver module.
 
-	  If you are unsure about this, say N here.
+	  This option is expected to find errors and may render your system
+	  unusable. You should say N here unless you are explicitly looking to
+	  test this functionality.
 
 config SYS_HYPERVISOR
 	bool
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 811e11c..0809cda 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -2954,7 +2954,7 @@ DAC960_DetectController(struct pci_dev *PCI_Device,
 	case DAC960_PD_Controller:
 	  if (!request_region(Controller->IO_Address, 0x80,
 			      Controller->FullModelName)) {
-		DAC960_Error("IO port 0x%d busy for Controller at\n",
+		DAC960_Error("IO port 0x%lx busy for Controller at\n",
 			     Controller, Controller->IO_Address);
 		goto Failure;
 	  }
@@ -2990,7 +2990,7 @@ DAC960_DetectController(struct pci_dev *PCI_Device,
 	case DAC960_P_Controller:
 	  if (!request_region(Controller->IO_Address, 0x80,
 			      Controller->FullModelName)){
-		DAC960_Error("IO port 0x%d busy for Controller at\n",
+		DAC960_Error("IO port 0x%lx busy for Controller at\n",
 		   	     Controller, Controller->IO_Address);
 		goto Failure;
 	  }
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index ba405b5..19a16b2 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -164,7 +164,7 @@ static void sock_shutdown(struct nbd_device *nbd)
 	spin_lock(&nbd->sock_lock);
 
 	if (!nbd->sock) {
-		spin_unlock_irq(&nbd->sock_lock);
+		spin_unlock(&nbd->sock_lock);
 		return;
 	}
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 2dc5c96..5545a67 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -376,7 +376,7 @@ static void virtblk_config_changed(struct virtio_device *vdev)
 
 static int init_vq(struct virtio_blk *vblk)
 {
-	int err = 0;
+	int err;
 	int i;
 	vq_callback_t **callbacks;
 	const char **names;
@@ -390,13 +390,13 @@ static int init_vq(struct virtio_blk *vblk)
 	if (err)
 		num_vqs = 1;
 
-	vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL);
+	vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
 	if (!vblk->vqs)
 		return -ENOMEM;
 
-	names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL);
-	callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL);
-	vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL);
+	names = kmalloc_array(num_vqs, sizeof(*names), GFP_KERNEL);
+	callbacks = kmalloc_array(num_vqs, sizeof(*callbacks), GFP_KERNEL);
+	vqs = kmalloc_array(num_vqs, sizeof(*vqs), GFP_KERNEL);
 	if (!names || !callbacks || !vqs) {
 		err = -ENOMEM;
 		goto out;
diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c
index ef51c9c..b6bb58c 100644
--- a/drivers/bluetooth/btwilink.c
+++ b/drivers/bluetooth/btwilink.c
@@ -310,7 +310,7 @@ static int bt_ti_probe(struct platform_device *pdev)
 	BT_DBG("HCI device registered (hdev %p)", hdev);
 
 	dev_set_drvdata(&pdev->dev, hst);
-	return err;
+	return 0;
 }
 
 static int bt_ti_remove(struct platform_device *pdev)
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 5ccb90e..8f6c23c 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -643,6 +643,14 @@ static const struct dmi_system_id bcm_wrong_irq_dmi_table[] = {
 		},
 		.driver_data = &acpi_active_low,
 	},
+	{	/* Handle ThinkPad 8 tablets with BCM2E55 chipset ACPI ID */
+		.ident = "Lenovo ThinkPad 8",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "ThinkPad 8"),
+		},
+		.driver_data = &acpi_active_low,
+	},
 	{ }
 };
 
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index 7010dca..7875105 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -111,6 +111,7 @@
 config QCOM_EBI2
 	bool "Qualcomm External Bus Interface 2 (EBI2)"
 	depends on HAS_IOMEM
+	depends on ARCH_QCOM || COMPILE_TEST
 	help
 	  Say y here to enable support for the Qualcomm External Bus
 	  Interface 2, which can be used to connect things like NAND Flash,
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 8de6187..3a9149c 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -813,9 +813,6 @@ int tpm_do_selftest(struct tpm_chip *chip)
 			continue;
 		}
 
-		if (rc < TPM_HEADER_SIZE)
-			return -EFAULT;
-
 		if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) {
 			dev_info(&chip->dev,
 				 "TPM is disabled/deactivated (0x%X)\n", rc);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index d433b1d..5649234 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1539,19 +1539,29 @@ static void remove_port_data(struct port *port)
 	spin_lock_irq(&port->inbuf_lock);
 	/* Remove unused data this port might have received. */
 	discard_port_data(port);
+	spin_unlock_irq(&port->inbuf_lock);
 
 	/* Remove buffers we queued up for the Host to send us data in. */
-	while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
-		free_buf(buf, true);
-	spin_unlock_irq(&port->inbuf_lock);
+	do {
+		spin_lock_irq(&port->inbuf_lock);
+		buf = virtqueue_detach_unused_buf(port->in_vq);
+		spin_unlock_irq(&port->inbuf_lock);
+		if (buf)
+			free_buf(buf, true);
+	} while (buf);
 
 	spin_lock_irq(&port->outvq_lock);
 	reclaim_consumed_buffers(port);
+	spin_unlock_irq(&port->outvq_lock);
 
 	/* Free pending buffers from the out-queue. */
-	while ((buf = virtqueue_detach_unused_buf(port->out_vq)))
-		free_buf(buf, true);
-	spin_unlock_irq(&port->outvq_lock);
+	do {
+		spin_lock_irq(&port->outvq_lock);
+		buf = virtqueue_detach_unused_buf(port->out_vq);
+		spin_unlock_irq(&port->outvq_lock);
+		if (buf)
+			free_buf(buf, true);
+	} while (buf);
 }
 
 /*
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f535f81..4737520 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -179,6 +179,7 @@ struct _pid {
 /**
  * struct cpudata -	Per CPU instance data storage
  * @cpu:		CPU number for this instance data
+ * @policy:		CPUFreq policy value
  * @update_util:	CPUFreq utility callback information
  * @update_util_set:	CPUFreq utility callback is set
  * @iowait_boost:	iowait-related boost fraction
@@ -201,6 +202,7 @@ struct _pid {
 struct cpudata {
 	int cpu;
 
+	unsigned int policy;
 	struct update_util_data update_util;
 	bool   update_util_set;
 
@@ -1142,10 +1144,8 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
-	int pstate = cpu->pstate.min_pstate;
-
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 	cpu->pstate.current_pstate = pstate;
 	/*
@@ -1157,6 +1157,20 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
 		      pstate_funcs.get_val(cpu, pstate));
 }
 
+static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+{
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+}
+
+static void intel_pstate_max_within_limits(struct cpudata *cpu)
+{
+	int min_pstate, max_pstate;
+
+	update_turbo_state();
+	intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
+	intel_pstate_set_pstate(cpu, max_pstate);
+}
+
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
@@ -1325,7 +1339,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 
 	from = cpu->pstate.current_pstate;
 
-	target_pstate = pstate_funcs.get_target_pstate(cpu);
+	target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
+		cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);
 
 	intel_pstate_update_pstate(cpu, target_pstate);
 
@@ -1491,7 +1506,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
 		 policy->cpuinfo.max_freq, policy->max);
 
-	cpu = all_cpu_data[0];
+	cpu = all_cpu_data[policy->cpu];
+	cpu->policy = policy->policy;
+
 	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
 	    policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
@@ -1499,7 +1516,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		policy->max = policy->cpuinfo.max_freq;
 	}
 
-	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits = &performance_limits;
 		if (policy->max >= policy->cpuinfo.max_freq) {
 			pr_debug("set performance\n");
@@ -1535,6 +1552,15 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
  out:
+	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		/*
+		 * NOHZ_FULL CPUs need this as the governor callback may not
+		 * be invoked on them.
+		 */
+		intel_pstate_clear_update_util_hook(policy->cpu);
+		intel_pstate_max_within_limits(cpu);
+	}
+
 	intel_pstate_set_update_util_hook(policy->cpu);
 
 	intel_pstate_hwp_set_policy(policy);
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index daadd20a..3e2ab3b 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -14,7 +14,7 @@
 
 config DEV_DAX_PMEM
 	tristate "PMEM DAX: direct access to persistent memory"
-	depends on NVDIMM_DAX
+	depends on LIBNVDIMM && NVDIMM_DAX
 	default DEV_DAX
 	help
 	  Support raw access to persistent memory.  Note that this
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 9630d88..4a15fa5 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -44,7 +44,6 @@ static void dax_pmem_percpu_exit(void *data)
 
 	dev_dbg(dax_pmem->dev, "%s\n", __func__);
 	percpu_ref_exit(ref);
-	wait_for_completion(&dax_pmem->cmp);
 }
 
 static void dax_pmem_percpu_kill(void *data)
@@ -54,6 +53,7 @@ static void dax_pmem_percpu_kill(void *data)
 
 	dev_dbg(dax_pmem->dev, "%s\n", __func__);
 	percpu_ref_kill(ref);
+	wait_for_completion(&dax_pmem->cmp);
 }
 
 static int dax_pmem_probe(struct device *dev)
diff --git a/drivers/extcon/extcon-qcom-spmi-misc.c b/drivers/extcon/extcon-qcom-spmi-misc.c
index ca957a5..b8cde09 100644
--- a/drivers/extcon/extcon-qcom-spmi-misc.c
+++ b/drivers/extcon/extcon-qcom-spmi-misc.c
@@ -51,7 +51,7 @@ static void qcom_usb_extcon_detect_cable(struct work_struct *work)
 	if (ret)
 		return;
 
-	extcon_set_state(info->edev, EXTCON_USB_HOST, !id);
+	extcon_set_state_sync(info->edev, EXTCON_USB_HOST, !id);
 }
 
 static irqreturn_t qcom_usb_irq_handler(int irq, void *dev_id)
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 309311b..1547589 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -73,13 +73,13 @@ struct rfc2734_header {
 
 #define fwnet_get_hdr_lf(h)		(((h)->w0 & 0xc0000000) >> 30)
 #define fwnet_get_hdr_ether_type(h)	(((h)->w0 & 0x0000ffff))
-#define fwnet_get_hdr_dg_size(h)	(((h)->w0 & 0x0fff0000) >> 16)
+#define fwnet_get_hdr_dg_size(h)	((((h)->w0 & 0x0fff0000) >> 16) + 1)
 #define fwnet_get_hdr_fg_off(h)		(((h)->w0 & 0x00000fff))
 #define fwnet_get_hdr_dgl(h)		(((h)->w1 & 0xffff0000) >> 16)
 
-#define fwnet_set_hdr_lf(lf)		((lf)  << 30)
+#define fwnet_set_hdr_lf(lf)		((lf) << 30)
 #define fwnet_set_hdr_ether_type(et)	(et)
-#define fwnet_set_hdr_dg_size(dgs)	((dgs) << 16)
+#define fwnet_set_hdr_dg_size(dgs)	(((dgs) - 1) << 16)
 #define fwnet_set_hdr_fg_off(fgo)	(fgo)
 
 #define fwnet_set_hdr_dgl(dgl)		((dgl) << 16)
@@ -578,6 +578,9 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 	int retval;
 	u16 ether_type;
 
+	if (len <= RFC2374_UNFRAG_HDR_SIZE)
+		return 0;
+
 	hdr.w0 = be32_to_cpu(buf[0]);
 	lf = fwnet_get_hdr_lf(&hdr);
 	if (lf == RFC2374_HDR_UNFRAG) {
@@ -602,7 +605,12 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 		return fwnet_finish_incoming_packet(net, skb, source_node_id,
 						    is_broadcast, ether_type);
 	}
+
 	/* A datagram fragment has been received, now the fun begins. */
+
+	if (len <= RFC2374_FRAG_HDR_SIZE)
+		return 0;
+
 	hdr.w1 = ntohl(buf[1]);
 	buf += 2;
 	len -= RFC2374_FRAG_HDR_SIZE;
@@ -614,7 +622,10 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 		fg_off = fwnet_get_hdr_fg_off(&hdr);
 	}
 	datagram_label = fwnet_get_hdr_dgl(&hdr);
-	dg_size = fwnet_get_hdr_dg_size(&hdr); /* ??? + 1 */
+	dg_size = fwnet_get_hdr_dg_size(&hdr);
+
+	if (fg_off + len > dg_size)
+		return 0;
 
 	spin_lock_irqsave(&dev->lock, flags);
 
@@ -722,6 +733,22 @@ static void fwnet_receive_packet(struct fw_card *card, struct fw_request *r,
 	fw_send_response(card, r, rcode);
 }
 
+static int gasp_source_id(__be32 *p)
+{
+	return be32_to_cpu(p[0]) >> 16;
+}
+
+static u32 gasp_specifier_id(__be32 *p)
+{
+	return (be32_to_cpu(p[0]) & 0xffff) << 8 |
+	       (be32_to_cpu(p[1]) & 0xff000000) >> 24;
+}
+
+static u32 gasp_version(__be32 *p)
+{
+	return be32_to_cpu(p[1]) & 0xffffff;
+}
+
 static void fwnet_receive_broadcast(struct fw_iso_context *context,
 		u32 cycle, size_t header_length, void *header, void *data)
 {
@@ -731,9 +758,6 @@ static void fwnet_receive_broadcast(struct fw_iso_context *context,
 	__be32 *buf_ptr;
 	int retval;
 	u32 length;
-	u16 source_node_id;
-	u32 specifier_id;
-	u32 ver;
 	unsigned long offset;
 	unsigned long flags;
 
@@ -750,22 +774,17 @@ static void fwnet_receive_broadcast(struct fw_iso_context *context,
 
 	spin_unlock_irqrestore(&dev->lock, flags);
 
-	specifier_id =    (be32_to_cpu(buf_ptr[0]) & 0xffff) << 8
-			| (be32_to_cpu(buf_ptr[1]) & 0xff000000) >> 24;
-	ver = be32_to_cpu(buf_ptr[1]) & 0xffffff;
-	source_node_id = be32_to_cpu(buf_ptr[0]) >> 16;
-
-	if (specifier_id == IANA_SPECIFIER_ID &&
-	    (ver == RFC2734_SW_VERSION
+	if (length > IEEE1394_GASP_HDR_SIZE &&
+	    gasp_specifier_id(buf_ptr) == IANA_SPECIFIER_ID &&
+	    (gasp_version(buf_ptr) == RFC2734_SW_VERSION
 #if IS_ENABLED(CONFIG_IPV6)
-	     || ver == RFC3146_SW_VERSION
+	     || gasp_version(buf_ptr) == RFC3146_SW_VERSION
 #endif
-	    )) {
-		buf_ptr += 2;
-		length -= IEEE1394_GASP_HDR_SIZE;
-		fwnet_incoming_packet(dev, buf_ptr, length, source_node_id,
+	    ))
+		fwnet_incoming_packet(dev, buf_ptr + 2,
+				      length - IEEE1394_GASP_HDR_SIZE,
+				      gasp_source_id(buf_ptr),
 				      context->card->generation, true);
-	}
 
 	packet.payload_length = dev->rcv_buffer_size;
 	packet.interrupt = 1;
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index cd5dc27..1ed6132 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -293,10 +293,10 @@ static void mvebu_gpio_irq_ack(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
-	u32 mask = ~(1 << (d->irq - gc->irq_base));
+	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	writel_relaxed(mask, mvebu_gpioreg_edge_cause(mvchip));
+	writel_relaxed(~mask, mvebu_gpioreg_edge_cause(mvchip));
 	irq_gc_unlock(gc);
 }
 
@@ -305,7 +305,7 @@ static void mvebu_gpio_edge_irq_mask(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
-	u32 mask = 1 << (d->irq - gc->irq_base);
+	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
 	ct->mask_cache_priv &= ~mask;
@@ -319,8 +319,7 @@ static void mvebu_gpio_edge_irq_unmask(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
-
-	u32 mask = 1 << (d->irq - gc->irq_base);
+	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
 	ct->mask_cache_priv |= mask;
@@ -333,8 +332,7 @@ static void mvebu_gpio_level_irq_mask(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
-
-	u32 mask = 1 << (d->irq - gc->irq_base);
+	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
 	ct->mask_cache_priv &= ~mask;
@@ -347,8 +345,7 @@ static void mvebu_gpio_level_irq_unmask(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct mvebu_gpio_chip *mvchip = gc->private;
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
-
-	u32 mask = 1 << (d->irq - gc->irq_base);
+	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
 	ct->mask_cache_priv |= mask;
@@ -462,7 +459,7 @@ static void mvebu_gpio_irq_handler(struct irq_desc *desc)
 	for (i = 0; i < mvchip->chip.ngpio; i++) {
 		int irq;
 
-		irq = mvchip->irqbase + i;
+		irq = irq_find_mapping(mvchip->domain, i);
 
 		if (!(cause & (1 << i)))
 			continue;
@@ -655,6 +652,7 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
 	struct irq_chip_type *ct;
 	struct clk *clk;
 	unsigned int ngpios;
+	bool have_irqs;
 	int soc_variant;
 	int i, cpu, id;
 	int err;
@@ -665,6 +663,9 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
 	else
 		soc_variant = MVEBU_GPIO_SOC_VARIANT_ORION;
 
+	/* Some gpio controllers do not provide irq support */
+	have_irqs = of_irq_count(np) != 0;
+
 	mvchip = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_gpio_chip),
 			      GFP_KERNEL);
 	if (!mvchip)
@@ -697,7 +698,8 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
 	mvchip->chip.get = mvebu_gpio_get;
 	mvchip->chip.direction_output = mvebu_gpio_direction_output;
 	mvchip->chip.set = mvebu_gpio_set;
-	mvchip->chip.to_irq = mvebu_gpio_to_irq;
+	if (have_irqs)
+		mvchip->chip.to_irq = mvebu_gpio_to_irq;
 	mvchip->chip.base = id * MVEBU_MAX_GPIO_PER_BANK;
 	mvchip->chip.ngpio = ngpios;
 	mvchip->chip.can_sleep = false;
@@ -758,34 +760,30 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
 	devm_gpiochip_add_data(&pdev->dev, &mvchip->chip, mvchip);
 
 	/* Some gpio controllers do not provide irq support */
-	if (!of_irq_count(np))
+	if (!have_irqs)
 		return 0;
 
-	/* Setup the interrupt handlers. Each chip can have up to 4
-	 * interrupt handlers, with each handler dealing with 8 GPIO
-	 * pins. */
-	for (i = 0; i < 4; i++) {
-		int irq = platform_get_irq(pdev, i);
-
-		if (irq < 0)
-			continue;
-		irq_set_chained_handler_and_data(irq, mvebu_gpio_irq_handler,
-						 mvchip);
+	mvchip->domain =
+	    irq_domain_add_linear(np, ngpios, &irq_generic_chip_ops, NULL);
+	if (!mvchip->domain) {
+		dev_err(&pdev->dev, "couldn't allocate irq domain %s (DT).\n",
+			mvchip->chip.label);
+		return -ENODEV;
 	}
 
-	mvchip->irqbase = irq_alloc_descs(-1, 0, ngpios, -1);
-	if (mvchip->irqbase < 0) {
-		dev_err(&pdev->dev, "no irqs\n");
-		return mvchip->irqbase;
+	err = irq_alloc_domain_generic_chips(
+	    mvchip->domain, ngpios, 2, np->name, handle_level_irq,
+	    IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_LEVEL, 0, 0);
+	if (err) {
+		dev_err(&pdev->dev, "couldn't allocate irq chips %s (DT).\n",
+			mvchip->chip.label);
+		goto err_domain;
 	}
 
-	gc = irq_alloc_generic_chip("mvebu_gpio_irq", 2, mvchip->irqbase,
-				    mvchip->membase, handle_level_irq);
-	if (!gc) {
-		dev_err(&pdev->dev, "Cannot allocate generic irq_chip\n");
-		return -ENOMEM;
-	}
-
+	/* NOTE: The common accessors cannot be used because of the percpu
+	 * access to the mask registers
+	 */
+	gc = irq_get_domain_generic_chip(mvchip->domain, 0);
 	gc->private = mvchip;
 	ct = &gc->chip_types[0];
 	ct->type = IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW;
@@ -803,27 +801,23 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
 	ct->handler = handle_edge_irq;
 	ct->chip.name = mvchip->chip.label;
 
-	irq_setup_generic_chip(gc, IRQ_MSK(ngpios), 0,
-			       IRQ_NOREQUEST, IRQ_LEVEL | IRQ_NOPROBE);
+	/* Setup the interrupt handlers. Each chip can have up to 4
+	 * interrupt handlers, with each handler dealing with 8 GPIO
+	 * pins.
+	 */
+	for (i = 0; i < 4; i++) {
+		int irq = platform_get_irq(pdev, i);
 
-	/* Setup irq domain on top of the generic chip. */
-	mvchip->domain = irq_domain_add_simple(np, mvchip->chip.ngpio,
-					       mvchip->irqbase,
-					       &irq_domain_simple_ops,
-					       mvchip);
-	if (!mvchip->domain) {
-		dev_err(&pdev->dev, "couldn't allocate irq domain %s (DT).\n",
-			mvchip->chip.label);
-		err = -ENODEV;
-		goto err_generic_chip;
+		if (irq < 0)
+			continue;
+		irq_set_chained_handler_and_data(irq, mvebu_gpio_irq_handler,
+						 mvchip);
 	}
 
 	return 0;
 
-err_generic_chip:
-	irq_remove_generic_chip(gc, IRQ_MSK(ngpios), IRQ_NOREQUEST,
-				IRQ_LEVEL | IRQ_NOPROBE);
-	kfree(gc);
+err_domain:
+	irq_domain_remove(mvchip->domain);
 
 	return err;
 }
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index ecad3f0..193f15d 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -26,14 +26,18 @@
 
 #include "gpiolib.h"
 
-static int of_gpiochip_match_node(struct gpio_chip *chip, void *data)
+static int of_gpiochip_match_node_and_xlate(struct gpio_chip *chip, void *data)
 {
-	return chip->gpiodev->dev.of_node == data;
+	struct of_phandle_args *gpiospec = data;
+
+	return chip->gpiodev->dev.of_node == gpiospec->np &&
+				chip->of_xlate(chip, gpiospec, NULL) >= 0;
 }
 
-static struct gpio_chip *of_find_gpiochip_by_node(struct device_node *np)
+static struct gpio_chip *of_find_gpiochip_by_xlate(
+					struct of_phandle_args *gpiospec)
 {
-	return gpiochip_find(np, of_gpiochip_match_node);
+	return gpiochip_find(gpiospec, of_gpiochip_match_node_and_xlate);
 }
 
 static struct gpio_desc *of_xlate_and_get_gpiod_flags(struct gpio_chip *chip,
@@ -79,7 +83,7 @@ struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np,
 		return ERR_PTR(ret);
 	}
 
-	chip = of_find_gpiochip_by_node(gpiospec.np);
+	chip = of_find_gpiochip_by_xlate(&gpiospec);
 	if (!chip) {
 		desc = ERR_PTR(-EPROBE_DEFER);
 		goto out;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 20e09b7..93ed0e0 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -21,6 +21,7 @@
 #include <linux/uaccess.h>
 #include <linux/compat.h>
 #include <linux/anon_inodes.h>
+#include <linux/file.h>
 #include <linux/kfifo.h>
 #include <linux/poll.h>
 #include <linux/timekeeping.h>
@@ -423,6 +424,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 {
 	struct gpiohandle_request handlereq;
 	struct linehandle_state *lh;
+	struct file *file;
 	int fd, i, ret;
 
 	if (copy_from_user(&handlereq, ip, sizeof(handlereq)))
@@ -499,26 +501,41 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 	i--;
 	lh->numdescs = handlereq.lines;
 
-	fd = anon_inode_getfd("gpio-linehandle",
-			      &linehandle_fileops,
-			      lh,
-			      O_RDONLY | O_CLOEXEC);
+	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		ret = fd;
 		goto out_free_descs;
 	}
 
+	file = anon_inode_getfile("gpio-linehandle",
+				  &linehandle_fileops,
+				  lh,
+				  O_RDONLY | O_CLOEXEC);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto out_put_unused_fd;
+	}
+
 	handlereq.fd = fd;
 	if (copy_to_user(ip, &handlereq, sizeof(handlereq))) {
-		ret = -EFAULT;
-		goto out_free_descs;
+		/*
+		 * fput() will trigger the release() callback, so do not go onto
+		 * the regular error cleanup path here.
+		 */
+		fput(file);
+		put_unused_fd(fd);
+		return -EFAULT;
 	}
 
+	fd_install(fd, file);
+
 	dev_dbg(&gdev->dev, "registered chardev handle for %d lines\n",
 		lh->numdescs);
 
 	return 0;
 
+out_put_unused_fd:
+	put_unused_fd(fd);
 out_free_descs:
 	for (; i >= 0; i--)
 		gpiod_free(lh->descs[i]);
@@ -721,6 +738,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 	struct gpioevent_request eventreq;
 	struct lineevent_state *le;
 	struct gpio_desc *desc;
+	struct file *file;
 	u32 offset;
 	u32 lflags;
 	u32 eflags;
@@ -815,23 +833,38 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 	if (ret)
 		goto out_free_desc;
 
-	fd = anon_inode_getfd("gpio-event",
-			      &lineevent_fileops,
-			      le,
-			      O_RDONLY | O_CLOEXEC);
+	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		ret = fd;
 		goto out_free_irq;
 	}
 
+	file = anon_inode_getfile("gpio-event",
+				  &lineevent_fileops,
+				  le,
+				  O_RDONLY | O_CLOEXEC);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto out_put_unused_fd;
+	}
+
 	eventreq.fd = fd;
 	if (copy_to_user(ip, &eventreq, sizeof(eventreq))) {
-		ret = -EFAULT;
-		goto out_free_irq;
+		/*
+		 * fput() will trigger the release() callback, so do not go onto
+		 * the regular error cleanup path here.
+		 */
+		fput(file);
+		put_unused_fd(fd);
+		return -EFAULT;
 	}
 
+	fd_install(fd, file);
+
 	return 0;
 
+out_put_unused_fd:
+	put_unused_fd(fd);
 out_free_irq:
 	free_irq(le->irq, le);
 out_free_desc:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index b0f6e69..82dc8d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -519,7 +519,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true,
 					   &duplicates);
 		if (unlikely(r != 0)) {
-			DRM_ERROR("ttm_eu_reserve_buffers failed.\n");
+			if (r != -ERESTARTSYS)
+				DRM_ERROR("ttm_eu_reserve_buffers failed.\n");
 			goto error_free_pages;
 		}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b4f4a92..7ca07e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1959,6 +1959,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	/* evict remaining vram memory */
 	amdgpu_bo_evict_vram(adev);
 
+	amdgpu_atombios_scratch_regs_save(adev);
 	pci_save_state(dev->pdev);
 	if (suspend) {
 		/* Shut down the device */
@@ -2010,6 +2011,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 			return r;
 		}
 	}
+	amdgpu_atombios_scratch_regs_restore(adev);
 
 	/* post card */
 	if (!amdgpu_card_posted(adev) || !resume) {
@@ -2268,8 +2270,6 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
 	}
 
 	if (need_full_reset) {
-		/* save scratch */
-		amdgpu_atombios_scratch_regs_save(adev);
 		r = amdgpu_suspend(adev);
 
 retry:
@@ -2279,8 +2279,9 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
 			amdgpu_display_stop_mc_access(adev, &save);
 			amdgpu_wait_for_idle(adev, AMD_IP_BLOCK_TYPE_GMC);
 		}
-
+		amdgpu_atombios_scratch_regs_save(adev);
 		r = amdgpu_asic_reset(adev);
+		amdgpu_atombios_scratch_regs_restore(adev);
 		/* post card */
 		amdgpu_atom_asic_init(adev->mode_info.atom_context);
 
@@ -2288,8 +2289,6 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
 			dev_info(adev->dev, "GPU reset succeeded, trying to resume\n");
 			r = amdgpu_resume(adev);
 		}
-		/* restore scratch */
-		amdgpu_atombios_scratch_regs_restore(adev);
 	}
 	if (!r) {
 		amdgpu_irq_gpu_reset_resume_helper(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 3a2e42f..77b34ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -68,6 +68,7 @@ int amdgpu_fence_slab_init(void)
 
 void amdgpu_fence_slab_fini(void)
 {
+	rcu_barrier();
 	kmem_cache_destroy(amdgpu_fence_slab);
 }
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 278708f..9fa8098 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -239,6 +239,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 	if (r) {
 		adev->irq.installed = false;
 		flush_work(&adev->hotplug_work);
+		cancel_work_sync(&adev->reset_work);
 		return r;
 	}
 
@@ -264,6 +265,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)
 		if (adev->irq.msi_enabled)
 			pci_disable_msi(adev->pdev);
 		flush_work(&adev->hotplug_work);
+		cancel_work_sync(&adev->reset_work);
 	}
 
 	for (i = 0; i < AMDGPU_MAX_IRQ_SRC_ID; ++i) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index c2c7fb1..203d98b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -459,10 +459,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		/* return all clocks in KHz */
 		dev_info.gpu_counter_freq = amdgpu_asic_get_xclk(adev) * 10;
 		if (adev->pm.dpm_enabled) {
-			dev_info.max_engine_clock =
-				adev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk * 10;
-			dev_info.max_memory_clock =
-				adev->pm.dpm.dyn_state.max_clock_voltage_on_ac.mclk * 10;
+			dev_info.max_engine_clock = amdgpu_dpm_get_sclk(adev, false) * 10;
+			dev_info.max_memory_clock = amdgpu_dpm_get_mclk(adev, false) * 10;
 		} else {
 			dev_info.max_engine_clock = adev->pm.default_sclk * 10;
 			dev_info.max_memory_clock = adev->pm.default_mclk * 10;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index aa074fa..f3efb1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -754,6 +754,10 @@ static const char *amdgpu_vram_names[] = {
 
 int amdgpu_bo_init(struct amdgpu_device *adev)
 {
+	/* reserve PAT memory space to WC for VRAM */
+	arch_io_reserve_memtype_wc(adev->mc.aper_base,
+				   adev->mc.aper_size);
+
 	/* Add an MTRR for the VRAM */
 	adev->mc.vram_mtrr = arch_phys_wc_add(adev->mc.aper_base,
 					      adev->mc.aper_size);
@@ -769,6 +773,7 @@ void amdgpu_bo_fini(struct amdgpu_device *adev)
 {
 	amdgpu_ttm_fini(adev);
 	arch_phys_wc_del(adev->mc.vram_mtrr);
+	arch_io_free_memtype_wc(adev->mc.aper_base, adev->mc.aper_size);
 }
 
 int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 06f2432..968c426 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1758,5 +1758,6 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
 		fence_put(adev->vm_manager.ids[i].first);
 		amdgpu_sync_free(&adev->vm_manager.ids[i].active);
 		fence_put(id->flushed_updates);
+		fence_put(id->last_flush);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 1d8c375..5be788b 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -4075,7 +4075,7 @@ static int ci_enable_uvd_dpm(struct amdgpu_device *adev, bool enable)
 							  pi->dpm_level_enable_mask.mclk_dpm_enable_mask);
 		}
 	} else {
-		if (pi->last_mclk_dpm_enable_mask & 0x1) {
+		if (pi->uvd_enabled) {
 			pi->uvd_enabled = false;
 			pi->dpm_level_enable_mask.mclk_dpm_enable_mask |= 1;
 			amdgpu_ci_send_msg_to_smc_with_parameter(adev,
@@ -6236,6 +6236,8 @@ static int ci_dpm_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	flush_work(&adev->pm.dpm.thermal.work);
+
 	mutex_lock(&adev->pm.mutex);
 	amdgpu_pm_sysfs_fini(adev);
 	ci_dpm_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 4108c68..9260cae 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -3151,10 +3151,6 @@ static int dce_v10_0_hw_fini(void *handle)
 
 static int dce_v10_0_suspend(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	amdgpu_atombios_scratch_regs_save(adev);
-
 	return dce_v10_0_hw_fini(handle);
 }
 
@@ -3165,8 +3161,6 @@ static int dce_v10_0_resume(void *handle)
 
 	ret = dce_v10_0_hw_init(handle);
 
-	amdgpu_atombios_scratch_regs_restore(adev);
-
 	/* turn on the BL */
 	if (adev->mode_info.bl_encoder) {
 		u8 bl_level = amdgpu_display_backlight_get_level(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index f264b8f..367739b 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -3215,10 +3215,6 @@ static int dce_v11_0_hw_fini(void *handle)
 
 static int dce_v11_0_suspend(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	amdgpu_atombios_scratch_regs_save(adev);
-
 	return dce_v11_0_hw_fini(handle);
 }
 
@@ -3229,8 +3225,6 @@ static int dce_v11_0_resume(void *handle)
 
 	ret = dce_v11_0_hw_init(handle);
 
-	amdgpu_atombios_scratch_regs_restore(adev);
-
 	/* turn on the BL */
 	if (adev->mode_info.bl_encoder) {
 		u8 bl_level = amdgpu_display_backlight_get_level(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index b948d6c..15f9fc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -2482,10 +2482,6 @@ static int dce_v6_0_hw_fini(void *handle)
 
 static int dce_v6_0_suspend(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	amdgpu_atombios_scratch_regs_save(adev);
-
 	return dce_v6_0_hw_fini(handle);
 }
 
@@ -2496,8 +2492,6 @@ static int dce_v6_0_resume(void *handle)
 
 	ret = dce_v6_0_hw_init(handle);
 
-	amdgpu_atombios_scratch_regs_restore(adev);
-
 	/* turn on the BL */
 	if (adev->mode_info.bl_encoder) {
 		u8 bl_level = amdgpu_display_backlight_get_level(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 5966166..8c4d808 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -3033,10 +3033,6 @@ static int dce_v8_0_hw_fini(void *handle)
 
 static int dce_v8_0_suspend(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	amdgpu_atombios_scratch_regs_save(adev);
-
 	return dce_v8_0_hw_fini(handle);
 }
 
@@ -3047,8 +3043,6 @@ static int dce_v8_0_resume(void *handle)
 
 	ret = dce_v8_0_hw_init(handle);
 
-	amdgpu_atombios_scratch_regs_restore(adev);
-
 	/* turn on the BL */
 	if (adev->mode_info.bl_encoder) {
 		u8 bl_level = amdgpu_display_backlight_get_level(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index ee6a48a..bb97182 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -640,7 +640,6 @@ static const u32 stoney_mgcg_cgcg_init[] =
 	mmCP_MEM_SLP_CNTL, 0xffffffff, 0x00020201,
 	mmRLC_MEM_SLP_CNTL, 0xffffffff, 0x00020201,
 	mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96940200,
-	mmATC_MISC_CG, 0xffffffff, 0x000c0200,
 };
 
 static void gfx_v8_0_set_ring_funcs(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index c22ef14..a16b220 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -100,6 +100,7 @@ static const u32 cz_mgcg_cgcg_init[] =
 
 static const u32 stoney_mgcg_cgcg_init[] =
 {
+	mmATC_MISC_CG, 0xffffffff, 0x000c0200,
 	mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index f8618a3..71d2856 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -3063,6 +3063,8 @@ static int kv_dpm_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	flush_work(&adev->pm.dpm.thermal.work);
+
 	mutex_lock(&adev->pm.mutex);
 	amdgpu_pm_sysfs_fini(adev);
 	kv_dpm_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 3de7bca..d6f85b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -3477,6 +3477,49 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 	int i;
 	struct si_dpm_quirk *p = si_dpm_quirk_list;
 
+	/* limit all SI kickers */
+	if (adev->asic_type == CHIP_PITCAIRN) {
+		if ((adev->pdev->revision == 0x81) ||
+		    (adev->pdev->device == 0x6810) ||
+		    (adev->pdev->device == 0x6811) ||
+		    (adev->pdev->device == 0x6816) ||
+		    (adev->pdev->device == 0x6817) ||
+		    (adev->pdev->device == 0x6806))
+			max_mclk = 120000;
+	} else if (adev->asic_type == CHIP_VERDE) {
+		if ((adev->pdev->revision == 0x81) ||
+		    (adev->pdev->revision == 0x83) ||
+		    (adev->pdev->revision == 0x87) ||
+		    (adev->pdev->device == 0x6820) ||
+		    (adev->pdev->device == 0x6821) ||
+		    (adev->pdev->device == 0x6822) ||
+		    (adev->pdev->device == 0x6823) ||
+		    (adev->pdev->device == 0x682A) ||
+		    (adev->pdev->device == 0x682B)) {
+			max_sclk = 75000;
+			max_mclk = 80000;
+		}
+	} else if (adev->asic_type == CHIP_OLAND) {
+		if ((adev->pdev->revision == 0xC7) ||
+		    (adev->pdev->revision == 0x80) ||
+		    (adev->pdev->revision == 0x81) ||
+		    (adev->pdev->revision == 0x83) ||
+		    (adev->pdev->device == 0x6604) ||
+		    (adev->pdev->device == 0x6605)) {
+			max_sclk = 75000;
+			max_mclk = 80000;
+		}
+	} else if (adev->asic_type == CHIP_HAINAN) {
+		if ((adev->pdev->revision == 0x81) ||
+		    (adev->pdev->revision == 0x83) ||
+		    (adev->pdev->revision == 0xC3) ||
+		    (adev->pdev->device == 0x6664) ||
+		    (adev->pdev->device == 0x6665) ||
+		    (adev->pdev->device == 0x6667)) {
+			max_sclk = 75000;
+			max_mclk = 80000;
+		}
+	}
 	/* Apply dpm quirks */
 	while (p && p->chip_device != 0) {
 		if (adev->pdev->vendor == p->chip_vendor &&
@@ -3489,22 +3532,6 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		}
 		++p;
 	}
-	/* limit mclk on all R7 370 parts for stability */
-	if (adev->pdev->device == 0x6811 &&
-	    adev->pdev->revision == 0x81)
-		max_mclk = 120000;
-	/* limit sclk/mclk on Jet parts for stability */
-	if (adev->pdev->device == 0x6665 &&
-	    adev->pdev->revision == 0xc3) {
-		max_sclk = 75000;
-		max_mclk = 80000;
-	}
-	/* Limit clocks for some HD8600 parts */
-	if (adev->pdev->device == 0x6660 &&
-	    adev->pdev->revision == 0x83) {
-		max_sclk = 75000;
-		max_mclk = 80000;
-	}
 
 	if (rps->vce_active) {
 		rps->evclk = adev->pm.dpm.vce_states[adev->pm.dpm.vce_level].evclk;
@@ -7777,6 +7804,8 @@ static int si_dpm_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	flush_work(&adev->pm.dpm.thermal.work);
+
 	mutex_lock(&adev->pm.mutex);
 	amdgpu_pm_sysfs_fini(adev);
 	si_dpm_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 8533269..6feed72 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -52,6 +52,8 @@
 #define VCE_V3_0_STACK_SIZE	(64 * 1024)
 #define VCE_V3_0_DATA_SIZE	((16 * 1024 * AMDGPU_MAX_VCE_HANDLES) + (52 * 1024))
 
+#define FW_52_8_3	((52 << 24) | (8 << 16) | (3 << 8))
+
 static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx);
 static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev);
 static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -382,6 +384,10 @@ static int vce_v3_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	/* 52.8.3 required for 3 ring support */
+	if (adev->vce.fw_version < FW_52_8_3)
+		adev->vce.num_rings = 2;
+
 	r = amdgpu_vce_resume(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index c0d9aad..7c13090 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1651,7 +1651,7 @@ static int vi_common_early_init(void *handle)
 			AMD_CG_SUPPORT_SDMA_MGCG |
 			AMD_CG_SUPPORT_SDMA_LS |
 			AMD_CG_SUPPORT_VCE_MGCG;
-		adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+		adev->pg_flags = AMD_PG_SUPPORT_GFX_PG |
 			AMD_PG_SUPPORT_GFX_SMG |
 			AMD_PG_SUPPORT_GFX_PIPELINE |
 			AMD_PG_SUPPORT_UVD |
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 1167205..2ba7937 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -716,7 +716,7 @@ int phm_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
 			*voltage = 1150;
 	} else {
 		ret = atomctrl_get_voltage_evv_on_sclk_ai(hwmgr, voltage_type, sclk, id, &vol);
-		*voltage = (uint16_t)vol/100;
+		*voltage = (uint16_t)(vol/100);
 	}
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index 1126bd4..0894527 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1320,7 +1320,8 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
 	if (0 != result)
 		return result;
 
-	*voltage = le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel);
+	*voltage = le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)
+				(&get_voltage_info_param_space))->ulVoltageLevel);
 
 	return result;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
index 7de701d..4477c55 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
@@ -1201,12 +1201,15 @@ static uint32_t make_classification_flags(struct pp_hwmgr *hwmgr,
 static int ppt_get_num_of_vce_state_table_entries_v1_0(struct pp_hwmgr *hwmgr)
 {
 	const ATOM_Tonga_POWERPLAYTABLE *pp_table = get_powerplay_table(hwmgr);
-	const ATOM_Tonga_VCE_State_Table *vce_state_table =
-				(ATOM_Tonga_VCE_State_Table *)(((unsigned long)pp_table) + le16_to_cpu(pp_table->usVCEStateTableOffset));
+	const ATOM_Tonga_VCE_State_Table *vce_state_table;
 
-	if (vce_state_table == NULL)
+
+	if (pp_table == NULL)
 		return 0;
 
+	vce_state_table = (void *)pp_table +
+			le16_to_cpu(pp_table->usVCEStateTableOffset);
+
 	return vce_state_table->ucNumEntries;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 609996c..7585402 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -1168,8 +1168,8 @@ int smu7_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 
 	tmp_result = (!smum_is_dpm_running(hwmgr)) ? 0 : -1;
 	PP_ASSERT_WITH_CODE(tmp_result == 0,
-			"DPM is already running right now, no need to enable DPM!",
-			return 0);
+			"DPM is already running",
+			);
 
 	if (smu7_voltage_control(hwmgr)) {
 		tmp_result = smu7_enable_voltage_control(hwmgr);
@@ -2127,15 +2127,18 @@ static int smu7_patch_acp_vddc(struct pp_hwmgr *hwmgr,
 }
 
 static int smu7_patch_limits_vddc(struct pp_hwmgr *hwmgr,
-				     struct phm_clock_and_voltage_limits *tab)
+				  struct phm_clock_and_voltage_limits *tab)
 {
+	uint32_t vddc, vddci;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
 	if (tab) {
-		smu7_patch_ppt_v0_with_vdd_leakage(hwmgr, (uint32_t *)&tab->vddc,
-							&data->vddc_leakage);
-		smu7_patch_ppt_v0_with_vdd_leakage(hwmgr, (uint32_t *)&tab->vddci,
-							&data->vddci_leakage);
+		smu7_patch_ppt_v0_with_vdd_leakage(hwmgr, &vddc,
+						   &data->vddc_leakage);
+		tab->vddc = vddc;
+		smu7_patch_ppt_v0_with_vdd_leakage(hwmgr, &vddci,
+						   &data->vddci_leakage);
+		tab->vddci = vddci;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 963a24d..910b8d5 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -645,6 +645,7 @@ void amd_sched_fini(struct amd_gpu_scheduler *sched)
 {
 	if (sched->thread)
 		kthread_stop(sched->thread);
+	rcu_barrier();
 	if (atomic_dec_and_test(&sched_fence_slab_ref))
 		kmem_cache_destroy(sched_fence_slab);
 }
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index 6b63bea..3653b5a 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -103,7 +103,7 @@ static void amd_sched_fence_free(struct rcu_head *rcu)
 }
 
 /**
- * amd_sched_fence_release - callback that fence can be freed
+ * amd_sched_fence_release_scheduled - callback that fence can be freed
  *
  * @fence: fence
  *
@@ -118,7 +118,7 @@ static void amd_sched_fence_release_scheduled(struct fence *f)
 }
 
 /**
- * amd_sched_fence_release_scheduled - drop extra reference
+ * amd_sched_fence_release_finished - drop extra reference
  *
  * @f: fence
  *
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 608df4c..0743e65 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -267,6 +267,8 @@ int ast_mm_init(struct ast_private *ast)
 		return ret;
 	}
 
+	arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+				   pci_resource_len(dev->pdev, 0));
 	ast->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
 					pci_resource_len(dev->pdev, 0));
 
@@ -275,11 +277,15 @@ int ast_mm_init(struct ast_private *ast)
 
 void ast_mm_fini(struct ast_private *ast)
 {
+	struct drm_device *dev = ast->dev;
+
 	ttm_bo_device_release(&ast->ttm.bdev);
 
 	ast_ttm_global_release(ast);
 
 	arch_phys_wc_del(ast->fb_mtrr);
+	arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+				pci_resource_len(dev->pdev, 0));
 }
 
 void ast_ttm_placement(struct ast_bo *bo, int domain)
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index bb2438d..5e7e63c 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -267,6 +267,9 @@ int cirrus_mm_init(struct cirrus_device *cirrus)
 		return ret;
 	}
 
+	arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+				   pci_resource_len(dev->pdev, 0));
+
 	cirrus->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
 					   pci_resource_len(dev->pdev, 0));
 
@@ -276,6 +279,8 @@ int cirrus_mm_init(struct cirrus_device *cirrus)
 
 void cirrus_mm_fini(struct cirrus_device *cirrus)
 {
+	struct drm_device *dev = cirrus->dev;
+
 	if (!cirrus->mm_inited)
 		return;
 
@@ -285,6 +290,8 @@ void cirrus_mm_fini(struct cirrus_device *cirrus)
 
 	arch_phys_wc_del(cirrus->fb_mtrr);
 	cirrus->fb_mtrr = 0;
+	arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+				pci_resource_len(dev->pdev, 0));
 }
 
 void cirrus_ttm_placement(struct cirrus_bo *bo, int domain)
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 2373960..e6862a7 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -420,18 +420,21 @@ drm_atomic_replace_property_blob_from_id(struct drm_crtc *crtc,
 					 ssize_t expected_size,
 					 bool *replaced)
 {
-	struct drm_device *dev = crtc->dev;
 	struct drm_property_blob *new_blob = NULL;
 
 	if (blob_id != 0) {
-		new_blob = drm_property_lookup_blob(dev, blob_id);
+		new_blob = drm_property_lookup_blob(crtc->dev, blob_id);
 		if (new_blob == NULL)
 			return -EINVAL;
-		if (expected_size > 0 && expected_size != new_blob->length)
+
+		if (expected_size > 0 && expected_size != new_blob->length) {
+			drm_property_unreference_blob(new_blob);
 			return -EINVAL;
+		}
 	}
 
 	drm_atomic_replace_property_blob(blob, new_blob, replaced);
+	drm_property_unreference_blob(new_blob);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index c3f8347..21f9926 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -594,10 +594,6 @@ drm_atomic_helper_check_planes(struct drm_device *dev,
 	struct drm_plane_state *plane_state;
 	int i, ret = 0;
 
-	ret = drm_atomic_normalize_zpos(dev, state);
-	if (ret)
-		return ret;
-
 	for_each_plane_in_state(state, plane, plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs;
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 04e4571..aa64448 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -914,6 +914,7 @@ static void drm_dp_destroy_port(struct kref *kref)
 		/* no need to clean up vcpi
 		 * as if we have no connector we never setup a vcpi */
 		drm_dp_port_teardown_pdt(port, port->pdt);
+		port->pdt = DP_PEER_DEVICE_NONE;
 	}
 	kfree(port);
 }
@@ -1159,7 +1160,9 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 			drm_dp_put_port(port);
 			goto out;
 		}
-		if (port->port_num >= DP_MST_LOGICAL_PORT_0) {
+		if ((port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV ||
+		     port->pdt == DP_PEER_DEVICE_SST_SINK) &&
+		    port->port_num >= DP_MST_LOGICAL_PORT_0) {
 			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
 			drm_mode_connector_set_tile_property(port->connector);
 		}
@@ -2919,6 +2922,7 @@ static void drm_dp_destroy_connector_work(struct work_struct *work)
 		mgr->cbs->destroy_connector(mgr, port->connector);
 
 		drm_dp_port_teardown_pdt(port, port->pdt);
+		port->pdt = DP_PEER_DEVICE_NONE;
 
 		if (!port->input && port->vcpi.vcpi > 0) {
 			drm_dp_mst_reset_vcpi_slots(mgr, port);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 03414bd..6c75e62 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -131,7 +131,12 @@ int drm_fb_helper_single_add_all_connectors(struct drm_fb_helper *fb_helper)
 	return 0;
 fail:
 	for (i = 0; i < fb_helper->connector_count; i++) {
-		kfree(fb_helper->connector_info[i]);
+		struct drm_fb_helper_connector *fb_helper_connector =
+			fb_helper->connector_info[i];
+
+		drm_connector_unreference(fb_helper_connector->connector);
+
+		kfree(fb_helper_connector);
 		fb_helper->connector_info[i] = NULL;
 	}
 	fb_helper->connector_count = 0;
@@ -603,6 +608,24 @@ int drm_fb_helper_blank(int blank, struct fb_info *info)
 }
 EXPORT_SYMBOL(drm_fb_helper_blank);
 
+static void drm_fb_helper_modeset_release(struct drm_fb_helper *helper,
+					  struct drm_mode_set *modeset)
+{
+	int i;
+
+	for (i = 0; i < modeset->num_connectors; i++) {
+		drm_connector_unreference(modeset->connectors[i]);
+		modeset->connectors[i] = NULL;
+	}
+	modeset->num_connectors = 0;
+
+	drm_mode_destroy(helper->dev, modeset->mode);
+	modeset->mode = NULL;
+
+	/* FIXME should hold a ref? */
+	modeset->fb = NULL;
+}
+
 static void drm_fb_helper_crtc_free(struct drm_fb_helper *helper)
 {
 	int i;
@@ -612,10 +635,12 @@ static void drm_fb_helper_crtc_free(struct drm_fb_helper *helper)
 		kfree(helper->connector_info[i]);
 	}
 	kfree(helper->connector_info);
+
 	for (i = 0; i < helper->crtc_count; i++) {
-		kfree(helper->crtc_info[i].mode_set.connectors);
-		if (helper->crtc_info[i].mode_set.mode)
-			drm_mode_destroy(helper->dev, helper->crtc_info[i].mode_set.mode);
+		struct drm_mode_set *modeset = &helper->crtc_info[i].mode_set;
+
+		drm_fb_helper_modeset_release(helper, modeset);
+		kfree(modeset->connectors);
 	}
 	kfree(helper->crtc_info);
 }
@@ -644,7 +669,9 @@ static void drm_fb_helper_dirty_work(struct work_struct *work)
 	clip->x2 = clip->y2 = 0;
 	spin_unlock_irqrestore(&helper->dirty_lock, flags);
 
-	helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1);
+	/* call dirty callback only when it has been really touched */
+	if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2)
+		helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1);
 }
 
 /**
@@ -2088,7 +2115,6 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
 	struct drm_fb_helper_crtc **crtcs;
 	struct drm_display_mode **modes;
 	struct drm_fb_offset *offsets;
-	struct drm_mode_set *modeset;
 	bool *enabled;
 	int width, height;
 	int i;
@@ -2136,45 +2162,35 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
 
 	/* need to set the modesets up here for use later */
 	/* fill out the connector<->crtc mappings into the modesets */
-	for (i = 0; i < fb_helper->crtc_count; i++) {
-		modeset = &fb_helper->crtc_info[i].mode_set;
-		modeset->num_connectors = 0;
-		modeset->fb = NULL;
-	}
+	for (i = 0; i < fb_helper->crtc_count; i++)
+		drm_fb_helper_modeset_release(fb_helper,
+					      &fb_helper->crtc_info[i].mode_set);
 
 	for (i = 0; i < fb_helper->connector_count; i++) {
 		struct drm_display_mode *mode = modes[i];
 		struct drm_fb_helper_crtc *fb_crtc = crtcs[i];
 		struct drm_fb_offset *offset = &offsets[i];
-		modeset = &fb_crtc->mode_set;
+		struct drm_mode_set *modeset = &fb_crtc->mode_set;
 
 		if (mode && fb_crtc) {
+			struct drm_connector *connector =
+				fb_helper->connector_info[i]->connector;
+
 			DRM_DEBUG_KMS("desired mode %s set on crtc %d (%d,%d)\n",
 				      mode->name, fb_crtc->mode_set.crtc->base.id, offset->x, offset->y);
+
 			fb_crtc->desired_mode = mode;
 			fb_crtc->x = offset->x;
 			fb_crtc->y = offset->y;
-			if (modeset->mode)
-				drm_mode_destroy(dev, modeset->mode);
 			modeset->mode = drm_mode_duplicate(dev,
 							   fb_crtc->desired_mode);
-			modeset->connectors[modeset->num_connectors++] = fb_helper->connector_info[i]->connector;
+			drm_connector_reference(connector);
+			modeset->connectors[modeset->num_connectors++] = connector;
 			modeset->fb = fb_helper->fb;
 			modeset->x = offset->x;
 			modeset->y = offset->y;
 		}
 	}
-
-	/* Clear out any old modes if there are no more connected outputs. */
-	for (i = 0; i < fb_helper->crtc_count; i++) {
-		modeset = &fb_helper->crtc_info[i].mode_set;
-		if (modeset->num_connectors == 0) {
-			BUG_ON(modeset->fb);
-			if (modeset->mode)
-				drm_mode_destroy(dev, modeset->mode);
-			modeset->mode = NULL;
-		}
-	}
 out:
 	kfree(crtcs);
 	kfree(modes);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index def78c8..f86e7c8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -262,6 +262,26 @@ int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state,
 	return 0;
 }
 
+int exynos_atomic_check(struct drm_device *dev,
+			struct drm_atomic_state *state)
+{
+	int ret;
+
+	ret = drm_atomic_helper_check_modeset(dev, state);
+	if (ret)
+		return ret;
+
+	ret = drm_atomic_normalize_zpos(dev, state);
+	if (ret)
+		return ret;
+
+	ret = drm_atomic_helper_check_planes(dev, state);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
 static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index d215149..80c4d5b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -301,6 +301,7 @@ static inline int exynos_dpi_bind(struct drm_device *dev,
 
 int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state,
 			 bool nonblock);
+int exynos_atomic_check(struct drm_device *dev, struct drm_atomic_state *state);
 
 
 extern struct platform_driver fimd_driver;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 40ce841..23cce0a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -190,7 +190,7 @@ dma_addr_t exynos_drm_fb_dma_addr(struct drm_framebuffer *fb, int index)
 static const struct drm_mode_config_funcs exynos_drm_mode_config_funcs = {
 	.fb_create = exynos_user_fb_create,
 	.output_poll_changed = exynos_drm_output_poll_changed,
-	.atomic_check = drm_atomic_helper_check,
+	.atomic_check = exynos_atomic_check,
 	.atomic_commit = exynos_atomic_commit,
 };
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index bfb2efd..18dfdd5 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1447,8 +1447,6 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	dev_priv->suspend_count++;
 
-	intel_display_set_init_power(dev_priv, false);
-
 	intel_csr_ucode_suspend(dev_priv);
 
 out:
@@ -1466,6 +1464,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 
 	disable_rpm_wakeref_asserts(dev_priv);
 
+	intel_display_set_init_power(dev_priv, false);
+
 	fw_csr = !IS_BROXTON(dev_priv) &&
 		suspend_to_idle(dev_priv) && dev_priv->csr.dmc_payload;
 	/*
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8b9ee4e..685e9e06 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2883,6 +2883,11 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 extern long i915_compat_ioctl(struct file *filp, unsigned int cmd,
 			      unsigned long arg);
 #endif
+extern const struct dev_pm_ops i915_pm_ops;
+
+extern int i915_driver_load(struct pci_dev *pdev,
+			    const struct pci_device_id *ent);
+extern void i915_driver_unload(struct drm_device *dev);
 extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask);
 extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv);
 extern void i915_reset(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 947e82c..23960de 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3550,8 +3550,6 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 
 	vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
 
-	WARN_ON(obj->pin_display > i915_vma_pin_count(vma));
-
 	i915_gem_object_flush_cpu_write_domain(obj);
 
 	old_write_domain = obj->base.write_domain;
@@ -3588,7 +3586,6 @@ i915_gem_object_unpin_from_display_plane(struct i915_vma *vma)
 		list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
 
 	i915_vma_unpin(vma);
-	WARN_ON(vma->obj->pin_display > i915_vma_pin_count(vma));
 }
 
 /**
@@ -3745,7 +3742,12 @@ void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
 	mappable = (vma->node.start + fence_size <=
 		    dev_priv->ggtt.mappable_end);
 
-	if (mappable && fenceable)
+	/*
+	 * Explicitly disable for rotated VMA since the display does not
+	 * need the fence and the VMA is not accessible to other users.
+	 */
+	if (mappable && fenceable &&
+	    vma->ggtt_view.type != I915_GGTT_VIEW_ROTATED)
 		vma->flags |= I915_VMA_CAN_FENCE;
 	else
 		vma->flags &= ~I915_VMA_CAN_FENCE;
diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index 8df1fa7..2c7ba0e 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -290,6 +290,8 @@ i915_vma_put_fence(struct i915_vma *vma)
 {
 	struct drm_i915_fence_reg *fence = vma->fence;
 
+	assert_rpm_wakelock_held(to_i915(vma->vm->dev));
+
 	if (!fence)
 		return 0;
 
@@ -341,6 +343,8 @@ i915_vma_get_fence(struct i915_vma *vma)
 	struct drm_i915_fence_reg *fence;
 	struct i915_vma *set = i915_gem_object_is_tiled(vma->obj) ? vma : NULL;
 
+	assert_rpm_wakelock_held(to_i915(vma->vm->dev));
+
 	/* Just update our place in the LRU if our fence is getting reused. */
 	if (vma->fence) {
 		fence = vma->fence;
@@ -371,6 +375,12 @@ void i915_gem_restore_fences(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	int i;
 
+	/* Note that this may be called outside of struct_mutex, by
+	 * runtime suspend/resume. The barrier we require is enforced by
+	 * rpm itself - all access to fences/GTT are only within an rpm
+	 * wakeref, and to acquire that wakeref you must pass through here.
+	 */
+
 	for (i = 0; i < dev_priv->num_fence_regs; i++) {
 		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
 		struct i915_vma *vma = reg->vma;
@@ -379,10 +389,17 @@ void i915_gem_restore_fences(struct drm_device *dev)
 		 * Commit delayed tiling changes if we have an object still
 		 * attached to the fence, otherwise just clear the fence.
 		 */
-		if (vma && !i915_gem_object_is_tiled(vma->obj))
-			vma = NULL;
+		if (vma && !i915_gem_object_is_tiled(vma->obj)) {
+			GEM_BUG_ON(!reg->dirty);
+			GEM_BUG_ON(vma->obj->fault_mappable);
 
-		fence_update(reg, vma);
+			list_move(&reg->link, &dev_priv->mm.fence_list);
+			vma->fence = NULL;
+			vma = NULL;
+		}
+
+		fence_write(reg, vma);
+		reg->vma = vma;
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 687c768..31e6edd 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -431,9 +431,6 @@ static const struct pci_device_id pciidlist[] = {
 };
 MODULE_DEVICE_TABLE(pci, pciidlist);
 
-extern int i915_driver_load(struct pci_dev *pdev,
-			    const struct pci_device_id *ent);
-
 static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct intel_device_info *intel_info =
@@ -463,8 +460,6 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return i915_driver_load(pdev, ent);
 }
 
-extern void i915_driver_unload(struct drm_device *dev);
-
 static void i915_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
@@ -473,8 +468,6 @@ static void i915_pci_remove(struct pci_dev *pdev)
 	drm_dev_unref(dev);
 }
 
-extern const struct dev_pm_ops i915_pm_ops;
-
 static struct pci_driver i915_pci_driver = {
 	.name = DRIVER_NAME,
 	.id_table = pciidlist,
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index c6e69e4..1f8af87 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1031,6 +1031,77 @@ static u8 translate_iboost(u8 val)
 	return mapping[val];
 }
 
+static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
+			     enum port port)
+{
+	const struct ddi_vbt_port_info *info =
+		&dev_priv->vbt.ddi_port_info[port];
+	enum port p;
+
+	if (!info->alternate_ddc_pin)
+		return;
+
+	for_each_port_masked(p, (1 << port) - 1) {
+		struct ddi_vbt_port_info *i = &dev_priv->vbt.ddi_port_info[p];
+
+		if (info->alternate_ddc_pin != i->alternate_ddc_pin)
+			continue;
+
+		DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, "
+			      "disabling port %c DVI/HDMI support\n",
+			      port_name(p), i->alternate_ddc_pin,
+			      port_name(port), port_name(p));
+
+		/*
+		 * If we have multiple ports supposedly sharing the
+		 * pin, then dvi/hdmi couldn't exist on the shared
+		 * port. Otherwise they share the same ddc bin and
+		 * system couldn't communicate with them separately.
+		 *
+		 * Due to parsing the ports in alphabetical order,
+		 * a higher port will always clobber a lower one.
+		 */
+		i->supports_dvi = false;
+		i->supports_hdmi = false;
+		i->alternate_ddc_pin = 0;
+	}
+}
+
+static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
+			    enum port port)
+{
+	const struct ddi_vbt_port_info *info =
+		&dev_priv->vbt.ddi_port_info[port];
+	enum port p;
+
+	if (!info->alternate_aux_channel)
+		return;
+
+	for_each_port_masked(p, (1 << port) - 1) {
+		struct ddi_vbt_port_info *i = &dev_priv->vbt.ddi_port_info[p];
+
+		if (info->alternate_aux_channel != i->alternate_aux_channel)
+			continue;
+
+		DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, "
+			      "disabling port %c DP support\n",
+			      port_name(p), i->alternate_aux_channel,
+			      port_name(port), port_name(p));
+
+		/*
+		 * If we have multiple ports supposedlt sharing the
+		 * aux channel, then DP couldn't exist on the shared
+		 * port. Otherwise they share the same aux channel
+		 * and system couldn't communicate with them separately.
+		 *
+		 * Due to parsing the ports in alphabetical order,
+		 * a higher port will always clobber a lower one.
+		 */
+		i->supports_dp = false;
+		i->alternate_aux_channel = 0;
+	}
+}
+
 static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 			   const struct bdb_header *bdb)
 {
@@ -1105,54 +1176,15 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 		DRM_DEBUG_KMS("Port %c is internal DP\n", port_name(port));
 
 	if (is_dvi) {
-		if (port == PORT_E) {
-			info->alternate_ddc_pin = ddc_pin;
-			/* if DDIE share ddc pin with other port, then
-			 * dvi/hdmi couldn't exist on the shared port.
-			 * Otherwise they share the same ddc bin and system
-			 * couldn't communicate with them seperately. */
-			if (ddc_pin == DDC_PIN_B) {
-				dev_priv->vbt.ddi_port_info[PORT_B].supports_dvi = 0;
-				dev_priv->vbt.ddi_port_info[PORT_B].supports_hdmi = 0;
-			} else if (ddc_pin == DDC_PIN_C) {
-				dev_priv->vbt.ddi_port_info[PORT_C].supports_dvi = 0;
-				dev_priv->vbt.ddi_port_info[PORT_C].supports_hdmi = 0;
-			} else if (ddc_pin == DDC_PIN_D) {
-				dev_priv->vbt.ddi_port_info[PORT_D].supports_dvi = 0;
-				dev_priv->vbt.ddi_port_info[PORT_D].supports_hdmi = 0;
-			}
-		} else if (ddc_pin == DDC_PIN_B && port != PORT_B)
-			DRM_DEBUG_KMS("Unexpected DDC pin for port B\n");
-		else if (ddc_pin == DDC_PIN_C && port != PORT_C)
-			DRM_DEBUG_KMS("Unexpected DDC pin for port C\n");
-		else if (ddc_pin == DDC_PIN_D && port != PORT_D)
-			DRM_DEBUG_KMS("Unexpected DDC pin for port D\n");
+		info->alternate_ddc_pin = ddc_pin;
+
+		sanitize_ddc_pin(dev_priv, port);
 	}
 
 	if (is_dp) {
-		if (port == PORT_E) {
-			info->alternate_aux_channel = aux_channel;
-			/* if DDIE share aux channel with other port, then
-			 * DP couldn't exist on the shared port. Otherwise
-			 * they share the same aux channel and system
-			 * couldn't communicate with them seperately. */
-			if (aux_channel == DP_AUX_A)
-				dev_priv->vbt.ddi_port_info[PORT_A].supports_dp = 0;
-			else if (aux_channel == DP_AUX_B)
-				dev_priv->vbt.ddi_port_info[PORT_B].supports_dp = 0;
-			else if (aux_channel == DP_AUX_C)
-				dev_priv->vbt.ddi_port_info[PORT_C].supports_dp = 0;
-			else if (aux_channel == DP_AUX_D)
-				dev_priv->vbt.ddi_port_info[PORT_D].supports_dp = 0;
-		}
-		else if (aux_channel == DP_AUX_A && port != PORT_A)
-			DRM_DEBUG_KMS("Unexpected AUX channel for port A\n");
-		else if (aux_channel == DP_AUX_B && port != PORT_B)
-			DRM_DEBUG_KMS("Unexpected AUX channel for port B\n");
-		else if (aux_channel == DP_AUX_C && port != PORT_C)
-			DRM_DEBUG_KMS("Unexpected AUX channel for port C\n");
-		else if (aux_channel == DP_AUX_D && port != PORT_D)
-			DRM_DEBUG_KMS("Unexpected AUX channel for port D\n");
+		info->alternate_aux_channel = aux_channel;
+
+		sanitize_aux_ch(dev_priv, port);
 	}
 
 	if (bdb->version >= 158) {
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 73b6858..1b20e16 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -192,7 +192,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 	struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
 	const int s_max = 3, ss_max = 3, eu_max = 8;
 	int s, ss;
-	u32 fuse2, eu_disable[s_max];
+	u32 fuse2, eu_disable[3]; /* s_max */
 
 	fuse2 = I915_READ(GEN8_FUSE2);
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index fbcfed6..0ad1879 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2978,7 +2978,8 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state)
 	/* Rotate src coordinates to match rotated GTT view */
 	if (intel_rotation_90_or_270(rotation))
 		drm_rect_rotate(&plane_state->base.src,
-				fb->width, fb->height, DRM_ROTATE_270);
+				fb->width << 16, fb->height << 16,
+				DRM_ROTATE_270);
 
 	/*
 	 * Handle the AUX surface first since
@@ -14310,7 +14311,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 
 	for_each_plane_in_state(state, plane, plane_state, i) {
 		struct intel_plane_state *intel_plane_state =
-			to_intel_plane_state(plane_state);
+			to_intel_plane_state(plane->state);
 
 		if (!intel_plane_state->wait_req)
 			continue;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 14a3cf0..3581b5a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1108,6 +1108,44 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 	return ret;
 }
 
+static enum port intel_aux_port(struct drm_i915_private *dev_priv,
+				enum port port)
+{
+	const struct ddi_vbt_port_info *info =
+		&dev_priv->vbt.ddi_port_info[port];
+	enum port aux_port;
+
+	if (!info->alternate_aux_channel) {
+		DRM_DEBUG_KMS("using AUX %c for port %c (platform default)\n",
+			      port_name(port), port_name(port));
+		return port;
+	}
+
+	switch (info->alternate_aux_channel) {
+	case DP_AUX_A:
+		aux_port = PORT_A;
+		break;
+	case DP_AUX_B:
+		aux_port = PORT_B;
+		break;
+	case DP_AUX_C:
+		aux_port = PORT_C;
+		break;
+	case DP_AUX_D:
+		aux_port = PORT_D;
+		break;
+	default:
+		MISSING_CASE(info->alternate_aux_channel);
+		aux_port = PORT_A;
+		break;
+	}
+
+	DRM_DEBUG_KMS("using AUX %c for port %c (VBT)\n",
+		      port_name(aux_port), port_name(port));
+
+	return aux_port;
+}
+
 static i915_reg_t g4x_aux_ctl_reg(struct drm_i915_private *dev_priv,
 				       enum port port)
 {
@@ -1168,36 +1206,9 @@ static i915_reg_t ilk_aux_data_reg(struct drm_i915_private *dev_priv,
 	}
 }
 
-/*
- * On SKL we don't have Aux for port E so we rely
- * on VBT to set a proper alternate aux channel.
- */
-static enum port skl_porte_aux_port(struct drm_i915_private *dev_priv)
-{
-	const struct ddi_vbt_port_info *info =
-		&dev_priv->vbt.ddi_port_info[PORT_E];
-
-	switch (info->alternate_aux_channel) {
-	case DP_AUX_A:
-		return PORT_A;
-	case DP_AUX_B:
-		return PORT_B;
-	case DP_AUX_C:
-		return PORT_C;
-	case DP_AUX_D:
-		return PORT_D;
-	default:
-		MISSING_CASE(info->alternate_aux_channel);
-		return PORT_A;
-	}
-}
-
 static i915_reg_t skl_aux_ctl_reg(struct drm_i915_private *dev_priv,
 				       enum port port)
 {
-	if (port == PORT_E)
-		port = skl_porte_aux_port(dev_priv);
-
 	switch (port) {
 	case PORT_A:
 	case PORT_B:
@@ -1213,9 +1224,6 @@ static i915_reg_t skl_aux_ctl_reg(struct drm_i915_private *dev_priv,
 static i915_reg_t skl_aux_data_reg(struct drm_i915_private *dev_priv,
 					enum port port, int index)
 {
-	if (port == PORT_E)
-		port = skl_porte_aux_port(dev_priv);
-
 	switch (port) {
 	case PORT_A:
 	case PORT_B:
@@ -1253,7 +1261,8 @@ static i915_reg_t intel_aux_data_reg(struct drm_i915_private *dev_priv,
 static void intel_aux_reg_init(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
-	enum port port = dp_to_dig_port(intel_dp)->port;
+	enum port port = intel_aux_port(dev_priv,
+					dp_to_dig_port(intel_dp)->port);
 	int i;
 
 	intel_dp->aux_ch_ctl_reg = intel_aux_ctl_reg(dev_priv, port);
@@ -3551,8 +3560,8 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 	/* Read the eDP Display control capabilities registers */
 	if ((intel_dp->dpcd[DP_EDP_CONFIGURATION_CAP] & DP_DPCD_DISPLAY_CONTROL_CAPABLE) &&
 	    drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV,
-			     intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd) ==
-			     sizeof(intel_dp->edp_dpcd)))
+			     intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd)) ==
+			     sizeof(intel_dp->edp_dpcd))
 		DRM_DEBUG_KMS("EDP DPCD : %*ph\n", (int) sizeof(intel_dp->edp_dpcd),
 			      intel_dp->edp_dpcd);
 
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index faa6762..c43dd9a 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -104,8 +104,10 @@ static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
 	int lines;
 
 	intel_fbc_get_plane_source_size(cache, NULL, &lines);
-	if (INTEL_INFO(dev_priv)->gen >= 7)
+	if (INTEL_GEN(dev_priv) == 7)
 		lines = min(lines, 2048);
+	else if (INTEL_GEN(dev_priv) >= 8)
+		lines = min(lines, 2560);
 
 	/* Hardware needs the full buffer stride, not just the active area. */
 	return lines * cache->fb.stride;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index a2f751c..db24f89 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3362,13 +3362,15 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	int num_active;
 	int id, i;
 
+	/* Clear the partitioning for disabled planes. */
+	memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
+	memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe]));
+
 	if (WARN_ON(!state))
 		return 0;
 
 	if (!cstate->base.active) {
 		ddb->pipe[pipe].start = ddb->pipe[pipe].end = 0;
-		memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
-		memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe]));
 		return 0;
 	}
 
@@ -3468,12 +3470,6 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 	return 0;
 }
 
-static uint32_t skl_pipe_pixel_rate(const struct intel_crtc_state *config)
-{
-	/* TODO: Take into account the scalers once we support them */
-	return config->base.adjusted_mode.crtc_clock;
-}
-
 /*
  * The max latency should be 257 (max the punit can code is 255 and we add 2us
  * for the read latency) and cpp should always be <= 8, so that
@@ -3524,7 +3520,7 @@ static uint32_t skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cst
 	 * Adjusted plane pixel rate is just the pipe's adjusted pixel rate
 	 * with additional adjustments for plane-specific scaling.
 	 */
-	adjusted_pixel_rate = skl_pipe_pixel_rate(cstate);
+	adjusted_pixel_rate = ilk_pipe_pixel_rate(cstate);
 	downscale_amount = skl_plane_downscale_amount(pstate);
 
 	pixel_rate = adjusted_pixel_rate * downscale_amount >> 16;
@@ -3736,11 +3732,11 @@ skl_compute_linetime_wm(struct intel_crtc_state *cstate)
 	if (!cstate->base.active)
 		return 0;
 
-	if (WARN_ON(skl_pipe_pixel_rate(cstate) == 0))
+	if (WARN_ON(ilk_pipe_pixel_rate(cstate) == 0))
 		return 0;
 
 	return DIV_ROUND_UP(8 * cstate->base.adjusted_mode.crtc_htotal * 1000,
-			    skl_pipe_pixel_rate(cstate));
+			    ilk_pipe_pixel_rate(cstate));
 }
 
 static void skl_compute_transition_wm(struct intel_crtc_state *cstate,
@@ -4050,6 +4046,12 @@ skl_compute_ddb(struct drm_atomic_state *state)
 		intel_state->wm_results.dirty_pipes = ~0;
 	}
 
+	/*
+	 * We're not recomputing for the pipes not included in the commit, so
+	 * make sure we start with the current state.
+	 */
+	memcpy(ddb, &dev_priv->wm.skl_hw.ddb, sizeof(*ddb));
+
 	for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
 		struct intel_crtc_state *cstate;
 
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 98df09c..9672b57 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -357,8 +357,8 @@ static int imx_drm_bind(struct device *dev)
 	int ret;
 
 	drm = drm_dev_alloc(&imx_drm_driver, dev);
-	if (!drm)
-		return -ENOMEM;
+	if (IS_ERR(drm))
+		return PTR_ERR(drm);
 
 	imxdrm = devm_kzalloc(dev, sizeof(*imxdrm), GFP_KERNEL);
 	if (!imxdrm) {
@@ -436,9 +436,11 @@ static int imx_drm_bind(struct device *dev)
 
 err_fbhelper:
 	drm_kms_helper_poll_fini(drm);
+#if IS_ENABLED(CONFIG_DRM_FBDEV_EMULATION)
 	if (imxdrm->fbhelper)
 		drm_fbdev_cma_fini(imxdrm->fbhelper);
 err_unbind:
+#endif
 	component_unbind_all(drm->dev, drm);
 err_vblank:
 	drm_vblank_cleanup(drm);
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index ce22d0a..d5864ed 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -103,11 +103,11 @@ drm_plane_state_to_vbo(struct drm_plane_state *state)
 	       (state->src_x >> 16) / 2 - eba;
 }
 
-static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane,
-				      struct drm_plane_state *old_state)
+static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane)
 {
 	struct drm_plane *plane = &ipu_plane->base;
 	struct drm_plane_state *state = plane->state;
+	struct drm_crtc_state *crtc_state = state->crtc->state;
 	struct drm_framebuffer *fb = state->fb;
 	unsigned long eba, ubo, vbo;
 	int active;
@@ -117,7 +117,7 @@ static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane,
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_YUV420:
 	case DRM_FORMAT_YVU420:
-		if (old_state->fb)
+		if (!drm_atomic_crtc_needs_modeset(crtc_state))
 			break;
 
 		/*
@@ -149,7 +149,7 @@ static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane,
 		break;
 	}
 
-	if (old_state->fb) {
+	if (!drm_atomic_crtc_needs_modeset(crtc_state)) {
 		active = ipu_idmac_get_current_buffer(ipu_plane->ipu_ch);
 		ipu_cpmem_set_buffer(ipu_plane->ipu_ch, !active, eba);
 		ipu_idmac_select_buffer(ipu_plane->ipu_ch, !active);
@@ -259,6 +259,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
 	struct drm_framebuffer *fb = state->fb;
 	struct drm_framebuffer *old_fb = old_state->fb;
 	unsigned long eba, ubo, vbo, old_ubo, old_vbo;
+	int hsub, vsub;
 
 	/* Ok to disable */
 	if (!fb)
@@ -355,7 +356,9 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
 		if ((ubo > 0xfffff8) || (vbo > 0xfffff8))
 			return -EINVAL;
 
-		if (old_fb) {
+		if (old_fb &&
+		    (old_fb->pixel_format == DRM_FORMAT_YUV420 ||
+		     old_fb->pixel_format == DRM_FORMAT_YVU420)) {
 			old_ubo = drm_plane_state_to_ubo(old_state);
 			old_vbo = drm_plane_state_to_vbo(old_state);
 			if (ubo != old_ubo || vbo != old_vbo)
@@ -370,6 +373,16 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
 
 		if (old_fb && old_fb->pitches[1] != fb->pitches[1])
 			crtc_state->mode_changed = true;
+
+		/*
+		 * The x/y offsets must be even in case of horizontal/vertical
+		 * chroma subsampling.
+		 */
+		hsub = drm_format_horz_chroma_subsampling(fb->pixel_format);
+		vsub = drm_format_vert_chroma_subsampling(fb->pixel_format);
+		if (((state->src_x >> 16) & (hsub - 1)) ||
+		    ((state->src_y >> 16) & (vsub - 1)))
+			return -EINVAL;
 	}
 
 	return 0;
@@ -392,7 +405,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
 		struct drm_crtc_state *crtc_state = state->crtc->state;
 
 		if (!drm_atomic_crtc_needs_modeset(crtc_state)) {
-			ipu_plane_atomic_set_base(ipu_plane, old_state);
+			ipu_plane_atomic_set_base(ipu_plane);
 			return;
 		}
 	}
@@ -424,6 +437,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
 			ipu_dp_set_global_alpha(ipu_plane->dp, false, 0, false);
 			break;
 		default:
+			ipu_dp_set_global_alpha(ipu_plane->dp, true, 0, true);
 			break;
 		}
 	}
@@ -437,7 +451,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
 	ipu_cpmem_set_high_priority(ipu_plane->ipu_ch);
 	ipu_idmac_set_double_buffer(ipu_plane->ipu_ch, 1);
 	ipu_cpmem_set_stride(ipu_plane->ipu_ch, state->fb->pitches[0]);
-	ipu_plane_atomic_set_base(ipu_plane, old_state);
+	ipu_plane_atomic_set_base(ipu_plane);
 	ipu_plane_enable(ipu_plane);
 }
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 919b35f..dcf7d11 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -266,6 +266,9 @@ int mgag200_mm_init(struct mga_device *mdev)
 		return ret;
 	}
 
+	arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+				   pci_resource_len(dev->pdev, 0));
+
 	mdev->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
 					 pci_resource_len(dev->pdev, 0));
 
@@ -274,10 +277,14 @@ int mgag200_mm_init(struct mga_device *mdev)
 
 void mgag200_mm_fini(struct mga_device *mdev)
 {
+	struct drm_device *dev = mdev->dev;
+
 	ttm_bo_device_release(&mdev->ttm.bdev);
 
 	mgag200_ttm_global_release(mdev);
 
+	arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+				pci_resource_len(dev->pdev, 0));
 	arch_phys_wc_del(mdev->fb_mtrr);
 	mdev->fb_mtrr = 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index dc57b62..193573d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -240,7 +240,8 @@ static bool nouveau_pr3_present(struct pci_dev *pdev)
 	if (!parent_adev)
 		return false;
 
-	return acpi_has_method(parent_adev->handle, "_PR3");
+	return parent_adev->power.flags.power_resources &&
+		acpi_has_method(parent_adev->handle, "_PR3");
 }
 
 static void nouveau_dsm_pci_probe(struct pci_dev *pdev, acpi_handle *dhandle_out,
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 1825dbc..a6dbe82 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -398,6 +398,9 @@ nouveau_ttm_init(struct nouveau_drm *drm)
 	/* VRAM init */
 	drm->gem.vram_available = drm->device.info.ram_user;
 
+	arch_io_reserve_memtype_wc(device->func->resource_addr(device, 1),
+				   device->func->resource_size(device, 1));
+
 	ret = ttm_bo_init_mm(&drm->ttm.bdev, TTM_PL_VRAM,
 			      drm->gem.vram_available >> PAGE_SHIFT);
 	if (ret) {
@@ -430,6 +433,8 @@ nouveau_ttm_init(struct nouveau_drm *drm)
 void
 nouveau_ttm_fini(struct nouveau_drm *drm)
 {
+	struct nvkm_device *device = nvxx_device(&drm->device);
+
 	ttm_bo_clean_mm(&drm->ttm.bdev, TTM_PL_VRAM);
 	ttm_bo_clean_mm(&drm->ttm.bdev, TTM_PL_TT);
 
@@ -439,4 +444,7 @@ nouveau_ttm_fini(struct nouveau_drm *drm)
 
 	arch_phys_wc_del(drm->ttm.mtrr);
 	drm->ttm.mtrr = 0;
+	arch_io_free_memtype_wc(device->func->resource_addr(device, 1),
+				device->func->resource_size(device, 1));
+
 }
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 103fc86..a0d4a05 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1396,9 +1396,7 @@ static void cayman_pcie_gart_fini(struct radeon_device *rdev)
 void cayman_cp_int_cntl_setup(struct radeon_device *rdev,
 			      int ring, u32 cp_int_cntl)
 {
-	u32 srbm_gfx_cntl = RREG32(SRBM_GFX_CNTL) & ~3;
-
-	WREG32(SRBM_GFX_CNTL, srbm_gfx_cntl | (ring & 3));
+	WREG32(SRBM_GFX_CNTL, RINGID(ring));
 	WREG32(CP_INT_CNTL, cp_int_cntl);
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_dp_auxch.c b/drivers/gpu/drm/radeon/radeon_dp_auxch.c
index 2d46564..474a8a18 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_auxch.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_auxch.c
@@ -105,7 +105,7 @@ radeon_dp_aux_transfer_native(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg
 
 	tmp &= AUX_HPD_SEL(0x7);
 	tmp |= AUX_HPD_SEL(chan->rec.hpd);
-	tmp |= AUX_EN | AUX_LS_READ_EN | AUX_HPD_DISCON(0x1);
+	tmp |= AUX_EN | AUX_LS_READ_EN;
 
 	WREG32(AUX_CONTROL + aux_offset[instance], tmp);
 
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index be30861..41b72ce 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -446,6 +446,10 @@ void radeon_bo_force_delete(struct radeon_device *rdev)
 
 int radeon_bo_init(struct radeon_device *rdev)
 {
+	/* reserve PAT memory space to WC for VRAM */
+	arch_io_reserve_memtype_wc(rdev->mc.aper_base,
+				   rdev->mc.aper_size);
+
 	/* Add an MTRR for the VRAM */
 	if (!rdev->fastfb_working) {
 		rdev->mc.vram_mtrr = arch_phys_wc_add(rdev->mc.aper_base,
@@ -463,6 +467,7 @@ void radeon_bo_fini(struct radeon_device *rdev)
 {
 	radeon_ttm_fini(rdev);
 	arch_phys_wc_del(rdev->mc.vram_mtrr);
+	arch_io_free_memtype_wc(rdev->mc.aper_base, rdev->mc.aper_size);
 }
 
 /* Returns how many bytes TTM can move per IB.
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 89bdf20..c4993452 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2999,6 +2999,49 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	int i;
 	struct si_dpm_quirk *p = si_dpm_quirk_list;
 
+	/* limit all SI kickers */
+	if (rdev->family == CHIP_PITCAIRN) {
+		if ((rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->device == 0x6810) ||
+		    (rdev->pdev->device == 0x6811) ||
+		    (rdev->pdev->device == 0x6816) ||
+		    (rdev->pdev->device == 0x6817) ||
+		    (rdev->pdev->device == 0x6806))
+			max_mclk = 120000;
+	} else if (rdev->family == CHIP_VERDE) {
+		if ((rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->revision == 0x87) ||
+		    (rdev->pdev->device == 0x6820) ||
+		    (rdev->pdev->device == 0x6821) ||
+		    (rdev->pdev->device == 0x6822) ||
+		    (rdev->pdev->device == 0x6823) ||
+		    (rdev->pdev->device == 0x682A) ||
+		    (rdev->pdev->device == 0x682B)) {
+			max_sclk = 75000;
+			max_mclk = 80000;
+		}
+	} else if (rdev->family == CHIP_OLAND) {
+		if ((rdev->pdev->revision == 0xC7) ||
+		    (rdev->pdev->revision == 0x80) ||
+		    (rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->device == 0x6604) ||
+		    (rdev->pdev->device == 0x6605)) {
+			max_sclk = 75000;
+			max_mclk = 80000;
+		}
+	} else if (rdev->family == CHIP_HAINAN) {
+		if ((rdev->pdev->revision == 0x81) ||
+		    (rdev->pdev->revision == 0x83) ||
+		    (rdev->pdev->revision == 0xC3) ||
+		    (rdev->pdev->device == 0x6664) ||
+		    (rdev->pdev->device == 0x6665) ||
+		    (rdev->pdev->device == 0x6667)) {
+			max_sclk = 75000;
+			max_mclk = 80000;
+		}
+	}
 	/* Apply dpm quirks */
 	while (p && p->chip_device != 0) {
 		if (rdev->pdev->vendor == p->chip_vendor &&
@@ -3011,16 +3054,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 		++p;
 	}
-	/* limit mclk on all R7 370 parts for stability */
-	if (rdev->pdev->device == 0x6811 &&
-	    rdev->pdev->revision == 0x81)
-		max_mclk = 120000;
-	/* limit sclk/mclk on Jet parts for stability */
-	if (rdev->pdev->device == 0x6665 &&
-	    rdev->pdev->revision == 0xc3) {
-		max_sclk = 75000;
-		max_mclk = 80000;
-	}
 
 	if (rps->vce_active) {
 		rps->evclk = rdev->pm.dpm.vce_states[rdev->pm.dpm.vce_level].evclk;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index bd9c3bb..392c7e6 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -231,8 +231,16 @@ static int rcar_du_atomic_check(struct drm_device *dev,
 	struct rcar_du_device *rcdu = dev->dev_private;
 	int ret;
 
-	ret = drm_atomic_helper_check(dev, state);
-	if (ret < 0)
+	ret = drm_atomic_helper_check_modeset(dev, state);
+	if (ret)
+		return ret;
+
+	ret = drm_atomic_normalize_zpos(dev, state);
+	if (ret)
+		return ret;
+
+	ret = drm_atomic_helper_check_planes(dev, state);
+	if (ret)
 		return ret;
 
 	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_VSP1_SOURCE))
diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c
index 2784919..9df3085 100644
--- a/drivers/gpu/drm/sti/sti_drv.c
+++ b/drivers/gpu/drm/sti/sti_drv.c
@@ -195,6 +195,26 @@ static void sti_atomic_work(struct work_struct *work)
 	sti_atomic_complete(private, private->commit.state);
 }
 
+static int sti_atomic_check(struct drm_device *dev,
+			    struct drm_atomic_state *state)
+{
+	int ret;
+
+	ret = drm_atomic_helper_check_modeset(dev, state);
+	if (ret)
+		return ret;
+
+	ret = drm_atomic_normalize_zpos(dev, state);
+	if (ret)
+		return ret;
+
+	ret = drm_atomic_helper_check_planes(dev, state);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
 static int sti_atomic_commit(struct drm_device *drm,
 			     struct drm_atomic_state *state, bool nonblock)
 {
@@ -248,7 +268,7 @@ static void sti_output_poll_changed(struct drm_device *ddev)
 static const struct drm_mode_config_funcs sti_mode_config_funcs = {
 	.fb_create = drm_fb_cma_create,
 	.output_poll_changed = sti_output_poll_changed,
-	.atomic_check = drm_atomic_helper_check,
+	.atomic_check = sti_atomic_check,
 	.atomic_commit = sti_atomic_commit,
 };
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index 7cf3678..5804870 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -338,8 +338,7 @@ static void vgdev_atomic_commit_tail(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_disables(dev, state);
 	drm_atomic_helper_commit_modeset_enables(dev, state);
-	drm_atomic_helper_commit_planes(dev, state,
-					DRM_PLANE_COMMIT_ACTIVE_ONLY);
+	drm_atomic_helper_commit_planes(dev, state, 0);
 
 	drm_atomic_helper_commit_hw_done(state);
 
diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c
index 2ba7d43..805b6fa 100644
--- a/drivers/gpu/ipu-v3/ipu-image-convert.c
+++ b/drivers/gpu/ipu-v3/ipu-image-convert.c
@@ -1617,7 +1617,7 @@ ipu_image_convert(struct ipu_soc *ipu, enum ipu_ic_task ic_task,
 	ctx = ipu_image_convert_prepare(ipu, ic_task, in, out, rot_mode,
 					complete, complete_context);
 	if (IS_ERR(ctx))
-		return ERR_PTR(PTR_ERR(ctx));
+		return ERR_CAST(ctx);
 
 	run = kzalloc(sizeof(*run), GFP_KERNEL);
 	if (!run) {
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 6cfb5ca..575aa65 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -179,6 +179,7 @@
 #define USB_DEVICE_ID_ATEN_4PORTKVM	0x2205
 #define USB_DEVICE_ID_ATEN_4PORTKVMC	0x2208
 #define USB_DEVICE_ID_ATEN_CS682	0x2213
+#define USB_DEVICE_ID_ATEN_CS692	0x8021
 
 #define USB_VENDOR_ID_ATMEL		0x03eb
 #define USB_DEVICE_ID_ATMEL_MULTITOUCH	0x211c
diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c
index 5614fee..3a84aaf 100644
--- a/drivers/hid/hid-sensor-custom.c
+++ b/drivers/hid/hid-sensor-custom.c
@@ -292,11 +292,11 @@ static ssize_t show_value(struct device *dev, struct device_attribute *attr,
 	bool input = false;
 	int value = 0;
 
-	if (sscanf(attr->attr.name, "feature-%d-%x-%s", &index, &usage,
+	if (sscanf(attr->attr.name, "feature-%x-%x-%s", &index, &usage,
 		   name) == 3) {
 		feature = true;
 		field_index = index + sensor_inst->input_field_count;
-	} else if (sscanf(attr->attr.name, "input-%d-%x-%s", &index, &usage,
+	} else if (sscanf(attr->attr.name, "input-%x-%x-%s", &index, &usage,
 		   name) == 3) {
 		input = true;
 		field_index = index;
@@ -398,7 +398,7 @@ static ssize_t store_value(struct device *dev, struct device_attribute *attr,
 	char name[HID_CUSTOM_NAME_LENGTH];
 	int value;
 
-	if (sscanf(attr->attr.name, "feature-%d-%x-%s", &index, &usage,
+	if (sscanf(attr->attr.name, "feature-%x-%x-%s", &index, &usage,
 		   name) == 3) {
 		field_index = index + sensor_inst->input_field_count;
 	} else
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index 658a607..c5c3d61 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -251,6 +251,9 @@ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id,
 	struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev);
 	int report_size;
 	int ret = 0;
+	u8 *val_ptr;
+	int buffer_index = 0;
+	int i;
 
 	mutex_lock(&data->mutex);
 	report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT);
@@ -271,7 +274,17 @@ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id,
 		goto done_proc;
 	}
 	ret = min(report_size, buffer_size);
-	memcpy(buffer, report->field[field_index]->value, ret);
+
+	val_ptr = (u8 *)report->field[field_index]->value;
+	for (i = 0; i < report->field[field_index]->report_count; ++i) {
+		if (buffer_index >= ret)
+			break;
+
+		memcpy(&((u8 *)buffer)[buffer_index], val_ptr,
+		       report->field[field_index]->report_size / 8);
+		val_ptr += sizeof(__s32);
+		buffer_index += (report->field[field_index]->report_size / 8);
+	}
 
 done_proc:
 	mutex_unlock(&data->mutex);
diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c
index e2517c1..0c9ac4d 100644
--- a/drivers/hid/intel-ish-hid/ipc/ipc.c
+++ b/drivers/hid/intel-ish-hid/ipc/ipc.c
@@ -638,6 +638,58 @@ irqreturn_t ish_irq_handler(int irq, void *dev_id)
 }
 
 /**
+ * ish_disable_dma() - disable dma communication between host and ISHFW
+ * @dev: ishtp device pointer
+ *
+ * Clear the dma enable bit and wait for dma inactive.
+ *
+ * Return: 0 for success else error code.
+ */
+static int ish_disable_dma(struct ishtp_device *dev)
+{
+	unsigned int	dma_delay;
+
+	/* Clear the dma enable bit */
+	ish_reg_write(dev, IPC_REG_ISH_RMP2, 0);
+
+	/* wait for dma inactive */
+	for (dma_delay = 0; dma_delay < MAX_DMA_DELAY &&
+		_ish_read_fw_sts_reg(dev) & (IPC_ISH_IN_DMA);
+		dma_delay += 5)
+		mdelay(5);
+
+	if (dma_delay >= MAX_DMA_DELAY) {
+		dev_err(dev->devc,
+			"Wait for DMA inactive timeout\n");
+		return	-EBUSY;
+	}
+
+	return 0;
+}
+
+/**
+ * ish_wakeup() - wakeup ishfw from waiting-for-host state
+ * @dev: ishtp device pointer
+ *
+ * Set the dma enable bit and send a void message to FW,
+ * it wil wakeup FW from waiting-for-host state.
+ */
+static void ish_wakeup(struct ishtp_device *dev)
+{
+	/* Set dma enable bit */
+	ish_reg_write(dev, IPC_REG_ISH_RMP2, IPC_RMP2_DMA_ENABLED);
+
+	/*
+	 * Send 0 IPC message so that ISH FW wakes up if it was already
+	 * asleep.
+	 */
+	ish_reg_write(dev, IPC_REG_HOST2ISH_DRBL, IPC_DRBL_BUSY_BIT);
+
+	/* Flush writes to doorbell and REMAP2 */
+	ish_reg_read(dev, IPC_REG_ISH_HOST_FWSTS);
+}
+
+/**
  * _ish_hw_reset() - HW reset
  * @dev: ishtp device pointer
  *
@@ -649,7 +701,6 @@ static int _ish_hw_reset(struct ishtp_device *dev)
 {
 	struct pci_dev *pdev = dev->pdev;
 	int	rv;
-	unsigned int	dma_delay;
 	uint16_t csr;
 
 	if (!pdev)
@@ -664,15 +715,8 @@ static int _ish_hw_reset(struct ishtp_device *dev)
 		return	-EINVAL;
 	}
 
-	/* Now trigger reset to FW */
-	ish_reg_write(dev, IPC_REG_ISH_RMP2, 0);
-
-	for (dma_delay = 0; dma_delay < MAX_DMA_DELAY &&
-		_ish_read_fw_sts_reg(dev) & (IPC_ISH_IN_DMA);
-		dma_delay += 5)
-		mdelay(5);
-
-	if (dma_delay >= MAX_DMA_DELAY) {
+	/* Disable dma communication between FW and host */
+	if (ish_disable_dma(dev)) {
 		dev_err(&pdev->dev,
 			"Can't reset - stuck with DMA in-progress\n");
 		return	-EBUSY;
@@ -690,16 +734,8 @@ static int _ish_hw_reset(struct ishtp_device *dev)
 	csr |= PCI_D0;
 	pci_write_config_word(pdev, pdev->pm_cap + PCI_PM_CTRL, csr);
 
-	ish_reg_write(dev, IPC_REG_ISH_RMP2, IPC_RMP2_DMA_ENABLED);
-
-	/*
-	 * Send 0 IPC message so that ISH FW wakes up if it was already
-	 * asleep
-	 */
-	ish_reg_write(dev, IPC_REG_HOST2ISH_DRBL, IPC_DRBL_BUSY_BIT);
-
-	/* Flush writes to doorbell and REMAP2 */
-	ish_reg_read(dev, IPC_REG_ISH_HOST_FWSTS);
+	/* Now we can enable ISH DMA operation and wakeup ISHFW */
+	ish_wakeup(dev);
 
 	return	0;
 }
@@ -758,16 +794,9 @@ static int _ish_ipc_reset(struct ishtp_device *dev)
 int ish_hw_start(struct ishtp_device *dev)
 {
 	ish_set_host_rdy(dev);
-	/* After that we can enable ISH DMA operation */
-	ish_reg_write(dev, IPC_REG_ISH_RMP2, IPC_RMP2_DMA_ENABLED);
 
-	/*
-	 * Send 0 IPC message so that ISH FW wakes up if it was already
-	 * asleep
-	 */
-	ish_reg_write(dev, IPC_REG_HOST2ISH_DRBL, IPC_DRBL_BUSY_BIT);
-	/* Flush write to doorbell */
-	ish_reg_read(dev, IPC_REG_ISH_HOST_FWSTS);
+	/* After that we can enable ISH DMA operation and wakeup ISHFW */
+	ish_wakeup(dev);
 
 	set_host_ready(dev);
 
@@ -876,6 +905,21 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev)
  */
 void	ish_device_disable(struct ishtp_device *dev)
 {
+	struct pci_dev *pdev = dev->pdev;
+
+	if (!pdev)
+		return;
+
+	/* Disable dma communication between FW and host */
+	if (ish_disable_dma(dev)) {
+		dev_err(&pdev->dev,
+			"Can't reset - stuck with DMA in-progress\n");
+		return;
+	}
+
+	/* Put ISH to D3hot state for power saving */
+	pci_set_power_state(pdev, PCI_D3hot);
+
 	dev->dev_state = ISHTP_DEV_DISABLED;
 	ish_clr_host_rdy(dev);
 }
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 42f0bee..20d647d 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -146,7 +146,7 @@ static int ish_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3;
 
 	/* request and enable interrupt */
-	ret = request_irq(pdev->irq, ish_irq_handler, IRQF_NO_SUSPEND,
+	ret = request_irq(pdev->irq, ish_irq_handler, IRQF_SHARED,
 			  KBUILD_MODNAME, dev);
 	if (ret) {
 		dev_err(&pdev->dev, "ISH: request IRQ failure (%d)\n",
@@ -202,6 +202,7 @@ static void ish_remove(struct pci_dev *pdev)
 	kfree(ishtp_dev);
 }
 
+#ifdef CONFIG_PM
 static struct device *ish_resume_device;
 
 /**
@@ -293,7 +294,6 @@ static int ish_resume(struct device *device)
 	return 0;
 }
 
-#ifdef CONFIG_PM
 static const struct dev_pm_ops ish_pm_ops = {
 	.suspend = ish_suspend,
 	.resume = ish_resume,
@@ -301,7 +301,7 @@ static const struct dev_pm_ops ish_pm_ops = {
 #define ISHTP_ISH_PM_OPS	(&ish_pm_ops)
 #else
 #define ISHTP_ISH_PM_OPS	NULL
-#endif
+#endif /* CONFIG_PM */
 
 static struct pci_driver ish_driver = {
 	.name = KBUILD_MODNAME,
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 354d49e..e6cfd32 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -63,6 +63,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS682, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS692, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FIGHTERSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_COMBATSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_ECLIPSE_YOKE, HID_QUIRK_NOGET },
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 4aa3cb6..bcd0630 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -314,10 +314,14 @@ static void heartbeat_onchannelcallback(void *context)
 	u8 *hbeat_txf_buf = util_heartbeat.recv_buffer;
 	struct icmsg_negotiate *negop = NULL;
 
-	vmbus_recvpacket(channel, hbeat_txf_buf,
-			 PAGE_SIZE, &recvlen, &requestid);
+	while (1) {
 
-	if (recvlen > 0) {
+		vmbus_recvpacket(channel, hbeat_txf_buf,
+				 PAGE_SIZE, &recvlen, &requestid);
+
+		if (!recvlen)
+			break;
+
 		icmsghdrp = (struct icmsg_hdr *)&hbeat_txf_buf[
 				sizeof(struct vmbuspipe_hdr)];
 
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index adae684..a74c075 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -536,8 +536,10 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 
 		hwdev->groups = devm_kcalloc(dev, ngroups, sizeof(*groups),
 					     GFP_KERNEL);
-		if (!hwdev->groups)
-			return ERR_PTR(-ENOMEM);
+		if (!hwdev->groups) {
+			err = -ENOMEM;
+			goto free_hwmon;
+		}
 
 		attrs = __hwmon_create_attrs(dev, drvdata, chip);
 		if (IS_ERR(attrs)) {
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 6d94e2e..d252276 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -79,12 +79,12 @@
 
 config I2C_HIX5HD2
 	tristate "Hix5hd2 high-speed I2C driver"
-	depends on ARCH_HIX5HD2 || COMPILE_TEST
+	depends on ARCH_HISI || ARCH_HIX5HD2 || COMPILE_TEST
 	help
-	  Say Y here to include support for high-speed I2C controller in the
-	  Hisilicon based hix5hd2 SoCs.
+	  Say Y here to include support for the high-speed I2C controller
+	  used in HiSilicon hix5hd2 SoCs.
 
