Merge branch 'linus' into x86/asm, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

715 files changed, 8023 insertions, 4744 deletions

diff --git a/CREDITS b/CREDITS
index 513aaa3546bf..837367624e45 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1864,10 +1864,11 @@ S: The Netherlands
 
 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/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index 4ba0a2a61926..640f65e79ef1 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -220,8 +220,11 @@ What:           /sys/class/cxl/<card>/reset
 Date:           October 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    write only
-                Writing 1 will issue a PERST to card which may cause the card
-                to reload the FPGA depending on load_image_on_perst.
+                Writing 1 will issue a PERST to card provided there are no
+                contexts active on any one of the card AFUs. This may cause
+                the card to reload the FPGA depending on load_image_on_perst.
+                Writing -1 will do a force PERST irrespective of any active
+                contexts on the card AFUs.
 Users:          https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<card>/perst_reloads_same_image (not in a guest)
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index e5b6497116f4..c75b64a85859 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -309,3 +309,4 @@ Version History
         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/clock/uniphier-clock.txt b/Documentation/devicetree/bindings/clock/uniphier-clock.txt
index c7179d3b5c33..812163060fa3 100644
--- a/Documentation/devicetree/bindings/clock/uniphier-clock.txt
+++ b/Documentation/devicetree/bindings/clock/uniphier-clock.txt
@@ -24,7 +24,7 @@ Example:
                 reg = <0x61840000 0x4000>;
 
                 clock {
-                        compatible = "socionext,uniphier-ld20-clock";
+                        compatible = "socionext,uniphier-ld11-clock";
                         #clock-cells = <1>;
                 };
 
@@ -43,8 +43,8 @@ Provided clocks:
 21: USB3 ch1 PHY1
 
 
-Media I/O (MIO) clock
----------------------
+Media I/O (MIO) clock, SD clock
+-------------------------------
 
 Required properties:
 - compatible: should be one of the following:
@@ -52,10 +52,10 @@ Required properties:
     "socionext,uniphier-ld4-mio-clock"  - for LD4 SoC.
     "socionext,uniphier-pro4-mio-clock" - for Pro4 SoC.
     "socionext,uniphier-sld8-mio-clock" - for sLD8 SoC.
-    "socionext,uniphier-pro5-mio-clock" - for Pro5 SoC.
-    "socionext,uniphier-pxs2-mio-clock" - for PXs2/LD6b SoC.
+    "socionext,uniphier-pro5-sd-clock"  - for Pro5 SoC.
+    "socionext,uniphier-pxs2-sd-clock"  - for PXs2/LD6b SoC.
     "socionext,uniphier-ld11-mio-clock" - for LD11 SoC.
-    "socionext,uniphier-ld20-mio-clock" - for LD20 SoC.
+    "socionext,uniphier-ld20-sd-clock"  - for LD20 SoC.
 - #clock-cells: should be 1.
 
 Example:
@@ -66,7 +66,7 @@ Example:
                 reg = <0x59810000 0x800>;
 
                 clock {
-                        compatible = "socionext,uniphier-ld20-mio-clock";
+                        compatible = "socionext,uniphier-ld11-mio-clock";
                         #clock-cells = <1>;
                 };
 
@@ -112,7 +112,7 @@ Example:
                 reg = <0x59820000 0x200>;
 
                 clock {
-                        compatible = "socionext,uniphier-ld20-peri-clock";
+                        compatible = "socionext,uniphier-ld11-peri-clock";
                         #clock-cells = <1>;
                 };
 
diff --git a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt
new file mode 100644
index 000000000000..fbbacd958240
--- /dev/null
+++ b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt
@@ -0,0 +1,23 @@
+* Aspeed BT (Block Transfer) IPMI interface
+
+The Aspeed SOCs (AST2400 and AST2500) are commonly used as BMCs
+(BaseBoard Management Controllers) and the BT interface can be used to
+perform in-band IPMI communication with their host.
+
+Required properties:
+
+- compatible : should be "aspeed,ast2400-bt-bmc"
+- reg: physical address and size of the registers
+
+Optional properties:
+
+- interrupts: interrupt generated by the BT interface. without an
+  interrupt, the driver will operate in poll mode.
+
+Example:
+
+        ibt@1e789140 {
+                compatible = "aspeed,ast2400-bt-bmc";
+                reg = <0x1e789140 0x18>;
+                interrupts = <8>;
+        };
diff --git a/Documentation/devicetree/bindings/ipmi.txt b/Documentation/devicetree/bindings/ipmi/ipmi-smic.txt
index d5f1a877ed3e..d5f1a877ed3e 100644
--- a/Documentation/devicetree/bindings/ipmi.txt
+++ b/Documentation/devicetree/bindings/ipmi/ipmi-smic.txt
diff --git a/Documentation/devicetree/bindings/net/marvell-orion-net.txt b/Documentation/devicetree/bindings/net/marvell-orion-net.txt
index bce52b2ec55e..6fd988c84c4f 100644
--- a/Documentation/devicetree/bindings/net/marvell-orion-net.txt
+++ b/Documentation/devicetree/bindings/net/marvell-orion-net.txt
@@ -49,6 +49,7 @@ Optional port properties:
 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 e6bbfccd56c3..5020524cddeb 100644
--- a/Documentation/devicetree/bindings/reset/uniphier-reset.txt
+++ b/Documentation/devicetree/bindings/reset/uniphier-reset.txt
@@ -6,25 +6,25 @@ System reset
 
 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 @@ Example:
         };
 
 
-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 @@ Peripheral reset
 
 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 a3eb154c32ca..227bb770b027 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 1e4000d83aee..8d27d1a603e7 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -9,6 +9,14 @@ Required properties:
     - "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/timer/jcore,pit.txt b/Documentation/devicetree/bindings/timer/jcore,pit.txt
new file mode 100644
index 000000000000..af5dd35469d7
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/jcore,pit.txt
@@ -0,0 +1,24 @@
+J-Core Programmable Interval Timer and Clocksource
+
+Required properties:
+
+- compatible: Must be "jcore,pit".
+
+- reg: Memory region(s) for timer/clocksource registers. For SMP,
+  there should be one region per cpu, indexed by the sequential,
+  zero-based hardware cpu number.
+
+- interrupts: An interrupt to assign for the timer. The actual pit
+  core is integrated with the aic and allows the timer interrupt
+  assignment to be programmed by software, but this property is
+  required in order to reserve an interrupt number that doesn't
+  conflict with other devices.
+
+
+Example:
+
+timer@200 {
+        compatible = "jcore,pit";
+        reg = < 0x200 0x30 0x500 0x30 >;
+        interrupts = < 0x48 >;
+};
diff --git a/Documentation/devicetree/bindings/usb/dwc2.txt b/Documentation/devicetree/bindings/usb/dwc2.txt
index 455f2c310a1b..2c30a5479069 100644
--- a/Documentation/devicetree/bindings/usb/dwc2.txt
+++ b/Documentation/devicetree/bindings/usb/dwc2.txt
@@ -28,10 +28,7 @@ Refer to phy/phy-bindings.txt for generic phy consumer properties
 - 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/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 219ffd41a911..74329fd0add2 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -395,32 +395,6 @@ is not associated with a file:
 
  or if empty, the mapping is anonymous.
 
-The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
-of the individual tasks of a process. In this file you will see a mapping marked
-as [stack] if that task sees it as a stack. Hence, for the example above, the
-task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
-
-08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
-08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
-0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
-a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0
-a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack]
-a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
-a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
-a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
-a800b000-a800e000 rw-p 00000000 00:00 0
-a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
-a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
-a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
-a8024000-a8027000 rw-p 00000000 00:00 0
-a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
-a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
-a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
-aff35000-aff4a000 rw-p 00000000 00:00 0
-ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
-
 The /proc/PID/smaps is an extension based on maps, showing the memory
 consumption for each of the process's mappings. For each of mappings there
 is a series of lines such as the following:
diff --git a/Documentation/gpio/board.txt b/Documentation/gpio/board.txt
index 40884c4fe40c..a0f61898d493 100644
--- a/Documentation/gpio/board.txt
+++ b/Documentation/gpio/board.txt
@@ -6,7 +6,7 @@ Note that it only applies to the new descriptor-based interface. For a
 description of the deprecated integer-based GPIO interface please refer to
 gpio-legacy.txt (actually, there is no real mapping possible with the old
 interface; you just fetch an integer from somewhere and request the
-corresponding GPIO.
+corresponding GPIO).
 
 All platforms can enable the GPIO library, but if the platform strictly
 requires GPIO functionality to be present, it needs to select GPIOLIB from its
@@ -162,6 +162,9 @@ The driver controlling "foo.0" will then be able to obtain its GPIOs as follows:
 
 Since the "led" GPIOs are mapped as active-high, this example will switch their
 signals to 1, i.e. enabling the LEDs. And for the "power" GPIO, which is mapped
-as active-low, its actual signal will be 0 after this code. Contrary to the legacy
-integer GPIO interface, the active-low property is handled during mapping and is
-thus transparent to GPIO consumers.
+as active-low, its actual signal will be 0 after this code. Contrary to the
+legacy integer GPIO interface, the active-low property is handled during
+mapping and is thus transparent to GPIO consumers.
+
+A set of functions such as gpiod_set_value() is available to work with
+the new descriptor-oriented interface.
diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt
index 0fe1c6e0dbcd..a20b2fae942b 100644
--- a/Documentation/networking/netdev-FAQ.txt
+++ b/Documentation/networking/netdev-FAQ.txt
@@ -29,8 +29,8 @@ A: There are always two trees (git repositories) in play.  Both are driven
    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 @@ Q: So where are we now in this cycle?
 
 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 @@ A: Normally Greg Kroah-Hartman collects stable commits himself, but
 
    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 4fb51d32fccc..399e4e866a9c 100644
--- a/Documentation/networking/nf_conntrack-sysctl.txt
+++ b/Documentation/networking/nf_conntrack-sysctl.txt
@@ -33,24 +33,6 @@ nf_conntrack_events - BOOLEAN
         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/MAINTAINERS b/MAINTAINERS
index 1cd38a7e0064..4012c2f98617 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1442,6 +1442,7 @@ F:	drivers/cpufreq/mvebu-cpufreq.c
 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 @@ S:	Supported
 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 @@ S:	Supported
 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/
@@ -4620,8 +4626,9 @@ F:	sound/usb/misc/ua101.c
 
 EXTENSIBLE FIRMWARE INTERFACE (EFI)
 M:      Matt Fleming <matt@codeblueprint.co.uk>
+M:      Ard Biesheuvel <ard.biesheuvel@linaro.org>
 L:      linux-efi@vger.kernel.org
-T:      git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
+T:      git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
 S:      Maintained
 F:      Documentation/efi-stub.txt
 F:      arch/ia64/kernel/efi.c
@@ -5286,6 +5293,12 @@ M:	Joe Perches <joe@perches.com>
 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>
@@ -8099,6 +8112,7 @@ S:	Maintained
 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
@@ -8212,7 +8226,7 @@ F:	include/linux/mfd/
 MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
 M:      Ulf Hansson <ulf.hansson@linaro.org>
 L:      linux-mmc@vger.kernel.org
-T:      git git://git.linaro.org/people/ulf.hansson/mmc.git
+T:      git git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc.git
 S:      Maintained
 F:      Documentation/devicetree/bindings/mmc/
 F:      drivers/mmc/
@@ -8508,11 +8522,10 @@ F:	Documentation/devicetree/bindings/net/wireless/
 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/
 
@@ -9299,7 +9312,7 @@ S:	Maintained
 F:      drivers/pci/host/*designware*
 
 PCI DRIVER FOR SYNOPSYS PROTOTYPING DEVICE
-M:      Joao Pinto <jpinto@synopsys.com>
+M:      Jose Abreu <Jose.Abreu@synopsys.com>
 L:      linux-pci@vger.kernel.org
 S:      Maintained
 F:      Documentation/devicetree/bindings/pci/designware-pcie.txt
@@ -9888,33 +9901,32 @@ F:	Documentation/scsi/LICENSE.qla4xxx
 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/
diff --git a/Makefile b/Makefile
index 512e47a53e9a..a2650f9c6a25 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index ecd12379e2cd..bd204bfa29ed 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -41,6 +41,8 @@ config ARC
         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 @@ if SMP
 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 @@ config ARC_SMP_HALT_ON_RESET
 
 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 @@ config ARC_DBG_TLB_PARANOIA
         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 aa82d13d4213..864adad52280 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -50,9 +50,6 @@ atleast_gcc44 :=  $(call cc-ifversion, -ge, 0404, y)
 
 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 e597cb34c16a..f94cf151e06a 100644
--- a/arch/arc/boot/Makefile
+++ b/arch/arc/boot/Makefile
@@ -14,9 +14,15 @@ UIMAGE_ENTRYADDR   = $(LINUX_START_TEXT)
 
 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: vmlinux FORCE
 $(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 db25c65155cb..7f3f9f63708c 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 fb781e34f322..b3410ff6a62d 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 7096f97a1434..aa2d6da9d187 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 847e3bbe387f..c8fbe4114bad 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 518222bb3f8e..6e91d8b339c3 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 48b37c693db3..cb954cdab070 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 e56f9fcc5581..772b67ca56e7 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 41fa2ec9e02c..9a34136d84b2 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 72f9179b1a24..c424d5abc318 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;
+
+        READ_BCR(ARC_REG_MCIP_BCR, mp);
 
-        if (!idu_detected)
+        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 9a2849756022..42e964db2967 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;
-
-        sec_to_patch = sechdrs[sechdrs[relsec].sh_info].sh_addr;
+        Elf32_Addr relocation, location, tgt_addr;
+        unsigned int tgtsec;
+
+        /*
+         * @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 be1972bd2729..59aa43cb146e 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 3df7f9c72f42..0385df77a697 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;
-}
 
-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           } }
-};
+        /* 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 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 934150e7ac48..82f9bc819f4a 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 97dddbefb86a..2b96cfc3be75 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 20afc65e22dc..60aab5a7522b 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 ec868a9081a1..bdb295e09160 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 f1967eeb32e7..b30e4e36bb00 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -237,15 +237,6 @@ ex_saved_reg1:
 
 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 @@ ENTRY(EV_TLBMissI)
 
         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 @@ ENTRY(EV_TLBMissD)
 
         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 b3df1c60d465..386eee6de232 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 2c49c3614bda..5357ea9c14b1 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 8789cd518933..950f07ba0337 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 a3824e61bd72..d7fdb2a7d97b 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 437d0740dec6..11f37ed1dbff 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -850,6 +850,7 @@ CONFIG_PWM_SUN4I=y
 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 194b69923389..ada0d29a660f 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 2cb9dc770e1d..314100a06ccb 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 703fa0f3cd8f..08030b18f10a 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/kvm/arm.c b/arch/arm/kvm/arm.c
index 03e9273f1876..08bb84f2ad58 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -1312,6 +1312,13 @@ static int init_hyp_mode(void)
                 goto out_err;
         }
 
+        err = create_hyp_mappings(kvm_ksym_ref(__bss_start),
+                                  kvm_ksym_ref(__bss_stop), PAGE_HYP_RO);
+        if (err) {
+                kvm_err("Cannot map bss section\n");
+                goto out_err;
+        }
+
         /*
          * Map the Hyp stack pages
          */
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 0df062d8b2c9..b54db47f6f32 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,
+        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 97fd25105e2c..45801b27ee5c 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 f9b6bd306cfe..541647f57192 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -23,6 +23,7 @@ config MACH_MVEBU_V7
         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 @@ config MACH_ARMADA_370
         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 @@ config MACH_ARMADA_375
         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 @@ config MACH_ARMADA_38X
         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 82dddee3a469..3930fbba30b4 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 6d8e8e3365d1..4cdfab31a0b6 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 @@ ENTRY(v4t_late_abort)
 /* 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 @@ ENTRY(v4t_late_abort)
 .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 @@ ENTRY(v4t_late_abort)
         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 @@ ENTRY(v4t_late_abort)
         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 @@ ENTRY(v4t_late_abort)
 .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 @@ ENTRY(v4t_late_abort)
 .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 @@ ENTRY(v4t_late_abort)
         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 @@ ENTRY(v4t_late_abort)
 .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 @@ ENTRY(v4t_late_abort)
         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 @@ ENTRY(v4t_late_abort)
         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 b/arch/arm64/Kconfig
index 30398dbc940a..969ef880d234 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -915,7 +915,7 @@ config RANDOMIZE_BASE
 
 config RANDOMIZE_MODULE_REGION_FULL
         bool "Randomize the module region independently from the core kernel"
-        depends on RANDOMIZE_BASE
+        depends on RANDOMIZE_BASE && !DYNAMIC_FTRACE
         default y
         help
           Randomizes the location of the module region without considering the
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index cfbdf02ef566..101794f5ce10 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -190,6 +190,7 @@ config ARCH_THUNDER
 
 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/Makefile b/arch/arm64/Makefile
index ab51aed6b6c1..3635b8662724 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -15,7 +15,7 @@ CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 GZFLAGS         :=-9
 
 ifneq ($(CONFIG_RELOCATABLE),)
-LDFLAGS_vmlinux         += -pie -Bsymbolic
+LDFLAGS_vmlinux         += -pie -shared -Bsymbolic
 endif
 
 ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
index 2d7872a36b91..b09f3bc5c6c1 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 220ac7057d12..97d331ec2500 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 337da90bd7da..7f0dc13b4087 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 e5e3ed678b6f..602e2c2e9a4d 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 46cdddfcea6c..e5eeca2c2456 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 5797933ef80e..ea0a8eceefd4 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 08fd7cf7769c..56a1b2e92cf3 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/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 758d74fedfad..a27c3245ba21 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -94,7 +94,7 @@ struct arm64_cpu_capabilities {
         u16 capability;
         int def_scope;                  /* default scope */
         bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
-        void (*enable)(void *);         /* Called on all active CPUs */
+        int (*enable)(void *);          /* Called on all active CPUs */
         union {
                 struct {        /* To be used for erratum handling only */
                         u32 midr_model;
diff --git a/arch/arm64/include/asm/exec.h b/arch/arm64/include/asm/exec.h
index db0563c23482..f7865dd9d868 100644
--- a/arch/arm64/include/asm/exec.h
+++ b/arch/arm64/include/asm/exec.h
@@ -18,6 +18,9 @@
 #ifndef __ASM_EXEC_H
 #define __ASM_EXEC_H
 
+#include <linux/sched.h>
+
 extern unsigned long arch_align_stack(unsigned long sp);
+void uao_thread_switch(struct task_struct *next);
 
 #endif  /* __ASM_EXEC_H */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index fd9d5fd788f5..f5ea0ba70f07 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -178,11 +178,6 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
         return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
 }
 
-static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
-{
-        return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR);
-}
-
 static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 {
         return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
@@ -203,6 +198,12 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
         return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
 }
 
+static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
+{
+        return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
+                kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+}
+
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
 {
         return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ba62df8c6e35..b71086d25195 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/include/asm/module.h b/arch/arm64/include/asm/module.h
index e12af6754634..06ff7fd9e81f 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -17,6 +17,7 @@
 #define __ASM_MODULE_H
 
 #include <asm-generic/module.h>
+#include <asm/memory.h>
 
 #define MODULE_ARCH_VERMAGIC    "aarch64"
 
@@ -32,6 +33,10 @@ u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
                           Elf64_Sym *sym);
 
 #ifdef CONFIG_RANDOMIZE_BASE
+#ifdef CONFIG_MODVERSIONS
+#define ARCH_RELOCATES_KCRCTAB
+#define reloc_start             (kimage_vaddr - KIMAGE_VADDR)
+#endif
 extern u64 module_alloc_base;
 #else
 #define module_alloc_base       ((u64)_etext - MODULES_VSIZE)
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 2fee2f59288c..5394c8405e66 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -44,48 +44,44 @@ static inline unsigned long __percpu_##op(void *ptr,			\
                                                                         \
         switch (size) {                                                 \
         case 1:                                                         \
-                do {                                                    \
-                        asm ("//__per_cpu_" #op "_1\n"                  \
-                        "ldxrb    %w[ret], %[ptr]\n"                    \
+                asm ("//__per_cpu_" #op "_1\n"                          \
+                "1:     ldxrb     %w[ret], %[ptr]\n"                    \
                         #asm_op " %w[ret], %w[ret], %w[val]\n"          \
-                        "stxrb    %w[loop], %w[ret], %[ptr]\n"          \
-                        : [loop] "=&r" (loop), [ret] "=&r" (ret),       \
-                          [ptr] "+Q"(*(u8 *)ptr)                        \
-                        : [val] "Ir" (val));                            \
-                } while (loop);                                         \
+                "       stxrb     %w[loop], %w[ret], %[ptr]\n"          \
+                "       cbnz      %w[loop], 1b"                         \
+                : [loop] "=&r" (loop), [ret] "=&r" (ret),               \
+                  [ptr] "+Q"(*(u8 *)ptr)                                \
+                : [val] "Ir" (val));                                    \
                 break;                                                  \
         case 2:                                                         \
-                do {                                                    \
-                        asm ("//__per_cpu_" #op "_2\n"                  \
-                        "ldxrh    %w[ret], %[ptr]\n"                    \
+                asm ("//__per_cpu_" #op "_2\n"                          \
+                "1:     ldxrh     %w[ret], %[ptr]\n"                    \
                         #asm_op " %w[ret], %w[ret], %w[val]\n"          \
-                        "stxrh    %w[loop], %w[ret], %[ptr]\n"          \
-                        : [loop] "=&r" (loop), [ret] "=&r" (ret),       \
-                          [ptr]  "+Q"(*(u16 *)ptr)                      \
-                        : [val] "Ir" (val));                            \
-                } while (loop);                                         \
+                "       stxrh     %w[loop], %w[ret], %[ptr]\n"          \
+                "       cbnz      %w[loop], 1b"                         \
+                : [loop] "=&r" (loop), [ret] "=&r" (ret),               \
+                  [ptr]  "+Q"(*(u16 *)ptr)                              \
+                : [val] "Ir" (val));                                    \
                 break;                                                  \
         case 4:                                                         \
-                do {                                                    \
-                        asm ("//__per_cpu_" #op "_4\n"                  \
-                        "ldxr     %w[ret], %[ptr]\n"                    \
+                asm ("//__per_cpu_" #op "_4\n"                          \
+                "1:     ldxr      %w[ret], %[ptr]\n"                    \
                         #asm_op " %w[ret], %w[ret], %w[val]\n"          \
-                        "stxr     %w[loop], %w[ret], %[ptr]\n"          \
-                        : [loop] "=&r" (loop), [ret] "=&r" (ret),       \
-                          [ptr] "+Q"(*(u32 *)ptr)                       \
-                        : [val] "Ir" (val));                            \
-                } while (loop);                                         \
+                "       stxr      %w[loop], %w[ret], %[ptr]\n"          \
+                "       cbnz      %w[loop], 1b"                         \
+                : [loop] "=&r" (loop), [ret] "=&r" (ret),               \
+                  [ptr] "+Q"(*(u32 *)ptr)                               \
+                : [val] "Ir" (val));                                    \
                 break;                                                  \
         case 8:                                                         \
-                do {                                                    \
-                        asm ("//__per_cpu_" #op "_8\n"                  \
-                        "ldxr     %[ret], %[ptr]\n"                     \
+                asm ("//__per_cpu_" #op "_8\n"                          \
+                "1:     ldxr      %[ret], %[ptr]\n"                     \
                         #asm_op " %[ret], %[ret], %[val]\n"             \
-                        "stxr     %w[loop], %[ret], %[ptr]\n"           \
-                        : [loop] "=&r" (loop), [ret] "=&r" (ret),       \
-                          [ptr] "+Q"(*(u64 *)ptr)                       \
-                        : [val] "Ir" (val));                            \
-                } while (loop);                                         \
+                "       stxr      %w[loop], %[ret], %[ptr]\n"           \
+                "       cbnz      %w[loop], 1b"                         \
+                : [loop] "=&r" (loop), [ret] "=&r" (ret),               \
+                  [ptr] "+Q"(*(u64 *)ptr)                               \
+                : [val] "Ir" (val));                                    \
                 break;                                                  \
         default:                                                        \
                 BUILD_BUG();                                            \
@@ -150,44 +146,40 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 
         switch (size) {
         case 1:
-                do {
-                        asm ("//__percpu_xchg_1\n"
-                        "ldxrb %w[ret], %[ptr]\n"
-                        "stxrb %w[loop], %w[val], %[ptr]\n"
-                        : [loop] "=&r"(loop), [ret] "=&r"(ret),
-                          [ptr] "+Q"(*(u8 *)ptr)
-                        : [val] "r" (val));
-                } while (loop);
+                asm ("//__percpu_xchg_1\n"
+                "1:     ldxrb   %w[ret], %[ptr]\n"
+                "       stxrb   %w[loop], %w[val], %[ptr]\n"
+                "       cbnz    %w[loop], 1b"
+                : [loop] "=&r"(loop), [ret] "=&r"(ret),
+                  [ptr] "+Q"(*(u8 *)ptr)
+                : [val] "r" (val));
                 break;
         case 2:
-                do {
-                        asm ("//__percpu_xchg_2\n"
-                        "ldxrh %w[ret], %[ptr]\n"
-                        "stxrh %w[loop], %w[val], %[ptr]\n"
-                        : [loop] "=&r"(loop), [ret] "=&r"(ret),
-                          [ptr] "+Q"(*(u16 *)ptr)
-                        : [val] "r" (val));
-                } while (loop);
+                asm ("//__percpu_xchg_2\n"
+                "1:     ldxrh   %w[ret], %[ptr]\n"
+                "       stxrh   %w[loop], %w[val], %[ptr]\n"
+                "       cbnz    %w[loop], 1b"
+                : [loop] "=&r"(loop), [ret] "=&r"(ret),
+                  [ptr] "+Q"(*(u16 *)ptr)
+                : [val] "r" (val));
                 break;
         case 4:
-                do {
-                        asm ("//__percpu_xchg_4\n"
-                        "ldxr %w[ret], %[ptr]\n"
-                        "stxr %w[loop], %w[val], %[ptr]\n"
-                        : [loop] "=&r"(loop), [ret] "=&r"(ret),
-                          [ptr] "+Q"(*(u32 *)ptr)
-                        : [val] "r" (val));
-                } while (loop);
+                asm ("//__percpu_xchg_4\n"
+                "1:     ldxr    %w[ret], %[ptr]\n"
+                "       stxr    %w[loop], %w[val], %[ptr]\n"
+                "       cbnz    %w[loop], 1b"
+                : [loop] "=&r"(loop), [ret] "=&r"(ret),
+                  [ptr] "+Q"(*(u32 *)ptr)
+                : [val] "r" (val));
                 break;
         case 8:
-                do {
-                        asm ("//__percpu_xchg_8\n"
-                        "ldxr %[ret], %[ptr]\n"
-                        "stxr %w[loop], %[val], %[ptr]\n"
-                        : [loop] "=&r"(loop), [ret] "=&r"(ret),
-                          [ptr] "+Q"(*(u64 *)ptr)
-                        : [val] "r" (val));
-                } while (loop);
+                asm ("//__percpu_xchg_8\n"
+                "1:     ldxr    %[ret], %[ptr]\n"
+                "       stxr    %w[loop], %[val], %[ptr]\n"
+                "       cbnz    %w[loop], 1b"
+                : [loop] "=&r"(loop), [ret] "=&r"(ret),
+                  [ptr] "+Q"(*(u64 *)ptr)
+                : [val] "r" (val));
                 break;
         default:
                 BUILD_BUG();
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index df2e53d3a969..60e34824e18c 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -188,8 +188,8 @@ static inline void spin_lock_prefetch(const void *ptr)
 
 #endif
 
-void cpu_enable_pan(void *__unused);
-void cpu_enable_uao(void *__unused);
-void cpu_enable_cache_maint_trap(void *__unused);
+int cpu_enable_pan(void *__unused);
+int cpu_enable_uao(void *__unused);
+int cpu_enable_cache_maint_trap(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index e8d46e8e6079..6c80b3699cb8 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -286,7 +286,7 @@ asm(
 
 #define write_sysreg_s(v, r) do {                                       \
         u64 __val = (u64)v;                                             \
-        asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val));  \
+        asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \
 } while (0)
 
 static inline void config_sctlr_el1(u32 clear, u32 set)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index bcaf6fba1b65..55d0adbf6509 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -21,6 +21,7 @@
 /*
  * User space memory access functions
  */
+#include <linux/bitops.h>
 #include <linux/kasan-checks.h>
 #include <linux/string.h>
 #include <linux/thread_info.h>
@@ -102,6 +103,13 @@ static inline void set_fs(mm_segment_t fs)
         flag;                                                           \
 })
 
+/*
+ * When dealing with data aborts or instruction traps we may end up with
+ * a tagged userland pointer. Clear the tag to get a sane pointer to pass
+ * on to access_ok(), for instance.
+ */
+#define untagged_addr(addr)             sign_extend64(addr, 55)
+
 #define access_ok(type, addr, size)     __range_ok(addr, size)
 #define user_addr_max                   get_fs
 
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 42ffdb54e162..b0988bb1bf64 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -280,35 +280,43 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 /*
  * Error-checking SWP macros implemented using ldxr{b}/stxr{b}
  */
-#define __user_swpX_asm(data, addr, res, temp, B)               \
+
+/* Arbitrary constant to ensure forward-progress of the LL/SC loop */
+#define __SWP_LL_SC_LOOPS       4
+
+#define __user_swpX_asm(data, addr, res, temp, temp2, B)        \
         __asm__ __volatile__(                                   \
+        "       mov             %w3, %w7\n"                     \
         ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,    \
                     CONFIG_ARM64_PAN)                           \
-        "0:     ldxr"B"         %w2, [%3]\n"                    \
-        "1:     stxr"B"         %w0, %w1, [%3]\n"               \
+        "0:     ldxr"B"         %w2, [%4]\n"                    \
+        "1:     stxr"B"         %w0, %w1, [%4]\n"               \
         "       cbz             %w0, 2f\n"                      \
-        "       mov             %w0, %w4\n"                     \
+        "       sub             %w3, %w3, #1\n"                 \
+        "       cbnz            %w3, 0b\n"                      \
+        "       mov             %w0, %w5\n"                     \
         "       b               3f\n"                           \
         "2:\n"                                                  \
         "       mov             %w1, %w2\n"                     \
         "3:\n"                                                  \
         "       .pushsection     .fixup,\"ax\"\n"               \
         "       .align          2\n"                            \
-        "4:     mov             %w0, %w5\n"                     \
+        "4:     mov             %w0, %w6\n"                     \
         "       b               3b\n"                           \
         "       .popsection"                                    \
         _ASM_EXTABLE(0b, 4b)                                    \
         _ASM_EXTABLE(1b, 4b)                                    \
         ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,    \
                 CONFIG_ARM64_PAN)                               \
-        : "=&r" (res), "+r" (data), "=&r" (temp)                \
-        : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)              \
+        : "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2) \
+        : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT),             \
+          "i" (__SWP_LL_SC_LOOPS)                               \
         : "memory")
 
-#define __user_swp_asm(data, addr, res, temp) \
-        __user_swpX_asm(data, addr, res, temp, "")
-#define __user_swpb_asm(data, addr, res, temp) \
-        __user_swpX_asm(data, addr, res, temp, "b")
+#define __user_swp_asm(data, addr, res, temp, temp2) \
+        __user_swpX_asm(data, addr, res, temp, temp2, "")
+#define __user_swpb_asm(data, addr, res, temp, temp2) \
+        __user_swpX_asm(data, addr, res, temp, temp2, "b")
 
 /*
  * Bit 22 of the instruction encoding distinguishes between
@@ -328,12 +336,12 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
         }
 
         while (1) {
-                unsigned long temp;
+                unsigned long temp, temp2;
 
                 if (type == TYPE_SWPB)
-                        __user_swpb_asm(*data, address, res, temp);
+                        __user_swpb_asm(*data, address, res, temp, temp2);
                 else
-                        __user_swp_asm(*data, address, res, temp);
+                        __user_swp_asm(*data, address, res, temp, temp2);
 
                 if (likely(res != -EAGAIN) || signal_pending(current))
                         break;
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0150394f4cab..b75e917aac46 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -39,10 +39,11 @@ has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
                 (arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
 }
 
-static void cpu_enable_trap_ctr_access(void *__unused)
+static int cpu_enable_trap_ctr_access(void *__unused)
 {
         /* Clear SCTLR_EL1.UCT */
         config_sctlr_el1(SCTLR_EL1_UCT, 0);
+        return 0;
 }
 
 #define MIDR_RANGE(model, min, max) \
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d577f263cc4a..c02504ea304b 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -19,7 +19,9 @@
 #define pr_fmt(fmt) "CPU features: " fmt
 
 #include <linux/bsearch.h>
+#include <linux/cpumask.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
@@ -941,7 +943,13 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
         for (; caps->matches; caps++)
                 if (caps->enable && cpus_have_cap(caps->capability))
-                        on_each_cpu(caps->enable, NULL, true);
+                        /*
+                         * Use stop_machine() as it schedules the work allowing
+                         * us to modify PSTATE, instead of on_each_cpu() which
+                         * uses an IPI, giving us a PSTATE that disappears when
+                         * we return.
+                         */
+                        stop_machine(caps->enable, NULL, cpu_online_mask);
 }
 
 /*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 427f6d3f084c..332e33193ccf 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -586,8 +586,9 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
         b.lt    4f                              // Skip if no PMU present
         mrs     x0, pmcr_el0                    // Disable debug access traps
         ubfx    x0, x0, #11, #5                 // to EL2 and allow access to
-        msr     mdcr_el2, x0                    // all PMU counters from EL1
 4:
+        csel    x0, xzr, x0, lt                 // all PMU counters from EL1
+        msr     mdcr_el2, x0                    // (if they exist)
 
         /* Stage-2 translation */
         msr     vttbr_el2, xzr
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 27b2f1387df4..01753cd7d3f0 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -49,6 +49,7 @@
 #include <asm/alternative.h>
 #include <asm/compat.h>
 #include <asm/cacheflush.h>
+#include <asm/exec.h>
 #include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
@@ -186,10 +187,19 @@ void __show_regs(struct pt_regs *regs)
         printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
                regs->pc, lr, regs->pstate);
         printk("sp : %016llx\n", sp);
-        for (i = top_reg; i >= 0; i--) {
+
+        i = top_reg;
+
+        while (i >= 0) {
                 printk("x%-2d: %016llx ", i, regs->regs[i]);
-                if (i % 2 == 0)
-                        printk("\n");
+                i--;
+
+                if (i % 2 == 0) {
+                        pr_cont("x%-2d: %016llx ", i, regs->regs[i]);
+                        i--;
+                }
+
+                pr_cont("\n");
         }
         printk("\n");
 }
@@ -301,7 +311,7 @@ static void tls_thread_switch(struct task_struct *next)
 }
 
 /* Restore the UAO state depending on next's addr_limit */
-static void uao_thread_switch(struct task_struct *next)
+void uao_thread_switch(struct task_struct *next)
 {
         if (IS_ENABLED(CONFIG_ARM64_UAO)) {
                 if (task_thread_info(next)->addr_limit == KERNEL_DS)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d3f151cfd4a1..8507703dabe4 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -544,6 +544,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
                         return;
                 }
                 bootcpu_valid = true;
+                early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
                 return;
         }
 
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index ad734142070d..bb0cd787a9d3 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -1,8 +1,11 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
+#include <asm/alternative.h>
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
+#include <asm/exec.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
@@ -50,6 +53,14 @@ void notrace __cpu_suspend_exit(void)
         set_my_cpu_offset(per_cpu_offset(cpu));
 
         /*
+         * PSTATE was not saved over suspend/resume, re-enable any detected
+         * features that might not have been set correctly.
+         */
+        asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+                        CONFIG_ARM64_PAN));
+        uao_thread_switch(current);
+
+        /*
          * Restore HW breakpoint registers to sane values
          * before debug exceptions are possibly reenabled
          * through local_dbg_restore.
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 5ff020f8fb7f..c9986b3e0a96 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -428,24 +428,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
         force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
 }
 
-void cpu_enable_cache_maint_trap(void *__unused)
+int cpu_enable_cache_maint_trap(void *__unused)
 {
         config_sctlr_el1(SCTLR_EL1_UCI, 0);
+        return 0;
 }
 