-	  This driver can also be built as a module.  If so, the module
+	  This driver can also be built as a module. If so, the module
 	  will be called i2c-hix5hd2.
 
 config I2C_I801
@@ -589,10 +589,10 @@
 
 config I2C_IMX
 	tristate "IMX I2C interface"
-	depends on ARCH_MXC || ARCH_LAYERSCAPE
+	depends on ARCH_MXC || ARCH_LAYERSCAPE || COLDFIRE
 	help
 	  Say Y here if you want to use the IIC bus controller on
-	  the Freescale i.MX/MXC or Layerscape processors.
+	  the Freescale i.MX/MXC, Layerscape or ColdFire processors.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-imx.
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index 1fe93c4..11e866d 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -95,6 +95,9 @@
 #define DW_IC_STATUS_TFE		BIT(2)
 #define DW_IC_STATUS_MST_ACTIVITY	BIT(5)
 
+#define DW_IC_SDA_HOLD_RX_SHIFT		16
+#define DW_IC_SDA_HOLD_RX_MASK		GENMASK(23, DW_IC_SDA_HOLD_RX_SHIFT)
+
 #define DW_IC_ERR_TX_ABRT	0x1
 
 #define DW_IC_TAR_10BITADDR_MASTER BIT(12)
@@ -420,12 +423,20 @@ int i2c_dw_init(struct dw_i2c_dev *dev)
 	/* Configure SDA Hold Time if required */
 	reg = dw_readl(dev, DW_IC_COMP_VERSION);
 	if (reg >= DW_IC_SDA_HOLD_MIN_VERS) {
-		if (dev->sda_hold_time) {
-			dw_writel(dev, dev->sda_hold_time, DW_IC_SDA_HOLD);
-		} else {
+		if (!dev->sda_hold_time) {
 			/* Keep previous hold time setting if no one set it */
 			dev->sda_hold_time = dw_readl(dev, DW_IC_SDA_HOLD);
 		}
+		/*
+		 * Workaround for avoiding TX arbitration lost in case I2C
+		 * slave pulls SDA down "too quickly" after falling egde of
+		 * SCL by enabling non-zero SDA RX hold. Specification says it
+		 * extends incoming SDA low to high transition while SCL is
+		 * high but it apprears to help also above issue.
+		 */
+		if (!(dev->sda_hold_time & DW_IC_SDA_HOLD_RX_MASK))
+			dev->sda_hold_time |= 1 << DW_IC_SDA_HOLD_RX_SHIFT;
+		dw_writel(dev, dev->sda_hold_time, DW_IC_SDA_HOLD);
 	} else {
 		dev_warn(dev->dev,
 			"Hardware too old to adjust SDA hold time.\n");
diff --git a/drivers/i2c/busses/i2c-digicolor.c b/drivers/i2c/busses/i2c-digicolor.c
index 9604024..49f2084 100644
--- a/drivers/i2c/busses/i2c-digicolor.c
+++ b/drivers/i2c/busses/i2c-digicolor.c
@@ -368,6 +368,7 @@ static const struct of_device_id dc_i2c_match[] = {
 	{ .compatible = "cnxt,cx92755-i2c" },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, dc_i2c_match);
 
 static struct platform_driver dc_i2c_driver = {
 	.probe   = dc_i2c_probe,
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 08847e8..eb3627f 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -146,6 +146,7 @@
 #define SMBHSTCFG_HST_EN	1
 #define SMBHSTCFG_SMB_SMI_EN	2
 #define SMBHSTCFG_I2C_EN	4
+#define SMBHSTCFG_SPD_WD	0x10
 
 /* TCO configuration bits for TCOCTL */
 #define TCOCTL_EN		0x0100
@@ -865,9 +866,16 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 		block = 1;
 		break;
 	case I2C_SMBUS_I2C_BLOCK_DATA:
-		/* NB: page 240 of ICH5 datasheet shows that the R/#W
-		 * bit should be cleared here, even when reading */
-		outb_p((addr & 0x7f) << 1, SMBHSTADD(priv));
+		/*
+		 * NB: page 240 of ICH5 datasheet shows that the R/#W
+		 * bit should be cleared here, even when reading.
+		 * However if SPD Write Disable is set (Lynx Point and later),
+		 * the read will fail if we don't set the R/#W bit.
+		 */
+		outb_p(((addr & 0x7f) << 1) |
+		       ((priv->original_hstcfg & SMBHSTCFG_SPD_WD) ?
+			(read_write & 0x01) : 0),
+		       SMBHSTADD(priv));
 		if (read_write == I2C_SMBUS_READ) {
 			/* NB: page 240 of ICH5 datasheet also shows
 			 * that DATA1 is the cmd field when reading */
@@ -1573,6 +1581,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		/* Disable SMBus interrupt feature if SMBus using SMI# */
 		priv->features &= ~FEATURE_IRQ;
 	}
+	if (temp & SMBHSTCFG_SPD_WD)
+		dev_info(&dev->dev, "SPD Write Disable is set\n");
 
 	/* Clear special mode bits */
 	if (priv->features & (FEATURE_SMBUS_PEC | FEATURE_BLOCK_BUFFER))
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 592a8f2..47fc1f1 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1009,10 +1009,13 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx,
 	rinfo->sda_gpio = of_get_named_gpio(pdev->dev.of_node, "sda-gpios", 0);
 	rinfo->scl_gpio = of_get_named_gpio(pdev->dev.of_node, "scl-gpios", 0);
 
-	if (!gpio_is_valid(rinfo->sda_gpio) ||
-	    !gpio_is_valid(rinfo->scl_gpio) ||
-	    IS_ERR(i2c_imx->pinctrl_pins_default) ||
-	    IS_ERR(i2c_imx->pinctrl_pins_gpio)) {
+	if (rinfo->sda_gpio == -EPROBE_DEFER ||
+	    rinfo->scl_gpio == -EPROBE_DEFER) {
+		return -EPROBE_DEFER;
+	} else if (!gpio_is_valid(rinfo->sda_gpio) ||
+		   !gpio_is_valid(rinfo->scl_gpio) ||
+		   IS_ERR(i2c_imx->pinctrl_pins_default) ||
+		   IS_ERR(i2c_imx->pinctrl_pins_gpio)) {
 		dev_dbg(&pdev->dev, "recovery information incomplete\n");
 		return 0;
 	}
diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c
index b8ea621..30132c3 100644
--- a/drivers/i2c/busses/i2c-jz4780.c
+++ b/drivers/i2c/busses/i2c-jz4780.c
@@ -729,6 +729,7 @@ static const struct of_device_id jz4780_i2c_of_matches[] = {
 	{ .compatible = "ingenic,jz4780-i2c", },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, jz4780_i2c_of_matches);
 
 static int jz4780_i2c_probe(struct platform_device *pdev)
 {
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index 50702c7..df22066 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -694,6 +694,8 @@ static int rk3x_i2c_v0_calc_timings(unsigned long clk_rate,
 	t_calc->div_low--;
 	t_calc->div_high--;
 
+	/* Give the tuning value 0, that would not update con register */
+	t_calc->tuning = 0;
 	/* Maximum divider supported by hw is 0xffff */
 	if (t_calc->div_low > 0xffff) {
 		t_calc->div_low = 0xffff;
diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c
index 263685c..05cf192 100644
--- a/drivers/i2c/busses/i2c-xgene-slimpro.c
+++ b/drivers/i2c/busses/i2c-xgene-slimpro.c
@@ -105,7 +105,7 @@ struct slimpro_i2c_dev {
 	struct mbox_chan *mbox_chan;
 	struct mbox_client mbox_client;
 	struct completion rd_complete;
-	u8 dma_buffer[I2C_SMBUS_BLOCK_MAX];
+	u8 dma_buffer[I2C_SMBUS_BLOCK_MAX + 1]; /* dma_buffer[0] is used for length */
 	u32 *resp_msg;
 };
 
diff --git a/drivers/i2c/busses/i2c-xlp9xx.c b/drivers/i2c/busses/i2c-xlp9xx.c
index 2a972ed7..e29ff37 100644
--- a/drivers/i2c/busses/i2c-xlp9xx.c
+++ b/drivers/i2c/busses/i2c-xlp9xx.c
@@ -426,6 +426,7 @@ static const struct of_device_id xlp9xx_i2c_of_match[] = {
 	{ .compatible = "netlogic,xlp980-i2c", },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, xlp9xx_i2c_of_match);
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id xlp9xx_i2c_acpi_ids[] = {
diff --git a/drivers/i2c/busses/i2c-xlr.c b/drivers/i2c/busses/i2c-xlr.c
index 0968f59..ad17d88 100644
--- a/drivers/i2c/busses/i2c-xlr.c
+++ b/drivers/i2c/busses/i2c-xlr.c
@@ -358,6 +358,7 @@ static const struct of_device_id xlr_i2c_dt_ids[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(of, xlr_i2c_dt_ids);
 
 static int xlr_i2c_probe(struct platform_device *pdev)
 {
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 5ab6721..b432b64 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -1681,6 +1681,7 @@ static struct i2c_client *of_i2c_register_device(struct i2c_adapter *adap,
 static void of_i2c_register_devices(struct i2c_adapter *adap)
 {
 	struct device_node *bus, *node;
+	struct i2c_client *client;
 
 	/* Only register child devices if the adapter has a node pointer set */
 	if (!adap->dev.of_node)
@@ -1695,7 +1696,14 @@ static void of_i2c_register_devices(struct i2c_adapter *adap)
 	for_each_available_child_of_node(bus, node) {
 		if (of_node_test_and_set_flag(node, OF_POPULATED))
 			continue;
-		of_i2c_register_device(adap, node);
+
+		client = of_i2c_register_device(adap, node);
+		if (IS_ERR(client)) {
+			dev_warn(&adap->dev,
+				 "Failed to create I2C device for %s\n",
+				 node->full_name);
+			of_node_clear_flag(node, OF_POPULATED);
+		}
 	}
 
 	of_node_put(bus);
@@ -2171,6 +2179,7 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
 	/* add the driver to the list of i2c drivers in the driver core */
 	driver->driver.owner = owner;
 	driver->driver.bus = &i2c_bus_type;
+	INIT_LIST_HEAD(&driver->clients);
 
 	/* When registration returns, the driver core
 	 * will have called probe() for all matching-but-unbound devices.
@@ -2181,7 +2190,6 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
 
 	pr_debug("driver [%s] registered\n", driver->driver.name);
 
-	INIT_LIST_HEAD(&driver->clients);
 	/* Walk the adapters that are already present */
 	i2c_for_each_dev(driver, __process_new_driver);
 
@@ -2299,6 +2307,7 @@ static int of_i2c_notify(struct notifier_block *nb, unsigned long action,
 		if (IS_ERR(client)) {
 			dev_err(&adap->dev, "failed to create client for '%s'\n",
 				 rd->dn->full_name);
+			of_node_clear_flag(rd->dn, OF_POPULATED);
 			return notifier_from_errno(PTR_ERR(client));
 		}
 		break;
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 7edcf32..99c0514 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -437,6 +437,8 @@
 config TI_ADC081C
 	tristate "Texas Instruments ADC081C/ADC101C/ADC121C family"
 	depends on I2C
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
 	help
 	  If you say yes here you get support for Texas Instruments ADC081C,
 	  ADC101C and ADC121C ADC chips.
diff --git a/drivers/iio/chemical/atlas-ph-sensor.c b/drivers/iio/chemical/atlas-ph-sensor.c
index bd321b3..ef761a5 100644
--- a/drivers/iio/chemical/atlas-ph-sensor.c
+++ b/drivers/iio/chemical/atlas-ph-sensor.c
@@ -213,13 +213,14 @@ static int atlas_check_ec_calibration(struct atlas_data *data)
 	struct device *dev = &data->client->dev;
 	int ret;
 	unsigned int val;
+	__be16	rval;
 
-	ret = regmap_bulk_read(data->regmap, ATLAS_REG_EC_PROBE, &val, 2);
+	ret = regmap_bulk_read(data->regmap, ATLAS_REG_EC_PROBE, &rval, 2);
 	if (ret)
 		return ret;
 
-	dev_info(dev, "probe set to K = %d.%.2d", be16_to_cpu(val) / 100,
-						 be16_to_cpu(val) % 100);
+	val = be16_to_cpu(rval);
+	dev_info(dev, "probe set to K = %d.%.2d", val / 100, val % 100);
 
 	ret = regmap_read(data->regmap, ATLAS_REG_EC_CALIB_STATUS, &val);
 	if (ret)
diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c
index 39dd202..066161a 100644
--- a/drivers/iio/temperature/maxim_thermocouple.c
+++ b/drivers/iio/temperature/maxim_thermocouple.c
@@ -123,22 +123,24 @@ static int maxim_thermocouple_read(struct maxim_thermocouple_data *data,
 {
 	unsigned int storage_bytes = data->chip->read_size;
 	unsigned int shift = chan->scan_type.shift + (chan->address * 8);
-	unsigned int buf;
+	__be16 buf16;
+	__be32 buf32;
 	int ret;
 
-	ret = spi_read(data->spi, (void *) &buf, storage_bytes);
-	if (ret)
-		return ret;
-
 	switch (storage_bytes) {
 	case 2:
-		*val = be16_to_cpu(buf);
+		ret = spi_read(data->spi, (void *)&buf16, storage_bytes);
+		*val = be16_to_cpu(buf16);
 		break;
 	case 4:
-		*val = be32_to_cpu(buf);
+		ret = spi_read(data->spi, (void *)&buf32, storage_bytes);
+		*val = be32_to_cpu(buf32);
 		break;
 	}
 
+	if (ret)
+		return ret;
+
 	/* check to be sure this is a valid reading */
 	if (*val & data->chip->status_bit)
 		return -EINVAL;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2217477..63036c7 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1019,7 +1019,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
 	if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
 		resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
-	resp.cache_line_size = L1_CACHE_BYTES;
+	resp.cache_line_size = cache_line_size();
 	resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq);
 	resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq);
 	resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 41f4c2a..7ce97da 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -52,7 +52,6 @@ enum {
 
 enum {
 	MLX5_IB_SQ_STRIDE	= 6,
-	MLX5_IB_CACHE_LINE_SIZE	= 64,
 };
 
 static const u32 mlx5_ib_opcode[] = {
diff --git a/drivers/infiniband/hw/qedr/Kconfig b/drivers/infiniband/hw/qedr/Kconfig
index 7c06d85..6c9f392 100644
--- a/drivers/infiniband/hw/qedr/Kconfig
+++ b/drivers/infiniband/hw/qedr/Kconfig
@@ -2,6 +2,7 @@
 	tristate "QLogic RoCE driver"
 	depends on 64BIT && QEDE
 	select QED_LL2
+	select QED_RDMA
 	---help---
 	  This driver provides low-level InfiniBand over Ethernet
 	  support for QLogic QED host channel adapters (HCAs).
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 7b8d2d9..da12717 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -63,6 +63,8 @@ enum ipoib_flush_level {
 
 enum {
 	IPOIB_ENCAP_LEN		  = 4,
+	IPOIB_PSEUDO_LEN	  = 20,
+	IPOIB_HARD_LEN		  = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN,
 
 	IPOIB_UD_HEAD_SIZE	  = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
 	IPOIB_UD_RX_SG		  = 2, /* max buffer needed for 4K mtu */
@@ -134,15 +136,21 @@ struct ipoib_header {
 	u16	reserved;
 };
 
-struct ipoib_cb {
-	struct qdisc_skb_cb	qdisc_cb;
-	u8			hwaddr[INFINIBAND_ALEN];
+struct ipoib_pseudo_header {
+	u8	hwaddr[INFINIBAND_ALEN];
 };
 
-static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb)
+static inline void skb_add_pseudo_hdr(struct sk_buff *skb)
 {
-	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb));
-	return (struct ipoib_cb *)skb->cb;
+	char *data = skb_push(skb, IPOIB_PSEUDO_LEN);
+
+	/*
+	 * only the ipoib header is present now, make room for a dummy
+	 * pseudo header and set skb field accordingly
+	 */
+	memset(data, 0, IPOIB_PSEUDO_LEN);
+	skb_reset_mac_header(skb);
+	skb_pull(skb, IPOIB_HARD_LEN);
 }
 
 /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 4ad297d..339a1ee 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level,
 #define IPOIB_CM_RX_DELAY       (3 * 256 * HZ)
 #define IPOIB_CM_RX_UPDATE_MASK (0x3)
 
+#define IPOIB_CM_RX_RESERVE     (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN)
+
 static struct ib_qp_attr ipoib_cm_err_attr = {
 	.qp_state = IB_QPS_ERR
 };
@@ -146,15 +148,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
 	struct sk_buff *skb;
 	int i;
 
-	skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12);
+	skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16));
 	if (unlikely(!skb))
 		return NULL;
 
 	/*
-	 * IPoIB adds a 4 byte header. So we need 12 more bytes to align the
+	 * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the
 	 * IP header to a multiple of 16.
 	 */
-	skb_reserve(skb, 12);
+	skb_reserve(skb, IPOIB_CM_RX_RESERVE);
 
 	mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE,
 				       DMA_FROM_DEVICE);
@@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	if (wc->byte_len < IPOIB_CM_COPYBREAK) {
 		int dlen = wc->byte_len;
 
-		small_skb = dev_alloc_skb(dlen + 12);
+		small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE);
 		if (small_skb) {
-			skb_reserve(small_skb, 12);
+			skb_reserve(small_skb, IPOIB_CM_RX_RESERVE);
 			ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0],
 						   dlen, DMA_FROM_DEVICE);
 			skb_copy_from_linear_data(skb, small_skb->data, dlen);
@@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 
 copied:
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
-	skb_reset_mac_header(skb);
-	skb_pull(skb, IPOIB_ENCAP_LEN);
+	skb_add_pseudo_hdr(skb);
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index be11d5d..830fecb 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -128,16 +128,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
 
 	buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
 
-	skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN);
+	skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN);
 	if (unlikely(!skb))
 		return NULL;
 
 	/*
-	 * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
-	 * header.  So we need 4 more bytes to get to 48 and align the
-	 * IP header to a multiple of 16.
+	 * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is
+	 * 64 bytes aligned
 	 */
-	skb_reserve(skb, 4);
+	skb_reserve(skb, sizeof(struct ipoib_pseudo_header));
 
 	mapping = priv->rx_ring[id].mapping;
 	mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
@@ -253,8 +252,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb_pull(skb, IB_GRH_BYTES);
 
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
-	skb_reset_mac_header(skb);
-	skb_pull(skb, IPOIB_ENCAP_LEN);
+	skb_add_pseudo_hdr(skb);
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 5636fc3d..b58d9dc 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -925,9 +925,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 				ipoib_neigh_free(neigh);
 				goto err_drop;
 			}
-			if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+			if (skb_queue_len(&neigh->queue) <
+			    IPOIB_MAX_PATH_REC_QUEUE) {
+				/* put pseudoheader back on for next time */
+				skb_push(skb, IPOIB_PSEUDO_LEN);
 				__skb_queue_tail(&neigh->queue, skb);
-			else {
+			} else {
 				ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
 					   skb_queue_len(&neigh->queue));
 				goto err_drop;
@@ -964,7 +967,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 }
 
 static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
-			     struct ipoib_cb *cb)
+			     struct ipoib_pseudo_header *phdr)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_path *path;
@@ -972,16 +975,18 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	path = __path_find(dev, cb->hwaddr + 4);
+	path = __path_find(dev, phdr->hwaddr + 4);
 	if (!path || !path->valid) {
 		int new_path = 0;
 
 		if (!path) {
-			path = path_rec_create(dev, cb->hwaddr + 4);
+			path = path_rec_create(dev, phdr->hwaddr + 4);
 			new_path = 1;
 		}
 		if (path) {
 			if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+				/* put pseudoheader back on for next time */
+				skb_push(skb, IPOIB_PSEUDO_LEN);
 				__skb_queue_tail(&path->queue, skb);
 			} else {
 				++dev->stats.tx_dropped;
@@ -1009,10 +1014,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 			  be16_to_cpu(path->pathrec.dlid));
 
 		spin_unlock_irqrestore(&priv->lock, flags);
-		ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr));
+		ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr));
 		return;
 	} else if ((path->query || !path_rec_start(dev, path)) &&
 		   skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+		/* put pseudoheader back on for next time */
+		skb_push(skb, IPOIB_PSEUDO_LEN);
 		__skb_queue_tail(&path->queue, skb);
 	} else {
 		++dev->stats.tx_dropped;
@@ -1026,13 +1033,15 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_neigh *neigh;
-	struct ipoib_cb *cb = ipoib_skb_cb(skb);
+	struct ipoib_pseudo_header *phdr;
 	struct ipoib_header *header;
 	unsigned long flags;
 
+	phdr = (struct ipoib_pseudo_header *) skb->data;
+	skb_pull(skb, sizeof(*phdr));
 	header = (struct ipoib_header *) skb->data;
 
-	if (unlikely(cb->hwaddr[4] == 0xff)) {
+	if (unlikely(phdr->hwaddr[4] == 0xff)) {
 		/* multicast, arrange "if" according to probability */
 		if ((header->proto != htons(ETH_P_IP)) &&
 		    (header->proto != htons(ETH_P_IPV6)) &&
@@ -1045,13 +1054,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NETDEV_TX_OK;
 		}
 		/* Add in the P_Key for multicast*/
-		cb->hwaddr[8] = (priv->pkey >> 8) & 0xff;
-		cb->hwaddr[9] = priv->pkey & 0xff;
+		phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
+		phdr->hwaddr[9] = priv->pkey & 0xff;
 
-		neigh = ipoib_neigh_get(dev, cb->hwaddr);
+		neigh = ipoib_neigh_get(dev, phdr->hwaddr);
 		if (likely(neigh))
 			goto send_using_neigh;
-		ipoib_mcast_send(dev, cb->hwaddr, skb);
+		ipoib_mcast_send(dev, phdr->hwaddr, skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -1060,16 +1069,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	case htons(ETH_P_IP):
 	case htons(ETH_P_IPV6):
 	case htons(ETH_P_TIPC):
-		neigh = ipoib_neigh_get(dev, cb->hwaddr);
+		neigh = ipoib_neigh_get(dev, phdr->hwaddr);
 		if (unlikely(!neigh)) {
-			neigh_add_path(skb, cb->hwaddr, dev);
+			neigh_add_path(skb, phdr->hwaddr, dev);
 			return NETDEV_TX_OK;
 		}
 		break;
 	case htons(ETH_P_ARP):
 	case htons(ETH_P_RARP):
 		/* for unicast ARP and RARP should always perform path find */
-		unicast_arp_send(skb, dev, cb);
+		unicast_arp_send(skb, dev, phdr);
 		return NETDEV_TX_OK;
 	default:
 		/* ethertype not supported by IPoIB */
@@ -1086,11 +1095,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			goto unref;
 		}
 	} else if (neigh->ah) {
-		ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr));
+		ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr));
 		goto unref;
 	}
 
 	if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+		/* put pseudoheader back on for next time */
+		skb_push(skb, sizeof(*phdr));
 		spin_lock_irqsave(&priv->lock, flags);
 		__skb_queue_tail(&neigh->queue, skb);
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1122,8 +1133,8 @@ static int ipoib_hard_header(struct sk_buff *skb,
 			     unsigned short type,
 			     const void *daddr, const void *saddr, unsigned len)
 {
+	struct ipoib_pseudo_header *phdr;
 	struct ipoib_header *header;
-	struct ipoib_cb *cb = ipoib_skb_cb(skb);
 
 	header = (struct ipoib_header *) skb_push(skb, sizeof *header);
 
@@ -1132,12 +1143,13 @@ static int ipoib_hard_header(struct sk_buff *skb,
 
 	/*
 	 * we don't rely on dst_entry structure,  always stuff the
-	 * destination address into skb->cb so we can figure out where
+	 * destination address into skb hard header so we can figure out where
 	 * to send the packet later.
 	 */
-	memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
+	phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr));
+	memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
 
-	return sizeof *header;
+	return IPOIB_HARD_LEN;
 }
 
 static void ipoib_set_mcast_list(struct net_device *dev)
@@ -1759,7 +1771,7 @@ void ipoib_setup(struct net_device *dev)
 
 	dev->flags		|= IFF_BROADCAST | IFF_MULTICAST;
 
-	dev->hard_header_len	 = IPOIB_ENCAP_LEN;
+	dev->hard_header_len	 = IPOIB_HARD_LEN;
 	dev->addr_len		 = INFINIBAND_ALEN;
 	dev->type		 = ARPHRD_INFINIBAND;
 	dev->tx_queue_len	 = ipoib_sendq_size * 2;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index d3394b6..1909dd2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -796,9 +796,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
 			__ipoib_mcast_add(dev, mcast);
 			list_add_tail(&mcast->list, &priv->multicast_list);
 		}
-		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
+		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) {
+			/* put pseudoheader back on for next time */
+			skb_push(skb, sizeof(struct ipoib_pseudo_header));
 			skb_queue_tail(&mcast->pkt_queue, skb);
-		else {
+		} else {
 			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb);
 		}
diff --git a/drivers/input/mouse/focaltech.c b/drivers/input/mouse/focaltech.c
index 54eceb3..a7d3968 100644
--- a/drivers/input/mouse/focaltech.c
+++ b/drivers/input/mouse/focaltech.c
@@ -43,7 +43,7 @@ int focaltech_detect(struct psmouse *psmouse, bool set_properties)
 
 	if (set_properties) {
 		psmouse->vendor = "FocalTech";
-		psmouse->name = "FocalTech Touchpad";
+		psmouse->name = "Touchpad";
 	}
 
 	return 0;
@@ -146,8 +146,8 @@ static void focaltech_report_state(struct psmouse *psmouse)
 	}
 	input_mt_report_pointer_emulation(dev, true);
 
-	input_report_key(psmouse->dev, BTN_LEFT, state->pressed);
-	input_sync(psmouse->dev);
+	input_report_key(dev, BTN_LEFT, state->pressed);
+	input_sync(dev);
 }
 
 static void focaltech_process_touch_packet(struct psmouse *psmouse,
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index f4bfb4b..073246c 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -877,6 +877,13 @@ static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
 		},
 	},
+	{
+		/* Schenker XMG C504 - Elantech touchpad */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "XMG"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C504"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 15c01c3..e6f9b2d 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2636,17 +2636,26 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	/* And we're up. Go go go! */
 	of_iommu_set_ops(dev->of_node, &arm_smmu_ops);
 #ifdef CONFIG_PCI
-	pci_request_acs();
-	ret = bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
-	if (ret)
-		return ret;
+	if (pci_bus_type.iommu_ops != &arm_smmu_ops) {
+		pci_request_acs();
+		ret = bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
+		if (ret)
+			return ret;
+	}
 #endif
 #ifdef CONFIG_ARM_AMBA
-	ret = bus_set_iommu(&amba_bustype, &arm_smmu_ops);
-	if (ret)
-		return ret;
+	if (amba_bustype.iommu_ops != &arm_smmu_ops) {
+		ret = bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+		if (ret)
+			return ret;
+	}
 #endif
-	return bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+	if (platform_bus_type.iommu_ops != &arm_smmu_ops) {
+		ret = bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+		if (ret)
+			return ret;
+	}
+	return 0;
 }
 
 static int arm_smmu_device_remove(struct platform_device *pdev)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index c841eb7..8f72814 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -324,8 +324,10 @@ struct arm_smmu_master_cfg {
 #define INVALID_SMENDX			-1
 #define __fwspec_cfg(fw) ((struct arm_smmu_master_cfg *)fw->iommu_priv)
 #define fwspec_smmu(fw)  (__fwspec_cfg(fw)->smmu)
+#define fwspec_smendx(fw, i) \
+	(i >= fw->num_ids ? INVALID_SMENDX : __fwspec_cfg(fw)->smendx[i])
 #define for_each_cfg_sme(fw, i, idx) \
-	for (i = 0; idx = __fwspec_cfg(fw)->smendx[i], i < fw->num_ids; ++i)
+	for (i = 0; idx = fwspec_smendx(fw, i), i < fw->num_ids; ++i)
 
 struct arm_smmu_device {
 	struct device			*dev;
@@ -1228,6 +1230,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return -ENXIO;
 	}
 
+	/*
+	 * FIXME: The arch/arm DMA API code tries to attach devices to its own
+	 * domains between of_xlate() and add_device() - we have no way to cope
+	 * with that, so until ARM gets converted to rely on groups and default
+	 * domains, just say no (but more politely than by dereferencing NULL).
+	 * This should be at least a WARN_ON once that's sorted.
+	 */
+	if (!fwspec->iommu_priv)
+		return -ENODEV;
+
 	smmu = fwspec_smmu(fwspec);
 	/* Ensure that the domain is finalised */
 	ret = arm_smmu_init_domain_context(domain, smmu);
@@ -1390,7 +1402,7 @@ static int arm_smmu_add_device(struct device *dev)
 		fwspec = dev->iommu_fwspec;
 		if (ret)
 			goto out_free;
-	} else if (fwspec) {
+	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
 		smmu = arm_smmu_get_by_node(to_of_node(fwspec->iommu_fwnode));
 	} else {
 		return -ENODEV;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a4407ea..3965e73 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1711,6 +1711,7 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
 	if (!iommu->domains || !iommu->domain_ids)
 		return;
 
+again:
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_entry_safe(info, tmp, &device_domain_list, global) {
 		struct dmar_domain *domain;
@@ -1723,10 +1724,19 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
 
 		domain = info->domain;
 
-		dmar_remove_one_dev_info(domain, info->dev);
+		__dmar_remove_one_dev_info(info);
 
-		if (!domain_type_is_vm_or_si(domain))
+		if (!domain_type_is_vm_or_si(domain)) {
+			/*
+			 * The domain_exit() function  can't be called under
+			 * device_domain_lock, as it takes this lock itself.
+			 * So release the lock here and re-run the loop
+			 * afterwards.
+			 */
+			spin_unlock_irqrestore(&device_domain_lock, flags);
 			domain_exit(domain);
+			goto again;
+		}
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c
index c0e7b62..1210244 100644
--- a/drivers/ipack/ipack.c
+++ b/drivers/ipack/ipack.c
@@ -178,7 +178,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 		       idev->id_vendor, idev->id_device);
 }
 
-ipack_device_attr(id_format, "0x%hhu\n");
+ipack_device_attr(id_format, "0x%hhx\n");
 
 static DEVICE_ATTR_RO(id);
 static DEVICE_ATTR_RO(id_device);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 8abde6b..6d53810 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -266,7 +266,7 @@ static struct raid_type {
 	{"raid10_offset", "raid10 offset (striped mirrors)",	    0, 2, 10, ALGORITHM_RAID10_OFFSET},
 	{"raid10_near",	  "raid10 near (striped mirrors)",	    0, 2, 10, ALGORITHM_RAID10_NEAR},
 	{"raid10",	  "raid10 (striped mirrors)",		    0, 2, 10, ALGORITHM_RAID10_DEFAULT},
-	{"raid4",	  "raid4 (dedicated last parity disk)",	    1, 2, 4,  ALGORITHM_PARITY_N}, /* raid4 layout = raid5_n */
+	{"raid4",	  "raid4 (dedicated first parity disk)",    1, 2, 5,  ALGORITHM_PARITY_0}, /* raid4 layout = raid5_0 */
 	{"raid5_n",	  "raid5 (dedicated last parity disk)",	    1, 2, 5,  ALGORITHM_PARITY_N},
 	{"raid5_ls",	  "raid5 (left symmetric)",		    1, 2, 5,  ALGORITHM_LEFT_SYMMETRIC},
 	{"raid5_rs",	  "raid5 (right symmetric)",		    1, 2, 5,  ALGORITHM_RIGHT_SYMMETRIC},
@@ -2087,11 +2087,11 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 		/*
 		 * No takeover/reshaping, because we don't have the extended v1.9.0 metadata
 		 */
-		if (le32_to_cpu(sb->level) != mddev->level) {
+		if (le32_to_cpu(sb->level) != mddev->new_level) {
 			DMERR("Reshaping/takeover raid sets not yet supported. (raid level/stripes/size change)");
 			return -EINVAL;
 		}
-		if (le32_to_cpu(sb->layout) != mddev->layout) {
+		if (le32_to_cpu(sb->layout) != mddev->new_layout) {
 			DMERR("Reshaping raid sets not yet supported. (raid layout change)");
 			DMERR("	 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
 			DMERR("	 Old layout: %s w/ %d copies",
@@ -2102,7 +2102,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 			      raid10_md_layout_to_copies(mddev->layout));
 			return -EINVAL;
 		}
-		if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
+		if (le32_to_cpu(sb->stripe_sectors) != mddev->new_chunk_sectors) {
 			DMERR("Reshaping raid sets not yet supported. (stripe sectors change)");
 			return -EINVAL;
 		}
@@ -2115,6 +2115,8 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 			return -EINVAL;
 		}
 
+		DMINFO("Discovered old metadata format; upgrading to extended metadata format");
+
 		/* Table line is checked vs. authoritative superblock */
 		rs_set_new(rs);
 	}
@@ -2258,7 +2260,8 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
 	if (!mddev->events && super_init_validation(rs, rdev))
 		return -EINVAL;
 
-	if (le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
+	if (le32_to_cpu(sb->compat_features) &&
+	    le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
 		rs->ti->error = "Unable to assemble array: Unknown flag(s) in compatible feature flags";
 		return -EINVAL;
 	}
@@ -3646,7 +3649,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 9, 0},
+	.version = {1, 9, 1},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index bdf1606..9a8b710 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -145,7 +145,6 @@ static void dispatch_bios(void *context, struct bio_list *bio_list)
 
 struct dm_raid1_bio_record {
 	struct mirror *m;
-	/* if details->bi_bdev == NULL, details were not saved */
 	struct dm_bio_details details;
 	region_t write_region;
 };
@@ -1200,8 +1199,6 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
 	struct dm_raid1_bio_record *bio_record =
 	  dm_per_bio_data(bio, sizeof(struct dm_raid1_bio_record));
 
-	bio_record->details.bi_bdev = NULL;
-
 	if (rw == WRITE) {
 		/* Save region for mirror_end_io() handler */
 		bio_record->write_region = dm_rh_bio_to_region(ms->rh, bio);
@@ -1260,22 +1257,12 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 	}
 
 	if (error == -EOPNOTSUPP)
-		goto out;
+		return error;
 
 	if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
-		goto out;
+		return error;
 
 	if (unlikely(error)) {
-		if (!bio_record->details.bi_bdev) {
-			/*
-			 * There wasn't enough memory to record necessary
-			 * information for a retry or there was no other
-			 * mirror in-sync.
-			 */
-			DMERR_LIMIT("Mirror read failed.");
-			return -EIO;
-		}
-
 		m = bio_record->m;
 
 		DMERR("Mirror read failed from %s. Trying alternative device.",
@@ -1291,7 +1278,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 			bd = &bio_record->details;
 
 			dm_bio_restore(bd, bio);
-			bio_record->details.bi_bdev = NULL;
+			bio->bi_error = 0;
 
 			queue_bio(ms, bio, rw);
 			return DM_ENDIO_INCOMPLETE;
@@ -1299,9 +1286,6 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 		DMERR("All replicated volumes dead, failing I/O");
 	}
 
-out:
-	bio_record->details.bi_bdev = NULL;
-
 	return error;
 }
 
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index dc75bea..1d0d2ad 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -856,8 +856,11 @@ int dm_old_init_request_queue(struct mapped_device *md)
 	kthread_init_worker(&md->kworker);
 	md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
 				       "kdmwork-%s", dm_device_name(md));
-	if (IS_ERR(md->kworker_task))
-		return PTR_ERR(md->kworker_task);
+	if (IS_ERR(md->kworker_task)) {
+		int error = PTR_ERR(md->kworker_task);
+		md->kworker_task = NULL;
+		return error;
+	}
 
 	elv_register_queue(md->queue);
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3e407a9..c4b53b3 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -695,37 +695,32 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 
 	tgt->type = dm_get_target_type(type);
 	if (!tgt->type) {
-		DMERR("%s: %s: unknown target type", dm_device_name(t->md),
-		      type);
+		DMERR("%s: %s: unknown target type", dm_device_name(t->md), type);
 		return -EINVAL;
 	}
 
 	if (dm_target_needs_singleton(tgt->type)) {
 		if (t->num_targets) {
-			DMERR("%s: target type %s must appear alone in table",
-			      dm_device_name(t->md), type);
-			return -EINVAL;
+			tgt->error = "singleton target type must appear alone in table";
+			goto bad;
 		}
 		t->singleton = true;
 	}
 
 	if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) {
-		DMERR("%s: target type %s may not be included in read-only tables",
-		      dm_device_name(t->md), type);
-		return -EINVAL;
+		tgt->error = "target type may not be included in a read-only table";
+		goto bad;
 	}
 
 	if (t->immutable_target_type) {
 		if (t->immutable_target_type != tgt->type) {
-			DMERR("%s: immutable target type %s cannot be mixed with other target types",
-			      dm_device_name(t->md), t->immutable_target_type->name);
-			return -EINVAL;
+			tgt->error = "immutable target type cannot be mixed with other target types";
+			goto bad;
 		}
 	} else if (dm_target_is_immutable(tgt->type)) {
 		if (t->num_targets) {
-			DMERR("%s: immutable target type %s cannot be mixed with other target types",
-			      dm_device_name(t->md), tgt->type->name);
-			return -EINVAL;
+			tgt->error = "immutable target type cannot be mixed with other target types";
+			goto bad;
 		}
 		t->immutable_target_type = tgt->type;
 	}
@@ -740,7 +735,6 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 	 */
 	if (!adjoin(t, tgt)) {
 		tgt->error = "Gap in table";
-		r = -EINVAL;
 		goto bad;
 	}
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 147af95..ef7bf1d 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1423,8 +1423,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	if (md->bs)
 		bioset_free(md->bs);
 
-	cleanup_srcu_struct(&md->io_barrier);
-
 	if (md->disk) {
 		spin_lock(&_minor_lock);
 		md->disk->private_data = NULL;
@@ -1436,6 +1434,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	if (md->queue)
 		blk_cleanup_queue(md->queue);
 
+	cleanup_srcu_struct(&md->io_barrier);
+
 	if (md->bdev) {
 		bdput(md->bdev);
 		md->bdev = NULL;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index eac84d8..2089d46 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3887,10 +3887,10 @@ array_state_show(struct mddev *mddev, char *page)
 			st = read_auto;
 			break;
 		case 0:
-			if (mddev->in_sync)
-				st = clean;
-			else if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
+			if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
 				st = write_pending;
+			else if (mddev->in_sync)
+				st = clean;
 			else if (mddev->safemode)
 				st = active_idle;
 			else
@@ -8144,14 +8144,14 @@ void md_do_sync(struct md_thread *thread)
 
 	if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    !test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
-	    mddev->curr_resync > 2) {
+	    mddev->curr_resync > 3) {
 		mddev->curr_resync_completed = mddev->curr_resync;
 		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 	}
 	mddev->pers->sync_request(mddev, max_sectors, &skipped);
 
 	if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
-	    mddev->curr_resync > 2) {
+	    mddev->curr_resync > 3) {
 		if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
 			if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 				if (mddev->curr_resync >= mddev->recovery_cp) {
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 1961d82..29e2df5 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -403,11 +403,14 @@ static void raid1_end_write_request(struct bio *bio)
 	struct bio *to_put = NULL;
 	int mirror = find_bio_disk(r1_bio, bio);
 	struct md_rdev *rdev = conf->mirrors[mirror].rdev;
+	bool discard_error;
+
+	discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD;
 
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_error) {
+	if (bio->bi_error && !discard_error) {
 		set_bit(WriteErrorSeen,	&rdev->flags);
 		if (!test_and_set_bit(WantReplacement, &rdev->flags))
 			set_bit(MD_RECOVERY_NEEDED, &
@@ -444,7 +447,7 @@ static void raid1_end_write_request(struct bio *bio)
 
 		/* Maybe we can clear some bad blocks. */
 		if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-				&first_bad, &bad_sectors)) {
+				&first_bad, &bad_sectors) && !discard_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
@@ -2294,17 +2297,23 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	 * This is all done synchronously while the array is
 	 * frozen
 	 */
+
+	bio = r1_bio->bios[r1_bio->read_disk];
+	bdevname(bio->bi_bdev, b);
+	bio_put(bio);
+	r1_bio->bios[r1_bio->read_disk] = NULL;
+
 	if (mddev->ro == 0) {
 		freeze_array(conf, 1);
 		fix_read_error(conf, r1_bio->read_disk,
 			       r1_bio->sector, r1_bio->sectors);
 		unfreeze_array(conf);
-	} else
-		md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
+	} else {
+		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
+	}
+
 	rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev);
 
-	bio = r1_bio->bios[r1_bio->read_disk];
-	bdevname(bio->bi_bdev, b);
 read_more:
 	disk = read_balance(conf, r1_bio, &max_sectors);
 	if (disk == -1) {
@@ -2315,11 +2324,6 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	} else {
 		const unsigned long do_sync
 			= r1_bio->master_bio->bi_opf & REQ_SYNC;
-		if (bio) {
-			r1_bio->bios[r1_bio->read_disk] =
-				mddev->ro ? IO_BLOCKED : NULL;
-			bio_put(bio);
-		}
 		r1_bio->read_disk = disk;
 		bio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev);
 		bio_trim(bio, r1_bio->sector - bio->bi_iter.bi_sector,
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index be1a9fc..39fddda 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -447,6 +447,9 @@ static void raid10_end_write_request(struct bio *bio)
 	struct r10conf *conf = r10_bio->mddev->private;
 	int slot, repl;
 	struct md_rdev *rdev = NULL;
+	bool discard_error;
+
+	discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD;
 
 	dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
 
@@ -460,7 +463,7 @@ static void raid10_end_write_request(struct bio *bio)
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_error) {
+	if (bio->bi_error && !discard_error) {
 		if (repl)
 			/* Never record new bad blocks to replacement,
 			 * just fail it.
@@ -503,7 +506,7 @@ static void raid10_end_write_request(struct bio *bio)
 		if (is_badblock(rdev,
 				r10_bio->devs[slot].addr,
 				r10_bio->sectors,
-				&first_bad, &bad_sectors)) {
+				&first_bad, &bad_sectors) && !discard_error) {
 			bio_put(bio);
 			if (repl)
 				r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 1b1ab4a..a227a9f 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1087,7 +1087,7 @@ static int r5l_recovery_log(struct r5l_log *log)
 	 * 1's seq + 10 and let superblock points to meta2. The same recovery will
 	 * not think meta 3 is a valid meta, because its seq doesn't match
 	 */
-	if (ctx.seq > log->last_cp_seq + 1) {
+	if (ctx.seq > log->last_cp_seq) {
 		int ret;
 
 		ret = r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq + 10);
@@ -1096,6 +1096,8 @@ static int r5l_recovery_log(struct r5l_log *log)
 		log->seq = ctx.seq + 11;
 		log->log_start = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
 		r5l_write_super(log, ctx.pos);
+		log->last_checkpoint = ctx.pos;
+		log->next_checkpoint = ctx.pos;
 	} else {
 		log->log_start = ctx.pos;
 		log->seq = ctx.seq;
@@ -1154,6 +1156,7 @@ static int r5l_load_log(struct r5l_log *log)
 	if (create_super) {
 		log->last_cp_seq = prandom_u32();
 		cp = 0;
+		r5l_log_write_empty_meta_block(log, cp, log->last_cp_seq);
 		/*
 		 * Make sure super points to correct address. Log might have
 		 * data very soon. If super hasn't correct log tail address,
@@ -1168,6 +1171,7 @@ static int r5l_load_log(struct r5l_log *log)
 	if (log->max_free_space > RECLAIM_MAX_FREE_SPACE)
 		log->max_free_space = RECLAIM_MAX_FREE_SPACE;
 	log->last_checkpoint = cp;
+	log->next_checkpoint = cp;
 
 	__free_page(page);
 
diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c
index d4bdba6..52bc42d 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.c
+++ b/drivers/media/usb/b2c2/flexcop-usb.c
@@ -73,23 +73,34 @@ static int flexcop_usb_readwrite_dw(struct flexcop_device *fc, u16 wRegOffsPCI,
 	u8 request_type = (read ? USB_DIR_IN : USB_DIR_OUT) | USB_TYPE_VENDOR;
 	u8 wAddress = B2C2_FLEX_PCIOFFSET_TO_INTERNALADDR(wRegOffsPCI) |
 		(read ? 0x80 : 0);
+	int ret;
 
-	int len = usb_control_msg(fc_usb->udev,
+	mutex_lock(&fc_usb->data_mutex);
+	if (!read)
+		memcpy(fc_usb->data, val, sizeof(*val));
+
+	ret = usb_control_msg(fc_usb->udev,
 			read ? B2C2_USB_CTRL_PIPE_IN : B2C2_USB_CTRL_PIPE_OUT,
 			request,
 			request_type, /* 0xc0 read or 0x40 write */
 			wAddress,
 			0,
-			val,
+			fc_usb->data,
 			sizeof(u32),
 			B2C2_WAIT_FOR_OPERATION_RDW * HZ);
 
-	if (len != sizeof(u32)) {
+	if (ret != sizeof(u32)) {
 		err("error while %s dword from %d (%d).", read ? "reading" :
 				"writing", wAddress, wRegOffsPCI);
-		return -EIO;
+		if (ret >= 0)
+			ret = -EIO;
 	}
-	return 0;
+
+	if (read && ret >= 0)
+		memcpy(val, fc_usb->data, sizeof(*val));
+	mutex_unlock(&fc_usb->data_mutex);
+
+	return ret;
 }
 /*
  * DKT 010817 - add support for V8 memory read/write and flash update
@@ -100,9 +111,14 @@ static int flexcop_usb_v8_memory_req(struct flexcop_usb *fc_usb,
 {
 	u8 request_type = USB_TYPE_VENDOR;
 	u16 wIndex;
-	int nWaitTime, pipe, len;
+	int nWaitTime, pipe, ret;
 	wIndex = page << 8;
 
+	if (buflen > sizeof(fc_usb->data)) {
+		err("Buffer size bigger than max URB control message\n");
+		return -EIO;
+	}
+
 	switch (req) {
 	case B2C2_USB_READ_V8_MEM:
 		nWaitTime = B2C2_WAIT_FOR_OPERATION_V8READ;
@@ -127,17 +143,32 @@ static int flexcop_usb_v8_memory_req(struct flexcop_usb *fc_usb,
 	deb_v8("v8mem: %02x %02x %04x %04x, len: %d\n", request_type, req,
 			wAddress, wIndex, buflen);
 
-	len = usb_control_msg(fc_usb->udev, pipe,
+	mutex_lock(&fc_usb->data_mutex);
+
+	if ((request_type & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT)
+		memcpy(fc_usb->data, pbBuffer, buflen);
+
+	ret = usb_control_msg(fc_usb->udev, pipe,
 			req,
 			request_type,
 			wAddress,
 			wIndex,
-			pbBuffer,
+			fc_usb->data,
 			buflen,
 			nWaitTime * HZ);
+	if (ret != buflen)
+		ret = -EIO;
 
-	debug_dump(pbBuffer, len, deb_v8);
-	return len == buflen ? 0 : -EIO;
+	if (ret >= 0) {
+		ret = 0;
+		if ((request_type & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN)
+			memcpy(pbBuffer, fc_usb->data, buflen);
+	}
+
+	mutex_unlock(&fc_usb->data_mutex);
+
+	debug_dump(pbBuffer, ret, deb_v8);
+	return ret;
 }
 
 #define bytes_left_to_read_on_page(paddr,buflen) \
@@ -196,29 +227,6 @@ static int flexcop_usb_get_mac_addr(struct flexcop_device *fc, int extended)
 		fc->dvb_adapter.proposed_mac, 6);
 }
 
-#if 0
-static int flexcop_usb_utility_req(struct flexcop_usb *fc_usb, int set,
-		flexcop_usb_utility_function_t func, u8 extra, u16 wIndex,
-		u16 buflen, u8 *pvBuffer)
-{
-	u16 wValue;
-	u8 request_type = (set ? USB_DIR_OUT : USB_DIR_IN) | USB_TYPE_VENDOR;
-	int nWaitTime = 2,
-	    pipe = set ? B2C2_USB_CTRL_PIPE_OUT : B2C2_USB_CTRL_PIPE_IN, len;
-	wValue = (func << 8) | extra;
-
-	len = usb_control_msg(fc_usb->udev,pipe,
-			B2C2_USB_UTILITY,
-			request_type,
-			wValue,
-			wIndex,
-			pvBuffer,
-			buflen,
-			nWaitTime * HZ);
-	return len == buflen ? 0 : -EIO;
-}
-#endif
-
 /* usb i2c stuff */
 static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c,
 		flexcop_usb_request_t req, flexcop_usb_i2c_function_t func,
@@ -226,9 +234,14 @@ static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c,
 {
 	struct flexcop_usb *fc_usb = i2c->fc->bus_specific;
 	u16 wValue, wIndex;
-	int nWaitTime,pipe,len;
+	int nWaitTime, pipe, ret;
 	u8 request_type = USB_TYPE_VENDOR;
 
+	if (buflen > sizeof(fc_usb->data)) {
+		err("Buffer size bigger than max URB control message\n");
+		return -EIO;
+	}
+
 	switch (func) {
 	case USB_FUNC_I2C_WRITE:
 	case USB_FUNC_I2C_MULTIWRITE:
@@ -257,15 +270,32 @@ static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c,
 			wValue & 0xff, wValue >> 8,
 			wIndex & 0xff, wIndex >> 8);
 
-	len = usb_control_msg(fc_usb->udev,pipe,
+	mutex_lock(&fc_usb->data_mutex);
+
+	if ((request_type & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT)
+		memcpy(fc_usb->data, buf, buflen);
+
+	ret = usb_control_msg(fc_usb->udev, pipe,
 			req,
 			request_type,
 			wValue,
 			wIndex,
-			buf,
+			fc_usb->data,
 			buflen,
 			nWaitTime * HZ);
-	return len == buflen ? 0 : -EREMOTEIO;
+
+	if (ret != buflen)
+		ret = -EIO;
+
+	if (ret >= 0) {
+		ret = 0;
+		if ((request_type & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN)
+			memcpy(buf, fc_usb->data, buflen);
+	}
+
+	mutex_unlock(&fc_usb->data_mutex);
+
+	return 0;
 }
 
 /* actual bus specific access functions,
@@ -516,6 +546,7 @@ static int flexcop_usb_probe(struct usb_interface *intf,
 	/* general flexcop init */
 	fc_usb = fc->bus_specific;
 	fc_usb->fc_dev = fc;
+	mutex_init(&fc_usb->data_mutex);
 
 	fc->read_ibi_reg  = flexcop_usb_read_ibi_reg;
 	fc->write_ibi_reg = flexcop_usb_write_ibi_reg;
diff --git a/drivers/media/usb/b2c2/flexcop-usb.h b/drivers/media/usb/b2c2/flexcop-usb.h
index 92529a9..25ad431 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.h
+++ b/drivers/media/usb/b2c2/flexcop-usb.h
@@ -29,6 +29,10 @@ struct flexcop_usb {
 
 	u8 tmp_buffer[1023+190];
 	int tmp_buffer_length;
+
+	/* for URB control messages */
+	u8 data[80];
+	struct mutex data_mutex;
 };
 
 #if 0
diff --git a/drivers/media/usb/cpia2/cpia2_usb.c b/drivers/media/usb/cpia2/cpia2_usb.c
index 13620cd..e9100a2 100644
--- a/drivers/media/usb/cpia2/cpia2_usb.c
+++ b/drivers/media/usb/cpia2/cpia2_usb.c
@@ -545,18 +545,30 @@ static void free_sbufs(struct camera_data *cam)
 static int write_packet(struct usb_device *udev,
 			u8 request, u8 * registers, u16 start, size_t size)
 {
+	unsigned char *buf;
+	int ret;
+
 	if (!registers || size <= 0)
 		return -EINVAL;
 
-	return usb_control_msg(udev,
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, registers, size);
+
+	ret = usb_control_msg(udev,
 			       usb_sndctrlpipe(udev, 0),
 			       request,
 			       USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 			       start,	/* value */
 			       0,	/* index */
-			       registers,	/* buffer */
+			       buf,	/* buffer */
 			       size,
 			       HZ);
+
+	kfree(buf);
+	return ret;
 }
 
 /****************************************************************************
@@ -567,18 +579,32 @@ static int write_packet(struct usb_device *udev,
 static int read_packet(struct usb_device *udev,
 		       u8 request, u8 * registers, u16 start, size_t size)
 {
+	unsigned char *buf;
+	int ret;
+
 	if (!registers || size <= 0)
 		return -EINVAL;
 
-	return usb_control_msg(udev,
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(udev,
 			       usb_rcvctrlpipe(udev, 0),
 			       request,
 			       USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_DEVICE,
 			       start,	/* value */
 			       0,	/* index */
-			       registers,	/* buffer */
+			       buf,	/* buffer */
 			       size,
 			       HZ);
+
+	if (ret >= 0)
+		memcpy(registers, buf, size);
+
+	kfree(buf);
+
+	return ret;
 }
 
 /******************************************************************************
diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c
index efa782e..b257780 100644
--- a/drivers/media/usb/dvb-usb/af9005.c
+++ b/drivers/media/usb/dvb-usb/af9005.c
@@ -52,17 +52,16 @@ u8 regmask[8] = { 0x01, 0x03, 0x07, 0x0f, 0x1f, 0x3f, 0x7f, 0xff };
 struct af9005_device_state {
 	u8 sequence;
 	int led_state;
+	unsigned char data[256];
+	struct mutex data_mutex;
 };
 
 static int af9005_generic_read_write(struct dvb_usb_device *d, u16 reg,
 			      int readwrite, int type, u8 * values, int len)
 {
 	struct af9005_device_state *st = d->priv;
-	u8 obuf[16] = { 0 };
-	u8 ibuf[17] = { 0 };
-	u8 command;
-	int i;
-	int ret;
+	u8 command, seq;
+	int i, ret;
 
 	if (len < 1) {
 		err("generic read/write, less than 1 byte. Makes no sense.");
@@ -73,16 +72,17 @@ static int af9005_generic_read_write(struct dvb_usb_device *d, u16 reg,
 		return -EINVAL;
 	}
 
-	obuf[0] = 14;		/* rest of buffer length low */
-	obuf[1] = 0;		/* rest of buffer length high */
+	mutex_lock(&st->data_mutex);
+	st->data[0] = 14;		/* rest of buffer length low */
+	st->data[1] = 0;		/* rest of buffer length high */
 
-	obuf[2] = AF9005_REGISTER_RW;	/* register operation */
-	obuf[3] = 12;		/* rest of buffer length */
+	st->data[2] = AF9005_REGISTER_RW;	/* register operation */
+	st->data[3] = 12;		/* rest of buffer length */
 
-	obuf[4] = st->sequence++;	/* sequence number */
+	st->data[4] = seq = st->sequence++;	/* sequence number */
 
-	obuf[5] = (u8) (reg >> 8);	/* register address */
-	obuf[6] = (u8) (reg & 0xff);
+	st->data[5] = (u8) (reg >> 8);	/* register address */
+	st->data[6] = (u8) (reg & 0xff);
 
 	if (type == AF9005_OFDM_REG) {
 		command = AF9005_CMD_OFDM_REG;
@@ -96,51 +96,52 @@ static int af9005_generic_read_write(struct dvb_usb_device *d, u16 reg,
 	command |= readwrite;
 	if (readwrite == AF9005_CMD_WRITE)
 		for (i = 0; i < len; i++)
-			obuf[8 + i] = values[i];
+			st->data[8 + i] = values[i];
 	else if (type == AF9005_TUNER_REG)
 		/* read command for tuner, the first byte contains the i2c address */
-		obuf[8] = values[0];
-	obuf[7] = command;
+		st->data[8] = values[0];
+	st->data[7] = command;
 
-	ret = dvb_usb_generic_rw(d, obuf, 16, ibuf, 17, 0);
+	ret = dvb_usb_generic_rw(d, st->data, 16, st->data, 17, 0);
 	if (ret)
-		return ret;
+		goto ret;
 
 	/* sanity check */
-	if (ibuf[2] != AF9005_REGISTER_RW_ACK) {
+	if (st->data[2] != AF9005_REGISTER_RW_ACK) {
 		err("generic read/write, wrong reply code.");
-		return -EIO;
+		ret = -EIO;
+		goto ret;
 	}
-	if (ibuf[3] != 0x0d) {
+	if (st->data[3] != 0x0d) {
 		err("generic read/write, wrong length in reply.");
-		return -EIO;
+		ret = -EIO;
+		goto ret;
 	}
-	if (ibuf[4] != obuf[4]) {
+	if (st->data[4] != seq) {
 		err("generic read/write, wrong sequence in reply.");
-		return -EIO;
+		ret = -EIO;
+		goto ret;
 	}
 	/*
-	   Windows driver doesn't check these fields, in fact sometimes
-	   the register in the reply is different that what has been sent
-
-	   if (ibuf[5] != obuf[5] || ibuf[6] != obuf[6]) {
-	   err("generic read/write, wrong register in reply.");
-	   return -EIO;
-	   }
-	   if (ibuf[7] != command) {
-	   err("generic read/write wrong command in reply.");
-	   return -EIO;
-	   }
+	 * In thesis, both input and output buffers should have
+	 * identical values for st->data[5] to st->data[8].
+	 * However, windows driver doesn't check these fields, in fact
+	 * sometimes the register in the reply is different that what
+	 * has been sent
 	 */
-	if (ibuf[16] != 0x01) {
+	if (st->data[16] != 0x01) {
 		err("generic read/write wrong status code in reply.");
-		return -EIO;
+		ret = -EIO;
+		goto ret;
 	}
+
 	if (readwrite == AF9005_CMD_READ)
 		for (i = 0; i < len; i++)
-			values[i] = ibuf[8 + i];
+			values[i] = st->data[8 + i];
 
-	return 0;
+ret:
+	mutex_unlock(&st->data_mutex);
+	return ret;
 
 }
 
@@ -464,8 +465,7 @@ int af9005_send_command(struct dvb_usb_device *d, u8 command, u8 * wbuf,
 	struct af9005_device_state *st = d->priv;
 
 	int ret, i, packet_len;
-	u8 buf[64];
-	u8 ibuf[64];
+	u8 seq;
 
 	if (wlen < 0) {
 		err("send command, wlen less than 0 bytes. Makes no sense.");
@@ -480,94 +480,97 @@ int af9005_send_command(struct dvb_usb_device *d, u8 command, u8 * wbuf,
 		return -EINVAL;
 	}
 	packet_len = wlen + 5;
-	buf[0] = (u8) (packet_len & 0xff);
-	buf[1] = (u8) ((packet_len & 0xff00) >> 8);
 
-	buf[2] = 0x26;		/* packet type */
-	buf[3] = wlen + 3;
-	buf[4] = st->sequence++;
-	buf[5] = command;
-	buf[6] = wlen;
+	mutex_lock(&st->data_mutex);
+
+	st->data[0] = (u8) (packet_len & 0xff);
+	st->data[1] = (u8) ((packet_len & 0xff00) >> 8);
+
+	st->data[2] = 0x26;		/* packet type */
+	st->data[3] = wlen + 3;
+	st->data[4] = seq = st->sequence++;
+	st->data[5] = command;
+	st->data[6] = wlen;
 	for (i = 0; i < wlen; i++)
-		buf[7 + i] = wbuf[i];
-	ret = dvb_usb_generic_rw(d, buf, wlen + 7, ibuf, rlen + 7, 0);
-	if (ret)
-		return ret;
-	if (ibuf[2] != 0x27) {
+		st->data[7 + i] = wbuf[i];
+	ret = dvb_usb_generic_rw(d, st->data, wlen + 7, st->data, rlen + 7, 0);
+	if (st->data[2] != 0x27) {
 		err("send command, wrong reply code.");
-		return -EIO;
-	}
-	if (ibuf[4] != buf[4]) {
+		ret = -EIO;
+	} else if (st->data[4] != seq) {
 		err("send command, wrong sequence in reply.");
-		return -EIO;
-	}
-	if (ibuf[5] != 0x01) {
+		ret = -EIO;
+	} else if (st->data[5] != 0x01) {
 		err("send command, wrong status code in reply.");
-		return -EIO;
-	}
-	if (ibuf[6] != rlen) {
+		ret = -EIO;
+	} else if (st->data[6] != rlen) {
 		err("send command, invalid data length in reply.");
-		return -EIO;
+		ret = -EIO;
 	}
-	for (i = 0; i < rlen; i++)
-		rbuf[i] = ibuf[i + 7];
-	return 0;
+	if (!ret) {
+		for (i = 0; i < rlen; i++)
+			rbuf[i] = st->data[i + 7];
+	}
+
+	mutex_unlock(&st->data_mutex);
+	return ret;
 }
 
 int af9005_read_eeprom(struct dvb_usb_device *d, u8 address, u8 * values,
 		       int len)
 {
 	struct af9005_device_state *st = d->priv;
-	u8 obuf[16], ibuf[14];
+	u8 seq;
 	int ret, i;
 
-	memset(obuf, 0, sizeof(obuf));
-	memset(ibuf, 0, sizeof(ibuf));
+	mutex_lock(&st->data_mutex);
 
-	obuf[0] = 14;		/* length of rest of packet low */
-	obuf[1] = 0;		/* length of rest of packer high */
+	memset(st->data, 0, sizeof(st->data));
 
-	obuf[2] = 0x2a;		/* read/write eeprom */
+	st->data[0] = 14;		/* length of rest of packet low */
+	st->data[1] = 0;		/* length of rest of packer high */
 
-	obuf[3] = 12;		/* size */
+	st->data[2] = 0x2a;		/* read/write eeprom */
 
-	obuf[4] = st->sequence++;
+	st->data[3] = 12;		/* size */
 
-	obuf[5] = 0;		/* read */
+	st->data[4] = seq = st->sequence++;
 
-	obuf[6] = len;
-	obuf[7] = address;
-	ret = dvb_usb_generic_rw(d, obuf, 16, ibuf, 14, 0);
-	if (ret)
-		return ret;
-	if (ibuf[2] != 0x2b) {
+	st->data[5] = 0;		/* read */
+
+	st->data[6] = len;
+	st->data[7] = address;
+	ret = dvb_usb_generic_rw(d, st->data, 16, st->data, 14, 0);
+	if (st->data[2] != 0x2b) {
 		err("Read eeprom, invalid reply code");
-		return -EIO;
-	}
-	if (ibuf[3] != 10) {
+		ret = -EIO;
+	} else if (st->data[3] != 10) {
 		err("Read eeprom, invalid reply length");
-		return -EIO;
-	}
-	if (ibuf[4] != obuf[4]) {
+		ret = -EIO;
+	} else if (st->data[4] != seq) {
 		err("Read eeprom, wrong sequence in reply ");
-		return -EIO;
-	}
-	if (ibuf[5] != 1) {
+		ret = -EIO;
+	} else if (st->data[5] != 1) {
 		err("Read eeprom, wrong status in reply ");
-		return -EIO;
+		ret = -EIO;
 	}
-	for (i = 0; i < len; i++) {
-		values[i] = ibuf[6 + i];
+
+	if (!ret) {
+		for (i = 0; i < len; i++)
+			values[i] = st->data[6 + i];
 	}
-	return 0;
+	mutex_unlock(&st->data_mutex);
+
+	return ret;
 }
 
-static int af9005_boot_packet(struct usb_device *udev, int type, u8 * reply)
+static int af9005_boot_packet(struct usb_device *udev, int type, u8 *reply,
+			      u8 *buf, int size)
 {
-	u8 buf[FW_BULKOUT_SIZE + 2];
 	u16 checksum;
 	int act_len, i, ret;
-	memset(buf, 0, sizeof(buf));
+
+	memset(buf, 0, size);
 	buf[0] = (u8) (FW_BULKOUT_SIZE & 0xff);
 	buf[1] = (u8) ((FW_BULKOUT_SIZE >> 8) & 0xff);
 	switch (type) {
@@ -720,15 +723,21 @@ static int af9005_download_firmware(struct usb_device *udev, const struct firmwa
 {
 	int i, packets, ret, act_len;
 
-	u8 buf[FW_BULKOUT_SIZE + 2];
+	u8 *buf;
 	u8 reply;
 
-	ret = af9005_boot_packet(udev, FW_CONFIG, &reply);
+	buf = kmalloc(FW_BULKOUT_SIZE + 2, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = af9005_boot_packet(udev, FW_CONFIG, &reply, buf,
+				 FW_BULKOUT_SIZE + 2);
 	if (ret)
-		return ret;
+		goto err;
 	if (reply != 0x01) {
 		err("before downloading firmware, FW_CONFIG expected 0x01, received 0x%x", reply);
-		return -EIO;
+		ret = -EIO;
+		goto err;
 	}
 	packets = fw->size / FW_BULKOUT_SIZE;
 	buf[0] = (u8) (FW_BULKOUT_SIZE & 0xff);
@@ -743,28 +752,35 @@ static int af9005_download_firmware(struct usb_device *udev, const struct firmwa
 				   buf, FW_BULKOUT_SIZE + 2, &act_len, 1000);
 		if (ret) {
 			err("firmware download failed at packet %d with code %d", i, ret);
-			return ret;
+			goto err;
 		}
 	}
-	ret = af9005_boot_packet(udev, FW_CONFIRM, &reply);
+	ret = af9005_boot_packet(udev, FW_CONFIRM, &reply,
+				 buf, FW_BULKOUT_SIZE + 2);
 	if (ret)
-		return ret;
+		goto err;
 	if (reply != (u8) (packets & 0xff)) {
 		err("after downloading firmware, FW_CONFIRM expected 0x%x, received 0x%x", packets & 0xff, reply);
-		return -EIO;
+		ret = -EIO;
+		goto err;
 	}
-	ret = af9005_boot_packet(udev, FW_BOOT, &reply);
+	ret = af9005_boot_packet(udev, FW_BOOT, &reply, buf,
+				 FW_BULKOUT_SIZE + 2);
 	if (ret)
-		return ret;
-	ret = af9005_boot_packet(udev, FW_CONFIG, &reply);
+		goto err;
+	ret = af9005_boot_packet(udev, FW_CONFIG, &reply, buf,
+				 FW_BULKOUT_SIZE + 2);
 	if (ret)
-		return ret;
+		goto err;
 	if (reply != 0x02) {
 		err("after downloading firmware, FW_CONFIG expected 0x02, received 0x%x", reply);
-		return -EIO;
+		ret = -EIO;
+		goto err;
 	}
 
-	return 0;
+err:
+	kfree(buf);
+	return ret;
 
 }
 
@@ -823,53 +839,59 @@ static int af9005_rc_query(struct dvb_usb_device *d, u32 * event, int *state)
 {
 	struct af9005_device_state *st = d->priv;
 	int ret, len;
-
-	u8 obuf[5];
-	u8 ibuf[256];
+	u8 seq;
 
 	*state = REMOTE_NO_KEY_PRESSED;
 	if (rc_decode == NULL) {
 		/* it shouldn't never come here */
 		return 0;
 	}
+
+	mutex_lock(&st->data_mutex);
+
 	/* deb_info("rc_query\n"); */
-	obuf[0] = 3;		/* rest of packet length low */
-	obuf[1] = 0;		/* rest of packet lentgh high */
-	obuf[2] = 0x40;		/* read remote */
-	obuf[3] = 1;		/* rest of packet length */
-	obuf[4] = st->sequence++;	/* sequence number */
-	ret = dvb_usb_generic_rw(d, obuf, 5, ibuf, 256, 0);
+	st->data[0] = 3;		/* rest of packet length low */
+	st->data[1] = 0;		/* rest of packet lentgh high */
+	st->data[2] = 0x40;		/* read remote */
+	st->data[3] = 1;		/* rest of packet length */
+	st->data[4] = seq = st->sequence++;	/* sequence number */
+	ret = dvb_usb_generic_rw(d, st->data, 5, st->data, 256, 0);
 	if (ret) {
 		err("rc query failed");
-		return ret;
+		goto ret;
 	}
-	if (ibuf[2] != 0x41) {
+	if (st->data[2] != 0x41) {
 		err("rc query bad header.");
-		return -EIO;
-	}
-	if (ibuf[4] != obuf[4]) {
+		ret = -EIO;
+		goto ret;
+	} else if (st->data[4] != seq) {
 		err("rc query bad sequence.");
-		return -EIO;
+		ret = -EIO;
+		goto ret;
 	}
-	len = ibuf[5];
+	len = st->data[5];
 	if (len > 246) {
 		err("rc query invalid length");
-		return -EIO;
+		ret = -EIO;
+		goto ret;
 	}
 	if (len > 0) {
 		deb_rc("rc data (%d) ", len);
-		debug_dump((ibuf + 6), len, deb_rc);
-		ret = rc_decode(d, &ibuf[6], len, event, state);
+		debug_dump((st->data + 6), len, deb_rc);
+		ret = rc_decode(d, &st->data[6], len, event, state);
 		if (ret) {
 			err("rc_decode failed");
-			return ret;
+			goto ret;
 		} else {
 			deb_rc("rc_decode state %x event %x\n", *state, *event);
 			if (*state == REMOTE_KEY_REPEAT)
 				*event = d->last_event;
 		}
 	}
-	return 0;
+
+ret:
+	mutex_unlock(&st->data_mutex);
+	return ret;
 }
 
 static int af9005_power_ctrl(struct dvb_usb_device *d, int onoff)
@@ -953,10 +975,16 @@ static int af9005_identify_state(struct usb_device *udev,
 				 int *cold)
 {
 	int ret;
-	u8 reply;
-	ret = af9005_boot_packet(udev, FW_CONFIG, &reply);
+	u8 reply, *buf;
+
+	buf = kmalloc(FW_BULKOUT_SIZE + 2, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = af9005_boot_packet(udev, FW_CONFIG, &reply,
+				 buf, FW_BULKOUT_SIZE + 2);
 	if (ret)
-		return ret;
+		goto err;
 	deb_info("result of FW_CONFIG in identify state %d\n", reply);
 	if (reply == 0x01)
 		*cold = 1;
@@ -965,7 +993,10 @@ static int af9005_identify_state(struct usb_device *udev,
 	else
 		return -EIO;
 	deb_info("Identify state cold = %d\n", *cold);
-	return 0;
+
+err:
+	kfree(buf);
+	return ret;
 }
 
 static struct dvb_usb_device_properties af9005_properties;
@@ -973,8 +1004,20 @@ static struct dvb_usb_device_properties af9005_properties;
 static int af9005_usb_probe(struct usb_interface *intf,
 			    const struct usb_device_id *id)
 {
-	return dvb_usb_device_init(intf, &af9005_properties,
-				   THIS_MODULE, NULL, adapter_nr);
+	struct dvb_usb_device *d;
+	struct af9005_device_state *st;
+	int ret;
+
+	ret = dvb_usb_device_init(intf, &af9005_properties,
+				  THIS_MODULE, &d, adapter_nr);
+
+	if (ret < 0)
+		return ret;
+
+	st = d->priv;
+	mutex_init(&st->data_mutex);
+
+	return 0;
 }
 
 enum af9005_usb_table_entry {
diff --git a/drivers/media/usb/dvb-usb/cinergyT2-core.c b/drivers/media/usb/dvb-usb/cinergyT2-core.c
index 9fd1527..8ac8254 100644
--- a/drivers/media/usb/dvb-usb/cinergyT2-core.c
+++ b/drivers/media/usb/dvb-usb/cinergyT2-core.c
@@ -41,6 +41,8 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
 struct cinergyt2_state {
 	u8 rc_counter;
+	unsigned char data[64];
+	struct mutex data_mutex;
 };
 
 /* We are missing a release hook with usb_device data */
@@ -50,38 +52,57 @@ static struct dvb_usb_device_properties cinergyt2_properties;
 
 static int cinergyt2_streaming_ctrl(struct dvb_usb_adapter *adap, int enable)
 {
-	char buf[] = { CINERGYT2_EP1_CONTROL_STREAM_TRANSFER, enable ? 1 : 0 };
-	char result[64];
-	return dvb_usb_generic_rw(adap->dev, buf, sizeof(buf), result,
-				sizeof(result), 0);
+	struct dvb_usb_device *d = adap->dev;
+	struct cinergyt2_state *st = d->priv;
+	int ret;
+
+	mutex_lock(&st->data_mutex);
+	st->data[0] = CINERGYT2_EP1_CONTROL_STREAM_TRANSFER;
+	st->data[1] = enable ? 1 : 0;
+
+	ret = dvb_usb_generic_rw(d, st->data, 2, st->data, 64, 0);
+	mutex_unlock(&st->data_mutex);
+
+	return ret;
 }
 
 static int cinergyt2_power_ctrl(struct dvb_usb_device *d, int enable)
 {
-	char buf[] = { CINERGYT2_EP1_SLEEP_MODE, enable ? 0 : 1 };
-	char state[3];
-	return dvb_usb_generic_rw(d, buf, sizeof(buf), state, sizeof(state), 0);
+	struct cinergyt2_state *st = d->priv;
+	int ret;
+
+	mutex_lock(&st->data_mutex);
+	st->data[0] = CINERGYT2_EP1_SLEEP_MODE;
+	st->data[1] = enable ? 0 : 1;
+
+	ret = dvb_usb_generic_rw(d, st->data, 2, st->data, 3, 0);
+	mutex_unlock(&st->data_mutex);
+
+	return ret;
 }
 
 static int cinergyt2_frontend_attach(struct dvb_usb_adapter *adap)
 {
-	char query[] = { CINERGYT2_EP1_GET_FIRMWARE_VERSION };
-	char state[3];
+	struct dvb_usb_device *d = adap->dev;
+	struct cinergyt2_state *st = d->priv;
 	int ret;
 
 	adap->fe_adap[0].fe = cinergyt2_fe_attach(adap->dev);
 
-	ret = dvb_usb_generic_rw(adap->dev, query, sizeof(query), state,
-				sizeof(state), 0);
+	mutex_lock(&st->data_mutex);
+	st->data[0] = CINERGYT2_EP1_GET_FIRMWARE_VERSION;
+
+	ret = dvb_usb_generic_rw(d, st->data, 1, st->data, 3, 0);
 	if (ret < 0) {
 		deb_rc("cinergyt2_power_ctrl() Failed to retrieve sleep "
 			"state info\n");
 	}
+	mutex_unlock(&st->data_mutex);
 
 	/* Copy this pointer as we are gonna need it in the release phase */
 	cinergyt2_usb_device = adap->dev;
 
-	return 0;
+	return ret;
 }
 
 static struct rc_map_table rc_map_cinergyt2_table[] = {
@@ -141,13 +162,18 @@ static int repeatable_keys[] = {
 static int cinergyt2_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
 {
 	struct cinergyt2_state *st = d->priv;
-	u8 key[5] = {0, 0, 0, 0, 0}, cmd = CINERGYT2_EP1_GET_RC_EVENTS;
-	int i;
+	int i, ret;
 
 	*state = REMOTE_NO_KEY_PRESSED;
 
-	dvb_usb_generic_rw(d, &cmd, 1, key, sizeof(key), 0);
-	if (key[4] == 0xff) {
+	mutex_lock(&st->data_mutex);
+	st->data[0] = CINERGYT2_EP1_GET_RC_EVENTS;
+
+	ret = dvb_usb_generic_rw(d, st->data, 1, st->data, 5, 0);
+	if (ret < 0)
+		goto ret;
+
+	if (st->data[4] == 0xff) {
 		/* key repeat */
 		st->rc_counter++;
 		if (st->rc_counter > RC_REPEAT_DELAY) {
@@ -157,31 +183,45 @@ static int cinergyt2_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
 					*event = d->last_event;
 					deb_rc("repeat key, event %x\n",
 						   *event);
-					return 0;
+					goto ret;
 				}
 			}
 			deb_rc("repeated key (non repeatable)\n");
 		}
-		return 0;
+		goto ret;
 	}
 
 	/* hack to pass checksum on the custom field */
-	key[2] = ~key[1];
-	dvb_usb_nec_rc_key_to_event(d, key, event, state);
-	if (key[0] != 0) {
+	st->data[2] = ~st->data[1];
+	dvb_usb_nec_rc_key_to_event(d, st->data, event, state);
+	if (st->data[0] != 0) {
 		if (*event != d->last_event)
 			st->rc_counter = 0;
 
-		deb_rc("key: %*ph\n", 5, key);
+		deb_rc("key: %*ph\n", 5, st->data);
 	}
-	return 0;
+
+ret:
+	mutex_unlock(&st->data_mutex);
+	return ret;
 }
 
 static int cinergyt2_usb_probe(struct usb_interface *intf,
 				const struct usb_device_id *id)
 {
-	return dvb_usb_device_init(intf, &cinergyt2_properties,
-					THIS_MODULE, NULL, adapter_nr);
+	struct dvb_usb_device *d;
+	struct cinergyt2_state *st;
+	int ret;
+
+	ret = dvb_usb_device_init(intf, &cinergyt2_properties,
+				  THIS_MODULE, &d, adapter_nr);
+	if (ret < 0)
+		return ret;
+
+	st = d->priv;
+	mutex_init(&st->data_mutex);
+
+	return 0;
 }
 
 
diff --git a/drivers/media/usb/dvb-usb/cinergyT2-fe.c b/drivers/media/usb/dvb-usb/cinergyT2-fe.c
index b3ec743..2d29b41 100644
--- a/drivers/media/usb/dvb-usb/cinergyT2-fe.c
+++ b/drivers/media/usb/dvb-usb/cinergyT2-fe.c
@@ -139,32 +139,42 @@ static uint16_t compute_tps(struct dtv_frontend_properties *op)
 struct cinergyt2_fe_state {
 	struct dvb_frontend fe;
 	struct dvb_usb_device *d;
+
+	unsigned char data[64];
+	struct mutex data_mutex;
+
+	struct dvbt_get_status_msg status;
 };
 
 static int cinergyt2_fe_read_status(struct dvb_frontend *fe,
 				    enum fe_status *status)
 {
 	struct cinergyt2_fe_state *state = fe->demodulator_priv;
-	struct dvbt_get_status_msg result;
-	u8 cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
 	int ret;
 
-	ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (u8 *)&result,
-			sizeof(result), 0);
+	mutex_lock(&state->data_mutex);
+	state->data[0] = CINERGYT2_EP1_GET_TUNER_STATUS;
+
+	ret = dvb_usb_generic_rw(state->d, state->data, 1,
+				 state->data, sizeof(state->status), 0);
+	if (!ret)
+		memcpy(&state->status, state->data, sizeof(state->status));
+	mutex_unlock(&state->data_mutex);
+
 	if (ret < 0)
 		return ret;
 
 	*status = 0;
 
-	if (0xffff - le16_to_cpu(result.gain) > 30)
+	if (0xffff - le16_to_cpu(state->status.gain) > 30)
 		*status |= FE_HAS_SIGNAL;
-	if (result.lock_bits & (1 << 6))
+	if (state->status.lock_bits & (1 << 6))
 		*status |= FE_HAS_LOCK;
-	if (result.lock_bits & (1 << 5))
+	if (state->status.lock_bits & (1 << 5))
 		*status |= FE_HAS_SYNC;
-	if (result.lock_bits & (1 << 4))
+	if (state->status.lock_bits & (1 << 4))
 		*status |= FE_HAS_CARRIER;
-	if (result.lock_bits & (1 << 1))
+	if (state->status.lock_bits & (1 << 1))
 		*status |= FE_HAS_VITERBI;
 
 	if ((*status & (FE_HAS_CARRIER | FE_HAS_VITERBI | FE_HAS_SYNC)) !=
@@ -177,34 +187,16 @@ static int cinergyt2_fe_read_status(struct dvb_frontend *fe,
 static int cinergyt2_fe_read_ber(struct dvb_frontend *fe, u32 *ber)
 {
 	struct cinergyt2_fe_state *state = fe->demodulator_priv;
-	struct dvbt_get_status_msg status;
-	char cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
-	int ret;
 
-	ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (char *)&status,
-				sizeof(status), 0);
-	if (ret < 0)
-		return ret;
-
-	*ber = le32_to_cpu(status.viterbi_error_rate);
+	*ber = le32_to_cpu(state->status.viterbi_error_rate);
 	return 0;
 }
 
 static int cinergyt2_fe_read_unc_blocks(struct dvb_frontend *fe, u32 *unc)
 {
 	struct cinergyt2_fe_state *state = fe->demodulator_priv;
-	struct dvbt_get_status_msg status;
-	u8 cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
-	int ret;
 
-	ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (u8 *)&status,
-				sizeof(status), 0);
-	if (ret < 0) {
-		err("cinergyt2_fe_read_unc_blocks() Failed! (Error=%d)\n",
-			ret);
-		return ret;
-	}
-	*unc = le32_to_cpu(status.uncorrected_block_count);
+	*unc = le32_to_cpu(state->status.uncorrected_block_count);
 	return 0;
 }
 
@@ -212,35 +204,16 @@ static int cinergyt2_fe_read_signal_strength(struct dvb_frontend *fe,
 						u16 *strength)
 {
 	struct cinergyt2_fe_state *state = fe->demodulator_priv;
-	struct dvbt_get_status_msg status;
-	char cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
-	int ret;
 
-	ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (char *)&status,
-				sizeof(status), 0);
-	if (ret < 0) {
-		err("cinergyt2_fe_read_signal_strength() Failed!"
-			" (Error=%d)\n", ret);
-		return ret;
-	}
-	*strength = (0xffff - le16_to_cpu(status.gain));
+	*strength = (0xffff - le16_to_cpu(state->status.gain));
 	return 0;
 }
 
 static int cinergyt2_fe_read_snr(struct dvb_frontend *fe, u16 *snr)
 {
 	struct cinergyt2_fe_state *state = fe->demodulator_priv;
-	struct dvbt_get_status_msg status;
-	char cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
-	int ret;
 
-	ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (char *)&status,
-				sizeof(status), 0);
-	if (ret < 0) {
-		err("cinergyt2_fe_read_snr() Failed! (Error=%d)\n", ret);
-		return ret;
-	}
-	*snr = (status.snr << 8) | status.snr;
+	*snr = (state->status.snr << 8) | state->status.snr;
 	return 0;
 }
 
@@ -266,34 +239,36 @@ static int cinergyt2_fe_set_frontend(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
 	struct cinergyt2_fe_state *state = fe->demodulator_priv;
-	struct dvbt_set_parameters_msg param;
-	char result[2];
+	struct dvbt_set_parameters_msg *param;
 	int err;
 
-	param.cmd = CINERGYT2_EP1_SET_TUNER_PARAMETERS;
-	param.tps = cpu_to_le16(compute_tps(fep));
-	param.freq = cpu_to_le32(fep->frequency / 1000);
-	param.flags = 0;
+	mutex_lock(&state->data_mutex);
+
+	param = (void *)state->data;
+	param->cmd = CINERGYT2_EP1_SET_TUNER_PARAMETERS;
+	param->tps = cpu_to_le16(compute_tps(fep));
+	param->freq = cpu_to_le32(fep->frequency / 1000);
+	param->flags = 0;
 
 	switch (fep->bandwidth_hz) {
 	default:
 	case 8000000:
-		param.bandwidth = 8;
+		param->bandwidth = 8;
 		break;
 	case 7000000:
-		param.bandwidth = 7;
+		param->bandwidth = 7;
 		break;
 	case 6000000:
-		param.bandwidth = 6;
+		param->bandwidth = 6;
 		break;
 	}
 
-	err = dvb_usb_generic_rw(state->d,
-			(char *)&param, sizeof(param),
-			result, sizeof(result), 0);
+	err = dvb_usb_generic_rw(state->d, state->data, sizeof(*param),
+				 state->data, 2, 0);
 	if (err < 0)
 		err("cinergyt2_fe_set_frontend() Failed! err=%d\n", err);
 
+	mutex_unlock(&state->data_mutex);
 	return (err < 0) ? err : 0;
 }
 
@@ -315,6 +290,7 @@ struct dvb_frontend *cinergyt2_fe_attach(struct dvb_usb_device *d)
 	s->d = d;
 	memcpy(&s->fe.ops, &cinergyt2_fe_ops, sizeof(struct dvb_frontend_ops));
 	s->fe.demodulator_priv = s;
+	mutex_init(&s->data_mutex);
 	return &s->fe;
 }
 
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index 907ac01..3977281 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -45,9 +45,6 @@
 #include "si2168.h"
 #include "si2157.h"
 
-/* Max transfer size done by I2C transfer functions */
-#define MAX_XFER_SIZE  80
-
 /* debug */
 static int dvb_usb_cxusb_debug;
 module_param_named(debug, dvb_usb_cxusb_debug, int, 0644);
@@ -61,23 +58,27 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 static int cxusb_ctrl_msg(struct dvb_usb_device *d,
 			  u8 cmd, u8 *wbuf, int wlen, u8 *rbuf, int rlen)
 {
-	int wo = (rbuf == NULL || rlen == 0); /* write-only */
-	u8 sndbuf[MAX_XFER_SIZE];
+	struct cxusb_state *st = d->priv;
+	int ret, wo;
 
-	if (1 + wlen > sizeof(sndbuf)) {
-		warn("i2c wr: len=%d is too big!\n",
-		     wlen);
+	if (1 + wlen > MAX_XFER_SIZE) {
+		warn("i2c wr: len=%d is too big!\n", wlen);
 		return -EOPNOTSUPP;
 	}
 
-	memset(sndbuf, 0, 1+wlen);
+	wo = (rbuf == NULL || rlen == 0); /* write-only */
 
-	sndbuf[0] = cmd;
-	memcpy(&sndbuf[1], wbuf, wlen);
+	mutex_lock(&st->data_mutex);
+	st->data[0] = cmd;
+	memcpy(&st->data[1], wbuf, wlen);
 	if (wo)
-		return dvb_usb_generic_write(d, sndbuf, 1+wlen);
+		ret = dvb_usb_generic_write(d, st->data, 1 + wlen);
 	else
-		return dvb_usb_generic_rw(d, sndbuf, 1+wlen, rbuf, rlen, 0);
+		ret = dvb_usb_generic_rw(d, st->data, 1 + wlen,
+					 rbuf, rlen, 0);
+
+	mutex_unlock(&st->data_mutex);
+	return ret;
 }
 
 /* GPIO */
@@ -1460,36 +1461,43 @@ static struct dvb_usb_device_properties cxusb_mygica_t230_properties;
 static int cxusb_probe(struct usb_interface *intf,
 		       const struct usb_device_id *id)
 {
+	struct dvb_usb_device *d;
+	struct cxusb_state *st;
+
 	if (0 == dvb_usb_device_init(intf, &cxusb_medion_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_bluebird_lgh064f_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_bluebird_dee1601_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_bluebird_lgz201_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_bluebird_dtt7579_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_bluebird_dualdig4_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_bluebird_nano2_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf,
 				&cxusb_bluebird_nano2_needsfirmware_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_aver_a868r_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf,
 				     &cxusb_bluebird_dualdig4_rev2_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_d680_dmb_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_mygica_d689_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &cxusb_mygica_t230_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
-	    0)
+				     THIS_MODULE, &d, adapter_nr) ||
+	    0) {
+		st = d->priv;
+		mutex_init(&st->data_mutex);
+
 		return 0;
+	}
 
 	return -EINVAL;
 }
diff --git a/drivers/media/usb/dvb-usb/cxusb.h b/drivers/media/usb/dvb-usb/cxusb.h
index 527ff79..9f3ee0e 100644
--- a/drivers/media/usb/dvb-usb/cxusb.h
+++ b/drivers/media/usb/dvb-usb/cxusb.h
@@ -28,10 +28,16 @@
 #define CMD_ANALOG        0x50
 #define CMD_DIGITAL       0x51
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  80
+
 struct cxusb_state {
 	u8 gpio_write_state[3];
 	struct i2c_client *i2c_client_demod;
 	struct i2c_client *i2c_client_tuner;
+
+	unsigned char data[MAX_XFER_SIZE];
+	struct mutex data_mutex;
 };
 
 #endif
diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c
index f319665..92d5408 100644
--- a/drivers/media/usb/dvb-usb/dib0700_core.c
+++ b/drivers/media/usb/dvb-usb/dib0700_core.c
@@ -213,7 +213,7 @@ static int dib0700_i2c_xfer_new(struct i2c_adapter *adap, struct i2c_msg *msg,
 						 usb_rcvctrlpipe(d->udev, 0),
 						 REQUEST_NEW_I2C_READ,
 						 USB_TYPE_VENDOR | USB_DIR_IN,
-						 value, index, msg[i].buf,
+						 value, index, st->buf,
 						 msg[i].len,
 						 USB_CTRL_GET_TIMEOUT);
 			if (result < 0) {
@@ -221,6 +221,14 @@ static int dib0700_i2c_xfer_new(struct i2c_adapter *adap, struct i2c_msg *msg,
 				break;
 			}
 
+			if (msg[i].len > sizeof(st->buf)) {
+				deb_info("buffer too small to fit %d bytes\n",
+					 msg[i].len);
+				return -EIO;
+			}
+
+			memcpy(msg[i].buf, st->buf, msg[i].len);
+
 			deb_data("<<< ");
 			debug_dump(msg[i].buf, msg[i].len, deb_data);
 
@@ -238,6 +246,13 @@ static int dib0700_i2c_xfer_new(struct i2c_adapter *adap, struct i2c_msg *msg,
 			/* I2C ctrl + FE bus; */
 			st->buf[3] = ((gen_mode << 6) & 0xC0) |
 				 ((bus_mode << 4) & 0x30);
+
+			if (msg[i].len > sizeof(st->buf) - 4) {
+				deb_info("i2c message to big: %d\n",
+					 msg[i].len);
+				return -EIO;
+			}
+
 			/* The Actual i2c payload */
 			memcpy(&st->buf[4], msg[i].buf, msg[i].len);
 
@@ -283,6 +298,11 @@ static int dib0700_i2c_xfer_legacy(struct i2c_adapter *adap,
 		/* fill in the address */
 		st->buf[1] = msg[i].addr << 1;
 		/* fill the buffer */
+		if (msg[i].len > sizeof(st->buf) - 2) {
+			deb_info("i2c xfer to big: %d\n",
+				msg[i].len);
+			return -EIO;
+		}
 		memcpy(&st->buf[2], msg[i].buf, msg[i].len);
 
 		/* write/read request */
@@ -292,13 +312,20 @@ static int dib0700_i2c_xfer_legacy(struct i2c_adapter *adap,
 
 			/* special thing in the current firmware: when length is zero the read-failed */
 			len = dib0700_ctrl_rd(d, st->buf, msg[i].len + 2,
-					msg[i+1].buf, msg[i+1].len);
+					      st->buf, msg[i + 1].len);
 			if (len <= 0) {
 				deb_info("I2C read failed on address 0x%02x\n",
 						msg[i].addr);
 				break;
 			}
 
+			if (msg[i + 1].len > sizeof(st->buf)) {
+				deb_info("i2c xfer buffer to small for %d\n",
+					msg[i].len);
+				return -EIO;
+			}
+			memcpy(msg[i + 1].buf, st->buf, msg[i + 1].len);
+
 			msg[i+1].len = len;
 
 			i++;
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index 0857b56..ef1b8ee 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -508,8 +508,6 @@ static int stk7700ph_tuner_attach(struct dvb_usb_adapter *adap)
 
 #define DEFAULT_RC_INTERVAL 50
 
-static u8 rc_request[] = { REQUEST_POLL_RC, 0 };
-
 /*
  * This function is used only when firmware is < 1.20 version. Newer
  * firmwares use bulk mode, with functions implemented at dib0700_core,
@@ -517,7 +515,6 @@ static u8 rc_request[] = { REQUEST_POLL_RC, 0 };
  */
 static int dib0700_rc_query_old_firmware(struct dvb_usb_device *d)
 {
-	u8 key[4];
 	enum rc_type protocol;
 	u32 scancode;
 	u8 toggle;
@@ -532,39 +529,43 @@ static int dib0700_rc_query_old_firmware(struct dvb_usb_device *d)
 		return 0;
 	}
 
-	i = dib0700_ctrl_rd(d, rc_request, 2, key, 4);
+	st->buf[0] = REQUEST_POLL_RC;
+	st->buf[1] = 0;
+
+	i = dib0700_ctrl_rd(d, st->buf, 2, st->buf, 4);
 	if (i <= 0) {
 		err("RC Query Failed");
-		return -1;
+		return -EIO;
 	}
 
 	/* losing half of KEY_0 events from Philipps rc5 remotes.. */
-	if (key[0] == 0 && key[1] == 0 && key[2] == 0 && key[3] == 0)
+	if (st->buf[0] == 0 && st->buf[1] == 0
+	    && st->buf[2] == 0 && st->buf[3] == 0)
 		return 0;
 
-	/* info("%d: %2X %2X %2X %2X",dvb_usb_dib0700_ir_proto,(int)key[3-2],(int)key[3-3],(int)key[3-1],(int)key[3]);  */
+	/* info("%d: %2X %2X %2X %2X",dvb_usb_dib0700_ir_proto,(int)st->buf[3 - 2],(int)st->buf[3 - 3],(int)st->buf[3 - 1],(int)st->buf[3]);  */
 
 	dib0700_rc_setup(d, NULL); /* reset ir sensor data to prevent false events */
 
 	switch (d->props.rc.core.protocol) {
 	case RC_BIT_NEC:
 		/* NEC protocol sends repeat code as 0 0 0 FF */
-		if ((key[3-2] == 0x00) && (key[3-3] == 0x00) &&
-		    (key[3] == 0xff)) {
+		if ((st->buf[3 - 2] == 0x00) && (st->buf[3 - 3] == 0x00) &&
+		    (st->buf[3] == 0xff)) {
 			rc_repeat(d->rc_dev);
 			return 0;
 		}
 
 		protocol = RC_TYPE_NEC;
-		scancode = RC_SCANCODE_NEC(key[3-2], key[3-3]);
+		scancode = RC_SCANCODE_NEC(st->buf[3 - 2], st->buf[3 - 3]);
 		toggle = 0;
 		break;
 
 	default:
 		/* RC-5 protocol changes toggle bit on new keypress */
 		protocol = RC_TYPE_RC5;
-		scancode = RC_SCANCODE_RC5(key[3-2], key[3-3]);
-		toggle = key[3-1];
+		scancode = RC_SCANCODE_RC5(st->buf[3 - 2], st->buf[3 - 3]);
+		toggle = st->buf[3 - 1];
 		break;
 	}
 
diff --git a/drivers/media/usb/dvb-usb/dibusb-common.c b/drivers/media/usb/dvb-usb/dibusb-common.c
index 18ed3bf..de3ee25 100644
--- a/drivers/media/usb/dvb-usb/dibusb-common.c
+++ b/drivers/media/usb/dvb-usb/dibusb-common.c
@@ -62,72 +62,117 @@ EXPORT_SYMBOL(dibusb_pid_filter_ctrl);
 
 int dibusb_power_ctrl(struct dvb_usb_device *d, int onoff)
 {
-	u8 b[3];
+	u8 *b;
 	int ret;
+
+	b = kmalloc(3, GFP_KERNEL);
+	if (!b)
+		return -ENOMEM;
+
 	b[0] = DIBUSB_REQ_SET_IOCTL;
 	b[1] = DIBUSB_IOCTL_CMD_POWER_MODE;
 	b[2] = onoff ? DIBUSB_IOCTL_POWER_WAKEUP : DIBUSB_IOCTL_POWER_SLEEP;
-	ret = dvb_usb_generic_write(d,b,3);
+
+	ret = dvb_usb_generic_write(d, b, 3);
+
+	kfree(b);
+
 	msleep(10);
+
 	return ret;
 }
 EXPORT_SYMBOL(dibusb_power_ctrl);
 
 int dibusb2_0_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
 {
-	u8 b[3] = { 0 };
 	int ret;
+	u8 *b;
+
+	b = kmalloc(3, GFP_KERNEL);
+	if (!b)
+		return -ENOMEM;
 
 	if ((ret = dibusb_streaming_ctrl(adap,onoff)) < 0)
-		return ret;
+		goto ret;
 
 	if (onoff) {
 		b[0] = DIBUSB_REQ_SET_STREAMING_MODE;
 		b[1] = 0x00;
-		if ((ret = dvb_usb_generic_write(adap->dev,b,2)) < 0)
-			return ret;
+		ret = dvb_usb_generic_write(adap->dev, b, 2);
+		if (ret  < 0)
+			goto ret;
 	}
 
 	b[0] = DIBUSB_REQ_SET_IOCTL;
 	b[1] = onoff ? DIBUSB_IOCTL_CMD_ENABLE_STREAM : DIBUSB_IOCTL_CMD_DISABLE_STREAM;
-	return dvb_usb_generic_write(adap->dev,b,3);
+	ret = dvb_usb_generic_write(adap->dev, b, 3);
+
+ret:
+	kfree(b);
+	return ret;
 }
 EXPORT_SYMBOL(dibusb2_0_streaming_ctrl);
 
 int dibusb2_0_power_ctrl(struct dvb_usb_device *d, int onoff)
 {
-	if (onoff) {
-		u8 b[3] = { DIBUSB_REQ_SET_IOCTL, DIBUSB_IOCTL_CMD_POWER_MODE, DIBUSB_IOCTL_POWER_WAKEUP };
-		return dvb_usb_generic_write(d,b,3);
-	} else
+	u8 *b;
+	int ret;
+
+	if (!onoff)
 		return 0;
+
+	b = kmalloc(3, GFP_KERNEL);
+	if (!b)
+		return -ENOMEM;
+
+	b[0] = DIBUSB_REQ_SET_IOCTL;
+	b[1] = DIBUSB_IOCTL_CMD_POWER_MODE;
+	b[2] = DIBUSB_IOCTL_POWER_WAKEUP;
+
+	ret = dvb_usb_generic_write(d, b, 3);
+
+	kfree(b);
+
+	return ret;
 }
 EXPORT_SYMBOL(dibusb2_0_power_ctrl);
 
 static int dibusb_i2c_msg(struct dvb_usb_device *d, u8 addr,
 			  u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen)
 {
-	u8 sndbuf[MAX_XFER_SIZE]; /* lead(1) devaddr,direction(1) addr(2) data(wlen) (len(2) (when reading)) */
-	/* write only ? */
-	int wo = (rbuf == NULL || rlen == 0),
-		len = 2 + wlen + (wo ? 0 : 2);
+	u8 *sndbuf;
+	int ret, wo, len;
 
-	if (4 + wlen > sizeof(sndbuf)) {
+	/* write only ? */
+	wo = (rbuf == NULL || rlen == 0);
+
+	len = 2 + wlen + (wo ? 0 : 2);
+
+	sndbuf = kmalloc(MAX_XFER_SIZE, GFP_KERNEL);
+	if (!sndbuf)
+		return -ENOMEM;
+
+	if (4 + wlen > MAX_XFER_SIZE) {
 		warn("i2c wr: len=%d is too big!\n", wlen);
-		return -EOPNOTSUPP;
+		ret = -EOPNOTSUPP;
+		goto ret;
 	}
 
 	sndbuf[0] = wo ? DIBUSB_REQ_I2C_WRITE : DIBUSB_REQ_I2C_READ;
 	sndbuf[1] = (addr << 1) | (wo ? 0 : 1);
 
-	memcpy(&sndbuf[2],wbuf,wlen);
+	memcpy(&sndbuf[2], wbuf, wlen);
 
 	if (!wo) {
-		sndbuf[wlen+2] = (rlen >> 8) & 0xff;
-		sndbuf[wlen+3] = rlen & 0xff;
+		sndbuf[wlen + 2] = (rlen >> 8) & 0xff;
+		sndbuf[wlen + 3] = rlen & 0xff;
 	}
 
-	return dvb_usb_generic_rw(d,sndbuf,len,rbuf,rlen,0);
+	ret = dvb_usb_generic_rw(d, sndbuf, len, rbuf, rlen, 0);
+
+ret:
+	kfree(sndbuf);
+	return ret;
 }
 
 /*
@@ -319,11 +364,27 @@ EXPORT_SYMBOL(rc_map_dibusb_table);
 
 int dibusb_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
 {
-	u8 key[5],cmd = DIBUSB_REQ_POLL_REMOTE;
-	dvb_usb_generic_rw(d,&cmd,1,key,5,0);
-	dvb_usb_nec_rc_key_to_event(d,key,event,state);
-	if (key[0] != 0)
-		deb_info("key: %*ph\n", 5, key);
-	return 0;
+	u8 *buf;
+	int ret;
+
+	buf = kmalloc(5, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	buf[0] = DIBUSB_REQ_POLL_REMOTE;
+
+	ret = dvb_usb_generic_rw(d, buf, 1, buf, 5, 0);
+	if (ret < 0)
+		goto ret;
+
+	dvb_usb_nec_rc_key_to_event(d, buf, event, state);
+
+	if (buf[0] != 0)
+		deb_info("key: %*ph\n", 5, buf);
+
+	kfree(buf);
+
+ret:
+	return ret;
 }
 EXPORT_SYMBOL(dibusb_rc_query);
diff --git a/drivers/media/usb/dvb-usb/dibusb.h b/drivers/media/usb/dvb-usb/dibusb.h
index 3f82163..697be2a 100644
--- a/drivers/media/usb/dvb-usb/dibusb.h
+++ b/drivers/media/usb/dvb-usb/dibusb.h
@@ -96,6 +96,9 @@
 #define DIBUSB_IOCTL_CMD_ENABLE_STREAM	0x01
 #define DIBUSB_IOCTL_CMD_DISABLE_STREAM	0x02
 
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE  64
+
 struct dibusb_state {
 	struct dib_fe_xfer_ops ops;
 	int mt2060_present;
diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c
index 6313433..4284f69 100644
--- a/drivers/media/usb/dvb-usb/digitv.c
+++ b/drivers/media/usb/dvb-usb/digitv.c
@@ -28,22 +28,26 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 static int digitv_ctrl_msg(struct dvb_usb_device *d,
 		u8 cmd, u8 vv, u8 *wbuf, int wlen, u8 *rbuf, int rlen)
 {
-	int wo = (rbuf == NULL || rlen == 0); /* write-only */
-	u8 sndbuf[7],rcvbuf[7];
-	memset(sndbuf,0,7); memset(rcvbuf,0,7);
+	struct digitv_state *st = d->priv;
+	int ret, wo;
 
-	sndbuf[0] = cmd;
-	sndbuf[1] = vv;
-	sndbuf[2] = wo ? wlen : rlen;
+	wo = (rbuf == NULL || rlen == 0); /* write-only */
+
+	memset(st->sndbuf, 0, 7);
+	memset(st->rcvbuf, 0, 7);
+
+	st->sndbuf[0] = cmd;
+	st->sndbuf[1] = vv;
+	st->sndbuf[2] = wo ? wlen : rlen;
 
 	if (wo) {
-		memcpy(&sndbuf[3],wbuf,wlen);
-		dvb_usb_generic_write(d,sndbuf,7);
+		memcpy(&st->sndbuf[3], wbuf, wlen);
+		ret = dvb_usb_generic_write(d, st->sndbuf, 7);
 	} else {
-		dvb_usb_generic_rw(d,sndbuf,7,rcvbuf,7,10);
-		memcpy(rbuf,&rcvbuf[3],rlen);
+		ret = dvb_usb_generic_rw(d, st->sndbuf, 7, st->rcvbuf, 7, 10);
+		memcpy(rbuf, &st->rcvbuf[3], rlen);
 	}
-	return 0;
+	return ret;
 }
 
 /* I2C */
diff --git a/drivers/media/usb/dvb-usb/digitv.h b/drivers/media/usb/dvb-usb/digitv.h
index 908c09f..581e09c 100644
--- a/drivers/media/usb/dvb-usb/digitv.h
+++ b/drivers/media/usb/dvb-usb/digitv.h
@@ -5,7 +5,10 @@
 #include "dvb-usb.h"
 
 struct digitv_state {
-    int is_nxt6000;
+	int is_nxt6000;
+
+	unsigned char sndbuf[7];
+	unsigned char rcvbuf[7];
 };
 
 /* protocol (from usblogging and the SDK:
diff --git a/drivers/media/usb/dvb-usb/dtt200u-fe.c b/drivers/media/usb/dvb-usb/dtt200u-fe.c
index c09332b..f5c042b 100644
--- a/drivers/media/usb/dvb-usb/dtt200u-fe.c
+++ b/drivers/media/usb/dvb-usb/dtt200u-fe.c
@@ -18,17 +18,28 @@ struct dtt200u_fe_state {
 
 	struct dtv_frontend_properties fep;
 	struct dvb_frontend frontend;
+
+	unsigned char data[80];
+	struct mutex data_mutex;
 };
 
 static int dtt200u_fe_read_status(struct dvb_frontend *fe,
 				  enum fe_status *stat)
 {
 	struct dtt200u_fe_state *state = fe->demodulator_priv;
-	u8 st = GET_TUNE_STATUS, b[3];
+	int ret;
 