 #define __user_cache_maint(insn, address, res)                  \
-        asm volatile (                                          \
-                "1:     " insn ", %1\n"                         \
-                "       mov     %w0, #0\n"                      \
-                "2:\n"                                          \
-                "       .pushsection .fixup,\"ax\"\n"           \
-                "       .align  2\n"                            \
-                "3:     mov     %w0, %w2\n"                     \
-                "       b       2b\n"                           \
-                "       .popsection\n"                          \
-                _ASM_EXTABLE(1b, 3b)                            \
-                : "=r" (res)                                    \
-                : "r" (address), "i" (-EFAULT) )
+        if (untagged_addr(address) >= user_addr_max())          \
+                res = -EFAULT;                                  \
+        else                                                    \
+                asm volatile (                                  \
+                        "1:     " insn ", %1\n"                 \
+                        "       mov     %w0, #0\n"              \
+                        "2:\n"                                  \
+                        "       .pushsection .fixup,\"ax\"\n"   \
+                        "       .align  2\n"                    \
+                        "3:     mov     %w0, %w2\n"             \
+                        "       b       2b\n"                   \
+                        "       .popsection\n"                  \
+                        _ASM_EXTABLE(1b, 3b)                    \
+                        : "=r" (res)                            \
+                        : "r" (address), "i" (-EFAULT) )
 
 static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 {
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 53d9159662fe..0f8788374815 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -29,7 +29,9 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/preempt.h>
 
+#include <asm/bug.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -670,9 +672,17 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 NOKPROBE_SYMBOL(do_debug_exception);
 
 #ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
 {
+        /*
+         * We modify PSTATE. This won't work from irq context as the PSTATE
+         * is discarded once we return from the exception.
+         */
+        WARN_ON_ONCE(in_interrupt());
+
         config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+        asm(SET_PSTATE_PAN(1));
+        return 0;
 }
 #endif /* CONFIG_ARM64_PAN */
 
@@ -683,8 +693,9 @@ void cpu_enable_pan(void *__unused)
  * We need to enable the feature at runtime (instead of adding it to
  * PSR_MODE_EL1h) as the feature may not be implemented by the cpu.
  */
-void cpu_enable_uao(void *__unused)
+int cpu_enable_uao(void *__unused)
 {
         asm(SET_PSTATE_UAO(1));
+        return 0;
 }
 #endif /* CONFIG_ARM64_UAO */
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 21c489bdeb4e..212c4d1e2f26 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -421,35 +421,35 @@ void __init mem_init(void)
 
         pr_notice("Virtual kernel memory layout:\n");
 #ifdef CONFIG_KASAN
-        pr_cont("    kasan   : 0x%16lx - 0x%16lx   (%6ld GB)\n",
+        pr_notice("    kasan   : 0x%16lx - 0x%16lx   (%6ld GB)\n",
                 MLG(KASAN_SHADOW_START, KASAN_SHADOW_END));
 #endif
-        pr_cont("    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+        pr_notice("    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n",
                 MLM(MODULES_VADDR, MODULES_END));
-        pr_cont("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
+        pr_notice("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
                 MLG(VMALLOC_START, VMALLOC_END));
-        pr_cont("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+        pr_notice("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
                 MLK_ROUNDUP(_text, _etext));
-        pr_cont("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+        pr_notice("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
                 MLK_ROUNDUP(__start_rodata, __init_begin));
-        pr_cont("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+        pr_notice("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
                 MLK_ROUNDUP(__init_begin, __init_end));
-        pr_cont("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+        pr_notice("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
                 MLK_ROUNDUP(_sdata, _edata));
-        pr_cont("       .bss : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+        pr_notice("       .bss : 0x%p" " - 0x%p" "   (%6ld KB)\n",
                 MLK_ROUNDUP(__bss_start, __bss_stop));
-        pr_cont("    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n",
+        pr_notice("    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n",
                 MLK(FIXADDR_START, FIXADDR_TOP));
-        pr_cont("    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+        pr_notice("    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n",
                 MLM(PCI_IO_START, PCI_IO_END));
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-        pr_cont("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n",
+        pr_notice("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n",
                 MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE));
-        pr_cont("              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
+        pr_notice("              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
                 MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
                     (unsigned long)virt_to_page(high_memory)));
 #endif
-        pr_cont("    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n",
+        pr_notice("    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n",
                 MLM(__phys_to_virt(memblock_start_of_DRAM()),
                     (unsigned long)high_memory));
 
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 778a985c8a70..4b32168cf91a 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 099e170a93ee..0068fd411a84 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 b408fe660cf8..3cef06875f5c 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 ad1f81f574e5..7138303cbbf2 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/kvm/mips.c b/arch/mips/kvm/mips.c
index ce961495b5e1..622037d851a3 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -14,6 +14,7 @@
 #include <linux/err.h>
 #include <linux/kdebug.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
 #include <linux/bootmem.h>
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index f7a184b6c35b..57d42d129033 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -32,9 +32,16 @@ static struct addr_range prep_kernel(void)
         void *addr = 0;
         struct elf_info ei;
         long len;
+        int uncompressed_image = 0;
 
-        partial_decompress(vmlinuz_addr, vmlinuz_size,
+        len = partial_decompress(vmlinuz_addr, vmlinuz_size,
                 elfheader, sizeof(elfheader), 0);
+        /* assume uncompressed data if -1 is returned */
+        if (len == -1) {
+                uncompressed_image = 1;
+                memcpy(elfheader, vmlinuz_addr, sizeof(elfheader));
+                printf("No valid compressed data found, assume uncompressed data\n\r");
+        }
 
         if (!parse_elf64(elfheader, &ei) && !parse_elf32(elfheader, &ei))
                 fatal("Error: not a valid PPC32 or PPC64 ELF file!\n\r");
@@ -67,6 +74,13 @@ static struct addr_range prep_kernel(void)
                                         "device tree\n\r");
         }
 
+        if (uncompressed_image) {
+                memcpy(addr, vmlinuz_addr + ei.elfoffset, ei.loadsize);
+                printf("0x%lx bytes of uncompressed data copied\n\r",
+                       ei.loadsize);
+                goto out;
+        }
+
         /* Finally, decompress the kernel */
         printf("Decompressing (0x%p <- 0x%p:0x%p)...\n\r", addr,
                vmlinuz_addr, vmlinuz_addr+vmlinuz_size);
@@ -82,7 +96,7 @@ static struct addr_range prep_kernel(void)
                          len, ei.loadsize);
 
         printf("Done! Decompressed 0x%lx bytes\n\r", len);
-
+out:
         flush_cache(addr, ei.loadsize);
 
         return (struct addr_range){addr, ei.memsize};
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index ee655ed1ff1b..1e8fceb308a5 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 01b8a13f0224..3919332965af 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 2e4e7d878c8e..84d49b197c32 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 f6f68f73e858..99e1397b71da 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/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index cf12c580f6b2..e8cdfec8d512 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -16,6 +16,10 @@
 
 #define __NR__exit __NR_exit
 
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
+
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f129408c6022..08ba447a4b3d 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -95,19 +95,35 @@ __start_interrupts:
 /* No virt vectors corresponding with 0x0..0x100 */
 EXC_VIRT_NONE(0x4000, 0x4100)
 
-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.
+        /*
+         * If running native on arch 2.06 or later, check if we are waking up
+         * from nap/sleep/winkle, and branch to idle handler.
          */
-        mfspr   r13,SPRN_SRR1
-        rlwinm. r13,r13,47-31,30,31
-        beq     9f
+#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
 
-        cmpwi   cr3,r13,2
-        GET_PACA(r13)
+EXC_REAL_BEGIN(system_reset, 0x100, 0x200)
+        SET_SCRATCH0(r13)
+        EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+                                 IDLETEST, 0x100)
+
+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 @@ BEGIN_FTR_SECTION
         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 @@ EXC_VIRT(trap_0b, 0x4b00, 0x4c00, 0xb00)
 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 9781c69eae57..03d089b3ed72 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 bd739fed26e3..72dac0b58061 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -90,6 +90,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
  * 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 @@ core_idle_lock_held:
         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 @@ _GLOBAL(pnv_powersave_common)
         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 @@ _GLOBAL(pnv_powersave_common)
 
         .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 @@ enter_winkle:
  * 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 9e7c10fe205f..ce6dc61b15b2 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 82ff5de8b1e7..a0ea63ac2b52 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/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index bb0354222b11..362954f98029 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -106,6 +106,8 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
         switch (REGION_ID(ea)) {
         case USER_REGION_ID:
                 pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
+                if (mm == NULL)
+                        return 1;
                 psize = get_slice_psize(mm, ea);
                 ssize = user_segment_size(ea);
                 vsid = get_vsid(mm->context.id, ea, ssize);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 75b9cd6150cc..a51c188b81f3 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -845,7 +845,7 @@ void __init dump_numa_cpu_topology(void)
                 return;
 
         for_each_online_node(node) {
-                printk(KERN_DEBUG "Node %d CPUs:", node);
+                pr_info("Node %d CPUs:", node);
 
                 count = 0;
                 /*
@@ -856,52 +856,18 @@ void __init dump_numa_cpu_topology(void)
                         if (cpumask_test_cpu(cpu,
                                         node_to_cpumask_map[node])) {
                                 if (count == 0)
-                                        printk(" %u", cpu);
+                                        pr_cont(" %u", cpu);
                                 ++count;
                         } else {
                                 if (count > 1)
-                                        printk("-%u", cpu - 1);
+                                        pr_cont("-%u", cpu - 1);
                                 count = 0;
                         }
                 }
 
                 if (count > 1)
-                        printk("-%u", nr_cpu_ids - 1);
-                printk("\n");
-        }
-}
-
-static void __init dump_numa_memory_topology(void)
-{
-        unsigned int node;
-        unsigned int count;
-
-        if (min_common_depth == -1 || !numa_enabled)
-                return;
-
-        for_each_online_node(node) {
-                unsigned long i;
-
-                printk(KERN_DEBUG "Node %d Memory:", node);
-
-                count = 0;
-
-                for (i = 0; i < memblock_end_of_DRAM();
-                     i += (1 << SECTION_SIZE_BITS)) {
-                        if (early_pfn_to_nid(i >> PAGE_SHIFT) == node) {
-                                if (count == 0)
-                                        printk(" 0x%lx", i);
-                                ++count;
-                        } else {
-                                if (count > 0)
-                                        printk("-0x%lx", i);
-                                count = 0;
-                        }
-                }
-
-                if (count > 0)
-                        printk("-0x%lx", i);
-                printk("\n");
+                        pr_cont("-%u", nr_cpu_ids - 1);
+                pr_cont("\n");
         }
 }
 
@@ -947,8 +913,6 @@ void __init initmem_init(void)
 
         if (parse_numa_properties())
                 setup_nonnuma();
-        else
-                dump_numa_memory_topology();
 
         memblock_dump_all();
 
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 0e49ec541ab5..bda8c43be78a 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/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 64053d9ac3f2..836c56290499 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 03323175de30..602af692efdc 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 02613bad8bbb..3066031a73fe 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 43446fa2a4e5..c74c59236f44 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 6693383bc01b..55d4fe174fd9 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)
-{
-        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)
+static int show_address(void *data, unsigned long address, int reliable)
 {
-        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 17431f63de00..955a7b6fa0a4 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 44f84b23d4e5..355db9db8210 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/intercept.c b/arch/s390/kvm/intercept.c
index 1cab8a177d0e..7a27eebab28a 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -119,8 +119,13 @@ static int handle_validity(struct kvm_vcpu *vcpu)
 
         vcpu->stat.exit_validity++;
         trace_kvm_s390_intercept_validity(vcpu, viwhy);
-        WARN_ONCE(true, "kvm: unhandled validity intercept 0x%x\n", viwhy);
-        return -EOPNOTSUPP;
+        KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%pK)", viwhy,
+                  current->pid, vcpu->kvm);
+
+        /* do not warn on invalid runtime instrumentation mode */
+        WARN_ONCE(viwhy != 0x44, "kvm: unhandled validity intercept 0x%x\n",
+                  viwhy);
+        return -EINVAL;
 }
 
 static int handle_instruction(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index cd404aa3931c..4a0c5bce3552 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 f56a39bd8ba6..b3e9d18f2ec6 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 16f4c3960b87..9a4de4599c7b 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 a6cfdabb6054..5b0ed48e5b0c 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 d9c5876c6121..8011e79f59c9 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 87990b7c6b0d..07c9f2e9bf57 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 bec481aaca16..7b4898a36eee 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 b68acc563235..5373136c412b 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 beba6c11554c..6aa3da152c20 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -926,48 +926,11 @@ tlb_type:	.word	0	/* Must NOT end up in BSS */
 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 59bbeff55024..07933b9e9ce0 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 11228861d9b4..8a6982dfd733 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 d3035ba6cd31..8182f7caf5b1 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 b7d0bd6b1406..69a439fa2fc1 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 780550e1afc7..9947427ce354 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 89358ee94851..059ea24ad73d 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         .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 885f00e81d1a..69912d2f8b54 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -38,7 +38,7 @@ lib-$(CONFIG_SPARC64) +=  NG4patch.o NG4copy_page.o NG4clear_page.o NG4memset.o
 lib-$(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 d5242b8c4f94..b79a6998d87c 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 4e962d993b10..dcec55f254ab 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 d5f585df2f3f..c629dbd121b6 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
          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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
          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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         .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 2e8ee7ad07a9..16a286c1a528 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 be0bf4590df8..6b0276ffc858 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 8e13ee1f4454..75bb93b1437f 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
          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 5d1e4d1ac21e..9cd42fcbc781 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 ff630dcb273c..5c358afd464e 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 96a14caf6966..d88c4ed50a00 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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
          * 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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 
 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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 
 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 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
         .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 ecc5692fa2b4..bb6ff73229e3 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 9eea392e44d4..ed92ce739558 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 97e1b211090c..4f0d50b33a72 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 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 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, 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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
          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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
         .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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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)
-
-93:     EX_LD_FP(LOAD(ldd, %o1, %f2))
+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), 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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
          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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
          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 88ad73d86fe4..db73010a1af8 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 845139d75537..c4ee858e352a 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 491ee69e4995..54f98706b03b 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
          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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
         .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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
         /* 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
          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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
         .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 482de093bdae..0252b218de45 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 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
         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 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
         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 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
 
 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 @@ ENTRY(___copy_in_user)	/* %o0=dst, %o1=src, %o2=len */
         .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 ac96ae236709..000000000000
--- 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 f2b77112e9d8..e20fbbafb0b0 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 b4f4733abc6e..5d2fd6cd3189 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 @@ __flush_tlb_page:	/* 22 insns */
 
         .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 @@ __flush_tlb_pending:	/* 26 insns */
 
         .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 @@ __flush_tlb_kernel_range:	/* 16 insns */
         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 @@ __cheetah_flush_tlb_pending:	/* 27 insns */
         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 @@ __hypervisor_tlb_tl0_error:
         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 @@ __hypervisor_flush_tlb_page: /* 11 insns */
         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 @@ __hypervisor_flush_tlb_pending: /* 16 insns */
         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 @@ tlb_patch_one:
         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 @@ cheetah_patch_cachetlbops:
          */
         .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 @@ xcall_flush_tlb_mm:	/* 21 insns */
         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 @@ xcall_flush_tlb_page:	/* 17 insns */
         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 @@ xcall_flush_tlb_kernel_range:	/* 25 insns */
         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 @@ xcall_fetch_glob_pmu_n4:
 
         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 @@ __hypervisor_tlb_xcall_error:
         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 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
         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 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
         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 @@ __hypervisor_xcall_flush_tlb_page: /* 17 insns */
         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 @@ xcall_kgdb_capture:
 
 #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 @@ hypervisor_patch_cachetlbops:
         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 @@ hypervisor_patch_cachetlbops:
         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 77f28ce9c646..9976fcecd17e 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 eab0915f5995..a74a2dbc0180 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 3ca87b5a8677..4f5ac726335f 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/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 1188bc849ee3..a39629206864 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -194,6 +194,8 @@
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 
 #define X86_FEATURE_INTEL_PT    ( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index de25aad07853..d34bd370074b 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/thread_info.h b/arch/x86/include/asm/thread_info.h
index 2aaca53c0974..ad6f5eb07a95 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -52,6 +52,15 @@ struct task_struct;
 #include <asm/cpufeature.h>
 #include <linux/atomic.h>
 
+struct thread_info {
+        unsigned long           flags;          /* low level flags */
+};
+
+#define INIT_THREAD_INFO(tsk)                   \
+{                                               \
+        .flags          = 0,                    \
+}
+
 #define init_stack              (init_thread_union.stack)
 
 #else /* !__ASSEMBLY__ */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8a5abaa7d453..931ced8ca345 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 620ab06bcf45..017bda12caae 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/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 8cb57df9398d..1db8dc490b66 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -32,6 +32,8 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 
         static const struct cpuid_bit cpuid_bits[] = {
                 { X86_FEATURE_INTEL_PT,         CR_EBX,25, 0x00000007, 0 },
+                { X86_FEATURE_AVX512_4VNNIW,    CR_EDX, 2, 0x00000007, 0 },
+                { X86_FEATURE_AVX512_4FMAPS,    CR_EDX, 3, 0x00000007, 0 },
                 { X86_FEATURE_APERFMPERF,       CR_ECX, 0, 0x00000006, 0 },
                 { X86_FEATURE_EPB,              CR_ECX, 3, 0x00000006, 0 },
                 { X86_FEATURE_HW_PSTATE,        CR_EDX, 7, 0x80000007, 0 },
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 81160578b91a..5130985b758b 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -27,6 +27,7 @@
 #include <asm/div64.h>
 #include <asm/x86_init.h>
 #include <asm/hypervisor.h>
+#include <asm/timer.h>
 #include <asm/apic.h>
 
 #define CPUID_VMWARE_INFO_LEAF  0x40000000
@@ -94,6 +95,10 @@ static void __init vmware_platform_setup(void)
         } else {
                 pr_warn("Failed to get TSC freq from the hypervisor\n");
         }
+
+#ifdef CONFIG_X86_IO_APIC
+        no_timer_check = 1;
+#endif
 }
 
 /*
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 124aa5c593f8..095ef7ddd6ae 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -74,6 +74,8 @@ void fpu__xstate_clear_all_cpu_caps(void)
         setup_clear_cpu_cap(X86_FEATURE_MPX);
         setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
         setup_clear_cpu_cap(X86_FEATURE_PKU);
+        setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
+        setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);
 }
 
 /*
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index efe73aacf966..7b0d3da52fb4 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 @@ trace:
         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 51402a7e4ca6..0bee04d41bed 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 bbfbca5fea0c..9c337b0e8ba7 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/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 40df33753bae..ec1f756f9dc9 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -105,9 +105,6 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
         /* Don't let flags to be set from userspace */
         act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
 
-        if (user_64bit_mode(current_pt_regs()))
-                return;
-
         if (in_ia32_syscall())
                 act->sa.sa_flags |= SA_IA32_ABI;
         if (in_x32_syscall())
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index dcbd45ad8db6..95d6fc549ad5 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1407,15 +1407,17 @@ __init void prefill_possible_map(void)
 
         /* No boot processor was found in mptable or ACPI MADT */
         if (!num_processors) {
-                int apicid = boot_cpu_physical_apicid;
-                int cpu = hard_smp_processor_id();
+                if (boot_cpu_has(X86_FEATURE_APIC)) {
+                        int apicid = boot_cpu_physical_apicid;
+                        int cpu = hard_smp_processor_id();
 
-                pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu);
+                        pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu);
 
-                /* Make sure boot cpu is enumerated */
-                if (apic->cpu_present_to_apicid(0) == BAD_APICID &&
-                    apic->apic_id_valid(apicid))
-                        generic_processor_info(apicid, boot_cpu_apic_version);
+                        /* Make sure boot cpu is enumerated */
+                        if (apic->cpu_present_to_apicid(0) == BAD_APICID &&
+                            apic->apic_id_valid(apicid))
+                                generic_processor_info(apicid, boot_cpu_apic_version);
+                }
 
                 if (!num_processors)
                         num_processors = 1;
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index 9298993dc8b7..2d721e533cf4 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/ioapic.c b/arch/x86/kvm/ioapic.c
index c7220ba94aa7..1a22de70f7f7 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -594,7 +594,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
         ioapic->irr = 0;
         ioapic->irr_delivered = 0;
         ioapic->id = 0;
-        memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
+        memset(ioapic->irq_eoi, 0x00, sizeof(ioapic->irq_eoi));
         rtc_irq_eoi_tracking_reset(ioapic);
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6c633de84dd7..e375235d81c9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5733,13 +5733,13 @@ static int kvmclock_cpu_online(unsigned int cpu)
 
 static void kvm_timer_init(void)
 {
-        int cpu;
-
         max_tsc_khz = tsc_khz;
 
         if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
 #ifdef CONFIG_CPU_FREQ
                 struct cpufreq_policy policy;
+                int cpu;
+
                 memset(&policy, 0, sizeof(policy));
                 cpu = get_cpu();
                 cpufreq_get_policy(&policy, cpu);
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index ddd2661c4502..887e57182716 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 170cc4ff057b..83e701f160a9 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/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index b4d5e95fe4df..4a6a5a26c582 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -40,7 +40,15 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
                  */
                 return BIOS_STATUS_UNIMPLEMENTED;
 
-        ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5);
+        /*
+         * If EFI_OLD_MEMMAP is set, we need to fall back to using our old EFI
+         * callback method, which uses efi_call() directly, with the kernel page tables:
+         */
+        if (unlikely(test_bit(EFI_OLD_MEMMAP, &efi.flags)))
+                ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5);
+        else
+                ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5);
+
         return ret;
 }
 EXPORT_SYMBOL_GPL(uv_bios_call);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c0fdd57da7aa..bdd855685403 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1837,6 +1837,7 @@ static void __init init_hvm_pv_info(void)
 
         xen_domain_type = XEN_HVM_DOMAIN;
 }
+#endif
 
 static int xen_cpu_up_prepare(unsigned int cpu)
 {
@@ -1887,6 +1888,7 @@ static int xen_cpu_up_online(unsigned int cpu)
         return 0;
 }
 
+#ifdef CONFIG_XEN_PVHVM
 #ifdef CONFIG_KEXEC_CORE
 static void xen_hvm_shutdown(void)
 {
diff --git a/block/badblocks.c b/block/badblocks.c
index 7be53cb1cc3c..6ebcef282314 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -133,6 +133,26 @@ retry:
 }
 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;
@@ -354,7 +376,8 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
                  * current range.  Earlier ranges could also overlap,
                  * but only this one can overlap the end of the range.
                  */
-                if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) {
+                if ((BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) &&
+                    (BB_OFFSET(p[lo]) < target)) {
                         /* Partial overlap, leave the tail of this range */
                         int ack = BB_ACK(p[lo]);
                         sector_t a = BB_OFFSET(p[lo]);
@@ -377,7 +400,8 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
                         lo--;
                 }
                 while (lo >= 0 &&
-                       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
+                       (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) &&
+                       (BB_OFFSET(p[lo]) < target)) {
                         /* This range does overlap */
                         if (BB_OFFSET(p[lo]) < s) {
                                 /* Keep the early parts of this range. */
@@ -399,6 +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 6a14b68b9135..3c882cbc7541 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 ddc2eed64771..f3d27a6dee09 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/Makefile b/drivers/Makefile
index f0afdfb3c7df..194d20bee7dc 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -21,7 +21,7 @@ obj-y				+= video/
 obj-y                           += idle/
 
 # IPMI must come before ACPI in order to provide IPMI opregion support
-obj-$(CONFIG_IPMI_HANDLER)      += char/ipmi/
+obj-y                           += char/ipmi/
 
 obj-$(CONFIG_ACPI)              += acpi/
 obj-$(CONFIG_SFI)               += sfi/
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index f1e6dcc7a827..54d48b90de2c 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 32e9ddc0cf2b..2b3210f42a46 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 028b22a3154e..e36218206bb0 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 3843f1fc5dbb..75ddd160a716 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 334d3c5ba617..d1f20143bb11 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -137,7 +137,9 @@ unlock:
         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 f0a029e68d3e..0d099a24f776 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 c983bf733ad3..bc3d914dfc3e 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 562af94bec35..3c71b982bf2a 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 ba5f11cebee2..9669fc7c19df 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 fdf44cac08e6..d02e7c0f5bfd 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -213,14 +213,16 @@ config DEBUG_DEVRES
           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 811e11c82f32..0809cda93cc0 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 ba405b55329f..19a16b2dbb91 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/rbd.c b/drivers/block/rbd.c
index abb71628ab61..7b274ff4632c 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -415,15 +415,15 @@ struct rbd_device {
 };
 
 /*
- * Flag bits for rbd_dev->flags.  If atomicity is required,
- * rbd_dev->lock is used to protect access.
- *
- * Currently, only the "removing" flag (which is coupled with the
- * "open_count" field) requires atomic access.
+ * Flag bits for rbd_dev->flags:
+ * - REMOVING (which is coupled with rbd_dev->open_count) is protected
+ *   by rbd_dev->lock
+ * - BLACKLISTED is protected by rbd_dev->lock_rwsem
  */
 enum rbd_dev_flags {
         RBD_DEV_FLAG_EXISTS,    /* mapped snapshot has not been deleted */
         RBD_DEV_FLAG_REMOVING,  /* this mapping is being removed */
+        RBD_DEV_FLAG_BLACKLISTED, /* our ceph_client is blacklisted */
 };
 
 static DEFINE_MUTEX(client_mutex);      /* Serialize client creation */
@@ -3926,6 +3926,7 @@ static void rbd_reregister_watch(struct work_struct *work)
         struct rbd_device *rbd_dev = container_of(to_delayed_work(work),
                                             struct rbd_device, watch_dwork);
         bool was_lock_owner = false;
+        bool need_to_wake = false;
         int ret;
 
         dout("%s rbd_dev %p\n", __func__, rbd_dev);
@@ -3935,19 +3936,27 @@ static void rbd_reregister_watch(struct work_struct *work)
                 was_lock_owner = rbd_release_lock(rbd_dev);
 
         mutex_lock(&rbd_dev->watch_mutex);
-        if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR)
-                goto fail_unlock;
+        if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR) {
+                mutex_unlock(&rbd_dev->watch_mutex);
+                goto out;
+        }
 
         ret = __rbd_register_watch(rbd_dev);
         if (ret) {
                 rbd_warn(rbd_dev, "failed to reregister watch: %d", ret);
-                if (ret != -EBLACKLISTED)
+                if (ret == -EBLACKLISTED || ret == -ENOENT) {
+                        set_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags);
+                        need_to_wake = true;
+                } else {
                         queue_delayed_work(rbd_dev->task_wq,
                                            &rbd_dev->watch_dwork,
                                            RBD_RETRY_DELAY);
-                goto fail_unlock;
+                }
+                mutex_unlock(&rbd_dev->watch_mutex);
+                goto out;
         }
 
+        need_to_wake = true;
         rbd_dev->watch_state = RBD_WATCH_STATE_REGISTERED;
         rbd_dev->watch_cookie = rbd_dev->watch_handle->linger_id;
         mutex_unlock(&rbd_dev->watch_mutex);
@@ -3963,13 +3972,10 @@ static void rbd_reregister_watch(struct work_struct *work)
                                  ret);
         }
 
+out:
         up_write(&rbd_dev->lock_rwsem);
-        wake_requests(rbd_dev, true);
-        return;
-
-fail_unlock:
-        mutex_unlock(&rbd_dev->watch_mutex);
-        up_write(&rbd_dev->lock_rwsem);
+        if (need_to_wake)
+                wake_requests(rbd_dev, true);
 }
 
 /*
@@ -4074,7 +4080,9 @@ static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
                 up_read(&rbd_dev->lock_rwsem);
                 schedule();
                 down_read(&rbd_dev->lock_rwsem);
-        } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
+        } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
+                 !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+
         finish_wait(&rbd_dev->lock_waitq, &wait);
 }
 
@@ -4166,8 +4174,16 @@ static void rbd_queue_workfn(struct work_struct *work)
 
         if (must_be_locked) {
                 down_read(&rbd_dev->lock_rwsem);
-                if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED)
+                if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
+                    !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
                         rbd_wait_state_locked(rbd_dev);
+
+                WARN_ON((rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED) ^
+                        !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+                if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+                        result = -EBLACKLISTED;
+                        goto err_unlock;
+                }
         }
 
         img_request = rbd_img_request_create(rbd_dev, offset, length, op_type,
diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c
index ef51c9c864c5..b6bb58c41df5 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 5ccb90ef0146..8f6c23c20c52 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 7010dcac9328..78751057164a 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -111,6 +111,7 @@ config OMAP_OCP2SCP
 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/hw_random/core.c b/drivers/char/hw_random/core.c
index 482794526e8c..d2d2c89de5b4 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -84,14 +84,14 @@ static size_t rng_buffer_size(void)
 
 static void add_early_randomness(struct hwrng *rng)
 {
-        unsigned char bytes[16];
         int bytes_read;
+        size_t size = min_t(size_t, 16, rng_buffer_size());
 
         mutex_lock(&reading_mutex);
-        bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1);
+        bytes_read = rng_get_data(rng, rng_buffer, size, 1);
         mutex_unlock(&reading_mutex);
         if (bytes_read > 0)
-                add_device_randomness(bytes, bytes_read);
+                add_device_randomness(rng_buffer, bytes_read);
 }
 
 static inline void cleanup_rng(struct kref *kref)
diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig
index 5a9350b1069a..7f816655cbbf 100644
--- a/drivers/char/ipmi/Kconfig
+++ b/drivers/char/ipmi/Kconfig
@@ -76,3 +76,11 @@ config IPMI_POWEROFF
          the IPMI management controller is capable of this.
 
 endif # IPMI_HANDLER
+
+config ASPEED_BT_IPMI_BMC
+        depends on ARCH_ASPEED
+        tristate "BT IPMI bmc driver"
+        help
+          Provides a driver for the BT (Block Transfer) IPMI interface
+          found on Aspeed SOCs (AST2400 and AST2500). The driver
+          implements the BMC side of the BT interface.
diff --git a/drivers/char/ipmi/Makefile b/drivers/char/ipmi/Makefile
index f3ffde1f5f1f..0d98cd91def1 100644
--- a/drivers/char/ipmi/Makefile
+++ b/drivers/char/ipmi/Makefile
@@ -11,3 +11,4 @@ obj-$(CONFIG_IPMI_SSIF) += ipmi_ssif.o
 obj-$(CONFIG_IPMI_POWERNV) += ipmi_powernv.o
 obj-$(CONFIG_IPMI_WATCHDOG) += ipmi_watchdog.o
 obj-$(CONFIG_IPMI_POWEROFF) += ipmi_poweroff.o
+obj-$(CONFIG_ASPEED_BT_IPMI_BMC) += bt-bmc.o
diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c
new file mode 100644
index 000000000000..b49e61320952
--- /dev/null
+++ b/drivers/char/ipmi/bt-bmc.c
@@ -0,0 +1,505 @@
+/*
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bt-bmc.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+
+/*
+ * This is a BMC device used to communicate to the host
+ */
+#define DEVICE_NAME     "ipmi-bt-host"
+
+#define BT_IO_BASE      0xe4
+#define BT_IRQ          10
+
+#define BT_CR0          0x0
+#define   BT_CR0_IO_BASE                16
+#define   BT_CR0_IRQ                    12
+#define   BT_CR0_EN_CLR_SLV_RDP         0x8
+#define   BT_CR0_EN_CLR_SLV_WRP         0x4
+#define   BT_CR0_ENABLE_IBT             0x1
+#define BT_CR1          0x4
+#define   BT_CR1_IRQ_H2B        0x01
+#define   BT_CR1_IRQ_HBUSY      0x40
+#define BT_CR2          0x8
+#define   BT_CR2_IRQ_H2B        0x01
+#define   BT_CR2_IRQ_HBUSY      0x40
+#define BT_CR3          0xc
+#define BT_CTRL         0x10
+#define   BT_CTRL_B_BUSY                0x80
+#define   BT_CTRL_H_BUSY                0x40
+#define   BT_CTRL_OEM0                  0x20
+#define   BT_CTRL_SMS_ATN               0x10
+#define   BT_CTRL_B2H_ATN               0x08
+#define   BT_CTRL_H2B_ATN               0x04
+#define   BT_CTRL_CLR_RD_PTR            0x02
+#define   BT_CTRL_CLR_WR_PTR            0x01
+#define BT_BMC2HOST     0x14
+#define BT_INTMASK      0x18
+#define   BT_INTMASK_B2H_IRQEN          0x01
+#define   BT_INTMASK_B2H_IRQ            0x02
+#define   BT_INTMASK_BMC_HWRST          0x80
+
+#define BT_BMC_BUFFER_SIZE 256
+
+struct bt_bmc {
+        struct device           dev;
+        struct miscdevice       miscdev;
+        void __iomem            *base;
+        int                     irq;
+        wait_queue_head_t       queue;
+        struct timer_list       poll_timer;
+        struct mutex            mutex;
+};
+
+static atomic_t open_count = ATOMIC_INIT(0);
+
+static u8 bt_inb(struct bt_bmc *bt_bmc, int reg)
+{
+        return ioread8(bt_bmc->base + reg);
+}
+
+static void bt_outb(struct bt_bmc *bt_bmc, u8 data, int reg)
+{
+        iowrite8(data, bt_bmc->base + reg);
+}
+
+static void clr_rd_ptr(struct bt_bmc *bt_bmc)
+{
+        bt_outb(bt_bmc, BT_CTRL_CLR_RD_PTR, BT_CTRL);
+}
+
+static void clr_wr_ptr(struct bt_bmc *bt_bmc)
+{
+        bt_outb(bt_bmc, BT_CTRL_CLR_WR_PTR, BT_CTRL);
+}
+
+static void clr_h2b_atn(struct bt_bmc *bt_bmc)
+{
+        bt_outb(bt_bmc, BT_CTRL_H2B_ATN, BT_CTRL);
+}
+
+static void set_b_busy(struct bt_bmc *bt_bmc)
+{
+        if (!(bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_B_BUSY))
+                bt_outb(bt_bmc, BT_CTRL_B_BUSY, BT_CTRL);
+}
+
+static void clr_b_busy(struct bt_bmc *bt_bmc)
+{
+        if (bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_B_BUSY)
+                bt_outb(bt_bmc, BT_CTRL_B_BUSY, BT_CTRL);
+}
+
+static void set_b2h_atn(struct bt_bmc *bt_bmc)
+{
+        bt_outb(bt_bmc, BT_CTRL_B2H_ATN, BT_CTRL);
+}
+
+static u8 bt_read(struct bt_bmc *bt_bmc)
+{
+        return bt_inb(bt_bmc, BT_BMC2HOST);
+}
+
+static ssize_t bt_readn(struct bt_bmc *bt_bmc, u8 *buf, size_t n)
+{
+        int i;
+
+        for (i = 0; i < n; i++)
+                buf[i] = bt_read(bt_bmc);
+        return n;
+}
+
+static void bt_write(struct bt_bmc *bt_bmc, u8 c)
+{
+        bt_outb(bt_bmc, c, BT_BMC2HOST);
+}
+
+static ssize_t bt_writen(struct bt_bmc *bt_bmc, u8 *buf, size_t n)
+{
+        int i;
+
+        for (i = 0; i < n; i++)
+                bt_write(bt_bmc, buf[i]);
+        return n;
+}
+
+static void set_sms_atn(struct bt_bmc *bt_bmc)
+{
+        bt_outb(bt_bmc, BT_CTRL_SMS_ATN, BT_CTRL);
+}
+
+static struct bt_bmc *file_bt_bmc(struct file *file)
+{
+        return container_of(file->private_data, struct bt_bmc, miscdev);
+}
+
+static int bt_bmc_open(struct inode *inode, struct file *file)
+{
+        struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+        if (atomic_inc_return(&open_count) == 1) {
+                clr_b_busy(bt_bmc);
+                return 0;
+        }
+
+        atomic_dec(&open_count);
+        return -EBUSY;
+}
+
+/*
+ * The BT (Block Transfer) interface means that entire messages are
+ * buffered by the host before a notification is sent to the BMC that
+ * there is data to be read. The first byte is the length and the
+ * message data follows. The read operation just tries to capture the
+ * whole before returning it to userspace.
+ *
+ * BT Message format :
+ *
+ *    Byte 1  Byte 2     Byte 3  Byte 4  Byte 5:N
+ *    Length  NetFn/LUN  Seq     Cmd     Data
+ *
+ */
+static ssize_t bt_bmc_read(struct file *file, char __user *buf,
+                           size_t count, loff_t *ppos)
+{
+        struct bt_bmc *bt_bmc = file_bt_bmc(file);
+        u8 len;
+        int len_byte = 1;
+        u8 kbuffer[BT_BMC_BUFFER_SIZE];
+        ssize_t ret = 0;
+        ssize_t nread;
+
+        if (!access_ok(VERIFY_WRITE, buf, count))
+                return -EFAULT;
+
+        WARN_ON(*ppos);
+
+        if (wait_event_interruptible(bt_bmc->queue,
+                                     bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_H2B_ATN))
+                return -ERESTARTSYS;
+
+        mutex_lock(&bt_bmc->mutex);
+
+        if (unlikely(!(bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_H2B_ATN))) {
+                ret = -EIO;
+                goto out_unlock;
+        }
+
+        set_b_busy(bt_bmc);
+        clr_h2b_atn(bt_bmc);
+        clr_rd_ptr(bt_bmc);
+
+        /*
+         * The BT frames start with the message length, which does not
+         * include the length byte.
+         */
+        kbuffer[0] = bt_read(bt_bmc);
+        len = kbuffer[0];
+
+        /* We pass the length back to userspace as well */
+        if (len + 1 > count)
+                len = count - 1;
+
+        while (len) {
+                nread = min_t(ssize_t, len, sizeof(kbuffer) - len_byte);
+
+                bt_readn(bt_bmc, kbuffer + len_byte, nread);
+
+                if (copy_to_user(buf, kbuffer, nread + len_byte)) {
+                        ret = -EFAULT;
+                        break;
+                }
+                len -= nread;
+                buf += nread + len_byte;
+                ret += nread + len_byte;
+                len_byte = 0;
+        }
+
+        clr_b_busy(bt_bmc);
+
+out_unlock:
+        mutex_unlock(&bt_bmc->mutex);
+        return ret;
+}
+
+/*
+ * BT Message response format :
+ *
+ *    Byte 1  Byte 2     Byte 3  Byte 4  Byte 5  Byte 6:N
+ *    Length  NetFn/LUN  Seq     Cmd     Code    Data
+ */
+static ssize_t bt_bmc_write(struct file *file, const char __user *buf,
+                            size_t count, loff_t *ppos)
+{
+        struct bt_bmc *bt_bmc = file_bt_bmc(file);
+        u8 kbuffer[BT_BMC_BUFFER_SIZE];
+        ssize_t ret = 0;
+        ssize_t nwritten;
+
+        /*
+         * send a minimum response size
+         */
+        if (count < 5)
+                return -EINVAL;
+
+        if (!access_ok(VERIFY_READ, buf, count))
+                return -EFAULT;
+
+        WARN_ON(*ppos);
+
+        /*
+         * There's no interrupt for clearing bmc busy so we have to
+         * poll
+         */
+        if (wait_event_interruptible(bt_bmc->queue,
+                                     !(bt_inb(bt_bmc, BT_CTRL) &
+                                       (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))))
+                return -ERESTARTSYS;
+
+        mutex_lock(&bt_bmc->mutex);
+
+        if (unlikely(bt_inb(bt_bmc, BT_CTRL) &
+                     (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))) {
+                ret = -EIO;
+                goto out_unlock;
+        }
+
+        clr_wr_ptr(bt_bmc);
+
+        while (count) {
+                nwritten = min_t(ssize_t, count, sizeof(kbuffer));
+                if (copy_from_user(&kbuffer, buf, nwritten)) {
+                        ret = -EFAULT;
+                        break;
+                }
+
+                bt_writen(bt_bmc, kbuffer, nwritten);
+
+                count -= nwritten;
+                buf += nwritten;
+                ret += nwritten;
+        }
+
+        set_b2h_atn(bt_bmc);
+
+out_unlock:
+        mutex_unlock(&bt_bmc->mutex);
+        return ret;
+}
+
+static long bt_bmc_ioctl(struct file *file, unsigned int cmd,
+                         unsigned long param)
+{
+        struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+        switch (cmd) {
+        case BT_BMC_IOCTL_SMS_ATN:
+                set_sms_atn(bt_bmc);
+                return 0;
+        }
+        return -EINVAL;
+}
+
+static int bt_bmc_release(struct inode *inode, struct file *file)
+{
+        struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+        atomic_dec(&open_count);
+        set_b_busy(bt_bmc);
+        return 0;
+}
+
+static unsigned int bt_bmc_poll(struct file *file, poll_table *wait)
+{
+        struct bt_bmc *bt_bmc = file_bt_bmc(file);
+        unsigned int mask = 0;
+        u8 ctrl;
+
+        poll_wait(file, &bt_bmc->queue, wait);
+
+        ctrl = bt_inb(bt_bmc, BT_CTRL);
+
+        if (ctrl & BT_CTRL_H2B_ATN)
+                mask |= POLLIN;
+
+        if (!(ctrl & (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN)))
+                mask |= POLLOUT;
+
+        return mask;
+}
+
+static const struct file_operations bt_bmc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = bt_bmc_open,
+        .read           = bt_bmc_read,
+        .write          = bt_bmc_write,
+        .release        = bt_bmc_release,
+        .poll           = bt_bmc_poll,
+        .unlocked_ioctl = bt_bmc_ioctl,
+};
+
+static void poll_timer(unsigned long data)
+{
+        struct bt_bmc *bt_bmc = (void *)data;
+
+        bt_bmc->poll_timer.expires += msecs_to_jiffies(500);
+        wake_up(&bt_bmc->queue);
+        add_timer(&bt_bmc->poll_timer);
+}
+
+static irqreturn_t bt_bmc_irq(int irq, void *arg)
+{
+        struct bt_bmc *bt_bmc = arg;
+        u32 reg;
+
+        reg = ioread32(bt_bmc->base + BT_CR2);
+        reg &= BT_CR2_IRQ_H2B | BT_CR2_IRQ_HBUSY;
+        if (!reg)
+                return IRQ_NONE;
+
+        /* ack pending IRQs */
+        iowrite32(reg, bt_bmc->base + BT_CR2);
+
+        wake_up(&bt_bmc->queue);
+        return IRQ_HANDLED;
+}
+
+static int bt_bmc_config_irq(struct bt_bmc *bt_bmc,
+                             struct platform_device *pdev)
+{
+        struct device *dev = &pdev->dev;
+        u32 reg;
+        int rc;
+
+        bt_bmc->irq = platform_get_irq(pdev, 0);
+        if (!bt_bmc->irq)
+                return -ENODEV;
+
+        rc = devm_request_irq(dev, bt_bmc->irq, bt_bmc_irq, IRQF_SHARED,
+                              DEVICE_NAME, bt_bmc);
+        if (rc < 0) {
+                dev_warn(dev, "Unable to request IRQ %d\n", bt_bmc->irq);
+                bt_bmc->irq = 0;
+                return rc;
+        }
+
+        /*
+         * Configure IRQs on the bmc clearing the H2B and HBUSY bits;
+         * H2B will be asserted when the bmc has data for us; HBUSY
+         * will be cleared (along with B2H) when we can write the next
+         * message to the BT buffer
+         */
+        reg = ioread32(bt_bmc->base + BT_CR1);
+        reg |= BT_CR1_IRQ_H2B | BT_CR1_IRQ_HBUSY;
+        iowrite32(reg, bt_bmc->base + BT_CR1);
+
+        return 0;
+}
+
+static int bt_bmc_probe(struct platform_device *pdev)
+{
+        struct bt_bmc *bt_bmc;
+        struct device *dev;
+        struct resource *res;
+        int rc;
+
+        if (!pdev || !pdev->dev.of_node)
+                return -ENODEV;
+
+        dev = &pdev->dev;
+        dev_info(dev, "Found bt bmc device\n");
+
+        bt_bmc = devm_kzalloc(dev, sizeof(*bt_bmc), GFP_KERNEL);
+        if (!bt_bmc)
+                return -ENOMEM;
+
+        dev_set_drvdata(&pdev->dev, bt_bmc);
+
+        res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+        bt_bmc->base = devm_ioremap_resource(&pdev->dev, res);
+        if (IS_ERR(bt_bmc->base))
+                return PTR_ERR(bt_bmc->base);
+
+        mutex_init(&bt_bmc->mutex);
+        init_waitqueue_head(&bt_bmc->queue);
+
+        bt_bmc->miscdev.minor   = MISC_DYNAMIC_MINOR,
+                bt_bmc->miscdev.name    = DEVICE_NAME,
+                bt_bmc->miscdev.fops    = &bt_bmc_fops,
+                bt_bmc->miscdev.parent = dev;
+        rc = misc_register(&bt_bmc->miscdev);
+        if (rc) {
+                dev_err(dev, "Unable to register misc device\n");
+                return rc;
+        }
+
+        bt_bmc_config_irq(bt_bmc, pdev);
+
+        if (bt_bmc->irq) {
+                dev_info(dev, "Using IRQ %d\n", bt_bmc->irq);
+        } else {
+                dev_info(dev, "No IRQ; using timer\n");
+                setup_timer(&bt_bmc->poll_timer, poll_timer,
+                            (unsigned long)bt_bmc);
+                bt_bmc->poll_timer.expires = jiffies + msecs_to_jiffies(10);
+                add_timer(&bt_bmc->poll_timer);
+        }
+
+        iowrite32((BT_IO_BASE << BT_CR0_IO_BASE) |
+                  (BT_IRQ << BT_CR0_IRQ) |
+                  BT_CR0_EN_CLR_SLV_RDP |
+                  BT_CR0_EN_CLR_SLV_WRP |
+                  BT_CR0_ENABLE_IBT,
+                  bt_bmc->base + BT_CR0);
+
+        clr_b_busy(bt_bmc);
+
+        return 0;
+}
+
+static int bt_bmc_remove(struct platform_device *pdev)
+{
+        struct bt_bmc *bt_bmc = dev_get_drvdata(&pdev->dev);
+
+        misc_deregister(&bt_bmc->miscdev);
+        if (!bt_bmc->irq)
+                del_timer_sync(&bt_bmc->poll_timer);
+        return 0;
+}
+
+static const struct of_device_id bt_bmc_match[] = {
+        { .compatible = "aspeed,ast2400-bt-bmc" },
+        { },
+};
+
+static struct platform_driver bt_bmc_driver = {
+        .driver = {
+                .name           = DEVICE_NAME,
+                .of_match_table = bt_bmc_match,
+        },
+        .probe = bt_bmc_probe,
+        .remove = bt_bmc_remove,
+};
+
+module_platform_driver(bt_bmc_driver);
+
+MODULE_DEVICE_TABLE(of, bt_bmc_match);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Alistair Popple <alistair@popple.id.au>");
+MODULE_DESCRIPTION("Linux device interface to the BT interface");
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index d8619998cfb5..fcdd886819f5 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -2891,11 +2891,11 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
                 intf->curr_channel = IPMI_MAX_CHANNELS;
         }
 
+        rv = ipmi_bmc_register(intf, i);
+
         if (rv == 0)
                 rv = add_proc_entries(intf, i);
 
-        rv = ipmi_bmc_register(intf, i);
-
  out:
         if (rv) {
                 if (intf->proc_dir)
@@ -2982,8 +2982,6 @@ int ipmi_unregister_smi(ipmi_smi_t intf)
         int intf_num = intf->intf_num;
         ipmi_user_t user;
 
-        ipmi_bmc_unregister(intf);
-
         mutex_lock(&smi_watchers_mutex);
         mutex_lock(&ipmi_interfaces_mutex);
         intf->intf_num = -1;
@@ -3007,6 +3005,7 @@ int ipmi_unregister_smi(ipmi_smi_t intf)
         mutex_unlock(&ipmi_interfaces_mutex);
 
         remove_proc_entries(intf);
+        ipmi_bmc_unregister(intf);
 
         /*
          * Call all the watcher interfaces to tell them that
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 8de61876f633..3a9149cf0110 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/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 190122e64a3a..85a449cf61e3 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -203,7 +203,7 @@ at91_clk_register_programmable(struct regmap *regmap,
         ret = clk_hw_register(NULL, &prog->hw);
         if (ret) {
                 kfree(prog);
-                hw = &prog->hw;
+                hw = ERR_PTR(ret);
         }
 
         return hw;
diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c
index b68bf573dcfb..8c7763fd9efc 100644
--- a/drivers/clk/bcm/clk-bcm2835.c
+++ b/drivers/clk/bcm/clk-bcm2835.c
@@ -502,8 +502,12 @@ static long bcm2835_pll_rate_from_divisors(unsigned long parent_rate,
 static long bcm2835_pll_round_rate(struct clk_hw *hw, unsigned long rate,
                                    unsigned long *parent_rate)
 {
+        struct bcm2835_pll *pll = container_of(hw, struct bcm2835_pll, hw);
+        const struct bcm2835_pll_data *data = pll->data;
         u32 ndiv, fdiv;
 
+        rate = clamp(rate, data->min_rate, data->max_rate);
+
         bcm2835_pll_choose_ndiv_and_fdiv(rate, *parent_rate, &ndiv, &fdiv);
 
         return bcm2835_pll_rate_from_divisors(*parent_rate, ndiv, fdiv, 1);
@@ -608,13 +612,6 @@ static int bcm2835_pll_set_rate(struct clk_hw *hw,
         u32 ana[4];
         int i;
 
-        if (rate < data->min_rate || rate > data->max_rate) {
-                dev_err(cprman->dev, "%s: rate out of spec: %lu vs (%lu, %lu)\n",
-                        clk_hw_get_name(hw), rate,
-                        data->min_rate, data->max_rate);
-                return -EINVAL;
-        }
-
         if (rate > data->max_fb_rate) {
                 use_fb_prediv = true;
                 rate /= 2;
diff --git a/drivers/clk/clk-max77686.c b/drivers/clk/clk-max77686.c
index b637f5979023..eb953d3b0b69 100644
--- a/drivers/clk/clk-max77686.c
+++ b/drivers/clk/clk-max77686.c
@@ -216,6 +216,7 @@ static int max77686_clk_probe(struct platform_device *pdev)
                 return -EINVAL;
         }
 
+        drv_data->num_clks = num_clks;
         drv_data->max_clk_data = devm_kcalloc(dev, num_clks,
                                               sizeof(*drv_data->max_clk_data),
                                               GFP_KERNEL);
diff --git a/drivers/clk/hisilicon/clk-hi6220.c b/drivers/clk/hisilicon/clk-hi6220.c
index fe364e63f8de..c0e8e1f196aa 100644
--- a/drivers/clk/hisilicon/clk-hi6220.c
+++ b/drivers/clk/hisilicon/clk-hi6220.c
@@ -195,7 +195,7 @@ static void __init hi6220_clk_sys_init(struct device_node *np)
         hi6220_clk_register_divider(hi6220_div_clks_sys,
                         ARRAY_SIZE(hi6220_div_clks_sys), clk_data);
 }
-CLK_OF_DECLARE(hi6220_clk_sys, "hisilicon,hi6220-sysctrl", hi6220_clk_sys_init);
+CLK_OF_DECLARE_DRIVER(hi6220_clk_sys, "hisilicon,hi6220-sysctrl", hi6220_clk_sys_init);
 
 
 /* clocks in media controller */
@@ -252,7 +252,7 @@ static void __init hi6220_clk_media_init(struct device_node *np)
         hi6220_clk_register_divider(hi6220_div_clks_media,
                                 ARRAY_SIZE(hi6220_div_clks_media), clk_data);
 }
-CLK_OF_DECLARE(hi6220_clk_media, "hisilicon,hi6220-mediactrl", hi6220_clk_media_init);
+CLK_OF_DECLARE_DRIVER(hi6220_clk_media, "hisilicon,hi6220-mediactrl", hi6220_clk_media_init);
 
 
 /* clocks in pmctrl */
diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig
index 380c372d528e..f042bd2a6a99 100644
--- a/drivers/clk/mediatek/Kconfig
+++ b/drivers/clk/mediatek/Kconfig
@@ -8,6 +8,7 @@ config COMMON_CLK_MEDIATEK
 
 config COMMON_CLK_MT8135
         bool "Clock driver for Mediatek MT8135"
+        depends on ARCH_MEDIATEK || COMPILE_TEST
         select COMMON_CLK_MEDIATEK
         default ARCH_MEDIATEK
         ---help---
@@ -15,6 +16,7 @@ config COMMON_CLK_MT8135
 
 config COMMON_CLK_MT8173
         bool "Clock driver for Mediatek MT8173"
+        depends on ARCH_MEDIATEK || COMPILE_TEST
         select COMMON_CLK_MEDIATEK
         default ARCH_MEDIATEK
         ---help---
diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index 45905fc0d75b..cecb0fdfaef6 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -305,7 +305,7 @@ static const struct of_device_id armada_3700_periph_clock_of_match[] = {
 };
 static int armada_3700_add_composite_clk(const struct clk_periph_data *data,
                                          void __iomem *reg, spinlock_t *lock,
-                                         struct device *dev, struct clk_hw *hw)
+                                         struct device *dev, struct clk_hw **hw)
 {
         const struct clk_ops *mux_ops = NULL, *gate_ops = NULL,
                 *rate_ops = NULL;
@@ -329,6 +329,7 @@ static int armada_3700_add_composite_clk(const struct clk_periph_data *data,
                 gate->lock = lock;
                 gate_ops = gate_hw->init->ops;
                 gate->reg = reg + (u64)gate->reg;
+                gate->flags = CLK_GATE_SET_TO_DISABLE;
         }
 
         if (data->rate_hw) {
@@ -353,13 +354,13 @@ static int armada_3700_add_composite_clk(const struct clk_periph_data *data,
                 }
         }
 
-        hw = clk_hw_register_composite(dev, data->name, data->parent_names,
+        *hw = clk_hw_register_composite(dev, data->name, data->parent_names,
                                        data->num_parents, mux_hw,
                                        mux_ops, rate_hw, rate_ops,
                                        gate_hw, gate_ops, CLK_IGNORE_UNUSED);
 
-        if (IS_ERR(hw))
-                return PTR_ERR(hw);
+        if (IS_ERR(*hw))
+                return PTR_ERR(*hw);
 
         return 0;
 }
@@ -400,7 +401,7 @@ static int armada_3700_periph_clock_probe(struct platform_device *pdev)
         spin_lock_init(&driver_data->lock);
 
         for (i = 0; i < num_periph; i++) {
-                struct clk_hw *hw = driver_data->hw_data->hws[i];
+                struct clk_hw **hw = &driver_data->hw_data->hws[i];
 
                 if (armada_3700_add_composite_clk(&data[i], reg,
                                                   &driver_data->lock, dev, hw))
diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c
index 51d152f735cc..17e68a724945 100644
--- a/drivers/clk/samsung/clk-exynos-audss.c
+++ b/drivers/clk/samsung/clk-exynos-audss.c
@@ -106,6 +106,7 @@ static const struct of_device_id exynos_audss_clk_of_match[] = {
         },
         { },
 };
+MODULE_DEVICE_TABLE(of, exynos_audss_clk_of_match);
 
 static void exynos_audss_clk_teardown(void)
 {
diff --git a/drivers/clk/uniphier/clk-uniphier-core.c b/drivers/clk/uniphier/clk-uniphier-core.c
index 5ffb898d0839..26c53f7963a4 100644
--- a/drivers/clk/uniphier/clk-uniphier-core.c
+++ b/drivers/clk/uniphier/clk-uniphier-core.c
@@ -79,7 +79,7 @@ static int uniphier_clk_probe(struct platform_device *pdev)
         hw_data->num = clk_num;
 
         /* avoid returning NULL for unused idx */
-        for (; clk_num >= 0; clk_num--)
+        while (--clk_num >= 0)
                 hw_data->hws[clk_num] = ERR_PTR(-EINVAL);
 
         for (p = data; p->name; p++) {
@@ -111,6 +111,10 @@ static int uniphier_clk_remove(struct platform_device *pdev)
 static const struct of_device_id uniphier_clk_match[] = {
         /* System clock */
         {
+                .compatible = "socionext,uniphier-sld3-clock",
+                .data = uniphier_sld3_sys_clk_data,
+        },
+        {
                 .compatible = "socionext,uniphier-ld4-clock",
                 .data = uniphier_ld4_sys_clk_data,
         },
@@ -138,7 +142,7 @@ static const struct of_device_id uniphier_clk_match[] = {
                 .compatible = "socionext,uniphier-ld20-clock",
                 .data = uniphier_ld20_sys_clk_data,
         },
-        /* Media I/O clock */
+        /* Media I/O clock, SD clock */
         {
                 .compatible = "socionext,uniphier-sld3-mio-clock",
                 .data = uniphier_sld3_mio_clk_data,
@@ -156,20 +160,20 @@ static const struct of_device_id uniphier_clk_match[] = {
                 .data = uniphier_sld3_mio_clk_data,
         },
         {
-                .compatible = "socionext,uniphier-pro5-mio-clock",
-                .data = uniphier_pro5_mio_clk_data,
+                .compatible = "socionext,uniphier-pro5-sd-clock",
+                .data = uniphier_pro5_sd_clk_data,
         },
         {
-                .compatible = "socionext,uniphier-pxs2-mio-clock",
-                .data = uniphier_pro5_mio_clk_data,
+                .compatible = "socionext,uniphier-pxs2-sd-clock",
+                .data = uniphier_pro5_sd_clk_data,
         },
         {
                 .compatible = "socionext,uniphier-ld11-mio-clock",
                 .data = uniphier_sld3_mio_clk_data,
         },
         {
-                .compatible = "socionext,uniphier-ld20-mio-clock",
-                .data = uniphier_pro5_mio_clk_data,
+                .compatible = "socionext,uniphier-ld20-sd-clock",
+                .data = uniphier_pro5_sd_clk_data,
         },
         /* Peripheral clock */
         {
diff --git a/drivers/clk/uniphier/clk-uniphier-mio.c b/drivers/clk/uniphier/clk-uniphier-mio.c
index 6aa7ec768d0b..218d20f099ce 100644
--- a/drivers/clk/uniphier/clk-uniphier-mio.c
+++ b/drivers/clk/uniphier/clk-uniphier-mio.c
@@ -93,7 +93,7 @@ const struct uniphier_clk_data uniphier_sld3_mio_clk_data[] = {
         { /* sentinel */ }
 };
 
-const struct uniphier_clk_data uniphier_pro5_mio_clk_data[] = {
+const struct uniphier_clk_data uniphier_pro5_sd_clk_data[] = {
         UNIPHIER_MIO_CLK_SD_FIXED,
         UNIPHIER_MIO_CLK_SD(0, 0),
         UNIPHIER_MIO_CLK_SD(1, 1),
diff --git a/drivers/clk/uniphier/clk-uniphier-mux.c b/drivers/clk/uniphier/clk-uniphier-mux.c
index 15a2f2cbe0d9..2c243a894f3b 100644
--- a/drivers/clk/uniphier/clk-uniphier-mux.c
+++ b/drivers/clk/uniphier/clk-uniphier-mux.c
@@ -42,7 +42,7 @@ static u8 uniphier_clk_mux_get_parent(struct clk_hw *hw)
         struct uniphier_clk_mux *mux = to_uniphier_clk_mux(hw);
         int num_parents = clk_hw_get_num_parents(hw);
         int ret;
-        u32 val;
+        unsigned int val;
         u8 i;
 
         ret = regmap_read(mux->regmap, mux->reg, &val);
diff --git a/drivers/clk/uniphier/clk-uniphier.h b/drivers/clk/uniphier/clk-uniphier.h
index 3ae184062388..0244dba1f4cf 100644
--- a/drivers/clk/uniphier/clk-uniphier.h
+++ b/drivers/clk/uniphier/clk-uniphier.h
@@ -115,7 +115,7 @@ extern const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[];
 extern const struct uniphier_clk_data uniphier_ld11_sys_clk_data[];
 extern const struct uniphier_clk_data uniphier_ld20_sys_clk_data[];
 extern const struct uniphier_clk_data uniphier_sld3_mio_clk_data[];
-extern const struct uniphier_clk_data uniphier_pro5_mio_clk_data[];
+extern const struct uniphier_clk_data uniphier_pro5_sd_clk_data[];
 extern const struct uniphier_clk_data uniphier_ld4_peri_clk_data[];
 extern const struct uniphier_clk_data uniphier_pro4_peri_clk_data[];
 
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 245190839359..e2c6e43cf8ca 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -417,6 +417,16 @@ config SYS_SUPPORTS_SH_TMU
 config SYS_SUPPORTS_EM_STI
         bool
 
+config CLKSRC_JCORE_PIT
+        bool "J-Core PIT timer driver" if COMPILE_TEST
+        depends on OF
+        depends on GENERIC_CLOCKEVENTS
+        depends on HAS_IOMEM
+        select CLKSRC_MMIO
+        help
+          This enables build of clocksource and clockevent driver for
+          the integrated PIT in the J-Core synthesizable, open source SoC.
+
 config SH_TIMER_CMT
         bool "Renesas CMT timer driver" if COMPILE_TEST
         depends on GENERIC_CLOCKEVENTS
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index fd9d6df0bbc0..cf87f407f1ad 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_ATMEL_TCB_CLKSRC)	+= tcb_clksrc.o
 obj-$(CONFIG_X86_PM_TIMER)      += acpi_pm.o
 obj-$(CONFIG_SCx200HR_TIMER)    += scx200_hrt.o
 obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC)    += cs5535-clockevt.o
+obj-$(CONFIG_CLKSRC_JCORE_PIT)          += jcore-pit.o
 obj-$(CONFIG_SH_TIMER_CMT)      += sh_cmt.o
 obj-$(CONFIG_SH_TIMER_MTU2)     += sh_mtu2.o
 obj-$(CONFIG_SH_TIMER_TMU)      += sh_tmu.o
diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
new file mode 100644
index 000000000000..54e1665aa03c
--- /dev/null
+++ b/drivers/clocksource/jcore-pit.c
@@ -0,0 +1,249 @@
+/*
+ * J-Core SoC PIT/clocksource driver
+ *
+ * Copyright (C) 2015-2016 Smart Energy Instruments, Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/sched_clock.h>
+#include <linux/cpu.h>
+#include <linux/cpuhotplug.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define PIT_IRQ_SHIFT           12
+#define PIT_PRIO_SHIFT          20
+#define PIT_ENABLE_SHIFT        26
+#define PIT_PRIO_MASK           0xf
+
+#define REG_PITEN               0x00
+#define REG_THROT               0x10
+#define REG_COUNT               0x14
+#define REG_BUSPD               0x18
+#define REG_SECHI               0x20
+#define REG_SECLO               0x24
+#define REG_NSEC                0x28
+
+struct jcore_pit {
+        struct clock_event_device       ced;
+        void __iomem                    *base;
+        unsigned long                   periodic_delta;
+        u32                             enable_val;
+};
+
+static void __iomem *jcore_pit_base;
+static struct jcore_pit __percpu *jcore_pit_percpu;
+
+static notrace u64 jcore_sched_clock_read(void)
+{
+        u32 seclo, nsec, seclo0;
+        __iomem void *base = jcore_pit_base;
+
+        seclo = readl(base + REG_SECLO);
+        do {
+                seclo0 = seclo;
+                nsec  = readl(base + REG_NSEC);
+                seclo = readl(base + REG_SECLO);
+        } while (seclo0 != seclo);
+
+        return seclo * NSEC_PER_SEC + nsec;
+}
+
+static cycle_t jcore_clocksource_read(struct clocksource *cs)
+{
+        return jcore_sched_clock_read();
+}
+
+static int jcore_pit_disable(struct jcore_pit *pit)
+{
+        writel(0, pit->base + REG_PITEN);
+        return 0;
+}
+
+static int jcore_pit_set(unsigned long delta, struct jcore_pit *pit)
+{
+        jcore_pit_disable(pit);
+        writel(delta, pit->base + REG_THROT);
+        writel(pit->enable_val, pit->base + REG_PITEN);
+        return 0;
+}
+
+static int jcore_pit_set_state_shutdown(struct clock_event_device *ced)
+{
+        struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+        return jcore_pit_disable(pit);
+}
+
+static int jcore_pit_set_state_oneshot(struct clock_event_device *ced)
+{
+        struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+        return jcore_pit_disable(pit);
+}
+
+static int jcore_pit_set_state_periodic(struct clock_event_device *ced)
+{
+        struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+        return jcore_pit_set(pit->periodic_delta, pit);
+}
+
+static int jcore_pit_set_next_event(unsigned long delta,
+                                    struct clock_event_device *ced)
+{
+        struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+        return jcore_pit_set(delta, pit);
+}
+
+static int jcore_pit_local_init(unsigned cpu)
+{
+        struct jcore_pit *pit = this_cpu_ptr(jcore_pit_percpu);
+        unsigned buspd, freq;
+
+        pr_info("Local J-Core PIT init on cpu %u\n", cpu);
+
+        buspd = readl(pit->base + REG_BUSPD);
+        freq = DIV_ROUND_CLOSEST(NSEC_PER_SEC, buspd);
+        pit->periodic_delta = DIV_ROUND_CLOSEST(NSEC_PER_SEC, HZ * buspd);
+
+        clockevents_config_and_register(&pit->ced, freq, 1, ULONG_MAX);
+
+        return 0;
+}
+
+static irqreturn_t jcore_timer_interrupt(int irq, void *dev_id)
+{
+        struct jcore_pit *pit = this_cpu_ptr(dev_id);
+
+        if (clockevent_state_oneshot(&pit->ced))
+                jcore_pit_disable(pit);
+
+        pit->ced.event_handler(&pit->ced);
+
+        return IRQ_HANDLED;
+}
+
+static int __init jcore_pit_init(struct device_node *node)
+{
+        int err;
+        unsigned pit_irq, cpu;
+        unsigned long hwirq;
+        u32 irqprio, enable_val;
+
+        jcore_pit_base = of_iomap(node, 0);
+        if (!jcore_pit_base) {
+                pr_err("Error: Cannot map base address for J-Core PIT\n");
+                return -ENXIO;
+        }
+
+        pit_irq = irq_of_parse_and_map(node, 0);
+        if (!pit_irq) {
+                pr_err("Error: J-Core PIT has no IRQ\n");
+                return -ENXIO;
+        }
+
+        pr_info("Initializing J-Core PIT at %p IRQ %d\n",
+                jcore_pit_base, pit_irq);
+
+        err = clocksource_mmio_init(jcore_pit_base, "jcore_pit_cs",
+                                    NSEC_PER_SEC, 400, 32,
+                                    jcore_clocksource_read);
+        if (err) {
+                pr_err("Error registering clocksource device: %d\n", err);
+                return err;
+        }
+
+        sched_clock_register(jcore_sched_clock_read, 32, NSEC_PER_SEC);
+
+        jcore_pit_percpu = alloc_percpu(struct jcore_pit);
+        if (!jcore_pit_percpu) {
+                pr_err("Failed to allocate memory for clock event device\n");
+                return -ENOMEM;
+        }
+
+        err = request_irq(pit_irq, jcore_timer_interrupt,
+                          IRQF_TIMER | IRQF_PERCPU,
+                          "jcore_pit", jcore_pit_percpu);
+        if (err) {
+                pr_err("pit irq request failed: %d\n", err);
+                free_percpu(jcore_pit_percpu);
+                return err;
+        }
+
+        /*
+         * The J-Core PIT is not hard-wired to a particular IRQ, but
+         * integrated with the interrupt controller such that the IRQ it
+         * generates is programmable, as follows:
+         *
+         * The bit layout of the PIT enable register is:
+         *
+         *      .....e..ppppiiiiiiii............
+         *
+         * where the .'s indicate unrelated/unused bits, e is enable,
+         * p is priority, and i is hard irq number.
+         *
+         * For the PIT included in AIC1 (obsolete but still in use),
+         * any hard irq (trap number) can be programmed via the 8
+         * iiiiiiii bits, and a priority (0-15) is programmable
+         * separately in the pppp bits.
+         *
+         * For the PIT included in AIC2 (current), the programming
+         * interface is equivalent modulo interrupt mapping. This is
+         * why a different compatible tag was not used. However only
+         * traps 64-127 (the ones actually intended to be used for
+         * interrupts, rather than syscalls/exceptions/etc.) can be
+         * programmed (the high 2 bits of i are ignored) and the
+         * priority pppp is <<2'd and or'd onto the irq number. This
+         * choice seems to have been made on the hardware engineering
+         * side under an assumption that preserving old AIC1 priority
+         * mappings was important. Future models will likely ignore
+         * the pppp field.
+         */
+        hwirq = irq_get_irq_data(pit_irq)->hwirq;
+        irqprio = (hwirq >> 2) & PIT_PRIO_MASK;
+        enable_val = (1U << PIT_ENABLE_SHIFT)
+                   | (hwirq << PIT_IRQ_SHIFT)
+                   | (irqprio << PIT_PRIO_SHIFT);
+
+        for_each_present_cpu(cpu) {
+                struct jcore_pit *pit = per_cpu_ptr(jcore_pit_percpu, cpu);
+
+                pit->base = of_iomap(node, cpu);
+                if (!pit->base) {
+                        pr_err("Unable to map PIT for cpu %u\n", cpu);
+                        continue;
+                }
+
+                pit->ced.name = "jcore_pit";
+                pit->ced.features = CLOCK_EVT_FEAT_PERIODIC
+                                  | CLOCK_EVT_FEAT_ONESHOT
+                                  | CLOCK_EVT_FEAT_PERCPU;
+                pit->ced.cpumask = cpumask_of(cpu);
+                pit->ced.rating = 400;
+                pit->ced.irq = pit_irq;
+                pit->ced.set_state_shutdown = jcore_pit_set_state_shutdown;
+                pit->ced.set_state_periodic = jcore_pit_set_state_periodic;
+                pit->ced.set_state_oneshot = jcore_pit_set_state_oneshot;
+                pit->ced.set_next_event = jcore_pit_set_next_event;
+
+                pit->enable_val = enable_val;
+        }
+
+        cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
+                          "AP_JCORE_TIMER_STARTING",
+                          jcore_pit_local_init, NULL);
+
+        return 0;
+}
+
+CLOCKSOURCE_OF_DECLARE(jcore_pit, "jcore,pit", jcore_pit_init);
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index c184eb84101e..4f87f3e76d83 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -152,6 +152,13 @@ static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id)
         return IRQ_HANDLED;
 }
 
+static cycle_t sun5i_clksrc_read(struct clocksource *clksrc)
+{
+        struct sun5i_timer_clksrc *cs = to_sun5i_timer_clksrc(clksrc);
+
+        return ~readl(cs->timer.base + TIMER_CNTVAL_LO_REG(1));
+}
+
 static int sun5i_rate_cb_clksrc(struct notifier_block *nb,
                                 unsigned long event, void *data)
 {
@@ -210,8 +217,13 @@ static int __init sun5i_setup_clocksource(struct device_node *node,
         writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
                base + TIMER_CTL_REG(1));
 
-        ret = clocksource_mmio_init(base + TIMER_CNTVAL_LO_REG(1), node->name,
-                                    rate, 340, 32, clocksource_mmio_readl_down);
+        cs->clksrc.name = node->name;
+        cs->clksrc.rating = 340;
+        cs->clksrc.read = sun5i_clksrc_read;
+        cs->clksrc.mask = CLOCKSOURCE_MASK(32);
+        cs->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+
+        ret = clocksource_register_hz(&cs->clksrc, rate);
         if (ret) {
                 pr_err("Couldn't register clock source.\n");
                 goto err_remove_notifier;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f535f8123258..4737520ec823 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 daadd20aa936..3e2ab3b14eea 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -14,7 +14,7 @@ if DEV_DAX
 