-	dvb_usb_generic_rw(state->d,&st,1,b,3,0);
+	mutex_lock(&state->data_mutex);
+	state->data[0] = GET_TUNE_STATUS;
 
-	switch (b[0]) {
+	ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 3, 0);
+	if (ret < 0) {
+		*stat = 0;
+		mutex_unlock(&state->data_mutex);
+		return ret;
+	}
+
+	switch (state->data[0]) {
 		case 0x01:
 			*stat = FE_HAS_SIGNAL | FE_HAS_CARRIER |
 				FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
@@ -41,51 +52,86 @@ static int dtt200u_fe_read_status(struct dvb_frontend *fe,
 			*stat = 0;
 			break;
 	}
+	mutex_unlock(&state->data_mutex);
 	return 0;
 }
 
 static int dtt200u_fe_read_ber(struct dvb_frontend* fe, u32 *ber)
 {
 	struct dtt200u_fe_state *state = fe->demodulator_priv;
-	u8 bw = GET_VIT_ERR_CNT,b[3];
-	dvb_usb_generic_rw(state->d,&bw,1,b,3,0);
-	*ber = (b[0] << 16) | (b[1] << 8) | b[2];
-	return 0;
+	int ret;
+
+	mutex_lock(&state->data_mutex);
+	state->data[0] = GET_VIT_ERR_CNT;
+
+	ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 3, 0);
+	if (ret >= 0)
+		*ber = (state->data[0] << 16) | (state->data[1] << 8) | state->data[2];
+
+	mutex_unlock(&state->data_mutex);
+	return ret;
 }
 
 static int dtt200u_fe_read_unc_blocks(struct dvb_frontend* fe, u32 *unc)
 {
 	struct dtt200u_fe_state *state = fe->demodulator_priv;
-	u8 bw = GET_RS_UNCOR_BLK_CNT,b[2];
+	int ret;
 
-	dvb_usb_generic_rw(state->d,&bw,1,b,2,0);
-	*unc = (b[0] << 8) | b[1];
-	return 0;
+	mutex_lock(&state->data_mutex);
+	state->data[0] = GET_RS_UNCOR_BLK_CNT;
+
+	ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 2, 0);
+	if (ret >= 0)
+		*unc = (state->data[0] << 8) | state->data[1];
+
+	mutex_unlock(&state->data_mutex);
+	return ret;
 }
 
 static int dtt200u_fe_read_signal_strength(struct dvb_frontend* fe, u16 *strength)
 {
 	struct dtt200u_fe_state *state = fe->demodulator_priv;
-	u8 bw = GET_AGC, b;
-	dvb_usb_generic_rw(state->d,&bw,1,&b,1,0);
-	*strength = (b << 8) | b;
-	return 0;
+	int ret;
+
+	mutex_lock(&state->data_mutex);
+	state->data[0] = GET_AGC;
+
+	ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 1, 0);
+	if (ret >= 0)
+		*strength = (state->data[0] << 8) | state->data[0];
+
+	mutex_unlock(&state->data_mutex);
+	return ret;
 }
 
 static int dtt200u_fe_read_snr(struct dvb_frontend* fe, u16 *snr)
 {
 	struct dtt200u_fe_state *state = fe->demodulator_priv;
-	u8 bw = GET_SNR,br;
-	dvb_usb_generic_rw(state->d,&bw,1,&br,1,0);
-	*snr = ~((br << 8) | br);
-	return 0;
+	int ret;
+
+	mutex_lock(&state->data_mutex);
+	state->data[0] = GET_SNR;
+
+	ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 1, 0);
+	if (ret >= 0)
+		*snr = ~((state->data[0] << 8) | state->data[0]);
+
+	mutex_unlock(&state->data_mutex);
+	return ret;
 }
 
 static int dtt200u_fe_init(struct dvb_frontend* fe)
 {
 	struct dtt200u_fe_state *state = fe->demodulator_priv;
-	u8 b = SET_INIT;
-	return dvb_usb_generic_write(state->d,&b,1);
+	int ret;
+
+	mutex_lock(&state->data_mutex);
+	state->data[0] = SET_INIT;
+
+	ret = dvb_usb_generic_write(state->d, state->data, 1);
+	mutex_unlock(&state->data_mutex);
+
+	return ret;
 }
 
 static int dtt200u_fe_sleep(struct dvb_frontend* fe)
@@ -105,39 +151,40 @@ static int dtt200u_fe_set_frontend(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
 	struct dtt200u_fe_state *state = fe->demodulator_priv;
-	int i;
-	enum fe_status st;
+	int ret;
 	u16 freq = fep->frequency / 250000;
-	u8 bwbuf[2] = { SET_BANDWIDTH, 0 },freqbuf[3] = { SET_RF_FREQ, 0, 0 };
 
+	mutex_lock(&state->data_mutex);
+	state->data[0] = SET_BANDWIDTH;
 	switch (fep->bandwidth_hz) {
 	case 8000000:
-		bwbuf[1] = 8;
+		state->data[1] = 8;
 		break;
 	case 7000000:
-		bwbuf[1] = 7;
+		state->data[1] = 7;
 		break;
 	case 6000000:
-		bwbuf[1] = 6;
+		state->data[1] = 6;
 		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
+		goto ret;
 	}
 
-	dvb_usb_generic_write(state->d,bwbuf,2);
+	ret = dvb_usb_generic_write(state->d, state->data, 2);
+	if (ret < 0)
+		goto ret;
 
-	freqbuf[1] = freq & 0xff;
-	freqbuf[2] = (freq >> 8) & 0xff;
-	dvb_usb_generic_write(state->d,freqbuf,3);
+	state->data[0] = SET_RF_FREQ;
+	state->data[1] = freq & 0xff;
+	state->data[2] = (freq >> 8) & 0xff;
+	ret = dvb_usb_generic_write(state->d, state->data, 3);
+	if (ret < 0)
+		goto ret;
 
-	for (i = 0; i < 30; i++) {
-		msleep(20);
-		dtt200u_fe_read_status(fe, &st);
-		if (st & FE_TIMEDOUT)
-			continue;
-	}
-
-	return 0;
+ret:
+	mutex_unlock(&state->data_mutex);
+	return ret;
 }
 
 static int dtt200u_fe_get_frontend(struct dvb_frontend* fe,
@@ -169,6 +216,7 @@ struct dvb_frontend* dtt200u_fe_attach(struct dvb_usb_device *d)
 	deb_info("attaching frontend dtt200u\n");
 
 	state->d = d;
+	mutex_init(&state->data_mutex);
 
 	memcpy(&state->frontend.ops,&dtt200u_fe_ops,sizeof(struct dvb_frontend_ops));
 	state->frontend.demodulator_priv = state;
diff --git a/drivers/media/usb/dvb-usb/dtt200u.c b/drivers/media/usb/dvb-usb/dtt200u.c
index d2a01b5..f88572c 100644
--- a/drivers/media/usb/dvb-usb/dtt200u.c
+++ b/drivers/media/usb/dvb-usb/dtt200u.c
@@ -20,75 +20,114 @@ MODULE_PARM_DESC(debug, "set debugging level (1=info,xfer=2 (or-able))." DVB_USB
 
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
+struct dtt200u_state {
+	unsigned char data[80];
+	struct mutex data_mutex;
+};
+
 static int dtt200u_power_ctrl(struct dvb_usb_device *d, int onoff)
 {
-	u8 b = SET_INIT;
+	struct dtt200u_state *st = d->priv;
+	int ret = 0;
+
+	mutex_lock(&st->data_mutex);
+
+	st->data[0] = SET_INIT;
 
 	if (onoff)
-		dvb_usb_generic_write(d,&b,2);
+		ret = dvb_usb_generic_write(d, st->data, 2);
 
-	return 0;
+	mutex_unlock(&st->data_mutex);
+	return ret;
 }
 
 static int dtt200u_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
 {
-	u8 b_streaming[2] = { SET_STREAMING, onoff };
-	u8 b_rst_pid = RESET_PID_FILTER;
+	struct dtt200u_state *st = adap->dev->priv;
+	int ret;
 
-	dvb_usb_generic_write(adap->dev, b_streaming, 2);
+	mutex_lock(&st->data_mutex);
+	st->data[0] = SET_STREAMING;
+	st->data[1] = onoff;
 
-	if (onoff == 0)
-		dvb_usb_generic_write(adap->dev, &b_rst_pid, 1);
-	return 0;
+	ret = dvb_usb_generic_write(adap->dev, st->data, 2);
+	if (ret < 0)
+		goto ret;
+
+	if (onoff)
+		goto ret;
+
+	st->data[0] = RESET_PID_FILTER;
+	ret = dvb_usb_generic_write(adap->dev, st->data, 1);
+
+ret:
+	mutex_unlock(&st->data_mutex);
+
+	return ret;
 }
 
 static int dtt200u_pid_filter(struct dvb_usb_adapter *adap, int index, u16 pid, int onoff)
 {
-	u8 b_pid[4];
+	struct dtt200u_state *st = adap->dev->priv;
+	int ret;
+
 	pid = onoff ? pid : 0;
 
-	b_pid[0] = SET_PID_FILTER;
-	b_pid[1] = index;
-	b_pid[2] = pid & 0xff;
-	b_pid[3] = (pid >> 8) & 0x1f;
+	mutex_lock(&st->data_mutex);
+	st->data[0] = SET_PID_FILTER;
+	st->data[1] = index;
+	st->data[2] = pid & 0xff;
+	st->data[3] = (pid >> 8) & 0x1f;
 
-	return dvb_usb_generic_write(adap->dev, b_pid, 4);
+	ret = dvb_usb_generic_write(adap->dev, st->data, 4);
+	mutex_unlock(&st->data_mutex);
+
+	return ret;
 }
 
 static int dtt200u_rc_query(struct dvb_usb_device *d)
 {
-	u8 key[5],cmd = GET_RC_CODE;
+	struct dtt200u_state *st = d->priv;
 	u32 scancode;
+	int ret;
 
-	dvb_usb_generic_rw(d,&cmd,1,key,5,0);
-	if (key[0] == 1) {
+	mutex_lock(&st->data_mutex);
+	st->data[0] = GET_RC_CODE;
+
+	ret = dvb_usb_generic_rw(d, st->data, 1, st->data, 5, 0);
+	if (ret < 0)
+		goto ret;
+
+	if (st->data[0] == 1) {
 		enum rc_type proto = RC_TYPE_NEC;
 
-		scancode = key[1];
-		if ((u8) ~key[1] != key[2]) {
+		scancode = st->data[1];
+		if ((u8) ~st->data[1] != st->data[2]) {
 			/* Extended NEC */
 			scancode = scancode << 8;
-			scancode |= key[2];
+			scancode |= st->data[2];
 			proto = RC_TYPE_NECX;
 		}
 		scancode = scancode << 8;
-		scancode |= key[3];
+		scancode |= st->data[3];
 
 		/* Check command checksum is ok */
-		if ((u8) ~key[3] == key[4])
+		if ((u8) ~st->data[3] == st->data[4])
 			rc_keydown(d->rc_dev, proto, scancode, 0);
 		else
 			rc_keyup(d->rc_dev);
-	} else if (key[0] == 2) {
+	} else if (st->data[0] == 2) {
 		rc_repeat(d->rc_dev);
 	} else {
 		rc_keyup(d->rc_dev);
 	}
 
-	if (key[0] != 0)
-		deb_info("key: %*ph\n", 5, key);
+	if (st->data[0] != 0)
+		deb_info("st->data: %*ph\n", 5, st->data);
 
-	return 0;
+ret:
+	mutex_unlock(&st->data_mutex);
+	return ret;
 }
 
 static int dtt200u_frontend_attach(struct dvb_usb_adapter *adap)
@@ -106,17 +145,24 @@ static struct dvb_usb_device_properties wt220u_miglia_properties;
 static int dtt200u_usb_probe(struct usb_interface *intf,
 		const struct usb_device_id *id)
 {
+	struct dvb_usb_device *d;
+	struct dtt200u_state *st;
+
 	if (0 == dvb_usb_device_init(intf, &dtt200u_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &wt220u_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &wt220u_fc_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &wt220u_zl0353_properties,
-				     THIS_MODULE, NULL, adapter_nr) ||
+				     THIS_MODULE, &d, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &wt220u_miglia_properties,
-				     THIS_MODULE, NULL, adapter_nr))
+				     THIS_MODULE, &d, adapter_nr)) {
+		st = d->priv;
+		mutex_init(&st->data_mutex);
+
 		return 0;
+	}
 
 	return -ENODEV;
 }
@@ -140,6 +186,8 @@ static struct dvb_usb_device_properties dtt200u_properties = {
 	.usb_ctrl = CYPRESS_FX2,
 	.firmware = "dvb-usb-dtt200u-01.fw",
 
+	.size_of_priv     = sizeof(struct dtt200u_state),
+
 	.num_adapters = 1,
 	.adapter = {
 		{
@@ -190,6 +238,8 @@ static struct dvb_usb_device_properties wt220u_properties = {
 	.usb_ctrl = CYPRESS_FX2,
 	.firmware = "dvb-usb-wt220u-02.fw",
 
+	.size_of_priv     = sizeof(struct dtt200u_state),
+
 	.num_adapters = 1,
 	.adapter = {
 		{
@@ -240,6 +290,8 @@ static struct dvb_usb_device_properties wt220u_fc_properties = {
 	.usb_ctrl = CYPRESS_FX2,
 	.firmware = "dvb-usb-wt220u-fc03.fw",
 
+	.size_of_priv     = sizeof(struct dtt200u_state),
+
 	.num_adapters = 1,
 	.adapter = {
 		{
@@ -290,6 +342,8 @@ static struct dvb_usb_device_properties wt220u_zl0353_properties = {
 	.usb_ctrl = CYPRESS_FX2,
 	.firmware = "dvb-usb-wt220u-zl0353-01.fw",
 
+	.size_of_priv     = sizeof(struct dtt200u_state),
+
 	.num_adapters = 1,
 	.adapter = {
 		{
@@ -340,6 +394,8 @@ static struct dvb_usb_device_properties wt220u_miglia_properties = {
 	.usb_ctrl = CYPRESS_FX2,
 	.firmware = "dvb-usb-wt220u-miglia-01.fw",
 
+	.size_of_priv     = sizeof(struct dtt200u_state),
+
 	.num_adapters = 1,
 	.generic_bulk_ctrl_endpoint = 0x01,
 
diff --git a/drivers/media/usb/dvb-usb/dtv5100.c b/drivers/media/usb/dvb-usb/dtv5100.c
index 3d11df4..c60fb54 100644
--- a/drivers/media/usb/dvb-usb/dtv5100.c
+++ b/drivers/media/usb/dvb-usb/dtv5100.c
@@ -31,9 +31,14 @@ module_param_named(debug, dvb_usb_dtv5100_debug, int, 0644);
 MODULE_PARM_DESC(debug, "set debugging level" DVB_USB_DEBUG_STATUS);
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
+struct dtv5100_state {
+	unsigned char data[80];
+};
+
 static int dtv5100_i2c_msg(struct dvb_usb_device *d, u8 addr,
 			   u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen)
 {
+	struct dtv5100_state *st = d->priv;
 	u8 request;
 	u8 type;
 	u16 value;
@@ -60,9 +65,10 @@ static int dtv5100_i2c_msg(struct dvb_usb_device *d, u8 addr,
 	}
 	index = (addr << 8) + wbuf[0];
 
+	memcpy(st->data, rbuf, rlen);
 	msleep(1); /* avoid I2C errors */
 	return usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0), request,
-			       type, value, index, rbuf, rlen,
+			       type, value, index, st->data, rlen,
 			       DTV5100_USB_TIMEOUT);
 }
 
@@ -176,7 +182,7 @@ static struct dvb_usb_device_properties dtv5100_properties = {
 	.caps = DVB_USB_IS_AN_I2C_ADAPTER,
 	.usb_ctrl = DEVICE_SPECIFIC,
 
-	.size_of_priv = 0,
+	.size_of_priv = sizeof(struct dtv5100_state),
 
 	.num_adapters = 1,
 	.adapter = {{
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 5fb0c65..2c720cb 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -852,7 +852,7 @@ static int su3000_power_ctrl(struct dvb_usb_device *d, int i)
 	if (i && !state->initialized) {
 		state->initialized = 1;
 		/* reset board */
-		dvb_usb_generic_rw(d, obuf, 2, NULL, 0, 0);
+		return dvb_usb_generic_rw(d, obuf, 2, NULL, 0, 0);
 	}
 
 	return 0;
diff --git a/drivers/media/usb/dvb-usb/gp8psk.c b/drivers/media/usb/dvb-usb/gp8psk.c
index 5d0384d..adfd764 100644
--- a/drivers/media/usb/dvb-usb/gp8psk.c
+++ b/drivers/media/usb/dvb-usb/gp8psk.c
@@ -24,6 +24,10 @@ MODULE_PARM_DESC(debug, "set debugging level (1=info,xfer=2,rc=4 (or-able))." DV
 
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
+struct gp8psk_state {
+	unsigned char data[80];
+};
+
 static int gp8psk_get_fw_version(struct dvb_usb_device *d, u8 *fw_vers)
 {
 	return (gp8psk_usb_in_op(d, GET_FW_VERS, 0, 0, fw_vers, 6));
@@ -53,17 +57,22 @@ static void gp8psk_info(struct dvb_usb_device *d)
 
 int gp8psk_usb_in_op(struct dvb_usb_device *d, u8 req, u16 value, u16 index, u8 *b, int blen)
 {
+	struct gp8psk_state *st = d->priv;
 	int ret = 0,try = 0;
 
+	if (blen > sizeof(st->data))
+		return -EIO;
+
 	if ((ret = mutex_lock_interruptible(&d->usb_mutex)))
 		return ret;
 
 	while (ret >= 0 && ret != blen && try < 3) {
+		memcpy(st->data, b, blen);
 		ret = usb_control_msg(d->udev,
 			usb_rcvctrlpipe(d->udev,0),
 			req,
 			USB_TYPE_VENDOR | USB_DIR_IN,
-			value,index,b,blen,
+			value, index, st->data, blen,
 			2000);
 		deb_info("reading number %d (ret: %d)\n",try,ret);
 		try++;
@@ -86,19 +95,24 @@ int gp8psk_usb_in_op(struct dvb_usb_device *d, u8 req, u16 value, u16 index, u8
 int gp8psk_usb_out_op(struct dvb_usb_device *d, u8 req, u16 value,
 			     u16 index, u8 *b, int blen)
 {
+	struct gp8psk_state *st = d->priv;
 	int ret;
 
 	deb_xfer("out: req. %x, val: %x, ind: %x, buffer: ",req,value,index);
 	debug_dump(b,blen,deb_xfer);
 
+	if (blen > sizeof(st->data))
+		return -EIO;
+
 	if ((ret = mutex_lock_interruptible(&d->usb_mutex)))
 		return ret;
 
+	memcpy(st->data, b, blen);
 	if (usb_control_msg(d->udev,
 			usb_sndctrlpipe(d->udev,0),
 			req,
 			USB_TYPE_VENDOR | USB_DIR_OUT,
-			value,index,b,blen,
+			value, index, st->data, blen,
 			2000) != blen) {
 		warn("usb out operation failed.");
 		ret = -EIO;
@@ -143,6 +157,11 @@ static int gp8psk_load_bcm4500fw(struct dvb_usb_device *d)
 			err("failed to load bcm4500 firmware.");
 			goto out_free;
 		}
+		if (buflen > 64) {
+			err("firmare chunk size bigger than 64 bytes.");
+			goto out_free;
+		}
+
 		memcpy(buf, ptr, buflen);
 		if (dvb_usb_generic_write(d, buf, buflen)) {
 			err("failed to load bcm4500 firmware.");
@@ -265,6 +284,8 @@ static struct dvb_usb_device_properties gp8psk_properties = {
 	.usb_ctrl = CYPRESS_FX2,
 	.firmware = "dvb-usb-gp8psk-01.fw",
 
+	.size_of_priv = sizeof(struct gp8psk_state),
+
 	.num_adapters = 1,
 	.adapter = {
 		{
diff --git a/drivers/media/usb/dvb-usb/nova-t-usb2.c b/drivers/media/usb/dvb-usb/nova-t-usb2.c
index fc7569e..1babd33 100644
--- a/drivers/media/usb/dvb-usb/nova-t-usb2.c
+++ b/drivers/media/usb/dvb-usb/nova-t-usb2.c
@@ -74,22 +74,31 @@ static struct rc_map_table rc_map_haupp_table[] = {
  */
 static int nova_t_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
 {
-	u8 key[5],cmd[2] = { DIBUSB_REQ_POLL_REMOTE, 0x35 }, data,toggle,custom;
+	u8 *buf, data, toggle, custom;
 	u16 raw;
-	int i;
+	int i, ret;
 	struct dibusb_device_state *st = d->priv;
 
-	dvb_usb_generic_rw(d,cmd,2,key,5,0);
+	buf = kmalloc(5, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	buf[0] = DIBUSB_REQ_POLL_REMOTE;
+	buf[1] = 0x35;
+	ret = dvb_usb_generic_rw(d, buf, 2, buf, 5, 0);
+	if (ret < 0)
+		goto ret;
 
 	*state = REMOTE_NO_KEY_PRESSED;
-	switch (key[0]) {
+	switch (buf[0]) {
 		case DIBUSB_RC_HAUPPAUGE_KEY_PRESSED:
-			raw = ((key[1] << 8) | key[2]) >> 3;
+			raw = ((buf[1] << 8) | buf[2]) >> 3;
 			toggle = !!(raw & 0x800);
 			data = raw & 0x3f;
 			custom = (raw >> 6) & 0x1f;
 
-			deb_rc("raw key code 0x%02x, 0x%02x, 0x%02x to c: %02x d: %02x toggle: %d\n",key[1],key[2],key[3],custom,data,toggle);
+			deb_rc("raw key code 0x%02x, 0x%02x, 0x%02x to c: %02x d: %02x toggle: %d\n",
+			       buf[1], buf[2], buf[3], custom, data, toggle);
 
 			for (i = 0; i < ARRAY_SIZE(rc_map_haupp_table); i++) {
 				if (rc5_data(&rc_map_haupp_table[i]) == data &&
@@ -117,7 +126,9 @@ static int nova_t_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
 			break;
 	}
 
-	return 0;
+ret:
+	kfree(buf);
+	return ret;
 }
 
 static int nova_t_read_mac_address (struct dvb_usb_device *d, u8 mac[6])
diff --git a/drivers/media/usb/dvb-usb/pctv452e.c b/drivers/media/usb/dvb-usb/pctv452e.c
index c05de1b..07fa08b 100644
--- a/drivers/media/usb/dvb-usb/pctv452e.c
+++ b/drivers/media/usb/dvb-usb/pctv452e.c
@@ -97,48 +97,53 @@ struct pctv452e_state {
 	u8 c;	   /* transaction counter, wraps around...  */
 	u8 initialized; /* set to 1 if 0x15 has been sent */
 	u16 last_rc_key;
+
+	unsigned char data[80];
 };
 
 static int tt3650_ci_msg(struct dvb_usb_device *d, u8 cmd, u8 *data,
 			 unsigned int write_len, unsigned int read_len)
 {
 	struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
-	u8 buf[64];
 	u8 id;
 	unsigned int rlen;
 	int ret;
 
-	BUG_ON(NULL == data && 0 != (write_len | read_len));
-	BUG_ON(write_len > 64 - 4);
-	BUG_ON(read_len > 64 - 4);
+	if (!data || (write_len > 64 - 4) || (read_len > 64 - 4)) {
+		err("%s: transfer data invalid", __func__);
+		return -EIO;
+	}
 
+	mutex_lock(&state->ca_mutex);
 	id = state->c++;
 
-	buf[0] = SYNC_BYTE_OUT;
-	buf[1] = id;
-	buf[2] = cmd;
-	buf[3] = write_len;
+	state->data[0] = SYNC_BYTE_OUT;
+	state->data[1] = id;
+	state->data[2] = cmd;
+	state->data[3] = write_len;
 
-	memcpy(buf + 4, data, write_len);
+	memcpy(state->data + 4, data, write_len);
 
 	rlen = (read_len > 0) ? 64 : 0;
-	ret = dvb_usb_generic_rw(d, buf, 4 + write_len,
-				  buf, rlen, /* delay_ms */ 0);
+	ret = dvb_usb_generic_rw(d, state->data, 4 + write_len,
+				  state->data, rlen, /* delay_ms */ 0);
 	if (0 != ret)
 		goto failed;
 
 	ret = -EIO;
-	if (SYNC_BYTE_IN != buf[0] || id != buf[1])
+	if (SYNC_BYTE_IN != state->data[0] || id != state->data[1])
 		goto failed;
 
-	memcpy(data, buf + 4, read_len);
+	memcpy(data, state->data + 4, read_len);
 
+	mutex_unlock(&state->ca_mutex);
 	return 0;
 
 failed:
 	err("CI error %d; %02X %02X %02X -> %*ph.",
-	     ret, SYNC_BYTE_OUT, id, cmd, 3, buf);
+	     ret, SYNC_BYTE_OUT, id, cmd, 3, state->data);
 
+	mutex_unlock(&state->ca_mutex);
 	return ret;
 }
 
@@ -405,52 +410,53 @@ static int pctv452e_i2c_msg(struct dvb_usb_device *d, u8 addr,
 				u8 *rcv_buf, u8 rcv_len)
 {
 	struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
-	u8 buf[64];
 	u8 id;
 	int ret;
 
+	mutex_lock(&state->ca_mutex);
 	id = state->c++;
 
 	ret = -EINVAL;
 	if (snd_len > 64 - 7 || rcv_len > 64 - 7)
 		goto failed;
 
-	buf[0] = SYNC_BYTE_OUT;
-	buf[1] = id;
-	buf[2] = PCTV_CMD_I2C;
-	buf[3] = snd_len + 3;
-	buf[4] = addr << 1;
-	buf[5] = snd_len;
-	buf[6] = rcv_len;
+	state->data[0] = SYNC_BYTE_OUT;
+	state->data[1] = id;
+	state->data[2] = PCTV_CMD_I2C;
+	state->data[3] = snd_len + 3;
+	state->data[4] = addr << 1;
+	state->data[5] = snd_len;
+	state->data[6] = rcv_len;
 
-	memcpy(buf + 7, snd_buf, snd_len);
+	memcpy(state->data + 7, snd_buf, snd_len);
 
-	ret = dvb_usb_generic_rw(d, buf, 7 + snd_len,
-				  buf, /* rcv_len */ 64,
+	ret = dvb_usb_generic_rw(d, state->data, 7 + snd_len,
+				  state->data, /* rcv_len */ 64,
 				  /* delay_ms */ 0);
 	if (ret < 0)
 		goto failed;
 
 	/* TT USB protocol error. */
 	ret = -EIO;
-	if (SYNC_BYTE_IN != buf[0] || id != buf[1])
+	if (SYNC_BYTE_IN != state->data[0] || id != state->data[1])
 		goto failed;
 
 	/* I2C device didn't respond as expected. */
 	ret = -EREMOTEIO;
-	if (buf[5] < snd_len || buf[6] < rcv_len)
+	if (state->data[5] < snd_len || state->data[6] < rcv_len)
 		goto failed;
 
-	memcpy(rcv_buf, buf + 7, rcv_len);
+	memcpy(rcv_buf, state->data + 7, rcv_len);
+	mutex_unlock(&state->ca_mutex);
 
 	return rcv_len;
 
 failed:
-	err("I2C error %d; %02X %02X  %02X %02X %02X -> "
-	     "%02X %02X  %02X %02X %02X.",
+	err("I2C error %d; %02X %02X  %02X %02X %02X -> %*ph",
 	     ret, SYNC_BYTE_OUT, id, addr << 1, snd_len, rcv_len,
-	     buf[0], buf[1], buf[4], buf[5], buf[6]);
+	     7, state->data);
 
+	mutex_unlock(&state->ca_mutex);
 	return ret;
 }
 
@@ -499,8 +505,7 @@ static u32 pctv452e_i2c_func(struct i2c_adapter *adapter)
 static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
 {
 	struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
-	u8 b0[] = { 0xaa, 0, PCTV_CMD_RESET, 1, 0 };
-	u8 rx[PCTV_ANSWER_LEN];
+	u8 *rx;
 	int ret;
 
 	info("%s: %d\n", __func__, i);
@@ -511,6 +516,11 @@ static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
 	if (state->initialized)
 		return 0;
 
+	rx = kmalloc(PCTV_ANSWER_LEN, GFP_KERNEL);
+	if (!rx)
+		return -ENOMEM;
+
+	mutex_lock(&state->ca_mutex);
 	/* hmm where shoud this should go? */
 	ret = usb_set_interface(d->udev, 0, ISOC_INTERFACE_ALTERNATIVE);
 	if (ret != 0)
@@ -518,65 +528,75 @@ static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
 			__func__, ret);
 
 	/* this is a one-time initialization, dont know where to put */
-	b0[1] = state->c++;
+	state->data[0] = 0xaa;
+	state->data[1] = state->c++;
+	state->data[2] = PCTV_CMD_RESET;
+	state->data[3] = 1;
+	state->data[4] = 0;
 	/* reset board */
-	ret = dvb_usb_generic_rw(d, b0, sizeof(b0), rx, PCTV_ANSWER_LEN, 0);
+	ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0);
 	if (ret)
-		return ret;
+		goto ret;
 
-	b0[1] = state->c++;
-	b0[4] = 1;
+	state->data[1] = state->c++;
+	state->data[4] = 1;
 	/* reset board (again?) */
-	ret = dvb_usb_generic_rw(d, b0, sizeof(b0), rx, PCTV_ANSWER_LEN, 0);
+	ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0);
 	if (ret)
-		return ret;
+		goto ret;
 
 	state->initialized = 1;
 
-	return 0;
+ret:
+	mutex_unlock(&state->ca_mutex);
+	kfree(rx);
+	return ret;
 }
 
 static int pctv452e_rc_query(struct dvb_usb_device *d)
 {
 	struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
-	u8 b[CMD_BUFFER_SIZE];
-	u8 rx[PCTV_ANSWER_LEN];
 	int ret, i;
-	u8 id = state->c++;
+	u8 id;
+
+	mutex_lock(&state->ca_mutex);
+	id = state->c++;
 
 	/* prepare command header  */
-	b[0] = SYNC_BYTE_OUT;
-	b[1] = id;
-	b[2] = PCTV_CMD_IR;
-	b[3] = 0;
+	state->data[0] = SYNC_BYTE_OUT;
+	state->data[1] = id;
+	state->data[2] = PCTV_CMD_IR;
+	state->data[3] = 0;
 
 	/* send ir request */
-	ret = dvb_usb_generic_rw(d, b, 4, rx, PCTV_ANSWER_LEN, 0);
+	ret = dvb_usb_generic_rw(d, state->data, 4,
+				 state->data, PCTV_ANSWER_LEN, 0);
 	if (ret != 0)
-		return ret;
+		goto ret;
 
 	if (debug > 3) {
-		info("%s: read: %2d: %*ph: ", __func__, ret, 3, rx);
-		for (i = 0; (i < rx[3]) && ((i+3) < PCTV_ANSWER_LEN); i++)
-			info(" %02x", rx[i+3]);
+		info("%s: read: %2d: %*ph: ", __func__, ret, 3, state->data);
+		for (i = 0; (i < state->data[3]) && ((i + 3) < PCTV_ANSWER_LEN); i++)
+			info(" %02x", state->data[i + 3]);
 
 		info("\n");
 	}
 
-	if ((rx[3] == 9) &&  (rx[12] & 0x01)) {
+	if ((state->data[3] == 9) &&  (state->data[12] & 0x01)) {
 		/* got a "press" event */
-		state->last_rc_key = RC_SCANCODE_RC5(rx[7], rx[6]);
+		state->last_rc_key = RC_SCANCODE_RC5(state->data[7], state->data[6]);
 		if (debug > 2)
 			info("%s: cmd=0x%02x sys=0x%02x\n",
-				__func__, rx[6], rx[7]);
+				__func__, state->data[6], state->data[7]);
 
 		rc_keydown(d->rc_dev, RC_TYPE_RC5, state->last_rc_key, 0);
 	} else if (state->last_rc_key) {
 		rc_keyup(d->rc_dev);
 		state->last_rc_key = 0;
 	}
-
-	return 0;
+ret:
+	mutex_unlock(&state->ca_mutex);
+	return ret;
 }
 
 static int pctv452e_read_mac_address(struct dvb_usb_device *d, u8 mac[6])
diff --git a/drivers/media/usb/dvb-usb/technisat-usb2.c b/drivers/media/usb/dvb-usb/technisat-usb2.c
index d9f3262..4706628 100644
--- a/drivers/media/usb/dvb-usb/technisat-usb2.c
+++ b/drivers/media/usb/dvb-usb/technisat-usb2.c
@@ -89,9 +89,13 @@ struct technisat_usb2_state {
 static int technisat_usb2_i2c_access(struct usb_device *udev,
 		u8 device_addr, u8 *tx, u8 txlen, u8 *rx, u8 rxlen)
 {
-	u8 b[64];
+	u8 *b;
 	int ret, actual_length;
 
+	b = kmalloc(64, GFP_KERNEL);
+	if (!b)
+		return -ENOMEM;
+
 	deb_i2c("i2c-access: %02x, tx: ", device_addr);
 	debug_dump(tx, txlen, deb_i2c);
 	deb_i2c(" ");
@@ -123,7 +127,7 @@ static int technisat_usb2_i2c_access(struct usb_device *udev,
 
 	if (ret < 0) {
 		err("i2c-error: out failed %02x = %d", device_addr, ret);
-		return -ENODEV;
+		goto err;
 	}
 
 	ret = usb_bulk_msg(udev,
@@ -131,7 +135,7 @@ static int technisat_usb2_i2c_access(struct usb_device *udev,
 			b, 64, &actual_length, 1000);
 	if (ret < 0) {
 		err("i2c-error: in failed %02x = %d", device_addr, ret);
-		return -ENODEV;
+		goto err;
 	}
 
 	if (b[0] != I2C_STATUS_OK) {
@@ -140,7 +144,7 @@ static int technisat_usb2_i2c_access(struct usb_device *udev,
 		if (!(b[0] == I2C_STATUS_NAK &&
 				device_addr == 0x60
 				/* && device_is_technisat_usb2 */))
-			return -ENODEV;
+			goto err;
 	}
 
 	deb_i2c("status: %d, ", b[0]);
@@ -154,7 +158,9 @@ static int technisat_usb2_i2c_access(struct usb_device *udev,
 
 	deb_i2c("\n");
 
-	return 0;
+err:
+	kfree(b);
+	return ret;
 }
 
 static int technisat_usb2_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msg,
diff --git a/drivers/media/usb/s2255/s2255drv.c b/drivers/media/usb/s2255/s2255drv.c
index c3a0e87..f7bb78c 100644
--- a/drivers/media/usb/s2255/s2255drv.c
+++ b/drivers/media/usb/s2255/s2255drv.c
@@ -1901,19 +1901,30 @@ static long s2255_vendor_req(struct s2255_dev *dev, unsigned char Request,
 			     s32 TransferBufferLength, int bOut)
 {
 	int r;
+	unsigned char *buf;
+
+	buf = kmalloc(TransferBufferLength, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
 	if (!bOut) {
 		r = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
 				    Request,
 				    USB_TYPE_VENDOR | USB_RECIP_DEVICE |
 				    USB_DIR_IN,
-				    Value, Index, TransferBuffer,
+				    Value, Index, buf,
 				    TransferBufferLength, HZ * 5);
+
+		if (r >= 0)
+			memcpy(TransferBuffer, buf, TransferBufferLength);
 	} else {
+		memcpy(buf, TransferBuffer, TransferBufferLength);
 		r = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
 				    Request, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-				    Value, Index, TransferBuffer,
+				    Value, Index, buf,
 				    TransferBufferLength, HZ * 5);
 	}
+	kfree(buf);
 	return r;
 }
 
diff --git a/drivers/media/usb/stkwebcam/stk-webcam.c b/drivers/media/usb/stkwebcam/stk-webcam.c
index db200c9..22a9aae 100644
--- a/drivers/media/usb/stkwebcam/stk-webcam.c
+++ b/drivers/media/usb/stkwebcam/stk-webcam.c
@@ -147,20 +147,26 @@ int stk_camera_write_reg(struct stk_camera *dev, u16 index, u8 value)
 int stk_camera_read_reg(struct stk_camera *dev, u16 index, int *value)
 {
 	struct usb_device *udev = dev->udev;
+	unsigned char *buf;
 	int ret;
 
+	buf = kmalloc(sizeof(u8), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
 			0x00,
 			USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 			0x00,
 			index,
-			(u8 *) value,
+			buf,
 			sizeof(u8),
 			500);
-	if (ret < 0)
-		return ret;
-	else
-		return 0;
+	if (ret >= 0)
+		memcpy(value, buf, sizeof(u8));
+
+	kfree(buf);
+	return ret;
 }
 
 static int stk_start_stream(struct stk_camera *dev)
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index af23d7d..2e5233b 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -247,7 +247,9 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
 	cxl_ctx_get();
 
 	if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {
+		put_pid(ctx->glpid);
 		put_pid(ctx->pid);
+		ctx->glpid = ctx->pid = NULL;
 		cxl_adapter_context_put(ctx->afu->adapter);
 		cxl_ctx_put();
 		goto out;
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index d0b421f..77080cc 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -194,6 +194,16 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	ctx->mmio_err_ff = !!(work.flags & CXL_START_WORK_ERR_FF);
 
 	/*
+	 * Increment the mapped context count for adapter. This also checks
+	 * if adapter_context_lock is taken.
+	 */
+	rc = cxl_adapter_context_get(ctx->afu->adapter);
+	if (rc) {
+		afu_release_irqs(ctx, ctx);
+		goto out;
+	}
+
+	/*
 	 * We grab the PID here and not in the file open to allow for the case
 	 * where a process (master, some daemon, etc) has opened the chardev on
 	 * behalf of another process, so the AFU's mm gets bound to the process
@@ -205,15 +215,6 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	ctx->pid = get_task_pid(current, PIDTYPE_PID);
 	ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID);
 
-	/*
-	 * Increment the mapped context count for adapter. This also checks
-	 * if adapter_context_lock is taken.
-	 */
-	rc = cxl_adapter_context_get(ctx->afu->adapter);
-	if (rc) {
-		afu_release_irqs(ctx, ctx);
-		goto out;
-	}
 
 	trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
 
@@ -221,6 +222,9 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 							amr))) {
 		afu_release_irqs(ctx, ctx);
 		cxl_adapter_context_put(ctx->afu->adapter);
+		put_pid(ctx->glpid);
+		put_pid(ctx->pid);
+		ctx->glpid = ctx->pid = NULL;
 		goto out;
 	}
 
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 8a679ec..fc2794b 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -352,17 +352,27 @@ int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
 		if (copy_from_user(sgl->lpage, user_addr + user_size -
 				   sgl->lpage_size, sgl->lpage_size)) {
 			rc = -EFAULT;
-			goto err_out1;
+			goto err_out2;
 		}
 	}
 	return 0;
 
+ err_out2:
+	__genwqe_free_consistent(cd, PAGE_SIZE, sgl->lpage,
+				 sgl->lpage_dma_addr);
+	sgl->lpage = NULL;
+	sgl->lpage_dma_addr = 0;
  err_out1:
 	__genwqe_free_consistent(cd, PAGE_SIZE, sgl->fpage,
 				 sgl->fpage_dma_addr);
+	sgl->fpage = NULL;
+	sgl->fpage_dma_addr = 0;
  err_out:
 	__genwqe_free_consistent(cd, sgl->sgl_size, sgl->sgl,
 				 sgl->sgl_dma_addr);
+	sgl->sgl = NULL;
+	sgl->sgl_dma_addr = 0;
+	sgl->sgl_size = 0;
 	return -ENOMEM;
 }
 
diff --git a/drivers/misc/mei/hw-txe.c b/drivers/misc/mei/hw-txe.c
index e6e5e55..60415a2 100644
--- a/drivers/misc/mei/hw-txe.c
+++ b/drivers/misc/mei/hw-txe.c
@@ -981,11 +981,13 @@ static bool mei_txe_check_and_ack_intrs(struct mei_device *dev, bool do_ack)
 	hisr = mei_txe_br_reg_read(hw, HISR_REG);
 
 	aliveness = mei_txe_aliveness_get(dev);
-	if (hhisr & IPC_HHIER_SEC && aliveness)
+	if (hhisr & IPC_HHIER_SEC && aliveness) {
 		ipc_isr = mei_txe_sec_reg_read_silent(hw,
 				SEC_IPC_HOST_INT_STATUS_REG);
-	else
+	} else {
 		ipc_isr = 0;
+		hhisr &= ~IPC_HHIER_SEC;
+	}
 
 	generated = generated ||
 		(hisr & HISR_INT_STS_MSK) ||
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index 1525870..33741ad 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -283,7 +283,7 @@ static void gru_unload_mm_tracker(struct gru_state *gru,
 	spin_lock(&gru->gs_asid_lock);
 	BUG_ON((asids->mt_ctxbitmap & ctxbitmap) != ctxbitmap);
 	asids->mt_ctxbitmap ^= ctxbitmap;
-	gru_dbg(grudev, "gid %d, gts %p, gms %p, ctxnum 0x%d, asidmap 0x%lx\n",
+	gru_dbg(grudev, "gid %d, gts %p, gms %p, ctxnum %d, asidmap 0x%lx\n",
 		gru->gs_gid, gts, gms, gts->ts_ctxnum, gms->ms_asidmap[0]);
 	spin_unlock(&gru->gs_asid_lock);
 	spin_unlock(&gms->ms_asid_lock);
diff --git a/drivers/misc/vmw_vmci/vmci_doorbell.c b/drivers/misc/vmw_vmci/vmci_doorbell.c
index a8cee33..b3fa738 100644
--- a/drivers/misc/vmw_vmci/vmci_doorbell.c
+++ b/drivers/misc/vmw_vmci/vmci_doorbell.c
@@ -431,6 +431,12 @@ int vmci_doorbell_create(struct vmci_handle *handle,
 	if (vmci_handle_is_invalid(*handle)) {
 		u32 context_id = vmci_get_context_id();
 
+		if (context_id == VMCI_INVALID_ID) {
+			pr_warn("Failed to get context ID\n");
+			result = VMCI_ERROR_NO_RESOURCES;
+			goto free_mem;
+		}
+
 		/* Let resource code allocate a free ID for us */
 		new_handle = vmci_make_handle(context_id, VMCI_INVALID_ID);
 	} else {
@@ -525,7 +531,7 @@ int vmci_doorbell_destroy(struct vmci_handle handle)
 
 	entry = container_of(resource, struct dbell_entry, resource);
 
-	if (vmci_guest_code_active()) {
+	if (!hlist_unhashed(&entry->node)) {
 		int result;
 
 		dbell_index_table_remove(entry);
diff --git a/drivers/misc/vmw_vmci/vmci_driver.c b/drivers/misc/vmw_vmci/vmci_driver.c
index 896be15..d7eaf1e 100644
--- a/drivers/misc/vmw_vmci/vmci_driver.c
+++ b/drivers/misc/vmw_vmci/vmci_driver.c
@@ -113,5 +113,5 @@ module_exit(vmci_drv_exit);
 
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMware Virtual Machine Communication Interface.");
-MODULE_VERSION("1.1.4.0-k");
+MODULE_VERSION("1.1.5.0-k");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/dw_mmc-pltfm.c b/drivers/mmc/host/dw_mmc-pltfm.c
index c0bb0c7..dbbc430 100644
--- a/drivers/mmc/host/dw_mmc-pltfm.c
+++ b/drivers/mmc/host/dw_mmc-pltfm.c
@@ -46,12 +46,13 @@ int dw_mci_pltfm_register(struct platform_device *pdev,
 	host->pdata = pdev->dev.platform_data;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	/* Get registers' physical base address */
-	host->phy_regs = regs->start;
 	host->regs = devm_ioremap_resource(&pdev->dev, regs);
 	if (IS_ERR(host->regs))
 		return PTR_ERR(host->regs);
 
+	/* Get registers' physical base address */
+	host->phy_regs = regs->start;
+
 	platform_set_drvdata(pdev, host);
 	return dw_mci_probe(host);
 }
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 8ef44a2a..90ed2e1 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -647,6 +647,7 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 	if (msm_host->pwr_irq < 0) {
 		dev_err(&pdev->dev, "Get pwr_irq failed (%d)\n",
 			msm_host->pwr_irq);
+		ret = msm_host->pwr_irq;
 		goto clk_disable;
 	}
 
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
index 0f68a99..141bd70 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
@@ -161,7 +161,7 @@ int gpmi_init(struct gpmi_nand_data *this)
 
 	ret = gpmi_enable_clk(this);
 	if (ret)
-		goto err_out;
+		return ret;
 	ret = gpmi_reset_block(r->gpmi_regs, false);
 	if (ret)
 		goto err_out;
@@ -197,6 +197,7 @@ int gpmi_init(struct gpmi_nand_data *this)
 	gpmi_disable_clk(this);
 	return 0;
 err_out:
+	gpmi_disable_clk(this);
 	return ret;
 }
 
@@ -270,7 +271,7 @@ int bch_set_geometry(struct gpmi_nand_data *this)
 
 	ret = gpmi_enable_clk(this);
 	if (ret)
-		goto err_out;
+		return ret;
 
 	/*
 	* Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this
@@ -308,6 +309,7 @@ int bch_set_geometry(struct gpmi_nand_data *this)
 	gpmi_disable_clk(this);
 	return 0;
 err_out:
+	gpmi_disable_clk(this);
 	return ret;
 }
 
diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c
index d54f666..dbf2562 100644
--- a/drivers/mtd/nand/mtk_ecc.c
+++ b/drivers/mtd/nand/mtk_ecc.c
@@ -86,6 +86,8 @@ struct mtk_ecc {
 	struct completion done;
 	struct mutex lock;
 	u32 sectors;
+
+	u8 eccdata[112];
 };
 
 static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc,
@@ -366,9 +368,8 @@ int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config,
 		   u8 *data, u32 bytes)
 {
 	dma_addr_t addr;
-	u8 *p;
-	u32 len, i, val;
-	int ret = 0;
+	u32 len;
+	int ret;
 
 	addr = dma_map_single(ecc->dev, data, bytes, DMA_TO_DEVICE);
 	ret = dma_mapping_error(ecc->dev, addr);
@@ -393,14 +394,12 @@ int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config,
 
 	/* Program ECC bytes to OOB: per sector oob = FDM + ECC + SPARE */
 	len = (config->strength * ECC_PARITY_BITS + 7) >> 3;
-	p = data + bytes;
 
-	/* write the parity bytes generated by the ECC back to the OOB region */
-	for (i = 0; i < len; i++) {
-		if ((i % 4) == 0)
-			val = readl(ecc->regs + ECC_ENCPAR(i / 4));
-		p[i] = (val >> ((i % 4) * 8)) & 0xff;
-	}
+	/* write the parity bytes generated by the ECC back to temp buffer */
+	__ioread32_copy(ecc->eccdata, ecc->regs + ECC_ENCPAR(0), round_up(len, 4));
+
+	/* copy into possibly unaligned OOB region with actual length */
+	memcpy(data + bytes, ecc->eccdata, len);
 timeout:
 
 	dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index e5718e5..3bde96a 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1095,10 +1095,11 @@ static void nand_release_data_interface(struct nand_chip *chip)
 /**
  * nand_reset - Reset and initialize a NAND device
  * @chip: The NAND chip
+ * @chipnr: Internal die id
  *
  * Returns 0 for success or negative error code otherwise
  */
-int nand_reset(struct nand_chip *chip)
+int nand_reset(struct nand_chip *chip, int chipnr)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
@@ -1107,9 +1108,17 @@ int nand_reset(struct nand_chip *chip)
 	if (ret)
 		return ret;
 
+	/*
+	 * The CS line has to be released before we can apply the new NAND
+	 * interface settings, hence this weird ->select_chip() dance.
+	 */
+	chip->select_chip(mtd, chipnr);
 	chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+	chip->select_chip(mtd, -1);
 
+	chip->select_chip(mtd, chipnr);
 	ret = nand_setup_data_interface(chip);
+	chip->select_chip(mtd, -1);
 	if (ret)
 		return ret;
 
@@ -1185,8 +1194,6 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	/* Shift to get chip number */
 	chipnr = ofs >> chip->chip_shift;
 
-	chip->select_chip(mtd, chipnr);
-
 	/*
 	 * Reset the chip.
 	 * If we want to check the WP through READ STATUS and check the bit 7
@@ -1194,7 +1201,9 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	 * some operation can also clear the bit 7 of status register
 	 * eg. erase/program a locked block
 	 */
-	nand_reset(chip);
+	nand_reset(chip, chipnr);
+
+	chip->select_chip(mtd, chipnr);
 
 	/* Check, if it is write protected */
 	if (nand_check_wp(mtd)) {
@@ -1244,8 +1253,6 @@ int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	/* Shift to get chip number */
 	chipnr = ofs >> chip->chip_shift;
 
-	chip->select_chip(mtd, chipnr);
-
 	/*
 	 * Reset the chip.
 	 * If we want to check the WP through READ STATUS and check the bit 7
@@ -1253,7 +1260,9 @@ int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	 * some operation can also clear the bit 7 of status register
 	 * eg. erase/program a locked block
 	 */
-	nand_reset(chip);
+	nand_reset(chip, chipnr);
+
+	chip->select_chip(mtd, chipnr);
 
 	/* Check, if it is write protected */
 	if (nand_check_wp(mtd)) {
@@ -2940,10 +2949,6 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
 	}
 
 	chipnr = (int)(to >> chip->chip_shift);
-	chip->select_chip(mtd, chipnr);
-
-	/* Shift to get page */
-	page = (int)(to >> chip->page_shift);
 
 	/*
 	 * Reset the chip. Some chips (like the Toshiba TC5832DC found in one
@@ -2951,7 +2956,12 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
 	 * if we don't do this. I have no clue why, but I seem to have 'fixed'
 	 * it in the doc2000 driver in August 1999.  dwmw2.
 	 */
-	nand_reset(chip);
+	nand_reset(chip, chipnr);
+
+	chip->select_chip(mtd, chipnr);
+
+	/* Shift to get page */
+	page = (int)(to >> chip->page_shift);
 
 	/* Check, if it is write protected */
 	if (nand_check_wp(mtd)) {
@@ -3984,14 +3994,14 @@ static struct nand_flash_dev *nand_get_flash_type(struct mtd_info *mtd,
 	int i, maf_idx;
 	u8 id_data[8];
 
-	/* Select the device */
-	chip->select_chip(mtd, 0);
-
 	/*
 	 * Reset the chip, required by some chips (e.g. Micron MT29FxGxxxxx)
 	 * after power-up.
 	 */
-	nand_reset(chip);
+	nand_reset(chip, 0);
+
+	/* Select the device */
+	chip->select_chip(mtd, 0);
 
 	/* Send the command for reading device ID */
 	chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1);
@@ -4329,17 +4339,31 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 		return PTR_ERR(type);
 	}
 
+	/* Initialize the ->data_interface field. */
 	ret = nand_init_data_interface(chip);
 	if (ret)
 		return ret;
 
+	/*
+	 * Setup the data interface correctly on the chip and controller side.
+	 * This explicit call to nand_setup_data_interface() is only required
+	 * for the first die, because nand_reset() has been called before
+	 * ->data_interface and ->default_onfi_timing_mode were set.
+	 * For the other dies, nand_reset() will automatically switch to the
+	 * best mode for us.
+	 */
+	ret = nand_setup_data_interface(chip);
+	if (ret)
+		return ret;
+
 	chip->select_chip(mtd, -1);
 
 	/* Check for a chip array */
 	for (i = 1; i < maxchips; i++) {
-		chip->select_chip(mtd, i);
 		/* See comment in nand_get_flash_type for reset */
-		nand_reset(chip);
+		nand_reset(chip, i);
+
+		chip->select_chip(mtd, i);
 		/* Send the command for reading device ID */
 		chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1);
 		/* Read manufacturer and device IDs */
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 2ff6215..c1f5c29 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -707,11 +707,11 @@ static int ubi_attach_fastmap(struct ubi_device *ubi,
 			     fmvhdr->vol_type,
 			     be32_to_cpu(fmvhdr->last_eb_bytes));
 
-		if (!av)
-			goto fail_bad;
-		if (PTR_ERR(av) == -EINVAL) {
-			ubi_err(ubi, "volume (ID %i) already exists",
-				fmvhdr->vol_id);
+		if (IS_ERR(av)) {
+			if (PTR_ERR(av) == -EEXIST)
+				ubi_err(ubi, "volume (ID %i) already exists",
+					fmvhdr->vol_id);
+
 			goto fail_bad;
 		}
 
diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c
index 76fb855..ef63d24 100644
--- a/drivers/net/dsa/b53/b53_mmap.c
+++ b/drivers/net/dsa/b53/b53_mmap.c
@@ -256,6 +256,7 @@ static const struct of_device_id b53_mmap_of_table[] = {
 	{ .compatible = "brcm,bcm63xx-switch" },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, b53_mmap_of_table);
 
 static struct platform_driver b53_mmap_driver = {
 	.probe = b53_mmap_probe,
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index e218887..e3ee27c 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1133,6 +1133,20 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static void bcm_sf2_sw_shutdown(struct platform_device *pdev)
+{
+	struct bcm_sf2_priv *priv = platform_get_drvdata(pdev);
+
+	/* For a kernel about to be kexec'd we want to keep the GPHY on for a
+	 * successful MDIO bus scan to occur. If we did turn off the GPHY
+	 * before (e.g: port_disable), this will also power it back on.
+	 *
+	 * Do not rely on kexec_in_progress, just power the PHY on.
+	 */
+	if (priv->hw_params.num_gphy == 1)
+		bcm_sf2_gphy_enable_set(priv->dev->ds, true);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int bcm_sf2_suspend(struct device *dev)
 {
@@ -1158,10 +1172,12 @@ static const struct of_device_id bcm_sf2_of_match[] = {
 	{ .compatible = "brcm,bcm7445-switch-v4.0" },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, bcm_sf2_of_match);
 
 static struct platform_driver bcm_sf2_driver = {
 	.probe	= bcm_sf2_sw_probe,
 	.remove	= bcm_sf2_sw_remove,
+	.shutdown = bcm_sf2_sw_shutdown,
 	.driver = {
 		.name = "brcm-sf2",
 		.of_match_table = bcm_sf2_of_match,
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index b047fd6..00c38bf 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -1358,6 +1358,7 @@ static const struct of_device_id nb8800_dt_ids[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(of, nb8800_dt_ids);
 
 static int nb8800_probe(struct platform_device *pdev)
 {
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index ae364c7..5370909 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1126,7 +1126,8 @@ static int bcm_enet_open(struct net_device *dev)
 	free_irq(dev->irq, dev);
 
 out_phy_disconnect:
-	phy_disconnect(phydev);
+	if (priv->has_phy)
+		phy_disconnect(phydev);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 856379c..31ca204 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1449,7 +1449,7 @@ static int bgmac_phy_connect(struct bgmac *bgmac)
 	phy_dev = phy_connect(bgmac->net_dev, bus_id, &bgmac_adjust_link,
 			      PHY_INTERFACE_MODE_MII);
 	if (IS_ERR(phy_dev)) {
-		dev_err(bgmac->dev, "PHY connecton failed\n");
+		dev_err(bgmac->dev, "PHY connection failed\n");
 		return PTR_ERR(phy_dev);
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 27f11a5..b3791b3 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -271,22 +271,25 @@ static inline u32 bnx2_tx_avail(struct bnx2 *bp, struct bnx2_tx_ring_info *txr)
 static u32
 bnx2_reg_rd_ind(struct bnx2 *bp, u32 offset)
 {
+	unsigned long flags;
 	u32 val;
 
-	spin_lock_bh(&bp->indirect_lock);
+	spin_lock_irqsave(&bp->indirect_lock, flags);
 	BNX2_WR(bp, BNX2_PCICFG_REG_WINDOW_ADDRESS, offset);
 	val = BNX2_RD(bp, BNX2_PCICFG_REG_WINDOW);
-	spin_unlock_bh(&bp->indirect_lock);
+	spin_unlock_irqrestore(&bp->indirect_lock, flags);
 	return val;
 }
 
 static void
 bnx2_reg_wr_ind(struct bnx2 *bp, u32 offset, u32 val)
 {
-	spin_lock_bh(&bp->indirect_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&bp->indirect_lock, flags);
 	BNX2_WR(bp, BNX2_PCICFG_REG_WINDOW_ADDRESS, offset);
 	BNX2_WR(bp, BNX2_PCICFG_REG_WINDOW, val);
-	spin_unlock_bh(&bp->indirect_lock);
+	spin_unlock_irqrestore(&bp->indirect_lock, flags);
 }
 
 static void
@@ -304,8 +307,10 @@ bnx2_shmem_rd(struct bnx2 *bp, u32 offset)
 static void
 bnx2_ctx_wr(struct bnx2 *bp, u32 cid_addr, u32 offset, u32 val)
 {
+	unsigned long flags;
+
 	offset += cid_addr;
-	spin_lock_bh(&bp->indirect_lock);
+	spin_lock_irqsave(&bp->indirect_lock, flags);
 	if (BNX2_CHIP(bp) == BNX2_CHIP_5709) {
 		int i;
 
@@ -322,7 +327,7 @@ bnx2_ctx_wr(struct bnx2 *bp, u32 cid_addr, u32 offset, u32 val)
 		BNX2_WR(bp, BNX2_CTX_DATA_ADR, offset);
 		BNX2_WR(bp, BNX2_CTX_DATA, val);
 	}
-	spin_unlock_bh(&bp->indirect_lock);
+	spin_unlock_irqrestore(&bp->indirect_lock, flags);
 }
 
 #ifdef BCM_CNIC
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 20fe6a8..0cee4c0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -15241,7 +15241,7 @@ static void bnx2x_init_cyclecounter(struct bnx2x *bp)
 	memset(&bp->cyclecounter, 0, sizeof(bp->cyclecounter));
 	bp->cyclecounter.read = bnx2x_cyclecounter_read;
 	bp->cyclecounter.mask = CYCLECOUNTER_MASK(64);
-	bp->cyclecounter.shift = 1;
+	bp->cyclecounter.shift = 0;
 	bp->cyclecounter.mult = 1;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index f320497..57eb4e1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -4057,7 +4057,7 @@ static void cfg_queues(struct adapter *adap)
 		 * capped by the number of available cores.
 		 */
 		if (n10g) {
-			i = num_online_cpus();
+			i = min_t(int, MAX_OFLD_QSETS, num_online_cpus());
 			s->ofldqsets = roundup(i, adap->params.nports);
 		} else {
 			s->ofldqsets = adap->params.nports;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 0945fa4..2471ff4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -135,15 +135,17 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
 }
 
 static int alloc_uld_rxqs(struct adapter *adap,
-			  struct sge_uld_rxq_info *rxq_info,
-			  unsigned int nq, unsigned int offset, bool lro)
+			  struct sge_uld_rxq_info *rxq_info, bool lro)
 {
 	struct sge *s = &adap->sge;
-	struct sge_ofld_rxq *q = rxq_info->uldrxq + offset;
-	unsigned short *ids = rxq_info->rspq_id + offset;
-	unsigned int per_chan = nq / adap->params.nports;
+	unsigned int nq = rxq_info->nrxq + rxq_info->nciq;
+	struct sge_ofld_rxq *q = rxq_info->uldrxq;
+	unsigned short *ids = rxq_info->rspq_id;
 	unsigned int bmap_idx = 0;
-	int i, err, msi_idx;
+	unsigned int per_chan;
+	int i, err, msi_idx, que_idx = 0;
+
+	per_chan = rxq_info->nrxq / adap->params.nports;
 
 	if (adap->flags & USING_MSIX)
 		msi_idx = 1;
@@ -151,12 +153,18 @@ static int alloc_uld_rxqs(struct adapter *adap,
 		msi_idx = -((int)s->intrq.abs_id + 1);
 
 	for (i = 0; i < nq; i++, q++) {
+		if (i == rxq_info->nrxq) {
+			/* start allocation of concentrator queues */
+			per_chan = rxq_info->nciq / adap->params.nports;
+			que_idx = 0;
+		}
+
 		if (msi_idx >= 0) {
 			bmap_idx = get_msix_idx_from_bmap(adap);
 			msi_idx = adap->msix_info_ulds[bmap_idx].idx;
 		}
 		err = t4_sge_alloc_rxq(adap, &q->rspq, false,
-				       adap->port[i / per_chan],
+				       adap->port[que_idx++ / per_chan],
 				       msi_idx,
 				       q->fl.size ? &q->fl : NULL,
 				       uldrx_handler,
@@ -165,29 +173,19 @@ static int alloc_uld_rxqs(struct adapter *adap,
 		if (err)
 			goto freeout;
 		if (msi_idx >= 0)
-			rxq_info->msix_tbl[i + offset] = bmap_idx;
+			rxq_info->msix_tbl[i] = bmap_idx;
 		memset(&q->stats, 0, sizeof(q->stats));
 		if (ids)
 			ids[i] = q->rspq.abs_id;
 	}
 	return 0;
 freeout:
-	q = rxq_info->uldrxq + offset;
+	q = rxq_info->uldrxq;
 	for ( ; i; i--, q++) {
 		if (q->rspq.desc)
 			free_rspq_fl(adap, &q->rspq,
 				     q->fl.size ? &q->fl : NULL);
 	}
-
-	/* We need to free rxq also in case of ciq allocation failure */
-	if (offset) {
-		q = rxq_info->uldrxq + offset;
-		for ( ; i; i--, q++) {
-			if (q->rspq.desc)
-				free_rspq_fl(adap, &q->rspq,
-					     q->fl.size ? &q->fl : NULL);
-		}
-	}
 	return err;
 }
 
@@ -205,9 +203,7 @@ setup_sge_queues_uld(struct adapter *adap, unsigned int uld_type, bool lro)
 			return -ENOMEM;
 	}
 
-	ret = !(!alloc_uld_rxqs(adap, rxq_info, rxq_info->nrxq, 0, lro) &&
-		 !alloc_uld_rxqs(adap, rxq_info, rxq_info->nciq,
-				 rxq_info->nrxq, lro));
+	ret = !(!alloc_uld_rxqs(adap, rxq_info, lro));
 
 	/* Tell uP to route control queue completions to rdma rspq */
 	if (adap->flags & FULL_INIT_DONE &&
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index 539de76..cbd68a8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -210,8 +210,10 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p)
 
 	/* Unbind queue from any existing class */
 	err = t4_sched_queue_unbind(pi, p);
-	if (err)
+	if (err) {
+		t4_free_mem(qe);
 		goto out;
+	}
 
 	/* Bind queue to specified class */
 	memset(qe, 0, sizeof(*qe));
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c
index e572a52..36bc2c7 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c
@@ -169,19 +169,28 @@ int vnic_rq_disable(struct vnic_rq *rq)
 {
 	unsigned int wait;
 	struct vnic_dev *vdev = rq->vdev;
+	int i;
 
-	iowrite32(0, &rq->ctrl->enable);
+	/* Due to a race condition with clearing RQ "mini-cache" in hw, we need
+	 * to disable the RQ twice to guarantee that stale descriptors are not
+	 * used when this RQ is re-enabled.
+	 */
+	for (i = 0; i < 2; i++) {
+		iowrite32(0, &rq->ctrl->enable);
 
-	/* Wait for HW to ACK disable request */
-	for (wait = 0; wait < 1000; wait++) {
-		if (!(ioread32(&rq->ctrl->running)))
-			return 0;
-		udelay(10);
+		/* Wait for HW to ACK disable request */
+		for (wait = 20000; wait > 0; wait--)
+			if (!ioread32(&rq->ctrl->running))
+				break;
+		if (!wait) {
+			vdev_neterr(vdev, "Failed to disable RQ[%d]\n",
+				    rq->index);
+
+			return -ETIMEDOUT;
+		}
 	}
 
-	vdev_neterr(vdev, "Failed to disable RQ[%d]\n", rq->index);
-
-	return -ETIMEDOUT;
+	return 0;
 }
 
 void vnic_rq_clean(struct vnic_rq *rq,
@@ -212,6 +221,11 @@ void vnic_rq_clean(struct vnic_rq *rq,
 			[fetch_index % VNIC_RQ_BUF_BLK_ENTRIES(count)];
 	iowrite32(fetch_index, &rq->ctrl->posted_index);
 
+	/* Anytime we write fetch_index, we need to re-write 0 to rq->enable
+	 * to re-sync internal VIC state.
+	 */
+	iowrite32(0, &rq->ctrl->enable);
+
 	vnic_dev_clear_desc_ring(&rq->ring);
 }
 
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index f928e6f..223f35c 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -669,6 +669,7 @@ static const struct of_device_id nps_enet_dt_ids[] = {
 	{ .compatible = "ezchip,nps-mgt-enet" },
 	{ /* Sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, nps_enet_dt_ids);
 
 static struct platform_driver nps_enet_driver = {
 	.probe = nps_enet_probe,
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 48a033e..5aa9d4d 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1430,14 +1430,14 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		skb_put(skb, pkt_len - 4);
 		data = skb->data;
 
+		if (!is_copybreak && need_swap)
+			swap_buffer(data, pkt_len);
+
 #if !defined(CONFIG_M5272)
 		if (fep->quirks & FEC_QUIRK_HAS_RACC)
 			data = skb_pull_inline(skb, 2);
 #endif
 
-		if (!is_copybreak && need_swap)
-			swap_buffer(data, pkt_len);
-
 		/* Extract the enhanced buffer descriptor */
 		ebdp = NULL;
 		if (fep->bufdesc_ex)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 8d70377..8ea3d95 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -2751,6 +2751,7 @@ static const struct of_device_id g_dsaf_match[] = {
 	{.compatible = "hisilicon,hns-dsaf-v2"},
 	{}
 };
+MODULE_DEVICE_TABLE(of, g_dsaf_match);
 
 static struct platform_driver g_dsaf_driver = {
 	.probe = hns_dsaf_probe,
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 33f4c48..501eb20 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -563,6 +563,7 @@ static const struct of_device_id hns_mdio_match[] = {
 	{.compatible = "hisilicon,hns-mdio"},
 	{}
 };
+MODULE_DEVICE_TABLE(of, hns_mdio_match);
 
 static const struct acpi_device_id hns_mdio_acpi_match[] = {
 	{ "HISI0141", 0 },
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index bfe17d9..5f44c55 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1190,7 +1190,7 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
 	if (!scrq)
 		return NULL;
 
-	scrq->msgs = (union sub_crq *)__get_free_pages(GFP_KERNEL, 2);
+	scrq->msgs = (union sub_crq *)__get_free_pages(GFP_ATOMIC, 2);
 	memset(scrq->msgs, 0, 4 * PAGE_SIZE);
 	if (!scrq->msgs) {
 		dev_warn(dev, "Couldn't allocate crq queue messages page\n");
@@ -1461,14 +1461,16 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
 	return rc;
 
 req_rx_irq_failed:
-	for (j = 0; j < i; j++)
+	for (j = 0; j < i; j++) {
 		free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]);
 		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+	}
 	i = adapter->req_tx_queues;
 req_tx_irq_failed:
-	for (j = 0; j < i; j++)
+	for (j = 0; j < i; j++) {
 		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
 		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+	}
 	release_sub_crqs_no_irqs(adapter);
 	return rc;
 }
@@ -3232,6 +3234,27 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->inflight_lock, flags);
 }
 
+static void ibmvnic_xport_event(struct work_struct *work)
+{
+	struct ibmvnic_adapter *adapter = container_of(work,
+						       struct ibmvnic_adapter,
+						       ibmvnic_xport);
+	struct device *dev = &adapter->vdev->dev;
+	long rc;
+
+	ibmvnic_free_inflight(adapter);
+	release_sub_crqs(adapter);
+	if (adapter->migrated) {
+		rc = ibmvnic_reenable_crq_queue(adapter);
+		if (rc)
+			dev_err(dev, "Error after enable rc=%ld\n", rc);
+		adapter->migrated = false;
+		rc = ibmvnic_send_crq_init(adapter);
+		if (rc)
+			dev_err(dev, "Error sending init rc=%ld\n", rc);
+	}
+}
+
 static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			       struct ibmvnic_adapter *adapter)
 {
@@ -3267,15 +3290,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		if (gen_crq->cmd == IBMVNIC_PARTITION_MIGRATED) {
 			dev_info(dev, "Re-enabling adapter\n");
 			adapter->migrated = true;
-			ibmvnic_free_inflight(adapter);
-			release_sub_crqs(adapter);
-			rc = ibmvnic_reenable_crq_queue(adapter);
-			if (rc)
-				dev_err(dev, "Error after enable rc=%ld\n", rc);
-			adapter->migrated = false;
-			rc = ibmvnic_send_crq_init(adapter);
-			if (rc)
-				dev_err(dev, "Error sending init rc=%ld\n", rc);
+			schedule_work(&adapter->ibmvnic_xport);
 		} else if (gen_crq->cmd == IBMVNIC_DEVICE_FAILOVER) {
 			dev_info(dev, "Backing device failover detected\n");
 			netif_carrier_off(netdev);
@@ -3284,8 +3299,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			/* The adapter lost the connection */
 			dev_err(dev, "Virtual Adapter failed (rc=%d)\n",
 				gen_crq->cmd);
-			ibmvnic_free_inflight(adapter);
-			release_sub_crqs(adapter);
+			schedule_work(&adapter->ibmvnic_xport);
 		}
 		return;
 	case IBMVNIC_CRQ_CMD_RSP:
@@ -3654,6 +3668,7 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		goto task_failed;
 
 	netdev->real_num_tx_queues = adapter->req_tx_queues;
+	netdev->mtu = adapter->req_mtu;
 
 	if (adapter->failover) {
 		adapter->failover = false;
@@ -3725,6 +3740,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	SET_NETDEV_DEV(netdev, &dev->dev);
 
 	INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp);
+	INIT_WORK(&adapter->ibmvnic_xport, ibmvnic_xport_event);
 
 	spin_lock_init(&adapter->stats_lock);
 
@@ -3792,6 +3808,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev->real_num_tx_queues = adapter->req_tx_queues;
+	netdev->mtu = adapter->req_mtu;
 
 	rc = register_netdev(netdev);
 	if (rc) {
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index bfc84c7..dd775d9 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -27,7 +27,7 @@
 /**************************************************************************/
 
 #define IBMVNIC_NAME		"ibmvnic"
-#define IBMVNIC_DRIVER_VERSION	"1.0"
+#define IBMVNIC_DRIVER_VERSION	"1.0.1"
 #define IBMVNIC_INVALID_MAP	-1
 #define IBMVNIC_STATS_TIMEOUT	1
 /* basic structures plus 100 2k buffers */
@@ -1048,5 +1048,6 @@ struct ibmvnic_adapter {
 	u8 map_id;
 
 	struct work_struct vnic_crq_init;
+	struct work_struct ibmvnic_xport;
 	bool failover;
 };
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 2030d7c..6d61e44 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -92,6 +92,7 @@
 #define I40E_AQ_LEN			256
 #define I40E_AQ_WORK_LIMIT		66 /* max number of VFs + a little */
 #define I40E_MAX_USER_PRIORITY		8
+#define I40E_DEFAULT_TRAFFIC_CLASS	BIT(0)
 #define I40E_DEFAULT_MSG_ENABLE		4
 #define I40E_QUEUE_WAIT_RETRY_LIMIT	10
 #define I40E_INT_NAME_STR_LEN		(IFNAMSIZ + 16)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ac1faee..31c97e3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4641,29 +4641,6 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
 }
 
 /**
- * i40e_pf_get_default_tc - Get bitmap for first enabled TC
- * @pf: PF being queried
- *
- * Return a bitmap for first enabled traffic class for this PF.
- **/
-static u8 i40e_pf_get_default_tc(struct i40e_pf *pf)
-{
-	u8 enabled_tc = pf->hw.func_caps.enabled_tcmap;
-	u8 i = 0;
-
-	if (!enabled_tc)
-		return 0x1; /* TC0 */
-
-	/* Find the first enabled TC */
-	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
-		if (enabled_tc & BIT(i))
-			break;
-	}
-
-	return BIT(i);
-}
-
-/**
  * i40e_pf_get_pf_tc_map - Get bitmap for enabled traffic classes
  * @pf: PF being queried
  *
@@ -4673,7 +4650,7 @@ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf)
 {
 	/* If DCB is not enabled for this PF then just return default TC */
 	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
-		return i40e_pf_get_default_tc(pf);
+		return I40E_DEFAULT_TRAFFIC_CLASS;
 
 	/* SFP mode we want PF to be enabled for all TCs */
 	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
@@ -4683,7 +4660,7 @@ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf)
 	if (pf->hw.func_caps.iscsi)
 		return i40e_get_iscsi_tc_map(pf);
 	else
-		return i40e_pf_get_default_tc(pf);
+		return I40E_DEFAULT_TRAFFIC_CLASS;
 }
 
 /**
@@ -5029,7 +5006,7 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 		if (v == pf->lan_vsi)
 			tc_map = i40e_pf_get_tc_map(pf);
 		else
-			tc_map = i40e_pf_get_default_tc(pf);
+			tc_map = I40E_DEFAULT_TRAFFIC_CLASS;
 #ifdef I40E_FCOE
 		if (pf->vsi[v]->type == I40E_VSI_FCOE)
 			tc_map = i40e_get_fcoe_tc_map(pf);
@@ -5717,7 +5694,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	u8 type;
 
 	/* Not DCB capable or capability disabled */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
+	if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
 		return ret;
 
 	/* Ignore if event is not for Nearest Bridge */
@@ -7707,6 +7684,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		pf->flags &= ~I40E_FLAG_MSIX_ENABLED;
 		kfree(pf->msix_entries);
 		pf->msix_entries = NULL;
+		pci_disable_msix(pf->pdev);
 		return -ENODEV;
 
 	} else if (v_actual == I40E_MIN_MSIX) {
@@ -9056,7 +9034,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 		return 0;
 
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode,
-				       nlflags, 0, 0, filter_mask, NULL);
+				       0, 0, nlflags, filter_mask, NULL);
 }
 
 /* Hardware supports L4 tunnel length of 128B (=2^7) which includes
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a244d9a..bd93d82 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9135,10 +9135,14 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 		goto fwd_add_err;
 	fwd_adapter->pool = pool;
 	fwd_adapter->real_adapter = adapter;
-	err = ixgbe_fwd_ring_up(vdev, fwd_adapter);
-	if (err)
-		goto fwd_add_err;
-	netif_tx_start_all_queues(vdev);
+
+	if (netif_running(pdev)) {
+		err = ixgbe_fwd_ring_up(vdev, fwd_adapter);
+		if (err)
+			goto fwd_add_err;
+		netif_tx_start_all_queues(vdev);
+	}
+
 	return fwd_adapter;
 fwd_add_err:
 	/* unwind counter and free adapter struct */
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 5583118..bf5cc55b 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -2968,6 +2968,22 @@ static void set_params(struct mv643xx_eth_private *mp,
 	mp->txq_count = pd->tx_queue_count ? : 1;
 }
 
+static int get_phy_mode(struct mv643xx_eth_private *mp)
+{
+	struct device *dev = mp->dev->dev.parent;
+	int iface = -1;
+
+	if (dev->of_node)
+		iface = of_get_phy_mode(dev->of_node);
+
+	/* Historical default if unspecified. We could also read/write
+	 * the interface state in the PSC1
+	 */
+	if (iface < 0)
+		iface = PHY_INTERFACE_MODE_GMII;
+	return iface;
+}
+
 static struct phy_device *phy_scan(struct mv643xx_eth_private *mp,
 				   int phy_addr)
 {
@@ -2994,7 +3010,7 @@ static struct phy_device *phy_scan(struct mv643xx_eth_private *mp,
 				"orion-mdio-mii", addr);
 
 		phydev = phy_connect(mp->dev, phy_id, mv643xx_eth_adjust_link,
-				PHY_INTERFACE_MODE_GMII);
+				     get_phy_mode(mp));
 		if (!IS_ERR(phydev)) {
 			phy_addr_set(mp, addr);
 			break;
@@ -3090,6 +3106,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 	if (!dev)
 		return -ENOMEM;
 
+	SET_NETDEV_DEV(dev, &pdev->dev);
 	mp = netdev_priv(dev);
 	platform_set_drvdata(pdev, mp);
 
@@ -3129,7 +3146,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 	if (pd->phy_node) {
 		mp->phy = of_phy_connect(mp->dev, pd->phy_node,
 					 mv643xx_eth_adjust_link, 0,
-					 PHY_INTERFACE_MODE_GMII);
+					 get_phy_mode(mp));
 		if (!mp->phy)
 			err = -ENODEV;
 		else
@@ -3187,8 +3204,6 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 	dev->priv_flags |= IFF_UNICAST_FLT;
 	dev->gso_max_segs = MV643XX_MAX_TSO_SEGS;
 
-	SET_NETDEV_DEV(dev, &pdev->dev);
-
 	if (mp->shared->win_protect)
 		wrl(mp, WINDOW_PROTECT(mp->port_num), mp->shared->win_protect);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index b1cef7a..e36bebc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2469,6 +2469,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 	kfree(priv->mfunc.master.slave_state);
 err_comm:
 	iounmap(priv->mfunc.comm);
+	priv->mfunc.comm = NULL;
 err_vhcr:
 	dma_free_coherent(&dev->persist->pdev->dev, PAGE_SIZE,
 			  priv->mfunc.vhcr,
@@ -2537,6 +2538,13 @@ void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev)
 	int slave;
 	u32 slave_read;
 
+	/* If the comm channel has not yet been initialized,
+	 * skip reporting the internal error event to all
+	 * the communication channels.
+	 */
+	if (!priv->mfunc.comm)
+		return;
+
 	/* Report an internal error event to all
 	 * communication channels.
 	 */
@@ -2571,6 +2579,7 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev)
 	}
 
 	iounmap(priv->mfunc.comm);
+	priv->mfunc.comm = NULL;
 }
 
 void mlx4_cmd_cleanup(struct mlx4_dev *dev, int cleanup_mask)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 08fc5fc..a5fc46b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -245,8 +245,11 @@ static u32 freq_to_shift(u16 freq)
 {
 	u32 freq_khz = freq * 1000;
 	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 tmp_rounded =
+		roundup_pow_of_two(max_val_cycles) > max_val_cycles ?
+		roundup_pow_of_two(max_val_cycles) - 1 : UINT_MAX;
 	u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
-		max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1;
+		max_val_cycles : tmp_rounded;
 	/* calculate max possible multiplier in order to fit in 64bit */
 	u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 132cea6..e3be7e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -127,7 +127,15 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		/* For TX we use the same irq per
 		ring we assigned for the RX    */
 		struct mlx4_en_cq *rx_cq;
+		int xdp_index;
 
+		/* The xdp tx irq must align with the rx ring that forwards to
+		 * it, so reindex these from 0. This should only happen when
+		 * tx_ring_num is not a multiple of rx_ring_num.
+		 */
+		xdp_index = (priv->xdp_ring_num - priv->tx_ring_num) + cq_idx;
+		if (xdp_index >= 0)
+			cq_idx = xdp_index;
 		cq_idx = cq_idx % priv->rx_ring_num;
 		rx_cq = priv->rx_cq[cq_idx];
 		cq->vector = rx_cq->vector;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 7e703be..12c99a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1733,6 +1733,13 @@ int mlx4_en_start_port(struct net_device *dev)
 		udp_tunnel_get_rx_info(dev);
 
 	priv->port_up = true;
+
+	/* Process all completions if exist to prevent
+	 * the queues freezing if they are full
+	 */
+	for (i = 0; i < priv->rx_ring_num; i++)
+		napi_schedule(&priv->rx_cq[i]->napi);
+
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
 
@@ -1910,8 +1917,9 @@ static void mlx4_en_clear_stats(struct net_device *dev)
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int i;
 
-	if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1))
-		en_dbg(HW, priv, "Failed dumping statistics\n");
+	if (!mlx4_is_slave(mdev->dev))
+		if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1))
+			en_dbg(HW, priv, "Failed dumping statistics\n");
 
 	memset(&priv->pstats, 0, sizeof(priv->pstats));
 	memset(&priv->pkstats, 0, sizeof(priv->pkstats));
@@ -2194,6 +2202,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 
 	if (!shutdown)
 		free_netdev(dev);
+	dev->ethtool_ops = NULL;
 }
 
 static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 5aa8b75..59473a0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -166,7 +166,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 		return PTR_ERR(mailbox);
 	err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0,
 			   MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
-			   MLX4_CMD_WRAPPED);
+			   MLX4_CMD_NATIVE);
 	if (err)
 		goto out;
 
@@ -322,7 +322,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 		err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma,
 				   in_mod | MLX4_DUMP_ETH_STATS_FLOW_CONTROL,
 				   0, MLX4_CMD_DUMP_ETH_STATS,
-				   MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
+				   MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 		if (err)
 			goto out;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index b66e03d..c06346a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -118,6 +118,29 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
 	return !loopback_ok;
 }
 
+static int mlx4_en_test_interrupts(struct mlx4_en_priv *priv)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int err = 0;
+	int i = 0;
+
+	err = mlx4_test_async(mdev->dev);
+	/* When not in MSI_X or slave, test only async */
+	if (!(mdev->dev->flags & MLX4_FLAG_MSI_X) || mlx4_is_slave(mdev->dev))
+		return err;
+
+	/* A loop over all completion vectors of current port,
+	 * for each vector check whether it works by mapping command
+	 * completions to that vector and performing a NOP command
+	 */
+	for (i = 0; i < priv->rx_ring_num; i++) {
+		err = mlx4_test_interrupt(mdev->dev, priv->rx_cq[i]->vector);
+		if (err)
+			break;
+	}
+
+	return err;
+}
 
 static int mlx4_en_test_link(struct mlx4_en_priv *priv)
 {
@@ -151,7 +174,6 @@ static int mlx4_en_test_speed(struct mlx4_en_priv *priv)
 void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_dev *mdev = priv->mdev;
 	int i, carrier_ok;
 
 	memset(buf, 0, sizeof(u64) * MLX4_EN_NUM_SELF_TEST);
@@ -177,7 +199,7 @@ void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf)
 			netif_carrier_on(dev);
 
 	}
-	buf[0] = mlx4_test_interrupts(mdev->dev);
+	buf[0] = mlx4_en_test_interrupts(priv);
 	buf[1] = mlx4_en_test_link(priv);
 	buf[2] = mlx4_en_test_speed(priv);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index cf8f8a7..cd3638e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -1361,53 +1361,49 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
 	kfree(priv->eq_table.uar_map);
 }
 
-/* A test that verifies that we can accept interrupts on all
- * the irq vectors of the device.
+/* A test that verifies that we can accept interrupts
+ * on the vector allocated for asynchronous events
+ */
+int mlx4_test_async(struct mlx4_dev *dev)
+{
+	return mlx4_NOP(dev);
+}
+EXPORT_SYMBOL(mlx4_test_async);
+
+/* A test that verifies that we can accept interrupts
+ * on the given irq vector of the tested port.
  * Interrupts are checked using the NOP command.
  */
-int mlx4_test_interrupts(struct mlx4_dev *dev)
+int mlx4_test_interrupt(struct mlx4_dev *dev, int vector)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	int i;
 	int err;
 
-	err = mlx4_NOP(dev);
-	/* When not in MSI_X, there is only one irq to check */
-	if (!(dev->flags & MLX4_FLAG_MSI_X) || mlx4_is_slave(dev))
-		return err;
+	/* Temporary use polling for command completions */
+	mlx4_cmd_use_polling(dev);
 
-	/* A loop over all completion vectors, for each vector we will check
-	 * whether it works by mapping command completions to that vector
-	 * and performing a NOP command
-	 */
-	for(i = 0; !err && (i < dev->caps.num_comp_vectors); ++i) {
-		/* Make sure request_irq was called */
-		if (!priv->eq_table.eq[i].have_irq)
-			continue;
-
-		/* Temporary use polling for command completions */
-		mlx4_cmd_use_polling(dev);
-
-		/* Map the new eq to handle all asynchronous events */
-		err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
-				  priv->eq_table.eq[i].eqn);
-		if (err) {
-			mlx4_warn(dev, "Failed mapping eq for interrupt test\n");
-			mlx4_cmd_use_events(dev);
-			break;
-		}
-
-		/* Go back to using events */
-		mlx4_cmd_use_events(dev);
-		err = mlx4_NOP(dev);
+	/* Map the new eq to handle all asynchronous events */
+	err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
+			  priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn);
+	if (err) {
+		mlx4_warn(dev, "Failed mapping eq for interrupt test\n");
+		goto out;
 	}
 
+	/* Go back to using events */
+	mlx4_cmd_use_events(dev);
+	err = mlx4_NOP(dev);
+
 	/* Return to default */
+	mlx4_cmd_use_polling(dev);
+out:
 	mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
 		    priv->eq_table.eq[MLX4_EQ_ASYNC].eqn);
+	mlx4_cmd_use_events(dev);
+
 	return err;
 }
-EXPORT_SYMBOL(mlx4_test_interrupts);
+EXPORT_SYMBOL(mlx4_test_interrupt);
 
 bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index c41ab31..84bab9f0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -49,9 +49,9 @@ enum {
 extern void __buggy_use_of_MLX4_GET(void);
 extern void __buggy_use_of_MLX4_PUT(void);
 
-static bool enable_qos = true;
+static bool enable_qos;
 module_param(enable_qos, bool, 0444);
-MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: on)");
+MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: off)");
 
 #define MLX4_GET(dest, source, offset)				      \
 	do {							      \
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7183ac4..6f4e67b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1102,6 +1102,14 @@ static int __set_port_type(struct mlx4_port_info *info,
 	int i;
 	int err = 0;
 
+	if ((port_type & mdev->caps.supported_type[info->port]) != port_type) {
+		mlx4_err(mdev,
+			 "Requested port type for port %d is not supported on this HCA\n",
+			 info->port);
+		err = -EINVAL;
+		goto err_sup;
+	}
+
 	mlx4_stop_sense(mdev);
 	mutex_lock(&priv->port_mutex);
 	info->tmp_type = port_type;
@@ -1147,7 +1155,7 @@ static int __set_port_type(struct mlx4_port_info *info,
 out:
 	mlx4_start_sense(mdev);
 	mutex_unlock(&priv->port_mutex);
-
+err_sup:
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index e4878f3..88ee7d8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -145,9 +145,10 @@ enum mlx4_resource {
 	RES_MTT,
 	RES_MAC,
 	RES_VLAN,
-	RES_EQ,
+	RES_NPORT_ID,
 	RES_COUNTER,
 	RES_FS_RULE,
+	RES_EQ,
 	MLX4_NUM_OF_RESOURCE_TYPE
 };
 
@@ -1329,8 +1330,6 @@ int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
 			       struct mlx4_cmd_info *cmd);
 int mlx4_common_set_vlan_fltr(struct mlx4_dev *dev, int function,
 				     int port, void *buf);
-int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave, u32 in_mod,
-				struct mlx4_cmd_mailbox *outbox);
 int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
 				   struct mlx4_vhcr *vhcr,
 				   struct mlx4_cmd_mailbox *inbox,
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index c5b2064..b656dd5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -1728,24 +1728,13 @@ int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
 	return err;
 }
 
-int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave,
-			       u32 in_mod, struct mlx4_cmd_mailbox *outbox)
-{
-	return mlx4_cmd_box(dev, 0, outbox->dma, in_mod, 0,
-			    MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
-			    MLX4_CMD_NATIVE);
-}
-
 int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
 				struct mlx4_vhcr *vhcr,
 				struct mlx4_cmd_mailbox *inbox,
 				struct mlx4_cmd_mailbox *outbox,
 				struct mlx4_cmd_info *cmd)
 {
-	if (slave != dev->caps.function)
-		return 0;
-	return mlx4_common_dump_eth_stats(dev, slave,
-					  vhcr->in_modifier, outbox);
+	return 0;
 }
 
 int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 84d7857..c548bea 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1605,13 +1605,14 @@ static int eq_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
 			r->com.from_state = r->com.state;
 			r->com.to_state = state;
 			r->com.state = RES_EQ_BUSY;
-			if (eq)
-				*eq = r;
 		}
 	}
 
 	spin_unlock_irq(mlx4_tlock(dev));
 
+	if (!err && eq)
+		*eq = r;
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 6cb3830..2c6e3c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -41,6 +41,13 @@
 
 #include "mlx5_core.h"
 
+struct mlx5_db_pgdir {
+	struct list_head	list;
+	unsigned long	       *bitmap;
+	__be32		       *db_page;
+	dma_addr_t		db_dma;
+};
+
 /* Handling for queue buffers -- we allocate a bunch of memory and
  * register it in a memory region at HCA virtual address 0.
  */
@@ -102,17 +109,28 @@ EXPORT_SYMBOL_GPL(mlx5_buf_free);
 static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
 						 int node)
 {
+	u32 db_per_page = PAGE_SIZE / cache_line_size();
 	struct mlx5_db_pgdir *pgdir;
 
 	pgdir = kzalloc(sizeof(*pgdir), GFP_KERNEL);
 	if (!pgdir)
 		return NULL;
 
-	bitmap_fill(pgdir->bitmap, MLX5_DB_PER_PAGE);
+	pgdir->bitmap = kcalloc(BITS_TO_LONGS(db_per_page),
+				sizeof(unsigned long),
+				GFP_KERNEL);
+
+	if (!pgdir->bitmap) {
+		kfree(pgdir);
+		return NULL;
+	}
+
+	bitmap_fill(pgdir->bitmap, db_per_page);
 
 	pgdir->db_page = mlx5_dma_zalloc_coherent_node(dev, PAGE_SIZE,
 						       &pgdir->db_dma, node);
 	if (!pgdir->db_page) {
+		kfree(pgdir->bitmap);
 		kfree(pgdir);
 		return NULL;
 	}
@@ -123,18 +141,19 @@ static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
 static int mlx5_alloc_db_from_pgdir(struct mlx5_db_pgdir *pgdir,
 				    struct mlx5_db *db)
 {
+	u32 db_per_page = PAGE_SIZE / cache_line_size();
 	int offset;
 	int i;
 
-	i = find_first_bit(pgdir->bitmap, MLX5_DB_PER_PAGE);
-	if (i >= MLX5_DB_PER_PAGE)
+	i = find_first_bit(pgdir->bitmap, db_per_page);
+	if (i >= db_per_page)
 		return -ENOMEM;
 
 	__clear_bit(i, pgdir->bitmap);
 
 	db->u.pgdir = pgdir;
 	db->index   = i;
-	offset = db->index * L1_CACHE_BYTES;
+	offset = db->index * cache_line_size();
 	db->db      = pgdir->db_page + offset / sizeof(*pgdir->db_page);
 	db->dma     = pgdir->db_dma  + offset;
 
@@ -181,14 +200,16 @@ EXPORT_SYMBOL_GPL(mlx5_db_alloc);
 
 void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 {
+	u32 db_per_page = PAGE_SIZE / cache_line_size();
 	mutex_lock(&dev->priv.pgdir_mutex);
 
 	__set_bit(db->index, db->u.pgdir->bitmap);
 
-	if (bitmap_full(db->u.pgdir->bitmap, MLX5_DB_PER_PAGE)) {
+	if (bitmap_full(db->u.pgdir->bitmap, db_per_page)) {
 		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
 				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
 		list_del(&db->u.pgdir->list);
+		kfree(db->u.pgdir->bitmap);
 		kfree(db->u.pgdir);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 460363b..7a43502 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -85,6 +85,9 @@
 #define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(128)
 
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
+#define MLX5E_DEFAULT_LRO_TIMEOUT                       32
+#define MLX5E_LRO_TIMEOUT_ARR_SIZE                      4
+
 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC      0x10
 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3
 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS      0x20
@@ -221,6 +224,7 @@ struct mlx5e_params {
 	struct ieee_ets ets;
 #endif
 	bool rx_am_enabled;
+	u32 lro_timeout;
 };
 
 struct mlx5e_tstamp {
@@ -888,5 +892,6 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
 void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
 struct rtnl_link_stats64 *
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
+u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout);
 
 #endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7eaf380..f4c687c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1971,9 +1971,7 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
 		 (priv->params.lro_wqe_sz -
 		  ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
-	MLX5_SET(tirc, tirc, lro_timeout_period_usecs,
-		 MLX5_CAP_ETH(priv->mdev,
-			      lro_timer_supported_periods[2]));
+	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout);
 }
 
 void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
@@ -3401,6 +3399,18 @@ static void mlx5e_query_min_inline(struct mlx5_core_dev *mdev,
 	}
 }
 
+u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
+{
+	int i;
+
+	/* The supported periods are organized in ascending order */
+	for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++)
+		if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout)
+			break;
+
+	return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
+}
+
 static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 					struct net_device *netdev,
 					const struct mlx5e_profile *profile,
@@ -3419,6 +3429,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 	priv->profile                      = profile;
 	priv->ppriv                        = ppriv;
 
+	priv->params.lro_timeout =
+		mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+
 	priv->params.log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 
 	/* set CQE compression */
@@ -4035,7 +4048,6 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv)
 	const struct mlx5e_profile *profile = priv->profile;
 	struct net_device *netdev = priv->netdev;
 
-	unregister_netdev(netdev);
 	destroy_workqueue(priv->wq);
 	if (profile->cleanup)
 		profile->cleanup(priv);
@@ -4052,6 +4064,7 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 	for (vport = 1; vport < total_vfs; vport++)
 		mlx5_eswitch_unregister_vport_rep(esw, vport);
 
+	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
 	mlx5e_destroy_netdev(mdev, priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3c97da1..7fe6559e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -457,6 +457,7 @@ void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw,
 	struct mlx5e_priv *priv = rep->priv_data;
 	struct net_device *netdev = priv->netdev;
 
+	unregister_netdev(netdev);
 	mlx5e_detach_netdev(esw->dev, netdev);
 	mlx5e_destroy_netdev(esw->dev, priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index abbf2c3..be1f733 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -931,8 +931,8 @@ static void esw_vport_change_handler(struct work_struct *work)
 	mutex_unlock(&esw->state_lock);
 }
 
-static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
-					struct mlx5_vport *vport)
+static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
+				       struct mlx5_vport *vport)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_group *vlan_grp = NULL;
@@ -949,9 +949,11 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 	int table_size = 2;
 	int err = 0;
 
-	if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support) ||
-	    !IS_ERR_OR_NULL(vport->egress.acl))
-		return;
+	if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support))
+		return -EOPNOTSUPP;
+
+	if (!IS_ERR_OR_NULL(vport->egress.acl))
+		return 0;
 
 	esw_debug(dev, "Create vport[%d] egress ACL log_max_size(%d)\n",
 		  vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size));
@@ -959,12 +961,12 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch egress flow namespace\n");
-		return;
+		return -EIO;
 	}
 
 	flow_group_in = mlx5_vzalloc(inlen);
 	if (!flow_group_in)
-		return;
+		return -ENOMEM;
 
 	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
 	if (IS_ERR(acl)) {
@@ -1009,6 +1011,7 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 		mlx5_destroy_flow_group(vlan_grp);
 	if (err && !IS_ERR_OR_NULL(acl))
 		mlx5_destroy_flow_table(acl);
+	return err;
 }
 
 static void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
@@ -1041,8 +1044,8 @@ static void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
 	vport->egress.acl = NULL;
 }
 
-static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
-					 struct mlx5_vport *vport)
+static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
+					struct mlx5_vport *vport)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_core_dev *dev = esw->dev;
@@ -1063,9 +1066,11 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	int table_size = 4;
 	int err = 0;
 
-	if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support) ||
-	    !IS_ERR_OR_NULL(vport->ingress.acl))
-		return;
+	if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
+		return -EOPNOTSUPP;
+
+	if (!IS_ERR_OR_NULL(vport->ingress.acl))
+		return 0;
 
 	esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n",
 		  vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));
@@ -1073,12 +1078,12 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n");
-		return;
+		return -EIO;
 	}
 
 	flow_group_in = mlx5_vzalloc(inlen);
 	if (!flow_group_in)
-		return;
+		return -ENOMEM;
 
 	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
 	if (IS_ERR(acl)) {
@@ -1167,6 +1172,7 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	}
 
 	kvfree(flow_group_in);
+	return err;
 }
 
 static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
@@ -1225,7 +1231,13 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 		return 0;
 	}
 
-	esw_vport_enable_ingress_acl(esw, vport);
+	err = esw_vport_enable_ingress_acl(esw, vport);
+	if (err) {
+		mlx5_core_warn(esw->dev,
+			       "failed to enable ingress acl (%d) on vport[%d]\n",
+			       err, vport->vport);
+		return err;
+	}
 
 	esw_debug(esw->dev,
 		  "vport[%d] configure ingress rules, vlan(%d) qos(%d)\n",
@@ -1299,7 +1311,13 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 		return 0;
 	}
 
-	esw_vport_enable_egress_acl(esw, vport);
+	err = esw_vport_enable_egress_acl(esw, vport);
+	if (err) {
+		mlx5_core_warn(esw->dev,
+			       "failed to enable egress acl (%d) on vport[%d]\n",
+			       err, vport->vport);
+		return err;
+	}
 
 	esw_debug(esw->dev,
 		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 5da2cc8..8969604 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -436,6 +436,9 @@ static void del_flow_group(struct fs_node *node)
 	fs_get_obj(ft, fg->node.parent);
 	dev = get_dev(&ft->node);
 
+	if (ft->autogroup.active)
+		ft->autogroup.num_groups--;
+
 	if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id))
 		mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n",
 			       fg->id, ft->id);
@@ -879,7 +882,7 @@ static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table *
 	tree_init_node(&fg->node, !is_auto_fg, del_flow_group);
 	tree_add_node(&fg->node, &ft->node);
 	/* Add node to group list */
-	list_add(&fg->node.list, ft->node.children.prev);
+	list_add(&fg->node.list, prev_fg);
 
 	return fg;
 }
@@ -893,7 +896,7 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
 		return ERR_PTR(-EPERM);
 
 	lock_ref_node(&ft->node);
-	fg = create_flow_group_common(ft, fg_in, &ft->node.children, false);
+	fg = create_flow_group_common(ft, fg_in, ft->node.children.prev, false);
 	unlock_ref_node(&ft->node);
 
 	return fg;
@@ -1012,7 +1015,7 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft,
 						u32 *match_criteria)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct list_head *prev = &ft->node.children;
+	struct list_head *prev = ft->node.children.prev;
 	unsigned int candidate_index = 0;
 	struct mlx5_flow_group *fg;
 	void *match_criteria_addr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 3a9195b..3b026c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -218,6 +218,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
 		goto err_out;
 
 	if (aging) {
+		counter->cache.lastuse = jiffies;
 		counter->aging = true;
 
 		spin_lock(&fc_stats->addlist_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 1a05fb9..5bcf934 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -61,10 +61,15 @@ enum {
 enum {
 	MLX5_NIC_IFC_FULL		= 0,
 	MLX5_NIC_IFC_DISABLED		= 1,
-	MLX5_NIC_IFC_NO_DRAM_NIC	= 2
+	MLX5_NIC_IFC_NO_DRAM_NIC	= 2,
+	MLX5_NIC_IFC_INVALID		= 3
 };
 
-static u8 get_nic_interface(struct mlx5_core_dev *dev)
+enum {
+	MLX5_DROP_NEW_HEALTH_WORK,
+};
+
+static u8 get_nic_state(struct mlx5_core_dev *dev)
 {
 	return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3;
 }
@@ -97,7 +102,7 @@ static int in_fatal(struct mlx5_core_dev *dev)
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
 
-	if (get_nic_interface(dev) == MLX5_NIC_IFC_DISABLED)
+	if (get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
 		return 1;
 
 	if (ioread32be(&h->fw_ver) == 0xffffffff)
@@ -127,7 +132,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev)
 
 static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 {
-	u8 nic_interface = get_nic_interface(dev);
+	u8 nic_interface = get_nic_state(dev);
 
 	switch (nic_interface) {
 	case MLX5_NIC_IFC_FULL:
@@ -149,8 +154,34 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 	mlx5_disable_device(dev);
 }
 
+static void health_recover(struct work_struct *work)
+{
+	struct mlx5_core_health *health;
+	struct delayed_work *dwork;
+	struct mlx5_core_dev *dev;
+	struct mlx5_priv *priv;
+	u8 nic_state;
+
+	dwork = container_of(work, struct delayed_work, work);
+	health = container_of(dwork, struct mlx5_core_health, recover_work);
+	priv = container_of(health, struct mlx5_priv, health);
+	dev = container_of(priv, struct mlx5_core_dev, priv);
+
+	nic_state = get_nic_state(dev);
+	if (nic_state == MLX5_NIC_IFC_INVALID) {
+		dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n");
+		return;
+	}
+
+	dev_err(&dev->pdev->dev, "starting health recovery flow\n");
+	mlx5_recover_device(dev);
+}
+
+/* How much time to wait until health resetting the driver (in msecs) */
+#define MLX5_RECOVERY_DELAY_MSECS 60000
 static void health_care(struct work_struct *work)
 {
+	unsigned long recover_delay = msecs_to_jiffies(MLX5_RECOVERY_DELAY_MSECS);
 	struct mlx5_core_health *health;
 	struct mlx5_core_dev *dev;
 	struct mlx5_priv *priv;
@@ -160,6 +191,14 @@ static void health_care(struct work_struct *work)
 	dev = container_of(priv, struct mlx5_core_dev, priv);
 	mlx5_core_warn(dev, "handling bad device here\n");
 	mlx5_handle_bad_state(dev);
+
+	spin_lock(&health->wq_lock);
+	if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
+		schedule_delayed_work(&health->recover_work, recover_delay);
+	else
+		dev_err(&dev->pdev->dev,
+			"new health works are not permitted at this stage\n");
+	spin_unlock(&health->wq_lock);
 }
 
 static const char *hsynd_str(u8 synd)
@@ -272,7 +311,13 @@ static void poll_health(unsigned long data)
 	if (in_fatal(dev) && !health->sick) {
 		health->sick = true;
 		print_health_info(dev);
-		schedule_work(&health->work);
+		spin_lock(&health->wq_lock);
+		if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
+			queue_work(health->wq, &health->work);
+		else
+			dev_err(&dev->pdev->dev,
+				"new health works are not permitted at this stage\n");
+		spin_unlock(&health->wq_lock);
 	}
 }
 
@@ -281,6 +326,8 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 	struct mlx5_core_health *health = &dev->priv.health;
 
 	init_timer(&health->timer);
+	health->sick = 0;
+	clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
 	health->health = &dev->iseg->health;
 	health->health_counter = &dev->iseg->health_counter;
 
@@ -297,11 +344,22 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev)
 	del_timer_sync(&health->timer);
 }
 
+void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	spin_lock(&health->wq_lock);
+	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	spin_unlock(&health->wq_lock);
+	cancel_delayed_work_sync(&health->recover_work);
+	cancel_work_sync(&health->work);
+}
+
 void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 
-	flush_work(&health->work);
+	destroy_workqueue(health->wq);
 }
 
 int mlx5_health_init(struct mlx5_core_dev *dev)
@@ -316,9 +374,13 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 
 	strcpy(name, "mlx5_health");
 	strcat(name, dev_name(&dev->pdev->dev));
+	health->wq = create_singlethread_workqueue(name);
 	kfree(name);
-
+	if (!health->wq)
+		return -ENOMEM;
+	spin_lock_init(&health->wq_lock);
 	INIT_WORK(&health->work, health_care);
+	INIT_DELAYED_WORK(&health->recover_work, health_recover);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d9c3c70..d5433c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -844,12 +844,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	struct pci_dev *pdev = dev->pdev;
 	int err;
 
-	err = mlx5_query_hca_caps(dev);
-	if (err) {
-		dev_err(&pdev->dev, "query hca failed\n");
-		goto out;
-	}
-
 	err = mlx5_query_board_id(dev);
 	if (err) {
 		dev_err(&pdev->dev, "query board id failed\n");
@@ -1023,6 +1017,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 
 	mlx5_start_health_poll(dev);
 
+	err = mlx5_query_hca_caps(dev);
+	if (err) {
+		dev_err(&pdev->dev, "query hca failed\n");
+		goto err_stop_poll;
+	}
+
 	if (boot && mlx5_init_once(dev, priv)) {
 		dev_err(&pdev->dev, "sw objs init failed\n");
 		goto err_stop_poll;
@@ -1313,10 +1313,16 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 	struct mlx5_priv *priv = &dev->priv;
 
 	dev_info(&pdev->dev, "%s was called\n", __func__);
+
 	mlx5_enter_error_state(dev);
 	mlx5_unload_one(dev, priv, false);
-	pci_save_state(pdev);
-	mlx5_pci_disable_device(dev);
+	/* In case of kernel call save the pci state and drain health wq */
+	if (state) {
+		pci_save_state(pdev);
+		mlx5_drain_health_wq(dev);
+		mlx5_pci_disable_device(dev);
+	}
+
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
 }
@@ -1373,11 +1379,6 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-void mlx5_disable_device(struct mlx5_core_dev *dev)
-{
-	mlx5_pci_err_detected(dev->pdev, 0);
-}
-
 static void mlx5_pci_resume(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
@@ -1427,6 +1428,18 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table);
 
+void mlx5_disable_device(struct mlx5_core_dev *dev)
+{
+	mlx5_pci_err_detected(dev->pdev, 0);
+}
+
+void mlx5_recover_device(struct mlx5_core_dev *dev)
+{
+	mlx5_pci_disable_device(dev);
+	if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED)
+		mlx5_pci_resume(dev->pdev);
+}
+
 static struct pci_driver mlx5_core_driver = {
 	.name           = DRIVER_NAME,
 	.id_table       = mlx5_core_pci_table,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 3d0cfb9..187662c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -83,6 +83,7 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
+void mlx5_recover_device(struct mlx5_core_dev *dev);
 int mlx5_sriov_init(struct mlx5_core_dev *dev);
 void mlx5_sriov_cleanup(struct mlx5_core_dev *dev);
 int mlx5_sriov_attach(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index cc4fd61..a57d5a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -209,6 +209,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 {
 	struct page *page;
+	u64 zero_addr = 1;
 	u64 addr;
 	int err;
 	int nid = dev_to_node(&dev->pdev->dev);
@@ -218,26 +219,35 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 		mlx5_core_warn(dev, "failed to allocate page\n");
 		return -ENOMEM;
 	}
+map:
 	addr = dma_map_page(&dev->pdev->dev, page, 0,
 			    PAGE_SIZE, DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(&dev->pdev->dev, addr)) {
 		mlx5_core_warn(dev, "failed dma mapping page\n");
 		err = -ENOMEM;
-		goto out_alloc;
+		goto err_mapping;
 	}
+
+	/* Firmware doesn't support page with physical address 0 */
+	if (addr == 0) {
+		zero_addr = addr;
+		goto map;
+	}
+
 	err = insert_page(dev, addr, page, func_id);
 	if (err) {
 		mlx5_core_err(dev, "failed to track allocated page\n");
-		goto out_mapping;
+		dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
 	}
 
-	return 0;
+err_mapping:
+	if (err)
+		__free_page(page);
 
-out_mapping:
-	dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
-
-out_alloc:
-	__free_page(page);
+	if (zero_addr == 0)
+		dma_unmap_page(&dev->pdev->dev, zero_addr, PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index e742bd4..912f71f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1838,11 +1838,17 @@ static const struct mlxsw_bus mlxsw_pci_bus = {
 	.cmd_exec		= mlxsw_pci_cmd_exec,
 };
 
-static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci)
+static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
+			      const struct pci_device_id *id)
 {
 	unsigned long end;
 
 	mlxsw_pci_write32(mlxsw_pci, SW_RESET, MLXSW_PCI_SW_RESET_RST_BIT);
+	if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) {
+		msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
+		return 0;
+	}
+
 	wmb(); /* reset needs to be written before we read control register */
 	end = jiffies + msecs_to_jiffies(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
 	do {
@@ -1909,7 +1915,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->pdev = pdev;
 	pci_set_drvdata(pdev, mlxsw_pci);
 
-	err = mlxsw_pci_sw_reset(mlxsw_pci);
+	err = mlxsw_pci_sw_reset(mlxsw_pci, id);
 	if (err) {
 		dev_err(&pdev->dev, "Software reset failed\n");
 		goto err_sw_reset;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 78fc557d..4573da2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -320,6 +320,8 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp,
 						lpm_tree);
 	if (err)
 		goto err_left_struct_set;
+	memcpy(&lpm_tree->prefix_usage, prefix_usage,
+	       sizeof(lpm_tree->prefix_usage));
 	return lpm_tree;
 
 err_left_struct_set:
@@ -343,7 +345,8 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
 
 	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
 		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
-		if (lpm_tree->proto == proto &&
+		if (lpm_tree->ref_count != 0 &&
+		    lpm_tree->proto == proto &&
 		    mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage,
 					     prefix_usage))
 			goto inc_ref_count;
@@ -1820,19 +1823,17 @@ static int mlxsw_sp_router_fib4_add(struct mlxsw_sp *mlxsw_sp,
 	return err;
 }
 
-static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
-				    struct fib_entry_notifier_info *fen_info)
+static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
+				     struct fib_entry_notifier_info *fen_info)
 {
 	struct mlxsw_sp_fib_entry *fib_entry;
 
 	if (mlxsw_sp->router.aborted)
-		return 0;
+		return;
 
 	fib_entry = mlxsw_sp_fib_entry_find(mlxsw_sp, fen_info);
-	if (!fib_entry) {
-		dev_warn(mlxsw_sp->bus_info->dev, "Failed to find FIB4 entry being removed.\n");
-		return -ENOENT;
-	}
+	if (!fib_entry)
+		return;
 
 	if (fib_entry->ref_count == 1) {
 		mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry);
@@ -1840,7 +1841,6 @@ static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry);
-	return 0;
 }
 
 static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
@@ -1862,7 +1862,8 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
 	if (err)
 		return err;
 
-	mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4, 0);
+	mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4,
+			     MLXSW_SP_LPM_TREE_MIN);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index c0c23e2..92bda87 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1088,6 +1088,7 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 err_port_admin_status_set:
 err_port_mtu_set:
 err_port_speed_set:
+	mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
 err_port_swid_set:
 err_port_system_port_mapping_set:
 port_not_usable:
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 1e8339a..32f2a45 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -107,4 +107,7 @@
 	---help---
 	  This enables the support for ...
 
+config QED_RDMA
+	bool
+
 endif # NET_VENDOR_QLOGIC
diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile
index cda0af7..967acf3 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -5,4 +5,4 @@
 	 qed_selftest.o qed_dcbx.o qed_debug.o
 qed-$(CONFIG_QED_SRIOV) += qed_sriov.o qed_vf.o
 qed-$(CONFIG_QED_LL2) += qed_ll2.o
-qed-$(CONFIG_INFINIBAND_QEDR) += qed_roce.o
+qed-$(CONFIG_QED_RDMA) += qed_roce.o
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 82370a1..0c42c24 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -47,13 +47,8 @@
 #define TM_ALIGN        BIT(TM_SHIFT)
 #define TM_ELEM_SIZE    4
 
-/* ILT constants */
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
 /* For RoCE we configure to 64K to cover for RoCE max tasks 256K purpose. */
-#define ILT_DEFAULT_HW_P_SIZE		4
-#else
-#define ILT_DEFAULT_HW_P_SIZE		3
-#endif
+#define ILT_DEFAULT_HW_P_SIZE	(IS_ENABLED(CONFIG_QED_RDMA) ? 4 : 3)
 
 #define ILT_PAGE_IN_BYTES(hw_p_size)	(1U << ((hw_p_size) + 12))
 #define ILT_CFG_REG(cli, reg)	PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
@@ -349,14 +344,14 @@ static struct qed_tid_seg *qed_cxt_tid_seg_info(struct qed_hwfn *p_hwfn,
 	return NULL;
 }
 
-void qed_cxt_set_srq_count(struct qed_hwfn *p_hwfn, u32 num_srqs)
+static void qed_cxt_set_srq_count(struct qed_hwfn *p_hwfn, u32 num_srqs)
 {
 	struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
 
 	p_mgr->srq_count = num_srqs;
 }
 
-u32 qed_cxt_get_srq_count(struct qed_hwfn *p_hwfn)
+static u32 qed_cxt_get_srq_count(struct qed_hwfn *p_hwfn)
 {
 	struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
 
@@ -1804,8 +1799,8 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, struct qed_cxt_info *p_info)
 	return 0;
 }
 
-void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
-			    struct qed_rdma_pf_params *p_params)
+static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
+				   struct qed_rdma_pf_params *p_params)
 {
 	u32 num_cons, num_tasks, num_qps, num_mrs, num_srqs;
 	enum protocol_type proto;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 130da1c..a4789a9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -1190,6 +1190,7 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn,
 	if (!dcbx_info)
 		return -ENOMEM;
 
+	memset(dcbx_info, 0, sizeof(*dcbx_info));
 	rc = qed_dcbx_query_params(p_hwfn, dcbx_info, QED_DCBX_OPERATIONAL_MIB);
 	if (rc) {
 		kfree(dcbx_info);
@@ -1225,6 +1226,7 @@ static struct qed_dcbx_get *qed_dcbnl_get_dcbx(struct qed_hwfn *hwfn,
 	if (!dcbx_info)
 		return NULL;
 
+	memset(dcbx_info, 0, sizeof(*dcbx_info));
 	if (qed_dcbx_query_params(hwfn, dcbx_info, type)) {
 		kfree(dcbx_info);
 		return NULL;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 88e7d5b..68f19ca 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -405,7 +405,7 @@ struct phy_defs {
 /***************************** Constant Arrays *******************************/
 
 /* Debug arrays */
-static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {0} };
+static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {NULL} };
 
 /* Chip constant definitions array */
 static struct chip_defs s_chip_defs[MAX_CHIP_IDS] = {
@@ -4028,10 +4028,10 @@ static enum dbg_status qed_mcp_trace_read_meta(struct qed_hwfn *p_hwfn,
 }
 
 /* Dump MCP Trace */
-enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
-				   struct qed_ptt *p_ptt,
-				   u32 *dump_buf,
-				   bool dump, u32 *num_dumped_dwords)
+static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
+					  struct qed_ptt *p_ptt,
+					  u32 *dump_buf,
+					  bool dump, u32 *num_dumped_dwords)
 {
 	u32 trace_data_grc_addr, trace_data_size_bytes, trace_data_size_dwords;
 	u32 trace_meta_size_dwords, running_bundle_id, offset = 0;
@@ -4130,10 +4130,10 @@ enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
 }
 
 /* Dump GRC FIFO */
-enum dbg_status qed_reg_fifo_dump(struct qed_hwfn *p_hwfn,
-				  struct qed_ptt *p_ptt,
-				  u32 *dump_buf,
-				  bool dump, u32 *num_dumped_dwords)
+static enum dbg_status qed_reg_fifo_dump(struct qed_hwfn *p_hwfn,
+					 struct qed_ptt *p_ptt,
+					 u32 *dump_buf,
+					 bool dump, u32 *num_dumped_dwords)
 {
 	u32 offset = 0, dwords_read, size_param_offset;
 	bool fifo_has_data;
@@ -4192,10 +4192,10 @@ enum dbg_status qed_reg_fifo_dump(struct qed_hwfn *p_hwfn,
 }
 
 /* Dump IGU FIFO */
-enum dbg_status qed_igu_fifo_dump(struct qed_hwfn *p_hwfn,
-				  struct qed_ptt *p_ptt,
-				  u32 *dump_buf,
-				  bool dump, u32 *num_dumped_dwords)
+static enum dbg_status qed_igu_fifo_dump(struct qed_hwfn *p_hwfn,
+					 struct qed_ptt *p_ptt,
+					 u32 *dump_buf,
+					 bool dump, u32 *num_dumped_dwords)
 {
 	u32 offset = 0, dwords_read, size_param_offset;
 	bool fifo_has_data;
@@ -4255,10 +4255,11 @@ enum dbg_status qed_igu_fifo_dump(struct qed_hwfn *p_hwfn,
 }
 
 /* Protection Override dump */
-enum dbg_status qed_protection_override_dump(struct qed_hwfn *p_hwfn,
-					     struct qed_ptt *p_ptt,
-					     u32 *dump_buf,
-					     bool dump, u32 *num_dumped_dwords)
+static enum dbg_status qed_protection_override_dump(struct qed_hwfn *p_hwfn,
+						    struct qed_ptt *p_ptt,
+						    u32 *dump_buf,
+						    bool dump,
+						    u32 *num_dumped_dwords)
 {
 	u32 offset = 0, size_param_offset, override_window_dwords;
 
@@ -6339,10 +6340,11 @@ enum dbg_status qed_print_fw_asserts_results(struct qed_hwfn *p_hwfn,
 }
 
 /* Wrapper for unifying the idle_chk and mcp_trace api */
-enum dbg_status qed_print_idle_chk_results_wrapper(struct qed_hwfn *p_hwfn,
-						   u32 *dump_buf,
-						   u32 num_dumped_dwords,
-						   char *results_buf)
+static enum dbg_status
+qed_print_idle_chk_results_wrapper(struct qed_hwfn *p_hwfn,
+				   u32 *dump_buf,
+				   u32 num_dumped_dwords,
+				   char *results_buf)
 {
 	u32 num_errors, num_warnnings;
 
@@ -6413,8 +6415,8 @@ static void qed_dbg_print_feature(u8 *p_text_buf, u32 text_size)
 
 #define QED_RESULTS_BUF_MIN_SIZE 16
 /* Generic function for decoding debug feature info */
-enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
-			       enum qed_dbg_features feature_idx)
+static enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
+				      enum qed_dbg_features feature_idx)
 {
 	struct qed_dbg_feature *feature =
 	    &p_hwfn->cdev->dbg_params.features[feature_idx];
@@ -6480,8 +6482,9 @@ enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
 }
 
 /* Generic function for performing the dump of a debug feature. */
-enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
-			     enum qed_dbg_features feature_idx)
+static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn,
+				    struct qed_ptt *p_ptt,
+				    enum qed_dbg_features feature_idx)
 {
 	struct qed_dbg_feature *feature =
 	    &p_hwfn->cdev->dbg_params.features[feature_idx];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 754f6a9..edae5fc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -497,12 +497,13 @@ int qed_resc_alloc(struct qed_dev *cdev)
 		if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
 			num_cons = qed_cxt_get_proto_cid_count(p_hwfn,
 							       PROTOCOLID_ROCE,
-							       0) * 2;
+							       NULL) * 2;
 			n_eqes += num_cons + 2 * MAX_NUM_VFS_BB;
 		} else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) {
 			num_cons =
 			    qed_cxt_get_proto_cid_count(p_hwfn,
-							PROTOCOLID_ISCSI, 0);
+							PROTOCOLID_ISCSI,
+							NULL);
 			n_eqes += 2 * num_cons;
 		}
 
@@ -1422,19 +1423,19 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
 	u32 *feat_num = p_hwfn->hw_info.feat_num;
 	int num_features = 1;
 
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
-	/* Roce CNQ each requires: 1 status block + 1 CNQ. We divide the
-	 * status blocks equally between L2 / RoCE but with consideration as
-	 * to how many l2 queues / cnqs we have
-	 */
-	if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
+	if (IS_ENABLED(CONFIG_QED_RDMA) &&
+	    p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
+		/* Roce CNQ each requires: 1 status block + 1 CNQ. We divide
+		 * the status blocks equally between L2 / RoCE but with
+		 * consideration as to how many l2 queues / cnqs we have.
+		 */
 		num_features++;
 
 		feat_num[QED_RDMA_CNQ] =
 			min_t(u32, RESC_NUM(p_hwfn, QED_SB) / num_features,
 			      RESC_NUM(p_hwfn, QED_RDMA_CNQ_RAM));
 	}
-#endif
+
 	feat_num[QED_PF_L2_QUE] = min_t(u32, RESC_NUM(p_hwfn, QED_SB) /
 						num_features,
 					RESC_NUM(p_hwfn, QED_L2_QUEUE));
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 02a8be2..63e1a1b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -38,6 +38,7 @@
 #include "qed_mcp.h"
 #include "qed_reg_addr.h"
 #include "qed_sp.h"
+#include "qed_roce.h"
 
 #define QED_LL2_RX_REGISTERED(ll2)	((ll2)->rx_queue.b_cb_registred)
 #define QED_LL2_TX_REGISTERED(ll2)	((ll2)->tx_queue.b_cb_registred)
@@ -140,11 +141,11 @@ static void qed_ll2_kill_buffers(struct qed_dev *cdev)
 		qed_ll2_dealloc_buffer(cdev, buffer);
 }
 
-void qed_ll2b_complete_rx_packet(struct qed_hwfn *p_hwfn,
-				 u8 connection_handle,
-				 struct qed_ll2_rx_packet *p_pkt,
-				 struct core_rx_fast_path_cqe *p_cqe,
-				 bool b_last_packet)
+static void qed_ll2b_complete_rx_packet(struct qed_hwfn *p_hwfn,
+					u8 connection_handle,
+					struct qed_ll2_rx_packet *p_pkt,
+					struct core_rx_fast_path_cqe *p_cqe,
+					bool b_last_packet)
 {
 	u16 packet_length = le16_to_cpu(p_cqe->packet_length);
 	struct qed_ll2_buffer *buffer = p_pkt->cookie;
@@ -515,7 +516,7 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie)
 	return rc;
 }
 
-void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
+static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 {
 	struct qed_ll2_info *p_ll2_conn = NULL;
 	struct qed_ll2_rx_packet *p_pkt = NULL;
@@ -537,8 +538,7 @@ void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 		if (!p_pkt)
 			break;
 
-		list_del(&p_pkt->list_entry);
-		list_add_tail(&p_pkt->list_entry, &p_rx->free_descq);
+		list_move_tail(&p_pkt->list_entry, &p_rx->free_descq);
 
 		rx_buf_addr = p_pkt->rx_buf_addr;
 		cookie = p_pkt->cookie;
@@ -992,9 +992,8 @@ static void qed_ll2_post_rx_buffer_notify_fw(struct qed_hwfn *p_hwfn,
 		p_posting_packet = list_first_entry(&p_rx->posting_descq,
 						    struct qed_ll2_rx_packet,
 						    list_entry);
-		list_del(&p_posting_packet->list_entry);
-		list_add_tail(&p_posting_packet->list_entry,
-			      &p_rx->active_descq);
+		list_move_tail(&p_posting_packet->list_entry,
+			       &p_rx->active_descq);
 		b_notify_fw = true;
 	}
 
@@ -1123,9 +1122,6 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
 	DMA_REGPAIR_LE(start_bd->addr, first_frag);
 	start_bd->nbytes = cpu_to_le16(first_frag_len);
 
-	SET_FIELD(start_bd->bd_flags.as_bitfield, CORE_TX_BD_FLAGS_ROCE_FLAV,
-		  type);
-
 	DP_VERBOSE(p_hwfn,
 		   (NETIF_MSG_TX_QUEUED | QED_MSG_LL2),
 		   "LL2 [q 0x%02x cid 0x%08x type 0x%08x] Tx Producer at [0x%04x] - set with a %04x bytes %02x BDs buffer at %08x:%08x\n",
@@ -1188,8 +1184,7 @@ static void qed_ll2_tx_packet_notify(struct qed_hwfn *p_hwfn,
 		if (!p_pkt)
 			break;
 
-		list_del(&p_pkt->list_entry);
-		list_add_tail(&p_pkt->list_entry, &p_tx->active_descq);
+		list_move_tail(&p_pkt->list_entry, &p_tx->active_descq);
 	}
 
 	SET_FIELD(db_msg.params, CORE_DB_DATA_DEST, DB_DEST_XCM);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index 80a5dc2..4e3d62a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -293,24 +293,4 @@ void qed_ll2_setup(struct qed_hwfn *p_hwfn,
  */
 void qed_ll2_free(struct qed_hwfn *p_hwfn,
 		  struct qed_ll2_info *p_ll2_connections);
-void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
-				     u8 connection_handle,
-				     void *cookie,
-				     dma_addr_t rx_buf_addr,
-				     u16 data_length,
-				     u8 data_length_error,
-				     u16 parse_flags,
-				     u16 vlan,
-				     u32 src_mac_addr_hi,
-				     u16 src_mac_addr_lo, bool b_last_packet);
-void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
-				     u8 connection_handle,
-				     void *cookie,
-				     dma_addr_t first_frag_addr,
-				     bool b_last_fragment, bool b_last_packet);
-void qed_ll2b_release_tx_gsi_packet(struct qed_hwfn *p_hwfn,
-				    u8 connection_handle,
-				    void *cookie,
-				    dma_addr_t first_frag_addr,
-				    bool b_last_fragment, bool b_last_packet);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 4ee3151..c418360 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -33,10 +33,8 @@
 #include "qed_hw.h"
 #include "qed_selftest.h"
 
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
 #define QED_ROCE_QPS			(8192)
 #define QED_ROCE_DPIS			(8)
-#endif
 
 static char version[] =
 	"QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n";
@@ -682,9 +680,7 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
 				  enum qed_int_mode int_mode)
 {
 	struct qed_sb_cnt_info sb_cnt_info;
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
-	int num_l2_queues;
-#endif
+	int num_l2_queues = 0;
 	int rc;
 	int i;
 
@@ -715,8 +711,9 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
 	cdev->int_params.fp_msix_cnt = cdev->int_params.out.num_vectors -
 				       cdev->num_hwfns;
 
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
-	num_l2_queues = 0;
+	if (!IS_ENABLED(CONFIG_QED_RDMA))
+		return 0;
+
 	for_each_hwfn(cdev, i)
 		num_l2_queues += FEAT_NUM(&cdev->hwfns[i], QED_PF_L2_QUE);
 
@@ -738,7 +735,6 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
 	DP_VERBOSE(cdev, QED_MSG_RDMA, "roce_msix_cnt=%d roce_msix_base=%d\n",
 		   cdev->int_params.rdma_msix_cnt,
 		   cdev->int_params.rdma_msix_base);
-#endif
 
 	return 0;
 }
@@ -843,18 +839,20 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 {
 	int i;
 
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
-	params->rdma_pf_params.num_qps = QED_ROCE_QPS;
-	params->rdma_pf_params.min_dpis = QED_ROCE_DPIS;
-	/* divide by 3 the MRs to avoid MF ILT overflow */
-	params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS;
-	params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX;
-#endif
 	for (i = 0; i < cdev->num_hwfns; i++) {
 		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
 
 		p_hwfn->pf_params = *params;
 	}
+
+	if (!IS_ENABLED(CONFIG_QED_RDMA))
+		return;
+
+	params->rdma_pf_params.num_qps = QED_ROCE_QPS;
+	params->rdma_pf_params.min_dpis = QED_ROCE_DPIS;
+	/* divide by 3 the MRs to avoid MF ILT overflow */
+	params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS;
+	params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX;
 }
 
 static int qed_slowpath_start(struct qed_dev *cdev,
@@ -880,6 +878,7 @@ static int qed_slowpath_start(struct qed_dev *cdev,
 		}
 	}
 
+	cdev->rx_coalesce_usecs = QED_DEFAULT_RX_USECS;
 	rc = qed_nic_setup(cdev);
 	if (rc)
 		goto err;
@@ -1432,7 +1431,7 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode)
 	return status;
 }
 
-struct qed_selftest_ops qed_selftest_ops_pass = {
+static struct qed_selftest_ops qed_selftest_ops_pass = {
 	.selftest_memory = &qed_selftest_memory,
 	.selftest_interrupt = &qed_selftest_interrupt,
 	.selftest_register = &qed_selftest_register,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 76831a3..f3a825a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -129,17 +129,12 @@ static void qed_bmap_release_id(struct qed_hwfn *p_hwfn,
 	}
 }
 
-u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
+static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
 {
 	/* First sb id for RoCE is after all the l2 sb */
 	return FEAT_NUM((struct qed_hwfn *)p_hwfn, QED_PF_L2_QUE) + rel_sb_id;
 }
 
-u32 qed_rdma_query_cau_timer_res(void *rdma_cxt)
-{
-	return QED_CAU_DEF_RX_TIMER_RES;
-}
-
 static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt,
 			  struct qed_rdma_start_in_params *params)
@@ -162,7 +157,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 	p_hwfn->p_rdma_info = p_rdma_info;
 	p_rdma_info->proto = PROTOCOLID_ROCE;
 
-	num_cons = qed_cxt_get_proto_cid_count(p_hwfn, p_rdma_info->proto, 0);
+	num_cons = qed_cxt_get_proto_cid_count(p_hwfn, p_rdma_info->proto,
+					       NULL);
 
 	p_rdma_info->num_qps = num_cons / 2;
 
@@ -275,7 +271,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-void qed_rdma_resc_free(struct qed_hwfn *p_hwfn)
+static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn)
 {
 	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
 
@@ -527,6 +523,26 @@ static int qed_rdma_start_fw(struct qed_hwfn *p_hwfn,
 	return qed_spq_post(p_hwfn, p_ent, NULL);
 }
 
+static int qed_rdma_alloc_tid(void *rdma_cxt, u32 *itid)
+{
+	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
+	int rc;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocate TID\n");
+
+	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+	rc = qed_rdma_bmap_alloc_id(p_hwfn,
+				    &p_hwfn->p_rdma_info->tid_map, itid);
+	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+	if (rc)
+		goto out;
+
+	rc = qed_cxt_dynamic_ilt_alloc(p_hwfn, QED_ELEM_TASK, *itid);
+out:
+	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocate TID - done, rc = %d\n", rc);
+	return rc;
+}
+
 static int qed_rdma_reserve_lkey(struct qed_hwfn *p_hwfn)
 {
 	struct qed_rdma_device *dev = p_hwfn->p_rdma_info->dev;
@@ -573,7 +589,7 @@ static int qed_rdma_setup(struct qed_hwfn *p_hwfn,
 	return qed_rdma_start_fw(p_hwfn, params, p_ptt);
 }
 
-int qed_rdma_stop(void *rdma_cxt)
+static int qed_rdma_stop(void *rdma_cxt)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct rdma_close_func_ramrod_data *p_ramrod;
@@ -629,8 +645,8 @@ int qed_rdma_stop(void *rdma_cxt)
 	return rc;
 }
 
-int qed_rdma_add_user(void *rdma_cxt,
-		      struct qed_rdma_add_user_out_params *out_params)
+static int qed_rdma_add_user(void *rdma_cxt,
+			     struct qed_rdma_add_user_out_params *out_params)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	u32 dpi_start_offset;
@@ -664,7 +680,7 @@ int qed_rdma_add_user(void *rdma_cxt,
 	return rc;
 }
 
-struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt)
+static struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct qed_rdma_port *p_port = p_hwfn->p_rdma_info->port;
@@ -680,7 +696,7 @@ struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt)
 	return p_port;
 }
 
-struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt)
+static struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 
@@ -690,7 +706,7 @@ struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt)
 	return p_hwfn->p_rdma_info->dev;
 }
 
-void qed_rdma_free_tid(void *rdma_cxt, u32 itid)
+static void qed_rdma_free_tid(void *rdma_cxt, u32 itid)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 
@@ -701,27 +717,7 @@ void qed_rdma_free_tid(void *rdma_cxt, u32 itid)
 	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 }
 
-int qed_rdma_alloc_tid(void *rdma_cxt, u32 *itid)
-{
-	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
-	int rc;
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocate TID\n");
-
-	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
-	rc = qed_rdma_bmap_alloc_id(p_hwfn,
-				    &p_hwfn->p_rdma_info->tid_map, itid);
-	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
-	if (rc)
-		goto out;
-
-	rc = qed_cxt_dynamic_ilt_alloc(p_hwfn, QED_ELEM_TASK, *itid);
-out:
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocate TID - done, rc = %d\n", rc);
-	return rc;
-}
-
-void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
+static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
 {
 	struct qed_hwfn *p_hwfn;
 	u16 qz_num;
@@ -816,7 +812,7 @@ static int qed_rdma_get_int(struct qed_dev *cdev, struct qed_int_info *info)
 	return 0;
 }
 
-int qed_rdma_alloc_pd(void *rdma_cxt, u16 *pd)
+static int qed_rdma_alloc_pd(void *rdma_cxt, u16 *pd)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	u32 returned_id;
@@ -836,7 +832,7 @@ int qed_rdma_alloc_pd(void *rdma_cxt, u16 *pd)
 	return rc;
 }
 
-void qed_rdma_free_pd(void *rdma_cxt, u16 pd)
+static void qed_rdma_free_pd(void *rdma_cxt, u16 pd)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 
@@ -873,8 +869,9 @@ qed_rdma_toggle_bit_create_resize_cq(struct qed_hwfn *p_hwfn, u16 icid)
 	return toggle_bit;
 }
 
-int qed_rdma_create_cq(void *rdma_cxt,
-		       struct qed_rdma_create_cq_in_params *params, u16 *icid)
+static int qed_rdma_create_cq(void *rdma_cxt,
+			      struct qed_rdma_create_cq_in_params *params,
+			      u16 *icid)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct qed_rdma_info *p_info = p_hwfn->p_rdma_info;
@@ -957,98 +954,10 @@ int qed_rdma_create_cq(void *rdma_cxt,
 	return rc;
 }
 
-int qed_rdma_resize_cq(void *rdma_cxt,
-		       struct qed_rdma_resize_cq_in_params *in_params,
-		       struct qed_rdma_resize_cq_out_params *out_params)
-{
-	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
-	struct rdma_resize_cq_output_params *p_ramrod_res;
-	struct rdma_resize_cq_ramrod_data *p_ramrod;
-	enum qed_rdma_toggle_bit toggle_bit;
-	struct qed_sp_init_data init_data;
-	struct qed_spq_entry *p_ent;
-	dma_addr_t ramrod_res_phys;
-	u8 fw_return_code;
-	int rc = -ENOMEM;
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", in_params->icid);
-
-	p_ramrod_res =
-	    (struct rdma_resize_cq_output_params *)
-	    dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
-			       sizeof(struct rdma_resize_cq_output_params),
-			       &ramrod_res_phys, GFP_KERNEL);
-	if (!p_ramrod_res) {
-		DP_NOTICE(p_hwfn,
-			  "qed resize cq failed: cannot allocate memory (ramrod)\n");
-		return rc;
-	}
-
-	/* Get SPQ entry */
-	memset(&init_data, 0, sizeof(init_data));
-	init_data.cid = in_params->icid;
-	init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
-	init_data.comp_mode = QED_SPQ_MODE_EBLOCK;
-
-	rc = qed_sp_init_request(p_hwfn, &p_ent,
-				 RDMA_RAMROD_RESIZE_CQ,
-				 p_hwfn->p_rdma_info->proto, &init_data);
-	if (rc)
-		goto err;
-
-	p_ramrod = &p_ent->ramrod.rdma_resize_cq;
-
-	p_ramrod->flags = 0;
-
-	/* toggle the bit for every resize or create cq for a given icid */
-	toggle_bit = qed_rdma_toggle_bit_create_resize_cq(p_hwfn,
-							  in_params->icid);
-
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_RESIZE_CQ_RAMROD_DATA_TOGGLE_BIT, toggle_bit);
-
-	SET_FIELD(p_ramrod->flags,
-		  RDMA_RESIZE_CQ_RAMROD_DATA_IS_TWO_LEVEL_PBL,
-		  in_params->pbl_two_level);
-
-	p_ramrod->pbl_log_page_size = in_params->pbl_page_size_log - 12;
-	p_ramrod->pbl_num_pages = cpu_to_le16(in_params->pbl_num_pages);
-	p_ramrod->max_cqes = cpu_to_le32(in_params->cq_size);
-	DMA_REGPAIR_LE(p_ramrod->pbl_addr, in_params->pbl_ptr);
-	DMA_REGPAIR_LE(p_ramrod->output_params_addr, ramrod_res_phys);
-
-	rc = qed_spq_post(p_hwfn, p_ent, &fw_return_code);
-	if (rc)
-		goto err;
-
-	if (fw_return_code != RDMA_RETURN_OK) {
-		DP_NOTICE(p_hwfn, "fw_return_code = %d\n", fw_return_code);
-		rc = -EINVAL;
-		goto err;
-	}
-
-	out_params->prod = le32_to_cpu(p_ramrod_res->old_cq_prod);
-	out_params->cons = le32_to_cpu(p_ramrod_res->old_cq_cons);
-
-	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
-			  sizeof(struct rdma_resize_cq_output_params),
-			  p_ramrod_res, ramrod_res_phys);
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Resized CQ, rc = %d\n", rc);
-
-	return rc;
-
-err:	dma_free_coherent(&p_hwfn->cdev->pdev->dev,
-			  sizeof(struct rdma_resize_cq_output_params),
-			  p_ramrod_res, ramrod_res_phys);
-	DP_NOTICE(p_hwfn, "Resized CQ, Failed - rc = %d\n", rc);
-
-	return rc;
-}
-
-int qed_rdma_destroy_cq(void *rdma_cxt,
-			struct qed_rdma_destroy_cq_in_params *in_params,
-			struct qed_rdma_destroy_cq_out_params *out_params)
+static int
+qed_rdma_destroy_cq(void *rdma_cxt,
+		    struct qed_rdma_destroy_cq_in_params *in_params,
+		    struct qed_rdma_destroy_cq_out_params *out_params)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct rdma_destroy_cq_output_params *p_ramrod_res;
@@ -1169,7 +1078,7 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode)
 	return flavor;
 }
 
-int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid)
+static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid)
 {
 	struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
 	u32 responder_icid;
@@ -1793,9 +1702,9 @@ static int qed_roce_sp_destroy_qp_requester(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
-		      struct qed_rdma_qp *qp,
-		      struct qed_rdma_query_qp_out_params *out_params)
+static int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
+			     struct qed_rdma_qp *qp,
+			     struct qed_rdma_query_qp_out_params *out_params)
 {
 	struct roce_query_qp_resp_output_params *p_resp_ramrod_res;
 	struct roce_query_qp_req_output_params *p_req_ramrod_res;
@@ -1936,7 +1845,7 @@ int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
+static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 {
 	u32 num_invalidated_mw = 0;
 	u32 num_bound_mw = 0;
@@ -1985,9 +1894,9 @@ int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 	return 0;
 }
 
-int qed_rdma_query_qp(void *rdma_cxt,
-		      struct qed_rdma_qp *qp,
-		      struct qed_rdma_query_qp_out_params *out_params)
+static int qed_rdma_query_qp(void *rdma_cxt,
+			     struct qed_rdma_qp *qp,
+			     struct qed_rdma_query_qp_out_params *out_params)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	int rc;
@@ -2022,7 +1931,7 @@ int qed_rdma_query_qp(void *rdma_cxt,
 	return rc;
 }
 
-int qed_rdma_destroy_qp(void *rdma_cxt, struct qed_rdma_qp *qp)
+static int qed_rdma_destroy_qp(void *rdma_cxt, struct qed_rdma_qp *qp)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	int rc = 0;
@@ -2038,7 +1947,7 @@ int qed_rdma_destroy_qp(void *rdma_cxt, struct qed_rdma_qp *qp)
 	return rc;
 }
 
-struct qed_rdma_qp *
+static struct qed_rdma_qp *
 qed_rdma_create_qp(void *rdma_cxt,
 		   struct qed_rdma_create_qp_in_params *in_params,
 		   struct qed_rdma_create_qp_out_params *out_params)
@@ -2215,9 +2124,9 @@ static int qed_roce_modify_qp(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-int qed_rdma_modify_qp(void *rdma_cxt,
-		       struct qed_rdma_qp *qp,
-		       struct qed_rdma_modify_qp_in_params *params)
+static int qed_rdma_modify_qp(void *rdma_cxt,
+			      struct qed_rdma_qp *qp,
+			      struct qed_rdma_modify_qp_in_params *params)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	enum qed_roce_qp_state prev_state;
@@ -2312,8 +2221,9 @@ int qed_rdma_modify_qp(void *rdma_cxt,
 	return rc;
 }
 
-int qed_rdma_register_tid(void *rdma_cxt,
-			  struct qed_rdma_register_tid_in_params *params)
+static int
+qed_rdma_register_tid(void *rdma_cxt,
+		      struct qed_rdma_register_tid_in_params *params)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct rdma_register_tid_ramrod_data *p_ramrod;
@@ -2450,7 +2360,7 @@ int qed_rdma_register_tid(void *rdma_cxt,
 	return rc;
 }
 
-int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid)
+static int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct rdma_deregister_tid_ramrod_data *p_ramrod;
@@ -2561,7 +2471,8 @@ void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	qed_rdma_dpm_conf(p_hwfn, p_ptt);
 }
 
-int qed_rdma_start(void *rdma_cxt, struct qed_rdma_start_in_params *params)
+static int qed_rdma_start(void *rdma_cxt,
+			  struct qed_rdma_start_in_params *params)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct qed_ptt *p_ptt;
@@ -2601,7 +2512,7 @@ static int qed_rdma_init(struct qed_dev *cdev,
 	return qed_rdma_start(QED_LEADING_HWFN(cdev), params);
 }
 
-void qed_rdma_remove_user(void *rdma_cxt, u16 dpi)
+static void qed_rdma_remove_user(void *rdma_cxt, u16 dpi)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 
@@ -2809,11 +2720,6 @@ static int qed_roce_ll2_stop(struct qed_dev *cdev)
 	struct qed_roce_ll2_info *roce_ll2 = hwfn->ll2;
 	int rc;
 
-	if (!cdev) {
-		DP_ERR(cdev, "qed roce ll2 stop: invalid cdev\n");
-		return -EINVAL;
-	}
-
 	if (roce_ll2->handle == QED_LL2_UNUSED_HANDLE) {
 		DP_ERR(cdev, "qed roce ll2 stop: cannot stop an unused LL2\n");
 		return -EINVAL;
@@ -2850,7 +2756,7 @@ static int qed_roce_ll2_tx(struct qed_dev *cdev,
 	int rc;
 	int i;
 
-	if (!cdev || !pkt || !params) {
+	if (!pkt || !params) {
 		DP_ERR(cdev,
 		       "roce ll2 tx: failed tx because one of the following is NULL - drv=%p, pkt=%p, params=%p\n",
 		       cdev, pkt, params);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h
index 2f091e8..279f342 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h
@@ -95,26 +95,6 @@ struct qed_rdma_info {
 	enum protocol_type proto;
 };
 
-struct qed_rdma_resize_cq_in_params {
-	u16 icid;
-	u32 cq_size;
-	bool pbl_two_level;
-	u64 pbl_ptr;
-	u16 pbl_num_pages;
-	u8 pbl_page_size_log;
-};
-
-struct qed_rdma_resize_cq_out_params {
-	u32 prod;
-	u32 cons;
-};
-
-struct qed_rdma_resize_cnq_in_params {
-	u32 cnq_id;
-	u32 pbl_page_size_log;
-	u64 pbl_ptr;
-};
-
 struct qed_rdma_qp {
 	struct regpair qp_handle;
 	struct regpair qp_handle_async;
@@ -181,36 +161,55 @@ struct qed_rdma_qp {
 	dma_addr_t shared_queue_phys_addr;
 };
 
-int
-qed_rdma_add_user(void *rdma_cxt,
-		  struct qed_rdma_add_user_out_params *out_params);
-int qed_rdma_alloc_pd(void *rdma_cxt, u16 *pd);
-int qed_rdma_alloc_tid(void *rdma_cxt, u32 *tid);
-int qed_rdma_deregister_tid(void *rdma_cxt, u32 tid);
-void qed_rdma_free_tid(void *rdma_cxt, u32 tid);
-struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt);
-struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt);
-int
-qed_rdma_register_tid(void *rdma_cxt,
-		      struct qed_rdma_register_tid_in_params *params);
-void qed_rdma_remove_user(void *rdma_cxt, u16 dpi);
-int qed_rdma_start(void *p_hwfn, struct qed_rdma_start_in_params *params);
-int qed_rdma_stop(void *rdma_cxt);
-u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id);
-u32 qed_rdma_query_cau_timer_res(void *p_hwfn);
-void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 cnq_index, u16 prod);
-void qed_rdma_resc_free(struct qed_hwfn *p_hwfn);
+#if IS_ENABLED(CONFIG_QED_RDMA)
+void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 void qed_async_roce_event(struct qed_hwfn *p_hwfn,
 			  struct event_ring_entry *p_eqe);
-int qed_rdma_destroy_qp(void *rdma_cxt, struct qed_rdma_qp *qp);
-int qed_rdma_modify_qp(void *rdma_cxt, struct qed_rdma_qp *qp,
-		       struct qed_rdma_modify_qp_in_params *params);
-int qed_rdma_query_qp(void *rdma_cxt, struct qed_rdma_qp *qp,
-		      struct qed_rdma_query_qp_out_params *out_params);
-
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
-void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
+				     u8 connection_handle,
+				     void *cookie,
+				     dma_addr_t first_frag_addr,
+				     bool b_last_fragment, bool b_last_packet);
+void qed_ll2b_release_tx_gsi_packet(struct qed_hwfn *p_hwfn,
+				    u8 connection_handle,
+				    void *cookie,
+				    dma_addr_t first_frag_addr,
+				    bool b_last_fragment, bool b_last_packet);
+void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
+				     u8 connection_handle,
+				     void *cookie,
+				     dma_addr_t rx_buf_addr,
+				     u16 data_length,
+				     u8 data_length_error,
+				     u16 parse_flags,
+				     u16 vlan,
+				     u32 src_mac_addr_hi,
+				     u16 src_mac_addr_lo, bool b_last_packet);
 #else
-void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {}
+static inline void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {}
+static inline void qed_async_roce_event(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) {}
+static inline void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
+						   u8 connection_handle,
+						   void *cookie,
+						   dma_addr_t first_frag_addr,
+						   bool b_last_fragment,
+						   bool b_last_packet) {}
+static inline void qed_ll2b_release_tx_gsi_packet(struct qed_hwfn *p_hwfn,
+						  u8 connection_handle,
+						  void *cookie,
+						  dma_addr_t first_frag_addr,
+						  bool b_last_fragment,
+						  bool b_last_packet) {}
+static inline void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
+						   u8 connection_handle,
+						   void *cookie,
+						   dma_addr_t rx_buf_addr,
+						   u16 data_length,
+						   u8 data_length_error,
+						   u16 parse_flags,
+						   u16 vlan,
+						   u32 src_mac_addr_hi,
+						   u16 src_mac_addr_lo,
+						   bool b_last_packet) {}
 #endif
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 652c908..b2c08e4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -80,7 +80,6 @@ union ramrod_data {
 	struct roce_destroy_qp_resp_ramrod_data roce_destroy_qp_resp;
 	struct roce_destroy_qp_req_ramrod_data roce_destroy_qp_req;
 	struct rdma_create_cq_ramrod_data rdma_create_cq;
-	struct rdma_resize_cq_ramrod_data rdma_resize_cq;
 	struct rdma_destroy_cq_ramrod_data rdma_destroy_cq;
 	struct rdma_srq_create_ramrod_data rdma_create_srq;
 	struct rdma_srq_destroy_ramrod_data rdma_destroy_srq;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index caff415..9fbaf94 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -28,9 +28,7 @@
 #include "qed_reg_addr.h"
 #include "qed_sp.h"
 #include "qed_sriov.h"
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
 #include "qed_roce.h"
-#endif
 
 /***************************************************************************
 * Structures & Definitions
@@ -240,11 +238,9 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn,
 			   struct event_ring_entry *p_eqe)
 {
 	switch (p_eqe->protocol_id) {
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
 	case PROTOCOLID_ROCE:
 		qed_async_roce_event(p_hwfn, p_eqe);
 		return 0;
-#endif
 	case PROTOCOLID_COMMON:
 		return qed_sriov_eqe_event(p_hwfn,
 					   p_eqe->opcode,
diff --git a/drivers/net/ethernet/qlogic/qede/Makefile b/drivers/net/ethernet/qlogic/qede/Makefile
index 28dc589..048a230 100644
--- a/drivers/net/ethernet/qlogic/qede/Makefile
+++ b/drivers/net/ethernet/qlogic/qede/Makefile
@@ -2,4 +2,4 @@
 
 qede-y := qede_main.o qede_ethtool.o
 qede-$(CONFIG_DCB) += qede_dcbnl.o
-qede-$(CONFIG_INFINIBAND_QEDR) += qede_roce.o
+qede-$(CONFIG_QED_RDMA) += qede_roce.o
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 28c0e9f..974689a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -348,12 +348,13 @@ bool qede_has_rx_work(struct qede_rx_queue *rxq);
 int qede_txq_has_work(struct qede_tx_queue *txq);
 void qede_recycle_rx_bd_ring(struct qede_rx_queue *rxq, struct qede_dev *edev,
 			     u8 count);
+void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
 
 #define RX_RING_SIZE_POW	13
 #define RX_RING_SIZE		((u16)BIT(RX_RING_SIZE_POW))
 #define NUM_RX_BDS_MAX		(RX_RING_SIZE - 1)
 #define NUM_RX_BDS_MIN		128
-#define NUM_RX_BDS_DEF		NUM_RX_BDS_MAX
+#define NUM_RX_BDS_DEF		((u16)BIT(10) - 1)
 
 #define TX_RING_SIZE_POW	13
 #define TX_RING_SIZE		((u16)BIT(TX_RING_SIZE_POW))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 25a9b29..12251a1 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -756,6 +756,8 @@ static void qede_get_channels(struct net_device *dev,
 	struct qede_dev *edev = netdev_priv(dev);
 
 	channels->max_combined = QEDE_MAX_RSS_CNT(edev);
+	channels->max_rx = QEDE_MAX_RSS_CNT(edev);
+	channels->max_tx = QEDE_MAX_RSS_CNT(edev);
 	channels->combined_count = QEDE_QUEUE_CNT(edev) - edev->fp_num_tx -
 					edev->fp_num_rx;
 	channels->tx_count = edev->fp_num_tx;
@@ -820,6 +822,13 @@ static int qede_set_channels(struct net_device *dev,
 	edev->req_queues = count;
 	edev->req_num_tx = channels->tx_count;
 	edev->req_num_rx = channels->rx_count;
+	/* Reset the indirection table if rx queue count is updated */
+	if ((edev->req_queues - edev->req_num_tx) != QEDE_RSS_COUNT(edev)) {
+		edev->rss_params_inited &= ~QEDE_RSS_INDIR_INITED;
+		memset(&edev->rss_params.rss_ind_table, 0,
+		       sizeof(edev->rss_params.rss_ind_table));
+	}
+
 	if (netif_running(dev))
 		qede_reload(edev, NULL, NULL);
 
@@ -1053,6 +1062,12 @@ static int qede_set_rxfh(struct net_device *dev, const u32 *indir,
 	struct qede_dev *edev = netdev_priv(dev);
 	int i;
 
+	if (edev->dev_info.common.num_hwfns > 1) {
+		DP_INFO(edev,
+			"RSS configuration is not supported for 100G devices\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
@@ -1184,8 +1199,8 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 	}
 
 	first_bd = (struct eth_tx_1st_bd *)qed_chain_consume(&txq->tx_pbl);
-	dma_unmap_page(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
-		       BD_UNMAP_LEN(first_bd), DMA_TO_DEVICE);
+	dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
+			 BD_UNMAP_LEN(first_bd), DMA_TO_DEVICE);
 	txq->sw_tx_cons++;
 	txq->sw_tx_ring[idx].skb = NULL;
 
@@ -1199,8 +1214,8 @@ static int qede_selftest_receive_traffic(struct qede_dev *edev)
 	struct qede_rx_queue *rxq = NULL;
 	struct sw_rx_data *sw_rx_data;
 	union eth_rx_cqe *cqe;
+	int i, rc = 0;
 	u8 *data_ptr;
-	int i;
 
 	for_each_queue(i) {
 		if (edev->fp_array[i].type & QEDE_FASTPATH_RX) {
@@ -1219,46 +1234,60 @@ static int qede_selftest_receive_traffic(struct qede_dev *edev)
 	 * queue and that the loopback traffic is not IP.
 	 */
 	for (i = 0; i < QEDE_SELFTEST_POLL_COUNT; i++) {
-		if (qede_has_rx_work(rxq))
+		if (!qede_has_rx_work(rxq)) {
+			usleep_range(100, 200);
+			continue;
+		}
+
+		hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr);
+		sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
+
+		/* Memory barrier to prevent the CPU from doing speculative
+		 * reads of CQE/BD before reading hw_comp_cons. If the CQE is
+		 * read before it is written by FW, then FW writes CQE and SB,
+		 * and then the CPU reads the hw_comp_cons, it will use an old
+		 * CQE.
+		 */
+		rmb();
+
+		/* Get the CQE from the completion ring */
+		cqe = (union eth_rx_cqe *)qed_chain_consume(&rxq->rx_comp_ring);
+
+		/* Get the data from the SW ring */
+		sw_rx_index = rxq->sw_rx_cons & NUM_RX_BDS_MAX;
+		sw_rx_data = &rxq->sw_rx_ring[sw_rx_index];
+		fp_cqe = &cqe->fast_path_regular;
+		len =  le16_to_cpu(fp_cqe->len_on_first_bd);
+		data_ptr = (u8 *)(page_address(sw_rx_data->data) +
+				  fp_cqe->placement_offset +
+				  sw_rx_data->page_offset);
+		if (ether_addr_equal(data_ptr,  edev->ndev->dev_addr) &&
+		    ether_addr_equal(data_ptr + ETH_ALEN,
+				     edev->ndev->dev_addr)) {
+			for (i = ETH_HLEN; i < len; i++)
+				if (data_ptr[i] != (unsigned char)(i & 0xff)) {
+					rc = -1;
+					break;
+				}
+
+			qede_recycle_rx_bd_ring(rxq, edev, 1);
+			qed_chain_recycle_consumed(&rxq->rx_comp_ring);
 			break;
-		usleep_range(100, 200);
+		}
+
+		DP_INFO(edev, "Not the transmitted packet\n");
+		qede_recycle_rx_bd_ring(rxq, edev, 1);
+		qed_chain_recycle_consumed(&rxq->rx_comp_ring);
 	}
 
-	if (!qede_has_rx_work(rxq)) {
+	if (i == QEDE_SELFTEST_POLL_COUNT) {
 		DP_NOTICE(edev, "Failed to receive the traffic\n");
 		return -1;
 	}
 
-	hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr);
-	sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
+	qede_update_rx_prod(edev, rxq);
 
-	/* Memory barrier to prevent the CPU from doing speculative reads of CQE
-	 * / BD before reading hw_comp_cons. If the CQE is read before it is
-	 * written by FW, then FW writes CQE and SB, and then the CPU reads the
-	 * hw_comp_cons, it will use an old CQE.
-	 */
-	rmb();
-
-	/* Get the CQE from the completion ring */
-	cqe = (union eth_rx_cqe *)qed_chain_consume(&rxq->rx_comp_ring);
-
-	/* Get the data from the SW ring */
-	sw_rx_index = rxq->sw_rx_cons & NUM_RX_BDS_MAX;
-	sw_rx_data = &rxq->sw_rx_ring[sw_rx_index];
-	fp_cqe = &cqe->fast_path_regular;
-	len =  le16_to_cpu(fp_cqe->len_on_first_bd);
-	data_ptr = (u8 *)(page_address(sw_rx_data->data) +
-		     fp_cqe->placement_offset + sw_rx_data->page_offset);
-	for (i = ETH_HLEN; i < len; i++)
-		if (data_ptr[i] != (unsigned char)(i & 0xff)) {
-			DP_NOTICE(edev, "Loopback test failed\n");
-			qede_recycle_rx_bd_ring(rxq, edev, 1);
-			return -1;
-		}
-
-	qede_recycle_rx_bd_ring(rxq, edev, 1);
-
-	return 0;
+	return rc;
 }
 
 static int qede_selftest_run_loopback(struct qede_dev *edev, u32 loopback_mode)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 343038c..7def29a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -313,8 +313,8 @@ static int qede_free_tx_pkt(struct qede_dev *edev,
 		split_bd_len = BD_UNMAP_LEN(split);
 		bds_consumed++;
 	}
-	dma_unmap_page(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
-		       BD_UNMAP_LEN(first_bd) + split_bd_len, DMA_TO_DEVICE);
+	dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
+			 BD_UNMAP_LEN(first_bd) + split_bd_len, DMA_TO_DEVICE);
 
 	/* Unmap the data of the skb frags */
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++, bds_consumed++) {
@@ -359,8 +359,8 @@ static void qede_free_failed_tx_pkt(struct qede_dev *edev,
 		nbd--;
 	}
 
-	dma_unmap_page(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
-		       BD_UNMAP_LEN(first_bd) + split_bd_len, DMA_TO_DEVICE);
+	dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
+			 BD_UNMAP_LEN(first_bd) + split_bd_len, DMA_TO_DEVICE);
 
 	/* Unmap the data of the skb frags */
 	for (i = 0; i < nbd; i++) {
@@ -943,8 +943,7 @@ static inline int qede_realloc_rx_buffer(struct qede_dev *edev,
 	return 0;
 }
 
-static inline void qede_update_rx_prod(struct qede_dev *edev,
-				       struct qede_rx_queue *rxq)
+void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq)
 {
 	u16 bd_prod = qed_chain_get_prod_idx(&rxq->rx_bd_ring);
 	u16 cqe_prod = qed_chain_get_prod_idx(&rxq->rx_comp_ring);
@@ -2941,7 +2940,7 @@ static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
 	txq->num_tx_buffers = edev->q_num_tx_buffers;
 
 	/* Allocate the parallel driver ring for Tx buffers */
-	size = sizeof(*txq->sw_tx_ring) * NUM_TX_BDS_MAX;
+	size = sizeof(*txq->sw_tx_ring) * TX_RING_SIZE;
 	txq->sw_tx_ring = kzalloc(size, GFP_KERNEL);
 	if (!txq->sw_tx_ring) {
 		DP_NOTICE(edev, "Tx buffers ring allocation failed\n");
@@ -2952,7 +2951,7 @@ static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
 					    QED_CHAIN_USE_TO_CONSUME_PRODUCE,
 					    QED_CHAIN_MODE_PBL,
 					    QED_CHAIN_CNT_TYPE_U16,
-					    NUM_TX_BDS_MAX,
+					    TX_RING_SIZE,
 					    sizeof(*p_virt), &txq->tx_pbl);
 	if (rc)
 		goto err;
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index e97968e..6fb3bee 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -1021,14 +1021,18 @@ void emac_mac_down(struct emac_adapter *adpt)
 	napi_disable(&adpt->rx_q.napi);
 
 	phy_stop(adpt->phydev);
-	phy_disconnect(adpt->phydev);
 
-	/* disable mac irq */
+	/* Interrupts must be disabled before the PHY is disconnected, to
+	 * avoid a race condition where adjust_link is null when we get
+	 * an interrupt.
+	 */
 	writel(DIS_INT, adpt->base + EMAC_INT_STATUS);
 	writel(0, adpt->base + EMAC_INT_MASK);
 	synchronize_irq(adpt->irq.irq);
 	free_irq(adpt->irq.irq, &adpt->irq);
 
+	phy_disconnect(adpt->phydev);
+
 	emac_mac_reset(adpt);
 
 	emac_tx_q_descs_free(adpt);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 9bf3b2b..4fede4b 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -575,6 +575,7 @@ static const struct of_device_id emac_dt_match[] = {
 	},
 	{}
 };
+MODULE_DEVICE_TABLE(of, emac_dt_match);
 
 #if IS_ENABLED(CONFIG_ACPI)
 static const struct acpi_device_id emac_acpi_match[] = {
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index e55638c..bf000d8 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8273,7 +8273,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if ((sizeof(dma_addr_t) > 4) &&
 	    (use_dac == 1 || (use_dac == -1 && pci_is_pcie(pdev) &&
 			      tp->mac_version >= RTL_GIGA_MAC_VER_18)) &&
-	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+	    !pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) &&
+	    !pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) {
 
 		/* CPlusCmd Dual Access Cycle is only needed for non-PCIe */
 		if (!pci_is_pcie(pdev))
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 5424fb3..24b7464 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1471,7 +1471,7 @@ static int rocker_world_check_init(struct rocker_port *rocker_port)
 	if (rocker->wops) {
 		if (rocker->wops->mode != mode) {
 			dev_err(&rocker->pdev->dev, "hardware has ports in different worlds, which is not supported\n");
-			return err;
+			return -EINVAL;
 		}
 		return 0;
 	}
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 431a608..4ca4613 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -1493,8 +1493,6 @@ static int ofdpa_port_ipv4_nh(struct ofdpa_port *ofdpa_port,
 	spin_lock_irqsave(&ofdpa->neigh_tbl_lock, lock_flags);
 
 	found = ofdpa_neigh_tbl_find(ofdpa, ip_addr);
-	if (found)
-		*index = found->index;
 
 	updating = found && adding;
 	removing = found && !adding;
@@ -1508,9 +1506,11 @@ static int ofdpa_port_ipv4_nh(struct ofdpa_port *ofdpa_port,
 		resolved = false;
 	} else if (removing) {
 		ofdpa_neigh_del(trans, found);
+		*index = found->index;
 	} else if (updating) {
 		ofdpa_neigh_update(found, trans, NULL, false);
 		resolved = !is_zero_ether_addr(found->eth_dst);
+		*index = found->index;
 	} else {
 		err = -ENOENT;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 4ec7397..a1b17cd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -347,10 +347,9 @@ static void dwmac4_display_ring(void *head, unsigned int size, bool rx)
 	pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
 
 	for (i = 0; i < size; i++) {
-		if (p->des0)
-			pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
-				i, (unsigned int)virt_to_phys(p),
-				p->des0, p->des1, p->des2, p->des3);
+		pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
+			i, (unsigned int)virt_to_phys(p),
+			p->des0, p->des1, p->des2, p->des3);
 		p++;
 	}
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 8dc9056..b15fc55 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -145,7 +145,7 @@ int stmmac_mdio_register(struct net_device *ndev);
 int stmmac_mdio_reset(struct mii_bus *mii);
 void stmmac_set_ethtool_ops(struct net_device *netdev);
 
-int stmmac_ptp_register(struct stmmac_priv *priv);
+void stmmac_ptp_register(struct stmmac_priv *priv);
 void stmmac_ptp_unregister(struct stmmac_priv *priv);
 int stmmac_resume(struct device *dev);
 int stmmac_suspend(struct device *dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 6c85b61..48e71fa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -676,7 +676,9 @@ static int stmmac_init_ptp(struct stmmac_priv *priv)
 	priv->hwts_tx_en = 0;
 	priv->hwts_rx_en = 0;
 
-	return stmmac_ptp_register(priv);
+	stmmac_ptp_register(priv);
+
+	return 0;
 }
 
 static void stmmac_release_ptp(struct stmmac_priv *priv)
@@ -1710,7 +1712,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	if (init_ptp) {
 		ret = stmmac_init_ptp(priv);
 		if (ret)
-			netdev_warn(priv->dev, "PTP support cannot init.\n");
+			netdev_warn(priv->dev, "fail to init PTP.\n");
 	}
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 289d527..1477471 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -177,7 +177,7 @@ static struct ptp_clock_info stmmac_ptp_clock_ops = {
  * Description: this function will register the ptp clock driver
  * to kernel. It also does some house keeping work.
  */
-int stmmac_ptp_register(struct stmmac_priv *priv)
+void stmmac_ptp_register(struct stmmac_priv *priv)
 {
 	spin_lock_init(&priv->ptp_lock);
 	priv->ptp_clock_ops = stmmac_ptp_clock_ops;
@@ -185,15 +185,10 @@ int stmmac_ptp_register(struct stmmac_priv *priv)
 	priv->ptp_clock = ptp_clock_register(&priv->ptp_clock_ops,
 					     priv->device);
 	if (IS_ERR(priv->ptp_clock)) {
+		netdev_err(priv->dev, "ptp_clock_register failed\n");
 		priv->ptp_clock = NULL;
-		return PTR_ERR(priv->ptp_clock);
-	}
-
-	spin_lock_init(&priv->ptp_lock);
-
-	netdev_dbg(priv->dev, "Added PTP HW clock successfully\n");
-
-	return 0;
+	} else if (priv->ptp_clock)
+		netdev_info(priv->dev, "registered PTP clock\n");
 }
 
 /**
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 0d00531..5eedac4 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -982,11 +982,13 @@ static int dwceqos_mii_probe(struct net_device *ndev)
 	if (netif_msg_probe(lp))
 		phy_attached_info(phydev);
 
-	phydev->supported &= PHY_GBIT_FEATURES;
+	phydev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause |
+			     SUPPORTED_Asym_Pause;
 
 	lp->link    = 0;
 	lp->speed   = 0;
 	lp->duplex  = DUPLEX_UNKNOWN;
+	lp->flowcontrol.autoneg = AUTONEG_ENABLE;
 
 	return 0;
 }
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 3c20e87..42edd7b 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -58,9 +58,9 @@ struct geneve_dev {
 	struct hlist_node  hlist;	/* vni hash table */
 	struct net	   *net;	/* netns for packet i/o */
 	struct net_device  *dev;	/* netdev for geneve tunnel */
-	struct geneve_sock *sock4;	/* IPv4 socket used for geneve tunnel */
+	struct geneve_sock __rcu *sock4;	/* IPv4 socket used for geneve tunnel */
 #if IS_ENABLED(CONFIG_IPV6)
-	struct geneve_sock *sock6;	/* IPv6 socket used for geneve tunnel */
+	struct geneve_sock __rcu *sock6;	/* IPv6 socket used for geneve tunnel */
 #endif
 	u8                 vni[3];	/* virtual network ID for tunnel */
 	u8                 ttl;		/* TTL override */
@@ -453,7 +453,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
 
 	skb_gro_pull(skb, gh_len);
 	skb_gro_postpull_rcsum(skb, gh, gh_len);
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 	flush = 0;
 
 out_unlock:
@@ -543,9 +543,19 @@ static void __geneve_sock_release(struct geneve_sock *gs)
 
 static void geneve_sock_release(struct geneve_dev *geneve)
 {
-	__geneve_sock_release(geneve->sock4);
+	struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4);
 #if IS_ENABLED(CONFIG_IPV6)
-	__geneve_sock_release(geneve->sock6);
+	struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6);
+
+	rcu_assign_pointer(geneve->sock6, NULL);
+#endif
+
+	rcu_assign_pointer(geneve->sock4, NULL);
+	synchronize_net();
+
+	__geneve_sock_release(gs4);
+#if IS_ENABLED(CONFIG_IPV6)
+	__geneve_sock_release(gs6);
 #endif
 }
 
@@ -586,10 +596,10 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
 	gs->flags = geneve->flags;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (ipv6)
-		geneve->sock6 = gs;
+		rcu_assign_pointer(geneve->sock6, gs);
 	else
 #endif
-		geneve->sock4 = gs;
+		rcu_assign_pointer(geneve->sock4, gs);
 
 	hash = geneve_net_vni_hash(geneve->vni);
 	hlist_add_head_rcu(&geneve->hlist, &gs->vni_list[hash]);
@@ -603,9 +613,7 @@ static int geneve_open(struct net_device *dev)
 	bool metadata = geneve->collect_md;
 	int ret = 0;
 
-	geneve->sock4 = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
-	geneve->sock6 = NULL;
 	if (ipv6 || metadata)
 		ret = geneve_sock_add(geneve, true);
 #endif
@@ -720,6 +728,9 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 	struct rtable *rt = NULL;
 	__u8 tos;
 
+	if (!rcu_dereference(geneve->sock4))
+		return ERR_PTR(-EIO);
+
 	memset(fl4, 0, sizeof(*fl4));
 	fl4->flowi4_mark = skb->mark;
 	fl4->flowi4_proto = IPPROTO_UDP;
@@ -772,11 +783,15 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
-	struct geneve_sock *gs6 = geneve->sock6;
 	struct dst_entry *dst = NULL;
 	struct dst_cache *dst_cache;
+	struct geneve_sock *gs6;
 	__u8 prio;
 
+	gs6 = rcu_dereference(geneve->sock6);
+	if (!gs6)
+		return ERR_PTR(-EIO);
+
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_mark = skb->mark;
 	fl6->flowi6_proto = IPPROTO_UDP;
@@ -842,7 +857,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 				   struct ip_tunnel_info *info)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
-	struct geneve_sock *gs4 = geneve->sock4;
+	struct geneve_sock *gs4;
 	struct rtable *rt = NULL;
 	const struct iphdr *iip; /* interior IP header */
 	int err = -EINVAL;
@@ -853,6 +868,10 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
 	u32 flags = geneve->flags;
 
+	gs4 = rcu_dereference(geneve->sock4);
+	if (!gs4)
+		goto tx_error;
+
 	if (geneve->collect_md) {
 		if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
 			netdev_dbg(dev, "no tunnel metadata\n");
@@ -932,9 +951,9 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 				    struct ip_tunnel_info *info)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
-	struct geneve_sock *gs6 = geneve->sock6;
 	struct dst_entry *dst = NULL;
 	const struct iphdr *iip; /* interior IP header */
+	struct geneve_sock *gs6;
 	int err = -EINVAL;
 	struct flowi6 fl6;
 	__u8 prio, ttl;
@@ -943,6 +962,10 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
 	u32 flags = geneve->flags;
 
+	gs6 = rcu_dereference(geneve->sock6);
+	if (!gs6)
+		goto tx_error;
+
 	if (geneve->collect_md) {
 		if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
 			netdev_dbg(dev, "no tunnel metadata\n");
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f0919bd..f638215 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -447,7 +447,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	 * Setup the sendside checksum offload only if this is not a
 	 * GSO packet.
 	 */
-	if (skb_is_gso(skb)) {
+	if ((net_trans_info & (INFO_TCP | INFO_UDP)) && skb_is_gso(skb)) {
 		struct ndis_tcp_lso_info *lso_info;
 
 		rndis_msg_size += NDIS_LSO_PPI_SIZE;
@@ -607,15 +607,18 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
 	       packet->total_data_buflen);
 
 	skb->protocol = eth_type_trans(skb, net);
-	if (csum_info) {
-		/* We only look at the IP checksum here.
-		 * Should we be dropping the packet if checksum
-		 * failed? How do we deal with other checksums - TCP/UDP?
-		 */
-		if (csum_info->receive.ip_checksum_succeeded)
+
+	/* skb is already created with CHECKSUM_NONE */
+	skb_checksum_none_assert(skb);
+
+	/*
+	 * In Linux, the IP checksum is always checked.
+	 * Do L4 checksum offload if enabled and present.
+	 */
+	if (csum_info && (net->features & NETIF_F_RXCSUM)) {
+		if (csum_info->receive.tcp_checksum_succeeded ||
+		    csum_info->receive.udp_checksum_succeeded)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
-		else
-			skb->ip_summed = CHECKSUM_NONE;
 	}
 
 	if (vlan_tci & VLAN_TAG_PRESENT)
@@ -696,12 +699,8 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 static void netvsc_get_drvinfo(struct net_device *net,
 			       struct ethtool_drvinfo *info)
 {
-	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct hv_device *dev = net_device_ctx->device_ctx;
-
 	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
 	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
-	strlcpy(info->bus_info, vmbus_dev_name(dev), sizeof(info->bus_info));
 }
 
 static void netvsc_get_channels(struct net_device *net,
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 3ea47f2..d2e61e0 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -397,6 +397,14 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb)
 #define DEFAULT_ENCRYPT false
 #define DEFAULT_ENCODING_SA 0
 
+static bool send_sci(const struct macsec_secy *secy)
+{
+	const struct macsec_tx_sc *tx_sc = &secy->tx_sc;
+
+	return tx_sc->send_sci ||
+		(secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb);
+}
+
 static sci_t make_sci(u8 *addr, __be16 port)
 {
 	sci_t sci;
@@ -437,15 +445,15 @@ static unsigned int macsec_extra_len(bool sci_present)
 
 /* Fill SecTAG according to IEEE 802.1AE-2006 10.5.3 */
 static void macsec_fill_sectag(struct macsec_eth_header *h,
-			       const struct macsec_secy *secy, u32 pn)
+			       const struct macsec_secy *secy, u32 pn,
+			       bool sci_present)
 {
 	const struct macsec_tx_sc *tx_sc = &secy->tx_sc;
 
-	memset(&h->tci_an, 0, macsec_sectag_len(tx_sc->send_sci));
+	memset(&h->tci_an, 0, macsec_sectag_len(sci_present));
 	h->eth.h_proto = htons(ETH_P_MACSEC);
 
-	if (tx_sc->send_sci ||
-	    (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb)) {
+	if (sci_present) {
 		h->tci_an |= MACSEC_TCI_SC;
 		memcpy(&h->secure_channel_id, &secy->sci,
 		       sizeof(h->secure_channel_id));
@@ -650,6 +658,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 	struct macsec_tx_sc *tx_sc;
 	struct macsec_tx_sa *tx_sa;
 	struct macsec_dev *macsec = macsec_priv(dev);
+	bool sci_present;
 	u32 pn;
 
 	secy = &macsec->secy;
@@ -687,7 +696,8 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 
 	unprotected_len = skb->len;
 	eth = eth_hdr(skb);
-	hh = (struct macsec_eth_header *)skb_push(skb, macsec_extra_len(tx_sc->send_sci));
+	sci_present = send_sci(secy);
+	hh = (struct macsec_eth_header *)skb_push(skb, macsec_extra_len(sci_present));
 	memmove(hh, eth, 2 * ETH_ALEN);
 
 	pn = tx_sa_update_pn(tx_sa, secy);
@@ -696,7 +706,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 		kfree_skb(skb);
 		return ERR_PTR(-ENOLINK);
 	}
-	macsec_fill_sectag(hh, secy, pn);
+	macsec_fill_sectag(hh, secy, pn, sci_present);
 	macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN);
 
 	skb_put(skb, secy->icv_len);
@@ -726,10 +736,10 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 	skb_to_sgvec(skb, sg, 0, skb->len);
 
 	if (tx_sc->encrypt) {
-		int len = skb->len - macsec_hdr_len(tx_sc->send_sci) -
+		int len = skb->len - macsec_hdr_len(sci_present) -
 			  secy->icv_len;
 		aead_request_set_crypt(req, sg, sg, len, iv);
-		aead_request_set_ad(req, macsec_hdr_len(tx_sc->send_sci));
+		aead_request_set_ad(req, macsec_hdr_len(sci_present));
 	} else {
 		aead_request_set_crypt(req, sg, sg, 0, iv);
 		aead_request_set_ad(req, skb->len - secy->icv_len);
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index f279a89..a52b560 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -42,19 +42,24 @@
 #define AT803X_MMD_ACCESS_CONTROL		0x0D
 #define AT803X_MMD_ACCESS_CONTROL_DATA		0x0E
 #define AT803X_FUNC_DATA			0x4003
+#define AT803X_REG_CHIP_CONFIG			0x1f
+#define AT803X_BT_BX_REG_SEL			0x8000
 
 #define AT803X_DEBUG_ADDR			0x1D
 #define AT803X_DEBUG_DATA			0x1E
 
+#define AT803X_MODE_CFG_MASK			0x0F
+#define AT803X_MODE_CFG_SGMII			0x01
+
+#define AT803X_PSSR			0x11	/*PHY-Specific Status Register*/
+#define AT803X_PSSR_MR_AN_COMPLETE	0x0200
+
 #define AT803X_DEBUG_REG_0			0x00
 #define AT803X_DEBUG_RX_CLK_DLY_EN		BIT(15)
 
 #define AT803X_DEBUG_REG_5			0x05
 #define AT803X_DEBUG_TX_CLK_DLY_EN		BIT(8)
 
-#define AT803X_REG_CHIP_CONFIG			0x1f
-#define AT803X_BT_BX_REG_SEL			0x8000
-
 #define ATH8030_PHY_ID 0x004dd076
 #define ATH8031_PHY_ID 0x004dd074
 #define ATH8035_PHY_ID 0x004dd072
@@ -209,7 +214,6 @@ static int at803x_suspend(struct phy_device *phydev)
 {
 	int value;
 	int wol_enabled;
-	int ccr;
 
 	mutex_lock(&phydev->lock);
 
@@ -225,16 +229,6 @@ static int at803x_suspend(struct phy_device *phydev)
 
 	phy_write(phydev, MII_BMCR, value);
 
-	if (phydev->interface != PHY_INTERFACE_MODE_SGMII)
-		goto done;
-
-	/* also power-down SGMII interface */
-	ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
-	phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr & ~AT803X_BT_BX_REG_SEL);
-	phy_write(phydev, MII_BMCR, phy_read(phydev, MII_BMCR) | BMCR_PDOWN);
-	phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr | AT803X_BT_BX_REG_SEL);
-
-done:
 	mutex_unlock(&phydev->lock);
 
 	return 0;
@@ -243,7 +237,6 @@ static int at803x_suspend(struct phy_device *phydev)
 static int at803x_resume(struct phy_device *phydev)
 {
 	int value;
-	int ccr;
 
 	mutex_lock(&phydev->lock);
 
@@ -251,17 +244,6 @@ static int at803x_resume(struct phy_device *phydev)
 	value &= ~(BMCR_PDOWN | BMCR_ISOLATE);
 	phy_write(phydev, MII_BMCR, value);
 
-	if (phydev->interface != PHY_INTERFACE_MODE_SGMII)
-		goto done;
-
-	/* also power-up SGMII interface */
-	ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
-	phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr & ~AT803X_BT_BX_REG_SEL);
-	value = phy_read(phydev, MII_BMCR) & ~(BMCR_PDOWN | BMCR_ISOLATE);
-	phy_write(phydev, MII_BMCR, value);
-	phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr | AT803X_BT_BX_REG_SEL);
-
-done:
 	mutex_unlock(&phydev->lock);
 
 	return 0;
@@ -381,6 +363,36 @@ static void at803x_link_change_notify(struct phy_device *phydev)
 	}
 }
 
+static int at803x_aneg_done(struct phy_device *phydev)
+{
+	int ccr;
+
+	int aneg_done = genphy_aneg_done(phydev);
+	if (aneg_done != BMSR_ANEGCOMPLETE)
+		return aneg_done;
+
+	/*
+	 * in SGMII mode, if copper side autoneg is successful,
+	 * also check SGMII side autoneg result
+	 */
+	ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
+	if ((ccr & AT803X_MODE_CFG_MASK) != AT803X_MODE_CFG_SGMII)
+		return aneg_done;
+
+	/* switch to SGMII/fiber page */
+	phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr & ~AT803X_BT_BX_REG_SEL);
+
+	/* check if the SGMII link is OK. */
+	if (!(phy_read(phydev, AT803X_PSSR) & AT803X_PSSR_MR_AN_COMPLETE)) {
+		pr_warn("803x_aneg_done: SGMII link is not ok\n");
+		aneg_done = 0;
+	}
+	/* switch back to copper page */
+	phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr | AT803X_BT_BX_REG_SEL);
+
+	return aneg_done;
+}
+
 static struct phy_driver at803x_driver[] = {
 {
 	/* ATHEROS 8035 */
@@ -432,6 +444,7 @@ static struct phy_driver at803x_driver[] = {
 	.flags			= PHY_HAS_INTERRUPT,
 	.config_aneg		= genphy_config_aneg,
 	.read_status		= genphy_read_status,
+	.aneg_done		= at803x_aneg_done,
 	.ack_interrupt		= &at803x_ack_interrupt,
 	.config_intr		= &at803x_config_intr,
 } };
diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index 03d54c4..800b39f 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -19,6 +19,7 @@
 #define TI_DP83848C_PHY_ID		0x20005ca0
 #define NS_DP83848C_PHY_ID		0x20005c90
 #define TLK10X_PHY_ID			0x2000a210
+#define TI_DP83822_PHY_ID		0x2000a240
 
 /* Registers */
 #define DP83848_MICR			0x11 /* MII Interrupt Control Register */
@@ -77,6 +78,7 @@ static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 	{ TI_DP83848C_PHY_ID, 0xfffffff0 },
 	{ NS_DP83848C_PHY_ID, 0xfffffff0 },
 	{ TLK10X_PHY_ID, 0xfffffff0 },
+	{ TI_DP83822_PHY_ID, 0xfffffff0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
@@ -105,6 +107,7 @@ static struct phy_driver dp83848_driver[] = {
 	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
+	DP83848_PHY_DRIVER(TI_DP83822_PHY_ID, "TI DP83822 10/100 Mbps PHY"),
 };
 module_phy_driver(dp83848_driver);
 
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index f79eb12..125cff5 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -433,13 +433,13 @@ int asix_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	mutex_lock(&dev->phy_mutex);
 	do {
 		ret = asix_set_sw_mii(dev, 0);
-		if (ret == -ENODEV)
+		if (ret == -ENODEV || ret == -ETIMEDOUT)
 			break;
 		usleep_range(1000, 1100);
 		ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
 				    0, 0, 1, &smsr, 0);
 	} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
-	if (ret == -ENODEV) {
+	if (ret == -ENODEV || ret == -ETIMEDOUT) {
 		mutex_unlock(&dev->phy_mutex);
 		return ret;
 	}
@@ -497,13 +497,13 @@ int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc)
 	mutex_lock(&dev->phy_mutex);
 	do {
 		ret = asix_set_sw_mii(dev, 1);
-		if (ret == -ENODEV)
+		if (ret == -ENODEV || ret == -ETIMEDOUT)
 			break;
 		usleep_range(1000, 1100);
 		ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
 				    0, 0, 1, &smsr, 1);
 	} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
-	if (ret == -ENODEV) {
+	if (ret == -ENODEV || ret == -ETIMEDOUT) {
 		mutex_unlock(&dev->phy_mutex);
 		return ret;
 	}
diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c
index 5662bab..3e37724 100644
--- a/drivers/net/usb/kalmia.c
+++ b/drivers/net/usb/kalmia.c
@@ -151,7 +151,7 @@ kalmia_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	status = kalmia_init_and_get_ethernet_addr(dev, ethernet_addr);
 
-	if (status < 0) {
+	if (status) {
 		usb_set_intfdata(intf, NULL);
 		usb_driver_release_interface(driver_of(intf), intf);
 		return status;
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index b5554f2..ef83ae3 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2279,6 +2279,7 @@ vmxnet3_set_mc(struct net_device *netdev)
 					&adapter->shared->devRead.rxFilterConf;
 	u8 *new_table = NULL;
 	dma_addr_t new_table_pa = 0;
+	bool new_table_pa_valid = false;
 	u32 new_mode = VMXNET3_RXM_UCAST;
 
 	if (netdev->flags & IFF_PROMISC) {
@@ -2307,13 +2308,15 @@ vmxnet3_set_mc(struct net_device *netdev)
 							new_table,
 							sz,
 							PCI_DMA_TODEVICE);
+				if (!dma_mapping_error(&adapter->pdev->dev,
+						       new_table_pa)) {
+					new_mode |= VMXNET3_RXM_MCAST;
+					new_table_pa_valid = true;
+					rxConf->mfTablePA = cpu_to_le64(
+								new_table_pa);
+				}
 			}
-
-			if (!dma_mapping_error(&adapter->pdev->dev,
-					       new_table_pa)) {
-				new_mode |= VMXNET3_RXM_MCAST;
-				rxConf->mfTablePA = cpu_to_le64(new_table_pa);
-			} else {
+			if (!new_table_pa_valid) {
 				netdev_info(netdev,
 					    "failed to copy mcast list, setting ALL_MULTI\n");
 				new_mode |= VMXNET3_RXM_ALL_MULTI;
@@ -2338,7 +2341,7 @@ vmxnet3_set_mc(struct net_device *netdev)
 			       VMXNET3_CMD_UPDATE_MAC_FILTERS);
 	spin_unlock_irqrestore(&adapter->cmd_lock, flags);
 
-	if (new_table_pa)
+	if (new_table_pa_valid)
 		dma_unmap_single(&adapter->pdev->dev, new_table_pa,
 				 rxConf->mfTableLen, PCI_DMA_TODEVICE);
 	kfree(new_table);
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 85c271c..820de6a 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -956,6 +956,7 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 	if (skb->pkt_type == PACKET_LOOPBACK) {
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
+		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
 		skb->pkt_type = PACKET_HOST;
 		goto out;
 	}
@@ -996,6 +997,7 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 {
 	skb->dev = vrf_dev;
 	skb->skb_iif = vrf_dev->ifindex;
+	IPCB(skb)->flags |= IPSKB_L3SLAVE;
 
 	/* loopback traffic; do not push through packet taps again.
 	 * Reset pkt_type for upper layers to process skb
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e7d1668..f3c2fa3 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -583,7 +583,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
 		}
 	}
 
-	pp = eth_gro_receive(head, skb);
+	pp = call_gro_receive(eth_gro_receive, head, skb);
 	flush = 0;
 
 out:
@@ -943,17 +943,20 @@ static bool vxlan_snoop(struct net_device *dev,
 static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
 {
 	struct vxlan_dev *vxlan;
+	struct vxlan_sock *sock4;
+	struct vxlan_sock *sock6 = NULL;
 	unsigned short family = dev->default_dst.remote_ip.sa.sa_family;
 
+	sock4 = rtnl_dereference(dev->vn4_sock);
+
 	/* The vxlan_sock is only used by dev, leaving group has
 	 * no effect on other vxlan devices.
 	 */
-	if (family == AF_INET && dev->vn4_sock &&
-	    atomic_read(&dev->vn4_sock->refcnt) == 1)
+	if (family == AF_INET && sock4 && atomic_read(&sock4->refcnt) == 1)
 		return false;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (family == AF_INET6 && dev->vn6_sock &&
-	    atomic_read(&dev->vn6_sock->refcnt) == 1)
+	sock6 = rtnl_dereference(dev->vn6_sock);
+	if (family == AF_INET6 && sock6 && atomic_read(&sock6->refcnt) == 1)
 		return false;
 #endif
 
@@ -961,10 +964,12 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
 		if (!netif_running(vxlan->dev) || vxlan == dev)
 			continue;
 
-		if (family == AF_INET && vxlan->vn4_sock != dev->vn4_sock)
+		if (family == AF_INET &&
+		    rtnl_dereference(vxlan->vn4_sock) != sock4)
 			continue;
 #if IS_ENABLED(CONFIG_IPV6)
-		if (family == AF_INET6 && vxlan->vn6_sock != dev->vn6_sock)
+		if (family == AF_INET6 &&
+		    rtnl_dereference(vxlan->vn6_sock) != sock6)
 			continue;
 #endif
 
@@ -1005,22 +1010,25 @@ static bool __vxlan_sock_release_prep(struct vxlan_sock *vs)
 
 static void vxlan_sock_release(struct vxlan_dev *vxlan)
 {
-	bool ipv4 = __vxlan_sock_release_prep(vxlan->vn4_sock);
+	struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
 #if IS_ENABLED(CONFIG_IPV6)
-	bool ipv6 = __vxlan_sock_release_prep(vxlan->vn6_sock);
+	struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+	rcu_assign_pointer(vxlan->vn6_sock, NULL);
 #endif
 
+	rcu_assign_pointer(vxlan->vn4_sock, NULL);
 	synchronize_net();
 
-	if (ipv4) {
-		udp_tunnel_sock_release(vxlan->vn4_sock->sock);
-		kfree(vxlan->vn4_sock);
+	if (__vxlan_sock_release_prep(sock4)) {
+		udp_tunnel_sock_release(sock4->sock);
+		kfree(sock4);
 	}
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (ipv6) {
-		udp_tunnel_sock_release(vxlan->vn6_sock->sock);
-		kfree(vxlan->vn6_sock);
+	if (__vxlan_sock_release_prep(sock6)) {
+		udp_tunnel_sock_release(sock6->sock);
+		kfree(sock6);
 	}
 #endif
 }
@@ -1036,18 +1044,21 @@ static int vxlan_igmp_join(struct vxlan_dev *vxlan)
 	int ret = -EINVAL;
 
 	if (ip->sa.sa_family == AF_INET) {
+		struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
 		struct ip_mreqn mreq = {
 			.imr_multiaddr.s_addr	= ip->sin.sin_addr.s_addr,
 			.imr_ifindex		= ifindex,
 		};
 
-		sk = vxlan->vn4_sock->sock->sk;
+		sk = sock4->sock->sk;
 		lock_sock(sk);
 		ret = ip_mc_join_group(sk, &mreq);
 		release_sock(sk);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
-		sk = vxlan->vn6_sock->sock->sk;
+		struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+		sk = sock6->sock->sk;
 		lock_sock(sk);
 		ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
 						   &ip->sin6.sin6_addr);
@@ -1067,18 +1078,21 @@ static int vxlan_igmp_leave(struct vxlan_dev *vxlan)
 	int ret = -EINVAL;
 
 	if (ip->sa.sa_family == AF_INET) {
+		struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
 		struct ip_mreqn mreq = {
 			.imr_multiaddr.s_addr	= ip->sin.sin_addr.s_addr,
 			.imr_ifindex		= ifindex,
 		};
 
-		sk = vxlan->vn4_sock->sock->sk;
+		sk = sock4->sock->sk;
 		lock_sock(sk);
 		ret = ip_mc_leave_group(sk, &mreq);
 		release_sock(sk);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
-		sk = vxlan->vn6_sock->sock->sk;
+		struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+		sk = sock6->sock->sk;
 		lock_sock(sk);
 		ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
 						   &ip->sin6.sin6_addr);
@@ -1828,11 +1842,15 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 					  struct dst_cache *dst_cache,
 					  const struct ip_tunnel_info *info)
 {
+	struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct dst_entry *ndst;
 	struct flowi6 fl6;
 	int err;
 
+	if (!sock6)
+		return ERR_PTR(-EIO);
+
 	if (tos && !info)
 		use_cache = false;
 	if (use_cache) {
@@ -1850,7 +1868,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 	fl6.flowi6_proto = IPPROTO_UDP;
 
 	err = ipv6_stub->ipv6_dst_lookup(vxlan->net,
-					 vxlan->vn6_sock->sock->sk,
+					 sock6->sock->sk,
 					 &ndst, &fl6);
 	if (err < 0)
 		return ERR_PTR(err);
@@ -1995,9 +2013,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (dst->sa.sa_family == AF_INET) {
-		if (!vxlan->vn4_sock)
+		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
+
+		if (!sock4)
 			goto drop;
-		sk = vxlan->vn4_sock->sock->sk;
+		sk = sock4->sock->sk;
 
 		rt = vxlan_get_route(vxlan, skb,
 				     rdst ? rdst->remote_ifindex : 0, tos,
@@ -2050,12 +2070,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				    src_port, dst_port, xnet, !udp_sum);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
+		struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
 		struct dst_entry *ndst;
 		u32 rt6i_flags;
 
-		if (!vxlan->vn6_sock)
+		if (!sock6)
 			goto drop;
-		sk = vxlan->vn6_sock->sock->sk;
+		sk = sock6->sock->sk;
 
 		ndst = vxlan6_get_route(vxlan, skb,
 					rdst ? rdst->remote_ifindex : 0, tos,
@@ -2415,9 +2436,10 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	dport = info->key.tp_dst ? : vxlan->cfg.dst_port;
 
 	if (ip_tunnel_info_af(info) == AF_INET) {
+		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
 		struct rtable *rt;
 
-		if (!vxlan->vn4_sock)
+		if (!sock4)
 			return -EINVAL;
 		rt = vxlan_get_route(vxlan, skb, 0, info->key.tos,
 				     info->key.u.ipv4.dst,
@@ -2429,8 +2451,6 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_IPV6)
 		struct dst_entry *ndst;
 
-		if (!vxlan->vn6_sock)
-			return -EINVAL;
 		ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos,
 					info->key.label, &info->key.u.ipv6.dst,
 					&info->key.u.ipv6.src, NULL, info);
@@ -2740,10 +2760,10 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 		return PTR_ERR(vs);
 #if IS_ENABLED(CONFIG_IPV6)
 	if (ipv6)
-		vxlan->vn6_sock = vs;
+		rcu_assign_pointer(vxlan->vn6_sock, vs);
 	else
 #endif
-		vxlan->vn4_sock = vs;
+		rcu_assign_pointer(vxlan->vn4_sock, vs);
 	vxlan_vs_add_dev(vs, vxlan);
 	return 0;
 }
@@ -2754,9 +2774,9 @@ static int vxlan_sock_add(struct vxlan_dev *vxlan)
 	bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA;
 	int ret = 0;
 
-	vxlan->vn4_sock = NULL;
+	RCU_INIT_POINTER(vxlan->vn4_sock, NULL);
 #if IS_ENABLED(CONFIG_IPV6)
-	vxlan->vn6_sock = NULL;
+	RCU_INIT_POINTER(vxlan->vn6_sock, NULL);
 	if (ipv6 || metadata)
 		ret = __vxlan_sock_add(vxlan, true);
 #endif
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 33ab334..4e9fe75 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -294,7 +294,7 @@
 config SLIC_DS26522
 	tristate "Slic Maxim ds26522 card support"
 	depends on SPI
-	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE
+	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE || COMPILE_TEST
 	help
 	  This module initializes and configures the slic maxim card
 	  in T1 or E1 mode.
diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c
index d06a887..b776a0a 100644
--- a/drivers/net/wan/slic_ds26522.c
+++ b/drivers/net/wan/slic_ds26522.c
@@ -223,12 +223,19 @@ static int slic_ds26522_probe(struct spi_device *spi)
 	return ret;
 }
 
+static const struct spi_device_id slic_ds26522_id[] = {
+	{ .name = "ds26522" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(spi, slic_ds26522_id);
+
 static const struct of_device_id slic_ds26522_match[] = {
 	{
 	 .compatible = "maxim,ds26522",
 	 },
 	{},
 };
+MODULE_DEVICE_TABLE(of, slic_ds26522_match);
 
 static struct spi_driver slic_ds26522_driver = {
 	.driver = {
@@ -239,6 +246,7 @@ static struct spi_driver slic_ds26522_driver = {
 		   },
 	.probe = slic_ds26522_probe,
 	.remove = slic_ds26522_remove,
+	.id_table = slic_ds26522_id,
 };
 
 static int __init slic_ds26522_init(void)
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index dda49af..521f1c5 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -450,6 +450,7 @@ struct ath10k_debug {
 	u32 pktlog_filter;
 	u32 reg_addr;
 	u32 nf_cal_period;
+	void *cal_data;
 
 	struct ath10k_fw_crash_data *fw_crash_data;
 };
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index 832da6e..82a4c67 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -30,6 +30,8 @@
 /* ms */
 #define ATH10K_DEBUG_HTT_STATS_INTERVAL 1000
 
+#define ATH10K_DEBUG_CAL_DATA_LEN 12064
+
 #define ATH10K_FW_CRASH_DUMP_VERSION 1
 
 /**
@@ -1451,56 +1453,51 @@ static const struct file_operations fops_fw_dbglog = {
 	.llseek = default_llseek,
 };
 
-static int ath10k_debug_cal_data_open(struct inode *inode, struct file *file)
+static int ath10k_debug_cal_data_fetch(struct ath10k *ar)
 {
-	struct ath10k *ar = inode->i_private;
-	void *buf;
 	u32 hi_addr;
 	__le32 addr;
 	int ret;
 
-	mutex_lock(&ar->conf_mutex);
+	lockdep_assert_held(&ar->conf_mutex);
 
-	if (ar->state != ATH10K_STATE_ON &&
-	    ar->state != ATH10K_STATE_UTF) {
-		ret = -ENETDOWN;
-		goto err;
-	}
-
-	buf = vmalloc(ar->hw_params.cal_data_len);
-	if (!buf) {
-		ret = -ENOMEM;
-		goto err;
-	}
+	if (WARN_ON(ar->hw_params.cal_data_len > ATH10K_DEBUG_CAL_DATA_LEN))
+		return -EINVAL;
 
 	hi_addr = host_interest_item_address(HI_ITEM(hi_board_data));
 
 	ret = ath10k_hif_diag_read(ar, hi_addr, &addr, sizeof(addr));
 	if (ret) {
-		ath10k_warn(ar, "failed to read hi_board_data address: %d\n", ret);
-		goto err_vfree;
+		ath10k_warn(ar, "failed to read hi_board_data address: %d\n",
+			    ret);
+		return ret;
 	}
 
-	ret = ath10k_hif_diag_read(ar, le32_to_cpu(addr), buf,
+	ret = ath10k_hif_diag_read(ar, le32_to_cpu(addr), ar->debug.cal_data,
 				   ar->hw_params.cal_data_len);
 	if (ret) {
 		ath10k_warn(ar, "failed to read calibration data: %d\n", ret);
-		goto err_vfree;
+		return ret;
 	}
 
-	file->private_data = buf;
+	return 0;
+}
 
+static int ath10k_debug_cal_data_open(struct inode *inode, struct file *file)
+{
+	struct ath10k *ar = inode->i_private;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state == ATH10K_STATE_ON ||
+	    ar->state == ATH10K_STATE_UTF) {
+		ath10k_debug_cal_data_fetch(ar);
+	}
+
+	file->private_data = ar;
 	mutex_unlock(&ar->conf_mutex);
 
 	return 0;
-
-err_vfree:
-	vfree(buf);
-
-err:
-	mutex_unlock(&ar->conf_mutex);
-
-	return ret;
 }
 
 static ssize_t ath10k_debug_cal_data_read(struct file *file,
@@ -1508,18 +1505,16 @@ static ssize_t ath10k_debug_cal_data_read(struct file *file,
 					  size_t count, loff_t *ppos)
 {
 	struct ath10k *ar = file->private_data;
-	void *buf = file->private_data;
 
-	return simple_read_from_buffer(user_buf, count, ppos,
-				       buf, ar->hw_params.cal_data_len);
-}
+	mutex_lock(&ar->conf_mutex);
 
-static int ath10k_debug_cal_data_release(struct inode *inode,
-					 struct file *file)
-{
-	vfree(file->private_data);
+	count = simple_read_from_buffer(user_buf, count, ppos,
+					ar->debug.cal_data,
+					ar->hw_params.cal_data_len);
 
-	return 0;
+	mutex_unlock(&ar->conf_mutex);
+
+	return count;
 }
 
 static ssize_t ath10k_write_ani_enable(struct file *file,
@@ -1580,7 +1575,6 @@ static const struct file_operations fops_ani_enable = {
 static const struct file_operations fops_cal_data = {
 	.open = ath10k_debug_cal_data_open,
 	.read = ath10k_debug_cal_data_read,
-	.release = ath10k_debug_cal_data_release,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
 };
@@ -1932,6 +1926,8 @@ void ath10k_debug_stop(struct ath10k *ar)
 {
 	lockdep_assert_held(&ar->conf_mutex);
 
+	ath10k_debug_cal_data_fetch(ar);
+
 	/* Must not use _sync to avoid deadlock, we do that in
 	 * ath10k_debug_destroy(). The check for htt_stats_mask is to avoid
 	 * warning from del_timer(). */
@@ -2344,6 +2340,10 @@ int ath10k_debug_create(struct ath10k *ar)
 	if (!ar->debug.fw_crash_data)
 		return -ENOMEM;
 
+	ar->debug.cal_data = vzalloc(ATH10K_DEBUG_CAL_DATA_LEN);
+	if (!ar->debug.cal_data)
+		return -ENOMEM;
+
 	INIT_LIST_HEAD(&ar->debug.fw_stats.pdevs);
 	INIT_LIST_HEAD(&ar->debug.fw_stats.vdevs);
 	INIT_LIST_HEAD(&ar->debug.fw_stats.peers);
@@ -2357,6 +2357,9 @@ void ath10k_debug_destroy(struct ath10k *ar)
 	vfree(ar->debug.fw_crash_data);
 	ar->debug.fw_crash_data = NULL;
 
+	vfree(ar->debug.cal_data);
+	ar->debug.cal_data = NULL;
+
 	ath10k_debug_fw_stats_reset(ar);
 
 	kfree(ar->debug.tpc_stats);
diff --git a/drivers/net/wireless/ath/ath6kl/sdio.c b/drivers/net/wireless/ath/ath6kl/sdio.c
index eab0ab9..76eb336 100644
--- a/drivers/net/wireless/ath/ath6kl/sdio.c
+++ b/drivers/net/wireless/ath/ath6kl/sdio.c
@@ -1401,6 +1401,7 @@ static const struct sdio_device_id ath6kl_sdio_devices[] = {
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x0))},
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x1))},
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x2))},
+	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x18))},
 	{},
 };
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_calib.c b/drivers/net/wireless/ath/ath9k/ar9003_calib.c
index b6f064a..7e27a06 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_calib.c
@@ -33,7 +33,6 @@ struct coeff {
 
 enum ar9003_cal_types {
 	IQ_MISMATCH_CAL = BIT(0),
-	TEMP_COMP_CAL = BIT(1),
 };
 
 static void ar9003_hw_setup_calibration(struct ath_hw *ah,
@@ -59,12 +58,6 @@ static void ar9003_hw_setup_calibration(struct ath_hw *ah,
 		/* Kick-off cal */
 		REG_SET_BIT(ah, AR_PHY_TIMING4, AR_PHY_TIMING4_DO_CAL);
 		break;
-	case TEMP_COMP_CAL:
-		ath_dbg(common, CALIBRATE,
-			"starting Temperature Compensation Calibration\n");
-		REG_SET_BIT(ah, AR_CH0_THERM, AR_CH0_THERM_LOCAL);
-		REG_SET_BIT(ah, AR_CH0_THERM, AR_CH0_THERM_START);
-		break;
 	default:
 		ath_err(common, "Invalid calibration type\n");
 		break;
@@ -93,8 +86,7 @@ static bool ar9003_hw_per_calibration(struct ath_hw *ah,
 		/*
 		* Accumulate cal measures for active chains
 		*/
-		if (cur_caldata->calCollect)
-			cur_caldata->calCollect(ah);
+		cur_caldata->calCollect(ah);
 		ah->cal_samples++;
 
 		if (ah->cal_samples >= cur_caldata->calNumSamples) {
@@ -107,8 +99,7 @@ static bool ar9003_hw_per_calibration(struct ath_hw *ah,
 			/*
 			* Process accumulated data
 			*/
-			if (cur_caldata->calPostProc)
-				cur_caldata->calPostProc(ah, numChains);
+			cur_caldata->calPostProc(ah, numChains);
 
 			/* Calibration has finished. */
 			caldata->CalValid |= cur_caldata->calType;
@@ -323,16 +314,9 @@ static const struct ath9k_percal_data iq_cal_single_sample = {
 	ar9003_hw_iqcalibrate
 };
 
-static const struct ath9k_percal_data temp_cal_single_sample = {
-	TEMP_COMP_CAL,
-	MIN_CAL_SAMPLES,
-	PER_MAX_LOG_COUNT,
-};
-
 static void ar9003_hw_init_cal_settings(struct ath_hw *ah)
 {
 	ah->iq_caldata.calData = &iq_cal_single_sample;
-	ah->temp_caldata.calData = &temp_cal_single_sample;
 
 	if (AR_SREV_9300_20_OR_LATER(ah)) {
 		ah->enabled_cals |= TX_IQ_CAL;
@@ -340,7 +324,7 @@ static void ar9003_hw_init_cal_settings(struct ath_hw *ah)
 			ah->enabled_cals |= TX_IQ_ON_AGC_CAL;
 	}
 
-	ah->supp_cals = IQ_MISMATCH_CAL | TEMP_COMP_CAL;
+	ah->supp_cals = IQ_MISMATCH_CAL;
 }
 
 #define OFF_UPPER_LT 24
@@ -1399,9 +1383,6 @@ static void ar9003_hw_init_cal_common(struct ath_hw *ah)
 	INIT_CAL(&ah->iq_caldata);
 	INSERT_CAL(ah, &ah->iq_caldata);
 
-	INIT_CAL(&ah->temp_caldata);
-	INSERT_CAL(ah, &ah->temp_caldata);
-
 	/* Initialize current pointer to first element in list */
 	ah->cal_list_curr = ah->cal_list;
 