 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 9630d8837ba9..4a15fa5df98b 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 ca957a5f4291..b8cde096a808 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/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index c06945160a41..5e23e2d305e7 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -11,7 +11,7 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \
                                    -mno-mmx -mno-sse
 
 cflags-$(CONFIG_ARM64)          := $(subst -pg,,$(KBUILD_CFLAGS))
-cflags-$(CONFIG_ARM)            := $(subst -pg,,$(KBUILD_CFLAGS)) \
+cflags-$(CONFIG_ARM)            := $(subst -pg,,$(KBUILD_CFLAGS)) -g0 \
                                    -fno-builtin -fpic -mno-single-pic-base
 
 cflags-$(CONFIG_EFI_ARMSTUB)    += -I$(srctree)/scripts/dtc/libfdt
@@ -79,5 +79,6 @@ quiet_cmd_stubcopy = STUBCPY $@
 # decompressor. So move our .data to .data.efistub, which is preserved
 # explicitly by the decompressor linker script.
 #
-STUBCOPY_FLAGS-$(CONFIG_ARM)    += --rename-section .data=.data.efistub
+STUBCOPY_FLAGS-$(CONFIG_ARM)    += --rename-section .data=.data.efistub \
+                                   -R ___ksymtab+sort -R ___kcrctab+sort
 STUBCOPY_RELOC-$(CONFIG_ARM)    := R_ARM_ABS
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 26ee00f6bd58..d011cb89d25e 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -284,7 +284,7 @@ config GPIO_MM_LANTIQ
 
 config GPIO_MOCKUP
         tristate "GPIO Testing Driver"
-        depends on GPIOLIB
+        depends on GPIOLIB && SYSFS
         select GPIO_SYSFS
         help
           This enables GPIO Testing driver, which provides a way to test GPIO
diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c
index 9457e2022bf6..dc37dbe4b46d 100644
--- a/drivers/gpio/gpio-ath79.c
+++ b/drivers/gpio/gpio-ath79.c
@@ -219,6 +219,7 @@ static const struct of_device_id ath79_gpio_of_match[] = {
         { .compatible = "qca,ar9340-gpio" },
         {},
 };
+MODULE_DEVICE_TABLE(of, ath79_gpio_of_match);
 
 static int ath79_gpio_probe(struct platform_device *pdev)
 {
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 425501c39527..793518a30afe 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -239,7 +239,7 @@ static int mpc8xxx_gpio_irq_map(struct irq_domain *h, unsigned int irq,
                                 irq_hw_number_t hwirq)
 {
         irq_set_chip_data(irq, h->host_data);
-        irq_set_chip_and_handler(irq, &mpc8xxx_irq_chip, handle_level_irq);
+        irq_set_chip_and_handler(irq, &mpc8xxx_irq_chip, handle_edge_irq);
 
         return 0;
 }
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index b9daa0bf32a4..ee1724806f46 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -308,8 +308,10 @@ static int mxs_gpio_probe(struct platform_device *pdev)
         writel(~0U, port->base + PINCTRL_IRQSTAT(port) + MXS_CLR);
 
         irq_base = irq_alloc_descs(-1, 0, 32, numa_node_id());
-        if (irq_base < 0)
-                return irq_base;
+        if (irq_base < 0) {
+                err = irq_base;
+                goto out_iounmap;
+        }
 
         port->domain = irq_domain_add_legacy(np, 32, irq_base, 0,
                                              &irq_domain_simple_ops, NULL);
@@ -349,6 +351,8 @@ out_irqdomain_remove:
         irq_domain_remove(port->domain);
 out_irqdesc_free:
         irq_free_descs(irq_base, 32);
+out_iounmap:
+        iounmap(port->base);
         return err;
 }
 
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index e7d422a6b90b..5b0042776ec7 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -409,7 +409,7 @@ static irqreturn_t stmpe_gpio_irq(int irq, void *dev)
                  * 801/1801/1600, bits are cleared when read.
                  * Edge detect register is not present on 801/1600/1801
                  */
-                if (stmpe->partnum != STMPE801 || stmpe->partnum != STMPE1600 ||
+                if (stmpe->partnum != STMPE801 && stmpe->partnum != STMPE1600 &&
                     stmpe->partnum != STMPE1801) {
                         stmpe_reg_write(stmpe, statmsbreg + i, status[i]);
                         stmpe_reg_write(stmpe,
diff --git a/drivers/gpio/gpio-ts4800.c b/drivers/gpio/gpio-ts4800.c
index 99256115bea5..c2a80b4cbf32 100644
--- a/drivers/gpio/gpio-ts4800.c
+++ b/drivers/gpio/gpio-ts4800.c
@@ -66,6 +66,7 @@ static const struct of_device_id ts4800_gpio_of_match[] = {
         { .compatible = "technologic,ts4800-gpio", },
         {},
 };
+MODULE_DEVICE_TABLE(of, ts4800_gpio_of_match);
 
 static struct platform_driver ts4800_gpio_driver = {
         .driver = {
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 58ece201b8e6..72a4b326fd0d 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -653,14 +653,17 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
 {
         int idx, i;
         unsigned int irq_flags;
+        int ret = -ENOENT;
 
         for (i = 0, idx = 0; idx <= index; i++) {
                 struct acpi_gpio_info info;
                 struct gpio_desc *desc;
 
                 desc = acpi_get_gpiod_by_index(adev, NULL, i, &info);
-                if (IS_ERR(desc))
+                if (IS_ERR(desc)) {
+                        ret = PTR_ERR(desc);
                         break;
+                }
                 if (info.gpioint && idx++ == index) {
                         int irq = gpiod_to_irq(desc);
 
@@ -679,7 +682,7 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
                 }
 
         }
-        return -ENOENT;
+        return ret;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get);
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index f0fc3a0d37c8..20e09b7c2de3 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -333,6 +333,13 @@ struct linehandle_state {
         u32 numdescs;
 };
 
+#define GPIOHANDLE_REQUEST_VALID_FLAGS \
+        (GPIOHANDLE_REQUEST_INPUT | \
+        GPIOHANDLE_REQUEST_OUTPUT | \
+        GPIOHANDLE_REQUEST_ACTIVE_LOW | \
+        GPIOHANDLE_REQUEST_OPEN_DRAIN | \
+        GPIOHANDLE_REQUEST_OPEN_SOURCE)
+
 static long linehandle_ioctl(struct file *filep, unsigned int cmd,
                              unsigned long arg)
 {
@@ -344,6 +351,8 @@ static long linehandle_ioctl(struct file *filep, unsigned int cmd,
         if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) {
                 int val;
 
+                memset(&ghd, 0, sizeof(ghd));
+
                 /* TODO: check if descriptors are really input */
                 for (i = 0; i < lh->numdescs; i++) {
                         val = gpiod_get_value_cansleep(lh->descs[i]);
@@ -444,6 +453,17 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
                 u32 lflags = handlereq.flags;
                 struct gpio_desc *desc;
 
+                if (offset >= gdev->ngpio) {
+                        ret = -EINVAL;
+                        goto out_free_descs;
+                }
+
+                /* Return an error if a unknown flag is set */
+                if (lflags & ~GPIOHANDLE_REQUEST_VALID_FLAGS) {
+                        ret = -EINVAL;
+                        goto out_free_descs;
+                }
+
                 desc = &gdev->descs[offset];
                 ret = gpiod_request(desc, lh->label);
                 if (ret)
@@ -536,6 +556,10 @@ struct lineevent_state {
         struct mutex read_lock;
 };
 
+#define GPIOEVENT_REQUEST_VALID_FLAGS \
+        (GPIOEVENT_REQUEST_RISING_EDGE | \
+        GPIOEVENT_REQUEST_FALLING_EDGE)
+
 static unsigned int lineevent_poll(struct file *filep,
                                    struct poll_table_struct *wait)
 {
@@ -623,6 +647,8 @@ static long lineevent_ioctl(struct file *filep, unsigned int cmd,
         if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) {
                 int val;
 
+                memset(&ghd, 0, sizeof(ghd));
+
                 val = gpiod_get_value_cansleep(le->desc);
                 if (val < 0)
                         return val;
@@ -726,6 +752,18 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
         lflags = eventreq.handleflags;
         eflags = eventreq.eventflags;
 
+        if (offset >= gdev->ngpio) {
+                ret = -EINVAL;
+                goto out_free_label;
+        }
+
+        /* Return an error if a unknown flag is set */
+        if ((lflags & ~GPIOHANDLE_REQUEST_VALID_FLAGS) ||
+            (eflags & ~GPIOEVENT_REQUEST_VALID_FLAGS)) {
+                ret = -EINVAL;
+                goto out_free_label;
+        }
+
         /* This is just wrong: we don't look for events on output lines */
         if (lflags & GPIOHANDLE_REQUEST_OUTPUT) {
                 ret = -EINVAL;
@@ -823,6 +861,8 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
         if (cmd == GPIO_GET_CHIPINFO_IOCTL) {
                 struct gpiochip_info chipinfo;
 
+                memset(&chipinfo, 0, sizeof(chipinfo));
+
                 strncpy(chipinfo.name, dev_name(&gdev->dev),
                         sizeof(chipinfo.name));
                 chipinfo.name[sizeof(chipinfo.name)-1] = '\0';
@@ -839,7 +879,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
                 if (copy_from_user(&lineinfo, ip, sizeof(lineinfo)))
                         return -EFAULT;
-                if (lineinfo.line_offset > gdev->ngpio)
+                if (lineinfo.line_offset >= gdev->ngpio)
                         return -EINVAL;
 
                 desc = &gdev->descs[lineinfo.line_offset];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index aa074fac0c7f..f3efb1c5dae9 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/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 2f58e9e2a59c..a51f8cbcfe26 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -332,17 +332,19 @@ static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
 {
         struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 
-        if (dcrtc->dpms != dpms) {
-                dcrtc->dpms = dpms;
-                if (!IS_ERR(dcrtc->clk) && !dpms_blanked(dpms))
-                        WARN_ON(clk_prepare_enable(dcrtc->clk));
-                armada_drm_crtc_update(dcrtc);
-                if (!IS_ERR(dcrtc->clk) && dpms_blanked(dpms))
-                        clk_disable_unprepare(dcrtc->clk);
+        if (dpms_blanked(dcrtc->dpms) != dpms_blanked(dpms)) {
                 if (dpms_blanked(dpms))
                         armada_drm_vblank_off(dcrtc);
-                else
+                else if (!IS_ERR(dcrtc->clk))
+                        WARN_ON(clk_prepare_enable(dcrtc->clk));
+                dcrtc->dpms = dpms;
+                armada_drm_crtc_update(dcrtc);
+                if (!dpms_blanked(dpms))
                         drm_crtc_vblank_on(&dcrtc->crtc);
+                else if (!IS_ERR(dcrtc->clk))
+                        clk_disable_unprepare(dcrtc->clk);
+        } else if (dcrtc->dpms != dpms) {
+                dcrtc->dpms = dpms;
         }
 }
 
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 608df4c90520..0743e65cb240 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 bb2438dd8733..5e7e63ce7bce 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/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
index cb86c7e5495c..d9230132dfbc 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
@@ -329,20 +329,34 @@ void etnaviv_buffer_queue(struct etnaviv_gpu *gpu, unsigned int event,
         /*
          * Append a LINK to the submitted command buffer to return to
          * the ring buffer.  return_target is the ring target address.
-         * We need three dwords: event, wait, link.
+         * We need at most 7 dwords in the return target: 2 cache flush +
+         * 2 semaphore stall + 1 event + 1 wait + 1 link.
          */
-        return_dwords = 3;
+        return_dwords = 7;
         return_target = etnaviv_buffer_reserve(gpu, buffer, return_dwords);
         CMD_LINK(cmdbuf, return_dwords, return_target);
 
         /*
-         * Append event, wait and link pointing back to the wait
-         * command to the ring buffer.
+         * Append a cache flush, stall, event, wait and link pointing back to
+         * the wait command to the ring buffer.
          */
+        if (gpu->exec_state == ETNA_PIPE_2D) {
+                CMD_LOAD_STATE(buffer, VIVS_GL_FLUSH_CACHE,
+                                       VIVS_GL_FLUSH_CACHE_PE2D);
+        } else {
+                CMD_LOAD_STATE(buffer, VIVS_GL_FLUSH_CACHE,
+                                       VIVS_GL_FLUSH_CACHE_DEPTH |
+                                       VIVS_GL_FLUSH_CACHE_COLOR);
+                CMD_LOAD_STATE(buffer, VIVS_TS_FLUSH_CACHE,
+                                       VIVS_TS_FLUSH_CACHE_FLUSH);
+        }
+        CMD_SEM(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
+        CMD_STALL(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
         CMD_LOAD_STATE(buffer, VIVS_GL_EVENT, VIVS_GL_EVENT_EVENT_ID(event) |
                        VIVS_GL_EVENT_FROM_PE);
         CMD_WAIT(buffer);
-        CMD_LINK(buffer, 2, return_target + 8);
+        CMD_LINK(buffer, 2, etnaviv_iommu_get_cmdbuf_va(gpu, buffer) +
+                            buffer->user_size - 4);
 
         if (drm_debug & DRM_UT_DRIVER)
                 pr_info("stream link to 0x%08x @ 0x%08x %p\n",
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index d3796ed8d8c5..169ac96e8f08 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -330,7 +330,8 @@ u32 etnaviv_iommu_get_cmdbuf_va(struct etnaviv_gpu *gpu,
                         return (u32)buf->vram_node.start;
 
                 mutex_lock(&mmu->lock);
-                ret = etnaviv_iommu_find_iova(mmu, &buf->vram_node, buf->size);
+                ret = etnaviv_iommu_find_iova(mmu, &buf->vram_node,
+                                              buf->size + SZ_64K);
                 if (ret < 0) {
                         mutex_unlock(&mmu->lock);
                         return 0;
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
index 3371635cd4d7..b2d5e188b1b8 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
@@ -51,6 +51,7 @@ static void fsl_dcu_drm_disable_crtc(struct drm_crtc *crtc)
                            DCU_MODE_DCU_MODE(DCU_MODE_OFF));
         regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
                      DCU_UPDATE_MODE_READREG);
+        clk_disable_unprepare(fsl_dev->pix_clk);
 }
 
 static void fsl_dcu_drm_crtc_enable(struct drm_crtc *crtc)
@@ -58,6 +59,7 @@ static void fsl_dcu_drm_crtc_enable(struct drm_crtc *crtc)
         struct drm_device *dev = crtc->dev;
         struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
 
+        clk_prepare_enable(fsl_dev->pix_clk);
         regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
                            DCU_MODE_DCU_MODE_MASK,
                            DCU_MODE_DCU_MODE(DCU_MODE_NORMAL));
@@ -116,8 +118,6 @@ static void fsl_dcu_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
                      DCU_THRESHOLD_LS_BF_VS(BF_VS_VAL) |
                      DCU_THRESHOLD_OUT_BUF_HIGH(BUF_MAX_VAL) |
                      DCU_THRESHOLD_OUT_BUF_LOW(BUF_MIN_VAL));
-        regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
-                     DCU_UPDATE_MODE_READREG);
         return;
 }
 
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
index 0884c45aefe8..e04efbed1a54 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
@@ -267,12 +267,8 @@ static int fsl_dcu_drm_pm_resume(struct device *dev)
                 return ret;
         }
 
-        ret = clk_prepare_enable(fsl_dev->pix_clk);
-        if (ret < 0) {
-                dev_err(dev, "failed to enable pix clk\n");
-                goto disable_dcu_clk;
-        }
-
+        if (fsl_dev->tcon)
+                fsl_tcon_bypass_enable(fsl_dev->tcon);
         fsl_dcu_drm_init_planes(fsl_dev->drm);
         drm_atomic_helper_resume(fsl_dev->drm, fsl_dev->state);
 
@@ -284,10 +280,6 @@ static int fsl_dcu_drm_pm_resume(struct device *dev)
         enable_irq(fsl_dev->irq);
 
         return 0;
-
-disable_dcu_clk:
-        clk_disable_unprepare(fsl_dev->clk);
-        return ret;
 }
 #endif
 
@@ -401,18 +393,12 @@ static int fsl_dcu_drm_probe(struct platform_device *pdev)
                 goto disable_clk;
         }
 
-        ret = clk_prepare_enable(fsl_dev->pix_clk);
-        if (ret < 0) {
-                dev_err(dev, "failed to enable pix clk\n");
-                goto unregister_pix_clk;
-        }
-
         fsl_dev->tcon = fsl_tcon_init(dev);
 
         drm = drm_dev_alloc(driver, dev);
         if (IS_ERR(drm)) {
                 ret = PTR_ERR(drm);
-                goto disable_pix_clk;
+                goto unregister_pix_clk;
         }
 
         fsl_dev->dev = dev;
@@ -433,8 +419,6 @@ static int fsl_dcu_drm_probe(struct platform_device *pdev)
 
 unref:
         drm_dev_unref(drm);
-disable_pix_clk:
-        clk_disable_unprepare(fsl_dev->pix_clk);
 unregister_pix_clk:
         clk_unregister(fsl_dev->pix_clk);
 disable_clk:
@@ -447,7 +431,6 @@ static int fsl_dcu_drm_remove(struct platform_device *pdev)
         struct fsl_dcu_drm_device *fsl_dev = platform_get_drvdata(pdev);
 
         clk_disable_unprepare(fsl_dev->clk);
-        clk_disable_unprepare(fsl_dev->pix_clk);
         clk_unregister(fsl_dev->pix_clk);
         drm_put_dev(fsl_dev->drm);
 
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
index a7e5486bd1e9..9e6f7d8112b3 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
@@ -211,11 +211,6 @@ void fsl_dcu_drm_init_planes(struct drm_device *dev)
                 for (j = 1; j <= fsl_dev->soc->layer_regs; j++)
                         regmap_write(fsl_dev->regmap, DCU_CTRLDESCLN(i, j), 0);
         }
-        regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
-                           DCU_MODE_DCU_MODE_MASK,
-                           DCU_MODE_DCU_MODE(DCU_MODE_OFF));
-        regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
-                     DCU_UPDATE_MODE_READREG);
 }
 
 struct drm_plane *fsl_dcu_drm_primary_create_plane(struct drm_device *dev)
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index 26edcc899712..e1dd75b18118 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -20,38 +20,6 @@
 #include "fsl_dcu_drm_drv.h"
 #include "fsl_tcon.h"
 
-static int
-fsl_dcu_drm_encoder_atomic_check(struct drm_encoder *encoder,
-                                 struct drm_crtc_state *crtc_state,
-                                 struct drm_connector_state *conn_state)
-{
-        return 0;
-}
-
-static void fsl_dcu_drm_encoder_disable(struct drm_encoder *encoder)
-{
-        struct drm_device *dev = encoder->dev;
-        struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
-
-        if (fsl_dev->tcon)
-                fsl_tcon_bypass_disable(fsl_dev->tcon);
-}
-
-static void fsl_dcu_drm_encoder_enable(struct drm_encoder *encoder)
-{
-        struct drm_device *dev = encoder->dev;
-        struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
-
-        if (fsl_dev->tcon)
-                fsl_tcon_bypass_enable(fsl_dev->tcon);
-}
-
-static const struct drm_encoder_helper_funcs encoder_helper_funcs = {
-        .atomic_check = fsl_dcu_drm_encoder_atomic_check,
-        .disable = fsl_dcu_drm_encoder_disable,
-        .enable = fsl_dcu_drm_encoder_enable,
-};
-
 static void fsl_dcu_drm_encoder_destroy(struct drm_encoder *encoder)
 {
         drm_encoder_cleanup(encoder);
@@ -68,13 +36,16 @@ int fsl_dcu_drm_encoder_create(struct fsl_dcu_drm_device *fsl_dev,
         int ret;
 
         encoder->possible_crtcs = 1;
+
+        /* Use bypass mode for parallel RGB/LVDS encoder */
+        if (fsl_dev->tcon)
+                fsl_tcon_bypass_enable(fsl_dev->tcon);
+
         ret = drm_encoder_init(fsl_dev->drm, encoder, &encoder_funcs,
                                DRM_MODE_ENCODER_LVDS, NULL);
         if (ret < 0)
                 return ret;
 
-        drm_encoder_helper_add(encoder, &encoder_helper_funcs);
-
         return 0;
 }
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 919b35f2ad24..dcf7d11ac380 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_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 1825dbc33192..a6dbe8258040 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/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index be30861afae9..41b72ce6613f 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/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index e8ae3dc476d1..18061a4bc2f2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -241,15 +241,15 @@ static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
                               void *ptr);
 
 MODULE_PARM_DESC(enable_fbdev, "Enable vmwgfx fbdev");
-module_param_named(enable_fbdev, enable_fbdev, int, 0600);
+module_param_named(enable_fbdev, enable_fbdev, int, S_IRUSR | S_IWUSR);
 MODULE_PARM_DESC(force_dma_api, "Force using the DMA API for TTM pages");
-module_param_named(force_dma_api, vmw_force_iommu, int, 0600);
+module_param_named(force_dma_api, vmw_force_iommu, int, S_IRUSR | S_IWUSR);
 MODULE_PARM_DESC(restrict_iommu, "Try to limit IOMMU usage for TTM pages");
-module_param_named(restrict_iommu, vmw_restrict_iommu, int, 0600);
+module_param_named(restrict_iommu, vmw_restrict_iommu, int, S_IRUSR | S_IWUSR);
 MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages");
-module_param_named(force_coherent, vmw_force_coherent, int, 0600);
+module_param_named(force_coherent, vmw_force_coherent, int, S_IRUSR | S_IWUSR);
 MODULE_PARM_DESC(restrict_dma_mask, "Restrict DMA mask to 44 bits with IOMMU");
-module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, 0600);
+module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, S_IRUSR | S_IWUSR);
 MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes");
 module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 070d750af16d..1e59a486bba8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -43,7 +43,7 @@
 
 #define VMWGFX_DRIVER_DATE "20160210"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 10
+#define VMWGFX_DRIVER_MINOR 11
 #define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FILE_PAGE_OFFSET 0x00100000
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index dc5beff2b4aa..c7b53d987f06 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -35,17 +35,37 @@
 #define VMW_RES_HT_ORDER 12
 
 /**
+ * enum vmw_resource_relocation_type - Relocation type for resources
+ *
+ * @vmw_res_rel_normal: Traditional relocation. The resource id in the
+ * command stream is replaced with the actual id after validation.
+ * @vmw_res_rel_nop: NOP relocation. The command is unconditionally replaced
+ * with a NOP.
+ * @vmw_res_rel_cond_nop: Conditional NOP relocation. If the resource id
+ * after validation is -1, the command is replaced with a NOP. Otherwise no
+ * action.
+ */
+enum vmw_resource_relocation_type {
+        vmw_res_rel_normal,
+        vmw_res_rel_nop,
+        vmw_res_rel_cond_nop,
+        vmw_res_rel_max
+};
+
+/**
  * struct vmw_resource_relocation - Relocation info for resources
  *
  * @head: List head for the software context's relocation list.
  * @res: Non-ref-counted pointer to the resource.
- * @offset: Offset of 4 byte entries into the command buffer where the
+ * @offset: Offset of single byte entries into the command buffer where the
  * id that needs fixup is located.
+ * @rel_type: Type of relocation.
  */
 struct vmw_resource_relocation {
         struct list_head head;
         const struct vmw_resource *res;
-        unsigned long offset;
+        u32 offset:29;
+        enum vmw_resource_relocation_type rel_type:3;
 };
 
 /**
@@ -109,7 +129,18 @@ static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
                                    struct vmw_dma_buffer *vbo,
                                    bool validate_as_mob,
                                    uint32_t *p_val_node);
-
+/**
+ * vmw_ptr_diff - Compute the offset from a to b in bytes
+ *
+ * @a: A starting pointer.
+ * @b: A pointer offset in the same address space.
+ *
+ * Returns: The offset in bytes between the two pointers.
+ */
+static size_t vmw_ptr_diff(void *a, void *b)
+{
+        return (unsigned long) b - (unsigned long) a;
+}
 
 /**
  * vmw_resources_unreserve - unreserve resources previously reserved for
@@ -409,11 +440,14 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
  * @list: Pointer to head of relocation list.
  * @res: The resource.
  * @offset: Offset into the command buffer currently being parsed where the
- * id that needs fixup is located. Granularity is 4 bytes.
+ * id that needs fixup is located. Granularity is one byte.
+ * @rel_type: Relocation type.
  */
 static int vmw_resource_relocation_add(struct list_head *list,
                                        const struct vmw_resource *res,
-                                       unsigned long offset)
+                                       unsigned long offset,
+                                       enum vmw_resource_relocation_type
+                                       rel_type)
 {
         struct vmw_resource_relocation *rel;
 
@@ -425,6 +459,7 @@ static int vmw_resource_relocation_add(struct list_head *list,
 
         rel->res = res;
         rel->offset = offset;
+        rel->rel_type = rel_type;
         list_add_tail(&rel->head, list);
 
         return 0;
@@ -459,11 +494,24 @@ static void vmw_resource_relocations_apply(uint32_t *cb,
 {
         struct vmw_resource_relocation *rel;
 
+        /* Validate the struct vmw_resource_relocation member size */
+        BUILD_BUG_ON(SVGA_CB_MAX_SIZE >= (1 << 29));
+        BUILD_BUG_ON(vmw_res_rel_max >= (1 << 3));
+
         list_for_each_entry(rel, list, head) {
-                if (likely(rel->res != NULL))
-                        cb[rel->offset] = rel->res->id;
-                else
-                        cb[rel->offset] = SVGA_3D_CMD_NOP;
+                u32 *addr = (u32 *)((unsigned long) cb + rel->offset);
+                switch (rel->rel_type) {
+                case vmw_res_rel_normal:
+                        *addr = rel->res->id;
+                        break;
+                case vmw_res_rel_nop:
+                        *addr = SVGA_3D_CMD_NOP;
+                        break;
+                default:
+                        if (rel->res->id == -1)
+                                *addr = SVGA_3D_CMD_NOP;
+                        break;
+                }
         }
 }
 
@@ -655,7 +703,9 @@ static int vmw_cmd_res_reloc_add(struct vmw_private *dev_priv,
         *p_val = NULL;
         ret = vmw_resource_relocation_add(&sw_context->res_relocations,
                                           res,
-                                          id_loc - sw_context->buf_start);
+                                          vmw_ptr_diff(sw_context->buf_start,
+                                                       id_loc),
+                                          vmw_res_rel_normal);
         if (unlikely(ret != 0))
                 return ret;
 
@@ -721,7 +771,8 @@ vmw_cmd_res_check(struct vmw_private *dev_priv,
 
                 return vmw_resource_relocation_add
                         (&sw_context->res_relocations, res,
-                         id_loc - sw_context->buf_start);
+                         vmw_ptr_diff(sw_context->buf_start, id_loc),
+                         vmw_res_rel_normal);
         }
 
         ret = vmw_user_resource_lookup_handle(dev_priv,
@@ -2143,10 +2194,10 @@ static int vmw_cmd_shader_define(struct vmw_private *dev_priv,
                 return ret;
 
         return vmw_resource_relocation_add(&sw_context->res_relocations,
-                                           NULL, &cmd->header.id -
-                                           sw_context->buf_start);
-
-        return 0;
+                                           NULL,
+                                           vmw_ptr_diff(sw_context->buf_start,
+                                                        &cmd->header.id),
+                                           vmw_res_rel_nop);
 }
 
 /**
@@ -2188,10 +2239,10 @@ static int vmw_cmd_shader_destroy(struct vmw_private *dev_priv,
                 return ret;
 
         return vmw_resource_relocation_add(&sw_context->res_relocations,
-                                           NULL, &cmd->header.id -
-                                           sw_context->buf_start);
-
-        return 0;
+                                           NULL,
+                                           vmw_ptr_diff(sw_context->buf_start,
+                                                        &cmd->header.id),
+                                           vmw_res_rel_nop);
 }
 
 /**
@@ -2848,8 +2899,7 @@ static int vmw_cmd_dx_cid_check(struct vmw_private *dev_priv,
  * @header: Pointer to the command header in the command stream.
  *
  * Check that the view exists, and if it was not created using this
- * command batch, make sure it's validated (present in the device) so that
- * the remove command will not confuse the device.
+ * command batch, conditionally make this command a NOP.
  */
 static int vmw_cmd_dx_view_remove(struct vmw_private *dev_priv,
                                   struct vmw_sw_context *sw_context,
@@ -2877,10 +2927,16 @@ static int vmw_cmd_dx_view_remove(struct vmw_private *dev_priv,
                 return ret;
 
         /*
-         * Add view to the validate list iff it was not created using this
-         * command batch.
+         * If the view wasn't created during this command batch, it might
+         * have been removed due to a context swapout, so add a
+         * relocation to conditionally make this command a NOP to avoid
+         * device errors.
          */
-        return vmw_view_res_val_add(sw_context, view);
+        return vmw_resource_relocation_add(&sw_context->res_relocations,
+                                           view,
+                                           vmw_ptr_diff(sw_context->buf_start,
+                                                        &cmd->header.id),
+                                           vmw_res_rel_cond_nop);
 }
 
 /**
@@ -3029,6 +3085,35 @@ static int vmw_cmd_dx_genmips(struct vmw_private *dev_priv,
                                    cmd->body.shaderResourceViewId);
 }
 
+/**
+ * vmw_cmd_dx_transfer_from_buffer -
+ * Validate an SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command
+ *
+ * @dev_priv: Pointer to a device private struct.
+ * @sw_context: The software context being used for this batch.
+ * @header: Pointer to the command header in the command stream.
+ */
+static int vmw_cmd_dx_transfer_from_buffer(struct vmw_private *dev_priv,
+                                           struct vmw_sw_context *sw_context,
+                                           SVGA3dCmdHeader *header)
+{
+        struct {
+                SVGA3dCmdHeader header;
+                SVGA3dCmdDXTransferFromBuffer body;
+        } *cmd = container_of(header, typeof(*cmd), header);
+        int ret;
+
+        ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
+                                user_surface_converter,
+                                &cmd->body.srcSid, NULL);
+        if (ret != 0)
+                return ret;
+
+        return vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
+                                 user_surface_converter,
+                                 &cmd->body.destSid, NULL);
+}
+
 static int vmw_cmd_check_not_3d(struct vmw_private *dev_priv,
                                 struct vmw_sw_context *sw_context,
                                 void *buf, uint32_t *size)
@@ -3379,6 +3464,9 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
                     &vmw_cmd_buffer_copy_check, true, false, true),
         VMW_CMD_DEF(SVGA_3D_CMD_DX_PRED_COPY_REGION,
                     &vmw_cmd_pred_copy_check, true, false, true),
+        VMW_CMD_DEF(SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER,
+                    &vmw_cmd_dx_transfer_from_buffer,
+                    true, false, true),
 };
 
 static int vmw_cmd_check(struct vmw_private *dev_priv,
@@ -3848,14 +3936,14 @@ static void *vmw_execbuf_cmdbuf(struct vmw_private *dev_priv,
         int ret;
 
         *header = NULL;
-        if (!dev_priv->cman || kernel_commands)
-                return kernel_commands;
-
         if (command_size > SVGA_CB_MAX_SIZE) {
                 DRM_ERROR("Command buffer is too large.\n");
                 return ERR_PTR(-EINVAL);
         }
 
+        if (!dev_priv->cman || kernel_commands)
+                return kernel_commands;
+
         /* If possible, add a little space for fencing. */
         cmdbuf_size = command_size + 512;
         cmdbuf_size = min_t(size_t, cmdbuf_size, SVGA_CB_MAX_SIZE);
@@ -4232,9 +4320,6 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
         ttm_bo_unref(&query_val.bo);
         ttm_bo_unref(&pinned_val.bo);
         vmw_dmabuf_unreference(&dev_priv->pinned_bo);
-        DRM_INFO("Dummy query bo pin count: %d\n",
-                 dev_priv->dummy_query_bo->pin_count);
-
 out_unlock:
         return;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 6a328d507a28..52ca1c9d070e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -574,10 +574,8 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
                 bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
                 long lret;
 
-                if (nonblock)
-                        return reservation_object_test_signaled_rcu(bo->resv, true) ? 0 : -EBUSY;
-
-                lret = reservation_object_wait_timeout_rcu(bo->resv, true, true, MAX_SCHEDULE_TIMEOUT);
+                lret = reservation_object_wait_timeout_rcu(bo->resv, true, true,
+                                        nonblock ? 0 : MAX_SCHEDULE_TIMEOUT);
                 if (!lret)
                         return -EBUSY;
                 else if (lret < 0)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index c2a721a8cef9..b445ce9b9757 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -324,7 +324,7 @@ static void vmw_hw_surface_destroy(struct vmw_resource *res)
         if (res->id != -1) {
 
                 cmd = vmw_fifo_reserve(dev_priv, vmw_surface_destroy_size());
-                if (unlikely(cmd == NULL)) {
+                if (unlikely(!cmd)) {
                         DRM_ERROR("Failed reserving FIFO space for surface "
                                   "destruction.\n");
                         return;
@@ -397,7 +397,7 @@ static int vmw_legacy_srf_create(struct vmw_resource *res)
 
         submit_size = vmw_surface_define_size(srf);
         cmd = vmw_fifo_reserve(dev_priv, submit_size);
-        if (unlikely(cmd == NULL)) {
+        if (unlikely(!cmd)) {
                 DRM_ERROR("Failed reserving FIFO space for surface "
                           "creation.\n");
                 ret = -ENOMEM;
@@ -446,11 +446,10 @@ static int vmw_legacy_srf_dma(struct vmw_resource *res,
         uint8_t *cmd;
         struct vmw_private *dev_priv = res->dev_priv;
 
-        BUG_ON(val_buf->bo == NULL);
-
+        BUG_ON(!val_buf->bo);
         submit_size = vmw_surface_dma_size(srf);
         cmd = vmw_fifo_reserve(dev_priv, submit_size);
-        if (unlikely(cmd == NULL)) {
+        if (unlikely(!cmd)) {
                 DRM_ERROR("Failed reserving FIFO space for surface "
                           "DMA.\n");
                 return -ENOMEM;
@@ -538,7 +537,7 @@ static int vmw_legacy_srf_destroy(struct vmw_resource *res)
 
         submit_size = vmw_surface_destroy_size();
         cmd = vmw_fifo_reserve(dev_priv, submit_size);
-        if (unlikely(cmd == NULL)) {
+        if (unlikely(!cmd)) {
                 DRM_ERROR("Failed reserving FIFO space for surface "
                           "eviction.\n");
                 return -ENOMEM;
@@ -578,7 +577,7 @@ static int vmw_surface_init(struct vmw_private *dev_priv,
         int ret;
         struct vmw_resource *res = &srf->res;
 
-        BUG_ON(res_free == NULL);
+        BUG_ON(!res_free);
         if (!dev_priv->has_mob)
                 vmw_fifo_resource_inc(dev_priv);
         ret = vmw_resource_init(dev_priv, res, true, res_free,
@@ -700,7 +699,6 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
         struct drm_vmw_surface_create_req *req = &arg->req;
         struct drm_vmw_surface_arg *rep = &arg->rep;
         struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-        struct drm_vmw_size __user *user_sizes;
         int ret;
         int i, j;
         uint32_t cur_bo_offset;
@@ -748,7 +746,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
         }
 
         user_srf = kzalloc(sizeof(*user_srf), GFP_KERNEL);
-        if (unlikely(user_srf == NULL)) {
+        if (unlikely(!user_srf)) {
                 ret = -ENOMEM;
                 goto out_no_user_srf;
         }
@@ -763,29 +761,21 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
         memcpy(srf->mip_levels, req->mip_levels, sizeof(srf->mip_levels));
         srf->num_sizes = num_sizes;
         user_srf->size = size;
-
-        srf->sizes = kmalloc(srf->num_sizes * sizeof(*srf->sizes), GFP_KERNEL);
-        if (unlikely(srf->sizes == NULL)) {
-                ret = -ENOMEM;
+        srf->sizes = memdup_user((struct drm_vmw_size __user *)(unsigned long)
+                                 req->size_addr,
+                                 sizeof(*srf->sizes) * srf->num_sizes);
+        if (IS_ERR(srf->sizes)) {
+                ret = PTR_ERR(srf->sizes);
                 goto out_no_sizes;
         }
-        srf->offsets = kmalloc(srf->num_sizes * sizeof(*srf->offsets),
-                               GFP_KERNEL);
-        if (unlikely(srf->offsets == NULL)) {
+        srf->offsets = kmalloc_array(srf->num_sizes,
+                                     sizeof(*srf->offsets),
+                                     GFP_KERNEL);
+        if (unlikely(!srf->offsets)) {
                 ret = -ENOMEM;
                 goto out_no_offsets;
         }
 