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 2a5d3ad..9cbca12 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -830,7 +830,6 @@ struct ath_hw {
 	/* Calibration */
 	u32 supp_cals;
 	struct ath9k_cal_list iq_caldata;
-	struct ath9k_cal_list temp_caldata;
 	struct ath9k_cal_list adcgain_caldata;
 	struct ath9k_cal_list adcdc_caldata;
 	struct ath9k_cal_list *cal_list;
diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
index 9448012..274dd5a 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
@@ -45,7 +45,7 @@ static int mwifiex_11n_dispatch_amsdu_pkt(struct mwifiex_private *priv,
 		skb_trim(skb, le16_to_cpu(local_rx_pd->rx_pkt_length));
 
 		ieee80211_amsdu_to_8023s(skb, &list, priv->curr_addr,
-					 priv->wdev.iftype, 0, false);
+					 priv->wdev.iftype, 0, NULL, NULL);
 
 		while (!skb_queue_empty(&list)) {
 			struct rx_packet_hdr *rx_hdr;
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
index 10166289..08d587a 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
@@ -238,7 +238,7 @@ struct rtl8xxxu_rxdesc16 {
 	u32 pattern1match:1;
 	u32 pattern0match:1;
 #endif
-	__le32 tsfl;
+	u32 tsfl;
 #if 0
 	u32 bassn:12;
 	u32 bavld:1;
@@ -368,7 +368,7 @@ struct rtl8xxxu_rxdesc24 {
 	u32 ldcp:1;
 	u32 splcp:1;
 #endif
-	__le32 tsfl;
+	u32 tsfl;
 };
 
 struct rtl8xxxu_txdesc32 {
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
index df54d27..a793fed 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
@@ -1461,7 +1461,9 @@ static int rtl8192eu_active_to_emu(struct rtl8xxxu_priv *priv)
 	int count, ret = 0;
 
 	/* Turn off RF */
-	rtl8xxxu_write8(priv, REG_RF_CTRL, 0);
+	val8 = rtl8xxxu_read8(priv, REG_RF_CTRL);
+	val8 &= ~RF_ENABLE;
+	rtl8xxxu_write8(priv, REG_RF_CTRL, val8);
 
 	/* Switch DPDT_SEL_P output from register 0x65[2] */
 	val8 = rtl8xxxu_read8(priv, REG_LEDCFG2);
@@ -1593,6 +1595,10 @@ static void rtl8192e_enable_rf(struct rtl8xxxu_priv *priv)
 	u32 val32;
 	u8 val8;
 
+	val32 = rtl8xxxu_read32(priv, REG_RX_WAIT_CCA);
+	val32 |= (BIT(22) | BIT(23));
+	rtl8xxxu_write32(priv, REG_RX_WAIT_CCA, val32);
+
 	val8 = rtl8xxxu_read8(priv, REG_GPIO_MUXCFG);
 	val8 |= BIT(5);
 	rtl8xxxu_write8(priv, REG_GPIO_MUXCFG, val8);
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
index 6c086b5..02b8ddd 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
@@ -1498,6 +1498,10 @@ static void rtl8723b_enable_rf(struct rtl8xxxu_priv *priv)
 	u32 val32;
 	u8 val8;
 
+	val32 = rtl8xxxu_read32(priv, REG_RX_WAIT_CCA);
+	val32 |= (BIT(22) | BIT(23));
+	rtl8xxxu_write32(priv, REG_RX_WAIT_CCA, val32);
+
 	/*
 	 * No indication anywhere as to what 0x0790 does. The 2 antenna
 	 * vendor code preserves bits 6-7 here.
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index b2d7f6e..a5e6ec2 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -5197,7 +5197,12 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb)
 		pkt_offset = roundup(pkt_len + drvinfo_sz + desc_shift +
 				     sizeof(struct rtl8xxxu_rxdesc16), 128);
 
-		if (pkt_cnt > 1)
+		/*
+		 * Only clone the skb if there's enough data at the end to
+		 * at least cover the rx descriptor
+		 */
+		if (pkt_cnt > 1 &&
+		    urb_len > (pkt_offset + sizeof(struct rtl8xxxu_rxdesc16)))
 			next_skb = skb_clone(skb, GFP_ATOMIC);
 
 		rx_status = IEEE80211_SKB_RXCB(skb);
@@ -5215,7 +5220,7 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb)
 			rtl8xxxu_rx_parse_phystats(priv, rx_status, phy_stats,
 						   rx_desc->rxmcs);
 
-		rx_status->mactime = le32_to_cpu(rx_desc->tsfl);
+		rx_status->mactime = rx_desc->tsfl;
 		rx_status->flag |= RX_FLAG_MACTIME_START;
 
 		if (!rx_desc->swdec)
@@ -5285,7 +5290,7 @@ int rtl8xxxu_parse_rxdesc24(struct rtl8xxxu_priv *priv, struct sk_buff *skb)
 		rtl8xxxu_rx_parse_phystats(priv, rx_status, phy_stats,
 					   rx_desc->rxmcs);
 
-	rx_status->mactime = le32_to_cpu(rx_desc->tsfl);
+	rx_status->mactime = rx_desc->tsfl;
 	rx_status->flag |= RX_FLAG_MACTIME_START;
 
 	if (!rx_desc->swdec)
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index f95760c..8e7f23c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -111,7 +111,7 @@ static void rtl_fw_do_work(const struct firmware *firmware, void *context,
 			if (!err)
 				goto found_alt;
 		}
-		pr_err("Firmware %s not available\n", rtlpriv->cfg->fw_name);
+		pr_err("Selected firmware is not available\n");
 		rtlpriv->max_fw_size = 0;
 		return;
 	}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
index e7b11b4..f361808 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
@@ -86,6 +86,7 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	u8 tid;
+	char *fw_name;
 
 	rtl8188ee_bt_reg_init(hw);
 	rtlpriv->dm.dm_initialgain_enable = 1;
@@ -169,10 +170,10 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw)
 		return 1;
 	}
 
-	rtlpriv->cfg->fw_name = "rtlwifi/rtl8188efw.bin";
+	fw_name = "rtlwifi/rtl8188efw.bin";
 	rtlpriv->max_fw_size = 0x8000;
-	pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
-	err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+	pr_info("Using firmware %s\n", fw_name);
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
@@ -284,7 +285,6 @@ static const struct rtl_hal_cfg rtl88ee_hal_cfg = {
 	.bar_id = 2,
 	.write_readback = true,
 	.name = "rtl88e_pci",
-	.fw_name = "rtlwifi/rtl8188efw.bin",
 	.ops = &rtl8188ee_hal_ops,
 	.mod_params = &rtl88ee_mod_params,
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
index 87aa209..8b6e37c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
@@ -96,6 +96,7 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	char *fw_name = "rtlwifi/rtl8192cfwU.bin";
 
 	rtl8192ce_bt_reg_init(hw);
 
@@ -167,15 +168,12 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
 	}
 
 	/* request fw */
-	if (IS_VENDOR_UMC_A_CUT(rtlhal->version) &&
-	    !IS_92C_SERIAL(rtlhal->version))
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cfwU.bin";
-	else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cfwU_B.bin";
+	if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
+		fw_name = "rtlwifi/rtl8192cfwU_B.bin";
 
 	rtlpriv->max_fw_size = 0x4000;
-	pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
-	err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+	pr_info("Using firmware %s\n", fw_name);
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
@@ -262,7 +260,6 @@ static const struct rtl_hal_cfg rtl92ce_hal_cfg = {
 	.bar_id = 2,
 	.write_readback = true,
 	.name = "rtl92c_pci",
-	.fw_name = "rtlwifi/rtl8192cfw.bin",
 	.ops = &rtl8192ce_hal_ops,
 	.mod_params = &rtl92ce_mod_params,
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
index 7c6f7f0..f953320 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
@@ -59,6 +59,7 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	int err;
+	char *fw_name;
 
 	rtlpriv->dm.dm_initialgain_enable = true;
 	rtlpriv->dm.dm_flag = 0;
@@ -77,18 +78,18 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw)
 	}
 	if (IS_VENDOR_UMC_A_CUT(rtlpriv->rtlhal.version) &&
 	    !IS_92C_SERIAL(rtlpriv->rtlhal.version)) {
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_A.bin";
+		fw_name = "rtlwifi/rtl8192cufw_A.bin";
 	} else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlpriv->rtlhal.version)) {
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_B.bin";
+		fw_name = "rtlwifi/rtl8192cufw_B.bin";
 	} else {
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_TMSC.bin";
+		fw_name = "rtlwifi/rtl8192cufw_TMSC.bin";
 	}
 	/* provide name of alternative file */
 	rtlpriv->cfg->alt_fw_name = "rtlwifi/rtl8192cufw.bin";
-	pr_info("Loading firmware %s\n", rtlpriv->cfg->fw_name);
+	pr_info("Loading firmware %s\n", fw_name);
 	rtlpriv->max_fw_size = 0x4000;
 	err = request_firmware_nowait(THIS_MODULE, 1,
-				      rtlpriv->cfg->fw_name, rtlpriv->io.dev,
+				      fw_name, rtlpriv->io.dev,
 				      GFP_KERNEL, hw, rtl_fw_cb);
 	return err;
 }
@@ -187,7 +188,6 @@ static struct rtl_hal_usbint_cfg rtl92cu_interface_cfg = {
 
 static struct rtl_hal_cfg rtl92cu_hal_cfg = {
 	.name = "rtl92c_usb",
-	.fw_name = "rtlwifi/rtl8192cufw.bin",
 	.ops = &rtl8192cu_hal_ops,
 	.mod_params = &rtl92cu_mod_params,
 	.usb_interface_cfg = &rtl92cu_interface_cfg,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
index 0538a4d..1ebfee1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
@@ -92,6 +92,7 @@ static int rtl92d_init_sw_vars(struct ieee80211_hw *hw)
 	u8 tid;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
+	char *fw_name = "rtlwifi/rtl8192defw.bin";
 
 	rtlpriv->dm.dm_initialgain_enable = true;
 	rtlpriv->dm.dm_flag = 0;
@@ -181,10 +182,10 @@ static int rtl92d_init_sw_vars(struct ieee80211_hw *hw)
 
 	rtlpriv->max_fw_size = 0x8000;
 	pr_info("Driver for Realtek RTL8192DE WLAN interface\n");
-	pr_info("Loading firmware file %s\n", rtlpriv->cfg->fw_name);
+	pr_info("Loading firmware file %s\n", fw_name);
 
 	/* request fw */
-	err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
@@ -266,7 +267,6 @@ static const struct rtl_hal_cfg rtl92de_hal_cfg = {
 	.bar_id = 2,
 	.write_readback = true,
 	.name = "rtl8192de",
-	.fw_name = "rtlwifi/rtl8192defw.bin",
 	.ops = &rtl8192de_hal_ops,
 	.mod_params = &rtl92de_mod_params,
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
index ac299cb..46b605de3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
@@ -91,6 +91,7 @@ int rtl92ee_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	int err = 0;
+	char *fw_name;
 
 	rtl92ee_bt_reg_init(hw);
 	rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support;
@@ -170,11 +171,11 @@ int rtl92ee_init_sw_vars(struct ieee80211_hw *hw)
 	}
 
 	/* request fw */
-	rtlpriv->cfg->fw_name = "rtlwifi/rtl8192eefw.bin";
+	fw_name = "rtlwifi/rtl8192eefw.bin";
 
 	rtlpriv->max_fw_size = 0x8000;
-	pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
-	err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+	pr_info("Using firmware %s\n", fw_name);
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
@@ -266,7 +267,6 @@ static const struct rtl_hal_cfg rtl92ee_hal_cfg = {
 	.bar_id = 2,
 	.write_readback = true,
 	.name = "rtl92ee_pci",
-	.fw_name = "rtlwifi/rtl8192eefw.bin",
 	.ops = &rtl8192ee_hal_ops,
 	.mod_params = &rtl92ee_mod_params,
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
index 5e8e02d..3e1eaea 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
@@ -89,12 +89,13 @@ static void rtl92se_fw_cb(const struct firmware *firmware, void *context)
 	struct ieee80211_hw *hw = context;
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rt_firmware *pfirmware = NULL;
+	char *fw_name = "rtlwifi/rtl8192sefw.bin";
 
 	RT_TRACE(rtlpriv, COMP_ERR, DBG_LOUD,
 			 "Firmware callback routine entered!\n");
 	complete(&rtlpriv->firmware_loading_complete);
 	if (!firmware) {
-		pr_err("Firmware %s not available\n", rtlpriv->cfg->fw_name);
+		pr_err("Firmware %s not available\n", fw_name);
 		rtlpriv->max_fw_size = 0;
 		return;
 	}
@@ -117,6 +118,7 @@ static int rtl92s_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	int err = 0;
 	u16 earlyrxthreshold = 7;
+	char *fw_name = "rtlwifi/rtl8192sefw.bin";
 
 	rtlpriv->dm.dm_initialgain_enable = true;
 	rtlpriv->dm.dm_flag = 0;
@@ -214,9 +216,9 @@ static int rtl92s_init_sw_vars(struct ieee80211_hw *hw)
 	rtlpriv->max_fw_size = RTL8190_MAX_FIRMWARE_CODE_SIZE*2 +
 			       sizeof(struct fw_hdr);
 	pr_info("Driver for Realtek RTL8192SE/RTL8191SE\n"
-		"Loading firmware %s\n", rtlpriv->cfg->fw_name);
+		"Loading firmware %s\n", fw_name);
 	/* request fw */
-	err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl92se_fw_cb);
 	if (err) {
@@ -310,7 +312,6 @@ static const struct rtl_hal_cfg rtl92se_hal_cfg = {
 	.bar_id = 1,
 	.write_readback = false,
 	.name = "rtl92s_pci",
-	.fw_name = "rtlwifi/rtl8192sefw.bin",
 	.ops = &rtl8192se_hal_ops,
 	.mod_params = &rtl92se_mod_params,
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
index 89c828a..c51a9e8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
@@ -94,6 +94,7 @@ int rtl8723e_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
 	int err = 0;
+	char *fw_name = "rtlwifi/rtl8723fw.bin";
 
 	rtl8723e_bt_reg_init(hw);
 
@@ -176,14 +177,12 @@ int rtl8723e_init_sw_vars(struct ieee80211_hw *hw)
 		return 1;
 	}
 
-	if (IS_VENDOR_8723_A_CUT(rtlhal->version))
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8723fw.bin";
-	else if (IS_81xxC_VENDOR_UMC_B_CUT(rtlhal->version))
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8723fw_B.bin";
+	if (IS_81xxC_VENDOR_UMC_B_CUT(rtlhal->version))
+		fw_name = "rtlwifi/rtl8723fw_B.bin";
 
 	rtlpriv->max_fw_size = 0x6000;
-	pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
-	err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+	pr_info("Using firmware %s\n", fw_name);
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
@@ -280,7 +279,6 @@ static const struct rtl_hal_cfg rtl8723e_hal_cfg = {
 	.bar_id = 2,
 	.write_readback = true,
 	.name = "rtl8723e_pci",
-	.fw_name = "rtlwifi/rtl8723efw.bin",
 	.ops = &rtl8723e_hal_ops,
 	.mod_params = &rtl8723e_mod_params,
 	.maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
index 20b53f0..847644d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
@@ -91,6 +91,7 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
+	char *fw_name = "rtlwifi/rtl8723befw.bin";
 
 	rtl8723be_bt_reg_init(hw);
 	rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer();
@@ -184,8 +185,8 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw)
 	}
 
 	rtlpriv->max_fw_size = 0x8000;
-	pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
-	err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+	pr_info("Using firmware %s\n", fw_name);
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
@@ -280,7 +281,6 @@ static const struct rtl_hal_cfg rtl8723be_hal_cfg = {
 	.bar_id = 2,
 	.write_readback = true,
 	.name = "rtl8723be_pci",
-	.fw_name = "rtlwifi/rtl8723befw.bin",
 	.ops = &rtl8723be_hal_ops,
 	.mod_params = &rtl8723be_mod_params,
 	.maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
index 22f687b1..297938e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
@@ -93,6 +93,7 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+	char *fw_name, *wowlan_fw_name;
 
 	rtl8821ae_bt_reg_init(hw);
 	rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer();
@@ -203,17 +204,17 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw)
 	}
 
 	if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8812aefw.bin";
-		rtlpriv->cfg->wowlan_fw_name = "rtlwifi/rtl8812aefw_wowlan.bin";
+		fw_name = "rtlwifi/rtl8812aefw.bin";
+		wowlan_fw_name = "rtlwifi/rtl8812aefw_wowlan.bin";
 	} else {
-		rtlpriv->cfg->fw_name = "rtlwifi/rtl8821aefw.bin";
-		rtlpriv->cfg->wowlan_fw_name = "rtlwifi/rtl8821aefw_wowlan.bin";
+		fw_name = "rtlwifi/rtl8821aefw.bin";
+		wowlan_fw_name = "rtlwifi/rtl8821aefw_wowlan.bin";
 	}
 
 	rtlpriv->max_fw_size = 0x8000;
 	/*load normal firmware*/
-	pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
-	err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+	pr_info("Using firmware %s\n", fw_name);
+	err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_fw_cb);
 	if (err) {
@@ -222,9 +223,9 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw)
 		return 1;
 	}
 	/*load wowlan firmware*/
-	pr_info("Using firmware %s\n", rtlpriv->cfg->wowlan_fw_name);
+	pr_info("Using firmware %s\n", wowlan_fw_name);
 	err = request_firmware_nowait(THIS_MODULE, 1,
-				      rtlpriv->cfg->wowlan_fw_name,
+				      wowlan_fw_name,
 				      rtlpriv->io.dev, GFP_KERNEL, hw,
 				      rtl_wowlan_fw_cb);
 	if (err) {
@@ -320,7 +321,6 @@ static const struct rtl_hal_cfg rtl8821ae_hal_cfg = {
 	.bar_id = 2,
 	.write_readback = true,
 	.name = "rtl8821ae_pci",
-	.fw_name = "rtlwifi/rtl8821aefw.bin",
 	.ops = &rtl8821ae_hal_ops,
 	.mod_params = &rtl8821ae_mod_params,
 	.maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL,
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 595f7d5..dafe486 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2278,9 +2278,7 @@ struct rtl_hal_cfg {
 	u8 bar_id;
 	bool write_readback;
 	char *name;
-	char *fw_name;
 	char *alt_fw_name;
-	char *wowlan_fw_name;
 	struct rtl_hal_ops *ops;
 	struct rtl_mod_params *mod_params;
 	struct rtl_hal_usbint_cfg *usb_interface_cfg;
diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index a6e94b1..47fe7f9 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -391,7 +391,6 @@ static void wl1271_remove(struct sdio_func *func)
 	pm_runtime_get_noresume(&func->dev);
 
 	platform_device_unregister(glue->core);
-	kfree(glue);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index 8b2b740..124c243 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -89,7 +89,7 @@
 	  Select Y if unsure
 
 config NVDIMM_DAX
-	tristate "NVDIMM DAX: Raw access to persistent memory"
+	bool "NVDIMM DAX: Raw access to persistent memory"
 	default LIBNVDIMM
 	depends on NVDIMM_PFN
 	help
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 3509cff..abe5c6b 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -2176,12 +2176,14 @@ static struct device **scan_labels(struct nd_region *nd_region)
 	return devs;
 
  err:
-	for (i = 0; devs[i]; i++)
-		if (is_nd_blk(&nd_region->dev))
-			namespace_blk_release(devs[i]);
-		else
-			namespace_pmem_release(devs[i]);
-	kfree(devs);
+	if (devs) {
+		for (i = 0; devs[i]; i++)
+			if (is_nd_blk(&nd_region->dev))
+				namespace_blk_release(devs[i]);
+			else
+				namespace_pmem_release(devs[i]);
+		kfree(devs);
+	}
 	return NULL;
 }
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 42b3a82..2461843 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -47,7 +47,7 @@ static struct nd_region *to_region(struct pmem_device *pmem)
 	return to_nd_region(to_dev(pmem)->parent);
 }
 
-static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
+static int pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
 		unsigned int len)
 {
 	struct device *dev = to_dev(pmem);
@@ -62,8 +62,12 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
 				__func__, (unsigned long long) sector,
 				cleared / 512, cleared / 512 > 1 ? "s" : "");
 		badblocks_clear(&pmem->bb, sector, cleared / 512);
+	} else {
+		return -EIO;
 	}
+
 	invalidate_pmem(pmem->virt_addr + offset, len);
+	return 0;
 }
 
 static void write_pmem(void *pmem_addr, struct page *page,
@@ -123,7 +127,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 		flush_dcache_page(page);
 		write_pmem(pmem_addr, page, off, len);
 		if (unlikely(bad_pmem)) {
-			pmem_clear_poison(pmem, pmem_off, len);
+			rc = pmem_clear_poison(pmem, pmem_off, len);
 			write_pmem(pmem_addr, page, off, len);
 		}
 	}
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 035f50c..bed1999 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -637,8 +637,6 @@ int dw_pcie_host_init(struct pcie_port *pp)
 		}
 	}
 
-	pp->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pp);
-
 	if (pp->ops->host_init)
 		pp->ops->host_init(pp);
 
@@ -809,6 +807,11 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 {
 	u32 val;
 
+	/* get iATU unroll support */
+	pp->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pp);
+	dev_dbg(pp->dev, "iATU unroll: %s\n",
+		pp->iatu_unroll_enabled ? "enabled" : "disabled");
+
 	/* set the number of lanes */
 	val = dw_pcie_readl_rc(pp, PCIE_PORT_LINK_CONTROL);
 	val &= ~PORT_LINK_MODE_MASK;
diff --git a/drivers/pci/host/pcie-qcom.c b/drivers/pci/host/pcie-qcom.c
index ef0a84c..3593640 100644
--- a/drivers/pci/host/pcie-qcom.c
+++ b/drivers/pci/host/pcie-qcom.c
@@ -533,11 +533,11 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 	if (IS_ERR(pcie->phy))
 		return PTR_ERR(pcie->phy);
 
+	pp->dev = dev;
 	ret = pcie->ops->get_resources(pcie);
 	if (ret)
 		return ret;
 
-	pp->dev = dev;
 	pp->root_bus_nr = -1;
 	pp->ops = &qcom_pcie_dw_ops;
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index bfdd074..ad70507 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -610,6 +610,7 @@ static int msi_verify_entries(struct pci_dev *dev)
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
  * @nvec: number of interrupts to allocate
+ * @affinity: flag to indicate cpu irq affinity mask should be set
  *
  * Setup the MSI capability structure of the device with the requested
  * number of interrupts.  A return value of zero indicates the successful
@@ -752,6 +753,7 @@ static void msix_program_entries(struct pci_dev *dev,
  * @dev: pointer to the pci_dev data structure of MSI-X device function
  * @entries: pointer to an array of struct msix_entry entries
  * @nvec: number of @entries
+ * @affinity: flag to indicate cpu irq affinity mask should be set
  *
  * Setup the MSI-X capability structure of device function with a
  * single MSI-X irq. A return of zero indicates the successful setup of
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 67426c0..5c1519b 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2754,7 +2754,7 @@ static int _regulator_set_voltage_time(struct regulator_dev *rdev,
 		ramp_delay = rdev->desc->ramp_delay;
 
 	if (ramp_delay == 0) {
-		rdev_warn(rdev, "ramp_delay not set\n");
+		rdev_dbg(rdev, "ramp_delay not set\n");
 		return 0;
 	}
 
diff --git a/drivers/reset/reset-uniphier.c b/drivers/reset/reset-uniphier.c
index 8b2558e..968c3ae 100644
--- a/drivers/reset/reset-uniphier.c
+++ b/drivers/reset/reset-uniphier.c
@@ -154,7 +154,7 @@ const struct uniphier_reset_data uniphier_sld3_mio_reset_data[] = {
 	UNIPHIER_RESET_END,
 };
 
-const struct uniphier_reset_data uniphier_pro5_mio_reset_data[] = {
+const struct uniphier_reset_data uniphier_pro5_sd_reset_data[] = {
 	UNIPHIER_MIO_RESET_SD(0, 0),
 	UNIPHIER_MIO_RESET_SD(1, 1),
 	UNIPHIER_MIO_RESET_EMMC_HW_RESET(6, 1),
@@ -360,7 +360,7 @@ static const struct of_device_id uniphier_reset_match[] = {
 		.compatible = "socionext,uniphier-ld20-reset",
 		.data = uniphier_ld20_sys_reset_data,
 	},
-	/* Media I/O reset */
+	/* Media I/O reset, SD reset */
 	{
 		.compatible = "socionext,uniphier-sld3-mio-reset",
 		.data = uniphier_sld3_mio_reset_data,
@@ -378,20 +378,20 @@ static const struct of_device_id uniphier_reset_match[] = {
 		.data = uniphier_sld3_mio_reset_data,
 	},
 	{
-		.compatible = "socionext,uniphier-pro5-mio-reset",
-		.data = uniphier_pro5_mio_reset_data,
+		.compatible = "socionext,uniphier-pro5-sd-reset",
+		.data = uniphier_pro5_sd_reset_data,
 	},
 	{
-		.compatible = "socionext,uniphier-pxs2-mio-reset",
-		.data = uniphier_pro5_mio_reset_data,
+		.compatible = "socionext,uniphier-pxs2-sd-reset",
+		.data = uniphier_pro5_sd_reset_data,
 	},
 	{
 		.compatible = "socionext,uniphier-ld11-mio-reset",
 		.data = uniphier_sld3_mio_reset_data,
 	},
 	{
-		.compatible = "socionext,uniphier-ld20-mio-reset",
-		.data = uniphier_pro5_mio_reset_data,
+		.compatible = "socionext,uniphier-ld20-sd-reset",
+		.data = uniphier_pro5_sd_reset_data,
 	},
 	/* Peripheral reset */
 	{
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 831935a..a7a8847 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1205,7 +1205,7 @@ static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm)
 				 mdc, lpm);
 			return mdc;
 		}
-		fcx_max_data = mdc * FCX_MAX_DATA_FACTOR;
+		fcx_max_data = (u32)mdc * FCX_MAX_DATA_FACTOR;
 		if (fcx_max_data < private->fcx_max_data) {
 			dev_warn(&device->cdev->dev,
 				 "The maximum data size for zHPF requests %u "
@@ -1675,7 +1675,7 @@ static u32 get_fcx_max_data(struct dasd_device *device)
 			 " data size for zHPF requests failed\n");
 		return 0;
 	} else
-		return mdc * FCX_MAX_DATA_FACTOR;
+		return (u32)mdc * FCX_MAX_DATA_FACTOR;
 }
 
 /*
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index 46be25c..876c7e6 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -780,7 +780,7 @@ static int cfg_wait_idle(void)
 static int __init chp_init(void)
 {
 	struct chp_id chpid;
-	int ret;
+	int state, ret;
 
 	ret = crw_register_handler(CRW_RSC_CPATH, chp_process_crw);
 	if (ret)
@@ -791,7 +791,9 @@ static int __init chp_init(void)
 		return 0;
 	/* Register available channel-paths. */
 	chp_id_for_each(&chpid) {
-		if (chp_info_get_status(chpid) != CHP_STATUS_NOT_RECOGNIZED)
+		state = chp_info_get_status(chpid);
+		if (state == CHP_STATUS_CONFIGURED ||
+		    state == CHP_STATUS_STANDBY)
 			chp_new(chpid);
 	}
 
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index db27390..790babc 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -353,7 +353,7 @@ static void NCR5380_print_phase(struct Scsi_Host *instance)
 #endif
 
 
-static int probe_irq __initdata;
+static int probe_irq;
 
 /**
  * probe_intr	-	helper for IRQ autoprobe
@@ -365,7 +365,7 @@ static int probe_irq __initdata;
  * used by the IRQ probe code.
  */
 
-static irqreturn_t __init probe_intr(int irq, void *dev_id)
+static irqreturn_t probe_intr(int irq, void *dev_id)
 {
 	probe_irq = irq;
 	return IRQ_HANDLED;
@@ -380,7 +380,7 @@ static irqreturn_t __init probe_intr(int irq, void *dev_id)
  * and then looking to see what interrupt actually turned up.
  */
 
-static int __init __maybe_unused NCR5380_probe_irq(struct Scsi_Host *instance,
+static int __maybe_unused NCR5380_probe_irq(struct Scsi_Host *instance,
 						int possible)
 {
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 3d53d63..f0cfb04 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -2636,18 +2636,9 @@ static int arcmsr_queue_command_lck(struct scsi_cmnd *cmd,
 	struct AdapterControlBlock *acb = (struct AdapterControlBlock *) host->hostdata;
 	struct CommandControlBlock *ccb;
 	int target = cmd->device->id;
-	int lun = cmd->device->lun;
-	uint8_t scsicmd = cmd->cmnd[0];
 	cmd->scsi_done = done;
 	cmd->host_scribble = NULL;
 	cmd->result = 0;
-	if ((scsicmd == SYNCHRONIZE_CACHE) ||(scsicmd == SEND_DIAGNOSTIC)){
-		if(acb->devstate[target][lun] == ARECA_RAID_GONE) {
-    			cmd->result = (DID_NO_CONNECT << 16);
-		}
-		cmd->scsi_done(cmd);
-		return 0;
-	}
 	if (target == 16) {
 		/* virtual device for iop message transfer */
 		arcmsr_handle_virtual_command(acb, cmd);
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 68138a6..d9239c2 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -900,8 +900,9 @@ void hwi_ring_cq_db(struct beiscsi_hba *phba,
 static struct sgl_handle *alloc_io_sgl_handle(struct beiscsi_hba *phba)
 {
 	struct sgl_handle *psgl_handle;
+	unsigned long flags;
 
-	spin_lock_bh(&phba->io_sgl_lock);
+	spin_lock_irqsave(&phba->io_sgl_lock, flags);
 	if (phba->io_sgl_hndl_avbl) {
 		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_IO,
 			    "BM_%d : In alloc_io_sgl_handle,"
@@ -919,14 +920,16 @@ static struct sgl_handle *alloc_io_sgl_handle(struct beiscsi_hba *phba)
 			phba->io_sgl_alloc_index++;
 	} else
 		psgl_handle = NULL;
-	spin_unlock_bh(&phba->io_sgl_lock);
+	spin_unlock_irqrestore(&phba->io_sgl_lock, flags);
 	return psgl_handle;
 }
 
 static void
 free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 {
-	spin_lock_bh(&phba->io_sgl_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&phba->io_sgl_lock, flags);
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_IO,
 		    "BM_%d : In free_,io_sgl_free_index=%d\n",
 		    phba->io_sgl_free_index);
@@ -941,7 +944,7 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 			     "value there=%p\n", phba->io_sgl_free_index,
 			     phba->io_sgl_hndl_base
 			     [phba->io_sgl_free_index]);
-		 spin_unlock_bh(&phba->io_sgl_lock);
+		 spin_unlock_irqrestore(&phba->io_sgl_lock, flags);
 		return;
 	}
 	phba->io_sgl_hndl_base[phba->io_sgl_free_index] = psgl_handle;
@@ -950,7 +953,7 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 		phba->io_sgl_free_index = 0;
 	else
 		phba->io_sgl_free_index++;
-	spin_unlock_bh(&phba->io_sgl_lock);
+	spin_unlock_irqrestore(&phba->io_sgl_lock, flags);
 }
 
 static inline struct wrb_handle *
@@ -958,15 +961,16 @@ beiscsi_get_wrb_handle(struct hwi_wrb_context *pwrb_context,
 		       unsigned int wrbs_per_cxn)
 {
 	struct wrb_handle *pwrb_handle;
+	unsigned long flags;
 
-	spin_lock_bh(&pwrb_context->wrb_lock);
+	spin_lock_irqsave(&pwrb_context->wrb_lock, flags);
 	pwrb_handle = pwrb_context->pwrb_handle_base[pwrb_context->alloc_index];
 	pwrb_context->wrb_handles_available--;
 	if (pwrb_context->alloc_index == (wrbs_per_cxn - 1))
 		pwrb_context->alloc_index = 0;
 	else
 		pwrb_context->alloc_index++;
-	spin_unlock_bh(&pwrb_context->wrb_lock);
+	spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags);
 
 	if (pwrb_handle)
 		memset(pwrb_handle->pwrb, 0, sizeof(*pwrb_handle->pwrb));
@@ -1001,14 +1005,16 @@ beiscsi_put_wrb_handle(struct hwi_wrb_context *pwrb_context,
 		       struct wrb_handle *pwrb_handle,
 		       unsigned int wrbs_per_cxn)
 {
-	spin_lock_bh(&pwrb_context->wrb_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&pwrb_context->wrb_lock, flags);
 	pwrb_context->pwrb_handle_base[pwrb_context->free_index] = pwrb_handle;
 	pwrb_context->wrb_handles_available++;
 	if (pwrb_context->free_index == (wrbs_per_cxn - 1))
 		pwrb_context->free_index = 0;
 	else
 		pwrb_context->free_index++;
-	spin_unlock_bh(&pwrb_context->wrb_lock);
+	spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags);
 }
 
 /**
@@ -1037,8 +1043,9 @@ free_wrb_handle(struct beiscsi_hba *phba, struct hwi_wrb_context *pwrb_context,
 static struct sgl_handle *alloc_mgmt_sgl_handle(struct beiscsi_hba *phba)
 {
 	struct sgl_handle *psgl_handle;
+	unsigned long flags;
 
-	spin_lock_bh(&phba->mgmt_sgl_lock);
+	spin_lock_irqsave(&phba->mgmt_sgl_lock, flags);
 	if (phba->eh_sgl_hndl_avbl) {
 		psgl_handle = phba->eh_sgl_hndl_base[phba->eh_sgl_alloc_index];
 		phba->eh_sgl_hndl_base[phba->eh_sgl_alloc_index] = NULL;
@@ -1056,14 +1063,16 @@ static struct sgl_handle *alloc_mgmt_sgl_handle(struct beiscsi_hba *phba)
 			phba->eh_sgl_alloc_index++;
 	} else
 		psgl_handle = NULL;
-	spin_unlock_bh(&phba->mgmt_sgl_lock);
+	spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags);
 	return psgl_handle;
 }
 
 void
 free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 {
-	spin_lock_bh(&phba->mgmt_sgl_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&phba->mgmt_sgl_lock, flags);
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
 		    "BM_%d : In  free_mgmt_sgl_handle,"
 		    "eh_sgl_free_index=%d\n",
@@ -1078,7 +1087,7 @@ free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 			    "BM_%d : Double Free in eh SGL ,"
 			    "eh_sgl_free_index=%d\n",
 			    phba->eh_sgl_free_index);
-		spin_unlock_bh(&phba->mgmt_sgl_lock);
+		spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags);
 		return;
 	}
 	phba->eh_sgl_hndl_base[phba->eh_sgl_free_index] = psgl_handle;
@@ -1088,7 +1097,7 @@ free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 		phba->eh_sgl_free_index = 0;
 	else
 		phba->eh_sgl_free_index++;
-	spin_unlock_bh(&phba->mgmt_sgl_lock);
+	spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags);
 }
 
 static void
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index c051694..f9b6fba 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -791,9 +791,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
 
 free_task:
 	/* regular RX path uses back_lock */
-	spin_lock_bh(&session->back_lock);
+	spin_lock(&session->back_lock);
 	__iscsi_put_task(task);
-	spin_unlock_bh(&session->back_lock);
+	spin_unlock(&session->back_lock);
 	return NULL;
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 9ff57de..d8b1fbd 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -1700,16 +1700,13 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		goto out_done;
 	}
 
-	switch (scmd->cmnd[0]) {
-	case SYNCHRONIZE_CACHE:
-		/*
-		 * FW takes care of flush cache on its own
-		 * No need to send it down
-		 */
+	/*
+	 * FW takes care of flush cache on its own for Virtual Disk.
+	 * No need to send it down for VD. For JBOD send SYNCHRONIZE_CACHE to FW.
+	 */
+	if ((scmd->cmnd[0] == SYNCHRONIZE_CACHE) && MEGASAS_IS_LOGICAL(scmd)) {
 		scmd->result = DID_OK << 16;
 		goto out_done;
-	default:
-		break;
 	}
 
 	return instance->instancet->build_and_issue_cmd(instance, scmd);
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index c905709..cf04a36 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -5134,6 +5134,7 @@ static void __exit scsi_debug_exit(void)
 	bus_unregister(&pseudo_lld_bus);
 	root_device_unregister(pseudo_primary);
 
+	vfree(map_storep);
 	vfree(dif_storep);
 	vfree(fake_storep);
 	kfree(sdebug_q_arr);
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 35c0dd9..a67b0ff 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -70,6 +70,7 @@
 #define SPI_SR			0x2c
 #define SPI_SR_EOQF		0x10000000
 #define SPI_SR_TCFQF		0x80000000
+#define SPI_SR_CLEAR		0xdaad0000
 
 #define SPI_RSER		0x30
 #define SPI_RSER_EOQFE		0x10000000
@@ -646,6 +647,11 @@ static const struct regmap_config dspi_regmap_config = {
 	.max_register = 0x88,
 };
 
+static void dspi_init(struct fsl_dspi *dspi)
+{
+	regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
+}
+
 static int dspi_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -709,6 +715,7 @@ static int dspi_probe(struct platform_device *pdev)
 		return PTR_ERR(dspi->regmap);
 	}
 
+	dspi_init(dspi);
 	dspi->irq = platform_get_irq(pdev, 0);
 	if (dspi->irq < 0) {
 		dev_err(&pdev->dev, "can't get platform irq\n");
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 7451585..2c175b9 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -458,7 +458,7 @@ static void fsl_espi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
 
 		mspi->len -= rx_nr_bytes;
 
-		if (mspi->rx)
+		if (rx_nr_bytes && mspi->rx)
 			mspi->get_rx(rx_data, mspi);
 	}
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 5787b72..838783c 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1618,9 +1618,11 @@ static void of_register_spi_devices(struct spi_master *master)
 		if (of_node_test_and_set_flag(nc, OF_POPULATED))
 			continue;
 		spi = of_register_spi_device(master, nc);
-		if (IS_ERR(spi))
+		if (IS_ERR(spi)) {
 			dev_warn(&master->dev, "Failed to create SPI device for %s\n",
 				nc->full_name);
+			of_node_clear_flag(nc, OF_POPULATED);
+		}
 	}
 }
 #else
@@ -3131,6 +3133,7 @@ static int of_spi_notify(struct notifier_block *nb, unsigned long action,
 		if (IS_ERR(spi)) {
 			pr_err("%s: failed to create for '%s'\n",
 					__func__, rd->dn->full_name);
+			of_node_clear_flag(rd->dn, OF_POPULATED);
 			return notifier_from_errno(PTR_ERR(spi));
 		}
 		break;
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 396ded5..209a8f7 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -1187,8 +1187,10 @@ int ion_query_heaps(struct ion_client *client, struct ion_heap_query *query)
 		hdata.type = heap->type;
 		hdata.heap_id = heap->id;
 
-		ret = copy_to_user(&buffer[cnt],
-				   &hdata, sizeof(hdata));
+		if (copy_to_user(&buffer[cnt], &hdata, sizeof(hdata))) {
+			ret = -EFAULT;
+			goto out;
+		}
 
 		cnt++;
 		if (cnt >= max_cnt)
diff --git a/drivers/staging/android/ion/ion_of.c b/drivers/staging/android/ion/ion_of.c
index 15bac92..46b2bb9 100644
--- a/drivers/staging/android/ion/ion_of.c
+++ b/drivers/staging/android/ion/ion_of.c
@@ -107,7 +107,7 @@ struct ion_platform_data *ion_parse_dt(struct platform_device *pdev,
 
 		heap_pdev = of_platform_device_create(node, heaps[i].name,
 						      &pdev->dev);
-		if (!pdev)
+		if (!heap_pdev)
 			return ERR_PTR(-ENOMEM);
 		heap_pdev->dev.platform_data = &heaps[i];
 
diff --git a/drivers/staging/greybus/arche-platform.c b/drivers/staging/greybus/arche-platform.c
index e36ee98..34307ac 100644
--- a/drivers/staging/greybus/arche-platform.c
+++ b/drivers/staging/greybus/arche-platform.c
@@ -128,6 +128,7 @@ int arche_platform_change_state(enum arche_platform_state state,
 	pdev = of_find_device_by_node(np);
 	if (!pdev) {
 		pr_err("arche-platform device not found\n");
+		of_node_put(np);
 		return -ENODEV;
 	}
 
diff --git a/drivers/staging/greybus/es2.c b/drivers/staging/greybus/es2.c
index 071bb1c..baab460 100644
--- a/drivers/staging/greybus/es2.c
+++ b/drivers/staging/greybus/es2.c
@@ -1548,7 +1548,8 @@ static int ap_probe(struct usb_interface *interface,
 	INIT_LIST_HEAD(&es2->arpcs);
 	spin_lock_init(&es2->arpc_lock);
 
-	if (es2_arpc_in_enable(es2))
+	retval = es2_arpc_in_enable(es2);
+	if (retval)
 		goto error;
 
 	retval = gb_hd_add(hd);
diff --git a/drivers/staging/greybus/gpio.c b/drivers/staging/greybus/gpio.c
index 5e06e42..250caa0 100644
--- a/drivers/staging/greybus/gpio.c
+++ b/drivers/staging/greybus/gpio.c
@@ -702,15 +702,13 @@ static int gb_gpio_probe(struct gbphy_device *gbphy_dev,
 	ret = gb_gpio_irqchip_add(gpio, irqc, 0,
 				   handle_level_irq, IRQ_TYPE_NONE);
 	if (ret) {
-		dev_err(&connection->bundle->dev,
-			"failed to add irq chip: %d\n", ret);
+		dev_err(&gbphy_dev->dev, "failed to add irq chip: %d\n", ret);
 		goto exit_line_free;
 	}
 
 	ret = gpiochip_add(gpio);
 	if (ret) {
-		dev_err(&connection->bundle->dev,
-			"failed to add gpio chip: %d\n", ret);
+		dev_err(&gbphy_dev->dev, "failed to add gpio chip: %d\n", ret);
 		goto exit_gpio_irqchip_remove;
 	}
 
diff --git a/drivers/staging/greybus/module.c b/drivers/staging/greybus/module.c
index 69f67dd..660b467 100644
--- a/drivers/staging/greybus/module.c
+++ b/drivers/staging/greybus/module.c
@@ -127,7 +127,7 @@ struct gb_module *gb_module_create(struct gb_host_device *hd, u8 module_id,
 	return module;
 
 err_put_interfaces:
-	for (--i; i > 0; --i)
+	for (--i; i >= 0; --i)
 		gb_interface_put(module->interfaces[i]);
 
 	put_device(&module->dev);
diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c
index 5ee7954..2633d2b 100644
--- a/drivers/staging/greybus/uart.c
+++ b/drivers/staging/greybus/uart.c
@@ -888,7 +888,7 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev,
 	minor = alloc_minor(gb_tty);
 	if (minor < 0) {
 		if (minor == -ENOSPC) {
-			dev_err(&connection->bundle->dev,
+			dev_err(&gbphy_dev->dev,
 				"no more free minor numbers\n");
 			retval = -ENODEV;
 		} else {
diff --git a/drivers/staging/iio/accel/sca3000_core.c b/drivers/staging/iio/accel/sca3000_core.c
index d626125..564b36d 100644
--- a/drivers/staging/iio/accel/sca3000_core.c
+++ b/drivers/staging/iio/accel/sca3000_core.c
@@ -468,6 +468,8 @@ static inline int __sca3000_get_base_freq(struct sca3000_state *st,
 	case SCA3000_MEAS_MODE_OP_2:
 		*base_freq = info->option_mode_2_freq;
 		break;
+	default:
+		ret = -EINVAL;
 	}
 error_ret:
 	return ret;
diff --git a/drivers/staging/lustre/lustre/llite/lproc_llite.c b/drivers/staging/lustre/lustre/llite/lproc_llite.c
index 6eae605..23fda9d 100644
--- a/drivers/staging/lustre/lustre/llite/lproc_llite.c
+++ b/drivers/staging/lustre/lustre/llite/lproc_llite.c
@@ -871,12 +871,10 @@ static ssize_t xattr_cache_store(struct kobject *kobj,
 }
 LUSTRE_RW_ATTR(xattr_cache);
 
-static ssize_t unstable_stats_show(struct kobject *kobj,
-				   struct attribute *attr,
-				   char *buf)
+static int ll_unstable_stats_seq_show(struct seq_file *m, void *v)
 {
-	struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
-					      ll_kobj);
+	struct super_block     *sb    = m->private;
+	struct ll_sb_info      *sbi   = ll_s2sbi(sb);
 	struct cl_client_cache *cache = sbi->ll_cache;
 	long pages;
 	int mb;
@@ -884,19 +882,21 @@ static ssize_t unstable_stats_show(struct kobject *kobj,
 	pages = atomic_long_read(&cache->ccc_unstable_nr);
 	mb = (pages * PAGE_SIZE) >> 20;
 
-	return sprintf(buf, "unstable_check:     %8d\n"
-			    "unstable_pages: %12ld\n"
-			    "unstable_mb:        %8d\n",
-			    cache->ccc_unstable_check, pages, mb);
+	seq_printf(m,
+		   "unstable_check:     %8d\n"
+		   "unstable_pages: %12ld\n"
+		   "unstable_mb:        %8d\n",
+		   cache->ccc_unstable_check, pages, mb);
+
+	return 0;
 }
 
-static ssize_t unstable_stats_store(struct kobject *kobj,
-				    struct attribute *attr,
-				    const char *buffer,
-				    size_t count)
+static ssize_t ll_unstable_stats_seq_write(struct file *file,
+					   const char __user *buffer,
+					   size_t count, loff_t *off)
 {
-	struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
-					      ll_kobj);
+	struct super_block *sb = ((struct seq_file *)file->private_data)->private;
+	struct ll_sb_info *sbi = ll_s2sbi(sb);
 	char kernbuf[128];
 	int val, rc;
 
@@ -922,7 +922,7 @@ static ssize_t unstable_stats_store(struct kobject *kobj,
 
 	return count;
 }
-LUSTRE_RW_ATTR(unstable_stats);
+LPROC_SEQ_FOPS(ll_unstable_stats);
 
 static ssize_t root_squash_show(struct kobject *kobj, struct attribute *attr,
 				char *buf)
@@ -995,6 +995,7 @@ static struct lprocfs_vars lprocfs_llite_obd_vars[] = {
 	/* { "filegroups",   lprocfs_rd_filegroups,  0, 0 }, */
 	{ "max_cached_mb",    &ll_max_cached_mb_fops, NULL },
 	{ "statahead_stats",  &ll_statahead_stats_fops, NULL, 0 },
+	{ "unstable_stats",   &ll_unstable_stats_fops, NULL },
 	{ "sbi_flags",	      &ll_sbi_flags_fops, NULL, 0 },
 	{ .name =		"nosquash_nids",
 	  .fops =		&ll_nosquash_nids_fops		},
@@ -1026,7 +1027,6 @@ static struct attribute *llite_attrs[] = {
 	&lustre_attr_max_easize.attr,
 	&lustre_attr_default_easize.attr,
 	&lustre_attr_xattr_cache.attr,
-	&lustre_attr_unstable_stats.attr,
 	&lustre_attr_root_squash.attr,
 	NULL,
 };
diff --git a/drivers/staging/media/bcm2048/radio-bcm2048.c b/drivers/staging/media/bcm2048/radio-bcm2048.c
index ea15cc6..4d9bd02 100644
--- a/drivers/staging/media/bcm2048/radio-bcm2048.c
+++ b/drivers/staging/media/bcm2048/radio-bcm2048.c
@@ -482,6 +482,8 @@ static int bcm2048_set_rds_no_lock(struct bcm2048_device *bdev, u8 rds_on)
 					   flags);
 		memset(&bdev->rds_info, 0, sizeof(bdev->rds_info));
 	}
+	if (err)
+		return err;
 
 	return bcm2048_send_command(bdev, BCM2048_I2C_FM_RDS_SYSTEM,
 				    bdev->cache_fm_rds_system);
diff --git a/drivers/staging/wilc1000/host_interface.c b/drivers/staging/wilc1000/host_interface.c
index 78f5613..6ab7443 100644
--- a/drivers/staging/wilc1000/host_interface.c
+++ b/drivers/staging/wilc1000/host_interface.c
@@ -3388,7 +3388,6 @@ int wilc_init(struct net_device *dev, struct host_if_drv **hif_drv_handler)
 
 	clients_count++;
 
-	destroy_workqueue(hif_workqueue);
 _fail_:
 	return result;
 }
diff --git a/drivers/thermal/intel_pch_thermal.c b/drivers/thermal/intel_pch_thermal.c
index 9b4815e..19bf202 100644
--- a/drivers/thermal/intel_pch_thermal.c
+++ b/drivers/thermal/intel_pch_thermal.c
@@ -20,10 +20,13 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/acpi.h>
 #include <linux/thermal.h>
 #include <linux/pm.h>
 
 /* Intel PCH thermal Device IDs */
+#define PCH_THERMAL_DID_HSW_1	0x9C24 /* Haswell PCH */
+#define PCH_THERMAL_DID_HSW_2	0x8C24 /* Haswell PCH */
 #define PCH_THERMAL_DID_WPT	0x9CA4 /* Wildcat Point */
 #define PCH_THERMAL_DID_SKL	0x9D31 /* Skylake PCH */
 
@@ -66,9 +69,53 @@ struct pch_thermal_device {
 	unsigned long crt_temp;
 	int hot_trip_id;
 	unsigned long hot_temp;
+	int psv_trip_id;
+	unsigned long psv_temp;
 	bool bios_enabled;
 };
 
+#ifdef CONFIG_ACPI
+
+/*
+ * On some platforms, there is a companion ACPI device, which adds
+ * passive trip temperature using _PSV method. There is no specific
+ * passive temperature setting in MMIO interface of this PCI device.
+ */
+static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
+				      int *nr_trips)
+{
+	struct acpi_device *adev;
+
+	ptd->psv_trip_id = -1;
+
+	adev = ACPI_COMPANION(&ptd->pdev->dev);
+	if (adev) {
+		unsigned long long r;
+		acpi_status status;
+
+		status = acpi_evaluate_integer(adev->handle, "_PSV", NULL,
+					       &r);
+		if (ACPI_SUCCESS(status)) {
+			unsigned long trip_temp;
+
+			trip_temp = DECI_KELVIN_TO_MILLICELSIUS(r);
+			if (trip_temp) {
+				ptd->psv_temp = trip_temp;
+				ptd->psv_trip_id = *nr_trips;
+				++(*nr_trips);
+			}
+		}
+	}
+}
+#else
+static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
+				      int *nr_trips)
+{
+	ptd->psv_trip_id = -1;
+
+}
+#endif
+
 static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips)
 {
 	u8 tsel;
@@ -119,6 +166,8 @@ static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips)
 		++(*nr_trips);
 	}
 
+	pch_wpt_add_acpi_psv_trip(ptd, nr_trips);
+
 	return 0;
 }
 
@@ -194,6 +243,8 @@ static int pch_get_trip_type(struct thermal_zone_device *tzd, int trip,
 		*type = THERMAL_TRIP_CRITICAL;
 	else if (ptd->hot_trip_id == trip)
 		*type = THERMAL_TRIP_HOT;
+	else if (ptd->psv_trip_id == trip)
+		*type = THERMAL_TRIP_PASSIVE;
 	else
 		return -EINVAL;
 
@@ -208,6 +259,8 @@ static int pch_get_trip_temp(struct thermal_zone_device *tzd, int trip, int *tem
 		*temp = ptd->crt_temp;
 	else if (ptd->hot_trip_id == trip)
 		*temp = ptd->hot_temp;
+	else if (ptd->psv_trip_id == trip)
+		*temp = ptd->psv_temp;
 	else
 		return -EINVAL;
 
@@ -242,6 +295,11 @@ static int intel_pch_thermal_probe(struct pci_dev *pdev,
 		ptd->ops = &pch_dev_ops_wpt;
 		dev_name = "pch_skylake";
 		break;
+	case PCH_THERMAL_DID_HSW_1:
+	case PCH_THERMAL_DID_HSW_2:
+		ptd->ops = &pch_dev_ops_wpt;
+		dev_name = "pch_haswell";
+		break;
 	default:
 		dev_err(&pdev->dev, "unknown pch thermal device\n");
 		return -ENODEV;
@@ -324,6 +382,8 @@ static int intel_pch_thermal_resume(struct device *device)
 static struct pci_device_id intel_pch_thermal_id[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_1) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_2) },
 	{ 0, },
 };
 MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id);
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 0e4dc0a..7a22307 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -669,20 +669,10 @@ static struct thermal_cooling_device_ops powerclamp_cooling_ops = {
 	.set_cur_state = powerclamp_set_cur_state,
 };
 
-static const struct x86_cpu_id intel_powerclamp_ids[] __initconst = {
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT },
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_ARAT },
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_NONSTOP_TSC },
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_CONSTANT_TSC},
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids);
-
 static int __init powerclamp_probe(void)
 {
-	if (!x86_match_cpu(intel_powerclamp_ids)) {
-		pr_err("Intel powerclamp does not run on family %d model %d\n",
-				boot_cpu_data.x86, boot_cpu_data.x86_model);
+	if (!boot_cpu_has(X86_FEATURE_MWAIT)) {
+		pr_err("CPU does not support MWAIT");
 		return -ENODEV;
 	}
 
diff --git a/drivers/tty/serial/8250/8250_lpss.c b/drivers/tty/serial/8250/8250_lpss.c
index 886fcf3..b992346 100644
--- a/drivers/tty/serial/8250/8250_lpss.c
+++ b/drivers/tty/serial/8250/8250_lpss.c
@@ -213,7 +213,7 @@ static int qrk_serial_setup(struct lpss8250 *lpss, struct uart_port *port)
 	struct pci_dev *pdev = to_pci_dev(port->dev);
 	int ret;
 
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, 0);
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 1bfb6fd..1731b98 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -83,7 +83,8 @@ static const struct serial8250_config uart_config[] = {
 		.name		= "16550A",
 		.fifo_size	= 16,
 		.tx_loadsz	= 16,
-		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 |
+				  UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT,
 		.rxtrig_bytes	= {1, 4, 8, 14},
 		.flags		= UART_CAP_FIFO,
 	},
diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c
index b8d9c8c..417d9e7 100644
--- a/drivers/tty/serial/8250/8250_uniphier.c
+++ b/drivers/tty/serial/8250/8250_uniphier.c
@@ -99,7 +99,7 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value)
 	case UART_LCR:
 		valshift = UNIPHIER_UART_LCR_SHIFT;
 		/* Divisor latch access bit does not exist. */
-		value &= ~(UART_LCR_DLAB << valshift);
+		value &= ~UART_LCR_DLAB;
 		/* fall through */
 	case UART_MCR:
 		offset = UNIPHIER_UART_LCR_MCR;
@@ -199,7 +199,7 @@ static int uniphier_uart_probe(struct platform_device *pdev)
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!regs) {
-		dev_err(dev, "failed to get memory resource");
+		dev_err(dev, "failed to get memory resource\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index c783140..25c1d7b 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1625,6 +1625,7 @@
 config SERIAL_STM32
 	tristate "STMicroelectronics STM32 serial port support"
 	select SERIAL_CORE
+	depends on HAS_DMA
 	depends on ARM || COMPILE_TEST
 	help
 	  This driver is for the on-chip Serial Controller on
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index fd8aa1f..168b10c 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -2132,11 +2132,29 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
 		mode |= ATMEL_US_USMODE_RS485;
 	} else if (termios->c_cflag & CRTSCTS) {
 		/* RS232 with hardware handshake (RTS/CTS) */
-		if (atmel_use_dma_rx(port) && !atmel_use_fifo(port)) {
-			dev_info(port->dev, "not enabling hardware flow control because DMA is used");
-			termios->c_cflag &= ~CRTSCTS;
-		} else {
+		if (atmel_use_fifo(port) &&
+		    !mctrl_gpio_to_gpiod(atmel_port->gpios, UART_GPIO_CTS)) {
+			/*
+			 * with ATMEL_US_USMODE_HWHS set, the controller will
+			 * be able to drive the RTS pin high/low when the RX
+			 * FIFO is above RXFTHRES/below RXFTHRES2.
+			 * It will also disable the transmitter when the CTS
+			 * pin is high.
+			 * This mode is not activated if CTS pin is a GPIO
+			 * because in this case, the transmitter is always
+			 * disabled (there must be an internal pull-up
+			 * responsible for this behaviour).
+			 * If the RTS pin is a GPIO, the controller won't be
+			 * able to drive it according to the FIFO thresholds,
+			 * but it will be handled by the driver.
+			 */
 			mode |= ATMEL_US_USMODE_HWHS;
+		} else {
+			/*
+			 * For platforms without FIFO, the flow control is
+			 * handled by the driver.
+			 */
+			mode |= ATMEL_US_USMODE_NORMAL;
 		}
 	} else {
 		/* RS232 without hadware handshake */
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index de9d510..76103f2 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -328,7 +328,7 @@ static void lpuart_dma_tx(struct lpuart_port *sport)
 
 	sport->dma_tx_bytes = uart_circ_chars_pending(xmit);
 
-	if (xmit->tail < xmit->head) {
+	if (xmit->tail < xmit->head || xmit->head == 0) {
 		sport->dma_tx_nents = 1;
 		sg_init_one(sgl, xmit->buf + xmit->tail, sport->dma_tx_bytes);
 	} else {
@@ -359,7 +359,6 @@ static void lpuart_dma_tx(struct lpuart_port *sport)
 	sport->dma_tx_in_progress = true;
 	sport->dma_tx_cookie = dmaengine_submit(sport->dma_tx_desc);
 	dma_async_issue_pending(sport->dma_tx_chan);
-
 }
 
 static void lpuart_dma_tx_complete(void *arg)
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index d391650..42caccb 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -419,6 +419,7 @@ static struct dmi_system_id pch_uart_dmi_table[] = {
 		},
 		(void *)MINNOW_UARTCLK,
 	},
+	{ }
 };
 
 /* Return UART clock, checking for board specific clocks. */
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 2675792..fb06725 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1130,9 +1130,13 @@ static int sc16is7xx_gpio_direction_output(struct gpio_chip *chip,
 {
 	struct sc16is7xx_port *s = gpiochip_get_data(chip);
 	struct uart_port *port = &s->p[0].port;
+	u8 state = sc16is7xx_port_read(port, SC16IS7XX_IOSTATE_REG);
 
-	sc16is7xx_port_update(port, SC16IS7XX_IOSTATE_REG, BIT(offset),
-			      val ? BIT(offset) : 0);
+	if (val)
+		state |= BIT(offset);
+	else
+		state &= ~BIT(offset);
+	sc16is7xx_port_write(port, SC16IS7XX_IOSTATE_REG, state);
 	sc16is7xx_port_update(port, SC16IS7XX_IODIR_REG, BIT(offset),
 			      BIT(offset));
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 6e4f636..f2303f3 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -111,7 +111,7 @@ void uart_write_wakeup(struct uart_port *port)
 	 * closed.  No cookie for you.
 	 */
 	BUG_ON(!state);
-	tty_wakeup(state->port.tty);
+	tty_port_tty_wakeup(&state->port);
 }
 
 static void uart_stop(struct tty_struct *tty)
@@ -632,7 +632,7 @@ static void uart_flush_buffer(struct tty_struct *tty)
 	if (port->ops->flush_buffer)
 		port->ops->flush_buffer(port);
 	uart_port_unlock(port, flags);
-	tty_wakeup(tty);
+	tty_port_tty_wakeup(&state->port);
 }
 
 /*
@@ -2746,8 +2746,6 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport)
 	uport->cons = drv->cons;
 	uport->minor = drv->tty_driver->minor_start + uport->line;
 
-	port->console = uart_console(uport);
-
 	/*
 	 * If this port is a console, then the spinlock is already
 	 * initialised.
@@ -2761,6 +2759,8 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport)
 
 	uart_configure_port(drv, state, uport);
 
+	port->console = uart_console(uport);
+
 	num_groups = 2;
 	if (uport->attr_group)
 		num_groups++;
diff --git a/drivers/tty/serial/stm32-usart.h b/drivers/tty/serial/stm32-usart.h
index 41d9749..cd97ceb 100644
--- a/drivers/tty/serial/stm32-usart.h
+++ b/drivers/tty/serial/stm32-usart.h
@@ -31,7 +31,7 @@ struct stm32_usart_info {
 	struct stm32_usart_config cfg;
 };
 
-#define UNDEF_REG ~0
+#define UNDEF_REG 0xff
 
 /* Register offsets */
 struct stm32_usart_info stm32f4_info = {
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index f37edaa..dd4c02f 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1200,6 +1200,7 @@ static int __init cdns_early_console_setup(struct earlycon_device *device,
 OF_EARLYCON_DECLARE(cdns, "xlnx,xuartps", cdns_early_console_setup);
 OF_EARLYCON_DECLARE(cdns, "cdns,uart-r1p8", cdns_early_console_setup);
 OF_EARLYCON_DECLARE(cdns, "cdns,uart-r1p12", cdns_early_console_setup);
+OF_EARLYCON_DECLARE(cdns, "xlnx,zynqmp-uart", cdns_early_console_setup);
 
 /**
  * cdns_uart_console_write - perform write operation
@@ -1438,6 +1439,7 @@ static const struct of_device_id cdns_uart_of_match[] = {
 	{ .compatible = "xlnx,xuartps", },
 	{ .compatible = "cdns,uart-r1p8", },
 	{ .compatible = "cdns,uart-r1p12", .data = &zynqmp_uart_def },
+	{ .compatible = "xlnx,zynqmp-uart", .data = &zynqmp_uart_def },
 	{}
 };
 MODULE_DEVICE_TABLE(of, cdns_uart_of_match);
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 06fb39c..8c3bf3d 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -870,10 +870,15 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	if (new_cols == vc->vc_cols && new_rows == vc->vc_rows)
 		return 0;
 
+	if (new_screen_size > (4 << 20))
+		return -EINVAL;
 	newscreen = kmalloc(new_screen_size, GFP_USER);
 	if (!newscreen)
 		return -ENOMEM;
 
+	if (vc == sel_cons)
+		clear_selection();
+
 	old_rows = vc->vc_rows;
 	old_row_size = vc->vc_size_row;
 
@@ -1176,7 +1181,7 @@ static void csi_J(struct vc_data *vc, int vpar)
 			break;
 		case 3: /* erase scroll-back buffer (and whole display) */
 			scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char,
-				    vc->vc_screenbuf_size >> 1);
+				    vc->vc_screenbuf_size);
 			set_origin(vc);
 			if (con_is_visible(vc))
 				update_screen(vc);
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index 96ae695..111b0e0b 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -188,6 +188,8 @@ static void host_stop(struct ci_hdrc *ci)
 
 	if (hcd) {
 		usb_remove_hcd(hcd);
+		ci->role = CI_ROLE_END;
+		synchronize_irq(ci->irq);
 		usb_put_hcd(hcd);
 		if (ci->platdata->reg_vbus && !ci_otg_is_fsm_mode(ci) &&
 			(ci->platdata->flags & CI_HDRC_TURN_VBUS_EARLY_ON))
diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c
index fa9b26b..4c0fa0b 100644
--- a/drivers/usb/dwc2/core.c
+++ b/drivers/usb/dwc2/core.c
@@ -463,9 +463,18 @@ static void dwc2_clear_force_mode(struct dwc2_hsotg *hsotg)
  */
 void dwc2_force_dr_mode(struct dwc2_hsotg *hsotg)
 {
+	bool ret;
+
 	switch (hsotg->dr_mode) {
 	case USB_DR_MODE_HOST:
-		dwc2_force_mode(hsotg, true);
+		ret = dwc2_force_mode(hsotg, true);
+		/*
+		 * NOTE: This is required for some rockchip soc based
+		 * platforms on their host-only dwc2.
+		 */
+		if (!ret)
+			msleep(50);
+
 		break;
 	case USB_DR_MODE_PERIPHERAL:
 		dwc2_force_mode(hsotg, false);
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index aad4107..2a21a04 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -259,6 +259,13 @@ enum dwc2_lx_state {
 	DWC2_L3,	/* Off state */
 };
 
+/*
+ * Gadget periodic tx fifo sizes as used by legacy driver
+ * EP0 is not included
+ */
+#define DWC2_G_P_LEGACY_TX_FIFO_SIZE {256, 256, 256, 256, 768, 768, 768, \
+					   768, 0, 0, 0, 0, 0, 0, 0}
+
 /* Gadget ep0 states */
 enum dwc2_ep0_state {
 	DWC2_EP0_SETUP,
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 4cd6403..24fbebc 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -186,10 +186,9 @@ static void dwc2_hsotg_ctrl_epint(struct dwc2_hsotg *hsotg,
  */
 static void dwc2_hsotg_init_fifo(struct dwc2_hsotg *hsotg)
 {
-	unsigned int fifo;
+	unsigned int ep;
 	unsigned int addr;
 	int timeout;
-	u32 dptxfsizn;
 	u32 val;
 
 	/* Reset fifo map if not correctly cleared during previous session */
@@ -217,16 +216,16 @@ static void dwc2_hsotg_init_fifo(struct dwc2_hsotg *hsotg)
 	 * them to endpoints dynamically according to maxpacket size value of
 	 * given endpoint.
 	 */
-	for (fifo = 1; fifo < MAX_EPS_CHANNELS; fifo++) {
-		dptxfsizn = dwc2_readl(hsotg->regs + DPTXFSIZN(fifo));
+	for (ep = 1; ep < MAX_EPS_CHANNELS; ep++) {
+		if (!hsotg->g_tx_fifo_sz[ep])
+			continue;
+		val = addr;
+		val |= hsotg->g_tx_fifo_sz[ep] << FIFOSIZE_DEPTH_SHIFT;
+		WARN_ONCE(addr + hsotg->g_tx_fifo_sz[ep] > hsotg->fifo_mem,
+			  "insufficient fifo memory");
+		addr += hsotg->g_tx_fifo_sz[ep];
 
-		val = (dptxfsizn & FIFOSIZE_DEPTH_MASK) | addr;
-		addr += dptxfsizn >> FIFOSIZE_DEPTH_SHIFT;
-
-		if (addr > hsotg->fifo_mem)
-			break;
-
-		dwc2_writel(val, hsotg->regs + DPTXFSIZN(fifo));
+		dwc2_writel(val, hsotg->regs + DPTXFSIZN(ep));
 	}
 
 	/*
@@ -3807,10 +3806,36 @@ static void dwc2_hsotg_dump(struct dwc2_hsotg *hsotg)
 static void dwc2_hsotg_of_probe(struct dwc2_hsotg *hsotg)
 {
 	struct device_node *np = hsotg->dev->of_node;
+	u32 len = 0;
+	u32 i = 0;
 
 	/* Enable dma if requested in device tree */
 	hsotg->g_using_dma = of_property_read_bool(np, "g-use-dma");
 
+	/*
+	* Register TX periodic fifo size per endpoint.
+	* EP0 is excluded since it has no fifo configuration.
+	*/
+	if (!of_find_property(np, "g-tx-fifo-size", &len))
+		goto rx_fifo;
+
+	len /= sizeof(u32);
+
+	/* Read tx fifo sizes other than ep0 */
+	if (of_property_read_u32_array(np, "g-tx-fifo-size",
+						&hsotg->g_tx_fifo_sz[1], len))
+		goto rx_fifo;
+
+	/* Add ep0 */
+	len++;
+
+	/* Make remaining TX fifos unavailable */
+	if (len < MAX_EPS_CHANNELS) {
+		for (i = len; i < MAX_EPS_CHANNELS; i++)
+			hsotg->g_tx_fifo_sz[i] = 0;
+	}
+
+rx_fifo:
 	/* Register RX fifo size */
 	of_property_read_u32(np, "g-rx-fifo-size", &hsotg->g_rx_fifo_sz);
 
@@ -3832,10 +3857,13 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg, int irq)
 	struct device *dev = hsotg->dev;
 	int epnum;
 	int ret;
+	int i;
+	u32 p_tx_fifo[] = DWC2_G_P_LEGACY_TX_FIFO_SIZE;
 
 	/* Initialize to legacy fifo configuration values */
 	hsotg->g_rx_fifo_sz = 2048;
 	hsotg->g_np_g_tx_fifo_sz = 1024;
+	memcpy(&hsotg->g_tx_fifo_sz[1], p_tx_fifo, sizeof(p_tx_fifo));
 	/* Device tree specific probe */
 	dwc2_hsotg_of_probe(hsotg);
 
@@ -3853,6 +3881,9 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg, int irq)
 	dev_dbg(dev, "NonPeriodic TXFIFO size: %d\n",
 						hsotg->g_np_g_tx_fifo_sz);
 	dev_dbg(dev, "RXFIFO size: %d\n", hsotg->g_rx_fifo_sz);
+	for (i = 0; i < MAX_EPS_CHANNELS; i++)
+		dev_dbg(dev, "Periodic TXFIFO%2d size: %d\n", i,
+						hsotg->g_tx_fifo_sz[i]);
 
 	hsotg->gadget.max_speed = USB_SPEED_HIGH;
 	hsotg->gadget.ops = &dwc2_hsotg_gadget_ops;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 07cc892..1dfa56a5f 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -783,6 +783,7 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
 		req->trb = trb;
 		req->trb_dma = dwc3_trb_dma_offset(dep, trb);
 		req->first_trb_index = dep->trb_enqueue;
+		dep->queued_requests++;
 	}
 
 	dwc3_ep_inc_enq(dep);
@@ -833,8 +834,6 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
 
 	trb->ctrl |= DWC3_TRB_CTRL_HWO;
 
-	dep->queued_requests++;
-
 	trace_dwc3_prepare_trb(dep, trb);
 }
 
@@ -1074,9 +1073,17 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
 
 	list_add_tail(&req->list, &dep->pending_list);
 
-	if (usb_endpoint_xfer_isoc(dep->endpoint.desc) &&
-			dep->flags & DWC3_EP_PENDING_REQUEST) {
-		if (list_empty(&dep->started_list)) {
+	/*
+	 * NOTICE: Isochronous endpoints should NEVER be prestarted. We must
+	 * wait for a XferNotReady event so we will know what's the current
+	 * (micro-)frame number.
+	 *
+	 * Without this trick, we are very, very likely gonna get Bus Expiry
+	 * errors which will force us issue EndTransfer command.
+	 */
+	if (usb_endpoint_xfer_isoc(dep->endpoint.desc)) {
+		if ((dep->flags & DWC3_EP_PENDING_REQUEST) &&
+				list_empty(&dep->started_list)) {
 			dwc3_stop_active_transfer(dwc, dep->number, true);
 			dep->flags = DWC3_EP_ENABLED;
 		}
@@ -1861,8 +1868,11 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
 	unsigned int		s_pkt = 0;
 	unsigned int		trb_status;
 
-	dep->queued_requests--;
 	dwc3_ep_inc_deq(dep);
+
+	if (req->trb == trb)
+		dep->queued_requests--;
+
 	trace_dwc3_complete_trb(dep, trb);
 
 	/*
@@ -2980,7 +2990,7 @@ int dwc3_gadget_init(struct dwc3 *dwc)
 	kfree(dwc->setup_buf);
 
 err2:
-	dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb),
+	dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb) * 2,
 			dwc->ep0_trb, dwc->ep0_trb_addr);
 
 err1:
@@ -3005,7 +3015,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc)
 	kfree(dwc->setup_buf);
 	kfree(dwc->zlp_buf);
 
-	dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb),
+	dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb) * 2,
 			dwc->ep0_trb, dwc->ep0_trb_addr);
 
 	dma_free_coherent(dwc->dev, sizeof(*dwc->ctrl_req),
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 54ad100..e40d47d 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -136,8 +136,60 @@ struct ffs_epfile {
 	/*
 	 * Buffer for holding data from partial reads which may happen since
 	 * we’re rounding user read requests to a multiple of a max packet size.
+	 *
+	 * The pointer is initialised with NULL value and may be set by
+	 * __ffs_epfile_read_data function to point to a temporary buffer.
+	 *
+	 * In normal operation, calls to __ffs_epfile_read_buffered will consume
+	 * data from said buffer and eventually free it.  Importantly, while the
+	 * function is using the buffer, it sets the pointer to NULL.  This is
+	 * all right since __ffs_epfile_read_data and __ffs_epfile_read_buffered
+	 * can never run concurrently (they are synchronised by epfile->mutex)
+	 * so the latter will not assign a new value to the pointer.
+	 *
+	 * Meanwhile ffs_func_eps_disable frees the buffer (if the pointer is
+	 * valid) and sets the pointer to READ_BUFFER_DROP value.  This special
+	 * value is crux of the synchronisation between ffs_func_eps_disable and
+	 * __ffs_epfile_read_data.
+	 *
+	 * Once __ffs_epfile_read_data is about to finish it will try to set the
+	 * pointer back to its old value (as described above), but seeing as the
+	 * pointer is not-NULL (namely READ_BUFFER_DROP) it will instead free
+	 * the buffer.
+	 *
+	 * == State transitions ==
+	 *
+	 * • ptr == NULL:  (initial state)
+	 *   ◦ __ffs_epfile_read_buffer_free: go to ptr == DROP
+	 *   ◦ __ffs_epfile_read_buffered:    nop
+	 *   ◦ __ffs_epfile_read_data allocates temp buffer: go to ptr == buf
+	 *   ◦ reading finishes:              n/a, not in ‘and reading’ state
+	 * • ptr == DROP:
+	 *   ◦ __ffs_epfile_read_buffer_free: nop
+	 *   ◦ __ffs_epfile_read_buffered:    go to ptr == NULL
+	 *   ◦ __ffs_epfile_read_data allocates temp buffer: free buf, nop
+	 *   ◦ reading finishes:              n/a, not in ‘and reading’ state
+	 * • ptr == buf:
+	 *   ◦ __ffs_epfile_read_buffer_free: free buf, go to ptr == DROP
+	 *   ◦ __ffs_epfile_read_buffered:    go to ptr == NULL and reading
+	 *   ◦ __ffs_epfile_read_data:        n/a, __ffs_epfile_read_buffered
+	 *                                    is always called first
+	 *   ◦ reading finishes:              n/a, not in ‘and reading’ state
+	 * • ptr == NULL and reading:
+	 *   ◦ __ffs_epfile_read_buffer_free: go to ptr == DROP and reading
+	 *   ◦ __ffs_epfile_read_buffered:    n/a, mutex is held
+	 *   ◦ __ffs_epfile_read_data:        n/a, mutex is held
+	 *   ◦ reading finishes and …
+	 *     … all data read:               free buf, go to ptr == NULL
+	 *     … otherwise:                   go to ptr == buf and reading
+	 * • ptr == DROP and reading:
+	 *   ◦ __ffs_epfile_read_buffer_free: nop
+	 *   ◦ __ffs_epfile_read_buffered:    n/a, mutex is held
+	 *   ◦ __ffs_epfile_read_data:        n/a, mutex is held
+	 *   ◦ reading finishes:              free buf, go to ptr == DROP
 	 */
-	struct ffs_buffer		*read_buffer;	/* P: epfile->mutex */
+	struct ffs_buffer		*read_buffer;
+#define READ_BUFFER_DROP ((struct ffs_buffer *)ERR_PTR(-ESHUTDOWN))
 
 	char				name[5];
 
@@ -736,25 +788,47 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep,
 	schedule_work(&io_data->work);
 }
 
+static void __ffs_epfile_read_buffer_free(struct ffs_epfile *epfile)
+{
+	/*
+	 * See comment in struct ffs_epfile for full read_buffer pointer
+	 * synchronisation story.
+	 */
+	struct ffs_buffer *buf = xchg(&epfile->read_buffer, READ_BUFFER_DROP);
+	if (buf && buf != READ_BUFFER_DROP)
+		kfree(buf);
+}
+
 /* Assumes epfile->mutex is held. */
 static ssize_t __ffs_epfile_read_buffered(struct ffs_epfile *epfile,
 					  struct iov_iter *iter)
 {
-	struct ffs_buffer *buf = epfile->read_buffer;
+	/*
+	 * Null out epfile->read_buffer so ffs_func_eps_disable does not free
+	 * the buffer while we are using it.  See comment in struct ffs_epfile
+	 * for full read_buffer pointer synchronisation story.
+	 */
+	struct ffs_buffer *buf = xchg(&epfile->read_buffer, NULL);
 	ssize_t ret;
-	if (!buf)
+	if (!buf || buf == READ_BUFFER_DROP)
 		return 0;
 
 	ret = copy_to_iter(buf->data, buf->length, iter);
 	if (buf->length == ret) {
 		kfree(buf);
-		epfile->read_buffer = NULL;
-	} else if (unlikely(iov_iter_count(iter))) {
+		return ret;
+	}
+
+	if (unlikely(iov_iter_count(iter))) {
 		ret = -EFAULT;
 	} else {
 		buf->length -= ret;
 		buf->data += ret;
 	}
+
+	if (cmpxchg(&epfile->read_buffer, NULL, buf))
+		kfree(buf);
+
 	return ret;
 }
 
@@ -783,7 +857,15 @@ static ssize_t __ffs_epfile_read_data(struct ffs_epfile *epfile,
 	buf->length = data_len;
 	buf->data = buf->storage;
 	memcpy(buf->storage, data + ret, data_len);
-	epfile->read_buffer = buf;
+
+	/*
+	 * At this point read_buffer is NULL or READ_BUFFER_DROP (if
+	 * ffs_func_eps_disable has been called in the meanwhile).  See comment
+	 * in struct ffs_epfile for full read_buffer pointer synchronisation
+	 * story.
+	 */
+	if (unlikely(cmpxchg(&epfile->read_buffer, NULL, buf)))
+		kfree(buf);
 
 	return ret;
 }
@@ -1097,8 +1179,7 @@ ffs_epfile_release(struct inode *inode, struct file *file)
 
 	ENTER();
 
-	kfree(epfile->read_buffer);
-	epfile->read_buffer = NULL;
+	__ffs_epfile_read_buffer_free(epfile);
 	ffs_data_closed(epfile->ffs);
 
 	return 0;
@@ -1724,24 +1805,20 @@ static void ffs_func_eps_disable(struct ffs_function *func)
 	unsigned count            = func->ffs->eps_count;
 	unsigned long flags;
 
+	spin_lock_irqsave(&func->ffs->eps_lock, flags);
 	do {
-		if (epfile)
-			mutex_lock(&epfile->mutex);
-		spin_lock_irqsave(&func->ffs->eps_lock, flags);
 		/* pending requests get nuked */
 		if (likely(ep->ep))
 			usb_ep_disable(ep->ep);
 		++ep;
-		spin_unlock_irqrestore(&func->ffs->eps_lock, flags);
 
 		if (epfile) {
 			epfile->ep = NULL;
-			kfree(epfile->read_buffer);
-			epfile->read_buffer = NULL;
-			mutex_unlock(&epfile->mutex);
+			__ffs_epfile_read_buffer_free(epfile);
 			++epfile;
 		}
 	} while (--count);
+	spin_unlock_irqrestore(&func->ffs->eps_lock, flags);
 }
 
 static int ffs_func_eps_enable(struct ffs_function *func)
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 9c8c9ed..fe18116 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -590,8 +590,9 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
 
 	/* throttle high/super speed IRQ rate back slightly */
 	if (gadget_is_dualspeed(dev->gadget))
-		req->no_interrupt = (dev->gadget->speed == USB_SPEED_HIGH ||
-				     dev->gadget->speed == USB_SPEED_SUPER)
+		req->no_interrupt = (((dev->gadget->speed == USB_SPEED_HIGH ||
+				       dev->gadget->speed == USB_SPEED_SUPER)) &&
+					!list_empty(&dev->tx_reqs))
 			? ((atomic_read(&dev->tx_qlen) % dev->qmult) != 0)
 			: 0;
 
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index bb1f6c8..45bc997 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -1978,7 +1978,7 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
 			dev_err(&pdev->dev, "of_probe: name error(%d)\n", ret);
 			goto err;
 		}
-		ep->ep.name = name;
+		ep->ep.name = kasprintf(GFP_KERNEL, "ep%d", ep->index);
 
 		ep->ep_regs = udc->regs + USBA_EPT_BASE(i);
 		ep->dma_regs = udc->regs + USBA_DMA_BASE(i);
diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c
index 876dca4..a268d9e 100644
--- a/drivers/usb/host/ehci-platform.c
+++ b/drivers/usb/host/ehci-platform.c
@@ -39,7 +39,7 @@
 
 #define DRIVER_DESC "EHCI generic platform driver"
 #define EHCI_MAX_CLKS 4
-#define EHCI_MAX_RSTS 3
+#define EHCI_MAX_RSTS 4
 #define hcd_to_ehci_priv(h) ((struct ehci_platform_priv *)hcd_to_ehci(h)->priv)
 
 struct ehci_platform_priv {
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 5b5880c..b38a228 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -221,6 +221,12 @@ static int usb_hcd_at91_probe(const struct hc_driver *driver,
 	ohci->num_ports = board->ports;
 	at91_start_hc(pdev);
 
+	/*
+	 * The RemoteWakeupConnected bit has to be set explicitly
+	 * before calling ohci_run. The reset value of this bit is 0.
+	 */
+	ohci->hc_control = OHCI_CTRL_RWC;
+
 	retval = usb_add_hcd(hcd, irq, IRQF_SHARED);
 	if (retval == 0) {
 		device_wakeup_enable(hcd->self.controller);
@@ -677,9 +683,6 @@ ohci_hcd_at91_drv_suspend(struct device *dev)
 	 * REVISIT: some boards will be able to turn VBUS off...
 	 */
 	if (!ohci_at91->wakeup) {
-		ohci->hc_control = ohci_readl(ohci, &ohci->regs->control);
-		ohci->hc_control &= OHCI_CTRL_RWC;
-		ohci_writel(ohci, ohci->hc_control, &ohci->regs->control);
 		ohci->rh_state = OHCI_RH_HALTED;
 
 		/* flush the writes */
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 1700908..86612ac 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -72,7 +72,7 @@
 static const char	hcd_name [] = "ohci_hcd";
 
 #define	STATECHANGE_DELAY	msecs_to_jiffies(300)
-#define	IO_WATCHDOG_DELAY	msecs_to_jiffies(250)
+#define	IO_WATCHDOG_DELAY	msecs_to_jiffies(275)
 
 #include "ohci.h"
 #include "pci-quirks.h"
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 730b9fd..0ef1690 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1166,7 +1166,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 				xhci_set_link_state(xhci, port_array, wIndex,
 							XDEV_RESUME);
 				spin_unlock_irqrestore(&xhci->lock, flags);
-				msleep(20);
+				msleep(USB_RESUME_TIMEOUT);
 				spin_lock_irqsave(&xhci->lock, flags);
 				xhci_set_link_state(xhci, port_array, wIndex,
 							XDEV_U0);
@@ -1355,6 +1355,35 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 	return 0;
 }
 
+/*
+ * Workaround for missing Cold Attach Status (CAS) if device re-plugged in S3.
+ * warm reset a USB3 device stuck in polling or compliance mode after resume.
+ * See Intel 100/c230 series PCH specification update Doc #332692-006 Errata #8
+ */
+static bool xhci_port_missing_cas_quirk(int port_index,
+					     __le32 __iomem **port_array)
+{
+	u32 portsc;
+
+	portsc = readl(port_array[port_index]);
+
+	/* if any of these are set we are not stuck */
+	if (portsc & (PORT_CONNECT | PORT_CAS))
+		return false;
+
+	if (((portsc & PORT_PLS_MASK) != XDEV_POLLING) &&
+	    ((portsc & PORT_PLS_MASK) != XDEV_COMP_MODE))
+		return false;
+
+	/* clear wakeup/change bits, and do a warm port reset */
+	portsc &= ~(PORT_RWC_BITS | PORT_CEC | PORT_WAKE_BITS);
+	portsc |= PORT_WR;
+	writel(portsc, port_array[port_index]);
+	/* flush write */
+	readl(port_array[port_index]);
+	return true;
+}
+
 int xhci_bus_resume(struct usb_hcd *hcd)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
@@ -1392,6 +1421,14 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 		u32 temp;
 
 		temp = readl(port_array[port_index]);
+
+		/* warm reset CAS limited ports stuck in polling/compliance */
+		if ((xhci->quirks & XHCI_MISSING_CAS) &&
+		    (hcd->speed >= HCD_USB3) &&
+		    xhci_port_missing_cas_quirk(port_index, port_array)) {
+			xhci_dbg(xhci, "reset stuck port %d\n", port_index);
+			continue;
+		}
 		if (DEV_SUPERSPEED_ANY(temp))
 			temp &= ~(PORT_RWC_BITS | PORT_CEC | PORT_WAKE_BITS);
 		else
@@ -1410,7 +1447,7 @@ int xhci_bus_resume(struct usb_hcd *hcd)
 
 	if (need_usb2_u3_exit) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
-		msleep(20);
+		msleep(USB_RESUME_TIMEOUT);
 		spin_lock_irqsave(&xhci->lock, flags);
 	}
 
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index d7b0f97..e96ae80 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -45,11 +45,13 @@
 
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI	0x8c31
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI	0x9c31
+#define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI	0x9cb1
 #define PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI		0x22b5
 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI		0xa12f
 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI	0x9d2f
 #define PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI		0x0aa8
 #define PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI		0x1aa8
+#define PCI_DEVICE_ID_INTEL_APL_XHCI			0x5aa8
 
 static const char hcd_name[] = "xhci_hcd";
 
@@ -153,7 +155,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_SPURIOUS_REBOOT;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
-		pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI) {
+		(pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI)) {
 		xhci->quirks |= XHCI_SPURIOUS_REBOOT;
 		xhci->quirks |= XHCI_SPURIOUS_WAKEUP;
 	}
@@ -169,6 +172,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
 		xhci->quirks |= XHCI_SSIC_PORT_UNUSED;
 	}
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+	    (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI))
+		xhci->quirks |= XHCI_MISSING_CAS;
+
 	if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
 			pdev->device == PCI_DEVICE_ID_EJ168) {
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index b2c1dc5..f945380 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -314,6 +314,8 @@ struct xhci_op_regs {
 #define XDEV_U2		(0x2 << 5)
 #define XDEV_U3		(0x3 << 5)
 #define XDEV_INACTIVE	(0x6 << 5)
+#define XDEV_POLLING	(0x7 << 5)
+#define XDEV_COMP_MODE  (0xa << 5)
 #define XDEV_RESUME	(0xf << 5)
 /* true: port has power (see HCC_PPC) */
 #define PORT_POWER	(1 << 9)
@@ -1653,6 +1655,7 @@ struct xhci_hcd {
 #define XHCI_MTK_HOST		(1 << 21)
 #define XHCI_SSIC_PORT_UNUSED	(1 << 22)
 #define XHCI_NO_64BIT_SUPPORT	(1 << 23)
+#define XHCI_MISSING_CAS	(1 << 24)
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;
 	/* There are two roothubs to keep track of bus suspend info for */
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index bff4869..4042ea0 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1255,6 +1255,7 @@ static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req,
 
 	map_dma_buffer(request, musb, musb_ep);
 
+	pm_runtime_get_sync(musb->controller);
 	spin_lock_irqsave(&musb->lock, lockflags);
 
 	/* don't queue if the ep is down */
@@ -1275,6 +1276,9 @@ static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req,
 
 unlock:
 	spin_unlock_irqrestore(&musb->lock, lockflags);
+	pm_runtime_mark_last_busy(musb->controller);
+	pm_runtime_put_autosuspend(musb->controller);
+
 	return status;
 }
 
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 1ab6973..cc12254 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -287,6 +287,7 @@ static int omap2430_musb_init(struct musb *musb)
 	}
 	musb->isr = omap2430_musb_interrupt;
 	phy_init(musb->phy);
+	phy_power_on(musb->phy);
 
 	l = musb_readl(musb->mregs, OTG_INTERFSEL);
 
@@ -323,8 +324,6 @@ static void omap2430_musb_enable(struct musb *musb)
 	struct musb_hdrc_platform_data *pdata = dev_get_platdata(dev);
 	struct omap_musb_board_data *data = pdata->board_data;
 
-	if (!WARN_ON(!musb->phy))
-		phy_power_on(musb->phy);
 
 	switch (glue->status) {
 
@@ -361,9 +360,6 @@ static void omap2430_musb_disable(struct musb *musb)
 	struct device *dev = musb->controller;
 	struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
 
-	if (!WARN_ON(!musb->phy))
-		phy_power_off(musb->phy);
-
 	if (glue->status != MUSB_UNKNOWN)
 		omap_control_usb_set_mode(glue->control_otghs,
 			USB_MODE_DISCONNECT);
@@ -375,6 +371,7 @@ static int omap2430_musb_exit(struct musb *musb)
 	struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
 
 	omap2430_low_level_exit(musb);
+	phy_power_off(musb->phy);
 	phy_exit(musb->phy);
 	musb->phy = NULL;
 	cancel_work_sync(&glue->omap_musb_mailbox_work);
diff --git a/drivers/usb/renesas_usbhs/rcar3.c b/drivers/usb/renesas_usbhs/rcar3.c
index 1d70add..d544b33 100644
--- a/drivers/usb/renesas_usbhs/rcar3.c
+++ b/drivers/usb/renesas_usbhs/rcar3.c
@@ -9,6 +9,7 @@
  *
  */
 
+#include <linux/delay.h>
 #include <linux/io.h>
 #include "common.h"
 #include "rcar3.h"
@@ -35,10 +36,13 @@ static int usbhs_rcar3_power_ctrl(struct platform_device *pdev,
 
 	usbhs_write32(priv, UGCTRL2, UGCTRL2_RESERVED_3 | UGCTRL2_USB0SEL_OTG);
 
-	if (enable)
+	if (enable) {
 		usbhs_bset(priv, LPSTS, LPSTS_SUSPM, LPSTS_SUSPM);
-	else
+		/* The controller on R-Car Gen3 needs to wait up to 45 usec */
+		udelay(45);
+	} else {
 		usbhs_bset(priv, LPSTS, LPSTS_SUSPM, 0);
+	}
 
 	return 0;
 }
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 54a4de0..f61477b 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -1077,7 +1077,9 @@ static int cp210x_tiocmget(struct tty_struct *tty)
 	u8 control;
 	int result;
 
-	cp210x_read_u8_reg(port, CP210X_GET_MDMSTS, &control);
+	result = cp210x_read_u8_reg(port, CP210X_GET_MDMSTS, &control);
+	if (result)
+		return result;
 
 	result = ((control & CONTROL_DTR) ? TIOCM_DTR : 0)
 		|((control & CONTROL_RTS) ? TIOCM_RTS : 0)
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index b2d767e..0ff7f38 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -986,7 +986,8 @@ static const struct usb_device_id id_table_combined[] = {
 	/* ekey Devices */
 	{ USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) },
 	/* Infineon Devices */
-	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_TC1798_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_TC2X7_PID, 1) },
 	/* GE Healthcare devices */
 	{ USB_DEVICE(GE_HEALTHCARE_VID, GE_HEALTHCARE_NEMO_TRACKER_PID) },
 	/* Active Research (Actisense) devices */
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index f87a938..21011c0 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -626,8 +626,9 @@
 /*
  * Infineon Technologies
  */
-#define INFINEON_VID		0x058b
-#define INFINEON_TRIBOARD_PID	0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+#define INFINEON_VID		        0x058b
+#define INFINEON_TRIBOARD_TC1798_PID	0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+#define INFINEON_TRIBOARD_TC2X7_PID	0x0043 /* DAS JTAG TriBoard TC2X7 V1.0 */
 
 /*
  * Acton Research Corp.
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index d213cf4..4a037b4 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1078,7 +1078,8 @@ static int usb_serial_probe(struct usb_interface *interface,
 
 	serial->disconnected = 0;
 
-	usb_serial_console_init(serial->port[0]->minor);
+	if (num_ports > 0)
+		usb_serial_console_init(serial->port[0]->minor);
 exit:
 	module_put(type->driver.owner);
 	return 0;
diff --git a/drivers/usb/wusbcore/crypto.c b/drivers/usb/wusbcore/crypto.c
index 79b2b62..79451f7 100644
--- a/drivers/usb/wusbcore/crypto.c
+++ b/drivers/usb/wusbcore/crypto.c
@@ -133,6 +133,13 @@ static void bytewise_xor(void *_bo, const void *_bi1, const void *_bi2,
 		bo[itr] = bi1[itr] ^ bi2[itr];
 }
 
+/* Scratch space for MAC calculations. */
+struct wusb_mac_scratch {
+	struct aes_ccm_b0 b0;
+	struct aes_ccm_b1 b1;
+	struct aes_ccm_a ax;
+};
+
 /*
  * CC-MAC function WUSB1.0[6.5]
  *
@@ -197,16 +204,15 @@ static void bytewise_xor(void *_bo, const void *_bi1, const void *_bi2,
  *       what sg[4] is for. Maybe there is a smarter way to do this.
  */
 static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
-			struct crypto_cipher *tfm_aes, void *mic,
+			struct crypto_cipher *tfm_aes,
+			struct wusb_mac_scratch *scratch,
+			void *mic,
 			const struct aes_ccm_nonce *n,
 			const struct aes_ccm_label *a, const void *b,
 			size_t blen)
 {
 	int result = 0;
 	SKCIPHER_REQUEST_ON_STACK(req, tfm_cbc);
-	struct aes_ccm_b0 b0;
-	struct aes_ccm_b1 b1;
-	struct aes_ccm_a ax;
 	struct scatterlist sg[4], sg_dst;
 	void *dst_buf;
 	size_t dst_size;
@@ -218,16 +224,17 @@ static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
 	 * These checks should be compile time optimized out
 	 * ensure @a fills b1's mac_header and following fields
 	 */
-	WARN_ON(sizeof(*a) != sizeof(b1) - sizeof(b1.la));
-	WARN_ON(sizeof(b0) != sizeof(struct aes_ccm_block));
-	WARN_ON(sizeof(b1) != sizeof(struct aes_ccm_block));
-	WARN_ON(sizeof(ax) != sizeof(struct aes_ccm_block));
+	WARN_ON(sizeof(*a) != sizeof(scratch->b1) - sizeof(scratch->b1.la));
+	WARN_ON(sizeof(scratch->b0) != sizeof(struct aes_ccm_block));
+	WARN_ON(sizeof(scratch->b1) != sizeof(struct aes_ccm_block));
+	WARN_ON(sizeof(scratch->ax) != sizeof(struct aes_ccm_block));
 
 	result = -ENOMEM;
 	zero_padding = blen % sizeof(struct aes_ccm_block);
 	if (zero_padding)
 		zero_padding = sizeof(struct aes_ccm_block) - zero_padding;
-	dst_size = blen + sizeof(b0) + sizeof(b1) + zero_padding;
+	dst_size = blen + sizeof(scratch->b0) + sizeof(scratch->b1) +
+		zero_padding;
 	dst_buf = kzalloc(dst_size, GFP_KERNEL);
 	if (!dst_buf)
 		goto error_dst_buf;
@@ -235,9 +242,9 @@ static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
 	memset(iv, 0, sizeof(iv));
 
 	/* Setup B0 */
-	b0.flags = 0x59;	/* Format B0 */
-	b0.ccm_nonce = *n;
-	b0.lm = cpu_to_be16(0);	/* WUSB1.0[6.5] sez l(m) is 0 */
+	scratch->b0.flags = 0x59;	/* Format B0 */
+	scratch->b0.ccm_nonce = *n;
+	scratch->b0.lm = cpu_to_be16(0);	/* WUSB1.0[6.5] sez l(m) is 0 */
 
 	/* Setup B1
 	 *
@@ -246,12 +253,12 @@ static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
 	 * 14'--after clarification, it means to use A's contents
 	 * for MAC Header, EO, sec reserved and padding.
 	 */
-	b1.la = cpu_to_be16(blen + 14);
-	memcpy(&b1.mac_header, a, sizeof(*a));
+	scratch->b1.la = cpu_to_be16(blen + 14);
+	memcpy(&scratch->b1.mac_header, a, sizeof(*a));
 
 	sg_init_table(sg, ARRAY_SIZE(sg));
-	sg_set_buf(&sg[0], &b0, sizeof(b0));
-	sg_set_buf(&sg[1], &b1, sizeof(b1));
+	sg_set_buf(&sg[0], &scratch->b0, sizeof(scratch->b0));
+	sg_set_buf(&sg[1], &scratch->b1, sizeof(scratch->b1));
 	sg_set_buf(&sg[2], b, blen);
 	/* 0 if well behaved :) */
 	sg_set_buf(&sg[3], bzero, zero_padding);
@@ -276,11 +283,12 @@ static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
 	 * POS Crypto API: size is assumed to be AES's block size.
 	 * Thanks for documenting it -- tip taken from airo.c
 	 */
-	ax.flags = 0x01;		/* as per WUSB 1.0 spec */
-	ax.ccm_nonce = *n;
-	ax.counter = 0;
-	crypto_cipher_encrypt_one(tfm_aes, (void *)&ax, (void *)&ax);
-	bytewise_xor(mic, &ax, iv, 8);
+	scratch->ax.flags = 0x01;		/* as per WUSB 1.0 spec */
+	scratch->ax.ccm_nonce = *n;
+	scratch->ax.counter = 0;
+	crypto_cipher_encrypt_one(tfm_aes, (void *)&scratch->ax,
+				  (void *)&scratch->ax);
+	bytewise_xor(mic, &scratch->ax, iv, 8);
 	result = 8;
 error_cbc_crypt:
 	kfree(dst_buf);
@@ -303,6 +311,7 @@ ssize_t wusb_prf(void *out, size_t out_size,
 	struct aes_ccm_nonce n = *_n;
 	struct crypto_skcipher *tfm_cbc;
 	struct crypto_cipher *tfm_aes;
+	struct wusb_mac_scratch *scratch;
 	u64 sfn = 0;
 	__le64 sfn_le;
 
@@ -329,17 +338,25 @@ ssize_t wusb_prf(void *out, size_t out_size,
 		printk(KERN_ERR "E: can't set AES key: %d\n", (int)result);
 		goto error_setkey_aes;
 	}
+	scratch = kmalloc(sizeof(*scratch), GFP_KERNEL);
+	if (!scratch) {
+		result = -ENOMEM;
+		goto error_alloc_scratch;
+	}
 
 	for (bitr = 0; bitr < (len + 63) / 64; bitr++) {
 		sfn_le = cpu_to_le64(sfn++);
 		memcpy(&n.sfn, &sfn_le, sizeof(n.sfn));	/* n.sfn++... */
-		result = wusb_ccm_mac(tfm_cbc, tfm_aes, out + bytes,
+		result = wusb_ccm_mac(tfm_cbc, tfm_aes, scratch, out + bytes,
 				      &n, a, b, blen);
 		if (result < 0)
 			goto error_ccm_mac;
 		bytes += result;
 	}
 	result = bytes;
+
+	kfree(scratch);
+error_alloc_scratch:
 error_ccm_mac:
 error_setkey_aes:
 	crypto_free_cipher(tfm_aes);
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index d624a52..031bc08 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -829,8 +829,9 @@ static long vfio_pci_ioctl(void *device_data,
 
 	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
 		struct vfio_irq_set hdr;
+		size_t size;
 		u8 *data = NULL;
-		int ret = 0;
+		int max, ret = 0;
 
 		minsz = offsetofend(struct vfio_irq_set, count);
 
@@ -838,23 +839,31 @@ static long vfio_pci_ioctl(void *device_data,
 			return -EFAULT;
 
 		if (hdr.argsz < minsz || hdr.index >= VFIO_PCI_NUM_IRQS ||
+		    hdr.count >= (U32_MAX - hdr.start) ||
 		    hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
 				  VFIO_IRQ_SET_ACTION_TYPE_MASK))
 			return -EINVAL;
 
-		if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
-			size_t size;
-			int max = vfio_pci_get_irq_count(vdev, hdr.index);
+		max = vfio_pci_get_irq_count(vdev, hdr.index);
+		if (hdr.start >= max || hdr.start + hdr.count > max)
+			return -EINVAL;
 
-			if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL)
-				size = sizeof(uint8_t);
-			else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD)
-				size = sizeof(int32_t);
-			else
-				return -EINVAL;
+		switch (hdr.flags & VFIO_IRQ_SET_DATA_TYPE_MASK) {
+		case VFIO_IRQ_SET_DATA_NONE:
+			size = 0;
+			break;
+		case VFIO_IRQ_SET_DATA_BOOL:
+			size = sizeof(uint8_t);
+			break;
+		case VFIO_IRQ_SET_DATA_EVENTFD:
+			size = sizeof(int32_t);
+			break;
+		default:
+			return -EINVAL;
+		}
 
-			if (hdr.argsz - minsz < hdr.count * size ||
-			    hdr.start >= max || hdr.start + hdr.count > max)
+		if (size) {
+			if (hdr.argsz - minsz < hdr.count * size)
 				return -EINVAL;
 
 			data = memdup_user((void __user *)(arg + minsz),
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index c2e6089..1c46045 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -256,7 +256,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
 	if (!is_irq_none(vdev))
 		return -EINVAL;
 
-	vdev->ctx = kzalloc(nvec * sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
+	vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
 	if (!vdev->ctx)
 		return -ENOMEM;
 
diff --git a/drivers/virtio/config.c b/drivers/virtio/config.c
deleted file mode 100644
index f70bcd2..0000000
--- a/drivers/virtio/config.c
+++ /dev/null
@@ -1,12 +0,0 @@
-/* Configuration space parsing helpers for virtio.
- *
- * The configuration is [type][len][... len bytes ...] fields.
- *
- * Copyright 2007 Rusty Russell, IBM Corporation.
- * GPL v2 or later.
- */
-#include <linux/err.h>
-#include <linux/virtio.h>
-#include <linux/virtio_config.h>
-#include <linux/bug.h>
-
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 4e7003d..181793f 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -577,6 +577,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
+	if (towards_target(vb))
+		virtballoon_changed(vdev);
 	return 0;
 
 out_del_vqs:
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 8c4e617..6d9e517 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -212,10 +212,18 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 		return -ENODEV;
 	}
 
-	rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
-	if (rc)
-		rc = dma_set_mask_and_coherent(&pci_dev->dev,
-						DMA_BIT_MASK(32));
+	rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64));
+	if (rc) {
+		rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
+	} else {
+		/*
+		 * The virtio ring base address is expressed as a 32-bit PFN,
+		 * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT.
+		 */
+		dma_set_coherent_mask(&pci_dev->dev,
+				DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT));
+	}
+
 	if (rc)
 		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
 
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index ed9c9ee..489bfc6 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -167,7 +167,7 @@ static bool vring_use_dma_api(struct virtio_device *vdev)
  * making all of the arch DMA ops work on the vring device itself
  * is a mess.  For now, we use the parent device for DMA ops.
  */
-static struct device *vring_dma_dev(const struct vring_virtqueue *vq)
+static inline struct device *vring_dma_dev(const struct vring_virtqueue *vq)
 {
 	return vq->vq.vdev->dev.parent;
 }
@@ -732,7 +732,8 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
 
 	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
 		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
-		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+		if (!vq->event)
+			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
 	}
 
 }
@@ -764,7 +765,8 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
 	 * entry. Always do both to keep code simple. */
 	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
 		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
-		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+		if (!vq->event)
+			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
 	}
 	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
 	END_USE(vq);
@@ -832,10 +834,11 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	 * more to do. */
 	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
 	 * either clear the flags bit or point the event index at the next
-	 * entry. Always do both to keep code simple. */
+	 * entry. Always update the event index to keep code simple. */
 	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
 		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
-		vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+		if (!vq->event)
+			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
 	}
 	/* TODO: tune this threshold */
 	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
@@ -953,7 +956,8 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback) {
 		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
-		vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+		if (!vq->event)
+			vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
 	}
 
 	/* Put everything in free lists. */
diff --git a/drivers/vme/vme.c b/drivers/vme/vme.c
index 15b6407..bdbadaa 100644
--- a/drivers/vme/vme.c
+++ b/drivers/vme/vme.c
@@ -156,12 +156,16 @@ size_t vme_get_size(struct vme_resource *resource)
 	case VME_MASTER:
 		retval = vme_master_get(resource, &enabled, &base, &size,
 			&aspace, &cycle, &dwidth);
+		if (retval)
+			return 0;
 
 		return size;
 		break;
 	case VME_SLAVE:
 		retval = vme_slave_get(resource, &enabled, &base, &size,
 			&buf_base, &aspace, &cycle);
+		if (retval)
+			return 0;
 
 		return size;
 		break;
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 2037e7a..d764236 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -91,11 +91,9 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
  */
 bool afs_cm_incoming_call(struct afs_call *call)
 {
-	u32 operation_id = ntohl(call->operation_ID);
+	_enter("{CB.OP %u}", call->operation_ID);
 
-	_enter("{CB.OP %u}", operation_id);
-
-	switch (operation_id) {
+	switch (call->operation_ID) {
 	case CBCallBack:
 		call->type = &afs_SRXCBCallBack;
 		return true;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 96f4d76..31c616a 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -364,7 +364,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 			buffer = kmap(page);
 			ret = afs_extract_data(call, buffer,
 					       call->count, true);
-			kunmap(buffer);
+			kunmap(page);
 			if (ret < 0)
 				return ret;
 		}
@@ -397,7 +397,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		page = call->reply3;
 		buffer = kmap(page);
 		memset(buffer + call->count, 0, PAGE_SIZE - call->count);
-		kunmap(buffer);
+		kunmap(page);
 	}
 
 	_leave(" = 0 [done]");
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 5497c84..535a38d 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -112,7 +112,7 @@ struct afs_call {
 	bool			need_attention;	/* T if RxRPC poked us */
 	u16			service_id;	/* RxRPC service ID to call */
 	__be16			port;		/* target UDP port */
-	__be32			operation_ID;	/* operation ID for an incoming call */
+	u32			operation_ID;	/* operation ID for an incoming call */
 	u32			count;		/* count for use in unmarshalling */
 	__be32			tmp;		/* place to extract temporary data */
 	afs_dataversion_t	store_version;	/* updated version expected from store */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 477928b..25f05a8 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -676,10 +676,11 @@ static int afs_deliver_cm_op_id(struct afs_call *call)
 	ASSERTCMP(call->offset, <, 4);
 
 	/* the operation ID forms the first four bytes of the request data */
-	ret = afs_extract_data(call, &call->operation_ID, 4, true);
+	ret = afs_extract_data(call, &call->tmp, 4, true);
 	if (ret < 0)
 		return ret;
 
+	call->operation_ID = ntohl(call->tmp);
 	call->state = AFS_CALL_AWAIT_REQUEST;
 	call->offset = 0;
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 210c94a..4607af3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2647,7 +2647,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 
 		btrfs_free_delayed_extent_op(extent_op);
 		if (ret) {
+			spin_lock(&delayed_refs->lock);
 			locked_ref->processing = 0;
+			delayed_refs->num_heads_ready++;
+			spin_unlock(&delayed_refs->lock);
 			btrfs_delayed_ref_unlock(locked_ref);
 			btrfs_put_delayed_ref(ref);
 			btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 66a7551..8ed05d9 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5569,7 +5569,7 @@ void le_bitmap_set(u8 *map, unsigned int start, int len)
 		*p |= mask_to_set;
 		len -= bits_to_set;
 		bits_to_set = BITS_PER_BYTE;
-		mask_to_set = ~(u8)0;
+		mask_to_set = ~0;
 		p++;
 	}
 	if (len) {
@@ -5589,7 +5589,7 @@ void le_bitmap_clear(u8 *map, unsigned int start, int len)
 		*p &= ~mask_to_clear;
 		len -= bits_to_clear;
 		bits_to_clear = BITS_PER_BYTE;
-		mask_to_clear = ~(u8)0;
+		mask_to_clear = ~0;
 		p++;
 	}
 	if (len) {
@@ -5679,7 +5679,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
 		kaddr[offset] |= mask_to_set;
 		len -= bits_to_set;
 		bits_to_set = BITS_PER_BYTE;
-		mask_to_set = ~(u8)0;
+		mask_to_set = ~0;
 		if (++offset >= PAGE_SIZE && len > 0) {
 			offset = 0;
 			page = eb->pages[++i];
@@ -5721,7 +5721,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
 		kaddr[offset] &= ~mask_to_clear;
 		len -= bits_to_clear;
 		bits_to_clear = BITS_PER_BYTE;
-		mask_to_clear = ~(u8)0;
+		mask_to_clear = ~0;
 		if (++offset >= PAGE_SIZE && len > 0) {
 			offset = 0;
 			page = eb->pages[++i];
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2b790bd..8e3a5a2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4605,8 +4605,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			BUG_ON(ret);
 			if (btrfs_should_throttle_delayed_refs(trans, root))
 				btrfs_async_run_delayed_refs(root,
-							     trans->transid,
-					trans->delayed_ref_updates * 2, 0);
+					trans->delayed_ref_updates * 2,
+					trans->transid, 0);
 			if (be_nice) {
 				if (truncate_space_check(trans, root,
 							 extent_num_bytes)) {
@@ -8931,9 +8931,14 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 	 *    So even we call qgroup_free_data(), it won't decrease reserved
 	 *    space.
 	 * 2) Not written to disk
-	 *    This means the reserved space should be freed here.
+	 *    This means the reserved space should be freed here. However,
+	 *    if a truncate invalidates the page (by clearing PageDirty)
+	 *    and the page is accounted for while allocating extent
+	 *    in btrfs_check_data_free_space() we let delayed_ref to
+	 *    free the entire extent.
 	 */
-	btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
+	if (PageDirty(page))
+		btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 18e1aa0f..7acbd2c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3814,6 +3814,11 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 		}
 		btrfs_release_path(path);
 		key.offset = next_key_min_offset;
+
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			goto out;
+		}
 	}
 	ret = 0;
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 0ec8ffa..c4af0cd 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2728,7 +2728,14 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 
 		bytenr = btrfs_node_blockptr(upper->eb, slot);
 		if (lowest) {
-			BUG_ON(bytenr != node->bytenr);
+			if (bytenr != node->bytenr) {
+				btrfs_err(root->fs_info,
+		"lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu",
+					  bytenr, node->bytenr, slot,
+					  upper->eb->start);
+				err = -EIO;
+				goto next;
+			}
 		} else {
 			if (node->eb->start == bytenr)
 				goto next;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 01bc36c..71261b4 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5805,6 +5805,64 @@ static int changed_extent(struct send_ctx *sctx,
 	int ret = 0;
 
 	if (sctx->cur_ino != sctx->cmp_key->objectid) {
+
+		if (result == BTRFS_COMPARE_TREE_CHANGED) {
+			struct extent_buffer *leaf_l;
+			struct extent_buffer *leaf_r;
+			struct btrfs_file_extent_item *ei_l;
+			struct btrfs_file_extent_item *ei_r;
+
+			leaf_l = sctx->left_path->nodes[0];
+			leaf_r = sctx->right_path->nodes[0];
+			ei_l = btrfs_item_ptr(leaf_l,
+					      sctx->left_path->slots[0],
+					      struct btrfs_file_extent_item);
+			ei_r = btrfs_item_ptr(leaf_r,
+					      sctx->right_path->slots[0],
+					      struct btrfs_file_extent_item);
+
+			/*
+			 * We may have found an extent item that has changed
+			 * only its disk_bytenr field and the corresponding
+			 * inode item was not updated. This case happens due to
+			 * very specific timings during relocation when a leaf
+			 * that contains file extent items is COWed while
+			 * relocation is ongoing and its in the stage where it
+			 * updates data pointers. So when this happens we can
+			 * safely ignore it since we know it's the same extent,
+			 * but just at different logical and physical locations
+			 * (when an extent is fully replaced with a new one, we
+			 * know the generation number must have changed too,
+			 * since snapshot creation implies committing the current
+			 * transaction, and the inode item must have been updated
+			 * as well).
+			 * This replacement of the disk_bytenr happens at
+			 * relocation.c:replace_file_extents() through
+			 * relocation.c:btrfs_reloc_cow_block().
+			 */
+			if (btrfs_file_extent_generation(leaf_l, ei_l) ==
+			    btrfs_file_extent_generation(leaf_r, ei_r) &&
+			    btrfs_file_extent_ram_bytes(leaf_l, ei_l) ==
+			    btrfs_file_extent_ram_bytes(leaf_r, ei_r) &&
+			    btrfs_file_extent_compression(leaf_l, ei_l) ==
+			    btrfs_file_extent_compression(leaf_r, ei_r) &&
+			    btrfs_file_extent_encryption(leaf_l, ei_l) ==
+			    btrfs_file_extent_encryption(leaf_r, ei_r) &&
+			    btrfs_file_extent_other_encoding(leaf_l, ei_l) ==
+			    btrfs_file_extent_other_encoding(leaf_r, ei_r) &&
+			    btrfs_file_extent_type(leaf_l, ei_l) ==
+			    btrfs_file_extent_type(leaf_r, ei_r) &&
+			    btrfs_file_extent_disk_bytenr(leaf_l, ei_l) !=
+			    btrfs_file_extent_disk_bytenr(leaf_r, ei_r) &&
+			    btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) ==
+			    btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) &&
+			    btrfs_file_extent_offset(leaf_l, ei_l) ==
+			    btrfs_file_extent_offset(leaf_r, ei_r) &&
+			    btrfs_file_extent_num_bytes(leaf_l, ei_l) ==
+			    btrfs_file_extent_num_bytes(leaf_r, ei_r))
+				return 0;
+		}
+
 		inconsistent_snapshot_error(sctx, result, "extent");
 		return -EIO;
 	}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 528cae1..3d33c4e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2713,14 +2713,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root,
 					     int index, int error)
 {
 	struct btrfs_log_ctx *ctx;
+	struct btrfs_log_ctx *safe;
 
-	if (!error) {
-		INIT_LIST_HEAD(&root->log_ctxs[index]);
-		return;
-	}
-
-	list_for_each_entry(ctx, &root->log_ctxs[index], list)
+	list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) {
+		list_del_init(&ctx->list);
 		ctx->log_ret = error;
+	}
 
 	INIT_LIST_HEAD(&root->log_ctxs[index]);
 }
@@ -2961,13 +2959,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	mutex_unlock(&root->log_mutex);
 
 out_wake_log_root:
-	/*
-	 * We needn't get log_mutex here because we are sure all
-	 * the other tasks are blocked.
-	 */
+	mutex_lock(&log_root_tree->log_mutex);
 	btrfs_remove_all_log_ctxs(log_root_tree, index2, ret);
 
-	mutex_lock(&log_root_tree->log_mutex);
 	log_root_tree->log_transid_committed++;
 	atomic_set(&log_root_tree->log_commit[index2], 0);
 	mutex_unlock(&log_root_tree->log_mutex);
@@ -2978,10 +2972,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
 		wake_up(&log_root_tree->log_commit_wait[index2]);
 out:
-	/* See above. */
-	btrfs_remove_all_log_ctxs(root, index1, ret);
-
 	mutex_lock(&root->log_mutex);
+	btrfs_remove_all_log_ctxs(root, index1, ret);
 	root->log_transid_committed++;
 	atomic_set(&root->log_commit[index1], 0);
 	mutex_unlock(&root->log_mutex);
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 79101651..42f9a0a 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -137,7 +137,7 @@ static bool exofs_check_page(struct page *page)
 bad_entry:
 	EXOFS_ERR(
 		"ERROR [exofs_check_page]: bad entry in directory(0x%lx): %s - "
-		"offset=%lu, inode=0x%llu, rec_len=%d, name_len=%d\n",
+		"offset=%lu, inode=0x%llx, rec_len=%d, name_len=%d\n",
 		dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs,
 		_LLU(le64_to_cpu(p->inode_no)),
 		rec_len, p->name_len);
diff --git a/fs/iomap.c b/fs/iomap.c
index 013d1d3..a8ee8c3 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct page *page = data;
 	int ret;
 
-	ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length,
-			NULL, iomap);
+	ret = __block_write_begin_int(page, pos, length, NULL, iomap);
 	if (ret)
 		return ret;
 
@@ -561,7 +560,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 	}
 
 	while (len > 0) {
-		ret = iomap_apply(inode, start, len, 0, ops, &ctx,
+		ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx,
 				iomap_fiemap_actor);
 		/* inode with no (attribute) mapping will give ENOENT */
 		if (ret == -ENOENT)
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 2bcb86e..78219d5 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -911,6 +911,7 @@ const struct file_operations kernfs_file_fops = {
 	.open		= kernfs_fop_open,
 	.release	= kernfs_fop_release,
 	.poll		= kernfs_fop_poll,
+	.fsync		= noop_fsync,
 };
 
 /**
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index b10d557..ee36efd 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -84,6 +84,8 @@ struct nfsd_net {
 	struct list_head client_lru;
 	struct list_head close_lru;
 	struct list_head del_recall_lru;
+
+	/* protected by blocked_locks_lock */
 	struct list_head blocked_locks_lru;
 
 	struct delayed_work laundromat_work;
@@ -91,6 +93,9 @@ struct nfsd_net {
 	/* client_lock protects the client lru list and session hash table */
 	spinlock_t client_lock;
 
+	/* protects blocked_locks_lru */
+	spinlock_t blocked_locks_lock;
+
 	struct file *rec_file;
 	bool in_grace;
 	const struct nfsd4_client_tracking_ops *client_tracking_ops;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9752beb..4b4beaa 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -217,7 +217,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 {
 	struct nfsd4_blocked_lock *cur, *found = NULL;
 
-	spin_lock(&nn->client_lock);
+	spin_lock(&nn->blocked_locks_lock);
 	list_for_each_entry(cur, &lo->lo_blocked, nbl_list) {
 		if (fh_match(fh, &cur->nbl_fh)) {
 			list_del_init(&cur->nbl_list);
@@ -226,7 +226,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 			break;
 		}
 	}
-	spin_unlock(&nn->client_lock);
+	spin_unlock(&nn->blocked_locks_lock);
 	if (found)
 		posix_unblock_lock(&found->nbl_lock);
 	return found;
@@ -1227,9 +1227,7 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp,
 
 static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-	struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
-
-	lockdep_assert_held(&oo->oo_owner.so_client->cl_lock);
+	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
 
 	list_del_init(&stp->st_locks);
 	nfs4_unhash_stid(&stp->st_stid);
@@ -1238,12 +1236,12 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 
 static void release_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-	struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
+	struct nfs4_client *clp = stp->st_stid.sc_client;
 	bool unhashed;
 
-	spin_lock(&oo->oo_owner.so_client->cl_lock);
+	spin_lock(&clp->cl_lock);
 	unhashed = unhash_lock_stateid(stp);
-	spin_unlock(&oo->oo_owner.so_client->cl_lock);
+	spin_unlock(&clp->cl_lock);
 	if (unhashed)
 		nfs4_put_stid(&stp->st_stid);
 }
@@ -4665,7 +4663,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 	 * indefinitely once the lock does become free.
 	 */
 	BUG_ON(!list_empty(&reaplist));
-	spin_lock(&nn->client_lock);
+	spin_lock(&nn->blocked_locks_lock);
 	while (!list_empty(&nn->blocked_locks_lru)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
 					struct nfsd4_blocked_lock, nbl_lru);
@@ -4678,7 +4676,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 		list_move(&nbl->nbl_lru, &reaplist);
 		list_del_init(&nbl->nbl_list);
 	}
-	spin_unlock(&nn->client_lock);
+	spin_unlock(&nn->blocked_locks_lock);
 
 	while (!list_empty(&reaplist)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
@@ -5439,13 +5437,13 @@ nfsd4_lm_notify(struct file_lock *fl)
 	bool queue = false;
 
 	/* An empty list means that something else is going to be using it */
-	spin_lock(&nn->client_lock);
+	spin_lock(&nn->blocked_locks_lock);
 	if (!list_empty(&nbl->nbl_list)) {
 		list_del_init(&nbl->nbl_list);
 		list_del_init(&nbl->nbl_lru);
 		queue = true;
 	}
-	spin_unlock(&nn->client_lock);
+	spin_unlock(&nn->blocked_locks_lock);
 
 	if (queue)
 		nfsd4_run_cb(&nbl->nbl_cb);
@@ -5868,10 +5866,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (fl_flags & FL_SLEEP) {
 		nbl->nbl_time = jiffies;
-		spin_lock(&nn->client_lock);
+		spin_lock(&nn->blocked_locks_lock);
 		list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
 		list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru);
-		spin_unlock(&nn->client_lock);
+		spin_unlock(&nn->blocked_locks_lock);
 	}
 
 	err = vfs_lock_file(filp, F_SETLK, file_lock, conflock);
@@ -5900,10 +5898,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (nbl) {
 		/* dequeue it if we queued it before */
 		if (fl_flags & FL_SLEEP) {
-			spin_lock(&nn->client_lock);
+			spin_lock(&nn->blocked_locks_lock);
 			list_del_init(&nbl->nbl_list);
 			list_del_init(&nbl->nbl_lru);
-			spin_unlock(&nn->client_lock);
+			spin_unlock(&nn->blocked_locks_lock);
 		}
 		free_blocked_lock(nbl);
 	}
@@ -6943,9 +6941,11 @@ static int nfs4_state_create_net(struct net *net)
 	INIT_LIST_HEAD(&nn->client_lru);
 	INIT_LIST_HEAD(&nn->close_lru);
 	INIT_LIST_HEAD(&nn->del_recall_lru);
-	INIT_LIST_HEAD(&nn->blocked_locks_lru);
 	spin_lock_init(&nn->client_lock);
 
+	spin_lock_init(&nn->blocked_locks_lock);
+	INIT_LIST_HEAD(&nn->blocked_locks_lru);
+
 	INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
 	get_net(net);
 
@@ -7063,14 +7063,14 @@ nfs4_state_shutdown_net(struct net *net)
 	}
 
 	BUG_ON(!list_empty(&reaplist));
-	spin_lock(&nn->client_lock);
+	spin_lock(&nn->blocked_locks_lock);
 	while (!list_empty(&nn->blocked_locks_lru)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
 					struct nfsd4_blocked_lock, nbl_lru);
 		list_move(&nbl->nbl_lru, &reaplist);
 		list_del_init(&nbl->nbl_list);
 	}
-	spin_unlock(&nn->client_lock);
+	spin_unlock(&nn->blocked_locks_lock);
 
 	while (!list_empty(&reaplist)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
index 1e8fe84..5355efb 100644
--- a/fs/orangefs/dcache.c
+++ b/fs/orangefs/dcache.c
@@ -73,7 +73,7 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
 		}
 	}
 
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 	ret = 1;
 out_release_op:
 	op_release(new_op);
@@ -94,8 +94,9 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
 static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	int ret;
+	unsigned long time = (unsigned long) dentry->d_fsdata;
 
-	if (time_before(jiffies, dentry->d_time))
+	if (time_before(jiffies, time))
 		return 1;
 
 	if (flags & LOOKUP_RCU)
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index 66ea0cc..02cc613 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -621,9 +621,9 @@ static int orangefs_file_release(struct inode *inode, struct file *file)
 	 * readahead cache (if any); this forces an expensive refresh of
 	 * data for the next caller of mmap (or 'get_block' accesses)
 	 */
-	if (file->f_path.dentry->d_inode &&
-	    file->f_path.dentry->d_inode->i_mapping &&
-	    mapping_nrpages(&file->f_path.dentry->d_inode->i_data)) {
+	if (file_inode(file) &&
+	    file_inode(file)->i_mapping &&
+	    mapping_nrpages(&file_inode(file)->i_data)) {
 		if (orangefs_features & ORANGEFS_FEATURE_READAHEAD) {
 			gossip_debug(GOSSIP_INODE_DEBUG,
 			    "calling flush_racache on %pU\n",
@@ -632,7 +632,7 @@ static int orangefs_file_release(struct inode *inode, struct file *file)
 			gossip_debug(GOSSIP_INODE_DEBUG,
 			    "flush_racache finished\n");
 		}
-		truncate_inode_pages(file->f_path.dentry->d_inode->i_mapping,
+		truncate_inode_pages(file_inode(file)->i_mapping,
 				     0);
 	}
 	return 0;
@@ -648,7 +648,7 @@ static int orangefs_fsync(struct file *file,
 {
 	int ret = -EINVAL;
 	struct orangefs_inode_s *orangefs_inode =
-		ORANGEFS_I(file->f_path.dentry->d_inode);
+		ORANGEFS_I(file_inode(file));
 	struct orangefs_kernel_op_s *new_op = NULL;
 
 	/* required call */
@@ -661,7 +661,7 @@ static int orangefs_fsync(struct file *file,
 
 	ret = service_operation(new_op,
 			"orangefs_fsync",
-			get_interruptible_flag(file->f_path.dentry->d_inode));
+			get_interruptible_flag(file_inode(file)));
 
 	gossip_debug(GOSSIP_FILE_DEBUG,
 		     "orangefs_fsync got return value of %d\n",
@@ -669,7 +669,7 @@ static int orangefs_fsync(struct file *file,
 
 	op_release(new_op);
 
-	orangefs_flush_inode(file->f_path.dentry->d_inode);
+	orangefs_flush_inode(file_inode(file));
 	return ret;
 }
 
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index d15d3d2..a290ff6 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -72,7 +72,7 @@ static int orangefs_create(struct inode *dir,
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
@@ -183,7 +183,7 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 
 	inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
 	if (IS_ERR(inode)) {
@@ -322,7 +322,7 @@ static int orangefs_symlink(struct inode *dir,
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
@@ -386,7 +386,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index eb09aa0..d484068 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -141,6 +141,9 @@ static struct client_debug_mask client_debug_mask;
  */
 static DEFINE_MUTEX(orangefs_debug_lock);
 
+/* Used to protect data in ORANGEFS_KMOD_DEBUG_HELP_FILE */
+static DEFINE_MUTEX(orangefs_help_file_lock);
+
 /*
  * initialize kmod debug operations, create orangefs debugfs dir and
  * ORANGEFS_KMOD_DEBUG_HELP_FILE.
@@ -289,6 +292,8 @@ static void *help_start(struct seq_file *m, loff_t *pos)
 
 	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_start: start\n");
 
+	mutex_lock(&orangefs_help_file_lock);
+
 	if (*pos == 0)
 		payload = m->private;
 
@@ -305,6 +310,7 @@ static void *help_next(struct seq_file *m, void *v, loff_t *pos)
 static void help_stop(struct seq_file *m, void *p)
 {
 	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_stop: start\n");
+	mutex_unlock(&orangefs_help_file_lock);
 }
 
 static int help_show(struct seq_file *m, void *v)
@@ -610,32 +616,54 @@ static int orangefs_prepare_cdm_array(char *debug_array_string)
  * /sys/kernel/debug/orangefs/debug-help can be catted to
  * see all the available kernel and client debug keywords.
  *
- * When the kernel boots, we have no idea what keywords the
+ * When orangefs.ko initializes, we have no idea what keywords the
  * client supports, nor their associated masks.
  *
- * We pass through this function once at boot and stamp a
+ * We pass through this function once at module-load and stamp a
  * boilerplate "we don't know" message for the client in the
  * debug-help file. We pass through here again when the client
  * starts and then we can fill out the debug-help file fully.
  *
  * The client might be restarted any number of times between
- * reboots, we only build the debug-help file the first time.
+ * module reloads, we only build the debug-help file the first time.
  */
 int orangefs_prepare_debugfs_help_string(int at_boot)
 {
-	int rc = -EINVAL;
-	int i;
-	int byte_count = 0;
 	char *client_title = "Client Debug Keywords:\n";
 	char *kernel_title = "Kernel Debug Keywords:\n";
+	size_t string_size =  DEBUG_HELP_STRING_SIZE;
+	size_t result_size;
+	size_t i;
+	char *new;
+	int rc = -EINVAL;
 
 	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
 
-	if (at_boot) {
-		byte_count += strlen(HELP_STRING_UNINITIALIZED);
+	if (at_boot)
 		client_title = HELP_STRING_UNINITIALIZED;
-	} else {
-		/*
+
+	/* build a new debug_help_string. */
+	new = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
+	if (!new) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * strlcat(dst, src, size) will append at most
+	 * "size - strlen(dst) - 1" bytes of src onto dst,
+	 * null terminating the result, and return the total
+	 * length of the string it tried to create.
+	 *
+	 * We'll just plow through here building our new debug
+	 * help string and let strlcat take care of assuring that
+	 * dst doesn't overflow.
+	 */
+	strlcat(new, client_title, string_size);
+
+	if (!at_boot) {
+
+                /*
 		 * fill the client keyword/mask array and remember
 		 * how many elements there were.
 		 */
@@ -644,64 +672,40 @@ int orangefs_prepare_debugfs_help_string(int at_boot)
 		if (cdm_element_count <= 0)
 			goto out;
 
-		/* Count the bytes destined for debug_help_string. */
-		byte_count += strlen(client_title);
-
 		for (i = 0; i < cdm_element_count; i++) {
-			byte_count += strlen(cdm_array[i].keyword + 2);
-			if (byte_count >= DEBUG_HELP_STRING_SIZE) {
-				pr_info("%s: overflow 1!\n", __func__);
-				goto out;
-			}
+			strlcat(new, "\t", string_size);
+			strlcat(new, cdm_array[i].keyword, string_size);
+			strlcat(new, "\n", string_size);
 		}
-
-		gossip_debug(GOSSIP_UTILS_DEBUG,
-			     "%s: cdm_element_count:%d:\n",
-			     __func__,
-			     cdm_element_count);
 	}
 
-	byte_count += strlen(kernel_title);
+	strlcat(new, "\n", string_size);
+	strlcat(new, kernel_title, string_size);
+
 	for (i = 0; i < num_kmod_keyword_mask_map; i++) {
-		byte_count +=
-			strlen(s_kmod_keyword_mask_map[i].keyword + 2);
-		if (byte_count >= DEBUG_HELP_STRING_SIZE) {
-			pr_info("%s: overflow 2!\n", __func__);
-			goto out;
-		}
+		strlcat(new, "\t", string_size);
+		strlcat(new, s_kmod_keyword_mask_map[i].keyword, string_size);
+		result_size = strlcat(new, "\n", string_size);
 	}
 
-	/* build debug_help_string. */
-	debug_help_string = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
-	if (!debug_help_string) {
-		rc = -ENOMEM;
+	/* See if we tried to put too many bytes into "new"... */
+	if (result_size >= string_size) {
+		kfree(new);
 		goto out;
 	}
 
-	strcat(debug_help_string, client_title);
-
-	if (!at_boot) {
-		for (i = 0; i < cdm_element_count; i++) {
-			strcat(debug_help_string, "\t");
-			strcat(debug_help_string, cdm_array[i].keyword);
-			strcat(debug_help_string, "\n");
-		}
-	}
-
-	strcat(debug_help_string, "\n");
-	strcat(debug_help_string, kernel_title);
-
-	for (i = 0; i < num_kmod_keyword_mask_map; i++) {
-		strcat(debug_help_string, "\t");
-		strcat(debug_help_string, s_kmod_keyword_mask_map[i].keyword);
-		strcat(debug_help_string, "\n");
+	if (at_boot) {
+		debug_help_string = new;
+	} else {
+		mutex_lock(&orangefs_help_file_lock);
+		memset(debug_help_string, 0, DEBUG_HELP_STRING_SIZE);
+		strlcat(debug_help_string, new, string_size);
+		mutex_unlock(&orangefs_help_file_lock);
 	}
 
 	rc = 0;
 
-out:
-
-	return rc;
+out:	return rc;
 
 }
 
@@ -959,8 +963,12 @@ int orangefs_debugfs_new_client_string(void __user *arg)
 	ret = copy_from_user(&client_debug_array_string,
                                      (void __user *)arg,
                                      ORANGEFS_MAX_DEBUG_STRING_LEN);
-	if (ret != 0)
+
+	if (ret != 0) {
+		pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
+			__func__);
 		return -EIO;
+	}
 
 	/*
 	 * The real client-core makes an effort to ensure
@@ -975,45 +983,18 @@ int orangefs_debugfs_new_client_string(void __user *arg)
 	client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] =
 		'\0';
 	
-	if (ret != 0) {
-		pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
-			__func__);
-		return -EIO;
-	}
-
 	pr_info("%s: client debug array string has been received.\n",
 		__func__);
 
 	if (!help_string_initialized) {
 
-		/* Free the "we don't know yet" default string... */
-		kfree(debug_help_string);
-
-		/* build a proper debug help string */
+		/* Build a proper debug help string. */
 		if (orangefs_prepare_debugfs_help_string(0)) {
 			gossip_err("%s: no debug help string \n",
 				   __func__);
 			return -EIO;
 		}
 
-		/* Replace the boilerplate boot-time debug-help file. */
-		debugfs_remove(help_file_dentry);
-
-		help_file_dentry =
-			debugfs_create_file(
-				ORANGEFS_KMOD_DEBUG_HELP_FILE,
-				0444,
-				debug_dir,
-				debug_help_string,
-				&debug_help_fops);
-
-		if (!help_file_dentry) {
-			gossip_err("%s: debugfs_create_file failed for"
-				   " :%s:!\n",
-				   __func__,
-				   ORANGEFS_KMOD_DEBUG_HELP_FILE);
-			return -EIO;
-		}
 	}
 
 	debug_mask_to_string(&client_debug_mask, 1);
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 0a82048..3bf803d 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -580,4 +580,11 @@ static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size)
 #endif
 }
 
+static inline void orangefs_set_timeout(struct dentry *dentry)
+{
+	unsigned long time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+
+	dentry->d_fsdata = (void *) time;
+}
+
 #endif /* __ORANGEFSKERNEL_H */
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
index 2e5b030..4113eb0 100644
--- a/fs/orangefs/orangefs-mod.c
+++ b/fs/orangefs/orangefs-mod.c
@@ -124,7 +124,7 @@ static int __init orangefs_init(void)
 	 * unknown at boot time.
 	 *
 	 * orangefs_prepare_debugfs_help_string will be used again
-	 * later to rebuild the debug-help file after the client starts
+	 * later to rebuild the debug-help-string after the client starts
 	 * and passes along the needed info. The argument signifies
 	 * which time orangefs_prepare_debugfs_help_string is being
 	 * called.
@@ -152,7 +152,9 @@ static int __init orangefs_init(void)
 
 	ret = register_filesystem(&orangefs_fs_type);
 	if (ret == 0) {
-		pr_info("orangefs: module version %s loaded\n", ORANGEFS_VERSION);
+		pr_info("%s: module version %s loaded\n",
+			__func__,
+			ORANGEFS_VERSION);
 		ret = 0;
 		goto out;
 	}
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index aeb60f7..36795ee 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -178,6 +178,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 		len -= bytes;
 	}
 
+	if (!error)
+		error = vfs_fsync(new_file, 0);
 	fput(new_file);
 out_fput:
 	fput(old_file);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index c58f01b..7fb53d0 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -270,9 +270,6 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
 	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
 		return NULL;
 
-	if (!realinode->i_op->get_acl)
-		return NULL;
-
 	old_cred = ovl_override_creds(inode->i_sb);
 	acl = get_acl(realinode, type);
 	revert_creds(old_cred);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index bcf3965..edd46a0 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1037,6 +1037,21 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
 
 	posix_acl_release(acl);
 
+	/*
+	 * Check if sgid bit needs to be cleared (actual setacl operation will
+	 * be done with mounter's capabilities and so that won't do it for us).
+	 */
+	if (unlikely(inode->i_mode & S_ISGID) &&
+	    handler->flags == ACL_TYPE_ACCESS &&
+	    !in_group_p(inode->i_gid) &&
+	    !capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
+		struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
+
+		err = ovl_setattr(dentry, &iattr);
+		if (err)
+			return err;
+	}
+
 	err = ovl_xattr_set(dentry, handler->name, value, size, flags);
 	if (!err)
 		ovl_copyattr(ovl_inode_real(inode, NULL), inode);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index adfc5b4..ca651ac 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1012,6 +1012,9 @@ static ssize_t auxv_read(struct file *file, char __user *buf,
 {
 	struct mm_struct *mm = file->private_data;
 	unsigned int nwords = 0;
+
+	if (!mm)
+		return 0;
 	do {
 		nwords += 2;
 	} while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index bd4a5e8..ca16c5d 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -543,6 +543,14 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 
 	if (err != -ENOENT)
 		ubifs_err(c, "cannot find next direntry, error %d", err);
+	else
+		/*
+		 * -ENOENT is a non-fatal error in this context, the TNC uses
+		 * it to indicate that the cursor moved past the current directory
+		 * and readdir() has to stop.
+		 */
+		err = 0;
+
 
 	/* 2 is a special value indicating that there are no more direntries */
 	ctx->pos = 2;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index c27344c..c6eb219 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3974,9 +3974,6 @@ xfs_bmap_remap_alloc(
 	 * allocating, so skip that check by pretending to be freeing.
 	 */
 	error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING);
-	if (error)
-		goto error0;
-error0:
 	xfs_perag_put(args.pag);
 	if (error)
 		trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_);
@@ -3999,6 +3996,39 @@ xfs_bmap_alloc(
 	return xfs_bmap_btalloc(ap);
 }
 
+/* Trim extent to fit a logical block range. */
+void
+xfs_trim_extent(
+	struct xfs_bmbt_irec	*irec,
+	xfs_fileoff_t		bno,
+	xfs_filblks_t		len)
+{
+	xfs_fileoff_t		distance;
+	xfs_fileoff_t		end = bno + len;
+
+	if (irec->br_startoff + irec->br_blockcount <= bno ||
+	    irec->br_startoff >= end) {
+		irec->br_blockcount = 0;
+		return;
+	}
+
+	if (irec->br_startoff < bno) {
+		distance = bno - irec->br_startoff;
+		if (isnullstartblock(irec->br_startblock))
+			irec->br_startblock = DELAYSTARTBLOCK;
+		if (irec->br_startblock != DELAYSTARTBLOCK &&
+		    irec->br_startblock != HOLESTARTBLOCK)
+			irec->br_startblock += distance;
+		irec->br_startoff += distance;
+		irec->br_blockcount -= distance;
+	}
+
+	if (end < irec->br_startoff + irec->br_blockcount) {
+		distance = irec->br_startoff + irec->br_blockcount - end;
+		irec->br_blockcount -= distance;
+	}
+}
+
 /*
  * Trim the returned map to the required bounds
  */
@@ -4829,6 +4859,219 @@ xfs_bmap_split_indlen(
 	return stolen;
 }
 
+int
+xfs_bmap_del_extent_delay(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	xfs_extnum_t		*idx,
+	struct xfs_bmbt_irec	*got,
+	struct xfs_bmbt_irec	*del)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_bmbt_irec	new;
+	int64_t			da_old, da_new, da_diff = 0;
+	xfs_fileoff_t		del_endoff, got_endoff;
+	xfs_filblks_t		got_indlen, new_indlen, stolen;
+	int			error = 0, state = 0;
+	bool			isrt;
+
+	XFS_STATS_INC(mp, xs_del_exlist);
+
+	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	del_endoff = del->br_startoff + del->br_blockcount;
+	got_endoff = got->br_startoff + got->br_blockcount;
+	da_old = startblockval(got->br_startblock);
+	da_new = 0;
+
+	ASSERT(*idx >= 0);
+	ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+	ASSERT(del->br_blockcount > 0);
+	ASSERT(got->br_startoff <= del->br_startoff);
+	ASSERT(got_endoff >= del_endoff);
+
+	if (isrt) {
+		int64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount);
+
+		do_div(rtexts, mp->m_sb.sb_rextsize);
+		xfs_mod_frextents(mp, rtexts);
+	}
+
+	/*
+	 * Update the inode delalloc counter now and wait to update the
+	 * sb counters as we might have to borrow some blocks for the
+	 * indirect block accounting.
+	 */
+	xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del->br_blockcount), 0,
+			isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS);
+	ip->i_delayed_blks -= del->br_blockcount;
+
+	if (whichfork == XFS_COW_FORK)
+		state |= BMAP_COWFORK;
+
+	if (got->br_startoff == del->br_startoff)
+		state |= BMAP_LEFT_CONTIG;
+	if (got_endoff == del_endoff)
+		state |= BMAP_RIGHT_CONTIG;
+
+	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
+	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
+		/*
+		 * Matches the whole extent.  Delete the entry.
+		 */
+		xfs_iext_remove(ip, *idx, 1, state);
+		--*idx;
+		break;
+	case BMAP_LEFT_CONTIG:
+		/*
+		 * Deleting the first part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_startoff = del_endoff;
+		got->br_blockcount -= del->br_blockcount;
+		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip,
+				got->br_blockcount), da_old);
+		got->br_startblock = nullstartblock((int)da_new);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case BMAP_RIGHT_CONTIG:
+		/*
+		 * Deleting the last part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount = got->br_blockcount - del->br_blockcount;
+		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip,
+				got->br_blockcount), da_old);
+		got->br_startblock = nullstartblock((int)da_new);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case 0:
+		/*
+		 * Deleting the middle of the extent.
+		 *
+		 * Distribute the original indlen reservation across the two new
+		 * extents.  Steal blocks from the deleted extent if necessary.
+		 * Stealing blocks simply fudges the fdblocks accounting below.
+		 * Warn if either of the new indlen reservations is zero as this
+		 * can lead to delalloc problems.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+
+		got->br_blockcount = del->br_startoff - got->br_startoff;
+		got_indlen = xfs_bmap_worst_indlen(ip, got->br_blockcount);
+
+		new.br_blockcount = got_endoff - del_endoff;
+		new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount);
+
+		WARN_ON_ONCE(!got_indlen || !new_indlen);
+		stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen,
+						       del->br_blockcount);
+
+		got->br_startblock = nullstartblock((int)got_indlen);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_);
+
+		new.br_startoff = del_endoff;
+		new.br_state = got->br_state;
+		new.br_startblock = nullstartblock((int)new_indlen);
+
+		++*idx;
+		xfs_iext_insert(ip, *idx, 1, &new, state);
+
+		da_new = got_indlen + new_indlen - stolen;
+		del->br_blockcount -= stolen;
+		break;
+	}
+
+	ASSERT(da_old >= da_new);
+	da_diff = da_old - da_new;
+	if (!isrt)
+		da_diff += del->br_blockcount;
+	if (da_diff)
+		xfs_mod_fdblocks(mp, da_diff, false);
+	return error;
+}
+
+void
+xfs_bmap_del_extent_cow(
+	struct xfs_inode	*ip,
+	xfs_extnum_t		*idx,
+	struct xfs_bmbt_irec	*got,
+	struct xfs_bmbt_irec	*del)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec	new;
+	xfs_fileoff_t		del_endoff, got_endoff;
+	int			state = BMAP_COWFORK;
+
+	XFS_STATS_INC(mp, xs_del_exlist);
+
+	del_endoff = del->br_startoff + del->br_blockcount;
+	got_endoff = got->br_startoff + got->br_blockcount;
+
+	ASSERT(*idx >= 0);
+	ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+	ASSERT(del->br_blockcount > 0);
+	ASSERT(got->br_startoff <= del->br_startoff);
+	ASSERT(got_endoff >= del_endoff);
+	ASSERT(!isnullstartblock(got->br_startblock));
+
+	if (got->br_startoff == del->br_startoff)
+		state |= BMAP_LEFT_CONTIG;
+	if (got_endoff == del_endoff)
+		state |= BMAP_RIGHT_CONTIG;
+
+	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
+	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
+		/*
+		 * Matches the whole extent.  Delete the entry.
+		 */
+		xfs_iext_remove(ip, *idx, 1, state);
+		--*idx;
+		break;
+	case BMAP_LEFT_CONTIG:
+		/*
+		 * Deleting the first part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_startoff = del_endoff;
+		got->br_blockcount -= del->br_blockcount;
+		got->br_startblock = del->br_startblock + del->br_blockcount;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case BMAP_RIGHT_CONTIG:
+		/*
+		 * Deleting the last part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount -= del->br_blockcount;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case 0:
+		/*
+		 * Deleting the middle of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount = del->br_startoff - got->br_startoff;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+
+		new.br_startoff = del_endoff;
+		new.br_blockcount = got_endoff - del_endoff;
+		new.br_state = got->br_state;
+		new.br_startblock = del->br_startblock + del->br_blockcount;
+
+		++*idx;
+		xfs_iext_insert(ip, *idx, 1, &new, state);
+		break;
+	}
+}
+
 /*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space (or undoing a delayed allocation).
@@ -5171,175 +5414,6 @@ xfs_bmap_del_extent(
 	return error;
 }
 
-/* Remove an extent from the CoW fork.  Similar to xfs_bmap_del_extent. */
-int
-xfs_bunmapi_cow(
-	struct xfs_inode		*ip,
-	struct xfs_bmbt_irec		*del)
-{
-	xfs_filblks_t			da_new;
-	xfs_filblks_t			da_old;
-	xfs_fsblock_t			del_endblock = 0;
-	xfs_fileoff_t			del_endoff;
-	int				delay;
-	struct xfs_bmbt_rec_host	*ep;
-	int				error;
-	struct xfs_bmbt_irec		got;
-	xfs_fileoff_t			got_endoff;
-	struct xfs_ifork		*ifp;
-	struct xfs_mount		*mp;
-	xfs_filblks_t			nblks;
-	struct xfs_bmbt_irec		new;
-	/* REFERENCED */
-	uint				qfield;
-	xfs_filblks_t			temp;
-	xfs_filblks_t			temp2;
-	int				state = BMAP_COWFORK;
-	int				eof;
-	xfs_extnum_t			eidx;
-
-	mp = ip->i_mount;
-	XFS_STATS_INC(mp, xs_del_exlist);
-
-	ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof,
-			&eidx, &got, &new);
-
-	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp;
-	ASSERT((eidx >= 0) && (eidx < ifp->if_bytes /
-		(uint)sizeof(xfs_bmbt_rec_t)));
-	ASSERT(del->br_blockcount > 0);
-	ASSERT(got.br_startoff <= del->br_startoff);
-	del_endoff = del->br_startoff + del->br_blockcount;
-	got_endoff = got.br_startoff + got.br_blockcount;
-	ASSERT(got_endoff >= del_endoff);
-	delay = isnullstartblock(got.br_startblock);
-	ASSERT(isnullstartblock(del->br_startblock) == delay);
-	qfield = 0;
-	error = 0;
-	/*
-	 * If deleting a real allocation, must free up the disk space.
-	 */
-	if (!delay) {
-		nblks = del->br_blockcount;
-		qfield = XFS_TRANS_DQ_BCOUNT;
-		/*
-		 * Set up del_endblock and cur for later.
-		 */
-		del_endblock = del->br_startblock + del->br_blockcount;
-		da_old = da_new = 0;
-	} else {
-		da_old = startblockval(got.br_startblock);
-		da_new = 0;
-		nblks = 0;
-	}
-	qfield = qfield;
-	nblks = nblks;
-
-	/*
-	 * Set flag value to use in switch statement.
-	 * Left-contig is 2, right-contig is 1.
-	 */
-	switch (((got.br_startoff == del->br_startoff) << 1) |
-		(got_endoff == del_endoff)) {
-	case 3:
-		/*
-		 * Matches the whole extent.  Delete the entry.
-		 */
-		xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK);
-		--eidx;
-		break;
-
-	case 2:
-		/*
-		 * Deleting the first part of the extent.
-		 */
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_startoff(ep, del_endoff);
-		temp = got.br_blockcount - del->br_blockcount;
-		xfs_bmbt_set_blockcount(ep, temp);
-		if (delay) {
-			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-				da_old);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-			da_new = temp;
-			break;
-		}
-		xfs_bmbt_set_startblock(ep, del_endblock);
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		break;
-
-	case 1:
-		/*
-		 * Deleting the last part of the extent.
-		 */
-		temp = got.br_blockcount - del->br_blockcount;
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(ep, temp);
-		if (delay) {
-			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-				da_old);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-			da_new = temp;
-			break;
-		}
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		break;
-
-	case 0:
-		/*
-		 * Deleting the middle of the extent.
-		 */
-		temp = del->br_startoff - got.br_startoff;
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(ep, temp);
-		new.br_startoff = del_endoff;
-		temp2 = got_endoff - del_endoff;
-		new.br_blockcount = temp2;
-		new.br_state = got.br_state;
-		if (!delay) {
-			new.br_startblock = del_endblock;
-		} else {
-			temp = xfs_bmap_worst_indlen(ip, temp);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			temp2 = xfs_bmap_worst_indlen(ip, temp2);
-			new.br_startblock = nullstartblock((int)temp2);
-			da_new = temp + temp2;
-			while (da_new > da_old) {
-				if (temp) {
-					temp--;
-					da_new--;
-					xfs_bmbt_set_startblock(ep,
-						nullstartblock((int)temp));
-				}
-				if (da_new == da_old)
-					break;
-				if (temp2) {
-					temp2--;
-					da_new--;
-					new.br_startblock =
-						nullstartblock((int)temp2);
-				}
-			}
-		}
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		xfs_iext_insert(ip, eidx + 1, 1, &new, state);
-		++eidx;
-		break;
-	}
-
-	/*
-	 * Account for change in delayed indirect blocks.
-	 * Nothing to do for disk quota accounting here.
-	 */
-	ASSERT(da_old >= da_new);
-	if (da_old > da_new)
-		xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false);
-
-	return error;
-}
-
 /*
  * Unmap (remove) blocks from a file.
  * If nexts is nonzero then the number of extents to remove is limited to
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index f97db71..7cae6ec 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -190,6 +190,8 @@ void	xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
 #define	XFS_BMAP_TRACE_EXLIST(ip,c,w)
 #endif
 
+void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
+		xfs_filblks_t len);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
@@ -221,7 +223,11 @@ int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
 		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
 		struct xfs_defer_ops *dfops, int *done);
-int	xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del);
+int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
+		xfs_extnum_t *idx, struct xfs_bmbt_irec *got,
+		struct xfs_bmbt_irec *del);
+void	xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx,
+		struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del);
 int	xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
 		xfs_extnum_t num);
 uint	xfs_default_attroffset(struct xfs_inode *ip);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 5c8e6f2..0e80993 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4826,7 +4826,7 @@ xfs_btree_calc_size(
 	return rval;
 }
 
-int
+static int
 xfs_btree_count_blocks_helper(
 	struct xfs_btree_cur	*cur,
 	int			level,
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 3cc3cf7..ac9a003 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc(
 	if (mp->m_quotainfo)
 		ndquots = mp->m_quotainfo->qi_dqperchunk;
 	else
-		ndquots = xfs_calc_dquots_per_chunk(
-					XFS_BB_TO_FSB(mp, bp->b_length));
+		ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
 
 	for (i = 0; i < ndquots; i++, d++) {
 		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index f6547fc..6b7579e 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -865,7 +865,6 @@ typedef struct xfs_timestamp {
  * padding field for v3 inodes.
  */
 #define	XFS_DINODE_MAGIC		0x494e	/* 'IN' */
-#define XFS_DINODE_GOOD_VERSION(v)	((v) >= 1 && (v) <= 3)
 typedef struct xfs_dinode {
 	__be16		di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
 	__be16		di_mode;	/* mode and type of file */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 8de9a3a..134424f 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -57,6 +57,17 @@ xfs_inobp_check(
 }
 #endif
 
+bool
+xfs_dinode_good_version(
+	struct xfs_mount *mp,
+	__u8		version)
+{
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return version == 3;
+
+	return version == 1 || version == 2;
+}
+
 /*
  * If we are doing readahead on an inode buffer, we might be in log recovery
  * reading an inode allocation buffer that hasn't yet been replayed, and hence
@@ -91,7 +102,7 @@ xfs_inode_buf_verify(
 
 		dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
 		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
-			    XFS_DINODE_GOOD_VERSION(dip->di_version);
+			xfs_dinode_good_version(mp, dip->di_version);
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
 						XFS_ERRTAG_ITOBP_INOTOBP,
 						XFS_RANDOM_ITOBP_INOTOBP))) {
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 62d9d46..3cfe12a 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -74,6 +74,8 @@ void	xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
 void	xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
 			       struct xfs_dinode *to);
 
+bool	xfs_dinode_good_version(struct xfs_mount *mp, __u8 version);
+
 #if defined(DEBUG)
 void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #else
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a314fc7..6e4f7f9 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -249,6 +249,7 @@ xfs_file_dio_aio_read(
 	struct xfs_inode	*ip = XFS_I(inode);
 	loff_t			isize = i_size_read(inode);
 	size_t			count = iov_iter_count(to);
+	loff_t			end = iocb->ki_pos + count - 1;
 	struct iov_iter		data;
 	struct xfs_buftarg	*target;
 	ssize_t			ret = 0;
@@ -272,49 +273,21 @@ xfs_file_dio_aio_read(
 
 	file_accessed(iocb->ki_filp);
 
-	/*
-	 * Locking is a bit tricky here. If we take an exclusive lock for direct
-	 * IO, we effectively serialise all new concurrent read IO to this file
-	 * and block it behind IO that is currently in progress because IO in
-	 * progress holds the IO lock shared. We only need to hold the lock
-	 * exclusive to blow away the page cache, so only take lock exclusively
-	 * if the page cache needs invalidation. This allows the normal direct
-	 * IO case of no page cache pages to proceeed concurrently without
-	 * serialisation.
-	 */
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
 	if (mapping->nrpages) {
-		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
-		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+		if (ret)
+			goto out_unlock;
 
 		/*
-		 * The generic dio code only flushes the range of the particular
-		 * I/O. Because we take an exclusive lock here, this whole
-		 * sequence is considerably more expensive for us. This has a
-		 * noticeable performance impact for any file with cached pages,
-		 * even when outside of the range of the particular I/O.
-		 *
-		 * Hence, amortize the cost of the lock against a full file
-		 * flush and reduce the chances of repeated iolock cycles going
-		 * forward.
+		 * Invalidate whole pages. This can return an error if we fail
+		 * to invalidate a page, but this should never happen on XFS.
+		 * Warn if it does fail.
 		 */
-		if (mapping->nrpages) {
-			ret = filemap_write_and_wait(mapping);
-			if (ret) {
-				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
-				return ret;
-			}
-
-			/*
-			 * Invalidate whole pages. This can return an error if
-			 * we fail to invalidate a page, but this should never
-			 * happen on XFS. Warn if it does fail.
-			 */
-			ret = invalidate_inode_pages2(mapping);
-			WARN_ON_ONCE(ret);
-			ret = 0;
-		}
-		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+		ret = invalidate_inode_pages2_range(mapping,
+				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+		WARN_ON_ONCE(ret);
+		ret = 0;
 	}
 
 	data = *to;
@@ -324,8 +297,9 @@ xfs_file_dio_aio_read(
 		iocb->ki_pos += ret;
 		iov_iter_advance(to, ret);
 	}
-	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 
+out_unlock:
+	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
 
@@ -570,61 +544,49 @@ xfs_file_dio_aio_write(
 	if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
 		return -EINVAL;
 
-	/* "unaligned" here means not aligned to a filesystem block */
+	/*
+	 * Don't take the exclusive iolock here unless the I/O is unaligned to
+	 * the file system block size.  We don't need to consider the EOF
+	 * extension case here because xfs_file_aio_write_checks() will relock
+	 * the inode as necessary for EOF zeroing cases and fill out the new
+	 * inode size as appropriate.
+	 */
 	if ((iocb->ki_pos & mp->m_blockmask) ||
-	    ((iocb->ki_pos + count) & mp->m_blockmask))
+	    ((iocb->ki_pos + count) & mp->m_blockmask)) {
 		unaligned_io = 1;
-
-	/*
-	 * We don't need to take an exclusive lock unless there page cache needs
-	 * to be invalidated or unaligned IO is being executed. We don't need to
-	 * consider the EOF extension case here because
-	 * xfs_file_aio_write_checks() will relock the inode as necessary for
-	 * EOF zeroing cases and fill out the new inode size as appropriate.
-	 */
-	if (unaligned_io || mapping->nrpages)
 		iolock = XFS_IOLOCK_EXCL;
-	else
+	} else {
 		iolock = XFS_IOLOCK_SHARED;
-	xfs_rw_ilock(ip, iolock);
-
-	/*
-	 * Recheck if there are cached pages that need invalidate after we got
-	 * the iolock to protect against other threads adding new pages while
-	 * we were waiting for the iolock.
-	 */
-	if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
-		xfs_rw_iunlock(ip, iolock);
-		iolock = XFS_IOLOCK_EXCL;
-		xfs_rw_ilock(ip, iolock);
 	}
 
+	xfs_rw_ilock(ip, iolock);
+
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
 	count = iov_iter_count(from);
 	end = iocb->ki_pos + count - 1;
 
-	/*
-	 * See xfs_file_dio_aio_read() for why we do a full-file flush here.
-	 */
 	if (mapping->nrpages) {
-		ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
 		if (ret)
 			goto out;
+
 		/*
 		 * Invalidate whole pages. This can return an error if we fail
 		 * to invalidate a page, but this should never happen on XFS.
 		 * Warn if it does fail.
 		 */
-		ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
+		ret = invalidate_inode_pages2_range(mapping,
+				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
 
 	/*
 	 * If we are doing unaligned IO, wait for all other IO to drain,
-	 * otherwise demote the lock if we had to flush cached pages
+	 * otherwise demote the lock if we had to take the exclusive lock
+	 * for other reasons in xfs_file_aio_write_checks.
 	 */
 	if (unaligned_io)
 		inode_dio_wait(inode);
@@ -947,134 +909,6 @@ xfs_file_fallocate(
 	return error;
 }
 
-/*
- * Flush all file writes out to disk.
- */
-static int
-xfs_file_wait_for_io(
-	struct inode	*inode,
-	loff_t		offset,
-	size_t		len)
-{
-	loff_t		rounding;
-	loff_t		ioffset;
-	loff_t		iendoffset;
-	loff_t		bs;
-	int		ret;
-
-	bs = inode->i_sb->s_blocksize;
-	inode_dio_wait(inode);
-
-	rounding = max_t(xfs_off_t, bs, PAGE_SIZE);
-	ioffset = round_down(offset, rounding);
-	iendoffset = round_up(offset + len, rounding) - 1;
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-					   iendoffset);
-	return ret;
-}
-
-/* Hook up to the VFS reflink function */
-STATIC int
-xfs_file_share_range(
-	struct file	*file_in,
-	loff_t		pos_in,
-	struct file	*file_out,
-	loff_t		pos_out,
-	u64		len,
-	bool		is_dedupe)
-{
-	struct inode	*inode_in;
-	struct inode	*inode_out;
-	ssize_t		ret;
-	loff_t		bs;
-	loff_t		isize;
-	int		same_inode;
-	loff_t		blen;
-	unsigned int	flags = 0;
-
-	inode_in = file_inode(file_in);
-	inode_out = file_inode(file_out);
-	bs = inode_out->i_sb->s_blocksize;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-	if (IS_SWAPFILE(inode_in) ||
-	    IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Reflink only works within this filesystem. */
-	if (inode_in->i_sb != inode_out->i_sb)
-		return -EXDEV;
-	same_inode = (inode_in->i_ino == inode_out->i_ino);
-
-	/* Don't reflink dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
-		return -EINVAL;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	/* Don't share DAX file data for now. */
-	if (IS_DAX(inode_in) || IS_DAX(inode_out))
-		return -EINVAL;
-
-	/* Are we going all the way to the end? */
-	isize = i_size_read(inode_in);
-	if (isize == 0)
-		return 0;
-	if (len == 0)
-		len = isize - pos_in;
-
-	/* Ensure offsets don't wrap and the input is inside i_size */
-	if (pos_in + len < pos_in || pos_out + len < pos_out ||
-	    pos_in + len > isize)
-		return -EINVAL;
-
-	/* Don't allow dedupe past EOF in the dest file */
-	if (is_dedupe) {
-		loff_t	disize;
-
-		disize = i_size_read(inode_out);
-		if (pos_out >= disize || pos_out + len > disize)
-			return -EINVAL;
-	}
-
-	/* If we're linking to EOF, continue to the block boundary. */
-	if (pos_in + len == isize)
-		blen = ALIGN(isize, bs) - pos_in;
-	else
-		blen = len;
-
-	/* Only reflink if we're aligned to block boundaries */
-	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
-	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
-		return -EINVAL;
-
-	/* Don't allow overlapped reflink within the same file */
-	if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen)
-		return -EINVAL;
-
-	/* Wait for the completion of any pending IOs on srcfile */
-	ret = xfs_file_wait_for_io(inode_in, pos_in, len);
-	if (ret)
-		goto out;
-	ret = xfs_file_wait_for_io(inode_out, pos_out, len);
-	if (ret)
-		goto out;
-
-	if (is_dedupe)
-		flags |= XFS_REFLINK_DEDUPE;
-	ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out),
-			pos_out, len, flags);
-	if (ret < 0)
-		goto out;
-
-out:
-	return ret;
-}
-
 STATIC ssize_t
 xfs_file_copy_range(
 	struct file	*file_in,
@@ -1086,7 +920,7 @@ xfs_file_copy_range(
 {
 	int		error;
 
-	error = xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 	if (error)
 		return error;
@@ -1101,7 +935,7 @@ xfs_file_clone_range(
 	loff_t		pos_out,
 	u64		len)
 {
-	return xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 }
 
@@ -1124,7 +958,7 @@ xfs_file_dedupe_range(
 	if (len > XFS_MAX_DEDUPE_LEN)
 		len = XFS_MAX_DEDUPE_LEN;
 
-	error = xfs_file_share_range(src_file, loff, dst_file, dst_loff,
+	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
 				     len, true);
 	if (error)
 		return error;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 14796b7..f295049 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1656,9 +1656,9 @@ void
 xfs_inode_set_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
-	trace_xfs_inode_set_eofblocks_tag(ip);
+	trace_xfs_inode_set_cowblocks_tag(ip);
 	return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks,
-			trace_xfs_perag_set_eofblocks,
+			trace_xfs_perag_set_cowblocks,
 			XFS_ICI_COWBLOCKS_TAG);
 }
 
@@ -1666,7 +1666,7 @@ void
 xfs_inode_clear_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
-	trace_xfs_inode_clear_eofblocks_tag(ip);
+	trace_xfs_inode_clear_cowblocks_tag(ip);
 	return __xfs_inode_clear_eofblocks_tag(ip,
-			trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG);
+			trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
 }
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d907eb9..436e109 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -566,6 +566,17 @@ xfs_file_iomap_begin_delay(
 	xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx,
 			&got, &prev);
 	if (!eof && got.br_startoff <= offset_fsb) {
+		if (xfs_is_reflink_inode(ip)) {
+			bool		shared;
+
+			end_fsb = min(XFS_B_TO_FSB(mp, offset + count),
+					maxbytes_fsb);
+			xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb);
+			error = xfs_reflink_reserve_cow(ip, &got, &shared);
+			if (error)
+				goto out_unlock;
+		}
+
 		trace_xfs_iomap_found(ip, offset, count, 0, &got);
 		goto done;
 	}
@@ -961,19 +972,13 @@ xfs_file_iomap_begin(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_bmbt_irec	imap;
 	xfs_fileoff_t		offset_fsb, end_fsb;
-	bool			shared, trimmed;
 	int			nimaps = 1, error = 0;
+	bool			shared = false, trimmed = false;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_reserve_cow_range(ip, offset, length);
-		if (error < 0)
-			return error;
-	}
-
 	if ((flags & IOMAP_WRITE) && !IS_DAX(inode) &&
 		   !xfs_get_extsz_hint(ip)) {
 		/* Reserve delalloc blocks for regular writeback. */
@@ -981,7 +986,16 @@ xfs_file_iomap_begin(
 				iomap);
 	}
 
-	lockmode = xfs_ilock_data_map_shared(ip);
+	/*
+	 * COW writes will allocate delalloc space, so we need to make sure
+	 * to take the lock exclusively here.
+	 */
+	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+		lockmode = XFS_ILOCK_EXCL;
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+	} else {
+		lockmode = xfs_ilock_data_map_shared(ip);
+	}
 
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
@@ -991,16 +1005,24 @@ xfs_file_iomap_begin(
 
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
 			       &nimaps, 0);
-	if (error) {
-		xfs_iunlock(ip, lockmode);
-		return error;
+	if (error)
+		goto out_unlock;
+
+	if (flags & IOMAP_REPORT) {
+		/* Trim the mapping to the nearest shared extent boundary. */
+		error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
+				&trimmed);
+		if (error)
+			goto out_unlock;
 	}
 
-	/* Trim the mapping to the nearest shared extent boundary. */
-	error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
-	if (error) {
-		xfs_iunlock(ip, lockmode);
-		return error;
+	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+		error = xfs_reflink_reserve_cow(ip, &imap, &shared);
+		if (error)
+			goto out_unlock;
+
+		end_fsb = imap.br_startoff + imap.br_blockcount;
+		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
 	}
 
 	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
@@ -1039,6 +1061,9 @@ xfs_file_iomap_begin(
 	if (shared)
 		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
+out_unlock:
+	xfs_iunlock(ip, lockmode);
+	return error;
 }
 
 static int
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index fc78739..b341f10 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1009,6 +1009,7 @@ xfs_mountfs(
  out_quota:
 	xfs_qm_unmount_quotas(mp);
  out_rtunmount:
+	mp->m_super->s_flags &= ~MS_ACTIVE;
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
 	IRELE(rip);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 5965e94..a279b4e 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -182,7 +182,8 @@ xfs_reflink_trim_around_shared(
 	if (!xfs_is_reflink_inode(ip) ||
 	    ISUNWRITTEN(irec) ||
 	    irec->br_startblock == HOLESTARTBLOCK ||
-	    irec->br_startblock == DELAYSTARTBLOCK) {
+	    irec->br_startblock == DELAYSTARTBLOCK ||
+	    isnullstartblock(irec->br_startblock)) {
 		*shared = false;
 		return 0;
 	}
@@ -227,50 +228,54 @@ xfs_reflink_trim_around_shared(
 	}
 }
 
-/* Create a CoW reservation for a range of blocks within a file. */
-static int
-__xfs_reflink_reserve_cow(
+/*
+ * Trim the passed in imap to the next shared/unshared extent boundary, and
+ * if imap->br_startoff points to a shared extent reserve space for it in the
+ * COW fork.  In this case *shared is set to true, else to false.
+ *
+ * Note that imap will always contain the block numbers for the existing blocks
+ * in the data fork, as the upper layers need them for read-modify-write
+ * operations.
+ */
+int
+xfs_reflink_reserve_cow(
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		*offset_fsb,
-	xfs_fileoff_t		end_fsb,
-	bool			*skipped)
+	struct xfs_bmbt_irec	*imap,
+	bool			*shared)
 {
-	struct xfs_bmbt_irec	got, prev, imap;
-	xfs_fileoff_t		orig_end_fsb;
-	int			nimaps, eof = 0, error = 0;
-	bool			shared = false, trimmed = false;
+	struct xfs_bmbt_irec	got, prev;
+	xfs_fileoff_t		end_fsb, orig_end_fsb;
+	int			eof = 0, error = 0;
+	bool			trimmed;
 	xfs_extnum_t		idx;
 	xfs_extlen_t		align;
 
-	/* Already reserved?  Skip the refcount btree access. */
-	xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx,
+	/*
+	 * Search the COW fork extent list first.  This serves two purposes:
+	 * first this implement the speculative preallocation using cowextisze,
+	 * so that we also unshared block adjacent to shared blocks instead
+	 * of just the shared blocks themselves.  Second the lookup in the
+	 * extent list is generally faster than going out to the shared extent
+	 * tree.
+	 */
+	xfs_bmap_search_extents(ip, imap->br_startoff, XFS_COW_FORK, &eof, &idx,
 			&got, &prev);
-	if (!eof && got.br_startoff <= *offset_fsb) {
-		end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount;
-		trace_xfs_reflink_cow_found(ip, &got);
-		goto done;
-	}
+	if (!eof && got.br_startoff <= imap->br_startoff) {
+		trace_xfs_reflink_cow_found(ip, imap);
+		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
 
-	/* Read extent from the source file. */
-	nimaps = 1;
-	error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
-			&imap, &nimaps, 0);
-	if (error)
-		goto out_unlock;
-	ASSERT(nimaps == 1);
+		*shared = true;
+		return 0;
+	}
 
 	/* Trim the mapping to the nearest shared extent boundary. */
-	error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
+	error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
 	if (error)
-		goto out_unlock;
-
-	end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount;
+		return error;
 
 	/* Not shared?  Just report the (potentially capped) extent. */
-	if (!shared) {
-		*skipped = true;
-		goto done;
-	}
+	if (!*shared)
+		return 0;
 
 	/*
 	 * Fork all the shared blocks from our write offset until the end of
@@ -278,72 +283,38 @@ __xfs_reflink_reserve_cow(
 	 */
 	error = xfs_qm_dqattach_locked(ip, 0);
 	if (error)
-		goto out_unlock;
+		return error;
+
+	end_fsb = orig_end_fsb = imap->br_startoff + imap->br_blockcount;
 
 	align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip));
 	if (align)
 		end_fsb = roundup_64(end_fsb, align);
 
 retry:
-	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb,
-			end_fsb - *offset_fsb, &got,
-			&prev, &idx, eof);
+	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff,
+			end_fsb - imap->br_startoff, &got, &prev, &idx, eof);
 	switch (error) {
 	case 0:
 		break;
 	case -ENOSPC:
 	case -EDQUOT:
 		/* retry without any preallocation */
-		trace_xfs_reflink_cow_enospc(ip, &imap);
+		trace_xfs_reflink_cow_enospc(ip, imap);
 		if (end_fsb != orig_end_fsb) {
 			end_fsb = orig_end_fsb;
 			goto retry;
 		}
 		/*FALLTHRU*/
 	default:
-		goto out_unlock;
+		return error;
 	}
 
 	if (end_fsb != orig_end_fsb)
 		xfs_inode_set_cowblocks_tag(ip);
 
 	trace_xfs_reflink_cow_alloc(ip, &got);
-done:
-	*offset_fsb = end_fsb;
-out_unlock:
-	return error;
-}
-
-/* Create a CoW reservation for part of a file. */
-int
-xfs_reflink_reserve_cow_range(
-	struct xfs_inode	*ip,
-	xfs_off_t		offset,
-	xfs_off_t		count)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb, end_fsb;
-	bool			skipped = false;
-	int			error;
-
-	trace_xfs_reflink_reserve_cow_range(ip, offset, count);
-
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	end_fsb = XFS_B_TO_FSB(mp, offset + count);
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	while (offset_fsb < end_fsb) {
-		error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb,
-				&skipped);
-		if (error) {
-			trace_xfs_reflink_reserve_cow_range_error(ip, error,
-				_RET_IP_);
-			break;
-		}
-	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-	return error;
+	return 0;
 }
 
 /* Allocate all CoW reservations covering a range of blocks in a file. */
@@ -358,9 +329,8 @@ __xfs_reflink_allocate_cow(
 	struct xfs_defer_ops	dfops;
 	struct xfs_trans	*tp;
 	xfs_fsblock_t		first_block;
-	xfs_fileoff_t		next_fsb;
 	int			nimaps = 1, error;
-	bool			skipped = false;
+	bool			shared;
 
 	xfs_defer_init(&dfops, &first_block);
 
@@ -371,33 +341,38 @@ __xfs_reflink_allocate_cow(
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
-	next_fsb = *offset_fsb;
-	error = __xfs_reflink_reserve_cow(ip, &next_fsb, end_fsb, &skipped);
+	/* Read extent from the source file. */
+	nimaps = 1;
+	error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
+			&imap, &nimaps, 0);
+	if (error)
+		goto out_unlock;
+	ASSERT(nimaps == 1);
+
+	error = xfs_reflink_reserve_cow(ip, &imap, &shared);
 	if (error)
 		goto out_trans_cancel;
 
-	if (skipped) {
-		*offset_fsb = next_fsb;
+	if (!shared) {
+		*offset_fsb = imap.br_startoff + imap.br_blockcount;
 		goto out_trans_cancel;
 	}
 
 	xfs_trans_ijoin(tp, ip, 0);
-	error = xfs_bmapi_write(tp, ip, *offset_fsb, next_fsb - *offset_fsb,
+	error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount,
 			XFS_BMAPI_COWFORK, &first_block,
 			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK),
 			&imap, &nimaps, &dfops);
 	if (error)
 		goto out_trans_cancel;
 
-	/* We might not have been able to map the whole delalloc extent */
-	*offset_fsb = min(*offset_fsb + imap.br_blockcount, next_fsb);
-
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
 		goto out_trans_cancel;
 
 	error = xfs_trans_commit(tp);
 
+	*offset_fsb = imap.br_startoff + imap.br_blockcount;
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -536,58 +511,49 @@ xfs_reflink_cancel_cow_blocks(
 	xfs_fileoff_t			offset_fsb,
 	xfs_fileoff_t			end_fsb)
 {
-	struct xfs_bmbt_irec		irec;
-	xfs_filblks_t			count_fsb;
+	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec		got, prev, del;
+	xfs_extnum_t			idx;
 	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
-	int				error = 0;
-	int				nimaps;
+	int				error = 0, eof = 0;
 
 	if (!xfs_is_reflink_inode(ip))
 		return 0;
 
-	/* Go find the old extent in the CoW fork. */
-	while (offset_fsb < end_fsb) {
-		nimaps = 1;
-		count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
-		error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
-				&nimaps, XFS_BMAPI_COWFORK);
-		if (error)
-			break;
-		ASSERT(nimaps == 1);
+	xfs_bmap_search_extents(ip, offset_fsb, XFS_COW_FORK, &eof, &idx,
+			&got, &prev);
+	if (eof)
+		return 0;
 
-		trace_xfs_reflink_cancel_cow(ip, &irec);
+	while (got.br_startoff < end_fsb) {
+		del = got;
+		xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
+		trace_xfs_reflink_cancel_cow(ip, &del);
 
-		if (irec.br_startblock == DELAYSTARTBLOCK) {
-			/* Free a delayed allocation. */
-			xfs_mod_fdblocks(ip->i_mount, irec.br_blockcount,
-					false);
-			ip->i_delayed_blks -= irec.br_blockcount;
-
-			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &irec);
+		if (isnullstartblock(del.br_startblock)) {
+			error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
+					&idx, &got, &del);
 			if (error)
 				break;
-		} else if (irec.br_startblock == HOLESTARTBLOCK) {
-			/* empty */
 		} else {
 			xfs_trans_ijoin(*tpp, ip, 0);
 			xfs_defer_init(&dfops, &firstfsb);
 
 			/* Free the CoW orphan record. */
 			error = xfs_refcount_free_cow_extent(ip->i_mount,
-					&dfops, irec.br_startblock,
-					irec.br_blockcount);
+					&dfops, del.br_startblock,
+					del.br_blockcount);
 			if (error)
 				break;
 
 			xfs_bmap_add_free(ip->i_mount, &dfops,
-					irec.br_startblock, irec.br_blockcount,
+					del.br_startblock, del.br_blockcount,
 					NULL);
 
 			/* Update quota accounting */
 			xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
-					-(long)irec.br_blockcount);
+					-(long)del.br_blockcount);
 
 			/* Roll the transaction */
 			error = xfs_defer_finish(tpp, &dfops, ip);
@@ -597,15 +563,18 @@ xfs_reflink_cancel_cow_blocks(
 			}
 
 			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &irec);
-			if (error)
-				break;
+			xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
 		}
 
-		/* Roll on... */
-		offset_fsb = irec.br_startoff + irec.br_blockcount;
+		if (++idx >= ifp->if_bytes / sizeof(struct xfs_bmbt_rec))
+			break;
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got);
 	}
 
+	/* clear tag if cow fork is emptied */
+	if (!ifp->if_bytes)
+		xfs_inode_clear_cowblocks_tag(ip);
+
 	return error;
 }
 
@@ -668,25 +637,26 @@ xfs_reflink_end_cow(
 	xfs_off_t			offset,
 	xfs_off_t			count)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_bmbt_irec		uirec;
+	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec		got, prev, del;
 	struct xfs_trans		*tp;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
-	xfs_filblks_t			count_fsb;
 	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
-	int				error;
+	int				error, eof = 0;
 	unsigned int			resblks;
-	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
-	int				nimaps;
+	xfs_extnum_t			idx;
 
 	trace_xfs_reflink_end_cow(ip, offset, count);
 
+	/* No COW extents?  That's easy! */
+	if (ifp->if_bytes == 0)
+		return 0;
+
 	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
 	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
-	count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
 
 	/* Start a rolling transaction to switch the mappings */
 	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
@@ -698,72 +668,65 @@ xfs_reflink_end_cow(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	/* Go find the old extent in the CoW fork. */
-	while (offset_fsb < end_fsb) {
-		/* Read extent from the source file */
-		nimaps = 1;
-		count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
-		error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
-				&nimaps, XFS_BMAPI_COWFORK);
-		if (error)
-			goto out_cancel;
-		ASSERT(nimaps == 1);
+	xfs_bmap_search_extents(ip, end_fsb - 1, XFS_COW_FORK, &eof, &idx,
+			&got, &prev);
 
-		ASSERT(irec.br_startblock != DELAYSTARTBLOCK);
-		trace_xfs_reflink_cow_remap(ip, &irec);
+	/* If there is a hole at end_fsb - 1 go to the previous extent */
+	if (eof || got.br_startoff > end_fsb) {
+		ASSERT(idx > 0);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got);
+	}
 
-		/*
-		 * We can have a hole in the CoW fork if part of a directio
-		 * write is CoW but part of it isn't.
-		 */
-		rlen = ilen = irec.br_blockcount;
-		if (irec.br_startblock == HOLESTARTBLOCK)
+	/* Walk backwards until we're out of the I/O range... */
+	while (got.br_startoff + got.br_blockcount > offset_fsb) {
+		del = got;
+		xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
+
+		/* Extent delete may have bumped idx forward */
+		if (!del.br_blockcount) {
+			idx--;
 			goto next_extent;
-
-		/* Unmap the old blocks in the data fork. */
-		while (rlen) {
-			xfs_defer_init(&dfops, &firstfsb);
-			error = __xfs_bunmapi(tp, ip, irec.br_startoff,
-					&rlen, 0, 1, &firstfsb, &dfops);
-			if (error)
-				goto out_defer;
-
-			/*
-			 * Trim the extent to whatever got unmapped.
-			 * Remember, bunmapi works backwards.
-			 */
-			uirec.br_startblock = irec.br_startblock + rlen;
-			uirec.br_startoff = irec.br_startoff + rlen;
-			uirec.br_blockcount = irec.br_blockcount - rlen;
-			irec.br_blockcount = rlen;
-			trace_xfs_reflink_cow_remap_piece(ip, &uirec);
-
-			/* Free the CoW orphan record. */
-			error = xfs_refcount_free_cow_extent(tp->t_mountp,
-					&dfops, uirec.br_startblock,
-					uirec.br_blockcount);
-			if (error)
-				goto out_defer;
-
-			/* Map the new blocks into the data fork. */
-			error = xfs_bmap_map_extent(tp->t_mountp, &dfops,
-					ip, &uirec);
-			if (error)
-				goto out_defer;
-
-			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &uirec);
-			if (error)
-				goto out_defer;
-
-			error = xfs_defer_finish(&tp, &dfops, ip);
-			if (error)
-				goto out_defer;
 		}
 
+		ASSERT(!isnullstartblock(got.br_startblock));
+
+		/* Unmap the old blocks in the data fork. */
+		xfs_defer_init(&dfops, &firstfsb);
+		rlen = del.br_blockcount;
+		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
+				&firstfsb, &dfops);
+		if (error)
+			goto out_defer;
+
+		/* Trim the extent to whatever got unmapped. */
+		if (rlen) {
+			xfs_trim_extent(&del, del.br_startoff + rlen,
+				del.br_blockcount - rlen);
+		}
+		trace_xfs_reflink_cow_remap(ip, &del);
+
+		/* Free the CoW orphan record. */
+		error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
+				del.br_startblock, del.br_blockcount);
+		if (error)
+			goto out_defer;
+
+		/* Map the new blocks into the data fork. */
+		error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
+		if (error)
+			goto out_defer;
+
+		/* Remove the mapping from the CoW fork. */
+		xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
+
+		error = xfs_defer_finish(&tp, &dfops, ip);
+		if (error)
+			goto out_defer;
+
 next_extent:
-		/* Roll on... */
-		offset_fsb = irec.br_startoff + ilen;
+		if (idx < 0)
+			break;
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got);
 	}
 
 	error = xfs_trans_commit(tp);
@@ -774,7 +737,6 @@ xfs_reflink_end_cow(
 
 out_defer:
 	xfs_defer_cancel(&dfops);
-out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
@@ -1312,19 +1274,26 @@ xfs_compare_extents(
  */
 int
 xfs_reflink_remap_range(
-	struct xfs_inode	*src,
-	xfs_off_t		srcoff,
-	struct xfs_inode	*dest,
-	xfs_off_t		destoff,
-	xfs_off_t		len,
-	unsigned int		flags)
+	struct file		*file_in,
+	loff_t			pos_in,
+	struct file		*file_out,
+	loff_t			pos_out,
+	u64			len,
+	bool			is_dedupe)
 {
+	struct inode		*inode_in = file_inode(file_in);
+	struct xfs_inode	*src = XFS_I(inode_in);
+	struct inode		*inode_out = file_inode(file_out);
+	struct xfs_inode	*dest = XFS_I(inode_out);
 	struct xfs_mount	*mp = src->i_mount;
+	loff_t			bs = inode_out->i_sb->s_blocksize;
+	bool			same_inode = (inode_in == inode_out);
 	xfs_fileoff_t		sfsbno, dfsbno;
 	xfs_filblks_t		fsblen;
-	int			error;
 	xfs_extlen_t		cowextsize;
-	bool			is_same;
+	loff_t			isize;
+	ssize_t			ret;
+	loff_t			blen;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return -EOPNOTSUPP;
@@ -1332,17 +1301,8 @@ xfs_reflink_remap_range(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	/* Don't reflink realtime inodes */
-	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
-		return -EINVAL;
-
-	if (flags & ~XFS_REFLINK_ALL)
-		return -EINVAL;
-
-	trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff);
-
 	/* Lock both files against IO */
-	if (src->i_ino == dest->i_ino) {
+	if (same_inode) {
 		xfs_ilock(src, XFS_IOLOCK_EXCL);
 		xfs_ilock(src, XFS_MMAPLOCK_EXCL);
 	} else {
@@ -1350,39 +1310,126 @@ xfs_reflink_remap_range(
 		xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
 	}
 
+	/* Don't touch certain kinds of inodes */
+	ret = -EPERM;
+	if (IS_IMMUTABLE(inode_out))
+		goto out_unlock;
+
+	ret = -ETXTBSY;
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		goto out_unlock;
+
+
+	/* Don't reflink dirs, pipes, sockets... */
+	ret = -EISDIR;
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		goto out_unlock;
+	ret = -EINVAL;
+	if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
+		goto out_unlock;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		goto out_unlock;
+
+	/* Don't reflink realtime inodes */
+	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
+		goto out_unlock;
+
+	/* Don't share DAX file data for now. */
+	if (IS_DAX(inode_in) || IS_DAX(inode_out))
+		goto out_unlock;
+
+	/* Are we going all the way to the end? */
+	isize = i_size_read(inode_in);
+	if (isize == 0) {
+		ret = 0;
+		goto out_unlock;
+	}
+
+	if (len == 0)
+		len = isize - pos_in;
+
+	/* Ensure offsets don't wrap and the input is inside i_size */
+	if (pos_in + len < pos_in || pos_out + len < pos_out ||
+	    pos_in + len > isize)
+		goto out_unlock;
+
+	/* Don't allow dedupe past EOF in the dest file */
+	if (is_dedupe) {
+		loff_t	disize;
+
+		disize = i_size_read(inode_out);
+		if (pos_out >= disize || pos_out + len > disize)
+			goto out_unlock;
+	}
+
+	/* If we're linking to EOF, continue to the block boundary. */
+	if (pos_in + len == isize)
+		blen = ALIGN(isize, bs) - pos_in;
+	else
+		blen = len;
+
+	/* Only reflink if we're aligned to block boundaries */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
+	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
+		goto out_unlock;
+
+	/* Don't allow overlapped reflink within the same file */
+	if (same_inode) {
+		if (pos_out + blen > pos_in && pos_out < pos_in + blen)
+			goto out_unlock;
+	}
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode_in);
+	if (!same_inode)
+		inode_dio_wait(inode_out);
+
+	ret = filemap_write_and_wait_range(inode_in->i_mapping,
+			pos_in, pos_in + len - 1);
+	if (ret)
+		goto out_unlock;
+
+	ret = filemap_write_and_wait_range(inode_out->i_mapping,
+			pos_out, pos_out + len - 1);
+	if (ret)
+		goto out_unlock;
+
+	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
+
 	/*
 	 * Check that the extents are the same.
 	 */
-	if (flags & XFS_REFLINK_DEDUPE) {
-		is_same = false;
-		error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest),
-				destoff, len, &is_same);
-		if (error)
-			goto out_error;
+	if (is_dedupe) {
+		bool		is_same = false;
+
+		ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out,
+				len, &is_same);
+		if (ret)
+			goto out_unlock;
 		if (!is_same) {
-			error = -EBADE;
-			goto out_error;
+			ret = -EBADE;
+			goto out_unlock;
 		}
 	}
 
-	error = xfs_reflink_set_inode_flag(src, dest);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_set_inode_flag(src, dest);
+	if (ret)
+		goto out_unlock;
 
 	/*
 	 * Invalidate the page cache so that we can clear any CoW mappings
 	 * in the destination file.
 	 */
-	truncate_inode_pages_range(&VFS_I(dest)->i_data, destoff,
-				   PAGE_ALIGN(destoff + len) - 1);
+	truncate_inode_pages_range(&inode_out->i_data, pos_out,
+				   PAGE_ALIGN(pos_out + len) - 1);
 
-	dfsbno = XFS_B_TO_FSBT(mp, destoff);
-	sfsbno = XFS_B_TO_FSBT(mp, srcoff);
+	dfsbno = XFS_B_TO_FSBT(mp, pos_out);
+	sfsbno = XFS_B_TO_FSBT(mp, pos_in);
 	fsblen = XFS_B_TO_FSB(mp, len);
-	error = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
-			destoff + len);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
+			pos_out + len);
+	if (ret)
+		goto out_unlock;
 
 	/*
 	 * Carry the cowextsize hint from src to dest if we're sharing the
@@ -1390,26 +1437,24 @@ xfs_reflink_remap_range(
 	 * has a cowextsize hint, and the destination file does not.
 	 */
 	cowextsize = 0;
-	if (srcoff == 0 && len == i_size_read(VFS_I(src)) &&
+	if (pos_in == 0 && len == i_size_read(inode_in) &&
 	    (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
-	    destoff == 0 && len >= i_size_read(VFS_I(dest)) &&
+	    pos_out == 0 && len >= i_size_read(inode_out) &&
 	    !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
 		cowextsize = src->i_d.di_cowextsize;
 
-	error = xfs_reflink_update_dest(dest, destoff + len, cowextsize);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize);
 
-out_error:
+out_unlock:
 	xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
 	xfs_iunlock(src, XFS_IOLOCK_EXCL);
 	if (src->i_ino != dest->i_ino) {
 		xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
 		xfs_iunlock(dest, XFS_IOLOCK_EXCL);
 	}
-	if (error)
-		trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_);
-	return error;
+	if (ret)
+		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
+	return ret;
 }
 
 /*
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 5dc3c8a..fad1160 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -26,8 +26,8 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
 
-extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip,
-		xfs_off_t offset, xfs_off_t count);
+extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap, bool *shared);
 extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip,
 		xfs_off_t offset, xfs_off_t count);
 extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
@@ -43,11 +43,8 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
-#define XFS_REFLINK_DEDUPE	1	/* only reflink if contents match */
-#define XFS_REFLINK_ALL		(XFS_REFLINK_DEDUPE)
-extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff,
-		struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len,
-		unsigned int flags);
+extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
+		struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
 extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
 		struct xfs_trans **tpp);
 extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 5f8d55d..276d302 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = {
 };
 
 
-struct kobj_type xfs_error_cfg_ktype = {
+static struct kobj_type xfs_error_cfg_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 	.default_attrs = xfs_error_attrs,
 };
 
-struct kobj_type xfs_error_ktype = {
+static struct kobj_type xfs_error_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 };
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ad188d3..0907752 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc);
 
-DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range);
+DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range);
 
 DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write);
@@ -3356,9 +3356,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece);
 
-DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index 43199a0..63554e9 100644
--- a/include/asm-generic/export.h
+++ b/include/asm-generic/export.h
@@ -70,7 +70,7 @@ KSYM(__kcrctab_\name):
 #include <generated/autoksyms.h>
 
 #define __EXPORT_SYMBOL(sym, val, sec)				\
-	__cond_export_sym(sym, val, sec, config_enabled(__KSYM_##sym))
+	__cond_export_sym(sym, val, sec, __is_defined(__KSYM_##sym))
 #define __cond_export_sym(sym, val, sec, conf)			\
 	___cond_export_sym(sym, val, sec, conf)
 #define ___cond_export_sym(sym, val, sec, enabled)		\
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 40e8870..0504ef8 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -118,9 +118,9 @@ do {									\
 #define this_cpu_generic_read(pcp)					\
 ({									\
 	typeof(pcp) __ret;						\
-	preempt_disable();						\
+	preempt_disable_notrace();					\
 	__ret = raw_cpu_generic_read(pcp);				\
-	preempt_enable();						\
+	preempt_enable_notrace();					\
 	__ret;								\
 })
 
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index 43cf193..8b4dc62 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -47,8 +47,14 @@ struct drm_crtc;
  * @src_h: height of visible portion of plane (in 16.16)
  * @rotation: rotation of the plane
  * @zpos: priority of the given plane on crtc (optional)
+ *	Note that multiple active planes on the same crtc can have an identical
+ *	zpos value. The rule to solving the conflict is to compare the plane
+ *	object IDs; the plane with a higher ID must be stacked on top of a
+ *	plane with a lower ID.
  * @normalized_zpos: normalized value of zpos: unique, range from 0 to N-1
- *	where N is the number of active planes for given crtc
+ *	where N is the number of active planes for given crtc. Note that
+ *	the driver must call drm_atomic_normalize_zpos() to update this before
+ *	it can be trusted.
  * @src: clipped source coordinates of the plane (in 16.16)
  * @dst: clipped destination coordinates of the plane
  * @visible: visibility of the plane
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index ddbeda6..689a8b9 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -326,6 +326,7 @@ struct pci_dev;
 int acpi_pci_irq_enable (struct pci_dev *dev);
 void acpi_penalize_isa_irq(int irq, int active);
 bool acpi_isa_irq_available(int irq);
+void acpi_penalize_sci_irq(int irq, int trigger, int polarity);
 void acpi_pci_irq_disable (struct pci_dev *dev);
 
 extern int ec_read(u8 addr, u8 *val);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6824556..cd184bd 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1169,13 +1169,6 @@ int __must_check __vmbus_driver_register(struct hv_driver *hv_driver,
 					 const char *mod_name);
 void vmbus_driver_unregister(struct hv_driver *hv_driver);
 
-static inline const char *vmbus_dev_name(const struct hv_device *device_obj)
-{
-	const struct kobject *kobj = &device_obj->device.kobj;
-
-	return kobj->name;
-}
-
 void vmbus_hvsock_device_unregister(struct vmbus_channel *channel);
 
 int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
diff --git a/include/linux/io.h b/include/linux/io.h
index e2c8419..82ef36e 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -141,4 +141,26 @@ enum {
 void *memremap(resource_size_t offset, size_t size, unsigned long flags);
 void memunmap(void *addr);
 
+/*
+ * On x86 PAT systems we have memory tracking that keeps track of
+ * the allowed mappings on memory ranges. This tracking works for
+ * all the in-kernel mapping APIs (ioremap*), but where the user
+ * wishes to map a range from a physical device into user memory
+ * the tracking won't be updated. This API is to be used by
+ * drivers which remap physical device pages into userspace,
+ * and wants to make sure they are mapped WC and not UC.
+ */
+#ifndef arch_io_reserve_memtype_wc
+static inline int arch_io_reserve_memtype_wc(resource_size_t base,
+					     resource_size_t size)
+{
+	return 0;
+}
+
+static inline void arch_io_free_memtype_wc(resource_size_t base,
+					   resource_size_t size)
+{
+}
+#endif
+
 #endif /* _LINUX_IO_H */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index e63e288..7892f55 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -19,11 +19,15 @@ struct vm_fault;
 #define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
 
 /*
- * Flags for iomap mappings:
+ * Flags for all iomap mappings:
  */
-#define IOMAP_F_MERGED	0x01	/* contains multiple blocks/extents */
-#define IOMAP_F_SHARED	0x02	/* block shared with another file */
-#define IOMAP_F_NEW	0x04	/* blocks have been newly allocated */
+#define IOMAP_F_NEW	0x01	/* blocks have been newly allocated */
+
+/*
+ * Flags that only need to be reported for IOMAP_REPORT requests:
+ */
+#define IOMAP_F_MERGED	0x10	/* contains multiple blocks/extents */
+#define IOMAP_F_SHARED	0x20	/* block shared with another file */
 
 /*
  * Magic value for blkno:
@@ -42,8 +46,9 @@ struct iomap {
 /*
  * Flags for iomap_begin / iomap_end.  No flag implies a read.
  */
-#define IOMAP_WRITE		(1 << 0)
-#define IOMAP_ZERO		(1 << 1)
+#define IOMAP_WRITE		(1 << 0) /* writing, must allocate blocks */
+#define IOMAP_ZERO		(1 << 1) /* zeroing operation, may skip holes */
+#define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
 
 struct iomap_ops {
 	/*
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 7e9a789..ca1ad9e 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -123,12 +123,12 @@ struct inet6_skb_parm {
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
-static inline bool skb_l3mdev_slave(__u16 flags)
+static inline bool ipv6_l3mdev_skb(__u16 flags)
 {
 	return flags & IP6SKB_L3SLAVE;
 }
 #else
-static inline bool skb_l3mdev_slave(__u16 flags)
+static inline bool ipv6_l3mdev_skb(__u16 flags)
 {
 	return false;
 }
@@ -139,11 +139,22 @@ static inline bool skb_l3mdev_slave(__u16 flags)
 
 static inline int inet6_iif(const struct sk_buff *skb)
 {
-	bool l3_slave = skb_l3mdev_slave(IP6CB(skb)->flags);
+	bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags);
 
 	return l3_slave ? skb->skb_iif : IP6CB(skb)->iif;
 }
 
+/* can not be used in TCP layer after tcp_v6_fill_cb */
+static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if defined(CONFIG_NET_L3_MASTER_DEV)
+	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
+	    ipv6_l3mdev_skb(IP6CB(skb)->flags))
+		return true;
+#endif
+	return false;
+}
+
 struct tcp6_request_sock {
 	struct tcp_request_sock	  tcp6rsk_tcp;
 };
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index 15ec117..8f2e059 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -31,7 +31,6 @@
  * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
  * the last step cherry picks the 2nd arg, we get a zero.
  */
-#define config_enabled(cfg)		___is_defined(cfg)
 #define __is_defined(x)			___is_defined(x)
 #define ___is_defined(val)		____is_defined(__ARG_PLACEHOLDER_##val)
 #define ____is_defined(arg1_or_junk)	__take_second_arg(arg1_or_junk 1, 0)
@@ -41,13 +40,13 @@
  * otherwise. For boolean options, this is equivalent to
  * IS_ENABLED(CONFIG_FOO).
  */
-#define IS_BUILTIN(option) config_enabled(option)
+#define IS_BUILTIN(option) __is_defined(option)
 
 /*
  * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0
  * otherwise.
  */
-#define IS_MODULE(option) config_enabled(option##_MODULE)
+#define IS_MODULE(option) __is_defined(option##_MODULE)
 
 /*
  * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f6a16429..3be7abd 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1399,7 +1399,8 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 		    u32 *lkey, u32 *rkey);
 int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
-int mlx4_test_interrupts(struct mlx4_dev *dev);
+int mlx4_test_interrupt(struct mlx4_dev *dev, int vector);
+int mlx4_test_async(struct mlx4_dev *dev);
 int mlx4_query_diag_counters(struct mlx4_dev *dev, u8 op_modifier,
 			     const u32 offset[], u32 value[],
 			     size_t array_len, u8 port);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 85c4786..ecc451d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -418,8 +418,12 @@ struct mlx5_core_health {
 	u32				prev;
 	int				miss_counter;
 	bool				sick;
+	/* wq spinlock to synchronize draining */
+	spinlock_t			wq_lock;
 	struct workqueue_struct	       *wq;
+	unsigned long			flags;
 	struct work_struct		work;
+	struct delayed_work		recover_work;
 };
 
 struct mlx5_cq_table {
@@ -626,10 +630,6 @@ struct mlx5_db {
 };
 
 enum {
-	MLX5_DB_PER_PAGE = PAGE_SIZE / L1_CACHE_BYTES,
-};
-
-enum {
 	MLX5_COMP_EQ_SIZE = 1024,
 };
 
@@ -638,13 +638,6 @@ enum {
 	MLX5_PTYS_EN = 1 << 2,
 };
 
-struct mlx5_db_pgdir {
-	struct list_head	list;
-	DECLARE_BITMAP(bitmap, MLX5_DB_PER_PAGE);
-	__be32		       *db_page;
-	dma_addr_t		db_dma;
-};
-
 typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
 
 struct mlx5_cmd_work_ent {
@@ -789,6 +782,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
+void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			struct mlx5_buf *buf, int node);
 int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7f2ae99..0f088f3 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -440,33 +440,7 @@ struct zone {
 	seqlock_t		span_seqlock;
 #endif
 
-	/*
-	 * wait_table		-- the array holding the hash table
-	 * wait_table_hash_nr_entries	-- the size of the hash table array
-	 * wait_table_bits	-- wait_table_size == (1 << wait_table_bits)
-	 *
-	 * The purpose of all these is to keep track of the people
-	 * waiting for a page to become available and make them
-	 * runnable again when possible. The trouble is that this
-	 * consumes a lot of space, especially when so few things
-	 * wait on pages at a given time. So instead of using
-	 * per-page waitqueues, we use a waitqueue hash table.
-	 *
-	 * The bucket discipline is to sleep on the same queue when
-	 * colliding and wake all in that wait queue when removing.
-	 * When something wakes, it must check to be sure its page is
-	 * truly available, a la thundering herd. The cost of a
-	 * collision is great, but given the expected load of the
-	 * table, they should be so rare as to be outweighed by the
-	 * benefits from the saved space.
-	 *
-	 * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
-	 * primary users of these fields, and in mm/page_alloc.c
-	 * free_area_init_core() performs the initialization of them.
-	 */
-	wait_queue_head_t	*wait_table;
-	unsigned long		wait_table_hash_nr_entries;
-	unsigned long		wait_table_bits;
+	int initialized;
 
 	/* Write-intensive fields used from the page allocator */
 	ZONE_PADDING(_pad1_)
@@ -546,7 +520,7 @@ static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn)
 
 static inline bool zone_is_initialized(struct zone *zone)
 {
-	return !!zone->wait_table;
+	return zone->initialized;
 }
 
 static inline bool zone_is_empty(struct zone *zone)
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index c5d3d502..d8905a2 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -1184,7 +1184,7 @@ int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
 			   int page);
 
 /* Reset and initialize a NAND device */
-int nand_reset(struct nand_chip *chip);
+int nand_reset(struct nand_chip *chip, int chipnr);
 
 /* Free resources held by the NAND device */
 void nand_cleanup(struct nand_chip *chip);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 136ae6bb..91ee364 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2169,7 +2169,10 @@ struct napi_gro_cb {
 	/* Used to determine if flush_id can be ignored */
 	u8	is_atomic:1;
 
-	/* 5 bit hole */
+	/* Number of gro_receive callbacks this packet already went through */
+	u8 recursion_counter:4;
+
+	/* 1 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
@@ -2180,6 +2183,40 @@ struct napi_gro_cb {
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
 
+#define GRO_RECURSION_LIMIT 15
+static inline int gro_recursion_inc_test(struct sk_buff *skb)
+{
+	return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
+}
+
+typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
+static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
+						struct sk_buff **head,
+						struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(head, skb);
+}
+
+typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **,
+					     struct sk_buff *);
+static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb,
+						   struct sock *sk,
+						   struct sk_buff **head,
+						   struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(sk, head, skb);
+}
+
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	struct net_device	*dev;	/* NULL is wildcarded here	     */
@@ -3877,7 +3914,7 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
 	     ldev = netdev_all_lower_get_next(dev, &(iter)))
 
 #define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \
-	for (iter = (dev)->all_adj_list.lower.next, \
+	for (iter = &(dev)->all_adj_list.lower, \
 	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \
 	     ldev; \
 	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 060d0ed..4741ecd 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1257,6 +1257,7 @@ extern u64 perf_swevent_set_period(struct perf_event *event);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_disable_local(struct perf_event *event);
+extern void perf_event_disable_inatomic(struct perf_event *event);
 extern void perf_event_task_tick(void);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index f9ae903..8978a60 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -146,6 +146,7 @@ enum qed_led_mode {
 #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr))
 
 #define QED_COALESCE_MAX 0xFF
+#define QED_DEFAULT_RX_USECS 12
 
 /* forward */
 struct qed_dev;
diff --git a/include/linux/qed/qede_roce.h b/include/linux/qed/qede_roce.h
index 99fbe6d..f48d64b 100644
--- a/include/linux/qed/qede_roce.h
+++ b/include/linux/qed/qede_roce.h
@@ -68,7 +68,7 @@ void qede_roce_unregister_driver(struct qedr_driver *drv);
 
 bool qede_roce_supported(struct qede_dev *dev);
 
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
+#if IS_ENABLED(CONFIG_QED_RDMA)
 int qede_roce_dev_add(struct qede_dev *dev);
 void qede_roce_dev_event_open(struct qede_dev *dev);
 void qede_roce_dev_event_close(struct qede_dev *dev);
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 9adc7b2..f667313 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -15,6 +15,7 @@
 
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/bug.h>
 #include <linux/lockdep.h>
@@ -116,22 +117,22 @@ struct reg_sequence {
 #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \
 ({ \
 	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
-	int ret; \
+	int pollret; \
 	might_sleep_if(sleep_us); \
 	for (;;) { \
-		ret = regmap_read((map), (addr), &(val)); \
-		if (ret) \
+		pollret = regmap_read((map), (addr), &(val)); \
+		if (pollret) \
 			break; \
 		if (cond) \
 			break; \
 		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
-			ret = regmap_read((map), (addr), &(val)); \
+			pollret = regmap_read((map), (addr), &(val)); \
 			break; \
 		} \
 		if (sleep_us) \
 			usleep_range((sleep_us >> 2) + 1, sleep_us); \
 	} \
-	ret ?: ((cond) ? 0 : -ETIMEDOUT); \
+	pollret ?: ((cond) ? 0 : -ETIMEDOUT); \
 })
 
 #ifdef CONFIG_REGMAP
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 601258f..32810f2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -936,6 +936,7 @@ struct sk_buff_fclones {
 
 /**
  *	skb_fclone_busy - check if fclone is busy
+ *	@sk: socket
  *	@skb: buffer
  *
  * Returns true if skb is a fast clone, and its clone is not freed.
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f2d0727..8f998af 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -174,6 +174,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+void __ipv6_sock_mc_close(struct sock *sk);
 void ipv6_sock_mc_close(struct sock *sk);
 bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
 		    const struct in6_addr *src_addr);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index bd19faa..14b51d7 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4047,14 +4047,29 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr);
  */
 
 /**
+ * ieee80211_data_to_8023_exthdr - convert an 802.11 data frame to 802.3
+ * @skb: the 802.11 data frame
+ * @ehdr: pointer to a &struct ethhdr that will get the header, instead
+ *	of it being pushed into the SKB
+ * @addr: the device MAC address
+ * @iftype: the virtual interface type
+ * Return: 0 on success. Non-zero on error.
+ */
+int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
+				  const u8 *addr, enum nl80211_iftype iftype);
+
+/**
  * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3
  * @skb: the 802.11 data frame
  * @addr: the device MAC address
  * @iftype: the virtual interface type
  * Return: 0 on success. Non-zero on error.
  */
-int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
-			   enum nl80211_iftype iftype);
+static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
+					 enum nl80211_iftype iftype)
+{
+	return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype);
+}
 
 /**
  * ieee80211_data_from_8023 - convert an 802.3 frame to 802.11
@@ -4072,22 +4087,23 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
 /**
  * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame
  *
- * Decode an IEEE 802.11n A-MSDU frame and convert it to a list of
- * 802.3 frames. The @list will be empty if the decode fails. The
- * @skb is consumed after the function returns.
+ * Decode an IEEE 802.11 A-MSDU and convert it to a list of 802.3 frames.
+ * The @list will be empty if the decode fails. The @skb must be fully
+ * header-less before being passed in here; it is freed in this function.
  *
- * @skb: The input IEEE 802.11n A-MSDU frame.
+ * @skb: The input A-MSDU frame without any headers.
  * @list: The output list of 802.3 frames. It must be allocated and
  *	initialized by by the caller.
  * @addr: The device MAC address.
  * @iftype: The device interface type.
  * @extra_headroom: The hardware extra headroom for SKBs in the @list.
- * @has_80211_header: Set it true if SKB is with IEEE 802.11 header.
+ * @check_da: DA to check in the inner ethernet header, or NULL
+ * @check_sa: SA to check in the inner ethernet header, or NULL
  */
 void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 			      const u8 *addr, enum nl80211_iftype iftype,
 			      const unsigned int extra_headroom,
-			      bool has_80211_header);
+			      const u8 *check_da, const u8 *check_sa);
 
 /**
  * cfg80211_classify8021d - determine the 802.1p/1d tag for a data frame
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 515352c..b0576cb 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -190,8 +190,8 @@ struct inet6_dev {
 	__u32			if_flags;
 	int			dead;
 