-        user_sizes = (struct drm_vmw_size __user *)(unsigned long)
-            req->size_addr;
-
-        ret = copy_from_user(srf->sizes, user_sizes,
-                             srf->num_sizes * sizeof(*srf->sizes));
-        if (unlikely(ret != 0)) {
-                ret = -EFAULT;
-                goto out_no_copy;
-        }
-
         srf->base_size = *srf->sizes;
         srf->autogen_filter = SVGA3D_TEX_FILTER_NONE;
         srf->multisample_count = 0;
@@ -923,7 +913,7 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 
         ret = -EINVAL;
         base = ttm_base_object_lookup_for_ref(dev_priv->tdev, handle);
-        if (unlikely(base == NULL)) {
+        if (unlikely(!base)) {
                 DRM_ERROR("Could not find surface to reference.\n");
                 goto out_no_lookup;
         }
@@ -1069,7 +1059,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 
         cmd = vmw_fifo_reserve(dev_priv, submit_len);
         cmd2 = (typeof(cmd2))cmd;
-        if (unlikely(cmd == NULL)) {
+        if (unlikely(!cmd)) {
                 DRM_ERROR("Failed reserving FIFO space for surface "
                           "creation.\n");
                 ret = -ENOMEM;
@@ -1135,7 +1125,7 @@ static int vmw_gb_surface_bind(struct vmw_resource *res,
         submit_size = sizeof(*cmd1) + (res->backup_dirty ? sizeof(*cmd2) : 0);
 
         cmd1 = vmw_fifo_reserve(dev_priv, submit_size);
-        if (unlikely(cmd1 == NULL)) {
+        if (unlikely(!cmd1)) {
                 DRM_ERROR("Failed reserving FIFO space for surface "
                           "binding.\n");
                 return -ENOMEM;
@@ -1185,7 +1175,7 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res,
 
         submit_size = sizeof(*cmd3) + (readback ? sizeof(*cmd1) : sizeof(*cmd2));
         cmd = vmw_fifo_reserve(dev_priv, submit_size);
-        if (unlikely(cmd == NULL)) {
+        if (unlikely(!cmd)) {
                 DRM_ERROR("Failed reserving FIFO space for surface "
                           "unbinding.\n");
                 return -ENOMEM;
@@ -1244,7 +1234,7 @@ static int vmw_gb_surface_destroy(struct vmw_resource *res)
         vmw_binding_res_list_scrub(&res->binding_head);
 
         cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd));
-        if (unlikely(cmd == NULL)) {
+        if (unlikely(!cmd)) {
                 DRM_ERROR("Failed reserving FIFO space for surface "
                           "destruction.\n");
                 mutex_unlock(&dev_priv->binding_mutex);
@@ -1410,7 +1400,7 @@ int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data,
 
         user_srf = container_of(base, struct vmw_user_surface, prime.base);
         srf = &user_srf->srf;
-        if (srf->res.backup == NULL) {
+        if (!srf->res.backup) {
                 DRM_ERROR("Shared GB surface is missing a backup buffer.\n");
                 goto out_bad_resource;
         }
@@ -1524,7 +1514,7 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
         }
 
         user_srf = kzalloc(sizeof(*user_srf), GFP_KERNEL);
-        if (unlikely(user_srf == NULL)) {
+        if (unlikely(!user_srf)) {
                 ret = -ENOMEM;
                 goto out_no_user_srf;
         }
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 4aa3cb63fd41..bcd06306f3e8 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) {
+
+                vmbus_recvpacket(channel, hbeat_txf_buf,
+                                 PAGE_SIZE, &recvlen, &requestid);
+
+                if (!recvlen)
+                        break;
 
-        if (recvlen > 0) {
                 icmsghdrp = (struct icmsg_hdr *)&hbeat_txf_buf[
                                 sizeof(struct vmbuspipe_hdr)];
 
diff --git a/drivers/hwmon/adm9240.c b/drivers/hwmon/adm9240.c
index 98114cef1e43..2fe1828bd10b 100644
--- a/drivers/hwmon/adm9240.c
+++ b/drivers/hwmon/adm9240.c
@@ -194,10 +194,10 @@ static struct adm9240_data *adm9240_update_device(struct device *dev)
                  * 0.5'C per two measurement cycles thus ignore possible
                  * but unlikely aliasing error on lsb reading. --Grant
                  */
-                data->temp = ((i2c_smbus_read_byte_data(client,
+                data->temp = (i2c_smbus_read_byte_data(client,
                                         ADM9240_REG_TEMP) << 8) |
                                         i2c_smbus_read_byte_data(client,
-                                        ADM9240_REG_TEMP_CONF)) / 128;
+                                        ADM9240_REG_TEMP_CONF);
 
                 for (i = 0; i < 2; i++) { /* read fans */
                         data->fan[i] = i2c_smbus_read_byte_data(client,
@@ -263,7 +263,7 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *dummy,
                 char *buf)
 {
         struct adm9240_data *data = adm9240_update_device(dev);
-        return sprintf(buf, "%d\n", data->temp * 500); /* 9-bit value */
+        return sprintf(buf, "%d\n", data->temp / 128 * 500); /* 9-bit value */
 }
 
 static ssize_t show_max(struct device *dev, struct device_attribute *devattr,
diff --git a/drivers/hwmon/max31790.c b/drivers/hwmon/max31790.c
index bef84e085973..c1b9275978f9 100644
--- a/drivers/hwmon/max31790.c
+++ b/drivers/hwmon/max31790.c
@@ -268,11 +268,13 @@ static int max31790_read_pwm(struct device *dev, u32 attr, int channel,
                              long *val)
 {
         struct max31790_data *data = max31790_update_device(dev);
-        u8 fan_config = data->fan_config[channel];
+        u8 fan_config;
 
         if (IS_ERR(data))
                 return PTR_ERR(data);
 
+        fan_config = data->fan_config[channel];
+
         switch (attr) {
         case hwmon_pwm_input:
                 *val = data->pwm[channel] >> 8;
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 6d94e2ec5b4f..d252276feadf 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -79,12 +79,12 @@ config I2C_AMD8111
 
 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_IMG
 
 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 1fe93c43215c..11e866d05368 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 9604024e0eb0..49f2084f7bb5 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 08847e8b8998..eb3627f35d12 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 592a8f26a708..47fc1f1acff7 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 b8ea62105f42..30132c3957cd 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 50702c7bb244..df220666d627 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 263685c7a512..05cf192ef1ac 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 2a972ed7aa0d..e29ff37a43bd 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 0968f59b6df5..ad17d88d8573 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 5ab67219f71e..1704fc84d647 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);
@@ -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 7edcf3238620..99c051490eff 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -437,6 +437,8 @@ config STX104
 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 bd321b305a0a..ef761a508630 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 39dd2026ccc9..066161a4bccd 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 22174774dbb8..63036c731626 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 41f4c2afbcdd..7ce97daf26c6 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 7c06d85568d4..6c9f3923e838 100644
--- a/drivers/infiniband/hw/qedr/Kconfig
+++ b/drivers/infiniband/hw/qedr/Kconfig
@@ -2,6 +2,7 @@ config INFINIBAND_QEDR
         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 7b8d2d9e2263..da12717a3eb7 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 4ad297d3de89..339a1eecdfe3 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 be11d5d5b8c1..830fecb6934c 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 5636fc3da6b8..b58d9dca5c93 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 @@ err_drop:
 }
 
 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 @@ send_using_neigh:
                         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 d3394b6add24..1909dd252c94 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/ipack/ipack.c b/drivers/ipack/ipack.c
index c0e7b624ce54..12102448fddd 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/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 82b0b5daf3f5..bc0af3307bbf 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -158,8 +158,8 @@ config PIC32_EVIC
         select IRQ_DOMAIN
 
 config JCORE_AIC
-        bool "J-Core integrated AIC"
-        depends on OF && (SUPERH || COMPILE_TEST)
+        bool "J-Core integrated AIC" if COMPILE_TEST
+        depends on OF
         select IRQ_DOMAIN
         help
           Support for the J-Core integrated AIC.
diff --git a/drivers/irqchip/irq-eznps.c b/drivers/irqchip/irq-eznps.c
index ebc2b0b15f67..2a7a38830a8d 100644
--- a/drivers/irqchip/irq-eznps.c
+++ b/drivers/irqchip/irq-eznps.c
@@ -135,7 +135,7 @@ static const struct irq_domain_ops nps400_irq_ops = {
 static int __init nps400_of_init(struct device_node *node,
                                  struct device_node *parent)
 {
-        static struct irq_domain *nps400_root_domain;
+        struct irq_domain *nps400_root_domain;
 
         if (parent) {
                 pr_err("DeviceTree incore ic not a root irq controller\n");
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 003495d91f9c..c5dee300e8a3 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1023,7 +1023,7 @@ static void its_free_tables(struct its_node *its)
 
 static int its_alloc_tables(struct its_node *its)
 {
-        u64 typer = readq_relaxed(its->base + GITS_TYPER);
+        u64 typer = gic_read_typer(its->base + GITS_TYPER);
         u32 ids = GITS_TYPER_DEVBITS(typer);
         u64 shr = GITS_BASER_InnerShareable;
         u64 cache = GITS_BASER_WaWb;
@@ -1198,7 +1198,7 @@ static void its_cpu_init_collection(void)
                  * We now have to bind each collection to its target
                  * redistributor.
                  */
-                if (readq_relaxed(its->base + GITS_TYPER) & GITS_TYPER_PTA) {
+                if (gic_read_typer(its->base + GITS_TYPER) & GITS_TYPER_PTA) {
                         /*
                          * This ITS wants the physical address of the
                          * redistributor.
@@ -1208,7 +1208,7 @@ static void its_cpu_init_collection(void)
                         /*
                          * This ITS wants a linear CPU number.
                          */
-                        target = readq_relaxed(gic_data_rdist_rd_base() + GICR_TYPER);
+                        target = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
                         target = GICR_TYPER_CPU_NUMBER(target) << 16;
                 }
 
@@ -1691,7 +1691,7 @@ static int __init its_probe_one(struct resource *res,
         INIT_LIST_HEAD(&its->its_device_list);
         its->base = its_base;
         its->phys_base = res->start;
-        its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+        its->ite_size = ((gic_read_typer(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
         its->numa_node = numa_node;
 
         its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
@@ -1763,7 +1763,7 @@ out_unmap:
 
 static bool gic_rdists_supports_plpis(void)
 {
-        return !!(readl_relaxed(gic_data_rdist_rd_base() + GICR_TYPER) & GICR_TYPER_PLPIS);
+        return !!(gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER) & GICR_TYPER_PLPIS);
 }
 
 int its_cpu_init(void)
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 58e5b4e87056..d6c404b3584d 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1279,7 +1279,7 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
                  */
                 *base += 0xf000;
                 cpuif_res.start += 0xf000;
-                pr_warn("GIC: Adjusting CPU interface base to %pa",
+                pr_warn("GIC: Adjusting CPU interface base to %pa\n",
                         &cpuif_res.start);
         }
 
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 8abde6b8cedc..6d53810963f7 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 bdf1606f67bc..9a8b71067c6e 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 dc75bea0d541..1d0d2adc050a 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 3e407a9cde1f..c4b53b332607 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 147af9536d0c..ef7bf1dd6900 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/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c
index d34bc3530385..2e3cf012ef48 100644
--- a/drivers/memstick/host/rtsx_usb_ms.c
+++ b/drivers/memstick/host/rtsx_usb_ms.c
@@ -524,6 +524,7 @@ static void rtsx_usb_ms_handle_req(struct work_struct *work)
         int rc;
 
         if (!host->req) {
+                pm_runtime_get_sync(ms_dev(host));
                 do {
                         rc = memstick_next_req(msh, &host->req);
                         dev_dbg(ms_dev(host), "next req %d\n", rc);
@@ -544,6 +545,7 @@ static void rtsx_usb_ms_handle_req(struct work_struct *work)
                                                 host->req->error);
                         }
                 } while (!rc);
+                pm_runtime_put(ms_dev(host));
         }
 
 }
@@ -570,6 +572,7 @@ static int rtsx_usb_ms_set_param(struct memstick_host *msh,
         dev_dbg(ms_dev(host), "%s: param = %d, value = %d\n",
                         __func__, param, value);
 
+        pm_runtime_get_sync(ms_dev(host));
         mutex_lock(&ucr->dev_mutex);
 
         err = rtsx_usb_card_exclusive_check(ucr, RTSX_USB_MS_CARD);
@@ -635,6 +638,7 @@ static int rtsx_usb_ms_set_param(struct memstick_host *msh,
         }
 out:
         mutex_unlock(&ucr->dev_mutex);
+        pm_runtime_put(ms_dev(host));
 
         /* power-on delay */
         if (param == MEMSTICK_POWER && value == MEMSTICK_POWER_ON)
@@ -681,6 +685,7 @@ static int rtsx_usb_detect_ms_card(void *__host)
         int err;
 
         for (;;) {
+                pm_runtime_get_sync(ms_dev(host));
                 mutex_lock(&ucr->dev_mutex);
 
                 /* Check pending MS card changes */
@@ -703,6 +708,7 @@ static int rtsx_usb_detect_ms_card(void *__host)
                 }
 
 poll_again:
+                pm_runtime_put(ms_dev(host));
                 if (host->eject)
                         break;
 
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index f3d34b941f85..2e5233b60971 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -229,6 +229,14 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
         if (ctx->status == STARTED)
                 goto out; /* already started */
 
+        /*
+         * 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)
+                goto out;
+
         if (task) {
                 ctx->pid = get_task_pid(task, PIDTYPE_PID);
                 ctx->glpid = get_task_pid(task->group_leader, PIDTYPE_PID);
@@ -239,7 +247,10 @@ 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/context.c b/drivers/misc/cxl/context.c
index c466ee2b0c97..5e506c19108a 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -238,6 +238,9 @@ int __detach_context(struct cxl_context *ctx)
         put_pid(ctx->glpid);
 
         cxl_ctx_put();
+
+        /* Decrease the attached context count on the adapter */
+        cxl_adapter_context_put(ctx->afu->adapter);
         return 0;
 }
 
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 01d372aba131..a144073593fa 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -618,6 +618,14 @@ struct cxl {
         bool perst_select_user;
         bool perst_same_image;
         bool psl_timebase_synced;
+
+        /*
+         * number of contexts mapped on to this card. Possible values are:
+         * >0: Number of contexts mapped and new one can be mapped.
+         *  0: No active contexts and new ones can be mapped.
+         * -1: No contexts mapped and new ones cannot be mapped.
+         */
+        atomic_t contexts_num;
 };
 
 int cxl_pci_alloc_one_irq(struct cxl *adapter);
@@ -944,4 +952,20 @@ bool cxl_pci_is_vphb_device(struct pci_dev *dev);
 
 /* decode AFU error bits in the PSL register PSL_SERR_An */
 void cxl_afu_decode_psl_serr(struct cxl_afu *afu, u64 serr);
+
+/*
+ * Increments the number of attached contexts on an adapter.
+ * In case an adapter_context_lock is taken the return -EBUSY.
+ */
+int cxl_adapter_context_get(struct cxl *adapter);
+
+/* Decrements the number of attached contexts on an adapter */
+void cxl_adapter_context_put(struct cxl *adapter);
+
+/* If no active contexts then prevents contexts from being attached */
+int cxl_adapter_context_lock(struct cxl *adapter);
+
+/* Unlock the contexts-lock if taken. Warn and force unlock otherwise */
+void cxl_adapter_context_unlock(struct cxl *adapter);
+
 #endif
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 5fb9894b157f..77080cc5fa0a 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
@@ -205,11 +215,16 @@ 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);
 
+
         trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
 
         if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,
                                                         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/cxl/guest.c b/drivers/misc/cxl/guest.c
index 9aa58a77a24d..3e102cd6ed91 100644
--- a/drivers/misc/cxl/guest.c
+++ b/drivers/misc/cxl/guest.c
@@ -1152,6 +1152,9 @@ struct cxl *cxl_guest_init_adapter(struct device_node *np, struct platform_devic
         if ((rc = cxl_sysfs_adapter_add(adapter)))
                 goto err_put1;
 
+        /* release the context lock as the adapter is configured */
+        cxl_adapter_context_unlock(adapter);
+
         return adapter;
 
 err_put1:
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index d9be23b24aa3..62e0dfb5f15b 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -243,8 +243,10 @@ struct cxl *cxl_alloc_adapter(void)
         if (dev_set_name(&adapter->dev, "card%i", adapter->adapter_num))
                 goto err2;
 
-        return adapter;
+        /* start with context lock taken */
+        atomic_set(&adapter->contexts_num, -1);
 
+        return adapter;
 err2:
         cxl_remove_adapter_nr(adapter);
 err1:
@@ -286,6 +288,44 @@ int cxl_afu_select_best_mode(struct cxl_afu *afu)
         return 0;
 }
 
+int cxl_adapter_context_get(struct cxl *adapter)
+{
+        int rc;
+
+        rc = atomic_inc_unless_negative(&adapter->contexts_num);
+        return rc >= 0 ? 0 : -EBUSY;
+}
+
+void cxl_adapter_context_put(struct cxl *adapter)
+{
+        atomic_dec_if_positive(&adapter->contexts_num);
+}
+
+int cxl_adapter_context_lock(struct cxl *adapter)
+{
+        int rc;
+        /* no active contexts -> contexts_num == 0 */
+        rc = atomic_cmpxchg(&adapter->contexts_num, 0, -1);
+        return rc ? -EBUSY : 0;
+}
+
+void cxl_adapter_context_unlock(struct cxl *adapter)
+{
+        int val = atomic_cmpxchg(&adapter->contexts_num, -1, 0);
+
+        /*
+         * contexts lock taken -> contexts_num == -1
+         * If not true then show a warning and force reset the lock.
+         * This will happen when context_unlock was requested without
+         * doing a context_lock.
+         */
+        if (val != -1) {
+                atomic_set(&adapter->contexts_num, 0);
+                WARN(1, "Adapter context unlocked with %d active contexts",
+                     val);
+        }
+}
+
 static int __init init_cxl(void)
 {
         int rc = 0;
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 7afad8477ad5..e96be9ca4e60 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1487,6 +1487,8 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
         if ((rc = cxl_native_register_psl_err_irq(adapter)))
                 goto err;
 
+        /* Release the context lock as adapter is configured */
+        cxl_adapter_context_unlock(adapter);
         return 0;
 
 err:
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index b043c20f158f..a8b6d6a635e9 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -75,12 +75,31 @@ static ssize_t reset_adapter_store(struct device *device,
         int val;
 
         rc = sscanf(buf, "%i", &val);
-        if ((rc != 1) || (val != 1))
+        if ((rc != 1) || (val != 1 && val != -1))
                 return -EINVAL;
 
-        if ((rc = cxl_ops->adapter_reset(adapter)))
-                return rc;
-        return count;
+        /*
+         * See if we can lock the context mapping that's only allowed
+         * when there are no contexts attached to the adapter. Once
+         * taken this will also prevent any context from getting activated.
+         */
+        if (val == 1) {
+                rc =  cxl_adapter_context_lock(adapter);
+                if (rc)
+                        goto out;
+
+                rc = cxl_ops->adapter_reset(adapter);
+                /* In case reset failed release context lock */
+                if (rc)
+                        cxl_adapter_context_unlock(adapter);
+
+        } else if (val == -1) {
+                /* Perform a forced adapter reset */
+                rc = cxl_ops->adapter_reset(adapter);
+        }
+
+out:
+        return rc ? rc : count;
 }
 
 static ssize_t load_image_on_perst_show(struct device *device,
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 8a679ecc8fd1..fc2794b513fa 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 e6e5e55a12ed..60415a2bfcbd 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 1525870f460a..33741ad4a74a 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 a8cee33ae8d2..b3fa738ae005 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 896be150e28f..d7eaf1eb11e7 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/card/block.c b/drivers/mmc/card/block.c
index c3335112e68c..709a872ed484 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -46,6 +46,7 @@
 #include <asm/uaccess.h>
 
 #include "queue.h"
+#include "block.h"
 
 MODULE_ALIAS("mmc:block");
 #ifdef MODULE_PARAM_PREFIX
@@ -1786,7 +1787,7 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq,
         struct mmc_blk_data *md = mq->data;
         struct mmc_packed *packed = mqrq->packed;
         bool do_rel_wr, do_data_tag;
-        u32 *packed_cmd_hdr;
+        __le32 *packed_cmd_hdr;
         u8 hdr_blocks;
         u8 i = 1;
 
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 3c15a75bae86..342f1e3f301e 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -31,7 +31,7 @@ enum mmc_packed_type {
 
 struct mmc_packed {
         struct list_head        list;
-        u32                     cmd_hdr[1024];
+        __le32                  cmd_hdr[1024];
         unsigned int            blocks;
         u8                      nr_entries;
         u8                      retries;
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 3486bc7fbb64..39fc5b2b96c5 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1263,6 +1263,16 @@ static int mmc_select_hs400es(struct mmc_card *card)
                 goto out_err;
         }
 
+        if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400_1_2V)
+                err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
+
+        if (err && card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400_1_8V)
+                err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
+
+        /* If fails try again during next card power cycle */
+        if (err)
+                goto out_err;
+
         err = mmc_select_bus_width(card);
         if (err < 0)
                 goto out_err;
@@ -1272,6 +1282,8 @@ static int mmc_select_hs400es(struct mmc_card *card)
         if (err)
                 goto out_err;
 
+        mmc_set_clock(host, card->ext_csd.hs_max_dtr);
+
         err = mmc_switch_status(card);
         if (err)
                 goto out_err;
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 4106295527b9..6e9c0f8fddb1 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -1138,11 +1138,6 @@ static void sdmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
         dev_dbg(sdmmc_dev(host), "%s\n", __func__);
         mutex_lock(&ucr->dev_mutex);
 
-        if (rtsx_usb_card_exclusive_check(ucr, RTSX_USB_SD_CARD)) {
-                mutex_unlock(&ucr->dev_mutex);
-                return;
-        }
-
         sd_set_power_mode(host, ios->power_mode);
         sd_set_bus_width(host, ios->bus_width);
         sd_set_timing(host, ios->timing, &host->ddr_mode);
@@ -1314,6 +1309,7 @@ static void rtsx_usb_update_led(struct work_struct *work)
                 container_of(work, struct rtsx_usb_sdmmc, led_work);
         struct rtsx_ucr *ucr = host->ucr;
 
+        pm_runtime_get_sync(sdmmc_dev(host));
         mutex_lock(&ucr->dev_mutex);
 
         if (host->led.brightness == LED_OFF)
@@ -1322,6 +1318,7 @@ static void rtsx_usb_update_led(struct work_struct *work)
                 rtsx_usb_turn_on_led(ucr);
 
         mutex_unlock(&ucr->dev_mutex);
+        pm_runtime_put(sdmmc_dev(host));
 }
 #endif
 
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 1f54fd8755c8..7123ef96ed18 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -346,7 +346,8 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
         struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
         u32 data;
 
-        if (unlikely(reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE)) {
+        if (unlikely(reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE ||
+                        reg == SDHCI_INT_STATUS)) {
                 if ((val & SDHCI_INT_CARD_INT) && !esdhc_is_usdhc(imx_data)) {
                         /*
                          * Clear and then set D3CD bit to avoid missing the
@@ -555,6 +556,25 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg)
         esdhc_clrset_le(host, 0xffff, val, reg);
 }
 
+static u8 esdhc_readb_le(struct sdhci_host *host, int reg)
+{
+        u8 ret;
+        u32 val;
+
+        switch (reg) {
+        case SDHCI_HOST_CONTROL:
+                val = readl(host->ioaddr + reg);
+
+                ret = val & SDHCI_CTRL_LED;
+                ret |= (val >> 5) & SDHCI_CTRL_DMA_MASK;
+                ret |= (val & ESDHC_CTRL_4BITBUS);
+                ret |= (val & ESDHC_CTRL_8BITBUS) << 3;
+                return ret;
+        }
+
+        return readb(host->ioaddr + reg);
+}
+
 static void esdhc_writeb_le(struct sdhci_host *host, u8 val, int reg)
 {
         struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -947,6 +967,7 @@ static void esdhc_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 static struct sdhci_ops sdhci_esdhc_ops = {
         .read_l = esdhc_readl_le,
         .read_w = esdhc_readw_le,
+        .read_b = esdhc_readb_le,
         .write_l = esdhc_writel_le,
         .write_w = esdhc_writew_le,
         .write_b = esdhc_writeb_le,
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index da8e40af6f85..410a55b1c25f 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -250,7 +250,7 @@ static void sdhci_arasan_hs400_enhanced_strobe(struct mmc_host *mmc,
         writel(vendor, host->ioaddr + SDHCI_ARASAN_VENDOR_REGISTER);
 }
 
-void sdhci_arasan_reset(struct sdhci_host *host, u8 mask)
+static void sdhci_arasan_reset(struct sdhci_host *host, u8 mask)
 {
         u8 ctrl;
         struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -265,6 +265,28 @@ void sdhci_arasan_reset(struct sdhci_host *host, u8 mask)
         }
 }
 
+static int sdhci_arasan_voltage_switch(struct mmc_host *mmc,
+                                       struct mmc_ios *ios)
+{
+        switch (ios->signal_voltage) {
+        case MMC_SIGNAL_VOLTAGE_180:
+                /*
+                 * Plese don't switch to 1V8 as arasan,5.1 doesn't
+                 * actually refer to this setting to indicate the
+                 * signal voltage and the state machine will be broken
+                 * actually if we force to enable 1V8. That's something
+                 * like broken quirk but we could work around here.
+                 */
+                return 0;
+        case MMC_SIGNAL_VOLTAGE_330:
+        case MMC_SIGNAL_VOLTAGE_120:
+                /* We don't support 3V3 and 1V2 */
+                break;
+        }
+
+        return -EINVAL;
+}
+
 static struct sdhci_ops sdhci_arasan_ops = {
         .set_clock = sdhci_arasan_set_clock,
         .get_max_clock = sdhci_pltfm_clk_get_max_clock,
@@ -661,6 +683,8 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 
                 host->mmc_host_ops.hs400_enhanced_strobe =
                                         sdhci_arasan_hs400_enhanced_strobe;
+                host->mmc_host_ops.start_signal_voltage_switch =
+                                        sdhci_arasan_voltage_switch;
         }
 
         ret = sdhci_add_host(host);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 72a1f1f5180a..1d9e00a00e9f 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -32,6 +32,14 @@
 #include "sdhci-pci.h"
 #include "sdhci-pci-o2micro.h"
 
+static int sdhci_pci_enable_dma(struct sdhci_host *host);
+static void sdhci_pci_set_bus_width(struct sdhci_host *host, int width);
+static void sdhci_pci_hw_reset(struct sdhci_host *host);
+static int sdhci_pci_select_drive_strength(struct sdhci_host *host,
+                                           struct mmc_card *card,
+                                           unsigned int max_dtr, int host_drv,
+                                           int card_drv, int *drv_type);
+
 /*****************************************************************************\
  *                                                                           *
  * Hardware specific quirk handling                                          *
@@ -390,6 +398,45 @@ static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
         return 0;
 }
 
+#define SDHCI_INTEL_PWR_TIMEOUT_CNT     20
+#define SDHCI_INTEL_PWR_TIMEOUT_UDELAY  100
+
+static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode,
+                                  unsigned short vdd)
+{
+        int cntr;
+        u8 reg;
+
+        sdhci_set_power(host, mode, vdd);
+
+        if (mode == MMC_POWER_OFF)
+                return;
+
+        /*
+         * Bus power might not enable after D3 -> D0 transition due to the
+         * present state not yet having propagated. Retry for up to 2ms.
+         */
+        for (cntr = 0; cntr < SDHCI_INTEL_PWR_TIMEOUT_CNT; cntr++) {
+                reg = sdhci_readb(host, SDHCI_POWER_CONTROL);
+                if (reg & SDHCI_POWER_ON)
+                        break;
+                udelay(SDHCI_INTEL_PWR_TIMEOUT_UDELAY);
+                reg |= SDHCI_POWER_ON;
+                sdhci_writeb(host, reg, SDHCI_POWER_CONTROL);
+        }
+}
+
+static const struct sdhci_ops sdhci_intel_byt_ops = {
+        .set_clock              = sdhci_set_clock,
+        .set_power              = sdhci_intel_set_power,
+        .enable_dma             = sdhci_pci_enable_dma,
+        .set_bus_width          = sdhci_pci_set_bus_width,
+        .reset                  = sdhci_reset,
+        .set_uhs_signaling      = sdhci_set_uhs_signaling,
+        .hw_reset               = sdhci_pci_hw_reset,
+        .select_drive_strength  = sdhci_pci_select_drive_strength,
+};
+
 static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
         .allow_runtime_pm = true,
         .probe_slot     = byt_emmc_probe_slot,
@@ -397,6 +444,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
         .quirks2        = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
                           SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 |
                           SDHCI_QUIRK2_STOP_WITH_TC,
+        .ops            = &sdhci_intel_byt_ops,
 };
 
 static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = {
@@ -405,6 +453,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = {
                         SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
         .allow_runtime_pm = true,
         .probe_slot     = byt_sdio_probe_slot,
+        .ops            = &sdhci_intel_byt_ops,
 };
 
 static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
@@ -415,6 +464,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
         .allow_runtime_pm = true,
         .own_cd_for_runtime_pm = true,
         .probe_slot     = byt_sd_probe_slot,
+        .ops            = &sdhci_intel_byt_ops,
 };
 
 /* Define Host controllers for Intel Merrifield platform */
@@ -1648,7 +1698,9 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
         }
 
         host->hw_name = "PCI";
-        host->ops = &sdhci_pci_ops;
+        host->ops = chip->fixes && chip->fixes->ops ?
+                    chip->fixes->ops :
+                    &sdhci_pci_ops;
         host->quirks = chip->quirks;
         host->quirks2 = chip->quirks2;
 
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 9c7c08b93223..6bccf56bc5ff 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -65,6 +65,8 @@ struct sdhci_pci_fixes {
 
         int                     (*suspend) (struct sdhci_pci_chip *);
         int                     (*resume) (struct sdhci_pci_chip *);
+
+        const struct sdhci_ops  *ops;
 };
 
 struct sdhci_pci_slot {
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index dd1938d341f7..d0f5c05fbc19 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -315,7 +315,7 @@ static void pxav3_set_power(struct sdhci_host *host, unsigned char mode,
         struct mmc_host *mmc = host->mmc;
         u8 pwr = host->pwr;
 
-        sdhci_set_power(host, mode, vdd);
+        sdhci_set_power_noreg(host, mode, vdd);
 
         if (host->pwr == pwr)
                 return;
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 48055666c655..71654b90227f 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -687,7 +687,7 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
                          * host->clock is in Hz.  target_timeout is in us.
                          * Hence, us = 1000000 * cycles / Hz.  Round up.
                          */
-                        val = 1000000 * data->timeout_clks;
+                        val = 1000000ULL * data->timeout_clks;
                         if (do_div(val, host->clock))
                                 target_timeout++;
                         target_timeout += val;
@@ -1077,6 +1077,10 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
         /* Initially, a command has no error */
         cmd->error = 0;
 
+        if ((host->quirks2 & SDHCI_QUIRK2_STOP_WITH_TC) &&
+            cmd->opcode == MMC_STOP_TRANSMISSION)
+                cmd->flags |= MMC_RSP_BUSY;
+
         /* Wait max 10 ms */
         timeout = 10;
 
@@ -1390,8 +1394,8 @@ static void sdhci_set_power_reg(struct sdhci_host *host, unsigned char mode,
                 sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
 }
 
-void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
-                     unsigned short vdd)
+void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode,
+                           unsigned short vdd)
 {
         u8 pwr = 0;
 
@@ -1455,20 +1459,17 @@ void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
                         mdelay(10);
         }
 }
-EXPORT_SYMBOL_GPL(sdhci_set_power);
+EXPORT_SYMBOL_GPL(sdhci_set_power_noreg);
 
-static void __sdhci_set_power(struct sdhci_host *host, unsigned char mode,
-                              unsigned short vdd)
+void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
+                     unsigned short vdd)
 {
-        struct mmc_host *mmc = host->mmc;
-
-        if (host->ops->set_power)
-                host->ops->set_power(host, mode, vdd);
-        else if (!IS_ERR(mmc->supply.vmmc))
-                sdhci_set_power_reg(host, mode, vdd);
+        if (IS_ERR(host->mmc->supply.vmmc))
+                sdhci_set_power_noreg(host, mode, vdd);
         else
-                sdhci_set_power(host, mode, vdd);
+                sdhci_set_power_reg(host, mode, vdd);
 }
+EXPORT_SYMBOL_GPL(sdhci_set_power);
 
 /*****************************************************************************\
  *                                                                           *
@@ -1609,7 +1610,10 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
                 }
         }
 
-        __sdhci_set_power(host, ios->power_mode, ios->vdd);
+        if (host->ops->set_power)
+                host->ops->set_power(host, ios->power_mode, ios->vdd);
+        else
+                sdhci_set_power(host, ios->power_mode, ios->vdd);
 
         if (host->ops->platform_send_init_74_clocks)
                 host->ops->platform_send_init_74_clocks(host, ios->power_mode);
@@ -2409,7 +2413,7 @@ static void sdhci_timeout_data_timer(unsigned long data)
  *                                                                           *
 \*****************************************************************************/
 
-static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
+static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
 {
         if (!host->cmd) {
                 /*
@@ -2453,11 +2457,6 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
                 return;
         }
 
-        if ((host->quirks2 & SDHCI_QUIRK2_STOP_WITH_TC) &&
-            !(host->cmd->flags & MMC_RSP_BUSY) && !host->data &&
-            host->cmd->opcode == MMC_STOP_TRANSMISSION)
-                *mask &= ~SDHCI_INT_DATA_END;
-
         if (intmask & SDHCI_INT_RESPONSE)
                 sdhci_finish_command(host);
 }
@@ -2680,8 +2679,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
                 }
 
                 if (intmask & SDHCI_INT_CMD_MASK)
-                        sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK,
-                                      &intmask);
+                        sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK);
 
                 if (intmask & SDHCI_INT_DATA_MASK)
                         sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK);
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index c722cd23205c..766df17fb7eb 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -683,6 +683,8 @@ u16 sdhci_calc_clk(struct sdhci_host *host, unsigned int clock,
 void sdhci_set_clock(struct sdhci_host *host, unsigned int clock);
 void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
                      unsigned short vdd);
+void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode,
+                           unsigned short vdd);
 void sdhci_set_bus_width(struct sdhci_host *host, int width);
 void sdhci_reset(struct sdhci_host *host, u8 mask);
 void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing);
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 95c4048a371e..388e46be6ad9 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -741,6 +741,7 @@ static int try_recover_peb(struct ubi_volume *vol, int pnum, int lnum,
                 goto out_put;
         }
 
+        vid_hdr = ubi_get_vid_hdr(vidb);
         ubi_assert(vid_hdr->vol_type == UBI_VID_DYNAMIC);
 
         mutex_lock(&ubi->buf_mutex);
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index d6384d965788..c1f5c29e458e 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -287,7 +287,7 @@ static int update_vol(struct ubi_device *ubi, struct ubi_attach_info *ai,
 
                 /* new_aeb is newer */
                 if (cmp_res & 1) {
-                        victim = ubi_alloc_aeb(ai, aeb->ec, aeb->pnum);
+                        victim = ubi_alloc_aeb(ai, aeb->pnum, aeb->ec);
                         if (!victim)
                                 return -ENOMEM;
 
@@ -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 76fb8552c9d9..ef63d24fef81 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 e218887f18b7..e3ee27ce13dd 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 b047fd607b83..00c38bf151e6 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 ae364c74baf3..537090952c45 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1126,7 +1126,8 @@ out_freeirq:
         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 856379cbb402..31ca204b38d2 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 27f11a5d5fe2..b3791b394715 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 20fe6a8c35c1..0cee4c0283f9 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 f320497368f4..57eb4e1345cb 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 0945fa49a5dd..2471ff465d5c 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 539de764bbd3..cbd68a8fe2e4 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 e572a527b18d..36bc2c71fba9 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);
 