+	u32			desync_factor;
 	u8			rndid[8];
-	struct timer_list	regen_timer;
 	struct list_head	tempaddr_list;
 
 	struct in6_addr		token;
diff --git a/include/net/ip.h b/include/net/ip.h
index bc43c0f..5413883 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -38,7 +38,7 @@ struct sock;
 struct inet_skb_parm {
 	int			iif;
 	struct ip_options	opt;		/* Compiled IP options		*/
-	unsigned char		flags;
+	u16			flags;
 
 #define IPSKB_FORWARDED		BIT(0)
 #define IPSKB_XFRM_TUNNEL_SIZE	BIT(1)
@@ -48,10 +48,16 @@ struct inet_skb_parm {
 #define IPSKB_DOREDIRECT	BIT(5)
 #define IPSKB_FRAG_PMTU		BIT(6)
 #define IPSKB_FRAG_SEGS		BIT(7)
+#define IPSKB_L3SLAVE		BIT(8)
 
 	u16			frag_max_size;
 };
 
+static inline bool ipv4_l3mdev_skb(u16 flags)
+{
+	return !!(flags & IPSKB_L3SLAVE);
+}
+
 static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
 {
 	return ip_hdr(skb)->ihl * 4;
@@ -572,7 +578,7 @@ int ip_options_rcv_srr(struct sk_buff *skb);
  */
 
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
-void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
@@ -594,7 +600,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 
 static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 {
-	ip_cmsg_recv_offset(msg, skb, 0);
+	ip_cmsg_recv_offset(msg, skb, 0, 0);
 }
 
 bool icmp_global_allow(void);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index fb961a5..a74e2aa 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -230,6 +230,8 @@ struct fib6_table {
 	rwlock_t		tb6_lock;
 	struct fib6_node	tb6_root;
 	struct inet_peer_base	tb6_peers;
+	unsigned int		flags;
+#define RT6_TABLE_HAS_DFLT_ROUTER	BIT(0)
 };
 
 #define RT6_TABLE_UNSPEC	RT_TABLE_UNSPEC
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index e0cd318..f83e78d 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -32,6 +32,7 @@ struct route_info {
 #define RT6_LOOKUP_F_SRCPREF_TMP	0x00000008
 #define RT6_LOOKUP_F_SRCPREF_PUBLIC	0x00000010
 #define RT6_LOOKUP_F_SRCPREF_COA	0x00000020
+#define RT6_LOOKUP_F_IGNORE_LINKSTATE	0x00000040
 
 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675)
  * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index a810dfc..e2dba93 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -811,14 +811,18 @@ enum mac80211_rate_control_flags {
  * in the control information, and it will be filled by the rate
  * control algorithm according to what should be sent. For example,
  * if this array contains, in the format { <idx>, <count> } the
- * information
+ * information::
+ *
  *    { 3, 2 }, { 2, 2 }, { 1, 4 }, { -1, 0 }, { -1, 0 }
+ *
  * then this means that the frame should be transmitted
  * up to twice at rate 3, up to twice at rate 2, and up to four
  * times at rate 1 if it doesn't get acknowledged. Say it gets
  * acknowledged by the peer after the fifth attempt, the status
- * information should then contain
+ * information should then contain::
+ *
  *   { 3, 2 }, { 2, 2 }, { 1, 1 }, { -1, 0 } ...
+ *
  * since it was transmitted twice at rate 3, twice at rate 2
  * and once at rate 1 after which we received an acknowledgement.
  */
@@ -1168,8 +1172,8 @@ enum mac80211_rx_vht_flags {
  * @rate_idx: index of data rate into band's supported rates or MCS index if
  *	HT or VHT is used (%RX_FLAG_HT/%RX_FLAG_VHT)
  * @vht_nss: number of streams (VHT only)
- * @flag: %RX_FLAG_*
- * @vht_flag: %RX_VHT_FLAG_*
+ * @flag: %RX_FLAG_\*
+ * @vht_flag: %RX_VHT_FLAG_\*
  * @rx_flags: internal RX flags for mac80211
  * @ampdu_reference: A-MPDU reference number, must be a different value for
  *	each A-MPDU but the same for each subframe within one A-MPDU
@@ -1432,7 +1436,7 @@ enum ieee80211_vif_flags {
  * @probe_req_reg: probe requests should be reported to mac80211 for this
  *	interface.
  * @drv_priv: data area for driver use, will always be aligned to
- *	sizeof(void *).
+ *	sizeof(void \*).
  * @txq: the multicast data TX queue (if driver uses the TXQ abstraction)
  */
 struct ieee80211_vif {
@@ -1743,7 +1747,7 @@ struct ieee80211_sta_rates {
  * @wme: indicates whether the STA supports QoS/WME (if local devices does,
  *	otherwise always false)
  * @drv_priv: data area for driver use, will always be aligned to
- *	sizeof(void *), size is determined in hw information.
+ *	sizeof(void \*), size is determined in hw information.
  * @uapsd_queues: bitmap of queues configured for uapsd. Only valid
  *	if wme is supported.
  * @max_sp: max Service Period. Only valid if wme is supported.
@@ -2146,12 +2150,12 @@ enum ieee80211_hw_flags {
  *
  * @radiotap_mcs_details: lists which MCS information can the HW
  *	reports, by default it is set to _MCS, _GI and _BW but doesn't
- *	include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_* values, only
+ *	include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_\* values, only
  *	adding _BW is supported today.
  *
  * @radiotap_vht_details: lists which VHT MCS information the HW reports,
  *	the default is _GI | _BANDWIDTH.
- *	Use the %IEEE80211_RADIOTAP_VHT_KNOWN_* values.
+ *	Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values.
  *
  * @radiotap_timestamp: Information for the radiotap timestamp field; if the
  *	'units_pos' member is set to a non-negative value it must be set to
@@ -2486,6 +2490,7 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
  * in the software stack cares about, we will, in the future, have mac80211
  * tell the driver which information elements are interesting in the sense
  * that we want to see changes in them. This will include
+ *
  *  - a list of information element IDs
  *  - a list of OUIs for the vendor information element
  *
diff --git a/include/net/sock.h b/include/net/sock.h
index ebf75db..73c6b00 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -252,6 +252,7 @@ struct sock_common {
   *	@sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
   *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
   *	@sk_sndbuf: size of send buffer in bytes
+  *	@sk_padding: unused element for alignment
   *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
@@ -302,7 +303,8 @@ struct sock_common {
   *	@sk_backlog_rcv: callback to process the backlog
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
   *	@sk_reuseport_cb: reuseport group container
- */
+  *	@sk_rcu: used during RCU grace period
+  */
 struct sock {
 	/*
 	 * Now struct inet_timewait_sock also uses sock_common, so please just
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f83b7f2..5b82d4d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -794,12 +794,23 @@ struct tcp_skb_cb {
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
 {
-	bool l3_slave = skb_l3mdev_slave(TCP_SKB_CB(skb)->header.h6.flags);
+	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 
 	return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
 }
 #endif
 
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
+	    ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+		return true;
+#endif
+	return false;
+}
+
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */
diff --git a/include/net/udp.h b/include/net/udp.h
index ea53a87..4948790 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -258,6 +258,7 @@ void udp_flush_pending_frames(struct sock *sk);
 void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
 int udp_rcv(struct sk_buff *skb);
 int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+int __udp_disconnect(struct sock *sk, int flags);
 int udp_disconnect(struct sock *sk, int flags);
 unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0255613..308adc4 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -225,9 +225,9 @@ struct vxlan_config {
 struct vxlan_dev {
 	struct hlist_node hlist;	/* vni hash table */
 	struct list_head  next;		/* vxlan's per namespace list */
-	struct vxlan_sock *vn4_sock;	/* listening socket for IPv4 */
+	struct vxlan_sock __rcu *vn4_sock;	/* listening socket for IPv4 */
 #if IS_ENABLED(CONFIG_IPV6)
-	struct vxlan_sock *vn6_sock;	/* listening socket for IPv6 */
+	struct vxlan_sock __rcu *vn6_sock;	/* listening socket for IPv6 */
 #endif
 	struct net_device *dev;
 	struct net	  *net;		/* netns for packet i/o */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 099a420..8e54723 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -119,8 +119,7 @@ struct ethtool_cmd {
 static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep,
 					 __u32 speed)
 {
-
-	ep->speed = (__u16)speed;
+	ep->speed = (__u16)(speed & 0xFFFF);
 	ep->speed_hi = (__u16)(speed >> 16);
 }
 
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 262f037..5a78be5 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -350,7 +350,7 @@ struct rtnexthop {
 #define RTNH_F_OFFLOAD		8	/* offloaded route */
 #define RTNH_F_LINKDOWN		16	/* carrier-down on nexthop */
 
-#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN)
+#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
 
 /* Macros to handle hexthops */
 
diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h
index 33d00a4..819d895 100644
--- a/include/uapi/sound/asoc.h
+++ b/include/uapi/sound/asoc.h
@@ -18,12 +18,6 @@
 #include <linux/types.h>
 #include <sound/asound.h>
 
-#ifndef __KERNEL__
-#error This API is an early revision and not enabled in the current
-#error kernel release, it will be enabled in a future kernel version
-#error with incompatible changes to what is here.
-#endif
-
 /*
  * Maximum number of channels topology kcontrol can represent.
  */
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index a521999..bf74eaa 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -53,7 +53,7 @@ static struct msg_msg *alloc_msg(size_t len)
 	size_t alen;
 
 	alen = min(len, DATALEN_MSG);
-	msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
+	msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL_ACCOUNT);
 	if (msg == NULL)
 		return NULL;
 
@@ -65,7 +65,7 @@ static struct msg_msg *alloc_msg(size_t len)
 	while (len > 0) {
 		struct msg_msgseg *seg;
 		alen = min(len, DATALEN_SEG);
-		seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL);
+		seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL_ACCOUNT);
 		if (seg == NULL)
 			goto out_err;
 		*pseg = seg;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c6e47e9..0e29213 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1960,6 +1960,12 @@ void perf_event_disable(struct perf_event *event)
 }
 EXPORT_SYMBOL_GPL(perf_event_disable);
 
+void perf_event_disable_inatomic(struct perf_event *event)
+{
+	event->pending_disable = 1;
+	irq_work_queue(&event->pending);
+}
+
 static void perf_set_shadow_time(struct perf_event *event,
 				 struct perf_event_context *ctx,
 				 u64 tstamp)
@@ -7075,8 +7081,8 @@ static int __perf_event_overflow(struct perf_event *event,
 	if (events && atomic_dec_and_test(&event->event_limit)) {
 		ret = 1;
 		event->pending_kill = POLL_HUP;
-		event->pending_disable = 1;
-		irq_work_queue(&event->pending);
+
+		perf_event_disable_inatomic(event);
 	}
 
 	READ_ONCE(event->overflow_handler)(event, data, regs);
@@ -8855,7 +8861,10 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
+	int remove_device;
+
 	mutex_lock(&pmus_lock);
+	remove_device = pmu_bus_running;
 	list_del_rcu(&pmu->entry);
 	mutex_unlock(&pmus_lock);
 
@@ -8869,10 +8878,12 @@ void perf_pmu_unregister(struct pmu *pmu)
 	free_percpu(pmu->pmu_disable_count);
 	if (pmu->type >= PERF_TYPE_MAX)
 		idr_remove(&pmu_idr, pmu->type);
-	if (pmu->nr_addr_filters)
-		device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
-	device_del(pmu->dev);
-	put_device(pmu->dev);
+	if (remove_device) {
+		if (pmu->nr_addr_filters)
+			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
+		device_del(pmu->dev);
+		put_device(pmu->dev);
+	}
 	free_pmu_context(pmu);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
diff --git a/kernel/fork.c b/kernel/fork.c
index 623259f..997ac1d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -315,6 +315,9 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 
 static void release_task_stack(struct task_struct *tsk)
 {
+	if (WARN_ON(tsk->state != TASK_DEAD))
+		return;  /* Better to leak the stack than to free prematurely */
+
 	account_kernel_stack(tsk, -1);
 	arch_release_thread_stack(tsk->stack);
 	free_thread_stack(tsk);
@@ -1862,6 +1865,7 @@ static __latent_entropy struct task_struct *copy_process(
 	atomic_dec(&p->cred->user->processes);
 	exit_creds(p);
 bad_fork_free:
+	p->state = TASK_DEAD;
 	put_task_stack(p);
 	free_task(p);
 fork_out:
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 8d44b3f..30e6d05 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -53,8 +53,15 @@ void notrace __sanitizer_cov_trace_pc(void)
 	/*
 	 * We are interested in code coverage as a function of a syscall inputs,
 	 * so we ignore code executed in interrupts.
+	 * The checks for whether we are in an interrupt are open-coded, because
+	 * 1. We can't use in_interrupt() here, since it also returns true
+	 *    when we are inside local_bh_disable() section.
+	 * 2. We don't want to use (in_irq() | in_serving_softirq() | in_nmi()),
+	 *    since that leads to slower generated code (three separate tests,
+	 *    one for each of the flags).
 	 */
-	if (!t || in_interrupt())
+	if (!t || (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET
+							| NMI_MASK)))
 		return;
 	mode = READ_ONCE(t->kcov_mode);
 	if (mode == KCOV_MODE_TRACE) {
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 1e7f5da..6ccb08f 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -498,9 +498,9 @@ static int enter_state(suspend_state_t state)
 
 #ifndef CONFIG_SUSPEND_SKIP_SYNC
 	trace_suspend_resume(TPS("sync_filesystems"), 0, true);
-	printk(KERN_INFO "PM: Syncing filesystems ... ");
+	pr_info("PM: Syncing filesystems ... ");
 	sys_sync();
-	printk("done.\n");
+	pr_cont("done.\n");
 	trace_suspend_resume(TPS("sync_filesystems"), 0, false);
 #endif
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8912aaf..8b08fb2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5192,21 +5192,14 @@ void sched_show_task(struct task_struct *p)
 	int ppid;
 	unsigned long state = p->state;
 
+	if (!try_get_task_stack(p))
+		return;
 	if (state)
 		state = __ffs(state) + 1;
 	printk(KERN_INFO "%-15.15s %c", p->comm,
 		state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
-#if BITS_PER_LONG == 32
-	if (state == TASK_RUNNING)
-		printk(KERN_CONT " running  ");
-	else
-		printk(KERN_CONT " %08lx ", thread_saved_pc(p));
-#else
 	if (state == TASK_RUNNING)
 		printk(KERN_CONT "  running task    ");
-	else
-		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
-#endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
@@ -5221,6 +5214,7 @@ void sched_show_task(struct task_struct *p)
 
 	print_worker_info(KERN_INFO, p);
 	show_stack(p, NULL);
+	put_task_stack(p);
 }
 
 void show_state_filter(unsigned long state_filter)
@@ -7515,11 +7509,27 @@ static struct kmem_cache *task_group_cache __read_mostly;
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
 DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
 
+#define WAIT_TABLE_BITS 8
+#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
+static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned;
+
+wait_queue_head_t *bit_waitqueue(void *word, int bit)
+{
+	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
+	unsigned long val = (unsigned long)word << shift | bit;
+
+	return bit_wait_table + hash_long(val, WAIT_TABLE_BITS);
+}
+EXPORT_SYMBOL(bit_waitqueue);
+
 void __init sched_init(void)
 {
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
+	for (i = 0; i < WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(bit_wait_table + i);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d941c97..c242944 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8839,7 +8839,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
-	struct rq *rq;
 	int i;
 
 	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8854,8 +8853,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
 	for_each_possible_cpu(i) {
-		rq = cpu_rq(i);
-
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
 				      GFP_KERNEL, cpu_to_node(i));
 		if (!cfs_rq)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4f70535..9453efe 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -480,16 +480,6 @@ void wake_up_bit(void *word, int bit)
 }
 EXPORT_SYMBOL(wake_up_bit);
 
-wait_queue_head_t *bit_waitqueue(void *word, int bit)
-{
-	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
-	const struct zone *zone = page_zone(virt_to_page(word));
-	unsigned long val = (unsigned long)word << shift | bit;
-
-	return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
-}
-EXPORT_SYMBOL(bit_waitqueue);
-
 /*
  * Manipulate the atomic_t address to produce a better bit waitqueue table hash
  * index (we're keying off bit -1, but that would produce a horrible hash
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 1bf81ef..744fa61 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -58,7 +58,7 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
 DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 const char * const softirq_to_name[NR_SOFTIRQS] = {
-	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
+	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL",
 	"TASKLET", "SCHED", "HRTIMER", "RCU"
 };
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 2d47980..c611c47 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -878,7 +878,7 @@ static inline struct timer_base *get_timer_base(u32 tflags)
 
 #ifdef CONFIG_NO_HZ_COMMON
 static inline struct timer_base *
-__get_target_base(struct timer_base *base, unsigned tflags)
+get_target_base(struct timer_base *base, unsigned tflags)
 {
 #ifdef CONFIG_SMP
 	if ((tflags & TIMER_PINNED) || !base->migration_enabled)
@@ -891,25 +891,27 @@ __get_target_base(struct timer_base *base, unsigned tflags)
 
 static inline void forward_timer_base(struct timer_base *base)
 {
+	unsigned long jnow = READ_ONCE(jiffies);
+
 	/*
 	 * We only forward the base when it's idle and we have a delta between
 	 * base clock and jiffies.
 	 */
-	if (!base->is_idle || (long) (jiffies - base->clk) < 2)
+	if (!base->is_idle || (long) (jnow - base->clk) < 2)
 		return;
 
 	/*
 	 * If the next expiry value is > jiffies, then we fast forward to
 	 * jiffies otherwise we forward to the next expiry value.
 	 */
-	if (time_after(base->next_expiry, jiffies))
-		base->clk = jiffies;
+	if (time_after(base->next_expiry, jnow))
+		base->clk = jnow;
 	else
 		base->clk = base->next_expiry;
 }
 #else
 static inline struct timer_base *
-__get_target_base(struct timer_base *base, unsigned tflags)
+get_target_base(struct timer_base *base, unsigned tflags)
 {
 	return get_timer_this_cpu_base(tflags);
 }
@@ -917,14 +919,6 @@ __get_target_base(struct timer_base *base, unsigned tflags)
 static inline void forward_timer_base(struct timer_base *base) { }
 #endif
 
-static inline struct timer_base *
-get_target_base(struct timer_base *base, unsigned tflags)
-{
-	struct timer_base *target = __get_target_base(base, tflags);
-
-	forward_timer_base(target);
-	return target;
-}
 
 /*
  * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
@@ -943,7 +937,14 @@ static struct timer_base *lock_timer_base(struct timer_list *timer,
 {
 	for (;;) {
 		struct timer_base *base;
-		u32 tf = timer->flags;
+		u32 tf;
+
+		/*
+		 * We need to use READ_ONCE() here, otherwise the compiler
+		 * might re-read @tf between the check for TIMER_MIGRATING
+		 * and spin_lock().
+		 */
+		tf = READ_ONCE(timer->flags);
 
 		if (!(tf & TIMER_MIGRATING)) {
 			base = get_timer_base(tf);
@@ -964,6 +965,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	unsigned long clk = 0, flags;
 	int ret = 0;
 
+	BUG_ON(!timer->function);
+
 	/*
 	 * This is a common optimization triggered by the networking code - if
 	 * the timer is re-modified to have the same timeout or ends up in the
@@ -972,13 +975,16 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	if (timer_pending(timer)) {
 		if (timer->expires == expires)
 			return 1;
-		/*
-		 * Take the current timer_jiffies of base, but without holding
-		 * the lock!
-		 */
-		base = get_timer_base(timer->flags);
-		clk = base->clk;
 
+		/*
+		 * We lock timer base and calculate the bucket index right
+		 * here. If the timer ends up in the same bucket, then we
+		 * just update the expiry time and avoid the whole
+		 * dequeue/enqueue dance.
+		 */
+		base = lock_timer_base(timer, &flags);
+
+		clk = base->clk;
 		idx = calc_wheel_index(expires, clk);
 
 		/*
@@ -988,14 +994,14 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 */
 		if (idx == timer_get_idx(timer)) {
 			timer->expires = expires;
-			return 1;
+			ret = 1;
+			goto out_unlock;
 		}
+	} else {
+		base = lock_timer_base(timer, &flags);
 	}
 
 	timer_stats_timer_set_start_info(timer);
-	BUG_ON(!timer->function);
-
-	base = lock_timer_base(timer, &flags);
 
 	ret = detach_if_pending(timer, base, false);
 	if (!ret && pending_only)
@@ -1025,12 +1031,16 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		}
 	}
 
+	/* Try to forward a stale timer base clock */
+	forward_timer_base(base);
+
 	timer->expires = expires;
 	/*
 	 * If 'idx' was calculated above and the base time did not advance
-	 * between calculating 'idx' and taking the lock, only enqueue_timer()
-	 * and trigger_dyntick_cpu() is required. Otherwise we need to
-	 * (re)calculate the wheel index via internal_add_timer().
+	 * between calculating 'idx' and possibly switching the base, only
+	 * enqueue_timer() and trigger_dyntick_cpu() is required. Otherwise
+	 * we need to (re)calculate the wheel index via
+	 * internal_add_timer().
 	 */
 	if (idx != UINT_MAX && clk == base->clk) {
 		enqueue_timer(base, timer, idx);
@@ -1510,12 +1520,16 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 	is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
 	base->next_expiry = nextevt;
 	/*
-	 * We have a fresh next event. Check whether we can forward the base:
+	 * We have a fresh next event. Check whether we can forward the
+	 * base. We can only do that when @basej is past base->clk
+	 * otherwise we might rewind base->clk.
 	 */
-	if (time_after(nextevt, jiffies))
-		base->clk = jiffies;
-	else if (time_after(nextevt, base->clk))
-		base->clk = nextevt;
+	if (time_after(basej, base->clk)) {
+		if (time_after(nextevt, basej))
+			base->clk = basej;
+		else if (time_after(nextevt, base->clk))
+			base->clk = nextevt;
+	}
 
 	if (time_before_eq(nextevt, basej)) {
 		expires = basem;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 33bc56c..b01e547 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -198,6 +198,7 @@
 	int "Warn for stack frames larger than (needs gcc 4.4)"
 	range 0 8192
 	default 0 if KASAN
+	default 2048 if GCC_PLUGIN_LATENT_ENTROPY
 	default 1024 if !64BIT
 	default 2048 if 64BIT
 	help
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 0a11396..144fe6b 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -292,7 +292,7 @@ unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size,
 	struct gen_pool_chunk *chunk;
 	unsigned long addr = 0;
 	int order = pool->min_alloc_order;
-	int nbits, start_bit = 0, end_bit, remain;
+	int nbits, start_bit, end_bit, remain;
 
 #ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
 	BUG_ON(in_nmi());
@@ -307,6 +307,7 @@ unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size,
 		if (size > atomic_read(&chunk->avail))
 			continue;
 
+		start_bit = 0;
 		end_bit = chunk_size(chunk) >> order;
 retry:
 		start_bit = algo(chunk->bits, end_bit, start_bit,
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 60f77f1..4d830e2 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -50,7 +50,7 @@
 					STACK_ALLOC_ALIGN)
 #define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - \
 		STACK_ALLOC_NULL_PROTECTION_BITS - STACK_ALLOC_OFFSET_BITS)
-#define STACK_ALLOC_SLABS_CAP 1024
+#define STACK_ALLOC_SLABS_CAP 8192
 #define STACK_ALLOC_MAX_SLABS \
 	(((1LL << (STACK_ALLOC_INDEX_BITS)) < STACK_ALLOC_SLABS_CAP) ? \
 	 (1LL << (STACK_ALLOC_INDEX_BITS)) : STACK_ALLOC_SLABS_CAP)
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 94346b4..0362da0 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -4831,7 +4831,7 @@ static struct bpf_test tests[] = {
 		{ },
 		INTERNAL,
 		{ 0x34 },
-		{ { 1, 0xbef } },
+		{ { ETH_HLEN, 0xbef } },
 		.fill_helper = bpf_fill_ld_abs_vlan_push_pop,
 	},
 	/*
diff --git a/mm/Kconfig b/mm/Kconfig
index be0ee11..86e3e0e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -187,7 +187,7 @@
 	bool "Allow for memory hot-add"
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
-	depends on !KASAN
+	depends on COMPILE_TEST || !KASAN
 
 config MEMORY_HOTPLUG_SPARSE
 	def_bool y
diff --git a/mm/filemap.c b/mm/filemap.c
index 849f459..c7fe2f1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -790,9 +790,7 @@ EXPORT_SYMBOL(__page_cache_alloc);
  */
 wait_queue_head_t *page_waitqueue(struct page *page)
 {
-	const struct zone *zone = page_zone(page);
-
-	return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
+	return bit_waitqueue(page, 0);
 }
 EXPORT_SYMBOL(page_waitqueue);
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index a5e453c..e5355a5 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1453,8 +1453,11 @@ static void kmemleak_scan(void)
 
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
-			scan_block(task_stack_page(p), task_stack_page(p) +
-				   THREAD_SIZE, NULL);
+			void *stack = try_get_task_stack(p);
+			if (stack) {
+				scan_block(stack, stack + THREAD_SIZE, NULL);
+				put_task_stack(p);
+			}
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
 	}
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 1d05cb9..234676e 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -554,6 +554,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
 	err = memcg_init_list_lru(lru, memcg_aware);
 	if (err) {
 		kfree(lru->node);
+		/* Do this so a list_lru_destroy() doesn't crash: */
+		lru->node = NULL;
 		goto out;
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ae052b5..0f870ba 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1917,6 +1917,15 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		     current->flags & PF_EXITING))
 		goto force;
 
+	/*
+	 * Prevent unbounded recursion when reclaim operations need to
+	 * allocate memory. This might exceed the limits temporarily,
+	 * but we prefer facilitating memory reclaim and getting back
+	 * under the limit over triggering OOM kills in these cases.
+	 */
+	if (unlikely(current->flags & PF_MEMALLOC))
+		goto force;
+
 	if (unlikely(task_in_memcg_oom(current)))
 		goto nomem;
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9629273..cad4b91 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -268,7 +268,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
 	unsigned long i, pfn, end_pfn, nr_pages;
 	int node = pgdat->node_id;
 	struct page *page;
-	struct zone *zone;
 
 	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
 	page = virt_to_page(pgdat);
@@ -276,19 +275,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
 	for (i = 0; i < nr_pages; i++, page++)
 		get_page_bootmem(node, page, NODE_INFO);
 
-	zone = &pgdat->node_zones[0];
-	for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
-		if (zone_is_initialized(zone)) {
-			nr_pages = zone->wait_table_hash_nr_entries
-				* sizeof(wait_queue_head_t);
-			nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
-			page = virt_to_page(zone->wait_table);
-
-			for (i = 0; i < nr_pages; i++, page++)
-				get_page_bootmem(node, page, NODE_INFO);
-		}
-	}
-
 	pfn = pgdat->node_start_pfn;
 	end_pfn = pgdat_end_pfn(pgdat);
 
@@ -2131,7 +2117,6 @@ void try_offline_node(int nid)
 	unsigned long start_pfn = pgdat->node_start_pfn;
 	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
 	unsigned long pfn;
-	int i;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
 		unsigned long section_nr = pfn_to_section_nr(pfn);
@@ -2158,20 +2143,6 @@ void try_offline_node(int nid)
 	 */
 	node_set_offline(nid);
 	unregister_one_node(nid);
-
-	/* free waittable in each zone */
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		struct zone *zone = pgdat->node_zones + i;
-
-		/*
-		 * wait_table may be allocated from boot memory,
-		 * here only free if it's allocated by vmalloc.
-		 */
-		if (is_vmalloc_addr(zone->wait_table)) {
-			vfree(zone->wait_table);
-			zone->wait_table = NULL;
-		}
-	}
 }
 EXPORT_SYMBOL(try_offline_node);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2b3bf67..072d791 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -92,7 +92,7 @@ int _node_numa_mem_[MAX_NUMNODES];
 #endif
 
 #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
-volatile u64 latent_entropy __latent_entropy;
+volatile unsigned long latent_entropy __latent_entropy;
 EXPORT_SYMBOL(latent_entropy);
 #endif
 
@@ -4224,7 +4224,7 @@ static void show_migration_types(unsigned char type)
 	}
 
 	*p = '\0';
-	printk("(%s) ", tmp);
+	printk(KERN_CONT "(%s) ", tmp);
 }
 
 /*
@@ -4335,7 +4335,8 @@ void show_free_areas(unsigned int filter)
 			free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;
 
 		show_node(zone);
-		printk("%s"
+		printk(KERN_CONT
+			"%s"
 			" free:%lukB"
 			" min:%lukB"
 			" low:%lukB"
@@ -4382,8 +4383,8 @@ void show_free_areas(unsigned int filter)
 			K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
 		printk("lowmem_reserve[]:");
 		for (i = 0; i < MAX_NR_ZONES; i++)
-			printk(" %ld", zone->lowmem_reserve[i]);
-		printk("\n");
+			printk(KERN_CONT " %ld", zone->lowmem_reserve[i]);
+		printk(KERN_CONT "\n");
 	}
 
 	for_each_populated_zone(zone) {
@@ -4394,7 +4395,7 @@ void show_free_areas(unsigned int filter)
 		if (skip_free_areas_node(filter, zone_to_nid(zone)))
 			continue;
 		show_node(zone);
-		printk("%s: ", zone->name);
+		printk(KERN_CONT "%s: ", zone->name);
 
 		spin_lock_irqsave(&zone->lock, flags);
 		for (order = 0; order < MAX_ORDER; order++) {
@@ -4412,11 +4413,12 @@ void show_free_areas(unsigned int filter)
 		}
 		spin_unlock_irqrestore(&zone->lock, flags);
 		for (order = 0; order < MAX_ORDER; order++) {
-			printk("%lu*%lukB ", nr[order], K(1UL) << order);
+			printk(KERN_CONT "%lu*%lukB ",
+			       nr[order], K(1UL) << order);
 			if (nr[order])
 				show_migration_types(types[order]);
 		}
-		printk("= %lukB\n", K(total));
+		printk(KERN_CONT "= %lukB\n", K(total));
 	}
 
 	hugetlb_show_meminfo();
@@ -4977,72 +4979,6 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 }
 
 /*
- * Helper functions to size the waitqueue hash table.
- * Essentially these want to choose hash table sizes sufficiently
- * large so that collisions trying to wait on pages are rare.
- * But in fact, the number of active page waitqueues on typical
- * systems is ridiculously low, less than 200. So this is even
- * conservative, even though it seems large.
- *
- * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
- * waitqueues, i.e. the size of the waitq table given the number of pages.
- */
-#define PAGES_PER_WAITQUEUE	256
-
-#ifndef CONFIG_MEMORY_HOTPLUG
-static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
-{
-	unsigned long size = 1;
-
-	pages /= PAGES_PER_WAITQUEUE;
-
-	while (size < pages)
-		size <<= 1;
-
-	/*
-	 * Once we have dozens or even hundreds of threads sleeping
-	 * on IO we've got bigger problems than wait queue collision.
-	 * Limit the size of the wait table to a reasonable size.
-	 */
-	size = min(size, 4096UL);
-
-	return max(size, 4UL);
-}
-#else
-/*
- * A zone's size might be changed by hot-add, so it is not possible to determine
- * a suitable size for its wait_table.  So we use the maximum size now.
- *
- * The max wait table size = 4096 x sizeof(wait_queue_head_t).   ie:
- *
- *    i386 (preemption config)    : 4096 x 16 = 64Kbyte.
- *    ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte.
- *    ia64, x86-64 (preemption)   : 4096 x 24 = 96Kbyte.
- *
- * The maximum entries are prepared when a zone's memory is (512K + 256) pages
- * or more by the traditional way. (See above).  It equals:
- *
- *    i386, x86-64, powerpc(4K page size) : =  ( 2G + 1M)byte.
- *    ia64(16K page size)                 : =  ( 8G + 4M)byte.
- *    powerpc (64K page size)             : =  (32G +16M)byte.
- */
-static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
-{
-	return 4096UL;
-}
-#endif
-
-/*
- * This is an integer logarithm so that shifts can be used later
- * to extract the more random high bits from the multiplicative
- * hash function before the remainder is taken.
- */
-static inline unsigned long wait_table_bits(unsigned long size)
-{
-	return ffz(~size);
-}
-
-/*
  * Initially all pages are reserved - free ones are freed
  * up by free_all_bootmem() once the early boot process is
  * done. Non-atomic initialization, single-pass.
@@ -5304,49 +5240,6 @@ void __init setup_per_cpu_pageset(void)
 			alloc_percpu(struct per_cpu_nodestat);
 }
 
-static noinline __ref
-int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
-{
-	int i;
-	size_t alloc_size;
-
-	/*
-	 * The per-page waitqueue mechanism uses hashed waitqueues
-	 * per zone.
-	 */
-	zone->wait_table_hash_nr_entries =
-		 wait_table_hash_nr_entries(zone_size_pages);
-	zone->wait_table_bits =
-		wait_table_bits(zone->wait_table_hash_nr_entries);
-	alloc_size = zone->wait_table_hash_nr_entries
-					* sizeof(wait_queue_head_t);
-
-	if (!slab_is_available()) {
-		zone->wait_table = (wait_queue_head_t *)
-			memblock_virt_alloc_node_nopanic(
-				alloc_size, zone->zone_pgdat->node_id);
-	} else {
-		/*
-		 * This case means that a zone whose size was 0 gets new memory
-		 * via memory hot-add.
-		 * But it may be the case that a new node was hot-added.  In
-		 * this case vmalloc() will not be able to use this new node's
-		 * memory - this wait_table must be initialized to use this new
-		 * node itself as well.
-		 * To use this new node's memory, further consideration will be
-		 * necessary.
-		 */
-		zone->wait_table = vmalloc(alloc_size);
-	}
-	if (!zone->wait_table)
-		return -ENOMEM;
-
-	for (i = 0; i < zone->wait_table_hash_nr_entries; ++i)
-		init_waitqueue_head(zone->wait_table + i);
-
-	return 0;
-}
-
 static __meminit void zone_pcp_init(struct zone *zone)
 {
 	/*
@@ -5367,10 +5260,7 @@ int __meminit init_currently_empty_zone(struct zone *zone,
 					unsigned long size)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
-	int ret;
-	ret = zone_wait_table_init(zone, size);
-	if (ret)
-		return ret;
+
 	pgdat->nr_zones = zone_idx(zone) + 1;
 
 	zone->zone_start_pfn = zone_start_pfn;
@@ -5382,6 +5272,7 @@ int __meminit init_currently_empty_zone(struct zone *zone,
 			zone_start_pfn, (zone_start_pfn + size));
 
 	zone_init_free_lists(zone);
+	zone->initialized = 1;
 
 	return 0;
 }
diff --git a/mm/slab.c b/mm/slab.c
index 090fb26..0b0550c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -233,6 +233,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent)
 	spin_lock_init(&parent->list_lock);
 	parent->free_objects = 0;
 	parent->free_touched = 0;
+	parent->num_slabs = 0;
 }
 
 #define MAKE_LIST(cachep, listp, slab, nodeid)				\
@@ -966,7 +967,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep,
 	 * guaranteed to be valid until irq is re-enabled, because it will be
 	 * freed after synchronize_sched().
 	 */
-	if (force_change)
+	if (old_shared && force_change)
 		synchronize_sched();
 
 fail:
@@ -1382,24 +1383,27 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
 	for_each_kmem_cache_node(cachep, node, n) {
 		unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
 		unsigned long active_slabs = 0, num_slabs = 0;
+		unsigned long num_slabs_partial = 0, num_slabs_free = 0;
+		unsigned long num_slabs_full;
 
 		spin_lock_irqsave(&n->list_lock, flags);
-		list_for_each_entry(page, &n->slabs_full, lru) {
-			active_objs += cachep->num;
-			active_slabs++;
-		}
+		num_slabs = n->num_slabs;
 		list_for_each_entry(page, &n->slabs_partial, lru) {
 			active_objs += page->active;
-			active_slabs++;
+			num_slabs_partial++;
 		}
 		list_for_each_entry(page, &n->slabs_free, lru)
-			num_slabs++;
+			num_slabs_free++;
 
 		free_objects += n->free_objects;
 		spin_unlock_irqrestore(&n->list_lock, flags);
 
-		num_slabs += active_slabs;
 		num_objs = num_slabs * cachep->num;
+		active_slabs = num_slabs - num_slabs_free;
+		num_slabs_full = num_slabs -
+			(num_slabs_partial + num_slabs_free);
+		active_objs += (num_slabs_full * cachep->num);
+
 		pr_warn("  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
 			node, active_slabs, num_slabs, active_objs, num_objs,
 			free_objects);
@@ -2314,6 +2318,7 @@ static int drain_freelist(struct kmem_cache *cache,
 
 		page = list_entry(p, struct page, lru);
 		list_del(&page->lru);
+		n->num_slabs--;
 		/*
 		 * Safe to drop the lock. The slab is no longer linked
 		 * to the cache.
@@ -2752,6 +2757,8 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page)
 		list_add_tail(&page->lru, &(n->slabs_free));
 	else
 		fixup_slab_list(cachep, n, page, &list);
+
+	n->num_slabs++;
 	STATS_INC_GROWN(cachep);
 	n->free_objects += cachep->num - page->active;
 	spin_unlock(&n->list_lock);
@@ -3443,6 +3450,7 @@ static void free_block(struct kmem_cache *cachep, void **objpp,
 
 		page = list_last_entry(&n->slabs_free, struct page, lru);
 		list_move(&page->lru, list);
+		n->num_slabs--;
 	}
 }
 
@@ -4099,6 +4107,8 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 	unsigned long num_objs;
 	unsigned long active_slabs = 0;
 	unsigned long num_slabs, free_objects = 0, shared_avail = 0;
+	unsigned long num_slabs_partial = 0, num_slabs_free = 0;
+	unsigned long num_slabs_full = 0;
 	const char *name;
 	char *error = NULL;
 	int node;
@@ -4111,33 +4121,34 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 		check_irq_on();
 		spin_lock_irq(&n->list_lock);
 
-		list_for_each_entry(page, &n->slabs_full, lru) {
-			if (page->active != cachep->num && !error)
-				error = "slabs_full accounting error";
-			active_objs += cachep->num;
-			active_slabs++;
-		}
+		num_slabs += n->num_slabs;
+
 		list_for_each_entry(page, &n->slabs_partial, lru) {
 			if (page->active == cachep->num && !error)
 				error = "slabs_partial accounting error";
 			if (!page->active && !error)
 				error = "slabs_partial accounting error";
 			active_objs += page->active;
-			active_slabs++;
+			num_slabs_partial++;
 		}
+
 		list_for_each_entry(page, &n->slabs_free, lru) {
 			if (page->active && !error)
 				error = "slabs_free accounting error";
-			num_slabs++;
+			num_slabs_free++;
 		}
+
 		free_objects += n->free_objects;
 		if (n->shared)
 			shared_avail += n->shared->avail;
 
 		spin_unlock_irq(&n->list_lock);
 	}
-	num_slabs += active_slabs;
 	num_objs = num_slabs * cachep->num;
+	active_slabs = num_slabs - num_slabs_free;
+	num_slabs_full = num_slabs - (num_slabs_partial + num_slabs_free);
+	active_objs += (num_slabs_full * cachep->num);
+
 	if (num_objs - active_objs != free_objects && !error)
 		error = "free_objects accounting error";
 
diff --git a/mm/slab.h b/mm/slab.h
index 9653f2e..bc05fdc 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -432,6 +432,7 @@ struct kmem_cache_node {
 	struct list_head slabs_partial;	/* partial list first, better asm code */
 	struct list_head slabs_full;
 	struct list_head slabs_free;
+	unsigned long num_slabs;
 	unsigned long free_objects;
 	unsigned int free_limit;
 	unsigned int colour_next;	/* Per-node cache coloring */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 744f926..76fda22 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3043,7 +3043,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					    sc.gfp_mask,
 					    sc.reclaim_idx);
 
+	current->flags |= PF_MEMALLOC;
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+	current->flags &= ~PF_MEMALLOC;
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 8de138d..f2531ad 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -664,7 +664,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, sizeof(*vhdr));
 	skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 08ce361..e034afb 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -652,7 +652,6 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
 			batadv_softif_destroy_sysfs(hard_iface->soft_iface);
 	}
 
-	hard_iface->soft_iface = NULL;
 	batadv_hardif_put(hard_iface);
 
 out:
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
index e0e1a88..d2905a8 100644
--- a/net/batman-adv/log.h
+++ b/net/batman-adv/log.h
@@ -63,7 +63,7 @@ enum batadv_dbg_level {
 	BATADV_DBG_NC		= BIT(5),
 	BATADV_DBG_MCAST	= BIT(6),
 	BATADV_DBG_TP_METER	= BIT(7),
-	BATADV_DBG_ALL		= 127,
+	BATADV_DBG_ALL		= 255,
 };
 
 #ifdef CONFIG_BATMAN_ADV_DEBUG
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 5f3bfc4..7c8d160 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -544,7 +544,7 @@ batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface,
 	if (bat_priv->algo_ops->neigh.hardif_init)
 		bat_priv->algo_ops->neigh.hardif_init(hardif_neigh);
 
-	hlist_add_head(&hardif_neigh->list, &hard_iface->neigh_list);
+	hlist_add_head_rcu(&hardif_neigh->list, &hard_iface->neigh_list);
 
 out:
 	spin_unlock_bh(&hard_iface->neigh_list_lock);
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index e228842..1015d9c 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -969,41 +969,38 @@ void __hci_req_enable_advertising(struct hci_request *req)
 	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
 }
 
-static u8 append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len)
+u8 append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len)
 {
-	size_t complete_len;
 	size_t short_len;
-	int max_len;
+	size_t complete_len;
 
-	max_len = HCI_MAX_AD_LENGTH - ad_len - 2;
+	/* no space left for name (+ NULL + type + len) */
+	if ((HCI_MAX_AD_LENGTH - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3)
+		return ad_len;
+
+	/* use complete name if present and fits */
 	complete_len = strlen(hdev->dev_name);
-	short_len = strlen(hdev->short_name);
-
-	/* no space left for name */
-	if (max_len < 1)
-		return ad_len;
-
-	/* no name set */
-	if (!complete_len)
-		return ad_len;
-
-	/* complete name fits and is eq to max short name len or smaller */
-	if (complete_len <= max_len &&
-	    complete_len <= HCI_MAX_SHORT_NAME_LENGTH) {
+	if (complete_len && complete_len <= HCI_MAX_SHORT_NAME_LENGTH)
 		return eir_append_data(ptr, ad_len, EIR_NAME_COMPLETE,
-				       hdev->dev_name, complete_len);
-	}
+				       hdev->dev_name, complete_len + 1);
 
-	/* short name set and fits */
-	if (short_len && short_len <= max_len) {
+	/* use short name if present */
+	short_len = strlen(hdev->short_name);
+	if (short_len)
 		return eir_append_data(ptr, ad_len, EIR_NAME_SHORT,
-				       hdev->short_name, short_len);
-	}
+				       hdev->short_name, short_len + 1);
 
-	/* no short name set so shorten complete name */
-	if (!short_len) {
-		return eir_append_data(ptr, ad_len, EIR_NAME_SHORT,
-				       hdev->dev_name, max_len);
+	/* use shortened full name if present, we already know that name
+	 * is longer then HCI_MAX_SHORT_NAME_LENGTH
+	 */
+	if (complete_len) {
+		u8 name[HCI_MAX_SHORT_NAME_LENGTH + 1];
+
+		memcpy(name, hdev->dev_name, HCI_MAX_SHORT_NAME_LENGTH);
+		name[HCI_MAX_SHORT_NAME_LENGTH] = '\0';
+
+		return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, name,
+				       sizeof(name));
 	}
 
 	return ad_len;
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 6b06629..dde77bd 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -106,6 +106,8 @@ static inline void hci_update_background_scan(struct hci_dev *hdev)
 void hci_request_setup(struct hci_dev *hdev);
 void hci_request_cancel_all(struct hci_dev *hdev);
 
+u8 append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len);
+
 static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type,
 				  u8 *data, u8 data_len)
 {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7360380..1fba2a0 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -6017,7 +6017,15 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev,
 	return err;
 }
 
-static u8 tlv_data_max_len(u32 adv_flags, bool is_adv_data)
+static u8 calculate_name_len(struct hci_dev *hdev)
+{
+	u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 3];
+
+	return append_local_name(hdev, buf, 0);
+}
+
+static u8 tlv_data_max_len(struct hci_dev *hdev, u32 adv_flags,
+			   bool is_adv_data)
 {
 	u8 max_len = HCI_MAX_AD_LENGTH;
 
@@ -6030,9 +6038,8 @@ static u8 tlv_data_max_len(u32 adv_flags, bool is_adv_data)
 		if (adv_flags & MGMT_ADV_FLAG_TX_POWER)
 			max_len -= 3;
 	} else {
-		/* at least 1 byte of name should fit in */
 		if (adv_flags & MGMT_ADV_FLAG_LOCAL_NAME)
-			max_len -= 3;
+			max_len -= calculate_name_len(hdev);
 
 		if (adv_flags & (MGMT_ADV_FLAG_APPEARANCE))
 			max_len -= 4;
@@ -6063,12 +6070,13 @@ static bool appearance_managed(u32 adv_flags)
 	return adv_flags & MGMT_ADV_FLAG_APPEARANCE;
 }
 
-static bool tlv_data_is_valid(u32 adv_flags, u8 *data, u8 len, bool is_adv_data)
+static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data,
+			      u8 len, bool is_adv_data)
 {
 	int i, cur_len;
 	u8 max_len;
 
-	max_len = tlv_data_max_len(adv_flags, is_adv_data);
+	max_len = tlv_data_max_len(hdev, adv_flags, is_adv_data);
 
 	if (len > max_len)
 		return false;
@@ -6215,8 +6223,8 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 		goto unlock;
 	}
 
-	if (!tlv_data_is_valid(flags, cp->data, cp->adv_data_len, true) ||
-	    !tlv_data_is_valid(flags, cp->data + cp->adv_data_len,
+	if (!tlv_data_is_valid(hdev, flags, cp->data, cp->adv_data_len, true) ||
+	    !tlv_data_is_valid(hdev, flags, cp->data + cp->adv_data_len,
 			       cp->scan_rsp_len, false)) {
 		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
 				      MGMT_STATUS_INVALID_PARAMS);
@@ -6429,8 +6437,8 @@ static int get_adv_size_info(struct sock *sk, struct hci_dev *hdev,
 
 	rp.instance = cp->instance;
 	rp.flags = cp->flags;
-	rp.max_adv_data_len = tlv_data_max_len(flags, true);
-	rp.max_scan_rsp_len = tlv_data_max_len(flags, false);
+	rp.max_adv_data_len = tlv_data_max_len(hdev, flags, true);
+	rp.max_scan_rsp_len = tlv_data_max_len(hdev, flags, false);
 
 	err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_ADV_SIZE_INFO,
 				MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index c5fea93..2136e45 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -972,13 +972,12 @@ static void br_multicast_enable(struct bridge_mcast_own_query *query)
 		mod_timer(&query->timer, jiffies);
 }
 
-void br_multicast_enable_port(struct net_bridge_port *port)
+static void __br_multicast_enable_port(struct net_bridge_port *port)
 {
 	struct net_bridge *br = port->br;
 
-	spin_lock(&br->multicast_lock);
 	if (br->multicast_disabled || !netif_running(br->dev))
-		goto out;
+		return;
 
 	br_multicast_enable(&port->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -987,8 +986,14 @@ void br_multicast_enable_port(struct net_bridge_port *port)
 	if (port->multicast_router == MDB_RTR_TYPE_PERM &&
 	    hlist_unhashed(&port->rlist))
 		br_multicast_add_router(br, port);
+}
 
-out:
+void br_multicast_enable_port(struct net_bridge_port *port)
+{
+	struct net_bridge *br = port->br;
+
+	spin_lock(&br->multicast_lock);
+	__br_multicast_enable_port(port);
 	spin_unlock(&br->multicast_lock);
 }
 
@@ -1994,8 +1999,9 @@ static void br_multicast_start_querier(struct net_bridge *br,
 
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 {
-	int err = 0;
 	struct net_bridge_mdb_htable *mdb;
+	struct net_bridge_port *port;
+	int err = 0;
 
 	spin_lock_bh(&br->multicast_lock);
 	if (br->multicast_disabled == !val)
@@ -2023,10 +2029,9 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 			goto rollback;
 	}
 
-	br_multicast_start_querier(br, &br->ip4_own_query);
-#if IS_ENABLED(CONFIG_IPV6)
-	br_multicast_start_querier(br, &br->ip6_own_query);
-#endif
+	br_multicast_open(br);
+	list_for_each_entry(port, &br->port_list, list)
+		__br_multicast_enable_port(port);
 
 unlock:
 	spin_unlock_bh(&br->multicast_lock);
diff --git a/net/core/dev.c b/net/core/dev.c
index 4bc19a1..820bac2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3035,6 +3035,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
 	}
 	return head;
 }
+EXPORT_SYMBOL_GPL(validate_xmit_skb_list);
 
 static void qdisc_pkt_len_init(struct sk_buff *skb)
 {
@@ -4511,6 +4512,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->encap_mark = 0;
+		NAPI_GRO_CB(skb)->recursion_counter = 0;
 		NAPI_GRO_CB(skb)->is_fou = 0;
 		NAPI_GRO_CB(skb)->is_atomic = 1;
 		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
@@ -5511,10 +5513,14 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
 {
 	struct netdev_adjacent *lower;
 
-	lower = list_first_or_null_rcu(&dev->all_adj_list.lower,
-				       struct netdev_adjacent, list);
+	lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
 
-	return lower ? lower->dev : NULL;
+	if (&lower->list == &dev->all_adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
+
+	return lower->dev;
 }
 EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 1a7b80f..ab193e5 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -246,15 +246,13 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	case htons(ETH_P_8021AD):
 	case htons(ETH_P_8021Q): {
 		const struct vlan_hdr *vlan;
+		struct vlan_hdr _vlan;
+		bool vlan_tag_present = skb && skb_vlan_tag_present(skb);
 
-		if (skb_vlan_tag_present(skb))
+		if (vlan_tag_present)
 			proto = skb->protocol;
 
-		if (!skb_vlan_tag_present(skb) ||
-		    proto == cpu_to_be16(ETH_P_8021Q) ||
-		    proto == cpu_to_be16(ETH_P_8021AD)) {
-			struct vlan_hdr _vlan;
-
+		if (!vlan_tag_present || eth_type_vlan(skb->protocol)) {
 			vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan),
 						    data, hlen, &_vlan);
 			if (!vlan)
@@ -272,7 +270,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 							     FLOW_DISSECTOR_KEY_VLAN,
 							     target_container);
 
-			if (skb_vlan_tag_present(skb)) {
+			if (vlan_tag_present) {
 				key_vlan->vlan_id = skb_vlan_tag_get_id(skb);
 				key_vlan->vlan_priority =
 					(skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 989434f..f61c0e0 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -215,13 +215,14 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id);
  */
 int peernet2id_alloc(struct net *net, struct net *peer)
 {
+	unsigned long flags;
 	bool alloc;
 	int id;
 
-	spin_lock_bh(&net->nsid_lock);
+	spin_lock_irqsave(&net->nsid_lock, flags);
 	alloc = atomic_read(&peer->count) == 0 ? false : true;
 	id = __peernet2id_alloc(net, peer, &alloc);
-	spin_unlock_bh(&net->nsid_lock);
+	spin_unlock_irqrestore(&net->nsid_lock, flags);
 	if (alloc && id >= 0)
 		rtnl_net_notifyid(net, RTM_NEWNSID, id);
 	return id;
@@ -230,11 +231,12 @@ int peernet2id_alloc(struct net *net, struct net *peer)
 /* This function returns, if assigned, the id of a peer netns. */
 int peernet2id(struct net *net, struct net *peer)
 {
+	unsigned long flags;
 	int id;
 
-	spin_lock_bh(&net->nsid_lock);
+	spin_lock_irqsave(&net->nsid_lock, flags);
 	id = __peernet2id(net, peer);
-	spin_unlock_bh(&net->nsid_lock);
+	spin_unlock_irqrestore(&net->nsid_lock, flags);
 	return id;
 }
 EXPORT_SYMBOL(peernet2id);
@@ -249,17 +251,18 @@ bool peernet_has_id(struct net *net, struct net *peer)
 
 struct net *get_net_ns_by_id(struct net *net, int id)
 {
+	unsigned long flags;
 	struct net *peer;
 
 	if (id < 0)
 		return NULL;
 
 	rcu_read_lock();
-	spin_lock_bh(&net->nsid_lock);
+	spin_lock_irqsave(&net->nsid_lock, flags);
 	peer = idr_find(&net->netns_ids, id);
 	if (peer)
 		get_net(peer);
-	spin_unlock_bh(&net->nsid_lock);
+	spin_unlock_irqrestore(&net->nsid_lock, flags);
 	rcu_read_unlock();
 
 	return peer;
@@ -422,17 +425,17 @@ static void cleanup_net(struct work_struct *work)
 		for_each_net(tmp) {
 			int id;
 
-			spin_lock_bh(&tmp->nsid_lock);
+			spin_lock_irq(&tmp->nsid_lock);
 			id = __peernet2id(tmp, net);
 			if (id >= 0)
 				idr_remove(&tmp->netns_ids, id);
-			spin_unlock_bh(&tmp->nsid_lock);
+			spin_unlock_irq(&tmp->nsid_lock);
 			if (id >= 0)
 				rtnl_net_notifyid(tmp, RTM_DELNSID, id);
 		}
-		spin_lock_bh(&net->nsid_lock);
+		spin_lock_irq(&net->nsid_lock);
 		idr_destroy(&net->netns_ids);
-		spin_unlock_bh(&net->nsid_lock);
+		spin_unlock_irq(&net->nsid_lock);
 
 	}
 	rtnl_unlock();
@@ -561,6 +564,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tb[NETNSA_MAX + 1];
+	unsigned long flags;
 	struct net *peer;
 	int nsid, err;
 
@@ -581,15 +585,15 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (IS_ERR(peer))
 		return PTR_ERR(peer);
 
-	spin_lock_bh(&net->nsid_lock);
+	spin_lock_irqsave(&net->nsid_lock, flags);
 	if (__peernet2id(net, peer) >= 0) {
-		spin_unlock_bh(&net->nsid_lock);
+		spin_unlock_irqrestore(&net->nsid_lock, flags);
 		err = -EEXIST;
 		goto out;
 	}
 
 	err = alloc_netid(net, peer, nsid);
-	spin_unlock_bh(&net->nsid_lock);
+	spin_unlock_irqrestore(&net->nsid_lock, flags);
 	if (err >= 0) {
 		rtnl_net_notifyid(net, RTM_NEWNSID, err);
 		err = 0;
@@ -711,10 +715,11 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
 		.idx = 0,
 		.s_idx = cb->args[0],
 	};
+	unsigned long flags;
 
-	spin_lock_bh(&net->nsid_lock);
+	spin_lock_irqsave(&net->nsid_lock, flags);
 	idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb);
-	spin_unlock_bh(&net->nsid_lock);
+	spin_unlock_irqrestore(&net->nsid_lock, flags);
 
 	cb->args[0] = net_cb.idx;
 	return skb->len;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 5219a9e..306b8f0 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -216,8 +216,8 @@
 #define M_QUEUE_XMIT		2	/* Inject packet into qdisc */
 
 /* If lock -- protects updating of if_list */
-#define   if_lock(t)           spin_lock(&(t->if_lock));
-#define   if_unlock(t)           spin_unlock(&(t->if_lock));
+#define   if_lock(t)           mutex_lock(&(t->if_lock));
+#define   if_unlock(t)           mutex_unlock(&(t->if_lock));
 
 /* Used to help with determining the pkts on receive */
 #define PKTGEN_MAGIC 0xbe9be955
@@ -423,7 +423,7 @@ struct pktgen_net {
 };
 
 struct pktgen_thread {
-	spinlock_t if_lock;		/* for list of devices */
+	struct mutex if_lock;		/* for list of devices */
 	struct list_head if_list;	/* All device here */
 	struct list_head th_list;
 	struct task_struct *tsk;
@@ -2010,11 +2010,13 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 {
 	struct pktgen_thread *t;
 
+	mutex_lock(&pktgen_thread_lock);
+
 	list_for_each_entry(t, &pn->pktgen_threads, th_list) {
 		struct pktgen_dev *pkt_dev;
 
-		rcu_read_lock();
-		list_for_each_entry_rcu(pkt_dev, &t->if_list, list) {
+		if_lock(t);
+		list_for_each_entry(pkt_dev, &t->if_list, list) {
 			if (pkt_dev->odev != dev)
 				continue;
 
@@ -2029,8 +2031,9 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 				       dev->name);
 			break;
 		}
-		rcu_read_unlock();
+		if_unlock(t);
 	}
+	mutex_unlock(&pktgen_thread_lock);
 }
 
 static int pktgen_device_event(struct notifier_block *unused,
@@ -3762,7 +3765,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn)
 		return -ENOMEM;
 	}
 
-	spin_lock_init(&t->if_lock);
+	mutex_init(&t->if_lock);
 	t->cpu = cpu;
 
 	INIT_LIST_HEAD(&t->if_list);
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index e92b759..9a1a352 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -129,7 +129,6 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 
 	return 0;
 }
-EXPORT_SYMBOL(reuseport_add_sock);
 
 static void reuseport_free_rcu(struct rcu_head *head)
 {
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 66dff5e..02acfff 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -439,7 +439,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, sizeof(*eh));
 	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 5ee1d43..4ebe2aa 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -300,10 +300,6 @@ static void hsr_forward_do(struct hsr_frame_info *frame)
 static void check_local_dest(struct hsr_priv *hsr, struct sk_buff *skb,
 			     struct hsr_frame_info *frame)
 {
-	struct net_device *master_dev;
-
-	master_dev = hsr_port_get_hsr(hsr, HSR_PT_MASTER)->dev;
-
 	if (hsr_addr_is_self(hsr, eth_hdr(skb)->h_dest)) {
 		frame->is_local_exclusive = true;
 		skb->pkt_type = PACKET_HOST;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1effc98..9648c97 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1391,7 +1391,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index cf50f7e..030d153 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -249,7 +249,7 @@ static struct sk_buff **fou_gro_receive(struct sock *sk,
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out_unlock;
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -441,7 +441,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 	if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
 		goto out_unlock;
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 	flush = 0;
 
 out_unlock:
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 96e0efe..d5cac99 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -229,7 +229,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
 	skb_gro_postpull_rcsum(skb, greh, grehlen);
 
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 	flush = 0;
 
 out_unlock:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 77c20a4..ca97835 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -25,6 +25,7 @@
 #include <net/inet_hashtables.h>
 #include <net/secure_seq.h>
 #include <net/ip.h>
+#include <net/tcp.h>
 #include <net/sock_reuseport.h>
 
 static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
@@ -172,7 +173,7 @@ EXPORT_SYMBOL_GPL(__inet_inherit_port);
 
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum, const __be32 daddr,
-				const int dif)
+				const int dif, bool exact_dif)
 {
 	int score = -1;
 	struct inet_sock *inet = inet_sk(sk);
@@ -186,7 +187,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				return -1;
 			score += 4;
 		}
-		if (sk->sk_bound_dev_if) {
+		if (sk->sk_bound_dev_if || exact_dif) {
 			if (sk->sk_bound_dev_if != dif)
 				return -1;
 			score += 4;
@@ -215,11 +216,12 @@ struct sock *__inet_lookup_listener(struct net *net,
 	unsigned int hash = inet_lhashfn(net, hnum);
 	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
 	int score, hiscore = 0, matches = 0, reuseport = 0;
+	bool exact_dif = inet_exact_dif_match(net, skb);
 	struct sock *sk, *result = NULL;
 	u32 phash = 0;
 
 	sk_for_each_rcu(sk, &ilb->head) {
-		score = compute_score(sk, net, hnum, daddr, dif);
+		score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
 		if (score > hiscore) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 05d1058..03e7f73 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -538,7 +538,6 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 {
 	struct iphdr *iph;
 	int ptr;
-	struct net_device *dev;
 	struct sk_buff *skb2;
 	unsigned int mtu, hlen, left, len, ll_rs;
 	int offset;
@@ -546,8 +545,6 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	struct rtable *rt = skb_rtable(skb);
 	int err = 0;
 
-	dev = rt->dst.dev;
-
 	/* for offloaded checksums cleanup checksum before fragmentation */
 	if (skb->ip_summed == CHECKSUM_PARTIAL &&
 	    (err = skb_checksum_help(skb)))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index af49197..b8a2d63 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -98,7 +98,7 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
 }
 
 static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
-				  int offset)
+				  int tlen, int offset)
 {
 	__wsum csum = skb->csum;
 
@@ -106,8 +106,9 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
 		return;
 
 	if (offset != 0)
-		csum = csum_sub(csum, csum_partial(skb_transport_header(skb),
-						   offset, 0));
+		csum = csum_sub(csum,
+				csum_partial(skb_transport_header(skb) + tlen,
+					     offset, 0));
 
 	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
 }
@@ -153,7 +154,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 }
 
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
-			 int offset)
+			 int tlen, int offset)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
 	unsigned int flags = inet->cmsg_flags;
@@ -216,7 +217,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
 	}
 
 	if (flags & IP_CMSG_CHECKSUM)
-		ip_cmsg_recv_checksum(msg, skb, offset);
+		ip_cmsg_recv_checksum(msg, skb, tlen, offset);
 }
 EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7cf7d6e..205e200 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -994,7 +994,7 @@ struct proto ping_prot = {
 	.init =		ping_init_sock,
 	.close =	ping_close,
 	.connect =	ip4_datagram_connect,
-	.disconnect =	udp_disconnect,
+	.disconnect =	__udp_disconnect,
 	.setsockopt =	ip_setsockopt,
 	.getsockopt =	ip_getsockopt,
 	.sendmsg =	ping_v4_sendmsg,
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 90a85c9..ecbe5a7 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -918,7 +918,7 @@ struct proto raw_prot = {
 	.close		   = raw_close,
 	.destroy	   = raw_destroy,
 	.connect	   = ip4_datagram_connect,
-	.disconnect	   = udp_disconnect,
+	.disconnect	   = __udp_disconnect,
 	.ioctl		   = raw_ioctl,
 	.init		   = raw_init,
 	.setsockopt	   = raw_setsockopt,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1cb67de..80bc36b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -96,11 +96,11 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
 }
 
 /* Update system visible IP port range */
@@ -109,10 +109,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 	kgid_t *data = table->data;
 	struct net *net =
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
-	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	write_seqlock(&net->ipv4.ping_group_range.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock(&net->ipv4.ping_group_range.lock);
 }
 
 /* Validate changes from /proc interface. */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bd5e8d1..61b7be3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -86,7 +86,6 @@
 
 int sysctl_tcp_tw_reuse __read_mostly;
 int sysctl_tcp_low_latency __read_mostly;
-EXPORT_SYMBOL(sysctl_tcp_low_latency);
 
 #ifdef CONFIG_TCP_MD5SIG
 static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
@@ -1887,7 +1886,6 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct inet_listen_hashbucket *ilb;
-	struct inet_connection_sock *icsk;
 	struct sock *sk = cur;
 
 	if (!sk) {
@@ -1909,7 +1907,6 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 			continue;
 		if (sk->sk_family == st->family)
 			return sk;
-		icsk = inet_csk(sk);
 	}
 	spin_unlock_bh(&ilb->lock);
 	st->offset = 0;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7d96dc2..d123d68 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1322,7 +1322,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
-		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr) + off);
+		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr), off);
 
 	err = copied;
 	if (flags & MSG_TRUNC)
@@ -1345,7 +1345,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 	goto try_again;
 }
 
-int udp_disconnect(struct sock *sk, int flags)
+int __udp_disconnect(struct sock *sk, int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	/*
@@ -1367,6 +1367,15 @@ int udp_disconnect(struct sock *sk, int flags)
 	sk_dst_reset(sk);
 	return 0;
 }
+EXPORT_SYMBOL(__udp_disconnect);
+
+int udp_disconnect(struct sock *sk, int flags)
+{
+	lock_sock(sk);
+	__udp_disconnect(sk, flags);
+	release_sock(sk);
+	return 0;
+}
 EXPORT_SYMBOL(udp_disconnect);
 
 void udp_lib_unhash(struct sock *sk)
@@ -2193,7 +2202,7 @@ int udp_abort(struct sock *sk, int err)
 
 	sk->sk_err = err;
 	sk->sk_error_report(sk);
-	udp_disconnect(sk, 0);
+	__udp_disconnect(sk, 0);
 
 	release_sock(sk);
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f9333c9..b2be1d9 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -295,7 +295,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
-	pp = udp_sk(sk)->gro_receive(sk, head, skb);
+	pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d8983e1..060dd99 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -147,9 +147,8 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev)
 }
 #endif
 
-static void __ipv6_regen_rndid(struct inet6_dev *idev);
-static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
-static void ipv6_regen_rndid(unsigned long data);
+static void ipv6_regen_rndid(struct inet6_dev *idev);
+static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
 
 static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
 static int ipv6_count_addresses(struct inet6_dev *idev);
@@ -409,9 +408,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 		goto err_release;
 	}
 
-	/* One reference from device.  We must do this before
-	 * we invoke __ipv6_regen_rndid().
-	 */
+	/* One reference from device. */
 	in6_dev_hold(ndev);
 
 	if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
@@ -425,17 +422,15 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 #endif
 
 	INIT_LIST_HEAD(&ndev->tempaddr_list);
-	setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev);
+	ndev->desync_factor = U32_MAX;
 	if ((dev->flags&IFF_LOOPBACK) ||
 	    dev->type == ARPHRD_TUNNEL ||
 	    dev->type == ARPHRD_TUNNEL6 ||
 	    dev->type == ARPHRD_SIT ||
 	    dev->type == ARPHRD_NONE) {
 		ndev->cnf.use_tempaddr = -1;
-	} else {
-		in6_dev_hold(ndev);
-		ipv6_regen_rndid((unsigned long) ndev);
-	}
+	} else
+		ipv6_regen_rndid(ndev);
 
 	ndev->token = in6addr_any;
 
@@ -447,7 +442,6 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	err = addrconf_sysctl_register(ndev);
 	if (err) {
 		ipv6_mc_destroy_dev(ndev);
-		del_timer(&ndev->regen_timer);
 		snmp6_unregister_dev(ndev);
 		goto err_release;
 	}
@@ -1190,6 +1184,8 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i
 	int ret = 0;
 	u32 addr_flags;
 	unsigned long now = jiffies;
+	long max_desync_factor;
+	s32 cnf_temp_preferred_lft;
 
 	write_lock_bh(&idev->lock);
 	if (ift) {
@@ -1222,23 +1218,42 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i
 	}
 	in6_ifa_hold(ifp);
 	memcpy(addr.s6_addr, ifp->addr.s6_addr, 8);
-	__ipv6_try_regen_rndid(idev, tmpaddr);
+	ipv6_try_regen_rndid(idev, tmpaddr);
 	memcpy(&addr.s6_addr[8], idev->rndid, 8);
 	age = (now - ifp->tstamp) / HZ;
-	tmp_valid_lft = min_t(__u32,
-			      ifp->valid_lft,
-			      idev->cnf.temp_valid_lft + age);
-	tmp_prefered_lft = min_t(__u32,
-				 ifp->prefered_lft,
-				 idev->cnf.temp_prefered_lft + age -
-				 idev->cnf.max_desync_factor);
-	tmp_plen = ifp->prefix_len;
-	tmp_tstamp = ifp->tstamp;
-	spin_unlock_bh(&ifp->lock);
 
 	regen_advance = idev->cnf.regen_max_retry *
 			idev->cnf.dad_transmits *
 			NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
+
+	/* recalculate max_desync_factor each time and update
+	 * idev->desync_factor if it's larger
+	 */
+	cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft);
+	max_desync_factor = min_t(__u32,
+				  idev->cnf.max_desync_factor,
+				  cnf_temp_preferred_lft - regen_advance);
+
+	if (unlikely(idev->desync_factor > max_desync_factor)) {
+		if (max_desync_factor > 0) {
+			get_random_bytes(&idev->desync_factor,
+					 sizeof(idev->desync_factor));
+			idev->desync_factor %= max_desync_factor;
+		} else {
+			idev->desync_factor = 0;
+		}
+	}
+
+	tmp_valid_lft = min_t(__u32,
+			      ifp->valid_lft,
+			      idev->cnf.temp_valid_lft + age);
+	tmp_prefered_lft = cnf_temp_preferred_lft + age -
+			    idev->desync_factor;
+	tmp_prefered_lft = min_t(__u32, ifp->prefered_lft, tmp_prefered_lft);
+	tmp_plen = ifp->prefix_len;
+	tmp_tstamp = ifp->tstamp;
+	spin_unlock_bh(&ifp->lock);
+
 	write_unlock_bh(&idev->lock);
 
 	/* A temporary address is created only if this calculated Preferred
@@ -2150,7 +2165,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev)
 }
 
 /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */
-static void __ipv6_regen_rndid(struct inet6_dev *idev)
+static void ipv6_regen_rndid(struct inet6_dev *idev)
 {
 regen:
 	get_random_bytes(idev->rndid, sizeof(idev->rndid));
@@ -2179,43 +2194,10 @@ static void __ipv6_regen_rndid(struct inet6_dev *idev)
 	}
 }
 
-static void ipv6_regen_rndid(unsigned long data)
-{
-	struct inet6_dev *idev = (struct inet6_dev *) data;
-	unsigned long expires;
-
-	rcu_read_lock_bh();
-	write_lock_bh(&idev->lock);
-
-	if (idev->dead)
-		goto out;
-
-	__ipv6_regen_rndid(idev);
-
-	expires = jiffies +
-		idev->cnf.temp_prefered_lft * HZ -
-		idev->cnf.regen_max_retry * idev->cnf.dad_transmits *
-		NEIGH_VAR(idev->nd_parms, RETRANS_TIME) -
-		idev->cnf.max_desync_factor * HZ;
-	if (time_before(expires, jiffies)) {
-		pr_warn("%s: too short regeneration interval; timer disabled for %s\n",
-			__func__, idev->dev->name);
-		goto out;
-	}
-
-	if (!mod_timer(&idev->regen_timer, expires))
-		in6_dev_hold(idev);
-
-out:
-	write_unlock_bh(&idev->lock);
-	rcu_read_unlock_bh();
-	in6_dev_put(idev);
-}
-
-static void  __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
+static void  ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
 {
 	if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0)
-		__ipv6_regen_rndid(idev);
+		ipv6_regen_rndid(idev);
 }
 
 /*
@@ -2356,7 +2338,7 @@ static void manage_tempaddrs(struct inet6_dev *idev,
 			max_valid = 0;
 
 		max_prefered = idev->cnf.temp_prefered_lft -
-			       idev->cnf.max_desync_factor - age;
+			       idev->desync_factor - age;
 		if (max_prefered < 0)
 			max_prefered = 0;
 
@@ -3018,7 +3000,7 @@ static void init_loopback(struct net_device *dev)
 				 * lo device down, release this obsolete dst and
 				 * reallocate a new router for ifa.
 				 */
-				if (sp_ifa->rt->dst.obsolete > 0) {
+				if (!atomic_read(&sp_ifa->rt->rt6i_ref)) {
 					ip6_rt_put(sp_ifa->rt);
 					sp_ifa->rt = NULL;
 				} else {
@@ -3594,9 +3576,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	if (!how)
 		idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
 
-	if (how && del_timer(&idev->regen_timer))
-		in6_dev_put(idev);
-
 	/* Step 3: clear tempaddr list */
 	while (!list_empty(&idev->tempaddr_list)) {
 		ifa = list_first_entry(&idev->tempaddr_list,
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 00cf28a..02761c9 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -96,7 +96,7 @@ EXPORT_SYMBOL(__inet6_lookup_established);
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum,
 				const struct in6_addr *daddr,
-				const int dif)
+				const int dif, bool exact_dif)
 {
 	int score = -1;
 
@@ -109,7 +109,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				return -1;
 			score++;
 		}
-		if (sk->sk_bound_dev_if) {
+		if (sk->sk_bound_dev_if || exact_dif) {
 			if (sk->sk_bound_dev_if != dif)
 				return -1;
 			score++;
@@ -131,11 +131,12 @@ struct sock *inet6_lookup_listener(struct net *net,
 	unsigned int hash = inet_lhashfn(net, hnum);
 	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
 	int score, hiscore = 0, matches = 0, reuseport = 0;
+	bool exact_dif = inet6_exact_dif_match(net, skb);
 	struct sock *sk, *result = NULL;
 	u32 phash = 0;
 
 	sk_for_each(sk, &ilb->head) {
-		score = compute_score(sk, net, hnum, daddr, dif);
+		score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
 		if (score > hiscore) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -263,13 +264,15 @@ EXPORT_SYMBOL_GPL(inet6_hash_connect);
 
 int inet6_hash(struct sock *sk)
 {
+	int err = 0;
+
 	if (sk->sk_state != TCP_CLOSE) {
 		local_bh_disable();
-		__inet_hash(sk, NULL, ipv6_rcv_saddr_equal);
+		err = __inet_hash(sk, NULL, ipv6_rcv_saddr_equal);
 		local_bh_enable();
 	}
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(inet6_hash);
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index e7bfd55..1fcf61f 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -246,7 +246,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	skb_gro_postpull_rcsum(skb, iph, nlen);
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 6a66adb..8778456 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -157,6 +157,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	hash = HASH(&any, local);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    ipv6_addr_any(&t->parms.raddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -164,6 +165,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	hash = HASH(remote, &any);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    ipv6_addr_any(&t->parms.laddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -1170,6 +1172,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	if (err)
 		return err;
 
+	skb->protocol = htons(ETH_P_IPV6);
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 5330262..636ec56 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -120,6 +120,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 static bool setsockopt_needs_rtnl(int optname)
 {
 	switch (optname) {
+	case IPV6_ADDRFORM:
 	case IPV6_ADD_MEMBERSHIP:
 	case IPV6_DROP_MEMBERSHIP:
 	case IPV6_JOIN_ANYCAST:
@@ -198,7 +199,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			}
 
 			fl6_free_socklist(sk);
-			ipv6_sock_mc_close(sk);
+			__ipv6_sock_mc_close(sk);
 
 			/*
 			 * Sock is moving from IPv6 to IPv4 (sk_prot), so
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 75c1fc5..14a3903 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -276,16 +276,14 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
 	return idev;
 }
 
-void ipv6_sock_mc_close(struct sock *sk)
+void __ipv6_sock_mc_close(struct sock *sk)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct ipv6_mc_socklist *mc_lst;
 	struct net *net = sock_net(sk);
 
-	if (!rcu_access_pointer(np->ipv6_mc_list))
-		return;
+	ASSERT_RTNL();
 
-	rtnl_lock();
 	while ((mc_lst = rtnl_dereference(np->ipv6_mc_list)) != NULL) {
 		struct net_device *dev;
 
@@ -303,8 +301,17 @@ void ipv6_sock_mc_close(struct sock *sk)
 
 		atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
 		kfree_rcu(mc_lst, rcu);
-
 	}
+}
+
+void ipv6_sock_mc_close(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	if (!rcu_access_pointer(np->ipv6_mc_list))
+		return;
+	rtnl_lock();
+	__ipv6_sock_mc_close(sk);
 	rtnl_unlock();
 }
 
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 0e983b6..66e2d9d 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -180,7 +180,7 @@ struct proto pingv6_prot = {
 	.init =		ping_init_sock,
 	.close =	ping_close,
 	.connect =	ip6_datagram_connect_v6_only,
-	.disconnect =	udp_disconnect,
+	.disconnect =	__udp_disconnect,
 	.setsockopt =	ipv6_setsockopt,
 	.getsockopt =	ipv6_getsockopt,
 	.sendmsg =	ping_v6_sendmsg,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 54404f0..054a1d8 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1241,7 +1241,7 @@ struct proto rawv6_prot = {
 	.close		   = rawv6_close,
 	.destroy	   = raw6_destroy,
 	.connect	   = ip6_datagram_connect_v6_only,
-	.disconnect	   = udp_disconnect,
+	.disconnect	   = __udp_disconnect,
 	.ioctl		   = rawv6_ioctl,
 	.init		   = rawv6_init_sk,
 	.setsockopt	   = rawv6_setsockopt,
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2160d5d..3815e85 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -456,7 +456,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
 	memmove(head->head + sizeof(struct frag_hdr), head->head,
 		(head->data - head->head) - sizeof(struct frag_hdr));
-	head->mac_header += sizeof(struct frag_hdr);
+	if (skb_mac_header_was_set(head))
+		head->mac_header += sizeof(struct frag_hdr);
 	head->network_header += sizeof(struct frag_hdr);
 
 	skb_reset_transport_header(head);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bdbc38e..947ed1d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -102,11 +102,13 @@ static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_add_route_info(struct net *net,
 					   const struct in6_addr *prefix, int prefixlen,
-					   const struct in6_addr *gwaddr, int ifindex,
+					   const struct in6_addr *gwaddr,
+					   struct net_device *dev,
 					   unsigned int pref);
 static struct rt6_info *rt6_get_route_info(struct net *net,
 					   const struct in6_addr *prefix, int prefixlen,
-					   const struct in6_addr *gwaddr, int ifindex);
+					   const struct in6_addr *gwaddr,
+					   struct net_device *dev);
 #endif
 
 struct uncached_list {
@@ -656,7 +658,8 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
 	struct net_device *dev = rt->dst.dev;
 
 	if (dev && !netif_carrier_ok(dev) &&
-	    idev->cnf.ignore_routes_with_linkdown)
+	    idev->cnf.ignore_routes_with_linkdown &&
+	    !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
 		goto out;
 
 	if (rt6_check_expired(rt))
@@ -803,7 +806,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 		rt = rt6_get_dflt_router(gwaddr, dev);
 	else
 		rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
-					gwaddr, dev->ifindex);
+					gwaddr, dev);
 
 	if (rt && !lifetime) {
 		ip6_del_rt(rt);
@@ -811,8 +814,8 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 	}
 
 	if (!rt && lifetime)
-		rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
-					pref);
+		rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr,
+					dev, pref);
 	else if (rt)
 		rt->rt6i_flags = RTF_ROUTEINFO |
 				 (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
@@ -1050,6 +1053,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	int strict = 0;
 
 	strict |= flags & RT6_LOOKUP_F_IFACE;
+	strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
 	if (net->ipv6.devconf_all->forwarding == 0)
 		strict |= RT6_LOOKUP_F_REACHABLE;
 
@@ -1789,7 +1793,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
 	};
 	struct fib6_table *table;
 	struct rt6_info *rt;
-	int flags = RT6_LOOKUP_F_IFACE;
+	int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_IGNORE_LINKSTATE;
 
 	table = fib6_get_table(net, cfg->fc_table);
 	if (!table)
@@ -2325,13 +2329,16 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_get_route_info(struct net *net,
 					   const struct in6_addr *prefix, int prefixlen,
-					   const struct in6_addr *gwaddr, int ifindex)
+					   const struct in6_addr *gwaddr,
+					   struct net_device *dev)
 {
+	u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO;
+	int ifindex = dev->ifindex;
 	struct fib6_node *fn;
 	struct rt6_info *rt = NULL;
 	struct fib6_table *table;
 
-	table = fib6_get_table(net, RT6_TABLE_INFO);
+	table = fib6_get_table(net, tb_id);
 	if (!table)
 		return NULL;
 
@@ -2357,12 +2364,13 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 
 static struct rt6_info *rt6_add_route_info(struct net *net,
 					   const struct in6_addr *prefix, int prefixlen,
-					   const struct in6_addr *gwaddr, int ifindex,
+					   const struct in6_addr *gwaddr,
+					   struct net_device *dev,
 					   unsigned int pref)
 {
 	struct fib6_config cfg = {
 		.fc_metric	= IP6_RT_PRIO_USER,
-		.fc_ifindex	= ifindex,
+		.fc_ifindex	= dev->ifindex,
 		.fc_dst_len	= prefixlen,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
 				  RTF_UP | RTF_PREF(pref),
@@ -2371,7 +2379,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 		.fc_nlinfo.nl_net = net,
 	};
 
-	cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
+	cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO,
 	cfg.fc_dst = *prefix;
 	cfg.fc_gateway = *gwaddr;
 
@@ -2381,16 +2389,17 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 
 	ip6_route_add(&cfg);
 
-	return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
+	return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev);
 }
 #endif
 
 struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
 {
+	u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT;
 	struct rt6_info *rt;
 	struct fib6_table *table;
 
-	table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
+	table = fib6_get_table(dev_net(dev), tb_id);
 	if (!table)
 		return NULL;
 
@@ -2424,20 +2433,20 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 
 	cfg.fc_gateway = *gwaddr;
 
-	ip6_route_add(&cfg);
+	if (!ip6_route_add(&cfg)) {
+		struct fib6_table *table;
+
+		table = fib6_get_table(dev_net(dev), cfg.fc_table);
+		if (table)
+			table->flags |= RT6_TABLE_HAS_DFLT_ROUTER;
+	}
 
 	return rt6_get_dflt_router(gwaddr, dev);
 }
 
-void rt6_purge_dflt_routers(struct net *net)
+static void __rt6_purge_dflt_routers(struct fib6_table *table)
 {
 	struct rt6_info *rt;
-	struct fib6_table *table;
-
-	/* NOTE: Keep consistent with rt6_get_dflt_router */
-	table = fib6_get_table(net, RT6_TABLE_DFLT);
-	if (!table)
-		return;
 
 restart:
 	read_lock_bh(&table->tb6_lock);
@@ -2451,6 +2460,27 @@ void rt6_purge_dflt_routers(struct net *net)
 		}
 	}
 	read_unlock_bh(&table->tb6_lock);
+
+	table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER;
+}
+
+void rt6_purge_dflt_routers(struct net *net)
+{
+	struct fib6_table *table;
+	struct hlist_head *head;
+	unsigned int h;
+
+	rcu_read_lock();
+
+	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+		head = &net->ipv6.fib_table_hash[h];
+		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
+			if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER)
+				__rt6_purge_dflt_routers(table);
+		}
+	}
+
+	rcu_read_unlock();
 }
 
 static void rtmsg_to_fib6_config(struct net *net,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9aa7c1c..b2ef061 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -427,7 +427,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 	if (is_udp4) {
 		if (inet->cmsg_flags)
-			ip_cmsg_recv(msg, skb);
+			ip_cmsg_recv_offset(msg, skb,
+					    sizeof(struct udphdr), off);
 	} else {
 		if (np->rxopt.all)
 			ip6_datagram_recv_specific_ctl(sk, msg, skb);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 42de4cc..fce25af 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -338,7 +338,7 @@ static int l2tp_ip_disconnect(struct sock *sk, int flags)
 	if (sock_flag(sk, SOCK_ZAPPED))
 		return 0;
 
-	return udp_disconnect(sk, flags);
+	return __udp_disconnect(sk, flags);
 }
 
 static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index ea2ae66..ad3468c 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -410,7 +410,7 @@ static int l2tp_ip6_disconnect(struct sock *sk, int flags)
 	if (sock_flag(sk, SOCK_ZAPPED))
 		return 0;
 
-	return udp_disconnect(sk, flags);
+	return __udp_disconnect(sk, flags);
 }
 
 static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c
index 7663c28..a4e0d59 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -18,21 +18,24 @@
 #include "key.h"
 #include "aes_ccm.h"
 
-void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			       u8 *data, size_t data_len, u8 *mic,
-			       size_t mic_len)
+int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
+			      u8 *data, size_t data_len, u8 *mic,
+			      size_t mic_len)
 {
 	struct scatterlist sg[3];
+	struct aead_request *aead_req;
+	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+	u8 *__aad;
 
-	char aead_req_data[sizeof(struct aead_request) +
-			   crypto_aead_reqsize(tfm)]
-		__aligned(__alignof__(struct aead_request));
-	struct aead_request *aead_req = (void *) aead_req_data;
+	aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC);
+	if (!aead_req)
+		return -ENOMEM;
 
-	memset(aead_req, 0, sizeof(aead_req_data));
+	__aad = (u8 *)aead_req + reqsize;
+	memcpy(__aad, aad, CCM_AAD_LEN);
 
 	sg_init_table(sg, 3);
-	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
 	sg_set_buf(&sg[1], data, data_len);
 	sg_set_buf(&sg[2], mic, mic_len);
 
@@ -41,6 +44,9 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	aead_request_set_ad(aead_req, sg[0].length);
 
 	crypto_aead_encrypt(aead_req);
+	kzfree(aead_req);
+
+	return 0;
 }
 
 int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
@@ -48,18 +54,23 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 			      size_t mic_len)
 {
 	struct scatterlist sg[3];
-	char aead_req_data[sizeof(struct aead_request) +
-			   crypto_aead_reqsize(tfm)]
-		__aligned(__alignof__(struct aead_request));
-	struct aead_request *aead_req = (void *) aead_req_data;
+	struct aead_request *aead_req;
+	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+	u8 *__aad;
+	int err;
 
 	if (data_len == 0)
 		return -EINVAL;
 
-	memset(aead_req, 0, sizeof(aead_req_data));
+	aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC);
+	if (!aead_req)
+		return -ENOMEM;
+
+	__aad = (u8 *)aead_req + reqsize;
+	memcpy(__aad, aad, CCM_AAD_LEN);
 
 	sg_init_table(sg, 3);
-	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
 	sg_set_buf(&sg[1], data, data_len);
 	sg_set_buf(&sg[2], mic, mic_len);
 
@@ -67,7 +78,10 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	aead_request_set_crypt(aead_req, sg, sg, data_len + mic_len, b_0);
 	aead_request_set_ad(aead_req, sg[0].length);
 
-	return crypto_aead_decrypt(aead_req);
+	err = crypto_aead_decrypt(aead_req);
+	kzfree(aead_req);
+
+	return err;
 }
 
 struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[],
diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h
index 6a73d1e..fcd3254 100644
--- a/net/mac80211/aes_ccm.h
+++ b/net/mac80211/aes_ccm.h
@@ -12,12 +12,14 @@
 
 #include <linux/crypto.h>
 
+#define CCM_AAD_LEN	32
+
 struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[],
 						    size_t key_len,
 						    size_t mic_len);
-void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
-			       u8 *data, size_t data_len, u8 *mic,
-			       size_t mic_len);
+int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
+			      u8 *data, size_t data_len, u8 *mic,
+			      size_t mic_len);
 int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 			      u8 *data, size_t data_len, u8 *mic,
 			      size_t mic_len);
diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c
index 3afe361f..8a4397c 100644
--- a/net/mac80211/aes_gcm.c
+++ b/net/mac80211/aes_gcm.c
@@ -15,20 +15,23 @@
 #include "key.h"
 #include "aes_gcm.h"
 
-void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
-			       u8 *data, size_t data_len, u8 *mic)
+int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			      u8 *data, size_t data_len, u8 *mic)
 {
 	struct scatterlist sg[3];
+	struct aead_request *aead_req;
+	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+	u8 *__aad;
 
-	char aead_req_data[sizeof(struct aead_request) +
-			   crypto_aead_reqsize(tfm)]
-		__aligned(__alignof__(struct aead_request));
-	struct aead_request *aead_req = (void *)aead_req_data;
+	aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC);
+	if (!aead_req)
+		return -ENOMEM;
 
-	memset(aead_req, 0, sizeof(aead_req_data));
+	__aad = (u8 *)aead_req + reqsize;
+	memcpy(__aad, aad, GCM_AAD_LEN);
 
 	sg_init_table(sg, 3);
-	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
 	sg_set_buf(&sg[1], data, data_len);
 	sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
 
@@ -37,24 +40,31 @@ void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 	aead_request_set_ad(aead_req, sg[0].length);
 
 	crypto_aead_encrypt(aead_req);
+	kzfree(aead_req);
+	return 0;
 }
 
 int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 			      u8 *data, size_t data_len, u8 *mic)
 {
 	struct scatterlist sg[3];
-	char aead_req_data[sizeof(struct aead_request) +
-			   crypto_aead_reqsize(tfm)]
-		__aligned(__alignof__(struct aead_request));
-	struct aead_request *aead_req = (void *)aead_req_data;
+	struct aead_request *aead_req;
+	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+	u8 *__aad;
+	int err;
 
 	if (data_len == 0)
 		return -EINVAL;
 
-	memset(aead_req, 0, sizeof(aead_req_data));
+	aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC);
+	if (!aead_req)
+		return -ENOMEM;
+
+	__aad = (u8 *)aead_req + reqsize;
+	memcpy(__aad, aad, GCM_AAD_LEN);
 
 	sg_init_table(sg, 3);
-	sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
 	sg_set_buf(&sg[1], data, data_len);
 	sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
 
@@ -63,7 +73,10 @@ int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 			       data_len + IEEE80211_GCMP_MIC_LEN, j_0);
 	aead_request_set_ad(aead_req, sg[0].length);
 
-	return crypto_aead_decrypt(aead_req);
+	err = crypto_aead_decrypt(aead_req);
+	kzfree(aead_req);
+
+	return err;
 }
 
 struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h
index 1347fda..55aed53 100644
--- a/net/mac80211/aes_gcm.h
+++ b/net/mac80211/aes_gcm.h
@@ -11,8 +11,10 @@
 
 #include <linux/crypto.h>
 
-void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
-			       u8 *data, size_t data_len, u8 *mic);
+#define GCM_AAD_LEN	32
+
+int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			      u8 *data, size_t data_len, u8 *mic);
 int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
 			      u8 *data, size_t data_len, u8 *mic);
 struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c
index 3ddd927..bd72a86 100644
--- a/net/mac80211/aes_gmac.c
+++ b/net/mac80211/aes_gmac.c
@@ -17,28 +17,27 @@
 #include "key.h"
 #include "aes_gmac.h"
 
-#define GMAC_MIC_LEN 16
-#define GMAC_NONCE_LEN 12
-#define AAD_LEN 20
-
 int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
 		       const u8 *data, size_t data_len, u8 *mic)
 {
 	struct scatterlist sg[4];
-	char aead_req_data[sizeof(struct aead_request) +
-			   crypto_aead_reqsize(tfm)]
-		__aligned(__alignof__(struct aead_request));
-	struct aead_request *aead_req = (void *)aead_req_data;
-	u8 zero[GMAC_MIC_LEN], iv[AES_BLOCK_SIZE];
+	u8 *zero, *__aad, iv[AES_BLOCK_SIZE];
+	struct aead_request *aead_req;
+	int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
 
 	if (data_len < GMAC_MIC_LEN)
 		return -EINVAL;
 
-	memset(aead_req, 0, sizeof(aead_req_data));
+	aead_req = kzalloc(reqsize + GMAC_MIC_LEN + GMAC_AAD_LEN, GFP_ATOMIC);
+	if (!aead_req)
+		return -ENOMEM;
 
-	memset(zero, 0, GMAC_MIC_LEN);
+	zero = (u8 *)aead_req + reqsize;
+	__aad = zero + GMAC_MIC_LEN;
+	memcpy(__aad, aad, GMAC_AAD_LEN);
+
 	sg_init_table(sg, 4);
-	sg_set_buf(&sg[0], aad, AAD_LEN);
+	sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN);
 	sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN);
 	sg_set_buf(&sg[2], zero, GMAC_MIC_LEN);
 	sg_set_buf(&sg[3], mic, GMAC_MIC_LEN);
@@ -49,9 +48,10 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
 
 	aead_request_set_tfm(aead_req, tfm);
 	aead_request_set_crypt(aead_req, sg, sg, 0, iv);
-	aead_request_set_ad(aead_req, AAD_LEN + data_len);
+	aead_request_set_ad(aead_req, GMAC_AAD_LEN + data_len);
 
 	crypto_aead_encrypt(aead_req);
+	kzfree(aead_req);
 
 	return 0;
 }
diff --git a/net/mac80211/aes_gmac.h b/net/mac80211/aes_gmac.h
index d328204..32e6442 100644
--- a/net/mac80211/aes_gmac.h
+++ b/net/mac80211/aes_gmac.h
@@ -11,6 +11,10 @@
 
 #include <linux/crypto.h>
 
+#define GMAC_AAD_LEN	20
+#define GMAC_MIC_LEN	16
+#define GMAC_NONCE_LEN	12
+
 struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[],
 						 size_t key_len);
 int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index c3f610b..eede5c6 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -820,7 +820,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		    mgmt->u.action.category == WLAN_CATEGORY_SPECTRUM_MGMT)
 			break;
 		rcu_read_lock();
-		sta = sta_info_get(sdata, mgmt->da);
+		sta = sta_info_get_bss(sdata, mgmt->da);
 		rcu_read_unlock();
 		if (!sta)
 			return -ENOLINK;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 6175db3..a47bbc9 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2298,6 +2298,8 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
 	__le16 fc = hdr->frame_control;
 	struct sk_buff_head frame_list;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
+	struct ethhdr ethhdr;
+	const u8 *check_da = ethhdr.h_dest, *check_sa = ethhdr.h_source;
 
 	if (unlikely(!ieee80211_is_data(fc)))
 		return RX_CONTINUE;
@@ -2308,24 +2310,53 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
 	if (!(status->rx_flags & IEEE80211_RX_AMSDU))
 		return RX_CONTINUE;
 
-	if (ieee80211_has_a4(hdr->frame_control) &&
-	    rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
-	    !rx->sdata->u.vlan.sta)
-		return RX_DROP_UNUSABLE;
+	if (unlikely(ieee80211_has_a4(hdr->frame_control))) {
+		switch (rx->sdata->vif.type) {
+		case NL80211_IFTYPE_AP_VLAN:
+			if (!rx->sdata->u.vlan.sta)
+				return RX_DROP_UNUSABLE;
+			break;
+		case NL80211_IFTYPE_STATION:
+			if (!rx->sdata->u.mgd.use_4addr)
+				return RX_DROP_UNUSABLE;
+			break;
+		default:
+			return RX_DROP_UNUSABLE;
+		}
+		check_da = NULL;
+		check_sa = NULL;
+	} else switch (rx->sdata->vif.type) {
+		case NL80211_IFTYPE_AP:
+		case NL80211_IFTYPE_AP_VLAN:
+			check_da = NULL;
+			break;
+		case NL80211_IFTYPE_STATION:
+			if (!rx->sta ||
+			    !test_sta_flag(rx->sta, WLAN_STA_TDLS_PEER))
+				check_sa = NULL;
+			break;
+		case NL80211_IFTYPE_MESH_POINT:
+			check_sa = NULL;
+			break;
+		default:
+			break;
+	}
 
-	if (is_multicast_ether_addr(hdr->addr1) &&
-	    ((rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
-	      rx->sdata->u.vlan.sta) ||
-	     (rx->sdata->vif.type == NL80211_IFTYPE_STATION &&
-	      rx->sdata->u.mgd.use_4addr)))
+	if (is_multicast_ether_addr(hdr->addr1))
 		return RX_DROP_UNUSABLE;
 
 	skb->dev = dev;
 	__skb_queue_head_init(&frame_list);
 
+	if (ieee80211_data_to_8023_exthdr(skb, &ethhdr,
+					  rx->sdata->vif.addr,
+					  rx->sdata->vif.type))
+		return RX_DROP_UNUSABLE;
+
 	ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr,
 				 rx->sdata->vif.type,
-				 rx->local->hw.extra_tx_headroom, true);
+				 rx->local->hw.extra_tx_headroom,
+				 check_da, check_sa);
 
 	while (!skb_queue_empty(&frame_list)) {
 		rx->skb = __skb_dequeue(&frame_list);
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index b48c1e1..42ce9bd 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -405,7 +405,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb,
 	u8 *pos;
 	u8 pn[6];
 	u64 pn64;
-	u8 aad[2 * AES_BLOCK_SIZE];
+	u8 aad[CCM_AAD_LEN];
 	u8 b_0[AES_BLOCK_SIZE];
 
 	if (info->control.hw_key &&
@@ -461,10 +461,8 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb,
 
 	pos += IEEE80211_CCMP_HDR_LEN;
 	ccmp_special_blocks(skb, pn, b_0, aad);
-	ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len,
-				  skb_put(skb, mic_len), mic_len);
-
-	return 0;
+	return ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len,
+					 skb_put(skb, mic_len), mic_len);
 }
 
 
@@ -639,7 +637,7 @@ static int gcmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 	u8 *pos;
 	u8 pn[6];
 	u64 pn64;
-	u8 aad[2 * AES_BLOCK_SIZE];
+	u8 aad[GCM_AAD_LEN];
 	u8 j_0[AES_BLOCK_SIZE];
 
 	if (info->control.hw_key &&
@@ -696,10 +694,8 @@ static int gcmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 
 	pos += IEEE80211_GCMP_HDR_LEN;
 	gcmp_special_blocks(skb, pn, j_0, aad);
-	ieee80211_aes_gcm_encrypt(key->u.gcmp.tfm, j_0, aad, pos, len,
-				  skb_put(skb, IEEE80211_GCMP_MIC_LEN));
-
-	return 0;
+	return ieee80211_aes_gcm_encrypt(key->u.gcmp.tfm, j_0, aad, pos, len,
+					 skb_put(skb, IEEE80211_GCMP_MIC_LEN));
 }
 
 ieee80211_tx_result
@@ -1123,9 +1119,9 @@ ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx)
 	struct ieee80211_key *key = tx->key;
 	struct ieee80211_mmie_16 *mmie;
 	struct ieee80211_hdr *hdr;
-	u8 aad[20];
+	u8 aad[GMAC_AAD_LEN];
 	u64 pn64;
-	u8 nonce[12];
+	u8 nonce[GMAC_NONCE_LEN];
 
 	if (WARN_ON(skb_queue_len(&tx->skbs) != 1))
 		return TX_DROP;
@@ -1171,7 +1167,7 @@ ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx)
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	struct ieee80211_key *key = rx->key;
 	struct ieee80211_mmie_16 *mmie;
-	u8 aad[20], mic[16], ipn[6], nonce[12];
+	u8 aad[GMAC_AAD_LEN], mic[GMAC_MIC_LEN], ipn[6], nonce[GMAC_NONCE_LEN];
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 
 	if (!ieee80211_is_mgmt(hdr->frame_control))
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 13290a7..1308a56 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -246,6 +246,7 @@ enum {
 	ncsi_dev_state_config_gls,
 	ncsi_dev_state_config_done,
 	ncsi_dev_state_suspend_select	= 0x0401,
+	ncsi_dev_state_suspend_gls,
 	ncsi_dev_state_suspend_dcnt,
 	ncsi_dev_state_suspend_dc,
 	ncsi_dev_state_suspend_deselect,
@@ -264,6 +265,7 @@ struct ncsi_dev_priv {
 #endif
 	unsigned int        package_num;     /* Number of packages         */
 	struct list_head    packages;        /* List of packages           */
+	struct ncsi_channel *hot_channel;    /* Channel was ever active    */
 	struct ncsi_request requests[256];   /* Request table              */
 	unsigned int        request_id;      /* Last used request ID       */
 #define NCSI_REQ_START_IDX	1
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index b41a661..6898e72 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -141,23 +141,35 @@ static int ncsi_aen_handler_hncdsc(struct ncsi_dev_priv *ndp,
 		return -ENODEV;
 
 	/* If the channel is active one, we need reconfigure it */
+	spin_lock_irqsave(&nc->lock, flags);
 	ncm = &nc->modes[NCSI_MODE_LINK];
 	hncdsc = (struct ncsi_aen_hncdsc_pkt *)h;
 	ncm->data[3] = ntohl(hncdsc->status);
 	if (!list_empty(&nc->link) ||
-	    nc->state != NCSI_CHANNEL_ACTIVE ||
-	    (ncm->data[3] & 0x1))
+	    nc->state != NCSI_CHANNEL_ACTIVE) {
+		spin_unlock_irqrestore(&nc->lock, flags);
 		return 0;
+	}
 
-	if (ndp->flags & NCSI_DEV_HWA)
+	spin_unlock_irqrestore(&nc->lock, flags);
+	if (!(ndp->flags & NCSI_DEV_HWA) && !(ncm->data[3] & 0x1))
 		ndp->flags |= NCSI_DEV_RESHUFFLE;
 
 	/* If this channel is the active one and the link doesn't
 	 * work, we have to choose another channel to be active one.
 	 * The logic here is exactly similar to what we do when link
 	 * is down on the active channel.
+	 *
+	 * On the other hand, we need configure it when host driver
+	 * state on the active channel becomes ready.
 	 */
 	ncsi_stop_channel_monitor(nc);
+
+	spin_lock_irqsave(&nc->lock, flags);
+	nc->state = (ncm->data[3] & 0x1) ? NCSI_CHANNEL_INACTIVE :
+					   NCSI_CHANNEL_ACTIVE;
+	spin_unlock_irqrestore(&nc->lock, flags);
+
 	spin_lock_irqsave(&ndp->lock, flags);
 	list_add_tail_rcu(&nc->link, &ndp->channel_queue);
 	spin_unlock_irqrestore(&ndp->lock, flags);
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 5e509e5..a3bd5fa 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -540,42 +540,86 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
 		nd->state = ncsi_dev_state_suspend_select;
 		/* Fall through */
 	case ncsi_dev_state_suspend_select:
+		ndp->pending_req_num = 1;
+
+		nca.type = NCSI_PKT_CMD_SP;
+		nca.package = np->id;
+		nca.channel = NCSI_RESERVED_CHANNEL;
+		if (ndp->flags & NCSI_DEV_HWA)
+			nca.bytes[0] = 0;
+		else
+			nca.bytes[0] = 1;
+
+		/* To retrieve the last link states of channels in current
+		 * package when current active channel needs fail over to
+		 * another one. It means we will possibly select another
+		 * channel as next active one. The link states of channels
+		 * are most important factor of the selection. So we need
+		 * accurate link states. Unfortunately, the link states on
+		 * inactive channels can't be updated with LSC AEN in time.
+		 */
+		if (ndp->flags & NCSI_DEV_RESHUFFLE)
+			nd->state = ncsi_dev_state_suspend_gls;
+		else
+			nd->state = ncsi_dev_state_suspend_dcnt;
+		ret = ncsi_xmit_cmd(&nca);
+		if (ret)
+			goto error;
+
+		break;
+	case ncsi_dev_state_suspend_gls:
+		ndp->pending_req_num = np->channel_num;
+
+		nca.type = NCSI_PKT_CMD_GLS;
+		nca.package = np->id;
+
+		nd->state = ncsi_dev_state_suspend_dcnt;
+		NCSI_FOR_EACH_CHANNEL(np, nc) {
+			nca.channel = nc->id;
+			ret = ncsi_xmit_cmd(&nca);
+			if (ret)
+				goto error;
+		}
+
+		break;
 	case ncsi_dev_state_suspend_dcnt:
+		ndp->pending_req_num = 1;
+
+		nca.type = NCSI_PKT_CMD_DCNT;
+		nca.package = np->id;
+		nca.channel = nc->id;
+
+		nd->state = ncsi_dev_state_suspend_dc;
+		ret = ncsi_xmit_cmd(&nca);
+		if (ret)
+			goto error;
+
+		break;
 	case ncsi_dev_state_suspend_dc:
+		ndp->pending_req_num = 1;
+
+		nca.type = NCSI_PKT_CMD_DC;
+		nca.package = np->id;
+		nca.channel = nc->id;
+		nca.bytes[0] = 1;
+
+		nd->state = ncsi_dev_state_suspend_deselect;
+		ret = ncsi_xmit_cmd(&nca);
+		if (ret)
+			goto error;
+
+		break;
 	case ncsi_dev_state_suspend_deselect:
 		ndp->pending_req_num = 1;
 
-		np = ndp->active_package;
-		nc = ndp->active_channel;
+		nca.type = NCSI_PKT_CMD_DP;
 		nca.package = np->id;
-		if (nd->state == ncsi_dev_state_suspend_select) {
-			nca.type = NCSI_PKT_CMD_SP;
-			nca.channel = NCSI_RESERVED_CHANNEL;
-			if (ndp->flags & NCSI_DEV_HWA)
-				nca.bytes[0] = 0;
-			else
-				nca.bytes[0] = 1;
-			nd->state = ncsi_dev_state_suspend_dcnt;
-		} else if (nd->state == ncsi_dev_state_suspend_dcnt) {
-			nca.type = NCSI_PKT_CMD_DCNT;
-			nca.channel = nc->id;
-			nd->state = ncsi_dev_state_suspend_dc;
-		} else if (nd->state == ncsi_dev_state_suspend_dc) {
-			nca.type = NCSI_PKT_CMD_DC;
-			nca.channel = nc->id;
-			nca.bytes[0] = 1;
-			nd->state = ncsi_dev_state_suspend_deselect;
-		} else if (nd->state == ncsi_dev_state_suspend_deselect) {
-			nca.type = NCSI_PKT_CMD_DP;
-			nca.channel = NCSI_RESERVED_CHANNEL;
-			nd->state = ncsi_dev_state_suspend_done;
-		}
+		nca.channel = NCSI_RESERVED_CHANNEL;
 
+		nd->state = ncsi_dev_state_suspend_done;
 		ret = ncsi_xmit_cmd(&nca);
-		if (ret) {
-			nd->state = ncsi_dev_state_functional;
-			return;
-		}
+		if (ret)
+			goto error;
 
 		break;
 	case ncsi_dev_state_suspend_done:
@@ -589,6 +633,10 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
 		netdev_warn(nd->dev, "Wrong NCSI state 0x%x in suspend\n",
 			    nd->state);
 	}
+
+	return;
+error:
+	nd->state = ncsi_dev_state_functional;
 }
 
 static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
@@ -597,6 +645,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 	struct net_device *dev = nd->dev;
 	struct ncsi_package *np = ndp->active_package;
 	struct ncsi_channel *nc = ndp->active_channel;
+	struct ncsi_channel *hot_nc = NULL;
 	struct ncsi_cmd_arg nca;
 	unsigned char index;
 	unsigned long flags;
@@ -702,12 +751,20 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 		break;
 	case ncsi_dev_state_config_done:
 		spin_lock_irqsave(&nc->lock, flags);
-		if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1)
+		if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) {
+			hot_nc = nc;
 			nc->state = NCSI_CHANNEL_ACTIVE;
-		else
+		} else {
+			hot_nc = NULL;
 			nc->state = NCSI_CHANNEL_INACTIVE;
+		}
 		spin_unlock_irqrestore(&nc->lock, flags);
 
+		/* Update the hot channel */
+		spin_lock_irqsave(&ndp->lock, flags);
+		ndp->hot_channel = hot_nc;
+		spin_unlock_irqrestore(&ndp->lock, flags);
+
 		ncsi_start_channel_monitor(nc);
 		ncsi_process_next_channel(ndp);
 		break;
@@ -725,10 +782,14 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
 static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
 {
 	struct ncsi_package *np;
-	struct ncsi_channel *nc, *found;
+	struct ncsi_channel *nc, *found, *hot_nc;
 	struct ncsi_channel_mode *ncm;
 	unsigned long flags;
 
+	spin_lock_irqsave(&ndp->lock, flags);
+	hot_nc = ndp->hot_channel;
+	spin_unlock_irqrestore(&ndp->lock, flags);
+
 	/* The search is done once an inactive channel with up
 	 * link is found.
 	 */
@@ -746,6 +807,9 @@ static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
 			if (!found)
 				found = nc;
 
+			if (nc == hot_nc)
+				found = nc;
+
 			ncm = &nc->modes[NCSI_MODE_LINK];
 			if (ncm->data[2] & 0x1) {
 				spin_unlock_irqrestore(&nc->lock, flags);
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index fcb5d1d..004af03 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -361,16 +361,9 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state)
 		if (ret == 0)
 			ret = -EPERM;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
-		int err;
-
-		RCU_INIT_POINTER(state->hook_entries, entry);
-		err = nf_queue(skb, state, verdict >> NF_VERDICT_QBITS);
-		if (err < 0) {
-			if (err == -ESRCH &&
-			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
-				goto next_hook;
-			kfree_skb(skb);
-		}
+		ret = nf_queue(skb, state, &entry, verdict);
+		if (ret == 1 && entry)
+			goto next_hook;
 	}
 	return ret;
 }
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index ba6a1d4..df2f5a3 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -983,7 +983,7 @@ static void gc_worker(struct work_struct *work)
 		return;
 
 	ratio = scanned ? expired_count * 100 / scanned : 0;
-	if (ratio >= 90)
+	if (ratio >= 90 || expired_count == GC_MAX_EVICTS)
 		next_run = 0;
 
 	gc_work->last_bucket = i;
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index e0adb59..9fdb655 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -18,7 +18,7 @@ unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state,
 
 /* nf_queue.c */
 int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
-	     unsigned int queuenum);
+	     struct nf_hook_entry **entryp, unsigned int verdict);
 void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry);
 int __init netfilter_queue_init(void);
 
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 96964a0..8f08d75 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -107,13 +107,8 @@ void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry)
 	rcu_read_unlock();
 }
 
-/*
- * Any packet that leaves via this function must come back
- * through nf_reinject().
- */
-int nf_queue(struct sk_buff *skb,
-	     struct nf_hook_state *state,
-	     unsigned int queuenum)
+static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
+		      unsigned int queuenum)
 {
 	int status = -ENOENT;
 	struct nf_queue_entry *entry = NULL;
@@ -161,6 +156,27 @@ int nf_queue(struct sk_buff *skb,
 	return status;
 }
 
+/* Packets leaving via this function must come back through nf_reinject(). */
+int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
+	     struct nf_hook_entry **entryp, unsigned int verdict)
+{
+	struct nf_hook_entry *entry = *entryp;
+	int ret;
+
+	RCU_INIT_POINTER(state->hook_entries, entry);
+	ret = __nf_queue(skb, state, verdict >> NF_VERDICT_QBITS);
+	if (ret < 0) {
+		if (ret == -ESRCH &&
+		    (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) {
+			*entryp = rcu_dereference(entry->next);
+			return 1;
+		}
+		kfree_skb(skb);
+	}
+
+	return 0;
+}
+
 void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 {
 	struct nf_hook_entry *hook_entry;
@@ -187,26 +203,26 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	entry->state.thresh = INT_MIN;
 
 	if (verdict == NF_ACCEPT) {
-	next_hook:
-		verdict = nf_iterate(skb, &entry->state, &hook_entry);
+		hook_entry = rcu_dereference(hook_entry->next);
+		if (hook_entry)
+next_hook:
+			verdict = nf_iterate(skb, &entry->state, &hook_entry);
 	}
 
 	switch (verdict & NF_VERDICT_MASK) {
 	case NF_ACCEPT:
 	case NF_STOP:
+okfn:
 		local_bh_disable();
 		entry->state.okfn(entry->state.net, entry->state.sk, skb);
 		local_bh_enable();
 		break;
 	case NF_QUEUE:
-		RCU_INIT_POINTER(entry->state.hook_entries, hook_entry);
-		err = nf_queue(skb, &entry->state,
-			       verdict >> NF_VERDICT_QBITS);
-		if (err < 0) {
-			if (err == -ESRCH &&
-			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+		err = nf_queue(skb, &entry->state, &hook_entry, verdict);
+		if (err == 1) {
+			if (hook_entry)
 				goto next_hook;
-			kfree_skb(skb);
+			goto okfn;
 		}
 		break;
 	case NF_STOLEN:
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b70d3ea..24db222 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4423,7 +4423,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
  */
 unsigned int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
 {
-	int val;
+	u32 val;
 
 	val = ntohl(nla_get_be32(attr));
 	if (val > max)
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index e3b83c3..517f087 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -158,7 +158,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
 		if (!(set->flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
-		timeout = be64_to_cpu(nla_get_be64(tb[NFTA_DYNSET_TIMEOUT]));
+		timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64(
+						tb[NFTA_DYNSET_TIMEOUT])));
 	}
 
 	priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]);
@@ -246,7 +247,8 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
 		goto nla_put_failure;
 	if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name))
 		goto nla_put_failure;
-	if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, cpu_to_be64(priv->timeout),
+	if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT,
+			 cpu_to_be64(jiffies_to_msecs(priv->timeout)),
 			 NFTA_DYNSET_PAD))
 		goto nla_put_failure;
 	if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr))
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index a84cf3d..47beb3a 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -59,7 +59,8 @@ static int nft_exthdr_init(const struct nft_ctx *ctx,
 			   const struct nlattr * const tb[])
 {
 	struct nft_exthdr *priv = nft_expr_priv(expr);
-	u32 offset, len, err;
+	u32 offset, len;
+	int err;
 
 	if (tb[NFTA_EXTHDR_DREG] == NULL ||
 	    tb[NFTA_EXTHDR_TYPE] == NULL ||
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 09473b4..baf694d 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -44,6 +44,7 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
 	[NFTA_HASH_LEN]		= { .type = NLA_U32 },
 	[NFTA_HASH_MODULUS]	= { .type = NLA_U32 },
 	[NFTA_HASH_SEED]	= { .type = NLA_U32 },
+	[NFTA_HASH_OFFSET]	= { .type = NLA_U32 },
 };
 
 static int nft_hash_init(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c
index c6d5358..fbc8800 100644
--- a/net/netfilter/nft_range.c
+++ b/net/netfilter/nft_range.c
@@ -28,22 +28,20 @@ static void nft_range_eval(const struct nft_expr *expr,
 			 const struct nft_pktinfo *pkt)
 {
 	const struct nft_range_expr *priv = nft_expr_priv(expr);
-	bool mismatch;
 	int d1, d2;
 
 	d1 = memcmp(&regs->data[priv->sreg], &priv->data_from, priv->len);
 	d2 = memcmp(&regs->data[priv->sreg], &priv->data_to, priv->len);
 	switch (priv->op) {
 	case NFT_RANGE_EQ:
-		mismatch = (d1 < 0 || d2 > 0);
+		if (d1 < 0 || d2 > 0)
+			regs->verdict.code = NFT_BREAK;
 		break;
 	case NFT_RANGE_NEQ:
-		mismatch = (d1 >= 0 && d2 <= 0);
+		if (d1 >= 0 && d2 <= 0)
+			regs->verdict.code = NFT_BREAK;
 		break;
 	}
-
-	if (mismatch)
-		regs->verdict.code = NFT_BREAK;
 }
 
 static const struct nla_policy nft_range_policy[NFTA_RANGE_MAX + 1] = {
@@ -59,6 +57,7 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
 	struct nft_range_expr *priv = nft_expr_priv(expr);
 	struct nft_data_desc desc_from, desc_to;
 	int err;
+	u32 op;
 
 	err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from),
 			    &desc_from, tb[NFTA_RANGE_FROM_DATA]);
@@ -80,7 +79,20 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
 	if (err < 0)
 		goto err2;
 
-	priv->op  = ntohl(nla_get_be32(tb[NFTA_RANGE_OP]));
+	err = nft_parse_u32_check(tb[NFTA_RANGE_OP], U8_MAX, &op);
+	if (err < 0)
+		goto err2;
+
+	switch (op) {
+	case NFT_RANGE_EQ:
+	case NFT_RANGE_NEQ:
+		break;
+	default:
+		err = -EINVAL;
+		goto err2;
+	}
+
+	priv->op  = op;
 	priv->len = desc_from.len;
 	return 0;
 err2:
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index e0aa7c1..fc49774 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1513,7 +1513,7 @@ xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn)
 	if (!num_hooks)
 		return ERR_PTR(-EINVAL);
 
-	ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL);
+	ops = kcalloc(num_hooks, sizeof(*ops), GFP_KERNEL);
 	if (ops == NULL)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c
index 018eed7..8668a5c 100644
--- a/net/netfilter/xt_NFLOG.c
+++ b/net/netfilter/xt_NFLOG.c
@@ -32,6 +32,7 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	li.u.ulog.copy_len   = info->len;
 	li.u.ulog.group	     = info->group;
 	li.u.ulog.qthreshold = info->threshold;
+	li.u.ulog.flags	     = 0;
 
 	if (info->flags & XT_NFLOG_F_COPY_LEN)
 		li.u.ulog.flags |= NF_LOG_F_COPY_LEN;
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 2fab0c6..b89b688 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -431,7 +431,7 @@ static void htable_put(struct xt_hashlimit_htable *hinfo)
    CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32 ie.
 */
 #define MAX_CPJ_v1 (0xFFFFFFFF / (HZ*60*60*24))
-#define MAX_CPJ (0xFFFFFFFFFFFFFFFF / (HZ*60*60*24))
+#define MAX_CPJ (0xFFFFFFFFFFFFFFFFULL / (HZ*60*60*24))
 
 /* Repeated shift and or gives us all 1s, final shift and add 1 gives
  * us the power of 2 below the theoretical max, so GCC simply does a
@@ -473,7 +473,7 @@ static u64 user2credits(u64 user, int revision)
 		return div64_u64(user * HZ * CREDITS_PER_JIFFY_v1,
 				 XT_HASHLIMIT_SCALE);
 	} else {
-		if (user > 0xFFFFFFFFFFFFFFFF / (HZ*CREDITS_PER_JIFFY))
+		if (user > 0xFFFFFFFFFFFFFFFFULL / (HZ*CREDITS_PER_JIFFY))
 			return div64_u64(user, XT_HASHLIMIT_SCALE_v2)
 				* HZ * CREDITS_PER_JIFFY;
 
diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c
index 89d5310..000e703 100644
--- a/net/netfilter/xt_ipcomp.c
+++ b/net/netfilter/xt_ipcomp.c
@@ -26,6 +26,8 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Fan Du <fan.du@windriver.com>");
 MODULE_DESCRIPTION("Xtables: IPv4/6 IPsec-IPComp SPI match");
+MODULE_ALIAS("ipt_ipcomp");
+MODULE_ALIAS("ip6t_ipcomp");
 
 /* Returns 1 if the spi is matched by the range, 0 otherwise */
 static inline bool
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 11db0d6..d2238b2 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -250,7 +250,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
 static int packet_direct_xmit(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
-	netdev_features_t features;
+	struct sk_buff *orig_skb = skb;
 	struct netdev_queue *txq;
 	int ret = NETDEV_TX_BUSY;
 
@@ -258,9 +258,8 @@ static int packet_direct_xmit(struct sk_buff *skb)
 		     !netif_carrier_ok(dev)))
 		goto drop;
 
-	features = netif_skb_features(skb);
-	if (skb_needs_linearize(skb, features) &&
-	    __skb_linearize(skb))
+	skb = validate_xmit_skb_list(skb, dev);
+	if (skb != orig_skb)
 		goto drop;
 
 	txq = skb_get_tx_queue(dev, skb);
@@ -280,7 +279,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	return ret;
 drop:
 	atomic_long_inc(&dev->tx_dropped);
-	kfree_skb(skb);
+	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
 
diff --git a/net/rds/Makefile b/net/rds/Makefile
index 0e72bec..56c7d27 100644
--- a/net/rds/Makefile
+++ b/net/rds/Makefile
@@ -13,5 +13,5 @@
 rds_tcp-y :=		tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \
 			tcp_send.o tcp_stats.o
 
-ccflags-$(CONFIG_RDS_DEBUG)	:=	-DDEBUG
+ccflags-$(CONFIG_RDS_DEBUG)	:=	-DRDS_DEBUG
 
diff --git a/net/rds/rds.h b/net/rds/rds.h
index fd0bccb..67ba67c 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -33,7 +33,7 @@
 #define KERNEL_HAS_ATOMIC64
 #endif
 
-#ifdef DEBUG
+#ifdef RDS_DEBUG
 #define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args)
 #else
 /* sigh, pr_debug() causes unused variable warnings */
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 4353a29..1ed18d8 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -276,7 +276,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 		goto error;
 
 	trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage),
-			 here, ERR_PTR(ret));
+			 here, NULL);
 
 	spin_lock_bh(&call->conn->params.peer->lock);
 	hlist_add_head(&call->error_link,
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 941b724..862eea6 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -193,8 +193,8 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
 		fl6->fl6_dport = htons(7001);
 		fl6->fl6_sport = htons(7000);
 		dst = ip6_route_output(&init_net, NULL, fl6);
-		if (IS_ERR(dst)) {
-			_leave(" [route err %ld]", PTR_ERR(dst));
+		if (dst->error) {
+			_leave(" [route err %d]", dst->error);
 			return;
 		}
 		break;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index a512b18..f893d18 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1028,8 +1028,7 @@ static struct nlattr *find_dump_kind(const struct nlmsghdr *n)
 
 	if (tb[1] == NULL)
 		return NULL;
-	if (nla_parse(tb2, TCA_ACT_MAX, nla_data(tb[1]),
-		      nla_len(tb[1]), NULL) < 0)
+	if (nla_parse_nested(tb2, TCA_ACT_MAX, tb[1], NULL) < 0)
 		return NULL;
 	kind = tb2[TCA_ACT_KIND];
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 667dc38..6b07fba 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -207,8 +207,11 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 			     u64 lastuse)
 {
-	tcf_lastuse_update(&a->tcfa_tm);
+	struct tcf_mirred *m = to_mirred(a);
+	struct tcf_t *tm = &m->tcf_tm;
+
 	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+	tm->lastuse = lastuse;
 }
 
 static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2ee29a3..2b2a797 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -345,7 +345,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 			if (err == 0) {
 				struct tcf_proto *next = rtnl_dereference(tp->next);
 
-				tfilter_notify(net, skb, n, tp, fh,
+				tfilter_notify(net, skb, n, tp,
+					       t->tcm_handle,
 					       RTM_DELTFILTER, false);
 				if (tcf_destroy(tp, false))
 					RCU_INIT_POINTER(*back, next);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 2a5c189..6cb0df8 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -418,6 +418,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	__u8 has_data = 0;
 	int gso = 0;
 	int pktcount = 0;
+	int auth_len = 0;
 	struct dst_entry *dst;
 	unsigned char *auth = NULL;	/* pointer to auth in skb data */
 
@@ -510,7 +511,12 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 			list_for_each_entry(chunk, &packet->chunk_list, list) {
 				int padded = SCTP_PAD4(chunk->skb->len);
 
-				if (pkt_size + padded > tp->pathmtu)
+				if (chunk == packet->auth)
+					auth_len = padded;
+				else if (auth_len + padded + packet->overhead >
+					 tp->pathmtu)
+					goto nomem;
+				else if (pkt_size + padded > tp->pathmtu)
 					break;
 				pkt_size += padded;
 			}
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 026e3bc..8ec20a6 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3422,6 +3422,12 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
 			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
 						  commands);
 
+		/* Report violation if chunk len overflows */
+		ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length));
+		if (ch_end > skb_tail_pointer(skb))
+			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+						  commands);
+
 		/* Now that we know we at least have a chunk header,
 		 * do things that are type appropriate.
 		 */
@@ -3453,12 +3459,6 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
 			}
 		}
 
-		/* Report violation if chunk len overflows */
-		ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length));
-		if (ch_end > skb_tail_pointer(skb))
-			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
-						  commands);
-
 		ch = (sctp_chunkhdr_t *) ch_end;
 	} while (ch_end < skb_tail_pointer(skb));
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fb02c70..9fbb6fe 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4687,7 +4687,7 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len,
 static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval,
 				  int __user *optlen)
 {
-	if (len <= 0)
+	if (len == 0)
 		return -EINVAL;
 	if (len > sizeof(struct sctp_event_subscribe))
 		len = sizeof(struct sctp_event_subscribe);
@@ -6430,6 +6430,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	if (get_user(len, optlen))
 		return -EFAULT;
 
+	if (len < 0)
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	switch (optname) {
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index d8bd97a..3dfd769 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1616,7 +1616,7 @@ gss_validate(struct rpc_task *task, __be32 *p)
 {
 	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 	struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
-	__be32		seq;
+	__be32		*seq = NULL;
 	struct kvec	iov;
 	struct xdr_buf	verf_buf;
 	struct xdr_netobj mic;
@@ -1631,9 +1631,12 @@ gss_validate(struct rpc_task *task, __be32 *p)
 		goto out_bad;
 	if (flav != RPC_AUTH_GSS)
 		goto out_bad;
-	seq = htonl(task->tk_rqstp->rq_seqno);
-	iov.iov_base = &seq;
-	iov.iov_len = sizeof(seq);
+	seq = kmalloc(4, GFP_NOFS);
+	if (!seq)
+		goto out_bad;
+	*seq = htonl(task->tk_rqstp->rq_seqno);
+	iov.iov_base = seq;
+	iov.iov_len = 4;
 	xdr_buf_from_iov(&iov, &verf_buf);
 	mic.data = (u8 *)p;
 	mic.len = len;
@@ -1653,11 +1656,13 @@ gss_validate(struct rpc_task *task, __be32 *p)
 	gss_put_ctx(ctx);
 	dprintk("RPC: %5u %s: gss_verify_mic succeeded.\n",
 			task->tk_pid, __func__);
+	kfree(seq);
 	return p + XDR_QUADLEN(len);
 out_bad:
 	gss_put_ctx(ctx);
 	dprintk("RPC: %5u %s failed ret %ld.\n", task->tk_pid, __func__,
 		PTR_ERR(ret));
+	kfree(seq);
 	return ret;
 }
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 244245b..90115ce 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -166,8 +166,8 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
 		       unsigned int usage, struct xdr_netobj *cksumout)
 {
 	struct scatterlist              sg[1];
-	int err;
-	u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
+	int err = -1;
+	u8 *checksumdata;
 	u8 rc4salt[4];
 	struct crypto_ahash *md5;
 	struct crypto_ahash *hmac_md5;
@@ -187,23 +187,22 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
 		return GSS_S_FAILURE;
 	}
 
+	checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
+	if (!checksumdata)
+		return GSS_S_FAILURE;
+
 	md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(md5))
-		return GSS_S_FAILURE;
+		goto out_free_cksum;
 
 	hmac_md5 = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0,
 				      CRYPTO_ALG_ASYNC);
-	if (IS_ERR(hmac_md5)) {
-		crypto_free_ahash(md5);
-		return GSS_S_FAILURE;
-	}
+	if (IS_ERR(hmac_md5))
+		goto out_free_md5;
 
 	req = ahash_request_alloc(md5, GFP_KERNEL);
-	if (!req) {
-		crypto_free_ahash(hmac_md5);
-		crypto_free_ahash(md5);
-		return GSS_S_FAILURE;
-	}
+	if (!req)
+		goto out_free_hmac_md5;
 
 	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
 
@@ -232,11 +231,8 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
 
 	ahash_request_free(req);
 	req = ahash_request_alloc(hmac_md5, GFP_KERNEL);
-	if (!req) {
-		crypto_free_ahash(hmac_md5);
-		crypto_free_ahash(md5);
-		return GSS_S_FAILURE;
-	}
+	if (!req)
+		goto out_free_hmac_md5;
 
 	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
 
@@ -258,8 +254,12 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
 	cksumout->len = kctx->gk5e->cksumlength;
 out:
 	ahash_request_free(req);
-	crypto_free_ahash(md5);
+out_free_hmac_md5:
 	crypto_free_ahash(hmac_md5);
+out_free_md5:
+	crypto_free_ahash(md5);
+out_free_cksum:
+	kfree(checksumdata);
 	return err ? GSS_S_FAILURE : 0;
 }
 
@@ -276,8 +276,8 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 	struct crypto_ahash *tfm;
 	struct ahash_request *req;
 	struct scatterlist              sg[1];
-	int err;
-	u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
+	int err = -1;
+	u8 *checksumdata;
 	unsigned int checksumlen;
 
 	if (kctx->gk5e->ctype == CKSUMTYPE_HMAC_MD5_ARCFOUR)
@@ -291,15 +291,17 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 		return GSS_S_FAILURE;
 	}
 
-	tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(tfm))
+	checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
+	if (checksumdata == NULL)
 		return GSS_S_FAILURE;
 
+	tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		goto out_free_cksum;
+
 	req = ahash_request_alloc(tfm, GFP_KERNEL);
-	if (!req) {
-		crypto_free_ahash(tfm);
-		return GSS_S_FAILURE;
-	}
+	if (!req)
+		goto out_free_ahash;
 
 	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
 
@@ -349,7 +351,10 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 	cksumout->len = kctx->gk5e->cksumlength;
 out:
 	ahash_request_free(req);
+out_free_ahash:
 	crypto_free_ahash(tfm);
+out_free_cksum:
+	kfree(checksumdata);
 	return err ? GSS_S_FAILURE : 0;
 }
 
@@ -368,8 +373,8 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
 	struct crypto_ahash *tfm;
 	struct ahash_request *req;
 	struct scatterlist sg[1];
-	int err;
-	u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
+	int err = -1;
+	u8 *checksumdata;
 	unsigned int checksumlen;
 
 	if (kctx->gk5e->keyed_cksum == 0) {
@@ -383,16 +388,18 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
 		return GSS_S_FAILURE;
 	}
 
+	checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
+	if (!checksumdata)
+		return GSS_S_FAILURE;
+
 	tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm))
-		return GSS_S_FAILURE;
+		goto out_free_cksum;
 	checksumlen = crypto_ahash_digestsize(tfm);
 
 	req = ahash_request_alloc(tfm, GFP_KERNEL);
-	if (!req) {
-		crypto_free_ahash(tfm);
-		return GSS_S_FAILURE;
-	}
+	if (!req)
+		goto out_free_ahash;
 
 	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
 
@@ -433,7 +440,10 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
 	}
 out:
 	ahash_request_free(req);
+out_free_ahash:
 	crypto_free_ahash(tfm);
+out_free_cksum:
+	kfree(checksumdata);
 	return err ? GSS_S_FAILURE : 0;
 }
 
@@ -666,14 +676,17 @@ gss_krb5_cts_crypt(struct crypto_skcipher *cipher, struct xdr_buf *buf,
 	u32 ret;
 	struct scatterlist sg[1];
 	SKCIPHER_REQUEST_ON_STACK(req, cipher);
-	u8 data[GSS_KRB5_MAX_BLOCKSIZE * 2];
+	u8 *data;
 	struct page **save_pages;
 	u32 len = buf->len - offset;
 
-	if (len > ARRAY_SIZE(data)) {
+	if (len > GSS_KRB5_MAX_BLOCKSIZE * 2) {
 		WARN_ON(0);
 		return -ENOMEM;
 	}
+	data = kmalloc(GSS_KRB5_MAX_BLOCKSIZE * 2, GFP_NOFS);
+	if (!data)
+		return -ENOMEM;
 
 	/*
 	 * For encryption, we want to read from the cleartext
@@ -708,6 +721,7 @@ gss_krb5_cts_crypt(struct crypto_skcipher *cipher, struct xdr_buf *buf,
 	ret = write_bytes_to_xdr_buf(buf, offset, data, len);
 
 out:
+	kfree(data);
 	return ret;
 }
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index d67f7e1..45662d7 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -718,30 +718,37 @@ gss_write_null_verf(struct svc_rqst *rqstp)
 static int
 gss_write_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq)
 {
-	__be32			xdr_seq;
+	__be32			*xdr_seq;
 	u32			maj_stat;
 	struct xdr_buf		verf_data;
 	struct xdr_netobj	mic;
 	__be32			*p;
 	struct kvec		iov;
+	int err = -1;
 
 	svc_putnl(rqstp->rq_res.head, RPC_AUTH_GSS);
-	xdr_seq = htonl(seq);
+	xdr_seq = kmalloc(4, GFP_KERNEL);
+	if (!xdr_seq)
+		return -1;
+	*xdr_seq = htonl(seq);
 
-	iov.iov_base = &xdr_seq;
-	iov.iov_len = sizeof(xdr_seq);
+	iov.iov_base = xdr_seq;
+	iov.iov_len = 4;
 	xdr_buf_from_iov(&iov, &verf_data);
 	p = rqstp->rq_res.head->iov_base + rqstp->rq_res.head->iov_len;
 	mic.data = (u8 *)(p + 1);
 	maj_stat = gss_get_mic(ctx_id, &verf_data, &mic);
 	if (maj_stat != GSS_S_COMPLETE)
-		return -1;
+		goto out;
 	*p++ = htonl(mic.len);
 	memset((u8 *)p + mic.len, 0, round_up_to_quad(mic.len) - mic.len);
 	p += XDR_QUADLEN(mic.len);
 	if (!xdr_ressize_check(rqstp, p))
-		return -1;
-	return 0;
+		goto out;
+	err = 0;
+out:
+	kfree(xdr_seq);
+	return err;
 }
 
 struct gss_domain {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 2d8545c..20027f8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -177,18 +177,26 @@ xprt_rdma_bc_allocate(struct rpc_task *task)
 		return -EINVAL;
 	}
 
+	/* svc_rdma_sendto releases this page */
 	page = alloc_page(RPCRDMA_DEF_GFP);
 	if (!page)
 		return -ENOMEM;
-
 	rqst->rq_buffer = page_address(page);
+
+	rqst->rq_rbuffer = kmalloc(rqst->rq_rcvsize, RPCRDMA_DEF_GFP);
+	if (!rqst->rq_rbuffer) {
+		put_page(page);
+		return -ENOMEM;
+	}
 	return 0;
 }
 
 static void
 xprt_rdma_bc_free(struct rpc_task *task)
 {
-	/* No-op: ctxt and page have already been freed. */
+	struct rpc_rqst *rqst = task->tk_rqstp;
+
+	kfree(rqst->rq_rbuffer);
 }
 
 static int
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 0137af1..e01c825 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2563,6 +2563,7 @@ static int bc_malloc(struct rpc_task *task)
 	buf->len = PAGE_SIZE;
 
 	rqst->rq_buffer = buf->data;
+	rqst->rq_rbuffer = (char *)rqst->rq_buffer + rqst->rq_callsize;
 	return 0;
 }
 
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 02beb35..3b95fe9 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -771,6 +771,9 @@ int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	u32 mask = BR_LEARNING | BR_LEARNING_SYNC | BR_FLOOD;
 	int err;
 
+	if (!netif_is_bridge_port(dev))
+		return -EOPNOTSUPP;
+
 	err = switchdev_port_attr_get(dev, &attr);
 	if (err && err != -EOPNOTSUPP)
 		return err;
@@ -926,6 +929,9 @@ int switchdev_port_bridge_setlink(struct net_device *dev,
 	struct nlattr *afspec;
 	int err = 0;
 
+	if (!netif_is_bridge_port(dev))
+		return -EOPNOTSUPP;
+
 	protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
 				   IFLA_PROTINFO);
 	if (protinfo) {
@@ -959,6 +965,9 @@ int switchdev_port_bridge_dellink(struct net_device *dev,
 {
 	struct nlattr *afspec;
 
+	if (!netif_is_bridge_port(dev))
+		return -EOPNOTSUPP;
+
 	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
 				 IFLA_AF_SPEC);
 	if (afspec)
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 753f774..aa1babb 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -247,11 +247,17 @@ int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb)
  *
  * RCU is locked, no other locks set
  */
-void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, u32 acked)
+void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l,
+			struct tipc_msg *hdr)
 {
 	struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq;
+	u16 acked = msg_bcast_ack(hdr);
 	struct sk_buff_head xmitq;
 
+	/* Ignore bc acks sent by peer before bcast synch point was received */
+	if (msg_bc_ack_invalid(hdr))
+		return;
+
 	__skb_queue_head_init(&xmitq);
 
 	tipc_bcast_lock(net);
@@ -279,11 +285,11 @@ int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
 	__skb_queue_head_init(&xmitq);
 
 	tipc_bcast_lock(net);
-	if (msg_type(hdr) == STATE_MSG) {
+	if (msg_type(hdr) != STATE_MSG) {
+		tipc_link_bc_init_rcv(l, hdr);
+	} else if (!msg_bc_ack_invalid(hdr)) {
 		tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr), &xmitq);
 		rc = tipc_link_bc_sync_rcv(l, hdr, &xmitq);
-	} else {
-		tipc_link_bc_init_rcv(l, hdr);
 	}
 	tipc_bcast_unlock(net);
 
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index 5ffe344..855d53c 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -55,7 +55,8 @@ void tipc_bcast_dec_bearer_dst_cnt(struct net *net, int bearer_id);
 int  tipc_bcast_get_mtu(struct net *net);
 int tipc_bcast_xmit(struct net *net, struct sk_buff_head *list);
 int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb);
-void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, u32 acked);
+void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l,
+			struct tipc_msg *hdr);
 int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
 			struct tipc_msg *hdr);
 int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index b36e16c..1055164 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1312,6 +1312,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 	msg_set_next_sent(hdr, l->snd_nxt);
 	msg_set_ack(hdr, l->rcv_nxt - 1);
 	msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1);
+	msg_set_bc_ack_invalid(hdr, !node_up);
 	msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1);
 	msg_set_link_tolerance(hdr, tolerance);
 	msg_set_linkprio(hdr, priority);
@@ -1574,6 +1575,7 @@ static void tipc_link_build_bc_init_msg(struct tipc_link *l,
 	__skb_queue_head_init(&list);
 	if (!tipc_link_build_bc_proto_msg(l->bc_rcvlink, false, 0, &list))
 		return;
+	msg_set_bc_ack_invalid(buf_msg(skb_peek(&list)), true);
 	tipc_link_xmit(l, &list, xmitq);
 }
 
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index c3832cd..50a7398 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -714,6 +714,23 @@ static inline void msg_set_peer_stopping(struct tipc_msg *m, u32 s)
 	msg_set_bits(m, 5, 13, 0x1, s);
 }
 
+static inline bool msg_bc_ack_invalid(struct tipc_msg *m)
+{
+	switch (msg_user(m)) {
+	case BCAST_PROTOCOL:
+	case NAME_DISTRIBUTOR:
+	case LINK_PROTOCOL:
+		return msg_bits(m, 5, 14, 0x1);
+	default:
+		return false;
+	}
+}
+
+static inline void msg_set_bc_ack_invalid(struct tipc_msg *m, bool invalid)
+{
+	msg_set_bits(m, 5, 14, 0x1, invalid);
+}
+
 static inline char *msg_media_addr(struct tipc_msg *m)
 {
 	return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET];
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index a04fe9b..c1cfd92 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -156,6 +156,7 @@ static void named_distribute(struct net *net, struct sk_buff_head *list,
 				pr_warn("Bulk publication failure\n");
 				return;
 			}
+			msg_set_bc_ack_invalid(buf_msg(skb), true);
 			item = (struct distr_item *)msg_data(buf_msg(skb));
 		}
 
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 7ef14e2..9d2f4c2 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1535,7 +1535,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 	if (unlikely(usr == LINK_PROTOCOL))
 		tipc_node_bc_sync_rcv(n, hdr, bearer_id, &xmitq);
 	else if (unlikely(tipc_link_acked(n->bc_entry.link) != bc_ack))
-		tipc_bcast_ack_rcv(net, n->bc_entry.link, bc_ack);
+		tipc_bcast_ack_rcv(net, n->bc_entry.link, hdr);
 
 	/* Receive packet directly if conditions permit */
 	tipc_node_read_lock(n);
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 0082f4b..14b3f00 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -104,13 +104,16 @@ static int wiphy_suspend(struct device *dev)
 
 	rtnl_lock();
 	if (rdev->wiphy.registered) {
-		if (!rdev->wiphy.wowlan_config)
+		if (!rdev->wiphy.wowlan_config) {
 			cfg80211_leave_all(rdev);
+			cfg80211_process_rdev_events(rdev);
+		}
 		if (rdev->ops->suspend)
 			ret = rdev_suspend(rdev, rdev->wiphy.wowlan_config);
 		if (ret == 1) {
 			/* Driver refuse to configure wowlan */
 			cfg80211_leave_all(rdev);
+			cfg80211_process_rdev_events(rdev);
 			ret = rdev_suspend(rdev, NULL);
 		}
 	}
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 8edce22..5ea12af 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -420,8 +420,8 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr)
 }
 EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen);
 
-static int __ieee80211_data_to_8023(struct sk_buff *skb, struct ethhdr *ehdr,
-				    const u8 *addr, enum nl80211_iftype iftype)
+int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
+				  const u8 *addr, enum nl80211_iftype iftype)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	struct {
@@ -525,13 +525,7 @@ static int __ieee80211_data_to_8023(struct sk_buff *skb, struct ethhdr *ehdr,
 
 	return 0;
 }
-
-int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
-			   enum nl80211_iftype iftype)
-{
-	return __ieee80211_data_to_8023(skb, NULL, addr, iftype);
-}
-EXPORT_SYMBOL(ieee80211_data_to_8023);
+EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr);
 
 int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
 			     enum nl80211_iftype iftype,
@@ -746,24 +740,18 @@ __ieee80211_amsdu_copy(struct sk_buff *skb, unsigned int hlen,
 void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 			      const u8 *addr, enum nl80211_iftype iftype,
 			      const unsigned int extra_headroom,
-			      bool has_80211_header)
+			      const u8 *check_da, const u8 *check_sa)
 {
 	unsigned int hlen = ALIGN(extra_headroom, 4);
 	struct sk_buff *frame = NULL;
 	u16 ethertype;
 	u8 *payload;
-	int offset = 0, remaining, err;
+	int offset = 0, remaining;
 	struct ethhdr eth;
 	bool reuse_frag = skb->head_frag && !skb_has_frag_list(skb);
 	bool reuse_skb = false;
 	bool last = false;
 
-	if (has_80211_header) {
-		err = __ieee80211_data_to_8023(skb, &eth, addr, iftype);
-		if (err)
-			goto out;
-	}
-
 	while (!last) {
 		unsigned int subframe_len;
 		int len;
@@ -780,8 +768,17 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 			goto purge;
 
 		offset += sizeof(struct ethhdr);
-		/* reuse skb for the last subframe */
 		last = remaining <= subframe_len + padding;
+
+		/* FIXME: should we really accept multicast DA? */
+		if ((check_da && !is_multicast_ether_addr(eth.h_dest) &&
+		     !ether_addr_equal(check_da, eth.h_dest)) ||
+		    (check_sa && !ether_addr_equal(check_sa, eth.h_source))) {
+			offset += len + padding;
+			continue;
+		}
+
+		/* reuse skb for the last subframe */
 		if (!skb_is_nonlinear(skb) && !reuse_frag && last) {
 			skb_pull(skb, offset);
 			frame = skb;
@@ -819,7 +816,6 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 
  purge:
 	__skb_queue_purge(list);
- out:
 	dev_kfree_skb(skb);
 }
 EXPORT_SYMBOL(ieee80211_amsdu_to_8023s);
diff --git a/samples/bpf/parse_ldabs.c b/samples/bpf/parse_ldabs.c
index d175501..6db6b21 100644
--- a/samples/bpf/parse_ldabs.c
+++ b/samples/bpf/parse_ldabs.c
@@ -4,6 +4,7 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
+#define KBUILD_MODNAME "foo"
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
diff --git a/samples/bpf/parse_simple.c b/samples/bpf/parse_simple.c
index cf2511c..10af53d 100644
--- a/samples/bpf/parse_simple.c
+++ b/samples/bpf/parse_simple.c
@@ -4,6 +4,7 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
+#define KBUILD_MODNAME "foo"
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c
index edab34d..95c1632 100644
--- a/samples/bpf/parse_varlen.c
+++ b/samples/bpf/parse_varlen.c
@@ -4,6 +4,7 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
+#define KBUILD_MODNAME "foo"
 #include <linux/if_ether.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c
index fa051b3..274c884 100644
--- a/samples/bpf/tcbpf1_kern.c
+++ b/samples/bpf/tcbpf1_kern.c
@@ -1,3 +1,4 @@
+#define KBUILD_MODNAME "foo"
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/if_ether.h>
 #include <uapi/linux/if_packet.h>
diff --git a/samples/bpf/tcbpf2_kern.c b/samples/bpf/tcbpf2_kern.c
index 3303bb8..9c823a6 100644
--- a/samples/bpf/tcbpf2_kern.c
+++ b/samples/bpf/tcbpf2_kern.c
@@ -5,6 +5,7 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
+#define KBUILD_MODNAME "foo"
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/if_ether.h>
 #include <uapi/linux/if_packet.h>
diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c
index 10ff734..1547b36 100644
--- a/samples/bpf/test_cgrp2_tc_kern.c
+++ b/samples/bpf/test_cgrp2_tc_kern.c
@@ -4,6 +4,7 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
+#define KBUILD_MODNAME "foo"
 #include <uapi/linux/if_ether.h>
 #include <uapi/linux/in6.h>
 #include <uapi/linux/ipv6.h>
diff --git a/scripts/gcc-plugins/cyc_complexity_plugin.c b/scripts/gcc-plugins/cyc_complexity_plugin.c
index 34df974..8af7db0 100644
--- a/scripts/gcc-plugins/cyc_complexity_plugin.c
+++ b/scripts/gcc-plugins/cyc_complexity_plugin.c
@@ -20,7 +20,7 @@
 
 #include "gcc-common.h"
 
-int plugin_is_GPL_compatible;
+__visible int plugin_is_GPL_compatible;
 
 static struct plugin_info cyc_complexity_plugin_info = {
 	.version	= "20160225",
@@ -49,7 +49,7 @@ static unsigned int cyc_complexity_execute(void)
 
 #include "gcc-generate-gimple-pass.h"
 
-int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
+__visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
 {
 	const char * const plugin_name = plugin_info->base_name;
 	struct register_pass_info cyc_complexity_pass_info;
diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h
index 172850b..950fd2e 100644
--- a/scripts/gcc-plugins/gcc-common.h
+++ b/scripts/gcc-plugins/gcc-common.h
@@ -130,6 +130,7 @@ extern void dump_gimple_stmt(pretty_printer *, gimple, int, int);
 #endif
 
 #define __unused __attribute__((__unused__))
+#define __visible __attribute__((visibility("default")))
 
 #define DECL_NAME_POINTER(node) IDENTIFIER_POINTER(DECL_NAME(node))
 #define DECL_NAME_LENGTH(node) IDENTIFIER_LENGTH(DECL_NAME(node))
diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c
index ff1939b..8160f1c 100644
--- a/scripts/gcc-plugins/latent_entropy_plugin.c
+++ b/scripts/gcc-plugins/latent_entropy_plugin.c
@@ -77,7 +77,7 @@
 
 #include "gcc-common.h"
 
-int plugin_is_GPL_compatible;
+__visible int plugin_is_GPL_compatible;
 
 static GTY(()) tree latent_entropy_decl;
 
@@ -340,7 +340,7 @@ static enum tree_code get_op(tree *rhs)
 		break;
 	}
 	if (rhs)
-		*rhs = build_int_cstu(unsigned_intDI_type_node, random_const);
+		*rhs = build_int_cstu(long_unsigned_type_node, random_const);
 	return op;
 }
 
@@ -372,7 +372,7 @@ static void __perturb_latent_entropy(gimple_stmt_iterator *gsi,
 	enum tree_code op;
 
 	/* 1. create temporary copy of latent_entropy */
-	temp = create_var(unsigned_intDI_type_node, "tmp_latent_entropy");
+	temp = create_var(long_unsigned_type_node, "temp_latent_entropy");
 
 	/* 2. read... */
 	add_referenced_var(latent_entropy_decl);
@@ -459,13 +459,13 @@ static void init_local_entropy(basic_block bb, tree local_entropy)
 	gsi_insert_before(&gsi, call, GSI_NEW_STMT);
 	update_stmt(call);
 
-	udi_frame_addr = fold_convert(unsigned_intDI_type_node, frame_addr);
+	udi_frame_addr = fold_convert(long_unsigned_type_node, frame_addr);
 	assign = gimple_build_assign(local_entropy, udi_frame_addr);
 	gsi_insert_after(&gsi, assign, GSI_NEW_STMT);
 	update_stmt(assign);
 
 	/* 3. create temporary copy of latent_entropy */
-	tmp = create_var(unsigned_intDI_type_node, "tmp_latent_entropy");
+	tmp = create_var(long_unsigned_type_node, "temp_latent_entropy");
 
 	/* 4. read the global entropy variable into local entropy */
 	add_referenced_var(latent_entropy_decl);
@@ -480,7 +480,7 @@ static void init_local_entropy(basic_block bb, tree local_entropy)
 	update_stmt(assign);
 
 	rand_cst = get_random_const();
-	rand_const = build_int_cstu(unsigned_intDI_type_node, rand_cst);
+	rand_const = build_int_cstu(long_unsigned_type_node, rand_cst);
 	op = get_op(NULL);
 	assign = create_assign(op, local_entropy, local_entropy, rand_const);
 	gsi_insert_after(&gsi, assign, GSI_NEW_STMT);
@@ -529,7 +529,7 @@ static unsigned int latent_entropy_execute(void)
 	}
 
 	/* 1. create the local entropy variable */
-	local_entropy = create_var(unsigned_intDI_type_node, "local_entropy");
+	local_entropy = create_var(long_unsigned_type_node, "local_entropy");
 
 	/* 2. initialize the local entropy variable */
 	init_local_entropy(bb, local_entropy);
@@ -561,10 +561,9 @@ static void latent_entropy_start_unit(void *gcc_data __unused,
 	if (in_lto_p)
 		return;
 
-	/* extern volatile u64 latent_entropy */
-	gcc_assert(TYPE_PRECISION(long_long_unsigned_type_node) == 64);
-	quals = TYPE_QUALS(long_long_unsigned_type_node) | TYPE_QUAL_VOLATILE;
-	type = build_qualified_type(long_long_unsigned_type_node, quals);
+	/* extern volatile unsigned long latent_entropy */
+	quals = TYPE_QUALS(long_unsigned_type_node) | TYPE_QUAL_VOLATILE;
+	type = build_qualified_type(long_unsigned_type_node, quals);
 	id = get_identifier("latent_entropy");
 	latent_entropy_decl = build_decl(UNKNOWN_LOCATION, VAR_DECL, id, type);
 
@@ -584,8 +583,8 @@ static void latent_entropy_start_unit(void *gcc_data __unused,
 	| TODO_update_ssa
 #include "gcc-generate-gimple-pass.h"
 
-int plugin_init(struct plugin_name_args *plugin_info,
-		struct plugin_gcc_version *version)
+__visible int plugin_init(struct plugin_name_args *plugin_info,
+			  struct plugin_gcc_version *version)
 {
 	bool enabled = true;
 	const char * const plugin_name = plugin_info->base_name;
diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c
index aedd611..7ea0b3f 100644
--- a/scripts/gcc-plugins/sancov_plugin.c
+++ b/scripts/gcc-plugins/sancov_plugin.c
@@ -21,7 +21,7 @@
 
 #include "gcc-common.h"
 
-int plugin_is_GPL_compatible;
+__visible int plugin_is_GPL_compatible;
 
 tree sancov_fndecl;
 
@@ -86,7 +86,7 @@ static void sancov_start_unit(void __unused *gcc_data, void __unused *user_data)
 #endif
 }
 
-int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
+__visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
 {
 	int i;
 	struct register_pass_info sancov_plugin_pass_info;
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index f826e87..d942c7c 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -41,7 +41,7 @@
 	bool "Large payload keys"
 	depends on KEYS
 	depends on TMPFS
-	select CRYPTO
+	depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y)
 	select CRYPTO_AES
 	select CRYPTO_ECB
 	select CRYPTO_RNG
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index c0b3030..835c1ab 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -9,6 +9,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) "big_key: "fmt
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/file.h>
@@ -341,44 +342,48 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
  */
 static int __init big_key_init(void)
 {
-	return register_key_type(&key_type_big_key);
-}
+	struct crypto_skcipher *cipher;
+	struct crypto_rng *rng;
+	int ret;
 
-/*
- * Initialize big_key crypto and RNG algorithms
- */
-static int __init big_key_crypto_init(void)
-{
-	int ret = -EINVAL;
-
-	/* init RNG */
-	big_key_rng = crypto_alloc_rng(big_key_rng_name, 0, 0);
-	if (IS_ERR(big_key_rng)) {
-		big_key_rng = NULL;
-		return -EFAULT;
+	rng = crypto_alloc_rng(big_key_rng_name, 0, 0);
+	if (IS_ERR(rng)) {
+		pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng));
+		return PTR_ERR(rng);
 	}
 
+	big_key_rng = rng;
+
 	/* seed RNG */
-	ret = crypto_rng_reset(big_key_rng, NULL, crypto_rng_seedsize(big_key_rng));
-	if (ret)
-		goto error;
+	ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng));
+	if (ret) {
+		pr_err("Can't reset rng: %d\n", ret);
+		goto error_rng;
+	}
 
 	/* init block cipher */
-	big_key_skcipher = crypto_alloc_skcipher(big_key_alg_name,
-						 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(big_key_skcipher)) {
-		big_key_skcipher = NULL;
-		ret = -EFAULT;
-		goto error;
+	cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(cipher)) {
+		ret = PTR_ERR(cipher);
+		pr_err("Can't alloc crypto: %d\n", ret);
+		goto error_rng;
+	}
+
+	big_key_skcipher = cipher;
+
+	ret = register_key_type(&key_type_big_key);
+	if (ret < 0) {
+		pr_err("Can't register type: %d\n", ret);
+		goto error_cipher;
 	}
 
 	return 0;
 
-error:
+error_cipher:
+	crypto_free_skcipher(big_key_skcipher);
+error_rng:
 	crypto_free_rng(big_key_rng);
-	big_key_rng = NULL;
 	return ret;
 }
 
-device_initcall(big_key_init);
-late_initcall(big_key_crypto_init);
+late_initcall(big_key_init);
diff --git a/security/keys/proc.c b/security/keys/proc.c
index f0611a6..b9f531c 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -181,7 +181,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 	struct timespec now;
 	unsigned long timo;
 	key_ref_t key_ref, skey_ref;
-	char xbuf[12];
+	char xbuf[16];
 	int rc;
 
 	struct keyring_search_context ctx = {
diff --git a/sound/core/info.c b/sound/core/info.c
index 895362a..8ab72e0 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -325,10 +325,15 @@ static ssize_t snd_info_text_entry_write(struct file *file,
 	size_t next;
 	int err = 0;
 
+	if (!entry->c.text.write)
+		return -EIO;
 	pos = *offset;
 	if (!valid_pos(pos, count))
 		return -EIO;
 	next = pos + count;
+	/* don't handle too large text inputs */
+	if (next > 16 * 1024)
+		return -EIO;
 	mutex_lock(&entry->access);
 	buf = data->wbuffer;
 	if (!buf) {
@@ -366,7 +371,9 @@ static int snd_info_seq_show(struct seq_file *seq, void *p)
 	struct snd_info_private_data *data = seq->private;
 	struct snd_info_entry *entry = data->entry;
 
-	if (entry->c.text.read) {
+	if (!entry->c.text.read) {
+		return -EIO;
+	} else {
 		data->rbuffer->buffer = (char *)seq; /* XXX hack! */
 		entry->c.text.read(entry, data->rbuffer);
 	}
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index dcc10281..37d9cfb 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -448,8 +448,8 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr)
 
 		ktime_get_ts64(&tm);
 		tm = timespec64_sub(tm, tmr->last_update);
-		cur_time.tv_nsec = tm.tv_nsec;
-		cur_time.tv_sec = tm.tv_sec;
+		cur_time.tv_nsec += tm.tv_nsec;
+		cur_time.tv_sec += tm.tv_sec;
 		snd_seq_sanity_real_time(&cur_time);
 	}
 	spin_unlock_irqrestore(&tmr->lock, flags);
diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c
index d17937b..7e3aa50 100644
--- a/sound/pci/asihpi/hpioctl.c
+++ b/sound/pci/asihpi/hpioctl.c
@@ -111,7 +111,7 @@ long asihpi_hpi_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return -EINVAL;
 
 	hm = kmalloc(sizeof(*hm), GFP_KERNEL);
-	hr = kmalloc(sizeof(*hr), GFP_KERNEL);
+	hr = kzalloc(sizeof(*hr), GFP_KERNEL);
 	if (!hm || !hr) {
 		err = -ENOMEM;
 		goto out;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index c3469f7..c64d986 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -341,8 +341,7 @@ enum {
 
 /* quirks for Nvidia */
 #define AZX_DCAPS_PRESET_NVIDIA \
-	(AZX_DCAPS_NO_MSI | /*AZX_DCAPS_ALIGN_BUFSIZE |*/ \
-	 AZX_DCAPS_NO_64BIT | AZX_DCAPS_CORBRP_SELF_CLEAR |\
+	(AZX_DCAPS_NO_MSI | AZX_DCAPS_CORBRP_SELF_CLEAR |\
 	 AZX_DCAPS_SNOOP_TYPE(NVIDIA))
 
 #define AZX_DCAPS_PRESET_CTHDA \
@@ -1716,6 +1715,10 @@ static int azx_first_init(struct azx *chip)
 		}
 	}
 
+	/* NVidia hardware normally only supports up to 40 bits of DMA */
+	if (chip->pci->vendor == PCI_VENDOR_ID_NVIDIA)
+		dma_bits = 40;
+
 	/* disable 64bit DMA address on some devices */
 	if (chip->driver_caps & AZX_DCAPS_NO_64BIT) {
 		dev_dbg(card->dev, "Disabling 64bit DMA\n");
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b58e8c7..2f909dd 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5811,8 +5811,6 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 #define ALC295_STANDARD_PINS \
 	{0x12, 0xb7a60130}, \
 	{0x14, 0x90170110}, \
-	{0x17, 0x21014020}, \
-	{0x18, 0x21a19030}, \
 	{0x21, 0x04211020}
 
 #define ALC298_STANDARD_PINS \
@@ -5859,11 +5857,19 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x1b, 0x02011020},
 		{0x21, 0x0221101f}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170110},
+		{0x1b, 0x01011020},
+		{0x21, 0x0221101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x14, 0x90170130},
 		{0x1b, 0x01014020},
 		{0x21, 0x0221103f}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x14, 0x90170130},
+		{0x1b, 0x01011020},
+		{0x21, 0x0221103f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170130},
 		{0x1b, 0x02011020},
 		{0x21, 0x0221103f}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -6039,7 +6045,13 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		ALC292_STANDARD_PINS,
 		{0x13, 0x90a60140}),
 	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-		ALC295_STANDARD_PINS),
+		ALC295_STANDARD_PINS,
+		{0x17, 0x21014020},
+		{0x18, 0x21a19030}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC295_STANDARD_PINS,
+		{0x17, 0x21014040},
+		{0x18, 0x21a19050}),
 	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC298_STANDARD_PINS,
 		{0x17, 0x90170110}),
@@ -6613,6 +6625,7 @@ enum {
 	ALC891_FIXUP_HEADSET_MODE,
 	ALC891_FIXUP_DELL_MIC_NO_PRESENCE,
 	ALC662_FIXUP_ACER_VERITON,
+	ALC892_FIXUP_ASROCK_MOBO,
 };
 
 static const struct hda_fixup alc662_fixups[] = {
@@ -6889,6 +6902,16 @@ static const struct hda_fixup alc662_fixups[] = {
 			{ }
 		}
 	},
+	[ALC892_FIXUP_ASROCK_MOBO] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x15, 0x40f000f0 }, /* disabled */
+			{ 0x16, 0x40f000f0 }, /* disabled */
+			{ 0x18, 0x01014011 }, /* LO */
+			{ 0x1a, 0x01014012 }, /* LO */
+			{ }
+		}
+	},
 };
 
 static const struct snd_pci_quirk alc662_fixup_tbl[] = {
@@ -6926,6 +6949,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
 	SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD),
+	SND_PCI_QUIRK(0x1849, 0x5892, "ASRock B150M", ALC892_FIXUP_ASROCK_MOBO),
 	SND_PCI_QUIRK(0x19da, 0xa130, "Zotac Z68", ALC662_FIXUP_ZOTAC_Z68),
 	SND_PCI_QUIRK(0x1b0a, 0x01b8, "ACER Veriton", ALC662_FIXUP_ACER_VERITON),
 	SND_PCI_QUIRK(0x1b35, 0x2206, "CZC P10T", ALC662_FIXUP_CZC_P10T),
diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index 18baea2..84f8674 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -148,11 +148,11 @@ SND_SOC_DAPM_OUTPUT("AOUTR"),
 };
 
 static const struct snd_soc_dapm_route cs4270_dapm_routes[] = {
-	{ "Capture", NULL, "AINA" },
-	{ "Capture", NULL, "AINB" },
+	{ "Capture", NULL, "AINL" },
+	{ "Capture", NULL, "AINR" },
 
-	{ "AOUTA", NULL, "Playback" },
-	{ "AOUTB", NULL, "Playback" },
+	{ "AOUTL", NULL, "Playback" },
+	{ "AOUTR", NULL, "Playback" },
 };
 
 /**
diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c
index 1152aa5..cf37936 100644
--- a/sound/soc/codecs/da7219.c
+++ b/sound/soc/codecs/da7219.c
@@ -880,7 +880,8 @@ static const struct snd_soc_dapm_widget da7219_dapm_widgets[] = {
 			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
 
 	/* DAI */
-	SND_SOC_DAPM_AIF_OUT("DAIOUT", "Capture", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("DAIOUT", "Capture", 0, DA7219_DAI_TDM_CTRL,
+			     DA7219_DAI_OE_SHIFT, DA7219_NO_INVERT),
 	SND_SOC_DAPM_AIF_IN("DAIIN", "Playback", 0, SND_SOC_NOPM, 0, 0),
 
 	/* Output Muxes */
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index b904492..90b5948 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -364,7 +364,12 @@ static int hdmi_of_xlate_dai_name(struct snd_soc_component *component,
 				  struct of_phandle_args *args,
 				  const char **dai_name)
 {
-	int id = args->args[0];
+	int id;
+
+	if (args->args_count)
+		id = args->args[0];
+	else
+		id = 0;
 
 	if (id < ARRAY_SIZE(hdmi_dai_name)) {
 		*dai_name = hdmi_dai_name[id];
diff --git a/sound/soc/codecs/rt298.c b/sound/soc/codecs/rt298.c
index 5555864..2db8179 100644
--- a/sound/soc/codecs/rt298.c
+++ b/sound/soc/codecs/rt298.c
@@ -249,6 +249,11 @@ static int rt298_jack_detect(struct rt298_priv *rt298, bool *hp, bool *mic)
 			snd_soc_dapm_force_enable_pin(dapm, "LDO1");
 			snd_soc_dapm_sync(dapm);
 
+			regmap_update_bits(rt298->regmap,
+				RT298_POWER_CTRL1, 0x1001, 0);
+			regmap_update_bits(rt298->regmap,
+				RT298_POWER_CTRL2, 0x4, 0x4);
+
 			regmap_write(rt298->regmap, RT298_SET_MIC1, 0x24);
 			msleep(50);
 
diff --git a/sound/soc/codecs/rt5663.c b/sound/soc/codecs/rt5663.c
index 01a18d8..00ff278 100644
--- a/sound/soc/codecs/rt5663.c
+++ b/sound/soc/codecs/rt5663.c
@@ -1547,11 +1547,11 @@ static int rt5663_jack_detect(struct snd_soc_codec *codec, int jack_insert)
 			msleep(sleep_time[i]);
 			val = snd_soc_read(codec, RT5663_EM_JACK_TYPE_2) &
 				0x0003;
+			dev_dbg(codec->dev, "%s: MX-00e7 val=%x sleep %d\n",
+				__func__, val, sleep_time[i]);
 			i++;
 			if (val == 0x1 || val == 0x2 || val == 0x3)
 				break;
-			dev_dbg(codec->dev, "%s: MX-00e7 val=%x sleep %d\n",
-				__func__, val, sleep_time[i]);
 		}
 		dev_dbg(codec->dev, "%s val = %d\n", __func__, val);
 		switch (val) {
diff --git a/sound/soc/codecs/sti-sas.c b/sound/soc/codecs/sti-sas.c
index 7b31ee9..d6e00c7 100644
--- a/sound/soc/codecs/sti-sas.c
+++ b/sound/soc/codecs/sti-sas.c
@@ -424,7 +424,7 @@ static const struct snd_soc_dai_ops stih407_dac_ops = {
 static const struct regmap_config stih407_sas_regmap = {
 	.reg_bits = 32,
 	.val_bits = 32,
-
+	.fast_io = true,
 	.max_register = STIH407_AUDIO_DAC_CTRL,
 	.reg_defaults = stih407_sas_reg_defaults,
 	.num_reg_defaults = ARRAY_SIZE(stih407_sas_reg_defaults),
diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c
index df5e5cb..810369f 100644
--- a/sound/soc/codecs/tas571x.c
+++ b/sound/soc/codecs/tas571x.c
@@ -341,20 +341,9 @@ static int tas571x_set_bias_level(struct snd_soc_codec *codec,
 					return ret;
 				}
 			}
-
-			gpiod_set_value(priv->pdn_gpio, 0);
-			usleep_range(5000, 6000);
-
-			regcache_cache_only(priv->regmap, false);
-			ret = regcache_sync(priv->regmap);
-			if (ret)
-				return ret;
 		}
 		break;
 	case SND_SOC_BIAS_OFF:
-		regcache_cache_only(priv->regmap, true);
-		gpiod_set_value(priv->pdn_gpio, 1);
-
 		if (!IS_ERR(priv->mclk))
 			clk_disable_unprepare(priv->mclk);
 		break;
@@ -401,16 +390,6 @@ static const struct snd_kcontrol_new tas5711_controls[] = {
 		   TAS571X_SOFT_MUTE_REG,
 		   TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
 		   1, 1),
-
-	SOC_DOUBLE_R_RANGE("CH1 Mixer Volume",
-			   TAS5717_CH1_LEFT_CH_MIX_REG,
-			   TAS5717_CH1_RIGHT_CH_MIX_REG,
-			   16, 0, 0x80, 0),
-
-	SOC_DOUBLE_R_RANGE("CH2 Mixer Volume",
-			   TAS5717_CH2_LEFT_CH_MIX_REG,
-			   TAS5717_CH2_RIGHT_CH_MIX_REG,
-			   16, 0, 0x80, 0),
 };
 
 static const struct regmap_range tas571x_readonly_regs_range[] = {
@@ -488,6 +467,16 @@ static const struct snd_kcontrol_new tas5717_controls[] = {
 		   TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
 		   1, 1),
 
+	SOC_DOUBLE_R_RANGE("CH1 Mixer Volume",
+			   TAS5717_CH1_LEFT_CH_MIX_REG,
+			   TAS5717_CH1_RIGHT_CH_MIX_REG,
+			   16, 0, 0x80, 0),
+
+	SOC_DOUBLE_R_RANGE("CH2 Mixer Volume",
+			   TAS5717_CH2_LEFT_CH_MIX_REG,
+			   TAS5717_CH2_RIGHT_CH_MIX_REG,
+			   16, 0, 0x80, 0),
+
 	/*
 	 * The biquads are named according to the register names.
 	 * Please note that TI's TAS57xx Graphical Development Environment
@@ -747,13 +736,14 @@ static int tas571x_i2c_probe(struct i2c_client *client,
 		/* pulse the active low reset line for ~100us */
 		usleep_range(100, 200);
 		gpiod_set_value(priv->reset_gpio, 0);
-		usleep_range(12000, 20000);
+		usleep_range(13500, 20000);
 	}
 
 	ret = regmap_write(priv->regmap, TAS571X_OSC_TRIM_REG, 0);
 	if (ret)
 		return ret;
 
+	usleep_range(50000, 60000);
 
 	memcpy(&priv->codec_driver, &tas571x_codec, sizeof(priv->codec_driver));
 	priv->codec_driver.component_driver.controls = priv->chip->controls;
@@ -770,9 +760,6 @@ static int tas571x_i2c_probe(struct i2c_client *client,
 			return ret;
 	}
 
-	regcache_cache_only(priv->regmap, true);
-	gpiod_set_value(priv->pdn_gpio, 1);
-
 	return snd_soc_register_codec(&client->dev, &priv->codec_driver,
 				      &tas571x_dai, 1);
 }
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 26eb5a0..fd5d1e0 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -47,6 +47,7 @@
 
 config SND_SOC_INTEL_HASWELL
 	tristate
+	select SND_SOC_INTEL_SST_FIRMWARE
 
 config SND_SOC_INTEL_BAYTRAIL
 	tristate
@@ -56,7 +57,6 @@
 	depends on X86_INTEL_LPSS && I2C && I2C_DESIGNWARE_PLATFORM
 	depends on DW_DMAC_CORE
 	select SND_SOC_INTEL_SST
-	select SND_SOC_INTEL_SST_FIRMWARE
 	select SND_SOC_INTEL_HASWELL
 	select SND_SOC_RT5640
 	help
@@ -138,7 +138,6 @@
 		   I2C_DESIGNWARE_PLATFORM
 	depends on DW_DMAC_CORE
 	select SND_SOC_INTEL_SST
-	select SND_SOC_INTEL_SST_FIRMWARE
 	select SND_SOC_INTEL_HASWELL
 	select SND_SOC_RT286
 	help
diff --git a/sound/soc/intel/atom/sst/sst_acpi.c b/sound/soc/intel/atom/sst/sst_acpi.c
index ba5c0d7..0a88537 100644
--- a/sound/soc/intel/atom/sst/sst_acpi.c
+++ b/sound/soc/intel/atom/sst/sst_acpi.c
@@ -416,6 +416,7 @@ static const struct dmi_system_id cht_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Surface 3"),
 		},
 	},
+	{ }
 };
 
 
diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index 6532b8f..865a21e 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -130,8 +130,8 @@ static int broxton_da7219_codec_init(struct snd_soc_pcm_runtime *rtd)
 	 */
 	ret = snd_soc_card_jack_new(rtd->card, "Headset Jack",
 			SND_JACK_HEADSET | SND_JACK_BTN_0 | SND_JACK_BTN_1 |
-			SND_JACK_BTN_2 | SND_JACK_BTN_3, &broxton_headset,
-			NULL, 0);
+			SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_LINEOUT,
+			&broxton_headset, NULL, 0);
 	if (ret) {
 		dev_err(rtd->dev, "Headset Jack creation failed: %d\n", ret);
 		return ret;
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 2989c16..06fa5e8 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -674,7 +674,7 @@ static int skl_probe(struct pci_dev *pci,
 
 	if (skl->nhlt == NULL) {
 		err = -ENODEV;
-		goto out_free;
+		goto out_display_power_off;
 	}
 
 	skl_nhlt_update_topology_bin(skl);
@@ -746,6 +746,9 @@ static int skl_probe(struct pci_dev *pci,
 	skl_machine_device_unregister(skl);
 out_nhlt_free:
 	skl_nhlt_free(skl->nhlt);
+out_display_power_off:
+	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
+		snd_hdac_display_power(bus, false);
 out_free:
 	skl->init_failed = 1;
 	skl_free(ebus);
@@ -785,8 +788,7 @@ static void skl_remove(struct pci_dev *pci)
 
 	release_firmware(skl->tplg);
 
-	if (pci_dev_run_wake(pci))
-		pm_runtime_get_noresume(&pci->dev);
+	pm_runtime_get_noresume(&pci->dev);
 
 	/* codec removal, invoke bus_device_remove */
 	snd_hdac_ext_bus_device_remove(ebus);
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index f2bf866..823b5a2 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -208,7 +208,7 @@
 
 config SND_MMP_SOC_BROWNSTONE
 	tristate "SoC Audio support for Marvell Brownstone"
-	depends on SND_MMP_SOC && MACH_BROWNSTONE
+	depends on SND_MMP_SOC && MACH_BROWNSTONE && I2C
 	select SND_MMP_SOC_SSPA
 	select MFD_WM8994
 	select SND_SOC_WM8994
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index 3cde9fb..eff3f9a 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -586,3 +586,6 @@ int asoc_qcom_lpass_cpu_platform_remove(struct platform_device *pdev)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_platform_remove);
+
+MODULE_DESCRIPTION("QTi LPASS CPU Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index e2ff538..07000f5 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -61,7 +61,40 @@ static int lpass_platform_pcmops_open(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
-	int ret;
+	struct snd_soc_dai *cpu_dai = soc_runtime->cpu_dai;
+	struct lpass_data *drvdata =
+		snd_soc_platform_get_drvdata(soc_runtime->platform);
+	struct lpass_variant *v = drvdata->variant;
+	int ret, dma_ch, dir = substream->stream;
+	struct lpass_pcm_data *data;
+
+	data = devm_kzalloc(soc_runtime->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->i2s_port = cpu_dai->driver->id;
+	runtime->private_data = data;
+
+	if (v->alloc_dma_channel)
+		dma_ch = v->alloc_dma_channel(drvdata, dir);
+	if (dma_ch < 0)
+		return dma_ch;
+
+	drvdata->substream[dma_ch] = substream;
+
+	ret = regmap_write(drvdata->lpaif_map,
+			LPAIF_DMACTL_REG(v, dma_ch, dir), 0);
+	if (ret) {
+		dev_err(soc_runtime->dev,
+			"%s() error writing to rdmactl reg: %d\n",
+			__func__, ret);
+			return ret;
+	}
+
+	if (dir == SNDRV_PCM_STREAM_PLAYBACK)
+		data->rdma_ch = dma_ch;
+	else
+		data->wrdma_ch = dma_ch;
 
 	snd_soc_set_runtime_hwparams(substream, &lpass_platform_pcm_hardware);
 
@@ -80,13 +113,40 @@ static int lpass_platform_pcmops_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
+static int lpass_platform_pcmops_close(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
+	struct lpass_data *drvdata =
+		snd_soc_platform_get_drvdata(soc_runtime->platform);
+	struct lpass_variant *v = drvdata->variant;
+	struct lpass_pcm_data *data;
+	int dma_ch, dir = substream->stream;
+
+	data = runtime->private_data;
+	v = drvdata->variant;
+
+	if (dir == SNDRV_PCM_STREAM_PLAYBACK)
+		dma_ch = data->rdma_ch;
+	else
+		dma_ch = data->wrdma_ch;
+
+	drvdata->substream[dma_ch] = NULL;
+
+	if (v->free_dma_channel)
+		v->free_dma_channel(drvdata, dma_ch);
+
+	return 0;
+}
+
 static int lpass_platform_pcmops_hw_params(struct snd_pcm_substream *substream,
 		struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
 	struct lpass_data *drvdata =
 		snd_soc_platform_get_drvdata(soc_runtime->platform);
-	struct lpass_pcm_data *pcm_data = drvdata->private_data;
+	struct snd_pcm_runtime *rt = substream->runtime;
+	struct lpass_pcm_data *pcm_data = rt->private_data;
 	struct lpass_variant *v = drvdata->variant;
 	snd_pcm_format_t format = params_format(params);
 	unsigned int channels = params_channels(params);
@@ -179,7 +239,8 @@ static int lpass_platform_pcmops_hw_free(struct snd_pcm_substream *substream)
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
 	struct lpass_data *drvdata =
 		snd_soc_platform_get_drvdata(soc_runtime->platform);
-	struct lpass_pcm_data *pcm_data = drvdata->private_data;
+	struct snd_pcm_runtime *rt = substream->runtime;
+	struct lpass_pcm_data *pcm_data = rt->private_data;
 	struct lpass_variant *v = drvdata->variant;
 	unsigned int reg;
 	int ret;
@@ -203,7 +264,8 @@ static int lpass_platform_pcmops_prepare(struct snd_pcm_substream *substream)
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
 	struct lpass_data *drvdata =
 		snd_soc_platform_get_drvdata(soc_runtime->platform);
-	struct lpass_pcm_data *pcm_data = drvdata->private_data;
+	struct snd_pcm_runtime *rt = substream->runtime;
+	struct lpass_pcm_data *pcm_data = rt->private_data;
 	struct lpass_variant *v = drvdata->variant;
 	int ret, ch, dir = substream->stream;
 
@@ -257,7 +319,8 @@ static int lpass_platform_pcmops_trigger(struct snd_pcm_substream *substream,
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
 	struct lpass_data *drvdata =
 		snd_soc_platform_get_drvdata(soc_runtime->platform);
-	struct lpass_pcm_data *pcm_data = drvdata->private_data;
+	struct snd_pcm_runtime *rt = substream->runtime;
+	struct lpass_pcm_data *pcm_data = rt->private_data;
 	struct lpass_variant *v = drvdata->variant;
 	int ret, ch, dir = substream->stream;
 
@@ -333,7 +396,8 @@ static snd_pcm_uframes_t lpass_platform_pcmops_pointer(
 	struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
 	struct lpass_data *drvdata =
 			snd_soc_platform_get_drvdata(soc_runtime->platform);
-	struct lpass_pcm_data *pcm_data = drvdata->private_data;
+	struct snd_pcm_runtime *rt = substream->runtime;
+	struct lpass_pcm_data *pcm_data = rt->private_data;
 	struct lpass_variant *v = drvdata->variant;
 	unsigned int base_addr, curr_addr;
 	int ret, ch, dir = substream->stream;
@@ -374,6 +438,7 @@ static int lpass_platform_pcmops_mmap(struct snd_pcm_substream *substream,
 
 static const struct snd_pcm_ops lpass_platform_pcm_ops = {
 	.open		= lpass_platform_pcmops_open,
+	.close		= lpass_platform_pcmops_close,
 	.ioctl		= snd_pcm_lib_ioctl,
 	.hw_params	= lpass_platform_pcmops_hw_params,
 	.hw_free	= lpass_platform_pcmops_hw_free,
@@ -470,117 +535,45 @@ static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
 {
 	struct snd_pcm *pcm = soc_runtime->pcm;
 	struct snd_pcm_substream *psubstream, *csubstream;
-	struct snd_soc_dai *cpu_dai = soc_runtime->cpu_dai;
-	struct lpass_data *drvdata =
-		snd_soc_platform_get_drvdata(soc_runtime->platform);
-	struct lpass_variant *v = drvdata->variant;
 	int ret = -EINVAL;
-	struct lpass_pcm_data *data;
 	size_t size = lpass_platform_pcm_hardware.buffer_bytes_max;
 
-	data = devm_kzalloc(soc_runtime->dev, sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	data->i2s_port = cpu_dai->driver->id;
-	drvdata->private_data = data;
-
 	psubstream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
 	if (psubstream) {
-		if (v->alloc_dma_channel)
-			data->rdma_ch = v->alloc_dma_channel(drvdata,
-						SNDRV_PCM_STREAM_PLAYBACK);
-
-		if (data->rdma_ch < 0)
-			return data->rdma_ch;
-
-		drvdata->substream[data->rdma_ch] = psubstream;
-
 		ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
 					soc_runtime->platform->dev,
 					size, &psubstream->dma_buffer);
-		if (ret)
-			goto playback_alloc_err;
-
-		ret = regmap_write(drvdata->lpaif_map,
-			LPAIF_RDMACTL_REG(v, data->rdma_ch), 0);
 		if (ret) {
-			dev_err(soc_runtime->dev,
-				"%s() error writing to rdmactl reg: %d\n",
-				__func__, ret);
-			goto capture_alloc_err;
+			dev_err(soc_runtime->dev, "Cannot allocate buffer(s)\n");
+			return ret;
 		}
 	}
 
 	csubstream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
 	if (csubstream) {
-		if (v->alloc_dma_channel)
-			data->wrdma_ch = v->alloc_dma_channel(drvdata,
-						SNDRV_PCM_STREAM_CAPTURE);
-
-		if (data->wrdma_ch < 0) {
-			ret = data->wrdma_ch;
-			goto capture_alloc_err;
-		}
-
-		drvdata->substream[data->wrdma_ch] = csubstream;
-
 		ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
 					soc_runtime->platform->dev,
 					size, &csubstream->dma_buffer);
-		if (ret)
-			goto capture_alloc_err;
-
-		ret = regmap_write(drvdata->lpaif_map,
-			LPAIF_WRDMACTL_REG(v, data->wrdma_ch), 0);
 		if (ret) {
-			dev_err(soc_runtime->dev,
-				"%s() error writing to wrdmactl reg: %d\n",
-				__func__, ret);
-			goto capture_reg_err;
+			dev_err(soc_runtime->dev, "Cannot allocate buffer(s)\n");
+			if (psubstream)
+				snd_dma_free_pages(&psubstream->dma_buffer);
+			return ret;
 		}
+
 	}
 
 	return 0;
-
-capture_reg_err:
-	if (csubstream)
-		snd_dma_free_pages(&csubstream->dma_buffer);
-
-capture_alloc_err:
-	if (psubstream)
-		snd_dma_free_pages(&psubstream->dma_buffer);
-
- playback_alloc_err:
-	dev_err(soc_runtime->dev, "Cannot allocate buffer(s)\n");
-
-	return ret;
 }
 
 static void lpass_platform_pcm_free(struct snd_pcm *pcm)
 {
-	struct snd_soc_pcm_runtime *rt;
-	struct lpass_data *drvdata;
-	struct lpass_pcm_data *data;
-	struct lpass_variant *v;
 	struct snd_pcm_substream *substream;
-	int ch, i;
+	int i;
 
 	for (i = 0; i < ARRAY_SIZE(pcm->streams); i++) {
 		substream = pcm->streams[i].substream;
 		if (substream) {
-			rt = substream->private_data;
-			drvdata = snd_soc_platform_get_drvdata(rt->platform);
-			data = drvdata->private_data;
-
-			ch = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-				? data->rdma_ch
-				: data->wrdma_ch;
-			v = drvdata->variant;
-			drvdata->substream[ch] = NULL;
-			if (v->free_dma_channel)
-				v->free_dma_channel(drvdata, ch);
-
 			snd_dma_free_pages(&substream->dma_buffer);
 			substream->dma_buffer.area = NULL;
 			substream->dma_buffer.addr = 0;
diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h
index 35b3cea..924971b 100644
--- a/sound/soc/qcom/lpass.h
+++ b/sound/soc/qcom/lpass.h
@@ -59,7 +59,6 @@ struct lpass_data {
 	struct clk *pcnoc_mport_clk;
 	struct clk *pcnoc_sway_clk;
 
-	void *private_data;
 };
 
 /* Vairant data per each SOC */
diff --git a/sound/soc/samsung/ac97.c b/sound/soc/samsung/ac97.c
index 97d6700..cbc0023 100644
--- a/sound/soc/samsung/ac97.c
+++ b/sound/soc/samsung/ac97.c
@@ -383,11 +383,6 @@ static int s3c_ac97_probe(struct platform_device *pdev)
 		goto err4;
 	}
 
-	ret = devm_snd_soc_register_component(&pdev->dev, &s3c_ac97_component,
-					 s3c_ac97_dai, ARRAY_SIZE(s3c_ac97_dai));
-	if (ret)
-		goto err5;
-
 	ret = samsung_asoc_dma_platform_register(&pdev->dev,
 						 ac97_pdata->dma_filter,
 						 NULL, NULL);
@@ -396,6 +391,11 @@ static int s3c_ac97_probe(struct platform_device *pdev)
 		goto err5;
 	}
 
+	ret = devm_snd_soc_register_component(&pdev->dev, &s3c_ac97_component,
+					 s3c_ac97_dai, ARRAY_SIZE(s3c_ac97_dai));
+	if (ret)
+		goto err5;
+
 	return 0;
 err5:
 	free_irq(irq_res->start, NULL);
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 7e32cf4..7825bff 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -1237,14 +1237,14 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "Unable to get drvdata\n");
 			return -EFAULT;
 		}
-		ret = devm_snd_soc_register_component(&sec_dai->pdev->dev,
-						&samsung_i2s_component,
-						&sec_dai->i2s_dai_drv, 1);
+		ret = samsung_asoc_dma_platform_register(&pdev->dev,
+					sec_dai->filter, "tx-sec", NULL);
 		if (ret != 0)
 			return ret;
 
-		return samsung_asoc_dma_platform_register(&pdev->dev,
-					sec_dai->filter, "tx-sec", NULL);
+		return devm_snd_soc_register_component(&sec_dai->pdev->dev,
+						&samsung_i2s_component,
+						&sec_dai->i2s_dai_drv, 1);
 	}
 
 	pri_dai = i2s_alloc_dai(pdev, false);
@@ -1314,6 +1314,11 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 	if (quirks & QUIRK_PRI_6CHAN)
 		pri_dai->i2s_dai_drv.playback.channels_max = 6;
 
+	ret = samsung_asoc_dma_platform_register(&pdev->dev, pri_dai->filter,
+						 NULL, NULL);
+	if (ret < 0)
+		goto err_disable_clk;
+
 	if (quirks & QUIRK_SEC_DAI) {
 		sec_dai = i2s_alloc_dai(pdev, true);
 		if (!sec_dai) {
@@ -1353,10 +1358,6 @@ static int samsung_i2s_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_free_dai;
 
-	ret = samsung_asoc_dma_platform_register(&pdev->dev, pri_dai->filter,
-						 NULL, NULL);
-	if (ret < 0)
-		goto err_free_dai;
 
 	pm_runtime_enable(&pdev->dev);
 
diff --git a/sound/soc/samsung/pcm.c b/sound/soc/samsung/pcm.c
index 43e367a..c484985 100644
--- a/sound/soc/samsung/pcm.c
+++ b/sound/soc/samsung/pcm.c
@@ -565,15 +565,6 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
 	pcm->dma_capture = &s3c_pcm_stereo_in[pdev->id];
 	pcm->dma_playback = &s3c_pcm_stereo_out[pdev->id];
 
-	pm_runtime_enable(&pdev->dev);
-
-	ret = devm_snd_soc_register_component(&pdev->dev, &s3c_pcm_component,
-					 &s3c_pcm_dai[pdev->id], 1);
-	if (ret != 0) {
-		dev_err(&pdev->dev, "failed to get register DAI: %d\n", ret);
-		goto err5;
-	}
-
 	ret = samsung_asoc_dma_platform_register(&pdev->dev, filter,
 						 NULL, NULL);
 	if (ret) {
@@ -581,8 +572,18 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
 		goto err5;
 	}
 
-	return 0;
+	pm_runtime_enable(&pdev->dev);
 
+	ret = devm_snd_soc_register_component(&pdev->dev, &s3c_pcm_component,
+					 &s3c_pcm_dai[pdev->id], 1);
+	if (ret != 0) {
+		dev_err(&pdev->dev, "failed to get register DAI: %d\n", ret);
+		goto err6;
+	}
+
+	return 0;
+err6:
+	pm_runtime_disable(&pdev->dev);
 err5:
 	clk_disable_unprepare(pcm->pclk);
 err4:
diff --git a/sound/soc/samsung/s3c2412-i2s.c b/sound/soc/samsung/s3c2412-i2s.c
index 3e89fbc..0a47182 100644
--- a/sound/soc/samsung/s3c2412-i2s.c
+++ b/sound/soc/samsung/s3c2412-i2s.c
@@ -168,19 +168,19 @@ static int s3c2412_iis_dev_probe(struct platform_device *pdev)
 	s3c2412_i2s_pcm_stereo_in.addr = res->start + S3C2412_IISRXD;
 	s3c2412_i2s_pcm_stereo_in.filter_data = pdata->dma_capture;
 
-	ret = s3c_i2sv2_register_component(&pdev->dev, -1,
-					   &s3c2412_i2s_component,
-					   &s3c2412_i2s_dai);
-	if (ret) {
-		pr_err("failed to register the dai\n");
-		return ret;
-	}
-
 	ret = samsung_asoc_dma_platform_register(&pdev->dev,
 						 pdata->dma_filter,
 						 NULL, NULL);
-	if (ret)
+	if (ret) {
 		pr_err("failed to register the DMA: %d\n", ret);
+		return ret;
+	}
+
+	ret = s3c_i2sv2_register_component(&pdev->dev, -1,
+					   &s3c2412_i2s_component,
+					   &s3c2412_i2s_dai);
+	if (ret)
+		pr_err("failed to register the dai\n");
 
 	return ret;
 }
diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c
index c78a936..9052f6a 100644
--- a/sound/soc/samsung/s3c24xx-i2s.c
+++ b/sound/soc/samsung/s3c24xx-i2s.c
@@ -474,18 +474,18 @@ static int s3c24xx_iis_dev_probe(struct platform_device *pdev)
 	s3c24xx_i2s_pcm_stereo_in.addr = res->start + S3C2410_IISFIFO;
 	s3c24xx_i2s_pcm_stereo_in.filter_data = pdata->dma_capture;
 
-	ret = devm_snd_soc_register_component(&pdev->dev,
-			&s3c24xx_i2s_component, &s3c24xx_i2s_dai, 1);
-	if (ret) {
-		pr_err("failed to register the dai\n");
-		return ret;
-	}
-
 	ret = samsung_asoc_dma_platform_register(&pdev->dev,
 						 pdata->dma_filter,
 						 NULL, NULL);
-	if (ret)
+	if (ret) {
 		pr_err("failed to register the dma: %d\n", ret);
+		return ret;
+	}
+
+	ret = devm_snd_soc_register_component(&pdev->dev,
+			&s3c24xx_i2s_component, &s3c24xx_i2s_dai, 1);
+	if (ret)
+		pr_err("failed to register the dai\n");
 
 	return ret;
 }
diff --git a/sound/soc/samsung/spdif.c b/sound/soc/samsung/spdif.c
index 26c1fbe..779504f 100644
--- a/sound/soc/samsung/spdif.c
+++ b/sound/soc/samsung/spdif.c
@@ -416,15 +416,6 @@ static int spdif_probe(struct platform_device *pdev)
 		goto err3;
 	}
 
-	dev_set_drvdata(&pdev->dev, spdif);
-
-	ret = devm_snd_soc_register_component(&pdev->dev,
-			&samsung_spdif_component, &samsung_spdif_dai, 1);
-	if (ret != 0) {
-		dev_err(&pdev->dev, "fail to register dai\n");
-		goto err4;
-	}
-
 	spdif_stereo_out.addr_width = 2;
 	spdif_stereo_out.addr = mem_res->start + DATA_OUTBUF;
 	filter = NULL;
@@ -432,7 +423,6 @@ static int spdif_probe(struct platform_device *pdev)
 		spdif_stereo_out.filter_data = spdif_pdata->dma_playback;
 		filter = spdif_pdata->dma_filter;
 	}
-
 	spdif->dma_playback = &spdif_stereo_out;
 
 	ret = samsung_asoc_dma_platform_register(&pdev->dev, filter,
@@ -442,6 +432,15 @@ static int spdif_probe(struct platform_device *pdev)
 		goto err4;
 	}
 
+	dev_set_drvdata(&pdev->dev, spdif);
+
+	ret = devm_snd_soc_register_component(&pdev->dev,
+			&samsung_spdif_component, &samsung_spdif_dai, 1);
+	if (ret != 0) {
+		dev_err(&pdev->dev, "fail to register dai\n");
+		goto err4;
+	}
+
 	return 0;
 err4:
 	iounmap(spdif->regs);
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index 1bc8ebc..ad54d4c 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -614,7 +614,11 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol,
 	iec958->status[3] = ucontrol->value.iec958.status[3];
 	mutex_unlock(&player->ctrl_lock);
 
-	uni_player_set_channel_status(player, NULL);
+	if (player->substream && player->substream->runtime)
+		uni_player_set_channel_status(player,
+					      player->substream->runtime);
+	else
+		uni_player_set_channel_status(player, NULL);
 
 	return 0;
 }
diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c
index e047ec0..56ed947 100644
--- a/sound/soc/sunxi/sun4i-codec.c
+++ b/sound/soc/sunxi/sun4i-codec.c
@@ -765,11 +765,11 @@ static struct snd_soc_card *sun4i_codec_create_card(struct device *dev)
 
 	card = devm_kzalloc(dev, sizeof(*card), GFP_KERNEL);
 	if (!card)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	card->dai_link = sun4i_codec_create_link(dev, &card->num_links);
 	if (!card->dai_link)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	card->dev		= dev;
 	card->name		= "sun4i-codec";
@@ -829,12 +829,6 @@ static int sun4i_codec_probe(struct platform_device *pdev)
 		return PTR_ERR(scodec->clk_module);
 	}
 
-	/* Enable the bus clock */
-	if (clk_prepare_enable(scodec->clk_apb)) {
-		dev_err(&pdev->dev, "Failed to enable the APB clock\n");
-		return -EINVAL;
-	}
-
 	scodec->gpio_pa = devm_gpiod_get_optional(&pdev->dev, "allwinner,pa",
 						  GPIOD_OUT_LOW);
 	if (IS_ERR(scodec->gpio_pa)) {
@@ -844,6 +838,12 @@ static int sun4i_codec_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* Enable the bus clock */
+	if (clk_prepare_enable(scodec->clk_apb)) {
+		dev_err(&pdev->dev, "Failed to enable the APB clock\n");
+		return -EINVAL;
+	}
+
 	/* DMA configuration for TX FIFO */
 	scodec->playback_dma_data.addr = res->start + SUN4I_CODEC_DAC_TXDATA;
 	scodec->playback_dma_data.maxburst = 4;
@@ -876,7 +876,8 @@ static int sun4i_codec_probe(struct platform_device *pdev)
 	}
 
 	card = sun4i_codec_create_card(&pdev->dev);
-	if (!card) {
+	if (IS_ERR(card)) {
+		ret = PTR_ERR(card);
 		dev_err(&pdev->dev, "Failed to create our card\n");
 		goto err_unregister_codec;
 	}
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index c60a776..8a59d47 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2907,6 +2907,23 @@ AU0828_DEVICE(0x2040, 0x7260, "Hauppauge", "HVR-950Q"),
 AU0828_DEVICE(0x2040, 0x7213, "Hauppauge", "HVR-950Q"),
 AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 
+/* Syntek STK1160 */
+{
+	.match_flags = USB_DEVICE_ID_MATCH_DEVICE |
+		       USB_DEVICE_ID_MATCH_INT_CLASS |
+		       USB_DEVICE_ID_MATCH_INT_SUBCLASS,
+	.idVendor = 0x05e1,
+	.idProduct = 0x0408,
+	.bInterfaceClass = USB_CLASS_AUDIO,
+	.bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "Syntek",
+		.product_name = "STK1160",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_AUDIO_ALIGN_TRANSFER
+	}
+},
+
 /* Digidesign Mbox */
 {
 	/* Thanks to Clemens Ladisch <clemens@ladisch.de> */
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 4490601..e8a1f69 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -754,7 +754,7 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		if (insn->type == INSN_JUMP_UNCONDITIONAL &&
 		    insn->jump_dest &&
 		    (insn->jump_dest->offset <= insn->offset ||
-		     insn->jump_dest->offset >= orig_insn->offset))
+		     insn->jump_dest->offset > orig_insn->offset))
 		    break;
 
 		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile
index 877a8a4..c012edb 100644
--- a/tools/virtio/ringtest/Makefile
+++ b/tools/virtio/ringtest/Makefile
@@ -3,8 +3,8 @@
 all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder ptr_ring noring
 
 CFLAGS += -Wall
-CFLAGS += -pthread -O2 -ggdb
-LDFLAGS += -pthread -O2 -ggdb
+CFLAGS += -pthread -O2 -ggdb -flto -fwhole-program
+LDFLAGS += -pthread -O2 -ggdb -flto -fwhole-program
 
 main.o: main.c main.h
 ring.o: ring.c main.h
diff --git a/tools/virtio/ringtest/main.c b/tools/virtio/ringtest/main.c
index 147abb4..f31353f 100644
--- a/tools/virtio/ringtest/main.c
+++ b/tools/virtio/ringtest/main.c
@@ -96,7 +96,13 @@ void set_affinity(const char *arg)
 	assert(!ret);
 }
 
-static void run_guest(void)
+void poll_used(void)
+{
+	while (used_empty())
+		busy_wait();
+}
+
+static void __attribute__((__flatten__)) run_guest(void)
 {
 	int completed_before;
 	int completed = 0;
@@ -141,7 +147,7 @@ static void run_guest(void)
 		assert(completed <= bufs);
 		assert(started <= bufs);
 		if (do_sleep) {
-			if (enable_call())
+			if (used_empty() && enable_call())
 				wait_for_call();
 		} else {
 			poll_used();
@@ -149,7 +155,13 @@ static void run_guest(void)
 	}
 }
 
-static void run_host(void)
+void poll_avail(void)
+{
+	while (avail_empty())
+		busy_wait();
+}
+
+static void __attribute__((__flatten__)) run_host(void)
 {
 	int completed_before;
 	int completed = 0;
@@ -160,7 +172,7 @@ static void run_host(void)
 
 	for (;;) {
 		if (do_sleep) {
-			if (enable_kick())
+			if (avail_empty() && enable_kick())
 				wait_for_kick();
 		} else {
 			poll_avail();
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 16917ac..34e63cc 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -56,15 +56,15 @@ void alloc_ring(void);
 int add_inbuf(unsigned, void *, void *);
 void *get_buf(unsigned *, void **);
 void disable_call();
+bool used_empty();
 bool enable_call();
 void kick_available();
-void poll_used();
 /* host side */
 void disable_kick();
+bool avail_empty();
 bool enable_kick();
 bool use_buf(unsigned *, void **);
 void call_used();
-void poll_avail();
 
 /* implemented by main */
 extern bool do_sleep;
diff --git a/tools/virtio/ringtest/noring.c b/tools/virtio/ringtest/noring.c
index eda2f48..b8d1c1d 100644
--- a/tools/virtio/ringtest/noring.c
+++ b/tools/virtio/ringtest/noring.c
@@ -24,8 +24,9 @@ void *get_buf(unsigned *lenp, void **bufp)
 	return "Buffer";
 }
 
-void poll_used(void)
+bool used_empty()
 {
+	return false;
 }
 
 void disable_call()
@@ -54,8 +55,9 @@ bool enable_kick()
 	assert(0);
 }
 
-void poll_avail(void)
+bool avail_empty()
 {
+	return false;
 }
 
 bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
index bd2ad1d..635b07b 100644
--- a/tools/virtio/ringtest/ptr_ring.c
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -133,18 +133,9 @@ void *get_buf(unsigned *lenp, void **bufp)
 	return datap;
 }
 
-void poll_used(void)
+bool used_empty()
 {
-	void *b;
-
-	do {
-		if (tailcnt == headcnt || __ptr_ring_full(&array)) {
-			b = NULL;
-			barrier();
-		} else {
-			b = "Buffer\n";
-		}
-	} while (!b);
+	return (tailcnt == headcnt || __ptr_ring_full(&array));
 }
 
 void disable_call()
@@ -173,14 +164,9 @@ bool enable_kick()
 	assert(0);
 }
 
-void poll_avail(void)
+bool avail_empty()
 {
-	void *b;
-
-	do {
-		barrier();
-		b = __ptr_ring_peek(&array);
-	} while (!b);
+	return !__ptr_ring_peek(&array);
 }
 
 bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/ring.c b/tools/virtio/ringtest/ring.c
index c25c8d2..747c5dd 100644
--- a/tools/virtio/ringtest/ring.c
+++ b/tools/virtio/ringtest/ring.c
@@ -163,12 +163,11 @@ void *get_buf(unsigned *lenp, void **bufp)
 	return datap;
 }
 
-void poll_used(void)
+bool used_empty()
 {
 	unsigned head = (ring_size - 1) & guest.last_used_idx;
 
-	while (ring[head].flags & DESC_HW)
-		busy_wait();
+	return (ring[head].flags & DESC_HW);
 }
 
 void disable_call()
@@ -180,13 +179,11 @@ void disable_call()
 
 bool enable_call()
 {
-	unsigned head = (ring_size - 1) & guest.last_used_idx;
-
 	event->call_index = guest.last_used_idx;
 	/* Flush call index write */
 	/* Barrier D (for pairing) */
 	smp_mb();
-	return ring[head].flags & DESC_HW;
+	return used_empty();
 }
 
 void kick_available(void)
@@ -213,20 +210,17 @@ void disable_kick()
 
 bool enable_kick()
 {
-	unsigned head = (ring_size - 1) & host.used_idx;
-
 	event->kick_index = host.used_idx;
 	/* Barrier C (for pairing) */
 	smp_mb();
-	return !(ring[head].flags & DESC_HW);
+	return avail_empty();
 }
 
-void poll_avail(void)
+bool avail_empty()
 {
 	unsigned head = (ring_size - 1) & host.used_idx;
 
-	while (!(ring[head].flags & DESC_HW))
-		busy_wait();
+	return !(ring[head].flags & DESC_HW);
 }
 
 bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/virtio_ring_0_9.c b/tools/virtio/ringtest/virtio_ring_0_9.c
index 7618662..bbc3043 100644
--- a/tools/virtio/ringtest/virtio_ring_0_9.c
+++ b/tools/virtio/ringtest/virtio_ring_0_9.c
@@ -194,24 +194,16 @@ void *get_buf(unsigned *lenp, void **bufp)
 	return datap;
 }
 
-void poll_used(void)
+bool used_empty()
 {
+	unsigned short last_used_idx = guest.last_used_idx;
 #ifdef RING_POLL
-	unsigned head = (ring_size - 1) & guest.last_used_idx;
+	unsigned short head = last_used_idx & (ring_size - 1);
+	unsigned index = ring.used->ring[head].id;
 
-	for (;;) {
-		unsigned index = ring.used->ring[head].id;
-
-		if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1))
-			busy_wait();
-		else
-			break;
-	}
+	return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
 #else
-	unsigned head = guest.last_used_idx;
-
-	while (ring.used->idx == head)
-		busy_wait();
+	return ring.used->idx == last_used_idx;
 #endif
 }
 
@@ -224,22 +216,11 @@ void disable_call()
 
 bool enable_call()
 {
-	unsigned short last_used_idx;
-
-	vring_used_event(&ring) = (last_used_idx = guest.last_used_idx);
+	vring_used_event(&ring) = guest.last_used_idx;
 	/* Flush call index write */
 	/* Barrier D (for pairing) */
 	smp_mb();
-#ifdef RING_POLL
-	{
-		unsigned short head = last_used_idx & (ring_size - 1);
-		unsigned index = ring.used->ring[head].id;
-
-		return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
-	}
-#else
-	return ring.used->idx == last_used_idx;
-#endif
+	return used_empty();
 }
 
 void kick_available(void)
@@ -266,36 +247,21 @@ void disable_kick()
 
 bool enable_kick()
 {
-	unsigned head = host.used_idx;
-
-	vring_avail_event(&ring) = head;
+	vring_avail_event(&ring) = host.used_idx;
 	/* Barrier C (for pairing) */
 	smp_mb();
-#ifdef RING_POLL
-	{
-		unsigned index = ring.avail->ring[head & (ring_size - 1)];
-
-		return (index ^ head ^ 0x8000) & ~(ring_size - 1);
-	}
-#else
-	return head == ring.avail->idx;
-#endif
+	return avail_empty();
 }
 
-void poll_avail(void)
+bool avail_empty()
 {
 	unsigned head = host.used_idx;
 #ifdef RING_POLL
-	for (;;) {
-		unsigned index = ring.avail->ring[head & (ring_size - 1)];
-		if ((index ^ head ^ 0x8000) & ~(ring_size - 1))
-			busy_wait();
-		else
-			break;
-	}
+	unsigned index = ring.avail->ring[head & (ring_size - 1)];
+
+	return ((index ^ head ^ 0x8000) & ~(ring_size - 1));
 #else
-	while (ring.avail->idx == head)
-		busy_wait();
+	return head == ring.avail->idx;
 #endif
 }
 
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index f397e9b..a29786d 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -42,6 +42,7 @@
 
 #ifdef CONFIG_HAVE_KVM_IRQFD
 
+static struct workqueue_struct *irqfd_cleanup_wq;
 
 static void
 irqfd_inject(struct work_struct *work)
@@ -167,7 +168,7 @@ irqfd_deactivate(struct kvm_kernel_irqfd *irqfd)
 
 	list_del_init(&irqfd->list);
 
-	schedule_work(&irqfd->shutdown);
+	queue_work(irqfd_cleanup_wq, &irqfd->shutdown);
 }
 
 int __attribute__((weak)) kvm_arch_set_irq_inatomic(
@@ -554,7 +555,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 	 * so that we guarantee there will not be any more interrupts on this
 	 * gsi once this deassign function returns.
 	 */
-	flush_work(&irqfd->shutdown);
+	flush_workqueue(irqfd_cleanup_wq);
 
 	return 0;
 }
@@ -591,7 +592,7 @@ kvm_irqfd_release(struct kvm *kvm)
 	 * Block until we know all outstanding shutdown jobs have completed
 	 * since we do not take a kvm* reference.
 	 */
-	flush_work(&irqfd->shutdown);
+	flush_workqueue(irqfd_cleanup_wq);
 
 }
 
@@ -621,8 +622,23 @@ void kvm_irq_routing_update(struct kvm *kvm)
 	spin_unlock_irq(&kvm->irqfds.lock);
 }
 
+/*
+ * create a host-wide workqueue for issuing deferred shutdown requests
+ * aggregated from all vm* instances. We need our own isolated
+ * queue to ease flushing work items when a VM exits.
+ */
+int kvm_irqfd_init(void)
+{
+	irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", 0, 0);
+	if (!irqfd_cleanup_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
 void kvm_irqfd_exit(void)
 {
+	destroy_workqueue(irqfd_cleanup_wq);
 }
 #endif
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2907b7b..5c36034 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3844,7 +3844,12 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	 * kvm_arch_init makes sure there's at most one caller
 	 * for architectures that support multiple implementations,
 	 * like intel and amd on x86.
+	 * kvm_arch_init must be called before kvm_irqfd_init to avoid creating
+	 * conflicts in case kvm is already setup for another implementation.
 	 */
+	r = kvm_irqfd_init();
+	if (r)
+		goto out_irqfd;
 
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
@@ -3926,6 +3931,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
 	kvm_irqfd_exit();
+out_irqfd:
 	kvm_arch_exit();
 out_fail:
 	return r;