-        vdev_neterr(vdev, "Failed to disable RQ[%d]\n", rq->index);
+                        return -ETIMEDOUT;
+                }
+        }
 
-        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 f928e6f79c89..223f35cc034c 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 48a033e64423..5aa9d4ded214 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 8d70377f6624..8ea3d95fa483 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 33f4c483af0f..501eb2090ca6 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 bfe17d9c022d..5f44c5520fbc 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 bfc84c7d0e11..dd775d951b73 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 2030d7c1dc94..6d61e443bdf8 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 ac1faee2a5b8..31c97e3937a4 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 a244d9a67264..bd93d823cc25 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 55831188bc32..bf5cc55ba24c 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 b1cef7a0f7ca..e36bebcab3f2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2469,6 +2469,7 @@ err_comm_admin:
         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 08fc5fc56d43..a5fc46bbcbe2 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 132cea655920..e3be7e44ff51 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 7e703bed7b82..12c99a2655f2 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 5aa8b751f417..59473a0ebcdf 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 b66e03d9711f..c06346a82496 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -118,6 +118,29 @@ mlx4_en_test_loopback_exit:
         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 cf8f8a72a801..cd3638e6fe25 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;
-
-        /* 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;
-                }
+        /* Temporary use polling for command completions */
+        mlx4_cmd_use_polling(dev);
 
-                /* 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 c41ab31a39f8..84bab9f0732e 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 7183ac4135d2..6f4e67bc3538 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 e4878f31e45d..88ee7d8a5923 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 c5b2064297a1..b656dd5772e5 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 84d7857ccc27..c548beaaf910 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 6cb38304669f..2c6e3c7b7417 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 460363b66cb1..7a43502a89cc 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 7eaf38020a8f..f4c687ce4c59 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 3c97da103d30..7fe6559e4ab3 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 abbf2c369923..be1f7333ab7f 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 @@ out:
                 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 @@ out:
         }
 
         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 5da2cc878582..89696048b045 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 3a9195b4169d..3b026c151cf2 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 1a05fb965c8d..5bcf93422ee0 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 @@ unlock:
 
 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 d9c3c70b29e4..d5433c49b2b0 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 3d0cfb9f18f9..187662c8ea96 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 cc4fd61914d3..a57d5a81eb05 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;
-
-out_mapping:
-        dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+err_mapping:
+        if (err)
+                __free_page(page);
 
-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 e742bd4e8894..912f71f84209 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 78fc557d6dd7..4573da2c5560 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 @@ err_fib_entry_insert:
         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 c0c23e2f3275..92bda8703f87 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1088,6 +1088,7 @@ err_port_stp_state_set:
 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 1e8339a67f6e..32f2a45f4ab2 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -107,4 +107,7 @@ config QEDE
         ---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 cda0af7fbc20..967acf322c09 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -5,4 +5,4 @@ qed-y := qed_cxt.o qed_dev.o qed_hw.o qed_init_fw_funcs.o qed_init_ops.o \
          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 82370a1a59ad..0c42c240b5cf 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 130da1c0490b..a4789a93b692 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 88e7d5bef909..68f19ca57f96 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 754f6a908858..edae5fc5fccd 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 02a8be2faed7..63e1a1b0ef8e 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 80a5dc2d652d..4e3d62a16cab 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 4ee3151e80c2..c418360ba02a 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 76831a398bed..f3a825a8f8d5 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 @@ free_rdma_info:
         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 @@ out:
         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 @@ err:
         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 @@ err:
         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 @@ err_resp:
         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 2f091e8a0f40..279f342af8db 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 652c90819758..b2c08e4d2a9b 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 caff41544898..9fbaf9429fd0 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 28dc58919c85..048a230c3ce0 100644
--- a/drivers/net/ethernet/qlogic/qede/Makefile
+++ b/drivers/net/ethernet/qlogic/qede/Makefile
@@ -2,4 +2,4 @@ obj-$(CONFIG_QEDE) := qede.o
 
 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 28c0e9f42c9e..974689a13337 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 25a9b293ee8f..12251a1032d1 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 343038ca047d..7def29aaf65c 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 e97968ed4b8f..6fb3bee904d3 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 9bf3b2b82e95..4fede4b86538 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 e55638c7505a..bf000d819a21 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 5424fb341613..24b746406bc7 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 431a60804272..4ca461322d60 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 4ec7397e7fb3..a1b17cd7886b 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 8dc9056c1001..b15fc55f1b96 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 6c85b61aaa0b..48e71fad4210 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 289d52725a6c..1477471f8d44 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 0d0053128542..5eedac495077 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 3c20e87bb761..42edd7b7902f 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 @@ out:
         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 f0919bd3a563..f6382150b16a 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 3ea47f28e143..d2e61e002926 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 f279a897a5c7..a52b560e428b 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 @@ done:
 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 03d54c4adc88..800b39f06279 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 f79eb12c326a..125cff57c759 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 5662babf0583..3e37724d30ae 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 b5554f2ebee4..ef83ae3b0a44 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 85c271c70d42..820de6a9ddde 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 e7d16687538b..f3c2fa3ab0d5 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 33ab3345d333..4e9fe75d7067 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -294,7 +294,7 @@ config FSL_UCC_HDLC
 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 d06a887a2352..b776a0ab106c 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 dda49af1eb74..521f1c55c19e 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 832da6ed9f13..82a4c67f3672 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);
-
-        if (ar->state != ATH10K_STATE_ON &&
-            ar->state != ATH10K_STATE_UTF) {
-                ret = -ENETDOWN;
-                goto err;
-        }
+        lockdep_assert_held(&ar->conf_mutex);
 
-        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;
+}
 
-        mutex_unlock(&ar->conf_mutex);
+static int ath10k_debug_cal_data_open(struct inode *inode, struct file *file)
+{
+        struct ath10k *ar = inode->i_private;
 
-        return 0;
+        mutex_lock(&ar->conf_mutex);
 
-err_vfree:
-        vfree(buf);
+        if (ar->state == ATH10K_STATE_ON ||
+            ar->state == ATH10K_STATE_UTF) {
+                ath10k_debug_cal_data_fetch(ar);
+        }
 
-err:
+        file->private_data = ar;
         mutex_unlock(&ar->conf_mutex);
 
-        return ret;
+        return 0;
 }
 
 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 eab0ab976af2..76eb33679d4b 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 b6f064a8d264..7e27a06e5df1 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 2a5d3ad1169c..9cbca1229bac 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 94480123efa3..274dd5a1574a 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 1016628926d2..08d587a342d3 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 df54d27e7851..a793fedc3654 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 6c086b5657e9..02b8ddd98a95 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 b2d7f6e69667..a5e6ec2152bf 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 f95760c13c56..8e7f23c11680 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 e7b11b40e68d..f361808def47 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 87aa209ae325..8b6e37ce3f66 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 7c6f7f0d18c6..f953320f0e23 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 0538a4d09568..1ebfee18882f 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 ac299cbe59b0..46b605de36e7 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 5e8e02d5de8a..3e1eaeac4fdc 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 89c828ad89f4..c51a9e8234e9 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 20b53f035483..847644d1f5f5 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 22f687b1f133..297938e0effd 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 595f7d5d091a..dafe486f8448 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 a6e94b1a12cb..47fe7f96a242 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 8b2b740d6679..124c2432ac9c 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -89,7 +89,7 @@ config NVDIMM_PFN
           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 3509cff68ef9..abe5c6bc756c 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 42b3a8217073..24618431a14b 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/nvme/host/core.c b/drivers/nvme/host/core.c
index 329381a28edf..79e679d12f3b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -554,7 +554,7 @@ int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 
         /* gcc-4.4.4 (at least) has issues with initializers and anon unions */
         c.identify.opcode = nvme_admin_identify;
-        c.identify.cns = cpu_to_le32(1);
+        c.identify.cns = cpu_to_le32(NVME_ID_CNS_CTRL);
 
         *id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
         if (!*id)
@@ -572,7 +572,7 @@ static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *n
         struct nvme_command c = { };
 
         c.identify.opcode = nvme_admin_identify;
-        c.identify.cns = cpu_to_le32(2);
+        c.identify.cns = cpu_to_le32(NVME_ID_CNS_NS_ACTIVE_LIST);
         c.identify.nsid = cpu_to_le32(nsid);
         return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000);
 }
@@ -900,9 +900,9 @@ static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
                 return -ENODEV;
         }
 
-        if (ns->ctrl->vs >= NVME_VS(1, 1))
+        if (ns->ctrl->vs >= NVME_VS(1, 1, 0))
                 memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui));
-        if (ns->ctrl->vs >= NVME_VS(1, 2))
+        if (ns->ctrl->vs >= NVME_VS(1, 2, 0))
                 memcpy(ns->uuid, (*id)->nguid, sizeof(ns->uuid));
 
         return 0;
@@ -1086,6 +1086,8 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
         int ret;
 
         while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
+                if (csts == ~0)
+                        return -ENODEV;
                 if ((csts & NVME_CSTS_RDY) == bit)
                         break;
 
@@ -1240,7 +1242,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
         }
         page_shift = NVME_CAP_MPSMIN(cap) + 12;
 
-        if (ctrl->vs >= NVME_VS(1, 1))
+        if (ctrl->vs >= NVME_VS(1, 1, 0))
                 ctrl->subsystem = NVME_CAP_NSSRC(cap);
 
         ret = nvme_identify_ctrl(ctrl, &id);
@@ -1840,7 +1842,7 @@ static void nvme_scan_work(struct work_struct *work)
                 return;
 
         nn = le32_to_cpu(id->nn);
-        if (ctrl->vs >= NVME_VS(1, 1) &&
+        if (ctrl->vs >= NVME_VS(1, 1, 0) &&
             !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
                 if (!nvme_scan_ns_list(ctrl, nn))
                         goto done;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 0fc99f0f2571..0248d0e21fee 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -99,6 +99,7 @@ struct nvme_dev {
         dma_addr_t cmb_dma_addr;
         u64 cmb_size;
         u32 cmbsz;
+        u32 cmbloc;
         struct nvme_ctrl ctrl;
         struct completion ioq_wait;
 };
@@ -893,7 +894,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
                          "I/O %d QID %d timeout, reset controller\n",
                          req->tag, nvmeq->qid);
                 nvme_dev_disable(dev, false);
-                queue_work(nvme_workq, &dev->reset_work);
+                nvme_reset(dev);
 
                 /*
                  * Mark the request as handled, since the inline shutdown
@@ -1214,7 +1215,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
         u64 cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
         struct nvme_queue *nvmeq;
 
-        dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1) ?
+        dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1, 0) ?
                                                 NVME_CAP_NSSRC(cap) : 0;
 
         if (dev->subsystem &&
@@ -1291,7 +1292,7 @@ static void nvme_watchdog_timer(unsigned long data)
 
         /* Skip controllers under certain specific conditions. */
         if (nvme_should_reset(dev, csts)) {
-                if (queue_work(nvme_workq, &dev->reset_work))
+                if (!nvme_reset(dev))
                         dev_warn(dev->dev,
                                 "Failed status: 0x%x, reset controller.\n",
                                 csts);
@@ -1331,28 +1332,37 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
         return ret >= 0 ? 0 : ret;
 }
 
+static ssize_t nvme_cmb_show(struct device *dev,
+                             struct device_attribute *attr,
+                             char *buf)
+{
+        struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+        return snprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz  : x%08x\n",
+                       ndev->cmbloc, ndev->cmbsz);
+}
+static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
+
 static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
 {
         u64 szu, size, offset;
-        u32 cmbloc;
         resource_size_t bar_size;
         struct pci_dev *pdev = to_pci_dev(dev->dev);
         void __iomem *cmb;
         dma_addr_t dma_addr;
 
-        if (!use_cmb_sqes)
-                return NULL;
-
         dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
         if (!(NVME_CMB_SZ(dev->cmbsz)))
                 return NULL;
+        dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
 
-        cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
+        if (!use_cmb_sqes)
+                return NULL;
 
         szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
         size = szu * NVME_CMB_SZ(dev->cmbsz);
-        offset = szu * NVME_CMB_OFST(cmbloc);
-        bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
+        offset = szu * NVME_CMB_OFST(dev->cmbloc);
+        bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc));
 
         if (offset > bar_size)
                 return NULL;
@@ -1365,7 +1375,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
         if (size > bar_size - offset)
                 size = bar_size - offset;
 
-        dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) + offset;
+        dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset;
         cmb = ioremap_wc(dma_addr, size);
         if (!cmb)
                 return NULL;
@@ -1511,9 +1521,9 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
         return 0;
 }
 
-static void nvme_disable_io_queues(struct nvme_dev *dev)
+static void nvme_disable_io_queues(struct nvme_dev *dev, int queues)
 {
-        int pass, queues = dev->online_queues - 1;
+        int pass;
         unsigned long timeout;
         u8 opcode = nvme_admin_delete_sq;
 
@@ -1616,9 +1626,25 @@ static int nvme_pci_enable(struct nvme_dev *dev)
                         dev->q_depth);
         }
 
-        if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2))
+        /*
+         * CMBs can currently only exist on >=1.2 PCIe devices. We only
+         * populate sysfs if a CMB is implemented. Note that we add the
+         * CMB attribute to the nvme_ctrl kobj which removes the need to remove
+         * it on exit. Since nvme_dev_attrs_group has no name we can pass
+         * NULL as final argument to sysfs_add_file_to_group.
+         */
+
+        if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2, 0)) {
                 dev->cmb = nvme_map_cmb(dev);
 
+                if (dev->cmbsz) {
+                        if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
+                                                    &dev_attr_cmb.attr, NULL))
+                                dev_warn(dev->dev,
+                                         "failed to add sysfs attribute for CMB\n");
+                }
+        }
+
         pci_enable_pcie_error_reporting(pdev);
         pci_save_state(pdev);
         return 0;
@@ -1649,7 +1675,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
 
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 {
-        int i;
+        int i, queues;
         u32 csts = -1;
 
         del_timer_sync(&dev->watchdog_timer);
@@ -1660,6 +1686,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
                 csts = readl(dev->bar + NVME_REG_CSTS);
         }
 
+        queues = dev->online_queues - 1;
         for (i = dev->queue_count - 1; i > 0; i--)
                 nvme_suspend_queue(dev->queues[i]);
 
@@ -1671,7 +1698,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
                 if (dev->queue_count)
                         nvme_suspend_queue(dev->queues[0]);
         } else {
-                nvme_disable_io_queues(dev);
+                nvme_disable_io_queues(dev, queues);
                 nvme_disable_admin_queue(dev, shutdown);
         }
         nvme_pci_disable(dev);
@@ -1818,11 +1845,10 @@ static int nvme_reset(struct nvme_dev *dev)
 {
         if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q))
                 return -ENODEV;
-
+        if (work_busy(&dev->reset_work))
+                return -ENODEV;
         if (!queue_work(nvme_workq, &dev->reset_work))
                 return -EBUSY;
-
-        flush_work(&dev->reset_work);
         return 0;
 }
 
@@ -1846,7 +1872,12 @@ static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 
 static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
 {
-        return nvme_reset(to_nvme_dev(ctrl));
+        struct nvme_dev *dev = to_nvme_dev(ctrl);
+        int ret = nvme_reset(dev);
+
+        if (!ret)
+                flush_work(&dev->reset_work);
+        return ret;
 }
 
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
@@ -1940,7 +1971,7 @@ static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
         if (prepare)
                 nvme_dev_disable(dev, false);
         else
-                queue_work(nvme_workq, &dev->reset_work);
+                nvme_reset(dev);
 }
 
 static void nvme_shutdown(struct pci_dev *pdev)
@@ -2009,7 +2040,7 @@ static int nvme_resume(struct device *dev)
         struct pci_dev *pdev = to_pci_dev(dev);
         struct nvme_dev *ndev = pci_get_drvdata(pdev);
 
-        queue_work(nvme_workq, &ndev->reset_work);
+        nvme_reset(ndev);
         return 0;
 }
 #endif
@@ -2048,7 +2079,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
         dev_info(dev->ctrl.device, "restart after slot reset\n");
         pci_restore_state(pdev);
-        queue_work(nvme_workq, &dev->reset_work);
+        nvme_reset(dev);
         return PCI_ERS_RESULT_RECOVERED;
 }
 
diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c
index c2a0a1c7d05d..3eaa4d27801e 100644
--- a/drivers/nvme/host/scsi.c
+++ b/drivers/nvme/host/scsi.c
@@ -606,7 +606,7 @@ static int nvme_fill_device_id_eui64(struct nvme_ns *ns, struct sg_io_hdr *hdr,
         eui = id_ns->eui64;
         len = sizeof(id_ns->eui64);
 
-        if (ns->ctrl->vs >= NVME_VS(1, 2)) {
+        if (ns->ctrl->vs >= NVME_VS(1, 2, 0)) {
                 if (bitmap_empty(eui, len * 8)) {
                         eui = id_ns->nguid;
                         len = sizeof(id_ns->nguid);
@@ -679,7 +679,7 @@ static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 {
         int res;
 
-        if (ns->ctrl->vs >= NVME_VS(1, 1)) {
+        if (ns->ctrl->vs >= NVME_VS(1, 1, 0)) {
                 res = nvme_fill_device_id_eui64(ns, hdr, resp, alloc_len);
                 if (res != -EOPNOTSUPP)
                         return res;
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 7ab9c9381b98..6fe4c48a21e4 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -199,7 +199,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
          */
 
         /* we support multiple ports and multiples hosts: */
-        id->mic = (1 << 0) | (1 << 1);
+        id->cmic = (1 << 0) | (1 << 1);
 
         /* no limit on data transfer sizes for now */
         id->mdts = 0;
@@ -511,13 +511,13 @@ int nvmet_parse_admin_cmd(struct nvmet_req *req)
         case nvme_admin_identify:
                 req->data_len = 4096;
                 switch (le32_to_cpu(cmd->identify.cns)) {
-                case 0x00:
+                case NVME_ID_CNS_NS:
                         req->execute = nvmet_execute_identify_ns;
                         return 0;
-                case 0x01:
+                case NVME_ID_CNS_CTRL:
                         req->execute = nvmet_execute_identify_ctrl;
                         return 0;
-                case 0x02:
+                case NVME_ID_CNS_NS_ACTIVE_LIST:
                         req->execute = nvmet_execute_identify_nslist;
                         return 0;
                 }
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 6559d5afa7bf..b4cacb6f0258 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -882,7 +882,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
         if (!subsys)
                 return NULL;
 
-        subsys->ver = (1 << 16) | (2 << 8) | 1; /* NVMe 1.2.1 */
+        subsys->ver = NVME_VS(1, 2, 1); /* NVMe 1.2.1 */
 
         switch (type) {
         case NVME_NQN_NVME:
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 6f65646e89cf..12f39eea569f 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -54,7 +54,7 @@ static void nvmet_format_discovery_entry(struct nvmf_disc_rsp_page_hdr *hdr,
         /* we support only dynamic controllers */
         e->cntlid = cpu_to_le16(NVME_CNTLID_DYNAMIC);
         e->asqsz = cpu_to_le16(NVMF_AQ_DEPTH);
-        e->nqntype = type;
+        e->subtype = type;
         memcpy(e->trsvcid, port->disc_addr.trsvcid, NVMF_TRSVCID_SIZE);
         memcpy(e->traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
         memcpy(e->tsas.common, port->disc_addr.tsas.common, NVMF_TSAS_SIZE);
@@ -187,7 +187,7 @@ int nvmet_parse_discovery_cmd(struct nvmet_req *req)
         case nvme_admin_identify:
                 req->data_len = 4096;
                 switch (le32_to_cpu(cmd->identify.cns)) {
-                case 0x01:
+                case NVME_ID_CNS_CTRL:
                         req->execute =
                                 nvmet_execute_identify_disc_ctrl;
                         return 0;
diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c
index 2cb7315e26d0..653707996342 100644
--- a/drivers/pci/host/pci-layerscape.c
+++ b/drivers/pci/host/pci-layerscape.c
@@ -247,6 +247,7 @@ static int __init ls_pcie_probe(struct platform_device *pdev)
 
         pp = &pcie->pp;
         pp->dev = dev;
+        pcie->drvdata = match->data;
         pp->ops = pcie->drvdata->ops;
 
         dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
@@ -256,7 +257,6 @@ static int __init ls_pcie_probe(struct platform_device *pdev)
                 return PTR_ERR(pcie->pp.dbi_base);
         }
 
-        pcie->drvdata = match->data;
         pcie->lut = pcie->pp.dbi_base + pcie->drvdata->lut_offset;
 
         if (!ls_pcie_is_bridge(pcie))
diff --git a/drivers/pci/host/pcie-designware-plat.c b/drivers/pci/host/pcie-designware-plat.c
index 537f58a664fa..8df6312ed300 100644
--- a/drivers/pci/host/pcie-designware-plat.c
+++ b/drivers/pci/host/pcie-designware-plat.c
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com)
  *
- * Authors: Joao Pinto <jpinto@synopsys.com>
+ * Authors: Joao Pinto <jpmpinto@gmail.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index bfdd0744b686..ad70507cfb56 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/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index c2ac7646b99f..a8ac4bcef2c0 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1011,7 +1011,7 @@ xgene_pmu_dev_ctx *acpi_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu,
         rc = acpi_dev_get_resources(adev, &resource_list,
                                     acpi_pmu_dev_add_resource, &res);
         acpi_dev_free_resource_list(&resource_list);
-        if (rc < 0 || IS_ERR(&res)) {
+        if (rc < 0) {
                 dev_err(dev, "PMU type %d: No resource address found\n", type);
                 goto err;
         }
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 67426c0477d3..5c1519b229e0 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 8b2558e7363e..968c3ae4535c 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 831935af7389..a7a88476e215 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 46be25c7461e..876c7e6e3a99 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/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index 637cf8973c9e..581001989937 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -384,7 +384,7 @@ void zfcp_dbf_san(char *tag, struct zfcp_dbf *dbf,
         /* if (len > rec_len):
          * dump data up to cap_len ignoring small duplicate in rec->payload
          */
-        spin_lock_irqsave(&dbf->pay_lock, flags);
+        spin_lock(&dbf->pay_lock);
         memset(payload, 0, sizeof(*payload));
         memcpy(payload->area, paytag, ZFCP_DBF_TAG_LEN);
         payload->fsf_req_id = req_id;
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index db2739079cbb..790babc5ef66 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/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 68138a647dfc..d9239c2d49b1 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/ipr.c b/drivers/scsi/ipr.c
index a8762a3efeef..532474109624 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -2586,7 +2586,6 @@ static void ipr_process_error(struct ipr_cmnd *ipr_cmd)
         struct ipr_hostrcb *hostrcb = ipr_cmd->u.hostrcb;
         u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc);
         u32 fd_ioasc;
-        char *envp[] = { "ASYNC_ERR_LOG=1", NULL };
 
         if (ioa_cfg->sis64)
                 fd_ioasc = be32_to_cpu(hostrcb->hcam.u.error64.fd_ioasc);
@@ -2607,8 +2606,8 @@ static void ipr_process_error(struct ipr_cmnd *ipr_cmd)
         }
 
         list_add_tail(&hostrcb->queue, &ioa_cfg->hostrcb_report_q);
+        schedule_work(&ioa_cfg->work_q);
         hostrcb = ipr_get_free_hostrcb(ioa_cfg);
-        kobject_uevent_env(&ioa_cfg->host->shost_dev.kobj, KOBJ_CHANGE, envp);
 
         ipr_send_hcam(ioa_cfg, IPR_HCAM_CDB_OP_CODE_LOG_DATA, hostrcb);
 }
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index c051694bfcb0..f9b6fba689ff 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/scsi_dh.c b/drivers/scsi/scsi_dh.c
index 54d446c9f56e..b8d3b97b217a 100644
--- a/drivers/scsi/scsi_dh.c
+++ b/drivers/scsi/scsi_dh.c
@@ -36,9 +36,9 @@ struct scsi_dh_blist {
 };
 
 static const struct scsi_dh_blist scsi_dh_blist[] = {
-        {"DGC", "RAID",                 "clariion" },
-        {"DGC", "DISK",                 "clariion" },
-        {"DGC", "VRAID",                "clariion" },
+        {"DGC", "RAID",                 "emc" },
+        {"DGC", "DISK",                 "emc" },
+        {"DGC", "VRAID",                "emc" },
 
         {"COMPAQ", "MSA1000 VOLUME",    "hp_sw" },
         {"COMPAQ", "HSV110",            "hp_sw" },
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 212e98d940bc..6f7128f49c30 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -1307,7 +1307,6 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget,
 static int scsi_report_lun_scan(struct scsi_target *starget, int bflags,
                                 enum scsi_scan_mode rescan)
 {
-        char devname[64];
         unsigned char scsi_cmd[MAX_COMMAND_SIZE];
         unsigned int length;
         u64 lun;
@@ -1349,9 +1348,6 @@ static int scsi_report_lun_scan(struct scsi_target *starget, int bflags,
                 }
         }
 
-        sprintf(devname, "host %d channel %d id %d",
-                shost->host_no, sdev->channel, sdev->id);
-
         /*
          * Allocate enough to hold the header (the same size as one scsi_lun)
          * plus the number of luns we are requesting.  511 was the default
@@ -1470,12 +1466,12 @@ retry:
  out_err:
         kfree(lun_data);
  out:
-        scsi_device_put(sdev);
         if (scsi_device_created(sdev))
                 /*
                  * the sdev we used didn't appear in the report luns scan
                  */
                 __scsi_remove_device(sdev);
+        scsi_device_put(sdev);
         return ret;
 }
 
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 35c0dd945668..a67b0ff6a362 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 7451585a080e..2c175b9495f7 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 5787b723b593..838783c3fed0 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 396ded52ab70..209a8f7ef02b 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 15bac92b7f04..46b2bb99bfd6 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 e36ee984485b..34307ac3f255 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 071bb1cfd3ae..baab460eeaa3 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 5e06e4229e42..250caa00de5e 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 69f67ddbd4a3..660b4674a76f 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 5ee7954bd9f9..2633d2bfb1b4 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 d626125d7af9..564b36d4f648 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 6eae60595905..23fda9d98bff 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/wilc1000/host_interface.c b/drivers/staging/wilc1000/host_interface.c
index 78f5613e9467..6ab7443eabde 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/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 39b928c2849d..b7d747e92c7a 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1804,6 +1804,10 @@ int iscsit_process_nop_out(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
          * Otherwise, initiator is not expecting a NOPIN is response.
          * Just ignore for now.
          */
+
+        if (cmd)
+                iscsit_free_cmd(cmd, false);
+
         return 0;
 }
 EXPORT_SYMBOL(iscsit_process_nop_out);
@@ -2982,7 +2986,7 @@ iscsit_build_nopin_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
 
         pr_debug("Built NOPIN %s Response ITT: 0x%08x, TTT: 0x%08x,"
                 " StatSN: 0x%08x, Length %u\n", (nopout_response) ?
-                "Solicitied" : "Unsolicitied", cmd->init_task_tag,
+                "Solicited" : "Unsolicited", cmd->init_task_tag,
                 cmd->targ_xfer_tag, cmd->stat_sn, cmd->buf_ptr_size);
 }
 EXPORT_SYMBOL(iscsit_build_nopin_rsp);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index adf419fa4291..15f79a2ca34a 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -434,7 +434,7 @@ static int iscsi_login_zero_tsih_s2(
 
                 /*
                  * Make MaxRecvDataSegmentLength PAGE_SIZE aligned for
-                 * Immediate Data + Unsolicitied Data-OUT if necessary..
+                 * Immediate Data + Unsolicited Data-OUT if necessary..
                  */
                 param = iscsi_find_param_from_key("MaxRecvDataSegmentLength",
                                                   conn->param_list);
@@ -646,7 +646,7 @@ static void iscsi_post_login_start_timers(struct iscsi_conn *conn)
 {
         struct iscsi_session *sess = conn->sess;
         /*
-         * FIXME: Unsolicitied NopIN support for ISER
+         * FIXME: Unsolicited NopIN support for ISER
          */
         if (conn->conn_transport->transport_type == ISCSI_INFINIBAND)
                 return;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 6094a6beddde..7dfefd66df93 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -754,15 +754,7 @@ EXPORT_SYMBOL(target_complete_cmd);
 
 void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length)
 {
-        if (scsi_status != SAM_STAT_GOOD) {
-                return;
-        }
-
-        /*
-         * Calculate new residual count based upon length of SCSI data
-         * transferred.
-         */
-        if (length < cmd->data_length) {
+        if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) {
                 if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
                         cmd->residual_count += cmd->data_length - length;
                 } else {
@@ -771,12 +763,6 @@ void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int len
                 }
 
                 cmd->data_length = length;
-        } else if (length > cmd->data_length) {
-                cmd->se_cmd_flags |= SCF_OVERFLOW_BIT;
-                cmd->residual_count = length - cmd->data_length;
-        } else {
-                cmd->se_cmd_flags &= ~(SCF_OVERFLOW_BIT | SCF_UNDERFLOW_BIT);
-                cmd->residual_count = 0;
         }
 
         target_complete_cmd(cmd, scsi_status);
@@ -1706,6 +1692,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
         case TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED:
         case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED:
         case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED:
+        case TCM_COPY_TARGET_DEVICE_NOT_REACHABLE:
                 break;
         case TCM_OUT_OF_RESOURCES:
                 sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -2547,8 +2534,12 @@ int target_get_sess_cmd(struct se_cmd *se_cmd, bool ack_kref)
          * fabric acknowledgement that requires two target_put_sess_cmd()
          * invocations before se_cmd descriptor release.
          */
-        if (ack_kref)
-                kref_get(&se_cmd->cmd_kref);
+        if (ack_kref) {
+                if (!kref_get_unless_zero(&se_cmd->cmd_kref))
+                        return -EINVAL;
+
+                se_cmd->se_cmd_flags |= SCF_ACK_KREF;
+        }
 
         spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
         if (se_sess->sess_tearing_down) {
@@ -2627,7 +2618,7 @@ EXPORT_SYMBOL(target_put_sess_cmd);
  */
 void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 {
-        struct se_cmd *se_cmd;
+        struct se_cmd *se_cmd, *tmp_cmd;
         unsigned long flags;
         int rc;
 
@@ -2639,14 +2630,16 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
         se_sess->sess_tearing_down = 1;
         list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list);
 
-        list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) {
+        list_for_each_entry_safe(se_cmd, tmp_cmd,
+                                 &se_sess->sess_wait_list, se_cmd_list) {
                 rc = kref_get_unless_zero(&se_cmd->cmd_kref);
                 if (rc) {
                         se_cmd->cmd_wait_set = 1;
                         spin_lock(&se_cmd->t_state_lock);
                         se_cmd->transport_state |= CMD_T_FABRIC_STOP;
                         spin_unlock(&se_cmd->t_state_lock);
-                }
+                } else
+                        list_del_init(&se_cmd->se_cmd_list);
         }
 
         spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
@@ -2871,6 +2864,12 @@ static const struct sense_info sense_info_table[] = {
                 .ascq = 0x03, /* LOGICAL BLOCK REFERENCE TAG CHECK FAILED */
                 .add_sector_info = true,
         },
+        [TCM_COPY_TARGET_DEVICE_NOT_REACHABLE] = {
+                .key = COPY_ABORTED,
+                .asc = 0x0d,
+                .ascq = 0x02, /* COPY TARGET DEVICE NOT REACHABLE */
+
+        },
         [TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE] = {
                 /*
                  * Returning ILLEGAL REQUEST would cause immediate IO errors on
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 62bf4fe5704a..47562509b489 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -96,7 +96,7 @@ struct tcmu_dev {
         size_t dev_size;
         u32 cmdr_size;
         u32 cmdr_last_cleaned;
-        /* Offset of data ring from start of mb */
+        /* Offset of data area from start of mb */
         /* Must add data_off and mb_addr to get the address */
         size_t data_off;
         size_t data_size;
@@ -349,7 +349,7 @@ static inline size_t spc_bitmap_free(unsigned long *bitmap)
 
 /*
  * We can't queue a command until we have space available on the cmd ring *and*
- * space available on the data ring.
+ * space available on the data area.
  *
  * Called with ring lock held.
  */
@@ -389,7 +389,8 @@ static bool is_ring_space_avail(struct tcmu_dev *udev, size_t cmd_size, size_t d
         return true;
 }
 
-static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
+static sense_reason_t
+tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 {
         struct tcmu_dev *udev = tcmu_cmd->tcmu_dev;
         struct se_cmd *se_cmd = tcmu_cmd->se_cmd;
@@ -405,7 +406,7 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
         DECLARE_BITMAP(old_bitmap, DATA_BLOCK_BITS);
 
         if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags))
-                return -EINVAL;
+                return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
         /*
          * Must be a certain minimum size for response sense info, but
@@ -432,11 +433,14 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
                 BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
                 data_length += se_cmd->t_bidi_data_sg->length;
         }
-        if ((command_size > (udev->cmdr_size / 2))
-            || data_length > udev->data_size)
-                pr_warn("TCMU: Request of size %zu/%zu may be too big for %u/%zu "
-                        "cmd/data ring buffers\n", command_size, data_length,
+        if ((command_size > (udev->cmdr_size / 2)) ||
+            data_length > udev->data_size) {
+                pr_warn("TCMU: Request of size %zu/%zu is too big for %u/%zu "
+                        "cmd ring/data area\n", command_size, data_length,
                         udev->cmdr_size, udev->data_size);
+                spin_unlock_irq(&udev->cmdr_lock);
+                return TCM_INVALID_CDB_FIELD;
+        }
 
         while (!is_ring_space_avail(udev, command_size, data_length)) {
                 int ret;
@@ -450,7 +454,7 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
                 finish_wait(&udev->wait_cmdr, &__wait);
                 if (!ret) {
                         pr_warn("tcmu: command timed out\n");
-                        return -ETIMEDOUT;
+                        return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
                 }
 
                 spin_lock_irq(&udev->cmdr_lock);
@@ -487,9 +491,7 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
 
         bitmap_copy(old_bitmap, udev->data_bitmap, DATA_BLOCK_BITS);
 
-        /*
-         * Fix up iovecs, and handle if allocation in data ring wrapped.
-         */
+        /* Handle allocating space from the data area */
         iov = &entry->req.iov[0];
         iov_cnt = 0;
         copy_to_data_area = (se_cmd->data_direction == DMA_TO_DEVICE
@@ -526,10 +528,11 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
         mod_timer(&udev->timeout,
                 round_jiffies_up(jiffies + msecs_to_jiffies(TCMU_TIME_OUT)));
 
-        return 0;
+        return TCM_NO_SENSE;
 }
 
-static int tcmu_queue_cmd(struct se_cmd *se_cmd)
+static sense_reason_t
+tcmu_queue_cmd(struct se_cmd *se_cmd)
 {
         struct se_device *se_dev = se_cmd->se_dev;
         struct tcmu_dev *udev = TCMU_DEV(se_dev);
@@ -538,10 +541,10 @@ static int tcmu_queue_cmd(struct se_cmd *se_cmd)
 
         tcmu_cmd = tcmu_alloc_cmd(se_cmd);
         if (!tcmu_cmd)
-                return -ENOMEM;
+                return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
         ret = tcmu_queue_cmd_ring(tcmu_cmd);
-        if (ret < 0) {
+        if (ret != TCM_NO_SENSE) {
                 pr_err("TCMU: Could not queue command\n");
                 spin_lock_irq(&udev->commands_lock);
                 idr_remove(&udev->commands, tcmu_cmd->cmd_id);
@@ -561,7 +564,7 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *
         if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) {
                 /*
                  * cmd has been completed already from timeout, just reclaim
-                 * data ring space and free cmd
+                 * data area space and free cmd
                  */
                 free_data_area(udev, cmd);
 
@@ -1129,20 +1132,9 @@ static sector_t tcmu_get_blocks(struct se_device *dev)
 }
 
 static sense_reason_t
-tcmu_pass_op(struct se_cmd *se_cmd)
-{
-        int ret = tcmu_queue_cmd(se_cmd);
-
-        if (ret != 0)
-                return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-        else
-                return TCM_NO_SENSE;
-}
-
-static sense_reason_t
 tcmu_parse_cdb(struct se_cmd *cmd)
 {
-        return passthrough_parse_cdb(cmd, tcmu_pass_op);
+        return passthrough_parse_cdb(cmd, tcmu_queue_cmd);
 }
 
 static const struct target_backend_ops tcmu_ops = {
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 75cd85426ae3..094a1440eacb 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -104,7 +104,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op
         }
         mutex_unlock(&g_device_mutex);
 
-        pr_err("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
+        pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
         return -EINVAL;
 }
 
@@ -185,7 +185,7 @@ static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op
 
 static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
                                 struct xcopy_op *xop, unsigned char *p,
-                                unsigned short tdll)
+                                unsigned short tdll, sense_reason_t *sense_ret)
 {
         struct se_device *local_dev = se_cmd->se_dev;
         unsigned char *desc = p;
@@ -193,6 +193,8 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
         unsigned short start = 0;
         bool src = true;
 
+        *sense_ret = TCM_INVALID_PARAMETER_LIST;
+
         if (offset != 0) {
                 pr_err("XCOPY target descriptor list length is not"
                         " multiple of %d\n", XCOPY_TARGET_DESC_LEN);
@@ -243,9 +245,16 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
                 rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, true);
         else
                 rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, false);
-
-        if (rc < 0)
+        /*
+         * If a matching IEEE NAA 0x83 descriptor for the requested device
+         * is not located on this node, return COPY_ABORTED with ASQ/ASQC
+         * 0x0d/0x02 - COPY_TARGET_DEVICE_NOT_REACHABLE to request the
+         * initiator to fall back to normal copy method.
+         */
+        if (rc < 0) {
+                *sense_ret = TCM_COPY_TARGET_DEVICE_NOT_REACHABLE;
                 goto out;
+        }
 
         pr_debug("XCOPY TGT desc: Source dev: %p NAA IEEE WWN: 0x%16phN\n",
                  xop->src_dev, &xop->src_tid_wwn[0]);
@@ -653,6 +662,7 @@ static int target_xcopy_read_source(
         rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, src_dev, &cdb[0],
                                 remote_port, true);
         if (rc < 0) {
+                ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
                 transport_generic_free_cmd(se_cmd, 0);
                 return rc;
         }
@@ -664,6 +674,7 @@ static int target_xcopy_read_source(
 
         rc = target_xcopy_issue_pt_cmd(xpt_cmd);
         if (rc < 0) {
+                ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
                 transport_generic_free_cmd(se_cmd, 0);
                 return rc;
         }
@@ -714,6 +725,7 @@ static int target_xcopy_write_destination(
                                 remote_port, false);
         if (rc < 0) {
                 struct se_cmd *src_cmd = &xop->src_pt_cmd->se_cmd;
+                ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
                 /*
                  * If the failure happened before the t_mem_list hand-off in
                  * target_xcopy_setup_pt_cmd(), Reset memory + clear flag so that
@@ -729,6 +741,7 @@ static int target_xcopy_write_destination(
 
         rc = target_xcopy_issue_pt_cmd(xpt_cmd);
         if (rc < 0) {
+                ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
                 se_cmd->se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
                 transport_generic_free_cmd(se_cmd, 0);
                 return rc;
@@ -815,9 +828,14 @@ static void target_xcopy_do_work(struct work_struct *work)
 out:
         xcopy_pt_undepend_remotedev(xop);
         kfree(xop);
-
-        pr_warn("target_xcopy_do_work: Setting X-COPY CHECK_CONDITION -> sending response\n");
-        ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+        /*
+         * Don't override an error scsi status if it has already been set
+         */
+        if (ec_cmd->scsi_status == SAM_STAT_GOOD) {
+                pr_warn_ratelimited("target_xcopy_do_work: rc: %d, Setting X-COPY"
+                        " CHECK_CONDITION -> sending response\n", rc);
+                ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+        }
         target_complete_cmd(ec_cmd, SAM_STAT_CHECK_CONDITION);
 }
 
@@ -875,7 +893,7 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd)
                 " tdll: %hu sdll: %u inline_dl: %u\n", list_id, list_id_usage,
                 tdll, sdll, inline_dl);
 
-        rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll);
+        rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll, &ret);
         if (rc <= 0)
                 goto out;
 
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 216e18cc9133..ff5de9a96643 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -572,10 +572,10 @@ static void ft_send_work(struct work_struct *work)
         if (target_submit_cmd(&cmd->se_cmd, cmd->sess->se_sess, fcp->fc_cdb,
                               &cmd->ft_sense_buffer[0], scsilun_to_int(&fcp->fc_lun),
                               ntohl(fcp->fc_dl), task_attr, data_dir,
-                              TARGET_SCF_ACK_KREF))
+                              TARGET_SCF_ACK_KREF | TARGET_SCF_USE_CPUID))
                 goto err;
 
-        pr_debug("r_ctl %x alloc target_submit_cmd\n", fh->fh_r_ctl);
+        pr_debug("r_ctl %x target_submit_cmd %p\n", fh->fh_r_ctl, cmd);
         return;
 
 err:
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index 6ffbb603d912..fd5c3de79470 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -39,6 +39,11 @@
 
 #include "tcm_fc.h"
 
+#define TFC_SESS_DBG(lport, fmt, args...) \
+        pr_debug("host%u: rport %6.6x: " fmt,      \
+                 (lport)->host->host_no,           \
+                 (lport)->port_id, ##args )
+
 static void ft_sess_delete_all(struct ft_tport *);
 
 /*
@@ -167,24 +172,29 @@ static struct ft_sess *ft_sess_get(struct fc_lport *lport, u32 port_id)
         struct ft_tport *tport;
         struct hlist_head *head;
         struct ft_sess *sess;
+        char *reason = "no session created";
 
         rcu_read_lock();
         tport = rcu_dereference(lport->prov[FC_TYPE_FCP]);
-        if (!tport)
+        if (!tport) {
+                reason = "not an FCP port";
                 goto out;
+        }
 
         head = &tport->hash[ft_sess_hash(port_id)];
         hlist_for_each_entry_rcu(sess, head, hash) {
                 if (sess->port_id == port_id) {
                         kref_get(&sess->kref);
                         rcu_read_unlock();
-                        pr_debug("port_id %x found %p\n", port_id, sess);
+                        TFC_SESS_DBG(lport, "port_id %x found %p\n",
+                                     port_id, sess);
                         return sess;
                 }
         }
 out:
         rcu_read_unlock();
-        pr_debug("port_id %x not found\n", port_id);
+        TFC_SESS_DBG(lport, "port_id %x not found, %s\n",
+                     port_id, reason);
         return NULL;
 }
 
@@ -195,7 +205,7 @@ static int ft_sess_alloc_cb(struct se_portal_group *se_tpg,
         struct ft_tport *tport = sess->tport;
         struct hlist_head *head = &tport->hash[ft_sess_hash(sess->port_id)];
 
-        pr_debug("port_id %x sess %p\n", sess->port_id, sess);
+        TFC_SESS_DBG(tport->lport, "port_id %x sess %p\n", sess->port_id, sess);
         hlist_add_head_rcu(&sess->hash, head);
         tport->sess_count++;
 
@@ -223,7 +233,7 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id,
 
         sess = kzalloc(sizeof(*sess), GFP_KERNEL);
         if (!sess)
-                return NULL;
+                return ERR_PTR(-ENOMEM);
 
         kref_init(&sess->kref); /* ref for table entry */
         sess->tport = tport;
@@ -234,8 +244,9 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id,
                                              TARGET_PROT_NORMAL, &initiatorname[0],
                                              sess, ft_sess_alloc_cb);
         if (IS_ERR(sess->se_sess)) {
+                int rc = PTR_ERR(sess->se_sess);
                 kfree(sess);
-                return NULL;
+                sess = ERR_PTR(rc);
         }
         return sess;
 }
@@ -319,7 +330,7 @@ void ft_sess_close(struct se_session *se_sess)
                 mutex_unlock(&ft_lport_lock);
                 return;
         }
-        pr_debug("port_id %x\n", port_id);
+        TFC_SESS_DBG(sess->tport->lport, "port_id %x close session\n", port_id);
         ft_sess_unhash(sess);
         mutex_unlock(&ft_lport_lock);
         ft_close_sess(sess);
@@ -379,8 +390,13 @@ static int ft_prli_locked(struct fc_rport_priv *rdata, u32 spp_len,
                 if (!(fcp_parm & FCP_SPPF_INIT_FCN))
                         return FC_SPP_RESP_CONF;
                 sess = ft_sess_create(tport, rdata->ids.port_id, rdata);
-                if (!sess)
-                        return FC_SPP_RESP_RES;
+                if (IS_ERR(sess)) {
+                        if (PTR_ERR(sess) == -EACCES) {
+                                spp->spp_flags &= ~FC_SPP_EST_IMG_PAIR;
+                                return FC_SPP_RESP_CONF;
+                        } else
+                                return FC_SPP_RESP_RES;
+                }
                 if (!sess->params)
                         rdata->prli_count++;
                 sess->params = fcp_parm;
@@ -423,8 +439,8 @@ static int ft_prli(struct fc_rport_priv *rdata, u32 spp_len,
         mutex_lock(&ft_lport_lock);
         ret = ft_prli_locked(rdata, spp_len, rspp, spp);
         mutex_unlock(&ft_lport_lock);
-        pr_debug("port_id %x flags %x ret %x\n",
-               rdata->ids.port_id, rspp ? rspp->spp_flags : 0, ret);
+        TFC_SESS_DBG(rdata->local_port, "port_id %x flags %x ret %x\n",
+                     rdata->ids.port_id, rspp ? rspp->spp_flags : 0, ret);
         return ret;
 }
 
@@ -477,11 +493,11 @@ static void ft_recv(struct fc_lport *lport, struct fc_frame *fp)
         struct ft_sess *sess;
         u32 sid = fc_frame_sid(fp);
 
-        pr_debug("sid %x\n", sid);
+        TFC_SESS_DBG(lport, "recv sid %x\n", sid);
 
         sess = ft_sess_get(lport, sid);
         if (!sess) {
-                pr_debug("sid %x sess lookup failed\n", sid);
+                TFC_SESS_DBG(lport, "sid %x sess lookup failed\n", sid);
                 /* TBD XXX - if FCP_CMND, send PRLO */
                 fc_frame_free(fp);
                 return;
diff --git a/drivers/thermal/intel_pch_thermal.c b/drivers/thermal/intel_pch_thermal.c
index 9b4815e81b0d..19bf2028e508 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 @@ read_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 0e4dc0afcfd2..7a223074df3d 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 886fcf37f291..b9923464599f 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 1bfb6fdbaa20..1731b98d2471 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 b8d9c8c9d02a..417d9e7038e1 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 c7831407a882..25c1d7bc0100 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1625,6 +1625,7 @@ config SERIAL_SPRD_CONSOLE
 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 fd8aa1f4ba78..168b10cad47b 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 de9d5107c00a..76103f2c4a80 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 d391650b82e7..42caccb5e87e 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 2675792a8f59..fb0672554123 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 6e4f63627479..f2303f390345 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 41d974923102..cd97ceb76e4f 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 f37edaa5ac75..dd4c02fa4820 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 06fb39c1d6dd..8c3bf3d613c0 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 96ae69502c86..111b0e0b8698 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 fa9b26b91507..4c0fa0b17353 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 aad4107ef927..2a21a0414b1d 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 4cd6403a7566..24fbebc9b409 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));
-
-                val = (dptxfsizn & FIFOSIZE_DEPTH_MASK) | addr;
-                addr += dptxfsizn >> FIFOSIZE_DEPTH_SHIFT;
-
-                if (addr > hsotg->fifo_mem)
-                        break;
+        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];
 
-                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 07cc8929f271..1dfa56a5f1c5 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 @@ err3:
         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 54ad100af35b..e40d47d47d82 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 9c8c9ed1dc9e..fe1811650dbc 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 bb1f6c8f0f01..45bc997d0711 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 876dca4fc216..a268d9e8d6cf 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 5b5880c0ae19..b38a228134df 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 1700908b84ef..86612ac3fda2 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 730b9fd26685..0ef16900efed 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 d7b0f97abbad..e96ae80d107e 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 b2c1dc5dc0f3..f945380035d0 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 bff4869a57cd..4042ea017985 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 1ab6973d4f61..cc1225485509 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 1d70add926f0..d544b331c9f2 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 54a4de0efdba..f61477bed3a8 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 b2d767e743fc..0ff7f38d7800 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 f87a938cf005..21011c0a4c64 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 d213cf44a7e4..4a037b4a79cf 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 79b2b628066d..79451f7ef1b7 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/vme/vme.c b/drivers/vme/vme.c
index 15b64076bc26..bdbadaa47ef3 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/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c
index e473e3b23720..6d1fbda0f461 100644
--- a/drivers/watchdog/wdat_wdt.c
+++ b/drivers/watchdog/wdat_wdt.c
@@ -499,6 +499,10 @@ static int wdat_wdt_resume_noirq(struct device *dev)
                 ret = wdat_wdt_enable_reboot(wdat);
                 if (ret)
                         return ret;
+
+                ret = wdat_wdt_ping(&wdat->wdd);
+                if (ret)
+                        return ret;
         }
 
         return wdat_wdt_start(&wdat->wdd);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index e12bd3635f83..26e5e8507f03 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -168,7 +168,9 @@ out:
 #endif  /* CONFIG_HIBERNATE_CALLBACKS */
 
 struct shutdown_handler {
-        const char *command;
+#define SHUTDOWN_CMD_SIZE 11
+        const char command[SHUTDOWN_CMD_SIZE];
+        bool flag;
         void (*cb)(void);
 };
 
@@ -206,22 +208,22 @@ static void do_reboot(void)
         ctrl_alt_del();
 }
 
+static struct shutdown_handler shutdown_handlers[] = {
+        { "poweroff",   true,   do_poweroff },
+        { "halt",       false,  do_poweroff },
+        { "reboot",     true,   do_reboot   },
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+        { "suspend",    true,   do_suspend  },
+#endif
+};
+
 static void shutdown_handler(struct xenbus_watch *watch,
                              const char **vec, unsigned int len)
 {
         char *str;
         struct xenbus_transaction xbt;
         int err;
-        static struct shutdown_handler handlers[] = {
-                { "poweroff",   do_poweroff },
-                { "halt",       do_poweroff },
-                { "reboot",     do_reboot   },
-#ifdef CONFIG_HIBERNATE_CALLBACKS
-                { "suspend",    do_suspend  },
-#endif
-                {NULL, NULL},
-        };
-        static struct shutdown_handler *handler;
+        int idx;
 
         if (shutting_down != SHUTDOWN_INVALID)
                 return;
@@ -238,13 +240,13 @@ static void shutdown_handler(struct xenbus_watch *watch,
                 return;
         }
 
-        for (handler = &handlers[0]; handler->command; handler++) {
-                if (strcmp(str, handler->command) == 0)
+        for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) {
+                if (strcmp(str, shutdown_handlers[idx].command) == 0)
                         break;
         }
 
         /* Only acknowledge commands which we are prepared to handle. */
-        if (handler->cb)
+        if (idx < ARRAY_SIZE(shutdown_handlers))
                 xenbus_write(xbt, "control", "shutdown", "");
 
         err = xenbus_transaction_end(xbt, 0);
@@ -253,8 +255,8 @@ static void shutdown_handler(struct xenbus_watch *watch,
                 goto again;
         }
 
-        if (handler->cb) {
-                handler->cb();
+        if (idx < ARRAY_SIZE(shutdown_handlers)) {
+                shutdown_handlers[idx].cb();
         } else {
                 pr_info("Ignoring shutdown request: %s\n", str);
                 shutting_down = SHUTDOWN_INVALID;
@@ -310,6 +312,9 @@ static struct notifier_block xen_reboot_nb = {
 static int setup_shutdown_watcher(void)
 {
         int err;
+        int idx;
+#define FEATURE_PATH_SIZE (SHUTDOWN_CMD_SIZE + sizeof("feature-"))
+        char node[FEATURE_PATH_SIZE];
 
         err = register_xenbus_watch(&shutdown_watch);
         if (err) {
@@ -326,6 +331,14 @@ static int setup_shutdown_watcher(void)
         }
 #endif
 
+        for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) {
+                if (!shutdown_handlers[idx].flag)
+                        continue;
+                snprintf(node, FEATURE_PATH_SIZE, "feature-%s",
+                         shutdown_handlers[idx].command);
+                xenbus_printf(XBT_NIL, "control", node, "%u", 1);
+        }
+
         return 0;
 }
 
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index c1010f018bd8..1e8be12ebb55 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -364,7 +364,7 @@ out:
 
 static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u)
 {
-        struct watch_adapter *watch, *tmp_watch;
+        struct watch_adapter *watch;
         char *path, *token;
         int err, rc;
         LIST_HEAD(staging_q);
@@ -399,7 +399,7 @@ static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u)
                 }
                 list_add(&watch->list, &u->watches);
         } else {
-                list_for_each_entry_safe(watch, tmp_watch, &u->watches, list) {
+                list_for_each_entry(watch, &u->watches, list) {
                         if (!strcmp(watch->token, token) &&
                             !strcmp(watch->watch.node, path)) {
                                 unregister_xenbus_watch(&watch->watch);
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index 611a23119675..6d40a972ffb2 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -335,7 +335,9 @@ static int backend_state;
 static void xenbus_reset_backend_state_changed(struct xenbus_watch *w,
                                         const char **v, unsigned int l)
 {
-        xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i", &backend_state);
+        if (xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i",
+                         &backend_state) != 1)
+                backend_state = XenbusStateUnknown;
         printk(KERN_DEBUG "XENBUS: backend %s %s\n",
                         v[XS_WATCH_PATH], xenbus_strstate(backend_state));
         wake_up(&backend_state_wq);
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 2037e7a77a37..d764236072b1 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 96f4d764d1a6..31c616ab9b40 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 5497c8496055..535a38d2c1d0 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 477928b25940..25f05a8d21b1 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/send.c b/fs/btrfs/send.c
index 01bc36cec26e..71261b459863 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 528cae123dc9..3d33c4e41e5f 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 @@ out_wake_log_root:
         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/ceph/file.c b/fs/ceph/file.c
index 7bf08825cc11..18630e800208 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1272,7 +1272,8 @@ again:
                 statret = __ceph_do_getattr(inode, page,
                                             CEPH_STAT_CAP_INLINE_DATA, !!page);
                 if (statret < 0) {
-                         __free_page(page);
+                        if (page)
+                                __free_page(page);
                         if (statret == -ENODATA) {
                                 BUG_ON(retry_op != READ_INLINE);
                                 goto again;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index bca1b49c1c4b..ef4d04647325 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1511,7 +1511,8 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
                         ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir);
         }
 
-        if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2) {
+        if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 &&
+            !(rinfo->hash_order && req->r_path2)) {
                 /* note dir version at start of readdir so we can tell
                  * if any dentries get dropped */
                 req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index a29ffce98187..b382e5910eea 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -845,6 +845,8 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
                 err = ceph_fs_debugfs_init(fsc);
                 if (err < 0)
                         goto fail;
+        } else {
+                root = dget(fsc->sb->s_root);
         }
 
         fsc->mount_state = CEPH_MOUNT_MOUNTED;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 40b703217977..febc28f9e2c2 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -16,7 +16,7 @@
 static int __remove_xattr(struct ceph_inode_info *ci,
                           struct ceph_inode_xattr *xattr);
 
-const struct xattr_handler ceph_other_xattr_handler;
+static const struct xattr_handler ceph_other_xattr_handler;
 
 /*
  * List of handlers for synthetic system.* attributes. Other
@@ -1086,7 +1086,7 @@ static int ceph_set_xattr_handler(const struct xattr_handler *handler,
         return __ceph_setxattr(inode, name, value, size, flags);
 }
 
-const struct xattr_handler ceph_other_xattr_handler = {
+static const struct xattr_handler ceph_other_xattr_handler = {
         .prefix = "",  /* match any name => handlers called with full name */
         .get = ceph_get_xattr_handler,
         .set = ceph_set_xattr_handler,
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 61057b7dbddb..98f87fe8f186 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -151,7 +151,10 @@ static int do_page_crypto(struct inode *inode,
                         struct page *src_page, struct page *dest_page,
                         gfp_t gfp_flags)
 {
-        u8 xts_tweak[FS_XTS_TWEAK_SIZE];
+        struct {
+                __le64 index;
+                u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)];
+        } xts_tweak;
         struct skcipher_request *req = NULL;
         DECLARE_FS_COMPLETION_RESULT(ecr);
         struct scatterlist dst, src;
@@ -171,17 +174,15 @@ static int do_page_crypto(struct inode *inode,
                 req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
                 page_crypt_complete, &ecr);
 
-        BUILD_BUG_ON(FS_XTS_TWEAK_SIZE < sizeof(index));
-        memcpy(xts_tweak, &index, sizeof(index));
-        memset(&xts_tweak[sizeof(index)], 0,
-                        FS_XTS_TWEAK_SIZE - sizeof(index));
+        BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE);
+        xts_tweak.index = cpu_to_le64(index);
+        memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding));
 
         sg_init_table(&dst, 1);
         sg_set_page(&dst, dest_page, PAGE_SIZE, 0);
         sg_init_table(&src, 1);
         sg_set_page(&src, src_page, PAGE_SIZE, 0);
-        skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE,
-                                        xts_tweak);
+        skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, &xts_tweak);
         if (rw == FS_DECRYPT)
                 res = crypto_skcipher_decrypt(req);
         else
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index ed115acb5dee..6865663aac69 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -109,6 +109,8 @@ int fscrypt_process_policy(struct file *filp,
         if (ret)
                 return ret;
 
+        inode_lock(inode);
+
         if (!inode_has_encryption_context(inode)) {
                 if (!S_ISDIR(inode->i_mode))
                         ret = -EINVAL;
@@ -127,6 +129,8 @@ int fscrypt_process_policy(struct file *filp,
                 ret = -EINVAL;
         }
 
+        inode_unlock(inode);
+
         mnt_drop_write_file(filp);
         return ret;
 }
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 79101651fe9e..42f9a0a0c4ca 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -137,7 +137,7 @@ Espan:
 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/ext2/inode.c b/fs/ext2/inode.c
index d831e24dc885..41b8b44a391c 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -622,7 +622,7 @@ static int ext2_get_blocks(struct inode *inode,
                            u32 *bno, bool *new, bool *boundary,
                            int create)
 {
-        int err = -EIO;
+        int err;
         int offsets[4];
         Indirect chain[4];
         Indirect *partial;
@@ -639,7 +639,7 @@ static int ext2_get_blocks(struct inode *inode,
         depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
 
         if (depth == 0)
-                return (err);
+                return -EIO;
 
         partial = ext2_get_branch(inode, depth, offsets, chain, &err);
         /* Simplest case - block found, no allocation needed */
@@ -761,7 +761,6 @@ static int ext2_get_blocks(struct inode *inode,
         ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
         mutex_unlock(&ei->truncate_mutex);
 got_it:
-        *bno = le32_to_cpu(chain[depth-1].key);
         if (count > blocks_to_boundary)
                 *boundary = true;
         err = count;
@@ -772,6 +771,8 @@ cleanup:
                 brelse(partial->bh);
                 partial--;
         }
+        if (err > 0)
+                *bno = le32_to_cpu(chain[depth-1].key);
         return err;
 }
 
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 02ddec6d8a7d..fdb19543af1e 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -128,12 +128,12 @@ static void debug_print_tree(struct ext4_sb_info *sbi)
         node = rb_first(&sbi->system_blks);
         while (node) {
                 entry = rb_entry(node, struct ext4_system_zone, node);
-                printk("%s%llu-%llu", first ? "" : ", ",
+                printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ",
                        entry->start_blk, entry->start_blk + entry->count - 1);
                 first = 0;
                 node = rb_next(node);
         }
-        printk("\n");
+        printk(KERN_CONT "\n");
 }
 
 int ext4_setup_system_zone(struct super_block *sb)
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 3ef1df6ae9ec..1aba469f8220 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -27,16 +27,15 @@
 #ifdef CONFIG_EXT4_DEBUG
 extern ushort ext4_mballoc_debug;
 
-#define mb_debug(n, fmt, a...)                                          \
-        do {                                                            \
-                if ((n) <= ext4_mballoc_debug) {                        \
-                        printk(KERN_DEBUG "(%s, %d): %s: ",             \
-                               __FILE__, __LINE__, __func__);           \
-                        printk(fmt, ## a);                              \
-                }                                                       \
-        } while (0)
+#define mb_debug(n, fmt, ...)                                           \
+do {                                                                    \
+        if ((n) <= ext4_mballoc_debug) {                                \
+                printk(KERN_DEBUG "(%s, %d): %s: " fmt,                 \
+                       __FILE__, __LINE__, __func__, ##__VA_ARGS__);    \
+        }                                                               \
+} while (0)
 #else
-#define mb_debug(n, fmt, a...)          no_printk(fmt, ## a)
+#define mb_debug(n, fmt, ...)   no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 #define EXT4_MB_HISTORY_ALLOC           1       /* allocation */
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index f92f10d4f66a..104f8bfba718 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -577,12 +577,13 @@ static inline unsigned dx_node_limit(struct inode *dir)
 static void dx_show_index(char * label, struct dx_entry *entries)
 {
         int i, n = dx_get_count (entries);
-        printk(KERN_DEBUG "%s index ", label);
+        printk(KERN_DEBUG "%s index", label);
         for (i = 0; i < n; i++) {
-                printk("%x->%lu ", i ? dx_get_hash(entries + i) :
-                                0, (unsigned long)dx_get_block(entries + i));
+                printk(KERN_CONT " %x->%lu",
+                       i ? dx_get_hash(entries + i) : 0,
+                       (unsigned long)dx_get_block(entries + i));
         }
-        printk("\n");
+        printk(KERN_CONT "\n");
 }
 
 struct stats
@@ -679,7 +680,7 @@ static struct stats dx_show_leaf(struct inode *dir,
                 }
                 de = ext4_next_entry(de, size);
         }
-        printk("(%i)\n", names);
+        printk(KERN_CONT "(%i)\n", names);
         return (struct stats) { names, space, 1 };
 }
 
@@ -798,7 +799,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
                 q = entries + count - 1;
                 while (p <= q) {
                         m = p + (q - p) / 2;
-                        dxtrace(printk("."));
+                        dxtrace(printk(KERN_CONT "."));
                         if (dx_get_hash(m) > hash)
                                 q = m - 1;
                         else
@@ -810,7 +811,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
                         at = entries;
                         while (n--)
                         {
-                                dxtrace(printk(","));
+                                dxtrace(printk(KERN_CONT ","));
                                 if (dx_get_hash(++at) > hash)
                                 {
                                         at--;
@@ -821,7 +822,8 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
                 }
 
                 at = p - 1;
-                dxtrace(printk(" %x->%u\n", at == entries ? 0 : dx_get_hash(at),
+                dxtrace(printk(KERN_CONT " %x->%u\n",
+                               at == entries ? 0 : dx_get_hash(at),
                                dx_get_block(at)));
                 frame->entries = entries;
                 frame->at = at;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6db81fbcbaa6..20da99da0a34 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -597,14 +597,15 @@ void __ext4_std_error(struct super_block *sb, const char *function,
 void __ext4_abort(struct super_block *sb, const char *function,
                 unsigned int line, const char *fmt, ...)
 {
+        struct va_format vaf;
         va_list args;
 
         save_error_info(sb, function, line);
         va_start(args, fmt);
-        printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id,
-               function, line);
-        vprintk(fmt, args);
-        printk("\n");
+        vaf.fmt = fmt;
+        vaf.va = &args;
+        printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n",
+               sb->s_id, function, line, &vaf);
         va_end(args);
 
         if ((sb->s_flags & MS_RDONLY) == 0) {
@@ -2715,12 +2716,12 @@ static void print_daily_error_info(unsigned long arg)
                        es->s_first_error_func,
                        le32_to_cpu(es->s_first_error_line));
                 if (es->s_first_error_ino)
-                        printk(": inode %u",
+                        printk(KERN_CONT ": inode %u",
                                le32_to_cpu(es->s_first_error_ino));
                 if (es->s_first_error_block)
-                        printk(": block %llu", (unsigned long long)
+                        printk(KERN_CONT ": block %llu", (unsigned long long)
                                le64_to_cpu(es->s_first_error_block));
-                printk("\n");
+                printk(KERN_CONT "\n");
         }
         if (es->s_last_error_time) {
                 printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
@@ -2729,12 +2730,12 @@ static void print_daily_error_info(unsigned long arg)
                        es->s_last_error_func,
                        le32_to_cpu(es->s_last_error_line));
                 if (es->s_last_error_ino)
-                        printk(": inode %u",
+                        printk(KERN_CONT ": inode %u",
                                le32_to_cpu(es->s_last_error_ino));
                 if (es->s_last_error_block)
-                        printk(": block %llu", (unsigned long long)
+                        printk(KERN_CONT ": block %llu", (unsigned long long)
                                le64_to_cpu(es->s_last_error_block));
-                printk("\n");
+                printk(KERN_CONT "\n");
         }
         mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ);  /* Once a day */
 }
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 73bcfd41f5f2..42145be5c6b4 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -223,14 +223,18 @@ static struct attribute *ext4_attrs[] = {
 EXT4_ATTR_FEATURE(lazy_itable_init);
 EXT4_ATTR_FEATURE(batched_discard);
 EXT4_ATTR_FEATURE(meta_bg_resize);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
 EXT4_ATTR_FEATURE(encryption);
+#endif
 EXT4_ATTR_FEATURE(metadata_csum_seed);
 
 static struct attribute *ext4_feat_attrs[] = {
         ATTR_LIST(lazy_itable_init),
         ATTR_LIST(batched_discard),
         ATTR_LIST(meta_bg_resize),
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
         ATTR_LIST(encryption),
+#endif
         ATTR_LIST(metadata_csum_seed),
         NULL,
 };
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c15d63389957..d77be9e9f535 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -61,18 +61,12 @@
 #include "acl.h"
 
 #ifdef EXT4_XATTR_DEBUG
-# define ea_idebug(inode, f...) do { \
-                printk(KERN_DEBUG "inode %s:%lu: ", \
-                        inode->i_sb->s_id, inode->i_ino); \
-                printk(f); \
-                printk("\n"); \
-        } while (0)
-# define ea_bdebug(bh, f...) do { \
-                printk(KERN_DEBUG "block %pg:%lu: ",               \
-                       bh->b_bdev, (unsigned long) bh->b_blocknr); \
-                printk(f); \
-                printk("\n"); \
-        } while (0)
+# define ea_idebug(inode, fmt, ...)                                     \
+        printk(KERN_DEBUG "inode %s:%lu: " fmt "\n",                    \
+               inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__)
+# define ea_bdebug(bh, fmt, ...)                                        \
+        printk(KERN_DEBUG "block %pg:%lu: " fmt "\n",                   \
+               bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__)
 #else
 # define ea_idebug(inode, fmt, ...)     no_printk(fmt, ##__VA_ARGS__)
 # define ea_bdebug(bh, fmt, ...)        no_printk(fmt, ##__VA_ARGS__)
@@ -241,7 +235,7 @@ __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
         int error = -EFSCORRUPTED;
 
         if (((void *) header >= end) ||
-            (header->h_magic != le32_to_cpu(EXT4_XATTR_MAGIC)))
+            (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)))
                 goto errout;
         error = ext4_xattr_check_names(entry, end, entry);
 errout:
diff --git a/fs/iomap.c b/fs/iomap.c
index 013d1d36fbbf..a8ee8c33ca78 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/isofs/inode.c b/fs/isofs/inode.c
index ad0c745ebad7..871c8b392099 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -687,6 +687,11 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
         pri_bh = NULL;
 
 root_found:
+        /* We don't support read-write mounts */
+        if (!(s->s_flags & MS_RDONLY)) {
+                error = -EACCES;
+                goto out_freebh;
+        }
 
         if (joliet_level && (pri == NULL || !opt.rock)) {
                 /* This is the case of Joliet with the norock mount flag.
@@ -1501,9 +1506,6 @@ struct inode *__isofs_iget(struct super_block *sb,
 static struct dentry *isofs_mount(struct file_system_type *fs_type,
         int flags, const char *dev_name, void *data)
 {
-        /* We don't support read-write mounts */
-        if (!(flags & MS_RDONLY))
-                return ERR_PTR(-EACCES);
         return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super);
 }
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 3d8246a9faa4..e1652665bd93 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1149,6 +1149,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
                 JBUFFER_TRACE(jh, "file as BJ_Reserved");
                 spin_lock(&journal->j_list_lock);
                 __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
+                spin_unlock(&journal->j_list_lock);
         } else if (jh->b_transaction == journal->j_committing_transaction) {
                 /* first access by this transaction */
                 jh->b_modified = 0;
@@ -1156,8 +1157,8 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
                 JBUFFER_TRACE(jh, "set next transaction");
                 spin_lock(&journal->j_list_lock);
                 jh->b_next_transaction = transaction;
+                spin_unlock(&journal->j_list_lock);
         }
-        spin_unlock(&journal->j_list_lock);
         jbd_unlock_bh_state(bh);
 
         /*
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 2bcb86e6e6ca..78219d5644e9 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/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 217847679f0e..2905479f214a 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -344,9 +344,10 @@ static void bl_write_cleanup(struct work_struct *work)
                 u64 start = hdr->args.offset & (loff_t)PAGE_MASK;
                 u64 end = (hdr->args.offset + hdr->args.count +
                         PAGE_SIZE - 1) & (loff_t)PAGE_MASK;
+                u64 lwb = hdr->args.offset + hdr->args.count;
 
                 ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
-                                        (end - start) >> SECTOR_SHIFT, end);
+                                        (end - start) >> SECTOR_SHIFT, lwb);
         }
 
         pnfs_ld_write_done(hdr);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ad917bd72b38..7897826d7c51 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1545,7 +1545,7 @@ static int update_open_stateid(struct nfs4_state *state,
         struct nfs_client *clp = server->nfs_client;
         struct nfs_inode *nfsi = NFS_I(state->inode);
         struct nfs_delegation *deleg_cur;
-        nfs4_stateid freeme = {0};
+        nfs4_stateid freeme = { };
         int ret = 0;
 
         fmode &= (FMODE_READ|FMODE_WRITE);
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
index 1e8fe844e69f..5355efba4bc8 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 @@ out_drop:
 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 66ea0cc37b18..02cc6139ec90 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 d15d3d2dba62..a290ff6ec756 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-kernel.h b/fs/orangefs/orangefs-kernel.h
index 0a82048f3aaf..3bf803d732c5 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/proc/array.c b/fs/proc/array.c
index 89600fd5963d..81818adb8e9e 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -412,10 +412,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
         mm = get_task_mm(task);
         if (mm) {
                 vsize = task_vsize(mm);
-                if (permitted) {
-                        eip = KSTK_EIP(task);
-                        esp = KSTK_ESP(task);
-                }
+                /*
+                 * esp and eip are intentionally zeroed out.  There is no
+                 * non-racy way to read them without freezing the task.
+                 * Programs that need reliable values can use ptrace(2).
+                 */
         }
 
         get_task_comm(tcomm, task);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8e654468ab67..ca651ac00660 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -252,7 +252,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
          * Inherently racy -- command line shares address space
          * with code and data.
          */
-        rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_FORCE);
+        rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
         if (rv <= 0)
                 goto out_free_page;
 
@@ -270,8 +270,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
                         int nr_read;
 
                         _count = min3(count, len, PAGE_SIZE);
-                        nr_read = access_remote_vm(mm, p, page, _count,
-                                        FOLL_FORCE);
+                        nr_read = access_remote_vm(mm, p, page, _count, 0);
                         if (nr_read < 0)
                                 rv = nr_read;
                         if (nr_read <= 0)
@@ -306,8 +305,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
                         bool final;
 
                         _count = min3(count, len, PAGE_SIZE);
-                        nr_read = access_remote_vm(mm, p, page, _count,
-                                        FOLL_FORCE);
+                        nr_read = access_remote_vm(mm, p, page, _count, 0);
                         if (nr_read < 0)
                                 rv = nr_read;
                         if (nr_read <= 0)
@@ -356,8 +354,7 @@ skip_argv:
                         bool final;
 
                         _count = min3(count, len, PAGE_SIZE);
-                        nr_read = access_remote_vm(mm, p, page, _count,
-                                        FOLL_FORCE);
+                        nr_read = access_remote_vm(mm, p, page, _count, 0);
                         if (nr_read < 0)
                                 rv = nr_read;
                         if (nr_read <= 0)
@@ -835,7 +832,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
         unsigned long addr = *ppos;
         ssize_t copied;
         char *page;
-        unsigned int flags = FOLL_FORCE;
+        unsigned int flags;
 
         if (!mm)
                 return 0;
@@ -848,6 +845,8 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
         if (!atomic_inc_not_zero(&mm->mm_users))
                 goto free;
 
+        /* Maybe we should limit FOLL_FORCE to actual ptrace users? */
+        flags = FOLL_FORCE;
         if (write)
                 flags |= FOLL_WRITE;
 
@@ -971,8 +970,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
                 max_len = min_t(size_t, PAGE_SIZE, count);
                 this_len = min(max_len, this_len);
 
-                retval = access_remote_vm(mm, (env_start + src),
-                        page, this_len, FOLL_FORCE);
+                retval = access_remote_vm(mm, (env_start + src), page, this_len, 0);
 
                 if (retval <= 0) {
                         ret = retval;
@@ -1014,6 +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/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6909582ce5e5..35b92d81692f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -266,24 +266,15 @@ static int do_maps_open(struct inode *inode, struct file *file,
  * /proc/PID/maps that is the stack of the main task.
  */
 static int is_stack(struct proc_maps_private *priv,
-                    struct vm_area_struct *vma, int is_pid)
+                    struct vm_area_struct *vma)
 {
-        int stack = 0;
-
-        if (is_pid) {
-                stack = vma->vm_start <= vma->vm_mm->start_stack &&
-                        vma->vm_end >= vma->vm_mm->start_stack;
-        } else {
-                struct inode *inode = priv->inode;
-                struct task_struct *task;
-
-                rcu_read_lock();
-                task = pid_task(proc_pid(inode), PIDTYPE_PID);
-                if (task)
-                        stack = vma_is_stack_for_task(vma, task);
-                rcu_read_unlock();
-        }
-        return stack;
+        /*
+         * We make no effort to guess what a given thread considers to be
+         * its "stack".  It's not even well-defined for programs written
+         * languages like Go.
+         */
+        return vma->vm_start <= vma->vm_mm->start_stack &&
+                vma->vm_end >= vma->vm_mm->start_stack;
 }
 
 static void
@@ -354,7 +345,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
                         goto done;
                 }
 
-                if (is_stack(priv, vma, is_pid))
+                if (is_stack(priv, vma))
                         name = "[stack]";
         }
 
@@ -1669,7 +1660,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
                 seq_file_path(m, file, "\n\t= ");
         } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
                 seq_puts(m, " heap");
-        } else if (is_stack(proc_priv, vma, is_pid)) {
+        } else if (is_stack(proc_priv, vma)) {
                 seq_puts(m, " stack");
         }
 
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index faacb0c0d857..37175621e890 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -124,25 +124,17 @@ unsigned long task_statm(struct mm_struct *mm,
 }
 
 static int is_stack(struct proc_maps_private *priv,
-                    struct vm_area_struct *vma, int is_pid)
+                    struct vm_area_struct *vma)
 {
         struct mm_struct *mm = vma->vm_mm;
-        int stack = 0;
-
-        if (is_pid) {
-                stack = vma->vm_start <= mm->start_stack &&
-                        vma->vm_end >= mm->start_stack;
-        } else {
-                struct inode *inode = priv->inode;
-                struct task_struct *task;
-
-                rcu_read_lock();
-                task = pid_task(proc_pid(inode), PIDTYPE_PID);
-                if (task)
-                        stack = vma_is_stack_for_task(vma, task);
-                rcu_read_unlock();
-        }
-        return stack;
+
+        /*
+         * We make no effort to guess what a given thread considers to be
+         * its "stack".  It's not even well-defined for programs written
+         * languages like Go.
+         */
+        return vma->vm_start <= mm->start_stack &&
+                vma->vm_end >= mm->start_stack;
 }
 
 /*
@@ -184,7 +176,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
         if (file) {
                 seq_pad(m, ' ');
                 seq_file_path(m, file, "");
-        } else if (mm && is_stack(priv, vma, is_pid)) {
+        } else if (mm && is_stack(priv, vma)) {
                 seq_pad(m, ' ');
                 seq_printf(m, "[stack]");
         }
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index c8f60df2733e..ca16c5d7bab1 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -439,7 +439,7 @@ static unsigned int vfs_dent_type(uint8_t type)
  */
 static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 {
-        int err;
+        int err = 0;
         struct qstr nm;
         union ubifs_key key;
         struct ubifs_dent_node *dent;
@@ -541,14 +541,20 @@ out:
         kfree(file->private_data);
         file->private_data = NULL;
 
-        if (err != -ENOENT) {
+        if (err != -ENOENT)
                 ubifs_err(c, "cannot find next direntry, error %d", err);
-                return 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;
-        return 0;
+        return err;
 }
 
 /* Free saved readdir() state when the directory is closed */
@@ -1060,9 +1066,9 @@ static void unlock_4_inodes(struct inode *inode1, struct inode *inode2,
         mutex_unlock(&ubifs_inode(inode1)->ui_mutex);
 }
 
-static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
-                        struct inode *new_dir, struct dentry *new_dentry,
-                        unsigned int flags)
+static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
+                     struct inode *new_dir, struct dentry *new_dentry,
+                     unsigned int flags)
 {
         struct ubifs_info *c = old_dir->i_sb->s_fs_info;
         struct inode *old_inode = d_inode(old_dentry);
@@ -1323,7 +1329,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry,
         return err;
 }
 
-static int ubifs_rename2(struct inode *old_dir, struct dentry *old_dentry,
+static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
                         struct inode *new_dir, struct dentry *new_dentry,
                         unsigned int flags)
 {
@@ -1336,7 +1342,7 @@ static int ubifs_rename2(struct inode *old_dir, struct dentry *old_dentry,
         if (flags & RENAME_EXCHANGE)
                 return ubifs_xrename(old_dir, old_dentry, new_dir, new_dentry);
 
-        return ubifs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
+        return do_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
 int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -1387,7 +1393,7 @@ const struct inode_operations ubifs_dir_inode_operations = {
         .mkdir       = ubifs_mkdir,
         .rmdir       = ubifs_rmdir,
         .mknod       = ubifs_mknod,
-        .rename      = ubifs_rename2,
+        .rename      = ubifs_rename,
         .setattr     = ubifs_setattr,
         .getattr     = ubifs_getattr,
         .listxattr   = ubifs_listxattr,
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 6c2f4d41ed73..d9f9615bfd71 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -172,6 +172,7 @@ out_cancel:
         host_ui->xattr_cnt -= 1;
         host_ui->xattr_size -= CALC_DENT_SIZE(nm->len);
         host_ui->xattr_size -= CALC_XATTR_BYTES(size);
+        host_ui->xattr_names -= nm->len;
         mutex_unlock(&host_ui->ui_mutex);
 out_free:
         make_bad_inode(inode);
@@ -478,6 +479,7 @@ out_cancel:
         host_ui->xattr_cnt += 1;
         host_ui->xattr_size += CALC_DENT_SIZE(nm->len);
         host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len);
+        host_ui->xattr_names += nm->len;
         mutex_unlock(&host_ui->ui_mutex);
         ubifs_release_budget(c, &req);
         make_bad_inode(inode);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index c27344cf38e1..c6eb21940783 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 @@ done:
         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 f97db7132564..7cae6ec27fa6 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 5c8e6f2ce44f..0e80993c8a59 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 3cc3cf767474..ac9a003dd29a 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 f6547fc5e016..6b7579e7b60a 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 8de9a3a29589..134424fac434 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 62d9d4681c8c..3cfe12a4f58a 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 a314fc7b56fa..6e4f7f900fea 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 */
-        if ((iocb->ki_pos & 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.
+         * 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 (unaligned_io || mapping->nrpages)
+        if ((iocb->ki_pos & mp->m_blockmask) ||
+            ((iocb->ki_pos + count) & mp->m_blockmask)) {
+                unaligned_io = 1;
                 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 @@ out_unlock:
         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 14796b744e0a..f295049db681 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 d907eb9f8ef3..436e109bb01e 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 fc7873942bea..b341f10cf481 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 5965e9455d91..a279b4e7f5fe 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);
-
-                trace_xfs_reflink_cancel_cow(ip, &irec);
+        xfs_bmap_search_extents(ip, offset_fsb, XFS_COW_FORK, &eof, &idx,
+                        &got, &prev);
+        if (eof)
+                return 0;
 
-                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;
+        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);
 
-                        /* 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;
+                }
+
+                ASSERT(!isnullstartblock(got.br_startblock));
 
                 /* 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);
+                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;
 
-                        /* 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;
+                /* 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);
 
-                        /* Map the new blocks into the data fork. */
-                        error = xfs_bmap_map_extent(tp->t_mountp, &dfops,
-                                        ip, &uirec);
-                        if (error)
-                                goto out_defer;
+                /* 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;
 
-                        /* Remove the mapping from the CoW fork. */
-                        error = xfs_bunmapi_cow(ip, &uirec);
-                        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;
 
-                        error = xfs_defer_finish(&tp, &dfops, ip);
-                        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 @@ next_extent:
 
 out_defer:
         xfs_defer_cancel(&dfops);
-out_cancel:
         xfs_trans_cancel(tp);
         xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
@@ -1312,19 +1274,26 @@ out_error:
  */
 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 5dc3c8ac12aa..fad11607c9ad 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 5f8d55d29a11..276d3023d60f 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 ad188d3a83f3..0907752be62d 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/acpi/pcc.h b/include/acpi/pcc.h
index 17a940a14477..8caa79c61703 100644
--- a/include/acpi/pcc.h
+++ b/include/acpi/pcc.h
@@ -21,7 +21,7 @@ extern void pcc_mbox_free_channel(struct mbox_chan *chan);
 static inline struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
                                                          int subspace_id)
 {
-        return NULL;
+        return ERR_PTR(-ENODEV);
 }
 static inline void pcc_mbox_free_channel(struct mbox_chan *chan) { }
 #endif
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index 43199a049da5..63554e9f6e0c 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/linux/acpi.h b/include/linux/acpi.h
index ddbeda6dbdc8..689a8b9b9c8f 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/clk-provider.h b/include/linux/clk-provider.h
index af596381fa0f..a428aec36ace 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -785,7 +785,7 @@ extern struct of_device_id __clk_of_table;
  * routines, one at of_clk_init(), and one at platform device probe
  */
 #define CLK_OF_DECLARE_DRIVER(name, compat, fn) \
-        static void name##_of_clk_init_driver(struct device_node *np)   \
+        static void __init name##_of_clk_init_driver(struct device_node *np) \
         {                                                               \
                 of_node_clear_flag(np, OF_POPULATED);                   \
                 fn(np);                                                 \
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 5fa55fc56e18..32dc0cbd51ca 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -677,10 +677,10 @@ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy,
                 if (best == table - 1)
                         return pos - table;
 
-                return best - pos;
+                return best - table;
         }
 
-        return best - pos;
+        return best - table;
 }
 
 /* Works only on sorted freq-tables */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 9b207a8c5af3..afe641c02dca 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -81,6 +81,7 @@ enum cpuhp_state {
         CPUHP_AP_ARM_ARCH_TIMER_STARTING,
         CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
         CPUHP_AP_DUMMY_TIMER_STARTING,
+        CPUHP_AP_JCORE_TIMER_STARTING,
         CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
         CPUHP_AP_ARM_TWD_STARTING,
         CPUHP_AP_METAG_TIMER_STARTING,
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6824556d37ed..cd184bdca58f 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 e2c8419278c1..82ef36eac8a1 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 e63e288dee83..7892f55a1866 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 7e9a789be5e0..ca1ad9ebbc92 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/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 8361c8d3edd1..b7e34313cdfe 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -290,7 +290,7 @@
 #define GITS_BASER_TYPE_SHIFT                   (56)
 #define GITS_BASER_TYPE(r)              (((r) >> GITS_BASER_TYPE_SHIFT) & 7)
 #define GITS_BASER_ENTRY_SIZE_SHIFT             (48)
-#define GITS_BASER_ENTRY_SIZE(r)        ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1)
+#define GITS_BASER_ENTRY_SIZE(r)        ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
 #define GITS_BASER_SHAREABILITY_SHIFT   (10)
 #define GITS_BASER_InnerShareable                                       \
         GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index 15ec117ec537..8f2e059e4d45 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 f6a164297358..3be7abd6e722 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 85c4786427e4..ecc451d89ccd 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/mm.h b/include/linux/mm.h
index ffbd72979ee7..a92c8d73aeaf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1271,10 +1271,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
                 void *buf, int len, unsigned int gup_flags);
 
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-                      unsigned long start, unsigned long nr_pages,
-                      unsigned int foll_flags, struct page **pages,
-                      struct vm_area_struct **vmas, int *nonblocking);
 long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
                             unsigned long start, unsigned long nr_pages,
                             unsigned int gup_flags, struct page **pages,
@@ -1391,7 +1387,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
                 !vma_growsup(vma->vm_next, addr);
 }
 
-int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t);
+int vma_is_stack_for_current(struct vm_area_struct *vma);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
                 unsigned long old_addr, struct vm_area_struct *new_vma,
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7f2ae99e5daf..0f088f3a2fed 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/netdevice.h b/include/linux/netdevice.h
index 136ae6bbe81e..91ee3643ccc8 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/nvme.h b/include/linux/nvme.h
index 7676557ce357..fc3c24206593 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -16,7 +16,6 @@
 #define _LINUX_NVME_H
 
 #include <linux/types.h>
-#include <linux/uuid.h>
 
 /* NQN names in commands fields specified one size */
 #define NVMF_NQN_FIELD_LEN      256
@@ -182,7 +181,7 @@ struct nvme_id_ctrl {
         char                    fr[8];
         __u8                    rab;
         __u8                    ieee[3];
-        __u8                    mic;
+        __u8                    cmic;
         __u8                    mdts;
         __le16                  cntlid;
         __le32                  ver;
@@ -202,7 +201,13 @@ struct nvme_id_ctrl {
         __u8                    apsta;
         __le16                  wctemp;
         __le16                  cctemp;
-        __u8                    rsvd270[50];
+        __le16                  mtfa;
+        __le32                  hmpre;
+        __le32                  hmmin;
+        __u8                    tnvmcap[16];
+        __u8                    unvmcap[16];
+        __le32                  rpmbs;
+        __u8                    rsvd316[4];
         __le16                  kas;
         __u8                    rsvd322[190];
         __u8                    sqes;
@@ -267,7 +272,7 @@ struct nvme_id_ns {
         __le16                  nabo;
         __le16                  nabspf;
         __u16                   rsvd46;
-        __le64                  nvmcap[2];
+        __u8                    nvmcap[16];
         __u8                    rsvd64[40];
         __u8                    nguid[16];
         __u8                    eui64[8];
@@ -277,6 +282,16 @@ struct nvme_id_ns {
 };
 
 enum {
+        NVME_ID_CNS_NS                  = 0x00,
+        NVME_ID_CNS_CTRL                = 0x01,
+        NVME_ID_CNS_NS_ACTIVE_LIST      = 0x02,
+        NVME_ID_CNS_NS_PRESENT_LIST     = 0x10,
+        NVME_ID_CNS_NS_PRESENT          = 0x11,
+        NVME_ID_CNS_CTRL_NS_LIST        = 0x12,
+        NVME_ID_CNS_CTRL_LIST           = 0x13,
+};
+
+enum {
         NVME_NS_FEAT_THIN       = 1 << 0,
         NVME_NS_FLBAS_LBA_MASK  = 0xf,
         NVME_NS_FLBAS_META_EXT  = 0x10,
@@ -556,8 +571,10 @@ enum nvme_admin_opcode {
         nvme_admin_set_features         = 0x09,
         nvme_admin_get_features         = 0x0a,
         nvme_admin_async_event          = 0x0c,
+        nvme_admin_ns_mgmt              = 0x0d,
         nvme_admin_activate_fw          = 0x10,
         nvme_admin_download_fw          = 0x11,
+        nvme_admin_ns_attach            = 0x15,
         nvme_admin_keep_alive           = 0x18,
         nvme_admin_format_nvm           = 0x80,
         nvme_admin_security_send        = 0x81,
@@ -583,6 +600,7 @@ enum {
         NVME_FEAT_WRITE_ATOMIC  = 0x0a,
         NVME_FEAT_ASYNC_EVENT   = 0x0b,
         NVME_FEAT_AUTO_PST      = 0x0c,
+        NVME_FEAT_HOST_MEM_BUF  = 0x0d,
         NVME_FEAT_KATO          = 0x0f,
         NVME_FEAT_SW_PROGRESS   = 0x80,
         NVME_FEAT_HOST_ID       = 0x81,
@@ -745,7 +763,7 @@ struct nvmf_common_command {
 struct nvmf_disc_rsp_page_entry {
         __u8            trtype;
         __u8            adrfam;
-        __u8            nqntype;
+        __u8            subtype;
         __u8            treq;
         __le16          portid;
         __le16          cntlid;
@@ -794,7 +812,7 @@ struct nvmf_connect_command {
 };
 
 struct nvmf_connect_data {
-        uuid_be         hostid;
+        __u8            hostid[16];
         __le16          cntlid;
         char            resv4[238];
         char            subsysnqn[NVMF_NQN_FIELD_LEN];
@@ -905,12 +923,23 @@ enum {
         NVME_SC_INVALID_VECTOR          = 0x108,
         NVME_SC_INVALID_LOG_PAGE        = 0x109,
         NVME_SC_INVALID_FORMAT          = 0x10a,
-        NVME_SC_FIRMWARE_NEEDS_RESET    = 0x10b,
+        NVME_SC_FW_NEEDS_CONV_RESET     = 0x10b,
         NVME_SC_INVALID_QUEUE           = 0x10c,
         NVME_SC_FEATURE_NOT_SAVEABLE    = 0x10d,
         NVME_SC_FEATURE_NOT_CHANGEABLE  = 0x10e,
         NVME_SC_FEATURE_NOT_PER_NS      = 0x10f,
-        NVME_SC_FW_NEEDS_RESET_SUBSYS   = 0x110,
+        NVME_SC_FW_NEEDS_SUBSYS_RESET   = 0x110,
+        NVME_SC_FW_NEEDS_RESET          = 0x111,
+        NVME_SC_FW_NEEDS_MAX_TIME       = 0x112,
+        NVME_SC_FW_ACIVATE_PROHIBITED   = 0x113,
+        NVME_SC_OVERLAPPING_RANGE       = 0x114,
+        NVME_SC_NS_INSUFFICENT_CAP      = 0x115,
+        NVME_SC_NS_ID_UNAVAILABLE       = 0x116,
+        NVME_SC_NS_ALREADY_ATTACHED     = 0x118,
+        NVME_SC_NS_IS_PRIVATE           = 0x119,
+        NVME_SC_NS_NOT_ATTACHED         = 0x11a,
+        NVME_SC_THIN_PROV_NOT_SUPP      = 0x11b,
+        NVME_SC_CTRL_LIST_INVALID       = 0x11c,
 
         /*
          * I/O Command Set Specific - NVM commands:
@@ -941,6 +970,7 @@ enum {
         NVME_SC_REFTAG_CHECK            = 0x284,
         NVME_SC_COMPARE_FAILED          = 0x285,
         NVME_SC_ACCESS_DENIED           = 0x286,
+        NVME_SC_UNWRITTEN_BLOCK         = 0x287,
 
         NVME_SC_DNR                     = 0x4000,
 };
@@ -960,6 +990,7 @@ struct nvme_completion {
         __le16  status;         /* did the command fail, and if so, why? */
 };
 
-#define NVME_VS(major, minor) (((major) << 16) | ((minor) << 8))
+#define NVME_VS(major, minor, tertiary) \
+        (((major) << 16) | ((minor) << 8) | (tertiary))
 
 #endif /* _LINUX_NVME_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 060d0ede88df..4741ecdb9817 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 f9ae903bbb84..8978a60371f4 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 99fbe6d55acb..f48d64b0e2fb 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 9adc7b21903d..f6673132431d 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 601258f6e621..32810f279f8e 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/linux/thread_info.h b/include/linux/thread_info.h
index 45f004e9cc59..2873baf5372a 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -14,17 +14,6 @@ struct timespec;
 struct compat_timespec;
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-struct thread_info {
-        unsigned long           flags;          /* low level flags */
-};
-
-#define INIT_THREAD_INFO(tsk)                   \
-{                                               \
-        .flags          = 0,                    \
-}
-#endif
-
-#ifdef CONFIG_THREAD_INFO_IN_TASK
 #define current_thread_info() ((struct thread_info *)current)
 #endif
 
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f2d072787947..8f998afc1384 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 bd19faad0d96..14b51d739c3b 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 515352c6280a..b0576cb2ab25 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 bc43c0fcae12..5413883ac47f 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 fb961a576abe..a74e2aa40ef4 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 e0cd318d5103..f83e78d071a3 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 a810dfcb83c2..e2dba93e374f 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 ebf75db08e06..73c6b008f1b7 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 f83b7f220a65..5b82d4d94834 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 ea53a87d880f..4948790d393d 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 0255613a54a4..308adc4154f4 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/target/target_core_base.h b/include/target/target_core_base.h
index fb8e3b6febdf..c2119008990a 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -177,6 +177,7 @@ enum tcm_sense_reason_table {
         TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED    = R(0x15),
         TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED  = R(0x16),
         TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED  = R(0x17),
+        TCM_COPY_TARGET_DEVICE_NOT_REACHABLE    = R(0x18),
 #undef R
 };
 
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 6965d0909554..cd2be1c8e9fb 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -75,6 +75,7 @@ header-y += bpf_perf_event.h
 header-y += bpf.h
 header-y += bpqether.h
 header-y += bsg.h
+header-y += bt-bmc.h
 header-y += btrfs.h
 header-y += can.h
 header-y += capability.h
diff --git a/include/uapi/linux/bt-bmc.h b/include/uapi/linux/bt-bmc.h
new file mode 100644
index 000000000000..d9ec766a63d0
--- /dev/null
+++ b/include/uapi/linux/bt-bmc.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_BT_BMC_H
+#define _UAPI_LINUX_BT_BMC_H
+
+#include <linux/ioctl.h>
+
+#define __BT_BMC_IOCTL_MAGIC    0xb1
+#define BT_BMC_IOCTL_SMS_ATN    _IO(__BT_BMC_IOCTL_MAGIC, 0x00)
+
+#endif /* _UAPI_LINUX_BT_BMC_H */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 099a4200732c..8e547231c1b7 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 262f0379d83a..5a78be518101 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/ipc/msgutil.c b/ipc/msgutil.c
index a521999de4f1..bf74eaa5c39f 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 c6e47e97b33f..0e292132efac 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/irq/manage.c b/kernel/irq/manage.c
index 0c5f1a5db654..9c4d30483264 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -721,6 +721,7 @@ int irq_set_parent(int irq, int parent_irq)
         irq_put_desc_unlock(desc, flags);
         return 0;
 }
+EXPORT_SYMBOL_GPL(irq_set_parent);
 #endif
 
 /*
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 8d44b3fea9d0..30e6d05aa5a9 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 1e7f5da648d9..6ccb08f57fcb 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 94732d1ab00a..42d4027f9e26 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7515,11 +7515,27 @@ 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 d941c97dfbc3..c242944f5cbd 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 4f7053579fe3..9453efe9b25a 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 1bf81ef91375..744fa611cae0 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 2d47980a1bc4..c611c47de884 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!
+                 * 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 = get_timer_base(timer->flags);
-                clk = base->clk;
+                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 33bc56cf60d7..b01e547d4d04 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -198,6 +198,7 @@ config FRAME_WARN
         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 0a1139644d32..144fe6b1a03e 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 60f77f1d470a..4d830e299989 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 94346b4d8984..0362da0b66c3 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 be0ee11fa0d9..86e3e0e74d20 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -187,7 +187,7 @@ config MEMORY_HOTPLUG
         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 849f459ad078..c7fe2f16503f 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/gup.c b/mm/gup.c
index 7aa113c2d373..ec4f82704b6f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -526,7 +526,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  * instead of __get_user_pages. __get_user_pages should be used only if
  * you need some special @gup_flags.
  */
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                 unsigned long start, unsigned long nr_pages,
                 unsigned int gup_flags, struct page **pages,
                 struct vm_area_struct **vmas, int *nonblocking)
@@ -631,7 +631,6 @@ next_page:
         } while (nr_pages);
         return i;
 }
-EXPORT_SYMBOL(__get_user_pages);
 
 bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags)
 {
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index a5e453cf05c4..e5355a5b423f 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 1d05cb9d363d..234676e31edd 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 ae052b5e3315..0f870ba43942 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1917,6 +1917,15 @@ retry:
                      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 962927309b6e..cad4b9125695 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/mprotect.c b/mm/mprotect.c
index bcdbe62f3e6d..11936526b08b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -25,7 +25,6 @@
 #include <linux/perf_event.h>
 #include <linux/pkeys.h>
 #include <linux/ksm.h>
-#include <linux/pkeys.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
diff --git a/mm/nommu.c b/mm/nommu.c
index db5fd1795298..8b8faaf2a9e9 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -109,7 +109,7 @@ unsigned int kobjsize(const void *objp)
         return PAGE_SIZE << compound_order(page);
 }
 
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                       unsigned long start, unsigned long nr_pages,
                       unsigned int foll_flags, struct page **pages,
                       struct vm_area_struct **vmas, int *nonblocking)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3f639739cab9..2dd614877de2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -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 090fb26b3a39..0b0550ca85b4 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 9653f2e2591a..bc05fdc3edce 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/util.c b/mm/util.c
index 952cbe7ad7b7..1a41553db866 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -230,8 +230,10 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /* Check if the vma is being used as a stack by this task */
-int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
+int vma_is_stack_for_current(struct vm_area_struct *vma)
 {
+        struct task_struct * __maybe_unused t = current;
+
         return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 744f926af442..76fda2268148 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 8de138d3306b..f2531ad66b68 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 08ce36147c4c..e034afbd1bb0 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 e0e1a88c3e58..d2905a855d1b 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 5f3bfc41aeb1..7c8d16086f0f 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 e2288421fe6b..1015d9c8d97d 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;
-
-        max_len = HCI_MAX_AD_LENGTH - ad_len - 2;
-        complete_len = strlen(hdev->dev_name);
-        short_len = strlen(hdev->short_name);
-
-        /* no space left for name */
-        if (max_len < 1)
-                return ad_len;
+        size_t complete_len;
 
-        /* no name set */
-        if (!complete_len)
+        /* no space left for name (+ NULL + type + len) */
+        if ((HCI_MAX_AD_LENGTH - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3)
                 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) {
+        /* use complete name if present and fits */
+        complete_len = strlen(hdev->dev_name);
+        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 6b06629245a8..dde77bd59f91 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 736038085feb..1fba2a03f8ae 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 c5fea9393946..2136e45f5277 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 @@ rollback:
                         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 4bc19a164ba5..820bac239738 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);
+
+        if (&lower->list == &dev->all_adj_list.lower)
+                return NULL;
+
+        *iter = &lower->list;
 
-        return lower ? lower->dev : NULL;
+        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 1a7b80f73376..ab193e5def07 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -246,15 +246,13 @@ ipv6:
         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 @@ ipv6:
                                                              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 989434f36f96..f61c0e02a413 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 5219a9e2127a..306b8f0e03c1 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 e92b759d906c..9a1a352fd1eb 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 66dff5e3d772..02acfff36028 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 5ee1d43f1310..4ebe2aa3e7d3 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 1effc986739e..9648c97e541f 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 cf50f7e2b012..030d1531e897 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 @@ next_proto:
         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 96e0efecefa6..d5cac99170b1 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 77c20a489218..ca97835bfec4 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 05d105832bdb..03e7f7310423 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 af4919792b6a..b8a2d63d1fb8 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 7cf7d6e380c2..205e2000d395 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 90a85c955872..ecbe5a7c2d6d 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 1cb67de106fe..80bc36b25de2 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 bd5e8d10893f..61b7be303eec 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 @@ get_sk:
                         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 7d96dc2d3d08..d123d68f4d1d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1322,7 +1322,7 @@ try_again:
                 *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 @@ csum_copy_err:
         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 f9333c963607..b2be1d9757ef 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -295,7 +295,7 @@ unflush:
 
         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 d8983e15f859..060dd9922018 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 @@ retry:
         }
         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;
+
+        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 = min_t(__u32,
-                                 ifp->prefered_lft,
-                                 idev->cnf.temp_prefered_lft + age -
-                                 idev->cnf.max_desync_factor);
+        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);
 
-        regen_advance = idev->cnf.regen_max_retry *
-                        idev->cnf.dad_transmits *
-                        NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
         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 @@ regen:
         }
 }
 
-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 @@ restart:
         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 00cf28ad4565..02761c9fe43e 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 e7bfd55899a3..1fcf61f1cbc3 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 6a66adba0c22..87784560dc46 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 @@ route_lookup:
         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 5330262ab673..636ec56f5f50 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 75c1fc54f188..14a3903f1c82 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 0e983b694ee8..66e2d9dfc43a 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 54404f08efcc..054a1d84fc5e 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 2160d5d009cb..3815e8505ed2 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 bdbc38e8bf29..947ed1ded026 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 @@ out:
 
 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 @@ restart:
                 }
         }
         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 9aa7c1c7a9ce..b2ef061e6836 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -427,7 +427,8 @@ try_again:
 
         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 42de4ccd159f..fce25afb652a 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 ea2ae6664cc8..ad3468c32b53 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 7663c28ba353..a4e0d59a40dd 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 6a73d1e4d186..fcd3254c5cf0 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 3afe361fd27c..8a4397cc1b08 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 1347fda6b76a..55aed5352494 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 3ddd927aaf30..bd72a862ddb7 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;
+
+        zero = (u8 *)aead_req + reqsize;
+        __aad = zero + GMAC_MIC_LEN;
+        memcpy(__aad, aad, GMAC_AAD_LEN);
 
-        memset(zero, 0, GMAC_MIC_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 d328204d73a8..32e6442c95be 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 c3f610bba3fe..eede5c6db8d5 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 6175db385ba7..a47bbc973f2d 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 b48c1e13e281..42ce9bd4426f 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 13290a70fa71..1308a56f2591 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 b41a6617d498..6898e7229285 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 5e509e547c2d..a3bd5fa8ad09 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:
-        case ncsi_dev_state_suspend_dcnt:
-        case ncsi_dev_state_suspend_dc:
-        case ncsi_dev_state_suspend_deselect:
                 ndp->pending_req_num = 1;
 
-                np = ndp->active_package;
-                nc = ndp->active_channel;
+                nca.type = NCSI_PKT_CMD_SP;
                 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;
+                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;
-                } 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;
+                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;
-                        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;
+                        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) {
-                        nd->state = ncsi_dev_state_functional;
-                        return;
-                }
+                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;
+
+                nca.type = NCSI_PKT_CMD_DP;
+                nca.package = np->id;
+                nca.channel = NCSI_RESERVED_CHANNEL;
+
+                nd->state = ncsi_dev_state_suspend_done;
+                ret = ncsi_xmit_cmd(&nca);
+                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 @@ error:
 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 fcb5d1df11e9..004af030ef1a 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -361,16 +361,9 @@ next_hook:
                 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 ba6a1d421222..df2f5a3901df 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 e0adb5959342..9fdb655f85bc 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 96964a0070e1..8f08d759844a 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 @@ err:
         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 b70d3ea1430e..24db22257586 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 e3b83c31da2e..517f08767a3c 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 a84cf3d66056..47beb3abcc9d 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 09473b415b95..baf694de3935 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 c6d5358482d1..fbc88009ca2e 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 e0aa7c1d0224..fc4977456c30 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 018eed7e1ff1..8668a5c18dc3 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 2fab0c65aa94..b89b688e9d01 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 89d53104c6b3..000e70377f85 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 11db0d619c00..d2238b204691 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 0e72bec1529f..56c7d27eefee 100644
--- a/net/rds/Makefile
+++ b/net/rds/Makefile
@@ -13,5 +13,5 @@ obj-$(CONFIG_RDS_TCP) += rds_tcp.o
 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 fd0bccb2f9f9..67ba67c058b1 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 4353a29f3b57..1ed18d8c9c9f 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 941b724d523b..862eea6b266c 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 a512b18c0088..f893d180da1c 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 667dc382df82..6b07fba5770b 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -207,8 +207,11 @@ out:
 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 2ee29a3375f6..2b2a7974e4bb 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -345,7 +345,8 @@ replay:
                         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 2a5c1896d18f..6cb0df859195 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 026e3bca4a94..8ec20a64a3f8 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 fb02c7033307..9fbb6feb8c27 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/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 02beb35f577f..3b95fe980fa2 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 753f774cb46f..aa1babbea385 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 5ffe34472ccd..855d53c64ab3 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 b36e16cdc945..1055164c6232 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 c3832cdf2278..50a739860d37 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 a04fe9be1c60..c1cfd92de17a 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 7ef14e2d2356..9d2f4c2b08ab 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 0082f4b01795..14b3f007826d 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 8edce22d1b93..5ea12afc7706 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 d17550198d06..6db6b21fdc6d 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 cf2511c33905..10af53d33cc2 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 edab34dce79b..95c16324760c 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 fa051b3d53ee..274c884c87fe 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 3303bb85593b..9c823a609e75 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 10ff73404e3a..1547b36a7b7b 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/security/keys/Kconfig b/security/keys/Kconfig
index f826e8739023..d942c7c2bc0a 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -41,7 +41,7 @@ config BIG_KEYS
         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 c0b3030b5634..835c1ab30d01 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 @@ error:
  */
 static int __init big_key_init(void)
 {
-        return register_key_type(&key_type_big_key);
-}
-
-/*
- * Initialize big_key crypto and RNG algorithms
- */
-static int __init big_key_crypto_init(void)
-{
-        int ret = -EINVAL;
+        struct crypto_skcipher *cipher;
+        struct crypto_rng *rng;
+        int ret;
 
-        /* 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 f0611a6368cd..b9f531c9e4fa 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/security/selinux/hooks.c b/security/selinux/hooks.c
index 085057936287..09fd6108e421 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3557,7 +3557,7 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
                 } else if (!vma->vm_file &&
                            ((vma->vm_start <= vma->vm_mm->start_stack &&
                              vma->vm_end >= vma->vm_mm->start_stack) ||
-                            vma_is_stack_for_task(vma, current))) {
+                            vma_is_stack_for_current(vma))) {
                         rc = current_has_perm(current, PROCESS__EXECSTACK);
                 } else if (vma->vm_file && vma->anon_vma) {
                         /*
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index dcc102813aef..37d9cfbc29f9 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 d17937b92331..7e3aa50b21f9 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 c3469f756ec2..c64d986009a9 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 b58e8c76346a..2f909dd8b7b8 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/usb/quirks-table.h b/sound/usb/quirks-table.h
index c60a776e815d..8a59d4782a0f 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/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 1188bc849ee3..a39629206864 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -194,6 +194,8 @@
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 
 #define X86_FEATURE_INTEL_PT    ( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 4490601a9235..e8a1f699058a 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/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 28510e72618a..2907b7b78654 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1346,21 +1346,19 @@ unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *w
 static int get_user_page_nowait(unsigned long start, int write,
                 struct page **page)
 {
-        int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET;
+        int flags = FOLL_NOWAIT | FOLL_HWPOISON;
 
         if (write)
                 flags |= FOLL_WRITE;
 
-        return __get_user_pages(current, current->mm, start, 1, flags, page,
-                        NULL, NULL);
+        return get_user_pages(start, 1, flags, page, NULL);
 }
 
 static inline int check_user_page_hwpoison(unsigned long addr)
 {
-        int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE;
+        int rc, flags = FOLL_HWPOISON | FOLL_WRITE;
 
-        rc = __get_user_pages(current, current->mm, addr, 1,
-                              flags, NULL, NULL, NULL);
+        rc = get_user_pages(addr, 1, flags, NULL, NULL);
         return rc == -EHWPOISON;
 }